3177 files changed, 116690 insertions, 48225 deletions

diff --git a/Documentation/ABI/testing/sysfs-class-rc-nuvoton b/Documentation/ABI/testing/sysfs-class-rc-nuvoton
new file mode 100644
index 000000000000..905bcdeedef2
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-rc-nuvoton
@@ -0,0 +1,15 @@
+What:		/sys/class/rc/rcN/wakeup_data
+Date:		Mar 2016
+KernelVersion:	4.6
+Contact:	Mauro Carvalho Chehab <m.chehab@samsung.com>
+Description:
+		Reading this file returns the stored CIR wakeup sequence.
+		It starts with a pulse, followed by a space, pulse etc.
+		All values are in microseconds.
+		The same format can be used to store a wakeup sequence
+		in the Nuvoton chip by writing to this file.
+
+		Note: Some systems reset the stored wakeup sequence to a
+		factory default on each boot. On such systems store the
+		wakeup sequence in a file and set it on boot using e.g.
+		a udev rule.
diff --git a/Documentation/DocBook/crypto-API.tmpl b/Documentation/DocBook/crypto-API.tmpl
index 07df23ea06e4..348619fcafb8 100644
--- a/Documentation/DocBook/crypto-API.tmpl
+++ b/Documentation/DocBook/crypto-API.tmpl
@@ -348,10 +348,7 @@
       <para>type:
        <itemizedlist>
         <listitem>
-         <para>blkcipher for synchronous block ciphers</para>
-        </listitem>
-        <listitem>
-         <para>ablkcipher for asynchronous block ciphers</para>
+         <para>skcipher for symmetric key ciphers</para>
         </listitem>
         <listitem>
          <para>cipher for single block ciphers that may be used with
@@ -485,6 +482,9 @@
       <para>CRYPTO_ALG_TYPE_RNG Random Number Generation</para>
      </listitem>
      <listitem>
+      <para>CRYPTO_ALG_TYPE_AKCIPHER Asymmetric cipher</para>
+     </listitem>
+     <listitem>
       <para>CRYPTO_ALG_TYPE_PCOMPRESS Enhanced version of
        CRYPTO_ALG_TYPE_COMPRESS allowing for segmented compression /
        decompression instead of performing the operation on one
@@ -597,7 +597,7 @@ kernel crypto API                                |   IPSEC Layer
       v                   v
 +-----------+       +-----------+
 |           |       |           |
-| ablkcipher|       |   ahash   |
+|  skcipher |       |   ahash   |
 |   (ctr)   | ---+  |  (ghash)  |
 +-----------+    |  +-----------+
                  |
@@ -658,7 +658,7 @@ kernel crypto API                                |   IPSEC Layer
 
       <listitem>
        <para>
-        The GCM AEAD cipher type implementation now invokes the ABLKCIPHER API
+        The GCM AEAD cipher type implementation now invokes the SKCIPHER API
         with the instantiated CTR(AES) cipher handle.
        </para>
 
@@ -669,7 +669,7 @@ kernel crypto API                                |   IPSEC Layer
        </para>
 
        <para>
-        That means that the ABLKCIPHER implementation of CTR(AES) only
+        That means that the SKCIPHER implementation of CTR(AES) only
         implements the CTR block chaining mode. After performing the block
         chaining operation, the CIPHER implementation of AES is invoked.
        </para>
@@ -677,7 +677,7 @@ kernel crypto API                                |   IPSEC Layer
 
       <listitem>
        <para>
-        The ABLKCIPHER of CTR(AES) now invokes the CIPHER API with the AES
+        The SKCIPHER of CTR(AES) now invokes the CIPHER API with the AES
         cipher handle to encrypt one block.
        </para>
       </listitem>
@@ -706,7 +706,7 @@ kernel crypto API                                |   IPSEC Layer
      <para>
       For example, CBC(AES) is implemented with cbc.c, and aes-generic.c. The
       ASCII art picture above applies as well with the difference that only
-      step (4) is used and the ABLKCIPHER block chaining mode is CBC.
+      step (4) is used and the SKCIPHER block chaining mode is CBC.
      </para>
     </sect2>
 
@@ -904,15 +904,14 @@ kernel crypto API            |       Caller
     </sect2>
    </sect1>
 
-   <sect1><title>Multi-Block Ciphers [BLKCIPHER] [ABLKCIPHER]</title>
+   <sect1><title>Multi-Block Ciphers</title>
     <para>
      Example of transformations: cbc(aes), ecb(arc4), ...
     </para>
 
     <para>
      This section describes the multi-block cipher transformation
-     implementations for both synchronous [BLKCIPHER] and
-     asynchronous [ABLKCIPHER] case. The multi-block ciphers are
+     implementations. The multi-block ciphers are
      used for transformations which operate on scatterlists of
      data supplied to the transformation functions. They output
      the result into a scatterlist of data as well.
@@ -921,16 +920,15 @@ kernel crypto API            |       Caller
     <sect2><title>Registration Specifics</title>
 
      <para>
-      The registration of [BLKCIPHER] or [ABLKCIPHER] algorithms
+      The registration of multi-block cipher algorithms
       is one of the most standard procedures throughout the crypto API.
      </para>
 
      <para>
       Note, if a cipher implementation requires a proper alignment
       of data, the caller should use the functions of
-      crypto_blkcipher_alignmask() or crypto_ablkcipher_alignmask()
-      respectively to identify a memory alignment mask. The kernel
-      crypto API is able to process requests that are unaligned.
+      crypto_skcipher_alignmask() to identify a memory alignment mask.
+      The kernel crypto API is able to process requests that are unaligned.
       This implies, however, additional overhead as the kernel
       crypto API needs to perform the realignment of the data which
       may imply moving of data.
@@ -945,14 +943,13 @@ kernel crypto API            |       Caller
 
      <para>
       Please refer to the single block cipher description for schematics
-      of the block cipher usage. The usage patterns are exactly the same
-      for [ABLKCIPHER] and [BLKCIPHER] as they are for plain [CIPHER].
+      of the block cipher usage.
      </para>
     </sect2>
 
     <sect2><title>Specifics Of Asynchronous Multi-Block Cipher</title>
      <para>
-      There are a couple of specifics to the [ABLKCIPHER] interface.
+      There are a couple of specifics to the asynchronous interface.
      </para>
 
      <para>
@@ -1692,7 +1689,28 @@ read(opfd, out, outlen);
 !Finclude/linux/crypto.h cipher_alg
 !Finclude/crypto/rng.h rng_alg
    </sect1>
-   <sect1><title>Asynchronous Block Cipher API</title>
+   <sect1><title>Symmetric Key Cipher API</title>
+!Pinclude/crypto/skcipher.h Symmetric Key Cipher API
+!Finclude/crypto/skcipher.h crypto_alloc_skcipher
+!Finclude/crypto/skcipher.h crypto_free_skcipher
+!Finclude/crypto/skcipher.h crypto_has_skcipher
+!Finclude/crypto/skcipher.h crypto_skcipher_ivsize
+!Finclude/crypto/skcipher.h crypto_skcipher_blocksize
+!Finclude/crypto/skcipher.h crypto_skcipher_setkey
+!Finclude/crypto/skcipher.h crypto_skcipher_reqtfm
+!Finclude/crypto/skcipher.h crypto_skcipher_encrypt
+!Finclude/crypto/skcipher.h crypto_skcipher_decrypt
+   </sect1>
+   <sect1><title>Symmetric Key Cipher Request Handle</title>
+!Pinclude/crypto/skcipher.h Symmetric Key Cipher Request Handle
+!Finclude/crypto/skcipher.h crypto_skcipher_reqsize
+!Finclude/crypto/skcipher.h skcipher_request_set_tfm
+!Finclude/crypto/skcipher.h skcipher_request_alloc
+!Finclude/crypto/skcipher.h skcipher_request_free
+!Finclude/crypto/skcipher.h skcipher_request_set_callback
+!Finclude/crypto/skcipher.h skcipher_request_set_crypt
+   </sect1>
+   <sect1><title>Asynchronous Block Cipher API - Deprecated</title>
 !Pinclude/linux/crypto.h Asynchronous Block Cipher API
 !Finclude/linux/crypto.h crypto_alloc_ablkcipher
 !Finclude/linux/crypto.h crypto_free_ablkcipher
@@ -1704,7 +1722,7 @@ read(opfd, out, outlen);
 !Finclude/linux/crypto.h crypto_ablkcipher_encrypt
 !Finclude/linux/crypto.h crypto_ablkcipher_decrypt
    </sect1>
-   <sect1><title>Asynchronous Cipher Request Handle</title>
+   <sect1><title>Asynchronous Cipher Request Handle - Deprecated</title>
 !Pinclude/linux/crypto.h Asynchronous Cipher Request Handle
 !Finclude/linux/crypto.h crypto_ablkcipher_reqsize
 !Finclude/linux/crypto.h ablkcipher_request_set_tfm
@@ -1733,10 +1751,9 @@ read(opfd, out, outlen);
 !Finclude/crypto/aead.h aead_request_free
 !Finclude/crypto/aead.h aead_request_set_callback
 !Finclude/crypto/aead.h aead_request_set_crypt
-!Finclude/crypto/aead.h aead_request_set_assoc
 !Finclude/crypto/aead.h aead_request_set_ad
    </sect1>
-   <sect1><title>Synchronous Block Cipher API</title>
+   <sect1><title>Synchronous Block Cipher API - Deprecated</title>
 !Pinclude/linux/crypto.h Synchronous Block Cipher API
 !Finclude/linux/crypto.h crypto_alloc_blkcipher
 !Finclude/linux/crypto.h crypto_free_blkcipher
@@ -1762,19 +1779,6 @@ read(opfd, out, outlen);
 !Finclude/linux/crypto.h crypto_cipher_encrypt_one
 !Finclude/linux/crypto.h crypto_cipher_decrypt_one
    </sect1>
-   <sect1><title>Synchronous Message Digest API</title>
-!Pinclude/linux/crypto.h Synchronous Message Digest API
-!Finclude/linux/crypto.h crypto_alloc_hash
-!Finclude/linux/crypto.h crypto_free_hash
-!Finclude/linux/crypto.h crypto_has_hash
-!Finclude/linux/crypto.h crypto_hash_blocksize
-!Finclude/linux/crypto.h crypto_hash_digestsize
-!Finclude/linux/crypto.h crypto_hash_init
-!Finclude/linux/crypto.h crypto_hash_update
-!Finclude/linux/crypto.h crypto_hash_final
-!Finclude/linux/crypto.h crypto_hash_digest
-!Finclude/linux/crypto.h crypto_hash_setkey
-   </sect1>
    <sect1><title>Message Digest Algorithm Definitions</title>
 !Pinclude/crypto/hash.h Message Digest Algorithm Definitions
 !Finclude/crypto/hash.h hash_alg_common
@@ -1825,15 +1829,36 @@ read(opfd, out, outlen);
 !Finclude/crypto/rng.h crypto_alloc_rng
 !Finclude/crypto/rng.h crypto_rng_alg
 !Finclude/crypto/rng.h crypto_free_rng
+!Finclude/crypto/rng.h crypto_rng_generate
 !Finclude/crypto/rng.h crypto_rng_get_bytes
 !Finclude/crypto/rng.h crypto_rng_reset
 !Finclude/crypto/rng.h crypto_rng_seedsize
 !Cinclude/crypto/rng.h
    </sect1>
+   <sect1><title>Asymmetric Cipher API</title>
+!Pinclude/crypto/akcipher.h Generic Public Key API
+!Finclude/crypto/akcipher.h akcipher_alg
+!Finclude/crypto/akcipher.h akcipher_request
+!Finclude/crypto/akcipher.h crypto_alloc_akcipher
+!Finclude/crypto/akcipher.h crypto_free_akcipher
+!Finclude/crypto/akcipher.h crypto_akcipher_set_pub_key
+!Finclude/crypto/akcipher.h crypto_akcipher_set_priv_key
+   </sect1>
+   <sect1><title>Asymmetric Cipher Request Handle</title>
+!Finclude/crypto/akcipher.h akcipher_request_alloc
+!Finclude/crypto/akcipher.h akcipher_request_free
+!Finclude/crypto/akcipher.h akcipher_request_set_callback
+!Finclude/crypto/akcipher.h akcipher_request_set_crypt
+!Finclude/crypto/akcipher.h crypto_akcipher_maxsize
+!Finclude/crypto/akcipher.h crypto_akcipher_encrypt
+!Finclude/crypto/akcipher.h crypto_akcipher_decrypt
+!Finclude/crypto/akcipher.h crypto_akcipher_sign
+!Finclude/crypto/akcipher.h crypto_akcipher_verify
+   </sect1>
   </chapter>
 
   <chapter id="Code"><title>Code Examples</title>
-   <sect1><title>Code Example For Asynchronous Block Cipher Operation</title>
+   <sect1><title>Code Example For Symmetric Key Cipher Operation</title>
     <programlisting>
 
 struct tcrypt_result {
@@ -1842,15 +1867,15 @@ struct tcrypt_result {
 };
 
 /* tie all data structures together */
-struct ablkcipher_def {
+struct skcipher_def {
 	struct scatterlist sg;
-	struct crypto_ablkcipher *tfm;
-	struct ablkcipher_request *req;
+	struct crypto_skcipher *tfm;
+	struct skcipher_request *req;
 	struct tcrypt_result result;
 };
 
 /* Callback function */
-static void test_ablkcipher_cb(struct crypto_async_request *req, int error)
+static void test_skcipher_cb(struct crypto_async_request *req, int error)
 {
 	struct tcrypt_result *result = req-&gt;data;
 
@@ -1862,15 +1887,15 @@ static void test_ablkcipher_cb(struct crypto_async_request *req, int error)
 }
 
 /* Perform cipher operation */
-static unsigned int test_ablkcipher_encdec(struct ablkcipher_def *ablk,
-					   int enc)
+static unsigned int test_skcipher_encdec(struct skcipher_def *sk,
+					 int enc)
 {
 	int rc = 0;
 
 	if (enc)
-		rc = crypto_ablkcipher_encrypt(ablk-&gt;req);
+		rc = crypto_skcipher_encrypt(sk-&gt;req);
 	else
-		rc = crypto_ablkcipher_decrypt(ablk-&gt;req);
+		rc = crypto_skcipher_decrypt(sk-&gt;req);
 
 	switch (rc) {
 	case 0:
@@ -1878,52 +1903,52 @@ static unsigned int test_ablkcipher_encdec(struct ablkcipher_def *ablk,
 	case -EINPROGRESS:
 	case -EBUSY:
 		rc = wait_for_completion_interruptible(
-			&amp;ablk-&gt;result.completion);
-		if (!rc &amp;&amp; !ablk-&gt;result.err) {
-			reinit_completion(&amp;ablk-&gt;result.completion);
+			&amp;sk-&gt;result.completion);
+		if (!rc &amp;&amp; !sk-&gt;result.err) {
+			reinit_completion(&amp;sk-&gt;result.completion);
 			break;
 		}
 	default:
-		pr_info("ablkcipher encrypt returned with %d result %d\n",
-		       rc, ablk-&gt;result.err);
+		pr_info("skcipher encrypt returned with %d result %d\n",
+			rc, sk-&gt;result.err);
 		break;
 	}
-	init_completion(&amp;ablk-&gt;result.completion);
+	init_completion(&amp;sk-&gt;result.completion);
 
 	return rc;
 }
 
 /* Initialize and trigger cipher operation */
-static int test_ablkcipher(void)
+static int test_skcipher(void)
 {
-	struct ablkcipher_def ablk;
-	struct crypto_ablkcipher *ablkcipher = NULL;
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_def sk;
+	struct crypto_skcipher *skcipher = NULL;
+	struct skcipher_request *req = NULL;
 	char *scratchpad = NULL;
 	char *ivdata = NULL;
 	unsigned char key[32];
 	int ret = -EFAULT;
 
-	ablkcipher = crypto_alloc_ablkcipher("cbc-aes-aesni", 0, 0);
-	if (IS_ERR(ablkcipher)) {
-		pr_info("could not allocate ablkcipher handle\n");
-		return PTR_ERR(ablkcipher);
+	skcipher = crypto_alloc_skcipher("cbc-aes-aesni", 0, 0);
+	if (IS_ERR(skcipher)) {
+		pr_info("could not allocate skcipher handle\n");
+		return PTR_ERR(skcipher);
 	}
 
-	req = ablkcipher_request_alloc(ablkcipher, GFP_KERNEL);
+	req = skcipher_request_alloc(skcipher, GFP_KERNEL);
 	if (IS_ERR(req)) {
 		pr_info("could not allocate request queue\n");
 		ret = PTR_ERR(req);
 		goto out;
 	}
 
-	ablkcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
-					test_ablkcipher_cb,
-					&amp;ablk.result);
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				      test_skcipher_cb,
+				      &amp;sk.result);
 
 	/* AES 256 with random key */
 	get_random_bytes(&amp;key, 32);
-	if (crypto_ablkcipher_setkey(ablkcipher, key, 32)) {
+	if (crypto_skcipher_setkey(skcipher, key, 32)) {
 		pr_info("key could not be set\n");
 		ret = -EAGAIN;
 		goto out;
@@ -1945,26 +1970,26 @@ static int test_ablkcipher(void)
 	}
 	get_random_bytes(scratchpad, 16);
 
-	ablk.tfm = ablkcipher;
-	ablk.req = req;
+	sk.tfm = skcipher;
+	sk.req = req;
 
 	/* We encrypt one block */
-	sg_init_one(&amp;ablk.sg, scratchpad, 16);
-	ablkcipher_request_set_crypt(req, &amp;ablk.sg, &amp;ablk.sg, 16, ivdata);
-	init_completion(&amp;ablk.result.completion);
+	sg_init_one(&amp;sk.sg, scratchpad, 16);
+	skcipher_request_set_crypt(req, &amp;sk.sg, &amp;sk.sg, 16, ivdata);
+	init_completion(&amp;sk.result.completion);
 
 	/* encrypt data */
-	ret = test_ablkcipher_encdec(&amp;ablk, 1);
+	ret = test_skcipher_encdec(&amp;sk, 1);
 	if (ret)
 		goto out;
 
 	pr_info("Encryption triggered successfully\n");
 
 out:
-	if (ablkcipher)
-		crypto_free_ablkcipher(ablkcipher);
+	if (skcipher)
+		crypto_free_skcipher(skcipher);
 	if (req)
-		ablkcipher_request_free(req);
+		skcipher_request_free(req);
 	if (ivdata)
 		kfree(ivdata);
 	if (scratchpad)
@@ -1974,77 +1999,6 @@ out:
     </programlisting>
    </sect1>
 
-   <sect1><title>Code Example For Synchronous Block Cipher Operation</title>
-    <programlisting>
-
-static int test_blkcipher(void)
-{
-	struct crypto_blkcipher *blkcipher = NULL;
-	char *cipher = "cbc(aes)";
-	// AES 128
-	charkey =
-"\x12\x34\x56\x78\x90\xab\xcd\xef\x12\x34\x56\x78\x90\xab\xcd\xef";
-	chariv =
-"\x12\x34\x56\x78\x90\xab\xcd\xef\x12\x34\x56\x78\x90\xab\xcd\xef";
-	unsigned int ivsize = 0;
-	char *scratchpad = NULL; // holds plaintext and ciphertext
-	struct scatterlist sg;
-	struct blkcipher_desc desc;
-	int ret = -EFAULT;
-
-	blkcipher = crypto_alloc_blkcipher(cipher, 0, 0);
-	if (IS_ERR(blkcipher)) {
-		printk("could not allocate blkcipher handle for %s\n", cipher);
-		return -PTR_ERR(blkcipher);
-	}
-
-	if (crypto_blkcipher_setkey(blkcipher, key, strlen(key))) {
-		printk("key could not be set\n");
-		ret = -EAGAIN;
-		goto out;
-	}
-
-	ivsize = crypto_blkcipher_ivsize(blkcipher);
-	if (ivsize) {
-		if (ivsize != strlen(iv))
-			printk("IV length differs from expected length\n");
-		crypto_blkcipher_set_iv(blkcipher, iv, ivsize);
-	}
-
-	scratchpad = kmalloc(crypto_blkcipher_blocksize(blkcipher), GFP_KERNEL);
-	if (!scratchpad) {
-		printk("could not allocate scratchpad for %s\n", cipher);
-		goto out;
-	}
-	/* get some random data that we want to encrypt */
-	get_random_bytes(scratchpad, crypto_blkcipher_blocksize(blkcipher));
-
-	desc.flags = 0;
-	desc.tfm = blkcipher;
-	sg_init_one(&amp;sg, scratchpad, crypto_blkcipher_blocksize(blkcipher));
-
-	/* encrypt data in place */
-	crypto_blkcipher_encrypt(&amp;desc, &amp;sg, &amp;sg,
-				 crypto_blkcipher_blocksize(blkcipher));
-
-	/* decrypt data in place
-	 * crypto_blkcipher_decrypt(&amp;desc, &amp;sg, &amp;sg,
-	 */			 crypto_blkcipher_blocksize(blkcipher));
-
-
-	printk("Cipher operation completed\n");
-	return 0;
-
-out:
-	if (blkcipher)
-		crypto_free_blkcipher(blkcipher);
-	if (scratchpad)
-		kzfree(scratchpad);
-	return ret;
-}
-    </programlisting>
-   </sect1>
-
    <sect1><title>Code Example For Use of Operational State Memory With SHASH</title>
     <programlisting>
 
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl
index cdd8b24db68d..cc303a2f641c 100644
--- a/Documentation/DocBook/device-drivers.tmpl
+++ b/Documentation/DocBook/device-drivers.tmpl
@@ -229,6 +229,7 @@ X!Isound/sound_firmware.c
 !Iinclude/media/v4l2-dv-timings.h
 !Iinclude/media/v4l2-event.h
 !Iinclude/media/v4l2-flash-led-class.h
+!Iinclude/media/v4l2-mc.h
 !Iinclude/media/v4l2-mediabus.h
 !Iinclude/media/v4l2-mem2mem.h
 !Iinclude/media/v4l2-of.h
diff --git a/Documentation/DocBook/media/v4l/controls.xml b/Documentation/DocBook/media/v4l/controls.xml
index f13a429093f1..361040e6b0f4 100644
--- a/Documentation/DocBook/media/v4l/controls.xml
+++ b/Documentation/DocBook/media/v4l/controls.xml
@@ -2330,6 +2330,14 @@ vertical search range for motion estimation module in video encoder.</entry>
 	      </row>
 
 	      <row><entry></entry></row>
+	      <row id="v4l2-mpeg-video-force-key-frame">
+		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_FORCE_KEY_FRAME</constant>&nbsp;</entry>
+		<entry>button</entry>
+	      </row><row><entry spanname="descr">Force a key frame for the next queued buffer. Applicable to encoders.
+This is a general, codec-agnostic keyframe control.</entry>
+	      </row>
+
+	      <row><entry></entry></row>
 	      <row>
 		<entry spanname="id"><constant>V4L2_CID_MPEG_VIDEO_H264_CPB_SIZE</constant>&nbsp;</entry>
 		<entry>integer</entry>
@@ -5070,6 +5078,46 @@ interface and may change in the future.</para>
 	    </entry>
 	  </row>
 	  <row>
+	    <entry spanname="id"><constant>V4L2_CID_DV_TX_IT_CONTENT_TYPE</constant></entry>
+	    <entry id="v4l2-dv-content-type">enum v4l2_dv_it_content_type</entry>
+	  </row>
+	  <row><entry spanname="descr">Configures the IT Content Type
+	    of the transmitted video. This information is sent over HDMI and DisplayPort connectors
+	    as part of the AVI InfoFrame. The term 'IT Content' is used for content that originates
+	    from a computer as opposed to content from a TV broadcast or an analog source. The
+	    enum&nbsp;v4l2_dv_it_content_type defines the possible content types:</entry>
+	  </row>
+	  <row>
+	    <entrytbl spanname="descr" cols="2">
+	      <tbody valign="top">
+	        <row>
+	          <entry><constant>V4L2_DV_IT_CONTENT_TYPE_GRAPHICS</constant>&nbsp;</entry>
+		  <entry>Graphics content. Pixel data should be passed unfiltered and without
+		  analog reconstruction.</entry>
+		</row>
+	        <row>
+	          <entry><constant>V4L2_DV_IT_CONTENT_TYPE_PHOTO</constant>&nbsp;</entry>
+		  <entry>Photo content. The content is derived from digital still pictures.
+		  The content should be passed through with minimal scaling and picture
+		  enhancements.</entry>
+		</row>
+	        <row>
+	          <entry><constant>V4L2_DV_IT_CONTENT_TYPE_CINEMA</constant>&nbsp;</entry>
+		  <entry>Cinema content.</entry>
+		</row>
+	        <row>
+	          <entry><constant>V4L2_DV_IT_CONTENT_TYPE_GAME</constant>&nbsp;</entry>
+		  <entry>Game content. Audio and video latency should be minimized.</entry>
+		</row>
+	        <row>
+	          <entry><constant>V4L2_DV_IT_CONTENT_TYPE_NO_ITC</constant>&nbsp;</entry>
+		  <entry>No IT Content information is available and the ITC bit in the AVI
+		  InfoFrame is set to 0.</entry>
+		</row>
+	      </tbody>
+	    </entrytbl>
+	  </row>
+	  <row>
 	    <entry spanname="id"><constant>V4L2_CID_DV_RX_POWER_PRESENT</constant></entry>
 	    <entry>bitmask</entry>
 	  </row>
@@ -5098,6 +5146,16 @@ interface and may change in the future.</para>
 	    This control is applicable to VGA, DVI-A/D, HDMI and DisplayPort connectors.
 	    </entry>
 	  </row>
+	  <row>
+	    <entry spanname="id"><constant>V4L2_CID_DV_RX_IT_CONTENT_TYPE</constant></entry>
+	    <entry>enum v4l2_dv_it_content_type</entry>
+	  </row>
+	  <row><entry spanname="descr">Reads the IT Content Type
+	    of the received video. This information is sent over HDMI and DisplayPort connectors
+	    as part of the AVI InfoFrame. The term 'IT Content' is used for content that originates
+	    from a computer as opposed to content from a TV broadcast or an analog source. See
+	    <constant>V4L2_CID_DV_TX_IT_CONTENT_TYPE</constant> for the available content types.</entry>
+	  </row>
 	  <row><entry></entry></row>
 	</tbody>
       </tgroup>
diff --git a/Documentation/DocBook/media/v4l/media-ioc-g-topology.xml b/Documentation/DocBook/media/v4l/media-ioc-g-topology.xml
index 63152ab9efba..e0d49fa329f0 100644
--- a/Documentation/DocBook/media/v4l/media-ioc-g-topology.xml
+++ b/Documentation/DocBook/media/v4l/media-ioc-g-topology.xml
@@ -48,9 +48,6 @@
 
   <refsect1>
     <title>Description</title>
-
-    <para><emphasis role="bold">NOTE:</emphasis> This new ioctl is programmed to be added on Kernel 4.6. Its definition/arguments may change until its final version.</para>
-
     <para>The typical usage of this ioctl is to call it twice.
     On the first call, the structure defined at &media-v2-topology; should
     be zeroed. At return, if no errors happen, this ioctl will return the
diff --git a/Documentation/DocBook/media/v4l/media-types.xml b/Documentation/DocBook/media/v4l/media-types.xml
index 1af384250910..5e3f20fdcf17 100644
--- a/Documentation/DocBook/media/v4l/media-types.xml
+++ b/Documentation/DocBook/media/v4l/media-types.xml
@@ -57,10 +57,6 @@
 	    <entry>Connector for a RGB composite signal.</entry>
 	  </row>
 	  <row>
-	    <entry><constant>MEDIA_ENT_F_CONN_TEST</constant></entry>
-	    <entry>Connector for a test generator.</entry>
-	  </row>
-	  <row>
 	    <entry><constant>MEDIA_ENT_F_CAM_SENSOR</constant></entry>
 	    <entry>Camera video sensor entity.</entry>
 	  </row>
@@ -84,7 +80,46 @@
 	  </row>
 	  <row>
 	    <entry><constant>MEDIA_ENT_F_TUNER</constant></entry>
-	    <entry>Digital TV, analog TV, radio and/or software radio tuner.</entry>
+	    <entry>Digital TV, analog TV, radio and/or software radio tuner,
+		   with consists on a PLL tuning stage that converts radio
+		   frequency (RF) signal into an Intermediate Frequency (IF).
+		   Modern tuners have internally IF-PLL decoders for audio
+		   and video, but older models have those stages implemented
+		   on separate entities.
+	    </entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_IF_VID_DECODER</constant></entry>
+	    <entry>IF-PLL video decoder. It receives the IF from a PLL
+		   and decodes the analog TV video signal. This is commonly
+		   found on some very old analog tuners, like Philips MK3
+		   designs. They all contain a tda9887 (or some software
+		   compatible similar chip, like tda9885). Those devices
+		   use a different I2C address than the tuner PLL.
+	    </entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_IF_AUD_DECODER</constant></entry>
+	    <entry>IF-PLL sound decoder. It receives the IF from a PLL
+		   and decodes the analog TV audio signal. This is commonly
+		   found on some very old analog hardware, like Micronas
+		   msp3400, Philips tda9840, tda985x, etc. Those devices
+		   use a different I2C address than the tuner PLL and
+		   should be controlled together with the IF-PLL video
+		   decoder.
+	    </entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_AUDIO_CAPTURE</constant></entry>
+	    <entry>Audio Capture Function Entity.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_AUDIO_PLAYBACK</constant></entry>
+	    <entry>Audio Playback Function Entity.</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_ENT_F_AUDIO_MIXER</constant></entry>
+	    <entry>Audio Mixer Function Entity.</entry>
 	  </row>
 	</tbody>
       </tgroup>
@@ -166,6 +201,46 @@
 	    <entry>Device node interface for Software Defined Radio (V4L)</entry>
 	    <entry>typically, /dev/swradio?</entry>
 	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_ALSA_PCM_CAPTURE</constant></entry>
+	    <entry>Device node interface for ALSA PCM Capture</entry>
+	    <entry>typically, /dev/snd/pcmC?D?c</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_ALSA_PCM_PLAYBACK</constant></entry>
+	    <entry>Device node interface for ALSA PCM Playback</entry>
+	    <entry>typically, /dev/snd/pcmC?D?p</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_ALSA_CONTROL</constant></entry>
+	    <entry>Device node interface for ALSA Control</entry>
+	    <entry>typically, /dev/snd/controlC?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_ALSA_COMPRESS</constant></entry>
+	    <entry>Device node interface for ALSA Compress</entry>
+	    <entry>typically, /dev/snd/compr?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_ALSA_RAWMIDI</constant></entry>
+	    <entry>Device node interface for ALSA Raw MIDI</entry>
+	    <entry>typically, /dev/snd/midi?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_ALSA_HWDEP</constant></entry>
+	    <entry>Device node interface for ALSA Hardware Dependent</entry>
+	    <entry>typically, /dev/snd/hwC?D?</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_ALSA_SEQUENCER</constant></entry>
+	    <entry>Device node interface for ALSA Sequencer</entry>
+	    <entry>typically, /dev/snd/seq</entry>
+	  </row>
+	  <row>
+	    <entry><constant>MEDIA_INTF_T_ALSA_TIMER</constant></entry>
+	    <entry>Device node interface for ALSA Timer</entry>
+	    <entry>typically, /dev/snd/timer</entry>
+	  </row>
 	</tbody>
       </tgroup>
     </table>
diff --git a/Documentation/DocBook/media/v4l/pixfmt-y12i.xml b/Documentation/DocBook/media/v4l/pixfmt-y12i.xml
new file mode 100644
index 000000000000..4a2d1e5f67e4
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/pixfmt-y12i.xml
@@ -0,0 +1,49 @@
+<refentry id="V4L2-PIX-FMT-Y12I">
+  <refmeta>
+    <refentrytitle>V4L2_PIX_FMT_Y12I ('Y12I')</refentrytitle>
+    &manvol;
+  </refmeta>
+  <refnamediv>
+    <refname><constant>V4L2_PIX_FMT_Y12I</constant></refname>
+    <refpurpose>Interleaved grey-scale image, e.g. from a stereo-pair</refpurpose>
+  </refnamediv>
+  <refsect1>
+    <title>Description</title>
+
+    <para>This is a grey-scale image with a depth of 12 bits per pixel, but with
+pixels from 2 sources interleaved and bit-packed. Each pixel is stored in a
+24-bit word in the little-endian order. On a little-endian machine these pixels
+can be deinterlaced using</para>
+
+<para>
+<programlisting>
+__u8 *buf;
+left0 = 0xfff &amp; *(__u16 *)buf;
+right0 = *(__u16 *)(buf + 1) >> 4;
+</programlisting>
+</para>
+
+    <example>
+      <title><constant>V4L2_PIX_FMT_Y12I</constant> 2 pixel data stream taking 3 bytes</title>
+
+      <formalpara>
+	<title>Bit-packed representation</title>
+	<para>pixels cross the byte boundary and have a ratio of 3 bytes for each
+          interleaved pixel.
+	  <informaltable frame="all">
+	    <tgroup cols="3" align="center">
+	      <colspec align="left" colwidth="2*" />
+	      <tbody valign="top">
+		<row>
+		  <entry>Y'<subscript>0left[7:0]</subscript></entry>
+		  <entry>Y'<subscript>0right[3:0]</subscript>Y'<subscript>0left[11:8]</subscript></entry>
+		  <entry>Y'<subscript>0right[11:4]</subscript></entry>
+		</row>
+	      </tbody>
+	    </tgroup>
+	  </informaltable>
+	</para>
+      </formalpara>
+    </example>
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/media/v4l/pixfmt-y8i.xml b/Documentation/DocBook/media/v4l/pixfmt-y8i.xml
new file mode 100644
index 000000000000..99f389d4c6c8
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/pixfmt-y8i.xml
@@ -0,0 +1,80 @@
+<refentry id="V4L2-PIX-FMT-Y8I">
+  <refmeta>
+    <refentrytitle>V4L2_PIX_FMT_Y8I ('Y8I ')</refentrytitle>
+    &manvol;
+  </refmeta>
+  <refnamediv>
+    <refname><constant>V4L2_PIX_FMT_Y8I</constant></refname>
+    <refpurpose>Interleaved grey-scale image, e.g. from a stereo-pair</refpurpose>
+  </refnamediv>
+  <refsect1>
+    <title>Description</title>
+
+    <para>This is a grey-scale image with a depth of 8 bits per pixel, but with
+pixels from 2 sources interleaved. Each pixel is stored in a 16-bit word. E.g.
+the R200 RealSense camera stores pixel from the left sensor in lower and from
+the right sensor in the higher 8 bits.</para>
+
+    <example>
+      <title><constant>V4L2_PIX_FMT_Y8I</constant> 4 &times; 4
+pixel image</title>
+
+      <formalpara>
+	<title>Byte Order.</title>
+	<para>Each cell is one byte.
+	  <informaltable frame="none">
+	    <tgroup cols="9" align="center">
+	      <colspec align="left" colwidth="2*" />
+	      <tbody valign="top">
+		<row>
+		  <entry>start&nbsp;+&nbsp;0:</entry>
+		  <entry>Y'<subscript>00left</subscript></entry>
+		  <entry>Y'<subscript>00right</subscript></entry>
+		  <entry>Y'<subscript>01left</subscript></entry>
+		  <entry>Y'<subscript>01right</subscript></entry>
+		  <entry>Y'<subscript>02left</subscript></entry>
+		  <entry>Y'<subscript>02right</subscript></entry>
+		  <entry>Y'<subscript>03left</subscript></entry>
+		  <entry>Y'<subscript>03right</subscript></entry>
+		</row>
+		<row>
+		  <entry>start&nbsp;+&nbsp;8:</entry>
+		  <entry>Y'<subscript>10left</subscript></entry>
+		  <entry>Y'<subscript>10right</subscript></entry>
+		  <entry>Y'<subscript>11left</subscript></entry>
+		  <entry>Y'<subscript>11right</subscript></entry>
+		  <entry>Y'<subscript>12left</subscript></entry>
+		  <entry>Y'<subscript>12right</subscript></entry>
+		  <entry>Y'<subscript>13left</subscript></entry>
+		  <entry>Y'<subscript>13right</subscript></entry>
+		</row>
+		<row>
+		  <entry>start&nbsp;+&nbsp;16:</entry>
+		  <entry>Y'<subscript>20left</subscript></entry>
+		  <entry>Y'<subscript>20right</subscript></entry>
+		  <entry>Y'<subscript>21left</subscript></entry>
+		  <entry>Y'<subscript>21right</subscript></entry>
+		  <entry>Y'<subscript>22left</subscript></entry>
+		  <entry>Y'<subscript>22right</subscript></entry>
+		  <entry>Y'<subscript>23left</subscript></entry>
+		  <entry>Y'<subscript>23right</subscript></entry>
+		</row>
+		<row>
+		  <entry>start&nbsp;+&nbsp;24:</entry>
+		  <entry>Y'<subscript>30left</subscript></entry>
+		  <entry>Y'<subscript>30right</subscript></entry>
+		  <entry>Y'<subscript>31left</subscript></entry>
+		  <entry>Y'<subscript>31right</subscript></entry>
+		  <entry>Y'<subscript>32left</subscript></entry>
+		  <entry>Y'<subscript>32right</subscript></entry>
+		  <entry>Y'<subscript>33left</subscript></entry>
+		  <entry>Y'<subscript>33right</subscript></entry>
+		</row>
+	      </tbody>
+	    </tgroup>
+	  </informaltable>
+	</para>
+      </formalpara>
+    </example>
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/media/v4l/pixfmt-yuv420m.xml b/Documentation/DocBook/media/v4l/pixfmt-yuv420m.xml
index e781cc61786c..7d13fe96657d 100644
--- a/Documentation/DocBook/media/v4l/pixfmt-yuv420m.xml
+++ b/Documentation/DocBook/media/v4l/pixfmt-yuv420m.xml
@@ -1,35 +1,43 @@
-    <refentry id="V4L2-PIX-FMT-YUV420M">
+    <refentry>
       <refmeta>
-	<refentrytitle>V4L2_PIX_FMT_YUV420M ('YM12')</refentrytitle>
+	<refentrytitle>V4L2_PIX_FMT_YUV420M ('YM12'), V4L2_PIX_FMT_YVU420M ('YM21')</refentrytitle>
 	&manvol;
       </refmeta>
       <refnamediv>
-	<refname> <constant>V4L2_PIX_FMT_YUV420M</constant></refname>
-	<refpurpose>Variation of <constant>V4L2_PIX_FMT_YUV420</constant>
-	  with planes non contiguous in memory. </refpurpose>
+	<refname id="V4L2-PIX-FMT-YUV420M"><constant>V4L2_PIX_FMT_YUV420M</constant></refname>
+	<refname id="V4L2-PIX-FMT-YVU420M"><constant>V4L2_PIX_FMT_YVU420M</constant></refname>
+	<refpurpose>Variation of <constant>V4L2_PIX_FMT_YUV420</constant> and
+	  <constant>V4L2_PIX_FMT_YVU420</constant> with planes non contiguous
+	  in memory.</refpurpose>
       </refnamediv>
 
       <refsect1>
 	<title>Description</title>
 
 	<para>This is a multi-planar format, as opposed to a packed format.
-The three components are separated into three sub- images or planes.
+The three components are separated into three sub-images or planes.</para>
 
-The Y plane is first. The Y plane has one byte per pixel. The Cb data
+	<para>The Y plane is first. The Y plane has one byte per pixel.
+For <constant>V4L2_PIX_FMT_YUV420M</constant> the Cb data
 constitutes the second plane which is half the width and half
 the height of the Y plane (and of the image). Each Cb belongs to four
 pixels, a two-by-two square of the image. For example,
 Cb<subscript>0</subscript> belongs to Y'<subscript>00</subscript>,
 Y'<subscript>01</subscript>, Y'<subscript>10</subscript>, and
 Y'<subscript>11</subscript>. The Cr data, just like the Cb plane, is
-in the third plane. </para>
+in the third plane.</para>
+
+	<para><constant>V4L2_PIX_FMT_YVU420M</constant> is the same except
+the Cr data is stored in the second plane and the Cb data in the third plane.
+</para>
 
 	<para>If the Y plane has pad bytes after each row, then the Cb
 and Cr planes have half as many pad bytes after their rows. In other
 words, two Cx rows (including padding) is exactly as long as one Y row
 (including padding).</para>
 
-	<para><constant>V4L2_PIX_FMT_YUV420M</constant> is intended to be
+	<para><constant>V4L2_PIX_FMT_YUV420M</constant> and
+<constant>V4L2_PIX_FMT_YVU420M</constant> are intended to be
 used only in drivers and applications that support the multi-planar API,
 described in <xref linkend="planar-apis"/>. </para>
 
diff --git a/Documentation/DocBook/media/v4l/pixfmt-yvu420m.xml b/Documentation/DocBook/media/v4l/pixfmt-yuv422m.xml
index 2330667907c7..dd502802cb75 100644
--- a/Documentation/DocBook/media/v4l/pixfmt-yvu420m.xml
+++ b/Documentation/DocBook/media/v4l/pixfmt-yuv422m.xml
@@ -1,40 +1,45 @@
-    <refentry id="V4L2-PIX-FMT-YVU420M">
+    <refentry>
       <refmeta>
-	<refentrytitle>V4L2_PIX_FMT_YVU420M ('YM21')</refentrytitle>
+	<refentrytitle>V4L2_PIX_FMT_YUV422M ('YM16'), V4L2_PIX_FMT_YVU422M ('YM61')</refentrytitle>
 	&manvol;
       </refmeta>
       <refnamediv>
-	<refname> <constant>V4L2_PIX_FMT_YVU420M</constant></refname>
-	<refpurpose>Variation of <constant>V4L2_PIX_FMT_YVU420</constant>
-	  with planes non contiguous in memory. </refpurpose>
+	<refname id="V4L2-PIX-FMT-YUV422M"><constant>V4L2_PIX_FMT_YUV422M</constant></refname>
+	<refname id="V4L2-PIX-FMT-YVU422M"><constant>V4L2_PIX_FMT_YVU422M</constant></refname>
+	<refpurpose>Planar formats with &frac12; horizontal resolution, also
+	known as YUV and YVU 4:2:2</refpurpose>
       </refnamediv>
 
       <refsect1>
 	<title>Description</title>
 
 	<para>This is a multi-planar format, as opposed to a packed format.
-The three components are separated into three sub-images or planes.
+The three components are separated into three sub-images or planes.</para>
 
-The Y plane is first. The Y plane has one byte per pixel. The Cr data
-constitutes the second plane which is half the width and half
-the height of the Y plane (and of the image). Each Cr belongs to four
-pixels, a two-by-two square of the image. For example,
-Cr<subscript>0</subscript> belongs to Y'<subscript>00</subscript>,
-Y'<subscript>01</subscript>, Y'<subscript>10</subscript>, and
-Y'<subscript>11</subscript>. The Cb data, just like the Cr plane, constitutes
-the third plane. </para>
+	<para>The Y plane is first. The Y plane has one byte per pixel.
+For <constant>V4L2_PIX_FMT_YUV422M</constant> the Cb data
+constitutes the second plane which is half the width of the Y plane (and of the
+image). Each Cb belongs to two pixels. For example,
+Cb<subscript>0</subscript> belongs to Y'<subscript>00</subscript>,
+Y'<subscript>01</subscript>. The Cr data, just like the Cb plane, is
+in the third plane. </para>
 
-	<para>If the Y plane has pad bytes after each row, then the Cr
-and Cb planes have half as many pad bytes after their rows. In other
+	<para><constant>V4L2_PIX_FMT_YVU422M</constant> is the same except
+the Cr data is stored in the second plane and the Cb data in the third plane.
+</para>
+
+	<para>If the Y plane has pad bytes after each row, then the Cb
+and Cr planes have half as many pad bytes after their rows. In other
 words, two Cx rows (including padding) is exactly as long as one Y row
 (including padding).</para>
 
-	<para><constant>V4L2_PIX_FMT_YVU420M</constant> is intended to be
+	<para><constant>V4L2_PIX_FMT_YUV422M</constant> and
+<constant>V4L2_PIX_FMT_YVU422M</constant> are intended to be
 used only in drivers and applications that support the multi-planar API,
 described in <xref linkend="planar-apis"/>. </para>
 
 	<example>
-	  <title><constant>V4L2_PIX_FMT_YVU420M</constant> 4 &times; 4
+	  <title><constant>V4L2_PIX_FMT_YUV422M</constant> 4 &times; 4
 pixel image</title>
 
 	  <formalpara>
@@ -75,24 +80,44 @@ pixel image</title>
 		    <row><entry></entry></row>
 		    <row>
 		      <entry>start1&nbsp;+&nbsp;0:</entry>
-		      <entry>Cr<subscript>00</subscript></entry>
-		      <entry>Cr<subscript>01</subscript></entry>
+		      <entry>Cb<subscript>00</subscript></entry>
+		      <entry>Cb<subscript>01</subscript></entry>
 		    </row>
 		    <row>
 		      <entry>start1&nbsp;+&nbsp;2:</entry>
-		      <entry>Cr<subscript>10</subscript></entry>
-		      <entry>Cr<subscript>11</subscript></entry>
+		      <entry>Cb<subscript>10</subscript></entry>
+		      <entry>Cb<subscript>11</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start1&nbsp;+&nbsp;4:</entry>
+		      <entry>Cb<subscript>20</subscript></entry>
+		      <entry>Cb<subscript>21</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start1&nbsp;+&nbsp;6:</entry>
+		      <entry>Cb<subscript>30</subscript></entry>
+		      <entry>Cb<subscript>31</subscript></entry>
 		    </row>
 		    <row><entry></entry></row>
 		    <row>
 		      <entry>start2&nbsp;+&nbsp;0:</entry>
-		      <entry>Cb<subscript>00</subscript></entry>
-		      <entry>Cb<subscript>01</subscript></entry>
+		      <entry>Cr<subscript>00</subscript></entry>
+		      <entry>Cr<subscript>01</subscript></entry>
 		    </row>
 		    <row>
 		      <entry>start2&nbsp;+&nbsp;2:</entry>
-		      <entry>Cb<subscript>10</subscript></entry>
-		      <entry>Cb<subscript>11</subscript></entry>
+		      <entry>Cr<subscript>10</subscript></entry>
+		      <entry>Cr<subscript>11</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start2&nbsp;+&nbsp;4:</entry>
+		      <entry>Cr<subscript>20</subscript></entry>
+		      <entry>Cr<subscript>21</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start2&nbsp;+&nbsp;6:</entry>
+		      <entry>Cr<subscript>30</subscript></entry>
+		      <entry>Cr<subscript>31</subscript></entry>
 		    </row>
 		  </tbody>
 		</tgroup>
@@ -113,36 +138,23 @@ pixel image</title>
 		    </row>
 		    <row>
 		      <entry>0</entry>
-		      <entry>Y</entry><entry></entry><entry>Y</entry><entry></entry>
-		      <entry>Y</entry><entry></entry><entry>Y</entry>
-		    </row>
-		    <row>
-		      <entry></entry>
-		      <entry></entry><entry>C</entry><entry></entry><entry></entry>
-		      <entry></entry><entry>C</entry><entry></entry>
+		      <entry>Y</entry><entry>C</entry><entry>Y</entry><entry></entry>
+		      <entry>Y</entry><entry>C</entry><entry>Y</entry>
 		    </row>
 		    <row>
 		      <entry>1</entry>
-		      <entry>Y</entry><entry></entry><entry>Y</entry><entry></entry>
-		      <entry>Y</entry><entry></entry><entry>Y</entry>
-		    </row>
-		    <row>
-		      <entry></entry>
+		      <entry>Y</entry><entry>C</entry><entry>Y</entry><entry></entry>
+		      <entry>Y</entry><entry>C</entry><entry>Y</entry>
 		    </row>
 		    <row>
 		      <entry>2</entry>
-		      <entry>Y</entry><entry></entry><entry>Y</entry><entry></entry>
-		      <entry>Y</entry><entry></entry><entry>Y</entry>
-		    </row>
-		    <row>
-		      <entry></entry>
-		      <entry></entry><entry>C</entry><entry></entry><entry></entry>
-		      <entry></entry><entry>C</entry><entry></entry>
+		      <entry>Y</entry><entry>C</entry><entry>Y</entry><entry></entry>
+		      <entry>Y</entry><entry>C</entry><entry>Y</entry>
 		    </row>
 		    <row>
 		      <entry>3</entry>
-		      <entry>Y</entry><entry></entry><entry>Y</entry><entry></entry>
-		      <entry>Y</entry><entry></entry><entry>Y</entry>
+		      <entry>Y</entry><entry>C</entry><entry>Y</entry><entry></entry>
+		      <entry>Y</entry><entry>C</entry><entry>Y</entry>
 		    </row>
 		  </tbody>
 		</tgroup>
diff --git a/Documentation/DocBook/media/v4l/pixfmt-yuv444m.xml b/Documentation/DocBook/media/v4l/pixfmt-yuv444m.xml
new file mode 100644
index 000000000000..1b7335940bc7
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/pixfmt-yuv444m.xml
@@ -0,0 +1,177 @@
+    <refentry>
+      <refmeta>
+	<refentrytitle>V4L2_PIX_FMT_YUV444M ('YM24'), V4L2_PIX_FMT_YVU444M ('YM42')</refentrytitle>
+	&manvol;
+      </refmeta>
+      <refnamediv>
+	<refname id="V4L2-PIX-FMT-YUV444M"><constant>V4L2_PIX_FMT_YUV444M</constant></refname>
+	<refname id="V4L2-PIX-FMT-YVU444M"><constant>V4L2_PIX_FMT_YVU444M</constant></refname>
+	<refpurpose>Planar formats with full horizontal resolution, also
+	known as YUV and YVU 4:4:4</refpurpose>
+      </refnamediv>
+
+      <refsect1>
+	<title>Description</title>
+
+	<para>This is a multi-planar format, as opposed to a packed format.
+The three components are separated into three sub-images or planes.</para>
+
+	<para>The Y plane is first. The Y plane has one byte per pixel.
+For <constant>V4L2_PIX_FMT_YUV444M</constant> the Cb data
+constitutes the second plane which is the same width and height as the Y plane
+(and as the image). The Cr data, just like the Cb plane, is in the third plane.
+</para>
+
+	<para><constant>V4L2_PIX_FMT_YVU444M</constant> is the same except
+the Cr data is stored in the second plane and the Cb data in the third plane.
+</para>
+	<para>If the Y plane has pad bytes after each row, then the Cb
+and Cr planes have the same number of pad bytes after their rows.</para>
+
+	<para><constant>V4L2_PIX_FMT_YUV444M</constant> and
+<constant>V4L2_PIX_FMT_YUV444M</constant> are intended to be
+used only in drivers and applications that support the multi-planar API,
+described in <xref linkend="planar-apis"/>. </para>
+
+	<example>
+	  <title><constant>V4L2_PIX_FMT_YUV444M</constant> 4 &times; 4
+pixel image</title>
+
+	  <formalpara>
+	    <title>Byte Order.</title>
+	    <para>Each cell is one byte.
+		<informaltable frame="none">
+		<tgroup cols="5" align="center">
+		  <colspec align="left" colwidth="2*" />
+		  <tbody valign="top">
+		    <row>
+		      <entry>start0&nbsp;+&nbsp;0:</entry>
+		      <entry>Y'<subscript>00</subscript></entry>
+		      <entry>Y'<subscript>01</subscript></entry>
+		      <entry>Y'<subscript>02</subscript></entry>
+		      <entry>Y'<subscript>03</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start0&nbsp;+&nbsp;4:</entry>
+		      <entry>Y'<subscript>10</subscript></entry>
+		      <entry>Y'<subscript>11</subscript></entry>
+		      <entry>Y'<subscript>12</subscript></entry>
+		      <entry>Y'<subscript>13</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start0&nbsp;+&nbsp;8:</entry>
+		      <entry>Y'<subscript>20</subscript></entry>
+		      <entry>Y'<subscript>21</subscript></entry>
+		      <entry>Y'<subscript>22</subscript></entry>
+		      <entry>Y'<subscript>23</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start0&nbsp;+&nbsp;12:</entry>
+		      <entry>Y'<subscript>30</subscript></entry>
+		      <entry>Y'<subscript>31</subscript></entry>
+		      <entry>Y'<subscript>32</subscript></entry>
+		      <entry>Y'<subscript>33</subscript></entry>
+		    </row>
+		    <row><entry></entry></row>
+		    <row>
+		      <entry>start1&nbsp;+&nbsp;0:</entry>
+		      <entry>Cb<subscript>00</subscript></entry>
+		      <entry>Cb<subscript>01</subscript></entry>
+		      <entry>Cb<subscript>02</subscript></entry>
+		      <entry>Cb<subscript>03</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start1&nbsp;+&nbsp;4:</entry>
+		      <entry>Cb<subscript>10</subscript></entry>
+		      <entry>Cb<subscript>11</subscript></entry>
+		      <entry>Cb<subscript>12</subscript></entry>
+		      <entry>Cb<subscript>13</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start1&nbsp;+&nbsp;8:</entry>
+		      <entry>Cb<subscript>20</subscript></entry>
+		      <entry>Cb<subscript>21</subscript></entry>
+		      <entry>Cb<subscript>22</subscript></entry>
+		      <entry>Cb<subscript>23</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start1&nbsp;+&nbsp;12:</entry>
+		      <entry>Cb<subscript>20</subscript></entry>
+		      <entry>Cb<subscript>21</subscript></entry>
+		      <entry>Cb<subscript>32</subscript></entry>
+		      <entry>Cb<subscript>33</subscript></entry>
+		    </row>
+		    <row><entry></entry></row>
+		    <row>
+		      <entry>start2&nbsp;+&nbsp;0:</entry>
+		      <entry>Cr<subscript>00</subscript></entry>
+		      <entry>Cr<subscript>01</subscript></entry>
+		      <entry>Cr<subscript>02</subscript></entry>
+		      <entry>Cr<subscript>03</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start2&nbsp;+&nbsp;4:</entry>
+		      <entry>Cr<subscript>10</subscript></entry>
+		      <entry>Cr<subscript>11</subscript></entry>
+		      <entry>Cr<subscript>12</subscript></entry>
+		      <entry>Cr<subscript>13</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start2&nbsp;+&nbsp;8:</entry>
+		      <entry>Cr<subscript>20</subscript></entry>
+		      <entry>Cr<subscript>21</subscript></entry>
+		      <entry>Cr<subscript>22</subscript></entry>
+		      <entry>Cr<subscript>23</subscript></entry>
+		    </row>
+		    <row>
+		      <entry>start2&nbsp;+&nbsp;12:</entry>
+		      <entry>Cr<subscript>30</subscript></entry>
+		      <entry>Cr<subscript>31</subscript></entry>
+		      <entry>Cr<subscript>32</subscript></entry>
+		      <entry>Cr<subscript>33</subscript></entry>
+		    </row>
+		  </tbody>
+		</tgroup>
+		</informaltable>
+	      </para>
+	  </formalpara>
+
+	  <formalpara>
+	    <title>Color Sample Location.</title>
+	    <para>
+		<informaltable frame="none">
+		<tgroup cols="7" align="center">
+		  <tbody valign="top">
+		    <row>
+		      <entry></entry>
+		      <entry>0</entry><entry></entry><entry>1</entry><entry></entry>
+		      <entry>2</entry><entry></entry><entry>3</entry>
+		    </row>
+		    <row>
+		      <entry>0</entry>
+		      <entry>YC</entry><entry></entry><entry>YC</entry><entry></entry>
+		      <entry>YC</entry><entry></entry><entry>YC</entry>
+		    </row>
+		    <row>
+		      <entry>1</entry>
+		      <entry>YC</entry><entry></entry><entry>YC</entry><entry></entry>
+		      <entry>YC</entry><entry></entry><entry>YC</entry>
+		    </row>
+		    <row>
+		      <entry>2</entry>
+		      <entry>YC</entry><entry></entry><entry>YC</entry><entry></entry>
+		      <entry>YC</entry><entry></entry><entry>YC</entry>
+		    </row>
+		    <row>
+		      <entry>3</entry>
+		      <entry>YC</entry><entry></entry><entry>YC</entry><entry></entry>
+		      <entry>YC</entry><entry></entry><entry>YC</entry>
+		    </row>
+		  </tbody>
+		</tgroup>
+		</informaltable>
+	      </para>
+	  </formalpara>
+	</example>
+      </refsect1>
+    </refentry>
diff --git a/Documentation/DocBook/media/v4l/pixfmt-z16.xml b/Documentation/DocBook/media/v4l/pixfmt-z16.xml
new file mode 100644
index 000000000000..3d87e4bf87b8
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/pixfmt-z16.xml
@@ -0,0 +1,81 @@
+<refentry id="V4L2-PIX-FMT-Z16">
+  <refmeta>
+    <refentrytitle>V4L2_PIX_FMT_Z16 ('Z16 ')</refentrytitle>
+    &manvol;
+  </refmeta>
+  <refnamediv>
+    <refname><constant>V4L2_PIX_FMT_Z16</constant></refname>
+    <refpurpose>Interleaved grey-scale image, e.g. from a stereo-pair</refpurpose>
+  </refnamediv>
+  <refsect1>
+    <title>Description</title>
+
+    <para>This is a 16-bit format, representing depth data. Each pixel is a
+distance to the respective point in the image coordinates. Distance unit can
+vary and has to be negotiated with the device separately. Each pixel is stored
+in a 16-bit word in the little endian byte order.
+</para>
+
+    <example>
+      <title><constant>V4L2_PIX_FMT_Z16</constant> 4 &times; 4
+pixel image</title>
+
+      <formalpara>
+	<title>Byte Order.</title>
+	<para>Each cell is one byte.
+	  <informaltable frame="none">
+	    <tgroup cols="9" align="center">
+	      <colspec align="left" colwidth="2*" />
+	      <tbody valign="top">
+		<row>
+		  <entry>start&nbsp;+&nbsp;0:</entry>
+		  <entry>Z<subscript>00low</subscript></entry>
+		  <entry>Z<subscript>00high</subscript></entry>
+		  <entry>Z<subscript>01low</subscript></entry>
+		  <entry>Z<subscript>01high</subscript></entry>
+		  <entry>Z<subscript>02low</subscript></entry>
+		  <entry>Z<subscript>02high</subscript></entry>
+		  <entry>Z<subscript>03low</subscript></entry>
+		  <entry>Z<subscript>03high</subscript></entry>
+		</row>
+		<row>
+		  <entry>start&nbsp;+&nbsp;8:</entry>
+		  <entry>Z<subscript>10low</subscript></entry>
+		  <entry>Z<subscript>10high</subscript></entry>
+		  <entry>Z<subscript>11low</subscript></entry>
+		  <entry>Z<subscript>11high</subscript></entry>
+		  <entry>Z<subscript>12low</subscript></entry>
+		  <entry>Z<subscript>12high</subscript></entry>
+		  <entry>Z<subscript>13low</subscript></entry>
+		  <entry>Z<subscript>13high</subscript></entry>
+		</row>
+		<row>
+		  <entry>start&nbsp;+&nbsp;16:</entry>
+		  <entry>Z<subscript>20low</subscript></entry>
+		  <entry>Z<subscript>20high</subscript></entry>
+		  <entry>Z<subscript>21low</subscript></entry>
+		  <entry>Z<subscript>21high</subscript></entry>
+		  <entry>Z<subscript>22low</subscript></entry>
+		  <entry>Z<subscript>22high</subscript></entry>
+		  <entry>Z<subscript>23low</subscript></entry>
+		  <entry>Z<subscript>23high</subscript></entry>
+		</row>
+		<row>
+		  <entry>start&nbsp;+&nbsp;24:</entry>
+		  <entry>Z<subscript>30low</subscript></entry>
+		  <entry>Z<subscript>30high</subscript></entry>
+		  <entry>Z<subscript>31low</subscript></entry>
+		  <entry>Z<subscript>31high</subscript></entry>
+		  <entry>Z<subscript>32low</subscript></entry>
+		  <entry>Z<subscript>32high</subscript></entry>
+		  <entry>Z<subscript>33low</subscript></entry>
+		  <entry>Z<subscript>33high</subscript></entry>
+		</row>
+	      </tbody>
+	    </tgroup>
+	  </informaltable>
+	</para>
+      </formalpara>
+    </example>
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/media/v4l/pixfmt.xml b/Documentation/DocBook/media/v4l/pixfmt.xml
index d871245d2973..5a08aeea4360 100644
--- a/Documentation/DocBook/media/v4l/pixfmt.xml
+++ b/Documentation/DocBook/media/v4l/pixfmt.xml
@@ -1620,6 +1620,8 @@ information.</para>
     &sub-y10b;
     &sub-y16;
     &sub-y16-be;
+    &sub-y8i;
+    &sub-y12i;
     &sub-uv8;
     &sub-yuyv;
     &sub-uyvy;
@@ -1628,7 +1630,8 @@ information.</para>
     &sub-y41p;
     &sub-yuv420;
     &sub-yuv420m;
-    &sub-yvu420m;
+    &sub-yuv422m;
+    &sub-yuv444m;
     &sub-yuv410;
     &sub-yuv422p;
     &sub-yuv411p;
@@ -1641,6 +1644,14 @@ information.</para>
     &sub-m420;
   </section>
 
+  <section id="depth-formats">
+    <title>Depth Formats</title>
+    <para>Depth data provides distance to points, mapped onto the image plane
+    </para>
+
+    &sub-z16;
+  </section>
+
   <section>
     <title>Compressed Formats</title>
 
diff --git a/Documentation/DocBook/media/v4l/vidioc-query-dv-timings.xml b/Documentation/DocBook/media/v4l/vidioc-query-dv-timings.xml
index e9c70a8f3476..0c93677d16b4 100644
--- a/Documentation/DocBook/media/v4l/vidioc-query-dv-timings.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-query-dv-timings.xml
@@ -60,9 +60,19 @@ input</refpurpose>
 automatically, similar to sensing the video standard. To do so, applications
 call <constant>VIDIOC_QUERY_DV_TIMINGS</constant> with a pointer to a
 &v4l2-dv-timings;. Once the hardware detects the timings, it will fill in the
-timings structure.
+timings structure.</para>
 
-If the timings could not be detected because there was no signal, then
+<para>Please note that drivers shall <emphasis>not</emphasis> switch timings automatically
+if new timings are detected. Instead, drivers should send the
+<constant>V4L2_EVENT_SOURCE_CHANGE</constant> event (if they support this) and expect
+that userspace will take action by calling <constant>VIDIOC_QUERY_DV_TIMINGS</constant>.
+The reason is that new timings usually mean different buffer sizes as well, and you
+cannot change buffer sizes on the fly. In general, applications that receive the
+Source Change event will have to call <constant>VIDIOC_QUERY_DV_TIMINGS</constant>,
+and if the detected timings are valid they will have to stop streaming, set the new
+timings, allocate new buffers and start streaming again.</para>
+
+<para>If the timings could not be detected because there was no signal, then
 <errorcode>ENOLINK</errorcode> is returned. If a signal was detected, but
 it was unstable and the receiver could not lock to the signal, then
 <errorcode>ENOLCK</errorcode> is returned. If the receiver could lock to the signal,
diff --git a/Documentation/DocBook/media/v4l/vidioc-querystd.xml b/Documentation/DocBook/media/v4l/vidioc-querystd.xml
index 222348542182..3ceae35fab03 100644
--- a/Documentation/DocBook/media/v4l/vidioc-querystd.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-querystd.xml
@@ -59,6 +59,16 @@ then the driver will return V4L2_STD_UNKNOWN. When detection is not
 possible or fails, the set must contain all standards supported by the
 current video input or output.</para>
 
+<para>Please note that drivers shall <emphasis>not</emphasis> switch the video standard
+automatically if a new video standard is detected. Instead, drivers should send the
+<constant>V4L2_EVENT_SOURCE_CHANGE</constant> event (if they support this) and expect
+that userspace will take action by calling <constant>VIDIOC_QUERYSTD</constant>.
+The reason is that a new video standard can mean different buffer sizes as well, and you
+cannot change buffer sizes on the fly. In general, applications that receive the
+Source Change event will have to call <constant>VIDIOC_QUERYSTD</constant>,
+and if the detected video standard is valid they will have to stop streaming, set the new
+standard, allocate new buffers and start streaming again.</para>
+
   </refsect1>
 
   <refsect1>
diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt
index e8d25e784214..ff49cf901148 100644
--- a/Documentation/cgroup-v2.txt
+++ b/Documentation/cgroup-v2.txt
@@ -7,7 +7,7 @@ This is the authoritative documentation on the design, interface and
 conventions of cgroup v2.  It describes all userland-visible aspects
 of cgroup including core and specific controller behaviors.  All
 future changes must be reflected in this document.  Documentation for
-v1 is available under Documentation/cgroup-legacy/.
+v1 is available under Documentation/cgroup-v1/.
 
 CONTENTS
 
diff --git a/Documentation/cpu-freq/intel-pstate.txt b/Documentation/cpu-freq/intel-pstate.txt
index f7b12c071d53..e6bd1e6512a5 100644
--- a/Documentation/cpu-freq/intel-pstate.txt
+++ b/Documentation/cpu-freq/intel-pstate.txt
@@ -25,7 +25,7 @@ callback, so cpufreq core can't request a transition to a specific frequency.
 The driver provides minimum and maximum frequency limits and callbacks to set a
 policy. The policy in cpufreq sysfs is referred to as the "scaling governor".
 The cpufreq core can request the driver to operate in any of the two policies:
-"performance: and "powersave". The driver decides which frequency to use based
+"performance" and "powersave". The driver decides which frequency to use based
 on the above policy selection considering minimum and maximum frequency limits.
 
 The Intel P-State driver falls under the latter category, which implements the
diff --git a/Documentation/crypto/api-intro.txt b/Documentation/crypto/api-intro.txt
index 8b49302712a8..beda682e8d77 100644
--- a/Documentation/crypto/api-intro.txt
+++ b/Documentation/crypto/api-intro.txt
@@ -49,28 +49,33 @@ under development.
 
 Here's an example of how to use the API:
 
-	#include <linux/crypto.h>
+	#include <crypto/ahash.h>
 	#include <linux/err.h>
 	#include <linux/scatterlist.h>
 	
 	struct scatterlist sg[2];
 	char result[128];
-	struct crypto_hash *tfm;
-	struct hash_desc desc;
+	struct crypto_ahash *tfm;
+	struct ahash_request *req;
 	
-	tfm = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
+	tfm = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm))
 		fail();
 		
 	/* ... set up the scatterlists ... */
 
-	desc.tfm = tfm;
-	desc.flags = 0;
-	
-	if (crypto_hash_digest(&desc, sg, 2, result))
+	req = ahash_request_alloc(tfm, GFP_ATOMIC);
+	if (!req)
 		fail();
+
+	ahash_request_set_callback(req, 0, NULL, NULL);
+	ahash_request_set_crypt(req, sg, result, 2);
 	
-	crypto_free_hash(tfm);
+	if (crypto_ahash_digest(req))
+		fail();
+
+	ahash_request_free(req);
+	crypto_free_ahash(tfm);
 
     
 Many real examples are available in the regression test module (tcrypt.c).
diff --git a/Documentation/device-mapper/cache-policies.txt b/Documentation/device-mapper/cache-policies.txt
index d9246a32e673..e5062ad18717 100644
--- a/Documentation/device-mapper/cache-policies.txt
+++ b/Documentation/device-mapper/cache-policies.txt
@@ -28,51 +28,16 @@ Overview of supplied cache replacement policies
 multiqueue (mq)
 ---------------
 
-This policy has been deprecated in favor of the smq policy (see below).
+This policy is now an alias for smq (see below).
 
-The multiqueue policy has three sets of 16 queues: one set for entries
-waiting for the cache and another two for those in the cache (a set for
-clean entries and a set for dirty entries).
+The following tunables are accepted, but have no effect:
 
-Cache entries in the queues are aged based on logical time. Entry into
-the cache is based on variable thresholds and queue selection is based
-on hit count on entry. The policy aims to take different cache miss
-costs into account and to adjust to varying load patterns automatically.
-
-Message and constructor argument pairs are:
 	'sequential_threshold <#nr_sequential_ios>'
 	'random_threshold <#nr_random_ios>'
 	'read_promote_adjustment <value>'
 	'write_promote_adjustment <value>'
 	'discard_promote_adjustment <value>'
 
-The sequential threshold indicates the number of contiguous I/Os
-required before a stream is treated as sequential.  Once a stream is
-considered sequential it will bypass the cache.  The random threshold
-is the number of intervening non-contiguous I/Os that must be seen
-before the stream is treated as random again.
-
-The sequential and random thresholds default to 512 and 4 respectively.
-
-Large, sequential I/Os are probably better left on the origin device
-since spindles tend to have good sequential I/O bandwidth.  The
-io_tracker counts contiguous I/Os to try to spot when the I/O is in one
-of these sequential modes.  But there are use-cases for wanting to
-promote sequential blocks to the cache (e.g. fast application startup).
-If sequential threshold is set to 0 the sequential I/O detection is
-disabled and sequential I/O will no longer implicitly bypass the cache.
-Setting the random threshold to 0 does _not_ disable the random I/O
-stream detection.
-
-Internally the mq policy determines a promotion threshold.  If the hit
-count of a block not in the cache goes above this threshold it gets
-promoted to the cache.  The read, write and discard promote adjustment
-tunables allow you to tweak the promotion threshold by adding a small
-value based on the io type.  They default to 4, 8 and 1 respectively.
-If you're trying to quickly warm a new cache device you may wish to
-reduce these to encourage promotion.  Remember to switch them back to
-their defaults after the cache fills though.
-
 Stochastic multiqueue (smq)
 ---------------------------
 
diff --git a/Documentation/devicetree/bindings/arm/altera/socfpga-eccmgr.txt b/Documentation/devicetree/bindings/arm/altera/socfpga-eccmgr.txt
new file mode 100644
index 000000000000..885f93d14ef9
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/altera/socfpga-eccmgr.txt
@@ -0,0 +1,49 @@
+Altera SoCFPGA ECC Manager
+This driver uses the EDAC framework to implement the SOCFPGA ECC Manager.
+The ECC Manager counts and corrects single bit errors and counts/handles
+double bit errors which are uncorrectable.
+
+Required Properties:
+- compatible : Should be "altr,socfpga-ecc-manager"
+- #address-cells: must be 1
+- #size-cells: must be 1
+- ranges : standard definition, should translate from local addresses
+
+Subcomponents:
+
+L2 Cache ECC
+Required Properties:
+- compatible : Should be "altr,socfpga-l2-ecc"
+- reg : Address and size for ECC error interrupt clear registers.
+- interrupts : Should be single bit error interrupt, then double bit error
+	interrupt. Note the rising edge type.
+
+On Chip RAM ECC
+Required Properties:
+- compatible : Should be "altr,socfpga-ocram-ecc"
+- reg : Address and size for ECC error interrupt clear registers.
+- iram : phandle to On-Chip RAM definition.
+- interrupts : Should be single bit error interrupt, then double bit error
+	interrupt. Note the rising edge type.
+
+Example:
+
+	eccmgr: eccmgr@ffd08140 {
+		compatible = "altr,socfpga-ecc-manager";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		l2-ecc@ffd08140 {
+			compatible = "altr,socfpga-l2-ecc";
+			reg = <0xffd08140 0x4>;
+			interrupts = <0 36 1>, <0 37 1>;
+		};
+
+		ocram-ecc@ffd08144 {
+			compatible = "altr,socfpga-ocram-ecc";
+			reg = <0xffd08144 0x4>;
+			iram = <&ocram>;
+			interrupts = <0 178 1>, <0 179 1>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/arm/omap/omap.txt b/Documentation/devicetree/bindings/arm/omap/omap.txt
index a2bd593881ca..66422d663184 100644
--- a/Documentation/devicetree/bindings/arm/omap/omap.txt
+++ b/Documentation/devicetree/bindings/arm/omap/omap.txt
@@ -23,6 +23,7 @@ Optional properties:
   during suspend.
 - ti,no-reset-on-init: When present, the module should not be reset at init
 - ti,no-idle-on-init: When present, the module should not be idled at init
+- ti,no-idle: When present, the module is never allowed to idle.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/clock/rockchip,rk3036-cru.txt b/Documentation/devicetree/bindings/clock/rockchip,rk3036-cru.txt
index ace05992a262..20df350b9ef3 100644
--- a/Documentation/devicetree/bindings/clock/rockchip,rk3036-cru.txt
+++ b/Documentation/devicetree/bindings/clock/rockchip,rk3036-cru.txt
@@ -30,7 +30,7 @@ that they are defined using standard clock bindings with following
 clock-output-names:
  - "xin24m" - crystal input - required,
  - "ext_i2s" - external I2S clock - optional,
- - "ext_gmac" - external GMAC clock - optional
+ - "rmii_clkin" - external EMAC clock - optional
 
 Example: Clock controller node:
 
diff --git a/Documentation/devicetree/bindings/edac/apm-xgene-edac.txt b/Documentation/devicetree/bindings/edac/apm-xgene-edac.txt
index 78e2a31c58d0..1006b0489464 100644
--- a/Documentation/devicetree/bindings/edac/apm-xgene-edac.txt
+++ b/Documentation/devicetree/bindings/edac/apm-xgene-edac.txt
@@ -16,6 +16,10 @@ Required properties:
 - regmap-mcba		: Regmap of the MCB-A (memory bridge) resource.
 - regmap-mcbb		: Regmap of the MCB-B (memory bridge) resource.
 - regmap-efuse		: Regmap of the PMD efuse resource.
+- regmap-rb		: Regmap of the register bus resource. This property
+			  is optional only for compatibility. If the RB
+			  error conditions are not cleared, it will
+			  continuously generate interrupt.
 - reg			: First resource shall be the CPU bus (PCP) resource.
 - interrupts            : Interrupt-specifier for MCU, PMD, L3, or SoC error
 			  IRQ(s).
@@ -64,6 +68,11 @@ Example:
 		reg = <0x0 0x1054a000 0x0 0x20>;
 	};
 
+	rb: rb@7e000000 {
+		compatible = "apm,xgene-rb", "syscon";
+		reg = <0x0 0x7e000000 0x0 0x10>;
+	};
+
 	edac@78800000 {
 		compatible = "apm,xgene-edac";
 		#address-cells = <2>;
@@ -73,6 +82,7 @@ Example:
 		regmap-mcba = <&mcba>;
 		regmap-mcbb = <&mcbb>;
 		regmap-efuse = <&efuse>;
+		regmap-rb = <&rb>;
 		reg = <0x0 0x78800000 0x0 0x100>;
 		interrupts = <0x0 0x20 0x4>,
 			     <0x0 0x21 0x4>,
diff --git a/Documentation/devicetree/bindings/gpio/microchip,pic32-gpio.txt b/Documentation/devicetree/bindings/gpio/microchip,pic32-gpio.txt
new file mode 100644
index 000000000000..ef3752889496
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/microchip,pic32-gpio.txt
@@ -0,0 +1,49 @@
+* Microchip PIC32 GPIO devices (PIO).
+
+Required properties:
+ - compatible: "microchip,pic32mzda-gpio"
+ - reg: Base address and length for the device.
+ - interrupts: The port interrupt shared by all pins.
+ - gpio-controller: Marks the port as GPIO controller.
+ - #gpio-cells: Two. The first cell is the pin number and
+   the second cell is used to specify the gpio polarity as defined in
+   defined in <dt-bindings/gpio/gpio.h>:
+      0 = GPIO_ACTIVE_HIGH
+      1 = GPIO_ACTIVE_LOW
+      2 = GPIO_OPEN_DRAIN
+ - interrupt-controller: Marks the device node as an interrupt controller.
+ - #interrupt-cells: Two. The first cell is the GPIO number and second cell
+   is used to specify the trigger type as defined in
+   <dt-bindings/interrupt-controller/irq.h>:
+      IRQ_TYPE_EDGE_RISING
+      IRQ_TYPE_EDGE_FALLING
+      IRQ_TYPE_EDGE_BOTH
+ - clocks: Clock specifier (see clock bindings for details).
+ - microchip,gpio-bank: Specifies which bank a controller owns.
+ - gpio-ranges: Interaction with the PINCTRL subsystem.
+
+Example:
+
+/* PORTA */
+gpio0: gpio0@1f860000 {
+	compatible = "microchip,pic32mzda-gpio";
+	reg = <0x1f860000 0x100>;
+	interrupts = <118 IRQ_TYPE_LEVEL_HIGH>;
+	#gpio-cells = <2>;
+	gpio-controller;
+	interrupt-controller;
+	#interrupt-cells = <2>;
+	clocks = <&PBCLK4>;
+	microchip,gpio-bank = <0>;
+	gpio-ranges = <&pic32_pinctrl 0 0 16>;
+};
+
+keys {
+	...
+
+	button@sw1 {
+		label = "ESC";
+		linux,code = <1>;
+		gpios = <&gpio0 12 0>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/hwmon/nsa320-mcu.txt b/Documentation/devicetree/bindings/hwmon/nsa320-mcu.txt
new file mode 100644
index 000000000000..0863e067c85b
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/nsa320-mcu.txt
@@ -0,0 +1,20 @@
+Bindings for the fan / temperature monitor microcontroller used on
+the Zyxel NSA 320 and several subsequent models.
+
+Required properties:
+- compatible	: "zyxel,nsa320-mcu"
+- data-gpios	: The GPIO pin connected to the data line on the MCU
+- clk-gpios	: The GPIO pin connected to the clock line on the MCU
+- act-gpios	: The GPIO pin connected to the active line on the MCU
+
+Example:
+
+	hwmon {
+		compatible = "zyxel,nsa320-mcu";
+		pinctrl-0 = <&pmx_mcu_data &pmx_mcu_clk &pmx_mcu_act>;
+		pinctrl-names = "default";
+
+		data-gpios = <&gpio0 14 GPIO_ACTIVE_HIGH>;
+		clk-gpios = <&gpio0 16 GPIO_ACTIVE_HIGH>;
+		act-gpios = <&gpio0 17 GPIO_ACTIVE_LOW>;
+	};
diff --git a/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt b/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
index a04a80f9cc70..c3b9c4cfe8df 100644
--- a/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
+++ b/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
@@ -10,6 +10,7 @@ Requires node properties:
 	"murata,ncp03wb473"
 	"murata,ncp15wl333"
 	"murata,ncp03wf104"
+	"murata,ncp15xh103"
 
 /* Usage of vendor name "ntc" is deprecated */
 <DEPRECATED>	"ntc,ncp15wb473"
diff --git a/Documentation/devicetree/bindings/iio/iio-bindings.txt b/Documentation/devicetree/bindings/iio/iio-bindings.txt
index 0b447d9ad196..68d6f8ce063b 100644
--- a/Documentation/devicetree/bindings/iio/iio-bindings.txt
+++ b/Documentation/devicetree/bindings/iio/iio-bindings.txt
@@ -82,7 +82,7 @@ vdd channel is connected to output 0 of the &ref device.
 
 	...
 
-	iio_hwmon {
+	iio-hwmon {
 		compatible = "iio-hwmon";
 		io-channels = <&adc 0>, <&adc 1>, <&adc 2>,
 			<&adc 3>, <&adc 4>, <&adc 5>,
diff --git a/Documentation/devicetree/bindings/interrupt-controller/al,alpine-msix.txt b/Documentation/devicetree/bindings/interrupt-controller/al,alpine-msix.txt
new file mode 100644
index 000000000000..f6f1c14bf99b
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/al,alpine-msix.txt
@@ -0,0 +1,26 @@
+Alpine MSIX controller
+
+See arm,gic-v3.txt for SPI and MSI definitions.
+
+Required properties:
+
+- compatible: should be "al,alpine-msix"
+- reg: physical base address and size of the registers
+- interrupt-parent: specifies the parent interrupt controller.
+- interrupt-controller: identifies the node as an interrupt controller
+- msi-controller: identifies the node as an PCI Message Signaled Interrupt
+		  controller
+- al,msi-base-spi: SPI base of the MSI frame
+- al,msi-num-spis: number of SPIs assigned to the MSI frame, relative to SPI0
+
+Example:
+
+msix: msix {
+	compatible = "al,alpine-msix";
+	reg = <0x0 0xfbe00000 0x0 0x100000>;
+	interrupt-parent = <&gic>;
+	interrupt-controller;
+	msi-controller;
+	al,msi-base-spi = <160>;
+	al,msi-num-spis = <160>;
+};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt
index 7803e77d85cb..007a5b46256a 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt
@@ -24,9 +24,8 @@ Main node required properties:
 		1 = edge triggered
 		4 = level triggered
 
-  Cells 4 and beyond are reserved for future use. When the 1st cell
-  has a value of 0 or 1, cells 4 and beyond act as padding, and may be
-  ignored. It is recommended that padding cells have a value of 0.
+  Cells 4 and beyond are reserved for future use and must have a value
+  of 0 if present.
 
 - reg : Specifies base physical address(s) and size of the GIC
   registers, in the following order:
diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt b/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt
index 5a1cb4bc3dfe..793c20ff8fcc 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt
@@ -16,6 +16,7 @@ Main node required properties:
 	"arm,cortex-a15-gic"
 	"arm,cortex-a7-gic"
 	"arm,cortex-a9-gic"
+	"arm,eb11mp-gic"
 	"arm,gic-400"
 	"arm,pl390"
 	"arm,tc11mp-gic"
diff --git a/Documentation/devicetree/bindings/interrupt-controller/marvell,odmi-controller.txt b/Documentation/devicetree/bindings/interrupt-controller/marvell,odmi-controller.txt
new file mode 100644
index 000000000000..8af0a8e613ab
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/marvell,odmi-controller.txt
@@ -0,0 +1,44 @@
+
+* Marvell ODMI for MSI support
+
+Some Marvell SoCs have an On-Die Message Interrupt (ODMI) controller
+which can be used by on-board peripheral for MSI interrupts.
+
+Required properties:
+
+- compatible           : The value here should contain:
+
+    "marvell,ap806-odmi-controller", "marvell,odmi-controller".
+
+- interrupt,controller : Identifies the node as an interrupt controller.
+
+- msi-controller       : Identifies the node as an MSI controller.
+
+- marvell,odmi-frames  : Number of ODMI frames available. Each frame
+                         provides a number of events.
+
+- reg                  : List of register definitions, one for each
+                         ODMI frame.
+
+- marvell,spi-base     : List of GIC base SPI interrupts, one for each
+                         ODMI frame. Those SPI interrupts are 0-based,
+                         i.e marvell,spi-base = <128> will use SPI #96.
+                         See Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt
+                         for details about the GIC Device Tree binding.
+
+- interrupt-parent     : Reference to the parent interrupt controller.
+
+Example:
+
+	odmi: odmi@300000 {
+		compatible = "marvell,ap806-odm-controller",
+			     "marvell,odmi-controller";
+		interrupt-controller;
+		msi-controller;
+		marvell,odmi-frames = <4>;
+		reg = <0x300000 0x4000>,
+		      <0x304000 0x4000>,
+		      <0x308000 0x4000>,
+		      <0x30C000 0x4000>;
+		marvell,spi-base = <128>, <136>, <144>, <152>;
+	};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/mips-gic.txt b/Documentation/devicetree/bindings/interrupt-controller/mips-gic.txt
index aae4c384ee1f..173595305e26 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/mips-gic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/mips-gic.txt
@@ -23,6 +23,12 @@ Optional properties:
 - mti,reserved-cpu-vectors : Specifies the list of CPU interrupt vectors
   to which the GIC may not route interrupts.  Valid values are 2 - 7.
   This property is ignored if the CPU is started in EIC mode.
+- mti,reserved-ipi-vectors : Specifies the range of GIC interrupts that are
+  reserved for IPIs.
+  It accepts 2 values, the 1st is the starting interrupt and the 2nd is the size
+  of the reserved range.
+  If not specified, the driver will allocate the last 2 * number of VPEs in the
+  system.
 
 Required properties for timer sub-node:
 - compatible : Should be "mti,gic-timer".
@@ -44,6 +50,7 @@ Example:
 		#interrupt-cells = <3>;
 
 		mti,reserved-cpu-vectors = <7>;
+		mti,reserved-ipi-vectors = <40 8>;
 
 		timer {
 			compatible = "mti,gic-timer";
diff --git a/Documentation/devicetree/bindings/interrupt-controller/sigma,smp8642-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/sigma,smp8642-intc.txt
new file mode 100644
index 000000000000..1f441fa0ad40
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/sigma,smp8642-intc.txt
@@ -0,0 +1,49 @@
+Sigma Designs SMP86xx/SMP87xx secondary interrupt controller
+
+Required properties:
+- compatible: should be "sigma,smp8642-intc"
+- reg: physical address of MMIO region
+- ranges: address space mapping of child nodes
+- interrupt-parent: phandle of parent interrupt controller
+- interrupt-controller: boolean
+- #address-cells: should be <1>
+- #size-cells: should be <1>
+
+One child node per control block with properties:
+- reg: address of registers for this control block
+- interrupt-controller: boolean
+- #interrupt-cells: should be <2>, interrupt index and flags per interrupts.txt
+- interrupts: interrupt spec of primary interrupt controller
+
+Example:
+
+interrupt-controller@6e000 {
+	compatible = "sigma,smp8642-intc";
+	reg = <0x6e000 0x400>;
+	ranges = <0x0 0x6e000 0x400>;
+	interrupt-parent = <&gic>;
+	interrupt-controller;
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	irq0: interrupt-controller@0 {
+		reg = <0x000 0x100>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	irq1: interrupt-controller@100 {
+		reg = <0x100 0x100>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupts = <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	irq2: interrupt-controller@300 {
+		reg = <0x300 0x100>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupts = <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/leds/leds-is31fl32xx.txt b/Documentation/devicetree/bindings/leds/leds-is31fl32xx.txt
new file mode 100644
index 000000000000..926c2117942c
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/leds-is31fl32xx.txt
@@ -0,0 +1,52 @@
+Binding for ISSI IS31FL32xx and Si-En SN32xx LED Drivers
+
+The IS31FL32xx/SN32xx family of LED drivers are I2C devices with multiple
+constant-current channels, each with independent 256-level PWM control.
+Each LED is represented as a sub-node of the device.
+
+Required properties:
+- compatible: one of
+	issi,is31fl3236
+	issi,is31fl3235
+	issi,is31fl3218
+	issi,is31fl3216
+	si-en,sn3218
+	si-en,sn3216
+- reg: I2C slave address
+- address-cells : must be 1
+- size-cells : must be 0
+
+LED sub-node properties:
+- reg : LED channel number (1..N)
+- label :  (optional)
+  see Documentation/devicetree/bindings/leds/common.txt
+- linux,default-trigger :  (optional)
+  see Documentation/devicetree/bindings/leds/common.txt
+
+
+Example:
+
+is31fl3236: led-controller@3c {
+	compatible = "issi,is31fl3236";
+	reg = <0x3c>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	led@1 {
+		reg = <1>;
+		label = "EB:blue:usr0";
+	};
+	led@2 {
+		reg = <2>;
+		label = "EB:blue:usr1";
+	};
+	...
+	led@36 {
+		reg = <36>;
+		label = "EB:blue:usr35";
+	};
+};
+
+For more product information please see the links below:
+http://www.issi.com/US/product-analog-fxled-driver.shtml
+http://www.si-en.com/product.asp?parentid=890
diff --git a/Documentation/devicetree/bindings/media/i2c/mt9v032.txt b/Documentation/devicetree/bindings/media/i2c/mt9v032.txt
index 202565313e82..100f0ae43269 100644
--- a/Documentation/devicetree/bindings/media/i2c/mt9v032.txt
+++ b/Documentation/devicetree/bindings/media/i2c/mt9v032.txt
@@ -20,6 +20,8 @@ Optional Properties:
 
 - link-frequencies: List of allowed link frequencies in Hz. Each frequency is
 	expressed as a 64-bit big-endian integer.
+- reset-gpios: GPIO handle which is connected to the reset pin of the chip.
+- standby-gpios: GPIO handle which is connected to the standby pin of the chip.
 
 For further reading on port node refer to
 Documentation/devicetree/bindings/media/video-interfaces.txt.
diff --git a/Documentation/devicetree/bindings/media/i2c/tvp5150.txt b/Documentation/devicetree/bindings/media/i2c/tvp5150.txt
new file mode 100644
index 000000000000..8c0fc1a26bf0
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/i2c/tvp5150.txt
@@ -0,0 +1,45 @@
+* Texas Instruments TVP5150 and TVP5151 video decoders
+
+The TVP5150 and TVP5151 are video decoders that convert baseband NTSC and PAL
+(and also SECAM in the TVP5151 case) video signals to either 8-bit 4:2:2 YUV
+with discrete syncs or 8-bit ITU-R BT.656 with embedded syncs output formats.
+
+Required Properties:
+- compatible: value must be "ti,tvp5150"
+- reg: I2C slave address
+
+Optional Properties:
+- pdn-gpios: phandle for the GPIO connected to the PDN pin, if any.
+- reset-gpios: phandle for the GPIO connected to the RESETB pin, if any.
+
+The device node must contain one 'port' child node for its digital output
+video port, in accordance with the video interface bindings defined in
+Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+Required Endpoint Properties for parallel synchronization:
+
+- hsync-active: active state of the HSYNC signal. Must be <1> (HIGH).
+- vsync-active: active state of the VSYNC signal. Must be <1> (HIGH).
+- field-even-active: field signal level during the even field data
+  transmission. Must be <0>.
+
+If none of hsync-active, vsync-active and field-even-active is specified,
+the endpoint is assumed to use embedded BT.656 synchronization.
+
+Example:
+
+&i2c2 {
+	...
+	tvp5150@5c {
+		compatible = "ti,tvp5150";
+		reg = <0x5c>;
+		pdn-gpios = <&gpio4 30 GPIO_ACTIVE_LOW>;
+		reset-gpios = <&gpio6 7 GPIO_ACTIVE_LOW>;
+
+		port {
+			tvp5150_1: endpoint {
+				remote-endpoint = <&ccdc_ep>;
+			};
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/media/rcar_vin.txt b/Documentation/devicetree/bindings/media/rcar_vin.txt
index 9dafe6b06cd2..619193ccf7ff 100644
--- a/Documentation/devicetree/bindings/media/rcar_vin.txt
+++ b/Documentation/devicetree/bindings/media/rcar_vin.txt
@@ -6,6 +6,7 @@ family of devices. The current blocks are always slaves and suppot one input
 channel which can be either RGB, YUYV or BT656.
 
  - compatible: Must be one of the following
+   - "renesas,vin-r8a7795" for the R8A7795 device
    - "renesas,vin-r8a7794" for the R8A7794 device
    - "renesas,vin-r8a7793" for the R8A7793 device
    - "renesas,vin-r8a7791" for the R8A7791 device
diff --git a/Documentation/devicetree/bindings/media/renesas,jpu.txt b/Documentation/devicetree/bindings/media/renesas,jpu.txt
index 0cb94201bf92..d3436e5190f9 100644
--- a/Documentation/devicetree/bindings/media/renesas,jpu.txt
+++ b/Documentation/devicetree/bindings/media/renesas,jpu.txt
@@ -5,11 +5,12 @@ and decoding function conforming to the JPEG baseline process, so that the JPU
 can encode image data and decode JPEG data quickly.
 
 Required properties:
-  - compatible: should containg one of the following:
-			- "renesas,jpu-r8a7790" for R-Car H2
-			- "renesas,jpu-r8a7791" for R-Car M2-W
-			- "renesas,jpu-r8a7792" for R-Car V2H
-			- "renesas,jpu-r8a7793" for R-Car M2-N
+- compatible: "renesas,jpu-<soctype>", "renesas,rcar-gen2-jpu" as fallback.
+	Examples with soctypes are:
+	  - "renesas,jpu-r8a7790" for R-Car H2
+	  - "renesas,jpu-r8a7791" for R-Car M2-W
+	  - "renesas,jpu-r8a7792" for R-Car V2H
+	  - "renesas,jpu-r8a7793" for R-Car M2-N
 
   - reg: Base address and length of the registers block for the JPU.
   - interrupts: JPU interrupt specifier.
@@ -17,7 +18,7 @@ Required properties:
 
 Example: R8A7790 (R-Car H2) JPU node
 	jpeg-codec@fe980000 {
-		compatible = "renesas,jpu-r8a7790";
+		compatible = "renesas,jpu-r8a7790", "renesas,rcar-gen2-jpu";
 		reg = <0 0xfe980000 0 0x10300>;
 		interrupts = <0 272 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp1_clks R8A7790_CLK_JPU>;
diff --git a/Documentation/devicetree/bindings/media/renesas,vsp1.txt b/Documentation/devicetree/bindings/media/renesas,vsp1.txt
index 87fe08abf36d..627405abd144 100644
--- a/Documentation/devicetree/bindings/media/renesas,vsp1.txt
+++ b/Documentation/devicetree/bindings/media/renesas,vsp1.txt
@@ -1,30 +1,18 @@
-* Renesas VSP1 Video Processing Engine
+* Renesas VSP Video Processing Engine
 
-The VSP1 is a video processing engine that supports up-/down-scaling, alpha
+The VSP is a video processing engine that supports up-/down-scaling, alpha
 blending, color space conversion and various other image processing features.
 It can be found in the Renesas R-Car second generation SoCs.
 
 Required properties:
 
-  - compatible: Must contain "renesas,vsp1"
+  - compatible: Must contain one of the following values
+    - "renesas,vsp1" for the R-Car Gen2 VSP1
+    - "renesas,vsp2" for the R-Car Gen3 VSP2
 
-  - reg: Base address and length of the registers block for the VSP1.
-  - interrupts: VSP1 interrupt specifier.
-  - clocks: A phandle + clock-specifier pair for the VSP1 functional clock.
-
-  - renesas,#rpf: Number of Read Pixel Formatter (RPF) modules in the VSP1.
-  - renesas,#uds: Number of Up Down Scaler (UDS) modules in the VSP1.
-  - renesas,#wpf: Number of Write Pixel Formatter (WPF) modules in the VSP1.
-
-
-Optional properties:
-
-  - renesas,has-lif: Boolean, indicates that the LCD Interface (LIF) module is
-    available.
-  - renesas,has-lut: Boolean, indicates that the Look Up Table (LUT) module is
-    available.
-  - renesas,has-sru: Boolean, indicates that the Super Resolution Unit (SRU)
-    module is available.
+  - reg: Base address and length of the registers block for the VSP.
+  - interrupts: VSP interrupt specifier.
+  - clocks: A phandle + clock-specifier pair for the VSP functional clock.
 
 
 Example: R8A7790 (R-Car H2) VSP1-S node
@@ -34,10 +22,4 @@ Example: R8A7790 (R-Car H2) VSP1-S node
 		reg = <0 0xfe928000 0 0x8000>;
 		interrupts = <0 267 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&mstp1_clks R8A7790_CLK_VSP1_S>;
-
-		renesas,has-lut;
-		renesas,has-sru;
-		renesas,#rpf = <5>;
-		renesas,#uds = <3>;
-		renesas,#wpf = <4>;
 	};
diff --git a/Documentation/devicetree/bindings/media/ti-cal.txt b/Documentation/devicetree/bindings/media/ti-cal.txt
new file mode 100644
index 000000000000..ae9b52f37576
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/ti-cal.txt
@@ -0,0 +1,72 @@
+Texas Instruments DRA72x CAMERA ADAPTATION LAYER (CAL)
+------------------------------------------------------
+
+The Camera Adaptation Layer (CAL) is a key component for image capture
+applications. The capture module provides the system interface and the
+processing capability to connect CSI2 image-sensor modules to the
+DRA72x device.
+
+Required properties:
+- compatible: must be "ti,dra72-cal"
+- reg:	CAL Top level, Receiver Core #0, Receiver Core #1 and Camera RX
+	control address space
+- reg-names: cal_top, cal_rx_core0, cal_rx_core1, and camerrx_control
+	     registers
+- interrupts: should contain IRQ line for the CAL;
+
+CAL supports 2 camera port nodes on MIPI bus. Each CSI2 camera port nodes
+should contain a 'port' child node with child 'endpoint' node. Please
+refer to the bindings defined in
+Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+Example:
+	cal: cal@4845b000 {
+		compatible = "ti,dra72-cal";
+		ti,hwmods = "cal";
+		reg = <0x4845B000 0x400>,
+		      <0x4845B800 0x40>,
+		      <0x4845B900 0x40>,
+		      <0x4A002e94 0x4>;
+		reg-names = "cal_top",
+			    "cal_rx_core0",
+			    "cal_rx_core1",
+			    "camerrx_control";
+		interrupts = <GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			csi2_0: port@0 {
+				reg = <0>;
+				endpoint {
+					slave-mode;
+					remote-endpoint = <&ar0330_1>;
+				};
+			};
+			csi2_1: port@1 {
+				reg = <1>;
+			};
+		};
+	};
+
+	i2c5: i2c@4807c000 {
+		ar0330@10 {
+			compatible = "ti,ar0330";
+			reg = <0x10>;
+
+			port {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				ar0330_1: endpoint {
+					reg = <0>;
+					clock-lanes = <1>;
+					data-lanes = <0 2 3 4>;
+					remote-endpoint = <&csi2_0>;
+				};
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt
index 81a9f9e6b45f..c8ac222eac67 100644
--- a/Documentation/devicetree/bindings/net/renesas,ravb.txt
+++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt
@@ -82,8 +82,8 @@ Example:
 				  "ch16", "ch17", "ch18", "ch19",
 				  "ch20", "ch21", "ch22", "ch23",
 				  "ch24";
-		clocks = <&mstp8_clks R8A7795_CLK_ETHERAVB>;
-		power-domains = <&cpg_clocks>;
+		clocks = <&cpg CPG_MOD 812>;
+		power-domains = <&cpg>;
 		phy-mode = "rgmii-id";
 		phy-handle = <&phy0>;
 
diff --git a/Documentation/devicetree/bindings/pci/designware-pcie.txt b/Documentation/devicetree/bindings/pci/designware-pcie.txt
index 5b0853df9d5a..64f2fff12128 100644
--- a/Documentation/devicetree/bindings/pci/designware-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/designware-pcie.txt
@@ -28,3 +28,20 @@ Optional properties:
 - clock-names: Must include the following entries:
 	- "pcie"
 	- "pcie_bus"
+
+Example configuration:
+
+	pcie: pcie@0xdffff000 {
+		compatible = "snps,dw-pcie";
+		reg = <0xdffff000 0x1000>, /* Controller registers */
+		      <0xd0000000 0x2000>; /* PCI config space */
+		reg-names = "ctrlreg", "config";
+		#address-cells = <3>;
+		#size-cells = <2>;
+		device_type = "pci";
+		ranges = <0x81000000 0 0x00000000 0xde000000 0 0x00010000
+			  0x82000000 0 0xd0400000 0xd0400000 0 0x0d000000>;
+		interrupts = <25>, <24>;
+		#interrupt-cells = <1>;
+		num-lanes = <1>;
+	};
diff --git a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt
index 6fbba53a309b..3be80c68941a 100644
--- a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt
@@ -13,6 +13,13 @@ Required properties:
 - clock-names: Must include the following additional entries:
 	- "pcie_phy"
 
+Optional properties:
+- fsl,tx-deemph-gen1: Gen1 De-emphasis value. Default: 0
+- fsl,tx-deemph-gen2-3p5db: Gen2 (3.5db) De-emphasis value. Default: 0
+- fsl,tx-deemph-gen2-6db: Gen2 (6db) De-emphasis value. Default: 20
+- fsl,tx-swing-full: Gen2 TX SWING FULL value. Default: 127
+- fsl,tx-swing-low: TX launch amplitude swing_low value. Default: 127
+
 Example:
 
 	pcie@0x01000000 {
diff --git a/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt b/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
index 4e8b90e43dd8..07a75094c5a8 100644
--- a/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
+++ b/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
@@ -8,6 +8,7 @@ OHCI and EHCI controllers.
 Required properties:
 - compatible: "renesas,pci-r8a7790" for the R8A7790 SoC;
 	      "renesas,pci-r8a7791" for the R8A7791 SoC;
+	      "renesas,pci-r8a7793" for the R8A7793 SoC;
 	      "renesas,pci-r8a7794" for the R8A7794 SoC;
 	      "renesas,pci-rcar-gen2" for a generic R-Car Gen2 compatible device
 
diff --git a/Documentation/devicetree/bindings/pci/pci-thunder-ecam.txt b/Documentation/devicetree/bindings/pci/pci-thunder-ecam.txt
new file mode 100644
index 000000000000..f478874b79ce
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/pci-thunder-ecam.txt
@@ -0,0 +1,30 @@
+* ThunderX PCI host controller for pass-1.x silicon
+
+Firmware-initialized PCI host controller to on-chip devices found on
+some Cavium ThunderX processors.  These devices have ECAM-based config
+access, but the BARs are all at fixed addresses.  We handle the fixed
+addresses by synthesizing Enhanced Allocation (EA) capabilities for
+these devices.
+
+The properties and their meanings are identical to those described in
+host-generic-pci.txt except as listed below.
+
+Properties of the host controller node that differ from
+host-generic-pci.txt:
+
+- compatible     : Must be "cavium,pci-host-thunder-ecam"
+
+Example:
+
+	pcie@84b000000000 {
+		compatible = "cavium,pci-host-thunder-ecam";
+		device_type = "pci";
+		msi-parent = <&its>;
+		msi-map = <0 &its 0x30000 0x10000>;
+		bus-range = <0 31>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		#stream-id-cells = <1>;
+		reg = <0x84b0 0x00000000 0 0x02000000>;  /* Configuration space */
+		ranges = <0x03000000 0x8180 0x00000000 0x8180 0x00000000 0x80 0x00000000>; /* mem ranges */
+	};
diff --git a/Documentation/devicetree/bindings/pci/pci-thunder-pem.txt b/Documentation/devicetree/bindings/pci/pci-thunder-pem.txt
new file mode 100644
index 000000000000..f131faea3b7c
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/pci-thunder-pem.txt
@@ -0,0 +1,43 @@
+* ThunderX PEM PCIe host controller
+
+Firmware-initialized PCI host controller found on some Cavium
+ThunderX processors.
+
+The properties and their meanings are identical to those described in
+host-generic-pci.txt except as listed below.
+
+Properties of the host controller node that differ from
+host-generic-pci.txt:
+
+- compatible     : Must be "cavium,pci-host-thunder-pem"
+
+- reg            : Two entries: First the configuration space for down
+                   stream devices base address and size, as accessed
+                   from the parent bus. Second, the register bank of
+                   the PEM device PCIe bridge.
+
+Example:
+
+    pci@87e0,c2000000 {
+	compatible = "cavium,pci-host-thunder-pem";
+	device_type = "pci";
+	msi-parent = <&its>;
+	msi-map = <0 &its 0x10000 0x10000>;
+	bus-range = <0x8f 0xc7>;
+	#size-cells = <2>;
+	#address-cells = <3>;
+
+	reg = <0x8880 0x8f000000 0x0 0x39000000>,  /* Configuration space */
+	      <0x87e0 0xc2000000 0x0 0x00010000>; /* PEM space */
+	ranges = <0x01000000 0x00 0x00020000 0x88b0 0x00020000 0x00 0x00010000>, /* I/O */
+		 <0x03000000 0x00 0x10000000 0x8890 0x10000000 0x0f 0xf0000000>, /* mem64 */
+		 <0x43000000 0x10 0x00000000 0x88a0 0x00000000 0x10 0x00000000>, /* mem64-pref */
+		 <0x03000000 0x87e0 0xc2f00000 0x87e0 0xc2000000 0x00 0x00100000>; /* mem64 PEM BAR4 */
+
+	#interrupt-cells = <1>;
+	interrupt-map-mask = <0 0 0 7>;
+	interrupt-map = <0 0 0 1 &gic0 0 0 0 24 4>, /* INTA */
+			<0 0 0 2 &gic0 0 0 0 25 4>, /* INTB */
+			<0 0 0 3 &gic0 0 0 0 26 4>, /* INTC */
+			<0 0 0 4 &gic0 0 0 0 27 4>; /* INTD */
+    };
diff --git a/Documentation/devicetree/bindings/pci/rcar-pci.txt b/Documentation/devicetree/bindings/pci/rcar-pci.txt
index 558fe528ae19..6cf99690eef9 100644
--- a/Documentation/devicetree/bindings/pci/rcar-pci.txt
+++ b/Documentation/devicetree/bindings/pci/rcar-pci.txt
@@ -4,6 +4,7 @@ Required properties:
 compatible: "renesas,pcie-r8a7779" for the R8A7779 SoC;
 	    "renesas,pcie-r8a7790" for the R8A7790 SoC;
 	    "renesas,pcie-r8a7791" for the R8A7791 SoC;
+	    "renesas,pcie-r8a7793" for the R8A7793 SoC;
 	    "renesas,pcie-r8a7795" for the R8A7795 SoC;
 	    "renesas,pcie-rcar-gen2" for a generic R-Car Gen2 compatible device.
 
diff --git a/Documentation/devicetree/bindings/pci/xilinx-nwl-pcie.txt b/Documentation/devicetree/bindings/pci/xilinx-nwl-pcie.txt
new file mode 100644
index 000000000000..337fc97d18c9
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/xilinx-nwl-pcie.txt
@@ -0,0 +1,68 @@
+* Xilinx NWL PCIe Root Port Bridge DT description
+
+Required properties:
+- compatible: Should contain "xlnx,nwl-pcie-2.11"
+- #address-cells: Address representation for root ports, set to <3>
+- #size-cells: Size representation for root ports, set to <2>
+- #interrupt-cells: specifies the number of cells needed to encode an
+	interrupt source. The value must be 1.
+- reg: Should contain Bridge, PCIe Controller registers location,
+	configuration space, and length
+- reg-names: Must include the following entries:
+	"breg": bridge registers
+	"pcireg": PCIe controller registers
+	"cfg": configuration space region
+- device_type: must be "pci"
+- interrupts: Should contain NWL PCIe interrupt
+- interrupt-names: Must include the following entries:
+	"msi1, msi0": interrupt asserted when MSI is received
+	"intx": interrupt asserted when a legacy interrupt is received
+	"misc": interrupt asserted when miscellaneous is received
+- interrupt-map-mask and interrupt-map: standard PCI properties to define the
+	mapping of the PCI interface to interrupt numbers.
+- ranges: ranges for the PCI memory regions (I/O space region is not
+	supported by hardware)
+	Please refer to the standard PCI bus binding document for a more
+	detailed explanation
+- msi-controller: indicates that this is MSI controller node
+- msi-parent:  MSI parent of the root complex itself
+- legacy-interrupt-controller: Interrupt controller device node for Legacy interrupts
+	- interrupt-controller: identifies the node as an interrupt controller
+	- #interrupt-cells: should be set to 1
+	- #address-cells: specifies the number of cells needed to encode an
+		address. The value must be 0.
+
+
+Example:
+++++++++
+
+nwl_pcie: pcie@fd0e0000 {
+	#address-cells = <3>;
+	#size-cells = <2>;
+	compatible = "xlnx,nwl-pcie-2.11";
+	#interrupt-cells = <1>;
+	msi-controller;
+	device_type = "pci";
+	interrupt-parent = <&gic>;
+	interrupts = <0 114 4>, <0 115 4>, <0 116 4>, <0 117 4>, <0 118 4>;
+	interrupt-names = "msi0", "msi1", "intx", "dummy", "misc";
+	interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+	interrupt-map = <0x0 0x0 0x0 0x1 &pcie_intc 0x1>,
+			<0x0 0x0 0x0 0x2 &pcie_intc 0x2>,
+			<0x0 0x0 0x0 0x3 &pcie_intc 0x3>,
+			<0x0 0x0 0x0 0x4 &pcie_intc 0x4>;
+
+	msi-parent = <&nwl_pcie>;
+	reg = <0x0 0xfd0e0000 0x0 0x1000>,
+	      <0x0 0xfd480000 0x0 0x1000>,
+	      <0x0 0xe0000000 0x0 0x1000000>;
+	reg-names = "breg", "pcireg", "cfg";
+	ranges = <0x02000000 0x00000000 0xe1000000 0x00000000 0xe1000000 0 0x0f000000>;
+
+	pcie_intc: legacy-interrupt-controller {
+		interrupt-controller;
+		#address-cells = <0>;
+		#interrupt-cells = <1>;
+	};
+
+};
diff --git a/Documentation/devicetree/bindings/pci/xilinx-pcie.txt b/Documentation/devicetree/bindings/pci/xilinx-pcie.txt
index 02f979a48aeb..fd57a81180a4 100644
--- a/Documentation/devicetree/bindings/pci/xilinx-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/xilinx-pcie.txt
@@ -17,7 +17,7 @@ Required properties:
 	Please refer to the standard PCI bus binding document for a more
 	detailed explanation
 
-Optional properties:
+Optional properties for Zynq/Microblaze:
 - bus-range: PCI bus numbers covered
 
 Interrupt controller child node
@@ -38,13 +38,13 @@ the four INTx interrupts in ISR and route them to this domain.
 
 Example:
 ++++++++
-
+Zynq:
 	pci_express: axi-pcie@50000000 {
 		#address-cells = <3>;
 		#size-cells = <2>;
 		#interrupt-cells = <1>;
 		compatible = "xlnx,axi-pcie-host-1.00.a";
-		reg = < 0x50000000 0x10000000 >;
+		reg = < 0x50000000 0x1000000 >;
 		device_type = "pci";
 		interrupts = < 0 52 4 >;
 		interrupt-map-mask = <0 0 0 7>;
@@ -60,3 +60,29 @@ Example:
 			#interrupt-cells = <1>;
 		};
 	};
+
+
+Microblaze:
+	pci_express: axi-pcie@10000000 {
+		#address-cells = <3>;
+		#size-cells = <2>;
+		#interrupt-cells = <1>;
+		compatible = "xlnx,axi-pcie-host-1.00.a";
+		reg = <0x10000000 0x4000000>;
+		device_type = "pci";
+		interrupt-parent = <&microblaze_0_intc>;
+		interrupts = <1 2>;
+		interrupt-map-mask = <0 0 0 7>;
+		interrupt-map = <0 0 0 1 &pcie_intc 1>,
+				<0 0 0 2 &pcie_intc 2>,
+				<0 0 0 3 &pcie_intc 3>,
+				<0 0 0 4 &pcie_intc 4>;
+		ranges = <0x02000000 0x00000000 0x80000000 0x80000000 0x00000000 0x10000000>;
+
+		pcie_intc: interrupt-controller {
+			interrupt-controller;
+			#address-cells = <0>;
+			#interrupt-cells = <1>;
+		};
+
+	};
diff --git a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
index 9213b27e1036..69617220c5d6 100644
--- a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
@@ -21,6 +21,8 @@ Required properties:
   "allwinner,sun9i-a80-r-pinctrl"
   "allwinner,sun8i-a83t-pinctrl"
   "allwinner,sun8i-h3-pinctrl"
+  "allwinner,sun8i-h3-r-pinctrl"
+  "allwinner,sun50i-a64-pinctrl"
 
 - reg: Should contain the register physical address and length for the
   pin controller.
diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,ns2-pinmux.txt b/Documentation/devicetree/bindings/pinctrl/brcm,ns2-pinmux.txt
new file mode 100644
index 000000000000..e295dda4bbba
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/brcm,ns2-pinmux.txt
@@ -0,0 +1,102 @@
+Broadcom Northstar2 IOMUX Controller
+
+The Northstar2 IOMUX controller supports group based mux configuration. There
+are some individual pins that support modifying the pinconf parameters.
+
+Required properties:
+
+- compatible:
+    Must be "brcm,ns2-pinmux"
+
+- reg:
+    Define the base and range of the I/O address space that contains the
+    Northstar2 IOMUX and pin configuration registers.
+
+Properties in sub nodes:
+
+- function:
+    The mux function to select
+
+- groups:
+    The list of groups to select with a given function
+
+- pins:
+    List of pin names to change configuration
+
+The generic properties bias-disable, bias-pull-down, bias-pull-up,
+drive-strength, slew-rate, input-enable, input-disable are supported
+for some individual pins listed at the end.
+
+For more details, refer to
+Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
+
+For example:
+
+	pinctrl: pinctrl@6501d130 {
+		compatible = "brcm,ns2-pinmux";
+		reg = <0x6501d130 0x08>,
+		      <0x660a0028 0x04>,
+		      <0x660009b0 0x40>;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&nand_sel &uart3_rx &sdio0_d4>;
+
+		/* Select nand function */
+		nand_sel: nand_sel {
+			function = "nand";
+			groups = "nand_grp";
+		};
+
+		/* Pull up the uart3 rx pin */
+		uart3_rx: uart3_rx {
+			pins = "uart3_sin";
+			bias-pull-up;
+		};
+
+		/* Set the drive strength of sdio d4 pin */
+		sdio0_d4: sdio0_d4 {
+			pins = "sdio0_data4";
+			drive-strength = <8>;
+		};
+	};
+
+List of supported functions and groups in Northstar2:
+
+"nand": "nand_grp"
+
+"nor": "nor_data_grp", "nor_adv_grp", "nor_addr_0_3_grp", "nor_addr_4_5_grp",
+	"nor_addr_6_7_grp", "nor_addr_8_9_grp", "nor_addr_10_11_grp",
+	"nor_addr_12_15_grp"
+
+"gpio": "gpio_0_1_grp", "gpio_2_5_grp", "gpio_6_7_grp", "gpio_8_9_grp",
+	"gpio_10_11_grp", "gpio_12_13_grp", "gpio_14_17_grp", "gpio_18_19_grp",
+	"gpio_20_21_grp", "gpio_22_23_grp", "gpio_24_25_grp", "gpio_26_27_grp",
+	"gpio_28_29_grp", "gpio_30_31_grp"
+
+"pcie": "pcie_ab1_clk_wak_grp", "pcie_a3_clk_wak_grp", "pcie_b3_clk_wak_grp",
+	"pcie_b2_clk_wak_grp", "pcie_a2_clk_wak_grp"
+
+"uart0": "uart0_modem_grp", "uart0_rts_cts_grp", "uart0_in_out_grp"
+
+"uart1": "uart1_ext_clk_grp", "uart1_dcd_dsr_grp", "uart1_ri_dtr_grp",
+	"uart1_rts_cts_grp", "uart1_in_out_grp"
+
+"uart2": "uart2_rts_cts_grp"
+
+"pwm": "pwm_0_grp", "pwm_1_grp", "pwm_2_grp", "pwm_3_grp"
+
+
+List of pins that support pinconf parameters:
+
+"qspi_wp", "qspi_hold", "qspi_cs", "qspi_sck", "uart3_sin", "uart3_sout",
+"qspi_mosi", "qspi_miso", "spi0_fss", "spi0_rxd", "spi0_txd", "spi0_sck",
+"spi1_fss", "spi1_rxd", "spi1_txd", "spi1_sck", "sdio0_data7",
+"sdio0_emmc_rst", "sdio0_led_on", "sdio0_wp", "sdio0_data3", "sdio0_data4",
+"sdio0_data5", "sdio0_data6", "sdio0_cmd", "sdio0_data0", "sdio0_data1",
+"sdio0_data2", "sdio1_led_on", "sdio1_wp", "sdio0_cd_l", "sdio0_clk",
+"sdio1_data5", "sdio1_data6", "sdio1_data7", "sdio1_emmc_rst", "sdio1_data1",
+"sdio1_data2", "sdio1_data3", "sdio1_data4", "sdio1_cd_l", "sdio1_clk",
+"sdio1_cmd", "sdio1_data0", "ext_mdio_0", "ext_mdc_0", "usb3_p1_vbus_ppc",
+"usb3_p1_overcurrent", "usb3_p0_vbus_ppc", "usb3_p0_overcurrent",
+"usb2_presence_indication", "usb2_vbus_present", "usb2_vbus_ppc",
+"usb2_overcurrent", "sata_led1", "sata_led0"
diff --git a/Documentation/devicetree/bindings/pinctrl/microchip,pic32-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/microchip,pic32-pinctrl.txt
new file mode 100644
index 000000000000..4b5efa51bec7
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/microchip,pic32-pinctrl.txt
@@ -0,0 +1,60 @@
+* Microchip PIC32 Pin Controller
+
+Please refer to pinctrl-bindings.txt, ../gpio/gpio.txt, and
+../interrupt-controller/interrupts.txt for generic information regarding
+pin controller, GPIO, and interrupt bindings.
+
+PIC32 'pin configuration node' is a node of a group of pins which can be
+used for a specific device or function. This node represents configuraions of
+pins, optional function, and optional mux related configuration.
+
+Required properties for pin controller node:
+ - compatible: "microchip,pic32mada-pinctrl"
+ - reg: Address range of the pinctrl registers.
+ - clocks: Clock specifier (see clock bindings for details)
+
+Required properties for pin configuration sub-nodes:
+ - pins: List of pins to which the configuration applies.
+
+Optional properties for pin configuration sub-nodes:
+----------------------------------------------------
+ - function: Mux function for the specified pins.
+ - bias-pull-up: Enable weak pull-up.
+ - bias-pull-down: Enable weak pull-down.
+ - input-enable: Set the pin as an input.
+ - output-low: Set the pin as an output level low.
+ - output-high: Set the pin as an output level high.
+ - microchip,digital: Enable digital I/O.
+ - microchip,analog: Enable analog I/O.
+
+Example:
+
+pic32_pinctrl: pinctrl@1f801400{
+	#address-cells = <1>;
+	#size-cells = <1>;
+	compatible = "microchip,pic32mzda-pinctrl";
+	reg = <0x1f801400 0x400>;
+	clocks = <&PBCLK1>;
+
+	pinctrl_uart2: pinctrl_uart2 {
+		uart2-tx {
+			pins = "G9";
+			function = "U2TX";
+			microchip,digital;
+			output-low;
+		};
+		uart2-rx {
+			pins = "B0";
+			function = "U2RX";
+			microchip,digital;
+			input-enable;
+		};
+	};
+};
+
+uart2: serial@1f822200 {
+	compatible = "microchip,pic32mzda-uart";
+	reg = <0x1f822200 0x50>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_uart2>;
+};
diff --git a/Documentation/devicetree/bindings/pinctrl/nxp,lpc1850-scu.txt b/Documentation/devicetree/bindings/pinctrl/nxp,lpc1850-scu.txt
index df0309c57505..bd8b0c69fa44 100644
--- a/Documentation/devicetree/bindings/pinctrl/nxp,lpc1850-scu.txt
+++ b/Documentation/devicetree/bindings/pinctrl/nxp,lpc1850-scu.txt
@@ -22,6 +22,10 @@ The following generic nodes are supported:
  - input-schmitt-disable
  - slew-rate
 
+NXP specific properties:
+ - nxp,gpio-pin-interrupt : Assign pin to gpio pin interrupt controller
+			    irq number 0 to 7. See example below.
+
 Not all pins support all properties so either refer to the NXP 1850/4350
 user manual or the pin table in the pinctrl-lpc18xx driver for supported
 pin properties.
@@ -54,4 +58,14 @@ pinctrl: pinctrl@40086000 {
 			bias-disable;
 		};
 	};
+
+	gpio_joystick_pins: gpio-joystick-pins {
+		gpio_joystick_1_cfg {
+			pins =  "p9_0";
+			function = "gpio";
+			nxp,gpio-pin-interrupt = <0>;
+			input-enable;
+			bias-disable;
+		};
+	};
 };
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt
index 9ffb0b276bb4..17631d0a9af7 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt
@@ -6,6 +6,7 @@ Required properties:
 - compatible: value should be one of the following.
 	"mediatek,mt2701-pinctrl", compatible with mt2701 pinctrl.
 	"mediatek,mt6397-pinctrl", compatible with mt6397 pinctrl.
+	"mediatek,mt7623-pinctrl", compatible with mt7623 pinctrl.
 	"mediatek,mt8127-pinctrl", compatible with mt8127 pinctrl.
 	"mediatek,mt8135-pinctrl", compatible with mt8135 pinctrl.
 	"mediatek,mt8173-pinctrl", compatible with mt8173 pinctrl.
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq4019-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,ipq4019-pinctrl.txt
new file mode 100644
index 000000000000..cfb8500dd56b
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq4019-pinctrl.txt
@@ -0,0 +1,74 @@
+Qualcomm Atheros IPQ4019 TLMM block
+
+This is the Top Level Mode Multiplexor block found on the Qualcomm IPQ8019
+platform, it provides pinctrl, pinmux, pinconf, and gpiolib facilities.
+
+Required properties:
+- compatible: "qcom,ipq4019-pinctrl"
+- reg: Should be the base address and length of the TLMM block.
+- interrupts: Should be the parent IRQ of the TLMM block.
+- interrupt-controller: Marks the device node as an interrupt controller.
+- #interrupt-cells: Should be two.
+- gpio-controller: Marks the device node as a GPIO controller.
+- #gpio-cells : Should be two.
+                The first cell is the gpio pin number and the
+                second cell is used for optional parameters.
+
+Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
+a general description of GPIO and interrupt bindings.
+
+Please refer to pinctrl-bindings.txt in this directory for details of the
+common pinctrl bindings used by client devices, including the meaning of the
+phrase "pin configuration node".
+
+The pin configuration nodes act as a container for an abitrary number of
+subnodes. Each of these subnodes represents some desired configuration for a
+pin, a group, or a list of pins or groups. This configuration can include the
+mux function to select on those pin(s)/group(s), and various pin configuration
+parameters, such as pull-up, drive strength, etc.
+
+The name of each subnode is not important; all subnodes should be enumerated
+and processed purely based on their content.
+
+Each subnode only affects those parameters that are explicitly listed. In
+other words, a subnode that lists a mux function but no pin configuration
+parameters implies no information about any pin configuration parameters.
+Similarly, a pin subnode that describes a pullup parameter implies no
+information about e.g. the mux function.
+
+
+The following generic properties as defined in pinctrl-bindings.txt are valid
+to specify in a pin configuration subnode:
+ pins, function, bias-disable, bias-pull-down, bias-pull,up, drive-strength.
+
+Non-empty subnodes must specify the 'pins' property.
+Note that not all properties are valid for all pins.
+
+
+Valid values for qcom,pins are:
+  gpio0-gpio99
+    Supports mux, bias and drive-strength
+
+Valid values for qcom,function are:
+gpio, blsp_uart1, blsp_i2c0, blsp_i2c1, blsp_uart0, blsp_spi1, blsp_spi0
+
+Example:
+
+	tlmm: pinctrl@1000000 {
+		compatible = "qcom,ipq4019-pinctrl";
+		reg = <0x1000000 0x300000>;
+
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupts = <0 208 0>;
+
+		serial_pins: serial_pinmux {
+			mux {
+				pins = "gpio60", "gpio61";
+				function = "blsp_uart0";
+				bias-disable;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
index 0cd701b1947f..c68b9554561f 100644
--- a/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
@@ -22,7 +22,7 @@ Required properties for iomux controller:
   - compatible: one of "rockchip,rk2928-pinctrl", "rockchip,rk3066a-pinctrl"
 		       "rockchip,rk3066b-pinctrl", "rockchip,rk3188-pinctrl"
 		       "rockchip,rk3228-pinctrl", "rockchip,rk3288-pinctrl"
-		       "rockchip,rk3368-pinctrl"
+		       "rockchip,rk3368-pinctrl", "rockchip,rk3399-pinctrl"
   - rockchip,grf: phandle referencing a syscon providing the
 	 "general register files"
 
diff --git a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
new file mode 100644
index 000000000000..7b4800cc251e
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
@@ -0,0 +1,126 @@
+* STM32 GPIO and Pin Mux/Config controller
+
+STMicroelectronics's STM32 MCUs intregrate a GPIO and Pin mux/config hardware
+controller. It controls the input/output settings on the available pins and
+also provides ability to multiplex and configure the output of various on-chip
+controllers onto these pads.
+
+Pin controller node:
+Required properies:
+ - compatible: value should be one of the following:
+   (a) "st,stm32f429-pinctrl"
+ - #address-cells: The value of this property must be 1
+ - #size-cells	: The value of this property must be 1
+ - ranges	: defines mapping between pin controller node (parent) to
+   gpio-bank node (children).
+ - pins-are-numbered: Specify the subnodes are using numbered pinmux to
+   specify pins.
+
+GPIO controller/bank node:
+Required properties:
+ - gpio-controller : Indicates this device is a GPIO controller
+ - #gpio-cells	  : Should be two.
+			The first cell is the pin number
+			The second one is the polarity:
+				- 0 for active high
+				- 1 for active low
+ - reg		  : The gpio address range, relative to the pinctrl range
+ - clocks	  : clock that drives this bank
+ - st,bank-name	  : Should be a name string for this bank as specified in
+   the datasheet
+
+Optional properties:
+ - reset:	  : Reference to the reset controller
+
+Example:
+#include <dt-bindings/pinctrl/stm32f429-pinfunc.h>
+...
+
+	pin-controller {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "st,stm32f429-pinctrl";
+		ranges = <0 0x40020000 0x3000>;
+		pins-are-numbered;
+
+		gpioa: gpio@40020000 {
+			gpio-controller;
+			#gpio-cells = <2>;
+			reg = <0x0 0x400>;
+			resets = <&reset_ahb1 0>;
+			st,bank-name = "GPIOA";
+		};
+		...
+		pin-functions nodes follow...
+	};
+
+Contents of function subnode node:
+----------------------------------
+Subnode format
+A pinctrl node should contain at least one subnode representing the
+pinctrl group available on the machine. Each subnode will list the
+pins it needs, and how they should be configured, with regard to muxer
+configuration, pullups, drive, output high/low and output speed.
+
+    node {
+	pinmux = <PIN_NUMBER_PINMUX>;
+	GENERIC_PINCONFIG;
+    };
+
+Required properties:
+- pinmux: integer array, represents gpio pin number and mux setting.
+  Supported pin number and mux varies for different SoCs, and are defined in
+  dt-bindings/pinctrl/<soc>-pinfunc.h directly.
+  These defines are calculated as:
+    ((port * 16 + line) << 8) | function
+  With:
+    - port: The gpio port index (PA = 0, PB = 1, ..., PK = 11)
+    - line: The line offset within the port (PA0 = 0, PA1 = 1, ..., PA15 = 15)
+    - function: The function number, can be:
+      * 0 : GPIO
+      * 1 : Alternate Function 0
+      * 2 : Alternate Function 1
+      * 3 : Alternate Function 2
+      * ...
+      * 16 : Alternate Function 15
+      * 17 : Analog
+
+Optional properties:
+- GENERIC_PINCONFIG: is the generic pinconfig options to use.
+  Available options are:
+   - bias-disable,
+   - bias-pull-down,
+   - bias-pull-up,
+   - drive-push-pull,
+   - drive-open-drain,
+   - output-low
+   - output-high
+   - slew-rate = <x>, with x being:
+       < 0 > : Low speed
+       < 1 > : Medium speed
+       < 2 > : Fast speed
+       < 3 > : High speed
+
+Example:
+
+pin-controller {
+...
+	usart1_pins_a: usart1@0 {
+		pins1 {
+			pinmux = <STM32F429_PA9_FUNC_USART1_TX>;
+			bias-disable;
+			drive-push-pull;
+			slew-rate = <0>;
+		};
+		pins2 {
+			pinmux = <STM32F429_PA10_FUNC_USART1_RX>;
+			bias-disable;
+		};
+	};
+};
+
+&usart1 {
+	pinctrl-0 = <&usart1_pins_a>;
+	pinctrl-names = "default";
+	status = "okay";
+};
diff --git a/Documentation/devicetree/bindings/regmap/regmap.txt b/Documentation/devicetree/bindings/regmap/regmap.txt
index b494f8b8ef72..e98a9652ccc8 100644
--- a/Documentation/devicetree/bindings/regmap/regmap.txt
+++ b/Documentation/devicetree/bindings/regmap/regmap.txt
@@ -5,15 +5,18 @@ Index     Device     Endianness properties
 ---------------------------------------------------
 1         BE         'big-endian'
 2         LE         'little-endian'
+3	  Native     'native-endian'
 
 For one device driver, which will run in different scenarios above
 on different SoCs using the devicetree, we need one way to simplify
 this.
 
-Required properties:
-- {big,little}-endian: these are boolean properties, if absent
-  meaning that the CPU and the Device are in the same endianness mode,
-  these properties are for register values and all the buffers only.
+Optional properties:
+- {big,little,native}-endian: these are boolean properties, if absent
+  then the implementation will choose a default based on the device
+  being controlled.  These properties are for register values and all
+  the buffers only.  Native endian means that the CPU and device have
+  the same endianness.
 
 Examples:
 Scenario 1 : CPU in LE mode & device in LE mode.
diff --git a/Documentation/devicetree/bindings/regulator/act8945a-regulator.txt b/Documentation/devicetree/bindings/regulator/act8945a-regulator.txt
new file mode 100644
index 000000000000..5c80a7779552
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/act8945a-regulator.txt
@@ -0,0 +1,80 @@
+Device-Tree bindings for regulators of Active-semi ACT8945A Multi-Function Device
+
+Required properties:
+ - compatible: "active-semi,act8945a", please refer to ../mfd/act8945a.txt.
+
+Optional properties:
+- active-semi,vsel-high: Indicates if the VSEL pin is set to logic-high.
+  If this property is missing, assume the VSEL pin is set to logic-low.
+
+Optional input supply properties:
+  - vp1-supply: The input supply for REG_DCDC1
+  - vp2-supply: The input supply for REG_DCDC2
+  - vp3-supply: The input supply for REG_DCDC3
+  - inl45-supply: The input supply for REG_LDO1 and REG_LDO2
+  - inl67-supply: The input supply for REG_LDO3 and REG_LDO4
+
+Any standard regulator properties can be used to configure the single regulator.
+
+The valid names for regulators are:
+	REG_DCDC1, REG_DCDC2, REG_DCDC3, REG_LDO1, REG_LDO2, REG_LDO3, REG_LDO4.
+
+Example:
+	pmic@5b {
+		compatible = "active-semi,act8945a";
+		reg = <0x5b>;
+		status = "okay";
+
+		active-semi,vsel-high;
+
+		regulators {
+			vdd_1v35_reg: REG_DCDC1 {
+				regulator-name = "VDD_1V35";
+				regulator-min-microvolt = <1350000>;
+				regulator-max-microvolt = <1350000>;
+				regulator-always-on;
+			};
+
+			vdd_1v2_reg: REG_DCDC2 {
+				regulator-name = "VDD_1V2";
+				regulator-min-microvolt = <1100000>;
+				regulator-max-microvolt = <1300000>;
+				regulator-always-on;
+			};
+
+			vdd_3v3_reg: REG_DCDC3 {
+				regulator-name = "VDD_3V3";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vdd_fuse_reg: REG_LDO1 {
+				regulator-name = "VDD_FUSE";
+				regulator-min-microvolt = <2500000>;
+				regulator-max-microvolt = <2500000>;
+				regulator-always-on;
+			};
+
+			vdd_3v3_lp_reg: REG_LDO2 {
+				regulator-name = "VDD_3V3_LP";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vdd_led_reg: REG_LDO3 {
+				regulator-name = "VDD_LED";
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vdd_sdhc_1v8_reg: REG_LDO4 {
+				regulator-name = "VDD_SDHC_1V8";
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/regulator/hisilicon,hi655x-regulator.txt b/Documentation/devicetree/bindings/regulator/hisilicon,hi655x-regulator.txt
new file mode 100644
index 000000000000..14cfdc564159
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/hisilicon,hi655x-regulator.txt
@@ -0,0 +1,29 @@
+Hisilicon Hi655x Voltage regulators
+
+Note:
+The Hi655x regulator control is managed by Hi655x PMIC.
+So the node of this regulator must be child node of Hi655x
+PMIC node.
+
+The driver uses the regulator core framework, so please also
+take the bindings of regulator.txt for reference.
+
+The valid names for regulators are:
+
+LDO2_2V8 LDO7_SDIO LDO10_2V85 LDO13_1V8 LDO14_2V8
+LDO15_1V8 LDO17_2V5 LDO19_3V0 LDO21_1V8 LDO22_1V2
+
+Example:
+        pmic: pmic@f8000000 {
+                compatible = "hisilicon,hi655x-pmic";
+		...
+		regulators {
+			ldo2: LDO2@a21 {
+				regulator-name = "LDO2_2V8";
+				regulator-min-microvolt = <2500000>;
+				regulator-max-microvolt = <3200000>;
+				regulator-enable-ramp-delay = <120>;
+			};
+			...
+		}
+	}
diff --git a/Documentation/devicetree/bindings/regulator/lp872x.txt b/Documentation/devicetree/bindings/regulator/lp872x.txt
index 78183182dad9..ca58a68ffdf1 100644
--- a/Documentation/devicetree/bindings/regulator/lp872x.txt
+++ b/Documentation/devicetree/bindings/regulator/lp872x.txt
@@ -28,6 +28,7 @@ Optional properties:
   - ti,dvs-gpio: GPIO specifier for external DVS pin control of LP872x devices.
   - ti,dvs-vsel: DVS selector. 0 = SEL_V1, 1 = SEL_V2.
   - ti,dvs-state: initial DVS pin state. 0 = DVS_LOW, 1 = DVS_HIGH.
+  - enable-gpios: GPIO specifier for EN pin control of LP872x devices.
 
   Sub nodes for regulator_init_data
     LP8720 has maximum 6 nodes. (child name: ldo1 ~ 5 and buck)
diff --git a/Documentation/devicetree/bindings/regulator/max77802.txt b/Documentation/devicetree/bindings/regulator/max77802.txt
index 09d796ed48be..879e98d3b9aa 100644
--- a/Documentation/devicetree/bindings/regulator/max77802.txt
+++ b/Documentation/devicetree/bindings/regulator/max77802.txt
@@ -60,7 +60,7 @@ The possible values for "regulator-initial-mode" and "regulator-mode" are:
 	1: Normal regulator voltage output mode.
 	3: Low Power which reduces the quiescent current down to only 1uA
 
-The list of valid modes are defined in the dt-bindings/clock/maxim,max77802.h
+The valid modes list is defined in the dt-bindings/regulator/maxim,max77802.h
 header and can be included by device tree source files.
 
 The standard "regulator-mode" property can only be used for regulators that
diff --git a/Documentation/devicetree/bindings/regulator/regulator-max77620.txt b/Documentation/devicetree/bindings/regulator/regulator-max77620.txt
new file mode 100644
index 000000000000..b3c8ca672024
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/regulator-max77620.txt
@@ -0,0 +1,200 @@
+Regulator DT binding for MAX77620 Power management IC from Maxim Semiconductor.
+
+Device has multiple DCDC(sd[0-3] and LDOs(ldo[0-8]). The input supply
+of these regulators are defined under parent device node.
+Details of regulator properties are defined as child node under
+sub-node "regulators" which is child node of device node.
+
+Please refer file <Documentation/devicetree/bindings/regulator/regulator.txt>
+for common regulator bindings used by client.
+
+Following are properties of parent node related to regulators.
+
+Optional properties:
+-------------------
+The input supply of regulators are the optional properties on the
+parent device node. The input supply of these regulators are provided
+through following properties:
+in-sd0-supply:		Input supply for SD0, INA-SD0 or INB-SD0 pins.
+in-sd1-supply:		Input supply for SD1.
+in-sd2-supply:		Input supply for SD2.
+in-sd3-supply:		Input supply for SD3.
+in-ldo0-1-supply:	Input supply for LDO0 and LDO1.
+in-ldo2-supply:		Input supply for LDO2.
+in-ldo3-5-supply:	Input supply for LDO3 and LDO5
+in-ldo4-6-supply:	Input supply for LDO4 and LDO6.
+in-ldo7-8-supply:	Input supply for LDO7 and LDO8.
+
+Optional sub nodes for regulators under "regulators" subnode:
+------------------------------------------------------------
+The subnodes name is the name of regulator and it must be one of:
+	sd[0-3], ldo[0-8]
+
+Each sub-node should contain the constraints and initialization
+information for that regulator. The definition for each of these
+nodes is defined using the standard binding for regulators found at
+<Documentation/devicetree/bindings/regulator/regulator.txt>.
+
+Theres are also additional properties for SD/LDOs. These additional properties
+are required to configure FPS configuration parameters for SDs and LDOs.
+Please refer <devicetree/bindings/mfd/max77620.txt> for more detail of Flexible
+Power Sequence (FPS).
+Following are additional properties:
+
+- maxim,active-fps-source:		FPS source for the regulators to get
+					enabled/disabled when system is in
+					active state.  Valid values are:
+					- MAX77620_FPS_SRC_0,
+						FPS source is FPS0.
+					- MAX77620_FPS_SRC_1,
+						FPS source is FPS1
+					- MAX77620_FPS_SRC_2 and
+						FPS source is FPS2
+					- MAX77620_FPS_SRC_NONE.
+						Regulator is not controlled
+						by FPS events and it gets
+						enabled/disabled by register
+						access.
+					Absence of this property will leave
+					the FPS configuration register for that
+					regulator to default configuration.
+
+- maxim,active-fps-power-up-slot:	Sequencing event slot number on which
+					the regulator get enabled when
+					master FPS input event set to HIGH.
+					Valid values are 0 to 7.
+					This is applicable if FPS source is
+					selected as FPS0, FPS1 or FPS2.
+			
+- maxim,active-fps-power-down-slot:	Sequencing event slot number on which
+					the regulator get disabled when master
+					FPS input event set to LOW.
+					Valid values are 0 to 7.
+					This is applicable if FPS source is
+					selected as FPS0, FPS1 or FPS2.
+			
+- maxim,suspend-fps-source:		This is same as property
+					"maxim,active-fps-source" but value
+					get configured when system enters in
+					to suspend state.
+
+- maxim,suspend-fps-power-up-slot:	This is same as property
+					"maxim,active-fps-power-up-slot" but
+					this value get configured into FPS
+					configuration register when system
+					enters into suspend.
+					This is applicable if suspend state
+					FPS source is selected as FPS0, FPS1 or
+
+- maxim,suspend-fps-power-down-slot:	This is same as property
+					"maxim,active-fps-power-down-slot" but
+					this value get configured into FPS
+					configuration register when system
+					enters into suspend.
+					This is applicable if suspend state
+					FPS source is selected as FPS0, FPS1 or
+					FPS2.
+
+Example:
+--------
+#include <dt-bindings/mfd/max77620.h>
+...
+max77620@3c {
+	in-ldo0-1-supply = <&max77620_sd2>;
+	in-ldo7-8-supply = <&max77620_sd2>;
+	regulators {
+		sd0 {
+			regulator-name = "vdd-core";
+			regulator-min-microvolt = <600000>;
+			regulator-max-microvolt = <1400000>;
+			regulator-boot-on;
+			regulator-always-on;
+			maxim,active-fps-source = <MAX77620_FPS_SRC_1>;
+		};
+
+		sd1 {
+			regulator-name = "vddio-ddr";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-always-on;
+			regulator-boot-on;
+			maxim,active-fps-source = <MAX77620_FPS_SRC_0>;
+		};
+
+		sd2 {
+			regulator-name = "vdd-pre-reg";
+			regulator-min-microvolt = <1350000>;
+			regulator-max-microvolt = <1350000>;
+		};
+
+		sd3 {
+			regulator-name = "vdd-1v8";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-always-on;
+			regulator-boot-on;
+		};
+
+		ldo0 {
+			regulator-name = "avdd-sys";
+			regulator-min-microvolt = <1200000>;
+			regulator-max-microvolt = <1200000>;
+			regulator-always-on;
+			regulator-boot-on;
+		};
+
+		ldo1 {
+			regulator-name = "vdd-pex";
+			regulator-min-microvolt = <1050000>;
+			regulator-max-microvolt = <1050000>;
+		};
+
+		ldo2 {
+			regulator-name = "vddio-sdmmc3";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <3300000>;
+		};
+
+		ldo3 {
+			regulator-name = "vdd-cam-hv";
+			regulator-min-microvolt = <2800000>;
+			regulator-max-microvolt = <2800000>;
+		};
+
+		ldo4 {
+			regulator-name = "vdd-rtc";
+			regulator-min-microvolt = <1250000>;
+			regulator-max-microvolt = <1250000>;
+			regulator-always-on;
+			regulator-boot-on;
+		};
+
+		ldo5 {
+			regulator-name = "avdd-ts-hv";
+			regulator-min-microvolt = <3000000>;
+			regulator-max-microvolt = <3000000>;
+		};
+
+		ldo6 {
+			regulator-name = "vdd-ts";
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-always-on;
+			regulator-boot-on;
+		};
+
+		ldo7 {
+			regulator-name = "vdd-gen-pll-edp";
+			regulator-min-microvolt = <1050000>;
+			regulator-max-microvolt = <1050000>;
+			regulator-always-on;
+			regulator-boot-on;
+		};
+
+		ldo8 {
+			regulator-name = "vdd-hdmi-dp";
+			regulator-min-microvolt = <1050000>;
+			regulator-max-microvolt = <1050000>;
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/regulator/regulator.txt b/Documentation/devicetree/bindings/regulator/regulator.txt
index 1d112fc456aa..ecfc593cac15 100644
--- a/Documentation/devicetree/bindings/regulator/regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/regulator.txt
@@ -44,6 +44,11 @@ Optional properties:
   any consumer request.
 - regulator-pull-down: Enable pull down resistor when the regulator is disabled.
 - regulator-over-current-protection: Enable over current protection.
+- regulator-active-discharge: tristate, enable/disable active discharge of
+  regulators. The values are:
+	0: Disable active discharge.
+	1: Enable active discharge.
+	Absence of this property will leave configuration to default.
 
 Deprecated properties:
 - regulator-compatible: If a regulator chip contains multiple
diff --git a/Documentation/devicetree/bindings/regulator/tps65217.txt b/Documentation/devicetree/bindings/regulator/tps65217.txt
index d18109657da6..4f05d208c95c 100644
--- a/Documentation/devicetree/bindings/regulator/tps65217.txt
+++ b/Documentation/devicetree/bindings/regulator/tps65217.txt
@@ -26,11 +26,7 @@ Example:
 		ti,pmic-shutdown-controller;
 
 		regulators {
-			#address-cells = <1>;
-			#size-cells = <0>;
-
 			dcdc1_reg: dcdc1 {
-				reg = <0>;
 				regulator-min-microvolt = <900000>;
 				regulator-max-microvolt = <1800000>;
 				regulator-boot-on;
@@ -38,7 +34,6 @@ Example:
 			};
 
 			dcdc2_reg: dcdc2 {
-				reg = <1>;
 				regulator-min-microvolt = <900000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-boot-on;
@@ -46,7 +41,6 @@ Example:
 			};
 
 			dcdc3_reg: dcc3 {
-				reg = <2>;
 				regulator-min-microvolt = <900000>;
 				regulator-max-microvolt = <1500000>;
 				regulator-boot-on;
@@ -54,7 +48,6 @@ Example:
 			};
 
 			ldo1_reg: ldo1 {
-				reg = <3>;
 				regulator-min-microvolt = <1000000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-boot-on;
@@ -62,7 +55,6 @@ Example:
 			};
 
 			ldo2_reg: ldo2 {
-				reg = <4>;
 				regulator-min-microvolt = <900000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-boot-on;
@@ -70,7 +62,6 @@ Example:
 			};
 
 			ldo3_reg: ldo3 {
-				reg = <5>;
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-boot-on;
@@ -78,7 +69,6 @@ Example:
 			};
 
 			ldo4_reg: ldo4 {
-				reg = <6>;
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-boot-on;
diff --git a/Documentation/devicetree/bindings/rng/brcm,bcm6368.txt b/Documentation/devicetree/bindings/rng/brcm,bcm6368.txt
new file mode 100644
index 000000000000..4b5ac600bfbd
--- /dev/null
+++ b/Documentation/devicetree/bindings/rng/brcm,bcm6368.txt
@@ -0,0 +1,17 @@
+BCM6368 Random number generator
+
+Required properties:
+
+- compatible : should be "brcm,bcm6368-rng"
+- reg : Specifies base physical address and size of the registers
+- clocks : phandle to clock-controller plus clock-specifier pair
+- clock-names : "ipsec" as a clock name
+
+Example:
+	random: rng@10004180 {
+		compatible = "brcm,bcm6368-rng";
+		reg = <0x10004180 0x14>;
+
+		clocks = <&periph_clk 18>;
+		clock-names = "ipsec";
+	};
diff --git a/Documentation/devicetree/bindings/rng/microchip,pic32-rng.txt b/Documentation/devicetree/bindings/rng/microchip,pic32-rng.txt
new file mode 100644
index 000000000000..c6d1003befb7
--- /dev/null
+++ b/Documentation/devicetree/bindings/rng/microchip,pic32-rng.txt
@@ -0,0 +1,17 @@
+* Microchip PIC32 Random Number Generator
+
+The PIC32 RNG provides a pseudo random number generator which can be seeded by
+another true random number generator.
+
+Required properties:
+- compatible : should be "microchip,pic32mzda-rng"
+- reg : Specifies base physical address and size of the registers.
+- clocks: clock phandle.
+
+Example:
+
+	rng: rng@1f8e6000 {
+		compatible = "microchip,pic32mzda-rng";
+		reg = <0x1f8e6000 0x1000>;
+		clocks = <&PBCLK5>;
+	};
diff --git a/Documentation/devicetree/bindings/rtc/alphascale,asm9260-rtc.txt b/Documentation/devicetree/bindings/rtc/alphascale,asm9260-rtc.txt
new file mode 100644
index 000000000000..76ebca568db9
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/alphascale,asm9260-rtc.txt
@@ -0,0 +1,19 @@
+* Alphascale asm9260 SoC Real Time Clock
+
+Required properties:
+- compatible: Should be "alphascale,asm9260-rtc"
+- reg: Physical base address of the controller and length
+       of memory mapped region.
+- interrupts: IRQ line for the RTC.
+- clocks: Reference to the clock entry.
+- clock-names: should contain:
+  * "ahb" for the SoC RTC clock
+
+Example:
+rtc0: rtc@800a0000 {
+	compatible = "alphascale,asm9260-rtc";
+	reg = <0x800a0000 0x100>;
+	clocks = <&acc CLKID_AHB_RTC>;
+	clock-names = "ahb";
+	interrupts = <2>;
+};
diff --git a/Documentation/devicetree/bindings/rtc/epson,rx6110.txt b/Documentation/devicetree/bindings/rtc/epson,rx6110.txt
new file mode 100644
index 000000000000..3dc313e01f77
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/epson,rx6110.txt
@@ -0,0 +1,39 @@
+Epson RX6110 Real Time Clock
+============================
+
+The Epson RX6110 can be used with SPI or I2C busses. The kind of
+bus depends on the SPISEL pin and can not be configured via software.
+
+I2C mode
+--------
+
+Required properties:
+  - compatible: should be: "epson,rx6110"
+  - reg : the I2C address of the device for I2C
+
+Example:
+
+	rtc: rtc@32 {
+		compatible = "epson,rx6110"
+		reg = <0x32>;
+	};
+
+SPI mode
+--------
+
+Required properties:
+  - compatible: should be: "epson,rx6110"
+  - reg: chip select number
+  - spi-cs-high: RX6110 needs chipselect high
+  - spi-cpha: RX6110 works with SPI shifted clock phase
+  - spi-cpol: RX6110 works with SPI inverse clock polarity
+
+Example:
+
+	rtc: rtc@3 {
+		compatible = "epson,rx6110"
+		reg = <3>
+		spi-cs-high;
+		spi-cpha;
+		spi-cpol;
+	};
diff --git a/Documentation/devicetree/bindings/rtc/maxim,ds3231.txt b/Documentation/devicetree/bindings/rtc/maxim,ds3231.txt
new file mode 100644
index 000000000000..ddef330d2709
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/maxim,ds3231.txt
@@ -0,0 +1,37 @@
+* Maxim DS3231 Real Time Clock
+
+Required properties:
+see: Documentation/devicetree/bindings/i2c/trivial-devices.txt
+
+Optional property:
+- #clock-cells: Should be 1.
+- clock-output-names:
+  overwrite the default clock names "ds3231_clk_sqw" and "ds3231_clk_32khz".
+
+Each clock is assigned an identifier and client nodes can use this identifier
+to specify the clock which they consume. Following indices are allowed:
+    - 0: square-wave output on the SQW pin
+    - 1: square-wave output on the 32kHz pin
+
+- interrupts: rtc alarm/event interrupt. When this property is selected,
+  clock on the SQW pin cannot be used.
+
+Example:
+
+ds3231: ds3231@51 {
+	compatible = "maxim,ds3231";
+	reg = <0x68>;
+	#clock-cells = <1>;
+};
+
+device1 {
+...
+	clocks = <&ds3231 0>;
+...
+};
+
+device2 {
+...
+	clocks = <&ds3231 1>;
+...
+};
diff --git a/Documentation/devicetree/bindings/rtc/microchip,pic32-rtc.txt b/Documentation/devicetree/bindings/rtc/microchip,pic32-rtc.txt
new file mode 100644
index 000000000000..180b7144bfcc
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/microchip,pic32-rtc.txt
@@ -0,0 +1,21 @@
+* Microchip PIC32 Real Time Clock and Calendar
+
+The RTCC keeps time in hours, minutes, and seconds, and one half second. It
+provides a calendar in weekday, date, month, and year. It also provides a
+configurable alarm.
+
+Required properties:
+- compatible: should be: "microchip,pic32mzda-rtc"
+- reg: physical base address of the controller and length of memory mapped
+    region.
+- interrupts: RTC alarm/event interrupt
+- clocks: clock phandle
+
+Example:
+
+	rtc: rtc@1f8c0000 {
+		compatible = "microchip,pic32mzda-rtc";
+		reg = <0x1f8c0000 0x60>;
+		interrupts = <166 IRQ_TYPE_EDGE_RISING>;
+		clocks = <&PBCLK6>;
+	};
diff --git a/Documentation/devicetree/bindings/rtc/s3c-rtc.txt b/Documentation/devicetree/bindings/rtc/s3c-rtc.txt
index ac2fcd6ff4b8..1068ffce9f91 100644
--- a/Documentation/devicetree/bindings/rtc/s3c-rtc.txt
+++ b/Documentation/devicetree/bindings/rtc/s3c-rtc.txt
@@ -14,6 +14,10 @@ Required properties:
   interrupt number is the rtc alarm interrupt and second interrupt number
   is the rtc tick interrupt. The number of cells representing a interrupt
   depends on the parent interrupt controller.
+- clocks: Must contain a list of phandle and clock specifier for the rtc
+          and source clocks.
+- clock-names: Must contain "rtc" and "rtc_src" entries sorted in the
+               same order as the clocks property.
 
 Example:
 
@@ -21,4 +25,6 @@ Example:
 		compatible = "samsung,s3c6410-rtc";
 		reg = <0x10070000 0x100>;
 		interrupts = <44 0 45 0>;
+		clocks = <&clock CLK_RTC>, <&s2mps11_osc S2MPS11_CLK_AP>;
+		clock-names = "rtc", "rtc_src";
 	};
diff --git a/Documentation/devicetree/bindings/scsi/hisilicon-sas.txt b/Documentation/devicetree/bindings/scsi/hisilicon-sas.txt
index f67e761bcc18..bf2411f366e5 100644
--- a/Documentation/devicetree/bindings/scsi/hisilicon-sas.txt
+++ b/Documentation/devicetree/bindings/scsi/hisilicon-sas.txt
@@ -5,6 +5,7 @@ The HiSilicon SAS controller supports SAS/SATA.
 Main node required properties:
   - compatible : value should be as follows:
 	(a) "hisilicon,hip05-sas-v1" for v1 hw in hip05 chipset
+	(b) "hisilicon,hip06-sas-v2" for v2 hw in hip06 chipset
   - sas-addr : array of 8 bytes for host SAS address
   - reg : Address and length of the SAS register
   - hisilicon,sas-syscon: phandle of syscon used for sas control
@@ -13,7 +14,7 @@ Main node required properties:
   - ctrl-clock-ena-reg : offset to controller clock enable register in ctrl reg
   - queue-count : number of delivery and completion queues in the controller
   - phy-count : number of phys accessible by the controller
-  - interrupts : Interrupts for phys, completion queues, and fatal
+  - interrupts : For v1 hw: Interrupts for phys, completion queues, and fatal
 		sources; the interrupts are ordered in 3 groups, as follows:
 			- Phy interrupts
 			- Completion queue interrupts
@@ -30,6 +31,24 @@ Main node required properties:
 		Fatal interrupts : the fatal interrupts are ordered as follows:
 			- ECC
 			- AXI bus
+		For v2 hw: Interrupts for phys, Sata, and completion queues;
+		the interrupts are ordered in 3 groups, as follows:
+			- Phy interrupts
+			- Sata interrupts
+			- Completion queue interrupts
+		Phy interrupts : Each controller has 2 phy interrupts:
+			- phy up/down
+			- channel interrupt
+		Sata interrupts : Each phy on the controller has 1 Sata
+			interrupt. The interrupts are ordered in increasing
+			order.
+		Completion queue interrupts : each completion queue has 1
+			interrupt source. The interrupts are ordered in
+			increasing order.
+
+Optional main node properties:
+ - hip06-sas-v2-quirk-amt : when set, indicates that the v2 controller has the
+			    "am-max-transmissions" limitation.
 
 Example:
 	sas0: sas@c1000000 {
diff --git a/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt b/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt
index 35ae1fb3537f..ed94c217c98d 100644
--- a/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt
+++ b/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt
@@ -9,7 +9,7 @@ Optional properties:
 - fsl,uart-has-rtscts : Indicate the uart has rts and cts
 - fsl,irda-mode : Indicate the uart supports irda mode
 - fsl,dte-mode : Indicate the uart works in DTE mode. The uart works
-                  is DCE mode by default.
+                  in DCE mode by default.
 
 Note: Each uart controller should have an alias correctly numbered
 in "aliases" node.
diff --git a/Documentation/devicetree/bindings/sound/cs4271.txt b/Documentation/devicetree/bindings/sound/cs4271.txt
index e2cd1d7539e5..6e699ceabacd 100644
--- a/Documentation/devicetree/bindings/sound/cs4271.txt
+++ b/Documentation/devicetree/bindings/sound/cs4271.txt
@@ -33,12 +33,19 @@ Optional properties:
 	Note that this is not needed in case the clocks are stable
 	throughout the entire runtime of the codec.
 
+ - vd-supply:	Digital power
+ - vl-supply:	Logic power
+ - va-supply:	Analog Power
+
 Examples:
 
 	codec_i2c: cs4271@10 {
 		compatible = "cirrus,cs4271";
 		reg = <0x10>;
 		reset-gpio = <&gpio 23 0>;
+		vd-supply = <&vdd_3v3_reg>;
+		vl-supply = <&vdd_3v3_reg>;
+		va-supply = <&vdd_3v3_reg>;
 	};
 
 	codec_spi: cs4271@0 {
diff --git a/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt b/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt
index ce55c0a6f757..4da41bf1888e 100644
--- a/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt
+++ b/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt
@@ -30,6 +30,8 @@ The compatible list for this generic sound card currently:
  "fsl,imx-audio-sgtl5000"
  (compatible with Documentation/devicetree/bindings/sound/imx-audio-sgtl5000.txt)
 
+ "fsl,imx-audio-wm8960"
+
 Required properties:
 
   - compatible		: Contains one of entries in the compatible list.
diff --git a/Documentation/devicetree/bindings/sparc_sun_oracle_rng.txt b/Documentation/devicetree/bindings/sparc_sun_oracle_rng.txt
new file mode 100644
index 000000000000..b0b211194c71
--- /dev/null
+++ b/Documentation/devicetree/bindings/sparc_sun_oracle_rng.txt
@@ -0,0 +1,30 @@
+HWRNG support for the n2_rng driver
+
+Required properties:
+- reg		: base address to sample from
+- compatible	: should contain one of the following
+	RNG versions:
+	- 'SUNW,n2-rng' for Niagara 2 Platform (SUN UltraSPARC T2 CPU)
+	- 'SUNW,vf-rng' for Victoria Falls Platform (SUN UltraSPARC T2 Plus CPU)
+	- 'SUNW,kt-rng' for Rainbow/Yosemite Falls Platform (SUN SPARC T3/T4), (UltraSPARC KT/Niagara 3 - development names)
+	more recent systems (after Oracle acquisition of SUN)
+	- 'ORCL,m4-rng' for SPARC T5/M5
+	- 'ORCL,m7-rng' for SPARC T7/M7
+
+Examples:
+/* linux LDOM on SPARC T5-2 */
+Node 0xf029a4f4
+	.node:  f029a4f4
+	rng-#units:  00000002
+	compatible: 'ORCL,m4-rng'
+	reg:  0000000e
+	name: 'random-number-generator'
+
+/* solaris on SPARC M7-8 */
+Node 0xf028c08c
+	rng-#units:  00000003
+	compatible: 'ORCL,m7-rng'
+	reg:  0000000e
+	name:  'random-number-generator'
+
+PS: see as well prtconfs.git by DaveM
diff --git a/Documentation/devicetree/bindings/spi/adi,axi-spi-engine.txt b/Documentation/devicetree/bindings/spi/adi,axi-spi-engine.txt
new file mode 100644
index 000000000000..8a18d71e6879
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/adi,axi-spi-engine.txt
@@ -0,0 +1,31 @@
+Analog Devices AXI SPI Engine controller Device Tree Bindings
+
+Required properties:
+- compatible		: Must be "adi,axi-spi-engine-1.00.a""
+- reg			: Physical base address and size of the register map.
+- interrupts		: Property with a value describing the interrupt
+			  number.
+- clock-names		: List of input clock names - "s_axi_aclk", "spi_clk"
+- clocks		: Clock phandles and specifiers (See clock bindings for
+			  details on clock-names and clocks).
+- #address-cells	: Must be <1>
+- #size-cells		: Must be <0>
+
+Optional subnodes:
+	Subnodes are use to represent the SPI slave devices connected to the SPI
+	master. They follow the generic SPI bindings as outlined in spi-bus.txt.
+
+Example:
+
+    spi@@44a00000 {
+		compatible = "adi,axi-spi-engine-1.00.a";
+		reg = <0x44a00000 0x1000>;
+		interrupts = <0 56 4>;
+		clocks = <&clkc 15 &clkc 15>;
+		clock-names = "s_axi_aclk", "spi_clk";
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		/* SPI devices */
+    };
diff --git a/Documentation/devicetree/bindings/spi/icpdas-lp8841-spi-rtc.txt b/Documentation/devicetree/bindings/spi/icpdas-lp8841-spi-rtc.txt
new file mode 100644
index 000000000000..852b651f3bc5
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/icpdas-lp8841-spi-rtc.txt
@@ -0,0 +1,54 @@
+* ICP DAS LP-8841 SPI Controller for RTC
+
+ICP DAS LP-8841 contains a DS-1302 RTC. RTC is connected to an IO
+memory register, which acts as an SPI master device.
+
+The device uses the standard MicroWire half-duplex transfer timing.
+Master output is set on low clock and sensed by the RTC on the rising
+edge. Master input is set by the RTC on the trailing edge and is sensed
+by the master on low clock.
+
+Required properties:
+
+- #address-cells: should be 1
+
+- #size-cells: should be 0
+
+- compatible: should be "icpdas,lp8841-spi-rtc"
+
+- reg: should provide IO memory address
+
+Requirements to SPI slave nodes:
+
+- There can be only one slave device.
+
+- The spi slave node should claim the following flags which are
+  required by the spi controller.
+
+  - spi-3wire: The master itself has only 3 wire. It cannor work in
+    full duplex mode.
+
+  - spi-cs-high: DS-1302 has active high chip select line. The master
+    doesn't support active low.
+
+  - spi-lsb-first: DS-1302 requires least significant bit first
+    transfers. The master only support this type of bit ordering.
+
+
+Example:
+
+spi@901c {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	compatible = "icpdas,lp8841-spi-rtc";
+	reg = <0x901c 0x1>;
+
+	rtc@0 {
+		compatible = "maxim,ds1302";
+		reg = <0>;
+		spi-max-frequency = <500000>;
+		spi-3wire;
+		spi-lsb-first;
+		spi-cs-high;
+	};
+};
diff --git a/Documentation/devicetree/bindings/spi/spi-rockchip.txt b/Documentation/devicetree/bindings/spi/spi-rockchip.txt
index 0c491bda4c65..1b14d69d8903 100644
--- a/Documentation/devicetree/bindings/spi/spi-rockchip.txt
+++ b/Documentation/devicetree/bindings/spi/spi-rockchip.txt
@@ -9,6 +9,7 @@ Required Properties:
     "rockchip,rk3066-spi" for rk3066.
     "rockchip,rk3188-spi", "rockchip,rk3066-spi" for rk3188.
     "rockchip,rk3288-spi", "rockchip,rk3066-spi" for rk3288.
+    "rockchip,rk3399-spi", "rockchip,rk3066-spi" for rk3399.
 - reg: physical base address of the controller and length of memory mapped
        region.
 - interrupts: The interrupt number to the cpu. The interrupt specifier format
diff --git a/Documentation/devicetree/bindings/spi/spi-xilinx.txt b/Documentation/devicetree/bindings/spi/spi-xilinx.txt
new file mode 100644
index 000000000000..c7b7856bd528
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/spi-xilinx.txt
@@ -0,0 +1,22 @@
+Xilinx SPI controller Device Tree Bindings
+-------------------------------------------------
+
+Required properties:
+- compatible		: Should be "xlnx,xps-spi-2.00.a" or "xlnx,xps-spi-2.00.b"
+- reg			: Physical base address and size of SPI registers map.
+- interrupts		: Property with a value describing the interrupt
+			  number.
+- interrupt-parent	: Must be core interrupt controller
+
+Optional properties:
+- xlnx,num-ss-bits	: Number of chip selects used.
+
+Example:
+	axi_quad_spi@41e00000 {
+			compatible = "xlnx,xps-spi-2.00.a";
+			interrupt-parent = <&intc>;
+			interrupts = <0 31 1>;
+			reg = <0x41e00000 0x10000>;
+			xlnx,num-ss-bits = <0x1>;
+	};
+
diff --git a/Documentation/devicetree/bindings/thermal/rcar-thermal.txt b/Documentation/devicetree/bindings/thermal/rcar-thermal.txt
index 332e625f6ed0..e5ee3f159893 100644
--- a/Documentation/devicetree/bindings/thermal/rcar-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/rcar-thermal.txt
@@ -1,8 +1,9 @@
 * Renesas R-Car Thermal
 
 Required properties:
-- compatible		: "renesas,thermal-<soctype>", "renesas,rcar-thermal"
-			  as fallback.
+- compatible		: "renesas,thermal-<soctype>",
+			   "renesas,rcar-gen2-thermal" (with thermal-zone) or
+			   "renesas,rcar-thermal" (without thermal-zone) as fallback.
 			  Examples with soctypes are:
 			    - "renesas,thermal-r8a73a4" (R-Mobile APE6)
 			    - "renesas,thermal-r8a7779" (R-Car H1)
@@ -36,3 +37,35 @@ thermal@e61f0000 {
 		0xe61f0300 0x38>;
 	interrupts = <0 69 IRQ_TYPE_LEVEL_HIGH>;
 };
+
+Example (with thermal-zone):
+
+thermal-zones {
+	cpu_thermal: cpu-thermal {
+		polling-delay-passive	= <1000>;
+		polling-delay		= <5000>;
+
+		thermal-sensors = <&thermal>;
+
+		trips {
+			cpu-crit {
+				temperature	= <115000>;
+				hysteresis	= <0>;
+				type		= "critical";
+			};
+		};
+		cooling-maps {
+		};
+	};
+};
+
+thermal: thermal@e61f0000 {
+	compatible =	"renesas,thermal-r8a7790",
+			"renesas,rcar-gen2-thermal",
+			"renesas,rcar-thermal";
+	reg = <0 0xe61f0000 0 0x14>, <0 0xe61f0100 0 0x38>;
+	interrupts = <0 69 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&mstp5_clks R8A7790_CLK_THERMAL>;
+	power-domains = <&cpg_clocks>;
+	#thermal-sensor-cells = <0>;
+};
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 72e2c5a2b327..83700da22b79 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -120,6 +120,7 @@ intercontrol	Inter Control Group
 invensense	InvenSense Inc.
 isee	ISEE 2007 S.L.
 isil	Intersil
+issi	Integrated Silicon Solutions Inc.
 jedec	JEDEC Solid State Technology Association
 karo	Ka-Ro electronics GmbH
 keymile	Keymile GmbH
@@ -170,6 +171,7 @@ opencores	OpenCores.org
 option	Option NV
 ortustech	Ortus Technology Co., Ltd.
 ovti	OmniVision Technologies
+ORCL	Oracle Corporation
 panasonic	Panasonic Corporation
 parade	Parade Technologies Inc.
 pericom	Pericom Technology Inc.
@@ -204,6 +206,7 @@ seagate	Seagate Technology PLC
 semtech	Semtech Corporation
 sgx	SGX Sensortech
 sharp	Sharp Corporation
+si-en	Si-En Technology Ltd.
 sigma	Sigma Designs, Inc.
 sil	Silicon Image
 silabs	Silicon Laboratories
@@ -227,6 +230,7 @@ startek	Startek
 ste	ST-Ericsson
 stericsson	ST-Ericsson
 synology	Synology, Inc.
+SUNW	Sun Microsystems, Inc
 tbs	TBS Technologies
 tcl	Toby Churchill Ltd.
 technologic	Technologic Systems
diff --git a/Documentation/dvb/README.dvb-usb b/Documentation/dvb/README.dvb-usb
index 669dc6ce4330..6f4b12f7b844 100644
--- a/Documentation/dvb/README.dvb-usb
+++ b/Documentation/dvb/README.dvb-usb
@@ -190,7 +190,7 @@ and watch another one.
 Patches, comments and suggestions are very very welcome.
 
 3. Acknowledgements
-   Amaury Demol (ademol@dibcom.fr) and Francois Kanounnikoff from DiBcom for
+   Amaury Demol (Amaury.Demol@parrot.com) and Francois Kanounnikoff from DiBcom for
     providing specs, code and help, on which the dvb-dibusb, dib3000mb and
     dib3000mc are based.
 
diff --git a/Documentation/filesystems/efivarfs.txt b/Documentation/filesystems/efivarfs.txt
index c477af086e65..686a64bba775 100644
--- a/Documentation/filesystems/efivarfs.txt
+++ b/Documentation/filesystems/efivarfs.txt
@@ -14,3 +14,10 @@ filesystem.
 efivarfs is typically mounted like this,
 
 	mount -t efivarfs none /sys/firmware/efi/efivars
+
+Due to the presence of numerous firmware bugs where removing non-standard
+UEFI variables causes the system firmware to fail to POST, efivarfs
+files that are not well-known standardized variables are created
+as immutable files.  This doesn't prevent removal - "chattr -i" will work -
+but it does prevent this kind of failure from being accomplished
+accidentally.
diff --git a/Documentation/hwmon/adm1275 b/Documentation/hwmon/adm1275
index d697229e3c18..791bc0bd91e6 100644
--- a/Documentation/hwmon/adm1275
+++ b/Documentation/hwmon/adm1275
@@ -14,6 +14,10 @@ Supported chips:
     Prefix: 'adm1276'
     Addresses scanned: -
     Datasheet: www.analog.com/static/imported-files/data_sheets/ADM1276.pdf
+  * Analog Devices ADM1278
+    Prefix: 'adm1278'
+    Addresses scanned: -
+    Datasheet: www.analog.com/static/imported-files/data_sheets/ADM1278.pdf
   * Analog Devices ADM1293/ADM1294
     Prefix: 'adm1293', 'adm1294'
     Addresses scanned: -
@@ -25,13 +29,15 @@ Author: Guenter Roeck <linux@roeck-us.net>
 Description
 -----------
 
-This driver supports hardware montoring for Analog Devices ADM1075, ADM1275,
-ADM1276, ADM1293, and ADM1294 Hot-Swap Controller and Digital Power Monitors.
+This driver supports hardware monitoring for Analog Devices ADM1075, ADM1275,
+ADM1276, ADM1278, ADM1293, and ADM1294 Hot-Swap Controller and Digital
+Power Monitors.
 
-ADM1075, ADM1275, ADM1276, ADM1293, and ADM1294 are hot-swap controllers that
-allow a circuit board to be removed from or inserted into a live backplane.
-They also feature current and voltage readback via an integrated 12
-bit analog-to-digital converter (ADC), accessed using a PMBus interface.
+ADM1075, ADM1275, ADM1276, ADM1278, ADM1293, and ADM1294 are hot-swap
+controllers that allow a circuit board to be removed from or inserted into
+a live backplane. They also feature current and voltage readback via an
+integrated 12 bit analog-to-digital converter (ADC), accessed using a
+PMBus interface.
 
 The driver is a client driver to the core PMBus driver. Please see
 Documentation/hwmon/pmbus for details on PMBus client drivers.
@@ -96,3 +102,14 @@ power1_reset_history	Write any value to reset history.
 
 			Power attributes are supported on ADM1075, ADM1276,
 			ADM1293, and ADM1294.
+
+temp1_input		Chip temperature.
+			Temperature attributes are only available on ADM1278.
+temp1_max		Maximum chip temperature.
+temp1_max_alarm		Temperature alarm.
+temp1_crit		Critical chip temperature.
+temp1_crit_alarm	Critical temperature high alarm.
+temp1_highest		Highest observed temperature.
+temp1_reset_history	Write any value to reset history.
+
+			Temperature attributes are supported on ADM1278.
diff --git a/Documentation/hwmon/lm25066 b/Documentation/hwmon/lm25066
index b34c3de5c1bc..2cb20ebb234d 100644
--- a/Documentation/hwmon/lm25066
+++ b/Documentation/hwmon/lm25066
@@ -36,7 +36,7 @@ Author: Guenter Roeck <linux@roeck-us.net>
 Description
 -----------
 
-This driver supports hardware montoring for National Semiconductor / TI LM25056,
+This driver supports hardware monitoring for National Semiconductor / TI LM25056,
 LM25063, LM25066, LM5064, and LM5066 Power Management, Monitoring, Control, and
 Protection ICs.
 
diff --git a/Documentation/hwmon/ltc2990 b/Documentation/hwmon/ltc2990
new file mode 100644
index 000000000000..c25211e90bdc
--- /dev/null
+++ b/Documentation/hwmon/ltc2990
@@ -0,0 +1,43 @@
+Kernel driver ltc2990
+=====================
+
+Supported chips:
+  * Linear Technology LTC2990
+    Prefix: 'ltc2990'
+    Addresses scanned: -
+    Datasheet: http://www.linear.com/product/ltc2990
+
+Author: Mike Looijmans <mike.looijmans@topic.nl>
+
+
+Description
+-----------
+
+LTC2990 is a Quad I2C Voltage, Current and Temperature Monitor.
+The chip's inputs can measure 4 voltages, or two inputs together (1+2 and 3+4)
+can be combined to measure a differential voltage, which is typically used to
+measure current through a series resistor, or a temperature.
+
+This driver currently uses the 2x differential mode only. In order to support
+other modes, the driver will need to be expanded.
+
+
+Usage Notes
+-----------
+
+This driver does not probe for PMBus devices. You will have to instantiate
+devices explicitly.
+
+
+Sysfs attributes
+----------------
+
+The "curr*_input" measurements actually report the voltage drop across the
+input pins in microvolts. This is equivalent to the current through a 1mOhm
+sense resistor. Divide the reported value by the actual sense resistor value
+in mOhm to get the actual value.
+
+in0_input     Voltage at Vcc pin in millivolt (range 2.5V to 5V)
+temp1_input   Internal chip temperature in millidegrees Celcius
+curr1_input   Current in mA across v1-v2 assuming a 1mOhm sense resistor.
+curr2_input   Current in mA across v3-v4 assuming a 1mOhm sense resistor.
diff --git a/Documentation/hwmon/max16064 b/Documentation/hwmon/max16064
index d59cc7829bec..265370f5cb82 100644
--- a/Documentation/hwmon/max16064
+++ b/Documentation/hwmon/max16064
@@ -13,7 +13,7 @@ Author: Guenter Roeck <linux@roeck-us.net>
 Description
 -----------
 
-This driver supports hardware montoring for Maxim MAX16064 Quad Power-Supply
+This driver supports hardware monitoring for Maxim MAX16064 Quad Power-Supply
 Controller with Active-Voltage Output Control and PMBus Interface.
 
 The driver is a client driver to the core PMBus driver.
diff --git a/Documentation/hwmon/max34440 b/Documentation/hwmon/max34440
index 37cbf472a19d..f5b1fcaa9e4e 100644
--- a/Documentation/hwmon/max34440
+++ b/Documentation/hwmon/max34440
@@ -33,7 +33,7 @@ Author: Guenter Roeck <linux@roeck-us.net>
 Description
 -----------
 
-This driver supports hardware montoring for Maxim MAX34440 PMBus 6-Channel
+This driver supports hardware monitoring for Maxim MAX34440 PMBus 6-Channel
 Power-Supply Manager, MAX34441 PMBus 5-Channel Power-Supply Manager
 and Intelligent Fan Controller, and MAX34446 PMBus Power-Supply Data Logger.
 It also supports the MAX34460 and MAX34461 PMBus Voltage Monitor & Sequencers.
diff --git a/Documentation/hwmon/max8688 b/Documentation/hwmon/max8688
index e78078638b91..ca233bec7a8a 100644
--- a/Documentation/hwmon/max8688
+++ b/Documentation/hwmon/max8688
@@ -13,7 +13,7 @@ Author: Guenter Roeck <linux@roeck-us.net>
 Description
 -----------
 
-This driver supports hardware montoring for Maxim MAX8688 Digital Power-Supply
+This driver supports hardware monitoring for Maxim MAX8688 Digital Power-Supply
 Controller/Monitor with PMBus Interface.
 
 The driver is a client driver to the core PMBus driver. Please see
diff --git a/Documentation/hwmon/nsa320 b/Documentation/hwmon/nsa320
new file mode 100644
index 000000000000..fdbd6947799b
--- /dev/null
+++ b/Documentation/hwmon/nsa320
@@ -0,0 +1,53 @@
+Kernel driver nsa320_hwmon
+==========================
+
+Supported chips:
+  * Holtek HT46R065 microcontroller with onboard firmware that configures
+	it to act as a hardware monitor.
+    Prefix: 'nsa320'
+    Addresses scanned: none
+    Datasheet: Not available, driver was reverse engineered based upon the
+	Zyxel kernel source
+
+Author:
+  Adam Baker <linux@baker-net.org.uk>
+
+Description
+-----------
+
+This chip is known to be used in the Zyxel NSA320 and NSA325 NAS Units and
+also in some variants of the NSA310 but the driver has only been tested
+on the NSA320. In all of these devices it is connected to the same 3 GPIO
+lines which are used to provide chip select, clock and data lines. The
+interface behaves similarly to SPI but at much lower speeds than are normally
+used for SPI.
+
+Following each chip select pulse the chip will generate a single 32 bit word
+that contains 0x55 as a marker to indicate that data is being read correctly,
+followed by an 8 bit fan speed in 100s of RPM and a 16 bit temperature in
+tenths of a degree.
+
+
+sysfs-Interface
+---------------
+
+temp1_input - temperature input
+fan1_input - fan speed
+
+Notes
+-----
+
+The access timings used in the driver are the same as used in the Zyxel
+provided kernel. Testing has shown that if the delay between chip select and
+the first clock pulse is reduced from 100 ms to just under 10ms then the chip
+will not produce any output. If the duration of either phase of the clock
+is reduced from 100 us to less than 15 us then data pulses are likely to be
+read twice corrupting the output. The above analysis is based upon a sample
+of one unit but suggests that the Zyxel provided delay values include a
+reasonable tolerance.
+
+The driver incorporates a limit that it will not check for updated values
+faster than once a second. This is because the hardware takes a relatively long
+time to read the data from the device and when it does it reads both temp and
+fan speed. As the most likely case for two accesses in quick succession is
+to read both of these values avoiding a second read delay is desirable.
diff --git a/Documentation/hwmon/ntc_thermistor b/Documentation/hwmon/ntc_thermistor
index 1d4cc847c6fe..8b9ff23edc32 100644
--- a/Documentation/hwmon/ntc_thermistor
+++ b/Documentation/hwmon/ntc_thermistor
@@ -3,9 +3,9 @@ Kernel driver ntc_thermistor
 
 Supported thermistors from Murata:
 * Murata NTC Thermistors NCP15WB473, NCP18WB473, NCP21WB473, NCP03WB473,
-  NCP15WL333, NCP03WF104
+  NCP15WL333, NCP03WF104, NCP15XH103
   Prefixes: 'ncp15wb473', 'ncp18wb473', 'ncp21wb473', 'ncp03wb473',
-  'ncp15wl333', 'ncp03wf104'
+  'ncp15wl333', 'ncp03wf104', 'ncp15xh103'
   Datasheet: Publicly available at Murata
 
 Supported thermistors from EPCOS:
diff --git a/Documentation/hwmon/pmbus b/Documentation/hwmon/pmbus
index b397675e876d..dfd9c65996c0 100644
--- a/Documentation/hwmon/pmbus
+++ b/Documentation/hwmon/pmbus
@@ -43,7 +43,7 @@ Author: Guenter Roeck <linux@roeck-us.net>
 Description
 -----------
 
-This driver supports hardware montoring for various PMBus compliant devices.
+This driver supports hardware monitoring for various PMBus compliant devices.
 It supports voltage, current, power, and temperature sensors as supported
 by the device.
 
diff --git a/Documentation/hwmon/zl6100 b/Documentation/hwmon/zl6100
index 33908a4d68ff..477a94b131ae 100644
--- a/Documentation/hwmon/zl6100
+++ b/Documentation/hwmon/zl6100
@@ -60,7 +60,7 @@ Author: Guenter Roeck <linux@roeck-us.net>
 Description
 -----------
 
-This driver supports hardware montoring for Intersil / Zilker Labs ZL6100 and
+This driver supports hardware monitoring for Intersil / Zilker Labs ZL6100 and
 compatible digital DC-DC controllers.
 
 The driver is a client driver to the core PMBus driver. Please see
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 551ecf09c8dd..def479154d59 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -193,6 +193,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			(e.g. thinkpad_acpi, sony_acpi, etc.) instead
 			of the ACPI video.ko driver.
 
+	acpi_force_32bit_fadt_addr
+			force FADT to use 32 bit addresses rather than the
+			64 bit X_* addresses. Some firmware have broken 64
+			bit addresses for force ACPI ignore these and use
+			the older legacy 32 bit addresses.
+
 	acpica_no_return_repair [HW, ACPI]
 			Disable AML predefined validation mechanism
 			This mechanism can repair the evaluation result to make
@@ -666,7 +672,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	clearcpuid=BITNUM [X86]
 			Disable CPUID feature X for the kernel. See
-			arch/x86/include/asm/cpufeature.h for the valid bit
+			arch/x86/include/asm/cpufeatures.h for the valid bit
 			numbers. Note the Linux specific bits are not necessarily
 			stable over kernel options, but the vendor specific
 			ones should be.
@@ -1687,6 +1693,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	ip=		[IP_PNP]
 			See Documentation/filesystems/nfs/nfsroot.txt.
 
+	irqaffinity=	[SMP] Set the default irq affinity mask
+			Format:
+			<cpu number>,...,<cpu number>
+			or
+			<cpu number>-<cpu number>
+			(must be a positive range in ascending order)
+			or a mixture
+			<cpu number>,...,<cpu number>-<cpu number>
+
 	irqfixup	[HW]
 			When an interrupt is not handled search all handlers
 			for it. Intended to get systems with badly broken
@@ -1750,7 +1765,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	keepinitrd	[HW,ARM]
 
-	kernelcore=nn[KMG]	[KNL,X86,IA-64,PPC] This parameter
+	kernelcore=	[KNL,X86,IA-64,PPC]
+			Format: nn[KMGTPE] | "mirror"
+			This parameter
 			specifies the amount of memory usable by the kernel
 			for non-movable allocations.  The requested amount is
 			spread evenly throughout all nodes in the system. The
@@ -1766,6 +1783,14 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			use the HighMem zone if it exists, and the Normal
 			zone if it does not.
 
+			Instead of specifying the amount of memory (nn[KMGTPE]),
+			you can specify "mirror" option. In case "mirror"
+			option is specified, mirrored (reliable) memory is used
+			for non-movable allocations and remaining memory is used
+			for Movable pages. nn[KMGTPE] and "mirror" are exclusive,
+			so you can NOT specify nn[KMGTPE] and "mirror" at the same
+			time.
+
 	kgdbdbgp=	[KGDB,HW] kgdb over EHCI usb debug port.
 			Format: <Controller#>[,poll interval]
 			The controller # is the number of the ehci usb debug
@@ -2566,6 +2591,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	nointroute	[IA-64]
 
+	noinvpcid	[X86] Disable the INVPCID cpu feature.
+
 	nojitter	[IA-64] Disables jitter checking for ITC timers.
 
 	no-kvmclock	[X86,KVM] Disable paravirtualized KVM clock driver
@@ -2721,6 +2748,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			we can turn it on.
 			on: enable the feature
 
+	page_poison=	[KNL] Boot-time parameter changing the state of
+			poisoning on the buddy allocator.
+			off: turn off poisoning
+			on: turn on poisoning
+
 	panic=		[KNL] Kernel behaviour on panic: delay <timeout>
 			timeout > 0: seconds before rebooting
 			timeout = 0: wait forever
@@ -3491,6 +3523,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	ro		[KNL] Mount root device read-only on boot
 
+	rodata=		[KNL]
+		on	Mark read-only kernel memory as read-only (default).
+		off	Leave read-only kernel memory writable for debugging.
+
 	root=		[KNL] Root filesystem
 			See name_to_dev_t comment in init/do_mounts.c.
 
@@ -3528,6 +3564,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	sched_debug	[KNL] Enables verbose scheduler debug messages.
 
+	schedstats=	[KNL,X86] Enable or disable scheduled statistics.
+			Allowed values are enable and disable. This feature
+			incurs a small amount of overhead in the scheduler
+			but is useful for debugging and performance tuning.
+
 	skew_tick=	[KNL] Offset the periodic timer tick per cpu to mitigate
 			xtime_lock contention on larger systems, and/or RCU lock
 			contention on all systems with CONFIG_MAXSMP set.
@@ -4235,6 +4276,17 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			The default value of this parameter is determined by
 			the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT.
 
+	workqueue.debug_force_rr_cpu
+			Workqueue used to implicitly guarantee that work
+			items queued without explicit CPU specified are put
+			on the local CPU.  This guarantee is no longer true
+			and while local CPU is still preferred work items
+			may be put on foreign CPUs.  This debug option
+			forces round-robin CPU selection to flush out
+			usages which depend on the now broken guarantee.
+			When enabled, memory and cache locality will be
+			impacted.
+
 	x2apic_phys	[X86-64,APIC] Use x2apic physical mode instead of
 			default x2apic cluster mode on platforms
 			supporting x2apic.
diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt
index ce2cfcf35c27..443f4b44ad97 100644
--- a/Documentation/memory-hotplug.txt
+++ b/Documentation/memory-hotplug.txt
@@ -256,10 +256,27 @@ If the memory block is offline, you'll read "offline".
 
 5.2. How to online memory
 ------------
-Even if the memory is hot-added, it is not at ready-to-use state.
-For using newly added memory, you have to "online" the memory block.
+When the memory is hot-added, the kernel decides whether or not to "online"
+it according to the policy which can be read from "auto_online_blocks" file:
 
-For onlining, you have to write "online" to the memory block's state file as:
+% cat /sys/devices/system/memory/auto_online_blocks
+
+The default is "offline" which means the newly added memory is not in a
+ready-to-use state and you have to "online" the newly added memory blocks
+manually. Automatic onlining can be requested by writing "online" to
+"auto_online_blocks" file:
+
+% echo online > /sys/devices/system/memory/auto_online_blocks
+
+This sets a global policy and impacts all memory blocks that will subsequently
+be hotplugged. Currently offline blocks keep their state. It is possible, under
+certain circumstances, that some memory blocks will be added but will fail to
+online. User space tools can check their "state" files
+(/sys/devices/system/memory/memoryXXX/state) and try to online them manually.
+
+If the automatic onlining wasn't requested, failed, or some memory block was
+offlined it is possible to change the individual block's state by writing to the
+"state" file:
 
 % echo online > /sys/devices/system/memory/memoryXXX/state
 
diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt
index 5d1128bf0282..5962949944fd 100644
--- a/Documentation/printk-formats.txt
+++ b/Documentation/printk-formats.txt
@@ -298,6 +298,24 @@ bitmap and its derivatives such as cpumask and nodemask:
 
 	Passed by reference.
 
+Flags bitfields such as page flags, gfp_flags:
+
+	%pGp	referenced|uptodate|lru|active|private
+	%pGg	GFP_USER|GFP_DMA32|GFP_NOWARN
+	%pGv	read|exec|mayread|maywrite|mayexec|denywrite
+
+	For printing flags bitfields as a collection of symbolic constants that
+	would construct the value. The type of flags is given by the third
+	character. Currently supported are [p]age flags, [v]ma_flags (both
+	expect unsigned long *) and [g]fp_flags (expects gfp_t *). The flag
+	names and print order depends on the particular	type.
+
+	Note that this format should not be used directly in TP_printk() part
+	of a tracepoint. Instead, use the show_*_flags() functions from
+	<trace/events/mmflags.h>.
+
+	Passed by reference.
+
 Network device features:
 
 	%pNF	0x000000000000c000
diff --git a/Documentation/ptp/testptp.c b/Documentation/ptp/testptp.c
index 6c6247aaa7b9..d99012f41602 100644
--- a/Documentation/ptp/testptp.c
+++ b/Documentation/ptp/testptp.c
@@ -277,13 +277,15 @@ int main(int argc, char *argv[])
 			       "  %d external time stamp channels\n"
 			       "  %d programmable periodic signals\n"
 			       "  %d pulse per second\n"
-			       "  %d programmable pins\n",
+			       "  %d programmable pins\n"
+			       "  %d cross timestamping\n",
 			       caps.max_adj,
 			       caps.n_alarm,
 			       caps.n_ext_ts,
 			       caps.n_per_out,
 			       caps.pps,
-			       caps.n_pins);
+			       caps.n_pins,
+			       caps.cross_timestamping);
 		}
 	}
 
diff --git a/Documentation/rtc.txt b/Documentation/rtc.txt
index 8446f1ea1410..ddc366026e00 100644
--- a/Documentation/rtc.txt
+++ b/Documentation/rtc.txt
@@ -157,6 +157,12 @@ wakealarm:	 The time at which the clock will generate a system wakeup
 		 the epoch by default, or if there's a leading +, seconds in the
 		 future, or if there is a leading +=, seconds ahead of the current
 		 alarm.
+offset:		 The amount which the rtc clock has been adjusted in firmware.
+		 Visible only if the driver supports clock offset adjustment.
+		 The unit is parts per billion, i.e. The number of clock ticks
+		 which are added to or removed from the rtc's base clock per
+		 billion ticks. A positive value makes a day pass more slowly,
+		 longer, and a negative value makes a day pass more quickly.
 
 IOCTL INTERFACE
 ---------------
diff --git a/Documentation/scsi/st.txt b/Documentation/scsi/st.txt
index b3211af63b79..ec0acf6acccd 100644
--- a/Documentation/scsi/st.txt
+++ b/Documentation/scsi/st.txt
@@ -2,7 +2,7 @@ This file contains brief information about the SCSI tape driver.
 The driver is currently maintained by Kai Mäkisara (email
 Kai.Makisara@kolumbus.fi)
 
-Last modified: Sun Aug 29 18:25:47 2010 by kai.makisara
+Last modified: Tue Feb  9 21:54:16 2016 by kai.makisara
 
 
 BASICS
@@ -408,10 +408,15 @@ MTSETPART Moves the tape to the partition given by the argument at the
 	specified by MTSEEK. MTSETPART is inactive unless
 	MT_ST_CAN_PARTITIONS set.
 MTMKPART Formats the tape with one partition (argument zero) or two
-	partitions (the argument gives in megabytes the size of
-	partition 1 that is physically the first partition of the
-	tape). The drive has to support partitions with size specified
-	by the initiator. Inactive unless MT_ST_CAN_PARTITIONS set.
+	partitions (argument non-zero). If the argument is positive,
+	it specifies the size of partition 1 in megabytes. For DDS
+	drives and several early drives this is the physically first
+	partition of the tape. If the argument is negative, its absolute
+	value specifies the size of partition 0 in megabytes. This is
+	the physically first partition of many later drives, like the
+	LTO drives from LTO-5 upwards. The drive has to support partitions
+	with size specified by the initiator. Inactive unless
+	MT_ST_CAN_PARTITIONS set.
 MTSETDRVBUFFER
 	Is used for several purposes. The command is obtained from count
         with mask MT_SET_OPTIONS, the low order bits are used as argument.
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index a93b414672a7..f4444c94ff28 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -58,6 +58,8 @@ show up in /proc/sys/kernel:
 - panic_on_stackoverflow
 - panic_on_unrecovered_nmi
 - panic_on_warn
+- perf_cpu_time_max_percent
+- perf_event_paranoid
 - pid_max
 - powersave-nap               [ PPC only ]
 - printk
@@ -639,6 +641,17 @@ allowed to execute.
 
 ==============================================================
 
+perf_event_paranoid:
+
+Controls use of the performance events system by unprivileged
+users (without CAP_SYS_ADMIN).  The default value is 1.
+
+ -1: Allow use of (almost) all events by all users
+>=0: Disallow raw tracepoint access by users without CAP_IOC_LOCK
+>=1: Disallow CPU event access by users without CAP_SYS_ADMIN
+>=2: Disallow kernel profiling by users without CAP_SYS_ADMIN
+
+==============================================================
 
 pid_max:
 
@@ -760,6 +773,14 @@ rtsig-nr shows the number of RT signals currently queued.
 
 ==============================================================
 
+sched_schedstats:
+
+Enables/disables scheduler statistics. Enabling this feature
+incurs a small amount of overhead in the scheduler but is
+useful for debugging and performance tuning.
+
+==============================================================
+
 sg-big-buff:
 
 This file shows the size of the generic SCSI (sg) buffer.
diff --git a/Documentation/timers/hpet.txt b/Documentation/timers/hpet.txt
index 767392ffd31e..a484d2c109d7 100644
--- a/Documentation/timers/hpet.txt
+++ b/Documentation/timers/hpet.txt
@@ -1,9 +1,7 @@
 		High Precision Event Timer Driver for Linux
 
 The High Precision Event Timer (HPET) hardware follows a specification
-by Intel and Microsoft which can be found at
-
-	http://www.intel.com/hardwaredesign/hpetspec_1.pdf
+by Intel and Microsoft, revision 1.
 
 Each HPET has one fixed-rate counter (at 10+ MHz, hence "High Precision")
 and up to 32 comparators.  Normally three or more comparators are provided,
diff --git a/Documentation/video4linux/CARDLIST.saa7134 b/Documentation/video4linux/CARDLIST.saa7134
index 282102014bb9..335c24338859 100644
--- a/Documentation/video4linux/CARDLIST.saa7134
+++ b/Documentation/video4linux/CARDLIST.saa7134
@@ -194,3 +194,4 @@
 193 -> WIS Voyager or compatible                [1905:7007]
 194 -> AverMedia AverTV/505                     [1461:a10a]
 195 -> Leadtek Winfast TV2100 FM                [107d:6f3a]
+196 -> SnaZio* TVPVR PRO                        [1779:13cf]
diff --git a/Documentation/video4linux/v4l2-controls.txt b/Documentation/video4linux/v4l2-controls.txt
index 5517db602f37..5e759cab4538 100644
--- a/Documentation/video4linux/v4l2-controls.txt
+++ b/Documentation/video4linux/v4l2-controls.txt
@@ -647,7 +647,6 @@ Or you can add specific controls to a handler:
 	volume = v4l2_ctrl_new_std(&video_ctrl_handler, &ops, V4L2_CID_AUDIO_VOLUME, ...);
 	v4l2_ctrl_new_std(&video_ctrl_handler, &ops, V4L2_CID_BRIGHTNESS, ...);
 	v4l2_ctrl_new_std(&video_ctrl_handler, &ops, V4L2_CID_CONTRAST, ...);
-	v4l2_ctrl_add_ctrl(&radio_ctrl_handler, volume);
 
 What you should not do is make two identical controls for two handlers.
 For example:
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 07e4cdf02407..4d0542c5206b 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2507,8 +2507,9 @@ struct kvm_create_device {
 
 4.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR
 
-Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device
-Type: device ioctl, vm ioctl
+Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
+  KVM_CAP_VCPU_ATTRIBUTES for vcpu device
+Type: device ioctl, vm ioctl, vcpu ioctl
 Parameters: struct kvm_device_attr
 Returns: 0 on success, -1 on error
 Errors:
@@ -2533,8 +2534,9 @@ struct kvm_device_attr {
 
 4.81 KVM_HAS_DEVICE_ATTR
 
-Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device
-Type: device ioctl, vm ioctl
+Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
+  KVM_CAP_VCPU_ATTRIBUTES for vcpu device
+Type: device ioctl, vm ioctl, vcpu ioctl
 Parameters: struct kvm_device_attr
 Returns: 0 on success, -1 on error
 Errors:
@@ -2577,6 +2579,8 @@ Possible features:
 	  Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
 	- KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 for the CPU.
 	  Depends on KVM_CAP_ARM_PSCI_0_2.
+	- KVM_ARM_VCPU_PMU_V3: Emulate PMUv3 for the CPU.
+	  Depends on KVM_CAP_ARM_PMU_V3.
 
 
 4.83 KVM_ARM_PREFERRED_TARGET
@@ -3035,6 +3039,87 @@ Returns: 0 on success, -1 on error
 
 Queues an SMI on the thread's vcpu.
 
+4.97 KVM_CAP_PPC_MULTITCE
+
+Capability: KVM_CAP_PPC_MULTITCE
+Architectures: ppc
+Type: vm
+
+This capability means the kernel is capable of handling hypercalls
+H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user
+space. This significantly accelerates DMA operations for PPC KVM guests.
+User space should expect that its handlers for these hypercalls
+are not going to be called if user space previously registered LIOBN
+in KVM (via KVM_CREATE_SPAPR_TCE or similar calls).
+
+In order to enable H_PUT_TCE_INDIRECT and H_STUFF_TCE use in the guest,
+user space might have to advertise it for the guest. For example,
+IBM pSeries (sPAPR) guest starts using them if "hcall-multi-tce" is
+present in the "ibm,hypertas-functions" device-tree property.
+
+The hypercalls mentioned above may or may not be processed successfully
+in the kernel based fast path. If they can not be handled by the kernel,
+they will get passed on to user space. So user space still has to have
+an implementation for these despite the in kernel acceleration.
+
+This capability is always enabled.
+
+4.98 KVM_CREATE_SPAPR_TCE_64
+
+Capability: KVM_CAP_SPAPR_TCE_64
+Architectures: powerpc
+Type: vm ioctl
+Parameters: struct kvm_create_spapr_tce_64 (in)
+Returns: file descriptor for manipulating the created TCE table
+
+This is an extension for KVM_CAP_SPAPR_TCE which only supports 32bit
+windows, described in 4.62 KVM_CREATE_SPAPR_TCE
+
+This capability uses extended struct in ioctl interface:
+
+/* for KVM_CAP_SPAPR_TCE_64 */
+struct kvm_create_spapr_tce_64 {
+	__u64 liobn;
+	__u32 page_shift;
+	__u32 flags;
+	__u64 offset;	/* in pages */
+	__u64 size; 	/* in pages */
+};
+
+The aim of extension is to support an additional bigger DMA window with
+a variable page size.
+KVM_CREATE_SPAPR_TCE_64 receives a 64bit window size, an IOMMU page shift and
+a bus offset of the corresponding DMA window, @size and @offset are numbers
+of IOMMU pages.
+
+@flags are not used at the moment.
+
+The rest of functionality is identical to KVM_CREATE_SPAPR_TCE.
+
+4.98 KVM_REINJECT_CONTROL
+
+Capability: KVM_CAP_REINJECT_CONTROL
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_reinject_control (in)
+Returns: 0 on success,
+         -EFAULT if struct kvm_reinject_control cannot be read,
+         -ENXIO if KVM_CREATE_PIT or KVM_CREATE_PIT2 didn't succeed earlier.
+
+i8254 (PIT) has two modes, reinject and !reinject.  The default is reinject,
+where KVM queues elapsed i8254 ticks and monitors completion of interrupt from
+vector(s) that i8254 injects.  Reinject mode dequeues a tick and injects its
+interrupt whenever there isn't a pending interrupt from i8254.
+!reinject mode injects an interrupt as soon as a tick arrives.
+
+struct kvm_reinject_control {
+	__u8 pit_reinject;
+	__u8 reserved[31];
+};
+
+pit_reinject = 0 (!reinject mode) is recommended, unless running an old
+operating system that uses the PIT for timing (e.g. Linux 2.4.x).
+
 5. The kvm_run structure
 ------------------------
 
@@ -3339,6 +3424,7 @@ EOI was received.
 
 		struct kvm_hyperv_exit {
 #define KVM_EXIT_HYPERV_SYNIC          1
+#define KVM_EXIT_HYPERV_HCALL          2
 			__u32 type;
 			union {
 				struct {
@@ -3347,6 +3433,11 @@ EOI was received.
 					__u64 evt_page;
 					__u64 msg_page;
 				} synic;
+				struct {
+					__u64 input;
+					__u64 result;
+					__u64 params[2];
+				} hcall;
 			} u;
 		};
 		/* KVM_EXIT_HYPERV */
diff --git a/Documentation/virtual/kvm/devices/s390_flic.txt b/Documentation/virtual/kvm/devices/s390_flic.txt
index d1ad9d5cae46..e3e314cb83e8 100644
--- a/Documentation/virtual/kvm/devices/s390_flic.txt
+++ b/Documentation/virtual/kvm/devices/s390_flic.txt
@@ -88,6 +88,8 @@ struct kvm_s390_io_adapter_req {
       perform a gmap translation for the guest address provided in addr,
       pin a userspace page for the translated address and add it to the
       list of mappings
+      Note: A new mapping will be created unconditionally; therefore,
+            the calling code should avoid making duplicate mappings.
 
     KVM_S390_IO_ADAPTER_UNMAP
       release a userspace page for the translated address specified in addr
diff --git a/Documentation/virtual/kvm/devices/vcpu.txt b/Documentation/virtual/kvm/devices/vcpu.txt
new file mode 100644
index 000000000000..c04165868faf
--- /dev/null
+++ b/Documentation/virtual/kvm/devices/vcpu.txt
@@ -0,0 +1,33 @@
+Generic vcpu interface
+====================================
+
+The virtual cpu "device" also accepts the ioctls KVM_SET_DEVICE_ATTR,
+KVM_GET_DEVICE_ATTR, and KVM_HAS_DEVICE_ATTR. The interface uses the same struct
+kvm_device_attr as other devices, but targets VCPU-wide settings and controls.
+
+The groups and attributes per virtual cpu, if any, are architecture specific.
+
+1. GROUP: KVM_ARM_VCPU_PMU_V3_CTRL
+Architectures: ARM64
+
+1.1. ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_IRQ
+Parameters: in kvm_device_attr.addr the address for PMU overflow interrupt is a
+            pointer to an int
+Returns: -EBUSY: The PMU overflow interrupt is already set
+         -ENXIO: The overflow interrupt not set when attempting to get it
+         -ENODEV: PMUv3 not supported
+         -EINVAL: Invalid PMU overflow interrupt number supplied
+
+A value describing the PMUv3 (Performance Monitor Unit v3) overflow interrupt
+number for this vcpu. This interrupt could be a PPI or SPI, but the interrupt
+type must be same for each vcpu. As a PPI, the interrupt number is the same for
+all vcpus, while as an SPI it must be a separate number per vcpu.
+
+1.2 ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_INIT
+Parameters: no additional parameter in kvm_device_attr.addr
+Returns: -ENODEV: PMUv3 not supported
+         -ENXIO: PMUv3 not properly configured as required prior to calling this
+                 attribute
+         -EBUSY: PMUv3 already initialized
+
+Request the initialization of the PMUv3.
diff --git a/Documentation/virtual/kvm/devices/vm.txt b/Documentation/virtual/kvm/devices/vm.txt
index f083a168eb35..a9ea8774a45f 100644
--- a/Documentation/virtual/kvm/devices/vm.txt
+++ b/Documentation/virtual/kvm/devices/vm.txt
@@ -84,3 +84,55 @@ Returns:    -EBUSY in case 1 or more vcpus are already activated (only in write
 	    -EFAULT if the given address is not accessible from kernel space
 	    -ENOMEM if not enough memory is available to process the ioctl
 	    0 in case of success
+
+3. GROUP: KVM_S390_VM_TOD
+Architectures: s390
+
+3.1. ATTRIBUTE: KVM_S390_VM_TOD_HIGH
+
+Allows user space to set/get the TOD clock extension (u8).
+
+Parameters: address of a buffer in user space to store the data (u8) to
+Returns:    -EFAULT if the given address is not accessible from kernel space
+	    -EINVAL if setting the TOD clock extension to != 0 is not supported
+
+3.2. ATTRIBUTE: KVM_S390_VM_TOD_LOW
+
+Allows user space to set/get bits 0-63 of the TOD clock register as defined in
+the POP (u64).
+
+Parameters: address of a buffer in user space to store the data (u64) to
+Returns:    -EFAULT if the given address is not accessible from kernel space
+
+4. GROUP: KVM_S390_VM_CRYPTO
+Architectures: s390
+
+4.1. ATTRIBUTE: KVM_S390_VM_CRYPTO_ENABLE_AES_KW (w/o)
+
+Allows user space to enable aes key wrapping, including generating a new
+wrapping key.
+
+Parameters: none
+Returns:    0
+
+4.2. ATTRIBUTE: KVM_S390_VM_CRYPTO_ENABLE_DEA_KW (w/o)
+
+Allows user space to enable dea key wrapping, including generating a new
+wrapping key.
+
+Parameters: none
+Returns:    0
+
+4.3. ATTRIBUTE: KVM_S390_VM_CRYPTO_DISABLE_AES_KW (w/o)
+
+Allows user space to disable aes key wrapping, clearing the wrapping key.
+
+Parameters: none
+Returns:    0
+
+4.4. ATTRIBUTE: KVM_S390_VM_CRYPTO_DISABLE_DEA_KW (w/o)
+
+Allows user space to disable dea key wrapping, clearing the wrapping key.
+
+Parameters: none
+Returns:    0
diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt
index daf9c0f742d2..481b6a9c25d5 100644
--- a/Documentation/virtual/kvm/mmu.txt
+++ b/Documentation/virtual/kvm/mmu.txt
@@ -358,7 +358,8 @@ In the first case there are two additional complications:
 - if CR4.SMEP is enabled: since we've turned the page into a kernel page,
   the kernel may now execute it.  We handle this by also setting spte.nx.
   If we get a user fetch or read fault, we'll change spte.u=1 and
-  spte.nx=gpte.nx back.
+  spte.nx=gpte.nx back.  For this to work, KVM forces EFER.NX to 1 when
+  shadow paging is in use.
 - if CR4.SMAP is disabled: since the page has been changed to a kernel
   page, it can not be reused when CR4.SMAP is enabled. We set
   CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note,
@@ -391,11 +392,11 @@ To instantiate a large spte, four constraints must be satisfied:
   write-protected pages
 - the guest page must be wholly contained by a single memory slot
 
-To check the last two conditions, the mmu maintains a ->write_count set of
+To check the last two conditions, the mmu maintains a ->disallow_lpage set of
 arrays for each memory slot and large page size.  Every write protected page
-causes its write_count to be incremented, thus preventing instantiation of
+causes its disallow_lpage to be incremented, thus preventing instantiation of
 a large spte.  The frames at the end of an unaligned memory slot have
-artificially inflated ->write_counts so they can never be instantiated.
+artificially inflated ->disallow_lpages so they can never be instantiated.
 
 Zapping all pages (page generation count)
 =========================================
diff --git a/Documentation/vm/page_owner.txt b/Documentation/vm/page_owner.txt
index 8f3ce9b3aa11..ffff1439076a 100644
--- a/Documentation/vm/page_owner.txt
+++ b/Documentation/vm/page_owner.txt
@@ -28,10 +28,11 @@ with page owner and page owner is disabled in runtime due to no enabling
 boot option, runtime overhead is marginal. If disabled in runtime, it
 doesn't require memory to store owner information, so there is no runtime
 memory overhead. And, page owner inserts just two unlikely branches into
-the page allocator hotpath and if it returns false then allocation is
-done like as the kernel without page owner. These two unlikely branches
-would not affect to allocation performance. Following is the kernel's
-code size change due to this facility.
+the page allocator hotpath and if not enabled, then allocation is done
+like as the kernel without page owner. These two unlikely branches should
+not affect to allocation performance, especially if the static keys jump
+label patching functionality is available. Following is the kernel's code
+size change due to this facility.
 
 - Without page owner
    text    data     bss     dec     hex filename
diff --git a/Documentation/vm/slub.txt b/Documentation/vm/slub.txt
index f0d340959319..84652419bff2 100644
--- a/Documentation/vm/slub.txt
+++ b/Documentation/vm/slub.txt
@@ -35,8 +35,8 @@ slub_debug=<Debug-Options>,<slab name>
 				Enable options only for select slabs
 
 Possible debug options are
-	F		Sanity checks on (enables SLAB_DEBUG_FREE. Sorry
-			SLAB legacy issues)
+	F		Sanity checks on (enables SLAB_DEBUG_CONSISTENCY_CHECKS
+			Sorry SLAB legacy issues)
 	Z		Red zoning
 	P		Poisoning (object and padding)
 	U		User tracking (free and alloc)
diff --git a/Documentation/watchdog/watchdog-parameters.txt b/Documentation/watchdog/watchdog-parameters.txt
index 9f9ec9f76039..4e4b6f10d841 100644
--- a/Documentation/watchdog/watchdog-parameters.txt
+++ b/Documentation/watchdog/watchdog-parameters.txt
@@ -400,3 +400,7 @@ wm8350_wdt:
 nowayout: Watchdog cannot be stopped once started
 	(default=kernel config parameter)
 -------------------------------------------------
+sun4v_wdt:
+timeout_ms: Watchdog timeout in milliseconds 1..180000, default=60000)
+nowayout: Watchdog cannot be stopped once started
+-------------------------------------------------
diff --git a/Documentation/x86/early-microcode.txt b/Documentation/x86/early-microcode.txt
index d62bea6796da..c956d99cf1de 100644
--- a/Documentation/x86/early-microcode.txt
+++ b/Documentation/x86/early-microcode.txt
@@ -40,3 +40,28 @@ cp ../microcode.bin kernel/x86/microcode/GenuineIntel.bin (or AuthenticAMD.bin)
 find . | cpio -o -H newc >../ucode.cpio
 cd ..
 cat ucode.cpio /boot/initrd-3.5.0.img >/boot/initrd-3.5.0.ucode.img
+
+Builtin microcode
+=================
+
+We can also load builtin microcode supplied through the regular firmware
+builtin method CONFIG_FIRMWARE_IN_KERNEL. Here's an example:
+
+CONFIG_FIRMWARE_IN_KERNEL=y
+CONFIG_EXTRA_FIRMWARE="intel-ucode/06-3a-09 amd-ucode/microcode_amd_fam15h.bin"
+CONFIG_EXTRA_FIRMWARE_DIR="/lib/firmware"
+
+This basically means, you have the following tree structure locally:
+
+/lib/firmware/
+|-- amd-ucode
+...
+|   |-- microcode_amd_fam15h.bin
+...
+|-- intel-ucode
+...
+|   |-- 06-3a-09
+...
+
+so that the build system can find those files and integrate them into
+the final kernel image. The early loader finds them and applies them.
diff --git a/Documentation/x86/exception-tables.txt b/Documentation/x86/exception-tables.txt
index 32901aa36f0a..e396bcd8d830 100644
--- a/Documentation/x86/exception-tables.txt
+++ b/Documentation/x86/exception-tables.txt
@@ -290,3 +290,38 @@ Due to the way that the exception table is built and needs to be ordered,
 only use exceptions for code in the .text section.  Any other section
 will cause the exception table to not be sorted correctly, and the
 exceptions will fail.
+
+Things changed when 64-bit support was added to x86 Linux. Rather than
+double the size of the exception table by expanding the two entries
+from 32-bits to 64 bits, a clever trick was used to store addresses
+as relative offsets from the table itself. The assembly code changed
+from:
+	.long 1b,3b
+to:
+        .long (from) - .
+        .long (to) - .
+
+and the C-code that uses these values converts back to absolute addresses
+like this:
+
+	ex_insn_addr(const struct exception_table_entry *x)
+	{
+		return (unsigned long)&x->insn + x->insn;
+	}
+
+In v4.6 the exception table entry was expanded with a new field "handler".
+This is also 32-bits wide and contains a third relative function
+pointer which points to one of:
+
+1) int ex_handler_default(const struct exception_table_entry *fixup)
+   This is legacy case that just jumps to the fixup code
+2) int ex_handler_fault(const struct exception_table_entry *fixup)
+   This case provides the fault number of the trap that occurred at
+   entry->insn. It is used to distinguish page faults from machine
+   check.
+3) int ex_handler_ext(const struct exception_table_entry *fixup)
+   This case is used for uaccess_err ... we need to set a flag
+   in the task structure. Before the handler functions existed this
+   case was handled by adding a large offset to the fixup to tag
+   it as special.
+More functions can easily be added.
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 68ed3114c363..0965a71f9942 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -60,6 +60,8 @@ Machine check
 		threshold to 1. Enabling this may make memory predictive failure
 		analysis less effective if the bios sets thresholds for memory
 		errors since we will not see details for all errors.
+   mce=recovery
+		Force-enable recoverable machine check code paths
 
    nomce (for compatibility with i386): same as mce=off
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 2900d481dba7..5e6f388f3c3e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -920,17 +920,24 @@ M:	Emilio López <emilio@elopez.com.ar>
 S:	Maintained
 F:	drivers/clk/sunxi/
 
-ARM/Amlogic MesonX SoC support
+ARM/Amlogic Meson SoC support
 M:	Carlo Caione <carlo@caione.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L:	linux-meson@googlegroups.com
+W:	http://linux-meson.com/
 S:	Maintained
-F:	drivers/media/rc/meson-ir.c
-N:	meson[x68]
+F:	arch/arm/mach-meson/
+F:	arch/arm/boot/dts/meson*
+N:	meson
 
 ARM/Annapurna Labs ALPINE ARCHITECTURE
 M:	Tsahee Zidenberg <tsahee@annapurnalabs.com>
+M:	Antoine Tenart <antoine.tenart@free-electrons.com>
 S:	Maintained
 F:	arch/arm/mach-alpine/
+F:	arch/arm/boot/dts/alpine*
+F:	arch/arm64/boot/dts/al/
+F:	drivers/*/*alpine*
 
 ARM/ATMEL AT91RM9200, AT91SAM9 AND SAMA5 SOC SUPPORT
 M:	Nicolas Ferre <nicolas.ferre@atmel.com>
@@ -1442,8 +1449,8 @@ S:	Maintained
 ARM/RENESAS ARM64 ARCHITECTURE
 M:	Simon Horman <horms@verge.net.au>
 M:	Magnus Damm <magnus.damm@gmail.com>
-L:	linux-sh@vger.kernel.org
-Q:	http://patchwork.kernel.org/project/linux-sh/list/
+L:	linux-renesas-soc@vger.kernel.org
+Q:	http://patchwork.kernel.org/project/linux-renesas-soc/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/horms/renesas.git next
 S:	Supported
 F:	arch/arm64/boot/dts/renesas/
@@ -2362,14 +2369,6 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rpi/linux-rpi.git
 S:	Maintained
 N:	bcm2835
 
-BROADCOM BCM33XX MIPS ARCHITECTURE
-M:	Kevin Cernekee <cernekee@gmail.com>
-L:	linux-mips@linux-mips.org
-S:	Maintained
-F:	arch/mips/bcm3384/*
-F:	arch/mips/include/asm/mach-bcm3384/*
-F:	arch/mips/kernel/*bmips*
-
 BROADCOM BCM47XX MIPS ARCHITECTURE
 M:	Hauke Mehrtens <hauke@hauke-m.de>
 M:	Rafał Miłecki <zajec5@gmail.com>
@@ -2423,6 +2422,7 @@ F:	arch/mips/bmips/*
 F:	arch/mips/include/asm/mach-bmips/*
 F:	arch/mips/kernel/*bmips*
 F:	arch/mips/boot/dts/brcm/bcm*.dts*
+F:	drivers/irqchip/irq-bcm63*
 F:	drivers/irqchip/irq-bcm7*
 F:	drivers/irqchip/irq-brcmstb*
 F:	include/linux/bcm963xx_nvram.h
@@ -3452,7 +3452,6 @@ F:	drivers/usb/dwc2/
 DESIGNWARE USB3 DRD IP DRIVER
 M:	Felipe Balbi <balbi@kernel.org>
 L:	linux-usb@vger.kernel.org
-L:	linux-omap@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git
 S:	Maintained
 F:	drivers/usb/dwc3/
@@ -4520,6 +4519,12 @@ L:	linuxppc-dev@lists.ozlabs.org
 S:	Maintained
 F:	drivers/dma/fsldma.*
 
+FREESCALE GPMI NAND DRIVER
+M:	Han Xu <han.xu@nxp.com>
+L:	linux-mtd@lists.infradead.org
+S:	Maintained
+F:	drivers/mtd/nand/gpmi-nand/*
+
 FREESCALE I2C CPM DRIVER
 M:	Jochen Friedrich <jochen@scram.de>
 L:	linuxppc-dev@lists.ozlabs.org
@@ -4536,7 +4541,7 @@ F:	include/linux/platform_data/video-imxfb.h
 F:	drivers/video/fbdev/imxfb.c
 
 FREESCALE QUAD SPI DRIVER
-M:	Han Xu <han.xu@freescale.com>
+M:	Han Xu <han.xu@nxp.com>
 L:	linux-mtd@lists.infradead.org
 S:	Maintained
 F:	drivers/mtd/spi-nor/fsl-quadspi.c
@@ -4550,6 +4555,15 @@ S:	Maintained
 F:	drivers/net/ethernet/freescale/fs_enet/
 F:	include/linux/fs_enet_pd.h
 
+FREESCALE IMX / MXC FEC DRIVER
+M:	Fugang Duan <fugang.duan@nxp.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/ethernet/freescale/fec_main.c
+F:	drivers/net/ethernet/freescale/fec_ptp.c
+F:	drivers/net/ethernet/freescale/fec.h
+F:	Documentation/devicetree/bindings/net/fsl-fec.txt
+
 FREESCALE QUICC ENGINE LIBRARY
 L:	linuxppc-dev@lists.ozlabs.org
 S:	Orphan
@@ -4993,9 +5007,9 @@ F:	Documentation/blockdev/cpqarray.txt
 F:	drivers/block/cpqarray.*
 
 HEWLETT-PACKARD SMART ARRAY RAID DRIVER (hpsa)
-M:	Don Brace <don.brace@pmcs.com>
+M:	Don Brace <don.brace@microsemi.com>
 L:	iss_storagedev@hp.com
-L:	storagedev@pmcs.com
+L:	esc.storagedev@microsemi.com
 L:	linux-scsi@vger.kernel.org
 S:	Supported
 F:	Documentation/scsi/hpsa.txt
@@ -5191,6 +5205,7 @@ F:	arch/x86/kernel/cpu/mshyperv.c
 F:	drivers/hid/hid-hyperv.c
 F:	drivers/hv/
 F:	drivers/input/serio/hyperv-keyboard.c
+F:	drivers/pci/host/pci-hyperv.c
 F:	drivers/net/hyperv/
 F:	drivers/scsi/storvsc_drv.c
 F:	drivers/video/fbdev/hyperv_fb.c
@@ -6136,7 +6151,7 @@ F:	include/uapi/linux/sunrpc/
 
 KERNEL SELFTEST FRAMEWORK
 M:	Shuah Khan <shuahkh@osg.samsung.com>
-L:	linux-api@vger.kernel.org
+L:	linux-kselftest@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/shuah/linux-kselftest
 S:	Maintained
 F:	tools/testing/selftests
@@ -6667,13 +6682,12 @@ S:	Maintained
 F:	arch/arm/mach-lpc32xx/
 
 LSILOGIC MPT FUSION DRIVERS (FC/SAS/SPI)
-M:	Nagalakshmi Nandigama <nagalakshmi.nandigama@avagotech.com>
-M:	Praveen Krishnamoorthy <praveen.krishnamoorthy@avagotech.com>
-M:	Sreekanth Reddy <sreekanth.reddy@avagotech.com>
-M:	Abhijit Mahajan <abhijit.mahajan@avagotech.com>
-L:	MPT-FusionLinux.pdl@avagotech.com
+M:	Sathya Prakash <sathya.prakash@broadcom.com>
+M:	Chaitra P B <chaitra.basappa@broadcom.com>
+M:	Suganath Prabu Subramani <suganath-prabu.subramani@broadcom.com>
+L:	MPT-FusionLinux.pdl@broadcom.com
 L:	linux-scsi@vger.kernel.org
-W:	http://www.lsilogic.com/support
+W:	http://www.avagotech.com/support/
 S:	Supported
 F:	drivers/message/fusion/
 F:	drivers/scsi/mpt2sas/
@@ -6766,6 +6780,7 @@ S:	Maintained
 F:	Documentation/networking/mac80211-injection.txt
 F:	include/net/mac80211.h
 F:	net/mac80211/
+F:	drivers/net/wireless/mac80211_hwsim.[ch]
 
 MACVLAN DRIVER
 M:	Patrick McHardy <kaber@trash.net>
@@ -6895,7 +6910,7 @@ MAXIM MAX77802 MULTIFUNCTION PMIC DEVICE DRIVERS
 M:	Javier Martinez Canillas <javier@osg.samsung.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
-F:	drivers/*/*max77802.c
+F:	drivers/*/*max77802*.c
 F:	Documentation/devicetree/bindings/*/*max77802.txt
 F:	include/dt-bindings/*/*max77802.h
 
@@ -6905,7 +6920,7 @@ M:	Krzysztof Kozlowski <k.kozlowski@samsung.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
 F:	drivers/*/max14577.c
-F:	drivers/*/max77686.c
+F:	drivers/*/max77686*.c
 F:	drivers/*/max77693.c
 F:	drivers/extcon/extcon-max14577.c
 F:	drivers/extcon/extcon-max77693.c
@@ -7221,10 +7236,8 @@ L:	linux-media@vger.kernel.org
 W:	https://linuxtv.org
 W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
-T:	git git://linuxtv.org/anttip/media_tree.git
 S:	Maintained
-F:	drivers/staging/media/mn88473/
-F:	drivers/media/dvb-frontends/mn88473.h
+F:	drivers/media/dvb-frontends/mn88473*
 
 MODULE SUPPORT
 M:	Rusty Russell <rusty@rustcorp.com.au>
@@ -7362,7 +7375,7 @@ F:	drivers/tty/isicom.c
 F:	include/linux/isicom.h
 
 MUSB MULTIPOINT HIGH SPEED DUAL-ROLE CONTROLLER
-M:	Felipe Balbi <balbi@kernel.org>
+M:	Bin Liu <b-liu@ti.com>
 L:	linux-usb@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git
 S:	Maintained
@@ -7385,6 +7398,17 @@ W:	https://www.myricom.com/support/downloads/myri10ge.html
 S:	Supported
 F:	drivers/net/ethernet/myricom/myri10ge/
 
+NAND FLASH SUBSYSTEM
+M:	Boris Brezillon <boris.brezillon@free-electrons.com>
+R:	Richard Weinberger <richard@nod.at>
+L:	linux-mtd@lists.infradead.org
+W:	http://www.linux-mtd.infradead.org/
+Q:	http://patchwork.ozlabs.org/project/linux-mtd/list/
+T:	git git://github.com/linux-nand/linux.git
+S:	Maintained
+F:	drivers/mtd/nand/
+F:	include/linux/mtd/nand*.h
+
 NATSEMI ETHERNET DRIVER (DP8381x)
 S:	Orphan
 F:	drivers/net/ethernet/natsemi/natsemi.c
@@ -7694,13 +7718,13 @@ S:	Maintained
 F:	arch/nios2/
 
 NOKIA N900 POWER SUPPLY DRIVERS
-M:	Pali Rohár <pali.rohar@gmail.com>
-S:	Maintained
+R:	Pali Rohár <pali.rohar@gmail.com>
 F:	include/linux/power/bq2415x_charger.h
 F:	include/linux/power/bq27xxx_battery.h
 F:	include/linux/power/isp1704_charger.h
 F:	drivers/power/bq2415x_charger.c
 F:	drivers/power/bq27xxx_battery.c
+F:	drivers/power/bq27xxx_battery_i2c.c
 F:	drivers/power/isp1704_charger.c
 F:	drivers/power/rx51_battery.c
 
@@ -7931,11 +7955,9 @@ F:	drivers/media/platform/omap3isp/
 F:	drivers/staging/media/omap4iss/
 
 OMAP USB SUPPORT
-M:	Felipe Balbi <balbi@kernel.org>
 L:	linux-usb@vger.kernel.org
 L:	linux-omap@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git
-S:	Maintained
+S:	Orphan
 F:	drivers/usb/*/*omap*
 F:	arch/arm/*omap*/usb*
 
@@ -8359,12 +8381,20 @@ L:	linux-pci@vger.kernel.org
 S:	Maintained
 F:	drivers/pci/host/*designware*
 
+PCI DRIVER FOR SYNOPSYS PROTOTYPING DEVICE
+M:	Joao Pinto <jpinto@synopsys.com>
+L:	linux-pci@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/pci/designware-pcie.txt
+F:	drivers/pci/host/pcie-designware-plat.c
+
 PCI DRIVER FOR GENERIC OF HOSTS
 M:	Will Deacon <will.deacon@arm.com>
 L:	linux-pci@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	Documentation/devicetree/bindings/pci/host-generic-pci.txt
+F:	drivers/pci/host/pci-host-common.c
 F:	drivers/pci/host/pci-host-generic.c
 
 PCI DRIVER FOR INTEL VOLUME MANAGEMENT DEVICE (VMD)
@@ -8410,6 +8440,14 @@ L:     linux-arm-msm@vger.kernel.org
 S:     Maintained
 F:     drivers/pci/host/*qcom*
 
+PCIE DRIVER FOR CAVIUM THUNDERX
+M:	David Daney <david.daney@cavium.com>
+L:	linux-pci@vger.kernel.org
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Supported
+F:	Documentation/devicetree/bindings/pci/pci-thunder-*
+F:	drivers/pci/host/pci-thunder-*
+
 PCMCIA SUBSYSTEM
 P:	Linux PCMCIA Team
 L:	linux-pcmcia@lists.infradead.org
@@ -8452,6 +8490,7 @@ PERFORMANCE EVENTS SUBSYSTEM
 M:	Peter Zijlstra <peterz@infradead.org>
 M:	Ingo Molnar <mingo@redhat.com>
 M:	Arnaldo Carvalho de Melo <acme@kernel.org>
+R:	Alexander Shishkin <alexander.shishkin@linux.intel.com>
 L:	linux-kernel@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf/core
 S:	Supported
@@ -9566,6 +9605,12 @@ M:	Andreas Noever <andreas.noever@gmail.com>
 S:	Maintained
 F:	drivers/thunderbolt/
 
+TI BQ27XXX POWER SUPPLY DRIVER
+R:	Andrew F. Davis <afd@ti.com>
+F:	include/linux/power/bq27xxx_battery.h
+F:	drivers/power/bq27xxx_battery.c
+F:	drivers/power/bq27xxx_battery_i2c.c
+
 TIMEKEEPING, CLOCKSOURCE CORE, NTP, ALARMTIMER
 M:	John Stultz <john.stultz@linaro.org>
 M:	Thomas Gleixner <tglx@linutronix.de>
@@ -9643,7 +9688,7 @@ F:	drivers/scsi/sg.c
 F:	include/scsi/sg.h
 
 SCSI SUBSYSTEM
-M:	"James E.J. Bottomley" <JBottomley@odin.com>
+M:	"James E.J. Bottomley" <jejb@linux.vnet.ibm.com>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi.git
 M:	"Martin K. Petersen" <martin.petersen@oracle.com>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mkp/scsi.git
@@ -9787,10 +9832,11 @@ S:	Supported
 F:	drivers/scsi/be2iscsi/
 
 Emulex 10Gbps NIC BE2, BE3-R, Lancer, Skyhawk-R DRIVER
-M:	Sathya Perla <sathya.perla@avagotech.com>
-M:	Ajit Khaparde <ajit.khaparde@avagotech.com>
-M:	Padmanabh Ratnakar <padmanabh.ratnakar@avagotech.com>
-M:	Sriharsha Basavapatna <sriharsha.basavapatna@avagotech.com>
+M:	Sathya Perla <sathya.perla@broadcom.com>
+M:	Ajit Khaparde <ajit.khaparde@broadcom.com>
+M:	Padmanabh Ratnakar <padmanabh.ratnakar@broadcom.com>
+M:	Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
+M:	Somnath Kotur <somnath.kotur@broadcom.com>
 L:	netdev@vger.kernel.org
 W:	http://www.emulex.com
 S:	Supported
@@ -10849,6 +10895,14 @@ L:	linux-omap@vger.kernel.org
 S:	Maintained
 F:	drivers/thermal/ti-soc-thermal/
 
+TI VPE/CAL DRIVERS
+M:	Benoit Parrot <bparrot@ti.com>
+L:	linux-media@vger.kernel.org
+W:	http://linuxtv.org/
+Q:	http://patchwork.linuxtv.org/project/linux-media/list/
+S:	Maintained
+F:	drivers/media/platform/ti-vpe/
+
 TI CDCE706 CLOCK DRIVER
 M:	Max Filippov <jcmvbkbc@gmail.com>
 S:	Maintained
@@ -12020,7 +12074,6 @@ F:	arch/arm64/xen/
 F:	arch/arm64/include/asm/xen/
 
 XEN NETWORK BACKEND DRIVER
-M:	Ian Campbell <ian.campbell@citrix.com>
 M:	Wei Liu <wei.liu2@citrix.com>
 L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
 L:	netdev@vger.kernel.org
diff --git a/Makefile b/Makefile
index 682840850f58..7b3ecdcdc6c1 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 5
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION =
 NAME = Blurry Fish Butt
 
 # *DOCUMENTATION*
diff --git a/arch/alpha/include/asm/pci.h b/arch/alpha/include/asm/pci.h
index 98f2eeee8f68..a06c24b3a2e1 100644
--- a/arch/alpha/include/asm/pci.h
+++ b/arch/alpha/include/asm/pci.h
@@ -7,7 +7,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/scatterlist.h>
 #include <asm/machvec.h>
-#include <asm-generic/pci-bridge.h>
 
 /*
  * The following structure is used to manage multiple PCI busses.
@@ -66,13 +65,6 @@ extern void pcibios_set_master(struct pci_dev *dev);
    decisions.  */
 #define PCI_DMA_BUS_IS_PHYS  0
 
-#ifdef CONFIG_PCI
-
-/* implement the pci_ DMA API in terms of the generic device dma_ one */
-#include <asm-generic/pci-dma-compat.h>
-
-#endif
-
 /* TODO: integrate with include/asm-generic/pci.h ? */
 static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 {
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 2f24447fef92..46bf263c3153 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -168,7 +168,7 @@ smp_callin(void)
 	      cpuid, current, current->active_mm));
 
 	preempt_disable();
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
 /* Wait until hwrpb->txrdy is clear for cpu.  Return -1 on timeout.  */
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 76dde9db7934..07a5cb944d4f 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -12,13 +12,12 @@ config ARC
 	select BUILDTIME_EXTABLE_SORT
 	select COMMON_CLK
 	select CLONE_BACKWARDS
-	# ARC Busybox based initramfs absolutely relies on DEVTMPFS for /dev
-	select DEVTMPFS if !INITRAMFS_SOURCE=""
 	select GENERIC_ATOMIC64
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_FIND_FIRST_BIT
 	# for now, we don't need GENERIC_IRQ_PROBE, CONFIG_GENERIC_IRQ_CHIP
 	select GENERIC_IRQ_SHOW
+	select GENERIC_PCI_IOMAP
 	select GENERIC_PENDING_IRQ if SMP
 	select GENERIC_SMP_IDLE_THREAD
 	select HAVE_ARCH_KGDB
@@ -39,6 +38,9 @@ config ARC
 	select PERF_USE_VMALLOC
 	select HAVE_DEBUG_STACKOVERFLOW
 
+config MIGHT_HAVE_PCI
+	bool
+
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
@@ -275,14 +277,6 @@ config ARC_DCCM_BASE
 	default "0xA0000000"
 	depends on ARC_HAS_DCCM
 
-config ARC_HAS_HW_MPY
-	bool "Use Hardware Multiplier (Normal or Faster XMAC)"
-	default y
-	help
-	  Influences how gcc generates code for MPY operations.
-	  If enabled, MPYxx insns are generated, provided by Standard/XMAC
-	  Multipler. Otherwise software multipy lib is used
-
 choice
 	prompt "MMU Version"
 	default ARC_MMU_V3 if ARC_CPU_770
@@ -338,6 +332,19 @@ config ARC_PAGE_SIZE_4K
 
 endchoice
 
+choice
+	prompt "MMU Super Page Size"
+	depends on ISA_ARCV2 && TRANSPARENT_HUGEPAGE
+	default ARC_HUGEPAGE_2M
+
+config ARC_HUGEPAGE_2M
+	bool "2MB"
+
+config ARC_HUGEPAGE_16M
+	bool "16MB"
+
+endchoice
+
 if ISA_ARCOMPACT
 
 config ARC_COMPACT_IRQ_LEVELS
@@ -410,7 +417,7 @@ config ARC_HAS_RTC
 	default n
 	depends on !SMP
 
-config ARC_HAS_GRTC
+config ARC_HAS_GFRC
 	bool "SMP synchronized 64-bit cycle counter"
 	default y
 	depends on SMP
@@ -529,14 +536,6 @@ config ARC_DBG_TLB_MISS_COUNT
 	  Counts number of I and D TLB Misses and exports them via Debugfs
 	  The counters can be cleared via Debugfs as well
 
-if SMP
-
-config ARC_IPI_DBG
-	bool "Debug Inter Core interrupts"
-	default n
-
-endif
-
 endif
 
 config ARC_UBOOT_SUPPORT
@@ -566,8 +565,36 @@ endmenu
 endmenu	 # "ARC Architecture Configuration"
 
 source "mm/Kconfig"
+
+config FORCE_MAX_ZONEORDER
+	int "Maximum zone order"
+	default "12" if ARC_HUGEPAGE_16M
+	default "11"
+
 source "net/Kconfig"
 source "drivers/Kconfig"
+
+menu "Bus Support"
+
+config PCI
+	bool "PCI support" if MIGHT_HAVE_PCI
+	help
+	  PCI is the name of a bus system, i.e., the way the CPU talks to
+	  the other stuff inside your box.  Find out if your board/platform
+	  has PCI.
+
+	  Note: PCIe support for Synopsys Device will be available only
+	  when HAPS DX is configured with PCIe RC bitmap. If you have PCI,
+	  say Y, otherwise N.
+
+config PCI_SYSCALL
+	def_bool PCI
+
+source "drivers/pci/Kconfig"
+source "drivers/pci/pcie/Kconfig"
+
+endmenu
+
 source "fs/Kconfig"
 source "arch/arc/Kconfig.debug"
 source "security/Kconfig"
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index aeb19021099e..c8230f3395f2 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -74,10 +74,6 @@ ldflags-$(CONFIG_CPU_BIG_ENDIAN)	+= -EB
 # --build-id w/o "-marclinux". Default arc-elf32-ld is OK
 ldflags-$(upto_gcc44)			+= -marclinux
 
-ifndef CONFIG_ARC_HAS_HW_MPY
-	cflags-y	+= -mno-mpy
-endif
-
 LIBGCC	:= $(shell $(CC) $(cflags-y) --print-libgcc-file-name)
 
 # Modules with short calls might break for calls into builtin-kernel
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
index f1ac9818b751..5d4e2a07ad3e 100644
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -39,6 +39,7 @@ CONFIG_IP_PNP_RARP=y
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -73,7 +74,6 @@ CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_DESIGNWARE_PLATFORM=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
 CONFIG_LOGO=y
@@ -91,12 +91,10 @@ CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_DW=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT3_FS=y
-CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
 CONFIG_TMPFS=y
-CONFIG_JFFS2_FS=y
 CONFIG_NFS_FS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
index 323486d6ee83..87ee46b237ef 100644
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -39,14 +39,10 @@ CONFIG_IP_PNP_RARP=y
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_AXS=y
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_NETDEVICES=y
@@ -78,14 +74,12 @@ CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_DESIGNWARE_PLATFORM=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set
 # CONFIG_LOGO_LINUX_CLUT224 is not set
-CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
 CONFIG_USB_OHCI_HCD=y
@@ -97,12 +91,10 @@ CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_DW=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT3_FS=y
-CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
 CONFIG_TMPFS=y
-CONFIG_JFFS2_FS=y
 CONFIG_NFS_FS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
index 66191cd0447e..d80daf4f7e73 100644
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -40,14 +40,10 @@ CONFIG_IP_PNP_RARP=y
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_AXS=y
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_NETDEVICES=y
@@ -79,14 +75,12 @@ CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_DESIGNWARE_PLATFORM=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set
 # CONFIG_LOGO_LINUX_CLUT224 is not set
-CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
 CONFIG_USB_OHCI_HCD=y
@@ -98,12 +92,10 @@ CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_DW=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT3_FS=y
-CONFIG_EXT4_FS=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
 CONFIG_TMPFS=y
-CONFIG_JFFS2_FS=y
 CONFIG_NFS_FS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig
index 138f9d887957..f41095340b6a 100644
--- a/arch/arc/configs/nsim_700_defconfig
+++ b/arch/arc/configs/nsim_700_defconfig
@@ -4,6 +4,7 @@ CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
@@ -26,7 +27,6 @@ CONFIG_ARC_PLAT_SIM=y
 CONFIG_ARC_BUILTIN_DTB_NAME="nsim_700"
 CONFIG_PREEMPT=y
 # CONFIG_COMPACTION is not set
-# CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -34,6 +34,7 @@ CONFIG_UNIX_DIAG=y
 CONFIG_NET_KEY=y
 CONFIG_INET=y
 # CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -51,7 +52,6 @@ CONFIG_SERIAL_ARC=y
 CONFIG_SERIAL_ARC_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
-# CONFIG_VGA_CONSOLE is not set
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 # CONFIG_IOMMU_SUPPORT is not set
@@ -63,4 +63,3 @@ CONFIG_NFS_FS=y
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
 # CONFIG_DEBUG_PREEMPT is not set
-CONFIG_XZ_DEC=y
diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig
index f68838e8068a..cfaa33cb5921 100644
--- a/arch/arc/configs/nsim_hs_defconfig
+++ b/arch/arc/configs/nsim_hs_defconfig
@@ -35,6 +35,7 @@ CONFIG_UNIX_DIAG=y
 CONFIG_NET_KEY=y
 CONFIG_INET=y
 # CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -49,7 +50,6 @@ CONFIG_SERIAL_ARC=y
 CONFIG_SERIAL_ARC_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
-# CONFIG_VGA_CONSOLE is not set
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 # CONFIG_IOMMU_SUPPORT is not set
@@ -61,4 +61,3 @@ CONFIG_NFS_FS=y
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
 # CONFIG_DEBUG_PREEMPT is not set
-CONFIG_XZ_DEC=y
diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig
index 96bd1c20fb0b..bb2a8dc778b5 100644
--- a/arch/arc/configs/nsim_hs_smp_defconfig
+++ b/arch/arc/configs/nsim_hs_smp_defconfig
@@ -2,6 +2,7 @@ CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
+# CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
@@ -21,13 +22,11 @@ CONFIG_MODULES=y
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARC_PLAT_SIM=y
-CONFIG_ARC_BOARD_ML509=y
 CONFIG_ISA_ARCV2=y
 CONFIG_SMP=y
 CONFIG_ARC_BUILTIN_DTB_NAME="nsim_hs_idu"
 CONFIG_PREEMPT=y
 # CONFIG_COMPACTION is not set
-# CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -35,6 +34,7 @@ CONFIG_UNIX_DIAG=y
 CONFIG_NET_KEY=y
 CONFIG_INET=y
 # CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -49,7 +49,6 @@ CONFIG_SERIAL_ARC=y
 CONFIG_SERIAL_ARC_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
-# CONFIG_VGA_CONSOLE is not set
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 # CONFIG_IOMMU_SUPPORT is not set
@@ -60,4 +59,3 @@ CONFIG_TMPFS=y
 CONFIG_NFS_FS=y
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
-CONFIG_XZ_DEC=y
diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig
index 31e1d95764ff..646182e93753 100644
--- a/arch/arc/configs/nsimosci_defconfig
+++ b/arch/arc/configs/nsimosci_defconfig
@@ -33,6 +33,7 @@ CONFIG_UNIX_DIAG=y
 CONFIG_NET_KEY=y
 CONFIG_INET=y
 # CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -58,7 +59,6 @@ CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_HID is not set
diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig
index fcae66683ca0..ceca2541950d 100644
--- a/arch/arc/configs/nsimosci_hs_defconfig
+++ b/arch/arc/configs/nsimosci_hs_defconfig
@@ -34,12 +34,12 @@ CONFIG_UNIX_DIAG=y
 CONFIG_NET_KEY=y
 CONFIG_INET=y
 # CONFIG_IPV6 is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_BLK_DEV is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_OSCI_LAN=y
 CONFIG_INPUT_EVDEV=y
 # CONFIG_MOUSE_PS2_ALPS is not set
 # CONFIG_MOUSE_PS2_LOGIPS2PP is not set
@@ -58,7 +58,6 @@ CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_HID is not set
diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig
index b01b659168ea..4b6da90f6f26 100644
--- a/arch/arc/configs/nsimosci_hs_smp_defconfig
+++ b/arch/arc/configs/nsimosci_hs_smp_defconfig
@@ -2,6 +2,7 @@ CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
@@ -18,15 +19,11 @@ CONFIG_MODULES=y
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARC_PLAT_SIM=y
-CONFIG_ARC_BOARD_ML509=y
 CONFIG_ISA_ARCV2=y
 CONFIG_SMP=y
-CONFIG_ARC_HAS_LL64=y
-# CONFIG_ARC_HAS_RTSC is not set
 CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs_idu"
 CONFIG_PREEMPT=y
 # CONFIG_COMPACTION is not set
-# CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_PACKET_DIAG=y
@@ -40,6 +37,7 @@ CONFIG_INET=y
 # CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -56,14 +54,11 @@ CONFIG_NETDEVICES=y
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-CONFIG_NET_OSCI_LAN=y
 # CONFIG_WLAN is not set
 CONFIG_INPUT_EVDEV=y
 CONFIG_MOUSE_PS2_TOUCHKIT=y
 # CONFIG_SERIO_SERPORT is not set
-CONFIG_SERIO_LIBPS2=y
 CONFIG_SERIO_ARC_PS2=y
-CONFIG_VT_HW_CONSOLE_BINDING=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
@@ -75,9 +70,6 @@ CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-CONFIG_ARCPGU_RGB888=y
-CONFIG_ARCPGU_DISPTYPE=0
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_HID is not set
diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig
index 3b4dc9cebcf1..9b342eaf95ae 100644
--- a/arch/arc/configs/tb10x_defconfig
+++ b/arch/arc/configs/tb10x_defconfig
@@ -3,6 +3,7 @@ CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="tb10x"
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
+# CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
@@ -26,12 +27,10 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLOCK is not set
 CONFIG_ARC_PLAT_TB10X=y
 CONFIG_ARC_CACHE_LINE_SHIFT=5
-CONFIG_ARC_STACK_NONEXEC=y
 CONFIG_HZ=250
 CONFIG_ARC_BUILTIN_DTB_NAME="abilis_tb100_dvk"
 CONFIG_PREEMPT_VOLUNTARY=y
 # CONFIG_COMPACTION is not set
-# CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -44,8 +43,8 @@ CONFIG_IP_MULTICAST=y
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
-CONFIG_PROC_DEVICETREE=y
 CONFIG_NETDEVICES=y
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
@@ -55,9 +54,6 @@ CONFIG_NETDEVICES=y
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
 CONFIG_STMMAC_ETH=y
-CONFIG_STMMAC_DEBUG_FS=y
-CONFIG_STMMAC_DA=y
-CONFIG_STMMAC_CHAINED=y
 # CONFIG_NET_VENDOR_WIZNET is not set
 # CONFIG_WLAN is not set
 # CONFIG_INPUT is not set
@@ -91,7 +87,6 @@ CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
 CONFIG_LEDS_TRIGGER_TRANSIENT=y
 CONFIG_DMADEVICES=y
 CONFIG_DW_DMAC=y
-CONFIG_NET_DMA=y
 CONFIG_ASYNC_TX_DMA=y
 # CONFIG_IOMMU_SUPPORT is not set
 # CONFIG_DNOTIFY is not set
@@ -100,17 +95,16 @@ CONFIG_TMPFS=y
 CONFIG_CONFIGFS_FS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 # CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_DEBUG_INFO=y
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
-CONFIG_MAGIC_SYSRQ=y
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_DEBUG_FS=y
 CONFIG_HEADERS_CHECK=y
 CONFIG_DEBUG_SECTION_MISMATCH=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_DEBUG_STACKOVERFLOW=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_SCHEDSTATS=y
 CONFIG_TIMER_STATS=y
-CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_MEMORY_INIT=y
-CONFIG_DEBUG_STACKOVERFLOW=y
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig
index f36c047b33ca..735985974a31 100644
--- a/arch/arc/configs/vdk_hs38_smp_defconfig
+++ b/arch/arc/configs/vdk_hs38_smp_defconfig
@@ -16,7 +16,7 @@ CONFIG_ARC_PLAT_AXS10X=y
 CONFIG_AXS103=y
 CONFIG_ISA_ARCV2=y
 CONFIG_SMP=y
-# CONFIG_ARC_HAS_GRTC is not set
+# CONFIG_ARC_HAS_GFRC is not set
 CONFIG_ARC_UBOOT_SUPPORT=y
 CONFIG_ARC_BUILTIN_DTB_NAME="vdk_hs38_smp"
 CONFIG_PREEMPT=y
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index 7fac7d85ed6a..f9f4c6f59fdb 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -10,7 +10,8 @@
 #define _ASM_ARC_ARCREGS_H
 
 /* Build Configuration Registers */
-#define ARC_REG_DCCMBASE_BCR	0x61	/* DCCM Base Addr */
+#define ARC_REG_AUX_DCCM	0x18	/* DCCM Base Addr ARCv2 */
+#define ARC_REG_DCCM_BASE_BUILD	0x61	/* DCCM Base Addr ARCompact */
 #define ARC_REG_CRC_BCR		0x62
 #define ARC_REG_VECBASE_BCR	0x68
 #define ARC_REG_PERIBASE_BCR	0x69
@@ -18,10 +19,10 @@
 #define ARC_REG_DPFP_BCR	0x6C	/* ARCompact: Dbl Precision FPU */
 #define ARC_REG_FP_V2_BCR	0xc8	/* ARCv2 FPU */
 #define ARC_REG_SLC_BCR		0xce
-#define ARC_REG_DCCM_BCR	0x74	/* DCCM Present + SZ */
+#define ARC_REG_DCCM_BUILD	0x74	/* DCCM size (common) */
 #define ARC_REG_TIMERS_BCR	0x75
 #define ARC_REG_AP_BCR		0x76
-#define ARC_REG_ICCM_BCR	0x78
+#define ARC_REG_ICCM_BUILD	0x78	/* ICCM size (common) */
 #define ARC_REG_XY_MEM_BCR	0x79
 #define ARC_REG_MAC_BCR		0x7a
 #define ARC_REG_MUL_BCR		0x7b
@@ -36,6 +37,7 @@
 #define ARC_REG_IRQ_BCR		0xF3
 #define ARC_REG_SMART_BCR	0xFF
 #define ARC_REG_CLUSTER_BCR	0xcf
+#define ARC_REG_AUX_ICCM	0x208	/* ICCM Base Addr (ARCv2) */
 
 /* status32 Bits Positions */
 #define STATUS_AE_BIT		5	/* Exception active */
@@ -246,7 +248,7 @@ struct bcr_perip {
 #endif
 };
 
-struct bcr_iccm {
+struct bcr_iccm_arcompact {
 #ifdef CONFIG_CPU_BIG_ENDIAN
 	unsigned int base:16, pad:5, sz:3, ver:8;
 #else
@@ -254,17 +256,15 @@ struct bcr_iccm {
 #endif
 };
 
-/* DCCM Base Address Register: ARC_REG_DCCMBASE_BCR */
-struct bcr_dccm_base {
+struct bcr_iccm_arcv2 {
 #ifdef CONFIG_CPU_BIG_ENDIAN
-	unsigned int addr:24, ver:8;
+	unsigned int pad:8, sz11:4, sz01:4, sz10:4, sz00:4, ver:8;
 #else
-	unsigned int ver:8, addr:24;
+	unsigned int ver:8, sz00:4, sz10:4, sz01:4, sz11:4, pad:8;
 #endif
 };
 
-/* DCCM RAM Configuration Register: ARC_REG_DCCM_BCR */
-struct bcr_dccm {
+struct bcr_dccm_arcompact {
 #ifdef CONFIG_CPU_BIG_ENDIAN
 	unsigned int res:21, sz:3, ver:8;
 #else
@@ -272,6 +272,14 @@ struct bcr_dccm {
 #endif
 };
 
+struct bcr_dccm_arcv2 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad2:12, cyc:3, pad1:1, sz1:4, sz0:4, ver:8;
+#else
+	unsigned int ver:8, sz0:4, sz1:4, pad1:1, cyc:3, pad2:12;
+#endif
+};
+
 /* ARCompact: Both SP and DP FPU BCRs have same format */
 struct bcr_fp_arcompact {
 #ifdef CONFIG_CPU_BIG_ENDIAN
@@ -315,9 +323,9 @@ struct bcr_bpu_arcv2 {
 
 struct bcr_generic {
 #ifdef CONFIG_CPU_BIG_ENDIAN
-	unsigned int pad:24, ver:8;
+	unsigned int info:24, ver:8;
 #else
-	unsigned int ver:8, pad:24;
+	unsigned int ver:8, info:24;
 #endif
 };
 
@@ -349,14 +357,13 @@ struct cpuinfo_arc {
 	struct cpuinfo_arc_bpu bpu;
 	struct bcr_identity core;
 	struct bcr_isa isa;
-	struct bcr_timer timers;
 	unsigned int vec_base;
 	struct cpuinfo_arc_ccm iccm, dccm;
 	struct {
 		unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, pad1:3,
 			     fpu_sp:1, fpu_dp:1, pad2:6,
 			     debug:1, ap:1, smart:1, rtt:1, pad3:4,
-			     pad4:8;
+			     timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4;
 	} extn;
 	struct bcr_mpy extn_mpy;
 	struct bcr_extn_xymem extn_xymem;
diff --git a/arch/arc/include/asm/dma.h b/arch/arc/include/asm/dma.h
index ca7c45181de9..01e47a69b034 100644
--- a/arch/arc/include/asm/dma.h
+++ b/arch/arc/include/asm/dma.h
@@ -10,5 +10,10 @@
 #define ASM_ARC_DMA_H
 
 #define MAX_DMA_ADDRESS 0xC0000000
+#ifdef CONFIG_PCI
+extern int isa_dma_bridge_buggy;
+#else
+#define isa_dma_bridge_buggy	0
+#endif
 
 #endif
diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h
index 694ece8a0243..947bf0cfdec0 100644
--- a/arch/arc/include/asm/io.h
+++ b/arch/arc/include/asm/io.h
@@ -16,6 +16,15 @@
 extern void __iomem *ioremap(unsigned long physaddr, unsigned long size);
 extern void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
 				  unsigned long flags);
+static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
+{
+	return (void __iomem *)port;
+}
+
+static inline void ioport_unmap(void __iomem *addr)
+{
+}
+
 extern void iounmap(const void __iomem *addr);
 
 #define ioremap_nocache(phy, sz)	ioremap(phy, sz)
diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h
index 4fd7d62a6e30..49014f0ef36d 100644
--- a/arch/arc/include/asm/irq.h
+++ b/arch/arc/include/asm/irq.h
@@ -16,11 +16,9 @@
 #ifdef CONFIG_ISA_ARCOMPACT
 #define TIMER0_IRQ      3
 #define TIMER1_IRQ      4
-#define IPI_IRQ		(NR_CPU_IRQS-1) /* dummy to enable SMP build for up hardware */
 #else
 #define TIMER0_IRQ      16
 #define TIMER1_IRQ      17
-#define IPI_IRQ         19
 #endif
 
 #include <linux/interrupt.h>
diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h
index 258b0e5ad332..37c2f751eebf 100644
--- a/arch/arc/include/asm/irqflags-arcv2.h
+++ b/arch/arc/include/asm/irqflags-arcv2.h
@@ -22,6 +22,7 @@
 #define AUX_IRQ_CTRL		0x00E
 #define AUX_IRQ_ACT		0x043	/* Active Intr across all levels */
 #define AUX_IRQ_LVL_PEND	0x200	/* Pending Intr across all levels */
+#define AUX_IRQ_HINT		0x201	/* For generating Soft Interrupts */
 #define AUX_IRQ_PRIORITY	0x206
 #define ICAUSE			0x40a
 #define AUX_IRQ_SELECT		0x40b
@@ -30,8 +31,11 @@
 /* Was Intr taken in User Mode */
 #define AUX_IRQ_ACT_BIT_U	31
 
-/* 0 is highest level, but taken by FIRQs, if present in design */
-#define ARCV2_IRQ_DEF_PRIO		0
+/*
+ * User space should be interruptable even by lowest prio interrupt
+ * Safe even if actual interrupt priorities is fewer or even one
+ */
+#define ARCV2_IRQ_DEF_PRIO	15
 
 /* seed value for status register */
 #define ISA_INIT_STATUS_BITS	(STATUS_IE_MASK | STATUS_AD_MASK | \
@@ -112,6 +116,16 @@ static inline int arch_irqs_disabled(void)
 	return arch_irqs_disabled_flags(arch_local_save_flags());
 }
 
+static inline void arc_softirq_trigger(int irq)
+{
+	write_aux_reg(AUX_IRQ_HINT, irq);
+}
+
+static inline void arc_softirq_clear(int irq)
+{
+	write_aux_reg(AUX_IRQ_HINT, 0);
+}
+
 #else
 
 .macro IRQ_DISABLE  scratch
diff --git a/arch/arc/include/asm/mcip.h b/arch/arc/include/asm/mcip.h
index 46f4e5351b2a..847e3bbe387f 100644
--- a/arch/arc/include/asm/mcip.h
+++ b/arch/arc/include/asm/mcip.h
@@ -39,8 +39,8 @@ struct mcip_cmd {
 #define CMD_DEBUG_SET_MASK		0x34
 #define CMD_DEBUG_SET_SELECT		0x36
 
-#define CMD_GRTC_READ_LO		0x42
-#define CMD_GRTC_READ_HI		0x43
+#define CMD_GFRC_READ_LO		0x42
+#define CMD_GFRC_READ_HI		0x43
 
 #define CMD_IDU_ENABLE			0x71
 #define CMD_IDU_DISABLE			0x72
diff --git a/arch/arc/include/asm/pci.h b/arch/arc/include/asm/pci.h
new file mode 100644
index 000000000000..ba56c23c1b20
--- /dev/null
+++ b/arch/arc/include/asm/pci.h
@@ -0,0 +1,28 @@
+/*
+ * Copyright (C) 2015-2016 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_PCI_H
+#define _ASM_ARC_PCI_H
+
+#ifdef __KERNEL__
+#include <linux/ioport.h>
+
+#define PCIBIOS_MIN_IO 0x100
+#define PCIBIOS_MIN_MEM 0x100000
+
+#define pcibios_assign_all_busses()	1
+/*
+ * The PCI address space does equal the physical memory address space.
+ * The networking and block device layers use this boolean for bounce
+ * buffer decisions.
+ */
+#define PCI_DMA_BUS_IS_PHYS	1
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_ARC_PCI_H */
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 57af2f05ae84..d426d4215513 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -179,37 +179,44 @@
 #define __S111  PAGE_U_X_W_R
 
 /****************************************************************
- * Page Table Lookup split
+ * 2 tier (PGD:PTE) software page walker
  *
- * We implement 2 tier paging and since this is all software, we are free
- * to customize the span of a PGD / PTE entry to suit us
- *
- *			32 bit virtual address
+ * [31]		    32 bit virtual address              [0]
  * -------------------------------------------------------
- * | BITS_FOR_PGD    |  BITS_FOR_PTE    |  BITS_IN_PAGE  |
+ * |               | <------------ PGDIR_SHIFT ----------> |
+ * |		   |					 |
+ * | BITS_FOR_PGD  |  BITS_FOR_PTE  | <-- PAGE_SHIFT --> |
  * -------------------------------------------------------
  *       |                  |                |
  *       |                  |                --> off in page frame
- *       |		    |
  *       |                  ---> index into Page Table
- *       |
  *       ----> index into Page Directory
+ *
+ * In a single page size configuration, only PAGE_SHIFT is fixed
+ * So both PGD and PTE sizing can be tweaked
+ *  e.g. 8K page (PAGE_SHIFT 13) can have
+ *  - PGDIR_SHIFT 21  -> 11:8:13 address split
+ *  - PGDIR_SHIFT 24  -> 8:11:13 address split
+ *
+ * If Super Page is configured, PGDIR_SHIFT becomes fixed too,
+ * so the sizing flexibility is gone.
  */
 
-#define BITS_IN_PAGE	PAGE_SHIFT
-
-/* Optimal Sizing of Pg Tbl - based on MMU page size */
-#if defined(CONFIG_ARC_PAGE_SIZE_8K)
-#define BITS_FOR_PTE	8		/* 11:8:13 */
-#elif defined(CONFIG_ARC_PAGE_SIZE_16K)
-#define BITS_FOR_PTE	8		/* 10:8:14 */
-#elif defined(CONFIG_ARC_PAGE_SIZE_4K)
-#define BITS_FOR_PTE	9		/* 11:9:12 */
+#if defined(CONFIG_ARC_HUGEPAGE_16M)
+#define PGDIR_SHIFT	24
+#elif defined(CONFIG_ARC_HUGEPAGE_2M)
+#define PGDIR_SHIFT	21
+#else
+/*
+ * Only Normal page support so "hackable" (see comment above)
+ * Default value provides 11:8:13 (8K), 11:9:12 (4K)
+ */
+#define PGDIR_SHIFT	21
 #endif
 
-#define BITS_FOR_PGD	(32 - BITS_FOR_PTE - BITS_IN_PAGE)
+#define BITS_FOR_PTE	(PGDIR_SHIFT - PAGE_SHIFT)
+#define BITS_FOR_PGD	(32 - PGDIR_SHIFT)
 
-#define PGDIR_SHIFT	(32 - BITS_FOR_PGD)
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)	/* vaddr span, not PDG sz */
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
diff --git a/arch/arc/kernel/Makefile b/arch/arc/kernel/Makefile
index e7f3625a19b5..1bc2036b19d7 100644
--- a/arch/arc/kernel/Makefile
+++ b/arch/arc/kernel/Makefile
@@ -12,6 +12,7 @@ obj-y	:= arcksyms.o setup.o irq.o time.o reset.o ptrace.o process.o devtree.o
 obj-y	+= signal.o traps.o sys.o troubleshoot.o stacktrace.o disasm.o clk.o
 obj-$(CONFIG_ISA_ARCOMPACT)		+= entry-compact.o intc-compact.o
 obj-$(CONFIG_ISA_ARCV2)			+= entry-arcv2.o intc-arcv2.o
+obj-$(CONFIG_PCI)  			+= pcibios.o
 
 obj-$(CONFIG_MODULES)			+= arcksyms.o module.o
 obj-$(CONFIG_SMP) 			+= smp.o
diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S
index cbfec79137bf..c1264607bbff 100644
--- a/arch/arc/kernel/entry-arcv2.S
+++ b/arch/arc/kernel/entry-arcv2.S
@@ -45,11 +45,12 @@ VECTOR	reserved		; Reserved slots
 VECTOR	handle_interrupt	; (16) Timer0
 VECTOR	handle_interrupt	; unused (Timer1)
 VECTOR	handle_interrupt	; unused (WDT)
-VECTOR	handle_interrupt	; (19) ICI (inter core interrupt)
-VECTOR	handle_interrupt
-VECTOR	handle_interrupt
-VECTOR	handle_interrupt
-VECTOR	handle_interrupt	; (23) End of fixed IRQs
+VECTOR	handle_interrupt	; (19) Inter core Interrupt (IPI)
+VECTOR	handle_interrupt	; (20) perf Interrupt
+VECTOR	handle_interrupt	; (21) Software Triggered Intr (Self IPI)
+VECTOR	handle_interrupt	; unused
+VECTOR	handle_interrupt	; (23) unused
+# End of fixed IRQs
 
 .rept CONFIG_ARC_NUMBER_OF_INTERRUPTS - 8
 	VECTOR	handle_interrupt
@@ -211,7 +212,11 @@ debug_marker_syscall:
 ; (since IRQ NOT allowed in DS in ARCv2, this can only happen if orig
 ; entry was via Exception in DS which got preempted in kernel).
 ;
-; IRQ RTIE won't reliably restore DE bit and/or BTA, needs handling
+; IRQ RTIE won't reliably restore DE bit and/or BTA, needs workaround
+;
+; Solution is return from Intr w/o any delay slot quirks into a kernel trampoline
+; and from pure kernel mode return to delay slot which handles DS bit/BTA correctly
+
 .Lintr_ret_to_delay_slot:
 debug_marker_ds:
 
@@ -222,18 +227,23 @@ debug_marker_ds:
 	ld	r2, [sp, PT_ret]
 	ld	r3, [sp, PT_status32]
 
+	; STAT32 for Int return created from scratch
+	; (No delay dlot, disable Further intr in trampoline)
+
 	bic  	r0, r3, STATUS_U_MASK|STATUS_DE_MASK|STATUS_IE_MASK|STATUS_L_MASK
 	st	r0, [sp, PT_status32]
 
 	mov	r1, .Lintr_ret_to_delay_slot_2
 	st	r1, [sp, PT_ret]
 
+	; Orig exception PC/STAT32 safekept @orig_r0 and @event stack slots
 	st	r2, [sp, 0]
 	st	r3, [sp, 4]
 
 	b	.Lisr_ret_fast_path
 
 .Lintr_ret_to_delay_slot_2:
+	; Trampoline to restore orig exception PC/STAT32/BTA/AUX_USER_SP
 	sub	sp, sp, SZ_PT_REGS
 	st	r9, [sp, -4]
 
@@ -243,11 +253,19 @@ debug_marker_ds:
 	ld	r9, [sp, 4]
 	sr	r9, [erstatus]
 
+	; restore AUX_USER_SP if returning to U mode
+	bbit0	r9, STATUS_U_BIT, 1f
+	ld	r9, [sp, PT_sp]
+	sr	r9, [AUX_USER_SP]
+
+1:
 	ld	r9, [sp, 8]
 	sr	r9, [erbta]
 
 	ld	r9, [sp, -4]
 	add	sp, sp, SZ_PT_REGS
+
+	; return from pure kernel mode to delay slot
 	rtie
 
 END(ret_from_exception)
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
index 0394f9f61b46..942526322ae7 100644
--- a/arch/arc/kernel/intc-arcv2.c
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -14,6 +14,8 @@
 #include <linux/irqchip.h>
 #include <asm/irq.h>
 
+static int irq_prio;
+
 /*
  * Early Hardware specific Interrupt setup
  * -Called very early (start_kernel -> setup_arch -> setup_processor)
@@ -24,6 +26,14 @@ void arc_init_IRQ(void)
 {
 	unsigned int tmp;
 
+	struct irq_build {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+		unsigned int pad:3, firq:1, prio:4, exts:8, irqs:8, ver:8;
+#else
+		unsigned int ver:8, irqs:8, exts:8, prio:4, firq:1, pad:3;
+#endif
+	} irq_bcr;
+
 	struct aux_irq_ctrl {
 #ifdef CONFIG_CPU_BIG_ENDIAN
 		unsigned int res3:18, save_idx_regs:1, res2:1,
@@ -46,28 +56,25 @@ void arc_init_IRQ(void)
 
 	WRITE_AUX(AUX_IRQ_CTRL, ictrl);
 
-	/* setup status32, don't enable intr yet as kernel doesn't want */
-	tmp = read_aux_reg(0xa);
-	tmp |= ISA_INIT_STATUS_BITS;
-	tmp &= ~STATUS_IE_MASK;
-	asm volatile("flag %0	\n"::"r"(tmp));
-
 	/*
 	 * ARCv2 core intc provides multiple interrupt priorities (upto 16).
 	 * Typical builds though have only two levels (0-high, 1-low)
 	 * Linux by default uses lower prio 1 for most irqs, reserving 0 for
 	 * NMI style interrupts in future (say perf)
-	 *
-	 * Read the intc BCR to confirm that Linux default priority is avail
-	 * in h/w
-	 *
-	 * Note:
-	 *  IRQ_BCR[27..24] contains N-1 (for N priority levels) and prio level
-	 *  is 0 based.
 	 */
-	tmp = (read_aux_reg(ARC_REG_IRQ_BCR) >> 24 ) & 0xF;
-	if (ARCV2_IRQ_DEF_PRIO > tmp)
-		panic("Linux default irq prio incorrect\n");
+
+	READ_BCR(ARC_REG_IRQ_BCR, irq_bcr);
+
+	irq_prio = irq_bcr.prio;	/* Encoded as N-1 for N levels */
+	pr_info("archs-intc\t: %d priority levels (default %d)%s\n",
+		irq_prio + 1, irq_prio,
+		irq_bcr.firq ? " FIRQ (not used)":"");
+
+	/* setup status32, don't enable intr yet as kernel doesn't want */
+	tmp = read_aux_reg(0xa);
+	tmp |= STATUS_AD_MASK | (irq_prio << 1);
+	tmp &= ~STATUS_IE_MASK;
+	asm volatile("flag %0	\n"::"r"(tmp));
 }
 
 static void arcv2_irq_mask(struct irq_data *data)
@@ -86,7 +93,7 @@ void arcv2_irq_enable(struct irq_data *data)
 {
 	/* set default priority */
 	write_aux_reg(AUX_IRQ_SELECT, data->irq);
-	write_aux_reg(AUX_IRQ_PRIORITY, ARCV2_IRQ_DEF_PRIO);
+	write_aux_reg(AUX_IRQ_PRIORITY, irq_prio);
 
 	/*
 	 * hw auto enables (linux unmask) all by default
diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c
index 06bcedf19b62..224d1c3aa9c4 100644
--- a/arch/arc/kernel/intc-compact.c
+++ b/arch/arc/kernel/intc-compact.c
@@ -81,9 +81,6 @@ static int arc_intc_domain_map(struct irq_domain *d, unsigned int irq,
 {
 	switch (irq) {
 	case TIMER0_IRQ:
-#ifdef CONFIG_SMP
-	case IPI_IRQ:
-#endif
 		irq_set_chip_and_handler(irq, &onchip_intc, handle_percpu_irq);
 		break;
 	default:
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index bd237acdf4f2..c41c364b926c 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -11,9 +11,13 @@
 #include <linux/smp.h>
 #include <linux/irq.h>
 #include <linux/spinlock.h>
+#include <asm/irqflags-arcv2.h>
 #include <asm/mcip.h>
 #include <asm/setup.h>
 
+#define IPI_IRQ		19
+#define SOFTIRQ_IRQ	21
+
 static char smp_cpuinfo_buf[128];
 static int idu_detected;
 
@@ -22,6 +26,7 @@ static DEFINE_RAW_SPINLOCK(mcip_lock);
 static void mcip_setup_per_cpu(int cpu)
 {
 	smp_ipi_irq_setup(cpu, IPI_IRQ);
+	smp_ipi_irq_setup(cpu, SOFTIRQ_IRQ);
 }
 
 static void mcip_ipi_send(int cpu)
@@ -29,46 +34,44 @@ static void mcip_ipi_send(int cpu)
 	unsigned long flags;
 	int ipi_was_pending;
 
+	/* ARConnect can only send IPI to others */
+	if (unlikely(cpu == raw_smp_processor_id())) {
+		arc_softirq_trigger(SOFTIRQ_IRQ);
+		return;
+	}
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+
 	/*
-	 * NOTE: We must spin here if the other cpu hasn't yet
-	 * serviced a previous message. This can burn lots
-	 * of time, but we MUST follows this protocol or
-	 * ipi messages can be lost!!!
-	 * Also, we must release the lock in this loop because
-	 * the other side may get to this same loop and not
-	 * be able to ack -- thus causing deadlock.
+	 * If receiver already has a pending interrupt, elide sending this one.
+	 * Linux cross core calling works well with concurrent IPIs
+	 * coalesced into one
+	 * see arch/arc/kernel/smp.c: ipi_send_msg_one()
 	 */
+	__mcip_cmd(CMD_INTRPT_READ_STATUS, cpu);
+	ipi_was_pending = read_aux_reg(ARC_REG_MCIP_READBACK);
+	if (!ipi_was_pending)
+		__mcip_cmd(CMD_INTRPT_GENERATE_IRQ, cpu);
 
-	do {
-		raw_spin_lock_irqsave(&mcip_lock, flags);
-		__mcip_cmd(CMD_INTRPT_READ_STATUS, cpu);
-		ipi_was_pending = read_aux_reg(ARC_REG_MCIP_READBACK);
-		if (ipi_was_pending == 0)
-			break; /* break out but keep lock */
-		raw_spin_unlock_irqrestore(&mcip_lock, flags);
-	} while (1);
-
-	__mcip_cmd(CMD_INTRPT_GENERATE_IRQ, cpu);
 	raw_spin_unlock_irqrestore(&mcip_lock, flags);
-
-#ifdef CONFIG_ARC_IPI_DBG
-	if (ipi_was_pending)
-		pr_info("IPI ACK delayed from cpu %d\n", cpu);
-#endif
 }
 
 static void mcip_ipi_clear(int irq)
 {
 	unsigned int cpu, c;
 	unsigned long flags;
-	unsigned int __maybe_unused copy;
+
+	if (unlikely(irq == SOFTIRQ_IRQ)) {
+		arc_softirq_clear(irq);
+		return;
+	}
 
 	raw_spin_lock_irqsave(&mcip_lock, flags);
 
 	/* Who sent the IPI */
 	__mcip_cmd(CMD_INTRPT_CHECK_SOURCE, 0);
 
-	copy = cpu = read_aux_reg(ARC_REG_MCIP_READBACK);	/* 1,2,4,8... */
+	cpu = read_aux_reg(ARC_REG_MCIP_READBACK);	/* 1,2,4,8... */
 
 	/*
 	 * In rare case, multiple concurrent IPIs sent to same target can
@@ -82,12 +85,6 @@ static void mcip_ipi_clear(int irq)
 	} while (cpu);
 
 	raw_spin_unlock_irqrestore(&mcip_lock, flags);
-
-#ifdef CONFIG_ARC_IPI_DBG
-	if (c != __ffs(copy))
-		pr_info("IPIs from %x coalesced to %x\n",
-			copy, raw_smp_processor_id());
-#endif
 }
 
 static void mcip_probe_n_setup(void)
@@ -96,13 +93,13 @@ static void mcip_probe_n_setup(void)
 #ifdef CONFIG_CPU_BIG_ENDIAN
 		unsigned int pad3:8,
 			     idu:1, llm:1, num_cores:6,
-			     iocoh:1,  grtc:1, dbg:1, pad2:1,
+			     iocoh:1,  gfrc:1, dbg:1, pad2:1,
 			     msg:1, sem:1, ipi:1, pad:1,
 			     ver:8;
 #else
 		unsigned int ver:8,
 			     pad:1, ipi:1, sem:1, msg:1,
-			     pad2:1, dbg:1, grtc:1, iocoh:1,
+			     pad2:1, dbg:1, gfrc:1, iocoh:1,
 			     num_cores:6, llm:1, idu:1,
 			     pad3:8;
 #endif
@@ -111,12 +108,13 @@ static void mcip_probe_n_setup(void)
 	READ_BCR(ARC_REG_MCIP_BCR, mp);
 
 	sprintf(smp_cpuinfo_buf,
-		"Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s\n",
+		"Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s%s\n",
 		mp.ver, mp.num_cores,
 		IS_AVAIL1(mp.ipi, "IPI "),
 		IS_AVAIL1(mp.idu, "IDU "),
+		IS_AVAIL1(mp.llm, "LLM "),
 		IS_AVAIL1(mp.dbg, "DEBUG "),
-		IS_AVAIL1(mp.grtc, "GRTC"));
+		IS_AVAIL1(mp.gfrc, "GFRC"));
 
 	idu_detected = mp.idu;
 
@@ -125,8 +123,8 @@ static void mcip_probe_n_setup(void)
 		__mcip_cmd_data(CMD_DEBUG_SET_MASK, 0xf, 0xf);
 	}
 
-	if (IS_ENABLED(CONFIG_ARC_HAS_GRTC) && !mp.grtc)
-		panic("kernel trying to use non-existent GRTC\n");
+	if (IS_ENABLED(CONFIG_ARC_HAS_GFRC) && !mp.gfrc)
+		panic("kernel trying to use non-existent GFRC\n");
 }
 
 struct plat_smp_ops plat_smp_ops = {
diff --git a/arch/arc/kernel/pcibios.c b/arch/arc/kernel/pcibios.c
new file mode 100644
index 000000000000..72e1d73d0bd6
--- /dev/null
+++ b/arch/arc/kernel/pcibios.c
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2014-2015 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/pci.h>
+
+/*
+ * We don't have to worry about legacy ISA devices, so nothing to do here
+ */
+resource_size_t pcibios_align_resource(void *data, const struct resource *res,
+				resource_size_t size, resource_size_t align)
+{
+	return res->start;
+}
+
+void pcibios_fixup_bus(struct pci_bus *bus)
+{
+}
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index e1b87444ea9a..cdc821df1809 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -42,9 +42,57 @@ struct task_struct *_current_task[NR_CPUS];	/* For stack switching */
 
 struct cpuinfo_arc cpuinfo_arc700[NR_CPUS];
 
+static void read_decode_ccm_bcr(struct cpuinfo_arc *cpu)
+{
+	if (is_isa_arcompact()) {
+		struct bcr_iccm_arcompact iccm;
+		struct bcr_dccm_arcompact dccm;
+
+		READ_BCR(ARC_REG_ICCM_BUILD, iccm);
+		if (iccm.ver) {
+			cpu->iccm.sz = 4096 << iccm.sz;	/* 8K to 512K */
+			cpu->iccm.base_addr = iccm.base << 16;
+		}
+
+		READ_BCR(ARC_REG_DCCM_BUILD, dccm);
+		if (dccm.ver) {
+			unsigned long base;
+			cpu->dccm.sz = 2048 << dccm.sz;	/* 2K to 256K */
+
+			base = read_aux_reg(ARC_REG_DCCM_BASE_BUILD);
+			cpu->dccm.base_addr = base & ~0xF;
+		}
+	} else {
+		struct bcr_iccm_arcv2 iccm;
+		struct bcr_dccm_arcv2 dccm;
+		unsigned long region;
+
+		READ_BCR(ARC_REG_ICCM_BUILD, iccm);
+		if (iccm.ver) {
+			cpu->iccm.sz = 256 << iccm.sz00;	/* 512B to 16M */
+			if (iccm.sz00 == 0xF && iccm.sz01 > 0)
+				cpu->iccm.sz <<= iccm.sz01;
+
+			region = read_aux_reg(ARC_REG_AUX_ICCM);
+			cpu->iccm.base_addr = region & 0xF0000000;
+		}
+
+		READ_BCR(ARC_REG_DCCM_BUILD, dccm);
+		if (dccm.ver) {
+			cpu->dccm.sz = 256 << dccm.sz0;
+			if (dccm.sz0 == 0xF && dccm.sz1 > 0)
+				cpu->dccm.sz <<= dccm.sz1;
+
+			region = read_aux_reg(ARC_REG_AUX_DCCM);
+			cpu->dccm.base_addr = region & 0xF0000000;
+		}
+	}
+}
+
 static void read_arc_build_cfg_regs(void)
 {
 	struct bcr_perip uncached_space;
+	struct bcr_timer timer;
 	struct bcr_generic bcr;
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
 	unsigned long perip_space;
@@ -53,7 +101,11 @@ static void read_arc_build_cfg_regs(void)
 	READ_BCR(AUX_IDENTITY, cpu->core);
 	READ_BCR(ARC_REG_ISA_CFG_BCR, cpu->isa);
 
-	READ_BCR(ARC_REG_TIMERS_BCR, cpu->timers);
+	READ_BCR(ARC_REG_TIMERS_BCR, timer);
+	cpu->extn.timer0 = timer.t0;
+	cpu->extn.timer1 = timer.t1;
+	cpu->extn.rtc = timer.rtc;
+
 	cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE);
 
 	READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space);
@@ -71,36 +123,11 @@ static void read_arc_build_cfg_regs(void)
 	cpu->extn.swap = read_aux_reg(ARC_REG_SWAP_BCR) ? 1 : 0;        /* 1,3 */
 	cpu->extn.crc = read_aux_reg(ARC_REG_CRC_BCR) ? 1 : 0;
 	cpu->extn.minmax = read_aux_reg(ARC_REG_MIXMAX_BCR) > 1 ? 1 : 0; /* 2 */
-
-	/* Note that we read the CCM BCRs independent of kernel config
-	 * This is to catch the cases where user doesn't know that
-	 * CCMs are present in hardware build
-	 */
-	{
-		struct bcr_iccm iccm;
-		struct bcr_dccm dccm;
-		struct bcr_dccm_base dccm_base;
-		unsigned int bcr_32bit_val;
-
-		bcr_32bit_val = read_aux_reg(ARC_REG_ICCM_BCR);
-		if (bcr_32bit_val) {
-			iccm = *((struct bcr_iccm *)&bcr_32bit_val);
-			cpu->iccm.base_addr = iccm.base << 16;
-			cpu->iccm.sz = 0x2000 << (iccm.sz - 1);
-		}
-
-		bcr_32bit_val = read_aux_reg(ARC_REG_DCCM_BCR);
-		if (bcr_32bit_val) {
-			dccm = *((struct bcr_dccm *)&bcr_32bit_val);
-			cpu->dccm.sz = 0x800 << (dccm.sz);
-
-			READ_BCR(ARC_REG_DCCMBASE_BCR, dccm_base);
-			cpu->dccm.base_addr = dccm_base.addr << 8;
-		}
-	}
-
 	READ_BCR(ARC_REG_XY_MEM_BCR, cpu->extn_xymem);
 
+	/* Read CCM BCRs for boot reporting even if not enabled in Kconfig */
+	read_decode_ccm_bcr(cpu);
+
 	read_decode_mmu_bcr();
 	read_decode_cache_bcr();
 
@@ -208,9 +235,9 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 		       (unsigned int)(arc_get_core_freq() / 10000) % 100);
 
 	n += scnprintf(buf + n, len - n, "Timers\t\t: %s%s%s%s\nISA Extn\t: ",
-		       IS_AVAIL1(cpu->timers.t0, "Timer0 "),
-		       IS_AVAIL1(cpu->timers.t1, "Timer1 "),
-		       IS_AVAIL2(cpu->timers.rtc, "64-bit RTC ",
+		       IS_AVAIL1(cpu->extn.timer0, "Timer0 "),
+		       IS_AVAIL1(cpu->extn.timer1, "Timer1 "),
+		       IS_AVAIL2(cpu->extn.rtc, "Local-64-bit-Ctr ",
 				 CONFIG_ARC_HAS_RTC));
 
 	n += i = scnprintf(buf + n, len - n, "%s%s%s%s%s",
@@ -232,8 +259,6 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 
 			n += scnprintf(buf + n, len - n, "mpy[opt %d] ", opt);
 		}
-		n += scnprintf(buf + n, len - n, "%s",
-			       IS_USED_CFG(CONFIG_ARC_HAS_HW_MPY));
 	}
 
 	n += scnprintf(buf + n, len - n, "%s%s%s%s%s%s%s%s\n",
@@ -293,13 +318,13 @@ static void arc_chk_core_config(void)
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
 	int fpu_enabled;
 
-	if (!cpu->timers.t0)
+	if (!cpu->extn.timer0)
 		panic("Timer0 is not present!\n");
 
-	if (!cpu->timers.t1)
+	if (!cpu->extn.timer1)
 		panic("Timer1 is not present!\n");
 
-	if (IS_ENABLED(CONFIG_ARC_HAS_RTC) && !cpu->timers.rtc)
+	if (IS_ENABLED(CONFIG_ARC_HAS_RTC) && !cpu->extn.rtc)
 		panic("RTC is not present\n");
 
 #ifdef CONFIG_ARC_HAS_DCCM
@@ -334,6 +359,7 @@ static void arc_chk_core_config(void)
 		panic("FPU non-existent, disable CONFIG_ARC_FPU_SAVE_RESTORE\n");
 
 	if (is_isa_arcv2() && IS_ENABLED(CONFIG_SMP) && cpu->isa.atomic &&
+	    IS_ENABLED(CONFIG_ARC_HAS_LLSC) &&
 	    !IS_ENABLED(CONFIG_ARC_STAR_9000923308))
 		panic("llock/scond livelock workaround missing\n");
 }
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index ef6e9e15b82a..4cb3add77c75 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -142,7 +142,7 @@ void start_kernel_secondary(void)
 
 	local_irq_enable();
 	preempt_disable();
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
 /*
@@ -336,11 +336,8 @@ irqreturn_t do_IPI(int irq, void *dev_id)
 		int rc;
 
 		rc = __do_IPI(msg);
-#ifdef CONFIG_ARC_IPI_DBG
-		/* IPI received but no valid @msg */
 		if (rc)
 			pr_info("IPI with bogus msg %ld in %ld\n", msg, copy);
-#endif
 		pending &= ~(1U << msg);
 	} while (pending);
 
diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c
index dfad287f1db1..156d9833ff84 100644
--- a/arch/arc/kernel/time.c
+++ b/arch/arc/kernel/time.c
@@ -62,7 +62,7 @@
 
 /********** Clock Source Device *********/
 
-#ifdef CONFIG_ARC_HAS_GRTC
+#ifdef CONFIG_ARC_HAS_GFRC
 
 static int arc_counter_setup(void)
 {
@@ -83,10 +83,10 @@ static cycle_t arc_counter_read(struct clocksource *cs)
 
 	local_irq_save(flags);
 
-	__mcip_cmd(CMD_GRTC_READ_LO, 0);
+	__mcip_cmd(CMD_GFRC_READ_LO, 0);
 	stamp.l = read_aux_reg(ARC_REG_MCIP_READBACK);
 
-	__mcip_cmd(CMD_GRTC_READ_HI, 0);
+	__mcip_cmd(CMD_GFRC_READ_HI, 0);
 	stamp.h = read_aux_reg(ARC_REG_MCIP_READBACK);
 
 	local_irq_restore(flags);
@@ -95,7 +95,7 @@ static cycle_t arc_counter_read(struct clocksource *cs)
 }
 
 static struct clocksource arc_counter = {
-	.name   = "ARConnect GRTC",
+	.name   = "ARConnect GFRC",
 	.rating = 400,
 	.read   = arc_counter_read,
 	.mask   = CLOCKSOURCE_MASK(64),
diff --git a/arch/arc/plat-axs10x/Kconfig b/arch/arc/plat-axs10x/Kconfig
index d475f9d4847c..426ac4b8bb39 100644
--- a/arch/arc/plat-axs10x/Kconfig
+++ b/arch/arc/plat-axs10x/Kconfig
@@ -11,6 +11,7 @@ menuconfig ARC_PLAT_AXS10X
 	select DW_APB_ICTL
 	select GPIO_DWAPB
 	select OF_GPIO
+	select MIGHT_HAVE_PCI
 	select GENERIC_IRQ_CHIP
 	select ARCH_REQUIRE_GPIOLIB
 	help
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 4f799e567fc8..1d00da16d980 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1212,7 +1212,6 @@ config PCI_HOST_ITE8152
 	select DMABOUNCE
 
 source "drivers/pci/Kconfig"
-source "drivers/pci/pcie/Kconfig"
 
 source "drivers/pcmcia/Kconfig"
 
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 7a6a58ef8aaf..43788b1a1ac5 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -195,5 +195,7 @@ CFLAGS_font.o := -Dstatic=
 $(obj)/font.c: $(FONTC)
 	$(call cmd,shipped)
 
+AFLAGS_hyp-stub.o := -Wa,-march=armv7-a
+
 $(obj)/hyp-stub.S: $(srctree)/arch/$(SRCARCH)/kernel/hyp-stub.S
 	$(call cmd,shipped)
diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi
index f3db13d2d90e..0cc150b87b86 100644
--- a/arch/arm/boot/dts/am335x-bone-common.dtsi
+++ b/arch/arm/boot/dts/am335x-bone-common.dtsi
@@ -285,8 +285,10 @@
 	};
 };
 
+
+/include/ "tps65217.dtsi"
+
 &tps {
-	compatible = "ti,tps65217";
 	/*
 	 * Configure pmic to enter OFF-state instead of SLEEP-state ("RTC-only
 	 * mode") at poweroff.  Most BeagleBone versions do not support RTC-only
@@ -307,17 +309,12 @@
 	ti,pmic-shutdown-controller;
 
 	regulators {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
 		dcdc1_reg: regulator@0 {
-			reg = <0>;
 			regulator-name = "vdds_dpr";
 			regulator-always-on;
 		};
 
 		dcdc2_reg: regulator@1 {
-			reg = <1>;
 			/* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */
 			regulator-name = "vdd_mpu";
 			regulator-min-microvolt = <925000>;
@@ -327,7 +324,6 @@
 		};
 
 		dcdc3_reg: regulator@2 {
-			reg = <2>;
 			/* VDD_CORE voltage limits 0.95V - 1.1V with +/-4% tolerance */
 			regulator-name = "vdd_core";
 			regulator-min-microvolt = <925000>;
@@ -337,25 +333,21 @@
 		};
 
 		ldo1_reg: regulator@3 {
-			reg = <3>;
 			regulator-name = "vio,vrtc,vdds";
 			regulator-always-on;
 		};
 
 		ldo2_reg: regulator@4 {
-			reg = <4>;
 			regulator-name = "vdd_3v3aux";
 			regulator-always-on;
 		};
 
 		ldo3_reg: regulator@5 {
-			reg = <5>;
 			regulator-name = "vdd_1v8";
 			regulator-always-on;
 		};
 
 		ldo4_reg: regulator@6 {
-			reg = <6>;
 			regulator-name = "vdd_3v3a";
 			regulator-always-on;
 		};
diff --git a/arch/arm/boot/dts/am335x-chilisom.dtsi b/arch/arm/boot/dts/am335x-chilisom.dtsi
index fda457b07e15..857d9894103a 100644
--- a/arch/arm/boot/dts/am335x-chilisom.dtsi
+++ b/arch/arm/boot/dts/am335x-chilisom.dtsi
@@ -128,21 +128,16 @@
 
 };
 
-&tps {
-	compatible = "ti,tps65217";
+/include/ "tps65217.dtsi"
 
+&tps {
 	regulators {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
 		dcdc1_reg: regulator@0 {
-			reg = <0>;
 			regulator-name = "vdds_dpr";
 			regulator-always-on;
 		};
 
 		dcdc2_reg: regulator@1 {
-			reg = <1>;
 			/* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */
 			regulator-name = "vdd_mpu";
 			regulator-min-microvolt = <925000>;
@@ -152,7 +147,6 @@
 		};
 
 		dcdc3_reg: regulator@2 {
-			reg = <2>;
 			/* VDD_CORE voltage limits 0.95V - 1.1V with +/-4% tolerance */
 			regulator-name = "vdd_core";
 			regulator-min-microvolt = <925000>;
@@ -162,28 +156,24 @@
 		};
 
 		ldo1_reg: regulator@3 {
-			reg = <3>;
 			regulator-name = "vio,vrtc,vdds";
 			regulator-boot-on;
 			regulator-always-on;
 		};
 
 		ldo2_reg: regulator@4 {
-			reg = <4>;
 			regulator-name = "vdd_3v3aux";
 			regulator-boot-on;
 			regulator-always-on;
 		};
 
 		ldo3_reg: regulator@5 {
-			reg = <5>;
 			regulator-name = "vdd_1v8";
 			regulator-boot-on;
 			regulator-always-on;
 		};
 
 		ldo4_reg: regulator@6 {
-			reg = <6>;
 			regulator-name = "vdd_3v3d";
 			regulator-boot-on;
 			regulator-always-on;
diff --git a/arch/arm/boot/dts/am335x-nano.dts b/arch/arm/boot/dts/am335x-nano.dts
index 77559a1ded60..f313999c503e 100644
--- a/arch/arm/boot/dts/am335x-nano.dts
+++ b/arch/arm/boot/dts/am335x-nano.dts
@@ -375,15 +375,11 @@
 	wp-gpios = <&gpio3 18 0>;
 };
 
-&tps {
-	compatible = "ti,tps65217";
+#include "tps65217.dtsi"
 
+&tps {
 	regulators {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
 		dcdc1_reg: regulator@0 {
-			reg = <0>;
 			/* +1.5V voltage with ±4% tolerance */
 			regulator-min-microvolt = <1450000>;
 			regulator-max-microvolt = <1550000>;
@@ -392,7 +388,6 @@
 		};
 
 		dcdc2_reg: regulator@1 {
-			reg = <1>;
 			/* VDD_MPU voltage limits 0.95V - 1.1V with ±4% tolerance */
 			regulator-name = "vdd_mpu";
 			regulator-min-microvolt = <915000>;
@@ -402,7 +397,6 @@
 		};
 
 		dcdc3_reg: regulator@2 {
-			reg = <2>;
 			/* VDD_CORE voltage limits 0.95V - 1.1V with ±4% tolerance */
 			regulator-name = "vdd_core";
 			regulator-min-microvolt = <915000>;
@@ -412,7 +406,6 @@
 		};
 
 		ldo1_reg: regulator@3 {
-			reg = <3>;
 			/* +1.8V voltage with ±4% tolerance */
 			regulator-min-microvolt = <1750000>;
 			regulator-max-microvolt = <1870000>;
@@ -421,7 +414,6 @@
 		};
 
 		ldo2_reg: regulator@4 {
-			reg = <4>;
 			/* +3.3V voltage with ±4% tolerance */
 			regulator-min-microvolt = <3175000>;
 			regulator-max-microvolt = <3430000>;
@@ -430,7 +422,6 @@
 		};
 
 		ldo3_reg: regulator@5 {
-			reg = <5>;
 			/* +1.8V voltage with ±4% tolerance */
 			regulator-min-microvolt = <1750000>;
 			regulator-max-microvolt = <1870000>;
@@ -439,7 +430,6 @@
 		};
 
 		ldo4_reg: regulator@6 {
-			reg = <6>;
 			/* +3.3V voltage with ±4% tolerance */
 			regulator-min-microvolt = <3175000>;
 			regulator-max-microvolt = <3430000>;
diff --git a/arch/arm/boot/dts/am335x-pepper.dts b/arch/arm/boot/dts/am335x-pepper.dts
index 471a3a70ea1f..8867aaaec54d 100644
--- a/arch/arm/boot/dts/am335x-pepper.dts
+++ b/arch/arm/boot/dts/am335x-pepper.dts
@@ -420,9 +420,9 @@
 	vin-supply = <&vbat>;
 };
 
-&tps {
-	compatible = "ti,tps65217";
+/include/ "tps65217.dtsi"
 
+&tps {
 	backlight {
 		isel = <1>; /* ISET1 */
 		fdim = <200>; /* TPS65217_BL_FDIM_200HZ */
@@ -430,17 +430,12 @@
 	};
 
 	regulators {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
 		dcdc1_reg: regulator@0 {
-			reg = <0>;
 			/* VDD_1V8 system supply */
 			regulator-always-on;
 		};
 
 		dcdc2_reg: regulator@1 {
-			reg = <1>;
 			/* VDD_CORE voltage limits 0.95V - 1.26V with +/-4% tolerance */
 			regulator-name = "vdd_core";
 			regulator-min-microvolt = <925000>;
@@ -450,7 +445,6 @@
 		};
 
 		dcdc3_reg: regulator@2 {
-			reg = <2>;
 			/* VDD_MPU voltage limits 0.95V - 1.1V with +/-4% tolerance */
 			regulator-name = "vdd_mpu";
 			regulator-min-microvolt = <925000>;
@@ -460,21 +454,18 @@
 		};
 
 		ldo1_reg: regulator@3 {
-			reg = <3>;
 			/* VRTC 1.8V always-on supply */
 			regulator-name = "vrtc,vdds";
 			regulator-always-on;
 		};
 
 		ldo2_reg: regulator@4 {
-			reg = <4>;
 			/* 3.3V rail */
 			regulator-name = "vdd_3v3aux";
 			regulator-always-on;
 		};
 
 		ldo3_reg: regulator@5 {
-			reg = <5>;
 			/* VDD_3V3A 3.3V rail */
 			regulator-name = "vdd_3v3a";
 			regulator-min-microvolt = <3300000>;
@@ -482,7 +473,6 @@
 		};
 
 		ldo4_reg: regulator@6 {
-			reg = <6>;
 			/* VDD_3V3B 3.3V rail */
 			regulator-name = "vdd_3v3b";
 			regulator-always-on;
diff --git a/arch/arm/boot/dts/am335x-shc.dts b/arch/arm/boot/dts/am335x-shc.dts
index 1b5b044fcd91..865de8500f1c 100644
--- a/arch/arm/boot/dts/am335x-shc.dts
+++ b/arch/arm/boot/dts/am335x-shc.dts
@@ -46,7 +46,7 @@
 			gpios = <&gpio1 29 GPIO_ACTIVE_HIGH>;
 			linux,code = <KEY_BACK>;
 			debounce-interval = <1000>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		front_button {
@@ -54,7 +54,7 @@
 			gpios = <&gpio1 25 GPIO_ACTIVE_HIGH>;
 			linux,code = <KEY_FRONT>;
 			debounce-interval = <1000>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/am335x-sl50.dts b/arch/arm/boot/dts/am335x-sl50.dts
index d38edfa53bb9..3303c281697b 100644
--- a/arch/arm/boot/dts/am335x-sl50.dts
+++ b/arch/arm/boot/dts/am335x-sl50.dts
@@ -375,19 +375,16 @@
 	pinctrl-0 = <&uart4_pins>;
 };
 
+#include "tps65217.dtsi"
+
 &tps {
-	compatible = "ti,tps65217";
 	ti,pmic-shutdown-controller;
 
 	interrupt-parent = <&intc>;
 	interrupts = <7>;	/* NNMI */
 
 	regulators {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
 		dcdc1_reg: regulator@0 {
-			reg = <0>;
 			/* VDDS_DDR */
 			regulator-min-microvolt = <1500000>;
 			regulator-max-microvolt = <1500000>;
@@ -395,7 +392,6 @@
 		};
 
 		dcdc2_reg: regulator@1 {
-			reg = <1>;
 			/* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */
 			regulator-name = "vdd_mpu";
 			regulator-min-microvolt = <925000>;
@@ -405,7 +401,6 @@
 		};
 
 		dcdc3_reg: regulator@2 {
-			reg = <2>;
 			/* VDD_CORE voltage limits 0.95V - 1.1V with +/-4% tolerance */
 			regulator-name = "vdd_core";
 			regulator-min-microvolt = <925000>;
@@ -415,7 +410,6 @@
 		};
 
 		ldo1_reg: regulator@3 {
-			reg = <3>;
 			/* VRTC / VIO / VDDS*/
 			regulator-always-on;
 			regulator-min-microvolt = <1800000>;
@@ -423,7 +417,6 @@
 		};
 
 		ldo2_reg: regulator@4 {
-			reg = <4>;
 			/* VDD_3V3AUX */
 			regulator-always-on;
 			regulator-min-microvolt = <3300000>;
@@ -431,7 +424,6 @@
 		};
 
 		ldo3_reg: regulator@5 {
-			reg = <5>;
 			/* VDD_1V8 */
 			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <1800000>;
@@ -439,7 +431,6 @@
 		};
 
 		ldo4_reg: regulator@6 {
-			reg = <6>;
 			/* VDD_3V3A */
 			regulator-min-microvolt = <3300000>;
 			regulator-max-microvolt = <3300000>;
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts
index 36c0fa6c362a..a0986c65be0c 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15.dts
+++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts
@@ -173,6 +173,8 @@
 
 		sound0_master: simple-audio-card,codec {
 			sound-dai = <&tlv320aic3104>;
+			assigned-clocks = <&clkoutmux2_clk_mux>;
+			assigned-clock-parents = <&sys_clk2_dclk_div>;
 			clocks = <&clkout2_clk>;
 		};
 	};
@@ -796,6 +798,8 @@
 	pinctrl-names = "default", "sleep";
 	pinctrl-0 = <&mcasp3_pins_default>;
 	pinctrl-1 = <&mcasp3_pins_sleep>;
+	assigned-clocks = <&mcasp3_ahclkx_mux>;
+	assigned-clock-parents = <&sys_clkin2>;
 	status = "okay";
 
 	op-mode = <0>;	/* MCASP_IIS_MODE */
diff --git a/arch/arm/boot/dts/am57xx-cl-som-am57x.dts b/arch/arm/boot/dts/am57xx-cl-som-am57x.dts
index 8d93882dc8d5..1c06cb76da07 100644
--- a/arch/arm/boot/dts/am57xx-cl-som-am57x.dts
+++ b/arch/arm/boot/dts/am57xx-cl-som-am57x.dts
@@ -545,7 +545,7 @@
 		ti,debounce-tol = /bits/ 16 <10>;
 		ti,debounce-rep = /bits/ 16 <1>;
 
-		linux,wakeup;
+		wakeup-source;
 	};
 };
 
diff --git a/arch/arm/boot/dts/armada-xp-axpwifiap.dts b/arch/arm/boot/dts/armada-xp-axpwifiap.dts
index 23fc670c0427..5c21b236721f 100644
--- a/arch/arm/boot/dts/armada-xp-axpwifiap.dts
+++ b/arch/arm/boot/dts/armada-xp-axpwifiap.dts
@@ -70,8 +70,8 @@
 	soc {
 		ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000
 			  MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000
-			  MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000
-			  MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>;
+			  MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000
+			  MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>;
 
 		pcie-controller {
 			status = "okay";
diff --git a/arch/arm/boot/dts/armada-xp-db.dts b/arch/arm/boot/dts/armada-xp-db.dts
index f774101416a5..ebe1d267406d 100644
--- a/arch/arm/boot/dts/armada-xp-db.dts
+++ b/arch/arm/boot/dts/armada-xp-db.dts
@@ -76,8 +76,8 @@
 		ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000
 			  MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000
 			  MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x1000000
-			  MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000
-			  MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>;
+			  MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000
+			  MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>;
 
 		devbus-bootcs {
 			status = "okay";
diff --git a/arch/arm/boot/dts/armada-xp-gp.dts b/arch/arm/boot/dts/armada-xp-gp.dts
index 4878d7353069..5730b875c4f5 100644
--- a/arch/arm/boot/dts/armada-xp-gp.dts
+++ b/arch/arm/boot/dts/armada-xp-gp.dts
@@ -95,8 +95,8 @@
 		ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000
 			  MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000
 			  MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x1000000
-			  MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000
-			  MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>;
+			  MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000
+			  MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>;
 
 		devbus-bootcs {
 			status = "okay";
diff --git a/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts b/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts
index fb9e1bbf2338..8af463f26ea1 100644
--- a/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts
+++ b/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts
@@ -65,8 +65,8 @@
 	soc {
 		ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000
 			MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000
-			MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000
-			MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>;
+			MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000
+			MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>;
 
 		pcie-controller {
 			status = "okay";
diff --git a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
index 6e9820e141f8..b89e6cf1271a 100644
--- a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
+++ b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
@@ -70,8 +70,8 @@
 	soc {
 		ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000
 			  MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000
-			  MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000
-			  MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>;
+			  MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000
+			  MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>;
 
 		pcie-controller {
 			status = "okay";
diff --git a/arch/arm/boot/dts/armada-xp-matrix.dts b/arch/arm/boot/dts/armada-xp-matrix.dts
index 6ab33837a2b6..6522b04f4a8e 100644
--- a/arch/arm/boot/dts/armada-xp-matrix.dts
+++ b/arch/arm/boot/dts/armada-xp-matrix.dts
@@ -68,8 +68,8 @@
 	soc {
 		ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000
 			  MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000
-			  MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000
-			  MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>;
+			  MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000
+			  MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>;
 
 		internal-regs {
 			serial@12000 {
diff --git a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts
index 62175a8848bc..d19f44c70925 100644
--- a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts
+++ b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts
@@ -64,8 +64,8 @@
 	soc {
 		ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000
 			  MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000
-			  MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000
-			  MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>;
+			  MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000
+			  MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>;
 
 		pcie-controller {
 			status = "okay";
diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
index a5db17782e08..853bd392a4fe 100644
--- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
+++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
@@ -65,9 +65,9 @@
 	soc {
 		ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000
 			  MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000
-			  MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x8000000
-			  MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000
-			  MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>;
+			  MBUS_ID(0x01, 0x2f) 0 0 0xe8000000 0x8000000
+			  MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000
+			  MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>;
 
 		devbus-bootcs {
 			status = "okay";
diff --git a/arch/arm/boot/dts/armada-xp-synology-ds414.dts b/arch/arm/boot/dts/armada-xp-synology-ds414.dts
index 2391b11dc546..d17dab0a6f51 100644
--- a/arch/arm/boot/dts/armada-xp-synology-ds414.dts
+++ b/arch/arm/boot/dts/armada-xp-synology-ds414.dts
@@ -78,8 +78,8 @@
 	soc {
 		ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000
 			  MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000
-			  MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000
-			  MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>;
+			  MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000
+			  MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>;
 
 		pcie-controller {
 			status = "okay";
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index c4d9175b90dc..f82aa44c3cee 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1500,6 +1500,16 @@
 			       0x48485200 0x2E00>;
 			#address-cells = <1>;
 			#size-cells = <1>;
+
+			/*
+			 * Do not allow gating of cpsw clock as workaround
+			 * for errata i877. Keeping internal clock disabled
+			 * causes the device switching characteristics
+			 * to degrade over time and eventually fail to meet
+			 * the data manual delay time/skew specs.
+			 */
+			ti,no-idle;
+
 			/*
 			 * rx_thresh_pend
 			 * rx_pend
diff --git a/arch/arm/boot/dts/imx23.dtsi b/arch/arm/boot/dts/imx23.dtsi
index 1c6c07538a78..302d1168f424 100644
--- a/arch/arm/boot/dts/imx23.dtsi
+++ b/arch/arm/boot/dts/imx23.dtsi
@@ -569,7 +569,7 @@
 		};
 	};
 
-	iio_hwmon {
+	iio-hwmon {
 		compatible = "iio-hwmon";
 		io-channels = <&lradc 8>;
 	};
diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi
index fae7b9069fc4..f637ec900cc8 100644
--- a/arch/arm/boot/dts/imx28.dtsi
+++ b/arch/arm/boot/dts/imx28.dtsi
@@ -1256,7 +1256,7 @@
 		};
 	};
 
-	iio_hwmon {
+	iio-hwmon {
 		compatible = "iio-hwmon";
 		io-channels = <&lradc 8>;
 	};
diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi
index 4f6ae921656f..f74d3db4846d 100644
--- a/arch/arm/boot/dts/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/imx6qdl.dtsi
@@ -896,7 +896,6 @@
 				#size-cells = <1>;
 				reg = <0x2100000 0x10000>;
 				ranges = <0 0x2100000 0x10000>;
-				interrupt-parent = <&intc>;
 				clocks = <&clks IMX6QDL_CLK_CAAM_MEM>,
 					 <&clks IMX6QDL_CLK_CAAM_ACLK>,
 					 <&clks IMX6QDL_CLK_CAAM_IPG>,
diff --git a/arch/arm/boot/dts/kirkwood-ds112.dts b/arch/arm/boot/dts/kirkwood-ds112.dts
index bf4143c6cb8f..b84af3da8c84 100644
--- a/arch/arm/boot/dts/kirkwood-ds112.dts
+++ b/arch/arm/boot/dts/kirkwood-ds112.dts
@@ -14,7 +14,7 @@
 #include "kirkwood-synology.dtsi"
 
 / {
-	model = "Synology DS111";
+	model = "Synology DS112";
 	compatible = "synology,ds111", "marvell,kirkwood";
 
 	memory {
diff --git a/arch/arm/boot/dts/mt2701-pinfunc.h b/arch/arm/boot/dts/mt2701-pinfunc.h
new file mode 100644
index 000000000000..e24ebc8d928e
--- /dev/null
+++ b/arch/arm/boot/dts/mt2701-pinfunc.h
@@ -0,0 +1,735 @@
+/*
+ * Copyright (c) 2015 MediaTek Inc.
+ * Author: Biao Huang <biao.huang@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DTS_MT2701_PINFUNC_H
+#define __DTS_MT2701_PINFUNC_H
+
+#include <dt-bindings/pinctrl/mt65xx.h>
+
+#define MT2701_PIN_0_PWRAP_SPI0_MI__FUNC_GPIO0 (MTK_PIN_NO(0) | 0)
+#define MT2701_PIN_0_PWRAP_SPI0_MI__FUNC_PWRAP_SPIDO (MTK_PIN_NO(0) | 1)
+#define MT2701_PIN_0_PWRAP_SPI0_MI__FUNC_PWRAP_SPIDI (MTK_PIN_NO(0) | 2)
+
+#define MT2701_PIN_1_PWRAP_SPI0_MO__FUNC_GPIO1 (MTK_PIN_NO(1) | 0)
+#define MT2701_PIN_1_PWRAP_SPI0_MO__FUNC_PWRAP_SPIDI (MTK_PIN_NO(1) | 1)
+#define MT2701_PIN_1_PWRAP_SPI0_MO__FUNC_PWRAP_SPIDO (MTK_PIN_NO(1) | 2)
+
+#define MT2701_PIN_2_PWRAP_INT__FUNC_GPIO2 (MTK_PIN_NO(2) | 0)
+#define MT2701_PIN_2_PWRAP_INT__FUNC_PWRAP_INT (MTK_PIN_NO(2) | 1)
+
+#define MT2701_PIN_3_PWRAP_SPI0_CK__FUNC_GPIO3 (MTK_PIN_NO(3) | 0)
+#define MT2701_PIN_3_PWRAP_SPI0_CK__FUNC_PWRAP_SPICK_I (MTK_PIN_NO(3) | 1)
+
+#define MT2701_PIN_4_PWRAP_SPI0_CSN__FUNC_GPIO4 (MTK_PIN_NO(4) | 0)
+#define MT2701_PIN_4_PWRAP_SPI0_CSN__FUNC_PWRAP_SPICS_B_I (MTK_PIN_NO(4) | 1)
+
+#define MT2701_PIN_5_PWRAP_SPI0_CK2__FUNC_GPIO5 (MTK_PIN_NO(5) | 0)
+#define MT2701_PIN_5_PWRAP_SPI0_CK2__FUNC_PWRAP_SPICK2_I (MTK_PIN_NO(5) | 1)
+#define MT2701_PIN_5_PWRAP_SPI0_CK2__FUNC_ANT_SEL1 (MTK_PIN_NO(5) | 5)
+
+#define MT2701_PIN_6_PWRAP_SPI0_CSN2__FUNC_GPIO6 (MTK_PIN_NO(6) | 0)
+#define MT2701_PIN_6_PWRAP_SPI0_CSN2__FUNC_PWRAP_SPICS2_B_I (MTK_PIN_NO(6) | 1)
+#define MT2701_PIN_6_PWRAP_SPI0_CSN2__FUNC_ANT_SEL0 (MTK_PIN_NO(6) | 5)
+#define MT2701_PIN_6_PWRAP_SPI0_CSN2__FUNC_DBG_MON_A_0 (MTK_PIN_NO(6) | 7)
+
+#define MT2701_PIN_7_SPI1_CSN__FUNC_GPIO7 (MTK_PIN_NO(7) | 0)
+#define MT2701_PIN_7_SPI1_CSN__FUNC_SPI1_CS (MTK_PIN_NO(7) | 1)
+#define MT2701_PIN_7_SPI1_CSN__FUNC_KCOL0 (MTK_PIN_NO(7) | 4)
+#define MT2701_PIN_7_SPI1_CSN__FUNC_DBG_MON_B_12 (MTK_PIN_NO(7) | 7)
+
+#define MT2701_PIN_8_SPI1_MI__FUNC_GPIO8 (MTK_PIN_NO(8) | 0)
+#define MT2701_PIN_8_SPI1_MI__FUNC_SPI1_MI (MTK_PIN_NO(8) | 1)
+#define MT2701_PIN_8_SPI1_MI__FUNC_SPI1_MO (MTK_PIN_NO(8) | 2)
+#define MT2701_PIN_8_SPI1_MI__FUNC_KCOL1 (MTK_PIN_NO(8) | 4)
+#define MT2701_PIN_8_SPI1_MI__FUNC_DBG_MON_B_13 (MTK_PIN_NO(8) | 7)
+
+#define MT2701_PIN_9_SPI1_MO__FUNC_GPIO9 (MTK_PIN_NO(9) | 0)
+#define MT2701_PIN_9_SPI1_MO__FUNC_SPI1_MO (MTK_PIN_NO(9) | 1)
+#define MT2701_PIN_9_SPI1_MO__FUNC_SPI1_MI (MTK_PIN_NO(9) | 2)
+#define MT2701_PIN_9_SPI1_MO__FUNC_EXT_FRAME_SYNC (MTK_PIN_NO(9) | 3)
+#define MT2701_PIN_9_SPI1_MO__FUNC_KCOL2 (MTK_PIN_NO(9) | 4)
+#define MT2701_PIN_9_SPI1_MO__FUNC_DBG_MON_B_14 (MTK_PIN_NO(9) | 7)
+
+#define MT2701_PIN_10_RTC32K_CK__FUNC_GPIO10 (MTK_PIN_NO(10) | 0)
+#define MT2701_PIN_10_RTC32K_CK__FUNC_RTC32K_CK (MTK_PIN_NO(10) | 1)
+
+#define MT2701_PIN_11_WATCHDOG__FUNC_GPIO11 (MTK_PIN_NO(11) | 0)
+#define MT2701_PIN_11_WATCHDOG__FUNC_WATCHDOG (MTK_PIN_NO(11) | 1)
+
+#define MT2701_PIN_12_SRCLKENA__FUNC_GPIO12 (MTK_PIN_NO(12) | 0)
+#define MT2701_PIN_12_SRCLKENA__FUNC_SRCLKENA (MTK_PIN_NO(12) | 1)
+
+#define MT2701_PIN_13_SRCLKENAI__FUNC_GPIO13 (MTK_PIN_NO(13) | 0)
+#define MT2701_PIN_13_SRCLKENAI__FUNC_SRCLKENAI (MTK_PIN_NO(13) | 1)
+
+#define MT2701_PIN_14_URXD2__FUNC_GPIO14 (MTK_PIN_NO(14) | 0)
+#define MT2701_PIN_14_URXD2__FUNC_URXD2 (MTK_PIN_NO(14) | 1)
+#define MT2701_PIN_14_URXD2__FUNC_UTXD2 (MTK_PIN_NO(14) | 2)
+#define MT2701_PIN_14_URXD2__FUNC_SRCCLKENAI2 (MTK_PIN_NO(14) | 5)
+#define MT2701_PIN_14_URXD2__FUNC_DBG_MON_B_30 (MTK_PIN_NO(14) | 7)
+
+#define MT2701_PIN_15_UTXD2__FUNC_GPIO15 (MTK_PIN_NO(15) | 0)
+#define MT2701_PIN_15_UTXD2__FUNC_UTXD2 (MTK_PIN_NO(15) | 1)
+#define MT2701_PIN_15_UTXD2__FUNC_URXD2 (MTK_PIN_NO(15) | 2)
+#define MT2701_PIN_15_UTXD2__FUNC_DBG_MON_B_31 (MTK_PIN_NO(15) | 7)
+
+#define MT2701_PIN_18_PCM_CLK__FUNC_GPIO18 (MTK_PIN_NO(18) | 0)
+#define MT2701_PIN_18_PCM_CLK__FUNC_PCM_CLK0 (MTK_PIN_NO(18) | 1)
+#define MT2701_PIN_18_PCM_CLK__FUNC_MRG_CLK (MTK_PIN_NO(18) | 2)
+#define MT2701_PIN_18_PCM_CLK__FUNC_MM_TEST_CK (MTK_PIN_NO(18) | 4)
+#define MT2701_PIN_18_PCM_CLK__FUNC_CONN_DSP_JCK (MTK_PIN_NO(18) | 5)
+#define MT2701_PIN_18_PCM_CLK__FUNC_WCN_PCM_CLKO (MTK_PIN_NO(18) | 6)
+#define MT2701_PIN_18_PCM_CLK__FUNC_DBG_MON_A_3 (MTK_PIN_NO(18) | 7)
+
+#define MT2701_PIN_19_PCM_SYNC__FUNC_GPIO19 (MTK_PIN_NO(19) | 0)
+#define MT2701_PIN_19_PCM_SYNC__FUNC_PCM_SYNC (MTK_PIN_NO(19) | 1)
+#define MT2701_PIN_19_PCM_SYNC__FUNC_MRG_SYNC (MTK_PIN_NO(19) | 2)
+#define MT2701_PIN_19_PCM_SYNC__FUNC_CONN_DSP_JINTP (MTK_PIN_NO(19) | 5)
+#define MT2701_PIN_19_PCM_SYNC__FUNC_WCN_PCM_SYNC (MTK_PIN_NO(19) | 6)
+#define MT2701_PIN_19_PCM_SYNC__FUNC_DBG_MON_A_5 (MTK_PIN_NO(19) | 7)
+
+#define MT2701_PIN_20_PCM_RX__FUNC_GPIO20 (MTK_PIN_NO(20) | 0)
+#define MT2701_PIN_20_PCM_RX__FUNC_PCM_RX (MTK_PIN_NO(20) | 1)
+#define MT2701_PIN_20_PCM_RX__FUNC_MRG_RX (MTK_PIN_NO(20) | 2)
+#define MT2701_PIN_20_PCM_RX__FUNC_MRG_TX (MTK_PIN_NO(20) | 3)
+#define MT2701_PIN_20_PCM_RX__FUNC_PCM_TX (MTK_PIN_NO(20) | 4)
+#define MT2701_PIN_20_PCM_RX__FUNC_CONN_DSP_JDI (MTK_PIN_NO(20) | 5)
+#define MT2701_PIN_20_PCM_RX__FUNC_WCN_PCM_RX (MTK_PIN_NO(20) | 6)
+#define MT2701_PIN_20_PCM_RX__FUNC_DBG_MON_A_4 (MTK_PIN_NO(20) | 7)
+
+#define MT2701_PIN_21_PCM_TX__FUNC_GPIO21 (MTK_PIN_NO(21) | 0)
+#define MT2701_PIN_21_PCM_TX__FUNC_PCM_TX (MTK_PIN_NO(21) | 1)
+#define MT2701_PIN_21_PCM_TX__FUNC_MRG_TX (MTK_PIN_NO(21) | 2)
+#define MT2701_PIN_21_PCM_TX__FUNC_MRG_RX (MTK_PIN_NO(21) | 3)
+#define MT2701_PIN_21_PCM_TX__FUNC_PCM_RX (MTK_PIN_NO(21) | 4)
+#define MT2701_PIN_21_PCM_TX__FUNC_CONN_DSP_JMS (MTK_PIN_NO(21) | 5)
+#define MT2701_PIN_21_PCM_TX__FUNC_WCN_PCM_TX (MTK_PIN_NO(21) | 6)
+#define MT2701_PIN_21_PCM_TX__FUNC_DBG_MON_A_2 (MTK_PIN_NO(21) | 7)
+
+#define MT2701_PIN_22_EINT0__FUNC_GPIO22 (MTK_PIN_NO(22) | 0)
+#define MT2701_PIN_22_EINT0__FUNC_UCTS0 (MTK_PIN_NO(22) | 1)
+#define MT2701_PIN_22_EINT0__FUNC_KCOL3 (MTK_PIN_NO(22) | 3)
+#define MT2701_PIN_22_EINT0__FUNC_CONN_DSP_JDO (MTK_PIN_NO(22) | 4)
+#define MT2701_PIN_22_EINT0__FUNC_EXT_FRAME_SYNC (MTK_PIN_NO(22) | 5)
+#define MT2701_PIN_22_EINT0__FUNC_DBG_MON_A_30 (MTK_PIN_NO(22) | 7)
+#define MT2701_PIN_22_EINT0__FUNC_PCIE0_PERST_N (MTK_PIN_NO(22) | 10)
+
+#define MT2701_PIN_23_EINT1__FUNC_GPIO23 (MTK_PIN_NO(23) | 0)
+#define MT2701_PIN_23_EINT1__FUNC_URTS0 (MTK_PIN_NO(23) | 1)
+#define MT2701_PIN_23_EINT1__FUNC_KCOL2 (MTK_PIN_NO(23) | 3)
+#define MT2701_PIN_23_EINT1__FUNC_CONN_MCU_TDO (MTK_PIN_NO(23) | 4)
+#define MT2701_PIN_23_EINT1__FUNC_EXT_FRAME_SYNC (MTK_PIN_NO(23) | 5)
+#define MT2701_PIN_23_EINT1__FUNC_DBG_MON_A_29 (MTK_PIN_NO(23) | 7)
+#define MT2701_PIN_23_EINT1__FUNC_PCIE1_PERST_N (MTK_PIN_NO(23) | 10)
+
+#define MT2701_PIN_24_EINT2__FUNC_GPIO24 (MTK_PIN_NO(24) | 0)
+#define MT2701_PIN_24_EINT2__FUNC_UCTS1 (MTK_PIN_NO(24) | 1)
+#define MT2701_PIN_24_EINT2__FUNC_KCOL1 (MTK_PIN_NO(24) | 3)
+#define MT2701_PIN_24_EINT2__FUNC_CONN_MCU_DBGACK_N (MTK_PIN_NO(24) | 4)
+#define MT2701_PIN_24_EINT2__FUNC_DBG_MON_A_28 (MTK_PIN_NO(24) | 7)
+#define MT2701_PIN_24_EINT2__FUNC_PCIE2_PERST_N (MTK_PIN_NO(24) | 10)
+
+#define MT2701_PIN_25_EINT3__FUNC_GPIO25 (MTK_PIN_NO(25) | 0)
+#define MT2701_PIN_25_EINT3__FUNC_URTS1 (MTK_PIN_NO(25) | 1)
+#define MT2701_PIN_25_EINT3__FUNC_KCOL0 (MTK_PIN_NO(25) | 3)
+#define MT2701_PIN_25_EINT3__FUNC_CONN_MCU_DBGI_N (MTK_PIN_NO(25) | 4)
+#define MT2701_PIN_25_EINT3__FUNC_DBG_MON_A_27 (MTK_PIN_NO(25) | 7)
+
+#define MT2701_PIN_26_EINT4__FUNC_GPIO26 (MTK_PIN_NO(26) | 0)
+#define MT2701_PIN_26_EINT4__FUNC_UCTS3 (MTK_PIN_NO(26) | 1)
+#define MT2701_PIN_26_EINT4__FUNC_DRV_VBUS_P1 (MTK_PIN_NO(26) | 2)
+#define MT2701_PIN_26_EINT4__FUNC_KROW3 (MTK_PIN_NO(26) | 3)
+#define MT2701_PIN_26_EINT4__FUNC_CONN_MCU_TCK0 (MTK_PIN_NO(26) | 4)
+#define MT2701_PIN_26_EINT4__FUNC_CONN_MCU_AICE_JCKC (MTK_PIN_NO(26) | 5)
+#define MT2701_PIN_26_EINT4__FUNC_PCIE2_WAKE_N (MTK_PIN_NO(26) | 6)
+#define MT2701_PIN_26_EINT4__FUNC_DBG_MON_A_26 (MTK_PIN_NO(26) | 7)
+
+#define MT2701_PIN_27_EINT5__FUNC_GPIO27 (MTK_PIN_NO(27) | 0)
+#define MT2701_PIN_27_EINT5__FUNC_URTS3 (MTK_PIN_NO(27) | 1)
+#define MT2701_PIN_27_EINT5__FUNC_IDDIG_P1 (MTK_PIN_NO(27) | 2)
+#define MT2701_PIN_27_EINT5__FUNC_KROW2 (MTK_PIN_NO(27) | 3)
+#define MT2701_PIN_27_EINT5__FUNC_CONN_MCU_TDI (MTK_PIN_NO(27) | 4)
+#define MT2701_PIN_27_EINT5__FUNC_PCIE1_WAKE_N (MTK_PIN_NO(27) | 6)
+#define MT2701_PIN_27_EINT5__FUNC_DBG_MON_A_25 (MTK_PIN_NO(27) | 7)
+
+#define MT2701_PIN_28_EINT6__FUNC_GPIO28 (MTK_PIN_NO(28) | 0)
+#define MT2701_PIN_28_EINT6__FUNC_DRV_VBUS (MTK_PIN_NO(28) | 1)
+#define MT2701_PIN_28_EINT6__FUNC_KROW1 (MTK_PIN_NO(28) | 3)
+#define MT2701_PIN_28_EINT6__FUNC_CONN_MCU_TRST_B (MTK_PIN_NO(28) | 4)
+#define MT2701_PIN_28_EINT6__FUNC_PCIE0_WAKE_N (MTK_PIN_NO(28) | 6)
+#define MT2701_PIN_28_EINT6__FUNC_DBG_MON_A_24 (MTK_PIN_NO(28) | 7)
+
+#define MT2701_PIN_29_EINT7__FUNC_GPIO29 (MTK_PIN_NO(29) | 0)
+#define MT2701_PIN_29_EINT7__FUNC_IDDIG (MTK_PIN_NO(29) | 1)
+#define MT2701_PIN_29_EINT7__FUNC_MSDC1_WP (MTK_PIN_NO(29) | 2)
+#define MT2701_PIN_29_EINT7__FUNC_KROW0 (MTK_PIN_NO(29) | 3)
+#define MT2701_PIN_29_EINT7__FUNC_CONN_MCU_TMS (MTK_PIN_NO(29) | 4)
+#define MT2701_PIN_29_EINT7__FUNC_CONN_MCU_AICE_JMSC (MTK_PIN_NO(29) | 5)
+#define MT2701_PIN_29_EINT7__FUNC_DBG_MON_A_23 (MTK_PIN_NO(29) | 7)
+#define MT2701_PIN_29_EINT7__FUNC_PCIE2_PERST_N (MTK_PIN_NO(29) | 14)
+
+#define MT2701_PIN_33_I2S1_DATA__FUNC_GPIO33 (MTK_PIN_NO(33) | 0)
+#define MT2701_PIN_33_I2S1_DATA__FUNC_I2S1_DATA (MTK_PIN_NO(33) | 1)
+#define MT2701_PIN_33_I2S1_DATA__FUNC_I2S1_DATA_BYPS (MTK_PIN_NO(33) | 2)
+#define MT2701_PIN_33_I2S1_DATA__FUNC_PCM_TX (MTK_PIN_NO(33) | 3)
+#define MT2701_PIN_33_I2S1_DATA__FUNC_IMG_TEST_CK (MTK_PIN_NO(33) | 4)
+#define MT2701_PIN_33_I2S1_DATA__FUNC_G1_RXD0 (MTK_PIN_NO(33) | 5)
+#define MT2701_PIN_33_I2S1_DATA__FUNC_WCN_PCM_TX (MTK_PIN_NO(33) | 6)
+#define MT2701_PIN_33_I2S1_DATA__FUNC_DBG_MON_B_8 (MTK_PIN_NO(33) | 7)
+
+#define MT2701_PIN_34_I2S1_DATA_IN__FUNC_GPIO34 (MTK_PIN_NO(34) | 0)
+#define MT2701_PIN_34_I2S1_DATA_IN__FUNC_I2S1_DATA_IN (MTK_PIN_NO(34) | 1)
+#define MT2701_PIN_34_I2S1_DATA_IN__FUNC_PCM_RX (MTK_PIN_NO(34) | 3)
+#define MT2701_PIN_34_I2S1_DATA_IN__FUNC_VDEC_TEST_CK (MTK_PIN_NO(34) | 4)
+#define MT2701_PIN_34_I2S1_DATA_IN__FUNC_G1_RXD1 (MTK_PIN_NO(34) | 5)
+#define MT2701_PIN_34_I2S1_DATA_IN__FUNC_WCN_PCM_RX (MTK_PIN_NO(34) | 6)
+#define MT2701_PIN_34_I2S1_DATA_IN__FUNC_DBG_MON_B_7 (MTK_PIN_NO(34) | 7)
+
+#define MT2701_PIN_35_I2S1_BCK__FUNC_GPIO35 (MTK_PIN_NO(35) | 0)
+#define MT2701_PIN_35_I2S1_BCK__FUNC_I2S1_BCK (MTK_PIN_NO(35) | 1)
+#define MT2701_PIN_35_I2S1_BCK__FUNC_PCM_CLK0 (MTK_PIN_NO(35) | 3)
+#define MT2701_PIN_35_I2S1_BCK__FUNC_G1_RXD2 (MTK_PIN_NO(35) | 5)
+#define MT2701_PIN_35_I2S1_BCK__FUNC_WCN_PCM_CLKO (MTK_PIN_NO(35) | 6)
+#define MT2701_PIN_35_I2S1_BCK__FUNC_DBG_MON_B_9 (MTK_PIN_NO(35) | 7)
+
+#define MT2701_PIN_36_I2S1_LRCK__FUNC_GPIO36 (MTK_PIN_NO(36) | 0)
+#define MT2701_PIN_36_I2S1_LRCK__FUNC_I2S1_LRCK (MTK_PIN_NO(36) | 1)
+#define MT2701_PIN_36_I2S1_LRCK__FUNC_PCM_SYNC (MTK_PIN_NO(36) | 3)
+#define MT2701_PIN_36_I2S1_LRCK__FUNC_G1_RXD3 (MTK_PIN_NO(36) | 5)
+#define MT2701_PIN_36_I2S1_LRCK__FUNC_WCN_PCM_SYNC (MTK_PIN_NO(36) | 6)
+#define MT2701_PIN_36_I2S1_LRCK__FUNC_DBG_MON_B_10 (MTK_PIN_NO(36) | 7)
+
+#define MT2701_PIN_37_I2S1_MCLK__FUNC_GPIO37 (MTK_PIN_NO(37) | 0)
+#define MT2701_PIN_37_I2S1_MCLK__FUNC_I2S1_MCLK (MTK_PIN_NO(37) | 1)
+#define MT2701_PIN_37_I2S1_MCLK__FUNC_G1_RXDV (MTK_PIN_NO(37) | 5)
+#define MT2701_PIN_37_I2S1_MCLK__FUNC_DBG_MON_B_11 (MTK_PIN_NO(37) | 7)
+
+#define MT2701_PIN_39_JTMS__FUNC_GPIO39 (MTK_PIN_NO(39) | 0)
+#define MT2701_PIN_39_JTMS__FUNC_JTMS (MTK_PIN_NO(39) | 1)
+#define MT2701_PIN_39_JTMS__FUNC_CONN_MCU_TMS (MTK_PIN_NO(39) | 2)
+#define MT2701_PIN_39_JTMS__FUNC_CONN_MCU_AICE_JMSC (MTK_PIN_NO(39) | 3)
+#define MT2701_PIN_39_JTMS__FUNC_DFD_TMS_XI (MTK_PIN_NO(39) | 4)
+
+#define MT2701_PIN_40_JTCK__FUNC_GPIO40 (MTK_PIN_NO(40) | 0)
+#define MT2701_PIN_40_JTCK__FUNC_JTCK (MTK_PIN_NO(40) | 1)
+#define MT2701_PIN_40_JTCK__FUNC_CONN_MCU_TCK1 (MTK_PIN_NO(40) | 2)
+#define MT2701_PIN_40_JTCK__FUNC_CONN_MCU_AICE_JCKC (MTK_PIN_NO(40) | 3)
+#define MT2701_PIN_40_JTCK__FUNC_DFD_TCK_XI (MTK_PIN_NO(40) | 4)
+
+#define MT2701_PIN_41_JTDI__FUNC_GPIO41 (MTK_PIN_NO(41) | 0)
+#define MT2701_PIN_41_JTDI__FUNC_JTDI (MTK_PIN_NO(41) | 1)
+#define MT2701_PIN_41_JTDI__FUNC_CONN_MCU_TDI (MTK_PIN_NO(41) | 2)
+#define MT2701_PIN_41_JTDI__FUNC_DFD_TDI_XI (MTK_PIN_NO(41) | 4)
+
+#define MT2701_PIN_42_JTDO__FUNC_GPIO42 (MTK_PIN_NO(42) | 0)
+#define MT2701_PIN_42_JTDO__FUNC_JTDO (MTK_PIN_NO(42) | 1)
+#define MT2701_PIN_42_JTDO__FUNC_CONN_MCU_TDO (MTK_PIN_NO(42) | 2)
+#define MT2701_PIN_42_JTDO__FUNC_DFD_TDO (MTK_PIN_NO(42) | 4)
+
+#define MT2701_PIN_43_NCLE__FUNC_GPIO43 (MTK_PIN_NO(43) | 0)
+#define MT2701_PIN_43_NCLE__FUNC_NCLE (MTK_PIN_NO(43) | 1)
+#define MT2701_PIN_43_NCLE__FUNC_EXT_XCS2 (MTK_PIN_NO(43) | 2)
+
+#define MT2701_PIN_44_NCEB1__FUNC_GPIO44 (MTK_PIN_NO(44) | 0)
+#define MT2701_PIN_44_NCEB1__FUNC_NCEB1 (MTK_PIN_NO(44) | 1)
+#define MT2701_PIN_44_NCEB1__FUNC_IDDIG (MTK_PIN_NO(44) | 2)
+
+#define MT2701_PIN_45_NCEB0__FUNC_GPIO45 (MTK_PIN_NO(45) | 0)
+#define MT2701_PIN_45_NCEB0__FUNC_NCEB0 (MTK_PIN_NO(45) | 1)
+#define MT2701_PIN_45_NCEB0__FUNC_DRV_VBUS (MTK_PIN_NO(45) | 2)
+
+#define MT2701_PIN_46_IR__FUNC_GPIO46 (MTK_PIN_NO(46) | 0)
+#define MT2701_PIN_46_IR__FUNC_IR (MTK_PIN_NO(46) | 1)
+
+#define MT2701_PIN_47_NREB__FUNC_GPIO47 (MTK_PIN_NO(47) | 0)
+#define MT2701_PIN_47_NREB__FUNC_NREB (MTK_PIN_NO(47) | 1)
+#define MT2701_PIN_47_NREB__FUNC_IDDIG_P1 (MTK_PIN_NO(47) | 2)
+
+#define MT2701_PIN_48_NRNB__FUNC_GPIO48 (MTK_PIN_NO(48) | 0)
+#define MT2701_PIN_48_NRNB__FUNC_NRNB (MTK_PIN_NO(48) | 1)
+#define MT2701_PIN_48_NRNB__FUNC_DRV_VBUS_P1 (MTK_PIN_NO(48) | 2)
+
+#define MT2701_PIN_49_I2S0_DATA__FUNC_GPIO49 (MTK_PIN_NO(49) | 0)
+#define MT2701_PIN_49_I2S0_DATA__FUNC_I2S0_DATA (MTK_PIN_NO(49) | 1)
+#define MT2701_PIN_49_I2S0_DATA__FUNC_I2S0_DATA_BYPS (MTK_PIN_NO(49) | 2)
+#define MT2701_PIN_49_I2S0_DATA__FUNC_PCM_TX (MTK_PIN_NO(49) | 3)
+#define MT2701_PIN_49_I2S0_DATA__FUNC_WCN_I2S_DO (MTK_PIN_NO(49) | 6)
+#define MT2701_PIN_49_I2S0_DATA__FUNC_DBG_MON_B_3 (MTK_PIN_NO(49) | 7)
+
+#define MT2701_PIN_53_SPI0_CSN__FUNC_GPIO53 (MTK_PIN_NO(53) | 0)
+#define MT2701_PIN_53_SPI0_CSN__FUNC_SPI0_CS (MTK_PIN_NO(53) | 1)
+#define MT2701_PIN_53_SPI0_CSN__FUNC_SPDIF (MTK_PIN_NO(53) | 3)
+#define MT2701_PIN_53_SPI0_CSN__FUNC_ADC_CK (MTK_PIN_NO(53) | 4)
+#define MT2701_PIN_53_SPI0_CSN__FUNC_PWM1 (MTK_PIN_NO(53) | 5)
+#define MT2701_PIN_53_SPI0_CSN__FUNC_DBG_MON_A_7 (MTK_PIN_NO(53) | 7)
+
+#define MT2701_PIN_54_SPI0_CK__FUNC_GPIO54 (MTK_PIN_NO(54) | 0)
+#define MT2701_PIN_54_SPI0_CK__FUNC_SPI0_CK (MTK_PIN_NO(54) | 1)
+#define MT2701_PIN_54_SPI0_CK__FUNC_SPDIF_IN1 (MTK_PIN_NO(54) | 3)
+#define MT2701_PIN_54_SPI0_CK__FUNC_ADC_DAT_IN (MTK_PIN_NO(54) | 4)
+#define MT2701_PIN_54_SPI0_CK__FUNC_DBG_MON_A_10 (MTK_PIN_NO(54) | 7)
+
+#define MT2701_PIN_55_SPI0_MI__FUNC_GPIO55 (MTK_PIN_NO(55) | 0)
+#define MT2701_PIN_55_SPI0_MI__FUNC_SPI0_MI (MTK_PIN_NO(55) | 1)
+#define MT2701_PIN_55_SPI0_MI__FUNC_SPI0_MO (MTK_PIN_NO(55) | 2)
+#define MT2701_PIN_55_SPI0_MI__FUNC_MSDC1_WP (MTK_PIN_NO(55) | 3)
+#define MT2701_PIN_55_SPI0_MI__FUNC_ADC_WS (MTK_PIN_NO(55) | 4)
+#define MT2701_PIN_55_SPI0_MI__FUNC_PWM2 (MTK_PIN_NO(55) | 5)
+#define MT2701_PIN_55_SPI0_MI__FUNC_DBG_MON_A_8 (MTK_PIN_NO(55) | 7)
+
+#define MT2701_PIN_56_SPI0_MO__FUNC_GPIO56 (MTK_PIN_NO(56) | 0)
+#define MT2701_PIN_56_SPI0_MO__FUNC_SPI0_MO (MTK_PIN_NO(56) | 1)
+#define MT2701_PIN_56_SPI0_MO__FUNC_SPI0_MI (MTK_PIN_NO(56) | 2)
+#define MT2701_PIN_56_SPI0_MO__FUNC_SPDIF_IN0 (MTK_PIN_NO(56) | 3)
+#define MT2701_PIN_56_SPI0_MO__FUNC_DBG_MON_A_9 (MTK_PIN_NO(56) | 7)
+
+#define MT2701_PIN_57_SDA1__FUNC_GPIO57 (MTK_PIN_NO(57) | 0)
+#define MT2701_PIN_57_SDA1__FUNC_SDA1 (MTK_PIN_NO(57) | 1)
+
+#define MT2701_PIN_58_SCL1__FUNC_GPIO58 (MTK_PIN_NO(58) | 0)
+#define MT2701_PIN_58_SCL1__FUNC_SCL1 (MTK_PIN_NO(58) | 1)
+
+#define MT2701_PIN_72_I2S0_DATA_IN__FUNC_GPIO72 (MTK_PIN_NO(72) | 0)
+#define MT2701_PIN_72_I2S0_DATA_IN__FUNC_I2S0_DATA_IN (MTK_PIN_NO(72) | 1)
+#define MT2701_PIN_72_I2S0_DATA_IN__FUNC_PCM_RX (MTK_PIN_NO(72) | 3)
+#define MT2701_PIN_72_I2S0_DATA_IN__FUNC_PWM0 (MTK_PIN_NO(72) | 4)
+#define MT2701_PIN_72_I2S0_DATA_IN__FUNC_DISP_PWM (MTK_PIN_NO(72) | 5)
+#define MT2701_PIN_72_I2S0_DATA_IN__FUNC_WCN_I2S_DI (MTK_PIN_NO(72) | 6)
+#define MT2701_PIN_72_I2S0_DATA_IN__FUNC_DBG_MON_B_2 (MTK_PIN_NO(72) | 7)
+
+#define MT2701_PIN_73_I2S0_LRCK__FUNC_GPIO73 (MTK_PIN_NO(73) | 0)
+#define MT2701_PIN_73_I2S0_LRCK__FUNC_I2S0_LRCK (MTK_PIN_NO(73) | 1)
+#define MT2701_PIN_73_I2S0_LRCK__FUNC_PCM_SYNC (MTK_PIN_NO(73) | 3)
+#define MT2701_PIN_73_I2S0_LRCK__FUNC_WCN_I2S_LRCK (MTK_PIN_NO(73) | 6)
+#define MT2701_PIN_73_I2S0_LRCK__FUNC_DBG_MON_B_5 (MTK_PIN_NO(73) | 7)
+
+#define MT2701_PIN_74_I2S0_BCK__FUNC_GPIO74 (MTK_PIN_NO(74) | 0)
+#define MT2701_PIN_74_I2S0_BCK__FUNC_I2S0_BCK (MTK_PIN_NO(74) | 1)
+#define MT2701_PIN_74_I2S0_BCK__FUNC_PCM_CLK0 (MTK_PIN_NO(74) | 3)
+#define MT2701_PIN_74_I2S0_BCK__FUNC_WCN_I2S_BCK (MTK_PIN_NO(74) | 6)
+#define MT2701_PIN_74_I2S0_BCK__FUNC_DBG_MON_B_4 (MTK_PIN_NO(74) | 7)
+
+#define MT2701_PIN_75_SDA0__FUNC_GPIO75 (MTK_PIN_NO(75) | 0)
+#define MT2701_PIN_75_SDA0__FUNC_SDA0 (MTK_PIN_NO(75) | 1)
+
+#define MT2701_PIN_76_SCL0__FUNC_GPIO76 (MTK_PIN_NO(76) | 0)
+#define MT2701_PIN_76_SCL0__FUNC_SCL0 (MTK_PIN_NO(76) | 1)
+
+#define MT2701_PIN_77_SDA2__FUNC_GPIO77 (MTK_PIN_NO(77) | 0)
+#define MT2701_PIN_77_SDA2__FUNC_SDA2 (MTK_PIN_NO(77) | 1)
+
+#define MT2701_PIN_78_SCL2__FUNC_GPIO78 (MTK_PIN_NO(78) | 0)
+#define MT2701_PIN_78_SCL2__FUNC_SCL2 (MTK_PIN_NO(78) | 1)
+
+#define MT2701_PIN_79_URXD0__FUNC_GPIO79 (MTK_PIN_NO(79) | 0)
+#define MT2701_PIN_79_URXD0__FUNC_URXD0 (MTK_PIN_NO(79) | 1)
+#define MT2701_PIN_79_URXD0__FUNC_UTXD0 (MTK_PIN_NO(79) | 2)
+#define MT2701_PIN_79_URXD0__FUNC_ (MTK_PIN_NO(79) | 5)
+
+#define MT2701_PIN_80_UTXD0__FUNC_GPIO80 (MTK_PIN_NO(80) | 0)
+#define MT2701_PIN_80_UTXD0__FUNC_UTXD0 (MTK_PIN_NO(80) | 1)
+#define MT2701_PIN_80_UTXD0__FUNC_URXD0 (MTK_PIN_NO(80) | 2)
+
+#define MT2701_PIN_81_URXD1__FUNC_GPIO81 (MTK_PIN_NO(81) | 0)
+#define MT2701_PIN_81_URXD1__FUNC_URXD1 (MTK_PIN_NO(81) | 1)
+#define MT2701_PIN_81_URXD1__FUNC_UTXD1 (MTK_PIN_NO(81) | 2)
+
+#define MT2701_PIN_82_UTXD1__FUNC_GPIO82 (MTK_PIN_NO(82) | 0)
+#define MT2701_PIN_82_UTXD1__FUNC_UTXD1 (MTK_PIN_NO(82) | 1)
+#define MT2701_PIN_82_UTXD1__FUNC_URXD1 (MTK_PIN_NO(82) | 2)
+
+#define MT2701_PIN_83_LCM_RST__FUNC_GPIO83 (MTK_PIN_NO(83) | 0)
+#define MT2701_PIN_83_LCM_RST__FUNC_LCM_RST (MTK_PIN_NO(83) | 1)
+#define MT2701_PIN_83_LCM_RST__FUNC_VDAC_CK_XI (MTK_PIN_NO(83) | 2)
+#define MT2701_PIN_83_LCM_RST__FUNC_DBG_MON_B_1 (MTK_PIN_NO(83) | 7)
+
+#define MT2701_PIN_84_DSI_TE__FUNC_GPIO84 (MTK_PIN_NO(84) | 0)
+#define MT2701_PIN_84_DSI_TE__FUNC_DSI_TE (MTK_PIN_NO(84) | 1)
+#define MT2701_PIN_84_DSI_TE__FUNC_DBG_MON_B_0 (MTK_PIN_NO(84) | 7)
+
+#define MT2701_PIN_91_TDN3__FUNC_GPI91 (MTK_PIN_NO(91) | 0)
+#define MT2701_PIN_91_TDN3__FUNC_TDN3 (MTK_PIN_NO(91) | 1)
+
+#define MT2701_PIN_92_TDP3__FUNC_GPI92 (MTK_PIN_NO(92) | 0)
+#define MT2701_PIN_92_TDP3__FUNC_TDP3 (MTK_PIN_NO(92) | 1)
+
+#define MT2701_PIN_93_TDN2__FUNC_GPI93 (MTK_PIN_NO(93) | 0)
+#define MT2701_PIN_93_TDN2__FUNC_TDN2 (MTK_PIN_NO(93) | 1)
+
+#define MT2701_PIN_94_TDP2__FUNC_GPI94 (MTK_PIN_NO(94) | 0)
+#define MT2701_PIN_94_TDP2__FUNC_TDP2 (MTK_PIN_NO(94) | 1)
+
+#define MT2701_PIN_95_TCN__FUNC_GPI95 (MTK_PIN_NO(95) | 0)
+#define MT2701_PIN_95_TCN__FUNC_TCN (MTK_PIN_NO(95) | 1)
+
+#define MT2701_PIN_96_TCP__FUNC_GPI96 (MTK_PIN_NO(96) | 0)
+#define MT2701_PIN_96_TCP__FUNC_TCP (MTK_PIN_NO(96) | 1)
+
+#define MT2701_PIN_97_TDN1__FUNC_GPI97 (MTK_PIN_NO(97) | 0)
+#define MT2701_PIN_97_TDN1__FUNC_TDN1 (MTK_PIN_NO(97) | 1)
+
+#define MT2701_PIN_98_TDP1__FUNC_GPI98 (MTK_PIN_NO(98) | 0)
+#define MT2701_PIN_98_TDP1__FUNC_TDP1 (MTK_PIN_NO(98) | 1)
+
+#define MT2701_PIN_99_TDN0__FUNC_GPI99 (MTK_PIN_NO(99) | 0)
+#define MT2701_PIN_99_TDN0__FUNC_TDN0 (MTK_PIN_NO(99) | 1)
+
+#define MT2701_PIN_100_TDP0__FUNC_GPI100 (MTK_PIN_NO(100) | 0)
+#define MT2701_PIN_100_TDP0__FUNC_TDP0 (MTK_PIN_NO(100) | 1)
+
+#define MT2701_PIN_101_SPI2_CSN__FUNC_GPIO101 (MTK_PIN_NO(101) | 0)
+#define MT2701_PIN_101_SPI2_CSN__FUNC_SPI2_CS (MTK_PIN_NO(101) | 1)
+#define MT2701_PIN_101_SPI2_CSN__FUNC_SCL3 (MTK_PIN_NO(101) | 3)
+#define MT2701_PIN_101_SPI2_CSN__FUNC_KROW0 (MTK_PIN_NO(101) | 4)
+
+#define MT2701_PIN_102_SPI2_MI__FUNC_GPIO102 (MTK_PIN_NO(102) | 0)
+#define MT2701_PIN_102_SPI2_MI__FUNC_SPI2_MI (MTK_PIN_NO(102) | 1)
+#define MT2701_PIN_102_SPI2_MI__FUNC_SPI2_MO (MTK_PIN_NO(102) | 2)
+#define MT2701_PIN_102_SPI2_MI__FUNC_SDA3 (MTK_PIN_NO(102) | 3)
+#define MT2701_PIN_102_SPI2_MI__FUNC_KROW1 (MTK_PIN_NO(102) | 4)
+
+#define MT2701_PIN_103_SPI2_MO__FUNC_GPIO103 (MTK_PIN_NO(103) | 0)
+#define MT2701_PIN_103_SPI2_MO__FUNC_SPI2_MO (MTK_PIN_NO(103) | 1)
+#define MT2701_PIN_103_SPI2_MO__FUNC_SPI2_MI (MTK_PIN_NO(103) | 2)
+#define MT2701_PIN_103_SPI2_MO__FUNC_SCL3 (MTK_PIN_NO(103) | 3)
+#define MT2701_PIN_103_SPI2_MO__FUNC_KROW2 (MTK_PIN_NO(103) | 4)
+
+#define MT2701_PIN_104_SPI2_CLK__FUNC_GPIO104 (MTK_PIN_NO(104) | 0)
+#define MT2701_PIN_104_SPI2_CLK__FUNC_SPI2_CK (MTK_PIN_NO(104) | 1)
+#define MT2701_PIN_104_SPI2_CLK__FUNC_SDA3 (MTK_PIN_NO(104) | 3)
+#define MT2701_PIN_104_SPI2_CLK__FUNC_KROW3 (MTK_PIN_NO(104) | 4)
+
+#define MT2701_PIN_105_MSDC1_CMD__FUNC_GPIO105 (MTK_PIN_NO(105) | 0)
+#define MT2701_PIN_105_MSDC1_CMD__FUNC_MSDC1_CMD (MTK_PIN_NO(105) | 1)
+#define MT2701_PIN_105_MSDC1_CMD__FUNC_ANT_SEL0 (MTK_PIN_NO(105) | 2)
+#define MT2701_PIN_105_MSDC1_CMD__FUNC_SDA1 (MTK_PIN_NO(105) | 3)
+#define MT2701_PIN_105_MSDC1_CMD__FUNC_I2SOUT_BCK (MTK_PIN_NO(105) | 6)
+#define MT2701_PIN_105_MSDC1_CMD__FUNC_DBG_MON_B_27 (MTK_PIN_NO(105) | 7)
+
+#define MT2701_PIN_106_MSDC1_CLK__FUNC_GPIO106 (MTK_PIN_NO(106) | 0)
+#define MT2701_PIN_106_MSDC1_CLK__FUNC_MSDC1_CLK (MTK_PIN_NO(106) | 1)
+#define MT2701_PIN_106_MSDC1_CLK__FUNC_ANT_SEL1 (MTK_PIN_NO(106) | 2)
+#define MT2701_PIN_106_MSDC1_CLK__FUNC_SCL1 (MTK_PIN_NO(106) | 3)
+#define MT2701_PIN_106_MSDC1_CLK__FUNC_I2SOUT_LRCK (MTK_PIN_NO(106) | 6)
+#define MT2701_PIN_106_MSDC1_CLK__FUNC_DBG_MON_B_28 (MTK_PIN_NO(106) | 7)
+
+#define MT2701_PIN_107_MSDC1_DAT0__FUNC_GPIO107 (MTK_PIN_NO(107) | 0)
+#define MT2701_PIN_107_MSDC1_DAT0__FUNC_MSDC1_DAT0 (MTK_PIN_NO(107) | 1)
+#define MT2701_PIN_107_MSDC1_DAT0__FUNC_ANT_SEL2 (MTK_PIN_NO(107) | 2)
+#define MT2701_PIN_107_MSDC1_DAT0__FUNC_UTXD0 (MTK_PIN_NO(107) | 5)
+#define MT2701_PIN_107_MSDC1_DAT0__FUNC_I2SOUT_DATA_OUT (MTK_PIN_NO(107) | 6)
+#define MT2701_PIN_107_MSDC1_DAT0__FUNC_DBG_MON_B_26 (MTK_PIN_NO(107) | 7)
+
+#define MT2701_PIN_108_MSDC1_DAT1__FUNC_GPIO108 (MTK_PIN_NO(108) | 0)
+#define MT2701_PIN_108_MSDC1_DAT1__FUNC_MSDC1_DAT1 (MTK_PIN_NO(108) | 1)
+#define MT2701_PIN_108_MSDC1_DAT1__FUNC_ANT_SEL3 (MTK_PIN_NO(108) | 2)
+#define MT2701_PIN_108_MSDC1_DAT1__FUNC_PWM0 (MTK_PIN_NO(108) | 3)
+#define MT2701_PIN_108_MSDC1_DAT1__FUNC_URXD0 (MTK_PIN_NO(108) | 5)
+#define MT2701_PIN_108_MSDC1_DAT1__FUNC_PWM1 (MTK_PIN_NO(108) | 6)
+#define MT2701_PIN_108_MSDC1_DAT1__FUNC_DBG_MON_B_25 (MTK_PIN_NO(108) | 7)
+
+#define MT2701_PIN_109_MSDC1_DAT2__FUNC_GPIO109 (MTK_PIN_NO(109) | 0)
+#define MT2701_PIN_109_MSDC1_DAT2__FUNC_MSDC1_DAT2 (MTK_PIN_NO(109) | 1)
+#define MT2701_PIN_109_MSDC1_DAT2__FUNC_ANT_SEL4 (MTK_PIN_NO(109) | 2)
+#define MT2701_PIN_109_MSDC1_DAT2__FUNC_SDA2 (MTK_PIN_NO(109) | 3)
+#define MT2701_PIN_109_MSDC1_DAT2__FUNC_UTXD1 (MTK_PIN_NO(109) | 5)
+#define MT2701_PIN_109_MSDC1_DAT2__FUNC_PWM2 (MTK_PIN_NO(109) | 6)
+#define MT2701_PIN_109_MSDC1_DAT2__FUNC_DBG_MON_B_24 (MTK_PIN_NO(109) | 7)
+
+#define MT2701_PIN_110_MSDC1_DAT3__FUNC_GPIO110 (MTK_PIN_NO(110) | 0)
+#define MT2701_PIN_110_MSDC1_DAT3__FUNC_MSDC1_DAT3 (MTK_PIN_NO(110) | 1)
+#define MT2701_PIN_110_MSDC1_DAT3__FUNC_ANT_SEL5 (MTK_PIN_NO(110) | 2)
+#define MT2701_PIN_110_MSDC1_DAT3__FUNC_SCL2 (MTK_PIN_NO(110) | 3)
+#define MT2701_PIN_110_MSDC1_DAT3__FUNC_EXT_FRAME_SYNC (MTK_PIN_NO(110) | 4)
+#define MT2701_PIN_110_MSDC1_DAT3__FUNC_URXD1 (MTK_PIN_NO(110) | 5)
+#define MT2701_PIN_110_MSDC1_DAT3__FUNC_PWM3 (MTK_PIN_NO(110) | 6)
+#define MT2701_PIN_110_MSDC1_DAT3__FUNC_DBG_MON_B_23 (MTK_PIN_NO(110) | 7)
+
+#define MT2701_PIN_111_MSDC0_DAT7__FUNC_GPIO111 (MTK_PIN_NO(111) | 0)
+#define MT2701_PIN_111_MSDC0_DAT7__FUNC_MSDC0_DAT7 (MTK_PIN_NO(111) | 1)
+#define MT2701_PIN_111_MSDC0_DAT7__FUNC_NLD7 (MTK_PIN_NO(111) | 4)
+
+#define MT2701_PIN_112_MSDC0_DAT6__FUNC_GPIO112 (MTK_PIN_NO(112) | 0)
+#define MT2701_PIN_112_MSDC0_DAT6__FUNC_MSDC0_DAT6 (MTK_PIN_NO(112) | 1)
+#define MT2701_PIN_112_MSDC0_DAT6__FUNC_NLD6 (MTK_PIN_NO(112) | 4)
+
+#define MT2701_PIN_113_MSDC0_DAT5__FUNC_GPIO113 (MTK_PIN_NO(113) | 0)
+#define MT2701_PIN_113_MSDC0_DAT5__FUNC_MSDC0_DAT5 (MTK_PIN_NO(113) | 1)
+#define MT2701_PIN_113_MSDC0_DAT5__FUNC_NLD5 (MTK_PIN_NO(113) | 4)
+
+#define MT2701_PIN_114_MSDC0_DAT4__FUNC_GPIO114 (MTK_PIN_NO(114) | 0)
+#define MT2701_PIN_114_MSDC0_DAT4__FUNC_MSDC0_DAT4 (MTK_PIN_NO(114) | 1)
+#define MT2701_PIN_114_MSDC0_DAT4__FUNC_NLD4 (MTK_PIN_NO(114) | 4)
+
+#define MT2701_PIN_115_MSDC0_RSTB__FUNC_GPIO115 (MTK_PIN_NO(115) | 0)
+#define MT2701_PIN_115_MSDC0_RSTB__FUNC_MSDC0_RSTB (MTK_PIN_NO(115) | 1)
+#define MT2701_PIN_115_MSDC0_RSTB__FUNC_NLD8 (MTK_PIN_NO(115) | 4)
+
+#define MT2701_PIN_116_MSDC0_CMD__FUNC_GPIO116 (MTK_PIN_NO(116) | 0)
+#define MT2701_PIN_116_MSDC0_CMD__FUNC_MSDC0_CMD (MTK_PIN_NO(116) | 1)
+#define MT2701_PIN_116_MSDC0_CMD__FUNC_NALE (MTK_PIN_NO(116) | 4)
+
+#define MT2701_PIN_117_MSDC0_CLK__FUNC_GPIO117 (MTK_PIN_NO(117) | 0)
+#define MT2701_PIN_117_MSDC0_CLK__FUNC_MSDC0_CLK (MTK_PIN_NO(117) | 1)
+#define MT2701_PIN_117_MSDC0_CLK__FUNC_NWEB (MTK_PIN_NO(117) | 4)
+
+#define MT2701_PIN_118_MSDC0_DAT3__FUNC_GPIO118 (MTK_PIN_NO(118) | 0)
+#define MT2701_PIN_118_MSDC0_DAT3__FUNC_MSDC0_DAT3 (MTK_PIN_NO(118) | 1)
+#define MT2701_PIN_118_MSDC0_DAT3__FUNC_NLD3 (MTK_PIN_NO(118) | 4)
+
+#define MT2701_PIN_119_MSDC0_DAT2__FUNC_GPIO119 (MTK_PIN_NO(119) | 0)
+#define MT2701_PIN_119_MSDC0_DAT2__FUNC_MSDC0_DAT2 (MTK_PIN_NO(119) | 1)
+#define MT2701_PIN_119_MSDC0_DAT2__FUNC_NLD2 (MTK_PIN_NO(119) | 4)
+
+#define MT2701_PIN_120_MSDC0_DAT1__FUNC_GPIO120 (MTK_PIN_NO(120) | 0)
+#define MT2701_PIN_120_MSDC0_DAT1__FUNC_MSDC0_DAT1 (MTK_PIN_NO(120) | 1)
+#define MT2701_PIN_120_MSDC0_DAT1__FUNC_NLD1 (MTK_PIN_NO(120) | 4)
+
+#define MT2701_PIN_121_MSDC0_DAT0__FUNC_GPIO121 (MTK_PIN_NO(121) | 0)
+#define MT2701_PIN_121_MSDC0_DAT0__FUNC_MSDC0_DAT0 (MTK_PIN_NO(121) | 1)
+#define MT2701_PIN_121_MSDC0_DAT0__FUNC_NLD0 (MTK_PIN_NO(121) | 4)
+#define MT2701_PIN_121_MSDC0_DAT0__FUNC_WATCHDOG (MTK_PIN_NO(121) | 5)
+
+#define MT2701_PIN_122_CEC__FUNC_GPIO122 (MTK_PIN_NO(122) | 0)
+#define MT2701_PIN_122_CEC__FUNC_CEC (MTK_PIN_NO(122) | 1)
+#define MT2701_PIN_122_CEC__FUNC_SDA2 (MTK_PIN_NO(122) | 4)
+#define MT2701_PIN_122_CEC__FUNC_URXD0 (MTK_PIN_NO(122) | 5)
+
+#define MT2701_PIN_123_HTPLG__FUNC_GPIO123 (MTK_PIN_NO(123) | 0)
+#define MT2701_PIN_123_HTPLG__FUNC_HTPLG (MTK_PIN_NO(123) | 1)
+#define MT2701_PIN_123_HTPLG__FUNC_SCL2 (MTK_PIN_NO(123) | 4)
+#define MT2701_PIN_123_HTPLG__FUNC_UTXD0 (MTK_PIN_NO(123) | 5)
+
+#define MT2701_PIN_124_HDMISCK__FUNC_GPIO124 (MTK_PIN_NO(124) | 0)
+#define MT2701_PIN_124_HDMISCK__FUNC_HDMISCK (MTK_PIN_NO(124) | 1)
+#define MT2701_PIN_124_HDMISCK__FUNC_SDA1 (MTK_PIN_NO(124) | 4)
+#define MT2701_PIN_124_HDMISCK__FUNC_PWM3 (MTK_PIN_NO(124) | 5)
+
+#define MT2701_PIN_125_HDMISD__FUNC_GPIO125 (MTK_PIN_NO(125) | 0)
+#define MT2701_PIN_125_HDMISD__FUNC_HDMISD (MTK_PIN_NO(125) | 1)
+#define MT2701_PIN_125_HDMISD__FUNC_SCL1 (MTK_PIN_NO(125) | 4)
+#define MT2701_PIN_125_HDMISD__FUNC_PWM4 (MTK_PIN_NO(125) | 5)
+
+#define MT2701_PIN_126_I2S0_MCLK__FUNC_GPIO126 (MTK_PIN_NO(126) | 0)
+#define MT2701_PIN_126_I2S0_MCLK__FUNC_I2S0_MCLK (MTK_PIN_NO(126) | 1)
+#define MT2701_PIN_126_I2S0_MCLK__FUNC_WCN_I2S_MCLK (MTK_PIN_NO(126) | 6)
+#define MT2701_PIN_126_I2S0_MCLK__FUNC_DBG_MON_B_6 (MTK_PIN_NO(126) | 7)
+
+#define MT2701_PIN_199_SPI1_CLK__FUNC_GPIO199 (MTK_PIN_NO(199) | 0)
+#define MT2701_PIN_199_SPI1_CLK__FUNC_SPI1_CK (MTK_PIN_NO(199) | 1)
+#define MT2701_PIN_199_SPI1_CLK__FUNC_EXT_FRAME_SYNC (MTK_PIN_NO(199) | 3)
+#define MT2701_PIN_199_SPI1_CLK__FUNC_KCOL3 (MTK_PIN_NO(199) | 4)
+#define MT2701_PIN_199_SPI1_CLK__FUNC_DBG_MON_B_15 (MTK_PIN_NO(199) | 7)
+
+#define MT2701_PIN_200_SPDIF_OUT__FUNC_GPIO200 (MTK_PIN_NO(200) | 0)
+#define MT2701_PIN_200_SPDIF_OUT__FUNC_SPDIF_OUT (MTK_PIN_NO(200) | 1)
+#define MT2701_PIN_200_SPDIF_OUT__FUNC_G1_TXD3 (MTK_PIN_NO(200) | 5)
+#define MT2701_PIN_200_SPDIF_OUT__FUNC_URXD2 (MTK_PIN_NO(200) | 6)
+#define MT2701_PIN_200_SPDIF_OUT__FUNC_DBG_MON_B_16 (MTK_PIN_NO(200) | 7)
+
+#define MT2701_PIN_201_SPDIF_IN0__FUNC_GPIO201 (MTK_PIN_NO(201) | 0)
+#define MT2701_PIN_201_SPDIF_IN0__FUNC_SPDIF_IN0 (MTK_PIN_NO(201) | 1)
+#define MT2701_PIN_201_SPDIF_IN0__FUNC_G1_TXEN (MTK_PIN_NO(201) | 5)
+#define MT2701_PIN_201_SPDIF_IN0__FUNC_UTXD2 (MTK_PIN_NO(201) | 6)
+#define MT2701_PIN_201_SPDIF_IN0__FUNC_DBG_MON_B_17 (MTK_PIN_NO(201) | 7)
+
+#define MT2701_PIN_202_SPDIF_IN1__FUNC_GPIO202 (MTK_PIN_NO(202) | 0)
+#define MT2701_PIN_202_SPDIF_IN1__FUNC_SPDIF_IN1 (MTK_PIN_NO(202) | 1)
+
+#define MT2701_PIN_203_PWM0__FUNC_GPIO203 (MTK_PIN_NO(203) | 0)
+#define MT2701_PIN_203_PWM0__FUNC_PWM0 (MTK_PIN_NO(203) | 1)
+#define MT2701_PIN_203_PWM0__FUNC_DISP_PWM (MTK_PIN_NO(203) | 2)
+#define MT2701_PIN_203_PWM0__FUNC_G1_TXD2 (MTK_PIN_NO(203) | 5)
+#define MT2701_PIN_203_PWM0__FUNC_DBG_MON_B_18 (MTK_PIN_NO(203) | 7)
+#define MT2701_PIN_203_PWM0__FUNC_I2S2_DATA (MTK_PIN_NO(203) | 9)
+
+#define MT2701_PIN_204_PWM1__FUNC_GPIO204 (MTK_PIN_NO(204) | 0)
+#define MT2701_PIN_204_PWM1__FUNC_PWM1 (MTK_PIN_NO(204) | 1)
+#define MT2701_PIN_204_PWM1__FUNC_CLKM3 (MTK_PIN_NO(204) | 2)
+#define MT2701_PIN_204_PWM1__FUNC_G1_TXD1 (MTK_PIN_NO(204) | 5)
+#define MT2701_PIN_204_PWM1__FUNC_DBG_MON_B_19 (MTK_PIN_NO(204) | 7)
+#define MT2701_PIN_204_PWM1__FUNC_I2S3_DATA (MTK_PIN_NO(204) | 9)
+
+#define MT2701_PIN_205_PWM2__FUNC_GPIO205 (MTK_PIN_NO(205) | 0)
+#define MT2701_PIN_205_PWM2__FUNC_PWM2 (MTK_PIN_NO(205) | 1)
+#define MT2701_PIN_205_PWM2__FUNC_CLKM2 (MTK_PIN_NO(205) | 2)
+#define MT2701_PIN_205_PWM2__FUNC_G1_TXD0 (MTK_PIN_NO(205) | 5)
+#define MT2701_PIN_205_PWM2__FUNC_DBG_MON_B_20 (MTK_PIN_NO(205) | 7)
+
+#define MT2701_PIN_206_PWM3__FUNC_GPIO206 (MTK_PIN_NO(206) | 0)
+#define MT2701_PIN_206_PWM3__FUNC_PWM3 (MTK_PIN_NO(206) | 1)
+#define MT2701_PIN_206_PWM3__FUNC_CLKM1 (MTK_PIN_NO(206) | 2)
+#define MT2701_PIN_206_PWM3__FUNC_EXT_FRAME_SYNC (MTK_PIN_NO(206) | 3)
+#define MT2701_PIN_206_PWM3__FUNC_G1_TXC (MTK_PIN_NO(206) | 5)
+#define MT2701_PIN_206_PWM3__FUNC_DBG_MON_B_21 (MTK_PIN_NO(206) | 7)
+
+#define MT2701_PIN_207_PWM4__FUNC_GPIO207 (MTK_PIN_NO(207) | 0)
+#define MT2701_PIN_207_PWM4__FUNC_PWM4 (MTK_PIN_NO(207) | 1)
+#define MT2701_PIN_207_PWM4__FUNC_CLKM0 (MTK_PIN_NO(207) | 2)
+#define MT2701_PIN_207_PWM4__FUNC_EXT_FRAME_SYNC (MTK_PIN_NO(207) | 3)
+#define MT2701_PIN_207_PWM4__FUNC_G1_RXC (MTK_PIN_NO(207) | 5)
+#define MT2701_PIN_207_PWM4__FUNC_DBG_MON_B_22 (MTK_PIN_NO(207) | 7)
+
+#define MT2701_PIN_208_AUD_EXT_CK1__FUNC_GPIO208 (MTK_PIN_NO(208) | 0)
+#define MT2701_PIN_208_AUD_EXT_CK1__FUNC_AUD_EXT_CK1 (MTK_PIN_NO(208) | 1)
+#define MT2701_PIN_208_AUD_EXT_CK1__FUNC_PWM0 (MTK_PIN_NO(208) | 2)
+#define MT2701_PIN_208_AUD_EXT_CK1__FUNC_ANT_SEL5 (MTK_PIN_NO(208) | 4)
+#define MT2701_PIN_208_AUD_EXT_CK1__FUNC_DISP_PWM (MTK_PIN_NO(208) | 5)
+#define MT2701_PIN_208_AUD_EXT_CK1__FUNC_DBG_MON_A_31 (MTK_PIN_NO(208) | 7)
+#define MT2701_PIN_208_AUD_EXT_CK1__FUNC_PCIE0_PERST_N (MTK_PIN_NO(208) | 11)
+
+#define MT2701_PIN_209_AUD_EXT_CK2__FUNC_GPIO209 (MTK_PIN_NO(209) | 0)
+#define MT2701_PIN_209_AUD_EXT_CK2__FUNC_AUD_EXT_CK2 (MTK_PIN_NO(209) | 1)
+#define MT2701_PIN_209_AUD_EXT_CK2__FUNC_MSDC1_WP (MTK_PIN_NO(209) | 2)
+#define MT2701_PIN_209_AUD_EXT_CK2__FUNC_PWM1 (MTK_PIN_NO(209) | 5)
+#define MT2701_PIN_209_AUD_EXT_CK2__FUNC_DBG_MON_A_32 (MTK_PIN_NO(209) | 7)
+#define MT2701_PIN_209_AUD_EXT_CK2__FUNC_PCIE1_PERST_N (MTK_PIN_NO(209) | 11)
+
+#define MT2701_PIN_236_EXT_SDIO3__FUNC_GPIO236 (MTK_PIN_NO(236) | 0)
+#define MT2701_PIN_236_EXT_SDIO3__FUNC_EXT_SDIO3 (MTK_PIN_NO(236) | 1)
+#define MT2701_PIN_236_EXT_SDIO3__FUNC_IDDIG (MTK_PIN_NO(236) | 2)
+#define MT2701_PIN_236_EXT_SDIO3__FUNC_DBG_MON_A_1 (MTK_PIN_NO(236) | 7)
+
+#define MT2701_PIN_237_EXT_SDIO2__FUNC_GPIO237 (MTK_PIN_NO(237) | 0)
+#define MT2701_PIN_237_EXT_SDIO2__FUNC_EXT_SDIO2 (MTK_PIN_NO(237) | 1)
+#define MT2701_PIN_237_EXT_SDIO2__FUNC_DRV_VBUS (MTK_PIN_NO(237) | 2)
+
+#define MT2701_PIN_238_EXT_SDIO1__FUNC_GPIO238 (MTK_PIN_NO(238) | 0)
+#define MT2701_PIN_238_EXT_SDIO1__FUNC_EXT_SDIO1 (MTK_PIN_NO(238) | 1)
+#define MT2701_PIN_238_EXT_SDIO1__FUNC_IDDIG_P1 (MTK_PIN_NO(238) | 2)
+
+#define MT2701_PIN_239_EXT_SDIO0__FUNC_GPIO239 (MTK_PIN_NO(239) | 0)
+#define MT2701_PIN_239_EXT_SDIO0__FUNC_EXT_SDIO0 (MTK_PIN_NO(239) | 1)
+#define MT2701_PIN_239_EXT_SDIO0__FUNC_DRV_VBUS_P1 (MTK_PIN_NO(239) | 2)
+
+#define MT2701_PIN_240_EXT_XCS__FUNC_GPIO240 (MTK_PIN_NO(240) | 0)
+#define MT2701_PIN_240_EXT_XCS__FUNC_EXT_XCS (MTK_PIN_NO(240) | 1)
+
+#define MT2701_PIN_241_EXT_SCK__FUNC_GPIO241 (MTK_PIN_NO(241) | 0)
+#define MT2701_PIN_241_EXT_SCK__FUNC_EXT_SCK (MTK_PIN_NO(241) | 1)
+
+#define MT2701_PIN_242_URTS2__FUNC_GPIO242 (MTK_PIN_NO(242) | 0)
+#define MT2701_PIN_242_URTS2__FUNC_URTS2 (MTK_PIN_NO(242) | 1)
+#define MT2701_PIN_242_URTS2__FUNC_UTXD3 (MTK_PIN_NO(242) | 2)
+#define MT2701_PIN_242_URTS2__FUNC_URXD3 (MTK_PIN_NO(242) | 3)
+#define MT2701_PIN_242_URTS2__FUNC_SCL1 (MTK_PIN_NO(242) | 4)
+#define MT2701_PIN_242_URTS2__FUNC_DBG_MON_B_32 (MTK_PIN_NO(242) | 7)
+
+#define MT2701_PIN_243_UCTS2__FUNC_GPIO243 (MTK_PIN_NO(243) | 0)
+#define MT2701_PIN_243_UCTS2__FUNC_UCTS2 (MTK_PIN_NO(243) | 1)
+#define MT2701_PIN_243_UCTS2__FUNC_URXD3 (MTK_PIN_NO(243) | 2)
+#define MT2701_PIN_243_UCTS2__FUNC_UTXD3 (MTK_PIN_NO(243) | 3)
+#define MT2701_PIN_243_UCTS2__FUNC_SDA1 (MTK_PIN_NO(243) | 4)
+#define MT2701_PIN_243_UCTS2__FUNC_DBG_MON_A_6 (MTK_PIN_NO(243) | 7)
+
+#define MT2701_PIN_244_HDMI_SDA_RX__FUNC_GPIO244 (MTK_PIN_NO(244) | 0)
+#define MT2701_PIN_244_HDMI_SDA_RX__FUNC_HDMI_SDA_RX (MTK_PIN_NO(244) | 1)
+
+#define MT2701_PIN_245_HDMI_SCL_RX__FUNC_GPIO245 (MTK_PIN_NO(245) | 0)
+#define MT2701_PIN_245_HDMI_SCL_RX__FUNC_HDMI_SCL_RX (MTK_PIN_NO(245) | 1)
+
+#define MT2701_PIN_246_MHL_SENCE__FUNC_GPIO246 (MTK_PIN_NO(246) | 0)
+
+#define MT2701_PIN_247_HDMI_HPD_CBUS_RX__FUNC_GPIO247 (MTK_PIN_NO(247) | 0)
+#define MT2701_PIN_247_HDMI_HPD_CBUS_RX__FUNC_HDMI_HPD_RX (MTK_PIN_NO(247) | 1)
+
+#define MT2701_PIN_248_HDMI_TESTOUTP_RX__FUNC_GPIO248 (MTK_PIN_NO(248) | 0)
+#define MT2701_PIN_248_HDMI_TESTOUTP_RX__FUNC_HDMI_TESTOUTP_RX (MTK_PIN_NO(248) | 1)
+
+#define MT2701_PIN_249_MSDC0E_RSTB__FUNC_MSDC0E_RSTB (MTK_PIN_NO(249) | 9)
+
+#define MT2701_PIN_250_MSDC0E_DAT7__FUNC_MSDC3_DAT7 (MTK_PIN_NO(250) | 9)
+#define MT2701_PIN_250_MSDC0E_DAT7__FUNC_PCIE0_CLKREQ_N (MTK_PIN_NO(250) | 14)
+
+#define MT2701_PIN_251_MSDC0E_DAT6__FUNC_MSDC3_DAT6 (MTK_PIN_NO(251) | 9)
+#define MT2701_PIN_251_MSDC0E_DAT6__FUNC_PCIE0_WAKE_N (MTK_PIN_NO(251) | 14)
+
+#define MT2701_PIN_252_MSDC0E_DAT5__FUNC_MSDC3_DAT5 (MTK_PIN_NO(252) | 9)
+#define MT2701_PIN_252_MSDC0E_DAT5__FUNC_PCIE1_CLKREQ_N (MTK_PIN_NO(252) | 14)
+
+#define MT2701_PIN_253_MSDC0E_DAT4__FUNC_MSDC3_DAT4 (MTK_PIN_NO(253) | 9)
+#define MT2701_PIN_253_MSDC0E_DAT4__FUNC_PCIE1_WAKE_N (MTK_PIN_NO(253) | 14)
+
+#define MT2701_PIN_254_MSDC0E_DAT3__FUNC_MSDC3_DAT3 (MTK_PIN_NO(254) | 9)
+#define MT2701_PIN_254_MSDC0E_DAT3__FUNC_PCIE2_CLKREQ_N (MTK_PIN_NO(254) | 14)
+
+#define MT2701_PIN_255_MSDC0E_DAT2__FUNC_MSDC3_DAT2 (MTK_PIN_NO(255) | 9)
+#define MT2701_PIN_255_MSDC0E_DAT2__FUNC_PCIE2_WAKE_N (MTK_PIN_NO(255) | 14)
+
+#define MT2701_PIN_256_MSDC0E_DAT1__FUNC_MSDC3_DAT1 (MTK_PIN_NO(256) | 9)
+
+#define MT2701_PIN_257_MSDC0E_DAT0__FUNC_MSDC3_DAT0 (MTK_PIN_NO(257) | 9)
+
+#define MT2701_PIN_258_MSDC0E_CMD__FUNC_MSDC3_CMD (MTK_PIN_NO(258) | 9)
+
+#define MT2701_PIN_259_MSDC0E_CLK__FUNC_MSDC3_CLK (MTK_PIN_NO(259) | 9)
+
+#define MT2701_PIN_260_MSDC0E_DSL__FUNC_MSDC3_DSL (MTK_PIN_NO(260) | 9)
+
+#define MT2701_PIN_261_MSDC1_INS__FUNC_GPIO261 (MTK_PIN_NO(261) | 0)
+#define MT2701_PIN_261_MSDC1_INS__FUNC_MSDC1_INS (MTK_PIN_NO(261) | 1)
+#define MT2701_PIN_261_MSDC1_INS__FUNC_DBG_MON_B_29 (MTK_PIN_NO(261) | 7)
+
+#define MT2701_PIN_262_G2_TXEN__FUNC_GPIO262 (MTK_PIN_NO(262) | 0)
+#define MT2701_PIN_262_G2_TXEN__FUNC_G2_TXEN (MTK_PIN_NO(262) | 1)
+
+#define MT2701_PIN_263_G2_TXD3__FUNC_GPIO263 (MTK_PIN_NO(263) | 0)
+#define MT2701_PIN_263_G2_TXD3__FUNC_G2_TXD3 (MTK_PIN_NO(263) | 1)
+#define MT2701_PIN_263_G2_TXD3__FUNC_ANT_SEL5 (MTK_PIN_NO(263) | 6)
+
+#define MT2701_PIN_264_G2_TXD2__FUNC_GPIO264 (MTK_PIN_NO(264) | 0)
+#define MT2701_PIN_264_G2_TXD2__FUNC_G2_TXD2 (MTK_PIN_NO(264) | 1)
+#define MT2701_PIN_264_G2_TXD2__FUNC_ANT_SEL4 (MTK_PIN_NO(264) | 6)
+
+#define MT2701_PIN_265_G2_TXD1__FUNC_GPIO265 (MTK_PIN_NO(265) | 0)
+#define MT2701_PIN_265_G2_TXD1__FUNC_G2_TXD1 (MTK_PIN_NO(265) | 1)
+#define MT2701_PIN_265_G2_TXD1__FUNC_ANT_SEL3 (MTK_PIN_NO(265) | 6)
+
+#define MT2701_PIN_266_G2_TXD0__FUNC_GPIO266 (MTK_PIN_NO(266) | 0)
+#define MT2701_PIN_266_G2_TXD0__FUNC_G2_TXD0 (MTK_PIN_NO(266) | 1)
+#define MT2701_PIN_266_G2_TXD0__FUNC_ANT_SEL2 (MTK_PIN_NO(266) | 6)
+
+#define MT2701_PIN_267_G2_TXC__FUNC_GPIO267 (MTK_PIN_NO(267) | 0)
+#define MT2701_PIN_267_G2_TXC__FUNC_G2_TXC (MTK_PIN_NO(267) | 1)
+
+#define MT2701_PIN_268_G2_RXC__FUNC_GPIO268 (MTK_PIN_NO(268) | 0)
+#define MT2701_PIN_268_G2_RXC__FUNC_G2_RXC (MTK_PIN_NO(268) | 1)
+
+#define MT2701_PIN_269_G2_RXD0__FUNC_GPIO269 (MTK_PIN_NO(269) | 0)
+#define MT2701_PIN_269_G2_RXD0__FUNC_G2_RXD0 (MTK_PIN_NO(269) | 1)
+
+#define MT2701_PIN_270_G2_RXD1__FUNC_GPIO270 (MTK_PIN_NO(270) | 0)
+#define MT2701_PIN_270_G2_RXD1__FUNC_G2_RXD1 (MTK_PIN_NO(270) | 1)
+
+#define MT2701_PIN_271_G2_RXD2__FUNC_GPIO271 (MTK_PIN_NO(271) | 0)
+#define MT2701_PIN_271_G2_RXD2__FUNC_G2_RXD2 (MTK_PIN_NO(271) | 1)
+
+#define MT2701_PIN_272_G2_RXD3__FUNC_GPIO272 (MTK_PIN_NO(272) | 0)
+#define MT2701_PIN_272_G2_RXD3__FUNC_G2_RXD3 (MTK_PIN_NO(272) | 1)
+
+#define MT2701_PIN_274_G2_RXDV__FUNC_GPIO274 (MTK_PIN_NO(274) | 0)
+#define MT2701_PIN_274_G2_RXDV__FUNC_G2_RXDV (MTK_PIN_NO(274) | 1)
+
+#define MT2701_PIN_275_MDC__FUNC_GPIO275 (MTK_PIN_NO(275) | 0)
+#define MT2701_PIN_275_MDC__FUNC_MDC (MTK_PIN_NO(275) | 1)
+#define MT2701_PIN_275_MDC__FUNC_ANT_SEL0 (MTK_PIN_NO(275) | 6)
+
+#define MT2701_PIN_276_MDIO__FUNC_GPIO276 (MTK_PIN_NO(276) | 0)
+#define MT2701_PIN_276_MDIO__FUNC_MDIO (MTK_PIN_NO(276) | 1)
+#define MT2701_PIN_276_MDIO__FUNC_ANT_SEL1 (MTK_PIN_NO(276) | 6)
+
+#define MT2701_PIN_278_JTAG_RESET__FUNC_GPIO278 (MTK_PIN_NO(278) | 0)
+#define MT2701_PIN_278_JTAG_RESET__FUNC_JTAG_RESET (MTK_PIN_NO(278) | 1)
+
+#endif /* __DTS_MT2701_PINFUNC_H */
diff --git a/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts b/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts
index 420788229e6f..aae8a7aceab7 100644
--- a/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts
+++ b/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts
@@ -228,6 +228,37 @@
 	};
 };
 
+&devbus_bootcs {
+	status = "okay";
+	devbus,keep-config;
+
+	flash@0 {
+		compatible = "jedec-flash";
+		reg = <0 0x40000>;
+		bank-width = <1>;
+
+		partitions {
+			compatible = "fixed-partitions";
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			header@0 {
+				reg = <0 0x30000>;
+				read-only;
+			};
+
+			uboot@30000 {
+				reg = <0x30000 0xF000>;
+				read-only;
+			};
+
+			uboot_env@3F000 {
+				reg = <0x3F000 0x1000>;
+			};
+		};
+	};
+};
+
 &mdio {
 	status = "okay";
 
diff --git a/arch/arm/boot/dts/r8a7791-porter.dts b/arch/arm/boot/dts/r8a7791-porter.dts
index 6713b1ea732b..01d239c3eaaa 100644
--- a/arch/arm/boot/dts/r8a7791-porter.dts
+++ b/arch/arm/boot/dts/r8a7791-porter.dts
@@ -283,7 +283,6 @@
 	pinctrl-names = "default";
 
 	status = "okay";
-	renesas,enable-gpio = <&gpio5 31 GPIO_ACTIVE_HIGH>;
 };
 
 &usbphy {
diff --git a/arch/arm/boot/dts/sama5d2-pinfunc.h b/arch/arm/boot/dts/sama5d2-pinfunc.h
index 1afe24629d1f..b0c912feaa2f 100644
--- a/arch/arm/boot/dts/sama5d2-pinfunc.h
+++ b/arch/arm/boot/dts/sama5d2-pinfunc.h
@@ -90,7 +90,7 @@
 #define PIN_PA14__I2SC1_MCK		PINMUX_PIN(PIN_PA14, 4, 2)
 #define PIN_PA14__FLEXCOM3_IO2		PINMUX_PIN(PIN_PA14, 5, 1)
 #define PIN_PA14__D9			PINMUX_PIN(PIN_PA14, 6, 2)
-#define PIN_PA15			14
+#define PIN_PA15			15
 #define PIN_PA15__GPIO			PINMUX_PIN(PIN_PA15, 0, 0)
 #define PIN_PA15__SPI0_MOSI		PINMUX_PIN(PIN_PA15, 1, 1)
 #define PIN_PA15__TF1			PINMUX_PIN(PIN_PA15, 2, 1)
diff --git a/arch/arm/boot/dts/socfpga.dtsi b/arch/arm/boot/dts/socfpga.dtsi
index 3ed4abdaaa9c..15cbc747c242 100644
--- a/arch/arm/boot/dts/socfpga.dtsi
+++ b/arch/arm/boot/dts/socfpga.dtsi
@@ -656,6 +656,26 @@
 			status = "disabled";
 		};
 
+		eccmgr: eccmgr@ffd08140 {
+			compatible = "altr,socfpga-ecc-manager";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges;
+
+			l2-ecc@ffd08140 {
+				compatible = "altr,socfpga-l2-ecc";
+				reg = <0xffd08140 0x4>;
+				interrupts = <0 36 1>, <0 37 1>;
+			};
+
+			ocram-ecc@ffd08144 {
+				compatible = "altr,socfpga-ocram-ecc";
+				reg = <0xffd08144 0x4>;
+				iram = <&ocram>;
+				interrupts = <0 178 1>, <0 179 1>;
+			};
+		};
+
 		L2: l2-cache@fffef000 {
 			compatible = "arm,pl310-cache";
 			reg = <0xfffef000 0x1000>;
diff --git a/arch/arm/boot/dts/tps65217.dtsi b/arch/arm/boot/dts/tps65217.dtsi
new file mode 100644
index 000000000000..a63272422d76
--- /dev/null
+++ b/arch/arm/boot/dts/tps65217.dtsi
@@ -0,0 +1,56 @@
+/*
+ * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Integrated Power Management Chip
+ * http://www.ti.com/lit/ds/symlink/tps65217.pdf
+ */
+
+&tps {
+	compatible = "ti,tps65217";
+
+	regulators {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		dcdc1_reg: regulator@0 {
+			reg = <0>;
+			regulator-compatible = "dcdc1";
+		};
+
+		dcdc2_reg: regulator@1 {
+			reg = <1>;
+			regulator-compatible = "dcdc2";
+		};
+
+		dcdc3_reg: regulator@2 {
+			reg = <2>;
+			regulator-compatible = "dcdc3";
+		};
+
+		ldo1_reg: regulator@3 {
+			reg = <3>;
+			regulator-compatible = "ldo1";
+		};
+
+		ldo2_reg: regulator@4 {
+			reg = <4>;
+			regulator-compatible = "ldo2";
+		};
+
+		ldo3_reg: regulator@5 {
+			reg = <5>;
+			regulator-compatible = "ldo3";
+		};
+
+		ldo4_reg: regulator@6 {
+			reg = <6>;
+			regulator-compatible = "ldo4";
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/vfxxx.dtsi b/arch/arm/boot/dts/vfxxx.dtsi
index a9ceb5bac40e..4539f8d909a5 100644
--- a/arch/arm/boot/dts/vfxxx.dtsi
+++ b/arch/arm/boot/dts/vfxxx.dtsi
@@ -629,5 +629,10 @@
 				status = "disabled";
 			};
 		};
+
+		iio-hwmon {
+			compatible = "iio-hwmon";
+			io-channels = <&adc0 16>, <&adc1 16>;
+		};
 	};
 };
diff --git a/arch/arm/common/icst.c b/arch/arm/common/icst.c
index 2dc6da70ae59..d7ed252708c5 100644
--- a/arch/arm/common/icst.c
+++ b/arch/arm/common/icst.c
@@ -16,7 +16,7 @@
  */
 #include <linux/module.h>
 #include <linux/kernel.h>
-
+#include <asm/div64.h>
 #include <asm/hardware/icst.h>
 
 /*
@@ -29,7 +29,11 @@ EXPORT_SYMBOL(icst525_s2div);
 
 unsigned long icst_hz(const struct icst_params *p, struct icst_vco vco)
 {
-	return p->ref * 2 * (vco.v + 8) / ((vco.r + 2) * p->s2div[vco.s]);
+	u64 dividend = p->ref * 2 * (u64)(vco.v + 8);
+	u32 divisor = (vco.r + 2) * p->s2div[vco.s];
+
+	do_div(dividend, divisor);
+	return (unsigned long)dividend;
 }
 
 EXPORT_SYMBOL(icst_hz);
@@ -58,6 +62,7 @@ icst_hz_to_vco(const struct icst_params *p, unsigned long freq)
 
 		if (f > p->vco_min && f <= p->vco_max)
 			break;
+		i++;
 	} while (i < 8);
 
 	if (i >= 8)
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index a7151744b85c..d18d6b42fcf5 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -292,24 +292,23 @@ CONFIG_FB=y
 CONFIG_FIRMWARE_EDID=y
 CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_TILEBLITTING=y
-CONFIG_OMAP2_DSS=m
-CONFIG_OMAP5_DSS_HDMI=y
-CONFIG_OMAP2_DSS_SDI=y
-CONFIG_OMAP2_DSS_DSI=y
+CONFIG_FB_OMAP5_DSS_HDMI=y
+CONFIG_FB_OMAP2_DSS_SDI=y
+CONFIG_FB_OMAP2_DSS_DSI=y
 CONFIG_FB_OMAP2=m
-CONFIG_DISPLAY_ENCODER_TFP410=m
-CONFIG_DISPLAY_ENCODER_TPD12S015=m
-CONFIG_DISPLAY_CONNECTOR_DVI=m
-CONFIG_DISPLAY_CONNECTOR_HDMI=m
-CONFIG_DISPLAY_CONNECTOR_ANALOG_TV=m
-CONFIG_DISPLAY_PANEL_DPI=m
-CONFIG_DISPLAY_PANEL_DSI_CM=m
-CONFIG_DISPLAY_PANEL_SONY_ACX565AKM=m
-CONFIG_DISPLAY_PANEL_LGPHILIPS_LB035Q02=m
-CONFIG_DISPLAY_PANEL_SHARP_LS037V7DW01=m
-CONFIG_DISPLAY_PANEL_TPO_TD028TTEC1=m
-CONFIG_DISPLAY_PANEL_TPO_TD043MTEA1=m
-CONFIG_DISPLAY_PANEL_NEC_NL8048HL11=m
+CONFIG_FB_OMAP2_ENCODER_TFP410=m
+CONFIG_FB_OMAP2_ENCODER_TPD12S015=m
+CONFIG_FB_OMAP2_CONNECTOR_DVI=m
+CONFIG_FB_OMAP2_CONNECTOR_HDMI=m
+CONFIG_FB_OMAP2_CONNECTOR_ANALOG_TV=m
+CONFIG_FB_OMAP2_PANEL_DPI=m
+CONFIG_FB_OMAP2_PANEL_DSI_CM=m
+CONFIG_FB_OMAP2_PANEL_SONY_ACX565AKM=m
+CONFIG_FB_OMAP2_PANEL_LGPHILIPS_LB035Q02=m
+CONFIG_FB_OMAP2_PANEL_SHARP_LS037V7DW01=m
+CONFIG_FB_OMAP2_PANEL_TPO_TD028TTEC1=m
+CONFIG_FB_OMAP2_PANEL_TPO_TD043MTEA1=m
+CONFIG_FB_OMAP2_PANEL_NEC_NL8048HL11=m
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 CONFIG_LCD_CLASS_DEVICE=y
 CONFIG_LCD_PLATFORM=y
diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c
index b445a5d56f43..da3c0428507b 100644
--- a/arch/arm/crypto/aes-ce-glue.c
+++ b/arch/arm/crypto/aes-ce-glue.c
@@ -15,6 +15,7 @@
 #include <crypto/ablk_helper.h>
 #include <crypto/algapi.h>
 #include <linux/module.h>
+#include <crypto/xts.h>
 
 MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions");
 MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
@@ -152,6 +153,10 @@ static int xts_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 	struct crypto_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm);
 	int ret;
 
+	ret = xts_check_key(tfm, in_key, key_len);
+	if (ret)
+		return ret;
+
 	ret = ce_aes_expandkey(&ctx->key1, in_key, key_len / 2);
 	if (!ret)
 		ret = ce_aes_expandkey(&ctx->key2, &in_key[key_len / 2],
@@ -364,7 +369,7 @@ static struct crypto_alg aes_algs[] = { {
 	.cra_blkcipher = {
 		.min_keysize	= AES_MIN_KEY_SIZE,
 		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
+		.ivsize		= 0,
 		.setkey		= ce_aes_setkey,
 		.encrypt	= ecb_encrypt,
 		.decrypt	= ecb_decrypt,
@@ -441,7 +446,7 @@ static struct crypto_alg aes_algs[] = { {
 	.cra_ablkcipher = {
 		.min_keysize	= AES_MIN_KEY_SIZE,
 		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
+		.ivsize		= 0,
 		.setkey		= ablk_set_key,
 		.encrypt	= ablk_encrypt,
 		.decrypt	= ablk_decrypt,
diff --git a/arch/arm/crypto/aesbs-glue.c b/arch/arm/crypto/aesbs-glue.c
index 6d685298690e..0511a6cafe24 100644
--- a/arch/arm/crypto/aesbs-glue.c
+++ b/arch/arm/crypto/aesbs-glue.c
@@ -13,6 +13,7 @@
 #include <crypto/ablk_helper.h>
 #include <crypto/algapi.h>
 #include <linux/module.h>
+#include <crypto/xts.h>
 
 #include "aes_glue.h"
 
@@ -89,6 +90,11 @@ static int aesbs_xts_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 {
 	struct aesbs_xts_ctx *ctx = crypto_tfm_ctx(tfm);
 	int bits = key_len * 4;
+	int err;
+
+	err = xts_check_key(tfm, in_key, key_len);
+	if (err)
+		return err;
 
 	if (private_AES_set_encrypt_key(in_key, bits, &ctx->enc.rk)) {
 		tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h
index 7da5503c0591..e08d15184056 100644
--- a/arch/arm/include/asm/arch_gicv3.h
+++ b/arch/arm/include/asm/arch_gicv3.h
@@ -117,6 +117,7 @@ static inline u32 gic_read_iar(void)
 	u32 irqstat;
 
 	asm volatile("mrc " __stringify(ICC_IAR1) : "=r" (irqstat));
+	dsb(sy);
 	return irqstat;
 }
 
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index d5525bfc7e3e..9156fc303afd 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -491,7 +491,6 @@ static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; }
 #endif
 
 #ifdef CONFIG_DEBUG_RODATA
-void mark_rodata_ro(void);
 void set_kernel_text_rw(void);
 void set_kernel_text_ro(void);
 #else
diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 194c91b610ff..15d58b42d5a1 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -19,38 +19,7 @@
 #ifndef __ARM_KVM_ASM_H__
 #define __ARM_KVM_ASM_H__
 
-/* 0 is reserved as an invalid value. */
-#define c0_MPIDR	1	/* MultiProcessor ID Register */
-#define c0_CSSELR	2	/* Cache Size Selection Register */
-#define c1_SCTLR	3	/* System Control Register */
-#define c1_ACTLR	4	/* Auxiliary Control Register */
-#define c1_CPACR	5	/* Coprocessor Access Control */
-#define c2_TTBR0	6	/* Translation Table Base Register 0 */
-#define c2_TTBR0_high	7	/* TTBR0 top 32 bits */
-#define c2_TTBR1	8	/* Translation Table Base Register 1 */
-#define c2_TTBR1_high	9	/* TTBR1 top 32 bits */
-#define c2_TTBCR	10	/* Translation Table Base Control R. */
-#define c3_DACR		11	/* Domain Access Control Register */
-#define c5_DFSR		12	/* Data Fault Status Register */
-#define c5_IFSR		13	/* Instruction Fault Status Register */
-#define c5_ADFSR	14	/* Auxilary Data Fault Status R */
-#define c5_AIFSR	15	/* Auxilary Instrunction Fault Status R */
-#define c6_DFAR		16	/* Data Fault Address Register */
-#define c6_IFAR		17	/* Instruction Fault Address Register */
-#define c7_PAR		18	/* Physical Address Register */
-#define c7_PAR_high	19	/* PAR top 32 bits */
-#define c9_L2CTLR	20	/* Cortex A15/A7 L2 Control Register */
-#define c10_PRRR	21	/* Primary Region Remap Register */
-#define c10_NMRR	22	/* Normal Memory Remap Register */
-#define c12_VBAR	23	/* Vector Base Address Register */
-#define c13_CID		24	/* Context ID Register */
-#define c13_TID_URW	25	/* Thread ID, User R/W */
-#define c13_TID_URO	26	/* Thread ID, User R/O */
-#define c13_TID_PRIV	27	/* Thread ID, Privileged */
-#define c14_CNTKCTL	28	/* Timer Control Register (PL1) */
-#define c10_AMAIR0	29	/* Auxilary Memory Attribute Indirection Reg0 */
-#define c10_AMAIR1	30	/* Auxilary Memory Attribute Indirection Reg1 */
-#define NR_CP15_REGS	31	/* Number of regs (incl. invalid) */
+#include <asm/virt.h>
 
 #define ARM_EXCEPTION_RESET	  0
 #define ARM_EXCEPTION_UNDEFINED   1
@@ -86,19 +55,15 @@ struct kvm_vcpu;
 extern char __kvm_hyp_init[];
 extern char __kvm_hyp_init_end[];
 
-extern char __kvm_hyp_exit[];
-extern char __kvm_hyp_exit_end[];
-
 extern char __kvm_hyp_vector[];
 
-extern char __kvm_hyp_code_start[];
-extern char __kvm_hyp_code_end[];
-
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
+
+extern void __init_stage2_translation(void);
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 3095df091ff8..ee5328fc4b06 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -68,12 +68,12 @@ static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu)
 
 static inline unsigned long *vcpu_pc(struct kvm_vcpu *vcpu)
 {
-	return &vcpu->arch.regs.usr_regs.ARM_pc;
+	return &vcpu->arch.ctxt.gp_regs.usr_regs.ARM_pc;
 }
 
 static inline unsigned long *vcpu_cpsr(struct kvm_vcpu *vcpu)
 {
-	return &vcpu->arch.regs.usr_regs.ARM_cpsr;
+	return &vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr;
 }
 
 static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
@@ -83,13 +83,13 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
 
 static inline bool mode_has_spsr(struct kvm_vcpu *vcpu)
 {
-	unsigned long cpsr_mode = vcpu->arch.regs.usr_regs.ARM_cpsr & MODE_MASK;
+	unsigned long cpsr_mode = vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr & MODE_MASK;
 	return (cpsr_mode > USR_MODE && cpsr_mode < SYSTEM_MODE);
 }
 
 static inline bool vcpu_mode_priv(struct kvm_vcpu *vcpu)
 {
-	unsigned long cpsr_mode = vcpu->arch.regs.usr_regs.ARM_cpsr & MODE_MASK;
+	unsigned long cpsr_mode = vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr & MODE_MASK;
 	return cpsr_mode > USR_MODE;;
 }
 
@@ -108,11 +108,6 @@ static inline phys_addr_t kvm_vcpu_get_fault_ipa(struct kvm_vcpu *vcpu)
 	return ((phys_addr_t)vcpu->arch.fault.hpfar & HPFAR_MASK) << 8;
 }
 
-static inline unsigned long kvm_vcpu_get_hyp_pc(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.fault.hyp_pc;
-}
-
 static inline bool kvm_vcpu_dabt_isvalid(struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_hsr(vcpu) & HSR_ISV;
@@ -143,6 +138,11 @@ static inline bool kvm_vcpu_dabt_iss1tw(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_S1PTW;
 }
 
+static inline bool kvm_vcpu_dabt_is_cm(struct kvm_vcpu *vcpu)
+{
+	return !!(kvm_vcpu_get_hsr(vcpu) & HSR_DABT_CM);
+}
+
 /* Get Access Size from a data abort */
 static inline int kvm_vcpu_dabt_get_as(struct kvm_vcpu *vcpu)
 {
@@ -192,7 +192,7 @@ static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu)
 
 static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.cp15[c0_MPIDR] & MPIDR_HWID_BITMASK;
+	return vcpu_cp15(vcpu, c0_MPIDR) & MPIDR_HWID_BITMASK;
 }
 
 static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index f9f27792d8ed..385070180c25 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -85,20 +85,61 @@ struct kvm_vcpu_fault_info {
 	u32 hsr;		/* Hyp Syndrome Register */
 	u32 hxfar;		/* Hyp Data/Inst. Fault Address Register */
 	u32 hpfar;		/* Hyp IPA Fault Address Register */
-	u32 hyp_pc;		/* PC when exception was taken from Hyp mode */
 };
 
-typedef struct vfp_hard_struct kvm_cpu_context_t;
+/*
+ * 0 is reserved as an invalid value.
+ * Order should be kept in sync with the save/restore code.
+ */
+enum vcpu_sysreg {
+	__INVALID_SYSREG__,
+	c0_MPIDR,		/* MultiProcessor ID Register */
+	c0_CSSELR,		/* Cache Size Selection Register */
+	c1_SCTLR,		/* System Control Register */
+	c1_ACTLR,		/* Auxiliary Control Register */
+	c1_CPACR,		/* Coprocessor Access Control */
+	c2_TTBR0,		/* Translation Table Base Register 0 */
+	c2_TTBR0_high,		/* TTBR0 top 32 bits */
+	c2_TTBR1,		/* Translation Table Base Register 1 */
+	c2_TTBR1_high,		/* TTBR1 top 32 bits */
+	c2_TTBCR,		/* Translation Table Base Control R. */
+	c3_DACR,		/* Domain Access Control Register */
+	c5_DFSR,		/* Data Fault Status Register */
+	c5_IFSR,		/* Instruction Fault Status Register */
+	c5_ADFSR,		/* Auxilary Data Fault Status R */
+	c5_AIFSR,		/* Auxilary Instrunction Fault Status R */
+	c6_DFAR,		/* Data Fault Address Register */
+	c6_IFAR,		/* Instruction Fault Address Register */
+	c7_PAR,			/* Physical Address Register */
+	c7_PAR_high,		/* PAR top 32 bits */
+	c9_L2CTLR,		/* Cortex A15/A7 L2 Control Register */
+	c10_PRRR,		/* Primary Region Remap Register */
+	c10_NMRR,		/* Normal Memory Remap Register */
+	c12_VBAR,		/* Vector Base Address Register */
+	c13_CID,		/* Context ID Register */
+	c13_TID_URW,		/* Thread ID, User R/W */
+	c13_TID_URO,		/* Thread ID, User R/O */
+	c13_TID_PRIV,		/* Thread ID, Privileged */
+	c14_CNTKCTL,		/* Timer Control Register (PL1) */
+	c10_AMAIR0,		/* Auxilary Memory Attribute Indirection Reg0 */
+	c10_AMAIR1,		/* Auxilary Memory Attribute Indirection Reg1 */
+	NR_CP15_REGS		/* Number of regs (incl. invalid) */
+};
+
+struct kvm_cpu_context {
+	struct kvm_regs	gp_regs;
+	struct vfp_hard_struct vfp;
+	u32 cp15[NR_CP15_REGS];
+};
+
+typedef struct kvm_cpu_context kvm_cpu_context_t;
 
 struct kvm_vcpu_arch {
-	struct kvm_regs regs;
+	struct kvm_cpu_context ctxt;
 
 	int target; /* Processor target */
 	DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES);
 
-	/* System control coprocessor (cp15) */
-	u32 cp15[NR_CP15_REGS];
-
 	/* The CPU type we expose to the VM */
 	u32 midr;
 
@@ -111,9 +152,6 @@ struct kvm_vcpu_arch {
 	/* Exception Information */
 	struct kvm_vcpu_fault_info fault;
 
-	/* Floating point registers (VFP and Advanced SIMD/NEON) */
-	struct vfp_hard_struct vfp_guest;
-
 	/* Host FP context */
 	kvm_cpu_context_t *host_cpu_context;
 
@@ -158,12 +196,14 @@ struct kvm_vcpu_stat {
 	u64 exits;
 };
 
+#define vcpu_cp15(v,r)	(v)->arch.ctxt.cp15[r]
+
 int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
 int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
 int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
-u64 kvm_call_hyp(void *hypfn, ...);
+unsigned long kvm_call_hyp(void *hypfn, ...);
 void force_vm_exit(const cpumask_t *mask);
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
@@ -220,6 +260,11 @@ static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
 	kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr);
 }
 
+static inline void __cpu_init_stage2(void)
+{
+	kvm_call_hyp(__init_stage2_translation);
+}
+
 static inline int kvm_arch_dev_ioctl_check_extension(long ext)
 {
 	return 0;
@@ -242,5 +287,20 @@ static inline void kvm_arm_init_debug(void) {}
 static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) {}
+static inline int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
+					     struct kvm_device_attr *attr)
+{
+	return -ENXIO;
+}
+static inline int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
+					     struct kvm_device_attr *attr)
+{
+	return -ENXIO;
+}
+static inline int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
+					     struct kvm_device_attr *attr)
+{
+	return -ENXIO;
+}
 
 #endif /* __ARM_KVM_HOST_H__ */
diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h
new file mode 100644
index 000000000000..f0e860761380
--- /dev/null
+++ b/arch/arm/include/asm/kvm_hyp.h
@@ -0,0 +1,139 @@
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM_KVM_HYP_H__
+#define __ARM_KVM_HYP_H__
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_mmu.h>
+#include <asm/vfp.h>
+
+#define __hyp_text __section(.hyp.text) notrace
+
+#define kern_hyp_va(v) (v)
+#define hyp_kern_va(v) (v)
+
+#define __ACCESS_CP15(CRn, Op1, CRm, Op2)	\
+	"mrc", "mcr", __stringify(p15, Op1, %0, CRn, CRm, Op2), u32
+#define __ACCESS_CP15_64(Op1, CRm)		\
+	"mrrc", "mcrr", __stringify(p15, Op1, %Q0, %R0, CRm), u64
+#define __ACCESS_VFP(CRn)			\
+	"mrc", "mcr", __stringify(p10, 7, %0, CRn, cr0, 0), u32
+
+#define __write_sysreg(v, r, w, c, t)	asm volatile(w " " c : : "r" ((t)(v)))
+#define write_sysreg(v, ...)		__write_sysreg(v, __VA_ARGS__)
+
+#define __read_sysreg(r, w, c, t) ({				\
+	t __val;						\
+	asm volatile(r " " c : "=r" (__val));			\
+	__val;							\
+})
+#define read_sysreg(...)		__read_sysreg(__VA_ARGS__)
+
+#define write_special(v, r)					\
+	asm volatile("msr " __stringify(r) ", %0" : : "r" (v))
+#define read_special(r) ({					\
+	u32 __val;						\
+	asm volatile("mrs %0, " __stringify(r) : "=r" (__val));	\
+	__val;							\
+})
+
+#define TTBR0		__ACCESS_CP15_64(0, c2)
+#define TTBR1		__ACCESS_CP15_64(1, c2)
+#define VTTBR		__ACCESS_CP15_64(6, c2)
+#define PAR		__ACCESS_CP15_64(0, c7)
+#define CNTV_CVAL	__ACCESS_CP15_64(3, c14)
+#define CNTVOFF		__ACCESS_CP15_64(4, c14)
+
+#define MIDR		__ACCESS_CP15(c0, 0, c0, 0)
+#define CSSELR		__ACCESS_CP15(c0, 2, c0, 0)
+#define VPIDR		__ACCESS_CP15(c0, 4, c0, 0)
+#define VMPIDR		__ACCESS_CP15(c0, 4, c0, 5)
+#define SCTLR		__ACCESS_CP15(c1, 0, c0, 0)
+#define CPACR		__ACCESS_CP15(c1, 0, c0, 2)
+#define HCR		__ACCESS_CP15(c1, 4, c1, 0)
+#define HDCR		__ACCESS_CP15(c1, 4, c1, 1)
+#define HCPTR		__ACCESS_CP15(c1, 4, c1, 2)
+#define HSTR		__ACCESS_CP15(c1, 4, c1, 3)
+#define TTBCR		__ACCESS_CP15(c2, 0, c0, 2)
+#define HTCR		__ACCESS_CP15(c2, 4, c0, 2)
+#define VTCR		__ACCESS_CP15(c2, 4, c1, 2)
+#define DACR		__ACCESS_CP15(c3, 0, c0, 0)
+#define DFSR		__ACCESS_CP15(c5, 0, c0, 0)
+#define IFSR		__ACCESS_CP15(c5, 0, c0, 1)
+#define ADFSR		__ACCESS_CP15(c5, 0, c1, 0)
+#define AIFSR		__ACCESS_CP15(c5, 0, c1, 1)
+#define HSR		__ACCESS_CP15(c5, 4, c2, 0)
+#define DFAR		__ACCESS_CP15(c6, 0, c0, 0)
+#define IFAR		__ACCESS_CP15(c6, 0, c0, 2)
+#define HDFAR		__ACCESS_CP15(c6, 4, c0, 0)
+#define HIFAR		__ACCESS_CP15(c6, 4, c0, 2)
+#define HPFAR		__ACCESS_CP15(c6, 4, c0, 4)
+#define ICIALLUIS	__ACCESS_CP15(c7, 0, c1, 0)
+#define ATS1CPR		__ACCESS_CP15(c7, 0, c8, 0)
+#define TLBIALLIS	__ACCESS_CP15(c8, 0, c3, 0)
+#define TLBIALLNSNHIS	__ACCESS_CP15(c8, 4, c3, 4)
+#define PRRR		__ACCESS_CP15(c10, 0, c2, 0)
+#define NMRR		__ACCESS_CP15(c10, 0, c2, 1)
+#define AMAIR0		__ACCESS_CP15(c10, 0, c3, 0)
+#define AMAIR1		__ACCESS_CP15(c10, 0, c3, 1)
+#define VBAR		__ACCESS_CP15(c12, 0, c0, 0)
+#define CID		__ACCESS_CP15(c13, 0, c0, 1)
+#define TID_URW		__ACCESS_CP15(c13, 0, c0, 2)
+#define TID_URO		__ACCESS_CP15(c13, 0, c0, 3)
+#define TID_PRIV	__ACCESS_CP15(c13, 0, c0, 4)
+#define HTPIDR		__ACCESS_CP15(c13, 4, c0, 2)
+#define CNTKCTL		__ACCESS_CP15(c14, 0, c1, 0)
+#define CNTV_CTL	__ACCESS_CP15(c14, 0, c3, 1)
+#define CNTHCTL		__ACCESS_CP15(c14, 4, c1, 0)
+
+#define VFP_FPEXC	__ACCESS_VFP(FPEXC)
+
+/* AArch64 compatibility macros, only for the timer so far */
+#define read_sysreg_el0(r)		read_sysreg(r##_el0)
+#define write_sysreg_el0(v, r)		write_sysreg(v, r##_el0)
+
+#define cntv_ctl_el0			CNTV_CTL
+#define cntv_cval_el0			CNTV_CVAL
+#define cntvoff_el2			CNTVOFF
+#define cnthctl_el2			CNTHCTL
+
+void __timer_save_state(struct kvm_vcpu *vcpu);
+void __timer_restore_state(struct kvm_vcpu *vcpu);
+
+void __vgic_v2_save_state(struct kvm_vcpu *vcpu);
+void __vgic_v2_restore_state(struct kvm_vcpu *vcpu);
+
+void __sysreg_save_state(struct kvm_cpu_context *ctxt);
+void __sysreg_restore_state(struct kvm_cpu_context *ctxt);
+
+void asmlinkage __vfp_save_state(struct vfp_hard_struct *vfp);
+void asmlinkage __vfp_restore_state(struct vfp_hard_struct *vfp);
+static inline bool __vfp_enabled(void)
+{
+	return !(read_sysreg(HCPTR) & (HCPTR_TCP(11) | HCPTR_TCP(10)));
+}
+
+void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt);
+void __hyp_text __banked_restore_state(struct kvm_cpu_context *ctxt);
+
+int asmlinkage __guest_enter(struct kvm_vcpu *vcpu,
+			     struct kvm_cpu_context *host);
+int asmlinkage __hyp_do_panic(const char *, int, u32);
+
+#endif /* __ARM_KVM_HYP_H__ */
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index a520b7987a29..da44be9db4fa 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -179,7 +179,7 @@ struct kvm;
 
 static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 {
-	return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101;
+	return (vcpu_cp15(vcpu, c1_SCTLR) & 0b101) == 0b101;
 }
 
 static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,
diff --git a/arch/arm/include/asm/pci.h b/arch/arm/include/asm/pci.h
index a5635444ca41..057d381f4e57 100644
--- a/arch/arm/include/asm/pci.h
+++ b/arch/arm/include/asm/pci.h
@@ -2,9 +2,6 @@
 #define ASMARM_PCI_H
 
 #ifdef __KERNEL__
-#include <asm-generic/pci-dma-compat.h>
-#include <asm-generic/pci-bridge.h>
-
 #include <asm/mach/pci.h> /* for pci_sys_data */
 
 extern unsigned long pcibios_min_io;
@@ -41,5 +38,4 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 }
 
 #endif /* __KERNEL__ */
- 
 #endif
diff --git a/arch/arm/include/asm/virt.h b/arch/arm/include/asm/virt.h
index 4371f45c5784..d4ceaf5f299b 100644
--- a/arch/arm/include/asm/virt.h
+++ b/arch/arm/include/asm/virt.h
@@ -74,6 +74,15 @@ static inline bool is_hyp_mode_mismatched(void)
 {
 	return !!(__boot_cpu_mode & BOOT_CPU_MODE_MISMATCH);
 }
+
+static inline bool is_kernel_in_hyp_mode(void)
+{
+	return false;
+}
+
+/* The section containing the hypervisor text */
+extern char __hyp_text_start[];
+extern char __hyp_text_end[];
 #endif
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h
index 0375c8caa061..9408a994cc91 100644
--- a/arch/arm/include/asm/xen/page-coherent.h
+++ b/arch/arm/include/asm/xen/page-coherent.h
@@ -35,14 +35,21 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
 	     dma_addr_t dev_addr, unsigned long offset, size_t size,
 	     enum dma_data_direction dir, struct dma_attrs *attrs)
 {
-	bool local = XEN_PFN_DOWN(dev_addr) == page_to_xen_pfn(page);
+	unsigned long page_pfn = page_to_xen_pfn(page);
+	unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
+	unsigned long compound_pages =
+		(1<<compound_order(page)) * XEN_PFN_PER_PAGE;
+	bool local = (page_pfn <= dev_pfn) &&
+		(dev_pfn - page_pfn < compound_pages);
+
 	/*
-	 * Dom0 is mapped 1:1, while the Linux page can be spanned accross
-	 * multiple Xen page, it's not possible to have a mix of local and
-	 * foreign Xen page. So if the first xen_pfn == mfn the page is local
-	 * otherwise it's a foreign page grant-mapped in dom0. If the page is
-	 * local we can safely call the native dma_ops function, otherwise we
-	 * call the xen specific function.
+	 * Dom0 is mapped 1:1, while the Linux page can span across
+	 * multiple Xen pages, it's not possible for it to contain a
+	 * mix of local and foreign Xen pages. So if the first xen_pfn
+	 * == mfn the page is local otherwise it's a foreign page
+	 * grant-mapped in dom0. If the page is local we can safely
+	 * call the native dma_ops function, otherwise we call the xen
+	 * specific function.
 	 */
 	if (local)
 		__generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 2c5f160be65e..ad325a8c7e1e 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -88,6 +88,7 @@ obj-$(CONFIG_DEBUG_LL)	+= debug.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 
 obj-$(CONFIG_ARM_VIRT_EXT)	+= hyp-stub.o
+AFLAGS_hyp-stub.o		:=-Wa,-march=armv7-a
 ifeq ($(CONFIG_ARM_PSCI),y)
 obj-$(CONFIG_SMP)		+= psci_smp.o
 endif
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 871b8267d211..27d05813ff09 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -170,41 +170,11 @@ int main(void)
   DEFINE(CACHE_WRITEBACK_GRANULE, __CACHE_WRITEBACK_GRANULE);
   BLANK();
 #ifdef CONFIG_KVM_ARM_HOST
-  DEFINE(VCPU_KVM,		offsetof(struct kvm_vcpu, kvm));
-  DEFINE(VCPU_MIDR,		offsetof(struct kvm_vcpu, arch.midr));
-  DEFINE(VCPU_CP15,		offsetof(struct kvm_vcpu, arch.cp15));
-  DEFINE(VCPU_VFP_GUEST,	offsetof(struct kvm_vcpu, arch.vfp_guest));
-  DEFINE(VCPU_VFP_HOST,		offsetof(struct kvm_vcpu, arch.host_cpu_context));
-  DEFINE(VCPU_REGS,		offsetof(struct kvm_vcpu, arch.regs));
-  DEFINE(VCPU_USR_REGS,		offsetof(struct kvm_vcpu, arch.regs.usr_regs));
-  DEFINE(VCPU_SVC_REGS,		offsetof(struct kvm_vcpu, arch.regs.svc_regs));
-  DEFINE(VCPU_ABT_REGS,		offsetof(struct kvm_vcpu, arch.regs.abt_regs));
-  DEFINE(VCPU_UND_REGS,		offsetof(struct kvm_vcpu, arch.regs.und_regs));
-  DEFINE(VCPU_IRQ_REGS,		offsetof(struct kvm_vcpu, arch.regs.irq_regs));
-  DEFINE(VCPU_FIQ_REGS,		offsetof(struct kvm_vcpu, arch.regs.fiq_regs));
-  DEFINE(VCPU_PC,		offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_pc));
-  DEFINE(VCPU_CPSR,		offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_cpsr));
-  DEFINE(VCPU_HCR,		offsetof(struct kvm_vcpu, arch.hcr));
-  DEFINE(VCPU_IRQ_LINES,	offsetof(struct kvm_vcpu, arch.irq_lines));
-  DEFINE(VCPU_HSR,		offsetof(struct kvm_vcpu, arch.fault.hsr));
-  DEFINE(VCPU_HxFAR,		offsetof(struct kvm_vcpu, arch.fault.hxfar));
-  DEFINE(VCPU_HPFAR,		offsetof(struct kvm_vcpu, arch.fault.hpfar));
-  DEFINE(VCPU_HYP_PC,		offsetof(struct kvm_vcpu, arch.fault.hyp_pc));
-  DEFINE(VCPU_VGIC_CPU,		offsetof(struct kvm_vcpu, arch.vgic_cpu));
-  DEFINE(VGIC_V2_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_hcr));
-  DEFINE(VGIC_V2_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr));
-  DEFINE(VGIC_V2_CPU_MISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_misr));
-  DEFINE(VGIC_V2_CPU_EISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_eisr));
-  DEFINE(VGIC_V2_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_v2.vgic_elrsr));
-  DEFINE(VGIC_V2_CPU_APR,	offsetof(struct vgic_cpu, vgic_v2.vgic_apr));
-  DEFINE(VGIC_V2_CPU_LR,	offsetof(struct vgic_cpu, vgic_v2.vgic_lr));
-  DEFINE(VGIC_CPU_NR_LR,	offsetof(struct vgic_cpu, nr_lr));
-  DEFINE(VCPU_TIMER_CNTV_CTL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl));
-  DEFINE(VCPU_TIMER_CNTV_CVAL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_cval));
-  DEFINE(KVM_TIMER_CNTVOFF,	offsetof(struct kvm, arch.timer.cntvoff));
-  DEFINE(KVM_TIMER_ENABLED,	offsetof(struct kvm, arch.timer.enabled));
-  DEFINE(KVM_VGIC_VCTRL,	offsetof(struct kvm, arch.vgic.vctrl_base));
-  DEFINE(KVM_VTTBR,		offsetof(struct kvm, arch.vttbr));
+  DEFINE(VCPU_GUEST_CTXT,	offsetof(struct kvm_vcpu, arch.ctxt));
+  DEFINE(VCPU_HOST_CTXT,	offsetof(struct kvm_vcpu, arch.host_cpu_context));
+  DEFINE(CPU_CTXT_VFP,		offsetof(struct kvm_cpu_context, vfp));
+  DEFINE(CPU_CTXT_GP_REGS,	offsetof(struct kvm_cpu_context, gp_regs));
+  DEFINE(GP_REGS_USR,		offsetof(struct kvm_regs, usr_regs));
 #endif
   BLANK();
 #ifdef CONFIG_VDSO
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 7d0cba6f1cc5..139791ed473d 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -176,13 +176,13 @@ static struct resource mem_res[] = {
 		.name = "Kernel code",
 		.start = 0,
 		.end = 0,
-		.flags = IORESOURCE_MEM
+		.flags = IORESOURCE_SYSTEM_RAM
 	},
 	{
 		.name = "Kernel data",
 		.start = 0,
 		.end = 0,
-		.flags = IORESOURCE_MEM
+		.flags = IORESOURCE_SYSTEM_RAM
 	}
 };
 
@@ -851,7 +851,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc)
 		res->name  = "System RAM";
 		res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
 		res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
-		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+		res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
 		request_resource(&iomem_resource, res);
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 37312f6749f3..baee70267f29 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -409,7 +409,7 @@ asmlinkage void secondary_start_kernel(void)
 	/*
 	 * OK, it's off to the idle thread for us
 	 */
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 8b60fde5ce48..b4139cbbbdd9 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -18,6 +18,11 @@
 	*(.proc.info.init)						\
 	VMLINUX_SYMBOL(__proc_info_end) = .;
 
+#define HYPERVISOR_TEXT							\
+	VMLINUX_SYMBOL(__hyp_text_start) = .;				\
+	*(.hyp.text)							\
+	VMLINUX_SYMBOL(__hyp_text_end) = .;
+
 #define IDMAP_TEXT							\
 	ALIGN_FUNCTION();						\
 	VMLINUX_SYMBOL(__idmap_text_start) = .;				\
@@ -108,6 +113,7 @@ SECTIONS
 			TEXT_TEXT
 			SCHED_TEXT
 			LOCK_TEXT
+			HYPERVISOR_TEXT
 			KPROBES_TEXT
 			*(.gnu.warning)
 			*(.glue_7)
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index c5eef02c52ba..eb1bf4309c13 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -17,6 +17,7 @@ AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt)
 KVM := ../../../virt/kvm
 kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o
 
+obj-$(CONFIG_KVM_ARM_HOST) += hyp/
 obj-y += kvm-arm.o init.o interrupts.o
 obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
 obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index dda1959f0dde..76552b51c7ae 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -28,6 +28,7 @@
 #include <linux/sched.h>
 #include <linux/kvm.h>
 #include <trace/events/kvm.h>
+#include <kvm/arm_pmu.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -265,6 +266,7 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 	kvm_mmu_free_memory_caches(vcpu);
 	kvm_timer_vcpu_terminate(vcpu);
 	kvm_vgic_vcpu_destroy(vcpu);
+	kvm_pmu_vcpu_destroy(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
@@ -320,6 +322,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	vcpu->cpu = -1;
 
 	kvm_arm_set_running_vcpu(NULL);
+	kvm_timer_vcpu_put(vcpu);
 }
 
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
@@ -506,18 +509,18 @@ static void kvm_arm_resume_guest(struct kvm *kvm)
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
-		wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
+		struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
 
 		vcpu->arch.pause = false;
-		wake_up_interruptible(wq);
+		swake_up(wq);
 	}
 }
 
 static void vcpu_sleep(struct kvm_vcpu *vcpu)
 {
-	wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
+	struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
 
-	wait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
+	swait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
 				       (!vcpu->arch.pause)));
 }
 
@@ -577,6 +580,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * non-preemptible context.
 		 */
 		preempt_disable();
+		kvm_pmu_flush_hwstate(vcpu);
 		kvm_timer_flush_hwstate(vcpu);
 		kvm_vgic_flush_hwstate(vcpu);
 
@@ -593,6 +597,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm) ||
 			vcpu->arch.power_off || vcpu->arch.pause) {
 			local_irq_enable();
+			kvm_pmu_sync_hwstate(vcpu);
 			kvm_timer_sync_hwstate(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
 			preempt_enable();
@@ -642,10 +647,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
 
 		/*
-		 * We must sync the timer state before the vgic state so that
-		 * the vgic can properly sample the updated state of the
+		 * We must sync the PMU and timer state before the vgic state so
+		 * that the vgic can properly sample the updated state of the
 		 * interrupt line.
 		 */
+		kvm_pmu_sync_hwstate(vcpu);
 		kvm_timer_sync_hwstate(vcpu);
 
 		kvm_vgic_sync_hwstate(vcpu);
@@ -823,11 +829,54 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static int kvm_arm_vcpu_set_attr(struct kvm_vcpu *vcpu,
+				 struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	default:
+		ret = kvm_arm_vcpu_arch_set_attr(vcpu, attr);
+		break;
+	}
+
+	return ret;
+}
+
+static int kvm_arm_vcpu_get_attr(struct kvm_vcpu *vcpu,
+				 struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	default:
+		ret = kvm_arm_vcpu_arch_get_attr(vcpu, attr);
+		break;
+	}
+
+	return ret;
+}
+
+static int kvm_arm_vcpu_has_attr(struct kvm_vcpu *vcpu,
+				 struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	default:
+		ret = kvm_arm_vcpu_arch_has_attr(vcpu, attr);
+		break;
+	}
+
+	return ret;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
 	struct kvm_vcpu *vcpu = filp->private_data;
 	void __user *argp = (void __user *)arg;
+	struct kvm_device_attr attr;
 
 	switch (ioctl) {
 	case KVM_ARM_VCPU_INIT: {
@@ -870,6 +919,21 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 			return -E2BIG;
 		return kvm_arm_copy_reg_indices(vcpu, user_list->reg);
 	}
+	case KVM_SET_DEVICE_ATTR: {
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			return -EFAULT;
+		return kvm_arm_vcpu_set_attr(vcpu, &attr);
+	}
+	case KVM_GET_DEVICE_ATTR: {
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			return -EFAULT;
+		return kvm_arm_vcpu_get_attr(vcpu, &attr);
+	}
+	case KVM_HAS_DEVICE_ATTR: {
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			return -EFAULT;
+		return kvm_arm_vcpu_has_attr(vcpu, &attr);
+	}
 	default:
 		return -EINVAL;
 	}
@@ -967,6 +1031,11 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	}
 }
 
+static void cpu_init_stage2(void *dummy)
+{
+	__cpu_init_stage2();
+}
+
 static void cpu_init_hyp_mode(void *dummy)
 {
 	phys_addr_t boot_pgd_ptr;
@@ -985,6 +1054,7 @@ static void cpu_init_hyp_mode(void *dummy)
 	vector_ptr = (unsigned long)__kvm_hyp_vector;
 
 	__cpu_init_hyp_mode(boot_pgd_ptr, pgd_ptr, hyp_stack_ptr, vector_ptr);
+	__cpu_init_stage2();
 
 	kvm_arm_init_debug();
 }
@@ -1035,6 +1105,82 @@ static inline void hyp_cpu_pm_init(void)
 }
 #endif
 
+static void teardown_common_resources(void)
+{
+	free_percpu(kvm_host_cpu_state);
+}
+
+static int init_common_resources(void)
+{
+	kvm_host_cpu_state = alloc_percpu(kvm_cpu_context_t);
+	if (!kvm_host_cpu_state) {
+		kvm_err("Cannot allocate host CPU state\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int init_subsystems(void)
+{
+	int err;
+
+	/*
+	 * Init HYP view of VGIC
+	 */
+	err = kvm_vgic_hyp_init();
+	switch (err) {
+	case 0:
+		vgic_present = true;
+		break;
+	case -ENODEV:
+	case -ENXIO:
+		vgic_present = false;
+		break;
+	default:
+		return err;
+	}
+
+	/*
+	 * Init HYP architected timer support
+	 */
+	err = kvm_timer_hyp_init();
+	if (err)
+		return err;
+
+	kvm_perf_init();
+	kvm_coproc_table_init();
+
+	return 0;
+}
+
+static void teardown_hyp_mode(void)
+{
+	int cpu;
+
+	if (is_kernel_in_hyp_mode())
+		return;
+
+	free_hyp_pgds();
+	for_each_possible_cpu(cpu)
+		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
+}
+
+static int init_vhe_mode(void)
+{
+	/*
+	 * Execute the init code on each CPU.
+	 */
+	on_each_cpu(cpu_init_stage2, NULL, 1);
+
+	/* set size of VMID supported by CPU */
+	kvm_vmid_bits = kvm_get_vmid_bits();
+	kvm_info("%d-bit VMID\n", kvm_vmid_bits);
+
+	kvm_info("VHE mode initialized successfully\n");
+	return 0;
+}
+
 /**
  * Inits Hyp-mode on all online CPUs
  */
@@ -1065,7 +1211,7 @@ static int init_hyp_mode(void)
 		stack_page = __get_free_page(GFP_KERNEL);
 		if (!stack_page) {
 			err = -ENOMEM;
-			goto out_free_stack_pages;
+			goto out_err;
 		}
 
 		per_cpu(kvm_arm_hyp_stack_page, cpu) = stack_page;
@@ -1074,16 +1220,16 @@ static int init_hyp_mode(void)
 	/*
 	 * Map the Hyp-code called directly from the host
 	 */
-	err = create_hyp_mappings(__kvm_hyp_code_start, __kvm_hyp_code_end);
+	err = create_hyp_mappings(__hyp_text_start, __hyp_text_end);
 	if (err) {
 		kvm_err("Cannot map world-switch code\n");
-		goto out_free_mappings;
+		goto out_err;
 	}
 
 	err = create_hyp_mappings(__start_rodata, __end_rodata);
 	if (err) {
 		kvm_err("Cannot map rodata section\n");
-		goto out_free_mappings;
+		goto out_err;
 	}
 
 	/*
@@ -1095,20 +1241,10 @@ static int init_hyp_mode(void)
 
 		if (err) {
 			kvm_err("Cannot map hyp stack\n");
-			goto out_free_mappings;
+			goto out_err;
 		}
 	}
 
-	/*
-	 * Map the host CPU structures
-	 */
-	kvm_host_cpu_state = alloc_percpu(kvm_cpu_context_t);
-	if (!kvm_host_cpu_state) {
-		err = -ENOMEM;
-		kvm_err("Cannot allocate host CPU state\n");
-		goto out_free_mappings;
-	}
-
 	for_each_possible_cpu(cpu) {
 		kvm_cpu_context_t *cpu_ctxt;
 
@@ -1117,7 +1253,7 @@ static int init_hyp_mode(void)
 
 		if (err) {
 			kvm_err("Cannot map host CPU state: %d\n", err);
-			goto out_free_context;
+			goto out_err;
 		}
 	}
 
@@ -1126,34 +1262,22 @@ static int init_hyp_mode(void)
 	 */
 	on_each_cpu(cpu_init_hyp_mode, NULL, 1);
 
-	/*
-	 * Init HYP view of VGIC
-	 */
-	err = kvm_vgic_hyp_init();
-	switch (err) {
-	case 0:
-		vgic_present = true;
-		break;
-	case -ENODEV:
-	case -ENXIO:
-		vgic_present = false;
-		break;
-	default:
-		goto out_free_context;
-	}
-
-	/*
-	 * Init HYP architected timer support
-	 */
-	err = kvm_timer_hyp_init();
-	if (err)
-		goto out_free_context;
-
 #ifndef CONFIG_HOTPLUG_CPU
 	free_boot_hyp_pgd();
 #endif
 
-	kvm_perf_init();
+	cpu_notifier_register_begin();
+
+	err = __register_cpu_notifier(&hyp_init_cpu_nb);
+
+	cpu_notifier_register_done();
+
+	if (err) {
+		kvm_err("Cannot register HYP init CPU notifier (%d)\n", err);
+		goto out_err;
+	}
+
+	hyp_cpu_pm_init();
 
 	/* set size of VMID supported by CPU */
 	kvm_vmid_bits = kvm_get_vmid_bits();
@@ -1162,14 +1286,9 @@ static int init_hyp_mode(void)
 	kvm_info("Hyp mode initialized successfully\n");
 
 	return 0;
-out_free_context:
-	free_percpu(kvm_host_cpu_state);
-out_free_mappings:
-	free_hyp_pgds();
-out_free_stack_pages:
-	for_each_possible_cpu(cpu)
-		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
+
 out_err:
+	teardown_hyp_mode();
 	kvm_err("error initializing Hyp mode: %d\n", err);
 	return err;
 }
@@ -1213,26 +1332,27 @@ int kvm_arch_init(void *opaque)
 		}
 	}
 
-	cpu_notifier_register_begin();
-
-	err = init_hyp_mode();
+	err = init_common_resources();
 	if (err)
-		goto out_err;
+		return err;
 
-	err = __register_cpu_notifier(&hyp_init_cpu_nb);
-	if (err) {
-		kvm_err("Cannot register HYP init CPU notifier (%d)\n", err);
+	if (is_kernel_in_hyp_mode())
+		err = init_vhe_mode();
+	else
+		err = init_hyp_mode();
+	if (err)
 		goto out_err;
-	}
-
-	cpu_notifier_register_done();
 
-	hyp_cpu_pm_init();
+	err = init_subsystems();
+	if (err)
+		goto out_hyp;
 
-	kvm_coproc_table_init();
 	return 0;
+
+out_hyp:
+	teardown_hyp_mode();
 out_err:
-	cpu_notifier_register_done();
+	teardown_common_resources();
 	return err;
 }
 
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index f3d88dc388bc..1bb2b79c01ff 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -16,6 +16,8 @@
  * along with this program; if not, write to the Free Software
  * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
  */
+
+#include <linux/bsearch.h>
 #include <linux/mm.h>
 #include <linux/kvm_host.h>
 #include <linux/uaccess.h>
@@ -54,8 +56,8 @@ static inline void vcpu_cp15_reg64_set(struct kvm_vcpu *vcpu,
 				       const struct coproc_reg *r,
 				       u64 val)
 {
-	vcpu->arch.cp15[r->reg] = val & 0xffffffff;
-	vcpu->arch.cp15[r->reg + 1] = val >> 32;
+	vcpu_cp15(vcpu, r->reg) = val & 0xffffffff;
+	vcpu_cp15(vcpu, r->reg + 1) = val >> 32;
 }
 
 static inline u64 vcpu_cp15_reg64_get(struct kvm_vcpu *vcpu,
@@ -63,9 +65,9 @@ static inline u64 vcpu_cp15_reg64_get(struct kvm_vcpu *vcpu,
 {
 	u64 val;
 
-	val = vcpu->arch.cp15[r->reg + 1];
+	val = vcpu_cp15(vcpu, r->reg + 1);
 	val = val << 32;
-	val = val | vcpu->arch.cp15[r->reg];
+	val = val | vcpu_cp15(vcpu, r->reg);
 	return val;
 }
 
@@ -104,7 +106,7 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
 	 * vcpu_id, but we read the 'U' bit from the underlying
 	 * hardware directly.
 	 */
-	vcpu->arch.cp15[c0_MPIDR] = ((read_cpuid_mpidr() & MPIDR_SMP_BITMASK) |
+	vcpu_cp15(vcpu, c0_MPIDR) = ((read_cpuid_mpidr() & MPIDR_SMP_BITMASK) |
 				     ((vcpu->vcpu_id >> 2) << MPIDR_LEVEL_BITS) |
 				     (vcpu->vcpu_id & 3));
 }
@@ -117,7 +119,7 @@ static bool access_actlr(struct kvm_vcpu *vcpu,
 	if (p->is_write)
 		return ignore_write(vcpu, p);
 
-	*vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c1_ACTLR];
+	*vcpu_reg(vcpu, p->Rt1) = vcpu_cp15(vcpu, c1_ACTLR);
 	return true;
 }
 
@@ -139,7 +141,7 @@ static bool access_l2ctlr(struct kvm_vcpu *vcpu,
 	if (p->is_write)
 		return ignore_write(vcpu, p);
 
-	*vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c9_L2CTLR];
+	*vcpu_reg(vcpu, p->Rt1) = vcpu_cp15(vcpu, c9_L2CTLR);
 	return true;
 }
 
@@ -156,7 +158,7 @@ static void reset_l2ctlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
 	ncores = min(ncores, 3U);
 	l2ctlr |= (ncores & 3) << 24;
 
-	vcpu->arch.cp15[c9_L2CTLR] = l2ctlr;
+	vcpu_cp15(vcpu, c9_L2CTLR) = l2ctlr;
 }
 
 static void reset_actlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
@@ -171,7 +173,7 @@ static void reset_actlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
 	else
 		actlr &= ~(1U << 6);
 
-	vcpu->arch.cp15[c1_ACTLR] = actlr;
+	vcpu_cp15(vcpu, c1_ACTLR) = actlr;
 }
 
 /*
@@ -218,9 +220,9 @@ bool access_vm_reg(struct kvm_vcpu *vcpu,
 
 	BUG_ON(!p->is_write);
 
-	vcpu->arch.cp15[r->reg] = *vcpu_reg(vcpu, p->Rt1);
+	vcpu_cp15(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt1);
 	if (p->is_64bit)
-		vcpu->arch.cp15[r->reg + 1] = *vcpu_reg(vcpu, p->Rt2);
+		vcpu_cp15(vcpu, r->reg + 1) = *vcpu_reg(vcpu, p->Rt2);
 
 	kvm_toggle_cache(vcpu, was_enabled);
 	return true;
@@ -381,17 +383,26 @@ static const struct coproc_reg cp15_regs[] = {
 	{ CRn(15), CRm( 0), Op1( 4), Op2( 0), is32, access_cbar},
 };
 
+static int check_reg_table(const struct coproc_reg *table, unsigned int n)
+{
+	unsigned int i;
+
+	for (i = 1; i < n; i++) {
+		if (cmp_reg(&table[i-1], &table[i]) >= 0) {
+			kvm_err("reg table %p out of order (%d)\n", table, i - 1);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
 /* Target specific emulation tables */
 static struct kvm_coproc_target_table *target_tables[KVM_ARM_NUM_TARGETS];
 
 void kvm_register_target_coproc_table(struct kvm_coproc_target_table *table)
 {
-	unsigned int i;
-
-	for (i = 1; i < table->num; i++)
-		BUG_ON(cmp_reg(&table->table[i-1],
-			       &table->table[i]) >= 0);
-
+	BUG_ON(check_reg_table(table->table, table->num));
 	target_tables[table->target] = table;
 }
 
@@ -405,29 +416,32 @@ static const struct coproc_reg *get_target_table(unsigned target, size_t *num)
 	return table->table;
 }
 
+#define reg_to_match_value(x)						\
+	({								\
+		unsigned long val;					\
+		val  = (x)->CRn << 11;					\
+		val |= (x)->CRm << 7;					\
+		val |= (x)->Op1 << 4;					\
+		val |= (x)->Op2 << 1;					\
+		val |= !(x)->is_64bit;					\
+		val;							\
+	 })
+
+static int match_reg(const void *key, const void *elt)
+{
+	const unsigned long pval = (unsigned long)key;
+	const struct coproc_reg *r = elt;
+
+	return pval - reg_to_match_value(r);
+}
+
 static const struct coproc_reg *find_reg(const struct coproc_params *params,
 					 const struct coproc_reg table[],
 					 unsigned int num)
 {
-	unsigned int i;
-
-	for (i = 0; i < num; i++) {
-		const struct coproc_reg *r = &table[i];
-
-		if (params->is_64bit != r->is_64)
-			continue;
-		if (params->CRn != r->CRn)
-			continue;
-		if (params->CRm != r->CRm)
-			continue;
-		if (params->Op1 != r->Op1)
-			continue;
-		if (params->Op2 != r->Op2)
-			continue;
+	unsigned long pval = reg_to_match_value(params);
 
-		return r;
-	}
-	return NULL;
+	return bsearch((void *)pval, table, num, sizeof(table[0]), match_reg);
 }
 
 static int emulate_cp15(struct kvm_vcpu *vcpu,
@@ -645,6 +659,9 @@ static struct coproc_reg invariant_cp15[] = {
 	{ CRn( 0), CRm( 0), Op1( 0), Op2( 3), is32, NULL, get_TLBTR },
 	{ CRn( 0), CRm( 0), Op1( 0), Op2( 6), is32, NULL, get_REVIDR },
 
+	{ CRn( 0), CRm( 0), Op1( 1), Op2( 1), is32, NULL, get_CLIDR },
+	{ CRn( 0), CRm( 0), Op1( 1), Op2( 7), is32, NULL, get_AIDR },
+
 	{ CRn( 0), CRm( 1), Op1( 0), Op2( 0), is32, NULL, get_ID_PFR0 },
 	{ CRn( 0), CRm( 1), Op1( 0), Op2( 1), is32, NULL, get_ID_PFR1 },
 	{ CRn( 0), CRm( 1), Op1( 0), Op2( 2), is32, NULL, get_ID_DFR0 },
@@ -660,9 +677,6 @@ static struct coproc_reg invariant_cp15[] = {
 	{ CRn( 0), CRm( 2), Op1( 0), Op2( 3), is32, NULL, get_ID_ISAR3 },
 	{ CRn( 0), CRm( 2), Op1( 0), Op2( 4), is32, NULL, get_ID_ISAR4 },
 	{ CRn( 0), CRm( 2), Op1( 0), Op2( 5), is32, NULL, get_ID_ISAR5 },
-
-	{ CRn( 0), CRm( 0), Op1( 1), Op2( 1), is32, NULL, get_CLIDR },
-	{ CRn( 0), CRm( 0), Op1( 1), Op2( 7), is32, NULL, get_AIDR },
 };
 
 /*
@@ -901,7 +915,7 @@ static int vfp_get_reg(const struct kvm_vcpu *vcpu, u64 id, void __user *uaddr)
 	if (vfpid < num_fp_regs()) {
 		if (KVM_REG_SIZE(id) != 8)
 			return -ENOENT;
-		return reg_to_user(uaddr, &vcpu->arch.vfp_guest.fpregs[vfpid],
+		return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpregs[vfpid],
 				   id);
 	}
 
@@ -911,13 +925,13 @@ static int vfp_get_reg(const struct kvm_vcpu *vcpu, u64 id, void __user *uaddr)
 
 	switch (vfpid) {
 	case KVM_REG_ARM_VFP_FPEXC:
-		return reg_to_user(uaddr, &vcpu->arch.vfp_guest.fpexc, id);
+		return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpexc, id);
 	case KVM_REG_ARM_VFP_FPSCR:
-		return reg_to_user(uaddr, &vcpu->arch.vfp_guest.fpscr, id);
+		return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpscr, id);
 	case KVM_REG_ARM_VFP_FPINST:
-		return reg_to_user(uaddr, &vcpu->arch.vfp_guest.fpinst, id);
+		return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpinst, id);
 	case KVM_REG_ARM_VFP_FPINST2:
-		return reg_to_user(uaddr, &vcpu->arch.vfp_guest.fpinst2, id);
+		return reg_to_user(uaddr, &vcpu->arch.ctxt.vfp.fpinst2, id);
 	case KVM_REG_ARM_VFP_MVFR0:
 		val = fmrx(MVFR0);
 		return reg_to_user(uaddr, &val, id);
@@ -945,7 +959,7 @@ static int vfp_set_reg(struct kvm_vcpu *vcpu, u64 id, const void __user *uaddr)
 	if (vfpid < num_fp_regs()) {
 		if (KVM_REG_SIZE(id) != 8)
 			return -ENOENT;
-		return reg_from_user(&vcpu->arch.vfp_guest.fpregs[vfpid],
+		return reg_from_user(&vcpu->arch.ctxt.vfp.fpregs[vfpid],
 				     uaddr, id);
 	}
 
@@ -955,13 +969,13 @@ static int vfp_set_reg(struct kvm_vcpu *vcpu, u64 id, const void __user *uaddr)
 
 	switch (vfpid) {
 	case KVM_REG_ARM_VFP_FPEXC:
-		return reg_from_user(&vcpu->arch.vfp_guest.fpexc, uaddr, id);
+		return reg_from_user(&vcpu->arch.ctxt.vfp.fpexc, uaddr, id);
 	case KVM_REG_ARM_VFP_FPSCR:
-		return reg_from_user(&vcpu->arch.vfp_guest.fpscr, uaddr, id);
+		return reg_from_user(&vcpu->arch.ctxt.vfp.fpscr, uaddr, id);
 	case KVM_REG_ARM_VFP_FPINST:
-		return reg_from_user(&vcpu->arch.vfp_guest.fpinst, uaddr, id);
+		return reg_from_user(&vcpu->arch.ctxt.vfp.fpinst, uaddr, id);
 	case KVM_REG_ARM_VFP_FPINST2:
-		return reg_from_user(&vcpu->arch.vfp_guest.fpinst2, uaddr, id);
+		return reg_from_user(&vcpu->arch.ctxt.vfp.fpinst2, uaddr, id);
 	/* These are invariant. */
 	case KVM_REG_ARM_VFP_MVFR0:
 		if (reg_from_user(&val, uaddr, id))
@@ -1030,7 +1044,7 @@ int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		val = vcpu_cp15_reg64_get(vcpu, r);
 		ret = reg_to_user(uaddr, &val, reg->id);
 	} else if (KVM_REG_SIZE(reg->id) == 4) {
-		ret = reg_to_user(uaddr, &vcpu->arch.cp15[r->reg], reg->id);
+		ret = reg_to_user(uaddr, &vcpu_cp15(vcpu, r->reg), reg->id);
 	}
 
 	return ret;
@@ -1060,7 +1074,7 @@ int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		if (!ret)
 			vcpu_cp15_reg64_set(vcpu, r, val);
 	} else if (KVM_REG_SIZE(reg->id) == 4) {
-		ret = reg_from_user(&vcpu->arch.cp15[r->reg], uaddr, reg->id);
+		ret = reg_from_user(&vcpu_cp15(vcpu, r->reg), uaddr, reg->id);
 	}
 
 	return ret;
@@ -1096,7 +1110,7 @@ static int write_demux_regids(u64 __user *uindices)
 static u64 cp15_to_index(const struct coproc_reg *reg)
 {
 	u64 val = KVM_REG_ARM | (15 << KVM_REG_ARM_COPROC_SHIFT);
-	if (reg->is_64) {
+	if (reg->is_64bit) {
 		val |= KVM_REG_SIZE_U64;
 		val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT);
 		/*
@@ -1210,8 +1224,8 @@ void kvm_coproc_table_init(void)
 	unsigned int i;
 
 	/* Make sure tables are unique and in order. */
-	for (i = 1; i < ARRAY_SIZE(cp15_regs); i++)
-		BUG_ON(cmp_reg(&cp15_regs[i-1], &cp15_regs[i]) >= 0);
+	BUG_ON(check_reg_table(cp15_regs, ARRAY_SIZE(cp15_regs)));
+	BUG_ON(check_reg_table(invariant_cp15, ARRAY_SIZE(invariant_cp15)));
 
 	/* We abuse the reset function to overwrite the table itself. */
 	for (i = 0; i < ARRAY_SIZE(invariant_cp15); i++)
@@ -1248,7 +1262,7 @@ void kvm_reset_coprocs(struct kvm_vcpu *vcpu)
 	const struct coproc_reg *table;
 
 	/* Catch someone adding a register without putting in reset entry. */
-	memset(vcpu->arch.cp15, 0x42, sizeof(vcpu->arch.cp15));
+	memset(vcpu->arch.ctxt.cp15, 0x42, sizeof(vcpu->arch.ctxt.cp15));
 
 	/* Generic chip reset first (so target could override). */
 	reset_coproc_regs(vcpu, cp15_regs, ARRAY_SIZE(cp15_regs));
@@ -1257,6 +1271,6 @@ void kvm_reset_coprocs(struct kvm_vcpu *vcpu)
 	reset_coproc_regs(vcpu, table, num);
 
 	for (num = 1; num < NR_CP15_REGS; num++)
-		if (vcpu->arch.cp15[num] == 0x42424242)
-			panic("Didn't reset vcpu->arch.cp15[%zi]", num);
+		if (vcpu_cp15(vcpu, num) == 0x42424242)
+			panic("Didn't reset vcpu_cp15(vcpu, %zi)", num);
 }
diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h
index 88d24a3a9778..eef1759c2b65 100644
--- a/arch/arm/kvm/coproc.h
+++ b/arch/arm/kvm/coproc.h
@@ -37,7 +37,7 @@ struct coproc_reg {
 	unsigned long Op1;
 	unsigned long Op2;
 
-	bool is_64;
+	bool is_64bit;
 
 	/* Trapped access from guest, if non-NULL. */
 	bool (*access)(struct kvm_vcpu *,
@@ -47,7 +47,7 @@ struct coproc_reg {
 	/* Initialization for vcpu. */
 	void (*reset)(struct kvm_vcpu *, const struct coproc_reg *);
 
-	/* Index into vcpu->arch.cp15[], or 0 if we don't need to save it. */
+	/* Index into vcpu_cp15(vcpu, ...), or 0 if we don't need to save it. */
 	unsigned long reg;
 
 	/* Value (usually reset value) */
@@ -104,25 +104,25 @@ static inline void reset_unknown(struct kvm_vcpu *vcpu,
 				 const struct coproc_reg *r)
 {
 	BUG_ON(!r->reg);
-	BUG_ON(r->reg >= ARRAY_SIZE(vcpu->arch.cp15));
-	vcpu->arch.cp15[r->reg] = 0xdecafbad;
+	BUG_ON(r->reg >= ARRAY_SIZE(vcpu->arch.ctxt.cp15));
+	vcpu_cp15(vcpu, r->reg) = 0xdecafbad;
 }
 
 static inline void reset_val(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
 {
 	BUG_ON(!r->reg);
-	BUG_ON(r->reg >= ARRAY_SIZE(vcpu->arch.cp15));
-	vcpu->arch.cp15[r->reg] = r->val;
+	BUG_ON(r->reg >= ARRAY_SIZE(vcpu->arch.ctxt.cp15));
+	vcpu_cp15(vcpu, r->reg) = r->val;
 }
 
 static inline void reset_unknown64(struct kvm_vcpu *vcpu,
 				   const struct coproc_reg *r)
 {
 	BUG_ON(!r->reg);
-	BUG_ON(r->reg + 1 >= ARRAY_SIZE(vcpu->arch.cp15));
+	BUG_ON(r->reg + 1 >= ARRAY_SIZE(vcpu->arch.ctxt.cp15));
 
-	vcpu->arch.cp15[r->reg] = 0xdecafbad;
-	vcpu->arch.cp15[r->reg+1] = 0xd0c0ffee;
+	vcpu_cp15(vcpu, r->reg) = 0xdecafbad;
+	vcpu_cp15(vcpu, r->reg+1) = 0xd0c0ffee;
 }
 
 static inline int cmp_reg(const struct coproc_reg *i1,
@@ -141,7 +141,7 @@ static inline int cmp_reg(const struct coproc_reg *i1,
 		return i1->Op1 - i2->Op1;
 	if (i1->Op2 != i2->Op2)
 		return i1->Op2 - i2->Op2;
-	return i2->is_64 - i1->is_64;
+	return i2->is_64bit - i1->is_64bit;
 }
 
 
@@ -150,8 +150,8 @@ static inline int cmp_reg(const struct coproc_reg *i1,
 #define CRm64(_x)       .CRn = _x, .CRm = 0
 #define Op1(_x) 	.Op1 = _x
 #define Op2(_x) 	.Op2 = _x
-#define is64		.is_64 = true
-#define is32		.is_64 = false
+#define is64		.is_64bit = true
+#define is32		.is_64bit = false
 
 bool access_vm_reg(struct kvm_vcpu *vcpu,
 		   const struct coproc_params *p,
diff --git a/arch/arm/kvm/emulate.c b/arch/arm/kvm/emulate.c
index dc99159857b4..a494def3f195 100644
--- a/arch/arm/kvm/emulate.c
+++ b/arch/arm/kvm/emulate.c
@@ -112,7 +112,7 @@ static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][15] = {
  */
 unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num)
 {
-	unsigned long *reg_array = (unsigned long *)&vcpu->arch.regs;
+	unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.gp_regs;
 	unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK;
 
 	switch (mode) {
@@ -147,15 +147,15 @@ unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu)
 	unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK;
 	switch (mode) {
 	case SVC_MODE:
-		return &vcpu->arch.regs.KVM_ARM_SVC_spsr;
+		return &vcpu->arch.ctxt.gp_regs.KVM_ARM_SVC_spsr;
 	case ABT_MODE:
-		return &vcpu->arch.regs.KVM_ARM_ABT_spsr;
+		return &vcpu->arch.ctxt.gp_regs.KVM_ARM_ABT_spsr;
 	case UND_MODE:
-		return &vcpu->arch.regs.KVM_ARM_UND_spsr;
+		return &vcpu->arch.ctxt.gp_regs.KVM_ARM_UND_spsr;
 	case IRQ_MODE:
-		return &vcpu->arch.regs.KVM_ARM_IRQ_spsr;
+		return &vcpu->arch.ctxt.gp_regs.KVM_ARM_IRQ_spsr;
 	case FIQ_MODE:
-		return &vcpu->arch.regs.KVM_ARM_FIQ_spsr;
+		return &vcpu->arch.ctxt.gp_regs.KVM_ARM_FIQ_spsr;
 	default:
 		BUG();
 	}
@@ -266,8 +266,8 @@ void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
 
 static u32 exc_vector_base(struct kvm_vcpu *vcpu)
 {
-	u32 sctlr = vcpu->arch.cp15[c1_SCTLR];
-	u32 vbar = vcpu->arch.cp15[c12_VBAR];
+	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
+	u32 vbar = vcpu_cp15(vcpu, c12_VBAR);
 
 	if (sctlr & SCTLR_V)
 		return 0xffff0000;
@@ -282,7 +282,7 @@ static u32 exc_vector_base(struct kvm_vcpu *vcpu)
 static void kvm_update_psr(struct kvm_vcpu *vcpu, unsigned long mode)
 {
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
-	u32 sctlr = vcpu->arch.cp15[c1_SCTLR];
+	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
 
 	*vcpu_cpsr(vcpu) = (cpsr & ~MODE_MASK) | mode;
 
@@ -357,22 +357,22 @@ static void inject_abt(struct kvm_vcpu *vcpu, bool is_pabt, unsigned long addr)
 
 	if (is_pabt) {
 		/* Set IFAR and IFSR */
-		vcpu->arch.cp15[c6_IFAR] = addr;
-		is_lpae = (vcpu->arch.cp15[c2_TTBCR] >> 31);
+		vcpu_cp15(vcpu, c6_IFAR) = addr;
+		is_lpae = (vcpu_cp15(vcpu, c2_TTBCR) >> 31);
 		/* Always give debug fault for now - should give guest a clue */
 		if (is_lpae)
-			vcpu->arch.cp15[c5_IFSR] = 1 << 9 | 0x22;
+			vcpu_cp15(vcpu, c5_IFSR) = 1 << 9 | 0x22;
 		else
-			vcpu->arch.cp15[c5_IFSR] = 2;
+			vcpu_cp15(vcpu, c5_IFSR) = 2;
 	} else { /* !iabt */
 		/* Set DFAR and DFSR */
-		vcpu->arch.cp15[c6_DFAR] = addr;
-		is_lpae = (vcpu->arch.cp15[c2_TTBCR] >> 31);
+		vcpu_cp15(vcpu, c6_DFAR) = addr;
+		is_lpae = (vcpu_cp15(vcpu, c2_TTBCR) >> 31);
 		/* Always give debug fault for now - should give guest a clue */
 		if (is_lpae)
-			vcpu->arch.cp15[c5_DFSR] = 1 << 9 | 0x22;
+			vcpu_cp15(vcpu, c5_DFSR) = 1 << 9 | 0x22;
 		else
-			vcpu->arch.cp15[c5_DFSR] = 2;
+			vcpu_cp15(vcpu, c5_DFSR) = 2;
 	}
 
 }
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 5fa69d7bae58..9093ed0f8b2a 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -25,7 +25,6 @@
 #include <asm/cputype.h>
 #include <asm/uaccess.h>
 #include <asm/kvm.h>
-#include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
 
@@ -55,7 +54,7 @@ static u64 core_reg_offset_from_id(u64 id)
 static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	u32 __user *uaddr = (u32 __user *)(long)reg->addr;
-	struct kvm_regs *regs = &vcpu->arch.regs;
+	struct kvm_regs *regs = &vcpu->arch.ctxt.gp_regs;
 	u64 off;
 
 	if (KVM_REG_SIZE(reg->id) != 4)
@@ -72,7 +71,7 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	u32 __user *uaddr = (u32 __user *)(long)reg->addr;
-	struct kvm_regs *regs = &vcpu->arch.regs;
+	struct kvm_regs *regs = &vcpu->arch.ctxt.gp_regs;
 	u64 off, val;
 
 	if (KVM_REG_SIZE(reg->id) != 4)
@@ -161,7 +160,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	u64 val;
 
 	val = kvm_arm_timer_get_reg(vcpu, reg->id);
-	return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id));
+	return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0;
 }
 
 static unsigned long num_core_regs(void)
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 3ede90d8b20b..3f1ef0dbc899 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -147,13 +147,6 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	switch (exception_index) {
 	case ARM_EXCEPTION_IRQ:
 		return 1;
-	case ARM_EXCEPTION_UNDEFINED:
-		kvm_err("Undefined exception in Hyp mode at: %#08lx\n",
-			kvm_vcpu_get_hyp_pc(vcpu));
-		BUG();
-		panic("KVM: Hypervisor undefined exception!\n");
-	case ARM_EXCEPTION_DATA_ABORT:
-	case ARM_EXCEPTION_PREF_ABORT:
 	case ARM_EXCEPTION_HVC:
 		/*
 		 * See ARM ARM B1.14.1: "Hyp traps on instructions
diff --git a/arch/arm/kvm/hyp/Makefile b/arch/arm/kvm/hyp/Makefile
new file mode 100644
index 000000000000..8dfa5f7f9290
--- /dev/null
+++ b/arch/arm/kvm/hyp/Makefile
@@ -0,0 +1,17 @@
+#
+# Makefile for Kernel-based Virtual Machine module, HYP part
+#
+
+KVM=../../../../virt/kvm
+
+obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
+obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o
+
+obj-$(CONFIG_KVM_ARM_HOST) += tlb.o
+obj-$(CONFIG_KVM_ARM_HOST) += cp15-sr.o
+obj-$(CONFIG_KVM_ARM_HOST) += vfp.o
+obj-$(CONFIG_KVM_ARM_HOST) += banked-sr.o
+obj-$(CONFIG_KVM_ARM_HOST) += entry.o
+obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o
+obj-$(CONFIG_KVM_ARM_HOST) += switch.o
+obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o
diff --git a/arch/arm/kvm/hyp/banked-sr.c b/arch/arm/kvm/hyp/banked-sr.c
new file mode 100644
index 000000000000..111bda8cdebd
--- /dev/null
+++ b/arch/arm/kvm/hyp/banked-sr.c
@@ -0,0 +1,77 @@
+/*
+ * Original code:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * Mostly rewritten in C by Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <asm/kvm_hyp.h>
+
+__asm__(".arch_extension     virt");
+
+void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt)
+{
+	ctxt->gp_regs.usr_regs.ARM_sp	= read_special(SP_usr);
+	ctxt->gp_regs.usr_regs.ARM_pc	= read_special(ELR_hyp);
+	ctxt->gp_regs.usr_regs.ARM_cpsr	= read_special(SPSR);
+	ctxt->gp_regs.KVM_ARM_SVC_sp	= read_special(SP_svc);
+	ctxt->gp_regs.KVM_ARM_SVC_lr	= read_special(LR_svc);
+	ctxt->gp_regs.KVM_ARM_SVC_spsr	= read_special(SPSR_svc);
+	ctxt->gp_regs.KVM_ARM_ABT_sp	= read_special(SP_abt);
+	ctxt->gp_regs.KVM_ARM_ABT_lr	= read_special(LR_abt);
+	ctxt->gp_regs.KVM_ARM_ABT_spsr	= read_special(SPSR_abt);
+	ctxt->gp_regs.KVM_ARM_UND_sp	= read_special(SP_und);
+	ctxt->gp_regs.KVM_ARM_UND_lr	= read_special(LR_und);
+	ctxt->gp_regs.KVM_ARM_UND_spsr	= read_special(SPSR_und);
+	ctxt->gp_regs.KVM_ARM_IRQ_sp	= read_special(SP_irq);
+	ctxt->gp_regs.KVM_ARM_IRQ_lr	= read_special(LR_irq);
+	ctxt->gp_regs.KVM_ARM_IRQ_spsr	= read_special(SPSR_irq);
+	ctxt->gp_regs.KVM_ARM_FIQ_r8	= read_special(R8_fiq);
+	ctxt->gp_regs.KVM_ARM_FIQ_r9	= read_special(R9_fiq);
+	ctxt->gp_regs.KVM_ARM_FIQ_r10	= read_special(R10_fiq);
+	ctxt->gp_regs.KVM_ARM_FIQ_fp	= read_special(R11_fiq);
+	ctxt->gp_regs.KVM_ARM_FIQ_ip	= read_special(R12_fiq);
+	ctxt->gp_regs.KVM_ARM_FIQ_sp	= read_special(SP_fiq);
+	ctxt->gp_regs.KVM_ARM_FIQ_lr	= read_special(LR_fiq);
+	ctxt->gp_regs.KVM_ARM_FIQ_spsr	= read_special(SPSR_fiq);
+}
+
+void __hyp_text __banked_restore_state(struct kvm_cpu_context *ctxt)
+{
+	write_special(ctxt->gp_regs.usr_regs.ARM_sp,	SP_usr);
+	write_special(ctxt->gp_regs.usr_regs.ARM_pc,	ELR_hyp);
+	write_special(ctxt->gp_regs.usr_regs.ARM_cpsr,	SPSR_cxsf);
+	write_special(ctxt->gp_regs.KVM_ARM_SVC_sp,	SP_svc);
+	write_special(ctxt->gp_regs.KVM_ARM_SVC_lr,	LR_svc);
+	write_special(ctxt->gp_regs.KVM_ARM_SVC_spsr,	SPSR_svc);
+	write_special(ctxt->gp_regs.KVM_ARM_ABT_sp,	SP_abt);
+	write_special(ctxt->gp_regs.KVM_ARM_ABT_lr,	LR_abt);
+	write_special(ctxt->gp_regs.KVM_ARM_ABT_spsr,	SPSR_abt);
+	write_special(ctxt->gp_regs.KVM_ARM_UND_sp,	SP_und);
+	write_special(ctxt->gp_regs.KVM_ARM_UND_lr,	LR_und);
+	write_special(ctxt->gp_regs.KVM_ARM_UND_spsr,	SPSR_und);
+	write_special(ctxt->gp_regs.KVM_ARM_IRQ_sp,	SP_irq);
+	write_special(ctxt->gp_regs.KVM_ARM_IRQ_lr,	LR_irq);
+	write_special(ctxt->gp_regs.KVM_ARM_IRQ_spsr,	SPSR_irq);
+	write_special(ctxt->gp_regs.KVM_ARM_FIQ_r8,	R8_fiq);
+	write_special(ctxt->gp_regs.KVM_ARM_FIQ_r9,	R9_fiq);
+	write_special(ctxt->gp_regs.KVM_ARM_FIQ_r10,	R10_fiq);
+	write_special(ctxt->gp_regs.KVM_ARM_FIQ_fp,	R11_fiq);
+	write_special(ctxt->gp_regs.KVM_ARM_FIQ_ip,	R12_fiq);
+	write_special(ctxt->gp_regs.KVM_ARM_FIQ_sp,	SP_fiq);
+	write_special(ctxt->gp_regs.KVM_ARM_FIQ_lr,	LR_fiq);
+	write_special(ctxt->gp_regs.KVM_ARM_FIQ_spsr,	SPSR_fiq);
+}
diff --git a/arch/arm/kvm/hyp/cp15-sr.c b/arch/arm/kvm/hyp/cp15-sr.c
new file mode 100644
index 000000000000..c4782812714c
--- /dev/null
+++ b/arch/arm/kvm/hyp/cp15-sr.c
@@ -0,0 +1,84 @@
+/*
+ * Original code:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * Mostly rewritten in C by Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <asm/kvm_hyp.h>
+
+static u64 *cp15_64(struct kvm_cpu_context *ctxt, int idx)
+{
+	return (u64 *)(ctxt->cp15 + idx);
+}
+
+void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
+{
+	ctxt->cp15[c0_MPIDR]		= read_sysreg(VMPIDR);
+	ctxt->cp15[c0_CSSELR]		= read_sysreg(CSSELR);
+	ctxt->cp15[c1_SCTLR]		= read_sysreg(SCTLR);
+	ctxt->cp15[c1_CPACR]		= read_sysreg(CPACR);
+	*cp15_64(ctxt, c2_TTBR0)	= read_sysreg(TTBR0);
+	*cp15_64(ctxt, c2_TTBR1)	= read_sysreg(TTBR1);
+	ctxt->cp15[c2_TTBCR]		= read_sysreg(TTBCR);
+	ctxt->cp15[c3_DACR]		= read_sysreg(DACR);
+	ctxt->cp15[c5_DFSR]		= read_sysreg(DFSR);
+	ctxt->cp15[c5_IFSR]		= read_sysreg(IFSR);
+	ctxt->cp15[c5_ADFSR]		= read_sysreg(ADFSR);
+	ctxt->cp15[c5_AIFSR]		= read_sysreg(AIFSR);
+	ctxt->cp15[c6_DFAR]		= read_sysreg(DFAR);
+	ctxt->cp15[c6_IFAR]		= read_sysreg(IFAR);
+	*cp15_64(ctxt, c7_PAR)		= read_sysreg(PAR);
+	ctxt->cp15[c10_PRRR]		= read_sysreg(PRRR);
+	ctxt->cp15[c10_NMRR]		= read_sysreg(NMRR);
+	ctxt->cp15[c10_AMAIR0]		= read_sysreg(AMAIR0);
+	ctxt->cp15[c10_AMAIR1]		= read_sysreg(AMAIR1);
+	ctxt->cp15[c12_VBAR]		= read_sysreg(VBAR);
+	ctxt->cp15[c13_CID]		= read_sysreg(CID);
+	ctxt->cp15[c13_TID_URW]		= read_sysreg(TID_URW);
+	ctxt->cp15[c13_TID_URO]		= read_sysreg(TID_URO);
+	ctxt->cp15[c13_TID_PRIV]	= read_sysreg(TID_PRIV);
+	ctxt->cp15[c14_CNTKCTL]		= read_sysreg(CNTKCTL);
+}
+
+void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt)
+{
+	write_sysreg(ctxt->cp15[c0_MPIDR],	VMPIDR);
+	write_sysreg(ctxt->cp15[c0_CSSELR],	CSSELR);
+	write_sysreg(ctxt->cp15[c1_SCTLR],	SCTLR);
+	write_sysreg(ctxt->cp15[c1_CPACR],	CPACR);
+	write_sysreg(*cp15_64(ctxt, c2_TTBR0),	TTBR0);
+	write_sysreg(*cp15_64(ctxt, c2_TTBR1),	TTBR1);
+	write_sysreg(ctxt->cp15[c2_TTBCR],	TTBCR);
+	write_sysreg(ctxt->cp15[c3_DACR],	DACR);
+	write_sysreg(ctxt->cp15[c5_DFSR],	DFSR);
+	write_sysreg(ctxt->cp15[c5_IFSR],	IFSR);
+	write_sysreg(ctxt->cp15[c5_ADFSR],	ADFSR);
+	write_sysreg(ctxt->cp15[c5_AIFSR],	AIFSR);
+	write_sysreg(ctxt->cp15[c6_DFAR],	DFAR);
+	write_sysreg(ctxt->cp15[c6_IFAR],	IFAR);
+	write_sysreg(*cp15_64(ctxt, c7_PAR),	PAR);
+	write_sysreg(ctxt->cp15[c10_PRRR],	PRRR);
+	write_sysreg(ctxt->cp15[c10_NMRR],	NMRR);
+	write_sysreg(ctxt->cp15[c10_AMAIR0],	AMAIR0);
+	write_sysreg(ctxt->cp15[c10_AMAIR1],	AMAIR1);
+	write_sysreg(ctxt->cp15[c12_VBAR],	VBAR);
+	write_sysreg(ctxt->cp15[c13_CID],	CID);
+	write_sysreg(ctxt->cp15[c13_TID_URW],	TID_URW);
+	write_sysreg(ctxt->cp15[c13_TID_URO],	TID_URO);
+	write_sysreg(ctxt->cp15[c13_TID_PRIV],	TID_PRIV);
+	write_sysreg(ctxt->cp15[c14_CNTKCTL],	CNTKCTL);
+}
diff --git a/arch/arm/kvm/hyp/entry.S b/arch/arm/kvm/hyp/entry.S
new file mode 100644
index 000000000000..21c238871c9e
--- /dev/null
+++ b/arch/arm/kvm/hyp/entry.S
@@ -0,0 +1,101 @@
+/*
+ * Copyright (C) 2016 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+*/
+
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/kvm_arm.h>
+
+	.arch_extension     virt
+
+	.text
+	.pushsection	.hyp.text, "ax"
+
+#define USR_REGS_OFFSET		(CPU_CTXT_GP_REGS + GP_REGS_USR)
+
+/* int __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host) */
+ENTRY(__guest_enter)
+	@ Save host registers
+	add	r1, r1, #(USR_REGS_OFFSET + S_R4)
+	stm	r1!, {r4-r12}
+	str	lr, [r1, #4]	@ Skip SP_usr (already saved)
+
+	@ Restore guest registers
+	add	r0, r0,  #(VCPU_GUEST_CTXT + USR_REGS_OFFSET + S_R0)
+	ldr	lr, [r0, #S_LR]
+	ldm	r0, {r0-r12}
+
+	clrex
+	eret
+ENDPROC(__guest_enter)
+
+ENTRY(__guest_exit)
+	/*
+	 * return convention:
+	 * guest r0, r1, r2 saved on the stack
+	 * r0: vcpu pointer
+	 * r1: exception code
+	 */
+
+	add	r2, r0, #(VCPU_GUEST_CTXT + USR_REGS_OFFSET + S_R3)
+	stm	r2!, {r3-r12}
+	str	lr, [r2, #4]
+	add	r2, r0, #(VCPU_GUEST_CTXT + USR_REGS_OFFSET + S_R0)
+	pop	{r3, r4, r5}		@ r0, r1, r2
+	stm	r2, {r3-r5}
+
+	ldr	r0, [r0, #VCPU_HOST_CTXT]
+	add	r0, r0, #(USR_REGS_OFFSET + S_R4)
+	ldm	r0!, {r4-r12}
+	ldr	lr, [r0, #4]
+
+	mov	r0, r1
+	bx	lr
+ENDPROC(__guest_exit)
+
+/*
+ * If VFPv3 support is not available, then we will not switch the VFP
+ * registers; however cp10 and cp11 accesses will still trap and fallback
+ * to the regular coprocessor emulation code, which currently will
+ * inject an undefined exception to the guest.
+ */
+#ifdef CONFIG_VFPv3
+ENTRY(__vfp_guest_restore)
+	push	{r3, r4, lr}
+
+	@ NEON/VFP used.  Turn on VFP access.
+	mrc	p15, 4, r1, c1, c1, 2		@ HCPTR
+	bic	r1, r1, #(HCPTR_TCP(10) | HCPTR_TCP(11))
+	mcr	p15, 4, r1, c1, c1, 2		@ HCPTR
+	isb
+
+	@ Switch VFP/NEON hardware state to the guest's
+	mov	r4, r0
+	ldr	r0, [r0, #VCPU_HOST_CTXT]
+	add	r0, r0, #CPU_CTXT_VFP
+	bl	__vfp_save_state
+	add	r0, r4, #(VCPU_GUEST_CTXT + CPU_CTXT_VFP)
+	bl	__vfp_restore_state
+
+	pop	{r3, r4, lr}
+	pop	{r0, r1, r2}
+	clrex
+	eret
+ENDPROC(__vfp_guest_restore)
+#endif
+
+	.popsection
+
diff --git a/arch/arm/kvm/hyp/hyp-entry.S b/arch/arm/kvm/hyp/hyp-entry.S
new file mode 100644
index 000000000000..78091383a5d9
--- /dev/null
+++ b/arch/arm/kvm/hyp/hyp-entry.S
@@ -0,0 +1,169 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#include <linux/linkage.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_asm.h>
+
+	.arch_extension     virt
+
+	.text
+	.pushsection	.hyp.text, "ax"
+
+.macro load_vcpu	reg
+	mrc	p15, 4, \reg, c13, c0, 2	@ HTPIDR
+.endm
+
+/********************************************************************
+ * Hypervisor exception vector and handlers
+ *
+ *
+ * The KVM/ARM Hypervisor ABI is defined as follows:
+ *
+ * Entry to Hyp mode from the host kernel will happen _only_ when an HVC
+ * instruction is issued since all traps are disabled when running the host
+ * kernel as per the Hyp-mode initialization at boot time.
+ *
+ * HVC instructions cause a trap to the vector page + offset 0x14 (see hyp_hvc
+ * below) when the HVC instruction is called from SVC mode (i.e. a guest or the
+ * host kernel) and they cause a trap to the vector page + offset 0x8 when HVC
+ * instructions are called from within Hyp-mode.
+ *
+ * Hyp-ABI: Calling HYP-mode functions from host (in SVC mode):
+ *    Switching to Hyp mode is done through a simple HVC #0 instruction. The
+ *    exception vector code will check that the HVC comes from VMID==0.
+ *    - r0 contains a pointer to a HYP function
+ *    - r1, r2, and r3 contain arguments to the above function.
+ *    - The HYP function will be called with its arguments in r0, r1 and r2.
+ *    On HYP function return, we return directly to SVC.
+ *
+ * Note that the above is used to execute code in Hyp-mode from a host-kernel
+ * point of view, and is a different concept from performing a world-switch and
+ * executing guest code SVC mode (with a VMID != 0).
+ */
+
+	.align 5
+__kvm_hyp_vector:
+	.global __kvm_hyp_vector
+
+	@ Hyp-mode exception vector
+	W(b)	hyp_reset
+	W(b)	hyp_undef
+	W(b)	hyp_svc
+	W(b)	hyp_pabt
+	W(b)	hyp_dabt
+	W(b)	hyp_hvc
+	W(b)	hyp_irq
+	W(b)	hyp_fiq
+
+.macro invalid_vector label, cause
+	.align
+\label:	mov	r0, #\cause
+	b	__hyp_panic
+.endm
+
+	invalid_vector	hyp_reset	ARM_EXCEPTION_RESET
+	invalid_vector	hyp_undef	ARM_EXCEPTION_UNDEFINED
+	invalid_vector	hyp_svc		ARM_EXCEPTION_SOFTWARE
+	invalid_vector	hyp_pabt	ARM_EXCEPTION_PREF_ABORT
+	invalid_vector	hyp_dabt	ARM_EXCEPTION_DATA_ABORT
+	invalid_vector	hyp_fiq		ARM_EXCEPTION_FIQ
+
+ENTRY(__hyp_do_panic)
+	mrs	lr, cpsr
+	bic	lr, lr, #MODE_MASK
+	orr	lr, lr, #SVC_MODE
+THUMB(	orr	lr, lr, #PSR_T_BIT	)
+	msr	spsr_cxsf, lr
+	ldr	lr, =panic
+	msr	ELR_hyp, lr
+	ldr	lr, =kvm_call_hyp
+	clrex
+	eret
+ENDPROC(__hyp_do_panic)
+
+hyp_hvc:
+	/*
+	 * Getting here is either because of a trap from a guest,
+	 * or from executing HVC from the host kernel, which means
+	 * "do something in Hyp mode".
+	 */
+	push	{r0, r1, r2}
+
+	@ Check syndrome register
+	mrc	p15, 4, r1, c5, c2, 0	@ HSR
+	lsr	r0, r1, #HSR_EC_SHIFT
+	cmp	r0, #HSR_EC_HVC
+	bne	guest_trap		@ Not HVC instr.
+
+	/*
+	 * Let's check if the HVC came from VMID 0 and allow simple
+	 * switch to Hyp mode
+	 */
+	mrrc    p15, 6, r0, r2, c2
+	lsr     r2, r2, #16
+	and     r2, r2, #0xff
+	cmp     r2, #0
+	bne	guest_trap		@ Guest called HVC
+
+	/*
+	 * Getting here means host called HVC, we shift parameters and branch
+	 * to Hyp function.
+	 */
+	pop	{r0, r1, r2}
+
+	/* Check for __hyp_get_vectors */
+	cmp	r0, #-1
+	mrceq	p15, 4, r0, c12, c0, 0	@ get HVBAR
+	beq	1f
+
+	push	{lr}
+
+	mov	lr, r0
+	mov	r0, r1
+	mov	r1, r2
+	mov	r2, r3
+
+THUMB(	orr	lr, #1)
+	blx	lr			@ Call the HYP function
+
+	pop	{lr}
+1:	eret
+
+guest_trap:
+	load_vcpu r0			@ Load VCPU pointer to r0
+
+#ifdef CONFIG_VFPv3
+	@ Check for a VFP access
+	lsr	r1, r1, #HSR_EC_SHIFT
+	cmp	r1, #HSR_EC_CP_0_13
+	beq	__vfp_guest_restore
+#endif
+
+	mov	r1, #ARM_EXCEPTION_HVC
+	b	__guest_exit
+
+hyp_irq:
+	push	{r0, r1, r2}
+	mov	r1, #ARM_EXCEPTION_IRQ
+	load_vcpu r0			@ Load VCPU pointer to r0
+	b	__guest_exit
+
+	.ltorg
+
+	.popsection
diff --git a/arch/arm/kvm/hyp/s2-setup.c b/arch/arm/kvm/hyp/s2-setup.c
new file mode 100644
index 000000000000..7be39af2ed6c
--- /dev/null
+++ b/arch/arm/kvm/hyp/s2-setup.c
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2016 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/types.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_hyp.h>
+
+void __hyp_text __init_stage2_translation(void)
+{
+	u64 val;
+
+	val = read_sysreg(VTCR) & ~VTCR_MASK;
+
+	val |= read_sysreg(HTCR) & VTCR_HTCR_SH;
+	val |= KVM_VTCR_SL0 | KVM_VTCR_T0SZ | KVM_VTCR_S;
+
+	write_sysreg(val, VTCR);
+}
diff --git a/arch/arm/kvm/hyp/switch.c b/arch/arm/kvm/hyp/switch.c
new file mode 100644
index 000000000000..b13caa90cd44
--- /dev/null
+++ b/arch/arm/kvm/hyp/switch.c
@@ -0,0 +1,232 @@
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <asm/kvm_asm.h>
+#include <asm/kvm_hyp.h>
+
+__asm__(".arch_extension     virt");
+
+/*
+ * Activate the traps, saving the host's fpexc register before
+ * overwriting it. We'll restore it on VM exit.
+ */
+static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu, u32 *fpexc_host)
+{
+	u32 val;
+
+	/*
+	 * We are about to set HCPTR.TCP10/11 to trap all floating point
+	 * register accesses to HYP, however, the ARM ARM clearly states that
+	 * traps are only taken to HYP if the operation would not otherwise
+	 * trap to SVC.  Therefore, always make sure that for 32-bit guests,
+	 * we set FPEXC.EN to prevent traps to SVC, when setting the TCP bits.
+	 */
+	val = read_sysreg(VFP_FPEXC);
+	*fpexc_host = val;
+	if (!(val & FPEXC_EN)) {
+		write_sysreg(val | FPEXC_EN, VFP_FPEXC);
+		isb();
+	}
+
+	write_sysreg(vcpu->arch.hcr | vcpu->arch.irq_lines, HCR);
+	/* Trap on AArch32 cp15 c15 accesses (EL1 or EL0) */
+	write_sysreg(HSTR_T(15), HSTR);
+	write_sysreg(HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11), HCPTR);
+	val = read_sysreg(HDCR);
+	write_sysreg(val | HDCR_TPM | HDCR_TPMCR, HDCR);
+}
+
+static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
+{
+	u32 val;
+
+	write_sysreg(0, HCR);
+	write_sysreg(0, HSTR);
+	val = read_sysreg(HDCR);
+	write_sysreg(val & ~(HDCR_TPM | HDCR_TPMCR), HDCR);
+	write_sysreg(0, HCPTR);
+}
+
+static void __hyp_text __activate_vm(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+	write_sysreg(kvm->arch.vttbr, VTTBR);
+	write_sysreg(vcpu->arch.midr, VPIDR);
+}
+
+static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
+{
+	write_sysreg(0, VTTBR);
+	write_sysreg(read_sysreg(MIDR), VPIDR);
+}
+
+static void __hyp_text __vgic_save_state(struct kvm_vcpu *vcpu)
+{
+	__vgic_v2_save_state(vcpu);
+}
+
+static void __hyp_text __vgic_restore_state(struct kvm_vcpu *vcpu)
+{
+	__vgic_v2_restore_state(vcpu);
+}
+
+static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
+{
+	u32 hsr = read_sysreg(HSR);
+	u8 ec = hsr >> HSR_EC_SHIFT;
+	u32 hpfar, far;
+
+	vcpu->arch.fault.hsr = hsr;
+
+	if (ec == HSR_EC_IABT)
+		far = read_sysreg(HIFAR);
+	else if (ec == HSR_EC_DABT)
+		far = read_sysreg(HDFAR);
+	else
+		return true;
+
+	/*
+	 * B3.13.5 Reporting exceptions taken to the Non-secure PL2 mode:
+	 *
+	 * Abort on the stage 2 translation for a memory access from a
+	 * Non-secure PL1 or PL0 mode:
+	 *
+	 * For any Access flag fault or Translation fault, and also for any
+	 * Permission fault on the stage 2 translation of a memory access
+	 * made as part of a translation table walk for a stage 1 translation,
+	 * the HPFAR holds the IPA that caused the fault. Otherwise, the HPFAR
+	 * is UNKNOWN.
+	 */
+	if (!(hsr & HSR_DABT_S1PTW) && (hsr & HSR_FSC_TYPE) == FSC_PERM) {
+		u64 par, tmp;
+
+		par = read_sysreg(PAR);
+		write_sysreg(far, ATS1CPR);
+		isb();
+
+		tmp = read_sysreg(PAR);
+		write_sysreg(par, PAR);
+
+		if (unlikely(tmp & 1))
+			return false; /* Translation failed, back to guest */
+
+		hpfar = ((tmp >> 12) & ((1UL << 28) - 1)) << 4;
+	} else {
+		hpfar = read_sysreg(HPFAR);
+	}
+
+	vcpu->arch.fault.hxfar = far;
+	vcpu->arch.fault.hpfar = hpfar;
+	return true;
+}
+
+static int __hyp_text __guest_run(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *host_ctxt;
+	struct kvm_cpu_context *guest_ctxt;
+	bool fp_enabled;
+	u64 exit_code;
+	u32 fpexc;
+
+	vcpu = kern_hyp_va(vcpu);
+	write_sysreg(vcpu, HTPIDR);
+
+	host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
+	guest_ctxt = &vcpu->arch.ctxt;
+
+	__sysreg_save_state(host_ctxt);
+	__banked_save_state(host_ctxt);
+
+	__activate_traps(vcpu, &fpexc);
+	__activate_vm(vcpu);
+
+	__vgic_restore_state(vcpu);
+	__timer_restore_state(vcpu);
+
+	__sysreg_restore_state(guest_ctxt);
+	__banked_restore_state(guest_ctxt);
+
+	/* Jump in the fire! */
+again:
+	exit_code = __guest_enter(vcpu, host_ctxt);
+	/* And we're baaack! */
+
+	if (exit_code == ARM_EXCEPTION_HVC && !__populate_fault_info(vcpu))
+		goto again;
+
+	fp_enabled = __vfp_enabled();
+
+	__banked_save_state(guest_ctxt);
+	__sysreg_save_state(guest_ctxt);
+	__timer_save_state(vcpu);
+	__vgic_save_state(vcpu);
+
+	__deactivate_traps(vcpu);
+	__deactivate_vm(vcpu);
+
+	__banked_restore_state(host_ctxt);
+	__sysreg_restore_state(host_ctxt);
+
+	if (fp_enabled) {
+		__vfp_save_state(&guest_ctxt->vfp);
+		__vfp_restore_state(&host_ctxt->vfp);
+	}
+
+	write_sysreg(fpexc, VFP_FPEXC);
+
+	return exit_code;
+}
+
+__alias(__guest_run) int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
+
+static const char * const __hyp_panic_string[] = {
+	[ARM_EXCEPTION_RESET]      = "\nHYP panic: RST   PC:%08x CPSR:%08x",
+	[ARM_EXCEPTION_UNDEFINED]  = "\nHYP panic: UNDEF PC:%08x CPSR:%08x",
+	[ARM_EXCEPTION_SOFTWARE]   = "\nHYP panic: SVC   PC:%08x CPSR:%08x",
+	[ARM_EXCEPTION_PREF_ABORT] = "\nHYP panic: PABRT PC:%08x CPSR:%08x",
+	[ARM_EXCEPTION_DATA_ABORT] = "\nHYP panic: DABRT PC:%08x ADDR:%08x",
+	[ARM_EXCEPTION_IRQ]        = "\nHYP panic: IRQ   PC:%08x CPSR:%08x",
+	[ARM_EXCEPTION_FIQ]        = "\nHYP panic: FIQ   PC:%08x CPSR:%08x",
+	[ARM_EXCEPTION_HVC]        = "\nHYP panic: HVC   PC:%08x CPSR:%08x",
+};
+
+void __hyp_text __noreturn __hyp_panic(int cause)
+{
+	u32 elr = read_special(ELR_hyp);
+	u32 val;
+
+	if (cause == ARM_EXCEPTION_DATA_ABORT)
+		val = read_sysreg(HDFAR);
+	else
+		val = read_special(SPSR);
+
+	if (read_sysreg(VTTBR)) {
+		struct kvm_vcpu *vcpu;
+		struct kvm_cpu_context *host_ctxt;
+
+		vcpu = (struct kvm_vcpu *)read_sysreg(HTPIDR);
+		host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
+		__deactivate_traps(vcpu);
+		__deactivate_vm(vcpu);
+		__sysreg_restore_state(host_ctxt);
+	}
+
+	/* Call panic for real */
+	__hyp_do_panic(__hyp_panic_string[cause], elr, val);
+
+	unreachable();
+}
diff --git a/arch/arm/kvm/hyp/tlb.c b/arch/arm/kvm/hyp/tlb.c
new file mode 100644
index 000000000000..a2636001e616
--- /dev/null
+++ b/arch/arm/kvm/hyp/tlb.c
@@ -0,0 +1,70 @@
+/*
+ * Original code:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * Mostly rewritten in C by Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <asm/kvm_hyp.h>
+
+/**
+ * Flush per-VMID TLBs
+ *
+ * __kvm_tlb_flush_vmid(struct kvm *kvm);
+ *
+ * We rely on the hardware to broadcast the TLB invalidation to all CPUs
+ * inside the inner-shareable domain (which is the case for all v7
+ * implementations).  If we come across a non-IS SMP implementation, we'll
+ * have to use an IPI based mechanism. Until then, we stick to the simple
+ * hardware assisted version.
+ *
+ * As v7 does not support flushing per IPA, just nuke the whole TLB
+ * instead, ignoring the ipa value.
+ */
+static void __hyp_text __tlb_flush_vmid(struct kvm *kvm)
+{
+	dsb(ishst);
+
+	/* Switch to requested VMID */
+	kvm = kern_hyp_va(kvm);
+	write_sysreg(kvm->arch.vttbr, VTTBR);
+	isb();
+
+	write_sysreg(0, TLBIALLIS);
+	dsb(ish);
+	isb();
+
+	write_sysreg(0, VTTBR);
+}
+
+__alias(__tlb_flush_vmid) void __kvm_tlb_flush_vmid(struct kvm *kvm);
+
+static void __hyp_text __tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+{
+	__tlb_flush_vmid(kvm);
+}
+
+__alias(__tlb_flush_vmid_ipa) void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm,
+							    phys_addr_t ipa);
+
+static void __hyp_text __tlb_flush_vm_context(void)
+{
+	write_sysreg(0, TLBIALLNSNHIS);
+	write_sysreg(0, ICIALLUIS);
+	dsb(ish);
+}
+
+__alias(__tlb_flush_vm_context) void __kvm_flush_vm_context(void);
diff --git a/arch/arm/kvm/hyp/vfp.S b/arch/arm/kvm/hyp/vfp.S
new file mode 100644
index 000000000000..7c297e87eb8b
--- /dev/null
+++ b/arch/arm/kvm/hyp/vfp.S
@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+#include <asm/vfpmacros.h>
+
+	.text
+	.pushsection	.hyp.text, "ax"
+
+/* void __vfp_save_state(struct vfp_hard_struct *vfp); */
+ENTRY(__vfp_save_state)
+	push	{r4, r5}
+	VFPFMRX	r1, FPEXC
+
+	@ Make sure *really* VFP is enabled so we can touch the registers.
+	orr	r5, r1, #FPEXC_EN
+	tst	r5, #FPEXC_EX		@ Check for VFP Subarchitecture
+	bic	r5, r5, #FPEXC_EX	@ FPEXC_EX disable
+	VFPFMXR	FPEXC, r5
+	isb
+
+	VFPFMRX	r2, FPSCR
+	beq	1f
+
+	@ If FPEXC_EX is 0, then FPINST/FPINST2 reads are upredictable, so
+	@ we only need to save them if FPEXC_EX is set.
+	VFPFMRX r3, FPINST
+	tst	r5, #FPEXC_FP2V
+	VFPFMRX r4, FPINST2, ne		@ vmrsne
+1:
+	VFPFSTMIA r0, r5		@ Save VFP registers
+	stm	r0, {r1-r4}		@ Save FPEXC, FPSCR, FPINST, FPINST2
+	pop	{r4, r5}
+	bx	lr
+ENDPROC(__vfp_save_state)
+
+/* void __vfp_restore_state(struct vfp_hard_struct *vfp);
+ * Assume FPEXC_EN is on and FPEXC_EX is off */
+ENTRY(__vfp_restore_state)
+	VFPFLDMIA r0, r1		@ Load VFP registers
+	ldm	r0, {r0-r3}		@ Load FPEXC, FPSCR, FPINST, FPINST2
+
+	VFPFMXR FPSCR, r1
+	tst	r0, #FPEXC_EX		@ Check for VFP Subarchitecture
+	beq	1f
+	VFPFMXR FPINST, r2
+	tst	r0, #FPEXC_FP2V
+	VFPFMXR FPINST2, r3, ne
+1:
+	VFPFMXR FPEXC, r0		@ FPEXC	(last, in case !EN)
+	bx	lr
+ENDPROC(__vfp_restore_state)
+
+	.popsection
diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S
index 3988e72d16ff..1f9ae17476f9 100644
--- a/arch/arm/kvm/init.S
+++ b/arch/arm/kvm/init.S
@@ -84,14 +84,6 @@ __do_hyp_init:
 	orr	r0, r0, r1
 	mcr	p15, 4, r0, c2, c0, 2	@ HTCR
 
-	mrc	p15, 4, r1, c2, c1, 2	@ VTCR
-	ldr	r2, =VTCR_MASK
-	bic	r1, r1, r2
-	bic	r0, r0, #(~VTCR_HTCR_SH)	@ clear non-reusable HTCR bits
-	orr	r1, r0, r1
-	orr	r1, r1, #(KVM_VTCR_SL0 | KVM_VTCR_T0SZ | KVM_VTCR_S)
-	mcr	p15, 4, r1, c2, c1, 2	@ VTCR
-
 	@ Use the same memory attributes for hyp. accesses as the kernel
 	@ (copy MAIRx ro HMAIRx).
 	mrc	p15, 0, r0, c10, c2, 0
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index 900ef6dd8f72..b1bd316f14c0 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -17,211 +17,14 @@
  */
 
 #include <linux/linkage.h>
-#include <linux/const.h>
-#include <asm/unified.h>
-#include <asm/page.h>
-#include <asm/ptrace.h>
-#include <asm/asm-offsets.h>
-#include <asm/kvm_asm.h>
-#include <asm/kvm_arm.h>
-#include <asm/vfpmacros.h>
-#include "interrupts_head.S"
 
 	.text
 
-__kvm_hyp_code_start:
-	.globl __kvm_hyp_code_start
-
-/********************************************************************
- * Flush per-VMID TLBs
- *
- * void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
- *
- * We rely on the hardware to broadcast the TLB invalidation to all CPUs
- * inside the inner-shareable domain (which is the case for all v7
- * implementations).  If we come across a non-IS SMP implementation, we'll
- * have to use an IPI based mechanism. Until then, we stick to the simple
- * hardware assisted version.
- *
- * As v7 does not support flushing per IPA, just nuke the whole TLB
- * instead, ignoring the ipa value.
- */
-ENTRY(__kvm_tlb_flush_vmid_ipa)
-	push	{r2, r3}
-
-	dsb	ishst
-	add	r0, r0, #KVM_VTTBR
-	ldrd	r2, r3, [r0]
-	mcrr	p15, 6, rr_lo_hi(r2, r3), c2	@ Write VTTBR
-	isb
-	mcr     p15, 0, r0, c8, c3, 0	@ TLBIALLIS (rt ignored)
-	dsb	ish
-	isb
-	mov	r2, #0
-	mov	r3, #0
-	mcrr	p15, 6, r2, r3, c2	@ Back to VMID #0
-	isb				@ Not necessary if followed by eret
-
-	pop	{r2, r3}
-	bx	lr
-ENDPROC(__kvm_tlb_flush_vmid_ipa)
-
-/**
- * void __kvm_tlb_flush_vmid(struct kvm *kvm) - Flush per-VMID TLBs
- *
- * Reuses __kvm_tlb_flush_vmid_ipa() for ARMv7, without passing address
- * parameter
- */
-
-ENTRY(__kvm_tlb_flush_vmid)
-	b	__kvm_tlb_flush_vmid_ipa
-ENDPROC(__kvm_tlb_flush_vmid)
-
-/********************************************************************
- * Flush TLBs and instruction caches of all CPUs inside the inner-shareable
- * domain, for all VMIDs
- *
- * void __kvm_flush_vm_context(void);
- */
-ENTRY(__kvm_flush_vm_context)
-	mov	r0, #0			@ rn parameter for c15 flushes is SBZ
-
-	/* Invalidate NS Non-Hyp TLB Inner Shareable (TLBIALLNSNHIS) */
-	mcr     p15, 4, r0, c8, c3, 4
-	/* Invalidate instruction caches Inner Shareable (ICIALLUIS) */
-	mcr     p15, 0, r0, c7, c1, 0
-	dsb	ish
-	isb				@ Not necessary if followed by eret
-
-	bx	lr
-ENDPROC(__kvm_flush_vm_context)
-
-
-/********************************************************************
- *  Hypervisor world-switch code
- *
- *
- * int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
- */
-ENTRY(__kvm_vcpu_run)
-	@ Save the vcpu pointer
-	mcr	p15, 4, vcpu, c13, c0, 2	@ HTPIDR
-
-	save_host_regs
-
-	restore_vgic_state
-	restore_timer_state
-
-	@ Store hardware CP15 state and load guest state
-	read_cp15_state store_to_vcpu = 0
-	write_cp15_state read_from_vcpu = 1
-
-	@ If the host kernel has not been configured with VFPv3 support,
-	@ then it is safer if we deny guests from using it as well.
-#ifdef CONFIG_VFPv3
-	@ Set FPEXC_EN so the guest doesn't trap floating point instructions
-	VFPFMRX r2, FPEXC		@ VMRS
-	push	{r2}
-	orr	r2, r2, #FPEXC_EN
-	VFPFMXR FPEXC, r2		@ VMSR
-#endif
-
-	@ Configure Hyp-role
-	configure_hyp_role vmentry
-
-	@ Trap coprocessor CRx accesses
-	set_hstr vmentry
-	set_hcptr vmentry, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11))
-	set_hdcr vmentry
-
-	@ Write configured ID register into MIDR alias
-	ldr	r1, [vcpu, #VCPU_MIDR]
-	mcr	p15, 4, r1, c0, c0, 0
-
-	@ Write guest view of MPIDR into VMPIDR
-	ldr	r1, [vcpu, #CP15_OFFSET(c0_MPIDR)]
-	mcr	p15, 4, r1, c0, c0, 5
-
-	@ Set up guest memory translation
-	ldr	r1, [vcpu, #VCPU_KVM]
-	add	r1, r1, #KVM_VTTBR
-	ldrd	r2, r3, [r1]
-	mcrr	p15, 6, rr_lo_hi(r2, r3), c2	@ Write VTTBR
-
-	@ We're all done, just restore the GPRs and go to the guest
-	restore_guest_regs
-	clrex				@ Clear exclusive monitor
-	eret
-
-__kvm_vcpu_return:
-	/*
-	 * return convention:
-	 * guest r0, r1, r2 saved on the stack
-	 * r0: vcpu pointer
-	 * r1: exception code
-	 */
-	save_guest_regs
-
-	@ Set VMID == 0
-	mov	r2, #0
-	mov	r3, #0
-	mcrr	p15, 6, r2, r3, c2	@ Write VTTBR
-
-	@ Don't trap coprocessor accesses for host kernel
-	set_hstr vmexit
-	set_hdcr vmexit
-	set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)), after_vfp_restore
-
-#ifdef CONFIG_VFPv3
-	@ Switch VFP/NEON hardware state to the host's
-	add	r7, vcpu, #VCPU_VFP_GUEST
-	store_vfp_state r7
-	add	r7, vcpu, #VCPU_VFP_HOST
-	ldr	r7, [r7]
-	restore_vfp_state r7
-
-after_vfp_restore:
-	@ Restore FPEXC_EN which we clobbered on entry
-	pop	{r2}
-	VFPFMXR FPEXC, r2
-#else
-after_vfp_restore:
-#endif
-
-	@ Reset Hyp-role
-	configure_hyp_role vmexit
-
-	@ Let host read hardware MIDR
-	mrc	p15, 0, r2, c0, c0, 0
-	mcr	p15, 4, r2, c0, c0, 0
-
-	@ Back to hardware MPIDR
-	mrc	p15, 0, r2, c0, c0, 5
-	mcr	p15, 4, r2, c0, c0, 5
-
-	@ Store guest CP15 state and restore host state
-	read_cp15_state store_to_vcpu = 1
-	write_cp15_state read_from_vcpu = 0
-
-	save_timer_state
-	save_vgic_state
-
-	restore_host_regs
-	clrex				@ Clear exclusive monitor
-#ifndef CONFIG_CPU_ENDIAN_BE8
-	mov	r0, r1			@ Return the return code
-	mov	r1, #0			@ Clear upper bits in return value
-#else
-	@ r1 already has return code
-	mov	r0, #0			@ Clear upper bits in return value
-#endif /* CONFIG_CPU_ENDIAN_BE8 */
-	bx	lr			@ return to IOCTL
-
 /********************************************************************
  *  Call function in Hyp mode
  *
  *
- * u64 kvm_call_hyp(void *hypfn, ...);
+ * unsigned long kvm_call_hyp(void *hypfn, ...);
  *
  * This is not really a variadic function in the classic C-way and care must
  * be taken when calling this to ensure parameters are passed in registers
@@ -232,7 +35,7 @@ after_vfp_restore:
  * passed as r0, r1, and r2 (a maximum of 3 arguments in addition to the
  * function pointer can be passed).  The function being called must be mapped
  * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
- * passed in r0 and r1.
+ * passed in r0 (strictly 32bit).
  *
  * A function pointer with a value of 0xffffffff has a special meaning,
  * and is used to implement __hyp_get_vectors in the same way as in
@@ -246,281 +49,4 @@ after_vfp_restore:
 ENTRY(kvm_call_hyp)
 	hvc	#0
 	bx	lr
-
-/********************************************************************
- * Hypervisor exception vector and handlers
- *
- *
- * The KVM/ARM Hypervisor ABI is defined as follows:
- *
- * Entry to Hyp mode from the host kernel will happen _only_ when an HVC
- * instruction is issued since all traps are disabled when running the host
- * kernel as per the Hyp-mode initialization at boot time.
- *
- * HVC instructions cause a trap to the vector page + offset 0x14 (see hyp_hvc
- * below) when the HVC instruction is called from SVC mode (i.e. a guest or the
- * host kernel) and they cause a trap to the vector page + offset 0x8 when HVC
- * instructions are called from within Hyp-mode.
- *
- * Hyp-ABI: Calling HYP-mode functions from host (in SVC mode):
- *    Switching to Hyp mode is done through a simple HVC #0 instruction. The
- *    exception vector code will check that the HVC comes from VMID==0 and if
- *    so will push the necessary state (SPSR, lr_usr) on the Hyp stack.
- *    - r0 contains a pointer to a HYP function
- *    - r1, r2, and r3 contain arguments to the above function.
- *    - The HYP function will be called with its arguments in r0, r1 and r2.
- *    On HYP function return, we return directly to SVC.
- *
- * Note that the above is used to execute code in Hyp-mode from a host-kernel
- * point of view, and is a different concept from performing a world-switch and
- * executing guest code SVC mode (with a VMID != 0).
- */
-
-/* Handle undef, svc, pabt, or dabt by crashing with a user notice */
-.macro bad_exception exception_code, panic_str
-	push	{r0-r2}
-	mrrc	p15, 6, r0, r1, c2	@ Read VTTBR
-	lsr	r1, r1, #16
-	ands	r1, r1, #0xff
-	beq	99f
-
-	load_vcpu			@ Load VCPU pointer
-	.if \exception_code == ARM_EXCEPTION_DATA_ABORT
-	mrc	p15, 4, r2, c5, c2, 0	@ HSR
-	mrc	p15, 4, r1, c6, c0, 0	@ HDFAR
-	str	r2, [vcpu, #VCPU_HSR]
-	str	r1, [vcpu, #VCPU_HxFAR]
-	.endif
-	.if \exception_code == ARM_EXCEPTION_PREF_ABORT
-	mrc	p15, 4, r2, c5, c2, 0	@ HSR
-	mrc	p15, 4, r1, c6, c0, 2	@ HIFAR
-	str	r2, [vcpu, #VCPU_HSR]
-	str	r1, [vcpu, #VCPU_HxFAR]
-	.endif
-	mov	r1, #\exception_code
-	b	__kvm_vcpu_return
-
-	@ We were in the host already. Let's craft a panic-ing return to SVC.
-99:	mrs	r2, cpsr
-	bic	r2, r2, #MODE_MASK
-	orr	r2, r2, #SVC_MODE
-THUMB(	orr	r2, r2, #PSR_T_BIT	)
-	msr	spsr_cxsf, r2
-	mrs	r1, ELR_hyp
-	ldr	r2, =panic
-	msr	ELR_hyp, r2
-	ldr	r0, =\panic_str
-	clrex				@ Clear exclusive monitor
-	eret
-.endm
-
-	.text
-
-	.align 5
-__kvm_hyp_vector:
-	.globl __kvm_hyp_vector
-
-	@ Hyp-mode exception vector
-	W(b)	hyp_reset
-	W(b)	hyp_undef
-	W(b)	hyp_svc
-	W(b)	hyp_pabt
-	W(b)	hyp_dabt
-	W(b)	hyp_hvc
-	W(b)	hyp_irq
-	W(b)	hyp_fiq
-
-	.align
-hyp_reset:
-	b	hyp_reset
-
-	.align
-hyp_undef:
-	bad_exception ARM_EXCEPTION_UNDEFINED, und_die_str
-
-	.align
-hyp_svc:
-	bad_exception ARM_EXCEPTION_HVC, svc_die_str
-
-	.align
-hyp_pabt:
-	bad_exception ARM_EXCEPTION_PREF_ABORT, pabt_die_str
-
-	.align
-hyp_dabt:
-	bad_exception ARM_EXCEPTION_DATA_ABORT, dabt_die_str
-
-	.align
-hyp_hvc:
-	/*
-	 * Getting here is either becuase of a trap from a guest or from calling
-	 * HVC from the host kernel, which means "switch to Hyp mode".
-	 */
-	push	{r0, r1, r2}
-
-	@ Check syndrome register
-	mrc	p15, 4, r1, c5, c2, 0	@ HSR
-	lsr	r0, r1, #HSR_EC_SHIFT
-	cmp	r0, #HSR_EC_HVC
-	bne	guest_trap		@ Not HVC instr.
-
-	/*
-	 * Let's check if the HVC came from VMID 0 and allow simple
-	 * switch to Hyp mode
-	 */
-	mrrc    p15, 6, r0, r2, c2
-	lsr     r2, r2, #16
-	and     r2, r2, #0xff
-	cmp     r2, #0
-	bne	guest_trap		@ Guest called HVC
-
-	/*
-	 * Getting here means host called HVC, we shift parameters and branch
-	 * to Hyp function.
-	 */
-	pop	{r0, r1, r2}
-
-	/* Check for __hyp_get_vectors */
-	cmp	r0, #-1
-	mrceq	p15, 4, r0, c12, c0, 0	@ get HVBAR
-	beq	1f
-
-	push	{lr}
-	mrs	lr, SPSR
-	push	{lr}
-
-	mov	lr, r0
-	mov	r0, r1
-	mov	r1, r2
-	mov	r2, r3
-
-THUMB(	orr	lr, #1)
-	blx	lr			@ Call the HYP function
-
-	pop	{lr}
-	msr	SPSR_csxf, lr
-	pop	{lr}
-1:	eret
-
-guest_trap:
-	load_vcpu			@ Load VCPU pointer to r0
-	str	r1, [vcpu, #VCPU_HSR]
-
-	@ Check if we need the fault information
-	lsr	r1, r1, #HSR_EC_SHIFT
-#ifdef CONFIG_VFPv3
-	cmp	r1, #HSR_EC_CP_0_13
-	beq	switch_to_guest_vfp
-#endif
-	cmp	r1, #HSR_EC_IABT
-	mrceq	p15, 4, r2, c6, c0, 2	@ HIFAR
-	beq	2f
-	cmp	r1, #HSR_EC_DABT
-	bne	1f
-	mrc	p15, 4, r2, c6, c0, 0	@ HDFAR
-
-2:	str	r2, [vcpu, #VCPU_HxFAR]
-
-	/*
-	 * B3.13.5 Reporting exceptions taken to the Non-secure PL2 mode:
-	 *
-	 * Abort on the stage 2 translation for a memory access from a
-	 * Non-secure PL1 or PL0 mode:
-	 *
-	 * For any Access flag fault or Translation fault, and also for any
-	 * Permission fault on the stage 2 translation of a memory access
-	 * made as part of a translation table walk for a stage 1 translation,
-	 * the HPFAR holds the IPA that caused the fault. Otherwise, the HPFAR
-	 * is UNKNOWN.
-	 */
-
-	/* Check for permission fault, and S1PTW */
-	mrc	p15, 4, r1, c5, c2, 0	@ HSR
-	and	r0, r1, #HSR_FSC_TYPE
-	cmp	r0, #FSC_PERM
-	tsteq	r1, #(1 << 7)		@ S1PTW
-	mrcne	p15, 4, r2, c6, c0, 4	@ HPFAR
-	bne	3f
-
-	/* Preserve PAR */
-	mrrc	p15, 0, r0, r1, c7	@ PAR
-	push	{r0, r1}
-
-	/* Resolve IPA using the xFAR */
-	mcr	p15, 0, r2, c7, c8, 0	@ ATS1CPR
-	isb
-	mrrc	p15, 0, r0, r1, c7	@ PAR
-	tst	r0, #1
-	bne	4f			@ Failed translation
-	ubfx	r2, r0, #12, #20
-	lsl	r2, r2, #4
-	orr	r2, r2, r1, lsl #24
-
-	/* Restore PAR */
-	pop	{r0, r1}
-	mcrr	p15, 0, r0, r1, c7	@ PAR
-
-3:	load_vcpu			@ Load VCPU pointer to r0
-	str	r2, [r0, #VCPU_HPFAR]
-
-1:	mov	r1, #ARM_EXCEPTION_HVC
-	b	__kvm_vcpu_return
-
-4:	pop	{r0, r1}		@ Failed translation, return to guest
-	mcrr	p15, 0, r0, r1, c7	@ PAR
-	clrex
-	pop	{r0, r1, r2}
-	eret
-
-/*
- * If VFPv3 support is not available, then we will not switch the VFP
- * registers; however cp10 and cp11 accesses will still trap and fallback
- * to the regular coprocessor emulation code, which currently will
- * inject an undefined exception to the guest.
- */
-#ifdef CONFIG_VFPv3
-switch_to_guest_vfp:
-	push	{r3-r7}
-
-	@ NEON/VFP used.  Turn on VFP access.
-	set_hcptr vmtrap, (HCPTR_TCP(10) | HCPTR_TCP(11))
-
-	@ Switch VFP/NEON hardware state to the guest's
-	add	r7, r0, #VCPU_VFP_HOST
-	ldr	r7, [r7]
-	store_vfp_state r7
-	add	r7, r0, #VCPU_VFP_GUEST
-	restore_vfp_state r7
-
-	pop	{r3-r7}
-	pop	{r0-r2}
-	clrex
-	eret
-#endif
-
-	.align
-hyp_irq:
-	push	{r0, r1, r2}
-	mov	r1, #ARM_EXCEPTION_IRQ
-	load_vcpu			@ Load VCPU pointer to r0
-	b	__kvm_vcpu_return
-
-	.align
-hyp_fiq:
-	b	hyp_fiq
-
-	.ltorg
-
-__kvm_hyp_code_end:
-	.globl	__kvm_hyp_code_end
-
-	.section ".rodata"
-
-und_die_str:
-	.ascii	"unexpected undefined exception in Hyp mode at: %#08x\n"
-pabt_die_str:
-	.ascii	"unexpected prefetch abort in Hyp mode at: %#08x\n"
-dabt_die_str:
-	.ascii	"unexpected data abort in Hyp mode at: %#08x\n"
-svc_die_str:
-	.ascii	"unexpected HVC/SVC trap in Hyp mode at: %#08x\n"
+ENDPROC(kvm_call_hyp)
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
deleted file mode 100644
index 51a59504bef4..000000000000
--- a/arch/arm/kvm/interrupts_head.S
+++ /dev/null
@@ -1,648 +0,0 @@
-#include <linux/irqchip/arm-gic.h>
-#include <asm/assembler.h>
-
-#define VCPU_USR_REG(_reg_nr)	(VCPU_USR_REGS + (_reg_nr * 4))
-#define VCPU_USR_SP		(VCPU_USR_REG(13))
-#define VCPU_USR_LR		(VCPU_USR_REG(14))
-#define CP15_OFFSET(_cp15_reg_idx) (VCPU_CP15 + (_cp15_reg_idx * 4))
-
-/*
- * Many of these macros need to access the VCPU structure, which is always
- * held in r0. These macros should never clobber r1, as it is used to hold the
- * exception code on the return path (except of course the macro that switches
- * all the registers before the final jump to the VM).
- */
-vcpu	.req	r0		@ vcpu pointer always in r0
-
-/* Clobbers {r2-r6} */
-.macro store_vfp_state vfp_base
-	@ The VFPFMRX and VFPFMXR macros are the VMRS and VMSR instructions
-	VFPFMRX	r2, FPEXC
-	@ Make sure VFP is enabled so we can touch the registers.
-	orr	r6, r2, #FPEXC_EN
-	VFPFMXR	FPEXC, r6
-
-	VFPFMRX	r3, FPSCR
-	tst	r2, #FPEXC_EX		@ Check for VFP Subarchitecture
-	beq	1f
-	@ If FPEXC_EX is 0, then FPINST/FPINST2 reads are upredictable, so
-	@ we only need to save them if FPEXC_EX is set.
-	VFPFMRX r4, FPINST
-	tst	r2, #FPEXC_FP2V
-	VFPFMRX r5, FPINST2, ne		@ vmrsne
-	bic	r6, r2, #FPEXC_EX	@ FPEXC_EX disable
-	VFPFMXR	FPEXC, r6
-1:
-	VFPFSTMIA \vfp_base, r6		@ Save VFP registers
-	stm	\vfp_base, {r2-r5}	@ Save FPEXC, FPSCR, FPINST, FPINST2
-.endm
-
-/* Assume FPEXC_EN is on and FPEXC_EX is off, clobbers {r2-r6} */
-.macro restore_vfp_state vfp_base
-	VFPFLDMIA \vfp_base, r6		@ Load VFP registers
-	ldm	\vfp_base, {r2-r5}	@ Load FPEXC, FPSCR, FPINST, FPINST2
-
-	VFPFMXR FPSCR, r3
-	tst	r2, #FPEXC_EX		@ Check for VFP Subarchitecture
-	beq	1f
-	VFPFMXR FPINST, r4
-	tst	r2, #FPEXC_FP2V
-	VFPFMXR FPINST2, r5, ne
-1:
-	VFPFMXR FPEXC, r2	@ FPEXC	(last, in case !EN)
-.endm
-
-/* These are simply for the macros to work - value don't have meaning */
-.equ usr, 0
-.equ svc, 1
-.equ abt, 2
-.equ und, 3
-.equ irq, 4
-.equ fiq, 5
-
-.macro push_host_regs_mode mode
-	mrs	r2, SP_\mode
-	mrs	r3, LR_\mode
-	mrs	r4, SPSR_\mode
-	push	{r2, r3, r4}
-.endm
-
-/*
- * Store all host persistent registers on the stack.
- * Clobbers all registers, in all modes, except r0 and r1.
- */
-.macro save_host_regs
-	/* Hyp regs. Only ELR_hyp (SPSR_hyp already saved) */
-	mrs	r2, ELR_hyp
-	push	{r2}
-
-	/* usr regs */
-	push	{r4-r12}	@ r0-r3 are always clobbered
-	mrs	r2, SP_usr
-	mov	r3, lr
-	push	{r2, r3}
-
-	push_host_regs_mode svc
-	push_host_regs_mode abt
-	push_host_regs_mode und
-	push_host_regs_mode irq
-
-	/* fiq regs */
-	mrs	r2, r8_fiq
-	mrs	r3, r9_fiq
-	mrs	r4, r10_fiq
-	mrs	r5, r11_fiq
-	mrs	r6, r12_fiq
-	mrs	r7, SP_fiq
-	mrs	r8, LR_fiq
-	mrs	r9, SPSR_fiq
-	push	{r2-r9}
-.endm
-
-.macro pop_host_regs_mode mode
-	pop	{r2, r3, r4}
-	msr	SP_\mode, r2
-	msr	LR_\mode, r3
-	msr	SPSR_\mode, r4
-.endm
-
-/*
- * Restore all host registers from the stack.
- * Clobbers all registers, in all modes, except r0 and r1.
- */
-.macro restore_host_regs
-	pop	{r2-r9}
-	msr	r8_fiq, r2
-	msr	r9_fiq, r3
-	msr	r10_fiq, r4
-	msr	r11_fiq, r5
-	msr	r12_fiq, r6
-	msr	SP_fiq, r7
-	msr	LR_fiq, r8
-	msr	SPSR_fiq, r9
-
-	pop_host_regs_mode irq
-	pop_host_regs_mode und
-	pop_host_regs_mode abt
-	pop_host_regs_mode svc
-
-	pop	{r2, r3}
-	msr	SP_usr, r2
-	mov	lr, r3
-	pop	{r4-r12}
-
-	pop	{r2}
-	msr	ELR_hyp, r2
-.endm
-
-/*
- * Restore SP, LR and SPSR for a given mode. offset is the offset of
- * this mode's registers from the VCPU base.
- *
- * Assumes vcpu pointer in vcpu reg
- *
- * Clobbers r1, r2, r3, r4.
- */
-.macro restore_guest_regs_mode mode, offset
-	add	r1, vcpu, \offset
-	ldm	r1, {r2, r3, r4}
-	msr	SP_\mode, r2
-	msr	LR_\mode, r3
-	msr	SPSR_\mode, r4
-.endm
-
-/*
- * Restore all guest registers from the vcpu struct.
- *
- * Assumes vcpu pointer in vcpu reg
- *
- * Clobbers *all* registers.
- */
-.macro restore_guest_regs
-	restore_guest_regs_mode svc, #VCPU_SVC_REGS
-	restore_guest_regs_mode abt, #VCPU_ABT_REGS
-	restore_guest_regs_mode und, #VCPU_UND_REGS
-	restore_guest_regs_mode irq, #VCPU_IRQ_REGS
-
-	add	r1, vcpu, #VCPU_FIQ_REGS
-	ldm	r1, {r2-r9}
-	msr	r8_fiq, r2
-	msr	r9_fiq, r3
-	msr	r10_fiq, r4
-	msr	r11_fiq, r5
-	msr	r12_fiq, r6
-	msr	SP_fiq, r7
-	msr	LR_fiq, r8
-	msr	SPSR_fiq, r9
-
-	@ Load return state
-	ldr	r2, [vcpu, #VCPU_PC]
-	ldr	r3, [vcpu, #VCPU_CPSR]
-	msr	ELR_hyp, r2
-	msr	SPSR_cxsf, r3
-
-	@ Load user registers
-	ldr	r2, [vcpu, #VCPU_USR_SP]
-	ldr	r3, [vcpu, #VCPU_USR_LR]
-	msr	SP_usr, r2
-	mov	lr, r3
-	add	vcpu, vcpu, #(VCPU_USR_REGS)
-	ldm	vcpu, {r0-r12}
-.endm
-
-/*
- * Save SP, LR and SPSR for a given mode. offset is the offset of
- * this mode's registers from the VCPU base.
- *
- * Assumes vcpu pointer in vcpu reg
- *
- * Clobbers r2, r3, r4, r5.
- */
-.macro save_guest_regs_mode mode, offset
-	add	r2, vcpu, \offset
-	mrs	r3, SP_\mode
-	mrs	r4, LR_\mode
-	mrs	r5, SPSR_\mode
-	stm	r2, {r3, r4, r5}
-.endm
-
-/*
- * Save all guest registers to the vcpu struct
- * Expects guest's r0, r1, r2 on the stack.
- *
- * Assumes vcpu pointer in vcpu reg
- *
- * Clobbers r2, r3, r4, r5.
- */
-.macro save_guest_regs
-	@ Store usr registers
-	add	r2, vcpu, #VCPU_USR_REG(3)
-	stm	r2, {r3-r12}
-	add	r2, vcpu, #VCPU_USR_REG(0)
-	pop	{r3, r4, r5}		@ r0, r1, r2
-	stm	r2, {r3, r4, r5}
-	mrs	r2, SP_usr
-	mov	r3, lr
-	str	r2, [vcpu, #VCPU_USR_SP]
-	str	r3, [vcpu, #VCPU_USR_LR]
-
-	@ Store return state
-	mrs	r2, ELR_hyp
-	mrs	r3, spsr
-	str	r2, [vcpu, #VCPU_PC]
-	str	r3, [vcpu, #VCPU_CPSR]
-
-	@ Store other guest registers
-	save_guest_regs_mode svc, #VCPU_SVC_REGS
-	save_guest_regs_mode abt, #VCPU_ABT_REGS
-	save_guest_regs_mode und, #VCPU_UND_REGS
-	save_guest_regs_mode irq, #VCPU_IRQ_REGS
-.endm
-
-/* Reads cp15 registers from hardware and stores them in memory
- * @store_to_vcpu: If 0, registers are written in-order to the stack,
- * 		   otherwise to the VCPU struct pointed to by vcpup
- *
- * Assumes vcpu pointer in vcpu reg
- *
- * Clobbers r2 - r12
- */
-.macro read_cp15_state store_to_vcpu
-	mrc	p15, 0, r2, c1, c0, 0	@ SCTLR
-	mrc	p15, 0, r3, c1, c0, 2	@ CPACR
-	mrc	p15, 0, r4, c2, c0, 2	@ TTBCR
-	mrc	p15, 0, r5, c3, c0, 0	@ DACR
-	mrrc	p15, 0, r6, r7, c2	@ TTBR 0
-	mrrc	p15, 1, r8, r9, c2	@ TTBR 1
-	mrc	p15, 0, r10, c10, c2, 0	@ PRRR
-	mrc	p15, 0, r11, c10, c2, 1	@ NMRR
-	mrc	p15, 2, r12, c0, c0, 0	@ CSSELR
-
-	.if \store_to_vcpu == 0
-	push	{r2-r12}		@ Push CP15 registers
-	.else
-	str	r2, [vcpu, #CP15_OFFSET(c1_SCTLR)]
-	str	r3, [vcpu, #CP15_OFFSET(c1_CPACR)]
-	str	r4, [vcpu, #CP15_OFFSET(c2_TTBCR)]
-	str	r5, [vcpu, #CP15_OFFSET(c3_DACR)]
-	add	r2, vcpu, #CP15_OFFSET(c2_TTBR0)
-	strd	r6, r7, [r2]
-	add	r2, vcpu, #CP15_OFFSET(c2_TTBR1)
-	strd	r8, r9, [r2]
-	str	r10, [vcpu, #CP15_OFFSET(c10_PRRR)]
-	str	r11, [vcpu, #CP15_OFFSET(c10_NMRR)]
-	str	r12, [vcpu, #CP15_OFFSET(c0_CSSELR)]
-	.endif
-
-	mrc	p15, 0, r2, c13, c0, 1	@ CID
-	mrc	p15, 0, r3, c13, c0, 2	@ TID_URW
-	mrc	p15, 0, r4, c13, c0, 3	@ TID_URO
-	mrc	p15, 0, r5, c13, c0, 4	@ TID_PRIV
-	mrc	p15, 0, r6, c5, c0, 0	@ DFSR
-	mrc	p15, 0, r7, c5, c0, 1	@ IFSR
-	mrc	p15, 0, r8, c5, c1, 0	@ ADFSR
-	mrc	p15, 0, r9, c5, c1, 1	@ AIFSR
-	mrc	p15, 0, r10, c6, c0, 0	@ DFAR
-	mrc	p15, 0, r11, c6, c0, 2	@ IFAR
-	mrc	p15, 0, r12, c12, c0, 0	@ VBAR
-
-	.if \store_to_vcpu == 0
-	push	{r2-r12}		@ Push CP15 registers
-	.else
-	str	r2, [vcpu, #CP15_OFFSET(c13_CID)]
-	str	r3, [vcpu, #CP15_OFFSET(c13_TID_URW)]
-	str	r4, [vcpu, #CP15_OFFSET(c13_TID_URO)]
-	str	r5, [vcpu, #CP15_OFFSET(c13_TID_PRIV)]
-	str	r6, [vcpu, #CP15_OFFSET(c5_DFSR)]
-	str	r7, [vcpu, #CP15_OFFSET(c5_IFSR)]
-	str	r8, [vcpu, #CP15_OFFSET(c5_ADFSR)]
-	str	r9, [vcpu, #CP15_OFFSET(c5_AIFSR)]
-	str	r10, [vcpu, #CP15_OFFSET(c6_DFAR)]
-	str	r11, [vcpu, #CP15_OFFSET(c6_IFAR)]
-	str	r12, [vcpu, #CP15_OFFSET(c12_VBAR)]
-	.endif
-
-	mrc	p15, 0, r2, c14, c1, 0	@ CNTKCTL
-	mrrc	p15, 0, r4, r5, c7	@ PAR
-	mrc	p15, 0, r6, c10, c3, 0	@ AMAIR0
-	mrc	p15, 0, r7, c10, c3, 1	@ AMAIR1
-
-	.if \store_to_vcpu == 0
-	push	{r2,r4-r7}
-	.else
-	str	r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
-	add	r12, vcpu, #CP15_OFFSET(c7_PAR)
-	strd	r4, r5, [r12]
-	str	r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)]
-	str	r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)]
-	.endif
-.endm
-
-/*
- * Reads cp15 registers from memory and writes them to hardware
- * @read_from_vcpu: If 0, registers are read in-order from the stack,
- *		    otherwise from the VCPU struct pointed to by vcpup
- *
- * Assumes vcpu pointer in vcpu reg
- */
-.macro write_cp15_state read_from_vcpu
-	.if \read_from_vcpu == 0
-	pop	{r2,r4-r7}
-	.else
-	ldr	r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
-	add	r12, vcpu, #CP15_OFFSET(c7_PAR)
-	ldrd	r4, r5, [r12]
-	ldr	r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)]
-	ldr	r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)]
-	.endif
-
-	mcr	p15, 0, r2, c14, c1, 0	@ CNTKCTL
-	mcrr	p15, 0, r4, r5, c7	@ PAR
-	mcr	p15, 0, r6, c10, c3, 0	@ AMAIR0
-	mcr	p15, 0, r7, c10, c3, 1	@ AMAIR1
-
-	.if \read_from_vcpu == 0
-	pop	{r2-r12}
-	.else
-	ldr	r2, [vcpu, #CP15_OFFSET(c13_CID)]
-	ldr	r3, [vcpu, #CP15_OFFSET(c13_TID_URW)]
-	ldr	r4, [vcpu, #CP15_OFFSET(c13_TID_URO)]
-	ldr	r5, [vcpu, #CP15_OFFSET(c13_TID_PRIV)]
-	ldr	r6, [vcpu, #CP15_OFFSET(c5_DFSR)]
-	ldr	r7, [vcpu, #CP15_OFFSET(c5_IFSR)]
-	ldr	r8, [vcpu, #CP15_OFFSET(c5_ADFSR)]
-	ldr	r9, [vcpu, #CP15_OFFSET(c5_AIFSR)]
-	ldr	r10, [vcpu, #CP15_OFFSET(c6_DFAR)]
-	ldr	r11, [vcpu, #CP15_OFFSET(c6_IFAR)]
-	ldr	r12, [vcpu, #CP15_OFFSET(c12_VBAR)]
-	.endif
-
-	mcr	p15, 0, r2, c13, c0, 1	@ CID
-	mcr	p15, 0, r3, c13, c0, 2	@ TID_URW
-	mcr	p15, 0, r4, c13, c0, 3	@ TID_URO
-	mcr	p15, 0, r5, c13, c0, 4	@ TID_PRIV
-	mcr	p15, 0, r6, c5, c0, 0	@ DFSR
-	mcr	p15, 0, r7, c5, c0, 1	@ IFSR
-	mcr	p15, 0, r8, c5, c1, 0	@ ADFSR
-	mcr	p15, 0, r9, c5, c1, 1	@ AIFSR
-	mcr	p15, 0, r10, c6, c0, 0	@ DFAR
-	mcr	p15, 0, r11, c6, c0, 2	@ IFAR
-	mcr	p15, 0, r12, c12, c0, 0	@ VBAR
-
-	.if \read_from_vcpu == 0
-	pop	{r2-r12}
-	.else
-	ldr	r2, [vcpu, #CP15_OFFSET(c1_SCTLR)]
-	ldr	r3, [vcpu, #CP15_OFFSET(c1_CPACR)]
-	ldr	r4, [vcpu, #CP15_OFFSET(c2_TTBCR)]
-	ldr	r5, [vcpu, #CP15_OFFSET(c3_DACR)]
-	add	r12, vcpu, #CP15_OFFSET(c2_TTBR0)
-	ldrd	r6, r7, [r12]
-	add	r12, vcpu, #CP15_OFFSET(c2_TTBR1)
-	ldrd	r8, r9, [r12]
-	ldr	r10, [vcpu, #CP15_OFFSET(c10_PRRR)]
-	ldr	r11, [vcpu, #CP15_OFFSET(c10_NMRR)]
-	ldr	r12, [vcpu, #CP15_OFFSET(c0_CSSELR)]
-	.endif
-
-	mcr	p15, 0, r2, c1, c0, 0	@ SCTLR
-	mcr	p15, 0, r3, c1, c0, 2	@ CPACR
-	mcr	p15, 0, r4, c2, c0, 2	@ TTBCR
-	mcr	p15, 0, r5, c3, c0, 0	@ DACR
-	mcrr	p15, 0, r6, r7, c2	@ TTBR 0
-	mcrr	p15, 1, r8, r9, c2	@ TTBR 1
-	mcr	p15, 0, r10, c10, c2, 0	@ PRRR
-	mcr	p15, 0, r11, c10, c2, 1	@ NMRR
-	mcr	p15, 2, r12, c0, c0, 0	@ CSSELR
-.endm
-
-/*
- * Save the VGIC CPU state into memory
- *
- * Assumes vcpu pointer in vcpu reg
- */
-.macro save_vgic_state
-	/* Get VGIC VCTRL base into r2 */
-	ldr	r2, [vcpu, #VCPU_KVM]
-	ldr	r2, [r2, #KVM_VGIC_VCTRL]
-	cmp	r2, #0
-	beq	2f
-
-	/* Compute the address of struct vgic_cpu */
-	add	r11, vcpu, #VCPU_VGIC_CPU
-
-	/* Save all interesting registers */
-	ldr	r4, [r2, #GICH_VMCR]
-	ldr	r5, [r2, #GICH_MISR]
-	ldr	r6, [r2, #GICH_EISR0]
-	ldr	r7, [r2, #GICH_EISR1]
-	ldr	r8, [r2, #GICH_ELRSR0]
-	ldr	r9, [r2, #GICH_ELRSR1]
-	ldr	r10, [r2, #GICH_APR]
-ARM_BE8(rev	r4, r4	)
-ARM_BE8(rev	r5, r5	)
-ARM_BE8(rev	r6, r6	)
-ARM_BE8(rev	r7, r7	)
-ARM_BE8(rev	r8, r8	)
-ARM_BE8(rev	r9, r9	)
-ARM_BE8(rev	r10, r10	)
-
-	str	r4, [r11, #VGIC_V2_CPU_VMCR]
-	str	r5, [r11, #VGIC_V2_CPU_MISR]
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	str	r6, [r11, #(VGIC_V2_CPU_EISR + 4)]
-	str	r7, [r11, #VGIC_V2_CPU_EISR]
-	str	r8, [r11, #(VGIC_V2_CPU_ELRSR + 4)]
-	str	r9, [r11, #VGIC_V2_CPU_ELRSR]
-#else
-	str	r6, [r11, #VGIC_V2_CPU_EISR]
-	str	r7, [r11, #(VGIC_V2_CPU_EISR + 4)]
-	str	r8, [r11, #VGIC_V2_CPU_ELRSR]
-	str	r9, [r11, #(VGIC_V2_CPU_ELRSR + 4)]
-#endif
-	str	r10, [r11, #VGIC_V2_CPU_APR]
-
-	/* Clear GICH_HCR */
-	mov	r5, #0
-	str	r5, [r2, #GICH_HCR]
-
-	/* Save list registers */
-	add	r2, r2, #GICH_LR0
-	add	r3, r11, #VGIC_V2_CPU_LR
-	ldr	r4, [r11, #VGIC_CPU_NR_LR]
-1:	ldr	r6, [r2], #4
-ARM_BE8(rev	r6, r6	)
-	str	r6, [r3], #4
-	subs	r4, r4, #1
-	bne	1b
-2:
-.endm
-
-/*
- * Restore the VGIC CPU state from memory
- *
- * Assumes vcpu pointer in vcpu reg
- */
-.macro restore_vgic_state
-	/* Get VGIC VCTRL base into r2 */
-	ldr	r2, [vcpu, #VCPU_KVM]
-	ldr	r2, [r2, #KVM_VGIC_VCTRL]
-	cmp	r2, #0
-	beq	2f
-
-	/* Compute the address of struct vgic_cpu */
-	add	r11, vcpu, #VCPU_VGIC_CPU
-
-	/* We only restore a minimal set of registers */
-	ldr	r3, [r11, #VGIC_V2_CPU_HCR]
-	ldr	r4, [r11, #VGIC_V2_CPU_VMCR]
-	ldr	r8, [r11, #VGIC_V2_CPU_APR]
-ARM_BE8(rev	r3, r3	)
-ARM_BE8(rev	r4, r4	)
-ARM_BE8(rev	r8, r8	)
-
-	str	r3, [r2, #GICH_HCR]
-	str	r4, [r2, #GICH_VMCR]
-	str	r8, [r2, #GICH_APR]
-
-	/* Restore list registers */
-	add	r2, r2, #GICH_LR0
-	add	r3, r11, #VGIC_V2_CPU_LR
-	ldr	r4, [r11, #VGIC_CPU_NR_LR]
-1:	ldr	r6, [r3], #4
-ARM_BE8(rev	r6, r6  )
-	str	r6, [r2], #4
-	subs	r4, r4, #1
-	bne	1b
-2:
-.endm
-
-#define CNTHCTL_PL1PCTEN	(1 << 0)
-#define CNTHCTL_PL1PCEN		(1 << 1)
-
-/*
- * Save the timer state onto the VCPU and allow physical timer/counter access
- * for the host.
- *
- * Assumes vcpu pointer in vcpu reg
- * Clobbers r2-r5
- */
-.macro save_timer_state
-	ldr	r4, [vcpu, #VCPU_KVM]
-	ldr	r2, [r4, #KVM_TIMER_ENABLED]
-	cmp	r2, #0
-	beq	1f
-
-	mrc	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
-	str	r2, [vcpu, #VCPU_TIMER_CNTV_CTL]
-
-	isb
-
-	mrrc	p15, 3, rr_lo_hi(r2, r3), c14	@ CNTV_CVAL
-	ldr	r4, =VCPU_TIMER_CNTV_CVAL
-	add	r5, vcpu, r4
-	strd	r2, r3, [r5]
-
-	@ Ensure host CNTVCT == CNTPCT
-	mov	r2, #0
-	mcrr	p15, 4, r2, r2, c14	@ CNTVOFF
-
-1:
-	mov	r2, #0			@ Clear ENABLE
-	mcr	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
-
-	@ Allow physical timer/counter access for the host
-	mrc	p15, 4, r2, c14, c1, 0	@ CNTHCTL
-	orr	r2, r2, #(CNTHCTL_PL1PCEN | CNTHCTL_PL1PCTEN)
-	mcr	p15, 4, r2, c14, c1, 0	@ CNTHCTL
-.endm
-
-/*
- * Load the timer state from the VCPU and deny physical timer/counter access
- * for the host.
- *
- * Assumes vcpu pointer in vcpu reg
- * Clobbers r2-r5
- */
-.macro restore_timer_state
-	@ Disallow physical timer access for the guest
-	@ Physical counter access is allowed
-	mrc	p15, 4, r2, c14, c1, 0	@ CNTHCTL
-	orr	r2, r2, #CNTHCTL_PL1PCTEN
-	bic	r2, r2, #CNTHCTL_PL1PCEN
-	mcr	p15, 4, r2, c14, c1, 0	@ CNTHCTL
-
-	ldr	r4, [vcpu, #VCPU_KVM]
-	ldr	r2, [r4, #KVM_TIMER_ENABLED]
-	cmp	r2, #0
-	beq	1f
-
-	ldr	r2, [r4, #KVM_TIMER_CNTVOFF]
-	ldr	r3, [r4, #(KVM_TIMER_CNTVOFF + 4)]
-	mcrr	p15, 4, rr_lo_hi(r2, r3), c14	@ CNTVOFF
-
-	ldr	r4, =VCPU_TIMER_CNTV_CVAL
-	add	r5, vcpu, r4
-	ldrd	r2, r3, [r5]
-	mcrr	p15, 3, rr_lo_hi(r2, r3), c14	@ CNTV_CVAL
-	isb
-
-	ldr	r2, [vcpu, #VCPU_TIMER_CNTV_CTL]
-	and	r2, r2, #3
-	mcr	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
-1:
-.endm
-
-.equ vmentry,	0
-.equ vmexit,	1
-
-/* Configures the HSTR (Hyp System Trap Register) on entry/return
- * (hardware reset value is 0) */
-.macro set_hstr operation
-	mrc	p15, 4, r2, c1, c1, 3
-	ldr	r3, =HSTR_T(15)
-	.if \operation == vmentry
-	orr	r2, r2, r3		@ Trap CR{15}
-	.else
-	bic	r2, r2, r3		@ Don't trap any CRx accesses
-	.endif
-	mcr	p15, 4, r2, c1, c1, 3
-.endm
-
-/* Configures the HCPTR (Hyp Coprocessor Trap Register) on entry/return
- * (hardware reset value is 0). Keep previous value in r2.
- * An ISB is emited on vmexit/vmtrap, but executed on vmexit only if
- * VFP wasn't already enabled (always executed on vmtrap).
- * If a label is specified with vmexit, it is branched to if VFP wasn't
- * enabled.
- */
-.macro set_hcptr operation, mask, label = none
-	mrc	p15, 4, r2, c1, c1, 2
-	ldr	r3, =\mask
-	.if \operation == vmentry
-	orr	r3, r2, r3		@ Trap coproc-accesses defined in mask
-	.else
-	bic	r3, r2, r3		@ Don't trap defined coproc-accesses
-	.endif
-	mcr	p15, 4, r3, c1, c1, 2
-	.if \operation != vmentry
-	.if \operation == vmexit
-	tst	r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
-	beq	1f
-	.endif
-	isb
-	.if \label != none
-	b	\label
-	.endif
-1:
-	.endif
-.endm
-
-/* Configures the HDCR (Hyp Debug Configuration Register) on entry/return
- * (hardware reset value is 0) */
-.macro set_hdcr operation
-	mrc	p15, 4, r2, c1, c1, 1
-	ldr	r3, =(HDCR_TPM|HDCR_TPMCR)
-	.if \operation == vmentry
-	orr	r2, r2, r3		@ Trap some perfmon accesses
-	.else
-	bic	r2, r2, r3		@ Don't trap any perfmon accesses
-	.endif
-	mcr	p15, 4, r2, c1, c1, 1
-.endm
-
-/* Enable/Disable: stage-2 trans., trap interrupts, trap wfi, trap smc */
-.macro configure_hyp_role operation
-	.if \operation == vmentry
-	ldr	r2, [vcpu, #VCPU_HCR]
-	ldr	r3, [vcpu, #VCPU_IRQ_LINES]
-	orr	r2, r2, r3
-	.else
-	mov	r2, #0
-	.endif
-	mcr	p15, 4, r2, c1, c1, 0	@ HCR
-.endm
-
-.macro load_vcpu
-	mrc	p15, 4, vcpu, c13, c0, 2	@ HTPIDR
-.endm
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index 7f33b2056ae6..0f6600f05137 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -206,7 +206,8 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	run->mmio.is_write	= is_write;
 	run->mmio.phys_addr	= fault_ipa;
 	run->mmio.len		= len;
-	memcpy(run->mmio.data, data_buf, len);
+	if (is_write)
+		memcpy(run->mmio.data, data_buf, len);
 
 	if (!ret) {
 		/* We handled the access successfully in the kernel. */
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index aba61fd3697a..58dbd5c439df 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -28,6 +28,7 @@
 #include <asm/kvm_mmio.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
+#include <asm/virt.h>
 
 #include "trace.h"
 
@@ -598,6 +599,9 @@ int create_hyp_mappings(void *from, void *to)
 	unsigned long start = KERN_TO_HYP((unsigned long)from);
 	unsigned long end = KERN_TO_HYP((unsigned long)to);
 
+	if (is_kernel_in_hyp_mode())
+		return 0;
+
 	start = start & PAGE_MASK;
 	end = PAGE_ALIGN(end);
 
@@ -630,6 +634,9 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
 	unsigned long start = KERN_TO_HYP((unsigned long)from);
 	unsigned long end = KERN_TO_HYP((unsigned long)to);
 
+	if (is_kernel_in_hyp_mode())
+		return 0;
+
 	/* Check for a valid kernel IO mapping */
 	if (!is_vmalloc_addr(from) || !is_vmalloc_addr(to - 1))
 		return -EINVAL;
@@ -1431,6 +1438,22 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		}
 
 		/*
+		 * Check for a cache maintenance operation. Since we
+		 * ended-up here, we know it is outside of any memory
+		 * slot. But we can't find out if that is for a device,
+		 * or if the guest is just being stupid. The only thing
+		 * we know for sure is that this range cannot be cached.
+		 *
+		 * So let's assume that the guest is just being
+		 * cautious, and skip the instruction.
+		 */
+		if (kvm_vcpu_dabt_is_cm(vcpu)) {
+			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+			ret = 1;
+			goto out_unlock;
+		}
+
+		/*
 		 * The IPA is reported as [MAX:12], so we need to
 		 * complement it with the bottom 12 bits from the
 		 * faulting VA. This is always 12 bits, irrespective
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index a9b3b905e661..c2b131527a64 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -70,7 +70,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 {
 	struct kvm *kvm = source_vcpu->kvm;
 	struct kvm_vcpu *vcpu = NULL;
-	wait_queue_head_t *wq;
+	struct swait_queue_head *wq;
 	unsigned long cpu_id;
 	unsigned long context_id;
 	phys_addr_t target_pc;
@@ -119,7 +119,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	smp_mb();		/* Make sure the above is visible */
 
 	wq = kvm_arch_vcpu_wq(vcpu);
-	wake_up_interruptible(wq);
+	swake_up(wq);
 
 	return PSCI_RET_SUCCESS;
 }
diff --git a/arch/arm/kvm/reset.c b/arch/arm/kvm/reset.c
index eeb85858d6bb..0048b5a62a50 100644
--- a/arch/arm/kvm/reset.c
+++ b/arch/arm/kvm/reset.c
@@ -71,7 +71,7 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	}
 
 	/* Reset core registers */
-	memcpy(&vcpu->arch.regs, reset_regs, sizeof(vcpu->arch.regs));
+	memcpy(&vcpu->arch.ctxt.gp_regs, reset_regs, sizeof(vcpu->arch.ctxt.gp_regs));
 
 	/* Reset CP15 registers */
 	kvm_reset_coprocs(vcpu);
diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c
index cfc696b972f3..fd8720532471 100644
--- a/arch/arm/mach-imx/gpc.c
+++ b/arch/arm/mach-imx/gpc.c
@@ -374,8 +374,13 @@ static struct pu_domain imx6q_pu_domain = {
 		.name = "PU",
 		.power_off = imx6q_pm_pu_power_off,
 		.power_on = imx6q_pm_pu_power_on,
-		.power_off_latency_ns = 25000,
-		.power_on_latency_ns = 2000000,
+		.states = {
+			[0] = {
+				.power_off_latency_ns = 25000,
+				.power_on_latency_ns = 2000000,
+			},
+		},
+		.state_count = 1,
 	},
 };
 
diff --git a/arch/arm/mach-lpc32xx/phy3250.c b/arch/arm/mach-lpc32xx/phy3250.c
index 77d6b1bab278..ee06fabdf60e 100644
--- a/arch/arm/mach-lpc32xx/phy3250.c
+++ b/arch/arm/mach-lpc32xx/phy3250.c
@@ -86,8 +86,8 @@ static int lpc32xx_clcd_setup(struct clcd_fb *fb)
 {
 	dma_addr_t dma;
 
-	fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev,
-		PANEL_SIZE, &dma, GFP_KERNEL);
+	fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, PANEL_SIZE, &dma,
+					  GFP_KERNEL);
 	if (!fb->fb.screen_base) {
 		printk(KERN_ERR "CLCD: unable to map framebuffer\n");
 		return -ENOMEM;
@@ -116,15 +116,14 @@ static int lpc32xx_clcd_setup(struct clcd_fb *fb)
 
 static int lpc32xx_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma)
 {
-	return dma_mmap_writecombine(&fb->dev->dev, vma,
-		fb->fb.screen_base, fb->fb.fix.smem_start,
-		fb->fb.fix.smem_len);
+	return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base,
+			   fb->fb.fix.smem_start, fb->fb.fix.smem_len);
 }
 
 static void lpc32xx_clcd_remove(struct clcd_fb *fb)
 {
-	dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len,
-		fb->fb.screen_base, fb->fb.fix.smem_start);
+	dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base,
+		    fb->fb.fix.smem_start);
 }
 
 /*
diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig
index 64e3d2ce9a07..b003e3afd693 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -3,7 +3,6 @@ menuconfig ARCH_MVEBU
 	depends on ARCH_MULTI_V7 || ARCH_MULTI_V5
 	select ARCH_SUPPORTS_BIG_ENDIAN
 	select CLKSRC_MMIO
-	select GENERIC_IRQ_CHIP
 	select PINCTRL
 	select PLAT_ORION
 	select SOC_BUS
@@ -29,6 +28,7 @@ config MACH_ARMADA_370
 	bool "Marvell Armada 370 boards"
 	depends on ARCH_MULTI_V7
 	select ARMADA_370_CLK
+	select ARMADA_370_XP_IRQ
 	select CPU_PJ4B
 	select MACH_MVEBU_V7
 	select PINCTRL_ARMADA_370
@@ -39,6 +39,7 @@ config MACH_ARMADA_370
 config MACH_ARMADA_375
 	bool "Marvell Armada 375 boards"
 	depends on ARCH_MULTI_V7
+	select ARMADA_370_XP_IRQ
 	select ARM_ERRATA_720789
 	select ARM_ERRATA_753970
 	select ARM_GIC
@@ -58,6 +59,7 @@ config MACH_ARMADA_38X
 	select ARM_ERRATA_720789
 	select ARM_ERRATA_753970
 	select ARM_GIC
+	select ARMADA_370_XP_IRQ
 	select ARMADA_38X_CLK
 	select HAVE_ARM_SCU
 	select HAVE_ARM_TWD if SMP
@@ -72,6 +74,7 @@ config MACH_ARMADA_39X
 	bool "Marvell Armada 39x boards"
 	depends on ARCH_MULTI_V7
 	select ARM_GIC
+	select ARMADA_370_XP_IRQ
 	select ARMADA_39X_CLK
 	select CACHE_L2X0
 	select HAVE_ARM_SCU
@@ -86,6 +89,7 @@ config MACH_ARMADA_39X
 config MACH_ARMADA_XP
 	bool "Marvell Armada XP boards"
 	depends on ARCH_MULTI_V7
+	select ARMADA_370_XP_IRQ
 	select ARMADA_XP_CLK
 	select CPU_PJ4B
 	select MACH_MVEBU_V7
diff --git a/arch/arm/mach-netx/fb.c b/arch/arm/mach-netx/fb.c
index d122ee6ab991..8814ee5e98fd 100644
--- a/arch/arm/mach-netx/fb.c
+++ b/arch/arm/mach-netx/fb.c
@@ -42,8 +42,8 @@ int netx_clcd_setup(struct clcd_fb *fb)
 
 	fb->panel = netx_panel;
 
-	fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev, 1024*1024,
-						    &dma, GFP_KERNEL);
+	fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, 1024 * 1024, &dma,
+					  GFP_KERNEL);
 	if (!fb->fb.screen_base) {
 		printk(KERN_ERR "CLCD: unable to map framebuffer\n");
 		return -ENOMEM;
@@ -57,16 +57,14 @@ int netx_clcd_setup(struct clcd_fb *fb)
 
 int netx_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma)
 {
-	return dma_mmap_writecombine(&fb->dev->dev, vma,
-				     fb->fb.screen_base,
-				     fb->fb.fix.smem_start,
-				     fb->fb.fix.smem_len);
+	return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base,
+			   fb->fb.fix.smem_start, fb->fb.fix.smem_len);
 }
 
 void netx_clcd_remove(struct clcd_fb *fb)
 {
-	dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len,
-			      fb->fb.screen_base, fb->fb.fix.smem_start);
+	dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base,
+		    fb->fb.fix.smem_start);
 }
 
 static AMBA_AHB_DEVICE(fb, "fb", 0, 0x00104000, { NETX_IRQ_LCD }, NULL);
diff --git a/arch/arm/mach-nspire/clcd.c b/arch/arm/mach-nspire/clcd.c
index abea12617b17..ea0e5b2ca1cd 100644
--- a/arch/arm/mach-nspire/clcd.c
+++ b/arch/arm/mach-nspire/clcd.c
@@ -90,8 +90,8 @@ int nspire_clcd_setup(struct clcd_fb *fb)
 	panel_size = ((panel->mode.xres * panel->mode.yres) * panel->bpp) / 8;
 	panel_size = ALIGN(panel_size, PAGE_SIZE);
 
-	fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev,
-		panel_size, &dma, GFP_KERNEL);
+	fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, panel_size, &dma,
+					  GFP_KERNEL);
 
 	if (!fb->fb.screen_base) {
 		pr_err("CLCD: unable to map framebuffer\n");
@@ -107,13 +107,12 @@ int nspire_clcd_setup(struct clcd_fb *fb)
 
 int nspire_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma)
 {
-	return dma_mmap_writecombine(&fb->dev->dev, vma,
-		fb->fb.screen_base, fb->fb.fix.smem_start,
-		fb->fb.fix.smem_len);
+	return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base,
+			   fb->fb.fix.smem_start, fb->fb.fix.smem_len);
 }
 
 void nspire_clcd_remove(struct clcd_fb *fb)
 {
-	dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len,
-		fb->fb.screen_base, fb->fb.fix.smem_start);
+	dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base,
+		    fb->fb.fix.smem_start);
 }
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index 809827265fb3..bab814d2f37d 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -18,6 +18,7 @@
 
 #include <asm/setup.h>
 #include <asm/mach/arch.h>
+#include <asm/system_info.h>
 
 #include "common.h"
 
@@ -77,12 +78,31 @@ static const char *const n900_boards_compat[] __initconst = {
 	NULL,
 };
 
+/* Set system_rev from atags */
+static void __init rx51_set_system_rev(const struct tag *tags)
+{
+	const struct tag *tag;
+
+	if (tags->hdr.tag != ATAG_CORE)
+		return;
+
+	for_each_tag(tag, tags) {
+		if (tag->hdr.tag == ATAG_REVISION) {
+			system_rev = tag->u.revision.rev;
+			break;
+		}
+	}
+}
+
 /* Legacy userspace on Nokia N900 needs ATAGS exported in /proc/atags,
  * save them while the data is still not overwritten
  */
 static void __init rx51_reserve(void)
 {
-	save_atags((const struct tag *)(PAGE_OFFSET + 0x100));
+	const struct tag *tags = (const struct tag *)(PAGE_OFFSET + 0x100);
+
+	save_atags(tags);
+	rx51_set_system_rev(tags);
 	omap_reserve();
 }
 
diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c
index 7b76ce01c21d..8633c703546a 100644
--- a/arch/arm/mach-omap2/gpmc-onenand.c
+++ b/arch/arm/mach-omap2/gpmc-onenand.c
@@ -101,10 +101,8 @@ static void omap2_onenand_set_async_mode(void __iomem *onenand_base)
 
 static void set_onenand_cfg(void __iomem *onenand_base)
 {
-	u32 reg;
+	u32 reg = ONENAND_SYS_CFG1_RDY | ONENAND_SYS_CFG1_INT;
 
-	reg = readw(onenand_base + ONENAND_REG_SYS_CFG1);
-	reg &= ~((0x7 << ONENAND_SYS_CFG1_BRL_SHIFT) | (0x7 << 9));
 	reg |=	(latency << ONENAND_SYS_CFG1_BRL_SHIFT) |
 		ONENAND_SYS_CFG1_BL_16;
 	if (onenand_flags & ONENAND_FLAG_SYNCREAD)
@@ -123,6 +121,7 @@ static void set_onenand_cfg(void __iomem *onenand_base)
 		reg |= ONENAND_SYS_CFG1_VHF;
 	else
 		reg &= ~ONENAND_SYS_CFG1_VHF;
+
 	writew(reg, onenand_base + ONENAND_REG_SYS_CFG1);
 }
 
@@ -289,6 +288,7 @@ static int omap2_onenand_setup_async(void __iomem *onenand_base)
 		}
 	}
 
+	onenand_async.sync_write = true;
 	omap2_onenand_calc_async_timings(&t);
 
 	ret = gpmc_cs_program_settings(gpmc_onenand_data->cs, &onenand_async);
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index 0437537751bc..f7ff3b9dad87 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -191,12 +191,22 @@ static int _omap_device_notifier_call(struct notifier_block *nb,
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct omap_device *od;
+	int err;
 
 	switch (event) {
 	case BUS_NOTIFY_DEL_DEVICE:
 		if (pdev->archdata.od)
 			omap_device_delete(pdev->archdata.od);
 		break;
+	case BUS_NOTIFY_UNBOUND_DRIVER:
+		od = to_omap_device(pdev);
+		if (od && (od->_state == OMAP_DEVICE_STATE_ENABLED)) {
+			dev_info(dev, "enabled after unload, idling\n");
+			err = omap_device_idle(pdev);
+			if (err)
+				dev_err(dev, "failed to idle\n");
+		}
+		break;
 	case BUS_NOTIFY_ADD_DEVICE:
 		if (pdev->dev.of_node)
 			omap_device_build_from_dt(pdev);
@@ -602,8 +612,10 @@ static int _od_runtime_resume(struct device *dev)
 	int ret;
 
 	ret = omap_device_enable(pdev);
-	if (ret)
+	if (ret) {
+		dev_err(dev, "use pm_runtime_put_sync_suspend() in driver?\n");
 		return ret;
+	}
 
 	return pm_generic_runtime_resume(dev);
 }
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index e9f65fec55c0..b6d62e4cdfdd 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -2200,6 +2200,11 @@ static int _enable(struct omap_hwmod *oh)
  */
 static int _idle(struct omap_hwmod *oh)
 {
+	if (oh->flags & HWMOD_NO_IDLE) {
+		oh->_int_flags |= _HWMOD_SKIP_ENABLE;
+		return 0;
+	}
+
 	pr_debug("omap_hwmod: %s: idling\n", oh->name);
 
 	if (oh->_state != _HWMOD_STATE_ENABLED) {
@@ -2504,6 +2509,8 @@ static int __init _init(struct omap_hwmod *oh, void *data)
 			oh->flags |= HWMOD_INIT_NO_RESET;
 		if (of_find_property(np, "ti,no-idle-on-init", NULL))
 			oh->flags |= HWMOD_INIT_NO_IDLE;
+		if (of_find_property(np, "ti,no-idle", NULL))
+			oh->flags |= HWMOD_NO_IDLE;
 	}
 
 	oh->_state = _HWMOD_STATE_INITIALIZED;
@@ -2630,7 +2637,7 @@ static void __init _setup_postsetup(struct omap_hwmod *oh)
 	 * XXX HWMOD_INIT_NO_IDLE does not belong in hwmod data -
 	 * it should be set by the core code as a runtime flag during startup
 	 */
-	if ((oh->flags & HWMOD_INIT_NO_IDLE) &&
+	if ((oh->flags & (HWMOD_INIT_NO_IDLE | HWMOD_NO_IDLE)) &&
 	    (postsetup_state == _HWMOD_STATE_IDLE)) {
 		oh->_int_flags |= _HWMOD_SKIP_ENABLE;
 		postsetup_state = _HWMOD_STATE_ENABLED;
diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h
index 76bce11c85a4..7c7a31169475 100644
--- a/arch/arm/mach-omap2/omap_hwmod.h
+++ b/arch/arm/mach-omap2/omap_hwmod.h
@@ -525,6 +525,8 @@ struct omap_hwmod_omap4_prcm {
  *     or idled.
  * HWMOD_OPT_CLKS_NEEDED: The optional clocks are needed for the module to
  *     operate and they need to be handled at the same time as the main_clk.
+ * HWMOD_NO_IDLE: Do not idle the hwmod at all. Useful to handle certain
+ *     IPs like CPSW on DRA7, where clocks to this module cannot be disabled.
  */
 #define HWMOD_SWSUP_SIDLE			(1 << 0)
 #define HWMOD_SWSUP_MSTANDBY			(1 << 1)
@@ -541,6 +543,7 @@ struct omap_hwmod_omap4_prcm {
 #define HWMOD_SWSUP_SIDLE_ACT			(1 << 12)
 #define HWMOD_RECONFIG_IO_CHAIN			(1 << 13)
 #define HWMOD_OPT_CLKS_NEEDED			(1 << 14)
+#define HWMOD_NO_IDLE				(1 << 15)
 
 /*
  * omap_hwmod._int_flags definitions
diff --git a/arch/arm/mach-shmobile/common.h b/arch/arm/mach-shmobile/common.h
index 9cb11215ceba..b3a4ed5289ec 100644
--- a/arch/arm/mach-shmobile/common.h
+++ b/arch/arm/mach-shmobile/common.h
@@ -4,7 +4,6 @@
 extern void shmobile_init_delay(void);
 extern void shmobile_boot_vector(void);
 extern unsigned long shmobile_boot_fn;
-extern unsigned long shmobile_boot_arg;
 extern unsigned long shmobile_boot_size;
 extern void shmobile_smp_boot(void);
 extern void shmobile_smp_sleep(void);
diff --git a/arch/arm/mach-shmobile/headsmp-scu.S b/arch/arm/mach-shmobile/headsmp-scu.S
index fa5248c52399..5e503d91ad70 100644
--- a/arch/arm/mach-shmobile/headsmp-scu.S
+++ b/arch/arm/mach-shmobile/headsmp-scu.S
@@ -38,9 +38,3 @@ ENTRY(shmobile_boot_scu)
 
 	b	secondary_startup
 ENDPROC(shmobile_boot_scu)
-
-	.text
-	.align	2
-	.globl	shmobile_scu_base
-shmobile_scu_base:
-	.space	4
diff --git a/arch/arm/mach-shmobile/headsmp.S b/arch/arm/mach-shmobile/headsmp.S
index 330c1fc63197..32e0bf6e3ccb 100644
--- a/arch/arm/mach-shmobile/headsmp.S
+++ b/arch/arm/mach-shmobile/headsmp.S
@@ -24,7 +24,6 @@
 	.arm
 	.align  12
 ENTRY(shmobile_boot_vector)
-	ldr     r0, 2f
 	ldr     r1, 1f
 	bx	r1
 
@@ -34,9 +33,6 @@ ENDPROC(shmobile_boot_vector)
 	.globl	shmobile_boot_fn
 shmobile_boot_fn:
 1:	.space	4
-	.globl	shmobile_boot_arg
-shmobile_boot_arg:
-2:	.space	4
 	.globl	shmobile_boot_size
 shmobile_boot_size:
 	.long	. - shmobile_boot_vector
@@ -46,13 +42,15 @@ shmobile_boot_size:
  */
 
 ENTRY(shmobile_smp_boot)
-						@ r0 = MPIDR_HWID_BITMASK
 	mrc	p15, 0, r1, c0, c0, 5		@ r1 = MPIDR
-	and	r0, r1, r0			@ r0 = cpu_logical_map() value
+	and	r0, r1, #0xffffff		@ MPIDR_HWID_BITMASK
+						@ r0 = cpu_logical_map() value
 	mov	r1, #0				@ r1 = CPU index
-	adr	r5, 1f				@ array of per-cpu mpidr values
-	adr	r6, 2f				@ array of per-cpu functions
-	adr	r7, 3f				@ array of per-cpu arguments
+	adr	r2, 1f
+	ldmia	r2, {r5, r6, r7}
+	add	r5, r5, r2			@ array of per-cpu mpidr values
+	add	r6, r6, r2			@ array of per-cpu functions
+	add	r7, r7, r2			@ array of per-cpu arguments
 
 shmobile_smp_boot_find_mpidr:
 	ldr	r8, [r5, r1, lsl #2]
@@ -80,12 +78,18 @@ ENTRY(shmobile_smp_sleep)
 	b	shmobile_smp_boot
 ENDPROC(shmobile_smp_sleep)
 
+	.align	2
+1:	.long	shmobile_smp_mpidr - .
+	.long	shmobile_smp_fn - 1b
+	.long	shmobile_smp_arg - 1b
+
+	.bss
 	.globl	shmobile_smp_mpidr
 shmobile_smp_mpidr:
-1:	.space	NR_CPUS * 4
+	.space	NR_CPUS * 4
 	.globl	shmobile_smp_fn
 shmobile_smp_fn:
-2:	.space	NR_CPUS * 4
+	.space	NR_CPUS * 4
 	.globl	shmobile_smp_arg
 shmobile_smp_arg:
-3:	.space	NR_CPUS * 4
+	.space	NR_CPUS * 4
diff --git a/arch/arm/mach-shmobile/platsmp-apmu.c b/arch/arm/mach-shmobile/platsmp-apmu.c
index 911884f7e28b..aba75c89f9c1 100644
--- a/arch/arm/mach-shmobile/platsmp-apmu.c
+++ b/arch/arm/mach-shmobile/platsmp-apmu.c
@@ -123,7 +123,6 @@ void __init shmobile_smp_apmu_prepare_cpus(unsigned int max_cpus,
 {
 	/* install boot code shared by all CPUs */
 	shmobile_boot_fn = virt_to_phys(shmobile_smp_boot);
-	shmobile_boot_arg = MPIDR_HWID_BITMASK;
 
 	/* perform per-cpu setup */
 	apmu_parse_cfg(apmu_init_cpu, apmu_config, num);
diff --git a/arch/arm/mach-shmobile/platsmp-scu.c b/arch/arm/mach-shmobile/platsmp-scu.c
index 64663110ab6c..081a097c9219 100644
--- a/arch/arm/mach-shmobile/platsmp-scu.c
+++ b/arch/arm/mach-shmobile/platsmp-scu.c
@@ -17,6 +17,9 @@
 #include <asm/smp_scu.h>
 #include "common.h"
 
+
+void __iomem *shmobile_scu_base;
+
 static int shmobile_smp_scu_notifier_call(struct notifier_block *nfb,
 					  unsigned long action, void *hcpu)
 {
@@ -41,7 +44,6 @@ void __init shmobile_smp_scu_prepare_cpus(unsigned int max_cpus)
 {
 	/* install boot code shared by all CPUs */
 	shmobile_boot_fn = virt_to_phys(shmobile_smp_boot);
-	shmobile_boot_arg = MPIDR_HWID_BITMASK;
 
 	/* enable SCU and cache coherency on booting CPU */
 	scu_enable(shmobile_scu_base);
diff --git a/arch/arm/mach-shmobile/smp-r8a7779.c b/arch/arm/mach-shmobile/smp-r8a7779.c
index b854fe2095ad..0b024a9dbd43 100644
--- a/arch/arm/mach-shmobile/smp-r8a7779.c
+++ b/arch/arm/mach-shmobile/smp-r8a7779.c
@@ -92,8 +92,6 @@ static void __init r8a7779_smp_prepare_cpus(unsigned int max_cpus)
 {
 	/* Map the reset vector (in headsmp-scu.S, headsmp.S) */
 	__raw_writel(__pa(shmobile_boot_vector), AVECR);
-	shmobile_boot_fn = virt_to_phys(shmobile_boot_scu);
-	shmobile_boot_arg = (unsigned long)shmobile_scu_base;
 
 	/* setup r8a7779 specific SCU bits */
 	shmobile_scu_base = IOMEM(R8A7779_SCU_BASE);
diff --git a/arch/arm/mach-socfpga/Makefile b/arch/arm/mach-socfpga/Makefile
index b8f9e238e4ab..ed15db19e561 100644
--- a/arch/arm/mach-socfpga/Makefile
+++ b/arch/arm/mach-socfpga/Makefile
@@ -5,3 +5,5 @@
 obj-y					:= socfpga.o
 obj-$(CONFIG_SMP)	+= headsmp.o platsmp.o
 obj-$(CONFIG_SOCFPGA_SUSPEND)	+= pm.o self-refresh.o
+obj-$(CONFIG_EDAC_ALTERA_L2C)	+= l2_cache.o
+obj-$(CONFIG_EDAC_ALTERA_OCRAM)	+= ocram.o
diff --git a/arch/arm/mach-socfpga/core.h b/arch/arm/mach-socfpga/core.h
index 5bc6ea87cdf7..575195be6687 100644
--- a/arch/arm/mach-socfpga/core.h
+++ b/arch/arm/mach-socfpga/core.h
@@ -36,6 +36,8 @@
 
 extern void socfpga_init_clocks(void);
 extern void socfpga_sysmgr_init(void);
+void socfpga_init_l2_ecc(void);
+void socfpga_init_ocram_ecc(void);
 
 extern void __iomem *sys_manager_base_addr;
 extern void __iomem *rst_manager_base_addr;
diff --git a/arch/arm/mach-socfpga/l2_cache.c b/arch/arm/mach-socfpga/l2_cache.c
new file mode 100644
index 000000000000..e3907ab58d05
--- /dev/null
+++ b/arch/arm/mach-socfpga/l2_cache.c
@@ -0,0 +1,41 @@
+/*
+ * Copyright Altera Corporation (C) 2016. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/io.h>
+#include <linux/of_platform.h>
+#include <linux/of_address.h>
+
+void socfpga_init_l2_ecc(void)
+{
+	struct device_node *np;
+	void __iomem *mapped_l2_edac_addr;
+
+	np = of_find_compatible_node(NULL, NULL, "altr,socfpga-l2-ecc");
+	if (!np) {
+		pr_err("Unable to find socfpga-l2-ecc in dtb\n");
+		return;
+	}
+
+	mapped_l2_edac_addr = of_iomap(np, 0);
+	of_node_put(np);
+	if (!mapped_l2_edac_addr) {
+		pr_err("Unable to find L2 ECC mapping in dtb\n");
+		return;
+	}
+
+	/* Enable ECC */
+	writel(0x01, mapped_l2_edac_addr);
+	iounmap(mapped_l2_edac_addr);
+}
diff --git a/arch/arm/mach-socfpga/ocram.c b/arch/arm/mach-socfpga/ocram.c
new file mode 100644
index 000000000000..60ec643ac2be
--- /dev/null
+++ b/arch/arm/mach-socfpga/ocram.c
@@ -0,0 +1,49 @@
+/*
+ * Copyright Altera Corporation (C) 2016. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/io.h>
+#include <linux/genalloc.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+
+#define ALTR_OCRAM_CLEAR_ECC          0x00000018
+#define ALTR_OCRAM_ECC_EN             0x00000019
+
+void socfpga_init_ocram_ecc(void)
+{
+	struct device_node *np;
+	void __iomem *mapped_ocr_edac_addr;
+
+	/* Find the OCRAM EDAC device tree node */
+	np = of_find_compatible_node(NULL, NULL, "altr,socfpga-ocram-ecc");
+	if (!np) {
+		pr_err("Unable to find socfpga-ocram-ecc\n");
+		return;
+	}
+
+	mapped_ocr_edac_addr = of_iomap(np, 0);
+	of_node_put(np);
+	if (!mapped_ocr_edac_addr) {
+		pr_err("Unable to map OCRAM ecc regs.\n");
+		return;
+	}
+
+	/* Clear any pending OCRAM ECC interrupts, then enable ECC */
+	writel(ALTR_OCRAM_CLEAR_ECC, mapped_ocr_edac_addr);
+	writel(ALTR_OCRAM_ECC_EN, mapped_ocr_edac_addr);
+
+	iounmap(mapped_ocr_edac_addr);
+}
diff --git a/arch/arm/mach-socfpga/socfpga.c b/arch/arm/mach-socfpga/socfpga.c
index a1c0efaa8794..7e0aad2ec3d1 100644
--- a/arch/arm/mach-socfpga/socfpga.c
+++ b/arch/arm/mach-socfpga/socfpga.c
@@ -59,6 +59,11 @@ static void __init socfpga_init_irq(void)
 {
 	irqchip_init();
 	socfpga_sysmgr_init();
+	if (IS_ENABLED(CONFIG_EDAC_ALTERA_L2C))
+		socfpga_init_l2_ecc();
+
+	if (IS_ENABLED(CONFIG_EDAC_ALTERA_OCRAM))
+		socfpga_init_ocram_ecc();
 }
 
 static void socfpga_cyclone5_restart(enum reboot_mode mode, const char *cmd)
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 4b4058db0781..66353caa35b9 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -173,7 +173,7 @@ unsigned long arch_mmap_rnd(void)
 {
 	unsigned long rnd;
 
-	rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1);
+	rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
 
 	return rnd << PAGE_SHIFT;
 }
diff --git a/arch/arm/mm/pageattr.c b/arch/arm/mm/pageattr.c
index cf30daff8932..d19b1ad29b07 100644
--- a/arch/arm/mm/pageattr.c
+++ b/arch/arm/mm/pageattr.c
@@ -49,6 +49,9 @@ static int change_memory_common(unsigned long addr, int numpages,
 		WARN_ON_ONCE(1);
 	}
 
+	if (!numpages)
+		return 0;
+
 	if (start < MODULES_VADDR || start >= MODULES_END)
 		return -EINVAL;
 
diff --git a/arch/arm/plat-samsung/pm-check.c b/arch/arm/plat-samsung/pm-check.c
index 04aff2c31b46..70f2f699bed3 100644
--- a/arch/arm/plat-samsung/pm-check.c
+++ b/arch/arm/plat-samsung/pm-check.c
@@ -53,8 +53,8 @@ static void s3c_pm_run_res(struct resource *ptr, run_fn_t fn, u32 *arg)
 		if (ptr->child != NULL)
 			s3c_pm_run_res(ptr->child, fn, arg);
 
-		if ((ptr->flags & IORESOURCE_MEM) &&
-		    strcmp(ptr->name, "System RAM") == 0) {
+		if ((ptr->flags & IORESOURCE_SYSTEM_RAM)
+				== IORESOURCE_SYSTEM_RAM) {
 			S3C_PMDBG("Found system RAM at %08lx..%08lx\n",
 				  (unsigned long)ptr->start,
 				  (unsigned long)ptr->end);
diff --git a/arch/arm/vdso/vdso.S b/arch/arm/vdso/vdso.S
index b2b97e3e7bab..a62a7b64f49c 100644
--- a/arch/arm/vdso/vdso.S
+++ b/arch/arm/vdso/vdso.S
@@ -23,9 +23,8 @@
 #include <linux/const.h>
 #include <asm/page.h>
 
-	__PAGE_ALIGNED_DATA
-
 	.globl vdso_start, vdso_end
+	.section .data..ro_after_init
 	.balign PAGE_SIZE
 vdso_start:
 	.incbin "arch/arm/vdso/vdso.so"
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 8cc62289a63e..b3f2522d266d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -235,8 +235,6 @@ config PCI_SYSCALL
 	def_bool PCI
 
 source "drivers/pci/Kconfig"
-source "drivers/pci/pcie/Kconfig"
-source "drivers/pci/hotplug/Kconfig"
 
 endmenu
 
@@ -750,6 +748,19 @@ config ARM64_LSE_ATOMICS
 	  not support these instructions and requires the kernel to be
 	  built with binutils >= 2.25.
 
+config ARM64_VHE
+	bool "Enable support for Virtualization Host Extensions (VHE)"
+	default y
+	help
+	  Virtualization Host Extensions (VHE) allow the kernel to run
+	  directly at EL2 (instead of EL1) on processors that support
+	  it. This leads to better performance for KVM, as they reduce
+	  the cost of the world switch.
+
+	  Selecting this option allows the VHE feature to be detected
+	  at runtime, and does not affect processors that do not
+	  implement this feature.
+
 endmenu
 
 endmenu
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 307237cfe728..b5e3f6d42b88 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -88,7 +88,7 @@ Image: vmlinux
 Image.%: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
-zinstall install: vmlinux
+zinstall install:
 	$(Q)$(MAKE) $(build)=$(boot) $@
 
 %.dtb: scripts
diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile
index abcbba2f01ba..305c552b5ec1 100644
--- a/arch/arm64/boot/Makefile
+++ b/arch/arm64/boot/Makefile
@@ -34,10 +34,10 @@ $(obj)/Image.lzma: $(obj)/Image FORCE
 $(obj)/Image.lzo: $(obj)/Image FORCE
 	$(call if_changed,lzo)
 
-install: $(obj)/Image
+install:
 	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
 	$(obj)/Image System.map "$(INSTALL_PATH)"
 
-zinstall: $(obj)/Image.gz
+zinstall:
 	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
 	$(obj)/Image.gz System.map "$(INSTALL_PATH)"
diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi
index fe30f7671ea3..3e40bd469cea 100644
--- a/arch/arm64/boot/dts/apm/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi
@@ -493,6 +493,11 @@
 			reg = <0x0 0x1054a000 0x0 0x20>;
 		};
 
+		rb: rb@7e000000 {
+			compatible = "apm,xgene-rb", "syscon";
+			reg = <0x0 0x7e000000 0x0 0x10>;
+		};
+
 		edac@78800000 {
 			compatible = "apm,xgene-edac";
 			#address-cells = <2>;
@@ -502,6 +507,7 @@
 			regmap-mcba = <&mcba>;
 			regmap-mcbb = <&mcbb>;
 			regmap-efuse = <&efuse>;
+			regmap-rb = <&rb>;
 			reg = <0x0 0x78800000 0x0 0x100>;
 			interrupts = <0x0 0x20 0x4>,
 				     <0x0 0x21 0x4>,
diff --git a/arch/arm64/boot/install.sh b/arch/arm64/boot/install.sh
index 12ed78aa6f0c..d91e1f022573 100644
--- a/arch/arm64/boot/install.sh
+++ b/arch/arm64/boot/install.sh
@@ -20,6 +20,20 @@
 #   $4 - default install path (blank if root directory)
 #
 
+verify () {
+	if [ ! -f "$1" ]; then
+		echo ""                                                   1>&2
+		echo " *** Missing file: $1"                              1>&2
+		echo ' *** You need to run "make" before "make install".' 1>&2
+		echo ""                                                   1>&2
+		exit 1
+	fi
+}
+
+# Make sure the files actually exist
+verify "$2"
+verify "$3"
+
 # User may have a custom install script
 if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi
 if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 05d9e16c0dfd..5c888049d061 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -15,6 +15,7 @@
 #include <crypto/algapi.h>
 #include <linux/module.h>
 #include <linux/cpufeature.h>
+#include <crypto/xts.h>
 
 #include "aes-ce-setkey.h"
 
@@ -85,6 +86,10 @@ static int xts_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 	struct crypto_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm);
 	int ret;
 
+	ret = xts_check_key(tfm, in_key, key_len);
+	if (ret)
+		return ret;
+
 	ret = aes_expandkey(&ctx->key1, in_key, key_len / 2);
 	if (!ret)
 		ret = aes_expandkey(&ctx->key2, &in_key[key_len / 2],
@@ -294,7 +299,7 @@ static struct crypto_alg aes_algs[] = { {
 	.cra_blkcipher = {
 		.min_keysize	= AES_MIN_KEY_SIZE,
 		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
+		.ivsize		= 0,
 		.setkey		= aes_setkey,
 		.encrypt	= ecb_encrypt,
 		.decrypt	= ecb_decrypt,
@@ -371,7 +376,7 @@ static struct crypto_alg aes_algs[] = { {
 	.cra_ablkcipher = {
 		.min_keysize	= AES_MIN_KEY_SIZE,
 		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
+		.ivsize		= 0,
 		.setkey		= ablk_set_key,
 		.encrypt	= ablk_encrypt,
 		.decrypt	= ablk_decrypt,
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 70fd9ffb58cf..cff532a6744e 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -1,5 +1,3 @@
-
-
 generic-y += bug.h
 generic-y += bugs.h
 generic-y += checksum.h
@@ -31,7 +29,6 @@ generic-y += msgbuf.h
 generic-y += msi.h
 generic-y += mutex.h
 generic-y += pci.h
-generic-y += pci-bridge.h
 generic-y += poll.h
 generic-y += preempt.h
 generic-y += resource.h
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 2731d3b25ed2..8ec88e5b290f 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -103,6 +103,7 @@ static inline u64 gic_read_iar_common(void)
 	u64 irqstat;
 
 	asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
+	dsb(sy);
 	return irqstat;
 }
 
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 7fc294c3bc5b..22dda613f9c9 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -156,8 +156,4 @@ int set_memory_rw(unsigned long addr, int numpages);
 int set_memory_x(unsigned long addr, int numpages);
 int set_memory_nx(unsigned long addr, int numpages);
 
-#ifdef CONFIG_DEBUG_RODATA
-void mark_rodata_ro(void);
-#endif
-
 #endif
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 8f271b83f910..a5c769b1c65b 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -30,8 +30,12 @@
 #define ARM64_HAS_LSE_ATOMICS			5
 #define ARM64_WORKAROUND_CAVIUM_23154		6
 #define ARM64_WORKAROUND_834220			7
+/* #define ARM64_HAS_NO_HW_PREFETCH		8 */
+/* #define ARM64_HAS_UAO			9 */
+/* #define ARM64_ALT_PAN_NOT_UAO		10 */
+#define ARM64_HAS_VIRT_HOST_EXTN		11
 
-#define ARM64_NCAPS				8
+#define ARM64_NCAPS				12
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index 9732908bfc8a..115ea2a64520 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -18,6 +18,7 @@
 
 #include <asm/cputype.h>
 #include <asm/cpufeature.h>
+#include <asm/virt.h>
 
 #ifdef __KERNEL__
 
@@ -35,10 +36,21 @@ struct arch_hw_breakpoint {
 	struct arch_hw_breakpoint_ctrl ctrl;
 };
 
+/* Privilege Levels */
+#define AARCH64_BREAKPOINT_EL1	1
+#define AARCH64_BREAKPOINT_EL0	2
+
+#define DBG_HMC_HYP		(1 << 13)
+
 static inline u32 encode_ctrl_reg(struct arch_hw_breakpoint_ctrl ctrl)
 {
-	return (ctrl.len << 5) | (ctrl.type << 3) | (ctrl.privilege << 1) |
+	u32 val = (ctrl.len << 5) | (ctrl.type << 3) | (ctrl.privilege << 1) |
 		ctrl.enabled;
+
+	if (is_kernel_in_hyp_mode() && ctrl.privilege == AARCH64_BREAKPOINT_EL1)
+		val |= DBG_HMC_HYP;
+
+	return val;
 }
 
 static inline void decode_ctrl_reg(u32 reg,
@@ -61,10 +73,6 @@ static inline void decode_ctrl_reg(u32 reg,
 #define ARM_BREAKPOINT_STORE	2
 #define AARCH64_ESR_ACCESS_MASK	(1 << 6)
 
-/* Privilege Levels */
-#define AARCH64_BREAKPOINT_EL1	1
-#define AARCH64_BREAKPOINT_EL0	2
-
 /* Lengths */
 #define ARM_BREAKPOINT_LEN_1	0x1
 #define ARM_BREAKPOINT_LEN_2	0x3
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 738a95f93e49..b56a0a81e4cb 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -23,6 +23,7 @@
 #include <asm/types.h>
 
 /* Hyp Configuration Register (HCR) bits */
+#define HCR_E2H		(UL(1) << 34)
 #define HCR_ID		(UL(1) << 33)
 #define HCR_CD		(UL(1) << 32)
 #define HCR_RW_SHIFT	31
@@ -81,7 +82,7 @@
 			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW)
 #define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF)
 #define HCR_INT_OVERRIDE   (HCR_FMO | HCR_IMO)
-
+#define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
 /* Hyp System Control Register (SCTLR_EL2) bits */
 #define SCTLR_EL2_EE	(1 << 25)
@@ -107,8 +108,6 @@
 #define TCR_EL2_MASK	(TCR_EL2_TG0 | TCR_EL2_SH0 | \
 			 TCR_EL2_ORGN0 | TCR_EL2_IRGN0 | TCR_EL2_T0SZ)
 
-#define TCR_EL2_FLAGS	(TCR_EL2_RES1 | TCR_EL2_PS_40B)
-
 /* VTCR_EL2 Registers bits */
 #define VTCR_EL2_RES1		(1 << 31)
 #define VTCR_EL2_PS_MASK	(7 << 16)
@@ -182,6 +181,7 @@
 #define CPTR_EL2_TCPAC	(1 << 31)
 #define CPTR_EL2_TTA	(1 << 20)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
+#define CPTR_EL2_DEFAULT	0x000033ff
 
 /* Hyp Debug Configuration Register bits */
 #define MDCR_EL2_TDRA		(1 << 11)
@@ -217,4 +217,7 @@
 	ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \
 	ECN(BKPT32), ECN(VECTOR32), ECN(BRK64)
 
+#define CPACR_EL1_FPEN		(3 << 20)
+#define CPACR_EL1_TTA		(1 << 28)
+
 #endif /* __ARM64_KVM_ARM_H__ */
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 52b777b7d407..2d02ba67478c 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -35,9 +35,6 @@ extern char __kvm_hyp_init_end[];
 
 extern char __kvm_hyp_vector[];
 
-#define	__kvm_hyp_code_start	__hyp_text_start
-#define	__kvm_hyp_code_end	__hyp_text_end
-
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
@@ -45,9 +42,12 @@ extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
 extern u64 __vgic_v3_get_ich_vtr_el2(void);
+extern void __vgic_v3_init_lrs(void);
 
 extern u32 __kvm_get_mdcr_el2(void);
 
+extern void __init_stage2_translation(void);
+
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 3066328cd86b..40bc1681b6d5 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -29,6 +29,7 @@
 #include <asm/kvm_mmio.h>
 #include <asm/ptrace.h>
 #include <asm/cputype.h>
+#include <asm/virt.h>
 
 unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num);
 unsigned long *vcpu_spsr32(const struct kvm_vcpu *vcpu);
@@ -43,6 +44,8 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
 static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
+	if (is_kernel_in_hyp_mode())
+		vcpu->arch.hcr_el2 |= HCR_E2H;
 	if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features))
 		vcpu->arch.hcr_el2 &= ~HCR_RW;
 }
@@ -127,10 +130,14 @@ static inline unsigned long *vcpu_spsr(const struct kvm_vcpu *vcpu)
 
 static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
 {
-	u32 mode = *vcpu_cpsr(vcpu) & PSR_MODE_MASK;
+	u32 mode;
 
-	if (vcpu_mode_is_32bit(vcpu))
+	if (vcpu_mode_is_32bit(vcpu)) {
+		mode = *vcpu_cpsr(vcpu) & COMPAT_PSR_MODE_MASK;
 		return mode > COMPAT_PSR_MODE_USR;
+	}
+
+	mode = *vcpu_cpsr(vcpu) & PSR_MODE_MASK;
 
 	return mode != PSR_MODE_EL0t;
 }
@@ -185,6 +192,11 @@ static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW);
 }
 
+static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
+{
+	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_CM);
+}
+
 static inline int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu)
 {
 	return 1 << ((kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT);
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 689d4c95e12f..71fa6fe9d54a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -25,7 +25,9 @@
 #include <linux/types.h>
 #include <linux/kvm_types.h>
 #include <asm/kvm.h>
+#include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
+#include <asm/kvm_perf_event.h>
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
@@ -36,10 +38,11 @@
 
 #include <kvm/arm_vgic.h>
 #include <kvm/arm_arch_timer.h>
+#include <kvm/arm_pmu.h>
 
 #define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS
 
-#define KVM_VCPU_MAX_FEATURES 3
+#define KVM_VCPU_MAX_FEATURES 4
 
 int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
@@ -114,6 +117,21 @@ enum vcpu_sysreg {
 	MDSCR_EL1,	/* Monitor Debug System Control Register */
 	MDCCINT_EL1,	/* Monitor Debug Comms Channel Interrupt Enable Reg */
 
+	/* Performance Monitors Registers */
+	PMCR_EL0,	/* Control Register */
+	PMSELR_EL0,	/* Event Counter Selection Register */
+	PMEVCNTR0_EL0,	/* Event Counter Register (0-30) */
+	PMEVCNTR30_EL0 = PMEVCNTR0_EL0 + 30,
+	PMCCNTR_EL0,	/* Cycle Counter Register */
+	PMEVTYPER0_EL0,	/* Event Type Register (0-30) */
+	PMEVTYPER30_EL0 = PMEVTYPER0_EL0 + 30,
+	PMCCFILTR_EL0,	/* Cycle Count Filter Register */
+	PMCNTENSET_EL0,	/* Count Enable Set Register */
+	PMINTENSET_EL1,	/* Interrupt Enable Set Register */
+	PMOVSSET_EL0,	/* Overflow Flag Status Set Register */
+	PMSWINC_EL0,	/* Software Increment Register */
+	PMUSERENR_EL0,	/* User Enable Register */
+
 	/* 32bit specific registers. Keep them at the end of the range */
 	DACR32_EL2,	/* Domain Access Control Register */
 	IFSR32_EL2,	/* Instruction Fault Status Register */
@@ -211,6 +229,7 @@ struct kvm_vcpu_arch {
 	/* VGIC state */
 	struct vgic_cpu vgic_cpu;
 	struct arch_timer_cpu timer_cpu;
+	struct kvm_pmu pmu;
 
 	/*
 	 * Anything that is not used directly from assembly code goes
@@ -342,5 +361,18 @@ void kvm_arm_init_debug(void);
 void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
+int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
+			       struct kvm_device_attr *attr);
+int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
+			       struct kvm_device_attr *attr);
+int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
+			       struct kvm_device_attr *attr);
+
+/* #define kvm_call_hyp(f, ...) __kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__) */
+
+static inline void __cpu_init_stage2(void)
+{
+	kvm_call_hyp(__init_stage2_translation);
+}
 
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
new file mode 100644
index 000000000000..a46b019ebcf5
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -0,0 +1,181 @@
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM64_KVM_HYP_H__
+#define __ARM64_KVM_HYP_H__
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_mmu.h>
+#include <asm/kvm_perf_event.h>
+#include <asm/sysreg.h>
+
+#define __hyp_text __section(.hyp.text) notrace
+
+static inline unsigned long __kern_hyp_va(unsigned long v)
+{
+	asm volatile(ALTERNATIVE("and %0, %0, %1",
+				 "nop",
+				 ARM64_HAS_VIRT_HOST_EXTN)
+		     : "+r" (v) : "i" (HYP_PAGE_OFFSET_MASK));
+	return v;
+}
+
+#define kern_hyp_va(v) (typeof(v))(__kern_hyp_va((unsigned long)(v)))
+
+static inline unsigned long __hyp_kern_va(unsigned long v)
+{
+	u64 offset = PAGE_OFFSET - HYP_PAGE_OFFSET;
+	asm volatile(ALTERNATIVE("add %0, %0, %1",
+				 "nop",
+				 ARM64_HAS_VIRT_HOST_EXTN)
+		     : "+r" (v) : "r" (offset));
+	return v;
+}
+
+#define hyp_kern_va(v) (typeof(v))(__hyp_kern_va((unsigned long)(v)))
+
+#define read_sysreg_elx(r,nvh,vh)					\
+	({								\
+		u64 reg;						\
+		asm volatile(ALTERNATIVE("mrs %0, " __stringify(r##nvh),\
+					 "mrs_s %0, " __stringify(r##vh),\
+					 ARM64_HAS_VIRT_HOST_EXTN)	\
+			     : "=r" (reg));				\
+		reg;							\
+	})
+
+#define write_sysreg_elx(v,r,nvh,vh)					\
+	do {								\
+		u64 __val = (u64)(v);					\
+		asm volatile(ALTERNATIVE("msr " __stringify(r##nvh) ", %x0",\
+					 "msr_s " __stringify(r##vh) ", %x0",\
+					 ARM64_HAS_VIRT_HOST_EXTN)	\
+					 : : "rZ" (__val));		\
+	} while (0)
+
+/*
+ * Unified accessors for registers that have a different encoding
+ * between VHE and non-VHE. They must be specified without their "ELx"
+ * encoding.
+ */
+#define read_sysreg_el2(r)						\
+	({								\
+		u64 reg;						\
+		asm volatile(ALTERNATIVE("mrs %0, " __stringify(r##_EL2),\
+					 "mrs %0, " __stringify(r##_EL1),\
+					 ARM64_HAS_VIRT_HOST_EXTN)	\
+			     : "=r" (reg));				\
+		reg;							\
+	})
+
+#define write_sysreg_el2(v,r)						\
+	do {								\
+		u64 __val = (u64)(v);					\
+		asm volatile(ALTERNATIVE("msr " __stringify(r##_EL2) ", %x0",\
+					 "msr " __stringify(r##_EL1) ", %x0",\
+					 ARM64_HAS_VIRT_HOST_EXTN)	\
+					 : : "rZ" (__val));		\
+	} while (0)
+
+#define read_sysreg_el0(r)	read_sysreg_elx(r, _EL0, _EL02)
+#define write_sysreg_el0(v,r)	write_sysreg_elx(v, r, _EL0, _EL02)
+#define read_sysreg_el1(r)	read_sysreg_elx(r, _EL1, _EL12)
+#define write_sysreg_el1(v,r)	write_sysreg_elx(v, r, _EL1, _EL12)
+
+/* The VHE specific system registers and their encoding */
+#define sctlr_EL12              sys_reg(3, 5, 1, 0, 0)
+#define cpacr_EL12              sys_reg(3, 5, 1, 0, 2)
+#define ttbr0_EL12              sys_reg(3, 5, 2, 0, 0)
+#define ttbr1_EL12              sys_reg(3, 5, 2, 0, 1)
+#define tcr_EL12                sys_reg(3, 5, 2, 0, 2)
+#define afsr0_EL12              sys_reg(3, 5, 5, 1, 0)
+#define afsr1_EL12              sys_reg(3, 5, 5, 1, 1)
+#define esr_EL12                sys_reg(3, 5, 5, 2, 0)
+#define far_EL12                sys_reg(3, 5, 6, 0, 0)
+#define mair_EL12               sys_reg(3, 5, 10, 2, 0)
+#define amair_EL12              sys_reg(3, 5, 10, 3, 0)
+#define vbar_EL12               sys_reg(3, 5, 12, 0, 0)
+#define contextidr_EL12         sys_reg(3, 5, 13, 0, 1)
+#define cntkctl_EL12            sys_reg(3, 5, 14, 1, 0)
+#define cntp_tval_EL02          sys_reg(3, 5, 14, 2, 0)
+#define cntp_ctl_EL02           sys_reg(3, 5, 14, 2, 1)
+#define cntp_cval_EL02          sys_reg(3, 5, 14, 2, 2)
+#define cntv_tval_EL02          sys_reg(3, 5, 14, 3, 0)
+#define cntv_ctl_EL02           sys_reg(3, 5, 14, 3, 1)
+#define cntv_cval_EL02          sys_reg(3, 5, 14, 3, 2)
+#define spsr_EL12               sys_reg(3, 5, 4, 0, 0)
+#define elr_EL12                sys_reg(3, 5, 4, 0, 1)
+
+/**
+ * hyp_alternate_select - Generates patchable code sequences that are
+ * used to switch between two implementations of a function, depending
+ * on the availability of a feature.
+ *
+ * @fname: a symbol name that will be defined as a function returning a
+ * function pointer whose type will match @orig and @alt
+ * @orig: A pointer to the default function, as returned by @fname when
+ * @cond doesn't hold
+ * @alt: A pointer to the alternate function, as returned by @fname
+ * when @cond holds
+ * @cond: a CPU feature (as described in asm/cpufeature.h)
+ */
+#define hyp_alternate_select(fname, orig, alt, cond)			\
+typeof(orig) * __hyp_text fname(void)					\
+{									\
+	typeof(alt) *val = orig;					\
+	asm volatile(ALTERNATIVE("nop		\n",			\
+				 "mov	%0, %1	\n",			\
+				 cond)					\
+		     : "+r" (val) : "r" (alt));				\
+	return val;							\
+}
+
+void __vgic_v2_save_state(struct kvm_vcpu *vcpu);
+void __vgic_v2_restore_state(struct kvm_vcpu *vcpu);
+
+void __vgic_v3_save_state(struct kvm_vcpu *vcpu);
+void __vgic_v3_restore_state(struct kvm_vcpu *vcpu);
+
+void __timer_save_state(struct kvm_vcpu *vcpu);
+void __timer_restore_state(struct kvm_vcpu *vcpu);
+
+void __sysreg_save_host_state(struct kvm_cpu_context *ctxt);
+void __sysreg_restore_host_state(struct kvm_cpu_context *ctxt);
+void __sysreg_save_guest_state(struct kvm_cpu_context *ctxt);
+void __sysreg_restore_guest_state(struct kvm_cpu_context *ctxt);
+void __sysreg32_save_state(struct kvm_vcpu *vcpu);
+void __sysreg32_restore_state(struct kvm_vcpu *vcpu);
+
+void __debug_save_state(struct kvm_vcpu *vcpu,
+			struct kvm_guest_debug_arch *dbg,
+			struct kvm_cpu_context *ctxt);
+void __debug_restore_state(struct kvm_vcpu *vcpu,
+			   struct kvm_guest_debug_arch *dbg,
+			   struct kvm_cpu_context *ctxt);
+void __debug_cond_save_host_state(struct kvm_vcpu *vcpu);
+void __debug_cond_restore_host_state(struct kvm_vcpu *vcpu);
+
+void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
+void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
+bool __fpsimd_enabled(void);
+
+u64 __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host_ctxt);
+void __noreturn __hyp_do_panic(unsigned long, ...);
+
+#endif /* __ARM64_KVM_HYP_H__ */
+
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 736433912a1e..9a9318adefa6 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -23,13 +23,16 @@
 #include <asm/cpufeature.h>
 
 /*
- * As we only have the TTBR0_EL2 register, we cannot express
+ * As ARMv8.0 only has the TTBR0_EL2 register, we cannot express
  * "negative" addresses. This makes it impossible to directly share
  * mappings with the kernel.
  *
  * Instead, give the HYP mode its own VA region at a fixed offset from
  * the kernel by just masking the top bits (which are all ones for a
  * kernel address).
+ *
+ * ARMv8.1 (using VHE) does have a TTBR1_EL2, and doesn't use these
+ * macros (the entire kernel runs at EL2).
  */
 #define HYP_PAGE_OFFSET_SHIFT	VA_BITS
 #define HYP_PAGE_OFFSET_MASK	((UL(1) << HYP_PAGE_OFFSET_SHIFT) - 1)
@@ -56,12 +59,19 @@
 
 #ifdef __ASSEMBLY__
 
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
+
 /*
  * Convert a kernel VA into a HYP VA.
  * reg: VA to be converted.
  */
 .macro kern_hyp_va	reg
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN	
 	and	\reg, \reg, #HYP_PAGE_OFFSET_MASK
+alternative_else
+	nop
+alternative_endif
 .endm
 
 #else
diff --git a/arch/arm64/include/asm/kvm_perf_event.h b/arch/arm64/include/asm/kvm_perf_event.h
new file mode 100644
index 000000000000..c18fdebb8f66
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_perf_event.h
@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ASM_KVM_PERF_EVENT_H
+#define __ASM_KVM_PERF_EVENT_H
+
+#define	ARMV8_PMU_MAX_COUNTERS	32
+#define	ARMV8_PMU_COUNTER_MASK	(ARMV8_PMU_MAX_COUNTERS - 1)
+
+/*
+ * Per-CPU PMCR: config reg
+ */
+#define ARMV8_PMU_PMCR_E	(1 << 0) /* Enable all counters */
+#define ARMV8_PMU_PMCR_P	(1 << 1) /* Reset all counters */
+#define ARMV8_PMU_PMCR_C	(1 << 2) /* Cycle counter reset */
+#define ARMV8_PMU_PMCR_D	(1 << 3) /* CCNT counts every 64th cpu cycle */
+#define ARMV8_PMU_PMCR_X	(1 << 4) /* Export to ETM */
+#define ARMV8_PMU_PMCR_DP	(1 << 5) /* Disable CCNT if non-invasive debug*/
+/* Determines which bit of PMCCNTR_EL0 generates an overflow */
+#define ARMV8_PMU_PMCR_LC	(1 << 6)
+#define	ARMV8_PMU_PMCR_N_SHIFT	11	 /* Number of counters supported */
+#define	ARMV8_PMU_PMCR_N_MASK	0x1f
+#define	ARMV8_PMU_PMCR_MASK	0x7f	 /* Mask for writable bits */
+
+/*
+ * PMOVSR: counters overflow flag status reg
+ */
+#define	ARMV8_PMU_OVSR_MASK		0xffffffff	/* Mask for writable bits */
+#define	ARMV8_PMU_OVERFLOWED_MASK	ARMV8_PMU_OVSR_MASK
+
+/*
+ * PMXEVTYPER: Event selection reg
+ */
+#define	ARMV8_PMU_EVTYPE_MASK	0xc80003ff	/* Mask for writable bits */
+#define	ARMV8_PMU_EVTYPE_EVENT	0x3ff		/* Mask for EVENT bits */
+
+#define ARMV8_PMU_EVTYPE_EVENT_SW_INCR	0	/* Software increment event */
+
+/*
+ * Event filters for PMUv3
+ */
+#define	ARMV8_PMU_EXCLUDE_EL1	(1 << 31)
+#define	ARMV8_PMU_EXCLUDE_EL0	(1 << 30)
+#define	ARMV8_PMU_INCLUDE_EL2	(1 << 27)
+
+/*
+ * PMUSERENR: user enable reg
+ */
+#define ARMV8_PMU_USERENR_MASK	0xf		/* Mask for writable bits */
+#define ARMV8_PMU_USERENR_EN	(1 << 0) /* PMU regs can be accessed at EL0 */
+#define ARMV8_PMU_USERENR_SW	(1 << 1) /* PMSWINC can be written at EL0 */
+#define ARMV8_PMU_USERENR_CR	(1 << 2) /* Cycle counter can be read at EL0 */
+#define ARMV8_PMU_USERENR_ER	(1 << 3) /* Event counter can be read at EL0 */
+
+#endif
diff --git a/arch/arm64/include/asm/pci.h b/arch/arm64/include/asm/pci.h
index b008a72f8bc0..b9a7ba9ca44c 100644
--- a/arch/arm64/include/asm/pci.h
+++ b/arch/arm64/include/asm/pci.h
@@ -7,8 +7,6 @@
 #include <linux/dma-mapping.h>
 
 #include <asm/io.h>
-#include <asm-generic/pci-bridge.h>
-#include <asm-generic/pci-dma-compat.h>
 
 #define PCIBIOS_MIN_IO		0x1000
 #define PCIBIOS_MIN_MEM		0
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index bf464de33f52..819aff5d593f 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -34,7 +34,7 @@
 /*
  * VMALLOC and SPARSEMEM_VMEMMAP ranges.
  *
- * VMEMAP_SIZE: allows the whole VA space to be covered by a struct page array
+ * VMEMAP_SIZE: allows the whole linear region to be covered by a struct page array
  *	(rounded up to PUD_SIZE).
  * VMALLOC_START: beginning of the kernel VA space
  * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space,
@@ -51,7 +51,9 @@
 
 #define VMALLOC_END		(PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
 
-#define vmemmap			((struct page *)(VMALLOC_END + SZ_64K))
+#define VMEMMAP_START		(VMALLOC_END + SZ_64K)
+#define vmemmap			((struct page *)VMEMMAP_START - \
+				 SECTION_ALIGN_DOWN(memstart_addr >> PAGE_SHIFT))
 
 #define FIRST_USER_ADDRESS	0UL
 
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 7a5df5252dd7..9f22dd607958 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -23,6 +23,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/ptrace.h>
+
 /*
  * __boot_cpu_mode records what mode CPUs were booted in.
  * A correctly-implemented bootloader must start all CPUs in the same mode:
@@ -50,6 +52,14 @@ static inline bool is_hyp_mode_mismatched(void)
 	return __boot_cpu_mode[0] != __boot_cpu_mode[1];
 }
 
+static inline bool is_kernel_in_hyp_mode(void)
+{
+	u64 el;
+
+	asm("mrs %0, CurrentEL" : "=r" (el));
+	return el == CurrentEL_EL2;
+}
+
 /* The section containing the hypervisor text */
 extern char __hyp_text_start[];
 extern char __hyp_text_end[];
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 2d4ca4bb0dd3..f209ea151dca 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -94,6 +94,7 @@ struct kvm_regs {
 #define KVM_ARM_VCPU_POWER_OFF		0 /* CPU is started in OFF state */
 #define KVM_ARM_VCPU_EL1_32BIT		1 /* CPU running a 32bit VM */
 #define KVM_ARM_VCPU_PSCI_0_2		2 /* CPU uses PSCI v0.2 */
+#define KVM_ARM_VCPU_PMU_V3		3 /* Support guest PMUv3 */
 
 struct kvm_vcpu_init {
 	__u32 target;
@@ -204,6 +205,11 @@ struct kvm_arch_memory_slot {
 #define KVM_DEV_ARM_VGIC_GRP_CTRL	4
 #define   KVM_DEV_ARM_VGIC_CTRL_INIT	0
 
+/* Device Control API on vcpu fd */
+#define KVM_ARM_VCPU_PMU_V3_CTRL	0
+#define   KVM_ARM_VCPU_PMU_V3_IRQ	0
+#define   KVM_ARM_VCPU_PMU_V3_INIT	1
+
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
 #define KVM_ARM_IRQ_TYPE_MASK		0xff
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index fffa4ac6c25a..b0ab4e93db0d 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -110,9 +110,6 @@ int main(void)
   DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_regs, regs));
   DEFINE(CPU_FP_REGS,		offsetof(struct kvm_regs, fp_regs));
   DEFINE(VCPU_FPEXC32_EL2,	offsetof(struct kvm_vcpu, arch.ctxt.sys_regs[FPEXC32_EL2]));
-  DEFINE(VCPU_ESR_EL2,		offsetof(struct kvm_vcpu, arch.fault.esr_el2));
-  DEFINE(VCPU_FAR_EL2,		offsetof(struct kvm_vcpu, arch.fault.far_el2));
-  DEFINE(VCPU_HPFAR_EL2,	offsetof(struct kvm_vcpu, arch.fault.hpfar_el2));
   DEFINE(VCPU_HOST_CONTEXT,	offsetof(struct kvm_vcpu, arch.host_cpu_context));
 #endif
 #ifdef CONFIG_CPU_PM
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 5c90aa490a2b..ba745199297e 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -26,6 +26,7 @@
 #include <asm/cpu_ops.h>
 #include <asm/processor.h>
 #include <asm/sysreg.h>
+#include <asm/virt.h>
 
 unsigned long elf_hwcap __read_mostly;
 EXPORT_SYMBOL_GPL(elf_hwcap);
@@ -621,6 +622,11 @@ static bool has_useable_gicv3_cpuif(const struct arm64_cpu_capabilities *entry)
 	return has_sre;
 }
 
+static bool runs_at_el2(const struct arm64_cpu_capabilities *entry)
+{
+	return is_kernel_in_hyp_mode();
+}
+
 static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "GIC system register CPU interface",
@@ -651,6 +657,11 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.min_field_value = 2,
 	},
 #endif /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */
+	{
+		.desc = "Virtualization Host Extensions",
+		.capability = ARM64_HAS_VIRT_HOST_EXTN,
+		.matches = runs_at_el2,
+	},
 	{},
 };
 
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 8aee3aeec3e6..c536c9e307b9 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -226,11 +226,28 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr)
 	return retval;
 }
 
+static void send_user_sigtrap(int si_code)
+{
+	struct pt_regs *regs = current_pt_regs();
+	siginfo_t info = {
+		.si_signo	= SIGTRAP,
+		.si_errno	= 0,
+		.si_code	= si_code,
+		.si_addr	= (void __user *)instruction_pointer(regs),
+	};
+
+	if (WARN_ON(!user_mode(regs)))
+		return;
+
+	if (interrupts_enabled(regs))
+		local_irq_enable();
+
+	force_sig_info(SIGTRAP, &info, current);
+}
+
 static int single_step_handler(unsigned long addr, unsigned int esr,
 			       struct pt_regs *regs)
 {
-	siginfo_t info;
-
 	/*
 	 * If we are stepping a pending breakpoint, call the hw_breakpoint
 	 * handler first.
@@ -239,11 +256,7 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
 		return 0;
 
 	if (user_mode(regs)) {
-		info.si_signo = SIGTRAP;
-		info.si_errno = 0;
-		info.si_code  = TRAP_HWBKPT;
-		info.si_addr  = (void __user *)instruction_pointer(regs);
-		force_sig_info(SIGTRAP, &info, current);
+		send_user_sigtrap(TRAP_HWBKPT);
 
 		/*
 		 * ptrace will disable single step unless explicitly
@@ -307,17 +320,8 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr)
 static int brk_handler(unsigned long addr, unsigned int esr,
 		       struct pt_regs *regs)
 {
-	siginfo_t info;
-
 	if (user_mode(regs)) {
-		info = (siginfo_t) {
-			.si_signo = SIGTRAP,
-			.si_errno = 0,
-			.si_code  = TRAP_BRKPT,
-			.si_addr  = (void __user *)instruction_pointer(regs),
-		};
-
-		force_sig_info(SIGTRAP, &info, current);
+		send_user_sigtrap(TRAP_BRKPT);
 	} else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) {
 		pr_warning("Unexpected kernel BRK exception at EL1\n");
 		return -EFAULT;
@@ -328,7 +332,6 @@ static int brk_handler(unsigned long addr, unsigned int esr,
 
 int aarch32_break_handler(struct pt_regs *regs)
 {
-	siginfo_t info;
 	u32 arm_instr;
 	u16 thumb_instr;
 	bool bp = false;
@@ -359,14 +362,7 @@ int aarch32_break_handler(struct pt_regs *regs)
 	if (!bp)
 		return -EFAULT;
 
-	info = (siginfo_t) {
-		.si_signo = SIGTRAP,
-		.si_errno = 0,
-		.si_code  = TRAP_BRKPT,
-		.si_addr  = pc,
-	};
-
-	force_sig_info(SIGTRAP, &info, current);
+	send_user_sigtrap(TRAP_BRKPT);
 	return 0;
 }
 
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 917d98108b3f..6f2f37743d3b 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -30,6 +30,7 @@
 #include <asm/cache.h>
 #include <asm/cputype.h>
 #include <asm/kernel-pgtable.h>
+#include <asm/kvm_arm.h>
 #include <asm/memory.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
@@ -464,9 +465,27 @@ CPU_LE(	bic	x0, x0, #(3 << 24)	)	// Clear the EE and E0E bits for EL1
 	isb
 	ret
 
+2:
+#ifdef CONFIG_ARM64_VHE
+	/*
+	 * Check for VHE being present. For the rest of the EL2 setup,
+	 * x2 being non-zero indicates that we do have VHE, and that the
+	 * kernel is intended to run at EL2.
+	 */
+	mrs	x2, id_aa64mmfr1_el1
+	ubfx	x2, x2, #8, #4
+#else
+	mov	x2, xzr
+#endif
+
 	/* Hyp configuration. */
-2:	mov	x0, #(1 << 31)			// 64-bit EL1
+	mov	x0, #HCR_RW			// 64-bit EL1
+	cbz	x2, set_hcr
+	orr	x0, x0, #HCR_TGE		// Enable Host Extensions
+	orr	x0, x0, #HCR_E2H
+set_hcr:
 	msr	hcr_el2, x0
+	isb
 
 	/* Generic timers. */
 	mrs	x0, cnthctl_el2
@@ -526,6 +545,13 @@ CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 	/* Stage-2 translation */
 	msr	vttbr_el2, xzr
 
+	cbz	x2, install_el2_stub
+
+	mov	w20, #BOOT_CPU_MODE_EL2		// This CPU booted in EL2
+	isb
+	ret
+
+install_el2_stub:
 	/* Hypervisor stub */
 	adrp	x0, __hyp_stub_vectors
 	add	x0, x0, #:lo12:__hyp_stub_vectors
diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h
index 999633bd7294..352f7abd91c9 100644
--- a/arch/arm64/kernel/image.h
+++ b/arch/arm64/kernel/image.h
@@ -89,6 +89,7 @@ __efistub_memcpy		= KALLSYMS_HIDE(__pi_memcpy);
 __efistub_memmove		= KALLSYMS_HIDE(__pi_memmove);
 __efistub_memset		= KALLSYMS_HIDE(__pi_memset);
 __efistub_strlen		= KALLSYMS_HIDE(__pi_strlen);
+__efistub_strnlen		= KALLSYMS_HIDE(__pi_strnlen);
 __efistub_strcmp		= KALLSYMS_HIDE(__pi_strcmp);
 __efistub_strncmp		= KALLSYMS_HIDE(__pi_strncmp);
 __efistub___flush_dcache_area	= KALLSYMS_HIDE(__pi___flush_dcache_area);
diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c
index b3d098bd34aa..c72de668e1d4 100644
--- a/arch/arm64/kernel/pci.c
+++ b/arch/arm64/kernel/pci.c
@@ -19,8 +19,6 @@
 #include <linux/of_platform.h>
 #include <linux/slab.h>
 
-#include <asm/pci-bridge.h>
-
 /*
  * Called after each bus is probed, but before its children are examined
  */
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index f7ab14c4d5df..1b52269ffa87 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -20,6 +20,7 @@
  */
 
 #include <asm/irq_regs.h>
+#include <asm/virt.h>
 
 #include <linux/of.h>
 #include <linux/perf/arm_pmu.h>
@@ -691,9 +692,12 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 
 	if (attr->exclude_idle)
 		return -EPERM;
+	if (is_kernel_in_hyp_mode() &&
+	    attr->exclude_kernel != attr->exclude_hv)
+		return -EINVAL;
 	if (attr->exclude_user)
 		config_base |= ARMV8_EXCLUDE_EL0;
-	if (attr->exclude_kernel)
+	if (!is_kernel_in_hyp_mode() && attr->exclude_kernel)
 		config_base |= ARMV8_EXCLUDE_EL1;
 	if (!attr->exclude_hv)
 		config_base |= ARMV8_INCLUDE_EL2;
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 8119479147db..450987d99b9b 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -73,13 +73,13 @@ static struct resource mem_res[] = {
 		.name = "Kernel code",
 		.start = 0,
 		.end = 0,
-		.flags = IORESOURCE_MEM
+		.flags = IORESOURCE_SYSTEM_RAM
 	},
 	{
 		.name = "Kernel data",
 		.start = 0,
 		.end = 0,
-		.flags = IORESOURCE_MEM
+		.flags = IORESOURCE_SYSTEM_RAM
 	}
 };
 
@@ -210,7 +210,7 @@ static void __init request_standard_resources(void)
 		res->name  = "System RAM";
 		res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
 		res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
-		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+		res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
 		request_resource(&iomem_resource, res);
 
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index e33fe33876ab..fd10eb663868 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -145,6 +145,10 @@ ENTRY(cpu_resume_mmu)
 ENDPROC(cpu_resume_mmu)
 	.popsection
 cpu_resume_after_mmu:
+#ifdef CONFIG_KASAN
+	mov	x0, sp
+	bl	kasan_unpoison_remaining_stack
+#endif
 	mov	x0, #0			// return zero on success
 	ldp	x19, x20, [sp, #16]
 	ldp	x21, x22, [sp, #32]
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index b1adc51b2c2e..460765799c64 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -195,7 +195,7 @@ asmlinkage void secondary_start_kernel(void)
 	/*
 	 * OK, it's off to the idle thread for us
 	 */
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 4fad9787ab46..d9751a4769e7 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -44,14 +44,13 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 	unsigned long irq_stack_ptr;
 
 	/*
-	 * Use raw_smp_processor_id() to avoid false-positives from
-	 * CONFIG_DEBUG_PREEMPT. get_wchan() calls unwind_frame() on sleeping
-	 * task stacks, we can be pre-empted in this case, so
-	 * {raw_,}smp_processor_id() may give us the wrong value. Sleeping
-	 * tasks can't ever be on an interrupt stack, so regardless of cpu,
-	 * the checks will always fail.
+	 * Switching between stacks is valid when tracing current and in
+	 * non-preemptible context.
 	 */
-	irq_stack_ptr = IRQ_STACK_PTR(raw_smp_processor_id());
+	if (tsk == current && !preemptible())
+		irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id());
+	else
+		irq_stack_ptr = 0;
 
 	low  = frame->sp;
 	/* irq stacks are not THREAD_SIZE aligned */
@@ -64,8 +63,8 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 		return -EINVAL;
 
 	frame->sp = fp + 0x10;
-	frame->fp = *(unsigned long *)(fp);
-	frame->pc = *(unsigned long *)(fp + 8);
+	frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
+	frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8));
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	if (tsk && tsk->ret_stack &&
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index cbedd724f48e..c5392081b49b 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -146,9 +146,18 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
 static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 {
 	struct stackframe frame;
-	unsigned long irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id());
+	unsigned long irq_stack_ptr;
 	int skip;
 
+	/*
+	 * Switching between stacks is valid when tracing current and in
+	 * non-preemptible context.
+	 */
+	if (tsk == current && !preemptible())
+		irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id());
+	else
+		irq_stack_ptr = 0;
+
 	pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
 
 	if (!tsk)
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index a5272c07d1cb..de7450df7629 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -36,6 +36,7 @@ config KVM
 	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_IRQFD
 	select KVM_ARM_VGIC_V3
+	select KVM_ARM_PMU if HW_PERF_EVENTS
 	---help---
 	  Support hosting virtualized guest machines.
 	  We don't support KVM with 16K page tables yet, due to the multiple
@@ -48,6 +49,12 @@ config KVM_ARM_HOST
 	---help---
 	  Provides host support for ARM processors.
 
+config KVM_ARM_PMU
+	bool
+	---help---
+	  Adds support for a virtual Performance Monitoring Unit (PMU) in
+	  virtual machines.
+
 source drivers/vhost/Kconfig
 
 endif # VIRTUALIZATION
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index caee9ee8e12a..122cff482ac4 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -26,3 +26,4 @@ kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2-emul.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3-emul.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arch_timer.o
+kvm-$(CONFIG_KVM_ARM_PMU) += $(KVM)/arm/pmu.o
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index fcb778899a38..32fad75bb9ff 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -194,7 +194,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	u64 val;
 
 	val = kvm_arm_timer_get_reg(vcpu, reg->id);
-	return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id));
+	return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0;
 }
 
 /**
@@ -380,3 +380,54 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	}
 	return 0;
 }
+
+int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
+			       struct kvm_device_attr *attr)
+{
+	int ret;
+
+	switch (attr->group) {
+	case KVM_ARM_VCPU_PMU_V3_CTRL:
+		ret = kvm_arm_pmu_v3_set_attr(vcpu, attr);
+		break;
+	default:
+		ret = -ENXIO;
+		break;
+	}
+
+	return ret;
+}
+
+int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
+			       struct kvm_device_attr *attr)
+{
+	int ret;
+
+	switch (attr->group) {
+	case KVM_ARM_VCPU_PMU_V3_CTRL:
+		ret = kvm_arm_pmu_v3_get_attr(vcpu, attr);
+		break;
+	default:
+		ret = -ENXIO;
+		break;
+	}
+
+	return ret;
+}
+
+int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
+			       struct kvm_device_attr *attr)
+{
+	int ret;
+
+	switch (attr->group) {
+	case KVM_ARM_VCPU_PMU_V3_CTRL:
+		ret = kvm_arm_pmu_v3_has_attr(vcpu, attr);
+		break;
+	default:
+		ret = -ENXIO;
+		break;
+	}
+
+	return ret;
+}
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 3e568dcd907b..7d8747c6427c 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -64,7 +64,7 @@ __do_hyp_init:
 	mrs	x4, tcr_el1
 	ldr	x5, =TCR_EL2_MASK
 	and	x4, x4, x5
-	ldr	x5, =TCR_EL2_FLAGS
+	mov	x5, #TCR_EL2_RES1
 	orr	x4, x4, x5
 
 #ifndef CONFIG_ARM64_VA_BITS_48
@@ -85,25 +85,14 @@ __do_hyp_init:
 	ldr_l	x5, idmap_t0sz
 	bfi	x4, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
 #endif
-	msr	tcr_el2, x4
-
-	ldr	x4, =VTCR_EL2_FLAGS
 	/*
 	 * Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS bits in
-	 * VTCR_EL2.
+	 * TCR_EL2.
 	 */
 	mrs	x5, ID_AA64MMFR0_EL1
 	bfi	x4, x5, #16, #3
-	/*
-	 * Read the VMIDBits bits from ID_AA64MMFR1_EL1 and set the VS bit in
-	 * VTCR_EL2.
-	 */
-	mrs	x5, ID_AA64MMFR1_EL1
-	ubfx	x5, x5, #5, #1
-	lsl	x5, x5, #VTCR_EL2_VS
-	orr	x4, x4, x5
 
-	msr	vtcr_el2, x4
+	msr	tcr_el2, x4
 
 	mrs	x4, mair_el1
 	msr	mair_el2, x4
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 0ccdcbbef3c2..0689a74e6ba0 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -17,7 +17,9 @@
 
 #include <linux/linkage.h>
 
+#include <asm/alternative.h>
 #include <asm/assembler.h>
+#include <asm/cpufeature.h>
 
 /*
  * u64 kvm_call_hyp(void *hypfn, ...);
@@ -38,6 +40,11 @@
  * arch/arm64/kernel/hyp_stub.S.
  */
 ENTRY(kvm_call_hyp)
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN	
 	hvc	#0
 	ret
+alternative_else
+	b	__vhe_hyp_call
+	nop
+alternative_endif
 ENDPROC(kvm_call_hyp)
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 826032bc3945..b6a8fc5ad1af 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -2,9 +2,12 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
-obj-$(CONFIG_KVM_ARM_HOST) += vgic-v2-sr.o
+KVM=../../../../virt/kvm
+
+obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
+obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o
+
 obj-$(CONFIG_KVM_ARM_HOST) += vgic-v3-sr.o
-obj-$(CONFIG_KVM_ARM_HOST) += timer-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += sysreg-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += debug-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += entry.o
@@ -12,3 +15,4 @@ obj-$(CONFIG_KVM_ARM_HOST) += switch.o
 obj-$(CONFIG_KVM_ARM_HOST) += fpsimd.o
 obj-$(CONFIG_KVM_ARM_HOST) += tlb.o
 obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o
+obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o
diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c
index c9c1e97501a9..053cf8b057c1 100644
--- a/arch/arm64/kvm/hyp/debug-sr.c
+++ b/arch/arm64/kvm/hyp/debug-sr.c
@@ -19,9 +19,7 @@
 #include <linux/kvm_host.h>
 
 #include <asm/kvm_asm.h>
-#include <asm/kvm_mmu.h>
-
-#include "hyp.h"
+#include <asm/kvm_hyp.h>
 
 #define read_debug(r,n)		read_sysreg(r##n##_el1)
 #define write_debug(v,r,n)	write_sysreg(v, r##n##_el1)
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index fd0fbe9b7e6a..ce9e5e5f28cf 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -130,9 +130,15 @@ ENDPROC(__guest_exit)
 ENTRY(__fpsimd_guest_restore)
 	stp	x4, lr, [sp, #-16]!
 
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
 	mrs	x2, cptr_el2
 	bic	x2, x2, #CPTR_EL2_TFP
 	msr	cptr_el2, x2
+alternative_else
+	mrs	x2, cpacr_el1
+	orr	x2, x2, #CPACR_EL1_FPEN
+	msr	cpacr_el1, x2
+alternative_endif
 	isb
 
 	mrs	x3, tpidr_el2
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 93e8d983c0bd..3488894397ff 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -19,7 +19,6 @@
 
 #include <asm/alternative.h>
 #include <asm/assembler.h>
-#include <asm/asm-offsets.h>
 #include <asm/cpufeature.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
@@ -38,10 +37,42 @@
 	ldp	x0, x1, [sp], #16
 .endm
 
+.macro do_el2_call
+	/*
+	 * Shuffle the parameters before calling the function
+	 * pointed to in x0. Assumes parameters in x[1,2,3].
+	 */
+	sub	sp, sp, #16
+	str	lr, [sp]
+	mov	lr, x0
+	mov	x0, x1
+	mov	x1, x2
+	mov	x2, x3
+	blr	lr
+	ldr	lr, [sp]
+	add	sp, sp, #16
+.endm
+
+ENTRY(__vhe_hyp_call)
+	do_el2_call
+	/*
+	 * We used to rely on having an exception return to get
+	 * an implicit isb. In the E2H case, we don't have it anymore.
+	 * rather than changing all the leaf functions, just do it here
+	 * before returning to the rest of the kernel.
+	 */
+	isb
+	ret
+ENDPROC(__vhe_hyp_call)
+	
 el1_sync:				// Guest trapped into EL2
 	save_x0_to_x3
 
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
 	mrs	x1, esr_el2
+alternative_else
+	mrs	x1, esr_el1
+alternative_endif
 	lsr	x2, x1, #ESR_ELx_EC_SHIFT
 
 	cmp	x2, #ESR_ELx_EC_HVC64
@@ -58,19 +89,13 @@ el1_sync:				// Guest trapped into EL2
 	mrs	x0, vbar_el2
 	b	2f
 
-1:	stp	lr, xzr, [sp, #-16]!
-
+1:
 	/*
-	 * Compute the function address in EL2, and shuffle the parameters.
+	 * Perform the EL2 call
 	 */
 	kern_hyp_va	x0
-	mov	lr, x0
-	mov	x0, x1
-	mov	x1, x2
-	mov	x2, x3
-	blr	lr
+	do_el2_call
 
-	ldp	lr, xzr, [sp], #16
 2:	eret
 
 el1_trap:
@@ -83,72 +108,10 @@ el1_trap:
 	cmp	x2, #ESR_ELx_EC_FP_ASIMD
 	b.eq	__fpsimd_guest_restore
 
-	cmp	x2, #ESR_ELx_EC_DABT_LOW
-	mov	x0, #ESR_ELx_EC_IABT_LOW
-	ccmp	x2, x0, #4, ne
-	b.ne	1f		// Not an abort we care about
-
-	/* This is an abort. Check for permission fault */
-alternative_if_not ARM64_WORKAROUND_834220
-	and	x2, x1, #ESR_ELx_FSC_TYPE
-	cmp	x2, #FSC_PERM
-	b.ne	1f		// Not a permission fault
-alternative_else
-	nop			// Use the permission fault path to
-	nop			// check for a valid S1 translation,
-	nop			// regardless of the ESR value.
-alternative_endif
-
-	/*
-	 * Check for Stage-1 page table walk, which is guaranteed
-	 * to give a valid HPFAR_EL2.
-	 */
-	tbnz	x1, #7, 1f	// S1PTW is set
-
-	/* Preserve PAR_EL1 */
-	mrs	x3, par_el1
-	stp	x3, xzr, [sp, #-16]!
-
-	/*
-	 * Permission fault, HPFAR_EL2 is invalid.
-	 * Resolve the IPA the hard way using the guest VA.
-	 * Stage-1 translation already validated the memory access rights.
-	 * As such, we can use the EL1 translation regime, and don't have
-	 * to distinguish between EL0 and EL1 access.
-	 */
-	mrs	x2, far_el2
-	at	s1e1r, x2
-	isb
-
-	/* Read result */
-	mrs	x3, par_el1
-	ldp	x0, xzr, [sp], #16	// Restore PAR_EL1 from the stack
-	msr	par_el1, x0
-	tbnz	x3, #0, 3f		// Bail out if we failed the translation
-	ubfx	x3, x3, #12, #36	// Extract IPA
-	lsl	x3, x3, #4		// and present it like HPFAR
-	b	2f
-
-1:	mrs	x3, hpfar_el2
-	mrs	x2, far_el2
-
-2:	mrs	x0, tpidr_el2
-	str	w1, [x0, #VCPU_ESR_EL2]
-	str	x2, [x0, #VCPU_FAR_EL2]
-	str	x3, [x0, #VCPU_HPFAR_EL2]
-
+	mrs	x0, tpidr_el2
 	mov	x1, #ARM_EXCEPTION_TRAP
 	b	__guest_exit
 
-	/*
-	 * Translation failed. Just return to the guest and
-	 * let it fault again. Another CPU is probably playing
-	 * behind our back.
-	 */
-3:	restore_x0_to_x3
-
-	eret
-
 el1_irq:
 	save_x0_to_x3
 	mrs	x0, tpidr_el2
diff --git a/arch/arm64/kvm/hyp/hyp.h b/arch/arm64/kvm/hyp/hyp.h
deleted file mode 100644
index fb275178b6af..000000000000
--- a/arch/arm64/kvm/hyp/hyp.h
+++ /dev/null
@@ -1,90 +0,0 @@
-/*
- * Copyright (C) 2015 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef __ARM64_KVM_HYP_H__
-#define __ARM64_KVM_HYP_H__
-
-#include <linux/compiler.h>
-#include <linux/kvm_host.h>
-#include <asm/kvm_mmu.h>
-#include <asm/sysreg.h>
-
-#define __hyp_text __section(.hyp.text) notrace
-
-#define kern_hyp_va(v) (typeof(v))((unsigned long)(v) & HYP_PAGE_OFFSET_MASK)
-#define hyp_kern_va(v) (typeof(v))((unsigned long)(v) - HYP_PAGE_OFFSET \
-						      + PAGE_OFFSET)
-
-/**
- * hyp_alternate_select - Generates patchable code sequences that are
- * used to switch between two implementations of a function, depending
- * on the availability of a feature.
- *
- * @fname: a symbol name that will be defined as a function returning a
- * function pointer whose type will match @orig and @alt
- * @orig: A pointer to the default function, as returned by @fname when
- * @cond doesn't hold
- * @alt: A pointer to the alternate function, as returned by @fname
- * when @cond holds
- * @cond: a CPU feature (as described in asm/cpufeature.h)
- */
-#define hyp_alternate_select(fname, orig, alt, cond)			\
-typeof(orig) * __hyp_text fname(void)					\
-{									\
-	typeof(alt) *val = orig;					\
-	asm volatile(ALTERNATIVE("nop		\n",			\
-				 "mov	%0, %1	\n",			\
-				 cond)					\
-		     : "+r" (val) : "r" (alt));				\
-	return val;							\
-}
-
-void __vgic_v2_save_state(struct kvm_vcpu *vcpu);
-void __vgic_v2_restore_state(struct kvm_vcpu *vcpu);
-
-void __vgic_v3_save_state(struct kvm_vcpu *vcpu);
-void __vgic_v3_restore_state(struct kvm_vcpu *vcpu);
-
-void __timer_save_state(struct kvm_vcpu *vcpu);
-void __timer_restore_state(struct kvm_vcpu *vcpu);
-
-void __sysreg_save_state(struct kvm_cpu_context *ctxt);
-void __sysreg_restore_state(struct kvm_cpu_context *ctxt);
-void __sysreg32_save_state(struct kvm_vcpu *vcpu);
-void __sysreg32_restore_state(struct kvm_vcpu *vcpu);
-
-void __debug_save_state(struct kvm_vcpu *vcpu,
-			struct kvm_guest_debug_arch *dbg,
-			struct kvm_cpu_context *ctxt);
-void __debug_restore_state(struct kvm_vcpu *vcpu,
-			   struct kvm_guest_debug_arch *dbg,
-			   struct kvm_cpu_context *ctxt);
-void __debug_cond_save_host_state(struct kvm_vcpu *vcpu);
-void __debug_cond_restore_host_state(struct kvm_vcpu *vcpu);
-
-void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
-void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
-static inline bool __fpsimd_enabled(void)
-{
-	return !(read_sysreg(cptr_el2) & CPTR_EL2_TFP);
-}
-
-u64 __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host_ctxt);
-void __noreturn __hyp_do_panic(unsigned long, ...);
-
-#endif /* __ARM64_KVM_HYP_H__ */
-
diff --git a/arch/arm64/kvm/hyp/s2-setup.c b/arch/arm64/kvm/hyp/s2-setup.c
new file mode 100644
index 000000000000..bfc54fd82797
--- /dev/null
+++ b/arch/arm64/kvm/hyp/s2-setup.c
@@ -0,0 +1,43 @@
+/*
+ * Copyright (C) 2016 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/types.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_hyp.h>
+
+void __hyp_text __init_stage2_translation(void)
+{
+	u64 val = VTCR_EL2_FLAGS;
+	u64 tmp;
+
+	/*
+	 * Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS
+	 * bits in VTCR_EL2. Amusingly, the PARange is 4 bits, while
+	 * PS is only 3. Fortunately, bit 19 is RES0 in VTCR_EL2...
+	 */
+	val |= (read_sysreg(id_aa64mmfr0_el1) & 7) << 16;
+
+	/*
+	 * Read the VMIDBits bits from ID_AA64MMFR1_EL1 and set the VS
+	 * bit in VTCR_EL2.
+	 */
+	tmp = (read_sysreg(id_aa64mmfr1_el1) >> 4) & 0xf;
+	val |= (tmp == 2) ? VTCR_EL2_VS : 0;
+
+	write_sysreg(val, vtcr_el2);
+}
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index ca8f5a5e2f96..437cfad5e3d8 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -15,7 +15,53 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "hyp.h"
+#include <linux/types.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_hyp.h>
+
+static bool __hyp_text __fpsimd_enabled_nvhe(void)
+{
+	return !(read_sysreg(cptr_el2) & CPTR_EL2_TFP);
+}
+
+static bool __hyp_text __fpsimd_enabled_vhe(void)
+{
+	return !!(read_sysreg(cpacr_el1) & CPACR_EL1_FPEN);
+}
+
+static hyp_alternate_select(__fpsimd_is_enabled,
+			    __fpsimd_enabled_nvhe, __fpsimd_enabled_vhe,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
+bool __hyp_text __fpsimd_enabled(void)
+{
+	return __fpsimd_is_enabled()();
+}
+
+static void __hyp_text __activate_traps_vhe(void)
+{
+	u64 val;
+
+	val = read_sysreg(cpacr_el1);
+	val |= CPACR_EL1_TTA;
+	val &= ~CPACR_EL1_FPEN;
+	write_sysreg(val, cpacr_el1);
+
+	write_sysreg(__kvm_hyp_vector, vbar_el1);
+}
+
+static void __hyp_text __activate_traps_nvhe(void)
+{
+	u64 val;
+
+	val = CPTR_EL2_DEFAULT;
+	val |= CPTR_EL2_TTA | CPTR_EL2_TFP;
+	write_sysreg(val, cptr_el2);
+}
+
+static hyp_alternate_select(__activate_traps_arch,
+			    __activate_traps_nvhe, __activate_traps_vhe,
+			    ARM64_HAS_VIRT_HOST_EXTN);
 
 static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 {
@@ -36,16 +82,37 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 	write_sysreg(val, hcr_el2);
 	/* Trap on AArch32 cp15 c15 accesses (EL1 or EL0) */
 	write_sysreg(1 << 15, hstr_el2);
-	write_sysreg(CPTR_EL2_TTA | CPTR_EL2_TFP, cptr_el2);
+	/* Make sure we trap PMU access from EL0 to EL2 */
+	write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
 	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
+	__activate_traps_arch()();
 }
 
-static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
+static void __hyp_text __deactivate_traps_vhe(void)
+{
+	extern char vectors[];	/* kernel exception vectors */
+
+	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+	write_sysreg(CPACR_EL1_FPEN, cpacr_el1);
+	write_sysreg(vectors, vbar_el1);
+}
+
+static void __hyp_text __deactivate_traps_nvhe(void)
 {
 	write_sysreg(HCR_RW, hcr_el2);
+	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
+}
+
+static hyp_alternate_select(__deactivate_traps_arch,
+			    __deactivate_traps_nvhe, __deactivate_traps_vhe,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
+static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
+{
+	__deactivate_traps_arch()();
 	write_sysreg(0, hstr_el2);
 	write_sysreg(read_sysreg(mdcr_el2) & MDCR_EL2_HPMN_MASK, mdcr_el2);
-	write_sysreg(0, cptr_el2);
+	write_sysreg(0, pmuserenr_el0);
 }
 
 static void __hyp_text __activate_vm(struct kvm_vcpu *vcpu)
@@ -85,6 +152,86 @@ static void __hyp_text __vgic_restore_state(struct kvm_vcpu *vcpu)
 	__vgic_call_restore_state()(vcpu);
 }
 
+static bool __hyp_text __true_value(void)
+{
+	return true;
+}
+
+static bool __hyp_text __false_value(void)
+{
+	return false;
+}
+
+static hyp_alternate_select(__check_arm_834220,
+			    __false_value, __true_value,
+			    ARM64_WORKAROUND_834220);
+
+static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
+{
+	u64 par, tmp;
+
+	/*
+	 * Resolve the IPA the hard way using the guest VA.
+	 *
+	 * Stage-1 translation already validated the memory access
+	 * rights. As such, we can use the EL1 translation regime, and
+	 * don't have to distinguish between EL0 and EL1 access.
+	 *
+	 * We do need to save/restore PAR_EL1 though, as we haven't
+	 * saved the guest context yet, and we may return early...
+	 */
+	par = read_sysreg(par_el1);
+	asm volatile("at s1e1r, %0" : : "r" (far));
+	isb();
+
+	tmp = read_sysreg(par_el1);
+	write_sysreg(par, par_el1);
+
+	if (unlikely(tmp & 1))
+		return false; /* Translation failed, back to guest */
+
+	/* Convert PAR to HPFAR format */
+	*hpfar = ((tmp >> 12) & ((1UL << 36) - 1)) << 4;
+	return true;
+}
+
+static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
+{
+	u64 esr = read_sysreg_el2(esr);
+	u8 ec = esr >> ESR_ELx_EC_SHIFT;
+	u64 hpfar, far;
+
+	vcpu->arch.fault.esr_el2 = esr;
+
+	if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
+		return true;
+
+	far = read_sysreg_el2(far);
+
+	/*
+	 * The HPFAR can be invalid if the stage 2 fault did not
+	 * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
+	 * bit is clear) and one of the two following cases are true:
+	 *   1. The fault was due to a permission fault
+	 *   2. The processor carries errata 834220
+	 *
+	 * Therefore, for all non S1PTW faults where we either have a
+	 * permission fault or the errata workaround is enabled, we
+	 * resolve the IPA using the AT instruction.
+	 */
+	if (!(esr & ESR_ELx_S1PTW) &&
+	    (__check_arm_834220()() || (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+		if (!__translate_far_to_hpfar(far, &hpfar))
+			return false;
+	} else {
+		hpfar = read_sysreg(hpfar_el2);
+	}
+
+	vcpu->arch.fault.far_el2 = far;
+	vcpu->arch.fault.hpfar_el2 = hpfar;
+	return true;
+}
+
 static int __hyp_text __guest_run(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
@@ -98,7 +245,7 @@ static int __hyp_text __guest_run(struct kvm_vcpu *vcpu)
 	host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
 	guest_ctxt = &vcpu->arch.ctxt;
 
-	__sysreg_save_state(host_ctxt);
+	__sysreg_save_host_state(host_ctxt);
 	__debug_cond_save_host_state(vcpu);
 
 	__activate_traps(vcpu);
@@ -112,16 +259,20 @@ static int __hyp_text __guest_run(struct kvm_vcpu *vcpu)
 	 * to Cortex-A57 erratum #852523.
 	 */
 	__sysreg32_restore_state(vcpu);
-	__sysreg_restore_state(guest_ctxt);
+	__sysreg_restore_guest_state(guest_ctxt);
 	__debug_restore_state(vcpu, kern_hyp_va(vcpu->arch.debug_ptr), guest_ctxt);
 
 	/* Jump in the fire! */
+again:
 	exit_code = __guest_enter(vcpu, host_ctxt);
 	/* And we're baaack! */
 
+	if (exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu))
+		goto again;
+
 	fp_enabled = __fpsimd_enabled();
 
-	__sysreg_save_state(guest_ctxt);
+	__sysreg_save_guest_state(guest_ctxt);
 	__sysreg32_save_state(vcpu);
 	__timer_save_state(vcpu);
 	__vgic_save_state(vcpu);
@@ -129,7 +280,7 @@ static int __hyp_text __guest_run(struct kvm_vcpu *vcpu)
 	__deactivate_traps(vcpu);
 	__deactivate_vm(vcpu);
 
-	__sysreg_restore_state(host_ctxt);
+	__sysreg_restore_host_state(host_ctxt);
 
 	if (fp_enabled) {
 		__fpsimd_save_state(&guest_ctxt->gp_regs.fp_regs);
@@ -146,11 +297,34 @@ __alias(__guest_run) int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
 static const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n";
 
-void __hyp_text __noreturn __hyp_panic(void)
+static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par)
 {
 	unsigned long str_va = (unsigned long)__hyp_panic_string;
-	u64 spsr = read_sysreg(spsr_el2);
-	u64 elr = read_sysreg(elr_el2);
+
+	__hyp_do_panic(hyp_kern_va(str_va),
+		       spsr,  elr,
+		       read_sysreg(esr_el2),   read_sysreg_el2(far),
+		       read_sysreg(hpfar_el2), par,
+		       (void *)read_sysreg(tpidr_el2));
+}
+
+static void __hyp_text __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par)
+{
+	panic(__hyp_panic_string,
+	      spsr,  elr,
+	      read_sysreg_el2(esr),   read_sysreg_el2(far),
+	      read_sysreg(hpfar_el2), par,
+	      (void *)read_sysreg(tpidr_el2));
+}
+
+static hyp_alternate_select(__hyp_call_panic,
+			    __hyp_call_panic_nvhe, __hyp_call_panic_vhe,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
+void __hyp_text __noreturn __hyp_panic(void)
+{
+	u64 spsr = read_sysreg_el2(spsr);
+	u64 elr = read_sysreg_el2(elr);
 	u64 par = read_sysreg(par_el1);
 
 	if (read_sysreg(vttbr_el2)) {
@@ -161,15 +335,11 @@ void __hyp_text __noreturn __hyp_panic(void)
 		host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
 		__deactivate_traps(vcpu);
 		__deactivate_vm(vcpu);
-		__sysreg_restore_state(host_ctxt);
+		__sysreg_restore_host_state(host_ctxt);
 	}
 
 	/* Call panic for real */
-	__hyp_do_panic(hyp_kern_va(str_va),
-		       spsr,  elr,
-		       read_sysreg(esr_el2),   read_sysreg(far_el2),
-		       read_sysreg(hpfar_el2), par,
-		       (void *)read_sysreg(tpidr_el2));
+	__hyp_call_panic()(spsr, elr, par);
 
 	unreachable();
 }
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 425630980229..0f7c40eb3f53 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -19,75 +19,122 @@
 #include <linux/kvm_host.h>
 
 #include <asm/kvm_asm.h>
-#include <asm/kvm_mmu.h>
+#include <asm/kvm_hyp.h>
 
-#include "hyp.h"
+/* Yes, this does nothing, on purpose */
+static void __hyp_text __sysreg_do_nothing(struct kvm_cpu_context *ctxt) { }
 
-/* ctxt is already in the HYP VA space */
-void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
+/*
+ * Non-VHE: Both host and guest must save everything.
+ *
+ * VHE: Host must save tpidr*_el[01], actlr_el1, sp0, pc, pstate, and
+ * guest must save everything.
+ */
+
+static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
 {
-	ctxt->sys_regs[MPIDR_EL1]	= read_sysreg(vmpidr_el2);
-	ctxt->sys_regs[CSSELR_EL1]	= read_sysreg(csselr_el1);
-	ctxt->sys_regs[SCTLR_EL1]	= read_sysreg(sctlr_el1);
 	ctxt->sys_regs[ACTLR_EL1]	= read_sysreg(actlr_el1);
-	ctxt->sys_regs[CPACR_EL1]	= read_sysreg(cpacr_el1);
-	ctxt->sys_regs[TTBR0_EL1]	= read_sysreg(ttbr0_el1);
-	ctxt->sys_regs[TTBR1_EL1]	= read_sysreg(ttbr1_el1);
-	ctxt->sys_regs[TCR_EL1]		= read_sysreg(tcr_el1);
-	ctxt->sys_regs[ESR_EL1]		= read_sysreg(esr_el1);
-	ctxt->sys_regs[AFSR0_EL1]	= read_sysreg(afsr0_el1);
-	ctxt->sys_regs[AFSR1_EL1]	= read_sysreg(afsr1_el1);
-	ctxt->sys_regs[FAR_EL1]		= read_sysreg(far_el1);
-	ctxt->sys_regs[MAIR_EL1]	= read_sysreg(mair_el1);
-	ctxt->sys_regs[VBAR_EL1]	= read_sysreg(vbar_el1);
-	ctxt->sys_regs[CONTEXTIDR_EL1]	= read_sysreg(contextidr_el1);
 	ctxt->sys_regs[TPIDR_EL0]	= read_sysreg(tpidr_el0);
 	ctxt->sys_regs[TPIDRRO_EL0]	= read_sysreg(tpidrro_el0);
 	ctxt->sys_regs[TPIDR_EL1]	= read_sysreg(tpidr_el1);
-	ctxt->sys_regs[AMAIR_EL1]	= read_sysreg(amair_el1);
-	ctxt->sys_regs[CNTKCTL_EL1]	= read_sysreg(cntkctl_el1);
+	ctxt->gp_regs.regs.sp		= read_sysreg(sp_el0);
+	ctxt->gp_regs.regs.pc		= read_sysreg_el2(elr);
+	ctxt->gp_regs.regs.pstate	= read_sysreg_el2(spsr);
+}
+
+static void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
+{
+	ctxt->sys_regs[MPIDR_EL1]	= read_sysreg(vmpidr_el2);
+	ctxt->sys_regs[CSSELR_EL1]	= read_sysreg(csselr_el1);
+	ctxt->sys_regs[SCTLR_EL1]	= read_sysreg_el1(sctlr);
+	ctxt->sys_regs[CPACR_EL1]	= read_sysreg_el1(cpacr);
+	ctxt->sys_regs[TTBR0_EL1]	= read_sysreg_el1(ttbr0);
+	ctxt->sys_regs[TTBR1_EL1]	= read_sysreg_el1(ttbr1);
+	ctxt->sys_regs[TCR_EL1]		= read_sysreg_el1(tcr);
+	ctxt->sys_regs[ESR_EL1]		= read_sysreg_el1(esr);
+	ctxt->sys_regs[AFSR0_EL1]	= read_sysreg_el1(afsr0);
+	ctxt->sys_regs[AFSR1_EL1]	= read_sysreg_el1(afsr1);
+	ctxt->sys_regs[FAR_EL1]		= read_sysreg_el1(far);
+	ctxt->sys_regs[MAIR_EL1]	= read_sysreg_el1(mair);
+	ctxt->sys_regs[VBAR_EL1]	= read_sysreg_el1(vbar);
+	ctxt->sys_regs[CONTEXTIDR_EL1]	= read_sysreg_el1(contextidr);
+	ctxt->sys_regs[AMAIR_EL1]	= read_sysreg_el1(amair);
+	ctxt->sys_regs[CNTKCTL_EL1]	= read_sysreg_el1(cntkctl);
 	ctxt->sys_regs[PAR_EL1]		= read_sysreg(par_el1);
 	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
 
-	ctxt->gp_regs.regs.sp		= read_sysreg(sp_el0);
-	ctxt->gp_regs.regs.pc		= read_sysreg(elr_el2);
-	ctxt->gp_regs.regs.pstate	= read_sysreg(spsr_el2);
 	ctxt->gp_regs.sp_el1		= read_sysreg(sp_el1);
-	ctxt->gp_regs.elr_el1		= read_sysreg(elr_el1);
-	ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg(spsr_el1);
+	ctxt->gp_regs.elr_el1		= read_sysreg_el1(elr);
+	ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(spsr);
+}
+
+static hyp_alternate_select(__sysreg_call_save_host_state,
+			    __sysreg_save_state, __sysreg_do_nothing,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
+void __hyp_text __sysreg_save_host_state(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_call_save_host_state()(ctxt);
+	__sysreg_save_common_state(ctxt);
+}
+
+void __hyp_text __sysreg_save_guest_state(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_save_state(ctxt);
+	__sysreg_save_common_state(ctxt);
 }
 
-void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt)
+static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
 {
-	write_sysreg(ctxt->sys_regs[MPIDR_EL1],	  vmpidr_el2);
-	write_sysreg(ctxt->sys_regs[CSSELR_EL1],  csselr_el1);
-	write_sysreg(ctxt->sys_regs[SCTLR_EL1],	  sctlr_el1);
 	write_sysreg(ctxt->sys_regs[ACTLR_EL1],	  actlr_el1);
-	write_sysreg(ctxt->sys_regs[CPACR_EL1],	  cpacr_el1);
-	write_sysreg(ctxt->sys_regs[TTBR0_EL1],	  ttbr0_el1);
-	write_sysreg(ctxt->sys_regs[TTBR1_EL1],	  ttbr1_el1);
-	write_sysreg(ctxt->sys_regs[TCR_EL1],	  tcr_el1);
-	write_sysreg(ctxt->sys_regs[ESR_EL1],	  esr_el1);
-	write_sysreg(ctxt->sys_regs[AFSR0_EL1],	  afsr0_el1);
-	write_sysreg(ctxt->sys_regs[AFSR1_EL1],	  afsr1_el1);
-	write_sysreg(ctxt->sys_regs[FAR_EL1],	  far_el1);
-	write_sysreg(ctxt->sys_regs[MAIR_EL1],	  mair_el1);
-	write_sysreg(ctxt->sys_regs[VBAR_EL1],	  vbar_el1);
-	write_sysreg(ctxt->sys_regs[CONTEXTIDR_EL1], contextidr_el1);
 	write_sysreg(ctxt->sys_regs[TPIDR_EL0],	  tpidr_el0);
 	write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0);
 	write_sysreg(ctxt->sys_regs[TPIDR_EL1],	  tpidr_el1);
-	write_sysreg(ctxt->sys_regs[AMAIR_EL1],	  amair_el1);
-	write_sysreg(ctxt->sys_regs[CNTKCTL_EL1], cntkctl_el1);
-	write_sysreg(ctxt->sys_regs[PAR_EL1],	  par_el1);
-	write_sysreg(ctxt->sys_regs[MDSCR_EL1],	  mdscr_el1);
-
-	write_sysreg(ctxt->gp_regs.regs.sp,	sp_el0);
-	write_sysreg(ctxt->gp_regs.regs.pc,	elr_el2);
-	write_sysreg(ctxt->gp_regs.regs.pstate,	spsr_el2);
-	write_sysreg(ctxt->gp_regs.sp_el1,	sp_el1);
-	write_sysreg(ctxt->gp_regs.elr_el1,	elr_el1);
-	write_sysreg(ctxt->gp_regs.spsr[KVM_SPSR_EL1], spsr_el1);
+	write_sysreg(ctxt->gp_regs.regs.sp,	  sp_el0);
+	write_sysreg_el2(ctxt->gp_regs.regs.pc,	  elr);
+	write_sysreg_el2(ctxt->gp_regs.regs.pstate, spsr);
+}
+
+static void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt)
+{
+	write_sysreg(ctxt->sys_regs[MPIDR_EL1],		vmpidr_el2);
+	write_sysreg(ctxt->sys_regs[CSSELR_EL1],	csselr_el1);
+	write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1],	sctlr);
+	write_sysreg_el1(ctxt->sys_regs[CPACR_EL1],	cpacr);
+	write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1],	ttbr0);
+	write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1],	ttbr1);
+	write_sysreg_el1(ctxt->sys_regs[TCR_EL1],	tcr);
+	write_sysreg_el1(ctxt->sys_regs[ESR_EL1],	esr);
+	write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1],	afsr0);
+	write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1],	afsr1);
+	write_sysreg_el1(ctxt->sys_regs[FAR_EL1],	far);
+	write_sysreg_el1(ctxt->sys_regs[MAIR_EL1],	mair);
+	write_sysreg_el1(ctxt->sys_regs[VBAR_EL1],	vbar);
+	write_sysreg_el1(ctxt->sys_regs[CONTEXTIDR_EL1],contextidr);
+	write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1],	amair);
+	write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1], 	cntkctl);
+	write_sysreg(ctxt->sys_regs[PAR_EL1],		par_el1);
+	write_sysreg(ctxt->sys_regs[MDSCR_EL1],		mdscr_el1);
+
+	write_sysreg(ctxt->gp_regs.sp_el1,		sp_el1);
+	write_sysreg_el1(ctxt->gp_regs.elr_el1,		elr);
+	write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],spsr);
+}
+
+static hyp_alternate_select(__sysreg_call_restore_host_state,
+			    __sysreg_restore_state, __sysreg_do_nothing,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
+void __hyp_text __sysreg_restore_host_state(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_call_restore_host_state()(ctxt);
+	__sysreg_restore_common_state(ctxt);
+}
+
+void __hyp_text __sysreg_restore_guest_state(struct kvm_cpu_context *ctxt)
+{
+	__sysreg_restore_state(ctxt);
+	__sysreg_restore_common_state(ctxt);
 }
 
 void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index 2a7e0d838698..be8177cdd3bf 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -15,7 +15,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "hyp.h"
+#include <asm/kvm_hyp.h>
 
 static void __hyp_text __tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
diff --git a/arch/arm64/kvm/hyp/vgic-v2-sr.c b/arch/arm64/kvm/hyp/vgic-v2-sr.c
deleted file mode 100644
index e71761238cfc..000000000000
--- a/arch/arm64/kvm/hyp/vgic-v2-sr.c
+++ /dev/null
@@ -1,84 +0,0 @@
-/*
- * Copyright (C) 2012-2015 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/compiler.h>
-#include <linux/irqchip/arm-gic.h>
-#include <linux/kvm_host.h>
-
-#include <asm/kvm_mmu.h>
-
-#include "hyp.h"
-
-/* vcpu is already in the HYP VA space */
-void __hyp_text __vgic_v2_save_state(struct kvm_vcpu *vcpu)
-{
-	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
-	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
-	struct vgic_dist *vgic = &kvm->arch.vgic;
-	void __iomem *base = kern_hyp_va(vgic->vctrl_base);
-	u32 eisr0, eisr1, elrsr0, elrsr1;
-	int i, nr_lr;
-
-	if (!base)
-		return;
-
-	nr_lr = vcpu->arch.vgic_cpu.nr_lr;
-	cpu_if->vgic_vmcr = readl_relaxed(base + GICH_VMCR);
-	cpu_if->vgic_misr = readl_relaxed(base + GICH_MISR);
-	eisr0  = readl_relaxed(base + GICH_EISR0);
-	elrsr0 = readl_relaxed(base + GICH_ELRSR0);
-	if (unlikely(nr_lr > 32)) {
-		eisr1  = readl_relaxed(base + GICH_EISR1);
-		elrsr1 = readl_relaxed(base + GICH_ELRSR1);
-	} else {
-		eisr1 = elrsr1 = 0;
-	}
-#ifdef CONFIG_CPU_BIG_ENDIAN
-	cpu_if->vgic_eisr  = ((u64)eisr0 << 32) | eisr1;
-	cpu_if->vgic_elrsr = ((u64)elrsr0 << 32) | elrsr1;
-#else
-	cpu_if->vgic_eisr  = ((u64)eisr1 << 32) | eisr0;
-	cpu_if->vgic_elrsr = ((u64)elrsr1 << 32) | elrsr0;
-#endif
-	cpu_if->vgic_apr    = readl_relaxed(base + GICH_APR);
-
-	writel_relaxed(0, base + GICH_HCR);
-
-	for (i = 0; i < nr_lr; i++)
-		cpu_if->vgic_lr[i] = readl_relaxed(base + GICH_LR0 + (i * 4));
-}
-
-/* vcpu is already in the HYP VA space */
-void __hyp_text __vgic_v2_restore_state(struct kvm_vcpu *vcpu)
-{
-	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
-	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
-	struct vgic_dist *vgic = &kvm->arch.vgic;
-	void __iomem *base = kern_hyp_va(vgic->vctrl_base);
-	int i, nr_lr;
-
-	if (!base)
-		return;
-
-	writel_relaxed(cpu_if->vgic_hcr, base + GICH_HCR);
-	writel_relaxed(cpu_if->vgic_vmcr, base + GICH_VMCR);
-	writel_relaxed(cpu_if->vgic_apr, base + GICH_APR);
-
-	nr_lr = vcpu->arch.vgic_cpu.nr_lr;
-	for (i = 0; i < nr_lr; i++)
-		writel_relaxed(cpu_if->vgic_lr[i], base + GICH_LR0 + (i * 4));
-}
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 9142e082f5f3..fff7cd42b3a3 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -19,9 +19,7 @@
 #include <linux/irqchip/arm-gic-v3.h>
 #include <linux/kvm_host.h>
 
-#include <asm/kvm_mmu.h>
-
-#include "hyp.h"
+#include <asm/kvm_hyp.h>
 
 #define vtr_to_max_lr_idx(v)		((v) & 0xf)
 #define vtr_to_nr_pri_bits(v)		(((u32)(v) >> 29) + 1)
@@ -39,12 +37,133 @@
 		asm volatile("msr_s " __stringify(r) ", %0" : : "r" (__val));\
 	} while (0)
 
-/* vcpu is already in the HYP VA space */
+static u64 __hyp_text __gic_v3_get_lr(unsigned int lr)
+{
+	switch (lr & 0xf) {
+	case 0:
+		return read_gicreg(ICH_LR0_EL2);
+	case 1:
+		return read_gicreg(ICH_LR1_EL2);
+	case 2:
+		return read_gicreg(ICH_LR2_EL2);
+	case 3:
+		return read_gicreg(ICH_LR3_EL2);
+	case 4:
+		return read_gicreg(ICH_LR4_EL2);
+	case 5:
+		return read_gicreg(ICH_LR5_EL2);
+	case 6:
+		return read_gicreg(ICH_LR6_EL2);
+	case 7:
+		return read_gicreg(ICH_LR7_EL2);
+	case 8:
+		return read_gicreg(ICH_LR8_EL2);
+	case 9:
+		return read_gicreg(ICH_LR9_EL2);
+	case 10:
+		return read_gicreg(ICH_LR10_EL2);
+	case 11:
+		return read_gicreg(ICH_LR11_EL2);
+	case 12:
+		return read_gicreg(ICH_LR12_EL2);
+	case 13:
+		return read_gicreg(ICH_LR13_EL2);
+	case 14:
+		return read_gicreg(ICH_LR14_EL2);
+	case 15:
+		return read_gicreg(ICH_LR15_EL2);
+	}
+
+	unreachable();
+}
+
+static void __hyp_text __gic_v3_set_lr(u64 val, int lr)
+{
+	switch (lr & 0xf) {
+	case 0:
+		write_gicreg(val, ICH_LR0_EL2);
+		break;
+	case 1:
+		write_gicreg(val, ICH_LR1_EL2);
+		break;
+	case 2:
+		write_gicreg(val, ICH_LR2_EL2);
+		break;
+	case 3:
+		write_gicreg(val, ICH_LR3_EL2);
+		break;
+	case 4:
+		write_gicreg(val, ICH_LR4_EL2);
+		break;
+	case 5:
+		write_gicreg(val, ICH_LR5_EL2);
+		break;
+	case 6:
+		write_gicreg(val, ICH_LR6_EL2);
+		break;
+	case 7:
+		write_gicreg(val, ICH_LR7_EL2);
+		break;
+	case 8:
+		write_gicreg(val, ICH_LR8_EL2);
+		break;
+	case 9:
+		write_gicreg(val, ICH_LR9_EL2);
+		break;
+	case 10:
+		write_gicreg(val, ICH_LR10_EL2);
+		break;
+	case 11:
+		write_gicreg(val, ICH_LR11_EL2);
+		break;
+	case 12:
+		write_gicreg(val, ICH_LR12_EL2);
+		break;
+	case 13:
+		write_gicreg(val, ICH_LR13_EL2);
+		break;
+	case 14:
+		write_gicreg(val, ICH_LR14_EL2);
+		break;
+	case 15:
+		write_gicreg(val, ICH_LR15_EL2);
+		break;
+	}
+}
+
+static void __hyp_text save_maint_int_state(struct kvm_vcpu *vcpu, int nr_lr)
+{
+	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+	int i;
+	bool expect_mi;
+
+	expect_mi = !!(cpu_if->vgic_hcr & ICH_HCR_UIE);
+
+	for (i = 0; i < nr_lr; i++) {
+		if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
+				continue;
+
+		expect_mi |= (!(cpu_if->vgic_lr[i] & ICH_LR_HW) &&
+			      (cpu_if->vgic_lr[i] & ICH_LR_EOI));
+	}
+
+	if (expect_mi) {
+		cpu_if->vgic_misr  = read_gicreg(ICH_MISR_EL2);
+
+		if (cpu_if->vgic_misr & ICH_MISR_EOI)
+			cpu_if->vgic_eisr = read_gicreg(ICH_EISR_EL2);
+		else
+			cpu_if->vgic_eisr = 0;
+	} else {
+		cpu_if->vgic_misr = 0;
+		cpu_if->vgic_eisr = 0;
+	}
+}
+
 void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 	u64 val;
-	u32 max_lr_idx, nr_pri_bits;
 
 	/*
 	 * Make sure stores to the GIC via the memory mapped interface
@@ -53,68 +172,66 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 	dsb(st);
 
 	cpu_if->vgic_vmcr  = read_gicreg(ICH_VMCR_EL2);
-	cpu_if->vgic_misr  = read_gicreg(ICH_MISR_EL2);
-	cpu_if->vgic_eisr  = read_gicreg(ICH_EISR_EL2);
-	cpu_if->vgic_elrsr = read_gicreg(ICH_ELSR_EL2);
 
-	write_gicreg(0, ICH_HCR_EL2);
-	val = read_gicreg(ICH_VTR_EL2);
-	max_lr_idx = vtr_to_max_lr_idx(val);
-	nr_pri_bits = vtr_to_nr_pri_bits(val);
+	if (vcpu->arch.vgic_cpu.live_lrs) {
+		int i;
+		u32 max_lr_idx, nr_pri_bits;
 
-	switch (max_lr_idx) {
-	case 15:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(15)] = read_gicreg(ICH_LR15_EL2);
-	case 14:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(14)] = read_gicreg(ICH_LR14_EL2);
-	case 13:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(13)] = read_gicreg(ICH_LR13_EL2);
-	case 12:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(12)] = read_gicreg(ICH_LR12_EL2);
-	case 11:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(11)] = read_gicreg(ICH_LR11_EL2);
-	case 10:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(10)] = read_gicreg(ICH_LR10_EL2);
-	case 9:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(9)] = read_gicreg(ICH_LR9_EL2);
-	case 8:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(8)] = read_gicreg(ICH_LR8_EL2);
-	case 7:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(7)] = read_gicreg(ICH_LR7_EL2);
-	case 6:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(6)] = read_gicreg(ICH_LR6_EL2);
-	case 5:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(5)] = read_gicreg(ICH_LR5_EL2);
-	case 4:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(4)] = read_gicreg(ICH_LR4_EL2);
-	case 3:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(3)] = read_gicreg(ICH_LR3_EL2);
-	case 2:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(2)] = read_gicreg(ICH_LR2_EL2);
-	case 1:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(1)] = read_gicreg(ICH_LR1_EL2);
-	case 0:
-		cpu_if->vgic_lr[VGIC_V3_LR_INDEX(0)] = read_gicreg(ICH_LR0_EL2);
-	}
+		cpu_if->vgic_elrsr = read_gicreg(ICH_ELSR_EL2);
 
-	switch (nr_pri_bits) {
-	case 7:
-		cpu_if->vgic_ap0r[3] = read_gicreg(ICH_AP0R3_EL2);
-		cpu_if->vgic_ap0r[2] = read_gicreg(ICH_AP0R2_EL2);
-	case 6:
-		cpu_if->vgic_ap0r[1] = read_gicreg(ICH_AP0R1_EL2);
-	default:
-		cpu_if->vgic_ap0r[0] = read_gicreg(ICH_AP0R0_EL2);
-	}
+		write_gicreg(0, ICH_HCR_EL2);
+		val = read_gicreg(ICH_VTR_EL2);
+		max_lr_idx = vtr_to_max_lr_idx(val);
+		nr_pri_bits = vtr_to_nr_pri_bits(val);
 
-	switch (nr_pri_bits) {
-	case 7:
-		cpu_if->vgic_ap1r[3] = read_gicreg(ICH_AP1R3_EL2);
-		cpu_if->vgic_ap1r[2] = read_gicreg(ICH_AP1R2_EL2);
-	case 6:
-		cpu_if->vgic_ap1r[1] = read_gicreg(ICH_AP1R1_EL2);
-	default:
-		cpu_if->vgic_ap1r[0] = read_gicreg(ICH_AP1R0_EL2);
+		save_maint_int_state(vcpu, max_lr_idx + 1);
+
+		for (i = 0; i <= max_lr_idx; i++) {
+			if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
+				continue;
+
+			if (cpu_if->vgic_elrsr & (1 << i)) {
+				cpu_if->vgic_lr[i] &= ~ICH_LR_STATE;
+				continue;
+			}
+
+			cpu_if->vgic_lr[i] = __gic_v3_get_lr(i);
+			__gic_v3_set_lr(0, i);
+		}
+
+		switch (nr_pri_bits) {
+		case 7:
+			cpu_if->vgic_ap0r[3] = read_gicreg(ICH_AP0R3_EL2);
+			cpu_if->vgic_ap0r[2] = read_gicreg(ICH_AP0R2_EL2);
+		case 6:
+			cpu_if->vgic_ap0r[1] = read_gicreg(ICH_AP0R1_EL2);
+		default:
+			cpu_if->vgic_ap0r[0] = read_gicreg(ICH_AP0R0_EL2);
+		}
+
+		switch (nr_pri_bits) {
+		case 7:
+			cpu_if->vgic_ap1r[3] = read_gicreg(ICH_AP1R3_EL2);
+			cpu_if->vgic_ap1r[2] = read_gicreg(ICH_AP1R2_EL2);
+		case 6:
+			cpu_if->vgic_ap1r[1] = read_gicreg(ICH_AP1R1_EL2);
+		default:
+			cpu_if->vgic_ap1r[0] = read_gicreg(ICH_AP1R0_EL2);
+		}
+
+		vcpu->arch.vgic_cpu.live_lrs = 0;
+	} else {
+		cpu_if->vgic_misr  = 0;
+		cpu_if->vgic_eisr  = 0;
+		cpu_if->vgic_elrsr = 0xffff;
+		cpu_if->vgic_ap0r[0] = 0;
+		cpu_if->vgic_ap0r[1] = 0;
+		cpu_if->vgic_ap0r[2] = 0;
+		cpu_if->vgic_ap0r[3] = 0;
+		cpu_if->vgic_ap1r[0] = 0;
+		cpu_if->vgic_ap1r[1] = 0;
+		cpu_if->vgic_ap1r[2] = 0;
+		cpu_if->vgic_ap1r[3] = 0;
 	}
 
 	val = read_gicreg(ICC_SRE_EL2);
@@ -128,6 +245,8 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 	u64 val;
 	u32 max_lr_idx, nr_pri_bits;
+	u16 live_lrs = 0;
+	int i;
 
 	/*
 	 * VFIQEn is RES1 if ICC_SRE_EL1.SRE is 1. This causes a
@@ -140,66 +259,46 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	write_gicreg(cpu_if->vgic_sre, ICC_SRE_EL1);
 	isb();
 
-	write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
-	write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2);
-
 	val = read_gicreg(ICH_VTR_EL2);
 	max_lr_idx = vtr_to_max_lr_idx(val);
 	nr_pri_bits = vtr_to_nr_pri_bits(val);
 
-	switch (nr_pri_bits) {
-	case 7:
-		 write_gicreg(cpu_if->vgic_ap1r[3], ICH_AP1R3_EL2);
-		 write_gicreg(cpu_if->vgic_ap1r[2], ICH_AP1R2_EL2);
-	case 6:
-		 write_gicreg(cpu_if->vgic_ap1r[1], ICH_AP1R1_EL2);
-	default:
-		 write_gicreg(cpu_if->vgic_ap1r[0], ICH_AP1R0_EL2);
-	}	 	                           
-		 	                           
-	switch (nr_pri_bits) {
-	case 7:
-		 write_gicreg(cpu_if->vgic_ap0r[3], ICH_AP0R3_EL2);
-		 write_gicreg(cpu_if->vgic_ap0r[2], ICH_AP0R2_EL2);
-	case 6:
-		 write_gicreg(cpu_if->vgic_ap0r[1], ICH_AP0R1_EL2);
-	default:
-		 write_gicreg(cpu_if->vgic_ap0r[0], ICH_AP0R0_EL2);
+	for (i = 0; i <= max_lr_idx; i++) {
+		if (cpu_if->vgic_lr[i] & ICH_LR_STATE)
+			live_lrs |= (1 << i);
 	}
 
-	switch (max_lr_idx) {
-	case 15:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(15)], ICH_LR15_EL2);
-	case 14:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(14)], ICH_LR14_EL2);
-	case 13:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(13)], ICH_LR13_EL2);
-	case 12:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(12)], ICH_LR12_EL2);
-	case 11:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(11)], ICH_LR11_EL2);
-	case 10:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(10)], ICH_LR10_EL2);
-	case 9:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(9)], ICH_LR9_EL2);
-	case 8:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(8)], ICH_LR8_EL2);
-	case 7:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(7)], ICH_LR7_EL2);
-	case 6:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(6)], ICH_LR6_EL2);
-	case 5:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(5)], ICH_LR5_EL2);
-	case 4:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(4)], ICH_LR4_EL2);
-	case 3:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(3)], ICH_LR3_EL2);
-	case 2:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(2)], ICH_LR2_EL2);
-	case 1:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(1)], ICH_LR1_EL2);
-	case 0:
-		write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(0)], ICH_LR0_EL2);
+	write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2);
+
+	if (live_lrs) {
+		write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
+
+		switch (nr_pri_bits) {
+		case 7:
+			write_gicreg(cpu_if->vgic_ap0r[3], ICH_AP0R3_EL2);
+			write_gicreg(cpu_if->vgic_ap0r[2], ICH_AP0R2_EL2);
+		case 6:
+			write_gicreg(cpu_if->vgic_ap0r[1], ICH_AP0R1_EL2);
+		default:
+			write_gicreg(cpu_if->vgic_ap0r[0], ICH_AP0R0_EL2);
+		}
+
+		switch (nr_pri_bits) {
+		case 7:
+			write_gicreg(cpu_if->vgic_ap1r[3], ICH_AP1R3_EL2);
+			write_gicreg(cpu_if->vgic_ap1r[2], ICH_AP1R2_EL2);
+		case 6:
+			write_gicreg(cpu_if->vgic_ap1r[1], ICH_AP1R1_EL2);
+		default:
+			write_gicreg(cpu_if->vgic_ap1r[0], ICH_AP1R0_EL2);
+		}
+
+		for (i = 0; i <= max_lr_idx; i++) {
+			if (!(live_lrs & (1 << i)))
+				continue;
+
+			__gic_v3_set_lr(cpu_if->vgic_lr[i], i);
+		}
 	}
 
 	/*
@@ -209,6 +308,7 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	 */
 	isb();
 	dsb(sy);
+	vcpu->arch.vgic_cpu.live_lrs = live_lrs;
 
 	/*
 	 * Prevent the guest from touching the GIC system registers if
@@ -220,6 +320,15 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	}
 }
 
+void __hyp_text __vgic_v3_init_lrs(void)
+{
+	int max_lr_idx = vtr_to_max_lr_idx(read_gicreg(ICH_VTR_EL2));
+	int i;
+
+	for (i = 0; i <= max_lr_idx; i++)
+		__gic_v3_set_lr(0, i);
+}
+
 static u64 __hyp_text __vgic_v3_read_ich_vtr_el2(void)
 {
 	return read_gicreg(ICH_VTR_EL2);
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index 648112e90ed5..4d1ac81870d2 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -27,7 +27,11 @@
 
 #define PSTATE_FAULT_BITS_64 	(PSR_MODE_EL1h | PSR_A_BIT | PSR_F_BIT | \
 				 PSR_I_BIT | PSR_D_BIT)
-#define EL1_EXCEPT_SYNC_OFFSET	0x200
+
+#define CURRENT_EL_SP_EL0_VECTOR	0x0
+#define CURRENT_EL_SP_ELx_VECTOR	0x200
+#define LOWER_EL_AArch64_VECTOR		0x400
+#define LOWER_EL_AArch32_VECTOR		0x600
 
 static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 {
@@ -97,6 +101,34 @@ static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt,
 		*fsr = 0x14;
 }
 
+enum exception_type {
+	except_type_sync	= 0,
+	except_type_irq		= 0x80,
+	except_type_fiq		= 0x100,
+	except_type_serror	= 0x180,
+};
+
+static u64 get_except_vector(struct kvm_vcpu *vcpu, enum exception_type type)
+{
+	u64 exc_offset;
+
+	switch (*vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT)) {
+	case PSR_MODE_EL1t:
+		exc_offset = CURRENT_EL_SP_EL0_VECTOR;
+		break;
+	case PSR_MODE_EL1h:
+		exc_offset = CURRENT_EL_SP_ELx_VECTOR;
+		break;
+	case PSR_MODE_EL0t:
+		exc_offset = LOWER_EL_AArch64_VECTOR;
+		break;
+	default:
+		exc_offset = LOWER_EL_AArch32_VECTOR;
+	}
+
+	return vcpu_sys_reg(vcpu, VBAR_EL1) + exc_offset + type;
+}
+
 static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr)
 {
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
@@ -108,8 +140,8 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr
 	*vcpu_spsr(vcpu) = cpsr;
 	*vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu);
 
+	*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
 	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
-	*vcpu_pc(vcpu) = vcpu_sys_reg(vcpu, VBAR_EL1) + EL1_EXCEPT_SYNC_OFFSET;
 
 	vcpu_sys_reg(vcpu, FAR_EL1) = addr;
 
@@ -143,8 +175,8 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 	*vcpu_spsr(vcpu) = cpsr;
 	*vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu);
 
+	*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
 	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
-	*vcpu_pc(vcpu) = vcpu_sys_reg(vcpu, VBAR_EL1) + EL1_EXCEPT_SYNC_OFFSET;
 
 	/*
 	 * Build an unknown exception, depending on the instruction
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index f34745cb3d23..9677bf069bcc 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -77,7 +77,11 @@ int kvm_arch_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_GUEST_DEBUG_HW_WPS:
 		r = get_num_wrps();
 		break;
+	case KVM_CAP_ARM_PMU_V3:
+		r = kvm_arm_support_pmu_v3();
+		break;
 	case KVM_CAP_SET_GUEST_DEBUG:
+	case KVM_CAP_VCPU_ATTRIBUTES:
 		r = 1;
 		break;
 	default:
@@ -120,6 +124,9 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	/* Reset system registers */
 	kvm_reset_sys_regs(vcpu);
 
+	/* Reset PMU */
+	kvm_pmu_vcpu_reset(vcpu);
+
 	/* Reset timer */
 	return kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq);
 }
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index eec3598b4184..61ba59104845 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -20,6 +20,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/bsearch.h>
 #include <linux/kvm_host.h>
 #include <linux/mm.h>
 #include <linux/uaccess.h>
@@ -34,6 +35,7 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_host.h>
 #include <asm/kvm_mmu.h>
+#include <asm/perf_event.h>
 
 #include <trace/events/kvm.h>
 
@@ -439,6 +441,344 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	vcpu_sys_reg(vcpu, MPIDR_EL1) = (1ULL << 31) | mpidr;
 }
 
+static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+	u64 pmcr, val;
+
+	asm volatile("mrs %0, pmcr_el0\n" : "=r" (pmcr));
+	/* Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) is reset to UNKNOWN
+	 * except PMCR.E resetting to zero.
+	 */
+	val = ((pmcr & ~ARMV8_PMU_PMCR_MASK)
+	       | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E);
+	vcpu_sys_reg(vcpu, PMCR_EL0) = val;
+}
+
+static bool pmu_access_el0_disabled(struct kvm_vcpu *vcpu)
+{
+	u64 reg = vcpu_sys_reg(vcpu, PMUSERENR_EL0);
+
+	return !((reg & ARMV8_PMU_USERENR_EN) || vcpu_mode_priv(vcpu));
+}
+
+static bool pmu_write_swinc_el0_disabled(struct kvm_vcpu *vcpu)
+{
+	u64 reg = vcpu_sys_reg(vcpu, PMUSERENR_EL0);
+
+	return !((reg & (ARMV8_PMU_USERENR_SW | ARMV8_PMU_USERENR_EN))
+		 || vcpu_mode_priv(vcpu));
+}
+
+static bool pmu_access_cycle_counter_el0_disabled(struct kvm_vcpu *vcpu)
+{
+	u64 reg = vcpu_sys_reg(vcpu, PMUSERENR_EL0);
+
+	return !((reg & (ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_EN))
+		 || vcpu_mode_priv(vcpu));
+}
+
+static bool pmu_access_event_counter_el0_disabled(struct kvm_vcpu *vcpu)
+{
+	u64 reg = vcpu_sys_reg(vcpu, PMUSERENR_EL0);
+
+	return !((reg & (ARMV8_PMU_USERENR_ER | ARMV8_PMU_USERENR_EN))
+		 || vcpu_mode_priv(vcpu));
+}
+
+static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			const struct sys_reg_desc *r)
+{
+	u64 val;
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	if (pmu_access_el0_disabled(vcpu))
+		return false;
+
+	if (p->is_write) {
+		/* Only update writeable bits of PMCR */
+		val = vcpu_sys_reg(vcpu, PMCR_EL0);
+		val &= ~ARMV8_PMU_PMCR_MASK;
+		val |= p->regval & ARMV8_PMU_PMCR_MASK;
+		vcpu_sys_reg(vcpu, PMCR_EL0) = val;
+		kvm_pmu_handle_pmcr(vcpu, val);
+	} else {
+		/* PMCR.P & PMCR.C are RAZ */
+		val = vcpu_sys_reg(vcpu, PMCR_EL0)
+		      & ~(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C);
+		p->regval = val;
+	}
+
+	return true;
+}
+
+static bool access_pmselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	if (pmu_access_event_counter_el0_disabled(vcpu))
+		return false;
+
+	if (p->is_write)
+		vcpu_sys_reg(vcpu, PMSELR_EL0) = p->regval;
+	else
+		/* return PMSELR.SEL field */
+		p->regval = vcpu_sys_reg(vcpu, PMSELR_EL0)
+			    & ARMV8_PMU_COUNTER_MASK;
+
+	return true;
+}
+
+static bool access_pmceid(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	u64 pmceid;
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	BUG_ON(p->is_write);
+
+	if (pmu_access_el0_disabled(vcpu))
+		return false;
+
+	if (!(p->Op2 & 1))
+		asm volatile("mrs %0, pmceid0_el0\n" : "=r" (pmceid));
+	else
+		asm volatile("mrs %0, pmceid1_el0\n" : "=r" (pmceid));
+
+	p->regval = pmceid;
+
+	return true;
+}
+
+static bool pmu_counter_idx_valid(struct kvm_vcpu *vcpu, u64 idx)
+{
+	u64 pmcr, val;
+
+	pmcr = vcpu_sys_reg(vcpu, PMCR_EL0);
+	val = (pmcr >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
+	if (idx >= val && idx != ARMV8_PMU_CYCLE_IDX)
+		return false;
+
+	return true;
+}
+
+static bool access_pmu_evcntr(struct kvm_vcpu *vcpu,
+			      struct sys_reg_params *p,
+			      const struct sys_reg_desc *r)
+{
+	u64 idx;
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	if (r->CRn == 9 && r->CRm == 13) {
+		if (r->Op2 == 2) {
+			/* PMXEVCNTR_EL0 */
+			if (pmu_access_event_counter_el0_disabled(vcpu))
+				return false;
+
+			idx = vcpu_sys_reg(vcpu, PMSELR_EL0)
+			      & ARMV8_PMU_COUNTER_MASK;
+		} else if (r->Op2 == 0) {
+			/* PMCCNTR_EL0 */
+			if (pmu_access_cycle_counter_el0_disabled(vcpu))
+				return false;
+
+			idx = ARMV8_PMU_CYCLE_IDX;
+		} else {
+			BUG();
+		}
+	} else if (r->CRn == 14 && (r->CRm & 12) == 8) {
+		/* PMEVCNTRn_EL0 */
+		if (pmu_access_event_counter_el0_disabled(vcpu))
+			return false;
+
+		idx = ((r->CRm & 3) << 3) | (r->Op2 & 7);
+	} else {
+		BUG();
+	}
+
+	if (!pmu_counter_idx_valid(vcpu, idx))
+		return false;
+
+	if (p->is_write) {
+		if (pmu_access_el0_disabled(vcpu))
+			return false;
+
+		kvm_pmu_set_counter_value(vcpu, idx, p->regval);
+	} else {
+		p->regval = kvm_pmu_get_counter_value(vcpu, idx);
+	}
+
+	return true;
+}
+
+static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			       const struct sys_reg_desc *r)
+{
+	u64 idx, reg;
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	if (pmu_access_el0_disabled(vcpu))
+		return false;
+
+	if (r->CRn == 9 && r->CRm == 13 && r->Op2 == 1) {
+		/* PMXEVTYPER_EL0 */
+		idx = vcpu_sys_reg(vcpu, PMSELR_EL0) & ARMV8_PMU_COUNTER_MASK;
+		reg = PMEVTYPER0_EL0 + idx;
+	} else if (r->CRn == 14 && (r->CRm & 12) == 12) {
+		idx = ((r->CRm & 3) << 3) | (r->Op2 & 7);
+		if (idx == ARMV8_PMU_CYCLE_IDX)
+			reg = PMCCFILTR_EL0;
+		else
+			/* PMEVTYPERn_EL0 */
+			reg = PMEVTYPER0_EL0 + idx;
+	} else {
+		BUG();
+	}
+
+	if (!pmu_counter_idx_valid(vcpu, idx))
+		return false;
+
+	if (p->is_write) {
+		kvm_pmu_set_counter_event_type(vcpu, p->regval, idx);
+		vcpu_sys_reg(vcpu, reg) = p->regval & ARMV8_PMU_EVTYPE_MASK;
+	} else {
+		p->regval = vcpu_sys_reg(vcpu, reg) & ARMV8_PMU_EVTYPE_MASK;
+	}
+
+	return true;
+}
+
+static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	u64 val, mask;
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	if (pmu_access_el0_disabled(vcpu))
+		return false;
+
+	mask = kvm_pmu_valid_counter_mask(vcpu);
+	if (p->is_write) {
+		val = p->regval & mask;
+		if (r->Op2 & 0x1) {
+			/* accessing PMCNTENSET_EL0 */
+			vcpu_sys_reg(vcpu, PMCNTENSET_EL0) |= val;
+			kvm_pmu_enable_counter(vcpu, val);
+		} else {
+			/* accessing PMCNTENCLR_EL0 */
+			vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= ~val;
+			kvm_pmu_disable_counter(vcpu, val);
+		}
+	} else {
+		p->regval = vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask;
+	}
+
+	return true;
+}
+
+static bool access_pminten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	u64 mask = kvm_pmu_valid_counter_mask(vcpu);
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	if (!vcpu_mode_priv(vcpu))
+		return false;
+
+	if (p->is_write) {
+		u64 val = p->regval & mask;
+
+		if (r->Op2 & 0x1)
+			/* accessing PMINTENSET_EL1 */
+			vcpu_sys_reg(vcpu, PMINTENSET_EL1) |= val;
+		else
+			/* accessing PMINTENCLR_EL1 */
+			vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= ~val;
+	} else {
+		p->regval = vcpu_sys_reg(vcpu, PMINTENSET_EL1) & mask;
+	}
+
+	return true;
+}
+
+static bool access_pmovs(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			 const struct sys_reg_desc *r)
+{
+	u64 mask = kvm_pmu_valid_counter_mask(vcpu);
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	if (pmu_access_el0_disabled(vcpu))
+		return false;
+
+	if (p->is_write) {
+		if (r->CRm & 0x2)
+			/* accessing PMOVSSET_EL0 */
+			kvm_pmu_overflow_set(vcpu, p->regval & mask);
+		else
+			/* accessing PMOVSCLR_EL0 */
+			vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= ~(p->regval & mask);
+	} else {
+		p->regval = vcpu_sys_reg(vcpu, PMOVSSET_EL0) & mask;
+	}
+
+	return true;
+}
+
+static bool access_pmswinc(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	u64 mask;
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	if (pmu_write_swinc_el0_disabled(vcpu))
+		return false;
+
+	if (p->is_write) {
+		mask = kvm_pmu_valid_counter_mask(vcpu);
+		kvm_pmu_software_increment(vcpu, p->regval & mask);
+		return true;
+	}
+
+	return false;
+}
+
+static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			     const struct sys_reg_desc *r)
+{
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return trap_raz_wi(vcpu, p, r);
+
+	if (p->is_write) {
+		if (!vcpu_mode_priv(vcpu))
+			return false;
+
+		vcpu_sys_reg(vcpu, PMUSERENR_EL0) = p->regval
+						    & ARMV8_PMU_USERENR_MASK;
+	} else {
+		p->regval = vcpu_sys_reg(vcpu, PMUSERENR_EL0)
+			    & ARMV8_PMU_USERENR_MASK;
+	}
+
+	return true;
+}
+
 /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
 #define DBG_BCR_BVR_WCR_WVR_EL1(n)					\
 	/* DBGBVRn_EL1 */						\
@@ -454,6 +794,20 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b111),	\
 	  trap_wcr, reset_wcr, n, 0,  get_wcr, set_wcr }
 
+/* Macro to expand the PMEVCNTRn_EL0 register */
+#define PMU_PMEVCNTR_EL0(n)						\
+	/* PMEVCNTRn_EL0 */						\
+	{ Op0(0b11), Op1(0b011), CRn(0b1110),				\
+	  CRm((0b1000 | (((n) >> 3) & 0x3))), Op2(((n) & 0x7)),		\
+	  access_pmu_evcntr, reset_unknown, (PMEVCNTR0_EL0 + n), }
+
+/* Macro to expand the PMEVTYPERn_EL0 register */
+#define PMU_PMEVTYPER_EL0(n)						\
+	/* PMEVTYPERn_EL0 */						\
+	{ Op0(0b11), Op1(0b011), CRn(0b1110),				\
+	  CRm((0b1100 | (((n) >> 3) & 0x3))), Op2(((n) & 0x7)),		\
+	  access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), }
+
 /*
  * Architected system registers.
  * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
@@ -583,10 +937,10 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	/* PMINTENSET_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b001),
-	  trap_raz_wi },
+	  access_pminten, reset_unknown, PMINTENSET_EL1 },
 	/* PMINTENCLR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b010),
-	  trap_raz_wi },
+	  access_pminten, NULL, PMINTENSET_EL1 },
 
 	/* MAIR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0010), Op2(0b000),
@@ -623,43 +977,46 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	/* PMCR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b000),
-	  trap_raz_wi },
+	  access_pmcr, reset_pmcr, },
 	/* PMCNTENSET_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b001),
-	  trap_raz_wi },
+	  access_pmcnten, reset_unknown, PMCNTENSET_EL0 },
 	/* PMCNTENCLR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b010),
-	  trap_raz_wi },
+	  access_pmcnten, NULL, PMCNTENSET_EL0 },
 	/* PMOVSCLR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b011),
-	  trap_raz_wi },
+	  access_pmovs, NULL, PMOVSSET_EL0 },
 	/* PMSWINC_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b100),
-	  trap_raz_wi },
+	  access_pmswinc, reset_unknown, PMSWINC_EL0 },
 	/* PMSELR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b101),
-	  trap_raz_wi },
+	  access_pmselr, reset_unknown, PMSELR_EL0 },
 	/* PMCEID0_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b110),
-	  trap_raz_wi },
+	  access_pmceid },
 	/* PMCEID1_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b111),
-	  trap_raz_wi },
+	  access_pmceid },
 	/* PMCCNTR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b000),
-	  trap_raz_wi },
+	  access_pmu_evcntr, reset_unknown, PMCCNTR_EL0 },
 	/* PMXEVTYPER_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b001),
-	  trap_raz_wi },
+	  access_pmu_evtyper },
 	/* PMXEVCNTR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b010),
-	  trap_raz_wi },
-	/* PMUSERENR_EL0 */
+	  access_pmu_evcntr },
+	/* PMUSERENR_EL0
+	 * This register resets as unknown in 64bit mode while it resets as zero
+	 * in 32bit mode. Here we choose to reset it as zero for consistency.
+	 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b000),
-	  trap_raz_wi },
+	  access_pmuserenr, reset_val, PMUSERENR_EL0, 0 },
 	/* PMOVSSET_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b011),
-	  trap_raz_wi },
+	  access_pmovs, reset_unknown, PMOVSSET_EL0 },
 
 	/* TPIDR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b010),
@@ -668,6 +1025,77 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b011),
 	  NULL, reset_unknown, TPIDRRO_EL0 },
 
+	/* PMEVCNTRn_EL0 */
+	PMU_PMEVCNTR_EL0(0),
+	PMU_PMEVCNTR_EL0(1),
+	PMU_PMEVCNTR_EL0(2),
+	PMU_PMEVCNTR_EL0(3),
+	PMU_PMEVCNTR_EL0(4),
+	PMU_PMEVCNTR_EL0(5),
+	PMU_PMEVCNTR_EL0(6),
+	PMU_PMEVCNTR_EL0(7),
+	PMU_PMEVCNTR_EL0(8),
+	PMU_PMEVCNTR_EL0(9),
+	PMU_PMEVCNTR_EL0(10),
+	PMU_PMEVCNTR_EL0(11),
+	PMU_PMEVCNTR_EL0(12),
+	PMU_PMEVCNTR_EL0(13),
+	PMU_PMEVCNTR_EL0(14),
+	PMU_PMEVCNTR_EL0(15),
+	PMU_PMEVCNTR_EL0(16),
+	PMU_PMEVCNTR_EL0(17),
+	PMU_PMEVCNTR_EL0(18),
+	PMU_PMEVCNTR_EL0(19),
+	PMU_PMEVCNTR_EL0(20),
+	PMU_PMEVCNTR_EL0(21),
+	PMU_PMEVCNTR_EL0(22),
+	PMU_PMEVCNTR_EL0(23),
+	PMU_PMEVCNTR_EL0(24),
+	PMU_PMEVCNTR_EL0(25),
+	PMU_PMEVCNTR_EL0(26),
+	PMU_PMEVCNTR_EL0(27),
+	PMU_PMEVCNTR_EL0(28),
+	PMU_PMEVCNTR_EL0(29),
+	PMU_PMEVCNTR_EL0(30),
+	/* PMEVTYPERn_EL0 */
+	PMU_PMEVTYPER_EL0(0),
+	PMU_PMEVTYPER_EL0(1),
+	PMU_PMEVTYPER_EL0(2),
+	PMU_PMEVTYPER_EL0(3),
+	PMU_PMEVTYPER_EL0(4),
+	PMU_PMEVTYPER_EL0(5),
+	PMU_PMEVTYPER_EL0(6),
+	PMU_PMEVTYPER_EL0(7),
+	PMU_PMEVTYPER_EL0(8),
+	PMU_PMEVTYPER_EL0(9),
+	PMU_PMEVTYPER_EL0(10),
+	PMU_PMEVTYPER_EL0(11),
+	PMU_PMEVTYPER_EL0(12),
+	PMU_PMEVTYPER_EL0(13),
+	PMU_PMEVTYPER_EL0(14),
+	PMU_PMEVTYPER_EL0(15),
+	PMU_PMEVTYPER_EL0(16),
+	PMU_PMEVTYPER_EL0(17),
+	PMU_PMEVTYPER_EL0(18),
+	PMU_PMEVTYPER_EL0(19),
+	PMU_PMEVTYPER_EL0(20),
+	PMU_PMEVTYPER_EL0(21),
+	PMU_PMEVTYPER_EL0(22),
+	PMU_PMEVTYPER_EL0(23),
+	PMU_PMEVTYPER_EL0(24),
+	PMU_PMEVTYPER_EL0(25),
+	PMU_PMEVTYPER_EL0(26),
+	PMU_PMEVTYPER_EL0(27),
+	PMU_PMEVTYPER_EL0(28),
+	PMU_PMEVTYPER_EL0(29),
+	PMU_PMEVTYPER_EL0(30),
+	/* PMCCFILTR_EL0
+	 * This register resets as unknown in 64bit mode while it resets as zero
+	 * in 32bit mode. Here we choose to reset it as zero for consistency.
+	 */
+	{ Op0(0b11), Op1(0b011), CRn(0b1110), CRm(0b1111), Op2(0b111),
+	  access_pmu_evtyper, reset_val, PMCCFILTR_EL0, 0 },
+
 	/* DACR32_EL2 */
 	{ Op0(0b11), Op1(0b100), CRn(0b0011), CRm(0b0000), Op2(0b000),
 	  NULL, reset_unknown, DACR32_EL2 },
@@ -857,6 +1285,20 @@ static const struct sys_reg_desc cp14_64_regs[] = {
 	{ Op1( 0), CRm( 2), .access = trap_raz_wi },
 };
 
+/* Macro to expand the PMEVCNTRn register */
+#define PMU_PMEVCNTR(n)							\
+	/* PMEVCNTRn */							\
+	{ Op1(0), CRn(0b1110),						\
+	  CRm((0b1000 | (((n) >> 3) & 0x3))), Op2(((n) & 0x7)),		\
+	  access_pmu_evcntr }
+
+/* Macro to expand the PMEVTYPERn register */
+#define PMU_PMEVTYPER(n)						\
+	/* PMEVTYPERn */						\
+	{ Op1(0), CRn(0b1110),						\
+	  CRm((0b1100 | (((n) >> 3) & 0x3))), Op2(((n) & 0x7)),		\
+	  access_pmu_evtyper }
+
 /*
  * Trapped cp15 registers. TTBR0/TTBR1 get a double encoding,
  * depending on the way they are accessed (as a 32bit or a 64bit
@@ -885,19 +1327,21 @@ static const struct sys_reg_desc cp15_regs[] = {
 	{ Op1( 0), CRn( 7), CRm(14), Op2( 2), access_dcsw },
 
 	/* PMU */
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 0), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 1), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 2), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 3), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 5), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 6), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 7), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(13), Op2( 0), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(13), Op2( 1), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(13), Op2( 2), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(14), Op2( 0), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(14), Op2( 1), trap_raz_wi },
-	{ Op1( 0), CRn( 9), CRm(14), Op2( 2), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 0), access_pmcr },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 1), access_pmcnten },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 2), access_pmcnten },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 3), access_pmovs },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 4), access_pmswinc },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 5), access_pmselr },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 6), access_pmceid },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 7), access_pmceid },
+	{ Op1( 0), CRn( 9), CRm(13), Op2( 0), access_pmu_evcntr },
+	{ Op1( 0), CRn( 9), CRm(13), Op2( 1), access_pmu_evtyper },
+	{ Op1( 0), CRn( 9), CRm(13), Op2( 2), access_pmu_evcntr },
+	{ Op1( 0), CRn( 9), CRm(14), Op2( 0), access_pmuserenr },
+	{ Op1( 0), CRn( 9), CRm(14), Op2( 1), access_pminten },
+	{ Op1( 0), CRn( 9), CRm(14), Op2( 2), access_pminten },
+	{ Op1( 0), CRn( 9), CRm(14), Op2( 3), access_pmovs },
 
 	{ Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, c10_PRRR },
 	{ Op1( 0), CRn(10), CRm( 2), Op2( 1), access_vm_reg, NULL, c10_NMRR },
@@ -908,10 +1352,78 @@ static const struct sys_reg_desc cp15_regs[] = {
 	{ Op1( 0), CRn(12), CRm(12), Op2( 5), trap_raz_wi },
 
 	{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
+
+	/* PMEVCNTRn */
+	PMU_PMEVCNTR(0),
+	PMU_PMEVCNTR(1),
+	PMU_PMEVCNTR(2),
+	PMU_PMEVCNTR(3),
+	PMU_PMEVCNTR(4),
+	PMU_PMEVCNTR(5),
+	PMU_PMEVCNTR(6),
+	PMU_PMEVCNTR(7),
+	PMU_PMEVCNTR(8),
+	PMU_PMEVCNTR(9),
+	PMU_PMEVCNTR(10),
+	PMU_PMEVCNTR(11),
+	PMU_PMEVCNTR(12),
+	PMU_PMEVCNTR(13),
+	PMU_PMEVCNTR(14),
+	PMU_PMEVCNTR(15),
+	PMU_PMEVCNTR(16),
+	PMU_PMEVCNTR(17),
+	PMU_PMEVCNTR(18),
+	PMU_PMEVCNTR(19),
+	PMU_PMEVCNTR(20),
+	PMU_PMEVCNTR(21),
+	PMU_PMEVCNTR(22),
+	PMU_PMEVCNTR(23),
+	PMU_PMEVCNTR(24),
+	PMU_PMEVCNTR(25),
+	PMU_PMEVCNTR(26),
+	PMU_PMEVCNTR(27),
+	PMU_PMEVCNTR(28),
+	PMU_PMEVCNTR(29),
+	PMU_PMEVCNTR(30),
+	/* PMEVTYPERn */
+	PMU_PMEVTYPER(0),
+	PMU_PMEVTYPER(1),
+	PMU_PMEVTYPER(2),
+	PMU_PMEVTYPER(3),
+	PMU_PMEVTYPER(4),
+	PMU_PMEVTYPER(5),
+	PMU_PMEVTYPER(6),
+	PMU_PMEVTYPER(7),
+	PMU_PMEVTYPER(8),
+	PMU_PMEVTYPER(9),
+	PMU_PMEVTYPER(10),
+	PMU_PMEVTYPER(11),
+	PMU_PMEVTYPER(12),
+	PMU_PMEVTYPER(13),
+	PMU_PMEVTYPER(14),
+	PMU_PMEVTYPER(15),
+	PMU_PMEVTYPER(16),
+	PMU_PMEVTYPER(17),
+	PMU_PMEVTYPER(18),
+	PMU_PMEVTYPER(19),
+	PMU_PMEVTYPER(20),
+	PMU_PMEVTYPER(21),
+	PMU_PMEVTYPER(22),
+	PMU_PMEVTYPER(23),
+	PMU_PMEVTYPER(24),
+	PMU_PMEVTYPER(25),
+	PMU_PMEVTYPER(26),
+	PMU_PMEVTYPER(27),
+	PMU_PMEVTYPER(28),
+	PMU_PMEVTYPER(29),
+	PMU_PMEVTYPER(30),
+	/* PMCCFILTR */
+	{ Op1(0), CRn(14), CRm(15), Op2(7), access_pmu_evtyper },
 };
 
 static const struct sys_reg_desc cp15_64_regs[] = {
 	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
+	{ Op1( 0), CRn( 0), CRm( 9), Op2( 0), access_pmu_evcntr },
 	{ Op1( 0), CRn( 0), CRm(12), Op2( 0), access_gic_sgi },
 	{ Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 },
 };
@@ -942,29 +1454,32 @@ static const struct sys_reg_desc *get_target_table(unsigned target,
 	}
 }
 
+#define reg_to_match_value(x)						\
+	({								\
+		unsigned long val;					\
+		val  = (x)->Op0 << 14;					\
+		val |= (x)->Op1 << 11;					\
+		val |= (x)->CRn << 7;					\
+		val |= (x)->CRm << 3;					\
+		val |= (x)->Op2;					\
+		val;							\
+	 })
+
+static int match_sys_reg(const void *key, const void *elt)
+{
+	const unsigned long pval = (unsigned long)key;
+	const struct sys_reg_desc *r = elt;
+
+	return pval - reg_to_match_value(r);
+}
+
 static const struct sys_reg_desc *find_reg(const struct sys_reg_params *params,
 					 const struct sys_reg_desc table[],
 					 unsigned int num)
 {
-	unsigned int i;
-
-	for (i = 0; i < num; i++) {
-		const struct sys_reg_desc *r = &table[i];
+	unsigned long pval = reg_to_match_value(params);
 
-		if (params->Op0 != r->Op0)
-			continue;
-		if (params->Op1 != r->Op1)
-			continue;
-		if (params->CRn != r->CRn)
-			continue;
-		if (params->CRm != r->CRm)
-			continue;
-		if (params->Op2 != r->Op2)
-			continue;
-
-		return r;
-	}
-	return NULL;
+	return bsearch((void *)pval, table, num, sizeof(table[0]), match_sys_reg);
 }
 
 int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run)
@@ -1007,10 +1522,9 @@ static int emulate_cp(struct kvm_vcpu *vcpu,
 		if (likely(r->access(vcpu, params, r))) {
 			/* Skip instruction, since it was emulated */
 			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+			/* Handled */
+			return 0;
 		}
-
-		/* Handled */
-		return 0;
 	}
 
 	/* Not handled */
@@ -1043,7 +1557,7 @@ static void unhandled_cp_access(struct kvm_vcpu *vcpu,
 }
 
 /**
- * kvm_handle_cp_64 -- handles a mrrc/mcrr trap on a guest CP15 access
+ * kvm_handle_cp_64 -- handles a mrrc/mcrr trap on a guest CP14/CP15 access
  * @vcpu: The VCPU pointer
  * @run:  The kvm_run struct
  */
@@ -1095,7 +1609,7 @@ out:
 }
 
 /**
- * kvm_handle_cp15_32 -- handles a mrc/mcr trap on a guest CP15 access
+ * kvm_handle_cp_32 -- handles a mrc/mcr trap on a guest CP14/CP15 access
  * @vcpu: The VCPU pointer
  * @run:  The kvm_run struct
  */
diff --git a/arch/arm64/lib/strnlen.S b/arch/arm64/lib/strnlen.S
index 2ca665711bf2..eae38da6e0bb 100644
--- a/arch/arm64/lib/strnlen.S
+++ b/arch/arm64/lib/strnlen.S
@@ -168,4 +168,4 @@ CPU_LE( lsr	tmp2, tmp2, tmp4 )	/* Shift (tmp1 & 63).  */
 .Lhit_limit:
 	mov	len, limit
 	ret
-ENDPROC(strnlen)
+ENDPIPROC(strnlen)
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 331c4ca6205c..a6e757cbab77 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -933,6 +933,10 @@ static int __init __iommu_dma_init(void)
 		ret = register_iommu_dma_ops_notifier(&platform_bus_type);
 	if (!ret)
 		ret = register_iommu_dma_ops_notifier(&amba_bustype);
+
+	/* handle devices queued before this arch_initcall */
+	if (!ret)
+		__iommu_attach_notifier(NULL, BUS_NOTIFY_ADD_DEVICE, NULL);
 	return ret;
 }
 arch_initcall(__iommu_dma_init);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 92ddac1e8ca2..abe2a9542b3a 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -371,6 +371,13 @@ static int __kprobes do_translation_fault(unsigned long addr,
 	return 0;
 }
 
+static int do_alignment_fault(unsigned long addr, unsigned int esr,
+			      struct pt_regs *regs)
+{
+	do_bad_area(addr, esr, regs);
+	return 0;
+}
+
 /*
  * This abort handler always returns "fault".
  */
@@ -418,7 +425,7 @@ static struct fault_info {
 	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
 	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
 	{ do_bad,		SIGBUS,  0,		"unknown 32"			},
-	{ do_bad,		SIGBUS,  BUS_ADRALN,	"alignment fault"		},
+	{ do_alignment_fault,	SIGBUS,  BUS_ADRALN,	"alignment fault"		},
 	{ do_bad,		SIGBUS,  0,		"unknown 34"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 35"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 36"			},
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 82d607c3614e..da30529bb1f6 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -306,10 +306,6 @@ static __init int setup_hugepagesz(char *opt)
 		hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
 	} else if (ps == PUD_SIZE) {
 		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
-	} else if (ps == (PAGE_SIZE * CONT_PTES)) {
-		hugetlb_add_hstate(CONT_PTE_SHIFT);
-	} else if (ps == (PMD_SIZE * CONT_PMDS)) {
-		hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT);
 	} else {
 		pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
 		return 0;
@@ -317,13 +313,3 @@ static __init int setup_hugepagesz(char *opt)
 	return 1;
 }
 __setup("hugepagesz=", setup_hugepagesz);
-
-#ifdef CONFIG_ARM64_64K_PAGES
-static __init int add_default_hugepagesz(void)
-{
-	if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
-		hugetlb_add_hstate(CONT_PMD_SHIFT);
-	return 0;
-}
-arch_initcall(add_default_hugepagesz);
-#endif
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index f3b061e67bfe..7802f216a67a 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -319,8 +319,8 @@ void __init mem_init(void)
 #endif
 		  MLG(VMALLOC_START, VMALLOC_END),
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-		  MLG((unsigned long)vmemmap,
-		      (unsigned long)vmemmap + VMEMMAP_SIZE),
+		  MLG(VMEMMAP_START,
+		      VMEMMAP_START + VMEMMAP_SIZE),
 		  MLM((unsigned long)virt_to_page(PAGE_OFFSET),
 		      (unsigned long)virt_to_page(high_memory)),
 #endif
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index 4c893b5189dd..232f787a088a 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -53,10 +53,10 @@ unsigned long arch_mmap_rnd(void)
 
 #ifdef CONFIG_COMPAT
 	if (test_thread_flag(TIF_32BIT))
-		rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_compat_bits) - 1);
+		rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
 	else
 #endif
-		rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1);
+		rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
 	return rnd << PAGE_SHIFT;
 }
 
diff --git a/arch/avr32/include/asm/cmpxchg.h b/arch/avr32/include/asm/cmpxchg.h
index 366bbeaeb405..572739b4c4b4 100644
--- a/arch/avr32/include/asm/cmpxchg.h
+++ b/arch/avr32/include/asm/cmpxchg.h
@@ -57,7 +57,7 @@ static inline unsigned long __cmpxchg_u32(volatile int *m, unsigned long old,
 		"	brne	1b\n"
 		"2:\n"
 		: [ret] "=&r"(ret), [m] "=m"(*m)
-		: "m"(m), [old] "ir"(old), [new] "r"(new)
+		: "m"(m), [old] "Ks21r"(old), [new] "r"(new)
 		: "memory", "cc");
 	return ret;
 }
diff --git a/arch/avr32/include/asm/pci.h b/arch/avr32/include/asm/pci.h
index a32a02372017..0f5f134b896a 100644
--- a/arch/avr32/include/asm/pci.h
+++ b/arch/avr32/include/asm/pci.h
@@ -5,6 +5,4 @@
 
 #define PCI_DMA_BUS_IS_PHYS	(1)
 
-#include <asm-generic/pci-dma-compat.h>
-
 #endif /* __ASM_AVR32_PCI_H__ */
diff --git a/arch/avr32/include/uapi/asm/unistd.h b/arch/avr32/include/uapi/asm/unistd.h
index b60132bb27ea..60c0f3afc1f9 100644
--- a/arch/avr32/include/uapi/asm/unistd.h
+++ b/arch/avr32/include/uapi/asm/unistd.h
@@ -337,5 +337,6 @@
 #define __NR_userfaultfd	322
 #define __NR_membarrier		323
 #define __NR_mlock2		324
+#define __NR_copy_file_range    325
 
 #endif /* _UAPI__ASM_AVR32_UNISTD_H */
diff --git a/arch/avr32/kernel/setup.c b/arch/avr32/kernel/setup.c
index 209ae5ad3495..e6928896da2a 100644
--- a/arch/avr32/kernel/setup.c
+++ b/arch/avr32/kernel/setup.c
@@ -49,13 +49,13 @@ static struct resource __initdata kernel_data = {
 	.name	= "Kernel data",
 	.start	= 0,
 	.end	= 0,
-	.flags	= IORESOURCE_MEM,
+	.flags	= IORESOURCE_SYSTEM_RAM,
 };
 static struct resource __initdata kernel_code = {
 	.name	= "Kernel code",
 	.start	= 0,
 	.end	= 0,
-	.flags	= IORESOURCE_MEM,
+	.flags	= IORESOURCE_SYSTEM_RAM,
 	.sibling = &kernel_data,
 };
 
@@ -134,7 +134,7 @@ add_physical_memory(resource_size_t start, resource_size_t end)
 	new->start = start;
 	new->end = end;
 	new->name = "System RAM";
-	new->flags = IORESOURCE_MEM;
+	new->flags = IORESOURCE_SYSTEM_RAM;
 
 	*pprev = new;
 }
diff --git a/arch/avr32/kernel/syscall-stubs.S b/arch/avr32/kernel/syscall-stubs.S
index f9c68fab0e2f..cb3991552f14 100644
--- a/arch/avr32/kernel/syscall-stubs.S
+++ b/arch/avr32/kernel/syscall-stubs.S
@@ -124,3 +124,12 @@ __sys_process_vm_writev:
 	call	sys_process_vm_writev
 	sub	sp, -4
 	popm	pc
+
+	.global __sys_copy_file_range
+	.type	__sys_copy_file_range,@function
+__sys_copy_file_range:
+	pushm	lr
+	st.w	--sp, ARG6
+	call	sys_copy_file_range
+	sub	sp, -4
+	popm	pc
diff --git a/arch/avr32/kernel/syscall_table.S b/arch/avr32/kernel/syscall_table.S
index 1915a443b491..64d71a781fa8 100644
--- a/arch/avr32/kernel/syscall_table.S
+++ b/arch/avr32/kernel/syscall_table.S
@@ -338,4 +338,5 @@ sys_call_table:
 	.long	sys_userfaultfd
 	.long	sys_membarrier
 	.long	sys_mlock2
+	.long   __sys_copy_file_range   /* 325 */
 	.long	sys_ni_syscall		/* r8 is saturated at nr_syscalls */
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index af76634f8d98..a63c12259e77 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -1233,8 +1233,6 @@ source "drivers/pci/Kconfig"
 
 source "drivers/pcmcia/Kconfig"
 
-source "drivers/pci/hotplug/Kconfig"
-
 endmenu
 
 menu "Executable file formats"
diff --git a/arch/blackfin/include/asm/pci.h b/arch/blackfin/include/asm/pci.h
index 14efc0db1ade..11ea1cb35036 100644
--- a/arch/blackfin/include/asm/pci.h
+++ b/arch/blackfin/include/asm/pci.h
@@ -4,7 +4,6 @@
 #define _ASM_BFIN_PCI_H
 
 #include <linux/scatterlist.h>
-#include <asm-generic/pci-dma-compat.h>
 #include <asm-generic/pci.h>
 
 #define PCIBIOS_MIN_IO 0x00001000
diff --git a/arch/blackfin/include/asm/pgtable.h b/arch/blackfin/include/asm/pgtable.h
index b88a1558b0b9..c1ee3d6533fb 100644
--- a/arch/blackfin/include/asm/pgtable.h
+++ b/arch/blackfin/include/asm/pgtable.h
@@ -97,6 +97,8 @@ extern unsigned long get_fb_unmapped_area(struct file *filp, unsigned long,
 					  unsigned long);
 #define HAVE_ARCH_FB_UNMAPPED_AREA
 
+#define pgprot_writecombine pgprot_noncached
+
 #include <asm-generic/pgtable.h>
 
 #endif				/* _BLACKFIN_PGTABLE_H */
diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c
index 0030e21cfceb..23c4ef5f8bdc 100644
--- a/arch/blackfin/mach-common/smp.c
+++ b/arch/blackfin/mach-common/smp.c
@@ -333,7 +333,7 @@ void secondary_start_kernel(void)
 
 	/* We are done with local CPU inits, unblock the boot CPU. */
 	set_cpu_online(cpu, true);
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
 void __init smp_prepare_boot_cpu(void)
diff --git a/arch/c6x/kernel/setup.c b/arch/c6x/kernel/setup.c
index 72e17f7ebd6f..786e36e2f61d 100644
--- a/arch/c6x/kernel/setup.c
+++ b/arch/c6x/kernel/setup.c
@@ -281,8 +281,6 @@ notrace void __init machine_init(unsigned long dt_ptr)
 	 */
 	set_ist(_vectors_start);
 
-	lockdep_init();
-
 	/*
 	 * dtb is passed in from bootloader.
 	 * fdt is linked in blob.
diff --git a/arch/cris/include/asm/pci.h b/arch/cris/include/asm/pci.h
index c15b4b4baafa..b1b289df04c7 100644
--- a/arch/cris/include/asm/pci.h
+++ b/arch/cris/include/asm/pci.h
@@ -48,9 +48,6 @@ extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 
 #endif /* __KERNEL__ */
 
-/* implement the pci_ DMA API in terms of the generic device dma_ one */
-#include <asm-generic/pci-dma-compat.h>
-
 /* generic pci stuff */
 #include <asm-generic/pci.h>
 
diff --git a/arch/frv/include/asm/pci.h b/arch/frv/include/asm/pci.h
index e43d22c58ad5..809cfc6707ab 100644
--- a/arch/frv/include/asm/pci.h
+++ b/arch/frv/include/asm/pci.h
@@ -15,7 +15,6 @@
 
 #include <linux/mm.h>
 #include <linux/scatterlist.h>
-#include <asm-generic/pci-dma-compat.h>
 #include <asm-generic/pci.h>
 
 struct pci_dev;
@@ -32,12 +31,6 @@ extern void consistent_sync_page(struct page *page, unsigned long offset,
 				 size_t size, int direction);
 #endif
 
-extern void *pci_alloc_consistent(struct pci_dev *hwdev, size_t size,
-				  dma_addr_t *dma_handle);
-
-extern void pci_free_consistent(struct pci_dev *hwdev, size_t size,
-				void *vaddr, dma_addr_t dma_handle);
-
 /* Return the index of the PCI controller for device PDEV. */
 #define pci_controller_num(PDEV)	(0)
 
diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c
index ff759f26b96a..983bae7d2665 100644
--- a/arch/hexagon/kernel/smp.c
+++ b/arch/hexagon/kernel/smp.c
@@ -180,7 +180,7 @@ void start_secondary(void)
 
 	local_irq_enable();
 
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
 
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index fb0515eb639b..b534ebab36ea 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -574,12 +574,8 @@ config PCI_DOMAINS
 config PCI_SYSCALL
 	def_bool PCI
 
-source "drivers/pci/pcie/Kconfig"
-
 source "drivers/pci/Kconfig"
 
-source "drivers/pci/hotplug/Kconfig"
-
 source "drivers/pcmcia/Kconfig"
 
 endmenu
diff --git a/arch/ia64/include/asm/pci.h b/arch/ia64/include/asm/pci.h
index 07039d168f37..c0835b0dc722 100644
--- a/arch/ia64/include/asm/pci.h
+++ b/arch/ia64/include/asm/pci.h
@@ -50,8 +50,6 @@ struct pci_dev;
 extern unsigned long ia64_max_iommu_merge_mask;
 #define PCI_DMA_BUS_IS_PHYS	(ia64_max_iommu_merge_mask == ~0UL)
 
-#include <asm-generic/pci-dma-compat.h>
-
 #define HAVE_PCI_MMAP
 extern int pci_mmap_page_range (struct pci_dev *dev, struct vm_area_struct *vma,
 				enum pci_mmap_state mmap_state, int write_combine);
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index caae3f4e4341..300dac3702f1 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -1178,7 +1178,7 @@ efi_initialize_iomem_resources(struct resource *code_resource,
 	efi_memory_desc_t *md;
 	u64 efi_desc_size;
 	char *name;
-	unsigned long flags;
+	unsigned long flags, desc;
 
 	efi_map_start = __va(ia64_boot_param->efi_memmap);
 	efi_map_end   = efi_map_start + ia64_boot_param->efi_memmap_size;
@@ -1193,6 +1193,8 @@ efi_initialize_iomem_resources(struct resource *code_resource,
 			continue;
 
 		flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+		desc = IORES_DESC_NONE;
+
 		switch (md->type) {
 
 			case EFI_MEMORY_MAPPED_IO:
@@ -1207,14 +1209,17 @@ efi_initialize_iomem_resources(struct resource *code_resource,
 				if (md->attribute & EFI_MEMORY_WP) {
 					name = "System ROM";
 					flags |= IORESOURCE_READONLY;
-				} else if (md->attribute == EFI_MEMORY_UC)
+				} else if (md->attribute == EFI_MEMORY_UC) {
 					name = "Uncached RAM";
-				else
+				} else {
 					name = "System RAM";
+					flags |= IORESOURCE_SYSRAM;
+				}
 				break;
 
 			case EFI_ACPI_MEMORY_NVS:
 				name = "ACPI Non-volatile Storage";
+				desc = IORES_DESC_ACPI_NV_STORAGE;
 				break;
 
 			case EFI_UNUSABLE_MEMORY:
@@ -1224,6 +1229,7 @@ efi_initialize_iomem_resources(struct resource *code_resource,
 
 			case EFI_PERSISTENT_MEMORY:
 				name = "Persistent Memory";
+				desc = IORES_DESC_PERSISTENT_MEMORY;
 				break;
 
 			case EFI_RESERVED_TYPE:
@@ -1246,6 +1252,7 @@ efi_initialize_iomem_resources(struct resource *code_resource,
 		res->start = md->phys_addr;
 		res->end = md->phys_addr + efi_md_size(md) - 1;
 		res->flags = flags;
+		res->desc = desc;
 
 		if (insert_resource(&iomem_resource, res) < 0)
 			kfree(res);
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 4f118b0d3091..2029a38a72ae 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -80,17 +80,17 @@ unsigned long vga_console_membase;
 
 static struct resource data_resource = {
 	.name	= "Kernel data",
-	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
 };
 
 static struct resource code_resource = {
 	.name	= "Kernel code",
-	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
 };
 
 static struct resource bss_resource = {
 	.name	= "Kernel bss",
-	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
 };
 
 unsigned long ia64_max_cacheline_size;
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 0e76fad27975..74fe317477e6 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -454,7 +454,7 @@ start_secondary (void *unused)
 	preempt_disable();
 	smp_callin();
 
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 	return 0;
 }
 
diff --git a/arch/ia64/pci/fixup.c b/arch/ia64/pci/fixup.c
index fc505d58f078..41caa99add51 100644
--- a/arch/ia64/pci/fixup.c
+++ b/arch/ia64/pci/fixup.c
@@ -17,14 +17,14 @@
  *
  * The standard boot ROM sequence for an x86 machine uses the BIOS
  * to select an initial video card for boot display. This boot video
- * card will have it's BIOS copied to C0000 in system RAM.
+ * card will have its BIOS copied to 0xC0000 in system RAM.
  * IORESOURCE_ROM_SHADOW is used to associate the boot video
  * card with this copy. On laptops this copy has to be used since
  * the main ROM may be compressed or combined with another image.
  * See pci_map_rom() for use of this flag. Before marking the device
  * with IORESOURCE_ROM_SHADOW check if a vga_default_device is already set
- * by either arch cde or vga-arbitration, if so only apply the fixup to this
- * already determined primary video card.
+ * by either arch code or vga-arbitration; if so only apply the fixup to this
+ * already-determined primary video card.
  */
 
 static void pci_fixup_video(struct pci_dev *pdev)
@@ -32,6 +32,7 @@ static void pci_fixup_video(struct pci_dev *pdev)
 	struct pci_dev *bridge;
 	struct pci_bus *bus;
 	u16 config;
+	struct resource *res;
 
 	if ((strcmp(ia64_platform_name, "dig") != 0)
 	    && (strcmp(ia64_platform_name, "hpzx1")  != 0))
@@ -61,8 +62,18 @@ static void pci_fixup_video(struct pci_dev *pdev)
 	if (!vga_default_device() || pdev == vga_default_device()) {
 		pci_read_config_word(pdev, PCI_COMMAND, &config);
 		if (config & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) {
-			pdev->resource[PCI_ROM_RESOURCE].flags |= IORESOURCE_ROM_SHADOW;
-			dev_printk(KERN_DEBUG, &pdev->dev, "Video device with shadowed ROM\n");
+			res = &pdev->resource[PCI_ROM_RESOURCE];
+
+			pci_disable_rom(pdev);
+			if (res->parent)
+				release_resource(res);
+
+			res->start = 0xC0000;
+			res->end = res->start + 0x20000 - 1;
+			res->flags = IORESOURCE_MEM | IORESOURCE_ROM_SHADOW |
+				     IORESOURCE_PCI_FIXED;
+			dev_info(&pdev->dev, "Video device with shadowed ROM at %pR\n",
+				 res);
 		}
 	}
 }
diff --git a/arch/ia64/sn/kernel/io_acpi_init.c b/arch/ia64/sn/kernel/io_acpi_init.c
index 0640739cc20c..231234c8d113 100644
--- a/arch/ia64/sn/kernel/io_acpi_init.c
+++ b/arch/ia64/sn/kernel/io_acpi_init.c
@@ -429,7 +429,8 @@ sn_acpi_slot_fixup(struct pci_dev *dev)
 	void __iomem *addr;
 	struct pcidev_info *pcidev_info = NULL;
 	struct sn_irq_info *sn_irq_info = NULL;
-	size_t image_size, size;
+	struct resource *res;
+	size_t size;
 
 	if (sn_acpi_get_pcidev_info(dev, &pcidev_info, &sn_irq_info)) {
 		panic("%s:  Failure obtaining pcidev_info for %s\n",
@@ -443,17 +444,20 @@ sn_acpi_slot_fixup(struct pci_dev *dev)
 		 * of the shadowed copy, and the actual length of the ROM image.
 		 */
 		size = pci_resource_len(dev, PCI_ROM_RESOURCE);
-		addr = ioremap(pcidev_info->pdi_pio_mapped_addr[PCI_ROM_RESOURCE],
-			       size);
-		image_size = pci_get_rom_size(dev, addr, size);
-		dev->resource[PCI_ROM_RESOURCE].start = (unsigned long) addr;
-		dev->resource[PCI_ROM_RESOURCE].end =
-					(unsigned long) addr + image_size - 1;
-		dev->resource[PCI_ROM_RESOURCE].flags |= IORESOURCE_ROM_BIOS_COPY;
+
+		res = &dev->resource[PCI_ROM_RESOURCE];
+
+		pci_disable_rom(dev);
+		if (res->parent)
+			release_resource(res);
+
+		res->start = pcidev_info->pdi_pio_mapped_addr[PCI_ROM_RESOURCE];
+		res->end = res->start + size - 1;
+		res->flags = IORESOURCE_MEM | IORESOURCE_ROM_SHADOW |
+			     IORESOURCE_PCI_FIXED;
 	}
 	sn_pci_fixup_slot(dev, pcidev_info, sn_irq_info);
 }
-
 EXPORT_SYMBOL(sn_acpi_slot_fixup);
 
 
diff --git a/arch/ia64/sn/kernel/io_init.c b/arch/ia64/sn/kernel/io_init.c
index 1be65eb074ec..c15a41e2d1f2 100644
--- a/arch/ia64/sn/kernel/io_init.c
+++ b/arch/ia64/sn/kernel/io_init.c
@@ -150,7 +150,8 @@ void
 sn_io_slot_fixup(struct pci_dev *dev)
 {
 	int idx;
-	unsigned long addr, end, size, start;
+	struct resource *res;
+	unsigned long addr, size;
 	struct pcidev_info *pcidev_info;
 	struct sn_irq_info *sn_irq_info;
 	int status;
@@ -175,55 +176,41 @@ sn_io_slot_fixup(struct pci_dev *dev)
 
 	/* Copy over PIO Mapped Addresses */
 	for (idx = 0; idx <= PCI_ROM_RESOURCE; idx++) {
-
-		if (!pcidev_info->pdi_pio_mapped_addr[idx]) {
+		if (!pcidev_info->pdi_pio_mapped_addr[idx])
 			continue;
-		}
 
-		start = dev->resource[idx].start;
-		end = dev->resource[idx].end;
-		size = end - start;
-		if (size == 0) {
+		res = &dev->resource[idx];
+
+		size = res->end - res->start;
+		if (size == 0)
 			continue;
-		}
-		addr = pcidev_info->pdi_pio_mapped_addr[idx];
-		addr = ((addr << 4) >> 4) | __IA64_UNCACHED_OFFSET;
-		dev->resource[idx].start = addr;
-		dev->resource[idx].end = addr + size;
+
+		res->start = pcidev_info->pdi_pio_mapped_addr[idx];
+		res->end = addr + size;
 
 		/*
 		 * if it's already in the device structure, remove it before
 		 * inserting
 		 */
-		if (dev->resource[idx].parent && dev->resource[idx].parent->child)
-			release_resource(&dev->resource[idx]);
+		if (res->parent && res->parent->child)
+			release_resource(res);
 
-		if (dev->resource[idx].flags & IORESOURCE_IO)
-			insert_resource(&ioport_resource, &dev->resource[idx]);
+		if (res->flags & IORESOURCE_IO)
+			insert_resource(&ioport_resource, res);
 		else
-			insert_resource(&iomem_resource, &dev->resource[idx]);
+			insert_resource(&iomem_resource, res);
 		/*
-		 * If ROM, set the actual ROM image size, and mark as
-		 * shadowed in PROM.
+		 * If ROM, mark as shadowed in PROM.
 		 */
 		if (idx == PCI_ROM_RESOURCE) {
-			size_t image_size;
-			void __iomem *rom;
-
-			rom = ioremap(pci_resource_start(dev, PCI_ROM_RESOURCE),
-				      size + 1);
-			image_size = pci_get_rom_size(dev, rom, size + 1);
-			dev->resource[PCI_ROM_RESOURCE].end =
-				dev->resource[PCI_ROM_RESOURCE].start +
-				image_size - 1;
-			dev->resource[PCI_ROM_RESOURCE].flags |=
-						 IORESOURCE_ROM_BIOS_COPY;
+			pci_disable_rom(dev);
+			res->flags = IORESOURCE_MEM | IORESOURCE_ROM_SHADOW |
+				     IORESOURCE_PCI_FIXED;
 		}
 	}
 
 	sn_pci_fixup_slot(dev, pcidev_info, sn_irq_info);
 }
-
 EXPORT_SYMBOL(sn_io_slot_fixup);
 
 /*
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index 2841c0a3fd3b..c82b29253991 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -387,8 +387,6 @@ config ISA
 
 source "drivers/pcmcia/Kconfig"
 
-source "drivers/pci/hotplug/Kconfig"
-
 endmenu
 
 
diff --git a/arch/m32r/kernel/setup.c b/arch/m32r/kernel/setup.c
index a5ecef7188ba..136c69f1fb8a 100644
--- a/arch/m32r/kernel/setup.c
+++ b/arch/m32r/kernel/setup.c
@@ -70,14 +70,14 @@ static struct resource data_resource = {
 	.name   = "Kernel data",
 	.start  = 0,
 	.end    = 0,
-	.flags  = IORESOURCE_BUSY | IORESOURCE_MEM
+	.flags  = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
 };
 
 static struct resource code_resource = {
 	.name   = "Kernel code",
 	.start  = 0,
 	.end    = 0,
-	.flags  = IORESOURCE_BUSY | IORESOURCE_MEM
+	.flags  = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
 };
 
 unsigned long memory_start;
diff --git a/arch/m32r/kernel/smpboot.c b/arch/m32r/kernel/smpboot.c
index a468467542f4..f98d2f6519d6 100644
--- a/arch/m32r/kernel/smpboot.c
+++ b/arch/m32r/kernel/smpboot.c
@@ -432,7 +432,7 @@ int __init start_secondary(void *unused)
 	 */
 	local_flush_tlb_all();
 
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 	return 0;
 }
 
diff --git a/arch/m32r/mm/init.c b/arch/m32r/mm/init.c
index 0d4146f644dc..11fa717d93b1 100644
--- a/arch/m32r/mm/init.c
+++ b/arch/m32r/mm/init.c
@@ -59,21 +59,24 @@ void free_initrd_mem(unsigned long, unsigned long);
 void __init zone_sizes_init(void)
 {
 	unsigned long  zones_size[MAX_NR_ZONES] = {0, };
-	unsigned long  max_dma;
-	unsigned long  low;
 	unsigned long  start_pfn;
 
 #ifdef CONFIG_MMU
-	start_pfn = START_PFN(0);
-	max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
-	low = MAX_LOW_PFN(0);
-
-	if (low < max_dma){
-		zones_size[ZONE_DMA] = low - start_pfn;
-		zones_size[ZONE_NORMAL] = 0;
-	} else {
-		zones_size[ZONE_DMA] = low - start_pfn;
-		zones_size[ZONE_NORMAL] = low - max_dma;
+	{
+		unsigned long  low;
+		unsigned long  max_dma;
+
+		start_pfn = START_PFN(0);
+		max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
+		low = MAX_LOW_PFN(0);
+
+		if (low < max_dma) {
+			zones_size[ZONE_DMA] = low - start_pfn;
+			zones_size[ZONE_NORMAL] = 0;
+		} else {
+			zones_size[ZONE_DMA] = low - start_pfn;
+			zones_size[ZONE_NORMAL] = low - max_dma;
+		}
 	}
 #else
 	zones_size[ZONE_DMA] = 0 >> PAGE_SHIFT;
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index fc96e814188e..d1fc4796025e 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -108,6 +108,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -266,6 +268,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -366,6 +374,7 @@ CONFIG_ARIADNE=y
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 CONFIG_HYDRA=y
 CONFIG_APNE=y
 CONFIG_ZORRO8390=y
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 05c904f08d9d..9bfe8be3658c 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -106,6 +106,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -264,6 +266,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -344,6 +352,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index d572b731c510..ebdcfae55580 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -106,6 +106,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -264,6 +266,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -353,6 +361,7 @@ CONFIG_ATARILANCE=y
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 CONFIG_NE2000=y
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 11a30c65ad44..8acc65e54995 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -104,6 +104,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -262,6 +264,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -343,6 +351,7 @@ CONFIG_BVME6000_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 6630a5154b9d..0c6a3d52b26e 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -106,6 +106,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -264,6 +266,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -345,6 +353,7 @@ CONFIG_HPLANCE=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 1d90b71d0903..12a8a6cb32f4 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -105,6 +105,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -266,6 +268,12 @@ CONFIG_DEV_APPLETALK=m
 CONFIG_IPDDP=m
 CONFIG_IPDDP_ENCAP=y
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -362,6 +370,7 @@ CONFIG_MAC89x0=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 CONFIG_MACSONIC=y
+# CONFIG_NET_VENDOR_NETRONOME is not set
 CONFIG_MAC8390=y
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 1fd21c1ca87f..64ff2dcb34c8 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -115,6 +115,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -276,6 +278,12 @@ CONFIG_DEV_APPLETALK=m
 CONFIG_IPDDP=m
 CONFIG_IPDDP_ENCAP=y
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -404,6 +412,7 @@ CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 CONFIG_MACSONIC=y
+# CONFIG_NET_VENDOR_NETRONOME is not set
 CONFIG_HYDRA=y
 CONFIG_MAC8390=y
 CONFIG_NE2000=y
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 74e10f79d7b1..07fc6abcfe0c 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -103,6 +103,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -261,6 +263,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -343,6 +351,7 @@ CONFIG_MVME147_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 7034e716f166..69903ded88f7 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -104,6 +104,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -262,6 +264,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -343,6 +351,7 @@ CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index f7deb5f702a6..bd8401686dde 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -104,6 +104,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -262,6 +264,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -352,6 +360,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 CONFIG_NE2000=y
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 0ce79eb0d805..5f9fb3ab9636 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -101,6 +101,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -259,6 +261,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -340,6 +348,7 @@ CONFIG_SUN3_82586=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 4cb787e4991f..5d1c674530e2 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -101,6 +101,8 @@ CONFIG_NFT_NAT=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -259,6 +261,12 @@ CONFIG_L2TP=m
 CONFIG_BRIDGE=m
 CONFIG_ATALK=m
 CONFIG_6LOWPAN=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_HOP=m
+CONFIG_6LOWPAN_GHC_UDP=m
+CONFIG_6LOWPAN_GHC_ICMPV6=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_DEST=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
+CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
@@ -341,6 +349,7 @@ CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RENESAS is not set
 # CONFIG_NET_VENDOR_ROCKER is not set
diff --git a/arch/m68k/include/asm/MC68328.h b/arch/m68k/include/asm/MC68328.h
index 4ebf098b8a1f..1a8080c4cc40 100644
--- a/arch/m68k/include/asm/MC68328.h
+++ b/arch/m68k/include/asm/MC68328.h
@@ -798,7 +798,7 @@
 
 /**********
  *
- * 0xFFFFF7xx -- Serial Periferial Interface Slave (SPIS)
+ * 0xFFFFF7xx -- Serial Peripheral Interface Slave (SPIS)
  *
  **********/
 
@@ -824,7 +824,7 @@
 
 /**********
  *
- * 0xFFFFF8xx -- Serial Periferial Interface Master (SPIM)
+ * 0xFFFFF8xx -- Serial Peripheral Interface Master (SPIM)
  *
  **********/
 
@@ -904,7 +904,7 @@
 
 #define UBAUD_PRESCALER_MASK	0x003f	/* Actual divisor is 65 - PRESCALER */
 #define UBAUD_PRESCALER_SHIFT	0
-#define UBAUD_DIVIDE_MASK	0x0700	/* Baud Rate freq. divizor */
+#define UBAUD_DIVIDE_MASK	0x0700	/* Baud Rate freq. divisor */
 #define UBAUD_DIVIDE_SHIFT	8
 #define UBAUD_BAUD_SRC		0x0800	/* Baud Rate Source */
 #define UBAUD_GPIOSRC		0x1000	/* GPIO source */
diff --git a/arch/m68k/include/asm/MC68EZ328.h b/arch/m68k/include/asm/MC68EZ328.h
index d1bde58ab0dd..fedac87c5d13 100644
--- a/arch/m68k/include/asm/MC68EZ328.h
+++ b/arch/m68k/include/asm/MC68EZ328.h
@@ -631,7 +631,7 @@
 
 /**********
  *
- * 0xFFFFF8xx -- Serial Periferial Interface Master (SPIM)
+ * 0xFFFFF8xx -- Serial Peripheral Interface Master (SPIM)
  *
  **********/
 
@@ -712,7 +712,7 @@
 
 #define UBAUD_PRESCALER_MASK	0x003f	/* Actual divisor is 65 - PRESCALER */
 #define UBAUD_PRESCALER_SHIFT	0
-#define UBAUD_DIVIDE_MASK	0x0700	/* Baud Rate freq. divizor */
+#define UBAUD_DIVIDE_MASK	0x0700	/* Baud Rate freq. divisor */
 #define UBAUD_DIVIDE_SHIFT	8
 #define UBAUD_BAUD_SRC		0x0800	/* Baud Rate Source */
 #define UBAUD_UCLKDIR		0x2000	/* UCLK Direction */
@@ -1160,7 +1160,7 @@ typedef volatile struct {
 #define DRAMMC_COL10		0x0080	/* Col address bit for MD10 PA11/PA0  */
 #define DRAMMC_COL9		0x0040	/* Col address bit for MD9  PA10/PA0  */
 #define DRAMMC_COL8		0x0020	/* Col address bit for MD8  PA9/PA0   */
-#define DRAMMC_REF_MASK		0x001f	/* Reresh Cycle */
+#define DRAMMC_REF_MASK		0x001f	/* Refresh Cycle */
 #define DRAMMC_REF_SHIFT	0
 
 /*
diff --git a/arch/m68k/include/asm/MC68VZ328.h b/arch/m68k/include/asm/MC68VZ328.h
index 6bd1bf1f85ea..34a51b2c784f 100644
--- a/arch/m68k/include/asm/MC68VZ328.h
+++ b/arch/m68k/include/asm/MC68VZ328.h
@@ -724,7 +724,7 @@
 
 /**********
  *
- * 0xFFFFF8xx -- Serial Periferial Interface Master (SPIM)
+ * 0xFFFFF8xx -- Serial Peripheral Interface Master (SPIM)
  *
  **********/
 
@@ -806,7 +806,7 @@
 
 #define UBAUD_PRESCALER_MASK	0x003f	/* Actual divisor is 65 - PRESCALER */
 #define UBAUD_PRESCALER_SHIFT	0
-#define UBAUD_DIVIDE_MASK	0x0700	/* Baud Rate freq. divizor */
+#define UBAUD_DIVIDE_MASK	0x0700	/* Baud Rate freq. divisor */
 #define UBAUD_DIVIDE_SHIFT	8
 #define UBAUD_BAUD_SRC		0x0800	/* Baud Rate Source */
 #define UBAUD_UCLKDIR		0x2000	/* UCLK Direction */
@@ -1256,7 +1256,7 @@ typedef struct {
 #define DRAMMC_COL10		0x0080	/* Col address bit for MD10 PA11/PA0  */
 #define DRAMMC_COL9		0x0040	/* Col address bit for MD9  PA10/PA0  */
 #define DRAMMC_COL8		0x0020	/* Col address bit for MD8  PA9/PA0   */
-#define DRAMMC_REF_MASK		0x001f	/* Reresh Cycle */
+#define DRAMMC_REF_MASK		0x001f	/* Refresh Cycle */
 #define DRAMMC_REF_SHIFT	0
 
 /*
diff --git a/arch/m68k/include/asm/m54xxacr.h b/arch/m68k/include/asm/m54xxacr.h
index 6d13cae44af5..59e171063c2f 100644
--- a/arch/m68k/include/asm/m54xxacr.h
+++ b/arch/m68k/include/asm/m54xxacr.h
@@ -23,8 +23,8 @@
 #define CACR_IEC	0x00008000	/* Enable instruction cache */
 #define CACR_DNFB	0x00002000	/* Inhibited fill buffer */
 #define CACR_IDPI	0x00001000	/* Disable CPUSHL */
-#define CACR_IHLCK	0x00000800	/* Intruction cache half lock */
-#define CACR_IDCM	0x00000400	/* Intruction cache inhibit */
+#define CACR_IHLCK	0x00000800	/* Instruction cache half lock */
+#define CACR_IDCM	0x00000400	/* Instruction cache inhibit */
 #define CACR_ICINVA	0x00000100	/* Invalidate instr cache */
 #define CACR_EUSP	0x00000020	/* Enable separate user a7 */
 
diff --git a/arch/m68k/include/asm/mac_iop.h b/arch/m68k/include/asm/mac_iop.h
index fde874a01e20..42566fd052bc 100644
--- a/arch/m68k/include/asm/mac_iop.h
+++ b/arch/m68k/include/asm/mac_iop.h
@@ -48,7 +48,7 @@
 
 /* IOP message status codes */
 
-#define IOP_MSGSTATUS_UNUSED	0	/* Unusued message structure       */
+#define IOP_MSGSTATUS_UNUSED	0	/* Unused message structure        */
 #define IOP_MSGSTATUS_WAITING	1	/* waiting for channel             */
 #define IOP_MSGSTATUS_SENT	2	/* message sent, awaiting reply    */
 #define IOP_MSGSTATUS_COMPLETE	3	/* message complete and reply rcvd */
diff --git a/arch/m68k/include/asm/mcftimer.h b/arch/m68k/include/asm/mcftimer.h
index 089f0f150bbf..1150e42c3f19 100644
--- a/arch/m68k/include/asm/mcftimer.h
+++ b/arch/m68k/include/asm/mcftimer.h
@@ -51,7 +51,7 @@
  *	Bit definitions for the Timer Event Registers (TER).
  */
 #define	MCFTIMER_TER_CAP	0x01		/* Capture event */
-#define	MCFTIMER_TER_REF	0x02		/* Refernece event */
+#define	MCFTIMER_TER_REF	0x02		/* Reference event */
 
 /****************************************************************************/
 #endif	/* mcftimer_h */
diff --git a/arch/m68k/include/asm/pci.h b/arch/m68k/include/asm/pci.h
index 848c3dfaad50..3a3dbcf4051d 100644
--- a/arch/m68k/include/asm/pci.h
+++ b/arch/m68k/include/asm/pci.h
@@ -1,7 +1,6 @@
 #ifndef _ASM_M68K_PCI_H
 #define _ASM_M68K_PCI_H
 
-#include <asm-generic/pci-dma-compat.h>
 #include <asm-generic/pci.h>
 
 /* The PCI address space does equal the physical memory
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index f9d96bf86910..bafaff6dcd7b 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -4,7 +4,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls		376
+#define NR_syscalls		377
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_OLD_STAT
diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h
index 36cf129de663..0ca729665f29 100644
--- a/arch/m68k/include/uapi/asm/unistd.h
+++ b/arch/m68k/include/uapi/asm/unistd.h
@@ -381,5 +381,6 @@
 #define __NR_userfaultfd	373
 #define __NR_membarrier		374
 #define __NR_mlock2		375
+#define __NR_copy_file_range	376
 
 #endif /* _UAPI_ASM_M68K_UNISTD_H_ */
diff --git a/arch/m68k/kernel/entry.S b/arch/m68k/kernel/entry.S
index b54ac7aba850..97cd3ea5f10b 100644
--- a/arch/m68k/kernel/entry.S
+++ b/arch/m68k/kernel/entry.S
@@ -71,13 +71,19 @@ ENTRY(__sys_vfork)
 
 ENTRY(sys_sigreturn)
 	SAVE_SWITCH_STACK
+	movel	%sp,%sp@-		  | switch_stack pointer
+	pea	%sp@(SWITCH_STACK_SIZE+4) | pt_regs pointer
 	jbsr	do_sigreturn
+	addql	#8,%sp
 	RESTORE_SWITCH_STACK
 	rts
 
 ENTRY(sys_rt_sigreturn)
 	SAVE_SWITCH_STACK
+	movel	%sp,%sp@-		  | switch_stack pointer
+	pea	%sp@(SWITCH_STACK_SIZE+4) | pt_regs pointer
 	jbsr	do_rt_sigreturn
+	addql	#8,%sp
 	RESTORE_SWITCH_STACK
 	rts
 
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index af1c4f330aef..2dcee3a88867 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -737,10 +737,8 @@ badframe:
 	return 1;
 }
 
-asmlinkage int do_sigreturn(unsigned long __unused)
+asmlinkage int do_sigreturn(struct pt_regs *regs, struct switch_stack *sw)
 {
-	struct switch_stack *sw = (struct switch_stack *) &__unused;
-	struct pt_regs *regs = (struct pt_regs *) (sw + 1);
 	unsigned long usp = rdusp();
 	struct sigframe __user *frame = (struct sigframe __user *)(usp - 4);
 	sigset_t set;
@@ -764,10 +762,8 @@ badframe:
 	return 0;
 }
 
-asmlinkage int do_rt_sigreturn(unsigned long __unused)
+asmlinkage int do_rt_sigreturn(struct pt_regs *regs, struct switch_stack *sw)
 {
-	struct switch_stack *sw = (struct switch_stack *) &__unused;
-	struct pt_regs *regs = (struct pt_regs *) (sw + 1);
 	unsigned long usp = rdusp();
 	struct rt_sigframe __user *frame = (struct rt_sigframe __user *)(usp - 4);
 	sigset_t set;
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index 282cd903f4c4..8bb94261ff97 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -396,3 +396,4 @@ ENTRY(sys_call_table)
 	.long sys_userfaultfd
 	.long sys_membarrier
 	.long sys_mlock2		/* 375 */
+	.long sys_copy_file_range
diff --git a/arch/m68k/mac/via.c b/arch/m68k/mac/via.c
index ce56e04386e7..920ff63d4a81 100644
--- a/arch/m68k/mac/via.c
+++ b/arch/m68k/mac/via.c
@@ -68,7 +68,7 @@ static int gIER,gIFR,gBufA,gBufB;
  * interrupt. This limitation also seems to apply to VIA clone logic cores in
  * Quadra-like ASICs. (RBV and OSS machines don't have this limitation.)
  *
- * We used to fake it by configuring the relevent VIA pin as an output
+ * We used to fake it by configuring the relevant VIA pin as an output
  * (to mask the interrupt) or input (to unmask). That scheme did not work on
  * (at least) the Quadra 700. A NuBus card's /NMRQ signal is an open-collector
  * circuit (see Designing Cards and Drivers for Macintosh II and Macintosh SE,
diff --git a/arch/metag/kernel/smp.c b/arch/metag/kernel/smp.c
index c3c6f0864881..bad13232de51 100644
--- a/arch/metag/kernel/smp.c
+++ b/arch/metag/kernel/smp.c
@@ -396,7 +396,7 @@ asmlinkage void secondary_start_kernel(void)
 	/*
 	 * OK, it's off to the idle thread for us
 	 */
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 53b69deceb99..3d793b55f60c 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -267,6 +267,9 @@ config PCI
 config PCI_DOMAINS
 	def_bool PCI
 
+config PCI_DOMAINS_GENERIC
+	def_bool PCI_DOMAINS
+
 config PCI_SYSCALL
 	def_bool PCI
 
diff --git a/arch/microblaze/include/asm/pci.h b/arch/microblaze/include/asm/pci.h
index dc9eb6657e3a..fc3ecb55f1b2 100644
--- a/arch/microblaze/include/asm/pci.h
+++ b/arch/microblaze/include/asm/pci.h
@@ -22,8 +22,6 @@
 #include <asm/prom.h>
 #include <asm/pci-bridge.h>
 
-#include <asm-generic/pci-dma-compat.h>
-
 #define PCIBIOS_MIN_IO		0x1000
 #define PCIBIOS_MIN_MEM		0x10000000
 
diff --git a/arch/microblaze/kernel/setup.c b/arch/microblaze/kernel/setup.c
index 89a2a9394927..f31ebb5dc26c 100644
--- a/arch/microblaze/kernel/setup.c
+++ b/arch/microblaze/kernel/setup.c
@@ -130,8 +130,6 @@ void __init machine_early_init(const char *cmdline, unsigned int ram,
 	memset(__bss_start, 0, __bss_stop-__bss_start);
 	memset(_ssbss, 0, _esbss-_ssbss);
 
-	lockdep_init();
-
 /* initialize device tree for usage in early_printk */
 	early_init_devtree(_fdt_start);
 
diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index ae838ed5fcf2..35654be3f1c0 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -123,17 +123,6 @@ unsigned long pci_address_to_pio(phys_addr_t address)
 }
 EXPORT_SYMBOL_GPL(pci_address_to_pio);
 
-/*
- * Return the domain number for this bus.
- */
-int pci_domain_nr(struct pci_bus *bus)
-{
-	struct pci_controller *hose = pci_bus_to_host(bus);
-
-	return hose->global_number;
-}
-EXPORT_SYMBOL(pci_domain_nr);
-
 /* This routine is meant to be used early during boot, when the
  * PCI bus numbers have not yet been assigned, and you need to
  * issue PCI config cycles to an OF device.
@@ -863,26 +852,10 @@ void pcibios_setup_bus_devices(struct pci_bus *bus)
 
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
-	/* When called from the generic PCI probe, read PCI<->PCI bridge
-	 * bases. This is -not- called when generating the PCI tree from
-	 * the OF device-tree.
-	 */
-	if (bus->self != NULL)
-		pci_read_bridge_bases(bus);
-
-	/* Now fixup the bus bus */
-	pcibios_setup_bus_self(bus);
-
-	/* Now fixup devices on that bus */
-	pcibios_setup_bus_devices(bus);
+	/* nothing to do */
 }
 EXPORT_SYMBOL(pcibios_fixup_bus);
 
-static int skip_isa_ioresource_align(struct pci_dev *dev)
-{
-	return 0;
-}
-
 /*
  * We need to avoid collisions with `mirrored' VGA ports
  * and other strange ISA hardware, so we always want the
@@ -899,20 +872,18 @@ static int skip_isa_ioresource_align(struct pci_dev *dev)
 resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 				resource_size_t size, resource_size_t align)
 {
-	struct pci_dev *dev = data;
-	resource_size_t start = res->start;
-
-	if (res->flags & IORESOURCE_IO) {
-		if (skip_isa_ioresource_align(dev))
-			return start;
-		if (start & 0x300)
-			start = (start + 0x3ff) & ~0x3ff;
-	}
-
-	return start;
+	return res->start;
 }
 EXPORT_SYMBOL(pcibios_align_resource);
 
+int pcibios_add_device(struct pci_dev *dev)
+{
+	dev->irq = of_irq_parse_and_map_pci(dev, 0, 0);
+
+	return 0;
+}
+EXPORT_SYMBOL(pcibios_add_device);
+
 /*
  * Reparent resource children of pr that conflict with res
  * under res, and make res replace those children.
@@ -1333,13 +1304,6 @@ static void pcibios_setup_phb_resources(struct pci_controller *hose,
 		 (unsigned long)hose->io_base_virt - _IO_BASE);
 }
 
-struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus)
-{
-	struct pci_controller *hose = bus->sysdata;
-
-	return of_node_get(hose->dn);
-}
-
 static void pcibios_scan_phb(struct pci_controller *hose)
 {
 	LIST_HEAD(resources);
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 57a945e832f4..7c4a4ce35603 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -151,6 +151,7 @@ config BMIPS_GENERIC
 	select CSRC_R4K
 	select SYNC_R4K
 	select COMMON_CLK
+	select BCM6345_L1_IRQ
 	select BCM7038_L1_IRQ
 	select BCM7120_L2_IRQ
 	select BRCMSTB_L2_IRQ
@@ -2085,7 +2086,7 @@ config PAGE_SIZE_32KB
 
 config PAGE_SIZE_64KB
 	bool "64kB"
-	depends on !CPU_R3000 && !CPU_TX39XX
+	depends on !CPU_R3000 && !CPU_TX39XX && !CPU_R6000
 	help
 	  Using 64kB page size will result in higher performance kernel at
 	  the price of higher memory consumption.  This option is available on
@@ -2169,7 +2170,6 @@ config MIPS_MT_SMP
 	select CPU_MIPSR2_IRQ_VI
 	select CPU_MIPSR2_IRQ_EI
 	select SYNC_R4K
-	select MIPS_GIC_IPI
 	select MIPS_MT
 	select SMP
 	select SMP_UP
@@ -2267,7 +2267,6 @@ config MIPS_VPE_APSP_API_MT
 config MIPS_CMP
 	bool "MIPS CMP framework support (DEPRECATED)"
 	depends on SYS_SUPPORTS_MIPS_CMP && !CPU_MIPSR6
-	select MIPS_GIC_IPI
 	select SMP
 	select SYNC_R4K
 	select SYS_SUPPORTS_SMP
@@ -2287,7 +2286,6 @@ config MIPS_CPS
 	select MIPS_CM
 	select MIPS_CPC
 	select MIPS_CPS_PM if HOTPLUG_CPU
-	select MIPS_GIC_IPI
 	select SMP
 	select SYNC_R4K if (CEVT_R4K || CSRC_R4K)
 	select SYS_SUPPORTS_HOTPLUG_CPU
@@ -2305,9 +2303,6 @@ config MIPS_CPS_PM
 	select MIPS_CPC
 	bool
 
-config MIPS_GIC_IPI
-	bool
-
 config MIPS_CM
 	bool
 
@@ -2876,8 +2871,6 @@ config PCI_DOMAINS
 
 source "drivers/pci/Kconfig"
 
-source "drivers/pci/pcie/Kconfig"
-
 #
 # ISA support is now enabled via select.  Too many systems still have the one
 # or other ISA chip on the board that users don't know about so don't expect
@@ -2937,8 +2930,6 @@ config ZONE_DMA32
 
 source "drivers/pcmcia/Kconfig"
 
-source "drivers/pci/hotplug/Kconfig"
-
 config RAPIDIO
 	tristate "RapidIO support"
 	depends on PCI
diff --git a/arch/mips/ath79/irq.c b/arch/mips/ath79/irq.c
index 511c06560dc1..2dfff1f19004 100644
--- a/arch/mips/ath79/irq.c
+++ b/arch/mips/ath79/irq.c
@@ -26,90 +26,6 @@
 #include "common.h"
 #include "machtypes.h"
 
-static void __init ath79_misc_intc_domain_init(
-	struct device_node *node, int irq);
-
-static void ath79_misc_irq_handler(struct irq_desc *desc)
-{
-	struct irq_domain *domain = irq_desc_get_handler_data(desc);
-	void __iomem *base = domain->host_data;
-	u32 pending;
-
-	pending = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_STATUS) &
-		  __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE);
-
-	if (!pending) {
-		spurious_interrupt();
-		return;
-	}
-
-	while (pending) {
-		int bit = __ffs(pending);
-
-		generic_handle_irq(irq_linear_revmap(domain, bit));
-		pending &= ~BIT(bit);
-	}
-}
-
-static void ar71xx_misc_irq_unmask(struct irq_data *d)
-{
-	void __iomem *base = irq_data_get_irq_chip_data(d);
-	unsigned int irq = d->hwirq;
-	u32 t;
-
-	t = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE);
-	__raw_writel(t | (1 << irq), base + AR71XX_RESET_REG_MISC_INT_ENABLE);
-
-	/* flush write */
-	__raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE);
-}
-
-static void ar71xx_misc_irq_mask(struct irq_data *d)
-{
-	void __iomem *base = irq_data_get_irq_chip_data(d);
-	unsigned int irq = d->hwirq;
-	u32 t;
-
-	t = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE);
-	__raw_writel(t & ~(1 << irq), base + AR71XX_RESET_REG_MISC_INT_ENABLE);
-
-	/* flush write */
-	__raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE);
-}
-
-static void ar724x_misc_irq_ack(struct irq_data *d)
-{
-	void __iomem *base = irq_data_get_irq_chip_data(d);
-	unsigned int irq = d->hwirq;
-	u32 t;
-
-	t = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_STATUS);
-	__raw_writel(t & ~(1 << irq), base + AR71XX_RESET_REG_MISC_INT_STATUS);
-
-	/* flush write */
-	__raw_readl(base + AR71XX_RESET_REG_MISC_INT_STATUS);
-}
-
-static struct irq_chip ath79_misc_irq_chip = {
-	.name		= "MISC",
-	.irq_unmask	= ar71xx_misc_irq_unmask,
-	.irq_mask	= ar71xx_misc_irq_mask,
-};
-
-static void __init ath79_misc_irq_init(void)
-{
-	if (soc_is_ar71xx() || soc_is_ar913x())
-		ath79_misc_irq_chip.irq_mask_ack = ar71xx_misc_irq_mask;
-	else if (soc_is_ar724x() ||
-		 soc_is_ar933x() ||
-		 soc_is_ar934x() ||
-		 soc_is_qca955x())
-		ath79_misc_irq_chip.irq_ack = ar724x_misc_irq_ack;
-	else
-		BUG();
-
-	ath79_misc_intc_domain_init(NULL, ATH79_CPU_IRQ(6));
-}
 
 static void ar934x_ip2_irq_dispatch(struct irq_desc *desc)
 {
@@ -212,142 +128,12 @@ static void qca955x_irq_init(void)
 	irq_set_chained_handler(ATH79_CPU_IRQ(3), qca955x_ip3_irq_dispatch);
 }
 
-/*
- * The IP2/IP3 lines are tied to a PCI/WMAC/USB device. Drivers for
- * these devices typically allocate coherent DMA memory, however the
- * DMA controller may still have some unsynchronized data in the FIFO.
- * Issue a flush in the handlers to ensure that the driver sees
- * the update.
- *
- * This array map the interrupt lines to the DDR write buffer channels.
- */
-
-static unsigned irq_wb_chan[8] = {
-	-1, -1, -1, -1, -1, -1, -1, -1,
-};
-
-asmlinkage void plat_irq_dispatch(void)
-{
-	unsigned long pending;
-	int irq;
-
-	pending = read_c0_status() & read_c0_cause() & ST0_IM;
-
-	if (!pending) {
-		spurious_interrupt();
-		return;
-	}
-
-	pending >>= CAUSEB_IP;
-	while (pending) {
-		irq = fls(pending) - 1;
-		if (irq < ARRAY_SIZE(irq_wb_chan) && irq_wb_chan[irq] != -1)
-			ath79_ddr_wb_flush(irq_wb_chan[irq]);
-		do_IRQ(MIPS_CPU_IRQ_BASE + irq);
-		pending &= ~BIT(irq);
-	}
-}
-
-static int misc_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw)
-{
-	irq_set_chip_and_handler(irq, &ath79_misc_irq_chip, handle_level_irq);
-	irq_set_chip_data(irq, d->host_data);
-	return 0;
-}
-
-static const struct irq_domain_ops misc_irq_domain_ops = {
-	.xlate = irq_domain_xlate_onecell,
-	.map = misc_map,
-};
-
-static void __init ath79_misc_intc_domain_init(
-	struct device_node *node, int irq)
-{
-	void __iomem *base = ath79_reset_base;
-	struct irq_domain *domain;
-
-	domain = irq_domain_add_legacy(node, ATH79_MISC_IRQ_COUNT,
-			ATH79_MISC_IRQ_BASE, 0, &misc_irq_domain_ops, base);
-	if (!domain)
-		panic("Failed to add MISC irqdomain");
-
-	/* Disable and clear all interrupts */
-	__raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_ENABLE);
-	__raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_STATUS);
-
-	irq_set_chained_handler_and_data(irq, ath79_misc_irq_handler, domain);
-}
-
-static int __init ath79_misc_intc_of_init(
-	struct device_node *node, struct device_node *parent)
-{
-	int irq;
-
-	irq = irq_of_parse_and_map(node, 0);
-	if (!irq)
-		panic("Failed to get MISC IRQ");
-
-	ath79_misc_intc_domain_init(node, irq);
-	return 0;
-}
-
-static int __init ar7100_misc_intc_of_init(
-	struct device_node *node, struct device_node *parent)
-{
-	ath79_misc_irq_chip.irq_mask_ack = ar71xx_misc_irq_mask;
-	return ath79_misc_intc_of_init(node, parent);
-}
-
-IRQCHIP_DECLARE(ar7100_misc_intc, "qca,ar7100-misc-intc",
-		ar7100_misc_intc_of_init);
-
-static int __init ar7240_misc_intc_of_init(
-	struct device_node *node, struct device_node *parent)
-{
-	ath79_misc_irq_chip.irq_ack = ar724x_misc_irq_ack;
-	return ath79_misc_intc_of_init(node, parent);
-}
-
-IRQCHIP_DECLARE(ar7240_misc_intc, "qca,ar7240-misc-intc",
-		ar7240_misc_intc_of_init);
-
-static int __init ar79_cpu_intc_of_init(
-	struct device_node *node, struct device_node *parent)
-{
-	int err, i, count;
-
-	/* Fill the irq_wb_chan table */
-	count = of_count_phandle_with_args(
-		node, "qca,ddr-wb-channels", "#qca,ddr-wb-channel-cells");
-
-	for (i = 0; i < count; i++) {
-		struct of_phandle_args args;
-		u32 irq = i;
-
-		of_property_read_u32_index(
-			node, "qca,ddr-wb-channel-interrupts", i, &irq);
-		if (irq >= ARRAY_SIZE(irq_wb_chan))
-			continue;
-
-		err = of_parse_phandle_with_args(
-			node, "qca,ddr-wb-channels",
-			"#qca,ddr-wb-channel-cells",
-			i, &args);
-		if (err)
-			return err;
-
-		irq_wb_chan[irq] = args.args[0];
-		pr_info("IRQ: Set flush channel of IRQ%d to %d\n",
-			irq, args.args[0]);
-	}
-
-	return mips_cpu_irq_of_init(node, parent);
-}
-IRQCHIP_DECLARE(ar79_cpu_intc, "qca,ar7100-cpu-intc",
-		ar79_cpu_intc_of_init);
-
 void __init arch_init_irq(void)
 {
+	unsigned irq_wb_chan2 = -1;
+	unsigned irq_wb_chan3 = -1;
+	bool misc_is_ar71xx;
+
 	if (mips_machtype == ATH79_MACH_GENERIC_OF) {
 		irqchip_init();
 		return;
@@ -355,14 +141,26 @@ void __init arch_init_irq(void)
 
 	if (soc_is_ar71xx() || soc_is_ar724x() ||
 	    soc_is_ar913x() || soc_is_ar933x()) {
-		irq_wb_chan[2] = 3;
-		irq_wb_chan[3] = 2;
+		irq_wb_chan2 = 3;
+		irq_wb_chan3 = 2;
 	} else if (soc_is_ar934x()) {
-		irq_wb_chan[3] = 2;
+		irq_wb_chan3 = 2;
 	}
 
-	mips_cpu_irq_init();
-	ath79_misc_irq_init();
+	ath79_cpu_irq_init(irq_wb_chan2, irq_wb_chan3);
+
+	if (soc_is_ar71xx() || soc_is_ar913x())
+		misc_is_ar71xx = true;
+	else if (soc_is_ar724x() ||
+		 soc_is_ar933x() ||
+		 soc_is_ar934x() ||
+		 soc_is_qca955x())
+		misc_is_ar71xx = false;
+	else
+		BUG();
+	ath79_misc_irq_init(
+		ath79_reset_base + AR71XX_RESET_REG_MISC_INT_STATUS,
+		ATH79_CPU_IRQ(6), ATH79_MISC_IRQ_BASE, misc_is_ar71xx);
 
 	if (soc_is_ar934x())
 		ar934x_ip2_irq_init();
diff --git a/arch/mips/bmips/irq.c b/arch/mips/bmips/irq.c
index e7fc6f9348ba..7efefcf44033 100644
--- a/arch/mips/bmips/irq.c
+++ b/arch/mips/bmips/irq.c
@@ -15,6 +15,12 @@
 #include <asm/irq_cpu.h>
 #include <asm/time.h>
 
+static const struct of_device_id smp_intc_dt_match[] = {
+	{ .compatible = "brcm,bcm7038-l1-intc" },
+	{ .compatible = "brcm,bcm6345-l1-intc" },
+	{}
+};
+
 unsigned int get_c0_compare_int(void)
 {
 	return CP0_LEGACY_COMPARE_IRQ;
@@ -24,8 +30,8 @@ void __init arch_init_irq(void)
 {
 	struct device_node *dn;
 
-	/* Only the STB (bcm7038) controller supports SMP IRQ affinity */
-	dn = of_find_compatible_node(NULL, NULL, "brcm,bcm7038-l1-intc");
+	/* Only these controllers support SMP IRQ affinity */
+	dn = of_find_matching_node(NULL, smp_intc_dt_match);
 	if (dn)
 		of_node_put(dn);
 	else
diff --git a/arch/mips/boot/compressed/uart-16550.c b/arch/mips/boot/compressed/uart-16550.c
index 408799a839b4..f7521142deda 100644
--- a/arch/mips/boot/compressed/uart-16550.c
+++ b/arch/mips/boot/compressed/uart-16550.c
@@ -17,7 +17,7 @@
 #define PORT(offset) (CKSEG1ADDR(AR7_REGS_UART0) + (4 * offset))
 #endif
 
-#ifdef CONFIG_MACH_JZ4740
+#if defined(CONFIG_MACH_JZ4740) || defined(CONFIG_MACH_JZ4780)
 #include <asm/mach-jz4740/base.h>
 #define PORT(offset) (CKSEG1ADDR(JZ4740_UART0_BASE_ADDR) + (4 * offset))
 #endif
diff --git a/arch/mips/boot/dts/brcm/bcm6328.dtsi b/arch/mips/boot/dts/brcm/bcm6328.dtsi
index 459b9b252c3b..9d19236f53e7 100644
--- a/arch/mips/boot/dts/brcm/bcm6328.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm6328.dtsi
@@ -74,6 +74,7 @@
 		timer: timer@10000040 {
 			compatible = "syscon";
 			reg = <0x10000040 0x2c>;
+			native-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm6368.dtsi b/arch/mips/boot/dts/brcm/bcm6368.dtsi
index 9c8d3fe28b31..1f6b9b5cddb4 100644
--- a/arch/mips/boot/dts/brcm/bcm6368.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm6368.dtsi
@@ -54,7 +54,7 @@
 		periph_cntl: syscon@10000000 {
 			compatible = "syscon";
 			reg = <0x10000000 0x14>;
-			little-endian;
+			native-endian;
 		};
 
 		reboot: syscon-reboot@10000008 {
diff --git a/arch/mips/boot/dts/brcm/bcm7125.dtsi b/arch/mips/boot/dts/brcm/bcm7125.dtsi
index 4fc7ecee273c..3ae16053a0c9 100644
--- a/arch/mips/boot/dts/brcm/bcm7125.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7125.dtsi
@@ -98,6 +98,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7125-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x60c>;
+			native-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7346.dtsi b/arch/mips/boot/dts/brcm/bcm7346.dtsi
index a3039bb53477..be7991917d29 100644
--- a/arch/mips/boot/dts/brcm/bcm7346.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7346.dtsi
@@ -118,6 +118,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7346-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
+			native-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7358.dtsi b/arch/mips/boot/dts/brcm/bcm7358.dtsi
index 4274ff41ec21..060805be619a 100644
--- a/arch/mips/boot/dts/brcm/bcm7358.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7358.dtsi
@@ -112,6 +112,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7358-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
+			native-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7360.dtsi b/arch/mips/boot/dts/brcm/bcm7360.dtsi
index 0dcc9163c27b..bcdb09bfe07b 100644
--- a/arch/mips/boot/dts/brcm/bcm7360.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7360.dtsi
@@ -112,6 +112,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7360-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
+			native-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7362.dtsi b/arch/mips/boot/dts/brcm/bcm7362.dtsi
index 2f3f9fc2c478..d3b1b762e6c3 100644
--- a/arch/mips/boot/dts/brcm/bcm7362.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7362.dtsi
@@ -118,6 +118,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7362-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
+			native-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7420.dtsi b/arch/mips/boot/dts/brcm/bcm7420.dtsi
index bee221b3b568..3302a1b8a5c9 100644
--- a/arch/mips/boot/dts/brcm/bcm7420.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7420.dtsi
@@ -99,6 +99,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7420-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x60c>;
+			native-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7425.dtsi b/arch/mips/boot/dts/brcm/bcm7425.dtsi
index 571f30f52e3f..15b27aae15a9 100644
--- a/arch/mips/boot/dts/brcm/bcm7425.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7425.dtsi
@@ -100,6 +100,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7425-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
+			native-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/boot/dts/brcm/bcm7435.dtsi b/arch/mips/boot/dts/brcm/bcm7435.dtsi
index 614ee211f71a..adb33e355043 100644
--- a/arch/mips/boot/dts/brcm/bcm7435.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7435.dtsi
@@ -114,6 +114,7 @@
 		sun_top_ctrl: syscon@404000 {
 			compatible = "brcm,bcm7425-sun-top-ctrl", "syscon";
 			reg = <0x404000 0x51c>;
+			native-endian;
 		};
 
 		reboot {
diff --git a/arch/mips/include/asm/elf.h b/arch/mips/include/asm/elf.h
index cefb7a596878..e090fc388e02 100644
--- a/arch/mips/include/asm/elf.h
+++ b/arch/mips/include/asm/elf.h
@@ -227,7 +227,7 @@ struct mips_elf_abiflags_v0 {
 	int __res = 1;							\
 	struct elfhdr *__h = (hdr);					\
 									\
-	if (__h->e_machine != EM_MIPS)					\
+	if (!mips_elf_check_machine(__h))				\
 		__res = 0;						\
 	if (__h->e_ident[EI_CLASS] != ELFCLASS32)			\
 		__res = 0;						\
@@ -258,7 +258,7 @@ struct mips_elf_abiflags_v0 {
 	int __res = 1;							\
 	struct elfhdr *__h = (hdr);					\
 									\
-	if (__h->e_machine != EM_MIPS)					\
+	if (!mips_elf_check_machine(__h))				\
 		__res = 0;						\
 	if (__h->e_ident[EI_CLASS] != ELFCLASS64)			\
 		__res = 0;						\
@@ -285,6 +285,11 @@ struct mips_elf_abiflags_v0 {
 
 #endif /* !defined(ELF_ARCH) */
 
+#define mips_elf_check_machine(x) ((x)->e_machine == EM_MIPS)
+
+#define vmcore_elf32_check_arch mips_elf_check_machine
+#define vmcore_elf64_check_arch mips_elf_check_machine
+
 struct mips_abi;
 
 extern struct mips_abi mips_abi;
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index 9cbf383b8834..f06f97bd62df 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -179,6 +179,10 @@ static inline void lose_fpu_inatomic(int save, struct task_struct *tsk)
 		if (save)
 			_save_fp(tsk);
 		__disable_fpu();
+	} else {
+		/* FPU should not have been left enabled with no owner */
+		WARN(read_c0_status() & ST0_CU1,
+		     "Orphaned FPU left enabled");
 	}
 	KSTK_STATUS(tsk) &= ~ST0_CU1;
 	clear_tsk_thread_flag(tsk, TIF_USEDFPU);
diff --git a/arch/mips/include/asm/mach-ath79/ath79.h b/arch/mips/include/asm/mach-ath79/ath79.h
index 2b3487213d1e..441faa92c3cd 100644
--- a/arch/mips/include/asm/mach-ath79/ath79.h
+++ b/arch/mips/include/asm/mach-ath79/ath79.h
@@ -144,4 +144,8 @@ static inline u32 ath79_reset_rr(unsigned reg)
 void ath79_device_reset_set(u32 mask);
 void ath79_device_reset_clear(u32 mask);
 
+void ath79_cpu_irq_init(unsigned irq_wb_chan2, unsigned irq_wb_chan3);
+void ath79_misc_irq_init(void __iomem *regs, int irq,
+			int irq_base, bool is_ar71xx);
+
 #endif /* __ASM_MACH_ATH79_H */
diff --git a/arch/mips/include/asm/octeon/octeon-feature.h b/arch/mips/include/asm/octeon/octeon-feature.h
index 8ebd3f579b84..3ed10a8d7865 100644
--- a/arch/mips/include/asm/octeon/octeon-feature.h
+++ b/arch/mips/include/asm/octeon/octeon-feature.h
@@ -128,7 +128,8 @@ static inline int octeon_has_feature(enum octeon_feature feature)
 	case OCTEON_FEATURE_PCIE:
 		return OCTEON_IS_MODEL(OCTEON_CN56XX)
 			|| OCTEON_IS_MODEL(OCTEON_CN52XX)
-			|| OCTEON_IS_MODEL(OCTEON_CN6XXX);
+			|| OCTEON_IS_MODEL(OCTEON_CN6XXX)
+			|| OCTEON_IS_MODEL(OCTEON_CN7XXX);
 
 	case OCTEON_FEATURE_SRIO:
 		return OCTEON_IS_MODEL(OCTEON_CN63XX)
diff --git a/arch/mips/include/asm/pci.h b/arch/mips/include/asm/pci.h
index 98c31e5d9579..8c16fb7b8fdb 100644
--- a/arch/mips/include/asm/pci.h
+++ b/arch/mips/include/asm/pci.h
@@ -102,7 +102,6 @@ static inline void pci_resource_to_user(const struct pci_dev *dev, int bar,
 #include <linux/scatterlist.h>
 #include <linux/string.h>
 #include <asm/io.h>
-#include <asm-generic/pci-bridge.h>
 
 struct pci_dev;
 
@@ -125,9 +124,6 @@ static inline int pci_proc_domain(struct pci_bus *bus)
 
 #endif /* __KERNEL__ */
 
-/* implement the pci_ DMA API in terms of the generic device dma_ one */
-#include <asm-generic/pci-dma-compat.h>
-
 /* Do platform specific device initialization at pci_enable_device() time */
 extern int pcibios_plat_dev_init(struct pci_dev *dev);
 
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index 3f832c3dd8f5..041153f5cf93 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -45,7 +45,7 @@ extern unsigned int vced_count, vcei_count;
  * User space process size: 2GB. This is hardcoded into a few places,
  * so don't change it unless you know what you are doing.
  */
-#define TASK_SIZE	0x7fff8000UL
+#define TASK_SIZE	0x80000000UL
 #endif
 
 #define STACK_TOP_MAX	TASK_SIZE
diff --git a/arch/mips/include/asm/smp-ops.h b/arch/mips/include/asm/smp-ops.h
index 6ba1fb8b11e2..db7c322f057f 100644
--- a/arch/mips/include/asm/smp-ops.h
+++ b/arch/mips/include/asm/smp-ops.h
@@ -44,8 +44,9 @@ static inline void plat_smp_setup(void)
 	mp_ops->smp_setup();
 }
 
-extern void gic_send_ipi_single(int cpu, unsigned int action);
-extern void gic_send_ipi_mask(const struct cpumask *mask, unsigned int action);
+extern void mips_smp_send_ipi_single(int cpu, unsigned int action);
+extern void mips_smp_send_ipi_mask(const struct cpumask *mask,
+				      unsigned int action);
 
 #else /* !CONFIG_SMP */
 
diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h
index a71da576883c..eebf39549606 100644
--- a/arch/mips/include/asm/stackframe.h
+++ b/arch/mips/include/asm/stackframe.h
@@ -289,7 +289,7 @@
 		.set	reorder
 		.set	noat
 		mfc0	a0, CP0_STATUS
-		li	v1, 0xff00
+		li	v1, ST0_CU1 | ST0_IM
 		ori	a0, STATMASK
 		xori	a0, STATMASK
 		mtc0	a0, CP0_STATUS
@@ -330,7 +330,7 @@
 		ori	a0, STATMASK
 		xori	a0, STATMASK
 		mtc0	a0, CP0_STATUS
-		li	v1, 0xff00
+		li	v1, ST0_CU1 | ST0_FR | ST0_IM
 		and	a0, v1
 		LONG_L	v0, PT_STATUS(sp)
 		nor	v1, $0, v1
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index 6499d93ae68d..47bc45a67e9b 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -101,10 +101,8 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	/* O32 ABI syscall() - Either 64-bit with O32 or 32-bit */
 	if ((config_enabled(CONFIG_32BIT) ||
 	    test_tsk_thread_flag(task, TIF_32BIT_REGS)) &&
-	    (regs->regs[2] == __NR_syscall)) {
+	    (regs->regs[2] == __NR_syscall))
 		i++;
-		n++;
-	}
 
 	while (n--)
 		ret |= mips_get_syscall_arg(args++, task, regs, i++);
diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h
index 90f03a7da665..3129795de940 100644
--- a/arch/mips/include/uapi/asm/unistd.h
+++ b/arch/mips/include/uapi/asm/unistd.h
@@ -380,16 +380,17 @@
 #define __NR_userfaultfd		(__NR_Linux + 357)
 #define __NR_membarrier			(__NR_Linux + 358)
 #define __NR_mlock2			(__NR_Linux + 359)
+#define __NR_copy_file_range		(__NR_Linux + 360)
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		359
+#define __NR_Linux_syscalls		360
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		359
+#define __NR_O32_Linux_syscalls		360
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -717,16 +718,17 @@
 #define __NR_userfaultfd		(__NR_Linux + 317)
 #define __NR_membarrier			(__NR_Linux + 318)
 #define __NR_mlock2			(__NR_Linux + 319)
+#define __NR_copy_file_range		(__NR_Linux + 320)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		319
+#define __NR_Linux_syscalls		320
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		319
+#define __NR_64_Linux_syscalls		320
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1058,15 +1060,16 @@
 #define __NR_userfaultfd		(__NR_Linux + 321)
 #define __NR_membarrier			(__NR_Linux + 322)
 #define __NR_mlock2			(__NR_Linux + 323)
+#define __NR_copy_file_range		(__NR_Linux + 324)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		323
+#define __NR_Linux_syscalls		324
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		323
+#define __NR_N32_Linux_syscalls		324
 
 #endif /* _UAPI_ASM_UNISTD_H */
diff --git a/arch/mips/jz4740/gpio.c b/arch/mips/jz4740/gpio.c
index 8c6d76c9b2d6..d9907e57e9b9 100644
--- a/arch/mips/jz4740/gpio.c
+++ b/arch/mips/jz4740/gpio.c
@@ -270,7 +270,7 @@ uint32_t jz_gpio_port_get_value(int port, uint32_t mask)
 }
 EXPORT_SYMBOL(jz_gpio_port_get_value);
 
-#define IRQ_TO_BIT(irq) BIT(irq_to_gpio(irq) & 0x1f)
+#define IRQ_TO_BIT(irq) BIT((irq - JZ4740_IRQ_GPIO(0)) & 0x1f)
 
 static void jz_gpio_check_trigger_both(struct jz_gpio_chip *chip, unsigned int irq)
 {
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 68e2b7db9348..b0988fd62fcc 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -52,7 +52,6 @@ obj-$(CONFIG_MIPS_MT_SMP)	+= smp-mt.o
 obj-$(CONFIG_MIPS_CMP)		+= smp-cmp.o
 obj-$(CONFIG_MIPS_CPS)		+= smp-cps.o cps-vec.o
 obj-$(CONFIG_MIPS_CPS_NS16550)	+= cps-vec-ns16550.o
-obj-$(CONFIG_MIPS_GIC_IPI)	+= smp-gic.o
 obj-$(CONFIG_MIPS_SPRAM)	+= spram.o
 
 obj-$(CONFIG_MIPS_VPE_LOADER)	+= vpe.o
diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c
index 1188e00bb120..1b992c6e3d8e 100644
--- a/arch/mips/kernel/binfmt_elfn32.c
+++ b/arch/mips/kernel/binfmt_elfn32.c
@@ -35,7 +35,7 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
 	int __res = 1;							\
 	struct elfhdr *__h = (hdr);					\
 									\
-	if (__h->e_machine != EM_MIPS)					\
+	if (!mips_elf_check_machine(__h))				\
 		__res = 0;						\
 	if (__h->e_ident[EI_CLASS] != ELFCLASS32)			\
 		__res = 0;						\
diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c
index 928767858b86..abd3affe5fb3 100644
--- a/arch/mips/kernel/binfmt_elfo32.c
+++ b/arch/mips/kernel/binfmt_elfo32.c
@@ -47,7 +47,7 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
 	int __res = 1;							\
 	struct elfhdr *__h = (hdr);					\
 									\
-	if (__h->e_machine != EM_MIPS)					\
+	if (!mips_elf_check_machine(__h))				\
 		__res = 0;						\
 	if (__h->e_ident[EI_CLASS] != ELFCLASS32)			\
 		__res = 0;						\
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index f2975d4d1e44..eddd5fd6fdfa 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -65,12 +65,10 @@ void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long sp)
 	status = regs->cp0_status & ~(ST0_CU0|ST0_CU1|ST0_FR|KU_MASK);
 	status |= KU_USER;
 	regs->cp0_status = status;
+	lose_fpu(0);
+	clear_thread_flag(TIF_MSA_CTX_LIVE);
 	clear_used_math();
-	clear_fpu_owner();
 	init_dsp();
-	clear_thread_flag(TIF_USEDMSA);
-	clear_thread_flag(TIF_MSA_CTX_LIVE);
-	disable_msa();
 	regs->cp0_epc = pc;
 	regs->regs[29] = sp;
 }
diff --git a/arch/mips/kernel/r2300_fpu.S b/arch/mips/kernel/r2300_fpu.S
index 5ce3b746cedc..b4ac6374a38f 100644
--- a/arch/mips/kernel/r2300_fpu.S
+++ b/arch/mips/kernel/r2300_fpu.S
@@ -125,7 +125,7 @@ LEAF(_restore_fp_context)
 	END(_restore_fp_context)
 	.set	reorder
 
-	.type	fault@function
+	.type	fault, @function
 	.ent	fault
 fault:	li	v0, -EFAULT
 	jr	ra
diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S
index f09546ee2cdc..17732f876eff 100644
--- a/arch/mips/kernel/r4k_fpu.S
+++ b/arch/mips/kernel/r4k_fpu.S
@@ -358,7 +358,7 @@ LEAF(_restore_msa_all_upper)
 
 	.set	reorder
 
-	.type	fault@function
+	.type	fault, @function
 	.ent	fault
 fault:	li	v0, -EFAULT				# failure
 	jr	ra
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 2d23c834ba96..a56317444bda 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -595,3 +595,4 @@ EXPORT(sys_call_table)
 	PTR	sys_userfaultfd
 	PTR	sys_membarrier
 	PTR	sys_mlock2
+	PTR	sys_copy_file_range		/* 4360 */
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index deac63315d0e..2b2dc14610d0 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -433,4 +433,5 @@ EXPORT(sys_call_table)
 	PTR	sys_userfaultfd
 	PTR	sys_membarrier
 	PTR	sys_mlock2
+	PTR	sys_copy_file_range		/* 5320 */
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 5a69eb48d0a8..2bf5c8593d91 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -423,4 +423,5 @@ EXPORT(sysn32_call_table)
 	PTR	sys_userfaultfd
 	PTR	sys_membarrier
 	PTR	sys_mlock2
+	PTR	sys_copy_file_range
 	.size	sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index e4b6d7c97822..c5b759e584c7 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -578,4 +578,5 @@ EXPORT(sys32_call_table)
 	PTR	sys_userfaultfd
 	PTR	sys_membarrier
 	PTR	sys_mlock2
+	PTR	sys_copy_file_range		/* 4360 */
 	.size	sys32_call_table,.-sys32_call_table
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 569a7d5242dd..4f607341a793 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -732,21 +732,23 @@ static void __init resource_init(void)
 			end = HIGHMEM_START - 1;
 
 		res = alloc_bootmem(sizeof(struct resource));
+
+		res->start = start;
+		res->end = end;
+		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+
 		switch (boot_mem_map.map[i].type) {
 		case BOOT_MEM_RAM:
 		case BOOT_MEM_INIT_RAM:
 		case BOOT_MEM_ROM_DATA:
 			res->name = "System RAM";
+			res->flags |= IORESOURCE_SYSRAM;
 			break;
 		case BOOT_MEM_RESERVED:
 		default:
 			res->name = "reserved";
 		}
 
-		res->start = start;
-		res->end = end;
-
-		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 		request_resource(&iomem_resource, res);
 
 		/*
@@ -782,6 +784,7 @@ static inline void prefill_possible_map(void) {}
 void __init setup_arch(char **cmdline_p)
 {
 	cpu_probe();
+	mips_cm_probe();
 	prom_init();
 
 	setup_early_fdc_console();
diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c
index d5e0f949dc48..76923349b4fe 100644
--- a/arch/mips/kernel/smp-cmp.c
+++ b/arch/mips/kernel/smp-cmp.c
@@ -149,8 +149,8 @@ void __init cmp_prepare_cpus(unsigned int max_cpus)
 }
 
 struct plat_smp_ops cmp_smp_ops = {
-	.send_ipi_single	= gic_send_ipi_single,
-	.send_ipi_mask		= gic_send_ipi_mask,
+	.send_ipi_single	= mips_smp_send_ipi_single,
+	.send_ipi_mask		= mips_smp_send_ipi_mask,
 	.init_secondary		= cmp_init_secondary,
 	.smp_finish		= cmp_smp_finish,
 	.boot_secondary		= cmp_boot_secondary,
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index 2ad4e4c96d61..253e1409338c 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -472,8 +472,8 @@ static struct plat_smp_ops cps_smp_ops = {
 	.boot_secondary		= cps_boot_secondary,
 	.init_secondary		= cps_init_secondary,
 	.smp_finish		= cps_smp_finish,
-	.send_ipi_single	= gic_send_ipi_single,
-	.send_ipi_mask		= gic_send_ipi_mask,
+	.send_ipi_single	= mips_smp_send_ipi_single,
+	.send_ipi_mask		= mips_smp_send_ipi_mask,
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_disable		= cps_cpu_disable,
 	.cpu_die		= cps_cpu_die,
diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c
index 86311a164ef1..4f9570a57e8d 100644
--- a/arch/mips/kernel/smp-mt.c
+++ b/arch/mips/kernel/smp-mt.c
@@ -121,7 +121,7 @@ static void vsmp_send_ipi_single(int cpu, unsigned int action)
 
 #ifdef CONFIG_MIPS_GIC
 	if (gic_present) {
-		gic_send_ipi_single(cpu, action);
+		mips_smp_send_ipi_single(cpu, action);
 		return;
 	}
 #endif
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index bd4385a8e6e8..37708d9af638 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -33,12 +33,16 @@
 #include <linux/cpu.h>
 #include <linux/err.h>
 #include <linux/ftrace.h>
+#include <linux/irqdomain.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
 
 #include <linux/atomic.h>
 #include <asm/cpu.h>
 #include <asm/processor.h>
 #include <asm/idle.h>
 #include <asm/r4k-timer.h>
+#include <asm/mips-cpc.h>
 #include <asm/mmu_context.h>
 #include <asm/time.h>
 #include <asm/setup.h>
@@ -79,6 +83,11 @@ static cpumask_t cpu_core_setup_map;
 
 cpumask_t cpu_coherent_mask;
 
+#ifdef CONFIG_GENERIC_IRQ_IPI
+static struct irq_desc *call_desc;
+static struct irq_desc *sched_desc;
+#endif
+
 static inline void set_cpu_sibling_map(int cpu)
 {
 	int i;
@@ -121,6 +130,7 @@ static inline void calculate_cpu_foreign_map(void)
 	cpumask_t temp_foreign_map;
 
 	/* Re-calculate the mask */
+	cpumask_clear(&temp_foreign_map);
 	for_each_online_cpu(i) {
 		core_present = 0;
 		for_each_cpu(k, &temp_foreign_map)
@@ -145,6 +155,133 @@ void register_smp_ops(struct plat_smp_ops *ops)
 	mp_ops = ops;
 }
 
+#ifdef CONFIG_GENERIC_IRQ_IPI
+void mips_smp_send_ipi_single(int cpu, unsigned int action)
+{
+	mips_smp_send_ipi_mask(cpumask_of(cpu), action);
+}
+
+void mips_smp_send_ipi_mask(const struct cpumask *mask, unsigned int action)
+{
+	unsigned long flags;
+	unsigned int core;
+	int cpu;
+
+	local_irq_save(flags);
+
+	switch (action) {
+	case SMP_CALL_FUNCTION:
+		__ipi_send_mask(call_desc, mask);
+		break;
+
+	case SMP_RESCHEDULE_YOURSELF:
+		__ipi_send_mask(sched_desc, mask);
+		break;
+
+	default:
+		BUG();
+	}
+
+	if (mips_cpc_present()) {
+		for_each_cpu(cpu, mask) {
+			core = cpu_data[cpu].core;
+
+			if (core == current_cpu_data.core)
+				continue;
+
+			while (!cpumask_test_cpu(cpu, &cpu_coherent_mask)) {
+				mips_cpc_lock_other(core);
+				write_cpc_co_cmd(CPC_Cx_CMD_PWRUP);
+				mips_cpc_unlock_other();
+			}
+		}
+	}
+
+	local_irq_restore(flags);
+}
+
+
+static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
+{
+	scheduler_ipi();
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
+{
+	generic_smp_call_function_interrupt();
+
+	return IRQ_HANDLED;
+}
+
+static struct irqaction irq_resched = {
+	.handler	= ipi_resched_interrupt,
+	.flags		= IRQF_PERCPU,
+	.name		= "IPI resched"
+};
+
+static struct irqaction irq_call = {
+	.handler	= ipi_call_interrupt,
+	.flags		= IRQF_PERCPU,
+	.name		= "IPI call"
+};
+
+static __init void smp_ipi_init_one(unsigned int virq,
+				    struct irqaction *action)
+{
+	int ret;
+
+	irq_set_handler(virq, handle_percpu_irq);
+	ret = setup_irq(virq, action);
+	BUG_ON(ret);
+}
+
+static int __init mips_smp_ipi_init(void)
+{
+	unsigned int call_virq, sched_virq;
+	struct irq_domain *ipidomain;
+	struct device_node *node;
+
+	node = of_irq_find_parent(of_root);
+	ipidomain = irq_find_matching_host(node, DOMAIN_BUS_IPI);
+
+	/*
+	 * Some platforms have half DT setup. So if we found irq node but
+	 * didn't find an ipidomain, try to search for one that is not in the
+	 * DT.
+	 */
+	if (node && !ipidomain)
+		ipidomain = irq_find_matching_host(NULL, DOMAIN_BUS_IPI);
+
+	BUG_ON(!ipidomain);
+
+	call_virq = irq_reserve_ipi(ipidomain, cpu_possible_mask);
+	BUG_ON(!call_virq);
+
+	sched_virq = irq_reserve_ipi(ipidomain, cpu_possible_mask);
+	BUG_ON(!sched_virq);
+
+	if (irq_domain_is_ipi_per_cpu(ipidomain)) {
+		int cpu;
+
+		for_each_cpu(cpu, cpu_possible_mask) {
+			smp_ipi_init_one(call_virq + cpu, &irq_call);
+			smp_ipi_init_one(sched_virq + cpu, &irq_resched);
+		}
+	} else {
+		smp_ipi_init_one(call_virq, &irq_call);
+		smp_ipi_init_one(sched_virq, &irq_resched);
+	}
+
+	call_desc = irq_to_desc(call_virq);
+	sched_desc = irq_to_desc(sched_virq);
+
+	return 0;
+}
+early_initcall(mips_smp_ipi_init);
+#endif
+
 /*
  * First C code run on the secondary CPUs after being started up by
  * the master.
@@ -191,7 +328,7 @@ asmlinkage void start_secondary(void)
 	WARN_ON_ONCE(!irqs_disabled());
 	mp_ops->smp_finish();
 
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
 static void stop_this_cpu(void *dummy)
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index bafcb7ad5c85..bf14da9f3e33 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -663,7 +663,7 @@ static int simulate_rdhwr_normal(struct pt_regs *regs, unsigned int opcode)
 	return -1;
 }
 
-static int simulate_rdhwr_mm(struct pt_regs *regs, unsigned short opcode)
+static int simulate_rdhwr_mm(struct pt_regs *regs, unsigned int opcode)
 {
 	if ((opcode & MM_POOL32A_FUNC) == MM_RDHWR) {
 		int rd = (opcode & MM_RS) >> 16;
@@ -690,15 +690,15 @@ static int simulate_sync(struct pt_regs *regs, unsigned int opcode)
 asmlinkage void do_ov(struct pt_regs *regs)
 {
 	enum ctx_state prev_state;
-	siginfo_t info;
+	siginfo_t info = {
+		.si_signo = SIGFPE,
+		.si_code = FPE_INTOVF,
+		.si_addr = (void __user *)regs->cp0_epc,
+	};
 
 	prev_state = exception_enter();
 	die_if_kernel("Integer overflow", regs);
 
-	info.si_code = FPE_INTOVF;
-	info.si_signo = SIGFPE;
-	info.si_errno = 0;
-	info.si_addr = (void __user *) regs->cp0_epc;
 	force_sig_info(SIGFPE, &info, current);
 	exception_exit(prev_state);
 }
@@ -874,7 +874,7 @@ out:
 void do_trap_or_bp(struct pt_regs *regs, unsigned int code,
 	const char *str)
 {
-	siginfo_t info;
+	siginfo_t info = { 0 };
 	char b[40];
 
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
@@ -903,7 +903,6 @@ void do_trap_or_bp(struct pt_regs *regs, unsigned int code,
 		else
 			info.si_code = FPE_INTOVF;
 		info.si_signo = SIGFPE;
-		info.si_errno = 0;
 		info.si_addr = (void __user *) regs->cp0_epc;
 		force_sig_info(SIGFPE, &info, current);
 		break;
@@ -1119,11 +1118,12 @@ no_r2_instr:
 	if (get_isa16_mode(regs->cp0_epc)) {
 		unsigned short mmop[2] = { 0 };
 
-		if (unlikely(get_user(mmop[0], epc) < 0))
+		if (unlikely(get_user(mmop[0], (u16 __user *)epc + 0) < 0))
 			status = SIGSEGV;
-		if (unlikely(get_user(mmop[1], epc) < 0))
+		if (unlikely(get_user(mmop[1], (u16 __user *)epc + 1) < 0))
 			status = SIGSEGV;
-		opcode = (mmop[0] << 16) | mmop[1];
+		opcode = mmop[0];
+		opcode = (opcode << 16) | mmop[1];
 
 		if (status < 0)
 			status = simulate_rdhwr_mm(regs, opcode);
@@ -1369,26 +1369,12 @@ asmlinkage void do_cpu(struct pt_regs *regs)
 		if (unlikely(compute_return_epc(regs) < 0))
 			break;
 
-		if (get_isa16_mode(regs->cp0_epc)) {
-			unsigned short mmop[2] = { 0 };
-
-			if (unlikely(get_user(mmop[0], epc) < 0))
-				status = SIGSEGV;
-			if (unlikely(get_user(mmop[1], epc) < 0))
-				status = SIGSEGV;
-			opcode = (mmop[0] << 16) | mmop[1];
-
-			if (status < 0)
-				status = simulate_rdhwr_mm(regs, opcode);
-		} else {
+		if (!get_isa16_mode(regs->cp0_epc)) {
 			if (unlikely(get_user(opcode, epc) < 0))
 				status = SIGSEGV;
 
 			if (!cpu_has_llsc && status < 0)
 				status = simulate_llsc(regs, opcode);
-
-			if (status < 0)
-				status = simulate_rdhwr_normal(regs, opcode);
 		}
 
 		if (status < 0)
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 8bc3977576e6..70ef1a43c114 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -445,8 +445,8 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 
 	dvcpu->arch.wait = 0;
 
-	if (waitqueue_active(&dvcpu->wq))
-		wake_up_interruptible(&dvcpu->wq);
+	if (swait_active(&dvcpu->wq))
+		swake_up(&dvcpu->wq);
 
 	return 0;
 }
@@ -702,7 +702,7 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu,
 	} else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) {
 		void __user *uaddr = (void __user *)(long)reg->addr;
 
-		return copy_to_user(uaddr, vs, 16);
+		return copy_to_user(uaddr, vs, 16) ? -EFAULT : 0;
 	} else {
 		return -EINVAL;
 	}
@@ -732,7 +732,7 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu,
 	} else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) {
 		void __user *uaddr = (void __user *)(long)reg->addr;
 
-		return copy_from_user(vs, uaddr, 16);
+		return copy_from_user(vs, uaddr, 16) ? -EFAULT : 0;
 	} else {
 		return -EINVAL;
 	}
@@ -1174,8 +1174,8 @@ static void kvm_mips_comparecount_func(unsigned long data)
 	kvm_mips_callbacks->queue_timer_int(vcpu);
 
 	vcpu->arch.wait = 0;
-	if (waitqueue_active(&vcpu->wq))
-		wake_up_interruptible(&vcpu->wq);
+	if (swait_active(&vcpu->wq))
+		swake_up(&vcpu->wq);
 }
 
 /* low level hrtimer wake routine */
diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c
index 5c81fdd032c3..353037699512 100644
--- a/arch/mips/mm/mmap.c
+++ b/arch/mips/mm/mmap.c
@@ -146,7 +146,7 @@ unsigned long arch_mmap_rnd(void)
 {
 	unsigned long rnd;
 
-	rnd = (unsigned long)get_random_int();
+	rnd = get_random_long();
 	rnd <<= PAGE_SHIFT;
 	if (TASK_IS_32BIT_ADDR)
 		rnd &= 0xfffffful;
@@ -174,7 +174,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 
 static inline unsigned long brk_rnd(void)
 {
-	unsigned long rnd = get_random_int();
+	unsigned long rnd = get_random_long();
 
 	rnd = rnd << PAGE_SHIFT;
 	/* 8MB for 32bit, 256MB for 64bit */
diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c
index 3bd0597d9c3d..91dec32c77b7 100644
--- a/arch/mips/mm/sc-mips.c
+++ b/arch/mips/mm/sc-mips.c
@@ -164,11 +164,13 @@ static int __init mips_sc_probe_cm3(void)
 
 	sets = cfg & CM_GCR_L2_CONFIG_SET_SIZE_MSK;
 	sets >>= CM_GCR_L2_CONFIG_SET_SIZE_SHF;
-	c->scache.sets = 64 << sets;
+	if (sets)
+		c->scache.sets = 64 << sets;
 
 	line_sz = cfg & CM_GCR_L2_CONFIG_LINE_SIZE_MSK;
 	line_sz >>= CM_GCR_L2_CONFIG_LINE_SIZE_SHF;
-	c->scache.linesz = 2 << line_sz;
+	if (line_sz)
+		c->scache.linesz = 2 << line_sz;
 
 	assoc = cfg & CM_GCR_L2_CONFIG_ASSOC_MSK;
 	assoc >>= CM_GCR_L2_CONFIG_ASSOC_SHF;
@@ -176,13 +178,12 @@ static int __init mips_sc_probe_cm3(void)
 	c->scache.waysize = c->scache.sets * c->scache.linesz;
 	c->scache.waybit = __ffs(c->scache.waysize);
 
-	c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT;
+	if (c->scache.linesz) {
+		c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT;
+		return 1;
+	}
 
-	return 1;
-}
-
-void __weak platform_early_l2_init(void)
-{
+	return 0;
 }
 
 static inline int __init mips_sc_probe(void)
@@ -194,12 +195,6 @@ static inline int __init mips_sc_probe(void)
 	/* Mark as not present until probe completed */
 	c->scache.flags |= MIPS_CACHE_NOT_PRESENT;
 
-	/*
-	 * Do we need some platform specific probing before
-	 * we configure L2?
-	 */
-	platform_early_l2_init();
-
 	if (mips_cm_revision() >= CM_REV_CM3)
 		return mips_sc_probe_cm3();
 
diff --git a/arch/mips/mti-malta/malta-init.c b/arch/mips/mti-malta/malta-init.c
index 571148c5fd0b..dc2c5214809d 100644
--- a/arch/mips/mti-malta/malta-init.c
+++ b/arch/mips/mti-malta/malta-init.c
@@ -293,7 +293,6 @@ mips_pci_controller:
 	console_config();
 #endif
 	/* Early detection of CMP support */
-	mips_cm_probe();
 	mips_cpc_probe();
 
 	if (!register_cps_smp_ops())
@@ -304,10 +303,3 @@ mips_pci_controller:
 		return;
 	register_up_smp_ops();
 }
-
-void platform_early_l2_init(void)
-{
-	/* L2 configuration lives in the CM3 */
-	if (mips_cm_revision() >= CM_REV_CM3)
-		mips_cm_probe();
-}
diff --git a/arch/mips/pci/fixup-loongson3.c b/arch/mips/pci/fixup-loongson3.c
index d708ae46d325..2b6d5e196f99 100644
--- a/arch/mips/pci/fixup-loongson3.c
+++ b/arch/mips/pci/fixup-loongson3.c
@@ -40,20 +40,25 @@ int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 
 static void pci_fixup_radeon(struct pci_dev *pdev)
 {
-	if (pdev->resource[PCI_ROM_RESOURCE].start)
+	struct resource *res = &pdev->resource[PCI_ROM_RESOURCE];
+
+	if (res->start)
 		return;
 
 	if (!loongson_sysconf.vgabios_addr)
 		return;
 
-	pdev->resource[PCI_ROM_RESOURCE].start =
-		loongson_sysconf.vgabios_addr;
-	pdev->resource[PCI_ROM_RESOURCE].end   =
-		loongson_sysconf.vgabios_addr + 256*1024 - 1;
-	pdev->resource[PCI_ROM_RESOURCE].flags |= IORESOURCE_ROM_COPY;
+	pci_disable_rom(pdev);
+	if (res->parent)
+		release_resource(res);
+
+	res->start = virt_to_phys((void *) loongson_sysconf.vgabios_addr);
+	res->end   = res->start + 256*1024 - 1;
+	res->flags = IORESOURCE_MEM | IORESOURCE_ROM_SHADOW |
+		     IORESOURCE_PCI_FIXED;
 
 	dev_info(&pdev->dev, "BAR %d: assigned %pR for Radeon ROM\n",
-			PCI_ROM_RESOURCE, &pdev->resource[PCI_ROM_RESOURCE]);
+		 PCI_ROM_RESOURCE, res);
 }
 
 DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_ATI, PCI_ANY_ID,
diff --git a/arch/mips/pci/pci-mt7620.c b/arch/mips/pci/pci-mt7620.c
index a009ee458934..1ae932c2d78b 100644
--- a/arch/mips/pci/pci-mt7620.c
+++ b/arch/mips/pci/pci-mt7620.c
@@ -297,12 +297,12 @@ static int mt7620_pci_probe(struct platform_device *pdev)
 		return PTR_ERR(rstpcie0);
 
 	bridge_base = devm_ioremap_resource(&pdev->dev, bridge_res);
-	if (!bridge_base)
-		return -ENOMEM;
+	if (IS_ERR(bridge_base))
+		return PTR_ERR(bridge_base);
 
 	pcie_base = devm_ioremap_resource(&pdev->dev, pcie_res);
-	if (!pcie_base)
-		return -ENOMEM;
+	if (IS_ERR(pcie_base))
+		return PTR_ERR(pcie_base);
 
 	iomem_resource.start = 0;
 	iomem_resource.end = ~0;
diff --git a/arch/mn10300/include/asm/pci.h b/arch/mn10300/include/asm/pci.h
index be3debb8fc02..51159fff025a 100644
--- a/arch/mn10300/include/asm/pci.h
+++ b/arch/mn10300/include/asm/pci.h
@@ -80,9 +80,6 @@ extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 
 #endif /* __KERNEL__ */
 
-/* implement the pci_ DMA API in terms of the generic device dma_ one */
-#include <asm-generic/pci-dma-compat.h>
-
 static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 {
 	return channel ? 15 : 14;
diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c
index f984193718b1..426173c4b0b9 100644
--- a/arch/mn10300/kernel/smp.c
+++ b/arch/mn10300/kernel/smp.c
@@ -675,7 +675,7 @@ int __init start_secondary(void *unused)
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 	init_clockevents();
 #endif
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 	return 0;
 }
 
diff --git a/arch/parisc/include/asm/cache.h b/arch/parisc/include/asm/cache.h
index 3d0e17bcc8e9..df0f52bd18b4 100644
--- a/arch/parisc/include/asm/cache.h
+++ b/arch/parisc/include/asm/cache.h
@@ -22,6 +22,9 @@
 
 #define __read_mostly __attribute__((__section__(".data..read_mostly")))
 
+/* Read-only memory is marked before mark_rodata_ro() is called. */
+#define __ro_after_init	__read_mostly
+
 void parisc_cache_init(void);	/* initializes cache-flushing */
 void disable_sr_hashing_asm(int); /* low level support for above */
 void disable_sr_hashing(void);   /* turns off space register hashing */
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index 845272ce9cc5..7bd69bd43a01 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -121,10 +121,6 @@ flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vma
 	}
 }
 
-#ifdef CONFIG_DEBUG_RODATA
-void mark_rodata_ro(void);
-#endif
-
 #include <asm/kmap_types.h>
 
 #define ARCH_HAS_KMAP
diff --git a/arch/parisc/include/asm/floppy.h b/arch/parisc/include/asm/floppy.h
index f84ff12574b7..6d8276cd25ca 100644
--- a/arch/parisc/include/asm/floppy.h
+++ b/arch/parisc/include/asm/floppy.h
@@ -33,7 +33,7 @@
  * floppy accesses go through the track buffer.
  */
 #define _CROSS_64KB(a,s,vdma) \
-(!vdma && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64))
+(!(vdma) && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64))
 
 #define CROSS_64KB(a,s) _CROSS_64KB(a,s,use_virtual_dma & 1)
 
diff --git a/arch/parisc/include/asm/pci.h b/arch/parisc/include/asm/pci.h
index 89c53bfff055..defebd956585 100644
--- a/arch/parisc/include/asm/pci.h
+++ b/arch/parisc/include/asm/pci.h
@@ -194,9 +194,6 @@ extern void pcibios_init_bridge(struct pci_dev *);
 #define PCIBIOS_MIN_IO          0x10
 #define PCIBIOS_MIN_MEM         0x1000 /* NBPG - but pci/setup-res.c dies */
 
-/* export the pci_ DMA API in terms of the dma_ one */
-#include <asm-generic/pci-dma-compat.h>
-
 static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 {
 	return channel ? 15 : 14;
diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h
index 35bdccbb2036..b75039f92116 100644
--- a/arch/parisc/include/uapi/asm/unistd.h
+++ b/arch/parisc/include/uapi/asm/unistd.h
@@ -361,8 +361,9 @@
 #define __NR_membarrier		(__NR_Linux + 343)
 #define __NR_userfaultfd	(__NR_Linux + 344)
 #define __NR_mlock2		(__NR_Linux + 345)
+#define __NR_copy_file_range	(__NR_Linux + 346)
 
-#define __NR_Linux_syscalls	(__NR_mlock2 + 1)
+#define __NR_Linux_syscalls	(__NR_copy_file_range + 1)
 
 
 #define __IGNORE_select		/* newselect */
diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c
index 9585c81f755f..ce0b2b4075c7 100644
--- a/arch/parisc/kernel/ptrace.c
+++ b/arch/parisc/kernel/ptrace.c
@@ -269,14 +269,19 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 
 long do_syscall_trace_enter(struct pt_regs *regs)
 {
-	long ret = 0;
-
 	/* Do the secure computing check first. */
 	secure_computing_strict(regs->gr[20]);
 
 	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
-	    tracehook_report_syscall_entry(regs))
-		ret = -1L;
+	    tracehook_report_syscall_entry(regs)) {
+		/*
+		 * Tracing decided this syscall should not happen or the
+		 * debugger stored an invalid system call number. Skip
+		 * the system call and the system call restart handling.
+		 */
+		regs->gr[20] = -1UL;
+		goto out;
+	}
 
 #ifdef CONFIG_64BIT
 	if (!is_compat_task())
@@ -290,7 +295,8 @@ long do_syscall_trace_enter(struct pt_regs *regs)
 			regs->gr[24] & 0xffffffff,
 			regs->gr[23] & 0xffffffff);
 
-	return ret ? : regs->gr[20];
+out:
+	return regs->gr[20];
 }
 
 void do_syscall_trace_exit(struct pt_regs *regs)
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 52e85973a283..c2a9cc55a62f 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -305,7 +305,7 @@ void __init smp_callin(void)
 
 	local_irq_enable();  /* Interrupts have been off until now */
 
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 
 	/* NOTREACHED */
 	panic("smp_callin() AAAAaaaaahhhh....\n");
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index 3fbd7252a4b2..fbafa0d0e2bf 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -343,7 +343,7 @@ tracesys_next:
 #endif
 
 	comiclr,>>=	__NR_Linux_syscalls, %r20, %r0
-	b,n	.Lsyscall_nosys
+	b,n	.Ltracesys_nosys
 
 	LDREGX  %r20(%r19), %r19
 
@@ -359,6 +359,9 @@ tracesys_next:
 	be      0(%sr7,%r19)
 	ldo	R%tracesys_exit(%r2),%r2
 
+.Ltracesys_nosys:
+	ldo	-ENOSYS(%r0),%r28		/* set errno */
+
 	/* Do *not* call this function on the gateway page, because it
 	makes a direct call to syscall_trace. */
 	
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index d4ffcfbc9885..585d50fc75c0 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -441,6 +441,7 @@
 	ENTRY_SAME(membarrier)
 	ENTRY_SAME(userfaultfd)
 	ENTRY_SAME(mlock2)		/* 345 */
+	ENTRY_SAME(copy_file_range)
 
 
 .ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b))
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 1b366c477687..3c07d6b96877 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -55,12 +55,12 @@ signed char pfnnid_map[PFNNID_MAP_MAX] __read_mostly;
 
 static struct resource data_resource = {
 	.name	= "Kernel data",
-	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM,
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
 };
 
 static struct resource code_resource = {
 	.name	= "Kernel code",
-	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM,
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
 };
 
 static struct resource pdcdata_resource = {
@@ -201,7 +201,7 @@ static void __init setup_bootmem(void)
 		res->name = "System RAM";
 		res->start = pmem_ranges[i].start_pfn << PAGE_SHIFT;
 		res->end = res->start + (pmem_ranges[i].pages << PAGE_SHIFT)-1;
-		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+		res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 		request_resource(&iomem_resource, res);
 	}
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index e4824fd04bb7..832cc461d0af 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -557,7 +557,7 @@ choice
 
 config PPC_4K_PAGES
 	bool "4k page size"
-	select HAVE_ARCH_SOFT_DIRTY if CHECKPOINT_RESTORE && PPC_BOOK3S
+	select HAVE_ARCH_SOFT_DIRTY if PPC_BOOK3S_64
 
 config PPC_16K_PAGES
 	bool "16k page size"
@@ -566,7 +566,7 @@ config PPC_16K_PAGES
 config PPC_64K_PAGES
 	bool "64k page size"
 	depends on !PPC_FSL_BOOK3E && (44x || PPC_STD_MMU_64 || PPC_BOOK3E_64)
-	select HAVE_ARCH_SOFT_DIRTY if CHECKPOINT_RESTORE && PPC_BOOK3S
+	select HAVE_ARCH_SOFT_DIRTY if PPC_BOOK3S_64
 
 config PPC_256K_PAGES
 	bool "256k page size"
@@ -828,14 +828,10 @@ config PCI_8260
 	select PPC_INDIRECT_PCI
 	default y
 
-source "drivers/pci/pcie/Kconfig"
-
 source "drivers/pci/Kconfig"
 
 source "drivers/pcmcia/Kconfig"
 
-source "drivers/pci/hotplug/Kconfig"
-
 config HAS_RAPIDIO
 	bool
 	default n
diff --git a/arch/powerpc/crypto/aes-spe-glue.c b/arch/powerpc/crypto/aes-spe-glue.c
index 93ee046d12cd..ab113198ed20 100644
--- a/arch/powerpc/crypto/aes-spe-glue.c
+++ b/arch/powerpc/crypto/aes-spe-glue.c
@@ -22,6 +22,7 @@
 #include <asm/byteorder.h>
 #include <asm/switch_to.h>
 #include <crypto/algapi.h>
+#include <crypto/xts.h>
 
 /*
  * MAX_BYTES defines the number of bytes that are allowed to be processed
@@ -126,6 +127,11 @@ static int ppc_xts_setkey(struct crypto_tfm *tfm, const u8 *in_key,
 		   unsigned int key_len)
 {
 	struct ppc_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+	int err;
+
+	err = xts_check_key(tfm, in_key, key_len);
+	if (err)
+		return err;
 
 	key_len >>= 1;
 
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 8d1c41d28318..ac07a30a7934 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -281,6 +281,10 @@ extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 			    pmd_t *pmdp);
 
+#define __HAVE_ARCH_PMDP_HUGE_SPLIT_PREPARE
+extern void pmdp_huge_split_prepare(struct vm_area_struct *vma,
+				    unsigned long address, pmd_t *pmdp);
+
 #define pmd_move_must_withdraw pmd_move_must_withdraw
 struct spinlock;
 static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index c5eb86f3d452..867c39b45df6 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -81,6 +81,7 @@ struct pci_dn;
 #define EEH_PE_KEEP		(1 << 8)	/* Keep PE on hotplug	*/
 #define EEH_PE_CFG_RESTRICTED	(1 << 9)	/* Block config on error */
 #define EEH_PE_REMOVED		(1 << 10)	/* Removed permanently	*/
+#define EEH_PE_PRI_BUS		(1 << 11)	/* Cached primary bus   */
 
 struct eeh_pe {
 	int type;			/* PE type: PHB/Bus/Device	*/
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 2aa79c864e91..7529aab068f5 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -33,8 +33,6 @@ static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu)
 }
 #endif
 
-#define SPAPR_TCE_SHIFT		12
-
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 #define KVM_DEFAULT_HPT_ORDER	24	/* 16MB HPT by default */
 #endif
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 9d08d8cbed1a..d7b343170453 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -182,7 +182,10 @@ struct kvmppc_spapr_tce_table {
 	struct list_head list;
 	struct kvm *kvm;
 	u64 liobn;
-	u32 window_size;
+	struct rcu_head rcu;
+	u32 page_shift;
+	u64 offset;		/* in pages */
+	u64 size;		/* window size in pages */
 	struct page *pages[0];
 };
 
@@ -289,7 +292,7 @@ struct kvmppc_vcore {
 	struct list_head runnable_threads;
 	struct list_head preempt_list;
 	spinlock_t lock;
-	wait_queue_head_t wq;
+	struct swait_queue_head wq;
 	spinlock_t stoltb_lock;	/* protects stolen_tb and preempt_tb */
 	u64 stolen_tb;
 	u64 preempt_tb;
@@ -629,7 +632,7 @@ struct kvm_vcpu_arch {
 	u8 prodded;
 	u32 last_inst;
 
-	wait_queue_head_t *wqp;
+	struct swait_queue_head *wqp;
 	struct kvmppc_vcore *vcore;
 	int ret;
 	int trap;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 2241d5357129..2544edabe7f3 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -165,9 +165,25 @@ extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu,
 extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
 
 extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
-				struct kvm_create_spapr_tce *args);
+				struct kvm_create_spapr_tce_64 *args);
+extern struct kvmppc_spapr_tce_table *kvmppc_find_table(
+		struct kvm_vcpu *vcpu, unsigned long liobn);
+extern long kvmppc_ioba_validate(struct kvmppc_spapr_tce_table *stt,
+		unsigned long ioba, unsigned long npages);
+extern long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *tt,
+		unsigned long tce);
+extern long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
+		unsigned long *ua, unsigned long **prmap);
+extern void kvmppc_tce_put(struct kvmppc_spapr_tce_table *tt,
+		unsigned long idx, unsigned long tce);
 extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 			     unsigned long ioba, unsigned long tce);
+extern long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
+		unsigned long liobn, unsigned long ioba,
+		unsigned long tce_list, unsigned long npages);
+extern long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
+		unsigned long liobn, unsigned long ioba,
+		unsigned long tce_value, unsigned long npages);
 extern long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 			     unsigned long ioba);
 extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
@@ -437,6 +453,8 @@ static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.irq_type == KVMPPC_IRQ_XICS;
 }
+extern void kvmppc_alloc_host_rm_ops(void);
+extern void kvmppc_free_host_rm_ops(void);
 extern void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu);
 extern int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu, unsigned long server);
 extern int kvm_vm_ioctl_xics_irq(struct kvm *kvm, struct kvm_irq_level *args);
@@ -445,7 +463,11 @@ extern u64 kvmppc_xics_get_icp(struct kvm_vcpu *vcpu);
 extern int kvmppc_xics_set_icp(struct kvm_vcpu *vcpu, u64 icpval);
 extern int kvmppc_xics_connect_vcpu(struct kvm_device *dev,
 			struct kvm_vcpu *vcpu, u32 cpu);
+extern void kvmppc_xics_ipi_action(void);
+extern int h_ipi_redirect;
 #else
+static inline void kvmppc_alloc_host_rm_ops(void) {};
+static inline void kvmppc_free_host_rm_ops(void) {};
 static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu)
 	{ return 0; }
 static inline void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu) { }
@@ -459,6 +481,33 @@ static inline int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd)
 	{ return 0; }
 #endif
 
+/*
+ * Host-side operations we want to set up while running in real
+ * mode in the guest operating on the xics.
+ * Currently only VCPU wakeup is supported.
+ */
+
+union kvmppc_rm_state {
+	unsigned long raw;
+	struct {
+		u32 in_host;
+		u32 rm_action;
+	};
+};
+
+struct kvmppc_host_rm_core {
+	union kvmppc_rm_state rm_state;
+	void *rm_data;
+	char pad[112];
+};
+
+struct kvmppc_host_rm_ops {
+	struct kvmppc_host_rm_core	*rm_core;
+	void		(*vcpu_kick)(struct kvm_vcpu *vcpu);
+};
+
+extern struct kvmppc_host_rm_ops *kvmppc_host_rm_ops_hv;
+
 static inline unsigned long kvmppc_get_epr(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_KVM_BOOKE_HV
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 54843ca5fa2b..78968c1ff931 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -10,7 +10,6 @@
 #include <linux/pci.h>
 #include <linux/list.h>
 #include <linux/ioport.h>
-#include <asm-generic/pci-bridge.h>
 
 struct device_node;
 
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 6f8065a7d487..a6f3ac0d4602 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -20,8 +20,6 @@
 #include <asm/prom.h>
 #include <asm/pci-bridge.h>
 
-#include <asm-generic/pci-dma-compat.h>
-
 /* Return values for pci_controller_ops.probe_mode function */
 #define PCI_PROBE_NONE		-1	/* Don't look at this bus at all */
 #define PCI_PROBE_NORMAL	0	/* Do normal PCI probing */
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index ac9fb114e25d..47897a30982d 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -78,6 +78,9 @@ static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
 	}
 	return __find_linux_pte_or_hugepte(pgdir, ea, is_thp, shift);
 }
+
+unsigned long vmalloc_to_phys(void *vmalloc_addr);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_PGTABLE_H */
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 825663c30945..78083ed20792 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -114,6 +114,9 @@ extern int cpu_to_core_id(int cpu);
 #define PPC_MSG_TICK_BROADCAST	2
 #define PPC_MSG_DEBUGGER_BREAK  3
 
+/* This is only used by the powernv kernel */
+#define PPC_MSG_RM_HOST_ACTION	4
+
 /* for irq controllers that have dedicated ipis per message (4) */
 extern int smp_request_message_ipi(int virq, int message);
 extern const char *smp_ipi_name[];
@@ -121,6 +124,7 @@ extern const char *smp_ipi_name[];
 /* for irq controllers with only a single ipi */
 extern void smp_muxed_ipi_set_data(int cpu, unsigned long data);
 extern void smp_muxed_ipi_message_pass(int cpu, int msg);
+extern void smp_muxed_ipi_set_message(int cpu, int msg);
 extern irqreturn_t smp_ipi_demux(void);
 
 void smp_init_pSeries(void);
diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h
index 8e86b48d0369..32e36b16773f 100644
--- a/arch/powerpc/include/asm/trace.h
+++ b/arch/powerpc/include/asm/trace.h
@@ -57,12 +57,14 @@ DEFINE_EVENT(ppc64_interrupt_class, timer_interrupt_exit,
 extern void hcall_tracepoint_regfunc(void);
 extern void hcall_tracepoint_unregfunc(void);
 
-TRACE_EVENT_FN(hcall_entry,
+TRACE_EVENT_FN_COND(hcall_entry,
 
 	TP_PROTO(unsigned long opcode, unsigned long *args),
 
 	TP_ARGS(opcode, args),
 
+	TP_CONDITION(cpu_online(raw_smp_processor_id())),
+
 	TP_STRUCT__entry(
 		__field(unsigned long, opcode)
 	),
@@ -76,13 +78,15 @@ TRACE_EVENT_FN(hcall_entry,
 	hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc
 );
 
-TRACE_EVENT_FN(hcall_exit,
+TRACE_EVENT_FN_COND(hcall_exit,
 
 	TP_PROTO(unsigned long opcode, unsigned long retval,
 		unsigned long *retbuf),
 
 	TP_ARGS(opcode, retval, retbuf),
 
+	TP_CONDITION(cpu_online(raw_smp_processor_id())),
+
 	TP_STRUCT__entry(
 		__field(unsigned long, opcode)
 		__field(unsigned long, retval)
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index 0e25bdb190bb..254604856e69 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -30,6 +30,7 @@
 #ifdef CONFIG_PPC_ICP_NATIVE
 extern int icp_native_init(void);
 extern void icp_native_flush_interrupt(void);
+extern void icp_native_cause_ipi_rm(int cpu);
 #else
 static inline int icp_native_init(void) { return -ENODEV; }
 #endif
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index ab4d4732c492..c93cf35ce379 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -333,6 +333,15 @@ struct kvm_create_spapr_tce {
 	__u32 window_size;
 };
 
+/* for KVM_CAP_SPAPR_TCE_64 */
+struct kvm_create_spapr_tce_64 {
+	__u64 liobn;
+	__u32 page_shift;
+	__u32 flags;
+	__u64 offset;	/* in pages */
+	__u64 size;	/* in pages */
+};
+
 /* for KVM_ALLOCATE_RMA */
 struct kvm_allocate_rma {
 	__u64 rma_size;
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 938742135ee0..650cfb31ea3d 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -418,8 +418,7 @@ static void *eeh_rmv_device(void *data, void *userdata)
 		eeh_pcid_put(dev);
 		if (driver->err_handler &&
 		    driver->err_handler->error_detected &&
-		    driver->err_handler->slot_reset &&
-		    driver->err_handler->resume)
+		    driver->err_handler->slot_reset)
 			return NULL;
 	}
 
@@ -564,6 +563,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	 */
 	eeh_pe_state_mark(pe, EEH_PE_KEEP);
 	if (bus) {
+		eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
 		pci_lock_rescan_remove();
 		pcibios_remove_pci_devices(bus);
 		pci_unlock_rescan_remove();
@@ -803,6 +803,7 @@ perm_error:
 	 * the their PCI config any more.
 	 */
 	if (frozen_bus) {
+		eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
 		eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
 
 		pci_lock_rescan_remove();
@@ -886,6 +887,7 @@ static void eeh_handle_special_event(void)
 					continue;
 
 				/* Notify all devices to be down */
+				eeh_pe_state_clear(pe, EEH_PE_PRI_BUS);
 				bus = eeh_pe_bus_get(phb_pe);
 				eeh_pe_dev_traverse(pe,
 					eeh_report_failure, NULL);
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index ca9e5371930e..98f81800e00c 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -928,7 +928,7 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
 		bus = pe->phb->bus;
 	} else if (pe->type & EEH_PE_BUS ||
 		   pe->type & EEH_PE_DEVICE) {
-		if (pe->bus) {
+		if (pe->state & EEH_PE_PRI_BUS) {
 			bus = pe->bus;
 			goto out;
 		}
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 05e804cdecaa..aec9a1b1d25b 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -109,8 +109,9 @@ void arch_unregister_hw_breakpoint(struct perf_event *bp)
 	 * If the breakpoint is unregistered between a hw_breakpoint_handler()
 	 * and the single_step_dabr_instruction(), then cleanup the breakpoint
 	 * restoration variables to prevent dangling pointers.
+	 * FIXME, this should not be using bp->ctx at all! Sayeth peterz.
 	 */
-	if (bp->ctx && bp->ctx->task)
+	if (bp->ctx && bp->ctx->task && bp->ctx->task != ((void *)-1L))
 		bp->ctx->task->thread.last_hit_ubp = NULL;
 }
 
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index ac64ffdb52c8..08b7a40de5f8 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -340,7 +340,7 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab)
 			if (name[0] == '.') {
 				if (strcmp(name+1, "TOC.") == 0)
 					syms[i].st_shndx = SHN_ABS;
-				memmove(name, name+1, strlen(name));
+				syms[i].st_name++;
 			}
 		}
 	}
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index dccc87e8fee5..3c5736e52a14 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1768,9 +1768,9 @@ static inline unsigned long brk_rnd(void)
 
 	/* 8MB for 32bit, 1GB for 64bit */
 	if (is_32bit_task())
-		rnd = (long)(get_random_int() % (1<<(23-PAGE_SHIFT)));
+		rnd = (get_random_long() % (1UL<<(23-PAGE_SHIFT)));
 	else
-		rnd = (long)(get_random_int() % (1<<(30-PAGE_SHIFT)));
+		rnd = (get_random_long() % (1UL<<(30-PAGE_SHIFT)));
 
 	return rnd << PAGE_SHIFT;
 }
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index ad8c9db61237..d544fa311757 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -114,8 +114,6 @@ extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */
 
 notrace void __init machine_init(u64 dt_ptr)
 {
-	lockdep_init();
-
 	/* Enable early debugging if any specified (see udbg.h) */
 	udbg_early_init();
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 5c03a6a9b054..f98be8383a39 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -255,9 +255,6 @@ void __init early_setup(unsigned long dt_ptr)
 	setup_paca(&boot_paca);
 	fixup_boot_paca();
 
-	/* Initialize lockdep early or else spinlocks will blow */
-	lockdep_init();
-
 	/* -------- printk is now safe to use ------- */
 
 	/* Enable early debugging if any specified (see udbg.h) */
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index ec9ec2058d2d..b7dea05f0725 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -206,7 +206,7 @@ int smp_request_message_ipi(int virq, int msg)
 
 #ifdef CONFIG_PPC_SMP_MUXED_IPI
 struct cpu_messages {
-	int messages;			/* current messages */
+	long messages;			/* current messages */
 	unsigned long data;		/* data for cause ipi */
 };
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct cpu_messages, ipi_message);
@@ -218,7 +218,7 @@ void smp_muxed_ipi_set_data(int cpu, unsigned long data)
 	info->data = data;
 }
 
-void smp_muxed_ipi_message_pass(int cpu, int msg)
+void smp_muxed_ipi_set_message(int cpu, int msg)
 {
 	struct cpu_messages *info = &per_cpu(ipi_message, cpu);
 	char *message = (char *)&info->messages;
@@ -228,6 +228,13 @@ void smp_muxed_ipi_message_pass(int cpu, int msg)
 	 */
 	smp_mb();
 	message[msg] = 1;
+}
+
+void smp_muxed_ipi_message_pass(int cpu, int msg)
+{
+	struct cpu_messages *info = &per_cpu(ipi_message, cpu);
+
+	smp_muxed_ipi_set_message(cpu, msg);
 	/*
 	 * cause_ipi functions are required to include a full barrier
 	 * before doing whatever causes the IPI.
@@ -236,20 +243,31 @@ void smp_muxed_ipi_message_pass(int cpu, int msg)
 }
 
 #ifdef __BIG_ENDIAN__
-#define IPI_MESSAGE(A) (1 << (24 - 8 * (A)))
+#define IPI_MESSAGE(A) (1uL << ((BITS_PER_LONG - 8) - 8 * (A)))
 #else
-#define IPI_MESSAGE(A) (1 << (8 * (A)))
+#define IPI_MESSAGE(A) (1uL << (8 * (A)))
 #endif
 
 irqreturn_t smp_ipi_demux(void)
 {
 	struct cpu_messages *info = this_cpu_ptr(&ipi_message);
-	unsigned int all;
+	unsigned long all;
 
 	mb();	/* order any irq clear */
 
 	do {
 		all = xchg(&info->messages, 0);
+#if defined(CONFIG_KVM_XICS) && defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE)
+		/*
+		 * Must check for PPC_MSG_RM_HOST_ACTION messages
+		 * before PPC_MSG_CALL_FUNCTION messages because when
+		 * a VM is destroyed, we call kick_all_cpus_sync()
+		 * to ensure that any pending PPC_MSG_RM_HOST_ACTION
+		 * messages have completed before we free any VCPUs.
+		 */
+		if (all & IPI_MESSAGE(PPC_MSG_RM_HOST_ACTION))
+			kvmppc_xics_ipi_action();
+#endif
 		if (all & IPI_MESSAGE(PPC_MSG_CALL_FUNCTION))
 			generic_smp_call_function_interrupt();
 		if (all & IPI_MESSAGE(PPC_MSG_RESCHEDULE))
@@ -727,7 +745,7 @@ void start_secondary(void *unused)
 
 	local_irq_enable();
 
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 
 	BUG();
 }
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 0570eef83fba..7f7b6d86ac73 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -8,7 +8,7 @@ ccflags-y := -Ivirt/kvm -Iarch/powerpc/kvm
 KVM := ../../../virt/kvm
 
 common-objs-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
-		$(KVM)/eventfd.o
+		$(KVM)/eventfd.o $(KVM)/vfio.o
 
 CFLAGS_e500_mmu.o := -I.
 CFLAGS_e500_mmu_host.o := -I.
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 638c6d9be9e0..b34220d2aa42 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -807,7 +807,7 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 {
 
 #ifdef CONFIG_PPC64
-	INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
+	INIT_LIST_HEAD_RCU(&kvm->arch.spapr_tce_tables);
 	INIT_LIST_HEAD(&kvm->arch.rtas_tokens);
 #endif
 
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 54cf9bc94dad..2c2d1030843a 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -14,6 +14,7 @@
  *
  * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  * Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com>
+ * Copyright 2016 Alexey Kardashevskiy, IBM Corporation <aik@au1.ibm.com>
  */
 
 #include <linux/types.h>
@@ -36,28 +37,69 @@
 #include <asm/ppc-opcode.h>
 #include <asm/kvm_host.h>
 #include <asm/udbg.h>
+#include <asm/iommu.h>
+#include <asm/tce.h>
 
-#define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
+static unsigned long kvmppc_tce_pages(unsigned long iommu_pages)
+{
+	return ALIGN(iommu_pages * sizeof(u64), PAGE_SIZE) / PAGE_SIZE;
+}
 
-static long kvmppc_stt_npages(unsigned long window_size)
+static unsigned long kvmppc_stt_pages(unsigned long tce_pages)
 {
-	return ALIGN((window_size >> SPAPR_TCE_SHIFT)
-		     * sizeof(u64), PAGE_SIZE) / PAGE_SIZE;
+	unsigned long stt_bytes = sizeof(struct kvmppc_spapr_tce_table) +
+			(tce_pages * sizeof(struct page *));
+
+	return tce_pages + ALIGN(stt_bytes, PAGE_SIZE) / PAGE_SIZE;
 }
 
-static void release_spapr_tce_table(struct kvmppc_spapr_tce_table *stt)
+static long kvmppc_account_memlimit(unsigned long stt_pages, bool inc)
 {
-	struct kvm *kvm = stt->kvm;
-	int i;
+	long ret = 0;
 
-	mutex_lock(&kvm->lock);
-	list_del(&stt->list);
-	for (i = 0; i < kvmppc_stt_npages(stt->window_size); i++)
+	if (!current || !current->mm)
+		return ret; /* process exited */
+
+	down_write(&current->mm->mmap_sem);
+
+	if (inc) {
+		unsigned long locked, lock_limit;
+
+		locked = current->mm->locked_vm + stt_pages;
+		lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
+			ret = -ENOMEM;
+		else
+			current->mm->locked_vm += stt_pages;
+	} else {
+		if (WARN_ON_ONCE(stt_pages > current->mm->locked_vm))
+			stt_pages = current->mm->locked_vm;
+
+		current->mm->locked_vm -= stt_pages;
+	}
+
+	pr_debug("[%d] RLIMIT_MEMLOCK KVM %c%ld %ld/%ld%s\n", current->pid,
+			inc ? '+' : '-',
+			stt_pages << PAGE_SHIFT,
+			current->mm->locked_vm << PAGE_SHIFT,
+			rlimit(RLIMIT_MEMLOCK),
+			ret ? " - exceeded" : "");
+
+	up_write(&current->mm->mmap_sem);
+
+	return ret;
+}
+
+static void release_spapr_tce_table(struct rcu_head *head)
+{
+	struct kvmppc_spapr_tce_table *stt = container_of(head,
+			struct kvmppc_spapr_tce_table, rcu);
+	unsigned long i, npages = kvmppc_tce_pages(stt->size);
+
+	for (i = 0; i < npages; i++)
 		__free_page(stt->pages[i]);
-	kfree(stt);
-	mutex_unlock(&kvm->lock);
 
-	kvm_put_kvm(kvm);
+	kfree(stt);
 }
 
 static int kvm_spapr_tce_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
@@ -65,7 +107,7 @@ static int kvm_spapr_tce_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct kvmppc_spapr_tce_table *stt = vma->vm_file->private_data;
 	struct page *page;
 
-	if (vmf->pgoff >= kvmppc_stt_npages(stt->window_size))
+	if (vmf->pgoff >= kvmppc_tce_pages(stt->size))
 		return VM_FAULT_SIGBUS;
 
 	page = stt->pages[vmf->pgoff];
@@ -88,7 +130,14 @@ static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
 {
 	struct kvmppc_spapr_tce_table *stt = filp->private_data;
 
-	release_spapr_tce_table(stt);
+	list_del_rcu(&stt->list);
+
+	kvm_put_kvm(stt->kvm);
+
+	kvmppc_account_memlimit(
+		kvmppc_stt_pages(kvmppc_tce_pages(stt->size)), false);
+	call_rcu(&stt->rcu, release_spapr_tce_table);
+
 	return 0;
 }
 
@@ -98,20 +147,29 @@ static const struct file_operations kvm_spapr_tce_fops = {
 };
 
 long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
-				   struct kvm_create_spapr_tce *args)
+				   struct kvm_create_spapr_tce_64 *args)
 {
 	struct kvmppc_spapr_tce_table *stt = NULL;
-	long npages;
+	unsigned long npages, size;
 	int ret = -ENOMEM;
 	int i;
 
+	if (!args->size)
+		return -EINVAL;
+
 	/* Check this LIOBN hasn't been previously allocated */
 	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
 		if (stt->liobn == args->liobn)
 			return -EBUSY;
 	}
 
-	npages = kvmppc_stt_npages(args->window_size);
+	size = args->size;
+	npages = kvmppc_tce_pages(size);
+	ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true);
+	if (ret) {
+		stt = NULL;
+		goto fail;
+	}
 
 	stt = kzalloc(sizeof(*stt) + npages * sizeof(struct page *),
 		      GFP_KERNEL);
@@ -119,7 +177,9 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 		goto fail;
 
 	stt->liobn = args->liobn;
-	stt->window_size = args->window_size;
+	stt->page_shift = args->page_shift;
+	stt->offset = args->offset;
+	stt->size = size;
 	stt->kvm = kvm;
 
 	for (i = 0; i < npages; i++) {
@@ -131,7 +191,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	kvm_get_kvm(kvm);
 
 	mutex_lock(&kvm->lock);
-	list_add(&stt->list, &kvm->arch.spapr_tce_tables);
+	list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
 
 	mutex_unlock(&kvm->lock);
 
@@ -148,3 +208,59 @@ fail:
 	}
 	return ret;
 }
+
+long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
+		unsigned long liobn, unsigned long ioba,
+		unsigned long tce_list, unsigned long npages)
+{
+	struct kvmppc_spapr_tce_table *stt;
+	long i, ret = H_SUCCESS, idx;
+	unsigned long entry, ua = 0;
+	u64 __user *tces, tce;
+
+	stt = kvmppc_find_table(vcpu, liobn);
+	if (!stt)
+		return H_TOO_HARD;
+
+	entry = ioba >> stt->page_shift;
+	/*
+	 * SPAPR spec says that the maximum size of the list is 512 TCEs
+	 * so the whole table fits in 4K page
+	 */
+	if (npages > 512)
+		return H_PARAMETER;
+
+	if (tce_list & (SZ_4K - 1))
+		return H_PARAMETER;
+
+	ret = kvmppc_ioba_validate(stt, ioba, npages);
+	if (ret != H_SUCCESS)
+		return ret;
+
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+	if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, NULL)) {
+		ret = H_TOO_HARD;
+		goto unlock_exit;
+	}
+	tces = (u64 __user *) ua;
+
+	for (i = 0; i < npages; ++i) {
+		if (get_user(tce, tces + i)) {
+			ret = H_TOO_HARD;
+			goto unlock_exit;
+		}
+		tce = be64_to_cpu(tce);
+
+		ret = kvmppc_tce_validate(stt, tce);
+		if (ret != H_SUCCESS)
+			goto unlock_exit;
+
+		kvmppc_tce_put(stt, entry + i, tce);
+	}
+
+unlock_exit:
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kvmppc_h_put_tce_indirect);
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 89e96b3e0039..44be73e6aa26 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -14,6 +14,7 @@
  *
  * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  * Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com>
+ * Copyright 2016 Alexey Kardashevskiy, IBM Corporation <aik@au1.ibm.com>
  */
 
 #include <linux/types.h>
@@ -30,76 +31,321 @@
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
 #include <asm/mmu-hash64.h>
+#include <asm/mmu_context.h>
 #include <asm/hvcall.h>
 #include <asm/synch.h>
 #include <asm/ppc-opcode.h>
 #include <asm/kvm_host.h>
 #include <asm/udbg.h>
+#include <asm/iommu.h>
+#include <asm/tce.h>
+#include <asm/iommu.h>
 
 #define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
 
-/* WARNING: This will be called in real-mode on HV KVM and virtual
+/*
+ * Finds a TCE table descriptor by LIOBN.
+ *
+ * WARNING: This will be called in real or virtual mode on HV KVM and virtual
  *          mode on PR KVM
  */
-long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
-		      unsigned long ioba, unsigned long tce)
+struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm_vcpu *vcpu,
+		unsigned long liobn)
 {
 	struct kvm *kvm = vcpu->kvm;
 	struct kvmppc_spapr_tce_table *stt;
 
+	list_for_each_entry_lockless(stt, &kvm->arch.spapr_tce_tables, list)
+		if (stt->liobn == liobn)
+			return stt;
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(kvmppc_find_table);
+
+/*
+ * Validates IO address.
+ *
+ * WARNING: This will be called in real-mode on HV KVM and virtual
+ *          mode on PR KVM
+ */
+long kvmppc_ioba_validate(struct kvmppc_spapr_tce_table *stt,
+		unsigned long ioba, unsigned long npages)
+{
+	unsigned long mask = (1ULL << stt->page_shift) - 1;
+	unsigned long idx = ioba >> stt->page_shift;
+
+	if ((ioba & mask) || (idx < stt->offset) ||
+			(idx - stt->offset + npages > stt->size) ||
+			(idx + npages < idx))
+		return H_PARAMETER;
+
+	return H_SUCCESS;
+}
+EXPORT_SYMBOL_GPL(kvmppc_ioba_validate);
+
+/*
+ * Validates TCE address.
+ * At the moment flags and page mask are validated.
+ * As the host kernel does not access those addresses (just puts them
+ * to the table and user space is supposed to process them), we can skip
+ * checking other things (such as TCE is a guest RAM address or the page
+ * was actually allocated).
+ *
+ * WARNING: This will be called in real-mode on HV KVM and virtual
+ *          mode on PR KVM
+ */
+long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt, unsigned long tce)
+{
+	unsigned long page_mask = ~((1ULL << stt->page_shift) - 1);
+	unsigned long mask = ~(page_mask | TCE_PCI_WRITE | TCE_PCI_READ);
+
+	if (tce & mask)
+		return H_PARAMETER;
+
+	return H_SUCCESS;
+}
+EXPORT_SYMBOL_GPL(kvmppc_tce_validate);
+
+/* Note on the use of page_address() in real mode,
+ *
+ * It is safe to use page_address() in real mode on ppc64 because
+ * page_address() is always defined as lowmem_page_address()
+ * which returns __va(PFN_PHYS(page_to_pfn(page))) which is arithmetic
+ * operation and does not access page struct.
+ *
+ * Theoretically page_address() could be defined different
+ * but either WANT_PAGE_VIRTUAL or HASHED_PAGE_VIRTUAL
+ * would have to be enabled.
+ * WANT_PAGE_VIRTUAL is never enabled on ppc32/ppc64,
+ * HASHED_PAGE_VIRTUAL could be enabled for ppc32 only and only
+ * if CONFIG_HIGHMEM is defined. As CONFIG_SPARSEMEM_VMEMMAP
+ * is not expected to be enabled on ppc32, page_address()
+ * is safe for ppc32 as well.
+ *
+ * WARNING: This will be called in real-mode on HV KVM and virtual
+ *          mode on PR KVM
+ */
+static u64 *kvmppc_page_address(struct page *page)
+{
+#if defined(HASHED_PAGE_VIRTUAL) || defined(WANT_PAGE_VIRTUAL)
+#error TODO: fix to avoid page_address() here
+#endif
+	return (u64 *) page_address(page);
+}
+
+/*
+ * Handles TCE requests for emulated devices.
+ * Puts guest TCE values to the table and expects user space to convert them.
+ * Called in both real and virtual modes.
+ * Cannot fail so kvmppc_tce_validate must be called before it.
+ *
+ * WARNING: This will be called in real-mode on HV KVM and virtual
+ *          mode on PR KVM
+ */
+void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt,
+		unsigned long idx, unsigned long tce)
+{
+	struct page *page;
+	u64 *tbl;
+
+	idx -= stt->offset;
+	page = stt->pages[idx / TCES_PER_PAGE];
+	tbl = kvmppc_page_address(page);
+
+	tbl[idx % TCES_PER_PAGE] = tce;
+}
+EXPORT_SYMBOL_GPL(kvmppc_tce_put);
+
+long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
+		unsigned long *ua, unsigned long **prmap)
+{
+	unsigned long gfn = gpa >> PAGE_SHIFT;
+	struct kvm_memory_slot *memslot;
+
+	memslot = search_memslots(kvm_memslots(kvm), gfn);
+	if (!memslot)
+		return -EINVAL;
+
+	*ua = __gfn_to_hva_memslot(memslot, gfn) |
+		(gpa & ~(PAGE_MASK | TCE_PCI_READ | TCE_PCI_WRITE));
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	if (prmap)
+		*prmap = &memslot->arch.rmap[gfn - memslot->base_gfn];
+#endif
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua);
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
+		      unsigned long ioba, unsigned long tce)
+{
+	struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn);
+	long ret;
+
 	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
 	/* 	    liobn, ioba, tce); */
 
-	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
-		if (stt->liobn == liobn) {
-			unsigned long idx = ioba >> SPAPR_TCE_SHIFT;
-			struct page *page;
-			u64 *tbl;
-
-			/* udbg_printf("H_PUT_TCE: liobn 0x%lx => stt=%p  window_size=0x%x\n", */
-			/* 	    liobn, stt, stt->window_size); */
-			if (ioba >= stt->window_size)
-				return H_PARAMETER;
-
-			page = stt->pages[idx / TCES_PER_PAGE];
-			tbl = (u64 *)page_address(page);
-
-			/* FIXME: Need to validate the TCE itself */
-			/* udbg_printf("tce @ %p\n", &tbl[idx % TCES_PER_PAGE]); */
-			tbl[idx % TCES_PER_PAGE] = tce;
-			return H_SUCCESS;
-		}
-	}
+	if (!stt)
+		return H_TOO_HARD;
+
+	ret = kvmppc_ioba_validate(stt, ioba, 1);
+	if (ret != H_SUCCESS)
+		return ret;
 
-	/* Didn't find the liobn, punt it to userspace */
-	return H_TOO_HARD;
+	ret = kvmppc_tce_validate(stt, tce);
+	if (ret != H_SUCCESS)
+		return ret;
+
+	kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
+
+	return H_SUCCESS;
 }
 EXPORT_SYMBOL_GPL(kvmppc_h_put_tce);
 
-long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
-		      unsigned long ioba)
+static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu,
+		unsigned long ua, unsigned long *phpa)
+{
+	pte_t *ptep, pte;
+	unsigned shift = 0;
+
+	ptep = __find_linux_pte_or_hugepte(vcpu->arch.pgdir, ua, NULL, &shift);
+	if (!ptep || !pte_present(*ptep))
+		return -ENXIO;
+	pte = *ptep;
+
+	if (!shift)
+		shift = PAGE_SHIFT;
+
+	/* Avoid handling anything potentially complicated in realmode */
+	if (shift > PAGE_SHIFT)
+		return -EAGAIN;
+
+	if (!pte_young(pte))
+		return -EAGAIN;
+
+	*phpa = (pte_pfn(pte) << PAGE_SHIFT) | (ua & ((1ULL << shift) - 1)) |
+			(ua & ~PAGE_MASK);
+
+	return 0;
+}
+
+long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
+		unsigned long liobn, unsigned long ioba,
+		unsigned long tce_list,	unsigned long npages)
 {
-	struct kvm *kvm = vcpu->kvm;
 	struct kvmppc_spapr_tce_table *stt;
+	long i, ret = H_SUCCESS;
+	unsigned long tces, entry, ua = 0;
+	unsigned long *rmap = NULL;
+
+	stt = kvmppc_find_table(vcpu, liobn);
+	if (!stt)
+		return H_TOO_HARD;
+
+	entry = ioba >> stt->page_shift;
+	/*
+	 * The spec says that the maximum size of the list is 512 TCEs
+	 * so the whole table addressed resides in 4K page
+	 */
+	if (npages > 512)
+		return H_PARAMETER;
+
+	if (tce_list & (SZ_4K - 1))
+		return H_PARAMETER;
+
+	ret = kvmppc_ioba_validate(stt, ioba, npages);
+	if (ret != H_SUCCESS)
+		return ret;
 
-	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
-		if (stt->liobn == liobn) {
-			unsigned long idx = ioba >> SPAPR_TCE_SHIFT;
-			struct page *page;
-			u64 *tbl;
+	if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
+		return H_TOO_HARD;
 
-			if (ioba >= stt->window_size)
-				return H_PARAMETER;
+	rmap = (void *) vmalloc_to_phys(rmap);
 
-			page = stt->pages[idx / TCES_PER_PAGE];
-			tbl = (u64 *)page_address(page);
+	/*
+	 * Synchronize with the MMU notifier callbacks in
+	 * book3s_64_mmu_hv.c (kvm_unmap_hva_hv etc.).
+	 * While we have the rmap lock, code running on other CPUs
+	 * cannot finish unmapping the host real page that backs
+	 * this guest real page, so we are OK to access the host
+	 * real page.
+	 */
+	lock_rmap(rmap);
+	if (kvmppc_rm_ua_to_hpa(vcpu, ua, &tces)) {
+		ret = H_TOO_HARD;
+		goto unlock_exit;
+	}
+
+	for (i = 0; i < npages; ++i) {
+		unsigned long tce = be64_to_cpu(((u64 *)tces)[i]);
+
+		ret = kvmppc_tce_validate(stt, tce);
+		if (ret != H_SUCCESS)
+			goto unlock_exit;
 
-			vcpu->arch.gpr[4] = tbl[idx % TCES_PER_PAGE];
-			return H_SUCCESS;
-		}
+		kvmppc_tce_put(stt, entry + i, tce);
 	}
 
-	/* Didn't find the liobn, punt it to userspace */
-	return H_TOO_HARD;
+unlock_exit:
+	unlock_rmap(rmap);
+
+	return ret;
+}
+
+long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
+		unsigned long liobn, unsigned long ioba,
+		unsigned long tce_value, unsigned long npages)
+{
+	struct kvmppc_spapr_tce_table *stt;
+	long i, ret;
+
+	stt = kvmppc_find_table(vcpu, liobn);
+	if (!stt)
+		return H_TOO_HARD;
+
+	ret = kvmppc_ioba_validate(stt, ioba, npages);
+	if (ret != H_SUCCESS)
+		return ret;
+
+	/* Check permission bits only to allow userspace poison TCE for debug */
+	if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
+		return H_PARAMETER;
+
+	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
+		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
+
+	return H_SUCCESS;
+}
+EXPORT_SYMBOL_GPL(kvmppc_h_stuff_tce);
+
+long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
+		      unsigned long ioba)
+{
+	struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn);
+	long ret;
+	unsigned long idx;
+	struct page *page;
+	u64 *tbl;
+
+	if (!stt)
+		return H_TOO_HARD;
+
+	ret = kvmppc_ioba_validate(stt, ioba, 1);
+	if (ret != H_SUCCESS)
+		return ret;
+
+	idx = (ioba >> stt->page_shift) - stt->offset;
+	page = stt->pages[idx / TCES_PER_PAGE];
+	tbl = (u64 *)page_address(page);
+
+	vcpu->arch.gpr[4] = tbl[idx % TCES_PER_PAGE];
+
+	return H_SUCCESS;
 }
 EXPORT_SYMBOL_GPL(kvmppc_h_get_tce);
+
+#endif /* KVM_BOOK3S_HV_POSSIBLE */
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index baeddb06811d..84fb4fcfaa41 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -81,6 +81,17 @@ static int target_smt_mode;
 module_param(target_smt_mode, int, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(target_smt_mode, "Target threads per core (0 = max)");
 
+#ifdef CONFIG_KVM_XICS
+static struct kernel_param_ops module_param_ops = {
+	.set = param_set_int,
+	.get = param_get_int,
+};
+
+module_param_cb(h_ipi_redirect, &module_param_ops, &h_ipi_redirect,
+							S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(h_ipi_redirect, "Redirect H_IPI wakeup to a free host core");
+#endif
+
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
 
@@ -114,11 +125,11 @@ static bool kvmppc_ipi_thread(int cpu)
 static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 {
 	int cpu;
-	wait_queue_head_t *wqp;
+	struct swait_queue_head *wqp;
 
 	wqp = kvm_arch_vcpu_wq(vcpu);
-	if (waitqueue_active(wqp)) {
-		wake_up_interruptible(wqp);
+	if (swait_active(wqp)) {
+		swake_up(wqp);
 		++vcpu->stat.halt_wakeup;
 	}
 
@@ -701,8 +712,8 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		tvcpu->arch.prodded = 1;
 		smp_mb();
 		if (vcpu->arch.ceded) {
-			if (waitqueue_active(&vcpu->wq)) {
-				wake_up_interruptible(&vcpu->wq);
+			if (swait_active(&vcpu->wq)) {
+				swake_up(&vcpu->wq);
 				vcpu->stat.halt_wakeup++;
 			}
 		}
@@ -768,7 +779,31 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		if (kvmppc_xics_enabled(vcpu)) {
 			ret = kvmppc_xics_hcall(vcpu, req);
 			break;
-		} /* fallthrough */
+		}
+		return RESUME_HOST;
+	case H_PUT_TCE:
+		ret = kvmppc_h_put_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
+						kvmppc_get_gpr(vcpu, 5),
+						kvmppc_get_gpr(vcpu, 6));
+		if (ret == H_TOO_HARD)
+			return RESUME_HOST;
+		break;
+	case H_PUT_TCE_INDIRECT:
+		ret = kvmppc_h_put_tce_indirect(vcpu, kvmppc_get_gpr(vcpu, 4),
+						kvmppc_get_gpr(vcpu, 5),
+						kvmppc_get_gpr(vcpu, 6),
+						kvmppc_get_gpr(vcpu, 7));
+		if (ret == H_TOO_HARD)
+			return RESUME_HOST;
+		break;
+	case H_STUFF_TCE:
+		ret = kvmppc_h_stuff_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
+						kvmppc_get_gpr(vcpu, 5),
+						kvmppc_get_gpr(vcpu, 6),
+						kvmppc_get_gpr(vcpu, 7));
+		if (ret == H_TOO_HARD)
+			return RESUME_HOST;
+		break;
 	default:
 		return RESUME_HOST;
 	}
@@ -1459,7 +1494,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
 	INIT_LIST_HEAD(&vcore->runnable_threads);
 	spin_lock_init(&vcore->lock);
 	spin_lock_init(&vcore->stoltb_lock);
-	init_waitqueue_head(&vcore->wq);
+	init_swait_queue_head(&vcore->wq);
 	vcore->preempt_tb = TB_NIL;
 	vcore->lpcr = kvm->arch.lpcr;
 	vcore->first_vcpuid = core * threads_per_subcore;
@@ -2279,6 +2314,46 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master)
 }
 
 /*
+ * Clear core from the list of active host cores as we are about to
+ * enter the guest. Only do this if it is the primary thread of the
+ * core (not if a subcore) that is entering the guest.
+ */
+static inline void kvmppc_clear_host_core(int cpu)
+{
+	int core;
+
+	if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu))
+		return;
+	/*
+	 * Memory barrier can be omitted here as we will do a smp_wmb()
+	 * later in kvmppc_start_thread and we need ensure that state is
+	 * visible to other CPUs only after we enter guest.
+	 */
+	core = cpu >> threads_shift;
+	kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 0;
+}
+
+/*
+ * Advertise this core as an active host core since we exited the guest
+ * Only need to do this if it is the primary thread of the core that is
+ * exiting.
+ */
+static inline void kvmppc_set_host_core(int cpu)
+{
+	int core;
+
+	if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu))
+		return;
+
+	/*
+	 * Memory barrier can be omitted here because we do a spin_unlock
+	 * immediately after this which provides the memory barrier.
+	 */
+	core = cpu >> threads_shift;
+	kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 1;
+}
+
+/*
  * Run a set of guest threads on a physical core.
  * Called with vc->lock held.
  */
@@ -2390,6 +2465,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 		}
 	}
 
+	kvmppc_clear_host_core(pcpu);
+
 	/* Start all the threads */
 	active = 0;
 	for (sub = 0; sub < core_info.n_subcores; ++sub) {
@@ -2486,6 +2563,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 			kvmppc_ipi_thread(pcpu + i);
 	}
 
+	kvmppc_set_host_core(pcpu);
+
 	spin_unlock(&vc->lock);
 
 	/* make sure updates to secondary vcpu structs are visible now */
@@ -2531,10 +2610,9 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 {
 	struct kvm_vcpu *vcpu;
 	int do_sleep = 1;
+	DECLARE_SWAITQUEUE(wait);
 
-	DEFINE_WAIT(wait);
-
-	prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
+	prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
 
 	/*
 	 * Check one last time for pending exceptions and ceded state after
@@ -2548,7 +2626,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 	}
 
 	if (!do_sleep) {
-		finish_wait(&vc->wq, &wait);
+		finish_swait(&vc->wq, &wait);
 		return;
 	}
 
@@ -2556,7 +2634,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 	trace_kvmppc_vcore_blocked(vc, 0);
 	spin_unlock(&vc->lock);
 	schedule();
-	finish_wait(&vc->wq, &wait);
+	finish_swait(&vc->wq, &wait);
 	spin_lock(&vc->lock);
 	vc->vcore_state = VCORE_INACTIVE;
 	trace_kvmppc_vcore_blocked(vc, 1);
@@ -2612,7 +2690,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 			kvmppc_start_thread(vcpu, vc);
 			trace_kvm_guest_enter(vcpu);
 		} else if (vc->vcore_state == VCORE_SLEEPING) {
-			wake_up(&vc->wq);
+			swake_up(&vc->wq);
 		}
 
 	}
@@ -2984,6 +3062,114 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 	goto out_srcu;
 }
 
+#ifdef CONFIG_KVM_XICS
+static int kvmppc_cpu_notify(struct notifier_block *self, unsigned long action,
+			void *hcpu)
+{
+	unsigned long cpu = (long)hcpu;
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+		kvmppc_set_host_core(cpu);
+		break;
+
+#ifdef CONFIG_HOTPLUG_CPU
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
+		kvmppc_clear_host_core(cpu);
+		break;
+#endif
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block kvmppc_cpu_notifier = {
+	    .notifier_call = kvmppc_cpu_notify,
+};
+
+/*
+ * Allocate a per-core structure for managing state about which cores are
+ * running in the host versus the guest and for exchanging data between
+ * real mode KVM and CPU running in the host.
+ * This is only done for the first VM.
+ * The allocated structure stays even if all VMs have stopped.
+ * It is only freed when the kvm-hv module is unloaded.
+ * It's OK for this routine to fail, we just don't support host
+ * core operations like redirecting H_IPI wakeups.
+ */
+void kvmppc_alloc_host_rm_ops(void)
+{
+	struct kvmppc_host_rm_ops *ops;
+	unsigned long l_ops;
+	int cpu, core;
+	int size;
+
+	/* Not the first time here ? */
+	if (kvmppc_host_rm_ops_hv != NULL)
+		return;
+
+	ops = kzalloc(sizeof(struct kvmppc_host_rm_ops), GFP_KERNEL);
+	if (!ops)
+		return;
+
+	size = cpu_nr_cores() * sizeof(struct kvmppc_host_rm_core);
+	ops->rm_core = kzalloc(size, GFP_KERNEL);
+
+	if (!ops->rm_core) {
+		kfree(ops);
+		return;
+	}
+
+	get_online_cpus();
+
+	for (cpu = 0; cpu < nr_cpu_ids; cpu += threads_per_core) {
+		if (!cpu_online(cpu))
+			continue;
+
+		core = cpu >> threads_shift;
+		ops->rm_core[core].rm_state.in_host = 1;
+	}
+
+	ops->vcpu_kick = kvmppc_fast_vcpu_kick_hv;
+
+	/*
+	 * Make the contents of the kvmppc_host_rm_ops structure visible
+	 * to other CPUs before we assign it to the global variable.
+	 * Do an atomic assignment (no locks used here), but if someone
+	 * beats us to it, just free our copy and return.
+	 */
+	smp_wmb();
+	l_ops = (unsigned long) ops;
+
+	if (cmpxchg64((unsigned long *)&kvmppc_host_rm_ops_hv, 0, l_ops)) {
+		put_online_cpus();
+		kfree(ops->rm_core);
+		kfree(ops);
+		return;
+	}
+
+	register_cpu_notifier(&kvmppc_cpu_notifier);
+
+	put_online_cpus();
+}
+
+void kvmppc_free_host_rm_ops(void)
+{
+	if (kvmppc_host_rm_ops_hv) {
+		unregister_cpu_notifier(&kvmppc_cpu_notifier);
+		kfree(kvmppc_host_rm_ops_hv->rm_core);
+		kfree(kvmppc_host_rm_ops_hv);
+		kvmppc_host_rm_ops_hv = NULL;
+	}
+}
+#endif
+
 static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 {
 	unsigned long lpcr, lpid;
@@ -2996,6 +3182,8 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 		return -ENOMEM;
 	kvm->arch.lpid = lpid;
 
+	kvmppc_alloc_host_rm_ops();
+
 	/*
 	 * Since we don't flush the TLB when tearing down a VM,
 	 * and this lpid might have previously been used,
@@ -3229,6 +3417,7 @@ static int kvmppc_book3s_init_hv(void)
 
 static void kvmppc_book3s_exit_hv(void)
 {
+	kvmppc_free_host_rm_ops();
 	kvmppc_hv_ops = NULL;
 }
 
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index fd7006bf6b1a..5f0380db3eab 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -283,3 +283,6 @@ void kvmhv_commence_exit(int trap)
 			kvmhv_interrupt_vcore(vc, ee);
 	}
 }
+
+struct kvmppc_host_rm_ops *kvmppc_host_rm_ops_hv;
+EXPORT_SYMBOL_GPL(kvmppc_host_rm_ops_hv);
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index 24f58076d49e..980d8a6f7284 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -17,12 +17,16 @@
 #include <asm/xics.h>
 #include <asm/debug.h>
 #include <asm/synch.h>
+#include <asm/cputhreads.h>
 #include <asm/ppc-opcode.h>
 
 #include "book3s_xics.h"
 
 #define DEBUG_PASSUP
 
+int h_ipi_redirect = 1;
+EXPORT_SYMBOL(h_ipi_redirect);
+
 static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
 			    u32 new_irq);
 
@@ -50,11 +54,84 @@ static void ics_rm_check_resend(struct kvmppc_xics *xics,
 
 /* -- ICP routines -- */
 
+#ifdef CONFIG_SMP
+static inline void icp_send_hcore_msg(int hcore, struct kvm_vcpu *vcpu)
+{
+	int hcpu;
+
+	hcpu = hcore << threads_shift;
+	kvmppc_host_rm_ops_hv->rm_core[hcore].rm_data = vcpu;
+	smp_muxed_ipi_set_message(hcpu, PPC_MSG_RM_HOST_ACTION);
+	icp_native_cause_ipi_rm(hcpu);
+}
+#else
+static inline void icp_send_hcore_msg(int hcore, struct kvm_vcpu *vcpu) { }
+#endif
+
+/*
+ * We start the search from our current CPU Id in the core map
+ * and go in a circle until we get back to our ID looking for a
+ * core that is running in host context and that hasn't already
+ * been targeted for another rm_host_ops.
+ *
+ * In the future, could consider using a fairer algorithm (one
+ * that distributes the IPIs better)
+ *
+ * Returns -1, if no CPU could be found in the host
+ * Else, returns a CPU Id which has been reserved for use
+ */
+static inline int grab_next_hostcore(int start,
+		struct kvmppc_host_rm_core *rm_core, int max, int action)
+{
+	bool success;
+	int core;
+	union kvmppc_rm_state old, new;
+
+	for (core = start + 1; core < max; core++)  {
+		old = new = READ_ONCE(rm_core[core].rm_state);
+
+		if (!old.in_host || old.rm_action)
+			continue;
+
+		/* Try to grab this host core if not taken already. */
+		new.rm_action = action;
+
+		success = cmpxchg64(&rm_core[core].rm_state.raw,
+						old.raw, new.raw) == old.raw;
+		if (success) {
+			/*
+			 * Make sure that the store to the rm_action is made
+			 * visible before we return to caller (and the
+			 * subsequent store to rm_data) to synchronize with
+			 * the IPI handler.
+			 */
+			smp_wmb();
+			return core;
+		}
+	}
+
+	return -1;
+}
+
+static inline int find_available_hostcore(int action)
+{
+	int core;
+	int my_core = smp_processor_id() >> threads_shift;
+	struct kvmppc_host_rm_core *rm_core = kvmppc_host_rm_ops_hv->rm_core;
+
+	core = grab_next_hostcore(my_core, rm_core, cpu_nr_cores(), action);
+	if (core == -1)
+		core = grab_next_hostcore(core, rm_core, my_core, action);
+
+	return core;
+}
+
 static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu,
 				struct kvm_vcpu *this_vcpu)
 {
 	struct kvmppc_icp *this_icp = this_vcpu->arch.icp;
 	int cpu;
+	int hcore;
 
 	/* Mark the target VCPU as having an interrupt pending */
 	vcpu->stat.queue_intr++;
@@ -66,11 +143,22 @@ static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu,
 		return;
 	}
 
-	/* Check if the core is loaded, if not, too hard */
+	/*
+	 * Check if the core is loaded,
+	 * if not, find an available host core to post to wake the VCPU,
+	 * if we can't find one, set up state to eventually return too hard.
+	 */
 	cpu = vcpu->arch.thread_cpu;
 	if (cpu < 0 || cpu >= nr_cpu_ids) {
-		this_icp->rm_action |= XICS_RM_KICK_VCPU;
-		this_icp->rm_kick_target = vcpu;
+		hcore = -1;
+		if (kvmppc_host_rm_ops_hv && h_ipi_redirect)
+			hcore = find_available_hostcore(XICS_RM_KICK_VCPU);
+		if (hcore != -1) {
+			icp_send_hcore_msg(hcore, vcpu);
+		} else {
+			this_icp->rm_action |= XICS_RM_KICK_VCPU;
+			this_icp->rm_kick_target = vcpu;
+		}
 		return;
 	}
 
@@ -623,3 +711,40 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
  bail:
 	return check_too_hard(xics, icp);
 }
+
+/*  --- Non-real mode XICS-related built-in routines ---  */
+
+/**
+ * Host Operations poked by RM KVM
+ */
+static void rm_host_ipi_action(int action, void *data)
+{
+	switch (action) {
+	case XICS_RM_KICK_VCPU:
+		kvmppc_host_rm_ops_hv->vcpu_kick(data);
+		break;
+	default:
+		WARN(1, "Unexpected rm_action=%d data=%p\n", action, data);
+		break;
+	}
+
+}
+
+void kvmppc_xics_ipi_action(void)
+{
+	int core;
+	unsigned int cpu = smp_processor_id();
+	struct kvmppc_host_rm_core *rm_corep;
+
+	core = cpu >> threads_shift;
+	rm_corep = &kvmppc_host_rm_ops_hv->rm_core[core];
+
+	if (rm_corep->rm_data) {
+		rm_host_ipi_action(rm_corep->rm_state.rm_action,
+							rm_corep->rm_data);
+		/* Order these stores against the real mode KVM */
+		rm_corep->rm_data = NULL;
+		smp_wmb();
+		rm_corep->rm_state.rm_action = 0;
+	}
+}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 6ee26de9a1de..85b32f16fa74 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1370,6 +1370,20 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	std	r6, VCPU_ACOP(r9)
 	stw	r7, VCPU_GUEST_PID(r9)
 	std	r8, VCPU_WORT(r9)
+	/*
+	 * Restore various registers to 0, where non-zero values
+	 * set by the guest could disrupt the host.
+	 */
+	li	r0, 0
+	mtspr	SPRN_IAMR, r0
+	mtspr	SPRN_CIABR, r0
+	mtspr	SPRN_DAWRX, r0
+	mtspr	SPRN_TCSCR, r0
+	mtspr	SPRN_WORT, r0
+	/* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */
+	li	r0, 1
+	sldi	r0, r0, 31
+	mtspr	SPRN_MMCRS, r0
 8:
 
 	/* Save and reset AMR and UAMOR before turning on the MMU */
@@ -2006,8 +2020,8 @@ hcall_real_table:
 	.long	0		/* 0x12c */
 	.long	0		/* 0x130 */
 	.long	DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table
-	.long	0		/* 0x138 */
-	.long	0		/* 0x13c */
+	.long	DOTSYM(kvmppc_h_stuff_tce) - hcall_real_table
+	.long	DOTSYM(kvmppc_rm_h_put_tce_indirect) - hcall_real_table
 	.long	0		/* 0x140 */
 	.long	0		/* 0x144 */
 	.long	0		/* 0x148 */
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index f2c75a1e0536..02176fd52f84 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -280,6 +280,37 @@ static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu)
 	return EMULATE_DONE;
 }
 
+static int kvmppc_h_pr_put_tce_indirect(struct kvm_vcpu *vcpu)
+{
+	unsigned long liobn = kvmppc_get_gpr(vcpu, 4);
+	unsigned long ioba = kvmppc_get_gpr(vcpu, 5);
+	unsigned long tce = kvmppc_get_gpr(vcpu, 6);
+	unsigned long npages = kvmppc_get_gpr(vcpu, 7);
+	long rc;
+
+	rc = kvmppc_h_put_tce_indirect(vcpu, liobn, ioba,
+			tce, npages);
+	if (rc == H_TOO_HARD)
+		return EMULATE_FAIL;
+	kvmppc_set_gpr(vcpu, 3, rc);
+	return EMULATE_DONE;
+}
+
+static int kvmppc_h_pr_stuff_tce(struct kvm_vcpu *vcpu)
+{
+	unsigned long liobn = kvmppc_get_gpr(vcpu, 4);
+	unsigned long ioba = kvmppc_get_gpr(vcpu, 5);
+	unsigned long tce_value = kvmppc_get_gpr(vcpu, 6);
+	unsigned long npages = kvmppc_get_gpr(vcpu, 7);
+	long rc;
+
+	rc = kvmppc_h_stuff_tce(vcpu, liobn, ioba, tce_value, npages);
+	if (rc == H_TOO_HARD)
+		return EMULATE_FAIL;
+	kvmppc_set_gpr(vcpu, 3, rc);
+	return EMULATE_DONE;
+}
+
 static int kvmppc_h_pr_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd)
 {
 	long rc = kvmppc_xics_hcall(vcpu, cmd);
@@ -306,6 +337,10 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
 		return kvmppc_h_pr_bulk_remove(vcpu);
 	case H_PUT_TCE:
 		return kvmppc_h_pr_put_tce(vcpu);
+	case H_PUT_TCE_INDIRECT:
+		return kvmppc_h_pr_put_tce_indirect(vcpu);
+	case H_STUFF_TCE:
+		return kvmppc_h_pr_stuff_tce(vcpu);
 	case H_CEDE:
 		kvmppc_set_msr_fast(vcpu, kvmppc_get_msr(vcpu) | MSR_EE);
 		kvm_vcpu_block(vcpu);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index a3b182dcb823..19aa59b0850c 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -33,6 +33,7 @@
 #include <asm/tlbflush.h>
 #include <asm/cputhreads.h>
 #include <asm/irqflags.h>
+#include <asm/iommu.h>
 #include "timing.h"
 #include "irq.h"
 #include "../mm/mmu_decl.h"
@@ -437,6 +438,16 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	unsigned int i;
 	struct kvm_vcpu *vcpu;
 
+#ifdef CONFIG_KVM_XICS
+	/*
+	 * We call kick_all_cpus_sync() to ensure that all
+	 * CPUs have executed any pending IPIs before we
+	 * continue and free VCPUs structures below.
+	 */
+	if (is_kvmppc_hv_enabled(kvm))
+		kick_all_cpus_sync();
+#endif
+
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		kvm_arch_vcpu_free(vcpu);
 
@@ -509,6 +520,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 
 #ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CAP_SPAPR_TCE:
+	case KVM_CAP_SPAPR_TCE_64:
 	case KVM_CAP_PPC_ALLOC_HTAB:
 	case KVM_CAP_PPC_RTAS:
 	case KVM_CAP_PPC_FIXUP_HCALL:
@@ -569,6 +581,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_PPC_GET_SMMU_INFO:
 		r = 1;
 		break;
+	case KVM_CAP_SPAPR_MULTITCE:
+		r = 1;
+		break;
 #endif
 	default:
 		r = 0;
@@ -1331,13 +1346,34 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		break;
 	}
 #ifdef CONFIG_PPC_BOOK3S_64
+	case KVM_CREATE_SPAPR_TCE_64: {
+		struct kvm_create_spapr_tce_64 create_tce_64;
+
+		r = -EFAULT;
+		if (copy_from_user(&create_tce_64, argp, sizeof(create_tce_64)))
+			goto out;
+		if (create_tce_64.flags) {
+			r = -EINVAL;
+			goto out;
+		}
+		r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce_64);
+		goto out;
+	}
 	case KVM_CREATE_SPAPR_TCE: {
 		struct kvm_create_spapr_tce create_tce;
+		struct kvm_create_spapr_tce_64 create_tce_64;
 
 		r = -EFAULT;
 		if (copy_from_user(&create_tce, argp, sizeof(create_tce)))
 			goto out;
-		r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce);
+
+		create_tce_64.liobn = create_tce.liobn;
+		create_tce_64.page_shift = IOMMU_PAGE_SHIFT_4K;
+		create_tce_64.offset = 0;
+		create_tce_64.size = create_tce.window_size >>
+				IOMMU_PAGE_SHIFT_4K;
+		create_tce_64.flags = 0;
+		r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce_64);
 		goto out;
 	}
 	case KVM_PPC_GET_SMMU_INFO: {
diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c
index 0762c1e08c88..edb09912f0c9 100644
--- a/arch/powerpc/mm/hash64_64k.c
+++ b/arch/powerpc/mm/hash64_64k.c
@@ -111,7 +111,13 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 	 */
 	if (!(old_pte & _PAGE_COMBO)) {
 		flush_hash_page(vpn, rpte, MMU_PAGE_64K, ssize, flags);
-		old_pte &= ~_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND;
+		/*
+		 * clear the old slot details from the old and new pte.
+		 * On hash insert failure we use old pte value and we don't
+		 * want slot information there if we have a insert failure.
+		 */
+		old_pte &= ~(_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND);
+		new_pte &= ~(_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND);
 		goto htab_insert_hpte;
 	}
 	/*
diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
index 49b152b0f926..eb2accdd76fd 100644
--- a/arch/powerpc/mm/hugepage-hash64.c
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -78,9 +78,19 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 		 * base page size. This is because demote_segment won't flush
 		 * hash page table entries.
 		 */
-		if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO))
+		if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO)) {
 			flush_hash_hugepage(vsid, ea, pmdp, MMU_PAGE_64K,
 					    ssize, flags);
+			/*
+			 * With THP, we also clear the slot information with
+			 * respect to all the 64K hash pte mapping the 16MB
+			 * page. They are all invalid now. This make sure we
+			 * don't find the slot valid when we fault with 4k
+			 * base page size.
+			 *
+			 */
+			memset(hpte_slot_array, 0, PTE_FRAG_SIZE);
+		}
 	}
 
 	valid = hpte_valid(hpte_slot_array, index);
diff --git a/arch/powerpc/mm/hugetlbpage-book3e.c b/arch/powerpc/mm/hugetlbpage-book3e.c
index 7e6d0880813f..83a8be791e06 100644
--- a/arch/powerpc/mm/hugetlbpage-book3e.c
+++ b/arch/powerpc/mm/hugetlbpage-book3e.c
@@ -8,6 +8,8 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 
+#include <asm/mmu.h>
+
 #ifdef CONFIG_PPC_FSL_BOOK3E
 #ifdef CONFIG_PPC64
 static inline int tlb1_next(void)
@@ -60,6 +62,14 @@ static inline void book3e_tlb_lock(void)
 	unsigned long tmp;
 	int token = smp_processor_id() + 1;
 
+	/*
+	 * Besides being unnecessary in the absence of SMT, this
+	 * check prevents trying to do lbarx/stbcx. on e5500 which
+	 * doesn't implement either feature.
+	 */
+	if (!cpu_has_feature(CPU_FTR_SMT))
+		return;
+
 	asm volatile("1: lbarx %0, 0, %1;"
 		     "cmpwi %0, 0;"
 		     "bne 2f;"
@@ -80,6 +90,9 @@ static inline void book3e_tlb_unlock(void)
 {
 	struct paca_struct *paca = get_paca();
 
+	if (!cpu_has_feature(CPU_FTR_SMT))
+		return;
+
 	isync();
 	paca->tcd_ptr->lock = 0;
 }
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index d0f0a514b04e..f078a1f94fc2 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -541,7 +541,7 @@ static int __init add_system_ram_resources(void)
 			res->name = "System RAM";
 			res->start = base;
 			res->end = base + size - 1;
-			res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+			res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 			WARN_ON(request_resource(&iomem_resource, res) < 0);
 		}
 	}
diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c
index 0f0502e12f6c..4087705ba90f 100644
--- a/arch/powerpc/mm/mmap.c
+++ b/arch/powerpc/mm/mmap.c
@@ -59,9 +59,9 @@ unsigned long arch_mmap_rnd(void)
 
 	/* 8MB for 32bit, 1GB for 64bit */
 	if (is_32bit_task())
-		rnd = (unsigned long)get_random_int() % (1<<(23-PAGE_SHIFT));
+		rnd = get_random_long() % (1<<(23-PAGE_SHIFT));
 	else
-		rnd = (unsigned long)get_random_int() % (1<<(30-PAGE_SHIFT));
+		rnd = get_random_long() % (1UL<<(30-PAGE_SHIFT));
 
 	return rnd << PAGE_SHIFT;
 }
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 83dfd7925c72..de37ff445362 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -243,3 +243,11 @@ void assert_pte_locked(struct mm_struct *mm, unsigned long addr)
 }
 #endif /* CONFIG_DEBUG_VM */
 
+unsigned long vmalloc_to_phys(void *va)
+{
+	unsigned long pfn = vmalloc_to_pfn(va);
+
+	BUG_ON(!pfn);
+	return __pa(pfn_to_kaddr(pfn)) + offset_in_page(va);
+}
+EXPORT_SYMBOL_GPL(vmalloc_to_phys);
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 3124a20d0fab..cdf2123d46db 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -646,6 +646,28 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 	return pgtable;
 }
 
+void pmdp_huge_split_prepare(struct vm_area_struct *vma,
+			     unsigned long address, pmd_t *pmdp)
+{
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+	VM_BUG_ON(REGION_ID(address) != USER_REGION_ID);
+
+	/*
+	 * We can't mark the pmd none here, because that will cause a race
+	 * against exit_mmap. We need to continue mark pmd TRANS HUGE, while
+	 * we spilt, but at the same time we wan't rest of the ppc64 code
+	 * not to insert hash pte on this, because we will be modifying
+	 * the deposited pgtable in the caller of this function. Hence
+	 * clear the _PAGE_USER so that we move the fault handling to
+	 * higher level function and that will serialize against ptl.
+	 * We need to flush existing hash pte entries here even though,
+	 * the translation is still valid, because we will withdraw
+	 * pgtable_t after this.
+	 */
+	pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_USER, 0);
+}
+
+
 /*
  * set a new huge pmd. We should not be called for updating
  * an existing pmd entry. That should go via pmd_hugepage_update.
@@ -663,10 +685,20 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));
 }
 
+/*
+ * We use this to invalidate a pmdp entry before switching from a
+ * hugepte to regular pmd entry.
+ */
 void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 		     pmd_t *pmdp)
 {
 	pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);
+
+	/*
+	 * This ensures that generic code that rely on IRQ disabling
+	 * to prevent a parallel THP split work as expected.
+	 */
+	kick_all_cpus_sync();
 }
 
 /*
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index 9f9dfda9ed2c..3b09ecfd0aee 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -493,14 +493,6 @@ static size_t event_to_attr_ct(struct hv_24x7_event_data *event)
 	}
 }
 
-static unsigned long vmalloc_to_phys(void *v)
-{
-	struct page *p = vmalloc_to_page(v);
-
-	BUG_ON(!p);
-	return page_to_phys(p) + offset_in_page(v);
-}
-
 /* */
 struct event_uniq {
 	struct rb_node node;
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 5f152b95ca0c..87f47e55aab6 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -444,9 +444,12 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data)
 	 * PCI devices of the PE are expected to be removed prior
 	 * to PE reset.
 	 */
-	if (!edev->pe->bus)
+	if (!(edev->pe->state & EEH_PE_PRI_BUS)) {
 		edev->pe->bus = pci_find_bus(hose->global_number,
 					     pdn->busno);
+		if (edev->pe->bus)
+			edev->pe->state |= EEH_PE_PRI_BUS;
+	}
 
 	/*
 	 * Enable EEH explicitly so that we will do EEH check
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 573ae1994097..f90dc04395bf 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -3180,6 +3180,7 @@ static void pnv_pci_ioda_shutdown(struct pci_controller *hose)
 
 static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
        .dma_dev_setup = pnv_pci_dma_dev_setup,
+       .dma_bus_setup = pnv_pci_dma_bus_setup,
 #ifdef CONFIG_PCI_MSI
        .setup_msi_irqs = pnv_setup_msi_irqs,
        .teardown_msi_irqs = pnv_teardown_msi_irqs,
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 2f55c86df703..b1ef84a6c9d1 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -599,6 +599,9 @@ int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
 	u64 rpn = __pa(uaddr) >> tbl->it_page_shift;
 	long i;
 
+	if (proto_tce & TCE_PCI_WRITE)
+		proto_tce |= TCE_PCI_READ;
+
 	for (i = 0; i < npages; i++) {
 		unsigned long newtce = proto_tce |
 			((rpn + i) << tbl->it_page_shift);
@@ -620,6 +623,9 @@ int pnv_tce_xchg(struct iommu_table *tbl, long index,
 
 	BUG_ON(*hpa & ~IOMMU_PAGE_MASK(tbl));
 
+	if (newtce & TCE_PCI_WRITE)
+		newtce |= TCE_PCI_READ;
+
 	oldtce = xchg(pnv_tce(tbl, idx), cpu_to_be64(newtce));
 	*hpa = be64_to_cpu(oldtce) & ~(TCE_PCI_READ | TCE_PCI_WRITE);
 	*direction = iommu_tce_direction(oldtce);
@@ -760,6 +766,26 @@ void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 		phb->dma_dev_setup(phb, pdev);
 }
 
+void pnv_pci_dma_bus_setup(struct pci_bus *bus)
+{
+	struct pci_controller *hose = bus->sysdata;
+	struct pnv_phb *phb = hose->private_data;
+	struct pnv_ioda_pe *pe;
+
+	list_for_each_entry(pe, &phb->ioda.pe_list, list) {
+		if (!(pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)))
+			continue;
+
+		if (!pe->pbus)
+			continue;
+
+		if (bus->number == ((pe->rid >> 8) & 0xFF)) {
+			pe->pbus = bus;
+			break;
+		}
+	}
+}
+
 void pnv_pci_shutdown(void)
 {
 	struct pci_controller *hose;
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 7f56313e8d72..00691a9b99af 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -242,6 +242,7 @@ extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
 extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
 
 extern void pnv_pci_dma_dev_setup(struct pci_dev *pdev);
+extern void pnv_pci_dma_bus_setup(struct pci_bus *bus);
 extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
 extern void pnv_teardown_msi_irqs(struct pci_dev *pdev);
 
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index eae32654bdf2..afdf62f2a695 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -159,6 +159,27 @@ static void icp_native_cause_ipi(int cpu, unsigned long data)
 	icp_native_set_qirr(cpu, IPI_PRIORITY);
 }
 
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+void icp_native_cause_ipi_rm(int cpu)
+{
+	/*
+	 * Currently not used to send IPIs to another CPU
+	 * on the same core. Only caller is KVM real mode.
+	 * Need the physical address of the XICS to be
+	 * previously saved in kvm_hstate in the paca.
+	 */
+	unsigned long xics_phys;
+
+	/*
+	 * Just like the cause_ipi functions, it is required to
+	 * include a full barrier (out8 includes a sync) before
+	 * causing the IPI.
+	 */
+	xics_phys = paca[cpu].kvm_hstate.xics_phys;
+	out_rm8((u8 *)(xics_phys + XICS_MFRR), IPI_PRIORITY);
+}
+#endif
+
 /*
  * Called when an interrupt is received on an off-line CPU to
  * clear the interrupt, so that the CPU can go back to nap mode.
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 3be9c832dec1..7e3e8a8338d6 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -254,12 +254,12 @@ config MARCH_ZEC12
 	  older machines.
 
 config MARCH_Z13
-	bool "IBM z13"
+	bool "IBM z13s and z13"
 	select HAVE_MARCH_Z13_FEATURES
 	help
-	  Select this to enable optimizations for IBM z13 (2964 series).
-	  The kernel will be slightly faster but will not work on older
-	  machines.
+	  Select this to enable optimizations for IBM z13s and z13 (2965 and
+	  2964 series). The kernel will be slightly faster but will not work on
+	  older machines.
 
 endchoice
 
@@ -605,8 +605,6 @@ config PCI_NR_MSI
 	  PCI devices.
 
 source "drivers/pci/Kconfig"
-source "drivers/pci/pcie/Kconfig"
-source "drivers/pci/hotplug/Kconfig"
 
 endif	# PCI
 
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index 0b9b95f3c703..48e1a2d3e318 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -27,6 +27,7 @@
 #include <linux/cpufeature.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
+#include <crypto/xts.h>
 #include "crypt_s390.h"
 
 #define AES_KEYLEN_128		1
@@ -587,6 +588,11 @@ static int xts_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 {
 	struct s390_xts_ctx *xts_ctx = crypto_tfm_ctx(tfm);
 	u32 *flags = &tfm->crt_flags;
+	int err;
+
+	err = xts_check_key(tfm, in_key, key_len);
+	if (err)
+		return err;
 
 	switch (key_len) {
 	case 32:
diff --git a/arch/s390/include/asm/clp.h b/arch/s390/include/asm/clp.h
index a0e71a501f7c..5687d62fb0cb 100644
--- a/arch/s390/include/asm/clp.h
+++ b/arch/s390/include/asm/clp.h
@@ -4,14 +4,23 @@
 /* CLP common request & response block size */
 #define CLP_BLK_SIZE			PAGE_SIZE
 
+#define CLP_LPS_BASE	0
+#define CLP_LPS_PCI	2
+
 struct clp_req_hdr {
 	u16 len;
 	u16 cmd;
+	u32 fmt		: 4;
+	u32 reserved1	: 28;
+	u64 reserved2;
 } __packed;
 
 struct clp_rsp_hdr {
 	u16 len;
 	u16 rsp;
+	u32 fmt		: 4;
+	u32 reserved1	: 28;
+	u64 reserved2;
 } __packed;
 
 /* CLP Response Codes */
@@ -25,4 +34,22 @@ struct clp_rsp_hdr {
 #define CLP_RC_NODATA			0x0080	/* No data available */
 #define CLP_RC_FC_UNKNOWN		0x0100	/* Function code not recognized */
 
+/* Store logical-processor characteristics request */
+struct clp_req_slpc {
+	struct clp_req_hdr hdr;
+} __packed;
+
+struct clp_rsp_slpc {
+	struct clp_rsp_hdr hdr;
+	u32 reserved2[4];
+	u32 lpif[8];
+	u32 reserved3[8];
+	u32 lpic[8];
+} __packed;
+
+struct clp_req_rsp_slpc {
+	struct clp_req_slpc request;
+	struct clp_rsp_slpc response;
+} __packed;
+
 #endif
diff --git a/arch/s390/include/asm/fpu/internal.h b/arch/s390/include/asm/fpu/internal.h
index ea91ddfe54eb..629c90865a07 100644
--- a/arch/s390/include/asm/fpu/internal.h
+++ b/arch/s390/include/asm/fpu/internal.h
@@ -40,6 +40,7 @@ static inline void convert_fp_to_vx(__vector128 *vxrs, freg_t *fprs)
 static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu)
 {
 	fpregs->pad = 0;
+	fpregs->fpc = fpu->fpc;
 	if (MACHINE_HAS_VX)
 		convert_vx_to_fp((freg_t *)&fpregs->fprs, fpu->vxrs);
 	else
@@ -49,6 +50,7 @@ static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu)
 
 static inline void fpregs_load(_s390_fp_regs *fpregs, struct fpu *fpu)
 {
+	fpu->fpc = fpregs->fpc;
 	if (MACHINE_HAS_VX)
 		convert_fp_to_vx(fpu->vxrs, (freg_t *)&fpregs->fprs);
 	else
diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
new file mode 100644
index 000000000000..d054c1b07a3c
--- /dev/null
+++ b/arch/s390/include/asm/gmap.h
@@ -0,0 +1,64 @@
+/*
+ *  KVM guest address space mapping code
+ *
+ *    Copyright IBM Corp. 2007, 2016
+ *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef _ASM_S390_GMAP_H
+#define _ASM_S390_GMAP_H
+
+/**
+ * struct gmap_struct - guest address space
+ * @crst_list: list of all crst tables used in the guest address space
+ * @mm: pointer to the parent mm_struct
+ * @guest_to_host: radix tree with guest to host address translation
+ * @host_to_guest: radix tree with pointer to segment table entries
+ * @guest_table_lock: spinlock to protect all entries in the guest page table
+ * @table: pointer to the page directory
+ * @asce: address space control element for gmap page table
+ * @pfault_enabled: defines if pfaults are applicable for the guest
+ */
+struct gmap {
+	struct list_head list;
+	struct list_head crst_list;
+	struct mm_struct *mm;
+	struct radix_tree_root guest_to_host;
+	struct radix_tree_root host_to_guest;
+	spinlock_t guest_table_lock;
+	unsigned long *table;
+	unsigned long asce;
+	unsigned long asce_end;
+	void *private;
+	bool pfault_enabled;
+};
+
+/**
+ * struct gmap_notifier - notify function block for page invalidation
+ * @notifier_call: address of callback function
+ */
+struct gmap_notifier {
+	struct list_head list;
+	void (*notifier_call)(struct gmap *gmap, unsigned long gaddr);
+};
+
+struct gmap *gmap_alloc(struct mm_struct *mm, unsigned long limit);
+void gmap_free(struct gmap *gmap);
+void gmap_enable(struct gmap *gmap);
+void gmap_disable(struct gmap *gmap);
+int gmap_map_segment(struct gmap *gmap, unsigned long from,
+		     unsigned long to, unsigned long len);
+int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len);
+unsigned long __gmap_translate(struct gmap *, unsigned long gaddr);
+unsigned long gmap_translate(struct gmap *, unsigned long gaddr);
+int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr);
+int gmap_fault(struct gmap *, unsigned long gaddr, unsigned int fault_flags);
+void gmap_discard(struct gmap *, unsigned long from, unsigned long to);
+void __gmap_zap(struct gmap *, unsigned long gaddr);
+void gmap_unlink(struct mm_struct *, unsigned long *table, unsigned long vmaddr);
+
+void gmap_register_ipte_notifier(struct gmap_notifier *);
+void gmap_unregister_ipte_notifier(struct gmap_notifier *);
+int gmap_ipte_notify(struct gmap *, unsigned long start, unsigned long len);
+
+#endif /* _ASM_S390_GMAP_H */
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 8959ebb6d2c9..6da41fab70fb 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -20,6 +20,7 @@
 #include <linux/kvm_types.h>
 #include <linux/kvm_host.h>
 #include <linux/kvm.h>
+#include <linux/seqlock.h>
 #include <asm/debug.h>
 #include <asm/cpu.h>
 #include <asm/fpu/api.h>
@@ -229,17 +230,11 @@ struct kvm_s390_itdb {
 	__u8	data[256];
 } __packed;
 
-struct kvm_s390_vregs {
-	__vector128 vrs[32];
-	__u8	reserved200[512];	/* for future vector expansion */
-} __packed;
-
 struct sie_page {
 	struct kvm_s390_sie_block sie_block;
 	__u8 reserved200[1024];		/* 0x0200 */
 	struct kvm_s390_itdb itdb;	/* 0x0600 */
-	__u8 reserved700[1280];		/* 0x0700 */
-	struct kvm_s390_vregs vregs;	/* 0x0c00 */
+	__u8 reserved700[2304];		/* 0x0700 */
 } __packed;
 
 struct kvm_vcpu_stat {
@@ -467,7 +462,7 @@ struct kvm_s390_irq_payload {
 struct kvm_s390_local_interrupt {
 	spinlock_t lock;
 	struct kvm_s390_float_interrupt *float_int;
-	wait_queue_head_t *wq;
+	struct swait_queue_head *wq;
 	atomic_t *cpuflags;
 	DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS);
 	struct kvm_s390_irq_payload irq;
@@ -558,6 +553,15 @@ struct kvm_vcpu_arch {
 	unsigned long pfault_token;
 	unsigned long pfault_select;
 	unsigned long pfault_compare;
+	bool cputm_enabled;
+	/*
+	 * The seqcount protects updates to cputm_start and sie_block.cputm,
+	 * this way we can have non-blocking reads with consistent values.
+	 * Only the owning VCPU thread (vcpu->cpu) is allowed to change these
+	 * values and to start/stop/enable/disable cpu timer accounting.
+	 */
+	seqcount_t cputm_seqcount;
+	__u64 cputm_start;
 };
 
 struct kvm_vm_stat {
@@ -596,15 +600,11 @@ struct s390_io_adapter {
 #define S390_ARCH_FAC_MASK_SIZE_U64 \
 	(S390_ARCH_FAC_MASK_SIZE_BYTE / sizeof(u64))
 
-struct kvm_s390_fac {
-	/* facility list requested by guest */
-	__u64 list[S390_ARCH_FAC_LIST_SIZE_U64];
-	/* facility mask supported by kvm & hosting machine */
-	__u64 mask[S390_ARCH_FAC_LIST_SIZE_U64];
-};
-
 struct kvm_s390_cpu_model {
-	struct kvm_s390_fac *fac;
+	/* facility mask supported by kvm & hosting machine */
+	__u64 fac_mask[S390_ARCH_FAC_LIST_SIZE_U64];
+	/* facility list requested by guest (in dma page) */
+	__u64 *fac_list;
 	struct cpuid cpu_id;
 	unsigned short ibc;
 };
@@ -623,6 +623,16 @@ struct kvm_s390_crypto_cb {
 	__u8    reserved80[128];                /* 0x0080 */
 };
 
+/*
+ * sie_page2 has to be allocated as DMA because fac_list and crycb need
+ * 31bit addresses in the sie control block.
+ */
+struct sie_page2 {
+	__u64 fac_list[S390_ARCH_FAC_LIST_SIZE_U64];	/* 0x0000 */
+	struct kvm_s390_crypto_cb crycb;		/* 0x0800 */
+	u8 reserved900[0x1000 - 0x900];			/* 0x0900 */
+} __packed;
+
 struct kvm_arch{
 	void *sca;
 	int use_esca;
@@ -643,6 +653,7 @@ struct kvm_arch{
 	int ipte_lock_count;
 	struct mutex ipte_mutex;
 	spinlock_t start_stop_lock;
+	struct sie_page2 *sie_page2;
 	struct kvm_s390_cpu_model model;
 	struct kvm_s390_crypto crypto;
 	u64 epoch;
diff --git a/arch/s390/include/asm/livepatch.h b/arch/s390/include/asm/livepatch.h
index 7aa799134a11..a52b6cca873d 100644
--- a/arch/s390/include/asm/livepatch.h
+++ b/arch/s390/include/asm/livepatch.h
@@ -37,7 +37,7 @@ static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 	regs->psw.addr = ip;
 }
 #else
-#error Live patching support is disabled; check CONFIG_LIVEPATCH
+#error Include linux/livepatch.h, not asm/livepatch.h
 #endif
 
 #endif
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index fb1b93ea3e3f..e485817f7b1a 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -15,17 +15,25 @@
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
+	spin_lock_init(&mm->context.list_lock);
+	INIT_LIST_HEAD(&mm->context.pgtable_list);
+	INIT_LIST_HEAD(&mm->context.gmap_list);
 	cpumask_clear(&mm->context.cpu_attach_mask);
 	atomic_set(&mm->context.attach_count, 0);
 	mm->context.flush_mm = 0;
-	mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS;
-	mm->context.asce_bits |= _ASCE_TYPE_REGION3;
 #ifdef CONFIG_PGSTE
 	mm->context.alloc_pgste = page_table_allocate_pgste;
 	mm->context.has_pgste = 0;
 	mm->context.use_skey = 0;
 #endif
-	mm->context.asce_limit = STACK_TOP_MAX;
+	if (mm->context.asce_limit == 0) {
+		/* context created by exec, set asce limit to 4TB */
+		mm->context.asce_bits = _ASCE_TABLE_LENGTH |
+			_ASCE_USER_BITS | _ASCE_TYPE_REGION3;
+		mm->context.asce_limit = STACK_TOP_MAX;
+	} else if (mm->context.asce_limit == (1UL << 31)) {
+		mm_inc_nr_pmds(mm);
+	}
 	crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
 	return 0;
 }
@@ -111,8 +119,6 @@ static inline void activate_mm(struct mm_struct *prev,
 static inline void arch_dup_mmap(struct mm_struct *oldmm,
 				 struct mm_struct *mm)
 {
-	if (oldmm->context.asce_limit < mm->context.asce_limit)
-		crst_table_downgrade(mm, oldmm->context.asce_limit);
 }
 
 static inline void arch_exit_mmap(struct mm_struct *mm)
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index c873e682b67f..b6bfa169a002 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -9,7 +9,6 @@
 #include <linux/pci.h>
 #include <linux/mutex.h>
 #include <asm-generic/pci.h>
-#include <asm-generic/pci-dma-compat.h>
 #include <asm/pci_clp.h>
 #include <asm/pci_debug.h>
 
@@ -45,7 +44,7 @@ struct zpci_fmb {
 	u64 rpcit_ops;
 	u64 dma_rbytes;
 	u64 dma_wbytes;
-} __packed __aligned(16);
+} __packed __aligned(64);
 
 enum zpci_state {
 	ZPCI_FN_STATE_RESERVED,
@@ -66,7 +65,6 @@ struct s390_domain;
 
 /* Private data per function */
 struct zpci_dev {
-	struct pci_dev	*pdev;
 	struct pci_bus	*bus;
 	struct list_head entry;		/* list of all zpci_devices, needed for hotplug, etc. */
 
@@ -192,7 +190,7 @@ int zpci_fmb_disable_device(struct zpci_dev *);
 /* Debug */
 int zpci_debug_init(void);
 void zpci_debug_exit(void);
-void zpci_debug_init_device(struct zpci_dev *);
+void zpci_debug_init_device(struct zpci_dev *, const char *);
 void zpci_debug_exit_device(struct zpci_dev *);
 void zpci_debug_info(struct zpci_dev *, struct seq_file *);
 
diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h
index dd78f92f1cce..e75c64cbcf08 100644
--- a/arch/s390/include/asm/pci_clp.h
+++ b/arch/s390/include/asm/pci_clp.h
@@ -49,9 +49,6 @@ struct clp_fh_list_entry {
 /* List PCI functions request */
 struct clp_req_list_pci {
 	struct clp_req_hdr hdr;
-	u32 fmt			:  4;	/* cmd request block format */
-	u32			: 28;
-	u64 reserved1;
 	u64 resume_token;
 	u64 reserved2;
 } __packed;
@@ -59,9 +56,6 @@ struct clp_req_list_pci {
 /* List PCI functions response */
 struct clp_rsp_list_pci {
 	struct clp_rsp_hdr hdr;
-	u32 fmt			:  4;	/* cmd request block format */
-	u32			: 28;
-	u64 reserved1;
 	u64 resume_token;
 	u32 reserved2;
 	u16 max_fn;
@@ -73,9 +67,6 @@ struct clp_rsp_list_pci {
 /* Query PCI function request */
 struct clp_req_query_pci {
 	struct clp_req_hdr hdr;
-	u32 fmt			:  4;	/* cmd request block format */
-	u32			: 28;
-	u64 reserved1;
 	u32 fh;				/* function handle */
 	u32 reserved2;
 	u64 reserved3;
@@ -84,9 +75,6 @@ struct clp_req_query_pci {
 /* Query PCI function response */
 struct clp_rsp_query_pci {
 	struct clp_rsp_hdr hdr;
-	u32 fmt			:  4;	/* cmd request block format */
-	u32			: 28;
-	u64			: 64;
 	u16 vfn;			/* virtual fn number */
 	u16			:  7;
 	u16 util_str_avail	:  1;	/* utility string available? */
@@ -108,21 +96,15 @@ struct clp_rsp_query_pci {
 /* Query PCI function group request */
 struct clp_req_query_pci_grp {
 	struct clp_req_hdr hdr;
-	u32 fmt			:  4;	/* cmd request block format */
-	u32			: 28;
-	u64 reserved1;
-	u32			: 24;
+	u32 reserved2		: 24;
 	u32 pfgid		:  8;	/* function group id */
-	u32 reserved2;
-	u64 reserved3;
+	u32 reserved3;
+	u64 reserved4;
 } __packed;
 
 /* Query PCI function group response */
 struct clp_rsp_query_pci_grp {
 	struct clp_rsp_hdr hdr;
-	u32 fmt			:  4;	/* cmd request block format */
-	u32			: 28;
-	u64 reserved1;
 	u16			:  4;
 	u16 noi			: 12;	/* number of interrupts */
 	u8 version;
@@ -141,9 +123,6 @@ struct clp_rsp_query_pci_grp {
 /* Set PCI function request */
 struct clp_req_set_pci {
 	struct clp_req_hdr hdr;
-	u32 fmt			:  4;	/* cmd request block format */
-	u32			: 28;
-	u64 reserved1;
 	u32 fh;				/* function handle */
 	u16 reserved2;
 	u8 oc;				/* operation controls */
@@ -154,9 +133,6 @@ struct clp_req_set_pci {
 /* Set PCI function response */
 struct clp_rsp_set_pci {
 	struct clp_rsp_hdr hdr;
-	u32 fmt			:  4;	/* cmd request block format */
-	u32			: 28;
-	u64 reserved1;
 	u32 fh;				/* function handle */
 	u32 reserved3;
 	u64 reserved4;
diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index 6d6556ca24aa..90240dfef76a 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -178,7 +178,6 @@
 	ret__;								\
 })
 
-#define this_cpu_cmpxchg_double_4 arch_this_cpu_cmpxchg_double
 #define this_cpu_cmpxchg_double_8 arch_this_cpu_cmpxchg_double
 
 #include <asm-generic/percpu.h>
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index f897ec73dc8c..1f7ff85c5e4c 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -21,7 +21,7 @@
 #define PMU_F_ERR_LSDA			0x0200
 #define PMU_F_ERR_MASK			(PMU_F_ERR_IBE|PMU_F_ERR_LSDA)
 
-/* Perf defintions for PMU event attributes in sysfs */
+/* Perf definitions for PMU event attributes in sysfs */
 extern __init const struct attribute_group **cpumf_cf_event_group(void);
 extern ssize_t cpumf_events_sysfs_show(struct device *dev,
 				       struct device_attribute *attr,
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 7b7858f158b4..9b3d9b6099f2 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -23,10 +23,6 @@ void page_table_free(struct mm_struct *, unsigned long *);
 void page_table_free_rcu(struct mmu_gather *, unsigned long *, unsigned long);
 extern int page_table_allocate_pgste;
 
-int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
-			  unsigned long key, bool nq);
-unsigned long get_guest_storage_key(struct mm_struct *mm, unsigned long addr);
-
 static inline void clear_table(unsigned long *s, unsigned long val, size_t n)
 {
 	typedef struct { char _[n]; } addrtype;
@@ -100,12 +96,26 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	spin_lock_init(&mm->context.list_lock);
-	INIT_LIST_HEAD(&mm->context.pgtable_list);
-	INIT_LIST_HEAD(&mm->context.gmap_list);
-	return (pgd_t *) crst_table_alloc(mm);
+	unsigned long *table = crst_table_alloc(mm);
+
+	if (!table)
+		return NULL;
+	if (mm->context.asce_limit == (1UL << 31)) {
+		/* Forking a compat process with 2 page table levels */
+		if (!pgtable_pmd_page_ctor(virt_to_page(table))) {
+			crst_table_free(mm, table);
+			return NULL;
+		}
+	}
+	return (pgd_t *) table;
+}
+
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	if (mm->context.asce_limit == (1UL << 31))
+		pgtable_pmd_page_dtor(virt_to_page(pgd));
+	crst_table_free(mm, (unsigned long *) pgd);
 }
-#define pgd_free(mm, pgd) crst_table_free(mm, (unsigned long *) pgd)
 
 static inline void pmd_populate(struct mm_struct *mm,
 				pmd_t *pmd, pgtable_t pte)
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 64ead8091248..2f66645587a2 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -298,15 +298,15 @@ static inline int is_module_addr(void *addr)
 
 /*
  * Segment table entry encoding (R = read-only, I = invalid, y = young bit):
- *				dy..R...I...wr
+ *				dy..R...I...rw
  * prot-none, clean, old	00..1...1...00
  * prot-none, clean, young	01..1...1...00
  * prot-none, dirty, old	10..1...1...00
  * prot-none, dirty, young	11..1...1...00
- * read-only, clean, old	00..1...1...01
- * read-only, clean, young	01..1...0...01
- * read-only, dirty, old	10..1...1...01
- * read-only, dirty, young	11..1...0...01
+ * read-only, clean, old	00..1...1...10
+ * read-only, clean, young	01..1...0...10
+ * read-only, dirty, old	10..1...1...10
+ * read-only, dirty, young	11..1...0...10
  * read-write, clean, old	00..1...1...11
  * read-write, clean, young	01..1...0...11
  * read-write, dirty, old	10..0...1...11
@@ -520,15 +520,6 @@ static inline int pmd_bad(pmd_t pmd)
 	return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0;
 }
 
-#define  __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
-extern int pmdp_set_access_flags(struct vm_area_struct *vma,
-				 unsigned long address, pmd_t *pmdp,
-				 pmd_t entry, int dirty);
-
-#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
-extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
-				  unsigned long address, pmd_t *pmdp);
-
 #define __HAVE_ARCH_PMD_WRITE
 static inline int pmd_write(pmd_t pmd)
 {
@@ -631,208 +622,6 @@ static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd)
 	return pmd;
 }
 
-static inline pgste_t pgste_get_lock(pte_t *ptep)
-{
-	unsigned long new = 0;
-#ifdef CONFIG_PGSTE
-	unsigned long old;
-
-	preempt_disable();
-	asm(
-		"	lg	%0,%2\n"
-		"0:	lgr	%1,%0\n"
-		"	nihh	%0,0xff7f\n"	/* clear PCL bit in old */
-		"	oihh	%1,0x0080\n"	/* set PCL bit in new */
-		"	csg	%0,%1,%2\n"
-		"	jl	0b\n"
-		: "=&d" (old), "=&d" (new), "=Q" (ptep[PTRS_PER_PTE])
-		: "Q" (ptep[PTRS_PER_PTE]) : "cc", "memory");
-#endif
-	return __pgste(new);
-}
-
-static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste)
-{
-#ifdef CONFIG_PGSTE
-	asm(
-		"	nihh	%1,0xff7f\n"	/* clear PCL bit */
-		"	stg	%1,%0\n"
-		: "=Q" (ptep[PTRS_PER_PTE])
-		: "d" (pgste_val(pgste)), "Q" (ptep[PTRS_PER_PTE])
-		: "cc", "memory");
-	preempt_enable();
-#endif
-}
-
-static inline pgste_t pgste_get(pte_t *ptep)
-{
-	unsigned long pgste = 0;
-#ifdef CONFIG_PGSTE
-	pgste = *(unsigned long *)(ptep + PTRS_PER_PTE);
-#endif
-	return __pgste(pgste);
-}
-
-static inline void pgste_set(pte_t *ptep, pgste_t pgste)
-{
-#ifdef CONFIG_PGSTE
-	*(pgste_t *)(ptep + PTRS_PER_PTE) = pgste;
-#endif
-}
-
-static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste,
-				       struct mm_struct *mm)
-{
-#ifdef CONFIG_PGSTE
-	unsigned long address, bits, skey;
-
-	if (!mm_use_skey(mm) || pte_val(*ptep) & _PAGE_INVALID)
-		return pgste;
-	address = pte_val(*ptep) & PAGE_MASK;
-	skey = (unsigned long) page_get_storage_key(address);
-	bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
-	/* Transfer page changed & referenced bit to guest bits in pgste */
-	pgste_val(pgste) |= bits << 48;		/* GR bit & GC bit */
-	/* Copy page access key and fetch protection bit to pgste */
-	pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT);
-	pgste_val(pgste) |= (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
-#endif
-	return pgste;
-
-}
-
-static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry,
-				 struct mm_struct *mm)
-{
-#ifdef CONFIG_PGSTE
-	unsigned long address;
-	unsigned long nkey;
-
-	if (!mm_use_skey(mm) || pte_val(entry) & _PAGE_INVALID)
-		return;
-	VM_BUG_ON(!(pte_val(*ptep) & _PAGE_INVALID));
-	address = pte_val(entry) & PAGE_MASK;
-	/*
-	 * Set page access key and fetch protection bit from pgste.
-	 * The guest C/R information is still in the PGSTE, set real
-	 * key C/R to 0.
-	 */
-	nkey = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
-	nkey |= (pgste_val(pgste) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 48;
-	page_set_storage_key(address, nkey, 0);
-#endif
-}
-
-static inline pgste_t pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry)
-{
-	if ((pte_val(entry) & _PAGE_PRESENT) &&
-	    (pte_val(entry) & _PAGE_WRITE) &&
-	    !(pte_val(entry) & _PAGE_INVALID)) {
-		if (!MACHINE_HAS_ESOP) {
-			/*
-			 * Without enhanced suppression-on-protection force
-			 * the dirty bit on for all writable ptes.
-			 */
-			pte_val(entry) |= _PAGE_DIRTY;
-			pte_val(entry) &= ~_PAGE_PROTECT;
-		}
-		if (!(pte_val(entry) & _PAGE_PROTECT))
-			/* This pte allows write access, set user-dirty */
-			pgste_val(pgste) |= PGSTE_UC_BIT;
-	}
-	*ptep = entry;
-	return pgste;
-}
-
-/**
- * struct gmap_struct - guest address space
- * @crst_list: list of all crst tables used in the guest address space
- * @mm: pointer to the parent mm_struct
- * @guest_to_host: radix tree with guest to host address translation
- * @host_to_guest: radix tree with pointer to segment table entries
- * @guest_table_lock: spinlock to protect all entries in the guest page table
- * @table: pointer to the page directory
- * @asce: address space control element for gmap page table
- * @pfault_enabled: defines if pfaults are applicable for the guest
- */
-struct gmap {
-	struct list_head list;
-	struct list_head crst_list;
-	struct mm_struct *mm;
-	struct radix_tree_root guest_to_host;
-	struct radix_tree_root host_to_guest;
-	spinlock_t guest_table_lock;
-	unsigned long *table;
-	unsigned long asce;
-	unsigned long asce_end;
-	void *private;
-	bool pfault_enabled;
-};
-
-/**
- * struct gmap_notifier - notify function block for page invalidation
- * @notifier_call: address of callback function
- */
-struct gmap_notifier {
-	struct list_head list;
-	void (*notifier_call)(struct gmap *gmap, unsigned long gaddr);
-};
-
-struct gmap *gmap_alloc(struct mm_struct *mm, unsigned long limit);
-void gmap_free(struct gmap *gmap);
-void gmap_enable(struct gmap *gmap);
-void gmap_disable(struct gmap *gmap);
-int gmap_map_segment(struct gmap *gmap, unsigned long from,
-		     unsigned long to, unsigned long len);
-int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len);
-unsigned long __gmap_translate(struct gmap *, unsigned long gaddr);
-unsigned long gmap_translate(struct gmap *, unsigned long gaddr);
-int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr);
-int gmap_fault(struct gmap *, unsigned long gaddr, unsigned int fault_flags);
-void gmap_discard(struct gmap *, unsigned long from, unsigned long to);
-void __gmap_zap(struct gmap *, unsigned long gaddr);
-bool gmap_test_and_clear_dirty(unsigned long address, struct gmap *);
-
-
-void gmap_register_ipte_notifier(struct gmap_notifier *);
-void gmap_unregister_ipte_notifier(struct gmap_notifier *);
-int gmap_ipte_notify(struct gmap *, unsigned long start, unsigned long len);
-void gmap_do_ipte_notify(struct mm_struct *, unsigned long addr, pte_t *);
-
-static inline pgste_t pgste_ipte_notify(struct mm_struct *mm,
-					unsigned long addr,
-					pte_t *ptep, pgste_t pgste)
-{
-#ifdef CONFIG_PGSTE
-	if (pgste_val(pgste) & PGSTE_IN_BIT) {
-		pgste_val(pgste) &= ~PGSTE_IN_BIT;
-		gmap_do_ipte_notify(mm, addr, ptep);
-	}
-#endif
-	return pgste;
-}
-
-/*
- * Certain architectures need to do special things when PTEs
- * within a page table are directly modified.  Thus, the following
- * hook is made available.
- */
-static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep, pte_t entry)
-{
-	pgste_t pgste;
-
-	if (mm_has_pgste(mm)) {
-		pgste = pgste_get_lock(ptep);
-		pgste_val(pgste) &= ~_PGSTE_GPS_ZERO;
-		pgste_set_key(ptep, pgste, entry, mm);
-		pgste = pgste_set_pte(ptep, pgste, entry);
-		pgste_set_unlock(ptep, pgste);
-	} else {
-		*ptep = entry;
-	}
-}
-
 /*
  * query functions pte_write/pte_dirty/pte_young only work if
  * pte_present() is true. Undefined behaviour if not..
@@ -998,96 +787,30 @@ static inline void __ptep_ipte_range(unsigned long address, int nr, pte_t *ptep)
 	} while (nr != 255);
 }
 
-static inline void ptep_flush_direct(struct mm_struct *mm,
-				     unsigned long address, pte_t *ptep)
-{
-	int active, count;
-
-	if (pte_val(*ptep) & _PAGE_INVALID)
-		return;
-	active = (mm == current->active_mm) ? 1 : 0;
-	count = atomic_add_return(0x10000, &mm->context.attach_count);
-	if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
-	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
-		__ptep_ipte_local(address, ptep);
-	else
-		__ptep_ipte(address, ptep);
-	atomic_sub(0x10000, &mm->context.attach_count);
-}
-
-static inline void ptep_flush_lazy(struct mm_struct *mm,
-				   unsigned long address, pte_t *ptep)
-{
-	int active, count;
-
-	if (pte_val(*ptep) & _PAGE_INVALID)
-		return;
-	active = (mm == current->active_mm) ? 1 : 0;
-	count = atomic_add_return(0x10000, &mm->context.attach_count);
-	if ((count & 0xffff) <= active) {
-		pte_val(*ptep) |= _PAGE_INVALID;
-		mm->context.flush_mm = 1;
-	} else
-		__ptep_ipte(address, ptep);
-	atomic_sub(0x10000, &mm->context.attach_count);
-}
-
 /*
- * Get (and clear) the user dirty bit for a pte.
+ * This is hard to understand. ptep_get_and_clear and ptep_clear_flush
+ * both clear the TLB for the unmapped pte. The reason is that
+ * ptep_get_and_clear is used in common code (e.g. change_pte_range)
+ * to modify an active pte. The sequence is
+ *   1) ptep_get_and_clear
+ *   2) set_pte_at
+ *   3) flush_tlb_range
+ * On s390 the tlb needs to get flushed with the modification of the pte
+ * if the pte is active. The only way how this can be implemented is to
+ * have ptep_get_and_clear do the tlb flush. In exchange flush_tlb_range
+ * is a nop.
  */
-static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm,
-						 unsigned long addr,
-						 pte_t *ptep)
-{
-	pgste_t pgste;
-	pte_t pte;
-	int dirty;
-
-	if (!mm_has_pgste(mm))
-		return 0;
-	pgste = pgste_get_lock(ptep);
-	dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT);
-	pgste_val(pgste) &= ~PGSTE_UC_BIT;
-	pte = *ptep;
-	if (dirty && (pte_val(pte) & _PAGE_PRESENT)) {
-		pgste = pgste_ipte_notify(mm, addr, ptep, pgste);
-		__ptep_ipte(addr, ptep);
-		if (MACHINE_HAS_ESOP || !(pte_val(pte) & _PAGE_WRITE))
-			pte_val(pte) |= _PAGE_PROTECT;
-		else
-			pte_val(pte) |= _PAGE_INVALID;
-		*ptep = pte;
-	}
-	pgste_set_unlock(ptep, pgste);
-	return dirty;
-}
+pte_t ptep_xchg_direct(struct mm_struct *, unsigned long, pte_t *, pte_t);
+pte_t ptep_xchg_lazy(struct mm_struct *, unsigned long, pte_t *, pte_t);
 
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long addr, pte_t *ptep)
 {
-	pgste_t pgste;
-	pte_t pte, oldpte;
-	int young;
-
-	if (mm_has_pgste(vma->vm_mm)) {
-		pgste = pgste_get_lock(ptep);
-		pgste = pgste_ipte_notify(vma->vm_mm, addr, ptep, pgste);
-	}
-
-	oldpte = pte = *ptep;
-	ptep_flush_direct(vma->vm_mm, addr, ptep);
-	young = pte_young(pte);
-	pte = pte_mkold(pte);
-
-	if (mm_has_pgste(vma->vm_mm)) {
-		pgste = pgste_update_all(&oldpte, pgste, vma->vm_mm);
-		pgste = pgste_set_pte(ptep, pgste, pte);
-		pgste_set_unlock(ptep, pgste);
-	} else
-		*ptep = pte;
+	pte_t pte = *ptep;
 
-	return young;
+	pte = ptep_xchg_direct(vma->vm_mm, addr, ptep, pte_mkold(pte));
+	return pte_young(pte);
 }
 
 #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
@@ -1097,104 +820,22 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
 	return ptep_test_and_clear_young(vma, address, ptep);
 }
 
-/*
- * This is hard to understand. ptep_get_and_clear and ptep_clear_flush
- * both clear the TLB for the unmapped pte. The reason is that
- * ptep_get_and_clear is used in common code (e.g. change_pte_range)
- * to modify an active pte. The sequence is
- *   1) ptep_get_and_clear
- *   2) set_pte_at
- *   3) flush_tlb_range
- * On s390 the tlb needs to get flushed with the modification of the pte
- * if the pte is active. The only way how this can be implemented is to
- * have ptep_get_and_clear do the tlb flush. In exchange flush_tlb_range
- * is a nop.
- */
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
-				       unsigned long address, pte_t *ptep)
+				       unsigned long addr, pte_t *ptep)
 {
-	pgste_t pgste;
-	pte_t pte;
-
-	if (mm_has_pgste(mm)) {
-		pgste = pgste_get_lock(ptep);
-		pgste = pgste_ipte_notify(mm, address, ptep, pgste);
-	}
-
-	pte = *ptep;
-	ptep_flush_lazy(mm, address, ptep);
-	pte_val(*ptep) = _PAGE_INVALID;
-
-	if (mm_has_pgste(mm)) {
-		pgste = pgste_update_all(&pte, pgste, mm);
-		pgste_set_unlock(ptep, pgste);
-	}
-	return pte;
+	return ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID));
 }
 
 #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
-static inline pte_t ptep_modify_prot_start(struct mm_struct *mm,
-					   unsigned long address,
-					   pte_t *ptep)
-{
-	pgste_t pgste;
-	pte_t pte;
-
-	if (mm_has_pgste(mm)) {
-		pgste = pgste_get_lock(ptep);
-		pgste_ipte_notify(mm, address, ptep, pgste);
-	}
-
-	pte = *ptep;
-	ptep_flush_lazy(mm, address, ptep);
-
-	if (mm_has_pgste(mm)) {
-		pgste = pgste_update_all(&pte, pgste, mm);
-		pgste_set(ptep, pgste);
-	}
-	return pte;
-}
-
-static inline void ptep_modify_prot_commit(struct mm_struct *mm,
-					   unsigned long address,
-					   pte_t *ptep, pte_t pte)
-{
-	pgste_t pgste;
-
-	if (mm_has_pgste(mm)) {
-		pgste = pgste_get(ptep);
-		pgste_set_key(ptep, pgste, pte, mm);
-		pgste = pgste_set_pte(ptep, pgste, pte);
-		pgste_set_unlock(ptep, pgste);
-	} else
-		*ptep = pte;
-}
+pte_t ptep_modify_prot_start(struct mm_struct *, unsigned long, pte_t *);
+void ptep_modify_prot_commit(struct mm_struct *, unsigned long, pte_t *, pte_t);
 
 #define __HAVE_ARCH_PTEP_CLEAR_FLUSH
 static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,
-				     unsigned long address, pte_t *ptep)
+				     unsigned long addr, pte_t *ptep)
 {
-	pgste_t pgste;
-	pte_t pte;
-
-	if (mm_has_pgste(vma->vm_mm)) {
-		pgste = pgste_get_lock(ptep);
-		pgste = pgste_ipte_notify(vma->vm_mm, address, ptep, pgste);
-	}
-
-	pte = *ptep;
-	ptep_flush_direct(vma->vm_mm, address, ptep);
-	pte_val(*ptep) = _PAGE_INVALID;
-
-	if (mm_has_pgste(vma->vm_mm)) {
-		if ((pgste_val(pgste) & _PGSTE_GPS_USAGE_MASK) ==
-		    _PGSTE_GPS_USAGE_UNUSED)
-			pte_val(pte) |= _PAGE_UNUSED;
-		pgste = pgste_update_all(&pte, pgste, vma->vm_mm);
-		pgste_set_unlock(ptep, pgste);
-	}
-	return pte;
+	return ptep_xchg_direct(vma->vm_mm, addr, ptep, __pte(_PAGE_INVALID));
 }
 
 /*
@@ -1206,80 +847,66 @@ static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,
  */
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
 static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
-					    unsigned long address,
+					    unsigned long addr,
 					    pte_t *ptep, int full)
 {
-	pgste_t pgste;
-	pte_t pte;
-
-	if (!full && mm_has_pgste(mm)) {
-		pgste = pgste_get_lock(ptep);
-		pgste = pgste_ipte_notify(mm, address, ptep, pgste);
-	}
-
-	pte = *ptep;
-	if (!full)
-		ptep_flush_lazy(mm, address, ptep);
-	pte_val(*ptep) = _PAGE_INVALID;
-
-	if (!full && mm_has_pgste(mm)) {
-		pgste = pgste_update_all(&pte, pgste, mm);
-		pgste_set_unlock(ptep, pgste);
+	if (full) {
+		pte_t pte = *ptep;
+		*ptep = __pte(_PAGE_INVALID);
+		return pte;
 	}
-	return pte;
+	return ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID));
 }
 
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
-static inline pte_t ptep_set_wrprotect(struct mm_struct *mm,
-				       unsigned long address, pte_t *ptep)
+static inline void ptep_set_wrprotect(struct mm_struct *mm,
+				      unsigned long addr, pte_t *ptep)
 {
-	pgste_t pgste;
 	pte_t pte = *ptep;
 
-	if (pte_write(pte)) {
-		if (mm_has_pgste(mm)) {
-			pgste = pgste_get_lock(ptep);
-			pgste = pgste_ipte_notify(mm, address, ptep, pgste);
-		}
-
-		ptep_flush_lazy(mm, address, ptep);
-		pte = pte_wrprotect(pte);
-
-		if (mm_has_pgste(mm)) {
-			pgste = pgste_set_pte(ptep, pgste, pte);
-			pgste_set_unlock(ptep, pgste);
-		} else
-			*ptep = pte;
-	}
-	return pte;
+	if (pte_write(pte))
+		ptep_xchg_lazy(mm, addr, ptep, pte_wrprotect(pte));
 }
 
 #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 static inline int ptep_set_access_flags(struct vm_area_struct *vma,
-					unsigned long address, pte_t *ptep,
+					unsigned long addr, pte_t *ptep,
 					pte_t entry, int dirty)
 {
-	pgste_t pgste;
-	pte_t oldpte;
-
-	oldpte = *ptep;
-	if (pte_same(oldpte, entry))
+	if (pte_same(*ptep, entry))
 		return 0;
-	if (mm_has_pgste(vma->vm_mm)) {
-		pgste = pgste_get_lock(ptep);
-		pgste = pgste_ipte_notify(vma->vm_mm, address, ptep, pgste);
-	}
+	ptep_xchg_direct(vma->vm_mm, addr, ptep, entry);
+	return 1;
+}
 
-	ptep_flush_direct(vma->vm_mm, address, ptep);
+/*
+ * Additional functions to handle KVM guest page tables
+ */
+void ptep_set_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t entry);
+void ptep_set_notify(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+void ptep_notify(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+void ptep_zap_unused(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep , int reset);
+void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+
+bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long address);
+int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
+			  unsigned char key, bool nq);
+unsigned char get_guest_storage_key(struct mm_struct *mm, unsigned long addr);
 
-	if (mm_has_pgste(vma->vm_mm)) {
-		if (pte_val(oldpte) & _PAGE_INVALID)
-			pgste_set_key(ptep, pgste, entry, vma->vm_mm);
-		pgste = pgste_set_pte(ptep, pgste, entry);
-		pgste_set_unlock(ptep, pgste);
-	} else
+/*
+ * Certain architectures need to do special things when PTEs
+ * within a page table are directly modified.  Thus, the following
+ * hook is made available.
+ */
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t entry)
+{
+	if (mm_has_pgste(mm))
+		ptep_set_pte_at(mm, addr, ptep, entry);
+	else
 		*ptep = entry;
-	return 1;
 }
 
 /*
@@ -1476,54 +1103,51 @@ static inline void __pmdp_idte_local(unsigned long address, pmd_t *pmdp)
 		: "cc" );
 }
 
-static inline void pmdp_flush_direct(struct mm_struct *mm,
-				     unsigned long address, pmd_t *pmdp)
-{
-	int active, count;
+pmd_t pmdp_xchg_direct(struct mm_struct *, unsigned long, pmd_t *, pmd_t);
+pmd_t pmdp_xchg_lazy(struct mm_struct *, unsigned long, pmd_t *, pmd_t);
 
-	if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
-		return;
-	if (!MACHINE_HAS_IDTE) {
-		__pmdp_csp(pmdp);
-		return;
-	}
-	active = (mm == current->active_mm) ? 1 : 0;
-	count = atomic_add_return(0x10000, &mm->context.attach_count);
-	if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
-	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
-		__pmdp_idte_local(address, pmdp);
-	else
-		__pmdp_idte(address, pmdp);
-	atomic_sub(0x10000, &mm->context.attach_count);
-}
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
-static inline void pmdp_flush_lazy(struct mm_struct *mm,
-				   unsigned long address, pmd_t *pmdp)
+#define __HAVE_ARCH_PGTABLE_DEPOSIT
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				pgtable_t pgtable);
+
+#define __HAVE_ARCH_PGTABLE_WITHDRAW
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
+
+#define  __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
+					unsigned long addr, pmd_t *pmdp,
+					pmd_t entry, int dirty)
 {
-	int active, count;
+	VM_BUG_ON(addr & ~HPAGE_MASK);
 
-	if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
-		return;
-	active = (mm == current->active_mm) ? 1 : 0;
-	count = atomic_add_return(0x10000, &mm->context.attach_count);
-	if ((count & 0xffff) <= active) {
-		pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID;
-		mm->context.flush_mm = 1;
-	} else if (MACHINE_HAS_IDTE)
-		__pmdp_idte(address, pmdp);
-	else
-		__pmdp_csp(pmdp);
-	atomic_sub(0x10000, &mm->context.attach_count);
+	entry = pmd_mkyoung(entry);
+	if (dirty)
+		entry = pmd_mkdirty(entry);
+	if (pmd_val(*pmdp) == pmd_val(entry))
+		return 0;
+	pmdp_xchg_direct(vma->vm_mm, addr, pmdp, entry);
+	return 1;
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
+static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
+					    unsigned long addr, pmd_t *pmdp)
+{
+	pmd_t pmd = *pmdp;
 
-#define __HAVE_ARCH_PGTABLE_DEPOSIT
-extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
-				       pgtable_t pgtable);
+	pmd = pmdp_xchg_direct(vma->vm_mm, addr, pmdp, pmd_mkold(pmd));
+	return pmd_young(pmd);
+}
 
-#define __HAVE_ARCH_PGTABLE_WITHDRAW
-extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
+#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
+static inline int pmdp_clear_flush_young(struct vm_area_struct *vma,
+					 unsigned long addr, pmd_t *pmdp)
+{
+	VM_BUG_ON(addr & ~HPAGE_MASK);
+	return pmdp_test_and_clear_young(vma, addr, pmdp);
+}
 
 static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 			      pmd_t *pmdp, pmd_t entry)
@@ -1539,66 +1163,48 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd)
 	return pmd;
 }
 
-#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
-static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
-					    unsigned long address, pmd_t *pmdp)
-{
-	pmd_t pmd;
-
-	pmd = *pmdp;
-	pmdp_flush_direct(vma->vm_mm, address, pmdp);
-	*pmdp = pmd_mkold(pmd);
-	return pmd_young(pmd);
-}
-
 #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
 static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
-					    unsigned long address, pmd_t *pmdp)
+					    unsigned long addr, pmd_t *pmdp)
 {
-	pmd_t pmd = *pmdp;
-
-	pmdp_flush_direct(mm, address, pmdp);
-	pmd_clear(pmdp);
-	return pmd;
+	return pmdp_xchg_direct(mm, addr, pmdp, __pmd(_SEGMENT_ENTRY_INVALID));
 }
 
 #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL
 static inline pmd_t pmdp_huge_get_and_clear_full(struct mm_struct *mm,
-						 unsigned long address,
+						 unsigned long addr,
 						 pmd_t *pmdp, int full)
 {
-	pmd_t pmd = *pmdp;
-
-	if (!full)
-		pmdp_flush_lazy(mm, address, pmdp);
-	pmd_clear(pmdp);
-	return pmd;
+	if (full) {
+		pmd_t pmd = *pmdp;
+		*pmdp = __pmd(_SEGMENT_ENTRY_INVALID);
+		return pmd;
+	}
+	return pmdp_xchg_lazy(mm, addr, pmdp, __pmd(_SEGMENT_ENTRY_INVALID));
 }
 
 #define __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH
 static inline pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma,
-					  unsigned long address, pmd_t *pmdp)
+					  unsigned long addr, pmd_t *pmdp)
 {
-	return pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
+	return pmdp_huge_get_and_clear(vma->vm_mm, addr, pmdp);
 }
 
 #define __HAVE_ARCH_PMDP_INVALIDATE
 static inline void pmdp_invalidate(struct vm_area_struct *vma,
-				   unsigned long address, pmd_t *pmdp)
+				   unsigned long addr, pmd_t *pmdp)
 {
-	pmdp_flush_direct(vma->vm_mm, address, pmdp);
+	pmdp_xchg_direct(vma->vm_mm, addr, pmdp, __pmd(_SEGMENT_ENTRY_INVALID));
 }
 
 #define __HAVE_ARCH_PMDP_SET_WRPROTECT
 static inline void pmdp_set_wrprotect(struct mm_struct *mm,
-				      unsigned long address, pmd_t *pmdp)
+				      unsigned long addr, pmd_t *pmdp)
 {
 	pmd_t pmd = *pmdp;
 
-	if (pmd_write(pmd)) {
-		pmdp_flush_direct(mm, address, pmdp);
-		set_pmd_at(mm, address, pmdp, pmd_wrprotect(pmd));
-	}
+	if (pmd_write(pmd))
+		pmd = pmdp_xchg_lazy(mm, addr, pmdp, pmd_wrprotect(pmd));
 }
 
 static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 1c4fe129486d..d6fd22ea270d 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -184,6 +184,10 @@ struct task_struct;
 struct mm_struct;
 struct seq_file;
 
+typedef int (*dump_trace_func_t)(void *data, unsigned long address);
+void dump_trace(dump_trace_func_t func, void *data,
+		struct task_struct *task, unsigned long sp);
+
 void show_cacheinfo(struct seq_file *m);
 
 /* Free all resources held by a thread. */
@@ -203,6 +207,14 @@ unsigned long get_wchan(struct task_struct *p);
 /* Has task runtime instrumentation enabled ? */
 #define is_ri_task(tsk) (!!(tsk)->thread.ri_cb)
 
+static inline unsigned long current_stack_pointer(void)
+{
+	unsigned long sp;
+
+	asm volatile("la %0,0(15)" : "=a" (sp));
+	return sp;
+}
+
 static inline unsigned short stap(void)
 {
 	unsigned short cpu_address;
diff --git a/arch/s390/include/asm/rwsem.h b/arch/s390/include/asm/rwsem.h
index 4b43ee7e6776..fead491dfc28 100644
--- a/arch/s390/include/asm/rwsem.h
+++ b/arch/s390/include/asm/rwsem.h
@@ -31,7 +31,7 @@
  * This should be totally fair - if anything is waiting, a process that wants a
  * lock will go to the back of the queue. When the currently active lock is
  * released, if there's a writer at the front of the queue, then that and only
- * that will be woken up; if there's a bunch of consequtive readers at the
+ * that will be woken up; if there's a bunch of consecutive readers at the
  * front, then they'll all be woken up, but no other readers will be.
  */
 
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 69837225119e..c0f0efbb6ab5 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -101,6 +101,8 @@ extern void pfault_fini(void);
 #define pfault_fini()		do { } while (0)
 #endif /* CONFIG_PFAULT */
 
+void report_user_fault(struct pt_regs *regs, long signr, int is_mm_fault);
+
 extern void cmma_init(void);
 
 extern void (*_machine_restart)(char *command);
diff --git a/arch/s390/include/asm/xor.h b/arch/s390/include/asm/xor.h
index c82eb12a5b18..c988df744a70 100644
--- a/arch/s390/include/asm/xor.h
+++ b/arch/s390/include/asm/xor.h
@@ -1 +1,20 @@
-#include <asm-generic/xor.h>
+/*
+ * Optimited xor routines
+ *
+ * Copyright IBM Corp. 2016
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+#ifndef _ASM_S390_XOR_H
+#define _ASM_S390_XOR_H
+
+extern struct xor_block_template xor_block_xc;
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES				\
+do {							\
+	xor_speed(&xor_block_xc);			\
+} while (0)
+
+#define XOR_SELECT_TEMPLATE(FASTEST)	(&xor_block_xc)
+
+#endif /* _ASM_S390_XOR_H */
diff --git a/arch/s390/include/uapi/asm/clp.h b/arch/s390/include/uapi/asm/clp.h
new file mode 100644
index 000000000000..ab72d9d24373
--- /dev/null
+++ b/arch/s390/include/uapi/asm/clp.h
@@ -0,0 +1,28 @@
+/*
+ * ioctl interface for /dev/clp
+ *
+ * Copyright IBM Corp. 2016
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef _ASM_CLP_H
+#define _ASM_CLP_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+struct clp_req {
+	unsigned int c : 1;
+	unsigned int r : 1;
+	unsigned int lps : 6;
+	unsigned int cmd : 8;
+	unsigned int : 16;
+	unsigned int reserved;
+	__u64 data_p;
+};
+
+#define CLP_IOCTL_MAGIC 'c'
+
+#define CLP_SYNC _IOWR(CLP_IOCTL_MAGIC, 0xC1, struct clp_req)
+
+#endif
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index fe84bd5fe7ce..347fe5afa419 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -154,6 +154,7 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_PFAULT (1UL << 5)
 #define KVM_SYNC_VRS    (1UL << 6)
 #define KVM_SYNC_RICCB  (1UL << 7)
+#define KVM_SYNC_FPRS   (1UL << 8)
 /* definition of registers in kvm_run */
 struct kvm_sync_regs {
 	__u64 prefix;	/* prefix register */
@@ -168,9 +169,12 @@ struct kvm_sync_regs {
 	__u64 pft;	/* pfault token [PFAULT] */
 	__u64 pfs;	/* pfault select [PFAULT] */
 	__u64 pfc;	/* pfault compare [PFAULT] */
-	__u64 vrs[32][2];	/* vector registers */
+	union {
+		__u64 vrs[32][2];	/* vector registers (KVM_SYNC_VRS) */
+		__u64 fprs[16];		/* fp registers (KVM_SYNC_FPRS) */
+	};
 	__u8  reserved[512];	/* for future vector expansion */
-	__u32 fpc;	/* only valid with vector registers */
+	__u32 fpc;		/* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */
 	__u8 padding[52];	/* riccb needs to be 64byte aligned */
 	__u8 riccb[64];		/* runtime instrumentation controls block */
 };
diff --git a/arch/s390/include/uapi/asm/sie.h b/arch/s390/include/uapi/asm/sie.h
index ee69c0854c88..5dbaa72baa64 100644
--- a/arch/s390/include/uapi/asm/sie.h
+++ b/arch/s390/include/uapi/asm/sie.h
@@ -7,6 +7,7 @@
 	{ 0x9c, "DIAG (0x9c) time slice end directed" },	\
 	{ 0x204, "DIAG (0x204) logical-cpu utilization" },	\
 	{ 0x258, "DIAG (0x258) page-reference services" },	\
+	{ 0x288, "DIAG (0x288) watchdog functions" },		\
 	{ 0x308, "DIAG (0x308) ipl functions" },		\
 	{ 0x500, "DIAG (0x500) KVM virtio functions" },		\
 	{ 0x501, "DIAG (0x501) KVM breakpoint" }
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 53bbc9e8b281..1f95cc1faeb7 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -12,6 +12,7 @@
 #include <asm/idle.h>
 #include <asm/vdso.h>
 #include <asm/pgtable.h>
+#include <asm/gmap.h>
 
 /*
  * Make sure that the compiler is new enough. We want a compiler that
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 66c94417c0ba..4af60374eba0 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -271,7 +271,7 @@ static int restore_sigregs_ext32(struct pt_regs *regs,
 
 	/* Restore high gprs from signal stack */
 	if (__copy_from_user(&gprs_high, &sregs_ext->gprs_high,
-			     sizeof(&sregs_ext->gprs_high)))
+			     sizeof(sregs_ext->gprs_high)))
 		return -EFAULT;
 	for (i = 0; i < NUM_GPRS; i++)
 		*(__u32 *)&regs->gprs[i] = gprs_high[i];
diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c
index 7f768914fb4f..7f48e568ac64 100644
--- a/arch/s390/kernel/cpcmd.c
+++ b/arch/s390/kernel/cpcmd.c
@@ -96,8 +96,7 @@ int cpcmd(const char *cmd, char *response, int rlen, int *response_code)
 			(((unsigned long)response + rlen) >> 31)) {
 		lowbuf = kmalloc(rlen, GFP_KERNEL | GFP_DMA);
 		if (!lowbuf) {
-			pr_warning("The cpcmd kernel function failed to "
-				   "allocate a response buffer\n");
+			pr_warn("The cpcmd kernel function failed to allocate a response buffer\n");
 			return -ENOMEM;
 		}
 		spin_lock_irqsave(&cpcmd_lock, flags);
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index c890a5589e59..aa12de72fd47 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -699,8 +699,7 @@ debug_info_t *debug_register_mode(const char *name, int pages_per_area,
 	/* Since debugfs currently does not support uid/gid other than root, */
 	/* we do not allow gid/uid != 0 until we get support for that. */
 	if ((uid != 0) || (gid != 0))
-		pr_warning("Root becomes the owner of all s390dbf files "
-			   "in sysfs\n");
+		pr_warn("Root becomes the owner of all s390dbf files in sysfs\n");
 	BUG_ON(!initialized);
 	mutex_lock(&debug_mutex);
 
@@ -1307,8 +1306,7 @@ debug_input_level_fn(debug_info_t * id, struct debug_view *view,
 		new_level = debug_get_uint(str);
 	}
 	if(new_level < 0) {
-		pr_warning("%s is not a valid level for a debug "
-			   "feature\n", str);
+		pr_warn("%s is not a valid level for a debug feature\n", str);
 		rc = -EINVAL;
 	} else {
 		debug_set_level(id, new_level);
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 62973efd214a..8cb9bfdd3ea8 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -1920,23 +1920,16 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr)
 			}
 			if (separator)
 				ptr += sprintf(ptr, "%c", separator);
-			/*
-			 * Use four '%' characters below because of the
-			 * following two conversions:
-			 *
-			 *  1) sprintf: %%%%r -> %%r
-			 *  2) printk : %%r   -> %r
-			 */
 			if (operand->flags & OPERAND_GPR)
-				ptr += sprintf(ptr, "%%%%r%i", value);
+				ptr += sprintf(ptr, "%%r%i", value);
 			else if (operand->flags & OPERAND_FPR)
-				ptr += sprintf(ptr, "%%%%f%i", value);
+				ptr += sprintf(ptr, "%%f%i", value);
 			else if (operand->flags & OPERAND_AR)
-				ptr += sprintf(ptr, "%%%%a%i", value);
+				ptr += sprintf(ptr, "%%a%i", value);
 			else if (operand->flags & OPERAND_CR)
-				ptr += sprintf(ptr, "%%%%c%i", value);
+				ptr += sprintf(ptr, "%%c%i", value);
 			else if (operand->flags & OPERAND_VR)
-				ptr += sprintf(ptr, "%%%%v%i", value);
+				ptr += sprintf(ptr, "%%v%i", value);
 			else if (operand->flags & OPERAND_PCREL)
 				ptr += sprintf(ptr, "%lx", (signed int) value
 								      + addr);
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 02bd02ff648b..1b6081c0aff9 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -11,6 +11,7 @@
 #include <linux/export.h>
 #include <linux/kdebug.h>
 #include <linux/ptrace.h>
+#include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <asm/processor.h>
@@ -19,28 +20,28 @@
 #include <asm/ipl.h>
 
 /*
- * For show_trace we have tree different stack to consider:
+ * For dump_trace we have tree different stack to consider:
  *   - the panic stack which is used if the kernel stack has overflown
  *   - the asynchronous interrupt stack (cpu related)
  *   - the synchronous kernel stack (process related)
- * The stack trace can start at any of the three stack and can potentially
+ * The stack trace can start at any of the three stacks and can potentially
  * touch all of them. The order is: panic stack, async stack, sync stack.
  */
 static unsigned long
-__show_trace(unsigned long sp, unsigned long low, unsigned long high)
+__dump_trace(dump_trace_func_t func, void *data, unsigned long sp,
+	     unsigned long low, unsigned long high)
 {
 	struct stack_frame *sf;
 	struct pt_regs *regs;
-	unsigned long addr;
 
 	while (1) {
 		if (sp < low || sp > high - sizeof(*sf))
 			return sp;
 		sf = (struct stack_frame *) sp;
-		addr = sf->gprs[8];
-		printk("([<%016lx>] %pSR)\n", addr, (void *)addr);
 		/* Follow the backchain. */
 		while (1) {
+			if (func(data, sf->gprs[8]))
+				return sp;
 			low = sp;
 			sp = sf->back_chain;
 			if (!sp)
@@ -48,46 +49,58 @@ __show_trace(unsigned long sp, unsigned long low, unsigned long high)
 			if (sp <= low || sp > high - sizeof(*sf))
 				return sp;
 			sf = (struct stack_frame *) sp;
-			addr = sf->gprs[8];
-			printk(" [<%016lx>] %pSR\n", addr, (void *)addr);
 		}
 		/* Zero backchain detected, check for interrupt frame. */
 		sp = (unsigned long) (sf + 1);
 		if (sp <= low || sp > high - sizeof(*regs))
 			return sp;
 		regs = (struct pt_regs *) sp;
-		addr = regs->psw.addr;
-		printk(" [<%016lx>] %pSR\n", addr, (void *)addr);
+		if (!user_mode(regs)) {
+			if (func(data, regs->psw.addr))
+				return sp;
+		}
 		low = sp;
 		sp = regs->gprs[15];
 	}
 }
 
-static void show_trace(struct task_struct *task, unsigned long *stack)
+void dump_trace(dump_trace_func_t func, void *data, struct task_struct *task,
+		unsigned long sp)
 {
-	const unsigned long frame_size =
-		STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
-	register unsigned long __r15 asm ("15");
-	unsigned long sp;
+	unsigned long frame_size;
 
-	sp = (unsigned long) stack;
-	if (!sp)
-		sp = task ? task->thread.ksp : __r15;
-	printk("Call Trace:\n");
+	frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
 #ifdef CONFIG_CHECK_STACK
-	sp = __show_trace(sp,
+	sp = __dump_trace(func, data, sp,
 			  S390_lowcore.panic_stack + frame_size - 4096,
 			  S390_lowcore.panic_stack + frame_size);
 #endif
-	sp = __show_trace(sp,
+	sp = __dump_trace(func, data, sp,
 			  S390_lowcore.async_stack + frame_size - ASYNC_SIZE,
 			  S390_lowcore.async_stack + frame_size);
 	if (task)
-		__show_trace(sp, (unsigned long) task_stack_page(task),
-			     (unsigned long) task_stack_page(task) + THREAD_SIZE);
+		__dump_trace(func, data, sp,
+			     (unsigned long)task_stack_page(task),
+			     (unsigned long)task_stack_page(task) + THREAD_SIZE);
 	else
-		__show_trace(sp, S390_lowcore.thread_info,
+		__dump_trace(func, data, sp,
+			     S390_lowcore.thread_info,
 			     S390_lowcore.thread_info + THREAD_SIZE);
+}
+EXPORT_SYMBOL_GPL(dump_trace);
+
+static int show_address(void *data, unsigned long address)
+{
+	printk("([<%016lx>] %pSR)\n", address, (void *)address);
+	return 0;
+}
+
+static void show_trace(struct task_struct *task, unsigned long sp)
+{
+	if (!sp)
+		sp = task ? task->thread.ksp : current_stack_pointer();
+	printk("Call Trace:\n");
+	dump_trace(show_address, NULL, task, sp);
 	if (!task)
 		task = current;
 	debug_show_held_locks(task);
@@ -95,15 +108,16 @@ static void show_trace(struct task_struct *task, unsigned long *stack)
 
 void show_stack(struct task_struct *task, unsigned long *sp)
 {
-	register unsigned long *__r15 asm ("15");
 	unsigned long *stack;
 	int i;
 
-	if (!sp)
-		stack = task ? (unsigned long *) task->thread.ksp : __r15;
-	else
-		stack = sp;
-
+	stack = sp;
+	if (!stack) {
+		if (!task)
+			stack = (unsigned long *)current_stack_pointer();
+		else
+			stack = (unsigned long *)task->thread.ksp;
+	}
 	for (i = 0; i < 20; i++) {
 		if (((addr_t) stack & (THREAD_SIZE-1)) == 0)
 			break;
@@ -112,7 +126,7 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 		printk("%016lx ", *stack++);
 	}
 	printk("\n");
-	show_trace(task, sp);
+	show_trace(task, (unsigned long)sp);
 }
 
 static void show_last_breaking_event(struct pt_regs *regs)
@@ -121,13 +135,9 @@ static void show_last_breaking_event(struct pt_regs *regs)
 	printk(" [<%016lx>] %pSR\n", regs->args[0], (void *)regs->args[0]);
 }
 
-static inline int mask_bits(struct pt_regs *regs, unsigned long bits)
-{
-	return (regs->psw.mask & bits) / ((~bits + 1) & bits);
-}
-
 void show_registers(struct pt_regs *regs)
 {
+	struct psw_bits *psw = &psw_bits(regs->psw);
 	char *mode;
 
 	mode = user_mode(regs) ? "User" : "Krnl";
@@ -136,13 +146,9 @@ void show_registers(struct pt_regs *regs)
 		printk(" (%pSR)", (void *)regs->psw.addr);
 	printk("\n");
 	printk("           R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x "
-	       "P:%x AS:%x CC:%x PM:%x", mask_bits(regs, PSW_MASK_PER),
-	       mask_bits(regs, PSW_MASK_DAT), mask_bits(regs, PSW_MASK_IO),
-	       mask_bits(regs, PSW_MASK_EXT), mask_bits(regs, PSW_MASK_KEY),
-	       mask_bits(regs, PSW_MASK_MCHECK), mask_bits(regs, PSW_MASK_WAIT),
-	       mask_bits(regs, PSW_MASK_PSTATE), mask_bits(regs, PSW_MASK_ASC),
-	       mask_bits(regs, PSW_MASK_CC), mask_bits(regs, PSW_MASK_PM));
-	printk(" EA:%x", mask_bits(regs, PSW_MASK_EA | PSW_MASK_BA));
+	       "P:%x AS:%x CC:%x PM:%x", psw->r, psw->t, psw->i, psw->e,
+	       psw->key, psw->m, psw->w, psw->p, psw->as, psw->cc, psw->pm);
+	printk(" RI:%x EA:%x", psw->ri, psw->eaba);
 	printk("\n%s GPRS: %016lx %016lx %016lx %016lx\n", mode,
 	       regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]);
 	printk("           %016lx %016lx %016lx %016lx\n",
@@ -160,7 +166,7 @@ void show_regs(struct pt_regs *regs)
 	show_registers(regs);
 	/* Show stack backtrace if pt_regs is from kernel mode */
 	if (!user_mode(regs))
-		show_trace(NULL, (unsigned long *) regs->gprs[15]);
+		show_trace(NULL, regs->gprs[15]);
 	show_last_breaking_event(regs);
 }
 
@@ -184,9 +190,8 @@ void die(struct pt_regs *regs, const char *str)
 #ifdef CONFIG_SMP
 	printk("SMP ");
 #endif
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	printk("DEBUG_PAGEALLOC");
-#endif
+	if (debug_pagealloc_enabled())
+		printk("DEBUG_PAGEALLOC");
 	printk("\n");
 	notify_die(DIE_OOPS, str, regs, 0, regs->int_code & 0xffff, SIGSEGV);
 	print_modules();
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index c55576bbaa1f..a0684de5a93b 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -448,7 +448,6 @@ void __init startup_init(void)
 	rescue_initrd();
 	clear_bss_section();
 	init_kernel_storage_key();
-	lockdep_init();
 	lockdep_off();
 	setup_lowcore_early();
 	setup_facility_list();
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index cd5a191381b9..2d47f9cfcb36 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -186,6 +186,7 @@ ENTRY(__switch_to)
 	stg	%r5,__LC_THREAD_INFO		# store thread info of next
 	stg	%r15,__LC_KERNEL_STACK		# store end of kernel stack
 	lg	%r15,__THREAD_ksp(%r1)		# load kernel stack of next
+	/* c4 is used in guest detection: arch/s390/kernel/perf_cpum_sf.c */
 	lctl	%c4,%c4,__TASK_pid(%r3)		# load pid to control reg. 4
 	mvc	__LC_CURRENT_PID(4,%r0),__TASK_pid(%r3) # store pid of next
 	lmg	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
@@ -1199,114 +1200,12 @@ cleanup_critical:
 	.quad	.Lpsw_idle_lpsw
 
 .Lcleanup_save_fpu_regs:
-	TSTMSK	__LC_CPU_FLAGS,_CIF_FPU
-	bor	%r14
-	clg	%r9,BASED(.Lcleanup_save_fpu_regs_done)
-	jhe	5f
-	clg	%r9,BASED(.Lcleanup_save_fpu_regs_fp)
-	jhe	4f
-	clg	%r9,BASED(.Lcleanup_save_fpu_regs_vx_high)
-	jhe	3f
-	clg	%r9,BASED(.Lcleanup_save_fpu_regs_vx_low)
-	jhe	2f
-	clg	%r9,BASED(.Lcleanup_save_fpu_fpc_end)
-	jhe	1f
-	lg	%r2,__LC_CURRENT
-	aghi	%r2,__TASK_thread
-0:	# Store floating-point controls
-	stfpc	__THREAD_FPU_fpc(%r2)
-1:	# Load register save area and check if VX is active
-	lg	%r3,__THREAD_FPU_regs(%r2)
-	TSTMSK	__LC_MACHINE_FLAGS,MACHINE_FLAG_VX
-	jz	4f			  # no VX -> store FP regs
-2:	# Store vector registers (V0-V15)
-	VSTM	%v0,%v15,0,%r3		  # vstm 0,15,0(3)
-3:	# Store vector registers (V16-V31)
-	VSTM	%v16,%v31,256,%r3	  # vstm 16,31,256(3)
-	j	5f			  # -> done, set CIF_FPU flag
-4:	# Store floating-point registers
-	std	0,0(%r3)
-	std	1,8(%r3)
-	std	2,16(%r3)
-	std	3,24(%r3)
-	std	4,32(%r3)
-	std	5,40(%r3)
-	std	6,48(%r3)
-	std	7,56(%r3)
-	std	8,64(%r3)
-	std	9,72(%r3)
-	std	10,80(%r3)
-	std	11,88(%r3)
-	std	12,96(%r3)
-	std	13,104(%r3)
-	std	14,112(%r3)
-	std	15,120(%r3)
-5:	# Set CIF_FPU flag
-	oi	__LC_CPU_FLAGS+7,_CIF_FPU
-	lg	%r9,48(%r11)		# return from save_fpu_regs
+	larl	%r9,save_fpu_regs
 	br	%r14
-.Lcleanup_save_fpu_fpc_end:
-	.quad	.Lsave_fpu_regs_fpc_end
-.Lcleanup_save_fpu_regs_vx_low:
-	.quad	.Lsave_fpu_regs_vx_low
-.Lcleanup_save_fpu_regs_vx_high:
-	.quad	.Lsave_fpu_regs_vx_high
-.Lcleanup_save_fpu_regs_fp:
-	.quad	.Lsave_fpu_regs_fp
-.Lcleanup_save_fpu_regs_done:
-	.quad	.Lsave_fpu_regs_done
 
 .Lcleanup_load_fpu_regs:
-	TSTMSK	__LC_CPU_FLAGS,_CIF_FPU
-	bnor	%r14
-	clg	%r9,BASED(.Lcleanup_load_fpu_regs_done)
-	jhe	1f
-	clg	%r9,BASED(.Lcleanup_load_fpu_regs_fp)
-	jhe	2f
-	clg	%r9,BASED(.Lcleanup_load_fpu_regs_vx_high)
-	jhe	3f
-	clg	%r9,BASED(.Lcleanup_load_fpu_regs_vx)
-	jhe	4f
-	lg	%r4,__LC_CURRENT
-	aghi	%r4,__TASK_thread
-	lfpc	__THREAD_FPU_fpc(%r4)
-	TSTMSK	__LC_MACHINE_FLAGS,MACHINE_FLAG_VX
-	lg	%r4,__THREAD_FPU_regs(%r4)	# %r4 <- reg save area
-	jz	2f				# -> no VX, load FP regs
-4:	# Load V0 ..V15 registers
-	VLM	%v0,%v15,0,%r4
-3:	# Load V16..V31 registers
-	VLM	%v16,%v31,256,%r4
-	j	1f
-2:	# Load floating-point registers
-	ld	0,0(%r4)
-	ld	1,8(%r4)
-	ld	2,16(%r4)
-	ld	3,24(%r4)
-	ld	4,32(%r4)
-	ld	5,40(%r4)
-	ld	6,48(%r4)
-	ld	7,56(%r4)
-	ld	8,64(%r4)
-	ld	9,72(%r4)
-	ld	10,80(%r4)
-	ld	11,88(%r4)
-	ld	12,96(%r4)
-	ld	13,104(%r4)
-	ld	14,112(%r4)
-	ld	15,120(%r4)
-1:	# Clear CIF_FPU bit
-	ni	__LC_CPU_FLAGS+7,255-_CIF_FPU
-	lg	%r9,48(%r11)		# return from load_fpu_regs
+	larl	%r9,load_fpu_regs
 	br	%r14
-.Lcleanup_load_fpu_regs_vx:
-	.quad	.Lload_fpu_regs_vx
-.Lcleanup_load_fpu_regs_vx_high:
-	.quad	.Lload_fpu_regs_vx_high
-.Lcleanup_load_fpu_regs_fp:
-	.quad	.Lload_fpu_regs_fp
-.Lcleanup_load_fpu_regs_done:
-	.quad	.Lload_fpu_regs_done
 
 /*
  * Integer constants
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index c5febe84eba6..03c2b469c472 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -16,7 +16,7 @@
 
 __HEAD
 ENTRY(startup_continue)
-	tm	__LC_STFLE_FAC_LIST+6,0x80	# LPP available ?
+	tm	__LC_STFLE_FAC_LIST+5,0x80	# LPP available ?
 	jz	0f
 	xc	__LC_LPP+1(7,0),__LC_LPP+1	# clear lpp and current_pid
 	mvi	__LC_LPP,0x80			#   and set LPP_MAGIC
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index f41d5208aaf7..c373a1d41d10 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -164,8 +164,7 @@ void do_softirq_own_stack(void)
 {
 	unsigned long old, new;
 
-	/* Get current stack pointer. */
-	asm volatile("la %0,0(15)" : "=a" (old));
+	old = current_stack_pointer();
 	/* Check against async. stack address range. */
 	new = S390_lowcore.async_stack;
 	if (((new - old) >> (PAGE_SHIFT + THREAD_ORDER)) != 0) {
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 929c147e07b4..58bf4572d457 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -383,7 +383,7 @@ static int __hw_perf_event_init(struct perf_event *event)
 
 	/* Validate the counter that is assigned to this event.
 	 * Because the counter facility can use numerous counters at the
-	 * same time without constraints, it is not necessary to explicity
+	 * same time without constraints, it is not necessary to explicitly
 	 * validate event groups (event->group_leader != event).
 	 */
 	err = validate_event(hwc);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 3d8da1e742c2..1a43474df541 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1022,10 +1022,13 @@ static int perf_push_sample(struct perf_event *event, struct sf_raw_sample *sfr)
 	/*
 	 * A non-zero guest program parameter indicates a guest
 	 * sample.
-	 * Note that some early samples might be misaccounted to
-	 * the host.
+	 * Note that some early samples or samples from guests without
+	 * lpp usage would be misaccounted to the host. We use the asn
+	 * value as a heuristic to detect most of these guest samples.
+	 * If the value differs from the host hpp value, we assume
+	 * it to be a KVM guest.
 	 */
-	if (sfr->basic.gpp)
+	if (sfr->basic.gpp || sfr->basic.prim_asn != (u16) sfr->basic.hpp)
 		sde_regs->in_guest = 1;
 
 	overflow = 0;
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index cfcba2dd9bb5..c3e4099b60a5 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -222,65 +222,23 @@ static int __init service_level_perf_register(void)
 }
 arch_initcall(service_level_perf_register);
 
-/* See also arch/s390/kernel/traps.c */
-static unsigned long __store_trace(struct perf_callchain_entry *entry,
-				   unsigned long sp,
-				   unsigned long low, unsigned long high)
+static int __perf_callchain_kernel(void *data, unsigned long address)
 {
-	struct stack_frame *sf;
-	struct pt_regs *regs;
-
-	while (1) {
-		if (sp < low || sp > high - sizeof(*sf))
-			return sp;
-		sf = (struct stack_frame *) sp;
-		perf_callchain_store(entry, sf->gprs[8]);
-		/* Follow the backchain. */
-		while (1) {
-			low = sp;
-			sp = sf->back_chain;
-			if (!sp)
-				break;
-			if (sp <= low || sp > high - sizeof(*sf))
-				return sp;
-			sf = (struct stack_frame *) sp;
-			perf_callchain_store(entry, sf->gprs[8]);
-		}
-		/* Zero backchain detected, check for interrupt frame. */
-		sp = (unsigned long) (sf + 1);
-		if (sp <= low || sp > high - sizeof(*regs))
-			return sp;
-		regs = (struct pt_regs *) sp;
-		perf_callchain_store(entry, sf->gprs[8]);
-		low = sp;
-		sp = regs->gprs[15];
-	}
+	struct perf_callchain_entry *entry = data;
+
+	perf_callchain_store(entry, address);
+	return 0;
 }
 
 void perf_callchain_kernel(struct perf_callchain_entry *entry,
 			   struct pt_regs *regs)
 {
-	unsigned long head;
-	struct stack_frame *head_sf;
-
 	if (user_mode(regs))
 		return;
-
-	head = regs->gprs[15];
-	head_sf = (struct stack_frame *) head;
-
-	if (!head_sf || !head_sf->back_chain)
-		return;
-
-	head = head_sf->back_chain;
-	head = __store_trace(entry, head, S390_lowcore.async_stack - ASYNC_SIZE,
-			     S390_lowcore.async_stack);
-
-	__store_trace(entry, head, S390_lowcore.thread_info,
-		      S390_lowcore.thread_info + THREAD_SIZE);
+	dump_trace(__perf_callchain_kernel, entry, NULL, regs->gprs[15]);
 }
 
-/* Perf defintions for PMU event attributes in sysfs */
+/* Perf definitions for PMU event attributes in sysfs */
 ssize_t cpumf_events_sysfs_show(struct device *dev,
 				struct device_attribute *attr, char *page)
 {
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 9220db5c996a..d3f9688f26b5 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -327,6 +327,7 @@ static void __init setup_lowcore(void)
 		+ PAGE_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
 	lc->current_task = (unsigned long) init_thread_union.thread_info.task;
 	lc->thread_info = (unsigned long) &init_thread_union;
+	lc->lpp = LPP_MAGIC;
 	lc->machine_flags = S390_lowcore.machine_flags;
 	lc->stfl_fac_list = S390_lowcore.stfl_fac_list;
 	memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
@@ -374,17 +375,17 @@ static void __init setup_lowcore(void)
 
 static struct resource code_resource = {
 	.name  = "Kernel code",
-	.flags = IORESOURCE_BUSY | IORESOURCE_MEM,
+	.flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
 };
 
 static struct resource data_resource = {
 	.name = "Kernel data",
-	.flags = IORESOURCE_BUSY | IORESOURCE_MEM,
+	.flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
 };
 
 static struct resource bss_resource = {
 	.name = "Kernel bss",
-	.flags = IORESOURCE_BUSY | IORESOURCE_MEM,
+	.flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
 };
 
 static struct resource __initdata *standard_resources[] = {
@@ -408,7 +409,7 @@ static void __init setup_resources(void)
 
 	for_each_memblock(memory, reg) {
 		res = alloc_bootmem_low(sizeof(*res));
-		res->flags = IORESOURCE_BUSY | IORESOURCE_MEM;
+		res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM;
 
 		res->name = "System RAM";
 		res->start = reg->base;
@@ -779,6 +780,7 @@ static int __init setup_hwcaps(void)
 		strcpy(elf_platform, "zEC12");
 		break;
 	case 0x2964:
+	case 0x2965:
 		strcpy(elf_platform, "z13");
 		break;
 	}
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 3c65a8eae34d..40a6b4f9c36c 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -798,7 +798,7 @@ static void smp_start_secondary(void *cpuvoid)
 	set_cpu_online(smp_processor_id(), true);
 	inc_irq_stat(CPU_RST);
 	local_irq_enable();
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
 /* Upping and downing of CPUs */
diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
index 5acba3cb7220..44f84b23d4e5 100644
--- a/arch/s390/kernel/stacktrace.c
+++ b/arch/s390/kernel/stacktrace.c
@@ -10,86 +10,64 @@
 #include <linux/kallsyms.h>
 #include <linux/module.h>
 
-static unsigned long save_context_stack(struct stack_trace *trace,
-					unsigned long sp,
-					unsigned long low,
-					unsigned long high,
-					int savesched)
+static int __save_address(void *data, unsigned long address, int nosched)
 {
-	struct stack_frame *sf;
-	struct pt_regs *regs;
-	unsigned long addr;
+	struct stack_trace *trace = data;
 
-	while(1) {
-		if (sp < low || sp > high)
-			return sp;
-		sf = (struct stack_frame *)sp;
-		while(1) {
-			addr = sf->gprs[8];
-			if (!trace->skip)
-				trace->entries[trace->nr_entries++] = addr;
-			else
-				trace->skip--;
-			if (trace->nr_entries >= trace->max_entries)
-				return sp;
-			low = sp;
-			sp = sf->back_chain;
-			if (!sp)
-				break;
-			if (sp <= low || sp > high - sizeof(*sf))
-				return sp;
-			sf = (struct stack_frame *)sp;
-		}
-		/* Zero backchain detected, check for interrupt frame. */
-		sp = (unsigned long)(sf + 1);
-		if (sp <= low || sp > high - sizeof(*regs))
-			return sp;
-		regs = (struct pt_regs *)sp;
-		addr = regs->psw.addr;
-		if (savesched || !in_sched_functions(addr)) {
-			if (!trace->skip)
-				trace->entries[trace->nr_entries++] = addr;
-			else
-				trace->skip--;
-		}
-		if (trace->nr_entries >= trace->max_entries)
-			return sp;
-		low = sp;
-		sp = regs->gprs[15];
+	if (nosched && in_sched_functions(address))
+		return 0;
+	if (trace->skip > 0) {
+		trace->skip--;
+		return 0;
 	}
+	if (trace->nr_entries < trace->max_entries) {
+		trace->entries[trace->nr_entries++] = address;
+		return 0;
+	}
+	return 1;
+}
+
+static int save_address(void *data, unsigned long address)
+{
+	return __save_address(data, address, 0);
+}
+
+static int save_address_nosched(void *data, unsigned long address)
+{
+	return __save_address(data, address, 1);
 }
 
 void save_stack_trace(struct stack_trace *trace)
 {
-	register unsigned long sp asm ("15");
-	unsigned long orig_sp, new_sp;
+	unsigned long sp;
 
-	orig_sp = sp;
-	new_sp = save_context_stack(trace, orig_sp,
-				    S390_lowcore.panic_stack - PAGE_SIZE,
-				    S390_lowcore.panic_stack, 1);
-	if (new_sp != orig_sp)
-		return;
-	new_sp = save_context_stack(trace, new_sp,
-				    S390_lowcore.async_stack - ASYNC_SIZE,
-				    S390_lowcore.async_stack, 1);
-	if (new_sp != orig_sp)
-		return;
-	save_context_stack(trace, new_sp,
-			   S390_lowcore.thread_info,
-			   S390_lowcore.thread_info + THREAD_SIZE, 1);
+	sp = current_stack_pointer();
+	dump_trace(save_address, trace, NULL, sp);
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace);
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
-	unsigned long sp, low, high;
+	unsigned long sp;
 
 	sp = tsk->thread.ksp;
-	low = (unsigned long) task_stack_page(tsk);
-	high = (unsigned long) task_pt_regs(tsk);
-	save_context_stack(trace, sp, low, high, 0);
+	if (tsk == current)
+		sp = current_stack_pointer();
+	dump_trace(save_address_nosched, trace, tsk, sp);
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
+
+void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
+{
+	unsigned long sp;
+
+	sp = kernel_stack_pointer(regs);
+	dump_trace(save_address, trace, NULL, sp);
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+EXPORT_SYMBOL_GPL(save_stack_trace_regs);
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 99f84ac31307..c4e5f183f225 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -499,8 +499,7 @@ static void etr_reset(void)
 		if (etr_port0_online && etr_port1_online)
 			set_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
 	} else if (etr_port0_online || etr_port1_online) {
-		pr_warning("The real or virtual hardware system does "
-			   "not provide an ETR interface\n");
+		pr_warn("The real or virtual hardware system does not provide an ETR interface\n");
 		etr_port0_online = etr_port1_online = 0;
 	}
 }
@@ -1464,8 +1463,7 @@ static void __init stp_reset(void)
 	if (rc == 0)
 		set_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags);
 	else if (stp_online) {
-		pr_warning("The real or virtual hardware system does "
-			   "not provide an STP interface\n");
+		pr_warn("The real or virtual hardware system does not provide an STP interface\n");
 		free_page((unsigned long) stp_page);
 		stp_page = NULL;
 		stp_online = 0;
diff --git a/arch/s390/kernel/trace.c b/arch/s390/kernel/trace.c
index 21a5df99552b..dde7654f5c68 100644
--- a/arch/s390/kernel/trace.c
+++ b/arch/s390/kernel/trace.c
@@ -18,6 +18,9 @@ void trace_s390_diagnose_norecursion(int diag_nr)
 	unsigned long flags;
 	unsigned int *depth;
 
+	/* Avoid lockdep recursion. */
+	if (IS_ENABLED(CONFIG_LOCKDEP))
+		return;
 	local_irq_save(flags);
 	depth = this_cpu_ptr(&diagnose_trace_depth);
 	if (*depth == 0) {
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 017eb03daee2..dd97a3e8a34a 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -22,8 +22,6 @@
 #include <asm/fpu/api.h>
 #include "entry.h"
 
-int show_unhandled_signals = 1;
-
 static inline void __user *get_trap_ip(struct pt_regs *regs)
 {
 	unsigned long address;
@@ -35,21 +33,6 @@ static inline void __user *get_trap_ip(struct pt_regs *regs)
 	return (void __user *) (address - (regs->int_code >> 16));
 }
 
-static inline void report_user_fault(struct pt_regs *regs, int signr)
-{
-	if ((task_pid_nr(current) > 1) && !show_unhandled_signals)
-		return;
-	if (!unhandled_signal(current, signr))
-		return;
-	if (!printk_ratelimit())
-		return;
-	printk("User process fault: interruption code %04x ilc:%d ",
-	       regs->int_code & 0xffff, regs->int_code >> 17);
-	print_vma_addr("in ", regs->psw.addr);
-	printk("\n");
-	show_regs(regs);
-}
-
 int is_valid_bugaddr(unsigned long addr)
 {
 	return 1;
@@ -65,7 +48,7 @@ void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
 		info.si_code = si_code;
 		info.si_addr = get_trap_ip(regs);
 		force_sig_info(si_signo, &info, current);
-		report_user_fault(regs, si_signo);
+		report_user_fault(regs, si_signo, 0);
         } else {
                 const struct exception_table_entry *fixup;
 		fixup = search_exception_tables(regs->psw.addr);
@@ -111,7 +94,7 @@ NOKPROBE_SYMBOL(do_per_trap);
 void default_trap_handler(struct pt_regs *regs)
 {
 	if (user_mode(regs)) {
-		report_user_fault(regs, SIGSEGV);
+		report_user_fault(regs, SIGSEGV, 0);
 		do_exit(SIGSEGV);
 	} else
 		die(regs, "Unknown program exception");
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 05f7de9869a9..1ea4095b67d7 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -14,6 +14,7 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 #include <asm/pgalloc.h>
+#include <asm/gmap.h>
 #include <asm/virtio-ccw.h>
 #include "kvm-s390.h"
 #include "trace.h"
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index d30db40437dc..66938d283b77 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -373,7 +373,7 @@ void ipte_unlock(struct kvm_vcpu *vcpu)
 }
 
 static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar,
-			  int write)
+			  enum gacc_mode mode)
 {
 	union alet alet;
 	struct ale ale;
@@ -454,7 +454,7 @@ static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar,
 		}
 	}
 
-	if (ale.fo == 1 && write)
+	if (ale.fo == 1 && mode == GACC_STORE)
 		return PGM_PROTECTION;
 
 	asce->val = aste.asce;
@@ -477,25 +477,28 @@ enum {
 };
 
 static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce,
-			 ar_t ar, int write)
+			 ar_t ar, enum gacc_mode mode)
 {
 	int rc;
-	psw_t *psw = &vcpu->arch.sie_block->gpsw;
+	struct psw_bits psw = psw_bits(vcpu->arch.sie_block->gpsw);
 	struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
 	struct trans_exc_code_bits *tec_bits;
 
 	memset(pgm, 0, sizeof(*pgm));
 	tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code;
-	tec_bits->fsi = write ? FSI_STORE : FSI_FETCH;
-	tec_bits->as = psw_bits(*psw).as;
+	tec_bits->fsi = mode == GACC_STORE ? FSI_STORE : FSI_FETCH;
+	tec_bits->as = psw.as;
 
-	if (!psw_bits(*psw).t) {
+	if (!psw.t) {
 		asce->val = 0;
 		asce->r = 1;
 		return 0;
 	}
 
-	switch (psw_bits(vcpu->arch.sie_block->gpsw).as) {
+	if (mode == GACC_IFETCH)
+		psw.as = psw.as == PSW_AS_HOME ? PSW_AS_HOME : PSW_AS_PRIMARY;
+
+	switch (psw.as) {
 	case PSW_AS_PRIMARY:
 		asce->val = vcpu->arch.sie_block->gcr[1];
 		return 0;
@@ -506,7 +509,7 @@ static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce,
 		asce->val = vcpu->arch.sie_block->gcr[13];
 		return 0;
 	case PSW_AS_ACCREG:
-		rc = ar_translation(vcpu, asce, ar, write);
+		rc = ar_translation(vcpu, asce, ar, mode);
 		switch (rc) {
 		case PGM_ALEN_TRANSLATION:
 		case PGM_ALE_SEQUENCE:
@@ -538,7 +541,7 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val)
  * @gva: guest virtual address
  * @gpa: points to where guest physical (absolute) address should be stored
  * @asce: effective asce
- * @write: indicates if access is a write access
+ * @mode: indicates the access mode to be used
  *
  * Translate a guest virtual address into a guest absolute address by means
  * of dynamic address translation as specified by the architecture.
@@ -554,7 +557,7 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val)
  */
 static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva,
 				     unsigned long *gpa, const union asce asce,
-				     int write)
+				     enum gacc_mode mode)
 {
 	union vaddress vaddr = {.addr = gva};
 	union raddress raddr = {.addr = gva};
@@ -699,7 +702,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva,
 real_address:
 	raddr.addr = kvm_s390_real_to_abs(vcpu, raddr.addr);
 absolute_address:
-	if (write && dat_protection)
+	if (mode == GACC_STORE && dat_protection)
 		return PGM_PROTECTION;
 	if (kvm_is_error_gpa(vcpu->kvm, raddr.addr))
 		return PGM_ADDRESSING;
@@ -728,7 +731,7 @@ static int low_address_protection_enabled(struct kvm_vcpu *vcpu,
 
 static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga,
 			    unsigned long *pages, unsigned long nr_pages,
-			    const union asce asce, int write)
+			    const union asce asce, enum gacc_mode mode)
 {
 	struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
 	psw_t *psw = &vcpu->arch.sie_block->gpsw;
@@ -740,13 +743,13 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga,
 	while (nr_pages) {
 		ga = kvm_s390_logical_to_effective(vcpu, ga);
 		tec_bits->addr = ga >> PAGE_SHIFT;
-		if (write && lap_enabled && is_low_address(ga)) {
+		if (mode == GACC_STORE && lap_enabled && is_low_address(ga)) {
 			pgm->code = PGM_PROTECTION;
 			return pgm->code;
 		}
 		ga &= PAGE_MASK;
 		if (psw_bits(*psw).t) {
-			rc = guest_translate(vcpu, ga, pages, asce, write);
+			rc = guest_translate(vcpu, ga, pages, asce, mode);
 			if (rc < 0)
 				return rc;
 			if (rc == PGM_PROTECTION)
@@ -768,7 +771,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga,
 }
 
 int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
-		 unsigned long len, int write)
+		 unsigned long len, enum gacc_mode mode)
 {
 	psw_t *psw = &vcpu->arch.sie_block->gpsw;
 	unsigned long _len, nr_pages, gpa, idx;
@@ -780,7 +783,7 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
 
 	if (!len)
 		return 0;
-	rc = get_vcpu_asce(vcpu, &asce, ar, write);
+	rc = get_vcpu_asce(vcpu, &asce, ar, mode);
 	if (rc)
 		return rc;
 	nr_pages = (((ga & ~PAGE_MASK) + len - 1) >> PAGE_SHIFT) + 1;
@@ -792,11 +795,11 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
 	need_ipte_lock = psw_bits(*psw).t && !asce.r;
 	if (need_ipte_lock)
 		ipte_lock(vcpu);
-	rc = guest_page_range(vcpu, ga, pages, nr_pages, asce, write);
+	rc = guest_page_range(vcpu, ga, pages, nr_pages, asce, mode);
 	for (idx = 0; idx < nr_pages && !rc; idx++) {
 		gpa = *(pages + idx) + (ga & ~PAGE_MASK);
 		_len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len);
-		if (write)
+		if (mode == GACC_STORE)
 			rc = kvm_write_guest(vcpu->kvm, gpa, data, _len);
 		else
 			rc = kvm_read_guest(vcpu->kvm, gpa, data, _len);
@@ -812,7 +815,7 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
 }
 
 int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
-		      void *data, unsigned long len, int write)
+		      void *data, unsigned long len, enum gacc_mode mode)
 {
 	unsigned long _len, gpa;
 	int rc = 0;
@@ -820,7 +823,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
 	while (len && !rc) {
 		gpa = kvm_s390_real_to_abs(vcpu, gra);
 		_len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len);
-		if (write)
+		if (mode)
 			rc = write_guest_abs(vcpu, gpa, data, _len);
 		else
 			rc = read_guest_abs(vcpu, gpa, data, _len);
@@ -841,7 +844,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
  * has to take care of this.
  */
 int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
-			    unsigned long *gpa, int write)
+			    unsigned long *gpa, enum gacc_mode mode)
 {
 	struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm;
 	psw_t *psw = &vcpu->arch.sie_block->gpsw;
@@ -851,19 +854,19 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
 
 	gva = kvm_s390_logical_to_effective(vcpu, gva);
 	tec = (struct trans_exc_code_bits *)&pgm->trans_exc_code;
-	rc = get_vcpu_asce(vcpu, &asce, ar, write);
+	rc = get_vcpu_asce(vcpu, &asce, ar, mode);
 	tec->addr = gva >> PAGE_SHIFT;
 	if (rc)
 		return rc;
 	if (is_low_address(gva) && low_address_protection_enabled(vcpu, asce)) {
-		if (write) {
+		if (mode == GACC_STORE) {
 			rc = pgm->code = PGM_PROTECTION;
 			return rc;
 		}
 	}
 
 	if (psw_bits(*psw).t && !asce.r) {	/* Use DAT? */
-		rc = guest_translate(vcpu, gva, gpa, asce, write);
+		rc = guest_translate(vcpu, gva, gpa, asce, mode);
 		if (rc > 0) {
 			if (rc == PGM_PROTECTION)
 				tec->b61 = 1;
@@ -883,7 +886,7 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
  * check_gva_range - test a range of guest virtual addresses for accessibility
  */
 int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
-		    unsigned long length, int is_write)
+		    unsigned long length, enum gacc_mode mode)
 {
 	unsigned long gpa;
 	unsigned long currlen;
@@ -892,7 +895,7 @@ int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
 	ipte_lock(vcpu);
 	while (length > 0 && !rc) {
 		currlen = min(length, PAGE_SIZE - (gva % PAGE_SIZE));
-		rc = guest_translate_address(vcpu, gva, ar, &gpa, is_write);
+		rc = guest_translate_address(vcpu, gva, ar, &gpa, mode);
 		gva += currlen;
 		length -= currlen;
 	}
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index ef03726cc661..df0a79dd8159 100644
--- a/arch/s390/kvm/gaccess.h
+++ b/arch/s390/kvm/gaccess.h
@@ -155,16 +155,22 @@ int read_guest_lc(struct kvm_vcpu *vcpu, unsigned long gra, void *data,
 	return kvm_read_guest(vcpu->kvm, gpa, data, len);
 }
 
+enum gacc_mode {
+	GACC_FETCH,
+	GACC_STORE,
+	GACC_IFETCH,
+};
+
 int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva,
-			    ar_t ar, unsigned long *gpa, int write);
+			    ar_t ar, unsigned long *gpa, enum gacc_mode mode);
 int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar,
-		    unsigned long length, int is_write);
+		    unsigned long length, enum gacc_mode mode);
 
 int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
-		 unsigned long len, int write);
+		 unsigned long len, enum gacc_mode mode);
 
 int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
-		      void *data, unsigned long len, int write);
+		      void *data, unsigned long len, enum gacc_mode mode);
 
 /**
  * write_guest - copy data from kernel space to guest space
@@ -215,7 +221,7 @@ static inline __must_check
 int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
 		unsigned long len)
 {
-	return access_guest(vcpu, ga, ar, data, len, 1);
+	return access_guest(vcpu, ga, ar, data, len, GACC_STORE);
 }
 
 /**
@@ -235,7 +241,27 @@ static inline __must_check
 int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data,
 	       unsigned long len)
 {
-	return access_guest(vcpu, ga, ar, data, len, 0);
+	return access_guest(vcpu, ga, ar, data, len, GACC_FETCH);
+}
+
+/**
+ * read_guest_instr - copy instruction data from guest space to kernel space
+ * @vcpu: virtual cpu
+ * @data: destination address in kernel space
+ * @len: number of bytes to copy
+ *
+ * Copy @len bytes from the current psw address (guest space) to @data (kernel
+ * space).
+ *
+ * The behaviour of read_guest_instr is identical to read_guest, except that
+ * instruction data will be read from primary space when in home-space or
+ * address-space mode.
+ */
+static inline __must_check
+int read_guest_instr(struct kvm_vcpu *vcpu, void *data, unsigned long len)
+{
+	return access_guest(vcpu, vcpu->arch.sie_block->gpsw.addr, 0, data, len,
+			    GACC_IFETCH);
 }
 
 /**
diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c
index d697312ce9ee..e8c6843b9600 100644
--- a/arch/s390/kvm/guestdbg.c
+++ b/arch/s390/kvm/guestdbg.c
@@ -17,7 +17,7 @@
 /*
  * Extends the address range given by *start and *stop to include the address
  * range starting with estart and the length len. Takes care of overflowing
- * intervals and tries to minimize the overall intervall size.
+ * intervals and tries to minimize the overall interval size.
  */
 static void extend_address_range(u64 *start, u64 *stop, u64 estart, int len)
 {
@@ -72,7 +72,7 @@ static void enable_all_hw_bp(struct kvm_vcpu *vcpu)
 		return;
 
 	/*
-	 * If the guest is not interrested in branching events, we can savely
+	 * If the guest is not interested in branching events, we can safely
 	 * limit them to the PER address range.
 	 */
 	if (!(*cr9 & PER_EVENT_BRANCH))
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index d53c10753c46..2e6b54e4d3f9 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -38,17 +38,32 @@ static const intercept_handler_t instruction_handlers[256] = {
 	[0xeb] = kvm_s390_handle_eb,
 };
 
-void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc)
+u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block;
+	u8 ilen = 0;
 
-	/* Use the length of the EXECUTE instruction if necessary */
-	if (sie_block->icptstatus & 1) {
-		ilc = (sie_block->icptstatus >> 4) & 0x6;
-		if (!ilc)
-			ilc = 4;
+	switch (vcpu->arch.sie_block->icptcode) {
+	case ICPT_INST:
+	case ICPT_INSTPROGI:
+	case ICPT_OPEREXC:
+	case ICPT_PARTEXEC:
+	case ICPT_IOINST:
+		/* instruction only stored for these icptcodes */
+		ilen = insn_length(vcpu->arch.sie_block->ipa >> 8);
+		/* Use the length of the EXECUTE instruction if necessary */
+		if (sie_block->icptstatus & 1) {
+			ilen = (sie_block->icptstatus >> 4) & 0x6;
+			if (!ilen)
+				ilen = 4;
+		}
+		break;
+	case ICPT_PROGI:
+		/* bit 1+2 of pgmilc are the ilc, so we directly get ilen */
+		ilen = vcpu->arch.sie_block->pgmilc & 0x6;
+		break;
 	}
-	sie_block->gpsw.addr = __rewind_psw(sie_block->gpsw, ilc);
+	return ilen;
 }
 
 static int handle_noop(struct kvm_vcpu *vcpu)
@@ -121,11 +136,13 @@ static int handle_instruction(struct kvm_vcpu *vcpu)
 	return -EOPNOTSUPP;
 }
 
-static void __extract_prog_irq(struct kvm_vcpu *vcpu,
-			       struct kvm_s390_pgm_info *pgm_info)
+static int inject_prog_on_prog_intercept(struct kvm_vcpu *vcpu)
 {
-	memset(pgm_info, 0, sizeof(struct kvm_s390_pgm_info));
-	pgm_info->code = vcpu->arch.sie_block->iprcc;
+	struct kvm_s390_pgm_info pgm_info = {
+		.code = vcpu->arch.sie_block->iprcc,
+		/* the PSW has already been rewound */
+		.flags = KVM_S390_PGM_FLAGS_NO_REWIND,
+	};
 
 	switch (vcpu->arch.sie_block->iprcc & ~PGM_PER) {
 	case PGM_AFX_TRANSLATION:
@@ -138,7 +155,7 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu,
 	case PGM_PRIMARY_AUTHORITY:
 	case PGM_SECONDARY_AUTHORITY:
 	case PGM_SPACE_SWITCH:
-		pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc;
+		pgm_info.trans_exc_code = vcpu->arch.sie_block->tecmc;
 		break;
 	case PGM_ALEN_TRANSLATION:
 	case PGM_ALE_SEQUENCE:
@@ -146,7 +163,7 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu,
 	case PGM_ASTE_SEQUENCE:
 	case PGM_ASTE_VALIDITY:
 	case PGM_EXTENDED_AUTHORITY:
-		pgm_info->exc_access_id = vcpu->arch.sie_block->eai;
+		pgm_info.exc_access_id = vcpu->arch.sie_block->eai;
 		break;
 	case PGM_ASCE_TYPE:
 	case PGM_PAGE_TRANSLATION:
@@ -154,32 +171,33 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu,
 	case PGM_REGION_SECOND_TRANS:
 	case PGM_REGION_THIRD_TRANS:
 	case PGM_SEGMENT_TRANSLATION:
-		pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc;
-		pgm_info->exc_access_id  = vcpu->arch.sie_block->eai;
-		pgm_info->op_access_id  = vcpu->arch.sie_block->oai;
+		pgm_info.trans_exc_code = vcpu->arch.sie_block->tecmc;
+		pgm_info.exc_access_id  = vcpu->arch.sie_block->eai;
+		pgm_info.op_access_id  = vcpu->arch.sie_block->oai;
 		break;
 	case PGM_MONITOR:
-		pgm_info->mon_class_nr = vcpu->arch.sie_block->mcn;
-		pgm_info->mon_code = vcpu->arch.sie_block->tecmc;
+		pgm_info.mon_class_nr = vcpu->arch.sie_block->mcn;
+		pgm_info.mon_code = vcpu->arch.sie_block->tecmc;
 		break;
 	case PGM_VECTOR_PROCESSING:
 	case PGM_DATA:
-		pgm_info->data_exc_code = vcpu->arch.sie_block->dxc;
+		pgm_info.data_exc_code = vcpu->arch.sie_block->dxc;
 		break;
 	case PGM_PROTECTION:
-		pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc;
-		pgm_info->exc_access_id  = vcpu->arch.sie_block->eai;
+		pgm_info.trans_exc_code = vcpu->arch.sie_block->tecmc;
+		pgm_info.exc_access_id  = vcpu->arch.sie_block->eai;
 		break;
 	default:
 		break;
 	}
 
 	if (vcpu->arch.sie_block->iprcc & PGM_PER) {
-		pgm_info->per_code = vcpu->arch.sie_block->perc;
-		pgm_info->per_atmid = vcpu->arch.sie_block->peratmid;
-		pgm_info->per_address = vcpu->arch.sie_block->peraddr;
-		pgm_info->per_access_id = vcpu->arch.sie_block->peraid;
+		pgm_info.per_code = vcpu->arch.sie_block->perc;
+		pgm_info.per_atmid = vcpu->arch.sie_block->peratmid;
+		pgm_info.per_address = vcpu->arch.sie_block->peraddr;
+		pgm_info.per_access_id = vcpu->arch.sie_block->peraid;
 	}
+	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
 }
 
 /*
@@ -208,7 +226,6 @@ static int handle_itdb(struct kvm_vcpu *vcpu)
 
 static int handle_prog(struct kvm_vcpu *vcpu)
 {
-	struct kvm_s390_pgm_info pgm_info;
 	psw_t psw;
 	int rc;
 
@@ -234,8 +251,7 @@ static int handle_prog(struct kvm_vcpu *vcpu)
 	if (rc)
 		return rc;
 
-	__extract_prog_irq(vcpu, &pgm_info);
-	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
+	return inject_prog_on_prog_intercept(vcpu);
 }
 
 /**
@@ -302,7 +318,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
 
 	/* Make sure that the source is paged-in */
 	rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg2],
-				     reg2, &srcaddr, 0);
+				     reg2, &srcaddr, GACC_FETCH);
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
 	rc = kvm_arch_fault_in_page(vcpu, srcaddr, 0);
@@ -311,14 +327,14 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
 
 	/* Make sure that the destination is paged-in */
 	rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg1],
-				     reg1, &dstaddr, 1);
+				     reg1, &dstaddr, GACC_STORE);
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
 	rc = kvm_arch_fault_in_page(vcpu, dstaddr, 1);
 	if (rc != 0)
 		return rc;
 
-	kvm_s390_rewind_psw(vcpu, 4);
+	kvm_s390_retry_instr(vcpu);
 
 	return 0;
 }
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index f88ca72c3a77..84efc2ba6a90 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -23,6 +23,7 @@
 #include <asm/uaccess.h>
 #include <asm/sclp.h>
 #include <asm/isc.h>
+#include <asm/gmap.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
 #include "trace-s390.h"
@@ -182,8 +183,9 @@ static int cpu_timer_interrupts_enabled(struct kvm_vcpu *vcpu)
 
 static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu)
 {
-	return (vcpu->arch.sie_block->cputm >> 63) &&
-	       cpu_timer_interrupts_enabled(vcpu);
+	if (!cpu_timer_interrupts_enabled(vcpu))
+		return 0;
+	return kvm_s390_get_cpu_timer(vcpu) >> 63;
 }
 
 static inline int is_ioirq(unsigned long irq_type)
@@ -335,23 +337,6 @@ static void set_intercept_indicators(struct kvm_vcpu *vcpu)
 	set_intercept_indicators_stop(vcpu);
 }
 
-static u16 get_ilc(struct kvm_vcpu *vcpu)
-{
-	switch (vcpu->arch.sie_block->icptcode) {
-	case ICPT_INST:
-	case ICPT_INSTPROGI:
-	case ICPT_OPEREXC:
-	case ICPT_PARTEXEC:
-	case ICPT_IOINST:
-		/* last instruction only stored for these icptcodes */
-		return insn_length(vcpu->arch.sie_block->ipa >> 8);
-	case ICPT_PROGI:
-		return vcpu->arch.sie_block->pgmilc;
-	default:
-		return 0;
-	}
-}
-
 static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -588,7 +573,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	struct kvm_s390_pgm_info pgm_info;
 	int rc = 0, nullifying = false;
-	u16 ilc = get_ilc(vcpu);
+	u16 ilen;
 
 	spin_lock(&li->lock);
 	pgm_info = li->irq.pgm;
@@ -596,8 +581,9 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
 	memset(&li->irq.pgm, 0, sizeof(pgm_info));
 	spin_unlock(&li->lock);
 
-	VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilc:%d",
-		   pgm_info.code, ilc);
+	ilen = pgm_info.flags & KVM_S390_PGM_FLAGS_ILC_MASK;
+	VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilen:%d",
+		   pgm_info.code, ilen);
 	vcpu->stat.deliver_program_int++;
 	trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
 					 pgm_info.code, 0);
@@ -681,10 +667,11 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
 				   (u8 *) __LC_PER_ACCESS_ID);
 	}
 
-	if (nullifying && vcpu->arch.sie_block->icptcode == ICPT_INST)
-		kvm_s390_rewind_psw(vcpu, ilc);
+	if (nullifying && !(pgm_info.flags & KVM_S390_PGM_FLAGS_NO_REWIND))
+		kvm_s390_rewind_psw(vcpu, ilen);
 
-	rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC);
+	/* bit 1+2 of the target are the ilc, so we can directly use ilen */
+	rc |= put_guest_lc(vcpu, ilen, (u16 *) __LC_PGM_ILC);
 	rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->gbea,
 				 (u64 *) __LC_LAST_BREAK);
 	rc |= put_guest_lc(vcpu, pgm_info.code,
@@ -923,9 +910,35 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 	return ckc_irq_pending(vcpu) || cpu_timer_irq_pending(vcpu);
 }
 
+static u64 __calculate_sltime(struct kvm_vcpu *vcpu)
+{
+	u64 now, cputm, sltime = 0;
+
+	if (ckc_interrupts_enabled(vcpu)) {
+		now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
+		sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
+		/* already expired or overflow? */
+		if (!sltime || vcpu->arch.sie_block->ckc <= now)
+			return 0;
+		if (cpu_timer_interrupts_enabled(vcpu)) {
+			cputm = kvm_s390_get_cpu_timer(vcpu);
+			/* already expired? */
+			if (cputm >> 63)
+				return 0;
+			return min(sltime, tod_to_ns(cputm));
+		}
+	} else if (cpu_timer_interrupts_enabled(vcpu)) {
+		sltime = kvm_s390_get_cpu_timer(vcpu);
+		/* already expired? */
+		if (sltime >> 63)
+			return 0;
+	}
+	return sltime;
+}
+
 int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 {
-	u64 now, sltime;
+	u64 sltime;
 
 	vcpu->stat.exit_wait_state++;
 
@@ -938,22 +951,20 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 		return -EOPNOTSUPP; /* disabled wait */
 	}
 
-	if (!ckc_interrupts_enabled(vcpu)) {
+	if (!ckc_interrupts_enabled(vcpu) &&
+	    !cpu_timer_interrupts_enabled(vcpu)) {
 		VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
 		__set_cpu_idle(vcpu);
 		goto no_timer;
 	}
 
-	now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
-	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
-
-	/* underflow */
-	if (vcpu->arch.sie_block->ckc < now)
+	sltime = __calculate_sltime(vcpu);
+	if (!sltime)
 		return 0;
 
 	__set_cpu_idle(vcpu);
 	hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
-	VCPU_EVENT(vcpu, 4, "enabled wait via clock comparator: %llu ns", sltime);
+	VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime);
 no_timer:
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 	kvm_vcpu_block(vcpu);
@@ -966,13 +977,13 @@ no_timer:
 
 void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
 {
-	if (waitqueue_active(&vcpu->wq)) {
+	if (swait_active(&vcpu->wq)) {
 		/*
 		 * The vcpu gave up the cpu voluntarily, mark it as a good
 		 * yield-candidate.
 		 */
 		vcpu->preempted = true;
-		wake_up_interruptible(&vcpu->wq);
+		swake_up(&vcpu->wq);
 		vcpu->stat.halt_wakeup++;
 	}
 }
@@ -980,18 +991,16 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
 enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
 {
 	struct kvm_vcpu *vcpu;
-	u64 now, sltime;
+	u64 sltime;
 
 	vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
-	now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
-	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
+	sltime = __calculate_sltime(vcpu);
 
 	/*
 	 * If the monotonic clock runs faster than the tod clock we might be
 	 * woken up too early and have to go back to sleep to avoid deadlocks.
 	 */
-	if (vcpu->arch.sie_block->ckc > now &&
-	    hrtimer_forward_now(timer, ns_to_ktime(sltime)))
+	if (sltime && hrtimer_forward_now(timer, ns_to_ktime(sltime)))
 		return HRTIMER_RESTART;
 	kvm_s390_vcpu_wakeup(vcpu);
 	return HRTIMER_NORESTART;
@@ -1059,8 +1068,16 @@ static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
 				   irq->u.pgm.code, 0);
 
+	if (!(irq->u.pgm.flags & KVM_S390_PGM_FLAGS_ILC_VALID)) {
+		/* auto detection if no valid ILC was given */
+		irq->u.pgm.flags &= ~KVM_S390_PGM_FLAGS_ILC_MASK;
+		irq->u.pgm.flags |= kvm_s390_get_ilen(vcpu);
+		irq->u.pgm.flags |= KVM_S390_PGM_FLAGS_ILC_VALID;
+	}
+
 	if (irq->u.pgm.code == PGM_PER) {
 		li->irq.pgm.code |= PGM_PER;
+		li->irq.pgm.flags = irq->u.pgm.flags;
 		/* only modify PER related information */
 		li->irq.pgm.per_address = irq->u.pgm.per_address;
 		li->irq.pgm.per_code = irq->u.pgm.per_code;
@@ -1069,6 +1086,7 @@ static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	} else if (!(irq->u.pgm.code & PGM_PER)) {
 		li->irq.pgm.code = (li->irq.pgm.code & PGM_PER) |
 				   irq->u.pgm.code;
+		li->irq.pgm.flags = irq->u.pgm.flags;
 		/* only modify non-PER information */
 		li->irq.pgm.trans_exc_code = irq->u.pgm.trans_exc_code;
 		li->irq.pgm.mon_code = irq->u.pgm.mon_code;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 4af21c771f9b..668c087513e5 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -30,6 +30,7 @@
 #include <asm/lowcore.h>
 #include <asm/etr.h>
 #include <asm/pgtable.h>
+#include <asm/gmap.h>
 #include <asm/nmi.h>
 #include <asm/switch_to.h>
 #include <asm/isc.h>
@@ -158,6 +159,8 @@ static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val,
 		kvm->arch.epoch -= *delta;
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			vcpu->arch.sie_block->epoch -= *delta;
+			if (vcpu->arch.cputm_enabled)
+				vcpu->arch.cputm_start += *delta;
 		}
 	}
 	return NOTIFY_OK;
@@ -274,16 +277,17 @@ static void kvm_s390_sync_dirty_log(struct kvm *kvm,
 	unsigned long address;
 	struct gmap *gmap = kvm->arch.gmap;
 
-	down_read(&gmap->mm->mmap_sem);
 	/* Loop over all guest pages */
 	last_gfn = memslot->base_gfn + memslot->npages;
 	for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) {
 		address = gfn_to_hva_memslot(memslot, cur_gfn);
 
-		if (gmap_test_and_clear_dirty(address, gmap))
+		if (test_and_clear_guest_dirty(gmap->mm, address))
 			mark_page_dirty(kvm, cur_gfn);
+		if (fatal_signal_pending(current))
+			return;
+		cond_resched();
 	}
-	up_read(&gmap->mm->mmap_sem);
 }
 
 /* Section: vm related */
@@ -352,8 +356,8 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		if (atomic_read(&kvm->online_vcpus)) {
 			r = -EBUSY;
 		} else if (MACHINE_HAS_VX) {
-			set_kvm_facility(kvm->arch.model.fac->mask, 129);
-			set_kvm_facility(kvm->arch.model.fac->list, 129);
+			set_kvm_facility(kvm->arch.model.fac_mask, 129);
+			set_kvm_facility(kvm->arch.model.fac_list, 129);
 			r = 0;
 		} else
 			r = -EINVAL;
@@ -367,8 +371,8 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		if (atomic_read(&kvm->online_vcpus)) {
 			r = -EBUSY;
 		} else if (test_facility(64)) {
-			set_kvm_facility(kvm->arch.model.fac->mask, 64);
-			set_kvm_facility(kvm->arch.model.fac->list, 64);
+			set_kvm_facility(kvm->arch.model.fac_mask, 64);
+			set_kvm_facility(kvm->arch.model.fac_list, 64);
 			r = 0;
 		}
 		mutex_unlock(&kvm->lock);
@@ -651,7 +655,7 @@ static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr)
 		memcpy(&kvm->arch.model.cpu_id, &proc->cpuid,
 		       sizeof(struct cpuid));
 		kvm->arch.model.ibc = proc->ibc;
-		memcpy(kvm->arch.model.fac->list, proc->fac_list,
+		memcpy(kvm->arch.model.fac_list, proc->fac_list,
 		       S390_ARCH_FAC_LIST_SIZE_BYTE);
 	} else
 		ret = -EFAULT;
@@ -685,7 +689,8 @@ static int kvm_s390_get_processor(struct kvm *kvm, struct kvm_device_attr *attr)
 	}
 	memcpy(&proc->cpuid, &kvm->arch.model.cpu_id, sizeof(struct cpuid));
 	proc->ibc = kvm->arch.model.ibc;
-	memcpy(&proc->fac_list, kvm->arch.model.fac->list, S390_ARCH_FAC_LIST_SIZE_BYTE);
+	memcpy(&proc->fac_list, kvm->arch.model.fac_list,
+	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 	if (copy_to_user((void __user *)attr->addr, proc, sizeof(*proc)))
 		ret = -EFAULT;
 	kfree(proc);
@@ -705,7 +710,7 @@ static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr)
 	}
 	get_cpu_id((struct cpuid *) &mach->cpuid);
 	mach->ibc = sclp.ibc;
-	memcpy(&mach->fac_mask, kvm->arch.model.fac->mask,
+	memcpy(&mach->fac_mask, kvm->arch.model.fac_mask,
 	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 	memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list,
 	       S390_ARCH_FAC_LIST_SIZE_BYTE);
@@ -1082,16 +1087,12 @@ static void kvm_s390_get_cpu_id(struct cpuid *cpu_id)
 	cpu_id->version = 0xff;
 }
 
-static int kvm_s390_crypto_init(struct kvm *kvm)
+static void kvm_s390_crypto_init(struct kvm *kvm)
 {
 	if (!test_kvm_facility(kvm, 76))
-		return 0;
-
-	kvm->arch.crypto.crycb = kzalloc(sizeof(*kvm->arch.crypto.crycb),
-					 GFP_KERNEL | GFP_DMA);
-	if (!kvm->arch.crypto.crycb)
-		return -ENOMEM;
+		return;
 
+	kvm->arch.crypto.crycb = &kvm->arch.sie_page2->crycb;
 	kvm_s390_set_crycb_format(kvm);
 
 	/* Enable AES/DEA protected key functions by default */
@@ -1101,8 +1102,6 @@ static int kvm_s390_crypto_init(struct kvm *kvm)
 			 sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
 	get_random_bytes(kvm->arch.crypto.crycb->dea_wrapping_key_mask,
 			 sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
-
-	return 0;
 }
 
 static void sca_dispose(struct kvm *kvm)
@@ -1156,37 +1155,30 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (!kvm->arch.dbf)
 		goto out_err;
 
-	/*
-	 * The architectural maximum amount of facilities is 16 kbit. To store
-	 * this amount, 2 kbyte of memory is required. Thus we need a full
-	 * page to hold the guest facility list (arch.model.fac->list) and the
-	 * facility mask (arch.model.fac->mask). Its address size has to be
-	 * 31 bits and word aligned.
-	 */
-	kvm->arch.model.fac =
-		(struct kvm_s390_fac *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
-	if (!kvm->arch.model.fac)
+	kvm->arch.sie_page2 =
+	     (struct sie_page2 *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	if (!kvm->arch.sie_page2)
 		goto out_err;
 
 	/* Populate the facility mask initially. */
-	memcpy(kvm->arch.model.fac->mask, S390_lowcore.stfle_fac_list,
+	memcpy(kvm->arch.model.fac_mask, S390_lowcore.stfle_fac_list,
 	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 	for (i = 0; i < S390_ARCH_FAC_LIST_SIZE_U64; i++) {
 		if (i < kvm_s390_fac_list_mask_size())
-			kvm->arch.model.fac->mask[i] &= kvm_s390_fac_list_mask[i];
+			kvm->arch.model.fac_mask[i] &= kvm_s390_fac_list_mask[i];
 		else
-			kvm->arch.model.fac->mask[i] = 0UL;
+			kvm->arch.model.fac_mask[i] = 0UL;
 	}
 
 	/* Populate the facility list initially. */
-	memcpy(kvm->arch.model.fac->list, kvm->arch.model.fac->mask,
+	kvm->arch.model.fac_list = kvm->arch.sie_page2->fac_list;
+	memcpy(kvm->arch.model.fac_list, kvm->arch.model.fac_mask,
 	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 
 	kvm_s390_get_cpu_id(&kvm->arch.model.cpu_id);
 	kvm->arch.model.ibc = sclp.ibc & 0x0fff;
 
-	if (kvm_s390_crypto_init(kvm) < 0)
-		goto out_err;
+	kvm_s390_crypto_init(kvm);
 
 	spin_lock_init(&kvm->arch.float_int.lock);
 	for (i = 0; i < FIRQ_LIST_COUNT; i++)
@@ -1222,8 +1214,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	return 0;
 out_err:
-	kfree(kvm->arch.crypto.crycb);
-	free_page((unsigned long)kvm->arch.model.fac);
+	free_page((unsigned long)kvm->arch.sie_page2);
 	debug_unregister(kvm->arch.dbf);
 	sca_dispose(kvm);
 	KVM_EVENT(3, "creation of vm failed: %d", rc);
@@ -1269,10 +1260,9 @@ static void kvm_free_vcpus(struct kvm *kvm)
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	kvm_free_vcpus(kvm);
-	free_page((unsigned long)kvm->arch.model.fac);
 	sca_dispose(kvm);
 	debug_unregister(kvm->arch.dbf);
-	kfree(kvm->arch.crypto.crycb);
+	free_page((unsigned long)kvm->arch.sie_page2);
 	if (!kvm_is_ucontrol(kvm))
 		gmap_free(kvm->arch.gmap);
 	kvm_s390_destroy_adapters(kvm);
@@ -1414,8 +1404,13 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 				    KVM_SYNC_PFAULT;
 	if (test_kvm_facility(vcpu->kvm, 64))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
-	if (test_kvm_facility(vcpu->kvm, 129))
+	/* fprs can be synchronized via vrs, even if the guest has no vx. With
+	 * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format.
+	 */
+	if (MACHINE_HAS_VX)
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
+	else
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS;
 
 	if (kvm_is_ucontrol(vcpu->kvm))
 		return __kvm_ucontrol_vcpu_init(vcpu);
@@ -1423,6 +1418,93 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+static void __start_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+	WARN_ON_ONCE(vcpu->arch.cputm_start != 0);
+	raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
+	vcpu->arch.cputm_start = get_tod_clock_fast();
+	raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
+}
+
+/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+static void __stop_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+	WARN_ON_ONCE(vcpu->arch.cputm_start == 0);
+	raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
+	vcpu->arch.sie_block->cputm -= get_tod_clock_fast() - vcpu->arch.cputm_start;
+	vcpu->arch.cputm_start = 0;
+	raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
+}
+
+/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+static void __enable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+	WARN_ON_ONCE(vcpu->arch.cputm_enabled);
+	vcpu->arch.cputm_enabled = true;
+	__start_cpu_timer_accounting(vcpu);
+}
+
+/* needs disabled preemption to protect from TOD sync and vcpu_load/put */
+static void __disable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+	WARN_ON_ONCE(!vcpu->arch.cputm_enabled);
+	__stop_cpu_timer_accounting(vcpu);
+	vcpu->arch.cputm_enabled = false;
+}
+
+static void enable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+	preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+	__enable_cpu_timer_accounting(vcpu);
+	preempt_enable();
+}
+
+static void disable_cpu_timer_accounting(struct kvm_vcpu *vcpu)
+{
+	preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+	__disable_cpu_timer_accounting(vcpu);
+	preempt_enable();
+}
+
+/* set the cpu timer - may only be called from the VCPU thread itself */
+void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm)
+{
+	preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+	raw_write_seqcount_begin(&vcpu->arch.cputm_seqcount);
+	if (vcpu->arch.cputm_enabled)
+		vcpu->arch.cputm_start = get_tod_clock_fast();
+	vcpu->arch.sie_block->cputm = cputm;
+	raw_write_seqcount_end(&vcpu->arch.cputm_seqcount);
+	preempt_enable();
+}
+
+/* update and get the cpu timer - can also be called from other VCPU threads */
+__u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu)
+{
+	unsigned int seq;
+	__u64 value;
+
+	if (unlikely(!vcpu->arch.cputm_enabled))
+		return vcpu->arch.sie_block->cputm;
+
+	preempt_disable(); /* protect from TOD sync and vcpu_load/put */
+	do {
+		seq = raw_read_seqcount(&vcpu->arch.cputm_seqcount);
+		/*
+		 * If the writer would ever execute a read in the critical
+		 * section, e.g. in irq context, we have a deadlock.
+		 */
+		WARN_ON_ONCE((seq & 1) && smp_processor_id() == vcpu->cpu);
+		value = vcpu->arch.sie_block->cputm;
+		/* if cputm_start is 0, accounting is being started/stopped */
+		if (likely(vcpu->arch.cputm_start))
+			value -= get_tod_clock_fast() - vcpu->arch.cputm_start;
+	} while (read_seqcount_retry(&vcpu->arch.cputm_seqcount, seq & ~1));
+	preempt_enable();
+	return value;
+}
+
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	/* Save host register state */
@@ -1430,10 +1512,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc;
 	vcpu->arch.host_fpregs.regs = current->thread.fpu.regs;
 
-	/* Depending on MACHINE_HAS_VX, data stored to vrs either
-	 * has vector register or floating point register format.
-	 */
-	current->thread.fpu.regs = vcpu->run->s.regs.vrs;
+	if (MACHINE_HAS_VX)
+		current->thread.fpu.regs = vcpu->run->s.regs.vrs;
+	else
+		current->thread.fpu.regs = vcpu->run->s.regs.fprs;
 	current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
 	if (test_fp_ctl(current->thread.fpu.fpc))
 		/* User space provided an invalid FPC, let's clear it */
@@ -1443,10 +1525,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	restore_access_regs(vcpu->run->s.regs.acrs);
 	gmap_enable(vcpu->arch.gmap);
 	atomic_or(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+	if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
+		__start_cpu_timer_accounting(vcpu);
+	vcpu->cpu = cpu;
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	vcpu->cpu = -1;
+	if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
+		__stop_cpu_timer_accounting(vcpu);
 	atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	gmap_disable(vcpu->arch.gmap);
 
@@ -1468,7 +1556,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	vcpu->arch.sie_block->gpsw.mask = 0UL;
 	vcpu->arch.sie_block->gpsw.addr = 0UL;
 	kvm_s390_set_prefix(vcpu, 0);
-	vcpu->arch.sie_block->cputm     = 0UL;
+	kvm_s390_set_cpu_timer(vcpu, 0);
 	vcpu->arch.sie_block->ckc       = 0UL;
 	vcpu->arch.sie_block->todpr     = 0;
 	memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
@@ -1538,7 +1626,8 @@ static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.cpu_id = model->cpu_id;
 	vcpu->arch.sie_block->ibc = model->ibc;
-	vcpu->arch.sie_block->fac = (int) (long) model->fac->list;
+	if (test_kvm_facility(vcpu->kvm, 7))
+		vcpu->arch.sie_block->fac = (u32)(u64) model->fac_list;
 }
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
@@ -1616,6 +1705,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
 	vcpu->arch.local_int.wq = &vcpu->wq;
 	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
+	seqcount_init(&vcpu->arch.cputm_seqcount);
 
 	rc = kvm_vcpu_init(vcpu, kvm, id);
 	if (rc)
@@ -1715,7 +1805,7 @@ static int kvm_arch_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu,
 			     (u64 __user *)reg->addr);
 		break;
 	case KVM_REG_S390_CPU_TIMER:
-		r = put_user(vcpu->arch.sie_block->cputm,
+		r = put_user(kvm_s390_get_cpu_timer(vcpu),
 			     (u64 __user *)reg->addr);
 		break;
 	case KVM_REG_S390_CLOCK_COMP:
@@ -1753,6 +1843,7 @@ static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu,
 					   struct kvm_one_reg *reg)
 {
 	int r = -EINVAL;
+	__u64 val;
 
 	switch (reg->id) {
 	case KVM_REG_S390_TODPR:
@@ -1764,8 +1855,9 @@ static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu,
 			     (u64 __user *)reg->addr);
 		break;
 	case KVM_REG_S390_CPU_TIMER:
-		r = get_user(vcpu->arch.sie_block->cputm,
-			     (u64 __user *)reg->addr);
+		r = get_user(val, (u64 __user *)reg->addr);
+		if (!r)
+			kvm_s390_set_cpu_timer(vcpu, val);
 		break;
 	case KVM_REG_S390_CLOCK_COMP:
 		r = get_user(vcpu->arch.sie_block->ckc,
@@ -2158,8 +2250,10 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
 
 static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
 {
-	psw_t *psw = &vcpu->arch.sie_block->gpsw;
-	u8 opcode;
+	struct kvm_s390_pgm_info pgm_info = {
+		.code = PGM_ADDRESSING,
+	};
+	u8 opcode, ilen;
 	int rc;
 
 	VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
@@ -2173,12 +2267,21 @@ static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
 	 * to look up the current opcode to get the length of the instruction
 	 * to be able to forward the PSW.
 	 */
-	rc = read_guest(vcpu, psw->addr, 0, &opcode, 1);
-	if (rc)
-		return kvm_s390_inject_prog_cond(vcpu, rc);
-	psw->addr = __rewind_psw(*psw, -insn_length(opcode));
-
-	return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	rc = read_guest_instr(vcpu, &opcode, 1);
+	ilen = insn_length(opcode);
+	if (rc < 0) {
+		return rc;
+	} else if (rc) {
+		/* Instruction-Fetching Exceptions - we can't detect the ilen.
+		 * Forward by arbitrary ilc, injection will take care of
+		 * nullification if necessary.
+		 */
+		pgm_info = vcpu->arch.pgm;
+		ilen = 4;
+	}
+	pgm_info.flags = ilen | KVM_S390_PGM_FLAGS_ILC_VALID;
+	kvm_s390_forward_psw(vcpu, ilen);
+	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
 }
 
 static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
@@ -2244,10 +2347,12 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 		 */
 		local_irq_disable();
 		__kvm_guest_enter();
+		__disable_cpu_timer_accounting(vcpu);
 		local_irq_enable();
 		exit_reason = sie64a(vcpu->arch.sie_block,
 				     vcpu->run->s.regs.gprs);
 		local_irq_disable();
+		__enable_cpu_timer_accounting(vcpu);
 		__kvm_guest_exit();
 		local_irq_enable();
 		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
@@ -2271,7 +2376,7 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 	}
 	if (kvm_run->kvm_dirty_regs & KVM_SYNC_ARCH0) {
-		vcpu->arch.sie_block->cputm = kvm_run->s.regs.cputm;
+		kvm_s390_set_cpu_timer(vcpu, kvm_run->s.regs.cputm);
 		vcpu->arch.sie_block->ckc = kvm_run->s.regs.ckc;
 		vcpu->arch.sie_block->todpr = kvm_run->s.regs.todpr;
 		vcpu->arch.sie_block->pp = kvm_run->s.regs.pp;
@@ -2293,7 +2398,7 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	kvm_run->psw_addr = vcpu->arch.sie_block->gpsw.addr;
 	kvm_run->s.regs.prefix = kvm_s390_get_prefix(vcpu);
 	memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128);
-	kvm_run->s.regs.cputm = vcpu->arch.sie_block->cputm;
+	kvm_run->s.regs.cputm = kvm_s390_get_cpu_timer(vcpu);
 	kvm_run->s.regs.ckc = vcpu->arch.sie_block->ckc;
 	kvm_run->s.regs.todpr = vcpu->arch.sie_block->todpr;
 	kvm_run->s.regs.pp = vcpu->arch.sie_block->pp;
@@ -2325,6 +2430,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	}
 
 	sync_regs(vcpu, kvm_run);
+	enable_cpu_timer_accounting(vcpu);
 
 	might_fault();
 	rc = __vcpu_run(vcpu);
@@ -2344,6 +2450,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		rc = 0;
 	}
 
+	disable_cpu_timer_accounting(vcpu);
 	store_regs(vcpu, kvm_run);
 
 	if (vcpu->sigset_active)
@@ -2364,7 +2471,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
 	unsigned char archmode = 1;
 	freg_t fprs[NUM_FPRS];
 	unsigned int px;
-	u64 clkcomp;
+	u64 clkcomp, cputm;
 	int rc;
 
 	px = kvm_s390_get_prefix(vcpu);
@@ -2381,12 +2488,12 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
 
 	/* manually convert vector registers if necessary */
 	if (MACHINE_HAS_VX) {
-		convert_vx_to_fp(fprs, current->thread.fpu.vxrs);
+		convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs);
 		rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
 				     fprs, 128);
 	} else {
 		rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
-				     vcpu->run->s.regs.vrs, 128);
+				     vcpu->run->s.regs.fprs, 128);
 	}
 	rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA,
 			      vcpu->run->s.regs.gprs, 128);
@@ -2398,8 +2505,9 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
 			      &vcpu->run->s.regs.fpc, 4);
 	rc |= write_guest_abs(vcpu, gpa + __LC_TOD_PROGREG_SAVE_AREA,
 			      &vcpu->arch.sie_block->todpr, 4);
+	cputm = kvm_s390_get_cpu_timer(vcpu);
 	rc |= write_guest_abs(vcpu, gpa + __LC_CPU_TIMER_SAVE_AREA,
-			      &vcpu->arch.sie_block->cputm, 8);
+			      &cputm, 8);
 	clkcomp = vcpu->arch.sie_block->ckc >> 8;
 	rc |= write_guest_abs(vcpu, gpa + __LC_CLOCK_COMP_SAVE_AREA,
 			      &clkcomp, 8);
@@ -2605,7 +2713,8 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
 	switch (mop->op) {
 	case KVM_S390_MEMOP_LOGICAL_READ:
 		if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
-			r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, false);
+			r = check_gva_range(vcpu, mop->gaddr, mop->ar,
+					    mop->size, GACC_FETCH);
 			break;
 		}
 		r = read_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size);
@@ -2616,7 +2725,8 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
 		break;
 	case KVM_S390_MEMOP_LOGICAL_WRITE:
 		if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
-			r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, true);
+			r = check_gva_range(vcpu, mop->gaddr, mop->ar,
+					    mop->size, GACC_STORE);
 			break;
 		}
 		if (copy_from_user(tmpbuf, uaddr, mop->size)) {
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index df1abada1f36..8621ab00ec8e 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -19,6 +19,7 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 #include <asm/facility.h>
+#include <asm/processor.h>
 
 typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
 
@@ -53,6 +54,11 @@ static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu)
 	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED;
 }
 
+static inline int is_vcpu_idle(struct kvm_vcpu *vcpu)
+{
+	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_WAIT;
+}
+
 static inline int kvm_is_ucontrol(struct kvm *kvm)
 {
 #ifdef CONFIG_KVM_S390_UCONTROL
@@ -154,8 +160,8 @@ static inline void kvm_s390_set_psw_cc(struct kvm_vcpu *vcpu, unsigned long cc)
 /* test availability of facility in a kvm instance */
 static inline int test_kvm_facility(struct kvm *kvm, unsigned long nr)
 {
-	return __test_facility(nr, kvm->arch.model.fac->mask) &&
-		__test_facility(nr, kvm->arch.model.fac->list);
+	return __test_facility(nr, kvm->arch.model.fac_mask) &&
+		__test_facility(nr, kvm->arch.model.fac_list);
 }
 
 static inline int set_kvm_facility(u64 *fac_list, unsigned long nr)
@@ -212,8 +218,22 @@ int kvm_s390_reinject_io_int(struct kvm *kvm,
 int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked);
 
 /* implemented in intercept.c */
-void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc);
+u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu);
 int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu);
+static inline void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilen)
+{
+	struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block;
+
+	sie_block->gpsw.addr = __rewind_psw(sie_block->gpsw, ilen);
+}
+static inline void kvm_s390_forward_psw(struct kvm_vcpu *vcpu, int ilen)
+{
+	kvm_s390_rewind_psw(vcpu, -ilen);
+}
+static inline void kvm_s390_retry_instr(struct kvm_vcpu *vcpu)
+{
+	kvm_s390_rewind_psw(vcpu, kvm_s390_get_ilen(vcpu));
+}
 
 /* implemented in priv.c */
 int is_valid_psw(psw_t *psw);
@@ -248,6 +268,8 @@ int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu);
 void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu);
 unsigned long kvm_s390_fac_list_mask_size(void);
 extern unsigned long kvm_s390_fac_list_mask[];
+void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm);
+__u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu);
 
 /* implemented in diag.c */
 int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index ed74e86d9b9e..0a1591d3d25d 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -23,6 +23,7 @@
 #include <asm/sysinfo.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
+#include <asm/gmap.h>
 #include <asm/io.h>
 #include <asm/ptrace.h>
 #include <asm/compat.h>
@@ -173,7 +174,7 @@ static int handle_skey(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
-	kvm_s390_rewind_psw(vcpu, 4);
+	kvm_s390_retry_instr(vcpu);
 	VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation");
 	return 0;
 }
@@ -184,7 +185,7 @@ static int handle_ipte_interlock(struct kvm_vcpu *vcpu)
 	if (psw_bits(vcpu->arch.sie_block->gpsw).p)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 	wait_event(vcpu->kvm->arch.ipte_wq, !ipte_lock_held(vcpu));
-	kvm_s390_rewind_psw(vcpu, 4);
+	kvm_s390_retry_instr(vcpu);
 	VCPU_EVENT(vcpu, 4, "%s", "retrying ipte interlock operation");
 	return 0;
 }
@@ -354,7 +355,7 @@ static int handle_stfl(struct kvm_vcpu *vcpu)
 	 * We need to shift the lower 32 facility bits (bit 0-31) from a u64
 	 * into a u32 memory representation. They will remain bits 0-31.
 	 */
-	fac = *vcpu->kvm->arch.model.fac->list >> 32;
+	fac = *vcpu->kvm->arch.model.fac_list >> 32;
 	rc = write_guest_lc(vcpu, offsetof(struct lowcore, stfl_fac_list),
 			    &fac, sizeof(fac));
 	if (rc)
@@ -759,8 +760,8 @@ static int handle_essa(struct kvm_vcpu *vcpu)
 	if (((vcpu->arch.sie_block->ipb & 0xf0000000) >> 28) > 6)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-	/* Rewind PSW to repeat the ESSA instruction */
-	kvm_s390_rewind_psw(vcpu, 4);
+	/* Retry the ESSA instruction */
+	kvm_s390_retry_instr(vcpu);
 	vcpu->arch.sie_block->cbrlo &= PAGE_MASK;	/* reset nceo */
 	cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo);
 	down_read(&gmap->mm->mmap_sem);
@@ -981,11 +982,12 @@ static int handle_tprot(struct kvm_vcpu *vcpu)
 		return -EOPNOTSUPP;
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT)
 		ipte_lock(vcpu);
-	ret = guest_translate_address(vcpu, address1, ar, &gpa, 1);
+	ret = guest_translate_address(vcpu, address1, ar, &gpa, GACC_STORE);
 	if (ret == PGM_PROTECTION) {
 		/* Write protected? Try again with read-only... */
 		cc = 1;
-		ret = guest_translate_address(vcpu, address1, ar, &gpa, 0);
+		ret = guest_translate_address(vcpu, address1, ar, &gpa,
+					      GACC_FETCH);
 	}
 	if (ret) {
 		if (ret == PGM_ADDRESSING || ret == PGM_TRANSLATION_SPEC) {
diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile
index 0e8fefe5b0ce..1d1af31e8354 100644
--- a/arch/s390/lib/Makefile
+++ b/arch/s390/lib/Makefile
@@ -3,7 +3,7 @@
 #
 
 lib-y += delay.o string.o uaccess.o find.o
-obj-y += mem.o
+obj-y += mem.o xor.o
 lib-$(CONFIG_SMP) += spinlock.o
 lib-$(CONFIG_KPROBES) += probes.o
 lib-$(CONFIG_UPROBES) += probes.o
diff --git a/arch/s390/lib/xor.c b/arch/s390/lib/xor.c
new file mode 100644
index 000000000000..7d94e3ec34a9
--- /dev/null
+++ b/arch/s390/lib/xor.c
@@ -0,0 +1,134 @@
+/*
+ * Optimized xor_block operation for RAID4/5
+ *
+ * Copyright IBM Corp. 2016
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/raid/xor.h>
+
+static void xor_xc_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+	asm volatile(
+		"	larl	1,2f\n"
+		"	aghi	%0,-1\n"
+		"	jm	3f\n"
+		"	srlg	0,%0,8\n"
+		"	ltgr	0,0\n"
+		"	jz	1f\n"
+		"0:	xc	0(256,%1),0(%2)\n"
+		"	la	%1,256(%1)\n"
+		"	la	%2,256(%2)\n"
+		"	brctg	0,0b\n"
+		"1:	ex	%0,0(1)\n"
+		"	j	3f\n"
+		"2:	xc	0(1,%1),0(%2)\n"
+		"3:\n"
+		: : "d" (bytes), "a" (p1), "a" (p2)
+		: "0", "1", "cc", "memory");
+}
+
+static void xor_xc_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		     unsigned long *p3)
+{
+	asm volatile(
+		"	larl	1,2f\n"
+		"	aghi	%0,-1\n"
+		"	jm	3f\n"
+		"	srlg	0,%0,8\n"
+		"	ltgr	0,0\n"
+		"	jz	1f\n"
+		"0:	xc	0(256,%1),0(%2)\n"
+		"	xc	0(256,%1),0(%3)\n"
+		"	la	%1,256(%1)\n"
+		"	la	%2,256(%2)\n"
+		"	la	%3,256(%3)\n"
+		"	brctg	0,0b\n"
+		"1:	ex	%0,0(1)\n"
+		"	ex	%0,6(1)\n"
+		"	j	3f\n"
+		"2:	xc	0(1,%1),0(%2)\n"
+		"	xc	0(1,%1),0(%3)\n"
+		"3:\n"
+		: "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3)
+		: : "0", "1", "cc", "memory");
+}
+
+static void xor_xc_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		     unsigned long *p3, unsigned long *p4)
+{
+	asm volatile(
+		"	larl	1,2f\n"
+		"	aghi	%0,-1\n"
+		"	jm	3f\n"
+		"	srlg	0,%0,8\n"
+		"	ltgr	0,0\n"
+		"	jz	1f\n"
+		"0:	xc	0(256,%1),0(%2)\n"
+		"	xc	0(256,%1),0(%3)\n"
+		"	xc	0(256,%1),0(%4)\n"
+		"	la	%1,256(%1)\n"
+		"	la	%2,256(%2)\n"
+		"	la	%3,256(%3)\n"
+		"	la	%4,256(%4)\n"
+		"	brctg	0,0b\n"
+		"1:	ex	%0,0(1)\n"
+		"	ex	%0,6(1)\n"
+		"	ex	%0,12(1)\n"
+		"	j	3f\n"
+		"2:	xc	0(1,%1),0(%2)\n"
+		"	xc	0(1,%1),0(%3)\n"
+		"	xc	0(1,%1),0(%4)\n"
+		"3:\n"
+		: "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4)
+		: : "0", "1", "cc", "memory");
+}
+
+static void xor_xc_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		     unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+	/* Get around a gcc oddity */
+	register unsigned long *reg7 asm ("7") = p5;
+
+	asm volatile(
+		"	larl	1,2f\n"
+		"	aghi	%0,-1\n"
+		"	jm	3f\n"
+		"	srlg	0,%0,8\n"
+		"	ltgr	0,0\n"
+		"	jz	1f\n"
+		"0:	xc	0(256,%1),0(%2)\n"
+		"	xc	0(256,%1),0(%3)\n"
+		"	xc	0(256,%1),0(%4)\n"
+		"	xc	0(256,%1),0(%5)\n"
+		"	la	%1,256(%1)\n"
+		"	la	%2,256(%2)\n"
+		"	la	%3,256(%3)\n"
+		"	la	%4,256(%4)\n"
+		"	la	%5,256(%5)\n"
+		"	brctg	0,0b\n"
+		"1:	ex	%0,0(1)\n"
+		"	ex	%0,6(1)\n"
+		"	ex	%0,12(1)\n"
+		"	ex	%0,18(1)\n"
+		"	j	3f\n"
+		"2:	xc	0(1,%1),0(%2)\n"
+		"	xc	0(1,%1),0(%3)\n"
+		"	xc	0(1,%1),0(%4)\n"
+		"	xc	0(1,%1),0(%5)\n"
+		"3:\n"
+		: "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4),
+		  "+a" (reg7)
+		: : "0", "1", "cc", "memory");
+}
+
+struct xor_block_template xor_block_xc = {
+	.name = "xc",
+	.do_2 = xor_xc_2,
+	.do_3 = xor_xc_3,
+	.do_4 = xor_xc_4,
+	.do_5 = xor_xc_5,
+};
+EXPORT_SYMBOL(xor_block_xc);
diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile
index 839592ca265c..2ae54cad2b6a 100644
--- a/arch/s390/mm/Makefile
+++ b/arch/s390/mm/Makefile
@@ -2,9 +2,11 @@
 # Makefile for the linux s390-specific parts of the memory manager.
 #
 
-obj-y		:= init.o fault.o extmem.o mmap.o vmem.o pgtable.o maccess.o
+obj-y		:= init.o fault.o extmem.o mmap.o vmem.o maccess.o
 obj-y		+= page-states.o gup.o extable.o pageattr.o mem_detect.o
+obj-y		+= pgtable.o pgalloc.o
 
 obj-$(CONFIG_CMM)		+= cmm.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_S390_PTDUMP)	+= dump_pagetables.o
+obj-$(CONFIG_PGSTE)		+= gmap.o
diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c
index a1bf4ad8925d..02042b6b66bf 100644
--- a/arch/s390/mm/extmem.c
+++ b/arch/s390/mm/extmem.c
@@ -265,7 +265,7 @@ query_segment_type (struct dcss_segment *seg)
 		goto out_free;
 	}
 	if (diag_cc > 1) {
-		pr_warning("Querying a DCSS type failed with rc=%ld\n", vmrc);
+		pr_warn("Querying a DCSS type failed with rc=%ld\n", vmrc);
 		rc = dcss_diag_translate_rc (vmrc);
 		goto out_free;
 	}
@@ -457,8 +457,7 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long
 		goto out_resource;
 	}
 	if (diag_cc > 1) {
-		pr_warning("Loading DCSS %s failed with rc=%ld\n", name,
-			   end_addr);
+		pr_warn("Loading DCSS %s failed with rc=%ld\n", name, end_addr);
 		rc = dcss_diag_translate_rc(end_addr);
 		dcss_diag(&purgeseg_scode, seg->dcss_name,
 				&dummy, &dummy);
@@ -574,8 +573,7 @@ segment_modify_shared (char *name, int do_nonshared)
 		goto out_unlock;
 	}
 	if (atomic_read (&seg->ref_count) != 1) {
-		pr_warning("DCSS %s is in use and cannot be reloaded\n",
-			   name);
+		pr_warn("DCSS %s is in use and cannot be reloaded\n", name);
 		rc = -EAGAIN;
 		goto out_unlock;
 	}
@@ -588,8 +586,8 @@ segment_modify_shared (char *name, int do_nonshared)
 			seg->res->flags |= IORESOURCE_READONLY;
 
 	if (request_resource(&iomem_resource, seg->res)) {
-		pr_warning("DCSS %s overlaps with used memory resources "
-			   "and cannot be reloaded\n", name);
+		pr_warn("DCSS %s overlaps with used memory resources and cannot be reloaded\n",
+			name);
 		rc = -EBUSY;
 		kfree(seg->res);
 		goto out_del_mem;
@@ -607,8 +605,8 @@ segment_modify_shared (char *name, int do_nonshared)
 		goto out_del_res;
 	}
 	if (diag_cc > 1) {
-		pr_warning("Reloading DCSS %s failed with rc=%ld\n", name,
-			   end_addr);
+		pr_warn("Reloading DCSS %s failed with rc=%ld\n",
+			name, end_addr);
 		rc = dcss_diag_translate_rc(end_addr);
 		goto out_del_res;
 	}
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 791a4146052c..cce577feab1e 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -32,6 +32,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/diag.h>
 #include <asm/pgtable.h>
+#include <asm/gmap.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/facility.h>
@@ -183,6 +184,8 @@ static void dump_fault_info(struct pt_regs *regs)
 {
 	unsigned long asce;
 
+	pr_alert("Failing address: %016lx TEID: %016lx\n",
+		 regs->int_parm_long & __FAIL_ADDR_MASK, regs->int_parm_long);
 	pr_alert("Fault in ");
 	switch (regs->int_parm_long & 3) {
 	case 3:
@@ -218,7 +221,9 @@ static void dump_fault_info(struct pt_regs *regs)
 	dump_pagetable(asce, regs->int_parm_long & __FAIL_ADDR_MASK);
 }
 
-static inline void report_user_fault(struct pt_regs *regs, long signr)
+int show_unhandled_signals = 1;
+
+void report_user_fault(struct pt_regs *regs, long signr, int is_mm_fault)
 {
 	if ((task_pid_nr(current) > 1) && !show_unhandled_signals)
 		return;
@@ -230,9 +235,8 @@ static inline void report_user_fault(struct pt_regs *regs, long signr)
 	       regs->int_code & 0xffff, regs->int_code >> 17);
 	print_vma_addr(KERN_CONT "in ", regs->psw.addr);
 	printk(KERN_CONT "\n");
-	printk(KERN_ALERT "failing address: %016lx TEID: %016lx\n",
-	       regs->int_parm_long & __FAIL_ADDR_MASK, regs->int_parm_long);
-	dump_fault_info(regs);
+	if (is_mm_fault)
+		dump_fault_info(regs);
 	show_regs(regs);
 }
 
@@ -244,7 +248,7 @@ static noinline void do_sigsegv(struct pt_regs *regs, int si_code)
 {
 	struct siginfo si;
 
-	report_user_fault(regs, SIGSEGV);
+	report_user_fault(regs, SIGSEGV, 1);
 	si.si_signo = SIGSEGV;
 	si.si_code = si_code;
 	si.si_addr = (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK);
@@ -272,8 +276,6 @@ static noinline void do_no_context(struct pt_regs *regs)
 	else
 		printk(KERN_ALERT "Unable to handle kernel paging request"
 		       " in virtual user address space\n");
-	printk(KERN_ALERT "failing address: %016lx TEID: %016lx\n",
-	       regs->int_parm_long & __FAIL_ADDR_MASK, regs->int_parm_long);
 	dump_fault_info(regs);
 	die(regs, "Oops");
 	do_exit(SIGKILL);
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
new file mode 100644
index 000000000000..69247b4dcc43
--- /dev/null
+++ b/arch/s390/mm/gmap.c
@@ -0,0 +1,774 @@
+/*
+ *  KVM guest address space mapping code
+ *
+ *    Copyright IBM Corp. 2007, 2016
+ *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/smp.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/swapops.h>
+#include <linux/ksm.h>
+#include <linux/mman.h>
+
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/gmap.h>
+#include <asm/tlb.h>
+
+/**
+ * gmap_alloc - allocate a guest address space
+ * @mm: pointer to the parent mm_struct
+ * @limit: maximum size of the gmap address space
+ *
+ * Returns a guest address space structure.
+ */
+struct gmap *gmap_alloc(struct mm_struct *mm, unsigned long limit)
+{
+	struct gmap *gmap;
+	struct page *page;
+	unsigned long *table;
+	unsigned long etype, atype;
+
+	if (limit < (1UL << 31)) {
+		limit = (1UL << 31) - 1;
+		atype = _ASCE_TYPE_SEGMENT;
+		etype = _SEGMENT_ENTRY_EMPTY;
+	} else if (limit < (1UL << 42)) {
+		limit = (1UL << 42) - 1;
+		atype = _ASCE_TYPE_REGION3;
+		etype = _REGION3_ENTRY_EMPTY;
+	} else if (limit < (1UL << 53)) {
+		limit = (1UL << 53) - 1;
+		atype = _ASCE_TYPE_REGION2;
+		etype = _REGION2_ENTRY_EMPTY;
+	} else {
+		limit = -1UL;
+		atype = _ASCE_TYPE_REGION1;
+		etype = _REGION1_ENTRY_EMPTY;
+	}
+	gmap = kzalloc(sizeof(struct gmap), GFP_KERNEL);
+	if (!gmap)
+		goto out;
+	INIT_LIST_HEAD(&gmap->crst_list);
+	INIT_RADIX_TREE(&gmap->guest_to_host, GFP_KERNEL);
+	INIT_RADIX_TREE(&gmap->host_to_guest, GFP_ATOMIC);
+	spin_lock_init(&gmap->guest_table_lock);
+	gmap->mm = mm;
+	page = alloc_pages(GFP_KERNEL, 2);
+	if (!page)
+		goto out_free;
+	page->index = 0;
+	list_add(&page->lru, &gmap->crst_list);
+	table = (unsigned long *) page_to_phys(page);
+	crst_table_init(table, etype);
+	gmap->table = table;
+	gmap->asce = atype | _ASCE_TABLE_LENGTH |
+		_ASCE_USER_BITS | __pa(table);
+	gmap->asce_end = limit;
+	down_write(&mm->mmap_sem);
+	list_add(&gmap->list, &mm->context.gmap_list);
+	up_write(&mm->mmap_sem);
+	return gmap;
+
+out_free:
+	kfree(gmap);
+out:
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(gmap_alloc);
+
+static void gmap_flush_tlb(struct gmap *gmap)
+{
+	if (MACHINE_HAS_IDTE)
+		__tlb_flush_asce(gmap->mm, gmap->asce);
+	else
+		__tlb_flush_global();
+}
+
+static void gmap_radix_tree_free(struct radix_tree_root *root)
+{
+	struct radix_tree_iter iter;
+	unsigned long indices[16];
+	unsigned long index;
+	void **slot;
+	int i, nr;
+
+	/* A radix tree is freed by deleting all of its entries */
+	index = 0;
+	do {
+		nr = 0;
+		radix_tree_for_each_slot(slot, root, &iter, index) {
+			indices[nr] = iter.index;
+			if (++nr == 16)
+				break;
+		}
+		for (i = 0; i < nr; i++) {
+			index = indices[i];
+			radix_tree_delete(root, index);
+		}
+	} while (nr > 0);
+}
+
+/**
+ * gmap_free - free a guest address space
+ * @gmap: pointer to the guest address space structure
+ */
+void gmap_free(struct gmap *gmap)
+{
+	struct page *page, *next;
+
+	/* Flush tlb. */
+	if (MACHINE_HAS_IDTE)
+		__tlb_flush_asce(gmap->mm, gmap->asce);
+	else
+		__tlb_flush_global();
+
+	/* Free all segment & region tables. */
+	list_for_each_entry_safe(page, next, &gmap->crst_list, lru)
+		__free_pages(page, 2);
+	gmap_radix_tree_free(&gmap->guest_to_host);
+	gmap_radix_tree_free(&gmap->host_to_guest);
+	down_write(&gmap->mm->mmap_sem);
+	list_del(&gmap->list);
+	up_write(&gmap->mm->mmap_sem);
+	kfree(gmap);
+}
+EXPORT_SYMBOL_GPL(gmap_free);
+
+/**
+ * gmap_enable - switch primary space to the guest address space
+ * @gmap: pointer to the guest address space structure
+ */
+void gmap_enable(struct gmap *gmap)
+{
+	S390_lowcore.gmap = (unsigned long) gmap;
+}
+EXPORT_SYMBOL_GPL(gmap_enable);
+
+/**
+ * gmap_disable - switch back to the standard primary address space
+ * @gmap: pointer to the guest address space structure
+ */
+void gmap_disable(struct gmap *gmap)
+{
+	S390_lowcore.gmap = 0UL;
+}
+EXPORT_SYMBOL_GPL(gmap_disable);
+
+/*
+ * gmap_alloc_table is assumed to be called with mmap_sem held
+ */
+static int gmap_alloc_table(struct gmap *gmap, unsigned long *table,
+			    unsigned long init, unsigned long gaddr)
+{
+	struct page *page;
+	unsigned long *new;
+
+	/* since we dont free the gmap table until gmap_free we can unlock */
+	page = alloc_pages(GFP_KERNEL, 2);
+	if (!page)
+		return -ENOMEM;
+	new = (unsigned long *) page_to_phys(page);
+	crst_table_init(new, init);
+	spin_lock(&gmap->mm->page_table_lock);
+	if (*table & _REGION_ENTRY_INVALID) {
+		list_add(&page->lru, &gmap->crst_list);
+		*table = (unsigned long) new | _REGION_ENTRY_LENGTH |
+			(*table & _REGION_ENTRY_TYPE_MASK);
+		page->index = gaddr;
+		page = NULL;
+	}
+	spin_unlock(&gmap->mm->page_table_lock);
+	if (page)
+		__free_pages(page, 2);
+	return 0;
+}
+
+/**
+ * __gmap_segment_gaddr - find virtual address from segment pointer
+ * @entry: pointer to a segment table entry in the guest address space
+ *
+ * Returns the virtual address in the guest address space for the segment
+ */
+static unsigned long __gmap_segment_gaddr(unsigned long *entry)
+{
+	struct page *page;
+	unsigned long offset, mask;
+
+	offset = (unsigned long) entry / sizeof(unsigned long);
+	offset = (offset & (PTRS_PER_PMD - 1)) * PMD_SIZE;
+	mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1);
+	page = virt_to_page((void *)((unsigned long) entry & mask));
+	return page->index + offset;
+}
+
+/**
+ * __gmap_unlink_by_vmaddr - unlink a single segment via a host address
+ * @gmap: pointer to the guest address space structure
+ * @vmaddr: address in the host process address space
+ *
+ * Returns 1 if a TLB flush is required
+ */
+static int __gmap_unlink_by_vmaddr(struct gmap *gmap, unsigned long vmaddr)
+{
+	unsigned long *entry;
+	int flush = 0;
+
+	spin_lock(&gmap->guest_table_lock);
+	entry = radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT);
+	if (entry) {
+		flush = (*entry != _SEGMENT_ENTRY_INVALID);
+		*entry = _SEGMENT_ENTRY_INVALID;
+	}
+	spin_unlock(&gmap->guest_table_lock);
+	return flush;
+}
+
+/**
+ * __gmap_unmap_by_gaddr - unmap a single segment via a guest address
+ * @gmap: pointer to the guest address space structure
+ * @gaddr: address in the guest address space
+ *
+ * Returns 1 if a TLB flush is required
+ */
+static int __gmap_unmap_by_gaddr(struct gmap *gmap, unsigned long gaddr)
+{
+	unsigned long vmaddr;
+
+	vmaddr = (unsigned long) radix_tree_delete(&gmap->guest_to_host,
+						   gaddr >> PMD_SHIFT);
+	return vmaddr ? __gmap_unlink_by_vmaddr(gmap, vmaddr) : 0;
+}
+
+/**
+ * gmap_unmap_segment - unmap segment from the guest address space
+ * @gmap: pointer to the guest address space structure
+ * @to: address in the guest address space
+ * @len: length of the memory area to unmap
+ *
+ * Returns 0 if the unmap succeeded, -EINVAL if not.
+ */
+int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len)
+{
+	unsigned long off;
+	int flush;
+
+	if ((to | len) & (PMD_SIZE - 1))
+		return -EINVAL;
+	if (len == 0 || to + len < to)
+		return -EINVAL;
+
+	flush = 0;
+	down_write(&gmap->mm->mmap_sem);
+	for (off = 0; off < len; off += PMD_SIZE)
+		flush |= __gmap_unmap_by_gaddr(gmap, to + off);
+	up_write(&gmap->mm->mmap_sem);
+	if (flush)
+		gmap_flush_tlb(gmap);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gmap_unmap_segment);
+
+/**
+ * gmap_map_segment - map a segment to the guest address space
+ * @gmap: pointer to the guest address space structure
+ * @from: source address in the parent address space
+ * @to: target address in the guest address space
+ * @len: length of the memory area to map
+ *
+ * Returns 0 if the mmap succeeded, -EINVAL or -ENOMEM if not.
+ */
+int gmap_map_segment(struct gmap *gmap, unsigned long from,
+		     unsigned long to, unsigned long len)
+{
+	unsigned long off;
+	int flush;
+
+	if ((from | to | len) & (PMD_SIZE - 1))
+		return -EINVAL;
+	if (len == 0 || from + len < from || to + len < to ||
+	    from + len > TASK_MAX_SIZE || to + len > gmap->asce_end)
+		return -EINVAL;
+
+	flush = 0;
+	down_write(&gmap->mm->mmap_sem);
+	for (off = 0; off < len; off += PMD_SIZE) {
+		/* Remove old translation */
+		flush |= __gmap_unmap_by_gaddr(gmap, to + off);
+		/* Store new translation */
+		if (radix_tree_insert(&gmap->guest_to_host,
+				      (to + off) >> PMD_SHIFT,
+				      (void *) from + off))
+			break;
+	}
+	up_write(&gmap->mm->mmap_sem);
+	if (flush)
+		gmap_flush_tlb(gmap);
+	if (off >= len)
+		return 0;
+	gmap_unmap_segment(gmap, to, len);
+	return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(gmap_map_segment);
+
+/**
+ * __gmap_translate - translate a guest address to a user space address
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: guest address
+ *
+ * Returns user space address which corresponds to the guest address or
+ * -EFAULT if no such mapping exists.
+ * This function does not establish potentially missing page table entries.
+ * The mmap_sem of the mm that belongs to the address space must be held
+ * when this function gets called.
+ */
+unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr)
+{
+	unsigned long vmaddr;
+
+	vmaddr = (unsigned long)
+		radix_tree_lookup(&gmap->guest_to_host, gaddr >> PMD_SHIFT);
+	return vmaddr ? (vmaddr | (gaddr & ~PMD_MASK)) : -EFAULT;
+}
+EXPORT_SYMBOL_GPL(__gmap_translate);
+
+/**
+ * gmap_translate - translate a guest address to a user space address
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: guest address
+ *
+ * Returns user space address which corresponds to the guest address or
+ * -EFAULT if no such mapping exists.
+ * This function does not establish potentially missing page table entries.
+ */
+unsigned long gmap_translate(struct gmap *gmap, unsigned long gaddr)
+{
+	unsigned long rc;
+
+	down_read(&gmap->mm->mmap_sem);
+	rc = __gmap_translate(gmap, gaddr);
+	up_read(&gmap->mm->mmap_sem);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(gmap_translate);
+
+/**
+ * gmap_unlink - disconnect a page table from the gmap shadow tables
+ * @gmap: pointer to guest mapping meta data structure
+ * @table: pointer to the host page table
+ * @vmaddr: vm address associated with the host page table
+ */
+void gmap_unlink(struct mm_struct *mm, unsigned long *table,
+		 unsigned long vmaddr)
+{
+	struct gmap *gmap;
+	int flush;
+
+	list_for_each_entry(gmap, &mm->context.gmap_list, list) {
+		flush = __gmap_unlink_by_vmaddr(gmap, vmaddr);
+		if (flush)
+			gmap_flush_tlb(gmap);
+	}
+}
+
+/**
+ * gmap_link - set up shadow page tables to connect a host to a guest address
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: guest address
+ * @vmaddr: vm address
+ *
+ * Returns 0 on success, -ENOMEM for out of memory conditions, and -EFAULT
+ * if the vm address is already mapped to a different guest segment.
+ * The mmap_sem of the mm that belongs to the address space must be held
+ * when this function gets called.
+ */
+int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
+{
+	struct mm_struct *mm;
+	unsigned long *table;
+	spinlock_t *ptl;
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	int rc;
+
+	/* Create higher level tables in the gmap page table */
+	table = gmap->table;
+	if ((gmap->asce & _ASCE_TYPE_MASK) >= _ASCE_TYPE_REGION1) {
+		table += (gaddr >> 53) & 0x7ff;
+		if ((*table & _REGION_ENTRY_INVALID) &&
+		    gmap_alloc_table(gmap, table, _REGION2_ENTRY_EMPTY,
+				     gaddr & 0xffe0000000000000UL))
+			return -ENOMEM;
+		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+	}
+	if ((gmap->asce & _ASCE_TYPE_MASK) >= _ASCE_TYPE_REGION2) {
+		table += (gaddr >> 42) & 0x7ff;
+		if ((*table & _REGION_ENTRY_INVALID) &&
+		    gmap_alloc_table(gmap, table, _REGION3_ENTRY_EMPTY,
+				     gaddr & 0xfffffc0000000000UL))
+			return -ENOMEM;
+		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+	}
+	if ((gmap->asce & _ASCE_TYPE_MASK) >= _ASCE_TYPE_REGION3) {
+		table += (gaddr >> 31) & 0x7ff;
+		if ((*table & _REGION_ENTRY_INVALID) &&
+		    gmap_alloc_table(gmap, table, _SEGMENT_ENTRY_EMPTY,
+				     gaddr & 0xffffffff80000000UL))
+			return -ENOMEM;
+		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+	}
+	table += (gaddr >> 20) & 0x7ff;
+	/* Walk the parent mm page table */
+	mm = gmap->mm;
+	pgd = pgd_offset(mm, vmaddr);
+	VM_BUG_ON(pgd_none(*pgd));
+	pud = pud_offset(pgd, vmaddr);
+	VM_BUG_ON(pud_none(*pud));
+	pmd = pmd_offset(pud, vmaddr);
+	VM_BUG_ON(pmd_none(*pmd));
+	/* large pmds cannot yet be handled */
+	if (pmd_large(*pmd))
+		return -EFAULT;
+	/* Link gmap segment table entry location to page table. */
+	rc = radix_tree_preload(GFP_KERNEL);
+	if (rc)
+		return rc;
+	ptl = pmd_lock(mm, pmd);
+	spin_lock(&gmap->guest_table_lock);
+	if (*table == _SEGMENT_ENTRY_INVALID) {
+		rc = radix_tree_insert(&gmap->host_to_guest,
+				       vmaddr >> PMD_SHIFT, table);
+		if (!rc)
+			*table = pmd_val(*pmd);
+	} else
+		rc = 0;
+	spin_unlock(&gmap->guest_table_lock);
+	spin_unlock(ptl);
+	radix_tree_preload_end();
+	return rc;
+}
+
+/**
+ * gmap_fault - resolve a fault on a guest address
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: guest address
+ * @fault_flags: flags to pass down to handle_mm_fault()
+ *
+ * Returns 0 on success, -ENOMEM for out of memory conditions, and -EFAULT
+ * if the vm address is already mapped to a different guest segment.
+ */
+int gmap_fault(struct gmap *gmap, unsigned long gaddr,
+	       unsigned int fault_flags)
+{
+	unsigned long vmaddr;
+	int rc;
+	bool unlocked;
+
+	down_read(&gmap->mm->mmap_sem);
+
+retry:
+	unlocked = false;
+	vmaddr = __gmap_translate(gmap, gaddr);
+	if (IS_ERR_VALUE(vmaddr)) {
+		rc = vmaddr;
+		goto out_up;
+	}
+	if (fixup_user_fault(current, gmap->mm, vmaddr, fault_flags,
+			     &unlocked)) {
+		rc = -EFAULT;
+		goto out_up;
+	}
+	/*
+	 * In the case that fixup_user_fault unlocked the mmap_sem during
+	 * faultin redo __gmap_translate to not race with a map/unmap_segment.
+	 */
+	if (unlocked)
+		goto retry;
+
+	rc = __gmap_link(gmap, gaddr, vmaddr);
+out_up:
+	up_read(&gmap->mm->mmap_sem);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(gmap_fault);
+
+/*
+ * this function is assumed to be called with mmap_sem held
+ */
+void __gmap_zap(struct gmap *gmap, unsigned long gaddr)
+{
+	unsigned long vmaddr;
+	spinlock_t *ptl;
+	pte_t *ptep;
+
+	/* Find the vm address for the guest address */
+	vmaddr = (unsigned long) radix_tree_lookup(&gmap->guest_to_host,
+						   gaddr >> PMD_SHIFT);
+	if (vmaddr) {
+		vmaddr |= gaddr & ~PMD_MASK;
+		/* Get pointer to the page table entry */
+		ptep = get_locked_pte(gmap->mm, vmaddr, &ptl);
+		if (likely(ptep))
+			ptep_zap_unused(gmap->mm, vmaddr, ptep, 0);
+		pte_unmap_unlock(ptep, ptl);
+	}
+}
+EXPORT_SYMBOL_GPL(__gmap_zap);
+
+void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to)
+{
+	unsigned long gaddr, vmaddr, size;
+	struct vm_area_struct *vma;
+
+	down_read(&gmap->mm->mmap_sem);
+	for (gaddr = from; gaddr < to;
+	     gaddr = (gaddr + PMD_SIZE) & PMD_MASK) {
+		/* Find the vm address for the guest address */
+		vmaddr = (unsigned long)
+			radix_tree_lookup(&gmap->guest_to_host,
+					  gaddr >> PMD_SHIFT);
+		if (!vmaddr)
+			continue;
+		vmaddr |= gaddr & ~PMD_MASK;
+		/* Find vma in the parent mm */
+		vma = find_vma(gmap->mm, vmaddr);
+		size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK));
+		zap_page_range(vma, vmaddr, size, NULL);
+	}
+	up_read(&gmap->mm->mmap_sem);
+}
+EXPORT_SYMBOL_GPL(gmap_discard);
+
+static LIST_HEAD(gmap_notifier_list);
+static DEFINE_SPINLOCK(gmap_notifier_lock);
+
+/**
+ * gmap_register_ipte_notifier - register a pte invalidation callback
+ * @nb: pointer to the gmap notifier block
+ */
+void gmap_register_ipte_notifier(struct gmap_notifier *nb)
+{
+	spin_lock(&gmap_notifier_lock);
+	list_add(&nb->list, &gmap_notifier_list);
+	spin_unlock(&gmap_notifier_lock);
+}
+EXPORT_SYMBOL_GPL(gmap_register_ipte_notifier);
+
+/**
+ * gmap_unregister_ipte_notifier - remove a pte invalidation callback
+ * @nb: pointer to the gmap notifier block
+ */
+void gmap_unregister_ipte_notifier(struct gmap_notifier *nb)
+{
+	spin_lock(&gmap_notifier_lock);
+	list_del_init(&nb->list);
+	spin_unlock(&gmap_notifier_lock);
+}
+EXPORT_SYMBOL_GPL(gmap_unregister_ipte_notifier);
+
+/**
+ * gmap_ipte_notify - mark a range of ptes for invalidation notification
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ * @len: size of area
+ *
+ * Returns 0 if for each page in the given range a gmap mapping exists and
+ * the invalidation notification could be set. If the gmap mapping is missing
+ * for one or more pages -EFAULT is returned. If no memory could be allocated
+ * -ENOMEM is returned. This function establishes missing page table entries.
+ */
+int gmap_ipte_notify(struct gmap *gmap, unsigned long gaddr, unsigned long len)
+{
+	unsigned long addr;
+	spinlock_t *ptl;
+	pte_t *ptep;
+	bool unlocked;
+	int rc = 0;
+
+	if ((gaddr & ~PAGE_MASK) || (len & ~PAGE_MASK))
+		return -EINVAL;
+	down_read(&gmap->mm->mmap_sem);
+	while (len) {
+		unlocked = false;
+		/* Convert gmap address and connect the page tables */
+		addr = __gmap_translate(gmap, gaddr);
+		if (IS_ERR_VALUE(addr)) {
+			rc = addr;
+			break;
+		}
+		/* Get the page mapped */
+		if (fixup_user_fault(current, gmap->mm, addr, FAULT_FLAG_WRITE,
+				     &unlocked)) {
+			rc = -EFAULT;
+			break;
+		}
+		/* While trying to map mmap_sem got unlocked. Let us retry */
+		if (unlocked)
+			continue;
+		rc = __gmap_link(gmap, gaddr, addr);
+		if (rc)
+			break;
+		/* Walk the process page table, lock and get pte pointer */
+		ptep = get_locked_pte(gmap->mm, addr, &ptl);
+		VM_BUG_ON(!ptep);
+		/* Set notification bit in the pgste of the pte */
+		if ((pte_val(*ptep) & (_PAGE_INVALID | _PAGE_PROTECT)) == 0) {
+			ptep_set_notify(gmap->mm, addr, ptep);
+			gaddr += PAGE_SIZE;
+			len -= PAGE_SIZE;
+		}
+		pte_unmap_unlock(ptep, ptl);
+	}
+	up_read(&gmap->mm->mmap_sem);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(gmap_ipte_notify);
+
+/**
+ * ptep_notify - call all invalidation callbacks for a specific pte.
+ * @mm: pointer to the process mm_struct
+ * @addr: virtual address in the process address space
+ * @pte: pointer to the page table entry
+ *
+ * This function is assumed to be called with the page table lock held
+ * for the pte to notify.
+ */
+void ptep_notify(struct mm_struct *mm, unsigned long vmaddr, pte_t *pte)
+{
+	unsigned long offset, gaddr;
+	unsigned long *table;
+	struct gmap_notifier *nb;
+	struct gmap *gmap;
+
+	offset = ((unsigned long) pte) & (255 * sizeof(pte_t));
+	offset = offset * (4096 / sizeof(pte_t));
+	spin_lock(&gmap_notifier_lock);
+	list_for_each_entry(gmap, &mm->context.gmap_list, list) {
+		table = radix_tree_lookup(&gmap->host_to_guest,
+					  vmaddr >> PMD_SHIFT);
+		if (!table)
+			continue;
+		gaddr = __gmap_segment_gaddr(table) + offset;
+		list_for_each_entry(nb, &gmap_notifier_list, list)
+			nb->notifier_call(gmap, gaddr);
+	}
+	spin_unlock(&gmap_notifier_lock);
+}
+EXPORT_SYMBOL_GPL(ptep_notify);
+
+static inline void thp_split_mm(struct mm_struct *mm)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	struct vm_area_struct *vma;
+	unsigned long addr;
+
+	for (vma = mm->mmap; vma != NULL; vma = vma->vm_next) {
+		for (addr = vma->vm_start;
+		     addr < vma->vm_end;
+		     addr += PAGE_SIZE)
+			follow_page(vma, addr, FOLL_SPLIT);
+		vma->vm_flags &= ~VM_HUGEPAGE;
+		vma->vm_flags |= VM_NOHUGEPAGE;
+	}
+	mm->def_flags |= VM_NOHUGEPAGE;
+#endif
+}
+
+/*
+ * switch on pgstes for its userspace process (for kvm)
+ */
+int s390_enable_sie(void)
+{
+	struct mm_struct *mm = current->mm;
+
+	/* Do we have pgstes? if yes, we are done */
+	if (mm_has_pgste(mm))
+		return 0;
+	/* Fail if the page tables are 2K */
+	if (!mm_alloc_pgste(mm))
+		return -EINVAL;
+	down_write(&mm->mmap_sem);
+	mm->context.has_pgste = 1;
+	/* split thp mappings and disable thp for future mappings */
+	thp_split_mm(mm);
+	up_write(&mm->mmap_sem);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(s390_enable_sie);
+
+/*
+ * Enable storage key handling from now on and initialize the storage
+ * keys with the default key.
+ */
+static int __s390_enable_skey(pte_t *pte, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	/*
+	 * Remove all zero page mappings,
+	 * after establishing a policy to forbid zero page mappings
+	 * following faults for that page will get fresh anonymous pages
+	 */
+	if (is_zero_pfn(pte_pfn(*pte)))
+		ptep_xchg_direct(walk->mm, addr, pte, __pte(_PAGE_INVALID));
+	/* Clear storage key */
+	ptep_zap_key(walk->mm, addr, pte);
+	return 0;
+}
+
+int s390_enable_skey(void)
+{
+	struct mm_walk walk = { .pte_entry = __s390_enable_skey };
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	int rc = 0;
+
+	down_write(&mm->mmap_sem);
+	if (mm_use_skey(mm))
+		goto out_up;
+
+	mm->context.use_skey = 1;
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		if (ksm_madvise(vma, vma->vm_start, vma->vm_end,
+				MADV_UNMERGEABLE, &vma->vm_flags)) {
+			mm->context.use_skey = 0;
+			rc = -ENOMEM;
+			goto out_up;
+		}
+	}
+	mm->def_flags &= ~VM_MERGEABLE;
+
+	walk.mm = mm;
+	walk_page_range(0, TASK_SIZE, &walk);
+
+out_up:
+	up_write(&mm->mmap_sem);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(s390_enable_skey);
+
+/*
+ * Reset CMMA state, make all pages stable again.
+ */
+static int __s390_reset_cmma(pte_t *pte, unsigned long addr,
+			     unsigned long next, struct mm_walk *walk)
+{
+	ptep_zap_unused(walk->mm, addr, pte, 1);
+	return 0;
+}
+
+void s390_reset_cmma(struct mm_struct *mm)
+{
+	struct mm_walk walk = { .pte_entry = __s390_reset_cmma };
+
+	down_write(&mm->mmap_sem);
+	walk.mm = mm;
+	walk_page_range(0, TASK_SIZE, &walk);
+	up_write(&mm->mmap_sem);
+}
+EXPORT_SYMBOL_GPL(s390_reset_cmma);
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index f81096b6940d..1b5e8983f4f3 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -105,11 +105,10 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr, pte_t *ptep)
 {
 	pmd_t *pmdp = (pmd_t *) ptep;
-	pte_t pte = huge_ptep_get(ptep);
+	pmd_t old;
 
-	pmdp_flush_direct(mm, addr, pmdp);
-	pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY;
-	return pte;
+	old = pmdp_xchg_direct(mm, addr, pmdp, __pmd(_SEGMENT_ENTRY_EMPTY));
+	return __pmd_to_pte(old);
 }
 
 pte_t *huge_pte_alloc(struct mm_struct *mm,
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index fec59c067d0d..792f9c63fbca 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -93,15 +93,19 @@ static int __memcpy_real(void *dest, void *src, size_t count)
  */
 int memcpy_real(void *dest, void *src, size_t count)
 {
+	int irqs_disabled, rc;
 	unsigned long flags;
-	int rc;
 
 	if (!count)
 		return 0;
-	local_irq_save(flags);
-	__arch_local_irq_stnsm(0xfbUL);
+	flags = __arch_local_irq_stnsm(0xf8UL);
+	irqs_disabled = arch_irqs_disabled_flags(flags);
+	if (!irqs_disabled)
+		trace_hardirqs_off();
 	rc = __memcpy_real(dest, src, count);
-	local_irq_restore(flags);
+	if (!irqs_disabled)
+		trace_hardirqs_on();
+	__arch_local_irq_ssm(flags);
 	return rc;
 }
 
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index 749c98407b41..f2a5c29a97e9 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -65,19 +65,17 @@ static pte_t *walk_page_table(unsigned long addr)
 static void change_page_attr(unsigned long addr, int numpages,
 			     pte_t (*set) (pte_t))
 {
-	pte_t *ptep, pte;
+	pte_t *ptep;
 	int i;
 
 	for (i = 0; i < numpages; i++) {
 		ptep = walk_page_table(addr);
 		if (WARN_ON_ONCE(!ptep))
 			break;
-		pte = *ptep;
-		pte = set(pte);
-		__ptep_ipte(addr, ptep);
-		*ptep = pte;
+		*ptep = set(*ptep);
 		addr += PAGE_SIZE;
 	}
+	__tlb_flush_kernel();
 }
 
 int set_memory_ro(unsigned long addr, int numpages)
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
new file mode 100644
index 000000000000..f6c3de26cda8
--- /dev/null
+++ b/arch/s390/mm/pgalloc.c
@@ -0,0 +1,360 @@
+/*
+ *  Page table allocation functions
+ *
+ *    Copyright IBM Corp. 2016
+ *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#include <linux/mm.h>
+#include <linux/sysctl.h>
+#include <asm/mmu_context.h>
+#include <asm/pgalloc.h>
+#include <asm/gmap.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+
+#ifdef CONFIG_PGSTE
+
+static int page_table_allocate_pgste_min = 0;
+static int page_table_allocate_pgste_max = 1;
+int page_table_allocate_pgste = 0;
+EXPORT_SYMBOL(page_table_allocate_pgste);
+
+static struct ctl_table page_table_sysctl[] = {
+	{
+		.procname	= "allocate_pgste",
+		.data		= &page_table_allocate_pgste,
+		.maxlen		= sizeof(int),
+		.mode		= S_IRUGO | S_IWUSR,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &page_table_allocate_pgste_min,
+		.extra2		= &page_table_allocate_pgste_max,
+	},
+	{ }
+};
+
+static struct ctl_table page_table_sysctl_dir[] = {
+	{
+		.procname	= "vm",
+		.maxlen		= 0,
+		.mode		= 0555,
+		.child		= page_table_sysctl,
+	},
+	{ }
+};
+
+static int __init page_table_register_sysctl(void)
+{
+	return register_sysctl_table(page_table_sysctl_dir) ? 0 : -ENOMEM;
+}
+__initcall(page_table_register_sysctl);
+
+#endif /* CONFIG_PGSTE */
+
+unsigned long *crst_table_alloc(struct mm_struct *mm)
+{
+	struct page *page = alloc_pages(GFP_KERNEL, 2);
+
+	if (!page)
+		return NULL;
+	return (unsigned long *) page_to_phys(page);
+}
+
+void crst_table_free(struct mm_struct *mm, unsigned long *table)
+{
+	free_pages((unsigned long) table, 2);
+}
+
+static void __crst_table_upgrade(void *arg)
+{
+	struct mm_struct *mm = arg;
+
+	if (current->active_mm == mm) {
+		clear_user_asce();
+		set_user_asce(mm);
+	}
+	__tlb_flush_local();
+}
+
+int crst_table_upgrade(struct mm_struct *mm, unsigned long limit)
+{
+	unsigned long *table, *pgd;
+	unsigned long entry;
+	int flush;
+
+	BUG_ON(limit > TASK_MAX_SIZE);
+	flush = 0;
+repeat:
+	table = crst_table_alloc(mm);
+	if (!table)
+		return -ENOMEM;
+	spin_lock_bh(&mm->page_table_lock);
+	if (mm->context.asce_limit < limit) {
+		pgd = (unsigned long *) mm->pgd;
+		if (mm->context.asce_limit <= (1UL << 31)) {
+			entry = _REGION3_ENTRY_EMPTY;
+			mm->context.asce_limit = 1UL << 42;
+			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
+						_ASCE_USER_BITS |
+						_ASCE_TYPE_REGION3;
+		} else {
+			entry = _REGION2_ENTRY_EMPTY;
+			mm->context.asce_limit = 1UL << 53;
+			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
+						_ASCE_USER_BITS |
+						_ASCE_TYPE_REGION2;
+		}
+		crst_table_init(table, entry);
+		pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd);
+		mm->pgd = (pgd_t *) table;
+		mm->task_size = mm->context.asce_limit;
+		table = NULL;
+		flush = 1;
+	}
+	spin_unlock_bh(&mm->page_table_lock);
+	if (table)
+		crst_table_free(mm, table);
+	if (mm->context.asce_limit < limit)
+		goto repeat;
+	if (flush)
+		on_each_cpu(__crst_table_upgrade, mm, 0);
+	return 0;
+}
+
+void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
+{
+	pgd_t *pgd;
+
+	if (current->active_mm == mm) {
+		clear_user_asce();
+		__tlb_flush_mm(mm);
+	}
+	while (mm->context.asce_limit > limit) {
+		pgd = mm->pgd;
+		switch (pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) {
+		case _REGION_ENTRY_TYPE_R2:
+			mm->context.asce_limit = 1UL << 42;
+			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
+						_ASCE_USER_BITS |
+						_ASCE_TYPE_REGION3;
+			break;
+		case _REGION_ENTRY_TYPE_R3:
+			mm->context.asce_limit = 1UL << 31;
+			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
+						_ASCE_USER_BITS |
+						_ASCE_TYPE_SEGMENT;
+			break;
+		default:
+			BUG();
+		}
+		mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN);
+		mm->task_size = mm->context.asce_limit;
+		crst_table_free(mm, (unsigned long *) pgd);
+	}
+	if (current->active_mm == mm)
+		set_user_asce(mm);
+}
+
+static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits)
+{
+	unsigned int old, new;
+
+	do {
+		old = atomic_read(v);
+		new = old ^ bits;
+	} while (atomic_cmpxchg(v, old, new) != old);
+	return new;
+}
+
+/*
+ * page table entry allocation/free routines.
+ */
+unsigned long *page_table_alloc(struct mm_struct *mm)
+{
+	unsigned long *table;
+	struct page *page;
+	unsigned int mask, bit;
+
+	/* Try to get a fragment of a 4K page as a 2K page table */
+	if (!mm_alloc_pgste(mm)) {
+		table = NULL;
+		spin_lock_bh(&mm->context.list_lock);
+		if (!list_empty(&mm->context.pgtable_list)) {
+			page = list_first_entry(&mm->context.pgtable_list,
+						struct page, lru);
+			mask = atomic_read(&page->_mapcount);
+			mask = (mask | (mask >> 4)) & 3;
+			if (mask != 3) {
+				table = (unsigned long *) page_to_phys(page);
+				bit = mask & 1;		/* =1 -> second 2K */
+				if (bit)
+					table += PTRS_PER_PTE;
+				atomic_xor_bits(&page->_mapcount, 1U << bit);
+				list_del(&page->lru);
+			}
+		}
+		spin_unlock_bh(&mm->context.list_lock);
+		if (table)
+			return table;
+	}
+	/* Allocate a fresh page */
+	page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
+	if (!page)
+		return NULL;
+	if (!pgtable_page_ctor(page)) {
+		__free_page(page);
+		return NULL;
+	}
+	/* Initialize page table */
+	table = (unsigned long *) page_to_phys(page);
+	if (mm_alloc_pgste(mm)) {
+		/* Return 4K page table with PGSTEs */
+		atomic_set(&page->_mapcount, 3);
+		clear_table(table, _PAGE_INVALID, PAGE_SIZE/2);
+		clear_table(table + PTRS_PER_PTE, 0, PAGE_SIZE/2);
+	} else {
+		/* Return the first 2K fragment of the page */
+		atomic_set(&page->_mapcount, 1);
+		clear_table(table, _PAGE_INVALID, PAGE_SIZE);
+		spin_lock_bh(&mm->context.list_lock);
+		list_add(&page->lru, &mm->context.pgtable_list);
+		spin_unlock_bh(&mm->context.list_lock);
+	}
+	return table;
+}
+
+void page_table_free(struct mm_struct *mm, unsigned long *table)
+{
+	struct page *page;
+	unsigned int bit, mask;
+
+	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+	if (!mm_alloc_pgste(mm)) {
+		/* Free 2K page table fragment of a 4K page */
+		bit = (__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t));
+		spin_lock_bh(&mm->context.list_lock);
+		mask = atomic_xor_bits(&page->_mapcount, 1U << bit);
+		if (mask & 3)
+			list_add(&page->lru, &mm->context.pgtable_list);
+		else
+			list_del(&page->lru);
+		spin_unlock_bh(&mm->context.list_lock);
+		if (mask != 0)
+			return;
+	}
+
+	pgtable_page_dtor(page);
+	atomic_set(&page->_mapcount, -1);
+	__free_page(page);
+}
+
+void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table,
+			 unsigned long vmaddr)
+{
+	struct mm_struct *mm;
+	struct page *page;
+	unsigned int bit, mask;
+
+	mm = tlb->mm;
+	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+	if (mm_alloc_pgste(mm)) {
+		gmap_unlink(mm, table, vmaddr);
+		table = (unsigned long *) (__pa(table) | 3);
+		tlb_remove_table(tlb, table);
+		return;
+	}
+	bit = (__pa(table) & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t));
+	spin_lock_bh(&mm->context.list_lock);
+	mask = atomic_xor_bits(&page->_mapcount, 0x11U << bit);
+	if (mask & 3)
+		list_add_tail(&page->lru, &mm->context.pgtable_list);
+	else
+		list_del(&page->lru);
+	spin_unlock_bh(&mm->context.list_lock);
+	table = (unsigned long *) (__pa(table) | (1U << bit));
+	tlb_remove_table(tlb, table);
+}
+
+static void __tlb_remove_table(void *_table)
+{
+	unsigned int mask = (unsigned long) _table & 3;
+	void *table = (void *)((unsigned long) _table ^ mask);
+	struct page *page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+
+	switch (mask) {
+	case 0:		/* pmd or pud */
+		free_pages((unsigned long) table, 2);
+		break;
+	case 1:		/* lower 2K of a 4K page table */
+	case 2:		/* higher 2K of a 4K page table */
+		if (atomic_xor_bits(&page->_mapcount, mask << 4) != 0)
+			break;
+		/* fallthrough */
+	case 3:		/* 4K page table with pgstes */
+		pgtable_page_dtor(page);
+		atomic_set(&page->_mapcount, -1);
+		__free_page(page);
+		break;
+	}
+}
+
+static void tlb_remove_table_smp_sync(void *arg)
+{
+	/* Simply deliver the interrupt */
+}
+
+static void tlb_remove_table_one(void *table)
+{
+	/*
+	 * This isn't an RCU grace period and hence the page-tables cannot be
+	 * assumed to be actually RCU-freed.
+	 *
+	 * It is however sufficient for software page-table walkers that rely
+	 * on IRQ disabling. See the comment near struct mmu_table_batch.
+	 */
+	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
+	__tlb_remove_table(table);
+}
+
+static void tlb_remove_table_rcu(struct rcu_head *head)
+{
+	struct mmu_table_batch *batch;
+	int i;
+
+	batch = container_of(head, struct mmu_table_batch, rcu);
+
+	for (i = 0; i < batch->nr; i++)
+		__tlb_remove_table(batch->tables[i]);
+
+	free_page((unsigned long)batch);
+}
+
+void tlb_table_flush(struct mmu_gather *tlb)
+{
+	struct mmu_table_batch **batch = &tlb->batch;
+
+	if (*batch) {
+		call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
+		*batch = NULL;
+	}
+}
+
+void tlb_remove_table(struct mmu_gather *tlb, void *table)
+{
+	struct mmu_table_batch **batch = &tlb->batch;
+
+	tlb->mm->context.flush_mm = 1;
+	if (*batch == NULL) {
+		*batch = (struct mmu_table_batch *)
+			__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
+		if (*batch == NULL) {
+			__tlb_flush_mm_lazy(tlb->mm);
+			tlb_remove_table_one(table);
+			return;
+		}
+		(*batch)->nr = 0;
+	}
+	(*batch)->tables[(*batch)->nr++] = table;
+	if ((*batch)->nr == MAX_TABLE_BATCH)
+		tlb_flush_mmu(tlb);
+}
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 5109827883ac..4324b87f9398 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -24,591 +24,397 @@
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
 
-unsigned long *crst_table_alloc(struct mm_struct *mm)
-{
-	struct page *page = alloc_pages(GFP_KERNEL, 2);
-
-	if (!page)
-		return NULL;
-	return (unsigned long *) page_to_phys(page);
+static inline pte_t ptep_flush_direct(struct mm_struct *mm,
+				      unsigned long addr, pte_t *ptep)
+{
+	int active, count;
+	pte_t old;
+
+	old = *ptep;
+	if (unlikely(pte_val(old) & _PAGE_INVALID))
+		return old;
+	active = (mm == current->active_mm) ? 1 : 0;
+	count = atomic_add_return(0x10000, &mm->context.attach_count);
+	if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
+	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
+		__ptep_ipte_local(addr, ptep);
+	else
+		__ptep_ipte(addr, ptep);
+	atomic_sub(0x10000, &mm->context.attach_count);
+	return old;
 }
 
-void crst_table_free(struct mm_struct *mm, unsigned long *table)
+static inline pte_t ptep_flush_lazy(struct mm_struct *mm,
+				    unsigned long addr, pte_t *ptep)
 {
-	free_pages((unsigned long) table, 2);
+	int active, count;
+	pte_t old;
+
+	old = *ptep;
+	if (unlikely(pte_val(old) & _PAGE_INVALID))
+		return old;
+	active = (mm == current->active_mm) ? 1 : 0;
+	count = atomic_add_return(0x10000, &mm->context.attach_count);
+	if ((count & 0xffff) <= active) {
+		pte_val(*ptep) |= _PAGE_INVALID;
+		mm->context.flush_mm = 1;
+	} else
+		__ptep_ipte(addr, ptep);
+	atomic_sub(0x10000, &mm->context.attach_count);
+	return old;
 }
 
-static void __crst_table_upgrade(void *arg)
+static inline pgste_t pgste_get_lock(pte_t *ptep)
 {
-	struct mm_struct *mm = arg;
+	unsigned long new = 0;
+#ifdef CONFIG_PGSTE
+	unsigned long old;
 
-	if (current->active_mm == mm) {
-		clear_user_asce();
-		set_user_asce(mm);
-	}
-	__tlb_flush_local();
+	preempt_disable();
+	asm(
+		"	lg	%0,%2\n"
+		"0:	lgr	%1,%0\n"
+		"	nihh	%0,0xff7f\n"	/* clear PCL bit in old */
+		"	oihh	%1,0x0080\n"	/* set PCL bit in new */
+		"	csg	%0,%1,%2\n"
+		"	jl	0b\n"
+		: "=&d" (old), "=&d" (new), "=Q" (ptep[PTRS_PER_PTE])
+		: "Q" (ptep[PTRS_PER_PTE]) : "cc", "memory");
+#endif
+	return __pgste(new);
 }
 
-int crst_table_upgrade(struct mm_struct *mm, unsigned long limit)
+static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste)
 {
-	unsigned long *table, *pgd;
-	unsigned long entry;
-	int flush;
-
-	BUG_ON(limit > TASK_MAX_SIZE);
-	flush = 0;
-repeat:
-	table = crst_table_alloc(mm);
-	if (!table)
-		return -ENOMEM;
-	spin_lock_bh(&mm->page_table_lock);
-	if (mm->context.asce_limit < limit) {
-		pgd = (unsigned long *) mm->pgd;
-		if (mm->context.asce_limit <= (1UL << 31)) {
-			entry = _REGION3_ENTRY_EMPTY;
-			mm->context.asce_limit = 1UL << 42;
-			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-						_ASCE_USER_BITS |
-						_ASCE_TYPE_REGION3;
-		} else {
-			entry = _REGION2_ENTRY_EMPTY;
-			mm->context.asce_limit = 1UL << 53;
-			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-						_ASCE_USER_BITS |
-						_ASCE_TYPE_REGION2;
-		}
-		crst_table_init(table, entry);
-		pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd);
-		mm->pgd = (pgd_t *) table;
-		mm->task_size = mm->context.asce_limit;
-		table = NULL;
-		flush = 1;
-	}
-	spin_unlock_bh(&mm->page_table_lock);
-	if (table)
-		crst_table_free(mm, table);
-	if (mm->context.asce_limit < limit)
-		goto repeat;
-	if (flush)
-		on_each_cpu(__crst_table_upgrade, mm, 0);
-	return 0;
+#ifdef CONFIG_PGSTE
+	asm(
+		"	nihh	%1,0xff7f\n"	/* clear PCL bit */
+		"	stg	%1,%0\n"
+		: "=Q" (ptep[PTRS_PER_PTE])
+		: "d" (pgste_val(pgste)), "Q" (ptep[PTRS_PER_PTE])
+		: "cc", "memory");
+	preempt_enable();
+#endif
 }
 
-void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
+static inline pgste_t pgste_get(pte_t *ptep)
 {
-	pgd_t *pgd;
-
-	if (current->active_mm == mm) {
-		clear_user_asce();
-		__tlb_flush_mm(mm);
-	}
-	while (mm->context.asce_limit > limit) {
-		pgd = mm->pgd;
-		switch (pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) {
-		case _REGION_ENTRY_TYPE_R2:
-			mm->context.asce_limit = 1UL << 42;
-			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-						_ASCE_USER_BITS |
-						_ASCE_TYPE_REGION3;
-			break;
-		case _REGION_ENTRY_TYPE_R3:
-			mm->context.asce_limit = 1UL << 31;
-			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
-						_ASCE_USER_BITS |
-						_ASCE_TYPE_SEGMENT;
-			break;
-		default:
-			BUG();
-		}
-		mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN);
-		mm->task_size = mm->context.asce_limit;
-		crst_table_free(mm, (unsigned long *) pgd);
-	}
-	if (current->active_mm == mm)
-		set_user_asce(mm);
+	unsigned long pgste = 0;
+#ifdef CONFIG_PGSTE
+	pgste = *(unsigned long *)(ptep + PTRS_PER_PTE);
+#endif
+	return __pgste(pgste);
 }
 
+static inline void pgste_set(pte_t *ptep, pgste_t pgste)
+{
 #ifdef CONFIG_PGSTE
+	*(pgste_t *)(ptep + PTRS_PER_PTE) = pgste;
+#endif
+}
 
-/**
- * gmap_alloc - allocate a guest address space
- * @mm: pointer to the parent mm_struct
- * @limit: maximum address of the gmap address space
- *
- * Returns a guest address space structure.
- */
-struct gmap *gmap_alloc(struct mm_struct *mm, unsigned long limit)
+static inline pgste_t pgste_update_all(pte_t pte, pgste_t pgste,
+				       struct mm_struct *mm)
 {
-	struct gmap *gmap;
-	struct page *page;
-	unsigned long *table;
-	unsigned long etype, atype;
-
-	if (limit < (1UL << 31)) {
-		limit = (1UL << 31) - 1;
-		atype = _ASCE_TYPE_SEGMENT;
-		etype = _SEGMENT_ENTRY_EMPTY;
-	} else if (limit < (1UL << 42)) {
-		limit = (1UL << 42) - 1;
-		atype = _ASCE_TYPE_REGION3;
-		etype = _REGION3_ENTRY_EMPTY;
-	} else if (limit < (1UL << 53)) {
-		limit = (1UL << 53) - 1;
-		atype = _ASCE_TYPE_REGION2;
-		etype = _REGION2_ENTRY_EMPTY;
-	} else {
-		limit = -1UL;
-		atype = _ASCE_TYPE_REGION1;
-		etype = _REGION1_ENTRY_EMPTY;
-	}
-	gmap = kzalloc(sizeof(struct gmap), GFP_KERNEL);
-	if (!gmap)
-		goto out;
-	INIT_LIST_HEAD(&gmap->crst_list);
-	INIT_RADIX_TREE(&gmap->guest_to_host, GFP_KERNEL);
-	INIT_RADIX_TREE(&gmap->host_to_guest, GFP_ATOMIC);
-	spin_lock_init(&gmap->guest_table_lock);
-	gmap->mm = mm;
-	page = alloc_pages(GFP_KERNEL, 2);
-	if (!page)
-		goto out_free;
-	page->index = 0;
-	list_add(&page->lru, &gmap->crst_list);
-	table = (unsigned long *) page_to_phys(page);
-	crst_table_init(table, etype);
-	gmap->table = table;
-	gmap->asce = atype | _ASCE_TABLE_LENGTH |
-		_ASCE_USER_BITS | __pa(table);
-	gmap->asce_end = limit;
-	down_write(&mm->mmap_sem);
-	list_add(&gmap->list, &mm->context.gmap_list);
-	up_write(&mm->mmap_sem);
-	return gmap;
-
-out_free:
-	kfree(gmap);
-out:
-	return NULL;
+#ifdef CONFIG_PGSTE
+	unsigned long address, bits, skey;
+
+	if (!mm_use_skey(mm) || pte_val(pte) & _PAGE_INVALID)
+		return pgste;
+	address = pte_val(pte) & PAGE_MASK;
+	skey = (unsigned long) page_get_storage_key(address);
+	bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
+	/* Transfer page changed & referenced bit to guest bits in pgste */
+	pgste_val(pgste) |= bits << 48;		/* GR bit & GC bit */
+	/* Copy page access key and fetch protection bit to pgste */
+	pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT);
+	pgste_val(pgste) |= (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
+#endif
+	return pgste;
+
 }
-EXPORT_SYMBOL_GPL(gmap_alloc);
 
-static void gmap_flush_tlb(struct gmap *gmap)
+static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry,
+				 struct mm_struct *mm)
 {
-	if (MACHINE_HAS_IDTE)
-		__tlb_flush_asce(gmap->mm, gmap->asce);
-	else
-		__tlb_flush_global();
+#ifdef CONFIG_PGSTE
+	unsigned long address;
+	unsigned long nkey;
+
+	if (!mm_use_skey(mm) || pte_val(entry) & _PAGE_INVALID)
+		return;
+	VM_BUG_ON(!(pte_val(*ptep) & _PAGE_INVALID));
+	address = pte_val(entry) & PAGE_MASK;
+	/*
+	 * Set page access key and fetch protection bit from pgste.
+	 * The guest C/R information is still in the PGSTE, set real
+	 * key C/R to 0.
+	 */
+	nkey = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
+	nkey |= (pgste_val(pgste) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 48;
+	page_set_storage_key(address, nkey, 0);
+#endif
 }
 
-static void gmap_radix_tree_free(struct radix_tree_root *root)
+static inline pgste_t pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry)
 {
-	struct radix_tree_iter iter;
-	unsigned long indices[16];
-	unsigned long index;
-	void **slot;
-	int i, nr;
-
-	/* A radix tree is freed by deleting all of its entries */
-	index = 0;
-	do {
-		nr = 0;
-		radix_tree_for_each_slot(slot, root, &iter, index) {
-			indices[nr] = iter.index;
-			if (++nr == 16)
-				break;
-		}
-		for (i = 0; i < nr; i++) {
-			index = indices[i];
-			radix_tree_delete(root, index);
+#ifdef CONFIG_PGSTE
+	if ((pte_val(entry) & _PAGE_PRESENT) &&
+	    (pte_val(entry) & _PAGE_WRITE) &&
+	    !(pte_val(entry) & _PAGE_INVALID)) {
+		if (!MACHINE_HAS_ESOP) {
+			/*
+			 * Without enhanced suppression-on-protection force
+			 * the dirty bit on for all writable ptes.
+			 */
+			pte_val(entry) |= _PAGE_DIRTY;
+			pte_val(entry) &= ~_PAGE_PROTECT;
 		}
-	} while (nr > 0);
+		if (!(pte_val(entry) & _PAGE_PROTECT))
+			/* This pte allows write access, set user-dirty */
+			pgste_val(pgste) |= PGSTE_UC_BIT;
+	}
+#endif
+	*ptep = entry;
+	return pgste;
 }
 
-/**
- * gmap_free - free a guest address space
- * @gmap: pointer to the guest address space structure
- */
-void gmap_free(struct gmap *gmap)
+static inline pgste_t pgste_ipte_notify(struct mm_struct *mm,
+					unsigned long addr,
+					pte_t *ptep, pgste_t pgste)
 {
-	struct page *page, *next;
-
-	/* Flush tlb. */
-	if (MACHINE_HAS_IDTE)
-		__tlb_flush_asce(gmap->mm, gmap->asce);
-	else
-		__tlb_flush_global();
-
-	/* Free all segment & region tables. */
-	list_for_each_entry_safe(page, next, &gmap->crst_list, lru)
-		__free_pages(page, 2);
-	gmap_radix_tree_free(&gmap->guest_to_host);
-	gmap_radix_tree_free(&gmap->host_to_guest);
-	down_write(&gmap->mm->mmap_sem);
-	list_del(&gmap->list);
-	up_write(&gmap->mm->mmap_sem);
-	kfree(gmap);
+#ifdef CONFIG_PGSTE
+	if (pgste_val(pgste) & PGSTE_IN_BIT) {
+		pgste_val(pgste) &= ~PGSTE_IN_BIT;
+		ptep_notify(mm, addr, ptep);
+	}
+#endif
+	return pgste;
 }
-EXPORT_SYMBOL_GPL(gmap_free);
 
-/**
- * gmap_enable - switch primary space to the guest address space
- * @gmap: pointer to the guest address space structure
- */
-void gmap_enable(struct gmap *gmap)
+static inline pgste_t ptep_xchg_start(struct mm_struct *mm,
+				      unsigned long addr, pte_t *ptep)
 {
-	S390_lowcore.gmap = (unsigned long) gmap;
+	pgste_t pgste = __pgste(0);
+
+	if (mm_has_pgste(mm)) {
+		pgste = pgste_get_lock(ptep);
+		pgste = pgste_ipte_notify(mm, addr, ptep, pgste);
+	}
+	return pgste;
 }
-EXPORT_SYMBOL_GPL(gmap_enable);
 
-/**
- * gmap_disable - switch back to the standard primary address space
- * @gmap: pointer to the guest address space structure
- */
-void gmap_disable(struct gmap *gmap)
+static inline void ptep_xchg_commit(struct mm_struct *mm,
+				    unsigned long addr, pte_t *ptep,
+				    pgste_t pgste, pte_t old, pte_t new)
 {
-	S390_lowcore.gmap = 0UL;
+	if (mm_has_pgste(mm)) {
+		if (pte_val(old) & _PAGE_INVALID)
+			pgste_set_key(ptep, pgste, new, mm);
+		if (pte_val(new) & _PAGE_INVALID) {
+			pgste = pgste_update_all(old, pgste, mm);
+			if ((pgste_val(pgste) & _PGSTE_GPS_USAGE_MASK) ==
+			    _PGSTE_GPS_USAGE_UNUSED)
+				pte_val(old) |= _PAGE_UNUSED;
+		}
+		pgste = pgste_set_pte(ptep, pgste, new);
+		pgste_set_unlock(ptep, pgste);
+	} else {
+		*ptep = new;
+	}
 }
-EXPORT_SYMBOL_GPL(gmap_disable);
 
-/*
- * gmap_alloc_table is assumed to be called with mmap_sem held
- */
-static int gmap_alloc_table(struct gmap *gmap, unsigned long *table,
-			    unsigned long init, unsigned long gaddr)
+pte_t ptep_xchg_direct(struct mm_struct *mm, unsigned long addr,
+		       pte_t *ptep, pte_t new)
 {
-	struct page *page;
-	unsigned long *new;
-
-	/* since we dont free the gmap table until gmap_free we can unlock */
-	page = alloc_pages(GFP_KERNEL, 2);
-	if (!page)
-		return -ENOMEM;
-	new = (unsigned long *) page_to_phys(page);
-	crst_table_init(new, init);
-	spin_lock(&gmap->mm->page_table_lock);
-	if (*table & _REGION_ENTRY_INVALID) {
-		list_add(&page->lru, &gmap->crst_list);
-		*table = (unsigned long) new | _REGION_ENTRY_LENGTH |
-			(*table & _REGION_ENTRY_TYPE_MASK);
-		page->index = gaddr;
-		page = NULL;
-	}
-	spin_unlock(&gmap->mm->page_table_lock);
-	if (page)
-		__free_pages(page, 2);
-	return 0;
+	pgste_t pgste;
+	pte_t old;
+
+	pgste = ptep_xchg_start(mm, addr, ptep);
+	old = ptep_flush_direct(mm, addr, ptep);
+	ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
+	return old;
 }
+EXPORT_SYMBOL(ptep_xchg_direct);
 
-/**
- * __gmap_segment_gaddr - find virtual address from segment pointer
- * @entry: pointer to a segment table entry in the guest address space
- *
- * Returns the virtual address in the guest address space for the segment
- */
-static unsigned long __gmap_segment_gaddr(unsigned long *entry)
+pte_t ptep_xchg_lazy(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t new)
 {
-	struct page *page;
-	unsigned long offset, mask;
-
-	offset = (unsigned long) entry / sizeof(unsigned long);
-	offset = (offset & (PTRS_PER_PMD - 1)) * PMD_SIZE;
-	mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1);
-	page = virt_to_page((void *)((unsigned long) entry & mask));
-	return page->index + offset;
+	pgste_t pgste;
+	pte_t old;
+
+	pgste = ptep_xchg_start(mm, addr, ptep);
+	old = ptep_flush_lazy(mm, addr, ptep);
+	ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
+	return old;
 }
+EXPORT_SYMBOL(ptep_xchg_lazy);
 
-/**
- * __gmap_unlink_by_vmaddr - unlink a single segment via a host address
- * @gmap: pointer to the guest address space structure
- * @vmaddr: address in the host process address space
- *
- * Returns 1 if a TLB flush is required
- */
-static int __gmap_unlink_by_vmaddr(struct gmap *gmap, unsigned long vmaddr)
+pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
+			     pte_t *ptep)
 {
-	unsigned long *entry;
-	int flush = 0;
-
-	spin_lock(&gmap->guest_table_lock);
-	entry = radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT);
-	if (entry) {
-		flush = (*entry != _SEGMENT_ENTRY_INVALID);
-		*entry = _SEGMENT_ENTRY_INVALID;
+	pgste_t pgste;
+	pte_t old;
+
+	pgste = ptep_xchg_start(mm, addr, ptep);
+	old = ptep_flush_lazy(mm, addr, ptep);
+	if (mm_has_pgste(mm)) {
+		pgste = pgste_update_all(old, pgste, mm);
+		pgste_set(ptep, pgste);
 	}
-	spin_unlock(&gmap->guest_table_lock);
-	return flush;
+	return old;
 }
+EXPORT_SYMBOL(ptep_modify_prot_start);
 
-/**
- * __gmap_unmap_by_gaddr - unmap a single segment via a guest address
- * @gmap: pointer to the guest address space structure
- * @gaddr: address in the guest address space
- *
- * Returns 1 if a TLB flush is required
- */
-static int __gmap_unmap_by_gaddr(struct gmap *gmap, unsigned long gaddr)
+void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
+			     pte_t *ptep, pte_t pte)
 {
-	unsigned long vmaddr;
+	pgste_t pgste;
 
-	vmaddr = (unsigned long) radix_tree_delete(&gmap->guest_to_host,
-						   gaddr >> PMD_SHIFT);
-	return vmaddr ? __gmap_unlink_by_vmaddr(gmap, vmaddr) : 0;
+	if (mm_has_pgste(mm)) {
+		pgste = pgste_get(ptep);
+		pgste_set_key(ptep, pgste, pte, mm);
+		pgste = pgste_set_pte(ptep, pgste, pte);
+		pgste_set_unlock(ptep, pgste);
+	} else {
+		*ptep = pte;
+	}
 }
+EXPORT_SYMBOL(ptep_modify_prot_commit);
 
-/**
- * gmap_unmap_segment - unmap segment from the guest address space
- * @gmap: pointer to the guest address space structure
- * @to: address in the guest address space
- * @len: length of the memory area to unmap
- *
- * Returns 0 if the unmap succeeded, -EINVAL if not.
- */
-int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len)
+static inline pmd_t pmdp_flush_direct(struct mm_struct *mm,
+				      unsigned long addr, pmd_t *pmdp)
 {
-	unsigned long off;
-	int flush;
-
-	if ((to | len) & (PMD_SIZE - 1))
-		return -EINVAL;
-	if (len == 0 || to + len < to)
-		return -EINVAL;
-
-	flush = 0;
-	down_write(&gmap->mm->mmap_sem);
-	for (off = 0; off < len; off += PMD_SIZE)
-		flush |= __gmap_unmap_by_gaddr(gmap, to + off);
-	up_write(&gmap->mm->mmap_sem);
-	if (flush)
-		gmap_flush_tlb(gmap);
-	return 0;
+	int active, count;
+	pmd_t old;
+
+	old = *pmdp;
+	if (pmd_val(old) & _SEGMENT_ENTRY_INVALID)
+		return old;
+	if (!MACHINE_HAS_IDTE) {
+		__pmdp_csp(pmdp);
+		return old;
+	}
+	active = (mm == current->active_mm) ? 1 : 0;
+	count = atomic_add_return(0x10000, &mm->context.attach_count);
+	if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
+	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
+		__pmdp_idte_local(addr, pmdp);
+	else
+		__pmdp_idte(addr, pmdp);
+	atomic_sub(0x10000, &mm->context.attach_count);
+	return old;
+}
+
+static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm,
+				    unsigned long addr, pmd_t *pmdp)
+{
+	int active, count;
+	pmd_t old;
+
+	old = *pmdp;
+	if (pmd_val(old) & _SEGMENT_ENTRY_INVALID)
+		return old;
+	active = (mm == current->active_mm) ? 1 : 0;
+	count = atomic_add_return(0x10000, &mm->context.attach_count);
+	if ((count & 0xffff) <= active) {
+		pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID;
+		mm->context.flush_mm = 1;
+	} else if (MACHINE_HAS_IDTE)
+		__pmdp_idte(addr, pmdp);
+	else
+		__pmdp_csp(pmdp);
+	atomic_sub(0x10000, &mm->context.attach_count);
+	return old;
 }
-EXPORT_SYMBOL_GPL(gmap_unmap_segment);
-
-/**
- * gmap_mmap_segment - map a segment to the guest address space
- * @gmap: pointer to the guest address space structure
- * @from: source address in the parent address space
- * @to: target address in the guest address space
- * @len: length of the memory area to map
- *
- * Returns 0 if the mmap succeeded, -EINVAL or -ENOMEM if not.
- */
-int gmap_map_segment(struct gmap *gmap, unsigned long from,
-		     unsigned long to, unsigned long len)
+
+pmd_t pmdp_xchg_direct(struct mm_struct *mm, unsigned long addr,
+		       pmd_t *pmdp, pmd_t new)
 {
-	unsigned long off;
-	int flush;
-
-	if ((from | to | len) & (PMD_SIZE - 1))
-		return -EINVAL;
-	if (len == 0 || from + len < from || to + len < to ||
-	    from + len - 1 > TASK_MAX_SIZE || to + len - 1 > gmap->asce_end)
-		return -EINVAL;
-
-	flush = 0;
-	down_write(&gmap->mm->mmap_sem);
-	for (off = 0; off < len; off += PMD_SIZE) {
-		/* Remove old translation */
-		flush |= __gmap_unmap_by_gaddr(gmap, to + off);
-		/* Store new translation */
-		if (radix_tree_insert(&gmap->guest_to_host,
-				      (to + off) >> PMD_SHIFT,
-				      (void *) from + off))
-			break;
-	}
-	up_write(&gmap->mm->mmap_sem);
-	if (flush)
-		gmap_flush_tlb(gmap);
-	if (off >= len)
-		return 0;
-	gmap_unmap_segment(gmap, to, len);
-	return -ENOMEM;
+	pmd_t old;
+
+	old = pmdp_flush_direct(mm, addr, pmdp);
+	*pmdp = new;
+	return old;
 }
-EXPORT_SYMBOL_GPL(gmap_map_segment);
-
-/**
- * __gmap_translate - translate a guest address to a user space address
- * @gmap: pointer to guest mapping meta data structure
- * @gaddr: guest address
- *
- * Returns user space address which corresponds to the guest address or
- * -EFAULT if no such mapping exists.
- * This function does not establish potentially missing page table entries.
- * The mmap_sem of the mm that belongs to the address space must be held
- * when this function gets called.
- */
-unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr)
+EXPORT_SYMBOL(pmdp_xchg_direct);
+
+pmd_t pmdp_xchg_lazy(struct mm_struct *mm, unsigned long addr,
+		     pmd_t *pmdp, pmd_t new)
 {
-	unsigned long vmaddr;
+	pmd_t old;
 
-	vmaddr = (unsigned long)
-		radix_tree_lookup(&gmap->guest_to_host, gaddr >> PMD_SHIFT);
-	return vmaddr ? (vmaddr | (gaddr & ~PMD_MASK)) : -EFAULT;
+	old = pmdp_flush_lazy(mm, addr, pmdp);
+	*pmdp = new;
+	return old;
 }
-EXPORT_SYMBOL_GPL(__gmap_translate);
-
-/**
- * gmap_translate - translate a guest address to a user space address
- * @gmap: pointer to guest mapping meta data structure
- * @gaddr: guest address
- *
- * Returns user space address which corresponds to the guest address or
- * -EFAULT if no such mapping exists.
- * This function does not establish potentially missing page table entries.
- */
-unsigned long gmap_translate(struct gmap *gmap, unsigned long gaddr)
+EXPORT_SYMBOL(pmdp_xchg_lazy);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				pgtable_t pgtable)
 {
-	unsigned long rc;
+	struct list_head *lh = (struct list_head *) pgtable;
 
-	down_read(&gmap->mm->mmap_sem);
-	rc = __gmap_translate(gmap, gaddr);
-	up_read(&gmap->mm->mmap_sem);
-	return rc;
+	assert_spin_locked(pmd_lockptr(mm, pmdp));
+
+	/* FIFO */
+	if (!pmd_huge_pte(mm, pmdp))
+		INIT_LIST_HEAD(lh);
+	else
+		list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp));
+	pmd_huge_pte(mm, pmdp) = pgtable;
 }
-EXPORT_SYMBOL_GPL(gmap_translate);
 
-/**
- * gmap_unlink - disconnect a page table from the gmap shadow tables
- * @gmap: pointer to guest mapping meta data structure
- * @table: pointer to the host page table
- * @vmaddr: vm address associated with the host page table
- */
-static void gmap_unlink(struct mm_struct *mm, unsigned long *table,
-			unsigned long vmaddr)
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 {
-	struct gmap *gmap;
-	int flush;
+	struct list_head *lh;
+	pgtable_t pgtable;
+	pte_t *ptep;
+
+	assert_spin_locked(pmd_lockptr(mm, pmdp));
 
-	list_for_each_entry(gmap, &mm->context.gmap_list, list) {
-		flush = __gmap_unlink_by_vmaddr(gmap, vmaddr);
-		if (flush)
-			gmap_flush_tlb(gmap);
+	/* FIFO */
+	pgtable = pmd_huge_pte(mm, pmdp);
+	lh = (struct list_head *) pgtable;
+	if (list_empty(lh))
+		pmd_huge_pte(mm, pmdp) = NULL;
+	else {
+		pmd_huge_pte(mm, pmdp) = (pgtable_t) lh->next;
+		list_del(lh);
 	}
+	ptep = (pte_t *) pgtable;
+	pte_val(*ptep) = _PAGE_INVALID;
+	ptep++;
+	pte_val(*ptep) = _PAGE_INVALID;
+	return pgtable;
 }
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-/**
- * gmap_link - set up shadow page tables to connect a host to a guest address
- * @gmap: pointer to guest mapping meta data structure
- * @gaddr: guest address
- * @vmaddr: vm address
- *
- * Returns 0 on success, -ENOMEM for out of memory conditions, and -EFAULT
- * if the vm address is already mapped to a different guest segment.
- * The mmap_sem of the mm that belongs to the address space must be held
- * when this function gets called.
- */
-int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
+#ifdef CONFIG_PGSTE
+void ptep_set_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t entry)
 {
-	struct mm_struct *mm;
-	unsigned long *table;
-	spinlock_t *ptl;
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	int rc;
-
-	/* Create higher level tables in the gmap page table */
-	table = gmap->table;
-	if ((gmap->asce & _ASCE_TYPE_MASK) >= _ASCE_TYPE_REGION1) {
-		table += (gaddr >> 53) & 0x7ff;
-		if ((*table & _REGION_ENTRY_INVALID) &&
-		    gmap_alloc_table(gmap, table, _REGION2_ENTRY_EMPTY,
-				     gaddr & 0xffe0000000000000UL))
-			return -ENOMEM;
-		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
-	}
-	if ((gmap->asce & _ASCE_TYPE_MASK) >= _ASCE_TYPE_REGION2) {
-		table += (gaddr >> 42) & 0x7ff;
-		if ((*table & _REGION_ENTRY_INVALID) &&
-		    gmap_alloc_table(gmap, table, _REGION3_ENTRY_EMPTY,
-				     gaddr & 0xfffffc0000000000UL))
-			return -ENOMEM;
-		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
-	}
-	if ((gmap->asce & _ASCE_TYPE_MASK) >= _ASCE_TYPE_REGION3) {
-		table += (gaddr >> 31) & 0x7ff;
-		if ((*table & _REGION_ENTRY_INVALID) &&
-		    gmap_alloc_table(gmap, table, _SEGMENT_ENTRY_EMPTY,
-				     gaddr & 0xffffffff80000000UL))
-			return -ENOMEM;
-		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
-	}
-	table += (gaddr >> 20) & 0x7ff;
-	/* Walk the parent mm page table */
-	mm = gmap->mm;
-	pgd = pgd_offset(mm, vmaddr);
-	VM_BUG_ON(pgd_none(*pgd));
-	pud = pud_offset(pgd, vmaddr);
-	VM_BUG_ON(pud_none(*pud));
-	pmd = pmd_offset(pud, vmaddr);
-	VM_BUG_ON(pmd_none(*pmd));
-	/* large pmds cannot yet be handled */
-	if (pmd_large(*pmd))
-		return -EFAULT;
-	/* Link gmap segment table entry location to page table. */
-	rc = radix_tree_preload(GFP_KERNEL);
-	if (rc)
-		return rc;
-	ptl = pmd_lock(mm, pmd);
-	spin_lock(&gmap->guest_table_lock);
-	if (*table == _SEGMENT_ENTRY_INVALID) {
-		rc = radix_tree_insert(&gmap->host_to_guest,
-				       vmaddr >> PMD_SHIFT, table);
-		if (!rc)
-			*table = pmd_val(*pmd);
-	} else
-		rc = 0;
-	spin_unlock(&gmap->guest_table_lock);
-	spin_unlock(ptl);
-	radix_tree_preload_end();
-	return rc;
+	pgste_t pgste;
+
+	/* the mm_has_pgste() check is done in set_pte_at() */
+	pgste = pgste_get_lock(ptep);
+	pgste_val(pgste) &= ~_PGSTE_GPS_ZERO;
+	pgste_set_key(ptep, pgste, entry, mm);
+	pgste = pgste_set_pte(ptep, pgste, entry);
+	pgste_set_unlock(ptep, pgste);
 }
 
-/**
- * gmap_fault - resolve a fault on a guest address
- * @gmap: pointer to guest mapping meta data structure
- * @gaddr: guest address
- * @fault_flags: flags to pass down to handle_mm_fault()
- *
- * Returns 0 on success, -ENOMEM for out of memory conditions, and -EFAULT
- * if the vm address is already mapped to a different guest segment.
- */
-int gmap_fault(struct gmap *gmap, unsigned long gaddr,
-	       unsigned int fault_flags)
+void ptep_set_notify(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
-	unsigned long vmaddr;
-	int rc;
-	bool unlocked;
-
-	down_read(&gmap->mm->mmap_sem);
-
-retry:
-	unlocked = false;
-	vmaddr = __gmap_translate(gmap, gaddr);
-	if (IS_ERR_VALUE(vmaddr)) {
-		rc = vmaddr;
-		goto out_up;
-	}
-	if (fixup_user_fault(current, gmap->mm, vmaddr, fault_flags,
-			     &unlocked)) {
-		rc = -EFAULT;
-		goto out_up;
-	}
-	/*
-	 * In the case that fixup_user_fault unlocked the mmap_sem during
-	 * faultin redo __gmap_translate to not race with a map/unmap_segment.
-	 */
-	if (unlocked)
-		goto retry;
+	pgste_t pgste;
 
-	rc = __gmap_link(gmap, gaddr, vmaddr);
-out_up:
-	up_read(&gmap->mm->mmap_sem);
-	return rc;
+	pgste = pgste_get_lock(ptep);
+	pgste_val(pgste) |= PGSTE_IN_BIT;
+	pgste_set_unlock(ptep, pgste);
 }
-EXPORT_SYMBOL_GPL(gmap_fault);
 
-static void gmap_zap_swap_entry(swp_entry_t entry, struct mm_struct *mm)
+static void ptep_zap_swap_entry(struct mm_struct *mm, swp_entry_t entry)
 {
 	if (!non_swap_entry(entry))
 		dec_mm_counter(mm, MM_SWAPENTS);
@@ -620,225 +426,99 @@ static void gmap_zap_swap_entry(swp_entry_t entry, struct mm_struct *mm)
 	free_swap_and_cache(entry);
 }
 
-/*
- * this function is assumed to be called with mmap_sem held
- */
-void __gmap_zap(struct gmap *gmap, unsigned long gaddr)
+void ptep_zap_unused(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, int reset)
 {
-	unsigned long vmaddr, ptev, pgstev;
-	pte_t *ptep, pte;
-	spinlock_t *ptl;
+	unsigned long pgstev;
 	pgste_t pgste;
+	pte_t pte;
 
-	/* Find the vm address for the guest address */
-	vmaddr = (unsigned long) radix_tree_lookup(&gmap->guest_to_host,
-						   gaddr >> PMD_SHIFT);
-	if (!vmaddr)
-		return;
-	vmaddr |= gaddr & ~PMD_MASK;
-	/* Get pointer to the page table entry */
-	ptep = get_locked_pte(gmap->mm, vmaddr, &ptl);
-	if (unlikely(!ptep))
-		return;
-	pte = *ptep;
-	if (!pte_swap(pte))
-		goto out_pte;
 	/* Zap unused and logically-zero pages */
 	pgste = pgste_get_lock(ptep);
 	pgstev = pgste_val(pgste);
-	ptev = pte_val(pte);
-	if (((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED) ||
-	    ((pgstev & _PGSTE_GPS_ZERO) && (ptev & _PAGE_INVALID))) {
-		gmap_zap_swap_entry(pte_to_swp_entry(pte), gmap->mm);
-		pte_clear(gmap->mm, vmaddr, ptep);
-	}
+	pte = *ptep;
+	if (pte_swap(pte) &&
+	    ((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED ||
+	     (pgstev & _PGSTE_GPS_ZERO))) {
+		ptep_zap_swap_entry(mm, pte_to_swp_entry(pte));
+		pte_clear(mm, addr, ptep);
+	}
+	if (reset)
+		pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK;
 	pgste_set_unlock(ptep, pgste);
-out_pte:
-	pte_unmap_unlock(ptep, ptl);
 }
-EXPORT_SYMBOL_GPL(__gmap_zap);
 
-void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to)
+void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
-	unsigned long gaddr, vmaddr, size;
-	struct vm_area_struct *vma;
-
-	down_read(&gmap->mm->mmap_sem);
-	for (gaddr = from; gaddr < to;
-	     gaddr = (gaddr + PMD_SIZE) & PMD_MASK) {
-		/* Find the vm address for the guest address */
-		vmaddr = (unsigned long)
-			radix_tree_lookup(&gmap->guest_to_host,
-					  gaddr >> PMD_SHIFT);
-		if (!vmaddr)
-			continue;
-		vmaddr |= gaddr & ~PMD_MASK;
-		/* Find vma in the parent mm */
-		vma = find_vma(gmap->mm, vmaddr);
-		size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK));
-		zap_page_range(vma, vmaddr, size, NULL);
-	}
-	up_read(&gmap->mm->mmap_sem);
-}
-EXPORT_SYMBOL_GPL(gmap_discard);
-
-static LIST_HEAD(gmap_notifier_list);
-static DEFINE_SPINLOCK(gmap_notifier_lock);
+	unsigned long ptev;
+	pgste_t pgste;
 
-/**
- * gmap_register_ipte_notifier - register a pte invalidation callback
- * @nb: pointer to the gmap notifier block
- */
-void gmap_register_ipte_notifier(struct gmap_notifier *nb)
-{
-	spin_lock(&gmap_notifier_lock);
-	list_add(&nb->list, &gmap_notifier_list);
-	spin_unlock(&gmap_notifier_lock);
+	/* Clear storage key */
+	pgste = pgste_get_lock(ptep);
+	pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT |
+			      PGSTE_GR_BIT | PGSTE_GC_BIT);
+	ptev = pte_val(*ptep);
+	if (!(ptev & _PAGE_INVALID) && (ptev & _PAGE_WRITE))
+		page_set_storage_key(ptev & PAGE_MASK, PAGE_DEFAULT_KEY, 1);
+	pgste_set_unlock(ptep, pgste);
 }
-EXPORT_SYMBOL_GPL(gmap_register_ipte_notifier);
 
-/**
- * gmap_unregister_ipte_notifier - remove a pte invalidation callback
- * @nb: pointer to the gmap notifier block
- */
-void gmap_unregister_ipte_notifier(struct gmap_notifier *nb)
-{
-	spin_lock(&gmap_notifier_lock);
-	list_del_init(&nb->list);
-	spin_unlock(&gmap_notifier_lock);
-}
-EXPORT_SYMBOL_GPL(gmap_unregister_ipte_notifier);
-
-/**
- * gmap_ipte_notify - mark a range of ptes for invalidation notification
- * @gmap: pointer to guest mapping meta data structure
- * @gaddr: virtual address in the guest address space
- * @len: size of area
- *
- * Returns 0 if for each page in the given range a gmap mapping exists and
- * the invalidation notification could be set. If the gmap mapping is missing
- * for one or more pages -EFAULT is returned. If no memory could be allocated
- * -ENOMEM is returned. This function establishes missing page table entries.
+/*
+ * Test and reset if a guest page is dirty
  */
-int gmap_ipte_notify(struct gmap *gmap, unsigned long gaddr, unsigned long len)
+bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr)
 {
-	unsigned long addr;
 	spinlock_t *ptl;
-	pte_t *ptep, entry;
 	pgste_t pgste;
-	bool unlocked;
-	int rc = 0;
-
-	if ((gaddr & ~PAGE_MASK) || (len & ~PAGE_MASK))
-		return -EINVAL;
-	down_read(&gmap->mm->mmap_sem);
-	while (len) {
-		unlocked = false;
-		/* Convert gmap address and connect the page tables */
-		addr = __gmap_translate(gmap, gaddr);
-		if (IS_ERR_VALUE(addr)) {
-			rc = addr;
-			break;
-		}
-		/* Get the page mapped */
-		if (fixup_user_fault(current, gmap->mm, addr, FAULT_FLAG_WRITE,
-				     &unlocked)) {
-			rc = -EFAULT;
-			break;
-		}
-		/* While trying to map mmap_sem got unlocked. Let us retry */
-		if (unlocked)
-			continue;
-		rc = __gmap_link(gmap, gaddr, addr);
-		if (rc)
-			break;
-		/* Walk the process page table, lock and get pte pointer */
-		ptep = get_locked_pte(gmap->mm, addr, &ptl);
-		VM_BUG_ON(!ptep);
-		/* Set notification bit in the pgste of the pte */
-		entry = *ptep;
-		if ((pte_val(entry) & (_PAGE_INVALID | _PAGE_PROTECT)) == 0) {
-			pgste = pgste_get_lock(ptep);
-			pgste_val(pgste) |= PGSTE_IN_BIT;
-			pgste_set_unlock(ptep, pgste);
-			gaddr += PAGE_SIZE;
-			len -= PAGE_SIZE;
-		}
-		pte_unmap_unlock(ptep, ptl);
-	}
-	up_read(&gmap->mm->mmap_sem);
-	return rc;
-}
-EXPORT_SYMBOL_GPL(gmap_ipte_notify);
-
-/**
- * gmap_do_ipte_notify - call all invalidation callbacks for a specific pte.
- * @mm: pointer to the process mm_struct
- * @addr: virtual address in the process address space
- * @pte: pointer to the page table entry
- *
- * This function is assumed to be called with the page table lock held
- * for the pte to notify.
- */
-void gmap_do_ipte_notify(struct mm_struct *mm, unsigned long vmaddr, pte_t *pte)
-{
-	unsigned long offset, gaddr;
-	unsigned long *table;
-	struct gmap_notifier *nb;
-	struct gmap *gmap;
-
-	offset = ((unsigned long) pte) & (255 * sizeof(pte_t));
-	offset = offset * (4096 / sizeof(pte_t));
-	spin_lock(&gmap_notifier_lock);
-	list_for_each_entry(gmap, &mm->context.gmap_list, list) {
-		table = radix_tree_lookup(&gmap->host_to_guest,
-					  vmaddr >> PMD_SHIFT);
-		if (!table)
-			continue;
-		gaddr = __gmap_segment_gaddr(table) + offset;
-		list_for_each_entry(nb, &gmap_notifier_list, list)
-			nb->notifier_call(gmap, gaddr);
+	pte_t *ptep;
+	pte_t pte;
+	bool dirty;
+
+	ptep = get_locked_pte(mm, addr, &ptl);
+	if (unlikely(!ptep))
+		return false;
+
+	pgste = pgste_get_lock(ptep);
+	dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT);
+	pgste_val(pgste) &= ~PGSTE_UC_BIT;
+	pte = *ptep;
+	if (dirty && (pte_val(pte) & _PAGE_PRESENT)) {
+		pgste = pgste_ipte_notify(mm, addr, ptep, pgste);
+		__ptep_ipte(addr, ptep);
+		if (MACHINE_HAS_ESOP || !(pte_val(pte) & _PAGE_WRITE))
+			pte_val(pte) |= _PAGE_PROTECT;
+		else
+			pte_val(pte) |= _PAGE_INVALID;
+		*ptep = pte;
 	}
-	spin_unlock(&gmap_notifier_lock);
+	pgste_set_unlock(ptep, pgste);
+
+	spin_unlock(ptl);
+	return dirty;
 }
-EXPORT_SYMBOL_GPL(gmap_do_ipte_notify);
+EXPORT_SYMBOL_GPL(test_and_clear_guest_dirty);
 
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
-			  unsigned long key, bool nq)
+			  unsigned char key, bool nq)
 {
+	unsigned long keyul;
 	spinlock_t *ptl;
 	pgste_t old, new;
 	pte_t *ptep;
-	bool unlocked;
 
 	down_read(&mm->mmap_sem);
-retry:
-	unlocked = false;
 	ptep = get_locked_pte(mm, addr, &ptl);
 	if (unlikely(!ptep)) {
 		up_read(&mm->mmap_sem);
 		return -EFAULT;
 	}
-	if (!(pte_val(*ptep) & _PAGE_INVALID) &&
-	     (pte_val(*ptep) & _PAGE_PROTECT)) {
-		pte_unmap_unlock(ptep, ptl);
-		/*
-		 * We do not really care about unlocked. We will retry either
-		 * way. But this allows fixup_user_fault to enable userfaultfd.
-		 */
-		if (fixup_user_fault(current, mm, addr, FAULT_FLAG_WRITE,
-				     &unlocked)) {
-			up_read(&mm->mmap_sem);
-			return -EFAULT;
-		}
-		goto retry;
-	}
 
 	new = old = pgste_get_lock(ptep);
 	pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT |
 			    PGSTE_ACC_BITS | PGSTE_FP_BIT);
-	pgste_val(new) |= (key & (_PAGE_CHANGED | _PAGE_REFERENCED)) << 48;
-	pgste_val(new) |= (key & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
+	keyul = (unsigned long) key;
+	pgste_val(new) |= (keyul & (_PAGE_CHANGED | _PAGE_REFERENCED)) << 48;
+	pgste_val(new) |= (keyul & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
 	if (!(pte_val(*ptep) & _PAGE_INVALID)) {
 		unsigned long address, bits, skey;
 
@@ -863,13 +543,12 @@ retry:
 }
 EXPORT_SYMBOL(set_guest_storage_key);
 
-unsigned long get_guest_storage_key(struct mm_struct *mm, unsigned long addr)
+unsigned char get_guest_storage_key(struct mm_struct *mm, unsigned long addr)
 {
+	unsigned char key;
 	spinlock_t *ptl;
 	pgste_t pgste;
 	pte_t *ptep;
-	uint64_t physaddr;
-	unsigned long key = 0;
 
 	down_read(&mm->mmap_sem);
 	ptep = get_locked_pte(mm, addr, &ptl);
@@ -880,13 +559,12 @@ unsigned long get_guest_storage_key(struct mm_struct *mm, unsigned long addr)
 	pgste = pgste_get_lock(ptep);
 
 	if (pte_val(*ptep) & _PAGE_INVALID) {
-		key |= (pgste_val(pgste) & PGSTE_ACC_BITS) >> 56;
+		key  = (pgste_val(pgste) & PGSTE_ACC_BITS) >> 56;
 		key |= (pgste_val(pgste) & PGSTE_FP_BIT) >> 56;
 		key |= (pgste_val(pgste) & PGSTE_GR_BIT) >> 48;
 		key |= (pgste_val(pgste) & PGSTE_GC_BIT) >> 48;
 	} else {
-		physaddr = pte_val(*ptep) & PAGE_MASK;
-		key = page_get_storage_key(physaddr);
+		key = page_get_storage_key(pte_val(*ptep) & PAGE_MASK);
 
 		/* Reflect guest's logical view, not physical */
 		if (pgste_val(pgste) & PGSTE_GR_BIT)
@@ -901,471 +579,4 @@ unsigned long get_guest_storage_key(struct mm_struct *mm, unsigned long addr)
 	return key;
 }
 EXPORT_SYMBOL(get_guest_storage_key);
-
-static int page_table_allocate_pgste_min = 0;
-static int page_table_allocate_pgste_max = 1;
-int page_table_allocate_pgste = 0;
-EXPORT_SYMBOL(page_table_allocate_pgste);
-
-static struct ctl_table page_table_sysctl[] = {
-	{
-		.procname	= "allocate_pgste",
-		.data		= &page_table_allocate_pgste,
-		.maxlen		= sizeof(int),
-		.mode		= S_IRUGO | S_IWUSR,
-		.proc_handler	= proc_dointvec,
-		.extra1		= &page_table_allocate_pgste_min,
-		.extra2		= &page_table_allocate_pgste_max,
-	},
-	{ }
-};
-
-static struct ctl_table page_table_sysctl_dir[] = {
-	{
-		.procname	= "vm",
-		.maxlen		= 0,
-		.mode		= 0555,
-		.child		= page_table_sysctl,
-	},
-	{ }
-};
-
-static int __init page_table_register_sysctl(void)
-{
-	return register_sysctl_table(page_table_sysctl_dir) ? 0 : -ENOMEM;
-}
-__initcall(page_table_register_sysctl);
-
-#else /* CONFIG_PGSTE */
-
-static inline void gmap_unlink(struct mm_struct *mm, unsigned long *table,
-			unsigned long vmaddr)
-{
-}
-
-#endif /* CONFIG_PGSTE */
-
-static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits)
-{
-	unsigned int old, new;
-
-	do {
-		old = atomic_read(v);
-		new = old ^ bits;
-	} while (atomic_cmpxchg(v, old, new) != old);
-	return new;
-}
-
-/*
- * page table entry allocation/free routines.
- */
-unsigned long *page_table_alloc(struct mm_struct *mm)
-{
-	unsigned long *table;
-	struct page *page;
-	unsigned int mask, bit;
-
-	/* Try to get a fragment of a 4K page as a 2K page table */
-	if (!mm_alloc_pgste(mm)) {
-		table = NULL;
-		spin_lock_bh(&mm->context.list_lock);
-		if (!list_empty(&mm->context.pgtable_list)) {
-			page = list_first_entry(&mm->context.pgtable_list,
-						struct page, lru);
-			mask = atomic_read(&page->_mapcount);
-			mask = (mask | (mask >> 4)) & 3;
-			if (mask != 3) {
-				table = (unsigned long *) page_to_phys(page);
-				bit = mask & 1;		/* =1 -> second 2K */
-				if (bit)
-					table += PTRS_PER_PTE;
-				atomic_xor_bits(&page->_mapcount, 1U << bit);
-				list_del(&page->lru);
-			}
-		}
-		spin_unlock_bh(&mm->context.list_lock);
-		if (table)
-			return table;
-	}
-	/* Allocate a fresh page */
-	page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
-	if (!page)
-		return NULL;
-	if (!pgtable_page_ctor(page)) {
-		__free_page(page);
-		return NULL;
-	}
-	/* Initialize page table */
-	table = (unsigned long *) page_to_phys(page);
-	if (mm_alloc_pgste(mm)) {
-		/* Return 4K page table with PGSTEs */
-		atomic_set(&page->_mapcount, 3);
-		clear_table(table, _PAGE_INVALID, PAGE_SIZE/2);
-		clear_table(table + PTRS_PER_PTE, 0, PAGE_SIZE/2);
-	} else {
-		/* Return the first 2K fragment of the page */
-		atomic_set(&page->_mapcount, 1);
-		clear_table(table, _PAGE_INVALID, PAGE_SIZE);
-		spin_lock_bh(&mm->context.list_lock);
-		list_add(&page->lru, &mm->context.pgtable_list);
-		spin_unlock_bh(&mm->context.list_lock);
-	}
-	return table;
-}
-
-void page_table_free(struct mm_struct *mm, unsigned long *table)
-{
-	struct page *page;
-	unsigned int bit, mask;
-
-	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
-	if (!mm_alloc_pgste(mm)) {
-		/* Free 2K page table fragment of a 4K page */
-		bit = (__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t));
-		spin_lock_bh(&mm->context.list_lock);
-		mask = atomic_xor_bits(&page->_mapcount, 1U << bit);
-		if (mask & 3)
-			list_add(&page->lru, &mm->context.pgtable_list);
-		else
-			list_del(&page->lru);
-		spin_unlock_bh(&mm->context.list_lock);
-		if (mask != 0)
-			return;
-	}
-
-	pgtable_page_dtor(page);
-	atomic_set(&page->_mapcount, -1);
-	__free_page(page);
-}
-
-void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table,
-			 unsigned long vmaddr)
-{
-	struct mm_struct *mm;
-	struct page *page;
-	unsigned int bit, mask;
-
-	mm = tlb->mm;
-	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
-	if (mm_alloc_pgste(mm)) {
-		gmap_unlink(mm, table, vmaddr);
-		table = (unsigned long *) (__pa(table) | 3);
-		tlb_remove_table(tlb, table);
-		return;
-	}
-	bit = (__pa(table) & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t));
-	spin_lock_bh(&mm->context.list_lock);
-	mask = atomic_xor_bits(&page->_mapcount, 0x11U << bit);
-	if (mask & 3)
-		list_add_tail(&page->lru, &mm->context.pgtable_list);
-	else
-		list_del(&page->lru);
-	spin_unlock_bh(&mm->context.list_lock);
-	table = (unsigned long *) (__pa(table) | (1U << bit));
-	tlb_remove_table(tlb, table);
-}
-
-static void __tlb_remove_table(void *_table)
-{
-	unsigned int mask = (unsigned long) _table & 3;
-	void *table = (void *)((unsigned long) _table ^ mask);
-	struct page *page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
-
-	switch (mask) {
-	case 0:		/* pmd or pud */
-		free_pages((unsigned long) table, 2);
-		break;
-	case 1:		/* lower 2K of a 4K page table */
-	case 2:		/* higher 2K of a 4K page table */
-		if (atomic_xor_bits(&page->_mapcount, mask << 4) != 0)
-			break;
-		/* fallthrough */
-	case 3:		/* 4K page table with pgstes */
-		pgtable_page_dtor(page);
-		atomic_set(&page->_mapcount, -1);
-		__free_page(page);
-		break;
-	}
-}
-
-static void tlb_remove_table_smp_sync(void *arg)
-{
-	/* Simply deliver the interrupt */
-}
-
-static void tlb_remove_table_one(void *table)
-{
-	/*
-	 * This isn't an RCU grace period and hence the page-tables cannot be
-	 * assumed to be actually RCU-freed.
-	 *
-	 * It is however sufficient for software page-table walkers that rely
-	 * on IRQ disabling. See the comment near struct mmu_table_batch.
-	 */
-	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
-	__tlb_remove_table(table);
-}
-
-static void tlb_remove_table_rcu(struct rcu_head *head)
-{
-	struct mmu_table_batch *batch;
-	int i;
-
-	batch = container_of(head, struct mmu_table_batch, rcu);
-
-	for (i = 0; i < batch->nr; i++)
-		__tlb_remove_table(batch->tables[i]);
-
-	free_page((unsigned long)batch);
-}
-
-void tlb_table_flush(struct mmu_gather *tlb)
-{
-	struct mmu_table_batch **batch = &tlb->batch;
-
-	if (*batch) {
-		call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
-		*batch = NULL;
-	}
-}
-
-void tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	struct mmu_table_batch **batch = &tlb->batch;
-
-	tlb->mm->context.flush_mm = 1;
-	if (*batch == NULL) {
-		*batch = (struct mmu_table_batch *)
-			__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
-		if (*batch == NULL) {
-			__tlb_flush_mm_lazy(tlb->mm);
-			tlb_remove_table_one(table);
-			return;
-		}
-		(*batch)->nr = 0;
-	}
-	(*batch)->tables[(*batch)->nr++] = table;
-	if ((*batch)->nr == MAX_TABLE_BATCH)
-		tlb_flush_mmu(tlb);
-}
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline void thp_split_vma(struct vm_area_struct *vma)
-{
-	unsigned long addr;
-
-	for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE)
-		follow_page(vma, addr, FOLL_SPLIT);
-}
-
-static inline void thp_split_mm(struct mm_struct *mm)
-{
-	struct vm_area_struct *vma;
-
-	for (vma = mm->mmap; vma != NULL; vma = vma->vm_next) {
-		thp_split_vma(vma);
-		vma->vm_flags &= ~VM_HUGEPAGE;
-		vma->vm_flags |= VM_NOHUGEPAGE;
-	}
-	mm->def_flags |= VM_NOHUGEPAGE;
-}
-#else
-static inline void thp_split_mm(struct mm_struct *mm)
-{
-}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-
-/*
- * switch on pgstes for its userspace process (for kvm)
- */
-int s390_enable_sie(void)
-{
-	struct mm_struct *mm = current->mm;
-
-	/* Do we have pgstes? if yes, we are done */
-	if (mm_has_pgste(mm))
-		return 0;
-	/* Fail if the page tables are 2K */
-	if (!mm_alloc_pgste(mm))
-		return -EINVAL;
-	down_write(&mm->mmap_sem);
-	mm->context.has_pgste = 1;
-	/* split thp mappings and disable thp for future mappings */
-	thp_split_mm(mm);
-	up_write(&mm->mmap_sem);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(s390_enable_sie);
-
-/*
- * Enable storage key handling from now on and initialize the storage
- * keys with the default key.
- */
-static int __s390_enable_skey(pte_t *pte, unsigned long addr,
-			      unsigned long next, struct mm_walk *walk)
-{
-	unsigned long ptev;
-	pgste_t pgste;
-
-	pgste = pgste_get_lock(pte);
-	/*
-	 * Remove all zero page mappings,
-	 * after establishing a policy to forbid zero page mappings
-	 * following faults for that page will get fresh anonymous pages
-	 */
-	if (is_zero_pfn(pte_pfn(*pte))) {
-		ptep_flush_direct(walk->mm, addr, pte);
-		pte_val(*pte) = _PAGE_INVALID;
-	}
-	/* Clear storage key */
-	pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT |
-			      PGSTE_GR_BIT | PGSTE_GC_BIT);
-	ptev = pte_val(*pte);
-	if (!(ptev & _PAGE_INVALID) && (ptev & _PAGE_WRITE))
-		page_set_storage_key(ptev & PAGE_MASK, PAGE_DEFAULT_KEY, 1);
-	pgste_set_unlock(pte, pgste);
-	return 0;
-}
-
-int s390_enable_skey(void)
-{
-	struct mm_walk walk = { .pte_entry = __s390_enable_skey };
-	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
-	int rc = 0;
-
-	down_write(&mm->mmap_sem);
-	if (mm_use_skey(mm))
-		goto out_up;
-
-	mm->context.use_skey = 1;
-	for (vma = mm->mmap; vma; vma = vma->vm_next) {
-		if (ksm_madvise(vma, vma->vm_start, vma->vm_end,
-				MADV_UNMERGEABLE, &vma->vm_flags)) {
-			mm->context.use_skey = 0;
-			rc = -ENOMEM;
-			goto out_up;
-		}
-	}
-	mm->def_flags &= ~VM_MERGEABLE;
-
-	walk.mm = mm;
-	walk_page_range(0, TASK_SIZE, &walk);
-
-out_up:
-	up_write(&mm->mmap_sem);
-	return rc;
-}
-EXPORT_SYMBOL_GPL(s390_enable_skey);
-
-/*
- * Reset CMMA state, make all pages stable again.
- */
-static int __s390_reset_cmma(pte_t *pte, unsigned long addr,
-			     unsigned long next, struct mm_walk *walk)
-{
-	pgste_t pgste;
-
-	pgste = pgste_get_lock(pte);
-	pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK;
-	pgste_set_unlock(pte, pgste);
-	return 0;
-}
-
-void s390_reset_cmma(struct mm_struct *mm)
-{
-	struct mm_walk walk = { .pte_entry = __s390_reset_cmma };
-
-	down_write(&mm->mmap_sem);
-	walk.mm = mm;
-	walk_page_range(0, TASK_SIZE, &walk);
-	up_write(&mm->mmap_sem);
-}
-EXPORT_SYMBOL_GPL(s390_reset_cmma);
-
-/*
- * Test and reset if a guest page is dirty
- */
-bool gmap_test_and_clear_dirty(unsigned long address, struct gmap *gmap)
-{
-	pte_t *pte;
-	spinlock_t *ptl;
-	bool dirty = false;
-
-	pte = get_locked_pte(gmap->mm, address, &ptl);
-	if (unlikely(!pte))
-		return false;
-
-	if (ptep_test_and_clear_user_dirty(gmap->mm, address, pte))
-		dirty = true;
-
-	spin_unlock(ptl);
-	return dirty;
-}
-EXPORT_SYMBOL_GPL(gmap_test_and_clear_dirty);
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address,
-			   pmd_t *pmdp)
-{
-	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
-	/* No need to flush TLB
-	 * On s390 reference bits are in storage key and never in TLB */
-	return pmdp_test_and_clear_young(vma, address, pmdp);
-}
-
-int pmdp_set_access_flags(struct vm_area_struct *vma,
-			  unsigned long address, pmd_t *pmdp,
-			  pmd_t entry, int dirty)
-{
-	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
-
-	entry = pmd_mkyoung(entry);
-	if (dirty)
-		entry = pmd_mkdirty(entry);
-	if (pmd_same(*pmdp, entry))
-		return 0;
-	pmdp_invalidate(vma, address, pmdp);
-	set_pmd_at(vma->vm_mm, address, pmdp, entry);
-	return 1;
-}
-
-void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
-				pgtable_t pgtable)
-{
-	struct list_head *lh = (struct list_head *) pgtable;
-
-	assert_spin_locked(pmd_lockptr(mm, pmdp));
-
-	/* FIFO */
-	if (!pmd_huge_pte(mm, pmdp))
-		INIT_LIST_HEAD(lh);
-	else
-		list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp));
-	pmd_huge_pte(mm, pmdp) = pgtable;
-}
-
-pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
-{
-	struct list_head *lh;
-	pgtable_t pgtable;
-	pte_t *ptep;
-
-	assert_spin_locked(pmd_lockptr(mm, pmdp));
-
-	/* FIFO */
-	pgtable = pmd_huge_pte(mm, pmdp);
-	lh = (struct list_head *) pgtable;
-	if (list_empty(lh))
-		pmd_huge_pte(mm, pmdp) = NULL;
-	else {
-		pmd_huge_pte(mm, pmdp) = (pgtable_t) lh->next;
-		list_del(lh);
-	}
-	ptep = (pte_t *) pgtable;
-	pte_val(*ptep) = _PAGE_INVALID;
-	ptep++;
-	pte_val(*ptep) = _PAGE_INVALID;
-	return pgtable;
-}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index ef7d6c8fea66..d27fccbad7c1 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -94,16 +94,15 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 			pgd_populate(&init_mm, pg_dir, pu_dir);
 		}
 		pu_dir = pud_offset(pg_dir, address);
-#ifndef CONFIG_DEBUG_PAGEALLOC
 		if (MACHINE_HAS_EDAT2 && pud_none(*pu_dir) && address &&
-		    !(address & ~PUD_MASK) && (address + PUD_SIZE <= end)) {
+		    !(address & ~PUD_MASK) && (address + PUD_SIZE <= end) &&
+		     !debug_pagealloc_enabled()) {
 			pud_val(*pu_dir) = __pa(address) |
 				_REGION_ENTRY_TYPE_R3 | _REGION3_ENTRY_LARGE |
 				(ro ? _REGION_ENTRY_PROTECT : 0);
 			address += PUD_SIZE;
 			continue;
 		}
-#endif
 		if (pud_none(*pu_dir)) {
 			pm_dir = vmem_pmd_alloc();
 			if (!pm_dir)
@@ -111,9 +110,9 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 			pud_populate(&init_mm, pu_dir, pm_dir);
 		}
 		pm_dir = pmd_offset(pu_dir, address);
-#ifndef CONFIG_DEBUG_PAGEALLOC
 		if (MACHINE_HAS_EDAT1 && pmd_none(*pm_dir) && address &&
-		    !(address & ~PMD_MASK) && (address + PMD_SIZE <= end)) {
+		    !(address & ~PMD_MASK) && (address + PMD_SIZE <= end) &&
+		    !debug_pagealloc_enabled()) {
 			pmd_val(*pm_dir) = __pa(address) |
 				_SEGMENT_ENTRY | _SEGMENT_ENTRY_LARGE |
 				_SEGMENT_ENTRY_YOUNG |
@@ -121,7 +120,6 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 			address += PMD_SIZE;
 			continue;
 		}
-#endif
 		if (pmd_none(*pm_dir)) {
 			pt_dir = vmem_pte_alloc(address);
 			if (!pt_dir)
diff --git a/arch/s390/oprofile/Makefile b/arch/s390/oprofile/Makefile
index 1bd23017191e..496e4a7ee00e 100644
--- a/arch/s390/oprofile/Makefile
+++ b/arch/s390/oprofile/Makefile
@@ -6,5 +6,5 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
 		oprofilefs.o oprofile_stats.o  \
 		timer_int.o )
 
-oprofile-y :=	$(DRIVER_OBJS) init.o backtrace.o
+oprofile-y :=	$(DRIVER_OBJS) init.o
 oprofile-y +=	hwsampler.o
diff --git a/arch/s390/oprofile/backtrace.c b/arch/s390/oprofile/backtrace.c
deleted file mode 100644
index fe0bfe370c45..000000000000
--- a/arch/s390/oprofile/backtrace.c
+++ /dev/null
@@ -1,76 +0,0 @@
-/*
- * S390 Version
- *   Copyright IBM Corp. 2005
- *   Author(s): Andreas Krebbel <Andreas.Krebbel@de.ibm.com>
- */
-
-#include <linux/oprofile.h>
-
-#include <asm/processor.h> /* for struct stack_frame */
-
-static unsigned long
-__show_trace(unsigned int *depth, unsigned long sp,
-	     unsigned long low, unsigned long high)
-{
-	struct stack_frame *sf;
-	struct pt_regs *regs;
-
-	while (*depth) {
-		if (sp < low || sp > high - sizeof(*sf))
-			return sp;
-		sf = (struct stack_frame *) sp;
-		(*depth)--;
-		oprofile_add_trace(sf->gprs[8]);
-
-		/* Follow the backchain.  */
-		while (*depth) {
-			low = sp;
-			sp = sf->back_chain;
-			if (!sp)
-				break;
-			if (sp <= low || sp > high - sizeof(*sf))
-				return sp;
-			sf = (struct stack_frame *) sp;
-			(*depth)--;
-			oprofile_add_trace(sf->gprs[8]);
-
-		}
-
-		if (*depth == 0)
-			break;
-
-		/* Zero backchain detected, check for interrupt frame.  */
-		sp = (unsigned long) (sf + 1);
-		if (sp <= low || sp > high - sizeof(*regs))
-			return sp;
-		regs = (struct pt_regs *) sp;
-		(*depth)--;
-		oprofile_add_trace(sf->gprs[8]);
-		low = sp;
-		sp = regs->gprs[15];
-	}
-	return sp;
-}
-
-void s390_backtrace(struct pt_regs * const regs, unsigned int depth)
-{
-	unsigned long head;
-	struct stack_frame* head_sf;
-
-	if (user_mode(regs))
-		return;
-
-	head = regs->gprs[15];
-	head_sf = (struct stack_frame*)head;
-
-	if (!head_sf->back_chain)
-		return;
-
-	head = head_sf->back_chain;
-
-	head = __show_trace(&depth, head, S390_lowcore.async_stack - ASYNC_SIZE,
-			    S390_lowcore.async_stack);
-
-	__show_trace(&depth, head, S390_lowcore.thread_info,
-		     S390_lowcore.thread_info + THREAD_SIZE);
-}
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index 9cfa2ffaa9d6..791935a65800 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -20,8 +20,6 @@
 
 #include "../../../drivers/oprofile/oprof.h"
 
-extern void s390_backtrace(struct pt_regs * const regs, unsigned int depth);
-
 #include "hwsampler.h"
 #include "op_counter.h"
 
@@ -456,6 +454,7 @@ static int oprofile_hwsampler_init(struct oprofile_operations *ops)
 		case 0x2097: case 0x2098: ops->cpu_type = "s390/z10"; break;
 		case 0x2817: case 0x2818: ops->cpu_type = "s390/z196"; break;
 		case 0x2827: case 0x2828: ops->cpu_type = "s390/zEC12"; break;
+		case 0x2964: case 0x2965: ops->cpu_type = "s390/z13"; break;
 		default: return -ENODEV;
 		}
 	}
@@ -494,6 +493,24 @@ static void oprofile_hwsampler_exit(void)
 	hwsampler_shutdown();
 }
 
+static int __s390_backtrace(void *data, unsigned long address)
+{
+	unsigned int *depth = data;
+
+	if (*depth == 0)
+		return 1;
+	(*depth)--;
+	oprofile_add_trace(address);
+	return 0;
+}
+
+static void s390_backtrace(struct pt_regs *regs, unsigned int depth)
+{
+	if (user_mode(regs))
+		return;
+	dump_trace(__s390_backtrace, &depth, NULL, regs->gprs[15]);
+}
+
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
 	ops->backtrace = s390_backtrace;
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 8f19c8f9d660..9fd59a7cfcd3 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -637,11 +637,9 @@ static void zpci_cleanup_bus_resources(struct zpci_dev *zdev)
 
 int pcibios_add_device(struct pci_dev *pdev)
 {
-	struct zpci_dev *zdev = to_zpci(pdev);
 	struct resource *res;
 	int i;
 
-	zdev->pdev = pdev;
 	pdev->dev.groups = zpci_attr_groups;
 	zpci_map_resources(pdev);
 
@@ -664,8 +662,7 @@ int pcibios_enable_device(struct pci_dev *pdev, int mask)
 {
 	struct zpci_dev *zdev = to_zpci(pdev);
 
-	zdev->pdev = pdev;
-	zpci_debug_init_device(zdev);
+	zpci_debug_init_device(zdev, dev_name(&pdev->dev));
 	zpci_fmb_enable_device(zdev);
 
 	return pci_enable_resources(pdev, mask);
@@ -677,7 +674,6 @@ void pcibios_disable_device(struct pci_dev *pdev)
 
 	zpci_fmb_disable_device(zdev);
 	zpci_debug_exit_device(zdev);
-	zdev->pdev = NULL;
 }
 
 #ifdef CONFIG_HIBERNATE_CALLBACKS
@@ -864,8 +860,11 @@ static inline int barsize(u8 size)
 
 static int zpci_mem_init(void)
 {
+	BUILD_BUG_ON(!is_power_of_2(__alignof__(struct zpci_fmb)) ||
+		     __alignof__(struct zpci_fmb) < sizeof(struct zpci_fmb));
+
 	zdev_fmb_cache = kmem_cache_create("PCI_FMB_cache", sizeof(struct zpci_fmb),
-				16, 0, NULL);
+					   __alignof__(struct zpci_fmb), 0, NULL);
 	if (!zdev_fmb_cache)
 		goto error_fmb;
 
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index d6e411ed8b1f..21591ddb4c1f 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -8,13 +8,19 @@
 #define KMSG_COMPONENT "zpci"
 #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
 
+#include <linux/compat.h>
 #include <linux/kernel.h>
+#include <linux/miscdevice.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/delay.h>
 #include <linux/pci.h>
+#include <linux/uaccess.h>
 #include <asm/pci_debug.h>
 #include <asm/pci_clp.h>
+#include <asm/compat.h>
+#include <asm/clp.h>
+#include <uapi/asm/clp.h>
 
 static inline void zpci_err_clp(unsigned int rsp, int rc)
 {
@@ -27,21 +33,43 @@ static inline void zpci_err_clp(unsigned int rsp, int rc)
 }
 
 /*
- * Call Logical Processor
- * Retry logic is handled by the caller.
+ * Call Logical Processor with c=1, lps=0 and command 1
+ * to get the bit mask of installed logical processors
  */
-static inline u8 clp_instr(void *data)
+static inline int clp_get_ilp(unsigned long *ilp)
+{
+	unsigned long mask;
+	int cc = 3;
+
+	asm volatile (
+		"	.insn	rrf,0xb9a00000,%[mask],%[cmd],8,0\n"
+		"0:	ipm	%[cc]\n"
+		"	srl	%[cc],28\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: [cc] "+d" (cc), [mask] "=d" (mask) : [cmd] "a" (1)
+		: "cc");
+	*ilp = mask;
+	return cc;
+}
+
+/*
+ * Call Logical Processor with c=0, the give constant lps and an lpcb request.
+ */
+static inline int clp_req(void *data, unsigned int lps)
 {
 	struct { u8 _[CLP_BLK_SIZE]; } *req = data;
 	u64 ignored;
-	u8 cc;
+	int cc = 3;
 
 	asm volatile (
-		"	.insn	rrf,0xb9a00000,%[ign],%[req],0x0,0x2\n"
-		"	ipm	%[cc]\n"
+		"	.insn	rrf,0xb9a00000,%[ign],%[req],0,%[lps]\n"
+		"0:	ipm	%[cc]\n"
 		"	srl	%[cc],28\n"
-		: [cc] "=d" (cc), [ign] "=d" (ignored), "+m" (*req)
-		: [req] "a" (req)
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: [cc] "+d" (cc), [ign] "=d" (ignored), "+m" (*req)
+		: [req] "a" (req), [lps] "i" (lps)
 		: "cc");
 	return cc;
 }
@@ -90,7 +118,7 @@ static int clp_query_pci_fngrp(struct zpci_dev *zdev, u8 pfgid)
 	rrb->response.hdr.len = sizeof(rrb->response);
 	rrb->request.pfgid = pfgid;
 
-	rc = clp_instr(rrb);
+	rc = clp_req(rrb, CLP_LPS_PCI);
 	if (!rc && rrb->response.hdr.rsp == CLP_RC_OK)
 		clp_store_query_pci_fngrp(zdev, &rrb->response);
 	else {
@@ -143,7 +171,7 @@ static int clp_query_pci_fn(struct zpci_dev *zdev, u32 fh)
 	rrb->response.hdr.len = sizeof(rrb->response);
 	rrb->request.fh = fh;
 
-	rc = clp_instr(rrb);
+	rc = clp_req(rrb, CLP_LPS_PCI);
 	if (!rc && rrb->response.hdr.rsp == CLP_RC_OK) {
 		rc = clp_store_query_pci_fn(zdev, &rrb->response);
 		if (rc)
@@ -214,7 +242,7 @@ static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command)
 		rrb->request.oc = command;
 		rrb->request.ndas = nr_dma_as;
 
-		rc = clp_instr(rrb);
+		rc = clp_req(rrb, CLP_LPS_PCI);
 		if (rrb->response.hdr.rsp == CLP_RC_SETPCIFN_BUSY) {
 			retries--;
 			if (retries < 0)
@@ -280,7 +308,7 @@ static int clp_list_pci(struct clp_req_rsp_list_pci *rrb,
 		rrb->request.resume_token = resume_token;
 
 		/* Get PCI function handle list */
-		rc = clp_instr(rrb);
+		rc = clp_req(rrb, CLP_LPS_PCI);
 		if (rc || rrb->response.hdr.rsp != CLP_RC_OK) {
 			zpci_err("List PCI FN:\n");
 			zpci_err_clp(rrb->response.hdr.rsp, rc);
@@ -391,3 +419,198 @@ int clp_rescan_pci_devices_simple(void)
 	clp_free_block(rrb);
 	return rc;
 }
+
+static int clp_base_slpc(struct clp_req *req, struct clp_req_rsp_slpc *lpcb)
+{
+	unsigned long limit = PAGE_SIZE - sizeof(lpcb->request);
+
+	if (lpcb->request.hdr.len != sizeof(lpcb->request) ||
+	    lpcb->response.hdr.len > limit)
+		return -EINVAL;
+	return clp_req(lpcb, CLP_LPS_BASE) ? -EOPNOTSUPP : 0;
+}
+
+static int clp_base_command(struct clp_req *req, struct clp_req_hdr *lpcb)
+{
+	switch (lpcb->cmd) {
+	case 0x0001: /* store logical-processor characteristics */
+		return clp_base_slpc(req, (void *) lpcb);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int clp_pci_slpc(struct clp_req *req, struct clp_req_rsp_slpc *lpcb)
+{
+	unsigned long limit = PAGE_SIZE - sizeof(lpcb->request);
+
+	if (lpcb->request.hdr.len != sizeof(lpcb->request) ||
+	    lpcb->response.hdr.len > limit)
+		return -EINVAL;
+	return clp_req(lpcb, CLP_LPS_PCI) ? -EOPNOTSUPP : 0;
+}
+
+static int clp_pci_list(struct clp_req *req, struct clp_req_rsp_list_pci *lpcb)
+{
+	unsigned long limit = PAGE_SIZE - sizeof(lpcb->request);
+
+	if (lpcb->request.hdr.len != sizeof(lpcb->request) ||
+	    lpcb->response.hdr.len > limit)
+		return -EINVAL;
+	if (lpcb->request.reserved2 != 0)
+		return -EINVAL;
+	return clp_req(lpcb, CLP_LPS_PCI) ? -EOPNOTSUPP : 0;
+}
+
+static int clp_pci_query(struct clp_req *req,
+			 struct clp_req_rsp_query_pci *lpcb)
+{
+	unsigned long limit = PAGE_SIZE - sizeof(lpcb->request);
+
+	if (lpcb->request.hdr.len != sizeof(lpcb->request) ||
+	    lpcb->response.hdr.len > limit)
+		return -EINVAL;
+	if (lpcb->request.reserved2 != 0 || lpcb->request.reserved3 != 0)
+		return -EINVAL;
+	return clp_req(lpcb, CLP_LPS_PCI) ? -EOPNOTSUPP : 0;
+}
+
+static int clp_pci_query_grp(struct clp_req *req,
+			     struct clp_req_rsp_query_pci_grp *lpcb)
+{
+	unsigned long limit = PAGE_SIZE - sizeof(lpcb->request);
+
+	if (lpcb->request.hdr.len != sizeof(lpcb->request) ||
+	    lpcb->response.hdr.len > limit)
+		return -EINVAL;
+	if (lpcb->request.reserved2 != 0 || lpcb->request.reserved3 != 0 ||
+	    lpcb->request.reserved4 != 0)
+		return -EINVAL;
+	return clp_req(lpcb, CLP_LPS_PCI) ? -EOPNOTSUPP : 0;
+}
+
+static int clp_pci_command(struct clp_req *req, struct clp_req_hdr *lpcb)
+{
+	switch (lpcb->cmd) {
+	case 0x0001: /* store logical-processor characteristics */
+		return clp_pci_slpc(req, (void *) lpcb);
+	case 0x0002: /* list PCI functions */
+		return clp_pci_list(req, (void *) lpcb);
+	case 0x0003: /* query PCI function */
+		return clp_pci_query(req, (void *) lpcb);
+	case 0x0004: /* query PCI function group */
+		return clp_pci_query_grp(req, (void *) lpcb);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int clp_normal_command(struct clp_req *req)
+{
+	struct clp_req_hdr *lpcb;
+	void __user *uptr;
+	int rc;
+
+	rc = -EINVAL;
+	if (req->lps != 0 && req->lps != 2)
+		goto out;
+
+	rc = -ENOMEM;
+	lpcb = clp_alloc_block(GFP_KERNEL);
+	if (!lpcb)
+		goto out;
+
+	rc = -EFAULT;
+	uptr = (void __force __user *)(unsigned long) req->data_p;
+	if (copy_from_user(lpcb, uptr, PAGE_SIZE) != 0)
+		goto out_free;
+
+	rc = -EINVAL;
+	if (lpcb->fmt != 0 || lpcb->reserved1 != 0 || lpcb->reserved2 != 0)
+		goto out_free;
+
+	switch (req->lps) {
+	case 0:
+		rc = clp_base_command(req, lpcb);
+		break;
+	case 2:
+		rc = clp_pci_command(req, lpcb);
+		break;
+	}
+	if (rc)
+		goto out_free;
+
+	rc = -EFAULT;
+	if (copy_to_user(uptr, lpcb, PAGE_SIZE) != 0)
+		goto out_free;
+
+	rc = 0;
+
+out_free:
+	clp_free_block(lpcb);
+out:
+	return rc;
+}
+
+static int clp_immediate_command(struct clp_req *req)
+{
+	void __user *uptr;
+	unsigned long ilp;
+	int exists;
+
+	if (req->cmd > 1 || clp_get_ilp(&ilp) != 0)
+		return -EINVAL;
+
+	uptr = (void __force __user *)(unsigned long) req->data_p;
+	if (req->cmd == 0) {
+		/* Command code 0: test for a specific processor */
+		exists = test_bit_inv(req->lps, &ilp);
+		return put_user(exists, (int __user *) uptr);
+	}
+	/* Command code 1: return bit mask of installed processors */
+	return put_user(ilp, (unsigned long __user *) uptr);
+}
+
+static long clp_misc_ioctl(struct file *filp, unsigned int cmd,
+			   unsigned long arg)
+{
+	struct clp_req req;
+	void __user *argp;
+
+	if (cmd != CLP_SYNC)
+		return -EINVAL;
+
+	argp = is_compat_task() ? compat_ptr(arg) : (void __user *) arg;
+	if (copy_from_user(&req, argp, sizeof(req)))
+		return -EFAULT;
+	if (req.r != 0)
+		return -EINVAL;
+	return req.c ? clp_immediate_command(&req) : clp_normal_command(&req);
+}
+
+static int clp_misc_release(struct inode *inode, struct file *filp)
+{
+	return 0;
+}
+
+static const struct file_operations clp_misc_fops = {
+	.owner = THIS_MODULE,
+	.open = nonseekable_open,
+	.release = clp_misc_release,
+	.unlocked_ioctl = clp_misc_ioctl,
+	.compat_ioctl = clp_misc_ioctl,
+	.llseek = no_llseek,
+};
+
+static struct miscdevice clp_misc_device = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "clp",
+	.fops = &clp_misc_fops,
+};
+
+static int __init clp_misc_init(void)
+{
+	return misc_register(&clp_misc_device);
+}
+
+device_initcall(clp_misc_init);
diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
index 4129b0a5fd78..c555de3d12d6 100644
--- a/arch/s390/pci/pci_debug.c
+++ b/arch/s390/pci/pci_debug.c
@@ -128,10 +128,9 @@ static const struct file_operations debugfs_pci_perf_fops = {
 	.release = single_release,
 };
 
-void zpci_debug_init_device(struct zpci_dev *zdev)
+void zpci_debug_init_device(struct zpci_dev *zdev, const char *name)
 {
-	zdev->debugfs_dev = debugfs_create_dir(dev_name(&zdev->pdev->dev),
-					       debugfs_root);
+	zdev->debugfs_dev = debugfs_create_dir(name, debugfs_root);
 	if (IS_ERR(zdev->debugfs_dev))
 		zdev->debugfs_dev = NULL;
 
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 4638b93c7632..a06ce8037cec 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -217,27 +217,29 @@ void dma_cleanup_tables(unsigned long *table)
 	dma_free_cpu_table(table);
 }
 
-static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev,
+static unsigned long __dma_alloc_iommu(struct device *dev,
 				       unsigned long start, int size)
 {
+	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
 	unsigned long boundary_size;
 
-	boundary_size = ALIGN(dma_get_seg_boundary(&zdev->pdev->dev) + 1,
+	boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
 			      PAGE_SIZE) >> PAGE_SHIFT;
 	return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages,
 				start, size, 0, boundary_size, 0);
 }
 
-static unsigned long dma_alloc_iommu(struct zpci_dev *zdev, int size)
+static unsigned long dma_alloc_iommu(struct device *dev, int size)
 {
+	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
 	unsigned long offset, flags;
 	int wrap = 0;
 
 	spin_lock_irqsave(&zdev->iommu_bitmap_lock, flags);
-	offset = __dma_alloc_iommu(zdev, zdev->next_bit, size);
+	offset = __dma_alloc_iommu(dev, zdev->next_bit, size);
 	if (offset == -1) {
 		/* wrap-around */
-		offset = __dma_alloc_iommu(zdev, 0, size);
+		offset = __dma_alloc_iommu(dev, 0, size);
 		wrap = 1;
 	}
 
@@ -251,8 +253,9 @@ static unsigned long dma_alloc_iommu(struct zpci_dev *zdev, int size)
 	return offset;
 }
 
-static void dma_free_iommu(struct zpci_dev *zdev, unsigned long offset, int size)
+static void dma_free_iommu(struct device *dev, unsigned long offset, int size)
 {
+	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
 	unsigned long flags;
 
 	spin_lock_irqsave(&zdev->iommu_bitmap_lock, flags);
@@ -293,7 +296,7 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page,
 
 	/* This rounds up number of pages based on size and offset */
 	nr_pages = iommu_num_pages(pa, size, PAGE_SIZE);
-	iommu_page_index = dma_alloc_iommu(zdev, nr_pages);
+	iommu_page_index = dma_alloc_iommu(dev, nr_pages);
 	if (iommu_page_index == -1) {
 		ret = -ENOSPC;
 		goto out_err;
@@ -319,7 +322,7 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page,
 	return dma_addr + (offset & ~PAGE_MASK);
 
 out_free:
-	dma_free_iommu(zdev, iommu_page_index, nr_pages);
+	dma_free_iommu(dev, iommu_page_index, nr_pages);
 out_err:
 	zpci_err("map error:\n");
 	zpci_err_dma(ret, pa);
@@ -346,7 +349,7 @@ static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr,
 
 	atomic64_add(npages, &zdev->unmapped_pages);
 	iommu_page_index = (dma_addr - zdev->start_dma) >> PAGE_SHIFT;
-	dma_free_iommu(zdev, iommu_page_index, npages);
+	dma_free_iommu(dev, iommu_page_index, npages);
 }
 
 static void *s390_dma_alloc(struct device *dev, size_t size,
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index b0e04751c5d5..fb2a9a560fdc 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -46,11 +46,14 @@ struct zpci_ccdf_avail {
 static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 {
 	struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
-	struct pci_dev *pdev = zdev ? zdev->pdev : NULL;
+	struct pci_dev *pdev = NULL;
 
 	zpci_err("error CCDF:\n");
 	zpci_err_hex(ccdf, sizeof(*ccdf));
 
+	if (zdev)
+		pdev = pci_get_slot(zdev->bus, ZPCI_DEVFN);
+
 	pr_err("%s: Event 0x%x reports an error for PCI function 0x%x\n",
 	       pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid);
 
@@ -58,6 +61,7 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 		return;
 
 	pdev->error_state = pci_channel_io_perm_failure;
+	pci_dev_put(pdev);
 }
 
 void zpci_event_error(void *data)
@@ -69,9 +73,12 @@ void zpci_event_error(void *data)
 static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 {
 	struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
-	struct pci_dev *pdev = zdev ? zdev->pdev : NULL;
+	struct pci_dev *pdev = NULL;
 	int ret;
 
+	if (zdev)
+		pdev = pci_get_slot(zdev->bus, ZPCI_DEVFN);
+
 	pr_info("%s: Event 0x%x reconfigured PCI function 0x%x\n",
 		pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid);
 	zpci_err("avail CCDF:\n");
@@ -138,6 +145,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 	default:
 		break;
 	}
+	if (pdev)
+		pci_dev_put(pdev);
 }
 
 void zpci_event_availability(void *data)
diff --git a/arch/score/kernel/setup.c b/arch/score/kernel/setup.c
index b48459afefdd..f3a0649ab521 100644
--- a/arch/score/kernel/setup.c
+++ b/arch/score/kernel/setup.c
@@ -101,7 +101,7 @@ static void __init resource_init(void)
 	res->name = "System RAM";
 	res->start = MEMORY_START;
 	res->end = MEMORY_START + MEMORY_SIZE - 1;
-	res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 	request_resource(&iomem_resource, res);
 
 	request_resource(res, &code_resource);
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index e13da05505dc..17a4f1593d65 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -847,14 +847,10 @@ config PCI
 config PCI_DOMAINS
 	bool
 
-source "drivers/pci/pcie/Kconfig"
-
 source "drivers/pci/Kconfig"
 
 source "drivers/pcmcia/Kconfig"
 
-source "drivers/pci/hotplug/Kconfig"
-
 endmenu
 
 menu "Executable file formats"
diff --git a/arch/sh/include/asm/pci.h b/arch/sh/include/asm/pci.h
index e343dbd02e41..644314f2b1ef 100644
--- a/arch/sh/include/asm/pci.h
+++ b/arch/sh/include/asm/pci.h
@@ -105,9 +105,6 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 	return channel ? 15 : 14;
 }
 
-/* generic DMA-mapping stuff */
-#include <asm-generic/pci-dma-compat.h>
-
 #endif /* __KERNEL__ */
 #endif /* __ASM_SH_PCI_H */
 
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index de19cfa768f2..3f1c18b28e8a 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -78,17 +78,17 @@ static char __initdata command_line[COMMAND_LINE_SIZE] = { 0, };
 
 static struct resource code_resource = {
 	.name = "Kernel code",
-	.flags = IORESOURCE_BUSY | IORESOURCE_MEM,
+	.flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
 };
 
 static struct resource data_resource = {
 	.name = "Kernel data",
-	.flags = IORESOURCE_BUSY | IORESOURCE_MEM,
+	.flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
 };
 
 static struct resource bss_resource = {
 	.name	= "Kernel bss",
-	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM,
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
 };
 
 unsigned long memory_start;
@@ -202,7 +202,7 @@ void __init __add_active_range(unsigned int nid, unsigned long start_pfn,
 	res->name = "System RAM";
 	res->start = start;
 	res->end = end - 1;
-	res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
 	if (request_resource(&iomem_resource, res)) {
 		pr_err("unable to request memory_resource 0x%lx 0x%lx\n",
diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c
index de6be008fc01..13f633add29a 100644
--- a/arch/sh/kernel/smp.c
+++ b/arch/sh/kernel/smp.c
@@ -203,7 +203,7 @@ asmlinkage void start_secondary(void)
 	set_cpu_online(cpu, true);
 	per_cpu(cpu_state, cpu) = CPU_ONLINE;
 
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
 extern struct {
diff --git a/arch/sparc/Makefile b/arch/sparc/Makefile
index eaee14637d93..8496a074bd0e 100644
--- a/arch/sparc/Makefile
+++ b/arch/sparc/Makefile
@@ -24,7 +24,13 @@ LDFLAGS        := -m elf32_sparc
 export BITS    := 32
 UTS_MACHINE    := sparc
 
+# We are adding -Wa,-Av8 to KBUILD_CFLAGS to deal with a specs bug in some
+# versions of gcc.  Some gcc versions won't pass -Av8 to binutils when you
+# give -mcpu=v8.  This silently worked with older bintutils versions but
+# does not any more.
 KBUILD_CFLAGS  += -m32 -mcpu=v8 -pipe -mno-fpu -fcall-used-g5 -fcall-used-g7
+KBUILD_CFLAGS  += -Wa,-Av8
+
 KBUILD_AFLAGS  += -m32 -Wa,-Av8
 
 else
diff --git a/arch/sparc/include/asm/pci.h b/arch/sparc/include/asm/pci.h
index d9c031f9910f..6e14fd179335 100644
--- a/arch/sparc/include/asm/pci.h
+++ b/arch/sparc/include/asm/pci.h
@@ -5,7 +5,4 @@
 #else
 #include <asm/pci_32.h>
 #endif
-
-#include <asm-generic/pci-dma-compat.h>
-
 #endif
diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h
index 1c26d440d288..b6de8b10a55b 100644
--- a/arch/sparc/include/uapi/asm/unistd.h
+++ b/arch/sparc/include/uapi/asm/unistd.h
@@ -422,8 +422,9 @@
 #define __NR_listen		354
 #define __NR_setsockopt		355
 #define __NR_mlock2		356
+#define __NR_copy_file_range	357
 
-#define NR_syscalls		357
+#define NR_syscalls		358
 
 /* Bitmask values returned from kern_features system call.  */
 #define KERN_FEATURE_MIXED_MODE_STACK	0x00000001
diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S
index 33c02b15f478..a83707c83be8 100644
--- a/arch/sparc/kernel/entry.S
+++ b/arch/sparc/kernel/entry.S
@@ -948,7 +948,24 @@ linux_syscall_trace:
 	cmp	%o0, 0
 	bne	3f
 	 mov	-ENOSYS, %o0
+
+	/* Syscall tracing can modify the registers.  */
+	ld	[%sp + STACKFRAME_SZ + PT_G1], %g1
+	sethi	%hi(sys_call_table), %l7
+	ld	[%sp + STACKFRAME_SZ + PT_I0], %i0
+	or	%l7, %lo(sys_call_table), %l7
+	ld	[%sp + STACKFRAME_SZ + PT_I1], %i1
+	ld	[%sp + STACKFRAME_SZ + PT_I2], %i2
+	ld	[%sp + STACKFRAME_SZ + PT_I3], %i3
+	ld	[%sp + STACKFRAME_SZ + PT_I4], %i4
+	ld	[%sp + STACKFRAME_SZ + PT_I5], %i5
+	cmp	%g1, NR_syscalls
+	bgeu	3f
+	 mov	-ENOSYS, %o0
+
+	sll	%g1, 2, %l4
 	mov	%i0, %o0
+	ld	[%l7 + %l4], %l7
 	mov	%i1, %o1
 	mov	%i2, %o2
 	mov	%i3, %o3
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index f2d30cab5b3f..cd1f592cd347 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -696,14 +696,6 @@ tlb_fixup_done:
 	call	__bzero
 	 sub	%o1, %o0, %o1
 
-#ifdef CONFIG_LOCKDEP
-	/* We have this call this super early, as even prom_init can grab
-	 * spinlocks and thus call into the lockdep code.
-	 */
-	call	lockdep_init
-	 nop
-#endif
-
 	call	prom_init
 	 mov	%l7, %o0			! OpenPROM cif handler
 
diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S
index afbaba52d2f1..d127130bf424 100644
--- a/arch/sparc/kernel/hvcalls.S
+++ b/arch/sparc/kernel/hvcalls.S
@@ -338,8 +338,9 @@ ENTRY(sun4v_mach_set_watchdog)
 	mov	%o1, %o4
 	mov	HV_FAST_MACH_SET_WATCHDOG, %o5
 	ta	HV_FAST_TRAP
+	brnz,a,pn %o4, 0f
 	stx	%o1, [%o4]
-	retl
+0:	retl
 	 nop
 ENDPROC(sun4v_mach_set_watchdog)
 
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index d88beff47bab..39aaec173f66 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -52,7 +52,7 @@ asmlinkage void sparc64_set_context(struct pt_regs *regs)
 	unsigned char fenab;
 	int err;
 
-	flush_user_windows();
+	synchronize_user_stack();
 	if (get_thread_wsaved()					||
 	    (((unsigned long)ucp) & (sizeof(unsigned long)-1))	||
 	    (!__access_ok(ucp, sizeof(*ucp))))
diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c
index b3a5d81b20f0..fb30e7c6a5b1 100644
--- a/arch/sparc/kernel/smp_32.c
+++ b/arch/sparc/kernel/smp_32.c
@@ -364,7 +364,7 @@ static void sparc_start_secondary(void *arg)
 	local_irq_enable();
 
 	wmb();
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 
 	/* We should never reach here! */
 	BUG();
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 19cd08d18672..8a6151a628ce 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -134,7 +134,7 @@ void smp_callin(void)
 
 	local_irq_enable();
 
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
 void cpu_panic(void)
diff --git a/arch/sparc/kernel/sparc_ksyms_64.c b/arch/sparc/kernel/sparc_ksyms_64.c
index a92d5d2c46a3..9e034f29dcc5 100644
--- a/arch/sparc/kernel/sparc_ksyms_64.c
+++ b/arch/sparc/kernel/sparc_ksyms_64.c
@@ -37,6 +37,7 @@ EXPORT_SYMBOL(sun4v_niagara_getperf);
 EXPORT_SYMBOL(sun4v_niagara_setperf);
 EXPORT_SYMBOL(sun4v_niagara2_getperf);
 EXPORT_SYMBOL(sun4v_niagara2_setperf);
+EXPORT_SYMBOL(sun4v_mach_set_watchdog);
 
 /* from hweight.S */
 EXPORT_SYMBOL(__arch_hweight8);
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index c690c8e16a96..b489e9759518 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -264,7 +264,7 @@ static unsigned long mmap_rnd(void)
 	unsigned long rnd = 0UL;
 
 	if (current->flags & PF_RANDOMIZE) {
-		unsigned long val = get_random_int();
+		unsigned long val = get_random_long();
 		if (test_thread_flag(TIF_32BIT))
 			rnd = (val % (1UL << (23UL-PAGE_SHIFT)));
 		else
diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S
index bb0008927598..c4a1b5c40e4e 100644
--- a/arch/sparc/kernel/syscalls.S
+++ b/arch/sparc/kernel/syscalls.S
@@ -158,7 +158,25 @@ linux_syscall_trace32:
 	 add	%sp, PTREGS_OFF, %o0
 	brnz,pn	%o0, 3f
 	 mov	-ENOSYS, %o0
+
+	/* Syscall tracing can modify the registers.  */
+	ldx	[%sp + PTREGS_OFF + PT_V9_G1], %g1
+	sethi	%hi(sys_call_table32), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I0], %i0
+	or	%l7, %lo(sys_call_table32), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I1], %i1
+	ldx	[%sp + PTREGS_OFF + PT_V9_I2], %i2
+	ldx	[%sp + PTREGS_OFF + PT_V9_I3], %i3
+	ldx	[%sp + PTREGS_OFF + PT_V9_I4], %i4
+	ldx	[%sp + PTREGS_OFF + PT_V9_I5], %i5
+
+	cmp	%g1, NR_syscalls
+	bgeu,pn	%xcc, 3f
+	 mov	-ENOSYS, %o0
+
+	sll	%g1, 2, %l4
 	srl	%i0, 0, %o0
+	lduw	[%l7 + %l4], %l7
 	srl	%i4, 0, %o4
 	srl	%i1, 0, %o1
 	srl	%i2, 0, %o2
@@ -170,7 +188,25 @@ linux_syscall_trace:
 	 add	%sp, PTREGS_OFF, %o0
 	brnz,pn	%o0, 3f
 	 mov	-ENOSYS, %o0
+
+	/* Syscall tracing can modify the registers.  */
+	ldx	[%sp + PTREGS_OFF + PT_V9_G1], %g1
+	sethi	%hi(sys_call_table64), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I0], %i0
+	or	%l7, %lo(sys_call_table64), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I1], %i1
+	ldx	[%sp + PTREGS_OFF + PT_V9_I2], %i2
+	ldx	[%sp + PTREGS_OFF + PT_V9_I3], %i3
+	ldx	[%sp + PTREGS_OFF + PT_V9_I4], %i4
+	ldx	[%sp + PTREGS_OFF + PT_V9_I5], %i5
+
+	cmp	%g1, NR_syscalls
+	bgeu,pn	%xcc, 3f
+	 mov	-ENOSYS, %o0
+
+	sll	%g1, 2, %l4
 	mov	%i0, %o0
+	lduw	[%l7 + %l4], %l7
 	mov	%i1, %o1
 	mov	%i2, %o2
 	mov	%i3, %o3
diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S
index e663b6c78de2..6c3dd6c52f8b 100644
--- a/arch/sparc/kernel/systbls_32.S
+++ b/arch/sparc/kernel/systbls_32.S
@@ -88,4 +88,4 @@ sys_call_table:
 /*340*/	.long sys_ni_syscall, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
 /*345*/	.long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
 /*350*/	.long sys_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen
-/*355*/	.long sys_setsockopt, sys_mlock2
+/*355*/	.long sys_setsockopt, sys_mlock2, sys_copy_file_range
diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S
index 1557121f4cdc..12b524cfcfa0 100644
--- a/arch/sparc/kernel/systbls_64.S
+++ b/arch/sparc/kernel/systbls_64.S
@@ -89,7 +89,7 @@ sys_call_table32:
 /*340*/	.word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
 	.word sys32_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
 /*350*/	.word sys32_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen
-	.word compat_sys_setsockopt, sys_mlock2
+	.word compat_sys_setsockopt, sys_mlock2, sys_copy_file_range
 
 #endif /* CONFIG_COMPAT */
 
@@ -170,4 +170,4 @@ sys_call_table:
 /*340*/	.word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
 	.word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
 /*350*/	.word sys64_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen
-	.word sys_setsockopt, sys_mlock2
+	.word sys_setsockopt, sys_mlock2, sys_copy_file_range
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 6f216853f272..1cfe6aab7a11 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2863,17 +2863,17 @@ void hugetlb_setup(struct pt_regs *regs)
 
 static struct resource code_resource = {
 	.name	= "Kernel code",
-	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
 };
 
 static struct resource data_resource = {
 	.name	= "Kernel data",
-	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
 };
 
 static struct resource bss_resource = {
 	.name	= "Kernel bss",
-	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
 };
 
 static inline resource_size_t compute_kern_paddr(void *addr)
@@ -2909,7 +2909,7 @@ static int __init report_memory(void)
 		res->name = "System RAM";
 		res->start = pavail[i].phys_addr;
 		res->end = pavail[i].phys_addr + pavail[i].reg_size - 1;
-		res->flags = IORESOURCE_BUSY | IORESOURCE_MEM;
+		res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM;
 
 		if (insert_resource(&iomem_resource, res) < 0) {
 			pr_warn("Resource insertion failed.\n");
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index de4a4fff9323..81719302b056 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -455,8 +455,6 @@ config TILE_PCI_IO
 
 source "drivers/pci/Kconfig"
 
-source "drivers/pci/pcie/Kconfig"
-
 config TILE_USB
 	tristate "Tilera USB host adapter support"
 	default y
@@ -467,8 +465,6 @@ config TILE_USB
 	  Provides USB host adapter support for the built-in EHCI and OHCI
 	  interfaces on TILE-Gx chips.
 
-source "drivers/pci/hotplug/Kconfig"
-
 endmenu
 
 menu "Executable file formats"
diff --git a/arch/tile/include/asm/pci.h b/arch/tile/include/asm/pci.h
index dfedd7ac7298..fe3de505b024 100644
--- a/arch/tile/include/asm/pci.h
+++ b/arch/tile/include/asm/pci.h
@@ -226,7 +226,4 @@ static inline int pcibios_assign_all_busses(void)
 /* Use any cpu for PCI. */
 #define cpumask_of_pcibus(bus) cpu_online_mask
 
-/* implement the pci_ DMA API in terms of the generic device dma_ one */
-#include <asm-generic/pci-dma-compat.h>
-
 #endif /* _ASM_TILE_PCI_H */
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index bbb855de6569..a992238e9b58 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -1632,14 +1632,14 @@ static struct resource data_resource = {
 	.name	= "Kernel data",
 	.start	= 0,
 	.end	= 0,
-	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
 };
 
 static struct resource code_resource = {
 	.name	= "Kernel code",
 	.start	= 0,
 	.end	= 0,
-	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
 };
 
 /*
@@ -1673,10 +1673,15 @@ insert_ram_resource(u64 start_pfn, u64 end_pfn, bool reserved)
 		kzalloc(sizeof(struct resource), GFP_ATOMIC);
 	if (!res)
 		return NULL;
-	res->name = reserved ? "Reserved" : "System RAM";
 	res->start = start_pfn << PAGE_SHIFT;
 	res->end = (end_pfn << PAGE_SHIFT) - 1;
 	res->flags = IORESOURCE_BUSY | IORESOURCE_MEM;
+	if (reserved) {
+		res->name = "Reserved";
+	} else {
+		res->name = "System RAM";
+		res->flags |= IORESOURCE_SYSRAM;
+	}
 	if (insert_resource(&iomem_resource, res)) {
 		kfree(res);
 		return NULL;
diff --git a/arch/tile/kernel/smpboot.c b/arch/tile/kernel/smpboot.c
index 20d52a98e171..6c0abaacec33 100644
--- a/arch/tile/kernel/smpboot.c
+++ b/arch/tile/kernel/smpboot.c
@@ -208,7 +208,7 @@ void online_secondary(void)
 	/* Set up tile-timer clock-event device on this cpu */
 	setup_tile_timer();
 
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
 int __cpu_up(unsigned int cpu, struct task_struct *tidle)
diff --git a/arch/um/kernel/reboot.c b/arch/um/kernel/reboot.c
index 9bdf67a092a5..b60a9f8cda75 100644
--- a/arch/um/kernel/reboot.c
+++ b/arch/um/kernel/reboot.c
@@ -12,6 +12,7 @@
 #include <skas.h>
 
 void (*pm_power_off)(void);
+EXPORT_SYMBOL(pm_power_off);
 
 static void kill_off_processes(void)
 {
diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c
index fc8be0e3a4ff..57acbd67d85d 100644
--- a/arch/um/kernel/signal.c
+++ b/arch/um/kernel/signal.c
@@ -69,7 +69,7 @@ void do_signal(struct pt_regs *regs)
 	struct ksignal ksig;
 	int handled_sig = 0;
 
-	if (get_signal(&ksig)) {
+	while (get_signal(&ksig)) {
 		handled_sig = 1;
 		/* Whee!  Actually deliver the signal.  */
 		handle_signal(&ksig, regs);
diff --git a/arch/unicore32/include/asm/pci.h b/arch/unicore32/include/asm/pci.h
index 38b3f3785c3c..37e55d018de5 100644
--- a/arch/unicore32/include/asm/pci.h
+++ b/arch/unicore32/include/asm/pci.h
@@ -13,8 +13,6 @@
 #define __UNICORE_PCI_H__
 
 #ifdef __KERNEL__
-#include <asm-generic/pci-dma-compat.h>
-#include <asm-generic/pci-bridge.h>
 #include <asm-generic/pci.h>
 #include <mach/hardware.h> /* for PCIBIOS_MIN_* */
 
@@ -23,5 +21,4 @@ extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 	enum pci_mmap_state mmap_state, int write_combine);
 
 #endif /* __KERNEL__ */
-
 #endif
diff --git a/arch/unicore32/include/mach/hardware.h b/arch/unicore32/include/mach/hardware.h
index 9e20b5d9ed50..25146232c7cf 100644
--- a/arch/unicore32/include/mach/hardware.h
+++ b/arch/unicore32/include/mach/hardware.h
@@ -28,11 +28,6 @@
 #define PCIBIOS_MIN_IO			0x4000 /* should lower than 64KB */
 #define PCIBIOS_MIN_MEM			io_v2p(PKUNITY_PCIMEM_BASE)
 
-/*
- * We override the standard dma-mask routines for bouncing.
- */
-#define	HAVE_ARCH_PCI_SET_DMA_MASK
-
 #define pcibios_assign_all_busses()	1
 
 #endif  /* __MACH_PUV3_HARDWARE_H__ */
diff --git a/arch/unicore32/kernel/setup.c b/arch/unicore32/kernel/setup.c
index 3fa317f96122..c2bffa5614a4 100644
--- a/arch/unicore32/kernel/setup.c
+++ b/arch/unicore32/kernel/setup.c
@@ -72,13 +72,13 @@ static struct resource mem_res[] = {
 		.name = "Kernel code",
 		.start = 0,
 		.end = 0,
-		.flags = IORESOURCE_MEM
+		.flags = IORESOURCE_SYSTEM_RAM
 	},
 	{
 		.name = "Kernel data",
 		.start = 0,
 		.end = 0,
-		.flags = IORESOURCE_MEM
+		.flags = IORESOURCE_SYSTEM_RAM
 	}
 };
 
@@ -211,7 +211,7 @@ request_standard_resources(struct meminfo *mi)
 		res->name  = "System RAM";
 		res->start = mi->bank[i].start;
 		res->end   = mi->bank[i].start + mi->bank[i].size - 1;
-		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+		res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
 		request_resource(&iomem_resource, res);
 
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
index 1538562cc720..eb3abf8ac44e 100644
--- a/arch/x86/Kbuild
+++ b/arch/x86/Kbuild
@@ -1,6 +1,7 @@
-
 obj-y += entry/
 
+obj-$(CONFIG_PERF_EVENTS) += events/
+
 obj-$(CONFIG_KVM) += kvm/
 
 # Xen paravirtualization support
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9af2e6338400..3c74b549ea9a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -303,6 +303,9 @@ config ARCH_SUPPORTS_UPROBES
 config FIX_EARLYCON_MEM
 	def_bool y
 
+config DEBUG_RODATA
+	def_bool y
+
 config PGTABLE_LEVELS
 	int
 	default 4 if X86_64
@@ -475,6 +478,7 @@ config X86_UV
 	depends on X86_64
 	depends on X86_EXTENDED_PLATFORM
 	depends on NUMA
+	depends on EFI
 	depends on X86_X2APIC
 	depends on PCI
 	---help---
@@ -777,8 +781,8 @@ config HPET_TIMER
 	  HPET is the next generation timer replacing legacy 8254s.
 	  The HPET provides a stable time base on SMP
 	  systems, unlike the TSC, but it is more expensive to access,
-	  as it is off-chip.  You can find the HPET spec at
-	  <http://www.intel.com/hardwaredesign/hpetspec_1.pdf>.
+	  as it is off-chip.  The interface used is documented
+	  in the HPET spec, revision 1.
 
 	  You can safely choose Y here.  However, HPET will only be
 	  activated if the platform and the BIOS support this feature.
@@ -1159,22 +1163,23 @@ config MICROCODE
 	bool "CPU microcode loading support"
 	default y
 	depends on CPU_SUP_AMD || CPU_SUP_INTEL
-	depends on BLK_DEV_INITRD
 	select FW_LOADER
 	---help---
-
 	  If you say Y here, you will be able to update the microcode on
-	  certain Intel and AMD processors. The Intel support is for the
-	  IA32 family, e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4,
-	  Xeon etc. The AMD support is for families 0x10 and later. You will
-	  obviously need the actual microcode binary data itself which is not
-	  shipped with the Linux kernel.
+	  Intel and AMD processors. The Intel support is for the IA32 family,
+	  e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4, Xeon etc. The
+	  AMD support is for families 0x10 and later. You will obviously need
+	  the actual microcode binary data itself which is not shipped with
+	  the Linux kernel.
 
-	  This option selects the general module only, you need to select
-	  at least one vendor specific module as well.
+	  The preferred method to load microcode from a detached initrd is described
+	  in Documentation/x86/early-microcode.txt. For that you need to enable
+	  CONFIG_BLK_DEV_INITRD in order for the loader to be able to scan the
+	  initrd for microcode blobs.
 
-	  To compile this driver as a module, choose M here: the module
-	  will be called microcode.
+	  In addition, you can build-in the microcode into the kernel. For that you
+	  need to enable FIRMWARE_IN_KERNEL and add the vendor-supplied microcode
+	  to the CONFIG_EXTRA_FIRMWARE config option.
 
 config MICROCODE_INTEL
 	bool "Intel microcode loading support"
@@ -2430,8 +2435,6 @@ config PCI_CNB20LE_QUIRK
 
 	  You should say N unless you know you need this.
 
-source "drivers/pci/pcie/Kconfig"
-
 source "drivers/pci/Kconfig"
 
 # x86_64 have no ISA slots, but can have ISA-style DMA.
@@ -2587,8 +2590,6 @@ config AMD_NB
 
 source "drivers/pcmcia/Kconfig"
 
-source "drivers/pci/hotplug/Kconfig"
-
 config RAPIDIO
 	tristate "RapidIO support"
 	depends on PCI
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 9b18ed97a8a2..67eec55093a5 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -74,28 +74,16 @@ config EFI_PGT_DUMP
 	  issues with the mapping of the EFI runtime regions into that
 	  table.
 
-config DEBUG_RODATA
-	bool "Write protect kernel read-only data structures"
-	default y
-	depends on DEBUG_KERNEL
-	---help---
-	  Mark the kernel read-only data as write-protected in the pagetables,
-	  in order to catch accidental (and incorrect) writes to such const
-	  data. This is recommended so that we can catch kernel bugs sooner.
-	  If in doubt, say "Y".
-
 config DEBUG_RODATA_TEST
-	bool "Testcase for the DEBUG_RODATA feature"
-	depends on DEBUG_RODATA
+	bool "Testcase for the marking rodata read-only"
 	default y
 	---help---
-	  This option enables a testcase for the DEBUG_RODATA
-	  feature as well as for the change_page_attr() infrastructure.
+	  This option enables a testcase for the setting rodata read-only
+	  as well as for the change_page_attr() infrastructure.
 	  If in doubt, say "N"
 
 config DEBUG_WX
 	bool "Warn on W+X mappings at boot"
-	depends on DEBUG_RODATA
 	select X86_PTDUMP_CORE
 	---help---
 	  Generate a warning if any W+X mappings are found at boot.
@@ -350,16 +338,6 @@ config DEBUG_IMR_SELFTEST
 
 	  If unsure say N here.
 
-config X86_DEBUG_STATIC_CPU_HAS
-	bool "Debug alternatives"
-	depends on DEBUG_KERNEL
-	---help---
-	  This option causes additional code to be generated which
-	  fails if static_cpu_has() is used before alternatives have
-	  run.
-
-	  If unsure, say N.
-
 config X86_DEBUG_FPU
 	bool "Debug the x86 FPU code"
 	depends on DEBUG_KERNEL
diff --git a/arch/x86/boot/cpuflags.h b/arch/x86/boot/cpuflags.h
index ea97697e51e4..4cb404fd45ce 100644
--- a/arch/x86/boot/cpuflags.h
+++ b/arch/x86/boot/cpuflags.h
@@ -1,7 +1,7 @@
 #ifndef BOOT_CPUFLAGS_H
 #define BOOT_CPUFLAGS_H
 
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/processor-flags.h>
 
 struct cpu_features {
diff --git a/arch/x86/boot/mkcpustr.c b/arch/x86/boot/mkcpustr.c
index 637097e66a62..f72498dc90d2 100644
--- a/arch/x86/boot/mkcpustr.c
+++ b/arch/x86/boot/mkcpustr.c
@@ -17,7 +17,7 @@
 
 #include "../include/asm/required-features.h"
 #include "../include/asm/disabled-features.h"
-#include "../include/asm/cpufeature.h"
+#include "../include/asm/cpufeatures.h"
 #include "../kernel/cpu/capflags.c"
 
 int main(void)
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index a7661c430cd9..0702d2531bc7 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -49,7 +49,6 @@ typedef unsigned int   u32;
 
 /* This must be large enough to hold the entire setup */
 u8 buf[SETUP_SECT_MAX*512];
-int is_big_kernel;
 
 #define PECOFF_RELOC_RESERVE 0x20
 
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index a212b68a4909..265901a84f3f 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -288,7 +288,7 @@ CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=y
 CONFIG_PRINTK_TIME=y
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
-CONFIG_FRAME_WARN=2048
+CONFIG_FRAME_WARN=1024
 CONFIG_MAGIC_SYSRQ=y
 # CONFIG_UNUSED_SYMBOLS is not set
 CONFIG_DEBUG_KERNEL=y
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 3633ad6145c5..064c7e2bd7c8 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -639,16 +639,11 @@ static int xts_aesni_setkey(struct crypto_tfm *tfm, const u8 *key,
 			    unsigned int keylen)
 {
 	struct aesni_xts_ctx *ctx = crypto_tfm_ctx(tfm);
-	u32 *flags = &tfm->crt_flags;
 	int err;
 
-	/* key consists of keys of equal size concatenated, therefore
-	 * the length must be even
-	 */
-	if (keylen % 2) {
-		*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-		return -EINVAL;
-	}
+	err = xts_check_key(tfm, key, keylen);
+	if (err)
+		return err;
 
 	/* first half of xts-key is for crypt */
 	err = aes_set_key_common(tfm, ctx->raw_crypt_ctx, key, keylen / 2);
diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c
index 5c8b6266a394..aa76cad9d262 100644
--- a/arch/x86/crypto/camellia_glue.c
+++ b/arch/x86/crypto/camellia_glue.c
@@ -1503,13 +1503,9 @@ int xts_camellia_setkey(struct crypto_tfm *tfm, const u8 *key,
 	u32 *flags = &tfm->crt_flags;
 	int err;
 
-	/* key consists of keys of equal size concatenated, therefore
-	 * the length must be even
-	 */
-	if (keylen % 2) {
-		*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-		return -EINVAL;
-	}
+	err = xts_check_key(tfm, key, keylen);
+	if (err)
+		return err;
 
 	/* first half of xts-key is for crypt */
 	err = __camellia_setkey(&ctx->crypt_ctx, key, keylen / 2, flags);
diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c
index fca459578c35..50e684768c55 100644
--- a/arch/x86/crypto/cast6_avx_glue.c
+++ b/arch/x86/crypto/cast6_avx_glue.c
@@ -329,13 +329,9 @@ static int xts_cast6_setkey(struct crypto_tfm *tfm, const u8 *key,
 	u32 *flags = &tfm->crt_flags;
 	int err;
 
-	/* key consists of keys of equal size concatenated, therefore
-	 * the length must be even
-	 */
-	if (keylen % 2) {
-		*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-		return -EINVAL;
-	}
+	err = xts_check_key(tfm, key, keylen);
+	if (err)
+		return err;
 
 	/* first half of xts-key is for crypt */
 	err = __cast6_setkey(&ctx->crypt_ctx, key, keylen / 2, flags);
diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c
index 07d2c6c86a54..27226df3f7d8 100644
--- a/arch/x86/crypto/crc32-pclmul_glue.c
+++ b/arch/x86/crypto/crc32-pclmul_glue.c
@@ -33,7 +33,7 @@
 #include <linux/crc32.h>
 #include <crypto/internal/hash.h>
 
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/cpu_device_id.h>
 #include <asm/fpu/api.h>
 
diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index 0e9871693f24..0857b1a1de3b 100644
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -30,7 +30,7 @@
 #include <linux/kernel.h>
 #include <crypto/internal/hash.h>
 
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/cpu_device_id.h>
 #include <asm/fpu/internal.h>
 
diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c
index a3fcfc97a311..cd4df9322501 100644
--- a/arch/x86/crypto/crct10dif-pclmul_glue.c
+++ b/arch/x86/crypto/crct10dif-pclmul_glue.c
@@ -30,7 +30,7 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <asm/fpu/api.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/cpu_device_id.h>
 
 asmlinkage __u16 crc_t10dif_pcl(__u16 crc, const unsigned char *buf,
diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c
index 5dc37026c7ce..6f778d3daa22 100644
--- a/arch/x86/crypto/serpent_avx_glue.c
+++ b/arch/x86/crypto/serpent_avx_glue.c
@@ -332,16 +332,11 @@ int xts_serpent_setkey(struct crypto_tfm *tfm, const u8 *key,
 		       unsigned int keylen)
 {
 	struct serpent_xts_ctx *ctx = crypto_tfm_ctx(tfm);
-	u32 *flags = &tfm->crt_flags;
 	int err;
 
-	/* key consists of keys of equal size concatenated, therefore
-	 * the length must be even
-	 */
-	if (keylen % 2) {
-		*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-		return -EINVAL;
-	}
+	err = xts_check_key(tfm, key, keylen);
+	if (err)
+		return err;
 
 	/* first half of xts-key is for crypt */
 	err = __serpent_setkey(&ctx->crypt_ctx, key, keylen / 2);
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
index 3643dd508f45..8943407e8917 100644
--- a/arch/x86/crypto/serpent_sse2_glue.c
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -309,16 +309,11 @@ static int xts_serpent_setkey(struct crypto_tfm *tfm, const u8 *key,
 			      unsigned int keylen)
 {
 	struct serpent_xts_ctx *ctx = crypto_tfm_ctx(tfm);
-	u32 *flags = &tfm->crt_flags;
 	int err;
 
-	/* key consists of keys of equal size concatenated, therefore
-	 * the length must be even
-	 */
-	if (keylen % 2) {
-		*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-		return -EINVAL;
-	}
+	err = xts_check_key(tfm, key, keylen);
+	if (err)
+		return err;
 
 	/* first half of xts-key is for crypt */
 	err = __serpent_setkey(&ctx->crypt_ctx, key, keylen / 2);
diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c
index a841e9765bd6..a8a0224fa0f8 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb.c
+++ b/arch/x86/crypto/sha-mb/sha1_mb.c
@@ -762,6 +762,38 @@ static int sha1_mb_async_digest(struct ahash_request *req)
 	return crypto_ahash_digest(mcryptd_req);
 }
 
+static int sha1_mb_async_export(struct ahash_request *req, void *out)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha1_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	return crypto_ahash_export(mcryptd_req, out);
+}
+
+static int sha1_mb_async_import(struct ahash_request *req, const void *in)
+{
+	struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct sha1_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+	struct crypto_shash *child = mcryptd_ahash_child(mcryptd_tfm);
+	struct mcryptd_hash_request_ctx *rctx;
+	struct shash_desc *desc;
+
+	memcpy(mcryptd_req, req, sizeof(*req));
+	ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+	rctx = ahash_request_ctx(mcryptd_req);
+	desc = &rctx->desc;
+	desc->tfm = child;
+	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	return crypto_ahash_import(mcryptd_req, in);
+}
+
 static int sha1_mb_async_init_tfm(struct crypto_tfm *tfm)
 {
 	struct mcryptd_ahash *mcryptd_tfm;
@@ -796,8 +828,11 @@ static struct ahash_alg sha1_mb_async_alg = {
 	.final          = sha1_mb_async_final,
 	.finup          = sha1_mb_async_finup,
 	.digest         = sha1_mb_async_digest,
+	.export		= sha1_mb_async_export,
+	.import		= sha1_mb_async_import,
 	.halg = {
 		.digestsize     = SHA1_DIGEST_SIZE,
+		.statesize	= sizeof(struct sha1_hash_ctx),
 		.base = {
 			.cra_name               = "sha1",
 			.cra_driver_name        = "sha1_mb",
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_submit_avx2.S b/arch/x86/crypto/sha-mb/sha1_mb_mgr_submit_avx2.S
index 2ab9560b53c8..c420d89b175f 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb_mgr_submit_avx2.S
+++ b/arch/x86/crypto/sha-mb/sha1_mb_mgr_submit_avx2.S
@@ -197,7 +197,7 @@ len_is_0:
 	vpinsrd  $1, _args_digest+1*32(state , idx, 4), %xmm0, %xmm0
 	vpinsrd  $2, _args_digest+2*32(state , idx, 4), %xmm0, %xmm0
 	vpinsrd  $3, _args_digest+3*32(state , idx, 4), %xmm0, %xmm0
-	movl    4*32(state, idx, 4), DWORD_tmp
+	movl     _args_digest+4*32(state, idx, 4), DWORD_tmp
 
 	vmovdqu  %xmm0, _result_digest(job_rax)
 	movl    DWORD_tmp, _result_digest+1*16(job_rax)
diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c
index 56d8a08ee479..2ebb5e9789f3 100644
--- a/arch/x86/crypto/twofish_glue_3way.c
+++ b/arch/x86/crypto/twofish_glue_3way.c
@@ -277,13 +277,9 @@ int xts_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
 	u32 *flags = &tfm->crt_flags;
 	int err;
 
-	/* key consists of keys of equal size concatenated, therefore
-	 * the length must be even
-	 */
-	if (keylen % 2) {
-		*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-		return -EINVAL;
-	}
+	err = xts_check_key(tfm, key, keylen);
+	if (err)
+		return err;
 
 	/* first half of xts-key is for crypt */
 	err = __twofish_setkey(&ctx->crypt_ctx, key, keylen / 2, flags);
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index e32206e09868..9a9e5884066c 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -201,37 +201,6 @@ For 32-bit we have the following conventions - kernel is built with
 	.byte 0xf1
 	.endm
 
-#else /* CONFIG_X86_64 */
-
-/*
- * For 32bit only simplified versions of SAVE_ALL/RESTORE_ALL. These
- * are different from the entry_32.S versions in not changing the segment
- * registers. So only suitable for in kernel use, not when transitioning
- * from or to user space. The resulting stack frame is not a standard
- * pt_regs frame. The main use case is calling C code from assembler
- * when all the registers need to be preserved.
- */
-
-	.macro SAVE_ALL
-	pushl %eax
-	pushl %ebp
-	pushl %edi
-	pushl %esi
-	pushl %edx
-	pushl %ecx
-	pushl %ebx
-	.endm
-
-	.macro RESTORE_ALL
-	popl %ebx
-	popl %ecx
-	popl %edx
-	popl %esi
-	popl %edi
-	popl %ebp
-	popl %eax
-	.endm
-
 #endif /* CONFIG_X86_64 */
 
 /*
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 03663740c866..e79d93d44ecd 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -26,6 +26,7 @@
 #include <asm/traps.h>
 #include <asm/vdso.h>
 #include <asm/uaccess.h>
+#include <asm/cpufeature.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
@@ -44,6 +45,8 @@ __visible void enter_from_user_mode(void)
 	CT_WARN_ON(ct_state() != CONTEXT_USER);
 	user_exit();
 }
+#else
+static inline void enter_from_user_mode(void) {}
 #endif
 
 static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
@@ -84,17 +87,6 @@ unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch)
 
 	work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY;
 
-#ifdef CONFIG_CONTEXT_TRACKING
-	/*
-	 * If TIF_NOHZ is set, we are required to call user_exit() before
-	 * doing anything that could touch RCU.
-	 */
-	if (work & _TIF_NOHZ) {
-		enter_from_user_mode();
-		work &= ~_TIF_NOHZ;
-	}
-#endif
-
 #ifdef CONFIG_SECCOMP
 	/*
 	 * Do seccomp first -- it should minimize exposure of other
@@ -171,16 +163,6 @@ long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch,
 	if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
 		BUG_ON(regs != task_pt_regs(current));
 
-	/*
-	 * If we stepped into a sysenter/syscall insn, it trapped in
-	 * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP.
-	 * If user-mode had set TF itself, then it's still clear from
-	 * do_debug() and we need to set it again to restore the user
-	 * state.  If we entered on the slow path, TF was already set.
-	 */
-	if (work & _TIF_SINGLESTEP)
-		regs->flags |= X86_EFLAGS_TF;
-
 #ifdef CONFIG_SECCOMP
 	/*
 	 * Call seccomp_phase2 before running the other hooks so that
@@ -268,6 +250,7 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 /* Called with IRQs disabled. */
 __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 {
+	struct thread_info *ti = pt_regs_to_thread_info(regs);
 	u32 cached_flags;
 
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled()))
@@ -275,12 +258,22 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 
 	lockdep_sys_exit();
 
-	cached_flags =
-		READ_ONCE(pt_regs_to_thread_info(regs)->flags);
+	cached_flags = READ_ONCE(ti->flags);
 
 	if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
 		exit_to_usermode_loop(regs, cached_flags);
 
+#ifdef CONFIG_COMPAT
+	/*
+	 * Compat syscalls set TS_COMPAT.  Make sure we clear it before
+	 * returning to user mode.  We need to clear it *after* signal
+	 * handling, because syscall restart has a fixup for compat
+	 * syscalls.  The fixup is exercised by the ptrace_syscall_32
+	 * selftest.
+	 */
+	ti->status &= ~TS_COMPAT;
+#endif
+
 	user_enter();
 }
 
@@ -332,33 +325,45 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs)
 	if (unlikely(cached_flags & SYSCALL_EXIT_WORK_FLAGS))
 		syscall_slow_exit_work(regs, cached_flags);
 
-#ifdef CONFIG_COMPAT
+	local_irq_disable();
+	prepare_exit_to_usermode(regs);
+}
+
+#ifdef CONFIG_X86_64
+__visible void do_syscall_64(struct pt_regs *regs)
+{
+	struct thread_info *ti = pt_regs_to_thread_info(regs);
+	unsigned long nr = regs->orig_ax;
+
+	enter_from_user_mode();
+	local_irq_enable();
+
+	if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY)
+		nr = syscall_trace_enter(regs);
+
 	/*
-	 * Compat syscalls set TS_COMPAT.  Make sure we clear it before
-	 * returning to user mode.
+	 * NB: Native and x32 syscalls are dispatched from the same
+	 * table.  The only functional difference is the x32 bit in
+	 * regs->orig_ax, which changes the behavior of some syscalls.
 	 */
-	ti->status &= ~TS_COMPAT;
-#endif
+	if (likely((nr & __SYSCALL_MASK) < NR_syscalls)) {
+		regs->ax = sys_call_table[nr & __SYSCALL_MASK](
+			regs->di, regs->si, regs->dx,
+			regs->r10, regs->r8, regs->r9);
+	}
 
-	local_irq_disable();
-	prepare_exit_to_usermode(regs);
+	syscall_return_slowpath(regs);
 }
+#endif
 
 #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
 /*
- * Does a 32-bit syscall.  Called with IRQs on and does all entry and
- * exit work and returns with IRQs off.  This function is extremely hot
- * in workloads that use it, and it's usually called from
+ * Does a 32-bit syscall.  Called with IRQs on in CONTEXT_KERNEL.  Does
+ * all entry and exit work and returns with IRQs off.  This function is
+ * extremely hot in workloads that use it, and it's usually called from
  * do_fast_syscall_32, so forcibly inline it to improve performance.
  */
-#ifdef CONFIG_X86_32
-/* 32-bit kernels use a trap gate for INT80, and the asm code calls here. */
-__visible
-#else
-/* 64-bit kernels use do_syscall_32_irqs_off() instead. */
-static
-#endif
-__always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
+static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
 {
 	struct thread_info *ti = pt_regs_to_thread_info(regs);
 	unsigned int nr = (unsigned int)regs->orig_ax;
@@ -393,14 +398,13 @@ __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
 	syscall_return_slowpath(regs);
 }
 
-#ifdef CONFIG_X86_64
-/* Handles INT80 on 64-bit kernels */
-__visible void do_syscall_32_irqs_off(struct pt_regs *regs)
+/* Handles int $0x80 */
+__visible void do_int80_syscall_32(struct pt_regs *regs)
 {
+	enter_from_user_mode();
 	local_irq_enable();
 	do_syscall_32_irqs_on(regs);
 }
-#endif
 
 /* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
 __visible long do_fast_syscall_32(struct pt_regs *regs)
@@ -420,12 +424,11 @@ __visible long do_fast_syscall_32(struct pt_regs *regs)
 	 */
 	regs->ip = landing_pad;
 
-	/*
-	 * Fetch EBP from where the vDSO stashed it.
-	 *
-	 * WARNING: We are in CONTEXT_USER and RCU isn't paying attention!
-	 */
+	enter_from_user_mode();
+
 	local_irq_enable();
+
+	/* Fetch EBP from where the vDSO stashed it. */
 	if (
 #ifdef CONFIG_X86_64
 		/*
@@ -443,9 +446,6 @@ __visible long do_fast_syscall_32(struct pt_regs *regs)
 		/* User code screwed up. */
 		local_irq_disable();
 		regs->ax = -EFAULT;
-#ifdef CONFIG_CONTEXT_TRACKING
-		enter_from_user_mode();
-#endif
 		prepare_exit_to_usermode(regs);
 		return 0;	/* Keep it simple: use IRET. */
 	}
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 77d8c5112900..10868aa734dc 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -40,7 +40,7 @@
 #include <asm/processor-flags.h>
 #include <asm/ftrace.h>
 #include <asm/irq_vectors.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
@@ -287,7 +287,58 @@ need_resched:
 END(resume_kernel)
 #endif
 
-	# SYSENTER  call handler stub
+GLOBAL(__begin_SYSENTER_singlestep_region)
+/*
+ * All code from here through __end_SYSENTER_singlestep_region is subject
+ * to being single-stepped if a user program sets TF and executes SYSENTER.
+ * There is absolutely nothing that we can do to prevent this from happening
+ * (thanks Intel!).  To keep our handling of this situation as simple as
+ * possible, we handle TF just like AC and NT, except that our #DB handler
+ * will ignore all of the single-step traps generated in this range.
+ */
+
+#ifdef CONFIG_XEN
+/*
+ * Xen doesn't set %esp to be precisely what the normal SYSENTER
+ * entry point expects, so fix it up before using the normal path.
+ */
+ENTRY(xen_sysenter_target)
+	addl	$5*4, %esp			/* remove xen-provided frame */
+	jmp	sysenter_past_esp
+#endif
+
+/*
+ * 32-bit SYSENTER entry.
+ *
+ * 32-bit system calls through the vDSO's __kernel_vsyscall enter here
+ * if X86_FEATURE_SEP is available.  This is the preferred system call
+ * entry on 32-bit systems.
+ *
+ * The SYSENTER instruction, in principle, should *only* occur in the
+ * vDSO.  In practice, a small number of Android devices were shipped
+ * with a copy of Bionic that inlined a SYSENTER instruction.  This
+ * never happened in any of Google's Bionic versions -- it only happened
+ * in a narrow range of Intel-provided versions.
+ *
+ * SYSENTER loads SS, ESP, CS, and EIP from previously programmed MSRs.
+ * IF and VM in RFLAGS are cleared (IOW: interrupts are off).
+ * SYSENTER does not save anything on the stack,
+ * and does not save old EIP (!!!), ESP, or EFLAGS.
+ *
+ * To avoid losing track of EFLAGS.VM (and thus potentially corrupting
+ * user and/or vm86 state), we explicitly disable the SYSENTER
+ * instruction in vm86 mode by reprogramming the MSRs.
+ *
+ * Arguments:
+ * eax  system call number
+ * ebx  arg1
+ * ecx  arg2
+ * edx  arg3
+ * esi  arg4
+ * edi  arg5
+ * ebp  user stack
+ * 0(%ebp) arg6
+ */
 ENTRY(entry_SYSENTER_32)
 	movl	TSS_sysenter_sp0(%esp), %esp
 sysenter_past_esp:
@@ -301,6 +352,29 @@ sysenter_past_esp:
 	SAVE_ALL pt_regs_ax=$-ENOSYS	/* save rest */
 
 	/*
+	 * SYSENTER doesn't filter flags, so we need to clear NT, AC
+	 * and TF ourselves.  To save a few cycles, we can check whether
+	 * either was set instead of doing an unconditional popfq.
+	 * This needs to happen before enabling interrupts so that
+	 * we don't get preempted with NT set.
+	 *
+	 * If TF is set, we will single-step all the way to here -- do_debug
+	 * will ignore all the traps.  (Yes, this is slow, but so is
+	 * single-stepping in general.  This allows us to avoid having
+	 * a more complicated code to handle the case where a user program
+	 * forces us to single-step through the SYSENTER entry code.)
+	 *
+	 * NB.: .Lsysenter_fix_flags is a label with the code under it moved
+	 * out-of-line as an optimization: NT is unlikely to be set in the
+	 * majority of the cases and instead of polluting the I$ unnecessarily,
+	 * we're keeping that code behind a branch which will predict as
+	 * not-taken and therefore its instructions won't be fetched.
+	 */
+	testl	$X86_EFLAGS_NT|X86_EFLAGS_AC|X86_EFLAGS_TF, PT_EFLAGS(%esp)
+	jnz	.Lsysenter_fix_flags
+.Lsysenter_flags_fixed:
+
+	/*
 	 * User mode is traced as though IRQs are on, and SYSENTER
 	 * turned them off.
 	 */
@@ -326,6 +400,15 @@ sysenter_past_esp:
 	popl	%eax			/* pt_regs->ax */
 
 	/*
+	 * Restore all flags except IF. (We restore IF separately because
+	 * STI gives a one-instruction window in which we won't be interrupted,
+	 * whereas POPF does not.)
+	 */
+	addl	$PT_EFLAGS-PT_DS, %esp	/* point esp at pt_regs->flags */
+	btr	$X86_EFLAGS_IF_BIT, (%esp)
+	popfl
+
+	/*
 	 * Return back to the vDSO, which will pop ecx and edx.
 	 * Don't bother with DS and ES (they already contain __USER_DS).
 	 */
@@ -338,28 +421,63 @@ sysenter_past_esp:
 .popsection
 	_ASM_EXTABLE(1b, 2b)
 	PTGS_TO_GS_EX
+
+.Lsysenter_fix_flags:
+	pushl	$X86_EFLAGS_FIXED
+	popfl
+	jmp	.Lsysenter_flags_fixed
+GLOBAL(__end_SYSENTER_singlestep_region)
 ENDPROC(entry_SYSENTER_32)
 
-	# system call handler stub
+/*
+ * 32-bit legacy system call entry.
+ *
+ * 32-bit x86 Linux system calls traditionally used the INT $0x80
+ * instruction.  INT $0x80 lands here.
+ *
+ * This entry point can be used by any 32-bit perform system calls.
+ * Instances of INT $0x80 can be found inline in various programs and
+ * libraries.  It is also used by the vDSO's __kernel_vsyscall
+ * fallback for hardware that doesn't support a faster entry method.
+ * Restarted 32-bit system calls also fall back to INT $0x80
+ * regardless of what instruction was originally used to do the system
+ * call.  (64-bit programs can use INT $0x80 as well, but they can
+ * only run on 64-bit kernels and therefore land in
+ * entry_INT80_compat.)
+ *
+ * This is considered a slow path.  It is not used by most libc
+ * implementations on modern hardware except during process startup.
+ *
+ * Arguments:
+ * eax  system call number
+ * ebx  arg1
+ * ecx  arg2
+ * edx  arg3
+ * esi  arg4
+ * edi  arg5
+ * ebp  arg6
+ */
 ENTRY(entry_INT80_32)
 	ASM_CLAC
 	pushl	%eax			/* pt_regs->orig_ax */
 	SAVE_ALL pt_regs_ax=$-ENOSYS	/* save rest */
 
 	/*
-	 * User mode is traced as though IRQs are on.  Unlike the 64-bit
-	 * case, INT80 is a trap gate on 32-bit kernels, so interrupts
-	 * are already on (unless user code is messing around with iopl).
+	 * User mode is traced as though IRQs are on, and the interrupt gate
+	 * turned them off.
 	 */
+	TRACE_IRQS_OFF
 
 	movl	%esp, %eax
-	call	do_syscall_32_irqs_on
+	call	do_int80_syscall_32
 .Lsyscall_32_done:
 
 restore_all:
 	TRACE_IRQS_IRET
 restore_all_notrace:
 #ifdef CONFIG_X86_ESPFIX32
+	ALTERNATIVE	"jmp restore_nocheck", "", X86_BUG_ESPFIX
+
 	movl	PT_EFLAGS(%esp), %eax		# mix EFLAGS, SS and CS
 	/*
 	 * Warning: PT_OLDSS(%esp) contains the wrong/random values if we
@@ -386,19 +504,6 @@ ENTRY(iret_exc	)
 
 #ifdef CONFIG_X86_ESPFIX32
 ldt_ss:
-#ifdef CONFIG_PARAVIRT
-	/*
-	 * The kernel can't run on a non-flat stack if paravirt mode
-	 * is active.  Rather than try to fixup the high bits of
-	 * ESP, bypass this code entirely.  This may break DOSemu
-	 * and/or Wine support in a paravirt VM, although the option
-	 * is still available to implement the setting of the high
-	 * 16-bits in the INTERRUPT_RETURN paravirt-op.
-	 */
-	cmpl	$0, pv_info+PARAVIRT_enabled
-	jne	restore_nocheck
-#endif
-
 /*
  * Setup and switch to ESPFIX stack
  *
@@ -631,14 +736,6 @@ ENTRY(spurious_interrupt_bug)
 END(spurious_interrupt_bug)
 
 #ifdef CONFIG_XEN
-/*
- * Xen doesn't set %esp to be precisely what the normal SYSENTER
- * entry point expects, so fix it up before using the normal path.
- */
-ENTRY(xen_sysenter_target)
-	addl	$5*4, %esp			/* remove xen-provided frame */
-	jmp	sysenter_past_esp
-
 ENTRY(xen_hypervisor_callback)
 	pushl	$-1				/* orig_ax = -1 => not a system call */
 	SAVE_ALL
@@ -938,51 +1035,48 @@ error_code:
 	jmp	ret_from_exception
 END(page_fault)
 
-/*
- * Debug traps and NMI can happen at the one SYSENTER instruction
- * that sets up the real kernel stack. Check here, since we can't
- * allow the wrong stack to be used.
- *
- * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have
- * already pushed 3 words if it hits on the sysenter instruction:
- * eflags, cs and eip.
- *
- * We just load the right stack, and push the three (known) values
- * by hand onto the new stack - while updating the return eip past
- * the instruction that would have done it for sysenter.
- */
-.macro FIX_STACK offset ok label
-	cmpw	$__KERNEL_CS, 4(%esp)
-	jne	\ok
-\label:
-	movl	TSS_sysenter_sp0 + \offset(%esp), %esp
-	pushfl
-	pushl	$__KERNEL_CS
-	pushl	$sysenter_past_esp
-.endm
-
 ENTRY(debug)
+	/*
+	 * #DB can happen at the first instruction of
+	 * entry_SYSENTER_32 or in Xen's SYSENTER prologue.  If this
+	 * happens, then we will be running on a very small stack.  We
+	 * need to detect this condition and switch to the thread
+	 * stack before calling any C code at all.
+	 *
+	 * If you edit this code, keep in mind that NMIs can happen in here.
+	 */
 	ASM_CLAC
-	cmpl	$entry_SYSENTER_32, (%esp)
-	jne	debug_stack_correct
-	FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn
-debug_stack_correct:
 	pushl	$-1				# mark this as an int
 	SAVE_ALL
-	TRACE_IRQS_OFF
 	xorl	%edx, %edx			# error code 0
 	movl	%esp, %eax			# pt_regs pointer
+
+	/* Are we currently on the SYSENTER stack? */
+	PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx)
+	subl	%eax, %ecx	/* ecx = (end of SYSENTER_stack) - esp */
+	cmpl	$SIZEOF_SYSENTER_stack, %ecx
+	jb	.Ldebug_from_sysenter_stack
+
+	TRACE_IRQS_OFF
+	call	do_debug
+	jmp	ret_from_exception
+
+.Ldebug_from_sysenter_stack:
+	/* We're on the SYSENTER stack.  Switch off. */
+	movl	%esp, %ebp
+	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esp
+	TRACE_IRQS_OFF
 	call	do_debug
+	movl	%ebp, %esp
 	jmp	ret_from_exception
 END(debug)
 
 /*
- * NMI is doubly nasty. It can happen _while_ we're handling
- * a debug fault, and the debug fault hasn't yet been able to
- * clear up the stack. So we first check whether we got  an
- * NMI on the sysenter entry path, but after that we need to
- * check whether we got an NMI on the debug path where the debug
- * fault happened on the sysenter path.
+ * NMI is doubly nasty.  It can happen on the first instruction of
+ * entry_SYSENTER_32 (just like #DB), but it can also interrupt the beginning
+ * of the #DB handler even if that #DB in turn hit before entry_SYSENTER_32
+ * switched stacks.  We handle both conditions by simply checking whether we
+ * interrupted kernel code running on the SYSENTER stack.
  */
 ENTRY(nmi)
 	ASM_CLAC
@@ -993,41 +1087,32 @@ ENTRY(nmi)
 	popl	%eax
 	je	nmi_espfix_stack
 #endif
-	cmpl	$entry_SYSENTER_32, (%esp)
-	je	nmi_stack_fixup
-	pushl	%eax
-	movl	%esp, %eax
-	/*
-	 * Do not access memory above the end of our stack page,
-	 * it might not exist.
-	 */
-	andl	$(THREAD_SIZE-1), %eax
-	cmpl	$(THREAD_SIZE-20), %eax
-	popl	%eax
-	jae	nmi_stack_correct
-	cmpl	$entry_SYSENTER_32, 12(%esp)
-	je	nmi_debug_stack_check
-nmi_stack_correct:
-	pushl	%eax
+
+	pushl	%eax				# pt_regs->orig_ax
 	SAVE_ALL
 	xorl	%edx, %edx			# zero error code
 	movl	%esp, %eax			# pt_regs pointer
+
+	/* Are we currently on the SYSENTER stack? */
+	PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx)
+	subl	%eax, %ecx	/* ecx = (end of SYSENTER_stack) - esp */
+	cmpl	$SIZEOF_SYSENTER_stack, %ecx
+	jb	.Lnmi_from_sysenter_stack
+
+	/* Not on SYSENTER stack. */
 	call	do_nmi
 	jmp	restore_all_notrace
 
-nmi_stack_fixup:
-	FIX_STACK 12, nmi_stack_correct, 1
-	jmp	nmi_stack_correct
-
-nmi_debug_stack_check:
-	cmpw	$__KERNEL_CS, 16(%esp)
-	jne	nmi_stack_correct
-	cmpl	$debug, (%esp)
-	jb	nmi_stack_correct
-	cmpl	$debug_esp_fix_insn, (%esp)
-	ja	nmi_stack_correct
-	FIX_STACK 24, nmi_stack_correct, 1
-	jmp	nmi_stack_correct
+.Lnmi_from_sysenter_stack:
+	/*
+	 * We're on the SYSENTER stack.  Switch off.  No one (not even debug)
+	 * is using the thread stack right now, so it's safe for us to use it.
+	 */
+	movl	%esp, %ebp
+	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esp
+	call	do_nmi
+	movl	%ebp, %esp
+	jmp	restore_all_notrace
 
 #ifdef CONFIG_X86_ESPFIX32
 nmi_espfix_stack:
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 9d34d3cfceb6..858b555e274b 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -103,6 +103,16 @@ ENDPROC(native_usergs_sysret64)
 /*
  * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers.
  *
+ * This is the only entry point used for 64-bit system calls.  The
+ * hardware interface is reasonably well designed and the register to
+ * argument mapping Linux uses fits well with the registers that are
+ * available when SYSCALL is used.
+ *
+ * SYSCALL instructions can be found inlined in libc implementations as
+ * well as some other programs and libraries.  There are also a handful
+ * of SYSCALL instructions in the vDSO used, for example, as a
+ * clock_gettimeofday fallback.
+ *
  * 64-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
  * then loads new ss, cs, and rip from previously programmed MSRs.
  * rflags gets masked by a value from another MSR (so CLD and CLAC
@@ -145,17 +155,11 @@ GLOBAL(entry_SYSCALL_64_after_swapgs)
 	movq	%rsp, PER_CPU_VAR(rsp_scratch)
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
+	TRACE_IRQS_OFF
+
 	/* Construct struct pt_regs on stack */
 	pushq	$__USER_DS			/* pt_regs->ss */
 	pushq	PER_CPU_VAR(rsp_scratch)	/* pt_regs->sp */
-	/*
-	 * Re-enable interrupts.
-	 * We use 'rsp_scratch' as a scratch space, hence irq-off block above
-	 * must execute atomically in the face of possible interrupt-driven
-	 * task preemption. We must enable interrupts only after we're done
-	 * with using rsp_scratch:
-	 */
-	ENABLE_INTERRUPTS(CLBR_NONE)
 	pushq	%r11				/* pt_regs->flags */
 	pushq	$__USER_CS			/* pt_regs->cs */
 	pushq	%rcx				/* pt_regs->ip */
@@ -171,9 +175,21 @@ GLOBAL(entry_SYSCALL_64_after_swapgs)
 	pushq	%r11				/* pt_regs->r11 */
 	sub	$(6*8), %rsp			/* pt_regs->bp, bx, r12-15 not saved */
 
-	testl	$_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz	tracesys
+	/*
+	 * If we need to do entry work or if we guess we'll need to do
+	 * exit work, go straight to the slow path.
+	 */
+	testl	$_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	entry_SYSCALL64_slow_path
+
 entry_SYSCALL_64_fastpath:
+	/*
+	 * Easy case: enable interrupts and issue the syscall.  If the syscall
+	 * needs pt_regs, we'll call a stub that disables interrupts again
+	 * and jumps to the slow path.
+	 */
+	TRACE_IRQS_ON
+	ENABLE_INTERRUPTS(CLBR_NONE)
 #if __SYSCALL_MASK == ~0
 	cmpq	$__NR_syscall_max, %rax
 #else
@@ -182,103 +198,56 @@ entry_SYSCALL_64_fastpath:
 #endif
 	ja	1f				/* return -ENOSYS (already in pt_regs->ax) */
 	movq	%r10, %rcx
+
+	/*
+	 * This call instruction is handled specially in stub_ptregs_64.
+	 * It might end up jumping to the slow path.  If it jumps, RAX
+	 * and all argument registers are clobbered.
+	 */
 	call	*sys_call_table(, %rax, 8)
+.Lentry_SYSCALL_64_after_fastpath_call:
+
 	movq	%rax, RAX(%rsp)
 1:
-/*
- * Syscall return path ending with SYSRET (fast path).
- * Has incompletely filled pt_regs.
- */
-	LOCKDEP_SYS_EXIT
-	/*
-	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
-	 * it is too small to ever cause noticeable irq latency.
-	 */
-	DISABLE_INTERRUPTS(CLBR_NONE)
 
 	/*
-	 * We must check ti flags with interrupts (or at least preemption)
-	 * off because we must *never* return to userspace without
-	 * processing exit work that is enqueued if we're preempted here.
-	 * In particular, returning to userspace with any of the one-shot
-	 * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is
-	 * very bad.
+	 * If we get here, then we know that pt_regs is clean for SYSRET64.
+	 * If we see that no exit work is required (which we are required
+	 * to check with IRQs off), then we can go straight to SYSRET64.
 	 */
+	DISABLE_INTERRUPTS(CLBR_NONE)
+	TRACE_IRQS_OFF
 	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz	int_ret_from_sys_call_irqs_off	/* Go to the slow path */
+	jnz	1f
 
-	RESTORE_C_REGS_EXCEPT_RCX_R11
+	LOCKDEP_SYS_EXIT
+	TRACE_IRQS_ON		/* user mode is traced as IRQs on */
 	movq	RIP(%rsp), %rcx
 	movq	EFLAGS(%rsp), %r11
+	RESTORE_C_REGS_EXCEPT_RCX_R11
 	movq	RSP(%rsp), %rsp
-	/*
-	 * 64-bit SYSRET restores rip from rcx,
-	 * rflags from r11 (but RF and VM bits are forced to 0),
-	 * cs and ss are loaded from MSRs.
-	 * Restoration of rflags re-enables interrupts.
-	 *
-	 * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
-	 * descriptor is not reinitialized.  This means that we should
-	 * avoid SYSRET with SS == NULL, which could happen if we schedule,
-	 * exit the kernel, and re-enter using an interrupt vector.  (All
-	 * interrupt entries on x86_64 set SS to NULL.)  We prevent that
-	 * from happening by reloading SS in __switch_to.  (Actually
-	 * detecting the failure in 64-bit userspace is tricky but can be
-	 * done.)
-	 */
 	USERGS_SYSRET64
 
-GLOBAL(int_ret_from_sys_call_irqs_off)
+1:
+	/*
+	 * The fast path looked good when we started, but something changed
+	 * along the way and we need to switch to the slow path.  Calling
+	 * raise(3) will trigger this, for example.  IRQs are off.
+	 */
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
-	jmp int_ret_from_sys_call
-
-	/* Do syscall entry tracing */
-tracesys:
-	movq	%rsp, %rdi
-	movl	$AUDIT_ARCH_X86_64, %esi
-	call	syscall_trace_enter_phase1
-	test	%rax, %rax
-	jnz	tracesys_phase2			/* if needed, run the slow path */
-	RESTORE_C_REGS_EXCEPT_RAX		/* else restore clobbered regs */
-	movq	ORIG_RAX(%rsp), %rax
-	jmp	entry_SYSCALL_64_fastpath	/* and return to the fast path */
-
-tracesys_phase2:
 	SAVE_EXTRA_REGS
 	movq	%rsp, %rdi
-	movl	$AUDIT_ARCH_X86_64, %esi
-	movq	%rax, %rdx
-	call	syscall_trace_enter_phase2
-
-	/*
-	 * Reload registers from stack in case ptrace changed them.
-	 * We don't reload %rax because syscall_trace_entry_phase2() returned
-	 * the value it wants us to use in the table lookup.
-	 */
-	RESTORE_C_REGS_EXCEPT_RAX
-	RESTORE_EXTRA_REGS
-#if __SYSCALL_MASK == ~0
-	cmpq	$__NR_syscall_max, %rax
-#else
-	andl	$__SYSCALL_MASK, %eax
-	cmpl	$__NR_syscall_max, %eax
-#endif
-	ja	1f				/* return -ENOSYS (already in pt_regs->ax) */
-	movq	%r10, %rcx			/* fixup for C */
-	call	*sys_call_table(, %rax, 8)
-	movq	%rax, RAX(%rsp)
-1:
-	/* Use IRET because user could have changed pt_regs->foo */
+	call	syscall_return_slowpath	/* returns with IRQs disabled */
+	jmp	return_from_SYSCALL_64
 
-/*
- * Syscall return path ending with IRET.
- * Has correct iret frame.
- */
-GLOBAL(int_ret_from_sys_call)
+entry_SYSCALL64_slow_path:
+	/* IRQs are off. */
 	SAVE_EXTRA_REGS
 	movq	%rsp, %rdi
-	call	syscall_return_slowpath	/* returns with IRQs disabled */
+	call	do_syscall_64		/* returns with IRQs disabled */
+
+return_from_SYSCALL_64:
 	RESTORE_EXTRA_REGS
 	TRACE_IRQS_IRETQ		/* we're about to change IF */
 
@@ -355,83 +324,45 @@ opportunistic_sysret_failed:
 	jmp	restore_c_regs_and_iret
 END(entry_SYSCALL_64)
 
+ENTRY(stub_ptregs_64)
+	/*
+	 * Syscalls marked as needing ptregs land here.
+	 * If we are on the fast path, we need to save the extra regs,
+	 * which we achieve by trying again on the slow path.  If we are on
+	 * the slow path, the extra regs are already saved.
+	 *
+	 * RAX stores a pointer to the C function implementing the syscall.
+	 * IRQs are on.
+	 */
+	cmpq	$.Lentry_SYSCALL_64_after_fastpath_call, (%rsp)
+	jne	1f
 
-	.macro FORK_LIKE func
-ENTRY(stub_\func)
-	SAVE_EXTRA_REGS 8
-	jmp	sys_\func
-END(stub_\func)
-	.endm
-
-	FORK_LIKE  clone
-	FORK_LIKE  fork
-	FORK_LIKE  vfork
-
-ENTRY(stub_execve)
-	call	sys_execve
-return_from_execve:
-	testl	%eax, %eax
-	jz	1f
-	/* exec failed, can use fast SYSRET code path in this case */
-	ret
-1:
-	/* must use IRET code path (pt_regs->cs may have changed) */
-	addq	$8, %rsp
-	ZERO_EXTRA_REGS
-	movq	%rax, RAX(%rsp)
-	jmp	int_ret_from_sys_call
-END(stub_execve)
-/*
- * Remaining execve stubs are only 7 bytes long.
- * ENTRY() often aligns to 16 bytes, which in this case has no benefits.
- */
-	.align	8
-GLOBAL(stub_execveat)
-	call	sys_execveat
-	jmp	return_from_execve
-END(stub_execveat)
-
-#if defined(CONFIG_X86_X32_ABI)
-	.align	8
-GLOBAL(stub_x32_execve)
-	call	compat_sys_execve
-	jmp	return_from_execve
-END(stub_x32_execve)
-	.align	8
-GLOBAL(stub_x32_execveat)
-	call	compat_sys_execveat
-	jmp	return_from_execve
-END(stub_x32_execveat)
-#endif
-
-/*
- * sigreturn is special because it needs to restore all registers on return.
- * This cannot be done with SYSRET, so use the IRET return path instead.
- */
-ENTRY(stub_rt_sigreturn)
 	/*
-	 * SAVE_EXTRA_REGS result is not normally needed:
-	 * sigreturn overwrites all pt_regs->GPREGS.
-	 * But sigreturn can fail (!), and there is no easy way to detect that.
-	 * To make sure RESTORE_EXTRA_REGS doesn't restore garbage on error,
-	 * we SAVE_EXTRA_REGS here.
+	 * Called from fast path -- disable IRQs again, pop return address
+	 * and jump to slow path
 	 */
-	SAVE_EXTRA_REGS 8
-	call	sys_rt_sigreturn
-return_from_stub:
-	addq	$8, %rsp
-	RESTORE_EXTRA_REGS
-	movq	%rax, RAX(%rsp)
-	jmp	int_ret_from_sys_call
-END(stub_rt_sigreturn)
+	DISABLE_INTERRUPTS(CLBR_NONE)
+	TRACE_IRQS_OFF
+	popq	%rax
+	jmp	entry_SYSCALL64_slow_path
 
-#ifdef CONFIG_X86_X32_ABI
-ENTRY(stub_x32_rt_sigreturn)
-	SAVE_EXTRA_REGS 8
-	call	sys32_x32_rt_sigreturn
-	jmp	return_from_stub
-END(stub_x32_rt_sigreturn)
-#endif
+1:
+	/* Called from C */
+	jmp	*%rax				/* called from C */
+END(stub_ptregs_64)
+
+.macro ptregs_stub func
+ENTRY(ptregs_\func)
+	leaq	\func(%rip), %rax
+	jmp	stub_ptregs_64
+END(ptregs_\func)
+.endm
+
+/* Instantiate ptregs_stub for each ptregs-using syscall */
+#define __SYSCALL_64_QUAL_(sym)
+#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_stub sym
+#define __SYSCALL_64(nr, sym, qual) __SYSCALL_64_QUAL_##qual(sym)
+#include <asm/syscalls_64.h>
 
 /*
  * A newly forked process directly context switches into this address.
@@ -439,7 +370,6 @@ END(stub_x32_rt_sigreturn)
  * rdi: prev task we switched from
  */
 ENTRY(ret_from_fork)
-
 	LOCK ; btr $TIF_FORK, TI_flags(%r8)
 
 	pushq	$0x0002
@@ -447,28 +377,32 @@ ENTRY(ret_from_fork)
 
 	call	schedule_tail			/* rdi: 'prev' task parameter */
 
-	RESTORE_EXTRA_REGS
-
 	testb	$3, CS(%rsp)			/* from kernel_thread? */
+	jnz	1f
 
 	/*
-	 * By the time we get here, we have no idea whether our pt_regs,
-	 * ti flags, and ti status came from the 64-bit SYSCALL fast path,
-	 * the slow path, or one of the 32-bit compat paths.
-	 * Use IRET code path to return, since it can safely handle
-	 * all of the above.
+	 * We came from kernel_thread.  This code path is quite twisted, and
+	 * someone should clean it up.
+	 *
+	 * copy_thread_tls stashes the function pointer in RBX and the
+	 * parameter to be passed in RBP.  The called function is permitted
+	 * to call do_execve and thereby jump to user mode.
 	 */
-	jnz	int_ret_from_sys_call
+	movq	RBP(%rsp), %rdi
+	call	*RBX(%rsp)
+	movl	$0, RAX(%rsp)
 
 	/*
-	 * We came from kernel_thread
-	 * nb: we depend on RESTORE_EXTRA_REGS above
+	 * Fall through as though we're exiting a syscall.  This makes a
+	 * twisted sort of sense if we just called do_execve.
 	 */
-	movq	%rbp, %rdi
-	call	*%rbx
-	movl	$0, RAX(%rsp)
-	RESTORE_EXTRA_REGS
-	jmp	int_ret_from_sys_call
+
+1:
+	movq	%rsp, %rdi
+	call	syscall_return_slowpath	/* returns with IRQs disabled */
+	TRACE_IRQS_ON			/* user mode is traced as IRQS on */
+	SWAPGS
+	jmp	restore_regs_and_iret
 END(ret_from_fork)
 
 /*
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index ff1c6d61f332..847f2f0c31e5 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -19,12 +19,21 @@
 	.section .entry.text, "ax"
 
 /*
- * 32-bit SYSENTER instruction entry.
+ * 32-bit SYSENTER entry.
  *
- * SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs.
- * IF and VM in rflags are cleared (IOW: interrupts are off).
+ * 32-bit system calls through the vDSO's __kernel_vsyscall enter here
+ * on 64-bit kernels running on Intel CPUs.
+ *
+ * The SYSENTER instruction, in principle, should *only* occur in the
+ * vDSO.  In practice, a small number of Android devices were shipped
+ * with a copy of Bionic that inlined a SYSENTER instruction.  This
+ * never happened in any of Google's Bionic versions -- it only happened
+ * in a narrow range of Intel-provided versions.
+ *
+ * SYSENTER loads SS, RSP, CS, and RIP from previously programmed MSRs.
+ * IF and VM in RFLAGS are cleared (IOW: interrupts are off).
  * SYSENTER does not save anything on the stack,
- * and does not save old rip (!!!) and rflags.
+ * and does not save old RIP (!!!), RSP, or RFLAGS.
  *
  * Arguments:
  * eax  system call number
@@ -35,10 +44,6 @@
  * edi  arg5
  * ebp  user stack
  * 0(%ebp) arg6
- *
- * This is purely a fast path. For anything complicated we use the int 0x80
- * path below. We set up a complete hardware stack frame to share code
- * with the int 0x80 path.
  */
 ENTRY(entry_SYSENTER_compat)
 	/* Interrupts are off on entry. */
@@ -66,8 +71,6 @@ ENTRY(entry_SYSENTER_compat)
 	 */
 	pushfq				/* pt_regs->flags (except IF = 0) */
 	orl	$X86_EFLAGS_IF, (%rsp)	/* Fix saved flags */
-	ASM_CLAC			/* Clear AC after saving FLAGS */
-
 	pushq	$__USER32_CS		/* pt_regs->cs */
 	xorq    %r8,%r8
 	pushq	%r8			/* pt_regs->ip = 0 (placeholder) */
@@ -90,19 +93,25 @@ ENTRY(entry_SYSENTER_compat)
 	cld
 
 	/*
-	 * Sysenter doesn't filter flags, so we need to clear NT
+	 * SYSENTER doesn't filter flags, so we need to clear NT and AC
 	 * ourselves.  To save a few cycles, we can check whether
-	 * NT was set instead of doing an unconditional popfq.
+	 * either was set instead of doing an unconditional popfq.
 	 * This needs to happen before enabling interrupts so that
 	 * we don't get preempted with NT set.
 	 *
+	 * If TF is set, we will single-step all the way to here -- do_debug
+	 * will ignore all the traps.  (Yes, this is slow, but so is
+	 * single-stepping in general.  This allows us to avoid having
+	 * a more complicated code to handle the case where a user program
+	 * forces us to single-step through the SYSENTER entry code.)
+	 *
 	 * NB.: .Lsysenter_fix_flags is a label with the code under it moved
 	 * out-of-line as an optimization: NT is unlikely to be set in the
 	 * majority of the cases and instead of polluting the I$ unnecessarily,
 	 * we're keeping that code behind a branch which will predict as
 	 * not-taken and therefore its instructions won't be fetched.
 	 */
-	testl	$X86_EFLAGS_NT, EFLAGS(%rsp)
+	testl	$X86_EFLAGS_NT|X86_EFLAGS_AC|X86_EFLAGS_TF, EFLAGS(%rsp)
 	jnz	.Lsysenter_fix_flags
 .Lsysenter_flags_fixed:
 
@@ -123,20 +132,42 @@ ENTRY(entry_SYSENTER_compat)
 	pushq	$X86_EFLAGS_FIXED
 	popfq
 	jmp	.Lsysenter_flags_fixed
+GLOBAL(__end_entry_SYSENTER_compat)
 ENDPROC(entry_SYSENTER_compat)
 
 /*
- * 32-bit SYSCALL instruction entry.
+ * 32-bit SYSCALL entry.
+ *
+ * 32-bit system calls through the vDSO's __kernel_vsyscall enter here
+ * on 64-bit kernels running on AMD CPUs.
+ *
+ * The SYSCALL instruction, in principle, should *only* occur in the
+ * vDSO.  In practice, it appears that this really is the case.
+ * As evidence:
+ *
+ *  - The calling convention for SYSCALL has changed several times without
+ *    anyone noticing.
  *
- * 32-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
- * then loads new ss, cs, and rip from previously programmed MSRs.
- * rflags gets masked by a value from another MSR (so CLD and CLAC
- * are not needed). SYSCALL does not save anything on the stack
- * and does not change rsp.
+ *  - Prior to the in-kernel X86_BUG_SYSRET_SS_ATTRS fixup, anything
+ *    user task that did SYSCALL without immediately reloading SS
+ *    would randomly crash.
  *
- * Note: rflags saving+masking-with-MSR happens only in Long mode
+ *  - Most programmers do not directly target AMD CPUs, and the 32-bit
+ *    SYSCALL instruction does not exist on Intel CPUs.  Even on AMD
+ *    CPUs, Linux disables the SYSCALL instruction on 32-bit kernels
+ *    because the SYSCALL instruction in legacy/native 32-bit mode (as
+ *    opposed to compat mode) is sufficiently poorly designed as to be
+ *    essentially unusable.
+ *
+ * 32-bit SYSCALL saves RIP to RCX, clears RFLAGS.RF, then saves
+ * RFLAGS to R11, then loads new SS, CS, and RIP from previously
+ * programmed MSRs.  RFLAGS gets masked by a value from another MSR
+ * (so CLD and CLAC are not needed).  SYSCALL does not save anything on
+ * the stack and does not change RSP.
+ *
+ * Note: RFLAGS saving+masking-with-MSR happens only in Long mode
  * (in legacy 32-bit mode, IF, RF and VM bits are cleared and that's it).
- * Don't get confused: rflags saving+masking depends on Long Mode Active bit
+ * Don't get confused: RFLAGS saving+masking depends on Long Mode Active bit
  * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes
  * or target CS descriptor's L bit (SYSCALL does not read segment descriptors).
  *
@@ -236,7 +267,21 @@ sysret32_from_system_call:
 END(entry_SYSCALL_compat)
 
 /*
- * Emulated IA32 system calls via int 0x80.
+ * 32-bit legacy system call entry.
+ *
+ * 32-bit x86 Linux system calls traditionally used the INT $0x80
+ * instruction.  INT $0x80 lands here.
+ *
+ * This entry point can be used by 32-bit and 64-bit programs to perform
+ * 32-bit system calls.  Instances of INT $0x80 can be found inline in
+ * various programs and libraries.  It is also used by the vDSO's
+ * __kernel_vsyscall fallback for hardware that doesn't support a faster
+ * entry method.  Restarted 32-bit system calls also fall back to INT
+ * $0x80 regardless of what instruction was originally used to do the
+ * system call.
+ *
+ * This is considered a slow path.  It is not used by most libc
+ * implementations on modern hardware except during process startup.
  *
  * Arguments:
  * eax  system call number
@@ -245,22 +290,14 @@ END(entry_SYSCALL_compat)
  * edx  arg3
  * esi  arg4
  * edi  arg5
- * ebp  arg6	(note: not saved in the stack frame, should not be touched)
- *
- * Notes:
- * Uses the same stack frame as the x86-64 version.
- * All registers except eax must be saved (but ptrace may violate that).
- * Arguments are zero extended. For system calls that want sign extension and
- * take long arguments a wrapper is needed. Most calls can just be called
- * directly.
- * Assumes it is only called from user space and entered with interrupts off.
+ * ebp  arg6
  */
-
 ENTRY(entry_INT80_compat)
 	/*
 	 * Interrupts are off on entry.
 	 */
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
+	ASM_CLAC			/* Do this early to minimize exposure */
 	SWAPGS
 
 	/*
@@ -299,7 +336,7 @@ ENTRY(entry_INT80_compat)
 	TRACE_IRQS_OFF
 
 	movq	%rsp, %rdi
-	call	do_syscall_32_irqs_off
+	call	do_int80_syscall_32
 .Lsyscall_32_done:
 
 	/* Go back to user mode. */
diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c
index 9a6649857106..8f895ee13a1c 100644
--- a/arch/x86/entry/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -6,17 +6,11 @@
 #include <asm/asm-offsets.h>
 #include <asm/syscall.h>
 
-#ifdef CONFIG_IA32_EMULATION
-#define SYM(sym, compat) compat
-#else
-#define SYM(sym, compat) sym
-#endif
-
-#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage long SYM(sym, compat)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
+#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
 #include <asm/syscalls_32.h>
 #undef __SYSCALL_I386
 
-#define __SYSCALL_I386(nr, sym, compat) [nr] = SYM(sym, compat),
+#define __SYSCALL_I386(nr, sym, qual) [nr] = sym,
 
 extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
index 41283d22be7a..9dbc5abb6162 100644
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -6,19 +6,14 @@
 #include <asm/asm-offsets.h>
 #include <asm/syscall.h>
 
-#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
+#define __SYSCALL_64_QUAL_(sym) sym
+#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_##sym
 
-#ifdef CONFIG_X86_X32_ABI
-# define __SYSCALL_X32(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
-#else
-# define __SYSCALL_X32(nr, sym, compat) /* nothing */
-#endif
-
-#define __SYSCALL_64(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
+#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long __SYSCALL_64_QUAL_##qual(sym)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 #include <asm/syscalls_64.h>
 #undef __SYSCALL_64
 
-#define __SYSCALL_64(nr, sym, compat) [nr] = sym,
+#define __SYSCALL_64(nr, sym, qual) [nr] = __SYSCALL_64_QUAL_##qual(sym),
 
 extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index dc1040a50bdc..2e5b565adacc 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -21,7 +21,7 @@
 12	common	brk			sys_brk
 13	64	rt_sigaction		sys_rt_sigaction
 14	common	rt_sigprocmask		sys_rt_sigprocmask
-15	64	rt_sigreturn		stub_rt_sigreturn
+15	64	rt_sigreturn		sys_rt_sigreturn/ptregs
 16	64	ioctl			sys_ioctl
 17	common	pread64			sys_pread64
 18	common	pwrite64		sys_pwrite64
@@ -62,10 +62,10 @@
 53	common	socketpair		sys_socketpair
 54	64	setsockopt		sys_setsockopt
 55	64	getsockopt		sys_getsockopt
-56	common	clone			stub_clone
-57	common	fork			stub_fork
-58	common	vfork			stub_vfork
-59	64	execve			stub_execve
+56	common	clone			sys_clone/ptregs
+57	common	fork			sys_fork/ptregs
+58	common	vfork			sys_vfork/ptregs
+59	64	execve			sys_execve/ptregs
 60	common	exit			sys_exit
 61	common	wait4			sys_wait4
 62	common	kill			sys_kill
@@ -178,7 +178,7 @@
 169	common	reboot			sys_reboot
 170	common	sethostname		sys_sethostname
 171	common	setdomainname		sys_setdomainname
-172	common	iopl			sys_iopl
+172	common	iopl			sys_iopl/ptregs
 173	common	ioperm			sys_ioperm
 174	64	create_module
 175	common	init_module		sys_init_module
@@ -328,7 +328,7 @@
 319	common	memfd_create		sys_memfd_create
 320	common	kexec_file_load		sys_kexec_file_load
 321	common	bpf			sys_bpf
-322	64	execveat		stub_execveat
+322	64	execveat		sys_execveat/ptregs
 323	common	userfaultfd		sys_userfaultfd
 324	common	membarrier		sys_membarrier
 325	common	mlock2			sys_mlock2
@@ -339,14 +339,14 @@
 # for native 64-bit operation.
 #
 512	x32	rt_sigaction		compat_sys_rt_sigaction
-513	x32	rt_sigreturn		stub_x32_rt_sigreturn
+513	x32	rt_sigreturn		sys32_x32_rt_sigreturn
 514	x32	ioctl			compat_sys_ioctl
 515	x32	readv			compat_sys_readv
 516	x32	writev			compat_sys_writev
 517	x32	recvfrom		compat_sys_recvfrom
 518	x32	sendmsg			compat_sys_sendmsg
 519	x32	recvmsg			compat_sys_recvmsg
-520	x32	execve			stub_x32_execve
+520	x32	execve			compat_sys_execve/ptregs
 521	x32	ptrace			compat_sys_ptrace
 522	x32	rt_sigpending		compat_sys_rt_sigpending
 523	x32	rt_sigtimedwait		compat_sys_rt_sigtimedwait
@@ -371,4 +371,4 @@
 542	x32	getsockopt		compat_sys_getsockopt
 543	x32	io_setup		compat_sys_io_setup
 544	x32	io_submit		compat_sys_io_submit
-545	x32	execveat		stub_x32_execveat
+545	x32	execveat		compat_sys_execveat/ptregs
diff --git a/arch/x86/entry/syscalls/syscalltbl.sh b/arch/x86/entry/syscalls/syscalltbl.sh
index 0e7f8ec071e7..cd3d3015d7df 100644
--- a/arch/x86/entry/syscalls/syscalltbl.sh
+++ b/arch/x86/entry/syscalls/syscalltbl.sh
@@ -3,13 +3,63 @@
 in="$1"
 out="$2"
 
+syscall_macro() {
+    abi="$1"
+    nr="$2"
+    entry="$3"
+
+    # Entry can be either just a function name or "function/qualifier"
+    real_entry="${entry%%/*}"
+    qualifier="${entry:${#real_entry}}"		# Strip the function name
+    qualifier="${qualifier:1}"			# Strip the slash, if any
+
+    echo "__SYSCALL_${abi}($nr, $real_entry, $qualifier)"
+}
+
+emit() {
+    abi="$1"
+    nr="$2"
+    entry="$3"
+    compat="$4"
+
+    if [ "$abi" == "64" -a -n "$compat" ]; then
+	echo "a compat entry for a 64-bit syscall makes no sense" >&2
+	exit 1
+    fi
+
+    if [ -z "$compat" ]; then
+	if [ -n "$entry" ]; then
+	    syscall_macro "$abi" "$nr" "$entry"
+	fi
+    else
+	echo "#ifdef CONFIG_X86_32"
+	if [ -n "$entry" ]; then
+	    syscall_macro "$abi" "$nr" "$entry"
+	fi
+	echo "#else"
+	syscall_macro "$abi" "$nr" "$compat"
+	echo "#endif"
+    fi
+}
+
 grep '^[0-9]' "$in" | sort -n | (
     while read nr abi name entry compat; do
 	abi=`echo "$abi" | tr '[a-z]' '[A-Z]'`
-	if [ -n "$compat" ]; then
-	    echo "__SYSCALL_${abi}($nr, $entry, $compat)"
-	elif [ -n "$entry" ]; then
-	    echo "__SYSCALL_${abi}($nr, $entry, $entry)"
+	if [ "$abi" == "COMMON" -o "$abi" == "64" ]; then
+	    # COMMON is the same as 64, except that we don't expect X32
+	    # programs to use it.  Our expectation has nothing to do with
+	    # any generated code, so treat them the same.
+	    emit 64 "$nr" "$entry" "$compat"
+	elif [ "$abi" == "X32" ]; then
+	    # X32 is equivalent to 64 on an X32-compatible kernel.
+	    echo "#ifdef CONFIG_X86_X32_ABI"
+	    emit 64 "$nr" "$entry" "$compat"
+	    echo "#endif"
+	elif [ "$abi" == "I386" ]; then
+	    emit "$abi" "$nr" "$entry" "$compat"
+	else
+	    echo "Unknown abi $abi" >&2
+	    exit 1
 	fi
     done
 ) > "$out"
diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h
index 0224987556ce..63a03bb91497 100644
--- a/arch/x86/entry/vdso/vdso2c.h
+++ b/arch/x86/entry/vdso/vdso2c.h
@@ -140,7 +140,7 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 	fprintf(outfile, "#include <asm/vdso.h>\n");
 	fprintf(outfile, "\n");
 	fprintf(outfile,
-		"static unsigned char raw_data[%lu] __page_aligned_data = {",
+		"static unsigned char raw_data[%lu] __ro_after_init __aligned(PAGE_SIZE) = {",
 		mapping_size);
 	for (j = 0; j < stripped_len; j++) {
 		if (j % 10 == 0)
@@ -150,16 +150,9 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 	}
 	fprintf(outfile, "\n};\n\n");
 
-	fprintf(outfile, "static struct page *pages[%lu];\n\n",
-		mapping_size / 4096);
-
 	fprintf(outfile, "const struct vdso_image %s = {\n", name);
 	fprintf(outfile, "\t.data = raw_data,\n");
 	fprintf(outfile, "\t.size = %lu,\n", mapping_size);
-	fprintf(outfile, "\t.text_mapping = {\n");
-	fprintf(outfile, "\t\t.name = \"[vdso]\",\n");
-	fprintf(outfile, "\t\t.pages = pages,\n");
-	fprintf(outfile, "\t},\n");
 	if (alt_sec) {
 		fprintf(outfile, "\t.alt = %lu,\n",
 			(unsigned long)GET_LE(&alt_sec->sh_offset));
diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index 08a317a9ae4b..7853b53959cd 100644
--- a/arch/x86/entry/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
@@ -11,7 +11,6 @@
 #include <linux/kernel.h>
 #include <linux/mm_types.h>
 
-#include <asm/cpufeature.h>
 #include <asm/processor.h>
 #include <asm/vdso.h>
 
diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S
index 3a1d9297074b..0109ac6cb79c 100644
--- a/arch/x86/entry/vdso/vdso32/system_call.S
+++ b/arch/x86/entry/vdso/vdso32/system_call.S
@@ -3,7 +3,7 @@
 */
 
 #include <asm/dwarf2.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 /*
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index b8f69e264ac4..10f704584922 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -20,6 +20,7 @@
 #include <asm/page.h>
 #include <asm/hpet.h>
 #include <asm/desc.h>
+#include <asm/cpufeature.h>
 
 #if defined(CONFIG_X86_64)
 unsigned int __read_mostly vdso64_enabled = 1;
@@ -27,13 +28,7 @@ unsigned int __read_mostly vdso64_enabled = 1;
 
 void __init init_vdso_image(const struct vdso_image *image)
 {
-	int i;
-	int npages = (image->size) / PAGE_SIZE;
-
 	BUG_ON(image->size % PAGE_SIZE != 0);
-	for (i = 0; i < npages; i++)
-		image->text_mapping.pages[i] =
-			virt_to_page(image->data + i*PAGE_SIZE);
 
 	apply_alternatives((struct alt_instr *)(image->data + image->alt),
 			   (struct alt_instr *)(image->data + image->alt +
@@ -90,18 +85,87 @@ static unsigned long vdso_addr(unsigned long start, unsigned len)
 #endif
 }
 
+static int vdso_fault(const struct vm_special_mapping *sm,
+		      struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	const struct vdso_image *image = vma->vm_mm->context.vdso_image;
+
+	if (!image || (vmf->pgoff << PAGE_SHIFT) >= image->size)
+		return VM_FAULT_SIGBUS;
+
+	vmf->page = virt_to_page(image->data + (vmf->pgoff << PAGE_SHIFT));
+	get_page(vmf->page);
+	return 0;
+}
+
+static const struct vm_special_mapping text_mapping = {
+	.name = "[vdso]",
+	.fault = vdso_fault,
+};
+
+static int vvar_fault(const struct vm_special_mapping *sm,
+		      struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	const struct vdso_image *image = vma->vm_mm->context.vdso_image;
+	long sym_offset;
+	int ret = -EFAULT;
+
+	if (!image)
+		return VM_FAULT_SIGBUS;
+
+	sym_offset = (long)(vmf->pgoff << PAGE_SHIFT) +
+		image->sym_vvar_start;
+
+	/*
+	 * Sanity check: a symbol offset of zero means that the page
+	 * does not exist for this vdso image, not that the page is at
+	 * offset zero relative to the text mapping.  This should be
+	 * impossible here, because sym_offset should only be zero for
+	 * the page past the end of the vvar mapping.
+	 */
+	if (sym_offset == 0)
+		return VM_FAULT_SIGBUS;
+
+	if (sym_offset == image->sym_vvar_page) {
+		ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address,
+				    __pa_symbol(&__vvar_page) >> PAGE_SHIFT);
+	} else if (sym_offset == image->sym_hpet_page) {
+#ifdef CONFIG_HPET_TIMER
+		if (hpet_address && vclock_was_used(VCLOCK_HPET)) {
+			ret = vm_insert_pfn_prot(
+				vma,
+				(unsigned long)vmf->virtual_address,
+				hpet_address >> PAGE_SHIFT,
+				pgprot_noncached(PAGE_READONLY));
+		}
+#endif
+	} else if (sym_offset == image->sym_pvclock_page) {
+		struct pvclock_vsyscall_time_info *pvti =
+			pvclock_pvti_cpu0_va();
+		if (pvti && vclock_was_used(VCLOCK_PVCLOCK)) {
+			ret = vm_insert_pfn(
+				vma,
+				(unsigned long)vmf->virtual_address,
+				__pa(pvti) >> PAGE_SHIFT);
+		}
+	}
+
+	if (ret == 0 || ret == -EBUSY)
+		return VM_FAULT_NOPAGE;
+
+	return VM_FAULT_SIGBUS;
+}
+
 static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned long addr, text_start;
 	int ret = 0;
-	static struct page *no_pages[] = {NULL};
-	static struct vm_special_mapping vvar_mapping = {
+	static const struct vm_special_mapping vvar_mapping = {
 		.name = "[vvar]",
-		.pages = no_pages,
+		.fault = vvar_fault,
 	};
-	struct pvclock_vsyscall_time_info *pvti;
 
 	if (calculate_addr) {
 		addr = vdso_addr(current->mm->start_stack,
@@ -121,6 +185,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 
 	text_start = addr - image->sym_vvar_start;
 	current->mm->context.vdso = (void __user *)text_start;
+	current->mm->context.vdso_image = image;
 
 	/*
 	 * MAYWRITE to allow gdb to COW and set breakpoints
@@ -130,7 +195,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 				       image->size,
 				       VM_READ|VM_EXEC|
 				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-				       &image->text_mapping);
+				       &text_mapping);
 
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
@@ -140,7 +205,8 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 	vma = _install_special_mapping(mm,
 				       addr,
 				       -image->sym_vvar_start,
-				       VM_READ|VM_MAYREAD,
+				       VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
+				       VM_PFNMAP,
 				       &vvar_mapping);
 
 	if (IS_ERR(vma)) {
@@ -148,41 +214,6 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 		goto up_fail;
 	}
 
-	if (image->sym_vvar_page)
-		ret = remap_pfn_range(vma,
-				      text_start + image->sym_vvar_page,
-				      __pa_symbol(&__vvar_page) >> PAGE_SHIFT,
-				      PAGE_SIZE,
-				      PAGE_READONLY);
-
-	if (ret)
-		goto up_fail;
-
-#ifdef CONFIG_HPET_TIMER
-	if (hpet_address && image->sym_hpet_page) {
-		ret = io_remap_pfn_range(vma,
-			text_start + image->sym_hpet_page,
-			hpet_address >> PAGE_SHIFT,
-			PAGE_SIZE,
-			pgprot_noncached(PAGE_READONLY));
-
-		if (ret)
-			goto up_fail;
-	}
-#endif
-
-	pvti = pvclock_pvti_cpu0_va();
-	if (pvti && image->sym_pvclock_page) {
-		ret = remap_pfn_range(vma,
-				      text_start + image->sym_pvclock_page,
-				      __pa(pvti) >> PAGE_SHIFT,
-				      PAGE_SIZE,
-				      PAGE_READONLY);
-
-		if (ret)
-			goto up_fail;
-	}
-
 up_fail:
 	if (ret)
 		current->mm->context.vdso = NULL;
@@ -254,7 +285,7 @@ static void vgetcpu_cpu_init(void *arg)
 #ifdef CONFIG_NUMA
 	node = cpu_to_node(cpu);
 #endif
-	if (cpu_has(&cpu_data(cpu), X86_FEATURE_RDTSCP))
+	if (static_cpu_has(X86_FEATURE_RDTSCP))
 		write_rdtscp_aux((node << 12) | cpu);
 
 	/*
diff --git a/arch/x86/entry/vsyscall/vsyscall_gtod.c b/arch/x86/entry/vsyscall/vsyscall_gtod.c
index 51e330416995..0fb3a104ac62 100644
--- a/arch/x86/entry/vsyscall/vsyscall_gtod.c
+++ b/arch/x86/entry/vsyscall/vsyscall_gtod.c
@@ -16,6 +16,8 @@
 #include <asm/vgtod.h>
 #include <asm/vvar.h>
 
+int vclocks_used __read_mostly;
+
 DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);
 
 void update_vsyscall_tz(void)
@@ -26,12 +28,17 @@ void update_vsyscall_tz(void)
 
 void update_vsyscall(struct timekeeper *tk)
 {
+	int vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode;
 	struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data;
 
+	/* Mark the new vclock used. */
+	BUILD_BUG_ON(VCLOCK_MAX >= 32);
+	WRITE_ONCE(vclocks_used, READ_ONCE(vclocks_used) | (1 << vclock_mode));
+
 	gtod_write_begin(vdata);
 
 	/* copy vsyscall data */
-	vdata->vclock_mode	= tk->tkr_mono.clock->archdata.vclock_mode;
+	vdata->vclock_mode	= vclock_mode;
 	vdata->cycle_last	= tk->tkr_mono.cycle_last;
 	vdata->mask		= tk->tkr_mono.mask;
 	vdata->mult		= tk->tkr_mono.mult;
diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile
new file mode 100644
index 000000000000..fdfea1511cc0
--- /dev/null
+++ b/arch/x86/events/Makefile
@@ -0,0 +1,13 @@
+obj-y			+= core.o
+
+obj-$(CONFIG_CPU_SUP_AMD)               += amd/core.o amd/uncore.o
+obj-$(CONFIG_X86_LOCAL_APIC)            += amd/ibs.o msr.o
+ifdef CONFIG_AMD_IOMMU
+obj-$(CONFIG_CPU_SUP_AMD)               += amd/iommu.o
+endif
+obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/core.o intel/bts.o intel/cqm.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/cstate.o intel/ds.o intel/knc.o 
+obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/lbr.o intel/p4.o intel/p6.o intel/pt.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/rapl.o msr.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= intel/uncore.o intel/uncore_nhmex.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= intel/uncore_snb.o intel/uncore_snbep.o
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/events/amd/core.c
index 58610539b048..049ada8d4e9c 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/events/amd/core.c
@@ -5,7 +5,7 @@
 #include <linux/slab.h>
 #include <asm/apicdef.h>
 
-#include "perf_event.h"
+#include "../perf_event.h"
 
 static __initconst const u64 amd_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/events/amd/ibs.c
index 989d3c215d2b..51087c29b2c2 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -14,7 +14,7 @@
 
 #include <asm/apic.h>
 
-#include "perf_event.h"
+#include "../perf_event.h"
 
 static u32 ibs_caps;
 
@@ -670,7 +670,7 @@ static __init int perf_event_ibs_init(void)
 	perf_ibs_pmu_init(&perf_ibs_op, "ibs_op");
 
 	register_nmi_handler(NMI_LOCAL, perf_ibs_nmi_handler, 0, "perf_ibs");
-	printk(KERN_INFO "perf: AMD IBS detected (0x%08x)\n", ibs_caps);
+	pr_info("perf: AMD IBS detected (0x%08x)\n", ibs_caps);
 
 	return 0;
 }
@@ -774,14 +774,14 @@ static int setup_ibs_ctl(int ibs_eilvt_off)
 		pci_read_config_dword(cpu_cfg, IBSCTL, &value);
 		if (value != (ibs_eilvt_off | IBSCTL_LVT_OFFSET_VALID)) {
 			pci_dev_put(cpu_cfg);
-			printk(KERN_DEBUG "Failed to setup IBS LVT offset, "
-			       "IBSCTL = 0x%08x\n", value);
+			pr_debug("Failed to setup IBS LVT offset, IBSCTL = 0x%08x\n",
+				 value);
 			return -EINVAL;
 		}
 	} while (1);
 
 	if (!nodes) {
-		printk(KERN_DEBUG "No CPU node configured for IBS\n");
+		pr_debug("No CPU node configured for IBS\n");
 		return -ENODEV;
 	}
 
@@ -810,7 +810,7 @@ static void force_ibs_eilvt_setup(void)
 	preempt_enable();
 
 	if (offset == APIC_EILVT_NR_MAX) {
-		printk(KERN_DEBUG "No EILVT entry available\n");
+		pr_debug("No EILVT entry available\n");
 		return;
 	}
 
diff --git a/arch/x86/kernel/cpu/perf_event_amd_iommu.c b/arch/x86/events/amd/iommu.c
index 97242a9242bd..635e5eba0caf 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_iommu.c
+++ b/arch/x86/events/amd/iommu.c
@@ -16,8 +16,8 @@
 #include <linux/cpumask.h>
 #include <linux/slab.h>
 
-#include "perf_event.h"
-#include "perf_event_amd_iommu.h"
+#include "../perf_event.h"
+#include "iommu.h"
 
 #define COUNTER_SHIFT		16
 
diff --git a/arch/x86/kernel/cpu/perf_event_amd_iommu.h b/arch/x86/events/amd/iommu.h
index 845d173278e3..845d173278e3 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_iommu.h
+++ b/arch/x86/events/amd/iommu.h
diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/events/amd/uncore.c
index 49742746a6c9..3db9569e658c 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -323,6 +323,8 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu)
 	return 0;
 
 fail:
+	if (amd_uncore_nb)
+		*per_cpu_ptr(amd_uncore_nb, cpu) = NULL;
 	kfree(uncore_nb);
 	return -ENOMEM;
 }
@@ -536,7 +538,7 @@ static int __init amd_uncore_init(void)
 		if (ret)
 			goto fail_nb;
 
-		printk(KERN_INFO "perf: AMD NB counters detected\n");
+		pr_info("perf: AMD NB counters detected\n");
 		ret = 0;
 	}
 
@@ -550,7 +552,7 @@ static int __init amd_uncore_init(void)
 		if (ret)
 			goto fail_l2;
 
-		printk(KERN_INFO "perf: AMD L2I counters detected\n");
+		pr_info("perf: AMD L2I counters detected\n");
 		ret = 0;
 	}
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/events/core.c
index 1b443db2db50..5e830d0c95c9 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/events/core.c
@@ -254,15 +254,16 @@ static bool check_hw_exists(void)
 	 * We still allow the PMU driver to operate:
 	 */
 	if (bios_fail) {
-		printk(KERN_CONT "Broken BIOS detected, complain to your hardware vendor.\n");
-		printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg_fail, val_fail);
+		pr_cont("Broken BIOS detected, complain to your hardware vendor.\n");
+		pr_err(FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n",
+			      reg_fail, val_fail);
 	}
 
 	return true;
 
 msr_fail:
-	printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n");
-	printk("%sFailed to access perfctr msr (MSR %x is %Lx)\n",
+	pr_cont("Broken PMU hardware detected, using software events only.\n");
+	pr_info("%sFailed to access perfctr msr (MSR %x is %Lx)\n",
 		boot_cpu_has(X86_FEATURE_HYPERVISOR) ? KERN_INFO : KERN_ERR,
 		reg, val_new);
 
@@ -596,6 +597,19 @@ void x86_pmu_disable_all(void)
 	}
 }
 
+/*
+ * There may be PMI landing after enabled=0. The PMI hitting could be before or
+ * after disable_all.
+ *
+ * If PMI hits before disable_all, the PMU will be disabled in the NMI handler.
+ * It will not be re-enabled in the NMI handler again, because enabled=0. After
+ * handling the NMI, disable_all will be called, which will not change the
+ * state either. If PMI hits after disable_all, the PMU is already disabled
+ * before entering NMI handler. The NMI handler will not change the state
+ * either.
+ *
+ * So either situation is harmless.
+ */
 static void x86_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/events/intel/bts.c
index 2cad71d1b14c..b99dc9258c0f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -26,7 +26,7 @@
 #include <asm-generic/sizes.h>
 #include <asm/perf_event.h>
 
-#include "perf_event.h"
+#include "../perf_event.h"
 
 struct bts_ctx {
 	struct perf_output_handle	handle;
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/events/intel/core.c
index fed2ab1f1065..68fa55b4d42e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/events/intel/core.c
@@ -18,7 +18,7 @@
 #include <asm/hardirq.h>
 #include <asm/apic.h>
 
-#include "perf_event.h"
+#include "../perf_event.h"
 
 /*
  * Intel PerfMon, used on Core and later.
@@ -1502,7 +1502,15 @@ static __initconst const u64 knl_hw_cache_extra_regs
 };
 
 /*
- * Use from PMIs where the LBRs are already disabled.
+ * Used from PMIs where the LBRs are already disabled.
+ *
+ * This function could be called consecutively. It is required to remain in
+ * disabled state if called consecutively.
+ *
+ * During consecutive calls, the same disable value will be written to related
+ * registers, so the PMU state remains unchanged. hw.state in
+ * intel_bts_disable_local will remain PERF_HES_STOPPED too in consecutive
+ * calls.
  */
 static void __intel_pmu_disable_all(void)
 {
@@ -1884,6 +1892,16 @@ again:
 	if (__test_and_clear_bit(62, (unsigned long *)&status)) {
 		handled++;
 		x86_pmu.drain_pebs(regs);
+		/*
+		 * There are cases where, even though, the PEBS ovfl bit is set
+		 * in GLOBAL_OVF_STATUS, the PEBS events may also have their
+		 * overflow bits set for their counters. We must clear them
+		 * here because they have been processed as exact samples in
+		 * the drain_pebs() routine. They must not be processed again
+		 * in the for_each_bit_set() loop for regular samples below.
+		 */
+		status &= ~cpuc->pebs_enabled;
+		status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
 	}
 
 	/*
@@ -1929,7 +1947,10 @@ again:
 		goto again;
 
 done:
-	__intel_pmu_enable_all(0, true);
+	/* Only restore PMU state when it's active. See x86_pmu_disable(). */
+	if (cpuc->enabled)
+		__intel_pmu_enable_all(0, true);
+
 	/*
 	 * Only unmask the NMI after the overflow counters
 	 * have been reset. This avoids spurious NMIs on
@@ -3396,6 +3417,7 @@ __init int intel_pmu_init(void)
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
 			X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
 
+		intel_pmu_pebs_data_source_nhm();
 		x86_add_quirk(intel_nehalem_quirk);
 
 		pr_cont("Nehalem events, ");
@@ -3459,6 +3481,7 @@ __init int intel_pmu_init(void)
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
 			X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
 
+		intel_pmu_pebs_data_source_nhm();
 		pr_cont("Westmere events, ");
 		break;
 
@@ -3581,7 +3604,7 @@ __init int intel_pmu_init(void)
 		intel_pmu_lbr_init_hsw();
 
 		x86_pmu.event_constraints = intel_bdw_event_constraints;
-		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
+		x86_pmu.pebs_constraints = intel_bdw_pebs_event_constraints;
 		x86_pmu.extra_regs = intel_snbep_extra_regs;
 		x86_pmu.pebs_aliases = intel_pebs_aliases_ivb;
 		x86_pmu.pebs_prec_dist = true;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/events/intel/cqm.c
index a316ca96f1b6..93cb412a5579 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -7,7 +7,7 @@
 #include <linux/perf_event.h>
 #include <linux/slab.h>
 #include <asm/cpu_device_id.h>
-#include "perf_event.h"
+#include "../perf_event.h"
 
 #define MSR_IA32_PQR_ASSOC	0x0c8f
 #define MSR_IA32_QM_CTR		0x0c8e
@@ -1244,15 +1244,12 @@ static struct pmu intel_cqm_pmu = {
 
 static inline void cqm_pick_event_reader(int cpu)
 {
-	int phys_id = topology_physical_package_id(cpu);
-	int i;
+	int reader;
 
-	for_each_cpu(i, &cqm_cpumask) {
-		if (phys_id == topology_physical_package_id(i))
-			return;	/* already got reader for this socket */
-	}
-
-	cpumask_set_cpu(cpu, &cqm_cpumask);
+	/* First online cpu in package becomes the reader */
+	reader = cpumask_any_and(&cqm_cpumask, topology_core_cpumask(cpu));
+	if (reader >= nr_cpu_ids)
+		cpumask_set_cpu(cpu, &cqm_cpumask);
 }
 
 static void intel_cqm_cpu_starting(unsigned int cpu)
@@ -1270,24 +1267,17 @@ static void intel_cqm_cpu_starting(unsigned int cpu)
 
 static void intel_cqm_cpu_exit(unsigned int cpu)
 {
-	int phys_id = topology_physical_package_id(cpu);
-	int i;
+	int target;
 
-	/*
-	 * Is @cpu a designated cqm reader?
-	 */
+	/* Is @cpu the current cqm reader for this package ? */
 	if (!cpumask_test_and_clear_cpu(cpu, &cqm_cpumask))
 		return;
 
-	for_each_online_cpu(i) {
-		if (i == cpu)
-			continue;
+	/* Find another online reader in this package */
+	target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
 
-		if (phys_id == topology_physical_package_id(i)) {
-			cpumask_set_cpu(i, &cqm_cpumask);
-			break;
-		}
-	}
+	if (target < nr_cpu_ids)
+		cpumask_set_cpu(target, &cqm_cpumask);
 }
 
 static int intel_cqm_cpu_notifier(struct notifier_block *nb,
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cstate.c b/arch/x86/events/intel/cstate.c
index 75a38b5a2e26..7946c4231169 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -89,7 +89,7 @@
 #include <linux/slab.h>
 #include <linux/perf_event.h>
 #include <asm/cpu_device_id.h>
-#include "perf_event.h"
+#include "../perf_event.h"
 
 #define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format)		\
 static ssize_t __cstate_##_var##_show(struct kobject *kobj,	\
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/events/intel/ds.c
index 10602f0a438f..ce7211a07c0b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -5,7 +5,7 @@
 #include <asm/perf_event.h>
 #include <asm/insn.h>
 
-#include "perf_event.h"
+#include "../perf_event.h"
 
 /* The size of a BTS record in bytes: */
 #define BTS_RECORD_SIZE		24
@@ -51,7 +51,8 @@ union intel_x86_pebs_dse {
 #define OP_LH (P(OP, LOAD) | P(LVL, HIT))
 #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
 
-static const u64 pebs_data_source[] = {
+/* Version for Sandy Bridge and later */
+static u64 pebs_data_source[] = {
 	P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */
 	OP_LH | P(LVL, L1)  | P(SNOOP, NONE),	/* 0x01: L1 local */
 	OP_LH | P(LVL, LFB) | P(SNOOP, NONE),	/* 0x02: LFB hit */
@@ -70,6 +71,14 @@ static const u64 pebs_data_source[] = {
 	OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */
 };
 
+/* Patch up minor differences in the bits */
+void __init intel_pmu_pebs_data_source_nhm(void)
+{
+	pebs_data_source[0x05] = OP_LH | P(LVL, L3)  | P(SNOOP, HIT);
+	pebs_data_source[0x06] = OP_LH | P(LVL, L3)  | P(SNOOP, HITM);
+	pebs_data_source[0x07] = OP_LH | P(LVL, L3)  | P(SNOOP, HITM);
+}
+
 static u64 precise_store_data(u64 status)
 {
 	union intel_x86_pebs_dse dse;
@@ -269,7 +278,7 @@ static int alloc_pebs_buffer(int cpu)
 	if (!x86_pmu.pebs)
 		return 0;
 
-	buffer = kzalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL, node);
+	buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
 	if (unlikely(!buffer))
 		return -ENOMEM;
 
@@ -286,7 +295,7 @@ static int alloc_pebs_buffer(int cpu)
 		per_cpu(insn_buffer, cpu) = ibuffer;
 	}
 
-	max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
+	max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size;
 
 	ds->pebs_buffer_base = (u64)(unsigned long)buffer;
 	ds->pebs_index = ds->pebs_buffer_base;
@@ -722,6 +731,30 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_bdw_pebs_event_constraints[] = {
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+	INTEL_PLD_CONSTRAINT(0x01cd, 0xf),    /* MEM_TRANS_RETIRED.* */
+	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_STORES */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_STORES */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */
+	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
+	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd2, 0xf),    /* MEM_LOAD_UOPS_L3_HIT_RETIRED.* */
+	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd3, 0xf),    /* MEM_LOAD_UOPS_L3_MISS_RETIRED.* */
+	/* Allow all events as PEBS with no flags */
+	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
+	EVENT_CONSTRAINT_END
+};
+
+
 struct event_constraint intel_skl_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2),	/* INST_RETIRED.PREC_DIST */
 	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
@@ -1319,19 +1352,28 @@ void __init intel_ds_init(void)
 
 	x86_pmu.bts  = boot_cpu_has(X86_FEATURE_BTS);
 	x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
+	x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
 	if (x86_pmu.pebs) {
 		char pebs_type = x86_pmu.intel_cap.pebs_trap ?  '+' : '-';
 		int format = x86_pmu.intel_cap.pebs_format;
 
 		switch (format) {
 		case 0:
-			printk(KERN_CONT "PEBS fmt0%c, ", pebs_type);
+			pr_cont("PEBS fmt0%c, ", pebs_type);
 			x86_pmu.pebs_record_size = sizeof(struct pebs_record_core);
+			/*
+			 * Using >PAGE_SIZE buffers makes the WRMSR to
+			 * PERF_GLOBAL_CTRL in intel_pmu_enable_all()
+			 * mysteriously hang on Core2.
+			 *
+			 * As a workaround, we don't do this.
+			 */
+			x86_pmu.pebs_buffer_size = PAGE_SIZE;
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_core;
 			break;
 
 		case 1:
-			printk(KERN_CONT "PEBS fmt1%c, ", pebs_type);
+			pr_cont("PEBS fmt1%c, ", pebs_type);
 			x86_pmu.pebs_record_size = sizeof(struct pebs_record_nhm);
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
 			break;
@@ -1351,7 +1393,7 @@ void __init intel_ds_init(void)
 			break;
 
 		default:
-			printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type);
+			pr_cont("no PEBS fmt%d%c, ", format, pebs_type);
 			x86_pmu.pebs = 0;
 		}
 	}
diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/events/intel/knc.c
index 5b0c232d1ee6..548d5f774b07 100644
--- a/arch/x86/kernel/cpu/perf_event_knc.c
+++ b/arch/x86/events/intel/knc.c
@@ -5,7 +5,7 @@
 
 #include <asm/hardirq.h>
 
-#include "perf_event.h"
+#include "../perf_event.h"
 
 static const u64 knc_perfmon_event_map[] =
 {
@@ -263,7 +263,9 @@ again:
 		goto again;
 
 done:
-	knc_pmu_enable_all(0);
+	/* Only restore PMU state when it's active. See x86_pmu_disable(). */
+	if (cpuc->enabled)
+		knc_pmu_enable_all(0);
 
 	return handled;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/events/intel/lbr.c
index 653f88d25987..69dd11887dd1 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -5,7 +5,7 @@
 #include <asm/msr.h>
 #include <asm/insn.h>
 
-#include "perf_event.h"
+#include "../perf_event.h"
 
 enum {
 	LBR_FORMAT_32		= 0x00,
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/events/intel/p4.c
index f2e56783af3d..0a5ede187d9c 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/events/intel/p4.c
@@ -13,7 +13,7 @@
 #include <asm/hardirq.h>
 #include <asm/apic.h>
 
-#include "perf_event.h"
+#include "../perf_event.h"
 
 #define P4_CNTR_LIMIT 3
 /*
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/events/intel/p6.c
index 7c1a0c07b607..1f5c47ab4c65 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/events/intel/p6.c
@@ -1,7 +1,7 @@
 #include <linux/perf_event.h>
 #include <linux/types.h>
 
-#include "perf_event.h"
+#include "../perf_event.h"
 
 /*
  * Not sure about some of these
diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/events/intel/pt.c
index c0bbd1033b7c..6af7cf71d6b2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -29,8 +29,8 @@
 #include <asm/io.h>
 #include <asm/intel_pt.h>
 
-#include "perf_event.h"
-#include "intel_pt.h"
+#include "../perf_event.h"
+#include "pt.h"
 
 static DEFINE_PER_CPU(struct pt, pt_ctx);
 
diff --git a/arch/x86/kernel/cpu/intel_pt.h b/arch/x86/events/intel/pt.h
index 336878a5d205..336878a5d205 100644
--- a/arch/x86/kernel/cpu/intel_pt.h
+++ b/arch/x86/events/intel/pt.h
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/events/intel/rapl.c
index 24a351ad628d..b834a3f55a01 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -44,11 +44,14 @@
  * the duration of the measurement. Tools may use a function such as
  * ldexp(raw_count, -32);
  */
+
+#define pr_fmt(fmt) "RAPL PMU: " fmt
+
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/perf_event.h>
 #include <asm/cpu_device_id.h>
-#include "perf_event.h"
+#include "../perf_event.h"
 
 /*
  * RAPL energy status counters
@@ -107,7 +110,7 @@ static ssize_t __rapl_##_var##_show(struct kobject *kobj,	\
 static struct kobj_attribute format_attr_##_var =		\
 	__ATTR(_name, 0444, __rapl_##_var##_show, NULL)
 
-#define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */
+#define RAPL_CNTR_WIDTH 32
 
 #define RAPL_EVENT_ATTR_STR(_name, v, str)					\
 static struct perf_pmu_events_attr event_attr_##v = {				\
@@ -117,23 +120,33 @@ static struct perf_pmu_events_attr event_attr_##v = {				\
 };
 
 struct rapl_pmu {
-	spinlock_t	 lock;
-	int		 n_active; /* number of active events */
-	struct list_head active_list;
-	struct pmu	 *pmu; /* pointer to rapl_pmu_class */
-	ktime_t		 timer_interval; /* in ktime_t unit */
-	struct hrtimer   hrtimer;
+	raw_spinlock_t		lock;
+	int			n_active;
+	int			cpu;
+	struct list_head	active_list;
+	struct pmu		*pmu;
+	ktime_t			timer_interval;
+	struct hrtimer		hrtimer;
 };
 
-static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly;  /* 1/2^hw_unit Joule */
-static struct pmu rapl_pmu_class;
+struct rapl_pmus {
+	struct pmu		pmu;
+	unsigned int		maxpkg;
+	struct rapl_pmu		*pmus[];
+};
+
+ /* 1/2^hw_unit Joule */
+static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly;
+static struct rapl_pmus *rapl_pmus;
 static cpumask_t rapl_cpu_mask;
-static int rapl_cntr_mask;
+static unsigned int rapl_cntr_mask;
+static u64 rapl_timer_ms;
 
-static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu);
-static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu_to_free);
+static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
+{
+	return rapl_pmus->pmus[topology_logical_package_id(cpu)];
+}
 
-static struct x86_pmu_quirk *rapl_quirks;
 static inline u64 rapl_read_counter(struct perf_event *event)
 {
 	u64 raw;
@@ -141,19 +154,10 @@ static inline u64 rapl_read_counter(struct perf_event *event)
 	return raw;
 }
 
-#define rapl_add_quirk(func_)						\
-do {									\
-	static struct x86_pmu_quirk __quirk __initdata = {		\
-		.func = func_,						\
-	};								\
-	__quirk.next = rapl_quirks;					\
-	rapl_quirks = &__quirk;						\
-} while (0)
-
 static inline u64 rapl_scale(u64 v, int cfg)
 {
 	if (cfg > NR_RAPL_DOMAINS) {
-		pr_warn("invalid domain %d, failed to scale data\n", cfg);
+		pr_warn("Invalid domain %d, failed to scale data\n", cfg);
 		return v;
 	}
 	/*
@@ -206,27 +210,21 @@ static void rapl_start_hrtimer(struct rapl_pmu *pmu)
 		     HRTIMER_MODE_REL_PINNED);
 }
 
-static void rapl_stop_hrtimer(struct rapl_pmu *pmu)
-{
-	hrtimer_cancel(&pmu->hrtimer);
-}
-
 static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer)
 {
-	struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
+	struct rapl_pmu *pmu = container_of(hrtimer, struct rapl_pmu, hrtimer);
 	struct perf_event *event;
 	unsigned long flags;
 
 	if (!pmu->n_active)
 		return HRTIMER_NORESTART;
 
-	spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&pmu->lock, flags);
 
-	list_for_each_entry(event, &pmu->active_list, active_entry) {
+	list_for_each_entry(event, &pmu->active_list, active_entry)
 		rapl_event_update(event);
-	}
 
-	spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&pmu->lock, flags);
 
 	hrtimer_forward_now(hrtimer, pmu->timer_interval);
 
@@ -260,28 +258,28 @@ static void __rapl_pmu_event_start(struct rapl_pmu *pmu,
 
 static void rapl_pmu_event_start(struct perf_event *event, int mode)
 {
-	struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
+	struct rapl_pmu *pmu = event->pmu_private;
 	unsigned long flags;
 
-	spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&pmu->lock, flags);
 	__rapl_pmu_event_start(pmu, event);
-	spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&pmu->lock, flags);
 }
 
 static void rapl_pmu_event_stop(struct perf_event *event, int mode)
 {
-	struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
+	struct rapl_pmu *pmu = event->pmu_private;
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long flags;
 
-	spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&pmu->lock, flags);
 
 	/* mark event as deactivated and stopped */
 	if (!(hwc->state & PERF_HES_STOPPED)) {
 		WARN_ON_ONCE(pmu->n_active <= 0);
 		pmu->n_active--;
 		if (pmu->n_active == 0)
-			rapl_stop_hrtimer(pmu);
+			hrtimer_cancel(&pmu->hrtimer);
 
 		list_del(&event->active_entry);
 
@@ -299,23 +297,23 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode)
 		hwc->state |= PERF_HES_UPTODATE;
 	}
 
-	spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&pmu->lock, flags);
 }
 
 static int rapl_pmu_event_add(struct perf_event *event, int mode)
 {
-	struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
+	struct rapl_pmu *pmu = event->pmu_private;
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long flags;
 
-	spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&pmu->lock, flags);
 
 	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
 
 	if (mode & PERF_EF_START)
 		__rapl_pmu_event_start(pmu, event);
 
-	spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&pmu->lock, flags);
 
 	return 0;
 }
@@ -329,15 +327,19 @@ static int rapl_pmu_event_init(struct perf_event *event)
 {
 	u64 cfg = event->attr.config & RAPL_EVENT_MASK;
 	int bit, msr, ret = 0;
+	struct rapl_pmu *pmu;
 
 	/* only look at RAPL events */
-	if (event->attr.type != rapl_pmu_class.type)
+	if (event->attr.type != rapl_pmus->pmu.type)
 		return -ENOENT;
 
 	/* check only supported bits are set */
 	if (event->attr.config & ~RAPL_EVENT_MASK)
 		return -EINVAL;
 
+	if (event->cpu < 0)
+		return -EINVAL;
+
 	/*
 	 * check event is known (determines counter)
 	 */
@@ -376,6 +378,9 @@ static int rapl_pmu_event_init(struct perf_event *event)
 		return -EINVAL;
 
 	/* must be done before validate_group */
+	pmu = cpu_to_rapl_pmu(event->cpu);
+	event->cpu = pmu->cpu;
+	event->pmu_private = pmu;
 	event->hw.event_base = msr;
 	event->hw.config = cfg;
 	event->hw.idx = bit;
@@ -506,139 +511,62 @@ const struct attribute_group *rapl_attr_groups[] = {
 	NULL,
 };
 
-static struct pmu rapl_pmu_class = {
-	.attr_groups	= rapl_attr_groups,
-	.task_ctx_nr	= perf_invalid_context, /* system-wide only */
-	.event_init	= rapl_pmu_event_init,
-	.add		= rapl_pmu_event_add, /* must have */
-	.del		= rapl_pmu_event_del, /* must have */
-	.start		= rapl_pmu_event_start,
-	.stop		= rapl_pmu_event_stop,
-	.read		= rapl_pmu_event_read,
-};
-
 static void rapl_cpu_exit(int cpu)
 {
-	struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
-	int i, phys_id = topology_physical_package_id(cpu);
-	int target = -1;
+	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
+	int target;
 
-	/* find a new cpu on same package */
-	for_each_online_cpu(i) {
-		if (i == cpu)
-			continue;
-		if (phys_id == topology_physical_package_id(i)) {
-			target = i;
-			break;
-		}
-	}
-	/*
-	 * clear cpu from cpumask
-	 * if was set in cpumask and still some cpu on package,
-	 * then move to new cpu
-	 */
-	if (cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask) && target >= 0)
-		cpumask_set_cpu(target, &rapl_cpu_mask);
+	/* Check if exiting cpu is used for collecting rapl events */
+	if (!cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask))
+		return;
 
-	WARN_ON(cpumask_empty(&rapl_cpu_mask));
-	/*
-	 * migrate events and context to new cpu
-	 */
-	if (target >= 0)
-		perf_pmu_migrate_context(pmu->pmu, cpu, target);
+	pmu->cpu = -1;
+	/* Find a new cpu to collect rapl events */
+	target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
 
-	/* cancel overflow polling timer for CPU */
-	rapl_stop_hrtimer(pmu);
+	/* Migrate rapl events to the new target */
+	if (target < nr_cpu_ids) {
+		cpumask_set_cpu(target, &rapl_cpu_mask);
+		pmu->cpu = target;
+		perf_pmu_migrate_context(pmu->pmu, cpu, target);
+	}
 }
 
 static void rapl_cpu_init(int cpu)
 {
-	int i, phys_id = topology_physical_package_id(cpu);
+	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
+	int target;
 
-	/* check if phys_is is already covered */
-	for_each_cpu(i, &rapl_cpu_mask) {
-		if (phys_id == topology_physical_package_id(i))
-			return;
-	}
-	/* was not found, so add it */
-	cpumask_set_cpu(cpu, &rapl_cpu_mask);
-}
-
-static __init void rapl_hsw_server_quirk(void)
-{
 	/*
-	 * DRAM domain on HSW server has fixed energy unit which can be
-	 * different than the unit from power unit MSR.
-	 * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2
-	 * of 2. Datasheet, September 2014, Reference Number: 330784-001 "
+	 * Check if there is an online cpu in the package which collects rapl
+	 * events already.
 	 */
-	rapl_hw_unit[RAPL_IDX_RAM_NRG_STAT] = 16;
+	target = cpumask_any_and(&rapl_cpu_mask, topology_core_cpumask(cpu));
+	if (target < nr_cpu_ids)
+		return;
+
+	cpumask_set_cpu(cpu, &rapl_cpu_mask);
+	pmu->cpu = cpu;
 }
 
 static int rapl_cpu_prepare(int cpu)
 {
-	struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
-	int phys_id = topology_physical_package_id(cpu);
-	u64 ms;
+	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
 
 	if (pmu)
 		return 0;
 
-	if (phys_id < 0)
-		return -1;
-
 	pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
 	if (!pmu)
-		return -1;
-	spin_lock_init(&pmu->lock);
+		return -ENOMEM;
 
+	raw_spin_lock_init(&pmu->lock);
 	INIT_LIST_HEAD(&pmu->active_list);
-
-	pmu->pmu = &rapl_pmu_class;
-
-	/*
-	 * use reference of 200W for scaling the timeout
-	 * to avoid missing counter overflows.
-	 * 200W = 200 Joules/sec
-	 * divide interval by 2 to avoid lockstep (2 * 100)
-	 * if hw unit is 32, then we use 2 ms 1/200/2
-	 */
-	if (rapl_hw_unit[0] < 32)
-		ms = (1000 / (2 * 100)) * (1ULL << (32 - rapl_hw_unit[0] - 1));
-	else
-		ms = 2;
-
-	pmu->timer_interval = ms_to_ktime(ms);
-
+	pmu->pmu = &rapl_pmus->pmu;
+	pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
+	pmu->cpu = -1;
 	rapl_hrtimer_init(pmu);
-
-	/* set RAPL pmu for this cpu for now */
-	per_cpu(rapl_pmu, cpu) = pmu;
-	per_cpu(rapl_pmu_to_free, cpu) = NULL;
-
-	return 0;
-}
-
-static void rapl_cpu_kfree(int cpu)
-{
-	struct rapl_pmu *pmu = per_cpu(rapl_pmu_to_free, cpu);
-
-	kfree(pmu);
-
-	per_cpu(rapl_pmu_to_free, cpu) = NULL;
-}
-
-static int rapl_cpu_dying(int cpu)
-{
-	struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
-
-	if (!pmu)
-		return 0;
-
-	per_cpu(rapl_pmu, cpu) = NULL;
-
-	per_cpu(rapl_pmu_to_free, cpu) = pmu;
-
+	rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
 	return 0;
 }
 
@@ -651,28 +579,20 @@ static int rapl_cpu_notifier(struct notifier_block *self,
 	case CPU_UP_PREPARE:
 		rapl_cpu_prepare(cpu);
 		break;
-	case CPU_STARTING:
-		rapl_cpu_init(cpu);
-		break;
-	case CPU_UP_CANCELED:
-	case CPU_DYING:
-		rapl_cpu_dying(cpu);
-		break;
+
+	case CPU_DOWN_FAILED:
 	case CPU_ONLINE:
-	case CPU_DEAD:
-		rapl_cpu_kfree(cpu);
+		rapl_cpu_init(cpu);
 		break;
+
 	case CPU_DOWN_PREPARE:
 		rapl_cpu_exit(cpu);
 		break;
-	default:
-		break;
 	}
-
 	return NOTIFY_OK;
 }
 
-static int rapl_check_hw_unit(void)
+static int rapl_check_hw_unit(bool apply_quirk)
 {
 	u64 msr_rapl_power_unit_bits;
 	int i;
@@ -683,28 +603,107 @@ static int rapl_check_hw_unit(void)
 	for (i = 0; i < NR_RAPL_DOMAINS; i++)
 		rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
 
+	/*
+	 * DRAM domain on HSW server and KNL has fixed energy unit which can be
+	 * different than the unit from power unit MSR. See
+	 * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2
+	 * of 2. Datasheet, September 2014, Reference Number: 330784-001 "
+	 */
+	if (apply_quirk)
+		rapl_hw_unit[RAPL_IDX_RAM_NRG_STAT] = 16;
+
+	/*
+	 * Calculate the timer rate:
+	 * Use reference of 200W for scaling the timeout to avoid counter
+	 * overflows. 200W = 200 Joules/sec
+	 * Divide interval by 2 to avoid lockstep (2 * 100)
+	 * if hw unit is 32, then we use 2 ms 1/200/2
+	 */
+	rapl_timer_ms = 2;
+	if (rapl_hw_unit[0] < 32) {
+		rapl_timer_ms = (1000 / (2 * 100));
+		rapl_timer_ms *= (1ULL << (32 - rapl_hw_unit[0] - 1));
+	}
+	return 0;
+}
+
+static void __init rapl_advertise(void)
+{
+	int i;
+
+	pr_info("API unit is 2^-32 Joules, %d fixed counters, %llu ms ovfl timer\n",
+		hweight32(rapl_cntr_mask), rapl_timer_ms);
+
+	for (i = 0; i < NR_RAPL_DOMAINS; i++) {
+		if (rapl_cntr_mask & (1 << i)) {
+			pr_info("hw unit of domain %s 2^-%d Joules\n",
+				rapl_domain_names[i], rapl_hw_unit[i]);
+		}
+	}
+}
+
+static int __init rapl_prepare_cpus(void)
+{
+	unsigned int cpu, pkg;
+	int ret;
+
+	for_each_online_cpu(cpu) {
+		pkg = topology_logical_package_id(cpu);
+		if (rapl_pmus->pmus[pkg])
+			continue;
+
+		ret = rapl_cpu_prepare(cpu);
+		if (ret)
+			return ret;
+		rapl_cpu_init(cpu);
+	}
+	return 0;
+}
+
+static void __init cleanup_rapl_pmus(void)
+{
+	int i;
+
+	for (i = 0; i < rapl_pmus->maxpkg; i++)
+		kfree(rapl_pmus->pmus + i);
+	kfree(rapl_pmus);
+}
+
+static int __init init_rapl_pmus(void)
+{
+	int maxpkg = topology_max_packages();
+	size_t size;
+
+	size = sizeof(*rapl_pmus) + maxpkg * sizeof(struct rapl_pmu *);
+	rapl_pmus = kzalloc(size, GFP_KERNEL);
+	if (!rapl_pmus)
+		return -ENOMEM;
+
+	rapl_pmus->maxpkg		= maxpkg;
+	rapl_pmus->pmu.attr_groups	= rapl_attr_groups;
+	rapl_pmus->pmu.task_ctx_nr	= perf_invalid_context;
+	rapl_pmus->pmu.event_init	= rapl_pmu_event_init;
+	rapl_pmus->pmu.add		= rapl_pmu_event_add;
+	rapl_pmus->pmu.del		= rapl_pmu_event_del;
+	rapl_pmus->pmu.start		= rapl_pmu_event_start;
+	rapl_pmus->pmu.stop		= rapl_pmu_event_stop;
+	rapl_pmus->pmu.read		= rapl_pmu_event_read;
 	return 0;
 }
 
-static const struct x86_cpu_id rapl_cpu_match[] = {
+static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
 	[0] = { .vendor = X86_VENDOR_INTEL, .family = 6 },
 	[1] = {},
 };
 
 static int __init rapl_pmu_init(void)
 {
-	struct rapl_pmu *pmu;
-	int cpu, ret;
-	struct x86_pmu_quirk *quirk;
-	int i;
+	bool apply_quirk = false;
+	int ret;
 
-	/*
-	 * check for Intel processor family 6
-	 */
 	if (!x86_match_cpu(rapl_cpu_match))
-		return 0;
+		return -ENODEV;
 
-	/* check supported CPU */
 	switch (boot_cpu_data.x86_model) {
 	case 42: /* Sandy Bridge */
 	case 58: /* Ivy Bridge */
@@ -712,7 +711,7 @@ static int __init rapl_pmu_init(void)
 		rapl_pmu_events_group.attrs = rapl_events_cln_attr;
 		break;
 	case 63: /* Haswell-Server */
-		rapl_add_quirk(rapl_hsw_server_quirk);
+		apply_quirk = true;
 		rapl_cntr_mask = RAPL_IDX_SRV;
 		rapl_pmu_events_group.attrs = rapl_events_srv_attr;
 		break;
@@ -728,56 +727,41 @@ static int __init rapl_pmu_init(void)
 		rapl_pmu_events_group.attrs = rapl_events_srv_attr;
 		break;
 	case 87: /* Knights Landing */
-		rapl_add_quirk(rapl_hsw_server_quirk);
+		apply_quirk = true;
 		rapl_cntr_mask = RAPL_IDX_KNL;
 		rapl_pmu_events_group.attrs = rapl_events_knl_attr;
-
+		break;
 	default:
-		/* unsupported */
-		return 0;
+		return -ENODEV;
 	}
-	ret = rapl_check_hw_unit();
+
+	ret = rapl_check_hw_unit(apply_quirk);
 	if (ret)
 		return ret;
 
-	/* run cpu model quirks */
-	for (quirk = rapl_quirks; quirk; quirk = quirk->next)
-		quirk->func();
-	cpu_notifier_register_begin();
+	ret = init_rapl_pmus();
+	if (ret)
+		return ret;
 
-	for_each_online_cpu(cpu) {
-		ret = rapl_cpu_prepare(cpu);
-		if (ret)
-			goto out;
-		rapl_cpu_init(cpu);
-	}
+	cpu_notifier_register_begin();
 
-	__perf_cpu_notifier(rapl_cpu_notifier);
+	ret = rapl_prepare_cpus();
+	if (ret)
+		goto out;
 
-	ret = perf_pmu_register(&rapl_pmu_class, "power", -1);
-	if (WARN_ON(ret)) {
-		pr_info("RAPL PMU detected, registration failed (%d), RAPL PMU disabled\n", ret);
-		cpu_notifier_register_done();
-		return -1;
-	}
+	ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1);
+	if (ret)
+		goto out;
 
-	pmu = __this_cpu_read(rapl_pmu);
+	__perf_cpu_notifier(rapl_cpu_notifier);
+	cpu_notifier_register_done();
+	rapl_advertise();
+	return 0;
 
-	pr_info("RAPL PMU detected,"
-		" API unit is 2^-32 Joules,"
-		" %d fixed counters"
-		" %llu ms ovfl timer\n",
-		hweight32(rapl_cntr_mask),
-		ktime_to_ms(pmu->timer_interval));
-	for (i = 0; i < NR_RAPL_DOMAINS; i++) {
-		if (rapl_cntr_mask & (1 << i)) {
-			pr_info("hw unit of domain %s 2^-%d Joules\n",
-				rapl_domain_names[i], rapl_hw_unit[i]);
-		}
-	}
 out:
+	pr_warn("Initialization failed (%d), disabled\n", ret);
+	cleanup_rapl_pmus();
 	cpu_notifier_register_done();
-
-	return 0;
+	return ret;
 }
 device_initcall(rapl_pmu_init);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/events/intel/uncore.c
index 3bf41d413775..7012d18bb293 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1,4 +1,4 @@
-#include "perf_event_intel_uncore.h"
+#include "uncore.h"
 
 static struct intel_uncore_type *empty_uncore[] = { NULL, };
 struct intel_uncore_type **uncore_msr_uncores = empty_uncore;
@@ -9,9 +9,9 @@ struct pci_driver *uncore_pci_driver;
 /* pci bus to socket mapping */
 DEFINE_RAW_SPINLOCK(pci2phy_map_lock);
 struct list_head pci2phy_map_head = LIST_HEAD_INIT(pci2phy_map_head);
-struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
+struct pci_extra_dev *uncore_extra_pci_dev;
+static int max_packages;
 
-static DEFINE_RAW_SPINLOCK(uncore_box_lock);
 /* mask of cpus that collect uncore events */
 static cpumask_t uncore_cpu_mask;
 
@@ -21,7 +21,7 @@ static struct event_constraint uncore_constraint_fixed =
 struct event_constraint uncore_constraint_empty =
 	EVENT_CONSTRAINT(0, 0, 0);
 
-int uncore_pcibus_to_physid(struct pci_bus *bus)
+static int uncore_pcibus_to_physid(struct pci_bus *bus)
 {
 	struct pci2phy_map *map;
 	int phys_id = -1;
@@ -38,6 +38,16 @@ int uncore_pcibus_to_physid(struct pci_bus *bus)
 	return phys_id;
 }
 
+static void uncore_free_pcibus_map(void)
+{
+	struct pci2phy_map *map, *tmp;
+
+	list_for_each_entry_safe(map, tmp, &pci2phy_map_head, list) {
+		list_del(&map->list);
+		kfree(map);
+	}
+}
+
 struct pci2phy_map *__find_pci2phy_map(int segment)
 {
 	struct pci2phy_map *map, *alloc = NULL;
@@ -82,43 +92,9 @@ ssize_t uncore_event_show(struct kobject *kobj,
 	return sprintf(buf, "%s", event->config);
 }
 
-struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
-{
-	return container_of(event->pmu, struct intel_uncore_pmu, pmu);
-}
-
 struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
 {
-	struct intel_uncore_box *box;
-
-	box = *per_cpu_ptr(pmu->box, cpu);
-	if (box)
-		return box;
-
-	raw_spin_lock(&uncore_box_lock);
-	/* Recheck in lock to handle races. */
-	if (*per_cpu_ptr(pmu->box, cpu))
-		goto out;
-	list_for_each_entry(box, &pmu->box_list, list) {
-		if (box->phys_id == topology_physical_package_id(cpu)) {
-			atomic_inc(&box->refcnt);
-			*per_cpu_ptr(pmu->box, cpu) = box;
-			break;
-		}
-	}
-out:
-	raw_spin_unlock(&uncore_box_lock);
-
-	return *per_cpu_ptr(pmu->box, cpu);
-}
-
-struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
-{
-	/*
-	 * perf core schedules event on the basis of cpu, uncore events are
-	 * collected by one of the cpus inside a physical package.
-	 */
-	return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
+	return pmu->boxes[topology_logical_package_id(cpu)];
 }
 
 u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
@@ -207,7 +183,8 @@ u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx)
 	return config;
 }
 
-static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_event *event, int idx)
+static void uncore_assign_hw_event(struct intel_uncore_box *box,
+				   struct perf_event *event, int idx)
 {
 	struct hw_perf_event *hwc = &event->hw;
 
@@ -302,24 +279,25 @@ static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box)
 	box->hrtimer.function = uncore_pmu_hrtimer;
 }
 
-static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int node)
+static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
+						 int node)
 {
+	int i, size, numshared = type->num_shared_regs ;
 	struct intel_uncore_box *box;
-	int i, size;
 
-	size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg);
+	size = sizeof(*box) + numshared * sizeof(struct intel_uncore_extra_reg);
 
 	box = kzalloc_node(size, GFP_KERNEL, node);
 	if (!box)
 		return NULL;
 
-	for (i = 0; i < type->num_shared_regs; i++)
+	for (i = 0; i < numshared; i++)
 		raw_spin_lock_init(&box->shared_regs[i].lock);
 
 	uncore_pmu_init_hrtimer(box);
-	atomic_set(&box->refcnt, 1);
 	box->cpu = -1;
-	box->phys_id = -1;
+	box->pci_phys_id = -1;
+	box->pkgid = -1;
 
 	/* set default hrtimer timeout */
 	box->hrtimer_duration = UNCORE_PMU_HRTIMER_INTERVAL;
@@ -341,7 +319,8 @@ static bool is_uncore_event(struct perf_event *event)
 }
 
 static int
-uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp)
+uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader,
+		      bool dogrp)
 {
 	struct perf_event *event;
 	int n, max_count;
@@ -402,7 +381,8 @@ uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *eve
 	return &type->unconstrainted;
 }
 
-static void uncore_put_event_constraint(struct intel_uncore_box *box, struct perf_event *event)
+static void uncore_put_event_constraint(struct intel_uncore_box *box,
+					struct perf_event *event)
 {
 	if (box->pmu->type->ops->put_constraint)
 		box->pmu->type->ops->put_constraint(box, event);
@@ -582,7 +562,7 @@ static void uncore_pmu_event_del(struct perf_event *event, int flags)
 		if (event == box->event_list[i]) {
 			uncore_put_event_constraint(box, event);
 
-			while (++i < box->n_events)
+			for (++i; i < box->n_events; i++)
 				box->event_list[i - 1] = box->event_list[i];
 
 			--box->n_events;
@@ -676,6 +656,7 @@ static int uncore_pmu_event_init(struct perf_event *event)
 	if (!box || box->cpu < 0)
 		return -EINVAL;
 	event->cpu = box->cpu;
+	event->pmu_private = box;
 
 	event->hw.idx = -1;
 	event->hw.last_tag = ~0ULL;
@@ -760,64 +741,110 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu)
 	}
 
 	ret = perf_pmu_register(&pmu->pmu, pmu->name, -1);
+	if (!ret)
+		pmu->registered = true;
 	return ret;
 }
 
+static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu)
+{
+	if (!pmu->registered)
+		return;
+	perf_pmu_unregister(&pmu->pmu);
+	pmu->registered = false;
+}
+
+static void __init __uncore_exit_boxes(struct intel_uncore_type *type, int cpu)
+{
+	struct intel_uncore_pmu *pmu = type->pmus;
+	struct intel_uncore_box *box;
+	int i, pkg;
+
+	if (pmu) {
+		pkg = topology_physical_package_id(cpu);
+		for (i = 0; i < type->num_boxes; i++, pmu++) {
+			box = pmu->boxes[pkg];
+			if (box)
+				uncore_box_exit(box);
+		}
+	}
+}
+
+static void __init uncore_exit_boxes(void *dummy)
+{
+	struct intel_uncore_type **types;
+
+	for (types = uncore_msr_uncores; *types; types++)
+		__uncore_exit_boxes(*types++, smp_processor_id());
+}
+
+static void uncore_free_boxes(struct intel_uncore_pmu *pmu)
+{
+	int pkg;
+
+	for (pkg = 0; pkg < max_packages; pkg++)
+		kfree(pmu->boxes[pkg]);
+	kfree(pmu->boxes);
+}
+
 static void __init uncore_type_exit(struct intel_uncore_type *type)
 {
+	struct intel_uncore_pmu *pmu = type->pmus;
 	int i;
 
-	for (i = 0; i < type->num_boxes; i++)
-		free_percpu(type->pmus[i].box);
-	kfree(type->pmus);
-	type->pmus = NULL;
+	if (pmu) {
+		for (i = 0; i < type->num_boxes; i++, pmu++) {
+			uncore_pmu_unregister(pmu);
+			uncore_free_boxes(pmu);
+		}
+		kfree(type->pmus);
+		type->pmus = NULL;
+	}
 	kfree(type->events_group);
 	type->events_group = NULL;
 }
 
 static void __init uncore_types_exit(struct intel_uncore_type **types)
 {
-	int i;
-	for (i = 0; types[i]; i++)
-		uncore_type_exit(types[i]);
+	for (; *types; types++)
+		uncore_type_exit(*types);
 }
 
-static int __init uncore_type_init(struct intel_uncore_type *type)
+static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 {
 	struct intel_uncore_pmu *pmus;
 	struct attribute_group *attr_group;
 	struct attribute **attrs;
+	size_t size;
 	int i, j;
 
 	pmus = kzalloc(sizeof(*pmus) * type->num_boxes, GFP_KERNEL);
 	if (!pmus)
 		return -ENOMEM;
 
-	type->pmus = pmus;
+	size = max_packages * sizeof(struct intel_uncore_box *);
 
+	for (i = 0; i < type->num_boxes; i++) {
+		pmus[i].func_id	= setid ? i : -1;
+		pmus[i].pmu_idx	= i;
+		pmus[i].type	= type;
+		pmus[i].boxes	= kzalloc(size, GFP_KERNEL);
+		if (!pmus[i].boxes)
+			return -ENOMEM;
+	}
+
+	type->pmus = pmus;
 	type->unconstrainted = (struct event_constraint)
 		__EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1,
 				0, type->num_counters, 0, 0);
 
-	for (i = 0; i < type->num_boxes; i++) {
-		pmus[i].func_id = -1;
-		pmus[i].pmu_idx = i;
-		pmus[i].type = type;
-		INIT_LIST_HEAD(&pmus[i].box_list);
-		pmus[i].box = alloc_percpu(struct intel_uncore_box *);
-		if (!pmus[i].box)
-			goto fail;
-	}
-
 	if (type->event_descs) {
-		i = 0;
-		while (type->event_descs[i].attr.attr.name)
-			i++;
+		for (i = 0; type->event_descs[i].attr.attr.name; i++);
 
 		attr_group = kzalloc(sizeof(struct attribute *) * (i + 1) +
 					sizeof(*attr_group), GFP_KERNEL);
 		if (!attr_group)
-			goto fail;
+			return -ENOMEM;
 
 		attrs = (struct attribute **)(attr_group + 1);
 		attr_group->name = "events";
@@ -831,25 +858,19 @@ static int __init uncore_type_init(struct intel_uncore_type *type)
 
 	type->pmu_group = &uncore_pmu_attr_group;
 	return 0;
-fail:
-	uncore_type_exit(type);
-	return -ENOMEM;
 }
 
-static int __init uncore_types_init(struct intel_uncore_type **types)
+static int __init
+uncore_types_init(struct intel_uncore_type **types, bool setid)
 {
-	int i, ret;
+	int ret;
 
-	for (i = 0; types[i]; i++) {
-		ret = uncore_type_init(types[i]);
+	for (; *types; types++) {
+		ret = uncore_type_init(*types, setid);
 		if (ret)
-			goto fail;
+			return ret;
 	}
 	return 0;
-fail:
-	while (--i >= 0)
-		uncore_type_exit(types[i]);
-	return ret;
 }
 
 /*
@@ -857,28 +878,28 @@ fail:
  */
 static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
+	struct intel_uncore_type *type;
 	struct intel_uncore_pmu *pmu;
 	struct intel_uncore_box *box;
-	struct intel_uncore_type *type;
-	int phys_id;
-	bool first_box = false;
+	int phys_id, pkg, ret;
 
 	phys_id = uncore_pcibus_to_physid(pdev->bus);
 	if (phys_id < 0)
 		return -ENODEV;
 
+	pkg = topology_phys_to_logical_pkg(phys_id);
+	if (WARN_ON_ONCE(pkg < 0))
+		return -EINVAL;
+
 	if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) {
 		int idx = UNCORE_PCI_DEV_IDX(id->driver_data);
-		uncore_extra_pci_dev[phys_id][idx] = pdev;
+
+		uncore_extra_pci_dev[pkg].dev[idx] = pdev;
 		pci_set_drvdata(pdev, NULL);
 		return 0;
 	}
 
 	type = uncore_pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
-	box = uncore_alloc_box(type, NUMA_NO_NODE);
-	if (!box)
-		return -ENOMEM;
-
 	/*
 	 * for performance monitoring unit with multiple boxes,
 	 * each box has a different function id.
@@ -890,44 +911,60 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	 * some device types. Hence PCI device idx would be 0 for all devices.
 	 * So increment pmu pointer to point to an unused array element.
 	 */
-	if (boot_cpu_data.x86_model == 87)
+	if (boot_cpu_data.x86_model == 87) {
 		while (pmu->func_id >= 0)
 			pmu++;
+	}
+
+	if (WARN_ON_ONCE(pmu->boxes[pkg] != NULL))
+		return -EINVAL;
+
+	box = uncore_alloc_box(type, NUMA_NO_NODE);
+	if (!box)
+		return -ENOMEM;
+
 	if (pmu->func_id < 0)
 		pmu->func_id = pdev->devfn;
 	else
 		WARN_ON_ONCE(pmu->func_id != pdev->devfn);
 
-	box->phys_id = phys_id;
+	atomic_inc(&box->refcnt);
+	box->pci_phys_id = phys_id;
+	box->pkgid = pkg;
 	box->pci_dev = pdev;
 	box->pmu = pmu;
 	uncore_box_init(box);
 	pci_set_drvdata(pdev, box);
 
-	raw_spin_lock(&uncore_box_lock);
-	if (list_empty(&pmu->box_list))
-		first_box = true;
-	list_add_tail(&box->list, &pmu->box_list);
-	raw_spin_unlock(&uncore_box_lock);
+	pmu->boxes[pkg] = box;
+	if (atomic_inc_return(&pmu->activeboxes) > 1)
+		return 0;
 
-	if (first_box)
-		uncore_pmu_register(pmu);
-	return 0;
+	/* First active box registers the pmu */
+	ret = uncore_pmu_register(pmu);
+	if (ret) {
+		pci_set_drvdata(pdev, NULL);
+		pmu->boxes[pkg] = NULL;
+		uncore_box_exit(box);
+		kfree(box);
+	}
+	return ret;
 }
 
 static void uncore_pci_remove(struct pci_dev *pdev)
 {
 	struct intel_uncore_box *box = pci_get_drvdata(pdev);
 	struct intel_uncore_pmu *pmu;
-	int i, cpu, phys_id;
-	bool last_box = false;
+	int i, phys_id, pkg;
 
 	phys_id = uncore_pcibus_to_physid(pdev->bus);
+	pkg = topology_phys_to_logical_pkg(phys_id);
+
 	box = pci_get_drvdata(pdev);
 	if (!box) {
 		for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) {
-			if (uncore_extra_pci_dev[phys_id][i] == pdev) {
-				uncore_extra_pci_dev[phys_id][i] = NULL;
+			if (uncore_extra_pci_dev[pkg].dev[i] == pdev) {
+				uncore_extra_pci_dev[pkg].dev[i] = NULL;
 				break;
 			}
 		}
@@ -936,33 +973,20 @@ static void uncore_pci_remove(struct pci_dev *pdev)
 	}
 
 	pmu = box->pmu;
-	if (WARN_ON_ONCE(phys_id != box->phys_id))
+	if (WARN_ON_ONCE(phys_id != box->pci_phys_id))
 		return;
 
 	pci_set_drvdata(pdev, NULL);
-
-	raw_spin_lock(&uncore_box_lock);
-	list_del(&box->list);
-	if (list_empty(&pmu->box_list))
-		last_box = true;
-	raw_spin_unlock(&uncore_box_lock);
-
-	for_each_possible_cpu(cpu) {
-		if (*per_cpu_ptr(pmu->box, cpu) == box) {
-			*per_cpu_ptr(pmu->box, cpu) = NULL;
-			atomic_dec(&box->refcnt);
-		}
-	}
-
-	WARN_ON_ONCE(atomic_read(&box->refcnt) != 1);
+	pmu->boxes[pkg] = NULL;
+	if (atomic_dec_return(&pmu->activeboxes) == 0)
+		uncore_pmu_unregister(pmu);
+	uncore_box_exit(box);
 	kfree(box);
-
-	if (last_box)
-		perf_pmu_unregister(&pmu->pmu);
 }
 
 static int __init uncore_pci_init(void)
 {
+	size_t size;
 	int ret;
 
 	switch (boot_cpu_data.x86_model) {
@@ -999,25 +1023,40 @@ static int __init uncore_pci_init(void)
 		ret = skl_uncore_pci_init();
 		break;
 	default:
-		return 0;
+		return -ENODEV;
 	}
 
 	if (ret)
 		return ret;
 
-	ret = uncore_types_init(uncore_pci_uncores);
+	size = max_packages * sizeof(struct pci_extra_dev);
+	uncore_extra_pci_dev = kzalloc(size, GFP_KERNEL);
+	if (!uncore_extra_pci_dev) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	ret = uncore_types_init(uncore_pci_uncores, false);
 	if (ret)
-		return ret;
+		goto errtype;
 
 	uncore_pci_driver->probe = uncore_pci_probe;
 	uncore_pci_driver->remove = uncore_pci_remove;
 
 	ret = pci_register_driver(uncore_pci_driver);
-	if (ret == 0)
-		pcidrv_registered = true;
-	else
-		uncore_types_exit(uncore_pci_uncores);
+	if (ret)
+		goto errtype;
+
+	pcidrv_registered = true;
+	return 0;
 
+errtype:
+	uncore_types_exit(uncore_pci_uncores);
+	kfree(uncore_extra_pci_dev);
+	uncore_extra_pci_dev = NULL;
+	uncore_free_pcibus_map();
+err:
+	uncore_pci_uncores = empty_uncore;
 	return ret;
 }
 
@@ -1027,173 +1066,139 @@ static void __init uncore_pci_exit(void)
 		pcidrv_registered = false;
 		pci_unregister_driver(uncore_pci_driver);
 		uncore_types_exit(uncore_pci_uncores);
-	}
-}
-
-/* CPU hot plug/unplug are serialized by cpu_add_remove_lock mutex */
-static LIST_HEAD(boxes_to_free);
-
-static void uncore_kfree_boxes(void)
-{
-	struct intel_uncore_box *box;
-
-	while (!list_empty(&boxes_to_free)) {
-		box = list_entry(boxes_to_free.next,
-				 struct intel_uncore_box, list);
-		list_del(&box->list);
-		kfree(box);
+		kfree(uncore_extra_pci_dev);
+		uncore_free_pcibus_map();
 	}
 }
 
 static void uncore_cpu_dying(int cpu)
 {
-	struct intel_uncore_type *type;
+	struct intel_uncore_type *type, **types = uncore_msr_uncores;
 	struct intel_uncore_pmu *pmu;
 	struct intel_uncore_box *box;
-	int i, j;
-
-	for (i = 0; uncore_msr_uncores[i]; i++) {
-		type = uncore_msr_uncores[i];
-		for (j = 0; j < type->num_boxes; j++) {
-			pmu = &type->pmus[j];
-			box = *per_cpu_ptr(pmu->box, cpu);
-			*per_cpu_ptr(pmu->box, cpu) = NULL;
-			if (box && atomic_dec_and_test(&box->refcnt))
-				list_add(&box->list, &boxes_to_free);
+	int i, pkg;
+
+	pkg = topology_logical_package_id(cpu);
+	for (; *types; types++) {
+		type = *types;
+		pmu = type->pmus;
+		for (i = 0; i < type->num_boxes; i++, pmu++) {
+			box = pmu->boxes[pkg];
+			if (box && atomic_dec_return(&box->refcnt) == 0)
+				uncore_box_exit(box);
 		}
 	}
 }
 
-static int uncore_cpu_starting(int cpu)
+static void uncore_cpu_starting(int cpu, bool init)
 {
-	struct intel_uncore_type *type;
+	struct intel_uncore_type *type, **types = uncore_msr_uncores;
 	struct intel_uncore_pmu *pmu;
-	struct intel_uncore_box *box, *exist;
-	int i, j, k, phys_id;
-
-	phys_id = topology_physical_package_id(cpu);
-
-	for (i = 0; uncore_msr_uncores[i]; i++) {
-		type = uncore_msr_uncores[i];
-		for (j = 0; j < type->num_boxes; j++) {
-			pmu = &type->pmus[j];
-			box = *per_cpu_ptr(pmu->box, cpu);
-			/* called by uncore_cpu_init? */
-			if (box && box->phys_id >= 0) {
-				uncore_box_init(box);
-				continue;
-			}
+	struct intel_uncore_box *box;
+	int i, pkg, ncpus = 1;
 
-			for_each_online_cpu(k) {
-				exist = *per_cpu_ptr(pmu->box, k);
-				if (exist && exist->phys_id == phys_id) {
-					atomic_inc(&exist->refcnt);
-					*per_cpu_ptr(pmu->box, cpu) = exist;
-					if (box) {
-						list_add(&box->list,
-							 &boxes_to_free);
-						box = NULL;
-					}
-					break;
-				}
-			}
+	if (init) {
+		/*
+		 * On init we get the number of online cpus in the package
+		 * and set refcount for all of them.
+		 */
+		ncpus = cpumask_weight(topology_core_cpumask(cpu));
+	}
 
-			if (box) {
-				box->phys_id = phys_id;
+	pkg = topology_logical_package_id(cpu);
+	for (; *types; types++) {
+		type = *types;
+		pmu = type->pmus;
+		for (i = 0; i < type->num_boxes; i++, pmu++) {
+			box = pmu->boxes[pkg];
+			if (!box)
+				continue;
+			/* The first cpu on a package activates the box */
+			if (atomic_add_return(ncpus, &box->refcnt) == ncpus)
 				uncore_box_init(box);
-			}
 		}
 	}
-	return 0;
 }
 
-static int uncore_cpu_prepare(int cpu, int phys_id)
+static int uncore_cpu_prepare(int cpu)
 {
-	struct intel_uncore_type *type;
+	struct intel_uncore_type *type, **types = uncore_msr_uncores;
 	struct intel_uncore_pmu *pmu;
 	struct intel_uncore_box *box;
-	int i, j;
-
-	for (i = 0; uncore_msr_uncores[i]; i++) {
-		type = uncore_msr_uncores[i];
-		for (j = 0; j < type->num_boxes; j++) {
-			pmu = &type->pmus[j];
-			if (pmu->func_id < 0)
-				pmu->func_id = j;
-
+	int i, pkg;
+
+	pkg = topology_logical_package_id(cpu);
+	for (; *types; types++) {
+		type = *types;
+		pmu = type->pmus;
+		for (i = 0; i < type->num_boxes; i++, pmu++) {
+			if (pmu->boxes[pkg])
+				continue;
+			/* First cpu of a package allocates the box */
 			box = uncore_alloc_box(type, cpu_to_node(cpu));
 			if (!box)
 				return -ENOMEM;
-
 			box->pmu = pmu;
-			box->phys_id = phys_id;
-			*per_cpu_ptr(pmu->box, cpu) = box;
+			box->pkgid = pkg;
+			pmu->boxes[pkg] = box;
 		}
 	}
 	return 0;
 }
 
-static void
-uncore_change_context(struct intel_uncore_type **uncores, int old_cpu, int new_cpu)
+static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu,
+				   int new_cpu)
 {
-	struct intel_uncore_type *type;
-	struct intel_uncore_pmu *pmu;
+	struct intel_uncore_pmu *pmu = type->pmus;
 	struct intel_uncore_box *box;
-	int i, j;
+	int i, pkg;
 
-	for (i = 0; uncores[i]; i++) {
-		type = uncores[i];
-		for (j = 0; j < type->num_boxes; j++) {
-			pmu = &type->pmus[j];
-			if (old_cpu < 0)
-				box = uncore_pmu_to_box(pmu, new_cpu);
-			else
-				box = uncore_pmu_to_box(pmu, old_cpu);
-			if (!box)
-				continue;
-
-			if (old_cpu < 0) {
-				WARN_ON_ONCE(box->cpu != -1);
-				box->cpu = new_cpu;
-				continue;
-			}
+	pkg = topology_logical_package_id(old_cpu < 0 ? new_cpu : old_cpu);
+	for (i = 0; i < type->num_boxes; i++, pmu++) {
+		box = pmu->boxes[pkg];
+		if (!box)
+			continue;
 
-			WARN_ON_ONCE(box->cpu != old_cpu);
-			if (new_cpu >= 0) {
-				uncore_pmu_cancel_hrtimer(box);
-				perf_pmu_migrate_context(&pmu->pmu,
-						old_cpu, new_cpu);
-				box->cpu = new_cpu;
-			} else {
-				box->cpu = -1;
-			}
+		if (old_cpu < 0) {
+			WARN_ON_ONCE(box->cpu != -1);
+			box->cpu = new_cpu;
+			continue;
 		}
+
+		WARN_ON_ONCE(box->cpu != old_cpu);
+		box->cpu = -1;
+		if (new_cpu < 0)
+			continue;
+
+		uncore_pmu_cancel_hrtimer(box);
+		perf_pmu_migrate_context(&pmu->pmu, old_cpu, new_cpu);
+		box->cpu = new_cpu;
 	}
 }
 
+static void uncore_change_context(struct intel_uncore_type **uncores,
+				  int old_cpu, int new_cpu)
+{
+	for (; *uncores; uncores++)
+		uncore_change_type_ctx(*uncores, old_cpu, new_cpu);
+}
+
 static void uncore_event_exit_cpu(int cpu)
 {
-	int i, phys_id, target;
+	int target;
 
-	/* if exiting cpu is used for collecting uncore events */
+	/* Check if exiting cpu is used for collecting uncore events */
 	if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask))
 		return;
 
-	/* find a new cpu to collect uncore events */
-	phys_id = topology_physical_package_id(cpu);
-	target = -1;
-	for_each_online_cpu(i) {
-		if (i == cpu)
-			continue;
-		if (phys_id == topology_physical_package_id(i)) {
-			target = i;
-			break;
-		}
-	}
+	/* Find a new cpu to collect uncore events */
+	target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
 
-	/* migrate uncore events to the new cpu */
-	if (target >= 0)
+	/* Migrate uncore events to the new target */
+	if (target < nr_cpu_ids)
 		cpumask_set_cpu(target, &uncore_cpu_mask);
+	else
+		target = -1;
 
 	uncore_change_context(uncore_msr_uncores, cpu, target);
 	uncore_change_context(uncore_pci_uncores, cpu, target);
@@ -1201,13 +1206,15 @@ static void uncore_event_exit_cpu(int cpu)
 
 static void uncore_event_init_cpu(int cpu)
 {
-	int i, phys_id;
+	int target;
 
-	phys_id = topology_physical_package_id(cpu);
-	for_each_cpu(i, &uncore_cpu_mask) {
-		if (phys_id == topology_physical_package_id(i))
-			return;
-	}
+	/*
+	 * Check if there is an online cpu in the package
+	 * which collects uncore events already.
+	 */
+	target = cpumask_any_and(&uncore_cpu_mask, topology_core_cpumask(cpu));
+	if (target < nr_cpu_ids)
+		return;
 
 	cpumask_set_cpu(cpu, &uncore_cpu_mask);
 
@@ -1220,39 +1227,25 @@ static int uncore_cpu_notifier(struct notifier_block *self,
 {
 	unsigned int cpu = (long)hcpu;
 
-	/* allocate/free data structure for uncore box */
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_UP_PREPARE:
-		uncore_cpu_prepare(cpu, -1);
-		break;
+		return notifier_from_errno(uncore_cpu_prepare(cpu));
+
 	case CPU_STARTING:
-		uncore_cpu_starting(cpu);
+		uncore_cpu_starting(cpu, false);
+	case CPU_DOWN_FAILED:
+		uncore_event_init_cpu(cpu);
 		break;
+
 	case CPU_UP_CANCELED:
 	case CPU_DYING:
 		uncore_cpu_dying(cpu);
 		break;
-	case CPU_ONLINE:
-	case CPU_DEAD:
-		uncore_kfree_boxes();
-		break;
-	default:
-		break;
-	}
 
-	/* select the cpu that collects uncore events */
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_DOWN_FAILED:
-	case CPU_STARTING:
-		uncore_event_init_cpu(cpu);
-		break;
 	case CPU_DOWN_PREPARE:
 		uncore_event_exit_cpu(cpu);
 		break;
-	default:
-		break;
 	}
-
 	return NOTIFY_OK;
 }
 
@@ -1265,9 +1258,29 @@ static struct notifier_block uncore_cpu_nb = {
 	.priority	= CPU_PRI_PERF + 1,
 };
 
-static void __init uncore_cpu_setup(void *dummy)
+static int __init type_pmu_register(struct intel_uncore_type *type)
 {
-	uncore_cpu_starting(smp_processor_id());
+	int i, ret;
+
+	for (i = 0; i < type->num_boxes; i++) {
+		ret = uncore_pmu_register(&type->pmus[i]);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static int __init uncore_msr_pmus_register(void)
+{
+	struct intel_uncore_type **types = uncore_msr_uncores;
+	int ret;
+
+	for (; *types; types++) {
+		ret = type_pmu_register(*types);
+		if (ret)
+			return ret;
+	}
+	return 0;
 }
 
 static int __init uncore_cpu_init(void)
@@ -1311,71 +1324,61 @@ static int __init uncore_cpu_init(void)
 		knl_uncore_cpu_init();
 		break;
 	default:
-		return 0;
+		return -ENODEV;
 	}
 
-	ret = uncore_types_init(uncore_msr_uncores);
+	ret = uncore_types_init(uncore_msr_uncores, true);
 	if (ret)
-		return ret;
+		goto err;
 
+	ret = uncore_msr_pmus_register();
+	if (ret)
+		goto err;
 	return 0;
+err:
+	uncore_types_exit(uncore_msr_uncores);
+	uncore_msr_uncores = empty_uncore;
+	return ret;
 }
 
-static int __init uncore_pmus_register(void)
+static void __init uncore_cpu_setup(void *dummy)
 {
-	struct intel_uncore_pmu *pmu;
-	struct intel_uncore_type *type;
-	int i, j;
-
-	for (i = 0; uncore_msr_uncores[i]; i++) {
-		type = uncore_msr_uncores[i];
-		for (j = 0; j < type->num_boxes; j++) {
-			pmu = &type->pmus[j];
-			uncore_pmu_register(pmu);
-		}
-	}
-
-	return 0;
+	uncore_cpu_starting(smp_processor_id(), true);
 }
 
-static void __init uncore_cpumask_init(void)
-{
-	int cpu;
-
-	/*
-	 * ony invoke once from msr or pci init code
-	 */
-	if (!cpumask_empty(&uncore_cpu_mask))
-		return;
+/* Lazy to avoid allocation of a few bytes for the normal case */
+static __initdata DECLARE_BITMAP(packages, MAX_LOCAL_APIC);
 
-	cpu_notifier_register_begin();
+static int __init uncore_cpumask_init(bool msr)
+{
+	unsigned int cpu;
 
 	for_each_online_cpu(cpu) {
-		int i, phys_id = topology_physical_package_id(cpu);
+		unsigned int pkg = topology_logical_package_id(cpu);
+		int ret;
 
-		for_each_cpu(i, &uncore_cpu_mask) {
-			if (phys_id == topology_physical_package_id(i)) {
-				phys_id = -1;
-				break;
-			}
-		}
-		if (phys_id < 0)
+		if (test_and_set_bit(pkg, packages))
 			continue;
-
-		uncore_cpu_prepare(cpu, phys_id);
+		/*
+		 * The first online cpu of each package allocates and takes
+		 * the refcounts for all other online cpus in that package.
+		 * If msrs are not enabled no allocation is required.
+		 */
+		if (msr) {
+			ret = uncore_cpu_prepare(cpu);
+			if (ret)
+				return ret;
+		}
 		uncore_event_init_cpu(cpu);
+		smp_call_function_single(cpu, uncore_cpu_setup, NULL, 1);
 	}
-	on_each_cpu(uncore_cpu_setup, NULL, 1);
-
 	__register_cpu_notifier(&uncore_cpu_nb);
-
-	cpu_notifier_register_done();
+	return 0;
 }
 
-
 static int __init intel_uncore_init(void)
 {
-	int ret;
+	int pret, cret, ret;
 
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return -ENODEV;
@@ -1383,19 +1386,27 @@ static int __init intel_uncore_init(void)
 	if (cpu_has_hypervisor)
 		return -ENODEV;
 
-	ret = uncore_pci_init();
-	if (ret)
-		goto fail;
-	ret = uncore_cpu_init();
-	if (ret) {
-		uncore_pci_exit();
-		goto fail;
-	}
-	uncore_cpumask_init();
+	max_packages = topology_max_packages();
+
+	pret = uncore_pci_init();
+	cret = uncore_cpu_init();
 
-	uncore_pmus_register();
+	if (cret && pret)
+		return -ENODEV;
+
+	cpu_notifier_register_begin();
+	ret = uncore_cpumask_init(!cret);
+	if (ret)
+		goto err;
+	cpu_notifier_register_done();
 	return 0;
-fail:
+
+err:
+	/* Undo box->init_box() */
+	on_each_cpu_mask(&uncore_cpu_mask, uncore_exit_boxes, NULL, 1);
+	uncore_types_exit(uncore_msr_uncores);
+	uncore_pci_exit();
+	cpu_notifier_register_done();
 	return ret;
 }
 device_initcall(intel_uncore_init);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/events/intel/uncore.h
index a7086b862156..79766b9a3580 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -1,8 +1,10 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/pci.h>
+#include <asm/apicdef.h>
+
 #include <linux/perf_event.h>
-#include "perf_event.h"
+#include "../perf_event.h"
 
 #define UNCORE_PMU_NAME_LEN		32
 #define UNCORE_PMU_HRTIMER_INTERVAL	(60LL * NSEC_PER_SEC)
@@ -19,11 +21,12 @@
 #define UNCORE_EXTRA_PCI_DEV		0xff
 #define UNCORE_EXTRA_PCI_DEV_MAX	3
 
-/* support up to 8 sockets */
-#define UNCORE_SOCKET_MAX		8
-
 #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff)
 
+struct pci_extra_dev {
+	struct pci_dev *dev[UNCORE_EXTRA_PCI_DEV_MAX];
+};
+
 struct intel_uncore_ops;
 struct intel_uncore_pmu;
 struct intel_uncore_box;
@@ -61,6 +64,7 @@ struct intel_uncore_type {
 
 struct intel_uncore_ops {
 	void (*init_box)(struct intel_uncore_box *);
+	void (*exit_box)(struct intel_uncore_box *);
 	void (*disable_box)(struct intel_uncore_box *);
 	void (*enable_box)(struct intel_uncore_box *);
 	void (*disable_event)(struct intel_uncore_box *, struct perf_event *);
@@ -73,13 +77,14 @@ struct intel_uncore_ops {
 };
 
 struct intel_uncore_pmu {
-	struct pmu pmu;
-	char name[UNCORE_PMU_NAME_LEN];
-	int pmu_idx;
-	int func_id;
-	struct intel_uncore_type *type;
-	struct intel_uncore_box ** __percpu box;
-	struct list_head box_list;
+	struct pmu			pmu;
+	char				name[UNCORE_PMU_NAME_LEN];
+	int				pmu_idx;
+	int				func_id;
+	bool				registered;
+	atomic_t			activeboxes;
+	struct intel_uncore_type	*type;
+	struct intel_uncore_box		**boxes;
 };
 
 struct intel_uncore_extra_reg {
@@ -89,7 +94,8 @@ struct intel_uncore_extra_reg {
 };
 
 struct intel_uncore_box {
-	int phys_id;
+	int pci_phys_id;
+	int pkgid;
 	int n_active;	/* number of active events */
 	int n_events;
 	int cpu;	/* cpu to collect events */
@@ -123,7 +129,6 @@ struct pci2phy_map {
 	int pbus_to_physid[256];
 };
 
-int uncore_pcibus_to_physid(struct pci_bus *bus);
 struct pci2phy_map *__find_pci2phy_map(int segment);
 
 ssize_t uncore_event_show(struct kobject *kobj,
@@ -305,14 +310,30 @@ static inline void uncore_box_init(struct intel_uncore_box *box)
 	}
 }
 
+static inline void uncore_box_exit(struct intel_uncore_box *box)
+{
+	if (test_and_clear_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
+		if (box->pmu->type->ops->exit_box)
+			box->pmu->type->ops->exit_box(box);
+	}
+}
+
 static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
 {
-	return (box->phys_id < 0);
+	return (box->pkgid < 0);
+}
+
+static inline struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
+{
+	return container_of(event->pmu, struct intel_uncore_pmu, pmu);
+}
+
+static inline struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
+{
+	return event->pmu_private;
 }
 
-struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event);
 struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu);
-struct intel_uncore_box *uncore_event_to_box(struct perf_event *event);
 u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event);
 void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
 void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
@@ -328,7 +349,7 @@ extern struct intel_uncore_type **uncore_pci_uncores;
 extern struct pci_driver *uncore_pci_driver;
 extern raw_spinlock_t pci2phy_map_lock;
 extern struct list_head pci2phy_map_head;
-extern struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
+extern struct pci_extra_dev *uncore_extra_pci_dev;
 extern struct event_constraint uncore_constraint_empty;
 
 /* perf_event_intel_uncore_snb.c */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c
index 2749965afed0..cda569332005 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c
+++ b/arch/x86/events/intel/uncore_nhmex.c
@@ -1,5 +1,5 @@
 /* Nehalem-EX/Westmere-EX uncore support */
-#include "perf_event_intel_uncore.h"
+#include "uncore.h"
 
 /* NHM-EX event control */
 #define NHMEX_PMON_CTL_EV_SEL_MASK	0x000000ff
@@ -201,6 +201,11 @@ static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box)
 	wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL);
 }
 
+static void nhmex_uncore_msr_exit_box(struct intel_uncore_box *box)
+{
+	wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, 0);
+}
+
 static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box)
 {
 	unsigned msr = uncore_msr_box_ctl(box);
@@ -250,6 +255,7 @@ static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct p
 
 #define NHMEX_UNCORE_OPS_COMMON_INIT()				\
 	.init_box	= nhmex_uncore_msr_init_box,		\
+	.exit_box	= nhmex_uncore_msr_exit_box,		\
 	.disable_box	= nhmex_uncore_msr_disable_box,		\
 	.enable_box	= nhmex_uncore_msr_enable_box,		\
 	.disable_event	= nhmex_uncore_msr_disable_event,	\
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 2bd030ddd0db..96531d2b843f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -1,5 +1,5 @@
 /* Nehalem/SandBridge/Haswell uncore support */
-#include "perf_event_intel_uncore.h"
+#include "uncore.h"
 
 /* Uncore IMC PCI IDs */
 #define PCI_DEVICE_ID_INTEL_SNB_IMC	0x0100
@@ -95,6 +95,12 @@ static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
 	}
 }
 
+static void snb_uncore_msr_exit_box(struct intel_uncore_box *box)
+{
+	if (box->pmu->pmu_idx == 0)
+		wrmsrl(SNB_UNC_PERF_GLOBAL_CTL, 0);
+}
+
 static struct uncore_event_desc snb_uncore_events[] = {
 	INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
 	{ /* end: all zeroes */ },
@@ -116,6 +122,7 @@ static struct attribute_group snb_uncore_format_group = {
 
 static struct intel_uncore_ops snb_uncore_msr_ops = {
 	.init_box	= snb_uncore_msr_init_box,
+	.exit_box	= snb_uncore_msr_exit_box,
 	.disable_event	= snb_uncore_msr_disable_event,
 	.enable_event	= snb_uncore_msr_enable_event,
 	.read_counter	= uncore_msr_read_counter,
@@ -231,6 +238,11 @@ static void snb_uncore_imc_init_box(struct intel_uncore_box *box)
 	box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL;
 }
 
+static void snb_uncore_imc_exit_box(struct intel_uncore_box *box)
+{
+	iounmap(box->io_addr);
+}
+
 static void snb_uncore_imc_enable_box(struct intel_uncore_box *box)
 {}
 
@@ -301,6 +313,7 @@ static int snb_uncore_imc_event_init(struct perf_event *event)
 		return -EINVAL;
 
 	event->cpu = box->cpu;
+	event->pmu_private = box;
 
 	event->hw.idx = -1;
 	event->hw.last_tag = ~0ULL;
@@ -458,6 +471,7 @@ static struct pmu snb_uncore_imc_pmu = {
 
 static struct intel_uncore_ops snb_uncore_imc_ops = {
 	.init_box	= snb_uncore_imc_init_box,
+	.exit_box	= snb_uncore_imc_exit_box,
 	.enable_box	= snb_uncore_imc_enable_box,
 	.disable_box	= snb_uncore_imc_disable_box,
 	.disable_event	= snb_uncore_imc_disable_event,
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 33acb884ccf1..93f6bd9bf761 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1,6 +1,5 @@
 /* SandyBridge-EP/IvyTown uncore support */
-#include "perf_event_intel_uncore.h"
-
+#include "uncore.h"
 
 /* SNB-EP Box level control */
 #define SNBEP_PMON_BOX_CTL_RST_CTRL	(1 << 0)
@@ -987,7 +986,9 @@ static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_eve
 
 	if (reg1->idx != EXTRA_REG_NONE) {
 		int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER;
-		struct pci_dev *filter_pdev = uncore_extra_pci_dev[box->phys_id][idx];
+		int pkg = topology_phys_to_logical_pkg(box->pci_phys_id);
+		struct pci_dev *filter_pdev = uncore_extra_pci_dev[pkg].dev[idx];
+
 		if (filter_pdev) {
 			pci_write_config_dword(filter_pdev, reg1->reg,
 						(u32)reg1->config);
@@ -2521,14 +2522,16 @@ static struct intel_uncore_type *hswep_msr_uncores[] = {
 
 void hswep_uncore_cpu_init(void)
 {
+	int pkg = topology_phys_to_logical_pkg(0);
+
 	if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
 
 	/* Detect 6-8 core systems with only two SBOXes */
-	if (uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3]) {
+	if (uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]) {
 		u32 capid4;
 
-		pci_read_config_dword(uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3],
+		pci_read_config_dword(uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3],
 				      0x94, &capid4);
 		if (((capid4 >> 6) & 0x3) == 0)
 			hswep_uncore_sbox.num_boxes = 2;
@@ -2875,11 +2878,13 @@ static struct intel_uncore_type bdx_uncore_sbox = {
 	.format_group		= &hswep_uncore_sbox_format_group,
 };
 
+#define BDX_MSR_UNCORE_SBOX	3
+
 static struct intel_uncore_type *bdx_msr_uncores[] = {
 	&bdx_uncore_ubox,
 	&bdx_uncore_cbox,
-	&bdx_uncore_sbox,
 	&hswep_uncore_pcu,
+	&bdx_uncore_sbox,
 	NULL,
 };
 
@@ -2888,6 +2893,10 @@ void bdx_uncore_cpu_init(void)
 	if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
 	uncore_msr_uncores = bdx_msr_uncores;
+
+	/* BDX-DE doesn't have SBOX */
+	if (boot_cpu_data.x86_model == 86)
+		uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
 }
 
 static struct intel_uncore_type bdx_uncore_ha = {
diff --git a/arch/x86/kernel/cpu/perf_event_msr.c b/arch/x86/events/msr.c
index ec863b9a9f78..ec863b9a9f78 100644
--- a/arch/x86/kernel/cpu/perf_event_msr.c
+++ b/arch/x86/events/msr.c
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/events/perf_event.h
index 7bb61e32fb29..68155cafa8a1 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -586,6 +586,7 @@ struct x86_pmu {
 			pebs_broken	:1,
 			pebs_prec_dist	:1;
 	int		pebs_record_size;
+	int		pebs_buffer_size;
 	void		(*drain_pebs)(struct pt_regs *regs);
 	struct event_constraint *pebs_constraints;
 	void		(*pebs_aliases)(struct perf_event *event);
@@ -860,6 +861,8 @@ extern struct event_constraint intel_ivb_pebs_event_constraints[];
 
 extern struct event_constraint intel_hsw_pebs_event_constraints[];
 
+extern struct event_constraint intel_bdw_pebs_event_constraints[];
+
 extern struct event_constraint intel_skl_pebs_event_constraints[];
 
 struct event_constraint *intel_pebs_constraints(struct perf_event *event);
@@ -904,6 +907,8 @@ void intel_pmu_lbr_init_skl(void);
 
 void intel_pmu_lbr_init_knl(void);
 
+void intel_pmu_pebs_data_source_nhm(void);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 void intel_pt_interrupt(void);
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 7bfc85bbb8ff..99afb665a004 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -152,12 +152,6 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	".popsection"
 
 /*
- * This must be included *after* the definition of ALTERNATIVE due to
- * <asm/arch_hweight.h>
- */
-#include <asm/cpufeature.h>
-
-/*
  * Alternative instructions for different CPU types or capabilities.
  *
  * This allows to use optimized instructions even on generic binary
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 3c56ef1ae068..5e828da2e18f 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -27,15 +27,23 @@ struct amd_l3_cache {
 };
 
 struct threshold_block {
-	unsigned int		block;
-	unsigned int		bank;
-	unsigned int		cpu;
-	u32			address;
-	u16			interrupt_enable;
-	bool			interrupt_capable;
-	u16			threshold_limit;
-	struct kobject		kobj;
-	struct list_head	miscj;
+	unsigned int	 block;			/* Number within bank */
+	unsigned int	 bank;			/* MCA bank the block belongs to */
+	unsigned int	 cpu;			/* CPU which controls MCA bank */
+	u32		 address;		/* MSR address for the block */
+	u16		 interrupt_enable;	/* Enable/Disable APIC interrupt */
+	bool		 interrupt_capable;	/* Bank can generate an interrupt. */
+
+	u16		 threshold_limit;	/*
+						 * Value upon which threshold
+						 * interrupt is generated.
+						 */
+
+	struct kobject	 kobj;			/* sysfs object */
+	struct list_head miscj;			/*
+						 * List of threshold blocks
+						 * within a bank.
+						 */
 };
 
 struct threshold_bank {
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index c80f6b6f3da2..0899cfc8dfe8 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -6,7 +6,6 @@
 
 #include <asm/alternative.h>
 #include <asm/cpufeature.h>
-#include <asm/processor.h>
 #include <asm/apicdef.h>
 #include <linux/atomic.h>
 #include <asm/fixmap.h>
diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h
index 259a7c1ef709..02e799fa43d1 100644
--- a/arch/x86/include/asm/arch_hweight.h
+++ b/arch/x86/include/asm/arch_hweight.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_HWEIGHT_H
 #define _ASM_X86_HWEIGHT_H
 
+#include <asm/cpufeatures.h>
+
 #ifdef CONFIG_64BIT
 /* popcnt %edi, %eax -- redundant REX prefix for alignment */
 #define POPCNT32 ".byte 0xf3,0x40,0x0f,0xb8,0xc7"
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 189679aba703..f5063b6659eb 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -44,19 +44,22 @@
 
 /* Exception table entry */
 #ifdef __ASSEMBLY__
-# define _ASM_EXTABLE(from,to)					\
+# define _ASM_EXTABLE_HANDLE(from, to, handler)			\
 	.pushsection "__ex_table","a" ;				\
-	.balign 8 ;						\
+	.balign 4 ;						\
 	.long (from) - . ;					\
 	.long (to) - . ;					\
+	.long (handler) - . ;					\
 	.popsection
 
-# define _ASM_EXTABLE_EX(from,to)				\
-	.pushsection "__ex_table","a" ;				\
-	.balign 8 ;						\
-	.long (from) - . ;					\
-	.long (to) - . + 0x7ffffff0 ;				\
-	.popsection
+# define _ASM_EXTABLE(from, to)					\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
+
+# define _ASM_EXTABLE_FAULT(from, to)				\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
+
+# define _ASM_EXTABLE_EX(from, to)				\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_ext)
 
 # define _ASM_NOKPROBE(entry)					\
 	.pushsection "_kprobe_blacklist","aw" ;			\
@@ -89,19 +92,24 @@
 	.endm
 
 #else
-# define _ASM_EXTABLE(from,to)					\
+# define _EXPAND_EXTABLE_HANDLE(x) #x
+# define _ASM_EXTABLE_HANDLE(from, to, handler)			\
 	" .pushsection \"__ex_table\",\"a\"\n"			\
-	" .balign 8\n"						\
+	" .balign 4\n"						\
 	" .long (" #from ") - .\n"				\
 	" .long (" #to ") - .\n"				\
+	" .long (" _EXPAND_EXTABLE_HANDLE(handler) ") - .\n"	\
 	" .popsection\n"
 
-# define _ASM_EXTABLE_EX(from,to)				\
-	" .pushsection \"__ex_table\",\"a\"\n"			\
-	" .balign 8\n"						\
-	" .long (" #from ") - .\n"				\
-	" .long (" #to ") - . + 0x7ffffff0\n"			\
-	" .popsection\n"
+# define _ASM_EXTABLE(from, to)					\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
+
+# define _ASM_EXTABLE_FAULT(from, to)				\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
+
+# define _ASM_EXTABLE_EX(from, to)				\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_ext)
+
 /* For C file, we already have NOKPROBE_SYMBOL macro */
 #endif
 
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index a584e1c50918..bfb28caf97b1 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -6,18 +6,17 @@
 
 /*
  * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
+ * And yes, this might be required on UP too when we're talking
  * to devices.
  */
 
 #ifdef CONFIG_X86_32
-/*
- * Some non-Intel clones support out of order store. wmb() ceases to be a
- * nop for these.
- */
-#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
-#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
-#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
+#define mb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "mfence", \
+				      X86_FEATURE_XMM2) ::: "memory", "cc")
+#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "lfence", \
+				       X86_FEATURE_XMM2) ::: "memory", "cc")
+#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "sfence", \
+				       X86_FEATURE_XMM2) ::: "memory", "cc")
 #else
 #define mb() 	asm volatile("mfence":::"memory")
 #define rmb()	asm volatile("lfence":::"memory")
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index cfe3b954d5e4..7766d1cf096e 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -91,7 +91,7 @@ set_bit(long nr, volatile unsigned long *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __set_bit(long nr, volatile unsigned long *addr)
+static __always_inline void __set_bit(long nr, volatile unsigned long *addr)
 {
 	asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory");
 }
@@ -128,13 +128,13 @@ clear_bit(long nr, volatile unsigned long *addr)
  * clear_bit() is atomic and implies release semantics before the memory
  * operation. It can be used for an unlock.
  */
-static inline void clear_bit_unlock(long nr, volatile unsigned long *addr)
+static __always_inline void clear_bit_unlock(long nr, volatile unsigned long *addr)
 {
 	barrier();
 	clear_bit(nr, addr);
 }
 
-static inline void __clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
 {
 	asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
 }
@@ -151,7 +151,7 @@ static inline void __clear_bit(long nr, volatile unsigned long *addr)
  * No memory barrier is required here, because x86 cannot reorder stores past
  * older loads. Same principle as spin_unlock.
  */
-static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
+static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
 {
 	barrier();
 	__clear_bit(nr, addr);
@@ -166,7 +166,7 @@ static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __change_bit(long nr, volatile unsigned long *addr)
+static __always_inline void __change_bit(long nr, volatile unsigned long *addr)
 {
 	asm volatile("btc %1,%0" : ADDR : "Ir" (nr));
 }
@@ -180,7 +180,7 @@ static inline void __change_bit(long nr, volatile unsigned long *addr)
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void change_bit(long nr, volatile unsigned long *addr)
+static __always_inline void change_bit(long nr, volatile unsigned long *addr)
 {
 	if (IS_IMMEDIATE(nr)) {
 		asm volatile(LOCK_PREFIX "xorb %1,%0"
@@ -201,7 +201,7 @@ static inline void change_bit(long nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline int test_and_set_bit(long nr, volatile unsigned long *addr)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", "c");
 }
@@ -228,7 +228,7 @@ test_and_set_bit_lock(long nr, volatile unsigned long *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
@@ -247,7 +247,7 @@ static inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline int test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", "c");
 }
@@ -268,7 +268,7 @@ static inline int test_and_clear_bit(long nr, volatile unsigned long *addr)
  * accessed from a hypervisor on the same CPU if running in a VM: don't change
  * this without also updating arch/x86/kernel/kvm.c
  */
-static inline int __test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline int __test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
@@ -280,7 +280,7 @@ static inline int __test_and_clear_bit(long nr, volatile unsigned long *addr)
 }
 
 /* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline int __test_and_change_bit(long nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
@@ -300,7 +300,7 @@ static inline int __test_and_change_bit(long nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline int test_and_change_bit(long nr, volatile unsigned long *addr)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", "c");
 }
@@ -311,7 +311,7 @@ static __always_inline int constant_test_bit(long nr, const volatile unsigned lo
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
-static inline int variable_test_bit(long nr, volatile const unsigned long *addr)
+static __always_inline int variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	int oldbit;
 
@@ -343,7 +343,7 @@ static int test_bit(int nr, const volatile unsigned long *addr);
  *
  * Undefined if no bit exists, so code should check against 0 first.
  */
-static inline unsigned long __ffs(unsigned long word)
+static __always_inline unsigned long __ffs(unsigned long word)
 {
 	asm("rep; bsf %1,%0"
 		: "=r" (word)
@@ -357,7 +357,7 @@ static inline unsigned long __ffs(unsigned long word)
  *
  * Undefined if no zero exists, so code should check against ~0UL first.
  */
-static inline unsigned long ffz(unsigned long word)
+static __always_inline unsigned long ffz(unsigned long word)
 {
 	asm("rep; bsf %1,%0"
 		: "=r" (word)
@@ -371,7 +371,7 @@ static inline unsigned long ffz(unsigned long word)
  *
  * Undefined if no set bit exists, so code should check against 0 first.
  */
-static inline unsigned long __fls(unsigned long word)
+static __always_inline unsigned long __fls(unsigned long word)
 {
 	asm("bsr %1,%0"
 	    : "=r" (word)
@@ -393,7 +393,7 @@ static inline unsigned long __fls(unsigned long word)
  * set bit if value is nonzero. The first (least significant) bit
  * is at position 1.
  */
-static inline int ffs(int x)
+static __always_inline int ffs(int x)
 {
 	int r;
 
@@ -434,7 +434,7 @@ static inline int ffs(int x)
  * set bit if value is nonzero. The last (most significant) bit is
  * at position 32.
  */
-static inline int fls(int x)
+static __always_inline int fls(int x)
 {
 	int r;
 
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index e63aa38e85fb..61518cf79437 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -91,16 +91,10 @@ void clflush_cache_range(void *addr, unsigned int size);
 
 #define mmio_flush_range(addr, size) clflush_cache_range(addr, size)
 
-#ifdef CONFIG_DEBUG_RODATA
-void mark_rodata_ro(void);
 extern const int rodata_test_data;
 extern int kernel_set_to_readonly;
 void set_kernel_text_rw(void);
 void set_kernel_text_ro(void);
-#else
-static inline void set_kernel_text_rw(void) { }
-static inline void set_kernel_text_ro(void) { }
-#endif
 
 #ifdef CONFIG_DEBUG_RODATA_TEST
 int rodata_test(void);
diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h
index eda81dc0f4ae..d194266acb28 100644
--- a/arch/x86/include/asm/clocksource.h
+++ b/arch/x86/include/asm/clocksource.h
@@ -3,10 +3,11 @@
 #ifndef _ASM_X86_CLOCKSOURCE_H
 #define _ASM_X86_CLOCKSOURCE_H
 
-#define VCLOCK_NONE 0  /* No vDSO clock available.	*/
-#define VCLOCK_TSC  1  /* vDSO should use vread_tsc.	*/
-#define VCLOCK_HPET 2  /* vDSO should use vread_hpet.	*/
-#define VCLOCK_PVCLOCK 3 /* vDSO should use vread_pvclock. */
+#define VCLOCK_NONE	0  /* No vDSO clock available.	*/
+#define VCLOCK_TSC	1  /* vDSO should use vread_tsc.	*/
+#define VCLOCK_HPET	2  /* vDSO should use vread_hpet.	*/
+#define VCLOCK_PVCLOCK	3 /* vDSO should use vread_pvclock. */
+#define VCLOCK_MAX	3
 
 struct arch_clocksource_data {
 	int vclock_mode;
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index ad19841eddfe..9733361fed6f 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -2,6 +2,7 @@
 #define ASM_X86_CMPXCHG_H
 
 #include <linux/compiler.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative.h> /* Provides LOCK_PREFIX */
 
 /*
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 7ad8c9464297..68e4e8258b84 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -1,288 +1,7 @@
-/*
- * Defines x86 CPU feature bits
- */
 #ifndef _ASM_X86_CPUFEATURE_H
 #define _ASM_X86_CPUFEATURE_H
 
-#ifndef _ASM_X86_REQUIRED_FEATURES_H
-#include <asm/required-features.h>
-#endif
-
-#ifndef _ASM_X86_DISABLED_FEATURES_H
-#include <asm/disabled-features.h>
-#endif
-
-#define NCAPINTS	16	/* N 32-bit words worth of info */
-#define NBUGINTS	1	/* N 32-bit bug flags */
-
-/*
- * Note: If the comment begins with a quoted string, that string is used
- * in /proc/cpuinfo instead of the macro name.  If the string is "",
- * this feature bit is not displayed in /proc/cpuinfo at all.
- */
-
-/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
-#define X86_FEATURE_FPU		( 0*32+ 0) /* Onboard FPU */
-#define X86_FEATURE_VME		( 0*32+ 1) /* Virtual Mode Extensions */
-#define X86_FEATURE_DE		( 0*32+ 2) /* Debugging Extensions */
-#define X86_FEATURE_PSE		( 0*32+ 3) /* Page Size Extensions */
-#define X86_FEATURE_TSC		( 0*32+ 4) /* Time Stamp Counter */
-#define X86_FEATURE_MSR		( 0*32+ 5) /* Model-Specific Registers */
-#define X86_FEATURE_PAE		( 0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE		( 0*32+ 7) /* Machine Check Exception */
-#define X86_FEATURE_CX8		( 0*32+ 8) /* CMPXCHG8 instruction */
-#define X86_FEATURE_APIC	( 0*32+ 9) /* Onboard APIC */
-#define X86_FEATURE_SEP		( 0*32+11) /* SYSENTER/SYSEXIT */
-#define X86_FEATURE_MTRR	( 0*32+12) /* Memory Type Range Registers */
-#define X86_FEATURE_PGE		( 0*32+13) /* Page Global Enable */
-#define X86_FEATURE_MCA		( 0*32+14) /* Machine Check Architecture */
-#define X86_FEATURE_CMOV	( 0*32+15) /* CMOV instructions */
-					  /* (plus FCMOVcc, FCOMI with FPU) */
-#define X86_FEATURE_PAT		( 0*32+16) /* Page Attribute Table */
-#define X86_FEATURE_PSE36	( 0*32+17) /* 36-bit PSEs */
-#define X86_FEATURE_PN		( 0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLUSH	( 0*32+19) /* CLFLUSH instruction */
-#define X86_FEATURE_DS		( 0*32+21) /* "dts" Debug Store */
-#define X86_FEATURE_ACPI	( 0*32+22) /* ACPI via MSR */
-#define X86_FEATURE_MMX		( 0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR	( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
-#define X86_FEATURE_XMM		( 0*32+25) /* "sse" */
-#define X86_FEATURE_XMM2	( 0*32+26) /* "sse2" */
-#define X86_FEATURE_SELFSNOOP	( 0*32+27) /* "ss" CPU self snoop */
-#define X86_FEATURE_HT		( 0*32+28) /* Hyper-Threading */
-#define X86_FEATURE_ACC		( 0*32+29) /* "tm" Automatic clock control */
-#define X86_FEATURE_IA64	( 0*32+30) /* IA-64 processor */
-#define X86_FEATURE_PBE		( 0*32+31) /* Pending Break Enable */
-
-/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
-/* Don't duplicate feature flags which are redundant with Intel! */
-#define X86_FEATURE_SYSCALL	( 1*32+11) /* SYSCALL/SYSRET */
-#define X86_FEATURE_MP		( 1*32+19) /* MP Capable. */
-#define X86_FEATURE_NX		( 1*32+20) /* Execute Disable */
-#define X86_FEATURE_MMXEXT	( 1*32+22) /* AMD MMX extensions */
-#define X86_FEATURE_FXSR_OPT	( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
-#define X86_FEATURE_GBPAGES	( 1*32+26) /* "pdpe1gb" GB pages */
-#define X86_FEATURE_RDTSCP	( 1*32+27) /* RDTSCP */
-#define X86_FEATURE_LM		( 1*32+29) /* Long Mode (x86-64) */
-#define X86_FEATURE_3DNOWEXT	( 1*32+30) /* AMD 3DNow! extensions */
-#define X86_FEATURE_3DNOW	( 1*32+31) /* 3DNow! */
-
-/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
-#define X86_FEATURE_RECOVERY	( 2*32+ 0) /* CPU in recovery mode */
-#define X86_FEATURE_LONGRUN	( 2*32+ 1) /* Longrun power control */
-#define X86_FEATURE_LRTI	( 2*32+ 3) /* LongRun table interface */
-
-/* Other features, Linux-defined mapping, word 3 */
-/* This range is used for feature bits which conflict or are synthesized */
-#define X86_FEATURE_CXMMX	( 3*32+ 0) /* Cyrix MMX extensions */
-#define X86_FEATURE_K6_MTRR	( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
-#define X86_FEATURE_CYRIX_ARR	( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
-#define X86_FEATURE_CENTAUR_MCR	( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
-/* cpu types for specific tunings: */
-#define X86_FEATURE_K8		( 3*32+ 4) /* "" Opteron, Athlon64 */
-#define X86_FEATURE_K7		( 3*32+ 5) /* "" Athlon */
-#define X86_FEATURE_P3		( 3*32+ 6) /* "" P3 */
-#define X86_FEATURE_P4		( 3*32+ 7) /* "" P4 */
-#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
-#define X86_FEATURE_UP		( 3*32+ 9) /* smp kernel running on up */
-/* free, was #define X86_FEATURE_FXSAVE_LEAK ( 3*32+10) * "" FXSAVE leaks FOP/FIP/FOP */
-#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_PEBS	( 3*32+12) /* Precise-Event Based Sampling */
-#define X86_FEATURE_BTS		( 3*32+13) /* Branch Trace Store */
-#define X86_FEATURE_SYSCALL32	( 3*32+14) /* "" syscall in ia32 userspace */
-#define X86_FEATURE_SYSENTER32	( 3*32+15) /* "" sysenter in ia32 userspace */
-#define X86_FEATURE_REP_GOOD	( 3*32+16) /* rep microcode works well */
-#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */
-#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */
-/* free, was #define X86_FEATURE_11AP	( 3*32+19) * "" Bad local APIC aka 11AP */
-#define X86_FEATURE_NOPL	( 3*32+20) /* The NOPL (0F 1F) instructions */
-#define X86_FEATURE_ALWAYS	( 3*32+21) /* "" Always-present feature */
-#define X86_FEATURE_XTOPOLOGY	( 3*32+22) /* cpu topology enum extensions */
-#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
-#define X86_FEATURE_NONSTOP_TSC	( 3*32+24) /* TSC does not stop in C states */
-/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */
-#define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
-#define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
-#define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
-#define X86_FEATURE_EAGER_FPU	( 3*32+29) /* "eagerfpu" Non lazy FPU restore */
-#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
-
-/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
-#define X86_FEATURE_XMM3	( 4*32+ 0) /* "pni" SSE-3 */
-#define X86_FEATURE_PCLMULQDQ	( 4*32+ 1) /* PCLMULQDQ instruction */
-#define X86_FEATURE_DTES64	( 4*32+ 2) /* 64-bit Debug Store */
-#define X86_FEATURE_MWAIT	( 4*32+ 3) /* "monitor" Monitor/Mwait support */
-#define X86_FEATURE_DSCPL	( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
-#define X86_FEATURE_VMX		( 4*32+ 5) /* Hardware virtualization */
-#define X86_FEATURE_SMX		( 4*32+ 6) /* Safer mode */
-#define X86_FEATURE_EST		( 4*32+ 7) /* Enhanced SpeedStep */
-#define X86_FEATURE_TM2		( 4*32+ 8) /* Thermal Monitor 2 */
-#define X86_FEATURE_SSSE3	( 4*32+ 9) /* Supplemental SSE-3 */
-#define X86_FEATURE_CID		( 4*32+10) /* Context ID */
-#define X86_FEATURE_SDBG	( 4*32+11) /* Silicon Debug */
-#define X86_FEATURE_FMA		( 4*32+12) /* Fused multiply-add */
-#define X86_FEATURE_CX16	( 4*32+13) /* CMPXCHG16B */
-#define X86_FEATURE_XTPR	( 4*32+14) /* Send Task Priority Messages */
-#define X86_FEATURE_PDCM	( 4*32+15) /* Performance Capabilities */
-#define X86_FEATURE_PCID	( 4*32+17) /* Process Context Identifiers */
-#define X86_FEATURE_DCA		( 4*32+18) /* Direct Cache Access */
-#define X86_FEATURE_XMM4_1	( 4*32+19) /* "sse4_1" SSE-4.1 */
-#define X86_FEATURE_XMM4_2	( 4*32+20) /* "sse4_2" SSE-4.2 */
-#define X86_FEATURE_X2APIC	( 4*32+21) /* x2APIC */
-#define X86_FEATURE_MOVBE	( 4*32+22) /* MOVBE instruction */
-#define X86_FEATURE_POPCNT      ( 4*32+23) /* POPCNT instruction */
-#define X86_FEATURE_TSC_DEADLINE_TIMER	( 4*32+24) /* Tsc deadline timer */
-#define X86_FEATURE_AES		( 4*32+25) /* AES instructions */
-#define X86_FEATURE_XSAVE	( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
-#define X86_FEATURE_OSXSAVE	( 4*32+27) /* "" XSAVE enabled in the OS */
-#define X86_FEATURE_AVX		( 4*32+28) /* Advanced Vector Extensions */
-#define X86_FEATURE_F16C	( 4*32+29) /* 16-bit fp conversions */
-#define X86_FEATURE_RDRAND	( 4*32+30) /* The RDRAND instruction */
-#define X86_FEATURE_HYPERVISOR	( 4*32+31) /* Running on a hypervisor */
-
-/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
-#define X86_FEATURE_XSTORE	( 5*32+ 2) /* "rng" RNG present (xstore) */
-#define X86_FEATURE_XSTORE_EN	( 5*32+ 3) /* "rng_en" RNG enabled */
-#define X86_FEATURE_XCRYPT	( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
-#define X86_FEATURE_XCRYPT_EN	( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
-#define X86_FEATURE_ACE2	( 5*32+ 8) /* Advanced Cryptography Engine v2 */
-#define X86_FEATURE_ACE2_EN	( 5*32+ 9) /* ACE v2 enabled */
-#define X86_FEATURE_PHE		( 5*32+10) /* PadLock Hash Engine */
-#define X86_FEATURE_PHE_EN	( 5*32+11) /* PHE enabled */
-#define X86_FEATURE_PMM		( 5*32+12) /* PadLock Montgomery Multiplier */
-#define X86_FEATURE_PMM_EN	( 5*32+13) /* PMM enabled */
-
-/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
-#define X86_FEATURE_LAHF_LM	( 6*32+ 0) /* LAHF/SAHF in long mode */
-#define X86_FEATURE_CMP_LEGACY	( 6*32+ 1) /* If yes HyperThreading not valid */
-#define X86_FEATURE_SVM		( 6*32+ 2) /* Secure virtual machine */
-#define X86_FEATURE_EXTAPIC	( 6*32+ 3) /* Extended APIC space */
-#define X86_FEATURE_CR8_LEGACY	( 6*32+ 4) /* CR8 in 32-bit mode */
-#define X86_FEATURE_ABM		( 6*32+ 5) /* Advanced bit manipulation */
-#define X86_FEATURE_SSE4A	( 6*32+ 6) /* SSE-4A */
-#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */
-#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */
-#define X86_FEATURE_OSVW	( 6*32+ 9) /* OS Visible Workaround */
-#define X86_FEATURE_IBS		( 6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_XOP		( 6*32+11) /* extended AVX instructions */
-#define X86_FEATURE_SKINIT	( 6*32+12) /* SKINIT/STGI instructions */
-#define X86_FEATURE_WDT		( 6*32+13) /* Watchdog timer */
-#define X86_FEATURE_LWP		( 6*32+15) /* Light Weight Profiling */
-#define X86_FEATURE_FMA4	( 6*32+16) /* 4 operands MAC instructions */
-#define X86_FEATURE_TCE		( 6*32+17) /* translation cache extension */
-#define X86_FEATURE_NODEID_MSR	( 6*32+19) /* NodeId MSR */
-#define X86_FEATURE_TBM		( 6*32+21) /* trailing bit manipulations */
-#define X86_FEATURE_TOPOEXT	( 6*32+22) /* topology extensions CPUID leafs */
-#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */
-#define X86_FEATURE_PERFCTR_NB  ( 6*32+24) /* NB performance counter extensions */
-#define X86_FEATURE_BPEXT	(6*32+26) /* data breakpoint extension */
-#define X86_FEATURE_PERFCTR_L2	( 6*32+28) /* L2 performance counter extensions */
-#define X86_FEATURE_MWAITX	( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
-
-/*
- * Auxiliary flags: Linux defined - For features scattered in various
- * CPUID levels like 0x6, 0xA etc, word 7.
- *
- * Reuse free bits when adding new feature flags!
- */
-
-#define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
-#define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
-
-#define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
-#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
-
-#define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
-
-/* Virtualization flags: Linux defined, word 8 */
-#define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
-#define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
-#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */
-#define X86_FEATURE_EPT         ( 8*32+ 3) /* Intel Extended Page Table */
-#define X86_FEATURE_VPID        ( 8*32+ 4) /* Intel Virtual Processor ID */
-
-#define X86_FEATURE_VMMCALL     ( 8*32+15) /* Prefer vmmcall to vmcall */
-#define X86_FEATURE_XENPV       ( 8*32+16) /* "" Xen paravirtual guest */
-
-
-/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
-#define X86_FEATURE_FSGSBASE	( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
-#define X86_FEATURE_TSC_ADJUST	( 9*32+ 1) /* TSC adjustment MSR 0x3b */
-#define X86_FEATURE_BMI1	( 9*32+ 3) /* 1st group bit manipulation extensions */
-#define X86_FEATURE_HLE		( 9*32+ 4) /* Hardware Lock Elision */
-#define X86_FEATURE_AVX2	( 9*32+ 5) /* AVX2 instructions */
-#define X86_FEATURE_SMEP	( 9*32+ 7) /* Supervisor Mode Execution Protection */
-#define X86_FEATURE_BMI2	( 9*32+ 8) /* 2nd group bit manipulation extensions */
-#define X86_FEATURE_ERMS	( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */
-#define X86_FEATURE_INVPCID	( 9*32+10) /* Invalidate Processor Context ID */
-#define X86_FEATURE_RTM		( 9*32+11) /* Restricted Transactional Memory */
-#define X86_FEATURE_CQM		( 9*32+12) /* Cache QoS Monitoring */
-#define X86_FEATURE_MPX		( 9*32+14) /* Memory Protection Extension */
-#define X86_FEATURE_AVX512F	( 9*32+16) /* AVX-512 Foundation */
-#define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
-#define X86_FEATURE_ADX		( 9*32+19) /* The ADCX and ADOX instructions */
-#define X86_FEATURE_SMAP	( 9*32+20) /* Supervisor Mode Access Prevention */
-#define X86_FEATURE_PCOMMIT	( 9*32+22) /* PCOMMIT instruction */
-#define X86_FEATURE_CLFLUSHOPT	( 9*32+23) /* CLFLUSHOPT instruction */
-#define X86_FEATURE_CLWB	( 9*32+24) /* CLWB instruction */
-#define X86_FEATURE_AVX512PF	( 9*32+26) /* AVX-512 Prefetch */
-#define X86_FEATURE_AVX512ER	( 9*32+27) /* AVX-512 Exponential and Reciprocal */
-#define X86_FEATURE_AVX512CD	( 9*32+28) /* AVX-512 Conflict Detection */
-#define X86_FEATURE_SHA_NI	( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
-
-/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */
-#define X86_FEATURE_XSAVEOPT	(10*32+ 0) /* XSAVEOPT */
-#define X86_FEATURE_XSAVEC	(10*32+ 1) /* XSAVEC */
-#define X86_FEATURE_XGETBV1	(10*32+ 2) /* XGETBV with ECX = 1 */
-#define X86_FEATURE_XSAVES	(10*32+ 3) /* XSAVES/XRSTORS */
-
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */
-#define X86_FEATURE_CQM_LLC	(11*32+ 1) /* LLC QoS if 1 */
-
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */
-#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */
-
-/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
-#define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
-
-/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
-#define X86_FEATURE_DTHERM	(14*32+ 0) /* Digital Thermal Sensor */
-#define X86_FEATURE_IDA		(14*32+ 1) /* Intel Dynamic Acceleration */
-#define X86_FEATURE_ARAT	(14*32+ 2) /* Always Running APIC Timer */
-#define X86_FEATURE_PLN		(14*32+ 4) /* Intel Power Limit Notification */
-#define X86_FEATURE_PTS		(14*32+ 6) /* Intel Package Thermal Status */
-#define X86_FEATURE_HWP		(14*32+ 7) /* Intel Hardware P-states */
-#define X86_FEATURE_HWP_NOTIFY	(14*32+ 8) /* HWP Notification */
-#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */
-#define X86_FEATURE_HWP_EPP	(14*32+10) /* HWP Energy Perf. Preference */
-#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */
-
-/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */
-#define X86_FEATURE_NPT		(15*32+ 0) /* Nested Page Table support */
-#define X86_FEATURE_LBRV	(15*32+ 1) /* LBR Virtualization support */
-#define X86_FEATURE_SVML	(15*32+ 2) /* "svm_lock" SVM locking MSR */
-#define X86_FEATURE_NRIPS	(15*32+ 3) /* "nrip_save" SVM next_rip save */
-#define X86_FEATURE_TSCRATEMSR  (15*32+ 4) /* "tsc_scale" TSC scaling support */
-#define X86_FEATURE_VMCBCLEAN   (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
-#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */
-#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */
-#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
-#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
-
-/*
- * BUG word(s)
- */
-#define X86_BUG(x)		(NCAPINTS*32 + (x))
-
-#define X86_BUG_F00F		X86_BUG(0) /* Intel F00F */
-#define X86_BUG_FDIV		X86_BUG(1) /* FPU FDIV */
-#define X86_BUG_COMA		X86_BUG(2) /* Cyrix 6x86 coma */
-#define X86_BUG_AMD_TLB_MMATCH	X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
-#define X86_BUG_AMD_APIC_C1E	X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
-#define X86_BUG_11AP		X86_BUG(5) /* Bad local APIC aka 11AP */
-#define X86_BUG_FXSAVE_LEAK	X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
-#define X86_BUG_CLFLUSH_MONITOR	X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
-#define X86_BUG_SYSRET_SS_ATTRS	X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
+#include <asm/processor.h>
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 
@@ -369,8 +88,7 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
  * is not relevant.
  */
 #define cpu_feature_enabled(bit)	\
-	(__builtin_constant_p(bit) && DISABLED_MASK_BIT_SET(bit) ? 0 :	\
-	 cpu_has(&boot_cpu_data, bit))
+	(__builtin_constant_p(bit) && DISABLED_MASK_BIT_SET(bit) ? 0 : static_cpu_has(bit))
 
 #define boot_cpu_has(bit)	cpu_has(&boot_cpu_data, bit)
 
@@ -406,106 +124,19 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 #define cpu_has_osxsave		boot_cpu_has(X86_FEATURE_OSXSAVE)
 #define cpu_has_hypervisor	boot_cpu_has(X86_FEATURE_HYPERVISOR)
 /*
- * Do not add any more of those clumsy macros - use static_cpu_has_safe() for
+ * Do not add any more of those clumsy macros - use static_cpu_has() for
  * fast paths and boot_cpu_has() otherwise!
  */
 
-#if __GNUC__ >= 4 && defined(CONFIG_X86_FAST_FEATURE_TESTS)
-extern void warn_pre_alternatives(void);
-extern bool __static_cpu_has_safe(u16 bit);
-
+#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS)
 /*
  * Static testing of CPU features.  Used the same as boot_cpu_has().
- * These are only valid after alternatives have run, but will statically
- * patch the target code for additional performance.
+ * These will statically patch the target code for additional
+ * performance.
  */
-static __always_inline __pure bool __static_cpu_has(u16 bit)
-{
-#ifdef CC_HAVE_ASM_GOTO
-
-#ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS
-
-		/*
-		 * Catch too early usage of this before alternatives
-		 * have run.
-		 */
-		asm_volatile_goto("1: jmp %l[t_warn]\n"
-			 "2:\n"
-			 ".section .altinstructions,\"a\"\n"
-			 " .long 1b - .\n"
-			 " .long 0\n"		/* no replacement */
-			 " .word %P0\n"		/* 1: do replace */
-			 " .byte 2b - 1b\n"	/* source len */
-			 " .byte 0\n"		/* replacement len */
-			 " .byte 0\n"		/* pad len */
-			 ".previous\n"
-			 /* skipping size check since replacement size = 0 */
-			 : : "i" (X86_FEATURE_ALWAYS) : : t_warn);
-
-#endif
-
-		asm_volatile_goto("1: jmp %l[t_no]\n"
-			 "2:\n"
-			 ".section .altinstructions,\"a\"\n"
-			 " .long 1b - .\n"
-			 " .long 0\n"		/* no replacement */
-			 " .word %P0\n"		/* feature bit */
-			 " .byte 2b - 1b\n"	/* source len */
-			 " .byte 0\n"		/* replacement len */
-			 " .byte 0\n"		/* pad len */
-			 ".previous\n"
-			 /* skipping size check since replacement size = 0 */
-			 : : "i" (bit) : : t_no);
-		return true;
-	t_no:
-		return false;
-
-#ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS
-	t_warn:
-		warn_pre_alternatives();
-		return false;
-#endif
-
-#else /* CC_HAVE_ASM_GOTO */
-
-		u8 flag;
-		/* Open-coded due to __stringify() in ALTERNATIVE() */
-		asm volatile("1: movb $0,%0\n"
-			     "2:\n"
-			     ".section .altinstructions,\"a\"\n"
-			     " .long 1b - .\n"
-			     " .long 3f - .\n"
-			     " .word %P1\n"		/* feature bit */
-			     " .byte 2b - 1b\n"		/* source len */
-			     " .byte 4f - 3f\n"		/* replacement len */
-			     " .byte 0\n"		/* pad len */
-			     ".previous\n"
-			     ".section .discard,\"aw\",@progbits\n"
-			     " .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */
-			     ".previous\n"
-			     ".section .altinstr_replacement,\"ax\"\n"
-			     "3: movb $1,%0\n"
-			     "4:\n"
-			     ".previous\n"
-			     : "=qm" (flag) : "i" (bit));
-		return flag;
-
-#endif /* CC_HAVE_ASM_GOTO */
-}
-
-#define static_cpu_has(bit)					\
-(								\
-	__builtin_constant_p(boot_cpu_has(bit)) ?		\
-		boot_cpu_has(bit) :				\
-	__builtin_constant_p(bit) ?				\
-		__static_cpu_has(bit) :				\
-		boot_cpu_has(bit)				\
-)
-
-static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
+static __always_inline __pure bool _static_cpu_has(u16 bit)
 {
-#ifdef CC_HAVE_ASM_GOTO
-		asm_volatile_goto("1: jmp %l[t_dynamic]\n"
+		asm_volatile_goto("1: jmp 6f\n"
 			 "2:\n"
 			 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
 			         "((5f-4f) - (2b-1b)),0x90\n"
@@ -530,66 +161,34 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
 			 " .byte 0\n"			/* repl len */
 			 " .byte 0\n"			/* pad len */
 			 ".previous\n"
-			 : : "i" (bit), "i" (X86_FEATURE_ALWAYS)
-			 : : t_dynamic, t_no);
+			 ".section .altinstr_aux,\"ax\"\n"
+			 "6:\n"
+			 " testb %[bitnum],%[cap_byte]\n"
+			 " jnz %l[t_yes]\n"
+			 " jmp %l[t_no]\n"
+			 ".previous\n"
+			 : : "i" (bit), "i" (X86_FEATURE_ALWAYS),
+			     [bitnum] "i" (1 << (bit & 7)),
+			     [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3])
+			 : : t_yes, t_no);
+	t_yes:
 		return true;
 	t_no:
 		return false;
-	t_dynamic:
-		return __static_cpu_has_safe(bit);
-#else
-		u8 flag;
-		/* Open-coded due to __stringify() in ALTERNATIVE() */
-		asm volatile("1: movb $2,%0\n"
-			     "2:\n"
-			     ".section .altinstructions,\"a\"\n"
-			     " .long 1b - .\n"		/* src offset */
-			     " .long 3f - .\n"		/* repl offset */
-			     " .word %P2\n"		/* always replace */
-			     " .byte 2b - 1b\n"		/* source len */
-			     " .byte 4f - 3f\n"		/* replacement len */
-			     " .byte 0\n"		/* pad len */
-			     ".previous\n"
-			     ".section .discard,\"aw\",@progbits\n"
-			     " .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */
-			     ".previous\n"
-			     ".section .altinstr_replacement,\"ax\"\n"
-			     "3: movb $0,%0\n"
-			     "4:\n"
-			     ".previous\n"
-			     ".section .altinstructions,\"a\"\n"
-			     " .long 1b - .\n"		/* src offset */
-			     " .long 5f - .\n"		/* repl offset */
-			     " .word %P1\n"		/* feature bit */
-			     " .byte 4b - 3b\n"		/* src len */
-			     " .byte 6f - 5f\n"		/* repl len */
-			     " .byte 0\n"		/* pad len */
-			     ".previous\n"
-			     ".section .discard,\"aw\",@progbits\n"
-			     " .byte 0xff + (6f-5f) - (4b-3b)\n" /* size check */
-			     ".previous\n"
-			     ".section .altinstr_replacement,\"ax\"\n"
-			     "5: movb $1,%0\n"
-			     "6:\n"
-			     ".previous\n"
-			     : "=qm" (flag)
-			     : "i" (bit), "i" (X86_FEATURE_ALWAYS));
-		return (flag == 2 ? __static_cpu_has_safe(bit) : flag);
-#endif /* CC_HAVE_ASM_GOTO */
 }
 
-#define static_cpu_has_safe(bit)				\
+#define static_cpu_has(bit)					\
 (								\
 	__builtin_constant_p(boot_cpu_has(bit)) ?		\
 		boot_cpu_has(bit) :				\
-		_static_cpu_has_safe(bit)			\
+		_static_cpu_has(bit)				\
 )
 #else
 /*
- * gcc 3.x is too stupid to do the static test; fall back to dynamic.
+ * Fall back to dynamic for gcc versions which don't support asm goto. Should be
+ * a minority now anyway.
  */
 #define static_cpu_has(bit)		boot_cpu_has(bit)
-#define static_cpu_has_safe(bit)	boot_cpu_has(bit)
 #endif
 
 #define cpu_has_bug(c, bit)		cpu_has(c, (bit))
@@ -597,7 +196,6 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
 #define clear_cpu_bug(c, bit)		clear_cpu_cap(c, (bit))
 
 #define static_cpu_has_bug(bit)		static_cpu_has((bit))
-#define static_cpu_has_bug_safe(bit)	static_cpu_has_safe((bit))
 #define boot_cpu_has_bug(bit)		cpu_has_bug(&boot_cpu_data, (bit))
 
 #define MAX_CPU_FEATURES		(NCAPINTS * 32)
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
new file mode 100644
index 000000000000..074b7604bd51
--- /dev/null
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -0,0 +1,300 @@
+#ifndef _ASM_X86_CPUFEATURES_H
+#define _ASM_X86_CPUFEATURES_H
+
+#ifndef _ASM_X86_REQUIRED_FEATURES_H
+#include <asm/required-features.h>
+#endif
+
+#ifndef _ASM_X86_DISABLED_FEATURES_H
+#include <asm/disabled-features.h>
+#endif
+
+/*
+ * Defines x86 CPU feature bits
+ */
+#define NCAPINTS	16	/* N 32-bit words worth of info */
+#define NBUGINTS	1	/* N 32-bit bug flags */
+
+/*
+ * Note: If the comment begins with a quoted string, that string is used
+ * in /proc/cpuinfo instead of the macro name.  If the string is "",
+ * this feature bit is not displayed in /proc/cpuinfo at all.
+ */
+
+/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
+#define X86_FEATURE_FPU		( 0*32+ 0) /* Onboard FPU */
+#define X86_FEATURE_VME		( 0*32+ 1) /* Virtual Mode Extensions */
+#define X86_FEATURE_DE		( 0*32+ 2) /* Debugging Extensions */
+#define X86_FEATURE_PSE		( 0*32+ 3) /* Page Size Extensions */
+#define X86_FEATURE_TSC		( 0*32+ 4) /* Time Stamp Counter */
+#define X86_FEATURE_MSR		( 0*32+ 5) /* Model-Specific Registers */
+#define X86_FEATURE_PAE		( 0*32+ 6) /* Physical Address Extensions */
+#define X86_FEATURE_MCE		( 0*32+ 7) /* Machine Check Exception */
+#define X86_FEATURE_CX8		( 0*32+ 8) /* CMPXCHG8 instruction */
+#define X86_FEATURE_APIC	( 0*32+ 9) /* Onboard APIC */
+#define X86_FEATURE_SEP		( 0*32+11) /* SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR	( 0*32+12) /* Memory Type Range Registers */
+#define X86_FEATURE_PGE		( 0*32+13) /* Page Global Enable */
+#define X86_FEATURE_MCA		( 0*32+14) /* Machine Check Architecture */
+#define X86_FEATURE_CMOV	( 0*32+15) /* CMOV instructions */
+					  /* (plus FCMOVcc, FCOMI with FPU) */
+#define X86_FEATURE_PAT		( 0*32+16) /* Page Attribute Table */
+#define X86_FEATURE_PSE36	( 0*32+17) /* 36-bit PSEs */
+#define X86_FEATURE_PN		( 0*32+18) /* Processor serial number */
+#define X86_FEATURE_CLFLUSH	( 0*32+19) /* CLFLUSH instruction */
+#define X86_FEATURE_DS		( 0*32+21) /* "dts" Debug Store */
+#define X86_FEATURE_ACPI	( 0*32+22) /* ACPI via MSR */
+#define X86_FEATURE_MMX		( 0*32+23) /* Multimedia Extensions */
+#define X86_FEATURE_FXSR	( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+#define X86_FEATURE_XMM		( 0*32+25) /* "sse" */
+#define X86_FEATURE_XMM2	( 0*32+26) /* "sse2" */
+#define X86_FEATURE_SELFSNOOP	( 0*32+27) /* "ss" CPU self snoop */
+#define X86_FEATURE_HT		( 0*32+28) /* Hyper-Threading */
+#define X86_FEATURE_ACC		( 0*32+29) /* "tm" Automatic clock control */
+#define X86_FEATURE_IA64	( 0*32+30) /* IA-64 processor */
+#define X86_FEATURE_PBE		( 0*32+31) /* Pending Break Enable */
+
+/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
+/* Don't duplicate feature flags which are redundant with Intel! */
+#define X86_FEATURE_SYSCALL	( 1*32+11) /* SYSCALL/SYSRET */
+#define X86_FEATURE_MP		( 1*32+19) /* MP Capable. */
+#define X86_FEATURE_NX		( 1*32+20) /* Execute Disable */
+#define X86_FEATURE_MMXEXT	( 1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_FXSR_OPT	( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
+#define X86_FEATURE_GBPAGES	( 1*32+26) /* "pdpe1gb" GB pages */
+#define X86_FEATURE_RDTSCP	( 1*32+27) /* RDTSCP */
+#define X86_FEATURE_LM		( 1*32+29) /* Long Mode (x86-64) */
+#define X86_FEATURE_3DNOWEXT	( 1*32+30) /* AMD 3DNow! extensions */
+#define X86_FEATURE_3DNOW	( 1*32+31) /* 3DNow! */
+
+/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
+#define X86_FEATURE_RECOVERY	( 2*32+ 0) /* CPU in recovery mode */
+#define X86_FEATURE_LONGRUN	( 2*32+ 1) /* Longrun power control */
+#define X86_FEATURE_LRTI	( 2*32+ 3) /* LongRun table interface */
+
+/* Other features, Linux-defined mapping, word 3 */
+/* This range is used for feature bits which conflict or are synthesized */
+#define X86_FEATURE_CXMMX	( 3*32+ 0) /* Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR	( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR	( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR	( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
+/* cpu types for specific tunings: */
+#define X86_FEATURE_K8		( 3*32+ 4) /* "" Opteron, Athlon64 */
+#define X86_FEATURE_K7		( 3*32+ 5) /* "" Athlon */
+#define X86_FEATURE_P3		( 3*32+ 6) /* "" P3 */
+#define X86_FEATURE_P4		( 3*32+ 7) /* "" P4 */
+#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
+#define X86_FEATURE_UP		( 3*32+ 9) /* smp kernel running on up */
+#define X86_FEATURE_ART		( 3*32+10) /* Platform has always running timer (ART) */
+#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
+#define X86_FEATURE_PEBS	( 3*32+12) /* Precise-Event Based Sampling */
+#define X86_FEATURE_BTS		( 3*32+13) /* Branch Trace Store */
+#define X86_FEATURE_SYSCALL32	( 3*32+14) /* "" syscall in ia32 userspace */
+#define X86_FEATURE_SYSENTER32	( 3*32+15) /* "" sysenter in ia32 userspace */
+#define X86_FEATURE_REP_GOOD	( 3*32+16) /* rep microcode works well */
+#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */
+#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */
+/* free, was #define X86_FEATURE_11AP	( 3*32+19) * "" Bad local APIC aka 11AP */
+#define X86_FEATURE_NOPL	( 3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_ALWAYS	( 3*32+21) /* "" Always-present feature */
+#define X86_FEATURE_XTOPOLOGY	( 3*32+22) /* cpu topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
+#define X86_FEATURE_NONSTOP_TSC	( 3*32+24) /* TSC does not stop in C states */
+/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */
+#define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
+#define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
+#define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
+#define X86_FEATURE_EAGER_FPU	( 3*32+29) /* "eagerfpu" Non lazy FPU restore */
+#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
+#define X86_FEATURE_MCE_RECOVERY ( 3*32+31) /* cpu has recoverable machine checks */
+
+/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
+#define X86_FEATURE_XMM3	( 4*32+ 0) /* "pni" SSE-3 */
+#define X86_FEATURE_PCLMULQDQ	( 4*32+ 1) /* PCLMULQDQ instruction */
+#define X86_FEATURE_DTES64	( 4*32+ 2) /* 64-bit Debug Store */
+#define X86_FEATURE_MWAIT	( 4*32+ 3) /* "monitor" Monitor/Mwait support */
+#define X86_FEATURE_DSCPL	( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
+#define X86_FEATURE_VMX		( 4*32+ 5) /* Hardware virtualization */
+#define X86_FEATURE_SMX		( 4*32+ 6) /* Safer mode */
+#define X86_FEATURE_EST		( 4*32+ 7) /* Enhanced SpeedStep */
+#define X86_FEATURE_TM2		( 4*32+ 8) /* Thermal Monitor 2 */
+#define X86_FEATURE_SSSE3	( 4*32+ 9) /* Supplemental SSE-3 */
+#define X86_FEATURE_CID		( 4*32+10) /* Context ID */
+#define X86_FEATURE_SDBG	( 4*32+11) /* Silicon Debug */
+#define X86_FEATURE_FMA		( 4*32+12) /* Fused multiply-add */
+#define X86_FEATURE_CX16	( 4*32+13) /* CMPXCHG16B */
+#define X86_FEATURE_XTPR	( 4*32+14) /* Send Task Priority Messages */
+#define X86_FEATURE_PDCM	( 4*32+15) /* Performance Capabilities */
+#define X86_FEATURE_PCID	( 4*32+17) /* Process Context Identifiers */
+#define X86_FEATURE_DCA		( 4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_XMM4_1	( 4*32+19) /* "sse4_1" SSE-4.1 */
+#define X86_FEATURE_XMM4_2	( 4*32+20) /* "sse4_2" SSE-4.2 */
+#define X86_FEATURE_X2APIC	( 4*32+21) /* x2APIC */
+#define X86_FEATURE_MOVBE	( 4*32+22) /* MOVBE instruction */
+#define X86_FEATURE_POPCNT      ( 4*32+23) /* POPCNT instruction */
+#define X86_FEATURE_TSC_DEADLINE_TIMER	( 4*32+24) /* Tsc deadline timer */
+#define X86_FEATURE_AES		( 4*32+25) /* AES instructions */
+#define X86_FEATURE_XSAVE	( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
+#define X86_FEATURE_OSXSAVE	( 4*32+27) /* "" XSAVE enabled in the OS */
+#define X86_FEATURE_AVX		( 4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_F16C	( 4*32+29) /* 16-bit fp conversions */
+#define X86_FEATURE_RDRAND	( 4*32+30) /* The RDRAND instruction */
+#define X86_FEATURE_HYPERVISOR	( 4*32+31) /* Running on a hypervisor */
+
+/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
+#define X86_FEATURE_XSTORE	( 5*32+ 2) /* "rng" RNG present (xstore) */
+#define X86_FEATURE_XSTORE_EN	( 5*32+ 3) /* "rng_en" RNG enabled */
+#define X86_FEATURE_XCRYPT	( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
+#define X86_FEATURE_XCRYPT_EN	( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
+#define X86_FEATURE_ACE2	( 5*32+ 8) /* Advanced Cryptography Engine v2 */
+#define X86_FEATURE_ACE2_EN	( 5*32+ 9) /* ACE v2 enabled */
+#define X86_FEATURE_PHE		( 5*32+10) /* PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN	( 5*32+11) /* PHE enabled */
+#define X86_FEATURE_PMM		( 5*32+12) /* PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN	( 5*32+13) /* PMM enabled */
+
+/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
+#define X86_FEATURE_LAHF_LM	( 6*32+ 0) /* LAHF/SAHF in long mode */
+#define X86_FEATURE_CMP_LEGACY	( 6*32+ 1) /* If yes HyperThreading not valid */
+#define X86_FEATURE_SVM		( 6*32+ 2) /* Secure virtual machine */
+#define X86_FEATURE_EXTAPIC	( 6*32+ 3) /* Extended APIC space */
+#define X86_FEATURE_CR8_LEGACY	( 6*32+ 4) /* CR8 in 32-bit mode */
+#define X86_FEATURE_ABM		( 6*32+ 5) /* Advanced bit manipulation */
+#define X86_FEATURE_SSE4A	( 6*32+ 6) /* SSE-4A */
+#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */
+#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */
+#define X86_FEATURE_OSVW	( 6*32+ 9) /* OS Visible Workaround */
+#define X86_FEATURE_IBS		( 6*32+10) /* Instruction Based Sampling */
+#define X86_FEATURE_XOP		( 6*32+11) /* extended AVX instructions */
+#define X86_FEATURE_SKINIT	( 6*32+12) /* SKINIT/STGI instructions */
+#define X86_FEATURE_WDT		( 6*32+13) /* Watchdog timer */
+#define X86_FEATURE_LWP		( 6*32+15) /* Light Weight Profiling */
+#define X86_FEATURE_FMA4	( 6*32+16) /* 4 operands MAC instructions */
+#define X86_FEATURE_TCE		( 6*32+17) /* translation cache extension */
+#define X86_FEATURE_NODEID_MSR	( 6*32+19) /* NodeId MSR */
+#define X86_FEATURE_TBM		( 6*32+21) /* trailing bit manipulations */
+#define X86_FEATURE_TOPOEXT	( 6*32+22) /* topology extensions CPUID leafs */
+#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */
+#define X86_FEATURE_PERFCTR_NB  ( 6*32+24) /* NB performance counter extensions */
+#define X86_FEATURE_BPEXT	(6*32+26) /* data breakpoint extension */
+#define X86_FEATURE_PERFCTR_L2	( 6*32+28) /* L2 performance counter extensions */
+#define X86_FEATURE_MWAITX	( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
+
+/*
+ * Auxiliary flags: Linux defined - For features scattered in various
+ * CPUID levels like 0x6, 0xA etc, word 7.
+ *
+ * Reuse free bits when adding new feature flags!
+ */
+
+#define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
+#define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+
+#define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
+#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
+
+#define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
+
+/* Virtualization flags: Linux defined, word 8 */
+#define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
+#define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
+#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */
+#define X86_FEATURE_EPT         ( 8*32+ 3) /* Intel Extended Page Table */
+#define X86_FEATURE_VPID        ( 8*32+ 4) /* Intel Virtual Processor ID */
+
+#define X86_FEATURE_VMMCALL     ( 8*32+15) /* Prefer vmmcall to vmcall */
+#define X86_FEATURE_XENPV       ( 8*32+16) /* "" Xen paravirtual guest */
+
+
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
+#define X86_FEATURE_FSGSBASE	( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
+#define X86_FEATURE_TSC_ADJUST	( 9*32+ 1) /* TSC adjustment MSR 0x3b */
+#define X86_FEATURE_BMI1	( 9*32+ 3) /* 1st group bit manipulation extensions */
+#define X86_FEATURE_HLE		( 9*32+ 4) /* Hardware Lock Elision */
+#define X86_FEATURE_AVX2	( 9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_SMEP	( 9*32+ 7) /* Supervisor Mode Execution Protection */
+#define X86_FEATURE_BMI2	( 9*32+ 8) /* 2nd group bit manipulation extensions */
+#define X86_FEATURE_ERMS	( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */
+#define X86_FEATURE_INVPCID	( 9*32+10) /* Invalidate Processor Context ID */
+#define X86_FEATURE_RTM		( 9*32+11) /* Restricted Transactional Memory */
+#define X86_FEATURE_CQM		( 9*32+12) /* Cache QoS Monitoring */
+#define X86_FEATURE_MPX		( 9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_AVX512F	( 9*32+16) /* AVX-512 Foundation */
+#define X86_FEATURE_AVX512DQ	( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
+#define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
+#define X86_FEATURE_ADX		( 9*32+19) /* The ADCX and ADOX instructions */
+#define X86_FEATURE_SMAP	( 9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_PCOMMIT	( 9*32+22) /* PCOMMIT instruction */
+#define X86_FEATURE_CLFLUSHOPT	( 9*32+23) /* CLFLUSHOPT instruction */
+#define X86_FEATURE_CLWB	( 9*32+24) /* CLWB instruction */
+#define X86_FEATURE_AVX512PF	( 9*32+26) /* AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER	( 9*32+27) /* AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD	( 9*32+28) /* AVX-512 Conflict Detection */
+#define X86_FEATURE_SHA_NI	( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
+#define X86_FEATURE_AVX512BW	( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */
+#define X86_FEATURE_AVX512VL	( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */
+
+/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */
+#define X86_FEATURE_XSAVEOPT	(10*32+ 0) /* XSAVEOPT */
+#define X86_FEATURE_XSAVEC	(10*32+ 1) /* XSAVEC */
+#define X86_FEATURE_XGETBV1	(10*32+ 2) /* XGETBV with ECX = 1 */
+#define X86_FEATURE_XSAVES	(10*32+ 3) /* XSAVES/XRSTORS */
+
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */
+#define X86_FEATURE_CQM_LLC	(11*32+ 1) /* LLC QoS if 1 */
+
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */
+#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */
+
+/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
+#define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
+
+/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
+#define X86_FEATURE_DTHERM	(14*32+ 0) /* Digital Thermal Sensor */
+#define X86_FEATURE_IDA		(14*32+ 1) /* Intel Dynamic Acceleration */
+#define X86_FEATURE_ARAT	(14*32+ 2) /* Always Running APIC Timer */
+#define X86_FEATURE_PLN		(14*32+ 4) /* Intel Power Limit Notification */
+#define X86_FEATURE_PTS		(14*32+ 6) /* Intel Package Thermal Status */
+#define X86_FEATURE_HWP		(14*32+ 7) /* Intel Hardware P-states */
+#define X86_FEATURE_HWP_NOTIFY	(14*32+ 8) /* HWP Notification */
+#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */
+#define X86_FEATURE_HWP_EPP	(14*32+10) /* HWP Energy Perf. Preference */
+#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */
+
+/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */
+#define X86_FEATURE_NPT		(15*32+ 0) /* Nested Page Table support */
+#define X86_FEATURE_LBRV	(15*32+ 1) /* LBR Virtualization support */
+#define X86_FEATURE_SVML	(15*32+ 2) /* "svm_lock" SVM locking MSR */
+#define X86_FEATURE_NRIPS	(15*32+ 3) /* "nrip_save" SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR  (15*32+ 4) /* "tsc_scale" TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN   (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
+#define X86_FEATURE_AVIC	(15*32+13) /* Virtual Interrupt Controller */
+
+/*
+ * BUG word(s)
+ */
+#define X86_BUG(x)		(NCAPINTS*32 + (x))
+
+#define X86_BUG_F00F		X86_BUG(0) /* Intel F00F */
+#define X86_BUG_FDIV		X86_BUG(1) /* FPU FDIV */
+#define X86_BUG_COMA		X86_BUG(2) /* Cyrix 6x86 coma */
+#define X86_BUG_AMD_TLB_MMATCH	X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
+#define X86_BUG_AMD_APIC_C1E	X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
+#define X86_BUG_11AP		X86_BUG(5) /* Bad local APIC aka 11AP */
+#define X86_BUG_FXSAVE_LEAK	X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
+#define X86_BUG_CLFLUSH_MONITOR	X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
+#define X86_BUG_SYSRET_SS_ATTRS	X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
+
+#ifdef CONFIG_X86_32
+/*
+ * 64-bit kernels don't use X86_BUG_ESPFIX.  Make the define conditional
+ * to avoid confusion.
+ */
+#define X86_BUG_ESPFIX		X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
+#endif
+
+#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h
index 278441f39856..eb5deb42484d 100644
--- a/arch/x86/include/asm/desc_defs.h
+++ b/arch/x86/include/asm/desc_defs.h
@@ -98,4 +98,27 @@ struct desc_ptr {
 
 #endif /* !__ASSEMBLY__ */
 
+/* Access rights as returned by LAR */
+#define AR_TYPE_RODATA		(0 * (1 << 9))
+#define AR_TYPE_RWDATA		(1 * (1 << 9))
+#define AR_TYPE_RODATA_EXPDOWN	(2 * (1 << 9))
+#define AR_TYPE_RWDATA_EXPDOWN	(3 * (1 << 9))
+#define AR_TYPE_XOCODE		(4 * (1 << 9))
+#define AR_TYPE_XRCODE		(5 * (1 << 9))
+#define AR_TYPE_XOCODE_CONF	(6 * (1 << 9))
+#define AR_TYPE_XRCODE_CONF	(7 * (1 << 9))
+#define AR_TYPE_MASK		(7 * (1 << 9))
+
+#define AR_DPL0			(0 * (1 << 13))
+#define AR_DPL3			(3 * (1 << 13))
+#define AR_DPL_MASK		(3 * (1 << 13))
+
+#define AR_A			(1 << 8)   /* "Accessed" */
+#define AR_S			(1 << 12)  /* If clear, "System" segment */
+#define AR_P			(1 << 15)  /* "Present" */
+#define AR_AVL			(1 << 20)  /* "AVaiLable" (no HW effect) */
+#define AR_L			(1 << 21)  /* "Long mode" for code segments */
+#define AR_DB			(1 << 22)  /* D/B, effect depends on type */
+#define AR_G			(1 << 23)  /* "Granularity" (limit in pages) */
+
 #endif /* _ASM_X86_DESC_DEFS_H */
diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h
index 535192f6bfad..3c69fed215c5 100644
--- a/arch/x86/include/asm/dmi.h
+++ b/arch/x86/include/asm/dmi.h
@@ -15,7 +15,7 @@ static __always_inline __init void *dmi_alloc(unsigned len)
 /* Use early IO mappings for DMI because it's initialized early */
 #define dmi_early_remap		early_ioremap
 #define dmi_early_unmap		early_iounmap
-#define dmi_remap		ioremap
+#define dmi_remap		ioremap_cache
 #define dmi_unmap		iounmap
 
 #endif /* _ASM_X86_DMI_H */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 1514753fd435..15340e36ddcb 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -256,7 +256,7 @@ extern int force_personality32;
    instruction set this CPU supports.  This could be done in user space,
    but it's not easy, and we've already done it here.  */
 
-#define ELF_HWCAP		(boot_cpu_data.x86_capability[0])
+#define ELF_HWCAP		(boot_cpu_data.x86_capability[CPUID_1_EDX])
 
 /* This yields a string that ld.so will use to load implementation
    specific libraries for optimization.  This is more specific in
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 6d7d0e52ed5a..8554f960e21b 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -138,7 +138,7 @@ extern void reserve_top_address(unsigned long reserve);
 extern int fixmaps_set;
 
 extern pte_t *kmap_pte;
-extern pgprot_t kmap_prot;
+#define kmap_prot PAGE_KERNEL
 extern pte_t *pkmap_page_table;
 
 void __native_set_fixmap(enum fixed_addresses idx, pte_t pte);
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 0fd440df63f1..a2124343edf5 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -17,6 +17,7 @@
 #include <asm/user.h>
 #include <asm/fpu/api.h>
 #include <asm/fpu/xstate.h>
+#include <asm/cpufeature.h>
 
 /*
  * High level FPU state handling functions:
@@ -58,22 +59,22 @@ extern u64 fpu__get_supported_xfeatures_mask(void);
  */
 static __always_inline __pure bool use_eager_fpu(void)
 {
-	return static_cpu_has_safe(X86_FEATURE_EAGER_FPU);
+	return static_cpu_has(X86_FEATURE_EAGER_FPU);
 }
 
 static __always_inline __pure bool use_xsaveopt(void)
 {
-	return static_cpu_has_safe(X86_FEATURE_XSAVEOPT);
+	return static_cpu_has(X86_FEATURE_XSAVEOPT);
 }
 
 static __always_inline __pure bool use_xsave(void)
 {
-	return static_cpu_has_safe(X86_FEATURE_XSAVE);
+	return static_cpu_has(X86_FEATURE_XSAVE);
 }
 
 static __always_inline __pure bool use_fxsr(void)
 {
-	return static_cpu_has_safe(X86_FEATURE_FXSR);
+	return static_cpu_has(X86_FEATURE_FXSR);
 }
 
 /*
@@ -300,7 +301,7 @@ static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate)
 
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	if (static_cpu_has_safe(X86_FEATURE_XSAVES))
+	if (static_cpu_has(X86_FEATURE_XSAVES))
 		XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
 	else
 		XSTATE_OP(XSAVE, xstate, lmask, hmask, err);
@@ -322,7 +323,7 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
 
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	if (static_cpu_has_safe(X86_FEATURE_XSAVES))
+	if (static_cpu_has(X86_FEATURE_XSAVES))
 		XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
 	else
 		XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
@@ -460,7 +461,7 @@ static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate)
 	 * pending. Clear the x87 state here by setting it to fixed values.
 	 * "m" is a random variable that should be in L1.
 	 */
-	if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) {
+	if (unlikely(static_cpu_has_bug(X86_BUG_FXSAVE_LEAK))) {
 		asm volatile(
 			"fnclex\n\t"
 			"emms\n\t"
@@ -589,7 +590,8 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
 	 * If the task has used the math, pre-load the FPU on xsave processors
 	 * or if the past 5 consecutive context-switches used math.
 	 */
-	fpu.preload = new_fpu->fpstate_active &&
+	fpu.preload = static_cpu_has(X86_FEATURE_FPU) &&
+		      new_fpu->fpstate_active &&
 		      (use_eager_fpu() || new_fpu->counter > 5);
 
 	if (old_fpu->fpregs_active) {
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index af30fdeb140d..f23cd8c80b1c 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -20,16 +20,15 @@
 
 /* Supported features which support lazy state saving */
 #define XFEATURE_MASK_LAZY	(XFEATURE_MASK_FP | \
-				 XFEATURE_MASK_SSE)
-
-/* Supported features which require eager state saving */
-#define XFEATURE_MASK_EAGER	(XFEATURE_MASK_BNDREGS | \
-				 XFEATURE_MASK_BNDCSR | \
+				 XFEATURE_MASK_SSE | \
 				 XFEATURE_MASK_YMM | \
 				 XFEATURE_MASK_OPMASK | \
 				 XFEATURE_MASK_ZMM_Hi256 | \
 				 XFEATURE_MASK_Hi16_ZMM)
 
+/* Supported features which require eager state saving */
+#define XFEATURE_MASK_EAGER	(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)
+
 /* All currently supported features */
 #define XCNTXT_MASK	(XFEATURE_MASK_LAZY | XFEATURE_MASK_EAGER)
 
diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h
index 793179cf8e21..6e4d170726b7 100644
--- a/arch/x86/include/asm/frame.h
+++ b/arch/x86/include/asm/frame.h
@@ -1,23 +1,44 @@
-#ifdef __ASSEMBLY__
+#ifndef _ASM_X86_FRAME_H
+#define _ASM_X86_FRAME_H
 
 #include <asm/asm.h>
 
-/* The annotation hides the frame from the unwinder and makes it look
-   like a ordinary ebp save/restore. This avoids some special cases for
-   frame pointer later */
+/*
+ * These are stack frame creation macros.  They should be used by every
+ * callable non-leaf asm function to make kernel stack traces more reliable.
+ */
+
 #ifdef CONFIG_FRAME_POINTER
-	.macro FRAME
-	__ASM_SIZE(push,)	%__ASM_REG(bp)
-	__ASM_SIZE(mov)		%__ASM_REG(sp), %__ASM_REG(bp)
-	.endm
-	.macro ENDFRAME
-	__ASM_SIZE(pop,)	%__ASM_REG(bp)
-	.endm
-#else
-	.macro FRAME
-	.endm
-	.macro ENDFRAME
-	.endm
-#endif
-
-#endif  /*  __ASSEMBLY__  */
+
+#ifdef __ASSEMBLY__
+
+.macro FRAME_BEGIN
+	push %_ASM_BP
+	_ASM_MOV %_ASM_SP, %_ASM_BP
+.endm
+
+.macro FRAME_END
+	pop %_ASM_BP
+.endm
+
+#else /* !__ASSEMBLY__ */
+
+#define FRAME_BEGIN				\
+	"push %" _ASM_BP "\n"			\
+	_ASM_MOV "%" _ASM_SP ", %" _ASM_BP "\n"
+
+#define FRAME_END "pop %" _ASM_BP "\n"
+
+#endif /* __ASSEMBLY__ */
+
+#define FRAME_OFFSET __ASM_SEL(4, 8)
+
+#else /* !CONFIG_FRAME_POINTER */
+
+#define FRAME_BEGIN
+#define FRAME_END
+#define FRAME_OFFSET 0
+
+#endif /* CONFIG_FRAME_POINTER */
+
+#endif /* _ASM_X86_FRAME_H */
diff --git a/arch/x86/include/asm/imr.h b/arch/x86/include/asm/imr.h
index cd2ce4068441..ebea2c9d2cdc 100644
--- a/arch/x86/include/asm/imr.h
+++ b/arch/x86/include/asm/imr.h
@@ -53,7 +53,7 @@
 #define IMR_MASK		(IMR_ALIGN - 1)
 
 int imr_add_range(phys_addr_t base, size_t size,
-		  unsigned int rmask, unsigned int wmask, bool lock);
+		  unsigned int rmask, unsigned int wmask);
 
 int imr_remove_range(phys_addr_t base, size_t size);
 
diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h
index cfc9a0d2d07c..a4fe16e42b7b 100644
--- a/arch/x86/include/asm/ipi.h
+++ b/arch/x86/include/asm/ipi.h
@@ -57,67 +57,13 @@ static inline void __xapic_wait_icr_idle(void)
 		cpu_relax();
 }
 
-static inline void
-__default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest)
-{
-	/*
-	 * Subtle. In the case of the 'never do double writes' workaround
-	 * we have to lock out interrupts to be safe.  As we don't care
-	 * of the value read we use an atomic rmw access to avoid costly
-	 * cli/sti.  Otherwise we use an even cheaper single atomic write
-	 * to the APIC.
-	 */
-	unsigned int cfg;
-
-	/*
-	 * Wait for idle.
-	 */
-	__xapic_wait_icr_idle();
-
-	/*
-	 * No need to touch the target chip field
-	 */
-	cfg = __prepare_ICR(shortcut, vector, dest);
-
-	/*
-	 * Send the IPI. The write to APIC_ICR fires this off.
-	 */
-	native_apic_mem_write(APIC_ICR, cfg);
-}
+void __default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest);
 
 /*
  * This is used to send an IPI with no shorthand notation (the destination is
  * specified in bits 56 to 63 of the ICR).
  */
-static inline void
- __default_send_IPI_dest_field(unsigned int mask, int vector, unsigned int dest)
-{
-	unsigned long cfg;
-
-	/*
-	 * Wait for idle.
-	 */
-	if (unlikely(vector == NMI_VECTOR))
-		safe_apic_wait_icr_idle();
-	else
-		__xapic_wait_icr_idle();
-
-	/*
-	 * prepare target chip field
-	 */
-	cfg = __prepare_ICR2(mask);
-	native_apic_mem_write(APIC_ICR2, cfg);
-
-	/*
-	 * program the ICR
-	 */
-	cfg = __prepare_ICR(0, vector, dest);
-
-	/*
-	 * Send the IPI. The write to APIC_ICR fires this off.
-	 */
-	native_apic_mem_write(APIC_ICR, cfg);
-}
+void __default_send_IPI_dest_field(unsigned int mask, int vector, unsigned int dest);
 
 extern void default_send_IPI_single(int cpu, int vector);
 extern void default_send_IPI_single_phys(int cpu, int vector);
diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h
index 78162f8e248b..d0afb05c84fc 100644
--- a/arch/x86/include/asm/irq_work.h
+++ b/arch/x86/include/asm/irq_work.h
@@ -1,7 +1,7 @@
 #ifndef _ASM_IRQ_WORK_H
 #define _ASM_IRQ_WORK_H
 
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 
 static inline bool arch_irq_work_has_interrupt(void)
 {
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 44adbb819041..01c8b501cb6d 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -32,6 +32,7 @@
 #include <asm/mtrr.h>
 #include <asm/msr-index.h>
 #include <asm/asm.h>
+#include <asm/kvm_page_track.h>
 
 #define KVM_MAX_VCPUS 255
 #define KVM_SOFT_MAX_VCPUS 160
@@ -214,6 +215,14 @@ struct kvm_mmu_memory_cache {
 	void *objects[KVM_NR_MEM_OBJS];
 };
 
+/*
+ * the pages used as guest page table on soft mmu are tracked by
+ * kvm_memory_slot.arch.gfn_track which is 16 bits, so the role bits used
+ * by indirect shadow page can not be more than 15 bits.
+ *
+ * Currently, we used 14 bits that are @level, @cr4_pae, @quadrant, @access,
+ * @nxe, @cr0_wp, @smep_andnot_wp and @smap_andnot_wp.
+ */
 union kvm_mmu_page_role {
 	unsigned word;
 	struct {
@@ -276,7 +285,7 @@ struct kvm_mmu_page {
 #endif
 
 	/* Number of writes since the last time traversal visited this page.  */
-	int write_flooding_count;
+	atomic_t write_flooding_count;
 };
 
 struct kvm_pio_request {
@@ -338,12 +347,8 @@ struct kvm_mmu {
 
 	struct rsvd_bits_validate guest_rsvd_check;
 
-	/*
-	 * Bitmap: bit set = last pte in walk
-	 * index[0:1]: level (zero-based)
-	 * index[2]: pte.ps
-	 */
-	u8 last_pte_bitmap;
+	/* Can have large pages at levels 2..last_nonleaf_level-1. */
+	u8 last_nonleaf_level;
 
 	bool nx;
 
@@ -498,7 +503,6 @@ struct kvm_vcpu_arch {
 	struct kvm_mmu_memory_cache mmu_page_header_cache;
 
 	struct fpu guest_fpu;
-	bool eager_fpu;
 	u64 xcr0;
 	u64 guest_supported_xcr0;
 	u32 guest_xstate_size;
@@ -644,12 +648,13 @@ struct kvm_vcpu_arch {
 };
 
 struct kvm_lpage_info {
-	int write_count;
+	int disallow_lpage;
 };
 
 struct kvm_arch_memory_slot {
 	struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES];
 	struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
+	unsigned short *gfn_track[KVM_PAGE_TRACK_MAX];
 };
 
 /*
@@ -694,6 +699,8 @@ struct kvm_arch {
 	 */
 	struct list_head active_mmu_pages;
 	struct list_head zapped_obsolete_pages;
+	struct kvm_page_track_notifier_node mmu_sp_tracker;
+	struct kvm_page_track_notifier_head track_notifier_head;
 
 	struct list_head assigned_dev_head;
 	struct iommu_domain *iommu_domain;
@@ -754,6 +761,8 @@ struct kvm_arch {
 
 	bool irqchip_split;
 	u8 nr_reserved_ioapic_pins;
+
+	bool disabled_lapic_found;
 };
 
 struct kvm_vm_stat {
@@ -988,6 +997,8 @@ void kvm_mmu_module_exit(void);
 void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
 int kvm_mmu_create(struct kvm_vcpu *vcpu);
 void kvm_mmu_setup(struct kvm_vcpu *vcpu);
+void kvm_mmu_init_vm(struct kvm *kvm);
+void kvm_mmu_uninit_vm(struct kvm *kvm);
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 		u64 dirty_mask, u64 nx_mask, u64 x_mask);
 
@@ -1127,8 +1138,6 @@ void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id);
 
 void kvm_inject_nmi(struct kvm_vcpu *vcpu);
 
-void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
-		       const u8 *new, int bytes);
 int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
 int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
 void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
new file mode 100644
index 000000000000..c2b8d24a235c
--- /dev/null
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -0,0 +1,61 @@
+#ifndef _ASM_X86_KVM_PAGE_TRACK_H
+#define _ASM_X86_KVM_PAGE_TRACK_H
+
+enum kvm_page_track_mode {
+	KVM_PAGE_TRACK_WRITE,
+	KVM_PAGE_TRACK_MAX,
+};
+
+/*
+ * The notifier represented by @kvm_page_track_notifier_node is linked into
+ * the head which will be notified when guest is triggering the track event.
+ *
+ * Write access on the head is protected by kvm->mmu_lock, read access
+ * is protected by track_srcu.
+ */
+struct kvm_page_track_notifier_head {
+	struct srcu_struct track_srcu;
+	struct hlist_head track_notifier_list;
+};
+
+struct kvm_page_track_notifier_node {
+	struct hlist_node node;
+
+	/*
+	 * It is called when guest is writing the write-tracked page
+	 * and write emulation is finished at that time.
+	 *
+	 * @vcpu: the vcpu where the write access happened.
+	 * @gpa: the physical address written by guest.
+	 * @new: the data was written to the address.
+	 * @bytes: the written length.
+	 */
+	void (*track_write)(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
+			    int bytes);
+};
+
+void kvm_page_track_init(struct kvm *kvm);
+
+void kvm_page_track_free_memslot(struct kvm_memory_slot *free,
+				 struct kvm_memory_slot *dont);
+int kvm_page_track_create_memslot(struct kvm_memory_slot *slot,
+				  unsigned long npages);
+
+void kvm_slot_page_track_add_page(struct kvm *kvm,
+				  struct kvm_memory_slot *slot, gfn_t gfn,
+				  enum kvm_page_track_mode mode);
+void kvm_slot_page_track_remove_page(struct kvm *kvm,
+				     struct kvm_memory_slot *slot, gfn_t gfn,
+				     enum kvm_page_track_mode mode);
+bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn,
+			      enum kvm_page_track_mode mode);
+
+void
+kvm_page_track_register_notifier(struct kvm *kvm,
+				 struct kvm_page_track_notifier_node *n);
+void
+kvm_page_track_unregister_notifier(struct kvm *kvm,
+				   struct kvm_page_track_notifier_node *n);
+void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
+			  int bytes);
+#endif
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index c1adf33fdd0d..bc62e7cbf1b1 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -17,15 +17,8 @@ static inline bool kvm_check_and_clear_guest_paused(void)
 }
 #endif /* CONFIG_KVM_GUEST */
 
-#ifdef CONFIG_DEBUG_RODATA
 #define KVM_HYPERCALL \
         ALTERNATIVE(".byte 0x0f,0x01,0xc1", ".byte 0x0f,0x01,0xd9", X86_FEATURE_VMMCALL)
-#else
-/* On AMD processors, vmcall will generate a trap that we will
- * then rewrite to the appropriate instruction.
- */
-#define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1"
-#endif
 
 /* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall
  * instruction.  The hypervisor may replace it with something else but only the
diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h
index 19c099afa861..e795f5274217 100644
--- a/arch/x86/include/asm/livepatch.h
+++ b/arch/x86/include/asm/livepatch.h
@@ -41,7 +41,7 @@ static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 	regs->ip = ip;
 }
 #else
-#error Live patching support is disabled; check CONFIG_LIVEPATCH
+#error Include linux/livepatch.h, not asm/livepatch.h
 #endif
 
 #endif /* _ASM_X86_LIVEPATCH_H */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 2ea4527e462f..92b6f651fa4f 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -40,8 +40,20 @@
 #define MCI_STATUS_AR	 (1ULL<<55)  /* Action required */
 
 /* AMD-specific bits */
-#define MCI_STATUS_DEFERRED	(1ULL<<44)  /* declare an uncorrected error */
+#define MCI_STATUS_DEFERRED	(1ULL<<44)  /* uncorrected error, deferred exception */
 #define MCI_STATUS_POISON	(1ULL<<43)  /* access poisonous data */
+#define MCI_STATUS_TCC		(1ULL<<55)  /* Task context corrupt */
+
+/*
+ * McaX field if set indicates a given bank supports MCA extensions:
+ *  - Deferred error interrupt type is specifiable by bank.
+ *  - MCx_MISC0[BlkPtr] field indicates presence of extended MISC registers,
+ *    But should not be used to determine MSR numbers.
+ *  - TCC bit is present in MCx_STATUS.
+ */
+#define MCI_CONFIG_MCAX		0x1
+#define MCI_IPID_MCATYPE	0xFFFF0000
+#define MCI_IPID_HWID		0xFFF
 
 /*
  * Note that the full MCACOD field of IA32_MCi_STATUS MSR is
@@ -91,6 +103,16 @@
 #define MCE_LOG_LEN 32
 #define MCE_LOG_SIGNATURE	"MACHINECHECK"
 
+/* AMD Scalable MCA */
+#define MSR_AMD64_SMCA_MC0_MISC0	0xc0002003
+#define MSR_AMD64_SMCA_MC0_CONFIG	0xc0002004
+#define MSR_AMD64_SMCA_MC0_IPID		0xc0002005
+#define MSR_AMD64_SMCA_MC0_MISC1	0xc000200a
+#define MSR_AMD64_SMCA_MCx_MISC(x)	(MSR_AMD64_SMCA_MC0_MISC0 + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_CONFIG(x)	(MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_IPID(x)	(MSR_AMD64_SMCA_MC0_IPID + 0x10*(x))
+#define MSR_AMD64_SMCA_MCx_MISCy(x, y)	((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x)))
+
 /*
  * This structure contains all data related to the MCE log.  Also
  * carries a signature to make it easier to find from external
@@ -113,6 +135,7 @@ struct mca_config {
 	bool ignore_ce;
 	bool disabled;
 	bool ser;
+	bool recovery;
 	bool bios_cmci_threshold;
 	u8 banks;
 	s8 bootlog;
@@ -287,4 +310,49 @@ struct cper_sec_mem_err;
 extern void apei_mce_report_mem_error(int corrected,
 				      struct cper_sec_mem_err *mem_err);
 
+/*
+ * Enumerate new IP types and HWID values in AMD processors which support
+ * Scalable MCA.
+ */
+#ifdef CONFIG_X86_MCE_AMD
+enum amd_ip_types {
+	SMCA_F17H_CORE = 0,	/* Core errors */
+	SMCA_DF,		/* Data Fabric */
+	SMCA_UMC,		/* Unified Memory Controller */
+	SMCA_PB,		/* Parameter Block */
+	SMCA_PSP,		/* Platform Security Processor */
+	SMCA_SMU,		/* System Management Unit */
+	N_AMD_IP_TYPES
+};
+
+struct amd_hwid {
+	const char *name;
+	unsigned int hwid;
+};
+
+extern struct amd_hwid amd_hwids[N_AMD_IP_TYPES];
+
+enum amd_core_mca_blocks {
+	SMCA_LS = 0,	/* Load Store */
+	SMCA_IF,	/* Instruction Fetch */
+	SMCA_L2_CACHE,	/* L2 cache */
+	SMCA_DE,	/* Decoder unit */
+	RES,		/* Reserved */
+	SMCA_EX,	/* Execution unit */
+	SMCA_FP,	/* Floating Point */
+	SMCA_L3_CACHE,	/* L3 cache */
+	N_CORE_MCA_BLOCKS
+};
+
+extern const char * const amd_core_mcablock_names[N_CORE_MCA_BLOCKS];
+
+enum amd_df_mca_blocks {
+	SMCA_CS = 0,	/* Coherent Slave */
+	SMCA_PIE,	/* Power management, Interrupts, etc */
+	N_DF_BLOCKS
+};
+
+extern const char * const amd_df_mcablock_names[N_DF_BLOCKS];
+#endif
+
 #endif /* _ASM_X86_MCE_H */
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 1e1b07a5a738..9d3a96c4da78 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -3,6 +3,7 @@
 
 #include <asm/cpu.h>
 #include <linux/earlycpio.h>
+#include <linux/initrd.h>
 
 #define native_rdmsr(msr, val1, val2)			\
 do {							\
@@ -143,4 +144,29 @@ static inline void reload_early_microcode(void)			{ }
 static inline bool
 get_builtin_firmware(struct cpio_data *cd, const char *name)	{ return false; }
 #endif
+
+static inline unsigned long get_initrd_start(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+	return initrd_start;
+#else
+	return 0;
+#endif
+}
+
+static inline unsigned long get_initrd_start_addr(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+#ifdef CONFIG_X86_32
+	unsigned long *initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start);
+
+	return (unsigned long)__pa_nodebug(*initrd_start_p);
+#else
+	return get_initrd_start();
+#endif
+#else /* CONFIG_BLK_DEV_INITRD */
+	return 0;
+#endif
+}
+
 #endif /* _ASM_X86_MICROCODE_H */
diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h
index 8559b0102ea1..603417f8dd6c 100644
--- a/arch/x86/include/asm/microcode_intel.h
+++ b/arch/x86/include/asm/microcode_intel.h
@@ -40,7 +40,6 @@ struct extended_sigtable {
 #define DEFAULT_UCODE_TOTALSIZE (DEFAULT_UCODE_DATASIZE + MC_HEADER_SIZE)
 #define EXT_HEADER_SIZE		(sizeof(struct extended_sigtable))
 #define EXT_SIGNATURE_SIZE	(sizeof(struct extended_signature))
-#define DWSIZE			(sizeof(u32))
 
 #define get_totalsize(mc) \
 	(((struct microcode_intel *)mc)->hdr.datasize ? \
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 55234d5e7160..1ea0baef1175 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -19,7 +19,8 @@ typedef struct {
 #endif
 
 	struct mutex lock;
-	void __user *vdso;
+	void __user *vdso;			/* vdso base address */
+	const struct vdso_image *vdso_image;	/* vdso image in use */
 
 	atomic_t perf_rdpmc_allowed;	/* nonzero if rdpmc is allowed */
 } mm_context_t;
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index b05402ef3b84..2da46ac16e37 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -1,7 +1,12 @@
 #ifndef _ASM_X86_MSR_INDEX_H
 #define _ASM_X86_MSR_INDEX_H
 
-/* CPU model specific register (MSR) numbers */
+/*
+ * CPU model specific register (MSR) numbers.
+ *
+ * Do not add new entries to this file unless the definitions are shared
+ * between multiple compilation units.
+ */
 
 /* x86-64 specific MSRs */
 #define MSR_EFER		0xc0000080 /* extended feature register */
@@ -230,10 +235,10 @@
 #define HWP_PACKAGE_LEVEL_REQUEST_BIT	(1<<11)
 
 /* IA32_HWP_CAPABILITIES */
-#define HWP_HIGHEST_PERF(x)		(x & 0xff)
-#define HWP_GUARANTEED_PERF(x)		((x & (0xff << 8)) >>8)
-#define HWP_MOSTEFFICIENT_PERF(x)	((x & (0xff << 16)) >>16)
-#define HWP_LOWEST_PERF(x)		((x & (0xff << 24)) >>24)
+#define HWP_HIGHEST_PERF(x)		(((x) >> 0) & 0xff)
+#define HWP_GUARANTEED_PERF(x)		(((x) >> 8) & 0xff)
+#define HWP_MOSTEFFICIENT_PERF(x)	(((x) >> 16) & 0xff)
+#define HWP_LOWEST_PERF(x)		(((x) >> 24) & 0xff)
 
 /* IA32_HWP_REQUEST */
 #define HWP_MIN_PERF(x) 		(x & 0xff)
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index c70689b5e5aa..0deeb2d26df7 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -3,6 +3,8 @@
 
 #include <linux/sched.h>
 
+#include <asm/cpufeature.h>
+
 #define MWAIT_SUBSTATE_MASK		0xf
 #define MWAIT_CSTATE_MASK		0xf
 #define MWAIT_SUBSTATE_SIZE		4
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 462594320d39..9ab7507ca1c2 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -20,6 +20,9 @@ struct pci_sysdata {
 #ifdef CONFIG_X86_64
 	void		*iommu;		/* IOMMU private data */
 #endif
+#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
+	void		*fwnode;	/* IRQ domain for MSI assignment */
+#endif
 };
 
 extern int pci_routeirq;
@@ -32,6 +35,7 @@ extern int noioapicreroute;
 static inline int pci_domain_nr(struct pci_bus *bus)
 {
 	struct pci_sysdata *sd = bus->sysdata;
+
 	return sd->domain;
 }
 
@@ -41,6 +45,17 @@ static inline int pci_proc_domain(struct pci_bus *bus)
 }
 #endif
 
+#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
+static inline void *_pci_root_bus_fwnode(struct pci_bus *bus)
+{
+	struct pci_sysdata *sd = bus->sysdata;
+
+	return sd->fwnode;
+}
+
+#define pci_root_bus_fwnode	_pci_root_bus_fwnode
+#endif
+
 /* Can be used to override the logic in pci_scan_bus for skipping
    already-configured bus numbers - to be used for buggy BIOSes
    or architectures with incomplete PCI setup by the loader */
@@ -105,9 +120,6 @@ void native_restore_msi_irqs(struct pci_dev *dev);
 #include <asm/pci_64.h>
 #endif
 
-/* implement the pci_ DMA API in terms of the generic device dma_ one */
-#include <asm-generic/pci-dma-compat.h>
-
 /* generic pci stuff */
 #include <asm-generic/pci.h>
 
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index 46873fbd44e1..d08eacd298c2 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -93,6 +93,8 @@ extern raw_spinlock_t pci_config_lock;
 extern int (*pcibios_enable_irq)(struct pci_dev *dev);
 extern void (*pcibios_disable_irq)(struct pci_dev *dev);
 
+extern bool mp_should_keep_irq(struct device *dev);
+
 struct pci_raw_ops {
 	int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn,
 						int reg, int len, u32 *val);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 7bcb861a04e5..5a2ed3ed2f26 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -165,6 +165,7 @@ struct x86_pmu_capability {
 #define GLOBAL_STATUS_ASIF				BIT_ULL(60)
 #define GLOBAL_STATUS_COUNTERS_FROZEN			BIT_ULL(59)
 #define GLOBAL_STATUS_LBRS_FROZEN			BIT_ULL(58)
+#define GLOBAL_STATUS_TRACE_TOPAPMI			BIT_ULL(55)
 
 /*
  * IBS cpuid feature detection
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index c57fd1ea9689..bf8b35d2035a 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -137,6 +137,11 @@ static inline void arch_clear_pmem(void __pmem *addr, size_t size)
 	arch_wb_cache_pmem(addr, size);
 }
 
+static inline void arch_invalidate_pmem(void __pmem *addr, size_t size)
+{
+	clflush_cache_range((void __force *) addr, size);
+}
+
 static inline bool __arch_has_wmb_pmem(void)
 {
 	/*
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 2d5a50cb61a2..983738ac014c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -13,7 +13,7 @@ struct vm86;
 #include <asm/types.h>
 #include <uapi/asm/sigcontext.h>
 #include <asm/current.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/page.h>
 #include <asm/pgtable_types.h>
 #include <asm/percpu.h>
@@ -24,7 +24,6 @@ struct vm86;
 #include <asm/fpu/types.h>
 
 #include <linux/personality.h>
-#include <linux/cpumask.h>
 #include <linux/cache.h>
 #include <linux/threads.h>
 #include <linux/math64.h>
@@ -129,6 +128,8 @@ struct cpuinfo_x86 {
 	u16			booted_cores;
 	/* Physical processor id: */
 	u16			phys_proc_id;
+	/* Logical processor id: */
+	u16			logical_proc_id;
 	/* Core id: */
 	u16			cpu_core_id;
 	/* Compute unit id */
@@ -298,10 +299,13 @@ struct tss_struct {
 	 */
 	unsigned long		io_bitmap[IO_BITMAP_LONGS + 1];
 
+#ifdef CONFIG_X86_32
 	/*
-	 * Space for the temporary SYSENTER stack:
+	 * Space for the temporary SYSENTER stack.
 	 */
+	unsigned long		SYSENTER_stack_canary;
 	unsigned long		SYSENTER_stack[64];
+#endif
 
 } ____cacheline_aligned;
 
@@ -766,7 +770,7 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
  * Return saved PC of a blocked thread.
  * What is this good for? it will be always the scheduler or ret_from_fork.
  */
-#define thread_saved_pc(t)	(*(unsigned long *)((t)->thread.sp - 8))
+#define thread_saved_pc(t)	READ_ONCE_NOCHECK(*(unsigned long *)((t)->thread.sp - 8))
 
 #define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
 extern unsigned long KSTK_ESP(struct task_struct *task);
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index a4a77286cb1d..9b9b30b19441 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -7,12 +7,23 @@
 
 void syscall_init(void);
 
+#ifdef CONFIG_X86_64
 void entry_SYSCALL_64(void);
-void entry_SYSCALL_compat(void);
+#endif
+
+#ifdef CONFIG_X86_32
 void entry_INT80_32(void);
-void entry_INT80_compat(void);
 void entry_SYSENTER_32(void);
+void __begin_SYSENTER_singlestep_region(void);
+void __end_SYSENTER_singlestep_region(void);
+#endif
+
+#ifdef CONFIG_IA32_EMULATION
 void entry_SYSENTER_compat(void);
+void __end_entry_SYSENTER_compat(void);
+void entry_SYSCALL_compat(void);
+void entry_INT80_compat(void);
+#endif
 
 void x86_configure_nx(void);
 void x86_report_nx(void);
diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h
index 0a5242428659..13b6cdd0af57 100644
--- a/arch/x86/include/asm/sections.h
+++ b/arch/x86/include/asm/sections.h
@@ -7,7 +7,7 @@
 extern char __brk_base[], __brk_limit[];
 extern struct exception_table_entry __stop___ex_table[];
 
-#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
+#if defined(CONFIG_X86_64)
 extern char __end_rodata_hpage_align[];
 #endif
 
diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h
index 89db46752a8f..452c88b8ad06 100644
--- a/arch/x86/include/asm/sighandling.h
+++ b/arch/x86/include/asm/sighandling.h
@@ -13,7 +13,6 @@
 			 X86_EFLAGS_CF | X86_EFLAGS_RF)
 
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
-int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc);
 int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
 		     struct pt_regs *regs, unsigned long mask);
 
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index ba665ebd17bb..db333300bd4b 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -15,7 +15,7 @@
 
 #include <linux/stringify.h>
 #include <asm/nops.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 
 /* "Raw" instruction opcodes */
 #define __ASM_CLAC	.byte 0x0f,0x01,0xca
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index dfcf0727623b..20a3de5cb3b0 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -16,7 +16,6 @@
 #endif
 #include <asm/thread_info.h>
 #include <asm/cpumask.h>
-#include <asm/cpufeature.h>
 
 extern int smp_num_siblings;
 extern unsigned int num_processors;
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index ff8b9a17dc4b..ca6ba3607705 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -78,6 +78,19 @@ int strcmp(const char *cs, const char *ct);
 #define memset(s, c, n) __memset(s, c, n)
 #endif
 
+/**
+ * memcpy_mcsafe - copy memory with indication if a machine check happened
+ *
+ * @dst:	destination address
+ * @src:	source address
+ * @cnt:	number of bytes to copy
+ *
+ * Low level memory copy function that catches machine checks
+ *
+ * Return true for success, false for fail
+ */
+bool memcpy_mcsafe(void *dst, const void *src, size_t cnt);
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_STRING_64_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index c7b551028740..82866697fcf1 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -49,7 +49,7 @@
  */
 #ifndef __ASSEMBLY__
 struct task_struct;
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <linux/atomic.h>
 
 struct thread_info {
@@ -134,10 +134,13 @@ struct thread_info {
 #define _TIF_ADDR32		(1 << TIF_ADDR32)
 #define _TIF_X32		(1 << TIF_X32)
 
-/* work to do in syscall_trace_enter() */
+/*
+ * work to do in syscall_trace_enter().  Also includes TIF_NOHZ for
+ * enter_from_user_mode()
+ */
 #define _TIF_WORK_SYSCALL_ENTRY	\
 	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT |	\
-	 _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT |	\
+	 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT |	\
 	 _TIF_NOHZ)
 
 /* work to do on any return to user space */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6df2029405a3..c24b4224d439 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -5,8 +5,57 @@
 #include <linux/sched.h>
 
 #include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/special_insns.h>
 
+static inline void __invpcid(unsigned long pcid, unsigned long addr,
+			     unsigned long type)
+{
+	struct { u64 d[2]; } desc = { { pcid, addr } };
+
+	/*
+	 * The memory clobber is because the whole point is to invalidate
+	 * stale TLB entries and, especially if we're flushing global
+	 * mappings, we don't want the compiler to reorder any subsequent
+	 * memory accesses before the TLB flush.
+	 *
+	 * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
+	 * invpcid (%rcx), %rax in long mode.
+	 */
+	asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
+		      : : "m" (desc), "a" (type), "c" (&desc) : "memory");
+}
+
+#define INVPCID_TYPE_INDIV_ADDR		0
+#define INVPCID_TYPE_SINGLE_CTXT	1
+#define INVPCID_TYPE_ALL_INCL_GLOBAL	2
+#define INVPCID_TYPE_ALL_NON_GLOBAL	3
+
+/* Flush all mappings for a given pcid and addr, not including globals. */
+static inline void invpcid_flush_one(unsigned long pcid,
+				     unsigned long addr)
+{
+	__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
+}
+
+/* Flush all mappings for a given PCID, not including globals. */
+static inline void invpcid_flush_single_context(unsigned long pcid)
+{
+	__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+}
+
+/* Flush all mappings, including globals, for all PCIDs. */
+static inline void invpcid_flush_all(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+}
+
+/* Flush all mappings for all PCIDs except globals. */
+static inline void invpcid_flush_all_nonglobals(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
+}
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else
@@ -104,6 +153,15 @@ static inline void __native_flush_tlb_global(void)
 {
 	unsigned long flags;
 
+	if (static_cpu_has(X86_FEATURE_INVPCID)) {
+		/*
+		 * Using INVPCID is considerably faster than a pair of writes
+		 * to CR4 sandwiched inside an IRQ flag save/restore.
+		 */
+		invpcid_flush_all();
+		return;
+	}
+
 	/*
 	 * Read-modify-write to CR4 - protect it from preemption and
 	 * from interrupts. (Use the raw variant because this code can
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 0fb46482dfde..7f991bd5031b 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -119,12 +119,23 @@ static inline void setup_node_to_cpumask_map(void) { }
 
 extern const struct cpumask *cpu_coregroup_mask(int cpu);
 
+#define topology_logical_package_id(cpu)	(cpu_data(cpu).logical_proc_id)
 #define topology_physical_package_id(cpu)	(cpu_data(cpu).phys_proc_id)
 #define topology_core_id(cpu)			(cpu_data(cpu).cpu_core_id)
 
 #ifdef ENABLE_TOPO_DEFINES
 #define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
 #define topology_sibling_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
+
+extern unsigned int __max_logical_packages;
+#define topology_max_packages()			(__max_logical_packages)
+int topology_update_package_map(unsigned int apicid, unsigned int cpu);
+extern int topology_phys_to_logical_pkg(unsigned int pkg);
+#else
+#define topology_max_packages()			(1)
+static inline int
+topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; }
+static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 6d7c5479bcea..174c4212780a 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -29,6 +29,8 @@ static inline cycles_t get_cycles(void)
 	return rdtsc();
 }
 
+extern struct system_counterval_t convert_art_to_tsc(cycle_t art);
+
 extern void tsc_init(void);
 extern void mark_tsc_unstable(char *reason);
 extern int unsynchronized_tsc(void);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index a4a30e4b2d34..c0f27d7ea7ff 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -90,12 +90,11 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
 	likely(!__range_not_ok(addr, size, user_addr_max()))
 
 /*
- * The exception table consists of pairs of addresses relative to the
- * exception table enty itself: the first is the address of an
- * instruction that is allowed to fault, and the second is the address
- * at which the program should continue.  No registers are modified,
- * so it is entirely up to the continuation code to figure out what to
- * do.
+ * The exception table consists of triples of addresses relative to the
+ * exception table entry itself. The first address is of an instruction
+ * that is allowed to fault, the second is the target at which the program
+ * should continue. The third is a handler function to deal with the fault
+ * caused by the instruction in the first field.
  *
  * All the routines below use bits of fixup code that are out of line
  * with the main instruction path.  This means when everything is well,
@@ -104,13 +103,14 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
  */
 
 struct exception_table_entry {
-	int insn, fixup;
+	int insn, fixup, handler;
 };
 /* This is not the generic standard exception_table_entry format */
 #define ARCH_HAS_SORT_EXTABLE
 #define ARCH_HAS_SEARCH_EXTABLE
 
-extern int fixup_exception(struct pt_regs *regs);
+extern int fixup_exception(struct pt_regs *regs, int trapnr);
+extern bool ex_has_fault_handler(unsigned long ip);
 extern int early_fixup_exception(unsigned long *ip);
 
 /*
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index f5dcb5204dcd..3fe0eac59462 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -48,20 +48,28 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
 
 		switch (n) {
 		case 1:
+			__uaccess_begin();
 			__put_user_size(*(u8 *)from, (u8 __user *)to,
 					1, ret, 1);
+			__uaccess_end();
 			return ret;
 		case 2:
+			__uaccess_begin();
 			__put_user_size(*(u16 *)from, (u16 __user *)to,
 					2, ret, 2);
+			__uaccess_end();
 			return ret;
 		case 4:
+			__uaccess_begin();
 			__put_user_size(*(u32 *)from, (u32 __user *)to,
 					4, ret, 4);
+			__uaccess_end();
 			return ret;
 		case 8:
+			__uaccess_begin();
 			__put_user_size(*(u64 *)from, (u64 __user *)to,
 					8, ret, 8);
+			__uaccess_end();
 			return ret;
 		}
 	}
@@ -103,13 +111,19 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
 
 		switch (n) {
 		case 1:
+			__uaccess_begin();
 			__get_user_size(*(u8 *)to, from, 1, ret, 1);
+			__uaccess_end();
 			return ret;
 		case 2:
+			__uaccess_begin();
 			__get_user_size(*(u16 *)to, from, 2, ret, 2);
+			__uaccess_end();
 			return ret;
 		case 4:
+			__uaccess_begin();
 			__get_user_size(*(u32 *)to, from, 4, ret, 4);
+			__uaccess_end();
 			return ret;
 		}
 	}
@@ -148,13 +162,19 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
 
 		switch (n) {
 		case 1:
+			__uaccess_begin();
 			__get_user_size(*(u8 *)to, from, 1, ret, 1);
+			__uaccess_end();
 			return ret;
 		case 2:
+			__uaccess_begin();
 			__get_user_size(*(u16 *)to, from, 2, ret, 2);
+			__uaccess_end();
 			return ret;
 		case 4:
+			__uaccess_begin();
 			__get_user_size(*(u32 *)to, from, 4, ret, 4);
+			__uaccess_end();
 			return ret;
 		}
 	}
@@ -170,13 +190,19 @@ static __always_inline unsigned long __copy_from_user_nocache(void *to,
 
 		switch (n) {
 		case 1:
+			__uaccess_begin();
 			__get_user_size(*(u8 *)to, from, 1, ret, 1);
+			__uaccess_end();
 			return ret;
 		case 2:
+			__uaccess_begin();
 			__get_user_size(*(u16 *)to, from, 2, ret, 2);
+			__uaccess_end();
 			return ret;
 		case 4:
+			__uaccess_begin();
 			__get_user_size(*(u32 *)to, from, 4, ret, 4);
+			__uaccess_end();
 			return ret;
 		}
 	}
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index b89c34c4019b..307698688fa1 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -8,7 +8,7 @@
 #include <linux/errno.h>
 #include <linux/lockdep.h>
 #include <asm/alternative.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/page.h>
 
 /*
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index deabaf9759b6..43dc55be524e 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -13,9 +13,6 @@ struct vdso_image {
 	void *data;
 	unsigned long size;   /* Always a multiple of PAGE_SIZE */
 
-	/* text_mapping.pages is big enough for data/size page pointers */
-	struct vm_special_mapping text_mapping;
-
 	unsigned long alt, alt_len;
 
 	long sym_vvar_start;  /* Negative offset to the vvar area */
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index f556c4843aa1..e728699db774 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -37,6 +37,12 @@ struct vsyscall_gtod_data {
 };
 extern struct vsyscall_gtod_data vsyscall_gtod_data;
 
+extern int vclocks_used;
+static inline bool vclock_was_used(int vclock)
+{
+	return READ_ONCE(vclocks_used) & (1 << vclock);
+}
+
 static inline unsigned gtod_read_begin(const struct vsyscall_gtod_data *s)
 {
 	unsigned ret;
diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h
index 968d57dd54c9..f320ee32d5a1 100644
--- a/arch/x86/include/asm/xen/pci.h
+++ b/arch/x86/include/asm/xen/pci.h
@@ -57,7 +57,7 @@ static inline int xen_pci_frontend_enable_msi(struct pci_dev *dev,
 {
 	if (xen_pci_frontend && xen_pci_frontend->enable_msi)
 		return xen_pci_frontend->enable_msi(dev, vectors);
-	return -ENODEV;
+	return -ENOSYS;
 }
 static inline void xen_pci_frontend_disable_msi(struct pci_dev *dev)
 {
@@ -69,7 +69,7 @@ static inline int xen_pci_frontend_enable_msix(struct pci_dev *dev,
 {
 	if (xen_pci_frontend && xen_pci_frontend->enable_msix)
 		return xen_pci_frontend->enable_msix(dev, vectors, nvec);
-	return -ENODEV;
+	return -ENOSYS;
 }
 static inline void xen_pci_frontend_disable_msix(struct pci_dev *dev)
 {
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index 7956412d09bd..9b1a91834ac8 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -226,7 +226,9 @@
 		(~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1))
 
 /* Declare the various hypercall operations. */
-#define HV_X64_HV_NOTIFY_LONG_SPIN_WAIT		0x0008
+#define HVCALL_NOTIFY_LONG_SPIN_WAIT		0x0008
+#define HVCALL_POST_MESSAGE			0x005c
+#define HVCALL_SIGNAL_EVENT			0x005d
 
 #define HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE		0x00000001
 #define HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT	12
diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h
index d485232f1e9f..62d4111c1c54 100644
--- a/arch/x86/include/uapi/asm/sigcontext.h
+++ b/arch/x86/include/uapi/asm/sigcontext.h
@@ -256,7 +256,7 @@ struct sigcontext_64 {
 	__u16				cs;
 	__u16				gs;
 	__u16				fs;
-	__u16				__pad0;
+	__u16				ss;
 	__u64				err;
 	__u64				trapno;
 	__u64				oldmask;
@@ -341,9 +341,37 @@ struct sigcontext {
 	__u64				rip;
 	__u64				eflags;		/* RFLAGS */
 	__u16				cs;
+
+	/*
+	 * Prior to 2.5.64 ("[PATCH] x86-64 updates for 2.5.64-bk3"),
+	 * Linux saved and restored fs and gs in these slots.  This
+	 * was counterproductive, as fsbase and gsbase were never
+	 * saved, so arch_prctl was presumably unreliable.
+	 *
+	 * These slots should never be reused without extreme caution:
+	 *
+	 *  - Some DOSEMU versions stash fs and gs in these slots manually,
+	 *    thus overwriting anything the kernel expects to be preserved
+	 *    in these slots.
+	 *
+	 *  - If these slots are ever needed for any other purpose,
+	 *    there is some risk that very old 64-bit binaries could get
+	 *    confused.  I doubt that many such binaries still work,
+	 *    though, since the same patch in 2.5.64 also removed the
+	 *    64-bit set_thread_area syscall, so it appears that there
+	 *    is no TLS API beyond modify_ldt that works in both pre-
+	 *    and post-2.5.64 kernels.
+	 *
+	 * If the kernel ever adds explicit fs, gs, fsbase, and gsbase
+	 * save/restore, it will most likely need to be opt-in and use
+	 * different context slots.
+	 */
 	__u16				gs;
 	__u16				fs;
-	__u16				__pad0;
+	union {
+		__u16			ss;	/* If UC_SIGCONTEXT_SS */
+		__u16			__pad0;	/* Alias name for old (!UC_SIGCONTEXT_SS) user-space */
+	};
 	__u64				err;
 	__u64				trapno;
 	__u64				oldmask;
diff --git a/arch/x86/include/uapi/asm/ucontext.h b/arch/x86/include/uapi/asm/ucontext.h
index b7c29c8017f2..e3d1ec90616e 100644
--- a/arch/x86/include/uapi/asm/ucontext.h
+++ b/arch/x86/include/uapi/asm/ucontext.h
@@ -1,11 +1,54 @@
 #ifndef _ASM_X86_UCONTEXT_H
 #define _ASM_X86_UCONTEXT_H
 
-#define UC_FP_XSTATE	0x1	/* indicates the presence of extended state
-				 * information in the memory layout pointed
-				 * by the fpstate pointer in the ucontext's
-				 * sigcontext struct (uc_mcontext).
-				 */
+/*
+ * Indicates the presence of extended state information in the memory
+ * layout pointed by the fpstate pointer in the ucontext's sigcontext
+ * struct (uc_mcontext).
+ */
+#define UC_FP_XSTATE	0x1
+
+#ifdef __x86_64__
+/*
+ * UC_SIGCONTEXT_SS will be set when delivering 64-bit or x32 signals on
+ * kernels that save SS in the sigcontext.  All kernels that set
+ * UC_SIGCONTEXT_SS will correctly restore at least the low 32 bits of esp
+ * regardless of SS (i.e. they implement espfix).
+ *
+ * Kernels that set UC_SIGCONTEXT_SS will also set UC_STRICT_RESTORE_SS
+ * when delivering a signal that came from 64-bit code.
+ *
+ * Sigreturn restores SS as follows:
+ *
+ * if (saved SS is valid || UC_STRICT_RESTORE_SS is set ||
+ *     saved CS is not 64-bit)
+ *         new SS = saved SS  (will fail IRET and signal if invalid)
+ * else
+ *         new SS = a flat 32-bit data segment
+ *
+ * This behavior serves three purposes:
+ *
+ * - Legacy programs that construct a 64-bit sigcontext from scratch
+ *   with zero or garbage in the SS slot (e.g. old CRIU) and call
+ *   sigreturn will still work.
+ *
+ * - Old DOSEMU versions sometimes catch a signal from a segmented
+ *   context, delete the old SS segment (with modify_ldt), and change
+ *   the saved CS to a 64-bit segment.  These DOSEMU versions expect
+ *   sigreturn to send them back to 64-bit mode without killing them,
+ *   despite the fact that the SS selector when the signal was raised is
+ *   no longer valid.  UC_STRICT_RESTORE_SS will be clear, so the kernel
+ *   will fix up SS for these DOSEMU versions.
+ *
+ * - Old and new programs that catch a signal and return without
+ *   modifying the saved context will end up in exactly the state they
+ *   started in, even if they were running in a segmented context when
+ *   the signal was raised..  Old kernels would lose track of the
+ *   previous SS value.
+ */
+#define UC_SIGCONTEXT_SS	0x2
+#define UC_STRICT_RESTORE_SS	0x4
+#endif
 
 #include <asm-generic/ucontext.h>
 
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index d1daead5fcdd..adb3eaf8fe2a 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -16,6 +16,7 @@
 #include <asm/cacheflush.h>
 #include <asm/realmode.h>
 
+#include <linux/ftrace.h>
 #include "../../realmode/rm/wakeup.h"
 #include "sleep.h"
 
@@ -107,7 +108,13 @@ int x86_acpi_suspend_lowlevel(void)
        saved_magic = 0x123456789abcdef0L;
 #endif /* CONFIG_64BIT */
 
+	/*
+	 * Pause/unpause graph tracing around do_suspend_lowlevel as it has
+	 * inconsistent call/return info after it jumps to the wakeup vector.
+	 */
+	pause_graph_tracing();
 	do_suspend_lowlevel();
+	unpause_graph_tracing();
 	return 0;
 }
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 8a5cddac7d44..531b9611c51d 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2078,6 +2078,20 @@ int generic_processor_info(int apicid, int version)
 		cpu = cpumask_next_zero(-1, cpu_present_mask);
 
 	/*
+	 * This can happen on physical hotplug. The sanity check at boot time
+	 * is done from native_smp_prepare_cpus() after num_possible_cpus() is
+	 * established.
+	 */
+	if (topology_update_package_map(apicid, cpu) < 0) {
+		int thiscpu = max + disabled_cpus;
+
+		pr_warning("ACPI: Package limit reached. Processor %d/0x%x ignored.\n",
+			   thiscpu, apicid);
+		disabled_cpus++;
+		return -ENOSPC;
+	}
+
+	/*
 	 * Validate version
 	 */
 	if (version == 0x0) {
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 9968f30cca3e..76f89e2b245a 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -53,7 +53,7 @@ void flat_init_apic_ldr(void)
 	apic_write(APIC_LDR, val);
 }
 
-static inline void _flat_send_IPI_mask(unsigned long mask, int vector)
+static void _flat_send_IPI_mask(unsigned long mask, int vector)
 {
 	unsigned long flags;
 
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index c80c02c6ec49..ab5c2c685a3c 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -30,7 +30,7 @@ static unsigned int numachip1_get_apic_id(unsigned long x)
 	unsigned long value;
 	unsigned int id = (x >> 24) & 0xff;
 
-	if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) {
+	if (static_cpu_has(X86_FEATURE_NODEID_MSR)) {
 		rdmsrl(MSR_FAM10H_NODE_ID, value);
 		id |= (value << 2) & 0xff00;
 	}
@@ -178,7 +178,7 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
 	this_cpu_write(cpu_llc_id, node);
 
 	/* Account for nodes per socket in multi-core-module processors */
-	if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) {
+	if (static_cpu_has(X86_FEATURE_NODEID_MSR)) {
 		rdmsrl(MSR_FAM10H_NODE_ID, val);
 		nodes = ((val >> 3) & 7) + 1;
 	}
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index eb45fc9b6124..28bde88b0085 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -18,6 +18,66 @@
 #include <asm/proto.h>
 #include <asm/ipi.h>
 
+void __default_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest)
+{
+	/*
+	 * Subtle. In the case of the 'never do double writes' workaround
+	 * we have to lock out interrupts to be safe.  As we don't care
+	 * of the value read we use an atomic rmw access to avoid costly
+	 * cli/sti.  Otherwise we use an even cheaper single atomic write
+	 * to the APIC.
+	 */
+	unsigned int cfg;
+
+	/*
+	 * Wait for idle.
+	 */
+	__xapic_wait_icr_idle();
+
+	/*
+	 * No need to touch the target chip field
+	 */
+	cfg = __prepare_ICR(shortcut, vector, dest);
+
+	/*
+	 * Send the IPI. The write to APIC_ICR fires this off.
+	 */
+	native_apic_mem_write(APIC_ICR, cfg);
+}
+
+/*
+ * This is used to send an IPI with no shorthand notation (the destination is
+ * specified in bits 56 to 63 of the ICR).
+ */
+void __default_send_IPI_dest_field(unsigned int mask, int vector, unsigned int dest)
+{
+	unsigned long cfg;
+
+	/*
+	 * Wait for idle.
+	 */
+	if (unlikely(vector == NMI_VECTOR))
+		safe_apic_wait_icr_idle();
+	else
+		__xapic_wait_icr_idle();
+
+	/*
+	 * prepare target chip field
+	 */
+	cfg = __prepare_ICR2(mask);
+	native_apic_mem_write(APIC_ICR2, cfg);
+
+	/*
+	 * program the ICR
+	 */
+	cfg = __prepare_ICR(0, vector, dest);
+
+	/*
+	 * Send the IPI. The write to APIC_ICR fires this off.
+	 */
+	native_apic_mem_write(APIC_ICR, cfg);
+}
+
 void default_send_IPI_single_phys(int cpu, int vector)
 {
 	unsigned long flags;
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 84a7524b202c..5c042466f274 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -59,7 +59,6 @@ void common(void) {
 
 #ifdef CONFIG_PARAVIRT
 	BLANK();
-	OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
 	OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
 	OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
 	OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 6ce39025f467..ecdc1d217dc0 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -7,7 +7,7 @@
 #include <linux/lguest.h>
 #include "../../../drivers/lguest/lg.h"
 
-#define __SYSCALL_I386(nr, sym, compat) [nr] = 1,
+#define __SYSCALL_I386(nr, sym, qual) [nr] = 1,
 static char syscalls[] = {
 #include <asm/syscalls_32.h>
 };
@@ -52,6 +52,11 @@ void foo(void)
 	DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) -
 	       offsetofend(struct tss_struct, SYSENTER_stack));
 
+	/* Offset from cpu_tss to SYSENTER_stack */
+	OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack);
+	/* Size of SYSENTER_stack */
+	DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack));
+
 #if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE)
 	BLANK();
 	OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled);
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index f2edafb5f24e..d875f97d4e0b 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -4,17 +4,11 @@
 
 #include <asm/ia32.h>
 
-#define __SYSCALL_64(nr, sym, compat) [nr] = 1,
-#define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1,
-#ifdef CONFIG_X86_X32_ABI
-# define __SYSCALL_X32(nr, sym, compat) [nr] = 1,
-#else
-# define __SYSCALL_X32(nr, sym, compat) /* nothing */
-#endif
+#define __SYSCALL_64(nr, sym, qual) [nr] = 1,
 static char syscalls_64[] = {
 #include <asm/syscalls_64.h>
 };
-#define __SYSCALL_I386(nr, sym, compat) [nr] = 1,
+#define __SYSCALL_I386(nr, sym, qual) [nr] = 1,
 static char syscalls_ia32[] = {
 #include <asm/syscalls_32.h>
 };
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 58031303e304..0d373d7affc8 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -30,33 +30,11 @@ obj-$(CONFIG_CPU_SUP_CENTAUR)		+= centaur.o
 obj-$(CONFIG_CPU_SUP_TRANSMETA_32)	+= transmeta.o
 obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
 
-obj-$(CONFIG_PERF_EVENTS)		+= perf_event.o
-
-ifdef CONFIG_PERF_EVENTS
-obj-$(CONFIG_CPU_SUP_AMD)		+= perf_event_amd.o perf_event_amd_uncore.o
-ifdef CONFIG_AMD_IOMMU
-obj-$(CONFIG_CPU_SUP_AMD)		+= perf_event_amd_iommu.o
-endif
-obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_p6.o perf_event_knc.o perf_event_p4.o
-obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
-obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_rapl.o perf_event_intel_cqm.o
-obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_pt.o perf_event_intel_bts.o
-obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_cstate.o
-
-obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= perf_event_intel_uncore.o \
-					   perf_event_intel_uncore_snb.o \
-					   perf_event_intel_uncore_snbep.o \
-					   perf_event_intel_uncore_nhmex.o
-obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_msr.o
-obj-$(CONFIG_CPU_SUP_AMD)		+= perf_event_msr.o
-endif
-
-
 obj-$(CONFIG_X86_MCE)			+= mcheck/
 obj-$(CONFIG_MTRR)			+= mtrr/
 obj-$(CONFIG_MICROCODE)			+= microcode/
 
-obj-$(CONFIG_X86_LOCAL_APIC)		+= perfctr-watchdog.o perf_event_amd_ibs.o
+obj-$(CONFIG_X86_LOCAL_APIC)		+= perfctr-watchdog.o
 
 obj-$(CONFIG_HYPERVISOR_GUEST)		+= vmware.o hypervisor.o mshyperv.o
 
@@ -64,7 +42,7 @@ ifdef CONFIG_X86_FEATURE_NAMES
 quiet_cmd_mkcapflags = MKCAP   $@
       cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $< $@
 
-cpufeature = $(src)/../../include/asm/cpufeature.h
+cpufeature = $(src)/../../include/asm/cpufeatures.h
 
 targets += capflags.c
 $(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.sh FORCE
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index a07956a08936..97c59fd60702 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -117,7 +117,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c)
 		void (*f_vide)(void);
 		u64 d, d2;
 
-		printk(KERN_INFO "AMD K6 stepping B detected - ");
+		pr_info("AMD K6 stepping B detected - ");
 
 		/*
 		 * It looks like AMD fixed the 2.6.2 bug and improved indirect
@@ -133,10 +133,9 @@ static void init_amd_k6(struct cpuinfo_x86 *c)
 		d = d2-d;
 
 		if (d > 20*K6_BUG_LOOP)
-			printk(KERN_CONT
-				"system stability may be impaired when more than 32 MB are used.\n");
+			pr_cont("system stability may be impaired when more than 32 MB are used.\n");
 		else
-			printk(KERN_CONT "probably OK (after B9730xxxx).\n");
+			pr_cont("probably OK (after B9730xxxx).\n");
 	}
 
 	/* K6 with old style WHCR */
@@ -154,7 +153,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c)
 			wbinvd();
 			wrmsr(MSR_K6_WHCR, l, h);
 			local_irq_restore(flags);
-			printk(KERN_INFO "Enabling old style K6 write allocation for %d Mb\n",
+			pr_info("Enabling old style K6 write allocation for %d Mb\n",
 				mbytes);
 		}
 		return;
@@ -175,7 +174,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c)
 			wbinvd();
 			wrmsr(MSR_K6_WHCR, l, h);
 			local_irq_restore(flags);
-			printk(KERN_INFO "Enabling new style K6 write allocation for %d Mb\n",
+			pr_info("Enabling new style K6 write allocation for %d Mb\n",
 				mbytes);
 		}
 
@@ -202,7 +201,7 @@ static void init_amd_k7(struct cpuinfo_x86 *c)
 	 */
 	if (c->x86_model >= 6 && c->x86_model <= 10) {
 		if (!cpu_has(c, X86_FEATURE_XMM)) {
-			printk(KERN_INFO "Enabling disabled K7/SSE Support.\n");
+			pr_info("Enabling disabled K7/SSE Support.\n");
 			msr_clear_bit(MSR_K7_HWCR, 15);
 			set_cpu_cap(c, X86_FEATURE_XMM);
 		}
@@ -216,9 +215,8 @@ static void init_amd_k7(struct cpuinfo_x86 *c)
 	if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) {
 		rdmsr(MSR_K7_CLK_CTL, l, h);
 		if ((l & 0xfff00000) != 0x20000000) {
-			printk(KERN_INFO
-			    "CPU: CLK_CTL MSR was %x. Reprogramming to %x\n",
-					l, ((l & 0x000fffff)|0x20000000));
+			pr_info("CPU: CLK_CTL MSR was %x. Reprogramming to %x\n",
+				l, ((l & 0x000fffff)|0x20000000));
 			wrmsr(MSR_K7_CLK_CTL, (l & 0x000fffff)|0x20000000, h);
 		}
 	}
@@ -485,7 +483,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
 			unsigned long pfn = tseg >> PAGE_SHIFT;
 
-			printk(KERN_DEBUG "tseg: %010llx\n", tseg);
+			pr_debug("tseg: %010llx\n", tseg);
 			if (pfn_range_is_mapped(pfn, pfn + 1))
 				set_memory_4k((unsigned long)__va(tseg), 1);
 		}
@@ -500,8 +498,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 
 			rdmsrl(MSR_K7_HWCR, val);
 			if (!(val & BIT(24)))
-				printk(KERN_WARNING FW_BUG "TSC doesn't count "
-					"with P0 frequency!\n");
+				pr_warn(FW_BUG "TSC doesn't count with P0 frequency!\n");
 		}
 	}
 
diff --git a/arch/x86/kernel/cpu/bugs_64.c b/arch/x86/kernel/cpu/bugs_64.c
index 04f0fe5af83e..a972ac4c7e7d 100644
--- a/arch/x86/kernel/cpu/bugs_64.c
+++ b/arch/x86/kernel/cpu/bugs_64.c
@@ -15,7 +15,7 @@ void __init check_bugs(void)
 {
 	identify_boot_cpu();
 #if !defined(CONFIG_SMP)
-	printk(KERN_INFO "CPU: ");
+	pr_info("CPU: ");
 	print_cpu_info(&boot_cpu_data);
 #endif
 	alternative_instructions();
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index ae20be6e483c..1661d8ec9280 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -1,7 +1,7 @@
 #include <linux/bitops.h>
 #include <linux/kernel.h>
 
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/e820.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
@@ -29,7 +29,7 @@ static void init_c3(struct cpuinfo_x86 *c)
 			rdmsr(MSR_VIA_FCR, lo, hi);
 			lo |= ACE_FCR;		/* enable ACE unit */
 			wrmsr(MSR_VIA_FCR, lo, hi);
-			printk(KERN_INFO "CPU: Enabled ACE h/w crypto\n");
+			pr_info("CPU: Enabled ACE h/w crypto\n");
 		}
 
 		/* enable RNG unit, if present and disabled */
@@ -37,7 +37,7 @@ static void init_c3(struct cpuinfo_x86 *c)
 			rdmsr(MSR_VIA_RNG, lo, hi);
 			lo |= RNG_ENABLE;	/* enable RNG unit */
 			wrmsr(MSR_VIA_RNG, lo, hi);
-			printk(KERN_INFO "CPU: Enabled h/w RNG\n");
+			pr_info("CPU: Enabled h/w RNG\n");
 		}
 
 		/* store Centaur Extended Feature Flags as
@@ -130,7 +130,7 @@ static void init_centaur(struct cpuinfo_x86 *c)
 			name = "C6";
 			fcr_set = ECX8|DSMC|EDCTLB|EMMX|ERETSTK;
 			fcr_clr = DPDC;
-			printk(KERN_NOTICE "Disabling bugged TSC.\n");
+			pr_notice("Disabling bugged TSC.\n");
 			clear_cpu_cap(c, X86_FEATURE_TSC);
 			break;
 		case 8:
@@ -163,11 +163,11 @@ static void init_centaur(struct cpuinfo_x86 *c)
 		newlo = (lo|fcr_set) & (~fcr_clr);
 
 		if (newlo != lo) {
-			printk(KERN_INFO "Centaur FCR was 0x%X now 0x%X\n",
+			pr_info("Centaur FCR was 0x%X now 0x%X\n",
 				lo, newlo);
 			wrmsr(MSR_IDT_FCR1, newlo, hi);
 		} else {
-			printk(KERN_INFO "Centaur FCR is 0x%X\n", lo);
+			pr_info("Centaur FCR is 0x%X\n", lo);
 		}
 		/* Emulate MTRRs using Centaur's MCR. */
 		set_cpu_cap(c, X86_FEATURE_CENTAUR_MCR);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 37830de8f60a..249461f95851 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -162,6 +162,22 @@ static int __init x86_mpx_setup(char *s)
 }
 __setup("nompx", x86_mpx_setup);
 
+static int __init x86_noinvpcid_setup(char *s)
+{
+	/* noinvpcid doesn't accept parameters */
+	if (s)
+		return -EINVAL;
+
+	/* do not emit a message if the feature is not present */
+	if (!boot_cpu_has(X86_FEATURE_INVPCID))
+		return 0;
+
+	setup_clear_cpu_cap(X86_FEATURE_INVPCID);
+	pr_info("noinvpcid: INVPCID feature disabled\n");
+	return 0;
+}
+early_param("noinvpcid", x86_noinvpcid_setup);
+
 #ifdef CONFIG_X86_32
 static int cachesize_override = -1;
 static int disable_x86_serial_nr = 1;
@@ -228,7 +244,7 @@ static void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
 	lo |= 0x200000;
 	wrmsr(MSR_IA32_BBL_CR_CTL, lo, hi);
 
-	printk(KERN_NOTICE "CPU serial number disabled.\n");
+	pr_notice("CPU serial number disabled.\n");
 	clear_cpu_cap(c, X86_FEATURE_PN);
 
 	/* Disabling the serial number may affect the cpuid level */
@@ -329,9 +345,8 @@ static void filter_cpuid_features(struct cpuinfo_x86 *c, bool warn)
 		if (!warn)
 			continue;
 
-		printk(KERN_WARNING
-		       "CPU: CPU feature " X86_CAP_FMT " disabled, no CPUID level 0x%x\n",
-				x86_cap_flag(df->feature), df->level);
+		pr_warn("CPU: CPU feature " X86_CAP_FMT " disabled, no CPUID level 0x%x\n",
+			x86_cap_flag(df->feature), df->level);
 	}
 }
 
@@ -510,7 +525,7 @@ void detect_ht(struct cpuinfo_x86 *c)
 	smp_num_siblings = (ebx & 0xff0000) >> 16;
 
 	if (smp_num_siblings == 1) {
-		printk_once(KERN_INFO "CPU0: Hyper-Threading is disabled\n");
+		pr_info_once("CPU0: Hyper-Threading is disabled\n");
 		goto out;
 	}
 
@@ -531,10 +546,10 @@ void detect_ht(struct cpuinfo_x86 *c)
 
 out:
 	if (!printed && (c->x86_max_cores * smp_num_siblings) > 1) {
-		printk(KERN_INFO  "CPU: Physical Processor ID: %d\n",
-		       c->phys_proc_id);
-		printk(KERN_INFO  "CPU: Processor Core ID: %d\n",
-		       c->cpu_core_id);
+		pr_info("CPU: Physical Processor ID: %d\n",
+			c->phys_proc_id);
+		pr_info("CPU: Processor Core ID: %d\n",
+			c->cpu_core_id);
 		printed = 1;
 	}
 #endif
@@ -559,9 +574,8 @@ static void get_cpu_vendor(struct cpuinfo_x86 *c)
 		}
 	}
 
-	printk_once(KERN_ERR
-			"CPU: vendor_id '%s' unknown, using generic init.\n" \
-			"CPU: Your system may be unstable.\n", v);
+	pr_err_once("CPU: vendor_id '%s' unknown, using generic init.\n" \
+		    "CPU: Your system may be unstable.\n", v);
 
 	c->x86_vendor = X86_VENDOR_UNKNOWN;
 	this_cpu = &default_cpu;
@@ -760,7 +774,7 @@ void __init early_cpu_init(void)
 	int count = 0;
 
 #ifdef CONFIG_PROCESSOR_SELECT
-	printk(KERN_INFO "KERNEL supported cpus:\n");
+	pr_info("KERNEL supported cpus:\n");
 #endif
 
 	for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) {
@@ -778,7 +792,7 @@ void __init early_cpu_init(void)
 			for (j = 0; j < 2; j++) {
 				if (!cpudev->c_ident[j])
 					continue;
-				printk(KERN_INFO "  %s %s\n", cpudev->c_vendor,
+				pr_info("  %s %s\n", cpudev->c_vendor,
 					cpudev->c_ident[j]);
 			}
 		}
@@ -803,6 +817,31 @@ static void detect_nopl(struct cpuinfo_x86 *c)
 #else
 	set_cpu_cap(c, X86_FEATURE_NOPL);
 #endif
+
+	/*
+	 * ESPFIX is a strange bug.  All real CPUs have it.  Paravirt
+	 * systems that run Linux at CPL > 0 may or may not have the
+	 * issue, but, even if they have the issue, there's absolutely
+	 * nothing we can do about it because we can't use the real IRET
+	 * instruction.
+	 *
+	 * NB: For the time being, only 32-bit kernels support
+	 * X86_BUG_ESPFIX as such.  64-bit kernels directly choose
+	 * whether to apply espfix using paravirt hooks.  If any
+	 * non-paravirt system ever shows up that does *not* have the
+	 * ESPFIX issue, we can change this.
+	 */
+#ifdef CONFIG_X86_32
+#ifdef CONFIG_PARAVIRT
+	do {
+		extern void native_iret(void);
+		if (pv_cpu_ops.iret == native_iret)
+			set_cpu_bug(c, X86_BUG_ESPFIX);
+	} while (0);
+#else
+	set_cpu_bug(c, X86_BUG_ESPFIX);
+#endif
+#endif
 }
 
 static void generic_identify(struct cpuinfo_x86 *c)
@@ -977,6 +1016,8 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 #ifdef CONFIG_NUMA
 	numa_add_cpu(smp_processor_id());
 #endif
+	/* The boot/hotplug time assigment got cleared, restore it */
+	c->logical_proc_id = topology_phys_to_logical_pkg(c->phys_proc_id);
 }
 
 /*
@@ -1061,7 +1102,7 @@ static void __print_cpu_msr(void)
 		for (index = index_min; index < index_max; index++) {
 			if (rdmsrl_safe(index, &val))
 				continue;
-			printk(KERN_INFO " MSR%08x: %016llx\n", index, val);
+			pr_info(" MSR%08x: %016llx\n", index, val);
 		}
 	}
 }
@@ -1100,19 +1141,19 @@ void print_cpu_info(struct cpuinfo_x86 *c)
 	}
 
 	if (vendor && !strstr(c->x86_model_id, vendor))
-		printk(KERN_CONT "%s ", vendor);
+		pr_cont("%s ", vendor);
 
 	if (c->x86_model_id[0])
-		printk(KERN_CONT "%s", c->x86_model_id);
+		pr_cont("%s", c->x86_model_id);
 	else
-		printk(KERN_CONT "%d86", c->x86);
+		pr_cont("%d86", c->x86);
 
-	printk(KERN_CONT " (family: 0x%x, model: 0x%x", c->x86, c->x86_model);
+	pr_cont(" (family: 0x%x, model: 0x%x", c->x86, c->x86_model);
 
 	if (c->x86_mask || c->cpuid_level >= 0)
-		printk(KERN_CONT ", stepping: 0x%x)\n", c->x86_mask);
+		pr_cont(", stepping: 0x%x)\n", c->x86_mask);
 	else
-		printk(KERN_CONT ")\n");
+		pr_cont(")\n");
 
 	print_cpu_msr(c);
 }
@@ -1438,7 +1479,7 @@ void cpu_init(void)
 
 	show_ucode_info_early();
 
-	printk(KERN_INFO "Initializing CPU#%d\n", cpu);
+	pr_info("Initializing CPU#%d\n", cpu);
 
 	if (cpu_feature_enabled(X86_FEATURE_VME) ||
 	    cpu_has_tsc ||
@@ -1475,20 +1516,6 @@ void cpu_init(void)
 }
 #endif
 
-#ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS
-void warn_pre_alternatives(void)
-{
-	WARN(1, "You're using static_cpu_has before alternatives have run!\n");
-}
-EXPORT_SYMBOL_GPL(warn_pre_alternatives);
-#endif
-
-inline bool __static_cpu_has_safe(u16 bit)
-{
-	return boot_cpu_has(bit);
-}
-EXPORT_SYMBOL_GPL(__static_cpu_has_safe);
-
 static void bsp_resume(void)
 {
 	if (this_cpu->c_bsp_resume)
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index aaf152e79637..6adef9cac23e 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -8,6 +8,7 @@
 #include <linux/timer.h>
 #include <asm/pci-direct.h>
 #include <asm/tsc.h>
+#include <asm/cpufeature.h>
 
 #include "cpu.h"
 
@@ -103,7 +104,7 @@ static void check_cx686_slop(struct cpuinfo_x86 *c)
 		local_irq_restore(flags);
 
 		if (ccr5 & 2) { /* possible wrong calibration done */
-			printk(KERN_INFO "Recalibrating delay loop with SLOP bit reset\n");
+			pr_info("Recalibrating delay loop with SLOP bit reset\n");
 			calibrate_delay();
 			c->loops_per_jiffy = loops_per_jiffy;
 		}
@@ -115,7 +116,7 @@ static void set_cx86_reorder(void)
 {
 	u8 ccr3;
 
-	printk(KERN_INFO "Enable Memory access reorder on Cyrix/NSC processor.\n");
+	pr_info("Enable Memory access reorder on Cyrix/NSC processor.\n");
 	ccr3 = getCx86(CX86_CCR3);
 	setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */
 
@@ -128,7 +129,7 @@ static void set_cx86_reorder(void)
 
 static void set_cx86_memwb(void)
 {
-	printk(KERN_INFO "Enable Memory-Write-back mode on Cyrix/NSC processor.\n");
+	pr_info("Enable Memory-Write-back mode on Cyrix/NSC processor.\n");
 
 	/* CCR2 bit 2: unlock NW bit */
 	setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) & ~0x04);
@@ -268,7 +269,7 @@ static void init_cyrix(struct cpuinfo_x86 *c)
 		 *  VSA1 we work around however.
 		 */
 
-		printk(KERN_INFO "Working around Cyrix MediaGX virtual DMA bugs.\n");
+		pr_info("Working around Cyrix MediaGX virtual DMA bugs.\n");
 		isa_dma_bridge_buggy = 2;
 
 		/* We do this before the PCI layer is running. However we
@@ -426,7 +427,7 @@ static void cyrix_identify(struct cpuinfo_x86 *c)
 		if (dir0 == 5 || dir0 == 3) {
 			unsigned char ccr3;
 			unsigned long flags;
-			printk(KERN_INFO "Enabling CPUID on Cyrix processor.\n");
+			pr_info("Enabling CPUID on Cyrix processor.\n");
 			local_irq_save(flags);
 			ccr3 = getCx86(CX86_CCR3);
 			/* enable MAPEN  */
diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c
index d820d8eae96b..73d391ae452f 100644
--- a/arch/x86/kernel/cpu/hypervisor.c
+++ b/arch/x86/kernel/cpu/hypervisor.c
@@ -56,7 +56,7 @@ detect_hypervisor_vendor(void)
 	}
 
 	if (max_pri)
-		printk(KERN_INFO "Hypervisor detected: %s\n", x86_hyper->name);
+		pr_info("Hypervisor detected: %s\n", x86_hyper->name);
 }
 
 void init_hypervisor(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 565648bc1a0a..1f7fdb91a818 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -8,7 +8,7 @@
 #include <linux/module.h>
 #include <linux/uaccess.h>
 
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/pgtable.h>
 #include <asm/msr.h>
 #include <asm/bugs.h>
@@ -61,7 +61,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	 */
 	if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2 &&
 	    c->microcode < 0x20e) {
-		printk(KERN_WARNING "Atom PSE erratum detected, BIOS microcode update recommended\n");
+		pr_warn("Atom PSE erratum detected, BIOS microcode update recommended\n");
 		clear_cpu_cap(c, X86_FEATURE_PSE);
 	}
 
@@ -140,7 +140,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
 		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
 		if (!(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING)) {
-			printk(KERN_INFO "Disabled fast string operations\n");
+			pr_info("Disabled fast string operations\n");
 			setup_clear_cpu_cap(X86_FEATURE_REP_GOOD);
 			setup_clear_cpu_cap(X86_FEATURE_ERMS);
 		}
@@ -160,6 +160,19 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		pr_info("Disabling PGE capability bit\n");
 		setup_clear_cpu_cap(X86_FEATURE_PGE);
 	}
+
+	if (c->cpuid_level >= 0x00000001) {
+		u32 eax, ebx, ecx, edx;
+
+		cpuid(0x00000001, &eax, &ebx, &ecx, &edx);
+		/*
+		 * If HTT (EDX[28]) is set EBX[16:23] contain the number of
+		 * apicids which are reserved per package. Store the resulting
+		 * shift value for the package management code.
+		 */
+		if (edx & (1U << 28))
+			c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff);
+	}
 }
 
 #ifdef CONFIG_X86_32
@@ -176,7 +189,7 @@ int ppro_with_ram_bug(void)
 	    boot_cpu_data.x86 == 6 &&
 	    boot_cpu_data.x86_model == 1 &&
 	    boot_cpu_data.x86_mask < 8) {
-		printk(KERN_INFO "Pentium Pro with Errata#50 detected. Taking evasive action.\n");
+		pr_info("Pentium Pro with Errata#50 detected. Taking evasive action.\n");
 		return 1;
 	}
 	return 0;
@@ -225,7 +238,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 
 		set_cpu_bug(c, X86_BUG_F00F);
 		if (!f00f_workaround_enabled) {
-			printk(KERN_NOTICE "Intel Pentium with F0 0F bug - workaround enabled.\n");
+			pr_notice("Intel Pentium with F0 0F bug - workaround enabled.\n");
 			f00f_workaround_enabled = 1;
 		}
 	}
@@ -244,7 +257,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 	 * Forcefully enable PAE if kernel parameter "forcepae" is present.
 	 */
 	if (forcepae) {
-		printk(KERN_WARNING "PAE forced!\n");
+		pr_warn("PAE forced!\n");
 		set_cpu_cap(c, X86_FEATURE_PAE);
 		add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE);
 	}
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 0b6c52388cf4..de6626c18e42 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -14,7 +14,7 @@
 #include <linux/sysfs.h>
 #include <linux/pci.h>
 
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/amd_nb.h>
 #include <asm/smp.h>
 
@@ -444,7 +444,7 @@ static ssize_t store_cache_disable(struct cacheinfo *this_leaf,
 	err = amd_set_l3_disable_slot(nb, cpu, slot, val);
 	if (err) {
 		if (err == -EEXIST)
-			pr_warning("L3 slot %d in use/index already disabled!\n",
+			pr_warn("L3 slot %d in use/index already disabled!\n",
 				   slot);
 		return err;
 	}
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index afa9f0d487ea..fbb5e90557a5 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -1,5 +1,5 @@
 #include <asm/cpu_device_id.h>
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <linux/cpu.h>
 #include <linux/module.h>
 #include <linux/slab.h>
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 4cfba4371a71..517619ea6498 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -115,7 +115,7 @@ static int raise_local(void)
 	int cpu = m->extcpu;
 
 	if (m->inject_flags & MCJ_EXCEPTION) {
-		printk(KERN_INFO "Triggering MCE exception on CPU %d\n", cpu);
+		pr_info("Triggering MCE exception on CPU %d\n", cpu);
 		switch (context) {
 		case MCJ_CTX_IRQ:
 			/*
@@ -128,15 +128,15 @@ static int raise_local(void)
 			raise_exception(m, NULL);
 			break;
 		default:
-			printk(KERN_INFO "Invalid MCE context\n");
+			pr_info("Invalid MCE context\n");
 			ret = -EINVAL;
 		}
-		printk(KERN_INFO "MCE exception done on CPU %d\n", cpu);
+		pr_info("MCE exception done on CPU %d\n", cpu);
 	} else if (m->status) {
-		printk(KERN_INFO "Starting machine check poll CPU %d\n", cpu);
+		pr_info("Starting machine check poll CPU %d\n", cpu);
 		raise_poll(m);
 		mce_notify_irq();
-		printk(KERN_INFO "Machine check poll done on CPU %d\n", cpu);
+		pr_info("Machine check poll done on CPU %d\n", cpu);
 	} else
 		m->finished = 0;
 
@@ -183,8 +183,7 @@ static void raise_mce(struct mce *m)
 		start = jiffies;
 		while (!cpumask_empty(mce_inject_cpumask)) {
 			if (!time_before(jiffies, start + 2*HZ)) {
-				printk(KERN_ERR
-				"Timeout waiting for mce inject %lx\n",
+				pr_err("Timeout waiting for mce inject %lx\n",
 					*cpumask_bits(mce_inject_cpumask));
 				break;
 			}
@@ -241,7 +240,7 @@ static int inject_init(void)
 {
 	if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL))
 		return -ENOMEM;
-	printk(KERN_INFO "Machine check injector initialized\n");
+	pr_info("Machine check injector initialized\n");
 	register_mce_write_callback(mce_write);
 	register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0,
 				"mce_notify");
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index 9c682c222071..5119766d9889 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/debugfs.h>
 #include <asm/mce.h>
+#include <asm/uaccess.h>
 
 #include "mce-internal.h"
 
@@ -29,7 +30,7 @@
  * panic situations)
  */
 
-enum context { IN_KERNEL = 1, IN_USER = 2 };
+enum context { IN_KERNEL = 1, IN_USER = 2, IN_KERNEL_RECOV = 3 };
 enum ser { SER_REQUIRED = 1, NO_SER = 2 };
 enum exception { EXCP_CONTEXT = 1, NO_EXCP = 2 };
 
@@ -48,6 +49,7 @@ static struct severity {
 #define MCESEV(s, m, c...) { .sev = MCE_ ## s ## _SEVERITY, .msg = m, ## c }
 #define  KERNEL		.context = IN_KERNEL
 #define  USER		.context = IN_USER
+#define  KERNEL_RECOV	.context = IN_KERNEL_RECOV
 #define  SER		.ser = SER_REQUIRED
 #define  NOSER		.ser = NO_SER
 #define  EXCP		.excp = EXCP_CONTEXT
@@ -87,6 +89,10 @@ static struct severity {
 		EXCP, KERNEL, MCGMASK(MCG_STATUS_RIPV, 0)
 		),
 	MCESEV(
+		PANIC, "In kernel and no restart IP",
+		EXCP, KERNEL_RECOV, MCGMASK(MCG_STATUS_RIPV, 0)
+		),
+	MCESEV(
 		DEFERRED, "Deferred error",
 		NOSER, MASK(MCI_STATUS_UC|MCI_STATUS_DEFERRED|MCI_STATUS_POISON, MCI_STATUS_DEFERRED)
 		),
@@ -123,6 +129,11 @@ static struct severity {
 		MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, MCG_STATUS_RIPV)
 		),
 	MCESEV(
+		AR, "Action required: data load in error recoverable area of kernel",
+		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
+		KERNEL_RECOV
+		),
+	MCESEV(
 		AR, "Action required: data load error in a user process",
 		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
 		USER
@@ -170,6 +181,9 @@ static struct severity {
 		)	/* always matches. keep at end */
 };
 
+#define mc_recoverable(mcg) (((mcg) & (MCG_STATUS_RIPV|MCG_STATUS_EIPV)) == \
+				(MCG_STATUS_RIPV|MCG_STATUS_EIPV))
+
 /*
  * If mcgstatus indicated that ip/cs on the stack were
  * no good, then "m->cs" will be zero and we will have
@@ -183,7 +197,11 @@ static struct severity {
  */
 static int error_context(struct mce *m)
 {
-	return ((m->cs & 3) == 3) ? IN_USER : IN_KERNEL;
+	if ((m->cs & 3) == 3)
+		return IN_USER;
+	if (mc_recoverable(m->mcgstatus) && ex_has_fault_handler(m->ip))
+		return IN_KERNEL_RECOV;
+	return IN_KERNEL;
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index a006f4cd792b..f0c921b03e42 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -961,6 +961,20 @@ static void mce_clear_state(unsigned long *toclear)
 	}
 }
 
+static int do_memory_failure(struct mce *m)
+{
+	int flags = MF_ACTION_REQUIRED;
+	int ret;
+
+	pr_err("Uncorrected hardware memory error in user-access at %llx", m->addr);
+	if (!(m->mcgstatus & MCG_STATUS_RIPV))
+		flags |= MF_MUST_KILL;
+	ret = memory_failure(m->addr >> PAGE_SHIFT, MCE_VECTOR, flags);
+	if (ret)
+		pr_err("Memory error not recovered");
+	return ret;
+}
+
 /*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.
@@ -998,8 +1012,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
 	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
 	char *msg = "Unknown";
-	u64 recover_paddr = ~0ull;
-	int flags = MF_ACTION_REQUIRED;
 	int lmce = 0;
 
 	/* If this CPU is offline, just bail out. */
@@ -1136,22 +1148,13 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	}
 
 	/*
-	 * At insane "tolerant" levels we take no action. Otherwise
-	 * we only die if we have no other choice. For less serious
-	 * issues we try to recover, or limit damage to the current
-	 * process.
+	 * If tolerant is at an insane level we drop requests to kill
+	 * processes and continue even when there is no way out.
 	 */
-	if (cfg->tolerant < 3) {
-		if (no_way_out)
-			mce_panic("Fatal machine check on current CPU", &m, msg);
-		if (worst == MCE_AR_SEVERITY) {
-			recover_paddr = m.addr;
-			if (!(m.mcgstatus & MCG_STATUS_RIPV))
-				flags |= MF_MUST_KILL;
-		} else if (kill_it) {
-			force_sig(SIGBUS, current);
-		}
-	}
+	if (cfg->tolerant == 3)
+		kill_it = 0;
+	else if (no_way_out)
+		mce_panic("Fatal machine check on current CPU", &m, msg);
 
 	if (worst > 0)
 		mce_report_event(regs);
@@ -1159,25 +1162,24 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 out:
 	sync_core();
 
-	if (recover_paddr == ~0ull)
-		goto done;
+	if (worst != MCE_AR_SEVERITY && !kill_it)
+		goto out_ist;
 
-	pr_err("Uncorrected hardware memory error in user-access at %llx",
-		 recover_paddr);
-	/*
-	 * We must call memory_failure() here even if the current process is
-	 * doomed. We still need to mark the page as poisoned and alert any
-	 * other users of the page.
-	 */
-	ist_begin_non_atomic(regs);
-	local_irq_enable();
-	if (memory_failure(recover_paddr >> PAGE_SHIFT, MCE_VECTOR, flags) < 0) {
-		pr_err("Memory error not recovered");
-		force_sig(SIGBUS, current);
+	/* Fault was in user mode and we need to take some action */
+	if ((m.cs & 3) == 3) {
+		ist_begin_non_atomic(regs);
+		local_irq_enable();
+
+		if (kill_it || do_memory_failure(&m))
+			force_sig(SIGBUS, current);
+		local_irq_disable();
+		ist_end_non_atomic();
+	} else {
+		if (!fixup_exception(regs, X86_TRAP_MC))
+			mce_panic("Failed kernel mode recovery", &m, NULL);
 	}
-	local_irq_disable();
-	ist_end_non_atomic();
-done:
+
+out_ist:
 	ist_exit(regs);
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
@@ -1576,6 +1578,17 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 
 		if (c->x86 == 6 && c->x86_model == 45)
 			quirk_no_way_out = quirk_sandybridge_ifu;
+		/*
+		 * MCG_CAP.MCG_SER_P is necessary but not sufficient to know
+		 * whether this processor will actually generate recoverable
+		 * machine checks. Check to see if this is an E7 model Xeon.
+		 * We can't do a model number check because E5 and E7 use the
+		 * same model number. E5 doesn't support recovery, E7 does.
+		 */
+		if (mca_cfg.recovery || (mca_cfg.ser &&
+			!strncmp(c->x86_model_id,
+				 "Intel(R) Xeon(R) CPU E7-", 24)))
+			set_cpu_cap(c, X86_FEATURE_MCE_RECOVERY);
 	}
 	if (cfg->monarch_timeout < 0)
 		cfg->monarch_timeout = 0;
@@ -1617,10 +1630,10 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 	case X86_VENDOR_AMD: {
 		u32 ebx = cpuid_ebx(0x80000007);
 
-		mce_amd_feature_init(c);
 		mce_flags.overflow_recov = !!(ebx & BIT(0));
 		mce_flags.succor	 = !!(ebx & BIT(1));
 		mce_flags.smca		 = !!(ebx & BIT(3));
+		mce_amd_feature_init(c);
 
 		break;
 		}
@@ -2028,6 +2041,8 @@ static int __init mcheck_enable(char *str)
 		cfg->bootlog = (str[0] == 'b');
 	else if (!strcmp(str, "bios_cmci_threshold"))
 		cfg->bios_cmci_threshold = true;
+	else if (!strcmp(str, "recovery"))
+		cfg->recovery = true;
 	else if (isdigit(str[0])) {
 		if (get_option(&str, &cfg->tolerant) == 2)
 			get_option(&str, &(cfg->monarch_timeout));
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index e99b15077e94..9d656fd436ef 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -1,5 +1,5 @@
 /*
- *  (c) 2005-2015 Advanced Micro Devices, Inc.
+ *  (c) 2005-2016 Advanced Micro Devices, Inc.
  *  Your use of this code is subject to the terms and conditions of the
  *  GNU general public license version 2. See "COPYING" or
  *  http://www.gnu.org/licenses/gpl.html
@@ -28,7 +28,7 @@
 #include <asm/msr.h>
 #include <asm/trace/irq_vectors.h>
 
-#define NR_BLOCKS         9
+#define NR_BLOCKS         5
 #define THRESHOLD_MAX     0xFFF
 #define INT_TYPE_APIC     0x00020000
 #define MASK_VALID_HI     0x80000000
@@ -49,6 +49,19 @@
 #define DEF_LVT_OFF		0x2
 #define DEF_INT_TYPE_APIC	0x2
 
+/* Scalable MCA: */
+
+/* Threshold LVT offset is at MSR0xC0000410[15:12] */
+#define SMCA_THR_LVT_OFF	0xF000
+
+/*
+ * OS is required to set the MCAX bit to acknowledge that it is now using the
+ * new MSR ranges and new registers under each bank. It also means that the OS
+ * will configure deferred errors in the new MCx_CONFIG register. If the bit is
+ * not set, uncorrectable errors will cause a system panic.
+ */
+#define SMCA_MCAX_EN_OFF	0x1
+
 static const char * const th_names[] = {
 	"load_store",
 	"insn_fetch",
@@ -58,6 +71,35 @@ static const char * const th_names[] = {
 	"execution_unit",
 };
 
+/* Define HWID to IP type mappings for Scalable MCA */
+struct amd_hwid amd_hwids[] = {
+	[SMCA_F17H_CORE]	= { "f17h_core",	0xB0 },
+	[SMCA_DF]		= { "data_fabric",	0x2E },
+	[SMCA_UMC]		= { "umc",		0x96 },
+	[SMCA_PB]		= { "param_block",	0x5 },
+	[SMCA_PSP]		= { "psp",		0xFF },
+	[SMCA_SMU]		= { "smu",		0x1 },
+};
+EXPORT_SYMBOL_GPL(amd_hwids);
+
+const char * const amd_core_mcablock_names[] = {
+	[SMCA_LS]		= "load_store",
+	[SMCA_IF]		= "insn_fetch",
+	[SMCA_L2_CACHE]		= "l2_cache",
+	[SMCA_DE]		= "decode_unit",
+	[RES]			= "",
+	[SMCA_EX]		= "execution_unit",
+	[SMCA_FP]		= "floating_point",
+	[SMCA_L3_CACHE]		= "l3_cache",
+};
+EXPORT_SYMBOL_GPL(amd_core_mcablock_names);
+
+const char * const amd_df_mcablock_names[] = {
+	[SMCA_CS]		= "coherent_slave",
+	[SMCA_PIE]		= "pie",
+};
+EXPORT_SYMBOL_GPL(amd_df_mcablock_names);
+
 static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks);
 static DEFINE_PER_CPU(unsigned char, bank_map);	/* see which banks are on */
 
@@ -84,6 +126,13 @@ struct thresh_restart {
 
 static inline bool is_shared_bank(int bank)
 {
+	/*
+	 * Scalable MCA provides for only one core to have access to the MSRs of
+	 * a shared bank.
+	 */
+	if (mce_flags.smca)
+		return false;
+
 	/* Bank 4 is for northbridge reporting and is thus shared */
 	return (bank == 4);
 }
@@ -135,6 +184,14 @@ static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi)
 	}
 
 	if (apic != msr) {
+		/*
+		 * On SMCA CPUs, LVT offset is programmed at a different MSR, and
+		 * the BIOS provides the value. The original field where LVT offset
+		 * was set is reserved. Return early here:
+		 */
+		if (mce_flags.smca)
+			return 0;
+
 		pr_err(FW_BUG "cpu %d, invalid threshold interrupt offset %d "
 		       "for bank %d, block %d (MSR%08X=0x%x%08x)\n",
 		       b->cpu, apic, b->bank, b->block, b->address, hi, lo);
@@ -144,10 +201,7 @@ static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi)
 	return 1;
 };
 
-/*
- * Called via smp_call_function_single(), must be called with correct
- * cpu affinity.
- */
+/* Reprogram MCx_MISC MSR behind this threshold bank. */
 static void threshold_restart_bank(void *_tr)
 {
 	struct thresh_restart *tr = _tr;
@@ -247,27 +301,116 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
 	wrmsr(MSR_CU_DEF_ERR, low, high);
 }
 
+static u32 get_block_address(u32 current_addr, u32 low, u32 high,
+			     unsigned int bank, unsigned int block)
+{
+	u32 addr = 0, offset = 0;
+
+	if (mce_flags.smca) {
+		if (!block) {
+			addr = MSR_AMD64_SMCA_MCx_MISC(bank);
+		} else {
+			/*
+			 * For SMCA enabled processors, BLKPTR field of the
+			 * first MISC register (MCx_MISC0) indicates presence of
+			 * additional MISC register set (MISC1-4).
+			 */
+			u32 low, high;
+
+			if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
+				return addr;
+
+			if (!(low & MCI_CONFIG_MCAX))
+				return addr;
+
+			if (!rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
+			    (low & MASK_BLKPTR_LO))
+				addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
+		}
+		return addr;
+	}
+
+	/* Fall back to method we used for older processors: */
+	switch (block) {
+	case 0:
+		addr = MSR_IA32_MCx_MISC(bank);
+		break;
+	case 1:
+		offset = ((low & MASK_BLKPTR_LO) >> 21);
+		if (offset)
+			addr = MCG_XBLK_ADDR + offset;
+		break;
+	default:
+		addr = ++current_addr;
+	}
+	return addr;
+}
+
+static int
+prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
+			int offset, u32 misc_high)
+{
+	unsigned int cpu = smp_processor_id();
+	struct threshold_block b;
+	int new;
+
+	if (!block)
+		per_cpu(bank_map, cpu) |= (1 << bank);
+
+	memset(&b, 0, sizeof(b));
+	b.cpu			= cpu;
+	b.bank			= bank;
+	b.block			= block;
+	b.address		= addr;
+	b.interrupt_capable	= lvt_interrupt_supported(bank, misc_high);
+
+	if (!b.interrupt_capable)
+		goto done;
+
+	b.interrupt_enable = 1;
+
+	if (mce_flags.smca) {
+		u32 smca_low, smca_high;
+		u32 smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank);
+
+		if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) {
+			smca_high |= SMCA_MCAX_EN_OFF;
+			wrmsr(smca_addr, smca_low, smca_high);
+		}
+
+		/* Gather LVT offset for thresholding: */
+		if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high))
+			goto out;
+
+		new = (smca_low & SMCA_THR_LVT_OFF) >> 12;
+	} else {
+		new = (misc_high & MASK_LVTOFF_HI) >> 20;
+	}
+
+	offset = setup_APIC_mce_threshold(offset, new);
+
+	if ((offset == new) && (mce_threshold_vector != amd_threshold_interrupt))
+		mce_threshold_vector = amd_threshold_interrupt;
+
+done:
+	mce_threshold_block_init(&b, offset);
+
+out:
+	return offset;
+}
+
 /* cpu init entry point, called from mce.c with preempt off */
 void mce_amd_feature_init(struct cpuinfo_x86 *c)
 {
-	struct threshold_block b;
-	unsigned int cpu = smp_processor_id();
 	u32 low = 0, high = 0, address = 0;
 	unsigned int bank, block;
-	int offset = -1, new;
+	int offset = -1;
 
 	for (bank = 0; bank < mca_cfg.banks; ++bank) {
 		for (block = 0; block < NR_BLOCKS; ++block) {
-			if (block == 0)
-				address = MSR_IA32_MCx_MISC(bank);
-			else if (block == 1) {
-				address = (low & MASK_BLKPTR_LO) >> 21;
-				if (!address)
-					break;
-
-				address += MCG_XBLK_ADDR;
-			} else
-				++address;
+			address = get_block_address(address, low, high, bank, block);
+			if (!address)
+				break;
 
 			if (rdmsr_safe(address, &low, &high))
 				break;
@@ -279,29 +422,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 			     (high & MASK_LOCKED_HI))
 				continue;
 
-			if (!block)
-				per_cpu(bank_map, cpu) |= (1 << bank);
-
-			memset(&b, 0, sizeof(b));
-			b.cpu			= cpu;
-			b.bank			= bank;
-			b.block			= block;
-			b.address		= address;
-			b.interrupt_capable	= lvt_interrupt_supported(bank, high);
-
-			if (!b.interrupt_capable)
-				goto init;
-
-			b.interrupt_enable = 1;
-			new	= (high & MASK_LVTOFF_HI) >> 20;
-			offset  = setup_APIC_mce_threshold(offset, new);
-
-			if ((offset == new) &&
-			    (mce_threshold_vector != amd_threshold_interrupt))
-				mce_threshold_vector = amd_threshold_interrupt;
-
-init:
-			mce_threshold_block_init(&b, offset);
+			offset = prepare_threshold_block(bank, block, address, offset, high);
 		}
 	}
 
@@ -394,16 +515,9 @@ static void amd_threshold_interrupt(void)
 		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
 			continue;
 		for (block = 0; block < NR_BLOCKS; ++block) {
-			if (block == 0) {
-				address = MSR_IA32_MCx_MISC(bank);
-			} else if (block == 1) {
-				address = (low & MASK_BLKPTR_LO) >> 21;
-				if (!address)
-					break;
-				address += MCG_XBLK_ADDR;
-			} else {
-				++address;
-			}
+			address = get_block_address(address, low, high, bank, block);
+			if (!address)
+				break;
 
 			if (rdmsr_safe(address, &low, &high))
 				break;
@@ -623,16 +737,11 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
 	if (err)
 		goto out_free;
 recurse:
-	if (!block) {
-		address = (low & MASK_BLKPTR_LO) >> 21;
-		if (!address)
-			return 0;
-		address += MCG_XBLK_ADDR;
-	} else {
-		++address;
-	}
+	address = get_block_address(address, low, high, bank, ++block);
+	if (!address)
+		return 0;
 
-	err = allocate_threshold_blocks(cpu, bank, ++block, address);
+	err = allocate_threshold_blocks(cpu, bank, block, address);
 	if (err)
 		goto out_free;
 
diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c
index 12402e10aeff..2a0717bf8033 100644
--- a/arch/x86/kernel/cpu/mcheck/p5.c
+++ b/arch/x86/kernel/cpu/mcheck/p5.c
@@ -26,14 +26,12 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code)
 	rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi);
 	rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi);
 
-	printk(KERN_EMERG
-		"CPU#%d: Machine Check Exception:  0x%8X (type 0x%8X).\n",
-		smp_processor_id(), loaddr, lotype);
+	pr_emerg("CPU#%d: Machine Check Exception:  0x%8X (type 0x%8X).\n",
+		 smp_processor_id(), loaddr, lotype);
 
 	if (lotype & (1<<5)) {
-		printk(KERN_EMERG
-			"CPU#%d: Possible thermal failure (CPU on fire ?).\n",
-			smp_processor_id());
+		pr_emerg("CPU#%d: Possible thermal failure (CPU on fire ?).\n",
+			 smp_processor_id());
 	}
 
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
@@ -61,12 +59,10 @@ void intel_p5_mcheck_init(struct cpuinfo_x86 *c)
 	/* Read registers before enabling: */
 	rdmsr(MSR_IA32_P5_MC_ADDR, l, h);
 	rdmsr(MSR_IA32_P5_MC_TYPE, l, h);
-	printk(KERN_INFO
-	       "Intel old style machine check architecture supported.\n");
+	pr_info("Intel old style machine check architecture supported.\n");
 
 	/* Enable MCE: */
 	cr4_set_bits(X86_CR4_MCE);
-	printk(KERN_INFO
-	       "Intel old style machine check reporting enabled on CPU#%d.\n",
-	       smp_processor_id());
+	pr_info("Intel old style machine check reporting enabled on CPU#%d.\n",
+		smp_processor_id());
 }
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 2c5aaf8c2e2f..0b445c2ff735 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -190,7 +190,7 @@ static int therm_throt_process(bool new_event, int event, int level)
 	/* if we just entered the thermal event */
 	if (new_event) {
 		if (event == THERMAL_THROTTLING_EVENT)
-			printk(KERN_CRIT "CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n",
+			pr_crit("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n",
 				this_cpu,
 				level == CORE_LEVEL ? "Core" : "Package",
 				state->count);
@@ -198,8 +198,7 @@ static int therm_throt_process(bool new_event, int event, int level)
 	}
 	if (old_event) {
 		if (event == THERMAL_THROTTLING_EVENT)
-			printk(KERN_INFO "CPU%d: %s temperature/speed normal\n",
-				this_cpu,
+			pr_info("CPU%d: %s temperature/speed normal\n", this_cpu,
 				level == CORE_LEVEL ? "Core" : "Package");
 		return 1;
 	}
@@ -417,8 +416,8 @@ static void intel_thermal_interrupt(void)
 
 static void unexpected_thermal_interrupt(void)
 {
-	printk(KERN_ERR "CPU%d: Unexpected LVT thermal interrupt!\n",
-			smp_processor_id());
+	pr_err("CPU%d: Unexpected LVT thermal interrupt!\n",
+		smp_processor_id());
 }
 
 static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt;
@@ -499,7 +498,7 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
 
 	if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
 		if (system_state == SYSTEM_BOOTING)
-			printk(KERN_DEBUG "CPU%d: Thermal monitoring handled by SMI\n", cpu);
+			pr_debug("CPU%d: Thermal monitoring handled by SMI\n", cpu);
 		return;
 	}
 
@@ -557,8 +556,8 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
 	l = apic_read(APIC_LVTTHMR);
 	apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
 
-	printk_once(KERN_INFO "CPU0: Thermal monitoring enabled (%s)\n",
-		       tm2 ? "TM2" : "TM1");
+	pr_info_once("CPU0: Thermal monitoring enabled (%s)\n",
+		      tm2 ? "TM2" : "TM1");
 
 	/* enable thermal throttle processing */
 	atomic_set(&therm_throt_en, 1);
diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c
index 7245980186ee..fcf9ae9384f4 100644
--- a/arch/x86/kernel/cpu/mcheck/threshold.c
+++ b/arch/x86/kernel/cpu/mcheck/threshold.c
@@ -12,8 +12,8 @@
 
 static void default_threshold_interrupt(void)
 {
-	printk(KERN_ERR "Unexpected threshold interrupt at vector %x\n",
-			 THRESHOLD_APIC_VECTOR);
+	pr_err("Unexpected threshold interrupt at vector %x\n",
+		THRESHOLD_APIC_VECTOR);
 }
 
 void (*mce_threshold_vector)(void) = default_threshold_interrupt;
diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c
index 01dd8702880b..c6a722e1d011 100644
--- a/arch/x86/kernel/cpu/mcheck/winchip.c
+++ b/arch/x86/kernel/cpu/mcheck/winchip.c
@@ -17,7 +17,7 @@ static void winchip_machine_check(struct pt_regs *regs, long error_code)
 {
 	ist_enter(regs);
 
-	printk(KERN_EMERG "CPU0: Machine Check Exception.\n");
+	pr_emerg("CPU0: Machine Check Exception.\n");
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
 
 	ist_exit(regs);
@@ -39,6 +39,5 @@ void winchip_mcheck_init(struct cpuinfo_x86 *c)
 
 	cr4_set_bits(X86_CR4_MCE);
 
-	printk(KERN_INFO
-	       "Winchip machine check reporting enabled on CPU#0.\n");
+	pr_info("Winchip machine check reporting enabled on CPU#0.\n");
 }
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 2233f8a76615..8581963894c7 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -431,10 +431,6 @@ int __init save_microcode_in_initrd_amd(void)
 	else
 		container = cont_va;
 
-	if (ucode_new_rev)
-		pr_info("microcode: updated early to new patch_level=0x%08x\n",
-			ucode_new_rev);
-
 	eax   = cpuid_eax(0x00000001);
 	eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
 
@@ -469,8 +465,7 @@ void reload_ucode_amd(void)
 	if (mc && rev < mc->hdr.patch_id) {
 		if (!__apply_microcode_amd(mc)) {
 			ucode_new_rev = mc->hdr.patch_id;
-			pr_info("microcode: reload patch_level=0x%08x\n",
-				ucode_new_rev);
+			pr_info("reload patch_level=0x%08x\n", ucode_new_rev);
 		}
 	}
 }
@@ -793,15 +788,13 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover)
 		return -EINVAL;
 	}
 
-	patch->data = kzalloc(patch_size, GFP_KERNEL);
+	patch->data = kmemdup(fw + SECTION_HDR_SIZE, patch_size, GFP_KERNEL);
 	if (!patch->data) {
 		pr_err("Patch data allocation failure.\n");
 		kfree(patch);
 		return -EINVAL;
 	}
 
-	/* All looks ok, copy patch... */
-	memcpy(patch->data, fw + SECTION_HDR_SIZE, patch_size);
 	INIT_LIST_HEAD(&patch->plist);
 	patch->patch_id  = mc_hdr->patch_id;
 	patch->equiv_cpu = proc_id;
@@ -953,10 +946,14 @@ struct microcode_ops * __init init_amd_microcode(void)
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
 	if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) {
-		pr_warning("AMD CPU family 0x%x not supported\n", c->x86);
+		pr_warn("AMD CPU family 0x%x not supported\n", c->x86);
 		return NULL;
 	}
 
+	if (ucode_new_rev)
+		pr_info_once("microcode updated early to new patch_level=0x%08x\n",
+			     ucode_new_rev);
+
 	return &microcode_amd_ops;
 }
 
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index faec7120c508..ac360bfbbdb6 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -43,16 +43,8 @@
 #define MICROCODE_VERSION	"2.01"
 
 static struct microcode_ops	*microcode_ops;
-
 static bool dis_ucode_ldr;
 
-static int __init disable_loader(char *str)
-{
-	dis_ucode_ldr = true;
-	return 1;
-}
-__setup("dis_ucode_ldr", disable_loader);
-
 /*
  * Synchronization.
  *
@@ -81,15 +73,16 @@ struct cpu_info_ctx {
 
 static bool __init check_loader_disabled_bsp(void)
 {
+	static const char *__dis_opt_str = "dis_ucode_ldr";
+
 #ifdef CONFIG_X86_32
 	const char *cmdline = (const char *)__pa_nodebug(boot_command_line);
-	const char *opt	    = "dis_ucode_ldr";
-	const char *option  = (const char *)__pa_nodebug(opt);
+	const char *option  = (const char *)__pa_nodebug(__dis_opt_str);
 	bool *res = (bool *)__pa_nodebug(&dis_ucode_ldr);
 
 #else /* CONFIG_X86_64 */
 	const char *cmdline = boot_command_line;
-	const char *option  = "dis_ucode_ldr";
+	const char *option  = __dis_opt_str;
 	bool *res = &dis_ucode_ldr;
 #endif
 
@@ -479,7 +472,7 @@ static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw)
 	enum ucode_state ustate;
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 
-	if (uci && uci->valid)
+	if (uci->valid)
 		return UCODE_OK;
 
 	if (collect_cpu_info(cpu))
@@ -630,7 +623,7 @@ int __init microcode_init(void)
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 	int error;
 
-	if (paravirt_enabled() || dis_ucode_ldr)
+	if (dis_ucode_ldr)
 		return -EINVAL;
 
 	if (c->x86_vendor == X86_VENDOR_INTEL)
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index ee81c544ee0d..cbb3cf09b065 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -39,9 +39,15 @@
 #include <asm/setup.h>
 #include <asm/msr.h>
 
-static unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT];
+/*
+ * Temporary microcode blobs pointers storage. We note here the pointers to
+ * microcode blobs we've got from whatever storage (detached initrd, builtin).
+ * Later on, we put those into final storage mc_saved_data.mc_saved.
+ */
+static unsigned long mc_tmp_ptrs[MAX_UCODE_COUNT];
+
 static struct mc_saved_data {
-	unsigned int mc_saved_count;
+	unsigned int num_saved;
 	struct microcode_intel **mc_saved;
 } mc_saved_data;
 
@@ -78,53 +84,50 @@ load_microcode_early(struct microcode_intel **saved,
 }
 
 static inline void
-copy_initrd_ptrs(struct microcode_intel **mc_saved, unsigned long *initrd,
-		  unsigned long off, int num_saved)
+copy_ptrs(struct microcode_intel **mc_saved, unsigned long *mc_ptrs,
+	  unsigned long off, int num_saved)
 {
 	int i;
 
 	for (i = 0; i < num_saved; i++)
-		mc_saved[i] = (struct microcode_intel *)(initrd[i] + off);
+		mc_saved[i] = (struct microcode_intel *)(mc_ptrs[i] + off);
 }
 
 #ifdef CONFIG_X86_32
 static void
-microcode_phys(struct microcode_intel **mc_saved_tmp,
-	       struct mc_saved_data *mc_saved_data)
+microcode_phys(struct microcode_intel **mc_saved_tmp, struct mc_saved_data *mcs)
 {
 	int i;
 	struct microcode_intel ***mc_saved;
 
-	mc_saved = (struct microcode_intel ***)
-		   __pa_nodebug(&mc_saved_data->mc_saved);
-	for (i = 0; i < mc_saved_data->mc_saved_count; i++) {
+	mc_saved = (struct microcode_intel ***)__pa_nodebug(&mcs->mc_saved);
+
+	for (i = 0; i < mcs->num_saved; i++) {
 		struct microcode_intel *p;
 
-		p = *(struct microcode_intel **)
-			__pa_nodebug(mc_saved_data->mc_saved + i);
+		p = *(struct microcode_intel **)__pa_nodebug(mcs->mc_saved + i);
 		mc_saved_tmp[i] = (struct microcode_intel *)__pa_nodebug(p);
 	}
 }
 #endif
 
 static enum ucode_state
-load_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd,
-	       unsigned long initrd_start, struct ucode_cpu_info *uci)
+load_microcode(struct mc_saved_data *mcs, unsigned long *mc_ptrs,
+	       unsigned long offset, struct ucode_cpu_info *uci)
 {
 	struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT];
-	unsigned int count = mc_saved_data->mc_saved_count;
+	unsigned int count = mcs->num_saved;
 
-	if (!mc_saved_data->mc_saved) {
-		copy_initrd_ptrs(mc_saved_tmp, initrd, initrd_start, count);
+	if (!mcs->mc_saved) {
+		copy_ptrs(mc_saved_tmp, mc_ptrs, offset, count);
 
 		return load_microcode_early(mc_saved_tmp, count, uci);
 	} else {
 #ifdef CONFIG_X86_32
-		microcode_phys(mc_saved_tmp, mc_saved_data);
+		microcode_phys(mc_saved_tmp, mcs);
 		return load_microcode_early(mc_saved_tmp, count, uci);
 #else
-		return load_microcode_early(mc_saved_data->mc_saved,
-						    count, uci);
+		return load_microcode_early(mcs->mc_saved, count, uci);
 #endif
 	}
 }
@@ -175,25 +178,25 @@ matching_model_microcode(struct microcode_header_intel *mc_header,
 }
 
 static int
-save_microcode(struct mc_saved_data *mc_saved_data,
+save_microcode(struct mc_saved_data *mcs,
 	       struct microcode_intel **mc_saved_src,
-	       unsigned int mc_saved_count)
+	       unsigned int num_saved)
 {
 	int i, j;
 	struct microcode_intel **saved_ptr;
 	int ret;
 
-	if (!mc_saved_count)
+	if (!num_saved)
 		return -EINVAL;
 
 	/*
 	 * Copy new microcode data.
 	 */
-	saved_ptr = kcalloc(mc_saved_count, sizeof(struct microcode_intel *), GFP_KERNEL);
+	saved_ptr = kcalloc(num_saved, sizeof(struct microcode_intel *), GFP_KERNEL);
 	if (!saved_ptr)
 		return -ENOMEM;
 
-	for (i = 0; i < mc_saved_count; i++) {
+	for (i = 0; i < num_saved; i++) {
 		struct microcode_header_intel *mc_hdr;
 		struct microcode_intel *mc;
 		unsigned long size;
@@ -207,20 +210,18 @@ save_microcode(struct mc_saved_data *mc_saved_data,
 		mc_hdr = &mc->hdr;
 		size   = get_totalsize(mc_hdr);
 
-		saved_ptr[i] = kmalloc(size, GFP_KERNEL);
+		saved_ptr[i] = kmemdup(mc, size, GFP_KERNEL);
 		if (!saved_ptr[i]) {
 			ret = -ENOMEM;
 			goto err;
 		}
-
-		memcpy(saved_ptr[i], mc, size);
 	}
 
 	/*
 	 * Point to newly saved microcode.
 	 */
-	mc_saved_data->mc_saved = saved_ptr;
-	mc_saved_data->mc_saved_count = mc_saved_count;
+	mcs->mc_saved  = saved_ptr;
+	mcs->num_saved = num_saved;
 
 	return 0;
 
@@ -284,22 +285,20 @@ static unsigned int _save_mc(struct microcode_intel **mc_saved,
  * BSP can stay in the platform.
  */
 static enum ucode_state __init
-get_matching_model_microcode(int cpu, unsigned long start,
-			     void *data, size_t size,
-			     struct mc_saved_data *mc_saved_data,
-			     unsigned long *mc_saved_in_initrd,
+get_matching_model_microcode(unsigned long start, void *data, size_t size,
+			     struct mc_saved_data *mcs, unsigned long *mc_ptrs,
 			     struct ucode_cpu_info *uci)
 {
-	u8 *ucode_ptr = data;
-	unsigned int leftover = size;
+	struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT];
+	struct microcode_header_intel *mc_header;
+	unsigned int num_saved = mcs->num_saved;
 	enum ucode_state state = UCODE_OK;
+	unsigned int leftover = size;
+	u8 *ucode_ptr = data;
 	unsigned int mc_size;
-	struct microcode_header_intel *mc_header;
-	struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT];
-	unsigned int mc_saved_count = mc_saved_data->mc_saved_count;
 	int i;
 
-	while (leftover && mc_saved_count < ARRAY_SIZE(mc_saved_tmp)) {
+	while (leftover && num_saved < ARRAY_SIZE(mc_saved_tmp)) {
 
 		if (leftover < sizeof(mc_header))
 			break;
@@ -318,32 +317,31 @@ get_matching_model_microcode(int cpu, unsigned long start,
 		 * the platform, we need to find and save microcode patches
 		 * with the same family and model as the BSP.
 		 */
-		if (matching_model_microcode(mc_header, uci->cpu_sig.sig) !=
-			 UCODE_OK) {
+		if (matching_model_microcode(mc_header, uci->cpu_sig.sig) != UCODE_OK) {
 			ucode_ptr += mc_size;
 			continue;
 		}
 
-		mc_saved_count = _save_mc(mc_saved_tmp, ucode_ptr, mc_saved_count);
+		num_saved = _save_mc(mc_saved_tmp, ucode_ptr, num_saved);
 
 		ucode_ptr += mc_size;
 	}
 
 	if (leftover) {
 		state = UCODE_ERROR;
-		goto out;
+		return state;
 	}
 
-	if (mc_saved_count == 0) {
+	if (!num_saved) {
 		state = UCODE_NFOUND;
-		goto out;
+		return state;
 	}
 
-	for (i = 0; i < mc_saved_count; i++)
-		mc_saved_in_initrd[i] = (unsigned long)mc_saved_tmp[i] - start;
+	for (i = 0; i < num_saved; i++)
+		mc_ptrs[i] = (unsigned long)mc_saved_tmp[i] - start;
+
+	mcs->num_saved = num_saved;
 
-	mc_saved_data->mc_saved_count = mc_saved_count;
-out:
 	return state;
 }
 
@@ -373,7 +371,7 @@ static int collect_cpu_info_early(struct ucode_cpu_info *uci)
 		native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]);
 		csig.pf = 1 << ((val[1] >> 18) & 7);
 	}
-	native_wrmsr(MSR_IA32_UCODE_REV, 0, 0);
+	native_wrmsrl(MSR_IA32_UCODE_REV, 0);
 
 	/* As documented in the SDM: Do a CPUID 1 here */
 	sync_core();
@@ -396,11 +394,11 @@ static void show_saved_mc(void)
 	unsigned int sig, pf, rev, total_size, data_size, date;
 	struct ucode_cpu_info uci;
 
-	if (mc_saved_data.mc_saved_count == 0) {
+	if (!mc_saved_data.num_saved) {
 		pr_debug("no microcode data saved.\n");
 		return;
 	}
-	pr_debug("Total microcode saved: %d\n", mc_saved_data.mc_saved_count);
+	pr_debug("Total microcode saved: %d\n", mc_saved_data.num_saved);
 
 	collect_cpu_info_early(&uci);
 
@@ -409,7 +407,7 @@ static void show_saved_mc(void)
 	rev = uci.cpu_sig.rev;
 	pr_debug("CPU: sig=0x%x, pf=0x%x, rev=0x%x\n", sig, pf, rev);
 
-	for (i = 0; i < mc_saved_data.mc_saved_count; i++) {
+	for (i = 0; i < mc_saved_data.num_saved; i++) {
 		struct microcode_header_intel *mc_saved_header;
 		struct extended_sigtable *ext_header;
 		int ext_sigcount;
@@ -465,7 +463,7 @@ int save_mc_for_early(u8 *mc)
 {
 	struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT];
 	unsigned int mc_saved_count_init;
-	unsigned int mc_saved_count;
+	unsigned int num_saved;
 	struct microcode_intel **mc_saved;
 	int ret = 0;
 	int i;
@@ -476,23 +474,23 @@ int save_mc_for_early(u8 *mc)
 	 */
 	mutex_lock(&x86_cpu_microcode_mutex);
 
-	mc_saved_count_init = mc_saved_data.mc_saved_count;
-	mc_saved_count = mc_saved_data.mc_saved_count;
+	mc_saved_count_init = mc_saved_data.num_saved;
+	num_saved = mc_saved_data.num_saved;
 	mc_saved = mc_saved_data.mc_saved;
 
-	if (mc_saved && mc_saved_count)
+	if (mc_saved && num_saved)
 		memcpy(mc_saved_tmp, mc_saved,
-		       mc_saved_count * sizeof(struct microcode_intel *));
+		       num_saved * sizeof(struct microcode_intel *));
 	/*
 	 * Save the microcode patch mc in mc_save_tmp structure if it's a newer
 	 * version.
 	 */
-	mc_saved_count = _save_mc(mc_saved_tmp, mc, mc_saved_count);
+	num_saved = _save_mc(mc_saved_tmp, mc, num_saved);
 
 	/*
 	 * Save the mc_save_tmp in global mc_saved_data.
 	 */
-	ret = save_microcode(&mc_saved_data, mc_saved_tmp, mc_saved_count);
+	ret = save_microcode(&mc_saved_data, mc_saved_tmp, num_saved);
 	if (ret) {
 		pr_err("Cannot save microcode patch.\n");
 		goto out;
@@ -536,7 +534,7 @@ static bool __init load_builtin_intel_microcode(struct cpio_data *cp)
 
 static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin";
 static __init enum ucode_state
-scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd,
+scan_microcode(struct mc_saved_data *mcs, unsigned long *mc_ptrs,
 	       unsigned long start, unsigned long size,
 	       struct ucode_cpu_info *uci)
 {
@@ -551,14 +549,18 @@ scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd,
 	cd.data = NULL;
 	cd.size = 0;
 
-	cd = find_cpio_data(p, (void *)start, size, &offset);
-	if (!cd.data) {
+	/* try built-in microcode if no initrd */
+	if (!size) {
 		if (!load_builtin_intel_microcode(&cd))
 			return UCODE_ERROR;
+	} else {
+		cd = find_cpio_data(p, (void *)start, size, &offset);
+		if (!cd.data)
+			return UCODE_ERROR;
 	}
 
-	return get_matching_model_microcode(0, start, cd.data, cd.size,
-					    mc_saved_data, initrd, uci);
+	return get_matching_model_microcode(start, cd.data, cd.size,
+					    mcs, mc_ptrs, uci);
 }
 
 /*
@@ -567,14 +569,11 @@ scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd,
 static void
 print_ucode_info(struct ucode_cpu_info *uci, unsigned int date)
 {
-	int cpu = smp_processor_id();
-
-	pr_info("CPU%d microcode updated early to revision 0x%x, date = %04x-%02x-%02x\n",
-		cpu,
-		uci->cpu_sig.rev,
-		date & 0xffff,
-		date >> 24,
-		(date >> 16) & 0xff);
+	pr_info_once("microcode updated early to revision 0x%x, date = %04x-%02x-%02x\n",
+		     uci->cpu_sig.rev,
+		     date & 0xffff,
+		     date >> 24,
+		     (date >> 16) & 0xff);
 }
 
 #ifdef CONFIG_X86_32
@@ -603,19 +602,19 @@ void show_ucode_info_early(void)
  */
 static void print_ucode(struct ucode_cpu_info *uci)
 {
-	struct microcode_intel *mc_intel;
+	struct microcode_intel *mc;
 	int *delay_ucode_info_p;
 	int *current_mc_date_p;
 
-	mc_intel = uci->mc;
-	if (mc_intel == NULL)
+	mc = uci->mc;
+	if (!mc)
 		return;
 
 	delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info);
 	current_mc_date_p = (int *)__pa_nodebug(&current_mc_date);
 
 	*delay_ucode_info_p = 1;
-	*current_mc_date_p = mc_intel->hdr.date;
+	*current_mc_date_p = mc->hdr.date;
 }
 #else
 
@@ -630,37 +629,35 @@ static inline void flush_tlb_early(void)
 
 static inline void print_ucode(struct ucode_cpu_info *uci)
 {
-	struct microcode_intel *mc_intel;
+	struct microcode_intel *mc;
 
-	mc_intel = uci->mc;
-	if (mc_intel == NULL)
+	mc = uci->mc;
+	if (!mc)
 		return;
 
-	print_ucode_info(uci, mc_intel->hdr.date);
+	print_ucode_info(uci, mc->hdr.date);
 }
 #endif
 
 static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
 {
-	struct microcode_intel *mc_intel;
+	struct microcode_intel *mc;
 	unsigned int val[2];
 
-	mc_intel = uci->mc;
-	if (mc_intel == NULL)
+	mc = uci->mc;
+	if (!mc)
 		return 0;
 
 	/* write microcode via MSR 0x79 */
-	native_wrmsr(MSR_IA32_UCODE_WRITE,
-	      (unsigned long) mc_intel->bits,
-	      (unsigned long) mc_intel->bits >> 16 >> 16);
-	native_wrmsr(MSR_IA32_UCODE_REV, 0, 0);
+	native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
+	native_wrmsrl(MSR_IA32_UCODE_REV, 0);
 
 	/* As documented in the SDM: Do a CPUID 1 here */
 	sync_core();
 
 	/* get the current revision from MSR 0x8B */
 	native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
-	if (val[1] != mc_intel->hdr.rev)
+	if (val[1] != mc->hdr.rev)
 		return -1;
 
 #ifdef CONFIG_X86_64
@@ -672,25 +669,26 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
 	if (early)
 		print_ucode(uci);
 	else
-		print_ucode_info(uci, mc_intel->hdr.date);
+		print_ucode_info(uci, mc->hdr.date);
 
 	return 0;
 }
 
 /*
  * This function converts microcode patch offsets previously stored in
- * mc_saved_in_initrd to pointers and stores the pointers in mc_saved_data.
+ * mc_tmp_ptrs to pointers and stores the pointers in mc_saved_data.
  */
 int __init save_microcode_in_initrd_intel(void)
 {
-	unsigned int count = mc_saved_data.mc_saved_count;
+	unsigned int count = mc_saved_data.num_saved;
 	struct microcode_intel *mc_saved[MAX_UCODE_COUNT];
 	int ret = 0;
 
-	if (count == 0)
+	if (!count)
 		return ret;
 
-	copy_initrd_ptrs(mc_saved, mc_saved_in_initrd, initrd_start, count);
+	copy_ptrs(mc_saved, mc_tmp_ptrs, get_initrd_start(), count);
+
 	ret = save_microcode(&mc_saved_data, mc_saved, count);
 	if (ret)
 		pr_err("Cannot save microcode patches from initrd.\n");
@@ -701,8 +699,7 @@ int __init save_microcode_in_initrd_intel(void)
 }
 
 static void __init
-_load_ucode_intel_bsp(struct mc_saved_data *mc_saved_data,
-		      unsigned long *initrd,
+_load_ucode_intel_bsp(struct mc_saved_data *mcs, unsigned long *mc_ptrs,
 		      unsigned long start, unsigned long size)
 {
 	struct ucode_cpu_info uci;
@@ -710,11 +707,11 @@ _load_ucode_intel_bsp(struct mc_saved_data *mc_saved_data,
 
 	collect_cpu_info_early(&uci);
 
-	ret = scan_microcode(mc_saved_data, initrd, start, size, &uci);
+	ret = scan_microcode(mcs, mc_ptrs, start, size, &uci);
 	if (ret != UCODE_OK)
 		return;
 
-	ret = load_microcode(mc_saved_data, initrd, start, &uci);
+	ret = load_microcode(mcs, mc_ptrs, start, &uci);
 	if (ret != UCODE_OK)
 		return;
 
@@ -728,53 +725,49 @@ void __init load_ucode_intel_bsp(void)
 	struct boot_params *p;
 
 	p	= (struct boot_params *)__pa_nodebug(&boot_params);
-	start	= p->hdr.ramdisk_image;
 	size	= p->hdr.ramdisk_size;
 
-	_load_ucode_intel_bsp(
-			(struct mc_saved_data *)__pa_nodebug(&mc_saved_data),
-			(unsigned long *)__pa_nodebug(&mc_saved_in_initrd),
-			start, size);
+	/*
+	 * Set start only if we have an initrd image. We cannot use initrd_start
+	 * because it is not set that early yet.
+	 */
+	start	= (size ? p->hdr.ramdisk_image : 0);
+
+	_load_ucode_intel_bsp((struct mc_saved_data *)__pa_nodebug(&mc_saved_data),
+			      (unsigned long *)__pa_nodebug(&mc_tmp_ptrs),
+			      start, size);
 #else
-	start	= boot_params.hdr.ramdisk_image + PAGE_OFFSET;
 	size	= boot_params.hdr.ramdisk_size;
+	start	= (size ? boot_params.hdr.ramdisk_image + PAGE_OFFSET : 0);
 
-	_load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd, start, size);
+	_load_ucode_intel_bsp(&mc_saved_data, mc_tmp_ptrs, start, size);
 #endif
 }
 
 void load_ucode_intel_ap(void)
 {
-	struct mc_saved_data *mc_saved_data_p;
+	unsigned long *mcs_tmp_p;
+	struct mc_saved_data *mcs_p;
 	struct ucode_cpu_info uci;
-	unsigned long *mc_saved_in_initrd_p;
-	unsigned long initrd_start_addr;
 	enum ucode_state ret;
 #ifdef CONFIG_X86_32
-	unsigned long *initrd_start_p;
 
-	mc_saved_in_initrd_p =
-		(unsigned long *)__pa_nodebug(mc_saved_in_initrd);
-	mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data);
-	initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start);
-	initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p);
+	mcs_tmp_p = (unsigned long *)__pa_nodebug(mc_tmp_ptrs);
+	mcs_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data);
 #else
-	mc_saved_data_p = &mc_saved_data;
-	mc_saved_in_initrd_p = mc_saved_in_initrd;
-	initrd_start_addr = initrd_start;
+	mcs_tmp_p = mc_tmp_ptrs;
+	mcs_p = &mc_saved_data;
 #endif
 
 	/*
 	 * If there is no valid ucode previously saved in memory, no need to
 	 * update ucode on this AP.
 	 */
-	if (mc_saved_data_p->mc_saved_count == 0)
+	if (!mcs_p->num_saved)
 		return;
 
 	collect_cpu_info_early(&uci);
-	ret = load_microcode(mc_saved_data_p, mc_saved_in_initrd_p,
-			     initrd_start_addr, &uci);
-
+	ret = load_microcode(mcs_p, mcs_tmp_p, get_initrd_start_addr(), &uci);
 	if (ret != UCODE_OK)
 		return;
 
@@ -786,13 +779,13 @@ void reload_ucode_intel(void)
 	struct ucode_cpu_info uci;
 	enum ucode_state ret;
 
-	if (!mc_saved_data.mc_saved_count)
+	if (!mc_saved_data.num_saved)
 		return;
 
 	collect_cpu_info_early(&uci);
 
 	ret = load_microcode_early(mc_saved_data.mc_saved,
-				   mc_saved_data.mc_saved_count, &uci);
+				   mc_saved_data.num_saved, &uci);
 	if (ret != UCODE_OK)
 		return;
 
@@ -825,7 +818,7 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
  * return 0 - no update found
  * return 1 - found update
  */
-static int get_matching_mc(struct microcode_intel *mc_intel, int cpu)
+static int get_matching_mc(struct microcode_intel *mc, int cpu)
 {
 	struct cpu_signature cpu_sig;
 	unsigned int csig, cpf, crev;
@@ -836,39 +829,36 @@ static int get_matching_mc(struct microcode_intel *mc_intel, int cpu)
 	cpf = cpu_sig.pf;
 	crev = cpu_sig.rev;
 
-	return has_newer_microcode(mc_intel, csig, cpf, crev);
+	return has_newer_microcode(mc, csig, cpf, crev);
 }
 
 static int apply_microcode_intel(int cpu)
 {
-	struct microcode_intel *mc_intel;
+	struct microcode_intel *mc;
 	struct ucode_cpu_info *uci;
+	struct cpuinfo_x86 *c;
 	unsigned int val[2];
-	int cpu_num = raw_smp_processor_id();
-	struct cpuinfo_x86 *c = &cpu_data(cpu_num);
-
-	uci = ucode_cpu_info + cpu;
-	mc_intel = uci->mc;
 
 	/* We should bind the task to the CPU */
-	BUG_ON(cpu_num != cpu);
+	if (WARN_ON(raw_smp_processor_id() != cpu))
+		return -1;
 
-	if (mc_intel == NULL)
+	uci = ucode_cpu_info + cpu;
+	mc = uci->mc;
+	if (!mc)
 		return 0;
 
 	/*
 	 * Microcode on this CPU could be updated earlier. Only apply the
-	 * microcode patch in mc_intel when it is newer than the one on this
+	 * microcode patch in mc when it is newer than the one on this
 	 * CPU.
 	 */
-	if (get_matching_mc(mc_intel, cpu) == 0)
+	if (!get_matching_mc(mc, cpu))
 		return 0;
 
 	/* write microcode via MSR 0x79 */
-	wrmsr(MSR_IA32_UCODE_WRITE,
-	      (unsigned long) mc_intel->bits,
-	      (unsigned long) mc_intel->bits >> 16 >> 16);
-	wrmsr(MSR_IA32_UCODE_REV, 0, 0);
+	wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
+	wrmsrl(MSR_IA32_UCODE_REV, 0);
 
 	/* As documented in the SDM: Do a CPUID 1 here */
 	sync_core();
@@ -876,16 +866,19 @@ static int apply_microcode_intel(int cpu)
 	/* get the current revision from MSR 0x8B */
 	rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
 
-	if (val[1] != mc_intel->hdr.rev) {
+	if (val[1] != mc->hdr.rev) {
 		pr_err("CPU%d update to revision 0x%x failed\n",
-		       cpu_num, mc_intel->hdr.rev);
+		       cpu, mc->hdr.rev);
 		return -1;
 	}
+
 	pr_info("CPU%d updated to revision 0x%x, date = %04x-%02x-%02x\n",
-		cpu_num, val[1],
-		mc_intel->hdr.date & 0xffff,
-		mc_intel->hdr.date >> 24,
-		(mc_intel->hdr.date >> 16) & 0xff);
+		cpu, val[1],
+		mc->hdr.date & 0xffff,
+		mc->hdr.date >> 24,
+		(mc->hdr.date >> 16) & 0xff);
+
+	c = &cpu_data(cpu);
 
 	uci->cpu_sig.rev = val[1];
 	c->microcode = val[1];
diff --git a/arch/x86/kernel/cpu/microcode/intel_lib.c b/arch/x86/kernel/cpu/microcode/intel_lib.c
index b96896bcbdaf..2ce1a7dc45b7 100644
--- a/arch/x86/kernel/cpu/microcode/intel_lib.c
+++ b/arch/x86/kernel/cpu/microcode/intel_lib.c
@@ -49,7 +49,7 @@ int microcode_sanity_check(void *mc, int print_err)
 	unsigned long total_size, data_size, ext_table_size;
 	struct microcode_header_intel *mc_header = mc;
 	struct extended_sigtable *ext_header = NULL;
-	int sum, orig_sum, ext_sigcount = 0, i;
+	u32 sum, orig_sum, ext_sigcount = 0, i;
 	struct extended_signature *ext_sig;
 
 	total_size = get_totalsize(mc_header);
@@ -57,69 +57,85 @@ int microcode_sanity_check(void *mc, int print_err)
 
 	if (data_size + MC_HEADER_SIZE > total_size) {
 		if (print_err)
-			pr_err("error! Bad data size in microcode data file\n");
+			pr_err("Error: bad microcode data file size.\n");
 		return -EINVAL;
 	}
 
 	if (mc_header->ldrver != 1 || mc_header->hdrver != 1) {
 		if (print_err)
-			pr_err("error! Unknown microcode update format\n");
+			pr_err("Error: invalid/unknown microcode update format.\n");
 		return -EINVAL;
 	}
+
 	ext_table_size = total_size - (MC_HEADER_SIZE + data_size);
 	if (ext_table_size) {
+		u32 ext_table_sum = 0;
+		u32 *ext_tablep;
+
 		if ((ext_table_size < EXT_HEADER_SIZE)
 		 || ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) {
 			if (print_err)
-				pr_err("error! Small exttable size in microcode data file\n");
+				pr_err("Error: truncated extended signature table.\n");
 			return -EINVAL;
 		}
+
 		ext_header = mc + MC_HEADER_SIZE + data_size;
 		if (ext_table_size != exttable_size(ext_header)) {
 			if (print_err)
-				pr_err("error! Bad exttable size in microcode data file\n");
+				pr_err("Error: extended signature table size mismatch.\n");
 			return -EFAULT;
 		}
+
 		ext_sigcount = ext_header->count;
-	}
 
-	/* check extended table checksum */
-	if (ext_table_size) {
-		int ext_table_sum = 0;
-		int *ext_tablep = (int *)ext_header;
+		/*
+		 * Check extended table checksum: the sum of all dwords that
+		 * comprise a valid table must be 0.
+		 */
+		ext_tablep = (u32 *)ext_header;
 
-		i = ext_table_size / DWSIZE;
+		i = ext_table_size / sizeof(u32);
 		while (i--)
 			ext_table_sum += ext_tablep[i];
+
 		if (ext_table_sum) {
 			if (print_err)
-				pr_warn("aborting, bad extended signature table checksum\n");
+				pr_warn("Bad extended signature table checksum, aborting.\n");
 			return -EINVAL;
 		}
 	}
 
-	/* calculate the checksum */
+	/*
+	 * Calculate the checksum of update data and header. The checksum of
+	 * valid update data and header including the extended signature table
+	 * must be 0.
+	 */
 	orig_sum = 0;
-	i = (MC_HEADER_SIZE + data_size) / DWSIZE;
+	i = (MC_HEADER_SIZE + data_size) / sizeof(u32);
 	while (i--)
-		orig_sum += ((int *)mc)[i];
+		orig_sum += ((u32 *)mc)[i];
+
 	if (orig_sum) {
 		if (print_err)
-			pr_err("aborting, bad checksum\n");
+			pr_err("Bad microcode data checksum, aborting.\n");
 		return -EINVAL;
 	}
+
 	if (!ext_table_size)
 		return 0;
-	/* check extended signature checksum */
+
+	/*
+	 * Check extended signature checksum: 0 => valid.
+	 */
 	for (i = 0; i < ext_sigcount; i++) {
 		ext_sig = (void *)ext_header + EXT_HEADER_SIZE +
 			  EXT_SIGNATURE_SIZE * i;
-		sum = orig_sum
-			- (mc_header->sig + mc_header->pf + mc_header->cksum)
-			+ (ext_sig->sig + ext_sig->pf + ext_sig->cksum);
+
+		sum = (mc_header->sig + mc_header->pf + mc_header->cksum) -
+		      (ext_sig->sig + ext_sig->pf + ext_sig->cksum);
 		if (sum) {
 			if (print_err)
-				pr_err("aborting, bad checksum\n");
+				pr_err("Bad extended signature checksum, aborting.\n");
 			return -EINVAL;
 		}
 	}
diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh
index 3f20710a5b23..6988c74409a8 100644
--- a/arch/x86/kernel/cpu/mkcapflags.sh
+++ b/arch/x86/kernel/cpu/mkcapflags.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 #
-# Generate the x86_cap/bug_flags[] arrays from include/asm/cpufeature.h
+# Generate the x86_cap/bug_flags[] arrays from include/asm/cpufeatures.h
 #
 
 IN=$1
@@ -49,8 +49,8 @@ dump_array()
 trap 'rm "$OUT"' EXIT
 
 (
-	echo "#ifndef _ASM_X86_CPUFEATURE_H"
-	echo "#include <asm/cpufeature.h>"
+	echo "#ifndef _ASM_X86_CPUFEATURES_H"
+	echo "#include <asm/cpufeatures.h>"
 	echo "#endif"
 	echo ""
 
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 20e242ea1bc4..4e7c6933691c 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -161,8 +161,8 @@ static void __init ms_hyperv_init_platform(void)
 	ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES);
 	ms_hyperv.hints    = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
 
-	printk(KERN_INFO "HyperV: features 0x%x, hints 0x%x\n",
-	       ms_hyperv.features, ms_hyperv.hints);
+	pr_info("HyperV: features 0x%x, hints 0x%x\n",
+		ms_hyperv.features, ms_hyperv.hints);
 
 #ifdef CONFIG_X86_LOCAL_APIC
 	if (ms_hyperv.features & HV_X64_MSR_APIC_FREQUENCY_AVAILABLE) {
@@ -174,8 +174,8 @@ static void __init ms_hyperv_init_platform(void)
 		rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency);
 		hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ);
 		lapic_timer_frequency = hv_lapic_frequency;
-		printk(KERN_INFO "HyperV: LAPIC Timer Frequency: %#x\n",
-				lapic_timer_frequency);
+		pr_info("HyperV: LAPIC Timer Frequency: %#x\n",
+			lapic_timer_frequency);
 	}
 #endif
 
diff --git a/arch/x86/kernel/cpu/mtrr/centaur.c b/arch/x86/kernel/cpu/mtrr/centaur.c
index 316fe3e60a97..3d689937fc1b 100644
--- a/arch/x86/kernel/cpu/mtrr/centaur.c
+++ b/arch/x86/kernel/cpu/mtrr/centaur.c
@@ -103,7 +103,7 @@ centaur_validate_add_page(unsigned long base, unsigned long size, unsigned int t
 	 */
 	if (type != MTRR_TYPE_WRCOMB &&
 	    (centaur_mcr_type == 0 || type != MTRR_TYPE_UNCACHABLE)) {
-		pr_warning("mtrr: only write-combining%s supported\n",
+		pr_warn("mtrr: only write-combining%s supported\n",
 			   centaur_mcr_type ? " and uncacheable are" : " is");
 		return -EINVAL;
 	}
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 0d98503c2245..31e951ce6dff 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -57,9 +57,9 @@ static int __initdata				nr_range;
 static struct var_mtrr_range_state __initdata	range_state[RANGE_NUM];
 
 static int __initdata debug_print;
-#define Dprintk(x...) do { if (debug_print) printk(KERN_DEBUG x); } while (0)
+#define Dprintk(x...) do { if (debug_print) pr_debug(x); } while (0)
 
-#define BIOS_BUG_MSG KERN_WARNING \
+#define BIOS_BUG_MSG \
 	"WARNING: BIOS bug: VAR MTRR %d contains strange UC entry under 1M, check with your system vendor!\n"
 
 static int __init
@@ -81,9 +81,9 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range,
 						base, base + size);
 	}
 	if (debug_print) {
-		printk(KERN_DEBUG "After WB checking\n");
+		pr_debug("After WB checking\n");
 		for (i = 0; i < nr_range; i++)
-			printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n",
+			pr_debug("MTRR MAP PFN: %016llx - %016llx\n",
 				 range[i].start, range[i].end);
 	}
 
@@ -101,7 +101,7 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range,
 		    (mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) &&
 		    (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) {
 			/* Var MTRR contains UC entry below 1M? Skip it: */
-			printk(BIOS_BUG_MSG, i);
+			pr_warn(BIOS_BUG_MSG, i);
 			if (base + size <= (1<<(20-PAGE_SHIFT)))
 				continue;
 			size -= (1<<(20-PAGE_SHIFT)) - base;
@@ -114,11 +114,11 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range,
 				 extra_remove_base + extra_remove_size);
 
 	if  (debug_print) {
-		printk(KERN_DEBUG "After UC checking\n");
+		pr_debug("After UC checking\n");
 		for (i = 0; i < RANGE_NUM; i++) {
 			if (!range[i].end)
 				continue;
-			printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n",
+			pr_debug("MTRR MAP PFN: %016llx - %016llx\n",
 				 range[i].start, range[i].end);
 		}
 	}
@@ -126,9 +126,9 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range,
 	/* sort the ranges */
 	nr_range = clean_sort_range(range, RANGE_NUM);
 	if  (debug_print) {
-		printk(KERN_DEBUG "After sorting\n");
+		pr_debug("After sorting\n");
 		for (i = 0; i < nr_range; i++)
-			printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n",
+			pr_debug("MTRR MAP PFN: %016llx - %016llx\n",
 				 range[i].start, range[i].end);
 	}
 
@@ -544,7 +544,7 @@ static void __init print_out_mtrr_range_state(void)
 		start_base = to_size_factor(start_base, &start_factor),
 		type = range_state[i].type;
 
-		printk(KERN_DEBUG "reg %d, base: %ld%cB, range: %ld%cB, type %s\n",
+		pr_debug("reg %d, base: %ld%cB, range: %ld%cB, type %s\n",
 			i, start_base, start_factor,
 			size_base, size_factor,
 			(type == MTRR_TYPE_UNCACHABLE) ? "UC" :
@@ -713,7 +713,7 @@ int __init mtrr_cleanup(unsigned address_bits)
 		return 0;
 
 	/* Print original var MTRRs at first, for debugging: */
-	printk(KERN_DEBUG "original variable MTRRs\n");
+	pr_debug("original variable MTRRs\n");
 	print_out_mtrr_range_state();
 
 	memset(range, 0, sizeof(range));
@@ -733,7 +733,7 @@ int __init mtrr_cleanup(unsigned address_bits)
 					  x_remove_base, x_remove_size);
 
 	range_sums = sum_ranges(range, nr_range);
-	printk(KERN_INFO "total RAM covered: %ldM\n",
+	pr_info("total RAM covered: %ldM\n",
 	       range_sums >> (20 - PAGE_SHIFT));
 
 	if (mtrr_chunk_size && mtrr_gran_size) {
@@ -745,12 +745,11 @@ int __init mtrr_cleanup(unsigned address_bits)
 
 		if (!result[i].bad) {
 			set_var_mtrr_all(address_bits);
-			printk(KERN_DEBUG "New variable MTRRs\n");
+			pr_debug("New variable MTRRs\n");
 			print_out_mtrr_range_state();
 			return 1;
 		}
-		printk(KERN_INFO "invalid mtrr_gran_size or mtrr_chunk_size, "
-		       "will find optimal one\n");
+		pr_info("invalid mtrr_gran_size or mtrr_chunk_size, will find optimal one\n");
 	}
 
 	i = 0;
@@ -768,7 +767,7 @@ int __init mtrr_cleanup(unsigned address_bits)
 				      x_remove_base, x_remove_size, i);
 			if (debug_print) {
 				mtrr_print_out_one_result(i);
-				printk(KERN_INFO "\n");
+				pr_info("\n");
 			}
 
 			i++;
@@ -779,7 +778,7 @@ int __init mtrr_cleanup(unsigned address_bits)
 	index_good = mtrr_search_optimal_index();
 
 	if (index_good != -1) {
-		printk(KERN_INFO "Found optimal setting for mtrr clean up\n");
+		pr_info("Found optimal setting for mtrr clean up\n");
 		i = index_good;
 		mtrr_print_out_one_result(i);
 
@@ -790,7 +789,7 @@ int __init mtrr_cleanup(unsigned address_bits)
 		gran_size <<= 10;
 		x86_setup_var_mtrrs(range, nr_range, chunk_size, gran_size);
 		set_var_mtrr_all(address_bits);
-		printk(KERN_DEBUG "New variable MTRRs\n");
+		pr_debug("New variable MTRRs\n");
 		print_out_mtrr_range_state();
 		return 1;
 	} else {
@@ -799,8 +798,8 @@ int __init mtrr_cleanup(unsigned address_bits)
 			mtrr_print_out_one_result(i);
 	}
 
-	printk(KERN_INFO "mtrr_cleanup: can not find optimal value\n");
-	printk(KERN_INFO "please specify mtrr_gran_size/mtrr_chunk_size\n");
+	pr_info("mtrr_cleanup: can not find optimal value\n");
+	pr_info("please specify mtrr_gran_size/mtrr_chunk_size\n");
 
 	return 0;
 }
@@ -918,7 +917,7 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 
 	/* kvm/qemu doesn't have mtrr set right, don't trim them all: */
 	if (!highest_pfn) {
-		printk(KERN_INFO "CPU MTRRs all blank - virtualized system.\n");
+		pr_info("CPU MTRRs all blank - virtualized system.\n");
 		return 0;
 	}
 
@@ -973,7 +972,8 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 							 end_pfn);
 
 	if (total_trim_size) {
-		pr_warning("WARNING: BIOS bug: CPU MTRRs don't cover all of memory, losing %lluMB of RAM.\n", total_trim_size >> 20);
+		pr_warn("WARNING: BIOS bug: CPU MTRRs don't cover all of memory, losing %lluMB of RAM.\n",
+			total_trim_size >> 20);
 
 		if (!changed_by_mtrr_cleanup)
 			WARN_ON(1);
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index c870af161008..fcbcb2f678ca 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -55,7 +55,7 @@ static inline void k8_check_syscfg_dram_mod_en(void)
 
 	rdmsr(MSR_K8_SYSCFG, lo, hi);
 	if (lo & K8_MTRRFIXRANGE_DRAM_MODIFY) {
-		printk(KERN_ERR FW_WARN "MTRR: CPU %u: SYSCFG[MtrrFixDramModEn]"
+		pr_err(FW_WARN "MTRR: CPU %u: SYSCFG[MtrrFixDramModEn]"
 		       " not cleared by BIOS, clearing this bit\n",
 		       smp_processor_id());
 		lo &= ~K8_MTRRFIXRANGE_DRAM_MODIFY;
@@ -501,14 +501,14 @@ void __init mtrr_state_warn(void)
 	if (!mask)
 		return;
 	if (mask & MTRR_CHANGE_MASK_FIXED)
-		pr_warning("mtrr: your CPUs had inconsistent fixed MTRR settings\n");
+		pr_warn("mtrr: your CPUs had inconsistent fixed MTRR settings\n");
 	if (mask & MTRR_CHANGE_MASK_VARIABLE)
-		pr_warning("mtrr: your CPUs had inconsistent variable MTRR settings\n");
+		pr_warn("mtrr: your CPUs had inconsistent variable MTRR settings\n");
 	if (mask & MTRR_CHANGE_MASK_DEFTYPE)
-		pr_warning("mtrr: your CPUs had inconsistent MTRRdefType settings\n");
+		pr_warn("mtrr: your CPUs had inconsistent MTRRdefType settings\n");
 
-	printk(KERN_INFO "mtrr: probably your BIOS does not setup all CPUs.\n");
-	printk(KERN_INFO "mtrr: corrected configuration.\n");
+	pr_info("mtrr: probably your BIOS does not setup all CPUs.\n");
+	pr_info("mtrr: corrected configuration.\n");
 }
 
 /*
@@ -519,8 +519,7 @@ void __init mtrr_state_warn(void)
 void mtrr_wrmsr(unsigned msr, unsigned a, unsigned b)
 {
 	if (wrmsr_safe(msr, a, b) < 0) {
-		printk(KERN_ERR
-			"MTRR: CPU %u: Writing MSR %x to %x:%x failed\n",
+		pr_err("MTRR: CPU %u: Writing MSR %x to %x:%x failed\n",
 			smp_processor_id(), msr, a, b);
 	}
 }
@@ -607,7 +606,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base,
 		tmp |= ~((1ULL<<(hi - 1)) - 1);
 
 		if (tmp != mask) {
-			printk(KERN_WARNING "mtrr: your BIOS has configured an incorrect mask, fixing it.\n");
+			pr_warn("mtrr: your BIOS has configured an incorrect mask, fixing it.\n");
 			add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
 			mask = tmp;
 		}
@@ -858,13 +857,13 @@ int generic_validate_add_page(unsigned long base, unsigned long size,
 	    boot_cpu_data.x86_model == 1 &&
 	    boot_cpu_data.x86_mask <= 7) {
 		if (base & ((1 << (22 - PAGE_SHIFT)) - 1)) {
-			pr_warning("mtrr: base(0x%lx000) is not 4 MiB aligned\n", base);
+			pr_warn("mtrr: base(0x%lx000) is not 4 MiB aligned\n", base);
 			return -EINVAL;
 		}
 		if (!(base + size < 0x70000 || base > 0x7003F) &&
 		    (type == MTRR_TYPE_WRCOMB
 		     || type == MTRR_TYPE_WRBACK)) {
-			pr_warning("mtrr: writable mtrr between 0x70000000 and 0x7003FFFF may hang the CPU.\n");
+			pr_warn("mtrr: writable mtrr between 0x70000000 and 0x7003FFFF may hang the CPU.\n");
 			return -EINVAL;
 		}
 	}
@@ -878,7 +877,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size,
 	     lbase = lbase >> 1, last = last >> 1)
 		;
 	if (lbase != last) {
-		pr_warning("mtrr: base(0x%lx000) is not aligned on a size(0x%lx000) boundary\n", base, size);
+		pr_warn("mtrr: base(0x%lx000) is not aligned on a size(0x%lx000) boundary\n", base, size);
 		return -EINVAL;
 	}
 	return 0;
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 5c3d149ee91c..10f8d4796240 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -47,7 +47,7 @@
 #include <linux/smp.h>
 #include <linux/syscore_ops.h>
 
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/e820.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
@@ -300,24 +300,24 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 		return error;
 
 	if (type >= MTRR_NUM_TYPES) {
-		pr_warning("mtrr: type: %u invalid\n", type);
+		pr_warn("mtrr: type: %u invalid\n", type);
 		return -EINVAL;
 	}
 
 	/* If the type is WC, check that this processor supports it */
 	if ((type == MTRR_TYPE_WRCOMB) && !have_wrcomb()) {
-		pr_warning("mtrr: your processor doesn't support write-combining\n");
+		pr_warn("mtrr: your processor doesn't support write-combining\n");
 		return -ENOSYS;
 	}
 
 	if (!size) {
-		pr_warning("mtrr: zero sized request\n");
+		pr_warn("mtrr: zero sized request\n");
 		return -EINVAL;
 	}
 
 	if ((base | (base + size - 1)) >>
 	    (boot_cpu_data.x86_phys_bits - PAGE_SHIFT)) {
-		pr_warning("mtrr: base or size exceeds the MTRR width\n");
+		pr_warn("mtrr: base or size exceeds the MTRR width\n");
 		return -EINVAL;
 	}
 
@@ -348,7 +348,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 				} else if (types_compatible(type, ltype))
 					continue;
 			}
-			pr_warning("mtrr: 0x%lx000,0x%lx000 overlaps existing"
+			pr_warn("mtrr: 0x%lx000,0x%lx000 overlaps existing"
 				" 0x%lx000,0x%lx000\n", base, size, lbase,
 				lsize);
 			goto out;
@@ -357,7 +357,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 		if (ltype != type) {
 			if (types_compatible(type, ltype))
 				continue;
-			pr_warning("mtrr: type mismatch for %lx000,%lx000 old: %s new: %s\n",
+			pr_warn("mtrr: type mismatch for %lx000,%lx000 old: %s new: %s\n",
 				base, size, mtrr_attrib_to_str(ltype),
 				mtrr_attrib_to_str(type));
 			goto out;
@@ -395,7 +395,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 static int mtrr_check(unsigned long base, unsigned long size)
 {
 	if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) {
-		pr_warning("mtrr: size and base must be multiples of 4 kiB\n");
+		pr_warn("mtrr: size and base must be multiples of 4 kiB\n");
 		pr_debug("mtrr: size: 0x%lx  base: 0x%lx\n", size, base);
 		dump_stack();
 		return -1;
@@ -493,16 +493,16 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
 		}
 	}
 	if (reg >= max) {
-		pr_warning("mtrr: register: %d too big\n", reg);
+		pr_warn("mtrr: register: %d too big\n", reg);
 		goto out;
 	}
 	mtrr_if->get(reg, &lbase, &lsize, &ltype);
 	if (lsize < 1) {
-		pr_warning("mtrr: MTRR %d not used\n", reg);
+		pr_warn("mtrr: MTRR %d not used\n", reg);
 		goto out;
 	}
 	if (mtrr_usage_table[reg] < 1) {
-		pr_warning("mtrr: reg: %d has count=0\n", reg);
+		pr_warn("mtrr: reg: %d has count=0\n", reg);
 		goto out;
 	}
 	if (--mtrr_usage_table[reg] < 1)
diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c
index 819d94982e07..f6f50c4ceaec 100644
--- a/arch/x86/kernel/cpu/rdrand.c
+++ b/arch/x86/kernel/cpu/rdrand.c
@@ -51,7 +51,7 @@ void x86_init_rdrand(struct cpuinfo_x86 *c)
 	for (i = 0; i < SANITY_CHECK_LOOPS; i++) {
 		if (!rdrand_long(&tmp)) {
 			clear_cpu_cap(c, X86_FEATURE_RDRAND);
-			printk_once(KERN_WARNING "rdrand: disabled\n");
+			pr_warn_once("rdrand: disabled\n");
 			return;
 		}
 	}
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 4c60eaf0571c..cd531355e838 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -87,10 +87,10 @@ void detect_extended_topology(struct cpuinfo_x86 *c)
 	c->x86_max_cores = (core_level_siblings / smp_num_siblings);
 
 	if (!printed) {
-		printk(KERN_INFO  "CPU: Physical Processor ID: %d\n",
+		pr_info("CPU: Physical Processor ID: %d\n",
 		       c->phys_proc_id);
 		if (c->x86_max_cores > 1)
-			printk(KERN_INFO  "CPU: Processor Core ID: %d\n",
+			pr_info("CPU: Processor Core ID: %d\n",
 			       c->cpu_core_id);
 		printed = 1;
 	}
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index 252da7aceca6..34178564be2a 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -1,6 +1,6 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/msr.h>
 #include "cpu.h"
 
@@ -33,7 +33,7 @@ static void init_transmeta(struct cpuinfo_x86 *c)
 	if (max >= 0x80860001) {
 		cpuid(0x80860001, &dummy, &cpu_rev, &cpu_freq, &cpu_flags);
 		if (cpu_rev != 0x02000000) {
-			printk(KERN_INFO "CPU: Processor revision %u.%u.%u.%u, %u MHz\n",
+			pr_info("CPU: Processor revision %u.%u.%u.%u, %u MHz\n",
 				(cpu_rev >> 24) & 0xff,
 				(cpu_rev >> 16) & 0xff,
 				(cpu_rev >> 8) & 0xff,
@@ -44,10 +44,10 @@ static void init_transmeta(struct cpuinfo_x86 *c)
 	if (max >= 0x80860002) {
 		cpuid(0x80860002, &new_cpu_rev, &cms_rev1, &cms_rev2, &dummy);
 		if (cpu_rev == 0x02000000) {
-			printk(KERN_INFO "CPU: Processor revision %08X, %u MHz\n",
+			pr_info("CPU: Processor revision %08X, %u MHz\n",
 				new_cpu_rev, cpu_freq);
 		}
-		printk(KERN_INFO "CPU: Code Morphing Software revision %u.%u.%u-%u-%u\n",
+		pr_info("CPU: Code Morphing Software revision %u.%u.%u-%u-%u\n",
 		       (cms_rev1 >> 24) & 0xff,
 		       (cms_rev1 >> 16) & 0xff,
 		       (cms_rev1 >> 8) & 0xff,
@@ -76,7 +76,7 @@ static void init_transmeta(struct cpuinfo_x86 *c)
 		      (void *)&cpu_info[56],
 		      (void *)&cpu_info[60]);
 		cpu_info[64] = '\0';
-		printk(KERN_INFO "CPU: %s\n", cpu_info);
+		pr_info("CPU: %s\n", cpu_info);
 	}
 
 	/* Unhide possibly hidden capability flags */
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 628a059a9a06..364e58346897 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -62,7 +62,7 @@ static unsigned long vmware_get_tsc_khz(void)
 	tsc_hz = eax | (((uint64_t)ebx) << 32);
 	do_div(tsc_hz, 1000);
 	BUG_ON(tsc_hz >> 32);
-	printk(KERN_INFO "TSC freq read from hypervisor : %lu.%03lu MHz\n",
+	pr_info("TSC freq read from hypervisor : %lu.%03lu MHz\n",
 			 (unsigned long) tsc_hz / 1000,
 			 (unsigned long) tsc_hz % 1000);
 
@@ -84,8 +84,7 @@ static void __init vmware_platform_setup(void)
 	if (ebx != UINT_MAX)
 		x86_platform.calibrate_tsc = vmware_get_tsc_khz;
 	else
-		printk(KERN_WARNING
-		       "Failed to get TSC freq from the hypervisor\n");
+		pr_warn("Failed to get TSC freq from the hypervisor\n");
 }
 
 /*
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 58f34319b29a..9ef978d69c22 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -57,10 +57,9 @@ struct crash_elf_data {
 	struct kimage *image;
 	/*
 	 * Total number of ram ranges we have after various adjustments for
-	 * GART, crash reserved region etc.
+	 * crash reserved region, etc.
 	 */
 	unsigned int max_nr_ranges;
-	unsigned long gart_start, gart_end;
 
 	/* Pointer to elf header */
 	void *ehdr;
@@ -201,17 +200,6 @@ static int get_nr_ram_ranges_callback(u64 start, u64 end, void *arg)
 	return 0;
 }
 
-static int get_gart_ranges_callback(u64 start, u64 end, void *arg)
-{
-	struct crash_elf_data *ced = arg;
-
-	ced->gart_start = start;
-	ced->gart_end = end;
-
-	/* Not expecting more than 1 gart aperture */
-	return 1;
-}
-
 
 /* Gather all the required information to prepare elf headers for ram regions */
 static void fill_up_crash_elf_data(struct crash_elf_data *ced,
@@ -226,22 +214,6 @@ static void fill_up_crash_elf_data(struct crash_elf_data *ced,
 
 	ced->max_nr_ranges = nr_ranges;
 
-	/*
-	 * We don't create ELF headers for GART aperture as an attempt
-	 * to dump this memory in second kernel leads to hang/crash.
-	 * If gart aperture is present, one needs to exclude that region
-	 * and that could lead to need of extra phdr.
-	 */
-	walk_iomem_res("GART", IORESOURCE_MEM, 0, -1,
-				ced, get_gart_ranges_callback);
-
-	/*
-	 * If we have gart region, excluding that could potentially split
-	 * a memory range, resulting in extra header. Account for  that.
-	 */
-	if (ced->gart_end)
-		ced->max_nr_ranges++;
-
 	/* Exclusion of crash region could split memory ranges */
 	ced->max_nr_ranges++;
 
@@ -350,13 +322,6 @@ static int elf_header_exclude_ranges(struct crash_elf_data *ced,
 			return ret;
 	}
 
-	/* Exclude GART region */
-	if (ced->gart_end) {
-		ret = exclude_mem_range(cmem, ced->gart_start, ced->gart_end);
-		if (ret)
-			return ret;
-	}
-
 	return ret;
 }
 
@@ -599,12 +564,12 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params)
 	/* Add ACPI tables */
 	cmd.type = E820_ACPI;
 	flags = IORESOURCE_MEM | IORESOURCE_BUSY;
-	walk_iomem_res("ACPI Tables", flags, 0, -1, &cmd,
+	walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1, &cmd,
 		       memmap_entry_callback);
 
 	/* Add ACPI Non-volatile Storage */
 	cmd.type = E820_NVS;
-	walk_iomem_res("ACPI Non-volatile Storage", flags, 0, -1, &cmd,
+	walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1, &cmd,
 			memmap_entry_callback);
 
 	/* Add crashk_low_res region */
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 9c30acfadae2..32e5699eadfe 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -265,9 +265,8 @@ int __die(const char *str, struct pt_regs *regs, long err)
 #ifdef CONFIG_SMP
 	printk("SMP ");
 #endif
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	printk("DEBUG_PAGEALLOC ");
-#endif
+	if (debug_pagealloc_enabled())
+		printk("DEBUG_PAGEALLOC ");
 #ifdef CONFIG_KASAN
 	printk("KASAN");
 #endif
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 569c1e4f96fe..621b501f8935 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -24,6 +24,7 @@
 #include <asm/e820.h>
 #include <asm/proto.h>
 #include <asm/setup.h>
+#include <asm/cpufeature.h>
 
 /*
  * The e820 map is the map that gets modified e.g. with command line parameters
@@ -925,6 +926,41 @@ static const char *e820_type_to_string(int e820_type)
 	}
 }
 
+static unsigned long e820_type_to_iomem_type(int e820_type)
+{
+	switch (e820_type) {
+	case E820_RESERVED_KERN:
+	case E820_RAM:
+		return IORESOURCE_SYSTEM_RAM;
+	case E820_ACPI:
+	case E820_NVS:
+	case E820_UNUSABLE:
+	case E820_PRAM:
+	case E820_PMEM:
+	default:
+		return IORESOURCE_MEM;
+	}
+}
+
+static unsigned long e820_type_to_iores_desc(int e820_type)
+{
+	switch (e820_type) {
+	case E820_ACPI:
+		return IORES_DESC_ACPI_TABLES;
+	case E820_NVS:
+		return IORES_DESC_ACPI_NV_STORAGE;
+	case E820_PMEM:
+		return IORES_DESC_PERSISTENT_MEMORY;
+	case E820_PRAM:
+		return IORES_DESC_PERSISTENT_MEMORY_LEGACY;
+	case E820_RESERVED_KERN:
+	case E820_RAM:
+	case E820_UNUSABLE:
+	default:
+		return IORES_DESC_NONE;
+	}
+}
+
 static bool do_mark_busy(u32 type, struct resource *res)
 {
 	/* this is the legacy bios/dos rom-shadow + mmio region */
@@ -967,7 +1003,8 @@ void __init e820_reserve_resources(void)
 		res->start = e820.map[i].addr;
 		res->end = end;
 
-		res->flags = IORESOURCE_MEM;
+		res->flags = e820_type_to_iomem_type(e820.map[i].type);
+		res->desc = e820_type_to_iores_desc(e820.map[i].type);
 
 		/*
 		 * don't register the region that could be conflicted with
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index d25097c3fc1d..0b1b9abd4d5f 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -114,6 +114,10 @@ void __kernel_fpu_begin(void)
 	kernel_fpu_disable();
 
 	if (fpu->fpregs_active) {
+		/*
+		 * Ignore return value -- we don't care if reg state
+		 * is clobbered.
+		 */
 		copy_fpregs_to_fpstate(fpu);
 	} else {
 		this_cpu_write(fpu_fpregs_owner_ctx, NULL);
@@ -189,8 +193,12 @@ void fpu__save(struct fpu *fpu)
 
 	preempt_disable();
 	if (fpu->fpregs_active) {
-		if (!copy_fpregs_to_fpstate(fpu))
-			fpregs_deactivate(fpu);
+		if (!copy_fpregs_to_fpstate(fpu)) {
+			if (use_eager_fpu())
+				copy_kernel_to_fpregs(&fpu->state);
+			else
+				fpregs_deactivate(fpu);
+		}
 	}
 	preempt_enable();
 }
@@ -223,14 +231,15 @@ void fpstate_init(union fpregs_state *state)
 }
 EXPORT_SYMBOL_GPL(fpstate_init);
 
-/*
- * Copy the current task's FPU state to a new task's FPU context.
- *
- * In both the 'eager' and the 'lazy' case we save hardware registers
- * directly to the destination buffer.
- */
-static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
+int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 {
+	dst_fpu->counter = 0;
+	dst_fpu->fpregs_active = 0;
+	dst_fpu->last_cpu = -1;
+
+	if (!src_fpu->fpstate_active || !cpu_has_fpu)
+		return 0;
+
 	WARN_ON_FPU(src_fpu != &current->thread.fpu);
 
 	/*
@@ -243,10 +252,9 @@ static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	/*
 	 * Save current FPU registers directly into the child
 	 * FPU context, without any memory-to-memory copying.
-	 *
-	 * If the FPU context got destroyed in the process (FNSAVE
-	 * done on old CPUs) then copy it back into the source
-	 * context and mark the current task for lazy restore.
+	 * In lazy mode, if the FPU context isn't loaded into
+	 * fpregs, CR0.TS will be set and do_device_not_available
+	 * will load the FPU context.
 	 *
 	 * We have to do all this with preemption disabled,
 	 * mostly because of the FNSAVE case, because in that
@@ -259,19 +267,13 @@ static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	preempt_disable();
 	if (!copy_fpregs_to_fpstate(dst_fpu)) {
 		memcpy(&src_fpu->state, &dst_fpu->state, xstate_size);
-		fpregs_deactivate(src_fpu);
+
+		if (use_eager_fpu())
+			copy_kernel_to_fpregs(&src_fpu->state);
+		else
+			fpregs_deactivate(src_fpu);
 	}
 	preempt_enable();
-}
-
-int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
-{
-	dst_fpu->counter = 0;
-	dst_fpu->fpregs_active = 0;
-	dst_fpu->last_cpu = -1;
-
-	if (src_fpu->fpstate_active && cpu_has_fpu)
-		fpu_copy(dst_fpu, src_fpu);
 
 	return 0;
 }
@@ -409,8 +411,10 @@ static inline void copy_init_fpstate_to_fpregs(void)
 {
 	if (use_xsave())
 		copy_kernel_to_xregs(&init_fpstate.xsave, -1);
-	else
+	else if (static_cpu_has(X86_FEATURE_FXSR))
 		copy_kernel_to_fxregs(&init_fpstate.fxsave);
+	else
+		copy_kernel_to_fregs(&init_fpstate.fsave);
 }
 
 /*
@@ -423,7 +427,7 @@ void fpu__clear(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu != &current->thread.fpu); /* Almost certainly an anomaly */
 
-	if (!use_eager_fpu()) {
+	if (!use_eager_fpu() || !static_cpu_has(X86_FEATURE_FPU)) {
 		/* FPU state will be reallocated lazily at the first use. */
 		fpu__drop(fpu);
 	} else {
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 6d9f0a7ef4c8..54c86fffbf9f 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -78,13 +78,15 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
 	cr0 &= ~(X86_CR0_TS | X86_CR0_EM);
 	write_cr0(cr0);
 
-	asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
-		     : "+m" (fsw), "+m" (fcw));
+	if (!test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) {
+		asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
+			     : "+m" (fsw), "+m" (fcw));
 
-	if (fsw == 0 && (fcw & 0x103f) == 0x003f)
-		set_cpu_cap(c, X86_FEATURE_FPU);
-	else
-		clear_cpu_cap(c, X86_FEATURE_FPU);
+		if (fsw == 0 && (fcw & 0x103f) == 0x003f)
+			set_cpu_cap(c, X86_FEATURE_FPU);
+		else
+			clear_cpu_cap(c, X86_FEATURE_FPU);
+	}
 
 #ifndef CONFIG_MATH_EMULATION
 	if (!cpu_has_fpu) {
@@ -132,7 +134,7 @@ static void __init fpu__init_system_generic(void)
 	 * Set up the legacy init FPU context. (xstate init might overwrite this
 	 * with a more modern format, if the CPU supports it.)
 	 */
-	fpstate_init_fxstate(&init_fpstate.fxsave);
+	fpstate_init(&init_fpstate);
 
 	fpu__init_system_mxcsr();
 }
@@ -260,7 +262,10 @@ static void __init fpu__init_system_xstate_size_legacy(void)
  * not only saved the restores along the way, but we also have the
  * FPU ready to be used for the original task.
  *
- * 'eager' switching is used on modern CPUs, there we switch the FPU
+ * 'lazy' is deprecated because it's almost never a performance win
+ * and it's much more complicated than 'eager'.
+ *
+ * 'eager' switching is by default on all CPUs, there we switch the FPU
  * state during every context switch, regardless of whether the task
  * has used FPU instructions in that time slice or not. This is done
  * because modern FPU context saving instructions are able to optimize
@@ -271,7 +276,7 @@ static void __init fpu__init_system_xstate_size_legacy(void)
  *   to use 'eager' restores, if we detect that a task is using the FPU
  *   frequently. See the fpu->counter logic in fpu/internal.h for that. ]
  */
-static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
+static enum { ENABLE, DISABLE } eagerfpu = ENABLE;
 
 /*
  * Find supported xfeatures based on cpu features and command-line input.
@@ -300,12 +305,6 @@ u64 __init fpu__get_supported_xfeatures_mask(void)
 static void __init fpu__clear_eager_fpu_features(void)
 {
 	setup_clear_cpu_cap(X86_FEATURE_MPX);
-	setup_clear_cpu_cap(X86_FEATURE_AVX);
-	setup_clear_cpu_cap(X86_FEATURE_AVX2);
-	setup_clear_cpu_cap(X86_FEATURE_AVX512F);
-	setup_clear_cpu_cap(X86_FEATURE_AVX512PF);
-	setup_clear_cpu_cap(X86_FEATURE_AVX512ER);
-	setup_clear_cpu_cap(X86_FEATURE_AVX512CD);
 }
 
 /*
@@ -348,15 +347,9 @@ static void __init fpu__init_system_ctx_switch(void)
  */
 static void __init fpu__init_parse_early_param(void)
 {
-	/*
-	 * No need to check "eagerfpu=auto" again, since it is the
-	 * initial default.
-	 */
 	if (cmdline_find_option_bool(boot_command_line, "eagerfpu=off")) {
 		eagerfpu = DISABLE;
 		fpu__clear_eager_fpu_features();
-	} else if (cmdline_find_option_bool(boot_command_line, "eagerfpu=on")) {
-		eagerfpu = ENABLE;
 	}
 
 	if (cmdline_find_option_bool(boot_command_line, "no387"))
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index d425cda5ae6d..6e8354f5a593 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -51,6 +51,9 @@ void fpu__xstate_clear_all_cpu_caps(void)
 	setup_clear_cpu_cap(X86_FEATURE_AVX512PF);
 	setup_clear_cpu_cap(X86_FEATURE_AVX512ER);
 	setup_clear_cpu_cap(X86_FEATURE_AVX512CD);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512DQ);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512BW);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512VL);
 	setup_clear_cpu_cap(X86_FEATURE_MPX);
 	setup_clear_cpu_cap(X86_FEATURE_XGETBV1);
 }
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 29408d6d6626..702547ce33c9 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -81,9 +81,9 @@ within(unsigned long addr, unsigned long start, unsigned long end)
 static unsigned long text_ip_addr(unsigned long ip)
 {
 	/*
-	 * On x86_64, kernel text mappings are mapped read-only with
-	 * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead
-	 * of the kernel text mapping to modify the kernel text.
+	 * On x86_64, kernel text mappings are mapped read-only, so we use
+	 * the kernel identity mapping instead of the kernel text mapping
+	 * to modify the kernel text.
 	 *
 	 * For 32bit kernels, these mappings are same and we can use
 	 * kernel identity mapping to modify code.
@@ -697,9 +697,8 @@ static inline void tramp_free(void *tramp) { }
 #endif
 
 /* Defined as markers to the end of the ftrace default trampolines */
-extern void ftrace_caller_end(void);
 extern void ftrace_regs_caller_end(void);
-extern void ftrace_return(void);
+extern void ftrace_epilogue(void);
 extern void ftrace_caller_op_ptr(void);
 extern void ftrace_regs_caller_op_ptr(void);
 
@@ -746,7 +745,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 		op_offset = (unsigned long)ftrace_regs_caller_op_ptr;
 	} else {
 		start_offset = (unsigned long)ftrace_caller;
-		end_offset = (unsigned long)ftrace_caller_end;
+		end_offset = (unsigned long)ftrace_epilogue;
 		op_offset = (unsigned long)ftrace_caller_op_ptr;
 	}
 
@@ -754,7 +753,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 
 	/*
 	 * Allocate enough size to store the ftrace_caller code,
-	 * the jmp to ftrace_return, as well as the address of
+	 * the jmp to ftrace_epilogue, as well as the address of
 	 * the ftrace_ops this trampoline is used for.
 	 */
 	trampoline = alloc_tramp(size + MCOUNT_INSN_SIZE + sizeof(void *));
@@ -772,8 +771,8 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 
 	ip = (unsigned long)trampoline + size;
 
-	/* The trampoline ends with a jmp to ftrace_return */
-	jmp = ftrace_jmp_replace(ip, (unsigned long)ftrace_return);
+	/* The trampoline ends with a jmp to ftrace_epilogue */
+	jmp = ftrace_jmp_replace(ip, (unsigned long)ftrace_epilogue);
 	memcpy(trampoline + size, jmp, MCOUNT_INSN_SIZE);
 
 	/*
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 2c0f3407bd1f..1f4422d5c8d0 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -40,13 +40,8 @@ pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
 /* Wipe all early page tables except for the kernel symbol map */
 static void __init reset_early_page_tables(void)
 {
-	unsigned long i;
-
-	for (i = 0; i < PTRS_PER_PGD-1; i++)
-		early_level4_pgt[i].pgd = 0;
-
+	memset(early_level4_pgt, 0, sizeof(pgd_t)*(PTRS_PER_PGD-1));
 	next_early_pgt = 0;
-
 	write_cr3(__pa_nodebug(early_level4_pgt));
 }
 
@@ -54,7 +49,6 @@ static void __init reset_early_page_tables(void)
 int __init early_make_pgtable(unsigned long address)
 {
 	unsigned long physaddr = address - __PAGE_OFFSET;
-	unsigned long i;
 	pgdval_t pgd, *pgd_p;
 	pudval_t pud, *pud_p;
 	pmdval_t pmd, *pmd_p;
@@ -81,8 +75,7 @@ again:
 		}
 
 		pud_p = (pudval_t *)early_dynamic_pgts[next_early_pgt++];
-		for (i = 0; i < PTRS_PER_PUD; i++)
-			pud_p[i] = 0;
+		memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD);
 		*pgd_p = (pgdval_t)pud_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE;
 	}
 	pud_p += pud_index(address);
@@ -97,8 +90,7 @@ again:
 		}
 
 		pmd_p = (pmdval_t *)early_dynamic_pgts[next_early_pgt++];
-		for (i = 0; i < PTRS_PER_PMD; i++)
-			pmd_p[i] = 0;
+		memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD);
 		*pud_p = (pudval_t)pmd_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE;
 	}
 	pmd = (physaddr & PMD_MASK) + early_pmd_flags;
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 6bc9ae24b6d2..54cdbd2003fe 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -19,7 +19,7 @@
 #include <asm/setup.h>
 #include <asm/processor-flags.h>
 #include <asm/msr-index.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/percpu.h>
 #include <asm/nops.h>
 #include <asm/bootparam.h>
@@ -389,6 +389,12 @@ default_entry:
 	/* Make changes effective */
 	wrmsr
 
+	/*
+	 * And make sure that all the mappings we set up have NX set from
+	 * the beginning.
+	 */
+	orl $(1 << (_PAGE_BIT_NX - 32)), pa(__supported_pte_mask + 4)
+
 enable_paging:
 
 /*
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index ffdc0e860390..22fbf9df61bb 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -38,7 +38,6 @@
 #define pud_index(x)	(((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
 
 L4_PAGE_OFFSET = pgd_index(__PAGE_OFFSET)
-L3_PAGE_OFFSET = pud_index(__PAGE_OFFSET)
 L4_START_KERNEL = pgd_index(__START_KERNEL_map)
 L3_START_KERNEL = pud_index(__START_KERNEL_map)
 
@@ -76,9 +75,7 @@ startup_64:
 	subq	$_text - __START_KERNEL_map, %rbp
 
 	/* Is the address not 2M aligned? */
-	movq	%rbp, %rax
-	andl	$~PMD_PAGE_MASK, %eax
-	testl	%eax, %eax
+	testl	$~PMD_PAGE_MASK, %ebp
 	jnz	bad_address
 
 	/*
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index b8e6ff5cd5d0..be0ebbb6d1d1 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -12,6 +12,7 @@
 #include <linux/pm.h>
 #include <linux/io.h>
 
+#include <asm/cpufeature.h>
 #include <asm/irqdomain.h>
 #include <asm/fixmap.h>
 #include <asm/hpet.h>
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 44256a62702b..ed15cd486d06 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -750,9 +750,7 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 {
 	int err;
-#ifdef CONFIG_DEBUG_RODATA
 	char opc[BREAK_INSTR_SIZE];
-#endif /* CONFIG_DEBUG_RODATA */
 
 	bpt->type = BP_BREAKPOINT;
 	err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
@@ -761,7 +759,6 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 		return err;
 	err = probe_kernel_write((char *)bpt->bpt_addr,
 				 arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE);
-#ifdef CONFIG_DEBUG_RODATA
 	if (!err)
 		return err;
 	/*
@@ -778,13 +775,12 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 	if (memcmp(opc, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE))
 		return -EINVAL;
 	bpt->type = BP_POKE_BREAKPOINT;
-#endif /* CONFIG_DEBUG_RODATA */
+
 	return err;
 }
 
 int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
 {
-#ifdef CONFIG_DEBUG_RODATA
 	int err;
 	char opc[BREAK_INSTR_SIZE];
 
@@ -801,8 +797,8 @@ int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
 	if (err || memcmp(opc, bpt->saved_instr, BREAK_INSTR_SIZE))
 		goto knl_write;
 	return err;
+
 knl_write:
-#endif /* CONFIG_DEBUG_RODATA */
 	return probe_kernel_write((char *)bpt->bpt_addr,
 				  (char *)bpt->saved_instr, BREAK_INSTR_SIZE);
 }
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 1deffe6cc873..0f05deeff5ce 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -988,7 +988,7 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 		 * In case the user-specified fault handler returned
 		 * zero, try to fix up.
 		 */
-		if (fixup_exception(regs))
+		if (fixup_exception(regs, trapnr))
 			return 1;
 
 		/*
diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S
index 87e1762e2bca..ed48a9f465f8 100644
--- a/arch/x86/kernel/mcount_64.S
+++ b/arch/x86/kernel/mcount_64.S
@@ -168,12 +168,14 @@ GLOBAL(ftrace_call)
 	restore_mcount_regs
 
 	/*
-	 * The copied trampoline must call ftrace_return as it
+	 * The copied trampoline must call ftrace_epilogue as it
 	 * still may need to call the function graph tracer.
+	 *
+	 * The code up to this label is copied into trampolines so
+	 * think twice before adding any new code or changing the
+	 * layout here.
 	 */
-GLOBAL(ftrace_caller_end)
-
-GLOBAL(ftrace_return)
+GLOBAL(ftrace_epilogue)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 GLOBAL(ftrace_graph_call)
@@ -244,14 +246,14 @@ GLOBAL(ftrace_regs_call)
 	popfq
 
 	/*
-	 * As this jmp to ftrace_return can be a short jump
+	 * As this jmp to ftrace_epilogue can be a short jump
 	 * it must not be copied into the trampoline.
 	 * The trampoline will add the code to jump
 	 * to the return.
 	 */
 GLOBAL(ftrace_regs_caller_end)
 
-	jmp ftrace_return
+	jmp ftrace_epilogue
 
 END(ftrace_regs_caller)
 
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 30ca7607cbbb..97340f2c437c 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -408,7 +408,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type)
 	processor.cpuflag = CPU_ENABLED;
 	processor.cpufeature = (boot_cpu_data.x86 << 8) |
 	    (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask;
-	processor.featureflag = boot_cpu_data.x86_capability[0];
+	processor.featureflag = boot_cpu_data.x86_capability[CPUID_1_EDX];
 	processor.reserved[0] = 0;
 	processor.reserved[1] = 0;
 	for (i = 0; i < 2; i++) {
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 64f9616f93f1..7f3550acde1b 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -40,7 +40,7 @@
 #include <linux/uaccess.h>
 #include <linux/gfp.h>
 
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/msr.h>
 
 static struct class *msr_class;
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 8a2cdd736fa4..04b132a767f1 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -30,6 +30,7 @@
 #include <asm/nmi.h>
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
+#include <asm/cache.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/nmi.h>
@@ -69,7 +70,7 @@ struct nmi_stats {
 
 static DEFINE_PER_CPU(struct nmi_stats, nmi_stats);
 
-static int ignore_nmis;
+static int ignore_nmis __read_mostly;
 
 int unknown_nmi_panic;
 /*
diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c
index 14415aff1813..92f70147a9a6 100644
--- a/arch/x86/kernel/pmem.c
+++ b/arch/x86/kernel/pmem.c
@@ -13,11 +13,11 @@ static int found(u64 start, u64 end, void *data)
 
 static __init int register_e820_pmem(void)
 {
-	char *pmem = "Persistent Memory (legacy)";
 	struct platform_device *pdev;
 	int rc;
 
-	rc = walk_iomem_res(pmem, IORESOURCE_MEM, 0, -1, NULL, found);
+	rc = walk_iomem_res_desc(IORES_DESC_PERSISTENT_MEMORY_LEGACY,
+				 IORESOURCE_MEM, 0, -1, NULL, found);
 	if (rc <= 0)
 		return 0;
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 9f7c21c22477..2915d54e9dd5 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -57,6 +57,9 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
 	  */
 	.io_bitmap		= { [0 ... IO_BITMAP_LONGS] = ~0 },
 #endif
+#ifdef CONFIG_X86_32
+	.SYSENTER_stack_canary	= STACK_END_MAGIC,
+#endif
 };
 EXPORT_PER_CPU_SYMBOL(cpu_tss);
 
@@ -418,9 +421,9 @@ static void mwait_idle(void)
 	if (!current_set_polling_and_test()) {
 		trace_cpu_idle_rcuidle(1, smp_processor_id());
 		if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) {
-			smp_mb(); /* quirk */
+			mb(); /* quirk */
 			clflush((void *)&current_thread_info()->flags);
-			smp_mb(); /* quirk */
+			mb(); /* quirk */
 		}
 
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d3d80e6d42a2..aa52c1009475 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -152,21 +152,21 @@ static struct resource data_resource = {
 	.name	= "Kernel data",
 	.start	= 0,
 	.end	= 0,
-	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
 };
 
 static struct resource code_resource = {
 	.name	= "Kernel code",
 	.start	= 0,
 	.end	= 0,
-	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
 };
 
 static struct resource bss_resource = {
 	.name	= "Kernel bss",
 	.start	= 0,
 	.end	= 0,
-	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
 };
 
 
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index cb6282c3638f..548ddf7d6fd2 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -61,7 +61,38 @@
 	regs->seg = GET_SEG(seg) | 3;			\
 } while (0)
 
-int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
+#ifdef CONFIG_X86_64
+/*
+ * If regs->ss will cause an IRET fault, change it.  Otherwise leave it
+ * alone.  Using this generally makes no sense unless
+ * user_64bit_mode(regs) would return true.
+ */
+static void force_valid_ss(struct pt_regs *regs)
+{
+	u32 ar;
+	asm volatile ("lar %[old_ss], %[ar]\n\t"
+		      "jz 1f\n\t"		/* If invalid: */
+		      "xorl %[ar], %[ar]\n\t"	/* set ar = 0 */
+		      "1:"
+		      : [ar] "=r" (ar)
+		      : [old_ss] "rm" ((u16)regs->ss));
+
+	/*
+	 * For a valid 64-bit user context, we need DPL 3, type
+	 * read-write data or read-write exp-down data, and S and P
+	 * set.  We can't use VERW because VERW doesn't check the
+	 * P bit.
+	 */
+	ar &= AR_DPL_MASK | AR_S | AR_P | AR_TYPE_MASK;
+	if (ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA) &&
+	    ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA_EXPDOWN))
+		regs->ss = __USER_DS;
+}
+#endif
+
+static int restore_sigcontext(struct pt_regs *regs,
+			      struct sigcontext __user *sc,
+			      unsigned long uc_flags)
 {
 	unsigned long buf_val;
 	void __user *buf;
@@ -94,15 +125,18 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 		COPY(r15);
 #endif /* CONFIG_X86_64 */
 
-#ifdef CONFIG_X86_32
 		COPY_SEG_CPL3(cs);
 		COPY_SEG_CPL3(ss);
-#else /* !CONFIG_X86_32 */
-		/* Kernel saves and restores only the CS segment register on signals,
-		 * which is the bare minimum needed to allow mixed 32/64-bit code.
-		 * App's signal handler can save/restore other segments if needed. */
-		COPY_SEG_CPL3(cs);
-#endif /* CONFIG_X86_32 */
+
+#ifdef CONFIG_X86_64
+		/*
+		 * Fix up SS if needed for the benefit of old DOSEMU and
+		 * CRIU.
+		 */
+		if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) &&
+			     user_64bit_mode(regs)))
+			force_valid_ss(regs);
+#endif
 
 		get_user_ex(tmpflags, &sc->flags);
 		regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
@@ -165,6 +199,7 @@ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
 		put_user_ex(regs->cs, &sc->cs);
 		put_user_ex(0, &sc->gs);
 		put_user_ex(0, &sc->fs);
+		put_user_ex(regs->ss, &sc->ss);
 #endif /* CONFIG_X86_32 */
 
 		put_user_ex(fpstate, &sc->fpstate);
@@ -403,6 +438,21 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 	return 0;
 }
 #else /* !CONFIG_X86_32 */
+static unsigned long frame_uc_flags(struct pt_regs *regs)
+{
+	unsigned long flags;
+
+	if (cpu_has_xsave)
+		flags = UC_FP_XSTATE | UC_SIGCONTEXT_SS;
+	else
+		flags = UC_SIGCONTEXT_SS;
+
+	if (likely(user_64bit_mode(regs)))
+		flags |= UC_STRICT_RESTORE_SS;
+
+	return flags;
+}
+
 static int __setup_rt_frame(int sig, struct ksignal *ksig,
 			    sigset_t *set, struct pt_regs *regs)
 {
@@ -422,10 +472,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 
 	put_user_try {
 		/* Create the ucontext.  */
-		if (cpu_has_xsave)
-			put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
-		else
-			put_user_ex(0, &frame->uc.uc_flags);
+		put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
 		save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 
@@ -459,10 +506,28 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 
 	regs->sp = (unsigned long)frame;
 
-	/* Set up the CS register to run signal handlers in 64-bit mode,
-	   even if the handler happens to be interrupting 32-bit code. */
+	/*
+	 * Set up the CS and SS registers to run signal handlers in
+	 * 64-bit mode, even if the handler happens to be interrupting
+	 * 32-bit or 16-bit code.
+	 *
+	 * SS is subtle.  In 64-bit mode, we don't need any particular
+	 * SS descriptor, but we do need SS to be valid.  It's possible
+	 * that the old SS is entirely bogus -- this can happen if the
+	 * signal we're trying to deliver is #GP or #SS caused by a bad
+	 * SS value.  We also have a compatbility issue here: DOSEMU
+	 * relies on the contents of the SS register indicating the
+	 * SS value at the time of the signal, even though that code in
+	 * DOSEMU predates sigreturn's ability to restore SS.  (DOSEMU
+	 * avoids relying on sigreturn to restore SS; instead it uses
+	 * a trampoline.)  So we do our best: if the old SS was valid,
+	 * we keep it.  Otherwise we replace it.
+	 */
 	regs->cs = __USER_CS;
 
+	if (unlikely(regs->ss != __USER_DS))
+		force_valid_ss(regs);
+
 	return 0;
 }
 #endif /* CONFIG_X86_32 */
@@ -489,10 +554,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
 
 	put_user_try {
 		/* Create the ucontext.  */
-		if (cpu_has_xsave)
-			put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
-		else
-			put_user_ex(0, &frame->uc.uc_flags);
+		put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
 		compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 		put_user_ex(0, &frame->uc.uc__pad0);
@@ -554,7 +616,11 @@ asmlinkage unsigned long sys_sigreturn(void)
 
 	set_current_blocked(&set);
 
-	if (restore_sigcontext(regs, &frame->sc))
+	/*
+	 * x86_32 has no uc_flags bits relevant to restore_sigcontext.
+	 * Save a few cycles by skipping the __get_user.
+	 */
+	if (restore_sigcontext(regs, &frame->sc, 0))
 		goto badframe;
 	return regs->ax;
 
@@ -570,16 +636,19 @@ asmlinkage long sys_rt_sigreturn(void)
 	struct pt_regs *regs = current_pt_regs();
 	struct rt_sigframe __user *frame;
 	sigset_t set;
+	unsigned long uc_flags;
 
 	frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
 		goto badframe;
+	if (__get_user(uc_flags, &frame->uc.uc_flags))
+		goto badframe;
 
 	set_current_blocked(&set);
 
-	if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
+	if (restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags))
 		goto badframe;
 
 	if (restore_altstack(&frame->uc.uc_stack))
@@ -692,12 +761,15 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 
 static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
 {
-#if defined(CONFIG_X86_32) || !defined(CONFIG_X86_64)
+#ifdef CONFIG_X86_64
+	if (is_ia32_task())
+		return __NR_ia32_restart_syscall;
+#endif
+#ifdef CONFIG_X86_X32_ABI
+	return __NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT);
+#else
 	return __NR_restart_syscall;
-#else /* !CONFIG_X86_32 && CONFIG_X86_64 */
-	return test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall :
-		__NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT);
-#endif /* CONFIG_X86_32 || !CONFIG_X86_64 */
+#endif
 }
 
 /*
@@ -763,6 +835,7 @@ asmlinkage long sys32_x32_rt_sigreturn(void)
 	struct pt_regs *regs = current_pt_regs();
 	struct rt_sigframe_x32 __user *frame;
 	sigset_t set;
+	unsigned long uc_flags;
 
 	frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);
 
@@ -770,10 +843,12 @@ asmlinkage long sys32_x32_rt_sigreturn(void)
 		goto badframe;
 	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
 		goto badframe;
+	if (__get_user(uc_flags, &frame->uc.uc_flags))
+		goto badframe;
 
 	set_current_blocked(&set);
 
-	if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
+	if (restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags))
 		goto badframe;
 
 	if (compat_restore_altstack(&frame->uc.uc_stack))
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 24d57f77b3c1..643dbdccf4bc 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -97,6 +97,14 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
 EXPORT_PER_CPU_SYMBOL(cpu_info);
 
+/* Logical package management. We might want to allocate that dynamically */
+static int *physical_to_logical_pkg __read_mostly;
+static unsigned long *physical_package_map __read_mostly;;
+static unsigned long *logical_package_map  __read_mostly;
+static unsigned int max_physical_pkg_id __read_mostly;
+unsigned int __max_logical_packages __read_mostly;
+EXPORT_SYMBOL(__max_logical_packages);
+
 static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
 {
 	unsigned long flags;
@@ -248,7 +256,98 @@ static void notrace start_secondary(void *unused)
 	x86_cpuinit.setup_percpu_clockev();
 
 	wmb();
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+}
+
+int topology_update_package_map(unsigned int apicid, unsigned int cpu)
+{
+	unsigned int new, pkg = apicid >> boot_cpu_data.x86_coreid_bits;
+
+	/* Called from early boot ? */
+	if (!physical_package_map)
+		return 0;
+
+	if (pkg >= max_physical_pkg_id)
+		return -EINVAL;
+
+	/* Set the logical package id */
+	if (test_and_set_bit(pkg, physical_package_map))
+		goto found;
+
+	if (pkg < __max_logical_packages) {
+		set_bit(pkg, logical_package_map);
+		physical_to_logical_pkg[pkg] = pkg;
+		goto found;
+	}
+	new = find_first_zero_bit(logical_package_map, __max_logical_packages);
+	if (new >= __max_logical_packages) {
+		physical_to_logical_pkg[pkg] = -1;
+		pr_warn("APIC(%x) Package %u exceeds logical package map\n",
+			apicid, pkg);
+		return -ENOSPC;
+	}
+	set_bit(new, logical_package_map);
+	pr_info("APIC(%x) Converting physical %u to logical package %u\n",
+		apicid, pkg, new);
+	physical_to_logical_pkg[pkg] = new;
+
+found:
+	cpu_data(cpu).logical_proc_id = physical_to_logical_pkg[pkg];
+	return 0;
+}
+
+/**
+ * topology_phys_to_logical_pkg - Map a physical package id to a logical
+ *
+ * Returns logical package id or -1 if not found
+ */
+int topology_phys_to_logical_pkg(unsigned int phys_pkg)
+{
+	if (phys_pkg >= max_physical_pkg_id)
+		return -1;
+	return physical_to_logical_pkg[phys_pkg];
+}
+EXPORT_SYMBOL(topology_phys_to_logical_pkg);
+
+static void __init smp_init_package_map(void)
+{
+	unsigned int ncpus, cpu;
+	size_t size;
+
+	/*
+	 * Today neither Intel nor AMD support heterogenous systems. That
+	 * might change in the future....
+	 */
+	ncpus = boot_cpu_data.x86_max_cores * smp_num_siblings;
+	__max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus);
+
+	/*
+	 * Possibly larger than what we need as the number of apic ids per
+	 * package can be smaller than the actual used apic ids.
+	 */
+	max_physical_pkg_id = DIV_ROUND_UP(MAX_LOCAL_APIC, ncpus);
+	size = max_physical_pkg_id * sizeof(unsigned int);
+	physical_to_logical_pkg = kmalloc(size, GFP_KERNEL);
+	memset(physical_to_logical_pkg, 0xff, size);
+	size = BITS_TO_LONGS(max_physical_pkg_id) * sizeof(unsigned long);
+	physical_package_map = kzalloc(size, GFP_KERNEL);
+	size = BITS_TO_LONGS(__max_logical_packages) * sizeof(unsigned long);
+	logical_package_map = kzalloc(size, GFP_KERNEL);
+
+	pr_info("Max logical packages: %u\n", __max_logical_packages);
+
+	for_each_present_cpu(cpu) {
+		unsigned int apicid = apic->cpu_present_to_apicid(cpu);
+
+		if (apicid == BAD_APICID || !apic->apic_id_valid(apicid))
+			continue;
+		if (!topology_update_package_map(apicid, cpu))
+			continue;
+		pr_warn("CPU %u APICId %x disabled\n", cpu, apicid);
+		per_cpu(x86_bios_cpu_apicid, cpu) = BAD_APICID;
+		set_cpu_possible(cpu, false);
+		set_cpu_present(cpu, false);
+	}
 }
 
 void __init smp_store_boot_cpu_info(void)
@@ -258,6 +357,7 @@ void __init smp_store_boot_cpu_info(void)
 
 	*c = boot_cpu_data;
 	c->cpu_index = id;
+	smp_init_package_map();
 }
 
 /*
diff --git a/arch/x86/kernel/test_nx.c b/arch/x86/kernel/test_nx.c
index 3f92ce07e525..27538f183c3b 100644
--- a/arch/x86/kernel/test_nx.c
+++ b/arch/x86/kernel/test_nx.c
@@ -142,7 +142,6 @@ static int test_NX(void)
 	 * by the error message
 	 */
 
-#ifdef CONFIG_DEBUG_RODATA
 	/* Test 3: Check if the .rodata section is executable */
 	if (rodata_test_data != 0xC3) {
 		printk(KERN_ERR "test_nx: .rodata marker has invalid value\n");
@@ -151,7 +150,6 @@ static int test_NX(void)
 		printk(KERN_ERR "test_nx: .rodata section is executable\n");
 		ret = -ENODEV;
 	}
-#endif
 
 #if 0
 	/* Test 4: Check if the .data section of a module is executable */
diff --git a/arch/x86/kernel/test_rodata.c b/arch/x86/kernel/test_rodata.c
index 5ecbfe5099da..cb4a01b41e27 100644
--- a/arch/x86/kernel/test_rodata.c
+++ b/arch/x86/kernel/test_rodata.c
@@ -76,5 +76,5 @@ int rodata_test(void)
 }
 
 MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Testcase for the DEBUG_RODATA infrastructure");
+MODULE_DESCRIPTION("Testcase for marking rodata as read-only");
 MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>");
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index ade185a46b1d..06cbe25861f1 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -83,30 +83,16 @@ gate_desc idt_table[NR_VECTORS] __page_aligned_bss;
 DECLARE_BITMAP(used_vectors, NR_VECTORS);
 EXPORT_SYMBOL_GPL(used_vectors);
 
-static inline void conditional_sti(struct pt_regs *regs)
+static inline void cond_local_irq_enable(struct pt_regs *regs)
 {
 	if (regs->flags & X86_EFLAGS_IF)
 		local_irq_enable();
 }
 
-static inline void preempt_conditional_sti(struct pt_regs *regs)
-{
-	preempt_count_inc();
-	if (regs->flags & X86_EFLAGS_IF)
-		local_irq_enable();
-}
-
-static inline void conditional_cli(struct pt_regs *regs)
-{
-	if (regs->flags & X86_EFLAGS_IF)
-		local_irq_disable();
-}
-
-static inline void preempt_conditional_cli(struct pt_regs *regs)
+static inline void cond_local_irq_disable(struct pt_regs *regs)
 {
 	if (regs->flags & X86_EFLAGS_IF)
 		local_irq_disable();
-	preempt_count_dec();
 }
 
 void ist_enter(struct pt_regs *regs)
@@ -199,7 +185,7 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
 	}
 
 	if (!user_mode(regs)) {
-		if (!fixup_exception(regs)) {
+		if (!fixup_exception(regs, trapnr)) {
 			tsk->thread.error_code = error_code;
 			tsk->thread.trap_nr = trapnr;
 			die(str, regs, error_code);
@@ -262,7 +248,6 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
 	tsk->thread.error_code = error_code;
 	tsk->thread.trap_nr = trapnr;
 
-#ifdef CONFIG_X86_64
 	if (show_unhandled_signals && unhandled_signal(tsk, signr) &&
 	    printk_ratelimit()) {
 		pr_info("%s[%d] trap %s ip:%lx sp:%lx error:%lx",
@@ -271,7 +256,6 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
 		print_vma_addr(" in ", regs->ip);
 		pr_cont("\n");
 	}
-#endif
 
 	force_sig_info(signr, info ?: SEND_SIG_PRIV, tsk);
 }
@@ -286,7 +270,7 @@ static void do_error_trap(struct pt_regs *regs, long error_code, char *str,
 
 	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) !=
 			NOTIFY_STOP) {
-		conditional_sti(regs);
+		cond_local_irq_enable(regs);
 		do_trap(trapnr, signr, str, regs, error_code,
 			fill_trap_info(regs, signr, trapnr, &info));
 	}
@@ -368,7 +352,7 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 	if (notify_die(DIE_TRAP, "bounds", regs, error_code,
 			X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP)
 		return;
-	conditional_sti(regs);
+	cond_local_irq_enable(regs);
 
 	if (!user_mode(regs))
 		die("bounds", regs, error_code);
@@ -443,7 +427,7 @@ do_general_protection(struct pt_regs *regs, long error_code)
 	struct task_struct *tsk;
 
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
-	conditional_sti(regs);
+	cond_local_irq_enable(regs);
 
 	if (v8086_mode(regs)) {
 		local_irq_enable();
@@ -453,7 +437,7 @@ do_general_protection(struct pt_regs *regs, long error_code)
 
 	tsk = current;
 	if (!user_mode(regs)) {
-		if (fixup_exception(regs))
+		if (fixup_exception(regs, X86_TRAP_GP))
 			return;
 
 		tsk->thread.error_code = error_code;
@@ -517,9 +501,11 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 	 * as we may switch to the interrupt stack.
 	 */
 	debug_stack_usage_inc();
-	preempt_conditional_sti(regs);
+	preempt_disable();
+	cond_local_irq_enable(regs);
 	do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
-	preempt_conditional_cli(regs);
+	cond_local_irq_disable(regs);
+	preempt_enable_no_resched();
 	debug_stack_usage_dec();
 exit:
 	ist_exit(regs);
@@ -571,6 +557,29 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
 NOKPROBE_SYMBOL(fixup_bad_iret);
 #endif
 
+static bool is_sysenter_singlestep(struct pt_regs *regs)
+{
+	/*
+	 * We don't try for precision here.  If we're anywhere in the region of
+	 * code that can be single-stepped in the SYSENTER entry path, then
+	 * assume that this is a useless single-step trap due to SYSENTER
+	 * being invoked with TF set.  (We don't know in advance exactly
+	 * which instructions will be hit because BTF could plausibly
+	 * be set.)
+	 */
+#ifdef CONFIG_X86_32
+	return (regs->ip - (unsigned long)__begin_SYSENTER_singlestep_region) <
+		(unsigned long)__end_SYSENTER_singlestep_region -
+		(unsigned long)__begin_SYSENTER_singlestep_region;
+#elif defined(CONFIG_IA32_EMULATION)
+	return (regs->ip - (unsigned long)entry_SYSENTER_compat) <
+		(unsigned long)__end_entry_SYSENTER_compat -
+		(unsigned long)entry_SYSENTER_compat;
+#else
+	return false;
+#endif
+}
+
 /*
  * Our handling of the processor debug registers is non-trivial.
  * We do not clear them on entry and exit from the kernel. Therefore
@@ -605,11 +614,42 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	ist_enter(regs);
 
 	get_debugreg(dr6, 6);
+	/*
+	 * The Intel SDM says:
+	 *
+	 *   Certain debug exceptions may clear bits 0-3. The remaining
+	 *   contents of the DR6 register are never cleared by the
+	 *   processor. To avoid confusion in identifying debug
+	 *   exceptions, debug handlers should clear the register before
+	 *   returning to the interrupted task.
+	 *
+	 * Keep it simple: clear DR6 immediately.
+	 */
+	set_debugreg(0, 6);
 
 	/* Filter out all the reserved bits which are preset to 1 */
 	dr6 &= ~DR6_RESERVED;
 
 	/*
+	 * The SDM says "The processor clears the BTF flag when it
+	 * generates a debug exception."  Clear TIF_BLOCKSTEP to keep
+	 * TIF_BLOCKSTEP in sync with the hardware BTF flag.
+	 */
+	clear_tsk_thread_flag(tsk, TIF_BLOCKSTEP);
+
+	if (unlikely(!user_mode(regs) && (dr6 & DR_STEP) &&
+		     is_sysenter_singlestep(regs))) {
+		dr6 &= ~DR_STEP;
+		if (!dr6)
+			goto exit;
+		/*
+		 * else we might have gotten a single-step trap and hit a
+		 * watchpoint at the same time, in which case we should fall
+		 * through and handle the watchpoint.
+		 */
+	}
+
+	/*
 	 * If dr6 has no reason to give us about the origin of this trap,
 	 * then it's very likely the result of an icebp/int01 trap.
 	 * User wants a sigtrap for that.
@@ -617,18 +657,10 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	if (!dr6 && user_mode(regs))
 		user_icebp = 1;
 
-	/* Catch kmemcheck conditions first of all! */
+	/* Catch kmemcheck conditions! */
 	if ((dr6 & DR_STEP) && kmemcheck_trap(regs))
 		goto exit;
 
-	/* DR6 may or may not be cleared by the CPU */
-	set_debugreg(0, 6);
-
-	/*
-	 * The processor cleared BTF, so don't mark that we need it set.
-	 */
-	clear_tsk_thread_flag(tsk, TIF_BLOCKSTEP);
-
 	/* Store the virtualized DR6 value */
 	tsk->thread.debugreg6 = dr6;
 
@@ -648,24 +680,25 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	debug_stack_usage_inc();
 
 	/* It's safe to allow irq's after DR6 has been saved */
-	preempt_conditional_sti(regs);
+	preempt_disable();
+	cond_local_irq_enable(regs);
 
 	if (v8086_mode(regs)) {
 		handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code,
 					X86_TRAP_DB);
-		preempt_conditional_cli(regs);
+		cond_local_irq_disable(regs);
+		preempt_enable_no_resched();
 		debug_stack_usage_dec();
 		goto exit;
 	}
 
-	/*
-	 * Single-stepping through system calls: ignore any exceptions in
-	 * kernel space, but re-enable TF when returning to user mode.
-	 *
-	 * We already checked v86 mode above, so we can check for kernel mode
-	 * by just checking the CPL of CS.
-	 */
-	if ((dr6 & DR_STEP) && !user_mode(regs)) {
+	if (WARN_ON_ONCE((dr6 & DR_STEP) && !user_mode(regs))) {
+		/*
+		 * Historical junk that used to handle SYSENTER single-stepping.
+		 * This should be unreachable now.  If we survive for a while
+		 * without anyone hitting this warning, we'll turn this into
+		 * an oops.
+		 */
 		tsk->thread.debugreg6 &= ~DR_STEP;
 		set_tsk_thread_flag(tsk, TIF_SINGLESTEP);
 		regs->flags &= ~X86_EFLAGS_TF;
@@ -673,10 +706,19 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	si_code = get_si_code(tsk->thread.debugreg6);
 	if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp)
 		send_sigtrap(tsk, regs, error_code, si_code);
-	preempt_conditional_cli(regs);
+	cond_local_irq_disable(regs);
+	preempt_enable_no_resched();
 	debug_stack_usage_dec();
 
 exit:
+#if defined(CONFIG_X86_32)
+	/*
+	 * This is the most likely code path that involves non-trivial use
+	 * of the SYSENTER stack.  Check that we haven't overrun it.
+	 */
+	WARN(this_cpu_read(cpu_tss.SYSENTER_stack_canary) != STACK_END_MAGIC,
+	     "Overran or corrupted SYSENTER stack\n");
+#endif
 	ist_exit(regs);
 }
 NOKPROBE_SYMBOL(do_debug);
@@ -696,10 +738,10 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 
 	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) == NOTIFY_STOP)
 		return;
-	conditional_sti(regs);
+	cond_local_irq_enable(regs);
 
 	if (!user_mode(regs)) {
-		if (!fixup_exception(regs)) {
+		if (!fixup_exception(regs, trapnr)) {
 			task->thread.error_code = error_code;
 			task->thread.trap_nr = trapnr;
 			die(str, regs, error_code);
@@ -743,20 +785,19 @@ do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
 dotraplinkage void
 do_spurious_interrupt_bug(struct pt_regs *regs, long error_code)
 {
-	conditional_sti(regs);
+	cond_local_irq_enable(regs);
 }
 
 dotraplinkage void
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
-	BUG_ON(use_eager_fpu());
 
 #ifdef CONFIG_MATH_EMULATION
-	if (read_cr0() & X86_CR0_EM) {
+	if (!boot_cpu_has(X86_FEATURE_FPU) && (read_cr0() & X86_CR0_EM)) {
 		struct math_emu_info info = { };
 
-		conditional_sti(regs);
+		cond_local_irq_enable(regs);
 
 		info.regs = regs;
 		math_emulate(&info);
@@ -765,7 +806,7 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 #endif
 	fpu__restore(&current->thread.fpu); /* interrupts still off */
 #ifdef CONFIG_X86_32
-	conditional_sti(regs);
+	cond_local_irq_enable(regs);
 #endif
 }
 NOKPROBE_SYMBOL(do_device_not_available);
@@ -868,7 +909,7 @@ void __init trap_init(void)
 #endif
 
 #ifdef CONFIG_X86_32
-	set_system_trap_gate(IA32_SYSCALL_VECTOR, entry_INT80_32);
+	set_system_intr_gate(IA32_SYSCALL_VECTOR, entry_INT80_32);
 	set_bit(IA32_SYSCALL_VECTOR, used_vectors);
 #endif
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 3d743da828d3..56380440d862 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -43,6 +43,11 @@ static DEFINE_STATIC_KEY_FALSE(__use_tsc);
 
 int tsc_clocksource_reliable;
 
+static u32 art_to_tsc_numerator;
+static u32 art_to_tsc_denominator;
+static u64 art_to_tsc_offset;
+struct clocksource *art_related_clocksource;
+
 /*
  * Use a ring-buffer like data structure, where a writer advances the head by
  * writing a new data entry and a reader advances the tail when it observes a
@@ -964,6 +969,37 @@ core_initcall(cpufreq_tsc);
 
 #endif /* CONFIG_CPU_FREQ */
 
+#define ART_CPUID_LEAF (0x15)
+#define ART_MIN_DENOMINATOR (1)
+
+
+/*
+ * If ART is present detect the numerator:denominator to convert to TSC
+ */
+static void detect_art(void)
+{
+	unsigned int unused[2];
+
+	if (boot_cpu_data.cpuid_level < ART_CPUID_LEAF)
+		return;
+
+	cpuid(ART_CPUID_LEAF, &art_to_tsc_denominator,
+	      &art_to_tsc_numerator, unused, unused+1);
+
+	/* Don't enable ART in a VM, non-stop TSC required */
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR) ||
+	    !boot_cpu_has(X86_FEATURE_NONSTOP_TSC) ||
+	    art_to_tsc_denominator < ART_MIN_DENOMINATOR)
+		return;
+
+	if (rdmsrl_safe(MSR_IA32_TSC_ADJUST, &art_to_tsc_offset))
+		return;
+
+	/* Make this sticky over multiple CPU init calls */
+	setup_force_cpu_cap(X86_FEATURE_ART);
+}
+
+
 /* clocksource code */
 
 static struct clocksource clocksource_tsc;
@@ -1071,6 +1107,25 @@ int unsynchronized_tsc(void)
 	return 0;
 }
 
+/*
+ * Convert ART to TSC given numerator/denominator found in detect_art()
+ */
+struct system_counterval_t convert_art_to_tsc(cycle_t art)
+{
+	u64 tmp, res, rem;
+
+	rem = do_div(art, art_to_tsc_denominator);
+
+	res = art * art_to_tsc_numerator;
+	tmp = rem * art_to_tsc_numerator;
+
+	do_div(tmp, art_to_tsc_denominator);
+	res += tmp + art_to_tsc_offset;
+
+	return (struct system_counterval_t) {.cs = art_related_clocksource,
+			.cycles = res};
+}
+EXPORT_SYMBOL(convert_art_to_tsc);
 
 static void tsc_refine_calibration_work(struct work_struct *work);
 static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
@@ -1142,6 +1197,8 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 		(unsigned long)tsc_khz % 1000);
 
 out:
+	if (boot_cpu_has(X86_FEATURE_ART))
+		art_related_clocksource = &clocksource_tsc;
 	clocksource_register_khz(&clocksource_tsc, tsc_khz);
 }
 
@@ -1235,6 +1292,8 @@ void __init tsc_init(void)
 		mark_tsc_unstable("TSCs unsynchronized");
 
 	check_system_tsc_reliable();
+
+	detect_art();
 }
 
 #ifdef CONFIG_SMP
@@ -1246,14 +1305,14 @@ void __init tsc_init(void)
  */
 unsigned long calibrate_delay_is_known(void)
 {
-	int i, cpu = smp_processor_id();
+	int sibling, cpu = smp_processor_id();
 
 	if (!tsc_disabled && !cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC))
 		return 0;
 
-	for_each_online_cpu(i)
-		if (cpu_data(i).phys_proc_id == cpu_data(cpu).phys_proc_id)
-			return cpu_data(i).loops_per_jiffy;
+	sibling = cpumask_any_but(topology_core_cpumask(cpu), cpu);
+	if (sibling < nr_cpu_ids)
+		return cpu_data(sibling).loops_per_jiffy;
 	return 0;
 }
 #endif
diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S
index 07efb35ee4bc..014ea59aa153 100644
--- a/arch/x86/kernel/verify_cpu.S
+++ b/arch/x86/kernel/verify_cpu.S
@@ -30,7 +30,7 @@
  * 	appropriately. Either display a message or halt.
  */
 
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/msr-index.h>
 
 verify_cpu:
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index e574b8546518..3dce1ca0a653 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -362,7 +362,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 	/* make room for real-mode segments */
 	tsk->thread.sp0 += 16;
 
-	if (static_cpu_has_safe(X86_FEATURE_SEP))
+	if (static_cpu_has(X86_FEATURE_SEP))
 		tsk->thread.sysenter_cs = 0;
 
 	load_sp0(tss, &tsk->thread);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 74e4bf11f562..5af9958cbdb6 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -41,29 +41,28 @@ ENTRY(phys_startup_64)
 jiffies_64 = jiffies;
 #endif
 
-#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
+#if defined(CONFIG_X86_64)
 /*
- * On 64-bit, align RODATA to 2MB so that even with CONFIG_DEBUG_RODATA
- * we retain large page mappings for boundaries spanning kernel text, rodata
- * and data sections.
+ * On 64-bit, align RODATA to 2MB so we retain large page mappings for
+ * boundaries spanning kernel text, rodata and data sections.
  *
  * However, kernel identity mappings will have different RWX permissions
  * to the pages mapping to text and to the pages padding (which are freed) the
  * text section. Hence kernel identity mappings will be broken to smaller
  * pages. For 64-bit, kernel text and kernel identity mappings are different,
- * so we can enable protection checks that come with CONFIG_DEBUG_RODATA,
- * as well as retain 2MB large page mappings for kernel text.
+ * so we can enable protection checks as well as retain 2MB large page
+ * mappings for kernel text.
  */
-#define X64_ALIGN_DEBUG_RODATA_BEGIN	. = ALIGN(HPAGE_SIZE);
+#define X64_ALIGN_RODATA_BEGIN	. = ALIGN(HPAGE_SIZE);
 
-#define X64_ALIGN_DEBUG_RODATA_END				\
+#define X64_ALIGN_RODATA_END					\
 		. = ALIGN(HPAGE_SIZE);				\
 		__end_rodata_hpage_align = .;
 
 #else
 
-#define X64_ALIGN_DEBUG_RODATA_BEGIN
-#define X64_ALIGN_DEBUG_RODATA_END
+#define X64_ALIGN_RODATA_BEGIN
+#define X64_ALIGN_RODATA_END
 
 #endif
 
@@ -112,13 +111,11 @@ SECTIONS
 
 	EXCEPTION_TABLE(16) :text = 0x9090
 
-#if defined(CONFIG_DEBUG_RODATA)
 	/* .text should occupy whole number of pages */
 	. = ALIGN(PAGE_SIZE);
-#endif
-	X64_ALIGN_DEBUG_RODATA_BEGIN
+	X64_ALIGN_RODATA_BEGIN
 	RO_DATA(PAGE_SIZE)
-	X64_ALIGN_DEBUG_RODATA_END
+	X64_ALIGN_RODATA_END
 
 	/* Data */
 	.data : AT(ADDR(.data) - LOAD_OFFSET) {
@@ -195,6 +192,17 @@ SECTIONS
 	:init
 #endif
 
+	/*
+	 * Section for code used exclusively before alternatives are run. All
+	 * references to such code must be patched out by alternatives, normally
+	 * by using X86_FEATURE_ALWAYS CPU feature bit.
+	 *
+	 * See static_cpu_has() for an example.
+	 */
+	.altinstr_aux : AT(ADDR(.altinstr_aux) - LOAD_OFFSET) {
+		*(.altinstr_aux)
+	}
+
 	INIT_DATA_SECTION(16)
 
 	.x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index a0695be19864..cd05942bc918 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -37,6 +37,8 @@ EXPORT_SYMBOL(__copy_user_nocache);
 EXPORT_SYMBOL(_copy_from_user);
 EXPORT_SYMBOL(_copy_to_user);
 
+EXPORT_SYMBOL_GPL(memcpy_mcsafe);
+
 EXPORT_SYMBOL(copy_page);
 EXPORT_SYMBOL(clear_page);
 
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index a1ff508bb423..464fa477afbf 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -13,9 +13,10 @@ kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(KVM)/async_pf.o
 
 kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
 			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
-			   hyperv.o
+			   hyperv.o page_track.o
 
 kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT)	+= assigned-dev.o iommu.o
+
 kvm-intel-y		+= vmx.o pmu_intel.o
 kvm-amd-y		+= svm.o pmu_amd.o
 
diff --git a/arch/x86/kvm/assigned-dev.c b/arch/x86/kvm/assigned-dev.c
index 9dc091acd5fb..308b8597c691 100644
--- a/arch/x86/kvm/assigned-dev.c
+++ b/arch/x86/kvm/assigned-dev.c
@@ -51,11 +51,9 @@ struct kvm_assigned_dev_kernel {
 static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
 						      int assigned_dev_id)
 {
-	struct list_head *ptr;
 	struct kvm_assigned_dev_kernel *match;
 
-	list_for_each(ptr, head) {
-		match = list_entry(ptr, struct kvm_assigned_dev_kernel, list);
+	list_for_each_entry(match, head, list) {
 		if (match->assigned_dev_id == assigned_dev_id)
 			return match;
 	}
@@ -373,14 +371,10 @@ static void kvm_free_assigned_device(struct kvm *kvm,
 
 void kvm_free_all_assigned_devices(struct kvm *kvm)
 {
-	struct list_head *ptr, *ptr2;
-	struct kvm_assigned_dev_kernel *assigned_dev;
-
-	list_for_each_safe(ptr, ptr2, &kvm->arch.assigned_dev_head) {
-		assigned_dev = list_entry(ptr,
-					  struct kvm_assigned_dev_kernel,
-					  list);
+	struct kvm_assigned_dev_kernel *assigned_dev, *tmp;
 
+	list_for_each_entry_safe(assigned_dev, tmp,
+				 &kvm->arch.assigned_dev_head, list) {
 		kvm_free_assigned_device(kvm, assigned_dev);
 	}
 }
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 6525e926f566..0029644bf09c 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -46,11 +46,18 @@ static u32 xstate_required_size(u64 xstate_bv, bool compacted)
 	return ret;
 }
 
+bool kvm_mpx_supported(void)
+{
+	return ((host_xcr0 & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR))
+		 && kvm_x86_ops->mpx_supported());
+}
+EXPORT_SYMBOL_GPL(kvm_mpx_supported);
+
 u64 kvm_supported_xcr0(void)
 {
 	u64 xcr0 = KVM_SUPPORTED_XCR0 & host_xcr0;
 
-	if (!kvm_x86_ops->mpx_supported())
+	if (!kvm_mpx_supported())
 		xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR);
 
 	return xcr0;
@@ -97,8 +104,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 	if (best && (best->eax & (F(XSAVES) | F(XSAVEC))))
 		best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
 
-	vcpu->arch.eager_fpu = use_eager_fpu() || guest_cpuid_has_mpx(vcpu);
-	if (vcpu->arch.eager_fpu)
+	if (use_eager_fpu())
 		kvm_x86_ops->fpu_activate(vcpu);
 
 	/*
@@ -295,7 +301,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 #endif
 	unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0;
 	unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0;
-	unsigned f_mpx = kvm_x86_ops->mpx_supported() ? F(MPX) : 0;
+	unsigned f_mpx = kvm_mpx_supported() ? F(MPX) : 0;
 	unsigned f_xsaves = kvm_x86_ops->xsaves_supported() ? F(XSAVES) : 0;
 
 	/* cpuid 1.edx */
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index c8eda1498121..66a6581724ad 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -5,6 +5,7 @@
 #include <asm/cpu.h>
 
 int kvm_update_cpuid(struct kvm_vcpu *vcpu);
+bool kvm_mpx_supported(void);
 struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
 					      u32 function, u32 index);
 int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
@@ -135,14 +136,6 @@ static inline bool guest_cpuid_has_rtm(struct kvm_vcpu *vcpu)
 	return best && (best->ebx & bit(X86_FEATURE_RTM));
 }
 
-static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu)
-{
-	struct kvm_cpuid_entry2 *best;
-
-	best = kvm_find_cpuid_entry(vcpu, 7, 0);
-	return best && (best->ebx & bit(X86_FEATURE_MPX));
-}
-
 static inline bool guest_cpuid_has_pcommit(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 1505587d06e9..b9b09fec173b 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -650,10 +650,10 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 	u16 sel;
 
 	la = seg_base(ctxt, addr.seg) + addr.ea;
-	*linear = la;
 	*max_size = 0;
 	switch (mode) {
 	case X86EMUL_MODE_PROT64:
+		*linear = la;
 		if (is_noncanonical_address(la))
 			goto bad;
 
@@ -662,6 +662,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 			goto bad;
 		break;
 	default:
+		*linear = la = (u32)la;
 		usable = ctxt->ops->get_segment(ctxt, &sel, &desc, NULL,
 						addr.seg);
 		if (!usable)
@@ -689,7 +690,6 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 			if (size > *max_size)
 				goto bad;
 		}
-		la &= (u32)-1;
 		break;
 	}
 	if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0))
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index c58ba67175ac..5ff3485acb60 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1043,6 +1043,27 @@ bool kvm_hv_hypercall_enabled(struct kvm *kvm)
 	return kvm->arch.hyperv.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE;
 }
 
+static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
+{
+	bool longmode;
+
+	longmode = is_64_bit_mode(vcpu);
+	if (longmode)
+		kvm_register_write(vcpu, VCPU_REGS_RAX, result);
+	else {
+		kvm_register_write(vcpu, VCPU_REGS_RDX, result >> 32);
+		kvm_register_write(vcpu, VCPU_REGS_RAX, result & 0xffffffff);
+	}
+}
+
+static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
+{
+	struct kvm_run *run = vcpu->run;
+
+	kvm_hv_hypercall_set_result(vcpu, run->hyperv.u.hcall.result);
+	return 1;
+}
+
 int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 {
 	u64 param, ingpa, outgpa, ret;
@@ -1055,7 +1076,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 	 */
 	if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) {
 		kvm_queue_exception(vcpu, UD_VECTOR);
-		return 0;
+		return 1;
 	}
 
 	longmode = is_64_bit_mode(vcpu);
@@ -1083,22 +1104,33 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 
 	trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa);
 
+	/* Hypercall continuation is not supported yet */
+	if (rep_cnt || rep_idx) {
+		res = HV_STATUS_INVALID_HYPERCALL_CODE;
+		goto set_result;
+	}
+
 	switch (code) {
-	case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT:
+	case HVCALL_NOTIFY_LONG_SPIN_WAIT:
 		kvm_vcpu_on_spin(vcpu);
 		break;
+	case HVCALL_POST_MESSAGE:
+	case HVCALL_SIGNAL_EVENT:
+		vcpu->run->exit_reason = KVM_EXIT_HYPERV;
+		vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL;
+		vcpu->run->hyperv.u.hcall.input = param;
+		vcpu->run->hyperv.u.hcall.params[0] = ingpa;
+		vcpu->run->hyperv.u.hcall.params[1] = outgpa;
+		vcpu->arch.complete_userspace_io =
+				kvm_hv_hypercall_complete_userspace;
+		return 0;
 	default:
 		res = HV_STATUS_INVALID_HYPERCALL_CODE;
 		break;
 	}
 
+set_result:
 	ret = res | (((u64)rep_done & 0xfff) << 32);
-	if (longmode) {
-		kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
-	} else {
-		kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32);
-		kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff);
-	}
-
+	kvm_hv_hypercall_set_result(vcpu, ret);
 	return 1;
 }
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index b0ea42b78ccd..a4bf5b45d65a 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -51,32 +51,9 @@
 #define RW_STATE_WORD0 3
 #define RW_STATE_WORD1 4
 
-/* Compute with 96 bit intermediate result: (a*b)/c */
-static u64 muldiv64(u64 a, u32 b, u32 c)
+static void pit_set_gate(struct kvm_pit *pit, int channel, u32 val)
 {
-	union {
-		u64 ll;
-		struct {
-			u32 low, high;
-		} l;
-	} u, res;
-	u64 rl, rh;
-
-	u.ll = a;
-	rl = (u64)u.l.low * (u64)b;
-	rh = (u64)u.l.high * (u64)b;
-	rh += (rl >> 32);
-	res.l.high = div64_u64(rh, c);
-	res.l.low = div64_u64(((mod_64(rh, c) << 32) + (rl & 0xffffffff)), c);
-	return res.ll;
-}
-
-static void pit_set_gate(struct kvm *kvm, int channel, u32 val)
-{
-	struct kvm_kpit_channel_state *c =
-		&kvm->arch.vpit->pit_state.channels[channel];
-
-	WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
+	struct kvm_kpit_channel_state *c = &pit->pit_state.channels[channel];
 
 	switch (c->mode) {
 	default:
@@ -97,18 +74,16 @@ static void pit_set_gate(struct kvm *kvm, int channel, u32 val)
 	c->gate = val;
 }
 
-static int pit_get_gate(struct kvm *kvm, int channel)
+static int pit_get_gate(struct kvm_pit *pit, int channel)
 {
-	WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
-
-	return kvm->arch.vpit->pit_state.channels[channel].gate;
+	return pit->pit_state.channels[channel].gate;
 }
 
-static s64 __kpit_elapsed(struct kvm *kvm)
+static s64 __kpit_elapsed(struct kvm_pit *pit)
 {
 	s64 elapsed;
 	ktime_t remaining;
-	struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
+	struct kvm_kpit_state *ps = &pit->pit_state;
 
 	if (!ps->period)
 		return 0;
@@ -128,26 +103,23 @@ static s64 __kpit_elapsed(struct kvm *kvm)
 	return elapsed;
 }
 
-static s64 kpit_elapsed(struct kvm *kvm, struct kvm_kpit_channel_state *c,
+static s64 kpit_elapsed(struct kvm_pit *pit, struct kvm_kpit_channel_state *c,
 			int channel)
 {
 	if (channel == 0)
-		return __kpit_elapsed(kvm);
+		return __kpit_elapsed(pit);
 
 	return ktime_to_ns(ktime_sub(ktime_get(), c->count_load_time));
 }
 
-static int pit_get_count(struct kvm *kvm, int channel)
+static int pit_get_count(struct kvm_pit *pit, int channel)
 {
-	struct kvm_kpit_channel_state *c =
-		&kvm->arch.vpit->pit_state.channels[channel];
+	struct kvm_kpit_channel_state *c = &pit->pit_state.channels[channel];
 	s64 d, t;
 	int counter;
 
-	WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
-
-	t = kpit_elapsed(kvm, c, channel);
-	d = muldiv64(t, KVM_PIT_FREQ, NSEC_PER_SEC);
+	t = kpit_elapsed(pit, c, channel);
+	d = mul_u64_u32_div(t, KVM_PIT_FREQ, NSEC_PER_SEC);
 
 	switch (c->mode) {
 	case 0:
@@ -167,17 +139,14 @@ static int pit_get_count(struct kvm *kvm, int channel)
 	return counter;
 }
 
-static int pit_get_out(struct kvm *kvm, int channel)
+static int pit_get_out(struct kvm_pit *pit, int channel)
 {
-	struct kvm_kpit_channel_state *c =
-		&kvm->arch.vpit->pit_state.channels[channel];
+	struct kvm_kpit_channel_state *c = &pit->pit_state.channels[channel];
 	s64 d, t;
 	int out;
 
-	WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
-
-	t = kpit_elapsed(kvm, c, channel);
-	d = muldiv64(t, KVM_PIT_FREQ, NSEC_PER_SEC);
+	t = kpit_elapsed(pit, c, channel);
+	d = mul_u64_u32_div(t, KVM_PIT_FREQ, NSEC_PER_SEC);
 
 	switch (c->mode) {
 	default:
@@ -202,29 +171,23 @@ static int pit_get_out(struct kvm *kvm, int channel)
 	return out;
 }
 
-static void pit_latch_count(struct kvm *kvm, int channel)
+static void pit_latch_count(struct kvm_pit *pit, int channel)
 {
-	struct kvm_kpit_channel_state *c =
-		&kvm->arch.vpit->pit_state.channels[channel];
-
-	WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
+	struct kvm_kpit_channel_state *c = &pit->pit_state.channels[channel];
 
 	if (!c->count_latched) {
-		c->latched_count = pit_get_count(kvm, channel);
+		c->latched_count = pit_get_count(pit, channel);
 		c->count_latched = c->rw_mode;
 	}
 }
 
-static void pit_latch_status(struct kvm *kvm, int channel)
+static void pit_latch_status(struct kvm_pit *pit, int channel)
 {
-	struct kvm_kpit_channel_state *c =
-		&kvm->arch.vpit->pit_state.channels[channel];
-
-	WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
+	struct kvm_kpit_channel_state *c = &pit->pit_state.channels[channel];
 
 	if (!c->status_latched) {
 		/* TODO: Return NULL COUNT (bit 6). */
-		c->status = ((pit_get_out(kvm, channel) << 7) |
+		c->status = ((pit_get_out(pit, channel) << 7) |
 				(c->rw_mode << 4) |
 				(c->mode << 1) |
 				c->bcd);
@@ -232,26 +195,24 @@ static void pit_latch_status(struct kvm *kvm, int channel)
 	}
 }
 
+static inline struct kvm_pit *pit_state_to_pit(struct kvm_kpit_state *ps)
+{
+	return container_of(ps, struct kvm_pit, pit_state);
+}
+
 static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian)
 {
 	struct kvm_kpit_state *ps = container_of(kian, struct kvm_kpit_state,
 						 irq_ack_notifier);
-	int value;
-
-	spin_lock(&ps->inject_lock);
-	value = atomic_dec_return(&ps->pending);
-	if (value < 0)
-		/* spurious acks can be generated if, for example, the
-		 * PIC is being reset.  Handle it gracefully here
-		 */
-		atomic_inc(&ps->pending);
-	else if (value > 0)
-		/* in this case, we had multiple outstanding pit interrupts
-		 * that we needed to inject.  Reinject
-		 */
-		queue_kthread_work(&ps->pit->worker, &ps->pit->expired);
-	ps->irq_ack = 1;
-	spin_unlock(&ps->inject_lock);
+	struct kvm_pit *pit = pit_state_to_pit(ps);
+
+	atomic_set(&ps->irq_ack, 1);
+	/* irq_ack should be set before pending is read.  Order accesses with
+	 * inc(pending) in pit_timer_fn and xchg(irq_ack, 0) in pit_do_work.
+	 */
+	smp_mb();
+	if (atomic_dec_if_positive(&ps->pending) > 0)
+		queue_kthread_work(&pit->worker, &pit->expired);
 }
 
 void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
@@ -282,45 +243,36 @@ static void pit_do_work(struct kthread_work *work)
 	struct kvm_vcpu *vcpu;
 	int i;
 	struct kvm_kpit_state *ps = &pit->pit_state;
-	int inject = 0;
 
-	/* Try to inject pending interrupts when
-	 * last one has been acked.
+	if (atomic_read(&ps->reinject) && !atomic_xchg(&ps->irq_ack, 0))
+		return;
+
+	kvm_set_irq(kvm, pit->irq_source_id, 0, 1, false);
+	kvm_set_irq(kvm, pit->irq_source_id, 0, 0, false);
+
+	/*
+	 * Provides NMI watchdog support via Virtual Wire mode.
+	 * The route is: PIT -> LVT0 in NMI mode.
+	 *
+	 * Note: Our Virtual Wire implementation does not follow
+	 * the MP specification.  We propagate a PIT interrupt to all
+	 * VCPUs and only when LVT0 is in NMI mode.  The interrupt can
+	 * also be simultaneously delivered through PIC and IOAPIC.
 	 */
-	spin_lock(&ps->inject_lock);
-	if (ps->irq_ack) {
-		ps->irq_ack = 0;
-		inject = 1;
-	}
-	spin_unlock(&ps->inject_lock);
-	if (inject) {
-		kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1, false);
-		kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0, false);
-
-		/*
-		 * Provides NMI watchdog support via Virtual Wire mode.
-		 * The route is: PIT -> PIC -> LVT0 in NMI mode.
-		 *
-		 * Note: Our Virtual Wire implementation is simplified, only
-		 * propagating PIT interrupts to all VCPUs when they have set
-		 * LVT0 to NMI delivery. Other PIC interrupts are just sent to
-		 * VCPU0, and only if its LVT0 is in EXTINT mode.
-		 */
-		if (atomic_read(&kvm->arch.vapics_in_nmi_mode) > 0)
-			kvm_for_each_vcpu(i, vcpu, kvm)
-				kvm_apic_nmi_wd_deliver(vcpu);
-	}
+	if (atomic_read(&kvm->arch.vapics_in_nmi_mode) > 0)
+		kvm_for_each_vcpu(i, vcpu, kvm)
+			kvm_apic_nmi_wd_deliver(vcpu);
 }
 
 static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
 {
 	struct kvm_kpit_state *ps = container_of(data, struct kvm_kpit_state, timer);
-	struct kvm_pit *pt = ps->kvm->arch.vpit;
+	struct kvm_pit *pt = pit_state_to_pit(ps);
 
-	if (ps->reinject || !atomic_read(&ps->pending)) {
+	if (atomic_read(&ps->reinject))
 		atomic_inc(&ps->pending);
-		queue_kthread_work(&pt->worker, &pt->expired);
-	}
+
+	queue_kthread_work(&pt->worker, &pt->expired);
 
 	if (ps->is_periodic) {
 		hrtimer_add_expires_ns(&ps->timer, ps->period);
@@ -329,30 +281,54 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
 		return HRTIMER_NORESTART;
 }
 
-static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
+static inline void kvm_pit_reset_reinject(struct kvm_pit *pit)
 {
-	struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
+	atomic_set(&pit->pit_state.pending, 0);
+	atomic_set(&pit->pit_state.irq_ack, 1);
+}
+
+void kvm_pit_set_reinject(struct kvm_pit *pit, bool reinject)
+{
+	struct kvm_kpit_state *ps = &pit->pit_state;
+	struct kvm *kvm = pit->kvm;
+
+	if (atomic_read(&ps->reinject) == reinject)
+		return;
+
+	if (reinject) {
+		/* The initial state is preserved while ps->reinject == 0. */
+		kvm_pit_reset_reinject(pit);
+		kvm_register_irq_ack_notifier(kvm, &ps->irq_ack_notifier);
+		kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
+	} else {
+		kvm_unregister_irq_ack_notifier(kvm, &ps->irq_ack_notifier);
+		kvm_unregister_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
+	}
+
+	atomic_set(&ps->reinject, reinject);
+}
+
+static void create_pit_timer(struct kvm_pit *pit, u32 val, int is_period)
+{
+	struct kvm_kpit_state *ps = &pit->pit_state;
+	struct kvm *kvm = pit->kvm;
 	s64 interval;
 
 	if (!ioapic_in_kernel(kvm) ||
 	    ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)
 		return;
 
-	interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ);
+	interval = mul_u64_u32_div(val, NSEC_PER_SEC, KVM_PIT_FREQ);
 
 	pr_debug("create pit timer, interval is %llu nsec\n", interval);
 
 	/* TODO The new value only affected after the retriggered */
 	hrtimer_cancel(&ps->timer);
-	flush_kthread_work(&ps->pit->expired);
+	flush_kthread_work(&pit->expired);
 	ps->period = interval;
 	ps->is_periodic = is_period;
 
-	ps->timer.function = pit_timer_fn;
-	ps->kvm = ps->pit->kvm;
-
-	atomic_set(&ps->pending, 0);
-	ps->irq_ack = 1;
+	kvm_pit_reset_reinject(pit);
 
 	/*
 	 * Do not allow the guest to program periodic timers with small
@@ -375,11 +351,9 @@ static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
 		      HRTIMER_MODE_ABS);
 }
 
-static void pit_load_count(struct kvm *kvm, int channel, u32 val)
+static void pit_load_count(struct kvm_pit *pit, int channel, u32 val)
 {
-	struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
-
-	WARN_ON(!mutex_is_locked(&ps->lock));
+	struct kvm_kpit_state *ps = &pit->pit_state;
 
 	pr_debug("load_count val is %d, channel is %d\n", val, channel);
 
@@ -404,29 +378,33 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val)
 	case 1:
         /* FIXME: enhance mode 4 precision */
 	case 4:
-		create_pit_timer(kvm, val, 0);
+		create_pit_timer(pit, val, 0);
 		break;
 	case 2:
 	case 3:
-		create_pit_timer(kvm, val, 1);
+		create_pit_timer(pit, val, 1);
 		break;
 	default:
-		destroy_pit_timer(kvm->arch.vpit);
+		destroy_pit_timer(pit);
 	}
 }
 
-void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val, int hpet_legacy_start)
+void kvm_pit_load_count(struct kvm_pit *pit, int channel, u32 val,
+		int hpet_legacy_start)
 {
 	u8 saved_mode;
+
+	WARN_ON_ONCE(!mutex_is_locked(&pit->pit_state.lock));
+
 	if (hpet_legacy_start) {
 		/* save existing mode for later reenablement */
 		WARN_ON(channel != 0);
-		saved_mode = kvm->arch.vpit->pit_state.channels[0].mode;
-		kvm->arch.vpit->pit_state.channels[0].mode = 0xff; /* disable timer */
-		pit_load_count(kvm, channel, val);
-		kvm->arch.vpit->pit_state.channels[0].mode = saved_mode;
+		saved_mode = pit->pit_state.channels[0].mode;
+		pit->pit_state.channels[0].mode = 0xff; /* disable timer */
+		pit_load_count(pit, channel, val);
+		pit->pit_state.channels[0].mode = saved_mode;
 	} else {
-		pit_load_count(kvm, channel, val);
+		pit_load_count(pit, channel, val);
 	}
 }
 
@@ -452,7 +430,6 @@ static int pit_ioport_write(struct kvm_vcpu *vcpu,
 {
 	struct kvm_pit *pit = dev_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
-	struct kvm *kvm = pit->kvm;
 	int channel, access;
 	struct kvm_kpit_channel_state *s;
 	u32 val = *(u32 *) data;
@@ -476,9 +453,9 @@ static int pit_ioport_write(struct kvm_vcpu *vcpu,
 				s = &pit_state->channels[channel];
 				if (val & (2 << channel)) {
 					if (!(val & 0x20))
-						pit_latch_count(kvm, channel);
+						pit_latch_count(pit, channel);
 					if (!(val & 0x10))
-						pit_latch_status(kvm, channel);
+						pit_latch_status(pit, channel);
 				}
 			}
 		} else {
@@ -486,7 +463,7 @@ static int pit_ioport_write(struct kvm_vcpu *vcpu,
 			s = &pit_state->channels[channel];
 			access = (val >> 4) & KVM_PIT_CHANNEL_MASK;
 			if (access == 0) {
-				pit_latch_count(kvm, channel);
+				pit_latch_count(pit, channel);
 			} else {
 				s->rw_mode = access;
 				s->read_state = access;
@@ -503,17 +480,17 @@ static int pit_ioport_write(struct kvm_vcpu *vcpu,
 		switch (s->write_state) {
 		default:
 		case RW_STATE_LSB:
-			pit_load_count(kvm, addr, val);
+			pit_load_count(pit, addr, val);
 			break;
 		case RW_STATE_MSB:
-			pit_load_count(kvm, addr, val << 8);
+			pit_load_count(pit, addr, val << 8);
 			break;
 		case RW_STATE_WORD0:
 			s->write_latch = val;
 			s->write_state = RW_STATE_WORD1;
 			break;
 		case RW_STATE_WORD1:
-			pit_load_count(kvm, addr, s->write_latch | (val << 8));
+			pit_load_count(pit, addr, s->write_latch | (val << 8));
 			s->write_state = RW_STATE_WORD0;
 			break;
 		}
@@ -529,7 +506,6 @@ static int pit_ioport_read(struct kvm_vcpu *vcpu,
 {
 	struct kvm_pit *pit = dev_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
-	struct kvm *kvm = pit->kvm;
 	int ret, count;
 	struct kvm_kpit_channel_state *s;
 	if (!pit_in_range(addr))
@@ -566,20 +542,20 @@ static int pit_ioport_read(struct kvm_vcpu *vcpu,
 		switch (s->read_state) {
 		default:
 		case RW_STATE_LSB:
-			count = pit_get_count(kvm, addr);
+			count = pit_get_count(pit, addr);
 			ret = count & 0xff;
 			break;
 		case RW_STATE_MSB:
-			count = pit_get_count(kvm, addr);
+			count = pit_get_count(pit, addr);
 			ret = (count >> 8) & 0xff;
 			break;
 		case RW_STATE_WORD0:
-			count = pit_get_count(kvm, addr);
+			count = pit_get_count(pit, addr);
 			ret = count & 0xff;
 			s->read_state = RW_STATE_WORD1;
 			break;
 		case RW_STATE_WORD1:
-			count = pit_get_count(kvm, addr);
+			count = pit_get_count(pit, addr);
 			ret = (count >> 8) & 0xff;
 			s->read_state = RW_STATE_WORD0;
 			break;
@@ -600,14 +576,13 @@ static int speaker_ioport_write(struct kvm_vcpu *vcpu,
 {
 	struct kvm_pit *pit = speaker_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
-	struct kvm *kvm = pit->kvm;
 	u32 val = *(u32 *) data;
 	if (addr != KVM_SPEAKER_BASE_ADDRESS)
 		return -EOPNOTSUPP;
 
 	mutex_lock(&pit_state->lock);
 	pit_state->speaker_data_on = (val >> 1) & 1;
-	pit_set_gate(kvm, 2, val & 1);
+	pit_set_gate(pit, 2, val & 1);
 	mutex_unlock(&pit_state->lock);
 	return 0;
 }
@@ -618,7 +593,6 @@ static int speaker_ioport_read(struct kvm_vcpu *vcpu,
 {
 	struct kvm_pit *pit = speaker_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
-	struct kvm *kvm = pit->kvm;
 	unsigned int refresh_clock;
 	int ret;
 	if (addr != KVM_SPEAKER_BASE_ADDRESS)
@@ -628,8 +602,8 @@ static int speaker_ioport_read(struct kvm_vcpu *vcpu,
 	refresh_clock = ((unsigned int)ktime_to_ns(ktime_get()) >> 14) & 1;
 
 	mutex_lock(&pit_state->lock);
-	ret = ((pit_state->speaker_data_on << 1) | pit_get_gate(kvm, 2) |
-		(pit_get_out(kvm, 2) << 5) | (refresh_clock << 4));
+	ret = ((pit_state->speaker_data_on << 1) | pit_get_gate(pit, 2) |
+		(pit_get_out(pit, 2) << 5) | (refresh_clock << 4));
 	if (len > sizeof(ret))
 		len = sizeof(ret);
 	memcpy(data, (char *)&ret, len);
@@ -637,33 +611,28 @@ static int speaker_ioport_read(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-void kvm_pit_reset(struct kvm_pit *pit)
+static void kvm_pit_reset(struct kvm_pit *pit)
 {
 	int i;
 	struct kvm_kpit_channel_state *c;
 
-	mutex_lock(&pit->pit_state.lock);
 	pit->pit_state.flags = 0;
 	for (i = 0; i < 3; i++) {
 		c = &pit->pit_state.channels[i];
 		c->mode = 0xff;
 		c->gate = (i != 2);
-		pit_load_count(pit->kvm, i, 0);
+		pit_load_count(pit, i, 0);
 	}
-	mutex_unlock(&pit->pit_state.lock);
 
-	atomic_set(&pit->pit_state.pending, 0);
-	pit->pit_state.irq_ack = 1;
+	kvm_pit_reset_reinject(pit);
 }
 
 static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask)
 {
 	struct kvm_pit *pit = container_of(kimn, struct kvm_pit, mask_notifier);
 
-	if (!mask) {
-		atomic_set(&pit->pit_state.pending, 0);
-		pit->pit_state.irq_ack = 1;
-	}
+	if (!mask)
+		kvm_pit_reset_reinject(pit);
 }
 
 static const struct kvm_io_device_ops pit_dev_ops = {
@@ -690,14 +659,10 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 		return NULL;
 
 	pit->irq_source_id = kvm_request_irq_source_id(kvm);
-	if (pit->irq_source_id < 0) {
-		kfree(pit);
-		return NULL;
-	}
+	if (pit->irq_source_id < 0)
+		goto fail_request;
 
 	mutex_init(&pit->pit_state.lock);
-	mutex_lock(&pit->pit_state.lock);
-	spin_lock_init(&pit->pit_state.inject_lock);
 
 	pid = get_pid(task_tgid(current));
 	pid_nr = pid_vnr(pid);
@@ -706,36 +671,30 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 	init_kthread_worker(&pit->worker);
 	pit->worker_task = kthread_run(kthread_worker_fn, &pit->worker,
 				       "kvm-pit/%d", pid_nr);
-	if (IS_ERR(pit->worker_task)) {
-		mutex_unlock(&pit->pit_state.lock);
-		kvm_free_irq_source_id(kvm, pit->irq_source_id);
-		kfree(pit);
-		return NULL;
-	}
+	if (IS_ERR(pit->worker_task))
+		goto fail_kthread;
+
 	init_kthread_work(&pit->expired, pit_do_work);
 
-	kvm->arch.vpit = pit;
 	pit->kvm = kvm;
 
 	pit_state = &pit->pit_state;
-	pit_state->pit = pit;
 	hrtimer_init(&pit_state->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	pit_state->timer.function = pit_timer_fn;
+
 	pit_state->irq_ack_notifier.gsi = 0;
 	pit_state->irq_ack_notifier.irq_acked = kvm_pit_ack_irq;
-	kvm_register_irq_ack_notifier(kvm, &pit_state->irq_ack_notifier);
-	pit_state->reinject = true;
-	mutex_unlock(&pit->pit_state.lock);
+	pit->mask_notifier.func = pit_mask_notifer;
 
 	kvm_pit_reset(pit);
 
-	pit->mask_notifier.func = pit_mask_notifer;
-	kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
+	kvm_pit_set_reinject(pit, true);
 
 	kvm_iodevice_init(&pit->dev, &pit_dev_ops);
 	ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, KVM_PIT_BASE_ADDRESS,
 				      KVM_PIT_MEM_LENGTH, &pit->dev);
 	if (ret < 0)
-		goto fail;
+		goto fail_register_pit;
 
 	if (flags & KVM_PIT_SPEAKER_DUMMY) {
 		kvm_iodevice_init(&pit->speaker_dev, &speaker_dev_ops);
@@ -743,42 +702,35 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 					      KVM_SPEAKER_BASE_ADDRESS, 4,
 					      &pit->speaker_dev);
 		if (ret < 0)
-			goto fail_unregister;
+			goto fail_register_speaker;
 	}
 
 	return pit;
 
-fail_unregister:
+fail_register_speaker:
 	kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->dev);
-
-fail:
-	kvm_unregister_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
-	kvm_unregister_irq_ack_notifier(kvm, &pit_state->irq_ack_notifier);
-	kvm_free_irq_source_id(kvm, pit->irq_source_id);
+fail_register_pit:
+	kvm_pit_set_reinject(pit, false);
 	kthread_stop(pit->worker_task);
+fail_kthread:
+	kvm_free_irq_source_id(kvm, pit->irq_source_id);
+fail_request:
 	kfree(pit);
 	return NULL;
 }
 
 void kvm_free_pit(struct kvm *kvm)
 {
-	struct hrtimer *timer;
-
-	if (kvm->arch.vpit) {
-		kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &kvm->arch.vpit->dev);
-		kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
-					      &kvm->arch.vpit->speaker_dev);
-		kvm_unregister_irq_mask_notifier(kvm, 0,
-					       &kvm->arch.vpit->mask_notifier);
-		kvm_unregister_irq_ack_notifier(kvm,
-				&kvm->arch.vpit->pit_state.irq_ack_notifier);
-		mutex_lock(&kvm->arch.vpit->pit_state.lock);
-		timer = &kvm->arch.vpit->pit_state.timer;
-		hrtimer_cancel(timer);
-		flush_kthread_work(&kvm->arch.vpit->expired);
-		kthread_stop(kvm->arch.vpit->worker_task);
-		kvm_free_irq_source_id(kvm, kvm->arch.vpit->irq_source_id);
-		mutex_unlock(&kvm->arch.vpit->pit_state.lock);
-		kfree(kvm->arch.vpit);
+	struct kvm_pit *pit = kvm->arch.vpit;
+
+	if (pit) {
+		kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->dev);
+		kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->speaker_dev);
+		kvm_pit_set_reinject(pit, false);
+		hrtimer_cancel(&pit->pit_state.timer);
+		flush_kthread_work(&pit->expired);
+		kthread_stop(pit->worker_task);
+		kvm_free_irq_source_id(kvm, pit->irq_source_id);
+		kfree(pit);
 	}
 }
diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h
index c84990b42b5b..2f5af0798326 100644
--- a/arch/x86/kvm/i8254.h
+++ b/arch/x86/kvm/i8254.h
@@ -22,19 +22,18 @@ struct kvm_kpit_channel_state {
 };
 
 struct kvm_kpit_state {
+	/* All members before "struct mutex lock" are protected by the lock. */
 	struct kvm_kpit_channel_state channels[3];
 	u32 flags;
 	bool is_periodic;
 	s64 period; 				/* unit: ns */
 	struct hrtimer timer;
-	atomic_t pending;			/* accumulated triggered timers */
-	bool reinject;
-	struct kvm *kvm;
 	u32    speaker_data_on;
+
 	struct mutex lock;
-	struct kvm_pit *pit;
-	spinlock_t inject_lock;
-	unsigned long irq_ack;
+	atomic_t reinject;
+	atomic_t pending; /* accumulated triggered timers */
+	atomic_t irq_ack;
 	struct kvm_irq_ack_notifier irq_ack_notifier;
 };
 
@@ -57,9 +56,11 @@ struct kvm_pit {
 #define KVM_MAX_PIT_INTR_INTERVAL   HZ / 100
 #define KVM_PIT_CHANNEL_MASK	    0x3
 
-void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val, int hpet_legacy_start);
 struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags);
 void kvm_free_pit(struct kvm *kvm);
-void kvm_pit_reset(struct kvm_pit *pit);
+
+void kvm_pit_load_count(struct kvm_pit *pit, int channel, u32 val,
+		int hpet_legacy_start);
+void kvm_pit_set_reinject(struct kvm_pit *pit, bool reinject);
 
 #endif
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 1facfd60b04a..9db47090ead0 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -94,7 +94,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
 static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic)
 {
 	ioapic->rtc_status.pending_eoi = 0;
-	bitmap_zero(ioapic->rtc_status.dest_map, KVM_MAX_VCPUS);
+	bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPUS);
 }
 
 static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic);
@@ -117,16 +117,16 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
 		return;
 
 	new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector);
-	old_val = test_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map);
+	old_val = test_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
 
 	if (new_val == old_val)
 		return;
 
 	if (new_val) {
-		__set_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map);
+		__set_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
 		ioapic->rtc_status.pending_eoi++;
 	} else {
-		__clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map);
+		__clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
 		ioapic->rtc_status.pending_eoi--;
 		rtc_status_pending_eoi_check_valid(ioapic);
 	}
@@ -156,7 +156,8 @@ static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic)
 
 static void rtc_irq_eoi(struct kvm_ioapic *ioapic, struct kvm_vcpu *vcpu)
 {
-	if (test_and_clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map)) {
+	if (test_and_clear_bit(vcpu->vcpu_id,
+			       ioapic->rtc_status.dest_map.map)) {
 		--ioapic->rtc_status.pending_eoi;
 		rtc_status_pending_eoi_check_valid(ioapic);
 	}
@@ -236,10 +237,17 @@ static void kvm_ioapic_inject_all(struct kvm_ioapic *ioapic, unsigned long irr)
 void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors)
 {
 	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
+	struct dest_map *dest_map = &ioapic->rtc_status.dest_map;
 	union kvm_ioapic_redirect_entry *e;
 	int index;
 
 	spin_lock(&ioapic->lock);
+
+	/* Make sure we see any missing RTC EOI */
+	if (test_bit(vcpu->vcpu_id, dest_map->map))
+		__set_bit(dest_map->vectors[vcpu->vcpu_id],
+			  ioapic_handled_vectors);
+
 	for (index = 0; index < IOAPIC_NUM_PINS; index++) {
 		e = &ioapic->redirtbl[index];
 		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
@@ -346,7 +354,7 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status)
 		 */
 		BUG_ON(ioapic->rtc_status.pending_eoi != 0);
 		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe,
-				ioapic->rtc_status.dest_map);
+					       &ioapic->rtc_status.dest_map);
 		ioapic->rtc_status.pending_eoi = (ret < 0 ? 0 : ret);
 	} else
 		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, NULL);
@@ -407,8 +415,14 @@ static void kvm_ioapic_eoi_inject_work(struct work_struct *work)
 static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
 			struct kvm_ioapic *ioapic, int vector, int trigger_mode)
 {
-	int i;
+	struct dest_map *dest_map = &ioapic->rtc_status.dest_map;
 	struct kvm_lapic *apic = vcpu->arch.apic;
+	int i;
+
+	/* RTC special handling */
+	if (test_bit(vcpu->vcpu_id, dest_map->map) &&
+	    vector == dest_map->vectors[vcpu->vcpu_id])
+		rtc_irq_eoi(ioapic, vcpu);
 
 	for (i = 0; i < IOAPIC_NUM_PINS; i++) {
 		union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
@@ -416,8 +430,6 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
 		if (ent->fields.vector != vector)
 			continue;
 
-		if (i == RTC_GSI)
-			rtc_irq_eoi(ioapic, vcpu);
 		/*
 		 * We are dropping lock while calling ack notifiers because ack
 		 * notifier callbacks for assigned devices call into IOAPIC
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index 2d16dc251d81..7d2692a49657 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -40,9 +40,21 @@ struct kvm_vcpu;
 #define RTC_GSI -1U
 #endif
 
+struct dest_map {
+	/* vcpu bitmap where IRQ has been sent */
+	DECLARE_BITMAP(map, KVM_MAX_VCPUS);
+
+	/*
+	 * Vector sent to a given vcpu, only valid when
+	 * the vcpu's bit in map is set
+	 */
+	u8 vectors[KVM_MAX_VCPUS];
+};
+
+
 struct rtc_status {
 	int pending_eoi;
-	DECLARE_BITMAP(dest_map, KVM_MAX_VCPUS);
+	struct dest_map dest_map;
 };
 
 union kvm_ioapic_redirect_entry {
@@ -118,7 +130,8 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
 		       int level, bool line_status);
 void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id);
 int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
-		struct kvm_lapic_irq *irq, unsigned long *dest_map);
+			     struct kvm_lapic_irq *irq,
+			     struct dest_map *dest_map);
 int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
 int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
 void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 3982b479bb5f..95fcc7b13866 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -33,7 +33,10 @@
  */
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
-	return apic_has_pending_timer(vcpu);
+	if (lapic_in_kernel(vcpu))
+		return apic_has_pending_timer(vcpu);
+
+	return 0;
 }
 EXPORT_SYMBOL(kvm_cpu_has_pending_timer);
 
@@ -137,8 +140,8 @@ EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt);
 
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu)
 {
-	kvm_inject_apic_timer_irqs(vcpu);
-	/* TODO: PIT, RTC etc. */
+	if (lapic_in_kernel(vcpu))
+		kvm_inject_apic_timer_irqs(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs);
 
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index ae5c78f2337d..61ebdc13a29a 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -109,14 +109,6 @@ static inline int irqchip_in_kernel(struct kvm *kvm)
 	return ret;
 }
 
-static inline int lapic_in_kernel(struct kvm_vcpu *vcpu)
-{
-	/* Same as irqchip_in_kernel(vcpu->kvm), but with less
-	 * pointer chasing and no unnecessary memory barriers.
-	 */
-	return vcpu->arch.apic != NULL;
-}
-
 void kvm_pic_reset(struct kvm_kpic_state *s);
 
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 8fc89efb5250..54ead79e444b 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -34,6 +34,7 @@
 #include "lapic.h"
 
 #include "hyperv.h"
+#include "x86.h"
 
 static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
 			   struct kvm *kvm, int irq_source_id, int level,
@@ -53,10 +54,12 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
 }
 
 int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
-		struct kvm_lapic_irq *irq, unsigned long *dest_map)
+		struct kvm_lapic_irq *irq, struct dest_map *dest_map)
 {
 	int i, r = -1;
 	struct kvm_vcpu *vcpu, *lowest = NULL;
+	unsigned long dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)];
+	unsigned int dest_vcpus = 0;
 
 	if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
 			kvm_lowest_prio_delivery(irq)) {
@@ -67,6 +70,8 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 	if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map))
 		return r;
 
+	memset(dest_vcpu_bitmap, 0, sizeof(dest_vcpu_bitmap));
+
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		if (!kvm_apic_present(vcpu))
 			continue;
@@ -80,13 +85,25 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 				r = 0;
 			r += kvm_apic_set_irq(vcpu, irq, dest_map);
 		} else if (kvm_lapic_enabled(vcpu)) {
-			if (!lowest)
-				lowest = vcpu;
-			else if (kvm_apic_compare_prio(vcpu, lowest) < 0)
-				lowest = vcpu;
+			if (!kvm_vector_hashing_enabled()) {
+				if (!lowest)
+					lowest = vcpu;
+				else if (kvm_apic_compare_prio(vcpu, lowest) < 0)
+					lowest = vcpu;
+			} else {
+				__set_bit(i, dest_vcpu_bitmap);
+				dest_vcpus++;
+			}
 		}
 	}
 
+	if (dest_vcpus != 0) {
+		int idx = kvm_vector_to_index(irq->vector, dest_vcpus,
+					dest_vcpu_bitmap, KVM_MAX_VCPUS);
+
+		lowest = kvm_get_vcpu(kvm, idx);
+	}
+
 	if (lowest)
 		r = kvm_apic_set_irq(lowest, irq, dest_map);
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 36591faed13b..443d2a57ad3d 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -281,7 +281,7 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu)
 	struct kvm_cpuid_entry2 *feat;
 	u32 v = APIC_VERSION;
 
-	if (!kvm_vcpu_has_lapic(vcpu))
+	if (!lapic_in_kernel(vcpu))
 		return;
 
 	feat = kvm_find_cpuid_entry(apic->vcpu, 0x1, 0);
@@ -475,26 +475,20 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
 
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
 {
-	int highest_irr;
-
 	/* This may race with setting of irr in __apic_accept_irq() and
 	 * value returned may be wrong, but kvm_vcpu_kick() in __apic_accept_irq
 	 * will cause vmexit immediately and the value will be recalculated
 	 * on the next vmentry.
 	 */
-	if (!kvm_vcpu_has_lapic(vcpu))
-		return 0;
-	highest_irr = apic_find_highest_irr(vcpu->arch.apic);
-
-	return highest_irr;
+	return apic_find_highest_irr(vcpu->arch.apic);
 }
 
 static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 			     int vector, int level, int trig_mode,
-			     unsigned long *dest_map);
+			     struct dest_map *dest_map);
 
 int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
-		unsigned long *dest_map)
+		     struct dest_map *dest_map)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
@@ -675,8 +669,33 @@ bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
 	}
 }
 
+int kvm_vector_to_index(u32 vector, u32 dest_vcpus,
+		       const unsigned long *bitmap, u32 bitmap_size)
+{
+	u32 mod;
+	int i, idx = -1;
+
+	mod = vector % dest_vcpus;
+
+	for (i = 0; i <= mod; i++) {
+		idx = find_next_bit(bitmap, bitmap_size, idx + 1);
+		BUG_ON(idx == bitmap_size);
+	}
+
+	return idx;
+}
+
+static void kvm_apic_disabled_lapic_found(struct kvm *kvm)
+{
+	if (!kvm->arch.disabled_lapic_found) {
+		kvm->arch.disabled_lapic_found = true;
+		printk(KERN_INFO
+		       "Disabled LAPIC found during irq injection\n");
+	}
+}
+
 bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
-		struct kvm_lapic_irq *irq, int *r, unsigned long *dest_map)
+		struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map)
 {
 	struct kvm_apic_map *map;
 	unsigned long bitmap = 1;
@@ -727,21 +746,42 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
 
 		dst = map->logical_map[cid];
 
-		if (kvm_lowest_prio_delivery(irq)) {
+		if (!kvm_lowest_prio_delivery(irq))
+			goto set_irq;
+
+		if (!kvm_vector_hashing_enabled()) {
 			int l = -1;
 			for_each_set_bit(i, &bitmap, 16) {
 				if (!dst[i])
 					continue;
 				if (l < 0)
 					l = i;
-				else if (kvm_apic_compare_prio(dst[i]->vcpu, dst[l]->vcpu) < 0)
+				else if (kvm_apic_compare_prio(dst[i]->vcpu,
+							dst[l]->vcpu) < 0)
 					l = i;
 			}
-
 			bitmap = (l >= 0) ? 1 << l : 0;
+		} else {
+			int idx;
+			unsigned int dest_vcpus;
+
+			dest_vcpus = hweight16(bitmap);
+			if (dest_vcpus == 0)
+				goto out;
+
+			idx = kvm_vector_to_index(irq->vector,
+				dest_vcpus, &bitmap, 16);
+
+			if (!dst[idx]) {
+				kvm_apic_disabled_lapic_found(kvm);
+				goto out;
+			}
+
+			bitmap = (idx >= 0) ? 1 << idx : 0;
 		}
 	}
 
+set_irq:
 	for_each_set_bit(i, &bitmap, 16) {
 		if (!dst[i])
 			continue;
@@ -754,6 +794,20 @@ out:
 	return ret;
 }
 
+/*
+ * This routine tries to handler interrupts in posted mode, here is how
+ * it deals with different cases:
+ * - For single-destination interrupts, handle it in posted mode
+ * - Else if vector hashing is enabled and it is a lowest-priority
+ *   interrupt, handle it in posted mode and use the following mechanism
+ *   to find the destinaiton vCPU.
+ *	1. For lowest-priority interrupts, store all the possible
+ *	   destination vCPUs in an array.
+ *	2. Use "guest vector % max number of destination vCPUs" to find
+ *	   the right destination vCPU in the array for the lowest-priority
+ *	   interrupt.
+ * - Otherwise, use remapped mode to inject the interrupt.
+ */
 bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
 			struct kvm_vcpu **dest_vcpu)
 {
@@ -795,16 +849,37 @@ bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
 		if (cid >= ARRAY_SIZE(map->logical_map))
 			goto out;
 
-		for_each_set_bit(i, &bitmap, 16) {
-			dst = map->logical_map[cid][i];
-			if (++r == 2)
+		if (kvm_vector_hashing_enabled() &&
+				kvm_lowest_prio_delivery(irq)) {
+			int idx;
+			unsigned int dest_vcpus;
+
+			dest_vcpus = hweight16(bitmap);
+			if (dest_vcpus == 0)
 				goto out;
-		}
 
-		if (dst && kvm_apic_present(dst->vcpu))
+			idx = kvm_vector_to_index(irq->vector, dest_vcpus,
+						  &bitmap, 16);
+
+			dst = map->logical_map[cid][idx];
+			if (!dst) {
+				kvm_apic_disabled_lapic_found(kvm);
+				goto out;
+			}
+
 			*dest_vcpu = dst->vcpu;
-		else
-			goto out;
+		} else {
+			for_each_set_bit(i, &bitmap, 16) {
+				dst = map->logical_map[cid][i];
+				if (++r == 2)
+					goto out;
+			}
+
+			if (dst && kvm_apic_present(dst->vcpu))
+				*dest_vcpu = dst->vcpu;
+			else
+				goto out;
+		}
 	}
 
 	ret = true;
@@ -819,7 +894,7 @@ out:
  */
 static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 			     int vector, int level, int trig_mode,
-			     unsigned long *dest_map)
+			     struct dest_map *dest_map)
 {
 	int result = 0;
 	struct kvm_vcpu *vcpu = apic->vcpu;
@@ -839,8 +914,10 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 
 		result = 1;
 
-		if (dest_map)
-			__set_bit(vcpu->vcpu_id, dest_map);
+		if (dest_map) {
+			__set_bit(vcpu->vcpu_id, dest_map->map);
+			dest_map->vectors[vcpu->vcpu_id] = vector;
+		}
 
 		if (apic_test_vector(vector, apic->regs + APIC_TMR) != !!trig_mode) {
 			if (trig_mode)
@@ -1195,7 +1272,7 @@ static void apic_update_lvtt(struct kvm_lapic *apic)
 static void apic_timer_expired(struct kvm_lapic *apic)
 {
 	struct kvm_vcpu *vcpu = apic->vcpu;
-	wait_queue_head_t *q = &vcpu->wq;
+	struct swait_queue_head *q = &vcpu->wq;
 	struct kvm_timer *ktimer = &apic->lapic_timer;
 
 	if (atomic_read(&apic->lapic_timer.pending))
@@ -1204,8 +1281,8 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 	atomic_inc(&apic->lapic_timer.pending);
 	kvm_set_pending_timer(vcpu);
 
-	if (waitqueue_active(q))
-		wake_up_interruptible(q);
+	if (swait_active(q))
+		swake_up(q);
 
 	if (apic_lvtt_tscdeadline(apic))
 		ktimer->expired_tscdeadline = ktimer->tscdeadline;
@@ -1239,7 +1316,7 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u64 guest_tsc, tsc_deadline;
 
-	if (!kvm_vcpu_has_lapic(vcpu))
+	if (!lapic_in_kernel(vcpu))
 		return;
 
 	if (apic->lapic_timer.expired_tscdeadline == 0)
@@ -1515,8 +1592,7 @@ static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
 
 void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu)
 {
-	if (kvm_vcpu_has_lapic(vcpu))
-		apic_reg_write(vcpu->arch.apic, APIC_EOI, 0);
+	apic_reg_write(vcpu->arch.apic, APIC_EOI, 0);
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi);
 
@@ -1566,7 +1642,7 @@ u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!kvm_vcpu_has_lapic(vcpu) || apic_lvtt_oneshot(apic) ||
+	if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) ||
 			apic_lvtt_period(apic))
 		return 0;
 
@@ -1577,7 +1653,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!kvm_vcpu_has_lapic(vcpu) || apic_lvtt_oneshot(apic) ||
+	if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) ||
 			apic_lvtt_period(apic))
 		return;
 
@@ -1590,9 +1666,6 @@ void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!kvm_vcpu_has_lapic(vcpu))
-		return;
-
 	apic_set_tpr(apic, ((cr8 & 0x0f) << 4)
 		     | (kvm_apic_get_reg(apic, APIC_TASKPRI) & 4));
 }
@@ -1601,9 +1674,6 @@ u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu)
 {
 	u64 tpr;
 
-	if (!kvm_vcpu_has_lapic(vcpu))
-		return 0;
-
 	tpr = (u64) kvm_apic_get_reg(vcpu->arch.apic, APIC_TASKPRI);
 
 	return (tpr & 0xf0) >> 4;
@@ -1728,8 +1798,7 @@ int apic_has_pending_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (kvm_vcpu_has_lapic(vcpu) && apic_enabled(apic) &&
-			apic_lvt_enabled(apic, APIC_LVTT))
+	if (apic_enabled(apic) && apic_lvt_enabled(apic, APIC_LVTT))
 		return atomic_read(&apic->lapic_timer.pending);
 
 	return 0;
@@ -1826,7 +1895,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	int highest_irr;
 
-	if (!kvm_vcpu_has_lapic(vcpu) || !apic_enabled(apic))
+	if (!apic_enabled(apic))
 		return -1;
 
 	apic_update_ppr(apic);
@@ -1854,9 +1923,6 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!kvm_vcpu_has_lapic(vcpu))
-		return;
-
 	if (atomic_read(&apic->lapic_timer.pending) > 0) {
 		kvm_apic_local_deliver(apic, APIC_LVTT);
 		if (apic_lvtt_tscdeadline(apic))
@@ -1932,7 +1998,7 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
 {
 	struct hrtimer *timer;
 
-	if (!kvm_vcpu_has_lapic(vcpu))
+	if (!lapic_in_kernel(vcpu))
 		return;
 
 	timer = &vcpu->arch.apic->lapic_timer.timer;
@@ -2105,7 +2171,7 @@ int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 reg, u64 data)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!kvm_vcpu_has_lapic(vcpu))
+	if (!lapic_in_kernel(vcpu))
 		return 1;
 
 	/* if this is ICR write vector before command */
@@ -2119,7 +2185,7 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u32 low, high = 0;
 
-	if (!kvm_vcpu_has_lapic(vcpu))
+	if (!lapic_in_kernel(vcpu))
 		return 1;
 
 	if (apic_reg_read(apic, reg, 4, &low))
@@ -2151,7 +2217,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 	u8 sipi_vector;
 	unsigned long pe;
 
-	if (!kvm_vcpu_has_lapic(vcpu) || !apic->pending_events)
+	if (!lapic_in_kernel(vcpu) || !apic->pending_events)
 		return;
 
 	/*
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 41bdb35b4b67..f71183e502ee 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -42,6 +42,9 @@ struct kvm_lapic {
 	unsigned long pending_events;
 	unsigned int sipi_vector;
 };
+
+struct dest_map;
+
 int kvm_create_lapic(struct kvm_vcpu *vcpu);
 void kvm_free_lapic(struct kvm_vcpu *vcpu);
 
@@ -60,11 +63,11 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu);
 void __kvm_apic_update_irr(u32 *pir, void *regs);
 void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir);
 int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
-		unsigned long *dest_map);
+		     struct dest_map *dest_map);
 int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type);
 
 bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
-		struct kvm_lapic_irq *irq, int *r, unsigned long *dest_map);
+		struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map);
 
 u64 kvm_get_apic_base(struct kvm_vcpu *vcpu);
 int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
@@ -103,7 +106,7 @@ static inline u32 kvm_apic_get_reg(struct kvm_lapic *apic, int reg_off)
 
 extern struct static_key kvm_no_apic_vcpu;
 
-static inline bool kvm_vcpu_has_lapic(struct kvm_vcpu *vcpu)
+static inline bool lapic_in_kernel(struct kvm_vcpu *vcpu)
 {
 	if (static_key_false(&kvm_no_apic_vcpu))
 		return vcpu->arch.apic;
@@ -130,7 +133,7 @@ static inline bool kvm_apic_sw_enabled(struct kvm_lapic *apic)
 
 static inline bool kvm_apic_present(struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_has_lapic(vcpu) && kvm_apic_hw_enabled(vcpu->arch.apic);
+	return lapic_in_kernel(vcpu) && kvm_apic_hw_enabled(vcpu->arch.apic);
 }
 
 static inline int kvm_lapic_enabled(struct kvm_vcpu *vcpu)
@@ -150,7 +153,7 @@ static inline bool kvm_vcpu_apicv_active(struct kvm_vcpu *vcpu)
 
 static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_has_lapic(vcpu) && vcpu->arch.apic->pending_events;
+	return lapic_in_kernel(vcpu) && vcpu->arch.apic->pending_events;
 }
 
 static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq)
@@ -161,7 +164,7 @@ static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq)
 
 static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_has_lapic(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+	return lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
 }
 
 static inline int kvm_apic_id(struct kvm_lapic *apic)
@@ -175,4 +178,6 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu);
 
 bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
 			struct kvm_vcpu **dest_vcpu);
+int kvm_vector_to_index(u32 vector, u32 dest_vcpus,
+			const unsigned long *bitmap, u32 bitmap_size);
 #endif
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 95a955de5964..c512f095cdac 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -41,6 +41,7 @@
 #include <asm/cmpxchg.h>
 #include <asm/io.h>
 #include <asm/vmx.h>
+#include <asm/kvm_page_track.h>
 
 /*
  * When setting this variable to true it enables Two-Dimensional-Paging
@@ -776,62 +777,85 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn,
 	return &slot->arch.lpage_info[level - 2][idx];
 }
 
+static void update_gfn_disallow_lpage_count(struct kvm_memory_slot *slot,
+					    gfn_t gfn, int count)
+{
+	struct kvm_lpage_info *linfo;
+	int i;
+
+	for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
+		linfo = lpage_info_slot(gfn, slot, i);
+		linfo->disallow_lpage += count;
+		WARN_ON(linfo->disallow_lpage < 0);
+	}
+}
+
+void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn)
+{
+	update_gfn_disallow_lpage_count(slot, gfn, 1);
+}
+
+void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn)
+{
+	update_gfn_disallow_lpage_count(slot, gfn, -1);
+}
+
 static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *slot;
-	struct kvm_lpage_info *linfo;
 	gfn_t gfn;
-	int i;
 
+	kvm->arch.indirect_shadow_pages++;
 	gfn = sp->gfn;
 	slots = kvm_memslots_for_spte_role(kvm, sp->role);
 	slot = __gfn_to_memslot(slots, gfn);
-	for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
-		linfo = lpage_info_slot(gfn, slot, i);
-		linfo->write_count += 1;
-	}
-	kvm->arch.indirect_shadow_pages++;
+
+	/* the non-leaf shadow pages are keeping readonly. */
+	if (sp->role.level > PT_PAGE_TABLE_LEVEL)
+		return kvm_slot_page_track_add_page(kvm, slot, gfn,
+						    KVM_PAGE_TRACK_WRITE);
+
+	kvm_mmu_gfn_disallow_lpage(slot, gfn);
 }
 
 static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *slot;
-	struct kvm_lpage_info *linfo;
 	gfn_t gfn;
-	int i;
 
+	kvm->arch.indirect_shadow_pages--;
 	gfn = sp->gfn;
 	slots = kvm_memslots_for_spte_role(kvm, sp->role);
 	slot = __gfn_to_memslot(slots, gfn);
-	for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
-		linfo = lpage_info_slot(gfn, slot, i);
-		linfo->write_count -= 1;
-		WARN_ON(linfo->write_count < 0);
-	}
-	kvm->arch.indirect_shadow_pages--;
+	if (sp->role.level > PT_PAGE_TABLE_LEVEL)
+		return kvm_slot_page_track_remove_page(kvm, slot, gfn,
+						       KVM_PAGE_TRACK_WRITE);
+
+	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
 
-static int __has_wrprotected_page(gfn_t gfn, int level,
-				  struct kvm_memory_slot *slot)
+static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level,
+					  struct kvm_memory_slot *slot)
 {
 	struct kvm_lpage_info *linfo;
 
 	if (slot) {
 		linfo = lpage_info_slot(gfn, slot, level);
-		return linfo->write_count;
+		return !!linfo->disallow_lpage;
 	}
 
-	return 1;
+	return true;
 }
 
-static int has_wrprotected_page(struct kvm_vcpu *vcpu, gfn_t gfn, int level)
+static bool mmu_gfn_lpage_is_disallowed(struct kvm_vcpu *vcpu, gfn_t gfn,
+					int level)
 {
 	struct kvm_memory_slot *slot;
 
 	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
-	return __has_wrprotected_page(gfn, level, slot);
+	return __mmu_gfn_lpage_is_disallowed(gfn, level, slot);
 }
 
 static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
@@ -897,7 +921,7 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn,
 	max_level = min(kvm_x86_ops->get_lpage_level(), host_level);
 
 	for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level)
-		if (__has_wrprotected_page(large_gfn, level, slot))
+		if (__mmu_gfn_lpage_is_disallowed(large_gfn, level, slot))
 			break;
 
 	return level - 1;
@@ -1323,23 +1347,29 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 		kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
 }
 
-static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
+bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
+				    struct kvm_memory_slot *slot, u64 gfn)
 {
-	struct kvm_memory_slot *slot;
 	struct kvm_rmap_head *rmap_head;
 	int i;
 	bool write_protected = false;
 
-	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
-
 	for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
 		rmap_head = __gfn_to_rmap(gfn, i, slot);
-		write_protected |= __rmap_write_protect(vcpu->kvm, rmap_head, true);
+		write_protected |= __rmap_write_protect(kvm, rmap_head, true);
 	}
 
 	return write_protected;
 }
 
+static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
+{
+	struct kvm_memory_slot *slot;
+
+	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+	return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn);
+}
+
 static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
 {
 	u64 *sptep;
@@ -1754,7 +1784,7 @@ static void mark_unsync(u64 *spte)
 static int nonpaging_sync_page(struct kvm_vcpu *vcpu,
 			       struct kvm_mmu_page *sp)
 {
-	return 1;
+	return 0;
 }
 
 static void nonpaging_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
@@ -1840,13 +1870,16 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp,
 	return nr_unsync_leaf;
 }
 
+#define INVALID_INDEX (-1)
+
 static int mmu_unsync_walk(struct kvm_mmu_page *sp,
 			   struct kvm_mmu_pages *pvec)
 {
+	pvec->nr = 0;
 	if (!sp->unsync_children)
 		return 0;
 
-	mmu_pages_add(pvec, sp, 0);
+	mmu_pages_add(pvec, sp, INVALID_INDEX);
 	return __mmu_unsync_walk(sp, pvec);
 }
 
@@ -1883,37 +1916,35 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 		if ((_sp)->role.direct || (_sp)->role.invalid) {} else
 
 /* @sp->gfn should be write-protected at the call site */
-static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
-			   struct list_head *invalid_list, bool clear_unsync)
+static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+			    struct list_head *invalid_list)
 {
 	if (sp->role.cr4_pae != !!is_pae(vcpu)) {
 		kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
-		return 1;
+		return false;
 	}
 
-	if (clear_unsync)
-		kvm_unlink_unsync_page(vcpu->kvm, sp);
-
-	if (vcpu->arch.mmu.sync_page(vcpu, sp)) {
+	if (vcpu->arch.mmu.sync_page(vcpu, sp) == 0) {
 		kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
-		return 1;
+		return false;
 	}
 
-	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
-	return 0;
+	return true;
 }
 
-static int kvm_sync_page_transient(struct kvm_vcpu *vcpu,
-				   struct kvm_mmu_page *sp)
+static void kvm_mmu_flush_or_zap(struct kvm_vcpu *vcpu,
+				 struct list_head *invalid_list,
+				 bool remote_flush, bool local_flush)
 {
-	LIST_HEAD(invalid_list);
-	int ret;
-
-	ret = __kvm_sync_page(vcpu, sp, &invalid_list, false);
-	if (ret)
-		kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
+	if (!list_empty(invalid_list)) {
+		kvm_mmu_commit_zap_page(vcpu->kvm, invalid_list);
+		return;
+	}
 
-	return ret;
+	if (remote_flush)
+		kvm_flush_remote_tlbs(vcpu->kvm);
+	else if (local_flush)
+		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 }
 
 #ifdef CONFIG_KVM_MMU_AUDIT
@@ -1923,46 +1954,38 @@ static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { }
 static void mmu_audit_disable(void) { }
 #endif
 
-static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 			 struct list_head *invalid_list)
 {
-	return __kvm_sync_page(vcpu, sp, invalid_list, true);
+	kvm_unlink_unsync_page(vcpu->kvm, sp);
+	return __kvm_sync_page(vcpu, sp, invalid_list);
 }
 
 /* @gfn should be write-protected at the call site */
-static void kvm_sync_pages(struct kvm_vcpu *vcpu,  gfn_t gfn)
+static bool kvm_sync_pages(struct kvm_vcpu *vcpu, gfn_t gfn,
+			   struct list_head *invalid_list)
 {
 	struct kvm_mmu_page *s;
-	LIST_HEAD(invalid_list);
-	bool flush = false;
+	bool ret = false;
 
 	for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
 		if (!s->unsync)
 			continue;
 
 		WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL);
-		kvm_unlink_unsync_page(vcpu->kvm, s);
-		if ((s->role.cr4_pae != !!is_pae(vcpu)) ||
-			(vcpu->arch.mmu.sync_page(vcpu, s))) {
-			kvm_mmu_prepare_zap_page(vcpu->kvm, s, &invalid_list);
-			continue;
-		}
-		flush = true;
+		ret |= kvm_sync_page(vcpu, s, invalid_list);
 	}
 
-	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
-	if (flush)
-		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+	return ret;
 }
 
 struct mmu_page_path {
-	struct kvm_mmu_page *parent[PT64_ROOT_LEVEL-1];
-	unsigned int idx[PT64_ROOT_LEVEL-1];
+	struct kvm_mmu_page *parent[PT64_ROOT_LEVEL];
+	unsigned int idx[PT64_ROOT_LEVEL];
 };
 
 #define for_each_sp(pvec, sp, parents, i)			\
-		for (i = mmu_pages_next(&pvec, &parents, -1),	\
-			sp = pvec.page[i].sp;			\
+		for (i = mmu_pages_first(&pvec, &parents);	\
 			i < pvec.nr && ({ sp = pvec.page[i].sp; 1;});	\
 			i = mmu_pages_next(&pvec, &parents, i))
 
@@ -1974,19 +1997,43 @@ static int mmu_pages_next(struct kvm_mmu_pages *pvec,
 
 	for (n = i+1; n < pvec->nr; n++) {
 		struct kvm_mmu_page *sp = pvec->page[n].sp;
+		unsigned idx = pvec->page[n].idx;
+		int level = sp->role.level;
 
-		if (sp->role.level == PT_PAGE_TABLE_LEVEL) {
-			parents->idx[0] = pvec->page[n].idx;
-			return n;
-		}
+		parents->idx[level-1] = idx;
+		if (level == PT_PAGE_TABLE_LEVEL)
+			break;
 
-		parents->parent[sp->role.level-2] = sp;
-		parents->idx[sp->role.level-1] = pvec->page[n].idx;
+		parents->parent[level-2] = sp;
 	}
 
 	return n;
 }
 
+static int mmu_pages_first(struct kvm_mmu_pages *pvec,
+			   struct mmu_page_path *parents)
+{
+	struct kvm_mmu_page *sp;
+	int level;
+
+	if (pvec->nr == 0)
+		return 0;
+
+	WARN_ON(pvec->page[0].idx != INVALID_INDEX);
+
+	sp = pvec->page[0].sp;
+	level = sp->role.level;
+	WARN_ON(level == PT_PAGE_TABLE_LEVEL);
+
+	parents->parent[level-2] = sp;
+
+	/* Also set up a sentinel.  Further entries in pvec are all
+	 * children of sp, so this element is never overwritten.
+	 */
+	parents->parent[level-1] = NULL;
+	return mmu_pages_next(pvec, parents, 0);
+}
+
 static void mmu_pages_clear_parents(struct mmu_page_path *parents)
 {
 	struct kvm_mmu_page *sp;
@@ -1994,22 +2041,14 @@ static void mmu_pages_clear_parents(struct mmu_page_path *parents)
 
 	do {
 		unsigned int idx = parents->idx[level];
-
 		sp = parents->parent[level];
 		if (!sp)
 			return;
 
+		WARN_ON(idx == INVALID_INDEX);
 		clear_unsync_child_bit(sp, idx);
 		level++;
-	} while (level < PT64_ROOT_LEVEL-1 && !sp->unsync_children);
-}
-
-static void kvm_mmu_pages_init(struct kvm_mmu_page *parent,
-			       struct mmu_page_path *parents,
-			       struct kvm_mmu_pages *pvec)
-{
-	parents->parent[parent->role.level-1] = NULL;
-	pvec->nr = 0;
+	} while (!sp->unsync_children);
 }
 
 static void mmu_sync_children(struct kvm_vcpu *vcpu,
@@ -2020,30 +2059,36 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu,
 	struct mmu_page_path parents;
 	struct kvm_mmu_pages pages;
 	LIST_HEAD(invalid_list);
+	bool flush = false;
 
-	kvm_mmu_pages_init(parent, &parents, &pages);
 	while (mmu_unsync_walk(parent, &pages)) {
 		bool protected = false;
 
 		for_each_sp(pages, sp, parents, i)
 			protected |= rmap_write_protect(vcpu, sp->gfn);
 
-		if (protected)
+		if (protected) {
 			kvm_flush_remote_tlbs(vcpu->kvm);
+			flush = false;
+		}
 
 		for_each_sp(pages, sp, parents, i) {
-			kvm_sync_page(vcpu, sp, &invalid_list);
+			flush |= kvm_sync_page(vcpu, sp, &invalid_list);
 			mmu_pages_clear_parents(&parents);
 		}
-		kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
-		cond_resched_lock(&vcpu->kvm->mmu_lock);
-		kvm_mmu_pages_init(parent, &parents, &pages);
+		if (need_resched() || spin_needbreak(&vcpu->kvm->mmu_lock)) {
+			kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
+			cond_resched_lock(&vcpu->kvm->mmu_lock);
+			flush = false;
+		}
 	}
+
+	kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
 }
 
 static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp)
 {
-	sp->write_flooding_count = 0;
+	atomic_set(&sp->write_flooding_count,  0);
 }
 
 static void clear_sp_write_flooding_count(u64 *spte)
@@ -2069,6 +2114,8 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	unsigned quadrant;
 	struct kvm_mmu_page *sp;
 	bool need_sync = false;
+	bool flush = false;
+	LIST_HEAD(invalid_list);
 
 	role = vcpu->arch.mmu.base_role;
 	role.level = level;
@@ -2092,8 +2139,16 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 		if (sp->role.word != role.word)
 			continue;
 
-		if (sp->unsync && kvm_sync_page_transient(vcpu, sp))
-			break;
+		if (sp->unsync) {
+			/* The page is good, but __kvm_sync_page might still end
+			 * up zapping it.  If so, break in order to rebuild it.
+			 */
+			if (!__kvm_sync_page(vcpu, sp, &invalid_list))
+				break;
+
+			WARN_ON(!list_empty(&invalid_list));
+			kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+		}
 
 		if (sp->unsync_children)
 			kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
@@ -2112,16 +2167,24 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	hlist_add_head(&sp->hash_link,
 		&vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]);
 	if (!direct) {
-		if (rmap_write_protect(vcpu, gfn))
+		/*
+		 * we should do write protection before syncing pages
+		 * otherwise the content of the synced shadow page may
+		 * be inconsistent with guest page table.
+		 */
+		account_shadowed(vcpu->kvm, sp);
+		if (level == PT_PAGE_TABLE_LEVEL &&
+		      rmap_write_protect(vcpu, gfn))
 			kvm_flush_remote_tlbs(vcpu->kvm);
-		if (level > PT_PAGE_TABLE_LEVEL && need_sync)
-			kvm_sync_pages(vcpu, gfn);
 
-		account_shadowed(vcpu->kvm, sp);
+		if (level > PT_PAGE_TABLE_LEVEL && need_sync)
+			flush |= kvm_sync_pages(vcpu, gfn, &invalid_list);
 	}
 	sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen;
 	clear_page(sp->spt);
 	trace_kvm_mmu_get_page(sp, true);
+
+	kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
 	return sp;
 }
 
@@ -2269,7 +2332,6 @@ static int mmu_zap_unsync_children(struct kvm *kvm,
 	if (parent->role.level == PT_PAGE_TABLE_LEVEL)
 		return 0;
 
-	kvm_mmu_pages_init(parent, &parents, &pages);
 	while (mmu_unsync_walk(parent, &pages)) {
 		struct kvm_mmu_page *sp;
 
@@ -2278,7 +2340,6 @@ static int mmu_zap_unsync_children(struct kvm *kvm,
 			mmu_pages_clear_parents(&parents);
 			zapped++;
 		}
-		kvm_mmu_pages_init(parent, &parents, &pages);
 	}
 
 	return zapped;
@@ -2354,8 +2415,8 @@ static bool prepare_zap_oldest_mmu_page(struct kvm *kvm,
 	if (list_empty(&kvm->arch.active_mmu_pages))
 		return false;
 
-	sp = list_entry(kvm->arch.active_mmu_pages.prev,
-			struct kvm_mmu_page, link);
+	sp = list_last_entry(&kvm->arch.active_mmu_pages,
+			     struct kvm_mmu_page, link);
 	kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
 
 	return true;
@@ -2408,7 +2469,7 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page);
 
-static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
+static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
 	trace_kvm_mmu_unsync_page(sp);
 	++vcpu->kvm->stat.mmu_unsync;
@@ -2417,37 +2478,26 @@ static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 	kvm_mmu_mark_parents_unsync(sp);
 }
 
-static void kvm_unsync_pages(struct kvm_vcpu *vcpu,  gfn_t gfn)
+static bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
+				   bool can_unsync)
 {
-	struct kvm_mmu_page *s;
-
-	for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
-		if (s->unsync)
-			continue;
-		WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL);
-		__kvm_unsync_page(vcpu, s);
-	}
-}
+	struct kvm_mmu_page *sp;
 
-static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
-				  bool can_unsync)
-{
-	struct kvm_mmu_page *s;
-	bool need_unsync = false;
+	if (kvm_page_track_is_active(vcpu, gfn, KVM_PAGE_TRACK_WRITE))
+		return true;
 
-	for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
+	for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
 		if (!can_unsync)
-			return 1;
+			return true;
 
-		if (s->role.level != PT_PAGE_TABLE_LEVEL)
-			return 1;
+		if (sp->unsync)
+			continue;
 
-		if (!s->unsync)
-			need_unsync = true;
+		WARN_ON(sp->role.level != PT_PAGE_TABLE_LEVEL);
+		kvm_unsync_page(vcpu, sp);
 	}
-	if (need_unsync)
-		kvm_unsync_pages(vcpu, gfn);
-	return 0;
+
+	return false;
 }
 
 static bool kvm_is_mmio_pfn(kvm_pfn_t pfn)
@@ -2503,7 +2553,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		 * be fixed if guest refault.
 		 */
 		if (level > PT_PAGE_TABLE_LEVEL &&
-		    has_wrprotected_page(vcpu, gfn, level))
+		    mmu_gfn_lpage_is_disallowed(vcpu, gfn, level))
 			goto done;
 
 		spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE;
@@ -2768,7 +2818,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
 	if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
 	    level == PT_PAGE_TABLE_LEVEL &&
 	    PageTransCompound(pfn_to_page(pfn)) &&
-	    !has_wrprotected_page(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
+	    !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
 		unsigned long mask;
 		/*
 		 * mmu_notifier_retry was successful and we hold the
@@ -2796,20 +2846,16 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
 static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
 				kvm_pfn_t pfn, unsigned access, int *ret_val)
 {
-	bool ret = true;
-
 	/* The pfn is invalid, report the error! */
 	if (unlikely(is_error_pfn(pfn))) {
 		*ret_val = kvm_handle_bad_page(vcpu, gfn, pfn);
-		goto exit;
+		return true;
 	}
 
 	if (unlikely(is_noslot_pfn(pfn)))
 		vcpu_cache_mmio_info(vcpu, gva, gfn, access);
 
-	ret = false;
-exit:
-	return ret;
+	return false;
 }
 
 static bool page_fault_can_be_fast(u32 error_code)
@@ -3273,7 +3319,7 @@ static bool is_shadow_zero_bits_set(struct kvm_mmu *mmu, u64 spte, int level)
 	return __is_rsvd_bits_set(&mmu->shadow_zero_check, spte, level);
 }
 
-static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct)
+static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct)
 {
 	if (direct)
 		return vcpu_match_mmio_gpa(vcpu, addr);
@@ -3332,7 +3378,7 @@ int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct)
 	u64 spte;
 	bool reserved;
 
-	if (quickly_check_mmio_pf(vcpu, addr, direct))
+	if (mmio_info_in_cache(vcpu, addr, direct))
 		return RET_MMIO_PF_EMULATE;
 
 	reserved = walk_shadow_page_get_mmio_spte(vcpu, addr, &spte);
@@ -3362,20 +3408,53 @@ int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct)
 }
 EXPORT_SYMBOL_GPL(handle_mmio_page_fault);
 
+static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu,
+					 u32 error_code, gfn_t gfn)
+{
+	if (unlikely(error_code & PFERR_RSVD_MASK))
+		return false;
+
+	if (!(error_code & PFERR_PRESENT_MASK) ||
+	      !(error_code & PFERR_WRITE_MASK))
+		return false;
+
+	/*
+	 * guest is writing the page which is write tracked which can
+	 * not be fixed by page fault handler.
+	 */
+	if (kvm_page_track_is_active(vcpu, gfn, KVM_PAGE_TRACK_WRITE))
+		return true;
+
+	return false;
+}
+
+static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr)
+{
+	struct kvm_shadow_walk_iterator iterator;
+	u64 spte;
+
+	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+		return;
+
+	walk_shadow_page_lockless_begin(vcpu);
+	for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) {
+		clear_sp_write_flooding_count(iterator.sptep);
+		if (!is_shadow_present_pte(spte))
+			break;
+	}
+	walk_shadow_page_lockless_end(vcpu);
+}
+
 static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
 				u32 error_code, bool prefault)
 {
-	gfn_t gfn;
+	gfn_t gfn = gva >> PAGE_SHIFT;
 	int r;
 
 	pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code);
 
-	if (unlikely(error_code & PFERR_RSVD_MASK)) {
-		r = handle_mmio_page_fault(vcpu, gva, true);
-
-		if (likely(r != RET_MMIO_PF_INVALID))
-			return r;
-	}
+	if (page_fault_handle_page_track(vcpu, error_code, gfn))
+		return 1;
 
 	r = mmu_topup_memory_caches(vcpu);
 	if (r)
@@ -3383,7 +3462,6 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
 
 	MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
 
-	gfn = gva >> PAGE_SHIFT;
 
 	return nonpaging_map(vcpu, gva & PAGE_MASK,
 			     error_code, gfn, prefault);
@@ -3460,12 +3538,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
 
 	MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
 
-	if (unlikely(error_code & PFERR_RSVD_MASK)) {
-		r = handle_mmio_page_fault(vcpu, gpa, true);
-
-		if (likely(r != RET_MMIO_PF_INVALID))
-			return r;
-	}
+	if (page_fault_handle_page_track(vcpu, error_code, gfn))
+		return 1;
 
 	r = mmu_topup_memory_caches(vcpu);
 	if (r)
@@ -3558,13 +3632,24 @@ static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
 	return false;
 }
 
-static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gpte)
+static inline bool is_last_gpte(struct kvm_mmu *mmu,
+				unsigned level, unsigned gpte)
 {
-	unsigned index;
+	/*
+	 * PT_PAGE_TABLE_LEVEL always terminates.  The RHS has bit 7 set
+	 * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means
+	 * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then.
+	 */
+	gpte |= level - PT_PAGE_TABLE_LEVEL - 1;
 
-	index = level - 1;
-	index |= (gpte & PT_PAGE_SIZE_MASK) >> (PT_PAGE_SIZE_SHIFT - 2);
-	return mmu->last_pte_bitmap & (1 << index);
+	/*
+	 * The RHS has bit 7 set iff level < mmu->last_nonleaf_level.
+	 * If it is clear, there are no large pages at this level, so clear
+	 * PT_PAGE_SIZE_MASK in gpte if that is the case.
+	 */
+	gpte &= level - mmu->last_nonleaf_level;
+
+	return gpte & PT_PAGE_SIZE_MASK;
 }
 
 #define PTTYPE_EPT 18 /* arbitrary */
@@ -3721,13 +3806,15 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
 void
 reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 {
+	bool uses_nx = context->nx || context->base_role.smep_andnot_wp;
+
 	/*
 	 * Passing "true" to the last argument is okay; it adds a check
 	 * on bit 8 of the SPTEs which KVM doesn't use anyway.
 	 */
 	__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
 				boot_cpu_data.x86_phys_bits,
-				context->shadow_root_level, context->nx,
+				context->shadow_root_level, uses_nx,
 				guest_cpuid_has_gbpages(vcpu), is_pse(vcpu),
 				true);
 }
@@ -3836,22 +3923,13 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu,
 	}
 }
 
-static void update_last_pte_bitmap(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
+static void update_last_nonleaf_level(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
 {
-	u8 map;
-	unsigned level, root_level = mmu->root_level;
-	const unsigned ps_set_index = 1 << 2;  /* bit 2 of index: ps */
-
-	if (root_level == PT32E_ROOT_LEVEL)
-		--root_level;
-	/* PT_PAGE_TABLE_LEVEL always terminates */
-	map = 1 | (1 << ps_set_index);
-	for (level = PT_DIRECTORY_LEVEL; level <= root_level; ++level) {
-		if (level <= PT_PDPE_LEVEL
-		    && (mmu->root_level >= PT32E_ROOT_LEVEL || is_pse(vcpu)))
-			map |= 1 << (ps_set_index | (level - 1));
-	}
-	mmu->last_pte_bitmap = map;
+	unsigned root_level = mmu->root_level;
+
+	mmu->last_nonleaf_level = root_level;
+	if (root_level == PT32_ROOT_LEVEL && is_pse(vcpu))
+		mmu->last_nonleaf_level++;
 }
 
 static void paging64_init_context_common(struct kvm_vcpu *vcpu,
@@ -3863,7 +3941,7 @@ static void paging64_init_context_common(struct kvm_vcpu *vcpu,
 
 	reset_rsvds_bits_mask(vcpu, context);
 	update_permission_bitmask(vcpu, context, false);
-	update_last_pte_bitmap(vcpu, context);
+	update_last_nonleaf_level(vcpu, context);
 
 	MMU_WARN_ON(!is_pae(vcpu));
 	context->page_fault = paging64_page_fault;
@@ -3890,7 +3968,7 @@ static void paging32_init_context(struct kvm_vcpu *vcpu,
 
 	reset_rsvds_bits_mask(vcpu, context);
 	update_permission_bitmask(vcpu, context, false);
-	update_last_pte_bitmap(vcpu, context);
+	update_last_nonleaf_level(vcpu, context);
 
 	context->page_fault = paging32_page_fault;
 	context->gva_to_gpa = paging32_gva_to_gpa;
@@ -3948,7 +4026,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 	}
 
 	update_permission_bitmask(vcpu, context, false);
-	update_last_pte_bitmap(vcpu, context);
+	update_last_nonleaf_level(vcpu, context);
 	reset_tdp_shadow_zero_bits_mask(vcpu, context);
 }
 
@@ -4054,7 +4132,7 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
 	}
 
 	update_permission_bitmask(vcpu, g_context, false);
-	update_last_pte_bitmap(vcpu, g_context);
+	update_last_nonleaf_level(vcpu, g_context);
 }
 
 static void init_kvm_mmu(struct kvm_vcpu *vcpu)
@@ -4125,18 +4203,6 @@ static bool need_remote_flush(u64 old, u64 new)
 	return (old & ~new & PT64_PERM_MASK) != 0;
 }
 
-static void mmu_pte_write_flush_tlb(struct kvm_vcpu *vcpu, bool zap_page,
-				    bool remote_flush, bool local_flush)
-{
-	if (zap_page)
-		return;
-
-	if (remote_flush)
-		kvm_flush_remote_tlbs(vcpu->kvm);
-	else if (local_flush)
-		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
-}
-
 static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
 				    const u8 *new, int *bytes)
 {
@@ -4186,7 +4252,8 @@ static bool detect_write_flooding(struct kvm_mmu_page *sp)
 	if (sp->role.level == PT_PAGE_TABLE_LEVEL)
 		return false;
 
-	return ++sp->write_flooding_count >= 3;
+	atomic_inc(&sp->write_flooding_count);
+	return atomic_read(&sp->write_flooding_count) >= 3;
 }
 
 /*
@@ -4248,15 +4315,15 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte)
 	return spte;
 }
 
-void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
-		       const u8 *new, int bytes)
+static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
+			      const u8 *new, int bytes)
 {
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	struct kvm_mmu_page *sp;
 	LIST_HEAD(invalid_list);
 	u64 entry, gentry, *spte;
 	int npte;
-	bool remote_flush, local_flush, zap_page;
+	bool remote_flush, local_flush;
 	union kvm_mmu_page_role mask = { };
 
 	mask.cr0_wp = 1;
@@ -4273,7 +4340,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	if (!ACCESS_ONCE(vcpu->kvm->arch.indirect_shadow_pages))
 		return;
 
-	zap_page = remote_flush = local_flush = false;
+	remote_flush = local_flush = false;
 
 	pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
 
@@ -4293,8 +4360,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
 		if (detect_write_misaligned(sp, gpa, bytes) ||
 		      detect_write_flooding(sp)) {
-			zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp,
-						     &invalid_list);
+			kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list);
 			++vcpu->kvm->stat.mmu_flooded;
 			continue;
 		}
@@ -4316,8 +4382,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 			++spte;
 		}
 	}
-	mmu_pte_write_flush_tlb(vcpu, zap_page, remote_flush, local_flush);
-	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
+	kvm_mmu_flush_or_zap(vcpu, &invalid_list, remote_flush, local_flush);
 	kvm_mmu_audit(vcpu, AUDIT_POST_PTE_WRITE);
 	spin_unlock(&vcpu->kvm->mmu_lock);
 }
@@ -4354,32 +4419,34 @@ static void make_mmu_pages_available(struct kvm_vcpu *vcpu)
 	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
 }
 
-static bool is_mmio_page_fault(struct kvm_vcpu *vcpu, gva_t addr)
-{
-	if (vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu))
-		return vcpu_match_mmio_gpa(vcpu, addr);
-
-	return vcpu_match_mmio_gva(vcpu, addr);
-}
-
 int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
 		       void *insn, int insn_len)
 {
 	int r, emulation_type = EMULTYPE_RETRY;
 	enum emulation_result er;
+	bool direct = vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu);
+
+	if (unlikely(error_code & PFERR_RSVD_MASK)) {
+		r = handle_mmio_page_fault(vcpu, cr2, direct);
+		if (r == RET_MMIO_PF_EMULATE) {
+			emulation_type = 0;
+			goto emulate;
+		}
+		if (r == RET_MMIO_PF_RETRY)
+			return 1;
+		if (r < 0)
+			return r;
+	}
 
 	r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code, false);
 	if (r < 0)
-		goto out;
-
-	if (!r) {
-		r = 1;
-		goto out;
-	}
+		return r;
+	if (!r)
+		return 1;
 
-	if (is_mmio_page_fault(vcpu, cr2))
+	if (mmio_info_in_cache(vcpu, cr2, direct))
 		emulation_type = 0;
-
+emulate:
 	er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len);
 
 	switch (er) {
@@ -4393,8 +4460,6 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
 	default:
 		BUG();
 	}
-out:
-	return r;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
 
@@ -4463,6 +4528,21 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu)
 	init_kvm_mmu(vcpu);
 }
 
+void kvm_mmu_init_vm(struct kvm *kvm)
+{
+	struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
+
+	node->track_write = kvm_mmu_pte_write;
+	kvm_page_track_register_notifier(kvm, node);
+}
+
+void kvm_mmu_uninit_vm(struct kvm *kvm)
+{
+	struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
+
+	kvm_page_track_unregister_notifier(kvm, node);
+}
+
 /* The return value indicates if tlb flush on all vcpus is needed. */
 typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head);
 
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 55ffb7b0f95e..58fe98a0a526 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -174,4 +174,9 @@ static inline bool permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 
 void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm);
 void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end);
+
+void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
+void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
+bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
+				    struct kvm_memory_slot *slot, u64 gfn);
 #endif
diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c
new file mode 100644
index 000000000000..11f76436f74f
--- /dev/null
+++ b/arch/x86/kvm/page_track.c
@@ -0,0 +1,222 @@
+/*
+ * Support KVM gust page tracking
+ *
+ * This feature allows us to track page access in guest. Currently, only
+ * write access is tracked.
+ *
+ * Copyright(C) 2015 Intel Corporation.
+ *
+ * Author:
+ *   Xiao Guangrong <guangrong.xiao@linux.intel.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ */
+
+#include <linux/kvm_host.h>
+#include <asm/kvm_host.h>
+#include <asm/kvm_page_track.h>
+
+#include "mmu.h"
+
+void kvm_page_track_free_memslot(struct kvm_memory_slot *free,
+				 struct kvm_memory_slot *dont)
+{
+	int i;
+
+	for (i = 0; i < KVM_PAGE_TRACK_MAX; i++)
+		if (!dont || free->arch.gfn_track[i] !=
+		      dont->arch.gfn_track[i]) {
+			kvfree(free->arch.gfn_track[i]);
+			free->arch.gfn_track[i] = NULL;
+		}
+}
+
+int kvm_page_track_create_memslot(struct kvm_memory_slot *slot,
+				  unsigned long npages)
+{
+	int  i;
+
+	for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) {
+		slot->arch.gfn_track[i] = kvm_kvzalloc(npages *
+					    sizeof(*slot->arch.gfn_track[i]));
+		if (!slot->arch.gfn_track[i])
+			goto track_free;
+	}
+
+	return 0;
+
+track_free:
+	kvm_page_track_free_memslot(slot, NULL);
+	return -ENOMEM;
+}
+
+static inline bool page_track_mode_is_valid(enum kvm_page_track_mode mode)
+{
+	if (mode < 0 || mode >= KVM_PAGE_TRACK_MAX)
+		return false;
+
+	return true;
+}
+
+static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn,
+			     enum kvm_page_track_mode mode, short count)
+{
+	int index, val;
+
+	index = gfn_to_index(gfn, slot->base_gfn, PT_PAGE_TABLE_LEVEL);
+
+	val = slot->arch.gfn_track[mode][index];
+
+	if (WARN_ON(val + count < 0 || val + count > USHRT_MAX))
+		return;
+
+	slot->arch.gfn_track[mode][index] += count;
+}
+
+/*
+ * add guest page to the tracking pool so that corresponding access on that
+ * page will be intercepted.
+ *
+ * It should be called under the protection both of mmu-lock and kvm->srcu
+ * or kvm->slots_lock.
+ *
+ * @kvm: the guest instance we are interested in.
+ * @slot: the @gfn belongs to.
+ * @gfn: the guest page.
+ * @mode: tracking mode, currently only write track is supported.
+ */
+void kvm_slot_page_track_add_page(struct kvm *kvm,
+				  struct kvm_memory_slot *slot, gfn_t gfn,
+				  enum kvm_page_track_mode mode)
+{
+
+	if (WARN_ON(!page_track_mode_is_valid(mode)))
+		return;
+
+	update_gfn_track(slot, gfn, mode, 1);
+
+	/*
+	 * new track stops large page mapping for the
+	 * tracked page.
+	 */
+	kvm_mmu_gfn_disallow_lpage(slot, gfn);
+
+	if (mode == KVM_PAGE_TRACK_WRITE)
+		if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn))
+			kvm_flush_remote_tlbs(kvm);
+}
+
+/*
+ * remove the guest page from the tracking pool which stops the interception
+ * of corresponding access on that page. It is the opposed operation of
+ * kvm_slot_page_track_add_page().
+ *
+ * It should be called under the protection both of mmu-lock and kvm->srcu
+ * or kvm->slots_lock.
+ *
+ * @kvm: the guest instance we are interested in.
+ * @slot: the @gfn belongs to.
+ * @gfn: the guest page.
+ * @mode: tracking mode, currently only write track is supported.
+ */
+void kvm_slot_page_track_remove_page(struct kvm *kvm,
+				     struct kvm_memory_slot *slot, gfn_t gfn,
+				     enum kvm_page_track_mode mode)
+{
+	if (WARN_ON(!page_track_mode_is_valid(mode)))
+		return;
+
+	update_gfn_track(slot, gfn, mode, -1);
+
+	/*
+	 * allow large page mapping for the tracked page
+	 * after the tracker is gone.
+	 */
+	kvm_mmu_gfn_allow_lpage(slot, gfn);
+}
+
+/*
+ * check if the corresponding access on the specified guest page is tracked.
+ */
+bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn,
+			      enum kvm_page_track_mode mode)
+{
+	struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+	int index = gfn_to_index(gfn, slot->base_gfn, PT_PAGE_TABLE_LEVEL);
+
+	if (WARN_ON(!page_track_mode_is_valid(mode)))
+		return false;
+
+	return !!ACCESS_ONCE(slot->arch.gfn_track[mode][index]);
+}
+
+void kvm_page_track_init(struct kvm *kvm)
+{
+	struct kvm_page_track_notifier_head *head;
+
+	head = &kvm->arch.track_notifier_head;
+	init_srcu_struct(&head->track_srcu);
+	INIT_HLIST_HEAD(&head->track_notifier_list);
+}
+
+/*
+ * register the notifier so that event interception for the tracked guest
+ * pages can be received.
+ */
+void
+kvm_page_track_register_notifier(struct kvm *kvm,
+				 struct kvm_page_track_notifier_node *n)
+{
+	struct kvm_page_track_notifier_head *head;
+
+	head = &kvm->arch.track_notifier_head;
+
+	spin_lock(&kvm->mmu_lock);
+	hlist_add_head_rcu(&n->node, &head->track_notifier_list);
+	spin_unlock(&kvm->mmu_lock);
+}
+
+/*
+ * stop receiving the event interception. It is the opposed operation of
+ * kvm_page_track_register_notifier().
+ */
+void
+kvm_page_track_unregister_notifier(struct kvm *kvm,
+				   struct kvm_page_track_notifier_node *n)
+{
+	struct kvm_page_track_notifier_head *head;
+
+	head = &kvm->arch.track_notifier_head;
+
+	spin_lock(&kvm->mmu_lock);
+	hlist_del_rcu(&n->node);
+	spin_unlock(&kvm->mmu_lock);
+	synchronize_srcu(&head->track_srcu);
+}
+
+/*
+ * Notify the node that write access is intercepted and write emulation is
+ * finished at this time.
+ *
+ * The node should figure out if the written page is the one that node is
+ * interested in by itself.
+ */
+void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
+			  int bytes)
+{
+	struct kvm_page_track_notifier_head *head;
+	struct kvm_page_track_notifier_node *n;
+	int idx;
+
+	head = &vcpu->kvm->arch.track_notifier_head;
+
+	if (hlist_empty(&head->track_notifier_list))
+		return;
+
+	idx = srcu_read_lock(&head->track_srcu);
+	hlist_for_each_entry_rcu(n, &head->track_notifier_list, node)
+		if (n->track_write)
+			n->track_write(vcpu, gpa, new, bytes);
+	srcu_read_unlock(&head->track_srcu, idx);
+}
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 6c9fed957cce..e159a8185ad9 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -189,8 +189,11 @@ static inline unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, u64 gpte)
 		((gpte & VMX_EPT_EXECUTABLE_MASK) ? ACC_EXEC_MASK : 0) |
 		ACC_USER_MASK;
 #else
-	access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK;
-	access &= ~(gpte >> PT64_NX_SHIFT);
+	BUILD_BUG_ON(ACC_EXEC_MASK != PT_PRESENT_MASK);
+	BUILD_BUG_ON(ACC_EXEC_MASK != 1);
+	access = gpte & (PT_WRITABLE_MASK | PT_USER_MASK | PT_PRESENT_MASK);
+	/* Combine NX with P (which is set here) to get ACC_EXEC_MASK.  */
+	access ^= (gpte >> PT64_NX_SHIFT);
 #endif
 
 	return access;
@@ -249,7 +252,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 			return ret;
 
 		kvm_vcpu_mark_page_dirty(vcpu, table_gfn);
-		walker->ptes[level] = pte;
+		walker->ptes[level - 1] = pte;
 	}
 	return 0;
 }
@@ -702,24 +705,17 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 
 	pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
 
-	if (unlikely(error_code & PFERR_RSVD_MASK)) {
-		r = handle_mmio_page_fault(vcpu, addr, mmu_is_nested(vcpu));
-		if (likely(r != RET_MMIO_PF_INVALID))
-			return r;
-
-		/*
-		 * page fault with PFEC.RSVD  = 1 is caused by shadow
-		 * page fault, should not be used to walk guest page
-		 * table.
-		 */
-		error_code &= ~PFERR_RSVD_MASK;
-	};
-
 	r = mmu_topup_memory_caches(vcpu);
 	if (r)
 		return r;
 
 	/*
+	 * If PFEC.RSVD is set, this is a shadow page fault.
+	 * The bit needs to be cleared before walking guest page tables.
+	 */
+	error_code &= ~PFERR_RSVD_MASK;
+
+	/*
 	 * Look up the guest pte for the faulting address.
 	 */
 	r = FNAME(walk_addr)(&walker, vcpu, addr, error_code);
@@ -735,6 +731,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 		return 0;
 	}
 
+	if (page_fault_handle_page_track(vcpu, error_code, walker.gfn)) {
+		shadow_page_table_clear_flood(vcpu, addr);
+		return 1;
+	}
+
 	vcpu->arch.write_fault_to_shadow_pgtable = false;
 
 	is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu,
@@ -945,7 +946,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 
 		if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte,
 					       sizeof(pt_element_t)))
-			return -EINVAL;
+			return 0;
 
 		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
 			vcpu->kvm->tlbs_dirty++;
@@ -977,7 +978,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 			 host_writable);
 	}
 
-	return !nr_present;
+	return nr_present;
 }
 
 #undef pt_element_t
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 31aa2c85dc97..06ce377dcbc9 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -257,7 +257,7 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 
 void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->arch.apic)
+	if (lapic_in_kernel(vcpu))
 		kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC);
 }
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index c13a64b7d789..95070386d599 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1858,8 +1858,7 @@ static int halt_interception(struct vcpu_svm *svm)
 static int vmmcall_interception(struct vcpu_svm *svm)
 {
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
-	kvm_emulate_hypercall(&svm->vcpu);
-	return 1;
+	return kvm_emulate_hypercall(&svm->vcpu);
 }
 
 static unsigned long nested_svm_get_tdp_cr3(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index ad9f6a23f139..2f1ea2f61e1f 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -996,11 +996,13 @@ TRACE_EVENT(kvm_enter_smm,
  * Tracepoint for VT-d posted-interrupts.
  */
 TRACE_EVENT(kvm_pi_irte_update,
-	TP_PROTO(unsigned int vcpu_id, unsigned int gsi,
-		 unsigned int gvec, u64 pi_desc_addr, bool set),
-	TP_ARGS(vcpu_id, gsi, gvec, pi_desc_addr, set),
+	TP_PROTO(unsigned int host_irq, unsigned int vcpu_id,
+		 unsigned int gsi, unsigned int gvec,
+		 u64 pi_desc_addr, bool set),
+	TP_ARGS(host_irq, vcpu_id, gsi, gvec, pi_desc_addr, set),
 
 	TP_STRUCT__entry(
+		__field(	unsigned int,	host_irq	)
 		__field(	unsigned int,	vcpu_id		)
 		__field(	unsigned int,	gsi		)
 		__field(	unsigned int,	gvec		)
@@ -1009,6 +1011,7 @@ TRACE_EVENT(kvm_pi_irte_update,
 	),
 
 	TP_fast_assign(
+		__entry->host_irq	= host_irq;
 		__entry->vcpu_id	= vcpu_id;
 		__entry->gsi		= gsi;
 		__entry->gvec		= gvec;
@@ -1016,9 +1019,10 @@ TRACE_EVENT(kvm_pi_irte_update,
 		__entry->set		= set;
 	),
 
-	TP_printk("VT-d PI is %s for this irq, vcpu %u, gsi: 0x%x, "
+	TP_printk("VT-d PI is %s for irq %u, vcpu %u, gsi: 0x%x, "
 		  "gvec: 0x%x, pi_desc_addr: 0x%llx",
 		  __entry->set ? "enabled and being updated" : "disabled",
+		  __entry->host_irq,
 		  __entry->vcpu_id,
 		  __entry->gsi,
 		  __entry->gvec,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e2951b6edbbc..5e45c2731a5d 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -596,6 +596,8 @@ struct vcpu_vmx {
 	/* Support for PML */
 #define PML_ENTITY_NUM		512
 	struct page *pml_pg;
+
+	u64 current_tsc_ratio;
 };
 
 enum segment_cache_field {
@@ -861,7 +863,6 @@ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu);
 static u64 construct_eptp(unsigned long root_hpa);
 static void kvm_cpu_vmxon(u64 addr);
 static void kvm_cpu_vmxoff(void);
-static bool vmx_mpx_supported(void);
 static bool vmx_xsaves_supported(void);
 static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
 static void vmx_set_segment(struct kvm_vcpu *vcpu,
@@ -961,25 +962,36 @@ static const u32 vmx_msr_index[] = {
 	MSR_EFER, MSR_TSC_AUX, MSR_STAR,
 };
 
-static inline bool is_page_fault(u32 intr_info)
+static inline bool is_exception_n(u32 intr_info, u8 vector)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
 			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK);
+		(INTR_TYPE_HARD_EXCEPTION | vector | INTR_INFO_VALID_MASK);
+}
+
+static inline bool is_debug(u32 intr_info)
+{
+	return is_exception_n(intr_info, DB_VECTOR);
+}
+
+static inline bool is_breakpoint(u32 intr_info)
+{
+	return is_exception_n(intr_info, BP_VECTOR);
+}
+
+static inline bool is_page_fault(u32 intr_info)
+{
+	return is_exception_n(intr_info, PF_VECTOR);
 }
 
 static inline bool is_no_device(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
-			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK);
+	return is_exception_n(intr_info, NM_VECTOR);
 }
 
 static inline bool is_invalid_opcode(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
-			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK);
+	return is_exception_n(intr_info, UD_VECTOR);
 }
 
 static inline bool is_external_interrupt(u32 intr_info)
@@ -1811,6 +1823,13 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 			return;
 		}
 		break;
+	case MSR_IA32_PEBS_ENABLE:
+		/* PEBS needs a quiescent period after being disabled (to write
+		 * a record).  Disabling PEBS through VMX MSR swapping doesn't
+		 * provide that period, so a CPU could write host's record into
+		 * guest's memory.
+		 */
+		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
 	}
 
 	for (i = 0; i < m->nr; ++i)
@@ -1848,26 +1867,31 @@ static void reload_tss(void)
 
 static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 {
-	u64 guest_efer;
-	u64 ignore_bits;
+	u64 guest_efer = vmx->vcpu.arch.efer;
+	u64 ignore_bits = 0;
 
-	guest_efer = vmx->vcpu.arch.efer;
+	if (!enable_ept) {
+		/*
+		 * NX is needed to handle CR0.WP=1, CR4.SMEP=1.  Testing
+		 * host CPUID is more efficient than testing guest CPUID
+		 * or CR4.  Host SMEP is anyway a requirement for guest SMEP.
+		 */
+		if (boot_cpu_has(X86_FEATURE_SMEP))
+			guest_efer |= EFER_NX;
+		else if (!(guest_efer & EFER_NX))
+			ignore_bits |= EFER_NX;
+	}
 
 	/*
-	 * NX is emulated; LMA and LME handled by hardware; SCE meaningless
-	 * outside long mode
+	 * LMA and LME handled by hardware; SCE meaningless outside long mode.
 	 */
-	ignore_bits = EFER_NX | EFER_SCE;
+	ignore_bits |= EFER_SCE;
 #ifdef CONFIG_X86_64
 	ignore_bits |= EFER_LMA | EFER_LME;
 	/* SCE is meaningful only in long mode on Intel */
 	if (guest_efer & EFER_LMA)
 		ignore_bits &= ~(u64)EFER_SCE;
 #endif
-	guest_efer &= ~ignore_bits;
-	guest_efer |= host_efer & ignore_bits;
-	vmx->guest_msrs[efer_offset].data = guest_efer;
-	vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
 
 	clear_atomic_switch_msr(vmx, MSR_EFER);
 
@@ -1878,16 +1902,21 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 	 */
 	if (cpu_has_load_ia32_efer ||
 	    (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) {
-		guest_efer = vmx->vcpu.arch.efer;
 		if (!(guest_efer & EFER_LMA))
 			guest_efer &= ~EFER_LME;
 		if (guest_efer != host_efer)
 			add_atomic_switch_msr(vmx, MSR_EFER,
 					      guest_efer, host_efer);
 		return false;
-	}
+	} else {
+		guest_efer &= ~ignore_bits;
+		guest_efer |= host_efer & ignore_bits;
 
-	return true;
+		vmx->guest_msrs[efer_offset].data = guest_efer;
+		vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
+
+		return true;
+	}
 }
 
 static unsigned long segment_base(u16 selector)
@@ -2127,14 +2156,16 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
 		vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
 
-		/* Setup TSC multiplier */
-		if (cpu_has_vmx_tsc_scaling())
-			vmcs_write64(TSC_MULTIPLIER,
-				     vcpu->arch.tsc_scaling_ratio);
-
 		vmx->loaded_vmcs->cpu = cpu;
 	}
 
+	/* Setup TSC multiplier */
+	if (kvm_has_tsc_control &&
+	    vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) {
+		vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio;
+		vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
+	}
+
 	vmx_vcpu_pi_load(vcpu, cpu);
 }
 
@@ -2584,7 +2615,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
 		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT;
 
-	if (vmx_mpx_supported())
+	if (kvm_mpx_supported())
 		vmx->nested.nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
 
 	/* We support free control of debug control saving. */
@@ -2605,7 +2636,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		VM_ENTRY_LOAD_IA32_PAT;
 	vmx->nested.nested_vmx_entry_ctls_high |=
 		(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER);
-	if (vmx_mpx_supported())
+	if (kvm_mpx_supported())
 		vmx->nested.nested_vmx_entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
 
 	/* We support free control of debug control loading. */
@@ -2849,7 +2880,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP);
 		break;
 	case MSR_IA32_BNDCFGS:
-		if (!vmx_mpx_supported())
+		if (!kvm_mpx_supported())
 			return 1;
 		msr_info->data = vmcs_read64(GUEST_BNDCFGS);
 		break;
@@ -2926,7 +2957,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vmcs_writel(GUEST_SYSENTER_ESP, data);
 		break;
 	case MSR_IA32_BNDCFGS:
-		if (!vmx_mpx_supported())
+		if (!kvm_mpx_supported())
 			return 1;
 		vmcs_write64(GUEST_BNDCFGS, data);
 		break;
@@ -3399,7 +3430,7 @@ static void init_vmcs_shadow_fields(void)
 	for (i = j = 0; i < max_shadow_read_write_fields; i++) {
 		switch (shadow_read_write_fields[i]) {
 		case GUEST_BNDCFGS:
-			if (!vmx_mpx_supported())
+			if (!kvm_mpx_supported())
 				continue;
 			break;
 		default:
@@ -5608,11 +5639,8 @@ static int handle_dr(struct kvm_vcpu *vcpu)
 	}
 
 	if (vcpu->guest_debug == 0) {
-		u32 cpu_based_vm_exec_control;
-
-		cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
-		cpu_based_vm_exec_control &= ~CPU_BASED_MOV_DR_EXITING;
-		vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+		vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
+				CPU_BASED_MOV_DR_EXITING);
 
 		/*
 		 * No more DR vmexits; force a reload of the debug registers
@@ -5649,8 +5677,6 @@ static void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val)
 
 static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
 {
-	u32 cpu_based_vm_exec_control;
-
 	get_debugreg(vcpu->arch.db[0], 0);
 	get_debugreg(vcpu->arch.db[1], 1);
 	get_debugreg(vcpu->arch.db[2], 2);
@@ -5659,10 +5685,7 @@ static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
 	vcpu->arch.dr7 = vmcs_readl(GUEST_DR7);
 
 	vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT;
-
-	cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
-	cpu_based_vm_exec_control |= CPU_BASED_MOV_DR_EXITING;
-	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+	vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, CPU_BASED_MOV_DR_EXITING);
 }
 
 static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
@@ -5747,8 +5770,7 @@ static int handle_halt(struct kvm_vcpu *vcpu)
 
 static int handle_vmcall(struct kvm_vcpu *vcpu)
 {
-	kvm_emulate_hypercall(vcpu);
-	return 1;
+	return kvm_emulate_hypercall(vcpu);
 }
 
 static int handle_invd(struct kvm_vcpu *vcpu)
@@ -6435,8 +6457,8 @@ static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx)
 
 	if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) {
 		/* Recycle the least recently used VMCS. */
-		item = list_entry(vmx->nested.vmcs02_pool.prev,
-			struct vmcs02_list, list);
+		item = list_last_entry(&vmx->nested.vmcs02_pool,
+				       struct vmcs02_list, list);
 		item->vmptr = vmx->nested.current_vmptr;
 		list_move(&item->list, &vmx->nested.vmcs02_pool);
 		return &item->vmcs02;
@@ -7752,6 +7774,13 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		else if (is_no_device(intr_info) &&
 			 !(vmcs12->guest_cr0 & X86_CR0_TS))
 			return false;
+		else if (is_debug(intr_info) &&
+			 vcpu->guest_debug &
+			 (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+			return false;
+		else if (is_breakpoint(intr_info) &&
+			 vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+			return false;
 		return vmcs12->exception_bitmap &
 				(1u << (intr_info & INTR_INFO_VECTOR_MASK));
 	case EXIT_REASON_EXTERNAL_INTERRUPT:
@@ -10256,7 +10285,7 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS);
 	vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP);
 	vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP);
-	if (vmx_mpx_supported())
+	if (kvm_mpx_supported())
 		vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
 	if (nested_cpu_has_xsaves(vmcs12))
 		vmcs12->xss_exit_bitmap = vmcs_read64(XSS_EXIT_BITMAP);
@@ -10764,13 +10793,26 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 		 */
 
 		kvm_set_msi_irq(e, &irq);
-		if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu))
+		if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) {
+			/*
+			 * Make sure the IRTE is in remapped mode if
+			 * we don't handle it in posted mode.
+			 */
+			ret = irq_set_vcpu_affinity(host_irq, NULL);
+			if (ret < 0) {
+				printk(KERN_INFO
+				   "failed to back to remapped mode, irq: %u\n",
+				   host_irq);
+				goto out;
+			}
+
 			continue;
+		}
 
 		vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
 		vcpu_info.vector = irq.vector;
 
-		trace_kvm_pi_irte_update(vcpu->vcpu_id, e->gsi,
+		trace_kvm_pi_irte_update(vcpu->vcpu_id, host_irq, e->gsi,
 				vcpu_info.vector, vcpu_info.pi_desc_addr, set);
 
 		if (set)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4244c2baf57d..7236bd3a4c3d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -123,6 +123,9 @@ module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
 unsigned int __read_mostly lapic_timer_advance_ns = 0;
 module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
 
+static bool __read_mostly vector_hashing = true;
+module_param(vector_hashing, bool, S_IRUGO);
+
 static bool __read_mostly backwards_tsc_observed = false;
 
 #define KVM_NR_SHARED_MSRS 16
@@ -1196,17 +1199,11 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 
 static uint32_t div_frac(uint32_t dividend, uint32_t divisor)
 {
-	uint32_t quotient, remainder;
-
-	/* Don't try to replace with do_div(), this one calculates
-	 * "(dividend << 32) / divisor" */
-	__asm__ ( "divl %4"
-		  : "=a" (quotient), "=d" (remainder)
-		  : "0" (0), "1" (dividend), "r" (divisor) );
-	return quotient;
+	do_shl32_div32(dividend, divisor);
+	return dividend;
 }
 
-static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz,
+static void kvm_get_time_scale(uint64_t scaled_hz, uint64_t base_hz,
 			       s8 *pshift, u32 *pmultiplier)
 {
 	uint64_t scaled64;
@@ -1214,8 +1211,8 @@ static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz,
 	uint64_t tps64;
 	uint32_t tps32;
 
-	tps64 = base_khz * 1000LL;
-	scaled64 = scaled_khz * 1000LL;
+	tps64 = base_hz;
+	scaled64 = scaled_hz;
 	while (tps64 > scaled64*2 || tps64 & 0xffffffff00000000ULL) {
 		tps64 >>= 1;
 		shift--;
@@ -1233,8 +1230,8 @@ static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz,
 	*pshift = shift;
 	*pmultiplier = div_frac(scaled64, tps32);
 
-	pr_debug("%s: base_khz %u => %u, shift %d, mul %u\n",
-		 __func__, base_khz, scaled_khz, shift, *pmultiplier);
+	pr_debug("%s: base_hz %llu => %llu, shift %d, mul %u\n",
+		 __func__, base_hz, scaled_hz, shift, *pmultiplier);
 }
 
 #ifdef CONFIG_X86_64
@@ -1293,23 +1290,23 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
 	return 0;
 }
 
-static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz)
+static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz)
 {
 	u32 thresh_lo, thresh_hi;
 	int use_scaling = 0;
 
 	/* tsc_khz can be zero if TSC calibration fails */
-	if (this_tsc_khz == 0) {
+	if (user_tsc_khz == 0) {
 		/* set tsc_scaling_ratio to a safe value */
 		vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio;
 		return -1;
 	}
 
 	/* Compute a scale to convert nanoseconds in TSC cycles */
-	kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000,
+	kvm_get_time_scale(user_tsc_khz * 1000LL, NSEC_PER_SEC,
 			   &vcpu->arch.virtual_tsc_shift,
 			   &vcpu->arch.virtual_tsc_mult);
-	vcpu->arch.virtual_tsc_khz = this_tsc_khz;
+	vcpu->arch.virtual_tsc_khz = user_tsc_khz;
 
 	/*
 	 * Compute the variation in TSC rate which is acceptable
@@ -1319,11 +1316,11 @@ static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz)
 	 */
 	thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm);
 	thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm);
-	if (this_tsc_khz < thresh_lo || this_tsc_khz > thresh_hi) {
-		pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", this_tsc_khz, thresh_lo, thresh_hi);
+	if (user_tsc_khz < thresh_lo || user_tsc_khz > thresh_hi) {
+		pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", user_tsc_khz, thresh_lo, thresh_hi);
 		use_scaling = 1;
 	}
-	return set_tsc_khz(vcpu, this_tsc_khz, use_scaling);
+	return set_tsc_khz(vcpu, user_tsc_khz, use_scaling);
 }
 
 static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
@@ -1716,7 +1713,7 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 
 static int kvm_guest_time_update(struct kvm_vcpu *v)
 {
-	unsigned long flags, this_tsc_khz, tgt_tsc_khz;
+	unsigned long flags, tgt_tsc_khz;
 	struct kvm_vcpu_arch *vcpu = &v->arch;
 	struct kvm_arch *ka = &v->kvm->arch;
 	s64 kernel_ns;
@@ -1742,8 +1739,8 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	/* Keep irq disabled to prevent changes to the clock */
 	local_irq_save(flags);
-	this_tsc_khz = __this_cpu_read(cpu_tsc_khz);
-	if (unlikely(this_tsc_khz == 0)) {
+	tgt_tsc_khz = __this_cpu_read(cpu_tsc_khz);
+	if (unlikely(tgt_tsc_khz == 0)) {
 		local_irq_restore(flags);
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
 		return 1;
@@ -1778,13 +1775,14 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	if (!vcpu->pv_time_enabled)
 		return 0;
 
-	if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) {
-		tgt_tsc_khz = kvm_has_tsc_control ?
-			vcpu->virtual_tsc_khz : this_tsc_khz;
-		kvm_get_time_scale(NSEC_PER_SEC / 1000, tgt_tsc_khz,
+	if (kvm_has_tsc_control)
+		tgt_tsc_khz = kvm_scale_tsc(v, tgt_tsc_khz);
+
+	if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) {
+		kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL,
 				   &vcpu->hv_clock.tsc_shift,
 				   &vcpu->hv_clock.tsc_to_system_mul);
-		vcpu->hw_tsc_khz = this_tsc_khz;
+		vcpu->hw_tsc_khz = tgt_tsc_khz;
 	}
 
 	/* With all the info we got, fill in the values */
@@ -2987,7 +2985,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 	kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked);
 
 	if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR &&
-	    kvm_vcpu_has_lapic(vcpu))
+	    lapic_in_kernel(vcpu))
 		vcpu->arch.apic->sipi_vector = events->sipi_vector;
 
 	if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
@@ -3000,7 +2998,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 			vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
 		else
 			vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
-		if (kvm_vcpu_has_lapic(vcpu)) {
+		if (lapic_in_kernel(vcpu)) {
 			if (events->smi.latched_init)
 				set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
 			else
@@ -3240,7 +3238,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	switch (ioctl) {
 	case KVM_GET_LAPIC: {
 		r = -EINVAL;
-		if (!vcpu->arch.apic)
+		if (!lapic_in_kernel(vcpu))
 			goto out;
 		u.lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);
 
@@ -3258,7 +3256,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	}
 	case KVM_SET_LAPIC: {
 		r = -EINVAL;
-		if (!vcpu->arch.apic)
+		if (!lapic_in_kernel(vcpu))
 			goto out;
 		u.lapic = memdup_user(argp, sizeof(*u.lapic));
 		if (IS_ERR(u.lapic))
@@ -3605,20 +3603,26 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
 
 static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps)
 {
-	mutex_lock(&kvm->arch.vpit->pit_state.lock);
-	memcpy(ps, &kvm->arch.vpit->pit_state, sizeof(struct kvm_pit_state));
-	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+	struct kvm_kpit_state *kps = &kvm->arch.vpit->pit_state;
+
+	BUILD_BUG_ON(sizeof(*ps) != sizeof(kps->channels));
+
+	mutex_lock(&kps->lock);
+	memcpy(ps, &kps->channels, sizeof(*ps));
+	mutex_unlock(&kps->lock);
 	return 0;
 }
 
 static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
 {
 	int i;
-	mutex_lock(&kvm->arch.vpit->pit_state.lock);
-	memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state));
+	struct kvm_pit *pit = kvm->arch.vpit;
+
+	mutex_lock(&pit->pit_state.lock);
+	memcpy(&pit->pit_state.channels, ps, sizeof(*ps));
 	for (i = 0; i < 3; i++)
-		kvm_pit_load_count(kvm, i, ps->channels[i].count, 0);
-	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+		kvm_pit_load_count(pit, i, ps->channels[i].count, 0);
+	mutex_unlock(&pit->pit_state.lock);
 	return 0;
 }
 
@@ -3638,29 +3642,39 @@ static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
 	int start = 0;
 	int i;
 	u32 prev_legacy, cur_legacy;
-	mutex_lock(&kvm->arch.vpit->pit_state.lock);
-	prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
+	struct kvm_pit *pit = kvm->arch.vpit;
+
+	mutex_lock(&pit->pit_state.lock);
+	prev_legacy = pit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
 	cur_legacy = ps->flags & KVM_PIT_FLAGS_HPET_LEGACY;
 	if (!prev_legacy && cur_legacy)
 		start = 1;
-	memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels,
-	       sizeof(kvm->arch.vpit->pit_state.channels));
-	kvm->arch.vpit->pit_state.flags = ps->flags;
+	memcpy(&pit->pit_state.channels, &ps->channels,
+	       sizeof(pit->pit_state.channels));
+	pit->pit_state.flags = ps->flags;
 	for (i = 0; i < 3; i++)
-		kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count,
+		kvm_pit_load_count(pit, i, pit->pit_state.channels[i].count,
 				   start && i == 0);
-	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+	mutex_unlock(&pit->pit_state.lock);
 	return 0;
 }
 
 static int kvm_vm_ioctl_reinject(struct kvm *kvm,
 				 struct kvm_reinject_control *control)
 {
-	if (!kvm->arch.vpit)
+	struct kvm_pit *pit = kvm->arch.vpit;
+
+	if (!pit)
 		return -ENXIO;
-	mutex_lock(&kvm->arch.vpit->pit_state.lock);
-	kvm->arch.vpit->pit_state.reinject = control->pit_reinject;
-	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+
+	/* pit->pit_state.lock was overloaded to prevent userspace from getting
+	 * an inconsistent state after running multiple KVM_REINJECT_CONTROL
+	 * ioctls in parallel.  Use a separate lock if that ioctl isn't rare.
+	 */
+	mutex_lock(&pit->pit_state.lock);
+	kvm_pit_set_reinject(pit, control->pit_reinject);
+	mutex_unlock(&pit->pit_state.lock);
+
 	return 0;
 }
 
@@ -4093,7 +4107,7 @@ static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
 
 	do {
 		n = min(len, 8);
-		if (!(vcpu->arch.apic &&
+		if (!(lapic_in_kernel(vcpu) &&
 		      !kvm_iodevice_write(vcpu, &vcpu->arch.apic->dev, addr, n, v))
 		    && kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, n, v))
 			break;
@@ -4113,7 +4127,7 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
 
 	do {
 		n = min(len, 8);
-		if (!(vcpu->arch.apic &&
+		if (!(lapic_in_kernel(vcpu) &&
 		      !kvm_iodevice_read(vcpu, &vcpu->arch.apic->dev,
 					 addr, n, v))
 		    && kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v))
@@ -4346,7 +4360,7 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
 	ret = kvm_vcpu_write_guest(vcpu, gpa, val, bytes);
 	if (ret < 0)
 		return 0;
-	kvm_mmu_pte_write(vcpu, gpa, val, bytes);
+	kvm_page_track_write(vcpu, gpa, val, bytes);
 	return 1;
 }
 
@@ -4604,7 +4618,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
 		return X86EMUL_CMPXCHG_FAILED;
 
 	kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
-	kvm_mmu_pte_write(vcpu, gpa, new, bytes);
+	kvm_page_track_write(vcpu, gpa, new, bytes);
 
 	return X86EMUL_CONTINUE;
 
@@ -6010,7 +6024,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu)
 	if (!kvm_x86_ops->update_cr8_intercept)
 		return;
 
-	if (!vcpu->arch.apic)
+	if (!lapic_in_kernel(vcpu))
 		return;
 
 	if (vcpu->arch.apicv_active)
@@ -6618,12 +6632,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	 * KVM_DEBUGREG_WONT_EXIT again.
 	 */
 	if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) {
-		int i;
-
 		WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP);
 		kvm_x86_ops->sync_dirty_debug_regs(vcpu);
-		for (i = 0; i < KVM_NR_DB_REGS; i++)
-			vcpu->arch.eff_db[i] = vcpu->arch.db[i];
+		kvm_update_dr0123(vcpu);
+		kvm_update_dr6(vcpu);
+		kvm_update_dr7(vcpu);
+		vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
 	}
 
 	/*
@@ -7038,7 +7052,7 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	if (!kvm_vcpu_has_lapic(vcpu) &&
+	if (!lapic_in_kernel(vcpu) &&
 	    mp_state->mp_state != KVM_MP_STATE_RUNNABLE)
 		return -EINVAL;
 
@@ -7314,7 +7328,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 	 * Every 255 times fpu_counter rolls over to 0; a guest that uses
 	 * the FPU in bursts will revert to loading it on demand.
 	 */
-	if (!vcpu->arch.eager_fpu) {
+	if (!use_eager_fpu()) {
 		if (++vcpu->fpu_counter < 5)
 			kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
 	}
@@ -7593,6 +7607,7 @@ bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
 }
 
 struct static_key kvm_no_apic_vcpu __read_mostly;
+EXPORT_SYMBOL_GPL(kvm_no_apic_vcpu);
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
@@ -7724,6 +7739,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn);
 	INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn);
 
+	kvm_page_track_init(kvm);
+	kvm_mmu_init_vm(kvm);
+
 	return 0;
 }
 
@@ -7850,6 +7868,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kfree(kvm->arch.vioapic);
 	kvm_free_vcpus(kvm);
 	kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
+	kvm_mmu_uninit_vm(kvm);
 }
 
 void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
@@ -7871,6 +7890,8 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			free->arch.lpage_info[i - 1] = NULL;
 		}
 	}
+
+	kvm_page_track_free_memslot(free, dont);
 }
 
 int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
@@ -7879,6 +7900,7 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 	int i;
 
 	for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
+		struct kvm_lpage_info *linfo;
 		unsigned long ugfn;
 		int lpages;
 		int level = i + 1;
@@ -7893,15 +7915,16 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 		if (i == 0)
 			continue;
 
-		slot->arch.lpage_info[i - 1] = kvm_kvzalloc(lpages *
-					sizeof(*slot->arch.lpage_info[i - 1]));
-		if (!slot->arch.lpage_info[i - 1])
+		linfo = kvm_kvzalloc(lpages * sizeof(*linfo));
+		if (!linfo)
 			goto out_free;
 
+		slot->arch.lpage_info[i - 1] = linfo;
+
 		if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1))
-			slot->arch.lpage_info[i - 1][0].write_count = 1;
+			linfo[0].disallow_lpage = 1;
 		if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1))
-			slot->arch.lpage_info[i - 1][lpages - 1].write_count = 1;
+			linfo[lpages - 1].disallow_lpage = 1;
 		ugfn = slot->userspace_addr >> PAGE_SHIFT;
 		/*
 		 * If the gfn and userspace address are not aligned wrt each
@@ -7913,10 +7936,13 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 			unsigned long j;
 
 			for (j = 0; j < lpages; ++j)
-				slot->arch.lpage_info[i - 1][j].write_count = 1;
+				linfo[j].disallow_lpage = 1;
 		}
 	}
 
+	if (kvm_page_track_create_memslot(slot, npages))
+		goto out_free;
+
 	return 0;
 
 out_free:
@@ -8370,6 +8396,12 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
 	return kvm_x86_ops->update_pi_irte(kvm, host_irq, guest_irq, set);
 }
 
+bool kvm_vector_hashing_enabled(void)
+{
+	return vector_hashing;
+}
+EXPORT_SYMBOL_GPL(kvm_vector_hashing_enabled);
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index f2afa5fe48a6..007940faa5c6 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -179,6 +179,7 @@ int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data);
 int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
 bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
 					  int page_num);
+bool kvm_vector_hashing_enabled(void);
 
 #define KVM_SUPPORTED_XCR0     (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \
 				| XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \
@@ -192,4 +193,19 @@ extern unsigned int min_timer_period_us;
 extern unsigned int lapic_timer_advance_ns;
 
 extern struct static_key kvm_no_apic_vcpu;
+
+/* Same "calling convention" as do_div:
+ * - divide (n << 32) by base
+ * - put result in n
+ * - return remainder
+ */
+#define do_shl32_div32(n, base)					\
+	({							\
+	    u32 __quot, __rem;					\
+	    asm("divl %2" : "=a" (__quot), "=d" (__rem)		\
+			: "rm" (base), "0" (0), "1" ((u32) n));	\
+	    n = __quot;						\
+	    __rem;						\
+	 })
+
 #endif
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 4ba229ac3f4f..fd57d3ae7e16 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -1520,12 +1520,6 @@ __init void lguest_init(void)
 	 */
 	reserve_top_address(lguest_data.reserve_mem);
 
-	/*
-	 * If we don't initialize the lock dependency checker now, it crashes
-	 * atomic_notifier_chain_register, then paravirt_disable_iospace.
-	 */
-	lockdep_init();
-
 	/* Hook in our special panic hypercall code. */
 	atomic_notifier_chain_register(&panic_notifier_list, &paniced);
 
@@ -1535,7 +1529,7 @@ __init void lguest_init(void)
 	 */
 	cpu_detect(&new_cpu_data);
 	/* head.S usually sets up the first capability word, so do it here. */
-	new_cpu_data.x86_capability[0] = cpuid_edx(1);
+	new_cpu_data.x86_capability[CPUID_1_EDX] = cpuid_edx(1);
 
 	/* Math is always hard! */
 	set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU);
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index a2fe51b00cce..65be7cfaf947 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,5 +1,5 @@
 #include <linux/linkage.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 /*
diff --git a/arch/x86/lib/cmdline.c b/arch/x86/lib/cmdline.c
index 422db000d727..5cc78bf57232 100644
--- a/arch/x86/lib/cmdline.c
+++ b/arch/x86/lib/cmdline.c
@@ -21,12 +21,16 @@ static inline int myisspace(u8 c)
  * @option: option string to look for
  *
  * Returns the position of that @option (starts counting with 1)
- * or 0 on not found.
+ * or 0 on not found.  @option will only be found if it is found
+ * as an entire word in @cmdline.  For instance, if @option="car"
+ * then a cmdline which contains "cart" will not match.
  */
-int cmdline_find_option_bool(const char *cmdline, const char *option)
+static int
+__cmdline_find_option_bool(const char *cmdline, int max_cmdline_size,
+			   const char *option)
 {
 	char c;
-	int len, pos = 0, wstart = 0;
+	int pos = 0, wstart = 0;
 	const char *opptr = NULL;
 	enum {
 		st_wordstart = 0,	/* Start of word/after whitespace */
@@ -37,11 +41,11 @@ int cmdline_find_option_bool(const char *cmdline, const char *option)
 	if (!cmdline)
 		return -1;      /* No command line */
 
-	len = min_t(int, strlen(cmdline), COMMAND_LINE_SIZE);
-	if (!len)
-		return 0;
-
-	while (len--) {
+	/*
+	 * This 'pos' check ensures we do not overrun
+	 * a non-NULL-terminated 'cmdline'
+	 */
+	while (pos < max_cmdline_size) {
 		c = *(char *)cmdline++;
 		pos++;
 
@@ -58,18 +62,35 @@ int cmdline_find_option_bool(const char *cmdline, const char *option)
 			/* fall through */
 
 		case st_wordcmp:
-			if (!*opptr)
+			if (!*opptr) {
+				/*
+				 * We matched all the way to the end of the
+				 * option we were looking for.  If the
+				 * command-line has a space _or_ ends, then
+				 * we matched!
+				 */
 				if (!c || myisspace(c))
 					return wstart;
-				else
-					state = st_wordskip;
-			else if (!c)
+				/*
+				 * We hit the end of the option, but _not_
+				 * the end of a word on the cmdline.  Not
+				 * a match.
+				 */
+			} else if (!c) {
+				/*
+				 * Hit the NULL terminator on the end of
+				 * cmdline.
+				 */
 				return 0;
-			else if (c != *opptr++)
-				state = st_wordskip;
-			else if (!len)		/* last word and is matching */
-				return wstart;
-			break;
+			} else if (c == *opptr++) {
+				/*
+				 * We are currently matching, so continue
+				 * to the next character on the cmdline.
+				 */
+				break;
+			}
+			state = st_wordskip;
+			/* fall through */
 
 		case st_wordskip:
 			if (!c)
@@ -82,3 +103,8 @@ int cmdline_find_option_bool(const char *cmdline, const char *option)
 
 	return 0;	/* Buffer overrun */
 }
+
+int cmdline_find_option_bool(const char *cmdline, const char *option)
+{
+	return __cmdline_find_option_bool(cmdline, COMMAND_LINE_SIZE, option);
+}
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index 009f98216b7e..24ef1c2104d4 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -1,7 +1,7 @@
 /* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */
 
 #include <linux/linkage.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 /*
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 982ce34f4a9b..2b0ef26da0bd 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -10,7 +10,7 @@
 #include <asm/current.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
@@ -232,17 +232,31 @@ ENDPROC(copy_user_enhanced_fast_string)
 
 /*
  * copy_user_nocache - Uncached memory copy with exception handling
- * This will force destination/source out of cache for more performance.
+ * This will force destination out of cache for more performance.
+ *
+ * Note: Cached memory copy is used when destination or size is not
+ * naturally aligned. That is:
+ *  - Require 8-byte alignment when size is 8 bytes or larger.
+ *  - Require 4-byte alignment when size is 4 bytes.
  */
 ENTRY(__copy_user_nocache)
 	ASM_STAC
+
+	/* If size is less than 8 bytes, go to 4-byte copy */
 	cmpl $8,%edx
-	jb 20f		/* less then 8 bytes, go to byte copy loop */
+	jb .L_4b_nocache_copy_entry
+
+	/* If destination is not 8-byte aligned, "cache" copy to align it */
 	ALIGN_DESTINATION
+
+	/* Set 4x8-byte copy count and remainder */
 	movl %edx,%ecx
 	andl $63,%edx
 	shrl $6,%ecx
-	jz 17f
+	jz .L_8b_nocache_copy_entry	/* jump if count is 0 */
+
+	/* Perform 4x8-byte nocache loop-copy */
+.L_4x8b_nocache_copy_loop:
 1:	movq (%rsi),%r8
 2:	movq 1*8(%rsi),%r9
 3:	movq 2*8(%rsi),%r10
@@ -262,60 +276,106 @@ ENTRY(__copy_user_nocache)
 	leaq 64(%rsi),%rsi
 	leaq 64(%rdi),%rdi
 	decl %ecx
-	jnz 1b
-17:	movl %edx,%ecx
+	jnz .L_4x8b_nocache_copy_loop
+
+	/* Set 8-byte copy count and remainder */
+.L_8b_nocache_copy_entry:
+	movl %edx,%ecx
 	andl $7,%edx
 	shrl $3,%ecx
-	jz 20f
-18:	movq (%rsi),%r8
-19:	movnti %r8,(%rdi)
+	jz .L_4b_nocache_copy_entry	/* jump if count is 0 */
+
+	/* Perform 8-byte nocache loop-copy */
+.L_8b_nocache_copy_loop:
+20:	movq (%rsi),%r8
+21:	movnti %r8,(%rdi)
 	leaq 8(%rsi),%rsi
 	leaq 8(%rdi),%rdi
 	decl %ecx
-	jnz 18b
-20:	andl %edx,%edx
-	jz 23f
+	jnz .L_8b_nocache_copy_loop
+
+	/* If no byte left, we're done */
+.L_4b_nocache_copy_entry:
+	andl %edx,%edx
+	jz .L_finish_copy
+
+	/* If destination is not 4-byte aligned, go to byte copy: */
+	movl %edi,%ecx
+	andl $3,%ecx
+	jnz .L_1b_cache_copy_entry
+
+	/* Set 4-byte copy count (1 or 0) and remainder */
 	movl %edx,%ecx
-21:	movb (%rsi),%al
-22:	movb %al,(%rdi)
+	andl $3,%edx
+	shrl $2,%ecx
+	jz .L_1b_cache_copy_entry	/* jump if count is 0 */
+
+	/* Perform 4-byte nocache copy: */
+30:	movl (%rsi),%r8d
+31:	movnti %r8d,(%rdi)
+	leaq 4(%rsi),%rsi
+	leaq 4(%rdi),%rdi
+
+	/* If no bytes left, we're done: */
+	andl %edx,%edx
+	jz .L_finish_copy
+
+	/* Perform byte "cache" loop-copy for the remainder */
+.L_1b_cache_copy_entry:
+	movl %edx,%ecx
+.L_1b_cache_copy_loop:
+40:	movb (%rsi),%al
+41:	movb %al,(%rdi)
 	incq %rsi
 	incq %rdi
 	decl %ecx
-	jnz 21b
-23:	xorl %eax,%eax
+	jnz .L_1b_cache_copy_loop
+
+	/* Finished copying; fence the prior stores */
+.L_finish_copy:
+	xorl %eax,%eax
 	ASM_CLAC
 	sfence
 	ret
 
 	.section .fixup,"ax"
-30:	shll $6,%ecx
+.L_fixup_4x8b_copy:
+	shll $6,%ecx
 	addl %ecx,%edx
-	jmp 60f
-40:	lea (%rdx,%rcx,8),%rdx
-	jmp 60f
-50:	movl %ecx,%edx
-60:	sfence
+	jmp .L_fixup_handle_tail
+.L_fixup_8b_copy:
+	lea (%rdx,%rcx,8),%rdx
+	jmp .L_fixup_handle_tail
+.L_fixup_4b_copy:
+	lea (%rdx,%rcx,4),%rdx
+	jmp .L_fixup_handle_tail
+.L_fixup_1b_copy:
+	movl %ecx,%edx
+.L_fixup_handle_tail:
+	sfence
 	jmp copy_user_handle_tail
 	.previous
 
-	_ASM_EXTABLE(1b,30b)
-	_ASM_EXTABLE(2b,30b)
-	_ASM_EXTABLE(3b,30b)
-	_ASM_EXTABLE(4b,30b)
-	_ASM_EXTABLE(5b,30b)
-	_ASM_EXTABLE(6b,30b)
-	_ASM_EXTABLE(7b,30b)
-	_ASM_EXTABLE(8b,30b)
-	_ASM_EXTABLE(9b,30b)
-	_ASM_EXTABLE(10b,30b)
-	_ASM_EXTABLE(11b,30b)
-	_ASM_EXTABLE(12b,30b)
-	_ASM_EXTABLE(13b,30b)
-	_ASM_EXTABLE(14b,30b)
-	_ASM_EXTABLE(15b,30b)
-	_ASM_EXTABLE(16b,30b)
-	_ASM_EXTABLE(18b,40b)
-	_ASM_EXTABLE(19b,40b)
-	_ASM_EXTABLE(21b,50b)
-	_ASM_EXTABLE(22b,50b)
+	_ASM_EXTABLE(1b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(2b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(3b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(4b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(5b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(6b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(7b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(8b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(9b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(10b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(11b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(12b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(13b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(14b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(15b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(16b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(20b,.L_fixup_8b_copy)
+	_ASM_EXTABLE(21b,.L_fixup_8b_copy)
+	_ASM_EXTABLE(30b,.L_fixup_4b_copy)
+	_ASM_EXTABLE(31b,.L_fixup_4b_copy)
+	_ASM_EXTABLE(40b,.L_fixup_1b_copy)
+	_ASM_EXTABLE(41b,.L_fixup_1b_copy)
 ENDPROC(__copy_user_nocache)
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index e912b2f6d36e..2f07c291dcc8 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -102,7 +102,7 @@ static void delay_mwaitx(unsigned long __loops)
 		 * Use cpu_tss as a cacheline-aligned, seldomly
 		 * accessed per-cpu variable as the monitor target.
 		 */
-		__monitorx(this_cpu_ptr(&cpu_tss), 0, 0);
+		__monitorx(raw_cpu_ptr(&cpu_tss), 0, 0);
 
 		/*
 		 * AMD, like Intel, supports the EAX hint and EAX=0xf
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 16698bba87de..cbb8ee5830ff 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -1,7 +1,7 @@
 /* Copyright 2002 Andi Kleen */
 
 #include <linux/linkage.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 /*
@@ -177,3 +177,120 @@ ENTRY(memcpy_orig)
 .Lend:
 	retq
 ENDPROC(memcpy_orig)
+
+#ifndef CONFIG_UML
+/*
+ * memcpy_mcsafe - memory copy with machine check exception handling
+ * Note that we only catch machine checks when reading the source addresses.
+ * Writes to target are posted and don't generate machine checks.
+ */
+ENTRY(memcpy_mcsafe)
+	cmpl $8, %edx
+	/* Less than 8 bytes? Go to byte copy loop */
+	jb .L_no_whole_words
+
+	/* Check for bad alignment of source */
+	testl $7, %esi
+	/* Already aligned */
+	jz .L_8byte_aligned
+
+	/* Copy one byte at a time until source is 8-byte aligned */
+	movl %esi, %ecx
+	andl $7, %ecx
+	subl $8, %ecx
+	negl %ecx
+	subl %ecx, %edx
+.L_copy_leading_bytes:
+	movb (%rsi), %al
+	movb %al, (%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz .L_copy_leading_bytes
+
+.L_8byte_aligned:
+	/* Figure out how many whole cache lines (64-bytes) to copy */
+	movl %edx, %ecx
+	andl $63, %edx
+	shrl $6, %ecx
+	jz .L_no_whole_cache_lines
+
+	/* Loop copying whole cache lines */
+.L_cache_w0: movq (%rsi), %r8
+.L_cache_w1: movq 1*8(%rsi), %r9
+.L_cache_w2: movq 2*8(%rsi), %r10
+.L_cache_w3: movq 3*8(%rsi), %r11
+	movq %r8, (%rdi)
+	movq %r9, 1*8(%rdi)
+	movq %r10, 2*8(%rdi)
+	movq %r11, 3*8(%rdi)
+.L_cache_w4: movq 4*8(%rsi), %r8
+.L_cache_w5: movq 5*8(%rsi), %r9
+.L_cache_w6: movq 6*8(%rsi), %r10
+.L_cache_w7: movq 7*8(%rsi), %r11
+	movq %r8, 4*8(%rdi)
+	movq %r9, 5*8(%rdi)
+	movq %r10, 6*8(%rdi)
+	movq %r11, 7*8(%rdi)
+	leaq 64(%rsi), %rsi
+	leaq 64(%rdi), %rdi
+	decl %ecx
+	jnz .L_cache_w0
+
+	/* Are there any trailing 8-byte words? */
+.L_no_whole_cache_lines:
+	movl %edx, %ecx
+	andl $7, %edx
+	shrl $3, %ecx
+	jz .L_no_whole_words
+
+	/* Copy trailing words */
+.L_copy_trailing_words:
+	movq (%rsi), %r8
+	mov %r8, (%rdi)
+	leaq 8(%rsi), %rsi
+	leaq 8(%rdi), %rdi
+	decl %ecx
+	jnz .L_copy_trailing_words
+
+	/* Any trailing bytes? */
+.L_no_whole_words:
+	andl %edx, %edx
+	jz .L_done_memcpy_trap
+
+	/* Copy trailing bytes */
+	movl %edx, %ecx
+.L_copy_trailing_bytes:
+	movb (%rsi), %al
+	movb %al, (%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz .L_copy_trailing_bytes
+
+	/* Copy successful. Return true */
+.L_done_memcpy_trap:
+	xorq %rax, %rax
+	ret
+ENDPROC(memcpy_mcsafe)
+
+	.section .fixup, "ax"
+	/* Return false for any failure */
+.L_memcpy_mcsafe_fail:
+	mov	$1, %rax
+	ret
+
+	.previous
+
+	_ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail)
+#endif
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index ca2afdd6d98e..90ce01bee00c 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -6,7 +6,7 @@
  *	- Copyright 2011 Fenghua Yu <fenghua.yu@intel.com>
  */
 #include <linux/linkage.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 #undef memmove
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 2661fad05827..c9c81227ea37 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -1,7 +1,7 @@
 /* Copyright 2002 Andi Kleen, SuSE Labs */
 
 #include <linux/linkage.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 .weak memset
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 4a6f1d9b5106..99bfb192803f 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -358,20 +358,19 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
 #define pgd_none(a)  pud_none(__pud(pgd_val(a)))
 #endif
 
-#ifdef CONFIG_X86_64
 static inline bool is_hypervisor_range(int idx)
 {
+#ifdef CONFIG_X86_64
 	/*
 	 * ffff800000000000 - ffff87ffffffffff is reserved for
 	 * the hypervisor.
 	 */
-	return paravirt_enabled() &&
-		(idx >= pgd_index(__PAGE_OFFSET) - 16) &&
-		(idx < pgd_index(__PAGE_OFFSET));
-}
+	return	(idx >= pgd_index(__PAGE_OFFSET) - 16) &&
+		(idx <  pgd_index(__PAGE_OFFSET));
 #else
-static inline bool is_hypervisor_range(int idx) { return false; }
+	return false;
 #endif
+}
 
 static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 				       bool checkwx)
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 903ec1e9c326..9dd7e4b7fcde 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -3,6 +3,9 @@
 #include <linux/sort.h>
 #include <asm/uaccess.h>
 
+typedef bool (*ex_handler_t)(const struct exception_table_entry *,
+			    struct pt_regs *, int);
+
 static inline unsigned long
 ex_insn_addr(const struct exception_table_entry *x)
 {
@@ -13,11 +16,56 @@ ex_fixup_addr(const struct exception_table_entry *x)
 {
 	return (unsigned long)&x->fixup + x->fixup;
 }
+static inline ex_handler_t
+ex_fixup_handler(const struct exception_table_entry *x)
+{
+	return (ex_handler_t)((unsigned long)&x->handler + x->handler);
+}
 
-int fixup_exception(struct pt_regs *regs)
+bool ex_handler_default(const struct exception_table_entry *fixup,
+		       struct pt_regs *regs, int trapnr)
 {
-	const struct exception_table_entry *fixup;
-	unsigned long new_ip;
+	regs->ip = ex_fixup_addr(fixup);
+	return true;
+}
+EXPORT_SYMBOL(ex_handler_default);
+
+bool ex_handler_fault(const struct exception_table_entry *fixup,
+		     struct pt_regs *regs, int trapnr)
+{
+	regs->ip = ex_fixup_addr(fixup);
+	regs->ax = trapnr;
+	return true;
+}
+EXPORT_SYMBOL_GPL(ex_handler_fault);
+
+bool ex_handler_ext(const struct exception_table_entry *fixup,
+		   struct pt_regs *regs, int trapnr)
+{
+	/* Special hack for uaccess_err */
+	current_thread_info()->uaccess_err = 1;
+	regs->ip = ex_fixup_addr(fixup);
+	return true;
+}
+EXPORT_SYMBOL(ex_handler_ext);
+
+bool ex_has_fault_handler(unsigned long ip)
+{
+	const struct exception_table_entry *e;
+	ex_handler_t handler;
+
+	e = search_exception_tables(ip);
+	if (!e)
+		return false;
+	handler = ex_fixup_handler(e);
+
+	return handler == ex_handler_fault;
+}
+
+int fixup_exception(struct pt_regs *regs, int trapnr)
+{
+	const struct exception_table_entry *e;
+	ex_handler_t handler;
 
 #ifdef CONFIG_PNPBIOS
 	if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) {
@@ -33,42 +81,34 @@ int fixup_exception(struct pt_regs *regs)
 	}
 #endif
 
-	fixup = search_exception_tables(regs->ip);
-	if (fixup) {
-		new_ip = ex_fixup_addr(fixup);
-
-		if (fixup->fixup - fixup->insn >= 0x7ffffff0 - 4) {
-			/* Special hack for uaccess_err */
-			current_thread_info()->uaccess_err = 1;
-			new_ip -= 0x7ffffff0;
-		}
-		regs->ip = new_ip;
-		return 1;
-	}
+	e = search_exception_tables(regs->ip);
+	if (!e)
+		return 0;
 
-	return 0;
+	handler = ex_fixup_handler(e);
+	return handler(e, regs, trapnr);
 }
 
 /* Restricted version used during very early boot */
 int __init early_fixup_exception(unsigned long *ip)
 {
-	const struct exception_table_entry *fixup;
+	const struct exception_table_entry *e;
 	unsigned long new_ip;
+	ex_handler_t handler;
 
-	fixup = search_exception_tables(*ip);
-	if (fixup) {
-		new_ip = ex_fixup_addr(fixup);
+	e = search_exception_tables(*ip);
+	if (!e)
+		return 0;
 
-		if (fixup->fixup - fixup->insn >= 0x7ffffff0 - 4) {
-			/* uaccess handling not supported during early boot */
-			return 0;
-		}
+	new_ip  = ex_fixup_addr(e);
+	handler = ex_fixup_handler(e);
 
-		*ip = new_ip;
-		return 1;
-	}
+	/* special handling not supported during early boot */
+	if (handler != ex_handler_default)
+		return 0;
 
-	return 0;
+	*ip = new_ip;
+	return 1;
 }
 
 /*
@@ -133,6 +173,8 @@ void sort_extable(struct exception_table_entry *start,
 		i += 4;
 		p->fixup += i;
 		i += 4;
+		p->handler += i;
+		i += 4;
 	}
 
 	sort(start, finish - start, sizeof(struct exception_table_entry),
@@ -145,6 +187,8 @@ void sort_extable(struct exception_table_entry *start,
 		i += 4;
 		p->fixup -= i;
 		i += 4;
+		p->handler -= i;
+		i += 4;
 	}
 }
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index eef44d9a3f77..03898aea6e0f 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -287,6 +287,9 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (!pmd_k)
 		return -1;
 
+	if (pmd_huge(*pmd_k))
+		return 0;
+
 	pte_k = pte_offset_kernel(pmd_k, address);
 	if (!pte_present(*pte_k))
 		return -1;
@@ -360,8 +363,6 @@ void vmalloc_sync_all(void)
  * 64-bit:
  *
  *   Handle a fault on the vmalloc area
- *
- * This assumes no large pages in there.
  */
 static noinline int vmalloc_fault(unsigned long address)
 {
@@ -403,17 +404,23 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (pud_none(*pud_ref))
 		return -1;
 
-	if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref))
+	if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref))
 		BUG();
 
+	if (pud_huge(*pud))
+		return 0;
+
 	pmd = pmd_offset(pud, address);
 	pmd_ref = pmd_offset(pud_ref, address);
 	if (pmd_none(*pmd_ref))
 		return -1;
 
-	if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref))
+	if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref))
 		BUG();
 
+	if (pmd_huge(*pmd))
+		return 0;
+
 	pte_ref = pte_offset_kernel(pmd_ref, address);
 	if (!pte_present(*pte_ref))
 		return -1;
@@ -656,7 +663,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 	int sig;
 
 	/* Are we prepared to handle this kernel fault? */
-	if (fixup_exception(regs)) {
+	if (fixup_exception(regs, X86_TRAP_PF)) {
 		/*
 		 * Any interrupt that takes a fault gets the fixup. This makes
 		 * the below recursive fault logic only apply to a faults from
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 6d5eb5900372..d8a798d8bf50 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -102,7 +102,6 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 			return 0;
 		}
 
-		page = pte_page(pte);
 		if (pte_devmap(pte)) {
 			pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
 			if (unlikely(!pgmap)) {
@@ -115,6 +114,7 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 			return 0;
 		}
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+		page = pte_page(pte);
 		get_page(page);
 		put_dev_pagemap(pgmap);
 		SetPageReferenced(page);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 493f54172b4a..9d56f271d519 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -150,13 +150,14 @@ static int page_size_mask;
 
 static void __init probe_page_size_mask(void)
 {
-#if !defined(CONFIG_DEBUG_PAGEALLOC) && !defined(CONFIG_KMEMCHECK)
+#if !defined(CONFIG_KMEMCHECK)
 	/*
-	 * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
+	 * For CONFIG_KMEMCHECK or pagealloc debugging, identity mapping will
+	 * use small pages.
 	 * This will simplify cpa(), which otherwise needs to support splitting
 	 * large pages into small in interrupt context, etc.
 	 */
-	if (cpu_has_pse)
+	if (cpu_has_pse && !debug_pagealloc_enabled())
 		page_size_mask |= 1 << PG_LEVEL_2M;
 #endif
 
@@ -666,21 +667,22 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	 * mark them not present - any buggy init-section access will
 	 * create a kernel page fault:
 	 */
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	printk(KERN_INFO "debug: unmapping init [mem %#010lx-%#010lx]\n",
-		begin, end - 1);
-	set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
-#else
-	/*
-	 * We just marked the kernel text read only above, now that
-	 * we are going to free part of that, we need to make that
-	 * writeable and non-executable first.
-	 */
-	set_memory_nx(begin, (end - begin) >> PAGE_SHIFT);
-	set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);
+	if (debug_pagealloc_enabled()) {
+		pr_info("debug: unmapping init [mem %#010lx-%#010lx]\n",
+			begin, end - 1);
+		set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
+	} else {
+		/*
+		 * We just marked the kernel text read only above, now that
+		 * we are going to free part of that, we need to make that
+		 * writeable and non-executable first.
+		 */
+		set_memory_nx(begin, (end - begin) >> PAGE_SHIFT);
+		set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);
 
-	free_reserved_area((void *)begin, (void *)end, POISON_FREE_INITMEM, what);
-#endif
+		free_reserved_area((void *)begin, (void *)end,
+				   POISON_FREE_INITMEM, what);
+	}
 }
 
 void free_initmem(void)
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index cb4ef3de61f9..bd7a9b9e2e14 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -388,7 +388,6 @@ repeat:
 }
 
 pte_t *kmap_pte;
-pgprot_t kmap_prot;
 
 static inline pte_t *kmap_get_fixmap_pte(unsigned long vaddr)
 {
@@ -405,8 +404,6 @@ static void __init kmap_init(void)
 	 */
 	kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN);
 	kmap_pte = kmap_get_fixmap_pte(kmap_vstart);
-
-	kmap_prot = PAGE_KERNEL;
 }
 
 #ifdef CONFIG_HIGHMEM
@@ -871,7 +868,6 @@ static noinline int do_test_wp_bit(void)
 	return flag;
 }
 
-#ifdef CONFIG_DEBUG_RODATA
 const int rodata_test_data = 0xC3;
 EXPORT_SYMBOL_GPL(rodata_test_data);
 
@@ -960,5 +956,3 @@ void mark_rodata_ro(void)
 	if (__supported_pte_mask & _PAGE_NX)
 		debug_checkwx();
 }
-#endif
-
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 5488d21123bd..214afda97911 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -53,6 +53,7 @@
 #include <asm/numa.h>
 #include <asm/cacheflush.h>
 #include <asm/init.h>
+#include <asm/uv/uv.h>
 #include <asm/setup.h>
 
 #include "mm_internal.h"
@@ -1074,7 +1075,6 @@ void __init mem_init(void)
 	mem_init_print_info(NULL);
 }
 
-#ifdef CONFIG_DEBUG_RODATA
 const int rodata_test_data = 0xC3;
 EXPORT_SYMBOL_GPL(rodata_test_data);
 
@@ -1166,8 +1166,6 @@ void mark_rodata_ro(void)
 	debug_checkwx();
 }
 
-#endif
-
 int kern_addr_valid(unsigned long addr)
 {
 	unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT;
@@ -1206,26 +1204,13 @@ int kern_addr_valid(unsigned long addr)
 
 static unsigned long probe_memory_block_size(void)
 {
-	/* start from 2g */
-	unsigned long bz = 1UL<<31;
-
-	if (totalram_pages >= (64ULL << (30 - PAGE_SHIFT))) {
-		pr_info("Using 2GB memory block size for large-memory system\n");
-		return 2UL * 1024 * 1024 * 1024;
-	}
-
-	/* less than 64g installed */
-	if ((max_pfn << PAGE_SHIFT) < (16UL << 32))
-		return MIN_MEMORY_BLOCK_SIZE;
+	unsigned long bz = MIN_MEMORY_BLOCK_SIZE;
 
-	/* get the tail size */
-	while (bz > MIN_MEMORY_BLOCK_SIZE) {
-		if (!((max_pfn << PAGE_SHIFT) & (bz - 1)))
-			break;
-		bz >>= 1;
-	}
+	/* if system is UV or has 64GB of RAM or more, use large blocks */
+	if (is_uv_system() || ((max_pfn << PAGE_SHIFT) >= (64UL << 30)))
+		bz = 2UL << 30; /* 2GB */
 
-	printk(KERN_DEBUG "memory block size : %ldMB\n", bz >> 20);
+	pr_info("x86/mm: Memory block size: %ldMB\n", bz >> 20);
 
 	return bz;
 }
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index d470cf219a2d..1b1110fa0057 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -120,11 +120,22 @@ void __init kasan_init(void)
 	kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END),
 			(void *)KASAN_SHADOW_END);
 
-	memset(kasan_zero_page, 0, PAGE_SIZE);
-
 	load_cr3(init_level4_pgt);
 	__flush_tlb_all();
-	init_task.kasan_depth = 0;
 
+	/*
+	 * kasan_zero_page has been used as early shadow memory, thus it may
+	 * contain some garbage. Now we can clear and write protect it, since
+	 * after the TLB flush no one should write to it.
+	 */
+	memset(kasan_zero_page, 0, PAGE_SIZE);
+	for (i = 0; i < PTRS_PER_PTE; i++) {
+		pte_t pte = __pte(__pa(kasan_zero_page) | __PAGE_KERNEL_RO);
+		set_pte(&kasan_zero_pte[i], pte);
+	}
+	/* Flush TLBs again to be sure that write protection applied. */
+	__flush_tlb_all();
+
+	init_task.kasan_depth = 0;
 	pr_info("KernelAddressSanitizer initialized\n");
 }
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 637ab34ed632..ddb2244b06a1 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -33,7 +33,7 @@
 struct kmmio_fault_page {
 	struct list_head list;
 	struct kmmio_fault_page *release_next;
-	unsigned long page; /* location of the fault page */
+	unsigned long addr; /* the requested address */
 	pteval_t old_presence; /* page presence prior to arming */
 	bool armed;
 
@@ -70,9 +70,16 @@ unsigned int kmmio_count;
 static struct list_head kmmio_page_table[KMMIO_PAGE_TABLE_SIZE];
 static LIST_HEAD(kmmio_probes);
 
-static struct list_head *kmmio_page_list(unsigned long page)
+static struct list_head *kmmio_page_list(unsigned long addr)
 {
-	return &kmmio_page_table[hash_long(page, KMMIO_PAGE_HASH_BITS)];
+	unsigned int l;
+	pte_t *pte = lookup_address(addr, &l);
+
+	if (!pte)
+		return NULL;
+	addr &= page_level_mask(l);
+
+	return &kmmio_page_table[hash_long(addr, KMMIO_PAGE_HASH_BITS)];
 }
 
 /* Accessed per-cpu */
@@ -98,15 +105,19 @@ static struct kmmio_probe *get_kmmio_probe(unsigned long addr)
 }
 
 /* You must be holding RCU read lock. */
-static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long page)
+static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long addr)
 {
 	struct list_head *head;
 	struct kmmio_fault_page *f;
+	unsigned int l;
+	pte_t *pte = lookup_address(addr, &l);
 
-	page &= PAGE_MASK;
-	head = kmmio_page_list(page);
+	if (!pte)
+		return NULL;
+	addr &= page_level_mask(l);
+	head = kmmio_page_list(addr);
 	list_for_each_entry_rcu(f, head, list) {
-		if (f->page == page)
+		if (f->addr == addr)
 			return f;
 	}
 	return NULL;
@@ -137,10 +148,10 @@ static void clear_pte_presence(pte_t *pte, bool clear, pteval_t *old)
 static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
 {
 	unsigned int level;
-	pte_t *pte = lookup_address(f->page, &level);
+	pte_t *pte = lookup_address(f->addr, &level);
 
 	if (!pte) {
-		pr_err("no pte for page 0x%08lx\n", f->page);
+		pr_err("no pte for addr 0x%08lx\n", f->addr);
 		return -1;
 	}
 
@@ -156,7 +167,7 @@ static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
 		return -1;
 	}
 
-	__flush_tlb_one(f->page);
+	__flush_tlb_one(f->addr);
 	return 0;
 }
 
@@ -176,12 +187,12 @@ static int arm_kmmio_fault_page(struct kmmio_fault_page *f)
 	int ret;
 	WARN_ONCE(f->armed, KERN_ERR pr_fmt("kmmio page already armed.\n"));
 	if (f->armed) {
-		pr_warning("double-arm: page 0x%08lx, ref %d, old %d\n",
-			   f->page, f->count, !!f->old_presence);
+		pr_warning("double-arm: addr 0x%08lx, ref %d, old %d\n",
+			   f->addr, f->count, !!f->old_presence);
 	}
 	ret = clear_page_presence(f, true);
-	WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming 0x%08lx failed.\n"),
-		  f->page);
+	WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming at 0x%08lx failed.\n"),
+		  f->addr);
 	f->armed = true;
 	return ret;
 }
@@ -191,7 +202,7 @@ static void disarm_kmmio_fault_page(struct kmmio_fault_page *f)
 {
 	int ret = clear_page_presence(f, false);
 	WARN_ONCE(ret < 0,
-			KERN_ERR "kmmio disarming 0x%08lx failed.\n", f->page);
+			KERN_ERR "kmmio disarming at 0x%08lx failed.\n", f->addr);
 	f->armed = false;
 }
 
@@ -215,6 +226,12 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 	struct kmmio_context *ctx;
 	struct kmmio_fault_page *faultpage;
 	int ret = 0; /* default to fault not handled */
+	unsigned long page_base = addr;
+	unsigned int l;
+	pte_t *pte = lookup_address(addr, &l);
+	if (!pte)
+		return -EINVAL;
+	page_base &= page_level_mask(l);
 
 	/*
 	 * Preemption is now disabled to prevent process switch during
@@ -227,7 +244,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 	preempt_disable();
 	rcu_read_lock();
 
-	faultpage = get_kmmio_fault_page(addr);
+	faultpage = get_kmmio_fault_page(page_base);
 	if (!faultpage) {
 		/*
 		 * Either this page fault is not caused by kmmio, or
@@ -239,7 +256,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 
 	ctx = &get_cpu_var(kmmio_ctx);
 	if (ctx->active) {
-		if (addr == ctx->addr) {
+		if (page_base == ctx->addr) {
 			/*
 			 * A second fault on the same page means some other
 			 * condition needs handling by do_page_fault(), the
@@ -267,9 +284,9 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 	ctx->active++;
 
 	ctx->fpage = faultpage;
-	ctx->probe = get_kmmio_probe(addr);
+	ctx->probe = get_kmmio_probe(page_base);
 	ctx->saved_flags = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF));
-	ctx->addr = addr;
+	ctx->addr = page_base;
 
 	if (ctx->probe && ctx->probe->pre_handler)
 		ctx->probe->pre_handler(ctx->probe, regs, addr);
@@ -354,12 +371,11 @@ out:
 }
 
 /* You must be holding kmmio_lock. */
-static int add_kmmio_fault_page(unsigned long page)
+static int add_kmmio_fault_page(unsigned long addr)
 {
 	struct kmmio_fault_page *f;
 
-	page &= PAGE_MASK;
-	f = get_kmmio_fault_page(page);
+	f = get_kmmio_fault_page(addr);
 	if (f) {
 		if (!f->count)
 			arm_kmmio_fault_page(f);
@@ -372,26 +388,25 @@ static int add_kmmio_fault_page(unsigned long page)
 		return -1;
 
 	f->count = 1;
-	f->page = page;
+	f->addr = addr;
 
 	if (arm_kmmio_fault_page(f)) {
 		kfree(f);
 		return -1;
 	}
 
-	list_add_rcu(&f->list, kmmio_page_list(f->page));
+	list_add_rcu(&f->list, kmmio_page_list(f->addr));
 
 	return 0;
 }
 
 /* You must be holding kmmio_lock. */
-static void release_kmmio_fault_page(unsigned long page,
+static void release_kmmio_fault_page(unsigned long addr,
 				struct kmmio_fault_page **release_list)
 {
 	struct kmmio_fault_page *f;
 
-	page &= PAGE_MASK;
-	f = get_kmmio_fault_page(page);
+	f = get_kmmio_fault_page(addr);
 	if (!f)
 		return;
 
@@ -420,18 +435,27 @@ int register_kmmio_probe(struct kmmio_probe *p)
 	int ret = 0;
 	unsigned long size = 0;
 	const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
+	unsigned int l;
+	pte_t *pte;
 
 	spin_lock_irqsave(&kmmio_lock, flags);
 	if (get_kmmio_probe(p->addr)) {
 		ret = -EEXIST;
 		goto out;
 	}
+
+	pte = lookup_address(p->addr, &l);
+	if (!pte) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	kmmio_count++;
 	list_add_rcu(&p->list, &kmmio_probes);
 	while (size < size_lim) {
 		if (add_kmmio_fault_page(p->addr + size))
 			pr_err("Unable to set page fault.\n");
-		size += PAGE_SIZE;
+		size += page_level_size(l);
 	}
 out:
 	spin_unlock_irqrestore(&kmmio_lock, flags);
@@ -506,11 +530,17 @@ void unregister_kmmio_probe(struct kmmio_probe *p)
 	const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
 	struct kmmio_fault_page *release_list = NULL;
 	struct kmmio_delayed_release *drelease;
+	unsigned int l;
+	pte_t *pte;
+
+	pte = lookup_address(p->addr, &l);
+	if (!pte)
+		return;
 
 	spin_lock_irqsave(&kmmio_lock, flags);
 	while (size < size_lim) {
 		release_kmmio_fault_page(p->addr + size, &release_list);
-		size += PAGE_SIZE;
+		size += page_level_size(l);
 	}
 	list_del_rcu(&p->list);
 	kmmio_count--;
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 96bd1e2bffaf..d2dc0438d654 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -71,12 +71,12 @@ unsigned long arch_mmap_rnd(void)
 
 	if (mmap_is_ia32())
 #ifdef CONFIG_COMPAT
-		rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_compat_bits) - 1);
+		rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
 #else
-		rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1);
+		rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
 #endif
 	else
-		rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1);
+		rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
 
 	return rnd << PAGE_SHIFT;
 }
@@ -94,18 +94,6 @@ static unsigned long mmap_base(unsigned long rnd)
 }
 
 /*
- * Bottom-up (legacy) layout on X86_32 did not support randomization, X86_64
- * does, but not when emulating X86_32
- */
-static unsigned long mmap_legacy_base(unsigned long rnd)
-{
-	if (mmap_is_ia32())
-		return TASK_UNMAPPED_BASE;
-	else
-		return TASK_UNMAPPED_BASE + rnd;
-}
-
-/*
  * This function, called very early during the creation of a new
  * process VM image, sets up which VM layout function to use:
  */
@@ -116,7 +104,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	if (current->flags & PF_RANDOMIZE)
 		random_factor = arch_mmap_rnd();
 
-	mm->mmap_legacy_base = mmap_legacy_base(random_factor);
+	mm->mmap_legacy_base = TASK_UNMAPPED_BASE + random_factor;
 
 	if (mmap_is_legacy()) {
 		mm->mmap_base = mm->mmap_legacy_base;
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index b2fd67da1701..ef05755a1900 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -123,7 +123,7 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
 		break;
 	}
 
-	if (regno > nr_registers) {
+	if (regno >= nr_registers) {
 		WARN_ONCE(1, "decoded an instruction with an invalid register");
 		return -EINVAL;
 	}
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index c3b3f653ed0c..f70c1ff46125 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -465,46 +465,67 @@ static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
 	return true;
 }
 
+/*
+ * Mark all currently memblock-reserved physical memory (which covers the
+ * kernel's own memory ranges) as hot-unswappable.
+ */
 static void __init numa_clear_kernel_node_hotplug(void)
 {
-	int i, nid;
-	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
-	unsigned long start, end;
-	struct memblock_region *r;
+	nodemask_t reserved_nodemask = NODE_MASK_NONE;
+	struct memblock_region *mb_region;
+	int i;
 
 	/*
+	 * We have to do some preprocessing of memblock regions, to
+	 * make them suitable for reservation.
+	 *
 	 * At this time, all memory regions reserved by memblock are
-	 * used by the kernel. Set the nid in memblock.reserved will
-	 * mark out all the nodes the kernel resides in.
+	 * used by the kernel, but those regions are not split up
+	 * along node boundaries yet, and don't necessarily have their
+	 * node ID set yet either.
+	 *
+	 * So iterate over all memory known to the x86 architecture,
+	 * and use those ranges to set the nid in memblock.reserved.
+	 * This will split up the memblock regions along node
+	 * boundaries and will set the node IDs as well.
 	 */
 	for (i = 0; i < numa_meminfo.nr_blks; i++) {
-		struct numa_memblk *mb = &numa_meminfo.blk[i];
+		struct numa_memblk *mb = numa_meminfo.blk + i;
+		int ret;
 
-		memblock_set_node(mb->start, mb->end - mb->start,
-				  &memblock.reserved, mb->nid);
+		ret = memblock_set_node(mb->start, mb->end - mb->start, &memblock.reserved, mb->nid);
+		WARN_ON_ONCE(ret);
 	}
 
 	/*
-	 * Mark all kernel nodes.
+	 * Now go over all reserved memblock regions, to construct a
+	 * node mask of all kernel reserved memory areas.
 	 *
-	 * When booting with mem=nn[kMG] or in a kdump kernel, numa_meminfo
-	 * may not include all the memblock.reserved memory ranges because
-	 * trim_snb_memory() reserves specific pages for Sandy Bridge graphics.
+	 * [ Note, when booting with mem=nn[kMG] or in a kdump kernel,
+	 *   numa_meminfo might not include all memblock.reserved
+	 *   memory ranges, because quirks such as trim_snb_memory()
+	 *   reserve specific pages for Sandy Bridge graphics. ]
 	 */
-	for_each_memblock(reserved, r)
-		if (r->nid != MAX_NUMNODES)
-			node_set(r->nid, numa_kernel_nodes);
+	for_each_memblock(reserved, mb_region) {
+		if (mb_region->nid != MAX_NUMNODES)
+			node_set(mb_region->nid, reserved_nodemask);
+	}
 
-	/* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
+	/*
+	 * Finally, clear the MEMBLOCK_HOTPLUG flag for all memory
+	 * belonging to the reserved node mask.
+	 *
+	 * Note that this will include memory regions that reside
+	 * on nodes that contain kernel memory - entire nodes
+	 * become hot-unpluggable:
+	 */
 	for (i = 0; i < numa_meminfo.nr_blks; i++) {
-		nid = numa_meminfo.blk[i].nid;
-		if (!node_isset(nid, numa_kernel_nodes))
-			continue;
+		struct numa_memblk *mb = numa_meminfo.blk + i;
 
-		start = numa_meminfo.blk[i].start;
-		end = numa_meminfo.blk[i].end;
+		if (!node_isset(mb->nid, reserved_nodemask))
+			continue;
 
-		memblock_clear_hotplug(start, end - start);
+		memblock_clear_hotplug(mb->start, mb->end - mb->start);
 	}
 }
 
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 2440814b0069..4d0b26253042 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -106,12 +106,6 @@ static inline unsigned long highmap_end_pfn(void)
 
 #endif
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
-# define debug_pagealloc 1
-#else
-# define debug_pagealloc 0
-#endif
-
 static inline int
 within(unsigned long addr, unsigned long start, unsigned long end)
 {
@@ -283,7 +277,7 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 		   __pa_symbol(__end_rodata) >> PAGE_SHIFT))
 		pgprot_val(forbidden) |= _PAGE_RW;
 
-#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
+#if defined(CONFIG_X86_64)
 	/*
 	 * Once the kernel maps the text as RO (kernel_set_to_readonly is set),
 	 * kernel text mappings for the large page aligned text, rodata sections
@@ -419,24 +413,30 @@ pmd_t *lookup_pmd_address(unsigned long address)
 phys_addr_t slow_virt_to_phys(void *__virt_addr)
 {
 	unsigned long virt_addr = (unsigned long)__virt_addr;
-	unsigned long phys_addr, offset;
+	phys_addr_t phys_addr;
+	unsigned long offset;
 	enum pg_level level;
 	pte_t *pte;
 
 	pte = lookup_address(virt_addr, &level);
 	BUG_ON(!pte);
 
+	/*
+	 * pXX_pfn() returns unsigned long, which must be cast to phys_addr_t
+	 * before being left-shifted PAGE_SHIFT bits -- this trick is to
+	 * make 32-PAE kernel work correctly.
+	 */
 	switch (level) {
 	case PG_LEVEL_1G:
-		phys_addr = pud_pfn(*(pud_t *)pte) << PAGE_SHIFT;
+		phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT;
 		offset = virt_addr & ~PUD_PAGE_MASK;
 		break;
 	case PG_LEVEL_2M:
-		phys_addr = pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT;
+		phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT;
 		offset = virt_addr & ~PMD_PAGE_MASK;
 		break;
 	default:
-		phys_addr = pte_pfn(*pte) << PAGE_SHIFT;
+		phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
 		offset = virt_addr & ~PAGE_MASK;
 	}
 
@@ -708,10 +708,10 @@ static int split_large_page(struct cpa_data *cpa, pte_t *kpte,
 {
 	struct page *base;
 
-	if (!debug_pagealloc)
+	if (!debug_pagealloc_enabled())
 		spin_unlock(&cpa_lock);
 	base = alloc_pages(GFP_KERNEL | __GFP_NOTRACK, 0);
-	if (!debug_pagealloc)
+	if (!debug_pagealloc_enabled())
 		spin_lock(&cpa_lock);
 	if (!base)
 		return -ENOMEM;
@@ -1122,8 +1122,10 @@ static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr,
 	/*
 	 * Ignore all non primary paths.
 	 */
-	if (!primary)
+	if (!primary) {
+		cpa->numpages = 1;
 		return 0;
+	}
 
 	/*
 	 * Ignore the NULL PTE for kernel identity mapping, as it is expected
@@ -1331,10 +1333,10 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
 		if (cpa->flags & (CPA_ARRAY | CPA_PAGES_ARRAY))
 			cpa->numpages = 1;
 
-		if (!debug_pagealloc)
+		if (!debug_pagealloc_enabled())
 			spin_lock(&cpa_lock);
 		ret = __change_page_attr(cpa, checkalias);
-		if (!debug_pagealloc)
+		if (!debug_pagealloc_enabled())
 			spin_unlock(&cpa_lock);
 		if (ret)
 			return ret;
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index f4ae536b0914..04e2e7144bee 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -943,7 +943,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
 			return -EINVAL;
 	}
 
-	*prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) |
+	*prot = __pgprot((pgprot_val(*prot) & (~_PAGE_CACHE_MASK)) |
 			 cachemode2protval(pcm));
 
 	return 0;
@@ -959,7 +959,7 @@ int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
 
 	/* Set prot based on lookup */
 	pcm = lookup_memtype(pfn_t_to_phys(pfn));
-	*prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) |
+	*prot = __pgprot((pgprot_val(*prot) & (~_PAGE_CACHE_MASK)) |
 			 cachemode2protval(pcm));
 
 	return 0;
diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c
index 92e2eacb3321..8bea84724a7d 100644
--- a/arch/x86/mm/setup_nx.c
+++ b/arch/x86/mm/setup_nx.c
@@ -4,6 +4,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/proto.h>
+#include <asm/cpufeature.h>
 
 static int disable_nx;
 
@@ -31,9 +32,8 @@ early_param("noexec", noexec_setup);
 
 void x86_configure_nx(void)
 {
-	if (boot_cpu_has(X86_FEATURE_NX) && !disable_nx)
-		__supported_pte_mask |= _PAGE_NX;
-	else
+	/* If disable_nx is set, clear NX on all new mappings going forward. */
+	if (disable_nx)
 		__supported_pte_mask &= ~_PAGE_NX;
 }
 
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index 50d86c0e9ba4..660a83c8287b 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -24,7 +24,6 @@
 #include <asm/nmi.h>
 #include <asm/apic.h>
 #include <asm/processor.h>
-#include <asm/cpufeature.h>
 
 #include "op_x86_model.h"
 #include "op_counter.h"
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 2879efc73a96..381a43c40bf7 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -12,7 +12,6 @@
 #include <linux/dmi.h>
 #include <linux/slab.h>
 
-#include <asm-generic/pci-bridge.h>
 #include <asm/acpi.h>
 #include <asm/segment.h>
 #include <asm/io.h>
@@ -711,28 +710,22 @@ int pcibios_add_device(struct pci_dev *dev)
 	return 0;
 }
 
-int pcibios_alloc_irq(struct pci_dev *dev)
+int pcibios_enable_device(struct pci_dev *dev, int mask)
 {
-	/*
-	 * If the PCI device was already claimed by core code and has
-	 * MSI enabled, probing of the pcibios IRQ will overwrite
-	 * dev->irq.  So bail out if MSI is already enabled.
-	 */
-	if (pci_dev_msi_enabled(dev))
-		return -EBUSY;
+	int err;
 
-	return pcibios_enable_irq(dev);
-}
+	if ((err = pci_enable_resources(dev, mask)) < 0)
+		return err;
 
-void pcibios_free_irq(struct pci_dev *dev)
-{
-	if (pcibios_disable_irq)
-		pcibios_disable_irq(dev);
+	if (!pci_dev_msi_enabled(dev))
+		return pcibios_enable_irq(dev);
+	return 0;
 }
 
-int pcibios_enable_device(struct pci_dev *dev, int mask)
+void pcibios_disable_device (struct pci_dev *dev)
 {
-	return pci_enable_resources(dev, mask);
+	if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq)
+		pcibios_disable_irq(dev);
 }
 
 int pci_ext_cfg_avail(void)
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index e58565556703..b7de1929714b 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -297,14 +297,14 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_MCH_PC1,	pcie_r
  *
  * The standard boot ROM sequence for an x86 machine uses the BIOS
  * to select an initial video card for boot display. This boot video
- * card will have it's BIOS copied to C0000 in system RAM.
+ * card will have its BIOS copied to 0xC0000 in system RAM.
  * IORESOURCE_ROM_SHADOW is used to associate the boot video
  * card with this copy. On laptops this copy has to be used since
  * the main ROM may be compressed or combined with another image.
  * See pci_map_rom() for use of this flag. Before marking the device
  * with IORESOURCE_ROM_SHADOW check if a vga_default_device is already set
- * by either arch cde or vga-arbitration, if so only apply the fixup to this
- * already determined primary video card.
+ * by either arch code or vga-arbitration; if so only apply the fixup to this
+ * already-determined primary video card.
  */
 
 static void pci_fixup_video(struct pci_dev *pdev)
@@ -312,6 +312,7 @@ static void pci_fixup_video(struct pci_dev *pdev)
 	struct pci_dev *bridge;
 	struct pci_bus *bus;
 	u16 config;
+	struct resource *res;
 
 	/* Is VGA routed to us? */
 	bus = pdev->bus;
@@ -336,8 +337,18 @@ static void pci_fixup_video(struct pci_dev *pdev)
 	if (!vga_default_device() || pdev == vga_default_device()) {
 		pci_read_config_word(pdev, PCI_COMMAND, &config);
 		if (config & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) {
-			pdev->resource[PCI_ROM_RESOURCE].flags |= IORESOURCE_ROM_SHADOW;
-			dev_printk(KERN_DEBUG, &pdev->dev, "Video device with shadowed ROM\n");
+			res = &pdev->resource[PCI_ROM_RESOURCE];
+
+			pci_disable_rom(pdev);
+			if (res->parent)
+				release_resource(res);
+
+			res->start = 0xC0000;
+			res->end = res->start + 0x20000 - 1;
+			res->flags = IORESOURCE_MEM | IORESOURCE_ROM_SHADOW |
+				     IORESOURCE_PCI_FIXED;
+			dev_info(&pdev->dev, "Video device with shadowed ROM at %pR\n",
+				 res);
 		}
 	}
 }
@@ -540,3 +551,10 @@ static void twinhead_reserve_killing_zone(struct pci_dev *dev)
         }
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone);
+
+static void pci_bdwep_bar(struct pci_dev *dev)
+{
+	dev->non_compliant_bars = 1;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_bdwep_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_bdwep_bar);
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 0d24e7c10145..8b93e634af84 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -215,7 +215,7 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 	int polarity;
 	int ret;
 
-	if (pci_has_managed_irq(dev))
+	if (dev->irq_managed && dev->irq > 0)
 		return 0;
 
 	switch (intel_mid_identify_cpu()) {
@@ -256,13 +256,10 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 
 static void intel_mid_pci_irq_disable(struct pci_dev *dev)
 {
-	if (pci_has_managed_irq(dev)) {
+	if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed &&
+	    dev->irq > 0) {
 		mp_unmap_irq(dev->irq);
 		dev->irq_managed = 0;
-		/*
-		 * Don't reset dev->irq here, otherwise
-		 * intel_mid_pci_irq_enable() will fail on next call.
-		 */
 	}
 }
 
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 32e70343e6fd..9bd115484745 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -1202,7 +1202,7 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			struct pci_dev *temp_dev;
 			int irq;
 
-			if (pci_has_managed_irq(dev))
+			if (dev->irq_managed && dev->irq > 0)
 				return 0;
 
 			irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
@@ -1230,7 +1230,8 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			}
 			dev = temp_dev;
 			if (irq >= 0) {
-				pci_set_managed_irq(dev, irq);
+				dev->irq_managed = 1;
+				dev->irq = irq;
 				dev_info(&dev->dev, "PCI->APIC IRQ transform: "
 					 "INT %c -> IRQ %d\n", 'A' + pin - 1, irq);
 				return 0;
@@ -1256,10 +1257,24 @@ static int pirq_enable_irq(struct pci_dev *dev)
 	return 0;
 }
 
+bool mp_should_keep_irq(struct device *dev)
+{
+	if (dev->power.is_prepared)
+		return true;
+#ifdef CONFIG_PM
+	if (dev->power.runtime_status == RPM_SUSPENDING)
+		return true;
+#endif
+
+	return false;
+}
+
 static void pirq_disable_irq(struct pci_dev *dev)
 {
-	if (io_apic_assign_pci_irqs && pci_has_managed_irq(dev)) {
+	if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) &&
+	    dev->irq_managed && dev->irq) {
 		mp_unmap_irq(dev->irq);
-		pci_reset_managed_irq(dev);
+		dev->irq = 0;
+		dev->irq_managed = 0;
 	}
 }
diff --git a/arch/x86/pci/vmd.c b/arch/x86/pci/vmd.c
index d57e48016f15..7792aba266df 100644
--- a/arch/x86/pci/vmd.c
+++ b/arch/x86/pci/vmd.c
@@ -503,6 +503,18 @@ static struct pci_ops vmd_ops = {
 	.write		= vmd_pci_write,
 };
 
+static void vmd_attach_resources(struct vmd_dev *vmd)
+{
+	vmd->dev->resource[VMD_MEMBAR1].child = &vmd->resources[1];
+	vmd->dev->resource[VMD_MEMBAR2].child = &vmd->resources[2];
+}
+
+static void vmd_detach_resources(struct vmd_dev *vmd)
+{
+	vmd->dev->resource[VMD_MEMBAR1].child = NULL;
+	vmd->dev->resource[VMD_MEMBAR2].child = NULL;
+}
+
 /*
  * VMD domains start at 0x1000 to not clash with ACPI _SEG domains.
  */
@@ -527,11 +539,28 @@ static int vmd_enable_domain(struct vmd_dev *vmd)
 	res = &vmd->dev->resource[VMD_CFGBAR];
 	vmd->resources[0] = (struct resource) {
 		.name  = "VMD CFGBAR",
-		.start = res->start,
+		.start = 0,
 		.end   = (resource_size(res) >> 20) - 1,
 		.flags = IORESOURCE_BUS | IORESOURCE_PCI_FIXED,
 	};
 
+	/*
+	 * If the window is below 4GB, clear IORESOURCE_MEM_64 so we can
+	 * put 32-bit resources in the window.
+	 *
+	 * There's no hardware reason why a 64-bit window *couldn't*
+	 * contain a 32-bit resource, but pbus_size_mem() computes the
+	 * bridge window size assuming a 64-bit window will contain no
+	 * 32-bit resources.  __pci_assign_resource() enforces that
+	 * artificial restriction to make sure everything will fit.
+	 *
+	 * The only way we could use a 64-bit non-prefechable MEMBAR is
+	 * if its address is <4GB so that we can convert it to a 32-bit
+	 * resource.  To be visible to the host OS, all VMD endpoints must
+	 * be initially configured by platform BIOS, which includes setting
+	 * up these resources.  We can assume the device is configured
+	 * according to the platform needs.
+	 */
 	res = &vmd->dev->resource[VMD_MEMBAR1];
 	upper_bits = upper_32_bits(res->end);
 	flags = res->flags & ~IORESOURCE_SIZEALIGN;
@@ -542,6 +571,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd)
 		.start = res->start,
 		.end   = res->end,
 		.flags = flags,
+		.parent = res,
 	};
 
 	res = &vmd->dev->resource[VMD_MEMBAR2];
@@ -554,6 +584,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd)
 		.start = res->start + 0x2000,
 		.end   = res->end,
 		.flags = flags,
+		.parent = res,
 	};
 
 	sd->domain = vmd_find_free_domain();
@@ -578,6 +609,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd)
 		return -ENODEV;
 	}
 
+	vmd_attach_resources(vmd);
 	vmd_setup_dma_ops(vmd);
 	dev_set_msi_domain(&vmd->bus->dev, vmd->irq_domain);
 	pci_rescan_bus(vmd->bus);
@@ -674,6 +706,7 @@ static void vmd_remove(struct pci_dev *dev)
 {
 	struct vmd_dev *vmd = pci_get_drvdata(dev);
 
+	vmd_detach_resources(vmd);
 	pci_set_drvdata(dev, NULL);
 	sysfs_remove_link(&vmd->dev->dev.kobj, "domain");
 	pci_stop_root_bus(vmd->bus);
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index ff31ab464213..beac4dfdade6 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -196,7 +196,10 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	return 0;
 
 error:
-	dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n");
+	if (ret == -ENOSYS)
+		dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n");
+	else if (ret)
+		dev_err(&dev->dev, "Xen PCI frontend error: %d!\n", ret);
 free:
 	kfree(v);
 	return ret;
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 2d66db8f80f9..ed30e79347e8 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -131,6 +131,27 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
 EXPORT_SYMBOL_GPL(efi_query_variable_store);
 
 /*
+ * Helper function for efi_reserve_boot_services() to figure out if we
+ * can free regions in efi_free_boot_services().
+ *
+ * Use this function to ensure we do not free regions owned by somebody
+ * else. We must only reserve (and then free) regions:
+ *
+ * - Not within any part of the kernel
+ * - Not the BIOS reserved area (E820_RESERVED, E820_NVS, etc)
+ */
+static bool can_free_region(u64 start, u64 size)
+{
+	if (start + size > __pa_symbol(_text) && start <= __pa_symbol(_end))
+		return false;
+
+	if (!e820_all_mapped(start, start+size, E820_RAM))
+		return false;
+
+	return true;
+}
+
+/*
  * The UEFI specification makes it clear that the operating system is free to do
  * whatever it wants with boot services code after ExitBootServices() has been
  * called. Ignoring this recommendation a significant bunch of EFI implementations 
@@ -147,26 +168,50 @@ void __init efi_reserve_boot_services(void)
 		efi_memory_desc_t *md = p;
 		u64 start = md->phys_addr;
 		u64 size = md->num_pages << EFI_PAGE_SHIFT;
+		bool already_reserved;
 
 		if (md->type != EFI_BOOT_SERVICES_CODE &&
 		    md->type != EFI_BOOT_SERVICES_DATA)
 			continue;
-		/* Only reserve where possible:
-		 * - Not within any already allocated areas
-		 * - Not over any memory area (really needed, if above?)
-		 * - Not within any part of the kernel
-		 * - Not the bios reserved area
-		*/
-		if ((start + size > __pa_symbol(_text)
-				&& start <= __pa_symbol(_end)) ||
-			!e820_all_mapped(start, start+size, E820_RAM) ||
-			memblock_is_region_reserved(start, size)) {
-			/* Could not reserve, skip it */
-			md->num_pages = 0;
-			memblock_dbg("Could not reserve boot range [0x%010llx-0x%010llx]\n",
-				     start, start+size-1);
-		} else
+
+		already_reserved = memblock_is_region_reserved(start, size);
+
+		/*
+		 * Because the following memblock_reserve() is paired
+		 * with free_bootmem_late() for this region in
+		 * efi_free_boot_services(), we must be extremely
+		 * careful not to reserve, and subsequently free,
+		 * critical regions of memory (like the kernel image) or
+		 * those regions that somebody else has already
+		 * reserved.
+		 *
+		 * A good example of a critical region that must not be
+		 * freed is page zero (first 4Kb of memory), which may
+		 * contain boot services code/data but is marked
+		 * E820_RESERVED by trim_bios_range().
+		 */
+		if (!already_reserved) {
 			memblock_reserve(start, size);
+
+			/*
+			 * If we are the first to reserve the region, no
+			 * one else cares about it. We own it and can
+			 * free it later.
+			 */
+			if (can_free_region(start, size))
+				continue;
+		}
+
+		/*
+		 * We don't own the region. We must not free it.
+		 *
+		 * Setting this bit for a boot services region really
+		 * doesn't make sense as far as the firmware is
+		 * concerned, but it does provide us with a way to tag
+		 * those regions that must not be paired with
+		 * free_bootmem_late().
+		 */
+		md->attribute |= EFI_MEMORY_RUNTIME;
 	}
 }
 
@@ -183,8 +228,8 @@ void __init efi_free_boot_services(void)
 		    md->type != EFI_BOOT_SERVICES_DATA)
 			continue;
 
-		/* Could not reserve boot area */
-		if (!size)
+		/* Do not free, someone else owns it: */
+		if (md->attribute & EFI_MEMORY_RUNTIME)
 			continue;
 
 		free_bootmem_late(start, size);
diff --git a/arch/x86/platform/geode/alix.c b/arch/x86/platform/geode/alix.c
index 76b6632d3143..1865c196f136 100644
--- a/arch/x86/platform/geode/alix.c
+++ b/arch/x86/platform/geode/alix.c
@@ -21,7 +21,7 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/string.h>
-#include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <linux/leds.h>
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
@@ -35,6 +35,11 @@
 #define BIOS_SIGNATURE_COREBOOT		0x500
 #define BIOS_REGION_SIZE		0x10000
 
+/*
+ * This driver is not modular, but to keep back compatibility
+ * with existing use cases, continuing with module_param is
+ * the easiest way forward.
+ */
 static bool force = 0;
 module_param(force, bool, 0444);
 /* FIXME: Award bios is not automatically detected as Alix platform */
@@ -192,9 +197,4 @@ static int __init alix_init(void)
 
 	return 0;
 }
-
-module_init(alix_init);
-
-MODULE_AUTHOR("Ed Wildgoose <kernel@wildgooses.com>");
-MODULE_DESCRIPTION("PCEngines ALIX System Setup");
-MODULE_LICENSE("GPL");
+device_initcall(alix_init);
diff --git a/arch/x86/platform/geode/geos.c b/arch/x86/platform/geode/geos.c
index aa733fba2471..4fcdb91318a0 100644
--- a/arch/x86/platform/geode/geos.c
+++ b/arch/x86/platform/geode/geos.c
@@ -19,7 +19,6 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/string.h>
-#include <linux/module.h>
 #include <linux/leds.h>
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
@@ -120,9 +119,4 @@ static int __init geos_init(void)
 
 	return 0;
 }
-
-module_init(geos_init);
-
-MODULE_AUTHOR("Philip Prindeville <philipp@redfish-solutions.com>");
-MODULE_DESCRIPTION("Traverse Technologies Geos System Setup");
-MODULE_LICENSE("GPL");
+device_initcall(geos_init);
diff --git a/arch/x86/platform/geode/net5501.c b/arch/x86/platform/geode/net5501.c
index 927e38c0089f..a2f6b982a729 100644
--- a/arch/x86/platform/geode/net5501.c
+++ b/arch/x86/platform/geode/net5501.c
@@ -20,7 +20,6 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/string.h>
-#include <linux/module.h>
 #include <linux/leds.h>
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
@@ -146,9 +145,4 @@ static int __init net5501_init(void)
 
 	return 0;
 }
-
-module_init(net5501_init);
-
-MODULE_AUTHOR("Philip Prindeville <philipp@redfish-solutions.com>");
-MODULE_DESCRIPTION("Soekris net5501 System Setup");
-MODULE_LICENSE("GPL");
+device_initcall(net5501_init);
diff --git a/arch/x86/platform/intel-mid/mfld.c b/arch/x86/platform/intel-mid/mfld.c
index 23381d2174ae..1eb47b6298c2 100644
--- a/arch/x86/platform/intel-mid/mfld.c
+++ b/arch/x86/platform/intel-mid/mfld.c
@@ -52,10 +52,7 @@ static unsigned long __init mfld_calibrate_tsc(void)
 	/* mark tsc clocksource as reliable */
 	set_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC_RELIABLE);
 
-	if (fast_calibrate)
-		return fast_calibrate;
-
-	return 0;
+	return fast_calibrate;
 }
 
 static void __init penwell_arch_setup(void)
diff --git a/arch/x86/platform/intel-mid/mrfl.c b/arch/x86/platform/intel-mid/mrfl.c
index aaca91753d32..bd1adc621781 100644
--- a/arch/x86/platform/intel-mid/mrfl.c
+++ b/arch/x86/platform/intel-mid/mrfl.c
@@ -81,10 +81,7 @@ static unsigned long __init tangier_calibrate_tsc(void)
 	/* mark tsc clocksource as reliable */
 	set_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC_RELIABLE);
 
-	if (fast_calibrate)
-		return fast_calibrate;
-
-	return 0;
+	return fast_calibrate;
 }
 
 static void __init tangier_arch_setup(void)
diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c
index c61b6c332e97..17d6d2296e4d 100644
--- a/arch/x86/platform/intel-quark/imr.c
+++ b/arch/x86/platform/intel-quark/imr.c
@@ -1,5 +1,5 @@
 /**
- * imr.c
+ * imr.c -- Intel Isolated Memory Region driver
  *
  * Copyright(c) 2013 Intel Corporation.
  * Copyright(c) 2015 Bryan O'Donoghue <pure.logic@nexus-software.ie>
@@ -31,7 +31,6 @@
 #include <linux/debugfs.h>
 #include <linux/init.h>
 #include <linux/mm.h>
-#include <linux/module.h>
 #include <linux/types.h>
 
 struct imr_device {
@@ -135,11 +134,9 @@ static int imr_read(struct imr_device *idev, u32 imr_id, struct imr_regs *imr)
  * @idev:	pointer to imr_device structure.
  * @imr_id:	IMR entry to write.
  * @imr:	IMR structure representing address and access masks.
- * @lock:	indicates if the IMR lock bit should be applied.
  * @return:	0 on success or error code passed from mbi_iosf on failure.
  */
-static int imr_write(struct imr_device *idev, u32 imr_id,
-		     struct imr_regs *imr, bool lock)
+static int imr_write(struct imr_device *idev, u32 imr_id, struct imr_regs *imr)
 {
 	unsigned long flags;
 	u32 reg = imr_id * IMR_NUM_REGS + idev->reg_base;
@@ -163,15 +160,6 @@ static int imr_write(struct imr_device *idev, u32 imr_id,
 	if (ret)
 		goto failed;
 
-	/* Lock bit must be set separately to addr_lo address bits. */
-	if (lock) {
-		imr->addr_lo |= IMR_LOCK;
-		ret = iosf_mbi_write(QRK_MBI_UNIT_MM, MBI_REG_WRITE,
-				     reg - IMR_NUM_REGS, imr->addr_lo);
-		if (ret)
-			goto failed;
-	}
-
 	local_irq_restore(flags);
 	return 0;
 failed:
@@ -270,17 +258,6 @@ static int imr_debugfs_register(struct imr_device *idev)
 }
 
 /**
- * imr_debugfs_unregister - unregister debugfs hooks.
- *
- * @idev:	pointer to imr_device structure.
- * @return:
- */
-static void imr_debugfs_unregister(struct imr_device *idev)
-{
-	debugfs_remove(idev->file);
-}
-
-/**
  * imr_check_params - check passed address range IMR alignment and non-zero size
  *
  * @base:	base address of intended IMR.
@@ -334,11 +311,10 @@ static inline int imr_address_overlap(phys_addr_t addr, struct imr_regs *imr)
  * @size:	physical size of region in bytes must be aligned to 1KiB.
  * @read_mask:	read access mask.
  * @write_mask:	write access mask.
- * @lock:	indicates whether or not to permanently lock this region.
  * @return:	zero on success or negative value indicating error.
  */
 int imr_add_range(phys_addr_t base, size_t size,
-		  unsigned int rmask, unsigned int wmask, bool lock)
+		  unsigned int rmask, unsigned int wmask)
 {
 	phys_addr_t end;
 	unsigned int i;
@@ -411,7 +387,7 @@ int imr_add_range(phys_addr_t base, size_t size,
 	imr.rmask = rmask;
 	imr.wmask = wmask;
 
-	ret = imr_write(idev, reg, &imr, lock);
+	ret = imr_write(idev, reg, &imr);
 	if (ret < 0) {
 		/*
 		 * In the highly unlikely event iosf_mbi_write failed
@@ -422,7 +398,7 @@ int imr_add_range(phys_addr_t base, size_t size,
 		imr.addr_hi = 0;
 		imr.rmask = IMR_READ_ACCESS_ALL;
 		imr.wmask = IMR_WRITE_ACCESS_ALL;
-		imr_write(idev, reg, &imr, false);
+		imr_write(idev, reg, &imr);
 	}
 failed:
 	mutex_unlock(&idev->lock);
@@ -518,7 +494,7 @@ static int __imr_remove_range(int reg, phys_addr_t base, size_t size)
 	imr.rmask = IMR_READ_ACCESS_ALL;
 	imr.wmask = IMR_WRITE_ACCESS_ALL;
 
-	ret = imr_write(idev, reg, &imr, false);
+	ret = imr_write(idev, reg, &imr);
 
 failed:
 	mutex_unlock(&idev->lock);
@@ -592,14 +568,14 @@ static void __init imr_fixup_memmap(struct imr_device *idev)
 	end = (unsigned long)__end_rodata - 1;
 
 	/*
-	 * Setup a locked IMR around the physical extent of the kernel
+	 * Setup an unlocked IMR around the physical extent of the kernel
 	 * from the beginning of the .text secton to the end of the
 	 * .rodata section as one physically contiguous block.
 	 *
 	 * We don't round up @size since it is already PAGE_SIZE aligned.
 	 * See vmlinux.lds.S for details.
 	 */
-	ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, true);
+	ret = imr_add_range(base, size, IMR_CPU, IMR_CPU);
 	if (ret < 0) {
 		pr_err("unable to setup IMR for kernel: %zu KiB (%lx - %lx)\n",
 			size / 1024, start, end);
@@ -614,7 +590,6 @@ static const struct x86_cpu_id imr_ids[] __initconst = {
 	{ X86_VENDOR_INTEL, 5, 9 },	/* Intel Quark SoC X1000. */
 	{}
 };
-MODULE_DEVICE_TABLE(x86cpu, imr_ids);
 
 /**
  * imr_init - entry point for IMR driver.
@@ -640,22 +615,4 @@ static int __init imr_init(void)
 	imr_fixup_memmap(idev);
 	return 0;
 }
-
-/**
- * imr_exit - exit point for IMR code.
- *
- * Deregisters debugfs, leave IMR state as-is.
- *
- * return:
- */
-static void __exit imr_exit(void)
-{
-	imr_debugfs_unregister(&imr_dev);
-}
-
-module_init(imr_init);
-module_exit(imr_exit);
-
-MODULE_AUTHOR("Bryan O'Donoghue <pure.logic@nexus-software.ie>");
-MODULE_DESCRIPTION("Intel Isolated Memory Region driver");
-MODULE_LICENSE("Dual BSD/GPL");
+device_initcall(imr_init);
diff --git a/arch/x86/platform/intel-quark/imr_selftest.c b/arch/x86/platform/intel-quark/imr_selftest.c
index 278e4da4222f..f5bad40936ac 100644
--- a/arch/x86/platform/intel-quark/imr_selftest.c
+++ b/arch/x86/platform/intel-quark/imr_selftest.c
@@ -1,5 +1,5 @@
 /**
- * imr_selftest.c
+ * imr_selftest.c -- Intel Isolated Memory Region self-test driver
  *
  * Copyright(c) 2013 Intel Corporation.
  * Copyright(c) 2015 Bryan O'Donoghue <pure.logic@nexus-software.ie>
@@ -15,7 +15,6 @@
 #include <asm/imr.h>
 #include <linux/init.h>
 #include <linux/mm.h>
-#include <linux/module.h>
 #include <linux/types.h>
 
 #define SELFTEST KBUILD_MODNAME ": "
@@ -61,30 +60,30 @@ static void __init imr_self_test(void)
 	int ret;
 
 	/* Test zero zero. */
-	ret = imr_add_range(0, 0, 0, 0, false);
+	ret = imr_add_range(0, 0, 0, 0);
 	imr_self_test_result(ret < 0, "zero sized IMR\n");
 
 	/* Test exact overlap. */
-	ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, false);
+	ret = imr_add_range(base, size, IMR_CPU, IMR_CPU);
 	imr_self_test_result(ret < 0, fmt_over, __va(base), __va(base + size));
 
 	/* Test overlap with base inside of existing. */
 	base += size - IMR_ALIGN;
-	ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, false);
+	ret = imr_add_range(base, size, IMR_CPU, IMR_CPU);
 	imr_self_test_result(ret < 0, fmt_over, __va(base), __va(base + size));
 
 	/* Test overlap with end inside of existing. */
 	base -= size + IMR_ALIGN * 2;
-	ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, false);
+	ret = imr_add_range(base, size, IMR_CPU, IMR_CPU);
 	imr_self_test_result(ret < 0, fmt_over, __va(base), __va(base + size));
 
 	/* Test that a 1 KiB IMR @ zero with read/write all will bomb out. */
 	ret = imr_add_range(0, IMR_ALIGN, IMR_READ_ACCESS_ALL,
-			    IMR_WRITE_ACCESS_ALL, false);
+			    IMR_WRITE_ACCESS_ALL);
 	imr_self_test_result(ret < 0, "1KiB IMR @ 0x00000000 - access-all\n");
 
 	/* Test that a 1 KiB IMR @ zero with CPU only will work. */
-	ret = imr_add_range(0, IMR_ALIGN, IMR_CPU, IMR_CPU, false);
+	ret = imr_add_range(0, IMR_ALIGN, IMR_CPU, IMR_CPU);
 	imr_self_test_result(ret >= 0, "1KiB IMR @ 0x00000000 - cpu-access\n");
 	if (ret >= 0) {
 		ret = imr_remove_range(0, IMR_ALIGN);
@@ -93,8 +92,7 @@ static void __init imr_self_test(void)
 
 	/* Test 2 KiB works. */
 	size = IMR_ALIGN * 2;
-	ret = imr_add_range(0, size, IMR_READ_ACCESS_ALL,
-			    IMR_WRITE_ACCESS_ALL, false);
+	ret = imr_add_range(0, size, IMR_READ_ACCESS_ALL, IMR_WRITE_ACCESS_ALL);
 	imr_self_test_result(ret >= 0, "2KiB IMR @ 0x00000000\n");
 	if (ret >= 0) {
 		ret = imr_remove_range(0, size);
@@ -106,7 +104,6 @@ static const struct x86_cpu_id imr_ids[] __initconst = {
 	{ X86_VENDOR_INTEL, 5, 9 },	/* Intel Quark SoC X1000. */
 	{}
 };
-MODULE_DEVICE_TABLE(x86cpu, imr_ids);
 
 /**
  * imr_self_test_init - entry point for IMR driver.
@@ -125,13 +122,4 @@ static int __init imr_self_test_init(void)
  *
  * return:
  */
-static void __exit imr_self_test_exit(void)
-{
-}
-
-module_init(imr_self_test_init);
-module_exit(imr_self_test_exit);
-
-MODULE_AUTHOR("Bryan O'Donoghue <pure.logic@nexus-software.ie>");
-MODULE_DESCRIPTION("Intel Isolated Memory Region self-test driver");
-MODULE_LICENSE("Dual BSD/GPL");
+device_initcall(imr_self_test_init);
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index 174781a404ff..00c319048d52 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -3,7 +3,7 @@
 
 #include <asm/asm.h>
 #include <asm/segment.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/cmpxchg.h>
 #include <asm/nops.h>
 
diff --git a/arch/x86/um/os-Linux/task_size.c b/arch/x86/um/os-Linux/task_size.c
index 8502ad30e61b..5adb6a2fd117 100644
--- a/arch/x86/um/os-Linux/task_size.c
+++ b/arch/x86/um/os-Linux/task_size.c
@@ -109,7 +109,7 @@ unsigned long os_get_top_address(void)
 		exit(1);
 	}
 
-	printf("0x%x\n", bottom << UM_KERN_PAGE_SHIFT);
+	printf("0x%lx\n", bottom << UM_KERN_PAGE_SHIFT);
 	printf("Locating the top of the address space ... ");
 	fflush(stdout);
 
@@ -134,7 +134,7 @@ out:
 		exit(1);
 	}
 	top <<= UM_KERN_PAGE_SHIFT;
-	printf("0x%x\n", top);
+	printf("0x%lx\n", top);
 
 	return top;
 }
diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c
index 439c0994b696..bfce503dffae 100644
--- a/arch/x86/um/sys_call_table_32.c
+++ b/arch/x86/um/sys_call_table_32.c
@@ -25,11 +25,11 @@
 
 #define old_mmap sys_old_mmap
 
-#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
+#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
 #include <asm/syscalls_32.h>
 
 #undef __SYSCALL_I386
-#define __SYSCALL_I386(nr, sym, compat) [ nr ] = sym,
+#define __SYSCALL_I386(nr, sym, qual) [ nr ] = sym,
 
 extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 
diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c
index b74ea6c2c0e7..f306413d3eb6 100644
--- a/arch/x86/um/sys_call_table_64.c
+++ b/arch/x86/um/sys_call_table_64.c
@@ -35,14 +35,11 @@
 #define stub_execveat sys_execveat
 #define stub_rt_sigreturn sys_rt_sigreturn
 
-#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
-#define __SYSCALL_X32(nr, sym, compat) /* Not supported */
-
-#define __SYSCALL_64(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
+#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
 #include <asm/syscalls_64.h>
 
 #undef __SYSCALL_64
-#define __SYSCALL_64(nr, sym, compat) [ nr ] = sym,
+#define __SYSCALL_64(nr, sym, qual) [ nr ] = sym,
 
 extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 
diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c
index ce7e3607a870..470564bbd08e 100644
--- a/arch/x86/um/user-offsets.c
+++ b/arch/x86/um/user-offsets.c
@@ -9,14 +9,12 @@
 #include <asm/types.h>
 
 #ifdef __i386__
-#define __SYSCALL_I386(nr, sym, compat) [nr] = 1,
+#define __SYSCALL_I386(nr, sym, qual) [nr] = 1,
 static char syscalls[] = {
 #include <asm/syscalls_32.h>
 };
 #else
-#define __SYSCALL_64(nr, sym, compat) [nr] = 1,
-#define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1,
-#define __SYSCALL_X32(nr, sym, compat) /* Not supported */
+#define __SYSCALL_64(nr, sym, qual) [nr] = 1,
 static char syscalls[] = {
 #include <asm/syscalls_64.h>
 };
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index d09e4c9d7cc5..2c261082eadf 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1654,7 +1654,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	cpu_detect(&new_cpu_data);
 	set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU);
 	new_cpu_data.wp_works_ok = 1;
-	new_cpu_data.x86_capability[0] = cpuid_edx(1);
+	new_cpu_data.x86_capability[CPUID_1_EDX] = cpuid_edx(1);
 #endif
 
 	if (xen_start_info->mod_start) {
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
index 724a08740a04..9466354d3e49 100644
--- a/arch/x86/xen/pmu.c
+++ b/arch/x86/xen/pmu.c
@@ -11,7 +11,7 @@
 #include "pmu.h"
 
 /* x86_pmu.handle_irq definition */
-#include "../kernel/cpu/perf_event.h"
+#include "../events/perf_event.h"
 
 #define XENPMU_IRQ_PROCESSING    1
 struct xenpmu {
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 3f4ebf0261f2..3c6d17fd423a 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -112,7 +112,7 @@ asmlinkage __visible void cpu_bringup_and_idle(int cpu)
 		xen_pvh_secondary_vcpu_init(cpu);
 #endif
 	cpu_bringup();
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
 static void xen_smp_intr_free(unsigned int cpu)
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index e9df1567d778..7e9464b0fc00 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -413,8 +413,6 @@ config FORCE_MAX_ZONEORDER
 
 source "drivers/pcmcia/Kconfig"
 
-source "drivers/pci/hotplug/Kconfig"
-
 config PLATFORM_WANT_DEFAULT_MEM
 	def_bool n
 
diff --git a/arch/xtensa/include/asm/pci.h b/arch/xtensa/include/asm/pci.h
index e438a00fbd63..5d6bd932ba4e 100644
--- a/arch/xtensa/include/asm/pci.h
+++ b/arch/xtensa/include/asm/pci.h
@@ -55,9 +55,6 @@ int pci_mmap_page_range(struct pci_dev *pdev, struct vm_area_struct *vma,
 
 #endif /* __KERNEL__ */
 
-/* Implement the pci_ DMA API in terms of the generic device dma_ one */
-#include <asm-generic/pci-dma-compat.h>
-
 /* Generic PCI */
 #include <asm-generic/pci.h>
 
diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c
index 4d02e38514f5..fc4ad21a5ed4 100644
--- a/arch/xtensa/kernel/smp.c
+++ b/arch/xtensa/kernel/smp.c
@@ -157,7 +157,7 @@ void secondary_start_kernel(void)
 
 	complete(&cpu_running);
 
-	cpu_startup_entry(CPUHP_ONLINE);
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
 static void mx_cpu_start(void *p)
diff --git a/block/Kconfig b/block/Kconfig
index 161491d0a879..0363cd731320 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -88,6 +88,19 @@ config BLK_DEV_INTEGRITY
 	T10/SCSI Data Integrity Field or the T13/ATA External Path
 	Protection.  If in doubt, say N.
 
+config BLK_DEV_DAX
+	bool "Block device DAX support"
+	depends on FS_DAX
+	depends on BROKEN
+	help
+	  When DAX support is available (CONFIG_FS_DAX) raw block
+	  devices can also support direct userspace access to the
+	  storage capacity via MMAP(2) similar to a file on a
+	  DAX-enabled filesystem.  However, the DAX I/O-path disables
+	  some standard I/O-statistics, and the MMAP(2) path has some
+	  operational differences due to bypassing the page
+	  cache.  If in doubt, say N.
+
 config BLK_DEV_THROTTLING
 	bool "Block layer bio throttling support"
 	depends on BLK_CGROUP=y
diff --git a/block/bio.c b/block/bio.c
index dbabd48b1934..cf7591551b17 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -874,7 +874,7 @@ int submit_bio_wait(int rw, struct bio *bio)
 	bio->bi_private = &ret;
 	bio->bi_end_io = submit_bio_wait_endio;
 	submit_bio(rw, bio);
-	wait_for_completion(&ret.event);
+	wait_for_completion_io(&ret.event);
 
 	return ret.error;
 }
@@ -1090,9 +1090,12 @@ int bio_uncopy_user(struct bio *bio)
 	if (!bio_flagged(bio, BIO_NULL_MAPPED)) {
 		/*
 		 * if we're in a workqueue, the request is orphaned, so
-		 * don't copy into a random user address space, just free.
+		 * don't copy into a random user address space, just free
+		 * and return -EINTR so user space doesn't expect any data.
 		 */
-		if (current->mm && bio_data_dir(bio) == READ)
+		if (!current->mm)
+			ret = -EINTR;
+		else if (bio_data_dir(bio) == READ)
 			ret = bio_copy_to_iter(bio, bmd->iter);
 		if (bmd->is_our_pages)
 			bio_free_pages(bio);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 5a37188b559f..66e6f1aae02e 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -788,6 +788,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 {
 	struct gendisk *disk;
 	struct blkcg_gq *blkg;
+	struct module *owner;
 	unsigned int major, minor;
 	int key_len, part, ret;
 	char *body;
@@ -804,7 +805,9 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	if (!disk)
 		return -ENODEV;
 	if (part) {
+		owner = disk->fops->owner;
 		put_disk(disk);
+		module_put(owner);
 		return -ENODEV;
 	}
 
@@ -820,7 +823,9 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		ret = PTR_ERR(blkg);
 		rcu_read_unlock();
 		spin_unlock_irq(disk->queue->queue_lock);
+		owner = disk->fops->owner;
 		put_disk(disk);
+		module_put(owner);
 		/*
 		 * If queue was bypassing, we should retry.  Do so after a
 		 * short msleep().  It isn't strictly necessary but queue
@@ -851,9 +856,13 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep);
 void blkg_conf_finish(struct blkg_conf_ctx *ctx)
 	__releases(ctx->disk->queue->queue_lock) __releases(rcu)
 {
+	struct module *owner;
+
 	spin_unlock_irq(ctx->disk->queue->queue_lock);
 	rcu_read_unlock();
+	owner = ctx->disk->fops->owner;
 	put_disk(ctx->disk);
+	module_put(owner);
 }
 EXPORT_SYMBOL_GPL(blkg_conf_finish);
 
diff --git a/block/blk-core.c b/block/blk-core.c
index ab51685988c2..45f4d7efbf34 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2198,7 +2198,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	if (q->mq_ops) {
 		if (blk_queue_io_stat(q))
 			blk_account_io_start(rq, true);
-		blk_mq_insert_request(rq, false, true, true);
+		blk_mq_insert_request(rq, false, true, false);
 		return 0;
 	}
 
@@ -2455,14 +2455,16 @@ struct request *blk_peek_request(struct request_queue *q)
 
 			rq = NULL;
 			break;
-		} else if (ret == BLKPREP_KILL) {
+		} else if (ret == BLKPREP_KILL || ret == BLKPREP_INVALID) {
+			int err = (ret == BLKPREP_INVALID) ? -EREMOTEIO : -EIO;
+
 			rq->cmd_flags |= REQ_QUIET;
 			/*
 			 * Mark this request as started so we don't trigger
 			 * any debug logic in the end I/O path.
 			 */
 			blk_start_request(rq);
-			__blk_end_request_all(rq, -EIO);
+			__blk_end_request_all(rq, err);
 		} else {
 			printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
 			break;
diff --git a/block/blk-map.c b/block/blk-map.c
index f565e11f465a..a54f0543b956 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -57,6 +57,49 @@ static int __blk_rq_unmap_user(struct bio *bio)
 	return ret;
 }
 
+static int __blk_rq_map_user_iov(struct request *rq,
+		struct rq_map_data *map_data, struct iov_iter *iter,
+		gfp_t gfp_mask, bool copy)
+{
+	struct request_queue *q = rq->q;
+	struct bio *bio, *orig_bio;
+	int ret;
+
+	if (copy)
+		bio = bio_copy_user_iov(q, map_data, iter, gfp_mask);
+	else
+		bio = bio_map_user_iov(q, iter, gfp_mask);
+
+	if (IS_ERR(bio))
+		return PTR_ERR(bio);
+
+	if (map_data && map_data->null_mapped)
+		bio_set_flag(bio, BIO_NULL_MAPPED);
+
+	iov_iter_advance(iter, bio->bi_iter.bi_size);
+	if (map_data)
+		map_data->offset += bio->bi_iter.bi_size;
+
+	orig_bio = bio;
+	blk_queue_bounce(q, &bio);
+
+	/*
+	 * We link the bounce buffer in and could have to traverse it
+	 * later so we have to get a ref to prevent it from being freed
+	 */
+	bio_get(bio);
+
+	ret = blk_rq_append_bio(q, rq, bio);
+	if (ret) {
+		bio_endio(bio);
+		__blk_rq_unmap_user(orig_bio);
+		bio_put(bio);
+		return ret;
+	}
+
+	return 0;
+}
+
 /**
  * blk_rq_map_user_iov - map user data to a request, for REQ_TYPE_BLOCK_PC usage
  * @q:		request queue where request should be inserted
@@ -82,10 +125,11 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 			struct rq_map_data *map_data,
 			const struct iov_iter *iter, gfp_t gfp_mask)
 {
-	struct bio *bio;
-	int unaligned = 0;
-	struct iov_iter i;
 	struct iovec iov, prv = {.iov_base = NULL, .iov_len = 0};
+	bool copy = (q->dma_pad_mask & iter->count) || map_data;
+	struct bio *bio = NULL;
+	struct iov_iter i;
+	int ret;
 
 	if (!iter || !iter->count)
 		return -EINVAL;
@@ -101,42 +145,29 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 		 */
 		if ((uaddr & queue_dma_alignment(q)) ||
 		    iovec_gap_to_prv(q, &prv, &iov))
-			unaligned = 1;
+			copy = true;
 
 		prv.iov_base = iov.iov_base;
 		prv.iov_len = iov.iov_len;
 	}
 
-	if (unaligned || (q->dma_pad_mask & iter->count) || map_data)
-		bio = bio_copy_user_iov(q, map_data, iter, gfp_mask);
-	else
-		bio = bio_map_user_iov(q, iter, gfp_mask);
-
-	if (IS_ERR(bio))
-		return PTR_ERR(bio);
-
-	if (map_data && map_data->null_mapped)
-		bio_set_flag(bio, BIO_NULL_MAPPED);
-
-	if (bio->bi_iter.bi_size != iter->count) {
-		/*
-		 * Grab an extra reference to this bio, as bio_unmap_user()
-		 * expects to be able to drop it twice as it happens on the
-		 * normal IO completion path
-		 */
-		bio_get(bio);
-		bio_endio(bio);
-		__blk_rq_unmap_user(bio);
-		return -EINVAL;
-	}
+	i = *iter;
+	do {
+		ret =__blk_rq_map_user_iov(rq, map_data, &i, gfp_mask, copy);
+		if (ret)
+			goto unmap_rq;
+		if (!bio)
+			bio = rq->bio;
+	} while (iov_iter_count(&i));
 
 	if (!bio_flagged(bio, BIO_USER_MAPPED))
 		rq->cmd_flags |= REQ_COPY_USER;
-
-	blk_queue_bounce(q, &bio);
-	bio_get(bio);
-	blk_rq_bio_prep(q, rq, bio);
 	return 0;
+
+unmap_rq:
+	__blk_rq_unmap_user(bio);
+	rq->bio = NULL;
+	return -EINVAL;
 }
 EXPORT_SYMBOL(blk_rq_map_user_iov);
 
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 888a7fec81f7..261353166dcf 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -304,7 +304,6 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 				   struct bio *nxt)
 {
 	struct bio_vec end_bv = { NULL }, nxt_bv;
-	struct bvec_iter iter;
 
 	if (!blk_queue_cluster(q))
 		return 0;
@@ -316,11 +315,8 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 	if (!bio_has_data(bio))
 		return 1;
 
-	bio_for_each_segment(end_bv, bio, iter)
-		if (end_bv.bv_len == iter.bi_size)
-			break;
-
-	nxt_bv = bio_iovec(nxt);
+	bio_get_last_bvec(bio, &end_bv);
+	bio_get_first_bvec(nxt, &nxt_bv);
 
 	if (!BIOVEC_PHYS_MERGEABLE(&end_bv, &nxt_bv))
 		return 0;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4c0622fae413..56c0a726b619 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -599,8 +599,10 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 		 * If a request wasn't started before the queue was
 		 * marked dying, kill it here or it'll go unnoticed.
 		 */
-		if (unlikely(blk_queue_dying(rq->q)))
-			blk_mq_complete_request(rq, -EIO);
+		if (unlikely(blk_queue_dying(rq->q))) {
+			rq->errors = -EIO;
+			blk_mq_end_request(rq, rq->errors);
+		}
 		return;
 	}
 
diff --git a/block/blk-settings.c b/block/blk-settings.c
index dd4973583978..c7bb666aafd1 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -91,8 +91,8 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 	lim->virt_boundary_mask = 0;
 	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
-	lim->max_sectors = lim->max_dev_sectors = lim->max_hw_sectors =
-		BLK_SAFE_MAX_SECTORS;
+	lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
+	lim->max_dev_sectors = 0;
 	lim->chunk_sectors = 0;
 	lim->max_write_same_sectors = 0;
 	lim->max_discard_sectors = 0;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index e140cc487ce1..dd93763057ce 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -147,10 +147,9 @@ static ssize_t queue_discard_granularity_show(struct request_queue *q, char *pag
 
 static ssize_t queue_discard_max_hw_show(struct request_queue *q, char *page)
 {
-	unsigned long long val;
 
-	val = q->limits.max_hw_discard_sectors << 9;
-	return sprintf(page, "%llu\n", val);
+	return sprintf(page, "%llu\n",
+		(unsigned long long)q->limits.max_hw_discard_sectors << 9);
 }
 
 static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index a753df2b3fc2..d0dd7882d8c7 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -39,7 +39,6 @@ struct deadline_data {
 	 */
 	struct request *next_rq[2];
 	unsigned int batching;		/* number of sequential requests made */
-	sector_t last_sector;		/* head position */
 	unsigned int starved;		/* times reads have starved writes */
 
 	/*
@@ -210,8 +209,6 @@ deadline_move_request(struct deadline_data *dd, struct request *rq)
 	dd->next_rq[WRITE] = NULL;
 	dd->next_rq[data_dir] = deadline_latter_request(rq);
 
-	dd->last_sector = rq_end_sector(rq);
-
 	/*
 	 * take it off the sort and fifo list, move
 	 * to dispatch queue
diff --git a/block/partition-generic.c b/block/partition-generic.c
index fefd01b496a0..5d8701941054 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -217,10 +217,21 @@ static void part_release(struct device *dev)
 	kfree(p);
 }
 
+static int part_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	struct hd_struct *part = dev_to_part(dev);
+
+	add_uevent_var(env, "PARTN=%u", part->partno);
+	if (part->info && part->info->volname[0])
+		add_uevent_var(env, "PARTNAME=%s", part->info->volname);
+	return 0;
+}
+
 struct device_type part_type = {
 	.name		= "partition",
 	.groups		= part_attr_groups,
 	.release	= part_release,
+	.uevent		= part_uevent,
 };
 
 static void delete_partition_rcu_cb(struct rcu_head *head)
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 3be07ad1d80d..93a1fdc1feee 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -84,15 +84,6 @@ config CRYPTO_RNG_DEFAULT
 	tristate
 	select CRYPTO_DRBG_MENU
 
-config CRYPTO_PCOMP
-	tristate
-	select CRYPTO_PCOMP2
-	select CRYPTO_ALGAPI
-
-config CRYPTO_PCOMP2
-	tristate
-	select CRYPTO_ALGAPI2
-
 config CRYPTO_AKCIPHER2
 	tristate
 	select CRYPTO_ALGAPI2
@@ -122,7 +113,6 @@ config CRYPTO_MANAGER2
 	select CRYPTO_AEAD2
 	select CRYPTO_HASH2
 	select CRYPTO_BLKCIPHER2
-	select CRYPTO_PCOMP2
 	select CRYPTO_AKCIPHER2
 
 config CRYPTO_USER
@@ -227,6 +217,9 @@ config CRYPTO_GLUE_HELPER_X86
 	depends on X86
 	select CRYPTO_ALGAPI
 
+config CRYPTO_ENGINE
+	tristate
+
 comment "Authenticated Encryption with Associated Data"
 
 config CRYPTO_CCM
@@ -1506,15 +1499,6 @@ config CRYPTO_DEFLATE
 
 	  You will most probably want this if using IPSec.
 
-config CRYPTO_ZLIB
-	tristate "Zlib compression algorithm"
-	select CRYPTO_PCOMP
-	select ZLIB_INFLATE
-	select ZLIB_DEFLATE
-	select NLATTR
-	help
-	  This is the zlib algorithm.
-
 config CRYPTO_LZO
 	tristate "LZO compression algorithm"
 	select CRYPTO_ALGAPI
@@ -1595,6 +1579,7 @@ endif	# if CRYPTO_DRBG_MENU
 
 config CRYPTO_JITTERENTROPY
 	tristate "Jitterentropy Non-Deterministic Random Number Generator"
+	select CRYPTO_RNG
 	help
 	  The Jitterentropy RNG is a noise that is intended
 	  to provide seed to another RNG. The RNG does not
diff --git a/crypto/Makefile b/crypto/Makefile
index 2acdbbd30475..4f4ef7eaae3f 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -7,6 +7,7 @@ crypto-y := api.o cipher.o compress.o memneq.o
 
 obj-$(CONFIG_CRYPTO_WORKQUEUE) += crypto_wq.o
 
+obj-$(CONFIG_CRYPTO_ENGINE) += crypto_engine.o
 obj-$(CONFIG_CRYPTO_FIPS) += fips.o
 
 crypto_algapi-$(CONFIG_PROC_FS) += proc.o
@@ -28,7 +29,6 @@ crypto_hash-y += ahash.o
 crypto_hash-y += shash.o
 obj-$(CONFIG_CRYPTO_HASH2) += crypto_hash.o
 
-obj-$(CONFIG_CRYPTO_PCOMP2) += pcompress.o
 obj-$(CONFIG_CRYPTO_AKCIPHER2) += akcipher.o
 
 $(obj)/rsapubkey-asn1.o: $(obj)/rsapubkey-asn1.c $(obj)/rsapubkey-asn1.h
@@ -99,10 +99,9 @@ obj-$(CONFIG_CRYPTO_SALSA20) += salsa20_generic.o
 obj-$(CONFIG_CRYPTO_CHACHA20) += chacha20_generic.o
 obj-$(CONFIG_CRYPTO_POLY1305) += poly1305_generic.o
 obj-$(CONFIG_CRYPTO_DEFLATE) += deflate.o
-obj-$(CONFIG_CRYPTO_ZLIB) += zlib.o
 obj-$(CONFIG_CRYPTO_MICHAEL_MIC) += michael_mic.o
 obj-$(CONFIG_CRYPTO_CRC32C) += crc32c_generic.o
-obj-$(CONFIG_CRYPTO_CRC32) += crc32.o
+obj-$(CONFIG_CRYPTO_CRC32) += crc32_generic.o
 obj-$(CONFIG_CRYPTO_CRCT10DIF) += crct10dif_common.o crct10dif_generic.o
 obj-$(CONFIG_CRYPTO_AUTHENC) += authenc.o authencesn.o
 obj-$(CONFIG_CRYPTO_LZO) += lzo.o
diff --git a/crypto/ahash.c b/crypto/ahash.c
index d19b52324cf5..5fc1f172963d 100644
--- a/crypto/ahash.c
+++ b/crypto/ahash.c
@@ -166,24 +166,6 @@ int crypto_ahash_walk_first(struct ahash_request *req,
 }
 EXPORT_SYMBOL_GPL(crypto_ahash_walk_first);
 
-int crypto_hash_walk_first_compat(struct hash_desc *hdesc,
-				  struct crypto_hash_walk *walk,
-				  struct scatterlist *sg, unsigned int len)
-{
-	walk->total = len;
-
-	if (!walk->total) {
-		walk->entrylen = 0;
-		return 0;
-	}
-
-	walk->alignmask = crypto_hash_alignmask(hdesc->tfm);
-	walk->sg = sg;
-	walk->flags = hdesc->flags & CRYPTO_TFM_REQ_MASK;
-
-	return hash_walk_new_entry(walk);
-}
-
 static int ahash_setkey_unaligned(struct crypto_ahash *tfm, const u8 *key,
 				unsigned int keylen)
 {
@@ -542,6 +524,12 @@ struct crypto_ahash *crypto_alloc_ahash(const char *alg_name, u32 type,
 }
 EXPORT_SYMBOL_GPL(crypto_alloc_ahash);
 
+int crypto_has_ahash(const char *alg_name, u32 type, u32 mask)
+{
+	return crypto_type_has_alg(alg_name, &crypto_ahash_type, type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_has_ahash);
+
 static int ahash_prepare_alg(struct ahash_alg *alg)
 {
 	struct crypto_alg *base = &alg->halg.base;
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 7be76aa31579..731255a6104f 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -987,6 +987,21 @@ unsigned int crypto_alg_extsize(struct crypto_alg *alg)
 }
 EXPORT_SYMBOL_GPL(crypto_alg_extsize);
 
+int crypto_type_has_alg(const char *name, const struct crypto_type *frontend,
+			u32 type, u32 mask)
+{
+	int ret = 0;
+	struct crypto_alg *alg = crypto_find_alg(name, frontend, type, mask);
+
+	if (!IS_ERR(alg)) {
+		crypto_mod_put(alg);
+		ret = 1;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(crypto_type_has_alg);
+
 static int __init crypto_algapi_init(void)
 {
 	crypto_init_proc();
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 38c1aa89d3a0..28556fce4267 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -65,18 +65,10 @@ struct skcipher_async_req {
 	struct skcipher_async_rsgl first_sgl;
 	struct list_head list;
 	struct scatterlist *tsg;
-	char iv[];
+	atomic_t *inflight;
+	struct skcipher_request req;
 };
 
-#define GET_SREQ(areq, ctx) (struct skcipher_async_req *)((char *)areq + \
-	crypto_skcipher_reqsize(crypto_skcipher_reqtfm(&ctx->req)))
-
-#define GET_REQ_SIZE(ctx) \
-	crypto_skcipher_reqsize(crypto_skcipher_reqtfm(&ctx->req))
-
-#define GET_IV_SIZE(ctx) \
-	crypto_skcipher_ivsize(crypto_skcipher_reqtfm(&ctx->req))
-
 #define MAX_SGL_ENTS ((4096 - sizeof(struct skcipher_sg_list)) / \
 		      sizeof(struct scatterlist) - 1)
 
@@ -102,15 +94,12 @@ static void skcipher_free_async_sgls(struct skcipher_async_req *sreq)
 
 static void skcipher_async_cb(struct crypto_async_request *req, int err)
 {
-	struct sock *sk = req->data;
-	struct alg_sock *ask = alg_sk(sk);
-	struct skcipher_ctx *ctx = ask->private;
-	struct skcipher_async_req *sreq = GET_SREQ(req, ctx);
+	struct skcipher_async_req *sreq = req->data;
 	struct kiocb *iocb = sreq->iocb;
 
-	atomic_dec(&ctx->inflight);
+	atomic_dec(sreq->inflight);
 	skcipher_free_async_sgls(sreq);
-	kfree(req);
+	kzfree(sreq);
 	iocb->ki_complete(iocb, err, err);
 }
 
@@ -306,8 +295,11 @@ static int skcipher_sendmsg(struct socket *sock, struct msghdr *msg,
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
+	struct sock *psk = ask->parent;
+	struct alg_sock *pask = alg_sk(psk);
 	struct skcipher_ctx *ctx = ask->private;
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(&ctx->req);
+	struct skcipher_tfm *skc = pask->private;
+	struct crypto_skcipher *tfm = skc->skcipher;
 	unsigned ivsize = crypto_skcipher_ivsize(tfm);
 	struct skcipher_sg_list *sgl;
 	struct af_alg_control con = {};
@@ -509,37 +501,43 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg,
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
+	struct sock *psk = ask->parent;
+	struct alg_sock *pask = alg_sk(psk);
 	struct skcipher_ctx *ctx = ask->private;
+	struct skcipher_tfm *skc = pask->private;
+	struct crypto_skcipher *tfm = skc->skcipher;
 	struct skcipher_sg_list *sgl;
 	struct scatterlist *sg;
 	struct skcipher_async_req *sreq;
 	struct skcipher_request *req;
 	struct skcipher_async_rsgl *last_rsgl = NULL;
-	unsigned int txbufs = 0, len = 0, tx_nents = skcipher_all_sg_nents(ctx);
-	unsigned int reqlen = sizeof(struct skcipher_async_req) +
-				GET_REQ_SIZE(ctx) + GET_IV_SIZE(ctx);
+	unsigned int txbufs = 0, len = 0, tx_nents;
+	unsigned int reqsize = crypto_skcipher_reqsize(tfm);
+	unsigned int ivsize = crypto_skcipher_ivsize(tfm);
 	int err = -ENOMEM;
 	bool mark = false;
+	char *iv;
 
-	lock_sock(sk);
-	req = kmalloc(reqlen, GFP_KERNEL);
-	if (unlikely(!req))
-		goto unlock;
+	sreq = kzalloc(sizeof(*sreq) + reqsize + ivsize, GFP_KERNEL);
+	if (unlikely(!sreq))
+		goto out;
 
-	sreq = GET_SREQ(req, ctx);
+	req = &sreq->req;
+	iv = (char *)(req + 1) + reqsize;
 	sreq->iocb = msg->msg_iocb;
-	memset(&sreq->first_sgl, '\0', sizeof(struct skcipher_async_rsgl));
 	INIT_LIST_HEAD(&sreq->list);
+	sreq->inflight = &ctx->inflight;
+
+	lock_sock(sk);
+	tx_nents = skcipher_all_sg_nents(ctx);
 	sreq->tsg = kcalloc(tx_nents, sizeof(*sg), GFP_KERNEL);
-	if (unlikely(!sreq->tsg)) {
-		kfree(req);
+	if (unlikely(!sreq->tsg))
 		goto unlock;
-	}
 	sg_init_table(sreq->tsg, tx_nents);
-	memcpy(sreq->iv, ctx->iv, GET_IV_SIZE(ctx));
-	skcipher_request_set_tfm(req, crypto_skcipher_reqtfm(&ctx->req));
-	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
-				      skcipher_async_cb, sk);
+	memcpy(iv, ctx->iv, ivsize);
+	skcipher_request_set_tfm(req, tfm);
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
+				      skcipher_async_cb, sreq);
 
 	while (iov_iter_count(&msg->msg_iter)) {
 		struct skcipher_async_rsgl *rsgl;
@@ -615,20 +613,22 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg,
 		sg_mark_end(sreq->tsg + txbufs - 1);
 
 	skcipher_request_set_crypt(req, sreq->tsg, sreq->first_sgl.sgl.sg,
-				   len, sreq->iv);
+				   len, iv);
 	err = ctx->enc ? crypto_skcipher_encrypt(req) :
 			 crypto_skcipher_decrypt(req);
 	if (err == -EINPROGRESS) {
 		atomic_inc(&ctx->inflight);
 		err = -EIOCBQUEUED;
+		sreq = NULL;
 		goto unlock;
 	}
 free:
 	skcipher_free_async_sgls(sreq);
-	kfree(req);
 unlock:
 	skcipher_wmem_wakeup(sk);
 	release_sock(sk);
+	kzfree(sreq);
+out:
 	return err;
 }
 
@@ -637,9 +637,12 @@ static int skcipher_recvmsg_sync(struct socket *sock, struct msghdr *msg,
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
+	struct sock *psk = ask->parent;
+	struct alg_sock *pask = alg_sk(psk);
 	struct skcipher_ctx *ctx = ask->private;
-	unsigned bs = crypto_skcipher_blocksize(crypto_skcipher_reqtfm(
-		&ctx->req));
+	struct skcipher_tfm *skc = pask->private;
+	struct crypto_skcipher *tfm = skc->skcipher;
+	unsigned bs = crypto_skcipher_blocksize(tfm);
 	struct skcipher_sg_list *sgl;
 	struct scatterlist *sg;
 	int err = -EAGAIN;
@@ -947,7 +950,8 @@ static int skcipher_accept_parent_nokey(void *private, struct sock *sk)
 	ask->private = ctx;
 
 	skcipher_request_set_tfm(&ctx->req, skcipher);
-	skcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+	skcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_SLEEP |
+						 CRYPTO_TFM_REQ_MAY_BACKLOG,
 				      af_alg_complete, &ctx->completion);
 
 	sk->sk_destruct = skcipher_sock_destruct;
diff --git a/crypto/crc32.c b/crypto/crc32_generic.c
index 187ded28cb0b..aa2a25fc7482 100644
--- a/crypto/crc32.c
+++ b/crypto/crc32_generic.c
@@ -131,7 +131,7 @@ static struct shash_alg alg = {
 	.digestsize	= CHKSUM_DIGEST_SIZE,
 	.base		= {
 		.cra_name		= "crc32",
-		.cra_driver_name	= "crc32-table",
+		.cra_driver_name	= "crc32-generic",
 		.cra_priority		= 100,
 		.cra_blocksize		= CHKSUM_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(u32),
@@ -157,3 +157,4 @@ MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>");
 MODULE_DESCRIPTION("CRC32 calculations wrapper for lib/crc32");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_CRYPTO("crc32");
+MODULE_ALIAS_CRYPTO("crc32-generic");
diff --git a/crypto/crypto_engine.c b/crypto/crypto_engine.c
new file mode 100644
index 000000000000..a55c82dd48ef
--- /dev/null
+++ b/crypto/crypto_engine.c
@@ -0,0 +1,355 @@
+/*
+ * Handle async block request by crypto hardware engine.
+ *
+ * Copyright (C) 2016 Linaro, Inc.
+ *
+ * Author: Baolin Wang <baolin.wang@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <linux/err.h>
+#include <linux/delay.h>
+#include "internal.h"
+
+#define CRYPTO_ENGINE_MAX_QLEN 10
+
+void crypto_finalize_request(struct crypto_engine *engine,
+			     struct ablkcipher_request *req, int err);
+
+/**
+ * crypto_pump_requests - dequeue one request from engine queue to process
+ * @engine: the hardware engine
+ * @in_kthread: true if we are in the context of the request pump thread
+ *
+ * This function checks if there is any request in the engine queue that
+ * needs processing and if so call out to the driver to initialize hardware
+ * and handle each request.
+ */
+static void crypto_pump_requests(struct crypto_engine *engine,
+				 bool in_kthread)
+{
+	struct crypto_async_request *async_req, *backlog;
+	struct ablkcipher_request *req;
+	unsigned long flags;
+	bool was_busy = false;
+	int ret;
+
+	spin_lock_irqsave(&engine->queue_lock, flags);
+
+	/* Make sure we are not already running a request */
+	if (engine->cur_req)
+		goto out;
+
+	/* If another context is idling then defer */
+	if (engine->idling) {
+		queue_kthread_work(&engine->kworker, &engine->pump_requests);
+		goto out;
+	}
+
+	/* Check if the engine queue is idle */
+	if (!crypto_queue_len(&engine->queue) || !engine->running) {
+		if (!engine->busy)
+			goto out;
+
+		/* Only do teardown in the thread */
+		if (!in_kthread) {
+			queue_kthread_work(&engine->kworker,
+					   &engine->pump_requests);
+			goto out;
+		}
+
+		engine->busy = false;
+		engine->idling = true;
+		spin_unlock_irqrestore(&engine->queue_lock, flags);
+
+		if (engine->unprepare_crypt_hardware &&
+		    engine->unprepare_crypt_hardware(engine))
+			pr_err("failed to unprepare crypt hardware\n");
+
+		spin_lock_irqsave(&engine->queue_lock, flags);
+		engine->idling = false;
+		goto out;
+	}
+
+	/* Get the fist request from the engine queue to handle */
+	backlog = crypto_get_backlog(&engine->queue);
+	async_req = crypto_dequeue_request(&engine->queue);
+	if (!async_req)
+		goto out;
+
+	req = ablkcipher_request_cast(async_req);
+
+	engine->cur_req = req;
+	if (backlog)
+		backlog->complete(backlog, -EINPROGRESS);
+
+	if (engine->busy)
+		was_busy = true;
+	else
+		engine->busy = true;
+
+	spin_unlock_irqrestore(&engine->queue_lock, flags);
+
+	/* Until here we get the request need to be encrypted successfully */
+	if (!was_busy && engine->prepare_crypt_hardware) {
+		ret = engine->prepare_crypt_hardware(engine);
+		if (ret) {
+			pr_err("failed to prepare crypt hardware\n");
+			goto req_err;
+		}
+	}
+
+	if (engine->prepare_request) {
+		ret = engine->prepare_request(engine, engine->cur_req);
+		if (ret) {
+			pr_err("failed to prepare request: %d\n", ret);
+			goto req_err;
+		}
+		engine->cur_req_prepared = true;
+	}
+
+	ret = engine->crypt_one_request(engine, engine->cur_req);
+	if (ret) {
+		pr_err("failed to crypt one request from queue\n");
+		goto req_err;
+	}
+	return;
+
+req_err:
+	crypto_finalize_request(engine, engine->cur_req, ret);
+	return;
+
+out:
+	spin_unlock_irqrestore(&engine->queue_lock, flags);
+}
+
+static void crypto_pump_work(struct kthread_work *work)
+{
+	struct crypto_engine *engine =
+		container_of(work, struct crypto_engine, pump_requests);
+
+	crypto_pump_requests(engine, true);
+}
+
+/**
+ * crypto_transfer_request - transfer the new request into the engine queue
+ * @engine: the hardware engine
+ * @req: the request need to be listed into the engine queue
+ */
+int crypto_transfer_request(struct crypto_engine *engine,
+			    struct ablkcipher_request *req, bool need_pump)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&engine->queue_lock, flags);
+
+	if (!engine->running) {
+		spin_unlock_irqrestore(&engine->queue_lock, flags);
+		return -ESHUTDOWN;
+	}
+
+	ret = ablkcipher_enqueue_request(&engine->queue, req);
+
+	if (!engine->busy && need_pump)
+		queue_kthread_work(&engine->kworker, &engine->pump_requests);
+
+	spin_unlock_irqrestore(&engine->queue_lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(crypto_transfer_request);
+
+/**
+ * crypto_transfer_request_to_engine - transfer one request to list into the
+ * engine queue
+ * @engine: the hardware engine
+ * @req: the request need to be listed into the engine queue
+ */
+int crypto_transfer_request_to_engine(struct crypto_engine *engine,
+				      struct ablkcipher_request *req)
+{
+	return crypto_transfer_request(engine, req, true);
+}
+EXPORT_SYMBOL_GPL(crypto_transfer_request_to_engine);
+
+/**
+ * crypto_finalize_request - finalize one request if the request is done
+ * @engine: the hardware engine
+ * @req: the request need to be finalized
+ * @err: error number
+ */
+void crypto_finalize_request(struct crypto_engine *engine,
+			     struct ablkcipher_request *req, int err)
+{
+	unsigned long flags;
+	bool finalize_cur_req = false;
+	int ret;
+
+	spin_lock_irqsave(&engine->queue_lock, flags);
+	if (engine->cur_req == req)
+		finalize_cur_req = true;
+	spin_unlock_irqrestore(&engine->queue_lock, flags);
+
+	if (finalize_cur_req) {
+		if (engine->cur_req_prepared && engine->unprepare_request) {
+			ret = engine->unprepare_request(engine, req);
+			if (ret)
+				pr_err("failed to unprepare request\n");
+		}
+
+		spin_lock_irqsave(&engine->queue_lock, flags);
+		engine->cur_req = NULL;
+		engine->cur_req_prepared = false;
+		spin_unlock_irqrestore(&engine->queue_lock, flags);
+	}
+
+	req->base.complete(&req->base, err);
+
+	queue_kthread_work(&engine->kworker, &engine->pump_requests);
+}
+EXPORT_SYMBOL_GPL(crypto_finalize_request);
+
+/**
+ * crypto_engine_start - start the hardware engine
+ * @engine: the hardware engine need to be started
+ *
+ * Return 0 on success, else on fail.
+ */
+int crypto_engine_start(struct crypto_engine *engine)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&engine->queue_lock, flags);
+
+	if (engine->running || engine->busy) {
+		spin_unlock_irqrestore(&engine->queue_lock, flags);
+		return -EBUSY;
+	}
+
+	engine->running = true;
+	spin_unlock_irqrestore(&engine->queue_lock, flags);
+
+	queue_kthread_work(&engine->kworker, &engine->pump_requests);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_engine_start);
+
+/**
+ * crypto_engine_stop - stop the hardware engine
+ * @engine: the hardware engine need to be stopped
+ *
+ * Return 0 on success, else on fail.
+ */
+int crypto_engine_stop(struct crypto_engine *engine)
+{
+	unsigned long flags;
+	unsigned limit = 500;
+	int ret = 0;
+
+	spin_lock_irqsave(&engine->queue_lock, flags);
+
+	/*
+	 * If the engine queue is not empty or the engine is on busy state,
+	 * we need to wait for a while to pump the requests of engine queue.
+	 */
+	while ((crypto_queue_len(&engine->queue) || engine->busy) && limit--) {
+		spin_unlock_irqrestore(&engine->queue_lock, flags);
+		msleep(20);
+		spin_lock_irqsave(&engine->queue_lock, flags);
+	}
+
+	if (crypto_queue_len(&engine->queue) || engine->busy)
+		ret = -EBUSY;
+	else
+		engine->running = false;
+
+	spin_unlock_irqrestore(&engine->queue_lock, flags);
+
+	if (ret)
+		pr_warn("could not stop engine\n");
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(crypto_engine_stop);
+
+/**
+ * crypto_engine_alloc_init - allocate crypto hardware engine structure and
+ * initialize it.
+ * @dev: the device attached with one hardware engine
+ * @rt: whether this queue is set to run as a realtime task
+ *
+ * This must be called from context that can sleep.
+ * Return: the crypto engine structure on success, else NULL.
+ */
+struct crypto_engine *crypto_engine_alloc_init(struct device *dev, bool rt)
+{
+	struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
+	struct crypto_engine *engine;
+
+	if (!dev)
+		return NULL;
+
+	engine = devm_kzalloc(dev, sizeof(*engine), GFP_KERNEL);
+	if (!engine)
+		return NULL;
+
+	engine->rt = rt;
+	engine->running = false;
+	engine->busy = false;
+	engine->idling = false;
+	engine->cur_req_prepared = false;
+	engine->priv_data = dev;
+	snprintf(engine->name, sizeof(engine->name),
+		 "%s-engine", dev_name(dev));
+
+	crypto_init_queue(&engine->queue, CRYPTO_ENGINE_MAX_QLEN);
+	spin_lock_init(&engine->queue_lock);
+
+	init_kthread_worker(&engine->kworker);
+	engine->kworker_task = kthread_run(kthread_worker_fn,
+					   &engine->kworker, "%s",
+					   engine->name);
+	if (IS_ERR(engine->kworker_task)) {
+		dev_err(dev, "failed to create crypto request pump task\n");
+		return NULL;
+	}
+	init_kthread_work(&engine->pump_requests, crypto_pump_work);
+
+	if (engine->rt) {
+		dev_info(dev, "will run requests pump with realtime priority\n");
+		sched_setscheduler(engine->kworker_task, SCHED_FIFO, &param);
+	}
+
+	return engine;
+}
+EXPORT_SYMBOL_GPL(crypto_engine_alloc_init);
+
+/**
+ * crypto_engine_exit - free the resources of hardware engine when exit
+ * @engine: the hardware engine need to be freed
+ *
+ * Return 0 for success.
+ */
+int crypto_engine_exit(struct crypto_engine *engine)
+{
+	int ret;
+
+	ret = crypto_engine_stop(engine);
+	if (ret)
+		return ret;
+
+	flush_kthread_worker(&engine->kworker);
+	kthread_stop(engine->kworker_task);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_engine_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Crypto hardware engine framework");
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 237f3795cfaa..43fe85f20d57 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -499,6 +499,7 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		if (link->dump == NULL)
 			return -EINVAL;
 
+		down_read(&crypto_alg_sem);
 		list_for_each_entry(alg, &crypto_alg_list, cra_list)
 			dump_alloc += CRYPTO_REPORT_MAXSIZE;
 
@@ -508,8 +509,11 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 				.done = link->done,
 				.min_dump_alloc = dump_alloc,
 			};
-			return netlink_dump_start(crypto_nlsk, skb, nlh, &c);
+			err = netlink_dump_start(crypto_nlsk, skb, nlh, &c);
 		}
+		up_read(&crypto_alg_sem);
+
+		return err;
 	}
 
 	err = nlmsg_parse(nlh, crypto_msg_min[type], attrs, CRYPTOCFGA_MAX,
diff --git a/crypto/drbg.c b/crypto/drbg.c
index ab6ef1d08568..1b86310db7b1 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -220,48 +220,6 @@ static inline unsigned short drbg_sec_strength(drbg_flag_t flags)
 }
 
 /*
- * FIPS 140-2 continuous self test
- * The test is performed on the result of one round of the output
- * function. Thus, the function implicitly knows the size of the
- * buffer.
- *
- * @drbg DRBG handle
- * @buf output buffer of random data to be checked
- *
- * return:
- *	true on success
- *	false on error
- */
-static bool drbg_fips_continuous_test(struct drbg_state *drbg,
-				      const unsigned char *buf)
-{
-#ifdef CONFIG_CRYPTO_FIPS
-	int ret = 0;
-	/* skip test if we test the overall system */
-	if (list_empty(&drbg->test_data.list))
-		return true;
-	/* only perform test in FIPS mode */
-	if (0 == fips_enabled)
-		return true;
-	if (!drbg->fips_primed) {
-		/* Priming of FIPS test */
-		memcpy(drbg->prev, buf, drbg_blocklen(drbg));
-		drbg->fips_primed = true;
-		/* return false due to priming, i.e. another round is needed */
-		return false;
-	}
-	ret = memcmp(drbg->prev, buf, drbg_blocklen(drbg));
-	if (!ret)
-		panic("DRBG continuous self test failed\n");
-	memcpy(drbg->prev, buf, drbg_blocklen(drbg));
-	/* the test shall pass when the two compared values are not equal */
-	return ret != 0;
-#else
-	return true;
-#endif /* CONFIG_CRYPTO_FIPS */
-}
-
-/*
  * Convert an integer into a byte representation of this integer.
  * The byte representation is big-endian
  *
@@ -603,11 +561,6 @@ static int drbg_ctr_generate(struct drbg_state *drbg,
 		}
 		outlen = (drbg_blocklen(drbg) < (buflen - len)) ?
 			  drbg_blocklen(drbg) : (buflen - len);
-		if (!drbg_fips_continuous_test(drbg, drbg->scratchpad)) {
-			/* 10.2.1.5.2 step 6 */
-			crypto_inc(drbg->V, drbg_blocklen(drbg));
-			continue;
-		}
 		/* 10.2.1.5.2 step 4.3 */
 		memcpy(buf + len, drbg->scratchpad, outlen);
 		len += outlen;
@@ -733,8 +686,6 @@ static int drbg_hmac_generate(struct drbg_state *drbg,
 			return ret;
 		outlen = (drbg_blocklen(drbg) < (buflen - len)) ?
 			  drbg_blocklen(drbg) : (buflen - len);
-		if (!drbg_fips_continuous_test(drbg, drbg->V))
-			continue;
 
 		/* 10.1.2.5 step 4.2 */
 		memcpy(buf + len, drbg->V, outlen);
@@ -963,10 +914,6 @@ static int drbg_hash_hashgen(struct drbg_state *drbg,
 		}
 		outlen = (drbg_blocklen(drbg) < (buflen - len)) ?
 			  drbg_blocklen(drbg) : (buflen - len);
-		if (!drbg_fips_continuous_test(drbg, dst)) {
-			crypto_inc(src, drbg_statelen(drbg));
-			continue;
-		}
 		/* 10.1.1.4 step hashgen 4.2 */
 		memcpy(buf + len, dst, outlen);
 		len += outlen;
@@ -1201,11 +1148,6 @@ static inline void drbg_dealloc_state(struct drbg_state *drbg)
 	drbg->reseed_ctr = 0;
 	drbg->d_ops = NULL;
 	drbg->core = NULL;
-#ifdef CONFIG_CRYPTO_FIPS
-	kzfree(drbg->prev);
-	drbg->prev = NULL;
-	drbg->fips_primed = false;
-#endif
 }
 
 /*
@@ -1244,12 +1186,6 @@ static inline int drbg_alloc_state(struct drbg_state *drbg)
 	drbg->C = kmalloc(drbg_statelen(drbg), GFP_KERNEL);
 	if (!drbg->C)
 		goto err;
-#ifdef CONFIG_CRYPTO_FIPS
-	drbg->prev = kmalloc(drbg_blocklen(drbg), GFP_KERNEL);
-	if (!drbg->prev)
-		goto err;
-	drbg->fips_primed = false;
-#endif
 	/* scratchpad is only generated for CTR and Hash */
 	if (drbg->core->flags & DRBG_HMAC)
 		sb_size = 0;
diff --git a/crypto/internal.h b/crypto/internal.h
index 00e42a3ed814..7eefcdb00227 100644
--- a/crypto/internal.h
+++ b/crypto/internal.h
@@ -104,6 +104,9 @@ int crypto_probing_notify(unsigned long val, void *v);
 
 unsigned int crypto_alg_extsize(struct crypto_alg *alg);
 
+int crypto_type_has_alg(const char *name, const struct crypto_type *frontend,
+			u32 type, u32 mask);
+
 static inline struct crypto_alg *crypto_alg_get(struct crypto_alg *alg)
 {
 	atomic_inc(&alg->cra_refcnt);
diff --git a/crypto/keywrap.c b/crypto/keywrap.c
index b1d106ce55f3..72014f963ba7 100644
--- a/crypto/keywrap.c
+++ b/crypto/keywrap.c
@@ -212,7 +212,7 @@ static int crypto_kw_decrypt(struct blkcipher_desc *desc,
 			  SEMIBSIZE))
 		ret = -EBADMSG;
 
-	memzero_explicit(&block, sizeof(struct crypto_kw_block));
+	memzero_explicit(block, sizeof(struct crypto_kw_block));
 
 	return ret;
 }
@@ -297,7 +297,7 @@ static int crypto_kw_encrypt(struct blkcipher_desc *desc,
 	/* establish the IV for the caller to pick up */
 	memcpy(desc->info, block->A, SEMIBSIZE);
 
-	memzero_explicit(&block, sizeof(struct crypto_kw_block));
+	memzero_explicit(block, sizeof(struct crypto_kw_block));
 
 	return 0;
 }
diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c
index f78d4fc4e38a..c4eb9da49d4f 100644
--- a/crypto/mcryptd.c
+++ b/crypto/mcryptd.c
@@ -522,6 +522,7 @@ static int mcryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
 	inst->alg.halg.base.cra_flags = type;
 
 	inst->alg.halg.digestsize = salg->digestsize;
+	inst->alg.halg.statesize = salg->statesize;
 	inst->alg.halg.base.cra_ctxsize = sizeof(struct mcryptd_hash_ctx);
 
 	inst->alg.halg.base.cra_init = mcryptd_hash_init_tfm;
diff --git a/crypto/pcompress.c b/crypto/pcompress.c
deleted file mode 100644
index 7a13b4088857..000000000000
--- a/crypto/pcompress.c
+++ /dev/null
@@ -1,115 +0,0 @@
-/*
- * Cryptographic API.
- *
- * Partial (de)compression operations.
- *
- * Copyright 2008 Sony Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.
- * If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/crypto.h>
-#include <linux/errno.h>
-#include <linux/module.h>
-#include <linux/seq_file.h>
-#include <linux/string.h>
-#include <linux/cryptouser.h>
-#include <net/netlink.h>
-
-#include <crypto/compress.h>
-#include <crypto/internal/compress.h>
-
-#include "internal.h"
-
-
-static int crypto_pcomp_init(struct crypto_tfm *tfm, u32 type, u32 mask)
-{
-	return 0;
-}
-
-static int crypto_pcomp_init_tfm(struct crypto_tfm *tfm)
-{
-	return 0;
-}
-
-#ifdef CONFIG_NET
-static int crypto_pcomp_report(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	struct crypto_report_comp rpcomp;
-
-	strncpy(rpcomp.type, "pcomp", sizeof(rpcomp.type));
-	if (nla_put(skb, CRYPTOCFGA_REPORT_COMPRESS,
-		    sizeof(struct crypto_report_comp), &rpcomp))
-		goto nla_put_failure;
-	return 0;
-
-nla_put_failure:
-	return -EMSGSIZE;
-}
-#else
-static int crypto_pcomp_report(struct sk_buff *skb, struct crypto_alg *alg)
-{
-	return -ENOSYS;
-}
-#endif
-
-static void crypto_pcomp_show(struct seq_file *m, struct crypto_alg *alg)
-	__attribute__ ((unused));
-static void crypto_pcomp_show(struct seq_file *m, struct crypto_alg *alg)
-{
-	seq_printf(m, "type         : pcomp\n");
-}
-
-static const struct crypto_type crypto_pcomp_type = {
-	.extsize	= crypto_alg_extsize,
-	.init		= crypto_pcomp_init,
-	.init_tfm	= crypto_pcomp_init_tfm,
-#ifdef CONFIG_PROC_FS
-	.show		= crypto_pcomp_show,
-#endif
-	.report		= crypto_pcomp_report,
-	.maskclear	= ~CRYPTO_ALG_TYPE_MASK,
-	.maskset	= CRYPTO_ALG_TYPE_MASK,
-	.type		= CRYPTO_ALG_TYPE_PCOMPRESS,
-	.tfmsize	= offsetof(struct crypto_pcomp, base),
-};
-
-struct crypto_pcomp *crypto_alloc_pcomp(const char *alg_name, u32 type,
-					u32 mask)
-{
-	return crypto_alloc_tfm(alg_name, &crypto_pcomp_type, type, mask);
-}
-EXPORT_SYMBOL_GPL(crypto_alloc_pcomp);
-
-int crypto_register_pcomp(struct pcomp_alg *alg)
-{
-	struct crypto_alg *base = &alg->base;
-
-	base->cra_type = &crypto_pcomp_type;
-	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
-	base->cra_flags |= CRYPTO_ALG_TYPE_PCOMPRESS;
-
-	return crypto_register_alg(base);
-}
-EXPORT_SYMBOL_GPL(crypto_register_pcomp);
-
-int crypto_unregister_pcomp(struct pcomp_alg *alg)
-{
-	return crypto_unregister_alg(&alg->base);
-}
-EXPORT_SYMBOL_GPL(crypto_unregister_pcomp);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Partial (de)compression type");
-MODULE_AUTHOR("Sony Corporation");
diff --git a/crypto/shash.c b/crypto/shash.c
index 359754591653..a051541a4a17 100644
--- a/crypto/shash.c
+++ b/crypto/shash.c
@@ -368,151 +368,6 @@ int crypto_init_shash_ops_async(struct crypto_tfm *tfm)
 	return 0;
 }
 
-static int shash_compat_setkey(struct crypto_hash *tfm, const u8 *key,
-			       unsigned int keylen)
-{
-	struct shash_desc **descp = crypto_hash_ctx(tfm);
-	struct shash_desc *desc = *descp;
-
-	return crypto_shash_setkey(desc->tfm, key, keylen);
-}
-
-static int shash_compat_init(struct hash_desc *hdesc)
-{
-	struct shash_desc **descp = crypto_hash_ctx(hdesc->tfm);
-	struct shash_desc *desc = *descp;
-
-	desc->flags = hdesc->flags;
-
-	return crypto_shash_init(desc);
-}
-
-static int shash_compat_update(struct hash_desc *hdesc, struct scatterlist *sg,
-			       unsigned int len)
-{
-	struct shash_desc **descp = crypto_hash_ctx(hdesc->tfm);
-	struct shash_desc *desc = *descp;
-	struct crypto_hash_walk walk;
-	int nbytes;
-
-	for (nbytes = crypto_hash_walk_first_compat(hdesc, &walk, sg, len);
-	     nbytes > 0; nbytes = crypto_hash_walk_done(&walk, nbytes))
-		nbytes = crypto_shash_update(desc, walk.data, nbytes);
-
-	return nbytes;
-}
-
-static int shash_compat_final(struct hash_desc *hdesc, u8 *out)
-{
-	struct shash_desc **descp = crypto_hash_ctx(hdesc->tfm);
-
-	return crypto_shash_final(*descp, out);
-}
-
-static int shash_compat_digest(struct hash_desc *hdesc, struct scatterlist *sg,
-			       unsigned int nbytes, u8 *out)
-{
-	unsigned int offset = sg->offset;
-	int err;
-
-	if (nbytes < min(sg->length, ((unsigned int)(PAGE_SIZE)) - offset)) {
-		struct shash_desc **descp = crypto_hash_ctx(hdesc->tfm);
-		struct shash_desc *desc = *descp;
-		void *data;
-
-		desc->flags = hdesc->flags;
-
-		data = kmap_atomic(sg_page(sg));
-		err = crypto_shash_digest(desc, data + offset, nbytes, out);
-		kunmap_atomic(data);
-		crypto_yield(desc->flags);
-		goto out;
-	}
-
-	err = shash_compat_init(hdesc);
-	if (err)
-		goto out;
-
-	err = shash_compat_update(hdesc, sg, nbytes);
-	if (err)
-		goto out;
-
-	err = shash_compat_final(hdesc, out);
-
-out:
-	return err;
-}
-
-static void crypto_exit_shash_ops_compat(struct crypto_tfm *tfm)
-{
-	struct shash_desc **descp = crypto_tfm_ctx(tfm);
-	struct shash_desc *desc = *descp;
-
-	crypto_free_shash(desc->tfm);
-	kzfree(desc);
-}
-
-static int crypto_init_shash_ops_compat(struct crypto_tfm *tfm)
-{
-	struct hash_tfm *crt = &tfm->crt_hash;
-	struct crypto_alg *calg = tfm->__crt_alg;
-	struct shash_alg *alg = __crypto_shash_alg(calg);
-	struct shash_desc **descp = crypto_tfm_ctx(tfm);
-	struct crypto_shash *shash;
-	struct shash_desc *desc;
-
-	if (!crypto_mod_get(calg))
-		return -EAGAIN;
-
-	shash = crypto_create_tfm(calg, &crypto_shash_type);
-	if (IS_ERR(shash)) {
-		crypto_mod_put(calg);
-		return PTR_ERR(shash);
-	}
-
-	desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(shash),
-		       GFP_KERNEL);
-	if (!desc) {
-		crypto_free_shash(shash);
-		return -ENOMEM;
-	}
-
-	*descp = desc;
-	desc->tfm = shash;
-	tfm->exit = crypto_exit_shash_ops_compat;
-
-	crt->init = shash_compat_init;
-	crt->update = shash_compat_update;
-	crt->final  = shash_compat_final;
-	crt->digest = shash_compat_digest;
-	crt->setkey = shash_compat_setkey;
-
-	crt->digestsize = alg->digestsize;
-
-	return 0;
-}
-
-static int crypto_init_shash_ops(struct crypto_tfm *tfm, u32 type, u32 mask)
-{
-	switch (mask & CRYPTO_ALG_TYPE_MASK) {
-	case CRYPTO_ALG_TYPE_HASH_MASK:
-		return crypto_init_shash_ops_compat(tfm);
-	}
-
-	return -EINVAL;
-}
-
-static unsigned int crypto_shash_ctxsize(struct crypto_alg *alg, u32 type,
-					 u32 mask)
-{
-	switch (mask & CRYPTO_ALG_TYPE_MASK) {
-	case CRYPTO_ALG_TYPE_HASH_MASK:
-		return sizeof(struct shash_desc *);
-	}
-
-	return 0;
-}
-
 static int crypto_shash_init_tfm(struct crypto_tfm *tfm)
 {
 	struct crypto_shash *hash = __crypto_shash_cast(tfm);
@@ -559,9 +414,7 @@ static void crypto_shash_show(struct seq_file *m, struct crypto_alg *alg)
 }
 
 static const struct crypto_type crypto_shash_type = {
-	.ctxsize = crypto_shash_ctxsize,
 	.extsize = crypto_alg_extsize,
-	.init = crypto_init_shash_ops,
 	.init_tfm = crypto_shash_init_tfm,
 #ifdef CONFIG_PROC_FS
 	.show = crypto_shash_show,
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index d199c0b1751c..69230e9d4ac9 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -118,7 +118,7 @@ static int crypto_init_skcipher_ops_blkcipher(struct crypto_tfm *tfm)
 	skcipher->decrypt = skcipher_decrypt_blkcipher;
 
 	skcipher->ivsize = crypto_blkcipher_ivsize(blkcipher);
-	skcipher->has_setkey = calg->cra_blkcipher.max_keysize;
+	skcipher->keysize = calg->cra_blkcipher.max_keysize;
 
 	return 0;
 }
@@ -211,7 +211,7 @@ static int crypto_init_skcipher_ops_ablkcipher(struct crypto_tfm *tfm)
 	skcipher->ivsize = crypto_ablkcipher_ivsize(ablkcipher);
 	skcipher->reqsize = crypto_ablkcipher_reqsize(ablkcipher) +
 			    sizeof(struct ablkcipher_request);
-	skcipher->has_setkey = calg->cra_ablkcipher.max_keysize;
+	skcipher->keysize = calg->cra_ablkcipher.max_keysize;
 
 	return 0;
 }
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 270bc4b82bd9..579dce071463 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -554,164 +554,6 @@ out:
 	crypto_free_blkcipher(tfm);
 }
 
-static int test_hash_jiffies_digest(struct hash_desc *desc,
-				    struct scatterlist *sg, int blen,
-				    char *out, int secs)
-{
-	unsigned long start, end;
-	int bcount;
-	int ret;
-
-	for (start = jiffies, end = start + secs * HZ, bcount = 0;
-	     time_before(jiffies, end); bcount++) {
-		ret = crypto_hash_digest(desc, sg, blen, out);
-		if (ret)
-			return ret;
-	}
-
-	printk("%6u opers/sec, %9lu bytes/sec\n",
-	       bcount / secs, ((long)bcount * blen) / secs);
-
-	return 0;
-}
-
-static int test_hash_jiffies(struct hash_desc *desc, struct scatterlist *sg,
-			     int blen, int plen, char *out, int secs)
-{
-	unsigned long start, end;
-	int bcount, pcount;
-	int ret;
-
-	if (plen == blen)
-		return test_hash_jiffies_digest(desc, sg, blen, out, secs);
-
-	for (start = jiffies, end = start + secs * HZ, bcount = 0;
-	     time_before(jiffies, end); bcount++) {
-		ret = crypto_hash_init(desc);
-		if (ret)
-			return ret;
-		for (pcount = 0; pcount < blen; pcount += plen) {
-			ret = crypto_hash_update(desc, sg, plen);
-			if (ret)
-				return ret;
-		}
-		/* we assume there is enough space in 'out' for the result */
-		ret = crypto_hash_final(desc, out);
-		if (ret)
-			return ret;
-	}
-
-	printk("%6u opers/sec, %9lu bytes/sec\n",
-	       bcount / secs, ((long)bcount * blen) / secs);
-
-	return 0;
-}
-
-static int test_hash_cycles_digest(struct hash_desc *desc,
-				   struct scatterlist *sg, int blen, char *out)
-{
-	unsigned long cycles = 0;
-	int i;
-	int ret;
-
-	local_irq_disable();
-
-	/* Warm-up run. */
-	for (i = 0; i < 4; i++) {
-		ret = crypto_hash_digest(desc, sg, blen, out);
-		if (ret)
-			goto out;
-	}
-
-	/* The real thing. */
-	for (i = 0; i < 8; i++) {
-		cycles_t start, end;
-
-		start = get_cycles();
-
-		ret = crypto_hash_digest(desc, sg, blen, out);
-		if (ret)
-			goto out;
-
-		end = get_cycles();
-
-		cycles += end - start;
-	}
-
-out:
-	local_irq_enable();
-
-	if (ret)
-		return ret;
-
-	printk("%6lu cycles/operation, %4lu cycles/byte\n",
-	       cycles / 8, cycles / (8 * blen));
-
-	return 0;
-}
-
-static int test_hash_cycles(struct hash_desc *desc, struct scatterlist *sg,
-			    int blen, int plen, char *out)
-{
-	unsigned long cycles = 0;
-	int i, pcount;
-	int ret;
-
-	if (plen == blen)
-		return test_hash_cycles_digest(desc, sg, blen, out);
-
-	local_irq_disable();
-
-	/* Warm-up run. */
-	for (i = 0; i < 4; i++) {
-		ret = crypto_hash_init(desc);
-		if (ret)
-			goto out;
-		for (pcount = 0; pcount < blen; pcount += plen) {
-			ret = crypto_hash_update(desc, sg, plen);
-			if (ret)
-				goto out;
-		}
-		ret = crypto_hash_final(desc, out);
-		if (ret)
-			goto out;
-	}
-
-	/* The real thing. */
-	for (i = 0; i < 8; i++) {
-		cycles_t start, end;
-
-		start = get_cycles();
-
-		ret = crypto_hash_init(desc);
-		if (ret)
-			goto out;
-		for (pcount = 0; pcount < blen; pcount += plen) {
-			ret = crypto_hash_update(desc, sg, plen);
-			if (ret)
-				goto out;
-		}
-		ret = crypto_hash_final(desc, out);
-		if (ret)
-			goto out;
-
-		end = get_cycles();
-
-		cycles += end - start;
-	}
-
-out:
-	local_irq_enable();
-
-	if (ret)
-		return ret;
-
-	printk("%6lu cycles/operation, %4lu cycles/byte\n",
-	       cycles / 8, cycles / (8 * blen));
-
-	return 0;
-}
-
 static void test_hash_sg_init(struct scatterlist *sg)
 {
 	int i;
@@ -723,69 +565,6 @@ static void test_hash_sg_init(struct scatterlist *sg)
 	}
 }
 
-static void test_hash_speed(const char *algo, unsigned int secs,
-			    struct hash_speed *speed)
-{
-	struct scatterlist sg[TVMEMSIZE];
-	struct crypto_hash *tfm;
-	struct hash_desc desc;
-	static char output[1024];
-	int i;
-	int ret;
-
-	tfm = crypto_alloc_hash(algo, 0, CRYPTO_ALG_ASYNC);
-
-	if (IS_ERR(tfm)) {
-		printk(KERN_ERR "failed to load transform for %s: %ld\n", algo,
-		       PTR_ERR(tfm));
-		return;
-	}
-
-	printk(KERN_INFO "\ntesting speed of %s (%s)\n", algo,
-			get_driver_name(crypto_hash, tfm));
-
-	desc.tfm = tfm;
-	desc.flags = 0;
-
-	if (crypto_hash_digestsize(tfm) > sizeof(output)) {
-		printk(KERN_ERR "digestsize(%u) > outputbuffer(%zu)\n",
-		       crypto_hash_digestsize(tfm), sizeof(output));
-		goto out;
-	}
-
-	test_hash_sg_init(sg);
-	for (i = 0; speed[i].blen != 0; i++) {
-		if (speed[i].blen > TVMEMSIZE * PAGE_SIZE) {
-			printk(KERN_ERR
-			       "template (%u) too big for tvmem (%lu)\n",
-			       speed[i].blen, TVMEMSIZE * PAGE_SIZE);
-			goto out;
-		}
-
-		if (speed[i].klen)
-			crypto_hash_setkey(tfm, tvmem[0], speed[i].klen);
-
-		printk(KERN_INFO "test%3u "
-		       "(%5u byte blocks,%5u bytes per update,%4u updates): ",
-		       i, speed[i].blen, speed[i].plen, speed[i].blen / speed[i].plen);
-
-		if (secs)
-			ret = test_hash_jiffies(&desc, sg, speed[i].blen,
-						speed[i].plen, output, secs);
-		else
-			ret = test_hash_cycles(&desc, sg, speed[i].blen,
-					       speed[i].plen, output);
-
-		if (ret) {
-			printk(KERN_ERR "hashing failed ret=%d\n", ret);
-			break;
-		}
-	}
-
-out:
-	crypto_free_hash(tfm);
-}
-
 static inline int do_one_ahash_op(struct ahash_request *req, int ret)
 {
 	if (ret == -EINPROGRESS || ret == -EBUSY) {
@@ -945,8 +724,8 @@ out:
 	return 0;
 }
 
-static void test_ahash_speed(const char *algo, unsigned int secs,
-			     struct hash_speed *speed)
+static void test_ahash_speed_common(const char *algo, unsigned int secs,
+				    struct hash_speed *speed, unsigned mask)
 {
 	struct scatterlist sg[TVMEMSIZE];
 	struct tcrypt_result tresult;
@@ -955,7 +734,7 @@ static void test_ahash_speed(const char *algo, unsigned int secs,
 	char *output;
 	int i, ret;
 
-	tfm = crypto_alloc_ahash(algo, 0, 0);
+	tfm = crypto_alloc_ahash(algo, 0, mask);
 	if (IS_ERR(tfm)) {
 		pr_err("failed to load transform for %s: %ld\n",
 		       algo, PTR_ERR(tfm));
@@ -1021,6 +800,18 @@ out:
 	crypto_free_ahash(tfm);
 }
 
+static void test_ahash_speed(const char *algo, unsigned int secs,
+			     struct hash_speed *speed)
+{
+	return test_ahash_speed_common(algo, secs, speed, 0);
+}
+
+static void test_hash_speed(const char *algo, unsigned int secs,
+			    struct hash_speed *speed)
+{
+	return test_ahash_speed_common(algo, secs, speed, CRYPTO_ALG_ASYNC);
+}
+
 static inline int do_one_acipher_op(struct ablkcipher_request *req, int ret)
 {
 	if (ret == -EINPROGRESS || ret == -EBUSY) {
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index ae8c57fd8bc7..b86883aedca1 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -96,13 +96,6 @@ struct comp_test_suite {
 	} comp, decomp;
 };
 
-struct pcomp_test_suite {
-	struct {
-		struct pcomp_testvec *vecs;
-		unsigned int count;
-	} comp, decomp;
-};
-
 struct hash_test_suite {
 	struct hash_testvec *vecs;
 	unsigned int count;
@@ -133,7 +126,6 @@ struct alg_test_desc {
 		struct aead_test_suite aead;
 		struct cipher_test_suite cipher;
 		struct comp_test_suite comp;
-		struct pcomp_test_suite pcomp;
 		struct hash_test_suite hash;
 		struct cprng_test_suite cprng;
 		struct drbg_test_suite drbg;
@@ -198,6 +190,61 @@ static int wait_async_op(struct tcrypt_result *tr, int ret)
 	return ret;
 }
 
+static int ahash_partial_update(struct ahash_request **preq,
+	struct crypto_ahash *tfm, struct hash_testvec *template,
+	void *hash_buff, int k, int temp, struct scatterlist *sg,
+	const char *algo, char *result, struct tcrypt_result *tresult)
+{
+	char *state;
+	struct ahash_request *req;
+	int statesize, ret = -EINVAL;
+
+	req = *preq;
+	statesize = crypto_ahash_statesize(
+			crypto_ahash_reqtfm(req));
+	state = kmalloc(statesize, GFP_KERNEL);
+	if (!state) {
+		pr_err("alt: hash: Failed to alloc state for %s\n", algo);
+		goto out_nostate;
+	}
+	ret = crypto_ahash_export(req, state);
+	if (ret) {
+		pr_err("alt: hash: Failed to export() for %s\n", algo);
+		goto out;
+	}
+	ahash_request_free(req);
+	req = ahash_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		pr_err("alg: hash: Failed to alloc request for %s\n", algo);
+		goto out_noreq;
+	}
+	ahash_request_set_callback(req,
+		CRYPTO_TFM_REQ_MAY_BACKLOG,
+		tcrypt_complete, tresult);
+
+	memcpy(hash_buff, template->plaintext + temp,
+		template->tap[k]);
+	sg_init_one(&sg[0], hash_buff, template->tap[k]);
+	ahash_request_set_crypt(req, sg, result, template->tap[k]);
+	ret = crypto_ahash_import(req, state);
+	if (ret) {
+		pr_err("alg: hash: Failed to import() for %s\n", algo);
+		goto out;
+	}
+	ret = wait_async_op(tresult, crypto_ahash_update(req));
+	if (ret)
+		goto out;
+	*preq = req;
+	ret = 0;
+	goto out_noreq;
+out:
+	ahash_request_free(req);
+out_noreq:
+	kfree(state);
+out_nostate:
+	return ret;
+}
+
 static int __test_hash(struct crypto_ahash *tfm, struct hash_testvec *template,
 		       unsigned int tcount, bool use_digest,
 		       const int align_offset)
@@ -385,6 +432,84 @@ static int __test_hash(struct crypto_ahash *tfm, struct hash_testvec *template,
 		}
 	}
 
+	/* partial update exercise */
+	j = 0;
+	for (i = 0; i < tcount; i++) {
+		/* alignment tests are only done with continuous buffers */
+		if (align_offset != 0)
+			break;
+
+		if (template[i].np < 2)
+			continue;
+
+		j++;
+		memset(result, 0, MAX_DIGEST_SIZE);
+
+		ret = -EINVAL;
+		hash_buff = xbuf[0];
+		memcpy(hash_buff, template[i].plaintext,
+			template[i].tap[0]);
+		sg_init_one(&sg[0], hash_buff, template[i].tap[0]);
+
+		if (template[i].ksize) {
+			crypto_ahash_clear_flags(tfm, ~0);
+			if (template[i].ksize > MAX_KEYLEN) {
+				pr_err("alg: hash: setkey failed on test %d for %s: key size %d > %d\n",
+					j, algo, template[i].ksize, MAX_KEYLEN);
+				ret = -EINVAL;
+				goto out;
+			}
+			memcpy(key, template[i].key, template[i].ksize);
+			ret = crypto_ahash_setkey(tfm, key, template[i].ksize);
+			if (ret) {
+				pr_err("alg: hash: setkey failed on test %d for %s: ret=%d\n",
+					j, algo, -ret);
+				goto out;
+			}
+		}
+
+		ahash_request_set_crypt(req, sg, result, template[i].tap[0]);
+		ret = wait_async_op(&tresult, crypto_ahash_init(req));
+		if (ret) {
+			pr_err("alt: hash: init failed on test %d for %s: ret=%d\n",
+				j, algo, -ret);
+			goto out;
+		}
+		ret = wait_async_op(&tresult, crypto_ahash_update(req));
+		if (ret) {
+			pr_err("alt: hash: update failed on test %d for %s: ret=%d\n",
+				j, algo, -ret);
+			goto out;
+		}
+
+		temp = template[i].tap[0];
+		for (k = 1; k < template[i].np; k++) {
+			ret = ahash_partial_update(&req, tfm, &template[i],
+				hash_buff, k, temp, &sg[0], algo, result,
+				&tresult);
+			if (ret) {
+				pr_err("hash: partial update failed on test %d for %s: ret=%d\n",
+					j, algo, -ret);
+				goto out_noreq;
+			}
+			temp += template[i].tap[k];
+		}
+		ret = wait_async_op(&tresult, crypto_ahash_final(req));
+		if (ret) {
+			pr_err("alt: hash: final failed on test %d for %s: ret=%d\n",
+				j, algo, -ret);
+			goto out;
+		}
+		if (memcmp(result, template[i].digest,
+			   crypto_ahash_digestsize(tfm))) {
+			pr_err("alg: hash: Partial Test %d failed for %s\n",
+			       j, algo);
+			hexdump(result, crypto_ahash_digestsize(tfm));
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
 	ret = 0;
 
 out:
@@ -488,6 +613,8 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 	aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				  tcrypt_complete, &result);
 
+	iv_len = crypto_aead_ivsize(tfm);
+
 	for (i = 0, j = 0; i < tcount; i++) {
 		if (template[i].np)
 			continue;
@@ -508,7 +635,6 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 
 		memcpy(input, template[i].input, template[i].ilen);
 		memcpy(assoc, template[i].assoc, template[i].alen);
-		iv_len = crypto_aead_ivsize(tfm);
 		if (template[i].iv)
 			memcpy(iv, template[i].iv, iv_len);
 		else
@@ -617,7 +743,7 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 		j++;
 
 		if (template[i].iv)
-			memcpy(iv, template[i].iv, MAX_IVLEN);
+			memcpy(iv, template[i].iv, iv_len);
 		else
 			memset(iv, 0, MAX_IVLEN);
 
@@ -1293,183 +1419,6 @@ out:
 	return ret;
 }
 
-static int test_pcomp(struct crypto_pcomp *tfm,
-		      struct pcomp_testvec *ctemplate,
-		      struct pcomp_testvec *dtemplate, int ctcount,
-		      int dtcount)
-{
-	const char *algo = crypto_tfm_alg_driver_name(crypto_pcomp_tfm(tfm));
-	unsigned int i;
-	char result[COMP_BUF_SIZE];
-	int res;
-
-	for (i = 0; i < ctcount; i++) {
-		struct comp_request req;
-		unsigned int produced = 0;
-
-		res = crypto_compress_setup(tfm, ctemplate[i].params,
-					    ctemplate[i].paramsize);
-		if (res) {
-			pr_err("alg: pcomp: compression setup failed on test "
-			       "%d for %s: error=%d\n", i + 1, algo, res);
-			return res;
-		}
-
-		res = crypto_compress_init(tfm);
-		if (res) {
-			pr_err("alg: pcomp: compression init failed on test "
-			       "%d for %s: error=%d\n", i + 1, algo, res);
-			return res;
-		}
-
-		memset(result, 0, sizeof(result));
-
-		req.next_in = ctemplate[i].input;
-		req.avail_in = ctemplate[i].inlen / 2;
-		req.next_out = result;
-		req.avail_out = ctemplate[i].outlen / 2;
-
-		res = crypto_compress_update(tfm, &req);
-		if (res < 0 && (res != -EAGAIN || req.avail_in)) {
-			pr_err("alg: pcomp: compression update failed on test "
-			       "%d for %s: error=%d\n", i + 1, algo, res);
-			return res;
-		}
-		if (res > 0)
-			produced += res;
-
-		/* Add remaining input data */
-		req.avail_in += (ctemplate[i].inlen + 1) / 2;
-
-		res = crypto_compress_update(tfm, &req);
-		if (res < 0 && (res != -EAGAIN || req.avail_in)) {
-			pr_err("alg: pcomp: compression update failed on test "
-			       "%d for %s: error=%d\n", i + 1, algo, res);
-			return res;
-		}
-		if (res > 0)
-			produced += res;
-
-		/* Provide remaining output space */
-		req.avail_out += COMP_BUF_SIZE - ctemplate[i].outlen / 2;
-
-		res = crypto_compress_final(tfm, &req);
-		if (res < 0) {
-			pr_err("alg: pcomp: compression final failed on test "
-			       "%d for %s: error=%d\n", i + 1, algo, res);
-			return res;
-		}
-		produced += res;
-
-		if (COMP_BUF_SIZE - req.avail_out != ctemplate[i].outlen) {
-			pr_err("alg: comp: Compression test %d failed for %s: "
-			       "output len = %d (expected %d)\n", i + 1, algo,
-			       COMP_BUF_SIZE - req.avail_out,
-			       ctemplate[i].outlen);
-			return -EINVAL;
-		}
-
-		if (produced != ctemplate[i].outlen) {
-			pr_err("alg: comp: Compression test %d failed for %s: "
-			       "returned len = %u (expected %d)\n", i + 1,
-			       algo, produced, ctemplate[i].outlen);
-			return -EINVAL;
-		}
-
-		if (memcmp(result, ctemplate[i].output, ctemplate[i].outlen)) {
-			pr_err("alg: pcomp: Compression test %d failed for "
-			       "%s\n", i + 1, algo);
-			hexdump(result, ctemplate[i].outlen);
-			return -EINVAL;
-		}
-	}
-
-	for (i = 0; i < dtcount; i++) {
-		struct comp_request req;
-		unsigned int produced = 0;
-
-		res = crypto_decompress_setup(tfm, dtemplate[i].params,
-					      dtemplate[i].paramsize);
-		if (res) {
-			pr_err("alg: pcomp: decompression setup failed on "
-			       "test %d for %s: error=%d\n", i + 1, algo, res);
-			return res;
-		}
-
-		res = crypto_decompress_init(tfm);
-		if (res) {
-			pr_err("alg: pcomp: decompression init failed on test "
-			       "%d for %s: error=%d\n", i + 1, algo, res);
-			return res;
-		}
-
-		memset(result, 0, sizeof(result));
-
-		req.next_in = dtemplate[i].input;
-		req.avail_in = dtemplate[i].inlen / 2;
-		req.next_out = result;
-		req.avail_out = dtemplate[i].outlen / 2;
-
-		res = crypto_decompress_update(tfm, &req);
-		if (res < 0 && (res != -EAGAIN || req.avail_in)) {
-			pr_err("alg: pcomp: decompression update failed on "
-			       "test %d for %s: error=%d\n", i + 1, algo, res);
-			return res;
-		}
-		if (res > 0)
-			produced += res;
-
-		/* Add remaining input data */
-		req.avail_in += (dtemplate[i].inlen + 1) / 2;
-
-		res = crypto_decompress_update(tfm, &req);
-		if (res < 0 && (res != -EAGAIN || req.avail_in)) {
-			pr_err("alg: pcomp: decompression update failed on "
-			       "test %d for %s: error=%d\n", i + 1, algo, res);
-			return res;
-		}
-		if (res > 0)
-			produced += res;
-
-		/* Provide remaining output space */
-		req.avail_out += COMP_BUF_SIZE - dtemplate[i].outlen / 2;
-
-		res = crypto_decompress_final(tfm, &req);
-		if (res < 0 && (res != -EAGAIN || req.avail_in)) {
-			pr_err("alg: pcomp: decompression final failed on "
-			       "test %d for %s: error=%d\n", i + 1, algo, res);
-			return res;
-		}
-		if (res > 0)
-			produced += res;
-
-		if (COMP_BUF_SIZE - req.avail_out != dtemplate[i].outlen) {
-			pr_err("alg: comp: Decompression test %d failed for "
-			       "%s: output len = %d (expected %d)\n", i + 1,
-			       algo, COMP_BUF_SIZE - req.avail_out,
-			       dtemplate[i].outlen);
-			return -EINVAL;
-		}
-
-		if (produced != dtemplate[i].outlen) {
-			pr_err("alg: comp: Decompression test %d failed for "
-			       "%s: returned len = %u (expected %d)\n", i + 1,
-			       algo, produced, dtemplate[i].outlen);
-			return -EINVAL;
-		}
-
-		if (memcmp(result, dtemplate[i].output, dtemplate[i].outlen)) {
-			pr_err("alg: pcomp: Decompression test %d failed for "
-			       "%s\n", i + 1, algo);
-			hexdump(result, dtemplate[i].outlen);
-			return -EINVAL;
-		}
-	}
-
-	return 0;
-}
-
-
 static int test_cprng(struct crypto_rng *tfm, struct cprng_testvec *template,
 		      unsigned int tcount)
 {
@@ -1640,28 +1589,6 @@ static int alg_test_comp(const struct alg_test_desc *desc, const char *driver,
 	return err;
 }
 
-static int alg_test_pcomp(const struct alg_test_desc *desc, const char *driver,
-			  u32 type, u32 mask)
-{
-	struct crypto_pcomp *tfm;
-	int err;
-
-	tfm = crypto_alloc_pcomp(driver, type, mask);
-	if (IS_ERR(tfm)) {
-		pr_err("alg: pcomp: Failed to load transform for %s: %ld\n",
-		       driver, PTR_ERR(tfm));
-		return PTR_ERR(tfm);
-	}
-
-	err = test_pcomp(tfm, desc->suite.pcomp.comp.vecs,
-			 desc->suite.pcomp.decomp.vecs,
-			 desc->suite.pcomp.comp.count,
-			 desc->suite.pcomp.decomp.count);
-
-	crypto_free_pcomp(tfm);
-	return err;
-}
-
 static int alg_test_hash(const struct alg_test_desc *desc, const char *driver,
 			 u32 type, u32 mask)
 {
@@ -2081,7 +2008,6 @@ static const struct alg_test_desc alg_test_descs[] = {
 	}, {
 		.alg = "ansi_cprng",
 		.test = alg_test_cprng,
-		.fips_allowed = 1,
 		.suite = {
 			.cprng = {
 				.vecs = ansi_cprng_aes_tv_template,
@@ -2132,6 +2058,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 	}, {
 		.alg = "authenc(hmac(sha1),cbc(des3_ede))",
 		.test = alg_test_aead,
+		.fips_allowed = 1,
 		.suite = {
 			.aead = {
 				.enc = {
@@ -2143,6 +2070,10 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "authenc(hmac(sha1),ctr(aes))",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+	}, {
 		.alg = "authenc(hmac(sha1),ecb(cipher_null))",
 		.test = alg_test_aead,
 		.suite = {
@@ -2162,6 +2093,10 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "authenc(hmac(sha1),rfc3686(ctr(aes)))",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+	}, {
 		.alg = "authenc(hmac(sha224),cbc(des))",
 		.test = alg_test_aead,
 		.suite = {
@@ -2177,6 +2112,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 	}, {
 		.alg = "authenc(hmac(sha224),cbc(des3_ede))",
 		.test = alg_test_aead,
+		.fips_allowed = 1,
 		.suite = {
 			.aead = {
 				.enc = {
@@ -2190,6 +2126,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 	}, {
 		.alg = "authenc(hmac(sha256),cbc(aes))",
 		.test = alg_test_aead,
+		.fips_allowed = 1,
 		.suite = {
 			.aead = {
 				.enc = {
@@ -2216,6 +2153,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 	}, {
 		.alg = "authenc(hmac(sha256),cbc(des3_ede))",
 		.test = alg_test_aead,
+		.fips_allowed = 1,
 		.suite = {
 			.aead = {
 				.enc = {
@@ -2227,6 +2165,14 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "authenc(hmac(sha256),ctr(aes))",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+	}, {
+		.alg = "authenc(hmac(sha256),rfc3686(ctr(aes)))",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+	}, {
 		.alg = "authenc(hmac(sha384),cbc(des))",
 		.test = alg_test_aead,
 		.suite = {
@@ -2242,6 +2188,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 	}, {
 		.alg = "authenc(hmac(sha384),cbc(des3_ede))",
 		.test = alg_test_aead,
+		.fips_allowed = 1,
 		.suite = {
 			.aead = {
 				.enc = {
@@ -2253,7 +2200,16 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "authenc(hmac(sha384),ctr(aes))",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+	}, {
+		.alg = "authenc(hmac(sha384),rfc3686(ctr(aes)))",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+	}, {
 		.alg = "authenc(hmac(sha512),cbc(aes))",
+		.fips_allowed = 1,
 		.test = alg_test_aead,
 		.suite = {
 			.aead = {
@@ -2281,6 +2237,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 	}, {
 		.alg = "authenc(hmac(sha512),cbc(des3_ede))",
 		.test = alg_test_aead,
+		.fips_allowed = 1,
 		.suite = {
 			.aead = {
 				.enc = {
@@ -2292,6 +2249,14 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "authenc(hmac(sha512),ctr(aes))",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+	}, {
+		.alg = "authenc(hmac(sha512),rfc3686(ctr(aes)))",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+	}, {
 		.alg = "cbc(aes)",
 		.test = alg_test_skcipher,
 		.fips_allowed = 1,
@@ -3840,22 +3805,6 @@ static const struct alg_test_desc alg_test_descs[] = {
 				}
 			}
 		}
-	}, {
-		.alg = "zlib",
-		.test = alg_test_pcomp,
-		.fips_allowed = 1,
-		.suite = {
-			.pcomp = {
-				.comp = {
-					.vecs = zlib_comp_tv_template,
-					.count = ZLIB_COMP_TEST_VECTORS
-				},
-				.decomp = {
-					.vecs = zlib_decomp_tv_template,
-					.count = ZLIB_DECOMP_TEST_VECTORS
-				}
-			}
-		}
 	}
 };
 
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index da0a8fd765f4..487ec880e889 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -25,9 +25,6 @@
 #define _CRYPTO_TESTMGR_H
 
 #include <linux/netlink.h>
-#include <linux/zlib.h>
-
-#include <crypto/compress.h>
 
 #define MAX_DIGEST_SIZE		64
 #define MAX_TAP			8
@@ -32268,14 +32265,6 @@ struct comp_testvec {
 	char output[COMP_BUF_SIZE];
 };
 
-struct pcomp_testvec {
-	const void *params;
-	unsigned int paramsize;
-	int inlen, outlen;
-	char input[COMP_BUF_SIZE];
-	char output[COMP_BUF_SIZE];
-};
-
 /*
  * Deflate test vectors (null-terminated strings).
  * Params: winbits=-11, Z_DEFAULT_COMPRESSION, MAX_MEM_LEVEL.
@@ -32356,139 +32345,6 @@ static struct comp_testvec deflate_decomp_tv_template[] = {
 	},
 };
 
-#define ZLIB_COMP_TEST_VECTORS 2
-#define ZLIB_DECOMP_TEST_VECTORS 2
-
-static const struct {
-	struct nlattr nla;
-	int val;
-} deflate_comp_params[] = {
-	{
-		.nla = {
-			.nla_len	= NLA_HDRLEN + sizeof(int),
-			.nla_type	= ZLIB_COMP_LEVEL,
-		},
-		.val			= Z_DEFAULT_COMPRESSION,
-	}, {
-		.nla = {
-			.nla_len	= NLA_HDRLEN + sizeof(int),
-			.nla_type	= ZLIB_COMP_METHOD,
-		},
-		.val			= Z_DEFLATED,
-	}, {
-		.nla = {
-			.nla_len	= NLA_HDRLEN + sizeof(int),
-			.nla_type	= ZLIB_COMP_WINDOWBITS,
-		},
-		.val			= -11,
-	}, {
-		.nla = {
-			.nla_len	= NLA_HDRLEN + sizeof(int),
-			.nla_type	= ZLIB_COMP_MEMLEVEL,
-		},
-		.val			= MAX_MEM_LEVEL,
-	}, {
-		.nla = {
-			.nla_len	= NLA_HDRLEN + sizeof(int),
-			.nla_type	= ZLIB_COMP_STRATEGY,
-		},
-		.val			= Z_DEFAULT_STRATEGY,
-	}
-};
-
-static const struct {
-	struct nlattr nla;
-	int val;
-} deflate_decomp_params[] = {
-	{
-		.nla = {
-			.nla_len	= NLA_HDRLEN + sizeof(int),
-			.nla_type	= ZLIB_DECOMP_WINDOWBITS,
-		},
-		.val			= -11,
-	}
-};
-
-static struct pcomp_testvec zlib_comp_tv_template[] = {
-	{
-		.params = &deflate_comp_params,
-		.paramsize = sizeof(deflate_comp_params),
-		.inlen	= 70,
-		.outlen	= 38,
-		.input	= "Join us now and share the software "
-			"Join us now and share the software ",
-		.output	= "\xf3\xca\xcf\xcc\x53\x28\x2d\x56"
-			  "\xc8\xcb\x2f\x57\x48\xcc\x4b\x51"
-			  "\x28\xce\x48\x2c\x4a\x55\x28\xc9"
-			  "\x48\x55\x28\xce\x4f\x2b\x29\x07"
-			  "\x71\xbc\x08\x2b\x01\x00",
-	}, {
-		.params = &deflate_comp_params,
-		.paramsize = sizeof(deflate_comp_params),
-		.inlen	= 191,
-		.outlen	= 122,
-		.input	= "This document describes a compression method based on the DEFLATE"
-			"compression algorithm.  This document defines the application of "
-			"the DEFLATE algorithm to the IP Payload Compression Protocol.",
-		.output	= "\x5d\x8d\x31\x0e\xc2\x30\x10\x04"
-			  "\xbf\xb2\x2f\xc8\x1f\x10\x04\x09"
-			  "\x89\xc2\x85\x3f\x70\xb1\x2f\xf8"
-			  "\x24\xdb\x67\xd9\x47\xc1\xef\x49"
-			  "\x68\x12\x51\xae\x76\x67\xd6\x27"
-			  "\x19\x88\x1a\xde\x85\xab\x21\xf2"
-			  "\x08\x5d\x16\x1e\x20\x04\x2d\xad"
-			  "\xf3\x18\xa2\x15\x85\x2d\x69\xc4"
-			  "\x42\x83\x23\xb6\x6c\x89\x71\x9b"
-			  "\xef\xcf\x8b\x9f\xcf\x33\xca\x2f"
-			  "\xed\x62\xa9\x4c\x80\xff\x13\xaf"
-			  "\x52\x37\xed\x0e\x52\x6b\x59\x02"
-			  "\xd9\x4e\xe8\x7a\x76\x1d\x02\x98"
-			  "\xfe\x8a\x87\x83\xa3\x4f\x56\x8a"
-			  "\xb8\x9e\x8e\x5c\x57\xd3\xa0\x79"
-			  "\xfa\x02",
-	},
-};
-
-static struct pcomp_testvec zlib_decomp_tv_template[] = {
-	{
-		.params = &deflate_decomp_params,
-		.paramsize = sizeof(deflate_decomp_params),
-		.inlen	= 122,
-		.outlen	= 191,
-		.input	= "\x5d\x8d\x31\x0e\xc2\x30\x10\x04"
-			  "\xbf\xb2\x2f\xc8\x1f\x10\x04\x09"
-			  "\x89\xc2\x85\x3f\x70\xb1\x2f\xf8"
-			  "\x24\xdb\x67\xd9\x47\xc1\xef\x49"
-			  "\x68\x12\x51\xae\x76\x67\xd6\x27"
-			  "\x19\x88\x1a\xde\x85\xab\x21\xf2"
-			  "\x08\x5d\x16\x1e\x20\x04\x2d\xad"
-			  "\xf3\x18\xa2\x15\x85\x2d\x69\xc4"
-			  "\x42\x83\x23\xb6\x6c\x89\x71\x9b"
-			  "\xef\xcf\x8b\x9f\xcf\x33\xca\x2f"
-			  "\xed\x62\xa9\x4c\x80\xff\x13\xaf"
-			  "\x52\x37\xed\x0e\x52\x6b\x59\x02"
-			  "\xd9\x4e\xe8\x7a\x76\x1d\x02\x98"
-			  "\xfe\x8a\x87\x83\xa3\x4f\x56\x8a"
-			  "\xb8\x9e\x8e\x5c\x57\xd3\xa0\x79"
-			  "\xfa\x02",
-		.output	= "This document describes a compression method based on the DEFLATE"
-			"compression algorithm.  This document defines the application of "
-			"the DEFLATE algorithm to the IP Payload Compression Protocol.",
-	}, {
-		.params = &deflate_decomp_params,
-		.paramsize = sizeof(deflate_decomp_params),
-		.inlen	= 38,
-		.outlen	= 70,
-		.input	= "\xf3\xca\xcf\xcc\x53\x28\x2d\x56"
-			  "\xc8\xcb\x2f\x57\x48\xcc\x4b\x51"
-			  "\x28\xce\x48\x2c\x4a\x55\x28\xc9"
-			  "\x48\x55\x28\xce\x4f\x2b\x29\x07"
-			  "\x71\xbc\x08\x2b\x01\x00",
-		.output	= "Join us now and share the software "
-			"Join us now and share the software ",
-	},
-};
-
 /*
  * LZO test vectors (null-terminated strings).
  */
diff --git a/crypto/xts.c b/crypto/xts.c
index f6fd43f100c8..26ba5833b994 100644
--- a/crypto/xts.c
+++ b/crypto/xts.c
@@ -35,16 +35,11 @@ static int setkey(struct crypto_tfm *parent, const u8 *key,
 {
 	struct priv *ctx = crypto_tfm_ctx(parent);
 	struct crypto_cipher *child = ctx->tweak;
-	u32 *flags = &parent->crt_flags;
 	int err;
 
-	/* key consists of keys of equal size concatenated, therefore
-	 * the length must be even */
-	if (keylen % 2) {
-		/* tell the user why there was an error */
-		*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-		return -EINVAL;
-	}
+	err = xts_check_key(parent, key, keylen);
+	if (err)
+		return err;
 
 	/* we need two cipher instances: one to compute the initial 'tweak'
 	 * by encrypting the IV (usually the 'plain' iv) and the other
diff --git a/crypto/zlib.c b/crypto/zlib.c
deleted file mode 100644
index d51a30a29e42..000000000000
--- a/crypto/zlib.c
+++ /dev/null
@@ -1,381 +0,0 @@
-/*
- * Cryptographic API.
- *
- * Zlib algorithm
- *
- * Copyright 2008 Sony Corporation
- *
- * Based on deflate.c, which is
- * Copyright (c) 2003 James Morris <jmorris@intercode.com.au>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * FIXME: deflate transforms will require up to a total of about 436k of kernel
- * memory on i386 (390k for compression, the rest for decompression), as the
- * current zlib kernel code uses a worst case pre-allocation system by default.
- * This needs to be fixed so that the amount of memory required is properly
- * related to the winbits and memlevel parameters.
- */
-
-#define pr_fmt(fmt)	"%s: " fmt, __func__
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/zlib.h>
-#include <linux/vmalloc.h>
-#include <linux/interrupt.h>
-#include <linux/mm.h>
-#include <linux/net.h>
-
-#include <crypto/internal/compress.h>
-
-#include <net/netlink.h>
-
-
-struct zlib_ctx {
-	struct z_stream_s comp_stream;
-	struct z_stream_s decomp_stream;
-	int decomp_windowBits;
-};
-
-
-static void zlib_comp_exit(struct zlib_ctx *ctx)
-{
-	struct z_stream_s *stream = &ctx->comp_stream;
-
-	if (stream->workspace) {
-		zlib_deflateEnd(stream);
-		vfree(stream->workspace);
-		stream->workspace = NULL;
-	}
-}
-
-static void zlib_decomp_exit(struct zlib_ctx *ctx)
-{
-	struct z_stream_s *stream = &ctx->decomp_stream;
-
-	if (stream->workspace) {
-		zlib_inflateEnd(stream);
-		vfree(stream->workspace);
-		stream->workspace = NULL;
-	}
-}
-
-static int zlib_init(struct crypto_tfm *tfm)
-{
-	return 0;
-}
-
-static void zlib_exit(struct crypto_tfm *tfm)
-{
-	struct zlib_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	zlib_comp_exit(ctx);
-	zlib_decomp_exit(ctx);
-}
-
-
-static int zlib_compress_setup(struct crypto_pcomp *tfm, const void *params,
-			       unsigned int len)
-{
-	struct zlib_ctx *ctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
-	struct z_stream_s *stream = &ctx->comp_stream;
-	struct nlattr *tb[ZLIB_COMP_MAX + 1];
-	int window_bits, mem_level;
-	size_t workspacesize;
-	int ret;
-
-	ret = nla_parse(tb, ZLIB_COMP_MAX, params, len, NULL);
-	if (ret)
-		return ret;
-
-	zlib_comp_exit(ctx);
-
-	window_bits = tb[ZLIB_COMP_WINDOWBITS]
-					? nla_get_u32(tb[ZLIB_COMP_WINDOWBITS])
-					: MAX_WBITS;
-	mem_level = tb[ZLIB_COMP_MEMLEVEL]
-					? nla_get_u32(tb[ZLIB_COMP_MEMLEVEL])
-					: DEF_MEM_LEVEL;
-
-	workspacesize = zlib_deflate_workspacesize(window_bits, mem_level);
-	stream->workspace = vzalloc(workspacesize);
-	if (!stream->workspace)
-		return -ENOMEM;
-
-	ret = zlib_deflateInit2(stream,
-				tb[ZLIB_COMP_LEVEL]
-					? nla_get_u32(tb[ZLIB_COMP_LEVEL])
-					: Z_DEFAULT_COMPRESSION,
-				tb[ZLIB_COMP_METHOD]
-					? nla_get_u32(tb[ZLIB_COMP_METHOD])
-					: Z_DEFLATED,
-				window_bits,
-				mem_level,
-				tb[ZLIB_COMP_STRATEGY]
-					? nla_get_u32(tb[ZLIB_COMP_STRATEGY])
-					: Z_DEFAULT_STRATEGY);
-	if (ret != Z_OK) {
-		vfree(stream->workspace);
-		stream->workspace = NULL;
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int zlib_compress_init(struct crypto_pcomp *tfm)
-{
-	int ret;
-	struct zlib_ctx *dctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
-	struct z_stream_s *stream = &dctx->comp_stream;
-
-	ret = zlib_deflateReset(stream);
-	if (ret != Z_OK)
-		return -EINVAL;
-
-	return 0;
-}
-
-static int zlib_compress_update(struct crypto_pcomp *tfm,
-				struct comp_request *req)
-{
-	int ret;
-	struct zlib_ctx *dctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
-	struct z_stream_s *stream = &dctx->comp_stream;
-
-	pr_debug("avail_in %u, avail_out %u\n", req->avail_in, req->avail_out);
-	stream->next_in = req->next_in;
-	stream->avail_in = req->avail_in;
-	stream->next_out = req->next_out;
-	stream->avail_out = req->avail_out;
-
-	ret = zlib_deflate(stream, Z_NO_FLUSH);
-	switch (ret) {
-	case Z_OK:
-		break;
-
-	case Z_BUF_ERROR:
-		pr_debug("zlib_deflate could not make progress\n");
-		return -EAGAIN;
-
-	default:
-		pr_debug("zlib_deflate failed %d\n", ret);
-		return -EINVAL;
-	}
-
-	ret = req->avail_out - stream->avail_out;
-	pr_debug("avail_in %lu, avail_out %lu (consumed %lu, produced %u)\n",
-		 stream->avail_in, stream->avail_out,
-		 req->avail_in - stream->avail_in, ret);
-	req->next_in = stream->next_in;
-	req->avail_in = stream->avail_in;
-	req->next_out = stream->next_out;
-	req->avail_out = stream->avail_out;
-	return ret;
-}
-
-static int zlib_compress_final(struct crypto_pcomp *tfm,
-			       struct comp_request *req)
-{
-	int ret;
-	struct zlib_ctx *dctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
-	struct z_stream_s *stream = &dctx->comp_stream;
-
-	pr_debug("avail_in %u, avail_out %u\n", req->avail_in, req->avail_out);
-	stream->next_in = req->next_in;
-	stream->avail_in = req->avail_in;
-	stream->next_out = req->next_out;
-	stream->avail_out = req->avail_out;
-
-	ret = zlib_deflate(stream, Z_FINISH);
-	if (ret != Z_STREAM_END) {
-		pr_debug("zlib_deflate failed %d\n", ret);
-		return -EINVAL;
-	}
-
-	ret = req->avail_out - stream->avail_out;
-	pr_debug("avail_in %lu, avail_out %lu (consumed %lu, produced %u)\n",
-		 stream->avail_in, stream->avail_out,
-		 req->avail_in - stream->avail_in, ret);
-	req->next_in = stream->next_in;
-	req->avail_in = stream->avail_in;
-	req->next_out = stream->next_out;
-	req->avail_out = stream->avail_out;
-	return ret;
-}
-
-
-static int zlib_decompress_setup(struct crypto_pcomp *tfm, const void *params,
-				 unsigned int len)
-{
-	struct zlib_ctx *ctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
-	struct z_stream_s *stream = &ctx->decomp_stream;
-	struct nlattr *tb[ZLIB_DECOMP_MAX + 1];
-	int ret = 0;
-
-	ret = nla_parse(tb, ZLIB_DECOMP_MAX, params, len, NULL);
-	if (ret)
-		return ret;
-
-	zlib_decomp_exit(ctx);
-
-	ctx->decomp_windowBits = tb[ZLIB_DECOMP_WINDOWBITS]
-				 ? nla_get_u32(tb[ZLIB_DECOMP_WINDOWBITS])
-				 : DEF_WBITS;
-
-	stream->workspace = vzalloc(zlib_inflate_workspacesize());
-	if (!stream->workspace)
-		return -ENOMEM;
-
-	ret = zlib_inflateInit2(stream, ctx->decomp_windowBits);
-	if (ret != Z_OK) {
-		vfree(stream->workspace);
-		stream->workspace = NULL;
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int zlib_decompress_init(struct crypto_pcomp *tfm)
-{
-	int ret;
-	struct zlib_ctx *dctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
-	struct z_stream_s *stream = &dctx->decomp_stream;
-
-	ret = zlib_inflateReset(stream);
-	if (ret != Z_OK)
-		return -EINVAL;
-
-	return 0;
-}
-
-static int zlib_decompress_update(struct crypto_pcomp *tfm,
-				  struct comp_request *req)
-{
-	int ret;
-	struct zlib_ctx *dctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
-	struct z_stream_s *stream = &dctx->decomp_stream;
-
-	pr_debug("avail_in %u, avail_out %u\n", req->avail_in, req->avail_out);
-	stream->next_in = req->next_in;
-	stream->avail_in = req->avail_in;
-	stream->next_out = req->next_out;
-	stream->avail_out = req->avail_out;
-
-	ret = zlib_inflate(stream, Z_SYNC_FLUSH);
-	switch (ret) {
-	case Z_OK:
-	case Z_STREAM_END:
-		break;
-
-	case Z_BUF_ERROR:
-		pr_debug("zlib_inflate could not make progress\n");
-		return -EAGAIN;
-
-	default:
-		pr_debug("zlib_inflate failed %d\n", ret);
-		return -EINVAL;
-	}
-
-	ret = req->avail_out - stream->avail_out;
-	pr_debug("avail_in %lu, avail_out %lu (consumed %lu, produced %u)\n",
-		 stream->avail_in, stream->avail_out,
-		 req->avail_in - stream->avail_in, ret);
-	req->next_in = stream->next_in;
-	req->avail_in = stream->avail_in;
-	req->next_out = stream->next_out;
-	req->avail_out = stream->avail_out;
-	return ret;
-}
-
-static int zlib_decompress_final(struct crypto_pcomp *tfm,
-				 struct comp_request *req)
-{
-	int ret;
-	struct zlib_ctx *dctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
-	struct z_stream_s *stream = &dctx->decomp_stream;
-
-	pr_debug("avail_in %u, avail_out %u\n", req->avail_in, req->avail_out);
-	stream->next_in = req->next_in;
-	stream->avail_in = req->avail_in;
-	stream->next_out = req->next_out;
-	stream->avail_out = req->avail_out;
-
-	if (dctx->decomp_windowBits < 0) {
-		ret = zlib_inflate(stream, Z_SYNC_FLUSH);
-		/*
-		 * Work around a bug in zlib, which sometimes wants to taste an
-		 * extra byte when being used in the (undocumented) raw deflate
-		 * mode. (From USAGI).
-		 */
-		if (ret == Z_OK && !stream->avail_in && stream->avail_out) {
-			const void *saved_next_in = stream->next_in;
-			u8 zerostuff = 0;
-
-			stream->next_in = &zerostuff;
-			stream->avail_in = 1;
-			ret = zlib_inflate(stream, Z_FINISH);
-			stream->next_in = saved_next_in;
-			stream->avail_in = 0;
-		}
-	} else
-		ret = zlib_inflate(stream, Z_FINISH);
-	if (ret != Z_STREAM_END) {
-		pr_debug("zlib_inflate failed %d\n", ret);
-		return -EINVAL;
-	}
-
-	ret = req->avail_out - stream->avail_out;
-	pr_debug("avail_in %lu, avail_out %lu (consumed %lu, produced %u)\n",
-		 stream->avail_in, stream->avail_out,
-		 req->avail_in - stream->avail_in, ret);
-	req->next_in = stream->next_in;
-	req->avail_in = stream->avail_in;
-	req->next_out = stream->next_out;
-	req->avail_out = stream->avail_out;
-	return ret;
-}
-
-
-static struct pcomp_alg zlib_alg = {
-	.compress_setup		= zlib_compress_setup,
-	.compress_init		= zlib_compress_init,
-	.compress_update	= zlib_compress_update,
-	.compress_final		= zlib_compress_final,
-	.decompress_setup	= zlib_decompress_setup,
-	.decompress_init	= zlib_decompress_init,
-	.decompress_update	= zlib_decompress_update,
-	.decompress_final	= zlib_decompress_final,
-
-	.base			= {
-		.cra_name	= "zlib",
-		.cra_flags	= CRYPTO_ALG_TYPE_PCOMPRESS,
-		.cra_ctxsize	= sizeof(struct zlib_ctx),
-		.cra_module	= THIS_MODULE,
-		.cra_init	= zlib_init,
-		.cra_exit	= zlib_exit,
-	}
-};
-
-static int __init zlib_mod_init(void)
-{
-	return crypto_register_pcomp(&zlib_alg);
-}
-
-static void __exit zlib_mod_fini(void)
-{
-	crypto_unregister_pcomp(&zlib_alg);
-}
-
-module_init(zlib_mod_init);
-module_exit(zlib_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Zlib Compression Algorithm");
-MODULE_AUTHOR("Sony Corporation");
-MODULE_ALIAS_CRYPTO("zlib");
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index cb648a49543a..edeb2d1d99be 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -43,6 +43,7 @@ acpi-y				+= pci_root.o pci_link.o pci_irq.o
 acpi-y				+= acpi_lpss.o acpi_apd.o
 acpi-y				+= acpi_platform.o
 acpi-y				+= acpi_pnp.o
+acpi-$(CONFIG_ARM_AMBA)	+= acpi_amba.o
 acpi-y				+= int340x_thermal.o
 acpi-y				+= power.o
 acpi-y				+= event.o
diff --git a/drivers/acpi/acpi_amba.c b/drivers/acpi/acpi_amba.c
new file mode 100644
index 000000000000..2a61b54ab968
--- /dev/null
+++ b/drivers/acpi/acpi_amba.c
@@ -0,0 +1,122 @@
+
+/*
+ * ACPI support for platform bus type.
+ *
+ * Copyright (C) 2015, Linaro Ltd
+ * Author: Graeme Gregory <graeme.gregory@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/acpi.h>
+#include <linux/amba/bus.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/ioport.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include "internal.h"
+
+static const struct acpi_device_id amba_id_list[] = {
+	{"ARMH0061", 0}, /* PL061 GPIO Device */
+	{"", 0},
+};
+
+static void amba_register_dummy_clk(void)
+{
+	static struct clk *amba_dummy_clk;
+
+	/* If clock already registered */
+	if (amba_dummy_clk)
+		return;
+
+	amba_dummy_clk = clk_register_fixed_rate(NULL, "apb_pclk", NULL,
+						CLK_IS_ROOT, 0);
+	clk_register_clkdev(amba_dummy_clk, "apb_pclk", NULL);
+}
+
+static int amba_handler_attach(struct acpi_device *adev,
+				const struct acpi_device_id *id)
+{
+	struct amba_device *dev;
+	struct resource_entry *rentry;
+	struct list_head resource_list;
+	bool address_found = false;
+	int irq_no = 0;
+	int ret;
+
+	/* If the ACPI node already has a physical device attached, skip it. */
+	if (adev->physical_node_count)
+		return 0;
+
+	dev = amba_device_alloc(dev_name(&adev->dev), 0, 0);
+	if (!dev) {
+		dev_err(&adev->dev, "%s(): amba_device_alloc() failed\n",
+			__func__);
+		return -ENOMEM;
+	}
+
+	INIT_LIST_HEAD(&resource_list);
+	ret = acpi_dev_get_resources(adev, &resource_list, NULL, NULL);
+	if (ret < 0)
+		goto err_free;
+
+	list_for_each_entry(rentry, &resource_list, node) {
+		switch (resource_type(rentry->res)) {
+		case IORESOURCE_MEM:
+			if (!address_found) {
+				dev->res = *rentry->res;
+				address_found = true;
+			}
+			break;
+		case IORESOURCE_IRQ:
+			if (irq_no < AMBA_NR_IRQS)
+				dev->irq[irq_no++] = rentry->res->start;
+			break;
+		default:
+			dev_warn(&adev->dev, "Invalid resource\n");
+			break;
+		}
+	}
+
+	acpi_dev_free_resource_list(&resource_list);
+
+	/*
+	 * If the ACPI node has a parent and that parent has a physical device
+	 * attached to it, that physical device should be the parent of
+	 * the amba device we are about to create.
+	 */
+	if (adev->parent)
+		dev->dev.parent = acpi_get_first_physical_node(adev->parent);
+
+	ACPI_COMPANION_SET(&dev->dev, adev);
+
+	ret = amba_device_add(dev, &iomem_resource);
+	if (ret) {
+		dev_err(&adev->dev, "%s(): amba_device_add() failed (%d)\n",
+		       __func__, ret);
+		goto err_free;
+	}
+
+	return 1;
+
+err_free:
+	amba_device_put(dev);
+	return ret;
+}
+
+static struct acpi_scan_handler amba_handler = {
+	.ids = amba_id_list,
+	.attach = amba_handler_attach,
+};
+
+void __init acpi_amba_init(void)
+{
+	amba_register_dummy_clk();
+	acpi_scan_add_handler(&amba_handler);
+}
diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c
index d507cf6deda0..d0aad06b3872 100644
--- a/drivers/acpi/acpi_apd.c
+++ b/drivers/acpi/acpi_apd.c
@@ -143,6 +143,7 @@ static const struct acpi_device_id acpi_apd_device_ids[] = {
 	/* Generic apd devices */
 #ifdef CONFIG_X86_AMD_PLATFORM_DEVICE
 	{ "AMD0010", APD_ADDR(cz_i2c_desc) },
+	{ "AMDI0010", APD_ADDR(cz_i2c_desc) },
 	{ "AMD0020", APD_ADDR(cz_uart_desc) },
 	{ "AMD0030", },
 #endif
diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c
index 296b7a14893a..159f7f19abce 100644
--- a/drivers/acpi/acpi_platform.c
+++ b/drivers/acpi/acpi_platform.c
@@ -43,7 +43,6 @@ static const struct acpi_device_id forbidden_id_list[] = {
 struct platform_device *acpi_create_platform_device(struct acpi_device *adev)
 {
 	struct platform_device *pdev = NULL;
-	struct acpi_device *acpi_parent;
 	struct platform_device_info pdevinfo;
 	struct resource_entry *rentry;
 	struct list_head resource_list;
@@ -62,7 +61,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev)
 	if (count < 0) {
 		return NULL;
 	} else if (count > 0) {
-		resources = kmalloc(count * sizeof(struct resource),
+		resources = kzalloc(count * sizeof(struct resource),
 				    GFP_KERNEL);
 		if (!resources) {
 			dev_err(&adev->dev, "No memory for resources\n");
@@ -82,22 +81,8 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev)
 	 * attached to it, that physical device should be the parent of the
 	 * platform device we are about to create.
 	 */
-	pdevinfo.parent = NULL;
-	acpi_parent = adev->parent;
-	if (acpi_parent) {
-		struct acpi_device_physical_node *entry;
-		struct list_head *list;
-
-		mutex_lock(&acpi_parent->physical_node_lock);
-		list = &acpi_parent->physical_node_list;
-		if (!list_empty(list)) {
-			entry = list_first_entry(list,
-					struct acpi_device_physical_node,
-					node);
-			pdevinfo.parent = entry->dev;
-		}
-		mutex_unlock(&acpi_parent->physical_node_lock);
-	}
+	pdevinfo.parent = adev->parent ?
+		acpi_get_first_physical_node(adev->parent) : NULL;
 	pdevinfo.name = dev_name(&adev->dev);
 	pdevinfo.id = -1;
 	pdevinfo.res = resources;
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 6979186dbd4b..b5e54f2da53d 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -514,7 +514,24 @@ static struct acpi_scan_handler processor_handler = {
 	},
 };
 
+static int acpi_processor_container_attach(struct acpi_device *dev,
+					   const struct acpi_device_id *id)
+{
+	return 1;
+}
+
+static const struct acpi_device_id processor_container_ids[] = {
+	{ ACPI_PROCESSOR_CONTAINER_HID, },
+	{ }
+};
+
+static struct acpi_scan_handler processor_container_handler = {
+	.ids = processor_container_ids,
+	.attach = acpi_processor_container_attach,
+};
+
 void __init acpi_processor_init(void)
 {
 	acpi_scan_add_handler_with_hotplug(&processor_handler, "processor");
+	acpi_scan_add_handler(&processor_container_handler);
 }
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index a76f8be1bfe7..4361bc98ef4c 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -218,13 +218,6 @@ struct acpi_video_device {
 	struct thermal_cooling_device *cooling_dev;
 };
 
-static const char device_decode[][30] = {
-	"motherboard VGA device",
-	"PCI VGA device",
-	"AGP VGA device",
-	"UNKNOWN",
-};
-
 static void acpi_video_device_notify(acpi_handle handle, u32 event, void *data);
 static void acpi_video_device_rebind(struct acpi_video_bus *video);
 static void acpi_video_device_bind(struct acpi_video_bus *video,
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index 55c8197036f3..51b073b68f16 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -165,7 +165,7 @@ ACPI_GLOBAL(u8, acpi_gbl_next_owner_id_offset);
 
 /* Initialization sequencing */
 
-ACPI_INIT_GLOBAL(u8, acpi_gbl_reg_methods_enabled, FALSE);
+ACPI_INIT_GLOBAL(u8, acpi_gbl_namespace_initialized, FALSE);
 
 /* Misc */
 
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index e4977fac9c1d..9562a10a1a18 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -85,7 +85,7 @@ union acpi_parse_object;
 #define ACPI_MTX_MEMORY                 5	/* Debug memory tracking lists */
 
 #define ACPI_MAX_MUTEX                  5
-#define ACPI_NUM_MUTEX                  ACPI_MAX_MUTEX+1
+#define ACPI_NUM_MUTEX                  (ACPI_MAX_MUTEX+1)
 
 /* Lock structure for reader/writer interfaces */
 
@@ -103,11 +103,11 @@ struct acpi_rw_lock {
 #define ACPI_LOCK_HARDWARE              1
 
 #define ACPI_MAX_LOCK                   1
-#define ACPI_NUM_LOCK                   ACPI_MAX_LOCK+1
+#define ACPI_NUM_LOCK                   (ACPI_MAX_LOCK+1)
 
 /* This Thread ID means that the mutex is not in use (unlocked) */
 
-#define ACPI_MUTEX_NOT_ACQUIRED         (acpi_thread_id) 0
+#define ACPI_MUTEX_NOT_ACQUIRED         ((acpi_thread_id) 0)
 
 /* This Thread ID means an invalid thread ID */
 
diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h
index 9684ed61284d..022d69cb345a 100644
--- a/drivers/acpi/acpica/acnamesp.h
+++ b/drivers/acpi/acpica/acnamesp.h
@@ -88,7 +88,7 @@
  */
 acpi_status acpi_ns_initialize_objects(void);
 
-acpi_status acpi_ns_initialize_devices(void);
+acpi_status acpi_ns_initialize_devices(u32 flags);
 
 /*
  * nsload -  Namespace loading
diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h
index 52f6bee52d47..5faeab41e302 100644
--- a/drivers/acpi/acpica/acpredef.h
+++ b/drivers/acpi/acpica/acpredef.h
@@ -1125,7 +1125,7 @@ const union acpi_predefined_info acpi_gbl_resource_names[] = {
 	PACKAGE_INFO(0, 0, 0, 0, 0, 0)	/* Table terminator */
 };
 
-static const union acpi_predefined_info acpi_gbl_scope_names[] = {
+const union acpi_predefined_info acpi_gbl_scope_names[] = {
 	{{"_GPE", 0, 0}},
 	{{"_PR_", 0, 0}},
 	{{"_SB_", 0, 0}},
diff --git a/drivers/acpi/acpica/dbcmds.c b/drivers/acpi/acpica/dbcmds.c
index 7ec62c461280..772178c96ccf 100644
--- a/drivers/acpi/acpica/dbcmds.c
+++ b/drivers/acpi/acpica/dbcmds.c
@@ -348,7 +348,7 @@ void acpi_db_display_table_info(char *table_arg)
 		} else {
 			/* If the pointer is null, the table has been unloaded */
 
-			ACPI_INFO((AE_INFO, "%4.4s - Table has been unloaded",
+			ACPI_INFO(("%4.4s - Table has been unloaded",
 				   table_desc->signature.ascii));
 		}
 	}
diff --git a/drivers/acpi/acpica/dbconvert.c b/drivers/acpi/acpica/dbconvert.c
index 9fee88f1c654..68f4e0f4b095 100644
--- a/drivers/acpi/acpica/dbconvert.c
+++ b/drivers/acpi/acpica/dbconvert.c
@@ -408,7 +408,7 @@ void acpi_db_dump_pld_buffer(union acpi_object *obj_desc)
 
 	new_buffer = acpi_db_encode_pld_buffer(pld_info);
 	if (!new_buffer) {
-		return;
+		goto exit;
 	}
 
 	/* The two bit-packed buffers should match */
@@ -479,6 +479,7 @@ void acpi_db_dump_pld_buffer(union acpi_object *obj_desc)
 			       pld_info->horizontal_offset);
 	}
 
-	ACPI_FREE(pld_info);
 	ACPI_FREE(new_buffer);
+exit:
+	ACPI_FREE(pld_info);
 }
diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c
index 6a72047aae1c..1982310e6d83 100644
--- a/drivers/acpi/acpica/dsmethod.c
+++ b/drivers/acpi/acpica/dsmethod.c
@@ -809,8 +809,7 @@ acpi_ds_terminate_control_method(union acpi_operand_object *method_desc,
 		if (method_desc->method.
 		    info_flags & ACPI_METHOD_SERIALIZED_PENDING) {
 			if (walk_state) {
-				ACPI_INFO((AE_INFO,
-					   "Marking method %4.4s as Serialized "
+				ACPI_INFO(("Marking method %4.4s as Serialized "
 					   "because of AE_ALREADY_EXISTS error",
 					   walk_state->method_node->name.
 					   ascii));
diff --git a/drivers/acpi/acpica/dsobject.c b/drivers/acpi/acpica/dsobject.c
index c303e9d9266f..a91de2b4603c 100644
--- a/drivers/acpi/acpica/dsobject.c
+++ b/drivers/acpi/acpica/dsobject.c
@@ -524,8 +524,7 @@ acpi_ds_build_internal_package_obj(struct acpi_walk_state *walk_state,
 			arg = arg->common.next;
 		}
 
-		ACPI_INFO((AE_INFO,
-			   "Actual Package length (%u) is larger than "
+		ACPI_INFO(("Actual Package length (%u) is larger than "
 			   "NumElements field (%u), truncated",
 			   i, element_count));
 	} else if (i < element_count) {
diff --git a/drivers/acpi/acpica/evgpeblk.c b/drivers/acpi/acpica/evgpeblk.c
index 9275e626ed8d..447fa1cac64f 100644
--- a/drivers/acpi/acpica/evgpeblk.c
+++ b/drivers/acpi/acpica/evgpeblk.c
@@ -499,8 +499,7 @@ acpi_ev_initialize_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 	}
 
 	if (gpe_enabled_count) {
-		ACPI_INFO((AE_INFO,
-			   "Enabled %u GPEs in block %02X to %02X",
+		ACPI_INFO(("Enabled %u GPEs in block %02X to %02X",
 			   gpe_enabled_count, (u32)gpe_block->block_base_number,
 			   (u32)(gpe_block->block_base_number +
 				 (gpe_block->gpe_count - 1))));
diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c
index 9fdd8d09141b..7dc75474c897 100644
--- a/drivers/acpi/acpica/evgpeinit.c
+++ b/drivers/acpi/acpica/evgpeinit.c
@@ -281,7 +281,7 @@ void acpi_ev_update_gpes(acpi_owner_id table_owner_id)
 	}
 
 	if (walk_info.count) {
-		ACPI_INFO((AE_INFO, "Enabled %u new GPEs", walk_info.count));
+		ACPI_INFO(("Enabled %u new GPEs", walk_info.count));
 	}
 
 	(void)acpi_ut_release_mutex(ACPI_MTX_EVENTS);
diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c
index 47092b4d633c..63924d1c737a 100644
--- a/drivers/acpi/acpica/evregion.c
+++ b/drivers/acpi/acpica/evregion.c
@@ -600,7 +600,7 @@ acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function)
 
 	if (region_obj2->extra.method_REG == NULL ||
 	    region_obj->region.handler == NULL ||
-	    !acpi_gbl_reg_methods_enabled) {
+	    !acpi_gbl_namespace_initialized) {
 		return_ACPI_STATUS(AE_OK);
 	}
 
diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c
index 011df210b7b2..f74161301037 100644
--- a/drivers/acpi/acpica/exconfig.c
+++ b/drivers/acpi/acpica/exconfig.c
@@ -252,7 +252,7 @@ acpi_ex_load_table_op(struct acpi_walk_state *walk_state,
 
 	status = acpi_get_table_by_index(table_index, &table);
 	if (ACPI_SUCCESS(status)) {
-		ACPI_INFO((AE_INFO, "Dynamic OEM Table Load:"));
+		ACPI_INFO(("Dynamic OEM Table Load:"));
 		acpi_tb_print_table_header(0, table);
 	}
 
@@ -472,7 +472,7 @@ acpi_ex_load_op(union acpi_operand_object *obj_desc,
 
 	/* Install the new table into the local data structures */
 
-	ACPI_INFO((AE_INFO, "Dynamic OEM Table Load:"));
+	ACPI_INFO(("Dynamic OEM Table Load:"));
 	(void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES);
 
 	status = acpi_tb_install_standard_table(ACPI_PTR_TO_PHYSADDR(table),
diff --git a/drivers/acpi/acpica/exoparg3.c b/drivers/acpi/acpica/exoparg3.c
index 28eb861c44eb..5aa21c4eda1d 100644
--- a/drivers/acpi/acpica/exoparg3.c
+++ b/drivers/acpi/acpica/exoparg3.c
@@ -123,8 +123,10 @@ acpi_status acpi_ex_opcode_3A_0T_0R(struct acpi_walk_state *walk_state)
 		 * op is intended for use by disassemblers in order to properly
 		 * disassemble control method invocations. The opcode or group of
 		 * opcodes should be surrounded by an "if (0)" clause to ensure that
-		 * AML interpreters never see the opcode.
+		 * AML interpreters never see the opcode. Thus, something is
+		 * wrong if an external opcode ever gets here.
 		 */
+		ACPI_ERROR((AE_INFO, "Executed External Op"));
 		status = AE_OK;
 		goto cleanup;
 
diff --git a/drivers/acpi/acpica/nseval.c b/drivers/acpi/acpica/nseval.c
index 65d58bea4320..5d59cfcef6f4 100644
--- a/drivers/acpi/acpica/nseval.c
+++ b/drivers/acpi/acpica/nseval.c
@@ -378,8 +378,7 @@ void acpi_ns_exec_module_code_list(void)
 		acpi_ut_remove_reference(prev);
 	}
 
-	ACPI_INFO((AE_INFO,
-		   "Executed %u blocks of module-level executable AML code",
+	ACPI_INFO(("Executed %u blocks of module-level executable AML code",
 		   method_count));
 
 	ACPI_FREE(info);
diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c
index bd75d46234a4..d4aa8b696ee9 100644
--- a/drivers/acpi/acpica/nsinit.c
+++ b/drivers/acpi/acpica/nsinit.c
@@ -46,6 +46,7 @@
 #include "acnamesp.h"
 #include "acdispat.h"
 #include "acinterp.h"
+#include "acevents.h"
 
 #define _COMPONENT          ACPI_NAMESPACE
 ACPI_MODULE_NAME("nsinit")
@@ -83,6 +84,8 @@ acpi_status acpi_ns_initialize_objects(void)
 
 	ACPI_FUNCTION_TRACE(ns_initialize_objects);
 
+	ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
+			  "[Init] Completing Initialization of ACPI Objects\n"));
 	ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH,
 			  "**** Starting initialization of namespace objects ****\n"));
 	ACPI_DEBUG_PRINT_RAW((ACPI_DB_INIT,
@@ -133,82 +136,108 @@ acpi_status acpi_ns_initialize_objects(void)
  *
  ******************************************************************************/
 
-acpi_status acpi_ns_initialize_devices(void)
+acpi_status acpi_ns_initialize_devices(u32 flags)
 {
-	acpi_status status;
+	acpi_status status = AE_OK;
 	struct acpi_device_walk_info info;
 
 	ACPI_FUNCTION_TRACE(ns_initialize_devices);
 
-	/* Init counters */
+	if (!(flags & ACPI_NO_DEVICE_INIT)) {
+		ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
+				  "[Init] Initializing ACPI Devices\n"));
 
-	info.device_count = 0;
-	info.num_STA = 0;
-	info.num_INI = 0;
+		/* Init counters */
 
-	ACPI_DEBUG_PRINT_RAW((ACPI_DB_INIT,
-			      "Initializing Device/Processor/Thermal objects "
-			      "and executing _INI/_STA methods:\n"));
+		info.device_count = 0;
+		info.num_STA = 0;
+		info.num_INI = 0;
 
-	/* Tree analysis: find all subtrees that contain _INI methods */
+		ACPI_DEBUG_PRINT_RAW((ACPI_DB_INIT,
+				      "Initializing Device/Processor/Thermal objects "
+				      "and executing _INI/_STA methods:\n"));
 
-	status = acpi_ns_walk_namespace(ACPI_TYPE_ANY, ACPI_ROOT_OBJECT,
-					ACPI_UINT32_MAX, FALSE,
-					acpi_ns_find_ini_methods, NULL, &info,
-					NULL);
-	if (ACPI_FAILURE(status)) {
-		goto error_exit;
-	}
+		/* Tree analysis: find all subtrees that contain _INI methods */
+
+		status = acpi_ns_walk_namespace(ACPI_TYPE_ANY, ACPI_ROOT_OBJECT,
+						ACPI_UINT32_MAX, FALSE,
+						acpi_ns_find_ini_methods, NULL,
+						&info, NULL);
+		if (ACPI_FAILURE(status)) {
+			goto error_exit;
+		}
+
+		/* Allocate the evaluation information block */
 
-	/* Allocate the evaluation information block */
+		info.evaluate_info =
+		    ACPI_ALLOCATE_ZEROED(sizeof(struct acpi_evaluate_info));
+		if (!info.evaluate_info) {
+			status = AE_NO_MEMORY;
+			goto error_exit;
+		}
 
-	info.evaluate_info =
-	    ACPI_ALLOCATE_ZEROED(sizeof(struct acpi_evaluate_info));
-	if (!info.evaluate_info) {
-		status = AE_NO_MEMORY;
-		goto error_exit;
+		/*
+		 * Execute the "global" _INI method that may appear at the root.
+		 * This support is provided for Windows compatibility (Vista+) and
+		 * is not part of the ACPI specification.
+		 */
+		info.evaluate_info->prefix_node = acpi_gbl_root_node;
+		info.evaluate_info->relative_pathname = METHOD_NAME__INI;
+		info.evaluate_info->parameters = NULL;
+		info.evaluate_info->flags = ACPI_IGNORE_RETURN_VALUE;
+
+		status = acpi_ns_evaluate(info.evaluate_info);
+		if (ACPI_SUCCESS(status)) {
+			info.num_INI++;
+		}
 	}
 
 	/*
-	 * Execute the "global" _INI method that may appear at the root. This
-	 * support is provided for Windows compatibility (Vista+) and is not
-	 * part of the ACPI specification.
+	 * Run all _REG methods
+	 *
+	 * Note: Any objects accessed by the _REG methods will be automatically
+	 * initialized, even if they contain executable AML (see the call to
+	 * acpi_ns_initialize_objects below).
 	 */
-	info.evaluate_info->prefix_node = acpi_gbl_root_node;
-	info.evaluate_info->relative_pathname = METHOD_NAME__INI;
-	info.evaluate_info->parameters = NULL;
-	info.evaluate_info->flags = ACPI_IGNORE_RETURN_VALUE;
+	if (!(flags & ACPI_NO_ADDRESS_SPACE_INIT)) {
+		ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
+				  "[Init] Executing _REG OpRegion methods\n"));
 
-	status = acpi_ns_evaluate(info.evaluate_info);
-	if (ACPI_SUCCESS(status)) {
-		info.num_INI++;
+		status = acpi_ev_initialize_op_regions();
+		if (ACPI_FAILURE(status)) {
+			goto error_exit;
+		}
 	}
 
-	/* Walk namespace to execute all _INIs on present devices */
+	if (!(flags & ACPI_NO_DEVICE_INIT)) {
 
-	status = acpi_ns_walk_namespace(ACPI_TYPE_ANY, ACPI_ROOT_OBJECT,
-					ACPI_UINT32_MAX, FALSE,
-					acpi_ns_init_one_device, NULL, &info,
-					NULL);
+		/* Walk namespace to execute all _INIs on present devices */
 
-	/*
-	 * Any _OSI requests should be completed by now. If the BIOS has
-	 * requested any Windows OSI strings, we will always truncate
-	 * I/O addresses to 16 bits -- for Windows compatibility.
-	 */
-	if (acpi_gbl_osi_data >= ACPI_OSI_WIN_2000) {
-		acpi_gbl_truncate_io_addresses = TRUE;
-	}
+		status = acpi_ns_walk_namespace(ACPI_TYPE_ANY, ACPI_ROOT_OBJECT,
+						ACPI_UINT32_MAX, FALSE,
+						acpi_ns_init_one_device, NULL,
+						&info, NULL);
 
-	ACPI_FREE(info.evaluate_info);
-	if (ACPI_FAILURE(status)) {
-		goto error_exit;
-	}
+		/*
+		 * Any _OSI requests should be completed by now. If the BIOS has
+		 * requested any Windows OSI strings, we will always truncate
+		 * I/O addresses to 16 bits -- for Windows compatibility.
+		 */
+		if (acpi_gbl_osi_data >= ACPI_OSI_WIN_2000) {
+			acpi_gbl_truncate_io_addresses = TRUE;
+		}
 
-	ACPI_DEBUG_PRINT_RAW((ACPI_DB_INIT,
-			      "    Executed %u _INI methods requiring %u _STA executions "
-			      "(examined %u objects)\n",
-			      info.num_INI, info.num_STA, info.device_count));
+		ACPI_FREE(info.evaluate_info);
+		if (ACPI_FAILURE(status)) {
+			goto error_exit;
+		}
+
+		ACPI_DEBUG_PRINT_RAW((ACPI_DB_INIT,
+				      "    Executed %u _INI methods requiring %u _STA executions "
+				      "(examined %u objects)\n",
+				      info.num_INI, info.num_STA,
+				      info.device_count));
+	}
 
 	return_ACPI_STATUS(status);
 
diff --git a/drivers/acpi/acpica/psargs.c b/drivers/acpi/acpica/psargs.c
index 305218539df2..d48cbed342c1 100644
--- a/drivers/acpi/acpica/psargs.c
+++ b/drivers/acpi/acpica/psargs.c
@@ -269,8 +269,7 @@ acpi_ps_get_next_namepath(struct acpi_walk_state *walk_state,
 	 */
 	if (ACPI_SUCCESS(status) &&
 	    possible_method_call && (node->type == ACPI_TYPE_METHOD)) {
-		if (GET_CURRENT_ARG_TYPE(walk_state->arg_types) ==
-		    ARGP_SUPERNAME) {
+		if (walk_state->opcode == AML_UNLOAD_OP) {
 			/*
 			 * acpi_ps_get_next_namestring has increased the AML pointer,
 			 * so we need to restore the saved AML pointer for method call.
@@ -697,7 +696,7 @@ static union acpi_parse_object *acpi_ps_get_next_field(struct acpi_parse_state
  *
  * PARAMETERS:  walk_state          - Current state
  *              parser_state        - Current parser state object
- *              arg_type            - The parser argument type (ARGP_*)
+ *              arg_type            - The argument type (AML_*_ARG)
  *              return_arg          - Where the next arg is returned
  *
  * RETURN:      Status, and an op object containing the next argument.
@@ -817,9 +816,9 @@ acpi_ps_get_next_arg(struct acpi_walk_state *walk_state,
 				return_ACPI_STATUS(AE_NO_MEMORY);
 			}
 
-			/* super_name allows argument to be a method call */
+			/* To support super_name arg of Unload */
 
-			if (arg_type == ARGP_SUPERNAME) {
+			if (walk_state->opcode == AML_UNLOAD_OP) {
 				status =
 				    acpi_ps_get_next_namepath(walk_state,
 							      parser_state, arg,
diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c
index b661a1e013fb..4dc6108de4ff 100644
--- a/drivers/acpi/acpica/tbinstal.c
+++ b/drivers/acpi/acpica/tbinstal.c
@@ -267,8 +267,7 @@ acpi_tb_install_standard_table(acpi_physical_address address,
 	if (!reload &&
 	    acpi_gbl_disable_ssdt_table_install &&
 	    ACPI_COMPARE_NAME(&new_table_desc.signature, ACPI_SIG_SSDT)) {
-		ACPI_INFO((AE_INFO,
-			   "Ignoring installation of %4.4s at %8.8X%8.8X",
+		ACPI_INFO(("Ignoring installation of %4.4s at %8.8X%8.8X",
 			   new_table_desc.signature.ascii,
 			   ACPI_FORMAT_UINT64(address)));
 		goto release_and_exit;
@@ -432,7 +431,7 @@ finish_override:
 		return;
 	}
 
-	ACPI_INFO((AE_INFO, "%4.4s 0x%8.8X%8.8X"
+	ACPI_INFO(("%4.4s 0x%8.8X%8.8X"
 		   " %s table override, new table: 0x%8.8X%8.8X",
 		   old_table_desc->signature.ascii,
 		   ACPI_FORMAT_UINT64(old_table_desc->address),
diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c
index fd4146d4ff49..26d61dbace0a 100644
--- a/drivers/acpi/acpica/tbprint.c
+++ b/drivers/acpi/acpica/tbprint.c
@@ -132,7 +132,7 @@ acpi_tb_print_table_header(acpi_physical_address address,
 
 		/* FACS only has signature and length fields */
 
-		ACPI_INFO((AE_INFO, "%-4.4s 0x%8.8X%8.8X %06X",
+		ACPI_INFO(("%-4.4s 0x%8.8X%8.8X %06X",
 			   header->signature, ACPI_FORMAT_UINT64(address),
 			   header->length));
 	} else if (ACPI_VALIDATE_RSDP_SIG(header->signature)) {
@@ -144,7 +144,7 @@ acpi_tb_print_table_header(acpi_physical_address address,
 		       ACPI_OEM_ID_SIZE);
 		acpi_tb_fix_string(local_header.oem_id, ACPI_OEM_ID_SIZE);
 
-		ACPI_INFO((AE_INFO, "RSDP 0x%8.8X%8.8X %06X (v%.2d %-6.6s)",
+		ACPI_INFO(("RSDP 0x%8.8X%8.8X %06X (v%.2d %-6.6s)",
 			   ACPI_FORMAT_UINT64(address),
 			   (ACPI_CAST_PTR(struct acpi_table_rsdp, header)->
 			    revision >
@@ -158,8 +158,7 @@ acpi_tb_print_table_header(acpi_physical_address address,
 
 		acpi_tb_cleanup_table_header(&local_header, header);
 
-		ACPI_INFO((AE_INFO,
-			   "%-4.4s 0x%8.8X%8.8X"
+		ACPI_INFO(("%-4.4s 0x%8.8X%8.8X"
 			   " %06X (v%.2d %-6.6s %-8.8s %08X %-4.4s %08X)",
 			   local_header.signature, ACPI_FORMAT_UINT64(address),
 			   local_header.length, local_header.revision,
diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c
index 3269bef371d7..9240c76d2823 100644
--- a/drivers/acpi/acpica/tbutils.c
+++ b/drivers/acpi/acpica/tbutils.c
@@ -174,9 +174,7 @@ struct acpi_table_header *acpi_tb_copy_dsdt(u32 table_index)
 				      ACPI_TABLE_ORIGIN_INTERNAL_VIRTUAL,
 				      new_table);
 
-	ACPI_INFO((AE_INFO,
-		   "Forced DSDT copy: length 0x%05X copied locally, original unmapped",
-		   new_table->length));
+	ACPI_INFO(("Forced DSDT copy: length 0x%05X copied locally, original unmapped", new_table->length));
 
 	return (new_table);
 }
diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c
index 278666e39563..3151968c10d1 100644
--- a/drivers/acpi/acpica/tbxfload.c
+++ b/drivers/acpi/acpica/tbxfload.c
@@ -47,6 +47,7 @@
 #include "accommon.h"
 #include "acnamesp.h"
 #include "actables.h"
+#include "acevents.h"
 
 #define _COMPONENT          ACPI_TABLES
 ACPI_MODULE_NAME("tbxfload")
@@ -68,6 +69,25 @@ acpi_status __init acpi_load_tables(void)
 
 	ACPI_FUNCTION_TRACE(acpi_load_tables);
 
+	/*
+	 * Install the default operation region handlers. These are the
+	 * handlers that are defined by the ACPI specification to be
+	 * "always accessible" -- namely, system_memory, system_IO, and
+	 * PCI_Config. This also means that no _REG methods need to be
+	 * run for these address spaces. We need to have these handlers
+	 * installed before any AML code can be executed, especially any
+	 * module-level code (11/2015).
+	 * Note that we allow OSPMs to install their own region handlers
+	 * between acpi_initialize_subsystem() and acpi_load_tables() to use
+	 * their customized default region handlers.
+	 */
+	status = acpi_ev_install_region_handlers();
+	if (ACPI_FAILURE(status) && status != AE_ALREADY_EXISTS) {
+		ACPI_EXCEPTION((AE_INFO, status,
+				"During Region initialization"));
+		return_ACPI_STATUS(status);
+	}
+
 	/* Load the namespace from the tables */
 
 	status = acpi_tb_load_namespace();
@@ -83,6 +103,20 @@ acpi_status __init acpi_load_tables(void)
 				"While loading namespace from ACPI tables"));
 	}
 
+	if (!acpi_gbl_group_module_level_code) {
+		/*
+		 * Initialize the objects that remain uninitialized. This
+		 * runs the executable AML that may be part of the
+		 * declaration of these objects:
+		 * operation_regions, buffer_fields, Buffers, and Packages.
+		 */
+		status = acpi_ns_initialize_objects();
+		if (ACPI_FAILURE(status)) {
+			return_ACPI_STATUS(status);
+		}
+	}
+
+	acpi_gbl_namespace_initialized = TRUE;
 	return_ACPI_STATUS(status);
 }
 
@@ -206,9 +240,7 @@ acpi_status acpi_tb_load_namespace(void)
 	}
 
 	if (!tables_failed) {
-		ACPI_INFO((AE_INFO,
-			   "%u ACPI AML tables successfully acquired and loaded\n",
-			   tables_loaded));
+		ACPI_INFO(("%u ACPI AML tables successfully acquired and loaded\n", tables_loaded));
 	} else {
 		ACPI_ERROR((AE_INFO,
 			    "%u table load failures, %u successful",
@@ -301,7 +333,7 @@ acpi_status acpi_load_table(struct acpi_table_header *table)
 
 	/* Install the table and load it into the namespace */
 
-	ACPI_INFO((AE_INFO, "Host-directed Dynamic ACPI Table Load:"));
+	ACPI_INFO(("Host-directed Dynamic ACPI Table Load:"));
 	(void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES);
 
 	status = acpi_tb_install_standard_table(ACPI_PTR_TO_PHYSADDR(table),
diff --git a/drivers/acpi/acpica/utcache.c b/drivers/acpi/acpica/utcache.c
index c9a720f2274a..f8e9978888e1 100644
--- a/drivers/acpi/acpica/utcache.c
+++ b/drivers/acpi/acpica/utcache.c
@@ -245,7 +245,7 @@ void *acpi_os_acquire_object(struct acpi_memory_list *cache)
 	acpi_status status;
 	void *object;
 
-	ACPI_FUNCTION_NAME(os_acquire_object);
+	ACPI_FUNCTION_TRACE(os_acquire_object);
 
 	if (!cache) {
 		return_PTR(NULL);
diff --git a/drivers/acpi/acpica/utnonansi.c b/drivers/acpi/acpica/utnonansi.c
index c427a5cda465..d5c3adf19bd0 100644
--- a/drivers/acpi/acpica/utnonansi.c
+++ b/drivers/acpi/acpica/utnonansi.c
@@ -140,6 +140,67 @@ int acpi_ut_stricmp(char *string1, char *string2)
 	return (c1 - c2);
 }
 
+#if defined (ACPI_DEBUGGER) || defined (ACPI_APPLICATION)
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_safe_strcpy, acpi_ut_safe_strcat, acpi_ut_safe_strncat
+ *
+ * PARAMETERS:  Adds a "DestSize" parameter to each of the standard string
+ *              functions. This is the size of the Destination buffer.
+ *
+ * RETURN:      TRUE if the operation would overflow the destination buffer.
+ *
+ * DESCRIPTION: Safe versions of standard Clib string functions. Ensure that
+ *              the result of the operation will not overflow the output string
+ *              buffer.
+ *
+ * NOTE:        These functions are typically only helpful for processing
+ *              user input and command lines. For most ACPICA code, the
+ *              required buffer length is precisely calculated before buffer
+ *              allocation, so the use of these functions is unnecessary.
+ *
+ ******************************************************************************/
+
+u8 acpi_ut_safe_strcpy(char *dest, acpi_size dest_size, char *source)
+{
+
+	if (strlen(source) >= dest_size) {
+		return (TRUE);
+	}
+
+	strcpy(dest, source);
+	return (FALSE);
+}
+
+u8 acpi_ut_safe_strcat(char *dest, acpi_size dest_size, char *source)
+{
+
+	if ((strlen(dest) + strlen(source)) >= dest_size) {
+		return (TRUE);
+	}
+
+	strcat(dest, source);
+	return (FALSE);
+}
+
+u8
+acpi_ut_safe_strncat(char *dest,
+		     acpi_size dest_size,
+		     char *source, acpi_size max_transfer_length)
+{
+	acpi_size actual_transfer_length;
+
+	actual_transfer_length = ACPI_MIN(max_transfer_length, strlen(source));
+
+	if ((strlen(dest) + actual_transfer_length) >= dest_size) {
+		return (TRUE);
+	}
+
+	strncat(dest, source, max_transfer_length);
+	return (FALSE);
+}
+#endif
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ut_strtoul64
@@ -155,7 +216,15 @@ int acpi_ut_stricmp(char *string1, char *string2)
  *              32-bit or 64-bit conversion, depending on the current mode
  *              of the interpreter.
  *
- * NOTE:        Does not support Octal strings, not needed.
+ * NOTES:       acpi_gbl_integer_byte_width should be set to the proper width.
+ *              For the core ACPICA code, this width depends on the DSDT
+ *              version. For iASL, the default byte width is always 8.
+ *
+ *              Does not support Octal strings, not needed at this time.
+ *
+ *              There is an earlier version of the function after this one,
+ *              below. It is slightly different than this one, and the two
+ *              may eventually may need to be merged. (01/2016).
  *
  ******************************************************************************/
 
@@ -171,7 +240,7 @@ acpi_status acpi_ut_strtoul64(char *string, u32 base, u64 *ret_integer)
 	u8 sign_of0x = 0;
 	u8 term = 0;
 
-	ACPI_FUNCTION_TRACE_STR(ut_stroul64, string);
+	ACPI_FUNCTION_TRACE_STR(ut_strtoul64, string);
 
 	switch (base) {
 	case ACPI_ANY_BASE:
@@ -318,63 +387,162 @@ error_exit:
 	}
 }
 
-#if defined (ACPI_DEBUGGER) || defined (ACPI_APPLICATION)
+#ifdef _OBSOLETE_FUNCTIONS
+/* TBD: use version in ACPICA main code base? */
+/* DONE: 01/2016 */
+
 /*******************************************************************************
  *
- * FUNCTION:    acpi_ut_safe_strcpy, acpi_ut_safe_strcat, acpi_ut_safe_strncat
+ * FUNCTION:    strtoul64
  *
- * PARAMETERS:  Adds a "DestSize" parameter to each of the standard string
- *              functions. This is the size of the Destination buffer.
+ * PARAMETERS:  string              - Null terminated string
+ *              terminater          - Where a pointer to the terminating byte
+ *                                    is returned
+ *              base                - Radix of the string
  *
- * RETURN:      TRUE if the operation would overflow the destination buffer.
+ * RETURN:      Converted value
  *
- * DESCRIPTION: Safe versions of standard Clib string functions. Ensure that
- *              the result of the operation will not overflow the output string
- *              buffer.
- *
- * NOTE:        These functions are typically only helpful for processing
- *              user input and command lines. For most ACPICA code, the
- *              required buffer length is precisely calculated before buffer
- *              allocation, so the use of these functions is unnecessary.
+ * DESCRIPTION: Convert a string into an unsigned value.
  *
  ******************************************************************************/
 
-u8 acpi_ut_safe_strcpy(char *dest, acpi_size dest_size, char *source)
+acpi_status strtoul64(char *string, u32 base, u64 *ret_integer)
 {
+	u32 index;
+	u32 sign;
+	u64 return_value = 0;
+	acpi_status status = AE_OK;
 
-	if (strlen(source) >= dest_size) {
-		return (TRUE);
+	*ret_integer = 0;
+
+	switch (base) {
+	case 0:
+	case 8:
+	case 10:
+	case 16:
+
+		break;
+
+	default:
+		/*
+		 * The specified Base parameter is not in the domain of
+		 * this function:
+		 */
+		return (AE_BAD_PARAMETER);
 	}
 
-	strcpy(dest, source);
-	return (FALSE);
-}
+	/* Skip over any white space in the buffer: */
 
-u8 acpi_ut_safe_strcat(char *dest, acpi_size dest_size, char *source)
-{
+	while (isspace((int)*string) || *string == '\t') {
+		++string;
+	}
 
-	if ((strlen(dest) + strlen(source)) >= dest_size) {
-		return (TRUE);
+	/*
+	 * The buffer may contain an optional plus or minus sign.
+	 * If it does, then skip over it but remember what is was:
+	 */
+	if (*string == '-') {
+		sign = ACPI_SIGN_NEGATIVE;
+		++string;
+	} else if (*string == '+') {
+		++string;
+		sign = ACPI_SIGN_POSITIVE;
+	} else {
+		sign = ACPI_SIGN_POSITIVE;
 	}
 
-	strcat(dest, source);
-	return (FALSE);
-}
+	/*
+	 * If the input parameter Base is zero, then we need to
+	 * determine if it is octal, decimal, or hexadecimal:
+	 */
+	if (base == 0) {
+		if (*string == '0') {
+			if (tolower((int)*(++string)) == 'x') {
+				base = 16;
+				++string;
+			} else {
+				base = 8;
+			}
+		} else {
+			base = 10;
+		}
+	}
 
-u8
-acpi_ut_safe_strncat(char *dest,
-		     acpi_size dest_size,
-		     char *source, acpi_size max_transfer_length)
-{
-	acpi_size actual_transfer_length;
+	/*
+	 * For octal and hexadecimal bases, skip over the leading
+	 * 0 or 0x, if they are present.
+	 */
+	if (base == 8 && *string == '0') {
+		string++;
+	}
 
-	actual_transfer_length = ACPI_MIN(max_transfer_length, strlen(source));
+	if (base == 16 && *string == '0' && tolower((int)*(++string)) == 'x') {
+		string++;
+	}
 
-	if ((strlen(dest) + actual_transfer_length) >= dest_size) {
-		return (TRUE);
+	/* Main loop: convert the string to an unsigned long */
+
+	while (*string) {
+		if (isdigit((int)*string)) {
+			index = ((u8)*string) - '0';
+		} else {
+			index = (u8)toupper((int)*string);
+			if (isupper((int)index)) {
+				index = index - 'A' + 10;
+			} else {
+				goto error_exit;
+			}
+		}
+
+		if (index >= base) {
+			goto error_exit;
+		}
+
+		/* Check to see if value is out of range: */
+
+		if (return_value > ((ACPI_UINT64_MAX - (u64)index) / (u64)base)) {
+			goto error_exit;
+		} else {
+			return_value *= base;
+			return_value += index;
+		}
+
+		++string;
 	}
 
-	strncat(dest, source, max_transfer_length);
-	return (FALSE);
+	/* If a minus sign was present, then "the conversion is negated": */
+
+	if (sign == ACPI_SIGN_NEGATIVE) {
+		return_value = (ACPI_UINT32_MAX - return_value) + 1;
+	}
+
+	*ret_integer = return_value;
+	return (status);
+
+error_exit:
+	switch (base) {
+	case 8:
+
+		status = AE_BAD_OCTAL_CONSTANT;
+		break;
+
+	case 10:
+
+		status = AE_BAD_DECIMAL_CONSTANT;
+		break;
+
+	case 16:
+
+		status = AE_BAD_HEX_CONSTANT;
+		break;
+
+	default:
+
+		/* Base validated above */
+
+		break;
+	}
+
+	return (status);
 }
 #endif
diff --git a/drivers/acpi/acpica/uttrack.c b/drivers/acpi/acpica/uttrack.c
index c7c2bb8f3559..60c406a8efcb 100644
--- a/drivers/acpi/acpica/uttrack.c
+++ b/drivers/acpi/acpica/uttrack.c
@@ -712,7 +712,7 @@ void acpi_ut_dump_allocations(u32 component, const char *module)
 	/* Print summary */
 
 	if (!num_outstanding) {
-		ACPI_INFO((AE_INFO, "No outstanding allocations"));
+		ACPI_INFO(("No outstanding allocations"));
 	} else {
 		ACPI_ERROR((AE_INFO, "%u(0x%X) Outstanding allocations",
 			    num_outstanding, num_outstanding));
diff --git a/drivers/acpi/acpica/utxferror.c b/drivers/acpi/acpica/utxferror.c
index 6fe59597b599..d9f15cbcd8a0 100644
--- a/drivers/acpi/acpica/utxferror.c
+++ b/drivers/acpi/acpica/utxferror.c
@@ -175,8 +175,7 @@ ACPI_EXPORT_SYMBOL(acpi_warning)
  * TBD: module_name and line_number args are not needed, should be removed.
  *
  ******************************************************************************/
-void ACPI_INTERNAL_VAR_XFACE
-acpi_info(const char *module_name, u32 line_number, const char *format, ...)
+void ACPI_INTERNAL_VAR_XFACE acpi_info(const char *format, ...)
 {
 	va_list arg_list;
 
diff --git a/drivers/acpi/acpica/utxfinit.c b/drivers/acpi/acpica/utxfinit.c
index 721b87cce908..75b5f27da267 100644
--- a/drivers/acpi/acpica/utxfinit.c
+++ b/drivers/acpi/acpica/utxfinit.c
@@ -154,21 +154,6 @@ acpi_status __init acpi_enable_subsystem(u32 flags)
 	 */
 	acpi_gbl_early_initialization = FALSE;
 
-	/*
-	 * Install the default operation region handlers. These are the
-	 * handlers that are defined by the ACPI specification to be
-	 * "always accessible" -- namely, system_memory, system_IO, and
-	 * PCI_Config. This also means that no _REG methods need to be
-	 * run for these address spaces. We need to have these handlers
-	 * installed before any AML code can be executed, especially any
-	 * module-level code (11/2015).
-	 */
-	status = acpi_ev_install_region_handlers();
-	if (ACPI_FAILURE(status)) {
-		ACPI_EXCEPTION((AE_INFO, status,
-				"During Region initialization"));
-		return_ACPI_STATUS(status);
-	}
 #if (!ACPI_REDUCED_HARDWARE)
 
 	/* Enable ACPI mode */
@@ -260,23 +245,6 @@ acpi_status __init acpi_initialize_objects(u32 flags)
 
 	ACPI_FUNCTION_TRACE(acpi_initialize_objects);
 
-	/*
-	 * Run all _REG methods
-	 *
-	 * Note: Any objects accessed by the _REG methods will be automatically
-	 * initialized, even if they contain executable AML (see the call to
-	 * acpi_ns_initialize_objects below).
-	 */
-	acpi_gbl_reg_methods_enabled = TRUE;
-	if (!(flags & ACPI_NO_ADDRESS_SPACE_INIT)) {
-		ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
-				  "[Init] Executing _REG OpRegion methods\n"));
-
-		status = acpi_ev_initialize_op_regions();
-		if (ACPI_FAILURE(status)) {
-			return_ACPI_STATUS(status);
-		}
-	}
 #ifdef ACPI_EXEC_APP
 	/*
 	 * This call implements the "initialization file" option for acpi_exec.
@@ -299,32 +267,27 @@ acpi_status __init acpi_initialize_objects(u32 flags)
 	 */
 	if (acpi_gbl_group_module_level_code) {
 		acpi_ns_exec_module_code_list();
-	}
-
-	/*
-	 * Initialize the objects that remain uninitialized. This runs the
-	 * executable AML that may be part of the declaration of these objects:
-	 * operation_regions, buffer_fields, Buffers, and Packages.
-	 */
-	if (!(flags & ACPI_NO_OBJECT_INIT)) {
-		ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
-				  "[Init] Completing Initialization of ACPI Objects\n"));
 
-		status = acpi_ns_initialize_objects();
-		if (ACPI_FAILURE(status)) {
-			return_ACPI_STATUS(status);
+		/*
+		 * Initialize the objects that remain uninitialized. This
+		 * runs the executable AML that may be part of the
+		 * declaration of these objects:
+		 * operation_regions, buffer_fields, Buffers, and Packages.
+		 */
+		if (!(flags & ACPI_NO_OBJECT_INIT)) {
+			status = acpi_ns_initialize_objects();
+			if (ACPI_FAILURE(status)) {
+				return_ACPI_STATUS(status);
+			}
 		}
 	}
 
 	/*
-	 * Initialize all device objects in the namespace. This runs the device
-	 * _STA and _INI methods.
+	 * Initialize all device/region objects in the namespace. This runs
+	 * the device _STA and _INI methods and region _REG methods.
 	 */
-	if (!(flags & ACPI_NO_DEVICE_INIT)) {
-		ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
-				  "[Init] Initializing ACPI Devices\n"));
-
-		status = acpi_ns_initialize_devices();
+	if (!(flags & (ACPI_NO_DEVICE_INIT | ACPI_NO_ADDRESS_SPACE_INIT))) {
+		status = acpi_ns_initialize_devices(flags);
 		if (ACPI_FAILURE(status)) {
 			return_ACPI_STATUS(status);
 		}
diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c
index a2c8d7adb6eb..da370e1d31f4 100644
--- a/drivers/acpi/apei/apei-base.c
+++ b/drivers/acpi/apei/apei-base.c
@@ -536,7 +536,8 @@ int apei_resources_request(struct apei_resources *resources,
 		goto err_unmap_ioport;
 	}
 
-	return 0;
+	goto arch_res_fini;
+
 err_unmap_ioport:
 	list_for_each_entry(res, &resources->ioport, list) {
 		if (res == res_bak)
@@ -551,7 +552,8 @@ err_unmap_iomem:
 		release_mem_region(res->start, res->end - res->start);
 	}
 arch_res_fini:
-	apei_resources_fini(&arch_res);
+	if (arch_apei_filter_addr)
+		apei_resources_fini(&arch_res);
 nvs_res_fini:
 	apei_resources_fini(&nvs_resources);
 	return rc;
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index 0431883653be..559c1173de1c 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -519,7 +519,7 @@ static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 			     u64 param3, u64 param4)
 {
 	int rc;
-	unsigned long pfn;
+	u64 base_addr, size;
 
 	/* If user manually set "flags", make sure it is legal */
 	if (flags && (flags &
@@ -545,10 +545,17 @@ static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 	/*
 	 * Disallow crazy address masks that give BIOS leeway to pick
 	 * injection address almost anywhere. Insist on page or
-	 * better granularity and that target address is normal RAM.
+	 * better granularity and that target address is normal RAM or
+	 * NVDIMM.
 	 */
-	pfn = PFN_DOWN(param1 & param2);
-	if (!page_is_ram(pfn) || ((param2 & PAGE_MASK) != PAGE_MASK))
+	base_addr = param1 & param2;
+	size = ~param2 + 1;
+
+	if (((param2 & PAGE_MASK) != PAGE_MASK) ||
+	    ((region_intersects(base_addr, size, IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE)
+				!= REGION_INTERSECTS) &&
+	     (region_intersects(base_addr, size, IORESOURCE_MEM, IORES_DESC_PERSISTENT_MEMORY)
+				!= REGION_INTERSECTS)))
 		return -EINVAL;
 
 inject:
diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index 6e6bc1059301..006c3894c6ea 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -1207,6 +1207,9 @@ static int __init erst_init(void)
 		"Failed to allocate %lld bytes for persistent store error log.\n",
 		erst_erange.size);
 
+	/* Cleanup ERST Resources */
+	apei_resources_fini(&erst_resources);
+
 	return 0;
 
 err_release_erange:
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 3dd9c462d22a..60746ef904e4 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -26,7 +26,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <linux/init.h>
 #include <linux/acpi.h>
 #include <linux/io.h>
@@ -79,6 +79,11 @@
 	((struct acpi_hest_generic_status *)				\
 	 ((struct ghes_estatus_node *)(estatus_node) + 1))
 
+/*
+ * This driver isn't really modular, however for the time being,
+ * continuing to use module_param is the easiest way to remain
+ * compatible with existing boot arg use cases.
+ */
 bool ghes_disable;
 module_param_named(disable, ghes_disable, bool, 0);
 
@@ -1148,18 +1153,4 @@ err_ioremap_exit:
 err:
 	return rc;
 }
-
-static void __exit ghes_exit(void)
-{
-	platform_driver_unregister(&ghes_platform_driver);
-	ghes_estatus_pool_exit();
-	ghes_ioremap_exit();
-}
-
-module_init(ghes_init);
-module_exit(ghes_exit);
-
-MODULE_AUTHOR("Huang Ying");
-MODULE_DESCRIPTION("APEI Generic Hardware Error Source support");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:GHES");
+device_initcall(ghes_init);
diff --git a/drivers/acpi/bgrt.c b/drivers/acpi/bgrt.c
index a83e3c62c5a9..75f128e766a9 100644
--- a/drivers/acpi/bgrt.c
+++ b/drivers/acpi/bgrt.c
@@ -1,4 +1,6 @@
 /*
+ * BGRT boot graphic support
+ * Authors: Matthew Garrett, Josh Triplett <josh@joshtriplett.org>
  * Copyright 2012 Red Hat, Inc <mjg@redhat.com>
  * Copyright 2012 Intel Corporation
  *
@@ -8,7 +10,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/sysfs.h>
@@ -103,9 +104,4 @@ out_kobject:
 	kobject_put(bgrt_kobj);
 	return ret;
 }
-
-module_init(bgrt_init);
-
-MODULE_AUTHOR("Matthew Garrett, Josh Triplett <josh@joshtriplett.org>");
-MODULE_DESCRIPTION("BGRT boot graphic support");
-MODULE_LICENSE("GPL");
+device_initcall(bgrt_init);
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 891c42d1cd65..0e8567846f1a 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -479,24 +479,38 @@ static void acpi_device_remove_notify_handler(struct acpi_device *device)
                              Device Matching
    -------------------------------------------------------------------------- */
 
-static struct acpi_device *acpi_primary_dev_companion(struct acpi_device *adev,
-						      const struct device *dev)
+/**
+ * acpi_get_first_physical_node - Get first physical node of an ACPI device
+ * @adev:	ACPI device in question
+ *
+ * Return: First physical node of ACPI device @adev
+ */
+struct device *acpi_get_first_physical_node(struct acpi_device *adev)
 {
 	struct mutex *physical_node_lock = &adev->physical_node_lock;
+	struct device *phys_dev;
 
 	mutex_lock(physical_node_lock);
 	if (list_empty(&adev->physical_node_list)) {
-		adev = NULL;
+		phys_dev = NULL;
 	} else {
 		const struct acpi_device_physical_node *node;
 
 		node = list_first_entry(&adev->physical_node_list,
 					struct acpi_device_physical_node, node);
-		if (node->dev != dev)
-			adev = NULL;
+
+		phys_dev = node->dev;
 	}
 	mutex_unlock(physical_node_lock);
-	return adev;
+	return phys_dev;
+}
+
+static struct acpi_device *acpi_primary_dev_companion(struct acpi_device *adev,
+						      const struct device *dev)
+{
+	const struct device *phys_dev = acpi_get_first_physical_node(adev);
+
+	return phys_dev && phys_dev == dev ? adev : NULL;
 }
 
 /**
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 6730f965b379..8adac69dba3d 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -39,6 +39,7 @@
 
 #include <linux/cpufreq.h>
 #include <linux/delay.h>
+#include <linux/ktime.h>
 
 #include <acpi/cppc_acpi.h>
 /*
@@ -63,58 +64,140 @@ static struct mbox_chan *pcc_channel;
 static void __iomem *pcc_comm_addr;
 static u64 comm_base_addr;
 static int pcc_subspace_idx = -1;
-static u16 pcc_cmd_delay;
 static bool pcc_channel_acquired;
+static ktime_t deadline;
+static unsigned int pcc_mpar, pcc_mrtt;
+
+/* pcc mapped address + header size + offset within PCC subspace */
+#define GET_PCC_VADDR(offs) (pcc_comm_addr + 0x8 + (offs))
 
 /*
  * Arbitrary Retries in case the remote processor is slow to respond
- * to PCC commands.
+ * to PCC commands. Keeping it high enough to cover emulators where
+ * the processors run painfully slow.
  */
 #define NUM_RETRIES 500
 
+static int check_pcc_chan(void)
+{
+	int ret = -EIO;
+	struct acpi_pcct_shared_memory __iomem *generic_comm_base = pcc_comm_addr;
+	ktime_t next_deadline = ktime_add(ktime_get(), deadline);
+
+	/* Retry in case the remote processor was too slow to catch up. */
+	while (!ktime_after(ktime_get(), next_deadline)) {
+		/*
+		 * Per spec, prior to boot the PCC space wil be initialized by
+		 * platform and should have set the command completion bit when
+		 * PCC can be used by OSPM
+		 */
+		if (readw_relaxed(&generic_comm_base->status) & PCC_CMD_COMPLETE) {
+			ret = 0;
+			break;
+		}
+		/*
+		 * Reducing the bus traffic in case this loop takes longer than
+		 * a few retries.
+		 */
+		udelay(3);
+	}
+
+	return ret;
+}
+
 static int send_pcc_cmd(u16 cmd)
 {
-	int retries, result = -EIO;
-	struct acpi_pcct_hw_reduced *pcct_ss = pcc_channel->con_priv;
+	int ret = -EIO;
 	struct acpi_pcct_shared_memory *generic_comm_base =
 		(struct acpi_pcct_shared_memory *) pcc_comm_addr;
-	u32 cmd_latency = pcct_ss->latency;
+	static ktime_t last_cmd_cmpl_time, last_mpar_reset;
+	static int mpar_count;
+	unsigned int time_delta;
 
-	/* Min time OS should wait before sending next command. */
-	udelay(pcc_cmd_delay);
+	/*
+	 * For CMD_WRITE we know for a fact the caller should have checked
+	 * the channel before writing to PCC space
+	 */
+	if (cmd == CMD_READ) {
+		ret = check_pcc_chan();
+		if (ret)
+			return ret;
+	}
+
+	/*
+	 * Handle the Minimum Request Turnaround Time(MRTT)
+	 * "The minimum amount of time that OSPM must wait after the completion
+	 * of a command before issuing the next command, in microseconds"
+	 */
+	if (pcc_mrtt) {
+		time_delta = ktime_us_delta(ktime_get(), last_cmd_cmpl_time);
+		if (pcc_mrtt > time_delta)
+			udelay(pcc_mrtt - time_delta);
+	}
+
+	/*
+	 * Handle the non-zero Maximum Periodic Access Rate(MPAR)
+	 * "The maximum number of periodic requests that the subspace channel can
+	 * support, reported in commands per minute. 0 indicates no limitation."
+	 *
+	 * This parameter should be ideally zero or large enough so that it can
+	 * handle maximum number of requests that all the cores in the system can
+	 * collectively generate. If it is not, we will follow the spec and just
+	 * not send the request to the platform after hitting the MPAR limit in
+	 * any 60s window
+	 */
+	if (pcc_mpar) {
+		if (mpar_count == 0) {
+			time_delta = ktime_ms_delta(ktime_get(), last_mpar_reset);
+			if (time_delta < 60 * MSEC_PER_SEC) {
+				pr_debug("PCC cmd not sent due to MPAR limit");
+				return -EIO;
+			}
+			last_mpar_reset = ktime_get();
+			mpar_count = pcc_mpar;
+		}
+		mpar_count--;
+	}
 
 	/* Write to the shared comm region. */
-	writew(cmd, &generic_comm_base->command);
+	writew_relaxed(cmd, &generic_comm_base->command);
 
 	/* Flip CMD COMPLETE bit */
-	writew(0, &generic_comm_base->status);
+	writew_relaxed(0, &generic_comm_base->status);
 
 	/* Ring doorbell */
-	result = mbox_send_message(pcc_channel, &cmd);
-	if (result < 0) {
+	ret = mbox_send_message(pcc_channel, &cmd);
+	if (ret < 0) {
 		pr_err("Err sending PCC mbox message. cmd:%d, ret:%d\n",
-				cmd, result);
-		return result;
+				cmd, ret);
+		return ret;
 	}
 
-	/* Wait for a nominal time to let platform process command. */
-	udelay(cmd_latency);
-
-	/* Retry in case the remote processor was too slow to catch up. */
-	for (retries = NUM_RETRIES; retries > 0; retries--) {
-		if (readw_relaxed(&generic_comm_base->status) & PCC_CMD_COMPLETE) {
-			result = 0;
-			break;
-		}
+	/*
+	 * For READs we need to ensure the cmd completed to ensure
+	 * the ensuing read()s can proceed. For WRITEs we dont care
+	 * because the actual write()s are done before coming here
+	 * and the next READ or WRITE will check if the channel
+	 * is busy/free at the entry of this call.
+	 *
+	 * If Minimum Request Turnaround Time is non-zero, we need
+	 * to record the completion time of both READ and WRITE
+	 * command for proper handling of MRTT, so we need to check
+	 * for pcc_mrtt in addition to CMD_READ
+	 */
+	if (cmd == CMD_READ || pcc_mrtt) {
+		ret = check_pcc_chan();
+		if (pcc_mrtt)
+			last_cmd_cmpl_time = ktime_get();
 	}
 
-	mbox_client_txdone(pcc_channel, result);
-	return result;
+	mbox_client_txdone(pcc_channel, ret);
+	return ret;
 }
 
 static void cppc_chan_tx_done(struct mbox_client *cl, void *msg, int ret)
 {
-	if (ret)
+	if (ret < 0)
 		pr_debug("TX did not complete: CMD sent:%x, ret:%d\n",
 				*(u16 *)msg, ret);
 	else
@@ -306,6 +389,7 @@ static int register_pcc_channel(int pcc_subspace_idx)
 {
 	struct acpi_pcct_hw_reduced *cppc_ss;
 	unsigned int len;
+	u64 usecs_lat;
 
 	if (pcc_subspace_idx >= 0) {
 		pcc_channel = pcc_mbox_request_channel(&cppc_mbox_cl,
@@ -335,7 +419,16 @@ static int register_pcc_channel(int pcc_subspace_idx)
 		 */
 		comm_base_addr = cppc_ss->base_address;
 		len = cppc_ss->length;
-		pcc_cmd_delay = cppc_ss->min_turnaround_time;
+
+		/*
+		 * cppc_ss->latency is just a Nominal value. In reality
+		 * the remote processor could be much slower to reply.
+		 * So add an arbitrary amount of wait on top of Nominal.
+		 */
+		usecs_lat = NUM_RETRIES * cppc_ss->latency;
+		deadline = ns_to_ktime(usecs_lat * NSEC_PER_USEC);
+		pcc_mrtt = cppc_ss->min_turnaround_time;
+		pcc_mpar = cppc_ss->max_access_rate;
 
 		pcc_comm_addr = acpi_os_ioremap(comm_base_addr, len);
 		if (!pcc_comm_addr) {
@@ -546,29 +639,74 @@ void acpi_cppc_processor_exit(struct acpi_processor *pr)
 }
 EXPORT_SYMBOL_GPL(acpi_cppc_processor_exit);
 
-static u64 get_phys_addr(struct cpc_reg *reg)
-{
-	/* PCC communication addr space begins at byte offset 0x8. */
-	if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM)
-		return (u64)comm_base_addr + 0x8 + reg->address;
-	else
-		return reg->address;
-}
+/*
+ * Since cpc_read and cpc_write are called while holding pcc_lock, it should be
+ * as fast as possible. We have already mapped the PCC subspace during init, so
+ * we can directly write to it.
+ */
 
-static void cpc_read(struct cpc_reg *reg, u64 *val)
+static int cpc_read(struct cpc_reg *reg, u64 *val)
 {
-	u64 addr = get_phys_addr(reg);
+	int ret_val = 0;
 
-	acpi_os_read_memory((acpi_physical_address)addr,
-			val, reg->bit_width);
+	*val = 0;
+	if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) {
+		void __iomem *vaddr = GET_PCC_VADDR(reg->address);
+
+		switch (reg->bit_width) {
+		case 8:
+			*val = readb_relaxed(vaddr);
+			break;
+		case 16:
+			*val = readw_relaxed(vaddr);
+			break;
+		case 32:
+			*val = readl_relaxed(vaddr);
+			break;
+		case 64:
+			*val = readq_relaxed(vaddr);
+			break;
+		default:
+			pr_debug("Error: Cannot read %u bit width from PCC\n",
+				reg->bit_width);
+			ret_val = -EFAULT;
+		}
+	} else
+		ret_val = acpi_os_read_memory((acpi_physical_address)reg->address,
+					val, reg->bit_width);
+	return ret_val;
 }
 
-static void cpc_write(struct cpc_reg *reg, u64 val)
+static int cpc_write(struct cpc_reg *reg, u64 val)
 {
-	u64 addr = get_phys_addr(reg);
+	int ret_val = 0;
 
-	acpi_os_write_memory((acpi_physical_address)addr,
-			val, reg->bit_width);
+	if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) {
+		void __iomem *vaddr = GET_PCC_VADDR(reg->address);
+
+		switch (reg->bit_width) {
+		case 8:
+			writeb_relaxed(val, vaddr);
+			break;
+		case 16:
+			writew_relaxed(val, vaddr);
+			break;
+		case 32:
+			writel_relaxed(val, vaddr);
+			break;
+		case 64:
+			writeq_relaxed(val, vaddr);
+			break;
+		default:
+			pr_debug("Error: Cannot write %u bit width to PCC\n",
+				reg->bit_width);
+			ret_val = -EFAULT;
+			break;
+		}
+	} else
+		ret_val = acpi_os_write_memory((acpi_physical_address)reg->address,
+				val, reg->bit_width);
+	return ret_val;
 }
 
 /**
@@ -604,7 +742,7 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
 			(ref_perf->cpc_entry.reg.space_id == ACPI_ADR_SPACE_PLATFORM_COMM) ||
 			(nom_perf->cpc_entry.reg.space_id == ACPI_ADR_SPACE_PLATFORM_COMM)) {
 		/* Ring doorbell once to update PCC subspace */
-		if (send_pcc_cmd(CMD_READ)) {
+		if (send_pcc_cmd(CMD_READ) < 0) {
 			ret = -EIO;
 			goto out_err;
 		}
@@ -662,7 +800,7 @@ int cppc_get_perf_ctrs(int cpunum, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
 	if ((delivered_reg->cpc_entry.reg.space_id == ACPI_ADR_SPACE_PLATFORM_COMM) ||
 			(reference_reg->cpc_entry.reg.space_id == ACPI_ADR_SPACE_PLATFORM_COMM)) {
 		/* Ring doorbell once to update PCC subspace */
-		if (send_pcc_cmd(CMD_READ)) {
+		if (send_pcc_cmd(CMD_READ) < 0) {
 			ret = -EIO;
 			goto out_err;
 		}
@@ -713,6 +851,13 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
 
 	spin_lock(&pcc_lock);
 
+	/* If this is PCC reg, check if channel is free before writing */
+	if (desired_reg->cpc_entry.reg.space_id == ACPI_ADR_SPACE_PLATFORM_COMM) {
+		ret = check_pcc_chan();
+		if (ret)
+			goto busy_channel;
+	}
+
 	/*
 	 * Skip writing MIN/MAX until Linux knows how to come up with
 	 * useful values.
@@ -722,10 +867,10 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
 	/* Is this a PCC reg ?*/
 	if (desired_reg->cpc_entry.reg.space_id == ACPI_ADR_SPACE_PLATFORM_COMM) {
 		/* Ring doorbell so Remote can get our perf request. */
-		if (send_pcc_cmd(CMD_WRITE))
+		if (send_pcc_cmd(CMD_WRITE) < 0)
 			ret = -EIO;
 	}
-
+busy_channel:
 	spin_unlock(&pcc_lock);
 
 	return ret;
diff --git a/drivers/acpi/ec_sys.c b/drivers/acpi/ec_sys.c
index bea8e425a8de..6c7dd7af789e 100644
--- a/drivers/acpi/ec_sys.c
+++ b/drivers/acpi/ec_sys.c
@@ -73,6 +73,9 @@ static ssize_t acpi_ec_write_io(struct file *f, const char __user *buf,
 	loff_t init_off = *off;
 	int err = 0;
 
+	if (!write_support)
+		return -EINVAL;
+
 	if (*off >= EC_SPACE_SIZE)
 		return 0;
 	if (*off + count >= EC_SPACE_SIZE) {
diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c
index 6322db64b4a4..384cfc3083e1 100644
--- a/drivers/acpi/fan.c
+++ b/drivers/acpi/fan.c
@@ -46,7 +46,7 @@ MODULE_DEVICE_TABLE(acpi, fan_device_ids);
 #ifdef CONFIG_PM_SLEEP
 static int acpi_fan_suspend(struct device *dev);
 static int acpi_fan_resume(struct device *dev);
-static struct dev_pm_ops acpi_fan_pm = {
+static const struct dev_pm_ops acpi_fan_pm = {
 	.resume = acpi_fan_resume,
 	.freeze = acpi_fan_suspend,
 	.thaw = acpi_fan_resume,
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 1e6833a5cd44..a37508ef66c1 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -20,6 +20,7 @@
 
 #define PREFIX "ACPI: "
 
+void acpi_initrd_initialize_tables(void);
 acpi_status acpi_os_initialize1(void);
 void init_acpi_device_notify(void);
 int acpi_scan_init(void);
@@ -29,6 +30,11 @@ void acpi_processor_init(void);
 void acpi_platform_init(void);
 void acpi_pnp_init(void);
 void acpi_int340x_thermal_init(void);
+#ifdef CONFIG_ARM_AMBA
+void acpi_amba_init(void);
+#else
+static inline void acpi_amba_init(void) {}
+#endif
 int acpi_sysfs_init(void);
 void acpi_container_init(void);
 void acpi_memory_hotplug_init(void);
@@ -106,6 +112,7 @@ bool acpi_device_is_present(struct acpi_device *adev);
 bool acpi_device_is_battery(struct acpi_device *adev);
 bool acpi_device_is_first_physical_node(struct acpi_device *adev,
 					const struct device *dev);
+struct device *acpi_get_first_physical_node(struct acpi_device *adev);
 
 /* --------------------------------------------------------------------------
                      Device Matching and Notification
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index ad6d8c6b777e..d0f35e63640b 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -21,6 +21,7 @@
 #include <linux/sort.h>
 #include <linux/pmem.h>
 #include <linux/io.h>
+#include <linux/nd.h>
 #include <asm/cacheflush.h>
 #include "nfit.h"
 
@@ -34,6 +35,18 @@ static bool force_enable_dimms;
 module_param(force_enable_dimms, bool, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(force_enable_dimms, "Ignore _STA (ACPI DIMM device) status");
 
+static unsigned int scrub_timeout = NFIT_ARS_TIMEOUT;
+module_param(scrub_timeout, uint, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(scrub_timeout, "Initial scrub timeout in seconds");
+
+/* after three payloads of overflow, it's dead jim */
+static unsigned int scrub_overflow_abort = 3;
+module_param(scrub_overflow_abort, uint, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(scrub_overflow_abort,
+		"Number of times we overflow ARS results before abort");
+
+static struct workqueue_struct *nfit_wq;
+
 struct nfit_table_prev {
 	struct list_head spas;
 	struct list_head memdevs;
@@ -72,9 +85,90 @@ static struct acpi_device *to_acpi_dev(struct acpi_nfit_desc *acpi_desc)
 	return to_acpi_device(acpi_desc->dev);
 }
 
+static int xlat_status(void *buf, unsigned int cmd)
+{
+	struct nd_cmd_clear_error *clear_err;
+	struct nd_cmd_ars_status *ars_status;
+	struct nd_cmd_ars_start *ars_start;
+	struct nd_cmd_ars_cap *ars_cap;
+	u16 flags;
+
+	switch (cmd) {
+	case ND_CMD_ARS_CAP:
+		ars_cap = buf;
+		if ((ars_cap->status & 0xffff) == NFIT_ARS_CAP_NONE)
+			return -ENOTTY;
+
+		/* Command failed */
+		if (ars_cap->status & 0xffff)
+			return -EIO;
+
+		/* No supported scan types for this range */
+		flags = ND_ARS_PERSISTENT | ND_ARS_VOLATILE;
+		if ((ars_cap->status >> 16 & flags) == 0)
+			return -ENOTTY;
+		break;
+	case ND_CMD_ARS_START:
+		ars_start = buf;
+		/* ARS is in progress */
+		if ((ars_start->status & 0xffff) == NFIT_ARS_START_BUSY)
+			return -EBUSY;
+
+		/* Command failed */
+		if (ars_start->status & 0xffff)
+			return -EIO;
+		break;
+	case ND_CMD_ARS_STATUS:
+		ars_status = buf;
+		/* Command failed */
+		if (ars_status->status & 0xffff)
+			return -EIO;
+		/* Check extended status (Upper two bytes) */
+		if (ars_status->status == NFIT_ARS_STATUS_DONE)
+			return 0;
+
+		/* ARS is in progress */
+		if (ars_status->status == NFIT_ARS_STATUS_BUSY)
+			return -EBUSY;
+
+		/* No ARS performed for the current boot */
+		if (ars_status->status == NFIT_ARS_STATUS_NONE)
+			return -EAGAIN;
+
+		/*
+		 * ARS interrupted, either we overflowed or some other
+		 * agent wants the scan to stop.  If we didn't overflow
+		 * then just continue with the returned results.
+		 */
+		if (ars_status->status == NFIT_ARS_STATUS_INTR) {
+			if (ars_status->flags & NFIT_ARS_F_OVERFLOW)
+				return -ENOSPC;
+			return 0;
+		}
+
+		/* Unknown status */
+		if (ars_status->status >> 16)
+			return -EIO;
+		break;
+	case ND_CMD_CLEAR_ERROR:
+		clear_err = buf;
+		if (clear_err->status & 0xffff)
+			return -EIO;
+		if (!clear_err->cleared)
+			return -EIO;
+		if (clear_err->length > clear_err->cleared)
+			return clear_err->cleared;
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc,
 		struct nvdimm *nvdimm, unsigned int cmd, void *buf,
-		unsigned int buf_len)
+		unsigned int buf_len, int *cmd_rc)
 {
 	struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc);
 	const struct nd_cmd_desc *desc = NULL;
@@ -185,6 +279,8 @@ static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc,
 			 * unfilled in the output buffer
 			 */
 			rc = buf_len - offset - in_buf.buffer.length;
+			if (cmd_rc)
+				*cmd_rc = xlat_status(buf, cmd);
 		} else {
 			dev_err(dev, "%s:%s underrun cmd: %s buf_len: %d out_len: %d\n",
 					__func__, dimm_name, cmd_name, buf_len,
@@ -469,37 +565,16 @@ static void nfit_mem_find_spa_bdw(struct acpi_nfit_desc *acpi_desc,
 	nfit_mem->bdw = NULL;
 }
 
-static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc,
+static void nfit_mem_init_bdw(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_mem *nfit_mem, struct acpi_nfit_system_address *spa)
 {
 	u16 dcr = __to_nfit_memdev(nfit_mem)->region_index;
 	struct nfit_memdev *nfit_memdev;
 	struct nfit_flush *nfit_flush;
-	struct nfit_dcr *nfit_dcr;
 	struct nfit_bdw *nfit_bdw;
 	struct nfit_idt *nfit_idt;
 	u16 idt_idx, range_index;
 
-	list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) {
-		if (nfit_dcr->dcr->region_index != dcr)
-			continue;
-		nfit_mem->dcr = nfit_dcr->dcr;
-		break;
-	}
-
-	if (!nfit_mem->dcr) {
-		dev_dbg(acpi_desc->dev, "SPA %d missing:%s%s\n",
-				spa->range_index, __to_nfit_memdev(nfit_mem)
-				? "" : " MEMDEV", nfit_mem->dcr ? "" : " DCR");
-		return -ENODEV;
-	}
-
-	/*
-	 * We've found enough to create an nvdimm, optionally
-	 * find an associated BDW
-	 */
-	list_add(&nfit_mem->list, &acpi_desc->dimms);
-
 	list_for_each_entry(nfit_bdw, &acpi_desc->bdws, list) {
 		if (nfit_bdw->bdw->region_index != dcr)
 			continue;
@@ -508,12 +583,12 @@ static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc,
 	}
 
 	if (!nfit_mem->bdw)
-		return 0;
+		return;
 
 	nfit_mem_find_spa_bdw(acpi_desc, nfit_mem);
 
 	if (!nfit_mem->spa_bdw)
-		return 0;
+		return;
 
 	range_index = nfit_mem->spa_bdw->range_index;
 	list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) {
@@ -538,8 +613,6 @@ static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc,
 		}
 		break;
 	}
-
-	return 0;
 }
 
 static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
@@ -548,7 +621,6 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
 	struct nfit_mem *nfit_mem, *found;
 	struct nfit_memdev *nfit_memdev;
 	int type = nfit_spa_type(spa);
-	u16 dcr;
 
 	switch (type) {
 	case NFIT_SPA_DCR:
@@ -559,14 +631,18 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
 	}
 
 	list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) {
-		int rc;
+		struct nfit_dcr *nfit_dcr;
+		u32 device_handle;
+		u16 dcr;
 
 		if (nfit_memdev->memdev->range_index != spa->range_index)
 			continue;
 		found = NULL;
 		dcr = nfit_memdev->memdev->region_index;
+		device_handle = nfit_memdev->memdev->device_handle;
 		list_for_each_entry(nfit_mem, &acpi_desc->dimms, list)
-			if (__to_nfit_memdev(nfit_mem)->region_index == dcr) {
+			if (__to_nfit_memdev(nfit_mem)->device_handle
+					== device_handle) {
 				found = nfit_mem;
 				break;
 			}
@@ -579,6 +655,31 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
 			if (!nfit_mem)
 				return -ENOMEM;
 			INIT_LIST_HEAD(&nfit_mem->list);
+			list_add(&nfit_mem->list, &acpi_desc->dimms);
+		}
+
+		list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) {
+			if (nfit_dcr->dcr->region_index != dcr)
+				continue;
+			/*
+			 * Record the control region for the dimm.  For
+			 * the ACPI 6.1 case, where there are separate
+			 * control regions for the pmem vs blk
+			 * interfaces, be sure to record the extended
+			 * blk details.
+			 */
+			if (!nfit_mem->dcr)
+				nfit_mem->dcr = nfit_dcr->dcr;
+			else if (nfit_mem->dcr->windows == 0
+					&& nfit_dcr->dcr->windows)
+				nfit_mem->dcr = nfit_dcr->dcr;
+			break;
+		}
+
+		if (dcr && !nfit_mem->dcr) {
+			dev_err(acpi_desc->dev, "SPA %d missing DCR %d\n",
+					spa->range_index, dcr);
+			return -ENODEV;
 		}
 
 		if (type == NFIT_SPA_DCR) {
@@ -595,6 +696,7 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
 				nfit_mem->idt_dcr = nfit_idt->idt;
 				break;
 			}
+			nfit_mem_init_bdw(acpi_desc, nfit_mem, spa);
 		} else {
 			/*
 			 * A single dimm may belong to multiple SPA-PM
@@ -603,13 +705,6 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
 			 */
 			nfit_mem->memdev_pmem = nfit_memdev->memdev;
 		}
-
-		if (found)
-			continue;
-
-		rc = nfit_mem_add(acpi_desc, nfit_mem, spa);
-		if (rc)
-			return rc;
 	}
 
 	return 0;
@@ -676,12 +771,11 @@ static struct attribute_group acpi_nfit_attribute_group = {
 	.attrs = acpi_nfit_attributes,
 };
 
-const struct attribute_group *acpi_nfit_attribute_groups[] = {
+static const struct attribute_group *acpi_nfit_attribute_groups[] = {
 	&nvdimm_bus_attribute_group,
 	&acpi_nfit_attribute_group,
 	NULL,
 };
-EXPORT_SYMBOL_GPL(acpi_nfit_attribute_groups);
 
 static struct acpi_nfit_memory_map *to_nfit_memdev(struct device *dev)
 {
@@ -918,7 +1012,7 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
 	if (!adev)
 		return;
 
-	for (i = ND_CMD_ARS_CAP; i <= ND_CMD_ARS_STATUS; i++)
+	for (i = ND_CMD_ARS_CAP; i <= ND_CMD_CLEAR_ERROR; i++)
 		if (acpi_check_dsm(adev->handle, uuid, 1, 1ULL << i))
 			set_bit(i, &nd_desc->dsm_mask);
 }
@@ -1106,7 +1200,7 @@ static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw,
 	writeq(cmd, mmio->addr.base + offset);
 	wmb_blk(nfit_blk);
 
-	if (nfit_blk->dimm_flags & ND_BLK_DCR_LATCH)
+	if (nfit_blk->dimm_flags & NFIT_BLK_DCR_LATCH)
 		readq(mmio->addr.base + offset);
 }
 
@@ -1142,7 +1236,7 @@ static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk,
 			memcpy_to_pmem(mmio->addr.aperture + offset,
 					iobuf + copied, c);
 		else {
-			if (nfit_blk->dimm_flags & ND_BLK_READ_FLUSH)
+			if (nfit_blk->dimm_flags & NFIT_BLK_READ_FLUSH)
 				mmio_flush_range((void __force *)
 					mmio->addr.aperture + offset, c);
 
@@ -1329,13 +1423,13 @@ static int acpi_nfit_blk_get_flags(struct nvdimm_bus_descriptor *nd_desc,
 
 	memset(&flags, 0, sizeof(flags));
 	rc = nd_desc->ndctl(nd_desc, nvdimm, ND_CMD_DIMM_FLAGS, &flags,
-			sizeof(flags));
+			sizeof(flags), NULL);
 
 	if (rc >= 0 && flags.status == 0)
 		nfit_blk->dimm_flags = flags.flags;
 	else if (rc == -ENOTTY) {
 		/* fall back to a conservative default */
-		nfit_blk->dimm_flags = ND_BLK_DCR_LATCH | ND_BLK_READ_FLUSH;
+		nfit_blk->dimm_flags = NFIT_BLK_DCR_LATCH | NFIT_BLK_READ_FLUSH;
 		rc = 0;
 	} else
 		rc = -ENXIO;
@@ -1474,93 +1568,85 @@ static void acpi_nfit_blk_region_disable(struct nvdimm_bus *nvdimm_bus,
 	/* devm will free nfit_blk */
 }
 
-static int ars_get_cap(struct nvdimm_bus_descriptor *nd_desc,
-		struct nd_cmd_ars_cap *cmd, u64 addr, u64 length)
+static int ars_get_cap(struct acpi_nfit_desc *acpi_desc,
+		struct nd_cmd_ars_cap *cmd, struct nfit_spa *nfit_spa)
 {
-	cmd->address = addr;
-	cmd->length = length;
+	struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc;
+	struct acpi_nfit_system_address *spa = nfit_spa->spa;
+	int cmd_rc, rc;
 
-	return nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_CAP, cmd,
-			sizeof(*cmd));
+	cmd->address = spa->address;
+	cmd->length = spa->length;
+	rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_CAP, cmd,
+			sizeof(*cmd), &cmd_rc);
+	if (rc < 0)
+		return rc;
+	return cmd_rc;
 }
 
-static int ars_do_start(struct nvdimm_bus_descriptor *nd_desc,
-		struct nd_cmd_ars_start *cmd, u64 addr, u64 length)
+static int ars_start(struct acpi_nfit_desc *acpi_desc, struct nfit_spa *nfit_spa)
 {
 	int rc;
+	int cmd_rc;
+	struct nd_cmd_ars_start ars_start;
+	struct acpi_nfit_system_address *spa = nfit_spa->spa;
+	struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc;
 
-	cmd->address = addr;
-	cmd->length = length;
-	cmd->type = ND_ARS_PERSISTENT;
+	memset(&ars_start, 0, sizeof(ars_start));
+	ars_start.address = spa->address;
+	ars_start.length = spa->length;
+	if (nfit_spa_type(spa) == NFIT_SPA_PM)
+		ars_start.type = ND_ARS_PERSISTENT;
+	else if (nfit_spa_type(spa) == NFIT_SPA_VOLATILE)
+		ars_start.type = ND_ARS_VOLATILE;
+	else
+		return -ENOTTY;
 
-	while (1) {
-		rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_START, cmd,
-				sizeof(*cmd));
-		if (rc)
-			return rc;
-		switch (cmd->status) {
-		case 0:
-			return 0;
-		case 1:
-			/* ARS unsupported, but we should never get here */
-			return 0;
-		case 2:
-			return -EINVAL;
-		case 3:
-			/* ARS is in progress */
-			msleep(1000);
-			break;
-		default:
-			return -ENXIO;
-		}
-	}
+	rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_START, &ars_start,
+			sizeof(ars_start), &cmd_rc);
+
+	if (rc < 0)
+		return rc;
+	return cmd_rc;
 }
 
-static int ars_get_status(struct nvdimm_bus_descriptor *nd_desc,
-		struct nd_cmd_ars_status *cmd)
+static int ars_continue(struct acpi_nfit_desc *acpi_desc)
 {
-	int rc;
+	int rc, cmd_rc;
+	struct nd_cmd_ars_start ars_start;
+	struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc;
+	struct nd_cmd_ars_status *ars_status = acpi_desc->ars_status;
+
+	memset(&ars_start, 0, sizeof(ars_start));
+	ars_start.address = ars_status->restart_address;
+	ars_start.length = ars_status->restart_length;
+	ars_start.type = ars_status->type;
+	rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_START, &ars_start,
+			sizeof(ars_start), &cmd_rc);
+	if (rc < 0)
+		return rc;
+	return cmd_rc;
+}
 
-	while (1) {
-		rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_STATUS, cmd,
-			sizeof(*cmd));
-		if (rc || cmd->status & 0xffff)
-			return -ENXIO;
+static int ars_get_status(struct acpi_nfit_desc *acpi_desc)
+{
+	struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc;
+	struct nd_cmd_ars_status *ars_status = acpi_desc->ars_status;
+	int rc, cmd_rc;
 
-		/* Check extended status (Upper two bytes) */
-		switch (cmd->status >> 16) {
-		case 0:
-			return 0;
-		case 1:
-			/* ARS is in progress */
-			msleep(1000);
-			break;
-		case 2:
-			/* No ARS performed for the current boot */
-			return 0;
-		default:
-			return -ENXIO;
-		}
-	}
+	rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_STATUS, ars_status,
+			acpi_desc->ars_status_size, &cmd_rc);
+	if (rc < 0)
+		return rc;
+	return cmd_rc;
 }
 
 static int ars_status_process_records(struct nvdimm_bus *nvdimm_bus,
-		struct nd_cmd_ars_status *ars_status, u64 start)
+		struct nd_cmd_ars_status *ars_status)
 {
 	int rc;
 	u32 i;
 
-	/*
-	 * The address field returned by ars_status should be either
-	 * less than or equal to the address we last started ARS for.
-	 * The (start, length) returned by ars_status should also have
-	 * non-zero overlap with the range we started ARS for.
-	 * If this is not the case, bail.
-	 */
-	if (ars_status->address > start ||
-			(ars_status->address + ars_status->length < start))
-		return -ENXIO;
-
 	for (i = 0; i < ars_status->num_records; i++) {
 		rc = nvdimm_bus_add_poison(nvdimm_bus,
 				ars_status->records[i].err_address,
@@ -1572,110 +1658,56 @@ static int ars_status_process_records(struct nvdimm_bus *nvdimm_bus,
 	return 0;
 }
 
-static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc,
-		struct nd_region_desc *ndr_desc)
+static void acpi_nfit_remove_resource(void *data)
 {
-	struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc;
-	struct nvdimm_bus *nvdimm_bus = acpi_desc->nvdimm_bus;
-	struct nd_cmd_ars_status *ars_status = NULL;
-	struct nd_cmd_ars_start *ars_start = NULL;
-	struct nd_cmd_ars_cap *ars_cap = NULL;
-	u64 start, len, cur, remaining;
-	int rc;
+	struct resource *res = data;
 
-	ars_cap = kzalloc(sizeof(*ars_cap), GFP_KERNEL);
-	if (!ars_cap)
-		return -ENOMEM;
-
-	start = ndr_desc->res->start;
-	len = ndr_desc->res->end - ndr_desc->res->start + 1;
-
-	rc = ars_get_cap(nd_desc, ars_cap, start, len);
-	if (rc)
-		goto out;
-
-	/*
-	 * If ARS is unsupported, or if the 'Persistent Memory Scrub' flag in
-	 * extended status is not set, skip this but continue initialization
-	 */
-	if ((ars_cap->status & 0xffff) ||
-		!(ars_cap->status >> 16 & ND_ARS_PERSISTENT)) {
-		dev_warn(acpi_desc->dev,
-			"ARS unsupported (status: 0x%x), won't create an error list\n",
-			ars_cap->status);
-		goto out;
-	}
-
-	/*
-	 * Check if a full-range ARS has been run. If so, use those results
-	 * without having to start a new ARS.
-	 */
-	ars_status = kzalloc(ars_cap->max_ars_out + sizeof(*ars_status),
-			GFP_KERNEL);
-	if (!ars_status) {
-		rc = -ENOMEM;
-		goto out;
-	}
+	remove_resource(res);
+}
 
-	rc = ars_get_status(nd_desc, ars_status);
-	if (rc)
-		goto out;
+static int acpi_nfit_insert_resource(struct acpi_nfit_desc *acpi_desc,
+		struct nd_region_desc *ndr_desc)
+{
+	struct resource *res, *nd_res = ndr_desc->res;
+	int is_pmem, ret;
 
-	if (ars_status->address <= start &&
-		(ars_status->address + ars_status->length >= start + len)) {
-		rc = ars_status_process_records(nvdimm_bus, ars_status, start);
-		goto out;
-	}
+	/* No operation if the region is already registered as PMEM */
+	is_pmem = region_intersects(nd_res->start, resource_size(nd_res),
+				IORESOURCE_MEM, IORES_DESC_PERSISTENT_MEMORY);
+	if (is_pmem == REGION_INTERSECTS)
+		return 0;
 
-	/*
-	 * ARS_STATUS can overflow if the number of poison entries found is
-	 * greater than the maximum buffer size (ars_cap->max_ars_out)
-	 * To detect overflow, check if the length field of ars_status
-	 * is less than the length we supplied. If so, process the
-	 * error entries we got, adjust the start point, and start again
-	 */
-	ars_start = kzalloc(sizeof(*ars_start), GFP_KERNEL);
-	if (!ars_start)
+	res = devm_kzalloc(acpi_desc->dev, sizeof(*res), GFP_KERNEL);
+	if (!res)
 		return -ENOMEM;
 
-	cur = start;
-	remaining = len;
-	do {
-		u64 done, end;
+	res->name = "Persistent Memory";
+	res->start = nd_res->start;
+	res->end = nd_res->end;
+	res->flags = IORESOURCE_MEM;
+	res->desc = IORES_DESC_PERSISTENT_MEMORY;
 
-		rc = ars_do_start(nd_desc, ars_start, cur, remaining);
-		if (rc)
-			goto out;
+	ret = insert_resource(&iomem_resource, res);
+	if (ret)
+		return ret;
 
-		rc = ars_get_status(nd_desc, ars_status);
-		if (rc)
-			goto out;
-
-		rc = ars_status_process_records(nvdimm_bus, ars_status, cur);
-		if (rc)
-			goto out;
-
-		end = min(cur + remaining,
-			ars_status->address + ars_status->length);
-		done = end - cur;
-		cur += done;
-		remaining -= done;
-	} while (remaining);
+	ret = devm_add_action(acpi_desc->dev, acpi_nfit_remove_resource, res);
+	if (ret) {
+		remove_resource(res);
+		return ret;
+	}
 
- out:
-	kfree(ars_cap);
-	kfree(ars_start);
-	kfree(ars_status);
-	return rc;
+	return 0;
 }
 
 static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc,
 		struct nd_mapping *nd_mapping, struct nd_region_desc *ndr_desc,
 		struct acpi_nfit_memory_map *memdev,
-		struct acpi_nfit_system_address *spa)
+		struct nfit_spa *nfit_spa)
 {
 	struct nvdimm *nvdimm = acpi_nfit_dimm_by_handle(acpi_desc,
 			memdev->device_handle);
+	struct acpi_nfit_system_address *spa = nfit_spa->spa;
 	struct nd_blk_region_desc *ndbr_desc;
 	struct nfit_mem *nfit_mem;
 	int blk_valid = 0;
@@ -1711,7 +1743,9 @@ static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc,
 		ndbr_desc->enable = acpi_nfit_blk_region_enable;
 		ndbr_desc->disable = acpi_nfit_blk_region_disable;
 		ndbr_desc->do_io = acpi_desc->blk_do_io;
-		if (!nvdimm_blk_region_create(acpi_desc->nvdimm_bus, ndr_desc))
+		nfit_spa->nd_region = nvdimm_blk_region_create(acpi_desc->nvdimm_bus,
+				ndr_desc);
+		if (!nfit_spa->nd_region)
 			return -ENOMEM;
 		break;
 	}
@@ -1731,7 +1765,7 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 	struct resource res;
 	int count = 0, rc;
 
-	if (nfit_spa->is_registered)
+	if (nfit_spa->nd_region)
 		return 0;
 
 	if (spa->range_index == 0) {
@@ -1768,47 +1802,332 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 		}
 		nd_mapping = &nd_mappings[count++];
 		rc = acpi_nfit_init_mapping(acpi_desc, nd_mapping, ndr_desc,
-				memdev, spa);
+				memdev, nfit_spa);
 		if (rc)
-			return rc;
+			goto out;
 	}
 
 	ndr_desc->nd_mapping = nd_mappings;
 	ndr_desc->num_mappings = count;
 	rc = acpi_nfit_init_interleave_set(acpi_desc, ndr_desc, spa);
 	if (rc)
-		return rc;
+		goto out;
 
 	nvdimm_bus = acpi_desc->nvdimm_bus;
 	if (nfit_spa_type(spa) == NFIT_SPA_PM) {
-		rc = acpi_nfit_find_poison(acpi_desc, ndr_desc);
+		rc = acpi_nfit_insert_resource(acpi_desc, ndr_desc);
 		if (rc) {
-			dev_err(acpi_desc->dev,
-				"error while performing ARS to find poison: %d\n",
+			dev_warn(acpi_desc->dev,
+				"failed to insert pmem resource to iomem: %d\n",
 				rc);
-			return rc;
+			goto out;
 		}
-		if (!nvdimm_pmem_region_create(nvdimm_bus, ndr_desc))
-			return -ENOMEM;
+
+		nfit_spa->nd_region = nvdimm_pmem_region_create(nvdimm_bus,
+				ndr_desc);
+		if (!nfit_spa->nd_region)
+			rc = -ENOMEM;
 	} else if (nfit_spa_type(spa) == NFIT_SPA_VOLATILE) {
-		if (!nvdimm_volatile_region_create(nvdimm_bus, ndr_desc))
-			return -ENOMEM;
+		nfit_spa->nd_region = nvdimm_volatile_region_create(nvdimm_bus,
+				ndr_desc);
+		if (!nfit_spa->nd_region)
+			rc = -ENOMEM;
+	}
+
+ out:
+	if (rc)
+		dev_err(acpi_desc->dev, "failed to register spa range %d\n",
+				nfit_spa->spa->range_index);
+	return rc;
+}
+
+static int ars_status_alloc(struct acpi_nfit_desc *acpi_desc,
+		u32 max_ars)
+{
+	struct device *dev = acpi_desc->dev;
+	struct nd_cmd_ars_status *ars_status;
+
+	if (acpi_desc->ars_status && acpi_desc->ars_status_size >= max_ars) {
+		memset(acpi_desc->ars_status, 0, acpi_desc->ars_status_size);
+		return 0;
 	}
 
-	nfit_spa->is_registered = 1;
+	if (acpi_desc->ars_status)
+		devm_kfree(dev, acpi_desc->ars_status);
+	acpi_desc->ars_status = NULL;
+	ars_status = devm_kzalloc(dev, max_ars, GFP_KERNEL);
+	if (!ars_status)
+		return -ENOMEM;
+	acpi_desc->ars_status = ars_status;
+	acpi_desc->ars_status_size = max_ars;
 	return 0;
 }
 
-static int acpi_nfit_register_regions(struct acpi_nfit_desc *acpi_desc)
+static int acpi_nfit_query_poison(struct acpi_nfit_desc *acpi_desc,
+		struct nfit_spa *nfit_spa)
+{
+	struct acpi_nfit_system_address *spa = nfit_spa->spa;
+	int rc;
+
+	if (!nfit_spa->max_ars) {
+		struct nd_cmd_ars_cap ars_cap;
+
+		memset(&ars_cap, 0, sizeof(ars_cap));
+		rc = ars_get_cap(acpi_desc, &ars_cap, nfit_spa);
+		if (rc < 0)
+			return rc;
+		nfit_spa->max_ars = ars_cap.max_ars_out;
+		nfit_spa->clear_err_unit = ars_cap.clear_err_unit;
+		/* check that the supported scrub types match the spa type */
+		if (nfit_spa_type(spa) == NFIT_SPA_VOLATILE &&
+				((ars_cap.status >> 16) & ND_ARS_VOLATILE) == 0)
+			return -ENOTTY;
+		else if (nfit_spa_type(spa) == NFIT_SPA_PM &&
+				((ars_cap.status >> 16) & ND_ARS_PERSISTENT) == 0)
+			return -ENOTTY;
+	}
+
+	if (ars_status_alloc(acpi_desc, nfit_spa->max_ars))
+		return -ENOMEM;
+
+	rc = ars_get_status(acpi_desc);
+	if (rc < 0 && rc != -ENOSPC)
+		return rc;
+
+	if (ars_status_process_records(acpi_desc->nvdimm_bus,
+				acpi_desc->ars_status))
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void acpi_nfit_async_scrub(struct acpi_nfit_desc *acpi_desc,
+		struct nfit_spa *nfit_spa)
+{
+	struct acpi_nfit_system_address *spa = nfit_spa->spa;
+	unsigned int overflow_retry = scrub_overflow_abort;
+	u64 init_ars_start = 0, init_ars_len = 0;
+	struct device *dev = acpi_desc->dev;
+	unsigned int tmo = scrub_timeout;
+	int rc;
+
+	if (nfit_spa->ars_done || !nfit_spa->nd_region)
+		return;
+
+	rc = ars_start(acpi_desc, nfit_spa);
+	/*
+	 * If we timed out the initial scan we'll still be busy here,
+	 * and will wait another timeout before giving up permanently.
+	 */
+	if (rc < 0 && rc != -EBUSY)
+		return;
+
+	do {
+		u64 ars_start, ars_len;
+
+		if (acpi_desc->cancel)
+			break;
+		rc = acpi_nfit_query_poison(acpi_desc, nfit_spa);
+		if (rc == -ENOTTY)
+			break;
+		if (rc == -EBUSY && !tmo) {
+			dev_warn(dev, "range %d ars timeout, aborting\n",
+					spa->range_index);
+			break;
+		}
+
+		if (rc == -EBUSY) {
+			/*
+			 * Note, entries may be appended to the list
+			 * while the lock is dropped, but the workqueue
+			 * being active prevents entries being deleted /
+			 * freed.
+			 */
+			mutex_unlock(&acpi_desc->init_mutex);
+			ssleep(1);
+			tmo--;
+			mutex_lock(&acpi_desc->init_mutex);
+			continue;
+		}
+
+		/* we got some results, but there are more pending... */
+		if (rc == -ENOSPC && overflow_retry--) {
+			if (!init_ars_len) {
+				init_ars_len = acpi_desc->ars_status->length;
+				init_ars_start = acpi_desc->ars_status->address;
+			}
+			rc = ars_continue(acpi_desc);
+		}
+
+		if (rc < 0) {
+			dev_warn(dev, "range %d ars continuation failed\n",
+					spa->range_index);
+			break;
+		}
+
+		if (init_ars_len) {
+			ars_start = init_ars_start;
+			ars_len = init_ars_len;
+		} else {
+			ars_start = acpi_desc->ars_status->address;
+			ars_len = acpi_desc->ars_status->length;
+		}
+		dev_dbg(dev, "spa range: %d ars from %#llx + %#llx complete\n",
+				spa->range_index, ars_start, ars_len);
+		/* notify the region about new poison entries */
+		nvdimm_region_notify(nfit_spa->nd_region,
+				NVDIMM_REVALIDATE_POISON);
+		break;
+	} while (1);
+}
+
+static void acpi_nfit_scrub(struct work_struct *work)
 {
+	struct device *dev;
+	u64 init_scrub_length = 0;
 	struct nfit_spa *nfit_spa;
+	u64 init_scrub_address = 0;
+	bool init_ars_done = false;
+	struct acpi_nfit_desc *acpi_desc;
+	unsigned int tmo = scrub_timeout;
+	unsigned int overflow_retry = scrub_overflow_abort;
 
+	acpi_desc = container_of(work, typeof(*acpi_desc), work);
+	dev = acpi_desc->dev;
+
+	/*
+	 * We scrub in 2 phases.  The first phase waits for any platform
+	 * firmware initiated scrubs to complete and then we go search for the
+	 * affected spa regions to mark them scanned.  In the second phase we
+	 * initiate a directed scrub for every range that was not scrubbed in
+	 * phase 1.
+	 */
+
+	/* process platform firmware initiated scrubs */
+ retry:
+	mutex_lock(&acpi_desc->init_mutex);
 	list_for_each_entry(nfit_spa, &acpi_desc->spas, list) {
-		int rc = acpi_nfit_register_region(acpi_desc, nfit_spa);
+		struct nd_cmd_ars_status *ars_status;
+		struct acpi_nfit_system_address *spa;
+		u64 ars_start, ars_len;
+		int rc;
 
-		if (rc)
-			return rc;
+		if (acpi_desc->cancel)
+			break;
+
+		if (nfit_spa->nd_region)
+			continue;
+
+		if (init_ars_done) {
+			/*
+			 * No need to re-query, we're now just
+			 * reconciling all the ranges covered by the
+			 * initial scrub
+			 */
+			rc = 0;
+		} else
+			rc = acpi_nfit_query_poison(acpi_desc, nfit_spa);
+
+		if (rc == -ENOTTY) {
+			/* no ars capability, just register spa and move on */
+			acpi_nfit_register_region(acpi_desc, nfit_spa);
+			continue;
+		}
+
+		if (rc == -EBUSY && !tmo) {
+			/* fallthrough to directed scrub in phase 2 */
+			dev_warn(dev, "timeout awaiting ars results, continuing...\n");
+			break;
+		} else if (rc == -EBUSY) {
+			mutex_unlock(&acpi_desc->init_mutex);
+			ssleep(1);
+			tmo--;
+			goto retry;
+		}
+
+		/* we got some results, but there are more pending... */
+		if (rc == -ENOSPC && overflow_retry--) {
+			ars_status = acpi_desc->ars_status;
+			/*
+			 * Record the original scrub range, so that we
+			 * can recall all the ranges impacted by the
+			 * initial scrub.
+			 */
+			if (!init_scrub_length) {
+				init_scrub_length = ars_status->length;
+				init_scrub_address = ars_status->address;
+			}
+			rc = ars_continue(acpi_desc);
+			if (rc == 0) {
+				mutex_unlock(&acpi_desc->init_mutex);
+				goto retry;
+			}
+		}
+
+		if (rc < 0) {
+			/*
+			 * Initial scrub failed, we'll give it one more
+			 * try below...
+			 */
+			break;
+		}
+
+		/* We got some final results, record completed ranges */
+		ars_status = acpi_desc->ars_status;
+		if (init_scrub_length) {
+			ars_start = init_scrub_address;
+			ars_len = ars_start + init_scrub_length;
+		} else {
+			ars_start = ars_status->address;
+			ars_len = ars_status->length;
+		}
+		spa = nfit_spa->spa;
+
+		if (!init_ars_done) {
+			init_ars_done = true;
+			dev_dbg(dev, "init scrub %#llx + %#llx complete\n",
+					ars_start, ars_len);
+		}
+		if (ars_start <= spa->address && ars_start + ars_len
+				>= spa->address + spa->length)
+			acpi_nfit_register_region(acpi_desc, nfit_spa);
 	}
+
+	/*
+	 * For all the ranges not covered by an initial scrub we still
+	 * want to see if there are errors, but it's ok to discover them
+	 * asynchronously.
+	 */
+	list_for_each_entry(nfit_spa, &acpi_desc->spas, list) {
+		/*
+		 * Flag all the ranges that still need scrubbing, but
+		 * register them now to make data available.
+		 */
+		if (nfit_spa->nd_region)
+			nfit_spa->ars_done = 1;
+		else
+			acpi_nfit_register_region(acpi_desc, nfit_spa);
+	}
+
+	list_for_each_entry(nfit_spa, &acpi_desc->spas, list)
+		acpi_nfit_async_scrub(acpi_desc, nfit_spa);
+	mutex_unlock(&acpi_desc->init_mutex);
+}
+
+static int acpi_nfit_register_regions(struct acpi_nfit_desc *acpi_desc)
+{
+	struct nfit_spa *nfit_spa;
+	int rc;
+
+	list_for_each_entry(nfit_spa, &acpi_desc->spas, list)
+		if (nfit_spa_type(nfit_spa->spa) == NFIT_SPA_DCR) {
+			/* BLK regions don't need to wait for ars results */
+			rc = acpi_nfit_register_region(acpi_desc, nfit_spa);
+			if (rc)
+				return rc;
+		}
+
+	queue_work(nfit_wq, &acpi_desc->work);
 	return 0;
 }
 
@@ -1894,15 +2213,64 @@ int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz)
 }
 EXPORT_SYMBOL_GPL(acpi_nfit_init);
 
-static struct acpi_nfit_desc *acpi_nfit_desc_init(struct acpi_device *adev)
+struct acpi_nfit_flush_work {
+	struct work_struct work;
+	struct completion cmp;
+};
+
+static void flush_probe(struct work_struct *work)
 {
-	struct nvdimm_bus_descriptor *nd_desc;
-	struct acpi_nfit_desc *acpi_desc;
-	struct device *dev = &adev->dev;
+	struct acpi_nfit_flush_work *flush;
 
-	acpi_desc = devm_kzalloc(dev, sizeof(*acpi_desc), GFP_KERNEL);
-	if (!acpi_desc)
-		return ERR_PTR(-ENOMEM);
+	flush = container_of(work, typeof(*flush), work);
+	complete(&flush->cmp);
+}
+
+static int acpi_nfit_flush_probe(struct nvdimm_bus_descriptor *nd_desc)
+{
+	struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc);
+	struct device *dev = acpi_desc->dev;
+	struct acpi_nfit_flush_work flush;
+
+	/* bounce the device lock to flush acpi_nfit_add / acpi_nfit_notify */
+	device_lock(dev);
+	device_unlock(dev);
+
+	/*
+	 * Scrub work could take 10s of seconds, userspace may give up so we
+	 * need to be interruptible while waiting.
+	 */
+	INIT_WORK_ONSTACK(&flush.work, flush_probe);
+	COMPLETION_INITIALIZER_ONSTACK(flush.cmp);
+	queue_work(nfit_wq, &flush.work);
+	return wait_for_completion_interruptible(&flush.cmp);
+}
+
+static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc,
+		struct nvdimm *nvdimm, unsigned int cmd)
+{
+	struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc);
+
+	if (nvdimm)
+		return 0;
+	if (cmd != ND_CMD_ARS_START)
+		return 0;
+
+	/*
+	 * The kernel and userspace may race to initiate a scrub, but
+	 * the scrub thread is prepared to lose that initial race.  It
+	 * just needs guarantees that any ars it initiates are not
+	 * interrupted by any intervening start reqeusts from userspace.
+	 */
+	if (work_busy(&acpi_desc->work))
+		return -EBUSY;
+
+	return 0;
+}
+
+void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev)
+{
+	struct nvdimm_bus_descriptor *nd_desc;
 
 	dev_set_drvdata(dev, acpi_desc);
 	acpi_desc->dev = dev;
@@ -1910,14 +2278,10 @@ static struct acpi_nfit_desc *acpi_nfit_desc_init(struct acpi_device *adev)
 	nd_desc = &acpi_desc->nd_desc;
 	nd_desc->provider_name = "ACPI.NFIT";
 	nd_desc->ndctl = acpi_nfit_ctl;
+	nd_desc->flush_probe = acpi_nfit_flush_probe;
+	nd_desc->clear_to_send = acpi_nfit_clear_to_send;
 	nd_desc->attr_groups = acpi_nfit_attribute_groups;
 
-	acpi_desc->nvdimm_bus = nvdimm_bus_register(dev, nd_desc);
-	if (!acpi_desc->nvdimm_bus) {
-		devm_kfree(dev, acpi_desc);
-		return ERR_PTR(-ENXIO);
-	}
-
 	INIT_LIST_HEAD(&acpi_desc->spa_maps);
 	INIT_LIST_HEAD(&acpi_desc->spas);
 	INIT_LIST_HEAD(&acpi_desc->dcrs);
@@ -1928,9 +2292,9 @@ static struct acpi_nfit_desc *acpi_nfit_desc_init(struct acpi_device *adev)
 	INIT_LIST_HEAD(&acpi_desc->dimms);
 	mutex_init(&acpi_desc->spa_map_mutex);
 	mutex_init(&acpi_desc->init_mutex);
-
-	return acpi_desc;
+	INIT_WORK(&acpi_desc->work, acpi_nfit_scrub);
 }
+EXPORT_SYMBOL_GPL(acpi_nfit_desc_init);
 
 static int acpi_nfit_add(struct acpi_device *adev)
 {
@@ -1949,12 +2313,13 @@ static int acpi_nfit_add(struct acpi_device *adev)
 		return 0;
 	}
 
-	acpi_desc = acpi_nfit_desc_init(adev);
-	if (IS_ERR(acpi_desc)) {
-		dev_err(dev, "%s: error initializing acpi_desc: %ld\n",
-				__func__, PTR_ERR(acpi_desc));
-		return PTR_ERR(acpi_desc);
-	}
+	acpi_desc = devm_kzalloc(dev, sizeof(*acpi_desc), GFP_KERNEL);
+	if (!acpi_desc)
+		return -ENOMEM;
+	acpi_nfit_desc_init(acpi_desc, &adev->dev);
+	acpi_desc->nvdimm_bus = nvdimm_bus_register(dev, &acpi_desc->nd_desc);
+	if (!acpi_desc->nvdimm_bus)
+		return -ENOMEM;
 
 	/*
 	 * Save the acpi header for later and then skip it,
@@ -1993,6 +2358,8 @@ static int acpi_nfit_remove(struct acpi_device *adev)
 {
 	struct acpi_nfit_desc *acpi_desc = dev_get_drvdata(&adev->dev);
 
+	acpi_desc->cancel = 1;
+	flush_workqueue(nfit_wq);
 	nvdimm_bus_unregister(acpi_desc->nvdimm_bus);
 	return 0;
 }
@@ -2017,12 +2384,19 @@ static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
 	}
 
 	if (!acpi_desc) {
-		acpi_desc = acpi_nfit_desc_init(adev);
-		if (IS_ERR(acpi_desc)) {
-			dev_err(dev, "%s: error initializing acpi_desc: %ld\n",
-				__func__, PTR_ERR(acpi_desc));
+		acpi_desc = devm_kzalloc(dev, sizeof(*acpi_desc), GFP_KERNEL);
+		if (!acpi_desc)
 			goto out_unlock;
-		}
+		acpi_nfit_desc_init(acpi_desc, &adev->dev);
+		acpi_desc->nvdimm_bus = nvdimm_bus_register(dev, &acpi_desc->nd_desc);
+		if (!acpi_desc->nvdimm_bus)
+			goto out_unlock;
+	} else {
+		/*
+		 * Finish previous registration before considering new
+		 * regions.
+		 */
+		flush_workqueue(nfit_wq);
 	}
 
 	/* Evaluate _FIT */
@@ -2090,12 +2464,17 @@ static __init int nfit_init(void)
 	acpi_str_to_uuid(UUID_NFIT_BUS, nfit_uuid[NFIT_DEV_BUS]);
 	acpi_str_to_uuid(UUID_NFIT_DIMM, nfit_uuid[NFIT_DEV_DIMM]);
 
+	nfit_wq = create_singlethread_workqueue("nfit");
+	if (!nfit_wq)
+		return -ENOMEM;
+
 	return acpi_bus_register_driver(&acpi_nfit_driver);
 }
 
 static __exit void nfit_exit(void)
 {
 	acpi_bus_unregister_driver(&acpi_nfit_driver);
+	destroy_workqueue(nfit_wq);
 }
 
 module_init(nfit_init);
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index 3d549a383659..c75576b2d50e 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -14,6 +14,7 @@
  */
 #ifndef __NFIT_H__
 #define __NFIT_H__
+#include <linux/workqueue.h>
 #include <linux/libnvdimm.h>
 #include <linux/types.h>
 #include <linux/uuid.h>
@@ -40,15 +41,32 @@ enum nfit_uuids {
 	NFIT_UUID_MAX,
 };
 
+enum nfit_fic {
+	NFIT_FIC_BYTE = 0x101, /* byte-addressable energy backed */
+	NFIT_FIC_BLK = 0x201, /* block-addressable non-energy backed */
+	NFIT_FIC_BYTEN = 0x301, /* byte-addressable non-energy backed */
+};
+
 enum {
-	ND_BLK_READ_FLUSH = 1,
-	ND_BLK_DCR_LATCH = 2,
+	NFIT_BLK_READ_FLUSH = 1,
+	NFIT_BLK_DCR_LATCH = 2,
+	NFIT_ARS_STATUS_DONE = 0,
+	NFIT_ARS_STATUS_BUSY = 1 << 16,
+	NFIT_ARS_STATUS_NONE = 2 << 16,
+	NFIT_ARS_STATUS_INTR = 3 << 16,
+	NFIT_ARS_START_BUSY = 6,
+	NFIT_ARS_CAP_NONE = 1,
+	NFIT_ARS_F_OVERFLOW = 1,
+	NFIT_ARS_TIMEOUT = 90,
 };
 
 struct nfit_spa {
 	struct acpi_nfit_system_address *spa;
 	struct list_head list;
-	int is_registered;
+	struct nd_region *nd_region;
+	unsigned int ars_done:1;
+	u32 clear_err_unit;
+	u32 max_ars;
 };
 
 struct nfit_dcr {
@@ -110,6 +128,10 @@ struct acpi_nfit_desc {
 	struct list_head idts;
 	struct nvdimm_bus *nvdimm_bus;
 	struct device *dev;
+	struct nd_cmd_ars_status *ars_status;
+	size_t ars_status_size;
+	struct work_struct work;
+	unsigned int cancel:1;
 	unsigned long dimm_dsm_force_en;
 	unsigned long bus_dsm_force_en;
 	int (*blk_do_io)(struct nd_blk_region *ndbr, resource_size_t dpa,
@@ -182,5 +204,5 @@ static inline struct acpi_nfit_desc *to_acpi_desc(
 
 const u8 *to_nfit_uuid(enum nfit_uuids id);
 int acpi_nfit_init(struct acpi_nfit_desc *nfit, acpi_size sz);
-extern const struct attribute_group *acpi_nfit_attribute_groups[];
+void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev);
 #endif /* __NFIT_H__ */
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 67da6fb72274..814d5f83b75e 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -602,6 +602,14 @@ acpi_os_predefined_override(const struct acpi_predefined_names *init_val,
 	return AE_OK;
 }
 
+static void acpi_table_taint(struct acpi_table_header *table)
+{
+	pr_warn(PREFIX
+		"Override [%4.4s-%8.8s], this is unsafe: tainting kernel\n",
+		table->signature, table->oem_table_id);
+	add_taint(TAINT_OVERRIDDEN_ACPI_TABLE, LOCKDEP_NOW_UNRELIABLE);
+}
+
 #ifdef CONFIG_ACPI_INITRD_TABLE_OVERRIDE
 #include <linux/earlycpio.h>
 #include <linux/memblock.h>
@@ -636,6 +644,7 @@ static const char * const table_sigs[] = {
 
 #define ACPI_OVERRIDE_TABLES 64
 static struct cpio_data __initdata acpi_initrd_files[ACPI_OVERRIDE_TABLES];
+static DECLARE_BITMAP(acpi_initrd_installed, ACPI_OVERRIDE_TABLES);
 
 #define MAP_CHUNK_SIZE   (NR_FIX_BTMAPS << PAGE_SHIFT)
 
@@ -746,96 +755,125 @@ void __init acpi_initrd_override(void *data, size_t size)
 		}
 	}
 }
-#endif /* CONFIG_ACPI_INITRD_TABLE_OVERRIDE */
 
-static void acpi_table_taint(struct acpi_table_header *table)
+acpi_status
+acpi_os_physical_table_override(struct acpi_table_header *existing_table,
+				acpi_physical_address *address, u32 *length)
 {
-	pr_warn(PREFIX
-		"Override [%4.4s-%8.8s], this is unsafe: tainting kernel\n",
-		table->signature, table->oem_table_id);
-	add_taint(TAINT_OVERRIDDEN_ACPI_TABLE, LOCKDEP_NOW_UNRELIABLE);
-}
+	int table_offset = 0;
+	int table_index = 0;
+	struct acpi_table_header *table;
+	u32 table_length;
 
+	*length = 0;
+	*address = 0;
+	if (!acpi_tables_addr)
+		return AE_OK;
 
-acpi_status
-acpi_os_table_override(struct acpi_table_header * existing_table,
-		       struct acpi_table_header ** new_table)
-{
-	if (!existing_table || !new_table)
-		return AE_BAD_PARAMETER;
+	while (table_offset + ACPI_HEADER_SIZE <= all_tables_size) {
+		table = acpi_os_map_memory(acpi_tables_addr + table_offset,
+					   ACPI_HEADER_SIZE);
+		if (table_offset + table->length > all_tables_size) {
+			acpi_os_unmap_memory(table, ACPI_HEADER_SIZE);
+			WARN_ON(1);
+			return AE_OK;
+		}
 
-	*new_table = NULL;
+		table_length = table->length;
 
-#ifdef CONFIG_ACPI_CUSTOM_DSDT
-	if (strncmp(existing_table->signature, "DSDT", 4) == 0)
-		*new_table = (struct acpi_table_header *)AmlCode;
-#endif
-	if (*new_table != NULL)
+		/* Only override tables matched */
+		if (test_bit(table_index, acpi_initrd_installed) ||
+		    memcmp(existing_table->signature, table->signature, 4) ||
+		    memcmp(table->oem_table_id, existing_table->oem_table_id,
+			   ACPI_OEM_TABLE_ID_SIZE)) {
+			acpi_os_unmap_memory(table, ACPI_HEADER_SIZE);
+			goto next_table;
+		}
+
+		*length = table_length;
+		*address = acpi_tables_addr + table_offset;
 		acpi_table_taint(existing_table);
+		acpi_os_unmap_memory(table, ACPI_HEADER_SIZE);
+		set_bit(table_index, acpi_initrd_installed);
+		break;
+
+next_table:
+		table_offset += table_length;
+		table_index++;
+	}
 	return AE_OK;
 }
 
-acpi_status
-acpi_os_physical_table_override(struct acpi_table_header *existing_table,
-				acpi_physical_address *address,
-				u32 *table_length)
+void __init acpi_initrd_initialize_tables(void)
 {
-#ifndef CONFIG_ACPI_INITRD_TABLE_OVERRIDE
-	*table_length = 0;
-	*address = 0;
-	return AE_OK;
-#else
 	int table_offset = 0;
+	int table_index = 0;
+	u32 table_length;
 	struct acpi_table_header *table;
 
-	*table_length = 0;
-	*address = 0;
-
 	if (!acpi_tables_addr)
-		return AE_OK;
-
-	do {
-		if (table_offset + ACPI_HEADER_SIZE > all_tables_size) {
-			WARN_ON(1);
-			return AE_OK;
-		}
+		return;
 
+	while (table_offset + ACPI_HEADER_SIZE <= all_tables_size) {
 		table = acpi_os_map_memory(acpi_tables_addr + table_offset,
 					   ACPI_HEADER_SIZE);
-
 		if (table_offset + table->length > all_tables_size) {
 			acpi_os_unmap_memory(table, ACPI_HEADER_SIZE);
 			WARN_ON(1);
-			return AE_OK;
+			return;
 		}
 
-		table_offset += table->length;
+		table_length = table->length;
 
-		if (memcmp(existing_table->signature, table->signature, 4)) {
-			acpi_os_unmap_memory(table,
-				     ACPI_HEADER_SIZE);
-			continue;
-		}
-
-		/* Only override tables with matching oem id */
-		if (memcmp(table->oem_table_id, existing_table->oem_table_id,
-			   ACPI_OEM_TABLE_ID_SIZE)) {
-			acpi_os_unmap_memory(table,
-				     ACPI_HEADER_SIZE);
-			continue;
+		/* Skip RSDT/XSDT which should only be used for override */
+		if (test_bit(table_index, acpi_initrd_installed) ||
+		    ACPI_COMPARE_NAME(table->signature, ACPI_SIG_RSDT) ||
+		    ACPI_COMPARE_NAME(table->signature, ACPI_SIG_XSDT)) {
+			acpi_os_unmap_memory(table, ACPI_HEADER_SIZE);
+			goto next_table;
 		}
 
-		table_offset -= table->length;
-		*table_length = table->length;
+		acpi_table_taint(table);
 		acpi_os_unmap_memory(table, ACPI_HEADER_SIZE);
-		*address = acpi_tables_addr + table_offset;
-		break;
-	} while (table_offset + ACPI_HEADER_SIZE < all_tables_size);
+		acpi_install_table(acpi_tables_addr + table_offset, TRUE);
+		set_bit(table_index, acpi_initrd_installed);
+next_table:
+		table_offset += table_length;
+		table_index++;
+	}
+}
+#else
+acpi_status
+acpi_os_physical_table_override(struct acpi_table_header *existing_table,
+				acpi_physical_address *address,
+				u32 *table_length)
+{
+	*table_length = 0;
+	*address = 0;
+	return AE_OK;
+}
+
+void __init acpi_initrd_initialize_tables(void)
+{
+}
+#endif /* CONFIG_ACPI_INITRD_TABLE_OVERRIDE */
 
-	if (*address != 0)
+acpi_status
+acpi_os_table_override(struct acpi_table_header *existing_table,
+		       struct acpi_table_header **new_table)
+{
+	if (!existing_table || !new_table)
+		return AE_BAD_PARAMETER;
+
+	*new_table = NULL;
+
+#ifdef CONFIG_ACPI_CUSTOM_DSDT
+	if (strncmp(existing_table->signature, "DSDT", 4) == 0)
+		*new_table = (struct acpi_table_header *)AmlCode;
+#endif
+	if (*new_table != NULL)
 		acpi_table_taint(existing_table);
 	return AE_OK;
-#endif
 }
 
 static irqreturn_t acpi_irq(int irq, void *dev_id)
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index d30184c7f3bc..2c45dd3acc17 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -33,6 +33,7 @@
 #include <linux/pci.h>
 #include <linux/acpi.h>
 #include <linux/slab.h>
+#include <linux/interrupt.h>
 
 #define PREFIX "ACPI: "
 
@@ -387,6 +388,23 @@ static inline int acpi_isa_register_gsi(struct pci_dev *dev)
 }
 #endif
 
+static inline bool acpi_pci_irq_valid(struct pci_dev *dev, u8 pin)
+{
+#ifdef CONFIG_X86
+	/*
+	 * On x86 irq line 0xff means "unknown" or "no connection"
+	 * (PCI 3.0, Section 6.2.4, footnote on page 223).
+	 */
+	if (dev->irq == 0xff) {
+		dev->irq = IRQ_NOTCONNECTED;
+		dev_warn(&dev->dev, "PCI INT %c: not connected\n",
+			 pin_name(pin));
+		return false;
+	}
+#endif
+	return true;
+}
+
 int acpi_pci_irq_enable(struct pci_dev *dev)
 {
 	struct acpi_prt_entry *entry;
@@ -406,7 +424,7 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 		return 0;
 	}
 
-	if (pci_has_managed_irq(dev))
+	if (dev->irq_managed && dev->irq > 0)
 		return 0;
 
 	entry = acpi_pci_irq_lookup(dev, pin);
@@ -431,11 +449,14 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 	} else
 		gsi = -1;
 
-	/*
-	 * No IRQ known to the ACPI subsystem - maybe the BIOS / 
-	 * driver reported one, then use it. Exit in any case.
-	 */
 	if (gsi < 0) {
+		/*
+		 * No IRQ known to the ACPI subsystem - maybe the BIOS /
+		 * driver reported one, then use it. Exit in any case.
+		 */
+		if (!acpi_pci_irq_valid(dev, pin))
+			return 0;
+
 		if (acpi_isa_register_gsi(dev))
 			dev_warn(&dev->dev, "PCI INT %c: no GSI\n",
 				 pin_name(pin));
@@ -451,7 +472,8 @@ int acpi_pci_irq_enable(struct pci_dev *dev)
 		kfree(entry);
 		return rc;
 	}
-	pci_set_managed_irq(dev, rc);
+	dev->irq = rc;
+	dev->irq_managed = 1;
 
 	if (link)
 		snprintf(link_desc, sizeof(link_desc), " -> Link[%s]", link);
@@ -474,9 +496,17 @@ void acpi_pci_irq_disable(struct pci_dev *dev)
 	u8 pin;
 
 	pin = dev->pin;
-	if (!pin || !pci_has_managed_irq(dev))
+	if (!pin || !dev->irq_managed || dev->irq <= 0)
 		return;
 
+	/* Keep IOAPIC pin configuration when suspending */
+	if (dev->dev.power.is_prepared)
+		return;
+#ifdef	CONFIG_PM
+	if (dev->dev.power.runtime_status == RPM_SUSPENDING)
+		return;
+#endif
+
 	entry = acpi_pci_irq_lookup(dev, pin);
 	if (!entry)
 		return;
@@ -496,6 +526,6 @@ void acpi_pci_irq_disable(struct pci_dev *dev)
 	dev_dbg(&dev->dev, "PCI INT %c disabled\n", pin_name(pin));
 	if (gsi >= 0) {
 		acpi_unregister_gsi(gsi);
-		pci_reset_managed_irq(dev);
+		dev->irq_managed = 0;
 	}
 }
diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c
index fa2863567eed..ededa909df2f 100644
--- a/drivers/acpi/pci_link.c
+++ b/drivers/acpi/pci_link.c
@@ -4,7 +4,6 @@
  *  Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com>
  *  Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
  *  Copyright (C) 2002       Dominik Brodowski <devel@brodo.de>
- *  Copyright (c) 2015, The Linux Foundation. All rights reserved.
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *
@@ -438,6 +437,7 @@ static int acpi_pci_link_set(struct acpi_pci_link *link, int irq)
  * enabled system.
  */
 
+#define ACPI_MAX_IRQS		256
 #define ACPI_MAX_ISA_IRQ	16
 
 #define PIRQ_PENALTY_PCI_AVAILABLE	(0)
@@ -447,7 +447,7 @@ static int acpi_pci_link_set(struct acpi_pci_link *link, int irq)
 #define PIRQ_PENALTY_ISA_USED		(16*16*16*16*16)
 #define PIRQ_PENALTY_ISA_ALWAYS		(16*16*16*16*16*16)
 
-static int acpi_irq_isa_penalty[ACPI_MAX_ISA_IRQ] = {
+static int acpi_irq_penalty[ACPI_MAX_IRQS] = {
 	PIRQ_PENALTY_ISA_ALWAYS,	/* IRQ0 timer */
 	PIRQ_PENALTY_ISA_ALWAYS,	/* IRQ1 keyboard */
 	PIRQ_PENALTY_ISA_ALWAYS,	/* IRQ2 cascade */
@@ -464,68 +464,9 @@ static int acpi_irq_isa_penalty[ACPI_MAX_ISA_IRQ] = {
 	PIRQ_PENALTY_ISA_USED,		/* IRQ13 fpe, sometimes */
 	PIRQ_PENALTY_ISA_USED,		/* IRQ14 ide0 */
 	PIRQ_PENALTY_ISA_USED,		/* IRQ15 ide1 */
+	/* >IRQ15 */
 };
 
-struct irq_penalty_info {
-	int irq;
-	int penalty;
-	struct list_head node;
-};
-
-static LIST_HEAD(acpi_irq_penalty_list);
-
-static int acpi_irq_get_penalty(int irq)
-{
-	struct irq_penalty_info *irq_info;
-
-	if (irq < ACPI_MAX_ISA_IRQ)
-		return acpi_irq_isa_penalty[irq];
-
-	list_for_each_entry(irq_info, &acpi_irq_penalty_list, node) {
-		if (irq_info->irq == irq)
-			return irq_info->penalty;
-	}
-
-	return 0;
-}
-
-static int acpi_irq_set_penalty(int irq, int new_penalty)
-{
-	struct irq_penalty_info *irq_info;
-
-	/* see if this is a ISA IRQ */
-	if (irq < ACPI_MAX_ISA_IRQ) {
-		acpi_irq_isa_penalty[irq] = new_penalty;
-		return 0;
-	}
-
-	/* next, try to locate from the dynamic list */
-	list_for_each_entry(irq_info, &acpi_irq_penalty_list, node) {
-		if (irq_info->irq == irq) {
-			irq_info->penalty  = new_penalty;
-			return 0;
-		}
-	}
-
-	/* nope, let's allocate a slot for this IRQ */
-	irq_info = kzalloc(sizeof(*irq_info), GFP_KERNEL);
-	if (!irq_info)
-		return -ENOMEM;
-
-	irq_info->irq = irq;
-	irq_info->penalty = new_penalty;
-	list_add_tail(&irq_info->node, &acpi_irq_penalty_list);
-
-	return 0;
-}
-
-static void acpi_irq_add_penalty(int irq, int penalty)
-{
-	int curpen = acpi_irq_get_penalty(irq);
-
-	acpi_irq_set_penalty(irq, curpen + penalty);
-}
-
 int __init acpi_irq_penalty_init(void)
 {
 	struct acpi_pci_link *link;
@@ -546,16 +487,15 @@ int __init acpi_irq_penalty_init(void)
 			    link->irq.possible_count;
 
 			for (i = 0; i < link->irq.possible_count; i++) {
-				if (link->irq.possible[i] < ACPI_MAX_ISA_IRQ) {
-					int irqpos = link->irq.possible[i];
-
-					acpi_irq_add_penalty(irqpos, penalty);
-				}
+				if (link->irq.possible[i] < ACPI_MAX_ISA_IRQ)
+					acpi_irq_penalty[link->irq.
+							 possible[i]] +=
+					    penalty;
 			}
 
 		} else if (link->irq.active) {
-			acpi_irq_add_penalty(link->irq.active,
-					     PIRQ_PENALTY_PCI_POSSIBLE);
+			acpi_irq_penalty[link->irq.active] +=
+			    PIRQ_PENALTY_PCI_POSSIBLE;
 		}
 	}
 
@@ -607,12 +547,12 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link)
 		 * the use of IRQs 9, 10, 11, and >15.
 		 */
 		for (i = (link->irq.possible_count - 1); i >= 0; i--) {
-			if (acpi_irq_get_penalty(irq) >
-			    acpi_irq_get_penalty(link->irq.possible[i]))
+			if (acpi_irq_penalty[irq] >
+			    acpi_irq_penalty[link->irq.possible[i]])
 				irq = link->irq.possible[i];
 		}
 	}
-	if (acpi_irq_get_penalty(irq) >= PIRQ_PENALTY_ISA_ALWAYS) {
+	if (acpi_irq_penalty[irq] >= PIRQ_PENALTY_ISA_ALWAYS) {
 		printk(KERN_ERR PREFIX "No IRQ available for %s [%s]. "
 			    "Try pci=noacpi or acpi=off\n",
 			    acpi_device_name(link->device),
@@ -628,8 +568,7 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link)
 			    acpi_device_bid(link->device));
 		return -ENODEV;
 	} else {
-		acpi_irq_add_penalty(link->irq.active, PIRQ_PENALTY_PCI_USING);
-
+		acpi_irq_penalty[link->irq.active] += PIRQ_PENALTY_PCI_USING;
 		printk(KERN_WARNING PREFIX "%s [%s] enabled at IRQ %d\n",
 		       acpi_device_name(link->device),
 		       acpi_device_bid(link->device), link->irq.active);
@@ -839,7 +778,7 @@ static void acpi_pci_link_remove(struct acpi_device *device)
 }
 
 /*
- * modify penalty from cmdline
+ * modify acpi_irq_penalty[] from cmdline
  */
 static int __init acpi_irq_penalty_update(char *str, int used)
 {
@@ -857,10 +796,13 @@ static int __init acpi_irq_penalty_update(char *str, int used)
 		if (irq < 0)
 			continue;
 
+		if (irq >= ARRAY_SIZE(acpi_irq_penalty))
+			continue;
+
 		if (used)
-			acpi_irq_add_penalty(irq, PIRQ_PENALTY_ISA_USED);
+			acpi_irq_penalty[irq] += PIRQ_PENALTY_ISA_USED;
 		else
-			acpi_irq_set_penalty(irq, PIRQ_PENALTY_PCI_AVAILABLE);
+			acpi_irq_penalty[irq] = PIRQ_PENALTY_PCI_AVAILABLE;
 
 		if (retval != 2)	/* no next number */
 			break;
@@ -877,15 +819,18 @@ static int __init acpi_irq_penalty_update(char *str, int used)
  */
 void acpi_penalize_isa_irq(int irq, int active)
 {
-	if (irq >= 0)
-		acpi_irq_add_penalty(irq, active ?
-			PIRQ_PENALTY_ISA_USED : PIRQ_PENALTY_PCI_USING);
+	if (irq >= 0 && irq < ARRAY_SIZE(acpi_irq_penalty)) {
+		if (active)
+			acpi_irq_penalty[irq] += PIRQ_PENALTY_ISA_USED;
+		else
+			acpi_irq_penalty[irq] += PIRQ_PENALTY_PCI_USING;
+	}
 }
 
 bool acpi_isa_irq_available(int irq)
 {
-	return irq >= 0 &&
-		(acpi_irq_get_penalty(irq) < PIRQ_PENALTY_ISA_ALWAYS);
+	return irq >= 0 && (irq >= ARRAY_SIZE(acpi_irq_penalty) ||
+			    acpi_irq_penalty[irq] < PIRQ_PENALTY_ISA_ALWAYS);
 }
 
 /*
@@ -895,18 +840,13 @@ bool acpi_isa_irq_available(int irq)
  */
 void acpi_penalize_sci_irq(int irq, int trigger, int polarity)
 {
-	int penalty;
-
-	if (irq < 0)
-		return;
-
-	if (trigger != ACPI_MADT_TRIGGER_LEVEL ||
-	    polarity != ACPI_MADT_POLARITY_ACTIVE_LOW)
-		penalty = PIRQ_PENALTY_ISA_ALWAYS;
-	else
-		penalty = PIRQ_PENALTY_PCI_USING;
-
-	acpi_irq_add_penalty(irq, penalty);
+	if (irq >= 0 && irq < ARRAY_SIZE(acpi_irq_penalty)) {
+		if (trigger != ACPI_MADT_TRIGGER_LEVEL ||
+		    polarity != ACPI_MADT_POLARITY_ACTIVE_LOW)
+			acpi_irq_penalty[irq] += PIRQ_PENALTY_ISA_ALWAYS;
+		else
+			acpi_irq_penalty[irq] += PIRQ_PENALTY_PCI_USING;
+	}
 }
 
 /*
diff --git a/drivers/acpi/pmic/intel_pmic_crc.c b/drivers/acpi/pmic/intel_pmic_crc.c
index 42df46a86c25..fcd1852dcdee 100644
--- a/drivers/acpi/pmic/intel_pmic_crc.c
+++ b/drivers/acpi/pmic/intel_pmic_crc.c
@@ -13,7 +13,7 @@
  * GNU General Public License for more details.
  */
 
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/acpi.h>
 #include <linux/mfd/intel_soc_pmic.h>
 #include <linux/regmap.h>
@@ -205,7 +205,4 @@ static int __init intel_crc_pmic_opregion_driver_init(void)
 {
 	return platform_driver_register(&intel_crc_pmic_opregion_driver);
 }
-module_init(intel_crc_pmic_opregion_driver_init);
-
-MODULE_DESCRIPTION("CrystalCove ACPI operation region driver");
-MODULE_LICENSE("GPL");
+device_initcall(intel_crc_pmic_opregion_driver_init);
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index 11154a330f07..d2fa8cb82d2b 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -314,7 +314,6 @@ static int __init acpi_processor_driver_init(void)
 	if (result < 0)
 		return result;
 
-	acpi_processor_syscore_init();
 	register_hotcpu_notifier(&acpi_cpu_notifier);
 	acpi_thermal_cpufreq_init();
 	acpi_processor_ppc_init();
@@ -330,7 +329,6 @@ static void __exit acpi_processor_driver_exit(void)
 	acpi_processor_ppc_exit();
 	acpi_thermal_cpufreq_exit();
 	unregister_hotcpu_notifier(&acpi_cpu_notifier);
-	acpi_processor_syscore_exit();
 	driver_unregister(&acpi_processor_driver);
 }
 
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 175c86bee3a9..444e3745c8b3 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -23,6 +23,7 @@
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
+#define pr_fmt(fmt) "ACPI: " fmt
 
 #include <linux/module.h>
 #include <linux/acpi.h>
@@ -30,7 +31,6 @@
 #include <linux/sched.h>       /* need_resched() */
 #include <linux/tick.h>
 #include <linux/cpuidle.h>
-#include <linux/syscore_ops.h>
 #include <acpi/processor.h>
 
 /*
@@ -43,8 +43,6 @@
 #include <asm/apic.h>
 #endif
 
-#define PREFIX "ACPI: "
-
 #define ACPI_PROCESSOR_CLASS            "processor"
 #define _COMPONENT              ACPI_PROCESSOR_COMPONENT
 ACPI_MODULE_NAME("processor_idle");
@@ -61,8 +59,8 @@ module_param(latency_factor, uint, 0644);
 
 static DEFINE_PER_CPU(struct cpuidle_device *, acpi_cpuidle_device);
 
-static DEFINE_PER_CPU(struct acpi_processor_cx * [CPUIDLE_STATE_MAX],
-								acpi_cstate);
+static
+DEFINE_PER_CPU(struct acpi_processor_cx * [CPUIDLE_STATE_MAX], acpi_cstate);
 
 static int disabled_by_idle_boot_param(void)
 {
@@ -81,9 +79,9 @@ static int set_max_cstate(const struct dmi_system_id *id)
 	if (max_cstate > ACPI_PROCESSOR_MAX_POWER)
 		return 0;
 
-	printk(KERN_NOTICE PREFIX "%s detected - limiting to C%ld max_cstate."
-	       " Override with \"processor.max_cstate=%d\"\n", id->ident,
-	       (long)id->driver_data, ACPI_PROCESSOR_MAX_POWER + 1);
+	pr_notice("%s detected - limiting to C%ld max_cstate."
+		  " Override with \"processor.max_cstate=%d\"\n", id->ident,
+		  (long)id->driver_data, ACPI_PROCESSOR_MAX_POWER + 1);
 
 	max_cstate = (long)id->driver_data;
 
@@ -194,42 +192,6 @@ static void lapic_timer_state_broadcast(struct acpi_processor *pr,
 
 #endif
 
-#ifdef CONFIG_PM_SLEEP
-static u32 saved_bm_rld;
-
-static int acpi_processor_suspend(void)
-{
-	acpi_read_bit_register(ACPI_BITREG_BUS_MASTER_RLD, &saved_bm_rld);
-	return 0;
-}
-
-static void acpi_processor_resume(void)
-{
-	u32 resumed_bm_rld = 0;
-
-	acpi_read_bit_register(ACPI_BITREG_BUS_MASTER_RLD, &resumed_bm_rld);
-	if (resumed_bm_rld == saved_bm_rld)
-		return;
-
-	acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_RLD, saved_bm_rld);
-}
-
-static struct syscore_ops acpi_processor_syscore_ops = {
-	.suspend = acpi_processor_suspend,
-	.resume = acpi_processor_resume,
-};
-
-void acpi_processor_syscore_init(void)
-{
-	register_syscore_ops(&acpi_processor_syscore_ops);
-}
-
-void acpi_processor_syscore_exit(void)
-{
-	unregister_syscore_ops(&acpi_processor_syscore_ops);
-}
-#endif /* CONFIG_PM_SLEEP */
-
 #if defined(CONFIG_X86)
 static void tsc_check_state(int state)
 {
@@ -351,7 +313,7 @@ static int acpi_processor_get_power_info_cst(struct acpi_processor *pr)
 
 	/* There must be at least 2 elements */
 	if (!cst || (cst->type != ACPI_TYPE_PACKAGE) || cst->package.count < 2) {
-		printk(KERN_ERR PREFIX "not enough elements in _CST\n");
+		pr_err("not enough elements in _CST\n");
 		ret = -EFAULT;
 		goto end;
 	}
@@ -360,7 +322,7 @@ static int acpi_processor_get_power_info_cst(struct acpi_processor *pr)
 
 	/* Validate number of power states. */
 	if (count < 1 || count != cst->package.count - 1) {
-		printk(KERN_ERR PREFIX "count given by _CST is not valid\n");
+		pr_err("count given by _CST is not valid\n");
 		ret = -EFAULT;
 		goto end;
 	}
@@ -469,11 +431,9 @@ static int acpi_processor_get_power_info_cst(struct acpi_processor *pr)
 		 * (From 1 through ACPI_PROCESSOR_MAX_POWER - 1)
 		 */
 		if (current_count >= (ACPI_PROCESSOR_MAX_POWER - 1)) {
-			printk(KERN_WARNING
-			       "Limiting number of power states to max (%d)\n",
-			       ACPI_PROCESSOR_MAX_POWER);
-			printk(KERN_WARNING
-			       "Please increase ACPI_PROCESSOR_MAX_POWER if needed.\n");
+			pr_warn("Limiting number of power states to max (%d)\n",
+				ACPI_PROCESSOR_MAX_POWER);
+			pr_warn("Please increase ACPI_PROCESSOR_MAX_POWER if needed.\n");
 			break;
 		}
 	}
@@ -1097,8 +1057,8 @@ int acpi_processor_power_init(struct acpi_processor *pr)
 			retval = cpuidle_register_driver(&acpi_idle_driver);
 			if (retval)
 				return retval;
-			printk(KERN_DEBUG "ACPI: %s registered with cpuidle\n",
-					acpi_idle_driver.name);
+			pr_debug("%s registered with cpuidle\n",
+				 acpi_idle_driver.name);
 		}
 
 		dev = kzalloc(sizeof(*dev), GFP_KERNEL);
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 407a3760e8de..5f28cf778349 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1930,6 +1930,7 @@ int __init acpi_scan_init(void)
 	acpi_memory_hotplug_init();
 	acpi_pnp_init();
 	acpi_int340x_thermal_init();
+	acpi_amba_init();
 
 	acpi_scan_add_handler(&generic_device_handler);
 
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 9cb975200cac..fbfcce3b5227 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -19,6 +19,7 @@
 #include <linux/reboot.h>
 #include <linux/acpi.h>
 #include <linux/module.h>
+#include <linux/syscore_ops.h>
 #include <asm/io.h>
 #include <trace/events/power.h>
 
@@ -677,6 +678,39 @@ static void acpi_sleep_suspend_setup(void)
 static inline void acpi_sleep_suspend_setup(void) {}
 #endif /* !CONFIG_SUSPEND */
 
+#ifdef CONFIG_PM_SLEEP
+static u32 saved_bm_rld;
+
+static int  acpi_save_bm_rld(void)
+{
+	acpi_read_bit_register(ACPI_BITREG_BUS_MASTER_RLD, &saved_bm_rld);
+	return 0;
+}
+
+static void  acpi_restore_bm_rld(void)
+{
+	u32 resumed_bm_rld = 0;
+
+	acpi_read_bit_register(ACPI_BITREG_BUS_MASTER_RLD, &resumed_bm_rld);
+	if (resumed_bm_rld == saved_bm_rld)
+		return;
+
+	acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_RLD, saved_bm_rld);
+}
+
+static struct syscore_ops acpi_sleep_syscore_ops = {
+	.suspend = acpi_save_bm_rld,
+	.resume = acpi_restore_bm_rld,
+};
+
+void acpi_sleep_syscore_init(void)
+{
+	register_syscore_ops(&acpi_sleep_syscore_ops);
+}
+#else
+static inline void acpi_sleep_syscore_init(void) {}
+#endif /* CONFIG_PM_SLEEP */
+
 #ifdef CONFIG_HIBERNATION
 static unsigned long s4_hardware_signature;
 static struct acpi_table_facs *facs;
@@ -839,6 +873,7 @@ int __init acpi_sleep_init(void)
 
 	sleep_states[ACPI_STATE_S0] = 1;
 
+	acpi_sleep_syscore_init();
 	acpi_sleep_suspend_setup();
 	acpi_sleep_hibernate_setup();
 
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index 6c0f0794aa82..f49c02442d65 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -32,6 +32,7 @@
 #include <linux/errno.h>
 #include <linux/acpi.h>
 #include <linux/bootmem.h>
+#include "internal.h"
 
 #define ACPI_MAX_TABLES		128
 
@@ -456,6 +457,7 @@ int __init acpi_table_init(void)
 	status = acpi_initialize_tables(initial_tables, ACPI_MAX_TABLES, 0);
 	if (ACPI_FAILURE(status))
 		return -EINVAL;
+	acpi_initrd_initialize_tables();
 
 	check_multiple_madt();
 	return 0;
@@ -484,3 +486,13 @@ static int __init acpi_force_table_verification_setup(char *s)
 }
 
 early_param("acpi_force_table_verification", acpi_force_table_verification_setup);
+
+static int __init acpi_force_32bit_fadt_addr(char *s)
+{
+	pr_info("Forcing 32 Bit FADT addresses\n");
+	acpi_gbl_use32_bit_fadt_addresses = TRUE;
+
+	return 0;
+}
+
+early_param("acpi_force_32bit_fadt_addr", acpi_force_32bit_fadt_addr);
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index f2f9873bb5c3..f12a72428aac 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -201,10 +201,6 @@ acpi_extract_package(union acpi_object *package,
 		u8 **pointer = NULL;
 		union acpi_object *element = &(package->package.elements[i]);
 
-		if (!element) {
-			return AE_BAD_DATA;
-		}
-
 		switch (element->type) {
 
 		case ACPI_TYPE_INTEGER:
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index a39e85f9efa9..7d00b7a015ea 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -2074,7 +2074,7 @@ static int binder_thread_write(struct binder_proc *proc,
 			if (get_user(cookie, (binder_uintptr_t __user *)ptr))
 				return -EFAULT;
 
-			ptr += sizeof(void *);
+			ptr += sizeof(cookie);
 			list_for_each_entry(w, &proc->delivered_death, entry) {
 				struct binder_ref_death *tmp_death = container_of(w, struct binder_ref_death, work);
 
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 594fcabd22cd..146dc0b8ec61 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -264,6 +264,26 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x3b2b), board_ahci }, /* PCH RAID */
 	{ PCI_VDEVICE(INTEL, 0x3b2c), board_ahci }, /* PCH RAID */
 	{ PCI_VDEVICE(INTEL, 0x3b2f), board_ahci }, /* PCH AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b0), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b1), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b2), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b3), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b4), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b5), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b6), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19b7), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19bE), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19bF), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c0), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c1), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c2), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c3), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c4), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c5), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c6), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19c7), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19cE), board_ahci }, /* DNV AHCI */
+	{ PCI_VDEVICE(INTEL, 0x19cF), board_ahci }, /* DNV AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1c02), board_ahci }, /* CPT AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1c03), board_ahci }, /* CPT AHCI */
 	{ PCI_VDEVICE(INTEL, 0x1c04), board_ahci }, /* CPT RAID */
@@ -347,15 +367,21 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */
 	{ PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */
 	{ PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* Lewisburg RAID*/
+	{ PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Lewisburg AHCI*/
 	{ PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* Lewisburg RAID*/
+	{ PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* Lewisburg RAID*/
 	{ PCI_VDEVICE(INTEL, 0xa182), board_ahci }, /* Lewisburg AHCI*/
 	{ PCI_VDEVICE(INTEL, 0xa184), board_ahci }, /* Lewisburg RAID*/
 	{ PCI_VDEVICE(INTEL, 0xa186), board_ahci }, /* Lewisburg RAID*/
 	{ PCI_VDEVICE(INTEL, 0xa18e), board_ahci }, /* Lewisburg RAID*/
+	{ PCI_VDEVICE(INTEL, 0xa1d2), board_ahci }, /* Lewisburg RAID*/
+	{ PCI_VDEVICE(INTEL, 0xa1d6), board_ahci }, /* Lewisburg RAID*/
 	{ PCI_VDEVICE(INTEL, 0xa202), board_ahci }, /* Lewisburg AHCI*/
 	{ PCI_VDEVICE(INTEL, 0xa204), board_ahci }, /* Lewisburg RAID*/
 	{ PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/
 	{ PCI_VDEVICE(INTEL, 0xa20e), board_ahci }, /* Lewisburg RAID*/
+	{ PCI_VDEVICE(INTEL, 0xa252), board_ahci }, /* Lewisburg RAID*/
+	{ PCI_VDEVICE(INTEL, 0xa256), board_ahci }, /* Lewisburg RAID*/
 
 	/* JMicron 360/1/3/5/6, match class to avoid IDE function */
 	{ PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
@@ -1305,6 +1331,44 @@ static inline void ahci_gtf_filter_workaround(struct ata_host *host)
 {}
 #endif
 
+#ifdef CONFIG_ARM64
+/*
+ * Due to ERRATA#22536, ThunderX needs to handle HOST_IRQ_STAT differently.
+ * Workaround is to make sure all pending IRQs are served before leaving
+ * handler.
+ */
+static irqreturn_t ahci_thunderx_irq_handler(int irq, void *dev_instance)
+{
+	struct ata_host *host = dev_instance;
+	struct ahci_host_priv *hpriv;
+	unsigned int rc = 0;
+	void __iomem *mmio;
+	u32 irq_stat, irq_masked;
+	unsigned int handled = 1;
+
+	VPRINTK("ENTER\n");
+	hpriv = host->private_data;
+	mmio = hpriv->mmio;
+	irq_stat = readl(mmio + HOST_IRQ_STAT);
+	if (!irq_stat)
+		return IRQ_NONE;
+
+	do {
+		irq_masked = irq_stat & hpriv->port_map;
+		spin_lock(&host->lock);
+		rc = ahci_handle_port_intr(host, irq_masked);
+		if (!rc)
+			handled = 0;
+		writel(irq_stat, mmio + HOST_IRQ_STAT);
+		irq_stat = readl(mmio + HOST_IRQ_STAT);
+		spin_unlock(&host->lock);
+	} while (irq_stat);
+	VPRINTK("EXIT\n");
+
+	return IRQ_RETVAL(handled);
+}
+#endif
+
 /*
  * ahci_init_msix() - optionally enable per-port MSI-X otherwise defer
  * to single msi.
@@ -1540,6 +1604,11 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (ahci_broken_devslp(pdev))
 		hpriv->flags |= AHCI_HFLAG_NO_DEVSLP;
 
+#ifdef CONFIG_ARM64
+	if (pdev->vendor == 0x177d && pdev->device == 0xa01c)
+		hpriv->irq_handler = ahci_thunderx_irq_handler;
+#endif
+
 	/* save initial config */
 	ahci_pci_save_initial_config(pdev, hpriv);
 
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index a4faa438889c..167ba7e3b92e 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -240,8 +240,7 @@ enum {
 						        error-handling stage) */
 	AHCI_HFLAG_NO_DEVSLP		= (1 << 17), /* no device sleep */
 	AHCI_HFLAG_NO_FBS		= (1 << 18), /* no FBS */
-	AHCI_HFLAG_EDGE_IRQ		= (1 << 19), /* HOST_IRQ_STAT behaves as
-							Edge Triggered */
+
 #ifdef CONFIG_PCI_MSI
 	AHCI_HFLAG_MULTI_MSI		= (1 << 20), /* multiple PCI MSIs */
 	AHCI_HFLAG_MULTI_MSIX		= (1 << 21), /* per-port MSI-X */
@@ -250,6 +249,7 @@ enum {
 	AHCI_HFLAG_MULTI_MSI		= 0,
 	AHCI_HFLAG_MULTI_MSIX		= 0,
 #endif
+	AHCI_HFLAG_WAKE_BEFORE_STOP	= (1 << 22), /* wake before DMA stop */
 
 	/* ap->flags bits */
 
@@ -360,6 +360,7 @@ struct ahci_host_priv {
 	 * be overridden anytime before the host is activated.
 	 */
 	void			(*start_engine)(struct ata_port *ap);
+	irqreturn_t 		(*irq_handler)(int irq, void *dev_instance);
 };
 
 #ifdef CONFIG_PCI_MSI
@@ -423,6 +424,7 @@ int ahci_reset_em(struct ata_host *host);
 void ahci_print_info(struct ata_host *host, const char *scc_s);
 int ahci_host_activate(struct ata_host *host, struct scsi_host_template *sht);
 void ahci_error_handler(struct ata_port *ap);
+u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked);
 
 static inline void __iomem *__ahci_port_base(struct ata_host *host,
 					     unsigned int port_no)
diff --git a/drivers/ata/ahci_brcmstb.c b/drivers/ata/ahci_brcmstb.c
index b36cae2fd04b..e87bcec0fd7c 100644
--- a/drivers/ata/ahci_brcmstb.c
+++ b/drivers/ata/ahci_brcmstb.c
@@ -317,6 +317,7 @@ static int brcm_ahci_probe(struct platform_device *pdev)
 	if (IS_ERR(hpriv))
 		return PTR_ERR(hpriv);
 	hpriv->plat_data = priv;
+	hpriv->flags = AHCI_HFLAG_WAKE_BEFORE_STOP;
 
 	brcm_sata_alpm_init(hpriv);
 
diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c
index e2c6d9e0c5ac..8e3f7faf00d3 100644
--- a/drivers/ata/ahci_xgene.c
+++ b/drivers/ata/ahci_xgene.c
@@ -548,6 +548,88 @@ softreset_retry:
 	return rc;
 }
 
+/**
+ * xgene_ahci_handle_broken_edge_irq - Handle the broken irq.
+ * @ata_host: Host that recieved the irq
+ * @irq_masked: HOST_IRQ_STAT value
+ *
+ * For hardware with broken edge trigger latch
+ * the HOST_IRQ_STAT register misses the edge interrupt
+ * when clearing of HOST_IRQ_STAT register and hardware
+ * reporting the PORT_IRQ_STAT register at the
+ * same clock cycle.
+ * As such, the algorithm below outlines the workaround.
+ *
+ * 1. Read HOST_IRQ_STAT register and save the state.
+ * 2. Clear the HOST_IRQ_STAT register.
+ * 3. Read back the HOST_IRQ_STAT register.
+ * 4. If HOST_IRQ_STAT register equals to zero, then
+ *    traverse the rest of port's PORT_IRQ_STAT register
+ *    to check if an interrupt is triggered at that point else
+ *    go to step 6.
+ * 5. If PORT_IRQ_STAT register of rest ports is not equal to zero
+ *    then update the state of HOST_IRQ_STAT saved in step 1.
+ * 6. Handle port interrupts.
+ * 7. Exit
+ */
+static int xgene_ahci_handle_broken_edge_irq(struct ata_host *host,
+					     u32 irq_masked)
+{
+	struct ahci_host_priv *hpriv = host->private_data;
+	void __iomem *port_mmio;
+	int i;
+
+	if (!readl(hpriv->mmio + HOST_IRQ_STAT)) {
+		for (i = 0; i < host->n_ports; i++) {
+			if (irq_masked & (1 << i))
+				continue;
+
+			port_mmio = ahci_port_base(host->ports[i]);
+			if (readl(port_mmio + PORT_IRQ_STAT))
+				irq_masked |= (1 << i);
+		}
+	}
+
+	return ahci_handle_port_intr(host, irq_masked);
+}
+
+static irqreturn_t xgene_ahci_irq_intr(int irq, void *dev_instance)
+{
+	struct ata_host *host = dev_instance;
+	struct ahci_host_priv *hpriv;
+	unsigned int rc = 0;
+	void __iomem *mmio;
+	u32 irq_stat, irq_masked;
+
+	VPRINTK("ENTER\n");
+
+	hpriv = host->private_data;
+	mmio = hpriv->mmio;
+
+	/* sigh.  0xffffffff is a valid return from h/w */
+	irq_stat = readl(mmio + HOST_IRQ_STAT);
+	if (!irq_stat)
+		return IRQ_NONE;
+
+	irq_masked = irq_stat & hpriv->port_map;
+
+	spin_lock(&host->lock);
+
+	/*
+	 * HOST_IRQ_STAT behaves as edge triggered latch meaning that
+	 * it should be cleared before all the port events are cleared.
+	 */
+	writel(irq_stat, mmio + HOST_IRQ_STAT);
+
+	rc = xgene_ahci_handle_broken_edge_irq(host, irq_masked);
+
+	spin_unlock(&host->lock);
+
+	VPRINTK("EXIT\n");
+
+	return IRQ_RETVAL(rc);
+}
+
 static struct ata_port_operations xgene_ahci_v1_ops = {
 	.inherits = &ahci_ops,
 	.host_stop = xgene_ahci_host_stop,
@@ -779,7 +861,8 @@ skip_clk_phy:
 		hpriv->flags = AHCI_HFLAG_NO_NCQ;
 		break;
 	case XGENE_AHCI_V2:
-		hpriv->flags |= AHCI_HFLAG_YES_FBS | AHCI_HFLAG_EDGE_IRQ;
+		hpriv->flags |= AHCI_HFLAG_YES_FBS;
+		hpriv->irq_handler = xgene_ahci_irq_intr;
 		break;
 	default:
 		break;
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index d61740e78d6d..85ea5142a095 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -113,6 +113,7 @@ static ssize_t ahci_store_em_buffer(struct device *dev,
 				    const char *buf, size_t size);
 static ssize_t ahci_show_em_supported(struct device *dev,
 				      struct device_attribute *attr, char *buf);
+static irqreturn_t ahci_single_level_irq_intr(int irq, void *dev_instance);
 
 static DEVICE_ATTR(ahci_host_caps, S_IRUGO, ahci_show_host_caps, NULL);
 static DEVICE_ATTR(ahci_host_cap2, S_IRUGO, ahci_show_host_cap2, NULL);
@@ -496,8 +497,8 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv)
 		}
 	}
 
-	/* fabricate port_map from cap.nr_ports */
-	if (!port_map) {
+	/* fabricate port_map from cap.nr_ports for < AHCI 1.3 */
+	if (!port_map && vers < 0x10300) {
 		port_map = (1 << ahci_nr_ports(cap)) - 1;
 		dev_warn(dev, "forcing PORTS_IMPL to 0x%x\n", port_map);
 
@@ -512,6 +513,9 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv)
 
 	if (!hpriv->start_engine)
 		hpriv->start_engine = ahci_start_engine;
+
+	if (!hpriv->irq_handler)
+		hpriv->irq_handler = ahci_single_level_irq_intr;
 }
 EXPORT_SYMBOL_GPL(ahci_save_initial_config);
 
@@ -593,8 +597,22 @@ EXPORT_SYMBOL_GPL(ahci_start_engine);
 int ahci_stop_engine(struct ata_port *ap)
 {
 	void __iomem *port_mmio = ahci_port_base(ap);
+	struct ahci_host_priv *hpriv = ap->host->private_data;
 	u32 tmp;
 
+	/*
+	 * On some controllers, stopping a port's DMA engine while the port
+	 * is in ALPM state (partial or slumber) results in failures on
+	 * subsequent DMA engine starts.  For those controllers, put the
+	 * port back in active state before stopping its DMA engine.
+	 */
+	if ((hpriv->flags & AHCI_HFLAG_WAKE_BEFORE_STOP) &&
+	    (ap->link.lpm_policy > ATA_LPM_MAX_POWER) &&
+	    ahci_set_lpm(&ap->link, ATA_LPM_MAX_POWER, ATA_LPM_WAKE_ONLY)) {
+		dev_err(ap->host->dev, "Failed to wake up port before engine stop\n");
+		return -EIO;
+	}
+
 	tmp = readl(port_mmio + PORT_CMD);
 
 	/* check if the HBA is idle */
@@ -689,6 +707,9 @@ static int ahci_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
 	void __iomem *port_mmio = ahci_port_base(ap);
 
 	if (policy != ATA_LPM_MAX_POWER) {
+		/* wakeup flag only applies to the max power policy */
+		hints &= ~ATA_LPM_WAKE_ONLY;
+
 		/*
 		 * Disable interrupts on Phy Ready. This keeps us from
 		 * getting woken up due to spurious phy ready
@@ -704,7 +725,8 @@ static int ahci_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
 		u32 cmd = readl(port_mmio + PORT_CMD);
 
 		if (policy == ATA_LPM_MAX_POWER || !(hints & ATA_LPM_HIPM)) {
-			cmd &= ~(PORT_CMD_ASP | PORT_CMD_ALPE);
+			if (!(hints & ATA_LPM_WAKE_ONLY))
+				cmd &= ~(PORT_CMD_ASP | PORT_CMD_ALPE);
 			cmd |= PORT_CMD_ICC_ACTIVE;
 
 			writel(cmd, port_mmio + PORT_CMD);
@@ -712,6 +734,9 @@ static int ahci_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
 
 			/* wait 10ms to be sure we've come out of LPM state */
 			ata_msleep(ap, 10);
+
+			if (hints & ATA_LPM_WAKE_ONLY)
+				return 0;
 		} else {
 			cmd |= PORT_CMD_ALPE;
 			if (policy == ATA_LPM_MIN_POWER)
@@ -1143,8 +1168,7 @@ static void ahci_port_init(struct device *dev, struct ata_port *ap,
 
 	/* mark esata ports */
 	tmp = readl(port_mmio + PORT_CMD);
-	if ((tmp & PORT_CMD_HPCP) ||
-	    ((tmp & PORT_CMD_ESP) && (hpriv->cap & HOST_CAP_SXS)))
+	if ((tmp & PORT_CMD_ESP) && (hpriv->cap & HOST_CAP_SXS))
 		ap->pflags |= ATA_PFLAG_EXTERNAL;
 }
 
@@ -1825,7 +1849,7 @@ static irqreturn_t ahci_multi_irqs_intr_hard(int irq, void *dev_instance)
 	return IRQ_HANDLED;
 }
 
-static u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked)
+u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked)
 {
 	unsigned int i, handled = 0;
 
@@ -1851,43 +1875,7 @@ static u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked)
 
 	return handled;
 }
-
-static irqreturn_t ahci_single_edge_irq_intr(int irq, void *dev_instance)
-{
-	struct ata_host *host = dev_instance;
-	struct ahci_host_priv *hpriv;
-	unsigned int rc = 0;
-	void __iomem *mmio;
-	u32 irq_stat, irq_masked;
-
-	VPRINTK("ENTER\n");
-
-	hpriv = host->private_data;
-	mmio = hpriv->mmio;
-
-	/* sigh.  0xffffffff is a valid return from h/w */
-	irq_stat = readl(mmio + HOST_IRQ_STAT);
-	if (!irq_stat)
-		return IRQ_NONE;
-
-	irq_masked = irq_stat & hpriv->port_map;
-
-	spin_lock(&host->lock);
-
-	/*
-	 * HOST_IRQ_STAT behaves as edge triggered latch meaning that
-	 * it should be cleared before all the port events are cleared.
-	 */
-	writel(irq_stat, mmio + HOST_IRQ_STAT);
-
-	rc = ahci_handle_port_intr(host, irq_masked);
-
-	spin_unlock(&host->lock);
-
-	VPRINTK("EXIT\n");
-
-	return IRQ_RETVAL(rc);
-}
+EXPORT_SYMBOL_GPL(ahci_handle_port_intr);
 
 static irqreturn_t ahci_single_level_irq_intr(int irq, void *dev_instance)
 {
@@ -2514,14 +2502,18 @@ int ahci_host_activate(struct ata_host *host, struct scsi_host_template *sht)
 	int irq = hpriv->irq;
 	int rc;
 
-	if (hpriv->flags & (AHCI_HFLAG_MULTI_MSI | AHCI_HFLAG_MULTI_MSIX))
+	if (hpriv->flags & (AHCI_HFLAG_MULTI_MSI | AHCI_HFLAG_MULTI_MSIX)) {
+		if (hpriv->irq_handler)
+			dev_warn(host->dev, "both AHCI_HFLAG_MULTI_MSI flag set \
+				 and custom irq handler implemented\n");
+
 		rc = ahci_host_activate_multi_irqs(host, sht);
-	else if (hpriv->flags & AHCI_HFLAG_EDGE_IRQ)
-		rc = ata_host_activate(host, irq, ahci_single_edge_irq_intr,
-				       IRQF_SHARED, sht);
-	else
-		rc = ata_host_activate(host, irq, ahci_single_level_irq_intr,
+	} else {
+		rc = ata_host_activate(host, irq, hpriv->irq_handler,
 				       IRQF_SHARED, sht);
+	}
+
+
 	return rc;
 }
 EXPORT_SYMBOL_GPL(ahci_host_activate);
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index cbb74719d2c1..55e257c268dd 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4125,6 +4125,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ "SAMSUNG CD-ROM SN-124", "N001",	ATA_HORKAGE_NODMA },
 	{ "Seagate STT20000A", NULL,		ATA_HORKAGE_NODMA },
 	{ " 2GB ATA Flash Disk", "ADMA428M",	ATA_HORKAGE_NODMA },
+	{ "VRFDFC22048UCHC-TE*", NULL,		ATA_HORKAGE_NODMA },
 	/* Odd clown on sil3726/4726 PMPs */
 	{ "Config  Disk",	NULL,		ATA_HORKAGE_DISABLE },
 
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 7e959f90c020..e417e1a1d02c 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -675,19 +675,18 @@ static int ata_ioc32(struct ata_port *ap)
 int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *scsidev,
 		     int cmd, void __user *arg)
 {
-	int val = -EINVAL, rc = -EINVAL;
+	unsigned long val;
+	int rc = -EINVAL;
 	unsigned long flags;
 
 	switch (cmd) {
-	case ATA_IOC_GET_IO32:
+	case HDIO_GET_32BIT:
 		spin_lock_irqsave(ap->lock, flags);
 		val = ata_ioc32(ap);
 		spin_unlock_irqrestore(ap->lock, flags);
-		if (copy_to_user(arg, &val, 1))
-			return -EFAULT;
-		return 0;
+		return put_user(val, (unsigned long __user *)arg);
 
-	case ATA_IOC_SET_IO32:
+	case HDIO_SET_32BIT:
 		val = (unsigned long) arg;
 		rc = 0;
 		spin_lock_irqsave(ap->lock, flags);
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index cdf6215a9a22..051b6158d1b7 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -997,12 +997,9 @@ static inline int ata_hsm_ok_in_wq(struct ata_port *ap,
 static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq)
 {
 	struct ata_port *ap = qc->ap;
-	unsigned long flags;
 
 	if (ap->ops->error_handler) {
 		if (in_wq) {
-			spin_lock_irqsave(ap->lock, flags);
-
 			/* EH might have kicked in while host lock is
 			 * released.
 			 */
@@ -1014,8 +1011,6 @@ static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq)
 				} else
 					ata_port_freeze(ap);
 			}
-
-			spin_unlock_irqrestore(ap->lock, flags);
 		} else {
 			if (likely(!(qc->err_mask & AC_ERR_HSM)))
 				ata_qc_complete(qc);
@@ -1024,10 +1019,8 @@ static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq)
 		}
 	} else {
 		if (in_wq) {
-			spin_lock_irqsave(ap->lock, flags);
 			ata_sff_irq_on(ap);
 			ata_qc_complete(qc);
-			spin_unlock_irqrestore(ap->lock, flags);
 		} else
 			ata_qc_complete(qc);
 	}
@@ -1048,9 +1041,10 @@ int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc,
 {
 	struct ata_link *link = qc->dev->link;
 	struct ata_eh_info *ehi = &link->eh_info;
-	unsigned long flags = 0;
 	int poll_next;
 
+	lockdep_assert_held(ap->lock);
+
 	WARN_ON_ONCE((qc->flags & ATA_QCFLAG_ACTIVE) == 0);
 
 	/* Make sure ata_sff_qc_issue() does not throw things
@@ -1112,14 +1106,6 @@ fsm_start:
 			}
 		}
 
-		/* Send the CDB (atapi) or the first data block (ata pio out).
-		 * During the state transition, interrupt handler shouldn't
-		 * be invoked before the data transfer is complete and
-		 * hsm_task_state is changed. Hence, the following locking.
-		 */
-		if (in_wq)
-			spin_lock_irqsave(ap->lock, flags);
-
 		if (qc->tf.protocol == ATA_PROT_PIO) {
 			/* PIO data out protocol.
 			 * send first data block.
@@ -1135,9 +1121,6 @@ fsm_start:
 			/* send CDB */
 			atapi_send_cdb(ap, qc);
 
-		if (in_wq)
-			spin_unlock_irqrestore(ap->lock, flags);
-
 		/* if polling, ata_sff_pio_task() handles the rest.
 		 * otherwise, interrupt handler takes over from here.
 		 */
@@ -1296,7 +1279,8 @@ fsm_start:
 		break;
 	default:
 		poll_next = 0;
-		BUG();
+		WARN(true, "ata%d: SFF host state machine in invalid state %d",
+		     ap->print_id, ap->hsm_task_state);
 	}
 
 	return poll_next;
@@ -1361,12 +1345,14 @@ static void ata_sff_pio_task(struct work_struct *work)
 	u8 status;
 	int poll_next;
 
+	spin_lock_irq(ap->lock);
+
 	BUG_ON(ap->sff_pio_task_link == NULL);
 	/* qc can be NULL if timeout occurred */
 	qc = ata_qc_from_tag(ap, link->active_tag);
 	if (!qc) {
 		ap->sff_pio_task_link = NULL;
-		return;
+		goto out_unlock;
 	}
 
 fsm_start:
@@ -1381,11 +1367,14 @@ fsm_start:
 	 */
 	status = ata_sff_busy_wait(ap, ATA_BUSY, 5);
 	if (status & ATA_BUSY) {
+		spin_unlock_irq(ap->lock);
 		ata_msleep(ap, 2);
+		spin_lock_irq(ap->lock);
+
 		status = ata_sff_busy_wait(ap, ATA_BUSY, 10);
 		if (status & ATA_BUSY) {
 			ata_sff_queue_pio_task(link, ATA_SHORT_PAUSE);
-			return;
+			goto out_unlock;
 		}
 	}
 
@@ -1402,6 +1391,8 @@ fsm_start:
 	 */
 	if (poll_next)
 		goto fsm_start;
+out_unlock:
+	spin_unlock_irq(ap->lock);
 }
 
 /**
diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c
index e3d4b059fcd1..e347e7acd8ed 100644
--- a/drivers/ata/pata_macio.c
+++ b/drivers/ata/pata_macio.c
@@ -22,6 +22,7 @@
 #include <linux/scatterlist.h>
 #include <linux/of.h>
 #include <linux/gfp.h>
+#include <linux/pci.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_host.h>
@@ -30,7 +31,6 @@
 #include <asm/macio.h>
 #include <asm/io.h>
 #include <asm/dbdma.h>
-#include <asm/pci-bridge.h>
 #include <asm/machdep.h>
 #include <asm/pmac_feature.h>
 #include <asm/mediabay.h>
diff --git a/drivers/ata/pata_rb532_cf.c b/drivers/ata/pata_rb532_cf.c
index 12fe0f3bb7e9..c8b6a780a290 100644
--- a/drivers/ata/pata_rb532_cf.c
+++ b/drivers/ata/pata_rb532_cf.c
@@ -32,6 +32,8 @@
 #include <linux/libata.h>
 #include <scsi/scsi_host.h>
 
+#include <asm/mach-rc32434/rb.h>
+
 #define DRV_NAME	"pata-rb532-cf"
 #define DRV_VERSION	"0.1.0"
 #define DRV_DESC	"PATA driver for RouterBOARD 532 Compact Flash"
@@ -107,6 +109,7 @@ static int rb532_pata_driver_probe(struct platform_device *pdev)
 	int gpio;
 	struct resource *res;
 	struct ata_host *ah;
+	struct cf_device *pdata;
 	struct rb532_cf_info *info;
 	int ret;
 
@@ -122,7 +125,13 @@ static int rb532_pata_driver_probe(struct platform_device *pdev)
 		return -ENOENT;
 	}
 
-	gpio = irq_to_gpio(irq);
+	pdata = dev_get_platdata(&pdev->dev);
+	if (!pdata) {
+		dev_err(&pdev->dev, "no platform data specified\n");
+		return -EINVAL;
+	}
+
+	gpio = pdata->gpio_pin;
 	if (gpio < 0) {
 		dev_err(&pdev->dev, "no GPIO found for irq%d\n", irq);
 		return -ENOENT;
diff --git a/drivers/base/component.c b/drivers/base/component.c
index 89f5cf68d80a..04a1582e80bb 100644
--- a/drivers/base/component.c
+++ b/drivers/base/component.c
@@ -206,6 +206,8 @@ static void component_match_release(struct device *master,
 		if (mc->release)
 			mc->release(master, mc->data);
 	}
+
+	kfree(match->compare);
 }
 
 static void devm_component_match_release(struct device *dev, void *res)
@@ -221,14 +223,14 @@ static int component_match_realloc(struct device *dev,
 	if (match->alloc == num)
 		return 0;
 
-	new = devm_kmalloc_array(dev, num, sizeof(*new), GFP_KERNEL);
+	new = kmalloc_array(num, sizeof(*new), GFP_KERNEL);
 	if (!new)
 		return -ENOMEM;
 
 	if (match->compare) {
 		memcpy(new, match->compare, sizeof(*new) *
 					    min(match->num, num));
-		devm_kfree(dev, match->compare);
+		kfree(match->compare);
 	}
 	match->compare = new;
 	match->alloc = num;
@@ -283,6 +285,24 @@ void component_match_add_release(struct device *master,
 }
 EXPORT_SYMBOL(component_match_add_release);
 
+static void free_master(struct master *master)
+{
+	struct component_match *match = master->match;
+	int i;
+
+	list_del(&master->node);
+
+	if (match) {
+		for (i = 0; i < match->num; i++) {
+			struct component *c = match->compare[i].component;
+			if (c)
+				c->master = NULL;
+		}
+	}
+
+	kfree(master);
+}
+
 int component_master_add_with_match(struct device *dev,
 	const struct component_master_ops *ops,
 	struct component_match *match)
@@ -309,11 +329,9 @@ int component_master_add_with_match(struct device *dev,
 
 	ret = try_to_bring_up_master(master, NULL);
 
-	if (ret < 0) {
-		/* Delete off the list if we weren't successful */
-		list_del(&master->node);
-		kfree(master);
-	}
+	if (ret < 0)
+		free_master(master);
+
 	mutex_unlock(&component_mutex);
 
 	return ret < 0 ? ret : 0;
@@ -324,25 +342,12 @@ void component_master_del(struct device *dev,
 	const struct component_master_ops *ops)
 {
 	struct master *master;
-	int i;
 
 	mutex_lock(&component_mutex);
 	master = __master_find(dev, ops);
 	if (master) {
-		struct component_match *match = master->match;
-
 		take_down_master(master);
-
-		list_del(&master->node);
-
-		if (match) {
-			for (i = 0; i < match->num; i++) {
-				struct component *c = match->compare[i].component;
-				if (c)
-					c->master = NULL;
-			}
-		}
-		kfree(master);
+		free_master(master);
 	}
 	mutex_unlock(&component_mutex);
 }
@@ -486,6 +491,8 @@ int component_add(struct device *dev, const struct component_ops *ops)
 
 	ret = try_to_bring_up_masters(component);
 	if (ret < 0) {
+		if (component->master)
+			remove_component(component->master, component);
 		list_del(&component->node);
 
 		kfree(component);
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 213456c2b123..f46dba8b7092 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -251,7 +251,7 @@ memory_block_action(unsigned long phys_index, unsigned long action, int online_t
 	return ret;
 }
 
-static int memory_block_change_state(struct memory_block *mem,
+int memory_block_change_state(struct memory_block *mem,
 		unsigned long to_state, unsigned long from_state_req)
 {
 	int ret = 0;
@@ -439,6 +439,37 @@ print_block_size(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR(block_size_bytes, 0444, print_block_size, NULL);
 
 /*
+ * Memory auto online policy.
+ */
+
+static ssize_t
+show_auto_online_blocks(struct device *dev, struct device_attribute *attr,
+			char *buf)
+{
+	if (memhp_auto_online)
+		return sprintf(buf, "online\n");
+	else
+		return sprintf(buf, "offline\n");
+}
+
+static ssize_t
+store_auto_online_blocks(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
+{
+	if (sysfs_streq(buf, "online"))
+		memhp_auto_online = true;
+	else if (sysfs_streq(buf, "offline"))
+		memhp_auto_online = false;
+	else
+		return -EINVAL;
+
+	return count;
+}
+
+static DEVICE_ATTR(auto_online_blocks, 0644, show_auto_online_blocks,
+		   store_auto_online_blocks);
+
+/*
  * Some architectures will have custom drivers to do this, and
  * will not need to do it from userspace.  The fake hot-add code
  * as well as ppc64 will do all of their discovery in userspace
@@ -746,6 +777,7 @@ static struct attribute *memory_root_attrs[] = {
 #endif
 
 	&dev_attr_block_size_bytes.attr,
+	&dev_attr_auto_online_blocks.attr,
 	NULL
 };
 
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 301b785f9f56..56705b52758e 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -104,6 +104,7 @@ static void genpd_sd_counter_inc(struct generic_pm_domain *genpd)
 
 static int genpd_power_on(struct generic_pm_domain *genpd, bool timed)
 {
+	unsigned int state_idx = genpd->state_idx;
 	ktime_t time_start;
 	s64 elapsed_ns;
 	int ret;
@@ -120,10 +121,10 @@ static int genpd_power_on(struct generic_pm_domain *genpd, bool timed)
 		return ret;
 
 	elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start));
-	if (elapsed_ns <= genpd->power_on_latency_ns)
+	if (elapsed_ns <= genpd->states[state_idx].power_on_latency_ns)
 		return ret;
 
-	genpd->power_on_latency_ns = elapsed_ns;
+	genpd->states[state_idx].power_on_latency_ns = elapsed_ns;
 	genpd->max_off_time_changed = true;
 	pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n",
 		 genpd->name, "on", elapsed_ns);
@@ -133,6 +134,7 @@ static int genpd_power_on(struct generic_pm_domain *genpd, bool timed)
 
 static int genpd_power_off(struct generic_pm_domain *genpd, bool timed)
 {
+	unsigned int state_idx = genpd->state_idx;
 	ktime_t time_start;
 	s64 elapsed_ns;
 	int ret;
@@ -149,10 +151,10 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool timed)
 		return ret;
 
 	elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start));
-	if (elapsed_ns <= genpd->power_off_latency_ns)
+	if (elapsed_ns <= genpd->states[state_idx].power_off_latency_ns)
 		return ret;
 
-	genpd->power_off_latency_ns = elapsed_ns;
+	genpd->states[state_idx].power_off_latency_ns = elapsed_ns;
 	genpd->max_off_time_changed = true;
 	pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n",
 		 genpd->name, "off", elapsed_ns);
@@ -485,8 +487,13 @@ static int pm_genpd_runtime_resume(struct device *dev)
 	if (timed && runtime_pm)
 		time_start = ktime_get();
 
-	genpd_start_dev(genpd, dev);
-	genpd_restore_dev(genpd, dev);
+	ret = genpd_start_dev(genpd, dev);
+	if (ret)
+		goto err_poweroff;
+
+	ret = genpd_restore_dev(genpd, dev);
+	if (ret)
+		goto err_stop;
 
 	/* Update resume latency value if the measured time exceeds it. */
 	if (timed && runtime_pm) {
@@ -501,6 +508,17 @@ static int pm_genpd_runtime_resume(struct device *dev)
 	}
 
 	return 0;
+
+err_stop:
+	genpd_stop_dev(genpd, dev);
+err_poweroff:
+	if (!dev->power.irq_safe) {
+		mutex_lock(&genpd->lock);
+		genpd_poweroff(genpd, 0);
+		mutex_unlock(&genpd->lock);
+	}
+
+	return ret;
 }
 
 static bool pd_ignore_unused;
@@ -585,6 +603,8 @@ static void pm_genpd_sync_poweroff(struct generic_pm_domain *genpd,
 	    || atomic_read(&genpd->sd_count) > 0)
 		return;
 
+	/* Choose the deepest state when suspending */
+	genpd->state_idx = genpd->state_count - 1;
 	genpd_power_off(genpd, timed);
 
 	genpd->status = GPD_STATE_POWER_OFF;
@@ -1378,7 +1398,7 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 	mutex_lock(&subdomain->lock);
 	mutex_lock_nested(&genpd->lock, SINGLE_DEPTH_NESTING);
 
-	if (!list_empty(&subdomain->slave_links) || subdomain->device_count) {
+	if (!list_empty(&subdomain->master_links) || subdomain->device_count) {
 		pr_warn("%s: unable to remove subdomain %s\n", genpd->name,
 			subdomain->name);
 		ret = -EBUSY;
@@ -1508,6 +1528,20 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 		genpd->dev_ops.start = pm_clk_resume;
 	}
 
+	if (genpd->state_idx >= GENPD_MAX_NUM_STATES) {
+		pr_warn("Initial state index out of bounds.\n");
+		genpd->state_idx = GENPD_MAX_NUM_STATES - 1;
+	}
+
+	if (genpd->state_count > GENPD_MAX_NUM_STATES) {
+		pr_warn("Limiting states to  %d\n", GENPD_MAX_NUM_STATES);
+		genpd->state_count = GENPD_MAX_NUM_STATES;
+	}
+
+	/* Use only one "off" state if there were no states declared */
+	if (genpd->state_count == 0)
+		genpd->state_count = 1;
+
 	mutex_lock(&gpd_list_lock);
 	list_add(&genpd->gpd_list_node, &gpd_list);
 	mutex_unlock(&gpd_list_lock);
@@ -1668,6 +1702,9 @@ struct generic_pm_domain *of_genpd_get_from_provider(
 	struct generic_pm_domain *genpd = ERR_PTR(-ENOENT);
 	struct of_genpd_provider *provider;
 
+	if (!genpdspec)
+		return ERR_PTR(-EINVAL);
+
 	mutex_lock(&of_genpd_mutex);
 
 	/* Check if we have such a provider in our array */
@@ -1864,6 +1901,7 @@ static int pm_genpd_summary_one(struct seq_file *s,
 	struct pm_domain_data *pm_data;
 	const char *kobj_path;
 	struct gpd_link *link;
+	char state[16];
 	int ret;
 
 	ret = mutex_lock_interruptible(&genpd->lock);
@@ -1872,7 +1910,13 @@ static int pm_genpd_summary_one(struct seq_file *s,
 
 	if (WARN_ON(genpd->status >= ARRAY_SIZE(status_lookup)))
 		goto exit;
-	seq_printf(s, "%-30s  %-15s ", genpd->name, status_lookup[genpd->status]);
+	if (genpd->status == GPD_STATE_POWER_OFF)
+		snprintf(state, sizeof(state), "%s-%u",
+			 status_lookup[genpd->status], genpd->state_idx);
+	else
+		snprintf(state, sizeof(state), "%s",
+			 status_lookup[genpd->status]);
+	seq_printf(s, "%-30s  %-15s ", genpd->name, state);
 
 	/*
 	 * Modifications on the list require holding locks on both
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index 1e937ac5f456..00a5436dd44b 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -98,7 +98,8 @@ static bool default_stop_ok(struct device *dev)
  *
  * This routine must be executed under the PM domain's lock.
  */
-static bool default_power_down_ok(struct dev_pm_domain *pd)
+static bool __default_power_down_ok(struct dev_pm_domain *pd,
+				     unsigned int state)
 {
 	struct generic_pm_domain *genpd = pd_to_genpd(pd);
 	struct gpd_link *link;
@@ -106,27 +107,9 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 	s64 min_off_time_ns;
 	s64 off_on_time_ns;
 
-	if (genpd->max_off_time_changed) {
-		struct gpd_link *link;
-
-		/*
-		 * We have to invalidate the cached results for the masters, so
-		 * use the observation that default_power_down_ok() is not
-		 * going to be called for any master until this instance
-		 * returns.
-		 */
-		list_for_each_entry(link, &genpd->slave_links, slave_node)
-			link->master->max_off_time_changed = true;
-
-		genpd->max_off_time_changed = false;
-		genpd->cached_power_down_ok = false;
-		genpd->max_off_time_ns = -1;
-	} else {
-		return genpd->cached_power_down_ok;
-	}
+	off_on_time_ns = genpd->states[state].power_off_latency_ns +
+		genpd->states[state].power_on_latency_ns;
 
-	off_on_time_ns = genpd->power_off_latency_ns +
-				genpd->power_on_latency_ns;
 
 	min_off_time_ns = -1;
 	/*
@@ -186,8 +169,6 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 			min_off_time_ns = constraint_ns;
 	}
 
-	genpd->cached_power_down_ok = true;
-
 	/*
 	 * If the computed minimum device off time is negative, there are no
 	 * latency constraints, so the domain can spend arbitrary time in the
@@ -201,10 +182,45 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 	 * time and the time needed to turn the domain on is the maximum
 	 * theoretical time this domain can spend in the "off" state.
 	 */
-	genpd->max_off_time_ns = min_off_time_ns - genpd->power_on_latency_ns;
+	genpd->max_off_time_ns = min_off_time_ns -
+		genpd->states[state].power_on_latency_ns;
 	return true;
 }
 
+static bool default_power_down_ok(struct dev_pm_domain *pd)
+{
+	struct generic_pm_domain *genpd = pd_to_genpd(pd);
+	struct gpd_link *link;
+
+	if (!genpd->max_off_time_changed)
+		return genpd->cached_power_down_ok;
+
+	/*
+	 * We have to invalidate the cached results for the masters, so
+	 * use the observation that default_power_down_ok() is not
+	 * going to be called for any master until this instance
+	 * returns.
+	 */
+	list_for_each_entry(link, &genpd->slave_links, slave_node)
+		link->master->max_off_time_changed = true;
+
+	genpd->max_off_time_ns = -1;
+	genpd->max_off_time_changed = false;
+	genpd->cached_power_down_ok = true;
+	genpd->state_idx = genpd->state_count - 1;
+
+	/* Find a state to power down to, starting from the deepest. */
+	while (!__default_power_down_ok(pd, genpd->state_idx)) {
+		if (genpd->state_idx == 0) {
+			genpd->cached_power_down_ok = false;
+			break;
+		}
+		genpd->state_idx--;
+	}
+
+	return genpd->cached_power_down_ok;
+}
+
 static bool always_on_power_down_ok(struct dev_pm_domain *domain)
 {
 	return false;
diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index cf351d3dab1c..433b60092972 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -13,50 +13,52 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/clk.h>
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/device.h>
 #include <linux/of.h>
 #include <linux/export.h>
+#include <linux/regulator/consumer.h>
 
 #include "opp.h"
 
 /*
- * The root of the list of all devices. All device_opp structures branch off
- * from here, with each device_opp containing the list of opp it supports in
+ * The root of the list of all opp-tables. All opp_table structures branch off
+ * from here, with each opp_table containing the list of opps it supports in
  * various states of availability.
  */
-static LIST_HEAD(dev_opp_list);
+static LIST_HEAD(opp_tables);
 /* Lock to allow exclusive modification to the device and opp lists */
-DEFINE_MUTEX(dev_opp_list_lock);
+DEFINE_MUTEX(opp_table_lock);
 
 #define opp_rcu_lockdep_assert()					\
 do {									\
 	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
-				!lockdep_is_held(&dev_opp_list_lock),	\
-			   "Missing rcu_read_lock() or "		\
-			   "dev_opp_list_lock protection");		\
+			 !lockdep_is_held(&opp_table_lock),		\
+			 "Missing rcu_read_lock() or "			\
+			 "opp_table_lock protection");			\
 } while (0)
 
-static struct device_list_opp *_find_list_dev(const struct device *dev,
-					      struct device_opp *dev_opp)
+static struct opp_device *_find_opp_dev(const struct device *dev,
+					struct opp_table *opp_table)
 {
-	struct device_list_opp *list_dev;
+	struct opp_device *opp_dev;
 
-	list_for_each_entry(list_dev, &dev_opp->dev_list, node)
-		if (list_dev->dev == dev)
-			return list_dev;
+	list_for_each_entry(opp_dev, &opp_table->dev_list, node)
+		if (opp_dev->dev == dev)
+			return opp_dev;
 
 	return NULL;
 }
 
-static struct device_opp *_managed_opp(const struct device_node *np)
+static struct opp_table *_managed_opp(const struct device_node *np)
 {
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 
-	list_for_each_entry_rcu(dev_opp, &dev_opp_list, node) {
-		if (dev_opp->np == np) {
+	list_for_each_entry_rcu(opp_table, &opp_tables, node) {
+		if (opp_table->np == np) {
 			/*
 			 * Multiple devices can point to the same OPP table and
 			 * so will have same node-pointer, np.
@@ -64,7 +66,7 @@ static struct device_opp *_managed_opp(const struct device_node *np)
 			 * But the OPPs will be considered as shared only if the
 			 * OPP table contains a "opp-shared" property.
 			 */
-			return dev_opp->shared_opp ? dev_opp : NULL;
+			return opp_table->shared_opp ? opp_table : NULL;
 		}
 	}
 
@@ -72,24 +74,24 @@ static struct device_opp *_managed_opp(const struct device_node *np)
 }
 
 /**
- * _find_device_opp() - find device_opp struct using device pointer
- * @dev:	device pointer used to lookup device OPPs
+ * _find_opp_table() - find opp_table struct using device pointer
+ * @dev:	device pointer used to lookup OPP table
  *
- * Search list of device OPPs for one containing matching device. Does a RCU
- * reader operation to grab the pointer needed.
+ * Search OPP table for one containing matching device. Does a RCU reader
+ * operation to grab the pointer needed.
  *
- * Return: pointer to 'struct device_opp' if found, otherwise -ENODEV or
+ * Return: pointer to 'struct opp_table' if found, otherwise -ENODEV or
  * -EINVAL based on type of error.
  *
  * Locking: For readers, this function must be called under rcu_read_lock().
- * device_opp is a RCU protected pointer, which means that device_opp is valid
+ * opp_table is a RCU protected pointer, which means that opp_table is valid
  * as long as we are under RCU lock.
  *
- * For Writers, this function must be called with dev_opp_list_lock held.
+ * For Writers, this function must be called with opp_table_lock held.
  */
-struct device_opp *_find_device_opp(struct device *dev)
+struct opp_table *_find_opp_table(struct device *dev)
 {
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 
 	opp_rcu_lockdep_assert();
 
@@ -98,9 +100,9 @@ struct device_opp *_find_device_opp(struct device *dev)
 		return ERR_PTR(-EINVAL);
 	}
 
-	list_for_each_entry_rcu(dev_opp, &dev_opp_list, node)
-		if (_find_list_dev(dev, dev_opp))
-			return dev_opp;
+	list_for_each_entry_rcu(opp_table, &opp_tables, node)
+		if (_find_opp_dev(dev, opp_table))
+			return opp_table;
 
 	return ERR_PTR(-ENODEV);
 }
@@ -213,16 +215,16 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_is_turbo);
  */
 unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev)
 {
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 	unsigned long clock_latency_ns;
 
 	rcu_read_lock();
 
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp))
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
 		clock_latency_ns = 0;
 	else
-		clock_latency_ns = dev_opp->clock_latency_ns_max;
+		clock_latency_ns = opp_table->clock_latency_ns_max;
 
 	rcu_read_unlock();
 	return clock_latency_ns;
@@ -230,6 +232,82 @@ unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev)
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency);
 
 /**
+ * dev_pm_opp_get_max_volt_latency() - Get max voltage latency in nanoseconds
+ * @dev: device for which we do this operation
+ *
+ * Return: This function returns the max voltage latency in nanoseconds.
+ *
+ * Locking: This function takes rcu_read_lock().
+ */
+unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
+{
+	struct opp_table *opp_table;
+	struct dev_pm_opp *opp;
+	struct regulator *reg;
+	unsigned long latency_ns = 0;
+	unsigned long min_uV = ~0, max_uV = 0;
+	int ret;
+
+	rcu_read_lock();
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		rcu_read_unlock();
+		return 0;
+	}
+
+	reg = opp_table->regulator;
+	if (IS_ERR(reg)) {
+		/* Regulator may not be required for device */
+		if (reg)
+			dev_err(dev, "%s: Invalid regulator (%ld)\n", __func__,
+				PTR_ERR(reg));
+		rcu_read_unlock();
+		return 0;
+	}
+
+	list_for_each_entry_rcu(opp, &opp_table->opp_list, node) {
+		if (!opp->available)
+			continue;
+
+		if (opp->u_volt_min < min_uV)
+			min_uV = opp->u_volt_min;
+		if (opp->u_volt_max > max_uV)
+			max_uV = opp->u_volt_max;
+	}
+
+	rcu_read_unlock();
+
+	/*
+	 * The caller needs to ensure that opp_table (and hence the regulator)
+	 * isn't freed, while we are executing this routine.
+	 */
+	ret = regulator_set_voltage_time(reg, min_uV, max_uV);
+	if (ret > 0)
+		latency_ns = ret * 1000;
+
+	return latency_ns;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_volt_latency);
+
+/**
+ * dev_pm_opp_get_max_transition_latency() - Get max transition latency in
+ *					     nanoseconds
+ * @dev: device for which we do this operation
+ *
+ * Return: This function returns the max transition latency, in nanoseconds, to
+ * switch from one OPP to other.
+ *
+ * Locking: This function takes rcu_read_lock().
+ */
+unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev)
+{
+	return dev_pm_opp_get_max_volt_latency(dev) +
+		dev_pm_opp_get_max_clock_latency(dev);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_transition_latency);
+
+/**
  * dev_pm_opp_get_suspend_opp() - Get suspend opp
  * @dev:	device for which we do this operation
  *
@@ -244,21 +322,21 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency);
  */
 struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev)
 {
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 
 	opp_rcu_lockdep_assert();
 
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp) || !dev_opp->suspend_opp ||
-	    !dev_opp->suspend_opp->available)
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table) || !opp_table->suspend_opp ||
+	    !opp_table->suspend_opp->available)
 		return NULL;
 
-	return dev_opp->suspend_opp;
+	return opp_table->suspend_opp;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp);
 
 /**
- * dev_pm_opp_get_opp_count() - Get number of opps available in the opp list
+ * dev_pm_opp_get_opp_count() - Get number of opps available in the opp table
  * @dev:	device for which we do this operation
  *
  * Return: This function returns the number of available opps if there are any,
@@ -268,21 +346,21 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp);
  */
 int dev_pm_opp_get_opp_count(struct device *dev)
 {
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 	struct dev_pm_opp *temp_opp;
 	int count = 0;
 
 	rcu_read_lock();
 
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp)) {
-		count = PTR_ERR(dev_opp);
-		dev_err(dev, "%s: device OPP not found (%d)\n",
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		count = PTR_ERR(opp_table);
+		dev_err(dev, "%s: OPP table not found (%d)\n",
 			__func__, count);
 		goto out_unlock;
 	}
 
-	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available)
 			count++;
 	}
@@ -299,7 +377,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_count);
  * @freq:		frequency to search for
  * @available:		true/false - match for available opp
  *
- * Return: Searches for exact match in the opp list and returns pointer to the
+ * Return: Searches for exact match in the opp table and returns pointer to the
  * matching opp if found, else returns ERR_PTR in case of error and should
  * be handled using IS_ERR. Error return values can be:
  * EINVAL:	for bad pointer
@@ -323,19 +401,20 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 					      unsigned long freq,
 					      bool available)
 {
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
 	opp_rcu_lockdep_assert();
 
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp)) {
-		int r = PTR_ERR(dev_opp);
-		dev_err(dev, "%s: device OPP not found (%d)\n", __func__, r);
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		int r = PTR_ERR(opp_table);
+
+		dev_err(dev, "%s: OPP table not found (%d)\n", __func__, r);
 		return ERR_PTR(r);
 	}
 
-	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available == available &&
 				temp_opp->rate == freq) {
 			opp = temp_opp;
@@ -371,7 +450,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_exact);
 struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 					     unsigned long *freq)
 {
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
 	opp_rcu_lockdep_assert();
@@ -381,11 +460,11 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 		return ERR_PTR(-EINVAL);
 	}
 
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp))
-		return ERR_CAST(dev_opp);
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
+		return ERR_CAST(opp_table);
 
-	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available && temp_opp->rate >= *freq) {
 			opp = temp_opp;
 			*freq = opp->rate;
@@ -421,7 +500,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil);
 struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 					      unsigned long *freq)
 {
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
 	opp_rcu_lockdep_assert();
@@ -431,11 +510,11 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 		return ERR_PTR(-EINVAL);
 	}
 
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp))
-		return ERR_CAST(dev_opp);
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
+		return ERR_CAST(opp_table);
 
-	list_for_each_entry_rcu(temp_opp, &dev_opp->opp_list, node) {
+	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available) {
 			/* go to the next node, before choosing prev */
 			if (temp_opp->rate > *freq)
@@ -451,130 +530,343 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor);
 
-/* List-dev Helpers */
-static void _kfree_list_dev_rcu(struct rcu_head *head)
+/*
+ * The caller needs to ensure that opp_table (and hence the clk) isn't freed,
+ * while clk returned here is used.
+ */
+static struct clk *_get_opp_clk(struct device *dev)
+{
+	struct opp_table *opp_table;
+	struct clk *clk;
+
+	rcu_read_lock();
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		dev_err(dev, "%s: device opp doesn't exist\n", __func__);
+		clk = ERR_CAST(opp_table);
+		goto unlock;
+	}
+
+	clk = opp_table->clk;
+	if (IS_ERR(clk))
+		dev_err(dev, "%s: No clock available for the device\n",
+			__func__);
+
+unlock:
+	rcu_read_unlock();
+	return clk;
+}
+
+static int _set_opp_voltage(struct device *dev, struct regulator *reg,
+			    unsigned long u_volt, unsigned long u_volt_min,
+			    unsigned long u_volt_max)
+{
+	int ret;
+
+	/* Regulator not available for device */
+	if (IS_ERR(reg)) {
+		dev_dbg(dev, "%s: regulator not available: %ld\n", __func__,
+			PTR_ERR(reg));
+		return 0;
+	}
+
+	dev_dbg(dev, "%s: voltages (mV): %lu %lu %lu\n", __func__, u_volt_min,
+		u_volt, u_volt_max);
+
+	ret = regulator_set_voltage_triplet(reg, u_volt_min, u_volt,
+					    u_volt_max);
+	if (ret)
+		dev_err(dev, "%s: failed to set voltage (%lu %lu %lu mV): %d\n",
+			__func__, u_volt_min, u_volt, u_volt_max, ret);
+
+	return ret;
+}
+
+/**
+ * dev_pm_opp_set_rate() - Configure new OPP based on frequency
+ * @dev:	 device for which we do this operation
+ * @target_freq: frequency to achieve
+ *
+ * This configures the power-supplies and clock source to the levels specified
+ * by the OPP corresponding to the target_freq.
+ *
+ * Locking: This function takes rcu_read_lock().
+ */
+int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
+{
+	struct opp_table *opp_table;
+	struct dev_pm_opp *old_opp, *opp;
+	struct regulator *reg;
+	struct clk *clk;
+	unsigned long freq, old_freq;
+	unsigned long u_volt, u_volt_min, u_volt_max;
+	unsigned long ou_volt, ou_volt_min, ou_volt_max;
+	int ret;
+
+	if (unlikely(!target_freq)) {
+		dev_err(dev, "%s: Invalid target frequency %lu\n", __func__,
+			target_freq);
+		return -EINVAL;
+	}
+
+	clk = _get_opp_clk(dev);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	freq = clk_round_rate(clk, target_freq);
+	if ((long)freq <= 0)
+		freq = target_freq;
+
+	old_freq = clk_get_rate(clk);
+
+	/* Return early if nothing to do */
+	if (old_freq == freq) {
+		dev_dbg(dev, "%s: old/new frequencies (%lu Hz) are same, nothing to do\n",
+			__func__, freq);
+		return 0;
+	}
+
+	rcu_read_lock();
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		dev_err(dev, "%s: device opp doesn't exist\n", __func__);
+		rcu_read_unlock();
+		return PTR_ERR(opp_table);
+	}
+
+	old_opp = dev_pm_opp_find_freq_ceil(dev, &old_freq);
+	if (!IS_ERR(old_opp)) {
+		ou_volt = old_opp->u_volt;
+		ou_volt_min = old_opp->u_volt_min;
+		ou_volt_max = old_opp->u_volt_max;
+	} else {
+		dev_err(dev, "%s: failed to find current OPP for freq %lu (%ld)\n",
+			__func__, old_freq, PTR_ERR(old_opp));
+	}
+
+	opp = dev_pm_opp_find_freq_ceil(dev, &freq);
+	if (IS_ERR(opp)) {
+		ret = PTR_ERR(opp);
+		dev_err(dev, "%s: failed to find OPP for freq %lu (%d)\n",
+			__func__, freq, ret);
+		rcu_read_unlock();
+		return ret;
+	}
+
+	u_volt = opp->u_volt;
+	u_volt_min = opp->u_volt_min;
+	u_volt_max = opp->u_volt_max;
+
+	reg = opp_table->regulator;
+
+	rcu_read_unlock();
+
+	/* Scaling up? Scale voltage before frequency */
+	if (freq > old_freq) {
+		ret = _set_opp_voltage(dev, reg, u_volt, u_volt_min,
+				       u_volt_max);
+		if (ret)
+			goto restore_voltage;
+	}
+
+	/* Change frequency */
+
+	dev_dbg(dev, "%s: switching OPP: %lu Hz --> %lu Hz\n",
+		__func__, old_freq, freq);
+
+	ret = clk_set_rate(clk, freq);
+	if (ret) {
+		dev_err(dev, "%s: failed to set clock rate: %d\n", __func__,
+			ret);
+		goto restore_voltage;
+	}
+
+	/* Scaling down? Scale voltage after frequency */
+	if (freq < old_freq) {
+		ret = _set_opp_voltage(dev, reg, u_volt, u_volt_min,
+				       u_volt_max);
+		if (ret)
+			goto restore_freq;
+	}
+
+	return 0;
+
+restore_freq:
+	if (clk_set_rate(clk, old_freq))
+		dev_err(dev, "%s: failed to restore old-freq (%lu Hz)\n",
+			__func__, old_freq);
+restore_voltage:
+	/* This shouldn't harm even if the voltages weren't updated earlier */
+	if (!IS_ERR(old_opp))
+		_set_opp_voltage(dev, reg, ou_volt, ou_volt_min, ou_volt_max);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_set_rate);
+
+/* OPP-dev Helpers */
+static void _kfree_opp_dev_rcu(struct rcu_head *head)
 {
-	struct device_list_opp *list_dev;
+	struct opp_device *opp_dev;
 
-	list_dev = container_of(head, struct device_list_opp, rcu_head);
-	kfree_rcu(list_dev, rcu_head);
+	opp_dev = container_of(head, struct opp_device, rcu_head);
+	kfree_rcu(opp_dev, rcu_head);
 }
 
-static void _remove_list_dev(struct device_list_opp *list_dev,
-			     struct device_opp *dev_opp)
+static void _remove_opp_dev(struct opp_device *opp_dev,
+			    struct opp_table *opp_table)
 {
-	opp_debug_unregister(list_dev, dev_opp);
-	list_del(&list_dev->node);
-	call_srcu(&dev_opp->srcu_head.srcu, &list_dev->rcu_head,
-		  _kfree_list_dev_rcu);
+	opp_debug_unregister(opp_dev, opp_table);
+	list_del(&opp_dev->node);
+	call_srcu(&opp_table->srcu_head.srcu, &opp_dev->rcu_head,
+		  _kfree_opp_dev_rcu);
 }
 
-struct device_list_opp *_add_list_dev(const struct device *dev,
-				      struct device_opp *dev_opp)
+struct opp_device *_add_opp_dev(const struct device *dev,
+				struct opp_table *opp_table)
 {
-	struct device_list_opp *list_dev;
+	struct opp_device *opp_dev;
 	int ret;
 
-	list_dev = kzalloc(sizeof(*list_dev), GFP_KERNEL);
-	if (!list_dev)
+	opp_dev = kzalloc(sizeof(*opp_dev), GFP_KERNEL);
+	if (!opp_dev)
 		return NULL;
 
-	/* Initialize list-dev */
-	list_dev->dev = dev;
-	list_add_rcu(&list_dev->node, &dev_opp->dev_list);
+	/* Initialize opp-dev */
+	opp_dev->dev = dev;
+	list_add_rcu(&opp_dev->node, &opp_table->dev_list);
 
-	/* Create debugfs entries for the dev_opp */
-	ret = opp_debug_register(list_dev, dev_opp);
+	/* Create debugfs entries for the opp_table */
+	ret = opp_debug_register(opp_dev, opp_table);
 	if (ret)
 		dev_err(dev, "%s: Failed to register opp debugfs (%d)\n",
 			__func__, ret);
 
-	return list_dev;
+	return opp_dev;
 }
 
 /**
- * _add_device_opp() - Find device OPP table or allocate a new one
+ * _add_opp_table() - Find OPP table or allocate a new one
  * @dev:	device for which we do this operation
  *
  * It tries to find an existing table first, if it couldn't find one, it
  * allocates a new OPP table and returns that.
  *
- * Return: valid device_opp pointer if success, else NULL.
+ * Return: valid opp_table pointer if success, else NULL.
  */
-static struct device_opp *_add_device_opp(struct device *dev)
+static struct opp_table *_add_opp_table(struct device *dev)
 {
-	struct device_opp *dev_opp;
-	struct device_list_opp *list_dev;
+	struct opp_table *opp_table;
+	struct opp_device *opp_dev;
+	struct device_node *np;
+	int ret;
 
-	/* Check for existing list for 'dev' first */
-	dev_opp = _find_device_opp(dev);
-	if (!IS_ERR(dev_opp))
-		return dev_opp;
+	/* Check for existing table for 'dev' first */
+	opp_table = _find_opp_table(dev);
+	if (!IS_ERR(opp_table))
+		return opp_table;
 
 	/*
-	 * Allocate a new device OPP table. In the infrequent case where a new
+	 * Allocate a new OPP table. In the infrequent case where a new
 	 * device is needed to be added, we pay this penalty.
 	 */
-	dev_opp = kzalloc(sizeof(*dev_opp), GFP_KERNEL);
-	if (!dev_opp)
+	opp_table = kzalloc(sizeof(*opp_table), GFP_KERNEL);
+	if (!opp_table)
 		return NULL;
 
-	INIT_LIST_HEAD(&dev_opp->dev_list);
+	INIT_LIST_HEAD(&opp_table->dev_list);
 
-	list_dev = _add_list_dev(dev, dev_opp);
-	if (!list_dev) {
-		kfree(dev_opp);
+	opp_dev = _add_opp_dev(dev, opp_table);
+	if (!opp_dev) {
+		kfree(opp_table);
 		return NULL;
 	}
 
-	srcu_init_notifier_head(&dev_opp->srcu_head);
-	INIT_LIST_HEAD(&dev_opp->opp_list);
+	/*
+	 * Only required for backward compatibility with v1 bindings, but isn't
+	 * harmful for other cases. And so we do it unconditionally.
+	 */
+	np = of_node_get(dev->of_node);
+	if (np) {
+		u32 val;
+
+		if (!of_property_read_u32(np, "clock-latency", &val))
+			opp_table->clock_latency_ns_max = val;
+		of_property_read_u32(np, "voltage-tolerance",
+				     &opp_table->voltage_tolerance_v1);
+		of_node_put(np);
+	}
+
+	/* Set regulator to a non-NULL error value */
+	opp_table->regulator = ERR_PTR(-ENXIO);
+
+	/* Find clk for the device */
+	opp_table->clk = clk_get(dev, NULL);
+	if (IS_ERR(opp_table->clk)) {
+		ret = PTR_ERR(opp_table->clk);
+		if (ret != -EPROBE_DEFER)
+			dev_dbg(dev, "%s: Couldn't find clock: %d\n", __func__,
+				ret);
+	}
 
-	/* Secure the device list modification */
-	list_add_rcu(&dev_opp->node, &dev_opp_list);
-	return dev_opp;
+	srcu_init_notifier_head(&opp_table->srcu_head);
+	INIT_LIST_HEAD(&opp_table->opp_list);
+
+	/* Secure the device table modification */
+	list_add_rcu(&opp_table->node, &opp_tables);
+	return opp_table;
 }
 
 /**
- * _kfree_device_rcu() - Free device_opp RCU handler
+ * _kfree_device_rcu() - Free opp_table RCU handler
  * @head:	RCU head
  */
 static void _kfree_device_rcu(struct rcu_head *head)
 {
-	struct device_opp *device_opp = container_of(head, struct device_opp, rcu_head);
+	struct opp_table *opp_table = container_of(head, struct opp_table,
+						   rcu_head);
 
-	kfree_rcu(device_opp, rcu_head);
+	kfree_rcu(opp_table, rcu_head);
 }
 
 /**
- * _remove_device_opp() - Removes a device OPP table
- * @dev_opp: device OPP table to be removed.
+ * _remove_opp_table() - Removes a OPP table
+ * @opp_table: OPP table to be removed.
  *
- * Removes/frees device OPP table it it doesn't contain any OPPs.
+ * Removes/frees OPP table if it doesn't contain any OPPs.
  */
-static void _remove_device_opp(struct device_opp *dev_opp)
+static void _remove_opp_table(struct opp_table *opp_table)
 {
-	struct device_list_opp *list_dev;
+	struct opp_device *opp_dev;
+
+	if (!list_empty(&opp_table->opp_list))
+		return;
 
-	if (!list_empty(&dev_opp->opp_list))
+	if (opp_table->supported_hw)
 		return;
 
-	if (dev_opp->supported_hw)
+	if (opp_table->prop_name)
 		return;
 
-	if (dev_opp->prop_name)
+	if (!IS_ERR(opp_table->regulator))
 		return;
 
-	list_dev = list_first_entry(&dev_opp->dev_list, struct device_list_opp,
-				    node);
+	/* Release clk */
+	if (!IS_ERR(opp_table->clk))
+		clk_put(opp_table->clk);
 
-	_remove_list_dev(list_dev, dev_opp);
+	opp_dev = list_first_entry(&opp_table->dev_list, struct opp_device,
+				   node);
+
+	_remove_opp_dev(opp_dev, opp_table);
 
 	/* dev_list must be empty now */
-	WARN_ON(!list_empty(&dev_opp->dev_list));
+	WARN_ON(!list_empty(&opp_table->dev_list));
 
-	list_del_rcu(&dev_opp->node);
-	call_srcu(&dev_opp->srcu_head.srcu, &dev_opp->rcu_head,
+	list_del_rcu(&opp_table->node);
+	call_srcu(&opp_table->srcu_head.srcu, &opp_table->rcu_head,
 		  _kfree_device_rcu);
 }
 
@@ -591,17 +883,17 @@ static void _kfree_opp_rcu(struct rcu_head *head)
 
 /**
  * _opp_remove()  - Remove an OPP from a table definition
- * @dev_opp:	points back to the device_opp struct this opp belongs to
+ * @opp_table:	points back to the opp_table struct this opp belongs to
  * @opp:	pointer to the OPP to remove
  * @notify:	OPP_EVENT_REMOVE notification should be sent or not
  *
- * This function removes an opp definition from the opp list.
+ * This function removes an opp definition from the opp table.
  *
- * Locking: The internal device_opp and opp structures are RCU protected.
+ * Locking: The internal opp_table and opp structures are RCU protected.
  * It is assumed that the caller holds required mutex for an RCU updater
  * strategy.
  */
-static void _opp_remove(struct device_opp *dev_opp,
+static void _opp_remove(struct opp_table *opp_table,
 			struct dev_pm_opp *opp, bool notify)
 {
 	/*
@@ -609,22 +901,23 @@ static void _opp_remove(struct device_opp *dev_opp,
 	 * frequency/voltage list.
 	 */
 	if (notify)
-		srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_REMOVE, opp);
+		srcu_notifier_call_chain(&opp_table->srcu_head,
+					 OPP_EVENT_REMOVE, opp);
 	opp_debug_remove_one(opp);
 	list_del_rcu(&opp->node);
-	call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
+	call_srcu(&opp_table->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
 
-	_remove_device_opp(dev_opp);
+	_remove_opp_table(opp_table);
 }
 
 /**
- * dev_pm_opp_remove()  - Remove an OPP from OPP list
+ * dev_pm_opp_remove()  - Remove an OPP from OPP table
  * @dev:	device for which we do this operation
  * @freq:	OPP to remove with matching 'freq'
  *
- * This function removes an opp from the opp list.
+ * This function removes an opp from the opp table.
  *
- * Locking: The internal device_opp and opp structures are RCU protected.
+ * Locking: The internal opp_table and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
@@ -633,17 +926,17 @@ static void _opp_remove(struct device_opp *dev_opp,
 void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 {
 	struct dev_pm_opp *opp;
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 	bool found = false;
 
-	/* Hold our list modification lock here */
-	mutex_lock(&dev_opp_list_lock);
+	/* Hold our table modification lock here */
+	mutex_lock(&opp_table_lock);
 
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp))
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
 		goto unlock;
 
-	list_for_each_entry(opp, &dev_opp->opp_list, node) {
+	list_for_each_entry(opp, &opp_table->opp_list, node) {
 		if (opp->rate == freq) {
 			found = true;
 			break;
@@ -656,14 +949,14 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 		goto unlock;
 	}
 
-	_opp_remove(dev_opp, opp, true);
+	_opp_remove(opp_table, opp, true);
 unlock:
-	mutex_unlock(&dev_opp_list_lock);
+	mutex_unlock(&opp_table_lock);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
 
 static struct dev_pm_opp *_allocate_opp(struct device *dev,
-					struct device_opp **dev_opp)
+					struct opp_table **opp_table)
 {
 	struct dev_pm_opp *opp;
 
@@ -674,8 +967,8 @@ static struct dev_pm_opp *_allocate_opp(struct device *dev,
 
 	INIT_LIST_HEAD(&opp->node);
 
-	*dev_opp = _add_device_opp(dev);
-	if (!*dev_opp) {
+	*opp_table = _add_opp_table(dev);
+	if (!*opp_table) {
 		kfree(opp);
 		return NULL;
 	}
@@ -683,22 +976,38 @@ static struct dev_pm_opp *_allocate_opp(struct device *dev,
 	return opp;
 }
 
+static bool _opp_supported_by_regulators(struct dev_pm_opp *opp,
+					 struct opp_table *opp_table)
+{
+	struct regulator *reg = opp_table->regulator;
+
+	if (!IS_ERR(reg) &&
+	    !regulator_is_supported_voltage(reg, opp->u_volt_min,
+					    opp->u_volt_max)) {
+		pr_warn("%s: OPP minuV: %lu maxuV: %lu, not supported by regulator\n",
+			__func__, opp->u_volt_min, opp->u_volt_max);
+		return false;
+	}
+
+	return true;
+}
+
 static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
-		    struct device_opp *dev_opp)
+		    struct opp_table *opp_table)
 {
 	struct dev_pm_opp *opp;
-	struct list_head *head = &dev_opp->opp_list;
+	struct list_head *head = &opp_table->opp_list;
 	int ret;
 
 	/*
 	 * Insert new OPP in order of increasing frequency and discard if
 	 * already present.
 	 *
-	 * Need to use &dev_opp->opp_list in the condition part of the 'for'
+	 * Need to use &opp_table->opp_list in the condition part of the 'for'
 	 * loop, don't replace it with head otherwise it will become an infinite
 	 * loop.
 	 */
-	list_for_each_entry_rcu(opp, &dev_opp->opp_list, node) {
+	list_for_each_entry_rcu(opp, &opp_table->opp_list, node) {
 		if (new_opp->rate > opp->rate) {
 			head = &opp->node;
 			continue;
@@ -716,14 +1025,20 @@ static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 			0 : -EEXIST;
 	}
 
-	new_opp->dev_opp = dev_opp;
+	new_opp->opp_table = opp_table;
 	list_add_rcu(&new_opp->node, head);
 
-	ret = opp_debug_create_one(new_opp, dev_opp);
+	ret = opp_debug_create_one(new_opp, opp_table);
 	if (ret)
 		dev_err(dev, "%s: Failed to register opp to debugfs (%d)\n",
 			__func__, ret);
 
+	if (!_opp_supported_by_regulators(new_opp, opp_table)) {
+		new_opp->available = false;
+		dev_warn(dev, "%s: OPP not supported by regulators (%lu)\n",
+			 __func__, new_opp->rate);
+	}
+
 	return 0;
 }
 
@@ -734,14 +1049,14 @@ static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
  * @u_volt:	Voltage in uVolts for this OPP
  * @dynamic:	Dynamically added OPPs.
  *
- * This function adds an opp definition to the opp list and returns status.
+ * This function adds an opp definition to the opp table and returns status.
  * The opp is made available by default and it can be controlled using
  * dev_pm_opp_enable/disable functions and may be removed by dev_pm_opp_remove.
  *
  * NOTE: "dynamic" parameter impacts OPPs added by the dev_pm_opp_of_add_table
  * and freed by dev_pm_opp_of_remove_table.
  *
- * Locking: The internal device_opp and opp structures are RCU protected.
+ * Locking: The internal opp_table and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
@@ -757,14 +1072,15 @@ static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 static int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt,
 		       bool dynamic)
 {
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 	struct dev_pm_opp *new_opp;
+	unsigned long tol;
 	int ret;
 
-	/* Hold our list modification lock here */
-	mutex_lock(&dev_opp_list_lock);
+	/* Hold our table modification lock here */
+	mutex_lock(&opp_table_lock);
 
-	new_opp = _allocate_opp(dev, &dev_opp);
+	new_opp = _allocate_opp(dev, &opp_table);
 	if (!new_opp) {
 		ret = -ENOMEM;
 		goto unlock;
@@ -772,33 +1088,36 @@ static int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt,
 
 	/* populate the opp table */
 	new_opp->rate = freq;
+	tol = u_volt * opp_table->voltage_tolerance_v1 / 100;
 	new_opp->u_volt = u_volt;
+	new_opp->u_volt_min = u_volt - tol;
+	new_opp->u_volt_max = u_volt + tol;
 	new_opp->available = true;
 	new_opp->dynamic = dynamic;
 
-	ret = _opp_add(dev, new_opp, dev_opp);
+	ret = _opp_add(dev, new_opp, opp_table);
 	if (ret)
 		goto free_opp;
 
-	mutex_unlock(&dev_opp_list_lock);
+	mutex_unlock(&opp_table_lock);
 
 	/*
 	 * Notify the changes in the availability of the operable
 	 * frequency/voltage list.
 	 */
-	srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ADD, new_opp);
+	srcu_notifier_call_chain(&opp_table->srcu_head, OPP_EVENT_ADD, new_opp);
 	return 0;
 
 free_opp:
-	_opp_remove(dev_opp, new_opp, false);
+	_opp_remove(opp_table, new_opp, false);
 unlock:
-	mutex_unlock(&dev_opp_list_lock);
+	mutex_unlock(&opp_table_lock);
 	return ret;
 }
 
 /* TODO: Support multiple regulators */
 static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
-			      struct device_opp *dev_opp)
+			      struct opp_table *opp_table)
 {
 	u32 microvolt[3] = {0};
 	u32 val;
@@ -807,9 +1126,9 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
 	char name[NAME_MAX];
 
 	/* Search for "opp-microvolt-<name>" */
-	if (dev_opp->prop_name) {
+	if (opp_table->prop_name) {
 		snprintf(name, sizeof(name), "opp-microvolt-%s",
-			 dev_opp->prop_name);
+			 opp_table->prop_name);
 		prop = of_find_property(opp->np, name, NULL);
 	}
 
@@ -844,14 +1163,20 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
 	}
 
 	opp->u_volt = microvolt[0];
-	opp->u_volt_min = microvolt[1];
-	opp->u_volt_max = microvolt[2];
+
+	if (count == 1) {
+		opp->u_volt_min = opp->u_volt;
+		opp->u_volt_max = opp->u_volt;
+	} else {
+		opp->u_volt_min = microvolt[1];
+		opp->u_volt_max = microvolt[2];
+	}
 
 	/* Search for "opp-microamp-<name>" */
 	prop = NULL;
-	if (dev_opp->prop_name) {
+	if (opp_table->prop_name) {
 		snprintf(name, sizeof(name), "opp-microamp-%s",
-			 dev_opp->prop_name);
+			 opp_table->prop_name);
 		prop = of_find_property(opp->np, name, NULL);
 	}
 
@@ -878,7 +1203,7 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
  * OPPs, which are available for those versions, based on its 'opp-supported-hw'
  * property.
  *
- * Locking: The internal device_opp and opp structures are RCU protected.
+ * Locking: The internal opp_table and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
@@ -887,44 +1212,44 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
 int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions,
 				unsigned int count)
 {
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 	int ret = 0;
 
-	/* Hold our list modification lock here */
-	mutex_lock(&dev_opp_list_lock);
+	/* Hold our table modification lock here */
+	mutex_lock(&opp_table_lock);
 
-	dev_opp = _add_device_opp(dev);
-	if (!dev_opp) {
+	opp_table = _add_opp_table(dev);
+	if (!opp_table) {
 		ret = -ENOMEM;
 		goto unlock;
 	}
 
-	/* Make sure there are no concurrent readers while updating dev_opp */
-	WARN_ON(!list_empty(&dev_opp->opp_list));
+	/* Make sure there are no concurrent readers while updating opp_table */
+	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	/* Do we already have a version hierarchy associated with dev_opp? */
-	if (dev_opp->supported_hw) {
+	/* Do we already have a version hierarchy associated with opp_table? */
+	if (opp_table->supported_hw) {
 		dev_err(dev, "%s: Already have supported hardware list\n",
 			__func__);
 		ret = -EBUSY;
 		goto err;
 	}
 
-	dev_opp->supported_hw = kmemdup(versions, count * sizeof(*versions),
+	opp_table->supported_hw = kmemdup(versions, count * sizeof(*versions),
 					GFP_KERNEL);
-	if (!dev_opp->supported_hw) {
+	if (!opp_table->supported_hw) {
 		ret = -ENOMEM;
 		goto err;
 	}
 
-	dev_opp->supported_hw_count = count;
-	mutex_unlock(&dev_opp_list_lock);
+	opp_table->supported_hw_count = count;
+	mutex_unlock(&opp_table_lock);
 	return 0;
 
 err:
-	_remove_device_opp(dev_opp);
+	_remove_opp_table(opp_table);
 unlock:
-	mutex_unlock(&dev_opp_list_lock);
+	mutex_unlock(&opp_table_lock);
 
 	return ret;
 }
@@ -932,13 +1257,13 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_supported_hw);
 
 /**
  * dev_pm_opp_put_supported_hw() - Releases resources blocked for supported hw
- * @dev: Device for which supported-hw has to be set.
+ * @dev: Device for which supported-hw has to be put.
  *
  * This is required only for the V2 bindings, and is called for a matching
- * dev_pm_opp_set_supported_hw(). Until this is called, the device_opp structure
+ * dev_pm_opp_set_supported_hw(). Until this is called, the opp_table structure
  * will not be freed.
  *
- * Locking: The internal device_opp and opp structures are RCU protected.
+ * Locking: The internal opp_table and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
@@ -946,42 +1271,43 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_supported_hw);
  */
 void dev_pm_opp_put_supported_hw(struct device *dev)
 {
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 
-	/* Hold our list modification lock here */
-	mutex_lock(&dev_opp_list_lock);
+	/* Hold our table modification lock here */
+	mutex_lock(&opp_table_lock);
 
-	/* Check for existing list for 'dev' first */
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp)) {
-		dev_err(dev, "Failed to find dev_opp: %ld\n", PTR_ERR(dev_opp));
+	/* Check for existing table for 'dev' first */
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		dev_err(dev, "Failed to find opp_table: %ld\n",
+			PTR_ERR(opp_table));
 		goto unlock;
 	}
 
-	/* Make sure there are no concurrent readers while updating dev_opp */
-	WARN_ON(!list_empty(&dev_opp->opp_list));
+	/* Make sure there are no concurrent readers while updating opp_table */
+	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	if (!dev_opp->supported_hw) {
+	if (!opp_table->supported_hw) {
 		dev_err(dev, "%s: Doesn't have supported hardware list\n",
 			__func__);
 		goto unlock;
 	}
 
-	kfree(dev_opp->supported_hw);
-	dev_opp->supported_hw = NULL;
-	dev_opp->supported_hw_count = 0;
+	kfree(opp_table->supported_hw);
+	opp_table->supported_hw = NULL;
+	opp_table->supported_hw_count = 0;
 
-	/* Try freeing device_opp if this was the last blocking resource */
-	_remove_device_opp(dev_opp);
+	/* Try freeing opp_table if this was the last blocking resource */
+	_remove_opp_table(opp_table);
 
 unlock:
-	mutex_unlock(&dev_opp_list_lock);
+	mutex_unlock(&opp_table_lock);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_supported_hw);
 
 /**
  * dev_pm_opp_set_prop_name() - Set prop-extn name
- * @dev: Device for which the regulator has to be set.
+ * @dev: Device for which the prop-name has to be set.
  * @name: name to postfix to properties.
  *
  * This is required only for the V2 bindings, and it enables a platform to
@@ -989,7 +1315,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_supported_hw);
  * which the extension will apply are opp-microvolt and opp-microamp. OPP core
  * should postfix the property name with -<name> while looking for them.
  *
- * Locking: The internal device_opp and opp structures are RCU protected.
+ * Locking: The internal opp_table and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
@@ -997,42 +1323,42 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_supported_hw);
  */
 int dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 {
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 	int ret = 0;
 
-	/* Hold our list modification lock here */
-	mutex_lock(&dev_opp_list_lock);
+	/* Hold our table modification lock here */
+	mutex_lock(&opp_table_lock);
 
-	dev_opp = _add_device_opp(dev);
-	if (!dev_opp) {
+	opp_table = _add_opp_table(dev);
+	if (!opp_table) {
 		ret = -ENOMEM;
 		goto unlock;
 	}
 
-	/* Make sure there are no concurrent readers while updating dev_opp */
-	WARN_ON(!list_empty(&dev_opp->opp_list));
+	/* Make sure there are no concurrent readers while updating opp_table */
+	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	/* Do we already have a prop-name associated with dev_opp? */
-	if (dev_opp->prop_name) {
+	/* Do we already have a prop-name associated with opp_table? */
+	if (opp_table->prop_name) {
 		dev_err(dev, "%s: Already have prop-name %s\n", __func__,
-			dev_opp->prop_name);
+			opp_table->prop_name);
 		ret = -EBUSY;
 		goto err;
 	}
 
-	dev_opp->prop_name = kstrdup(name, GFP_KERNEL);
-	if (!dev_opp->prop_name) {
+	opp_table->prop_name = kstrdup(name, GFP_KERNEL);
+	if (!opp_table->prop_name) {
 		ret = -ENOMEM;
 		goto err;
 	}
 
-	mutex_unlock(&dev_opp_list_lock);
+	mutex_unlock(&opp_table_lock);
 	return 0;
 
 err:
-	_remove_device_opp(dev_opp);
+	_remove_opp_table(opp_table);
 unlock:
-	mutex_unlock(&dev_opp_list_lock);
+	mutex_unlock(&opp_table_lock);
 
 	return ret;
 }
@@ -1040,13 +1366,13 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_prop_name);
 
 /**
  * dev_pm_opp_put_prop_name() - Releases resources blocked for prop-name
- * @dev: Device for which the regulator has to be set.
+ * @dev: Device for which the prop-name has to be put.
  *
  * This is required only for the V2 bindings, and is called for a matching
- * dev_pm_opp_set_prop_name(). Until this is called, the device_opp structure
+ * dev_pm_opp_set_prop_name(). Until this is called, the opp_table structure
  * will not be freed.
  *
- * Locking: The internal device_opp and opp structures are RCU protected.
+ * Locking: The internal opp_table and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
@@ -1054,45 +1380,154 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_prop_name);
  */
 void dev_pm_opp_put_prop_name(struct device *dev)
 {
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 
-	/* Hold our list modification lock here */
-	mutex_lock(&dev_opp_list_lock);
+	/* Hold our table modification lock here */
+	mutex_lock(&opp_table_lock);
 
-	/* Check for existing list for 'dev' first */
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp)) {
-		dev_err(dev, "Failed to find dev_opp: %ld\n", PTR_ERR(dev_opp));
+	/* Check for existing table for 'dev' first */
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		dev_err(dev, "Failed to find opp_table: %ld\n",
+			PTR_ERR(opp_table));
 		goto unlock;
 	}
 
-	/* Make sure there are no concurrent readers while updating dev_opp */
-	WARN_ON(!list_empty(&dev_opp->opp_list));
+	/* Make sure there are no concurrent readers while updating opp_table */
+	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	if (!dev_opp->prop_name) {
+	if (!opp_table->prop_name) {
 		dev_err(dev, "%s: Doesn't have a prop-name\n", __func__);
 		goto unlock;
 	}
 
-	kfree(dev_opp->prop_name);
-	dev_opp->prop_name = NULL;
+	kfree(opp_table->prop_name);
+	opp_table->prop_name = NULL;
 
-	/* Try freeing device_opp if this was the last blocking resource */
-	_remove_device_opp(dev_opp);
+	/* Try freeing opp_table if this was the last blocking resource */
+	_remove_opp_table(opp_table);
 
 unlock:
-	mutex_unlock(&dev_opp_list_lock);
+	mutex_unlock(&opp_table_lock);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_prop_name);
 
-static bool _opp_is_supported(struct device *dev, struct device_opp *dev_opp,
+/**
+ * dev_pm_opp_set_regulator() - Set regulator name for the device
+ * @dev: Device for which regulator name is being set.
+ * @name: Name of the regulator.
+ *
+ * In order to support OPP switching, OPP layer needs to know the name of the
+ * device's regulator, as the core would be required to switch voltages as well.
+ *
+ * This must be called before any OPPs are initialized for the device.
+ *
+ * Locking: The internal opp_table and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks
+ * to keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex cannot be locked.
+ */
+int dev_pm_opp_set_regulator(struct device *dev, const char *name)
+{
+	struct opp_table *opp_table;
+	struct regulator *reg;
+	int ret;
+
+	mutex_lock(&opp_table_lock);
+
+	opp_table = _add_opp_table(dev);
+	if (!opp_table) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	/* This should be called before OPPs are initialized */
+	if (WARN_ON(!list_empty(&opp_table->opp_list))) {
+		ret = -EBUSY;
+		goto err;
+	}
+
+	/* Already have a regulator set */
+	if (WARN_ON(!IS_ERR(opp_table->regulator))) {
+		ret = -EBUSY;
+		goto err;
+	}
+	/* Allocate the regulator */
+	reg = regulator_get_optional(dev, name);
+	if (IS_ERR(reg)) {
+		ret = PTR_ERR(reg);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "%s: no regulator (%s) found: %d\n",
+				__func__, name, ret);
+		goto err;
+	}
+
+	opp_table->regulator = reg;
+
+	mutex_unlock(&opp_table_lock);
+	return 0;
+
+err:
+	_remove_opp_table(opp_table);
+unlock:
+	mutex_unlock(&opp_table_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulator);
+
+/**
+ * dev_pm_opp_put_regulator() - Releases resources blocked for regulator
+ * @dev: Device for which regulator was set.
+ *
+ * Locking: The internal opp_table and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks
+ * to keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex cannot be locked.
+ */
+void dev_pm_opp_put_regulator(struct device *dev)
+{
+	struct opp_table *opp_table;
+
+	mutex_lock(&opp_table_lock);
+
+	/* Check for existing table for 'dev' first */
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		dev_err(dev, "Failed to find opp_table: %ld\n",
+			PTR_ERR(opp_table));
+		goto unlock;
+	}
+
+	if (IS_ERR(opp_table->regulator)) {
+		dev_err(dev, "%s: Doesn't have regulator set\n", __func__);
+		goto unlock;
+	}
+
+	/* Make sure there are no concurrent readers while updating opp_table */
+	WARN_ON(!list_empty(&opp_table->opp_list));
+
+	regulator_put(opp_table->regulator);
+	opp_table->regulator = ERR_PTR(-ENXIO);
+
+	/* Try freeing opp_table if this was the last blocking resource */
+	_remove_opp_table(opp_table);
+
+unlock:
+	mutex_unlock(&opp_table_lock);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulator);
+
+static bool _opp_is_supported(struct device *dev, struct opp_table *opp_table,
 			      struct device_node *np)
 {
-	unsigned int count = dev_opp->supported_hw_count;
+	unsigned int count = opp_table->supported_hw_count;
 	u32 version;
 	int ret;
 
-	if (!dev_opp->supported_hw)
+	if (!opp_table->supported_hw)
 		return true;
 
 	while (count--) {
@@ -1105,7 +1540,7 @@ static bool _opp_is_supported(struct device *dev, struct device_opp *dev_opp,
 		}
 
 		/* Both of these are bitwise masks of the versions */
-		if (!(version & dev_opp->supported_hw[count]))
+		if (!(version & opp_table->supported_hw[count]))
 			return false;
 	}
 
@@ -1117,11 +1552,11 @@ static bool _opp_is_supported(struct device *dev, struct device_opp *dev_opp,
  * @dev:	device for which we do this operation
  * @np:		device node
  *
- * This function adds an opp definition to the opp list and returns status. The
+ * This function adds an opp definition to the opp table and returns status. The
  * opp can be controlled using dev_pm_opp_enable/disable functions and may be
  * removed by dev_pm_opp_remove.
  *
- * Locking: The internal device_opp and opp structures are RCU protected.
+ * Locking: The internal opp_table and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
@@ -1137,16 +1572,16 @@ static bool _opp_is_supported(struct device *dev, struct device_opp *dev_opp,
  */
 static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 {
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 	struct dev_pm_opp *new_opp;
 	u64 rate;
 	u32 val;
 	int ret;
 
-	/* Hold our list modification lock here */
-	mutex_lock(&dev_opp_list_lock);
+	/* Hold our table modification lock here */
+	mutex_lock(&opp_table_lock);
 
-	new_opp = _allocate_opp(dev, &dev_opp);
+	new_opp = _allocate_opp(dev, &opp_table);
 	if (!new_opp) {
 		ret = -ENOMEM;
 		goto unlock;
@@ -1159,7 +1594,7 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 	}
 
 	/* Check if the OPP supports hardware's hierarchy of versions or not */
-	if (!_opp_is_supported(dev, dev_opp, np)) {
+	if (!_opp_is_supported(dev, opp_table, np)) {
 		dev_dbg(dev, "OPP not supported by hardware: %llu\n", rate);
 		goto free_opp;
 	}
@@ -1179,30 +1614,30 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 	if (!of_property_read_u32(np, "clock-latency-ns", &val))
 		new_opp->clock_latency_ns = val;
 
-	ret = opp_parse_supplies(new_opp, dev, dev_opp);
+	ret = opp_parse_supplies(new_opp, dev, opp_table);
 	if (ret)
 		goto free_opp;
 
-	ret = _opp_add(dev, new_opp, dev_opp);
+	ret = _opp_add(dev, new_opp, opp_table);
 	if (ret)
 		goto free_opp;
 
 	/* OPP to select on device suspend */
 	if (of_property_read_bool(np, "opp-suspend")) {
-		if (dev_opp->suspend_opp) {
+		if (opp_table->suspend_opp) {
 			dev_warn(dev, "%s: Multiple suspend OPPs found (%lu %lu)\n",
-				 __func__, dev_opp->suspend_opp->rate,
+				 __func__, opp_table->suspend_opp->rate,
 				 new_opp->rate);
 		} else {
 			new_opp->suspend = true;
-			dev_opp->suspend_opp = new_opp;
+			opp_table->suspend_opp = new_opp;
 		}
 	}
 
-	if (new_opp->clock_latency_ns > dev_opp->clock_latency_ns_max)
-		dev_opp->clock_latency_ns_max = new_opp->clock_latency_ns;
+	if (new_opp->clock_latency_ns > opp_table->clock_latency_ns_max)
+		opp_table->clock_latency_ns_max = new_opp->clock_latency_ns;
 
-	mutex_unlock(&dev_opp_list_lock);
+	mutex_unlock(&opp_table_lock);
 
 	pr_debug("%s: turbo:%d rate:%lu uv:%lu uvmin:%lu uvmax:%lu latency:%lu\n",
 		 __func__, new_opp->turbo, new_opp->rate, new_opp->u_volt,
@@ -1213,13 +1648,13 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 	 * Notify the changes in the availability of the operable
 	 * frequency/voltage list.
 	 */
-	srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ADD, new_opp);
+	srcu_notifier_call_chain(&opp_table->srcu_head, OPP_EVENT_ADD, new_opp);
 	return 0;
 
 free_opp:
-	_opp_remove(dev_opp, new_opp, false);
+	_opp_remove(opp_table, new_opp, false);
 unlock:
-	mutex_unlock(&dev_opp_list_lock);
+	mutex_unlock(&opp_table_lock);
 	return ret;
 }
 
@@ -1229,11 +1664,11 @@ unlock:
  * @freq:	Frequency in Hz for this OPP
  * @u_volt:	Voltage in uVolts for this OPP
  *
- * This function adds an opp definition to the opp list and returns status.
+ * This function adds an opp definition to the opp table and returns status.
  * The opp is made available by default and it can be controlled using
  * dev_pm_opp_enable/disable functions.
  *
- * Locking: The internal device_opp and opp structures are RCU protected.
+ * Locking: The internal opp_table and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
@@ -1265,7 +1700,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_add);
  * copy operation, returns 0 if no modification was done OR modification was
  * successful.
  *
- * Locking: The internal device_opp and opp structures are RCU protected.
+ * Locking: The internal opp_table and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks to
  * keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
@@ -1274,7 +1709,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_add);
 static int _opp_set_availability(struct device *dev, unsigned long freq,
 				 bool availability_req)
 {
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 	struct dev_pm_opp *new_opp, *tmp_opp, *opp = ERR_PTR(-ENODEV);
 	int r = 0;
 
@@ -1283,18 +1718,18 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 	if (!new_opp)
 		return -ENOMEM;
 
-	mutex_lock(&dev_opp_list_lock);
+	mutex_lock(&opp_table_lock);
 
-	/* Find the device_opp */
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp)) {
-		r = PTR_ERR(dev_opp);
+	/* Find the opp_table */
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		r = PTR_ERR(opp_table);
 		dev_warn(dev, "%s: Device OPP not found (%d)\n", __func__, r);
 		goto unlock;
 	}
 
 	/* Do we have the frequency? */
-	list_for_each_entry(tmp_opp, &dev_opp->opp_list, node) {
+	list_for_each_entry(tmp_opp, &opp_table->opp_list, node) {
 		if (tmp_opp->rate == freq) {
 			opp = tmp_opp;
 			break;
@@ -1315,21 +1750,21 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 	new_opp->available = availability_req;
 
 	list_replace_rcu(&opp->node, &new_opp->node);
-	mutex_unlock(&dev_opp_list_lock);
-	call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
+	mutex_unlock(&opp_table_lock);
+	call_srcu(&opp_table->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
 
 	/* Notify the change of the OPP availability */
 	if (availability_req)
-		srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ENABLE,
-					 new_opp);
+		srcu_notifier_call_chain(&opp_table->srcu_head,
+					 OPP_EVENT_ENABLE, new_opp);
 	else
-		srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_DISABLE,
-					 new_opp);
+		srcu_notifier_call_chain(&opp_table->srcu_head,
+					 OPP_EVENT_DISABLE, new_opp);
 
 	return 0;
 
 unlock:
-	mutex_unlock(&dev_opp_list_lock);
+	mutex_unlock(&opp_table_lock);
 	kfree(new_opp);
 	return r;
 }
@@ -1343,7 +1778,7 @@ unlock:
  * corresponding error value. It is meant to be used for users an OPP available
  * after being temporarily made unavailable with dev_pm_opp_disable.
  *
- * Locking: The internal device_opp and opp structures are RCU protected.
+ * Locking: The internal opp_table and opp structures are RCU protected.
  * Hence this function indirectly uses RCU and mutex locks to keep the
  * integrity of the internal data structures. Callers should ensure that
  * this function is *NOT* called under RCU protection or in contexts where
@@ -1369,7 +1804,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_enable);
  * control by users to make this OPP not available until the circumstances are
  * right to make it available again (with a call to dev_pm_opp_enable).
  *
- * Locking: The internal device_opp and opp structures are RCU protected.
+ * Locking: The internal opp_table and opp structures are RCU protected.
  * Hence this function indirectly uses RCU and mutex locks to keep the
  * integrity of the internal data structures. Callers should ensure that
  * this function is *NOT* called under RCU protection or in contexts where
@@ -1387,26 +1822,26 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_disable);
 
 /**
  * dev_pm_opp_get_notifier() - find notifier_head of the device with opp
- * @dev:	device pointer used to lookup device OPPs.
+ * @dev:	device pointer used to lookup OPP table.
  *
  * Return: pointer to  notifier head if found, otherwise -ENODEV or
  * -EINVAL based on type of error casted as pointer. value must be checked
  *  with IS_ERR to determine valid pointer or error result.
  *
- * Locking: This function must be called under rcu_read_lock(). dev_opp is a RCU
- * protected pointer. The reason for the same is that the opp pointer which is
- * returned will remain valid for use with opp_get_{voltage, freq} only while
+ * Locking: This function must be called under rcu_read_lock(). opp_table is a
+ * RCU protected pointer. The reason for the same is that the opp pointer which
+ * is returned will remain valid for use with opp_get_{voltage, freq} only while
  * under the locked area. The pointer returned must be used prior to unlocking
  * with rcu_read_unlock() to maintain the integrity of the pointer.
  */
 struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev)
 {
-	struct device_opp *dev_opp = _find_device_opp(dev);
+	struct opp_table *opp_table = _find_opp_table(dev);
 
-	if (IS_ERR(dev_opp))
-		return ERR_CAST(dev_opp); /* matching type */
+	if (IS_ERR(opp_table))
+		return ERR_CAST(opp_table); /* matching type */
 
-	return &dev_opp->srcu_head;
+	return &opp_table->srcu_head;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier);
 
@@ -1414,11 +1849,11 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier);
 /**
  * dev_pm_opp_of_remove_table() - Free OPP table entries created from static DT
  *				  entries
- * @dev:	device pointer used to lookup device OPPs.
+ * @dev:	device pointer used to lookup OPP table.
  *
  * Free OPPs created using static entries present in DT.
  *
- * Locking: The internal device_opp and opp structures are RCU protected.
+ * Locking: The internal opp_table and opp structures are RCU protected.
  * Hence this function indirectly uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
@@ -1426,38 +1861,38 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier);
  */
 void dev_pm_opp_of_remove_table(struct device *dev)
 {
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 	struct dev_pm_opp *opp, *tmp;
 
-	/* Hold our list modification lock here */
-	mutex_lock(&dev_opp_list_lock);
+	/* Hold our table modification lock here */
+	mutex_lock(&opp_table_lock);
 
-	/* Check for existing list for 'dev' */
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp)) {
-		int error = PTR_ERR(dev_opp);
+	/* Check for existing table for 'dev' */
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		int error = PTR_ERR(opp_table);
 
 		if (error != -ENODEV)
-			WARN(1, "%s: dev_opp: %d\n",
+			WARN(1, "%s: opp_table: %d\n",
 			     IS_ERR_OR_NULL(dev) ?
 					"Invalid device" : dev_name(dev),
 			     error);
 		goto unlock;
 	}
 
-	/* Find if dev_opp manages a single device */
-	if (list_is_singular(&dev_opp->dev_list)) {
+	/* Find if opp_table manages a single device */
+	if (list_is_singular(&opp_table->dev_list)) {
 		/* Free static OPPs */
-		list_for_each_entry_safe(opp, tmp, &dev_opp->opp_list, node) {
+		list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) {
 			if (!opp->dynamic)
-				_opp_remove(dev_opp, opp, true);
+				_opp_remove(opp_table, opp, true);
 		}
 	} else {
-		_remove_list_dev(_find_list_dev(dev, dev_opp), dev_opp);
+		_remove_opp_dev(_find_opp_dev(dev, opp_table), opp_table);
 	}
 
 unlock:
-	mutex_unlock(&dev_opp_list_lock);
+	mutex_unlock(&opp_table_lock);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table);
 
@@ -1478,22 +1913,22 @@ struct device_node *_of_get_opp_desc_node(struct device *dev)
 static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 {
 	struct device_node *np;
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 	int ret = 0, count = 0;
 
-	mutex_lock(&dev_opp_list_lock);
+	mutex_lock(&opp_table_lock);
 
-	dev_opp = _managed_opp(opp_np);
-	if (dev_opp) {
+	opp_table = _managed_opp(opp_np);
+	if (opp_table) {
 		/* OPPs are already managed */
-		if (!_add_list_dev(dev, dev_opp))
+		if (!_add_opp_dev(dev, opp_table))
 			ret = -ENOMEM;
-		mutex_unlock(&dev_opp_list_lock);
+		mutex_unlock(&opp_table_lock);
 		return ret;
 	}
-	mutex_unlock(&dev_opp_list_lock);
+	mutex_unlock(&opp_table_lock);
 
-	/* We have opp-list node now, iterate over it and add OPPs */
+	/* We have opp-table node now, iterate over it and add OPPs */
 	for_each_available_child_of_node(opp_np, np) {
 		count++;
 
@@ -1509,19 +1944,19 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 	if (WARN_ON(!count))
 		return -ENOENT;
 
-	mutex_lock(&dev_opp_list_lock);
+	mutex_lock(&opp_table_lock);
 
-	dev_opp = _find_device_opp(dev);
-	if (WARN_ON(IS_ERR(dev_opp))) {
-		ret = PTR_ERR(dev_opp);
-		mutex_unlock(&dev_opp_list_lock);
+	opp_table = _find_opp_table(dev);
+	if (WARN_ON(IS_ERR(opp_table))) {
+		ret = PTR_ERR(opp_table);
+		mutex_unlock(&opp_table_lock);
 		goto free_table;
 	}
 
-	dev_opp->np = opp_np;
-	dev_opp->shared_opp = of_property_read_bool(opp_np, "opp-shared");
+	opp_table->np = opp_np;
+	opp_table->shared_opp = of_property_read_bool(opp_np, "opp-shared");
 
-	mutex_unlock(&dev_opp_list_lock);
+	mutex_unlock(&opp_table_lock);
 
 	return 0;
 
@@ -1550,7 +1985,7 @@ static int _of_add_opp_table_v1(struct device *dev)
 	 */
 	nr = prop->length / sizeof(u32);
 	if (nr % 2) {
-		dev_err(dev, "%s: Invalid OPP list\n", __func__);
+		dev_err(dev, "%s: Invalid OPP table\n", __func__);
 		return -EINVAL;
 	}
 
@@ -1570,11 +2005,11 @@ static int _of_add_opp_table_v1(struct device *dev)
 
 /**
  * dev_pm_opp_of_add_table() - Initialize opp table from device tree
- * @dev:	device pointer used to lookup device OPPs.
+ * @dev:	device pointer used to lookup OPP table.
  *
  * Register the initial OPP table with the OPP library for given device.
  *
- * Locking: The internal device_opp and opp structures are RCU protected.
+ * Locking: The internal opp_table and opp structures are RCU protected.
  * Hence this function indirectly uses RCU updater strategy with mutex locks
  * to keep the integrity of the internal data structures. Callers should ensure
  * that this function is *NOT* called under RCU protection or in contexts where
diff --git a/drivers/base/power/opp/cpu.c b/drivers/base/power/opp/cpu.c
index 9f0c15570f64..ba2bdbd932ef 100644
--- a/drivers/base/power/opp/cpu.c
+++ b/drivers/base/power/opp/cpu.c
@@ -31,7 +31,7 @@
  * @table:	Cpufreq table returned back to caller
  *
  * Generate a cpufreq table for a provided device- this assumes that the
- * opp list is already initialized and ready for usage.
+ * opp table is already initialized and ready for usage.
  *
  * This function allocates required memory for the cpufreq table. It is
  * expected that the caller does the required maintenance such as freeing
@@ -44,7 +44,7 @@
  * WARNING: It is  important for the callers to ensure refreshing their copy of
  * the table if any of the mentioned functions have been invoked in the interim.
  *
- * Locking: The internal device_opp and opp structures are RCU protected.
+ * Locking: The internal opp_table and opp structures are RCU protected.
  * Since we just use the regular accessor functions to access the internal data
  * structures, we use RCU read lock inside this function. As a result, users of
  * this function DONOT need to use explicit locks for invoking.
@@ -122,15 +122,15 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_free_cpufreq_table);
 /* Required only for V1 bindings, as v2 can manage it from DT itself */
 int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask)
 {
-	struct device_list_opp *list_dev;
-	struct device_opp *dev_opp;
+	struct opp_device *opp_dev;
+	struct opp_table *opp_table;
 	struct device *dev;
 	int cpu, ret = 0;
 
-	mutex_lock(&dev_opp_list_lock);
+	mutex_lock(&opp_table_lock);
 
-	dev_opp = _find_device_opp(cpu_dev);
-	if (IS_ERR(dev_opp)) {
+	opp_table = _find_opp_table(cpu_dev);
+	if (IS_ERR(opp_table)) {
 		ret = -EINVAL;
 		goto unlock;
 	}
@@ -146,15 +146,15 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, cpumask_var_t cpumask)
 			continue;
 		}
 
-		list_dev = _add_list_dev(dev, dev_opp);
-		if (!list_dev) {
-			dev_err(dev, "%s: failed to add list-dev for cpu%d device\n",
+		opp_dev = _add_opp_dev(dev, opp_table);
+		if (!opp_dev) {
+			dev_err(dev, "%s: failed to add opp-dev for cpu%d device\n",
 				__func__, cpu);
 			continue;
 		}
 	}
 unlock:
-	mutex_unlock(&dev_opp_list_lock);
+	mutex_unlock(&opp_table_lock);
 
 	return ret;
 }
diff --git a/drivers/base/power/opp/debugfs.c b/drivers/base/power/opp/debugfs.c
index ddfe4773e922..ef1ae6b52042 100644
--- a/drivers/base/power/opp/debugfs.c
+++ b/drivers/base/power/opp/debugfs.c
@@ -34,9 +34,9 @@ void opp_debug_remove_one(struct dev_pm_opp *opp)
 	debugfs_remove_recursive(opp->dentry);
 }
 
-int opp_debug_create_one(struct dev_pm_opp *opp, struct device_opp *dev_opp)
+int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table)
 {
-	struct dentry *pdentry = dev_opp->dentry;
+	struct dentry *pdentry = opp_table->dentry;
 	struct dentry *d;
 	char name[25];	/* 20 chars for 64 bit value + 5 (opp:\0) */
 
@@ -83,52 +83,52 @@ int opp_debug_create_one(struct dev_pm_opp *opp, struct device_opp *dev_opp)
 	return 0;
 }
 
-static int device_opp_debug_create_dir(struct device_list_opp *list_dev,
-				       struct device_opp *dev_opp)
+static int opp_list_debug_create_dir(struct opp_device *opp_dev,
+				     struct opp_table *opp_table)
 {
-	const struct device *dev = list_dev->dev;
+	const struct device *dev = opp_dev->dev;
 	struct dentry *d;
 
-	opp_set_dev_name(dev, dev_opp->dentry_name);
+	opp_set_dev_name(dev, opp_table->dentry_name);
 
 	/* Create device specific directory */
-	d = debugfs_create_dir(dev_opp->dentry_name, rootdir);
+	d = debugfs_create_dir(opp_table->dentry_name, rootdir);
 	if (!d) {
 		dev_err(dev, "%s: Failed to create debugfs dir\n", __func__);
 		return -ENOMEM;
 	}
 
-	list_dev->dentry = d;
-	dev_opp->dentry = d;
+	opp_dev->dentry = d;
+	opp_table->dentry = d;
 
 	return 0;
 }
 
-static int device_opp_debug_create_link(struct device_list_opp *list_dev,
-					struct device_opp *dev_opp)
+static int opp_list_debug_create_link(struct opp_device *opp_dev,
+				      struct opp_table *opp_table)
 {
-	const struct device *dev = list_dev->dev;
+	const struct device *dev = opp_dev->dev;
 	char name[NAME_MAX];
 	struct dentry *d;
 
-	opp_set_dev_name(list_dev->dev, name);
+	opp_set_dev_name(opp_dev->dev, name);
 
 	/* Create device specific directory link */
-	d = debugfs_create_symlink(name, rootdir, dev_opp->dentry_name);
+	d = debugfs_create_symlink(name, rootdir, opp_table->dentry_name);
 	if (!d) {
 		dev_err(dev, "%s: Failed to create link\n", __func__);
 		return -ENOMEM;
 	}
 
-	list_dev->dentry = d;
+	opp_dev->dentry = d;
 
 	return 0;
 }
 
 /**
  * opp_debug_register - add a device opp node to the debugfs 'opp' directory
- * @list_dev: list-dev pointer for device
- * @dev_opp: the device-opp being added
+ * @opp_dev: opp-dev pointer for device
+ * @opp_table: the device-opp being added
  *
  * Dynamically adds device specific directory in debugfs 'opp' directory. If the
  * device-opp is shared with other devices, then links will be created for all
@@ -136,73 +136,72 @@ static int device_opp_debug_create_link(struct device_list_opp *list_dev,
  *
  * Return: 0 on success, otherwise negative error.
  */
-int opp_debug_register(struct device_list_opp *list_dev,
-		       struct device_opp *dev_opp)
+int opp_debug_register(struct opp_device *opp_dev, struct opp_table *opp_table)
 {
 	if (!rootdir) {
 		pr_debug("%s: Uninitialized rootdir\n", __func__);
 		return -EINVAL;
 	}
 
-	if (dev_opp->dentry)
-		return device_opp_debug_create_link(list_dev, dev_opp);
+	if (opp_table->dentry)
+		return opp_list_debug_create_link(opp_dev, opp_table);
 
-	return device_opp_debug_create_dir(list_dev, dev_opp);
+	return opp_list_debug_create_dir(opp_dev, opp_table);
 }
 
-static void opp_migrate_dentry(struct device_list_opp *list_dev,
-			       struct device_opp *dev_opp)
+static void opp_migrate_dentry(struct opp_device *opp_dev,
+			       struct opp_table *opp_table)
 {
-	struct device_list_opp *new_dev;
+	struct opp_device *new_dev;
 	const struct device *dev;
 	struct dentry *dentry;
 
-	/* Look for next list-dev */
-	list_for_each_entry(new_dev, &dev_opp->dev_list, node)
-		if (new_dev != list_dev)
+	/* Look for next opp-dev */
+	list_for_each_entry(new_dev, &opp_table->dev_list, node)
+		if (new_dev != opp_dev)
 			break;
 
 	/* new_dev is guaranteed to be valid here */
 	dev = new_dev->dev;
 	debugfs_remove_recursive(new_dev->dentry);
 
-	opp_set_dev_name(dev, dev_opp->dentry_name);
+	opp_set_dev_name(dev, opp_table->dentry_name);
 
-	dentry = debugfs_rename(rootdir, list_dev->dentry, rootdir,
-				dev_opp->dentry_name);
+	dentry = debugfs_rename(rootdir, opp_dev->dentry, rootdir,
+				opp_table->dentry_name);
 	if (!dentry) {
 		dev_err(dev, "%s: Failed to rename link from: %s to %s\n",
-			__func__, dev_name(list_dev->dev), dev_name(dev));
+			__func__, dev_name(opp_dev->dev), dev_name(dev));
 		return;
 	}
 
 	new_dev->dentry = dentry;
-	dev_opp->dentry = dentry;
+	opp_table->dentry = dentry;
 }
 
 /**
  * opp_debug_unregister - remove a device opp node from debugfs opp directory
- * @list_dev: list-dev pointer for device
- * @dev_opp: the device-opp being removed
+ * @opp_dev: opp-dev pointer for device
+ * @opp_table: the device-opp being removed
  *
  * Dynamically removes device specific directory from debugfs 'opp' directory.
  */
-void opp_debug_unregister(struct device_list_opp *list_dev,
-			  struct device_opp *dev_opp)
+void opp_debug_unregister(struct opp_device *opp_dev,
+			  struct opp_table *opp_table)
 {
-	if (list_dev->dentry == dev_opp->dentry) {
+	if (opp_dev->dentry == opp_table->dentry) {
 		/* Move the real dentry object under another device */
-		if (!list_is_singular(&dev_opp->dev_list)) {
-			opp_migrate_dentry(list_dev, dev_opp);
+		if (!list_is_singular(&opp_table->dev_list)) {
+			opp_migrate_dentry(opp_dev, opp_table);
 			goto out;
 		}
-		dev_opp->dentry = NULL;
+		opp_table->dentry = NULL;
 	}
 
-	debugfs_remove_recursive(list_dev->dentry);
+	debugfs_remove_recursive(opp_dev->dentry);
 
 out:
-	list_dev->dentry = NULL;
+	opp_dev->dentry = NULL;
 }
 
 static int __init opp_debug_init(void)
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index 690638ef36ee..f67f806fcf3a 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -22,13 +22,16 @@
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
 
+struct clk;
+struct regulator;
+
 /* Lock to allow exclusive modification to the device and opp lists */
-extern struct mutex dev_opp_list_lock;
+extern struct mutex opp_table_lock;
 
 /*
  * Internal data structure organization with the OPP layer library is as
  * follows:
- * dev_opp_list (root)
+ * opp_tables (root)
  *	|- device 1 (represents voltage domain 1)
  *	|	|- opp 1 (availability, freq, voltage)
  *	|	|- opp 2 ..
@@ -37,18 +40,18 @@ extern struct mutex dev_opp_list_lock;
  *	|- device 2 (represents the next voltage domain)
  *	...
  *	`- device m (represents mth voltage domain)
- * device 1, 2.. are represented by dev_opp structure while each opp
+ * device 1, 2.. are represented by opp_table structure while each opp
  * is represented by the opp structure.
  */
 
 /**
  * struct dev_pm_opp - Generic OPP description structure
- * @node:	opp list node. The nodes are maintained throughout the lifetime
+ * @node:	opp table node. The nodes are maintained throughout the lifetime
  *		of boot. It is expected only an optimal set of OPPs are
  *		added to the library by the SoC framework.
- *		RCU usage: opp list is traversed with RCU locks. node
+ *		RCU usage: opp table is traversed with RCU locks. node
  *		modification is possible realtime, hence the modifications
- *		are protected by the dev_opp_list_lock for integrity.
+ *		are protected by the opp_table_lock for integrity.
  *		IMPORTANT: the opp nodes should be maintained in increasing
  *		order.
  * @available:	true/false - marks if this OPP as available or not
@@ -62,7 +65,7 @@ extern struct mutex dev_opp_list_lock;
  * @u_amp:	Maximum current drawn by the device in microamperes
  * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's
  *		frequency from any other OPP's frequency.
- * @dev_opp:	points back to the device_opp struct this opp belongs to
+ * @opp_table:	points back to the opp_table struct this opp belongs to
  * @rcu_head:	RCU callback head used for deferred freeing
  * @np:		OPP's device node.
  * @dentry:	debugfs dentry pointer (per opp)
@@ -84,7 +87,7 @@ struct dev_pm_opp {
 	unsigned long u_amp;
 	unsigned long clock_latency_ns;
 
-	struct device_opp *dev_opp;
+	struct opp_table *opp_table;
 	struct rcu_head rcu_head;
 
 	struct device_node *np;
@@ -95,16 +98,16 @@ struct dev_pm_opp {
 };
 
 /**
- * struct device_list_opp - devices managed by 'struct device_opp'
+ * struct opp_device - devices managed by 'struct opp_table'
  * @node:	list node
  * @dev:	device to which the struct object belongs
  * @rcu_head:	RCU callback head used for deferred freeing
  * @dentry:	debugfs dentry pointer (per device)
  *
- * This is an internal data structure maintaining the list of devices that are
- * managed by 'struct device_opp'.
+ * This is an internal data structure maintaining the devices that are managed
+ * by 'struct opp_table'.
  */
-struct device_list_opp {
+struct opp_device {
 	struct list_head node;
 	const struct device *dev;
 	struct rcu_head rcu_head;
@@ -115,16 +118,16 @@ struct device_list_opp {
 };
 
 /**
- * struct device_opp - Device opp structure
- * @node:	list node - contains the devices with OPPs that
+ * struct opp_table - Device opp structure
+ * @node:	table node - contains the devices with OPPs that
  *		have been registered. Nodes once added are not modified in this
- *		list.
- *		RCU usage: nodes are not modified in the list of device_opp,
- *		however addition is possible and is secured by dev_opp_list_lock
+ *		table.
+ *		RCU usage: nodes are not modified in the table of opp_table,
+ *		however addition is possible and is secured by opp_table_lock
  * @srcu_head:	notifier head to notify the OPP availability changes.
  * @rcu_head:	RCU callback head used for deferred freeing
  * @dev_list:	list of devices that share these OPPs
- * @opp_list:	list of opps
+ * @opp_list:	table of opps
  * @np:		struct device_node pointer for opp's DT node.
  * @clock_latency_ns_max: Max clock latency in nanoseconds.
  * @shared_opp: OPP is shared between multiple devices.
@@ -132,9 +135,13 @@ struct device_list_opp {
  * @supported_hw: Array of version number to support.
  * @supported_hw_count: Number of elements in supported_hw array.
  * @prop_name: A name to postfix to many DT properties, while parsing them.
+ * @clk: Device's clock handle
+ * @regulator: Supply regulator
  * @dentry:	debugfs dentry pointer of the real device directory (not links).
  * @dentry_name: Name of the real dentry.
  *
+ * @voltage_tolerance_v1: In percentage, for v1 bindings only.
+ *
  * This is an internal data structure maintaining the link to opps attached to
  * a device. This structure is not meant to be shared to users as it is
  * meant for book keeping and private to OPP library.
@@ -143,7 +150,7 @@ struct device_list_opp {
  * need to wait for the grace period of both of them before freeing any
  * resources. And so we have used kfree_rcu() from within call_srcu() handlers.
  */
-struct device_opp {
+struct opp_table {
 	struct list_head node;
 
 	struct srcu_notifier_head srcu_head;
@@ -153,12 +160,18 @@ struct device_opp {
 
 	struct device_node *np;
 	unsigned long clock_latency_ns_max;
+
+	/* For backward compatibility with v1 bindings */
+	unsigned int voltage_tolerance_v1;
+
 	bool shared_opp;
 	struct dev_pm_opp *suspend_opp;
 
 	unsigned int *supported_hw;
 	unsigned int supported_hw_count;
 	const char *prop_name;
+	struct clk *clk;
+	struct regulator *regulator;
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dentry;
@@ -167,30 +180,27 @@ struct device_opp {
 };
 
 /* Routines internal to opp core */
-struct device_opp *_find_device_opp(struct device *dev);
-struct device_list_opp *_add_list_dev(const struct device *dev,
-				      struct device_opp *dev_opp);
+struct opp_table *_find_opp_table(struct device *dev);
+struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table);
 struct device_node *_of_get_opp_desc_node(struct device *dev);
 
 #ifdef CONFIG_DEBUG_FS
 void opp_debug_remove_one(struct dev_pm_opp *opp);
-int opp_debug_create_one(struct dev_pm_opp *opp, struct device_opp *dev_opp);
-int opp_debug_register(struct device_list_opp *list_dev,
-		       struct device_opp *dev_opp);
-void opp_debug_unregister(struct device_list_opp *list_dev,
-			  struct device_opp *dev_opp);
+int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table);
+int opp_debug_register(struct opp_device *opp_dev, struct opp_table *opp_table);
+void opp_debug_unregister(struct opp_device *opp_dev, struct opp_table *opp_table);
 #else
 static inline void opp_debug_remove_one(struct dev_pm_opp *opp) {}
 
 static inline int opp_debug_create_one(struct dev_pm_opp *opp,
-				       struct device_opp *dev_opp)
+				       struct opp_table *opp_table)
 { return 0; }
-static inline int opp_debug_register(struct device_list_opp *list_dev,
-				     struct device_opp *dev_opp)
+static inline int opp_debug_register(struct opp_device *opp_dev,
+				     struct opp_table *opp_table)
 { return 0; }
 
-static inline void opp_debug_unregister(struct device_list_opp *list_dev,
-					struct device_opp *dev_opp)
+static inline void opp_debug_unregister(struct opp_device *opp_dev,
+					struct opp_table *opp_table)
 { }
 #endif		/* DEBUG_FS */
 
diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c
index a311cfa4c5bd..a6975795e7f3 100644
--- a/drivers/base/power/trace.c
+++ b/drivers/base/power/trace.c
@@ -166,14 +166,14 @@ void generate_pm_trace(const void *tracedata, unsigned int user)
 }
 EXPORT_SYMBOL(generate_pm_trace);
 
-extern char __tracedata_start, __tracedata_end;
+extern char __tracedata_start[], __tracedata_end[];
 static int show_file_hash(unsigned int value)
 {
 	int match;
 	char *tracedata;
 
 	match = 0;
-	for (tracedata = &__tracedata_start ; tracedata < &__tracedata_end ;
+	for (tracedata = __tracedata_start ; tracedata < __tracedata_end ;
 			tracedata += 2 + sizeof(unsigned long)) {
 		unsigned short lineno = *(unsigned short *)tracedata;
 		const char *file = *(const char **)(tracedata + 2);
diff --git a/drivers/base/property.c b/drivers/base/property.c
index c359351d50f1..76628a7b45f1 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -218,7 +218,8 @@ bool fwnode_property_present(struct fwnode_handle *fwnode, const char *propname)
 	bool ret;
 
 	ret = __fwnode_property_present(fwnode, propname);
-	if (ret == false && fwnode && fwnode->secondary)
+	if (ret == false && !IS_ERR_OR_NULL(fwnode) &&
+	    !IS_ERR_OR_NULL(fwnode->secondary))
 		ret = __fwnode_property_present(fwnode->secondary, propname);
 	return ret;
 }
@@ -423,7 +424,8 @@ EXPORT_SYMBOL_GPL(device_property_match_string);
 	int _ret_;									\
 	_ret_ = FWNODE_PROP_READ(_fwnode_, _propname_, _type_, _proptype_,		\
 				 _val_, _nval_);					\
-	if (_ret_ == -EINVAL && _fwnode_ && _fwnode_->secondary)			\
+	if (_ret_ == -EINVAL && !IS_ERR_OR_NULL(_fwnode_) &&				\
+	    !IS_ERR_OR_NULL(_fwnode_->secondary))					\
 		_ret_ = FWNODE_PROP_READ(_fwnode_->secondary, _propname_, _type_,	\
 				_proptype_, _val_, _nval_);				\
 	_ret_;										\
@@ -593,7 +595,8 @@ int fwnode_property_read_string_array(struct fwnode_handle *fwnode,
 	int ret;
 
 	ret = __fwnode_property_read_string_array(fwnode, propname, val, nval);
-	if (ret == -EINVAL && fwnode && fwnode->secondary)
+	if (ret == -EINVAL && !IS_ERR_OR_NULL(fwnode) &&
+	    !IS_ERR_OR_NULL(fwnode->secondary))
 		ret = __fwnode_property_read_string_array(fwnode->secondary,
 							  propname, val, nval);
 	return ret;
@@ -621,7 +624,8 @@ int fwnode_property_read_string(struct fwnode_handle *fwnode,
 	int ret;
 
 	ret = __fwnode_property_read_string(fwnode, propname, val);
-	if (ret == -EINVAL && fwnode && fwnode->secondary)
+	if (ret == -EINVAL && !IS_ERR_OR_NULL(fwnode) &&
+	    !IS_ERR_OR_NULL(fwnode->secondary))
 		ret = __fwnode_property_read_string(fwnode->secondary,
 						    propname, val);
 	return ret;
@@ -820,11 +824,16 @@ void device_remove_property_set(struct device *dev)
 	 * the pset. If there is no real firmware node (ACPI/DT) primary
 	 * will hold the pset.
 	 */
-	if (!is_pset_node(fwnode))
-		fwnode = fwnode->secondary;
-	if (!IS_ERR(fwnode) && is_pset_node(fwnode))
+	if (is_pset_node(fwnode)) {
+		set_primary_fwnode(dev, NULL);
 		pset_free_set(to_pset_node(fwnode));
-	set_secondary_fwnode(dev, NULL);
+	} else {
+		fwnode = fwnode->secondary;
+		if (!IS_ERR(fwnode) && is_pset_node(fwnode)) {
+			set_secondary_fwnode(dev, NULL);
+			pset_free_set(to_pset_node(fwnode));
+		}
+	}
 }
 EXPORT_SYMBOL_GPL(device_remove_property_set);
 
diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index 3df977054781..5c79526245c2 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -110,6 +110,7 @@ struct regmap {
 	/* number of bits to (left) shift the reg value when formatting*/
 	int reg_shift;
 	int reg_stride;
+	int reg_stride_order;
 
 	/* regcache specific members */
 	const struct regcache_ops *cache_ops;
@@ -263,4 +264,19 @@ static inline const char *regmap_name(const struct regmap *map)
 	return map->name;
 }
 
+static inline unsigned int regmap_get_offset(const struct regmap *map,
+					     unsigned int index)
+{
+	if (map->reg_stride_order >= 0)
+		return index << map->reg_stride_order;
+	else
+		return index * map->reg_stride;
+}
+
+static inline unsigned int regcache_get_index_by_order(const struct regmap *map,
+						       unsigned int reg)
+{
+	return reg >> map->reg_stride_order;
+}
+
 #endif
diff --git a/drivers/base/regmap/regcache-flat.c b/drivers/base/regmap/regcache-flat.c
index 686c9e0b930e..3ee72550b1e3 100644
--- a/drivers/base/regmap/regcache-flat.c
+++ b/drivers/base/regmap/regcache-flat.c
@@ -16,20 +16,30 @@
 
 #include "internal.h"
 
+static inline unsigned int regcache_flat_get_index(const struct regmap *map,
+						   unsigned int reg)
+{
+	return regcache_get_index_by_order(map, reg);
+}
+
 static int regcache_flat_init(struct regmap *map)
 {
 	int i;
 	unsigned int *cache;
 
-	map->cache = kcalloc(map->max_register + 1, sizeof(unsigned int),
-			     GFP_KERNEL);
+	if (!map || map->reg_stride_order < 0)
+		return -EINVAL;
+
+	map->cache = kcalloc(regcache_flat_get_index(map, map->max_register)
+			     + 1, sizeof(unsigned int), GFP_KERNEL);
 	if (!map->cache)
 		return -ENOMEM;
 
 	cache = map->cache;
 
 	for (i = 0; i < map->num_reg_defaults; i++)
-		cache[map->reg_defaults[i].reg] = map->reg_defaults[i].def;
+		cache[regcache_flat_get_index(map, map->reg_defaults[i].reg)] =
+				map->reg_defaults[i].def;
 
 	return 0;
 }
@@ -47,7 +57,7 @@ static int regcache_flat_read(struct regmap *map,
 {
 	unsigned int *cache = map->cache;
 
-	*value = cache[reg];
+	*value = cache[regcache_flat_get_index(map, reg)];
 
 	return 0;
 }
@@ -57,7 +67,7 @@ static int regcache_flat_write(struct regmap *map, unsigned int reg,
 {
 	unsigned int *cache = map->cache;
 
-	cache[reg] = value;
+	cache[regcache_flat_get_index(map, reg)] = value;
 
 	return 0;
 }
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index 348be3a35410..4170b7d95276 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -30,7 +30,7 @@ static int regcache_hw_init(struct regmap *map)
 	int i, j;
 	int ret;
 	int count;
-	unsigned int val;
+	unsigned int reg, val;
 	void *tmp_buf;
 
 	if (!map->num_reg_defaults_raw)
@@ -57,7 +57,7 @@ static int regcache_hw_init(struct regmap *map)
 		bool cache_bypass = map->cache_bypass;
 		dev_warn(map->dev, "No cache defaults, reading back from HW\n");
 
-		/* Bypass the cache access till data read from HW*/
+		/* Bypass the cache access till data read from HW */
 		map->cache_bypass = true;
 		tmp_buf = kmalloc(map->cache_size_raw, GFP_KERNEL);
 		if (!tmp_buf) {
@@ -65,29 +65,48 @@ static int regcache_hw_init(struct regmap *map)
 			goto err_free;
 		}
 		ret = regmap_raw_read(map, 0, tmp_buf,
-				      map->num_reg_defaults_raw);
+				      map->cache_size_raw);
 		map->cache_bypass = cache_bypass;
-		if (ret < 0)
-			goto err_cache_free;
-
-		map->reg_defaults_raw = tmp_buf;
-		map->cache_free = 1;
+		if (ret == 0) {
+			map->reg_defaults_raw = tmp_buf;
+			map->cache_free = 1;
+		} else {
+			kfree(tmp_buf);
+		}
 	}
 
 	/* fill the reg_defaults */
 	for (i = 0, j = 0; i < map->num_reg_defaults_raw; i++) {
-		if (regmap_volatile(map, i * map->reg_stride))
+		reg = i * map->reg_stride;
+
+		if (!regmap_readable(map, reg))
 			continue;
-		val = regcache_get_val(map, map->reg_defaults_raw, i);
-		map->reg_defaults[j].reg = i * map->reg_stride;
+
+		if (regmap_volatile(map, reg))
+			continue;
+
+		if (map->reg_defaults_raw) {
+			val = regcache_get_val(map, map->reg_defaults_raw, i);
+		} else {
+			bool cache_bypass = map->cache_bypass;
+
+			map->cache_bypass = true;
+			ret = regmap_read(map, reg, &val);
+			map->cache_bypass = cache_bypass;
+			if (ret != 0) {
+				dev_err(map->dev, "Failed to read %d: %d\n",
+					reg, ret);
+				goto err_free;
+			}
+		}
+
+		map->reg_defaults[j].reg = reg;
 		map->reg_defaults[j].def = val;
 		j++;
 	}
 
 	return 0;
 
-err_cache_free:
-	kfree(tmp_buf);
 err_free:
 	kfree(map->reg_defaults);
 
diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c
index 9b0d202414d0..26f799e71c82 100644
--- a/drivers/base/regmap/regmap-irq.c
+++ b/drivers/base/regmap/regmap-irq.c
@@ -379,6 +379,7 @@ static int regmap_irq_map(struct irq_domain *h, unsigned int virq,
 	irq_set_chip_data(virq, data);
 	irq_set_chip(virq, &data->irq_chip);
 	irq_set_nested_thread(virq, 1);
+	irq_set_parent(virq, data->irq);
 	irq_set_noprobe(virq);
 
 	return 0;
@@ -655,13 +656,34 @@ EXPORT_SYMBOL_GPL(regmap_add_irq_chip);
  *
  * @irq: Primary IRQ for the device
  * @d:   regmap_irq_chip_data allocated by regmap_add_irq_chip()
+ *
+ * This function also dispose all mapped irq on chip.
  */
 void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *d)
 {
+	unsigned int virq;
+	int hwirq;
+
 	if (!d)
 		return;
 
 	free_irq(irq, d);
+
+	/* Dispose all virtual irq from irq domain before removing it */
+	for (hwirq = 0; hwirq < d->chip->num_irqs; hwirq++) {
+		/* Ignore hwirq if holes in the IRQ list */
+		if (!d->chip->irqs[hwirq].mask)
+			continue;
+
+		/*
+		 * Find the virtual irq of hwirq on chip and if it is
+		 * there then dispose it
+		 */
+		virq = irq_find_mapping(d->domain, hwirq);
+		if (virq)
+			irq_dispose_mapping(virq);
+	}
+
 	irq_domain_remove(d->domain);
 	kfree(d->type_buf);
 	kfree(d->type_buf_def);
@@ -674,6 +696,88 @@ void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *d)
 }
 EXPORT_SYMBOL_GPL(regmap_del_irq_chip);
 
+static void devm_regmap_irq_chip_release(struct device *dev, void *res)
+{
+	struct regmap_irq_chip_data *d = *(struct regmap_irq_chip_data **)res;
+
+	regmap_del_irq_chip(d->irq, d);
+}
+
+static int devm_regmap_irq_chip_match(struct device *dev, void *res, void *data)
+
+{
+	struct regmap_irq_chip_data **r = res;
+
+	if (!r || !*r) {
+		WARN_ON(!r || !*r);
+		return 0;
+	}
+	return *r == data;
+}
+
+/**
+ * devm_regmap_add_irq_chip(): Resource manager regmap_add_irq_chip()
+ *
+ * @dev:       The device pointer on which irq_chip belongs to.
+ * @map:       The regmap for the device.
+ * @irq:       The IRQ the device uses to signal interrupts
+ * @irq_flags: The IRQF_ flags to use for the primary interrupt.
+ * @chip:      Configuration for the interrupt controller.
+ * @data:      Runtime data structure for the controller, allocated on success
+ *
+ * Returns 0 on success or an errno on failure.
+ *
+ * The regmap_irq_chip data automatically be released when the device is
+ * unbound.
+ */
+int devm_regmap_add_irq_chip(struct device *dev, struct regmap *map, int irq,
+			     int irq_flags, int irq_base,
+			     const struct regmap_irq_chip *chip,
+			     struct regmap_irq_chip_data **data)
+{
+	struct regmap_irq_chip_data **ptr, *d;
+	int ret;
+
+	ptr = devres_alloc(devm_regmap_irq_chip_release, sizeof(*ptr),
+			   GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	ret = regmap_add_irq_chip(map, irq, irq_flags, irq_base,
+				  chip, &d);
+	if (ret < 0) {
+		devres_free(ptr);
+		return ret;
+	}
+
+	*ptr = d;
+	devres_add(dev, ptr);
+	*data = d;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devm_regmap_add_irq_chip);
+
+/**
+ * devm_regmap_del_irq_chip(): Resource managed regmap_del_irq_chip()
+ *
+ * @dev: Device for which which resource was allocated.
+ * @irq: Primary IRQ for the device
+ * @d:   regmap_irq_chip_data allocated by regmap_add_irq_chip()
+ */
+void devm_regmap_del_irq_chip(struct device *dev, int irq,
+			      struct regmap_irq_chip_data *data)
+{
+	int rc;
+
+	WARN_ON(irq != data->irq);
+	rc = devres_release(dev, devm_regmap_irq_chip_release,
+			    devm_regmap_irq_chip_match, data);
+
+	if (rc != 0)
+		WARN_ON(rc);
+}
+EXPORT_SYMBOL_GPL(devm_regmap_del_irq_chip);
+
 /**
  * regmap_irq_chip_get_base(): Retrieve interrupt base for a regmap IRQ chip
  *
diff --git a/drivers/base/regmap/regmap-mmio.c b/drivers/base/regmap/regmap-mmio.c
index 8812bfb9e3b8..7526906ca080 100644
--- a/drivers/base/regmap/regmap-mmio.c
+++ b/drivers/base/regmap/regmap-mmio.c
@@ -25,26 +25,14 @@
 
 struct regmap_mmio_context {
 	void __iomem *regs;
-	unsigned reg_bytes;
 	unsigned val_bytes;
-	unsigned pad_bytes;
 	struct clk *clk;
-};
 
-static inline void regmap_mmio_regsize_check(size_t reg_size)
-{
-	switch (reg_size) {
-	case 1:
-	case 2:
-	case 4:
-#ifdef CONFIG_64BIT
-	case 8:
-#endif
-		break;
-	default:
-		BUG();
-	}
-}
+	void (*reg_write)(struct regmap_mmio_context *ctx,
+			  unsigned int reg, unsigned int val);
+	unsigned int (*reg_read)(struct regmap_mmio_context *ctx,
+			         unsigned int reg);
+};
 
 static int regmap_mmio_regbits_check(size_t reg_bits)
 {
@@ -88,72 +76,62 @@ static int regmap_mmio_get_min_stride(size_t val_bits)
 	return min_stride;
 }
 
-static inline void regmap_mmio_count_check(size_t count, u32 offset)
+static void regmap_mmio_write8(struct regmap_mmio_context *ctx,
+				unsigned int reg,
+				unsigned int val)
+{
+	writeb(val, ctx->regs + reg);
+}
+
+static void regmap_mmio_write16le(struct regmap_mmio_context *ctx,
+				  unsigned int reg,
+				  unsigned int val)
 {
-	BUG_ON(count <= offset);
+	writew(val, ctx->regs + reg);
 }
 
-static inline unsigned int
-regmap_mmio_get_offset(const void *reg, size_t reg_size)
+static void regmap_mmio_write16be(struct regmap_mmio_context *ctx,
+				  unsigned int reg,
+				  unsigned int val)
 {
-	switch (reg_size) {
-	case 1:
-		return *(u8 *)reg;
-	case 2:
-		return *(u16 *)reg;
-	case 4:
-		return *(u32 *)reg;
+	iowrite16be(val, ctx->regs + reg);
+}
+
+static void regmap_mmio_write32le(struct regmap_mmio_context *ctx,
+				  unsigned int reg,
+				  unsigned int val)
+{
+	writel(val, ctx->regs + reg);
+}
+
+static void regmap_mmio_write32be(struct regmap_mmio_context *ctx,
+				  unsigned int reg,
+				  unsigned int val)
+{
+	iowrite32be(val, ctx->regs + reg);
+}
+
 #ifdef CONFIG_64BIT
-	case 8:
-		return *(u64 *)reg;
-#endif
-	default:
-		BUG();
-	}
+static void regmap_mmio_write64le(struct regmap_mmio_context *ctx,
+				  unsigned int reg,
+				  unsigned int val)
+{
+	writeq(val, ctx->regs + reg);
 }
+#endif
 
-static int regmap_mmio_gather_write(void *context,
-				    const void *reg, size_t reg_size,
-				    const void *val, size_t val_size)
+static int regmap_mmio_write(void *context, unsigned int reg, unsigned int val)
 {
 	struct regmap_mmio_context *ctx = context;
-	unsigned int offset;
 	int ret;
 
-	regmap_mmio_regsize_check(reg_size);
-
 	if (!IS_ERR(ctx->clk)) {
 		ret = clk_enable(ctx->clk);
 		if (ret < 0)
 			return ret;
 	}
 
-	offset = regmap_mmio_get_offset(reg, reg_size);
-
-	while (val_size) {
-		switch (ctx->val_bytes) {
-		case 1:
-			__raw_writeb(*(u8 *)val, ctx->regs + offset);
-			break;
-		case 2:
-			__raw_writew(*(u16 *)val, ctx->regs + offset);
-			break;
-		case 4:
-			__raw_writel(*(u32 *)val, ctx->regs + offset);
-			break;
-#ifdef CONFIG_64BIT
-		case 8:
-			__raw_writeq(*(u64 *)val, ctx->regs + offset);
-			break;
-#endif
-		default:
-			/* Should be caught by regmap_mmio_check_config */
-			BUG();
-		}
-		val_size -= ctx->val_bytes;
-		val += ctx->val_bytes;
-		offset += ctx->val_bytes;
-	}
+	ctx->reg_write(ctx, reg, val);
 
 	if (!IS_ERR(ctx->clk))
 		clk_disable(ctx->clk);
@@ -161,59 +139,56 @@ static int regmap_mmio_gather_write(void *context,
 	return 0;
 }
 
-static int regmap_mmio_write(void *context, const void *data, size_t count)
+static unsigned int regmap_mmio_read8(struct regmap_mmio_context *ctx,
+				      unsigned int reg)
 {
-	struct regmap_mmio_context *ctx = context;
-	unsigned int offset = ctx->reg_bytes + ctx->pad_bytes;
+	return readb(ctx->regs + reg);
+}
+
+static unsigned int regmap_mmio_read16le(struct regmap_mmio_context *ctx,
+				         unsigned int reg)
+{
+	return readw(ctx->regs + reg);
+}
+
+static unsigned int regmap_mmio_read16be(struct regmap_mmio_context *ctx,
+				         unsigned int reg)
+{
+	return ioread16be(ctx->regs + reg);
+}
+
+static unsigned int regmap_mmio_read32le(struct regmap_mmio_context *ctx,
+				         unsigned int reg)
+{
+	return readl(ctx->regs + reg);
+}
 
-	regmap_mmio_count_check(count, offset);
+static unsigned int regmap_mmio_read32be(struct regmap_mmio_context *ctx,
+				         unsigned int reg)
+{
+	return ioread32be(ctx->regs + reg);
+}
 
-	return regmap_mmio_gather_write(context, data, ctx->reg_bytes,
-					data + offset, count - offset);
+#ifdef CONFIG_64BIT
+static unsigned int regmap_mmio_read64le(struct regmap_mmio_context *ctx,
+				         unsigned int reg)
+{
+	return readq(ctx->regs + reg);
 }
+#endif
 
-static int regmap_mmio_read(void *context,
-			    const void *reg, size_t reg_size,
-			    void *val, size_t val_size)
+static int regmap_mmio_read(void *context, unsigned int reg, unsigned int *val)
 {
 	struct regmap_mmio_context *ctx = context;
-	unsigned int offset;
 	int ret;
 
-	regmap_mmio_regsize_check(reg_size);
-
 	if (!IS_ERR(ctx->clk)) {
 		ret = clk_enable(ctx->clk);
 		if (ret < 0)
 			return ret;
 	}
 
-	offset = regmap_mmio_get_offset(reg, reg_size);
-
-	while (val_size) {
-		switch (ctx->val_bytes) {
-		case 1:
-			*(u8 *)val = __raw_readb(ctx->regs + offset);
-			break;
-		case 2:
-			*(u16 *)val = __raw_readw(ctx->regs + offset);
-			break;
-		case 4:
-			*(u32 *)val = __raw_readl(ctx->regs + offset);
-			break;
-#ifdef CONFIG_64BIT
-		case 8:
-			*(u64 *)val = __raw_readq(ctx->regs + offset);
-			break;
-#endif
-		default:
-			/* Should be caught by regmap_mmio_check_config */
-			BUG();
-		}
-		val_size -= ctx->val_bytes;
-		val += ctx->val_bytes;
-		offset += ctx->val_bytes;
-	}
+	*val = ctx->reg_read(ctx, reg);
 
 	if (!IS_ERR(ctx->clk))
 		clk_disable(ctx->clk);
@@ -232,14 +207,11 @@ static void regmap_mmio_free_context(void *context)
 	kfree(context);
 }
 
-static struct regmap_bus regmap_mmio = {
+static const struct regmap_bus regmap_mmio = {
 	.fast_io = true,
-	.write = regmap_mmio_write,
-	.gather_write = regmap_mmio_gather_write,
-	.read = regmap_mmio_read,
+	.reg_write = regmap_mmio_write,
+	.reg_read = regmap_mmio_read,
 	.free_context = regmap_mmio_free_context,
-	.reg_format_endian_default = REGMAP_ENDIAN_NATIVE,
-	.val_format_endian_default = REGMAP_ENDIAN_NATIVE,
 };
 
 static struct regmap_mmio_context *regmap_mmio_gen_context(struct device *dev,
@@ -265,24 +237,71 @@ static struct regmap_mmio_context *regmap_mmio_gen_context(struct device *dev,
 	if (config->reg_stride < min_stride)
 		return ERR_PTR(-EINVAL);
 
-	switch (config->reg_format_endian) {
-	case REGMAP_ENDIAN_DEFAULT:
-	case REGMAP_ENDIAN_NATIVE:
-		break;
-	default:
-		return ERR_PTR(-EINVAL);
-	}
-
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return ERR_PTR(-ENOMEM);
 
 	ctx->regs = regs;
 	ctx->val_bytes = config->val_bits / 8;
-	ctx->reg_bytes = config->reg_bits / 8;
-	ctx->pad_bytes = config->pad_bits / 8;
 	ctx->clk = ERR_PTR(-ENODEV);
 
+	switch (config->reg_format_endian) {
+	case REGMAP_ENDIAN_DEFAULT:
+	case REGMAP_ENDIAN_LITTLE:
+#ifdef __LITTLE_ENDIAN
+	case REGMAP_ENDIAN_NATIVE:
+#endif
+		switch (config->val_bits) {
+		case 8:
+			ctx->reg_read = regmap_mmio_read8;
+			ctx->reg_write = regmap_mmio_write8;
+			break;
+		case 16:
+			ctx->reg_read = regmap_mmio_read16le;
+			ctx->reg_write = regmap_mmio_write16le;
+			break;
+		case 32:
+			ctx->reg_read = regmap_mmio_read32le;
+			ctx->reg_write = regmap_mmio_write32le;
+			break;
+#ifdef CONFIG_64BIT
+		case 64:
+			ctx->reg_read = regmap_mmio_read64le;
+			ctx->reg_write = regmap_mmio_write64le;
+			break;
+#endif
+		default:
+			ret = -EINVAL;
+			goto err_free;
+		}
+		break;
+	case REGMAP_ENDIAN_BIG:
+#ifdef __BIG_ENDIAN
+	case REGMAP_ENDIAN_NATIVE:
+#endif
+		switch (config->val_bits) {
+		case 8:
+			ctx->reg_read = regmap_mmio_read8;
+			ctx->reg_write = regmap_mmio_write8;
+			break;
+		case 16:
+			ctx->reg_read = regmap_mmio_read16be;
+			ctx->reg_write = regmap_mmio_write16be;
+			break;
+		case 32:
+			ctx->reg_read = regmap_mmio_read32be;
+			ctx->reg_write = regmap_mmio_write32be;
+			break;
+		default:
+			ret = -EINVAL;
+			goto err_free;
+		}
+		break;
+	default:
+		ret = -EINVAL;
+		goto err_free;
+	}
+
 	if (clk_id == NULL)
 		return ctx;
 
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index ee54e841de4a..df2d2ef5d6b3 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -19,6 +19,7 @@
 #include <linux/rbtree.h>
 #include <linux/sched.h>
 #include <linux/delay.h>
+#include <linux/log2.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -557,6 +558,8 @@ enum regmap_endian regmap_get_val_endian(struct device *dev,
 			endian = REGMAP_ENDIAN_BIG;
 		else if (of_property_read_bool(np, "little-endian"))
 			endian = REGMAP_ENDIAN_LITTLE;
+		else if (of_property_read_bool(np, "native-endian"))
+			endian = REGMAP_ENDIAN_NATIVE;
 
 		/* If the endianness was specified in DT, use that */
 		if (endian != REGMAP_ENDIAN_DEFAULT)
@@ -638,6 +641,10 @@ struct regmap *__regmap_init(struct device *dev,
 		map->reg_stride = config->reg_stride;
 	else
 		map->reg_stride = 1;
+	if (is_power_of_2(map->reg_stride))
+		map->reg_stride_order = ilog2(map->reg_stride);
+	else
+		map->reg_stride_order = -1;
 	map->use_single_read = config->use_single_rw || !bus || !bus->read;
 	map->use_single_write = config->use_single_rw || !bus || !bus->write;
 	map->can_multi_write = config->can_multi_write && bus && bus->write;
@@ -1308,7 +1315,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg,
 	if (map->writeable_reg)
 		for (i = 0; i < val_len / map->format.val_bytes; i++)
 			if (!map->writeable_reg(map->dev,
-						reg + (i * map->reg_stride)))
+					       reg + regmap_get_offset(map, i)))
 				return -EINVAL;
 
 	if (!map->cache_bypass && map->format.parse_val) {
@@ -1316,7 +1323,8 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg,
 		int val_bytes = map->format.val_bytes;
 		for (i = 0; i < val_len / val_bytes; i++) {
 			ival = map->format.parse_val(val + (i * val_bytes));
-			ret = regcache_write(map, reg + (i * map->reg_stride),
+			ret = regcache_write(map,
+					     reg + regmap_get_offset(map, i),
 					     ival);
 			if (ret) {
 				dev_err(map->dev,
@@ -1690,100 +1698,63 @@ int regmap_raw_write(struct regmap *map, unsigned int reg,
 EXPORT_SYMBOL_GPL(regmap_raw_write);
 
 /**
- * regmap_field_write(): Write a value to a single register field
- *
- * @field: Register field to write to
- * @val: Value to be written
- *
- * A value of zero will be returned on success, a negative errno will
- * be returned in error cases.
- */
-int regmap_field_write(struct regmap_field *field, unsigned int val)
-{
-	return regmap_update_bits(field->regmap, field->reg,
-				field->mask, val << field->shift);
-}
-EXPORT_SYMBOL_GPL(regmap_field_write);
-
-/**
- * regmap_field_update_bits():	Perform a read/modify/write cycle
- *                              on the register field
+ * regmap_field_update_bits_base():
+ *	Perform a read/modify/write cycle on the register field
+ *	with change, async, force option
  *
  * @field: Register field to write to
  * @mask: Bitmask to change
  * @val: Value to be written
+ * @change: Boolean indicating if a write was done
+ * @async: Boolean indicating asynchronously
+ * @force: Boolean indicating use force update
  *
  * A value of zero will be returned on success, a negative errno will
  * be returned in error cases.
  */
-int regmap_field_update_bits(struct regmap_field *field, unsigned int mask, unsigned int val)
+int regmap_field_update_bits_base(struct regmap_field *field,
+				  unsigned int mask, unsigned int val,
+				  bool *change, bool async, bool force)
 {
 	mask = (mask << field->shift) & field->mask;
 
-	return regmap_update_bits(field->regmap, field->reg,
-				  mask, val << field->shift);
+	return regmap_update_bits_base(field->regmap, field->reg,
+				       mask, val << field->shift,
+				       change, async, force);
 }
-EXPORT_SYMBOL_GPL(regmap_field_update_bits);
+EXPORT_SYMBOL_GPL(regmap_field_update_bits_base);
 
 /**
- * regmap_fields_write(): Write a value to a single register field with port ID
- *
- * @field: Register field to write to
- * @id: port ID
- * @val: Value to be written
- *
- * A value of zero will be returned on success, a negative errno will
- * be returned in error cases.
- */
-int regmap_fields_write(struct regmap_field *field, unsigned int id,
-			unsigned int val)
-{
-	if (id >= field->id_size)
-		return -EINVAL;
-
-	return regmap_update_bits(field->regmap,
-				  field->reg + (field->id_offset * id),
-				  field->mask, val << field->shift);
-}
-EXPORT_SYMBOL_GPL(regmap_fields_write);
-
-int regmap_fields_force_write(struct regmap_field *field, unsigned int id,
-			unsigned int val)
-{
-	if (id >= field->id_size)
-		return -EINVAL;
-
-	return regmap_write_bits(field->regmap,
-				  field->reg + (field->id_offset * id),
-				  field->mask, val << field->shift);
-}
-EXPORT_SYMBOL_GPL(regmap_fields_force_write);
-
-/**
- * regmap_fields_update_bits():	Perform a read/modify/write cycle
- *                              on the register field
+ * regmap_fields_update_bits_base():
+ *	Perform a read/modify/write cycle on the register field
+ *	with change, async, force option
  *
  * @field: Register field to write to
  * @id: port ID
  * @mask: Bitmask to change
  * @val: Value to be written
+ * @change: Boolean indicating if a write was done
+ * @async: Boolean indicating asynchronously
+ * @force: Boolean indicating use force update
  *
  * A value of zero will be returned on success, a negative errno will
  * be returned in error cases.
  */
-int regmap_fields_update_bits(struct regmap_field *field,  unsigned int id,
-			      unsigned int mask, unsigned int val)
+int regmap_fields_update_bits_base(struct regmap_field *field,  unsigned int id,
+				   unsigned int mask, unsigned int val,
+				   bool *change, bool async, bool force)
 {
 	if (id >= field->id_size)
 		return -EINVAL;
 
 	mask = (mask << field->shift) & field->mask;
 
-	return regmap_update_bits(field->regmap,
-				  field->reg + (field->id_offset * id),
-				  mask, val << field->shift);
+	return regmap_update_bits_base(field->regmap,
+				       field->reg + (field->id_offset * id),
+				       mask, val << field->shift,
+				       change, async, force);
 }
-EXPORT_SYMBOL_GPL(regmap_fields_update_bits);
+EXPORT_SYMBOL_GPL(regmap_fields_update_bits_base);
 
 /*
  * regmap_bulk_write(): Write multiple registers to the device
@@ -1846,8 +1817,9 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val,
 				goto out;
 			}
 
-			ret = _regmap_write(map, reg + (i * map->reg_stride),
-					ival);
+			ret = _regmap_write(map,
+					    reg + regmap_get_offset(map, i),
+					    ival);
 			if (ret != 0)
 				goto out;
 		}
@@ -2253,6 +2225,9 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
 
 	WARN_ON(!map->bus);
 
+	if (!map->bus || !map->bus->read)
+		return -EINVAL;
+
 	range = _regmap_range_lookup(map, reg);
 	if (range) {
 		ret = _regmap_select_page(map, &reg, range,
@@ -2416,7 +2391,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
 		 * cost as we expect to hit the cache.
 		 */
 		for (i = 0; i < val_count; i++) {
-			ret = _regmap_read(map, reg + (i * map->reg_stride),
+			ret = _regmap_read(map, reg + regmap_get_offset(map, i),
 					   &v);
 			if (ret != 0)
 				goto out;
@@ -2568,7 +2543,7 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val,
 	} else {
 		for (i = 0; i < val_count; i++) {
 			unsigned int ival;
-			ret = regmap_read(map, reg + (i * map->reg_stride),
+			ret = regmap_read(map, reg + regmap_get_offset(map, i),
 					  &ival);
 			if (ret != 0)
 				return ret;
@@ -2648,138 +2623,36 @@ static int _regmap_update_bits(struct regmap *map, unsigned int reg,
 }
 
 /**
- * regmap_update_bits: Perform a read/modify/write cycle on the register map
- *
- * @map: Register map to update
- * @reg: Register to update
- * @mask: Bitmask to change
- * @val: New value for bitmask
- *
- * Returns zero for success, a negative number on error.
- */
-int regmap_update_bits(struct regmap *map, unsigned int reg,
-		       unsigned int mask, unsigned int val)
-{
-	int ret;
-
-	map->lock(map->lock_arg);
-	ret = _regmap_update_bits(map, reg, mask, val, NULL, false);
-	map->unlock(map->lock_arg);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(regmap_update_bits);
-
-/**
- * regmap_write_bits: Perform a read/modify/write cycle on the register map
- *
- * @map: Register map to update
- * @reg: Register to update
- * @mask: Bitmask to change
- * @val: New value for bitmask
- *
- * Returns zero for success, a negative number on error.
- */
-int regmap_write_bits(struct regmap *map, unsigned int reg,
-		      unsigned int mask, unsigned int val)
-{
-	int ret;
-
-	map->lock(map->lock_arg);
-	ret = _regmap_update_bits(map, reg, mask, val, NULL, true);
-	map->unlock(map->lock_arg);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(regmap_write_bits);
-
-/**
- * regmap_update_bits_async: Perform a read/modify/write cycle on the register
- *                           map asynchronously
- *
- * @map: Register map to update
- * @reg: Register to update
- * @mask: Bitmask to change
- * @val: New value for bitmask
- *
- * With most buses the read must be done synchronously so this is most
- * useful for devices with a cache which do not need to interact with
- * the hardware to determine the current register value.
- *
- * Returns zero for success, a negative number on error.
- */
-int regmap_update_bits_async(struct regmap *map, unsigned int reg,
-			     unsigned int mask, unsigned int val)
-{
-	int ret;
-
-	map->lock(map->lock_arg);
-
-	map->async = true;
-
-	ret = _regmap_update_bits(map, reg, mask, val, NULL, false);
-
-	map->async = false;
-
-	map->unlock(map->lock_arg);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(regmap_update_bits_async);
-
-/**
- * regmap_update_bits_check: Perform a read/modify/write cycle on the
- *                           register map and report if updated
- *
- * @map: Register map to update
- * @reg: Register to update
- * @mask: Bitmask to change
- * @val: New value for bitmask
- * @change: Boolean indicating if a write was done
- *
- * Returns zero for success, a negative number on error.
- */
-int regmap_update_bits_check(struct regmap *map, unsigned int reg,
-			     unsigned int mask, unsigned int val,
-			     bool *change)
-{
-	int ret;
-
-	map->lock(map->lock_arg);
-	ret = _regmap_update_bits(map, reg, mask, val, change, false);
-	map->unlock(map->lock_arg);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(regmap_update_bits_check);
-
-/**
- * regmap_update_bits_check_async: Perform a read/modify/write cycle on the
- *                                 register map asynchronously and report if
- *                                 updated
+ * regmap_update_bits_base:
+ *	Perform a read/modify/write cycle on the
+ *	register map with change, async, force option
  *
  * @map: Register map to update
  * @reg: Register to update
  * @mask: Bitmask to change
  * @val: New value for bitmask
  * @change: Boolean indicating if a write was done
+ * @async: Boolean indicating asynchronously
+ * @force: Boolean indicating use force update
  *
+ * if async was true,
  * With most buses the read must be done synchronously so this is most
  * useful for devices with a cache which do not need to interact with
  * the hardware to determine the current register value.
  *
  * Returns zero for success, a negative number on error.
  */
-int regmap_update_bits_check_async(struct regmap *map, unsigned int reg,
-				   unsigned int mask, unsigned int val,
-				   bool *change)
+int regmap_update_bits_base(struct regmap *map, unsigned int reg,
+			    unsigned int mask, unsigned int val,
+			    bool *change, bool async, bool force)
 {
 	int ret;
 
 	map->lock(map->lock_arg);
 
-	map->async = true;
+	map->async = async;
 
-	ret = _regmap_update_bits(map, reg, mask, val, change, false);
+	ret = _regmap_update_bits(map, reg, mask, val, change, force);
 
 	map->async = false;
 
@@ -2787,7 +2660,7 @@ int regmap_update_bits_check_async(struct regmap *map, unsigned int reg,
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(regmap_update_bits_check_async);
+EXPORT_SYMBOL_GPL(regmap_update_bits_base);
 
 void regmap_async_complete_cb(struct regmap_async *async, int ret)
 {
diff --git a/drivers/block/cryptoloop.c b/drivers/block/cryptoloop.c
index 99e773cb70d0..3d31761c0ed0 100644
--- a/drivers/block/cryptoloop.c
+++ b/drivers/block/cryptoloop.c
@@ -21,9 +21,9 @@
 
 #include <linux/module.h>
 
+#include <crypto/skcipher.h>
 #include <linux/init.h>
 #include <linux/string.h>
-#include <linux/crypto.h>
 #include <linux/blkdev.h>
 #include <linux/scatterlist.h>
 #include <asm/uaccess.h>
@@ -46,7 +46,7 @@ cryptoloop_init(struct loop_device *lo, const struct loop_info64 *info)
 	char *cipher;
 	char *mode;
 	char *cmsp = cms;			/* c-m string pointer */
-	struct crypto_blkcipher *tfm;
+	struct crypto_skcipher *tfm;
 
 	/* encryption breaks for non sector aligned offsets */
 
@@ -82,12 +82,12 @@ cryptoloop_init(struct loop_device *lo, const struct loop_info64 *info)
 	*cmsp++ = ')';
 	*cmsp = 0;
 
-	tfm = crypto_alloc_blkcipher(cms, 0, CRYPTO_ALG_ASYNC);
+	tfm = crypto_alloc_skcipher(cms, 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm))
 		return PTR_ERR(tfm);
 
-	err = crypto_blkcipher_setkey(tfm, info->lo_encrypt_key,
-				      info->lo_encrypt_key_size);
+	err = crypto_skcipher_setkey(tfm, info->lo_encrypt_key,
+				     info->lo_encrypt_key_size);
 	
 	if (err != 0)
 		goto out_free_tfm;
@@ -96,17 +96,14 @@ cryptoloop_init(struct loop_device *lo, const struct loop_info64 *info)
 	return 0;
 
  out_free_tfm:
-	crypto_free_blkcipher(tfm);
+	crypto_free_skcipher(tfm);
 
  out:
 	return err;
 }
 
 
-typedef int (*encdec_cbc_t)(struct blkcipher_desc *desc,
-			struct scatterlist *sg_out,
-			struct scatterlist *sg_in,
-			unsigned int nsg);
+typedef int (*encdec_cbc_t)(struct skcipher_request *req);
 
 static int
 cryptoloop_transfer(struct loop_device *lo, int cmd,
@@ -114,11 +111,8 @@ cryptoloop_transfer(struct loop_device *lo, int cmd,
 		    struct page *loop_page, unsigned loop_off,
 		    int size, sector_t IV)
 {
-	struct crypto_blkcipher *tfm = lo->key_data;
-	struct blkcipher_desc desc = {
-		.tfm = tfm,
-		.flags = CRYPTO_TFM_REQ_MAY_SLEEP,
-	};
+	struct crypto_skcipher *tfm = lo->key_data;
+	SKCIPHER_REQUEST_ON_STACK(req, tfm);
 	struct scatterlist sg_out;
 	struct scatterlist sg_in;
 
@@ -127,6 +121,10 @@ cryptoloop_transfer(struct loop_device *lo, int cmd,
 	unsigned in_offs, out_offs;
 	int err;
 
+	skcipher_request_set_tfm(req, tfm);
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
+				      NULL, NULL);
+
 	sg_init_table(&sg_out, 1);
 	sg_init_table(&sg_in, 1);
 
@@ -135,13 +133,13 @@ cryptoloop_transfer(struct loop_device *lo, int cmd,
 		in_offs = raw_off;
 		out_page = loop_page;
 		out_offs = loop_off;
-		encdecfunc = crypto_blkcipher_crt(tfm)->decrypt;
+		encdecfunc = crypto_skcipher_decrypt;
 	} else {
 		in_page = loop_page;
 		in_offs = loop_off;
 		out_page = raw_page;
 		out_offs = raw_off;
-		encdecfunc = crypto_blkcipher_crt(tfm)->encrypt;
+		encdecfunc = crypto_skcipher_encrypt;
 	}
 
 	while (size > 0) {
@@ -152,10 +150,10 @@ cryptoloop_transfer(struct loop_device *lo, int cmd,
 		sg_set_page(&sg_in, in_page, sz, in_offs);
 		sg_set_page(&sg_out, out_page, sz, out_offs);
 
-		desc.info = iv;
-		err = encdecfunc(&desc, &sg_out, &sg_in, sz);
+		skcipher_request_set_crypt(req, &sg_in, &sg_out, sz, iv);
+		err = encdecfunc(req);
 		if (err)
-			return err;
+			goto out;
 
 		IV++;
 		size -= sz;
@@ -163,7 +161,11 @@ cryptoloop_transfer(struct loop_device *lo, int cmd,
 		out_offs += sz;
 	}
 
-	return 0;
+	err = 0;
+
+out:
+	skcipher_request_zero(req);
+	return err;
 }
 
 static int
@@ -175,9 +177,9 @@ cryptoloop_ioctl(struct loop_device *lo, int cmd, unsigned long arg)
 static int
 cryptoloop_release(struct loop_device *lo)
 {
-	struct crypto_blkcipher *tfm = lo->key_data;
+	struct crypto_skcipher *tfm = lo->key_data;
 	if (tfm != NULL) {
-		crypto_free_blkcipher(tfm);
+		crypto_free_skcipher(tfm);
 		lo->key_data = NULL;
 		return 0;
 	}
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 34bc84efc29e..c227fd4cad75 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -26,13 +26,13 @@
 #ifndef _DRBD_INT_H
 #define _DRBD_INT_H
 
+#include <crypto/hash.h>
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <linux/list.h>
 #include <linux/sched.h>
 #include <linux/bitops.h>
 #include <linux/slab.h>
-#include <linux/crypto.h>
 #include <linux/ratelimit.h>
 #include <linux/tcp.h>
 #include <linux/mutex.h>
@@ -724,11 +724,11 @@ struct drbd_connection {
 
 	struct list_head transfer_log;	/* all requests not yet fully processed */
 
-	struct crypto_hash *cram_hmac_tfm;
-	struct crypto_hash *integrity_tfm;  /* checksums we compute, updates protected by connection->data->mutex */
-	struct crypto_hash *peer_integrity_tfm;  /* checksums we verify, only accessed from receiver thread  */
-	struct crypto_hash *csums_tfm;
-	struct crypto_hash *verify_tfm;
+	struct crypto_shash *cram_hmac_tfm;
+	struct crypto_ahash *integrity_tfm;  /* checksums we compute, updates protected by connection->data->mutex */
+	struct crypto_ahash *peer_integrity_tfm;  /* checksums we verify, only accessed from receiver thread  */
+	struct crypto_ahash *csums_tfm;
+	struct crypto_ahash *verify_tfm;
 	void *int_dig_in;
 	void *int_dig_vv;
 
@@ -1524,8 +1524,8 @@ static inline void ov_out_of_sync_print(struct drbd_device *device)
 }
 
 
-extern void drbd_csum_bio(struct crypto_hash *, struct bio *, void *);
-extern void drbd_csum_ee(struct crypto_hash *, struct drbd_peer_request *, void *);
+extern void drbd_csum_bio(struct crypto_ahash *, struct bio *, void *);
+extern void drbd_csum_ee(struct crypto_ahash *, struct drbd_peer_request *, void *);
 /* worker callbacks */
 extern int w_e_end_data_req(struct drbd_work *, int);
 extern int w_e_end_rsdata_req(struct drbd_work *, int);
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 5b43dfb79819..fa209773d494 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -1340,7 +1340,7 @@ void drbd_send_ack_dp(struct drbd_peer_device *peer_device, enum drbd_packet cmd
 		      struct p_data *dp, int data_size)
 {
 	if (peer_device->connection->peer_integrity_tfm)
-		data_size -= crypto_hash_digestsize(peer_device->connection->peer_integrity_tfm);
+		data_size -= crypto_ahash_digestsize(peer_device->connection->peer_integrity_tfm);
 	_drbd_send_ack(peer_device, cmd, dp->sector, cpu_to_be32(data_size),
 		       dp->block_id);
 }
@@ -1629,7 +1629,7 @@ int drbd_send_dblock(struct drbd_peer_device *peer_device, struct drbd_request *
 	sock = &peer_device->connection->data;
 	p = drbd_prepare_command(peer_device, sock);
 	digest_size = peer_device->connection->integrity_tfm ?
-		      crypto_hash_digestsize(peer_device->connection->integrity_tfm) : 0;
+		      crypto_ahash_digestsize(peer_device->connection->integrity_tfm) : 0;
 
 	if (!p)
 		return -EIO;
@@ -1718,7 +1718,7 @@ int drbd_send_block(struct drbd_peer_device *peer_device, enum drbd_packet cmd,
 	p = drbd_prepare_command(peer_device, sock);
 
 	digest_size = peer_device->connection->integrity_tfm ?
-		      crypto_hash_digestsize(peer_device->connection->integrity_tfm) : 0;
+		      crypto_ahash_digestsize(peer_device->connection->integrity_tfm) : 0;
 
 	if (!p)
 		return -EIO;
@@ -2498,11 +2498,11 @@ void conn_free_crypto(struct drbd_connection *connection)
 {
 	drbd_free_sock(connection);
 
-	crypto_free_hash(connection->csums_tfm);
-	crypto_free_hash(connection->verify_tfm);
-	crypto_free_hash(connection->cram_hmac_tfm);
-	crypto_free_hash(connection->integrity_tfm);
-	crypto_free_hash(connection->peer_integrity_tfm);
+	crypto_free_ahash(connection->csums_tfm);
+	crypto_free_ahash(connection->verify_tfm);
+	crypto_free_shash(connection->cram_hmac_tfm);
+	crypto_free_ahash(connection->integrity_tfm);
+	crypto_free_ahash(connection->peer_integrity_tfm);
 	kfree(connection->int_dig_in);
 	kfree(connection->int_dig_vv);
 
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index c055c5e12f24..226eb0c9f0fb 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -2160,19 +2160,34 @@ check_net_options(struct drbd_connection *connection, struct net_conf *new_net_c
 }
 
 struct crypto {
-	struct crypto_hash *verify_tfm;
-	struct crypto_hash *csums_tfm;
-	struct crypto_hash *cram_hmac_tfm;
-	struct crypto_hash *integrity_tfm;
+	struct crypto_ahash *verify_tfm;
+	struct crypto_ahash *csums_tfm;
+	struct crypto_shash *cram_hmac_tfm;
+	struct crypto_ahash *integrity_tfm;
 };
 
 static int
-alloc_hash(struct crypto_hash **tfm, char *tfm_name, int err_alg)
+alloc_shash(struct crypto_shash **tfm, char *tfm_name, int err_alg)
 {
 	if (!tfm_name[0])
 		return NO_ERROR;
 
-	*tfm = crypto_alloc_hash(tfm_name, 0, CRYPTO_ALG_ASYNC);
+	*tfm = crypto_alloc_shash(tfm_name, 0, 0);
+	if (IS_ERR(*tfm)) {
+		*tfm = NULL;
+		return err_alg;
+	}
+
+	return NO_ERROR;
+}
+
+static int
+alloc_ahash(struct crypto_ahash **tfm, char *tfm_name, int err_alg)
+{
+	if (!tfm_name[0])
+		return NO_ERROR;
+
+	*tfm = crypto_alloc_ahash(tfm_name, 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(*tfm)) {
 		*tfm = NULL;
 		return err_alg;
@@ -2187,24 +2202,24 @@ alloc_crypto(struct crypto *crypto, struct net_conf *new_net_conf)
 	char hmac_name[CRYPTO_MAX_ALG_NAME];
 	enum drbd_ret_code rv;
 
-	rv = alloc_hash(&crypto->csums_tfm, new_net_conf->csums_alg,
-		       ERR_CSUMS_ALG);
+	rv = alloc_ahash(&crypto->csums_tfm, new_net_conf->csums_alg,
+			 ERR_CSUMS_ALG);
 	if (rv != NO_ERROR)
 		return rv;
-	rv = alloc_hash(&crypto->verify_tfm, new_net_conf->verify_alg,
-		       ERR_VERIFY_ALG);
+	rv = alloc_ahash(&crypto->verify_tfm, new_net_conf->verify_alg,
+			 ERR_VERIFY_ALG);
 	if (rv != NO_ERROR)
 		return rv;
-	rv = alloc_hash(&crypto->integrity_tfm, new_net_conf->integrity_alg,
-		       ERR_INTEGRITY_ALG);
+	rv = alloc_ahash(&crypto->integrity_tfm, new_net_conf->integrity_alg,
+			 ERR_INTEGRITY_ALG);
 	if (rv != NO_ERROR)
 		return rv;
 	if (new_net_conf->cram_hmac_alg[0] != 0) {
 		snprintf(hmac_name, CRYPTO_MAX_ALG_NAME, "hmac(%s)",
 			 new_net_conf->cram_hmac_alg);
 
-		rv = alloc_hash(&crypto->cram_hmac_tfm, hmac_name,
-			       ERR_AUTH_ALG);
+		rv = alloc_shash(&crypto->cram_hmac_tfm, hmac_name,
+				 ERR_AUTH_ALG);
 	}
 
 	return rv;
@@ -2212,10 +2227,10 @@ alloc_crypto(struct crypto *crypto, struct net_conf *new_net_conf)
 
 static void free_crypto(struct crypto *crypto)
 {
-	crypto_free_hash(crypto->cram_hmac_tfm);
-	crypto_free_hash(crypto->integrity_tfm);
-	crypto_free_hash(crypto->csums_tfm);
-	crypto_free_hash(crypto->verify_tfm);
+	crypto_free_shash(crypto->cram_hmac_tfm);
+	crypto_free_ahash(crypto->integrity_tfm);
+	crypto_free_ahash(crypto->csums_tfm);
+	crypto_free_ahash(crypto->verify_tfm);
 }
 
 int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info)
@@ -2292,23 +2307,23 @@ int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info)
 	rcu_assign_pointer(connection->net_conf, new_net_conf);
 
 	if (!rsr) {
-		crypto_free_hash(connection->csums_tfm);
+		crypto_free_ahash(connection->csums_tfm);
 		connection->csums_tfm = crypto.csums_tfm;
 		crypto.csums_tfm = NULL;
 	}
 	if (!ovr) {
-		crypto_free_hash(connection->verify_tfm);
+		crypto_free_ahash(connection->verify_tfm);
 		connection->verify_tfm = crypto.verify_tfm;
 		crypto.verify_tfm = NULL;
 	}
 
-	crypto_free_hash(connection->integrity_tfm);
+	crypto_free_ahash(connection->integrity_tfm);
 	connection->integrity_tfm = crypto.integrity_tfm;
 	if (connection->cstate >= C_WF_REPORT_PARAMS && connection->agreed_pro_version >= 100)
 		/* Do this without trying to take connection->data.mutex again.  */
 		__drbd_send_protocol(connection, P_PROTOCOL_UPDATE);
 
-	crypto_free_hash(connection->cram_hmac_tfm);
+	crypto_free_shash(connection->cram_hmac_tfm);
 	connection->cram_hmac_tfm = crypto.cram_hmac_tfm;
 
 	mutex_unlock(&connection->resource->conf_update);
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 1957fe8601dc..050aaa1c0350 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1627,7 +1627,7 @@ read_in_block(struct drbd_peer_device *peer_device, u64 id, sector_t sector,
 
 	digest_size = 0;
 	if (!trim && peer_device->connection->peer_integrity_tfm) {
-		digest_size = crypto_hash_digestsize(peer_device->connection->peer_integrity_tfm);
+		digest_size = crypto_ahash_digestsize(peer_device->connection->peer_integrity_tfm);
 		/*
 		 * FIXME: Receive the incoming digest into the receive buffer
 		 *	  here, together with its struct p_data?
@@ -1741,7 +1741,7 @@ static int recv_dless_read(struct drbd_peer_device *peer_device, struct drbd_req
 
 	digest_size = 0;
 	if (peer_device->connection->peer_integrity_tfm) {
-		digest_size = crypto_hash_digestsize(peer_device->connection->peer_integrity_tfm);
+		digest_size = crypto_ahash_digestsize(peer_device->connection->peer_integrity_tfm);
 		err = drbd_recv_all_warn(peer_device->connection, dig_in, digest_size);
 		if (err)
 			return err;
@@ -3321,7 +3321,7 @@ static int receive_protocol(struct drbd_connection *connection, struct packet_in
 	int p_proto, p_discard_my_data, p_two_primaries, cf;
 	struct net_conf *nc, *old_net_conf, *new_net_conf = NULL;
 	char integrity_alg[SHARED_SECRET_MAX] = "";
-	struct crypto_hash *peer_integrity_tfm = NULL;
+	struct crypto_ahash *peer_integrity_tfm = NULL;
 	void *int_dig_in = NULL, *int_dig_vv = NULL;
 
 	p_proto		= be32_to_cpu(p->protocol);
@@ -3402,14 +3402,14 @@ static int receive_protocol(struct drbd_connection *connection, struct packet_in
 		 * change.
 		 */
 
-		peer_integrity_tfm = crypto_alloc_hash(integrity_alg, 0, CRYPTO_ALG_ASYNC);
+		peer_integrity_tfm = crypto_alloc_ahash(integrity_alg, 0, CRYPTO_ALG_ASYNC);
 		if (!peer_integrity_tfm) {
 			drbd_err(connection, "peer data-integrity-alg %s not supported\n",
 				 integrity_alg);
 			goto disconnect;
 		}
 
-		hash_size = crypto_hash_digestsize(peer_integrity_tfm);
+		hash_size = crypto_ahash_digestsize(peer_integrity_tfm);
 		int_dig_in = kmalloc(hash_size, GFP_KERNEL);
 		int_dig_vv = kmalloc(hash_size, GFP_KERNEL);
 		if (!(int_dig_in && int_dig_vv)) {
@@ -3439,7 +3439,7 @@ static int receive_protocol(struct drbd_connection *connection, struct packet_in
 	mutex_unlock(&connection->resource->conf_update);
 	mutex_unlock(&connection->data.mutex);
 
-	crypto_free_hash(connection->peer_integrity_tfm);
+	crypto_free_ahash(connection->peer_integrity_tfm);
 	kfree(connection->int_dig_in);
 	kfree(connection->int_dig_vv);
 	connection->peer_integrity_tfm = peer_integrity_tfm;
@@ -3457,7 +3457,7 @@ static int receive_protocol(struct drbd_connection *connection, struct packet_in
 disconnect_rcu_unlock:
 	rcu_read_unlock();
 disconnect:
-	crypto_free_hash(peer_integrity_tfm);
+	crypto_free_ahash(peer_integrity_tfm);
 	kfree(int_dig_in);
 	kfree(int_dig_vv);
 	conn_request_state(connection, NS(conn, C_DISCONNECTING), CS_HARD);
@@ -3469,15 +3469,15 @@ disconnect:
  * return: NULL (alg name was "")
  *         ERR_PTR(error) if something goes wrong
  *         or the crypto hash ptr, if it worked out ok. */
-static struct crypto_hash *drbd_crypto_alloc_digest_safe(const struct drbd_device *device,
+static struct crypto_ahash *drbd_crypto_alloc_digest_safe(const struct drbd_device *device,
 		const char *alg, const char *name)
 {
-	struct crypto_hash *tfm;
+	struct crypto_ahash *tfm;
 
 	if (!alg[0])
 		return NULL;
 
-	tfm = crypto_alloc_hash(alg, 0, CRYPTO_ALG_ASYNC);
+	tfm = crypto_alloc_ahash(alg, 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm)) {
 		drbd_err(device, "Can not allocate \"%s\" as %s (reason: %ld)\n",
 			alg, name, PTR_ERR(tfm));
@@ -3530,8 +3530,8 @@ static int receive_SyncParam(struct drbd_connection *connection, struct packet_i
 	struct drbd_device *device;
 	struct p_rs_param_95 *p;
 	unsigned int header_size, data_size, exp_max_sz;
-	struct crypto_hash *verify_tfm = NULL;
-	struct crypto_hash *csums_tfm = NULL;
+	struct crypto_ahash *verify_tfm = NULL;
+	struct crypto_ahash *csums_tfm = NULL;
 	struct net_conf *old_net_conf, *new_net_conf = NULL;
 	struct disk_conf *old_disk_conf = NULL, *new_disk_conf = NULL;
 	const int apv = connection->agreed_pro_version;
@@ -3678,14 +3678,14 @@ static int receive_SyncParam(struct drbd_connection *connection, struct packet_i
 			if (verify_tfm) {
 				strcpy(new_net_conf->verify_alg, p->verify_alg);
 				new_net_conf->verify_alg_len = strlen(p->verify_alg) + 1;
-				crypto_free_hash(peer_device->connection->verify_tfm);
+				crypto_free_ahash(peer_device->connection->verify_tfm);
 				peer_device->connection->verify_tfm = verify_tfm;
 				drbd_info(device, "using verify-alg: \"%s\"\n", p->verify_alg);
 			}
 			if (csums_tfm) {
 				strcpy(new_net_conf->csums_alg, p->csums_alg);
 				new_net_conf->csums_alg_len = strlen(p->csums_alg) + 1;
-				crypto_free_hash(peer_device->connection->csums_tfm);
+				crypto_free_ahash(peer_device->connection->csums_tfm);
 				peer_device->connection->csums_tfm = csums_tfm;
 				drbd_info(device, "using csums-alg: \"%s\"\n", p->csums_alg);
 			}
@@ -3729,9 +3729,9 @@ disconnect:
 	mutex_unlock(&connection->resource->conf_update);
 	/* just for completeness: actually not needed,
 	 * as this is not reached if csums_tfm was ok. */
-	crypto_free_hash(csums_tfm);
+	crypto_free_ahash(csums_tfm);
 	/* but free the verify_tfm again, if csums_tfm did not work out */
-	crypto_free_hash(verify_tfm);
+	crypto_free_ahash(verify_tfm);
 	conn_request_state(peer_device->connection, NS(conn, C_DISCONNECTING), CS_HARD);
 	return -EIO;
 }
@@ -4925,14 +4925,13 @@ static int drbd_do_auth(struct drbd_connection *connection)
 {
 	struct drbd_socket *sock;
 	char my_challenge[CHALLENGE_LEN];  /* 64 Bytes... */
-	struct scatterlist sg;
 	char *response = NULL;
 	char *right_response = NULL;
 	char *peers_ch = NULL;
 	unsigned int key_len;
 	char secret[SHARED_SECRET_MAX]; /* 64 byte */
 	unsigned int resp_size;
-	struct hash_desc desc;
+	SHASH_DESC_ON_STACK(desc, connection->cram_hmac_tfm);
 	struct packet_info pi;
 	struct net_conf *nc;
 	int err, rv;
@@ -4945,12 +4944,12 @@ static int drbd_do_auth(struct drbd_connection *connection)
 	memcpy(secret, nc->shared_secret, key_len);
 	rcu_read_unlock();
 
-	desc.tfm = connection->cram_hmac_tfm;
-	desc.flags = 0;
+	desc->tfm = connection->cram_hmac_tfm;
+	desc->flags = 0;
 
-	rv = crypto_hash_setkey(connection->cram_hmac_tfm, (u8 *)secret, key_len);
+	rv = crypto_shash_setkey(connection->cram_hmac_tfm, (u8 *)secret, key_len);
 	if (rv) {
-		drbd_err(connection, "crypto_hash_setkey() failed with %d\n", rv);
+		drbd_err(connection, "crypto_shash_setkey() failed with %d\n", rv);
 		rv = -1;
 		goto fail;
 	}
@@ -5011,7 +5010,7 @@ static int drbd_do_auth(struct drbd_connection *connection)
 		goto fail;
 	}
 
-	resp_size = crypto_hash_digestsize(connection->cram_hmac_tfm);
+	resp_size = crypto_shash_digestsize(connection->cram_hmac_tfm);
 	response = kmalloc(resp_size, GFP_NOIO);
 	if (response == NULL) {
 		drbd_err(connection, "kmalloc of response failed\n");
@@ -5019,10 +5018,7 @@ static int drbd_do_auth(struct drbd_connection *connection)
 		goto fail;
 	}
 
-	sg_init_table(&sg, 1);
-	sg_set_buf(&sg, peers_ch, pi.size);
-
-	rv = crypto_hash_digest(&desc, &sg, sg.length, response);
+	rv = crypto_shash_digest(desc, peers_ch, pi.size, response);
 	if (rv) {
 		drbd_err(connection, "crypto_hash_digest() failed with %d\n", rv);
 		rv = -1;
@@ -5070,9 +5066,8 @@ static int drbd_do_auth(struct drbd_connection *connection)
 		goto fail;
 	}
 
-	sg_set_buf(&sg, my_challenge, CHALLENGE_LEN);
-
-	rv = crypto_hash_digest(&desc, &sg, sg.length, right_response);
+	rv = crypto_shash_digest(desc, my_challenge, CHALLENGE_LEN,
+				 right_response);
 	if (rv) {
 		drbd_err(connection, "crypto_hash_digest() failed with %d\n", rv);
 		rv = -1;
@@ -5091,6 +5086,7 @@ static int drbd_do_auth(struct drbd_connection *connection)
 	kfree(peers_ch);
 	kfree(response);
 	kfree(right_response);
+	shash_desc_zero(desc);
 
 	return rv;
 }
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index eff716c27b1f..4d87499f0d54 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -274,51 +274,56 @@ void drbd_request_endio(struct bio *bio)
 		complete_master_bio(device, &m);
 }
 
-void drbd_csum_ee(struct crypto_hash *tfm, struct drbd_peer_request *peer_req, void *digest)
+void drbd_csum_ee(struct crypto_ahash *tfm, struct drbd_peer_request *peer_req, void *digest)
 {
-	struct hash_desc desc;
+	AHASH_REQUEST_ON_STACK(req, tfm);
 	struct scatterlist sg;
 	struct page *page = peer_req->pages;
 	struct page *tmp;
 	unsigned len;
 
-	desc.tfm = tfm;
-	desc.flags = 0;
+	ahash_request_set_tfm(req, tfm);
+	ahash_request_set_callback(req, 0, NULL, NULL);
 
 	sg_init_table(&sg, 1);
-	crypto_hash_init(&desc);
+	crypto_ahash_init(req);
 
 	while ((tmp = page_chain_next(page))) {
 		/* all but the last page will be fully used */
 		sg_set_page(&sg, page, PAGE_SIZE, 0);
-		crypto_hash_update(&desc, &sg, sg.length);
+		ahash_request_set_crypt(req, &sg, NULL, sg.length);
+		crypto_ahash_update(req);
 		page = tmp;
 	}
 	/* and now the last, possibly only partially used page */
 	len = peer_req->i.size & (PAGE_SIZE - 1);
 	sg_set_page(&sg, page, len ?: PAGE_SIZE, 0);
-	crypto_hash_update(&desc, &sg, sg.length);
-	crypto_hash_final(&desc, digest);
+	ahash_request_set_crypt(req, &sg, digest, sg.length);
+	crypto_ahash_finup(req);
+	ahash_request_zero(req);
 }
 
-void drbd_csum_bio(struct crypto_hash *tfm, struct bio *bio, void *digest)
+void drbd_csum_bio(struct crypto_ahash *tfm, struct bio *bio, void *digest)
 {
-	struct hash_desc desc;
+	AHASH_REQUEST_ON_STACK(req, tfm);
 	struct scatterlist sg;
 	struct bio_vec bvec;
 	struct bvec_iter iter;
 
-	desc.tfm = tfm;
-	desc.flags = 0;
+	ahash_request_set_tfm(req, tfm);
+	ahash_request_set_callback(req, 0, NULL, NULL);
 
 	sg_init_table(&sg, 1);
-	crypto_hash_init(&desc);
+	crypto_ahash_init(req);
 
 	bio_for_each_segment(bvec, bio, iter) {
 		sg_set_page(&sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset);
-		crypto_hash_update(&desc, &sg, sg.length);
+		ahash_request_set_crypt(req, &sg, NULL, sg.length);
+		crypto_ahash_update(req);
 	}
-	crypto_hash_final(&desc, digest);
+	ahash_request_set_crypt(req, NULL, digest, 0);
+	crypto_ahash_final(req);
+	ahash_request_zero(req);
 }
 
 /* MAYBE merge common code with w_e_end_ov_req */
@@ -337,7 +342,7 @@ static int w_e_send_csum(struct drbd_work *w, int cancel)
 	if (unlikely((peer_req->flags & EE_WAS_ERROR) != 0))
 		goto out;
 
-	digest_size = crypto_hash_digestsize(peer_device->connection->csums_tfm);
+	digest_size = crypto_ahash_digestsize(peer_device->connection->csums_tfm);
 	digest = kmalloc(digest_size, GFP_NOIO);
 	if (digest) {
 		sector_t sector = peer_req->i.sector;
@@ -1113,7 +1118,7 @@ int w_e_end_csum_rs_req(struct drbd_work *w, int cancel)
 		 * a real fix would be much more involved,
 		 * introducing more locking mechanisms */
 		if (peer_device->connection->csums_tfm) {
-			digest_size = crypto_hash_digestsize(peer_device->connection->csums_tfm);
+			digest_size = crypto_ahash_digestsize(peer_device->connection->csums_tfm);
 			D_ASSERT(device, digest_size == di->digest_size);
 			digest = kmalloc(digest_size, GFP_NOIO);
 		}
@@ -1163,7 +1168,7 @@ int w_e_end_ov_req(struct drbd_work *w, int cancel)
 	if (unlikely(cancel))
 		goto out;
 
-	digest_size = crypto_hash_digestsize(peer_device->connection->verify_tfm);
+	digest_size = crypto_ahash_digestsize(peer_device->connection->verify_tfm);
 	digest = kmalloc(digest_size, GFP_NOIO);
 	if (!digest) {
 		err = 1;	/* terminate the connection in case the allocation failed */
@@ -1235,7 +1240,7 @@ int w_e_end_ov_reply(struct drbd_work *w, int cancel)
 	di = peer_req->digest;
 
 	if (likely((peer_req->flags & EE_WAS_ERROR) == 0)) {
-		digest_size = crypto_hash_digestsize(peer_device->connection->verify_tfm);
+		digest_size = crypto_ahash_digestsize(peer_device->connection->verify_tfm);
 		digest = kmalloc(digest_size, GFP_NOIO);
 		if (digest) {
 			drbd_csum_ee(peer_device->connection->verify_tfm, peer_req, digest);
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 9e251201dd48..84708a5f8c52 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -866,7 +866,7 @@ static void set_fdc(int drive)
 }
 
 /* locks the driver */
-static int lock_fdc(int drive, bool interruptible)
+static int lock_fdc(int drive)
 {
 	if (WARN(atomic_read(&usage_count) == 0,
 		 "Trying to lock fdc while usage count=0\n"))
@@ -2173,7 +2173,7 @@ static int do_format(int drive, struct format_descr *tmp_format_req)
 {
 	int ret;
 
-	if (lock_fdc(drive, true))
+	if (lock_fdc(drive))
 		return -EINTR;
 
 	set_floppy(drive);
@@ -2960,7 +2960,7 @@ static int user_reset_fdc(int drive, int arg, bool interruptible)
 {
 	int ret;
 
-	if (lock_fdc(drive, interruptible))
+	if (lock_fdc(drive))
 		return -EINTR;
 
 	if (arg == FD_RESET_ALWAYS)
@@ -3243,7 +3243,7 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g,
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 		mutex_lock(&open_lock);
-		if (lock_fdc(drive, true)) {
+		if (lock_fdc(drive)) {
 			mutex_unlock(&open_lock);
 			return -EINTR;
 		}
@@ -3263,7 +3263,7 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g,
 	} else {
 		int oldStretch;
 
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		if (cmd != FDDEFPRM) {
 			/* notice a disk change immediately, else
@@ -3349,7 +3349,7 @@ static int get_floppy_geometry(int drive, int type, struct floppy_struct **g)
 	if (type)
 		*g = &floppy_type[type];
 	else {
-		if (lock_fdc(drive, false))
+		if (lock_fdc(drive))
 			return -EINTR;
 		if (poll_drive(false, 0) == -EINTR)
 			return -EINTR;
@@ -3433,7 +3433,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		if (UDRS->fd_ref != 1)
 			/* somebody else has this drive open */
 			return -EBUSY;
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 
 		/* do the actual eject. Fails on
@@ -3445,7 +3445,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		process_fd_request();
 		return ret;
 	case FDCLRPRM:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		current_type[drive] = NULL;
 		floppy_sizes[drive] = MAX_DISK_SIZE << 1;
@@ -3467,7 +3467,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		UDP->flags &= ~FTD_MSG;
 		return 0;
 	case FDFMTBEG:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		if (poll_drive(true, FD_RAW_NEED_DISK) == -EINTR)
 			return -EINTR;
@@ -3484,7 +3484,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		return do_format(drive, &inparam.f);
 	case FDFMTEND:
 	case FDFLUSH:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		return invalidate_drive(bdev);
 	case FDSETEMSGTRESH:
@@ -3507,7 +3507,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		outparam = UDP;
 		break;
 	case FDPOLLDRVSTAT:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		if (poll_drive(true, FD_RAW_NEED_DISK) == -EINTR)
 			return -EINTR;
@@ -3530,7 +3530,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 	case FDRAWCMD:
 		if (type)
 			return -EINVAL;
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		set_floppy(drive);
 		i = raw_cmd_ioctl(cmd, (void __user *)param);
@@ -3539,7 +3539,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 		process_fd_request();
 		return i;
 	case FDTWADDLE:
-		if (lock_fdc(drive, true))
+		if (lock_fdc(drive))
 			return -EINTR;
 		twaddle();
 		process_fd_request();
@@ -3663,6 +3663,11 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 
 	opened_bdev[drive] = bdev;
 
+	if (!(mode & (FMODE_READ|FMODE_WRITE))) {
+		res = -EINVAL;
+		goto out;
+	}
+
 	res = -ENXIO;
 
 	if (!floppy_track_buffer) {
@@ -3706,21 +3711,20 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 	if (UFDCS->rawcmd == 1)
 		UFDCS->rawcmd = 2;
 
-	if (!(mode & FMODE_NDELAY)) {
-		if (mode & (FMODE_READ|FMODE_WRITE)) {
-			UDRS->last_checked = 0;
-			clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
-			check_disk_change(bdev);
-			if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags))
-				goto out;
-			if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags))
-				goto out;
-		}
-		res = -EROFS;
-		if ((mode & FMODE_WRITE) &&
-		    !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags))
-			goto out;
-	}
+	UDRS->last_checked = 0;
+	clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
+	check_disk_change(bdev);
+	if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags))
+		goto out;
+	if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags))
+		goto out;
+
+	res = -EROFS;
+
+	if ((mode & FMODE_WRITE) &&
+			!test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags))
+		goto out;
+
 	mutex_unlock(&open_lock);
 	mutex_unlock(&floppy_mutex);
 	return 0;
@@ -3748,7 +3752,8 @@ static unsigned int floppy_check_events(struct gendisk *disk,
 		return DISK_EVENT_MEDIA_CHANGE;
 
 	if (time_after(jiffies, UDRS->last_checked + UDP->checkfreq)) {
-		lock_fdc(drive, false);
+		if (lock_fdc(drive))
+			return -EINTR;
 		poll_drive(false, 0);
 		process_fd_request();
 	}
@@ -3847,7 +3852,9 @@ static int floppy_revalidate(struct gendisk *disk)
 			 "VFS: revalidate called on non-open device.\n"))
 			return -EFAULT;
 
-		lock_fdc(drive, false);
+		res = lock_fdc(drive);
+		if (res)
+			return res;
 		cf = (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags) ||
 		      test_bit(FD_VERIFY_BIT, &UDRS->flags));
 		if (!(cf || test_bit(drive, &fake_change) || drive_no_geom(drive))) {
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 8ba1e97d573c..64a7b5971b57 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -478,7 +478,7 @@ static int null_lnvm_id(struct nvm_dev *dev, struct nvm_id *id)
 	id->ver_id = 0x1;
 	id->vmnt = 0;
 	id->cgrps = 1;
-	id->cap = 0x3;
+	id->cap = 0x2;
 	id->dom = 0x1;
 
 	id->ppaf.blk_offset = 0;
@@ -707,9 +707,7 @@ static int null_add_dev(void)
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, nullb->q);
 	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, nullb->q);
 
-
 	mutex_lock(&lock);
-	list_add_tail(&nullb->list, &nullb_list);
 	nullb->index = nullb_indexes++;
 	mutex_unlock(&lock);
 
@@ -743,6 +741,10 @@ static int null_add_dev(void)
 	strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
 
 	add_disk(disk);
+
+	mutex_lock(&lock);
+	list_add_tail(&nullb->list, &nullb_list);
+	mutex_unlock(&lock);
 done:
 	return 0;
 
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 562b5a4ca7b7..78a39f736c64 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -126,7 +126,7 @@
 */
 #include <linux/types.h>
 
-static bool verbose = 0;
+static int verbose = 0;
 static int major = PD_MAJOR;
 static char *name = PD_NAME;
 static int cluster = 64;
@@ -161,7 +161,7 @@ enum {D_PRT, D_PRO, D_UNI, D_MOD, D_GEO, D_SBY, D_DLY, D_SLV};
 static DEFINE_MUTEX(pd_mutex);
 static DEFINE_SPINLOCK(pd_lock);
 
-module_param(verbose, bool, 0);
+module_param(verbose, int, 0);
 module_param(major, int, 0);
 module_param(name, charp, 0);
 module_param(cluster, int, 0);
diff --git a/drivers/block/paride/pt.c b/drivers/block/paride/pt.c
index 1740d75e8a32..216a94fed5b4 100644
--- a/drivers/block/paride/pt.c
+++ b/drivers/block/paride/pt.c
@@ -117,7 +117,7 @@
 
 */
 
-static bool verbose = 0;
+static int verbose = 0;
 static int major = PT_MAJOR;
 static char *name = PT_NAME;
 static int disable = 0;
@@ -152,7 +152,7 @@ static int (*drives[4])[6] = {&drive0, &drive1, &drive2, &drive3};
 
 #include <asm/uaccess.h>
 
-module_param(verbose, bool, 0);
+module_param(verbose, int, 0);
 module_param(major, int, 0);
 module_param(name, charp, 0);
 module_param_array(drive0, int, NULL, 0);
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 8a8dc91c39f7..83eb9e6bf8b0 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1873,6 +1873,43 @@ again:
 	return err;
 }
 
+static int negotiate_mq(struct blkfront_info *info)
+{
+	unsigned int backend_max_queues = 0;
+	int err;
+	unsigned int i;
+
+	BUG_ON(info->nr_rings);
+
+	/* Check if backend supports multiple queues. */
+	err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
+			   "multi-queue-max-queues", "%u", &backend_max_queues);
+	if (err < 0)
+		backend_max_queues = 1;
+
+	info->nr_rings = min(backend_max_queues, xen_blkif_max_queues);
+	/* We need at least one ring. */
+	if (!info->nr_rings)
+		info->nr_rings = 1;
+
+	info->rinfo = kzalloc(sizeof(struct blkfront_ring_info) * info->nr_rings, GFP_KERNEL);
+	if (!info->rinfo) {
+		xenbus_dev_fatal(info->xbdev, -ENOMEM, "allocating ring_info structure");
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < info->nr_rings; i++) {
+		struct blkfront_ring_info *rinfo;
+
+		rinfo = &info->rinfo[i];
+		INIT_LIST_HEAD(&rinfo->indirect_pages);
+		INIT_LIST_HEAD(&rinfo->grants);
+		rinfo->dev_info = info;
+		INIT_WORK(&rinfo->work, blkif_restart_queue);
+		spin_lock_init(&rinfo->ring_lock);
+	}
+	return 0;
+}
 /**
  * Entry point to this code when a new device is created.  Allocate the basic
  * structures and the ring buffer for communication with the backend, and
@@ -1883,9 +1920,7 @@ static int blkfront_probe(struct xenbus_device *dev,
 			  const struct xenbus_device_id *id)
 {
 	int err, vdevice;
-	unsigned int r_index;
 	struct blkfront_info *info;
-	unsigned int backend_max_queues = 0;
 
 	/* FIXME: Use dynamic device id if this is not set. */
 	err = xenbus_scanf(XBT_NIL, dev->nodename,
@@ -1936,33 +1971,10 @@ static int blkfront_probe(struct xenbus_device *dev,
 	}
 
 	info->xbdev = dev;
-	/* Check if backend supports multiple queues. */
-	err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
-			   "multi-queue-max-queues", "%u", &backend_max_queues);
-	if (err < 0)
-		backend_max_queues = 1;
-
-	info->nr_rings = min(backend_max_queues, xen_blkif_max_queues);
-	/* We need at least one ring. */
-	if (!info->nr_rings)
-		info->nr_rings = 1;
-
-	info->rinfo = kzalloc(sizeof(struct blkfront_ring_info) * info->nr_rings, GFP_KERNEL);
-	if (!info->rinfo) {
-		xenbus_dev_fatal(dev, -ENOMEM, "allocating ring_info structure");
+	err = negotiate_mq(info);
+	if (err) {
 		kfree(info);
-		return -ENOMEM;
-	}
-
-	for (r_index = 0; r_index < info->nr_rings; r_index++) {
-		struct blkfront_ring_info *rinfo;
-
-		rinfo = &info->rinfo[r_index];
-		INIT_LIST_HEAD(&rinfo->indirect_pages);
-		INIT_LIST_HEAD(&rinfo->grants);
-		rinfo->dev_info = info;
-		INIT_WORK(&rinfo->work, blkif_restart_queue);
-		spin_lock_init(&rinfo->ring_lock);
+		return err;
 	}
 
 	mutex_init(&info->mutex);
@@ -2123,12 +2135,16 @@ static int blkif_recover(struct blkfront_info *info)
 static int blkfront_resume(struct xenbus_device *dev)
 {
 	struct blkfront_info *info = dev_get_drvdata(&dev->dev);
-	int err;
+	int err = 0;
 
 	dev_dbg(&dev->dev, "blkfront_resume: %s\n", dev->nodename);
 
 	blkif_free(info, info->connected == BLKIF_STATE_CONNECTED);
 
+	err = negotiate_mq(info);
+	if (err)
+		return err;
+
 	err = talk_to_blkback(dev, info);
 
 	/*
diff --git a/drivers/char/agp/uninorth-agp.c b/drivers/char/agp/uninorth-agp.c
index 05755441250c..fdced547ad59 100644
--- a/drivers/char/agp/uninorth-agp.c
+++ b/drivers/char/agp/uninorth-agp.c
@@ -10,7 +10,6 @@
 #include <linux/delay.h>
 #include <linux/vmalloc.h>
 #include <asm/uninorth.h>
-#include <asm/pci-bridge.h>
 #include <asm/prom.h>
 #include <asm/pmac_feature.h>
 #include "agp.h"
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index 240b6cf1d97c..be54e5331a45 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -42,7 +42,7 @@
 /*
  * The High Precision Event Timer driver.
  * This driver is closely modelled after the rtc.c driver.
- * http://www.intel.com/hardwaredesign/hpetspec_1.pdf
+ * See HPET spec revision 1.
  */
 #define	HPET_USER_FREQ	(64)
 #define	HPET_DRIFT	(500)
diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index ff00331bff49..67ee8b08ab53 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -77,7 +77,7 @@ config HW_RANDOM_ATMEL
 
 config HW_RANDOM_BCM63XX
 	tristate "Broadcom BCM63xx Random Number Generator support"
-	depends on BCM63XX
+	depends on BCM63XX || BMIPS_GENERIC
 	default HW_RANDOM
 	---help---
 	  This driver provides kernel-side support for the Random Number
@@ -382,6 +382,19 @@ config HW_RANDOM_STM32
 
 	  If unsure, say N.
 
+config HW_RANDOM_PIC32
+	tristate "Microchip PIC32 Random Number Generator support"
+	depends on HW_RANDOM && MACH_PIC32
+	default y
+	---help---
+	  This driver provides kernel-side support for the Random Number
+	  Generator hardware found on a PIC32.
+
+	  To compile this driver as a module, choose M here. the
+	  module will be called pic32-rng.
+
+	  If unsure, say Y.
+
 endif # HW_RANDOM
 
 config UML_RANDOM
diff --git a/drivers/char/hw_random/Makefile b/drivers/char/hw_random/Makefile
index 5ad397635128..f5a6fa7690e7 100644
--- a/drivers/char/hw_random/Makefile
+++ b/drivers/char/hw_random/Makefile
@@ -33,3 +33,4 @@ obj-$(CONFIG_HW_RANDOM_MSM) += msm-rng.o
 obj-$(CONFIG_HW_RANDOM_ST) += st-rng.o
 obj-$(CONFIG_HW_RANDOM_XGENE) += xgene-rng.o
 obj-$(CONFIG_HW_RANDOM_STM32) += stm32-rng.o
+obj-$(CONFIG_HW_RANDOM_PIC32) += pic32-rng.o
diff --git a/drivers/char/hw_random/bcm63xx-rng.c b/drivers/char/hw_random/bcm63xx-rng.c
index 4b31f1387f37..ca9c40309757 100644
--- a/drivers/char/hw_random/bcm63xx-rng.c
+++ b/drivers/char/hw_random/bcm63xx-rng.c
@@ -79,10 +79,8 @@ static int bcm63xx_rng_data_read(struct hwrng *rng, u32 *data)
 static int bcm63xx_rng_probe(struct platform_device *pdev)
 {
 	struct resource *r;
-	struct clk *clk;
 	int ret;
 	struct bcm63xx_rng_priv *priv;
-	struct hwrng *rng;
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!r) {
@@ -132,10 +130,19 @@ static int bcm63xx_rng_probe(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_OF
+static const struct of_device_id bcm63xx_rng_of_match[] = {
+	{ .compatible = "brcm,bcm6368-rng", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, bcm63xx_rng_of_match);
+#endif
+
 static struct platform_driver bcm63xx_rng_driver = {
 	.probe		= bcm63xx_rng_probe,
 	.driver		= {
 		.name	= "bcm63xx-rng",
+		.of_match_table = of_match_ptr(bcm63xx_rng_of_match),
 	},
 };
 
diff --git a/drivers/char/hw_random/exynos-rng.c b/drivers/char/hw_random/exynos-rng.c
index 30cf4623184f..ada081232528 100644
--- a/drivers/char/hw_random/exynos-rng.c
+++ b/drivers/char/hw_random/exynos-rng.c
@@ -144,8 +144,7 @@ static int exynos_rng_probe(struct platform_device *pdev)
 	return devm_hwrng_register(&pdev->dev, &exynos_rng->rng);
 }
 
-#ifdef CONFIG_PM
-static int exynos_rng_runtime_suspend(struct device *dev)
+static int __maybe_unused exynos_rng_runtime_suspend(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct exynos_rng *exynos_rng = platform_get_drvdata(pdev);
@@ -155,7 +154,7 @@ static int exynos_rng_runtime_suspend(struct device *dev)
 	return 0;
 }
 
-static int exynos_rng_runtime_resume(struct device *dev)
+static int __maybe_unused exynos_rng_runtime_resume(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct exynos_rng *exynos_rng = platform_get_drvdata(pdev);
@@ -163,12 +162,12 @@ static int exynos_rng_runtime_resume(struct device *dev)
 	return clk_prepare_enable(exynos_rng->clk);
 }
 
-static int exynos_rng_suspend(struct device *dev)
+static int __maybe_unused exynos_rng_suspend(struct device *dev)
 {
 	return pm_runtime_force_suspend(dev);
 }
 
-static int exynos_rng_resume(struct device *dev)
+static int __maybe_unused exynos_rng_resume(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct exynos_rng *exynos_rng = platform_get_drvdata(pdev);
@@ -180,7 +179,6 @@ static int exynos_rng_resume(struct device *dev)
 
 	return exynos_rng_configure(exynos_rng);
 }
-#endif
 
 static const struct dev_pm_ops exynos_rng_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(exynos_rng_suspend, exynos_rng_resume)
diff --git a/drivers/char/hw_random/n2-drv.c b/drivers/char/hw_random/n2-drv.c
index 843d6f6aee7a..3b06c1d6cfb2 100644
--- a/drivers/char/hw_random/n2-drv.c
+++ b/drivers/char/hw_random/n2-drv.c
@@ -743,6 +743,16 @@ static const struct of_device_id n2rng_match[] = {
 		.compatible	= "SUNW,kt-rng",
 		.data		= (void *) 1,
 	},
+	{
+		.name		= "random-number-generator",
+		.compatible	= "ORCL,m4-rng",
+		.data		= (void *) 1,
+	},
+	{
+		.name		= "random-number-generator",
+		.compatible	= "ORCL,m7-rng",
+		.data		= (void *) 1,
+	},
 	{},
 };
 MODULE_DEVICE_TABLE(of, n2rng_match);
diff --git a/drivers/char/hw_random/pic32-rng.c b/drivers/char/hw_random/pic32-rng.c
new file mode 100644
index 000000000000..108897bea2d0
--- /dev/null
+++ b/drivers/char/hw_random/pic32-rng.c
@@ -0,0 +1,155 @@
+/*
+ * PIC32 RNG driver
+ *
+ * Joshua Henderson <joshua.henderson@microchip.com>
+ * Copyright (C) 2016 Microchip Technology Inc.  All rights reserved.
+ *
+ * This program is free software; you can distribute it and/or modify it
+ * under the terms of the GNU General Public License (Version 2) as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ * for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/err.h>
+#include <linux/hw_random.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#define RNGCON		0x04
+#define  TRNGEN		BIT(8)
+#define  PRNGEN		BIT(9)
+#define  PRNGCONT	BIT(10)
+#define  TRNGMOD	BIT(11)
+#define  SEEDLOAD	BIT(12)
+#define RNGPOLY1	0x08
+#define RNGPOLY2	0x0C
+#define RNGNUMGEN1	0x10
+#define RNGNUMGEN2	0x14
+#define RNGSEED1	0x18
+#define RNGSEED2	0x1C
+#define RNGRCNT		0x20
+#define  RCNT_MASK	0x7F
+
+struct pic32_rng {
+	void __iomem	*base;
+	struct hwrng	rng;
+	struct clk	*clk;
+};
+
+/*
+ * The TRNG can generate up to 24Mbps. This is a timeout that should be safe
+ * enough given the instructions in the loop and that the TRNG may not always
+ * be at maximum rate.
+ */
+#define RNG_TIMEOUT 500
+
+static int pic32_rng_read(struct hwrng *rng, void *buf, size_t max,
+			  bool wait)
+{
+	struct pic32_rng *priv = container_of(rng, struct pic32_rng, rng);
+	u64 *data = buf;
+	u32 t;
+	unsigned int timeout = RNG_TIMEOUT;
+
+	if (max < 8)
+		return 0;
+
+	do {
+		t = readl(priv->base + RNGRCNT) & RCNT_MASK;
+		if (t == 64) {
+			/* TRNG value comes through the seed registers */
+			*data = ((u64)readl(priv->base + RNGSEED2) << 32) +
+				readl(priv->base + RNGSEED1);
+			return 8;
+		}
+	} while (wait && --timeout);
+
+	return -EIO;
+}
+
+static int pic32_rng_probe(struct platform_device *pdev)
+{
+	struct pic32_rng *priv;
+	struct resource *res;
+	u32 v;
+	int ret;
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(priv->base))
+		return PTR_ERR(priv->base);
+
+	priv->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(priv->clk))
+		return PTR_ERR(priv->clk);
+
+	ret = clk_prepare_enable(priv->clk);
+	if (ret)
+		return ret;
+
+	/* enable TRNG in enhanced mode */
+	v = TRNGEN | TRNGMOD;
+	writel(v, priv->base + RNGCON);
+
+	priv->rng.name = pdev->name;
+	priv->rng.read = pic32_rng_read;
+
+	ret = hwrng_register(&priv->rng);
+	if (ret)
+		goto err_register;
+
+	platform_set_drvdata(pdev, priv);
+
+	return 0;
+
+err_register:
+	clk_disable_unprepare(priv->clk);
+	return ret;
+}
+
+static int pic32_rng_remove(struct platform_device *pdev)
+{
+	struct pic32_rng *rng = platform_get_drvdata(pdev);
+
+	hwrng_unregister(&rng->rng);
+	writel(0, rng->base + RNGCON);
+	clk_disable_unprepare(rng->clk);
+	return 0;
+}
+
+static const struct of_device_id pic32_rng_of_match[] = {
+	{ .compatible	= "microchip,pic32mzda-rng", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, pic32_rng_of_match);
+
+static struct platform_driver pic32_rng_driver = {
+	.probe		= pic32_rng_probe,
+	.remove		= pic32_rng_remove,
+	.driver		= {
+		.name	= "pic32-rng",
+		.owner	= THIS_MODULE,
+		.of_match_table = of_match_ptr(pic32_rng_of_match),
+	},
+};
+
+module_platform_driver(pic32_rng_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Joshua Henderson <joshua.henderson@microchip.com>");
+MODULE_DESCRIPTION("Microchip PIC32 RNG Driver");
diff --git a/drivers/char/random.c b/drivers/char/random.c
index d0da5d852d41..b583e5336630 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1819,6 +1819,28 @@ unsigned int get_random_int(void)
 EXPORT_SYMBOL(get_random_int);
 
 /*
+ * Same as get_random_int(), but returns unsigned long.
+ */
+unsigned long get_random_long(void)
+{
+	__u32 *hash;
+	unsigned long ret;
+
+	if (arch_get_random_long(&ret))
+		return ret;
+
+	hash = get_cpu_var(get_random_int_hash);
+
+	hash[0] += current->pid + jiffies + random_get_entropy();
+	md5_transform(hash, random_int_secret);
+	ret = *(unsigned long *)hash;
+	put_cpu_var(get_random_int_hash);
+
+	return ret;
+}
+EXPORT_SYMBOL(get_random_long);
+
+/*
  * randomize_range() returns a start address such that
  *
  *    [...... <range> .....]
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index b038e3666058..bae4be6501df 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -43,7 +43,7 @@ obj-$(CONFIG_COMMON_CLK_SI514)		+= clk-si514.o
 obj-$(CONFIG_COMMON_CLK_SI570)		+= clk-si570.o
 obj-$(CONFIG_COMMON_CLK_CDCE925)	+= clk-cdce925.o
 obj-$(CONFIG_ARCH_STM32)		+= clk-stm32f4.o
-obj-$(CONFIG_ARCH_TANGOX)		+= clk-tango4.o
+obj-$(CONFIG_ARCH_TANGO)		+= clk-tango4.o
 obj-$(CONFIG_CLK_TWL6040)		+= clk-twl6040.o
 obj-$(CONFIG_ARCH_U300)			+= clk-u300.o
 obj-$(CONFIG_ARCH_VT8500)		+= clk-vt8500.o
diff --git a/drivers/clk/clk-gpio.c b/drivers/clk/clk-gpio.c
index 19fed65587e8..7b09a265d79f 100644
--- a/drivers/clk/clk-gpio.c
+++ b/drivers/clk/clk-gpio.c
@@ -289,7 +289,7 @@ static void __init of_gpio_clk_setup(struct device_node *node,
 
 	num_parents = of_clk_get_parent_count(node);
 	if (num_parents < 0)
-		return;
+		num_parents = 0;
 
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
diff --git a/drivers/clk/clk-scpi.c b/drivers/clk/clk-scpi.c
index cd0f2726f5e0..89e9ca78bb94 100644
--- a/drivers/clk/clk-scpi.c
+++ b/drivers/clk/clk-scpi.c
@@ -299,7 +299,7 @@ static int scpi_clocks_probe(struct platform_device *pdev)
 	/* Add the virtual cpufreq device */
 	cpufreq_dev = platform_device_register_simple("scpi-cpufreq",
 						      -1, NULL, 0);
-	if (!cpufreq_dev)
+	if (IS_ERR(cpufreq_dev))
 		pr_warn("unable to register cpufreq device");
 
 	return 0;
diff --git a/drivers/clk/mvebu/dove-divider.c b/drivers/clk/mvebu/dove-divider.c
index d5c5bfa35a5a..3e0b52daa35f 100644
--- a/drivers/clk/mvebu/dove-divider.c
+++ b/drivers/clk/mvebu/dove-divider.c
@@ -247,7 +247,7 @@ static struct clk_onecell_data dove_divider_data = {
 
 void __init dove_divider_clk_init(struct device_node *np)
 {
-	void *base;
+	void __iomem *base;
 
 	base = of_iomap(np, 0);
 	if (WARN_ON(!base))
diff --git a/drivers/clk/qcom/gcc-apq8084.c b/drivers/clk/qcom/gcc-apq8084.c
index cf73e539e9f6..070037a29ea5 100644
--- a/drivers/clk/qcom/gcc-apq8084.c
+++ b/drivers/clk/qcom/gcc-apq8084.c
@@ -3587,7 +3587,6 @@ static const struct regmap_config gcc_apq8084_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x1fc0,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc gcc_apq8084_desc = {
diff --git a/drivers/clk/qcom/gcc-ipq806x.c b/drivers/clk/qcom/gcc-ipq806x.c
index b692ae881d6a..dd5402bac620 100644
--- a/drivers/clk/qcom/gcc-ipq806x.c
+++ b/drivers/clk/qcom/gcc-ipq806x.c
@@ -3005,7 +3005,6 @@ static const struct regmap_config gcc_ipq806x_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x3e40,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc gcc_ipq806x_desc = {
diff --git a/drivers/clk/qcom/gcc-msm8660.c b/drivers/clk/qcom/gcc-msm8660.c
index f6a2b14dfec4..ad413036f7c7 100644
--- a/drivers/clk/qcom/gcc-msm8660.c
+++ b/drivers/clk/qcom/gcc-msm8660.c
@@ -2702,7 +2702,6 @@ static const struct regmap_config gcc_msm8660_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x363c,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc gcc_msm8660_desc = {
diff --git a/drivers/clk/qcom/gcc-msm8916.c b/drivers/clk/qcom/gcc-msm8916.c
index e3bf09d7d0ef..8cc9b2868b41 100644
--- a/drivers/clk/qcom/gcc-msm8916.c
+++ b/drivers/clk/qcom/gcc-msm8916.c
@@ -3336,7 +3336,6 @@ static const struct regmap_config gcc_msm8916_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x80000,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc gcc_msm8916_desc = {
diff --git a/drivers/clk/qcom/gcc-msm8960.c b/drivers/clk/qcom/gcc-msm8960.c
index f31111e32d44..983dd7dc89a7 100644
--- a/drivers/clk/qcom/gcc-msm8960.c
+++ b/drivers/clk/qcom/gcc-msm8960.c
@@ -3468,7 +3468,6 @@ static const struct regmap_config gcc_msm8960_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x3660,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct regmap_config gcc_apq8064_regmap_config = {
@@ -3477,7 +3476,6 @@ static const struct regmap_config gcc_apq8064_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x3880,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc gcc_msm8960_desc = {
diff --git a/drivers/clk/qcom/gcc-msm8974.c b/drivers/clk/qcom/gcc-msm8974.c
index df164d618e34..335952db309b 100644
--- a/drivers/clk/qcom/gcc-msm8974.c
+++ b/drivers/clk/qcom/gcc-msm8974.c
@@ -2680,7 +2680,6 @@ static const struct regmap_config gcc_msm8974_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x1fc0,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc gcc_msm8974_desc = {
diff --git a/drivers/clk/qcom/lcc-ipq806x.c b/drivers/clk/qcom/lcc-ipq806x.c
index 62e79fadd5f7..db3998e5e2d8 100644
--- a/drivers/clk/qcom/lcc-ipq806x.c
+++ b/drivers/clk/qcom/lcc-ipq806x.c
@@ -419,7 +419,6 @@ static const struct regmap_config lcc_ipq806x_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0xfc,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc lcc_ipq806x_desc = {
diff --git a/drivers/clk/qcom/lcc-msm8960.c b/drivers/clk/qcom/lcc-msm8960.c
index bf95bb0ea1b8..4fcf9d1d233c 100644
--- a/drivers/clk/qcom/lcc-msm8960.c
+++ b/drivers/clk/qcom/lcc-msm8960.c
@@ -524,7 +524,6 @@ static const struct regmap_config lcc_msm8960_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0xfc,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc lcc_msm8960_desc = {
diff --git a/drivers/clk/qcom/mmcc-apq8084.c b/drivers/clk/qcom/mmcc-apq8084.c
index 1e703fda8a0f..30777f9f1a43 100644
--- a/drivers/clk/qcom/mmcc-apq8084.c
+++ b/drivers/clk/qcom/mmcc-apq8084.c
@@ -3368,7 +3368,6 @@ static const struct regmap_config mmcc_apq8084_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x5104,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc mmcc_apq8084_desc = {
diff --git a/drivers/clk/qcom/mmcc-msm8960.c b/drivers/clk/qcom/mmcc-msm8960.c
index d73a048d3b9d..00e36192a1de 100644
--- a/drivers/clk/qcom/mmcc-msm8960.c
+++ b/drivers/clk/qcom/mmcc-msm8960.c
@@ -3029,7 +3029,6 @@ static const struct regmap_config mmcc_msm8960_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x334,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct regmap_config mmcc_apq8064_regmap_config = {
@@ -3038,7 +3037,6 @@ static const struct regmap_config mmcc_apq8064_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x350,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc mmcc_msm8960_desc = {
diff --git a/drivers/clk/qcom/mmcc-msm8974.c b/drivers/clk/qcom/mmcc-msm8974.c
index bbe28ed93669..9d790bcadf25 100644
--- a/drivers/clk/qcom/mmcc-msm8974.c
+++ b/drivers/clk/qcom/mmcc-msm8974.c
@@ -2594,7 +2594,6 @@ static const struct regmap_config mmcc_msm8974_regmap_config = {
 	.val_bits	= 32,
 	.max_register	= 0x5104,
 	.fast_io	= true,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static const struct qcom_cc_desc mmcc_msm8974_desc = {
diff --git a/drivers/clk/rockchip/clk-rk3036.c b/drivers/clk/rockchip/clk-rk3036.c
index ebce98033fbb..bc7fbac83ab7 100644
--- a/drivers/clk/rockchip/clk-rk3036.c
+++ b/drivers/clk/rockchip/clk-rk3036.c
@@ -133,7 +133,7 @@ PNAME(mux_spdif_p)	= { "spdif_src", "spdif_frac", "xin12m" };
 PNAME(mux_uart0_p)	= { "uart0_src", "uart0_frac", "xin24m" };
 PNAME(mux_uart1_p)	= { "uart1_src", "uart1_frac", "xin24m" };
 PNAME(mux_uart2_p)	= { "uart2_src", "uart2_frac", "xin24m" };
-PNAME(mux_mac_p)	= { "mac_pll_src", "ext_gmac" };
+PNAME(mux_mac_p)	= { "mac_pll_src", "rmii_clkin" };
 PNAME(mux_dclk_p)	= { "dclk_lcdc", "dclk_cru" };
 
 static struct rockchip_pll_clock rk3036_pll_clks[] __initdata = {
@@ -224,16 +224,16 @@ static struct rockchip_clk_branch rk3036_clk_branches[] __initdata = {
 			RK2928_CLKGATE_CON(2), 2, GFLAGS),
 
 	COMPOSITE_NODIV(SCLK_TIMER0, "sclk_timer0", mux_timer_p, CLK_IGNORE_UNUSED,
-			RK2928_CLKSEL_CON(2), 4, 1, DFLAGS,
+			RK2928_CLKSEL_CON(2), 4, 1, MFLAGS,
 			RK2928_CLKGATE_CON(1), 0, GFLAGS),
 	COMPOSITE_NODIV(SCLK_TIMER1, "sclk_timer1", mux_timer_p, CLK_IGNORE_UNUSED,
-			RK2928_CLKSEL_CON(2), 5, 1, DFLAGS,
+			RK2928_CLKSEL_CON(2), 5, 1, MFLAGS,
 			RK2928_CLKGATE_CON(1), 1, GFLAGS),
 	COMPOSITE_NODIV(SCLK_TIMER2, "sclk_timer2", mux_timer_p, CLK_IGNORE_UNUSED,
-			RK2928_CLKSEL_CON(2), 6, 1, DFLAGS,
+			RK2928_CLKSEL_CON(2), 6, 1, MFLAGS,
 			RK2928_CLKGATE_CON(2), 4, GFLAGS),
 	COMPOSITE_NODIV(SCLK_TIMER3, "sclk_timer3", mux_timer_p, CLK_IGNORE_UNUSED,
-			RK2928_CLKSEL_CON(2), 7, 1, DFLAGS,
+			RK2928_CLKSEL_CON(2), 7, 1, MFLAGS,
 			RK2928_CLKGATE_CON(2), 5, GFLAGS),
 
 	MUX(0, "uart_pll_clk", mux_pll_src_apll_dpll_gpll_usb480m_p, 0,
@@ -242,11 +242,11 @@ static struct rockchip_clk_branch rk3036_clk_branches[] __initdata = {
 			RK2928_CLKSEL_CON(13), 0, 7, DFLAGS,
 			RK2928_CLKGATE_CON(1), 8, GFLAGS),
 	COMPOSITE_NOMUX(0, "uart1_src", "uart_pll_clk", 0,
-			RK2928_CLKSEL_CON(13), 0, 7, DFLAGS,
-			RK2928_CLKGATE_CON(1), 8, GFLAGS),
+			RK2928_CLKSEL_CON(14), 0, 7, DFLAGS,
+			RK2928_CLKGATE_CON(1), 10, GFLAGS),
 	COMPOSITE_NOMUX(0, "uart2_src", "uart_pll_clk", 0,
-			RK2928_CLKSEL_CON(13), 0, 7, DFLAGS,
-			RK2928_CLKGATE_CON(1), 8, GFLAGS),
+			RK2928_CLKSEL_CON(15), 0, 7, DFLAGS,
+			RK2928_CLKGATE_CON(1), 12, GFLAGS),
 	COMPOSITE_FRACMUX(0, "uart0_frac", "uart0_src", CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(17), 0,
 			RK2928_CLKGATE_CON(1), 9, GFLAGS,
@@ -279,13 +279,13 @@ static struct rockchip_clk_branch rk3036_clk_branches[] __initdata = {
 			RK2928_CLKGATE_CON(3), 2, GFLAGS),
 
 	COMPOSITE_NODIV(0, "sclk_sdmmc_src", mux_mmc_src_p, 0,
-			RK2928_CLKSEL_CON(12), 8, 2, DFLAGS,
+			RK2928_CLKSEL_CON(12), 8, 2, MFLAGS,
 			RK2928_CLKGATE_CON(2), 11, GFLAGS),
 	DIV(SCLK_SDMMC, "sclk_sdmmc", "sclk_sdmmc_src", 0,
 			RK2928_CLKSEL_CON(11), 0, 7, DFLAGS),
 
 	COMPOSITE_NODIV(0, "sclk_sdio_src", mux_mmc_src_p, 0,
-			RK2928_CLKSEL_CON(12), 10, 2, DFLAGS,
+			RK2928_CLKSEL_CON(12), 10, 2, MFLAGS,
 			RK2928_CLKGATE_CON(2), 13, GFLAGS),
 	DIV(SCLK_SDIO, "sclk_sdio", "sclk_sdio_src", 0,
 			RK2928_CLKSEL_CON(11), 8, 7, DFLAGS),
@@ -344,12 +344,12 @@ static struct rockchip_clk_branch rk3036_clk_branches[] __initdata = {
 			RK2928_CLKGATE_CON(10), 5, GFLAGS),
 
 	COMPOSITE_NOGATE(0, "mac_pll_src", mux_pll_src_3plls_p, 0,
-			RK2928_CLKSEL_CON(21), 0, 2, MFLAGS, 4, 5, DFLAGS),
+			RK2928_CLKSEL_CON(21), 0, 2, MFLAGS, 9, 5, DFLAGS),
 	MUX(SCLK_MACREF, "mac_clk_ref", mux_mac_p, CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(21), 3, 1, MFLAGS),
 
 	COMPOSITE_NOMUX(SCLK_MAC, "mac_clk", "mac_clk_ref", 0,
-			RK2928_CLKSEL_CON(21), 9, 5, DFLAGS,
+			RK2928_CLKSEL_CON(21), 4, 5, DFLAGS,
 			RK2928_CLKGATE_CON(2), 6, GFLAGS),
 
 	MUX(SCLK_HDMI, "dclk_hdmi", mux_dclk_p, 0,
diff --git a/drivers/clk/rockchip/clk-rk3368.c b/drivers/clk/rockchip/clk-rk3368.c
index be0ede522269..21f3ea909fab 100644
--- a/drivers/clk/rockchip/clk-rk3368.c
+++ b/drivers/clk/rockchip/clk-rk3368.c
@@ -780,13 +780,13 @@ static struct rockchip_clk_branch rk3368_clk_branches[] __initdata = {
 	GATE(PCLK_TSADC, "pclk_tsadc", "pclk_peri", 0, RK3368_CLKGATE_CON(20), 0, GFLAGS),
 
 	/* pclk_pd_alive gates */
-	GATE(PCLK_TIMER1, "pclk_timer1", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 8, GFLAGS),
-	GATE(PCLK_TIMER0, "pclk_timer0", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 7, GFLAGS),
-	GATE(0, "pclk_alive_niu", "pclk_pd_alive", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(14), 12, GFLAGS),
-	GATE(PCLK_GRF, "pclk_grf", "pclk_pd_alive", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(14), 11, GFLAGS),
-	GATE(PCLK_GPIO3, "pclk_gpio3", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 3, GFLAGS),
-	GATE(PCLK_GPIO2, "pclk_gpio2", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 2, GFLAGS),
-	GATE(PCLK_GPIO1, "pclk_gpio1", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 1, GFLAGS),
+	GATE(PCLK_TIMER1, "pclk_timer1", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(22), 13, GFLAGS),
+	GATE(PCLK_TIMER0, "pclk_timer0", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(22), 12, GFLAGS),
+	GATE(0, "pclk_alive_niu", "pclk_pd_alive", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(22), 9, GFLAGS),
+	GATE(PCLK_GRF, "pclk_grf", "pclk_pd_alive", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(22), 8, GFLAGS),
+	GATE(PCLK_GPIO3, "pclk_gpio3", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(22), 3, GFLAGS),
+	GATE(PCLK_GPIO2, "pclk_gpio2", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(22), 2, GFLAGS),
+	GATE(PCLK_GPIO1, "pclk_gpio1", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(22), 1, GFLAGS),
 
 	/*
 	 * pclk_vio gates
@@ -796,12 +796,12 @@ static struct rockchip_clk_branch rk3368_clk_branches[] __initdata = {
 	GATE(0, "pclk_dphytx", "hclk_vio", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(14), 8, GFLAGS),
 
 	/* pclk_pd_pmu gates */
-	GATE(PCLK_PMUGRF, "pclk_pmugrf", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 0, GFLAGS),
-	GATE(PCLK_GPIO0, "pclk_gpio0", "pclk_pd_pmu", 0, RK3368_CLKGATE_CON(17), 4, GFLAGS),
-	GATE(PCLK_SGRF, "pclk_sgrf", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 3, GFLAGS),
-	GATE(0, "pclk_pmu_noc", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 2, GFLAGS),
-	GATE(0, "pclk_intmem1", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 1, GFLAGS),
-	GATE(PCLK_PMU, "pclk_pmu", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 2, GFLAGS),
+	GATE(PCLK_PMUGRF, "pclk_pmugrf", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(23), 5, GFLAGS),
+	GATE(PCLK_GPIO0, "pclk_gpio0", "pclk_pd_pmu", 0, RK3368_CLKGATE_CON(23), 4, GFLAGS),
+	GATE(PCLK_SGRF, "pclk_sgrf", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(23), 3, GFLAGS),
+	GATE(0, "pclk_pmu_noc", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(23), 2, GFLAGS),
+	GATE(0, "pclk_intmem1", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(23), 1, GFLAGS),
+	GATE(PCLK_PMU, "pclk_pmu", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(23), 0, GFLAGS),
 
 	/* timer gates */
 	GATE(0, "sclk_timer15", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 11, GFLAGS),
diff --git a/drivers/clk/tegra/clk-emc.c b/drivers/clk/tegra/clk-emc.c
index e1fe8f35d45c..74e7544f861b 100644
--- a/drivers/clk/tegra/clk-emc.c
+++ b/drivers/clk/tegra/clk-emc.c
@@ -450,8 +450,10 @@ static int load_timings_from_dt(struct tegra_clk_emc *tegra,
 		struct emc_timing *timing = tegra->timings + (i++);
 
 		err = load_one_timing_from_dt(tegra, timing, child);
-		if (err)
+		if (err) {
+			of_node_put(child);
 			return err;
+		}
 
 		timing->ram_code = ram_code;
 	}
@@ -499,9 +501,9 @@ struct clk *tegra_clk_register_emc(void __iomem *base, struct device_node *np,
 		 * fuses until the apbmisc driver is loaded.
 		 */
 		err = load_timings_from_dt(tegra, node, node_ram_code);
+		of_node_put(node);
 		if (err)
 			return ERR_PTR(err);
-		of_node_put(node);
 		break;
 	}
 
diff --git a/drivers/clk/tegra/clk-id.h b/drivers/clk/tegra/clk-id.h
index 19ce0738ee76..62ea38187b71 100644
--- a/drivers/clk/tegra/clk-id.h
+++ b/drivers/clk/tegra/clk-id.h
@@ -11,6 +11,7 @@ enum clk_id {
 	tegra_clk_afi,
 	tegra_clk_amx,
 	tegra_clk_amx1,
+	tegra_clk_apb2ape,
 	tegra_clk_apbdma,
 	tegra_clk_apbif,
 	tegra_clk_ape,
diff --git a/drivers/clk/tegra/clk-pll.c b/drivers/clk/tegra/clk-pll.c
index a534bfab30b3..6ac3f843e7ca 100644
--- a/drivers/clk/tegra/clk-pll.c
+++ b/drivers/clk/tegra/clk-pll.c
@@ -86,15 +86,21 @@
 #define PLLE_SS_DISABLE (PLLE_SS_CNTL_BYPASS_SS | PLLE_SS_CNTL_INTERP_RESET |\
 				PLLE_SS_CNTL_SSC_BYP)
 #define PLLE_SS_MAX_MASK 0x1ff
-#define PLLE_SS_MAX_VAL 0x25
+#define PLLE_SS_MAX_VAL_TEGRA114 0x25
+#define PLLE_SS_MAX_VAL_TEGRA210 0x21
 #define PLLE_SS_INC_MASK (0xff << 16)
 #define PLLE_SS_INC_VAL (0x1 << 16)
 #define PLLE_SS_INCINTRV_MASK (0x3f << 24)
-#define PLLE_SS_INCINTRV_VAL (0x20 << 24)
+#define PLLE_SS_INCINTRV_VAL_TEGRA114 (0x20 << 24)
+#define PLLE_SS_INCINTRV_VAL_TEGRA210 (0x23 << 24)
 #define PLLE_SS_COEFFICIENTS_MASK \
 	(PLLE_SS_MAX_MASK | PLLE_SS_INC_MASK | PLLE_SS_INCINTRV_MASK)
-#define PLLE_SS_COEFFICIENTS_VAL \
-	(PLLE_SS_MAX_VAL | PLLE_SS_INC_VAL | PLLE_SS_INCINTRV_VAL)
+#define PLLE_SS_COEFFICIENTS_VAL_TEGRA114 \
+	(PLLE_SS_MAX_VAL_TEGRA114 | PLLE_SS_INC_VAL |\
+	 PLLE_SS_INCINTRV_VAL_TEGRA114)
+#define PLLE_SS_COEFFICIENTS_VAL_TEGRA210 \
+	(PLLE_SS_MAX_VAL_TEGRA210 | PLLE_SS_INC_VAL |\
+	 PLLE_SS_INCINTRV_VAL_TEGRA210)
 
 #define PLLE_AUX_PLLP_SEL	BIT(2)
 #define PLLE_AUX_USE_LOCKDET	BIT(3)
@@ -880,7 +886,7 @@ static int clk_plle_training(struct tegra_clk_pll *pll)
 static int clk_plle_enable(struct clk_hw *hw)
 {
 	struct tegra_clk_pll *pll = to_clk_pll(hw);
-	unsigned long input_rate = clk_get_rate(clk_get_parent(hw->clk));
+	unsigned long input_rate = clk_hw_get_rate(clk_hw_get_parent(hw));
 	struct tegra_clk_pll_freq_table sel;
 	u32 val;
 	int err;
@@ -1378,7 +1384,7 @@ static int clk_plle_tegra114_enable(struct clk_hw *hw)
 	u32 val;
 	int ret;
 	unsigned long flags = 0;
-	unsigned long input_rate = clk_get_rate(clk_get_parent(hw->clk));
+	unsigned long input_rate = clk_hw_get_rate(clk_hw_get_parent(hw));
 
 	if (_get_table_rate(hw, &sel, pll->params->fixed_rate, input_rate))
 		return -EINVAL;
@@ -1401,7 +1407,7 @@ static int clk_plle_tegra114_enable(struct clk_hw *hw)
 	val |= PLLE_MISC_IDDQ_SW_CTRL;
 	val &= ~PLLE_MISC_IDDQ_SW_VALUE;
 	val |= PLLE_MISC_PLLE_PTS;
-	val |= PLLE_MISC_VREG_BG_CTRL_MASK | PLLE_MISC_VREG_CTRL_MASK;
+	val &= ~(PLLE_MISC_VREG_BG_CTRL_MASK | PLLE_MISC_VREG_CTRL_MASK);
 	pll_writel_misc(val, pll);
 	udelay(5);
 
@@ -1428,7 +1434,7 @@ static int clk_plle_tegra114_enable(struct clk_hw *hw)
 	val = pll_readl(PLLE_SS_CTRL, pll);
 	val &= ~(PLLE_SS_CNTL_CENTER | PLLE_SS_CNTL_INVERT);
 	val &= ~PLLE_SS_COEFFICIENTS_MASK;
-	val |= PLLE_SS_COEFFICIENTS_VAL;
+	val |= PLLE_SS_COEFFICIENTS_VAL_TEGRA114;
 	pll_writel(val, PLLE_SS_CTRL, pll);
 	val &= ~(PLLE_SS_CNTL_SSC_BYP | PLLE_SS_CNTL_BYPASS_SS);
 	pll_writel(val, PLLE_SS_CTRL, pll);
@@ -2012,9 +2018,9 @@ static int clk_plle_tegra210_enable(struct clk_hw *hw)
 	struct tegra_clk_pll *pll = to_clk_pll(hw);
 	struct tegra_clk_pll_freq_table sel;
 	u32 val;
-	int ret;
+	int ret = 0;
 	unsigned long flags = 0;
-	unsigned long input_rate = clk_get_rate(clk_get_parent(hw->clk));
+	unsigned long input_rate = clk_hw_get_rate(clk_hw_get_parent(hw));
 
 	if (_get_table_rate(hw, &sel, pll->params->fixed_rate, input_rate))
 		return -EINVAL;
@@ -2022,22 +2028,20 @@ static int clk_plle_tegra210_enable(struct clk_hw *hw)
 	if (pll->lock)
 		spin_lock_irqsave(pll->lock, flags);
 
+	val = pll_readl(pll->params->aux_reg, pll);
+	if (val & PLLE_AUX_SEQ_ENABLE)
+		goto out;
+
 	val = pll_readl_base(pll);
 	val &= ~BIT(30); /* Disable lock override */
 	pll_writel_base(val, pll);
 
-	val = pll_readl(pll->params->aux_reg, pll);
-	val |= PLLE_AUX_ENABLE_SWCTL;
-	val &= ~PLLE_AUX_SEQ_ENABLE;
-	pll_writel(val, pll->params->aux_reg, pll);
-	udelay(1);
-
 	val = pll_readl_misc(pll);
 	val |= PLLE_MISC_LOCK_ENABLE;
 	val |= PLLE_MISC_IDDQ_SW_CTRL;
 	val &= ~PLLE_MISC_IDDQ_SW_VALUE;
 	val |= PLLE_MISC_PLLE_PTS;
-	val |= PLLE_MISC_VREG_BG_CTRL_MASK | PLLE_MISC_VREG_CTRL_MASK;
+	val &= ~(PLLE_MISC_VREG_BG_CTRL_MASK | PLLE_MISC_VREG_CTRL_MASK);
 	pll_writel_misc(val, pll);
 	udelay(5);
 
@@ -2067,7 +2071,7 @@ static int clk_plle_tegra210_enable(struct clk_hw *hw)
 	val = pll_readl(PLLE_SS_CTRL, pll);
 	val &= ~(PLLE_SS_CNTL_CENTER | PLLE_SS_CNTL_INVERT);
 	val &= ~PLLE_SS_COEFFICIENTS_MASK;
-	val |= PLLE_SS_COEFFICIENTS_VAL;
+	val |= PLLE_SS_COEFFICIENTS_VAL_TEGRA210;
 	pll_writel(val, PLLE_SS_CTRL, pll);
 	val &= ~(PLLE_SS_CNTL_SSC_BYP | PLLE_SS_CNTL_BYPASS_SS);
 	pll_writel(val, PLLE_SS_CTRL, pll);
@@ -2104,15 +2108,25 @@ static void clk_plle_tegra210_disable(struct clk_hw *hw)
 	if (pll->lock)
 		spin_lock_irqsave(pll->lock, flags);
 
+	/* If PLLE HW sequencer is enabled, SW should not disable PLLE */
+	val = pll_readl(pll->params->aux_reg, pll);
+	if (val & PLLE_AUX_SEQ_ENABLE)
+		goto out;
+
 	val = pll_readl_base(pll);
 	val &= ~PLLE_BASE_ENABLE;
 	pll_writel_base(val, pll);
 
+	val = pll_readl(pll->params->aux_reg, pll);
+	val |= PLLE_AUX_ENABLE_SWCTL | PLLE_AUX_SS_SWCTL;
+	pll_writel(val, pll->params->aux_reg, pll);
+
 	val = pll_readl_misc(pll);
 	val |= PLLE_MISC_IDDQ_SW_CTRL | PLLE_MISC_IDDQ_SW_VALUE;
 	pll_writel_misc(val, pll);
 	udelay(1);
 
+out:
 	if (pll->lock)
 		spin_unlock_irqrestore(pll->lock, flags);
 }
diff --git a/drivers/clk/tegra/clk-tegra-periph.c b/drivers/clk/tegra/clk-tegra-periph.c
index 6ad381a888a6..ea2b9cbf9e70 100644
--- a/drivers/clk/tegra/clk-tegra-periph.c
+++ b/drivers/clk/tegra/clk-tegra-periph.c
@@ -773,7 +773,7 @@ static struct tegra_periph_init_data periph_clks[] = {
 	XUSB("xusb_dev_src", mux_clkm_pllp_pllc_pllre, CLK_SOURCE_XUSB_DEV_SRC, 95, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_dev_src),
 	XUSB("xusb_dev_src", mux_clkm_pllp_pllre, CLK_SOURCE_XUSB_DEV_SRC, 95, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_dev_src_8),
 	MUX8("dbgapb", mux_pllp_clkm_2, CLK_SOURCE_DBGAPB, 185, TEGRA_PERIPH_NO_RESET, tegra_clk_dbgapb),
-	MUX8("msenc", mux_pllc2_c_c3_pllp_plla1_clkm, CLK_SOURCE_NVENC, 219, 0, tegra_clk_nvenc),
+	MUX8("nvenc", mux_pllc2_c_c3_pllp_plla1_clkm, CLK_SOURCE_NVENC, 219, 0, tegra_clk_nvenc),
 	MUX8("nvdec", mux_pllc2_c_c3_pllp_plla1_clkm, CLK_SOURCE_NVDEC, 194, 0, tegra_clk_nvdec),
 	MUX8("nvjpg", mux_pllc2_c_c3_pllp_plla1_clkm, CLK_SOURCE_NVJPG, 195, 0, tegra_clk_nvjpg),
 	MUX8("ape", mux_plla_pllc4_out0_pllc_pllc4_out1_pllp_pllc4_out2_clkm, CLK_SOURCE_APE, 198, TEGRA_PERIPH_ON_APB, tegra_clk_ape),
@@ -782,7 +782,7 @@ static struct tegra_periph_init_data periph_clks[] = {
 	NODIV("sor1", mux_clkm_sor1_brick_sor1_src, CLK_SOURCE_SOR1, 15, MASK(1), 183, 0, tegra_clk_sor1, &sor1_lock),
 	MUX8("sdmmc_legacy", mux_pllp_out3_clkm_pllp_pllc4, CLK_SOURCE_SDMMC_LEGACY, 193, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_sdmmc_legacy),
 	MUX8("qspi", mux_pllp_pllc_pllc_out1_pllc4_out2_pllc4_out1_clkm_pllc4_out0, CLK_SOURCE_QSPI, 211, TEGRA_PERIPH_ON_APB, tegra_clk_qspi),
-	MUX("vii2c", mux_pllp_pllc_clkm, CLK_SOURCE_VI_I2C, 208, TEGRA_PERIPH_ON_APB, tegra_clk_vi_i2c),
+	I2C("vii2c", mux_pllp_pllc_clkm, CLK_SOURCE_VI_I2C, 208, tegra_clk_vi_i2c),
 	MUX("mipibif", mux_pllp_clkm, CLK_SOURCE_MIPIBIF, 173, TEGRA_PERIPH_ON_APB, tegra_clk_mipibif),
 	MUX("uartape", mux_pllp_pllc_clkm, CLK_SOURCE_UARTAPE, 212, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_uartape),
 	MUX8("tsecb", mux_pllp_pllc2_c_c3_clkm, CLK_SOURCE_TSECB, 206, 0, tegra_clk_tsecb),
@@ -829,6 +829,7 @@ static struct tegra_periph_init_data gate_clks[] = {
 	GATE("xusb_gate", "osc", 143, 0, tegra_clk_xusb_gate, 0),
 	GATE("pll_p_out_cpu", "pll_p", 223, 0, tegra_clk_pll_p_out_cpu, 0),
 	GATE("pll_p_out_adsp", "pll_p", 187, 0, tegra_clk_pll_p_out_adsp, 0),
+	GATE("apb2ape", "clk_m", 107, 0, tegra_clk_apb2ape, 0),
 };
 
 static struct tegra_periph_init_data div_clks[] = {
diff --git a/drivers/clk/tegra/clk-tegra-super-gen4.c b/drivers/clk/tegra/clk-tegra-super-gen4.c
index 4559a20e3af6..474de0f0c26d 100644
--- a/drivers/clk/tegra/clk-tegra-super-gen4.c
+++ b/drivers/clk/tegra/clk-tegra-super-gen4.c
@@ -67,7 +67,7 @@ static const char *cclk_lp_parents[] = { "clk_m", "pll_c", "clk_32k", "pll_m",
 					 "pll_p", "pll_p_out4", "unused",
 					 "unused", "pll_x", "pll_x_out0" };
 
-const struct tegra_super_gen_info tegra_super_gen_info_gen4 = {
+static const struct tegra_super_gen_info tegra_super_gen_info_gen4 = {
 	.gen = gen4,
 	.sclk_parents = sclk_parents,
 	.cclk_g_parents = cclk_g_parents,
@@ -93,7 +93,7 @@ static const char *cclk_lp_parents_gen5[] = { "clk_m", "unused", "clk_32k", "unu
 					"unused", "unused", "unused", "unused",
 					"dfllCPU_out" };
 
-const struct tegra_super_gen_info tegra_super_gen_info_gen5 = {
+static const struct tegra_super_gen_info tegra_super_gen_info_gen5 = {
 	.gen = gen5,
 	.sclk_parents = sclk_parents_gen5,
 	.cclk_g_parents = cclk_g_parents_gen5,
@@ -171,7 +171,7 @@ static void __init tegra_sclk_init(void __iomem *clk_base,
 	*dt_clk = clk;
 }
 
-void __init tegra_super_clk_init(void __iomem *clk_base,
+static void __init tegra_super_clk_init(void __iomem *clk_base,
 				void __iomem *pmc_base,
 				struct tegra_clk *tegra_clks,
 				struct tegra_clk_pll_params *params,
diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c
index 58514c44ea83..637041fd53ad 100644
--- a/drivers/clk/tegra/clk-tegra210.c
+++ b/drivers/clk/tegra/clk-tegra210.c
@@ -59,8 +59,8 @@
 #define PLLC3_MISC3 0x50c
 
 #define PLLM_BASE 0x90
-#define PLLM_MISC0 0x9c
 #define PLLM_MISC1 0x98
+#define PLLM_MISC2 0x9c
 #define PLLP_BASE 0xa0
 #define PLLP_MISC0 0xac
 #define PLLP_MISC1 0x680
@@ -99,7 +99,7 @@
 #define PLLC4_MISC0 0x5a8
 #define PLLC4_OUT 0x5e4
 #define PLLMB_BASE 0x5e8
-#define PLLMB_MISC0 0x5ec
+#define PLLMB_MISC1 0x5ec
 #define PLLA1_BASE 0x6a4
 #define PLLA1_MISC0 0x6a8
 #define PLLA1_MISC1 0x6ac
@@ -243,7 +243,8 @@ static unsigned long tegra210_input_freq[] = {
 };
 
 static const char *mux_pllmcp_clkm[] = {
-	"pll_m", "pll_c", "pll_p", "clk_m", "pll_m_ud", "pll_c2", "pll_c3",
+	"pll_m", "pll_c", "pll_p", "clk_m", "pll_m_ud", "pll_mb", "pll_mb",
+	"pll_p",
 };
 #define mux_pllmcp_clkm_idx NULL
 
@@ -367,12 +368,12 @@ static const char *mux_pllmcp_clkm[] = {
 /* PLLMB */
 #define PLLMB_BASE_LOCK			(1 << 27)
 
-#define PLLMB_MISC0_LOCK_OVERRIDE	(1 << 18)
-#define PLLMB_MISC0_IDDQ		(1 << 17)
-#define PLLMB_MISC0_LOCK_ENABLE		(1 << 16)
+#define PLLMB_MISC1_LOCK_OVERRIDE	(1 << 18)
+#define PLLMB_MISC1_IDDQ		(1 << 17)
+#define PLLMB_MISC1_LOCK_ENABLE		(1 << 16)
 
-#define PLLMB_MISC0_DEFAULT_VALUE	0x00030000
-#define PLLMB_MISC0_WRITE_MASK		0x0007ffff
+#define PLLMB_MISC1_DEFAULT_VALUE	0x00030000
+#define PLLMB_MISC1_WRITE_MASK		0x0007ffff
 
 /* PLLP */
 #define PLLP_BASE_OVERRIDE		(1 << 28)
@@ -457,7 +458,8 @@ static void pllcx_check_defaults(struct tegra_clk_pll_params *params)
 			PLLCX_MISC3_WRITE_MASK);
 }
 
-void tegra210_pllcx_set_defaults(const char *name, struct tegra_clk_pll *pllcx)
+static void tegra210_pllcx_set_defaults(const char *name,
+					struct tegra_clk_pll *pllcx)
 {
 	pllcx->params->defaults_set = true;
 
@@ -482,22 +484,22 @@ void tegra210_pllcx_set_defaults(const char *name, struct tegra_clk_pll *pllcx)
 	udelay(1);
 }
 
-void _pllc_set_defaults(struct tegra_clk_pll *pllcx)
+static void _pllc_set_defaults(struct tegra_clk_pll *pllcx)
 {
 	tegra210_pllcx_set_defaults("PLL_C", pllcx);
 }
 
-void _pllc2_set_defaults(struct tegra_clk_pll *pllcx)
+static void _pllc2_set_defaults(struct tegra_clk_pll *pllcx)
 {
 	tegra210_pllcx_set_defaults("PLL_C2", pllcx);
 }
 
-void _pllc3_set_defaults(struct tegra_clk_pll *pllcx)
+static void _pllc3_set_defaults(struct tegra_clk_pll *pllcx)
 {
 	tegra210_pllcx_set_defaults("PLL_C3", pllcx);
 }
 
-void _plla1_set_defaults(struct tegra_clk_pll *pllcx)
+static void _plla1_set_defaults(struct tegra_clk_pll *pllcx)
 {
 	tegra210_pllcx_set_defaults("PLL_A1", pllcx);
 }
@@ -507,7 +509,7 @@ void _plla1_set_defaults(struct tegra_clk_pll *pllcx)
  * PLL with dynamic ramp and fractional SDM. Dynamic ramp is not used.
  * Fractional SDM is allowed to provide exact audio rates.
  */
-void tegra210_plla_set_defaults(struct tegra_clk_pll *plla)
+static void tegra210_plla_set_defaults(struct tegra_clk_pll *plla)
 {
 	u32 mask;
 	u32 val = readl_relaxed(clk_base + plla->params->base_reg);
@@ -559,7 +561,7 @@ void tegra210_plla_set_defaults(struct tegra_clk_pll *plla)
  * PLLD
  * PLL with fractional SDM.
  */
-void tegra210_plld_set_defaults(struct tegra_clk_pll *plld)
+static void tegra210_plld_set_defaults(struct tegra_clk_pll *plld)
 {
 	u32 val;
 	u32 mask = 0xffff;
@@ -698,7 +700,7 @@ static void plldss_defaults(const char *pll_name, struct tegra_clk_pll *plldss,
 	udelay(1);
 }
 
-void tegra210_plld2_set_defaults(struct tegra_clk_pll *plld2)
+static void tegra210_plld2_set_defaults(struct tegra_clk_pll *plld2)
 {
 	plldss_defaults("PLL_D2", plld2, PLLD2_MISC0_DEFAULT_VALUE,
 			PLLD2_MISC1_CFG_DEFAULT_VALUE,
@@ -706,7 +708,7 @@ void tegra210_plld2_set_defaults(struct tegra_clk_pll *plld2)
 			PLLD2_MISC3_CTRL2_DEFAULT_VALUE);
 }
 
-void tegra210_plldp_set_defaults(struct tegra_clk_pll *plldp)
+static void tegra210_plldp_set_defaults(struct tegra_clk_pll *plldp)
 {
 	plldss_defaults("PLL_DP", plldp, PLLDP_MISC0_DEFAULT_VALUE,
 			PLLDP_MISC1_CFG_DEFAULT_VALUE,
@@ -719,7 +721,7 @@ void tegra210_plldp_set_defaults(struct tegra_clk_pll *plldp)
  * Base and misc0 layout is the same as PLLD2/PLLDP, but no SDM/SSC support.
  * VCO is exposed to the clock tree via fixed 1/3 and 1/5 dividers.
  */
-void tegra210_pllc4_set_defaults(struct tegra_clk_pll *pllc4)
+static void tegra210_pllc4_set_defaults(struct tegra_clk_pll *pllc4)
 {
 	plldss_defaults("PLL_C4", pllc4, PLLC4_MISC0_DEFAULT_VALUE, 0, 0, 0);
 }
@@ -728,7 +730,7 @@ void tegra210_pllc4_set_defaults(struct tegra_clk_pll *pllc4)
  * PLLRE
  * VCO is exposed to the clock tree directly along with post-divider output
  */
-void tegra210_pllre_set_defaults(struct tegra_clk_pll *pllre)
+static void tegra210_pllre_set_defaults(struct tegra_clk_pll *pllre)
 {
 	u32 mask;
 	u32 val = readl_relaxed(clk_base + pllre->params->base_reg);
@@ -780,13 +782,13 @@ static void pllx_get_dyn_steps(struct clk_hw *hw, u32 *step_a, u32 *step_b)
 {
 	unsigned long input_rate;
 
-	if (!IS_ERR_OR_NULL(hw->clk)) {
+	/* cf rate */
+	if (!IS_ERR_OR_NULL(hw->clk))
 		input_rate = clk_hw_get_rate(clk_hw_get_parent(hw));
-		/* cf rate */
-		input_rate /= tegra_pll_get_fixed_mdiv(hw, input_rate);
-	} else {
+	else
 		input_rate = 38400000;
-	}
+
+	input_rate /= tegra_pll_get_fixed_mdiv(hw, input_rate);
 
 	switch (input_rate) {
 	case 12000000:
@@ -841,7 +843,7 @@ static void pllx_check_defaults(struct tegra_clk_pll *pll)
 			PLLX_MISC5_WRITE_MASK);
 }
 
-void tegra210_pllx_set_defaults(struct tegra_clk_pll *pllx)
+static void tegra210_pllx_set_defaults(struct tegra_clk_pll *pllx)
 {
 	u32 val;
 	u32 step_a, step_b;
@@ -901,7 +903,7 @@ void tegra210_pllx_set_defaults(struct tegra_clk_pll *pllx)
 }
 
 /* PLLMB */
-void tegra210_pllmb_set_defaults(struct tegra_clk_pll *pllmb)
+static void tegra210_pllmb_set_defaults(struct tegra_clk_pll *pllmb)
 {
 	u32 mask, val = readl_relaxed(clk_base + pllmb->params->base_reg);
 
@@ -914,15 +916,15 @@ void tegra210_pllmb_set_defaults(struct tegra_clk_pll *pllmb)
 		 * PLL is ON: check if defaults already set, then set those
 		 * that can be updated in flight.
 		 */
-		val = PLLMB_MISC0_DEFAULT_VALUE & (~PLLMB_MISC0_IDDQ);
-		mask = PLLMB_MISC0_LOCK_ENABLE | PLLMB_MISC0_LOCK_OVERRIDE;
+		val = PLLMB_MISC1_DEFAULT_VALUE & (~PLLMB_MISC1_IDDQ);
+		mask = PLLMB_MISC1_LOCK_ENABLE | PLLMB_MISC1_LOCK_OVERRIDE;
 		_pll_misc_chk_default(clk_base, pllmb->params, 0, val,
-				~mask & PLLMB_MISC0_WRITE_MASK);
+				~mask & PLLMB_MISC1_WRITE_MASK);
 
 		/* Enable lock detect */
 		val = readl_relaxed(clk_base + pllmb->params->ext_misc_reg[0]);
 		val &= ~mask;
-		val |= PLLMB_MISC0_DEFAULT_VALUE & mask;
+		val |= PLLMB_MISC1_DEFAULT_VALUE & mask;
 		writel_relaxed(val, clk_base + pllmb->params->ext_misc_reg[0]);
 		udelay(1);
 
@@ -930,7 +932,7 @@ void tegra210_pllmb_set_defaults(struct tegra_clk_pll *pllmb)
 	}
 
 	/* set IDDQ, enable lock detect */
-	writel_relaxed(PLLMB_MISC0_DEFAULT_VALUE,
+	writel_relaxed(PLLMB_MISC1_DEFAULT_VALUE,
 			clk_base + pllmb->params->ext_misc_reg[0]);
 	udelay(1);
 }
@@ -960,7 +962,7 @@ static void pllp_check_defaults(struct tegra_clk_pll *pll, bool enabled)
 			~mask & PLLP_MISC1_WRITE_MASK);
 }
 
-void tegra210_pllp_set_defaults(struct tegra_clk_pll *pllp)
+static void tegra210_pllp_set_defaults(struct tegra_clk_pll *pllp)
 {
 	u32 mask;
 	u32 val = readl_relaxed(clk_base + pllp->params->base_reg);
@@ -1022,7 +1024,7 @@ static void pllu_check_defaults(struct tegra_clk_pll *pll, bool hw_control)
 			~mask & PLLU_MISC1_WRITE_MASK);
 }
 
-void tegra210_pllu_set_defaults(struct tegra_clk_pll *pllu)
+static void tegra210_pllu_set_defaults(struct tegra_clk_pll *pllu)
 {
 	u32 val = readl_relaxed(clk_base + pllu->params->base_reg);
 
@@ -1212,8 +1214,9 @@ static void tegra210_clk_pll_set_gain(struct tegra_clk_pll_freq_table *cfg)
 	cfg->m *= PLL_SDM_COEFF;
 }
 
-unsigned long tegra210_clk_adjust_vco_min(struct tegra_clk_pll_params *params,
-					  unsigned long parent_rate)
+static unsigned long
+tegra210_clk_adjust_vco_min(struct tegra_clk_pll_params *params,
+			    unsigned long parent_rate)
 {
 	unsigned long vco_min = params->vco_min;
 
@@ -1386,7 +1389,7 @@ static struct tegra_clk_pll_params pll_c_params = {
 	.mdiv_default = 3,
 	.div_nmp = &pllc_nmp,
 	.freq_table = pll_cx_freq_table,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
+	.flags = TEGRA_PLL_USE_LOCK,
 	.set_defaults = _pllc_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
@@ -1425,7 +1428,7 @@ static struct tegra_clk_pll_params pll_c2_params = {
 	.ext_misc_reg[2] = PLLC2_MISC2,
 	.ext_misc_reg[3] = PLLC2_MISC3,
 	.freq_table = pll_cx_freq_table,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
+	.flags = TEGRA_PLL_USE_LOCK,
 	.set_defaults = _pllc2_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
@@ -1455,7 +1458,7 @@ static struct tegra_clk_pll_params pll_c3_params = {
 	.ext_misc_reg[2] = PLLC3_MISC2,
 	.ext_misc_reg[3] = PLLC3_MISC3,
 	.freq_table = pll_cx_freq_table,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
+	.flags = TEGRA_PLL_USE_LOCK,
 	.set_defaults = _pllc3_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
@@ -1505,7 +1508,6 @@ static struct tegra_clk_pll_params pll_c4_vco_params = {
 	.base_reg = PLLC4_BASE,
 	.misc_reg = PLLC4_MISC0,
 	.lock_mask = PLL_BASE_LOCK,
-	.lock_enable_bit_idx = PLLSS_MISC_LOCK_ENABLE,
 	.lock_delay = 300,
 	.max_p = PLL_QLIN_PDIV_MAX,
 	.ext_misc_reg[0] = PLLC4_MISC0,
@@ -1517,8 +1519,7 @@ static struct tegra_clk_pll_params pll_c4_vco_params = {
 	.div_nmp = &pllss_nmp,
 	.freq_table = pll_c4_vco_freq_table,
 	.set_defaults = tegra210_pllc4_set_defaults,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE |
-		 TEGRA_PLL_VCO_OUT,
+	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_VCO_OUT,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
 
@@ -1559,15 +1560,15 @@ static struct tegra_clk_pll_params pll_m_params = {
 	.vco_min = 800000000,
 	.vco_max = 1866000000,
 	.base_reg = PLLM_BASE,
-	.misc_reg = PLLM_MISC1,
+	.misc_reg = PLLM_MISC2,
 	.lock_mask = PLL_BASE_LOCK,
 	.lock_enable_bit_idx = PLLM_MISC_LOCK_ENABLE,
 	.lock_delay = 300,
-	.iddq_reg = PLLM_MISC0,
+	.iddq_reg = PLLM_MISC2,
 	.iddq_bit_idx = PLLM_IDDQ_BIT,
 	.max_p = PLL_QLIN_PDIV_MAX,
-	.ext_misc_reg[0] = PLLM_MISC0,
-	.ext_misc_reg[0] = PLLM_MISC1,
+	.ext_misc_reg[0] = PLLM_MISC2,
+	.ext_misc_reg[1] = PLLM_MISC1,
 	.round_p_to_pdiv = pll_qlin_p_to_pdiv,
 	.pdiv_tohw = pll_qlin_pdiv_to_hw,
 	.div_nmp = &pllm_nmp,
@@ -1586,19 +1587,18 @@ static struct tegra_clk_pll_params pll_mb_params = {
 	.vco_min = 800000000,
 	.vco_max = 1866000000,
 	.base_reg = PLLMB_BASE,
-	.misc_reg = PLLMB_MISC0,
+	.misc_reg = PLLMB_MISC1,
 	.lock_mask = PLL_BASE_LOCK,
-	.lock_enable_bit_idx = PLLMB_MISC_LOCK_ENABLE,
 	.lock_delay = 300,
-	.iddq_reg = PLLMB_MISC0,
+	.iddq_reg = PLLMB_MISC1,
 	.iddq_bit_idx = PLLMB_IDDQ_BIT,
 	.max_p = PLL_QLIN_PDIV_MAX,
-	.ext_misc_reg[0] = PLLMB_MISC0,
+	.ext_misc_reg[0] = PLLMB_MISC1,
 	.round_p_to_pdiv = pll_qlin_p_to_pdiv,
 	.pdiv_tohw = pll_qlin_pdiv_to_hw,
 	.div_nmp = &pllm_nmp,
 	.freq_table = pll_m_freq_table,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
+	.flags = TEGRA_PLL_USE_LOCK,
 	.set_defaults = tegra210_pllmb_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
@@ -1671,7 +1671,6 @@ static struct tegra_clk_pll_params pll_re_vco_params = {
 	.base_reg = PLLRE_BASE,
 	.misc_reg = PLLRE_MISC0,
 	.lock_mask = PLLRE_MISC_LOCK,
-	.lock_enable_bit_idx = PLLRE_MISC_LOCK_ENABLE,
 	.lock_delay = 300,
 	.max_p = PLL_QLIN_PDIV_MAX,
 	.ext_misc_reg[0] = PLLRE_MISC0,
@@ -1681,8 +1680,7 @@ static struct tegra_clk_pll_params pll_re_vco_params = {
 	.pdiv_tohw = pll_qlin_pdiv_to_hw,
 	.div_nmp = &pllre_nmp,
 	.freq_table = pll_re_vco_freq_table,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_LOCK_MISC |
-		 TEGRA_PLL_HAS_LOCK_ENABLE | TEGRA_PLL_VCO_OUT,
+	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_LOCK_MISC | TEGRA_PLL_VCO_OUT,
 	.set_defaults = tegra210_pllre_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
@@ -1712,7 +1710,6 @@ static struct tegra_clk_pll_params pll_p_params = {
 	.base_reg = PLLP_BASE,
 	.misc_reg = PLLP_MISC0,
 	.lock_mask = PLL_BASE_LOCK,
-	.lock_enable_bit_idx = PLLP_MISC_LOCK_ENABLE,
 	.lock_delay = 300,
 	.iddq_reg = PLLP_MISC0,
 	.iddq_bit_idx = PLLXP_IDDQ_BIT,
@@ -1721,8 +1718,7 @@ static struct tegra_clk_pll_params pll_p_params = {
 	.div_nmp = &pllp_nmp,
 	.freq_table = pll_p_freq_table,
 	.fixed_rate = 408000000,
-	.flags = TEGRA_PLL_FIXED | TEGRA_PLL_USE_LOCK |
-		 TEGRA_PLL_HAS_LOCK_ENABLE | TEGRA_PLL_VCO_OUT,
+	.flags = TEGRA_PLL_FIXED | TEGRA_PLL_USE_LOCK | TEGRA_PLL_VCO_OUT,
 	.set_defaults = tegra210_pllp_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
@@ -1750,7 +1746,7 @@ static struct tegra_clk_pll_params pll_a1_params = {
 	.ext_misc_reg[2] = PLLA1_MISC2,
 	.ext_misc_reg[3] = PLLA1_MISC3,
 	.freq_table = pll_cx_freq_table,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
+	.flags = TEGRA_PLL_USE_LOCK,
 	.set_defaults = _plla1_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
@@ -1787,7 +1783,6 @@ static struct tegra_clk_pll_params pll_a_params = {
 	.base_reg = PLLA_BASE,
 	.misc_reg = PLLA_MISC0,
 	.lock_mask = PLL_BASE_LOCK,
-	.lock_enable_bit_idx = PLLA_MISC_LOCK_ENABLE,
 	.lock_delay = 300,
 	.round_p_to_pdiv = pll_qlin_p_to_pdiv,
 	.pdiv_tohw = pll_qlin_pdiv_to_hw,
@@ -1802,8 +1797,7 @@ static struct tegra_clk_pll_params pll_a_params = {
 	.ext_misc_reg[1] = PLLA_MISC1,
 	.ext_misc_reg[2] = PLLA_MISC2,
 	.freq_table = pll_a_freq_table,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_MDIV_NEW |
-		 TEGRA_PLL_HAS_LOCK_ENABLE,
+	.flags = TEGRA_PLL_USE_LOCK | TEGRA_MDIV_NEW,
 	.set_defaults = tegra210_plla_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 	.set_gain = tegra210_clk_pll_set_gain,
@@ -1836,7 +1830,6 @@ static struct tegra_clk_pll_params pll_d_params = {
 	.base_reg = PLLD_BASE,
 	.misc_reg = PLLD_MISC0,
 	.lock_mask = PLL_BASE_LOCK,
-	.lock_enable_bit_idx = PLLD_MISC_LOCK_ENABLE,
 	.lock_delay = 1000,
 	.iddq_reg = PLLD_MISC0,
 	.iddq_bit_idx = PLLD_IDDQ_BIT,
@@ -1850,7 +1843,7 @@ static struct tegra_clk_pll_params pll_d_params = {
 	.ext_misc_reg[0] = PLLD_MISC0,
 	.ext_misc_reg[1] = PLLD_MISC1,
 	.freq_table = pll_d_freq_table,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
+	.flags = TEGRA_PLL_USE_LOCK,
 	.mdiv_default = 1,
 	.set_defaults = tegra210_plld_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
@@ -1876,7 +1869,6 @@ static struct tegra_clk_pll_params pll_d2_params = {
 	.base_reg = PLLD2_BASE,
 	.misc_reg = PLLD2_MISC0,
 	.lock_mask = PLL_BASE_LOCK,
-	.lock_enable_bit_idx = PLLSS_MISC_LOCK_ENABLE,
 	.lock_delay = 300,
 	.iddq_reg = PLLD2_BASE,
 	.iddq_bit_idx = PLLSS_IDDQ_BIT,
@@ -1897,7 +1889,7 @@ static struct tegra_clk_pll_params pll_d2_params = {
 	.mdiv_default = 1,
 	.freq_table = tegra210_pll_d2_freq_table,
 	.set_defaults = tegra210_plld2_set_defaults,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
+	.flags = TEGRA_PLL_USE_LOCK,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 	.set_gain = tegra210_clk_pll_set_gain,
 	.adjust_vco = tegra210_clk_adjust_vco_min,
@@ -1920,7 +1912,6 @@ static struct tegra_clk_pll_params pll_dp_params = {
 	.base_reg = PLLDP_BASE,
 	.misc_reg = PLLDP_MISC,
 	.lock_mask = PLL_BASE_LOCK,
-	.lock_enable_bit_idx = PLLSS_MISC_LOCK_ENABLE,
 	.lock_delay = 300,
 	.iddq_reg = PLLDP_BASE,
 	.iddq_bit_idx = PLLSS_IDDQ_BIT,
@@ -1941,7 +1932,7 @@ static struct tegra_clk_pll_params pll_dp_params = {
 	.mdiv_default = 1,
 	.freq_table = pll_dp_freq_table,
 	.set_defaults = tegra210_plldp_set_defaults,
-	.flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
+	.flags = TEGRA_PLL_USE_LOCK,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 	.set_gain = tegra210_clk_pll_set_gain,
 	.adjust_vco = tegra210_clk_adjust_vco_min,
@@ -1973,7 +1964,6 @@ static struct tegra_clk_pll_params pll_u_vco_params = {
 	.base_reg = PLLU_BASE,
 	.misc_reg = PLLU_MISC0,
 	.lock_mask = PLL_BASE_LOCK,
-	.lock_enable_bit_idx = PLLU_MISC_LOCK_ENABLE,
 	.lock_delay = 1000,
 	.iddq_reg = PLLU_MISC0,
 	.iddq_bit_idx = PLLU_IDDQ_BIT,
@@ -1983,8 +1973,7 @@ static struct tegra_clk_pll_params pll_u_vco_params = {
 	.pdiv_tohw = pll_qlin_pdiv_to_hw,
 	.div_nmp = &pllu_nmp,
 	.freq_table = pll_u_freq_table,
-	.flags = TEGRA_PLLU | TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE |
-		 TEGRA_PLL_VCO_OUT,
+	.flags = TEGRA_PLLU | TEGRA_PLL_USE_LOCK | TEGRA_PLL_VCO_OUT,
 	.set_defaults = tegra210_pllu_set_defaults,
 	.calc_rate = tegra210_pll_fixed_mdiv_cfg,
 };
@@ -2218,6 +2207,7 @@ static struct tegra_clk tegra210_clks[tegra_clk_max] __initdata = {
 	[tegra_clk_pll_c4_out1] = { .dt_id = TEGRA210_CLK_PLL_C4_OUT1, .present = true },
 	[tegra_clk_pll_c4_out2] = { .dt_id = TEGRA210_CLK_PLL_C4_OUT2, .present = true },
 	[tegra_clk_pll_c4_out3] = { .dt_id = TEGRA210_CLK_PLL_C4_OUT3, .present = true },
+	[tegra_clk_apb2ape] = { .dt_id = TEGRA210_CLK_APB2APE, .present = true },
 };
 
 static struct tegra_devclk devclks[] __initdata = {
@@ -2519,7 +2509,7 @@ static void __init tegra210_pll_init(void __iomem *clk_base,
 
 	/* PLLU_VCO */
 	val = readl(clk_base + pll_u_vco_params.base_reg);
-	val &= ~BIT(24); /* disable PLLU_OVERRIDE */
+	val &= ~PLLU_BASE_OVERRIDE; /* disable PLLU_OVERRIDE */
 	writel(val, clk_base + pll_u_vco_params.base_reg);
 
 	clk = tegra_clk_register_pllre("pll_u_vco", "pll_ref", clk_base, pmc,
@@ -2738,8 +2728,6 @@ static struct tegra_clk_init_table init_table[] __initdata = {
 	{ TEGRA210_CLK_DFLL_REF, TEGRA210_CLK_PLL_P, 51000000, 1 },
 	{ TEGRA210_CLK_SBC4, TEGRA210_CLK_PLL_P, 12000000, 1 },
 	{ TEGRA210_CLK_PLL_RE_VCO, TEGRA210_CLK_CLK_MAX, 672000000, 1 },
-	{ TEGRA210_CLK_PLL_U_OUT1, TEGRA210_CLK_CLK_MAX, 48000000, 1 },
-	{ TEGRA210_CLK_PLL_U_OUT2, TEGRA210_CLK_CLK_MAX, 60000000, 1 },
 	{ TEGRA210_CLK_XUSB_GATE, TEGRA210_CLK_CLK_MAX, 0, 1 },
 	{ TEGRA210_CLK_XUSB_SS_SRC, TEGRA210_CLK_PLL_U_480M, 120000000, 0 },
 	{ TEGRA210_CLK_XUSB_FS_SRC, TEGRA210_CLK_PLL_U_48M, 48000000, 0 },
diff --git a/drivers/clk/ti/dpll3xxx.c b/drivers/clk/ti/dpll3xxx.c
index 1c300388782b..cc739291a3ce 100644
--- a/drivers/clk/ti/dpll3xxx.c
+++ b/drivers/clk/ti/dpll3xxx.c
@@ -460,7 +460,8 @@ int omap3_noncore_dpll_enable(struct clk_hw *hw)
 
 	parent = clk_hw_get_parent(hw);
 
-	if (clk_hw_get_rate(hw) == clk_get_rate(dd->clk_bypass)) {
+	if (clk_hw_get_rate(hw) ==
+	    clk_hw_get_rate(__clk_get_hw(dd->clk_bypass))) {
 		WARN_ON(parent != __clk_get_hw(dd->clk_bypass));
 		r = _omap3_noncore_dpll_bypass(clk);
 	} else {
diff --git a/drivers/clk/versatile/clk-icst.c b/drivers/clk/versatile/clk-icst.c
index e62f8cb2c9b5..3bca438ecd19 100644
--- a/drivers/clk/versatile/clk-icst.c
+++ b/drivers/clk/versatile/clk-icst.c
@@ -78,6 +78,9 @@ static int vco_set(struct clk_icst *icst, struct icst_vco vco)
 	ret = regmap_read(icst->map, icst->vcoreg_off, &val);
 	if (ret)
 		return ret;
+
+	/* Mask the 18 bits used by the VCO */
+	val &= ~0x7ffff;
 	val |= vco.v | (vco.r << 9) | (vco.s << 16);
 
 	/* This magic unlocks the VCO so it can be controlled */
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 33db7406c0e2..c346be650892 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -160,6 +160,7 @@ config CLKSRC_EFM32
 config CLKSRC_LPC32XX
 	bool "Clocksource for LPC32XX" if COMPILE_TEST
 	depends on GENERIC_CLOCKEVENTS && HAS_IOMEM
+	depends on ARM
 	select CLKSRC_MMIO
 	select CLKSRC_OF
 	help
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index c64d543d64bf..5152b3898155 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -32,6 +32,14 @@
 #define CNTTIDR		0x08
 #define CNTTIDR_VIRT(n)	(BIT(1) << ((n) * 4))
 
+#define CNTACR(n)	(0x40 + ((n) * 4))
+#define CNTACR_RPCT	BIT(0)
+#define CNTACR_RVCT	BIT(1)
+#define CNTACR_RFRQ	BIT(2)
+#define CNTACR_RVOFF	BIT(3)
+#define CNTACR_RWVT	BIT(4)
+#define CNTACR_RWPT	BIT(5)
+
 #define CNTVCT_LO	0x08
 #define CNTVCT_HI	0x0c
 #define CNTFRQ		0x10
@@ -67,7 +75,7 @@ static int arch_timer_ppi[MAX_TIMER_PPI];
 
 static struct clock_event_device __percpu *arch_timer_evt;
 
-static bool arch_timer_use_virtual = true;
+static enum ppi_nr arch_timer_uses_ppi = VIRT_PPI;
 static bool arch_timer_c3stop;
 static bool arch_timer_mem_use_virtual;
 
@@ -263,14 +271,22 @@ static void __arch_timer_setup(unsigned type,
 		clk->name = "arch_sys_timer";
 		clk->rating = 450;
 		clk->cpumask = cpumask_of(smp_processor_id());
-		if (arch_timer_use_virtual) {
-			clk->irq = arch_timer_ppi[VIRT_PPI];
+		clk->irq = arch_timer_ppi[arch_timer_uses_ppi];
+		switch (arch_timer_uses_ppi) {
+		case VIRT_PPI:
 			clk->set_state_shutdown = arch_timer_shutdown_virt;
+			clk->set_state_oneshot_stopped = arch_timer_shutdown_virt;
 			clk->set_next_event = arch_timer_set_next_event_virt;
-		} else {
-			clk->irq = arch_timer_ppi[PHYS_SECURE_PPI];
+			break;
+		case PHYS_SECURE_PPI:
+		case PHYS_NONSECURE_PPI:
+		case HYP_PPI:
 			clk->set_state_shutdown = arch_timer_shutdown_phys;
+			clk->set_state_oneshot_stopped = arch_timer_shutdown_phys;
 			clk->set_next_event = arch_timer_set_next_event_phys;
+			break;
+		default:
+			BUG();
 		}
 	} else {
 		clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
@@ -279,10 +295,12 @@ static void __arch_timer_setup(unsigned type,
 		clk->cpumask = cpu_all_mask;
 		if (arch_timer_mem_use_virtual) {
 			clk->set_state_shutdown = arch_timer_shutdown_virt_mem;
+			clk->set_state_oneshot_stopped = arch_timer_shutdown_virt_mem;
 			clk->set_next_event =
 				arch_timer_set_next_event_virt_mem;
 		} else {
 			clk->set_state_shutdown = arch_timer_shutdown_phys_mem;
+			clk->set_state_oneshot_stopped = arch_timer_shutdown_phys_mem;
 			clk->set_next_event =
 				arch_timer_set_next_event_phys_mem;
 		}
@@ -338,17 +356,20 @@ static void arch_counter_set_user_access(void)
 	arch_timer_set_cntkctl(cntkctl);
 }
 
+static bool arch_timer_has_nonsecure_ppi(void)
+{
+	return (arch_timer_uses_ppi == PHYS_SECURE_PPI &&
+		arch_timer_ppi[PHYS_NONSECURE_PPI]);
+}
+
 static int arch_timer_setup(struct clock_event_device *clk)
 {
 	__arch_timer_setup(ARCH_CP15_TIMER, clk);
 
-	if (arch_timer_use_virtual)
-		enable_percpu_irq(arch_timer_ppi[VIRT_PPI], 0);
-	else {
-		enable_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI], 0);
-		if (arch_timer_ppi[PHYS_NONSECURE_PPI])
-			enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], 0);
-	}
+	enable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], 0);
+
+	if (arch_timer_has_nonsecure_ppi())
+		enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], 0);
 
 	arch_counter_set_user_access();
 	if (IS_ENABLED(CONFIG_ARM_ARCH_TIMER_EVTSTREAM))
@@ -390,7 +411,7 @@ static void arch_timer_banner(unsigned type)
 		     (unsigned long)arch_timer_rate / 1000000,
 		     (unsigned long)(arch_timer_rate / 10000) % 100,
 		     type & ARCH_CP15_TIMER ?
-			arch_timer_use_virtual ? "virt" : "phys" :
+		     (arch_timer_uses_ppi == VIRT_PPI) ? "virt" : "phys" :
 			"",
 		     type == (ARCH_CP15_TIMER | ARCH_MEM_TIMER) ?  "/" : "",
 		     type & ARCH_MEM_TIMER ?
@@ -460,7 +481,7 @@ static void __init arch_counter_register(unsigned type)
 
 	/* Register the CP15 based counter if we have one */
 	if (type & ARCH_CP15_TIMER) {
-		if (IS_ENABLED(CONFIG_ARM64) || arch_timer_use_virtual)
+		if (IS_ENABLED(CONFIG_ARM64) || arch_timer_uses_ppi == VIRT_PPI)
 			arch_timer_read_counter = arch_counter_get_cntvct;
 		else
 			arch_timer_read_counter = arch_counter_get_cntpct;
@@ -490,13 +511,9 @@ static void arch_timer_stop(struct clock_event_device *clk)
 	pr_debug("arch_timer_teardown disable IRQ%d cpu #%d\n",
 		 clk->irq, smp_processor_id());
 
-	if (arch_timer_use_virtual)
-		disable_percpu_irq(arch_timer_ppi[VIRT_PPI]);
-	else {
-		disable_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI]);
-		if (arch_timer_ppi[PHYS_NONSECURE_PPI])
-			disable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI]);
-	}
+	disable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi]);
+	if (arch_timer_has_nonsecure_ppi())
+		disable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI]);
 
 	clk->set_state_shutdown(clk);
 }
@@ -562,12 +579,14 @@ static int __init arch_timer_register(void)
 		goto out;
 	}
 
-	if (arch_timer_use_virtual) {
-		ppi = arch_timer_ppi[VIRT_PPI];
+	ppi = arch_timer_ppi[arch_timer_uses_ppi];
+	switch (arch_timer_uses_ppi) {
+	case VIRT_PPI:
 		err = request_percpu_irq(ppi, arch_timer_handler_virt,
 					 "arch_timer", arch_timer_evt);
-	} else {
-		ppi = arch_timer_ppi[PHYS_SECURE_PPI];
+		break;
+	case PHYS_SECURE_PPI:
+	case PHYS_NONSECURE_PPI:
 		err = request_percpu_irq(ppi, arch_timer_handler_phys,
 					 "arch_timer", arch_timer_evt);
 		if (!err && arch_timer_ppi[PHYS_NONSECURE_PPI]) {
@@ -578,6 +597,13 @@ static int __init arch_timer_register(void)
 				free_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI],
 						arch_timer_evt);
 		}
+		break;
+	case HYP_PPI:
+		err = request_percpu_irq(ppi, arch_timer_handler_phys,
+					 "arch_timer", arch_timer_evt);
+		break;
+	default:
+		BUG();
 	}
 
 	if (err) {
@@ -602,15 +628,10 @@ static int __init arch_timer_register(void)
 out_unreg_notify:
 	unregister_cpu_notifier(&arch_timer_cpu_nb);
 out_free_irq:
-	if (arch_timer_use_virtual)
-		free_percpu_irq(arch_timer_ppi[VIRT_PPI], arch_timer_evt);
-	else {
-		free_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI],
+	free_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], arch_timer_evt);
+	if (arch_timer_has_nonsecure_ppi())
+		free_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI],
 				arch_timer_evt);
-		if (arch_timer_ppi[PHYS_NONSECURE_PPI])
-			free_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI],
-					arch_timer_evt);
-	}
 
 out_free:
 	free_percpu(arch_timer_evt);
@@ -697,12 +718,25 @@ static void __init arch_timer_init(void)
 	 *
 	 * If no interrupt provided for virtual timer, we'll have to
 	 * stick to the physical timer. It'd better be accessible...
+	 *
+	 * On ARMv8.1 with VH extensions, the kernel runs in HYP. VHE
+	 * accesses to CNTP_*_EL1 registers are silently redirected to
+	 * their CNTHP_*_EL2 counterparts, and use a different PPI
+	 * number.
 	 */
 	if (is_hyp_mode_available() || !arch_timer_ppi[VIRT_PPI]) {
-		arch_timer_use_virtual = false;
+		bool has_ppi;
 
-		if (!arch_timer_ppi[PHYS_SECURE_PPI] ||
-		    !arch_timer_ppi[PHYS_NONSECURE_PPI]) {
+		if (is_kernel_in_hyp_mode()) {
+			arch_timer_uses_ppi = HYP_PPI;
+			has_ppi = !!arch_timer_ppi[HYP_PPI];
+		} else {
+			arch_timer_uses_ppi = PHYS_SECURE_PPI;
+			has_ppi = (!!arch_timer_ppi[PHYS_SECURE_PPI] ||
+				   !!arch_timer_ppi[PHYS_NONSECURE_PPI]);
+		}
+
+		if (!has_ppi) {
 			pr_warn("arch_timer: No interrupt available, giving up\n");
 			return;
 		}
@@ -735,7 +769,7 @@ static void __init arch_timer_of_init(struct device_node *np)
 	 */
 	if (IS_ENABLED(CONFIG_ARM) &&
 	    of_property_read_bool(np, "arm,cpu-registers-not-fw-configured"))
-			arch_timer_use_virtual = false;
+		arch_timer_uses_ppi = PHYS_SECURE_PPI;
 
 	arch_timer_init();
 }
@@ -757,7 +791,6 @@ static void __init arch_timer_mem_init(struct device_node *np)
 	}
 
 	cnttidr = readl_relaxed(cntctlbase + CNTTIDR);
-	iounmap(cntctlbase);
 
 	/*
 	 * Try to find a virtual capable frame. Otherwise fall back to a
@@ -765,20 +798,31 @@ static void __init arch_timer_mem_init(struct device_node *np)
 	 */
 	for_each_available_child_of_node(np, frame) {
 		int n;
+		u32 cntacr;
 
 		if (of_property_read_u32(frame, "frame-number", &n)) {
 			pr_err("arch_timer: Missing frame-number\n");
-			of_node_put(best_frame);
 			of_node_put(frame);
-			return;
+			goto out;
 		}
 
-		if (cnttidr & CNTTIDR_VIRT(n)) {
+		/* Try enabling everything, and see what sticks */
+		cntacr = CNTACR_RFRQ | CNTACR_RWPT | CNTACR_RPCT |
+			 CNTACR_RWVT | CNTACR_RVOFF | CNTACR_RVCT;
+		writel_relaxed(cntacr, cntctlbase + CNTACR(n));
+		cntacr = readl_relaxed(cntctlbase + CNTACR(n));
+
+		if ((cnttidr & CNTTIDR_VIRT(n)) &&
+		    !(~cntacr & (CNTACR_RWVT | CNTACR_RVCT))) {
 			of_node_put(best_frame);
 			best_frame = frame;
 			arch_timer_mem_use_virtual = true;
 			break;
 		}
+
+		if (~cntacr & (CNTACR_RWPT | CNTACR_RPCT))
+			continue;
+
 		of_node_put(best_frame);
 		best_frame = of_node_get(frame);
 	}
@@ -786,24 +830,26 @@ static void __init arch_timer_mem_init(struct device_node *np)
 	base = arch_counter_base = of_iomap(best_frame, 0);
 	if (!base) {
 		pr_err("arch_timer: Can't map frame's registers\n");
-		of_node_put(best_frame);
-		return;
+		goto out;
 	}
 
 	if (arch_timer_mem_use_virtual)
 		irq = irq_of_parse_and_map(best_frame, 1);
 	else
 		irq = irq_of_parse_and_map(best_frame, 0);
-	of_node_put(best_frame);
+
 	if (!irq) {
 		pr_err("arch_timer: Frame missing %s irq",
 		       arch_timer_mem_use_virtual ? "virt" : "phys");
-		return;
+		goto out;
 	}
 
 	arch_timer_detect_rate(base, np);
 	arch_timer_mem_register(base, irq);
 	arch_timer_common_init();
+out:
+	iounmap(cntctlbase);
+	of_node_put(best_frame);
 }
 CLOCKSOURCE_OF_DECLARE(armv7_arch_timer_mem, "arm,armv7-timer-mem",
 		       arch_timer_mem_init);
diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c
index d189d8cb69f7..9df0d1699d22 100644
--- a/drivers/clocksource/arm_global_timer.c
+++ b/drivers/clocksource/arm_global_timer.c
@@ -16,6 +16,7 @@
 #include <linux/clockchips.h>
 #include <linux/cpu.h>
 #include <linux/clk.h>
+#include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/of.h>
@@ -174,6 +175,7 @@ static int gt_clockevents_init(struct clock_event_device *clk)
 	clk->set_state_shutdown = gt_clockevent_shutdown;
 	clk->set_state_periodic = gt_clockevent_set_periodic;
 	clk->set_state_oneshot = gt_clockevent_shutdown;
+	clk->set_state_oneshot_stopped = gt_clockevent_shutdown;
 	clk->set_next_event = gt_clockevent_set_next_event;
 	clk->cpumask = cpumask_of(cpu);
 	clk->rating = 300;
@@ -221,6 +223,21 @@ static u64 notrace gt_sched_clock_read(void)
 }
 #endif
 
+static unsigned long gt_read_long(void)
+{
+	return readl_relaxed(gt_base + GT_COUNTER0);
+}
+
+static struct delay_timer gt_delay_timer = {
+	.read_current_timer = gt_read_long,
+};
+
+static void __init gt_delay_timer_init(void)
+{
+	gt_delay_timer.freq = gt_clk_rate;
+	register_current_timer_delay(&gt_delay_timer);
+}
+
 static void __init gt_clocksource_init(void)
 {
 	writel(0, gt_base + GT_CONTROL);
@@ -317,6 +334,7 @@ static void __init global_timer_of_register(struct device_node *np)
 	/* Immediately configure the timer on the boot CPU */
 	gt_clocksource_init();
 	gt_clockevents_init(this_cpu_ptr(gt_evt));
+	gt_delay_timer_init();
 
 	return;
 
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index ff44082a0827..be09bc0b5e26 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -313,6 +313,7 @@ static struct clock_event_device mct_comp_device = {
 	.set_state_periodic	= mct_set_state_periodic,
 	.set_state_shutdown	= mct_set_state_shutdown,
 	.set_state_oneshot	= mct_set_state_shutdown,
+	.set_state_oneshot_stopped = mct_set_state_shutdown,
 	.tick_resume		= mct_set_state_shutdown,
 };
 
@@ -452,6 +453,7 @@ static int exynos4_local_timer_setup(struct mct_clock_event_device *mevt)
 	evt->set_state_periodic = set_state_periodic;
 	evt->set_state_shutdown = set_state_shutdown;
 	evt->set_state_oneshot = set_state_shutdown;
+	evt->set_state_oneshot_stopped = set_state_shutdown;
 	evt->tick_resume = set_state_shutdown;
 	evt->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
 	evt->rating = 450;
diff --git a/drivers/clocksource/rockchip_timer.c b/drivers/clocksource/rockchip_timer.c
index 8c77a529d0d4..b991b288c803 100644
--- a/drivers/clocksource/rockchip_timer.c
+++ b/drivers/clocksource/rockchip_timer.c
@@ -122,23 +122,23 @@ static void __init rk_timer_init(struct device_node *np)
 	pclk = of_clk_get_by_name(np, "pclk");
 	if (IS_ERR(pclk)) {
 		pr_err("Failed to get pclk for '%s'\n", TIMER_NAME);
-		return;
+		goto out_unmap;
 	}
 
 	if (clk_prepare_enable(pclk)) {
 		pr_err("Failed to enable pclk for '%s'\n", TIMER_NAME);
-		return;
+		goto out_unmap;
 	}
 
 	timer_clk = of_clk_get_by_name(np, "timer");
 	if (IS_ERR(timer_clk)) {
 		pr_err("Failed to get timer clock for '%s'\n", TIMER_NAME);
-		return;
+		goto out_timer_clk;
 	}
 
 	if (clk_prepare_enable(timer_clk)) {
 		pr_err("Failed to enable timer clock\n");
-		return;
+		goto out_timer_clk;
 	}
 
 	bc_timer.freq = clk_get_rate(timer_clk);
@@ -146,7 +146,7 @@ static void __init rk_timer_init(struct device_node *np)
 	irq = irq_of_parse_and_map(np, 0);
 	if (!irq) {
 		pr_err("Failed to map interrupts for '%s'\n", TIMER_NAME);
-		return;
+		goto out_irq;
 	}
 
 	ce->name = TIMER_NAME;
@@ -164,10 +164,19 @@ static void __init rk_timer_init(struct device_node *np)
 	ret = request_irq(irq, rk_timer_interrupt, IRQF_TIMER, TIMER_NAME, ce);
 	if (ret) {
 		pr_err("Failed to initialize '%s': %d\n", TIMER_NAME, ret);
-		return;
+		goto out_irq;
 	}
 
 	clockevents_config_and_register(ce, bc_timer.freq, 1, UINT_MAX);
+
+	return;
+
+out_irq:
+	clk_disable_unprepare(timer_clk);
+out_timer_clk:
+	clk_disable_unprepare(pclk);
+out_unmap:
+	iounmap(bc_timer.base);
 }
 
 CLOCKSOURCE_OF_DECLARE(rk_timer, "rockchip,rk3288-timer", rk_timer_init);
diff --git a/drivers/clocksource/time-lpc32xx.c b/drivers/clocksource/time-lpc32xx.c
index 1316876b487a..daae61e8c820 100644
--- a/drivers/clocksource/time-lpc32xx.c
+++ b/drivers/clocksource/time-lpc32xx.c
@@ -18,6 +18,7 @@
 #include <linux/clk.h>
 #include <linux/clockchips.h>
 #include <linux/clocksource.h>
+#include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/kernel.h>
@@ -43,6 +44,7 @@
 struct lpc32xx_clock_event_ddata {
 	struct clock_event_device evtdev;
 	void __iomem *base;
+	u32 ticks_per_jiffy;
 };
 
 /* Needed for the sched clock */
@@ -53,6 +55,15 @@ static u64 notrace lpc32xx_read_sched_clock(void)
 	return readl(clocksource_timer_counter);
 }
 
+static unsigned long lpc32xx_delay_timer_read(void)
+{
+	return readl(clocksource_timer_counter);
+}
+
+static struct delay_timer lpc32xx_delay_timer = {
+	.read_current_timer = lpc32xx_delay_timer_read,
+};
+
 static int lpc32xx_clkevt_next_event(unsigned long delta,
 				     struct clock_event_device *evtdev)
 {
@@ -60,14 +71,13 @@ static int lpc32xx_clkevt_next_event(unsigned long delta,
 		container_of(evtdev, struct lpc32xx_clock_event_ddata, evtdev);
 
 	/*
-	 * Place timer in reset and program the delta in the prescale
-	 * register (PR). When the prescale counter matches the value
-	 * in PR the counter register is incremented and the compare
-	 * match will trigger. After setup the timer is released from
-	 * reset and enabled.
+	 * Place timer in reset and program the delta in the match
+	 * channel 0 (MR0). When the timer counter matches the value
+	 * in MR0 register the match will trigger an interrupt.
+	 * After setup the timer is released from reset and enabled.
 	 */
 	writel_relaxed(LPC32XX_TIMER_TCR_CRST, ddata->base + LPC32XX_TIMER_TCR);
-	writel_relaxed(delta, ddata->base + LPC32XX_TIMER_PR);
+	writel_relaxed(delta, ddata->base + LPC32XX_TIMER_MR0);
 	writel_relaxed(LPC32XX_TIMER_TCR_CEN, ddata->base + LPC32XX_TIMER_TCR);
 
 	return 0;
@@ -86,11 +96,39 @@ static int lpc32xx_clkevt_shutdown(struct clock_event_device *evtdev)
 
 static int lpc32xx_clkevt_oneshot(struct clock_event_device *evtdev)
 {
+	struct lpc32xx_clock_event_ddata *ddata =
+		container_of(evtdev, struct lpc32xx_clock_event_ddata, evtdev);
+
 	/*
 	 * When using oneshot, we must also disable the timer
 	 * to wait for the first call to set_next_event().
 	 */
-	return lpc32xx_clkevt_shutdown(evtdev);
+	writel_relaxed(0, ddata->base + LPC32XX_TIMER_TCR);
+
+	/* Enable interrupt, reset on match and stop on match (MCR). */
+	writel_relaxed(LPC32XX_TIMER_MCR_MR0I | LPC32XX_TIMER_MCR_MR0R |
+		       LPC32XX_TIMER_MCR_MR0S, ddata->base + LPC32XX_TIMER_MCR);
+	return 0;
+}
+
+static int lpc32xx_clkevt_periodic(struct clock_event_device *evtdev)
+{
+	struct lpc32xx_clock_event_ddata *ddata =
+		container_of(evtdev, struct lpc32xx_clock_event_ddata, evtdev);
+
+	/* Enable interrupt and reset on match. */
+	writel_relaxed(LPC32XX_TIMER_MCR_MR0I | LPC32XX_TIMER_MCR_MR0R,
+		       ddata->base + LPC32XX_TIMER_MCR);
+
+	/*
+	 * Place timer in reset and program the delta in the match
+	 * channel 0 (MR0).
+	 */
+	writel_relaxed(LPC32XX_TIMER_TCR_CRST, ddata->base + LPC32XX_TIMER_TCR);
+	writel_relaxed(ddata->ticks_per_jiffy, ddata->base + LPC32XX_TIMER_MR0);
+	writel_relaxed(LPC32XX_TIMER_TCR_CEN, ddata->base + LPC32XX_TIMER_TCR);
+
+	return 0;
 }
 
 static irqreturn_t lpc32xx_clock_event_handler(int irq, void *dev_id)
@@ -108,11 +146,13 @@ static irqreturn_t lpc32xx_clock_event_handler(int irq, void *dev_id)
 static struct lpc32xx_clock_event_ddata lpc32xx_clk_event_ddata = {
 	.evtdev = {
 		.name			= "lpc3220 clockevent",
-		.features		= CLOCK_EVT_FEAT_ONESHOT,
+		.features		= CLOCK_EVT_FEAT_ONESHOT |
+					  CLOCK_EVT_FEAT_PERIODIC,
 		.rating			= 300,
 		.set_next_event		= lpc32xx_clkevt_next_event,
 		.set_state_shutdown	= lpc32xx_clkevt_shutdown,
 		.set_state_oneshot	= lpc32xx_clkevt_oneshot,
+		.set_state_periodic	= lpc32xx_clkevt_periodic,
 	},
 };
 
@@ -162,6 +202,8 @@ static int __init lpc32xx_clocksource_init(struct device_node *np)
 	}
 
 	clocksource_timer_counter = base + LPC32XX_TIMER_TC;
+	lpc32xx_delay_timer.freq = rate;
+	register_current_timer_delay(&lpc32xx_delay_timer);
 	sched_clock_register(lpc32xx_read_sched_clock, 32, rate);
 
 	return 0;
@@ -210,18 +252,16 @@ static int __init lpc32xx_clockevent_init(struct device_node *np)
 
 	/*
 	 * Disable timer and clear any pending interrupt (IR) on match
-	 * channel 0 (MR0). Configure a compare match value of 1 on MR0
-	 * and enable interrupt, reset on match and stop on match (MCR).
+	 * channel 0 (MR0). Clear the prescaler as it's not used.
 	 */
 	writel_relaxed(0, base + LPC32XX_TIMER_TCR);
+	writel_relaxed(0, base + LPC32XX_TIMER_PR);
 	writel_relaxed(0, base + LPC32XX_TIMER_CTCR);
 	writel_relaxed(LPC32XX_TIMER_IR_MR0INT, base + LPC32XX_TIMER_IR);
-	writel_relaxed(1, base + LPC32XX_TIMER_MR0);
-	writel_relaxed(LPC32XX_TIMER_MCR_MR0I | LPC32XX_TIMER_MCR_MR0R |
-		       LPC32XX_TIMER_MCR_MR0S, base + LPC32XX_TIMER_MCR);
 
 	rate = clk_get_rate(clk);
 	lpc32xx_clk_event_ddata.base = base;
+	lpc32xx_clk_event_ddata.ticks_per_jiffy = DIV_ROUND_CLOSEST(rate, HZ);
 	clockevents_config_and_register(&lpc32xx_clk_event_ddata.evtdev,
 					rate, 1, -1);
 
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 659879a56dba..a7f45853c103 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -19,6 +19,7 @@ config CPU_FREQ
 if CPU_FREQ
 
 config CPU_FREQ_GOV_COMMON
+	select IRQ_WORK
 	bool
 
 config CPU_FREQ_BOOST_SW
@@ -296,6 +297,7 @@ endif
 config QORIQ_CPUFREQ
 	tristate "CPU frequency scaling driver for Freescale QorIQ SoCs"
 	depends on OF && COMMON_CLK && (PPC_E500MC || ARM)
+	depends on !CPU_THERMAL || THERMAL
 	select CLK_QORIQ
 	help
 	  This adds the CPUFreq driver support for Freescale QorIQ SoCs
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 0031069b64c9..14b1f9393b05 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -84,10 +84,10 @@ config ARM_KIRKWOOD_CPUFREQ
 	  SoCs.
 
 config ARM_MT8173_CPUFREQ
-	bool "Mediatek MT8173 CPUFreq support"
+	tristate "Mediatek MT8173 CPUFreq support"
 	depends on ARCH_MEDIATEK && REGULATOR
 	depends on ARM64 || (ARM_CPU_TOPOLOGY && COMPILE_TEST)
-	depends on !CPU_THERMAL || THERMAL=y
+	depends on !CPU_THERMAL || THERMAL
 	select PM_OPP
 	help
 	  This adds the CPUFreq driver support for Mediatek MT8173 SoC.
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 51eef87bbc37..59a7b380fbe2 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -70,6 +70,8 @@ struct acpi_cpufreq_data {
 	unsigned int cpu_feature;
 	unsigned int acpi_perf_cpu;
 	cpumask_var_t freqdomain_cpus;
+	void (*cpu_freq_write)(struct acpi_pct_register *reg, u32 val);
+	u32 (*cpu_freq_read)(struct acpi_pct_register *reg);
 };
 
 /* acpi_perf_data is a pointer to percpu data. */
@@ -243,125 +245,119 @@ static unsigned extract_freq(u32 val, struct acpi_cpufreq_data *data)
 	}
 }
 
-struct msr_addr {
-	u32 reg;
-};
+u32 cpu_freq_read_intel(struct acpi_pct_register *not_used)
+{
+	u32 val, dummy;
 
-struct io_addr {
-	u16 port;
-	u8 bit_width;
-};
+	rdmsr(MSR_IA32_PERF_CTL, val, dummy);
+	return val;
+}
+
+void cpu_freq_write_intel(struct acpi_pct_register *not_used, u32 val)
+{
+	u32 lo, hi;
+
+	rdmsr(MSR_IA32_PERF_CTL, lo, hi);
+	lo = (lo & ~INTEL_MSR_RANGE) | (val & INTEL_MSR_RANGE);
+	wrmsr(MSR_IA32_PERF_CTL, lo, hi);
+}
+
+u32 cpu_freq_read_amd(struct acpi_pct_register *not_used)
+{
+	u32 val, dummy;
+
+	rdmsr(MSR_AMD_PERF_CTL, val, dummy);
+	return val;
+}
+
+void cpu_freq_write_amd(struct acpi_pct_register *not_used, u32 val)
+{
+	wrmsr(MSR_AMD_PERF_CTL, val, 0);
+}
+
+u32 cpu_freq_read_io(struct acpi_pct_register *reg)
+{
+	u32 val;
+
+	acpi_os_read_port(reg->address, &val, reg->bit_width);
+	return val;
+}
+
+void cpu_freq_write_io(struct acpi_pct_register *reg, u32 val)
+{
+	acpi_os_write_port(reg->address, val, reg->bit_width);
+}
 
 struct drv_cmd {
-	unsigned int type;
-	const struct cpumask *mask;
-	union {
-		struct msr_addr msr;
-		struct io_addr io;
-	} addr;
+	struct acpi_pct_register *reg;
 	u32 val;
+	union {
+		void (*write)(struct acpi_pct_register *reg, u32 val);
+		u32 (*read)(struct acpi_pct_register *reg);
+	} func;
 };
 
 /* Called via smp_call_function_single(), on the target CPU */
 static void do_drv_read(void *_cmd)
 {
 	struct drv_cmd *cmd = _cmd;
-	u32 h;
 
-	switch (cmd->type) {
-	case SYSTEM_INTEL_MSR_CAPABLE:
-	case SYSTEM_AMD_MSR_CAPABLE:
-		rdmsr(cmd->addr.msr.reg, cmd->val, h);
-		break;
-	case SYSTEM_IO_CAPABLE:
-		acpi_os_read_port((acpi_io_address)cmd->addr.io.port,
-				&cmd->val,
-				(u32)cmd->addr.io.bit_width);
-		break;
-	default:
-		break;
-	}
+	cmd->val = cmd->func.read(cmd->reg);
 }
 
-/* Called via smp_call_function_many(), on the target CPUs */
-static void do_drv_write(void *_cmd)
+static u32 drv_read(struct acpi_cpufreq_data *data, const struct cpumask *mask)
 {
-	struct drv_cmd *cmd = _cmd;
-	u32 lo, hi;
+	struct acpi_processor_performance *perf = to_perf_data(data);
+	struct drv_cmd cmd = {
+		.reg = &perf->control_register,
+		.func.read = data->cpu_freq_read,
+	};
+	int err;
 
-	switch (cmd->type) {
-	case SYSTEM_INTEL_MSR_CAPABLE:
-		rdmsr(cmd->addr.msr.reg, lo, hi);
-		lo = (lo & ~INTEL_MSR_RANGE) | (cmd->val & INTEL_MSR_RANGE);
-		wrmsr(cmd->addr.msr.reg, lo, hi);
-		break;
-	case SYSTEM_AMD_MSR_CAPABLE:
-		wrmsr(cmd->addr.msr.reg, cmd->val, 0);
-		break;
-	case SYSTEM_IO_CAPABLE:
-		acpi_os_write_port((acpi_io_address)cmd->addr.io.port,
-				cmd->val,
-				(u32)cmd->addr.io.bit_width);
-		break;
-	default:
-		break;
-	}
+	err = smp_call_function_any(mask, do_drv_read, &cmd, 1);
+	WARN_ON_ONCE(err);	/* smp_call_function_any() was buggy? */
+	return cmd.val;
 }
 
-static void drv_read(struct drv_cmd *cmd)
+/* Called via smp_call_function_many(), on the target CPUs */
+static void do_drv_write(void *_cmd)
 {
-	int err;
-	cmd->val = 0;
+	struct drv_cmd *cmd = _cmd;
 
-	err = smp_call_function_any(cmd->mask, do_drv_read, cmd, 1);
-	WARN_ON_ONCE(err);	/* smp_call_function_any() was buggy? */
+	cmd->func.write(cmd->reg, cmd->val);
 }
 
-static void drv_write(struct drv_cmd *cmd)
+static void drv_write(struct acpi_cpufreq_data *data,
+		      const struct cpumask *mask, u32 val)
 {
+	struct acpi_processor_performance *perf = to_perf_data(data);
+	struct drv_cmd cmd = {
+		.reg = &perf->control_register,
+		.val = val,
+		.func.write = data->cpu_freq_write,
+	};
 	int this_cpu;
 
 	this_cpu = get_cpu();
-	if (cpumask_test_cpu(this_cpu, cmd->mask))
-		do_drv_write(cmd);
-	smp_call_function_many(cmd->mask, do_drv_write, cmd, 1);
+	if (cpumask_test_cpu(this_cpu, mask))
+		do_drv_write(&cmd);
+
+	smp_call_function_many(mask, do_drv_write, &cmd, 1);
 	put_cpu();
 }
 
-static u32
-get_cur_val(const struct cpumask *mask, struct acpi_cpufreq_data *data)
+static u32 get_cur_val(const struct cpumask *mask, struct acpi_cpufreq_data *data)
 {
-	struct acpi_processor_performance *perf;
-	struct drv_cmd cmd;
+	u32 val;
 
 	if (unlikely(cpumask_empty(mask)))
 		return 0;
 
-	switch (data->cpu_feature) {
-	case SYSTEM_INTEL_MSR_CAPABLE:
-		cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
-		cmd.addr.msr.reg = MSR_IA32_PERF_CTL;
-		break;
-	case SYSTEM_AMD_MSR_CAPABLE:
-		cmd.type = SYSTEM_AMD_MSR_CAPABLE;
-		cmd.addr.msr.reg = MSR_AMD_PERF_CTL;
-		break;
-	case SYSTEM_IO_CAPABLE:
-		cmd.type = SYSTEM_IO_CAPABLE;
-		perf = to_perf_data(data);
-		cmd.addr.io.port = perf->control_register.address;
-		cmd.addr.io.bit_width = perf->control_register.bit_width;
-		break;
-	default:
-		return 0;
-	}
-
-	cmd.mask = mask;
-	drv_read(&cmd);
+	val = drv_read(data, mask);
 
-	pr_debug("get_cur_val = %u\n", cmd.val);
+	pr_debug("get_cur_val = %u\n", val);
 
-	return cmd.val;
+	return val;
 }
 
 static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
@@ -416,7 +412,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 {
 	struct acpi_cpufreq_data *data = policy->driver_data;
 	struct acpi_processor_performance *perf;
-	struct drv_cmd cmd;
+	const struct cpumask *mask;
 	unsigned int next_perf_state = 0; /* Index into perf table */
 	int result = 0;
 
@@ -434,42 +430,21 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 		} else {
 			pr_debug("Already at target state (P%d)\n",
 				next_perf_state);
-			goto out;
+			return 0;
 		}
 	}
 
-	switch (data->cpu_feature) {
-	case SYSTEM_INTEL_MSR_CAPABLE:
-		cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
-		cmd.addr.msr.reg = MSR_IA32_PERF_CTL;
-		cmd.val = (u32) perf->states[next_perf_state].control;
-		break;
-	case SYSTEM_AMD_MSR_CAPABLE:
-		cmd.type = SYSTEM_AMD_MSR_CAPABLE;
-		cmd.addr.msr.reg = MSR_AMD_PERF_CTL;
-		cmd.val = (u32) perf->states[next_perf_state].control;
-		break;
-	case SYSTEM_IO_CAPABLE:
-		cmd.type = SYSTEM_IO_CAPABLE;
-		cmd.addr.io.port = perf->control_register.address;
-		cmd.addr.io.bit_width = perf->control_register.bit_width;
-		cmd.val = (u32) perf->states[next_perf_state].control;
-		break;
-	default:
-		result = -ENODEV;
-		goto out;
-	}
-
-	/* cpufreq holds the hotplug lock, so we are safe from here on */
-	if (policy->shared_type != CPUFREQ_SHARED_TYPE_ANY)
-		cmd.mask = policy->cpus;
-	else
-		cmd.mask = cpumask_of(policy->cpu);
+	/*
+	 * The core won't allow CPUs to go away until the governor has been
+	 * stopped, so we can rely on the stability of policy->cpus.
+	 */
+	mask = policy->shared_type == CPUFREQ_SHARED_TYPE_ANY ?
+		cpumask_of(policy->cpu) : policy->cpus;
 
-	drv_write(&cmd);
+	drv_write(data, mask, perf->states[next_perf_state].control);
 
 	if (acpi_pstate_strict) {
-		if (!check_freqs(cmd.mask, data->freq_table[index].frequency,
+		if (!check_freqs(mask, data->freq_table[index].frequency,
 					data)) {
 			pr_debug("acpi_cpufreq_target failed (%d)\n",
 				policy->cpu);
@@ -480,7 +455,6 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	if (!result)
 		perf->state = next_perf_state;
 
-out:
 	return result;
 }
 
@@ -740,15 +714,21 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		}
 		pr_debug("SYSTEM IO addr space\n");
 		data->cpu_feature = SYSTEM_IO_CAPABLE;
+		data->cpu_freq_read = cpu_freq_read_io;
+		data->cpu_freq_write = cpu_freq_write_io;
 		break;
 	case ACPI_ADR_SPACE_FIXED_HARDWARE:
 		pr_debug("HARDWARE addr space\n");
 		if (check_est_cpu(cpu)) {
 			data->cpu_feature = SYSTEM_INTEL_MSR_CAPABLE;
+			data->cpu_freq_read = cpu_freq_read_intel;
+			data->cpu_freq_write = cpu_freq_write_intel;
 			break;
 		}
 		if (check_amd_hwpstate_cpu(cpu)) {
 			data->cpu_feature = SYSTEM_AMD_MSR_CAPABLE;
+			data->cpu_freq_read = cpu_freq_read_amd;
+			data->cpu_freq_write = cpu_freq_write_amd;
 			break;
 		}
 		result = -ENODEV;
diff --git a/drivers/cpufreq/amd_freq_sensitivity.c b/drivers/cpufreq/amd_freq_sensitivity.c
index f6b79ab0070b..404360cad25c 100644
--- a/drivers/cpufreq/amd_freq_sensitivity.c
+++ b/drivers/cpufreq/amd_freq_sensitivity.c
@@ -21,7 +21,7 @@
 #include <asm/msr.h>
 #include <asm/cpufeature.h>
 
-#include "cpufreq_governor.h"
+#include "cpufreq_ondemand.h"
 
 #define MSR_AMD64_FREQ_SENSITIVITY_ACTUAL	0xc0010080
 #define MSR_AMD64_FREQ_SENSITIVITY_REFERENCE	0xc0010081
@@ -45,10 +45,10 @@ static unsigned int amd_powersave_bias_target(struct cpufreq_policy *policy,
 	long d_actual, d_reference;
 	struct msr actual, reference;
 	struct cpu_data_t *data = &per_cpu(cpu_data, policy->cpu);
-	struct dbs_data *od_data = policy->governor_data;
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct dbs_data *od_data = policy_dbs->dbs_data;
 	struct od_dbs_tuners *od_tuners = od_data->tuners;
-	struct od_cpu_dbs_info_s *od_info =
-		od_data->cdata->get_cpu_dbs_info_s(policy->cpu);
+	struct od_policy_dbs_info *od_info = to_dbs_info(policy_dbs);
 
 	if (!od_info->freq_table)
 		return freq_next;
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 0ca74d070058..f951f911786e 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -31,9 +31,8 @@
 
 struct private_data {
 	struct device *cpu_dev;
-	struct regulator *cpu_reg;
 	struct thermal_cooling_device *cdev;
-	unsigned int voltage_tolerance; /* in percentage */
+	const char *reg_name;
 };
 
 static struct freq_attr *cpufreq_dt_attr[] = {
@@ -44,175 +43,128 @@ static struct freq_attr *cpufreq_dt_attr[] = {
 
 static int set_target(struct cpufreq_policy *policy, unsigned int index)
 {
-	struct dev_pm_opp *opp;
-	struct cpufreq_frequency_table *freq_table = policy->freq_table;
-	struct clk *cpu_clk = policy->clk;
 	struct private_data *priv = policy->driver_data;
-	struct device *cpu_dev = priv->cpu_dev;
-	struct regulator *cpu_reg = priv->cpu_reg;
-	unsigned long volt = 0, tol = 0;
-	int volt_old = 0;
-	unsigned int old_freq, new_freq;
-	long freq_Hz, freq_exact;
-	int ret;
-
-	freq_Hz = clk_round_rate(cpu_clk, freq_table[index].frequency * 1000);
-	if (freq_Hz <= 0)
-		freq_Hz = freq_table[index].frequency * 1000;
 
-	freq_exact = freq_Hz;
-	new_freq = freq_Hz / 1000;
-	old_freq = clk_get_rate(cpu_clk) / 1000;
+	return dev_pm_opp_set_rate(priv->cpu_dev,
+				   policy->freq_table[index].frequency * 1000);
+}
 
-	if (!IS_ERR(cpu_reg)) {
-		unsigned long opp_freq;
+/*
+ * An earlier version of opp-v1 bindings used to name the regulator
+ * "cpu0-supply", we still need to handle that for backwards compatibility.
+ */
+static const char *find_supply_name(struct device *dev)
+{
+	struct device_node *np;
+	struct property *pp;
+	int cpu = dev->id;
+	const char *name = NULL;
 
-		rcu_read_lock();
-		opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_Hz);
-		if (IS_ERR(opp)) {
-			rcu_read_unlock();
-			dev_err(cpu_dev, "failed to find OPP for %ld\n",
-				freq_Hz);
-			return PTR_ERR(opp);
-		}
-		volt = dev_pm_opp_get_voltage(opp);
-		opp_freq = dev_pm_opp_get_freq(opp);
-		rcu_read_unlock();
-		tol = volt * priv->voltage_tolerance / 100;
-		volt_old = regulator_get_voltage(cpu_reg);
-		dev_dbg(cpu_dev, "Found OPP: %ld kHz, %ld uV\n",
-			opp_freq / 1000, volt);
-	}
+	np = of_node_get(dev->of_node);
 
-	dev_dbg(cpu_dev, "%u MHz, %d mV --> %u MHz, %ld mV\n",
-		old_freq / 1000, (volt_old > 0) ? volt_old / 1000 : -1,
-		new_freq / 1000, volt ? volt / 1000 : -1);
+	/* This must be valid for sure */
+	if (WARN_ON(!np))
+		return NULL;
 
-	/* scaling up?  scale voltage before frequency */
-	if (!IS_ERR(cpu_reg) && new_freq > old_freq) {
-		ret = regulator_set_voltage_tol(cpu_reg, volt, tol);
-		if (ret) {
-			dev_err(cpu_dev, "failed to scale voltage up: %d\n",
-				ret);
-			return ret;
+	/* Try "cpu0" for older DTs */
+	if (!cpu) {
+		pp = of_find_property(np, "cpu0-supply", NULL);
+		if (pp) {
+			name = "cpu0";
+			goto node_put;
 		}
 	}
 
-	ret = clk_set_rate(cpu_clk, freq_exact);
-	if (ret) {
-		dev_err(cpu_dev, "failed to set clock rate: %d\n", ret);
-		if (!IS_ERR(cpu_reg) && volt_old > 0)
-			regulator_set_voltage_tol(cpu_reg, volt_old, tol);
-		return ret;
+	pp = of_find_property(np, "cpu-supply", NULL);
+	if (pp) {
+		name = "cpu";
+		goto node_put;
 	}
 
-	/* scaling down?  scale voltage after frequency */
-	if (!IS_ERR(cpu_reg) && new_freq < old_freq) {
-		ret = regulator_set_voltage_tol(cpu_reg, volt, tol);
-		if (ret) {
-			dev_err(cpu_dev, "failed to scale voltage down: %d\n",
-				ret);
-			clk_set_rate(cpu_clk, old_freq * 1000);
-		}
-	}
-
-	return ret;
+	dev_dbg(dev, "no regulator for cpu%d\n", cpu);
+node_put:
+	of_node_put(np);
+	return name;
 }
 
-static int allocate_resources(int cpu, struct device **cdev,
-			      struct regulator **creg, struct clk **cclk)
+static int resources_available(void)
 {
 	struct device *cpu_dev;
 	struct regulator *cpu_reg;
 	struct clk *cpu_clk;
 	int ret = 0;
-	char *reg_cpu0 = "cpu0", *reg_cpu = "cpu", *reg;
+	const char *name;
 
-	cpu_dev = get_cpu_device(cpu);
+	cpu_dev = get_cpu_device(0);
 	if (!cpu_dev) {
-		pr_err("failed to get cpu%d device\n", cpu);
+		pr_err("failed to get cpu0 device\n");
 		return -ENODEV;
 	}
 
-	/* Try "cpu0" for older DTs */
-	if (!cpu)
-		reg = reg_cpu0;
-	else
-		reg = reg_cpu;
-
-try_again:
-	cpu_reg = regulator_get_optional(cpu_dev, reg);
-	ret = PTR_ERR_OR_ZERO(cpu_reg);
+	cpu_clk = clk_get(cpu_dev, NULL);
+	ret = PTR_ERR_OR_ZERO(cpu_clk);
 	if (ret) {
 		/*
-		 * If cpu's regulator supply node is present, but regulator is
-		 * not yet registered, we should try defering probe.
+		 * If cpu's clk node is present, but clock is not yet
+		 * registered, we should try defering probe.
 		 */
-		if (ret == -EPROBE_DEFER) {
-			dev_dbg(cpu_dev, "cpu%d regulator not ready, retry\n",
-				cpu);
-			return ret;
-		}
-
-		/* Try with "cpu-supply" */
-		if (reg == reg_cpu0) {
-			reg = reg_cpu;
-			goto try_again;
-		}
+		if (ret == -EPROBE_DEFER)
+			dev_dbg(cpu_dev, "clock not ready, retry\n");
+		else
+			dev_err(cpu_dev, "failed to get clock: %d\n", ret);
 
-		dev_dbg(cpu_dev, "no regulator for cpu%d: %d\n", cpu, ret);
+		return ret;
 	}
 
-	cpu_clk = clk_get(cpu_dev, NULL);
-	ret = PTR_ERR_OR_ZERO(cpu_clk);
-	if (ret) {
-		/* put regulator */
-		if (!IS_ERR(cpu_reg))
-			regulator_put(cpu_reg);
+	clk_put(cpu_clk);
 
+	name = find_supply_name(cpu_dev);
+	/* Platform doesn't require regulator */
+	if (!name)
+		return 0;
+
+	cpu_reg = regulator_get_optional(cpu_dev, name);
+	ret = PTR_ERR_OR_ZERO(cpu_reg);
+	if (ret) {
 		/*
-		 * If cpu's clk node is present, but clock is not yet
-		 * registered, we should try defering probe.
+		 * If cpu's regulator supply node is present, but regulator is
+		 * not yet registered, we should try defering probe.
 		 */
 		if (ret == -EPROBE_DEFER)
-			dev_dbg(cpu_dev, "cpu%d clock not ready, retry\n", cpu);
+			dev_dbg(cpu_dev, "cpu0 regulator not ready, retry\n");
 		else
-			dev_err(cpu_dev, "failed to get cpu%d clock: %d\n", cpu,
-				ret);
-	} else {
-		*cdev = cpu_dev;
-		*creg = cpu_reg;
-		*cclk = cpu_clk;
+			dev_dbg(cpu_dev, "no regulator for cpu0: %d\n", ret);
+
+		return ret;
 	}
 
-	return ret;
+	regulator_put(cpu_reg);
+	return 0;
 }
 
 static int cpufreq_init(struct cpufreq_policy *policy)
 {
 	struct cpufreq_frequency_table *freq_table;
-	struct device_node *np;
 	struct private_data *priv;
 	struct device *cpu_dev;
-	struct regulator *cpu_reg;
 	struct clk *cpu_clk;
 	struct dev_pm_opp *suspend_opp;
-	unsigned long min_uV = ~0, max_uV = 0;
 	unsigned int transition_latency;
-	bool need_update = false;
+	bool opp_v1 = false;
+	const char *name;
 	int ret;
 
-	ret = allocate_resources(policy->cpu, &cpu_dev, &cpu_reg, &cpu_clk);
-	if (ret) {
-		pr_err("%s: Failed to allocate resources: %d\n", __func__, ret);
-		return ret;
+	cpu_dev = get_cpu_device(policy->cpu);
+	if (!cpu_dev) {
+		pr_err("failed to get cpu%d device\n", policy->cpu);
+		return -ENODEV;
 	}
 
-	np = of_node_get(cpu_dev->of_node);
-	if (!np) {
-		dev_err(cpu_dev, "failed to find cpu%d node\n", policy->cpu);
-		ret = -ENOENT;
-		goto out_put_reg_clk;
+	cpu_clk = clk_get(cpu_dev, NULL);
+	if (IS_ERR(cpu_clk)) {
+		ret = PTR_ERR(cpu_clk);
+		dev_err(cpu_dev, "%s: failed to get clk: %d\n", __func__, ret);
+		return ret;
 	}
 
 	/* Get OPP-sharing information from "operating-points-v2" bindings */
@@ -223,9 +175,23 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		 * finding shared-OPPs for backward compatibility.
 		 */
 		if (ret == -ENOENT)
-			need_update = true;
+			opp_v1 = true;
 		else
-			goto out_node_put;
+			goto out_put_clk;
+	}
+
+	/*
+	 * OPP layer will be taking care of regulators now, but it needs to know
+	 * the name of the regulator first.
+	 */
+	name = find_supply_name(cpu_dev);
+	if (name) {
+		ret = dev_pm_opp_set_regulator(cpu_dev, name);
+		if (ret) {
+			dev_err(cpu_dev, "Failed to set regulator for cpu%d: %d\n",
+				policy->cpu, ret);
+			goto out_put_clk;
+		}
 	}
 
 	/*
@@ -246,12 +212,12 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	 */
 	ret = dev_pm_opp_get_opp_count(cpu_dev);
 	if (ret <= 0) {
-		pr_debug("OPP table is not ready, deferring probe\n");
+		dev_dbg(cpu_dev, "OPP table is not ready, deferring probe\n");
 		ret = -EPROBE_DEFER;
 		goto out_free_opp;
 	}
 
-	if (need_update) {
+	if (opp_v1) {
 		struct cpufreq_dt_platform_data *pd = cpufreq_get_driver_data();
 
 		if (!pd || !pd->independent_clocks)
@@ -265,10 +231,6 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		if (ret)
 			dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n",
 				__func__, ret);
-
-		of_property_read_u32(np, "clock-latency", &transition_latency);
-	} else {
-		transition_latency = dev_pm_opp_get_max_clock_latency(cpu_dev);
 	}
 
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
@@ -277,62 +239,16 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		goto out_free_opp;
 	}
 
-	of_property_read_u32(np, "voltage-tolerance", &priv->voltage_tolerance);
-
-	if (!transition_latency)
-		transition_latency = CPUFREQ_ETERNAL;
-
-	if (!IS_ERR(cpu_reg)) {
-		unsigned long opp_freq = 0;
-
-		/*
-		 * Disable any OPPs where the connected regulator isn't able to
-		 * provide the specified voltage and record minimum and maximum
-		 * voltage levels.
-		 */
-		while (1) {
-			struct dev_pm_opp *opp;
-			unsigned long opp_uV, tol_uV;
-
-			rcu_read_lock();
-			opp = dev_pm_opp_find_freq_ceil(cpu_dev, &opp_freq);
-			if (IS_ERR(opp)) {
-				rcu_read_unlock();
-				break;
-			}
-			opp_uV = dev_pm_opp_get_voltage(opp);
-			rcu_read_unlock();
-
-			tol_uV = opp_uV * priv->voltage_tolerance / 100;
-			if (regulator_is_supported_voltage(cpu_reg,
-							   opp_uV - tol_uV,
-							   opp_uV + tol_uV)) {
-				if (opp_uV < min_uV)
-					min_uV = opp_uV;
-				if (opp_uV > max_uV)
-					max_uV = opp_uV;
-			} else {
-				dev_pm_opp_disable(cpu_dev, opp_freq);
-			}
-
-			opp_freq++;
-		}
-
-		ret = regulator_set_voltage_time(cpu_reg, min_uV, max_uV);
-		if (ret > 0)
-			transition_latency += ret * 1000;
-	}
+	priv->reg_name = name;
 
 	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
 	if (ret) {
-		pr_err("failed to init cpufreq table: %d\n", ret);
+		dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret);
 		goto out_free_priv;
 	}
 
 	priv->cpu_dev = cpu_dev;
-	priv->cpu_reg = cpu_reg;
 	policy->driver_data = priv;
-
 	policy->clk = cpu_clk;
 
 	rcu_read_lock();
@@ -357,9 +273,11 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		cpufreq_dt_attr[1] = &cpufreq_freq_attr_scaling_boost_freqs;
 	}
 
-	policy->cpuinfo.transition_latency = transition_latency;
+	transition_latency = dev_pm_opp_get_max_transition_latency(cpu_dev);
+	if (!transition_latency)
+		transition_latency = CPUFREQ_ETERNAL;
 
-	of_node_put(np);
+	policy->cpuinfo.transition_latency = transition_latency;
 
 	return 0;
 
@@ -369,12 +287,10 @@ out_free_priv:
 	kfree(priv);
 out_free_opp:
 	dev_pm_opp_of_cpumask_remove_table(policy->cpus);
-out_node_put:
-	of_node_put(np);
-out_put_reg_clk:
+	if (name)
+		dev_pm_opp_put_regulator(cpu_dev);
+out_put_clk:
 	clk_put(cpu_clk);
-	if (!IS_ERR(cpu_reg))
-		regulator_put(cpu_reg);
 
 	return ret;
 }
@@ -386,9 +302,10 @@ static int cpufreq_exit(struct cpufreq_policy *policy)
 	cpufreq_cooling_unregister(priv->cdev);
 	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
 	dev_pm_opp_of_cpumask_remove_table(policy->related_cpus);
+	if (priv->reg_name)
+		dev_pm_opp_put_regulator(priv->cpu_dev);
+
 	clk_put(policy->clk);
-	if (!IS_ERR(priv->cpu_reg))
-		regulator_put(priv->cpu_reg);
 	kfree(priv);
 
 	return 0;
@@ -441,9 +358,6 @@ static struct cpufreq_driver dt_cpufreq_driver = {
 
 static int dt_cpufreq_probe(struct platform_device *pdev)
 {
-	struct device *cpu_dev;
-	struct regulator *cpu_reg;
-	struct clk *cpu_clk;
 	int ret;
 
 	/*
@@ -453,19 +367,15 @@ static int dt_cpufreq_probe(struct platform_device *pdev)
 	 *
 	 * FIXME: Is checking this only for CPU0 sufficient ?
 	 */
-	ret = allocate_resources(0, &cpu_dev, &cpu_reg, &cpu_clk);
+	ret = resources_available();
 	if (ret)
 		return ret;
 
-	clk_put(cpu_clk);
-	if (!IS_ERR(cpu_reg))
-		regulator_put(cpu_reg);
-
 	dt_cpufreq_driver.driver_data = dev_get_platdata(&pdev->dev);
 
 	ret = cpufreq_register_driver(&dt_cpufreq_driver);
 	if (ret)
-		dev_err(cpu_dev, "failed register driver: %d\n", ret);
+		dev_err(&pdev->dev, "failed register driver: %d\n", ret);
 
 	return ret;
 }
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index e979ec78b695..4c7825856eab 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -38,48 +38,10 @@ static inline bool policy_is_inactive(struct cpufreq_policy *policy)
 	return cpumask_empty(policy->cpus);
 }
 
-static bool suitable_policy(struct cpufreq_policy *policy, bool active)
-{
-	return active == !policy_is_inactive(policy);
-}
-
-/* Finds Next Acive/Inactive policy */
-static struct cpufreq_policy *next_policy(struct cpufreq_policy *policy,
-					  bool active)
-{
-	do {
-		/* No more policies in the list */
-		if (list_is_last(&policy->policy_list, &cpufreq_policy_list))
-			return NULL;
-
-		policy = list_next_entry(policy, policy_list);
-	} while (!suitable_policy(policy, active));
-
-	return policy;
-}
-
-static struct cpufreq_policy *first_policy(bool active)
-{
-	struct cpufreq_policy *policy;
-
-	/* No policies in the list */
-	if (list_empty(&cpufreq_policy_list))
-		return NULL;
-
-	policy = list_first_entry(&cpufreq_policy_list, typeof(*policy),
-				  policy_list);
-
-	if (!suitable_policy(policy, active))
-		policy = next_policy(policy, active);
-
-	return policy;
-}
-
 /* Macros to iterate over CPU policies */
-#define for_each_suitable_policy(__policy, __active)	\
-	for (__policy = first_policy(__active);		\
-	     __policy;					\
-	     __policy = next_policy(__policy, __active))
+#define for_each_suitable_policy(__policy, __active)			 \
+	list_for_each_entry(__policy, &cpufreq_policy_list, policy_list) \
+		if ((__active) == !policy_is_inactive(__policy))
 
 #define for_each_active_policy(__policy)		\
 	for_each_suitable_policy(__policy, true)
@@ -102,7 +64,6 @@ static LIST_HEAD(cpufreq_governor_list);
 static struct cpufreq_driver *cpufreq_driver;
 static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
 static DEFINE_RWLOCK(cpufreq_driver_lock);
-DEFINE_MUTEX(cpufreq_governor_lock);
 
 /* Flag to suspend/resume CPUFreq governors */
 static bool cpufreq_suspended;
@@ -113,10 +74,8 @@ static inline bool has_target(void)
 }
 
 /* internal prototypes */
-static int __cpufreq_governor(struct cpufreq_policy *policy,
-		unsigned int event);
+static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event);
 static unsigned int __cpufreq_get(struct cpufreq_policy *policy);
-static void handle_update(struct work_struct *work);
 
 /**
  * Two notifier lists: the "policy" list is involved in the
@@ -818,12 +777,7 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
 	ssize_t ret;
 
 	down_read(&policy->rwsem);
-
-	if (fattr->show)
-		ret = fattr->show(policy, buf);
-	else
-		ret = -EIO;
-
+	ret = fattr->show(policy, buf);
 	up_read(&policy->rwsem);
 
 	return ret;
@@ -838,18 +792,12 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 
 	get_online_cpus();
 
-	if (!cpu_online(policy->cpu))
-		goto unlock;
-
-	down_write(&policy->rwsem);
-
-	if (fattr->store)
+	if (cpu_online(policy->cpu)) {
+		down_write(&policy->rwsem);
 		ret = fattr->store(policy, buf, count);
-	else
-		ret = -EIO;
+		up_write(&policy->rwsem);
+	}
 
-	up_write(&policy->rwsem);
-unlock:
 	put_online_cpus();
 
 	return ret;
@@ -959,6 +907,11 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy)
 	return cpufreq_add_dev_symlink(policy);
 }
 
+__weak struct cpufreq_governor *cpufreq_default_governor(void)
+{
+	return NULL;
+}
+
 static int cpufreq_init_policy(struct cpufreq_policy *policy)
 {
 	struct cpufreq_governor *gov = NULL;
@@ -968,11 +921,14 @@ static int cpufreq_init_policy(struct cpufreq_policy *policy)
 
 	/* Update governor of new_policy to the governor used before hotplug */
 	gov = find_governor(policy->last_governor);
-	if (gov)
+	if (gov) {
 		pr_debug("Restoring governor %s for cpu %d\n",
 				policy->governor->name, policy->cpu);
-	else
-		gov = CPUFREQ_DEFAULT_GOVERNOR;
+	} else {
+		gov = cpufreq_default_governor();
+		if (!gov)
+			return -ENODATA;
+	}
 
 	new_policy.governor = gov;
 
@@ -996,36 +952,45 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cp
 	if (cpumask_test_cpu(cpu, policy->cpus))
 		return 0;
 
+	down_write(&policy->rwsem);
 	if (has_target()) {
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP);
 		if (ret) {
 			pr_err("%s: Failed to stop governor\n", __func__);
-			return ret;
+			goto unlock;
 		}
 	}
 
-	down_write(&policy->rwsem);
 	cpumask_set_cpu(cpu, policy->cpus);
-	up_write(&policy->rwsem);
 
 	if (has_target()) {
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_START);
 		if (!ret)
-			ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+			ret = cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
 
-		if (ret) {
+		if (ret)
 			pr_err("%s: Failed to start governor\n", __func__);
-			return ret;
-		}
 	}
 
-	return 0;
+unlock:
+	up_write(&policy->rwsem);
+	return ret;
+}
+
+static void handle_update(struct work_struct *work)
+{
+	struct cpufreq_policy *policy =
+		container_of(work, struct cpufreq_policy, update);
+	unsigned int cpu = policy->cpu;
+	pr_debug("handle_update for cpu %u called\n", cpu);
+	cpufreq_update_policy(cpu);
 }
 
 static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 {
 	struct device *dev = get_cpu_device(cpu);
 	struct cpufreq_policy *policy;
+	int ret;
 
 	if (WARN_ON(!dev))
 		return NULL;
@@ -1043,7 +1008,13 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 	if (!zalloc_cpumask_var(&policy->real_cpus, GFP_KERNEL))
 		goto err_free_rcpumask;
 
-	kobject_init(&policy->kobj, &ktype_cpufreq);
+	ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq,
+				   cpufreq_global_kobject, "policy%u", cpu);
+	if (ret) {
+		pr_err("%s: failed to init policy->kobj: %d\n", __func__, ret);
+		goto err_free_real_cpus;
+	}
+
 	INIT_LIST_HEAD(&policy->policy_list);
 	init_rwsem(&policy->rwsem);
 	spin_lock_init(&policy->transition_lock);
@@ -1054,6 +1025,8 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 	policy->cpu = cpu;
 	return policy;
 
+err_free_real_cpus:
+	free_cpumask_var(policy->real_cpus);
 err_free_rcpumask:
 	free_cpumask_var(policy->related_cpus);
 err_free_cpumask:
@@ -1158,16 +1131,6 @@ static int cpufreq_online(unsigned int cpu)
 		cpumask_copy(policy->related_cpus, policy->cpus);
 		/* Remember CPUs present at the policy creation time. */
 		cpumask_and(policy->real_cpus, policy->cpus, cpu_present_mask);
-
-		/* Name and add the kobject */
-		ret = kobject_add(&policy->kobj, cpufreq_global_kobject,
-				  "policy%u",
-				  cpumask_first(policy->related_cpus));
-		if (ret) {
-			pr_err("%s: failed to add policy->kobj: %d\n", __func__,
-			       ret);
-			goto out_exit_policy;
-		}
 	}
 
 	/*
@@ -1309,9 +1272,10 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 	return ret;
 }
 
-static void cpufreq_offline_prepare(unsigned int cpu)
+static void cpufreq_offline(unsigned int cpu)
 {
 	struct cpufreq_policy *policy;
+	int ret;
 
 	pr_debug("%s: unregistering CPU %u\n", __func__, cpu);
 
@@ -1321,13 +1285,13 @@ static void cpufreq_offline_prepare(unsigned int cpu)
 		return;
 	}
 
+	down_write(&policy->rwsem);
 	if (has_target()) {
-		int ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP);
 		if (ret)
 			pr_err("%s: Failed to stop governor\n", __func__);
 	}
 
-	down_write(&policy->rwsem);
 	cpumask_clear_cpu(cpu, policy->cpus);
 
 	if (policy_is_inactive(policy)) {
@@ -1340,39 +1304,27 @@ static void cpufreq_offline_prepare(unsigned int cpu)
 		/* Nominate new CPU */
 		policy->cpu = cpumask_any(policy->cpus);
 	}
-	up_write(&policy->rwsem);
 
 	/* Start governor again for active policy */
 	if (!policy_is_inactive(policy)) {
 		if (has_target()) {
-			int ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
+			ret = cpufreq_governor(policy, CPUFREQ_GOV_START);
 			if (!ret)
-				ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+				ret = cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
 
 			if (ret)
 				pr_err("%s: Failed to start governor\n", __func__);
 		}
-	} else if (cpufreq_driver->stop_cpu) {
-		cpufreq_driver->stop_cpu(policy);
-	}
-}
 
-static void cpufreq_offline_finish(unsigned int cpu)
-{
-	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
-
-	if (!policy) {
-		pr_debug("%s: No cpu_data found\n", __func__);
-		return;
+		goto unlock;
 	}
 
-	/* Only proceed for inactive policies */
-	if (!policy_is_inactive(policy))
-		return;
+	if (cpufreq_driver->stop_cpu)
+		cpufreq_driver->stop_cpu(policy);
 
 	/* If cpu is last user of policy, free policy */
 	if (has_target()) {
-		int ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
 		if (ret)
 			pr_err("%s: Failed to exit governor\n", __func__);
 	}
@@ -1386,6 +1338,9 @@ static void cpufreq_offline_finish(unsigned int cpu)
 		cpufreq_driver->exit(policy);
 		policy->freq_table = NULL;
 	}
+
+unlock:
+	up_write(&policy->rwsem);
 }
 
 /**
@@ -1401,10 +1356,8 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 	if (!policy)
 		return;
 
-	if (cpu_online(cpu)) {
-		cpufreq_offline_prepare(cpu);
-		cpufreq_offline_finish(cpu);
-	}
+	if (cpu_online(cpu))
+		cpufreq_offline(cpu);
 
 	cpumask_clear_cpu(cpu, policy->real_cpus);
 	remove_cpu_dev_symlink(policy, cpu);
@@ -1413,15 +1366,6 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 		cpufreq_policy_free(policy, true);
 }
 
-static void handle_update(struct work_struct *work)
-{
-	struct cpufreq_policy *policy =
-		container_of(work, struct cpufreq_policy, update);
-	unsigned int cpu = policy->cpu;
-	pr_debug("handle_update for cpu %u called\n", cpu);
-	cpufreq_update_policy(cpu);
-}
-
 /**
  *	cpufreq_out_of_sync - If actual and saved CPU frequency differs, we're
  *	in deep trouble.
@@ -1584,6 +1528,7 @@ EXPORT_SYMBOL(cpufreq_generic_suspend);
 void cpufreq_suspend(void)
 {
 	struct cpufreq_policy *policy;
+	int ret;
 
 	if (!cpufreq_driver)
 		return;
@@ -1594,7 +1539,11 @@ void cpufreq_suspend(void)
 	pr_debug("%s: Suspending Governors\n", __func__);
 
 	for_each_active_policy(policy) {
-		if (__cpufreq_governor(policy, CPUFREQ_GOV_STOP))
+		down_write(&policy->rwsem);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		up_write(&policy->rwsem);
+
+		if (ret)
 			pr_err("%s: Failed to stop governor for policy: %p\n",
 				__func__, policy);
 		else if (cpufreq_driver->suspend
@@ -1616,6 +1565,7 @@ suspend:
 void cpufreq_resume(void)
 {
 	struct cpufreq_policy *policy;
+	int ret;
 
 	if (!cpufreq_driver)
 		return;
@@ -1628,13 +1578,20 @@ void cpufreq_resume(void)
 	pr_debug("%s: Resuming Governors\n", __func__);
 
 	for_each_active_policy(policy) {
-		if (cpufreq_driver->resume && cpufreq_driver->resume(policy))
+		if (cpufreq_driver->resume && cpufreq_driver->resume(policy)) {
 			pr_err("%s: Failed to resume driver: %p\n", __func__,
 				policy);
-		else if (__cpufreq_governor(policy, CPUFREQ_GOV_START)
-		    || __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))
-			pr_err("%s: Failed to start governor for policy: %p\n",
-				__func__, policy);
+		} else {
+			down_write(&policy->rwsem);
+			ret = cpufreq_governor(policy, CPUFREQ_GOV_START);
+			if (!ret)
+				cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+			up_write(&policy->rwsem);
+
+			if (ret)
+				pr_err("%s: Failed to start governor for policy: %p\n",
+				       __func__, policy);
+		}
 	}
 
 	/*
@@ -1846,7 +1803,8 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 			    unsigned int relation)
 {
 	unsigned int old_target_freq = target_freq;
-	int retval = -EINVAL;
+	struct cpufreq_frequency_table *freq_table;
+	int index, retval;
 
 	if (cpufreq_disabled())
 		return -ENODEV;
@@ -1873,34 +1831,28 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 	policy->restore_freq = policy->cur;
 
 	if (cpufreq_driver->target)
-		retval = cpufreq_driver->target(policy, target_freq, relation);
-	else if (cpufreq_driver->target_index) {
-		struct cpufreq_frequency_table *freq_table;
-		int index;
-
-		freq_table = cpufreq_frequency_get_table(policy->cpu);
-		if (unlikely(!freq_table)) {
-			pr_err("%s: Unable to find freq_table\n", __func__);
-			goto out;
-		}
+		return cpufreq_driver->target(policy, target_freq, relation);
 
-		retval = cpufreq_frequency_table_target(policy, freq_table,
-				target_freq, relation, &index);
-		if (unlikely(retval)) {
-			pr_err("%s: Unable to find matching freq\n", __func__);
-			goto out;
-		}
+	if (!cpufreq_driver->target_index)
+		return -EINVAL;
 
-		if (freq_table[index].frequency == policy->cur) {
-			retval = 0;
-			goto out;
-		}
+	freq_table = cpufreq_frequency_get_table(policy->cpu);
+	if (unlikely(!freq_table)) {
+		pr_err("%s: Unable to find freq_table\n", __func__);
+		return -EINVAL;
+	}
 
-		retval = __target_index(policy, freq_table, index);
+	retval = cpufreq_frequency_table_target(policy, freq_table, target_freq,
+						relation, &index);
+	if (unlikely(retval)) {
+		pr_err("%s: Unable to find matching freq\n", __func__);
+		return retval;
 	}
 
-out:
-	return retval;
+	if (freq_table[index].frequency == policy->cur)
+		return 0;
+
+	return __target_index(policy, freq_table, index);
 }
 EXPORT_SYMBOL_GPL(__cpufreq_driver_target);
 
@@ -1920,20 +1872,14 @@ int cpufreq_driver_target(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_driver_target);
 
-static int __cpufreq_governor(struct cpufreq_policy *policy,
-					unsigned int event)
+__weak struct cpufreq_governor *cpufreq_fallback_governor(void)
 {
-	int ret;
+	return NULL;
+}
 
-	/* Only must be defined when default governor is known to have latency
-	   restrictions, like e.g. conservative or ondemand.
-	   That this is the case is already ensured in Kconfig
-	*/
-#ifdef CONFIG_CPU_FREQ_GOV_PERFORMANCE
-	struct cpufreq_governor *gov = &cpufreq_gov_performance;
-#else
-	struct cpufreq_governor *gov = NULL;
-#endif
+static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event)
+{
+	int ret;
 
 	/* Don't start any governor operations if we are entering suspend */
 	if (cpufreq_suspended)
@@ -1948,12 +1894,14 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 	if (policy->governor->max_transition_latency &&
 	    policy->cpuinfo.transition_latency >
 	    policy->governor->max_transition_latency) {
-		if (!gov)
-			return -EINVAL;
-		else {
+		struct cpufreq_governor *gov = cpufreq_fallback_governor();
+
+		if (gov) {
 			pr_warn("%s governor failed, too long transition latency of HW, fallback to %s governor\n",
 				policy->governor->name, gov->name);
 			policy->governor = gov;
+		} else {
+			return -EINVAL;
 		}
 	}
 
@@ -1963,21 +1911,6 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 
 	pr_debug("%s: for CPU %u, event %u\n", __func__, policy->cpu, event);
 
-	mutex_lock(&cpufreq_governor_lock);
-	if ((policy->governor_enabled && event == CPUFREQ_GOV_START)
-	    || (!policy->governor_enabled
-	    && (event == CPUFREQ_GOV_LIMITS || event == CPUFREQ_GOV_STOP))) {
-		mutex_unlock(&cpufreq_governor_lock);
-		return -EBUSY;
-	}
-
-	if (event == CPUFREQ_GOV_STOP)
-		policy->governor_enabled = false;
-	else if (event == CPUFREQ_GOV_START)
-		policy->governor_enabled = true;
-
-	mutex_unlock(&cpufreq_governor_lock);
-
 	ret = policy->governor->governor(policy, event);
 
 	if (!ret) {
@@ -1985,14 +1918,6 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 			policy->governor->initialized++;
 		else if (event == CPUFREQ_GOV_POLICY_EXIT)
 			policy->governor->initialized--;
-	} else {
-		/* Restore original values */
-		mutex_lock(&cpufreq_governor_lock);
-		if (event == CPUFREQ_GOV_STOP)
-			policy->governor_enabled = true;
-		else if (event == CPUFREQ_GOV_START)
-			policy->governor_enabled = false;
-		mutex_unlock(&cpufreq_governor_lock);
 	}
 
 	if (((event == CPUFREQ_GOV_POLICY_INIT) && ret) ||
@@ -2147,7 +2072,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	old_gov = policy->governor;
 	/* end old governor */
 	if (old_gov) {
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP);
 		if (ret) {
 			/* This can happen due to race with other operations */
 			pr_debug("%s: Failed to Stop Governor: %s (%d)\n",
@@ -2155,10 +2080,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 			return ret;
 		}
 
-		up_write(&policy->rwsem);
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
-		down_write(&policy->rwsem);
-
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
 		if (ret) {
 			pr_err("%s: Failed to Exit Governor: %s (%d)\n",
 			       __func__, old_gov->name, ret);
@@ -2168,32 +2090,30 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 
 	/* start new governor */
 	policy->governor = new_policy->governor;
-	ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT);
+	ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT);
 	if (!ret) {
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_START);
 		if (!ret)
 			goto out;
 
-		up_write(&policy->rwsem);
-		__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
-		down_write(&policy->rwsem);
+		cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
 	}
 
 	/* new governor failed, so re-start old one */
 	pr_debug("starting governor %s failed\n", policy->governor->name);
 	if (old_gov) {
 		policy->governor = old_gov;
-		if (__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT))
+		if (cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT))
 			policy->governor = NULL;
 		else
-			__cpufreq_governor(policy, CPUFREQ_GOV_START);
+			cpufreq_governor(policy, CPUFREQ_GOV_START);
 	}
 
 	return ret;
 
  out:
 	pr_debug("governor: change or update limits\n");
-	return __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+	return cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
 }
 
 /**
@@ -2260,11 +2180,7 @@ static int cpufreq_cpu_callback(struct notifier_block *nfb,
 		break;
 
 	case CPU_DOWN_PREPARE:
-		cpufreq_offline_prepare(cpu);
-		break;
-
-	case CPU_POST_DEAD:
-		cpufreq_offline_finish(cpu);
+		cpufreq_offline(cpu);
 		break;
 
 	case CPU_DOWN_FAILED:
@@ -2297,8 +2213,11 @@ static int cpufreq_boost_set_sw(int state)
 				       __func__);
 				break;
 			}
+
+			down_write(&policy->rwsem);
 			policy->user_policy.max = policy->max;
-			__cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+			cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+			up_write(&policy->rwsem);
 		}
 	}
 
@@ -2384,7 +2303,7 @@ EXPORT_SYMBOL_GPL(cpufreq_boost_enabled);
  * submitted by the CPU Frequency driver.
  *
  * Registers a CPU Frequency driver to this core code. This code
- * returns zero on success, -EBUSY when another driver got here first
+ * returns zero on success, -EEXIST when another driver got here first
  * (and isn't unregistered in the meantime).
  *
  */
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 606ad74abe6e..bf4913f6453b 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -14,6 +14,22 @@
 #include <linux/slab.h>
 #include "cpufreq_governor.h"
 
+struct cs_policy_dbs_info {
+	struct policy_dbs_info policy_dbs;
+	unsigned int down_skip;
+	unsigned int requested_freq;
+};
+
+static inline struct cs_policy_dbs_info *to_dbs_info(struct policy_dbs_info *policy_dbs)
+{
+	return container_of(policy_dbs, struct cs_policy_dbs_info, policy_dbs);
+}
+
+struct cs_dbs_tuners {
+	unsigned int down_threshold;
+	unsigned int freq_step;
+};
+
 /* Conservative governor macros */
 #define DEF_FREQUENCY_UP_THRESHOLD		(80)
 #define DEF_FREQUENCY_DOWN_THRESHOLD		(20)
@@ -21,21 +37,6 @@
 #define DEF_SAMPLING_DOWN_FACTOR		(1)
 #define MAX_SAMPLING_DOWN_FACTOR		(10)
 
-static DEFINE_PER_CPU(struct cs_cpu_dbs_info_s, cs_cpu_dbs_info);
-
-static int cs_cpufreq_governor_dbs(struct cpufreq_policy *policy,
-				   unsigned int event);
-
-#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
-static
-#endif
-struct cpufreq_governor cpufreq_gov_conservative = {
-	.name			= "conservative",
-	.governor		= cs_cpufreq_governor_dbs,
-	.max_transition_latency	= TRANSITION_LATENCY_LIMIT,
-	.owner			= THIS_MODULE,
-};
-
 static inline unsigned int get_freq_target(struct cs_dbs_tuners *cs_tuners,
 					   struct cpufreq_policy *policy)
 {
@@ -57,27 +58,28 @@ static inline unsigned int get_freq_target(struct cs_dbs_tuners *cs_tuners,
  * Any frequency increase takes it to the maximum frequency. Frequency reduction
  * happens at minimum steps of 5% (default) of maximum frequency
  */
-static void cs_check_cpu(int cpu, unsigned int load)
+static unsigned int cs_dbs_timer(struct cpufreq_policy *policy)
 {
-	struct cs_cpu_dbs_info_s *dbs_info = &per_cpu(cs_cpu_dbs_info, cpu);
-	struct cpufreq_policy *policy = dbs_info->cdbs.shared->policy;
-	struct dbs_data *dbs_data = policy->governor_data;
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs);
+	struct dbs_data *dbs_data = policy_dbs->dbs_data;
 	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
+	unsigned int load = dbs_update(policy);
 
 	/*
 	 * break out if we 'cannot' reduce the speed as the user might
 	 * want freq_step to be zero
 	 */
 	if (cs_tuners->freq_step == 0)
-		return;
+		goto out;
 
 	/* Check for frequency increase */
-	if (load > cs_tuners->up_threshold) {
+	if (load > dbs_data->up_threshold) {
 		dbs_info->down_skip = 0;
 
 		/* if we are already at full speed then break out early */
 		if (dbs_info->requested_freq == policy->max)
-			return;
+			goto out;
 
 		dbs_info->requested_freq += get_freq_target(cs_tuners, policy);
 
@@ -86,12 +88,12 @@ static void cs_check_cpu(int cpu, unsigned int load)
 
 		__cpufreq_driver_target(policy, dbs_info->requested_freq,
 			CPUFREQ_RELATION_H);
-		return;
+		goto out;
 	}
 
 	/* if sampling_down_factor is active break out early */
-	if (++dbs_info->down_skip < cs_tuners->sampling_down_factor)
-		return;
+	if (++dbs_info->down_skip < dbs_data->sampling_down_factor)
+		goto out;
 	dbs_info->down_skip = 0;
 
 	/* Check for frequency decrease */
@@ -101,7 +103,7 @@ static void cs_check_cpu(int cpu, unsigned int load)
 		 * if we cannot reduce the frequency anymore, break out early
 		 */
 		if (policy->cur == policy->min)
-			return;
+			goto out;
 
 		freq_target = get_freq_target(cs_tuners, policy);
 		if (dbs_info->requested_freq > freq_target)
@@ -111,58 +113,25 @@ static void cs_check_cpu(int cpu, unsigned int load)
 
 		__cpufreq_driver_target(policy, dbs_info->requested_freq,
 				CPUFREQ_RELATION_L);
-		return;
 	}
-}
-
-static unsigned int cs_dbs_timer(struct cpufreq_policy *policy, bool modify_all)
-{
-	struct dbs_data *dbs_data = policy->governor_data;
-	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
-
-	if (modify_all)
-		dbs_check_cpu(dbs_data, policy->cpu);
 
-	return delay_for_sampling_rate(cs_tuners->sampling_rate);
+ out:
+	return dbs_data->sampling_rate;
 }
 
 static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
-		void *data)
-{
-	struct cpufreq_freqs *freq = data;
-	struct cs_cpu_dbs_info_s *dbs_info =
-					&per_cpu(cs_cpu_dbs_info, freq->cpu);
-	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(freq->cpu);
-
-	if (!policy)
-		return 0;
-
-	/* policy isn't governed by conservative governor */
-	if (policy->governor != &cpufreq_gov_conservative)
-		return 0;
-
-	/*
-	 * we only care if our internally tracked freq moves outside the 'valid'
-	 * ranges of frequency available to us otherwise we do not change it
-	*/
-	if (dbs_info->requested_freq > policy->max
-			|| dbs_info->requested_freq < policy->min)
-		dbs_info->requested_freq = freq->new;
-
-	return 0;
-}
+				void *data);
 
 static struct notifier_block cs_cpufreq_notifier_block = {
 	.notifier_call = dbs_cpufreq_notifier,
 };
 
 /************************** sysfs interface ************************/
-static struct common_dbs_data cs_dbs_cdata;
+static struct dbs_governor cs_dbs_gov;
 
 static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
 		const char *buf, size_t count)
 {
-	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
 	unsigned int input;
 	int ret;
 	ret = sscanf(buf, "%u", &input);
@@ -170,22 +139,7 @@ static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
 	if (ret != 1 || input > MAX_SAMPLING_DOWN_FACTOR || input < 1)
 		return -EINVAL;
 
-	cs_tuners->sampling_down_factor = input;
-	return count;
-}
-
-static ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
-{
-	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
-	unsigned int input;
-	int ret;
-	ret = sscanf(buf, "%u", &input);
-
-	if (ret != 1)
-		return -EINVAL;
-
-	cs_tuners->sampling_rate = max(input, dbs_data->min_sampling_rate);
+	dbs_data->sampling_down_factor = input;
 	return count;
 }
 
@@ -200,7 +154,7 @@ static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
 	if (ret != 1 || input > 100 || input <= cs_tuners->down_threshold)
 		return -EINVAL;
 
-	cs_tuners->up_threshold = input;
+	dbs_data->up_threshold = input;
 	return count;
 }
 
@@ -214,7 +168,7 @@ static ssize_t store_down_threshold(struct dbs_data *dbs_data, const char *buf,
 
 	/* cannot be lower than 11 otherwise freq will not fall */
 	if (ret != 1 || input < 11 || input > 100 ||
-			input >= cs_tuners->up_threshold)
+			input >= dbs_data->up_threshold)
 		return -EINVAL;
 
 	cs_tuners->down_threshold = input;
@@ -224,8 +178,7 @@ static ssize_t store_down_threshold(struct dbs_data *dbs_data, const char *buf,
 static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
 		const char *buf, size_t count)
 {
-	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
-	unsigned int input, j;
+	unsigned int input;
 	int ret;
 
 	ret = sscanf(buf, "%u", &input);
@@ -235,21 +188,14 @@ static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
 	if (input > 1)
 		input = 1;
 
-	if (input == cs_tuners->ignore_nice_load) /* nothing to do */
+	if (input == dbs_data->ignore_nice_load) /* nothing to do */
 		return count;
 
-	cs_tuners->ignore_nice_load = input;
+	dbs_data->ignore_nice_load = input;
 
 	/* we need to re-evaluate prev_cpu_idle */
-	for_each_online_cpu(j) {
-		struct cs_cpu_dbs_info_s *dbs_info;
-		dbs_info = &per_cpu(cs_cpu_dbs_info, j);
-		dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j,
-					&dbs_info->cdbs.prev_cpu_wall, 0);
-		if (cs_tuners->ignore_nice_load)
-			dbs_info->cdbs.prev_cpu_nice =
-				kcpustat_cpu(j).cpustat[CPUTIME_NICE];
-	}
+	gov_update_cpu_data(dbs_data);
+
 	return count;
 }
 
@@ -275,55 +221,47 @@ static ssize_t store_freq_step(struct dbs_data *dbs_data, const char *buf,
 	return count;
 }
 
-show_store_one(cs, sampling_rate);
-show_store_one(cs, sampling_down_factor);
-show_store_one(cs, up_threshold);
-show_store_one(cs, down_threshold);
-show_store_one(cs, ignore_nice_load);
-show_store_one(cs, freq_step);
-declare_show_sampling_rate_min(cs);
-
-gov_sys_pol_attr_rw(sampling_rate);
-gov_sys_pol_attr_rw(sampling_down_factor);
-gov_sys_pol_attr_rw(up_threshold);
-gov_sys_pol_attr_rw(down_threshold);
-gov_sys_pol_attr_rw(ignore_nice_load);
-gov_sys_pol_attr_rw(freq_step);
-gov_sys_pol_attr_ro(sampling_rate_min);
-
-static struct attribute *dbs_attributes_gov_sys[] = {
-	&sampling_rate_min_gov_sys.attr,
-	&sampling_rate_gov_sys.attr,
-	&sampling_down_factor_gov_sys.attr,
-	&up_threshold_gov_sys.attr,
-	&down_threshold_gov_sys.attr,
-	&ignore_nice_load_gov_sys.attr,
-	&freq_step_gov_sys.attr,
+gov_show_one_common(sampling_rate);
+gov_show_one_common(sampling_down_factor);
+gov_show_one_common(up_threshold);
+gov_show_one_common(ignore_nice_load);
+gov_show_one_common(min_sampling_rate);
+gov_show_one(cs, down_threshold);
+gov_show_one(cs, freq_step);
+
+gov_attr_rw(sampling_rate);
+gov_attr_rw(sampling_down_factor);
+gov_attr_rw(up_threshold);
+gov_attr_rw(ignore_nice_load);
+gov_attr_ro(min_sampling_rate);
+gov_attr_rw(down_threshold);
+gov_attr_rw(freq_step);
+
+static struct attribute *cs_attributes[] = {
+	&min_sampling_rate.attr,
+	&sampling_rate.attr,
+	&sampling_down_factor.attr,
+	&up_threshold.attr,
+	&down_threshold.attr,
+	&ignore_nice_load.attr,
+	&freq_step.attr,
 	NULL
 };
 
-static struct attribute_group cs_attr_group_gov_sys = {
-	.attrs = dbs_attributes_gov_sys,
-	.name = "conservative",
-};
+/************************** sysfs end ************************/
 
-static struct attribute *dbs_attributes_gov_pol[] = {
-	&sampling_rate_min_gov_pol.attr,
-	&sampling_rate_gov_pol.attr,
-	&sampling_down_factor_gov_pol.attr,
-	&up_threshold_gov_pol.attr,
-	&down_threshold_gov_pol.attr,
-	&ignore_nice_load_gov_pol.attr,
-	&freq_step_gov_pol.attr,
-	NULL
-};
+static struct policy_dbs_info *cs_alloc(void)
+{
+	struct cs_policy_dbs_info *dbs_info;
 
-static struct attribute_group cs_attr_group_gov_pol = {
-	.attrs = dbs_attributes_gov_pol,
-	.name = "conservative",
-};
+	dbs_info = kzalloc(sizeof(*dbs_info), GFP_KERNEL);
+	return dbs_info ? &dbs_info->policy_dbs : NULL;
+}
 
-/************************** sysfs end ************************/
+static void cs_free(struct policy_dbs_info *policy_dbs)
+{
+	kfree(to_dbs_info(policy_dbs));
+}
 
 static int cs_init(struct dbs_data *dbs_data, bool notify)
 {
@@ -335,11 +273,11 @@ static int cs_init(struct dbs_data *dbs_data, bool notify)
 		return -ENOMEM;
 	}
 
-	tuners->up_threshold = DEF_FREQUENCY_UP_THRESHOLD;
 	tuners->down_threshold = DEF_FREQUENCY_DOWN_THRESHOLD;
-	tuners->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR;
-	tuners->ignore_nice_load = 0;
 	tuners->freq_step = DEF_FREQUENCY_STEP;
+	dbs_data->up_threshold = DEF_FREQUENCY_UP_THRESHOLD;
+	dbs_data->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR;
+	dbs_data->ignore_nice_load = 0;
 
 	dbs_data->tuners = tuners;
 	dbs_data->min_sampling_rate = MIN_SAMPLING_RATE_RATIO *
@@ -361,35 +299,66 @@ static void cs_exit(struct dbs_data *dbs_data, bool notify)
 	kfree(dbs_data->tuners);
 }
 
-define_get_cpu_dbs_routines(cs_cpu_dbs_info);
+static void cs_start(struct cpufreq_policy *policy)
+{
+	struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data);
+
+	dbs_info->down_skip = 0;
+	dbs_info->requested_freq = policy->cur;
+}
 
-static struct common_dbs_data cs_dbs_cdata = {
-	.governor = GOV_CONSERVATIVE,
-	.attr_group_gov_sys = &cs_attr_group_gov_sys,
-	.attr_group_gov_pol = &cs_attr_group_gov_pol,
-	.get_cpu_cdbs = get_cpu_cdbs,
-	.get_cpu_dbs_info_s = get_cpu_dbs_info_s,
+static struct dbs_governor cs_dbs_gov = {
+	.gov = {
+		.name = "conservative",
+		.governor = cpufreq_governor_dbs,
+		.max_transition_latency = TRANSITION_LATENCY_LIMIT,
+		.owner = THIS_MODULE,
+	},
+	.kobj_type = { .default_attrs = cs_attributes },
 	.gov_dbs_timer = cs_dbs_timer,
-	.gov_check_cpu = cs_check_cpu,
+	.alloc = cs_alloc,
+	.free = cs_free,
 	.init = cs_init,
 	.exit = cs_exit,
-	.mutex = __MUTEX_INITIALIZER(cs_dbs_cdata.mutex),
+	.start = cs_start,
 };
 
-static int cs_cpufreq_governor_dbs(struct cpufreq_policy *policy,
-				   unsigned int event)
+#define CPU_FREQ_GOV_CONSERVATIVE	(&cs_dbs_gov.gov)
+
+static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
+				void *data)
 {
-	return cpufreq_governor_dbs(policy, &cs_dbs_cdata, event);
+	struct cpufreq_freqs *freq = data;
+	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(freq->cpu);
+	struct cs_policy_dbs_info *dbs_info;
+
+	if (!policy)
+		return 0;
+
+	/* policy isn't governed by conservative governor */
+	if (policy->governor != CPU_FREQ_GOV_CONSERVATIVE)
+		return 0;
+
+	dbs_info = to_dbs_info(policy->governor_data);
+	/*
+	 * we only care if our internally tracked freq moves outside the 'valid'
+	 * ranges of frequency available to us otherwise we do not change it
+	*/
+	if (dbs_info->requested_freq > policy->max
+			|| dbs_info->requested_freq < policy->min)
+		dbs_info->requested_freq = freq->new;
+
+	return 0;
 }
 
 static int __init cpufreq_gov_dbs_init(void)
 {
-	return cpufreq_register_governor(&cpufreq_gov_conservative);
+	return cpufreq_register_governor(CPU_FREQ_GOV_CONSERVATIVE);
 }
 
 static void __exit cpufreq_gov_dbs_exit(void)
 {
-	cpufreq_unregister_governor(&cpufreq_gov_conservative);
+	cpufreq_unregister_governor(CPU_FREQ_GOV_CONSERVATIVE);
 }
 
 MODULE_AUTHOR("Alexander Clouter <alex@digriz.org.uk>");
@@ -399,6 +368,11 @@ MODULE_DESCRIPTION("'cpufreq_conservative' - A dynamic cpufreq governor for "
 MODULE_LICENSE("GPL");
 
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
+struct cpufreq_governor *cpufreq_default_governor(void)
+{
+	return CPU_FREQ_GOV_CONSERVATIVE;
+}
+
 fs_initcall(cpufreq_gov_dbs_init);
 #else
 module_init(cpufreq_gov_dbs_init);
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index e0d111024d48..1c25ef405616 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -18,95 +18,193 @@
 
 #include <linux/export.h>
 #include <linux/kernel_stat.h>
+#include <linux/sched.h>
 #include <linux/slab.h>
 
 #include "cpufreq_governor.h"
 
-static struct attribute_group *get_sysfs_attr(struct dbs_data *dbs_data)
-{
-	if (have_governor_per_policy())
-		return dbs_data->cdata->attr_group_gov_pol;
-	else
-		return dbs_data->cdata->attr_group_gov_sys;
-}
+static DEFINE_PER_CPU(struct cpu_dbs_info, cpu_dbs);
+
+static DEFINE_MUTEX(gov_dbs_data_mutex);
 
-void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
+/* Common sysfs tunables */
+/**
+ * store_sampling_rate - update sampling rate effective immediately if needed.
+ *
+ * If new rate is smaller than the old, simply updating
+ * dbs.sampling_rate might not be appropriate. For example, if the
+ * original sampling_rate was 1 second and the requested new sampling rate is 10
+ * ms because the user needs immediate reaction from ondemand governor, but not
+ * sure if higher frequency will be required or not, then, the governor may
+ * change the sampling rate too late; up to 1 second later. Thus, if we are
+ * reducing the sampling rate, we need to make the new value effective
+ * immediately.
+ *
+ * This must be called with dbs_data->mutex held, otherwise traversing
+ * policy_dbs_list isn't safe.
+ */
+ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf,
+			    size_t count)
 {
-	struct cpu_dbs_info *cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
-	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
-	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
-	struct cpufreq_policy *policy = cdbs->shared->policy;
-	unsigned int sampling_rate;
-	unsigned int max_load = 0;
-	unsigned int ignore_nice;
-	unsigned int j;
+	struct policy_dbs_info *policy_dbs;
+	unsigned int rate;
+	int ret;
+	ret = sscanf(buf, "%u", &rate);
+	if (ret != 1)
+		return -EINVAL;
 
-	if (dbs_data->cdata->governor == GOV_ONDEMAND) {
-		struct od_cpu_dbs_info_s *od_dbs_info =
-				dbs_data->cdata->get_cpu_dbs_info_s(cpu);
+	dbs_data->sampling_rate = max(rate, dbs_data->min_sampling_rate);
 
+	/*
+	 * We are operating under dbs_data->mutex and so the list and its
+	 * entries can't be freed concurrently.
+	 */
+	list_for_each_entry(policy_dbs, &dbs_data->policy_dbs_list, list) {
+		mutex_lock(&policy_dbs->timer_mutex);
 		/*
-		 * Sometimes, the ondemand governor uses an additional
-		 * multiplier to give long delays. So apply this multiplier to
-		 * the 'sampling_rate', so as to keep the wake-up-from-idle
-		 * detection logic a bit conservative.
+		 * On 32-bit architectures this may race with the
+		 * sample_delay_ns read in dbs_update_util_handler(), but that
+		 * really doesn't matter.  If the read returns a value that's
+		 * too big, the sample will be skipped, but the next invocation
+		 * of dbs_update_util_handler() (when the update has been
+		 * completed) will take a sample.
+		 *
+		 * If this runs in parallel with dbs_work_handler(), we may end
+		 * up overwriting the sample_delay_ns value that it has just
+		 * written, but it will be corrected next time a sample is
+		 * taken, so it shouldn't be significant.
 		 */
-		sampling_rate = od_tuners->sampling_rate;
-		sampling_rate *= od_dbs_info->rate_mult;
+		gov_update_sample_delay(policy_dbs, 0);
+		mutex_unlock(&policy_dbs->timer_mutex);
+	}
 
-		ignore_nice = od_tuners->ignore_nice_load;
-	} else {
-		sampling_rate = cs_tuners->sampling_rate;
-		ignore_nice = cs_tuners->ignore_nice_load;
+	return count;
+}
+EXPORT_SYMBOL_GPL(store_sampling_rate);
+
+/**
+ * gov_update_cpu_data - Update CPU load data.
+ * @dbs_data: Top-level governor data pointer.
+ *
+ * Update CPU load data for all CPUs in the domain governed by @dbs_data
+ * (that may be a single policy or a bunch of them if governor tunables are
+ * system-wide).
+ *
+ * Call under the @dbs_data mutex.
+ */
+void gov_update_cpu_data(struct dbs_data *dbs_data)
+{
+	struct policy_dbs_info *policy_dbs;
+
+	list_for_each_entry(policy_dbs, &dbs_data->policy_dbs_list, list) {
+		unsigned int j;
+
+		for_each_cpu(j, policy_dbs->policy->cpus) {
+			struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);
+
+			j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, &j_cdbs->prev_cpu_wall,
+								  dbs_data->io_is_busy);
+			if (dbs_data->ignore_nice_load)
+				j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+		}
 	}
+}
+EXPORT_SYMBOL_GPL(gov_update_cpu_data);
+
+static inline struct dbs_data *to_dbs_data(struct kobject *kobj)
+{
+	return container_of(kobj, struct dbs_data, kobj);
+}
+
+static inline struct governor_attr *to_gov_attr(struct attribute *attr)
+{
+	return container_of(attr, struct governor_attr, attr);
+}
+
+static ssize_t governor_show(struct kobject *kobj, struct attribute *attr,
+			     char *buf)
+{
+	struct dbs_data *dbs_data = to_dbs_data(kobj);
+	struct governor_attr *gattr = to_gov_attr(attr);
+
+	return gattr->show(dbs_data, buf);
+}
+
+static ssize_t governor_store(struct kobject *kobj, struct attribute *attr,
+			      const char *buf, size_t count)
+{
+	struct dbs_data *dbs_data = to_dbs_data(kobj);
+	struct governor_attr *gattr = to_gov_attr(attr);
+	int ret = -EBUSY;
+
+	mutex_lock(&dbs_data->mutex);
+
+	if (dbs_data->usage_count)
+		ret = gattr->store(dbs_data, buf, count);
+
+	mutex_unlock(&dbs_data->mutex);
+
+	return ret;
+}
+
+/*
+ * Sysfs Ops for accessing governor attributes.
+ *
+ * All show/store invocations for governor specific sysfs attributes, will first
+ * call the below show/store callbacks and the attribute specific callback will
+ * be called from within it.
+ */
+static const struct sysfs_ops governor_sysfs_ops = {
+	.show	= governor_show,
+	.store	= governor_store,
+};
+
+unsigned int dbs_update(struct cpufreq_policy *policy)
+{
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct dbs_data *dbs_data = policy_dbs->dbs_data;
+	unsigned int ignore_nice = dbs_data->ignore_nice_load;
+	unsigned int max_load = 0;
+	unsigned int sampling_rate, io_busy, j;
+
+	/*
+	 * Sometimes governors may use an additional multiplier to increase
+	 * sample delays temporarily.  Apply that multiplier to sampling_rate
+	 * so as to keep the wake-up-from-idle detection logic a bit
+	 * conservative.
+	 */
+	sampling_rate = dbs_data->sampling_rate * policy_dbs->rate_mult;
+	/*
+	 * For the purpose of ondemand, waiting for disk IO is an indication
+	 * that you're performance critical, and not that the system is actually
+	 * idle, so do not add the iowait time to the CPU idle time then.
+	 */
+	io_busy = dbs_data->io_is_busy;
 
 	/* Get Absolute Load */
 	for_each_cpu(j, policy->cpus) {
-		struct cpu_dbs_info *j_cdbs;
+		struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);
 		u64 cur_wall_time, cur_idle_time;
 		unsigned int idle_time, wall_time;
 		unsigned int load;
-		int io_busy = 0;
-
-		j_cdbs = dbs_data->cdata->get_cpu_cdbs(j);
 
-		/*
-		 * For the purpose of ondemand, waiting for disk IO is
-		 * an indication that you're performance critical, and
-		 * not that the system is actually idle. So do not add
-		 * the iowait time to the cpu idle time.
-		 */
-		if (dbs_data->cdata->governor == GOV_ONDEMAND)
-			io_busy = od_tuners->io_is_busy;
 		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time, io_busy);
 
-		wall_time = (unsigned int)
-			(cur_wall_time - j_cdbs->prev_cpu_wall);
+		wall_time = cur_wall_time - j_cdbs->prev_cpu_wall;
 		j_cdbs->prev_cpu_wall = cur_wall_time;
 
-		if (cur_idle_time < j_cdbs->prev_cpu_idle)
-			cur_idle_time = j_cdbs->prev_cpu_idle;
-
-		idle_time = (unsigned int)
-			(cur_idle_time - j_cdbs->prev_cpu_idle);
-		j_cdbs->prev_cpu_idle = cur_idle_time;
+		if (cur_idle_time <= j_cdbs->prev_cpu_idle) {
+			idle_time = 0;
+		} else {
+			idle_time = cur_idle_time - j_cdbs->prev_cpu_idle;
+			j_cdbs->prev_cpu_idle = cur_idle_time;
+		}
 
 		if (ignore_nice) {
-			u64 cur_nice;
-			unsigned long cur_nice_jiffies;
-
-			cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE] -
-					 cdbs->prev_cpu_nice;
-			/*
-			 * Assumption: nice time between sampling periods will
-			 * be less than 2^32 jiffies for 32 bit sys
-			 */
-			cur_nice_jiffies = (unsigned long)
-					cputime64_to_jiffies64(cur_nice);
+			u64 cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 
-			cdbs->prev_cpu_nice =
-				kcpustat_cpu(j).cpustat[CPUTIME_NICE];
-			idle_time += jiffies_to_usecs(cur_nice_jiffies);
+			idle_time += cputime_to_usecs(cur_nice - j_cdbs->prev_cpu_nice);
+			j_cdbs->prev_cpu_nice = cur_nice;
 		}
 
 		if (unlikely(!wall_time || wall_time < idle_time))
@@ -128,10 +226,10 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 		 * dropped down. So we perform the copy only once, upon the
 		 * first wake-up from idle.)
 		 *
-		 * Detecting this situation is easy: the governor's deferrable
-		 * timer would not have fired during CPU-idle periods. Hence
-		 * an unusually large 'wall_time' (as compared to the sampling
-		 * rate) indicates this scenario.
+		 * Detecting this situation is easy: the governor's utilization
+		 * update handler would not have run during CPU-idle periods.
+		 * Hence, an unusually large 'wall_time' (as compared to the
+		 * sampling rate) indicates this scenario.
 		 *
 		 * prev_load can be zero in two cases and we must recalculate it
 		 * for both cases:
@@ -156,222 +254,224 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 		if (load > max_load)
 			max_load = load;
 	}
-
-	dbs_data->cdata->gov_check_cpu(cpu, max_load);
+	return max_load;
 }
-EXPORT_SYMBOL_GPL(dbs_check_cpu);
+EXPORT_SYMBOL_GPL(dbs_update);
 
-void gov_add_timers(struct cpufreq_policy *policy, unsigned int delay)
+static void gov_set_update_util(struct policy_dbs_info *policy_dbs,
+				unsigned int delay_us)
 {
-	struct dbs_data *dbs_data = policy->governor_data;
-	struct cpu_dbs_info *cdbs;
+	struct cpufreq_policy *policy = policy_dbs->policy;
 	int cpu;
 
+	gov_update_sample_delay(policy_dbs, delay_us);
+	policy_dbs->last_sample_time = 0;
+
 	for_each_cpu(cpu, policy->cpus) {
-		cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
-		cdbs->timer.expires = jiffies + delay;
-		add_timer_on(&cdbs->timer, cpu);
+		struct cpu_dbs_info *cdbs = &per_cpu(cpu_dbs, cpu);
+
+		cpufreq_set_update_util_data(cpu, &cdbs->update_util);
 	}
 }
-EXPORT_SYMBOL_GPL(gov_add_timers);
 
-static inline void gov_cancel_timers(struct cpufreq_policy *policy)
+static inline void gov_clear_update_util(struct cpufreq_policy *policy)
 {
-	struct dbs_data *dbs_data = policy->governor_data;
-	struct cpu_dbs_info *cdbs;
 	int i;
 
-	for_each_cpu(i, policy->cpus) {
-		cdbs = dbs_data->cdata->get_cpu_cdbs(i);
-		del_timer_sync(&cdbs->timer);
-	}
-}
+	for_each_cpu(i, policy->cpus)
+		cpufreq_set_update_util_data(i, NULL);
 
-void gov_cancel_work(struct cpu_common_dbs_info *shared)
-{
-	/* Tell dbs_timer_handler() to skip queuing up work items. */
-	atomic_inc(&shared->skip_work);
-	/*
-	 * If dbs_timer_handler() is already running, it may not notice the
-	 * incremented skip_work, so wait for it to complete to prevent its work
-	 * item from being queued up after the cancel_work_sync() below.
-	 */
-	gov_cancel_timers(shared->policy);
-	/*
-	 * In case dbs_timer_handler() managed to run and spawn a work item
-	 * before the timers have been canceled, wait for that work item to
-	 * complete and then cancel all of the timers set up by it.  If
-	 * dbs_timer_handler() runs again at that point, it will see the
-	 * positive value of skip_work and won't spawn any more work items.
-	 */
-	cancel_work_sync(&shared->work);
-	gov_cancel_timers(shared->policy);
-	atomic_set(&shared->skip_work, 0);
+	synchronize_sched();
 }
-EXPORT_SYMBOL_GPL(gov_cancel_work);
 
-/* Will return if we need to evaluate cpu load again or not */
-static bool need_load_eval(struct cpu_common_dbs_info *shared,
-			   unsigned int sampling_rate)
+static void gov_cancel_work(struct cpufreq_policy *policy)
 {
-	if (policy_is_shared(shared->policy)) {
-		ktime_t time_now = ktime_get();
-		s64 delta_us = ktime_us_delta(time_now, shared->time_stamp);
-
-		/* Do nothing if we recently have sampled */
-		if (delta_us < (s64)(sampling_rate / 2))
-			return false;
-		else
-			shared->time_stamp = time_now;
-	}
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
 
-	return true;
+	gov_clear_update_util(policy_dbs->policy);
+	irq_work_sync(&policy_dbs->irq_work);
+	cancel_work_sync(&policy_dbs->work);
+	atomic_set(&policy_dbs->work_count, 0);
+	policy_dbs->work_in_progress = false;
 }
 
 static void dbs_work_handler(struct work_struct *work)
 {
-	struct cpu_common_dbs_info *shared = container_of(work, struct
-					cpu_common_dbs_info, work);
+	struct policy_dbs_info *policy_dbs;
 	struct cpufreq_policy *policy;
-	struct dbs_data *dbs_data;
-	unsigned int sampling_rate, delay;
-	bool eval_load;
-
-	policy = shared->policy;
-	dbs_data = policy->governor_data;
+	struct dbs_governor *gov;
 
-	/* Kill all timers */
-	gov_cancel_timers(policy);
+	policy_dbs = container_of(work, struct policy_dbs_info, work);
+	policy = policy_dbs->policy;
+	gov = dbs_governor_of(policy);
 
-	if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
-		struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
-
-		sampling_rate = cs_tuners->sampling_rate;
-	} else {
-		struct od_dbs_tuners *od_tuners = dbs_data->tuners;
-
-		sampling_rate = od_tuners->sampling_rate;
-	}
-
-	eval_load = need_load_eval(shared, sampling_rate);
+	/*
+	 * Make sure cpufreq_governor_limits() isn't evaluating load or the
+	 * ondemand governor isn't updating the sampling rate in parallel.
+	 */
+	mutex_lock(&policy_dbs->timer_mutex);
+	gov_update_sample_delay(policy_dbs, gov->gov_dbs_timer(policy));
+	mutex_unlock(&policy_dbs->timer_mutex);
 
+	/* Allow the utilization update handler to queue up more work. */
+	atomic_set(&policy_dbs->work_count, 0);
 	/*
-	 * Make sure cpufreq_governor_limits() isn't evaluating load in
-	 * parallel.
+	 * If the update below is reordered with respect to the sample delay
+	 * modification, the utilization update handler may end up using a stale
+	 * sample delay value.
 	 */
-	mutex_lock(&shared->timer_mutex);
-	delay = dbs_data->cdata->gov_dbs_timer(policy, eval_load);
-	mutex_unlock(&shared->timer_mutex);
+	smp_wmb();
+	policy_dbs->work_in_progress = false;
+}
 
-	atomic_dec(&shared->skip_work);
+static void dbs_irq_work(struct irq_work *irq_work)
+{
+	struct policy_dbs_info *policy_dbs;
 
-	gov_add_timers(policy, delay);
+	policy_dbs = container_of(irq_work, struct policy_dbs_info, irq_work);
+	schedule_work(&policy_dbs->work);
 }
 
-static void dbs_timer_handler(unsigned long data)
+static void dbs_update_util_handler(struct update_util_data *data, u64 time,
+				    unsigned long util, unsigned long max)
 {
-	struct cpu_dbs_info *cdbs = (struct cpu_dbs_info *)data;
-	struct cpu_common_dbs_info *shared = cdbs->shared;
+	struct cpu_dbs_info *cdbs = container_of(data, struct cpu_dbs_info, update_util);
+	struct policy_dbs_info *policy_dbs = cdbs->policy_dbs;
+	u64 delta_ns, lst;
 
 	/*
-	 * Timer handler may not be allowed to queue the work at the moment,
-	 * because:
-	 * - Another timer handler has done that
-	 * - We are stopping the governor
-	 * - Or we are updating the sampling rate of the ondemand governor
+	 * The work may not be allowed to be queued up right now.
+	 * Possible reasons:
+	 * - Work has already been queued up or is in progress.
+	 * - It is too early (too little time from the previous sample).
 	 */
-	if (atomic_inc_return(&shared->skip_work) > 1)
-		atomic_dec(&shared->skip_work);
-	else
-		queue_work(system_wq, &shared->work);
-}
+	if (policy_dbs->work_in_progress)
+		return;
 
-static void set_sampling_rate(struct dbs_data *dbs_data,
-		unsigned int sampling_rate)
-{
-	if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
-		struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
-		cs_tuners->sampling_rate = sampling_rate;
-	} else {
-		struct od_dbs_tuners *od_tuners = dbs_data->tuners;
-		od_tuners->sampling_rate = sampling_rate;
+	/*
+	 * If the reads below are reordered before the check above, the value
+	 * of sample_delay_ns used in the computation may be stale.
+	 */
+	smp_rmb();
+	lst = READ_ONCE(policy_dbs->last_sample_time);
+	delta_ns = time - lst;
+	if ((s64)delta_ns < policy_dbs->sample_delay_ns)
+		return;
+
+	/*
+	 * If the policy is not shared, the irq_work may be queued up right away
+	 * at this point.  Otherwise, we need to ensure that only one of the
+	 * CPUs sharing the policy will do that.
+	 */
+	if (policy_dbs->is_shared) {
+		if (!atomic_add_unless(&policy_dbs->work_count, 1, 1))
+			return;
+
+		/*
+		 * If another CPU updated last_sample_time in the meantime, we
+		 * shouldn't be here, so clear the work counter and bail out.
+		 */
+		if (unlikely(lst != READ_ONCE(policy_dbs->last_sample_time))) {
+			atomic_set(&policy_dbs->work_count, 0);
+			return;
+		}
 	}
+
+	policy_dbs->last_sample_time = time;
+	policy_dbs->work_in_progress = true;
+	irq_work_queue(&policy_dbs->irq_work);
 }
 
-static int alloc_common_dbs_info(struct cpufreq_policy *policy,
-				 struct common_dbs_data *cdata)
+static struct policy_dbs_info *alloc_policy_dbs_info(struct cpufreq_policy *policy,
+						     struct dbs_governor *gov)
 {
-	struct cpu_common_dbs_info *shared;
+	struct policy_dbs_info *policy_dbs;
 	int j;
 
-	/* Allocate memory for the common information for policy->cpus */
-	shared = kzalloc(sizeof(*shared), GFP_KERNEL);
-	if (!shared)
-		return -ENOMEM;
+	/* Allocate memory for per-policy governor data. */
+	policy_dbs = gov->alloc();
+	if (!policy_dbs)
+		return NULL;
 
-	/* Set shared for all CPUs, online+offline */
-	for_each_cpu(j, policy->related_cpus)
-		cdata->get_cpu_cdbs(j)->shared = shared;
+	policy_dbs->policy = policy;
+	mutex_init(&policy_dbs->timer_mutex);
+	atomic_set(&policy_dbs->work_count, 0);
+	init_irq_work(&policy_dbs->irq_work, dbs_irq_work);
+	INIT_WORK(&policy_dbs->work, dbs_work_handler);
 
-	mutex_init(&shared->timer_mutex);
-	atomic_set(&shared->skip_work, 0);
-	INIT_WORK(&shared->work, dbs_work_handler);
-	return 0;
+	/* Set policy_dbs for all CPUs, online+offline */
+	for_each_cpu(j, policy->related_cpus) {
+		struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);
+
+		j_cdbs->policy_dbs = policy_dbs;
+		j_cdbs->update_util.func = dbs_update_util_handler;
+	}
+	return policy_dbs;
 }
 
-static void free_common_dbs_info(struct cpufreq_policy *policy,
-				 struct common_dbs_data *cdata)
+static void free_policy_dbs_info(struct policy_dbs_info *policy_dbs,
+				 struct dbs_governor *gov)
 {
-	struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(policy->cpu);
-	struct cpu_common_dbs_info *shared = cdbs->shared;
 	int j;
 
-	mutex_destroy(&shared->timer_mutex);
+	mutex_destroy(&policy_dbs->timer_mutex);
 
-	for_each_cpu(j, policy->cpus)
-		cdata->get_cpu_cdbs(j)->shared = NULL;
+	for_each_cpu(j, policy_dbs->policy->related_cpus) {
+		struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);
 
-	kfree(shared);
+		j_cdbs->policy_dbs = NULL;
+		j_cdbs->update_util.func = NULL;
+	}
+	gov->free(policy_dbs);
 }
 
-static int cpufreq_governor_init(struct cpufreq_policy *policy,
-				 struct dbs_data *dbs_data,
-				 struct common_dbs_data *cdata)
+static int cpufreq_governor_init(struct cpufreq_policy *policy)
 {
+	struct dbs_governor *gov = dbs_governor_of(policy);
+	struct dbs_data *dbs_data;
+	struct policy_dbs_info *policy_dbs;
 	unsigned int latency;
-	int ret;
+	int ret = 0;
 
 	/* State should be equivalent to EXIT */
 	if (policy->governor_data)
 		return -EBUSY;
 
-	if (dbs_data) {
-		if (WARN_ON(have_governor_per_policy()))
-			return -EINVAL;
+	policy_dbs = alloc_policy_dbs_info(policy, gov);
+	if (!policy_dbs)
+		return -ENOMEM;
 
-		ret = alloc_common_dbs_info(policy, cdata);
-		if (ret)
-			return ret;
+	/* Protect gov->gdbs_data against concurrent updates. */
+	mutex_lock(&gov_dbs_data_mutex);
 
+	dbs_data = gov->gdbs_data;
+	if (dbs_data) {
+		if (WARN_ON(have_governor_per_policy())) {
+			ret = -EINVAL;
+			goto free_policy_dbs_info;
+		}
+		policy_dbs->dbs_data = dbs_data;
+		policy->governor_data = policy_dbs;
+
+		mutex_lock(&dbs_data->mutex);
 		dbs_data->usage_count++;
-		policy->governor_data = dbs_data;
-		return 0;
+		list_add(&policy_dbs->list, &dbs_data->policy_dbs_list);
+		mutex_unlock(&dbs_data->mutex);
+		goto out;
 	}
 
 	dbs_data = kzalloc(sizeof(*dbs_data), GFP_KERNEL);
-	if (!dbs_data)
-		return -ENOMEM;
-
-	ret = alloc_common_dbs_info(policy, cdata);
-	if (ret)
-		goto free_dbs_data;
+	if (!dbs_data) {
+		ret = -ENOMEM;
+		goto free_policy_dbs_info;
+	}
 
-	dbs_data->cdata = cdata;
-	dbs_data->usage_count = 1;
+	INIT_LIST_HEAD(&dbs_data->policy_dbs_list);
+	mutex_init(&dbs_data->mutex);
 
-	ret = cdata->init(dbs_data, !policy->governor->initialized);
+	ret = gov->init(dbs_data, !policy->governor->initialized);
 	if (ret)
-		goto free_common_dbs_info;
+		goto free_policy_dbs_info;
 
 	/* policy latency is in ns. Convert it to us first */
 	latency = policy->cpuinfo.transition_latency / 1000;
@@ -381,216 +481,156 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy,
 	/* Bring kernel and HW constraints together */
 	dbs_data->min_sampling_rate = max(dbs_data->min_sampling_rate,
 					  MIN_LATENCY_MULTIPLIER * latency);
-	set_sampling_rate(dbs_data, max(dbs_data->min_sampling_rate,
-					latency * LATENCY_MULTIPLIER));
+	dbs_data->sampling_rate = max(dbs_data->min_sampling_rate,
+				      LATENCY_MULTIPLIER * latency);
 
 	if (!have_governor_per_policy())
-		cdata->gdbs_data = dbs_data;
+		gov->gdbs_data = dbs_data;
 
-	policy->governor_data = dbs_data;
+	policy->governor_data = policy_dbs;
 
-	ret = sysfs_create_group(get_governor_parent_kobj(policy),
-				 get_sysfs_attr(dbs_data));
-	if (ret)
-		goto reset_gdbs_data;
+	policy_dbs->dbs_data = dbs_data;
+	dbs_data->usage_count = 1;
+	list_add(&policy_dbs->list, &dbs_data->policy_dbs_list);
 
-	return 0;
+	gov->kobj_type.sysfs_ops = &governor_sysfs_ops;
+	ret = kobject_init_and_add(&dbs_data->kobj, &gov->kobj_type,
+				   get_governor_parent_kobj(policy),
+				   "%s", gov->gov.name);
+	if (!ret)
+		goto out;
+
+	/* Failure, so roll back. */
+	pr_err("cpufreq: Governor initialization failed (dbs_data kobject init error %d)\n", ret);
 
-reset_gdbs_data:
 	policy->governor_data = NULL;
 
 	if (!have_governor_per_policy())
-		cdata->gdbs_data = NULL;
-	cdata->exit(dbs_data, !policy->governor->initialized);
-free_common_dbs_info:
-	free_common_dbs_info(policy, cdata);
-free_dbs_data:
+		gov->gdbs_data = NULL;
+	gov->exit(dbs_data, !policy->governor->initialized);
 	kfree(dbs_data);
+
+free_policy_dbs_info:
+	free_policy_dbs_info(policy_dbs, gov);
+
+out:
+	mutex_unlock(&gov_dbs_data_mutex);
 	return ret;
 }
 
-static int cpufreq_governor_exit(struct cpufreq_policy *policy,
-				 struct dbs_data *dbs_data)
+static int cpufreq_governor_exit(struct cpufreq_policy *policy)
 {
-	struct common_dbs_data *cdata = dbs_data->cdata;
-	struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(policy->cpu);
+	struct dbs_governor *gov = dbs_governor_of(policy);
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct dbs_data *dbs_data = policy_dbs->dbs_data;
+	int count;
 
-	/* State should be equivalent to INIT */
-	if (!cdbs->shared || cdbs->shared->policy)
-		return -EBUSY;
+	/* Protect gov->gdbs_data against concurrent updates. */
+	mutex_lock(&gov_dbs_data_mutex);
+
+	mutex_lock(&dbs_data->mutex);
+	list_del(&policy_dbs->list);
+	count = --dbs_data->usage_count;
+	mutex_unlock(&dbs_data->mutex);
 
-	if (!--dbs_data->usage_count) {
-		sysfs_remove_group(get_governor_parent_kobj(policy),
-				   get_sysfs_attr(dbs_data));
+	if (!count) {
+		kobject_put(&dbs_data->kobj);
 
 		policy->governor_data = NULL;
 
 		if (!have_governor_per_policy())
-			cdata->gdbs_data = NULL;
+			gov->gdbs_data = NULL;
 
-		cdata->exit(dbs_data, policy->governor->initialized == 1);
+		gov->exit(dbs_data, policy->governor->initialized == 1);
+		mutex_destroy(&dbs_data->mutex);
 		kfree(dbs_data);
 	} else {
 		policy->governor_data = NULL;
 	}
 
-	free_common_dbs_info(policy, cdata);
+	free_policy_dbs_info(policy_dbs, gov);
+
+	mutex_unlock(&gov_dbs_data_mutex);
 	return 0;
 }
 
-static int cpufreq_governor_start(struct cpufreq_policy *policy,
-				  struct dbs_data *dbs_data)
+static int cpufreq_governor_start(struct cpufreq_policy *policy)
 {
-	struct common_dbs_data *cdata = dbs_data->cdata;
-	unsigned int sampling_rate, ignore_nice, j, cpu = policy->cpu;
-	struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(cpu);
-	struct cpu_common_dbs_info *shared = cdbs->shared;
-	int io_busy = 0;
+	struct dbs_governor *gov = dbs_governor_of(policy);
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct dbs_data *dbs_data = policy_dbs->dbs_data;
+	unsigned int sampling_rate, ignore_nice, j;
+	unsigned int io_busy;
 
 	if (!policy->cur)
 		return -EINVAL;
 
-	/* State should be equivalent to INIT */
-	if (!shared || shared->policy)
-		return -EBUSY;
+	policy_dbs->is_shared = policy_is_shared(policy);
+	policy_dbs->rate_mult = 1;
 
-	if (cdata->governor == GOV_CONSERVATIVE) {
-		struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
-
-		sampling_rate = cs_tuners->sampling_rate;
-		ignore_nice = cs_tuners->ignore_nice_load;
-	} else {
-		struct od_dbs_tuners *od_tuners = dbs_data->tuners;
-
-		sampling_rate = od_tuners->sampling_rate;
-		ignore_nice = od_tuners->ignore_nice_load;
-		io_busy = od_tuners->io_is_busy;
-	}
-
-	shared->policy = policy;
-	shared->time_stamp = ktime_get();
+	sampling_rate = dbs_data->sampling_rate;
+	ignore_nice = dbs_data->ignore_nice_load;
+	io_busy = dbs_data->io_is_busy;
 
 	for_each_cpu(j, policy->cpus) {
-		struct cpu_dbs_info *j_cdbs = cdata->get_cpu_cdbs(j);
+		struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);
 		unsigned int prev_load;
 
-		j_cdbs->prev_cpu_idle =
-			get_cpu_idle_time(j, &j_cdbs->prev_cpu_wall, io_busy);
+		j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, &j_cdbs->prev_cpu_wall, io_busy);
 
-		prev_load = (unsigned int)(j_cdbs->prev_cpu_wall -
-					    j_cdbs->prev_cpu_idle);
-		j_cdbs->prev_load = 100 * prev_load /
-				    (unsigned int)j_cdbs->prev_cpu_wall;
+		prev_load = j_cdbs->prev_cpu_wall - j_cdbs->prev_cpu_idle;
+		j_cdbs->prev_load = 100 * prev_load / (unsigned int)j_cdbs->prev_cpu_wall;
 
 		if (ignore_nice)
 			j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
-
-		__setup_timer(&j_cdbs->timer, dbs_timer_handler,
-			      (unsigned long)j_cdbs,
-			      TIMER_DEFERRABLE | TIMER_IRQSAFE);
 	}
 
-	if (cdata->governor == GOV_CONSERVATIVE) {
-		struct cs_cpu_dbs_info_s *cs_dbs_info =
-			cdata->get_cpu_dbs_info_s(cpu);
-
-		cs_dbs_info->down_skip = 0;
-		cs_dbs_info->requested_freq = policy->cur;
-	} else {
-		struct od_ops *od_ops = cdata->gov_ops;
-		struct od_cpu_dbs_info_s *od_dbs_info = cdata->get_cpu_dbs_info_s(cpu);
-
-		od_dbs_info->rate_mult = 1;
-		od_dbs_info->sample_type = OD_NORMAL_SAMPLE;
-		od_ops->powersave_bias_init_cpu(cpu);
-	}
+	gov->start(policy);
 
-	gov_add_timers(policy, delay_for_sampling_rate(sampling_rate));
+	gov_set_update_util(policy_dbs, sampling_rate);
 	return 0;
 }
 
-static int cpufreq_governor_stop(struct cpufreq_policy *policy,
-				 struct dbs_data *dbs_data)
+static int cpufreq_governor_stop(struct cpufreq_policy *policy)
 {
-	struct cpu_dbs_info *cdbs = dbs_data->cdata->get_cpu_cdbs(policy->cpu);
-	struct cpu_common_dbs_info *shared = cdbs->shared;
-
-	/* State should be equivalent to START */
-	if (!shared || !shared->policy)
-		return -EBUSY;
-
-	gov_cancel_work(shared);
-	shared->policy = NULL;
-
+	gov_cancel_work(policy);
 	return 0;
 }
 
-static int cpufreq_governor_limits(struct cpufreq_policy *policy,
-				   struct dbs_data *dbs_data)
+static int cpufreq_governor_limits(struct cpufreq_policy *policy)
 {
-	struct common_dbs_data *cdata = dbs_data->cdata;
-	unsigned int cpu = policy->cpu;
-	struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(cpu);
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
 
-	/* State should be equivalent to START */
-	if (!cdbs->shared || !cdbs->shared->policy)
-		return -EBUSY;
+	mutex_lock(&policy_dbs->timer_mutex);
+
+	if (policy->max < policy->cur)
+		__cpufreq_driver_target(policy, policy->max, CPUFREQ_RELATION_H);
+	else if (policy->min > policy->cur)
+		__cpufreq_driver_target(policy, policy->min, CPUFREQ_RELATION_L);
+
+	gov_update_sample_delay(policy_dbs, 0);
 
-	mutex_lock(&cdbs->shared->timer_mutex);
-	if (policy->max < cdbs->shared->policy->cur)
-		__cpufreq_driver_target(cdbs->shared->policy, policy->max,
-					CPUFREQ_RELATION_H);
-	else if (policy->min > cdbs->shared->policy->cur)
-		__cpufreq_driver_target(cdbs->shared->policy, policy->min,
-					CPUFREQ_RELATION_L);
-	dbs_check_cpu(dbs_data, cpu);
-	mutex_unlock(&cdbs->shared->timer_mutex);
+	mutex_unlock(&policy_dbs->timer_mutex);
 
 	return 0;
 }
 
-int cpufreq_governor_dbs(struct cpufreq_policy *policy,
-			 struct common_dbs_data *cdata, unsigned int event)
+int cpufreq_governor_dbs(struct cpufreq_policy *policy, unsigned int event)
 {
-	struct dbs_data *dbs_data;
-	int ret;
-
-	/* Lock governor to block concurrent initialization of governor */
-	mutex_lock(&cdata->mutex);
-
-	if (have_governor_per_policy())
-		dbs_data = policy->governor_data;
-	else
-		dbs_data = cdata->gdbs_data;
-
-	if (!dbs_data && (event != CPUFREQ_GOV_POLICY_INIT)) {
-		ret = -EINVAL;
-		goto unlock;
-	}
-
-	switch (event) {
-	case CPUFREQ_GOV_POLICY_INIT:
-		ret = cpufreq_governor_init(policy, dbs_data, cdata);
-		break;
-	case CPUFREQ_GOV_POLICY_EXIT:
-		ret = cpufreq_governor_exit(policy, dbs_data);
-		break;
-	case CPUFREQ_GOV_START:
-		ret = cpufreq_governor_start(policy, dbs_data);
-		break;
-	case CPUFREQ_GOV_STOP:
-		ret = cpufreq_governor_stop(policy, dbs_data);
-		break;
-	case CPUFREQ_GOV_LIMITS:
-		ret = cpufreq_governor_limits(policy, dbs_data);
-		break;
-	default:
-		ret = -EINVAL;
+	if (event == CPUFREQ_GOV_POLICY_INIT) {
+		return cpufreq_governor_init(policy);
+	} else if (policy->governor_data) {
+		switch (event) {
+		case CPUFREQ_GOV_POLICY_EXIT:
+			return cpufreq_governor_exit(policy);
+		case CPUFREQ_GOV_START:
+			return cpufreq_governor_start(policy);
+		case CPUFREQ_GOV_STOP:
+			return cpufreq_governor_stop(policy);
+		case CPUFREQ_GOV_LIMITS:
+			return cpufreq_governor_limits(policy);
+		}
 	}
-
-unlock:
-	mutex_unlock(&cdata->mutex);
-
-	return ret;
+	return -EINVAL;
 }
 EXPORT_SYMBOL_GPL(cpufreq_governor_dbs);
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index 91e767a058a7..61ff82fe0613 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -18,6 +18,7 @@
 #define _CPUFREQ_GOVERNOR_H
 
 #include <linux/atomic.h>
+#include <linux/irq_work.h>
 #include <linux/cpufreq.h>
 #include <linux/kernel_stat.h>
 #include <linux/module.h>
@@ -41,96 +42,68 @@
 enum {OD_NORMAL_SAMPLE, OD_SUB_SAMPLE};
 
 /*
- * Macro for creating governors sysfs routines
- *
- * - gov_sys: One governor instance per whole system
- * - gov_pol: One governor instance per policy
+ * Abbreviations:
+ * dbs: used as a shortform for demand based switching It helps to keep variable
+ *	names smaller, simpler
+ * cdbs: common dbs
+ * od_*: On-demand governor
+ * cs_*: Conservative governor
  */
 
-/* Create attributes */
-#define gov_sys_attr_ro(_name)						\
-static struct global_attr _name##_gov_sys =				\
-__ATTR(_name, 0444, show_##_name##_gov_sys, NULL)
-
-#define gov_sys_attr_rw(_name)						\
-static struct global_attr _name##_gov_sys =				\
-__ATTR(_name, 0644, show_##_name##_gov_sys, store_##_name##_gov_sys)
-
-#define gov_pol_attr_ro(_name)						\
-static struct freq_attr _name##_gov_pol =				\
-__ATTR(_name, 0444, show_##_name##_gov_pol, NULL)
-
-#define gov_pol_attr_rw(_name)						\
-static struct freq_attr _name##_gov_pol =				\
-__ATTR(_name, 0644, show_##_name##_gov_pol, store_##_name##_gov_pol)
+/* Governor demand based switching data (per-policy or global). */
+struct dbs_data {
+	int usage_count;
+	void *tuners;
+	unsigned int min_sampling_rate;
+	unsigned int ignore_nice_load;
+	unsigned int sampling_rate;
+	unsigned int sampling_down_factor;
+	unsigned int up_threshold;
+	unsigned int io_is_busy;
 
-#define gov_sys_pol_attr_rw(_name)					\
-	gov_sys_attr_rw(_name);						\
-	gov_pol_attr_rw(_name)
+	struct kobject kobj;
+	struct list_head policy_dbs_list;
+	/*
+	 * Protect concurrent updates to governor tunables from sysfs,
+	 * policy_dbs_list and usage_count.
+	 */
+	struct mutex mutex;
+};
 
-#define gov_sys_pol_attr_ro(_name)					\
-	gov_sys_attr_ro(_name);						\
-	gov_pol_attr_ro(_name)
+/* Governor's specific attributes */
+struct dbs_data;
+struct governor_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct dbs_data *dbs_data, char *buf);
+	ssize_t (*store)(struct dbs_data *dbs_data, const char *buf,
+			 size_t count);
+};
 
-/* Create show/store routines */
-#define show_one(_gov, file_name)					\
-static ssize_t show_##file_name##_gov_sys				\
-(struct kobject *kobj, struct attribute *attr, char *buf)		\
+#define gov_show_one(_gov, file_name)					\
+static ssize_t show_##file_name						\
+(struct dbs_data *dbs_data, char *buf)					\
 {									\
-	struct _gov##_dbs_tuners *tuners = _gov##_dbs_cdata.gdbs_data->tuners; \
-	return sprintf(buf, "%u\n", tuners->file_name);			\
-}									\
-									\
-static ssize_t show_##file_name##_gov_pol				\
-(struct cpufreq_policy *policy, char *buf)				\
-{									\
-	struct dbs_data *dbs_data = policy->governor_data;		\
 	struct _gov##_dbs_tuners *tuners = dbs_data->tuners;		\
 	return sprintf(buf, "%u\n", tuners->file_name);			\
 }
 
-#define store_one(_gov, file_name)					\
-static ssize_t store_##file_name##_gov_sys				\
-(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) \
-{									\
-	struct dbs_data *dbs_data = _gov##_dbs_cdata.gdbs_data;		\
-	return store_##file_name(dbs_data, buf, count);			\
-}									\
-									\
-static ssize_t store_##file_name##_gov_pol				\
-(struct cpufreq_policy *policy, const char *buf, size_t count)		\
+#define gov_show_one_common(file_name)					\
+static ssize_t show_##file_name						\
+(struct dbs_data *dbs_data, char *buf)					\
 {									\
-	struct dbs_data *dbs_data = policy->governor_data;		\
-	return store_##file_name(dbs_data, buf, count);			\
+	return sprintf(buf, "%u\n", dbs_data->file_name);		\
 }
 
-#define show_store_one(_gov, file_name)					\
-show_one(_gov, file_name);						\
-store_one(_gov, file_name)
+#define gov_attr_ro(_name)						\
+static struct governor_attr _name =					\
+__ATTR(_name, 0444, show_##_name, NULL)
 
-/* create helper routines */
-#define define_get_cpu_dbs_routines(_dbs_info)				\
-static struct cpu_dbs_info *get_cpu_cdbs(int cpu)			\
-{									\
-	return &per_cpu(_dbs_info, cpu).cdbs;				\
-}									\
-									\
-static void *get_cpu_dbs_info_s(int cpu)				\
-{									\
-	return &per_cpu(_dbs_info, cpu);				\
-}
-
-/*
- * Abbreviations:
- * dbs: used as a shortform for demand based switching It helps to keep variable
- *	names smaller, simpler
- * cdbs: common dbs
- * od_*: On-demand governor
- * cs_*: Conservative governor
- */
+#define gov_attr_rw(_name)						\
+static struct governor_attr _name =					\
+__ATTR(_name, 0644, show_##_name, store_##_name)
 
 /* Common to all CPUs of a policy */
-struct cpu_common_dbs_info {
+struct policy_dbs_info {
 	struct cpufreq_policy *policy;
 	/*
 	 * Per policy mutex that serializes load evaluation from limit-change
@@ -138,11 +111,27 @@ struct cpu_common_dbs_info {
 	 */
 	struct mutex timer_mutex;
 
-	ktime_t time_stamp;
-	atomic_t skip_work;
+	u64 last_sample_time;
+	s64 sample_delay_ns;
+	atomic_t work_count;
+	struct irq_work irq_work;
 	struct work_struct work;
+	/* dbs_data may be shared between multiple policy objects */
+	struct dbs_data *dbs_data;
+	struct list_head list;
+	/* Multiplier for increasing sample delay temporarily. */
+	unsigned int rate_mult;
+	/* Status indicators */
+	bool is_shared;		/* This object is used by multiple CPUs */
+	bool work_in_progress;	/* Work is being queued up or in progress */
 };
 
+static inline void gov_update_sample_delay(struct policy_dbs_info *policy_dbs,
+					   unsigned int delay_us)
+{
+	policy_dbs->sample_delay_ns = delay_us * NSEC_PER_USEC;
+}
+
 /* Per cpu structures */
 struct cpu_dbs_info {
 	u64 prev_cpu_idle;
@@ -155,54 +144,14 @@ struct cpu_dbs_info {
 	 * wake-up from idle.
 	 */
 	unsigned int prev_load;
-	struct timer_list timer;
-	struct cpu_common_dbs_info *shared;
-};
-
-struct od_cpu_dbs_info_s {
-	struct cpu_dbs_info cdbs;
-	struct cpufreq_frequency_table *freq_table;
-	unsigned int freq_lo;
-	unsigned int freq_lo_jiffies;
-	unsigned int freq_hi_jiffies;
-	unsigned int rate_mult;
-	unsigned int sample_type:1;
-};
-
-struct cs_cpu_dbs_info_s {
-	struct cpu_dbs_info cdbs;
-	unsigned int down_skip;
-	unsigned int requested_freq;
-};
-
-/* Per policy Governors sysfs tunables */
-struct od_dbs_tuners {
-	unsigned int ignore_nice_load;
-	unsigned int sampling_rate;
-	unsigned int sampling_down_factor;
-	unsigned int up_threshold;
-	unsigned int powersave_bias;
-	unsigned int io_is_busy;
-};
-
-struct cs_dbs_tuners {
-	unsigned int ignore_nice_load;
-	unsigned int sampling_rate;
-	unsigned int sampling_down_factor;
-	unsigned int up_threshold;
-	unsigned int down_threshold;
-	unsigned int freq_step;
+	struct update_util_data update_util;
+	struct policy_dbs_info *policy_dbs;
 };
 
 /* Common Governor data across policies */
-struct dbs_data;
-struct common_dbs_data {
-	/* Common across governors */
-	#define GOV_ONDEMAND		0
-	#define GOV_CONSERVATIVE	1
-	int governor;
-	struct attribute_group *attr_group_gov_sys; /* one governor - system */
-	struct attribute_group *attr_group_gov_pol; /* one governor - policy */
+struct dbs_governor {
+	struct cpufreq_governor gov;
+	struct kobj_type kobj_type;
 
 	/*
 	 * Common data for platforms that don't set
@@ -210,74 +159,32 @@ struct common_dbs_data {
 	 */
 	struct dbs_data *gdbs_data;
 
-	struct cpu_dbs_info *(*get_cpu_cdbs)(int cpu);
-	void *(*get_cpu_dbs_info_s)(int cpu);
-	unsigned int (*gov_dbs_timer)(struct cpufreq_policy *policy,
-				      bool modify_all);
-	void (*gov_check_cpu)(int cpu, unsigned int load);
+	unsigned int (*gov_dbs_timer)(struct cpufreq_policy *policy);
+	struct policy_dbs_info *(*alloc)(void);
+	void (*free)(struct policy_dbs_info *policy_dbs);
 	int (*init)(struct dbs_data *dbs_data, bool notify);
 	void (*exit)(struct dbs_data *dbs_data, bool notify);
-
-	/* Governor specific ops, see below */
-	void *gov_ops;
-
-	/*
-	 * Protects governor's data (struct dbs_data and struct common_dbs_data)
-	 */
-	struct mutex mutex;
+	void (*start)(struct cpufreq_policy *policy);
 };
 
-/* Governor Per policy data */
-struct dbs_data {
-	struct common_dbs_data *cdata;
-	unsigned int min_sampling_rate;
-	int usage_count;
-	void *tuners;
-};
+static inline struct dbs_governor *dbs_governor_of(struct cpufreq_policy *policy)
+{
+	return container_of(policy->governor, struct dbs_governor, gov);
+}
 
-/* Governor specific ops, will be passed to dbs_data->gov_ops */
+/* Governor specific operations */
 struct od_ops {
-	void (*powersave_bias_init_cpu)(int cpu);
 	unsigned int (*powersave_bias_target)(struct cpufreq_policy *policy,
 			unsigned int freq_next, unsigned int relation);
-	void (*freq_increase)(struct cpufreq_policy *policy, unsigned int freq);
 };
 
-static inline int delay_for_sampling_rate(unsigned int sampling_rate)
-{
-	int delay = usecs_to_jiffies(sampling_rate);
-
-	/* We want all CPUs to do sampling nearly on same jiffy */
-	if (num_online_cpus() > 1)
-		delay -= jiffies % delay;
-
-	return delay;
-}
-
-#define declare_show_sampling_rate_min(_gov)				\
-static ssize_t show_sampling_rate_min_gov_sys				\
-(struct kobject *kobj, struct attribute *attr, char *buf)		\
-{									\
-	struct dbs_data *dbs_data = _gov##_dbs_cdata.gdbs_data;		\
-	return sprintf(buf, "%u\n", dbs_data->min_sampling_rate);	\
-}									\
-									\
-static ssize_t show_sampling_rate_min_gov_pol				\
-(struct cpufreq_policy *policy, char *buf)				\
-{									\
-	struct dbs_data *dbs_data = policy->governor_data;		\
-	return sprintf(buf, "%u\n", dbs_data->min_sampling_rate);	\
-}
-
-extern struct mutex cpufreq_governor_lock;
-
-void gov_add_timers(struct cpufreq_policy *policy, unsigned int delay);
-void gov_cancel_work(struct cpu_common_dbs_info *shared);
-void dbs_check_cpu(struct dbs_data *dbs_data, int cpu);
-int cpufreq_governor_dbs(struct cpufreq_policy *policy,
-		struct common_dbs_data *cdata, unsigned int event);
+unsigned int dbs_update(struct cpufreq_policy *policy);
+int cpufreq_governor_dbs(struct cpufreq_policy *policy, unsigned int event);
 void od_register_powersave_bias_handler(unsigned int (*f)
 		(struct cpufreq_policy *, unsigned int, unsigned int),
 		unsigned int powersave_bias);
 void od_unregister_powersave_bias_handler(void);
+ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf,
+			    size_t count);
+void gov_update_cpu_data(struct dbs_data *dbs_data);
 #endif /* _CPUFREQ_GOVERNOR_H */
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index eae51070c034..acd80272ded6 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -16,7 +16,8 @@
 #include <linux/percpu-defs.h>
 #include <linux/slab.h>
 #include <linux/tick.h>
-#include "cpufreq_governor.h"
+
+#include "cpufreq_ondemand.h"
 
 /* On-demand governor macros */
 #define DEF_FREQUENCY_UP_THRESHOLD		(80)
@@ -27,24 +28,10 @@
 #define MIN_FREQUENCY_UP_THRESHOLD		(11)
 #define MAX_FREQUENCY_UP_THRESHOLD		(100)
 
-static DEFINE_PER_CPU(struct od_cpu_dbs_info_s, od_cpu_dbs_info);
-
 static struct od_ops od_ops;
 
-#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
-static struct cpufreq_governor cpufreq_gov_ondemand;
-#endif
-
 static unsigned int default_powersave_bias;
 
-static void ondemand_powersave_bias_init_cpu(int cpu)
-{
-	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
-
-	dbs_info->freq_table = cpufreq_frequency_get_table(cpu);
-	dbs_info->freq_lo = 0;
-}
-
 /*
  * Not all CPUs want IO time to be accounted as busy; this depends on how
  * efficient idling at a higher frequency/voltage is.
@@ -70,8 +57,8 @@ static int should_io_be_busy(void)
 
 /*
  * Find right freq to be set now with powersave_bias on.
- * Returns the freq_hi to be used right now and will set freq_hi_jiffies,
- * freq_lo, and freq_lo_jiffies in percpu area for averaging freqs.
+ * Returns the freq_hi to be used right now and will set freq_hi_delay_us,
+ * freq_lo, and freq_lo_delay_us in percpu area for averaging freqs.
  */
 static unsigned int generic_powersave_bias_target(struct cpufreq_policy *policy,
 		unsigned int freq_next, unsigned int relation)
@@ -79,15 +66,15 @@ static unsigned int generic_powersave_bias_target(struct cpufreq_policy *policy,
 	unsigned int freq_req, freq_reduc, freq_avg;
 	unsigned int freq_hi, freq_lo;
 	unsigned int index = 0;
-	unsigned int jiffies_total, jiffies_hi, jiffies_lo;
-	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
-						   policy->cpu);
-	struct dbs_data *dbs_data = policy->governor_data;
+	unsigned int delay_hi_us;
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct od_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs);
+	struct dbs_data *dbs_data = policy_dbs->dbs_data;
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 
 	if (!dbs_info->freq_table) {
 		dbs_info->freq_lo = 0;
-		dbs_info->freq_lo_jiffies = 0;
+		dbs_info->freq_lo_delay_us = 0;
 		return freq_next;
 	}
 
@@ -110,31 +97,30 @@ static unsigned int generic_powersave_bias_target(struct cpufreq_policy *policy,
 	/* Find out how long we have to be in hi and lo freqs */
 	if (freq_hi == freq_lo) {
 		dbs_info->freq_lo = 0;
-		dbs_info->freq_lo_jiffies = 0;
+		dbs_info->freq_lo_delay_us = 0;
 		return freq_lo;
 	}
-	jiffies_total = usecs_to_jiffies(od_tuners->sampling_rate);
-	jiffies_hi = (freq_avg - freq_lo) * jiffies_total;
-	jiffies_hi += ((freq_hi - freq_lo) / 2);
-	jiffies_hi /= (freq_hi - freq_lo);
-	jiffies_lo = jiffies_total - jiffies_hi;
+	delay_hi_us = (freq_avg - freq_lo) * dbs_data->sampling_rate;
+	delay_hi_us += (freq_hi - freq_lo) / 2;
+	delay_hi_us /= freq_hi - freq_lo;
+	dbs_info->freq_hi_delay_us = delay_hi_us;
 	dbs_info->freq_lo = freq_lo;
-	dbs_info->freq_lo_jiffies = jiffies_lo;
-	dbs_info->freq_hi_jiffies = jiffies_hi;
+	dbs_info->freq_lo_delay_us = dbs_data->sampling_rate - delay_hi_us;
 	return freq_hi;
 }
 
-static void ondemand_powersave_bias_init(void)
+static void ondemand_powersave_bias_init(struct cpufreq_policy *policy)
 {
-	int i;
-	for_each_online_cpu(i) {
-		ondemand_powersave_bias_init_cpu(i);
-	}
+	struct od_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data);
+
+	dbs_info->freq_table = cpufreq_frequency_get_table(policy->cpu);
+	dbs_info->freq_lo = 0;
 }
 
 static void dbs_freq_increase(struct cpufreq_policy *policy, unsigned int freq)
 {
-	struct dbs_data *dbs_data = policy->governor_data;
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct dbs_data *dbs_data = policy_dbs->dbs_data;
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 
 	if (od_tuners->powersave_bias)
@@ -152,21 +138,21 @@ static void dbs_freq_increase(struct cpufreq_policy *policy, unsigned int freq)
  * (default), then we try to increase frequency. Else, we adjust the frequency
  * proportional to load.
  */
-static void od_check_cpu(int cpu, unsigned int load)
+static void od_update(struct cpufreq_policy *policy)
 {
-	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
-	struct cpufreq_policy *policy = dbs_info->cdbs.shared->policy;
-	struct dbs_data *dbs_data = policy->governor_data;
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct od_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs);
+	struct dbs_data *dbs_data = policy_dbs->dbs_data;
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+	unsigned int load = dbs_update(policy);
 
 	dbs_info->freq_lo = 0;
 
 	/* Check for frequency increase */
-	if (load > od_tuners->up_threshold) {
+	if (load > dbs_data->up_threshold) {
 		/* If switching to max speed, apply sampling_down_factor */
 		if (policy->cur < policy->max)
-			dbs_info->rate_mult =
-				od_tuners->sampling_down_factor;
+			policy_dbs->rate_mult = dbs_data->sampling_down_factor;
 		dbs_freq_increase(policy, policy->max);
 	} else {
 		/* Calculate the next frequency proportional to load */
@@ -177,177 +163,70 @@ static void od_check_cpu(int cpu, unsigned int load)
 		freq_next = min_f + load * (max_f - min_f) / 100;
 
 		/* No longer fully busy, reset rate_mult */
-		dbs_info->rate_mult = 1;
+		policy_dbs->rate_mult = 1;
 
-		if (!od_tuners->powersave_bias) {
-			__cpufreq_driver_target(policy, freq_next,
-					CPUFREQ_RELATION_C);
-			return;
-		}
+		if (od_tuners->powersave_bias)
+			freq_next = od_ops.powersave_bias_target(policy,
+								 freq_next,
+								 CPUFREQ_RELATION_L);
 
-		freq_next = od_ops.powersave_bias_target(policy, freq_next,
-					CPUFREQ_RELATION_L);
 		__cpufreq_driver_target(policy, freq_next, CPUFREQ_RELATION_C);
 	}
 }
 
-static unsigned int od_dbs_timer(struct cpufreq_policy *policy, bool modify_all)
+static unsigned int od_dbs_timer(struct cpufreq_policy *policy)
 {
-	struct dbs_data *dbs_data = policy->governor_data;
-	unsigned int cpu = policy->cpu;
-	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
-			cpu);
-	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
-	int delay = 0, sample_type = dbs_info->sample_type;
-
-	if (!modify_all)
-		goto max_delay;
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct dbs_data *dbs_data = policy_dbs->dbs_data;
+	struct od_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs);
+	int sample_type = dbs_info->sample_type;
 
 	/* Common NORMAL_SAMPLE setup */
 	dbs_info->sample_type = OD_NORMAL_SAMPLE;
-	if (sample_type == OD_SUB_SAMPLE) {
-		delay = dbs_info->freq_lo_jiffies;
+	/*
+	 * OD_SUB_SAMPLE doesn't make sense if sample_delay_ns is 0, so ignore
+	 * it then.
+	 */
+	if (sample_type == OD_SUB_SAMPLE && policy_dbs->sample_delay_ns > 0) {
 		__cpufreq_driver_target(policy, dbs_info->freq_lo,
 					CPUFREQ_RELATION_H);
-	} else {
-		dbs_check_cpu(dbs_data, cpu);
-		if (dbs_info->freq_lo) {
-			/* Setup timer for SUB_SAMPLE */
-			dbs_info->sample_type = OD_SUB_SAMPLE;
-			delay = dbs_info->freq_hi_jiffies;
-		}
+		return dbs_info->freq_lo_delay_us;
 	}
 
-max_delay:
-	if (!delay)
-		delay = delay_for_sampling_rate(od_tuners->sampling_rate
-				* dbs_info->rate_mult);
-
-	return delay;
-}
-
-/************************** sysfs interface ************************/
-static struct common_dbs_data od_dbs_cdata;
-
-/**
- * update_sampling_rate - update sampling rate effective immediately if needed.
- * @new_rate: new sampling rate
- *
- * If new rate is smaller than the old, simply updating
- * dbs_tuners_int.sampling_rate might not be appropriate. For example, if the
- * original sampling_rate was 1 second and the requested new sampling rate is 10
- * ms because the user needs immediate reaction from ondemand governor, but not
- * sure if higher frequency will be required or not, then, the governor may
- * change the sampling rate too late; up to 1 second later. Thus, if we are
- * reducing the sampling rate, we need to make the new value effective
- * immediately.
- */
-static void update_sampling_rate(struct dbs_data *dbs_data,
-		unsigned int new_rate)
-{
-	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
-	struct cpumask cpumask;
-	int cpu;
-
-	od_tuners->sampling_rate = new_rate = max(new_rate,
-			dbs_data->min_sampling_rate);
-
-	/*
-	 * Lock governor so that governor start/stop can't execute in parallel.
-	 */
-	mutex_lock(&od_dbs_cdata.mutex);
-
-	cpumask_copy(&cpumask, cpu_online_mask);
-
-	for_each_cpu(cpu, &cpumask) {
-		struct cpufreq_policy *policy;
-		struct od_cpu_dbs_info_s *dbs_info;
-		struct cpu_dbs_info *cdbs;
-		struct cpu_common_dbs_info *shared;
-		unsigned long next_sampling, appointed_at;
-
-		dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
-		cdbs = &dbs_info->cdbs;
-		shared = cdbs->shared;
-
-		/*
-		 * A valid shared and shared->policy means governor hasn't
-		 * stopped or exited yet.
-		 */
-		if (!shared || !shared->policy)
-			continue;
-
-		policy = shared->policy;
-
-		/* clear all CPUs of this policy */
-		cpumask_andnot(&cpumask, &cpumask, policy->cpus);
+	od_update(policy);
 
-		/*
-		 * Update sampling rate for CPUs whose policy is governed by
-		 * dbs_data. In case of governor_per_policy, only a single
-		 * policy will be governed by dbs_data, otherwise there can be
-		 * multiple policies that are governed by the same dbs_data.
-		 */
-		if (dbs_data != policy->governor_data)
-			continue;
-
-		/*
-		 * Checking this for any CPU should be fine, timers for all of
-		 * them are scheduled together.
-		 */
-		next_sampling = jiffies + usecs_to_jiffies(new_rate);
-		appointed_at = dbs_info->cdbs.timer.expires;
-
-		if (time_before(next_sampling, appointed_at)) {
-			gov_cancel_work(shared);
-			gov_add_timers(policy, usecs_to_jiffies(new_rate));
-
-		}
+	if (dbs_info->freq_lo) {
+		/* Setup timer for SUB_SAMPLE */
+		dbs_info->sample_type = OD_SUB_SAMPLE;
+		return dbs_info->freq_hi_delay_us;
 	}
 
-	mutex_unlock(&od_dbs_cdata.mutex);
+	return dbs_data->sampling_rate * policy_dbs->rate_mult;
 }
 
-static ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
-{
-	unsigned int input;
-	int ret;
-	ret = sscanf(buf, "%u", &input);
-	if (ret != 1)
-		return -EINVAL;
-
-	update_sampling_rate(dbs_data, input);
-	return count;
-}
+/************************** sysfs interface ************************/
+static struct dbs_governor od_dbs_gov;
 
 static ssize_t store_io_is_busy(struct dbs_data *dbs_data, const char *buf,
 		size_t count)
 {
-	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 	unsigned int input;
 	int ret;
-	unsigned int j;
 
 	ret = sscanf(buf, "%u", &input);
 	if (ret != 1)
 		return -EINVAL;
-	od_tuners->io_is_busy = !!input;
+	dbs_data->io_is_busy = !!input;
 
 	/* we need to re-evaluate prev_cpu_idle */
-	for_each_online_cpu(j) {
-		struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
-									j);
-		dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j,
-			&dbs_info->cdbs.prev_cpu_wall, od_tuners->io_is_busy);
-	}
+	gov_update_cpu_data(dbs_data);
+
 	return count;
 }
 
 static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
 		size_t count)
 {
-	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 	unsigned int input;
 	int ret;
 	ret = sscanf(buf, "%u", &input);
@@ -357,40 +236,43 @@ static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
 		return -EINVAL;
 	}
 
-	od_tuners->up_threshold = input;
+	dbs_data->up_threshold = input;
 	return count;
 }
 
 static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
 		const char *buf, size_t count)
 {
-	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
-	unsigned int input, j;
+	struct policy_dbs_info *policy_dbs;
+	unsigned int input;
 	int ret;
 	ret = sscanf(buf, "%u", &input);
 
 	if (ret != 1 || input > MAX_SAMPLING_DOWN_FACTOR || input < 1)
 		return -EINVAL;
-	od_tuners->sampling_down_factor = input;
+
+	dbs_data->sampling_down_factor = input;
 
 	/* Reset down sampling multiplier in case it was active */
-	for_each_online_cpu(j) {
-		struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
-				j);
-		dbs_info->rate_mult = 1;
+	list_for_each_entry(policy_dbs, &dbs_data->policy_dbs_list, list) {
+		/*
+		 * Doing this without locking might lead to using different
+		 * rate_mult values in od_update() and od_dbs_timer().
+		 */
+		mutex_lock(&policy_dbs->timer_mutex);
+		policy_dbs->rate_mult = 1;
+		mutex_unlock(&policy_dbs->timer_mutex);
 	}
+
 	return count;
 }
 
 static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
 		const char *buf, size_t count)
 {
-	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 	unsigned int input;
 	int ret;
 
-	unsigned int j;
-
 	ret = sscanf(buf, "%u", &input);
 	if (ret != 1)
 		return -EINVAL;
@@ -398,22 +280,14 @@ static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
 	if (input > 1)
 		input = 1;
 
-	if (input == od_tuners->ignore_nice_load) { /* nothing to do */
+	if (input == dbs_data->ignore_nice_load) { /* nothing to do */
 		return count;
 	}
-	od_tuners->ignore_nice_load = input;
+	dbs_data->ignore_nice_load = input;
 
 	/* we need to re-evaluate prev_cpu_idle */
-	for_each_online_cpu(j) {
-		struct od_cpu_dbs_info_s *dbs_info;
-		dbs_info = &per_cpu(od_cpu_dbs_info, j);
-		dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j,
-			&dbs_info->cdbs.prev_cpu_wall, od_tuners->io_is_busy);
-		if (od_tuners->ignore_nice_load)
-			dbs_info->cdbs.prev_cpu_nice =
-				kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+	gov_update_cpu_data(dbs_data);
 
-	}
 	return count;
 }
 
@@ -421,6 +295,7 @@ static ssize_t store_powersave_bias(struct dbs_data *dbs_data, const char *buf,
 		size_t count)
 {
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+	struct policy_dbs_info *policy_dbs;
 	unsigned int input;
 	int ret;
 	ret = sscanf(buf, "%u", &input);
@@ -432,59 +307,54 @@ static ssize_t store_powersave_bias(struct dbs_data *dbs_data, const char *buf,
 		input = 1000;
 
 	od_tuners->powersave_bias = input;
-	ondemand_powersave_bias_init();
+
+	list_for_each_entry(policy_dbs, &dbs_data->policy_dbs_list, list)
+		ondemand_powersave_bias_init(policy_dbs->policy);
+
 	return count;
 }
 
-show_store_one(od, sampling_rate);
-show_store_one(od, io_is_busy);
-show_store_one(od, up_threshold);
-show_store_one(od, sampling_down_factor);
-show_store_one(od, ignore_nice_load);
-show_store_one(od, powersave_bias);
-declare_show_sampling_rate_min(od);
-
-gov_sys_pol_attr_rw(sampling_rate);
-gov_sys_pol_attr_rw(io_is_busy);
-gov_sys_pol_attr_rw(up_threshold);
-gov_sys_pol_attr_rw(sampling_down_factor);
-gov_sys_pol_attr_rw(ignore_nice_load);
-gov_sys_pol_attr_rw(powersave_bias);
-gov_sys_pol_attr_ro(sampling_rate_min);
-
-static struct attribute *dbs_attributes_gov_sys[] = {
-	&sampling_rate_min_gov_sys.attr,
-	&sampling_rate_gov_sys.attr,
-	&up_threshold_gov_sys.attr,
-	&sampling_down_factor_gov_sys.attr,
-	&ignore_nice_load_gov_sys.attr,
-	&powersave_bias_gov_sys.attr,
-	&io_is_busy_gov_sys.attr,
+gov_show_one_common(sampling_rate);
+gov_show_one_common(up_threshold);
+gov_show_one_common(sampling_down_factor);
+gov_show_one_common(ignore_nice_load);
+gov_show_one_common(min_sampling_rate);
+gov_show_one_common(io_is_busy);
+gov_show_one(od, powersave_bias);
+
+gov_attr_rw(sampling_rate);
+gov_attr_rw(io_is_busy);
+gov_attr_rw(up_threshold);
+gov_attr_rw(sampling_down_factor);
+gov_attr_rw(ignore_nice_load);
+gov_attr_rw(powersave_bias);
+gov_attr_ro(min_sampling_rate);
+
+static struct attribute *od_attributes[] = {
+	&min_sampling_rate.attr,
+	&sampling_rate.attr,
+	&up_threshold.attr,
+	&sampling_down_factor.attr,
+	&ignore_nice_load.attr,
+	&powersave_bias.attr,
+	&io_is_busy.attr,
 	NULL
 };
 
-static struct attribute_group od_attr_group_gov_sys = {
-	.attrs = dbs_attributes_gov_sys,
-	.name = "ondemand",
-};
+/************************** sysfs end ************************/
 
-static struct attribute *dbs_attributes_gov_pol[] = {
-	&sampling_rate_min_gov_pol.attr,
-	&sampling_rate_gov_pol.attr,
-	&up_threshold_gov_pol.attr,
-	&sampling_down_factor_gov_pol.attr,
-	&ignore_nice_load_gov_pol.attr,
-	&powersave_bias_gov_pol.attr,
-	&io_is_busy_gov_pol.attr,
-	NULL
-};
+static struct policy_dbs_info *od_alloc(void)
+{
+	struct od_policy_dbs_info *dbs_info;
 
-static struct attribute_group od_attr_group_gov_pol = {
-	.attrs = dbs_attributes_gov_pol,
-	.name = "ondemand",
-};
+	dbs_info = kzalloc(sizeof(*dbs_info), GFP_KERNEL);
+	return dbs_info ? &dbs_info->policy_dbs : NULL;
+}
 
-/************************** sysfs end ************************/
+static void od_free(struct policy_dbs_info *policy_dbs)
+{
+	kfree(to_dbs_info(policy_dbs));
+}
 
 static int od_init(struct dbs_data *dbs_data, bool notify)
 {
@@ -503,7 +373,7 @@ static int od_init(struct dbs_data *dbs_data, bool notify)
 	put_cpu();
 	if (idle_time != -1ULL) {
 		/* Idle micro accounting is supported. Use finer thresholds */
-		tuners->up_threshold = MICRO_FREQUENCY_UP_THRESHOLD;
+		dbs_data->up_threshold = MICRO_FREQUENCY_UP_THRESHOLD;
 		/*
 		 * In nohz/micro accounting case we set the minimum frequency
 		 * not depending on HZ, but fixed (very low). The deferred
@@ -511,17 +381,17 @@ static int od_init(struct dbs_data *dbs_data, bool notify)
 		*/
 		dbs_data->min_sampling_rate = MICRO_FREQUENCY_MIN_SAMPLE_RATE;
 	} else {
-		tuners->up_threshold = DEF_FREQUENCY_UP_THRESHOLD;
+		dbs_data->up_threshold = DEF_FREQUENCY_UP_THRESHOLD;
 
 		/* For correct statistics, we need 10 ticks for each measure */
 		dbs_data->min_sampling_rate = MIN_SAMPLING_RATE_RATIO *
 			jiffies_to_usecs(10);
 	}
 
-	tuners->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR;
-	tuners->ignore_nice_load = 0;
+	dbs_data->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR;
+	dbs_data->ignore_nice_load = 0;
 	tuners->powersave_bias = default_powersave_bias;
-	tuners->io_is_busy = should_io_be_busy();
+	dbs_data->io_is_busy = should_io_be_busy();
 
 	dbs_data->tuners = tuners;
 	return 0;
@@ -532,33 +402,38 @@ static void od_exit(struct dbs_data *dbs_data, bool notify)
 	kfree(dbs_data->tuners);
 }
 
-define_get_cpu_dbs_routines(od_cpu_dbs_info);
+static void od_start(struct cpufreq_policy *policy)
+{
+	struct od_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data);
+
+	dbs_info->sample_type = OD_NORMAL_SAMPLE;
+	ondemand_powersave_bias_init(policy);
+}
 
 static struct od_ops od_ops = {
-	.powersave_bias_init_cpu = ondemand_powersave_bias_init_cpu,
 	.powersave_bias_target = generic_powersave_bias_target,
-	.freq_increase = dbs_freq_increase,
 };
 
-static struct common_dbs_data od_dbs_cdata = {
-	.governor = GOV_ONDEMAND,
-	.attr_group_gov_sys = &od_attr_group_gov_sys,
-	.attr_group_gov_pol = &od_attr_group_gov_pol,
-	.get_cpu_cdbs = get_cpu_cdbs,
-	.get_cpu_dbs_info_s = get_cpu_dbs_info_s,
+static struct dbs_governor od_dbs_gov = {
+	.gov = {
+		.name = "ondemand",
+		.governor = cpufreq_governor_dbs,
+		.max_transition_latency	= TRANSITION_LATENCY_LIMIT,
+		.owner = THIS_MODULE,
+	},
+	.kobj_type = { .default_attrs = od_attributes },
 	.gov_dbs_timer = od_dbs_timer,
-	.gov_check_cpu = od_check_cpu,
-	.gov_ops = &od_ops,
+	.alloc = od_alloc,
+	.free = od_free,
 	.init = od_init,
 	.exit = od_exit,
-	.mutex = __MUTEX_INITIALIZER(od_dbs_cdata.mutex),
+	.start = od_start,
 };
 
+#define CPU_FREQ_GOV_ONDEMAND	(&od_dbs_gov.gov)
+
 static void od_set_powersave_bias(unsigned int powersave_bias)
 {
-	struct cpufreq_policy *policy;
-	struct dbs_data *dbs_data;
-	struct od_dbs_tuners *od_tuners;
 	unsigned int cpu;
 	cpumask_t done;
 
@@ -567,22 +442,25 @@ static void od_set_powersave_bias(unsigned int powersave_bias)
 
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
-		struct cpu_common_dbs_info *shared;
+		struct cpufreq_policy *policy;
+		struct policy_dbs_info *policy_dbs;
+		struct dbs_data *dbs_data;
+		struct od_dbs_tuners *od_tuners;
 
 		if (cpumask_test_cpu(cpu, &done))
 			continue;
 
-		shared = per_cpu(od_cpu_dbs_info, cpu).cdbs.shared;
-		if (!shared)
+		policy = cpufreq_cpu_get_raw(cpu);
+		if (!policy || policy->governor != CPU_FREQ_GOV_ONDEMAND)
 			continue;
 
-		policy = shared->policy;
-		cpumask_or(&done, &done, policy->cpus);
-
-		if (policy->governor != &cpufreq_gov_ondemand)
+		policy_dbs = policy->governor_data;
+		if (!policy_dbs)
 			continue;
 
-		dbs_data = policy->governor_data;
+		cpumask_or(&done, &done, policy->cpus);
+
+		dbs_data = policy_dbs->dbs_data;
 		od_tuners = dbs_data->tuners;
 		od_tuners->powersave_bias = default_powersave_bias;
 	}
@@ -605,30 +483,14 @@ void od_unregister_powersave_bias_handler(void)
 }
 EXPORT_SYMBOL_GPL(od_unregister_powersave_bias_handler);
 
-static int od_cpufreq_governor_dbs(struct cpufreq_policy *policy,
-		unsigned int event)
-{
-	return cpufreq_governor_dbs(policy, &od_dbs_cdata, event);
-}
-
-#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
-static
-#endif
-struct cpufreq_governor cpufreq_gov_ondemand = {
-	.name			= "ondemand",
-	.governor		= od_cpufreq_governor_dbs,
-	.max_transition_latency	= TRANSITION_LATENCY_LIMIT,
-	.owner			= THIS_MODULE,
-};
-
 static int __init cpufreq_gov_dbs_init(void)
 {
-	return cpufreq_register_governor(&cpufreq_gov_ondemand);
+	return cpufreq_register_governor(CPU_FREQ_GOV_ONDEMAND);
 }
 
 static void __exit cpufreq_gov_dbs_exit(void)
 {
-	cpufreq_unregister_governor(&cpufreq_gov_ondemand);
+	cpufreq_unregister_governor(CPU_FREQ_GOV_ONDEMAND);
 }
 
 MODULE_AUTHOR("Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>");
@@ -638,6 +500,11 @@ MODULE_DESCRIPTION("'cpufreq_ondemand' - A dynamic cpufreq governor for "
 MODULE_LICENSE("GPL");
 
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
+struct cpufreq_governor *cpufreq_default_governor(void)
+{
+	return CPU_FREQ_GOV_ONDEMAND;
+}
+
 fs_initcall(cpufreq_gov_dbs_init);
 #else
 module_init(cpufreq_gov_dbs_init);
diff --git a/drivers/cpufreq/cpufreq_ondemand.h b/drivers/cpufreq/cpufreq_ondemand.h
new file mode 100644
index 000000000000..f0121db3cd9e
--- /dev/null
+++ b/drivers/cpufreq/cpufreq_ondemand.h
@@ -0,0 +1,30 @@
+/*
+ * Header file for CPUFreq ondemand governor and related code.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "cpufreq_governor.h"
+
+struct od_policy_dbs_info {
+	struct policy_dbs_info policy_dbs;
+	struct cpufreq_frequency_table *freq_table;
+	unsigned int freq_lo;
+	unsigned int freq_lo_delay_us;
+	unsigned int freq_hi_delay_us;
+	unsigned int sample_type:1;
+};
+
+static inline struct od_policy_dbs_info *to_dbs_info(struct policy_dbs_info *policy_dbs)
+{
+	return container_of(policy_dbs, struct od_policy_dbs_info, policy_dbs);
+}
+
+struct od_dbs_tuners {
+	unsigned int powersave_bias;
+};
diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c
index cf117deb39b1..af9f4b96f5a8 100644
--- a/drivers/cpufreq/cpufreq_performance.c
+++ b/drivers/cpufreq/cpufreq_performance.c
@@ -33,10 +33,7 @@ static int cpufreq_governor_performance(struct cpufreq_policy *policy,
 	return 0;
 }
 
-#ifdef CONFIG_CPU_FREQ_GOV_PERFORMANCE_MODULE
-static
-#endif
-struct cpufreq_governor cpufreq_gov_performance = {
+static struct cpufreq_governor cpufreq_gov_performance = {
 	.name		= "performance",
 	.governor	= cpufreq_governor_performance,
 	.owner		= THIS_MODULE,
@@ -52,6 +49,19 @@ static void __exit cpufreq_gov_performance_exit(void)
 	cpufreq_unregister_governor(&cpufreq_gov_performance);
 }
 
+#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE
+struct cpufreq_governor *cpufreq_default_governor(void)
+{
+	return &cpufreq_gov_performance;
+}
+#endif
+#ifndef CONFIG_CPU_FREQ_GOV_PERFORMANCE_MODULE
+struct cpufreq_governor *cpufreq_fallback_governor(void)
+{
+	return &cpufreq_gov_performance;
+}
+#endif
+
 MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
 MODULE_DESCRIPTION("CPUfreq policy governor 'performance'");
 MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c
index e3b874c235ea..b8b400232a74 100644
--- a/drivers/cpufreq/cpufreq_powersave.c
+++ b/drivers/cpufreq/cpufreq_powersave.c
@@ -33,10 +33,7 @@ static int cpufreq_governor_powersave(struct cpufreq_policy *policy,
 	return 0;
 }
 
-#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE
-static
-#endif
-struct cpufreq_governor cpufreq_gov_powersave = {
+static struct cpufreq_governor cpufreq_gov_powersave = {
 	.name		= "powersave",
 	.governor	= cpufreq_governor_powersave,
 	.owner		= THIS_MODULE,
@@ -57,6 +54,11 @@ MODULE_DESCRIPTION("CPUfreq policy governor 'powersave'");
 MODULE_LICENSE("GPL");
 
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE
+struct cpufreq_governor *cpufreq_default_governor(void)
+{
+	return &cpufreq_gov_powersave;
+}
+
 fs_initcall(cpufreq_gov_powersave_init);
 #else
 module_init(cpufreq_gov_powersave_init);
diff --git a/drivers/cpufreq/cpufreq_userspace.c b/drivers/cpufreq/cpufreq_userspace.c
index 4dbf1db16aca..4d16f45ee1da 100644
--- a/drivers/cpufreq/cpufreq_userspace.c
+++ b/drivers/cpufreq/cpufreq_userspace.c
@@ -89,10 +89,7 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
 	return rc;
 }
 
-#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE
-static
-#endif
-struct cpufreq_governor cpufreq_gov_userspace = {
+static struct cpufreq_governor cpufreq_gov_userspace = {
 	.name		= "userspace",
 	.governor	= cpufreq_governor_userspace,
 	.store_setspeed	= cpufreq_set,
@@ -116,6 +113,11 @@ MODULE_DESCRIPTION("CPUfreq policy governor 'userspace'");
 MODULE_LICENSE("GPL");
 
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE
+struct cpufreq_governor *cpufreq_default_governor(void)
+{
+	return &cpufreq_gov_userspace;
+}
+
 fs_initcall(cpufreq_gov_userspace_init);
 #else
 module_init(cpufreq_gov_userspace_init);
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index cd83d477e32d..cb5607495816 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -71,7 +71,7 @@ struct sample {
 	u64 mperf;
 	u64 tsc;
 	int freq;
-	ktime_t time;
+	u64 time;
 };
 
 struct pstate_data {
@@ -103,13 +103,13 @@ struct _pid {
 struct cpudata {
 	int cpu;
 
-	struct timer_list timer;
+	struct update_util_data update_util;
 
 	struct pstate_data pstate;
 	struct vid_data vid;
 	struct _pid pid;
 
-	ktime_t last_sample_time;
+	u64	last_sample_time;
 	u64	prev_aperf;
 	u64	prev_mperf;
 	u64	prev_tsc;
@@ -120,6 +120,7 @@ struct cpudata {
 static struct cpudata **all_cpu_data;
 struct pstate_adjust_policy {
 	int sample_rate_ms;
+	s64 sample_rate_ns;
 	int deadband;
 	int setpoint;
 	int p_gain_pct;
@@ -197,8 +198,8 @@ static struct perf_limits *limits = &powersave_limits;
 
 static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
 			     int deadband, int integral) {
-	pid->setpoint = setpoint;
-	pid->deadband  = deadband;
+	pid->setpoint = int_tofp(setpoint);
+	pid->deadband  = int_tofp(deadband);
 	pid->integral  = int_tofp(integral);
 	pid->last_err  = int_tofp(setpoint) - int_tofp(busy);
 }
@@ -224,9 +225,9 @@ static signed int pid_calc(struct _pid *pid, int32_t busy)
 	int32_t pterm, dterm, fp_error;
 	int32_t integral_limit;
 
-	fp_error = int_tofp(pid->setpoint) - busy;
+	fp_error = pid->setpoint - busy;
 
-	if (abs(fp_error) <= int_tofp(pid->deadband))
+	if (abs(fp_error) <= pid->deadband)
 		return 0;
 
 	pterm = mul_fp(pid->p_gain, fp_error);
@@ -286,7 +287,7 @@ static inline void update_turbo_state(void)
 		 cpu->pstate.max_pstate == cpu->pstate.turbo_pstate);
 }
 
-static void intel_pstate_hwp_set(void)
+static void intel_pstate_hwp_set(const struct cpumask *cpumask)
 {
 	int min, hw_min, max, hw_max, cpu, range, adj_range;
 	u64 value, cap;
@@ -296,9 +297,7 @@ static void intel_pstate_hwp_set(void)
 	hw_max = HWP_HIGHEST_PERF(cap);
 	range = hw_max - hw_min;
 
-	get_online_cpus();
-
-	for_each_online_cpu(cpu) {
+	for_each_cpu(cpu, cpumask) {
 		rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);
 		adj_range = limits->min_perf_pct * range / 100;
 		min = hw_min + adj_range;
@@ -317,7 +316,12 @@ static void intel_pstate_hwp_set(void)
 		value |= HWP_MAX_PERF(max);
 		wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value);
 	}
+}
 
+static void intel_pstate_hwp_set_online_cpus(void)
+{
+	get_online_cpus();
+	intel_pstate_hwp_set(cpu_online_mask);
 	put_online_cpus();
 }
 
@@ -439,7 +443,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 	limits->no_turbo = clamp_t(int, input, 0, 1);
 
 	if (hwp_active)
-		intel_pstate_hwp_set();
+		intel_pstate_hwp_set_online_cpus();
 
 	return count;
 }
@@ -465,7 +469,7 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
 				  int_tofp(100));
 
 	if (hwp_active)
-		intel_pstate_hwp_set();
+		intel_pstate_hwp_set_online_cpus();
 	return count;
 }
 
@@ -490,7 +494,7 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
 				  int_tofp(100));
 
 	if (hwp_active)
-		intel_pstate_hwp_set();
+		intel_pstate_hwp_set_online_cpus();
 	return count;
 }
 
@@ -531,6 +535,9 @@ static void __init intel_pstate_sysfs_expose_params(void)
 
 static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 {
+	/* First disable HWP notification interrupt as we don't process them */
+	wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00);
+
 	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
 }
 
@@ -712,7 +719,7 @@ static void core_set_pstate(struct cpudata *cpudata, int pstate)
 	if (limits->no_turbo && !limits->turbo_disabled)
 		val |= (u64)1 << 32;
 
-	wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val);
+	wrmsrl(MSR_IA32_PERF_CTL, val);
 }
 
 static int knl_get_turbo_pstate(void)
@@ -824,11 +831,11 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
 	 * policy, or by cpu specific default values determined through
 	 * experimentation.
 	 */
-	max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf), limits->max_perf));
+	max_perf_adj = fp_toint(max_perf * limits->max_perf);
 	*max = clamp_t(int, max_perf_adj,
 			cpu->pstate.min_pstate, cpu->pstate.turbo_pstate);
 
-	min_perf = fp_toint(mul_fp(int_tofp(max_perf), limits->min_perf));
+	min_perf = fp_toint(max_perf * limits->min_perf);
 	*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
 }
 
@@ -874,16 +881,10 @@ static inline void intel_pstate_calc_busy(struct cpudata *cpu)
 	core_pct = int_tofp(sample->aperf) * int_tofp(100);
 	core_pct = div64_u64(core_pct, int_tofp(sample->mperf));
 
-	sample->freq = fp_toint(
-		mul_fp(int_tofp(
-			cpu->pstate.max_pstate_physical *
-			cpu->pstate.scaling / 100),
-			core_pct));
-
 	sample->core_pct_busy = (int32_t)core_pct;
 }
 
-static inline void intel_pstate_sample(struct cpudata *cpu)
+static inline bool intel_pstate_sample(struct cpudata *cpu, u64 time)
 {
 	u64 aperf, mperf;
 	unsigned long flags;
@@ -893,14 +894,14 @@ static inline void intel_pstate_sample(struct cpudata *cpu)
 	rdmsrl(MSR_IA32_APERF, aperf);
 	rdmsrl(MSR_IA32_MPERF, mperf);
 	tsc = rdtsc();
-	if ((cpu->prev_mperf == mperf) || (cpu->prev_tsc == tsc)) {
+	if (cpu->prev_mperf == mperf || cpu->prev_tsc == tsc) {
 		local_irq_restore(flags);
-		return;
+		return false;
 	}
 	local_irq_restore(flags);
 
 	cpu->last_sample_time = cpu->sample.time;
-	cpu->sample.time = ktime_get();
+	cpu->sample.time = time;
 	cpu->sample.aperf = aperf;
 	cpu->sample.mperf = mperf;
 	cpu->sample.tsc =  tsc;
@@ -908,27 +909,16 @@ static inline void intel_pstate_sample(struct cpudata *cpu)
 	cpu->sample.mperf -= cpu->prev_mperf;
 	cpu->sample.tsc -= cpu->prev_tsc;
 
-	intel_pstate_calc_busy(cpu);
-
 	cpu->prev_aperf = aperf;
 	cpu->prev_mperf = mperf;
 	cpu->prev_tsc = tsc;
+	return true;
 }
 
-static inline void intel_hwp_set_sample_time(struct cpudata *cpu)
-{
-	int delay;
-
-	delay = msecs_to_jiffies(50);
-	mod_timer_pinned(&cpu->timer, jiffies + delay);
-}
-
-static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
+static inline int32_t get_avg_frequency(struct cpudata *cpu)
 {
-	int delay;
-
-	delay = msecs_to_jiffies(pid_params.sample_rate_ms);
-	mod_timer_pinned(&cpu->timer, jiffies + delay);
+	return div64_u64(cpu->pstate.max_pstate_physical * cpu->sample.aperf *
+		cpu->pstate.scaling, cpu->sample.mperf);
 }
 
 static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
@@ -954,7 +944,6 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
 	mperf = cpu->sample.mperf + delta_iowait_mperf;
 	cpu->prev_cummulative_iowait = cummulative_iowait;
 
-
 	/*
 	 * The load can be estimated as the ratio of the mperf counter
 	 * running at a constant frequency during active periods
@@ -970,8 +959,9 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
 static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
 {
 	int32_t core_busy, max_pstate, current_pstate, sample_ratio;
-	s64 duration_us;
-	u32 sample_time;
+	u64 duration_ns;
+
+	intel_pstate_calc_busy(cpu);
 
 	/*
 	 * core_busy is the ratio of actual performance to max
@@ -990,18 +980,16 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
 	core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate));
 
 	/*
-	 * Since we have a deferred timer, it will not fire unless
-	 * we are in C0.  So, determine if the actual elapsed time
-	 * is significantly greater (3x) than our sample interval.  If it
-	 * is, then we were idle for a long enough period of time
-	 * to adjust our busyness.
+	 * Since our utilization update callback will not run unless we are
+	 * in C0, check if the actual elapsed time is significantly greater (3x)
+	 * than our sample interval.  If it is, then we were idle for a long
+	 * enough period of time to adjust our busyness.
 	 */
-	sample_time = pid_params.sample_rate_ms  * USEC_PER_MSEC;
-	duration_us = ktime_us_delta(cpu->sample.time,
-				     cpu->last_sample_time);
-	if (duration_us > sample_time * 3) {
-		sample_ratio = div_fp(int_tofp(sample_time),
-				      int_tofp(duration_us));
+	duration_ns = cpu->sample.time - cpu->last_sample_time;
+	if ((s64)duration_ns > pid_params.sample_rate_ns * 3
+	    && cpu->last_sample_time > 0) {
+		sample_ratio = div_fp(int_tofp(pid_params.sample_rate_ns),
+				      int_tofp(duration_ns));
 		core_busy = mul_fp(core_busy, sample_ratio);
 	}
 
@@ -1028,26 +1016,21 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 		sample->mperf,
 		sample->aperf,
 		sample->tsc,
-		sample->freq);
+		get_avg_frequency(cpu));
 }
 
-static void intel_hwp_timer_func(unsigned long __data)
+static void intel_pstate_update_util(struct update_util_data *data, u64 time,
+				     unsigned long util, unsigned long max)
 {
-	struct cpudata *cpu = (struct cpudata *) __data;
+	struct cpudata *cpu = container_of(data, struct cpudata, update_util);
+	u64 delta_ns = time - cpu->sample.time;
 
-	intel_pstate_sample(cpu);
-	intel_hwp_set_sample_time(cpu);
-}
+	if ((s64)delta_ns >= pid_params.sample_rate_ns) {
+		bool sample_taken = intel_pstate_sample(cpu, time);
 
-static void intel_pstate_timer_func(unsigned long __data)
-{
-	struct cpudata *cpu = (struct cpudata *) __data;
-
-	intel_pstate_sample(cpu);
-
-	intel_pstate_adjust_busy_pstate(cpu);
-
-	intel_pstate_set_sample_time(cpu);
+		if (sample_taken && !hwp_active)
+			intel_pstate_adjust_busy_pstate(cpu);
+	}
 }
 
 #define ICPU(model, policy) \
@@ -1095,24 +1078,19 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 
 	cpu->cpu = cpunum;
 
-	if (hwp_active)
+	if (hwp_active) {
 		intel_pstate_hwp_enable(cpu);
+		pid_params.sample_rate_ms = 50;
+		pid_params.sample_rate_ns = 50 * NSEC_PER_MSEC;
+	}
 
 	intel_pstate_get_cpu_pstates(cpu);
 
-	init_timer_deferrable(&cpu->timer);
-	cpu->timer.data = (unsigned long)cpu;
-	cpu->timer.expires = jiffies + HZ/100;
-
-	if (!hwp_active)
-		cpu->timer.function = intel_pstate_timer_func;
-	else
-		cpu->timer.function = intel_hwp_timer_func;
-
 	intel_pstate_busy_pid_reset(cpu);
-	intel_pstate_sample(cpu);
+	intel_pstate_sample(cpu, 0);
 
-	add_timer_on(&cpu->timer, cpunum);
+	cpu->update_util.func = intel_pstate_update_util;
+	cpufreq_set_update_util_data(cpunum, &cpu->update_util);
 
 	pr_debug("intel_pstate: controlling: cpu %d\n", cpunum);
 
@@ -1128,7 +1106,7 @@ static unsigned int intel_pstate_get(unsigned int cpu_num)
 	if (!cpu)
 		return 0;
 	sample = &cpu->sample;
-	return sample->freq;
+	return get_avg_frequency(cpu);
 }
 
 static int intel_pstate_set_policy(struct cpufreq_policy *policy)
@@ -1141,7 +1119,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 		pr_debug("intel_pstate: set performance\n");
 		limits = &performance_limits;
 		if (hwp_active)
-			intel_pstate_hwp_set();
+			intel_pstate_hwp_set(policy->cpus);
 		return 0;
 	}
 
@@ -1173,7 +1151,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 				  int_tofp(100));
 
 	if (hwp_active)
-		intel_pstate_hwp_set();
+		intel_pstate_hwp_set(policy->cpus);
 
 	return 0;
 }
@@ -1196,7 +1174,9 @@ static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
 
 	pr_debug("intel_pstate: CPU %d exiting\n", cpu_num);
 
-	del_timer_sync(&all_cpu_data[cpu_num]->timer);
+	cpufreq_set_update_util_data(cpu_num, NULL);
+	synchronize_sched();
+
 	if (hwp_active)
 		return;
 
@@ -1260,6 +1240,7 @@ static int intel_pstate_msrs_not_valid(void)
 static void copy_pid_params(struct pstate_adjust_policy *policy)
 {
 	pid_params.sample_rate_ms = policy->sample_rate_ms;
+	pid_params.sample_rate_ns = pid_params.sample_rate_ms * NSEC_PER_MSEC;
 	pid_params.p_gain_pct = policy->p_gain_pct;
 	pid_params.i_gain_pct = policy->i_gain_pct;
 	pid_params.d_gain_pct = policy->d_gain_pct;
@@ -1397,6 +1378,11 @@ static inline bool intel_pstate_platform_pwr_mgmt_exists(void) { return false; }
 static inline bool intel_pstate_has_acpi_ppc(void) { return false; }
 #endif /* CONFIG_ACPI */
 
+static const struct x86_cpu_id hwp_support_ids[] __initconst = {
+	{ X86_VENDOR_INTEL, 6, X86_MODEL_ANY, X86_FEATURE_HWP },
+	{}
+};
+
 static int __init intel_pstate_init(void)
 {
 	int cpu, rc = 0;
@@ -1406,17 +1392,16 @@ static int __init intel_pstate_init(void)
 	if (no_load)
 		return -ENODEV;
 
+	if (x86_match_cpu(hwp_support_ids) && !no_hwp) {
+		copy_cpu_funcs(&core_params.funcs);
+		hwp_active++;
+		goto hwp_cpu_matched;
+	}
+
 	id = x86_match_cpu(intel_pstate_cpu_ids);
 	if (!id)
 		return -ENODEV;
 
-	/*
-	 * The Intel pstate driver will be ignored if the platform
-	 * firmware has its own power management modes.
-	 */
-	if (intel_pstate_platform_pwr_mgmt_exists())
-		return -ENODEV;
-
 	cpu_def = (struct cpu_defaults *)id->driver_data;
 
 	copy_pid_params(&cpu_def->pid_policy);
@@ -1425,17 +1410,20 @@ static int __init intel_pstate_init(void)
 	if (intel_pstate_msrs_not_valid())
 		return -ENODEV;
 
+hwp_cpu_matched:
+	/*
+	 * The Intel pstate driver will be ignored if the platform
+	 * firmware has its own power management modes.
+	 */
+	if (intel_pstate_platform_pwr_mgmt_exists())
+		return -ENODEV;
+
 	pr_info("Intel P-state driver initializing.\n");
 
 	all_cpu_data = vzalloc(sizeof(void *) * num_possible_cpus());
 	if (!all_cpu_data)
 		return -ENOMEM;
 
-	if (static_cpu_has_safe(X86_FEATURE_HWP) && !no_hwp) {
-		pr_info("intel_pstate: HWP enabled\n");
-		hwp_active++;
-	}
-
 	if (!hwp_active && hwp_only)
 		goto out;
 
@@ -1446,12 +1434,16 @@ static int __init intel_pstate_init(void)
 	intel_pstate_debug_expose_params();
 	intel_pstate_sysfs_expose_params();
 
+	if (hwp_active)
+		pr_info("intel_pstate: HWP enabled\n");
+
 	return rc;
 out:
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		if (all_cpu_data[cpu]) {
-			del_timer_sync(&all_cpu_data[cpu]->timer);
+			cpufreq_set_update_util_data(cpu, NULL);
+			synchronize_sched();
 			kfree(all_cpu_data[cpu]);
 		}
 	}
diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c
index 1efba340456d..2058e6d292ce 100644
--- a/drivers/cpufreq/mt8173-cpufreq.c
+++ b/drivers/cpufreq/mt8173-cpufreq.c
@@ -17,6 +17,7 @@
 #include <linux/cpu_cooling.h>
 #include <linux/cpufreq.h>
 #include <linux/cpumask.h>
+#include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pm_opp.h>
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 547890fd9572..50bf12033bbc 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -28,6 +28,8 @@
 #include <linux/of.h>
 #include <linux/reboot.h>
 #include <linux/slab.h>
+#include <linux/cpu.h>
+#include <trace/events/power.h>
 
 #include <asm/cputhreads.h>
 #include <asm/firmware.h>
@@ -42,13 +44,24 @@
 
 static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1];
 static bool rebooting, throttled, occ_reset;
+static unsigned int *core_to_chip_map;
+
+static const char * const throttle_reason[] = {
+	"No throttling",
+	"Power Cap",
+	"Processor Over Temperature",
+	"Power Supply Failure",
+	"Over Current",
+	"OCC Reset"
+};
 
 static struct chip {
 	unsigned int id;
 	bool throttled;
+	bool restore;
+	u8 throttle_reason;
 	cpumask_t mask;
 	struct work_struct throttle;
-	bool restore;
 } *chips;
 
 static int nr_chips;
@@ -312,13 +325,14 @@ static inline unsigned int get_nominal_index(void)
 static void powernv_cpufreq_throttle_check(void *data)
 {
 	unsigned int cpu = smp_processor_id();
+	unsigned int chip_id = core_to_chip_map[cpu_core_index_of_thread(cpu)];
 	unsigned long pmsr;
 	int pmsr_pmax, i;
 
 	pmsr = get_pmspr(SPRN_PMSR);
 
 	for (i = 0; i < nr_chips; i++)
-		if (chips[i].id == cpu_to_chip_id(cpu))
+		if (chips[i].id == chip_id)
 			break;
 
 	/* Check for Pmax Capping */
@@ -328,17 +342,17 @@ static void powernv_cpufreq_throttle_check(void *data)
 			goto next;
 		chips[i].throttled = true;
 		if (pmsr_pmax < powernv_pstate_info.nominal)
-			pr_crit("CPU %d on Chip %u has Pmax reduced below nominal frequency (%d < %d)\n",
-				cpu, chips[i].id, pmsr_pmax,
-				powernv_pstate_info.nominal);
-		else
-			pr_info("CPU %d on Chip %u has Pmax reduced below turbo frequency (%d < %d)\n",
-				cpu, chips[i].id, pmsr_pmax,
-				powernv_pstate_info.max);
+			pr_warn_once("CPU %d on Chip %u has Pmax reduced below nominal frequency (%d < %d)\n",
+				     cpu, chips[i].id, pmsr_pmax,
+				     powernv_pstate_info.nominal);
+		trace_powernv_throttle(chips[i].id,
+				      throttle_reason[chips[i].throttle_reason],
+				      pmsr_pmax);
 	} else if (chips[i].throttled) {
 		chips[i].throttled = false;
-		pr_info("CPU %d on Chip %u has Pmax restored to %d\n", cpu,
-			chips[i].id, pmsr_pmax);
+		trace_powernv_throttle(chips[i].id,
+				      throttle_reason[chips[i].throttle_reason],
+				      pmsr_pmax);
 	}
 
 	/* Check if Psafe_mode_active is set in PMSR. */
@@ -356,7 +370,7 @@ next:
 
 	if (throttled) {
 		pr_info("PMSR = %16lx\n", pmsr);
-		pr_crit("CPU Frequency could be throttled\n");
+		pr_warn("CPU Frequency could be throttled\n");
 	}
 }
 
@@ -423,18 +437,19 @@ void powernv_cpufreq_work_fn(struct work_struct *work)
 {
 	struct chip *chip = container_of(work, struct chip, throttle);
 	unsigned int cpu;
-	cpumask_var_t mask;
+	cpumask_t mask;
 
-	smp_call_function_any(&chip->mask,
+	get_online_cpus();
+	cpumask_and(&mask, &chip->mask, cpu_online_mask);
+	smp_call_function_any(&mask,
 			      powernv_cpufreq_throttle_check, NULL, 0);
 
 	if (!chip->restore)
-		return;
+		goto out;
 
 	chip->restore = false;
-	cpumask_copy(mask, &chip->mask);
-	for_each_cpu_and(cpu, mask, cpu_online_mask) {
-		int index, tcpu;
+	for_each_cpu(cpu, &mask) {
+		int index;
 		struct cpufreq_policy policy;
 
 		cpufreq_get_policy(&policy, cpu);
@@ -442,20 +457,12 @@ void powernv_cpufreq_work_fn(struct work_struct *work)
 					       policy.cur,
 					       CPUFREQ_RELATION_C, &index);
 		powernv_cpufreq_target_index(&policy, index);
-		for_each_cpu(tcpu, policy.cpus)
-			cpumask_clear_cpu(tcpu, mask);
+		cpumask_andnot(&mask, &mask, policy.cpus);
 	}
+out:
+	put_online_cpus();
 }
 
-static char throttle_reason[][30] = {
-					"No throttling",
-					"Power Cap",
-					"Processor Over Temperature",
-					"Power Supply Failure",
-					"Over Current",
-					"OCC Reset"
-				     };
-
 static int powernv_cpufreq_occ_msg(struct notifier_block *nb,
 				   unsigned long msg_type, void *_msg)
 {
@@ -481,7 +488,7 @@ static int powernv_cpufreq_occ_msg(struct notifier_block *nb,
 		 */
 		if (!throttled) {
 			throttled = true;
-			pr_crit("CPU frequency is throttled for duration\n");
+			pr_warn("CPU frequency is throttled for duration\n");
 		}
 
 		break;
@@ -505,23 +512,18 @@ static int powernv_cpufreq_occ_msg(struct notifier_block *nb,
 			return 0;
 		}
 
-		if (omsg.throttle_status &&
+		for (i = 0; i < nr_chips; i++)
+			if (chips[i].id == omsg.chip)
+				break;
+
+		if (omsg.throttle_status >= 0 &&
 		    omsg.throttle_status <= OCC_MAX_THROTTLE_STATUS)
-			pr_info("OCC: Chip %u Pmax reduced due to %s\n",
-				(unsigned int)omsg.chip,
-				throttle_reason[omsg.throttle_status]);
-		else if (!omsg.throttle_status)
-			pr_info("OCC: Chip %u %s\n", (unsigned int)omsg.chip,
-				throttle_reason[omsg.throttle_status]);
-		else
-			return 0;
+			chips[i].throttle_reason = omsg.throttle_status;
 
-		for (i = 0; i < nr_chips; i++)
-			if (chips[i].id == omsg.chip) {
-				if (!omsg.throttle_status)
-					chips[i].restore = true;
-				schedule_work(&chips[i].throttle);
-			}
+		if (!omsg.throttle_status)
+			chips[i].restore = true;
+
+		schedule_work(&chips[i].throttle);
 	}
 	return 0;
 }
@@ -556,29 +558,54 @@ static int init_chip_info(void)
 	unsigned int chip[256];
 	unsigned int cpu, i;
 	unsigned int prev_chip_id = UINT_MAX;
+	cpumask_t cpu_mask;
+	int ret = -ENOMEM;
+
+	core_to_chip_map = kcalloc(cpu_nr_cores(), sizeof(unsigned int),
+				   GFP_KERNEL);
+	if (!core_to_chip_map)
+		goto out;
 
-	for_each_possible_cpu(cpu) {
+	cpumask_copy(&cpu_mask, cpu_possible_mask);
+	for_each_cpu(cpu, &cpu_mask) {
 		unsigned int id = cpu_to_chip_id(cpu);
 
 		if (prev_chip_id != id) {
 			prev_chip_id = id;
 			chip[nr_chips++] = id;
 		}
+		core_to_chip_map[cpu_core_index_of_thread(cpu)] = id;
+		cpumask_andnot(&cpu_mask, &cpu_mask, cpu_sibling_mask(cpu));
 	}
 
-	chips = kmalloc_array(nr_chips, sizeof(struct chip), GFP_KERNEL);
+	chips = kcalloc(nr_chips, sizeof(struct chip), GFP_KERNEL);
 	if (!chips)
-		return -ENOMEM;
+		goto free_chip_map;
 
 	for (i = 0; i < nr_chips; i++) {
 		chips[i].id = chip[i];
-		chips[i].throttled = false;
 		cpumask_copy(&chips[i].mask, cpumask_of_node(chip[i]));
 		INIT_WORK(&chips[i].throttle, powernv_cpufreq_work_fn);
-		chips[i].restore = false;
 	}
 
 	return 0;
+free_chip_map:
+	kfree(core_to_chip_map);
+out:
+	return ret;
+}
+
+static inline void clean_chip_info(void)
+{
+	kfree(chips);
+	kfree(core_to_chip_map);
+}
+
+static inline void unregister_all_notifiers(void)
+{
+	opal_message_notifier_unregister(OPAL_MSG_OCC,
+					 &powernv_cpufreq_opal_nb);
+	unregister_reboot_notifier(&powernv_cpufreq_reboot_nb);
 }
 
 static int __init powernv_cpufreq_init(void)
@@ -591,28 +618,35 @@ static int __init powernv_cpufreq_init(void)
 
 	/* Discover pstates from device tree and init */
 	rc = init_powernv_pstates();
-	if (rc) {
-		pr_info("powernv-cpufreq disabled. System does not support PState control\n");
-		return rc;
-	}
+	if (rc)
+		goto out;
 
 	/* Populate chip info */
 	rc = init_chip_info();
 	if (rc)
-		return rc;
+		goto out;
 
 	register_reboot_notifier(&powernv_cpufreq_reboot_nb);
 	opal_message_notifier_register(OPAL_MSG_OCC, &powernv_cpufreq_opal_nb);
-	return cpufreq_register_driver(&powernv_cpufreq_driver);
+
+	rc = cpufreq_register_driver(&powernv_cpufreq_driver);
+	if (!rc)
+		return 0;
+
+	pr_info("Failed to register the cpufreq driver (%d)\n", rc);
+	unregister_all_notifiers();
+	clean_chip_info();
+out:
+	pr_info("Platform driver disabled. System does not support PState control\n");
+	return rc;
 }
 module_init(powernv_cpufreq_init);
 
 static void __exit powernv_cpufreq_exit(void)
 {
-	unregister_reboot_notifier(&powernv_cpufreq_reboot_nb);
-	opal_message_notifier_unregister(OPAL_MSG_OCC,
-					 &powernv_cpufreq_opal_nb);
 	cpufreq_unregister_driver(&powernv_cpufreq_driver);
+	unregister_all_notifiers();
+	clean_chip_info();
 }
 module_exit(powernv_cpufreq_exit);
 
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 0742b3296673..27fc733cb5b9 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -199,8 +199,8 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev);
 static void get_typical_interval(struct menu_device *data)
 {
 	int i, divisor;
-	unsigned int max, thresh;
-	uint64_t avg, stddev;
+	unsigned int max, thresh, avg;
+	uint64_t sum, variance;
 
 	thresh = UINT_MAX; /* Discard outliers above this value */
 
@@ -208,52 +208,51 @@ again:
 
 	/* First calculate the average of past intervals */
 	max = 0;
-	avg = 0;
+	sum = 0;
 	divisor = 0;
 	for (i = 0; i < INTERVALS; i++) {
 		unsigned int value = data->intervals[i];
 		if (value <= thresh) {
-			avg += value;
+			sum += value;
 			divisor++;
 			if (value > max)
 				max = value;
 		}
 	}
 	if (divisor == INTERVALS)
-		avg >>= INTERVAL_SHIFT;
+		avg = sum >> INTERVAL_SHIFT;
 	else
-		do_div(avg, divisor);
+		avg = div_u64(sum, divisor);
 
-	/* Then try to determine standard deviation */
-	stddev = 0;
+	/* Then try to determine variance */
+	variance = 0;
 	for (i = 0; i < INTERVALS; i++) {
 		unsigned int value = data->intervals[i];
 		if (value <= thresh) {
-			int64_t diff = value - avg;
-			stddev += diff * diff;
+			int64_t diff = (int64_t)value - avg;
+			variance += diff * diff;
 		}
 	}
 	if (divisor == INTERVALS)
-		stddev >>= INTERVAL_SHIFT;
+		variance >>= INTERVAL_SHIFT;
 	else
-		do_div(stddev, divisor);
+		do_div(variance, divisor);
 
 	/*
-	 * The typical interval is obtained when standard deviation is small
-	 * or standard deviation is small compared to the average interval.
-	 *
-	 * int_sqrt() formal parameter type is unsigned long. When the
-	 * greatest difference to an outlier exceeds ~65 ms * sqrt(divisor)
-	 * the resulting squared standard deviation exceeds the input domain
-	 * of int_sqrt on platforms where unsigned long is 32 bits in size.
-	 * In such case reject the candidate average.
+	 * The typical interval is obtained when standard deviation is
+	 * small (stddev <= 20 us, variance <= 400 us^2) or standard
+	 * deviation is small compared to the average interval (avg >
+	 * 6*stddev, avg^2 > 36*variance). The average is smaller than
+	 * UINT_MAX aka U32_MAX, so computing its square does not
+	 * overflow a u64. We simply reject this candidate average if
+	 * the standard deviation is greater than 715 s (which is
+	 * rather unlikely).
 	 *
 	 * Use this result only if there is no timer to wake us up sooner.
 	 */
-	if (likely(stddev <= ULONG_MAX)) {
-		stddev = int_sqrt(stddev);
-		if (((avg > stddev * 6) && (divisor * 4 >= INTERVALS * 3))
-							|| stddev <= 20) {
+	if (likely(variance <= U64_MAX/36)) {
+		if ((((u64)avg*avg > variance*36) && (divisor * 4 >= INTERVALS * 3))
+							|| variance <= 400) {
 			if (data->next_timer_us > avg)
 				data->predicted_us = avg;
 			return;
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 07d494276aad..477fffdb4f49 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -296,6 +296,7 @@ config CRYPTO_DEV_OMAP_AES
 	depends on ARCH_OMAP2 || ARCH_OMAP3 || ARCH_OMAP2PLUS
 	select CRYPTO_AES
 	select CRYPTO_BLKCIPHER
+	select CRYPTO_ENGINE
 	help
 	  OMAP processors have AES module accelerator. Select this if you
 	  want to use the OMAP module for AES algorithms.
@@ -487,7 +488,7 @@ config CRYPTO_DEV_IMGTEC_HASH
 
 config CRYPTO_DEV_SUN4I_SS
 	tristate "Support for Allwinner Security System cryptographic accelerator"
-	depends on ARCH_SUNXI
+	depends on ARCH_SUNXI && !64BIT
 	select CRYPTO_MD5
 	select CRYPTO_SHA1
 	select CRYPTO_AES
@@ -507,6 +508,10 @@ config CRYPTO_DEV_ROCKCHIP
 	depends on OF && ARCH_ROCKCHIP
 	select CRYPTO_AES
 	select CRYPTO_DES
+	select CRYPTO_MD5
+	select CRYPTO_SHA1
+	select CRYPTO_SHA256
+	select CRYPTO_HASH
 	select CRYPTO_BLKCIPHER
 
 	help
diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c
index 3eb3f1279fb7..e3d40a8dfffb 100644
--- a/drivers/crypto/atmel-aes.c
+++ b/drivers/crypto/atmel-aes.c
@@ -369,12 +369,6 @@ static inline size_t atmel_aes_padlen(size_t len, size_t block_size)
 	return len ? block_size - len : 0;
 }
 
-static inline struct aead_request *
-aead_request_cast(struct crypto_async_request *req)
-{
-	return container_of(req, struct aead_request, base);
-}
-
 static struct atmel_aes_dev *atmel_aes_find_dev(struct atmel_aes_base_ctx *ctx)
 {
 	struct atmel_aes_dev *aes_dd = NULL;
@@ -2085,9 +2079,9 @@ static int atmel_aes_probe(struct platform_device *pdev)
 	}
 
 	aes_dd->io_base = devm_ioremap_resource(&pdev->dev, aes_res);
-	if (!aes_dd->io_base) {
+	if (IS_ERR(aes_dd->io_base)) {
 		dev_err(dev, "can't ioremap\n");
-		err = -ENOMEM;
+		err = PTR_ERR(aes_dd->io_base);
 		goto res_err;
 	}
 
diff --git a/drivers/crypto/atmel-sha-regs.h b/drivers/crypto/atmel-sha-regs.h
index 83b2d7425666..e08897109cab 100644
--- a/drivers/crypto/atmel-sha-regs.h
+++ b/drivers/crypto/atmel-sha-regs.h
@@ -8,6 +8,8 @@
 #define SHA_CR_START			(1 << 0)
 #define SHA_CR_FIRST			(1 << 4)
 #define SHA_CR_SWRST			(1 << 8)
+#define SHA_CR_WUIHV			(1 << 12)
+#define SHA_CR_WUIEHV			(1 << 13)
 
 #define SHA_MR				0x04
 #define SHA_MR_MODE_MASK		(0x3 << 0)
@@ -15,6 +17,8 @@
 #define SHA_MR_MODE_AUTO		0x1
 #define SHA_MR_MODE_PDC			0x2
 #define SHA_MR_PROCDLY			(1 << 4)
+#define SHA_MR_UIHV			(1 << 5)
+#define SHA_MR_UIEHV			(1 << 6)
 #define SHA_MR_ALGO_SHA1		(0 << 8)
 #define SHA_MR_ALGO_SHA256		(1 << 8)
 #define SHA_MR_ALGO_SHA384		(2 << 8)
diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c
index 20de861aa0ea..97e34799e077 100644
--- a/drivers/crypto/atmel-sha.c
+++ b/drivers/crypto/atmel-sha.c
@@ -53,6 +53,7 @@
 
 #define SHA_FLAGS_FINUP		BIT(16)
 #define SHA_FLAGS_SG		BIT(17)
+#define SHA_FLAGS_ALGO_MASK	GENMASK(22, 18)
 #define SHA_FLAGS_SHA1		BIT(18)
 #define SHA_FLAGS_SHA224	BIT(19)
 #define SHA_FLAGS_SHA256	BIT(20)
@@ -60,11 +61,12 @@
 #define SHA_FLAGS_SHA512	BIT(22)
 #define SHA_FLAGS_ERROR		BIT(23)
 #define SHA_FLAGS_PAD		BIT(24)
+#define SHA_FLAGS_RESTORE	BIT(25)
 
 #define SHA_OP_UPDATE	1
 #define SHA_OP_FINAL	2
 
-#define SHA_BUFFER_LEN		PAGE_SIZE
+#define SHA_BUFFER_LEN		(PAGE_SIZE / 16)
 
 #define ATMEL_SHA_DMA_THRESHOLD		56
 
@@ -73,10 +75,15 @@ struct atmel_sha_caps {
 	bool	has_dualbuff;
 	bool	has_sha224;
 	bool	has_sha_384_512;
+	bool	has_uihv;
 };
 
 struct atmel_sha_dev;
 
+/*
+ * .statesize = sizeof(struct atmel_sha_reqctx) must be <= PAGE_SIZE / 8 as
+ * tested by the ahash_prepare_alg() function.
+ */
 struct atmel_sha_reqctx {
 	struct atmel_sha_dev	*dd;
 	unsigned long	flags;
@@ -95,7 +102,7 @@ struct atmel_sha_reqctx {
 
 	size_t block_size;
 
-	u8	buffer[0] __aligned(sizeof(u32));
+	u8 buffer[SHA_BUFFER_LEN + SHA512_BLOCK_SIZE] __aligned(sizeof(u32));
 };
 
 struct atmel_sha_ctx {
@@ -122,6 +129,7 @@ struct atmel_sha_dev {
 	spinlock_t		lock;
 	int			err;
 	struct tasklet_struct	done_task;
+	struct tasklet_struct	queue_task;
 
 	unsigned long		flags;
 	struct crypto_queue	queue;
@@ -317,7 +325,8 @@ static int atmel_sha_init(struct ahash_request *req)
 static void atmel_sha_write_ctrl(struct atmel_sha_dev *dd, int dma)
 {
 	struct atmel_sha_reqctx *ctx = ahash_request_ctx(dd->req);
-	u32 valcr = 0, valmr = SHA_MR_MODE_AUTO;
+	u32 valmr = SHA_MR_MODE_AUTO;
+	unsigned int i, hashsize = 0;
 
 	if (likely(dma)) {
 		if (!dd->caps.has_dma)
@@ -329,22 +338,62 @@ static void atmel_sha_write_ctrl(struct atmel_sha_dev *dd, int dma)
 		atmel_sha_write(dd, SHA_IER, SHA_INT_DATARDY);
 	}
 
-	if (ctx->flags & SHA_FLAGS_SHA1)
+	switch (ctx->flags & SHA_FLAGS_ALGO_MASK) {
+	case SHA_FLAGS_SHA1:
 		valmr |= SHA_MR_ALGO_SHA1;
-	else if (ctx->flags & SHA_FLAGS_SHA224)
+		hashsize = SHA1_DIGEST_SIZE;
+		break;
+
+	case SHA_FLAGS_SHA224:
 		valmr |= SHA_MR_ALGO_SHA224;
-	else if (ctx->flags & SHA_FLAGS_SHA256)
+		hashsize = SHA256_DIGEST_SIZE;
+		break;
+
+	case SHA_FLAGS_SHA256:
 		valmr |= SHA_MR_ALGO_SHA256;
-	else if (ctx->flags & SHA_FLAGS_SHA384)
+		hashsize = SHA256_DIGEST_SIZE;
+		break;
+
+	case SHA_FLAGS_SHA384:
 		valmr |= SHA_MR_ALGO_SHA384;
-	else if (ctx->flags & SHA_FLAGS_SHA512)
+		hashsize = SHA512_DIGEST_SIZE;
+		break;
+
+	case SHA_FLAGS_SHA512:
 		valmr |= SHA_MR_ALGO_SHA512;
+		hashsize = SHA512_DIGEST_SIZE;
+		break;
+
+	default:
+		break;
+	}
 
 	/* Setting CR_FIRST only for the first iteration */
-	if (!(ctx->digcnt[0] || ctx->digcnt[1]))
-		valcr = SHA_CR_FIRST;
+	if (!(ctx->digcnt[0] || ctx->digcnt[1])) {
+		atmel_sha_write(dd, SHA_CR, SHA_CR_FIRST);
+	} else if (dd->caps.has_uihv && (ctx->flags & SHA_FLAGS_RESTORE)) {
+		const u32 *hash = (const u32 *)ctx->digest;
+
+		/*
+		 * Restore the hardware context: update the User Initialize
+		 * Hash Value (UIHV) with the value saved when the latest
+		 * 'update' operation completed on this very same crypto
+		 * request.
+		 */
+		ctx->flags &= ~SHA_FLAGS_RESTORE;
+		atmel_sha_write(dd, SHA_CR, SHA_CR_WUIHV);
+		for (i = 0; i < hashsize / sizeof(u32); ++i)
+			atmel_sha_write(dd, SHA_REG_DIN(i), hash[i]);
+		atmel_sha_write(dd, SHA_CR, SHA_CR_FIRST);
+		valmr |= SHA_MR_UIHV;
+	}
+	/*
+	 * WARNING: If the UIHV feature is not available, the hardware CANNOT
+	 * process concurrent requests: the internal registers used to store
+	 * the hash/digest are still set to the partial digest output values
+	 * computed during the latest round.
+	 */
 
-	atmel_sha_write(dd, SHA_CR, valcr);
 	atmel_sha_write(dd, SHA_MR, valmr);
 }
 
@@ -713,23 +762,31 @@ static void atmel_sha_copy_hash(struct ahash_request *req)
 {
 	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
 	u32 *hash = (u32 *)ctx->digest;
-	int i;
+	unsigned int i, hashsize;
 
-	if (ctx->flags & SHA_FLAGS_SHA1)
-		for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(u32); i++)
-			hash[i] = atmel_sha_read(ctx->dd, SHA_REG_DIGEST(i));
-	else if (ctx->flags & SHA_FLAGS_SHA224)
-		for (i = 0; i < SHA224_DIGEST_SIZE / sizeof(u32); i++)
-			hash[i] = atmel_sha_read(ctx->dd, SHA_REG_DIGEST(i));
-	else if (ctx->flags & SHA_FLAGS_SHA256)
-		for (i = 0; i < SHA256_DIGEST_SIZE / sizeof(u32); i++)
-			hash[i] = atmel_sha_read(ctx->dd, SHA_REG_DIGEST(i));
-	else if (ctx->flags & SHA_FLAGS_SHA384)
-		for (i = 0; i < SHA384_DIGEST_SIZE / sizeof(u32); i++)
-			hash[i] = atmel_sha_read(ctx->dd, SHA_REG_DIGEST(i));
-	else
-		for (i = 0; i < SHA512_DIGEST_SIZE / sizeof(u32); i++)
-			hash[i] = atmel_sha_read(ctx->dd, SHA_REG_DIGEST(i));
+	switch (ctx->flags & SHA_FLAGS_ALGO_MASK) {
+	case SHA_FLAGS_SHA1:
+		hashsize = SHA1_DIGEST_SIZE;
+		break;
+
+	case SHA_FLAGS_SHA224:
+	case SHA_FLAGS_SHA256:
+		hashsize = SHA256_DIGEST_SIZE;
+		break;
+
+	case SHA_FLAGS_SHA384:
+	case SHA_FLAGS_SHA512:
+		hashsize = SHA512_DIGEST_SIZE;
+		break;
+
+	default:
+		/* Should not happen... */
+		return;
+	}
+
+	for (i = 0; i < hashsize / sizeof(u32); ++i)
+		hash[i] = atmel_sha_read(ctx->dd, SHA_REG_DIGEST(i));
+	ctx->flags |= SHA_FLAGS_RESTORE;
 }
 
 static void atmel_sha_copy_ready_hash(struct ahash_request *req)
@@ -782,20 +839,20 @@ static void atmel_sha_finish_req(struct ahash_request *req, int err)
 	dd->flags &= ~(SHA_FLAGS_BUSY | SHA_FLAGS_FINAL | SHA_FLAGS_CPU |
 			SHA_FLAGS_DMA_READY | SHA_FLAGS_OUTPUT_READY);
 
-	clk_disable_unprepare(dd->iclk);
+	clk_disable(dd->iclk);
 
 	if (req->base.complete)
 		req->base.complete(&req->base, err);
 
 	/* handle new request */
-	tasklet_schedule(&dd->done_task);
+	tasklet_schedule(&dd->queue_task);
 }
 
 static int atmel_sha_hw_init(struct atmel_sha_dev *dd)
 {
 	int err;
 
-	err = clk_prepare_enable(dd->iclk);
+	err = clk_enable(dd->iclk);
 	if (err)
 		return err;
 
@@ -822,7 +879,7 @@ static void atmel_sha_hw_version_init(struct atmel_sha_dev *dd)
 	dev_info(dd->dev,
 			"version: 0x%x\n", dd->hw_version);
 
-	clk_disable_unprepare(dd->iclk);
+	clk_disable(dd->iclk);
 }
 
 static int atmel_sha_handle_queue(struct atmel_sha_dev *dd,
@@ -922,36 +979,17 @@ static int atmel_sha_update(struct ahash_request *req)
 static int atmel_sha_final(struct ahash_request *req)
 {
 	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
-	struct atmel_sha_ctx *tctx = crypto_tfm_ctx(req->base.tfm);
-	struct atmel_sha_dev *dd = tctx->dd;
-
-	int err = 0;
 
 	ctx->flags |= SHA_FLAGS_FINUP;
 
 	if (ctx->flags & SHA_FLAGS_ERROR)
 		return 0; /* uncompleted hash is not needed */
 
-	if (ctx->bufcnt) {
-		return atmel_sha_enqueue(req, SHA_OP_FINAL);
-	} else if (!(ctx->flags & SHA_FLAGS_PAD)) { /* add padding */
-		err = atmel_sha_hw_init(dd);
-		if (err)
-			goto err1;
-
-		dd->flags |= SHA_FLAGS_BUSY;
-		err = atmel_sha_final_req(dd);
-	} else {
+	if (ctx->flags & SHA_FLAGS_PAD)
 		/* copy ready hash (+ finalize hmac) */
 		return atmel_sha_finish(req);
-	}
 
-err1:
-	if (err != -EINPROGRESS)
-		/* done_task will not finish it, so do it here */
-		atmel_sha_finish_req(req, err);
-
-	return err;
+	return atmel_sha_enqueue(req, SHA_OP_FINAL);
 }
 
 static int atmel_sha_finup(struct ahash_request *req)
@@ -979,11 +1017,27 @@ static int atmel_sha_digest(struct ahash_request *req)
 	return atmel_sha_init(req) ?: atmel_sha_finup(req);
 }
 
+
+static int atmel_sha_export(struct ahash_request *req, void *out)
+{
+	const struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
+
+	memcpy(out, ctx, sizeof(*ctx));
+	return 0;
+}
+
+static int atmel_sha_import(struct ahash_request *req, const void *in)
+{
+	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
+
+	memcpy(ctx, in, sizeof(*ctx));
+	return 0;
+}
+
 static int atmel_sha_cra_init(struct crypto_tfm *tfm)
 {
 	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
-				 sizeof(struct atmel_sha_reqctx) +
-				 SHA_BUFFER_LEN + SHA512_BLOCK_SIZE);
+				 sizeof(struct atmel_sha_reqctx));
 
 	return 0;
 }
@@ -995,8 +1049,11 @@ static struct ahash_alg sha_1_256_algs[] = {
 	.final		= atmel_sha_final,
 	.finup		= atmel_sha_finup,
 	.digest		= atmel_sha_digest,
+	.export		= atmel_sha_export,
+	.import		= atmel_sha_import,
 	.halg = {
 		.digestsize	= SHA1_DIGEST_SIZE,
+		.statesize	= sizeof(struct atmel_sha_reqctx),
 		.base	= {
 			.cra_name		= "sha1",
 			.cra_driver_name	= "atmel-sha1",
@@ -1016,8 +1073,11 @@ static struct ahash_alg sha_1_256_algs[] = {
 	.final		= atmel_sha_final,
 	.finup		= atmel_sha_finup,
 	.digest		= atmel_sha_digest,
+	.export		= atmel_sha_export,
+	.import		= atmel_sha_import,
 	.halg = {
 		.digestsize	= SHA256_DIGEST_SIZE,
+		.statesize	= sizeof(struct atmel_sha_reqctx),
 		.base	= {
 			.cra_name		= "sha256",
 			.cra_driver_name	= "atmel-sha256",
@@ -1039,8 +1099,11 @@ static struct ahash_alg sha_224_alg = {
 	.final		= atmel_sha_final,
 	.finup		= atmel_sha_finup,
 	.digest		= atmel_sha_digest,
+	.export		= atmel_sha_export,
+	.import		= atmel_sha_import,
 	.halg = {
 		.digestsize	= SHA224_DIGEST_SIZE,
+		.statesize	= sizeof(struct atmel_sha_reqctx),
 		.base	= {
 			.cra_name		= "sha224",
 			.cra_driver_name	= "atmel-sha224",
@@ -1062,8 +1125,11 @@ static struct ahash_alg sha_384_512_algs[] = {
 	.final		= atmel_sha_final,
 	.finup		= atmel_sha_finup,
 	.digest		= atmel_sha_digest,
+	.export		= atmel_sha_export,
+	.import		= atmel_sha_import,
 	.halg = {
 		.digestsize	= SHA384_DIGEST_SIZE,
+		.statesize	= sizeof(struct atmel_sha_reqctx),
 		.base	= {
 			.cra_name		= "sha384",
 			.cra_driver_name	= "atmel-sha384",
@@ -1083,8 +1149,11 @@ static struct ahash_alg sha_384_512_algs[] = {
 	.final		= atmel_sha_final,
 	.finup		= atmel_sha_finup,
 	.digest		= atmel_sha_digest,
+	.export		= atmel_sha_export,
+	.import		= atmel_sha_import,
 	.halg = {
 		.digestsize	= SHA512_DIGEST_SIZE,
+		.statesize	= sizeof(struct atmel_sha_reqctx),
 		.base	= {
 			.cra_name		= "sha512",
 			.cra_driver_name	= "atmel-sha512",
@@ -1100,16 +1169,18 @@ static struct ahash_alg sha_384_512_algs[] = {
 },
 };
 
+static void atmel_sha_queue_task(unsigned long data)
+{
+	struct atmel_sha_dev *dd = (struct atmel_sha_dev *)data;
+
+	atmel_sha_handle_queue(dd, NULL);
+}
+
 static void atmel_sha_done_task(unsigned long data)
 {
 	struct atmel_sha_dev *dd = (struct atmel_sha_dev *)data;
 	int err = 0;
 
-	if (!(SHA_FLAGS_BUSY & dd->flags)) {
-		atmel_sha_handle_queue(dd, NULL);
-		return;
-	}
-
 	if (SHA_FLAGS_CPU & dd->flags) {
 		if (SHA_FLAGS_OUTPUT_READY & dd->flags) {
 			dd->flags &= ~SHA_FLAGS_OUTPUT_READY;
@@ -1272,14 +1343,23 @@ static void atmel_sha_get_cap(struct atmel_sha_dev *dd)
 	dd->caps.has_dualbuff = 0;
 	dd->caps.has_sha224 = 0;
 	dd->caps.has_sha_384_512 = 0;
+	dd->caps.has_uihv = 0;
 
 	/* keep only major version number */
 	switch (dd->hw_version & 0xff0) {
+	case 0x510:
+		dd->caps.has_dma = 1;
+		dd->caps.has_dualbuff = 1;
+		dd->caps.has_sha224 = 1;
+		dd->caps.has_sha_384_512 = 1;
+		dd->caps.has_uihv = 1;
+		break;
 	case 0x420:
 		dd->caps.has_dma = 1;
 		dd->caps.has_dualbuff = 1;
 		dd->caps.has_sha224 = 1;
 		dd->caps.has_sha_384_512 = 1;
+		dd->caps.has_uihv = 1;
 		break;
 	case 0x410:
 		dd->caps.has_dma = 1;
@@ -1366,6 +1446,8 @@ static int atmel_sha_probe(struct platform_device *pdev)
 
 	tasklet_init(&sha_dd->done_task, atmel_sha_done_task,
 					(unsigned long)sha_dd);
+	tasklet_init(&sha_dd->queue_task, atmel_sha_queue_task,
+					(unsigned long)sha_dd);
 
 	crypto_init_queue(&sha_dd->queue, ATMEL_SHA_QUEUE_LENGTH);
 
@@ -1404,12 +1486,16 @@ static int atmel_sha_probe(struct platform_device *pdev)
 	}
 
 	sha_dd->io_base = devm_ioremap_resource(&pdev->dev, sha_res);
-	if (!sha_dd->io_base) {
+	if (IS_ERR(sha_dd->io_base)) {
 		dev_err(dev, "can't ioremap\n");
-		err = -ENOMEM;
+		err = PTR_ERR(sha_dd->io_base);
 		goto res_err;
 	}
 
+	err = clk_prepare(sha_dd->iclk);
+	if (err)
+		goto res_err;
+
 	atmel_sha_hw_version_init(sha_dd);
 
 	atmel_sha_get_cap(sha_dd);
@@ -1421,12 +1507,12 @@ static int atmel_sha_probe(struct platform_device *pdev)
 			if (IS_ERR(pdata)) {
 				dev_err(&pdev->dev, "platform data not available\n");
 				err = PTR_ERR(pdata);
-				goto res_err;
+				goto iclk_unprepare;
 			}
 		}
 		if (!pdata->dma_slave) {
 			err = -ENXIO;
-			goto res_err;
+			goto iclk_unprepare;
 		}
 		err = atmel_sha_dma_init(sha_dd, pdata);
 		if (err)
@@ -1457,7 +1543,10 @@ err_algs:
 	if (sha_dd->caps.has_dma)
 		atmel_sha_dma_cleanup(sha_dd);
 err_sha_dma:
+iclk_unprepare:
+	clk_unprepare(sha_dd->iclk);
 res_err:
+	tasklet_kill(&sha_dd->queue_task);
 	tasklet_kill(&sha_dd->done_task);
 sha_dd_err:
 	dev_err(dev, "initialization failed.\n");
@@ -1478,17 +1567,13 @@ static int atmel_sha_remove(struct platform_device *pdev)
 
 	atmel_sha_unregister_algs(sha_dd);
 
+	tasklet_kill(&sha_dd->queue_task);
 	tasklet_kill(&sha_dd->done_task);
 
 	if (sha_dd->caps.has_dma)
 		atmel_sha_dma_cleanup(sha_dd);
 
-	iounmap(sha_dd->io_base);
-
-	clk_put(sha_dd->iclk);
-
-	if (sha_dd->irq >= 0)
-		free_irq(sha_dd->irq, sha_dd);
+	clk_unprepare(sha_dd->iclk);
 
 	return 0;
 }
diff --git a/drivers/crypto/atmel-tdes.c b/drivers/crypto/atmel-tdes.c
index 2c7a628d0375..bf467d7be35c 100644
--- a/drivers/crypto/atmel-tdes.c
+++ b/drivers/crypto/atmel-tdes.c
@@ -1417,9 +1417,9 @@ static int atmel_tdes_probe(struct platform_device *pdev)
 	}
 
 	tdes_dd->io_base = devm_ioremap_resource(&pdev->dev, tdes_res);
-	if (!tdes_dd->io_base) {
+	if (IS_ERR(tdes_dd->io_base)) {
 		dev_err(dev, "can't ioremap\n");
-		err = -ENOMEM;
+		err = PTR_ERR(tdes_dd->io_base);
 		goto res_err;
 	}
 
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index 69d4a1326fee..44d30b45f3cc 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -534,7 +534,7 @@ static int caam_probe(struct platform_device *pdev)
 	 * long pointers in master configuration register
 	 */
 	clrsetbits_32(&ctrl->mcr, MCFGR_AWCACHE_MASK, MCFGR_AWCACHE_CACH |
-		      MCFGR_AWCACHE_BUFF | MCFGR_WDENABLE |
+		      MCFGR_AWCACHE_BUFF | MCFGR_WDENABLE | MCFGR_LARGE_BURST |
 		      (sizeof(dma_addr_t) == sizeof(u64) ? MCFGR_LONG_PTR : 0));
 
 	/*
diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c
index f7e0d8d4c3da..6fd63a600614 100644
--- a/drivers/crypto/caam/jr.c
+++ b/drivers/crypto/caam/jr.c
@@ -65,7 +65,7 @@ static int caam_reset_hw_jr(struct device *dev)
 /*
  * Shutdown JobR independent of platform property code
  */
-int caam_jr_shutdown(struct device *dev)
+static int caam_jr_shutdown(struct device *dev)
 {
 	struct caam_drv_private_jr *jrp = dev_get_drvdata(dev);
 	dma_addr_t inpbusaddr, outbusaddr;
diff --git a/drivers/crypto/caam/regs.h b/drivers/crypto/caam/regs.h
index a8a79975682f..0ba9c40597dc 100644
--- a/drivers/crypto/caam/regs.h
+++ b/drivers/crypto/caam/regs.h
@@ -455,7 +455,8 @@ struct caam_ctrl {
 #define MCFGR_AXIPIPE_MASK	(0xf << MCFGR_AXIPIPE_SHIFT)
 
 #define MCFGR_AXIPRI		0x00000008 /* Assert AXI priority sideband */
-#define MCFGR_BURST_64		0x00000001 /* Max burst size */
+#define MCFGR_LARGE_BURST	0x00000004 /* 128/256-byte burst size */
+#define MCFGR_BURST_64		0x00000001 /* 64-byte burst size */
 
 /* JRSTART register offsets */
 #define JRSTART_JR0_START       0x00000001 /* Start Job ring 0 */
diff --git a/drivers/crypto/ccp/Makefile b/drivers/crypto/ccp/Makefile
index 55a1f3951578..b750592cc936 100644
--- a/drivers/crypto/ccp/Makefile
+++ b/drivers/crypto/ccp/Makefile
@@ -1,5 +1,5 @@
 obj-$(CONFIG_CRYPTO_DEV_CCP_DD) += ccp.o
-ccp-objs := ccp-dev.o ccp-ops.o ccp-platform.o
+ccp-objs := ccp-dev.o ccp-ops.o ccp-dev-v3.o ccp-platform.o
 ccp-$(CONFIG_PCI) += ccp-pci.o
 
 obj-$(CONFIG_CRYPTO_DEV_CCP_CRYPTO) += ccp-crypto.o
diff --git a/drivers/crypto/ccp/ccp-crypto-aes-cmac.c b/drivers/crypto/ccp/ccp-crypto-aes-cmac.c
index d89f20c04266..3d9acc53d247 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes-cmac.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes-cmac.c
@@ -220,6 +220,39 @@ static int ccp_aes_cmac_digest(struct ahash_request *req)
 	return ccp_aes_cmac_finup(req);
 }
 
+static int ccp_aes_cmac_export(struct ahash_request *req, void *out)
+{
+	struct ccp_aes_cmac_req_ctx *rctx = ahash_request_ctx(req);
+	struct ccp_aes_cmac_exp_ctx state;
+
+	state.null_msg = rctx->null_msg;
+	memcpy(state.iv, rctx->iv, sizeof(state.iv));
+	state.buf_count = rctx->buf_count;
+	memcpy(state.buf, rctx->buf, sizeof(state.buf));
+
+	/* 'out' may not be aligned so memcpy from local variable */
+	memcpy(out, &state, sizeof(state));
+
+	return 0;
+}
+
+static int ccp_aes_cmac_import(struct ahash_request *req, const void *in)
+{
+	struct ccp_aes_cmac_req_ctx *rctx = ahash_request_ctx(req);
+	struct ccp_aes_cmac_exp_ctx state;
+
+	/* 'in' may not be aligned so memcpy to local variable */
+	memcpy(&state, in, sizeof(state));
+
+	memset(rctx, 0, sizeof(*rctx));
+	rctx->null_msg = state.null_msg;
+	memcpy(rctx->iv, state.iv, sizeof(rctx->iv));
+	rctx->buf_count = state.buf_count;
+	memcpy(rctx->buf, state.buf, sizeof(rctx->buf));
+
+	return 0;
+}
+
 static int ccp_aes_cmac_setkey(struct crypto_ahash *tfm, const u8 *key,
 			       unsigned int key_len)
 {
@@ -352,10 +385,13 @@ int ccp_register_aes_cmac_algs(struct list_head *head)
 	alg->final = ccp_aes_cmac_final;
 	alg->finup = ccp_aes_cmac_finup;
 	alg->digest = ccp_aes_cmac_digest;
+	alg->export = ccp_aes_cmac_export;
+	alg->import = ccp_aes_cmac_import;
 	alg->setkey = ccp_aes_cmac_setkey;
 
 	halg = &alg->halg;
 	halg->digestsize = AES_BLOCK_SIZE;
+	halg->statesize = sizeof(struct ccp_aes_cmac_exp_ctx);
 
 	base = &halg->base;
 	snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "cmac(aes)");
diff --git a/drivers/crypto/ccp/ccp-crypto-aes.c b/drivers/crypto/ccp/ccp-crypto-aes.c
index 7984f910884d..89291c15015c 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes.c
@@ -1,7 +1,7 @@
 /*
  * AMD Cryptographic Coprocessor (CCP) AES crypto API support
  *
- * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ * Copyright (C) 2013,2016 Advanced Micro Devices, Inc.
  *
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  *
@@ -259,6 +259,7 @@ static struct crypto_alg ccp_aes_rfc3686_defaults = {
 
 struct ccp_aes_def {
 	enum ccp_aes_mode mode;
+	unsigned int version;
 	const char *name;
 	const char *driver_name;
 	unsigned int blocksize;
@@ -269,6 +270,7 @@ struct ccp_aes_def {
 static struct ccp_aes_def aes_algs[] = {
 	{
 		.mode		= CCP_AES_MODE_ECB,
+		.version	= CCP_VERSION(3, 0),
 		.name		= "ecb(aes)",
 		.driver_name	= "ecb-aes-ccp",
 		.blocksize	= AES_BLOCK_SIZE,
@@ -277,6 +279,7 @@ static struct ccp_aes_def aes_algs[] = {
 	},
 	{
 		.mode		= CCP_AES_MODE_CBC,
+		.version	= CCP_VERSION(3, 0),
 		.name		= "cbc(aes)",
 		.driver_name	= "cbc-aes-ccp",
 		.blocksize	= AES_BLOCK_SIZE,
@@ -285,6 +288,7 @@ static struct ccp_aes_def aes_algs[] = {
 	},
 	{
 		.mode		= CCP_AES_MODE_CFB,
+		.version	= CCP_VERSION(3, 0),
 		.name		= "cfb(aes)",
 		.driver_name	= "cfb-aes-ccp",
 		.blocksize	= AES_BLOCK_SIZE,
@@ -293,6 +297,7 @@ static struct ccp_aes_def aes_algs[] = {
 	},
 	{
 		.mode		= CCP_AES_MODE_OFB,
+		.version	= CCP_VERSION(3, 0),
 		.name		= "ofb(aes)",
 		.driver_name	= "ofb-aes-ccp",
 		.blocksize	= 1,
@@ -301,6 +306,7 @@ static struct ccp_aes_def aes_algs[] = {
 	},
 	{
 		.mode		= CCP_AES_MODE_CTR,
+		.version	= CCP_VERSION(3, 0),
 		.name		= "ctr(aes)",
 		.driver_name	= "ctr-aes-ccp",
 		.blocksize	= 1,
@@ -309,6 +315,7 @@ static struct ccp_aes_def aes_algs[] = {
 	},
 	{
 		.mode		= CCP_AES_MODE_CTR,
+		.version	= CCP_VERSION(3, 0),
 		.name		= "rfc3686(ctr(aes))",
 		.driver_name	= "rfc3686-ctr-aes-ccp",
 		.blocksize	= 1,
@@ -357,8 +364,11 @@ static int ccp_register_aes_alg(struct list_head *head,
 int ccp_register_aes_algs(struct list_head *head)
 {
 	int i, ret;
+	unsigned int ccpversion = ccp_version();
 
 	for (i = 0; i < ARRAY_SIZE(aes_algs); i++) {
+		if (aes_algs[i].version > ccpversion)
+			continue;
 		ret = ccp_register_aes_alg(head, &aes_algs[i]);
 		if (ret)
 			return ret;
diff --git a/drivers/crypto/ccp/ccp-crypto-sha.c b/drivers/crypto/ccp/ccp-crypto-sha.c
index d14b3f28e010..b5ad72897dc2 100644
--- a/drivers/crypto/ccp/ccp-crypto-sha.c
+++ b/drivers/crypto/ccp/ccp-crypto-sha.c
@@ -1,7 +1,7 @@
 /*
  * AMD Cryptographic Coprocessor (CCP) SHA crypto API support
  *
- * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ * Copyright (C) 2013,2016 Advanced Micro Devices, Inc.
  *
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  *
@@ -207,6 +207,43 @@ static int ccp_sha_digest(struct ahash_request *req)
 	return ccp_sha_finup(req);
 }
 
+static int ccp_sha_export(struct ahash_request *req, void *out)
+{
+	struct ccp_sha_req_ctx *rctx = ahash_request_ctx(req);
+	struct ccp_sha_exp_ctx state;
+
+	state.type = rctx->type;
+	state.msg_bits = rctx->msg_bits;
+	state.first = rctx->first;
+	memcpy(state.ctx, rctx->ctx, sizeof(state.ctx));
+	state.buf_count = rctx->buf_count;
+	memcpy(state.buf, rctx->buf, sizeof(state.buf));
+
+	/* 'out' may not be aligned so memcpy from local variable */
+	memcpy(out, &state, sizeof(state));
+
+	return 0;
+}
+
+static int ccp_sha_import(struct ahash_request *req, const void *in)
+{
+	struct ccp_sha_req_ctx *rctx = ahash_request_ctx(req);
+	struct ccp_sha_exp_ctx state;
+
+	/* 'in' may not be aligned so memcpy to local variable */
+	memcpy(&state, in, sizeof(state));
+
+	memset(rctx, 0, sizeof(*rctx));
+	rctx->type = state.type;
+	rctx->msg_bits = state.msg_bits;
+	rctx->first = state.first;
+	memcpy(rctx->ctx, state.ctx, sizeof(rctx->ctx));
+	rctx->buf_count = state.buf_count;
+	memcpy(rctx->buf, state.buf, sizeof(rctx->buf));
+
+	return 0;
+}
+
 static int ccp_sha_setkey(struct crypto_ahash *tfm, const u8 *key,
 			  unsigned int key_len)
 {
@@ -304,6 +341,7 @@ static void ccp_hmac_sha_cra_exit(struct crypto_tfm *tfm)
 }
 
 struct ccp_sha_def {
+	unsigned int version;
 	const char *name;
 	const char *drv_name;
 	enum ccp_sha_type type;
@@ -313,6 +351,7 @@ struct ccp_sha_def {
 
 static struct ccp_sha_def sha_algs[] = {
 	{
+		.version	= CCP_VERSION(3, 0),
 		.name		= "sha1",
 		.drv_name	= "sha1-ccp",
 		.type		= CCP_SHA_TYPE_1,
@@ -320,6 +359,7 @@ static struct ccp_sha_def sha_algs[] = {
 		.block_size	= SHA1_BLOCK_SIZE,
 	},
 	{
+		.version	= CCP_VERSION(3, 0),
 		.name		= "sha224",
 		.drv_name	= "sha224-ccp",
 		.type		= CCP_SHA_TYPE_224,
@@ -327,6 +367,7 @@ static struct ccp_sha_def sha_algs[] = {
 		.block_size	= SHA224_BLOCK_SIZE,
 	},
 	{
+		.version	= CCP_VERSION(3, 0),
 		.name		= "sha256",
 		.drv_name	= "sha256-ccp",
 		.type		= CCP_SHA_TYPE_256,
@@ -403,9 +444,12 @@ static int ccp_register_sha_alg(struct list_head *head,
 	alg->final = ccp_sha_final;
 	alg->finup = ccp_sha_finup;
 	alg->digest = ccp_sha_digest;
+	alg->export = ccp_sha_export;
+	alg->import = ccp_sha_import;
 
 	halg = &alg->halg;
 	halg->digestsize = def->digest_size;
+	halg->statesize = sizeof(struct ccp_sha_exp_ctx);
 
 	base = &halg->base;
 	snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "%s", def->name);
@@ -440,8 +484,11 @@ static int ccp_register_sha_alg(struct list_head *head,
 int ccp_register_sha_algs(struct list_head *head)
 {
 	int i, ret;
+	unsigned int ccpversion = ccp_version();
 
 	for (i = 0; i < ARRAY_SIZE(sha_algs); i++) {
+		if (sha_algs[i].version > ccpversion)
+			continue;
 		ret = ccp_register_sha_alg(head, &sha_algs[i]);
 		if (ret)
 			return ret;
diff --git a/drivers/crypto/ccp/ccp-crypto.h b/drivers/crypto/ccp/ccp-crypto.h
index 76a96f0f44c6..a326ec20bfa8 100644
--- a/drivers/crypto/ccp/ccp-crypto.h
+++ b/drivers/crypto/ccp/ccp-crypto.h
@@ -129,6 +129,15 @@ struct ccp_aes_cmac_req_ctx {
 	struct ccp_cmd cmd;
 };
 
+struct ccp_aes_cmac_exp_ctx {
+	unsigned int null_msg;
+
+	u8 iv[AES_BLOCK_SIZE];
+
+	unsigned int buf_count;
+	u8 buf[AES_BLOCK_SIZE];
+};
+
 /***** SHA related defines *****/
 #define MAX_SHA_CONTEXT_SIZE	SHA256_DIGEST_SIZE
 #define MAX_SHA_BLOCK_SIZE	SHA256_BLOCK_SIZE
@@ -171,6 +180,19 @@ struct ccp_sha_req_ctx {
 	struct ccp_cmd cmd;
 };
 
+struct ccp_sha_exp_ctx {
+	enum ccp_sha_type type;
+
+	u64 msg_bits;
+
+	unsigned int first;
+
+	u8 ctx[MAX_SHA_CONTEXT_SIZE];
+
+	unsigned int buf_count;
+	u8 buf[MAX_SHA_BLOCK_SIZE];
+};
+
 /***** Common Context Structure *****/
 struct ccp_ctx {
 	int (*complete)(struct crypto_async_request *req, int ret);
diff --git a/drivers/crypto/ccp/ccp-dev-v3.c b/drivers/crypto/ccp/ccp-dev-v3.c
new file mode 100644
index 000000000000..7d5eab49179e
--- /dev/null
+++ b/drivers/crypto/ccp/ccp-dev-v3.c
@@ -0,0 +1,533 @@
+/*
+ * AMD Cryptographic Coprocessor (CCP) driver
+ *
+ * Copyright (C) 2013,2016 Advanced Micro Devices, Inc.
+ *
+ * Author: Tom Lendacky <thomas.lendacky@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/kthread.h>
+#include <linux/interrupt.h>
+#include <linux/ccp.h>
+
+#include "ccp-dev.h"
+
+static int ccp_do_cmd(struct ccp_op *op, u32 *cr, unsigned int cr_count)
+{
+	struct ccp_cmd_queue *cmd_q = op->cmd_q;
+	struct ccp_device *ccp = cmd_q->ccp;
+	void __iomem *cr_addr;
+	u32 cr0, cmd;
+	unsigned int i;
+	int ret = 0;
+
+	/* We could read a status register to see how many free slots
+	 * are actually available, but reading that register resets it
+	 * and you could lose some error information.
+	 */
+	cmd_q->free_slots--;
+
+	cr0 = (cmd_q->id << REQ0_CMD_Q_SHIFT)
+	      | (op->jobid << REQ0_JOBID_SHIFT)
+	      | REQ0_WAIT_FOR_WRITE;
+
+	if (op->soc)
+		cr0 |= REQ0_STOP_ON_COMPLETE
+		       | REQ0_INT_ON_COMPLETE;
+
+	if (op->ioc || !cmd_q->free_slots)
+		cr0 |= REQ0_INT_ON_COMPLETE;
+
+	/* Start at CMD_REQ1 */
+	cr_addr = ccp->io_regs + CMD_REQ0 + CMD_REQ_INCR;
+
+	mutex_lock(&ccp->req_mutex);
+
+	/* Write CMD_REQ1 through CMD_REQx first */
+	for (i = 0; i < cr_count; i++, cr_addr += CMD_REQ_INCR)
+		iowrite32(*(cr + i), cr_addr);
+
+	/* Tell the CCP to start */
+	wmb();
+	iowrite32(cr0, ccp->io_regs + CMD_REQ0);
+
+	mutex_unlock(&ccp->req_mutex);
+
+	if (cr0 & REQ0_INT_ON_COMPLETE) {
+		/* Wait for the job to complete */
+		ret = wait_event_interruptible(cmd_q->int_queue,
+					       cmd_q->int_rcvd);
+		if (ret || cmd_q->cmd_error) {
+			/* On error delete all related jobs from the queue */
+			cmd = (cmd_q->id << DEL_Q_ID_SHIFT)
+			      | op->jobid;
+
+			iowrite32(cmd, ccp->io_regs + DEL_CMD_Q_JOB);
+
+			if (!ret)
+				ret = -EIO;
+		} else if (op->soc) {
+			/* Delete just head job from the queue on SoC */
+			cmd = DEL_Q_ACTIVE
+			      | (cmd_q->id << DEL_Q_ID_SHIFT)
+			      | op->jobid;
+
+			iowrite32(cmd, ccp->io_regs + DEL_CMD_Q_JOB);
+		}
+
+		cmd_q->free_slots = CMD_Q_DEPTH(cmd_q->q_status);
+
+		cmd_q->int_rcvd = 0;
+	}
+
+	return ret;
+}
+
+static int ccp_perform_aes(struct ccp_op *op)
+{
+	u32 cr[6];
+
+	/* Fill out the register contents for REQ1 through REQ6 */
+	cr[0] = (CCP_ENGINE_AES << REQ1_ENGINE_SHIFT)
+		| (op->u.aes.type << REQ1_AES_TYPE_SHIFT)
+		| (op->u.aes.mode << REQ1_AES_MODE_SHIFT)
+		| (op->u.aes.action << REQ1_AES_ACTION_SHIFT)
+		| (op->ksb_key << REQ1_KEY_KSB_SHIFT);
+	cr[1] = op->src.u.dma.length - 1;
+	cr[2] = ccp_addr_lo(&op->src.u.dma);
+	cr[3] = (op->ksb_ctx << REQ4_KSB_SHIFT)
+		| (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
+		| ccp_addr_hi(&op->src.u.dma);
+	cr[4] = ccp_addr_lo(&op->dst.u.dma);
+	cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
+		| ccp_addr_hi(&op->dst.u.dma);
+
+	if (op->u.aes.mode == CCP_AES_MODE_CFB)
+		cr[0] |= ((0x7f) << REQ1_AES_CFB_SIZE_SHIFT);
+
+	if (op->eom)
+		cr[0] |= REQ1_EOM;
+
+	if (op->init)
+		cr[0] |= REQ1_INIT;
+
+	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
+}
+
+static int ccp_perform_xts_aes(struct ccp_op *op)
+{
+	u32 cr[6];
+
+	/* Fill out the register contents for REQ1 through REQ6 */
+	cr[0] = (CCP_ENGINE_XTS_AES_128 << REQ1_ENGINE_SHIFT)
+		| (op->u.xts.action << REQ1_AES_ACTION_SHIFT)
+		| (op->u.xts.unit_size << REQ1_XTS_AES_SIZE_SHIFT)
+		| (op->ksb_key << REQ1_KEY_KSB_SHIFT);
+	cr[1] = op->src.u.dma.length - 1;
+	cr[2] = ccp_addr_lo(&op->src.u.dma);
+	cr[3] = (op->ksb_ctx << REQ4_KSB_SHIFT)
+		| (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
+		| ccp_addr_hi(&op->src.u.dma);
+	cr[4] = ccp_addr_lo(&op->dst.u.dma);
+	cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
+		| ccp_addr_hi(&op->dst.u.dma);
+
+	if (op->eom)
+		cr[0] |= REQ1_EOM;
+
+	if (op->init)
+		cr[0] |= REQ1_INIT;
+
+	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
+}
+
+static int ccp_perform_sha(struct ccp_op *op)
+{
+	u32 cr[6];
+
+	/* Fill out the register contents for REQ1 through REQ6 */
+	cr[0] = (CCP_ENGINE_SHA << REQ1_ENGINE_SHIFT)
+		| (op->u.sha.type << REQ1_SHA_TYPE_SHIFT)
+		| REQ1_INIT;
+	cr[1] = op->src.u.dma.length - 1;
+	cr[2] = ccp_addr_lo(&op->src.u.dma);
+	cr[3] = (op->ksb_ctx << REQ4_KSB_SHIFT)
+		| (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
+		| ccp_addr_hi(&op->src.u.dma);
+
+	if (op->eom) {
+		cr[0] |= REQ1_EOM;
+		cr[4] = lower_32_bits(op->u.sha.msg_bits);
+		cr[5] = upper_32_bits(op->u.sha.msg_bits);
+	} else {
+		cr[4] = 0;
+		cr[5] = 0;
+	}
+
+	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
+}
+
+static int ccp_perform_rsa(struct ccp_op *op)
+{
+	u32 cr[6];
+
+	/* Fill out the register contents for REQ1 through REQ6 */
+	cr[0] = (CCP_ENGINE_RSA << REQ1_ENGINE_SHIFT)
+		| (op->u.rsa.mod_size << REQ1_RSA_MOD_SIZE_SHIFT)
+		| (op->ksb_key << REQ1_KEY_KSB_SHIFT)
+		| REQ1_EOM;
+	cr[1] = op->u.rsa.input_len - 1;
+	cr[2] = ccp_addr_lo(&op->src.u.dma);
+	cr[3] = (op->ksb_ctx << REQ4_KSB_SHIFT)
+		| (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
+		| ccp_addr_hi(&op->src.u.dma);
+	cr[4] = ccp_addr_lo(&op->dst.u.dma);
+	cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
+		| ccp_addr_hi(&op->dst.u.dma);
+
+	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
+}
+
+static int ccp_perform_passthru(struct ccp_op *op)
+{
+	u32 cr[6];
+
+	/* Fill out the register contents for REQ1 through REQ6 */
+	cr[0] = (CCP_ENGINE_PASSTHRU << REQ1_ENGINE_SHIFT)
+		| (op->u.passthru.bit_mod << REQ1_PT_BW_SHIFT)
+		| (op->u.passthru.byte_swap << REQ1_PT_BS_SHIFT);
+
+	if (op->src.type == CCP_MEMTYPE_SYSTEM)
+		cr[1] = op->src.u.dma.length - 1;
+	else
+		cr[1] = op->dst.u.dma.length - 1;
+
+	if (op->src.type == CCP_MEMTYPE_SYSTEM) {
+		cr[2] = ccp_addr_lo(&op->src.u.dma);
+		cr[3] = (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
+			| ccp_addr_hi(&op->src.u.dma);
+
+		if (op->u.passthru.bit_mod != CCP_PASSTHRU_BITWISE_NOOP)
+			cr[3] |= (op->ksb_key << REQ4_KSB_SHIFT);
+	} else {
+		cr[2] = op->src.u.ksb * CCP_KSB_BYTES;
+		cr[3] = (CCP_MEMTYPE_KSB << REQ4_MEMTYPE_SHIFT);
+	}
+
+	if (op->dst.type == CCP_MEMTYPE_SYSTEM) {
+		cr[4] = ccp_addr_lo(&op->dst.u.dma);
+		cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
+			| ccp_addr_hi(&op->dst.u.dma);
+	} else {
+		cr[4] = op->dst.u.ksb * CCP_KSB_BYTES;
+		cr[5] = (CCP_MEMTYPE_KSB << REQ6_MEMTYPE_SHIFT);
+	}
+
+	if (op->eom)
+		cr[0] |= REQ1_EOM;
+
+	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
+}
+
+static int ccp_perform_ecc(struct ccp_op *op)
+{
+	u32 cr[6];
+
+	/* Fill out the register contents for REQ1 through REQ6 */
+	cr[0] = REQ1_ECC_AFFINE_CONVERT
+		| (CCP_ENGINE_ECC << REQ1_ENGINE_SHIFT)
+		| (op->u.ecc.function << REQ1_ECC_FUNCTION_SHIFT)
+		| REQ1_EOM;
+	cr[1] = op->src.u.dma.length - 1;
+	cr[2] = ccp_addr_lo(&op->src.u.dma);
+	cr[3] = (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
+		| ccp_addr_hi(&op->src.u.dma);
+	cr[4] = ccp_addr_lo(&op->dst.u.dma);
+	cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
+		| ccp_addr_hi(&op->dst.u.dma);
+
+	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
+}
+
+static int ccp_trng_read(struct hwrng *rng, void *data, size_t max, bool wait)
+{
+	struct ccp_device *ccp = container_of(rng, struct ccp_device, hwrng);
+	u32 trng_value;
+	int len = min_t(int, sizeof(trng_value), max);
+
+	/*
+	 * Locking is provided by the caller so we can update device
+	 * hwrng-related fields safely
+	 */
+	trng_value = ioread32(ccp->io_regs + TRNG_OUT_REG);
+	if (!trng_value) {
+		/* Zero is returned if not data is available or if a
+		 * bad-entropy error is present. Assume an error if
+		 * we exceed TRNG_RETRIES reads of zero.
+		 */
+		if (ccp->hwrng_retries++ > TRNG_RETRIES)
+			return -EIO;
+
+		return 0;
+	}
+
+	/* Reset the counter and save the rng value */
+	ccp->hwrng_retries = 0;
+	memcpy(data, &trng_value, len);
+
+	return len;
+}
+
+static int ccp_init(struct ccp_device *ccp)
+{
+	struct device *dev = ccp->dev;
+	struct ccp_cmd_queue *cmd_q;
+	struct dma_pool *dma_pool;
+	char dma_pool_name[MAX_DMAPOOL_NAME_LEN];
+	unsigned int qmr, qim, i;
+	int ret;
+
+	/* Find available queues */
+	qim = 0;
+	qmr = ioread32(ccp->io_regs + Q_MASK_REG);
+	for (i = 0; i < MAX_HW_QUEUES; i++) {
+		if (!(qmr & (1 << i)))
+			continue;
+
+		/* Allocate a dma pool for this queue */
+		snprintf(dma_pool_name, sizeof(dma_pool_name), "%s_q%d",
+			 ccp->name, i);
+		dma_pool = dma_pool_create(dma_pool_name, dev,
+					   CCP_DMAPOOL_MAX_SIZE,
+					   CCP_DMAPOOL_ALIGN, 0);
+		if (!dma_pool) {
+			dev_err(dev, "unable to allocate dma pool\n");
+			ret = -ENOMEM;
+			goto e_pool;
+		}
+
+		cmd_q = &ccp->cmd_q[ccp->cmd_q_count];
+		ccp->cmd_q_count++;
+
+		cmd_q->ccp = ccp;
+		cmd_q->id = i;
+		cmd_q->dma_pool = dma_pool;
+
+		/* Reserve 2 KSB regions for the queue */
+		cmd_q->ksb_key = KSB_START + ccp->ksb_start++;
+		cmd_q->ksb_ctx = KSB_START + ccp->ksb_start++;
+		ccp->ksb_count -= 2;
+
+		/* Preset some register values and masks that are queue
+		 * number dependent
+		 */
+		cmd_q->reg_status = ccp->io_regs + CMD_Q_STATUS_BASE +
+				    (CMD_Q_STATUS_INCR * i);
+		cmd_q->reg_int_status = ccp->io_regs + CMD_Q_INT_STATUS_BASE +
+					(CMD_Q_STATUS_INCR * i);
+		cmd_q->int_ok = 1 << (i * 2);
+		cmd_q->int_err = 1 << ((i * 2) + 1);
+
+		cmd_q->free_slots = CMD_Q_DEPTH(ioread32(cmd_q->reg_status));
+
+		init_waitqueue_head(&cmd_q->int_queue);
+
+		/* Build queue interrupt mask (two interrupts per queue) */
+		qim |= cmd_q->int_ok | cmd_q->int_err;
+
+#ifdef CONFIG_ARM64
+		/* For arm64 set the recommended queue cache settings */
+		iowrite32(ccp->axcache, ccp->io_regs + CMD_Q_CACHE_BASE +
+			  (CMD_Q_CACHE_INC * i));
+#endif
+
+		dev_dbg(dev, "queue #%u available\n", i);
+	}
+	if (ccp->cmd_q_count == 0) {
+		dev_notice(dev, "no command queues available\n");
+		ret = -EIO;
+		goto e_pool;
+	}
+	dev_notice(dev, "%u command queues available\n", ccp->cmd_q_count);
+
+	/* Disable and clear interrupts until ready */
+	iowrite32(0x00, ccp->io_regs + IRQ_MASK_REG);
+	for (i = 0; i < ccp->cmd_q_count; i++) {
+		cmd_q = &ccp->cmd_q[i];
+
+		ioread32(cmd_q->reg_int_status);
+		ioread32(cmd_q->reg_status);
+	}
+	iowrite32(qim, ccp->io_regs + IRQ_STATUS_REG);
+
+	/* Request an irq */
+	ret = ccp->get_irq(ccp);
+	if (ret) {
+		dev_err(dev, "unable to allocate an IRQ\n");
+		goto e_pool;
+	}
+
+	/* Initialize the queues used to wait for KSB space and suspend */
+	init_waitqueue_head(&ccp->ksb_queue);
+	init_waitqueue_head(&ccp->suspend_queue);
+
+	/* Create a kthread for each queue */
+	for (i = 0; i < ccp->cmd_q_count; i++) {
+		struct task_struct *kthread;
+
+		cmd_q = &ccp->cmd_q[i];
+
+		kthread = kthread_create(ccp_cmd_queue_thread, cmd_q,
+					 "%s-q%u", ccp->name, cmd_q->id);
+		if (IS_ERR(kthread)) {
+			dev_err(dev, "error creating queue thread (%ld)\n",
+				PTR_ERR(kthread));
+			ret = PTR_ERR(kthread);
+			goto e_kthread;
+		}
+
+		cmd_q->kthread = kthread;
+		wake_up_process(kthread);
+	}
+
+	/* Register the RNG */
+	ccp->hwrng.name = ccp->rngname;
+	ccp->hwrng.read = ccp_trng_read;
+	ret = hwrng_register(&ccp->hwrng);
+	if (ret) {
+		dev_err(dev, "error registering hwrng (%d)\n", ret);
+		goto e_kthread;
+	}
+
+	ccp_add_device(ccp);
+
+	/* Enable interrupts */
+	iowrite32(qim, ccp->io_regs + IRQ_MASK_REG);
+
+	return 0;
+
+e_kthread:
+	for (i = 0; i < ccp->cmd_q_count; i++)
+		if (ccp->cmd_q[i].kthread)
+			kthread_stop(ccp->cmd_q[i].kthread);
+
+	ccp->free_irq(ccp);
+
+e_pool:
+	for (i = 0; i < ccp->cmd_q_count; i++)
+		dma_pool_destroy(ccp->cmd_q[i].dma_pool);
+
+	return ret;
+}
+
+static void ccp_destroy(struct ccp_device *ccp)
+{
+	struct ccp_cmd_queue *cmd_q;
+	struct ccp_cmd *cmd;
+	unsigned int qim, i;
+
+	/* Remove this device from the list of available units first */
+	ccp_del_device(ccp);
+
+	/* Unregister the RNG */
+	hwrng_unregister(&ccp->hwrng);
+
+	/* Stop the queue kthreads */
+	for (i = 0; i < ccp->cmd_q_count; i++)
+		if (ccp->cmd_q[i].kthread)
+			kthread_stop(ccp->cmd_q[i].kthread);
+
+	/* Build queue interrupt mask (two interrupt masks per queue) */
+	qim = 0;
+	for (i = 0; i < ccp->cmd_q_count; i++) {
+		cmd_q = &ccp->cmd_q[i];
+		qim |= cmd_q->int_ok | cmd_q->int_err;
+	}
+
+	/* Disable and clear interrupts */
+	iowrite32(0x00, ccp->io_regs + IRQ_MASK_REG);
+	for (i = 0; i < ccp->cmd_q_count; i++) {
+		cmd_q = &ccp->cmd_q[i];
+
+		ioread32(cmd_q->reg_int_status);
+		ioread32(cmd_q->reg_status);
+	}
+	iowrite32(qim, ccp->io_regs + IRQ_STATUS_REG);
+
+	ccp->free_irq(ccp);
+
+	for (i = 0; i < ccp->cmd_q_count; i++)
+		dma_pool_destroy(ccp->cmd_q[i].dma_pool);
+
+	/* Flush the cmd and backlog queue */
+	while (!list_empty(&ccp->cmd)) {
+		/* Invoke the callback directly with an error code */
+		cmd = list_first_entry(&ccp->cmd, struct ccp_cmd, entry);
+		list_del(&cmd->entry);
+		cmd->callback(cmd->data, -ENODEV);
+	}
+	while (!list_empty(&ccp->backlog)) {
+		/* Invoke the callback directly with an error code */
+		cmd = list_first_entry(&ccp->backlog, struct ccp_cmd, entry);
+		list_del(&cmd->entry);
+		cmd->callback(cmd->data, -ENODEV);
+	}
+}
+
+static irqreturn_t ccp_irq_handler(int irq, void *data)
+{
+	struct device *dev = data;
+	struct ccp_device *ccp = dev_get_drvdata(dev);
+	struct ccp_cmd_queue *cmd_q;
+	u32 q_int, status;
+	unsigned int i;
+
+	status = ioread32(ccp->io_regs + IRQ_STATUS_REG);
+
+	for (i = 0; i < ccp->cmd_q_count; i++) {
+		cmd_q = &ccp->cmd_q[i];
+
+		q_int = status & (cmd_q->int_ok | cmd_q->int_err);
+		if (q_int) {
+			cmd_q->int_status = status;
+			cmd_q->q_status = ioread32(cmd_q->reg_status);
+			cmd_q->q_int_status = ioread32(cmd_q->reg_int_status);
+
+			/* On error, only save the first error value */
+			if ((q_int & cmd_q->int_err) && !cmd_q->cmd_error)
+				cmd_q->cmd_error = CMD_Q_ERROR(cmd_q->q_status);
+
+			cmd_q->int_rcvd = 1;
+
+			/* Acknowledge the interrupt and wake the kthread */
+			iowrite32(q_int, ccp->io_regs + IRQ_STATUS_REG);
+			wake_up_interruptible(&cmd_q->int_queue);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static struct ccp_actions ccp3_actions = {
+	.perform_aes = ccp_perform_aes,
+	.perform_xts_aes = ccp_perform_xts_aes,
+	.perform_sha = ccp_perform_sha,
+	.perform_rsa = ccp_perform_rsa,
+	.perform_passthru = ccp_perform_passthru,
+	.perform_ecc = ccp_perform_ecc,
+	.init = ccp_init,
+	.destroy = ccp_destroy,
+	.irqhandler = ccp_irq_handler,
+};
+
+struct ccp_vdata ccpv3 = {
+	.version = CCP_VERSION(3, 0),
+	.perform = &ccp3_actions,
+};
diff --git a/drivers/crypto/ccp/ccp-dev.c b/drivers/crypto/ccp/ccp-dev.c
index 861bacc1bb94..336e5b780fcb 100644
--- a/drivers/crypto/ccp/ccp-dev.c
+++ b/drivers/crypto/ccp/ccp-dev.c
@@ -1,7 +1,7 @@
 /*
  * AMD Cryptographic Coprocessor (CCP) driver
  *
- * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ * Copyright (C) 2013,2016 Advanced Micro Devices, Inc.
  *
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  *
@@ -16,6 +16,8 @@
 #include <linux/sched.h>
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
+#include <linux/rwlock_types.h>
+#include <linux/types.h>
 #include <linux/mutex.h>
 #include <linux/delay.h>
 #include <linux/hw_random.h>
@@ -37,20 +39,107 @@ struct ccp_tasklet_data {
 	struct ccp_cmd *cmd;
 };
 
-static struct ccp_device *ccp_dev;
-static inline struct ccp_device *ccp_get_device(void)
+/* List of CCPs, CCP count, read-write access lock, and access functions
+ *
+ * Lock structure: get ccp_unit_lock for reading whenever we need to
+ * examine the CCP list. While holding it for reading we can acquire
+ * the RR lock to update the round-robin next-CCP pointer. The unit lock
+ * must be acquired before the RR lock.
+ *
+ * If the unit-lock is acquired for writing, we have total control over
+ * the list, so there's no value in getting the RR lock.
+ */
+static DEFINE_RWLOCK(ccp_unit_lock);
+static LIST_HEAD(ccp_units);
+
+/* Round-robin counter */
+static DEFINE_RWLOCK(ccp_rr_lock);
+static struct ccp_device *ccp_rr;
+
+/* Ever-increasing value to produce unique unit numbers */
+static atomic_t ccp_unit_ordinal;
+unsigned int ccp_increment_unit_ordinal(void)
 {
-	return ccp_dev;
+	return atomic_inc_return(&ccp_unit_ordinal);
 }
 
-static inline void ccp_add_device(struct ccp_device *ccp)
+/**
+ * ccp_add_device - add a CCP device to the list
+ *
+ * @ccp: ccp_device struct pointer
+ *
+ * Put this CCP on the unit list, which makes it available
+ * for use.
+ *
+ * Returns zero if a CCP device is present, -ENODEV otherwise.
+ */
+void ccp_add_device(struct ccp_device *ccp)
 {
-	ccp_dev = ccp;
+	unsigned long flags;
+
+	write_lock_irqsave(&ccp_unit_lock, flags);
+	list_add_tail(&ccp->entry, &ccp_units);
+	if (!ccp_rr)
+		/* We already have the list lock (we're first) so this
+		 * pointer can't change on us. Set its initial value.
+		 */
+		ccp_rr = ccp;
+	write_unlock_irqrestore(&ccp_unit_lock, flags);
 }
 
-static inline void ccp_del_device(struct ccp_device *ccp)
+/**
+ * ccp_del_device - remove a CCP device from the list
+ *
+ * @ccp: ccp_device struct pointer
+ *
+ * Remove this unit from the list of devices. If the next device
+ * up for use is this one, adjust the pointer. If this is the last
+ * device, NULL the pointer.
+ */
+void ccp_del_device(struct ccp_device *ccp)
 {
-	ccp_dev = NULL;
+	unsigned long flags;
+
+	write_lock_irqsave(&ccp_unit_lock, flags);
+	if (ccp_rr == ccp) {
+		/* ccp_unit_lock is read/write; any read access
+		 * will be suspended while we make changes to the
+		 * list and RR pointer.
+		 */
+		if (list_is_last(&ccp_rr->entry, &ccp_units))
+			ccp_rr = list_first_entry(&ccp_units, struct ccp_device,
+						  entry);
+		else
+			ccp_rr = list_next_entry(ccp_rr, entry);
+	}
+	list_del(&ccp->entry);
+	if (list_empty(&ccp_units))
+		ccp_rr = NULL;
+	write_unlock_irqrestore(&ccp_unit_lock, flags);
+}
+
+static struct ccp_device *ccp_get_device(void)
+{
+	unsigned long flags;
+	struct ccp_device *dp = NULL;
+
+	/* We round-robin through the unit list.
+	 * The (ccp_rr) pointer refers to the next unit to use.
+	 */
+	read_lock_irqsave(&ccp_unit_lock, flags);
+	if (!list_empty(&ccp_units)) {
+		write_lock_irqsave(&ccp_rr_lock, flags);
+		dp = ccp_rr;
+		if (list_is_last(&ccp_rr->entry, &ccp_units))
+			ccp_rr = list_first_entry(&ccp_units, struct ccp_device,
+						  entry);
+		else
+			ccp_rr = list_next_entry(ccp_rr, entry);
+		write_unlock_irqrestore(&ccp_rr_lock, flags);
+	}
+	read_unlock_irqrestore(&ccp_unit_lock, flags);
+
+	return dp;
 }
 
 /**
@@ -60,14 +149,41 @@ static inline void ccp_del_device(struct ccp_device *ccp)
  */
 int ccp_present(void)
 {
-	if (ccp_get_device())
-		return 0;
+	unsigned long flags;
+	int ret;
 
-	return -ENODEV;
+	read_lock_irqsave(&ccp_unit_lock, flags);
+	ret = list_empty(&ccp_units);
+	read_unlock_irqrestore(&ccp_unit_lock, flags);
+
+	return ret ? -ENODEV : 0;
 }
 EXPORT_SYMBOL_GPL(ccp_present);
 
 /**
+ * ccp_version - get the version of the CCP device
+ *
+ * Returns the version from the first unit on the list;
+ * otherwise a zero if no CCP device is present
+ */
+unsigned int ccp_version(void)
+{
+	struct ccp_device *dp;
+	unsigned long flags;
+	int ret = 0;
+
+	read_lock_irqsave(&ccp_unit_lock, flags);
+	if (!list_empty(&ccp_units)) {
+		dp = list_first_entry(&ccp_units, struct ccp_device, entry);
+		ret = dp->vdata->version;
+	}
+	read_unlock_irqrestore(&ccp_unit_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ccp_version);
+
+/**
  * ccp_enqueue_cmd - queue an operation for processing by the CCP
  *
  * @cmd: ccp_cmd struct to be processed
@@ -221,7 +337,12 @@ static void ccp_do_cmd_complete(unsigned long data)
 	complete(&tdata->completion);
 }
 
-static int ccp_cmd_queue_thread(void *data)
+/**
+ * ccp_cmd_queue_thread - create a kernel thread to manage a CCP queue
+ *
+ * @data: thread-specific data
+ */
+int ccp_cmd_queue_thread(void *data)
 {
 	struct ccp_cmd_queue *cmd_q = (struct ccp_cmd_queue *)data;
 	struct ccp_cmd *cmd;
@@ -257,35 +378,6 @@ static int ccp_cmd_queue_thread(void *data)
 	return 0;
 }
 
-static int ccp_trng_read(struct hwrng *rng, void *data, size_t max, bool wait)
-{
-	struct ccp_device *ccp = container_of(rng, struct ccp_device, hwrng);
-	u32 trng_value;
-	int len = min_t(int, sizeof(trng_value), max);
-
-	/*
-	 * Locking is provided by the caller so we can update device
-	 * hwrng-related fields safely
-	 */
-	trng_value = ioread32(ccp->io_regs + TRNG_OUT_REG);
-	if (!trng_value) {
-		/* Zero is returned if not data is available or if a
-		 * bad-entropy error is present. Assume an error if
-		 * we exceed TRNG_RETRIES reads of zero.
-		 */
-		if (ccp->hwrng_retries++ > TRNG_RETRIES)
-			return -EIO;
-
-		return 0;
-	}
-
-	/* Reset the counter and save the rng value */
-	ccp->hwrng_retries = 0;
-	memcpy(data, &trng_value, len);
-
-	return len;
-}
-
 /**
  * ccp_alloc_struct - allocate and initialize the ccp_device struct
  *
@@ -309,253 +401,11 @@ struct ccp_device *ccp_alloc_struct(struct device *dev)
 	ccp->ksb_count = KSB_COUNT;
 	ccp->ksb_start = 0;
 
-	return ccp;
-}
-
-/**
- * ccp_init - initialize the CCP device
- *
- * @ccp: ccp_device struct
- */
-int ccp_init(struct ccp_device *ccp)
-{
-	struct device *dev = ccp->dev;
-	struct ccp_cmd_queue *cmd_q;
-	struct dma_pool *dma_pool;
-	char dma_pool_name[MAX_DMAPOOL_NAME_LEN];
-	unsigned int qmr, qim, i;
-	int ret;
-
-	/* Find available queues */
-	qim = 0;
-	qmr = ioread32(ccp->io_regs + Q_MASK_REG);
-	for (i = 0; i < MAX_HW_QUEUES; i++) {
-		if (!(qmr & (1 << i)))
-			continue;
-
-		/* Allocate a dma pool for this queue */
-		snprintf(dma_pool_name, sizeof(dma_pool_name), "ccp_q%d", i);
-		dma_pool = dma_pool_create(dma_pool_name, dev,
-					   CCP_DMAPOOL_MAX_SIZE,
-					   CCP_DMAPOOL_ALIGN, 0);
-		if (!dma_pool) {
-			dev_err(dev, "unable to allocate dma pool\n");
-			ret = -ENOMEM;
-			goto e_pool;
-		}
-
-		cmd_q = &ccp->cmd_q[ccp->cmd_q_count];
-		ccp->cmd_q_count++;
-
-		cmd_q->ccp = ccp;
-		cmd_q->id = i;
-		cmd_q->dma_pool = dma_pool;
-
-		/* Reserve 2 KSB regions for the queue */
-		cmd_q->ksb_key = KSB_START + ccp->ksb_start++;
-		cmd_q->ksb_ctx = KSB_START + ccp->ksb_start++;
-		ccp->ksb_count -= 2;
-
-		/* Preset some register values and masks that are queue
-		 * number dependent
-		 */
-		cmd_q->reg_status = ccp->io_regs + CMD_Q_STATUS_BASE +
-				    (CMD_Q_STATUS_INCR * i);
-		cmd_q->reg_int_status = ccp->io_regs + CMD_Q_INT_STATUS_BASE +
-					(CMD_Q_STATUS_INCR * i);
-		cmd_q->int_ok = 1 << (i * 2);
-		cmd_q->int_err = 1 << ((i * 2) + 1);
-
-		cmd_q->free_slots = CMD_Q_DEPTH(ioread32(cmd_q->reg_status));
-
-		init_waitqueue_head(&cmd_q->int_queue);
-
-		/* Build queue interrupt mask (two interrupts per queue) */
-		qim |= cmd_q->int_ok | cmd_q->int_err;
+	ccp->ord = ccp_increment_unit_ordinal();
+	snprintf(ccp->name, MAX_CCP_NAME_LEN, "ccp-%u", ccp->ord);
+	snprintf(ccp->rngname, MAX_CCP_NAME_LEN, "ccp-%u-rng", ccp->ord);
 
-#ifdef CONFIG_ARM64
-		/* For arm64 set the recommended queue cache settings */
-		iowrite32(ccp->axcache, ccp->io_regs + CMD_Q_CACHE_BASE +
-			  (CMD_Q_CACHE_INC * i));
-#endif
-
-		dev_dbg(dev, "queue #%u available\n", i);
-	}
-	if (ccp->cmd_q_count == 0) {
-		dev_notice(dev, "no command queues available\n");
-		ret = -EIO;
-		goto e_pool;
-	}
-	dev_notice(dev, "%u command queues available\n", ccp->cmd_q_count);
-
-	/* Disable and clear interrupts until ready */
-	iowrite32(0x00, ccp->io_regs + IRQ_MASK_REG);
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		cmd_q = &ccp->cmd_q[i];
-
-		ioread32(cmd_q->reg_int_status);
-		ioread32(cmd_q->reg_status);
-	}
-	iowrite32(qim, ccp->io_regs + IRQ_STATUS_REG);
-
-	/* Request an irq */
-	ret = ccp->get_irq(ccp);
-	if (ret) {
-		dev_err(dev, "unable to allocate an IRQ\n");
-		goto e_pool;
-	}
-
-	/* Initialize the queues used to wait for KSB space and suspend */
-	init_waitqueue_head(&ccp->ksb_queue);
-	init_waitqueue_head(&ccp->suspend_queue);
-
-	/* Create a kthread for each queue */
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		struct task_struct *kthread;
-
-		cmd_q = &ccp->cmd_q[i];
-
-		kthread = kthread_create(ccp_cmd_queue_thread, cmd_q,
-					 "ccp-q%u", cmd_q->id);
-		if (IS_ERR(kthread)) {
-			dev_err(dev, "error creating queue thread (%ld)\n",
-				PTR_ERR(kthread));
-			ret = PTR_ERR(kthread);
-			goto e_kthread;
-		}
-
-		cmd_q->kthread = kthread;
-		wake_up_process(kthread);
-	}
-
-	/* Register the RNG */
-	ccp->hwrng.name = "ccp-rng";
-	ccp->hwrng.read = ccp_trng_read;
-	ret = hwrng_register(&ccp->hwrng);
-	if (ret) {
-		dev_err(dev, "error registering hwrng (%d)\n", ret);
-		goto e_kthread;
-	}
-
-	/* Make the device struct available before enabling interrupts */
-	ccp_add_device(ccp);
-
-	/* Enable interrupts */
-	iowrite32(qim, ccp->io_regs + IRQ_MASK_REG);
-
-	return 0;
-
-e_kthread:
-	for (i = 0; i < ccp->cmd_q_count; i++)
-		if (ccp->cmd_q[i].kthread)
-			kthread_stop(ccp->cmd_q[i].kthread);
-
-	ccp->free_irq(ccp);
-
-e_pool:
-	for (i = 0; i < ccp->cmd_q_count; i++)
-		dma_pool_destroy(ccp->cmd_q[i].dma_pool);
-
-	return ret;
-}
-
-/**
- * ccp_destroy - tear down the CCP device
- *
- * @ccp: ccp_device struct
- */
-void ccp_destroy(struct ccp_device *ccp)
-{
-	struct ccp_cmd_queue *cmd_q;
-	struct ccp_cmd *cmd;
-	unsigned int qim, i;
-
-	/* Remove general access to the device struct */
-	ccp_del_device(ccp);
-
-	/* Unregister the RNG */
-	hwrng_unregister(&ccp->hwrng);
-
-	/* Stop the queue kthreads */
-	for (i = 0; i < ccp->cmd_q_count; i++)
-		if (ccp->cmd_q[i].kthread)
-			kthread_stop(ccp->cmd_q[i].kthread);
-
-	/* Build queue interrupt mask (two interrupt masks per queue) */
-	qim = 0;
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		cmd_q = &ccp->cmd_q[i];
-		qim |= cmd_q->int_ok | cmd_q->int_err;
-	}
-
-	/* Disable and clear interrupts */
-	iowrite32(0x00, ccp->io_regs + IRQ_MASK_REG);
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		cmd_q = &ccp->cmd_q[i];
-
-		ioread32(cmd_q->reg_int_status);
-		ioread32(cmd_q->reg_status);
-	}
-	iowrite32(qim, ccp->io_regs + IRQ_STATUS_REG);
-
-	ccp->free_irq(ccp);
-
-	for (i = 0; i < ccp->cmd_q_count; i++)
-		dma_pool_destroy(ccp->cmd_q[i].dma_pool);
-
-	/* Flush the cmd and backlog queue */
-	while (!list_empty(&ccp->cmd)) {
-		/* Invoke the callback directly with an error code */
-		cmd = list_first_entry(&ccp->cmd, struct ccp_cmd, entry);
-		list_del(&cmd->entry);
-		cmd->callback(cmd->data, -ENODEV);
-	}
-	while (!list_empty(&ccp->backlog)) {
-		/* Invoke the callback directly with an error code */
-		cmd = list_first_entry(&ccp->backlog, struct ccp_cmd, entry);
-		list_del(&cmd->entry);
-		cmd->callback(cmd->data, -ENODEV);
-	}
-}
-
-/**
- * ccp_irq_handler - handle interrupts generated by the CCP device
- *
- * @irq: the irq associated with the interrupt
- * @data: the data value supplied when the irq was created
- */
-irqreturn_t ccp_irq_handler(int irq, void *data)
-{
-	struct device *dev = data;
-	struct ccp_device *ccp = dev_get_drvdata(dev);
-	struct ccp_cmd_queue *cmd_q;
-	u32 q_int, status;
-	unsigned int i;
-
-	status = ioread32(ccp->io_regs + IRQ_STATUS_REG);
-
-	for (i = 0; i < ccp->cmd_q_count; i++) {
-		cmd_q = &ccp->cmd_q[i];
-
-		q_int = status & (cmd_q->int_ok | cmd_q->int_err);
-		if (q_int) {
-			cmd_q->int_status = status;
-			cmd_q->q_status = ioread32(cmd_q->reg_status);
-			cmd_q->q_int_status = ioread32(cmd_q->reg_int_status);
-
-			/* On error, only save the first error value */
-			if ((q_int & cmd_q->int_err) && !cmd_q->cmd_error)
-				cmd_q->cmd_error = CMD_Q_ERROR(cmd_q->q_status);
-
-			cmd_q->int_rcvd = 1;
-
-			/* Acknowledge the interrupt and wake the kthread */
-			iowrite32(q_int, ccp->io_regs + IRQ_STATUS_REG);
-			wake_up_interruptible(&cmd_q->int_queue);
-		}
-	}
-
-	return IRQ_HANDLED;
+	return ccp;
 }
 
 #ifdef CONFIG_PM
@@ -577,41 +427,22 @@ bool ccp_queues_suspended(struct ccp_device *ccp)
 }
 #endif
 
-#ifdef CONFIG_X86
-static const struct x86_cpu_id ccp_support[] = {
-	{ X86_VENDOR_AMD, 22, },
-	{ },
-};
-#endif
-
 static int __init ccp_mod_init(void)
 {
 #ifdef CONFIG_X86
-	struct cpuinfo_x86 *cpuinfo = &boot_cpu_data;
 	int ret;
 
-	if (!x86_match_cpu(ccp_support))
-		return -ENODEV;
-
-	switch (cpuinfo->x86) {
-	case 22:
-		if ((cpuinfo->x86_model < 48) || (cpuinfo->x86_model > 63))
-			return -ENODEV;
-
-		ret = ccp_pci_init();
-		if (ret)
-			return ret;
-
-		/* Don't leave the driver loaded if init failed */
-		if (!ccp_get_device()) {
-			ccp_pci_exit();
-			return -ENODEV;
-		}
-
-		return 0;
+	ret = ccp_pci_init();
+	if (ret)
+		return ret;
 
-		break;
+	/* Don't leave the driver loaded if init failed */
+	if (ccp_present() != 0) {
+		ccp_pci_exit();
+		return -ENODEV;
 	}
+
+	return 0;
 #endif
 
 #ifdef CONFIG_ARM64
@@ -622,7 +453,7 @@ static int __init ccp_mod_init(void)
 		return ret;
 
 	/* Don't leave the driver loaded if init failed */
-	if (!ccp_get_device()) {
+	if (ccp_present() != 0) {
 		ccp_platform_exit();
 		return -ENODEV;
 	}
@@ -636,13 +467,7 @@ static int __init ccp_mod_init(void)
 static void __exit ccp_mod_exit(void)
 {
 #ifdef CONFIG_X86
-	struct cpuinfo_x86 *cpuinfo = &boot_cpu_data;
-
-	switch (cpuinfo->x86) {
-	case 22:
-		ccp_pci_exit();
-		break;
-	}
+	ccp_pci_exit();
 #endif
 
 #ifdef CONFIG_ARM64
diff --git a/drivers/crypto/ccp/ccp-dev.h b/drivers/crypto/ccp/ccp-dev.h
index 6ff89031fb96..7745d0be491d 100644
--- a/drivers/crypto/ccp/ccp-dev.h
+++ b/drivers/crypto/ccp/ccp-dev.h
@@ -1,7 +1,7 @@
 /*
  * AMD Cryptographic Coprocessor (CCP) driver
  *
- * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ * Copyright (C) 2013,2016 Advanced Micro Devices, Inc.
  *
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  *
@@ -23,6 +23,7 @@
 #include <linux/hw_random.h>
 #include <linux/bitops.h>
 
+#define MAX_CCP_NAME_LEN		16
 #define MAX_DMAPOOL_NAME_LEN		32
 
 #define MAX_HW_QUEUES			5
@@ -140,6 +141,29 @@
 #define CCP_ECC_RESULT_OFFSET		60
 #define CCP_ECC_RESULT_SUCCESS		0x0001
 
+struct ccp_op;
+
+/* Structure for computation functions that are device-specific */
+struct ccp_actions {
+	int (*perform_aes)(struct ccp_op *);
+	int (*perform_xts_aes)(struct ccp_op *);
+	int (*perform_sha)(struct ccp_op *);
+	int (*perform_rsa)(struct ccp_op *);
+	int (*perform_passthru)(struct ccp_op *);
+	int (*perform_ecc)(struct ccp_op *);
+	int (*init)(struct ccp_device *);
+	void (*destroy)(struct ccp_device *);
+	irqreturn_t (*irqhandler)(int, void *);
+};
+
+/* Structure to hold CCP version-specific values */
+struct ccp_vdata {
+	unsigned int version;
+	struct ccp_actions *perform;
+};
+
+extern struct ccp_vdata ccpv3;
+
 struct ccp_device;
 struct ccp_cmd;
 
@@ -184,6 +208,13 @@ struct ccp_cmd_queue {
 } ____cacheline_aligned;
 
 struct ccp_device {
+	struct list_head entry;
+
+	struct ccp_vdata *vdata;
+	unsigned int ord;
+	char name[MAX_CCP_NAME_LEN];
+	char rngname[MAX_CCP_NAME_LEN];
+
 	struct device *dev;
 
 	/*
@@ -258,18 +289,132 @@ struct ccp_device {
 	unsigned int axcache;
 };
 
+enum ccp_memtype {
+	CCP_MEMTYPE_SYSTEM = 0,
+	CCP_MEMTYPE_KSB,
+	CCP_MEMTYPE_LOCAL,
+	CCP_MEMTYPE__LAST,
+};
+
+struct ccp_dma_info {
+	dma_addr_t address;
+	unsigned int offset;
+	unsigned int length;
+	enum dma_data_direction dir;
+};
+
+struct ccp_dm_workarea {
+	struct device *dev;
+	struct dma_pool *dma_pool;
+	unsigned int length;
+
+	u8 *address;
+	struct ccp_dma_info dma;
+};
+
+struct ccp_sg_workarea {
+	struct scatterlist *sg;
+	int nents;
+
+	struct scatterlist *dma_sg;
+	struct device *dma_dev;
+	unsigned int dma_count;
+	enum dma_data_direction dma_dir;
+
+	unsigned int sg_used;
+
+	u64 bytes_left;
+};
+
+struct ccp_data {
+	struct ccp_sg_workarea sg_wa;
+	struct ccp_dm_workarea dm_wa;
+};
+
+struct ccp_mem {
+	enum ccp_memtype type;
+	union {
+		struct ccp_dma_info dma;
+		u32 ksb;
+	} u;
+};
+
+struct ccp_aes_op {
+	enum ccp_aes_type type;
+	enum ccp_aes_mode mode;
+	enum ccp_aes_action action;
+};
+
+struct ccp_xts_aes_op {
+	enum ccp_aes_action action;
+	enum ccp_xts_aes_unit_size unit_size;
+};
+
+struct ccp_sha_op {
+	enum ccp_sha_type type;
+	u64 msg_bits;
+};
+
+struct ccp_rsa_op {
+	u32 mod_size;
+	u32 input_len;
+};
+
+struct ccp_passthru_op {
+	enum ccp_passthru_bitwise bit_mod;
+	enum ccp_passthru_byteswap byte_swap;
+};
+
+struct ccp_ecc_op {
+	enum ccp_ecc_function function;
+};
+
+struct ccp_op {
+	struct ccp_cmd_queue *cmd_q;
+
+	u32 jobid;
+	u32 ioc;
+	u32 soc;
+	u32 ksb_key;
+	u32 ksb_ctx;
+	u32 init;
+	u32 eom;
+
+	struct ccp_mem src;
+	struct ccp_mem dst;
+
+	union {
+		struct ccp_aes_op aes;
+		struct ccp_xts_aes_op xts;
+		struct ccp_sha_op sha;
+		struct ccp_rsa_op rsa;
+		struct ccp_passthru_op passthru;
+		struct ccp_ecc_op ecc;
+	} u;
+};
+
+static inline u32 ccp_addr_lo(struct ccp_dma_info *info)
+{
+	return lower_32_bits(info->address + info->offset);
+}
+
+static inline u32 ccp_addr_hi(struct ccp_dma_info *info)
+{
+	return upper_32_bits(info->address + info->offset) & 0x0000ffff;
+}
+
 int ccp_pci_init(void);
 void ccp_pci_exit(void);
 
 int ccp_platform_init(void);
 void ccp_platform_exit(void);
 
+void ccp_add_device(struct ccp_device *ccp);
+void ccp_del_device(struct ccp_device *ccp);
+
 struct ccp_device *ccp_alloc_struct(struct device *dev);
-int ccp_init(struct ccp_device *ccp);
-void ccp_destroy(struct ccp_device *ccp);
 bool ccp_queues_suspended(struct ccp_device *ccp);
-
-irqreturn_t ccp_irq_handler(int irq, void *data);
+int ccp_cmd_queue_thread(void *data);
 
 int ccp_run_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd);
 
diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c
index 6613aee79b87..eefdf595f758 100644
--- a/drivers/crypto/ccp/ccp-ops.c
+++ b/drivers/crypto/ccp/ccp-ops.c
@@ -1,7 +1,7 @@
 /*
  * AMD Cryptographic Coprocessor (CCP) driver
  *
- * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ * Copyright (C) 2013,2016 Advanced Micro Devices, Inc.
  *
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  *
@@ -13,124 +13,12 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/pci.h>
-#include <linux/pci_ids.h>
-#include <linux/kthread.h>
-#include <linux/sched.h>
 #include <linux/interrupt.h>
-#include <linux/spinlock.h>
-#include <linux/mutex.h>
-#include <linux/delay.h>
-#include <linux/ccp.h>
-#include <linux/scatterlist.h>
 #include <crypto/scatterwalk.h>
-#include <crypto/sha.h>
+#include <linux/ccp.h>
 
 #include "ccp-dev.h"
 
-enum ccp_memtype {
-	CCP_MEMTYPE_SYSTEM = 0,
-	CCP_MEMTYPE_KSB,
-	CCP_MEMTYPE_LOCAL,
-	CCP_MEMTYPE__LAST,
-};
-
-struct ccp_dma_info {
-	dma_addr_t address;
-	unsigned int offset;
-	unsigned int length;
-	enum dma_data_direction dir;
-};
-
-struct ccp_dm_workarea {
-	struct device *dev;
-	struct dma_pool *dma_pool;
-	unsigned int length;
-
-	u8 *address;
-	struct ccp_dma_info dma;
-};
-
-struct ccp_sg_workarea {
-	struct scatterlist *sg;
-	int nents;
-
-	struct scatterlist *dma_sg;
-	struct device *dma_dev;
-	unsigned int dma_count;
-	enum dma_data_direction dma_dir;
-
-	unsigned int sg_used;
-
-	u64 bytes_left;
-};
-
-struct ccp_data {
-	struct ccp_sg_workarea sg_wa;
-	struct ccp_dm_workarea dm_wa;
-};
-
-struct ccp_mem {
-	enum ccp_memtype type;
-	union {
-		struct ccp_dma_info dma;
-		u32 ksb;
-	} u;
-};
-
-struct ccp_aes_op {
-	enum ccp_aes_type type;
-	enum ccp_aes_mode mode;
-	enum ccp_aes_action action;
-};
-
-struct ccp_xts_aes_op {
-	enum ccp_aes_action action;
-	enum ccp_xts_aes_unit_size unit_size;
-};
-
-struct ccp_sha_op {
-	enum ccp_sha_type type;
-	u64 msg_bits;
-};
-
-struct ccp_rsa_op {
-	u32 mod_size;
-	u32 input_len;
-};
-
-struct ccp_passthru_op {
-	enum ccp_passthru_bitwise bit_mod;
-	enum ccp_passthru_byteswap byte_swap;
-};
-
-struct ccp_ecc_op {
-	enum ccp_ecc_function function;
-};
-
-struct ccp_op {
-	struct ccp_cmd_queue *cmd_q;
-
-	u32 jobid;
-	u32 ioc;
-	u32 soc;
-	u32 ksb_key;
-	u32 ksb_ctx;
-	u32 init;
-	u32 eom;
-
-	struct ccp_mem src;
-	struct ccp_mem dst;
-
-	union {
-		struct ccp_aes_op aes;
-		struct ccp_xts_aes_op xts;
-		struct ccp_sha_op sha;
-		struct ccp_rsa_op rsa;
-		struct ccp_passthru_op passthru;
-		struct ccp_ecc_op ecc;
-	} u;
-};
-
 /* SHA initial context values */
 static const __be32 ccp_sha1_init[CCP_SHA_CTXSIZE / sizeof(__be32)] = {
 	cpu_to_be32(SHA1_H0), cpu_to_be32(SHA1_H1),
@@ -152,253 +40,6 @@ static const __be32 ccp_sha256_init[CCP_SHA_CTXSIZE / sizeof(__be32)] = {
 	cpu_to_be32(SHA256_H6), cpu_to_be32(SHA256_H7),
 };
 
-static u32 ccp_addr_lo(struct ccp_dma_info *info)
-{
-	return lower_32_bits(info->address + info->offset);
-}
-
-static u32 ccp_addr_hi(struct ccp_dma_info *info)
-{
-	return upper_32_bits(info->address + info->offset) & 0x0000ffff;
-}
-
-static int ccp_do_cmd(struct ccp_op *op, u32 *cr, unsigned int cr_count)
-{
-	struct ccp_cmd_queue *cmd_q = op->cmd_q;
-	struct ccp_device *ccp = cmd_q->ccp;
-	void __iomem *cr_addr;
-	u32 cr0, cmd;
-	unsigned int i;
-	int ret = 0;
-
-	/* We could read a status register to see how many free slots
-	 * are actually available, but reading that register resets it
-	 * and you could lose some error information.
-	 */
-	cmd_q->free_slots--;
-
-	cr0 = (cmd_q->id << REQ0_CMD_Q_SHIFT)
-	      | (op->jobid << REQ0_JOBID_SHIFT)
-	      | REQ0_WAIT_FOR_WRITE;
-
-	if (op->soc)
-		cr0 |= REQ0_STOP_ON_COMPLETE
-		       | REQ0_INT_ON_COMPLETE;
-
-	if (op->ioc || !cmd_q->free_slots)
-		cr0 |= REQ0_INT_ON_COMPLETE;
-
-	/* Start at CMD_REQ1 */
-	cr_addr = ccp->io_regs + CMD_REQ0 + CMD_REQ_INCR;
-
-	mutex_lock(&ccp->req_mutex);
-
-	/* Write CMD_REQ1 through CMD_REQx first */
-	for (i = 0; i < cr_count; i++, cr_addr += CMD_REQ_INCR)
-		iowrite32(*(cr + i), cr_addr);
-
-	/* Tell the CCP to start */
-	wmb();
-	iowrite32(cr0, ccp->io_regs + CMD_REQ0);
-
-	mutex_unlock(&ccp->req_mutex);
-
-	if (cr0 & REQ0_INT_ON_COMPLETE) {
-		/* Wait for the job to complete */
-		ret = wait_event_interruptible(cmd_q->int_queue,
-					       cmd_q->int_rcvd);
-		if (ret || cmd_q->cmd_error) {
-			/* On error delete all related jobs from the queue */
-			cmd = (cmd_q->id << DEL_Q_ID_SHIFT)
-			      | op->jobid;
-
-			iowrite32(cmd, ccp->io_regs + DEL_CMD_Q_JOB);
-
-			if (!ret)
-				ret = -EIO;
-		} else if (op->soc) {
-			/* Delete just head job from the queue on SoC */
-			cmd = DEL_Q_ACTIVE
-			      | (cmd_q->id << DEL_Q_ID_SHIFT)
-			      | op->jobid;
-
-			iowrite32(cmd, ccp->io_regs + DEL_CMD_Q_JOB);
-		}
-
-		cmd_q->free_slots = CMD_Q_DEPTH(cmd_q->q_status);
-
-		cmd_q->int_rcvd = 0;
-	}
-
-	return ret;
-}
-
-static int ccp_perform_aes(struct ccp_op *op)
-{
-	u32 cr[6];
-
-	/* Fill out the register contents for REQ1 through REQ6 */
-	cr[0] = (CCP_ENGINE_AES << REQ1_ENGINE_SHIFT)
-		| (op->u.aes.type << REQ1_AES_TYPE_SHIFT)
-		| (op->u.aes.mode << REQ1_AES_MODE_SHIFT)
-		| (op->u.aes.action << REQ1_AES_ACTION_SHIFT)
-		| (op->ksb_key << REQ1_KEY_KSB_SHIFT);
-	cr[1] = op->src.u.dma.length - 1;
-	cr[2] = ccp_addr_lo(&op->src.u.dma);
-	cr[3] = (op->ksb_ctx << REQ4_KSB_SHIFT)
-		| (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
-		| ccp_addr_hi(&op->src.u.dma);
-	cr[4] = ccp_addr_lo(&op->dst.u.dma);
-	cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
-		| ccp_addr_hi(&op->dst.u.dma);
-
-	if (op->u.aes.mode == CCP_AES_MODE_CFB)
-		cr[0] |= ((0x7f) << REQ1_AES_CFB_SIZE_SHIFT);
-
-	if (op->eom)
-		cr[0] |= REQ1_EOM;
-
-	if (op->init)
-		cr[0] |= REQ1_INIT;
-
-	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
-}
-
-static int ccp_perform_xts_aes(struct ccp_op *op)
-{
-	u32 cr[6];
-
-	/* Fill out the register contents for REQ1 through REQ6 */
-	cr[0] = (CCP_ENGINE_XTS_AES_128 << REQ1_ENGINE_SHIFT)
-		| (op->u.xts.action << REQ1_AES_ACTION_SHIFT)
-		| (op->u.xts.unit_size << REQ1_XTS_AES_SIZE_SHIFT)
-		| (op->ksb_key << REQ1_KEY_KSB_SHIFT);
-	cr[1] = op->src.u.dma.length - 1;
-	cr[2] = ccp_addr_lo(&op->src.u.dma);
-	cr[3] = (op->ksb_ctx << REQ4_KSB_SHIFT)
-		| (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
-		| ccp_addr_hi(&op->src.u.dma);
-	cr[4] = ccp_addr_lo(&op->dst.u.dma);
-	cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
-		| ccp_addr_hi(&op->dst.u.dma);
-
-	if (op->eom)
-		cr[0] |= REQ1_EOM;
-
-	if (op->init)
-		cr[0] |= REQ1_INIT;
-
-	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
-}
-
-static int ccp_perform_sha(struct ccp_op *op)
-{
-	u32 cr[6];
-
-	/* Fill out the register contents for REQ1 through REQ6 */
-	cr[0] = (CCP_ENGINE_SHA << REQ1_ENGINE_SHIFT)
-		| (op->u.sha.type << REQ1_SHA_TYPE_SHIFT)
-		| REQ1_INIT;
-	cr[1] = op->src.u.dma.length - 1;
-	cr[2] = ccp_addr_lo(&op->src.u.dma);
-	cr[3] = (op->ksb_ctx << REQ4_KSB_SHIFT)
-		| (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
-		| ccp_addr_hi(&op->src.u.dma);
-
-	if (op->eom) {
-		cr[0] |= REQ1_EOM;
-		cr[4] = lower_32_bits(op->u.sha.msg_bits);
-		cr[5] = upper_32_bits(op->u.sha.msg_bits);
-	} else {
-		cr[4] = 0;
-		cr[5] = 0;
-	}
-
-	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
-}
-
-static int ccp_perform_rsa(struct ccp_op *op)
-{
-	u32 cr[6];
-
-	/* Fill out the register contents for REQ1 through REQ6 */
-	cr[0] = (CCP_ENGINE_RSA << REQ1_ENGINE_SHIFT)
-		| (op->u.rsa.mod_size << REQ1_RSA_MOD_SIZE_SHIFT)
-		| (op->ksb_key << REQ1_KEY_KSB_SHIFT)
-		| REQ1_EOM;
-	cr[1] = op->u.rsa.input_len - 1;
-	cr[2] = ccp_addr_lo(&op->src.u.dma);
-	cr[3] = (op->ksb_ctx << REQ4_KSB_SHIFT)
-		| (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
-		| ccp_addr_hi(&op->src.u.dma);
-	cr[4] = ccp_addr_lo(&op->dst.u.dma);
-	cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
-		| ccp_addr_hi(&op->dst.u.dma);
-
-	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
-}
-
-static int ccp_perform_passthru(struct ccp_op *op)
-{
-	u32 cr[6];
-
-	/* Fill out the register contents for REQ1 through REQ6 */
-	cr[0] = (CCP_ENGINE_PASSTHRU << REQ1_ENGINE_SHIFT)
-		| (op->u.passthru.bit_mod << REQ1_PT_BW_SHIFT)
-		| (op->u.passthru.byte_swap << REQ1_PT_BS_SHIFT);
-
-	if (op->src.type == CCP_MEMTYPE_SYSTEM)
-		cr[1] = op->src.u.dma.length - 1;
-	else
-		cr[1] = op->dst.u.dma.length - 1;
-
-	if (op->src.type == CCP_MEMTYPE_SYSTEM) {
-		cr[2] = ccp_addr_lo(&op->src.u.dma);
-		cr[3] = (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
-			| ccp_addr_hi(&op->src.u.dma);
-
-		if (op->u.passthru.bit_mod != CCP_PASSTHRU_BITWISE_NOOP)
-			cr[3] |= (op->ksb_key << REQ4_KSB_SHIFT);
-	} else {
-		cr[2] = op->src.u.ksb * CCP_KSB_BYTES;
-		cr[3] = (CCP_MEMTYPE_KSB << REQ4_MEMTYPE_SHIFT);
-	}
-
-	if (op->dst.type == CCP_MEMTYPE_SYSTEM) {
-		cr[4] = ccp_addr_lo(&op->dst.u.dma);
-		cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
-			| ccp_addr_hi(&op->dst.u.dma);
-	} else {
-		cr[4] = op->dst.u.ksb * CCP_KSB_BYTES;
-		cr[5] = (CCP_MEMTYPE_KSB << REQ6_MEMTYPE_SHIFT);
-	}
-
-	if (op->eom)
-		cr[0] |= REQ1_EOM;
-
-	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
-}
-
-static int ccp_perform_ecc(struct ccp_op *op)
-{
-	u32 cr[6];
-
-	/* Fill out the register contents for REQ1 through REQ6 */
-	cr[0] = REQ1_ECC_AFFINE_CONVERT
-		| (CCP_ENGINE_ECC << REQ1_ENGINE_SHIFT)
-		| (op->u.ecc.function << REQ1_ECC_FUNCTION_SHIFT)
-		| REQ1_EOM;
-	cr[1] = op->src.u.dma.length - 1;
-	cr[2] = ccp_addr_lo(&op->src.u.dma);
-	cr[3] = (CCP_MEMTYPE_SYSTEM << REQ4_MEMTYPE_SHIFT)
-		| ccp_addr_hi(&op->src.u.dma);
-	cr[4] = ccp_addr_lo(&op->dst.u.dma);
-	cr[5] = (CCP_MEMTYPE_SYSTEM << REQ6_MEMTYPE_SHIFT)
-		| ccp_addr_hi(&op->dst.u.dma);
-
-	return ccp_do_cmd(op, cr, ARRAY_SIZE(cr));
-}
-
 static u32 ccp_alloc_ksb(struct ccp_device *ccp, unsigned int count)
 {
 	int start;
@@ -837,7 +478,7 @@ static int ccp_copy_to_from_ksb(struct ccp_cmd_queue *cmd_q,
 
 	op.u.passthru.byte_swap = byte_swap;
 
-	return ccp_perform_passthru(&op);
+	return cmd_q->ccp->vdata->perform->perform_passthru(&op);
 }
 
 static int ccp_copy_to_ksb(struct ccp_cmd_queue *cmd_q,
@@ -969,7 +610,7 @@ static int ccp_run_aes_cmac_cmd(struct ccp_cmd_queue *cmd_q,
 			}
 		}
 
-		ret = ccp_perform_aes(&op);
+		ret = cmd_q->ccp->vdata->perform->perform_aes(&op);
 		if (ret) {
 			cmd->engine_error = cmd_q->cmd_error;
 			goto e_src;
@@ -1131,7 +772,7 @@ static int ccp_run_aes_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 				op.soc = 1;
 		}
 
-		ret = ccp_perform_aes(&op);
+		ret = cmd_q->ccp->vdata->perform->perform_aes(&op);
 		if (ret) {
 			cmd->engine_error = cmd_q->cmd_error;
 			goto e_dst;
@@ -1296,7 +937,7 @@ static int ccp_run_xts_aes_cmd(struct ccp_cmd_queue *cmd_q,
 		if (!src.sg_wa.bytes_left)
 			op.eom = 1;
 
-		ret = ccp_perform_xts_aes(&op);
+		ret = cmd_q->ccp->vdata->perform->perform_xts_aes(&op);
 		if (ret) {
 			cmd->engine_error = cmd_q->cmd_error;
 			goto e_dst;
@@ -1453,7 +1094,7 @@ static int ccp_run_sha_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 		if (sha->final && !src.sg_wa.bytes_left)
 			op.eom = 1;
 
-		ret = ccp_perform_sha(&op);
+		ret = cmd_q->ccp->vdata->perform->perform_sha(&op);
 		if (ret) {
 			cmd->engine_error = cmd_q->cmd_error;
 			goto e_data;
@@ -1633,7 +1274,7 @@ static int ccp_run_rsa_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 	op.u.rsa.mod_size = rsa->key_size;
 	op.u.rsa.input_len = i_len;
 
-	ret = ccp_perform_rsa(&op);
+	ret = cmd_q->ccp->vdata->perform->perform_rsa(&op);
 	if (ret) {
 		cmd->engine_error = cmd_q->cmd_error;
 		goto e_dst;
@@ -1758,7 +1399,7 @@ static int ccp_run_passthru_cmd(struct ccp_cmd_queue *cmd_q,
 		op.dst.u.dma.offset = dst.sg_wa.sg_used;
 		op.dst.u.dma.length = op.src.u.dma.length;
 
-		ret = ccp_perform_passthru(&op);
+		ret = cmd_q->ccp->vdata->perform->perform_passthru(&op);
 		if (ret) {
 			cmd->engine_error = cmd_q->cmd_error;
 			goto e_dst;
@@ -1870,7 +1511,7 @@ static int ccp_run_ecc_mm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 
 	op.u.ecc.function = cmd->u.ecc.function;
 
-	ret = ccp_perform_ecc(&op);
+	ret = cmd_q->ccp->vdata->perform->perform_ecc(&op);
 	if (ret) {
 		cmd->engine_error = cmd_q->cmd_error;
 		goto e_dst;
@@ -2034,7 +1675,7 @@ static int ccp_run_ecc_pm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 
 	op.u.ecc.function = cmd->u.ecc.function;
 
-	ret = ccp_perform_ecc(&op);
+	ret = cmd_q->ccp->vdata->perform->perform_ecc(&op);
 	if (ret) {
 		cmd->engine_error = cmd_q->cmd_error;
 		goto e_dst;
diff --git a/drivers/crypto/ccp/ccp-pci.c b/drivers/crypto/ccp/ccp-pci.c
index 7690467c42f8..0bf262e36b6b 100644
--- a/drivers/crypto/ccp/ccp-pci.c
+++ b/drivers/crypto/ccp/ccp-pci.c
@@ -1,7 +1,7 @@
 /*
  * AMD Cryptographic Coprocessor (CCP) driver
  *
- * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ * Copyright (C) 2013,2016 Advanced Micro Devices, Inc.
  *
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  *
@@ -59,9 +59,11 @@ static int ccp_get_msix_irqs(struct ccp_device *ccp)
 	ccp_pci->msix_count = ret;
 	for (v = 0; v < ccp_pci->msix_count; v++) {
 		/* Set the interrupt names and request the irqs */
-		snprintf(ccp_pci->msix[v].name, name_len, "ccp-%u", v);
+		snprintf(ccp_pci->msix[v].name, name_len, "%s-%u",
+			 ccp->name, v);
 		ccp_pci->msix[v].vector = msix_entry[v].vector;
-		ret = request_irq(ccp_pci->msix[v].vector, ccp_irq_handler,
+		ret = request_irq(ccp_pci->msix[v].vector,
+				  ccp->vdata->perform->irqhandler,
 				  0, ccp_pci->msix[v].name, dev);
 		if (ret) {
 			dev_notice(dev, "unable to allocate MSI-X IRQ (%d)\n",
@@ -94,7 +96,8 @@ static int ccp_get_msi_irq(struct ccp_device *ccp)
 		return ret;
 
 	ccp->irq = pdev->irq;
-	ret = request_irq(ccp->irq, ccp_irq_handler, 0, "ccp", dev);
+	ret = request_irq(ccp->irq, ccp->vdata->perform->irqhandler, 0,
+			  ccp->name, dev);
 	if (ret) {
 		dev_notice(dev, "unable to allocate MSI IRQ (%d)\n", ret);
 		goto e_msi;
@@ -179,6 +182,12 @@ static int ccp_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto e_err;
 
 	ccp->dev_specific = ccp_pci;
+	ccp->vdata = (struct ccp_vdata *)id->driver_data;
+	if (!ccp->vdata || !ccp->vdata->version) {
+		ret = -ENODEV;
+		dev_err(dev, "missing driver data\n");
+		goto e_err;
+	}
 	ccp->get_irq = ccp_get_irqs;
 	ccp->free_irq = ccp_free_irqs;
 
@@ -221,7 +230,7 @@ static int ccp_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	dev_set_drvdata(dev, ccp);
 
-	ret = ccp_init(ccp);
+	ret = ccp->vdata->perform->init(ccp);
 	if (ret)
 		goto e_iomap;
 
@@ -251,7 +260,7 @@ static void ccp_pci_remove(struct pci_dev *pdev)
 	if (!ccp)
 		return;
 
-	ccp_destroy(ccp);
+	ccp->vdata->perform->destroy(ccp);
 
 	pci_iounmap(pdev, ccp->io_map);
 
@@ -312,7 +321,7 @@ static int ccp_pci_resume(struct pci_dev *pdev)
 #endif
 
 static const struct pci_device_id ccp_pci_table[] = {
-	{ PCI_VDEVICE(AMD, 0x1537), },
+	{ PCI_VDEVICE(AMD, 0x1537), (kernel_ulong_t)&ccpv3 },
 	/* Last entry must be zero */
 	{ 0, }
 };
diff --git a/drivers/crypto/ccp/ccp-platform.c b/drivers/crypto/ccp/ccp-platform.c
index 66dd7c9d08c3..351f28d8c336 100644
--- a/drivers/crypto/ccp/ccp-platform.c
+++ b/drivers/crypto/ccp/ccp-platform.c
@@ -1,7 +1,7 @@
 /*
  * AMD Cryptographic Coprocessor (CCP) driver
  *
- * Copyright (C) 2014 Advanced Micro Devices, Inc.
+ * Copyright (C) 2014,2016 Advanced Micro Devices, Inc.
  *
  * Author: Tom Lendacky <thomas.lendacky@amd.com>
  *
@@ -32,6 +32,33 @@ struct ccp_platform {
 	int coherent;
 };
 
+static const struct acpi_device_id ccp_acpi_match[];
+static const struct of_device_id ccp_of_match[];
+
+static struct ccp_vdata *ccp_get_of_version(struct platform_device *pdev)
+{
+#ifdef CONFIG_OF
+	const struct of_device_id *match;
+
+	match = of_match_node(ccp_of_match, pdev->dev.of_node);
+	if (match && match->data)
+		return (struct ccp_vdata *)match->data;
+#endif
+	return 0;
+}
+
+static struct ccp_vdata *ccp_get_acpi_version(struct platform_device *pdev)
+{
+#ifdef CONFIG_ACPI
+	const struct acpi_device_id *match;
+
+	match = acpi_match_device(ccp_acpi_match, &pdev->dev);
+	if (match && match->driver_data)
+		return (struct ccp_vdata *)match->driver_data;
+#endif
+	return 0;
+}
+
 static int ccp_get_irq(struct ccp_device *ccp)
 {
 	struct device *dev = ccp->dev;
@@ -43,7 +70,8 @@ static int ccp_get_irq(struct ccp_device *ccp)
 		return ret;
 
 	ccp->irq = ret;
-	ret = request_irq(ccp->irq, ccp_irq_handler, 0, "ccp", dev);
+	ret = request_irq(ccp->irq, ccp->vdata->perform->irqhandler, 0,
+			  ccp->name, dev);
 	if (ret) {
 		dev_notice(dev, "unable to allocate IRQ (%d)\n", ret);
 		return ret;
@@ -106,6 +134,13 @@ static int ccp_platform_probe(struct platform_device *pdev)
 		goto e_err;
 
 	ccp->dev_specific = ccp_platform;
+	ccp->vdata = pdev->dev.of_node ? ccp_get_of_version(pdev)
+					 : ccp_get_acpi_version(pdev);
+	if (!ccp->vdata || !ccp->vdata->version) {
+		ret = -ENODEV;
+		dev_err(dev, "missing driver data\n");
+		goto e_err;
+	}
 	ccp->get_irq = ccp_get_irqs;
 	ccp->free_irq = ccp_free_irqs;
 
@@ -137,7 +172,7 @@ static int ccp_platform_probe(struct platform_device *pdev)
 
 	dev_set_drvdata(dev, ccp);
 
-	ret = ccp_init(ccp);
+	ret = ccp->vdata->perform->init(ccp);
 	if (ret)
 		goto e_err;
 
@@ -155,7 +190,7 @@ static int ccp_platform_remove(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct ccp_device *ccp = dev_get_drvdata(dev);
 
-	ccp_destroy(ccp);
+	ccp->vdata->perform->destroy(ccp);
 
 	dev_notice(dev, "disabled\n");
 
@@ -214,7 +249,7 @@ static int ccp_platform_resume(struct platform_device *pdev)
 
 #ifdef CONFIG_ACPI
 static const struct acpi_device_id ccp_acpi_match[] = {
-	{ "AMDI0C00", 0 },
+	{ "AMDI0C00", (kernel_ulong_t)&ccpv3 },
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, ccp_acpi_match);
@@ -222,7 +257,8 @@ MODULE_DEVICE_TABLE(acpi, ccp_acpi_match);
 
 #ifdef CONFIG_OF
 static const struct of_device_id ccp_of_match[] = {
-	{ .compatible = "amd,ccp-seattle-v1a" },
+	{ .compatible = "amd,ccp-seattle-v1a",
+	  .data = (const void *)&ccpv3 },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, ccp_of_match);
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index e52496a172d0..2296934455fc 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -1031,6 +1031,18 @@ static int aead_perform(struct aead_request *req, int encrypt,
 	BUG_ON(ivsize && !req->iv);
 	memcpy(crypt->iv, req->iv, ivsize);
 
+	buf = chainup_buffers(dev, req->src, crypt->auth_len,
+			      &src_hook, flags, src_direction);
+	req_ctx->src = src_hook.next;
+	crypt->src_buf = src_hook.phys_next;
+	if (!buf)
+		goto free_buf_src;
+
+	lastlen = buf->buf_len;
+	if (lastlen >= authsize)
+		crypt->icv_rev_aes = buf->phys_addr +
+				     buf->buf_len - authsize;
+
 	req_ctx->dst = NULL;
 
 	if (req->src != req->dst) {
@@ -1055,20 +1067,6 @@ static int aead_perform(struct aead_request *req, int encrypt,
 		}
 	}
 
-	buf = chainup_buffers(dev, req->src, crypt->auth_len,
-			      &src_hook, flags, src_direction);
-	req_ctx->src = src_hook.next;
-	crypt->src_buf = src_hook.phys_next;
-	if (!buf)
-		goto free_buf_src;
-
-	if (!encrypt || !req_ctx->dst) {
-		lastlen = buf->buf_len;
-		if (lastlen >= authsize)
-			crypt->icv_rev_aes = buf->phys_addr +
-					     buf->buf_len - authsize;
-	}
-
 	if (unlikely(lastlen < authsize)) {
 		/* The 12 hmac bytes are scattered,
 		 * we need to copy them into a safe buffer */
diff --git a/drivers/crypto/marvell/cesa.c b/drivers/crypto/marvell/cesa.c
index 0643e3366e33..c0656e7f37b5 100644
--- a/drivers/crypto/marvell/cesa.c
+++ b/drivers/crypto/marvell/cesa.c
@@ -306,7 +306,7 @@ static int mv_cesa_dev_dma_init(struct mv_cesa_dev *cesa)
 		return -ENOMEM;
 
 	dma->padding_pool = dmam_pool_create("cesa_padding", dev, 72, 1, 0);
-	if (!dma->cache_pool)
+	if (!dma->padding_pool)
 		return -ENOMEM;
 
 	cesa->dma = dma;
diff --git a/drivers/crypto/omap-aes.c b/drivers/crypto/omap-aes.c
index dd355bd19474..d420ec751c7c 100644
--- a/drivers/crypto/omap-aes.c
+++ b/drivers/crypto/omap-aes.c
@@ -36,6 +36,7 @@
 #include <linux/interrupt.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/aes.h>
+#include <crypto/algapi.h>
 
 #define DST_MAXBURST			4
 #define DMA_MIN				(DST_MAXBURST * sizeof(u32))
@@ -152,13 +153,10 @@ struct omap_aes_dev {
 	unsigned long		flags;
 	int			err;
 
-	spinlock_t		lock;
-	struct crypto_queue	queue;
-
 	struct tasklet_struct	done_task;
-	struct tasklet_struct	queue_task;
 
 	struct ablkcipher_request	*req;
+	struct crypto_engine		*engine;
 
 	/*
 	 * total is used by PIO mode for book keeping so introduce
@@ -532,9 +530,7 @@ static void omap_aes_finish_req(struct omap_aes_dev *dd, int err)
 
 	pr_debug("err: %d\n", err);
 
-	dd->flags &= ~FLAGS_BUSY;
-
-	req->base.complete(&req->base, err);
+	crypto_finalize_request(dd->engine, req, err);
 }
 
 static int omap_aes_crypt_dma_stop(struct omap_aes_dev *dd)
@@ -604,34 +600,25 @@ static int omap_aes_copy_sgs(struct omap_aes_dev *dd)
 }
 
 static int omap_aes_handle_queue(struct omap_aes_dev *dd,
-			       struct ablkcipher_request *req)
+				 struct ablkcipher_request *req)
 {
-	struct crypto_async_request *async_req, *backlog;
-	struct omap_aes_ctx *ctx;
-	struct omap_aes_reqctx *rctx;
-	unsigned long flags;
-	int err, ret = 0, len;
-
-	spin_lock_irqsave(&dd->lock, flags);
 	if (req)
-		ret = ablkcipher_enqueue_request(&dd->queue, req);
-	if (dd->flags & FLAGS_BUSY) {
-		spin_unlock_irqrestore(&dd->lock, flags);
-		return ret;
-	}
-	backlog = crypto_get_backlog(&dd->queue);
-	async_req = crypto_dequeue_request(&dd->queue);
-	if (async_req)
-		dd->flags |= FLAGS_BUSY;
-	spin_unlock_irqrestore(&dd->lock, flags);
+		return crypto_transfer_request_to_engine(dd->engine, req);
 
-	if (!async_req)
-		return ret;
+	return 0;
+}
 
-	if (backlog)
-		backlog->complete(backlog, -EINPROGRESS);
+static int omap_aes_prepare_req(struct crypto_engine *engine,
+				struct ablkcipher_request *req)
+{
+	struct omap_aes_ctx *ctx = crypto_ablkcipher_ctx(
+			crypto_ablkcipher_reqtfm(req));
+	struct omap_aes_dev *dd = omap_aes_find_dev(ctx);
+	struct omap_aes_reqctx *rctx;
+	int len;
 
-	req = ablkcipher_request_cast(async_req);
+	if (!dd)
+		return -ENODEV;
 
 	/* assign new request to device */
 	dd->req = req;
@@ -662,16 +649,20 @@ static int omap_aes_handle_queue(struct omap_aes_dev *dd,
 	dd->ctx = ctx;
 	ctx->dd = dd;
 
-	err = omap_aes_write_ctrl(dd);
-	if (!err)
-		err = omap_aes_crypt_dma_start(dd);
-	if (err) {
-		/* aes_task will not finish it, so do it here */
-		omap_aes_finish_req(dd, err);
-		tasklet_schedule(&dd->queue_task);
-	}
+	return omap_aes_write_ctrl(dd);
+}
 
-	return ret; /* return ret, which is enqueue return value */
+static int omap_aes_crypt_req(struct crypto_engine *engine,
+			      struct ablkcipher_request *req)
+{
+	struct omap_aes_ctx *ctx = crypto_ablkcipher_ctx(
+			crypto_ablkcipher_reqtfm(req));
+	struct omap_aes_dev *dd = omap_aes_find_dev(ctx);
+
+	if (!dd)
+		return -ENODEV;
+
+	return omap_aes_crypt_dma_start(dd);
 }
 
 static void omap_aes_done_task(unsigned long data)
@@ -704,18 +695,10 @@ static void omap_aes_done_task(unsigned long data)
 	}
 
 	omap_aes_finish_req(dd, 0);
-	omap_aes_handle_queue(dd, NULL);
 
 	pr_debug("exit\n");
 }
 
-static void omap_aes_queue_task(unsigned long data)
-{
-	struct omap_aes_dev *dd = (struct omap_aes_dev *)data;
-
-	omap_aes_handle_queue(dd, NULL);
-}
-
 static int omap_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
 {
 	struct omap_aes_ctx *ctx = crypto_ablkcipher_ctx(
@@ -1175,9 +1158,6 @@ static int omap_aes_probe(struct platform_device *pdev)
 	dd->dev = dev;
 	platform_set_drvdata(pdev, dd);
 
-	spin_lock_init(&dd->lock);
-	crypto_init_queue(&dd->queue, OMAP_AES_QUEUE_LENGTH);
-
 	err = (dev->of_node) ? omap_aes_get_res_of(dd, dev, &res) :
 			       omap_aes_get_res_pdev(dd, pdev, &res);
 	if (err)
@@ -1209,7 +1189,6 @@ static int omap_aes_probe(struct platform_device *pdev)
 		 (reg & dd->pdata->minor_mask) >> dd->pdata->minor_shift);
 
 	tasklet_init(&dd->done_task, omap_aes_done_task, (unsigned long)dd);
-	tasklet_init(&dd->queue_task, omap_aes_queue_task, (unsigned long)dd);
 
 	err = omap_aes_dma_init(dd);
 	if (err && AES_REG_IRQ_STATUS(dd) && AES_REG_IRQ_ENABLE(dd)) {
@@ -1250,7 +1229,20 @@ static int omap_aes_probe(struct platform_device *pdev)
 		}
 	}
 
+	/* Initialize crypto engine */
+	dd->engine = crypto_engine_alloc_init(dev, 1);
+	if (!dd->engine)
+		goto err_algs;
+
+	dd->engine->prepare_request = omap_aes_prepare_req;
+	dd->engine->crypt_one_request = omap_aes_crypt_req;
+	err = crypto_engine_start(dd->engine);
+	if (err)
+		goto err_engine;
+
 	return 0;
+err_engine:
+	crypto_engine_exit(dd->engine);
 err_algs:
 	for (i = dd->pdata->algs_info_size - 1; i >= 0; i--)
 		for (j = dd->pdata->algs_info[i].registered - 1; j >= 0; j--)
@@ -1260,7 +1252,6 @@ err_algs:
 		omap_aes_dma_cleanup(dd);
 err_irq:
 	tasklet_kill(&dd->done_task);
-	tasklet_kill(&dd->queue_task);
 	pm_runtime_disable(dev);
 err_res:
 	dd = NULL;
@@ -1286,8 +1277,8 @@ static int omap_aes_remove(struct platform_device *pdev)
 			crypto_unregister_alg(
 					&dd->pdata->algs_info[i].algs_list[j]);
 
+	crypto_engine_exit(dd->engine);
 	tasklet_kill(&dd->done_task);
-	tasklet_kill(&dd->queue_task);
 	omap_aes_dma_cleanup(dd);
 	pm_runtime_disable(dd->dev);
 	dd = NULL;
diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/qat/qat_common/adf_accel_devices.h
index f96d427e502c..5a07208ce778 100644
--- a/drivers/crypto/qat/qat_common/adf_accel_devices.h
+++ b/drivers/crypto/qat/qat_common/adf_accel_devices.h
@@ -55,8 +55,8 @@
 
 #define ADF_DH895XCC_DEVICE_NAME "dh895xcc"
 #define ADF_DH895XCCVF_DEVICE_NAME "dh895xccvf"
-#define ADF_C62X_DEVICE_NAME "c62x"
-#define ADF_C62XVF_DEVICE_NAME "c62xvf"
+#define ADF_C62X_DEVICE_NAME "c6xx"
+#define ADF_C62XVF_DEVICE_NAME "c6xxvf"
 #define ADF_C3XXX_DEVICE_NAME "c3xxx"
 #define ADF_C3XXXVF_DEVICE_NAME "c3xxxvf"
 #define ADF_DH895XCC_PCI_DEVICE_ID 0x435
diff --git a/drivers/crypto/qat/qat_common/adf_aer.c b/drivers/crypto/qat/qat_common/adf_aer.c
index e78a1d7d88fc..b40d9c8dad96 100644
--- a/drivers/crypto/qat/qat_common/adf_aer.c
+++ b/drivers/crypto/qat/qat_common/adf_aer.c
@@ -121,7 +121,6 @@ static void adf_device_reset_worker(struct work_struct *work)
 	adf_dev_restarting_notify(accel_dev);
 	adf_dev_stop(accel_dev);
 	adf_dev_shutdown(accel_dev);
-	adf_dev_restore(accel_dev);
 	if (adf_dev_init(accel_dev) || adf_dev_start(accel_dev)) {
 		/* The device hanged and we can't restart it so stop here */
 		dev_err(&GET_DEV(accel_dev), "Restart device failed\n");
diff --git a/drivers/crypto/qat/qat_common/adf_cfg_user.h b/drivers/crypto/qat/qat_common/adf_cfg_user.h
index ef5988afd4c6..b5484bfa6996 100644
--- a/drivers/crypto/qat/qat_common/adf_cfg_user.h
+++ b/drivers/crypto/qat/qat_common/adf_cfg_user.h
@@ -58,7 +58,7 @@ struct adf_user_cfg_key_val {
 		uint64_t padding3;
 	};
 	enum adf_cfg_val_type type;
-};
+} __packed;
 
 struct adf_user_cfg_section {
 	char name[ADF_CFG_MAX_SECTION_LEN_IN_BYTES];
@@ -70,7 +70,7 @@ struct adf_user_cfg_section {
 		struct adf_user_cfg_section *next;
 		uint64_t padding3;
 	};
-};
+} __packed;
 
 struct adf_user_cfg_ctl_data {
 	union {
@@ -78,5 +78,5 @@ struct adf_user_cfg_ctl_data {
 		uint64_t padding;
 	};
 	uint8_t device_id;
-};
+} __packed;
 #endif
diff --git a/drivers/crypto/qat/qat_common/adf_hw_arbiter.c b/drivers/crypto/qat/qat_common/adf_hw_arbiter.c
index f267d9e42e0b..d7dd18d9bef8 100644
--- a/drivers/crypto/qat/qat_common/adf_hw_arbiter.c
+++ b/drivers/crypto/qat/qat_common/adf_hw_arbiter.c
@@ -49,7 +49,6 @@
 #include "adf_transport_internal.h"
 
 #define ADF_ARB_NUM 4
-#define ADF_ARB_REQ_RING_NUM 8
 #define ADF_ARB_REG_SIZE 0x4
 #define ADF_ARB_WTR_SIZE 0x20
 #define ADF_ARB_OFFSET 0x30000
@@ -64,15 +63,6 @@
 	ADF_CSR_WR(csr_addr, ADF_ARB_RINGSRVARBEN_OFFSET + \
 	(ADF_ARB_REG_SLOT * index), value)
 
-#define WRITE_CSR_ARB_RESPORDERING(csr_addr, index, value) \
-	ADF_CSR_WR(csr_addr, (ADF_ARB_OFFSET + \
-	ADF_ARB_RO_EN_OFFSET) + (ADF_ARB_REG_SIZE * index), value)
-
-#define WRITE_CSR_ARB_WEIGHT(csr_addr, arb, index, value) \
-	ADF_CSR_WR(csr_addr, (ADF_ARB_OFFSET + \
-	ADF_ARB_WTR_OFFSET) + (ADF_ARB_WTR_SIZE * arb) + \
-	(ADF_ARB_REG_SIZE * index), value)
-
 #define WRITE_CSR_ARB_SARCONFIG(csr_addr, index, value) \
 	ADF_CSR_WR(csr_addr, ADF_ARB_OFFSET + \
 	(ADF_ARB_REG_SIZE * index), value)
@@ -99,15 +89,6 @@ int adf_init_arb(struct adf_accel_dev *accel_dev)
 	for (arb = 0; arb < ADF_ARB_NUM; arb++)
 		WRITE_CSR_ARB_SARCONFIG(csr, arb, arb_cfg);
 
-	/* Setup service weighting */
-	for (arb = 0; arb < ADF_ARB_NUM; arb++)
-		for (i = 0; i < ADF_ARB_REQ_RING_NUM; i++)
-			WRITE_CSR_ARB_WEIGHT(csr, arb, i, 0xFFFFFFFF);
-
-	/* Setup ring response ordering */
-	for (i = 0; i < ADF_ARB_REQ_RING_NUM; i++)
-		WRITE_CSR_ARB_RESPORDERING(csr, i, 0xFFFFFFFF);
-
 	/* Setup worker queue registers */
 	for (i = 0; i < hw_data->num_engines; i++)
 		WRITE_CSR_ARB_WQCFG(csr, i, i);
diff --git a/drivers/crypto/qat/qat_common/icp_qat_uclo.h b/drivers/crypto/qat/qat_common/icp_qat_uclo.h
index d97db990955d..5d1ee7e53492 100644
--- a/drivers/crypto/qat/qat_common/icp_qat_uclo.h
+++ b/drivers/crypto/qat/qat_common/icp_qat_uclo.h
@@ -112,27 +112,27 @@ enum icp_qat_uof_mem_region {
 };
 
 enum icp_qat_uof_regtype {
-	ICP_NO_DEST,
-	ICP_GPA_REL,
-	ICP_GPA_ABS,
-	ICP_GPB_REL,
-	ICP_GPB_ABS,
-	ICP_SR_REL,
-	ICP_SR_RD_REL,
-	ICP_SR_WR_REL,
-	ICP_SR_ABS,
-	ICP_SR_RD_ABS,
-	ICP_SR_WR_ABS,
-	ICP_DR_REL,
-	ICP_DR_RD_REL,
-	ICP_DR_WR_REL,
-	ICP_DR_ABS,
-	ICP_DR_RD_ABS,
-	ICP_DR_WR_ABS,
-	ICP_LMEM,
-	ICP_LMEM0,
-	ICP_LMEM1,
-	ICP_NEIGH_REL,
+	ICP_NO_DEST	= 0,
+	ICP_GPA_REL	= 1,
+	ICP_GPA_ABS	= 2,
+	ICP_GPB_REL	= 3,
+	ICP_GPB_ABS	= 4,
+	ICP_SR_REL	= 5,
+	ICP_SR_RD_REL	= 6,
+	ICP_SR_WR_REL	= 7,
+	ICP_SR_ABS	= 8,
+	ICP_SR_RD_ABS	= 9,
+	ICP_SR_WR_ABS	= 10,
+	ICP_DR_REL	= 19,
+	ICP_DR_RD_REL	= 20,
+	ICP_DR_WR_REL	= 21,
+	ICP_DR_ABS	= 22,
+	ICP_DR_RD_ABS	= 23,
+	ICP_DR_WR_ABS	= 24,
+	ICP_LMEM	= 26,
+	ICP_LMEM0	= 27,
+	ICP_LMEM1	= 28,
+	ICP_NEIGH_REL	= 31,
 };
 
 enum icp_qat_css_fwtype {
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index 59e4c3af15ed..1e8852a8a057 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -1064,8 +1064,7 @@ static int qat_alg_aead_init(struct crypto_aead *tfm,
 	if (IS_ERR(ctx->hash_tfm))
 		return PTR_ERR(ctx->hash_tfm);
 	ctx->qat_hash_alg = hash;
-	crypto_aead_set_reqsize(tfm, sizeof(struct aead_request) +
-				     sizeof(struct qat_crypto_request));
+	crypto_aead_set_reqsize(tfm, sizeof(struct qat_crypto_request));
 	return 0;
 }
 
@@ -1114,8 +1113,7 @@ static int qat_alg_ablkcipher_init(struct crypto_tfm *tfm)
 	struct qat_alg_ablkcipher_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	spin_lock_init(&ctx->lock);
-	tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request) +
-					sizeof(struct qat_crypto_request);
+	tfm->crt_ablkcipher.reqsize = sizeof(struct qat_crypto_request);
 	ctx->tfm = tfm;
 	return 0;
 }
diff --git a/drivers/crypto/qat/qat_common/qat_asym_algs.c b/drivers/crypto/qat/qat_common/qat_asym_algs.c
index 51c594fdacdc..e5c0727d4876 100644
--- a/drivers/crypto/qat/qat_common/qat_asym_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_asym_algs.c
@@ -340,14 +340,16 @@ static int qat_rsa_enc(struct akcipher_request *req)
 
 	if (!ret)
 		return -EINPROGRESS;
-unmap_src:
-	if (qat_req->src_align)
-		dma_free_coherent(dev, ctx->key_sz, qat_req->src_align,
-				  qat_req->in.enc.m);
-	else
-		if (!dma_mapping_error(dev, qat_req->in.enc.m))
-			dma_unmap_single(dev, qat_req->in.enc.m, ctx->key_sz,
-					 DMA_TO_DEVICE);
+
+	if (!dma_mapping_error(dev, qat_req->phy_out))
+		dma_unmap_single(dev, qat_req->phy_out,
+				 sizeof(struct qat_rsa_output_params),
+				 DMA_TO_DEVICE);
+unmap_in_params:
+	if (!dma_mapping_error(dev, qat_req->phy_in))
+		dma_unmap_single(dev, qat_req->phy_in,
+				 sizeof(struct qat_rsa_input_params),
+				 DMA_TO_DEVICE);
 unmap_dst:
 	if (qat_req->dst_align)
 		dma_free_coherent(dev, ctx->key_sz, qat_req->dst_align,
@@ -356,15 +358,14 @@ unmap_dst:
 		if (!dma_mapping_error(dev, qat_req->out.enc.c))
 			dma_unmap_single(dev, qat_req->out.enc.c, ctx->key_sz,
 					 DMA_FROM_DEVICE);
-unmap_in_params:
-	if (!dma_mapping_error(dev, qat_req->phy_in))
-		dma_unmap_single(dev, qat_req->phy_in,
-				 sizeof(struct qat_rsa_input_params),
-				 DMA_TO_DEVICE);
-	if (!dma_mapping_error(dev, qat_req->phy_out))
-		dma_unmap_single(dev, qat_req->phy_out,
-				 sizeof(struct qat_rsa_output_params),
-				 DMA_TO_DEVICE);
+unmap_src:
+	if (qat_req->src_align)
+		dma_free_coherent(dev, ctx->key_sz, qat_req->src_align,
+				  qat_req->in.enc.m);
+	else
+		if (!dma_mapping_error(dev, qat_req->in.enc.m))
+			dma_unmap_single(dev, qat_req->in.enc.m, ctx->key_sz,
+					 DMA_TO_DEVICE);
 	return ret;
 }
 
@@ -472,14 +473,16 @@ static int qat_rsa_dec(struct akcipher_request *req)
 
 	if (!ret)
 		return -EINPROGRESS;
-unmap_src:
-	if (qat_req->src_align)
-		dma_free_coherent(dev, ctx->key_sz, qat_req->src_align,
-				  qat_req->in.dec.c);
-	else
-		if (!dma_mapping_error(dev, qat_req->in.dec.c))
-			dma_unmap_single(dev, qat_req->in.dec.c, ctx->key_sz,
-					 DMA_TO_DEVICE);
+
+	if (!dma_mapping_error(dev, qat_req->phy_out))
+		dma_unmap_single(dev, qat_req->phy_out,
+				 sizeof(struct qat_rsa_output_params),
+				 DMA_TO_DEVICE);
+unmap_in_params:
+	if (!dma_mapping_error(dev, qat_req->phy_in))
+		dma_unmap_single(dev, qat_req->phy_in,
+				 sizeof(struct qat_rsa_input_params),
+				 DMA_TO_DEVICE);
 unmap_dst:
 	if (qat_req->dst_align)
 		dma_free_coherent(dev, ctx->key_sz, qat_req->dst_align,
@@ -488,15 +491,14 @@ unmap_dst:
 		if (!dma_mapping_error(dev, qat_req->out.dec.m))
 			dma_unmap_single(dev, qat_req->out.dec.m, ctx->key_sz,
 					 DMA_FROM_DEVICE);
-unmap_in_params:
-	if (!dma_mapping_error(dev, qat_req->phy_in))
-		dma_unmap_single(dev, qat_req->phy_in,
-				 sizeof(struct qat_rsa_input_params),
-				 DMA_TO_DEVICE);
-	if (!dma_mapping_error(dev, qat_req->phy_out))
-		dma_unmap_single(dev, qat_req->phy_out,
-				 sizeof(struct qat_rsa_output_params),
-				 DMA_TO_DEVICE);
+unmap_src:
+	if (qat_req->src_align)
+		dma_free_coherent(dev, ctx->key_sz, qat_req->src_align,
+				  qat_req->in.dec.c);
+	else
+		if (!dma_mapping_error(dev, qat_req->in.dec.c))
+			dma_unmap_single(dev, qat_req->in.dec.c, ctx->key_sz,
+					 DMA_TO_DEVICE);
 	return ret;
 }
 
diff --git a/drivers/crypto/qat/qat_common/qat_uclo.c b/drivers/crypto/qat/qat_common/qat_uclo.c
index 25d15f19c2b3..9b961b37a282 100644
--- a/drivers/crypto/qat/qat_common/qat_uclo.c
+++ b/drivers/crypto/qat/qat_common/qat_uclo.c
@@ -688,7 +688,7 @@ static int qat_uclo_map_ae(struct icp_qat_fw_loader_handle *handle, int max_ae)
 	int mflag = 0;
 	struct icp_qat_uclo_objhandle *obj_handle = handle->obj_handle;
 
-	for (ae = 0; ae <= max_ae; ae++) {
+	for (ae = 0; ae < max_ae; ae++) {
 		if (!test_bit(ae,
 			      (unsigned long *)&handle->hal_handle->ae_mask))
 			continue;
diff --git a/drivers/crypto/rockchip/Makefile b/drivers/crypto/rockchip/Makefile
index 7051c6c715f3..30f91297b4b6 100644
--- a/drivers/crypto/rockchip/Makefile
+++ b/drivers/crypto/rockchip/Makefile
@@ -1,3 +1,4 @@
 obj-$(CONFIG_CRYPTO_DEV_ROCKCHIP) += rk_crypto.o
 rk_crypto-objs := rk3288_crypto.o \
 		  rk3288_crypto_ablkcipher.o \
+		  rk3288_crypto_ahash.o
diff --git a/drivers/crypto/rockchip/rk3288_crypto.c b/drivers/crypto/rockchip/rk3288_crypto.c
index da9c73dce4af..af508258d2ea 100644
--- a/drivers/crypto/rockchip/rk3288_crypto.c
+++ b/drivers/crypto/rockchip/rk3288_crypto.c
@@ -208,6 +208,8 @@ static void rk_crypto_tasklet_cb(unsigned long data)
 
 	if (crypto_tfm_alg_type(async_req->tfm) == CRYPTO_ALG_TYPE_ABLKCIPHER)
 		dev->ablk_req = ablkcipher_request_cast(async_req);
+	else
+		dev->ahash_req = ahash_request_cast(async_req);
 	err = dev->start(dev);
 	if (err)
 		dev->complete(dev, err);
@@ -220,6 +222,9 @@ static struct rk_crypto_tmp *rk_cipher_algs[] = {
 	&rk_cbc_des_alg,
 	&rk_ecb_des3_ede_alg,
 	&rk_cbc_des3_ede_alg,
+	&rk_ahash_sha1,
+	&rk_ahash_sha256,
+	&rk_ahash_md5,
 };
 
 static int rk_crypto_register(struct rk_crypto_info *crypto_info)
@@ -229,15 +234,24 @@ static int rk_crypto_register(struct rk_crypto_info *crypto_info)
 
 	for (i = 0; i < ARRAY_SIZE(rk_cipher_algs); i++) {
 		rk_cipher_algs[i]->dev = crypto_info;
-		err = crypto_register_alg(&rk_cipher_algs[i]->alg);
+		if (rk_cipher_algs[i]->type == ALG_TYPE_CIPHER)
+			err = crypto_register_alg(
+					&rk_cipher_algs[i]->alg.crypto);
+		else
+			err = crypto_register_ahash(
+					&rk_cipher_algs[i]->alg.hash);
 		if (err)
 			goto err_cipher_algs;
 	}
 	return 0;
 
 err_cipher_algs:
-	for (k = 0; k < i; k++)
-		crypto_unregister_alg(&rk_cipher_algs[k]->alg);
+	for (k = 0; k < i; k++) {
+		if (rk_cipher_algs[i]->type == ALG_TYPE_CIPHER)
+			crypto_unregister_alg(&rk_cipher_algs[k]->alg.crypto);
+		else
+			crypto_unregister_ahash(&rk_cipher_algs[i]->alg.hash);
+	}
 	return err;
 }
 
@@ -245,8 +259,12 @@ static void rk_crypto_unregister(void)
 {
 	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(rk_cipher_algs); i++)
-		crypto_unregister_alg(&rk_cipher_algs[i]->alg);
+	for (i = 0; i < ARRAY_SIZE(rk_cipher_algs); i++) {
+		if (rk_cipher_algs[i]->type == ALG_TYPE_CIPHER)
+			crypto_unregister_alg(&rk_cipher_algs[i]->alg.crypto);
+		else
+			crypto_unregister_ahash(&rk_cipher_algs[i]->alg.hash);
+	}
 }
 
 static void rk_crypto_action(void *data)
diff --git a/drivers/crypto/rockchip/rk3288_crypto.h b/drivers/crypto/rockchip/rk3288_crypto.h
index e499c2c6c903..d7b71fea320b 100644
--- a/drivers/crypto/rockchip/rk3288_crypto.h
+++ b/drivers/crypto/rockchip/rk3288_crypto.h
@@ -6,6 +6,10 @@
 #include <crypto/algapi.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
+#include <crypto/internal/hash.h>
+
+#include <crypto/md5.h>
+#include <crypto/sha.h>
 
 #define _SBF(v, f)			((v) << (f))
 
@@ -149,6 +153,28 @@
 #define RK_CRYPTO_TDES_KEY3_0		0x0130
 #define RK_CRYPTO_TDES_KEY3_1		0x0134
 
+/* HASH */
+#define RK_CRYPTO_HASH_CTRL		0x0180
+#define RK_CRYPTO_HASH_SWAP_DO		BIT(3)
+#define RK_CRYPTO_HASH_SWAP_DI		BIT(2)
+#define RK_CRYPTO_HASH_SHA1		_SBF(0x00, 0)
+#define RK_CRYPTO_HASH_MD5		_SBF(0x01, 0)
+#define RK_CRYPTO_HASH_SHA256		_SBF(0x02, 0)
+#define RK_CRYPTO_HASH_PRNG		_SBF(0x03, 0)
+
+#define RK_CRYPTO_HASH_STS		0x0184
+#define RK_CRYPTO_HASH_DONE		BIT(0)
+
+#define RK_CRYPTO_HASH_MSG_LEN		0x0188
+#define RK_CRYPTO_HASH_DOUT_0		0x018c
+#define RK_CRYPTO_HASH_DOUT_1		0x0190
+#define RK_CRYPTO_HASH_DOUT_2		0x0194
+#define RK_CRYPTO_HASH_DOUT_3		0x0198
+#define RK_CRYPTO_HASH_DOUT_4		0x019c
+#define RK_CRYPTO_HASH_DOUT_5		0x01a0
+#define RK_CRYPTO_HASH_DOUT_6		0x01a4
+#define RK_CRYPTO_HASH_DOUT_7		0x01a8
+
 #define CRYPTO_READ(dev, offset)		  \
 		readl_relaxed(((dev)->reg + (offset)))
 #define CRYPTO_WRITE(dev, offset, val)	  \
@@ -166,6 +192,7 @@ struct rk_crypto_info {
 	struct crypto_queue		queue;
 	struct tasklet_struct		crypto_tasklet;
 	struct ablkcipher_request	*ablk_req;
+	struct ahash_request		*ahash_req;
 	/* device lock */
 	spinlock_t			lock;
 
@@ -195,15 +222,36 @@ struct rk_crypto_info {
 	void (*unload_data)(struct rk_crypto_info *dev);
 };
 
+/* the private variable of hash */
+struct rk_ahash_ctx {
+	struct rk_crypto_info		*dev;
+	/* for fallback */
+	struct crypto_ahash		*fallback_tfm;
+};
+
+/* the privete variable of hash for fallback */
+struct rk_ahash_rctx {
+	struct ahash_request		fallback_req;
+};
+
 /* the private variable of cipher */
 struct rk_cipher_ctx {
 	struct rk_crypto_info		*dev;
 	unsigned int			keylen;
 };
 
+enum alg_type {
+	ALG_TYPE_HASH,
+	ALG_TYPE_CIPHER,
+};
+
 struct rk_crypto_tmp {
-	struct rk_crypto_info *dev;
-	struct crypto_alg alg;
+	struct rk_crypto_info		*dev;
+	union {
+		struct crypto_alg	crypto;
+		struct ahash_alg	hash;
+	} alg;
+	enum alg_type			type;
 };
 
 extern struct rk_crypto_tmp rk_ecb_aes_alg;
@@ -213,4 +261,8 @@ extern struct rk_crypto_tmp rk_cbc_des_alg;
 extern struct rk_crypto_tmp rk_ecb_des3_ede_alg;
 extern struct rk_crypto_tmp rk_cbc_des3_ede_alg;
 
+extern struct rk_crypto_tmp rk_ahash_sha1;
+extern struct rk_crypto_tmp rk_ahash_sha256;
+extern struct rk_crypto_tmp rk_ahash_md5;
+
 #endif
diff --git a/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c b/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c
index d98b681f6c06..b5a3afe222e4 100644
--- a/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c
+++ b/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c
@@ -336,7 +336,7 @@ static int rk_ablk_cra_init(struct crypto_tfm *tfm)
 	struct crypto_alg *alg = tfm->__crt_alg;
 	struct rk_crypto_tmp *algt;
 
-	algt = container_of(alg, struct rk_crypto_tmp, alg);
+	algt = container_of(alg, struct rk_crypto_tmp, alg.crypto);
 
 	ctx->dev = algt->dev;
 	ctx->dev->align_size = crypto_tfm_alg_alignmask(tfm) + 1;
@@ -357,7 +357,8 @@ static void rk_ablk_cra_exit(struct crypto_tfm *tfm)
 }
 
 struct rk_crypto_tmp rk_ecb_aes_alg = {
-	.alg = {
+	.type = ALG_TYPE_CIPHER,
+	.alg.crypto = {
 		.cra_name		= "ecb(aes)",
 		.cra_driver_name	= "ecb-aes-rk",
 		.cra_priority		= 300,
@@ -381,7 +382,8 @@ struct rk_crypto_tmp rk_ecb_aes_alg = {
 };
 
 struct rk_crypto_tmp rk_cbc_aes_alg = {
-	.alg = {
+	.type = ALG_TYPE_CIPHER,
+	.alg.crypto = {
 		.cra_name		= "cbc(aes)",
 		.cra_driver_name	= "cbc-aes-rk",
 		.cra_priority		= 300,
@@ -406,7 +408,8 @@ struct rk_crypto_tmp rk_cbc_aes_alg = {
 };
 
 struct rk_crypto_tmp rk_ecb_des_alg = {
-	.alg = {
+	.type = ALG_TYPE_CIPHER,
+	.alg.crypto = {
 		.cra_name		= "ecb(des)",
 		.cra_driver_name	= "ecb-des-rk",
 		.cra_priority		= 300,
@@ -430,7 +433,8 @@ struct rk_crypto_tmp rk_ecb_des_alg = {
 };
 
 struct rk_crypto_tmp rk_cbc_des_alg = {
-	.alg = {
+	.type = ALG_TYPE_CIPHER,
+	.alg.crypto = {
 		.cra_name		= "cbc(des)",
 		.cra_driver_name	= "cbc-des-rk",
 		.cra_priority		= 300,
@@ -455,7 +459,8 @@ struct rk_crypto_tmp rk_cbc_des_alg = {
 };
 
 struct rk_crypto_tmp rk_ecb_des3_ede_alg = {
-	.alg = {
+	.type = ALG_TYPE_CIPHER,
+	.alg.crypto = {
 		.cra_name		= "ecb(des3_ede)",
 		.cra_driver_name	= "ecb-des3-ede-rk",
 		.cra_priority		= 300,
@@ -480,7 +485,8 @@ struct rk_crypto_tmp rk_ecb_des3_ede_alg = {
 };
 
 struct rk_crypto_tmp rk_cbc_des3_ede_alg = {
-	.alg = {
+	.type = ALG_TYPE_CIPHER,
+	.alg.crypto = {
 		.cra_name		= "cbc(des3_ede)",
 		.cra_driver_name	= "cbc-des3-ede-rk",
 		.cra_priority		= 300,
diff --git a/drivers/crypto/rockchip/rk3288_crypto_ahash.c b/drivers/crypto/rockchip/rk3288_crypto_ahash.c
new file mode 100644
index 000000000000..718588219f75
--- /dev/null
+++ b/drivers/crypto/rockchip/rk3288_crypto_ahash.c
@@ -0,0 +1,404 @@
+/*
+ * Crypto acceleration support for Rockchip RK3288
+ *
+ * Copyright (c) 2015, Fuzhou Rockchip Electronics Co., Ltd
+ *
+ * Author: Zain Wang <zain.wang@rock-chips.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * Some ideas are from marvell/cesa.c and s5p-sss.c driver.
+ */
+#include "rk3288_crypto.h"
+
+/*
+ * IC can not process zero message hash,
+ * so we put the fixed hash out when met zero message.
+ */
+
+static int zero_message_process(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	int rk_digest_size = crypto_ahash_digestsize(tfm);
+
+	switch (rk_digest_size) {
+	case SHA1_DIGEST_SIZE:
+		memcpy(req->result, sha1_zero_message_hash, rk_digest_size);
+		break;
+	case SHA256_DIGEST_SIZE:
+		memcpy(req->result, sha256_zero_message_hash, rk_digest_size);
+		break;
+	case MD5_DIGEST_SIZE:
+		memcpy(req->result, md5_zero_message_hash, rk_digest_size);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void rk_ahash_crypto_complete(struct rk_crypto_info *dev, int err)
+{
+	if (dev->ahash_req->base.complete)
+		dev->ahash_req->base.complete(&dev->ahash_req->base, err);
+}
+
+static void rk_ahash_reg_init(struct rk_crypto_info *dev)
+{
+	int reg_status = 0;
+
+	reg_status = CRYPTO_READ(dev, RK_CRYPTO_CTRL) |
+		     RK_CRYPTO_HASH_FLUSH | _SBF(0xffff, 16);
+	CRYPTO_WRITE(dev, RK_CRYPTO_CTRL, reg_status);
+
+	reg_status = CRYPTO_READ(dev, RK_CRYPTO_CTRL);
+	reg_status &= (~RK_CRYPTO_HASH_FLUSH);
+	reg_status |= _SBF(0xffff, 16);
+	CRYPTO_WRITE(dev, RK_CRYPTO_CTRL, reg_status);
+
+	memset_io(dev->reg + RK_CRYPTO_HASH_DOUT_0, 0, 32);
+
+	CRYPTO_WRITE(dev, RK_CRYPTO_INTENA, RK_CRYPTO_HRDMA_ERR_ENA |
+					    RK_CRYPTO_HRDMA_DONE_ENA);
+
+	CRYPTO_WRITE(dev, RK_CRYPTO_INTSTS, RK_CRYPTO_HRDMA_ERR_INT |
+					    RK_CRYPTO_HRDMA_DONE_INT);
+
+	CRYPTO_WRITE(dev, RK_CRYPTO_HASH_CTRL, dev->mode |
+					       RK_CRYPTO_HASH_SWAP_DO);
+
+	CRYPTO_WRITE(dev, RK_CRYPTO_CONF, RK_CRYPTO_BYTESWAP_HRFIFO |
+					  RK_CRYPTO_BYTESWAP_BRFIFO |
+					  RK_CRYPTO_BYTESWAP_BTFIFO);
+
+	CRYPTO_WRITE(dev, RK_CRYPTO_HASH_MSG_LEN, dev->total);
+}
+
+static int rk_ahash_init(struct ahash_request *req)
+{
+	struct rk_ahash_rctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct rk_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+
+	ahash_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm);
+	rctx->fallback_req.base.flags = req->base.flags &
+					CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	return crypto_ahash_init(&rctx->fallback_req);
+}
+
+static int rk_ahash_update(struct ahash_request *req)
+{
+	struct rk_ahash_rctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct rk_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+
+	ahash_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm);
+	rctx->fallback_req.base.flags = req->base.flags &
+					CRYPTO_TFM_REQ_MAY_SLEEP;
+	rctx->fallback_req.nbytes = req->nbytes;
+	rctx->fallback_req.src = req->src;
+
+	return crypto_ahash_update(&rctx->fallback_req);
+}
+
+static int rk_ahash_final(struct ahash_request *req)
+{
+	struct rk_ahash_rctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct rk_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+
+	ahash_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm);
+	rctx->fallback_req.base.flags = req->base.flags &
+					CRYPTO_TFM_REQ_MAY_SLEEP;
+	rctx->fallback_req.result = req->result;
+
+	return crypto_ahash_final(&rctx->fallback_req);
+}
+
+static int rk_ahash_finup(struct ahash_request *req)
+{
+	struct rk_ahash_rctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct rk_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+
+	ahash_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm);
+	rctx->fallback_req.base.flags = req->base.flags &
+					CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	rctx->fallback_req.nbytes = req->nbytes;
+	rctx->fallback_req.src = req->src;
+	rctx->fallback_req.result = req->result;
+
+	return crypto_ahash_finup(&rctx->fallback_req);
+}
+
+static int rk_ahash_import(struct ahash_request *req, const void *in)
+{
+	struct rk_ahash_rctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct rk_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+
+	ahash_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm);
+	rctx->fallback_req.base.flags = req->base.flags &
+					CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	return crypto_ahash_import(&rctx->fallback_req, in);
+}
+
+static int rk_ahash_export(struct ahash_request *req, void *out)
+{
+	struct rk_ahash_rctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct rk_ahash_ctx *ctx = crypto_ahash_ctx(tfm);
+
+	ahash_request_set_tfm(&rctx->fallback_req, ctx->fallback_tfm);
+	rctx->fallback_req.base.flags = req->base.flags &
+					CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	return crypto_ahash_export(&rctx->fallback_req, out);
+}
+
+static int rk_ahash_digest(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct rk_ahash_ctx *tctx = crypto_tfm_ctx(req->base.tfm);
+	struct rk_crypto_info *dev = NULL;
+	unsigned long flags;
+	int ret;
+
+	if (!req->nbytes)
+		return zero_message_process(req);
+
+	dev = tctx->dev;
+	dev->total = req->nbytes;
+	dev->left_bytes = req->nbytes;
+	dev->aligned = 0;
+	dev->mode = 0;
+	dev->align_size = 4;
+	dev->sg_dst = NULL;
+	dev->sg_src = req->src;
+	dev->first = req->src;
+	dev->nents = sg_nents(req->src);
+
+	switch (crypto_ahash_digestsize(tfm)) {
+	case SHA1_DIGEST_SIZE:
+		dev->mode = RK_CRYPTO_HASH_SHA1;
+		break;
+	case SHA256_DIGEST_SIZE:
+		dev->mode = RK_CRYPTO_HASH_SHA256;
+		break;
+	case MD5_DIGEST_SIZE:
+		dev->mode = RK_CRYPTO_HASH_MD5;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	rk_ahash_reg_init(dev);
+
+	spin_lock_irqsave(&dev->lock, flags);
+	ret = crypto_enqueue_request(&dev->queue, &req->base);
+	spin_unlock_irqrestore(&dev->lock, flags);
+
+	tasklet_schedule(&dev->crypto_tasklet);
+
+	/*
+	 * it will take some time to process date after last dma transmission.
+	 *
+	 * waiting time is relative with the last date len,
+	 * so cannot set a fixed time here.
+	 * 10-50 makes system not call here frequently wasting
+	 * efficiency, and make it response quickly when dma
+	 * complete.
+	 */
+	while (!CRYPTO_READ(dev, RK_CRYPTO_HASH_STS))
+		usleep_range(10, 50);
+
+	memcpy_fromio(req->result, dev->reg + RK_CRYPTO_HASH_DOUT_0,
+		      crypto_ahash_digestsize(tfm));
+
+	return 0;
+}
+
+static void crypto_ahash_dma_start(struct rk_crypto_info *dev)
+{
+	CRYPTO_WRITE(dev, RK_CRYPTO_HRDMAS, dev->addr_in);
+	CRYPTO_WRITE(dev, RK_CRYPTO_HRDMAL, (dev->count + 3) / 4);
+	CRYPTO_WRITE(dev, RK_CRYPTO_CTRL, RK_CRYPTO_HASH_START |
+					  (RK_CRYPTO_HASH_START << 16));
+}
+
+static int rk_ahash_set_data_start(struct rk_crypto_info *dev)
+{
+	int err;
+
+	err = dev->load_data(dev, dev->sg_src, NULL);
+	if (!err)
+		crypto_ahash_dma_start(dev);
+	return err;
+}
+
+static int rk_ahash_start(struct rk_crypto_info *dev)
+{
+	return rk_ahash_set_data_start(dev);
+}
+
+static int rk_ahash_crypto_rx(struct rk_crypto_info *dev)
+{
+	int err = 0;
+
+	dev->unload_data(dev);
+	if (dev->left_bytes) {
+		if (dev->aligned) {
+			if (sg_is_last(dev->sg_src)) {
+				dev_warn(dev->dev, "[%s:%d], Lack of data\n",
+					 __func__, __LINE__);
+				err = -ENOMEM;
+				goto out_rx;
+			}
+			dev->sg_src = sg_next(dev->sg_src);
+		}
+		err = rk_ahash_set_data_start(dev);
+	} else {
+		dev->complete(dev, 0);
+	}
+
+out_rx:
+	return err;
+}
+
+static int rk_cra_hash_init(struct crypto_tfm *tfm)
+{
+	struct rk_ahash_ctx *tctx = crypto_tfm_ctx(tfm);
+	struct rk_crypto_tmp *algt;
+	struct ahash_alg *alg = __crypto_ahash_alg(tfm->__crt_alg);
+
+	const char *alg_name = crypto_tfm_alg_name(tfm);
+
+	algt = container_of(alg, struct rk_crypto_tmp, alg.hash);
+
+	tctx->dev = algt->dev;
+	tctx->dev->addr_vir = (void *)__get_free_page(GFP_KERNEL);
+	if (!tctx->dev->addr_vir) {
+		dev_err(tctx->dev->dev, "failed to kmalloc for addr_vir\n");
+		return -ENOMEM;
+	}
+	tctx->dev->start = rk_ahash_start;
+	tctx->dev->update = rk_ahash_crypto_rx;
+	tctx->dev->complete = rk_ahash_crypto_complete;
+
+	/* for fallback */
+	tctx->fallback_tfm = crypto_alloc_ahash(alg_name, 0,
+					       CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(tctx->fallback_tfm)) {
+		dev_err(tctx->dev->dev, "Could not load fallback driver.\n");
+		return PTR_ERR(tctx->fallback_tfm);
+	}
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				 sizeof(struct rk_ahash_rctx) +
+				 crypto_ahash_reqsize(tctx->fallback_tfm));
+
+	return tctx->dev->enable_clk(tctx->dev);
+}
+
+static void rk_cra_hash_exit(struct crypto_tfm *tfm)
+{
+	struct rk_ahash_ctx *tctx = crypto_tfm_ctx(tfm);
+
+	free_page((unsigned long)tctx->dev->addr_vir);
+	return tctx->dev->disable_clk(tctx->dev);
+}
+
+struct rk_crypto_tmp rk_ahash_sha1 = {
+	.type = ALG_TYPE_HASH,
+	.alg.hash = {
+		.init = rk_ahash_init,
+		.update = rk_ahash_update,
+		.final = rk_ahash_final,
+		.finup = rk_ahash_finup,
+		.export = rk_ahash_export,
+		.import = rk_ahash_import,
+		.digest = rk_ahash_digest,
+		.halg = {
+			 .digestsize = SHA1_DIGEST_SIZE,
+			 .statesize = sizeof(struct sha1_state),
+			 .base = {
+				  .cra_name = "sha1",
+				  .cra_driver_name = "rk-sha1",
+				  .cra_priority = 300,
+				  .cra_flags = CRYPTO_ALG_ASYNC |
+					       CRYPTO_ALG_NEED_FALLBACK,
+				  .cra_blocksize = SHA1_BLOCK_SIZE,
+				  .cra_ctxsize = sizeof(struct rk_ahash_ctx),
+				  .cra_alignmask = 3,
+				  .cra_init = rk_cra_hash_init,
+				  .cra_exit = rk_cra_hash_exit,
+				  .cra_module = THIS_MODULE,
+				  }
+			 }
+	}
+};
+
+struct rk_crypto_tmp rk_ahash_sha256 = {
+	.type = ALG_TYPE_HASH,
+	.alg.hash = {
+		.init = rk_ahash_init,
+		.update = rk_ahash_update,
+		.final = rk_ahash_final,
+		.finup = rk_ahash_finup,
+		.export = rk_ahash_export,
+		.import = rk_ahash_import,
+		.digest = rk_ahash_digest,
+		.halg = {
+			 .digestsize = SHA256_DIGEST_SIZE,
+			 .statesize = sizeof(struct sha256_state),
+			 .base = {
+				  .cra_name = "sha256",
+				  .cra_driver_name = "rk-sha256",
+				  .cra_priority = 300,
+				  .cra_flags = CRYPTO_ALG_ASYNC |
+					       CRYPTO_ALG_NEED_FALLBACK,
+				  .cra_blocksize = SHA256_BLOCK_SIZE,
+				  .cra_ctxsize = sizeof(struct rk_ahash_ctx),
+				  .cra_alignmask = 3,
+				  .cra_init = rk_cra_hash_init,
+				  .cra_exit = rk_cra_hash_exit,
+				  .cra_module = THIS_MODULE,
+				  }
+			 }
+	}
+};
+
+struct rk_crypto_tmp rk_ahash_md5 = {
+	.type = ALG_TYPE_HASH,
+	.alg.hash = {
+		.init = rk_ahash_init,
+		.update = rk_ahash_update,
+		.final = rk_ahash_final,
+		.finup = rk_ahash_finup,
+		.export = rk_ahash_export,
+		.import = rk_ahash_import,
+		.digest = rk_ahash_digest,
+		.halg = {
+			 .digestsize = MD5_DIGEST_SIZE,
+			 .statesize = sizeof(struct md5_state),
+			 .base = {
+				  .cra_name = "md5",
+				  .cra_driver_name = "rk-md5",
+				  .cra_priority = 300,
+				  .cra_flags = CRYPTO_ALG_ASYNC |
+					       CRYPTO_ALG_NEED_FALLBACK,
+				  .cra_blocksize = SHA1_BLOCK_SIZE,
+				  .cra_ctxsize = sizeof(struct rk_ahash_ctx),
+				  .cra_alignmask = 3,
+				  .cra_init = rk_cra_hash_init,
+				  .cra_exit = rk_cra_hash_exit,
+				  .cra_module = THIS_MODULE,
+				  }
+			}
+	}
+};
diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c
index f214a8755827..5f161a9777e3 100644
--- a/drivers/crypto/s5p-sss.c
+++ b/drivers/crypto/s5p-sss.c
@@ -224,6 +224,7 @@ static inline struct samsung_aes_variant *find_s5p_sss_version
 {
 	if (IS_ENABLED(CONFIG_OF) && (pdev->dev.of_node)) {
 		const struct of_device_id *match;
+
 		match = of_match_node(s5p_sss_dt_match,
 					pdev->dev.of_node);
 		return (struct samsung_aes_variant *)match->data;
@@ -382,7 +383,7 @@ static void s5p_set_aes(struct s5p_aes_dev *dev,
 	void __iomem *keystart;
 
 	if (iv)
-		memcpy(dev->aes_ioaddr + SSS_REG_AES_IV_DATA(0), iv, 0x10);
+		memcpy_toio(dev->aes_ioaddr + SSS_REG_AES_IV_DATA(0), iv, 0x10);
 
 	if (keylen == AES_KEYSIZE_256)
 		keystart = dev->aes_ioaddr + SSS_REG_AES_KEY_DATA(0);
@@ -391,13 +392,12 @@ static void s5p_set_aes(struct s5p_aes_dev *dev,
 	else
 		keystart = dev->aes_ioaddr + SSS_REG_AES_KEY_DATA(4);
 
-	memcpy(keystart, key, keylen);
+	memcpy_toio(keystart, key, keylen);
 }
 
 static void s5p_aes_crypt_start(struct s5p_aes_dev *dev, unsigned long mode)
 {
 	struct ablkcipher_request  *req = dev->req;
-
 	uint32_t                    aes_control;
 	int                         err;
 	unsigned long               flags;
@@ -518,7 +518,7 @@ static int s5p_aes_crypt(struct ablkcipher_request *req, unsigned long mode)
 	struct s5p_aes_dev         *dev    = ctx->dev;
 
 	if (!IS_ALIGNED(req->nbytes, AES_BLOCK_SIZE)) {
-		pr_err("request size is not exact amount of AES blocks\n");
+		dev_err(dev->dev, "request size is not exact amount of AES blocks\n");
 		return -EINVAL;
 	}
 
@@ -566,7 +566,7 @@ static int s5p_aes_cbc_decrypt(struct ablkcipher_request *req)
 
 static int s5p_aes_cra_init(struct crypto_tfm *tfm)
 {
-	struct s5p_aes_ctx  *ctx = crypto_tfm_ctx(tfm);
+	struct s5p_aes_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	ctx->dev = s5p_dev;
 	tfm->crt_ablkcipher.reqsize = sizeof(struct s5p_aes_reqctx);
@@ -701,7 +701,7 @@ static int s5p_aes_probe(struct platform_device *pdev)
 			goto err_algs;
 	}
 
-	pr_info("s5p-sss driver registered\n");
+	dev_info(dev, "s5p-sss driver registered\n");
 
 	return 0;
 
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index 6c4f91c5e6b3..c3f3d89e4831 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -182,7 +182,6 @@ struct sahara_sha_reqctx {
 	u8			buf[SAHARA_MAX_SHA_BLOCK_SIZE];
 	u8			rembuf[SAHARA_MAX_SHA_BLOCK_SIZE];
 	u8			context[SHA256_DIGEST_SIZE + 4];
-	struct mutex		mutex;
 	unsigned int		mode;
 	unsigned int		digest_size;
 	unsigned int		context_size;
@@ -1096,7 +1095,6 @@ static int sahara_sha_enqueue(struct ahash_request *req, int last)
 	if (!req->nbytes && !last)
 		return 0;
 
-	mutex_lock(&rctx->mutex);
 	rctx->last = last;
 
 	if (!rctx->active) {
@@ -1109,7 +1107,6 @@ static int sahara_sha_enqueue(struct ahash_request *req, int last)
 	mutex_unlock(&dev->queue_mutex);
 
 	wake_up_process(dev->kthread);
-	mutex_unlock(&rctx->mutex);
 
 	return ret;
 }
@@ -1137,8 +1134,6 @@ static int sahara_sha_init(struct ahash_request *req)
 	rctx->context_size = rctx->digest_size + 4;
 	rctx->active = 0;
 
-	mutex_init(&rctx->mutex);
-
 	return 0;
 }
 
@@ -1167,26 +1162,18 @@ static int sahara_sha_digest(struct ahash_request *req)
 
 static int sahara_sha_export(struct ahash_request *req, void *out)
 {
-	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
-	struct sahara_ctx *ctx = crypto_ahash_ctx(ahash);
 	struct sahara_sha_reqctx *rctx = ahash_request_ctx(req);
 
-	memcpy(out, ctx, sizeof(struct sahara_ctx));
-	memcpy(out + sizeof(struct sahara_sha_reqctx), rctx,
-	       sizeof(struct sahara_sha_reqctx));
+	memcpy(out, rctx, sizeof(struct sahara_sha_reqctx));
 
 	return 0;
 }
 
 static int sahara_sha_import(struct ahash_request *req, const void *in)
 {
-	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
-	struct sahara_ctx *ctx = crypto_ahash_ctx(ahash);
 	struct sahara_sha_reqctx *rctx = ahash_request_ctx(req);
 
-	memcpy(ctx, in, sizeof(struct sahara_ctx));
-	memcpy(rctx, in + sizeof(struct sahara_sha_reqctx),
-	       sizeof(struct sahara_sha_reqctx));
+	memcpy(rctx, in, sizeof(struct sahara_sha_reqctx));
 
 	return 0;
 }
@@ -1272,6 +1259,7 @@ static struct ahash_alg sha_v3_algs[] = {
 	.export		= sahara_sha_export,
 	.import		= sahara_sha_import,
 	.halg.digestsize	= SHA1_DIGEST_SIZE,
+	.halg.statesize         = sizeof(struct sahara_sha_reqctx),
 	.halg.base	= {
 		.cra_name		= "sha1",
 		.cra_driver_name	= "sahara-sha1",
@@ -1299,6 +1287,7 @@ static struct ahash_alg sha_v4_algs[] = {
 	.export		= sahara_sha_export,
 	.import		= sahara_sha_import,
 	.halg.digestsize	= SHA256_DIGEST_SIZE,
+	.halg.statesize         = sizeof(struct sahara_sha_reqctx),
 	.halg.base	= {
 		.cra_name		= "sha256",
 		.cra_driver_name	= "sahara-sha256",
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
index a19ee127edca..7be3fbcd8d78 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
@@ -251,11 +251,10 @@ static int sun4i_ss_cipher_poll(struct ablkcipher_request *areq)
 		spaces = readl(ss->base + SS_FCSR);
 		rx_cnt = SS_RXFIFO_SPACES(spaces);
 		tx_cnt = SS_TXFIFO_SPACES(spaces);
-		dev_dbg(ss->dev, "%x %u/%u %u/%u cnt=%u %u/%u %u/%u cnt=%u %u %u\n",
+		dev_dbg(ss->dev, "%x %u/%u %u/%u cnt=%u %u/%u %u/%u cnt=%u %u\n",
 			mode,
 			oi, mi.length, ileft, areq->nbytes, rx_cnt,
-			oo, mo.length, oleft, areq->nbytes, tx_cnt,
-			todo, ob);
+			oo, mo.length, oleft, areq->nbytes, tx_cnt, ob);
 
 		if (tx_cnt == 0)
 			continue;
diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c
index 4c243c1ffc7f..790f7cadc1ed 100644
--- a/drivers/crypto/ux500/cryp/cryp_core.c
+++ b/drivers/crypto/ux500/cryp/cryp_core.c
@@ -1440,9 +1440,9 @@ static int ux500_cryp_probe(struct platform_device *pdev)
 
 	device_data->phybase = res->start;
 	device_data->base = devm_ioremap_resource(dev, res);
-	if (!device_data->base) {
+	if (IS_ERR(device_data->base)) {
 		dev_err(dev, "[%s]: ioremap failed!", __func__);
-		ret = -ENOMEM;
+		ret = PTR_ERR(device_data->base);
 		goto out;
 	}
 
diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index d6fdc583ce5d..574e87c7f2b8 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -1659,9 +1659,9 @@ static int ux500_hash_probe(struct platform_device *pdev)
 
 	device_data->phybase = res->start;
 	device_data->base = devm_ioremap_resource(dev, res);
-	if (!device_data->base) {
+	if (IS_ERR(device_data->base)) {
 		dev_err(dev, "%s: ioremap() failed!\n", __func__);
-		ret = -ENOMEM;
+		ret = PTR_ERR(device_data->base);
 		goto out;
 	}
 	spin_lock_init(&device_data->ctx_lock);
diff --git a/drivers/devfreq/tegra-devfreq.c b/drivers/devfreq/tegra-devfreq.c
index 848b93ee930f..fe9dce0245bf 100644
--- a/drivers/devfreq/tegra-devfreq.c
+++ b/drivers/devfreq/tegra-devfreq.c
@@ -500,6 +500,8 @@ static int tegra_devfreq_target(struct device *dev, unsigned long *freq,
 	clk_set_min_rate(tegra->emc_clock, rate);
 	clk_set_rate(tegra->emc_clock, 0);
 
+	*freq = rate;
+
 	return 0;
 }
 
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 64f5d1bdbb48..8e304b1befc5 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -176,6 +176,7 @@
 #define AT_XDMAC_MAX_CHAN	0x20
 #define AT_XDMAC_MAX_CSIZE	16	/* 16 data */
 #define AT_XDMAC_MAX_DWIDTH	8	/* 64 bits */
+#define AT_XDMAC_RESIDUE_MAX_RETRIES	5
 
 #define AT_XDMAC_DMA_BUSWIDTHS\
 	(BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) |\
@@ -1395,8 +1396,8 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	struct at_xdmac_desc	*desc, *_desc;
 	struct list_head	*descs_list;
 	enum dma_status		ret;
-	int			residue;
-	u32			cur_nda, mask, value;
+	int			residue, retry;
+	u32			cur_nda, check_nda, cur_ubc, mask, value;
 	u8			dwidth = 0;
 	unsigned long		flags;
 
@@ -1433,7 +1434,42 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 			cpu_relax();
 	}
 
+	/*
+	 * When processing the residue, we need to read two registers but we
+	 * can't do it in an atomic way. AT_XDMAC_CNDA is used to find where
+	 * we stand in the descriptor list and AT_XDMAC_CUBC is used
+	 * to know how many data are remaining for the current descriptor.
+	 * Since the dma channel is not paused to not loose data, between the
+	 * AT_XDMAC_CNDA and AT_XDMAC_CUBC read, we may have change of
+	 * descriptor.
+	 * For that reason, after reading AT_XDMAC_CUBC, we check if we are
+	 * still using the same descriptor by reading a second time
+	 * AT_XDMAC_CNDA. If AT_XDMAC_CNDA has changed, it means we have to
+	 * read again AT_XDMAC_CUBC.
+	 * Memory barriers are used to ensure the read order of the registers.
+	 * A max number of retries is set because unlikely it can never ends if
+	 * we are transferring a lot of data with small buffers.
+	 */
 	cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
+	rmb();
+	cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
+	for (retry = 0; retry < AT_XDMAC_RESIDUE_MAX_RETRIES; retry++) {
+		rmb();
+		check_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
+
+		if (likely(cur_nda == check_nda))
+			break;
+
+		cur_nda = check_nda;
+		rmb();
+		cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
+	}
+
+	if (unlikely(retry >= AT_XDMAC_RESIDUE_MAX_RETRIES)) {
+		ret = DMA_ERROR;
+		goto spin_unlock;
+	}
+
 	/*
 	 * Remove size of all microblocks already transferred and the current
 	 * one. Then add the remaining size to transfer of the current
@@ -1446,7 +1482,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 		if ((desc->lld.mbr_nda & 0xfffffffc) == cur_nda)
 			break;
 	}
-	residue += at_xdmac_chan_read(atchan, AT_XDMAC_CUBC) << dwidth;
+	residue += cur_ubc << dwidth;
 
 	dma_set_residue(txstate, residue);
 
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index e893318560db..5ad0ec1f0e29 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -156,7 +156,6 @@ static void dwc_initialize(struct dw_dma_chan *dwc)
 
 	/* Enable interrupts */
 	channel_set_bit(dw, MASK.XFER, dwc->mask);
-	channel_set_bit(dw, MASK.BLOCK, dwc->mask);
 	channel_set_bit(dw, MASK.ERROR, dwc->mask);
 
 	dwc->initialized = true;
@@ -588,6 +587,9 @@ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc,
 
 		spin_unlock_irqrestore(&dwc->lock, flags);
 	}
+
+	/* Re-enable interrupts */
+	channel_set_bit(dw, MASK.BLOCK, dwc->mask);
 }
 
 /* ------------------------------------------------------------------------- */
@@ -618,11 +620,8 @@ static void dw_dma_tasklet(unsigned long data)
 			dwc_scan_descriptors(dw, dwc);
 	}
 
-	/*
-	 * Re-enable interrupts.
-	 */
+	/* Re-enable interrupts */
 	channel_set_bit(dw, MASK.XFER, dw->all_chan_mask);
-	channel_set_bit(dw, MASK.BLOCK, dw->all_chan_mask);
 	channel_set_bit(dw, MASK.ERROR, dw->all_chan_mask);
 }
 
@@ -1261,6 +1260,7 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 int dw_dma_cyclic_start(struct dma_chan *chan)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	struct dw_dma		*dw = to_dw_dma(chan->device);
 	unsigned long		flags;
 
 	if (!test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) {
@@ -1269,7 +1269,12 @@ int dw_dma_cyclic_start(struct dma_chan *chan)
 	}
 
 	spin_lock_irqsave(&dwc->lock, flags);
+
+	/* Enable interrupts to perform cyclic transfer */
+	channel_set_bit(dw, MASK.BLOCK, dwc->mask);
+
 	dwc_dostart(dwc, dwc->cdesc->desc[0]);
+
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	return 0;
diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c
index 4c30fdd092b3..358f9689a3f5 100644
--- a/drivers/dma/dw/pci.c
+++ b/drivers/dma/dw/pci.c
@@ -108,6 +108,10 @@ static const struct pci_device_id dw_pci_id_table[] = {
 
 	/* Haswell */
 	{ PCI_VDEVICE(INTEL, 0x9c60) },
+
+	/* Broadwell */
+	{ PCI_VDEVICE(INTEL, 0x9ce0) },
+
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, dw_pci_id_table);
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index d92d65549406..e3d7fcb69b4c 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -113,6 +113,9 @@
 #define GET_NUM_REGN(x)		((x & 0x300000) >> 20) /* bits 20-21 */
 #define CHMAP_EXIST		BIT(24)
 
+/* CCSTAT register */
+#define EDMA_CCSTAT_ACTV	BIT(4)
+
 /*
  * Max of 20 segments per channel to conserve PaRAM slots
  * Also note that MAX_NR_SG should be atleast the no.of periods
@@ -1680,9 +1683,20 @@ static void edma_issue_pending(struct dma_chan *chan)
 	spin_unlock_irqrestore(&echan->vchan.lock, flags);
 }
 
+/*
+ * This limit exists to avoid a possible infinite loop when waiting for proof
+ * that a particular transfer is completed. This limit can be hit if there
+ * are large bursts to/from slow devices or the CPU is never able to catch
+ * the DMA hardware idle. On an AM335x transfering 48 bytes from the UART
+ * RX-FIFO, as many as 55 loops have been seen.
+ */
+#define EDMA_MAX_TR_WAIT_LOOPS 1000
+
 static u32 edma_residue(struct edma_desc *edesc)
 {
 	bool dst = edesc->direction == DMA_DEV_TO_MEM;
+	int loop_count = EDMA_MAX_TR_WAIT_LOOPS;
+	struct edma_chan *echan = edesc->echan;
 	struct edma_pset *pset = edesc->pset;
 	dma_addr_t done, pos;
 	int i;
@@ -1691,7 +1705,32 @@ static u32 edma_residue(struct edma_desc *edesc)
 	 * We always read the dst/src position from the first RamPar
 	 * pset. That's the one which is active now.
 	 */
-	pos = edma_get_position(edesc->echan->ecc, edesc->echan->slot[0], dst);
+	pos = edma_get_position(echan->ecc, echan->slot[0], dst);
+
+	/*
+	 * "pos" may represent a transfer request that is still being
+	 * processed by the EDMACC or EDMATC. We will busy wait until
+	 * any one of the situations occurs:
+	 *   1. the DMA hardware is idle
+	 *   2. a new transfer request is setup
+	 *   3. we hit the loop limit
+	 */
+	while (edma_read(echan->ecc, EDMA_CCSTAT) & EDMA_CCSTAT_ACTV) {
+		/* check if a new transfer request is setup */
+		if (edma_get_position(echan->ecc,
+				      echan->slot[0], dst) != pos) {
+			break;
+		}
+
+		if (!--loop_count) {
+			dev_dbg_ratelimited(echan->vchan.chan.device->dev,
+				"%s: timeout waiting for PaRAM update\n",
+				__func__);
+			break;
+		}
+
+		cpu_relax();
+	}
 
 	/*
 	 * Cyclic is simple. Just subtract pset[0].addr from pos.
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index 2209f75fdf05..aac85c30c2cf 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -522,6 +522,8 @@ static dma_cookie_t fsldma_run_tx_complete_actions(struct fsldma_chan *chan,
 			chan_dbg(chan, "LD %p callback\n", desc);
 			txd->callback(txd->callback_param);
 		}
+
+		dma_descriptor_unmap(txd);
 	}
 
 	/* Run any dependencies */
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 1d5df2ef148b..21539d5c54c3 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -861,32 +861,42 @@ void ioat_timer_event(unsigned long data)
 			return;
 	}
 
+	spin_lock_bh(&ioat_chan->cleanup_lock);
+
+	/* handle the no-actives case */
+	if (!ioat_ring_active(ioat_chan)) {
+		spin_lock_bh(&ioat_chan->prep_lock);
+		check_active(ioat_chan);
+		spin_unlock_bh(&ioat_chan->prep_lock);
+		spin_unlock_bh(&ioat_chan->cleanup_lock);
+		return;
+	}
+
 	/* if we haven't made progress and we have already
 	 * acknowledged a pending completion once, then be more
 	 * forceful with a restart
 	 */
-	spin_lock_bh(&ioat_chan->cleanup_lock);
 	if (ioat_cleanup_preamble(ioat_chan, &phys_complete))
 		__cleanup(ioat_chan, phys_complete);
 	else if (test_bit(IOAT_COMPLETION_ACK, &ioat_chan->state)) {
+		u32 chanerr;
+
+		chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
+		dev_warn(to_dev(ioat_chan), "Restarting channel...\n");
+		dev_warn(to_dev(ioat_chan), "CHANSTS: %#Lx CHANERR: %#x\n",
+			 status, chanerr);
+		dev_warn(to_dev(ioat_chan), "Active descriptors: %d\n",
+			 ioat_ring_active(ioat_chan));
+
 		spin_lock_bh(&ioat_chan->prep_lock);
 		ioat_restart_channel(ioat_chan);
 		spin_unlock_bh(&ioat_chan->prep_lock);
 		spin_unlock_bh(&ioat_chan->cleanup_lock);
 		return;
-	} else {
+	} else
 		set_bit(IOAT_COMPLETION_ACK, &ioat_chan->state);
-		mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT);
-	}
-
 
-	if (ioat_ring_active(ioat_chan))
-		mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT);
-	else {
-		spin_lock_bh(&ioat_chan->prep_lock);
-		check_active(ioat_chan);
-		spin_unlock_bh(&ioat_chan->prep_lock);
-	}
+	mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT);
 	spin_unlock_bh(&ioat_chan->cleanup_lock);
 }
 
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index e4f43125e0fb..f039cfadf17b 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -1300,10 +1300,10 @@ static int iop_adma_probe(struct platform_device *pdev)
 	 * note: writecombine gives slightly better performance, but
 	 * requires that we explicitly flush the writes
 	 */
-	adev->dma_desc_pool_virt = dma_alloc_writecombine(&pdev->dev,
-							  plat_data->pool_size,
-							  &adev->dma_desc_pool,
-							  GFP_KERNEL);
+	adev->dma_desc_pool_virt = dma_alloc_wc(&pdev->dev,
+						plat_data->pool_size,
+						&adev->dma_desc_pool,
+						GFP_KERNEL);
 	if (!adev->dma_desc_pool_virt) {
 		ret = -ENOMEM;
 		goto err_free_adev;
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 14091f878f80..3922a5d56806 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -964,8 +964,8 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 	 * requires that we explicitly flush the writes
 	 */
 	mv_chan->dma_desc_pool_virt =
-	  dma_alloc_writecombine(&pdev->dev, MV_XOR_POOL_SIZE,
-				 &mv_chan->dma_desc_pool, GFP_KERNEL);
+	  dma_alloc_wc(&pdev->dev, MV_XOR_POOL_SIZE, &mv_chan->dma_desc_pool,
+		       GFP_KERNEL);
 	if (!mv_chan->dma_desc_pool_virt)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c
index f2a0310ae771..debca824bed6 100644
--- a/drivers/dma/pxa_dma.c
+++ b/drivers/dma/pxa_dma.c
@@ -583,6 +583,8 @@ static void set_updater_desc(struct pxad_desc_sw *sw_desc,
 		(PXA_DCMD_LENGTH & sizeof(u32));
 	if (flags & DMA_PREP_INTERRUPT)
 		updater->dcmd |= PXA_DCMD_ENDIRQEN;
+	if (sw_desc->cyclic)
+		sw_desc->hw_desc[sw_desc->nb_desc - 2]->ddadr = sw_desc->first;
 }
 
 static bool is_desc_completed(struct virt_dma_desc *vd)
@@ -673,6 +675,10 @@ static irqreturn_t pxad_chan_handler(int irq, void *dev_id)
 		dev_dbg(&chan->vc.chan.dev->device,
 			"%s(): checking txd %p[%x]: completed=%d\n",
 			__func__, vd, vd->tx.cookie, is_desc_completed(vd));
+		if (to_pxad_sw_desc(vd)->cyclic) {
+			vchan_cyclic_callback(vd);
+			break;
+		}
 		if (is_desc_completed(vd)) {
 			list_del(&vd->node);
 			vchan_cookie_complete(vd);
@@ -1080,7 +1086,7 @@ pxad_prep_dma_cyclic(struct dma_chan *dchan,
 		return NULL;
 
 	pxad_get_config(chan, dir, &dcmd, &dsadr, &dtadr);
-	dcmd |= PXA_DCMD_ENDIRQEN | (PXA_DCMD_LENGTH | period_len);
+	dcmd |= PXA_DCMD_ENDIRQEN | (PXA_DCMD_LENGTH & period_len);
 	dev_dbg(&chan->vc.chan.dev->device,
 		"%s(): buf_addr=0x%lx len=%zu period=%zu dir=%d flags=%lx\n",
 		__func__, (unsigned long)buf_addr, len, period_len, dir, flags);
diff --git a/drivers/dma/qcom_bam_dma.c b/drivers/dma/qcom_bam_dma.c
index 5a250cdc8376..d34aef7a101b 100644
--- a/drivers/dma/qcom_bam_dma.c
+++ b/drivers/dma/qcom_bam_dma.c
@@ -502,8 +502,8 @@ static int bam_alloc_chan(struct dma_chan *chan)
 		return 0;
 
 	/* allocate FIFO descriptor space, but only if necessary */
-	bchan->fifo_virt = dma_alloc_writecombine(bdev->dev, BAM_DESC_FIFO_SIZE,
-				&bchan->fifo_phys, GFP_KERNEL);
+	bchan->fifo_virt = dma_alloc_wc(bdev->dev, BAM_DESC_FIFO_SIZE,
+					&bchan->fifo_phys, GFP_KERNEL);
 
 	if (!bchan->fifo_virt) {
 		dev_err(bdev->dev, "Failed to allocate desc fifo\n");
@@ -538,8 +538,8 @@ static void bam_free_chan(struct dma_chan *chan)
 	bam_reset_channel(bchan);
 	spin_unlock_irqrestore(&bchan->vc.lock, flags);
 
-	dma_free_writecombine(bdev->dev, BAM_DESC_FIFO_SIZE, bchan->fifo_virt,
-				bchan->fifo_phys);
+	dma_free_wc(bdev->dev, BAM_DESC_FIFO_SIZE, bchan->fifo_virt,
+		    bchan->fifo_phys);
 	bchan->fifo_virt = NULL;
 
 	/* mask irq for pipe/channel */
@@ -1231,9 +1231,9 @@ static int bam_dma_remove(struct platform_device *pdev)
 		bam_dma_terminate_all(&bdev->channels[i].vc.chan);
 		tasklet_kill(&bdev->channels[i].vc.task);
 
-		dma_free_writecombine(bdev->dev, BAM_DESC_FIFO_SIZE,
-			bdev->channels[i].fifo_virt,
-			bdev->channels[i].fifo_phys);
+		dma_free_wc(bdev->dev, BAM_DESC_FIFO_SIZE,
+			    bdev->channels[i].fifo_virt,
+			    bdev->channels[i].fifo_phys);
 	}
 
 	tasklet_kill(&bdev->task);
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index ef25000a5bc6..37755e63cc28 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -367,14 +367,30 @@ config EDAC_OCTEON_PCI
 	  Support for error detection and correction on the
 	  Cavium Octeon family of SOCs.
 
-config EDAC_ALTERA_MC
-	bool "Altera SDRAM Memory Controller EDAC"
+config EDAC_ALTERA
+	bool "Altera SOCFPGA ECC"
 	depends on EDAC_MM_EDAC=y && ARCH_SOCFPGA
 	help
 	  Support for error detection and correction on the
-	  Altera SDRAM memory controller. Note that the
-	  preloader must initialize the SDRAM before loading
-	  the kernel.
+	  Altera SOCs. This must be selected for SDRAM ECC.
+	  Note that the preloader must initialize the SDRAM
+	  before loading the kernel.
+
+config EDAC_ALTERA_L2C
+	bool "Altera L2 Cache ECC"
+	depends on EDAC_ALTERA=y
+	select CACHE_L2X0
+	help
+	  Support for error detection and correction on the
+	  Altera L2 cache Memory for Altera SoCs. This option
+	  requires L2 cache so it will force that selection.
+
+config EDAC_ALTERA_OCRAM
+	bool "Altera On-Chip RAM ECC"
+	depends on EDAC_ALTERA=y && SRAM && GENERIC_ALLOCATOR
+	help
+	  Support for error detection and correction on the
+	  Altera On-Chip RAM Memory for Altera SoCs.
 
 config EDAC_SYNOPSYS
 	tristate "Synopsys DDR Memory Controller"
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index be163e20fe56..f9e4a3e0e6e9 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -67,6 +67,6 @@ obj-$(CONFIG_EDAC_OCTEON_L2C)		+= octeon_edac-l2c.o
 obj-$(CONFIG_EDAC_OCTEON_LMC)		+= octeon_edac-lmc.o
 obj-$(CONFIG_EDAC_OCTEON_PCI)		+= octeon_edac-pci.o
 
-obj-$(CONFIG_EDAC_ALTERA_MC)		+= altera_edac.o
+obj-$(CONFIG_EDAC_ALTERA)		+= altera_edac.o
 obj-$(CONFIG_EDAC_SYNOPSYS)		+= synopsys_edac.o
 obj-$(CONFIG_EDAC_XGENE)		+= xgene_edac.o
diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c
index 929640981d8a..63e42098726d 100644
--- a/drivers/edac/altera_edac.c
+++ b/drivers/edac/altera_edac.c
@@ -1,5 +1,5 @@
 /*
- *  Copyright Altera Corporation (C) 2014-2015. All rights reserved.
+ *  Copyright Altera Corporation (C) 2014-2016. All rights reserved.
  *  Copyright 2011-2012 Calxeda, Inc.
  *
  * This program is free software; you can redistribute it and/or modify it
@@ -17,8 +17,10 @@
  * Adapted from the highbank_mc_edac driver.
  */
 
+#include <asm/cacheflush.h>
 #include <linux/ctype.h>
 #include <linux/edac.h>
+#include <linux/genalloc.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/mfd/syscon.h>
@@ -34,6 +36,7 @@
 
 #define EDAC_MOD_STR		"altera_edac"
 #define EDAC_VERSION		"1"
+#define EDAC_DEVICE		"Altera"
 
 static const struct altr_sdram_prv_data c5_data = {
 	.ecc_ctrl_offset    = CV_CTLCFG_OFST,
@@ -75,6 +78,31 @@ static const struct altr_sdram_prv_data a10_data = {
 	.ue_set_mask        = A10_DIAGINT_TDERRA_MASK,
 };
 
+/************************** EDAC Device Defines **************************/
+
+/* OCRAM ECC Management Group Defines */
+#define ALTR_MAN_GRP_OCRAM_ECC_OFFSET   0x04
+#define ALTR_OCR_ECC_EN                 BIT(0)
+#define ALTR_OCR_ECC_INJS               BIT(1)
+#define ALTR_OCR_ECC_INJD               BIT(2)
+#define ALTR_OCR_ECC_SERR               BIT(3)
+#define ALTR_OCR_ECC_DERR               BIT(4)
+
+/* L2 ECC Management Group Defines */
+#define ALTR_MAN_GRP_L2_ECC_OFFSET      0x00
+#define ALTR_L2_ECC_EN                  BIT(0)
+#define ALTR_L2_ECC_INJS                BIT(1)
+#define ALTR_L2_ECC_INJD                BIT(2)
+
+#define ALTR_UE_TRIGGER_CHAR            'U'   /* Trigger for UE */
+#define ALTR_TRIGGER_READ_WRD_CNT       32    /* Line size x 4 */
+#define ALTR_TRIG_OCRAM_BYTE_SIZE       128   /* Line size x 4 */
+#define ALTR_TRIG_L2C_BYTE_SIZE         4096  /* Full Page */
+
+/*********************** EDAC Memory Controller Functions ****************/
+
+/* The SDRAM controller uses the EDAC Memory Controller framework.       */
+
 static irqreturn_t altr_sdram_mc_err_handler(int irq, void *dev_id)
 {
 	struct mem_ctl_info *mci = dev_id;
@@ -504,6 +532,466 @@ static struct platform_driver altr_sdram_edac_driver = {
 
 module_platform_driver(altr_sdram_edac_driver);
 
+/************************* EDAC Parent Probe *************************/
+
+static const struct of_device_id altr_edac_device_of_match[];
+
+static const struct of_device_id altr_edac_of_match[] = {
+	{ .compatible = "altr,socfpga-ecc-manager" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, altr_edac_of_match);
+
+static int altr_edac_probe(struct platform_device *pdev)
+{
+	of_platform_populate(pdev->dev.of_node, altr_edac_device_of_match,
+			     NULL, &pdev->dev);
+	return 0;
+}
+
+static struct platform_driver altr_edac_driver = {
+	.probe =  altr_edac_probe,
+	.driver = {
+		.name = "socfpga_ecc_manager",
+		.of_match_table = altr_edac_of_match,
+	},
+};
+module_platform_driver(altr_edac_driver);
+
+/************************* EDAC Device Functions *************************/
+
+/*
+ * EDAC Device Functions (shared between various IPs).
+ * The discrete memories use the EDAC Device framework. The probe
+ * and error handling functions are very similar between memories
+ * so they are shared. The memory allocation and freeing for EDAC
+ * trigger testing are different for each memory.
+ */
+
+const struct edac_device_prv_data ocramecc_data;
+const struct edac_device_prv_data l2ecc_data;
+
+struct edac_device_prv_data {
+	int (*setup)(struct platform_device *pdev, void __iomem *base);
+	int ce_clear_mask;
+	int ue_clear_mask;
+	char dbgfs_name[20];
+	void * (*alloc_mem)(size_t size, void **other);
+	void (*free_mem)(void *p, size_t size, void *other);
+	int ecc_enable_mask;
+	int ce_set_mask;
+	int ue_set_mask;
+	int trig_alloc_sz;
+};
+
+struct altr_edac_device_dev {
+	void __iomem *base;
+	int sb_irq;
+	int db_irq;
+	const struct edac_device_prv_data *data;
+	struct dentry *debugfs_dir;
+	char *edac_dev_name;
+};
+
+static irqreturn_t altr_edac_device_handler(int irq, void *dev_id)
+{
+	irqreturn_t ret_value = IRQ_NONE;
+	struct edac_device_ctl_info *dci = dev_id;
+	struct altr_edac_device_dev *drvdata = dci->pvt_info;
+	const struct edac_device_prv_data *priv = drvdata->data;
+
+	if (irq == drvdata->sb_irq) {
+		if (priv->ce_clear_mask)
+			writel(priv->ce_clear_mask, drvdata->base);
+		edac_device_handle_ce(dci, 0, 0, drvdata->edac_dev_name);
+		ret_value = IRQ_HANDLED;
+	} else if (irq == drvdata->db_irq) {
+		if (priv->ue_clear_mask)
+			writel(priv->ue_clear_mask, drvdata->base);
+		edac_device_handle_ue(dci, 0, 0, drvdata->edac_dev_name);
+		panic("\nEDAC:ECC_DEVICE[Uncorrectable errors]\n");
+		ret_value = IRQ_HANDLED;
+	} else {
+		WARN_ON(1);
+	}
+
+	return ret_value;
+}
+
+static ssize_t altr_edac_device_trig(struct file *file,
+				     const char __user *user_buf,
+				     size_t count, loff_t *ppos)
+
+{
+	u32 *ptemp, i, error_mask;
+	int result = 0;
+	u8 trig_type;
+	unsigned long flags;
+	struct edac_device_ctl_info *edac_dci = file->private_data;
+	struct altr_edac_device_dev *drvdata = edac_dci->pvt_info;
+	const struct edac_device_prv_data *priv = drvdata->data;
+	void *generic_ptr = edac_dci->dev;
+
+	if (!user_buf || get_user(trig_type, user_buf))
+		return -EFAULT;
+
+	if (!priv->alloc_mem)
+		return -ENOMEM;
+
+	/*
+	 * Note that generic_ptr is initialized to the device * but in
+	 * some alloc_functions, this is overridden and returns data.
+	 */
+	ptemp = priv->alloc_mem(priv->trig_alloc_sz, &generic_ptr);
+	if (!ptemp) {
+		edac_printk(KERN_ERR, EDAC_DEVICE,
+			    "Inject: Buffer Allocation error\n");
+		return -ENOMEM;
+	}
+
+	if (trig_type == ALTR_UE_TRIGGER_CHAR)
+		error_mask = priv->ue_set_mask;
+	else
+		error_mask = priv->ce_set_mask;
+
+	edac_printk(KERN_ALERT, EDAC_DEVICE,
+		    "Trigger Error Mask (0x%X)\n", error_mask);
+
+	local_irq_save(flags);
+	/* write ECC corrupted data out. */
+	for (i = 0; i < (priv->trig_alloc_sz / sizeof(*ptemp)); i++) {
+		/* Read data so we're in the correct state */
+		rmb();
+		if (ACCESS_ONCE(ptemp[i]))
+			result = -1;
+		/* Toggle Error bit (it is latched), leave ECC enabled */
+		writel(error_mask, drvdata->base);
+		writel(priv->ecc_enable_mask, drvdata->base);
+		ptemp[i] = i;
+	}
+	/* Ensure it has been written out */
+	wmb();
+	local_irq_restore(flags);
+
+	if (result)
+		edac_printk(KERN_ERR, EDAC_DEVICE, "Mem Not Cleared\n");
+
+	/* Read out written data. ECC error caused here */
+	for (i = 0; i < ALTR_TRIGGER_READ_WRD_CNT; i++)
+		if (ACCESS_ONCE(ptemp[i]) != i)
+			edac_printk(KERN_ERR, EDAC_DEVICE,
+				    "Read doesn't match written data\n");
+
+	if (priv->free_mem)
+		priv->free_mem(ptemp, priv->trig_alloc_sz, generic_ptr);
+
+	return count;
+}
+
+static const struct file_operations altr_edac_device_inject_fops = {
+	.open = simple_open,
+	.write = altr_edac_device_trig,
+	.llseek = generic_file_llseek,
+};
+
+static void altr_create_edacdev_dbgfs(struct edac_device_ctl_info *edac_dci,
+				      const struct edac_device_prv_data *priv)
+{
+	struct altr_edac_device_dev *drvdata = edac_dci->pvt_info;
+
+	if (!IS_ENABLED(CONFIG_EDAC_DEBUG))
+		return;
+
+	drvdata->debugfs_dir = edac_debugfs_create_dir(drvdata->edac_dev_name);
+	if (!drvdata->debugfs_dir)
+		return;
+
+	if (!edac_debugfs_create_file(priv->dbgfs_name, S_IWUSR,
+				      drvdata->debugfs_dir, edac_dci,
+				      &altr_edac_device_inject_fops))
+		debugfs_remove_recursive(drvdata->debugfs_dir);
+}
+
+static const struct of_device_id altr_edac_device_of_match[] = {
+#ifdef CONFIG_EDAC_ALTERA_L2C
+	{ .compatible = "altr,socfpga-l2-ecc", .data = (void *)&l2ecc_data },
+#endif
+#ifdef CONFIG_EDAC_ALTERA_OCRAM
+	{ .compatible = "altr,socfpga-ocram-ecc",
+	  .data = (void *)&ocramecc_data },
+#endif
+	{},
+};
+MODULE_DEVICE_TABLE(of, altr_edac_device_of_match);
+
+/*
+ * altr_edac_device_probe()
+ *	This is a generic EDAC device driver that will support
+ *	various Altera memory devices such as the L2 cache ECC and
+ *	OCRAM ECC as well as the memories for other peripherals.
+ *	Module specific initialization is done by passing the
+ *	function index in the device tree.
+ */
+static int altr_edac_device_probe(struct platform_device *pdev)
+{
+	struct edac_device_ctl_info *dci;
+	struct altr_edac_device_dev *drvdata;
+	struct resource *r;
+	int res = 0;
+	struct device_node *np = pdev->dev.of_node;
+	char *ecc_name = (char *)np->name;
+	static int dev_instance;
+
+	if (!devres_open_group(&pdev->dev, NULL, GFP_KERNEL)) {
+		edac_printk(KERN_ERR, EDAC_DEVICE,
+			    "Unable to open devm\n");
+		return -ENOMEM;
+	}
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!r) {
+		edac_printk(KERN_ERR, EDAC_DEVICE,
+			    "Unable to get mem resource\n");
+		res = -ENODEV;
+		goto fail;
+	}
+
+	if (!devm_request_mem_region(&pdev->dev, r->start, resource_size(r),
+				     dev_name(&pdev->dev))) {
+		edac_printk(KERN_ERR, EDAC_DEVICE,
+			    "%s:Error requesting mem region\n", ecc_name);
+		res = -EBUSY;
+		goto fail;
+	}
+
+	dci = edac_device_alloc_ctl_info(sizeof(*drvdata), ecc_name,
+					 1, ecc_name, 1, 0, NULL, 0,
+					 dev_instance++);
+
+	if (!dci) {
+		edac_printk(KERN_ERR, EDAC_DEVICE,
+			    "%s: Unable to allocate EDAC device\n", ecc_name);
+		res = -ENOMEM;
+		goto fail;
+	}
+
+	drvdata = dci->pvt_info;
+	dci->dev = &pdev->dev;
+	platform_set_drvdata(pdev, dci);
+	drvdata->edac_dev_name = ecc_name;
+
+	drvdata->base = devm_ioremap(&pdev->dev, r->start, resource_size(r));
+	if (!drvdata->base)
+		goto fail1;
+
+	/* Get driver specific data for this EDAC device */
+	drvdata->data = of_match_node(altr_edac_device_of_match, np)->data;
+
+	/* Check specific dependencies for the module */
+	if (drvdata->data->setup) {
+		res = drvdata->data->setup(pdev, drvdata->base);
+		if (res)
+			goto fail1;
+	}
+
+	drvdata->sb_irq = platform_get_irq(pdev, 0);
+	res = devm_request_irq(&pdev->dev, drvdata->sb_irq,
+			       altr_edac_device_handler,
+			       0, dev_name(&pdev->dev), dci);
+	if (res)
+		goto fail1;
+
+	drvdata->db_irq = platform_get_irq(pdev, 1);
+	res = devm_request_irq(&pdev->dev, drvdata->db_irq,
+			       altr_edac_device_handler,
+			       0, dev_name(&pdev->dev), dci);
+	if (res)
+		goto fail1;
+
+	dci->mod_name = "Altera ECC Manager";
+	dci->dev_name = drvdata->edac_dev_name;
+
+	res = edac_device_add_device(dci);
+	if (res)
+		goto fail1;
+
+	altr_create_edacdev_dbgfs(dci, drvdata->data);
+
+	devres_close_group(&pdev->dev, NULL);
+
+	return 0;
+
+fail1:
+	edac_device_free_ctl_info(dci);
+fail:
+	devres_release_group(&pdev->dev, NULL);
+	edac_printk(KERN_ERR, EDAC_DEVICE,
+		    "%s:Error setting up EDAC device: %d\n", ecc_name, res);
+
+	return res;
+}
+
+static int altr_edac_device_remove(struct platform_device *pdev)
+{
+	struct edac_device_ctl_info *dci = platform_get_drvdata(pdev);
+	struct altr_edac_device_dev *drvdata = dci->pvt_info;
+
+	debugfs_remove_recursive(drvdata->debugfs_dir);
+	edac_device_del_device(&pdev->dev);
+	edac_device_free_ctl_info(dci);
+
+	return 0;
+}
+
+static struct platform_driver altr_edac_device_driver = {
+	.probe =  altr_edac_device_probe,
+	.remove = altr_edac_device_remove,
+	.driver = {
+		.name = "altr_edac_device",
+		.of_match_table = altr_edac_device_of_match,
+	},
+};
+module_platform_driver(altr_edac_device_driver);
+
+/*********************** OCRAM EDAC Device Functions *********************/
+
+#ifdef CONFIG_EDAC_ALTERA_OCRAM
+
+static void *ocram_alloc_mem(size_t size, void **other)
+{
+	struct device_node *np;
+	struct gen_pool *gp;
+	void *sram_addr;
+
+	np = of_find_compatible_node(NULL, NULL, "altr,socfpga-ocram-ecc");
+	if (!np)
+		return NULL;
+
+	gp = of_gen_pool_get(np, "iram", 0);
+	of_node_put(np);
+	if (!gp)
+		return NULL;
+
+	sram_addr = (void *)gen_pool_alloc(gp, size);
+	if (!sram_addr)
+		return NULL;
+
+	memset(sram_addr, 0, size);
+	/* Ensure data is written out */
+	wmb();
+
+	/* Remember this handle for freeing  later */
+	*other = gp;
+
+	return sram_addr;
+}
+
+static void ocram_free_mem(void *p, size_t size, void *other)
+{
+	gen_pool_free((struct gen_pool *)other, (u32)p, size);
+}
+
+/*
+ * altr_ocram_check_deps()
+ *	Test for OCRAM cache ECC dependencies upon entry because
+ *	platform specific startup should have initialized the
+ *	On-Chip RAM memory and enabled the ECC.
+ *	Can't turn on ECC here because accessing un-initialized
+ *	memory will cause CE/UE errors possibly causing an ABORT.
+ */
+static int altr_ocram_check_deps(struct platform_device *pdev,
+				 void __iomem *base)
+{
+	if (readl(base) & ALTR_OCR_ECC_EN)
+		return 0;
+
+	edac_printk(KERN_ERR, EDAC_DEVICE,
+		    "OCRAM: No ECC present or ECC disabled.\n");
+	return -ENODEV;
+}
+
+const struct edac_device_prv_data ocramecc_data = {
+	.setup = altr_ocram_check_deps,
+	.ce_clear_mask = (ALTR_OCR_ECC_EN | ALTR_OCR_ECC_SERR),
+	.ue_clear_mask = (ALTR_OCR_ECC_EN | ALTR_OCR_ECC_DERR),
+	.dbgfs_name = "altr_ocram_trigger",
+	.alloc_mem = ocram_alloc_mem,
+	.free_mem = ocram_free_mem,
+	.ecc_enable_mask = ALTR_OCR_ECC_EN,
+	.ce_set_mask = (ALTR_OCR_ECC_EN | ALTR_OCR_ECC_INJS),
+	.ue_set_mask = (ALTR_OCR_ECC_EN | ALTR_OCR_ECC_INJD),
+	.trig_alloc_sz = ALTR_TRIG_OCRAM_BYTE_SIZE,
+};
+
+#endif	/* CONFIG_EDAC_ALTERA_OCRAM */
+
+/********************* L2 Cache EDAC Device Functions ********************/
+
+#ifdef CONFIG_EDAC_ALTERA_L2C
+
+static void *l2_alloc_mem(size_t size, void **other)
+{
+	struct device *dev = *other;
+	void *ptemp = devm_kzalloc(dev, size, GFP_KERNEL);
+
+	if (!ptemp)
+		return NULL;
+
+	/* Make sure everything is written out */
+	wmb();
+
+	/*
+	 * Clean all cache levels up to LoC (includes L2)
+	 * This ensures the corrupted data is written into
+	 * L2 cache for readback test (which causes ECC error).
+	 */
+	flush_cache_all();
+
+	return ptemp;
+}
+
+static void l2_free_mem(void *p, size_t size, void *other)
+{
+	struct device *dev = other;
+
+	if (dev && p)
+		devm_kfree(dev, p);
+}
+
+/*
+ * altr_l2_check_deps()
+ *	Test for L2 cache ECC dependencies upon entry because
+ *	platform specific startup should have initialized the L2
+ *	memory and enabled the ECC.
+ *	Bail if ECC is not enabled.
+ *	Note that L2 Cache Enable is forced at build time.
+ */
+static int altr_l2_check_deps(struct platform_device *pdev,
+			      void __iomem *base)
+{
+	if (readl(base) & ALTR_L2_ECC_EN)
+		return 0;
+
+	edac_printk(KERN_ERR, EDAC_DEVICE,
+		    "L2: No ECC present, or ECC disabled\n");
+	return -ENODEV;
+}
+
+const struct edac_device_prv_data l2ecc_data = {
+	.setup = altr_l2_check_deps,
+	.ce_clear_mask = 0,
+	.ue_clear_mask = 0,
+	.dbgfs_name = "altr_l2_trigger",
+	.alloc_mem = l2_alloc_mem,
+	.free_mem = l2_free_mem,
+	.ecc_enable_mask = ALTR_L2_ECC_EN,
+	.ce_set_mask = (ALTR_L2_ECC_EN | ALTR_L2_ECC_INJS),
+	.ue_set_mask = (ALTR_L2_ECC_EN | ALTR_L2_ECC_INJD),
+	.trig_alloc_sz = ALTR_TRIG_L2C_BYTE_SIZE,
+};
+
+#endif	/* CONFIG_EDAC_ALTERA_L2C */
+
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Thor Thayer");
-MODULE_DESCRIPTION("EDAC Driver for Altera SDRAM Controller");
+MODULE_DESCRIPTION("EDAC Driver for Altera Memories");
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 9eee13ef83a5..d87a47547ba5 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -1452,7 +1452,7 @@ static u64 f1x_get_norm_dct_addr(struct amd64_pvt *pvt, u8 range,
 	u64 chan_off;
 	u64 dram_base		= get_dram_base(pvt, range);
 	u64 hole_off		= f10_dhar_offset(pvt);
-	u64 dct_sel_base_off	= (pvt->dct_sel_hi & 0xFFFFFC00) << 16;
+	u64 dct_sel_base_off	= (u64)(pvt->dct_sel_hi & 0xFFFFFC00) << 16;
 
 	if (hi_rng) {
 		/*
diff --git a/drivers/edac/debugfs.c b/drivers/edac/debugfs.c
index 54d2f668cb0a..92dbb7e2320c 100644
--- a/drivers/edac/debugfs.c
+++ b/drivers/edac/debugfs.c
@@ -53,7 +53,7 @@ int __init edac_debugfs_init(void)
 
 void edac_debugfs_exit(void)
 {
-	debugfs_remove(edac_debugfs);
+	debugfs_remove_recursive(edac_debugfs);
 }
 
 int edac_create_debugfs_nodes(struct mem_ctl_info *mci)
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 8adfc167c2e3..1472f48c8ac6 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -535,60 +535,21 @@ static void edac_mc_workq_function(struct work_struct *work_req)
 
 	mutex_lock(&mem_ctls_mutex);
 
-	/* if this control struct has movd to offline state, we are done */
-	if (mci->op_state == OP_OFFLINE) {
+	if (mci->op_state != OP_RUNNING_POLL) {
 		mutex_unlock(&mem_ctls_mutex);
 		return;
 	}
 
-	/* Only poll controllers that are running polled and have a check */
-	if (edac_mc_assert_error_check_and_clear() && (mci->edac_check != NULL))
+	if (edac_mc_assert_error_check_and_clear())
 		mci->edac_check(mci);
 
 	mutex_unlock(&mem_ctls_mutex);
 
-	/* Reschedule */
+	/* Queue ourselves again. */
 	edac_queue_work(&mci->work, msecs_to_jiffies(edac_mc_get_poll_msec()));
 }
 
 /*
- * edac_mc_workq_setup
- *	initialize a workq item for this mci
- *	passing in the new delay period in msec
- *
- *	locking model:
- *
- *		called with the mem_ctls_mutex held
- */
-static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec)
-{
-	edac_dbg(0, "\n");
-
-	/* if this instance is not in the POLL state, then simply return */
-	if (mci->op_state != OP_RUNNING_POLL)
-		return;
-
-	INIT_DELAYED_WORK(&mci->work, edac_mc_workq_function);
-
-	edac_queue_work(&mci->work, msecs_to_jiffies(msec));
-}
-
-/*
- * edac_mc_workq_teardown
- *	stop the workq processing on this mci
- *
- *	locking model:
- *
- *		called WITHOUT lock held
- */
-static void edac_mc_workq_teardown(struct mem_ctl_info *mci)
-{
-	mci->op_state = OP_OFFLINE;
-
-	edac_stop_work(&mci->work);
-}
-
-/*
  * edac_mc_reset_delay_period(unsigned long value)
  *
  *	user space has updated our poll period value, need to
@@ -771,12 +732,12 @@ int edac_mc_add_mc_with_groups(struct mem_ctl_info *mci,
 		goto fail1;
 	}
 
-	/* If there IS a check routine, then we are running POLLED */
-	if (mci->edac_check != NULL) {
-		/* This instance is NOW RUNNING */
+	if (mci->edac_check) {
 		mci->op_state = OP_RUNNING_POLL;
 
-		edac_mc_workq_setup(mci, edac_mc_get_poll_msec());
+		INIT_DELAYED_WORK(&mci->work, edac_mc_workq_function);
+		edac_queue_work(&mci->work, msecs_to_jiffies(edac_mc_get_poll_msec()));
+
 	} else {
 		mci->op_state = OP_RUNNING_INTERRUPT;
 	}
@@ -823,15 +784,16 @@ struct mem_ctl_info *edac_mc_del_mc(struct device *dev)
 		return NULL;
 	}
 
+	/* mark MCI offline: */
+	mci->op_state = OP_OFFLINE;
+
 	if (!del_mc_from_global_list(mci))
 		edac_mc_owner = NULL;
-	mutex_unlock(&mem_ctls_mutex);
 
-	/* flush workq processes */
-	edac_mc_workq_teardown(mci);
+	mutex_unlock(&mem_ctls_mutex);
 
-	/* marking MCI offline */
-	mci->op_state = OP_OFFLINE;
+	if (mci->edac_check)
+		edac_stop_work(&mci->work);
 
 	/* remove from sysfs */
 	edac_remove_sysfs_mci_device(mci);
diff --git a/drivers/edac/edac_pci.c b/drivers/edac/edac_pci.c
index 99685388d3fb..8f2f2899a7a2 100644
--- a/drivers/edac/edac_pci.c
+++ b/drivers/edac/edac_pci.c
@@ -195,55 +195,24 @@ static void edac_pci_workq_function(struct work_struct *work_req)
 
 	mutex_lock(&edac_pci_ctls_mutex);
 
-	if (pci->op_state == OP_RUNNING_POLL) {
-		/* we might be in POLL mode, but there may NOT be a poll func
-		 */
-		if ((pci->edac_check != NULL) && edac_pci_get_check_errors())
-			pci->edac_check(pci);
-
-		/* if we are on a one second period, then use round */
-		msec = edac_pci_get_poll_msec();
-		if (msec == 1000)
-			delay = round_jiffies_relative(msecs_to_jiffies(msec));
-		else
-			delay = msecs_to_jiffies(msec);
-
-		/* Reschedule only if we are in POLL mode */
-		edac_queue_work(&pci->work, delay);
+	if (pci->op_state != OP_RUNNING_POLL) {
+		mutex_unlock(&edac_pci_ctls_mutex);
+		return;
 	}
 
-	mutex_unlock(&edac_pci_ctls_mutex);
-}
-
-/*
- * edac_pci_workq_setup()
- * 	initialize a workq item for this edac_pci instance
- * 	passing in the new delay period in msec
- *
- *	locking model:
- *		called when 'edac_pci_ctls_mutex' is locked
- */
-static void edac_pci_workq_setup(struct edac_pci_ctl_info *pci,
-				 unsigned int msec)
-{
-	edac_dbg(0, "\n");
+	if (edac_pci_get_check_errors())
+		pci->edac_check(pci);
 
-	INIT_DELAYED_WORK(&pci->work, edac_pci_workq_function);
+	/* if we are on a one second period, then use round */
+	msec = edac_pci_get_poll_msec();
+	if (msec == 1000)
+		delay = round_jiffies_relative(msecs_to_jiffies(msec));
+	else
+		delay = msecs_to_jiffies(msec);
 
-	edac_queue_work(&pci->work, msecs_to_jiffies(edac_pci_get_poll_msec()));
-}
+	edac_queue_work(&pci->work, delay);
 
-/*
- * edac_pci_workq_teardown()
- * 	stop the workq processing on this edac_pci instance
- */
-static void edac_pci_workq_teardown(struct edac_pci_ctl_info *pci)
-{
-	edac_dbg(0, "\n");
-
-	pci->op_state = OP_OFFLINE;
-
-	edac_stop_work(&pci->work);
+	mutex_unlock(&edac_pci_ctls_mutex);
 }
 
 /*
@@ -289,10 +258,12 @@ int edac_pci_add_device(struct edac_pci_ctl_info *pci, int edac_idx)
 		goto fail1;
 	}
 
-	if (pci->edac_check != NULL) {
+	if (pci->edac_check) {
 		pci->op_state = OP_RUNNING_POLL;
 
-		edac_pci_workq_setup(pci, 1000);
+		INIT_DELAYED_WORK(&pci->work, edac_pci_workq_function);
+		edac_queue_work(&pci->work, msecs_to_jiffies(edac_pci_get_poll_msec()));
+
 	} else {
 		pci->op_state = OP_RUNNING_INTERRUPT;
 	}
@@ -350,8 +321,8 @@ struct edac_pci_ctl_info *edac_pci_del_device(struct device *dev)
 
 	mutex_unlock(&edac_pci_ctls_mutex);
 
-	/* stop the workq timer */
-	edac_pci_workq_teardown(pci);
+	if (pci->edac_check)
+		edac_stop_work(&pci->work);
 
 	edac_printk(KERN_INFO, EDAC_PCI,
 		"Removed device %d for %s %s: DEV %s\n",
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index e3a945ce374b..49768c08ac07 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -147,6 +147,135 @@ static const char * const mc6_mce_desc[] = {
 	"Status Register File",
 };
 
+/* Scalable MCA error strings */
+static const char * const f17h_ls_mce_desc[] = {
+	"Load queue parity",
+	"Store queue parity",
+	"Miss address buffer payload parity",
+	"L1 TLB parity",
+	"",						/* reserved */
+	"DC tag error type 6",
+	"DC tag error type 1",
+	"Internal error type 1",
+	"Internal error type 2",
+	"Sys Read data error thread 0",
+	"Sys read data error thread 1",
+	"DC tag error type 2",
+	"DC data error type 1 (poison comsumption)",
+	"DC data error type 2",
+	"DC data error type 3",
+	"DC tag error type 4",
+	"L2 TLB parity",
+	"PDC parity error",
+	"DC tag error type 3",
+	"DC tag error type 5",
+	"L2 fill data error",
+};
+
+static const char * const f17h_if_mce_desc[] = {
+	"microtag probe port parity error",
+	"IC microtag or full tag multi-hit error",
+	"IC full tag parity",
+	"IC data array parity",
+	"Decoupling queue phys addr parity error",
+	"L0 ITLB parity error",
+	"L1 ITLB parity error",
+	"L2 ITLB parity error",
+	"BPQ snoop parity on Thread 0",
+	"BPQ snoop parity on Thread 1",
+	"L1 BTB multi-match error",
+	"L2 BTB multi-match error",
+};
+
+static const char * const f17h_l2_mce_desc[] = {
+	"L2M tag multi-way-hit error",
+	"L2M tag ECC error",
+	"L2M data ECC error",
+	"HW assert",
+};
+
+static const char * const f17h_de_mce_desc[] = {
+	"uop cache tag parity error",
+	"uop cache data parity error",
+	"Insn buffer parity error",
+	"Insn dispatch queue parity error",
+	"Fetch address FIFO parity",
+	"Patch RAM data parity",
+	"Patch RAM sequencer parity",
+	"uop buffer parity"
+};
+
+static const char * const f17h_ex_mce_desc[] = {
+	"Watchdog timeout error",
+	"Phy register file parity",
+	"Flag register file parity",
+	"Immediate displacement register file parity",
+	"Address generator payload parity",
+	"EX payload parity",
+	"Checkpoint queue parity",
+	"Retire dispatch queue parity",
+};
+
+static const char * const f17h_fp_mce_desc[] = {
+	"Physical register file parity",
+	"Freelist parity error",
+	"Schedule queue parity",
+	"NSQ parity error",
+	"Retire queue parity",
+	"Status register file parity",
+};
+
+static const char * const f17h_l3_mce_desc[] = {
+	"Shadow tag macro ECC error",
+	"Shadow tag macro multi-way-hit error",
+	"L3M tag ECC error",
+	"L3M tag multi-way-hit error",
+	"L3M data ECC error",
+	"XI parity, L3 fill done channel error",
+	"L3 victim queue parity",
+	"L3 HW assert",
+};
+
+static const char * const f17h_cs_mce_desc[] = {
+	"Illegal request from transport layer",
+	"Address violation",
+	"Security violation",
+	"Illegal response from transport layer",
+	"Unexpected response",
+	"Parity error on incoming request or probe response data",
+	"Parity error on incoming read response data",
+	"Atomic request parity",
+	"ECC error on probe filter access",
+};
+
+static const char * const f17h_pie_mce_desc[] = {
+	"HW assert",
+	"Internal PIE register security violation",
+	"Error on GMI link",
+	"Poison data written to internal PIE register",
+};
+
+static const char * const f17h_umc_mce_desc[] = {
+	"DRAM ECC error",
+	"Data poison error on DRAM",
+	"SDP parity error",
+	"Advanced peripheral bus error",
+	"Command/address parity error",
+	"Write data CRC error",
+};
+
+static const char * const f17h_pb_mce_desc[] = {
+	"Parameter Block RAM ECC error",
+};
+
+static const char * const f17h_psp_mce_desc[] = {
+	"PSP RAM ECC or parity error",
+};
+
+static const char * const f17h_smu_mce_desc[] = {
+	"SMU RAM ECC or parity error",
+};
+
 static bool f12h_mc0_mce(u16 ec, u8 xec)
 {
 	bool ret = false;
@@ -691,6 +820,177 @@ static void decode_mc6_mce(struct mce *m)
 	pr_emerg(HW_ERR "Corrupted MC6 MCE info?\n");
 }
 
+static void decode_f17h_core_errors(const char *ip_name, u8 xec,
+				   unsigned int mca_type)
+{
+	const char * const *error_desc_array;
+	size_t len;
+
+	pr_emerg(HW_ERR "%s Error: ", ip_name);
+
+	switch (mca_type) {
+	case SMCA_LS:
+		error_desc_array = f17h_ls_mce_desc;
+		len = ARRAY_SIZE(f17h_ls_mce_desc) - 1;
+
+		if (xec == 0x4) {
+			pr_cont("Unrecognized LS MCA error code.\n");
+			return;
+		}
+		break;
+
+	case SMCA_IF:
+		error_desc_array = f17h_if_mce_desc;
+		len = ARRAY_SIZE(f17h_if_mce_desc) - 1;
+		break;
+
+	case SMCA_L2_CACHE:
+		error_desc_array = f17h_l2_mce_desc;
+		len = ARRAY_SIZE(f17h_l2_mce_desc) - 1;
+		break;
+
+	case SMCA_DE:
+		error_desc_array = f17h_de_mce_desc;
+		len = ARRAY_SIZE(f17h_de_mce_desc) - 1;
+		break;
+
+	case SMCA_EX:
+		error_desc_array = f17h_ex_mce_desc;
+		len = ARRAY_SIZE(f17h_ex_mce_desc) - 1;
+		break;
+
+	case SMCA_FP:
+		error_desc_array = f17h_fp_mce_desc;
+		len = ARRAY_SIZE(f17h_fp_mce_desc) - 1;
+		break;
+
+	case SMCA_L3_CACHE:
+		error_desc_array = f17h_l3_mce_desc;
+		len = ARRAY_SIZE(f17h_l3_mce_desc) - 1;
+		break;
+
+	default:
+		pr_cont("Corrupted MCA core error info.\n");
+		return;
+	}
+
+	if (xec > len) {
+		pr_cont("Unrecognized %s MCA bank error code.\n",
+			 amd_core_mcablock_names[mca_type]);
+		return;
+	}
+
+	pr_cont("%s.\n", error_desc_array[xec]);
+}
+
+static void decode_df_errors(u8 xec, unsigned int mca_type)
+{
+	const char * const *error_desc_array;
+	size_t len;
+
+	pr_emerg(HW_ERR "Data Fabric Error: ");
+
+	switch (mca_type) {
+	case  SMCA_CS:
+		error_desc_array = f17h_cs_mce_desc;
+		len = ARRAY_SIZE(f17h_cs_mce_desc) - 1;
+		break;
+
+	case SMCA_PIE:
+		error_desc_array = f17h_pie_mce_desc;
+		len = ARRAY_SIZE(f17h_pie_mce_desc) - 1;
+		break;
+
+	default:
+		pr_cont("Corrupted MCA Data Fabric info.\n");
+		return;
+	}
+
+	if (xec > len) {
+		pr_cont("Unrecognized %s MCA bank error code.\n",
+			 amd_df_mcablock_names[mca_type]);
+		return;
+	}
+
+	pr_cont("%s.\n", error_desc_array[xec]);
+}
+
+/* Decode errors according to Scalable MCA specification */
+static void decode_smca_errors(struct mce *m)
+{
+	u32 addr = MSR_AMD64_SMCA_MCx_IPID(m->bank);
+	unsigned int hwid, mca_type, i;
+	u8 xec = XEC(m->status, xec_mask);
+	const char * const *error_desc_array;
+	const char *ip_name;
+	u32 low, high;
+	size_t len;
+
+	if (rdmsr_safe(addr, &low, &high)) {
+		pr_emerg("Invalid IP block specified, error information is unreliable.\n");
+		return;
+	}
+
+	hwid = high & MCI_IPID_HWID;
+	mca_type = (high & MCI_IPID_MCATYPE) >> 16;
+
+	pr_emerg(HW_ERR "MC%d IPID value: 0x%08x%08x\n", m->bank, high, low);
+
+	/*
+	 * Based on hwid and mca_type values, decode errors from respective IPs.
+	 * Note: mca_type values make sense only in the context of an hwid.
+	 */
+	for (i = 0; i < ARRAY_SIZE(amd_hwids); i++)
+		if (amd_hwids[i].hwid == hwid)
+			break;
+
+	switch (i) {
+	case SMCA_F17H_CORE:
+		ip_name = (mca_type == SMCA_L3_CACHE) ?
+			  "L3 Cache" : "F17h Core";
+		return decode_f17h_core_errors(ip_name, xec, mca_type);
+		break;
+
+	case SMCA_DF:
+		return decode_df_errors(xec, mca_type);
+		break;
+
+	case SMCA_UMC:
+		error_desc_array = f17h_umc_mce_desc;
+		len = ARRAY_SIZE(f17h_umc_mce_desc) - 1;
+		break;
+
+	case SMCA_PB:
+		error_desc_array = f17h_pb_mce_desc;
+		len = ARRAY_SIZE(f17h_pb_mce_desc) - 1;
+		break;
+
+	case SMCA_PSP:
+		error_desc_array = f17h_psp_mce_desc;
+		len = ARRAY_SIZE(f17h_psp_mce_desc) - 1;
+		break;
+
+	case SMCA_SMU:
+		error_desc_array = f17h_smu_mce_desc;
+		len = ARRAY_SIZE(f17h_smu_mce_desc) - 1;
+		break;
+
+	default:
+		pr_emerg(HW_ERR "HWID:%d does not match any existing IPs.\n", hwid);
+		return;
+	}
+
+	ip_name = amd_hwids[i].name;
+	pr_emerg(HW_ERR "%s Error: ", ip_name);
+
+	if (xec > len) {
+		pr_cont("Unrecognized %s MCA bank error code.\n", ip_name);
+		return;
+	}
+
+	pr_cont("%s.\n", error_desc_array[xec]);
+}
+
 static inline void amd_decode_err_code(u16 ec)
 {
 	if (INT_ERROR(ec)) {
@@ -752,6 +1052,7 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 	struct mce *m = (struct mce *)data;
 	struct cpuinfo_x86 *c = &cpu_data(m->extcpu);
 	int ecc;
+	u32 ebx = cpuid_ebx(0x80000007);
 
 	if (amd_filter_mce(m))
 		return NOTIFY_STOP;
@@ -769,11 +1070,20 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 		((m->status & MCI_STATUS_PCC)	? "PCC"	  : "-"),
 		((m->status & MCI_STATUS_ADDRV)	? "AddrV" : "-"));
 
-	if (c->x86 == 0x15 || c->x86 == 0x16)
+	if (c->x86 >= 0x15)
 		pr_cont("|%s|%s",
 			((m->status & MCI_STATUS_DEFERRED) ? "Deferred" : "-"),
 			((m->status & MCI_STATUS_POISON)   ? "Poison"   : "-"));
 
+	if (!!(ebx & BIT(3))) {
+		u32 low, high;
+		u32 addr = MSR_AMD64_SMCA_MCx_CONFIG(m->bank);
+
+		if (!rdmsr_safe(addr, &low, &high) &&
+		    (low & MCI_CONFIG_MCAX))
+			pr_cont("|%s", ((m->status & MCI_STATUS_TCC) ? "TCC" : "-"));
+	}
+
 	/* do the two bits[14:13] together */
 	ecc = (m->status >> 45) & 0x3;
 	if (ecc)
@@ -784,6 +1094,11 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 	if (m->status & MCI_STATUS_ADDRV)
 		pr_emerg(HW_ERR "MC%d Error Address: 0x%016llx\n", m->bank, m->addr);
 
+	if (!!(ebx & BIT(3))) {
+		decode_smca_errors(m);
+		goto err_code;
+	}
+
 	if (!fam_ops)
 		goto err_code;
 
@@ -834,6 +1149,7 @@ static struct notifier_block amd_mce_dec_nb = {
 static int __init mce_amd_init(void)
 {
 	struct cpuinfo_x86 *c = &boot_cpu_data;
+	u32 ebx;
 
 	if (c->x86_vendor != X86_VENDOR_AMD)
 		return -ENODEV;
@@ -888,10 +1204,18 @@ static int __init mce_amd_init(void)
 		fam_ops->mc2_mce = f16h_mc2_mce;
 		break;
 
+	case 0x17:
+		ebx = cpuid_ebx(0x80000007);
+		xec_mask = 0x3f;
+		if (!(ebx & BIT(3))) {
+			printk(KERN_WARNING "Decoding supported only on Scalable MCA processors.\n");
+			goto err_out;
+		}
+		break;
+
 	default:
 		printk(KERN_WARNING "Huh? What family is it: 0x%x?!\n", c->x86);
-		kfree(fam_ops);
-		fam_ops = NULL;
+		goto err_out;
 	}
 
 	pr_info("MCE: In-kernel MCE decoding enabled.\n");
@@ -899,6 +1223,11 @@ static int __init mce_amd_init(void)
 	mce_register_decode_chain(&amd_mce_dec_nb);
 
 	return 0;
+
+err_out:
+	kfree(fam_ops);
+	fam_ops = NULL;
+	return -EINVAL;
 }
 early_initcall(mce_amd_init);
 
diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c
index b7139c160baf..ca63d0da8889 100644
--- a/drivers/edac/mpc85xx_edac.c
+++ b/drivers/edac/mpc85xx_edac.c
@@ -1244,7 +1244,7 @@ static struct platform_driver * const drivers[] = {
 static int __init mpc85xx_mc_init(void)
 {
 	int res = 0;
-	u32 pvr = 0;
+	u32 __maybe_unused pvr = 0;
 
 	printk(KERN_INFO "Freescale(R) MPC85xx EDAC driver, "
 	       "(C) 2006 Montavista Software\n");
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index e438ee5b433f..93f0d4120289 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -1574,7 +1574,7 @@ static int knl_get_dimm_capacity(struct sbridge_pvt *pvt, u64 *mc_sizes)
 				for (cha = 0; cha < KNL_MAX_CHAS; cha++) {
 					if (knl_get_mc_route(target,
 						mc_route_reg[cha]) == channel
-						&& participants[channel]) {
+						&& !participants[channel]) {
 						participant_count++;
 						participants[channel] = 1;
 						break;
@@ -1839,8 +1839,8 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 		edac_dbg(0, "TAD#%d: up to %u.%03u GB (0x%016Lx), socket interleave %d, memory interleave %d, TGT: %d, %d, %d, %d, reg=0x%08x\n",
 			 n_tads, gb, (mb*1000)/1024,
 			 ((u64)tmp_mb) << 20L,
-			 (u32)TAD_SOCK(reg),
-			 (u32)TAD_CH(reg),
+			 (u32)(1 << TAD_SOCK(reg)),
+			 (u32)TAD_CH(reg) + 1,
 			 (u32)TAD_TGT0(reg),
 			 (u32)TAD_TGT1(reg),
 			 (u32)TAD_TGT2(reg),
@@ -2118,7 +2118,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 	}
 
 	ch_way = TAD_CH(reg) + 1;
-	sck_way = TAD_SOCK(reg) + 1;
+	sck_way = 1 << TAD_SOCK(reg);
 
 	if (ch_way == 3)
 		idx = addr >> 6;
@@ -2175,7 +2175,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 		 n_tads,
 		 addr,
 		 limit,
-		 (u32)TAD_SOCK(reg),
+		 sck_way,
 		 ch_way,
 		 offset,
 		 idx,
@@ -2190,18 +2190,12 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 			offset, addr);
 		return -EINVAL;
 	}
-	addr -= offset;
-	/* Store the low bits [0:6] of the addr */
-	ch_addr = addr & 0x7f;
-	/* Remove socket wayness and remove 6 bits */
-	addr >>= 6;
-	addr = div_u64(addr, sck_xch);
-#if 0
-	/* Divide by channel way */
-	addr = addr / ch_way;
-#endif
-	/* Recover the last 6 bits */
-	ch_addr |= addr << 6;
+
+	ch_addr = addr - offset;
+	ch_addr >>= (6 + shiftup);
+	ch_addr /= ch_way * sck_way;
+	ch_addr <<= (6 + shiftup);
+	ch_addr |= addr & ((1 << (6 + shiftup)) - 1);
 
 	/*
 	 * Step 3) Decode rank
diff --git a/drivers/edac/xgene_edac.c b/drivers/edac/xgene_edac.c
index 41f876414a18..bf19b6e3bd12 100644
--- a/drivers/edac/xgene_edac.c
+++ b/drivers/edac/xgene_edac.c
@@ -61,6 +61,7 @@ struct xgene_edac {
 	struct regmap		*mcba_map;
 	struct regmap		*mcbb_map;
 	struct regmap		*efuse_map;
+	struct regmap		*rb_map;
 	void __iomem		*pcp_csr;
 	spinlock_t		lock;
 	struct dentry           *dfs;
@@ -1057,7 +1058,7 @@ static bool xgene_edac_l3_promote_to_uc_err(u32 l3cesr, u32 l3celr)
 		case 0x041:
 			return true;
 		}
-	} else if (L3C_ELR_ERRSYN(l3celr) == 9)
+	} else if (L3C_ELR_ERRWAY(l3celr) == 9)
 		return true;
 
 	return false;
@@ -1353,6 +1354,17 @@ static int xgene_edac_l3_remove(struct xgene_edac_dev_ctx *l3)
 #define GLBL_MDED_ERRH			0x0848
 #define GLBL_MDED_ERRHMASK		0x084c
 
+/* IO Bus Registers */
+#define RBCSR				0x0000
+#define STICKYERR_MASK			BIT(0)
+#define RBEIR				0x0008
+#define AGENT_OFFLINE_ERR_MASK		BIT(30)
+#define UNIMPL_RBPAGE_ERR_MASK		BIT(29)
+#define WORD_ALIGNED_ERR_MASK		BIT(28)
+#define PAGE_ACCESS_ERR_MASK		BIT(27)
+#define WRITE_ACCESS_MASK		BIT(26)
+#define RBERRADDR_RD(src)		((src) & 0x03FFFFFF)
+
 static const char * const soc_mem_err_v1[] = {
 	"10GbE0",
 	"10GbE1",
@@ -1470,6 +1482,51 @@ static void xgene_edac_rb_report(struct edac_device_ctl_info *edac_dev)
 	u32 err_addr_hi;
 	u32 reg;
 
+	/* If the register bus resource isn't available, just skip it */
+	if (!ctx->edac->rb_map)
+		goto rb_skip;
+
+	/*
+	 * Check RB access errors
+	 * 1. Out of range
+	 * 2. Un-implemented page
+	 * 3. Un-aligned access
+	 * 4. Offline slave IP
+	 */
+	if (regmap_read(ctx->edac->rb_map, RBCSR, &reg))
+		return;
+	if (reg & STICKYERR_MASK) {
+		bool write;
+		u32 address;
+
+		dev_err(edac_dev->dev, "IOB bus access error(s)\n");
+		if (regmap_read(ctx->edac->rb_map, RBEIR, &reg))
+			return;
+		write = reg & WRITE_ACCESS_MASK ? 1 : 0;
+		address = RBERRADDR_RD(reg);
+		if (reg & AGENT_OFFLINE_ERR_MASK)
+			dev_err(edac_dev->dev,
+				"IOB bus %s access to offline agent error\n",
+				write ? "write" : "read");
+		if (reg & UNIMPL_RBPAGE_ERR_MASK)
+			dev_err(edac_dev->dev,
+				"IOB bus %s access to unimplemented page error\n",
+				write ? "write" : "read");
+		if (reg & WORD_ALIGNED_ERR_MASK)
+			dev_err(edac_dev->dev,
+				"IOB bus %s word aligned access error\n",
+				write ? "write" : "read");
+		if (reg & PAGE_ACCESS_ERR_MASK)
+			dev_err(edac_dev->dev,
+				"IOB bus %s to page out of range access error\n",
+				write ? "write" : "read");
+		if (regmap_write(ctx->edac->rb_map, RBEIR, 0))
+			return;
+		if (regmap_write(ctx->edac->rb_map, RBCSR, 0))
+			return;
+	}
+rb_skip:
+
 	/* IOB Bridge agent transaction error interrupt */
 	reg = readl(ctx->dev_csr + IOBBATRANSERRINTSTS);
 	if (!reg)
@@ -1852,6 +1909,17 @@ static int xgene_edac_probe(struct platform_device *pdev)
 		goto out_err;
 	}
 
+	/*
+	 * NOTE: The register bus resource is optional for compatibility
+	 * reason.
+	 */
+	edac->rb_map = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
+						       "regmap-rb");
+	if (IS_ERR(edac->rb_map)) {
+		dev_warn(edac->dev, "missing syscon regmap rb\n");
+		edac->rb_map = NULL;
+	}
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	edac->pcp_csr = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(edac->pcp_csr)) {
diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index 756eca8c4cf8..10e6774ab2a2 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -221,7 +221,7 @@ sanity_check(struct efi_variable *var, efi_char16_t *name, efi_guid_t vendor,
 	}
 
 	if ((attributes & ~EFI_VARIABLE_MASK) != 0 ||
-	    efivar_validate(name, data, size) == false) {
+	    efivar_validate(vendor, name, data, size) == false) {
 		printk(KERN_ERR "efivars: Malformed variable content\n");
 		return -EINVAL;
 	}
@@ -447,7 +447,8 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj,
 	}
 
 	if ((attributes & ~EFI_VARIABLE_MASK) != 0 ||
-	    efivar_validate(name, data, size) == false) {
+	    efivar_validate(new_var->VendorGuid, name, data,
+			    size) == false) {
 		printk(KERN_ERR "efivars: Malformed variable content\n");
 		return -EINVAL;
 	}
@@ -540,38 +541,30 @@ static ssize_t efivar_delete(struct file *filp, struct kobject *kobj,
 static int
 efivar_create_sysfs_entry(struct efivar_entry *new_var)
 {
-	int i, short_name_size;
+	int short_name_size;
 	char *short_name;
-	unsigned long variable_name_size;
-	efi_char16_t *variable_name;
+	unsigned long utf8_name_size;
+	efi_char16_t *variable_name = new_var->var.VariableName;
 	int ret;
 
-	variable_name = new_var->var.VariableName;
-	variable_name_size = ucs2_strlen(variable_name) * sizeof(efi_char16_t);
-
 	/*
-	 * Length of the variable bytes in ASCII, plus the '-' separator,
+	 * Length of the variable bytes in UTF8, plus the '-' separator,
 	 * plus the GUID, plus trailing NUL
 	 */
-	short_name_size = variable_name_size / sizeof(efi_char16_t)
-				+ 1 + EFI_VARIABLE_GUID_LEN + 1;
-
-	short_name = kzalloc(short_name_size, GFP_KERNEL);
+	utf8_name_size = ucs2_utf8size(variable_name);
+	short_name_size = utf8_name_size + 1 + EFI_VARIABLE_GUID_LEN + 1;
 
+	short_name = kmalloc(short_name_size, GFP_KERNEL);
 	if (!short_name)
 		return -ENOMEM;
 
-	/* Convert Unicode to normal chars (assume top bits are 0),
-	   ala UTF-8 */
-	for (i=0; i < (int)(variable_name_size / sizeof(efi_char16_t)); i++) {
-		short_name[i] = variable_name[i] & 0xFF;
-	}
+	ucs2_as_utf8(short_name, variable_name, short_name_size);
+
 	/* This is ugly, but necessary to separate one vendor's
 	   private variables from another's.         */
-
-	*(short_name + strlen(short_name)) = '-';
+	short_name[utf8_name_size] = '-';
 	efi_guid_to_str(&new_var->var.VendorGuid,
-			 short_name + strlen(short_name));
+			 short_name + utf8_name_size + 1);
 
 	new_var->kobj.kset = efivars_kset;
 
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index 70a0fb10517f..7f2ea21c730d 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -165,67 +165,133 @@ validate_ascii_string(efi_char16_t *var_name, int match, u8 *buffer,
 }
 
 struct variable_validate {
+	efi_guid_t vendor;
 	char *name;
 	bool (*validate)(efi_char16_t *var_name, int match, u8 *data,
 			 unsigned long len);
 };
 
+/*
+ * This is the list of variables we need to validate, as well as the
+ * whitelist for what we think is safe not to default to immutable.
+ *
+ * If it has a validate() method that's not NULL, it'll go into the
+ * validation routine.  If not, it is assumed valid, but still used for
+ * whitelisting.
+ *
+ * Note that it's sorted by {vendor,name}, but globbed names must come after
+ * any other name with the same prefix.
+ */
 static const struct variable_validate variable_validate[] = {
-	{ "BootNext", validate_uint16 },
-	{ "BootOrder", validate_boot_order },
-	{ "DriverOrder", validate_boot_order },
-	{ "Boot*", validate_load_option },
-	{ "Driver*", validate_load_option },
-	{ "ConIn", validate_device_path },
-	{ "ConInDev", validate_device_path },
-	{ "ConOut", validate_device_path },
-	{ "ConOutDev", validate_device_path },
-	{ "ErrOut", validate_device_path },
-	{ "ErrOutDev", validate_device_path },
-	{ "Timeout", validate_uint16 },
-	{ "Lang", validate_ascii_string },
-	{ "PlatformLang", validate_ascii_string },
-	{ "", NULL },
+	{ EFI_GLOBAL_VARIABLE_GUID, "BootNext", validate_uint16 },
+	{ EFI_GLOBAL_VARIABLE_GUID, "BootOrder", validate_boot_order },
+	{ EFI_GLOBAL_VARIABLE_GUID, "Boot*", validate_load_option },
+	{ EFI_GLOBAL_VARIABLE_GUID, "DriverOrder", validate_boot_order },
+	{ EFI_GLOBAL_VARIABLE_GUID, "Driver*", validate_load_option },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ConIn", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ConInDev", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ConOut", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ConOutDev", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ErrOut", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ErrOutDev", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "Lang", validate_ascii_string },
+	{ EFI_GLOBAL_VARIABLE_GUID, "OsIndications", NULL },
+	{ EFI_GLOBAL_VARIABLE_GUID, "PlatformLang", validate_ascii_string },
+	{ EFI_GLOBAL_VARIABLE_GUID, "Timeout", validate_uint16 },
+	{ LINUX_EFI_CRASH_GUID, "*", NULL },
+	{ NULL_GUID, "", NULL },
 };
 
+static bool
+variable_matches(const char *var_name, size_t len, const char *match_name,
+		 int *match)
+{
+	for (*match = 0; ; (*match)++) {
+		char c = match_name[*match];
+		char u = var_name[*match];
+
+		/* Wildcard in the matching name means we've matched */
+		if (c == '*')
+			return true;
+
+		/* Case sensitive match */
+		if (!c && *match == len)
+			return true;
+
+		if (c != u)
+			return false;
+
+		if (!c)
+			return true;
+	}
+	return true;
+}
+
 bool
-efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len)
+efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
+		unsigned long data_size)
 {
 	int i;
-	u16 *unicode_name = var_name;
+	unsigned long utf8_size;
+	u8 *utf8_name;
 
-	for (i = 0; variable_validate[i].validate != NULL; i++) {
-		const char *name = variable_validate[i].name;
-		int match;
+	utf8_size = ucs2_utf8size(var_name);
+	utf8_name = kmalloc(utf8_size + 1, GFP_KERNEL);
+	if (!utf8_name)
+		return false;
 
-		for (match = 0; ; match++) {
-			char c = name[match];
-			u16 u = unicode_name[match];
+	ucs2_as_utf8(utf8_name, var_name, utf8_size);
+	utf8_name[utf8_size] = '\0';
 
-			/* All special variables are plain ascii */
-			if (u > 127)
-				return true;
+	for (i = 0; variable_validate[i].name[0] != '\0'; i++) {
+		const char *name = variable_validate[i].name;
+		int match = 0;
 
-			/* Wildcard in the matching name means we've matched */
-			if (c == '*')
-				return variable_validate[i].validate(var_name,
-							     match, data, len);
+		if (efi_guidcmp(vendor, variable_validate[i].vendor))
+			continue;
 
-			/* Case sensitive match */
-			if (c != u)
+		if (variable_matches(utf8_name, utf8_size+1, name, &match)) {
+			if (variable_validate[i].validate == NULL)
 				break;
-
-			/* Reached the end of the string while matching */
-			if (!c)
-				return variable_validate[i].validate(var_name,
-							     match, data, len);
+			kfree(utf8_name);
+			return variable_validate[i].validate(var_name, match,
+							     data, data_size);
 		}
 	}
-
+	kfree(utf8_name);
 	return true;
 }
 EXPORT_SYMBOL_GPL(efivar_validate);
 
+bool
+efivar_variable_is_removable(efi_guid_t vendor, const char *var_name,
+			     size_t len)
+{
+	int i;
+	bool found = false;
+	int match = 0;
+
+	/*
+	 * Check if our variable is in the validated variables list
+	 */
+	for (i = 0; variable_validate[i].name[0] != '\0'; i++) {
+		if (efi_guidcmp(variable_validate[i].vendor, vendor))
+			continue;
+
+		if (variable_matches(var_name, len,
+				     variable_validate[i].name, &match)) {
+			found = true;
+			break;
+		}
+	}
+
+	/*
+	 * If it's in our list, it is removable.
+	 */
+	return found;
+}
+EXPORT_SYMBOL_GPL(efivar_variable_is_removable);
+
 static efi_status_t
 check_var_size(u32 attributes, unsigned long size)
 {
@@ -852,7 +918,7 @@ int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes,
 
 	*set = false;
 
-	if (efivar_validate(name, data, *size) == false)
+	if (efivar_validate(*vendor, name, data, *size) == false)
 		return -EINVAL;
 
 	/*
diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c
index 72791232e46b..81037e5fe301 100644
--- a/drivers/firmware/iscsi_ibft.c
+++ b/drivers/firmware/iscsi_ibft.c
@@ -319,6 +319,9 @@ static ssize_t ibft_attr_show_nic(void *data, int type, char *buf)
 		val = cpu_to_be32(~((1 << (32-nic->subnet_mask_prefix))-1));
 		str += sprintf(str, "%pI4", &val);
 		break;
+	case ISCSI_BOOT_ETH_PREFIX_LEN:
+		str += sprintf(str, "%d\n", nic->subnet_mask_prefix);
+		break;
 	case ISCSI_BOOT_ETH_ORIGIN:
 		str += sprintf(str, "%d\n", nic->origin);
 		break;
@@ -460,6 +463,7 @@ static umode_t ibft_check_nic_for(void *data, int type)
 		if (address_not_null(nic->ip_addr))
 			rc = S_IRUGO;
 		break;
+	case ISCSI_BOOT_ETH_PREFIX_LEN:
 	case ISCSI_BOOT_ETH_SUBNET_MASK:
 		if (nic->subnet_mask_prefix)
 			rc = S_IRUGO;
diff --git a/drivers/gpio/gpio-altera.c b/drivers/gpio/gpio-altera.c
index 2aeaebd1c6e7..3f87a03abc22 100644
--- a/drivers/gpio/gpio-altera.c
+++ b/drivers/gpio/gpio-altera.c
@@ -312,8 +312,8 @@ static int altera_gpio_probe(struct platform_device *pdev)
 		handle_simple_irq, IRQ_TYPE_NONE);
 
 	if (ret) {
-		dev_info(&pdev->dev, "could not add irqchip\n");
-		return ret;
+		dev_err(&pdev->dev, "could not add irqchip\n");
+		goto teardown;
 	}
 
 	gpiochip_set_chained_irqchip(&altera_gc->mmchip.gc,
@@ -326,6 +326,7 @@ static int altera_gpio_probe(struct platform_device *pdev)
 skip_irq:
 	return 0;
 teardown:
+	of_mm_gpiochip_remove(&altera_gc->mmchip);
 	pr_err("%s: registration failed with status %d\n",
 		node->full_name, ret);
 
diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c
index ec58f4288649..cd007a67b302 100644
--- a/drivers/gpio/gpio-davinci.c
+++ b/drivers/gpio/gpio-davinci.c
@@ -195,7 +195,7 @@ static int davinci_gpio_of_xlate(struct gpio_chip *gc,
 static int davinci_gpio_probe(struct platform_device *pdev)
 {
 	int i, base;
-	unsigned ngpio;
+	unsigned ngpio, nbank;
 	struct davinci_gpio_controller *chips;
 	struct davinci_gpio_platform_data *pdata;
 	struct davinci_gpio_regs __iomem *regs;
@@ -224,8 +224,9 @@ static int davinci_gpio_probe(struct platform_device *pdev)
 	if (WARN_ON(ARCH_NR_GPIOS < ngpio))
 		ngpio = ARCH_NR_GPIOS;
 
+	nbank = DIV_ROUND_UP(ngpio, 32);
 	chips = devm_kzalloc(dev,
-			     ngpio * sizeof(struct davinci_gpio_controller),
+			     nbank * sizeof(struct davinci_gpio_controller),
 			     GFP_KERNEL);
 	if (!chips)
 		return -ENOMEM;
@@ -511,7 +512,7 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev)
 			return irq;
 		}
 
-		irq_domain = irq_domain_add_legacy(NULL, ngpio, irq, 0,
+		irq_domain = irq_domain_add_legacy(dev->of_node, ngpio, irq, 0,
 							&davinci_gpio_irq_ops,
 							chips);
 		if (!irq_domain) {
diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index cf41440aff91..d9ab0cd1d205 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -196,6 +196,44 @@ static int gpio_rcar_irq_set_wake(struct irq_data *d, unsigned int on)
 	return 0;
 }
 
+static void gpio_rcar_irq_bus_lock(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct gpio_rcar_priv *p = gpiochip_get_data(gc);
+
+	pm_runtime_get_sync(&p->pdev->dev);
+}
+
+static void gpio_rcar_irq_bus_sync_unlock(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct gpio_rcar_priv *p = gpiochip_get_data(gc);
+
+	pm_runtime_put(&p->pdev->dev);
+}
+
+
+static int gpio_rcar_irq_request_resources(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct gpio_rcar_priv *p = gpiochip_get_data(gc);
+	int error;
+
+	error = pm_runtime_get_sync(&p->pdev->dev);
+	if (error < 0)
+		return error;
+
+	return 0;
+}
+
+static void gpio_rcar_irq_release_resources(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct gpio_rcar_priv *p = gpiochip_get_data(gc);
+
+	pm_runtime_put(&p->pdev->dev);
+}
+
 static irqreturn_t gpio_rcar_irq_handler(int irq, void *dev_id)
 {
 	struct gpio_rcar_priv *p = dev_id;
@@ -450,6 +488,10 @@ static int gpio_rcar_probe(struct platform_device *pdev)
 	irq_chip->irq_unmask = gpio_rcar_irq_enable;
 	irq_chip->irq_set_type = gpio_rcar_irq_set_type;
 	irq_chip->irq_set_wake = gpio_rcar_irq_set_wake;
+	irq_chip->irq_bus_lock = gpio_rcar_irq_bus_lock;
+	irq_chip->irq_bus_sync_unlock = gpio_rcar_irq_bus_sync_unlock;
+	irq_chip->irq_request_resources = gpio_rcar_irq_request_resources;
+	irq_chip->irq_release_resources = gpio_rcar_irq_release_resources;
 	irq_chip->flags	= IRQCHIP_SET_TYPE_MASKED | IRQCHIP_MASK_ON_SUSPEND;
 
 	ret = gpiochip_add_data(gpio_chip, p);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 82edf95b7740..5e7770f9a415 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -87,6 +87,8 @@ extern int amdgpu_sched_jobs;
 extern int amdgpu_sched_hw_submission;
 extern int amdgpu_enable_semaphores;
 extern int amdgpu_powerplay;
+extern unsigned amdgpu_pcie_gen_cap;
+extern unsigned amdgpu_pcie_lane_cap;
 
 #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS	        3000
 #define AMDGPU_MAX_USEC_TIMEOUT			100000	/* 100 ms */
@@ -132,47 +134,6 @@ extern int amdgpu_powerplay;
 #define AMDGPU_RESET_VCE			(1 << 13)
 #define AMDGPU_RESET_VCE1			(1 << 14)
 
-/* CG block flags */
-#define AMDGPU_CG_BLOCK_GFX			(1 << 0)
-#define AMDGPU_CG_BLOCK_MC			(1 << 1)
-#define AMDGPU_CG_BLOCK_SDMA			(1 << 2)
-#define AMDGPU_CG_BLOCK_UVD			(1 << 3)
-#define AMDGPU_CG_BLOCK_VCE			(1 << 4)
-#define AMDGPU_CG_BLOCK_HDP			(1 << 5)
-#define AMDGPU_CG_BLOCK_BIF			(1 << 6)
-
-/* CG flags */
-#define AMDGPU_CG_SUPPORT_GFX_MGCG		(1 << 0)
-#define AMDGPU_CG_SUPPORT_GFX_MGLS		(1 << 1)
-#define AMDGPU_CG_SUPPORT_GFX_CGCG		(1 << 2)
-#define AMDGPU_CG_SUPPORT_GFX_CGLS		(1 << 3)
-#define AMDGPU_CG_SUPPORT_GFX_CGTS		(1 << 4)
-#define AMDGPU_CG_SUPPORT_GFX_CGTS_LS		(1 << 5)
-#define AMDGPU_CG_SUPPORT_GFX_CP_LS		(1 << 6)
-#define AMDGPU_CG_SUPPORT_GFX_RLC_LS		(1 << 7)
-#define AMDGPU_CG_SUPPORT_MC_LS			(1 << 8)
-#define AMDGPU_CG_SUPPORT_MC_MGCG		(1 << 9)
-#define AMDGPU_CG_SUPPORT_SDMA_LS		(1 << 10)
-#define AMDGPU_CG_SUPPORT_SDMA_MGCG		(1 << 11)
-#define AMDGPU_CG_SUPPORT_BIF_LS		(1 << 12)
-#define AMDGPU_CG_SUPPORT_UVD_MGCG		(1 << 13)
-#define AMDGPU_CG_SUPPORT_VCE_MGCG		(1 << 14)
-#define AMDGPU_CG_SUPPORT_HDP_LS		(1 << 15)
-#define AMDGPU_CG_SUPPORT_HDP_MGCG		(1 << 16)
-
-/* PG flags */
-#define AMDGPU_PG_SUPPORT_GFX_PG		(1 << 0)
-#define AMDGPU_PG_SUPPORT_GFX_SMG		(1 << 1)
-#define AMDGPU_PG_SUPPORT_GFX_DMG		(1 << 2)
-#define AMDGPU_PG_SUPPORT_UVD			(1 << 3)
-#define AMDGPU_PG_SUPPORT_VCE			(1 << 4)
-#define AMDGPU_PG_SUPPORT_CP			(1 << 5)
-#define AMDGPU_PG_SUPPORT_GDS			(1 << 6)
-#define AMDGPU_PG_SUPPORT_RLC_SMU_HS		(1 << 7)
-#define AMDGPU_PG_SUPPORT_SDMA			(1 << 8)
-#define AMDGPU_PG_SUPPORT_ACP			(1 << 9)
-#define AMDGPU_PG_SUPPORT_SAMU			(1 << 10)
-
 /* GFX current status */
 #define AMDGPU_GFX_NORMAL_MODE			0x00000000L
 #define AMDGPU_GFX_SAFE_MODE			0x00000001L
@@ -606,8 +567,6 @@ struct amdgpu_sa_manager {
 	uint32_t		align;
 };
 
-struct amdgpu_sa_bo;
-
 /* sub-allocation buffer */
 struct amdgpu_sa_bo {
 	struct list_head		olist;
@@ -2360,6 +2319,8 @@ bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo);
 int amdgpu_ttm_tt_set_userptr(struct ttm_tt *ttm, uint64_t addr,
 				     uint32_t flags);
 bool amdgpu_ttm_tt_has_userptr(struct ttm_tt *ttm);
+bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
+				  unsigned long end);
 bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm);
 uint32_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm,
 				 struct ttm_mem_reg *mem);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index a081dda9fa2f..7a4b101e10c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -795,6 +795,12 @@ static int amdgpu_cgs_query_system_info(void *cgs_device,
 	case CGS_SYSTEM_INFO_PCIE_MLW:
 		sys_info->value = adev->pm.pcie_mlw_mask;
 		break;
+	case CGS_SYSTEM_INFO_CG_FLAGS:
+		sys_info->value = adev->cg_flags;
+		break;
+	case CGS_SYSTEM_INFO_PG_FLAGS:
+		sys_info->value = adev->pg_flags;
+		break;
 	default:
 		return -ENODEV;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 89c3dd62ba21..119cdc2c43e7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -77,7 +77,7 @@ void amdgpu_connector_hotplug(struct drm_connector *connector)
 			} else if (amdgpu_atombios_dp_needs_link_train(amdgpu_connector)) {
 				/* Don't try to start link training before we
 				 * have the dpcd */
-				if (!amdgpu_atombios_dp_get_dpcd(amdgpu_connector))
+				if (amdgpu_atombios_dp_get_dpcd(amdgpu_connector))
 					return;
 
 				/* set it to OFF so that drm_helper_connector_dpms()
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 65531463f88e..51bfc114584e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1795,15 +1795,20 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon)
 	}
 
 	/* post card */
-	amdgpu_atom_asic_init(adev->mode_info.atom_context);
+	if (!amdgpu_card_posted(adev))
+		amdgpu_atom_asic_init(adev->mode_info.atom_context);
 
 	r = amdgpu_resume(adev);
+	if (r)
+		DRM_ERROR("amdgpu_resume failed (%d).\n", r);
 
 	amdgpu_fence_driver_resume(adev);
 
-	r = amdgpu_ib_ring_tests(adev);
-	if (r)
-		DRM_ERROR("ib ring test failed (%d).\n", r);
+	if (resume) {
+		r = amdgpu_ib_ring_tests(adev);
+		if (r)
+			DRM_ERROR("ib ring test failed (%d).\n", r);
+	}
 
 	r = amdgpu_late_init(adev);
 	if (r)
@@ -1933,80 +1938,97 @@ retry:
 	return r;
 }
 
+#define AMDGPU_DEFAULT_PCIE_GEN_MASK 0x30007  /* gen: chipset 1/2, asic 1/2/3 */
+#define AMDGPU_DEFAULT_PCIE_MLW_MASK 0x2f0000 /* 1/2/4/8/16 lanes */
+
 void amdgpu_get_pcie_info(struct amdgpu_device *adev)
 {
 	u32 mask;
 	int ret;
 
-	if (pci_is_root_bus(adev->pdev->bus))
-		return;
+	if (amdgpu_pcie_gen_cap)
+		adev->pm.pcie_gen_mask = amdgpu_pcie_gen_cap;
 
-	if (amdgpu_pcie_gen2 == 0)
-		return;
+	if (amdgpu_pcie_lane_cap)
+		adev->pm.pcie_mlw_mask = amdgpu_pcie_lane_cap;
 
-	if (adev->flags & AMD_IS_APU)
+	/* covers APUs as well */
+	if (pci_is_root_bus(adev->pdev->bus)) {
+		if (adev->pm.pcie_gen_mask == 0)
+			adev->pm.pcie_gen_mask = AMDGPU_DEFAULT_PCIE_GEN_MASK;
+		if (adev->pm.pcie_mlw_mask == 0)
+			adev->pm.pcie_mlw_mask = AMDGPU_DEFAULT_PCIE_MLW_MASK;
 		return;
+	}
 
-	ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask);
-	if (!ret) {
-		adev->pm.pcie_gen_mask = (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
-					  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 |
-					  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3);
-
-		if (mask & DRM_PCIE_SPEED_25)
-			adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1;
-		if (mask & DRM_PCIE_SPEED_50)
-			adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2;
-		if (mask & DRM_PCIE_SPEED_80)
-			adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3;
-	}
-	ret = drm_pcie_get_max_link_width(adev->ddev, &mask);
-	if (!ret) {
-		switch (mask) {
-		case 32:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 16:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 12:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 8:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 4:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 2:
-			adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-						  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
-			break;
-		case 1:
-			adev->pm.pcie_mlw_mask = CAIL_PCIE_LINK_WIDTH_SUPPORT_X1;
-			break;
-		default:
-			break;
+	if (adev->pm.pcie_gen_mask == 0) {
+		ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask);
+		if (!ret) {
+			adev->pm.pcie_gen_mask = (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+						  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 |
+						  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3);
+
+			if (mask & DRM_PCIE_SPEED_25)
+				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1;
+			if (mask & DRM_PCIE_SPEED_50)
+				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2;
+			if (mask & DRM_PCIE_SPEED_80)
+				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3;
+		} else {
+			adev->pm.pcie_gen_mask = AMDGPU_DEFAULT_PCIE_GEN_MASK;
+		}
+	}
+	if (adev->pm.pcie_mlw_mask == 0) {
+		ret = drm_pcie_get_max_link_width(adev->ddev, &mask);
+		if (!ret) {
+			switch (mask) {
+			case 32:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 16:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 12:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 8:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 4:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 2:
+				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case 1:
+				adev->pm.pcie_mlw_mask = CAIL_PCIE_LINK_WIDTH_SUPPORT_X1;
+				break;
+			default:
+				break;
+			}
+		} else {
+			adev->pm.pcie_mlw_mask = AMDGPU_DEFAULT_PCIE_MLW_MASK;
 		}
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index acd066d0a805..1846d65b7285 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -72,8 +72,8 @@ static void amdgpu_flip_work_func(struct work_struct *__work)
 
 	struct drm_crtc *crtc = &amdgpuCrtc->base;
 	unsigned long flags;
-	unsigned i;
-	int vpos, hpos, stat, min_udelay;
+	unsigned i, repcnt = 4;
+	int vpos, hpos, stat, min_udelay = 0;
 	struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id];
 
 	amdgpu_flip_wait_fence(adev, &work->excl);
@@ -96,7 +96,7 @@ static void amdgpu_flip_work_func(struct work_struct *__work)
 	 * In practice this won't execute very often unless on very fast
 	 * machines because the time window for this to happen is very small.
 	 */
-	for (;;) {
+	while (amdgpuCrtc->enabled && --repcnt) {
 		/* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank
 		 * start in hpos, and to the "fudged earlier" vblank start in
 		 * vpos.
@@ -112,12 +112,24 @@ static void amdgpu_flip_work_func(struct work_struct *__work)
 			break;
 
 		/* Sleep at least until estimated real start of hw vblank */
-		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
 		min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5);
+		if (min_udelay > vblank->framedur_ns / 2000) {
+			/* Don't wait ridiculously long - something is wrong */
+			repcnt = 0;
+			break;
+		}
+		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
 		usleep_range(min_udelay, 2 * min_udelay);
 		spin_lock_irqsave(&crtc->dev->event_lock, flags);
 	};
 
+	if (!repcnt)
+		DRM_DEBUG_DRIVER("Delay problem on crtc %d: min_udelay %d, "
+				 "framedur %d, linedur %d, stat %d, vpos %d, "
+				 "hpos %d\n", work->crtc_id, min_udelay,
+				 vblank->framedur_ns / 1000,
+				 vblank->linedur_ns / 1000, stat, vpos, hpos);
+
 	/* do the flip (mmio) */
 	adev->mode_info.funcs->page_flip(adev, work->crtc_id, work->base);
 	/* set the flip status */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 9c1af8976bef..9ef1db87cf26 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -83,6 +83,8 @@ int amdgpu_sched_jobs = 32;
 int amdgpu_sched_hw_submission = 2;
 int amdgpu_enable_semaphores = 0;
 int amdgpu_powerplay = -1;
+unsigned amdgpu_pcie_gen_cap = 0;
+unsigned amdgpu_pcie_lane_cap = 0;
 
 MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes");
 module_param_named(vramlimit, amdgpu_vram_limit, int, 0600);
@@ -170,6 +172,12 @@ MODULE_PARM_DESC(powerplay, "Powerplay component (1 = enable, 0 = disable, -1 =
 module_param_named(powerplay, amdgpu_powerplay, int, 0444);
 #endif
 
+MODULE_PARM_DESC(pcie_gen_cap, "PCIE Gen Caps (0: autodetect (default))");
+module_param_named(pcie_gen_cap, amdgpu_pcie_gen_cap, uint, 0444);
+
+MODULE_PARM_DESC(pcie_lane_cap, "PCIE Lane Caps (0: autodetect (default))");
+module_param_named(pcie_lane_cap, amdgpu_pcie_lane_cap, uint, 0444);
+
 static struct pci_device_id pciidlist[] = {
 #ifdef CONFIG_DRM_AMDGPU_CIK
 	/* Kaveri */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 7380f782cd14..d20c2a8929cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -596,7 +596,8 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 		break;
 	}
 	ttm_eu_backoff_reservation(&ticket, &list);
-	if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE))
+	if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE) &&
+	    !amdgpu_vm_debug)
 		amdgpu_gem_va_update_vm(adev, bo_va, args->operation);
 
 	drm_gem_object_unreference_unlocked(gobj);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index b1969f2b2038..d4e2780c0796 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -142,7 +142,8 @@ static void amdgpu_mn_invalidate_range_start(struct mmu_notifier *mn,
 
 		list_for_each_entry(bo, &node->bos, mn_list) {
 
-			if (!bo->tbo.ttm || bo->tbo.ttm->state != tt_bound)
+			if (!amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm, start,
+							  end))
 				continue;
 
 			r = amdgpu_bo_reserve(bo, true);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 7d8d84eaea4a..95a4a25d8df9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -113,6 +113,10 @@ static ssize_t amdgpu_get_dpm_forced_performance_level(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 
+	if  ((adev->flags & AMD_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return snprintf(buf, PAGE_SIZE, "off\n");
+
 	if (adev->pp_enabled) {
 		enum amd_dpm_forced_level level;
 
@@ -140,6 +144,11 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev,
 	enum amdgpu_dpm_forced_level level;
 	int ret = 0;
 
+	/* Can't force performance level when the card is off */
+	if  ((adev->flags & AMD_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return -EINVAL;
+
 	if (strncmp("low", buf, strlen("low")) == 0) {
 		level = AMDGPU_DPM_FORCED_LEVEL_LOW;
 	} else if (strncmp("high", buf, strlen("high")) == 0) {
@@ -157,6 +166,7 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev,
 		mutex_lock(&adev->pm.mutex);
 		if (adev->pm.dpm.thermal_active) {
 			count = -EINVAL;
+			mutex_unlock(&adev->pm.mutex);
 			goto fail;
 		}
 		ret = amdgpu_dpm_force_performance_level(adev, level);
@@ -167,8 +177,6 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev,
 		mutex_unlock(&adev->pm.mutex);
 	}
 fail:
-	mutex_unlock(&adev->pm.mutex);
-
 	return count;
 }
 
@@ -182,8 +190,14 @@ static ssize_t amdgpu_hwmon_show_temp(struct device *dev,
 				      char *buf)
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
+	struct drm_device *ddev = adev->ddev;
 	int temp;
 
+	/* Can't get temperature when the card is off */
+	if  ((adev->flags & AMD_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return -EINVAL;
+
 	if (!adev->pp_enabled && !adev->pm.funcs->get_temperature)
 		temp = 0;
 	else
@@ -634,11 +648,6 @@ force:
 
 	/* update display watermarks based on new power state */
 	amdgpu_display_bandwidth_update(adev);
-	/* update displays */
-	amdgpu_dpm_display_configuration_changed(adev);
-
-	adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs;
-	adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count;
 
 	/* wait for the rings to drain */
 	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
@@ -655,6 +664,12 @@ force:
 
 	amdgpu_dpm_post_set_power_state(adev);
 
+	/* update displays */
+	amdgpu_dpm_display_configuration_changed(adev);
+
+	adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs;
+	adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count;
+
 	if (adev->pm.funcs->force_performance_level) {
 		if (adev->pm.dpm.thermal_active) {
 			enum amdgpu_dpm_forced_level level = adev->pm.dpm.forced_level;
@@ -847,12 +862,16 @@ static int amdgpu_debugfs_pm_info(struct seq_file *m, void *data)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct amdgpu_device *adev = dev->dev_private;
+	struct drm_device *ddev = adev->ddev;
 
 	if (!adev->pm.dpm_enabled) {
 		seq_printf(m, "dpm not enabled\n");
 		return 0;
 	}
-	if (adev->pp_enabled) {
+	if  ((adev->flags & AMD_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) {
+		seq_printf(m, "PX asic powered off\n");
+	} else if (adev->pp_enabled) {
 		amdgpu_dpm_debugfs_print_current_performance_level(adev, m);
 	} else {
 		mutex_lock(&adev->pm.mutex);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
index b9d0d55f6b47..3cb6d6c413c7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
@@ -143,8 +143,10 @@ static int amdgpu_pp_late_init(void *handle)
 					adev->powerplay.pp_handle);
 
 #ifdef CONFIG_DRM_AMD_POWERPLAY
-	if (adev->pp_enabled)
+	if (adev->pp_enabled) {
 		amdgpu_pm_sysfs_init(adev);
+		amdgpu_dpm_dispatch_task(adev, AMD_PP_EVENT_COMPLETE_INIT, NULL, NULL);
+	}
 #endif
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
index 8b88edb0434b..ca72a2e487b9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
@@ -354,12 +354,15 @@ int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager,
 
 		for (i = 0, count = 0; i < AMDGPU_MAX_RINGS; ++i)
 			if (fences[i])
-				fences[count++] = fences[i];
+				fences[count++] = fence_get(fences[i]);
 
 		if (count) {
 			spin_unlock(&sa_manager->wq.lock);
 			t = fence_wait_any_timeout(fences, count, false,
 						   MAX_SCHEDULE_TIMEOUT);
+			for (i = 0; i < count; ++i)
+				fence_put(fences[i]);
+
 			r = (t > 0) ? 0 : t;
 			spin_lock(&sa_manager->wq.lock);
 		} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 55cf05e1c81c..1cbb16e15307 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -712,7 +712,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm)
 						       0, PAGE_SIZE,
 						       PCI_DMA_BIDIRECTIONAL);
 		if (pci_dma_mapping_error(adev->pdev, gtt->ttm.dma_address[i])) {
-			while (--i) {
+			while (i--) {
 				pci_unmap_page(adev->pdev, gtt->ttm.dma_address[i],
 					       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
 				gtt->ttm.dma_address[i] = 0;
@@ -783,6 +783,25 @@ bool amdgpu_ttm_tt_has_userptr(struct ttm_tt *ttm)
 	return !!gtt->userptr;
 }
 
+bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
+				  unsigned long end)
+{
+	struct amdgpu_ttm_tt *gtt = (void *)ttm;
+	unsigned long size;
+
+	if (gtt == NULL)
+		return false;
+
+	if (gtt->ttm.ttm.state != tt_bound || !gtt->userptr)
+		return false;
+
+	size = (unsigned long)gtt->ttm.ttm.num_pages * PAGE_SIZE;
+	if (gtt->userptr > end || gtt->userptr + size <= start)
+		return false;
+
+	return true;
+}
+
 bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm)
 {
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
index 21aacc1f45c1..bf731e9f643e 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
@@ -265,15 +265,27 @@ static int amdgpu_atombios_dp_get_dp_link_config(struct drm_connector *connector
 	unsigned max_lane_num = drm_dp_max_lane_count(dpcd);
 	unsigned lane_num, i, max_pix_clock;
 
-	for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) {
-		for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) {
-			max_pix_clock = (lane_num * link_rates[i] * 8) / bpp;
+	if (amdgpu_connector_encoder_get_dp_bridge_encoder_id(connector) ==
+	    ENCODER_OBJECT_ID_NUTMEG) {
+		for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) {
+			max_pix_clock = (lane_num * 270000 * 8) / bpp;
 			if (max_pix_clock >= pix_clock) {
 				*dp_lanes = lane_num;
-				*dp_rate = link_rates[i];
+				*dp_rate = 270000;
 				return 0;
 			}
 		}
+	} else {
+		for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) {
+			for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) {
+				max_pix_clock = (lane_num * link_rates[i] * 8) / bpp;
+				if (max_pix_clock >= pix_clock) {
+					*dp_lanes = lane_num;
+					*dp_rate = link_rates[i];
+					return 0;
+				}
+			}
+		}
 	}
 
 	return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index 8b4731d4e10e..474ca02b0949 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -31,6 +31,7 @@
 #include "ci_dpm.h"
 #include "gfx_v7_0.h"
 #include "atom.h"
+#include "amd_pcie.h"
 #include <linux/seq_file.h>
 
 #include "smu/smu_7_0_1_d.h"
@@ -5835,18 +5836,16 @@ static int ci_dpm_init(struct amdgpu_device *adev)
 	u8 frev, crev;
 	struct ci_power_info *pi;
 	int ret;
-	u32 mask;
 
 	pi = kzalloc(sizeof(struct ci_power_info), GFP_KERNEL);
 	if (pi == NULL)
 		return -ENOMEM;
 	adev->pm.dpm.priv = pi;
 
-	ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask);
-	if (ret)
-		pi->sys_pcie_mask = 0;
-	else
-		pi->sys_pcie_mask = mask;
+	pi->sys_pcie_mask =
+		(adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_MASK) >>
+		CAIL_PCIE_LINK_SPEED_SUPPORT_SHIFT;
+
 	pi->force_pcie_gen = AMDGPU_PCIE_GEN_INVALID;
 
 	pi->pcie_gen_performance.max = AMDGPU_PCIE_GEN1;
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index fd9c9588ef46..155965ed14a3 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1762,6 +1762,9 @@ static void cik_program_aspm(struct amdgpu_device *adev)
 	if (amdgpu_aspm == 0)
 		return;
 
+	if (pci_is_root_bus(adev->pdev->bus))
+		return;
+
 	/* XXX double check APUs */
 	if (adev->flags & AMD_IS_APU)
 		return;
@@ -2332,72 +2335,72 @@ static int cik_common_early_init(void *handle)
 	switch (adev->asic_type) {
 	case CHIP_BONAIRE:
 		adev->cg_flags =
-			AMDGPU_CG_SUPPORT_GFX_MGCG |
-			AMDGPU_CG_SUPPORT_GFX_MGLS |
-			/*AMDGPU_CG_SUPPORT_GFX_CGCG |*/
-			AMDGPU_CG_SUPPORT_GFX_CGLS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS_LS |
-			AMDGPU_CG_SUPPORT_GFX_CP_LS |
-			AMDGPU_CG_SUPPORT_MC_LS |
-			AMDGPU_CG_SUPPORT_MC_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_LS |
-			AMDGPU_CG_SUPPORT_BIF_LS |
-			AMDGPU_CG_SUPPORT_VCE_MGCG |
-			AMDGPU_CG_SUPPORT_UVD_MGCG |
-			AMDGPU_CG_SUPPORT_HDP_LS |
-			AMDGPU_CG_SUPPORT_HDP_MGCG;
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_MGLS |
+			/*AMD_CG_SUPPORT_GFX_CGCG |*/
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_CGTS |
+			AMD_CG_SUPPORT_GFX_CGTS_LS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_MC_MGCG |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_VCE_MGCG |
+			AMD_CG_SUPPORT_UVD_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags = 0;
 		adev->external_rev_id = adev->rev_id + 0x14;
 		break;
 	case CHIP_HAWAII:
 		adev->cg_flags =
-			AMDGPU_CG_SUPPORT_GFX_MGCG |
-			AMDGPU_CG_SUPPORT_GFX_MGLS |
-			/*AMDGPU_CG_SUPPORT_GFX_CGCG |*/
-			AMDGPU_CG_SUPPORT_GFX_CGLS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS |
-			AMDGPU_CG_SUPPORT_GFX_CP_LS |
-			AMDGPU_CG_SUPPORT_MC_LS |
-			AMDGPU_CG_SUPPORT_MC_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_LS |
-			AMDGPU_CG_SUPPORT_BIF_LS |
-			AMDGPU_CG_SUPPORT_VCE_MGCG |
-			AMDGPU_CG_SUPPORT_UVD_MGCG |
-			AMDGPU_CG_SUPPORT_HDP_LS |
-			AMDGPU_CG_SUPPORT_HDP_MGCG;
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_MGLS |
+			/*AMD_CG_SUPPORT_GFX_CGCG |*/
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_CGTS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_MC_MGCG |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_VCE_MGCG |
+			AMD_CG_SUPPORT_UVD_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags = 0;
 		adev->external_rev_id = 0x28;
 		break;
 	case CHIP_KAVERI:
 		adev->cg_flags =
-			AMDGPU_CG_SUPPORT_GFX_MGCG |
-			AMDGPU_CG_SUPPORT_GFX_MGLS |
-			/*AMDGPU_CG_SUPPORT_GFX_CGCG |*/
-			AMDGPU_CG_SUPPORT_GFX_CGLS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS_LS |
-			AMDGPU_CG_SUPPORT_GFX_CP_LS |
-			AMDGPU_CG_SUPPORT_SDMA_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_LS |
-			AMDGPU_CG_SUPPORT_BIF_LS |
-			AMDGPU_CG_SUPPORT_VCE_MGCG |
-			AMDGPU_CG_SUPPORT_UVD_MGCG |
-			AMDGPU_CG_SUPPORT_HDP_LS |
-			AMDGPU_CG_SUPPORT_HDP_MGCG;
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_MGLS |
+			/*AMD_CG_SUPPORT_GFX_CGCG |*/
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_CGTS |
+			AMD_CG_SUPPORT_GFX_CGTS_LS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_VCE_MGCG |
+			AMD_CG_SUPPORT_UVD_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags =
-			/*AMDGPU_PG_SUPPORT_GFX_PG |
-			  AMDGPU_PG_SUPPORT_GFX_SMG |
-			  AMDGPU_PG_SUPPORT_GFX_DMG |*/
-			AMDGPU_PG_SUPPORT_UVD |
-			/*AMDGPU_PG_SUPPORT_VCE |
-			  AMDGPU_PG_SUPPORT_CP |
-			  AMDGPU_PG_SUPPORT_GDS |
-			  AMDGPU_PG_SUPPORT_RLC_SMU_HS |
-			  AMDGPU_PG_SUPPORT_ACP |
-			  AMDGPU_PG_SUPPORT_SAMU |*/
+			/*AMD_PG_SUPPORT_GFX_PG |
+			  AMD_PG_SUPPORT_GFX_SMG |
+			  AMD_PG_SUPPORT_GFX_DMG |*/
+			AMD_PG_SUPPORT_UVD |
+			/*AMD_PG_SUPPORT_VCE |
+			  AMD_PG_SUPPORT_CP |
+			  AMD_PG_SUPPORT_GDS |
+			  AMD_PG_SUPPORT_RLC_SMU_HS |
+			  AMD_PG_SUPPORT_ACP |
+			  AMD_PG_SUPPORT_SAMU |*/
 			0;
 		if (adev->pdev->device == 0x1312 ||
 			adev->pdev->device == 0x1316 ||
@@ -2409,29 +2412,29 @@ static int cik_common_early_init(void *handle)
 	case CHIP_KABINI:
 	case CHIP_MULLINS:
 		adev->cg_flags =
-			AMDGPU_CG_SUPPORT_GFX_MGCG |
-			AMDGPU_CG_SUPPORT_GFX_MGLS |
-			/*AMDGPU_CG_SUPPORT_GFX_CGCG |*/
-			AMDGPU_CG_SUPPORT_GFX_CGLS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS |
-			AMDGPU_CG_SUPPORT_GFX_CGTS_LS |
-			AMDGPU_CG_SUPPORT_GFX_CP_LS |
-			AMDGPU_CG_SUPPORT_SDMA_MGCG |
-			AMDGPU_CG_SUPPORT_SDMA_LS |
-			AMDGPU_CG_SUPPORT_BIF_LS |
-			AMDGPU_CG_SUPPORT_VCE_MGCG |
-			AMDGPU_CG_SUPPORT_UVD_MGCG |
-			AMDGPU_CG_SUPPORT_HDP_LS |
-			AMDGPU_CG_SUPPORT_HDP_MGCG;
+			AMD_CG_SUPPORT_GFX_MGCG |
+			AMD_CG_SUPPORT_GFX_MGLS |
+			/*AMD_CG_SUPPORT_GFX_CGCG |*/
+			AMD_CG_SUPPORT_GFX_CGLS |
+			AMD_CG_SUPPORT_GFX_CGTS |
+			AMD_CG_SUPPORT_GFX_CGTS_LS |
+			AMD_CG_SUPPORT_GFX_CP_LS |
+			AMD_CG_SUPPORT_SDMA_MGCG |
+			AMD_CG_SUPPORT_SDMA_LS |
+			AMD_CG_SUPPORT_BIF_LS |
+			AMD_CG_SUPPORT_VCE_MGCG |
+			AMD_CG_SUPPORT_UVD_MGCG |
+			AMD_CG_SUPPORT_HDP_LS |
+			AMD_CG_SUPPORT_HDP_MGCG;
 		adev->pg_flags =
-			/*AMDGPU_PG_SUPPORT_GFX_PG |
-			  AMDGPU_PG_SUPPORT_GFX_SMG | */
-			AMDGPU_PG_SUPPORT_UVD |
-			/*AMDGPU_PG_SUPPORT_VCE |
-			  AMDGPU_PG_SUPPORT_CP |
-			  AMDGPU_PG_SUPPORT_GDS |
-			  AMDGPU_PG_SUPPORT_RLC_SMU_HS |
-			  AMDGPU_PG_SUPPORT_SAMU |*/
+			/*AMD_PG_SUPPORT_GFX_PG |
+			  AMD_PG_SUPPORT_GFX_SMG | */
+			AMD_PG_SUPPORT_UVD |
+			/*AMD_PG_SUPPORT_VCE |
+			  AMD_PG_SUPPORT_CP |
+			  AMD_PG_SUPPORT_GDS |
+			  AMD_PG_SUPPORT_RLC_SMU_HS |
+			  AMD_PG_SUPPORT_SAMU |*/
 			0;
 		if (adev->asic_type == CHIP_KABINI) {
 			if (adev->rev_id == 0)
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index 5f712ceddf08..c55ecf0ea845 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -885,7 +885,7 @@ static void cik_enable_sdma_mgcg(struct amdgpu_device *adev,
 {
 	u32 orig, data;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_SDMA_MGCG)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_SDMA_MGCG)) {
 		WREG32(mmSDMA0_CLK_CTRL + SDMA0_REGISTER_OFFSET, 0x00000100);
 		WREG32(mmSDMA0_CLK_CTRL + SDMA1_REGISTER_OFFSET, 0x00000100);
 	} else {
@@ -906,7 +906,7 @@ static void cik_enable_sdma_mgls(struct amdgpu_device *adev,
 {
 	u32 orig, data;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_SDMA_LS)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_SDMA_LS)) {
 		orig = data = RREG32(mmSDMA0_POWER_CNTL + SDMA0_REGISTER_OFFSET);
 		data |= 0x100;
 		if (orig != data)
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
index 4dd17f2dd905..e7ef2261ff4a 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
@@ -445,13 +445,13 @@ static int cz_dpm_init(struct amdgpu_device *adev)
 	pi->gfx_pg_threshold = 500;
 	pi->caps_fps = true;
 	/* uvd */
-	pi->caps_uvd_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_UVD) ? true : false;
+	pi->caps_uvd_pg = (adev->pg_flags & AMD_PG_SUPPORT_UVD) ? true : false;
 	pi->caps_uvd_dpm = true;
 	/* vce */
-	pi->caps_vce_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_VCE) ? true : false;
+	pi->caps_vce_pg = (adev->pg_flags & AMD_PG_SUPPORT_VCE) ? true : false;
 	pi->caps_vce_dpm = true;
 	/* acp */
-	pi->caps_acp_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_ACP) ? true : false;
+	pi->caps_acp_pg = (adev->pg_flags & AMD_PG_SUPPORT_ACP) ? true : false;
 	pi->caps_acp_dpm = true;
 
 	pi->caps_stable_power_state = false;
@@ -2202,8 +2202,7 @@ static void cz_dpm_powergate_vce(struct amdgpu_device *adev, bool gate)
 							    AMD_PG_STATE_GATE);
 
 				cz_enable_vce_dpm(adev, false);
-				/* TODO: to figure out why vce can't be poweroff. */
-				/* cz_send_msg_to_smc(adev, PPSMC_MSG_VCEPowerOFF); */
+				cz_send_msg_to_smc(adev, PPSMC_MSG_VCEPowerOFF);
 				pi->vce_power_gated = true;
 			} else {
 				cz_send_msg_to_smc(adev, PPSMC_MSG_VCEPowerON);
@@ -2226,10 +2225,8 @@ static void cz_dpm_powergate_vce(struct amdgpu_device *adev, bool gate)
 		}
 	} else { /*pi->caps_vce_pg*/
 		cz_update_vce_dpm(adev);
-		cz_enable_vce_dpm(adev, true);
+		cz_enable_vce_dpm(adev, !gate);
 	}
-
-	return;
 }
 
 const struct amd_ip_funcs cz_dpm_ip_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 6c76139de1c9..06602df707f8 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -3628,6 +3628,19 @@ static void gfx_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 					unsigned vm_id, uint64_t pd_addr)
 {
 	int usepfp = (ring->type == AMDGPU_RING_TYPE_GFX);
+	uint32_t seq = ring->fence_drv.sync_seq;
+	uint64_t addr = ring->fence_drv.gpu_addr;
+
+	amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));
+	amdgpu_ring_write(ring, (WAIT_REG_MEM_MEM_SPACE(1) | /* memory */
+				 WAIT_REG_MEM_FUNCTION(3) | /* equal */
+				 WAIT_REG_MEM_ENGINE(usepfp)));   /* pfp or me */
+	amdgpu_ring_write(ring, addr & 0xfffffffc);
+	amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
+	amdgpu_ring_write(ring, seq);
+	amdgpu_ring_write(ring, 0xffffffff);
+	amdgpu_ring_write(ring, 4); /* poll interval */
+
 	if (usepfp) {
 		/* synce CE with ME to prevent CE fetch CEIB before context switch done */
 		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
@@ -4109,7 +4122,7 @@ static void gfx_v7_0_enable_cgcg(struct amdgpu_device *adev, bool enable)
 
 	orig = data = RREG32(mmRLC_CGCG_CGLS_CTRL);
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_CGCG)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG)) {
 		gfx_v7_0_enable_gui_idle_interrupt(adev, true);
 
 		tmp = gfx_v7_0_halt_rlc(adev);
@@ -4147,9 +4160,9 @@ static void gfx_v7_0_enable_mgcg(struct amdgpu_device *adev, bool enable)
 {
 	u32 data, orig, tmp = 0;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_MGCG)) {
-		if (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_MGLS) {
-			if (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_CP_LS) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) {
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGLS) {
+			if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CP_LS) {
 				orig = data = RREG32(mmCP_MEM_SLP_CNTL);
 				data |= CP_MEM_SLP_CNTL__CP_MEM_LS_EN_MASK;
 				if (orig != data)
@@ -4176,14 +4189,14 @@ static void gfx_v7_0_enable_mgcg(struct amdgpu_device *adev, bool enable)
 
 		gfx_v7_0_update_rlc(adev, tmp);
 
-		if (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_CGTS) {
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGTS) {
 			orig = data = RREG32(mmCGTS_SM_CTRL_REG);
 			data &= ~CGTS_SM_CTRL_REG__SM_MODE_MASK;
 			data |= (0x2 << CGTS_SM_CTRL_REG__SM_MODE__SHIFT);
 			data |= CGTS_SM_CTRL_REG__SM_MODE_ENABLE_MASK;
 			data &= ~CGTS_SM_CTRL_REG__OVERRIDE_MASK;
-			if ((adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_MGLS) &&
-			    (adev->cg_flags & AMDGPU_CG_SUPPORT_GFX_CGTS_LS))
+			if ((adev->cg_flags & AMD_CG_SUPPORT_GFX_MGLS) &&
+			    (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGTS_LS))
 				data &= ~CGTS_SM_CTRL_REG__LS_OVERRIDE_MASK;
 			data &= ~CGTS_SM_CTRL_REG__ON_MONITOR_ADD_MASK;
 			data |= CGTS_SM_CTRL_REG__ON_MONITOR_ADD_EN_MASK;
@@ -4249,7 +4262,7 @@ static void gfx_v7_0_enable_sclk_slowdown_on_pu(struct amdgpu_device *adev,
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_RLC_SMU_HS))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS))
 		data |= RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PU_ENABLE_MASK;
 	else
 		data &= ~RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PU_ENABLE_MASK;
@@ -4263,7 +4276,7 @@ static void gfx_v7_0_enable_sclk_slowdown_on_pd(struct amdgpu_device *adev,
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_RLC_SMU_HS))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS))
 		data |= RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PD_ENABLE_MASK;
 	else
 		data &= ~RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PD_ENABLE_MASK;
@@ -4276,7 +4289,7 @@ static void gfx_v7_0_enable_cp_pg(struct amdgpu_device *adev, bool enable)
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_CP))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_CP))
 		data &= ~0x8000;
 	else
 		data |= 0x8000;
@@ -4289,7 +4302,7 @@ static void gfx_v7_0_enable_gds_pg(struct amdgpu_device *adev, bool enable)
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_GDS))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GDS))
 		data &= ~0x2000;
 	else
 		data |= 0x2000;
@@ -4370,7 +4383,7 @@ static void gfx_v7_0_enable_gfx_cgpg(struct amdgpu_device *adev,
 {
 	u32 data, orig;
 
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_PG)) {
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) {
 		orig = data = RREG32(mmRLC_PG_CNTL);
 		data |= RLC_PG_CNTL__GFX_POWER_GATING_ENABLE_MASK;
 		if (orig != data)
@@ -4442,7 +4455,7 @@ static void gfx_v7_0_enable_gfx_static_mgpg(struct amdgpu_device *adev,
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_SMG))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_SMG))
 		data |= RLC_PG_CNTL__STATIC_PER_CU_PG_ENABLE_MASK;
 	else
 		data &= ~RLC_PG_CNTL__STATIC_PER_CU_PG_ENABLE_MASK;
@@ -4456,7 +4469,7 @@ static void gfx_v7_0_enable_gfx_dynamic_mgpg(struct amdgpu_device *adev,
 	u32 data, orig;
 
 	orig = data = RREG32(mmRLC_PG_CNTL);
-	if (enable && (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_DMG))
+	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_DMG))
 		data |= RLC_PG_CNTL__DYN_PER_CU_PG_ENABLE_MASK;
 	else
 		data &= ~RLC_PG_CNTL__DYN_PER_CU_PG_ENABLE_MASK;
@@ -4623,15 +4636,15 @@ static void gfx_v7_0_get_csb_buffer(struct amdgpu_device *adev,
 
 static void gfx_v7_0_init_pg(struct amdgpu_device *adev)
 {
-	if (adev->pg_flags & (AMDGPU_PG_SUPPORT_GFX_PG |
-			      AMDGPU_PG_SUPPORT_GFX_SMG |
-			      AMDGPU_PG_SUPPORT_GFX_DMG |
-			      AMDGPU_PG_SUPPORT_CP |
-			      AMDGPU_PG_SUPPORT_GDS |
-			      AMDGPU_PG_SUPPORT_RLC_SMU_HS)) {
+	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
+			      AMD_PG_SUPPORT_GFX_SMG |
+			      AMD_PG_SUPPORT_GFX_DMG |
+			      AMD_PG_SUPPORT_CP |
+			      AMD_PG_SUPPORT_GDS |
+			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
 		gfx_v7_0_enable_sclk_slowdown_on_pu(adev, true);
 		gfx_v7_0_enable_sclk_slowdown_on_pd(adev, true);
-		if (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_PG) {
+		if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG) {
 			gfx_v7_0_init_gfx_cgpg(adev);
 			gfx_v7_0_enable_cp_pg(adev, true);
 			gfx_v7_0_enable_gds_pg(adev, true);
@@ -4643,14 +4656,14 @@ static void gfx_v7_0_init_pg(struct amdgpu_device *adev)
 
 static void gfx_v7_0_fini_pg(struct amdgpu_device *adev)
 {
-	if (adev->pg_flags & (AMDGPU_PG_SUPPORT_GFX_PG |
-			      AMDGPU_PG_SUPPORT_GFX_SMG |
-			      AMDGPU_PG_SUPPORT_GFX_DMG |
-			      AMDGPU_PG_SUPPORT_CP |
-			      AMDGPU_PG_SUPPORT_GDS |
-			      AMDGPU_PG_SUPPORT_RLC_SMU_HS)) {
+	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
+			      AMD_PG_SUPPORT_GFX_SMG |
+			      AMD_PG_SUPPORT_GFX_DMG |
+			      AMD_PG_SUPPORT_CP |
+			      AMD_PG_SUPPORT_GDS |
+			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
 		gfx_v7_0_update_gfx_pg(adev, false);
-		if (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_PG) {
+		if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG) {
 			gfx_v7_0_enable_cp_pg(adev, false);
 			gfx_v7_0_enable_gds_pg(adev, false);
 		}
@@ -5527,14 +5540,14 @@ static int gfx_v7_0_set_powergating_state(void *handle,
 	if (state == AMD_PG_STATE_GATE)
 		gate = true;
 
-	if (adev->pg_flags & (AMDGPU_PG_SUPPORT_GFX_PG |
-			      AMDGPU_PG_SUPPORT_GFX_SMG |
-			      AMDGPU_PG_SUPPORT_GFX_DMG |
-			      AMDGPU_PG_SUPPORT_CP |
-			      AMDGPU_PG_SUPPORT_GDS |
-			      AMDGPU_PG_SUPPORT_RLC_SMU_HS)) {
+	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
+			      AMD_PG_SUPPORT_GFX_SMG |
+			      AMD_PG_SUPPORT_GFX_DMG |
+			      AMD_PG_SUPPORT_CP |
+			      AMD_PG_SUPPORT_GDS |
+			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
 		gfx_v7_0_update_gfx_pg(adev, gate);
-		if (adev->pg_flags & AMDGPU_PG_SUPPORT_GFX_PG) {
+		if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG) {
 			gfx_v7_0_enable_cp_pg(adev, gate);
 			gfx_v7_0_enable_gds_pg(adev, gate);
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 8f8ec37ecd88..7086ac17abee 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -4809,7 +4809,8 @@ static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));
 	amdgpu_ring_write(ring, (WAIT_REG_MEM_MEM_SPACE(1) | /* memory */
-		 WAIT_REG_MEM_FUNCTION(3))); /* equal */
+				 WAIT_REG_MEM_FUNCTION(3) | /* equal */
+				 WAIT_REG_MEM_ENGINE(usepfp))); /* pfp or me */
 	amdgpu_ring_write(ring, addr & 0xfffffffc);
 	amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
 	amdgpu_ring_write(ring, seq);
@@ -4995,7 +4996,7 @@ static int gfx_v8_0_set_priv_reg_fault_state(struct amdgpu_device *adev,
 	case AMDGPU_IRQ_STATE_ENABLE:
 		cp_int_cntl = RREG32(mmCP_INT_CNTL_RING0);
 		cp_int_cntl = REG_SET_FIELD(cp_int_cntl, CP_INT_CNTL_RING0,
-					    PRIV_REG_INT_ENABLE, 0);
+					    PRIV_REG_INT_ENABLE, 1);
 		WREG32(mmCP_INT_CNTL_RING0, cp_int_cntl);
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 8aa2991ab379..b8060795b27b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -792,7 +792,7 @@ static void gmc_v7_0_enable_mc_ls(struct amdgpu_device *adev,
 
 	for (i = 0; i < ARRAY_SIZE(mc_cg_registers); i++) {
 		orig = data = RREG32(mc_cg_registers[i]);
-		if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_MC_LS))
+		if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_LS))
 			data |= mc_cg_ls_en[i];
 		else
 			data &= ~mc_cg_ls_en[i];
@@ -809,7 +809,7 @@ static void gmc_v7_0_enable_mc_mgcg(struct amdgpu_device *adev,
 
 	for (i = 0; i < ARRAY_SIZE(mc_cg_registers); i++) {
 		orig = data = RREG32(mc_cg_registers[i]);
-		if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_MC_MGCG))
+		if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG))
 			data |= mc_cg_en[i];
 		else
 			data &= ~mc_cg_en[i];
@@ -825,7 +825,7 @@ static void gmc_v7_0_enable_bif_mgls(struct amdgpu_device *adev,
 
 	orig = data = RREG32_PCIE(ixPCIE_CNTL2);
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_BIF_LS)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_BIF_LS)) {
 		data = REG_SET_FIELD(data, PCIE_CNTL2, SLV_MEM_LS_EN, 1);
 		data = REG_SET_FIELD(data, PCIE_CNTL2, MST_MEM_LS_EN, 1);
 		data = REG_SET_FIELD(data, PCIE_CNTL2, REPLAY_MEM_LS_EN, 1);
@@ -848,7 +848,7 @@ static void gmc_v7_0_enable_hdp_mgcg(struct amdgpu_device *adev,
 
 	orig = data = RREG32(mmHDP_HOST_PATH_CNTL);
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_HDP_MGCG))
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_HDP_MGCG))
 		data = REG_SET_FIELD(data, HDP_HOST_PATH_CNTL, CLOCK_GATING_DIS, 0);
 	else
 		data = REG_SET_FIELD(data, HDP_HOST_PATH_CNTL, CLOCK_GATING_DIS, 1);
@@ -864,7 +864,7 @@ static void gmc_v7_0_enable_hdp_ls(struct amdgpu_device *adev,
 
 	orig = data = RREG32(mmHDP_MEM_POWER_LS);
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_HDP_LS))
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS))
 		data = REG_SET_FIELD(data, HDP_MEM_POWER_LS, LS_ENABLE, 1);
 	else
 		data = REG_SET_FIELD(data, HDP_MEM_POWER_LS, LS_ENABLE, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
index 7e9154c7f1db..654d76723bc3 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
@@ -2859,11 +2859,11 @@ static int kv_dpm_init(struct amdgpu_device *adev)
 	pi->voltage_drop_t = 0;
 	pi->caps_sclk_throttle_low_notification = false;
 	pi->caps_fps = false; /* true? */
-	pi->caps_uvd_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_UVD) ? true : false;
+	pi->caps_uvd_pg = (adev->pg_flags & AMD_PG_SUPPORT_UVD) ? true : false;
 	pi->caps_uvd_dpm = true;
-	pi->caps_vce_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_VCE) ? true : false;
-	pi->caps_samu_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_SAMU) ? true : false;
-	pi->caps_acp_pg = (adev->pg_flags & AMDGPU_PG_SUPPORT_ACP) ? true : false;
+	pi->caps_vce_pg = (adev->pg_flags & AMD_PG_SUPPORT_VCE) ? true : false;
+	pi->caps_samu_pg = (adev->pg_flags & AMD_PG_SUPPORT_SAMU) ? true : false;
+	pi->caps_acp_pg = (adev->pg_flags & AMD_PG_SUPPORT_ACP) ? true : false;
 	pi->caps_stable_p_state = false;
 
 	ret = kv_parse_sys_info_table(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index 5e9f73af83a8..fbd3767671bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -611,7 +611,7 @@ static void uvd_v4_2_enable_mgcg(struct amdgpu_device *adev,
 {
 	u32 orig, data;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_UVD_MGCG)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG)) {
 		data = RREG32_UVD_CTX(ixUVD_CGC_MEM_CTRL);
 		data = 0xfff;
 		WREG32_UVD_CTX(ixUVD_CGC_MEM_CTRL, data);
@@ -830,6 +830,9 @@ static int uvd_v4_2_set_clockgating_state(void *handle,
 	bool gate = false;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG))
+		return 0;
+
 	if (state == AMD_CG_STATE_GATE)
 		gate = true;
 
@@ -848,7 +851,10 @@ static int uvd_v4_2_set_powergating_state(void *handle,
 	 * revisit this when there is a cleaner line between
 	 * the smc and the hw blocks
 	 */
-	 struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_UVD))
+		return 0;
 
 	if (state == AMD_PG_STATE_GATE) {
 		uvd_v4_2_stop(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index 38864f562981..57f1c5bf3bf1 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -774,6 +774,11 @@ static int uvd_v5_0_process_interrupt(struct amdgpu_device *adev,
 static int uvd_v5_0_set_clockgating_state(void *handle,
 					  enum amd_clockgating_state state)
 {
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG))
+		return 0;
+
 	return 0;
 }
 
@@ -789,6 +794,9 @@ static int uvd_v5_0_set_powergating_state(void *handle,
 	 */
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_UVD))
+		return 0;
+
 	if (state == AMD_PG_STATE_GATE) {
 		uvd_v5_0_stop(adev);
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 3d5913926436..0b365b7651ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -532,7 +532,7 @@ static int uvd_v6_0_start(struct amdgpu_device *adev)
 	uvd_v6_0_mc_resume(adev);
 
 	/* Set dynamic clock gating in S/W control mode */
-	if (adev->cg_flags & AMDGPU_CG_SUPPORT_UVD_MGCG) {
+	if (adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG) {
 		if (adev->flags & AMD_IS_APU)
 			cz_set_uvd_clock_gating_branches(adev, false);
 		else
@@ -1000,7 +1000,7 @@ static int uvd_v6_0_set_clockgating_state(void *handle,
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
 
-	if (!(adev->cg_flags & AMDGPU_CG_SUPPORT_UVD_MGCG))
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG))
 		return 0;
 
 	if (enable) {
@@ -1030,6 +1030,9 @@ static int uvd_v6_0_set_powergating_state(void *handle,
 	 */
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_UVD))
+		return 0;
+
 	if (state == AMD_PG_STATE_GATE) {
 		uvd_v6_0_stop(adev);
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
index 52ac7a8f1e58..a822edacfa95 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
@@ -373,7 +373,7 @@ static void vce_v2_0_enable_mgcg(struct amdgpu_device *adev, bool enable)
 {
 	bool sw_cg = false;
 
-	if (enable && (adev->cg_flags & AMDGPU_CG_SUPPORT_VCE_MGCG)) {
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG)) {
 		if (sw_cg)
 			vce_v2_0_set_sw_cg(adev, true);
 		else
@@ -608,6 +608,9 @@ static int vce_v2_0_set_powergating_state(void *handle,
 	 */
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_VCE))
+		return 0;
+
 	if (state == AMD_PG_STATE_GATE)
 		/* XXX do we need a vce_v2_0_stop()? */
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index e99af81e4aec..d662fa9f9091 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -277,7 +277,7 @@ static int vce_v3_0_start(struct amdgpu_device *adev)
 		WREG32_P(mmVCE_STATUS, 0, ~1);
 
 		/* Set Clock-Gating off */
-		if (adev->cg_flags & AMDGPU_CG_SUPPORT_VCE_MGCG)
+		if (adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG)
 			vce_v3_0_set_vce_sw_clock_gating(adev, false);
 
 		if (r) {
@@ -676,7 +676,7 @@ static int vce_v3_0_set_clockgating_state(void *handle,
 	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
 	int i;
 
-	if (!(adev->cg_flags & AMDGPU_CG_SUPPORT_VCE_MGCG))
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG))
 		return 0;
 
 	mutex_lock(&adev->grbm_idx_mutex);
@@ -728,6 +728,9 @@ static int vce_v3_0_set_powergating_state(void *handle,
 	 */
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (!(adev->pg_flags & AMD_PG_SUPPORT_VCE))
+		return 0;
+
 	if (state == AMD_PG_STATE_GATE)
 		/* XXX do we need a vce_v3_0_stop()? */
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 89f5a1ff6f43..0d14d108a6c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1457,8 +1457,7 @@ static int vi_common_early_init(void *handle)
 	case CHIP_STONEY:
 		adev->has_uvd = true;
 		adev->cg_flags = 0;
-		/* Disable UVD pg */
-		adev->pg_flags = /* AMDGPU_PG_SUPPORT_UVD | */AMDGPU_PG_SUPPORT_VCE;
+		adev->pg_flags = 0;
 		adev->external_rev_id = adev->rev_id + 0x1;
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index 1195d06f55bc..dbf7e6413cab 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -85,6 +85,38 @@ enum amd_powergating_state {
 	AMD_PG_STATE_UNGATE,
 };
 
+/* CG flags */
+#define AMD_CG_SUPPORT_GFX_MGCG			(1 << 0)
+#define AMD_CG_SUPPORT_GFX_MGLS			(1 << 1)
+#define AMD_CG_SUPPORT_GFX_CGCG			(1 << 2)
+#define AMD_CG_SUPPORT_GFX_CGLS			(1 << 3)
+#define AMD_CG_SUPPORT_GFX_CGTS			(1 << 4)
+#define AMD_CG_SUPPORT_GFX_CGTS_LS		(1 << 5)
+#define AMD_CG_SUPPORT_GFX_CP_LS		(1 << 6)
+#define AMD_CG_SUPPORT_GFX_RLC_LS		(1 << 7)
+#define AMD_CG_SUPPORT_MC_LS			(1 << 8)
+#define AMD_CG_SUPPORT_MC_MGCG			(1 << 9)
+#define AMD_CG_SUPPORT_SDMA_LS			(1 << 10)
+#define AMD_CG_SUPPORT_SDMA_MGCG		(1 << 11)
+#define AMD_CG_SUPPORT_BIF_LS			(1 << 12)
+#define AMD_CG_SUPPORT_UVD_MGCG			(1 << 13)
+#define AMD_CG_SUPPORT_VCE_MGCG			(1 << 14)
+#define AMD_CG_SUPPORT_HDP_LS			(1 << 15)
+#define AMD_CG_SUPPORT_HDP_MGCG			(1 << 16)
+
+/* PG flags */
+#define AMD_PG_SUPPORT_GFX_PG			(1 << 0)
+#define AMD_PG_SUPPORT_GFX_SMG			(1 << 1)
+#define AMD_PG_SUPPORT_GFX_DMG			(1 << 2)
+#define AMD_PG_SUPPORT_UVD			(1 << 3)
+#define AMD_PG_SUPPORT_VCE			(1 << 4)
+#define AMD_PG_SUPPORT_CP			(1 << 5)
+#define AMD_PG_SUPPORT_GDS			(1 << 6)
+#define AMD_PG_SUPPORT_RLC_SMU_HS		(1 << 7)
+#define AMD_PG_SUPPORT_SDMA			(1 << 8)
+#define AMD_PG_SUPPORT_ACP			(1 << 9)
+#define AMD_PG_SUPPORT_SAMU			(1 << 10)
+
 enum amd_pm_state_type {
 	/* not used for dpm */
 	POWER_STATE_TYPE_DEFAULT,
diff --git a/drivers/gpu/drm/amd/include/cgs_common.h b/drivers/gpu/drm/amd/include/cgs_common.h
index 713aec954692..aec38fc3834f 100644
--- a/drivers/gpu/drm/amd/include/cgs_common.h
+++ b/drivers/gpu/drm/amd/include/cgs_common.h
@@ -109,6 +109,8 @@ enum cgs_system_info_id {
 	CGS_SYSTEM_INFO_ADAPTER_BDF_ID = 1,
 	CGS_SYSTEM_INFO_PCIE_GEN_INFO,
 	CGS_SYSTEM_INFO_PCIE_MLW,
+	CGS_SYSTEM_INFO_CG_FLAGS,
+	CGS_SYSTEM_INFO_PG_FLAGS,
 	CGS_SYSTEM_INFO_ID_MAXIMUM,
 };
 
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index aa67244a77ae..589599f66fcc 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -402,8 +402,11 @@ int pp_dpm_dispatch_tasks(void *handle, enum amd_pp_event event_id, void *input,
 
 		data.requested_ui_label = power_state_convert(ps);
 		ret = pem_handle_event(pp_handle->eventmgr, event_id, &data);
+		break;
 	}
-	break;
+	case AMD_PP_EVENT_COMPLETE_INIT:
+		ret = pem_handle_event(pp_handle->eventmgr, event_id, &data);
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c b/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c
index 83be3cf210e0..6b52c78cb404 100644
--- a/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c
+++ b/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c
@@ -165,6 +165,7 @@ const struct action_chain resume_action_chain = {
 };
 
 static const pem_event_action *complete_init_event[] = {
+	unblock_adjust_power_state_tasks,
 	adjust_power_state_tasks,
 	enable_gfx_clock_gating_tasks,
 	enable_gfx_voltage_island_power_gating_tasks,
diff --git a/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c b/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c
index 52a3efc97f05..46410e3c7349 100644
--- a/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c
@@ -31,7 +31,7 @@
 static int pem_init(struct pp_eventmgr *eventmgr)
 {
 	int result = 0;
-	struct pem_event_data event_data;
+	struct pem_event_data event_data = { {0} };
 
 	/* Initialize PowerPlay feature info */
 	pem_init_feature_info(eventmgr);
@@ -52,7 +52,7 @@ static int pem_init(struct pp_eventmgr *eventmgr)
 
 static void pem_fini(struct pp_eventmgr *eventmgr)
 {
-	struct pem_event_data event_data;
+	struct pem_event_data event_data = { {0} };
 
 	pem_uninit_featureInfo(eventmgr);
 	pem_unregister_interrupts(eventmgr);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c
index ad7700822a1c..ff08ce41bde9 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c
@@ -226,7 +226,7 @@ int cz_dpm_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate)
 		}
 	} else {
 		cz_dpm_update_vce_dpm(hwmgr);
-		cz_enable_disable_vce_dpm(hwmgr, true);
+		cz_enable_disable_vce_dpm(hwmgr, !bgate);
 		return 0;
 	}
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
index 0874ab42ee95..cf01177ca3b5 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
@@ -174,6 +174,8 @@ static int cz_initialize_dpm_defaults(struct pp_hwmgr *hwmgr)
 {
 	struct cz_hwmgr *cz_hwmgr = (struct cz_hwmgr *)(hwmgr->backend);
 	uint32_t i;
+	struct cgs_system_info sys_info = {0};
+	int result;
 
 	cz_hwmgr->gfx_ramp_step = 256*25/100;
 
@@ -247,6 +249,22 @@ static int cz_initialize_dpm_defaults(struct pp_hwmgr *hwmgr)
 	phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 				   PHM_PlatformCaps_DisableVoltageIsland);
 
+	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+		      PHM_PlatformCaps_UVDPowerGating);
+	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+		      PHM_PlatformCaps_VCEPowerGating);
+	sys_info.size = sizeof(struct cgs_system_info);
+	sys_info.info_id = CGS_SYSTEM_INFO_PG_FLAGS;
+	result = cgs_query_system_info(hwmgr->device, &sys_info);
+	if (!result) {
+		if (sys_info.value & AMD_PG_SUPPORT_UVD)
+			phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+				      PHM_PlatformCaps_UVDPowerGating);
+		if (sys_info.value & AMD_PG_SUPPORT_VCE)
+			phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+				      PHM_PlatformCaps_VCEPowerGating);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
index 44a925006479..980d3bf8ea76 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
@@ -4451,6 +4451,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 	pp_atomctrl_gpio_pin_assignment gpio_pin_assignment;
 	struct phm_ppt_v1_information *pptable_info = (struct phm_ppt_v1_information *)(hwmgr->pptable);
 	phw_tonga_ulv_parm *ulv;
+	struct cgs_system_info sys_info = {0};
 
 	PP_ASSERT_WITH_CODE((NULL != hwmgr),
 		"Invalid Parameter!", return -1;);
@@ -4615,9 +4616,23 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 
 	data->vddc_phase_shed_control = 0;
 
-	if (0 == result) {
-		struct cgs_system_info sys_info = {0};
+	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+		      PHM_PlatformCaps_UVDPowerGating);
+	phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
+		      PHM_PlatformCaps_VCEPowerGating);
+	sys_info.size = sizeof(struct cgs_system_info);
+	sys_info.info_id = CGS_SYSTEM_INFO_PG_FLAGS;
+	result = cgs_query_system_info(hwmgr->device, &sys_info);
+	if (!result) {
+		if (sys_info.value & AMD_PG_SUPPORT_UVD)
+			phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+				      PHM_PlatformCaps_UVDPowerGating);
+		if (sys_info.value & AMD_PG_SUPPORT_VCE)
+			phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+				      PHM_PlatformCaps_VCEPowerGating);
+	}
 
+	if (0 == result) {
 		data->is_tlu_enabled = 0;
 		hwmgr->platform_descriptor.hardwareActivityPerformanceLevels =
 			TONGA_MAX_HARDWARE_POWERLEVELS;
diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index 9759009d1da3..b1480acbb3c3 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -227,7 +227,7 @@ static int ast_get_dram_info(struct drm_device *dev)
 	} while (ast_read32(ast, 0x10000) != 0x01);
 	data = ast_read32(ast, 0x10004);
 
-	if (data & 0x400)
+	if (data & 0x40)
 		ast->dram_bus_width = 16;
 	else
 		ast->dram_bus_width = 32;
diff --git a/drivers/gpu/drm/bochs/bochs_drv.c b/drivers/gpu/drm/bochs/bochs_drv.c
index 7f1a3604b19f..b332b4d3b0e2 100644
--- a/drivers/gpu/drm/bochs/bochs_drv.c
+++ b/drivers/gpu/drm/bochs/bochs_drv.c
@@ -182,8 +182,8 @@ static const struct pci_device_id bochs_pci_tbl[] = {
 	{
 		.vendor      = 0x1234,
 		.device      = 0x1111,
-		.subvendor   = 0x1af4,
-		.subdevice   = 0x1100,
+		.subvendor   = PCI_SUBVENDOR_ID_REDHAT_QUMRANET,
+		.subdevice   = PCI_SUBDEVICE_ID_QEMU,
 		.driver_data = BOCHS_QEMU_STDVGA,
 	},
 	{
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c
index b1619e29a564..7bc394ec9fb3 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.c
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.c
@@ -33,8 +33,9 @@ static struct drm_driver driver;
 
 /* only bind to the cirrus chip in qemu */
 static const struct pci_device_id pciidlist[] = {
-	{ PCI_VENDOR_ID_CIRRUS, PCI_DEVICE_ID_CIRRUS_5446, 0x1af4, 0x1100, 0,
-	  0, 0 },
+	{ PCI_VENDOR_ID_CIRRUS, PCI_DEVICE_ID_CIRRUS_5446,
+	  PCI_SUBVENDOR_ID_REDHAT_QUMRANET, PCI_SUBDEVICE_ID_QEMU,
+	  0, 0, 0 },
 	{ PCI_VENDOR_ID_CIRRUS, PCI_DEVICE_ID_CIRRUS_5446, PCI_VENDOR_ID_XEN,
 	  0x0001, 0, 0, 0 },
 	{0,}
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 3f74193885f1..9a7b44616b55 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -65,8 +65,6 @@ drm_atomic_state_init(struct drm_device *dev, struct drm_atomic_state *state)
 	 */
 	state->allow_modeset = true;
 
-	state->num_connector = ACCESS_ONCE(dev->mode_config.num_connector);
-
 	state->crtcs = kcalloc(dev->mode_config.num_crtc,
 			       sizeof(*state->crtcs), GFP_KERNEL);
 	if (!state->crtcs)
@@ -83,16 +81,6 @@ drm_atomic_state_init(struct drm_device *dev, struct drm_atomic_state *state)
 				      sizeof(*state->plane_states), GFP_KERNEL);
 	if (!state->plane_states)
 		goto fail;
-	state->connectors = kcalloc(state->num_connector,
-				    sizeof(*state->connectors),
-				    GFP_KERNEL);
-	if (!state->connectors)
-		goto fail;
-	state->connector_states = kcalloc(state->num_connector,
-					  sizeof(*state->connector_states),
-					  GFP_KERNEL);
-	if (!state->connector_states)
-		goto fail;
 
 	state->dev = dev;
 
@@ -823,19 +811,27 @@ drm_atomic_get_connector_state(struct drm_atomic_state *state,
 
 	index = drm_connector_index(connector);
 
-	/*
-	 * Construction of atomic state updates can race with a connector
-	 * hot-add which might overflow. In this case flip the table and just
-	 * restart the entire ioctl - no one is fast enough to livelock a cpu
-	 * with physical hotplug events anyway.
-	 *
-	 * Note that we only grab the indexes once we have the right lock to
-	 * prevent hotplug/unplugging of connectors. So removal is no problem,
-	 * at most the array is a bit too large.
-	 */
 	if (index >= state->num_connector) {
-		DRM_DEBUG_ATOMIC("Hot-added connector would overflow state array, restarting\n");
-		return ERR_PTR(-EAGAIN);
+		struct drm_connector **c;
+		struct drm_connector_state **cs;
+		int alloc = max(index + 1, config->num_connector);
+
+		c = krealloc(state->connectors, alloc * sizeof(*state->connectors), GFP_KERNEL);
+		if (!c)
+			return ERR_PTR(-ENOMEM);
+
+		state->connectors = c;
+		memset(&state->connectors[state->num_connector], 0,
+		       sizeof(*state->connectors) * (alloc - state->num_connector));
+
+		cs = krealloc(state->connector_states, alloc * sizeof(*state->connector_states), GFP_KERNEL);
+		if (!cs)
+			return ERR_PTR(-ENOMEM);
+
+		state->connector_states = cs;
+		memset(&state->connector_states[state->num_connector], 0,
+		       sizeof(*state->connector_states) * (alloc - state->num_connector));
+		state->num_connector = alloc;
 	}
 
 	if (state->connector_states[index])
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 7c523060a076..4f2d3e161593 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1493,7 +1493,7 @@ void drm_atomic_helper_swap_state(struct drm_device *dev,
 {
 	int i;
 
-	for (i = 0; i < dev->mode_config.num_connector; i++) {
+	for (i = 0; i < state->num_connector; i++) {
 		struct drm_connector *connector = state->connectors[i];
 
 		if (!connector)
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index d40bab29747e..f6191215b2cb 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -918,12 +918,19 @@ int drm_connector_init(struct drm_device *dev,
 	connector->base.properties = &connector->properties;
 	connector->dev = dev;
 	connector->funcs = funcs;
+
+	connector->connector_id = ida_simple_get(&config->connector_ida, 0, 0, GFP_KERNEL);
+	if (connector->connector_id < 0) {
+		ret = connector->connector_id;
+		goto out_put;
+	}
+
 	connector->connector_type = connector_type;
 	connector->connector_type_id =
 		ida_simple_get(connector_ida, 1, 0, GFP_KERNEL);
 	if (connector->connector_type_id < 0) {
 		ret = connector->connector_type_id;
-		goto out_put;
+		goto out_put_id;
 	}
 	connector->name =
 		kasprintf(GFP_KERNEL, "%s-%d",
@@ -931,7 +938,7 @@ int drm_connector_init(struct drm_device *dev,
 			  connector->connector_type_id);
 	if (!connector->name) {
 		ret = -ENOMEM;
-		goto out_put;
+		goto out_put_type_id;
 	}
 
 	INIT_LIST_HEAD(&connector->probed_modes);
@@ -959,7 +966,12 @@ int drm_connector_init(struct drm_device *dev,
 	}
 
 	connector->debugfs_entry = NULL;
-
+out_put_type_id:
+	if (ret)
+		ida_remove(connector_ida, connector->connector_type_id);
+out_put_id:
+	if (ret)
+		ida_remove(&config->connector_ida, connector->connector_id);
 out_put:
 	if (ret)
 		drm_mode_object_put(dev, &connector->base);
@@ -996,6 +1008,9 @@ void drm_connector_cleanup(struct drm_connector *connector)
 	ida_remove(&drm_connector_enum_list[connector->connector_type].ida,
 		   connector->connector_type_id);
 
+	ida_remove(&dev->mode_config.connector_ida,
+		   connector->connector_id);
+
 	kfree(connector->display_info.bus_formats);
 	drm_mode_object_put(dev, &connector->base);
 	kfree(connector->name);
@@ -1013,32 +1028,6 @@ void drm_connector_cleanup(struct drm_connector *connector)
 EXPORT_SYMBOL(drm_connector_cleanup);
 
 /**
- * drm_connector_index - find the index of a registered connector
- * @connector: connector to find index for
- *
- * Given a registered connector, return the index of that connector within a DRM
- * device's list of connectors.
- */
-unsigned int drm_connector_index(struct drm_connector *connector)
-{
-	unsigned int index = 0;
-	struct drm_connector *tmp;
-	struct drm_mode_config *config = &connector->dev->mode_config;
-
-	WARN_ON(!drm_modeset_is_locked(&config->connection_mutex));
-
-	drm_for_each_connector(tmp, connector->dev) {
-		if (tmp == connector)
-			return index;
-
-		index++;
-	}
-
-	BUG();
-}
-EXPORT_SYMBOL(drm_connector_index);
-
-/**
  * drm_connector_register - register a connector
  * @connector: the connector to register
  *
@@ -5789,6 +5778,7 @@ void drm_mode_config_init(struct drm_device *dev)
 	INIT_LIST_HEAD(&dev->mode_config.plane_list);
 	idr_init(&dev->mode_config.crtc_idr);
 	idr_init(&dev->mode_config.tile_idr);
+	ida_init(&dev->mode_config.connector_ida);
 
 	drm_modeset_lock_all(dev);
 	drm_mode_create_standard_properties(dev);
@@ -5869,6 +5859,7 @@ void drm_mode_config_cleanup(struct drm_device *dev)
 		crtc->funcs->destroy(crtc);
 	}
 
+	ida_destroy(&dev->mode_config.connector_ida);
 	idr_destroy(&dev->mode_config.tile_idr);
 	idr_destroy(&dev->mode_config.crtc_idr);
 	drm_modeset_lock_fini(&dev->mode_config.connection_mutex);
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 8ae13de272c4..27fbd79d0daf 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -1159,11 +1159,13 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb,
 			drm_dp_put_port(port);
 			goto out;
 		}
-
-		drm_mode_connector_set_tile_property(port->connector);
-
+		if (port->port_num >= DP_MST_LOGICAL_PORT_0) {
+			port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc);
+			drm_mode_connector_set_tile_property(port->connector);
+		}
 		(*mstb->mgr->cbs->register_connector)(port->connector);
 	}
+
 out:
 	/* put reference to this port */
 	drm_dp_put_port(port);
@@ -1188,8 +1190,8 @@ static void drm_dp_update_port(struct drm_dp_mst_branch *mstb,
 	port->ddps = conn_stat->displayport_device_plug_status;
 
 	if (old_ddps != port->ddps) {
-		dowork = true;
 		if (port->ddps) {
+			dowork = true;
 		} else {
 			port->available_pbn = 0;
 		}
@@ -1294,13 +1296,8 @@ static void drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *m
 		if (port->input)
 			continue;
 
-		if (!port->ddps) {
-			if (port->cached_edid) {
-				kfree(port->cached_edid);
-				port->cached_edid = NULL;
-			}
+		if (!port->ddps)
 			continue;
-		}
 
 		if (!port->available_pbn)
 			drm_dp_send_enum_path_resources(mgr, mstb, port);
@@ -1311,12 +1308,6 @@ static void drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *m
 				drm_dp_check_and_send_link_address(mgr, mstb_child);
 				drm_dp_put_mst_branch_device(mstb_child);
 			}
-		} else if (port->pdt == DP_PEER_DEVICE_SST_SINK ||
-			port->pdt == DP_PEER_DEVICE_DP_LEGACY_CONV) {
-			if (!port->cached_edid) {
-				port->cached_edid =
-					drm_get_edid(port->connector, &port->aux.ddc);
-			}
 		}
 	}
 }
@@ -1336,8 +1327,6 @@ static void drm_dp_mst_link_probe_work(struct work_struct *work)
 		drm_dp_check_and_send_link_address(mgr, mstb);
 		drm_dp_put_mst_branch_device(mstb);
 	}
-
-	(*mgr->cbs->hotplug)(mgr);
 }
 
 static bool drm_dp_validate_guid(struct drm_dp_mst_topology_mgr *mgr,
@@ -1597,6 +1586,7 @@ static void drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr,
 			for (i = 0; i < txmsg->reply.u.link_addr.nports; i++) {
 				drm_dp_add_port(mstb, mgr->dev, &txmsg->reply.u.link_addr.ports[i]);
 			}
+			(*mgr->cbs->hotplug)(mgr);
 		}
 	} else {
 		mstb->link_address_sent = false;
@@ -2293,6 +2283,8 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr)
 			drm_dp_update_port(mstb, &msg.u.conn_stat);
 
 			DRM_DEBUG_KMS("Got CSN: pn: %d ldps:%d ddps: %d mcs: %d ip: %d pdt: %d\n", msg.u.conn_stat.port_number, msg.u.conn_stat.legacy_device_plug_status, msg.u.conn_stat.displayport_device_plug_status, msg.u.conn_stat.message_capability_status, msg.u.conn_stat.input_port, msg.u.conn_stat.peer_device_type);
+			(*mgr->cbs->hotplug)(mgr);
+
 		} else if (msg.req_type == DP_RESOURCE_STATUS_NOTIFY) {
 			drm_dp_send_up_ack_reply(mgr, mgr->mst_primary, msg.req_type, seqno, false);
 			if (!mstb)
@@ -2379,6 +2371,10 @@ enum drm_connector_status drm_dp_mst_detect_port(struct drm_connector *connector
 
 	case DP_PEER_DEVICE_SST_SINK:
 		status = connector_status_connected;
+		/* for logical ports - cache the EDID */
+		if (port->port_num >= 8 && !port->cached_edid) {
+			port->cached_edid = drm_get_edid(connector, &port->aux.ddc);
+		}
 		break;
 	case DP_PEER_DEVICE_DP_LEGACY_CONV:
 		if (port->ldps)
@@ -2433,7 +2429,10 @@ struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_
 
 	if (port->cached_edid)
 		edid = drm_edid_duplicate(port->cached_edid);
-
+	else {
+		edid = drm_get_edid(connector, &port->aux.ddc);
+		drm_mode_connector_set_tile_property(connector);
+	}
 	port->has_audio = drm_detect_monitor_audio(edid);
 	drm_dp_put_port(port);
 	return edid;
diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c
index e5df53b6e229..1f500a1b9969 100644
--- a/drivers/gpu/drm/drm_gem_cma_helper.c
+++ b/drivers/gpu/drm/drm_gem_cma_helper.c
@@ -109,8 +109,8 @@ struct drm_gem_cma_object *drm_gem_cma_create(struct drm_device *drm,
 	if (IS_ERR(cma_obj))
 		return cma_obj;
 
-	cma_obj->vaddr = dma_alloc_writecombine(drm->dev, size,
-			&cma_obj->paddr, GFP_KERNEL | __GFP_NOWARN);
+	cma_obj->vaddr = dma_alloc_wc(drm->dev, size, &cma_obj->paddr,
+				      GFP_KERNEL | __GFP_NOWARN);
 	if (!cma_obj->vaddr) {
 		dev_err(drm->dev, "failed to allocate buffer with size %zu\n",
 			size);
@@ -192,8 +192,8 @@ void drm_gem_cma_free_object(struct drm_gem_object *gem_obj)
 	cma_obj = to_drm_gem_cma_obj(gem_obj);
 
 	if (cma_obj->vaddr) {
-		dma_free_writecombine(gem_obj->dev->dev, cma_obj->base.size,
-				      cma_obj->vaddr, cma_obj->paddr);
+		dma_free_wc(gem_obj->dev->dev, cma_obj->base.size,
+			    cma_obj->vaddr, cma_obj->paddr);
 	} else if (gem_obj->import_attach) {
 		drm_prime_gem_destroy(gem_obj, cma_obj->sgt);
 	}
@@ -324,9 +324,8 @@ static int drm_gem_cma_mmap_obj(struct drm_gem_cma_object *cma_obj,
 	vma->vm_flags &= ~VM_PFNMAP;
 	vma->vm_pgoff = 0;
 
-	ret = dma_mmap_writecombine(cma_obj->base.dev->dev, vma,
-				    cma_obj->vaddr, cma_obj->paddr,
-				    vma->vm_end - vma->vm_start);
+	ret = dma_mmap_wc(cma_obj->base.dev->dev, vma, cma_obj->vaddr,
+			  cma_obj->paddr, vma->vm_end - vma->vm_start);
 	if (ret)
 		drm_gem_vm_close(vma);
 
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index d12a4efa651b..1fe14579e8c9 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -224,6 +224,64 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe,
 		diff = (flags & DRM_CALLED_FROM_VBLIRQ) != 0;
 	}
 
+	/*
+	 * Within a drm_vblank_pre_modeset - drm_vblank_post_modeset
+	 * interval? If so then vblank irqs keep running and it will likely
+	 * happen that the hardware vblank counter is not trustworthy as it
+	 * might reset at some point in that interval and vblank timestamps
+	 * are not trustworthy either in that interval. Iow. this can result
+	 * in a bogus diff >> 1 which must be avoided as it would cause
+	 * random large forward jumps of the software vblank counter.
+	 */
+	if (diff > 1 && (vblank->inmodeset & 0x2)) {
+		DRM_DEBUG_VBL("clamping vblank bump to 1 on crtc %u: diffr=%u"
+			      " due to pre-modeset.\n", pipe, diff);
+		diff = 1;
+	}
+
+	/*
+	 * FIMXE: Need to replace this hack with proper seqlocks.
+	 *
+	 * Restrict the bump of the software vblank counter to a safe maximum
+	 * value of +1 whenever there is the possibility that concurrent readers
+	 * of vblank timestamps could be active at the moment, as the current
+	 * implementation of the timestamp caching and updating is not safe
+	 * against concurrent readers for calls to store_vblank() with a bump
+	 * of anything but +1. A bump != 1 would very likely return corrupted
+	 * timestamps to userspace, because the same slot in the cache could
+	 * be concurrently written by store_vblank() and read by one of those
+	 * readers without the read-retry logic detecting the collision.
+	 *
+	 * Concurrent readers can exist when we are called from the
+	 * drm_vblank_off() or drm_vblank_on() functions and other non-vblank-
+	 * irq callers. However, all those calls to us are happening with the
+	 * vbl_lock locked to prevent drm_vblank_get(), so the vblank refcount
+	 * can't increase while we are executing. Therefore a zero refcount at
+	 * this point is safe for arbitrary counter bumps if we are called
+	 * outside vblank irq, a non-zero count is not 100% safe. Unfortunately
+	 * we must also accept a refcount of 1, as whenever we are called from
+	 * drm_vblank_get() -> drm_vblank_enable() the refcount will be 1 and
+	 * we must let that one pass through in order to not lose vblank counts
+	 * during vblank irq off - which would completely defeat the whole
+	 * point of this routine.
+	 *
+	 * Whenever we are called from vblank irq, we have to assume concurrent
+	 * readers exist or can show up any time during our execution, even if
+	 * the refcount is currently zero, as vblank irqs are usually only
+	 * enabled due to the presence of readers, and because when we are called
+	 * from vblank irq we can't hold the vbl_lock to protect us from sudden
+	 * bumps in vblank refcount. Therefore also restrict bumps to +1 when
+	 * called from vblank irq.
+	 */
+	if ((diff > 1) && (atomic_read(&vblank->refcount) > 1 ||
+	    (flags & DRM_CALLED_FROM_VBLIRQ))) {
+		DRM_DEBUG_VBL("clamping vblank bump to 1 on crtc %u: diffr=%u "
+			      "refcount %u, vblirq %u\n", pipe, diff,
+			      atomic_read(&vblank->refcount),
+			      (flags & DRM_CALLED_FROM_VBLIRQ) != 0);
+		diff = 1;
+	}
+
 	DRM_DEBUG_VBL("updating vblank count on crtc %u:"
 		      " current=%u, diff=%u, hw=%u hw_last=%u\n",
 		      pipe, vblank->count, diff, cur_vblank, vblank->last);
@@ -1316,7 +1374,13 @@ void drm_vblank_off(struct drm_device *dev, unsigned int pipe)
 	spin_lock_irqsave(&dev->event_lock, irqflags);
 
 	spin_lock(&dev->vbl_lock);
-	vblank_disable_and_save(dev, pipe);
+	DRM_DEBUG_VBL("crtc %d, vblank enabled %d, inmodeset %d\n",
+		      pipe, vblank->enabled, vblank->inmodeset);
+
+	/* Avoid redundant vblank disables without previous drm_vblank_on(). */
+	if (drm_core_check_feature(dev, DRIVER_ATOMIC) || !vblank->inmodeset)
+		vblank_disable_and_save(dev, pipe);
+
 	wake_up(&vblank->queue);
 
 	/*
@@ -1418,6 +1482,9 @@ void drm_vblank_on(struct drm_device *dev, unsigned int pipe)
 		return;
 
 	spin_lock_irqsave(&dev->vbl_lock, irqflags);
+	DRM_DEBUG_VBL("crtc %d, vblank enabled %d, inmodeset %d\n",
+		      pipe, vblank->enabled, vblank->inmodeset);
+
 	/* Drop our private "prevent drm_vblank_get" refcount */
 	if (vblank->inmodeset) {
 		atomic_dec(&vblank->refcount);
@@ -1430,8 +1497,7 @@ void drm_vblank_on(struct drm_device *dev, unsigned int pipe)
 	 * re-enable interrupts if there are users left, or the
 	 * user wishes vblank interrupts to be enabled all the time.
 	 */
-	if (atomic_read(&vblank->refcount) != 0 ||
-	    (!dev->vblank_disable_immediate && drm_vblank_offdelay == 0))
+	if (atomic_read(&vblank->refcount) != 0 || drm_vblank_offdelay == 0)
 		WARN_ON(drm_vblank_enable(dev, pipe));
 	spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
 }
@@ -1526,6 +1592,7 @@ void drm_vblank_post_modeset(struct drm_device *dev, unsigned int pipe)
 	if (vblank->inmodeset) {
 		spin_lock_irqsave(&dev->vbl_lock, irqflags);
 		dev->vblank_disable_allowed = true;
+		drm_reset_vblank_timestamp(dev, pipe);
 		spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
 
 		if (vblank->inmodeset & 0x2)
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index a33162cf4f4c..3c1ce44483d9 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -1113,8 +1113,8 @@ struct etnaviv_cmdbuf *etnaviv_gpu_cmdbuf_new(struct etnaviv_gpu *gpu, u32 size,
 	if (!cmdbuf)
 		return NULL;
 
-	cmdbuf->vaddr = dma_alloc_writecombine(gpu->dev, size, &cmdbuf->paddr,
-					       GFP_KERNEL);
+	cmdbuf->vaddr = dma_alloc_wc(gpu->dev, size, &cmdbuf->paddr,
+				     GFP_KERNEL);
 	if (!cmdbuf->vaddr) {
 		kfree(cmdbuf);
 		return NULL;
@@ -1128,8 +1128,8 @@ struct etnaviv_cmdbuf *etnaviv_gpu_cmdbuf_new(struct etnaviv_gpu *gpu, u32 size,
 
 void etnaviv_gpu_cmdbuf_free(struct etnaviv_cmdbuf *cmdbuf)
 {
-	dma_free_writecombine(cmdbuf->gpu->dev, cmdbuf->size,
-			      cmdbuf->vaddr, cmdbuf->paddr);
+	dma_free_wc(cmdbuf->gpu->dev, cmdbuf->size, cmdbuf->vaddr,
+		    cmdbuf->paddr);
 	kfree(cmdbuf);
 }
 
diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig
index 83efca941388..f17d39279596 100644
--- a/drivers/gpu/drm/exynos/Kconfig
+++ b/drivers/gpu/drm/exynos/Kconfig
@@ -1,6 +1,6 @@
 config DRM_EXYNOS
 	tristate "DRM Support for Samsung SoC EXYNOS Series"
-	depends on OF && DRM && (PLAT_SAMSUNG || ARCH_MULTIPLATFORM)
+	depends on OF && DRM && (ARCH_S3C64XX || ARCH_EXYNOS || ARCH_MULTIPLATFORM)
 	select DRM_KMS_HELPER
 	select DRM_KMS_FB_HELPER
 	select FB_CFB_FILLRECT
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 1bf6a21130c7..162ab93e99cb 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -93,7 +93,7 @@ static int decon_enable_vblank(struct exynos_drm_crtc *crtc)
 	if (test_bit(BIT_SUSPENDED, &ctx->flags))
 		return -EPERM;
 
-	if (test_and_set_bit(BIT_IRQS_ENABLED, &ctx->flags)) {
+	if (!test_and_set_bit(BIT_IRQS_ENABLED, &ctx->flags)) {
 		val = VIDINTCON0_INTEN;
 		if (ctx->out_type == IFTYPE_I80)
 			val |= VIDINTCON0_FRAMEDONE;
@@ -402,8 +402,6 @@ static void decon_enable(struct exynos_drm_crtc *crtc)
 		decon_enable_vblank(ctx->crtc);
 
 	decon_commit(ctx->crtc);
-
-	set_bit(BIT_SUSPENDED, &ctx->flags);
 }
 
 static void decon_disable(struct exynos_drm_crtc *crtc)
@@ -582,9 +580,9 @@ out:
 static int exynos5433_decon_suspend(struct device *dev)
 {
 	struct decon_context *ctx = dev_get_drvdata(dev);
-	int i;
+	int i = ARRAY_SIZE(decon_clks_name);
 
-	for (i = 0; i < ARRAY_SIZE(decon_clks_name); i++)
+	while (--i >= 0)
 		clk_disable_unprepare(ctx->clks[i]);
 
 	return 0;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index e977a81af2e6..26e81d191f56 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -1782,6 +1782,7 @@ static int exynos_dsi_bind(struct device *dev, struct device *master,
 
 	bridge = of_drm_find_bridge(dsi->bridge_node);
 	if (bridge) {
+		encoder->bridge = bridge;
 		drm_bridge_attach(drm_dev, bridge);
 	}
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
index f6118baa8e3e..8baabd813ff5 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
@@ -50,7 +50,7 @@ static int exynos_drm_fb_mmap(struct fb_info *info,
 	if (vm_size > exynos_gem->size)
 		return -EINVAL;
 
-	ret = dma_mmap_attrs(helper->dev->dev, vma, exynos_gem->pages,
+	ret = dma_mmap_attrs(helper->dev->dev, vma, exynos_gem->cookie,
 			     exynos_gem->dma_addr, exynos_gem->size,
 			     &exynos_gem->dma_attrs);
 	if (ret < 0) {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index c747824f3c98..8a4f4a0211d0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -1723,7 +1723,7 @@ static int fimc_probe(struct platform_device *pdev)
 		goto err_put_clk;
 	}
 
-	DRM_DEBUG_KMS("id[%d]ippdrv[0x%x]\n", ctx->id, (int)ippdrv);
+	DRM_DEBUG_KMS("id[%d]ippdrv[%p]\n", ctx->id, ippdrv);
 
 	spin_lock_init(&ctx->lock);
 	platform_set_drvdata(pdev, ctx);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index c17efdb238a6..8dfe6e113a88 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -1166,7 +1166,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 		goto err_free_event;
 	}
 
-	cmd = (struct drm_exynos_g2d_cmd *)(uint32_t)req->cmd;
+	cmd = (struct drm_exynos_g2d_cmd *)(unsigned long)req->cmd;
 
 	if (copy_from_user(cmdlist->data + cmdlist->last,
 				(void __user *)cmd,
@@ -1184,7 +1184,8 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	if (req->cmd_buf_nr) {
 		struct drm_exynos_g2d_cmd *cmd_buf;
 
-		cmd_buf = (struct drm_exynos_g2d_cmd *)(uint32_t)req->cmd_buf;
+		cmd_buf = (struct drm_exynos_g2d_cmd *)
+				(unsigned long)req->cmd_buf;
 
 		if (copy_from_user(cmdlist->data + cmdlist->last,
 					(void __user *)cmd_buf,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 32358c5e3db4..26b5e4bd55b6 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -218,7 +218,7 @@ static struct exynos_drm_gem *exynos_drm_gem_init(struct drm_device *dev,
 		return ERR_PTR(ret);
 	}
 
-	DRM_DEBUG_KMS("created file object = 0x%x\n", (unsigned int)obj->filp);
+	DRM_DEBUG_KMS("created file object = %p\n", obj->filp);
 
 	return exynos_gem;
 }
@@ -335,7 +335,7 @@ static int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem *exynos_gem,
 	if (vm_size > exynos_gem->size)
 		return -EINVAL;
 
-	ret = dma_mmap_attrs(drm_dev->dev, vma, exynos_gem->pages,
+	ret = dma_mmap_attrs(drm_dev->dev, vma, exynos_gem->cookie,
 			     exynos_gem->dma_addr, exynos_gem->size,
 			     &exynos_gem->dma_attrs);
 	if (ret < 0) {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index 7aecd23cfa11..5d20da8f957e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -1723,7 +1723,7 @@ static int gsc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	DRM_DEBUG_KMS("id[%d]ippdrv[0x%x]\n", ctx->id, (int)ippdrv);
+	DRM_DEBUG_KMS("id[%d]ippdrv[%p]\n", ctx->id, ippdrv);
 
 	mutex_init(&ctx->lock);
 	platform_set_drvdata(pdev, ctx);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
index 67d24236e745..95eeb9116f10 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
@@ -208,7 +208,7 @@ static struct exynos_drm_ippdrv *ipp_find_drv_by_handle(u32 prop_id)
 	 * e.g PAUSE state, queue buf, command control.
 	 */
 	list_for_each_entry(ippdrv, &exynos_drm_ippdrv_list, drv_list) {
-		DRM_DEBUG_KMS("count[%d]ippdrv[0x%x]\n", count++, (int)ippdrv);
+		DRM_DEBUG_KMS("count[%d]ippdrv[%p]\n", count++, ippdrv);
 
 		mutex_lock(&ippdrv->cmd_lock);
 		list_for_each_entry(c_node, &ippdrv->cmd_list, list) {
@@ -388,8 +388,8 @@ int exynos_drm_ipp_set_property(struct drm_device *drm_dev, void *data,
 	}
 	property->prop_id = ret;
 
-	DRM_DEBUG_KMS("created prop_id[%d]cmd[%d]ippdrv[0x%x]\n",
-		property->prop_id, property->cmd, (int)ippdrv);
+	DRM_DEBUG_KMS("created prop_id[%d]cmd[%d]ippdrv[%p]\n",
+		property->prop_id, property->cmd, ippdrv);
 
 	/* stored property information and ippdrv in private data */
 	c_node->property = *property;
@@ -518,7 +518,7 @@ static int ipp_put_mem_node(struct drm_device *drm_dev,
 {
 	int i;
 
-	DRM_DEBUG_KMS("node[0x%x]\n", (int)m_node);
+	DRM_DEBUG_KMS("node[%p]\n", m_node);
 
 	if (!m_node) {
 		DRM_ERROR("invalid dequeue node.\n");
@@ -562,7 +562,7 @@ static struct drm_exynos_ipp_mem_node
 	m_node->buf_id = qbuf->buf_id;
 	INIT_LIST_HEAD(&m_node->list);
 
-	DRM_DEBUG_KMS("m_node[0x%x]ops_id[%d]\n", (int)m_node, qbuf->ops_id);
+	DRM_DEBUG_KMS("m_node[%p]ops_id[%d]\n", m_node, qbuf->ops_id);
 	DRM_DEBUG_KMS("prop_id[%d]buf_id[%d]\n", qbuf->prop_id, m_node->buf_id);
 
 	for_each_ipp_planar(i) {
@@ -582,8 +582,8 @@ static struct drm_exynos_ipp_mem_node
 
 			buf_info->handles[i] = qbuf->handle[i];
 			buf_info->base[i] = *addr;
-			DRM_DEBUG_KMS("i[%d]base[0x%x]hd[0x%lx]\n", i,
-				      buf_info->base[i], buf_info->handles[i]);
+			DRM_DEBUG_KMS("i[%d]base[%pad]hd[0x%lx]\n", i,
+				      &buf_info->base[i], buf_info->handles[i]);
 		}
 	}
 
@@ -664,7 +664,7 @@ static void ipp_put_event(struct drm_exynos_ipp_cmd_node *c_node,
 
 	mutex_lock(&c_node->event_lock);
 	list_for_each_entry_safe(e, te, &c_node->event_list, base.link) {
-		DRM_DEBUG_KMS("count[%d]e[0x%x]\n", count++, (int)e);
+		DRM_DEBUG_KMS("count[%d]e[%p]\n", count++, e);
 
 		/*
 		 * qbuf == NULL condition means all event deletion.
@@ -755,7 +755,7 @@ static struct drm_exynos_ipp_mem_node
 
 	/* find memory node from memory list */
 	list_for_each_entry(m_node, head, list) {
-		DRM_DEBUG_KMS("count[%d]m_node[0x%x]\n", count++, (int)m_node);
+		DRM_DEBUG_KMS("count[%d]m_node[%p]\n", count++, m_node);
 
 		/* compare buffer id */
 		if (m_node->buf_id == qbuf->buf_id)
@@ -772,7 +772,7 @@ static int ipp_set_mem_node(struct exynos_drm_ippdrv *ippdrv,
 	struct exynos_drm_ipp_ops *ops = NULL;
 	int ret = 0;
 
-	DRM_DEBUG_KMS("node[0x%x]\n", (int)m_node);
+	DRM_DEBUG_KMS("node[%p]\n", m_node);
 
 	if (!m_node) {
 		DRM_ERROR("invalid queue node.\n");
@@ -1237,7 +1237,7 @@ static int ipp_start_property(struct exynos_drm_ippdrv *ippdrv,
 			m_node = list_first_entry(head,
 				struct drm_exynos_ipp_mem_node, list);
 
-			DRM_DEBUG_KMS("m_node[0x%x]\n", (int)m_node);
+			DRM_DEBUG_KMS("m_node[%p]\n", m_node);
 
 			ret = ipp_set_mem_node(ippdrv, c_node, m_node);
 			if (ret) {
@@ -1610,8 +1610,8 @@ static int ipp_subdrv_probe(struct drm_device *drm_dev, struct device *dev)
 		}
 		ippdrv->prop_list.ipp_id = ret;
 
-		DRM_DEBUG_KMS("count[%d]ippdrv[0x%x]ipp_id[%d]\n",
-			count++, (int)ippdrv, ret);
+		DRM_DEBUG_KMS("count[%d]ippdrv[%p]ipp_id[%d]\n",
+			count++, ippdrv, ret);
 
 		/* store parent device for node */
 		ippdrv->parent_dev = dev;
@@ -1668,7 +1668,7 @@ static int ipp_subdrv_open(struct drm_device *drm_dev, struct device *dev,
 
 	file_priv->ipp_dev = dev;
 
-	DRM_DEBUG_KMS("done priv[0x%x]\n", (int)dev);
+	DRM_DEBUG_KMS("done priv[%p]\n", dev);
 
 	return 0;
 }
@@ -1685,8 +1685,8 @@ static void ipp_subdrv_close(struct drm_device *drm_dev, struct device *dev,
 		mutex_lock(&ippdrv->cmd_lock);
 		list_for_each_entry_safe(c_node, tc_node,
 			&ippdrv->cmd_list, list) {
-			DRM_DEBUG_KMS("count[%d]ippdrv[0x%x]\n",
-				count++, (int)ippdrv);
+			DRM_DEBUG_KMS("count[%d]ippdrv[%p]\n",
+				count++, ippdrv);
 
 			if (c_node->filp == file) {
 				/*
diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c
index 4eaef36aec5a..9869d70e9e54 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_mic.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c
@@ -18,6 +18,7 @@
 #include <linux/of.h>
 #include <linux/of_graph.h>
 #include <linux/clk.h>
+#include <linux/component.h>
 #include <drm/drmP.h>
 #include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
@@ -306,9 +307,9 @@ exit:
 	return ret;
 }
 
-void mic_disable(struct drm_bridge *bridge) { }
+static void mic_disable(struct drm_bridge *bridge) { }
 
-void mic_post_disable(struct drm_bridge *bridge)
+static void mic_post_disable(struct drm_bridge *bridge)
 {
 	struct exynos_mic *mic = bridge->driver_private;
 	int i;
@@ -328,7 +329,7 @@ already_disabled:
 	mutex_unlock(&mic_mutex);
 }
 
-void mic_pre_enable(struct drm_bridge *bridge)
+static void mic_pre_enable(struct drm_bridge *bridge)
 {
 	struct exynos_mic *mic = bridge->driver_private;
 	int ret, i;
@@ -371,11 +372,35 @@ already_enabled:
 	mutex_unlock(&mic_mutex);
 }
 
-void mic_enable(struct drm_bridge *bridge) { }
+static void mic_enable(struct drm_bridge *bridge) { }
 
-void mic_destroy(struct drm_bridge *bridge)
+static const struct drm_bridge_funcs mic_bridge_funcs = {
+	.disable = mic_disable,
+	.post_disable = mic_post_disable,
+	.pre_enable = mic_pre_enable,
+	.enable = mic_enable,
+};
+
+static int exynos_mic_bind(struct device *dev, struct device *master,
+			   void *data)
 {
-	struct exynos_mic *mic = bridge->driver_private;
+	struct exynos_mic *mic = dev_get_drvdata(dev);
+	int ret;
+
+	mic->bridge.funcs = &mic_bridge_funcs;
+	mic->bridge.of_node = dev->of_node;
+	mic->bridge.driver_private = mic;
+	ret = drm_bridge_add(&mic->bridge);
+	if (ret)
+		DRM_ERROR("mic: Failed to add MIC to the global bridge list\n");
+
+	return ret;
+}
+
+static void exynos_mic_unbind(struct device *dev, struct device *master,
+			      void *data)
+{
+	struct exynos_mic *mic = dev_get_drvdata(dev);
 	int i;
 
 	mutex_lock(&mic_mutex);
@@ -387,16 +412,16 @@ void mic_destroy(struct drm_bridge *bridge)
 
 already_disabled:
 	mutex_unlock(&mic_mutex);
+
+	drm_bridge_remove(&mic->bridge);
 }
 
-static const struct drm_bridge_funcs mic_bridge_funcs = {
-	.disable = mic_disable,
-	.post_disable = mic_post_disable,
-	.pre_enable = mic_pre_enable,
-	.enable = mic_enable,
+static const struct component_ops exynos_mic_component_ops = {
+	.bind	= exynos_mic_bind,
+	.unbind	= exynos_mic_unbind,
 };
 
-int exynos_mic_probe(struct platform_device *pdev)
+static int exynos_mic_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct exynos_mic *mic;
@@ -435,17 +460,8 @@ int exynos_mic_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	mic->bridge.funcs = &mic_bridge_funcs;
-	mic->bridge.of_node = dev->of_node;
-	mic->bridge.driver_private = mic;
-	ret = drm_bridge_add(&mic->bridge);
-	if (ret) {
-		DRM_ERROR("mic: Failed to add MIC to the global bridge list\n");
-		goto err;
-	}
-
 	for (i = 0; i < NUM_CLKS; i++) {
-		mic->clks[i] = of_clk_get_by_name(dev->of_node, clk_names[i]);
+		mic->clks[i] = devm_clk_get(dev, clk_names[i]);
 		if (IS_ERR(mic->clks[i])) {
 			DRM_ERROR("mic: Failed to get clock (%s)\n",
 								clk_names[i]);
@@ -454,7 +470,10 @@ int exynos_mic_probe(struct platform_device *pdev)
 		}
 	}
 
+	platform_set_drvdata(pdev, mic);
+
 	DRM_DEBUG_KMS("MIC has been probed\n");
+	return component_add(dev, &exynos_mic_component_ops);
 
 err:
 	return ret;
@@ -462,14 +481,7 @@ err:
 
 static int exynos_mic_remove(struct platform_device *pdev)
 {
-	struct exynos_mic *mic = platform_get_drvdata(pdev);
-	int i;
-
-	drm_bridge_remove(&mic->bridge);
-
-	for (i = NUM_CLKS - 1; i > -1; i--)
-		clk_put(mic->clks[i]);
-
+	component_del(&pdev->dev, &exynos_mic_component_ops);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index bea0f7826d30..ce59f4443394 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -754,7 +754,7 @@ static int rotator_probe(struct platform_device *pdev)
 		goto err_ippdrv_register;
 	}
 
-	DRM_DEBUG_KMS("ippdrv[0x%x]\n", (int)ippdrv);
+	DRM_DEBUG_KMS("ippdrv[%p]\n", ippdrv);
 
 	platform_set_drvdata(pdev, rot);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 62ac4e5fa51d..b605bd7395ec 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -223,7 +223,7 @@ static void vidi_fake_vblank_handler(struct work_struct *work)
 	}
 }
 
-static int vidi_show_connection(struct device *dev,
+static ssize_t vidi_show_connection(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	struct vidi_context *ctx = dev_get_drvdata(dev);
@@ -238,7 +238,7 @@ static int vidi_show_connection(struct device *dev,
 	return rc;
 }
 
-static int vidi_store_connection(struct device *dev,
+static ssize_t vidi_store_connection(struct device *dev,
 				struct device_attribute *attr,
 				const char *buf, size_t len)
 {
@@ -294,7 +294,9 @@ int vidi_connection_ioctl(struct drm_device *drm_dev, void *data,
 	}
 
 	if (vidi->connection) {
-		struct edid *raw_edid  = (struct edid *)(uint32_t)vidi->edid;
+		struct edid *raw_edid;
+
+		raw_edid = (struct edid *)(unsigned long)vidi->edid;
 		if (!drm_edid_is_valid(raw_edid)) {
 			DRM_DEBUG_KMS("edid data is invalid.\n");
 			return -EINVAL;
diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index 34e38749a817..f8ee740c0e26 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -1382,8 +1382,16 @@ static void tda998x_connector_destroy(struct drm_connector *connector)
 	drm_connector_cleanup(connector);
 }
 
+static int tda998x_connector_dpms(struct drm_connector *connector, int mode)
+{
+	if (drm_core_check_feature(connector->dev, DRIVER_ATOMIC))
+		return drm_atomic_helper_connector_dpms(connector, mode);
+	else
+		return drm_helper_connector_dpms(connector, mode);
+}
+
 static const struct drm_connector_funcs tda998x_connector_funcs = {
-	.dpms = drm_atomic_helper_connector_dpms,
+	.dpms = tda998x_connector_dpms,
 	.reset = drm_atomic_helper_connector_reset,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.detect = tda998x_connector_detect,
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 0fc38bb7276c..cf39ed3133d6 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -825,8 +825,11 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 		}
 
 		for_each_pipe(dev_priv, pipe) {
-			if (!intel_display_power_is_enabled(dev_priv,
-						POWER_DOMAIN_PIPE(pipe))) {
+			enum intel_display_power_domain power_domain;
+
+			power_domain = POWER_DOMAIN_PIPE(pipe);
+			if (!intel_display_power_get_if_enabled(dev_priv,
+								power_domain)) {
 				seq_printf(m, "Pipe %c power disabled\n",
 					   pipe_name(pipe));
 				continue;
@@ -840,6 +843,8 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 			seq_printf(m, "Pipe %c IER:\t%08x\n",
 				   pipe_name(pipe),
 				   I915_READ(GEN8_DE_PIPE_IER(pipe)));
+
+			intel_display_power_put(dev_priv, power_domain);
 		}
 
 		seq_printf(m, "Display Engine port interrupt mask:\t%08x\n",
@@ -3985,6 +3990,7 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe,
 	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe];
 	struct intel_crtc *crtc = to_intel_crtc(intel_get_crtc_for_pipe(dev,
 									pipe));
+	enum intel_display_power_domain power_domain;
 	u32 val = 0; /* shut up gcc */
 	int ret;
 
@@ -3995,7 +4001,8 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe,
 	if (pipe_crc->source && source)
 		return -EINVAL;
 
-	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PIPE(pipe))) {
+	power_domain = POWER_DOMAIN_PIPE(pipe);
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) {
 		DRM_DEBUG_KMS("Trying to capture CRC while pipe is off\n");
 		return -EIO;
 	}
@@ -4012,7 +4019,7 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe,
 		ret = ivb_pipe_crc_ctl_reg(dev, pipe, &source, &val);
 
 	if (ret != 0)
-		return ret;
+		goto out;
 
 	/* none -> real source transition */
 	if (source) {
@@ -4024,8 +4031,10 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe,
 		entries = kcalloc(INTEL_PIPE_CRC_ENTRIES_NR,
 				  sizeof(pipe_crc->entries[0]),
 				  GFP_KERNEL);
-		if (!entries)
-			return -ENOMEM;
+		if (!entries) {
+			ret = -ENOMEM;
+			goto out;
+		}
 
 		/*
 		 * When IPS gets enabled, the pipe CRC changes. Since IPS gets
@@ -4081,7 +4090,12 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe,
 		hsw_enable_ips(crtc);
 	}
 
-	return 0;
+	ret = 0;
+
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 /*
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f0f75d7c0d94..b0847b915545 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -751,6 +751,7 @@ struct intel_csr {
 	uint32_t mmio_count;
 	i915_reg_t mmioaddr[8];
 	uint32_t mmiodata[8];
+	uint32_t dc_state;
 };
 
 #define DEV_INFO_FOR_EACH_FLAG(func, sep) \
@@ -1988,6 +1989,9 @@ enum hdmi_force_audio {
 #define I915_GTT_OFFSET_NONE ((u32)-1)
 
 struct drm_i915_gem_object_ops {
+	unsigned int flags;
+#define I915_GEM_OBJECT_HAS_STRUCT_PAGE 0x1
+
 	/* Interface between the GEM object and its backing storage.
 	 * get_pages() is called once prior to the use of the associated set
 	 * of pages before to binding them into the GTT, and put_pages() is
@@ -2003,6 +2007,7 @@ struct drm_i915_gem_object_ops {
 	 */
 	int (*get_pages)(struct drm_i915_gem_object *);
 	void (*put_pages)(struct drm_i915_gem_object *);
+
 	int (*dmabuf_export)(struct drm_i915_gem_object *);
 	void (*release)(struct drm_i915_gem_object *);
 };
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ddc21d4b388d..bb44bad15403 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4425,6 +4425,7 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 }
 
 static const struct drm_i915_gem_object_ops i915_gem_object_ops = {
+	.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE,
 	.get_pages = i915_gem_object_get_pages_gtt,
 	.put_pages = i915_gem_object_put_pages_gtt,
 };
@@ -5261,7 +5262,7 @@ i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj, int n)
 	struct page *page;
 
 	/* Only default objects have per-page dirty tracking */
-	if (WARN_ON(obj->ops != &i915_gem_object_ops))
+	if (WARN_ON((obj->ops->flags & I915_GEM_OBJECT_HAS_STRUCT_PAGE) == 0))
 		return NULL;
 
 	page = i915_gem_object_get_page(obj, n);
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 19fb0bddc1cd..59e45b3a6937 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -789,9 +789,10 @@ i915_gem_userptr_dmabuf_export(struct drm_i915_gem_object *obj)
 }
 
 static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = {
-	.dmabuf_export = i915_gem_userptr_dmabuf_export,
+	.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE,
 	.get_pages = i915_gem_userptr_get_pages,
 	.put_pages = i915_gem_userptr_put_pages,
+	.dmabuf_export = i915_gem_userptr_dmabuf_export,
 	.release = i915_gem_userptr_release,
 };
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 007ae83a4086..4897728713f6 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3287,19 +3287,20 @@ enum skl_disp_power_wells {
 
 #define PORT_HOTPLUG_STAT	_MMIO(dev_priv->info.display_mmio_offset + 0x61114)
 /*
- * HDMI/DP bits are gen4+
+ * HDMI/DP bits are g4x+
  *
  * WARNING: Bspec for hpd status bits on gen4 seems to be completely confused.
  * Please check the detailed lore in the commit message for for experimental
  * evidence.
  */
-#define   PORTD_HOTPLUG_LIVE_STATUS_G4X		(1 << 29)
+/* Bspec says GM45 should match G4X/VLV/CHV, but reality disagrees */
+#define   PORTD_HOTPLUG_LIVE_STATUS_GM45	(1 << 29)
+#define   PORTC_HOTPLUG_LIVE_STATUS_GM45	(1 << 28)
+#define   PORTB_HOTPLUG_LIVE_STATUS_GM45	(1 << 27)
+/* G4X/VLV/CHV DP/HDMI bits again match Bspec */
+#define   PORTD_HOTPLUG_LIVE_STATUS_G4X		(1 << 27)
 #define   PORTC_HOTPLUG_LIVE_STATUS_G4X		(1 << 28)
-#define   PORTB_HOTPLUG_LIVE_STATUS_G4X		(1 << 27)
-/* VLV DP/HDMI bits again match Bspec */
-#define   PORTD_HOTPLUG_LIVE_STATUS_VLV		(1 << 27)
-#define   PORTC_HOTPLUG_LIVE_STATUS_VLV		(1 << 28)
-#define   PORTB_HOTPLUG_LIVE_STATUS_VLV		(1 << 29)
+#define   PORTB_HOTPLUG_LIVE_STATUS_G4X		(1 << 29)
 #define   PORTD_HOTPLUG_INT_STATUS		(3 << 21)
 #define   PORTD_HOTPLUG_INT_LONG_PULSE		(2 << 21)
 #define   PORTD_HOTPLUG_INT_SHORT_PULSE		(1 << 21)
@@ -7514,7 +7515,7 @@ enum skl_disp_power_wells {
 #define  DPLL_CFGCR2_PDIV_7 (4<<2)
 #define  DPLL_CFGCR2_CENTRAL_FREQ_MASK	(3)
 
-#define DPLL_CFGCR1(id)	_MMIO_PIPE((id) - SKL_DPLL1, _DPLL1_CFGCR1, _DPLL2_CFGCR2)
+#define DPLL_CFGCR1(id)	_MMIO_PIPE((id) - SKL_DPLL1, _DPLL1_CFGCR1, _DPLL2_CFGCR1)
 #define DPLL_CFGCR2(id)	_MMIO_PIPE((id) - SKL_DPLL1, _DPLL1_CFGCR2, _DPLL2_CFGCR2)
 
 /* BXT display engine PLL */
diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index a2aa09ce3202..a8af594fbd00 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -49,7 +49,7 @@ static void i915_save_display(struct drm_device *dev)
 		dev_priv->regfile.savePP_ON_DELAYS = I915_READ(PCH_PP_ON_DELAYS);
 		dev_priv->regfile.savePP_OFF_DELAYS = I915_READ(PCH_PP_OFF_DELAYS);
 		dev_priv->regfile.savePP_DIVISOR = I915_READ(PCH_PP_DIVISOR);
-	} else if (!IS_VALLEYVIEW(dev) && !IS_CHERRYVIEW(dev)) {
+	} else if (INTEL_INFO(dev)->gen <= 4) {
 		dev_priv->regfile.savePP_CONTROL = I915_READ(PP_CONTROL);
 		dev_priv->regfile.savePP_ON_DELAYS = I915_READ(PP_ON_DELAYS);
 		dev_priv->regfile.savePP_OFF_DELAYS = I915_READ(PP_OFF_DELAYS);
@@ -84,7 +84,7 @@ static void i915_restore_display(struct drm_device *dev)
 		I915_WRITE(PCH_PP_OFF_DELAYS, dev_priv->regfile.savePP_OFF_DELAYS);
 		I915_WRITE(PCH_PP_DIVISOR, dev_priv->regfile.savePP_DIVISOR);
 		I915_WRITE(PCH_PP_CONTROL, dev_priv->regfile.savePP_CONTROL);
-	} else if (!IS_VALLEYVIEW(dev) && !IS_CHERRYVIEW(dev)) {
+	} else if (INTEL_INFO(dev)->gen <= 4) {
 		I915_WRITE(PP_ON_DELAYS, dev_priv->regfile.savePP_ON_DELAYS);
 		I915_WRITE(PP_OFF_DELAYS, dev_priv->regfile.savePP_OFF_DELAYS);
 		I915_WRITE(PP_DIVISOR, dev_priv->regfile.savePP_DIVISOR);
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 31f6d212fb1b..30f921421b0c 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -527,6 +527,8 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder)
 
 	mutex_lock(&dev_priv->av_mutex);
 	intel_dig_port->audio_connector = connector;
+	/* referred in audio callbacks */
+	dev_priv->dig_port_map[port] = intel_encoder;
 	mutex_unlock(&dev_priv->av_mutex);
 
 	if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify)
@@ -554,6 +556,7 @@ void intel_audio_codec_disable(struct intel_encoder *intel_encoder)
 
 	mutex_lock(&dev_priv->av_mutex);
 	intel_dig_port->audio_connector = NULL;
+	dev_priv->dig_port_map[port] = NULL;
 	mutex_unlock(&dev_priv->av_mutex);
 
 	if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify)
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 9c89df1af036..a7b4a524fadd 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -71,22 +71,29 @@ static bool intel_crt_get_hw_state(struct intel_encoder *encoder,
 	struct intel_crt *crt = intel_encoder_to_crt(encoder);
 	enum intel_display_power_domain power_domain;
 	u32 tmp;
+	bool ret;
 
 	power_domain = intel_display_port_power_domain(encoder);
-	if (!intel_display_power_is_enabled(dev_priv, power_domain))
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
+	ret = false;
+
 	tmp = I915_READ(crt->adpa_reg);
 
 	if (!(tmp & ADPA_DAC_ENABLE))
-		return false;
+		goto out;
 
 	if (HAS_PCH_CPT(dev))
 		*pipe = PORT_TO_PIPE_CPT(tmp);
 	else
 		*pipe = PORT_TO_PIPE(tmp);
 
-	return true;
+	ret = true;
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 static unsigned int intel_crt_get_flags(struct intel_encoder *encoder)
diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c
index 9bb63a85997a..647d85e77c2f 100644
--- a/drivers/gpu/drm/i915/intel_csr.c
+++ b/drivers/gpu/drm/i915/intel_csr.c
@@ -240,6 +240,8 @@ void intel_csr_load_program(struct drm_i915_private *dev_priv)
 		I915_WRITE(dev_priv->csr.mmioaddr[i],
 			   dev_priv->csr.mmiodata[i]);
 	}
+
+	dev_priv->csr.dc_state = 0;
 }
 
 static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index e6408e5583d7..084d5586585d 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1589,7 +1589,8 @@ skl_ddi_pll_select(struct intel_crtc *intel_crtc,
 			 DPLL_CFGCR2_KDIV(wrpll_params.kdiv) |
 			 DPLL_CFGCR2_PDIV(wrpll_params.pdiv) |
 			 wrpll_params.central_freq;
-	} else if (intel_encoder->type == INTEL_OUTPUT_DISPLAYPORT) {
+	} else if (intel_encoder->type == INTEL_OUTPUT_DISPLAYPORT ||
+		   intel_encoder->type == INTEL_OUTPUT_DP_MST) {
 		switch (crtc_state->port_clock / 2) {
 		case 81000:
 			ctrl1 |= DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_810, 0);
@@ -1968,13 +1969,16 @@ bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector)
 	enum transcoder cpu_transcoder;
 	enum intel_display_power_domain power_domain;
 	uint32_t tmp;
+	bool ret;
 
 	power_domain = intel_display_port_power_domain(intel_encoder);
-	if (!intel_display_power_is_enabled(dev_priv, power_domain))
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
-	if (!intel_encoder->get_hw_state(intel_encoder, &pipe))
-		return false;
+	if (!intel_encoder->get_hw_state(intel_encoder, &pipe)) {
+		ret = false;
+		goto out;
+	}
 
 	if (port == PORT_A)
 		cpu_transcoder = TRANSCODER_EDP;
@@ -1986,23 +1990,33 @@ bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector)
 	switch (tmp & TRANS_DDI_MODE_SELECT_MASK) {
 	case TRANS_DDI_MODE_SELECT_HDMI:
 	case TRANS_DDI_MODE_SELECT_DVI:
-		return (type == DRM_MODE_CONNECTOR_HDMIA);
+		ret = type == DRM_MODE_CONNECTOR_HDMIA;
+		break;
 
 	case TRANS_DDI_MODE_SELECT_DP_SST:
-		if (type == DRM_MODE_CONNECTOR_eDP)
-			return true;
-		return (type == DRM_MODE_CONNECTOR_DisplayPort);
+		ret = type == DRM_MODE_CONNECTOR_eDP ||
+		      type == DRM_MODE_CONNECTOR_DisplayPort;
+		break;
+
 	case TRANS_DDI_MODE_SELECT_DP_MST:
 		/* if the transcoder is in MST state then
 		 * connector isn't connected */
-		return false;
+		ret = false;
+		break;
 
 	case TRANS_DDI_MODE_SELECT_FDI:
-		return (type == DRM_MODE_CONNECTOR_VGA);
+		ret = type == DRM_MODE_CONNECTOR_VGA;
+		break;
 
 	default:
-		return false;
+		ret = false;
+		break;
 	}
+
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 bool intel_ddi_get_hw_state(struct intel_encoder *encoder,
@@ -2014,15 +2028,18 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder,
 	enum intel_display_power_domain power_domain;
 	u32 tmp;
 	int i;
+	bool ret;
 
 	power_domain = intel_display_port_power_domain(encoder);
-	if (!intel_display_power_is_enabled(dev_priv, power_domain))
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
+	ret = false;
+
 	tmp = I915_READ(DDI_BUF_CTL(port));
 
 	if (!(tmp & DDI_BUF_CTL_ENABLE))
-		return false;
+		goto out;
 
 	if (port == PORT_A) {
 		tmp = I915_READ(TRANS_DDI_FUNC_CTL(TRANSCODER_EDP));
@@ -2040,25 +2057,32 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder,
 			break;
 		}
 
-		return true;
-	} else {
-		for (i = TRANSCODER_A; i <= TRANSCODER_C; i++) {
-			tmp = I915_READ(TRANS_DDI_FUNC_CTL(i));
+		ret = true;
 
-			if ((tmp & TRANS_DDI_PORT_MASK)
-			    == TRANS_DDI_SELECT_PORT(port)) {
-				if ((tmp & TRANS_DDI_MODE_SELECT_MASK) == TRANS_DDI_MODE_SELECT_DP_MST)
-					return false;
+		goto out;
+	}
 
-				*pipe = i;
-				return true;
-			}
+	for (i = TRANSCODER_A; i <= TRANSCODER_C; i++) {
+		tmp = I915_READ(TRANS_DDI_FUNC_CTL(i));
+
+		if ((tmp & TRANS_DDI_PORT_MASK) == TRANS_DDI_SELECT_PORT(port)) {
+			if ((tmp & TRANS_DDI_MODE_SELECT_MASK) ==
+			    TRANS_DDI_MODE_SELECT_DP_MST)
+				goto out;
+
+			*pipe = i;
+			ret = true;
+
+			goto out;
 		}
 	}
 
 	DRM_DEBUG_KMS("No pipe for ddi port %c found\n", port_name(port));
 
-	return false;
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 void intel_ddi_enable_pipe_clock(struct intel_crtc *intel_crtc)
@@ -2507,12 +2531,14 @@ static bool hsw_ddi_wrpll_get_hw_state(struct drm_i915_private *dev_priv,
 {
 	uint32_t val;
 
-	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS))
+	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
 		return false;
 
 	val = I915_READ(WRPLL_CTL(pll->id));
 	hw_state->wrpll = val;
 
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+
 	return val & WRPLL_PLL_ENABLE;
 }
 
@@ -2522,12 +2548,14 @@ static bool hsw_ddi_spll_get_hw_state(struct drm_i915_private *dev_priv,
 {
 	uint32_t val;
 
-	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS))
+	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
 		return false;
 
 	val = I915_READ(SPLL_CTL);
 	hw_state->spll = val;
 
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+
 	return val & SPLL_PLL_ENABLE;
 }
 
@@ -2644,16 +2672,19 @@ static bool skl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 	uint32_t val;
 	unsigned int dpll;
 	const struct skl_dpll_regs *regs = skl_dpll_regs;
+	bool ret;
 
-	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS))
+	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
 		return false;
 
+	ret = false;
+
 	/* DPLL0 is not part of the shared DPLLs, so pll->id is 0 for DPLL1 */
 	dpll = pll->id + 1;
 
 	val = I915_READ(regs[pll->id].ctl);
 	if (!(val & LCPLL_PLL_ENABLE))
-		return false;
+		goto out;
 
 	val = I915_READ(DPLL_CTRL1);
 	hw_state->ctrl1 = (val >> (dpll * 6)) & 0x3f;
@@ -2663,8 +2694,12 @@ static bool skl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 		hw_state->cfgcr1 = I915_READ(regs[pll->id].cfgcr1);
 		hw_state->cfgcr2 = I915_READ(regs[pll->id].cfgcr2);
 	}
+	ret = true;
 
-	return true;
+out:
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+
+	return ret;
 }
 
 static void skl_shared_dplls_init(struct drm_i915_private *dev_priv)
@@ -2931,13 +2966,16 @@ static bool bxt_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 {
 	enum port port = (enum port)pll->id;	/* 1:1 port->PLL mapping */
 	uint32_t val;
+	bool ret;
 
-	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS))
+	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
 		return false;
 
+	ret = false;
+
 	val = I915_READ(BXT_PORT_PLL_ENABLE(port));
 	if (!(val & PORT_PLL_ENABLE))
-		return false;
+		goto out;
 
 	hw_state->ebb0 = I915_READ(BXT_PORT_PLL_EBB_0(port));
 	hw_state->ebb0 &= PORT_PLL_P1_MASK | PORT_PLL_P2_MASK;
@@ -2984,7 +3022,12 @@ static bool bxt_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 				 I915_READ(BXT_PORT_PCS_DW12_LN23(port)));
 	hw_state->pcsdw12 &= LANE_STAGGER_MASK | LANESTAGGER_STRAP_OVRD;
 
-	return true;
+	ret = true;
+
+out:
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+
+	return ret;
 }
 
 static void bxt_shared_dplls_init(struct drm_i915_private *dev_priv)
@@ -3119,11 +3162,15 @@ bool intel_ddi_is_audio_enabled(struct drm_i915_private *dev_priv,
 {
 	u32 temp;
 
-	if (intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_AUDIO)) {
+	if (intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_AUDIO)) {
 		temp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD);
+
+		intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO);
+
 		if (temp & AUDIO_OUTPUT_ENABLE(intel_crtc->pipe))
 			return true;
 	}
+
 	return false;
 }
 
@@ -3311,7 +3358,6 @@ void intel_ddi_init(struct drm_device *dev, enum port port)
 	intel_encoder->get_config = intel_ddi_get_config;
 
 	intel_dig_port->port = port;
-	dev_priv->dig_port_map[port] = intel_encoder;
 	intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) &
 					  (DDI_BUF_PORT_REVERSAL |
 					   DDI_A_4_LANES);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 5feb65725c04..46947fffd599 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1351,18 +1351,21 @@ void assert_pipe(struct drm_i915_private *dev_priv,
 	bool cur_state;
 	enum transcoder cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv,
 								      pipe);
+	enum intel_display_power_domain power_domain;
 
 	/* if we need the pipe quirk it must be always on */
 	if ((pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE) ||
 	    (pipe == PIPE_B && dev_priv->quirks & QUIRK_PIPEB_FORCE))
 		state = true;
 
-	if (!intel_display_power_is_enabled(dev_priv,
-				POWER_DOMAIN_TRANSCODER(cpu_transcoder))) {
-		cur_state = false;
-	} else {
+	power_domain = POWER_DOMAIN_TRANSCODER(cpu_transcoder);
+	if (intel_display_power_get_if_enabled(dev_priv, power_domain)) {
 		u32 val = I915_READ(PIPECONF(cpu_transcoder));
 		cur_state = !!(val & PIPECONF_ENABLE);
+
+		intel_display_power_put(dev_priv, power_domain);
+	} else {
+		cur_state = false;
 	}
 
 	I915_STATE_WARN(cur_state != state,
@@ -8171,18 +8174,22 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum intel_display_power_domain power_domain;
 	uint32_t tmp;
+	bool ret;
 
-	if (!intel_display_power_is_enabled(dev_priv,
-					    POWER_DOMAIN_PIPE(crtc->pipe)))
+	power_domain = POWER_DOMAIN_PIPE(crtc->pipe);
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
 	pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe;
 	pipe_config->shared_dpll = DPLL_ID_PRIVATE;
 
+	ret = false;
+
 	tmp = I915_READ(PIPECONF(crtc->pipe));
 	if (!(tmp & PIPECONF_ENABLE))
-		return false;
+		goto out;
 
 	if (IS_G4X(dev) || IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) {
 		switch (tmp & PIPECONF_BPC_MASK) {
@@ -8262,7 +8269,12 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 	pipe_config->base.adjusted_mode.crtc_clock =
 		pipe_config->port_clock / pipe_config->pixel_multiplier;
 
-	return true;
+	ret = true;
+
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 static void ironlake_init_pch_refclk(struct drm_device *dev)
@@ -9366,18 +9378,21 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum intel_display_power_domain power_domain;
 	uint32_t tmp;
+	bool ret;
 
-	if (!intel_display_power_is_enabled(dev_priv,
-					    POWER_DOMAIN_PIPE(crtc->pipe)))
+	power_domain = POWER_DOMAIN_PIPE(crtc->pipe);
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
 	pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe;
 	pipe_config->shared_dpll = DPLL_ID_PRIVATE;
 
+	ret = false;
 	tmp = I915_READ(PIPECONF(crtc->pipe));
 	if (!(tmp & PIPECONF_ENABLE))
-		return false;
+		goto out;
 
 	switch (tmp & PIPECONF_BPC_MASK) {
 	case PIPECONF_6BPC:
@@ -9440,7 +9455,12 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 
 	ironlake_get_pfit_config(crtc, pipe_config);
 
-	return true;
+	ret = true;
+
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv)
@@ -9950,12 +9970,17 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	enum intel_display_power_domain pfit_domain;
+	enum intel_display_power_domain power_domain;
+	unsigned long power_domain_mask;
 	uint32_t tmp;
+	bool ret;
 
-	if (!intel_display_power_is_enabled(dev_priv,
-					 POWER_DOMAIN_PIPE(crtc->pipe)))
+	power_domain = POWER_DOMAIN_PIPE(crtc->pipe);
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
+	power_domain_mask = BIT(power_domain);
+
+	ret = false;
 
 	pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe;
 	pipe_config->shared_dpll = DPLL_ID_PRIVATE;
@@ -9982,13 +10007,14 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 			pipe_config->cpu_transcoder = TRANSCODER_EDP;
 	}
 
-	if (!intel_display_power_is_enabled(dev_priv,
-			POWER_DOMAIN_TRANSCODER(pipe_config->cpu_transcoder)))
-		return false;
+	power_domain = POWER_DOMAIN_TRANSCODER(pipe_config->cpu_transcoder);
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
+		goto out;
+	power_domain_mask |= BIT(power_domain);
 
 	tmp = I915_READ(PIPECONF(pipe_config->cpu_transcoder));
 	if (!(tmp & PIPECONF_ENABLE))
-		return false;
+		goto out;
 
 	haswell_get_ddi_port_state(crtc, pipe_config);
 
@@ -9998,14 +10024,14 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 		skl_init_scalers(dev, crtc, pipe_config);
 	}
 
-	pfit_domain = POWER_DOMAIN_PIPE_PANEL_FITTER(crtc->pipe);
-
 	if (INTEL_INFO(dev)->gen >= 9) {
 		pipe_config->scaler_state.scaler_id = -1;
 		pipe_config->scaler_state.scaler_users &= ~(1 << SKL_CRTC_INDEX);
 	}
 
-	if (intel_display_power_is_enabled(dev_priv, pfit_domain)) {
+	power_domain = POWER_DOMAIN_PIPE_PANEL_FITTER(crtc->pipe);
+	if (intel_display_power_get_if_enabled(dev_priv, power_domain)) {
+		power_domain_mask |= BIT(power_domain);
 		if (INTEL_INFO(dev)->gen >= 9)
 			skylake_get_pfit_config(crtc, pipe_config);
 		else
@@ -10023,7 +10049,13 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 		pipe_config->pixel_multiplier = 1;
 	}
 
-	return true;
+	ret = true;
+
+out:
+	for_each_power_domain(power_domain, power_domain_mask)
+		intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 static void i845_update_cursor(struct drm_crtc *crtc, u32 base, bool on)
@@ -13630,7 +13662,7 @@ static bool ibx_pch_dpll_get_hw_state(struct drm_i915_private *dev_priv,
 {
 	uint32_t val;
 
-	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS))
+	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS))
 		return false;
 
 	val = I915_READ(PCH_DPLL(pll->id));
@@ -13638,6 +13670,8 @@ static bool ibx_pch_dpll_get_hw_state(struct drm_i915_private *dev_priv,
 	hw_state->fp0 = I915_READ(PCH_FP0(pll->id));
 	hw_state->fp1 = I915_READ(PCH_FP1(pll->id));
 
+	intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS);
+
 	return val & DPLL_VCO_ENABLE;
 }
 
@@ -15568,10 +15602,12 @@ void i915_redisable_vga(struct drm_device *dev)
 	 * level, just check if the power well is enabled instead of trying to
 	 * follow the "don't touch the power well if we don't need it" policy
 	 * the rest of the driver uses. */
-	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_VGA))
+	if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_VGA))
 		return;
 
 	i915_redisable_vga_power_on(dev);
+
+	intel_display_power_put(dev_priv, POWER_DOMAIN_VGA);
 }
 
 static bool primary_get_hw_state(struct intel_plane *plane)
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 796e3d313cb9..cdc2c15873dc 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -2362,15 +2362,18 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum intel_display_power_domain power_domain;
 	u32 tmp;
+	bool ret;
 
 	power_domain = intel_display_port_power_domain(encoder);
-	if (!intel_display_power_is_enabled(dev_priv, power_domain))
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
+	ret = false;
+
 	tmp = I915_READ(intel_dp->output_reg);
 
 	if (!(tmp & DP_PORT_EN))
-		return false;
+		goto out;
 
 	if (IS_GEN7(dev) && port == PORT_A) {
 		*pipe = PORT_TO_PIPE_CPT(tmp);
@@ -2381,7 +2384,9 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
 			u32 trans_dp = I915_READ(TRANS_DP_CTL(p));
 			if (TRANS_DP_PIPE_TO_PORT(trans_dp) == port) {
 				*pipe = p;
-				return true;
+				ret = true;
+
+				goto out;
 			}
 		}
 
@@ -2393,7 +2398,12 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
 		*pipe = PORT_TO_PIPE(tmp);
 	}
 
-	return true;
+	ret = true;
+
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 static void intel_dp_get_config(struct intel_encoder *encoder,
@@ -4493,20 +4503,20 @@ static bool g4x_digital_port_connected(struct drm_i915_private *dev_priv,
 	return I915_READ(PORT_HOTPLUG_STAT) & bit;
 }
 
-static bool vlv_digital_port_connected(struct drm_i915_private *dev_priv,
-				       struct intel_digital_port *port)
+static bool gm45_digital_port_connected(struct drm_i915_private *dev_priv,
+					struct intel_digital_port *port)
 {
 	u32 bit;
 
 	switch (port->port) {
 	case PORT_B:
-		bit = PORTB_HOTPLUG_LIVE_STATUS_VLV;
+		bit = PORTB_HOTPLUG_LIVE_STATUS_GM45;
 		break;
 	case PORT_C:
-		bit = PORTC_HOTPLUG_LIVE_STATUS_VLV;
+		bit = PORTC_HOTPLUG_LIVE_STATUS_GM45;
 		break;
 	case PORT_D:
-		bit = PORTD_HOTPLUG_LIVE_STATUS_VLV;
+		bit = PORTD_HOTPLUG_LIVE_STATUS_GM45;
 		break;
 	default:
 		MISSING_CASE(port->port);
@@ -4558,8 +4568,8 @@ bool intel_digital_port_connected(struct drm_i915_private *dev_priv,
 		return cpt_digital_port_connected(dev_priv, port);
 	else if (IS_BROXTON(dev_priv))
 		return bxt_digital_port_connected(dev_priv, port);
-	else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		return vlv_digital_port_connected(dev_priv, port);
+	else if (IS_GM45(dev_priv))
+		return gm45_digital_port_connected(dev_priv, port);
 	else
 		return g4x_digital_port_connected(dev_priv, port);
 }
@@ -6035,7 +6045,6 @@ intel_dp_init(struct drm_device *dev,
 	}
 
 	intel_dig_port->port = port;
-	dev_priv->dig_port_map[port] = intel_encoder;
 	intel_dig_port->dp.output_reg = output_reg;
 
 	intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT;
diff --git a/drivers/gpu/drm/i915/intel_dp_link_training.c b/drivers/gpu/drm/i915/intel_dp_link_training.c
index 88887938e0bf..0b8eefc2acc5 100644
--- a/drivers/gpu/drm/i915/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/intel_dp_link_training.c
@@ -215,27 +215,46 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp)
 	}
 }
 
-static void
-intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
+/*
+ * Pick training pattern for channel equalization. Training Pattern 3 for HBR2
+ * or 1.2 devices that support it, Training Pattern 2 otherwise.
+ */
+static u32 intel_dp_training_pattern(struct intel_dp *intel_dp)
 {
-	bool channel_eq = false;
-	int tries, cr_tries;
-	uint32_t training_pattern = DP_TRAINING_PATTERN_2;
+	u32 training_pattern = DP_TRAINING_PATTERN_2;
+	bool source_tps3, sink_tps3;
 
 	/*
-	 * Training Pattern 3 for HBR2 or 1.2 devices that support it.
-	 *
 	 * Intel platforms that support HBR2 also support TPS3. TPS3 support is
-	 * also mandatory for downstream devices that support HBR2.
+	 * also mandatory for downstream devices that support HBR2. However, not
+	 * all sinks follow the spec.
 	 *
 	 * Due to WaDisableHBR2 SKL < B0 is the only exception where TPS3 is
-	 * supported but still not enabled.
+	 * supported in source but still not enabled.
 	 */
-	if (intel_dp_source_supports_hbr2(intel_dp) &&
-	    drm_dp_tps3_supported(intel_dp->dpcd))
+	source_tps3 = intel_dp_source_supports_hbr2(intel_dp);
+	sink_tps3 = drm_dp_tps3_supported(intel_dp->dpcd);
+
+	if (source_tps3 && sink_tps3) {
 		training_pattern = DP_TRAINING_PATTERN_3;
-	else if (intel_dp->link_rate == 540000)
-		DRM_ERROR("5.4 Gbps link rate without HBR2/TPS3 support\n");
+	} else if (intel_dp->link_rate == 540000) {
+		if (!source_tps3)
+			DRM_DEBUG_KMS("5.4 Gbps link rate without source HBR2/TPS3 support\n");
+		if (!sink_tps3)
+			DRM_DEBUG_KMS("5.4 Gbps link rate without sink TPS3 support\n");
+	}
+
+	return training_pattern;
+}
+
+static void
+intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
+{
+	bool channel_eq = false;
+	int tries, cr_tries;
+	u32 training_pattern;
+
+	training_pattern = intel_dp_training_pattern(intel_dp);
 
 	/* channel equalization */
 	if (!intel_dp_set_link_train(intel_dp,
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index ea5415851c6e..df7f3cb66056 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1428,6 +1428,8 @@ bool __intel_display_power_is_enabled(struct drm_i915_private *dev_priv,
 				      enum intel_display_power_domain domain);
 void intel_display_power_get(struct drm_i915_private *dev_priv,
 			     enum intel_display_power_domain domain);
+bool intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv,
+					enum intel_display_power_domain domain);
 void intel_display_power_put(struct drm_i915_private *dev_priv,
 			     enum intel_display_power_domain domain);
 
@@ -1514,6 +1516,7 @@ enable_rpm_wakeref_asserts(struct drm_i915_private *dev_priv)
 	enable_rpm_wakeref_asserts(dev_priv)
 
 void intel_runtime_pm_get(struct drm_i915_private *dev_priv);
+bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_put(struct drm_i915_private *dev_priv);
 
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index 44742fa2f616..0193c62a53ef 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -664,13 +664,16 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
 	struct drm_device *dev = encoder->base.dev;
 	enum intel_display_power_domain power_domain;
 	enum port port;
+	bool ret;
 
 	DRM_DEBUG_KMS("\n");
 
 	power_domain = intel_display_port_power_domain(encoder);
-	if (!intel_display_power_is_enabled(dev_priv, power_domain))
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
+	ret = false;
+
 	/* XXX: this only works for one DSI output */
 	for_each_dsi_port(port, intel_dsi->ports) {
 		i915_reg_t ctrl_reg = IS_BROXTON(dev) ?
@@ -691,12 +694,16 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
 		if (dpi_enabled || (func & CMD_MODE_DATA_WIDTH_MASK)) {
 			if (I915_READ(MIPI_DEVICE_READY(port)) & DEVICE_READY) {
 				*pipe = port == PORT_A ? PIPE_A : PIPE_B;
-				return true;
+				ret = true;
+
+				goto out;
 			}
 		}
 	}
+out:
+	intel_display_power_put(dev_priv, power_domain);
 
-	return false;
+	return ret;
 }
 
 static void intel_dsi_get_config(struct intel_encoder *encoder,
diff --git a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
index a5e99ac305da..e8113ad65477 100644
--- a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
+++ b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
@@ -204,10 +204,28 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data)
 	struct drm_device *dev = intel_dsi->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	if (dev_priv->vbt.dsi.seq_version >= 3)
+		data++;
+
 	gpio = *data++;
 
 	/* pull up/down */
-	action = *data++;
+	action = *data++ & 1;
+
+	if (gpio >= ARRAY_SIZE(gtable)) {
+		DRM_DEBUG_KMS("unknown gpio %u\n", gpio);
+		goto out;
+	}
+
+	if (!IS_VALLEYVIEW(dev_priv)) {
+		DRM_DEBUG_KMS("GPIO element not supported on this platform\n");
+		goto out;
+	}
+
+	if (dev_priv->vbt.dsi.seq_version >= 3) {
+		DRM_DEBUG_KMS("GPIO element v3 not supported\n");
+		goto out;
+	}
 
 	function = gtable[gpio].function_reg;
 	pad = gtable[gpio].pad_reg;
@@ -226,6 +244,7 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data)
 	vlv_gpio_nc_write(dev_priv, pad, val);
 	mutex_unlock(&dev_priv->sb_lock);
 
+out:
 	return data;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 4a77639a489d..616108c4bc3e 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -880,15 +880,18 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder,
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
 	enum intel_display_power_domain power_domain;
 	u32 tmp;
+	bool ret;
 
 	power_domain = intel_display_port_power_domain(encoder);
-	if (!intel_display_power_is_enabled(dev_priv, power_domain))
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
+	ret = false;
+
 	tmp = I915_READ(intel_hdmi->hdmi_reg);
 
 	if (!(tmp & SDVO_ENABLE))
-		return false;
+		goto out;
 
 	if (HAS_PCH_CPT(dev))
 		*pipe = PORT_TO_PIPE_CPT(tmp);
@@ -897,7 +900,12 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder,
 	else
 		*pipe = PORT_TO_PIPE(tmp);
 
-	return true;
+	ret = true;
+
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 static void intel_hdmi_get_config(struct intel_encoder *encoder,
@@ -2146,7 +2154,6 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 void intel_hdmi_init(struct drm_device *dev,
 		     i915_reg_t hdmi_reg, enum port port)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_digital_port *intel_dig_port;
 	struct intel_encoder *intel_encoder;
 	struct intel_connector *intel_connector;
@@ -2215,7 +2222,6 @@ void intel_hdmi_init(struct drm_device *dev,
 		intel_encoder->cloneable |= 1 << INTEL_OUTPUT_HDMI;
 
 	intel_dig_port->port = port;
-	dev_priv->dig_port_map[port] = intel_encoder;
 	intel_dig_port->hdmi.hdmi_reg = hdmi_reg;
 	intel_dig_port->dp.output_reg = INVALID_MMIO_REG;
 
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 25254b5c1ac5..52fbe530fc9e 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -664,6 +664,12 @@ int intel_setup_gmbus(struct drm_device *dev)
 
 		bus->adapter.algo = &gmbus_algorithm;
 
+		/*
+		 * We wish to retry with bit banging
+		 * after a timed out GMBUS attempt.
+		 */
+		bus->adapter.retries = 1;
+
 		/* By default use a conservative clock rate */
 		bus->reg0 = pin | GMBUS_RATE_100KHZ;
 
@@ -683,7 +689,7 @@ int intel_setup_gmbus(struct drm_device *dev)
 	return 0;
 
 err:
-	while (--pin) {
+	while (pin--) {
 		if (!intel_gmbus_is_valid_pin(dev_priv, pin))
 			continue;
 
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 0da0240caf81..bc04d8d29acb 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -75,22 +75,30 @@ static bool intel_lvds_get_hw_state(struct intel_encoder *encoder,
 	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
 	enum intel_display_power_domain power_domain;
 	u32 tmp;
+	bool ret;
 
 	power_domain = intel_display_port_power_domain(encoder);
-	if (!intel_display_power_is_enabled(dev_priv, power_domain))
+	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
+	ret = false;
+
 	tmp = I915_READ(lvds_encoder->reg);
 
 	if (!(tmp & LVDS_PORT_EN))
-		return false;
+		goto out;
 
 	if (HAS_PCH_CPT(dev))
 		*pipe = PORT_TO_PIPE_CPT(tmp);
 	else
 		*pipe = PORT_TO_PIPE(tmp);
 
-	return true;
+	ret = true;
+
+out:
+	intel_display_power_put(dev_priv, power_domain);
+
+	return ret;
 }
 
 static void intel_lvds_get_config(struct intel_encoder *encoder,
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index eb5fa05cf476..b28c29f20e75 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -1783,16 +1783,20 @@ static uint32_t ilk_compute_cur_wm(const struct intel_crtc_state *cstate,
 				   const struct intel_plane_state *pstate,
 				   uint32_t mem_value)
 {
-	int bpp = pstate->base.fb ? pstate->base.fb->bits_per_pixel / 8 : 0;
+	/*
+	 * We treat the cursor plane as always-on for the purposes of watermark
+	 * calculation.  Until we have two-stage watermark programming merged,
+	 * this is necessary to avoid flickering.
+	 */
+	int cpp = 4;
+	int width = pstate->visible ? pstate->base.crtc_w : 64;
 
-	if (!cstate->base.active || !pstate->visible)
+	if (!cstate->base.active)
 		return 0;
 
 	return ilk_wm_method2(ilk_pipe_pixel_rate(cstate),
 			      cstate->base.adjusted_mode.crtc_htotal,
-			      drm_rect_width(&pstate->dst),
-			      bpp,
-			      mem_value);
+			      width, cpp, mem_value);
 }
 
 /* Only for WM_LP. */
@@ -2825,7 +2829,10 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
 	memset(ddb, 0, sizeof(*ddb));
 
 	for_each_pipe(dev_priv, pipe) {
-		if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PIPE(pipe)))
+		enum intel_display_power_domain power_domain;
+
+		power_domain = POWER_DOMAIN_PIPE(pipe);
+		if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 			continue;
 
 		for_each_plane(dev_priv, pipe, plane) {
@@ -2837,6 +2844,8 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
 		val = I915_READ(CUR_BUF_CFG(pipe));
 		skl_ddb_entry_init_from_hw(&ddb->plane[pipe][PLANE_CURSOR],
 					   val);
+
+		intel_display_power_put(dev_priv, power_domain);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index ddbdbffe829a..4f43d9b32e66 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -470,6 +470,43 @@ static void gen9_set_dc_state_debugmask_memory_up(
 	}
 }
 
+static void gen9_write_dc_state(struct drm_i915_private *dev_priv,
+				u32 state)
+{
+	int rewrites = 0;
+	int rereads = 0;
+	u32 v;
+
+	I915_WRITE(DC_STATE_EN, state);
+
+	/* It has been observed that disabling the dc6 state sometimes
+	 * doesn't stick and dmc keeps returning old value. Make sure
+	 * the write really sticks enough times and also force rewrite until
+	 * we are confident that state is exactly what we want.
+	 */
+	do  {
+		v = I915_READ(DC_STATE_EN);
+
+		if (v != state) {
+			I915_WRITE(DC_STATE_EN, state);
+			rewrites++;
+			rereads = 0;
+		} else if (rereads++ > 5) {
+			break;
+		}
+
+	} while (rewrites < 100);
+
+	if (v != state)
+		DRM_ERROR("Writing dc state to 0x%x failed, now 0x%x\n",
+			  state, v);
+
+	/* Most of the times we need one retry, avoid spam */
+	if (rewrites > 1)
+		DRM_DEBUG_KMS("Rewrote dc state to 0x%x %d times\n",
+			      state, rewrites);
+}
+
 static void gen9_set_dc_state(struct drm_i915_private *dev_priv, uint32_t state)
 {
 	uint32_t val;
@@ -494,10 +531,18 @@ static void gen9_set_dc_state(struct drm_i915_private *dev_priv, uint32_t state)
 	val = I915_READ(DC_STATE_EN);
 	DRM_DEBUG_KMS("Setting DC state from %02x to %02x\n",
 		      val & mask, state);
+
+	/* Check if DMC is ignoring our DC state requests */
+	if ((val & mask) != dev_priv->csr.dc_state)
+		DRM_ERROR("DC state mismatch (0x%x -> 0x%x)\n",
+			  dev_priv->csr.dc_state, val & mask);
+
 	val &= ~mask;
 	val |= state;
-	I915_WRITE(DC_STATE_EN, val);
-	POSTING_READ(DC_STATE_EN);
+
+	gen9_write_dc_state(dev_priv, val);
+
+	dev_priv->csr.dc_state = val & mask;
 }
 
 void bxt_enable_dc9(struct drm_i915_private *dev_priv)
@@ -1442,6 +1487,22 @@ static void chv_pipe_power_well_disable(struct drm_i915_private *dev_priv,
 	chv_set_pipe_power_well(dev_priv, power_well, false);
 }
 
+static void
+__intel_display_power_get_domain(struct drm_i915_private *dev_priv,
+				 enum intel_display_power_domain domain)
+{
+	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+	struct i915_power_well *power_well;
+	int i;
+
+	for_each_power_well(i, power_well, BIT(domain), power_domains) {
+		if (!power_well->count++)
+			intel_power_well_enable(dev_priv, power_well);
+	}
+
+	power_domains->domain_use_count[domain]++;
+}
+
 /**
  * intel_display_power_get - grab a power domain reference
  * @dev_priv: i915 device instance
@@ -1457,24 +1518,53 @@ static void chv_pipe_power_well_disable(struct drm_i915_private *dev_priv,
 void intel_display_power_get(struct drm_i915_private *dev_priv,
 			     enum intel_display_power_domain domain)
 {
-	struct i915_power_domains *power_domains;
-	struct i915_power_well *power_well;
-	int i;
+	struct i915_power_domains *power_domains = &dev_priv->power_domains;
 
 	intel_runtime_pm_get(dev_priv);
 
-	power_domains = &dev_priv->power_domains;
+	mutex_lock(&power_domains->lock);
+
+	__intel_display_power_get_domain(dev_priv, domain);
+
+	mutex_unlock(&power_domains->lock);
+}
+
+/**
+ * intel_display_power_get_if_enabled - grab a reference for an enabled display power domain
+ * @dev_priv: i915 device instance
+ * @domain: power domain to reference
+ *
+ * This function grabs a power domain reference for @domain and ensures that the
+ * power domain and all its parents are powered up. Therefore users should only
+ * grab a reference to the innermost power domain they need.
+ *
+ * Any power domain reference obtained by this function must have a symmetric
+ * call to intel_display_power_put() to release the reference again.
+ */
+bool intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv,
+					enum intel_display_power_domain domain)
+{
+	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+	bool is_enabled;
+
+	if (!intel_runtime_pm_get_if_in_use(dev_priv))
+		return false;
 
 	mutex_lock(&power_domains->lock);
 
-	for_each_power_well(i, power_well, BIT(domain), power_domains) {
-		if (!power_well->count++)
-			intel_power_well_enable(dev_priv, power_well);
+	if (__intel_display_power_is_enabled(dev_priv, domain)) {
+		__intel_display_power_get_domain(dev_priv, domain);
+		is_enabled = true;
+	} else {
+		is_enabled = false;
 	}
 
-	power_domains->domain_use_count[domain]++;
-
 	mutex_unlock(&power_domains->lock);
+
+	if (!is_enabled)
+		intel_runtime_pm_put(dev_priv);
+
+	return is_enabled;
 }
 
 /**
@@ -2213,15 +2303,15 @@ void intel_power_domains_init_hw(struct drm_i915_private *dev_priv, bool resume)
  */
 void intel_power_domains_suspend(struct drm_i915_private *dev_priv)
 {
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
-		skl_display_core_uninit(dev_priv);
-
 	/*
 	 * Even if power well support was disabled we still want to disable
 	 * power wells while we are system suspended.
 	 */
 	if (!i915.disable_power_well)
 		intel_display_power_put(dev_priv, POWER_DOMAIN_INIT);
+
+	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
+		skl_display_core_uninit(dev_priv);
 }
 
 /**
@@ -2246,6 +2336,41 @@ void intel_runtime_pm_get(struct drm_i915_private *dev_priv)
 }
 
 /**
+ * intel_runtime_pm_get_if_in_use - grab a runtime pm reference if device in use
+ * @dev_priv: i915 device instance
+ *
+ * This function grabs a device-level runtime pm reference if the device is
+ * already in use and ensures that it is powered up.
+ *
+ * Any runtime pm reference obtained by this function must have a symmetric
+ * call to intel_runtime_pm_put() to release the reference again.
+ */
+bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	struct device *device = &dev->pdev->dev;
+
+	if (IS_ENABLED(CONFIG_PM)) {
+		int ret = pm_runtime_get_if_in_use(device);
+
+		/*
+		 * In cases runtime PM is disabled by the RPM core and we get
+		 * an -EINVAL return value we are not supposed to call this
+		 * function, since the power state is undefined. This applies
+		 * atm to the late/early system suspend/resume handlers.
+		 */
+		WARN_ON_ONCE(ret < 0);
+		if (ret <= 0)
+			return false;
+	}
+
+	atomic_inc(&dev_priv->pm.wakeref_count);
+	assert_rpm_wakelock_held(dev_priv);
+
+	return true;
+}
+
+/**
  * intel_runtime_pm_get_noresume - grab a runtime pm reference
  * @dev_priv: i915 device instance
  *
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index 30a57185bdb4..287226311413 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -64,6 +64,7 @@ static void ipu_fb_enable(struct ipu_crtc *ipu_crtc)
 	/* Start DC channel and DI after IDMAC */
 	ipu_dc_enable_channel(ipu_crtc->dc);
 	ipu_di_enable(ipu_crtc->di);
+	drm_crtc_vblank_on(&ipu_crtc->base);
 
 	ipu_crtc->enabled = 1;
 }
@@ -80,6 +81,7 @@ static void ipu_fb_disable(struct ipu_crtc *ipu_crtc)
 	ipu_di_disable(ipu_crtc->di);
 	ipu_plane_disable(ipu_crtc->plane[0]);
 	ipu_dc_disable(ipu);
+	drm_crtc_vblank_off(&ipu_crtc->base);
 
 	ipu_crtc->enabled = 0;
 }
diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c
index 591ba2f1ae03..26bb1b626fe3 100644
--- a/drivers/gpu/drm/imx/ipuv3-plane.c
+++ b/drivers/gpu/drm/imx/ipuv3-plane.c
@@ -42,6 +42,7 @@ static const uint32_t ipu_plane_formats[] = {
 	DRM_FORMAT_YVYU,
 	DRM_FORMAT_YUV420,
 	DRM_FORMAT_YVU420,
+	DRM_FORMAT_RGB565,
 };
 
 int ipu_plane_irq(struct ipu_plane *ipu_plane)
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 78f520d05de9..e3acc35e3805 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1520,7 +1520,7 @@ nouveau_ttm_tt_populate(struct ttm_tt *ttm)
 				    DMA_BIDIRECTIONAL);
 
 		if (dma_mapping_error(pdev, addr)) {
-			while (--i) {
+			while (i--) {
 				dma_unmap_page(pdev, ttm_dma->dma_address[i],
 					       PAGE_SIZE, DMA_BIDIRECTIONAL);
 				ttm_dma->dma_address[i] = 0;
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 24be27d3cd18..20935eb2a09e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -635,10 +635,6 @@ nouveau_display_resume(struct drm_device *dev, bool runtime)
 		nv_crtc->lut.depth = 0;
 	}
 
-	/* Make sure that drm and hw vblank irqs get resumed if needed. */
-	for (head = 0; head < dev->mode_config.num_crtc; head++)
-		drm_vblank_on(dev, head);
-
 	/* This should ensure we don't hit a locking problem when someone
 	 * wakes us up via a connector.  We should never go into suspend
 	 * while the display is on anyways.
@@ -648,6 +644,10 @@ nouveau_display_resume(struct drm_device *dev, bool runtime)
 
 	drm_helper_resume_force_mode(dev);
 
+	/* Make sure that drm and hw vblank irqs get resumed if needed. */
+	for (head = 0; head < dev->mode_config.num_crtc; head++)
+		drm_vblank_on(dev, head);
+
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 		struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_platform.c b/drivers/gpu/drm/nouveau/nouveau_platform.c
index 8a70cec59bcd..2dfe58af12e4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_platform.c
+++ b/drivers/gpu/drm/nouveau/nouveau_platform.c
@@ -24,7 +24,7 @@
 static int nouveau_platform_probe(struct platform_device *pdev)
 {
 	const struct nvkm_device_tegra_func *func;
-	struct nvkm_device *device;
+	struct nvkm_device *device = NULL;
 	struct drm_device *drm;
 	int ret;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
index 7f8a42721eb2..e7e581d6a8ff 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
@@ -252,32 +252,40 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func,
 
 	if (!(tdev = kzalloc(sizeof(*tdev), GFP_KERNEL)))
 		return -ENOMEM;
-	*pdevice = &tdev->device;
+
 	tdev->func = func;
 	tdev->pdev = pdev;
 	tdev->irq = -1;
 
 	tdev->vdd = devm_regulator_get(&pdev->dev, "vdd");
-	if (IS_ERR(tdev->vdd))
-		return PTR_ERR(tdev->vdd);
+	if (IS_ERR(tdev->vdd)) {
+		ret = PTR_ERR(tdev->vdd);
+		goto free;
+	}
 
 	tdev->rst = devm_reset_control_get(&pdev->dev, "gpu");
-	if (IS_ERR(tdev->rst))
-		return PTR_ERR(tdev->rst);
+	if (IS_ERR(tdev->rst)) {
+		ret = PTR_ERR(tdev->rst);
+		goto free;
+	}
 
 	tdev->clk = devm_clk_get(&pdev->dev, "gpu");
-	if (IS_ERR(tdev->clk))
-		return PTR_ERR(tdev->clk);
+	if (IS_ERR(tdev->clk)) {
+		ret = PTR_ERR(tdev->clk);
+		goto free;
+	}
 
 	tdev->clk_pwr = devm_clk_get(&pdev->dev, "pwr");
-	if (IS_ERR(tdev->clk_pwr))
-		return PTR_ERR(tdev->clk_pwr);
+	if (IS_ERR(tdev->clk_pwr)) {
+		ret = PTR_ERR(tdev->clk_pwr);
+		goto free;
+	}
 
 	nvkm_device_tegra_probe_iommu(tdev);
 
 	ret = nvkm_device_tegra_power_up(tdev);
 	if (ret)
-		return ret;
+		goto remove;
 
 	tdev->gpu_speedo = tegra_sku_info.gpu_speedo_value;
 	ret = nvkm_device_ctor(&nvkm_device_tegra_func, NULL, &pdev->dev,
@@ -285,9 +293,19 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func,
 			       cfg, dbg, detect, mmio, subdev_mask,
 			       &tdev->device);
 	if (ret)
-		return ret;
+		goto powerdown;
+
+	*pdevice = &tdev->device;
 
 	return 0;
+
+powerdown:
+	nvkm_device_tegra_power_down(tdev);
+remove:
+	nvkm_device_tegra_remove_iommu(tdev);
+free:
+	kfree(tdev);
+	return ret;
 }
 #else
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c
index 74e2f7c6c07e..9688970eca47 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c
@@ -328,6 +328,7 @@ nvkm_dp_train(struct work_struct *w)
 		.outp = outp,
 	}, *dp = &_dp;
 	u32 datarate = 0;
+	u8  pwr;
 	int ret;
 
 	if (!outp->base.info.location && disp->func->sor.magic)
@@ -355,6 +356,15 @@ nvkm_dp_train(struct work_struct *w)
 	/* disable link interrupt handling during link training */
 	nvkm_notify_put(&outp->irq);
 
+	/* ensure sink is not in a low-power state */
+	if (!nvkm_rdaux(outp->aux, DPCD_SC00, &pwr, 1)) {
+		if ((pwr & DPCD_SC00_SET_POWER) != DPCD_SC00_SET_POWER_D0) {
+			pwr &= ~DPCD_SC00_SET_POWER;
+			pwr |=  DPCD_SC00_SET_POWER_D0;
+			nvkm_wraux(outp->aux, DPCD_SC00, &pwr, 1);
+		}
+	}
+
 	/* enable down-spreading and execute pre-train script from vbios */
 	dp_link_train_init(dp, outp->dpcd[3] & 0x01);
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h
index 9596290329c7..6e10c5e0ef11 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h
@@ -71,5 +71,11 @@
 #define DPCD_LS0C_LANE1_POST_CURSOR2                                       0x0c
 #define DPCD_LS0C_LANE0_POST_CURSOR2                                       0x03
 
+/* DPCD Sink Control */
+#define DPCD_SC00                                                       0x00600
+#define DPCD_SC00_SET_POWER                                                0x03
+#define DPCD_SC00_SET_POWER_D0                                             0x01
+#define DPCD_SC00_SET_POWER_D3                                             0x03
+
 void nvkm_dp_train(struct work_struct *);
 #endif
diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
index dfebdc4aa0f2..85dfe3674b41 100644
--- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
+++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
@@ -573,10 +573,9 @@ static int omap_dmm_remove(struct platform_device *dev)
 
 		kfree(omap_dmm->engines);
 		if (omap_dmm->refill_va)
-			dma_free_writecombine(omap_dmm->dev,
-				REFILL_BUFFER_SIZE * omap_dmm->num_engines,
-				omap_dmm->refill_va,
-				omap_dmm->refill_pa);
+			dma_free_wc(omap_dmm->dev,
+				    REFILL_BUFFER_SIZE * omap_dmm->num_engines,
+				    omap_dmm->refill_va, omap_dmm->refill_pa);
 		if (omap_dmm->dummy_page)
 			__free_page(omap_dmm->dummy_page);
 
@@ -701,9 +700,9 @@ static int omap_dmm_probe(struct platform_device *dev)
 	omap_dmm->dummy_pa = page_to_phys(omap_dmm->dummy_page);
 
 	/* alloc refill memory */
-	omap_dmm->refill_va = dma_alloc_writecombine(&dev->dev,
-				REFILL_BUFFER_SIZE * omap_dmm->num_engines,
-				&omap_dmm->refill_pa, GFP_KERNEL);
+	omap_dmm->refill_va = dma_alloc_wc(&dev->dev,
+					   REFILL_BUFFER_SIZE * omap_dmm->num_engines,
+					   &omap_dmm->refill_pa, GFP_KERNEL);
 	if (!omap_dmm->refill_va) {
 		dev_err(&dev->dev, "could not allocate refill memory\n");
 		goto fail;
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 8495a1a4b617..359b0d7e8ef7 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -1330,8 +1330,8 @@ void omap_gem_free_object(struct drm_gem_object *obj)
 			omap_gem_detach_pages(obj);
 
 		if (!is_shmem(obj)) {
-			dma_free_writecombine(dev->dev, obj->size,
-					omap_obj->vaddr, omap_obj->paddr);
+			dma_free_wc(dev->dev, obj->size, omap_obj->vaddr,
+				    omap_obj->paddr);
 		} else if (omap_obj->vaddr) {
 			vunmap(omap_obj->vaddr);
 		}
@@ -1395,8 +1395,8 @@ struct drm_gem_object *omap_gem_new(struct drm_device *dev,
 		/* attempt to allocate contiguous memory if we don't
 		 * have DMM for remappign discontiguous buffers
 		 */
-		omap_obj->vaddr =  dma_alloc_writecombine(dev->dev, size,
-				&omap_obj->paddr, GFP_KERNEL);
+		omap_obj->vaddr =  dma_alloc_wc(dev->dev, size,
+						&omap_obj->paddr, GFP_KERNEL);
 		if (!omap_obj->vaddr) {
 			kfree(omap_obj);
 
diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c
index 2ae8577497ca..7c2e78201ead 100644
--- a/drivers/gpu/drm/qxl/qxl_ioctl.c
+++ b/drivers/gpu/drm/qxl/qxl_ioctl.c
@@ -168,7 +168,8 @@ static int qxl_process_single_command(struct qxl_device *qdev,
 		       cmd->command_size))
 		return -EFAULT;
 
-	reloc_info = kmalloc(sizeof(struct qxl_reloc_info) * cmd->relocs_num, GFP_KERNEL);
+	reloc_info = kmalloc_array(cmd->relocs_num,
+				   sizeof(struct qxl_reloc_info), GFP_KERNEL);
 	if (!reloc_info)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/qxl/qxl_prime.c b/drivers/gpu/drm/qxl/qxl_prime.c
index 3d031b50a8fd..9f029dda1f07 100644
--- a/drivers/gpu/drm/qxl/qxl_prime.c
+++ b/drivers/gpu/drm/qxl/qxl_prime.c
@@ -68,5 +68,5 @@ int qxl_gem_prime_mmap(struct drm_gem_object *obj,
 		       struct vm_area_struct *area)
 {
 	WARN_ONCE(1, "not implemented");
-	return ENOSYS;
+	return -ENOSYS;
 }
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 44ee72e04df9..6af832545bc5 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -315,15 +315,27 @@ int radeon_dp_get_dp_link_config(struct drm_connector *connector,
 	unsigned max_lane_num = drm_dp_max_lane_count(dpcd);
 	unsigned lane_num, i, max_pix_clock;
 
-	for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) {
-		for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) {
-			max_pix_clock = (lane_num * link_rates[i] * 8) / bpp;
+	if (radeon_connector_encoder_get_dp_bridge_encoder_id(connector) ==
+	    ENCODER_OBJECT_ID_NUTMEG) {
+		for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) {
+			max_pix_clock = (lane_num * 270000 * 8) / bpp;
 			if (max_pix_clock >= pix_clock) {
 				*dp_lanes = lane_num;
-				*dp_rate = link_rates[i];
+				*dp_rate = 270000;
 				return 0;
 			}
 		}
+	} else {
+		for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) {
+			for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) {
+				max_pix_clock = (lane_num * link_rates[i] * 8) / bpp;
+				if (max_pix_clock >= pix_clock) {
+					*dp_lanes = lane_num;
+					*dp_rate = link_rates[i];
+					return 0;
+				}
+			}
+		}
 	}
 
 	return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index a9b01bcf7d0a..432480ff9d22 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -34,7 +34,6 @@
 #include <asm/machdep.h>
 #include <asm/pmac_feature.h>
 #include <asm/prom.h>
-#include <asm/pci-bridge.h>
 #endif /* CONFIG_PPC_PMAC */
 
 /* from radeon_legacy_encoder.c */
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 902b59cebac5..4197ca1bb1e4 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1744,7 +1744,6 @@ int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon)
 	}
 
 	drm_kms_helper_poll_enable(dev);
-	drm_helper_hpd_irq_event(dev);
 
 	/* set the power state here in case we are a PX system or headless */
 	if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled)
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 298ea1c453c3..2d9196a447fd 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -403,7 +403,8 @@ static void radeon_flip_work_func(struct work_struct *__work)
 	struct drm_crtc *crtc = &radeon_crtc->base;
 	unsigned long flags;
 	int r;
-	int vpos, hpos, stat, min_udelay;
+	int vpos, hpos, stat, min_udelay = 0;
+	unsigned repcnt = 4;
 	struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id];
 
         down_read(&rdev->exclusive_lock);
@@ -454,7 +455,7 @@ static void radeon_flip_work_func(struct work_struct *__work)
 	 * In practice this won't execute very often unless on very fast
 	 * machines because the time window for this to happen is very small.
 	 */
-	for (;;) {
+	while (radeon_crtc->enabled && --repcnt) {
 		/* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank
 		 * start in hpos, and to the "fudged earlier" vblank start in
 		 * vpos.
@@ -470,12 +471,24 @@ static void radeon_flip_work_func(struct work_struct *__work)
 			break;
 
 		/* Sleep at least until estimated real start of hw vblank */
-		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
 		min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5);
+		if (min_udelay > vblank->framedur_ns / 2000) {
+			/* Don't wait ridiculously long - something is wrong */
+			repcnt = 0;
+			break;
+		}
+		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
 		usleep_range(min_udelay, 2 * min_udelay);
 		spin_lock_irqsave(&crtc->dev->event_lock, flags);
 	};
 
+	if (!repcnt)
+		DRM_DEBUG_DRIVER("Delay problem on crtc %d: min_udelay %d, "
+				 "framedur %d, linedur %d, stat %d, vpos %d, "
+				 "hpos %d\n", work->crtc_id, min_udelay,
+				 vblank->framedur_ns / 1000,
+				 vblank->linedur_ns / 1000, stat, vpos, hpos);
+
 	/* do the flip (mmio) */
 	radeon_page_flip(rdev, radeon_crtc->crtc_id, work->base);
 
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 460c8f2989da..7a98823bacd1 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -276,8 +276,12 @@ static void radeon_pm_set_clocks(struct radeon_device *rdev)
 	if (rdev->irq.installed) {
 		for (i = 0; i < rdev->num_crtc; i++) {
 			if (rdev->pm.active_crtcs & (1 << i)) {
-				rdev->pm.req_vblank |= (1 << i);
-				drm_vblank_get(rdev->ddev, i);
+				/* This can fail if a modeset is in progress */
+				if (drm_vblank_get(rdev->ddev, i) == 0)
+					rdev->pm.req_vblank |= (1 << i);
+				else
+					DRM_DEBUG_DRIVER("crtc %d no vblank, can glitch\n",
+							 i);
 			}
 		}
 	}
@@ -1078,10 +1082,6 @@ force:
 	/* update displays */
 	radeon_dpm_display_configuration_changed(rdev);
 
-	rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs;
-	rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count;
-	rdev->pm.dpm.single_display = single_display;
-
 	/* wait for the rings to drain */
 	for (i = 0; i < RADEON_NUM_RINGS; i++) {
 		struct radeon_ring *ring = &rdev->ring[i];
@@ -1097,6 +1097,10 @@ force:
 
 	radeon_dpm_post_set_power_state(rdev);
 
+	rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs;
+	rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count;
+	rdev->pm.dpm.single_display = single_display;
+
 	if (rdev->asic->dpm.force_performance_level) {
 		if (rdev->pm.dpm.thermal_active) {
 			enum radeon_dpm_forced_level level = rdev->pm.dpm.forced_level;
diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c
index c507896aca45..197b157b73d0 100644
--- a/drivers/gpu/drm/radeon/radeon_sa.c
+++ b/drivers/gpu/drm/radeon/radeon_sa.c
@@ -349,8 +349,13 @@ int radeon_sa_bo_new(struct radeon_device *rdev,
 			/* see if we can skip over some allocations */
 		} while (radeon_sa_bo_next_hole(sa_manager, fences, tries));
 
+		for (i = 0; i < RADEON_NUM_RINGS; ++i)
+			radeon_fence_ref(fences[i]);
+
 		spin_unlock(&sa_manager->wq.lock);
 		r = radeon_fence_wait_any(rdev, fences, false);
+		for (i = 0; i < RADEON_NUM_RINGS; ++i)
+			radeon_fence_unref(&fences[i]);
 		spin_lock(&sa_manager->wq.lock);
 		/* if we have nothing to wait for block */
 		if (r == -ENOENT) {
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index e34307459e50..e06ac546a90f 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -758,7 +758,7 @@ static int radeon_ttm_tt_populate(struct ttm_tt *ttm)
 						       0, PAGE_SIZE,
 						       PCI_DMA_BIDIRECTIONAL);
 		if (pci_dma_mapping_error(rdev->pdev, gtt->ttm.dma_address[i])) {
-			while (--i) {
+			while (i--) {
 				pci_unmap_page(rdev->pdev, gtt->ttm.dma_address[i],
 					       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
 				gtt->ttm.dma_address[i] = 0;
diff --git a/drivers/gpu/drm/sti/sti_cursor.c b/drivers/gpu/drm/sti/sti_cursor.c
index 807863106b8d..bd736ace3f81 100644
--- a/drivers/gpu/drm/sti/sti_cursor.c
+++ b/drivers/gpu/drm/sti/sti_cursor.c
@@ -157,17 +157,15 @@ static void sti_cursor_atomic_update(struct drm_plane *drm_plane,
 		cursor->height = src_h;
 
 		if (cursor->pixmap.base)
-			dma_free_writecombine(cursor->dev,
-					      cursor->pixmap.size,
-					      cursor->pixmap.base,
-					      cursor->pixmap.paddr);
+			dma_free_wc(cursor->dev, cursor->pixmap.size,
+				    cursor->pixmap.base, cursor->pixmap.paddr);
 
 		cursor->pixmap.size = cursor->width * cursor->height;
 
-		cursor->pixmap.base = dma_alloc_writecombine(cursor->dev,
-							cursor->pixmap.size,
-							&cursor->pixmap.paddr,
-							GFP_KERNEL | GFP_DMA);
+		cursor->pixmap.base = dma_alloc_wc(cursor->dev,
+						   cursor->pixmap.size,
+						   &cursor->pixmap.paddr,
+						   GFP_KERNEL | GFP_DMA);
 		if (!cursor->pixmap.base) {
 			DRM_ERROR("Failed to allocate memory for pixmap\n");
 			return;
@@ -252,8 +250,8 @@ struct drm_plane *sti_cursor_create(struct drm_device *drm_dev,
 
 	/* Allocate clut buffer */
 	size = 0x100 * sizeof(unsigned short);
-	cursor->clut = dma_alloc_writecombine(dev, size, &cursor->clut_paddr,
-					      GFP_KERNEL | GFP_DMA);
+	cursor->clut = dma_alloc_wc(dev, size, &cursor->clut_paddr,
+				    GFP_KERNEL | GFP_DMA);
 
 	if (!cursor->clut) {
 		DRM_ERROR("Failed to allocate memory for cursor clut\n");
@@ -286,7 +284,7 @@ struct drm_plane *sti_cursor_create(struct drm_device *drm_dev,
 	return &cursor->plane.drm_plane;
 
 err_plane:
-	dma_free_writecombine(dev, size, cursor->clut, cursor->clut_paddr);
+	dma_free_wc(dev, size, cursor->clut, cursor->clut_paddr);
 err_clut:
 	devm_kfree(dev, cursor);
 	return NULL;
diff --git a/drivers/gpu/drm/sti/sti_gdp.c b/drivers/gpu/drm/sti/sti_gdp.c
index f9a1d92c9d95..514551c857bb 100644
--- a/drivers/gpu/drm/sti/sti_gdp.c
+++ b/drivers/gpu/drm/sti/sti_gdp.c
@@ -312,8 +312,7 @@ static void sti_gdp_init(struct sti_gdp *gdp)
 	/* Allocate all the nodes within a single memory page */
 	size = sizeof(struct sti_gdp_node) *
 	    GDP_NODE_PER_FIELD * GDP_NODE_NB_BANK;
-	base = dma_alloc_writecombine(gdp->dev,
-				      size, &dma_addr, GFP_KERNEL | GFP_DMA);
+	base = dma_alloc_wc(gdp->dev, size, &dma_addr, GFP_KERNEL | GFP_DMA);
 
 	if (!base) {
 		DRM_ERROR("Failed to allocate memory for GDP node\n");
diff --git a/drivers/gpu/drm/sti/sti_hqvdp.c b/drivers/gpu/drm/sti/sti_hqvdp.c
index 43861b52261d..1d3c3d029603 100644
--- a/drivers/gpu/drm/sti/sti_hqvdp.c
+++ b/drivers/gpu/drm/sti/sti_hqvdp.c
@@ -617,9 +617,9 @@ static void sti_hqvdp_init(struct sti_hqvdp *hqvdp)
 
 	/* Allocate memory for the VDP commands */
 	size = NB_VDP_CMD * sizeof(struct sti_hqvdp_cmd);
-	hqvdp->hqvdp_cmd = dma_alloc_writecombine(hqvdp->dev, size,
-					 &hqvdp->hqvdp_cmd_paddr,
-					 GFP_KERNEL | GFP_DMA);
+	hqvdp->hqvdp_cmd = dma_alloc_wc(hqvdp->dev, size,
+					&hqvdp->hqvdp_cmd_paddr,
+					GFP_KERNEL | GFP_DMA);
 	if (!hqvdp->hqvdp_cmd) {
 		DRM_ERROR("Failed to allocate memory for VDP cmd\n");
 		return;
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index 33add93b4ed9..3b0d8c392b70 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -175,8 +175,7 @@ static void tegra_bo_free(struct drm_device *drm, struct tegra_bo *bo)
 		sg_free_table(bo->sgt);
 		kfree(bo->sgt);
 	} else if (bo->vaddr) {
-		dma_free_writecombine(drm->dev, bo->gem.size, bo->vaddr,
-				      bo->paddr);
+		dma_free_wc(drm->dev, bo->gem.size, bo->vaddr, bo->paddr);
 	}
 }
 
@@ -233,8 +232,8 @@ static int tegra_bo_alloc(struct drm_device *drm, struct tegra_bo *bo)
 	} else {
 		size_t size = bo->gem.size;
 
-		bo->vaddr = dma_alloc_writecombine(drm->dev, size, &bo->paddr,
-						   GFP_KERNEL | __GFP_NOWARN);
+		bo->vaddr = dma_alloc_wc(drm->dev, size, &bo->paddr,
+					 GFP_KERNEL | __GFP_NOWARN);
 		if (!bo->vaddr) {
 			dev_err(drm->dev,
 				"failed to allocate buffer of size %zu\n",
@@ -472,8 +471,8 @@ int tegra_drm_mmap(struct file *file, struct vm_area_struct *vma)
 		vma->vm_flags &= ~VM_PFNMAP;
 		vma->vm_pgoff = 0;
 
-		ret = dma_mmap_writecombine(gem->dev->dev, vma, bo->vaddr,
-					    bo->paddr, gem->size);
+		ret = dma_mmap_wc(gem->dev->dev, vma, bo->vaddr, bo->paddr,
+				  gem->size);
 		if (ret) {
 			drm_gem_vm_close(vma);
 			return ret;
diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index 18dfe3ec9a62..034ef2de9037 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -215,7 +215,7 @@ struct vc4_bo *vc4_bo_create(struct drm_device *dev, size_t unaligned_size,
 	struct drm_gem_cma_object *cma_obj;
 
 	if (size == 0)
-		return NULL;
+		return ERR_PTR(-EINVAL);
 
 	/* First, try to get a vc4_bo from the kernel BO cache. */
 	if (from_cache) {
@@ -237,7 +237,7 @@ struct vc4_bo *vc4_bo_create(struct drm_device *dev, size_t unaligned_size,
 		if (IS_ERR(cma_obj)) {
 			DRM_ERROR("Failed to allocate from CMA:\n");
 			vc4_bo_stats_dump(vc4);
-			return NULL;
+			return ERR_PTR(-ENOMEM);
 		}
 	}
 
@@ -259,8 +259,8 @@ int vc4_dumb_create(struct drm_file *file_priv,
 		args->size = args->pitch * args->height;
 
 	bo = vc4_bo_create(dev, args->size, false);
-	if (!bo)
-		return -ENOMEM;
+	if (IS_ERR(bo))
+		return PTR_ERR(bo);
 
 	ret = drm_gem_handle_create(file_priv, &bo->base.base, &args->handle);
 	drm_gem_object_unreference_unlocked(&bo->base.base);
@@ -398,9 +398,8 @@ int vc4_mmap(struct file *filp, struct vm_area_struct *vma)
 	vma->vm_flags &= ~VM_PFNMAP;
 	vma->vm_pgoff = 0;
 
-	ret = dma_mmap_writecombine(bo->base.base.dev->dev, vma,
-				    bo->base.vaddr, bo->base.paddr,
-				    vma->vm_end - vma->vm_start);
+	ret = dma_mmap_wc(bo->base.base.dev->dev, vma, bo->base.vaddr,
+			  bo->base.paddr, vma->vm_end - vma->vm_start);
 	if (ret)
 		drm_gem_vm_close(vma);
 
@@ -443,8 +442,8 @@ int vc4_create_bo_ioctl(struct drm_device *dev, void *data,
 	 * get zeroed, and that might leak data between users.
 	 */
 	bo = vc4_bo_create(dev, args->size, false);
-	if (!bo)
-		return -ENOMEM;
+	if (IS_ERR(bo))
+		return PTR_ERR(bo);
 
 	ret = drm_gem_handle_create(file_priv, &bo->base.base, &args->handle);
 	drm_gem_object_unreference_unlocked(&bo->base.base);
@@ -496,8 +495,8 @@ vc4_create_shader_bo_ioctl(struct drm_device *dev, void *data,
 	}
 
 	bo = vc4_bo_create(dev, args->size, true);
-	if (!bo)
-		return -ENOMEM;
+	if (IS_ERR(bo))
+		return PTR_ERR(bo);
 
 	ret = copy_from_user(bo->base.vaddr,
 			     (void __user *)(uintptr_t)args->data,
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 080865ec2bae..51a63330d4f8 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -91,8 +91,12 @@ struct vc4_dev {
 	struct vc4_bo *overflow_mem;
 	struct work_struct overflow_mem_work;
 
+	int power_refcount;
+
+	/* Mutex controlling the power refcount. */
+	struct mutex power_lock;
+
 	struct {
-		uint32_t last_ct0ca, last_ct1ca;
 		struct timer_list timer;
 		struct work_struct reset_work;
 	} hangcheck;
@@ -142,6 +146,7 @@ struct vc4_seqno_cb {
 };
 
 struct vc4_v3d {
+	struct vc4_dev *vc4;
 	struct platform_device *pdev;
 	void __iomem *regs;
 };
@@ -192,6 +197,11 @@ struct vc4_exec_info {
 	/* Sequence number for this bin/render job. */
 	uint64_t seqno;
 
+	/* Last current addresses the hardware was processing when the
+	 * hangcheck timer checked on us.
+	 */
+	uint32_t last_ct0ca, last_ct1ca;
+
 	/* Kernel-space copy of the ioctl arguments */
 	struct drm_vc4_submit_cl *args;
 
@@ -434,7 +444,6 @@ void vc4_plane_async_set_fb(struct drm_plane *plane,
 extern struct platform_driver vc4_v3d_driver;
 int vc4_v3d_debugfs_ident(struct seq_file *m, void *unused);
 int vc4_v3d_debugfs_regs(struct seq_file *m, void *unused);
-int vc4_v3d_set_power(struct vc4_dev *vc4, bool on);
 
 /* vc4_validate.c */
 int
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 48ce30a6f4b5..202aa1544acc 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -23,6 +23,7 @@
 
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/device.h>
 #include <linux/io.h>
 
@@ -228,8 +229,16 @@ vc4_reset(struct drm_device *dev)
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 
 	DRM_INFO("Resetting GPU.\n");
-	vc4_v3d_set_power(vc4, false);
-	vc4_v3d_set_power(vc4, true);
+
+	mutex_lock(&vc4->power_lock);
+	if (vc4->power_refcount) {
+		/* Power the device off and back on the by dropping the
+		 * reference on runtime PM.
+		 */
+		pm_runtime_put_sync_suspend(&vc4->v3d->pdev->dev);
+		pm_runtime_get_sync(&vc4->v3d->pdev->dev);
+	}
+	mutex_unlock(&vc4->power_lock);
 
 	vc4_irq_reset(dev);
 
@@ -257,10 +266,17 @@ vc4_hangcheck_elapsed(unsigned long data)
 	struct drm_device *dev = (struct drm_device *)data;
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	uint32_t ct0ca, ct1ca;
+	unsigned long irqflags;
+	struct vc4_exec_info *exec;
+
+	spin_lock_irqsave(&vc4->job_lock, irqflags);
+	exec = vc4_first_job(vc4);
 
 	/* If idle, we can stop watching for hangs. */
-	if (list_empty(&vc4->job_list))
+	if (!exec) {
+		spin_unlock_irqrestore(&vc4->job_lock, irqflags);
 		return;
+	}
 
 	ct0ca = V3D_READ(V3D_CTNCA(0));
 	ct1ca = V3D_READ(V3D_CTNCA(1));
@@ -268,14 +284,16 @@ vc4_hangcheck_elapsed(unsigned long data)
 	/* If we've made any progress in execution, rearm the timer
 	 * and wait.
 	 */
-	if (ct0ca != vc4->hangcheck.last_ct0ca ||
-	    ct1ca != vc4->hangcheck.last_ct1ca) {
-		vc4->hangcheck.last_ct0ca = ct0ca;
-		vc4->hangcheck.last_ct1ca = ct1ca;
+	if (ct0ca != exec->last_ct0ca || ct1ca != exec->last_ct1ca) {
+		exec->last_ct0ca = ct0ca;
+		exec->last_ct1ca = ct1ca;
+		spin_unlock_irqrestore(&vc4->job_lock, irqflags);
 		vc4_queue_hangcheck(dev);
 		return;
 	}
 
+	spin_unlock_irqrestore(&vc4->job_lock, irqflags);
+
 	/* We've gone too long with no progress, reset.  This has to
 	 * be done from a work struct, since resetting can sleep and
 	 * this timer hook isn't allowed to.
@@ -340,12 +358,7 @@ vc4_wait_for_seqno(struct drm_device *dev, uint64_t seqno, uint64_t timeout_ns,
 	finish_wait(&vc4->job_wait_queue, &wait);
 	trace_vc4_wait_for_seqno_end(dev, seqno);
 
-	if (ret && ret != -ERESTARTSYS) {
-		DRM_ERROR("timeout waiting for render thread idle\n");
-		return ret;
-	}
-
-	return 0;
+	return ret;
 }
 
 static void
@@ -578,9 +591,9 @@ vc4_get_bcl(struct drm_device *dev, struct vc4_exec_info *exec)
 	}
 
 	bo = vc4_bo_create(dev, exec_size, true);
-	if (!bo) {
+	if (IS_ERR(bo)) {
 		DRM_ERROR("Couldn't allocate BO for binning\n");
-		ret = -ENOMEM;
+		ret = PTR_ERR(bo);
 		goto fail;
 	}
 	exec->exec_bo = &bo->base;
@@ -617,6 +630,7 @@ fail:
 static void
 vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	unsigned i;
 
 	/* Need the struct lock for drm_gem_object_unreference(). */
@@ -635,6 +649,11 @@ vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec)
 	}
 	mutex_unlock(&dev->struct_mutex);
 
+	mutex_lock(&vc4->power_lock);
+	if (--vc4->power_refcount == 0)
+		pm_runtime_put(&vc4->v3d->pdev->dev);
+	mutex_unlock(&vc4->power_lock);
+
 	kfree(exec);
 }
 
@@ -746,6 +765,9 @@ vc4_wait_bo_ioctl(struct drm_device *dev, void *data,
 	struct drm_gem_object *gem_obj;
 	struct vc4_bo *bo;
 
+	if (args->pad != 0)
+		return -EINVAL;
+
 	gem_obj = drm_gem_object_lookup(dev, file_priv, args->handle);
 	if (!gem_obj) {
 		DRM_ERROR("Failed to look up GEM BO %d\n", args->handle);
@@ -772,7 +794,7 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct drm_vc4_submit_cl *args = data;
 	struct vc4_exec_info *exec;
-	int ret;
+	int ret = 0;
 
 	if ((args->flags & ~VC4_SUBMIT_CL_USE_CLEAR_COLOR) != 0) {
 		DRM_ERROR("Unknown flags: 0x%02x\n", args->flags);
@@ -785,6 +807,15 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 		return -ENOMEM;
 	}
 
+	mutex_lock(&vc4->power_lock);
+	if (vc4->power_refcount++ == 0)
+		ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev);
+	mutex_unlock(&vc4->power_lock);
+	if (ret < 0) {
+		kfree(exec);
+		return ret;
+	}
+
 	exec->args = args;
 	INIT_LIST_HEAD(&exec->unref_list);
 
@@ -839,6 +870,8 @@ vc4_gem_init(struct drm_device *dev)
 		    (unsigned long)dev);
 
 	INIT_WORK(&vc4->job_done_work, vc4_job_done_work);
+
+	mutex_init(&vc4->power_lock);
 }
 
 void
diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c
index b68060e758db..78a21357fb2d 100644
--- a/drivers/gpu/drm/vc4/vc4_irq.c
+++ b/drivers/gpu/drm/vc4/vc4_irq.c
@@ -57,7 +57,7 @@ vc4_overflow_mem_work(struct work_struct *work)
 	struct vc4_bo *bo;
 
 	bo = vc4_bo_create(dev, 256 * 1024, true);
-	if (!bo) {
+	if (IS_ERR(bo)) {
 		DRM_ERROR("Couldn't allocate binner overflow mem\n");
 		return;
 	}
diff --git a/drivers/gpu/drm/vc4/vc4_render_cl.c b/drivers/gpu/drm/vc4/vc4_render_cl.c
index 8a2a312e2c1b..0f12418725e5 100644
--- a/drivers/gpu/drm/vc4/vc4_render_cl.c
+++ b/drivers/gpu/drm/vc4/vc4_render_cl.c
@@ -316,20 +316,11 @@ static int vc4_create_rcl_bo(struct drm_device *dev, struct vc4_exec_info *exec,
 	size += xtiles * ytiles * loop_body_size;
 
 	setup->rcl = &vc4_bo_create(dev, size, true)->base;
-	if (!setup->rcl)
-		return -ENOMEM;
+	if (IS_ERR(setup->rcl))
+		return PTR_ERR(setup->rcl);
 	list_add_tail(&to_vc4_bo(&setup->rcl->base)->unref_head,
 		      &exec->unref_list);
 
-	rcl_u8(setup, VC4_PACKET_TILE_RENDERING_MODE_CONFIG);
-	rcl_u32(setup,
-		(setup->color_write ? (setup->color_write->paddr +
-				       args->color_write.offset) :
-		 0));
-	rcl_u16(setup, args->width);
-	rcl_u16(setup, args->height);
-	rcl_u16(setup, args->color_write.bits);
-
 	/* The tile buffer gets cleared when the previous tile is stored.  If
 	 * the clear values changed between frames, then the tile buffer has
 	 * stale clear values in it, so we have to do a store in None mode (no
@@ -349,6 +340,15 @@ static int vc4_create_rcl_bo(struct drm_device *dev, struct vc4_exec_info *exec,
 		rcl_u32(setup, 0); /* no address, since we're in None mode */
 	}
 
+	rcl_u8(setup, VC4_PACKET_TILE_RENDERING_MODE_CONFIG);
+	rcl_u32(setup,
+		(setup->color_write ? (setup->color_write->paddr +
+				       args->color_write.offset) :
+		 0));
+	rcl_u16(setup, args->width);
+	rcl_u16(setup, args->height);
+	rcl_u16(setup, args->color_write.bits);
+
 	for (y = min_y_tile; y <= max_y_tile; y++) {
 		for (x = min_x_tile; x <= max_x_tile; x++) {
 			bool first = (x == min_x_tile && y == min_y_tile);
diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c
index 314ff71db978..31de5d17bc85 100644
--- a/drivers/gpu/drm/vc4/vc4_v3d.c
+++ b/drivers/gpu/drm/vc4/vc4_v3d.c
@@ -17,6 +17,7 @@
  */
 
 #include "linux/component.h"
+#include "linux/pm_runtime.h"
 #include "vc4_drv.h"
 #include "vc4_regs.h"
 
@@ -144,18 +145,6 @@ int vc4_v3d_debugfs_ident(struct seq_file *m, void *unused)
 }
 #endif /* CONFIG_DEBUG_FS */
 
-int
-vc4_v3d_set_power(struct vc4_dev *vc4, bool on)
-{
-	/* XXX: This interface is needed for GPU reset, and the way to
-	 * do it is to turn our power domain off and back on.  We
-	 * can't just reset from within the driver, because the reset
-	 * bits are in the power domain's register area, and get set
-	 * during the poweron process.
-	 */
-	return 0;
-}
-
 static void vc4_v3d_init_hw(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
@@ -167,6 +156,29 @@ static void vc4_v3d_init_hw(struct drm_device *dev)
 	V3D_WRITE(V3D_VPMBASE, 0);
 }
 
+#ifdef CONFIG_PM
+static int vc4_v3d_runtime_suspend(struct device *dev)
+{
+	struct vc4_v3d *v3d = dev_get_drvdata(dev);
+	struct vc4_dev *vc4 = v3d->vc4;
+
+	vc4_irq_uninstall(vc4->dev);
+
+	return 0;
+}
+
+static int vc4_v3d_runtime_resume(struct device *dev)
+{
+	struct vc4_v3d *v3d = dev_get_drvdata(dev);
+	struct vc4_dev *vc4 = v3d->vc4;
+
+	vc4_v3d_init_hw(vc4->dev);
+	vc4_irq_postinstall(vc4->dev);
+
+	return 0;
+}
+#endif
+
 static int vc4_v3d_bind(struct device *dev, struct device *master, void *data)
 {
 	struct platform_device *pdev = to_platform_device(dev);
@@ -179,6 +191,8 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data)
 	if (!v3d)
 		return -ENOMEM;
 
+	dev_set_drvdata(dev, v3d);
+
 	v3d->pdev = pdev;
 
 	v3d->regs = vc4_ioremap_regs(pdev, 0);
@@ -186,6 +200,7 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data)
 		return PTR_ERR(v3d->regs);
 
 	vc4->v3d = v3d;
+	v3d->vc4 = vc4;
 
 	if (V3D_READ(V3D_IDENT0) != V3D_EXPECTED_IDENT0) {
 		DRM_ERROR("V3D_IDENT0 read 0x%08x instead of 0x%08x\n",
@@ -207,6 +222,8 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data)
 		return ret;
 	}
 
+	pm_runtime_enable(dev);
+
 	return 0;
 }
 
@@ -216,6 +233,8 @@ static void vc4_v3d_unbind(struct device *dev, struct device *master,
 	struct drm_device *drm = dev_get_drvdata(master);
 	struct vc4_dev *vc4 = to_vc4_dev(drm);
 
+	pm_runtime_disable(dev);
+
 	drm_irq_uninstall(drm);
 
 	/* Disable the binner's overflow memory address, so the next
@@ -228,6 +247,10 @@ static void vc4_v3d_unbind(struct device *dev, struct device *master,
 	vc4->v3d = NULL;
 }
 
+static const struct dev_pm_ops vc4_v3d_pm_ops = {
+	SET_RUNTIME_PM_OPS(vc4_v3d_runtime_suspend, vc4_v3d_runtime_resume, NULL)
+};
+
 static const struct component_ops vc4_v3d_ops = {
 	.bind   = vc4_v3d_bind,
 	.unbind = vc4_v3d_unbind,
@@ -255,5 +278,6 @@ struct platform_driver vc4_v3d_driver = {
 	.driver = {
 		.name = "vc4_v3d",
 		.of_match_table = vc4_v3d_dt_match,
+		.pm = &vc4_v3d_pm_ops,
 	},
 };
diff --git a/drivers/gpu/drm/vc4/vc4_validate.c b/drivers/gpu/drm/vc4/vc4_validate.c
index e26d9f6face3..24c2c746e8f3 100644
--- a/drivers/gpu/drm/vc4/vc4_validate.c
+++ b/drivers/gpu/drm/vc4/vc4_validate.c
@@ -401,8 +401,8 @@ validate_tile_binning_config(VALIDATE_ARGS)
 	tile_bo = vc4_bo_create(dev, exec->tile_alloc_offset + tile_alloc_size,
 				true);
 	exec->tile_bo = &tile_bo->base;
-	if (!exec->tile_bo)
-		return -ENOMEM;
+	if (IS_ERR(exec->tile_bo))
+		return PTR_ERR(exec->tile_bo);
 	list_add_tail(&tile_bo->unref_head, &exec->unref_list);
 
 	/* tile alloc address. */
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
index db082bea8daf..c5a1a08b0449 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
@@ -563,6 +563,8 @@ static void vmw_sou_connector_destroy(struct drm_connector *connector)
 
 static const struct drm_connector_funcs vmw_sou_connector_funcs = {
 	.dpms = vmw_du_connector_dpms,
+	.detect = vmw_du_connector_detect,
+	.fill_modes = vmw_du_connector_fill_modes,
 	.set_property = vmw_du_connector_set_property,
 	.destroy = vmw_sou_connector_destroy,
 };
diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
index da462afcb225..dd2dbb9746ce 100644
--- a/drivers/gpu/host1x/bus.c
+++ b/drivers/gpu/host1x/bus.c
@@ -18,6 +18,7 @@
 #include <linux/host1x.h>
 #include <linux/of.h>
 #include <linux/slab.h>
+#include <linux/of_device.h>
 
 #include "bus.h"
 #include "dev.h"
@@ -394,6 +395,7 @@ static int host1x_device_add(struct host1x *host1x,
 	device->dev.coherent_dma_mask = host1x->dev->coherent_dma_mask;
 	device->dev.dma_mask = &device->dev.coherent_dma_mask;
 	dev_set_name(&device->dev, "%s", driver->driver.name);
+	of_dma_configure(&device->dev, host1x->dev->of_node);
 	device->dev.release = host1x_device_release;
 	device->dev.bus = &host1x_bus_type;
 	device->dev.parent = host1x->dev;
diff --git a/drivers/gpu/host1x/cdma.c b/drivers/gpu/host1x/cdma.c
index 5a8c8d55317a..a18db4d5347c 100644
--- a/drivers/gpu/host1x/cdma.c
+++ b/drivers/gpu/host1x/cdma.c
@@ -52,8 +52,8 @@ static void host1x_pushbuffer_destroy(struct push_buffer *pb)
 	struct host1x *host1x = cdma_to_host1x(cdma);
 
 	if (pb->phys != 0)
-		dma_free_writecombine(host1x->dev, pb->size_bytes + 4,
-				      pb->mapped, pb->phys);
+		dma_free_wc(host1x->dev, pb->size_bytes + 4, pb->mapped,
+			    pb->phys);
 
 	pb->mapped = NULL;
 	pb->phys = 0;
@@ -76,8 +76,8 @@ static int host1x_pushbuffer_init(struct push_buffer *pb)
 	pb->pos = 0;
 
 	/* allocate and map pushbuffer memory */
-	pb->mapped = dma_alloc_writecombine(host1x->dev, pb->size_bytes + 4,
-					    &pb->phys, GFP_KERNEL);
+	pb->mapped = dma_alloc_wc(host1x->dev, pb->size_bytes + 4, &pb->phys,
+				  GFP_KERNEL);
 	if (!pb->mapped)
 		goto fail;
 
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index 314bf3718cc7..ff348690df94 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -23,6 +23,7 @@
 #include <linux/of_device.h>
 #include <linux/clk.h>
 #include <linux/io.h>
+#include <linux/dma-mapping.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/host1x.h>
@@ -68,6 +69,7 @@ static const struct host1x_info host1x01_info = {
 	.nb_bases	= 8,
 	.init		= host1x01_init,
 	.sync_offset	= 0x3000,
+	.dma_mask	= DMA_BIT_MASK(32),
 };
 
 static const struct host1x_info host1x02_info = {
@@ -77,6 +79,7 @@ static const struct host1x_info host1x02_info = {
 	.nb_bases = 12,
 	.init = host1x02_init,
 	.sync_offset = 0x3000,
+	.dma_mask = DMA_BIT_MASK(32),
 };
 
 static const struct host1x_info host1x04_info = {
@@ -86,6 +89,7 @@ static const struct host1x_info host1x04_info = {
 	.nb_bases = 64,
 	.init = host1x04_init,
 	.sync_offset = 0x2100,
+	.dma_mask = DMA_BIT_MASK(34),
 };
 
 static const struct host1x_info host1x05_info = {
@@ -95,6 +99,7 @@ static const struct host1x_info host1x05_info = {
 	.nb_bases = 64,
 	.init = host1x05_init,
 	.sync_offset = 0x2100,
+	.dma_mask = DMA_BIT_MASK(34),
 };
 
 static struct of_device_id host1x_of_match[] = {
@@ -148,6 +153,8 @@ static int host1x_probe(struct platform_device *pdev)
 	if (IS_ERR(host->regs))
 		return PTR_ERR(host->regs);
 
+	dma_set_mask_and_coherent(host->dev, host->info->dma_mask);
+
 	if (host->info->init) {
 		err = host->info->init(host);
 		if (err)
diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h
index 0b6e8e9629c5..dace124994bb 100644
--- a/drivers/gpu/host1x/dev.h
+++ b/drivers/gpu/host1x/dev.h
@@ -96,6 +96,7 @@ struct host1x_info {
 	int	nb_mlocks;		/* host1x: number of mlocks */
 	int	(*init)(struct host1x *); /* initialize per SoC ops */
 	int	sync_offset;
+	u64	dma_mask;		/* mask of addressable memory */
 };
 
 struct host1x {
diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index 63bd63f3c7df..defa7995f213 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -467,9 +467,8 @@ static inline int copy_gathers(struct host1x_job *job, struct device *dev)
 		size += g->words * sizeof(u32);
 	}
 
-	job->gather_copy_mapped = dma_alloc_writecombine(dev, size,
-							 &job->gather_copy,
-							 GFP_KERNEL);
+	job->gather_copy_mapped = dma_alloc_wc(dev, size, &job->gather_copy,
+					       GFP_KERNEL);
 	if (!job->gather_copy_mapped) {
 		job->gather_copy_mapped = NULL;
 		return -ENOMEM;
@@ -578,9 +577,8 @@ void host1x_job_unpin(struct host1x_job *job)
 	job->num_unpins = 0;
 
 	if (job->gather_copy_size)
-		dma_free_writecombine(job->channel->dev, job->gather_copy_size,
-				      job->gather_copy_mapped,
-				      job->gather_copy);
+		dma_free_wc(job->channel->dev, job->gather_copy_size,
+		            job->gather_copy_mapped, job->gather_copy);
 }
 EXPORT_SYMBOL(host1x_job_unpin);
 
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index f2e13eb8339f..e00db3f510dd 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -1050,6 +1050,17 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base)
 	for (i = 0; i < ARRAY_SIZE(client_reg); i++) {
 		const struct ipu_platform_reg *reg = &client_reg[i];
 		struct platform_device *pdev;
+		struct device_node *of_node;
+
+		/* Associate subdevice with the corresponding port node */
+		of_node = of_graph_get_port_by_id(dev->of_node, i);
+		if (!of_node) {
+			dev_info(dev,
+				 "no port@%d node in %s, not using %s%d\n",
+				 i, dev->of_node->full_name,
+				 (i / 2) ? "DI" : "CSI", i % 2);
+			continue;
+		}
 
 		pdev = platform_device_alloc(reg->name, id++);
 		if (!pdev) {
@@ -1057,17 +1068,9 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base)
 			goto err_register;
 		}
 
+		pdev->dev.of_node = of_node;
 		pdev->dev.parent = dev;
 
-		/* Associate subdevice with the corresponding port node */
-		pdev->dev.of_node = of_graph_get_port_by_id(dev->of_node, i);
-		if (!pdev->dev.of_node) {
-			dev_err(dev, "missing port@%d node in %s\n", i,
-				dev->of_node->full_name);
-			ret = -ENODEV;
-			goto err_register;
-		}
-
 		ret = platform_device_add_data(pdev, &reg->pdata,
 					       sizeof(reg->pdata));
 		if (!ret)
@@ -1289,10 +1292,6 @@ static int ipu_probe(struct platform_device *pdev)
 	ipu->irq_sync = irq_sync;
 	ipu->irq_err = irq_err;
 
-	ret = ipu_irq_init(ipu);
-	if (ret)
-		goto out_failed_irq;
-
 	ret = device_reset(&pdev->dev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to reset: %d\n", ret);
@@ -1302,6 +1301,10 @@ static int ipu_probe(struct platform_device *pdev)
 	if (ret)
 		goto out_failed_reset;
 
+	ret = ipu_irq_init(ipu);
+	if (ret)
+		goto out_failed_irq;
+
 	/* Set MCU_T to divide MCU access window into 2 */
 	ipu_cm_write(ipu, 0x00400000L | (IPU_MCU_T_DEFAULT << 18),
 			IPU_DISP_GEN);
@@ -1324,9 +1327,9 @@ static int ipu_probe(struct platform_device *pdev)
 failed_add_clients:
 	ipu_submodules_exit(ipu);
 failed_submodules_init:
-out_failed_reset:
 	ipu_irq_exit(ipu);
 out_failed_irq:
+out_failed_reset:
 	clk_disable_unprepare(ipu->clk);
 	return ret;
 }
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 4ebc796b4f33..2f8c0f40930b 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -256,12 +256,6 @@ struct hv_monitor_page {
 	u8 rsvdz4[1984];
 };
 
-/* Declare the various hypercall operations. */
-enum hv_call_code {
-	HVCALL_POST_MESSAGE	= 0x005c,
-	HVCALL_SIGNAL_EVENT	= 0x005d,
-};
-
 /* Definition of the hv_post_message hypercall input structure. */
 struct hv_input_post_message {
 	union hv_connection_id connectionid;
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 60fb80bd353d..5c2d13a687aa 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -685,6 +685,20 @@ config SENSORS_LTC2945
 	  This driver can also be built as a module. If so, the module will
 	  be called ltc2945.
 
+config SENSORS_LTC2990
+	tristate "Linear Technology LTC2990 (current monitoring mode only)"
+	depends on I2C
+	help
+	  If you say yes here you get support for Linear Technology LTC2990
+	  I2C System Monitor. The LTC2990 supports a combination of voltage,
+	  current and temperature monitoring, but in addition to the Vcc supply
+	  voltage and chip temperature, this driver currently only supports
+	  reading two currents by measuring two differential voltages across
+	  series resistors.
+
+	  This driver can also be built as a module. If so, the module will
+	  be called ltc2990.
+
 config SENSORS_LTC4151
 	tristate "Linear Technology LTC4151"
 	depends on I2C
@@ -1127,7 +1141,7 @@ config SENSORS_NTC_THERMISTOR
 
 	  Currently, this driver supports
 	  NCP15WB473, NCP18WB473, NCP21WB473, NCP03WB473, NCP15WL333,
-	  and NCP03WF104 from Murata and B57330V2103 from EPCOS.
+	  NCP03WF104 and NCP15XH103 from Murata and B57330V2103 from EPCOS.
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called ntc-thermistor.
@@ -1176,6 +1190,21 @@ config SENSORS_NCT7904
 	  This driver can also be built as a module.  If so, the module
 	  will be called nct7904.
 
+config SENSORS_NSA320
+	tristate "ZyXEL NSA320 and compatible fan speed and temperature sensors"
+	depends on GPIOLIB && OF
+	depends on MACH_KIRKWOOD || COMPILE_TEST
+	help
+	  If you say yes here you get support for hardware monitoring
+	  for the ZyXEL NSA320 Media Server and other compatible devices
+	  (probably the NSA325 and some NSA310 variants).
+
+	  The sensor data is taken from a Holtek HT46R065 microcontroller
+	  connected to GPIO lines.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called nsa320-hwmon.
+
 config SENSORS_PCF8591
 	tristate "Philips PCF8591 ADC/DAC"
 	depends on I2C
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index 30c94df31465..58cc3acba7e7 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -100,6 +100,7 @@ obj-$(CONFIG_SENSORS_LM95234)	+= lm95234.o
 obj-$(CONFIG_SENSORS_LM95241)	+= lm95241.o
 obj-$(CONFIG_SENSORS_LM95245)	+= lm95245.o
 obj-$(CONFIG_SENSORS_LTC2945)	+= ltc2945.o
+obj-$(CONFIG_SENSORS_LTC2990)	+= ltc2990.o
 obj-$(CONFIG_SENSORS_LTC4151)	+= ltc4151.o
 obj-$(CONFIG_SENSORS_LTC4215)	+= ltc4215.o
 obj-$(CONFIG_SENSORS_LTC4222)	+= ltc4222.o
@@ -123,6 +124,7 @@ obj-$(CONFIG_SENSORS_NCT6683)	+= nct6683.o
 obj-$(CONFIG_SENSORS_NCT6775)	+= nct6775.o
 obj-$(CONFIG_SENSORS_NCT7802)	+= nct7802.o
 obj-$(CONFIG_SENSORS_NCT7904)	+= nct7904.o
+obj-$(CONFIG_SENSORS_NSA320)	+= nsa320-hwmon.o
 obj-$(CONFIG_SENSORS_NTC_THERMISTOR)	+= ntc_thermistor.o
 obj-$(CONFIG_SENSORS_PC87360)	+= pc87360.o
 obj-$(CONFIG_SENSORS_PC87427)	+= pc87427.o
@@ -149,7 +151,7 @@ obj-$(CONFIG_SENSORS_TMP103)	+= tmp103.o
 obj-$(CONFIG_SENSORS_TMP401)	+= tmp401.o
 obj-$(CONFIG_SENSORS_TMP421)	+= tmp421.o
 obj-$(CONFIG_SENSORS_TWL4030_MADC)+= twl4030-madc-hwmon.o
-obj-$(CONFIG_SENSORS_VEXPRESS)	+= vexpress.o
+obj-$(CONFIG_SENSORS_VEXPRESS)	+= vexpress-hwmon.o
 obj-$(CONFIG_SENSORS_VIA_CPUTEMP)+= via-cputemp.o
 obj-$(CONFIG_SENSORS_VIA686A)	+= via686a.o
 obj-$(CONFIG_SENSORS_VT1211)	+= vt1211.o
diff --git a/drivers/hwmon/ads1015.c b/drivers/hwmon/ads1015.c
index f155b8380481..2b3105c8aed3 100644
--- a/drivers/hwmon/ads1015.c
+++ b/drivers/hwmon/ads1015.c
@@ -126,7 +126,7 @@ static int ads1015_reg_to_mv(struct i2c_client *client, unsigned int channel,
 	struct ads1015_data *data = i2c_get_clientdata(client);
 	unsigned int pga = data->channel_data[channel].pga;
 	int fullscale = fullscale_table[pga];
-	const unsigned mask = data->id == ads1115 ? 0x7fff : 0x7ff0;
+	const int mask = data->id == ads1115 ? 0x7fff : 0x7ff0;
 
 	return DIV_ROUND_CLOSEST(reg * fullscale, mask);
 }
diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c
index 82de3deeb18a..685568b1236d 100644
--- a/drivers/hwmon/gpio-fan.c
+++ b/drivers/hwmon/gpio-fan.c
@@ -406,16 +406,11 @@ static int gpio_fan_get_cur_state(struct thermal_cooling_device *cdev,
 				  unsigned long *state)
 {
 	struct gpio_fan_data *fan_data = cdev->devdata;
-	int r;
 
 	if (!fan_data)
 		return -EINVAL;
 
-	r = get_fan_speed_index(fan_data);
-	if (r < 0)
-		return r;
-
-	*state = r;
+	*state = fan_data->speed_index;
 	return 0;
 }
 
diff --git a/drivers/hwmon/iio_hwmon.c b/drivers/hwmon/iio_hwmon.c
index 17ae2eb26ce2..b550ba5fa58a 100644
--- a/drivers/hwmon/iio_hwmon.c
+++ b/drivers/hwmon/iio_hwmon.c
@@ -67,6 +67,7 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 	enum iio_chan_type type;
 	struct iio_channel *channels;
 	const char *name = "iio_hwmon";
+	char *sname;
 
 	if (dev->of_node && dev->of_node->name)
 		name = dev->of_node->name;
@@ -144,7 +145,15 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 
 	st->attr_group.attrs = st->attrs;
 	st->groups[0] = &st->attr_group;
-	st->hwmon_dev = hwmon_device_register_with_groups(dev, name, st,
+
+	sname = devm_kstrdup(dev, name, GFP_KERNEL);
+	if (!sname) {
+		ret = -ENOMEM;
+		goto error_release_channels;
+	}
+
+	strreplace(sname, '-', '_');
+	st->hwmon_dev = hwmon_device_register_with_groups(dev, sname, st,
 							  st->groups);
 	if (IS_ERR(st->hwmon_dev)) {
 		ret = PTR_ERR(st->hwmon_dev);
diff --git a/drivers/hwmon/ltc2990.c b/drivers/hwmon/ltc2990.c
new file mode 100644
index 000000000000..8f8fe059ab48
--- /dev/null
+++ b/drivers/hwmon/ltc2990.c
@@ -0,0 +1,161 @@
+/*
+ * Driver for Linear Technology LTC2990 power monitor
+ *
+ * Copyright (C) 2014 Topic Embedded Products
+ * Author: Mike Looijmans <mike.looijmans@topic.nl>
+ *
+ * License: GPLv2
+ *
+ * This driver assumes the chip is wired as a dual current monitor, and
+ * reports the voltage drop across two series resistors. It also reports
+ * the chip's internal temperature and Vcc power supply voltage.
+ */
+
+#include <linux/err.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/i2c.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#define LTC2990_STATUS	0x00
+#define LTC2990_CONTROL	0x01
+#define LTC2990_TRIGGER	0x02
+#define LTC2990_TINT_MSB	0x04
+#define LTC2990_V1_MSB	0x06
+#define LTC2990_V2_MSB	0x08
+#define LTC2990_V3_MSB	0x0A
+#define LTC2990_V4_MSB	0x0C
+#define LTC2990_VCC_MSB	0x0E
+
+#define LTC2990_CONTROL_KELVIN		BIT(7)
+#define LTC2990_CONTROL_SINGLE		BIT(6)
+#define LTC2990_CONTROL_MEASURE_ALL	(0x3 << 3)
+#define LTC2990_CONTROL_MODE_CURRENT	0x06
+#define LTC2990_CONTROL_MODE_VOLTAGE	0x07
+
+/* convert raw register value to sign-extended integer in 16-bit range */
+static int ltc2990_voltage_to_int(int raw)
+{
+	if (raw & BIT(14))
+		return -(0x4000 - (raw & 0x3FFF)) << 2;
+	else
+		return (raw & 0x3FFF) << 2;
+}
+
+/* Return the converted value from the given register in uV or mC */
+static int ltc2990_get_value(struct i2c_client *i2c, u8 reg, int *result)
+{
+	int val;
+
+	val = i2c_smbus_read_word_swapped(i2c, reg);
+	if (unlikely(val < 0))
+		return val;
+
+	switch (reg) {
+	case LTC2990_TINT_MSB:
+		/* internal temp, 0.0625 degrees/LSB, 13-bit  */
+		val = (val & 0x1FFF) << 3;
+		*result = (val * 1000) >> 7;
+		break;
+	case LTC2990_V1_MSB:
+	case LTC2990_V3_MSB:
+		 /* Vx-Vy, 19.42uV/LSB. Depends on mode. */
+		*result = ltc2990_voltage_to_int(val) * 1942 / (4 * 100);
+		break;
+	case LTC2990_VCC_MSB:
+		/* Vcc, 305.18μV/LSB, 2.5V offset */
+		*result = (ltc2990_voltage_to_int(val) * 30518 /
+			   (4 * 100 * 1000)) + 2500;
+		break;
+	default:
+		return -EINVAL; /* won't happen, keep compiler happy */
+	}
+
+	return 0;
+}
+
+static ssize_t ltc2990_show_value(struct device *dev,
+				  struct device_attribute *da, char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
+	int value;
+	int ret;
+
+	ret = ltc2990_get_value(dev_get_drvdata(dev), attr->index, &value);
+	if (unlikely(ret < 0))
+		return ret;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", value);
+}
+
+static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, ltc2990_show_value, NULL,
+			  LTC2990_TINT_MSB);
+static SENSOR_DEVICE_ATTR(curr1_input, S_IRUGO, ltc2990_show_value, NULL,
+			  LTC2990_V1_MSB);
+static SENSOR_DEVICE_ATTR(curr2_input, S_IRUGO, ltc2990_show_value, NULL,
+			  LTC2990_V3_MSB);
+static SENSOR_DEVICE_ATTR(in0_input, S_IRUGO, ltc2990_show_value, NULL,
+			  LTC2990_VCC_MSB);
+
+static struct attribute *ltc2990_attrs[] = {
+	&sensor_dev_attr_temp1_input.dev_attr.attr,
+	&sensor_dev_attr_curr1_input.dev_attr.attr,
+	&sensor_dev_attr_curr2_input.dev_attr.attr,
+	&sensor_dev_attr_in0_input.dev_attr.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(ltc2990);
+
+static int ltc2990_i2c_probe(struct i2c_client *i2c,
+			     const struct i2c_device_id *id)
+{
+	int ret;
+	struct device *hwmon_dev;
+
+	if (!i2c_check_functionality(i2c->adapter, I2C_FUNC_SMBUS_BYTE_DATA |
+				     I2C_FUNC_SMBUS_WORD_DATA))
+		return -ENODEV;
+
+	/* Setup continuous mode, current monitor */
+	ret = i2c_smbus_write_byte_data(i2c, LTC2990_CONTROL,
+					LTC2990_CONTROL_MEASURE_ALL |
+					LTC2990_CONTROL_MODE_CURRENT);
+	if (ret < 0) {
+		dev_err(&i2c->dev, "Error: Failed to set control mode.\n");
+		return ret;
+	}
+	/* Trigger once to start continuous conversion */
+	ret = i2c_smbus_write_byte_data(i2c, LTC2990_TRIGGER, 1);
+	if (ret < 0) {
+		dev_err(&i2c->dev, "Error: Failed to start acquisition.\n");
+		return ret;
+	}
+
+	hwmon_dev = devm_hwmon_device_register_with_groups(&i2c->dev,
+							   i2c->name,
+							   i2c,
+							   ltc2990_groups);
+
+	return PTR_ERR_OR_ZERO(hwmon_dev);
+}
+
+static const struct i2c_device_id ltc2990_i2c_id[] = {
+	{ "ltc2990", 0 },
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, ltc2990_i2c_id);
+
+static struct i2c_driver ltc2990_i2c_driver = {
+	.driver = {
+		.name = "ltc2990",
+	},
+	.probe    = ltc2990_i2c_probe,
+	.id_table = ltc2990_i2c_id,
+};
+
+module_i2c_driver(ltc2990_i2c_driver);
+
+MODULE_DESCRIPTION("LTC2990 Sensor Driver");
+MODULE_AUTHOR("Topic Embedded Products");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/hwmon/nsa320-hwmon.c b/drivers/hwmon/nsa320-hwmon.c
new file mode 100644
index 000000000000..0517a265741f
--- /dev/null
+++ b/drivers/hwmon/nsa320-hwmon.c
@@ -0,0 +1,215 @@
+/*
+ * drivers/hwmon/nsa320-hwmon.c
+ *
+ * ZyXEL NSA320 Media Servers
+ * hardware monitoring
+ *
+ * Copyright (C) 2016 Adam Baker <linux@baker-net.org.uk>
+ * based on a board file driver
+ * Copyright (C) 2012 Peter Schildmann <linux@schildmann.info>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License v2 as published by the
+ * Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/bitops.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/jiffies.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+
+/* Tests for error return values rely upon this value being < 0x80 */
+#define MAGIC_NUMBER 0x55
+
+/*
+ * The Zyxel hwmon MCU is a Holtek HT46R065 that is factory programmed
+ * to perform temperature and fan speed monitoring. It is read by taking
+ * the active pin low. The 32 bit output word is then clocked onto the
+ * data line. The MSB of the data word is a magic nuber to indicate it
+ * has been read correctly, the next byte is the fan speed (in hundreds
+ * of RPM) and the last two bytes are the temperature (in tenths of a
+ * degree)
+ */
+
+struct nsa320_hwmon {
+	struct mutex		update_lock;	/* lock GPIO operations */
+	unsigned long		last_updated;	/* jiffies */
+	unsigned long		mcu_data;
+	struct gpio_desc	*act;
+	struct gpio_desc	*clk;
+	struct gpio_desc	*data;
+};
+
+enum nsa320_inputs {
+	NSA320_TEMP = 0,
+	NSA320_FAN = 1,
+};
+
+static const char * const nsa320_input_names[] = {
+	[NSA320_TEMP] = "System Temperature",
+	[NSA320_FAN] = "Chassis Fan",
+};
+
+/*
+ * Although this protocol looks similar to SPI the long delay
+ * between the active (aka chip select) signal and the shorter
+ * delay between clock pulses are needed for reliable operation.
+ * The delays provided are taken from the manufacturer kernel,
+ * testing suggest they probably incorporate a reasonable safety
+ * margin. (The single device tested became unreliable if the
+ * delay was reduced to 1/10th of this value.)
+ */
+static s32 nsa320_hwmon_update(struct device *dev)
+{
+	u32 mcu_data;
+	u32 mask;
+	struct nsa320_hwmon *hwmon = dev_get_drvdata(dev);
+
+	mutex_lock(&hwmon->update_lock);
+
+	mcu_data = hwmon->mcu_data;
+
+	if (time_after(jiffies, hwmon->last_updated + HZ) || mcu_data == 0) {
+		gpiod_set_value(hwmon->act, 1);
+		msleep(100);
+
+		mcu_data = 0;
+		for (mask = BIT(31); mask; mask >>= 1) {
+			gpiod_set_value(hwmon->clk, 0);
+			usleep_range(100, 200);
+			gpiod_set_value(hwmon->clk, 1);
+			usleep_range(100, 200);
+			if (gpiod_get_value(hwmon->data))
+				mcu_data |= mask;
+		}
+
+		gpiod_set_value(hwmon->act, 0);
+		dev_dbg(dev, "Read raw MCU data %08x\n", mcu_data);
+
+		if ((mcu_data >> 24) != MAGIC_NUMBER) {
+			dev_dbg(dev, "Read invalid MCU data %08x\n", mcu_data);
+			mcu_data = -EIO;
+		} else {
+			hwmon->mcu_data = mcu_data;
+			hwmon->last_updated = jiffies;
+		}
+	}
+
+	mutex_unlock(&hwmon->update_lock);
+
+	return mcu_data;
+}
+
+static ssize_t show_label(struct device *dev,
+			  struct device_attribute *attr, char *buf)
+{
+	int channel = to_sensor_dev_attr(attr)->index;
+
+	return sprintf(buf, "%s\n", nsa320_input_names[channel]);
+}
+
+static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	s32 mcu_data = nsa320_hwmon_update(dev);
+
+	if (mcu_data < 0)
+		return mcu_data;
+
+	return sprintf(buf, "%d\n", (mcu_data & 0xffff) * 100);
+}
+
+static ssize_t show_fan(struct device *dev, struct device_attribute *attr,
+			char *buf)
+{
+	s32 mcu_data = nsa320_hwmon_update(dev);
+
+	if (mcu_data < 0)
+		return mcu_data;
+
+	return sprintf(buf, "%d\n", ((mcu_data & 0xff0000) >> 16) * 100);
+}
+
+static SENSOR_DEVICE_ATTR(temp1_label, S_IRUGO, show_label, NULL, NSA320_TEMP);
+static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL);
+static SENSOR_DEVICE_ATTR(fan1_label, S_IRUGO, show_label, NULL, NSA320_FAN);
+static DEVICE_ATTR(fan1_input, S_IRUGO, show_fan, NULL);
+
+static struct attribute *nsa320_attrs[] = {
+	&sensor_dev_attr_temp1_label.dev_attr.attr,
+	&dev_attr_temp1_input.attr,
+	&sensor_dev_attr_fan1_label.dev_attr.attr,
+	&dev_attr_fan1_input.attr,
+	NULL
+};
+
+ATTRIBUTE_GROUPS(nsa320);
+
+static const struct of_device_id of_nsa320_hwmon_match[] = {
+	{ .compatible = "zyxel,nsa320-mcu", },
+	{ },
+};
+
+static int nsa320_hwmon_probe(struct platform_device *pdev)
+{
+	struct nsa320_hwmon	*hwmon;
+	struct device		*classdev;
+
+	hwmon = devm_kzalloc(&pdev->dev, sizeof(*hwmon), GFP_KERNEL);
+	if (!hwmon)
+		return -ENOMEM;
+
+	/* Look up the GPIO pins to use */
+	hwmon->act = devm_gpiod_get(&pdev->dev, "act", GPIOD_OUT_LOW);
+	if (IS_ERR(hwmon->act))
+		return PTR_ERR(hwmon->act);
+
+	hwmon->clk = devm_gpiod_get(&pdev->dev, "clk", GPIOD_OUT_HIGH);
+	if (IS_ERR(hwmon->clk))
+		return PTR_ERR(hwmon->clk);
+
+	hwmon->data = devm_gpiod_get(&pdev->dev, "data", GPIOD_IN);
+	if (IS_ERR(hwmon->data))
+		return PTR_ERR(hwmon->data);
+
+	mutex_init(&hwmon->update_lock);
+
+	classdev = devm_hwmon_device_register_with_groups(&pdev->dev,
+					"nsa320", hwmon, nsa320_groups);
+
+	return PTR_ERR_OR_ZERO(classdev);
+
+}
+
+/* All allocations use devres so remove() is not needed. */
+
+static struct platform_driver nsa320_hwmon_driver = {
+	.probe = nsa320_hwmon_probe,
+	.driver = {
+		.name = "nsa320-hwmon",
+		.of_match_table = of_match_ptr(of_nsa320_hwmon_match),
+	},
+};
+
+module_platform_driver(nsa320_hwmon_driver);
+
+MODULE_DEVICE_TABLE(of, of_nsa320_hwmon_match);
+MODULE_AUTHOR("Peter Schildmann <linux@schildmann.info>");
+MODULE_AUTHOR("Adam Baker <linux@baker-net.org.uk>");
+MODULE_DESCRIPTION("NSA320 Hardware Monitoring");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:nsa320-hwmon");
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index feed30646d91..faa6e8dfbaaf 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -54,6 +54,7 @@ static const struct platform_device_id ntc_thermistor_id[] = {
 	{ "ncp15wl333", TYPE_NCPXXWL333 },
 	{ "b57330v2103", TYPE_B57330V2103},
 	{ "ncp03wf104", TYPE_NCPXXWF104 },
+	{ "ncp15xh103", TYPE_NCPXXXH103 },
 	{ },
 };
 
@@ -173,6 +174,43 @@ static const struct ntc_compensation ncpXXwf104[] = {
 	{ .temp_c	= 125, .ohm	= 2522 },
 };
 
+static const struct ntc_compensation ncpXXxh103[] = {
+	{ .temp_c	= -40, .ohm	= 247565 },
+	{ .temp_c	= -35, .ohm	= 181742 },
+	{ .temp_c	= -30, .ohm	= 135128 },
+	{ .temp_c	= -25, .ohm	= 101678 },
+	{ .temp_c	= -20, .ohm	= 77373 },
+	{ .temp_c	= -15, .ohm	= 59504 },
+	{ .temp_c	= -10, .ohm	= 46222 },
+	{ .temp_c	= -5, .ohm	= 36244 },
+	{ .temp_c	= 0, .ohm	= 28674 },
+	{ .temp_c	= 5, .ohm	= 22878 },
+	{ .temp_c	= 10, .ohm	= 18399 },
+	{ .temp_c	= 15, .ohm	= 14910 },
+	{ .temp_c	= 20, .ohm	= 12169 },
+	{ .temp_c	= 25, .ohm	= 10000 },
+	{ .temp_c	= 30, .ohm	= 8271 },
+	{ .temp_c	= 35, .ohm	= 6883 },
+	{ .temp_c	= 40, .ohm	= 5762 },
+	{ .temp_c	= 45, .ohm	= 4851 },
+	{ .temp_c	= 50, .ohm	= 4105 },
+	{ .temp_c	= 55, .ohm	= 3492 },
+	{ .temp_c	= 60, .ohm	= 2985 },
+	{ .temp_c	= 65, .ohm	= 2563 },
+	{ .temp_c	= 70, .ohm	= 2211 },
+	{ .temp_c	= 75, .ohm	= 1915 },
+	{ .temp_c	= 80, .ohm	= 1666 },
+	{ .temp_c	= 85, .ohm	= 1454 },
+	{ .temp_c	= 90, .ohm	= 1275 },
+	{ .temp_c	= 95, .ohm	= 1121 },
+	{ .temp_c	= 100, .ohm	= 990 },
+	{ .temp_c	= 105, .ohm	= 876 },
+	{ .temp_c	= 110, .ohm	= 779 },
+	{ .temp_c	= 115, .ohm	= 694 },
+	{ .temp_c	= 120, .ohm	= 620 },
+	{ .temp_c	= 125, .ohm	= 556 },
+};
+
 /*
  * The following compensation table is from the specification of EPCOS NTC
  * Thermistors Datasheet
@@ -260,6 +298,8 @@ static const struct of_device_id ntc_match[] = {
 		.data = &ntc_thermistor_id[5]},
 	{ .compatible = "murata,ncp03wf104",
 		.data = &ntc_thermistor_id[6] },
+	{ .compatible = "murata,ncp15xh103",
+		.data = &ntc_thermistor_id[7] },
 
 	/* Usage of vendor name "ntc" is deprecated */
 	{ .compatible = "ntc,ncp15wb473",
@@ -609,6 +649,10 @@ static int ntc_thermistor_probe(struct platform_device *pdev)
 		data->comp = ncpXXwf104;
 		data->n_comp = ARRAY_SIZE(ncpXXwf104);
 		break;
+	case TYPE_NCPXXXH103:
+		data->comp = ncpXXxh103;
+		data->n_comp = ARRAY_SIZE(ncpXXxh103);
+		break;
 	default:
 		dev_err(&pdev->dev, "Unknown device type: %lu(%s)\n",
 				pdev_id->driver_data, pdev_id->name);
diff --git a/drivers/hwmon/pmbus/Kconfig b/drivers/hwmon/pmbus/Kconfig
index 7e5cc3d025ef..054d3d863802 100644
--- a/drivers/hwmon/pmbus/Kconfig
+++ b/drivers/hwmon/pmbus/Kconfig
@@ -31,8 +31,8 @@ config SENSORS_ADM1275
 	default n
 	help
 	  If you say yes here you get hardware monitoring support for Analog
-	  Devices ADM1075, ADM1275, ADM1276, ADM1293, and ADM1294 Hot-Swap
-	  Controller and Digital Power Monitors.
+	  Devices ADM1075, ADM1275, ADM1276, ADM1278, ADM1293, and ADM1294
+	  Hot-Swap Controller and Digital Power Monitors.
 
 	  This driver can also be built as a module. If so, the module will
 	  be called adm1275.
diff --git a/drivers/hwmon/pmbus/adm1275.c b/drivers/hwmon/pmbus/adm1275.c
index 188af4c89f40..3baa4f4a8c5e 100644
--- a/drivers/hwmon/pmbus/adm1275.c
+++ b/drivers/hwmon/pmbus/adm1275.c
@@ -24,7 +24,7 @@
 #include <linux/bitops.h>
 #include "pmbus.h"
 
-enum chips { adm1075, adm1275, adm1276, adm1293, adm1294 };
+enum chips { adm1075, adm1275, adm1276, adm1278, adm1293, adm1294 };
 
 #define ADM1275_MFR_STATUS_IOUT_WARN2	BIT(0)
 #define ADM1293_MFR_STATUS_VAUX_UV_WARN	BIT(5)
@@ -41,6 +41,10 @@ enum chips { adm1075, adm1275, adm1276, adm1293, adm1294 };
 #define ADM1075_IRANGE_25		BIT(3)
 #define ADM1075_IRANGE_MASK		(BIT(3) | BIT(4))
 
+#define ADM1278_TEMP1_EN		BIT(3)
+#define ADM1278_VIN_EN			BIT(2)
+#define ADM1278_VOUT_EN			BIT(1)
+
 #define ADM1293_IRANGE_25		0
 #define ADM1293_IRANGE_50		BIT(6)
 #define ADM1293_IRANGE_100		BIT(7)
@@ -54,6 +58,7 @@ enum chips { adm1075, adm1275, adm1276, adm1293, adm1294 };
 
 #define ADM1293_VAUX_EN			BIT(1)
 
+#define ADM1278_PEAK_TEMP		0xd7
 #define ADM1275_IOUT_WARN2_LIMIT	0xd7
 #define ADM1275_DEVICE_CONFIG		0xd8
 
@@ -80,6 +85,7 @@ struct adm1275_data {
 	bool have_iout_min;
 	bool have_pin_min;
 	bool have_pin_max;
+	bool have_temp_max;
 	struct pmbus_driver_info info;
 };
 
@@ -113,6 +119,13 @@ static const struct coefficients adm1276_coefficients[] = {
 	[4] = { 2115, 0, -1 },		/* power, vrange not set */
 };
 
+static const struct coefficients adm1278_coefficients[] = {
+	[0] = { 19599, 0, -2 },		/* voltage */
+	[1] = { 800, 20475, -1 },	/* current */
+	[2] = { 6123, 0, -2 },		/* power */
+	[3] = { 42, 31880, -1 },	/* temperature */
+};
+
 static const struct coefficients adm1293_coefficients[] = {
 	[0] = { 3333, -1, 0 },		/* voltage, vrange 1.2V */
 	[1] = { 5552, -5, -1 },		/* voltage, vrange 7.4V */
@@ -196,6 +209,11 @@ static int adm1275_read_word_data(struct i2c_client *client, int page, int reg)
 			return -ENXIO;
 		ret = pmbus_read_word_data(client, 0, ADM1276_PEAK_PIN);
 		break;
+	case PMBUS_VIRT_READ_TEMP_MAX:
+		if (!data->have_temp_max)
+			return -ENXIO;
+		ret = pmbus_read_word_data(client, 0, ADM1278_PEAK_TEMP);
+		break;
 	case PMBUS_VIRT_RESET_IOUT_HISTORY:
 	case PMBUS_VIRT_RESET_VOUT_HISTORY:
 	case PMBUS_VIRT_RESET_VIN_HISTORY:
@@ -204,6 +222,10 @@ static int adm1275_read_word_data(struct i2c_client *client, int page, int reg)
 		if (!data->have_pin_max)
 			return -ENXIO;
 		break;
+	case PMBUS_VIRT_RESET_TEMP_HISTORY:
+		if (!data->have_temp_max)
+			return -ENXIO;
+		break;
 	default:
 		ret = -ENODATA;
 		break;
@@ -245,6 +267,9 @@ static int adm1275_write_word_data(struct i2c_client *client, int page, int reg,
 			ret = pmbus_write_word_data(client, 0,
 						    ADM1293_PIN_MIN, 0);
 		break;
+	case PMBUS_VIRT_RESET_TEMP_HISTORY:
+		ret = pmbus_write_word_data(client, 0, ADM1278_PEAK_TEMP, 0);
+		break;
 	default:
 		ret = -ENODATA;
 		break;
@@ -312,6 +337,7 @@ static const struct i2c_device_id adm1275_id[] = {
 	{ "adm1075", adm1075 },
 	{ "adm1275", adm1275 },
 	{ "adm1276", adm1276 },
+	{ "adm1278", adm1278 },
 	{ "adm1293", adm1293 },
 	{ "adm1294", adm1294 },
 	{ }
@@ -329,6 +355,7 @@ static int adm1275_probe(struct i2c_client *client,
 	const struct i2c_device_id *mid;
 	const struct coefficients *coefficients;
 	int vindex = -1, voindex = -1, cindex = -1, pindex = -1;
+	int tindex = -1;
 
 	if (!i2c_check_functionality(client->adapter,
 				     I2C_FUNC_SMBUS_READ_BYTE_DATA
@@ -386,6 +413,7 @@ static int adm1275_probe(struct i2c_client *client,
 	info->format[PSC_VOLTAGE_OUT] = direct;
 	info->format[PSC_CURRENT_OUT] = direct;
 	info->format[PSC_POWER] = direct;
+	info->format[PSC_TEMPERATURE] = direct;
 	info->func[0] = PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT;
 
 	info->read_word_data = adm1275_read_word_data;
@@ -460,6 +488,27 @@ static int adm1275_probe(struct i2c_client *client,
 			info->func[0] |=
 			  PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT;
 		break;
+	case adm1278:
+		data->have_vout = true;
+		data->have_pin_max = true;
+		data->have_temp_max = true;
+
+		coefficients = adm1278_coefficients;
+		vindex = 0;
+		cindex = 1;
+		pindex = 2;
+		tindex = 3;
+
+		info->func[0] |= PMBUS_HAVE_PIN | PMBUS_HAVE_STATUS_INPUT;
+		if (config & ADM1278_TEMP1_EN)
+			info->func[0] |=
+				PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP;
+		if (config & ADM1278_VIN_EN)
+			info->func[0] |= PMBUS_HAVE_VIN;
+		if (config & ADM1278_VOUT_EN)
+			info->func[0] |=
+				PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT;
+		break;
 	case adm1293:
 	case adm1294:
 		data->have_iout_min = true;
@@ -537,6 +586,11 @@ static int adm1275_probe(struct i2c_client *client,
 		info->b[PSC_POWER] = coefficients[pindex].b;
 		info->R[PSC_POWER] = coefficients[pindex].R;
 	}
+	if (tindex >= 0) {
+		info->m[PSC_TEMPERATURE] = coefficients[tindex].m;
+		info->b[PSC_TEMPERATURE] = coefficients[tindex].b;
+		info->R[PSC_TEMPERATURE] = coefficients[tindex].R;
+	}
 
 	return pmbus_do_probe(client, id, info);
 }
diff --git a/drivers/hwmon/vexpress.c b/drivers/hwmon/vexpress-hwmon.c
index 8ba419d343f8..8ba419d343f8 100644
--- a/drivers/hwmon/vexpress.c
+++ b/drivers/hwmon/vexpress-hwmon.c
diff --git a/drivers/i2c/busses/i2c-brcmstb.c b/drivers/i2c/busses/i2c-brcmstb.c
index 3711df1d4526..4a45408dd820 100644
--- a/drivers/i2c/busses/i2c-brcmstb.c
+++ b/drivers/i2c/busses/i2c-brcmstb.c
@@ -586,8 +586,7 @@ static int brcmstb_i2c_probe(struct platform_device *pdev)
 	if (!dev)
 		return -ENOMEM;
 
-	dev->bsc_regmap = devm_kzalloc(&pdev->dev, sizeof(struct bsc_regs *),
-				       GFP_KERNEL);
+	dev->bsc_regmap = devm_kzalloc(&pdev->dev, sizeof(*dev->bsc_regmap), GFP_KERNEL);
 	if (!dev->bsc_regmap)
 		return -ENOMEM;
 
diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c
index 438f1b4964c0..d656657b805c 100644
--- a/drivers/i2c/busses/i2c-designware-platdrv.c
+++ b/drivers/i2c/busses/i2c-designware-platdrv.c
@@ -123,6 +123,7 @@ static const struct acpi_device_id dw_i2c_acpi_match[] = {
 	{ "80860F41", 0 },
 	{ "808622C1", 0 },
 	{ "AMD0010", ACCESS_INTR_MASK },
+	{ "AMDI0010", ACCESS_INTR_MASK },
 	{ "AMDI0510", 0 },
 	{ "APMC0D0F", 0 },
 	{ }
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index f62d69799a9c..27fa0cb09538 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -1271,6 +1271,8 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	switch (dev->device) {
 	case PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_SMBUS:
 	case PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_SMBUS:
+	case PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS:
+	case PCI_DEVICE_ID_INTEL_LEWISBURG_SSKU_SMBUS:
 	case PCI_DEVICE_ID_INTEL_DNV_SMBUS:
 		priv->features |= FEATURE_I2C_BLOCK_READ;
 		priv->features |= FEATURE_IRQ;
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index 08d26ba61ed3..13c45296ce5b 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -1450,7 +1450,8 @@ omap_i2c_probe(struct platform_device *pdev)
 
 err_unuse_clocks:
 	omap_i2c_write_reg(omap, OMAP_I2C_CON_REG, 0);
-	pm_runtime_put(omap->dev);
+	pm_runtime_dont_use_autosuspend(omap->dev);
+	pm_runtime_put_sync(omap->dev);
 	pm_runtime_disable(&pdev->dev);
 err_free_mem:
 
@@ -1468,6 +1469,7 @@ static int omap_i2c_remove(struct platform_device *pdev)
 		return ret;
 
 	omap_i2c_write_reg(omap, OMAP_I2C_CON_REG, 0);
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	return 0;
diff --git a/drivers/i2c/busses/i2c-uniphier-f.c b/drivers/i2c/busses/i2c-uniphier-f.c
index f3e5ff8522f0..213ba55e17c3 100644
--- a/drivers/i2c/busses/i2c-uniphier-f.c
+++ b/drivers/i2c/busses/i2c-uniphier-f.c
@@ -467,7 +467,7 @@ static int uniphier_fi2c_clk_init(struct device *dev,
 		bus_speed = UNIPHIER_FI2C_DEFAULT_SPEED;
 
 	if (!bus_speed) {
-		dev_err(dev, "clock-freqyency should not be zero\n");
+		dev_err(dev, "clock-frequency should not be zero\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/i2c/busses/i2c-uniphier.c b/drivers/i2c/busses/i2c-uniphier.c
index 1f4f3f53819c..89eaa8a7e1e0 100644
--- a/drivers/i2c/busses/i2c-uniphier.c
+++ b/drivers/i2c/busses/i2c-uniphier.c
@@ -328,7 +328,7 @@ static int uniphier_i2c_clk_init(struct device *dev,
 		bus_speed = UNIPHIER_I2C_DEFAULT_SPEED;
 
 	if (!bus_speed) {
-		dev_err(dev, "clock-freqyency should not be zero\n");
+		dev_err(dev, "clock-frequency should not be zero\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/ide/pdc202xx_new.c b/drivers/ide/pdc202xx_new.c
index 9ad014a7afc7..b33646be699c 100644
--- a/drivers/ide/pdc202xx_new.c
+++ b/drivers/ide/pdc202xx_new.c
@@ -28,7 +28,6 @@
 
 #ifdef CONFIG_PPC_PMAC
 #include <asm/prom.h>
-#include <asm/pci-bridge.h>
 #endif
 
 #define DRV_NAME "pdc202xx_new"
diff --git a/drivers/ide/pmac.c b/drivers/ide/pmac.c
index 96a345248224..7f0434f7e486 100644
--- a/drivers/ide/pmac.c
+++ b/drivers/ide/pmac.c
@@ -40,7 +40,6 @@
 #include <asm/io.h>
 #include <asm/dbdma.h>
 #include <asm/ide.h>
-#include <asm/pci-bridge.h>
 #include <asm/machdep.h>
 #include <asm/pmac_feature.h>
 #include <asm/sections.h>
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 00da80e02154..94b80a51ab68 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -358,6 +358,7 @@ int ib_register_device(struct ib_device *device,
 	ret = device->query_device(device, &device->attrs, &uhw);
 	if (ret) {
 		printk(KERN_WARNING "Couldn't query the device attributes\n");
+		ib_cache_cleanup_one(device);
 		goto out;
 	}
 
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index f334090bb612..1e37f3515d98 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -1071,7 +1071,7 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num,
 		}
 	}
 
-	if (rec->hop_limit > 1 || use_roce) {
+	if (rec->hop_limit > 0 || use_roce) {
 		ah_attr->ah_flags = IB_AH_GRH;
 		ah_attr->grh.dgid = rec->dgid;
 
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index 3de93517efe4..14606afbfaa8 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -336,7 +336,6 @@ static ssize_t _show_port_gid_attr(struct ib_port *p,
 	union ib_gid gid;
 	struct ib_gid_attr gid_attr = {};
 	ssize_t ret;
-	va_list args;
 
 	ret = ib_query_gid(p->ibdev, p->port_num, tab_attr->index, &gid,
 			   &gid_attr);
@@ -348,7 +347,6 @@ static ssize_t _show_port_gid_attr(struct ib_port *p,
 err:
 	if (gid_attr.ndev)
 		dev_put(gid_attr.ndev);
-	va_end(args);
 	return ret;
 }
 
@@ -722,12 +720,11 @@ static struct attribute_group *get_counter_table(struct ib_device *dev,
 
 	if (get_perf_mad(dev, port_num, IB_PMA_CLASS_PORT_INFO,
 				&cpi, 40, sizeof(cpi)) >= 0) {
-
-		if (cpi.capability_mask && IB_PMA_CLASS_CAP_EXT_WIDTH)
+		if (cpi.capability_mask & IB_PMA_CLASS_CAP_EXT_WIDTH)
 			/* We have extended counters */
 			return &pma_group_ext;
 
-		if (cpi.capability_mask && IB_PMA_CLASS_CAP_EXT_WIDTH_NOIETF)
+		if (cpi.capability_mask & IB_PMA_CLASS_CAP_EXT_WIDTH_NOIETF)
 			/* But not the IETF ones */
 			return &pma_group_noietf;
 	}
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 6ffc9c4e93af..6c6fbff19752 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -1970,7 +1970,8 @@ ssize_t ib_uverbs_create_qp(struct ib_uverbs_file *file,
 		   resp_size);
 	INIT_UDATA(&uhw, buf + sizeof(cmd),
 		   (unsigned long)cmd.response + resp_size,
-		   in_len - sizeof(cmd), out_len - resp_size);
+		   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len - resp_size);
 
 	memset(&cmd_ex, 0, sizeof(cmd_ex));
 	cmd_ex.user_handle = cmd.user_handle;
@@ -3413,7 +3414,8 @@ ssize_t ib_uverbs_create_srq(struct ib_uverbs_file *file,
 
 	INIT_UDATA(&udata, buf + sizeof cmd,
 		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd, out_len - sizeof resp);
+		   in_len - sizeof cmd - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len - sizeof resp);
 
 	ret = __uverbs_create_xsrq(file, ib_dev, &xcmd, &udata);
 	if (ret)
@@ -3439,7 +3441,8 @@ ssize_t ib_uverbs_create_xsrq(struct ib_uverbs_file *file,
 
 	INIT_UDATA(&udata, buf + sizeof cmd,
 		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd, out_len - sizeof resp);
+		   in_len - sizeof cmd - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len - sizeof resp);
 
 	ret = __uverbs_create_xsrq(file, ib_dev, &cmd, &udata);
 	if (ret)
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 26833bfa639b..d68f506c1922 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -817,17 +817,48 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
 }
 
-static void edit_counter(struct mlx4_counter *cnt,
-					struct ib_pma_portcounters *pma_cnt)
+static void edit_counter(struct mlx4_counter *cnt, void *counters,
+			 __be16 attr_id)
 {
-	ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_data,
-			     (be64_to_cpu(cnt->tx_bytes) >> 2));
-	ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_data,
-			     (be64_to_cpu(cnt->rx_bytes) >> 2));
-	ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_packets,
-			     be64_to_cpu(cnt->tx_frames));
-	ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_packets,
-			     be64_to_cpu(cnt->rx_frames));
+	switch (attr_id) {
+	case IB_PMA_PORT_COUNTERS:
+	{
+		struct ib_pma_portcounters *pma_cnt =
+			(struct ib_pma_portcounters *)counters;
+
+		ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_data,
+				     (be64_to_cpu(cnt->tx_bytes) >> 2));
+		ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_data,
+				     (be64_to_cpu(cnt->rx_bytes) >> 2));
+		ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_packets,
+				     be64_to_cpu(cnt->tx_frames));
+		ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_packets,
+				     be64_to_cpu(cnt->rx_frames));
+		break;
+	}
+	case IB_PMA_PORT_COUNTERS_EXT:
+	{
+		struct ib_pma_portcounters_ext *pma_cnt_ext =
+			(struct ib_pma_portcounters_ext *)counters;
+
+		pma_cnt_ext->port_xmit_data =
+			cpu_to_be64(be64_to_cpu(cnt->tx_bytes) >> 2);
+		pma_cnt_ext->port_rcv_data =
+			cpu_to_be64(be64_to_cpu(cnt->rx_bytes) >> 2);
+		pma_cnt_ext->port_xmit_packets = cnt->tx_frames;
+		pma_cnt_ext->port_rcv_packets = cnt->rx_frames;
+		break;
+	}
+	}
+}
+
+static int iboe_process_mad_port_info(void *out_mad)
+{
+	struct ib_class_port_info cpi = {};
+
+	cpi.capability_mask = IB_PMA_CLASS_CAP_EXT_WIDTH;
+	memcpy(out_mad, &cpi, sizeof(cpi));
+	return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
 }
 
 static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
@@ -842,6 +873,9 @@ static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	if (in_mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_PERF_MGMT)
 		return -EINVAL;
 
+	if (in_mad->mad_hdr.attr_id == IB_PMA_CLASS_PORT_INFO)
+		return iboe_process_mad_port_info((void *)(out_mad->data + 40));
+
 	memset(&counter_stats, 0, sizeof(counter_stats));
 	mutex_lock(&dev->counters_table[port_num - 1].mutex);
 	list_for_each_entry(tmp_counter,
@@ -863,7 +897,8 @@ static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		switch (counter_stats.counter_mode & 0xf) {
 		case 0:
 			edit_counter(&counter_stats,
-				     (void *)(out_mad->data + 40));
+				     (void *)(out_mad->data + 40),
+				     in_mad->mad_hdr.attr_id);
 			err = IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
 			break;
 		default:
@@ -894,8 +929,10 @@ int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	 */
 	if (link == IB_LINK_LAYER_INFINIBAND) {
 		if (mlx4_is_slave(dev->dev) &&
-		    in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT &&
-		    in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS)
+		    (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT &&
+		     (in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS ||
+		      in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS_EXT ||
+		      in_mad->mad_hdr.attr_id == IB_PMA_CLASS_PORT_INFO)))
 			return iboe_process_mad(ibdev, mad_flags, port_num, in_wc,
 						in_grh, in_mad, out_mad);
 
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index bc5536f00b6c..fd97534762b8 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1681,9 +1681,12 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 	}
 
 	if (qp->ibqp.uobject)
-		context->usr_page = cpu_to_be32(to_mucontext(ibqp->uobject->context)->uar.index);
+		context->usr_page = cpu_to_be32(
+			mlx4_to_hw_uar_index(dev->dev,
+					     to_mucontext(ibqp->uobject->context)->uar.index));
 	else
-		context->usr_page = cpu_to_be32(dev->priv_uar.index);
+		context->usr_page = cpu_to_be32(
+			mlx4_to_hw_uar_index(dev->dev, dev->priv_uar.index));
 
 	if (attr_mask & IB_QP_DEST_QPN)
 		context->remote_qpn = cpu_to_be32(attr->dest_qp_num);
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 9116bc3988a6..34cb8e87c7b8 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -270,8 +270,10 @@ static int sq_overhead(enum ib_qp_type qp_type)
 		/* fall through */
 	case IB_QPT_RC:
 		size += sizeof(struct mlx5_wqe_ctrl_seg) +
-			sizeof(struct mlx5_wqe_atomic_seg) +
-			sizeof(struct mlx5_wqe_raddr_seg);
+			max(sizeof(struct mlx5_wqe_atomic_seg) +
+			    sizeof(struct mlx5_wqe_raddr_seg),
+			    sizeof(struct mlx5_wqe_umr_ctrl_seg) +
+			    sizeof(struct mlx5_mkey_seg));
 		break;
 
 	case IB_QPT_XRC_TGT:
@@ -279,9 +281,9 @@ static int sq_overhead(enum ib_qp_type qp_type)
 
 	case IB_QPT_UC:
 		size += sizeof(struct mlx5_wqe_ctrl_seg) +
-			sizeof(struct mlx5_wqe_raddr_seg) +
-			sizeof(struct mlx5_wqe_umr_ctrl_seg) +
-			sizeof(struct mlx5_mkey_seg);
+			max(sizeof(struct mlx5_wqe_raddr_seg),
+			    sizeof(struct mlx5_wqe_umr_ctrl_seg) +
+			    sizeof(struct mlx5_mkey_seg));
 		break;
 
 	case IB_QPT_UD:
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 4659256cd95e..3b2ddd64a371 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -75,7 +75,8 @@ static void mlx5_ib_srq_event(struct mlx5_core_srq *srq, enum mlx5_event type)
 
 static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq,
 			   struct mlx5_create_srq_mbox_in **in,
-			   struct ib_udata *udata, int buf_size, int *inlen)
+			   struct ib_udata *udata, int buf_size, int *inlen,
+			   int is_xrc)
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
 	struct mlx5_ib_create_srq ucmd = {};
@@ -87,13 +88,8 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq,
 	int ncont;
 	u32 offset;
 	u32 uidx = MLX5_IB_DEFAULT_UIDX;
-	int drv_data = udata->inlen - sizeof(struct ib_uverbs_cmd_hdr);
 
-	if (drv_data < 0)
-		return -EINVAL;
-
-	ucmdlen = (drv_data < sizeof(ucmd)) ?
-		  drv_data : sizeof(ucmd);
+	ucmdlen = min(udata->inlen, sizeof(ucmd));
 
 	if (ib_copy_from_udata(&ucmd, udata, ucmdlen)) {
 		mlx5_ib_dbg(dev, "failed copy udata\n");
@@ -103,15 +99,17 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq,
 	if (ucmd.reserved0 || ucmd.reserved1)
 		return -EINVAL;
 
-	if (drv_data > sizeof(ucmd) &&
+	if (udata->inlen > sizeof(ucmd) &&
 	    !ib_is_udata_cleared(udata, sizeof(ucmd),
-				 drv_data - sizeof(ucmd)))
+				 udata->inlen - sizeof(ucmd)))
 		return -EINVAL;
 
-	err = get_srq_user_index(to_mucontext(pd->uobject->context),
-				 &ucmd, udata->inlen, &uidx);
-	if (err)
-		return err;
+	if (is_xrc) {
+		err = get_srq_user_index(to_mucontext(pd->uobject->context),
+					 &ucmd, udata->inlen, &uidx);
+		if (err)
+			return err;
+	}
 
 	srq->wq_sig = !!(ucmd.flags & MLX5_SRQ_FLAG_SIGNATURE);
 
@@ -151,7 +149,8 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq,
 	(*in)->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT;
 	(*in)->ctx.pgoff_cqn = cpu_to_be32(offset << 26);
 
-	if (MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1) {
+	if ((MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1) &&
+	     is_xrc){
 		xsrqc = MLX5_ADDR_OF(create_xrc_srq_in, *in,
 				     xrc_srq_context_entry);
 		MLX5_SET(xrc_srqc, xsrqc, user_index, uidx);
@@ -170,7 +169,7 @@ err_umem:
 
 static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq,
 			     struct mlx5_create_srq_mbox_in **in, int buf_size,
-			     int *inlen)
+			     int *inlen, int is_xrc)
 {
 	int err;
 	int i;
@@ -224,7 +223,8 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq,
 
 	(*in)->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT;
 
-	if (MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1) {
+	if ((MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1) &&
+	     is_xrc){
 		xsrqc = MLX5_ADDR_OF(create_xrc_srq_in, *in,
 				     xrc_srq_context_entry);
 		/* 0xffffff means we ask to work with cqe version 0 */
@@ -302,10 +302,14 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
 		    desc_size, init_attr->attr.max_wr, srq->msrq.max, srq->msrq.max_gs,
 		    srq->msrq.max_avail_gather);
 
+	is_xrc = (init_attr->srq_type == IB_SRQT_XRC);
+
 	if (pd->uobject)
-		err = create_srq_user(pd, srq, &in, udata, buf_size, &inlen);
+		err = create_srq_user(pd, srq, &in, udata, buf_size, &inlen,
+				      is_xrc);
 	else
-		err = create_srq_kernel(dev, srq, &in, buf_size, &inlen);
+		err = create_srq_kernel(dev, srq, &in, buf_size, &inlen,
+					is_xrc);
 
 	if (err) {
 		mlx5_ib_warn(dev, "create srq %s failed, err %d\n",
@@ -313,7 +317,6 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
 		goto err_srq;
 	}
 
-	is_xrc = (init_attr->srq_type == IB_SRQT_XRC);
 	in->ctx.state_log_sz = ilog2(srq->msrq.max);
 	flgs = ((srq->msrq.wqe_shift - 4) | (is_xrc << 5) | (srq->wq_sig << 7)) << 24;
 	xrcdn = 0;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma.h b/drivers/infiniband/hw/ocrdma/ocrdma.h
index 040bb8b5cb15..12503f15fbd6 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma.h
@@ -323,9 +323,6 @@ struct ocrdma_cq {
 			 */
 	u32 max_hw_cqe;
 	bool phase_change;
-	bool deferred_arm, deferred_sol;
-	bool first_arm;
-
 	spinlock_t cq_lock ____cacheline_aligned; /* provide synchronization
 						   * to cq polling
 						   */
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index 573849354cb9..f38743018cb4 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -228,6 +228,11 @@ static int ocrdma_alloc_resources(struct ocrdma_dev *dev)
 
 	ocrdma_alloc_pd_pool(dev);
 
+	if (!ocrdma_alloc_stats_resources(dev)) {
+		pr_err("%s: stats resource allocation failed\n", __func__);
+		goto alloc_err;
+	}
+
 	spin_lock_init(&dev->av_tbl.lock);
 	spin_lock_init(&dev->flush_q_lock);
 	return 0;
@@ -238,6 +243,7 @@ alloc_err:
 
 static void ocrdma_free_resources(struct ocrdma_dev *dev)
 {
+	ocrdma_release_stats_resources(dev);
 	kfree(dev->stag_arr);
 	kfree(dev->qp_tbl);
 	kfree(dev->cq_tbl);
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
index 86c303a620c1..255f774080a4 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
@@ -64,10 +64,11 @@ static int ocrdma_add_stat(char *start, char *pcur,
 	return cpy_len;
 }
 
-static bool ocrdma_alloc_stats_mem(struct ocrdma_dev *dev)
+bool ocrdma_alloc_stats_resources(struct ocrdma_dev *dev)
 {
 	struct stats_mem *mem = &dev->stats_mem;
 
+	mutex_init(&dev->stats_lock);
 	/* Alloc mbox command mem*/
 	mem->size = max_t(u32, sizeof(struct ocrdma_rdma_stats_req),
 			sizeof(struct ocrdma_rdma_stats_resp));
@@ -91,13 +92,14 @@ static bool ocrdma_alloc_stats_mem(struct ocrdma_dev *dev)
 	return true;
 }
 
-static void ocrdma_release_stats_mem(struct ocrdma_dev *dev)
+void ocrdma_release_stats_resources(struct ocrdma_dev *dev)
 {
 	struct stats_mem *mem = &dev->stats_mem;
 
 	if (mem->va)
 		dma_free_coherent(&dev->nic_info.pdev->dev, mem->size,
 				  mem->va, mem->pa);
+	mem->va = NULL;
 	kfree(mem->debugfs_mem);
 }
 
@@ -838,15 +840,9 @@ void ocrdma_add_port_stats(struct ocrdma_dev *dev)
 				&dev->reset_stats, &ocrdma_dbg_ops))
 		goto err;
 
-	/* Now create dma_mem for stats mbx command */
-	if (!ocrdma_alloc_stats_mem(dev))
-		goto err;
-
-	mutex_init(&dev->stats_lock);
 
 	return;
 err:
-	ocrdma_release_stats_mem(dev);
 	debugfs_remove_recursive(dev->dir);
 	dev->dir = NULL;
 }
@@ -855,9 +851,7 @@ void ocrdma_rem_port_stats(struct ocrdma_dev *dev)
 {
 	if (!dev->dir)
 		return;
-	debugfs_remove(dev->dir);
-	mutex_destroy(&dev->stats_lock);
-	ocrdma_release_stats_mem(dev);
+	debugfs_remove_recursive(dev->dir);
 }
 
 void ocrdma_init_debugfs(void)
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.h b/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
index c9e58d04c7b8..bba1fec4f11f 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
@@ -65,6 +65,8 @@ enum OCRDMA_STATS_TYPE {
 
 void ocrdma_rem_debugfs(void);
 void ocrdma_init_debugfs(void);
+bool ocrdma_alloc_stats_resources(struct ocrdma_dev *dev);
+void ocrdma_release_stats_resources(struct ocrdma_dev *dev);
 void ocrdma_rem_port_stats(struct ocrdma_dev *dev);
 void ocrdma_add_port_stats(struct ocrdma_dev *dev);
 int ocrdma_pma_counters(struct ocrdma_dev *dev,
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index d4c687b548d8..12420e4ecf3d 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -125,8 +125,8 @@ int ocrdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr,
 					IB_DEVICE_SYS_IMAGE_GUID |
 					IB_DEVICE_LOCAL_DMA_LKEY |
 					IB_DEVICE_MEM_MGT_EXTENSIONS;
-	attr->max_sge = min(dev->attr.max_send_sge, dev->attr.max_srq_sge);
-	attr->max_sge_rd = 0;
+	attr->max_sge = dev->attr.max_send_sge;
+	attr->max_sge_rd = attr->max_sge;
 	attr->max_cq = dev->attr.max_cq;
 	attr->max_cqe = dev->attr.max_cqe;
 	attr->max_mr = dev->attr.max_mr;
@@ -1094,7 +1094,6 @@ struct ib_cq *ocrdma_create_cq(struct ib_device *ibdev,
 	spin_lock_init(&cq->comp_handler_lock);
 	INIT_LIST_HEAD(&cq->sq_head);
 	INIT_LIST_HEAD(&cq->rq_head);
-	cq->first_arm = true;
 
 	if (ib_ctx) {
 		uctx = get_ocrdma_ucontext(ib_ctx);
@@ -2726,8 +2725,7 @@ static int ocrdma_update_ud_rcqe(struct ib_wc *ibwc, struct ocrdma_cqe *cqe)
 		OCRDMA_CQE_UD_STATUS_MASK) >> OCRDMA_CQE_UD_STATUS_SHIFT;
 	ibwc->src_qp = le32_to_cpu(cqe->flags_status_srcqpn) &
 						OCRDMA_CQE_SRCQP_MASK;
-	ibwc->pkey_index = le32_to_cpu(cqe->ud.rxlen_pkey) &
-						OCRDMA_CQE_PKEY_MASK;
+	ibwc->pkey_index = 0;
 	ibwc->wc_flags = IB_WC_GRH;
 	ibwc->byte_len = (le32_to_cpu(cqe->ud.rxlen_pkey) >>
 					OCRDMA_CQE_UD_XFER_LEN_SHIFT);
@@ -2911,12 +2909,9 @@ expand_cqe:
 	}
 stop_cqe:
 	cq->getp = cur_getp;
-	if (cq->deferred_arm || polled_hw_cqes) {
-		ocrdma_ring_cq_db(dev, cq->id, cq->deferred_arm,
-				  cq->deferred_sol, polled_hw_cqes);
-		cq->deferred_arm = false;
-		cq->deferred_sol = false;
-	}
+
+	if (polled_hw_cqes)
+		ocrdma_ring_cq_db(dev, cq->id, false, false, polled_hw_cqes);
 
 	return i;
 }
@@ -3000,13 +2995,7 @@ int ocrdma_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags cq_flags)
 	if (cq_flags & IB_CQ_SOLICITED)
 		sol_needed = true;
 
-	if (cq->first_arm) {
-		ocrdma_ring_cq_db(dev, cq_id, arm_needed, sol_needed, 0);
-		cq->first_arm = false;
-	}
-
-	cq->deferred_arm = true;
-	cq->deferred_sol = sol_needed;
+	ocrdma_ring_cq_db(dev, cq_id, arm_needed, sol_needed, 0);
 	spin_unlock_irqrestore(&cq->cq_lock, flags);
 
 	return 0;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 5ea0c14070d1..fa9c42ff1fb0 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -245,8 +245,6 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	skb_reset_mac_header(skb);
 	skb_pull(skb, IPOIB_ENCAP_LEN);
 
-	skb->truesize = SKB_TRUESIZE(skb->len);
-
 	++dev->stats.rx_packets;
 	dev->stats.rx_bytes += skb->len;
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 050dfa175d16..25889311b1e9 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -456,7 +456,10 @@ out_locked:
 	return status;
 }
 
-static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
+/*
+ * Caller must hold 'priv->lock'
+ */
+static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ib_sa_multicast *multicast;
@@ -466,6 +469,10 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
 	ib_sa_comp_mask comp_mask;
 	int ret = 0;
 
+	if (!priv->broadcast ||
+	    !test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
+		return -EINVAL;
+
 	ipoib_dbg_mcast(priv, "joining MGID %pI6\n", mcast->mcmember.mgid.raw);
 
 	rec.mgid     = mcast->mcmember.mgid;
@@ -525,20 +532,23 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
 			rec.join_state = 4;
 #endif
 	}
+	spin_unlock_irq(&priv->lock);
 
 	multicast = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port,
 					 &rec, comp_mask, GFP_KERNEL,
 					 ipoib_mcast_join_complete, mcast);
+	spin_lock_irq(&priv->lock);
 	if (IS_ERR(multicast)) {
 		ret = PTR_ERR(multicast);
 		ipoib_warn(priv, "ib_sa_join_multicast failed, status %d\n", ret);
-		spin_lock_irq(&priv->lock);
 		/* Requeue this join task with a backoff delay */
 		__ipoib_mcast_schedule_join_thread(priv, mcast, 1);
 		clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
 		spin_unlock_irq(&priv->lock);
 		complete(&mcast->done);
+		spin_lock_irq(&priv->lock);
 	}
+	return 0;
 }
 
 void ipoib_mcast_join_task(struct work_struct *work)
@@ -620,9 +630,10 @@ void ipoib_mcast_join_task(struct work_struct *work)
 				/* Found the next unjoined group */
 				init_completion(&mcast->done);
 				set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
-				spin_unlock_irq(&priv->lock);
-				ipoib_mcast_join(dev, mcast);
-				spin_lock_irq(&priv->lock);
+				if (ipoib_mcast_join(dev, mcast)) {
+					spin_unlock_irq(&priv->lock);
+					return;
+				}
 			} else if (!delay_until ||
 				 time_before(mcast->delay_until, delay_until))
 				delay_until = mcast->delay_until;
@@ -641,10 +652,9 @@ out:
 	if (mcast) {
 		init_completion(&mcast->done);
 		set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
+		ipoib_mcast_join(dev, mcast);
 	}
 	spin_unlock_irq(&priv->lock);
-	if (mcast)
-		ipoib_mcast_join(dev, mcast);
 }
 
 int ipoib_mcast_start_thread(struct net_device *dev)
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 6727954ab74b..e8a84d12b7ff 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -1207,7 +1207,6 @@ static void xpad_led_disconnect(struct usb_xpad *xpad)
 #else
 static int xpad_led_probe(struct usb_xpad *xpad) { return 0; }
 static void xpad_led_disconnect(struct usb_xpad *xpad) { }
-static void xpad_identify_controller(struct usb_xpad *xpad) { }
 #endif
 
 static int xpad_start_input(struct usb_xpad *xpad)
diff --git a/drivers/input/keyboard/adp5589-keys.c b/drivers/input/keyboard/adp5589-keys.c
index 4d446d5085aa..c01a1d648f9f 100644
--- a/drivers/input/keyboard/adp5589-keys.c
+++ b/drivers/input/keyboard/adp5589-keys.c
@@ -235,7 +235,7 @@ struct adp5589_kpad {
 	unsigned short gpimapsize;
 	unsigned extend_cfg;
 	bool is_adp5585;
-	bool adp5585_support_row5;
+	bool support_row5;
 #ifdef CONFIG_GPIOLIB
 	unsigned char gpiomap[ADP5589_MAXGPIO];
 	bool export_gpio;
@@ -485,7 +485,7 @@ static int adp5589_build_gpiomap(struct adp5589_kpad *kpad,
 	if (kpad->extend_cfg & C4_EXTEND_CFG)
 		pin_used[kpad->var->c4_extend_cfg] = true;
 
-	if (!kpad->adp5585_support_row5)
+	if (!kpad->support_row5)
 		pin_used[5] = true;
 
 	for (i = 0; i < kpad->var->maxgpio; i++)
@@ -884,12 +884,13 @@ static int adp5589_probe(struct i2c_client *client,
 
 	switch (id->driver_data) {
 	case ADP5585_02:
-		kpad->adp5585_support_row5 = true;
+		kpad->support_row5 = true;
 	case ADP5585_01:
 		kpad->is_adp5585 = true;
 		kpad->var = &const_adp5585;
 		break;
 	case ADP5589:
+		kpad->support_row5 = true;
 		kpad->var = &const_adp5589;
 		break;
 	}
diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c
index 378db10001df..4401be225d64 100644
--- a/drivers/input/keyboard/cap11xx.c
+++ b/drivers/input/keyboard/cap11xx.c
@@ -304,8 +304,10 @@ static int cap11xx_init_leds(struct device *dev,
 		led->cdev.brightness = LED_OFF;
 
 		error = of_property_read_u32(child, "reg", &reg);
-		if (error != 0 || reg >= num_leds)
+		if (error != 0 || reg >= num_leds) {
+			of_node_put(child);
 			return -EINVAL;
+		}
 
 		led->reg = reg;
 		led->priv = priv;
@@ -313,8 +315,10 @@ static int cap11xx_init_leds(struct device *dev,
 		INIT_WORK(&led->work, cap11xx_led_work);
 
 		error = devm_led_classdev_register(dev, &led->cdev);
-		if (error)
+		if (error) {
+			of_node_put(child);
 			return error;
+		}
 
 		priv->num_leds++;
 		led++;
diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig
index d6d16fa78281..1f2337abcf2f 100644
--- a/drivers/input/misc/Kconfig
+++ b/drivers/input/misc/Kconfig
@@ -733,7 +733,7 @@ config INPUT_XEN_KBDDEV_FRONTEND
 	  module will be called xen-kbdfront.
 
 config INPUT_SIRFSOC_ONKEY
-	bool "CSR SiRFSoC power on/off/suspend key support"
+	tristate "CSR SiRFSoC power on/off/suspend key support"
 	depends on ARCH_SIRF && OF
 	default y
 	help
diff --git a/drivers/input/misc/sirfsoc-onkey.c b/drivers/input/misc/sirfsoc-onkey.c
index 9d5b89befe6f..ed7237f19539 100644
--- a/drivers/input/misc/sirfsoc-onkey.c
+++ b/drivers/input/misc/sirfsoc-onkey.c
@@ -101,7 +101,7 @@ static void sirfsoc_pwrc_close(struct input_dev *input)
 static const struct of_device_id sirfsoc_pwrc_of_match[] = {
 	{ .compatible = "sirf,prima2-pwrc" },
 	{},
-}
+};
 MODULE_DEVICE_TABLE(of, sirfsoc_pwrc_of_match);
 
 static int sirfsoc_pwrc_probe(struct platform_device *pdev)
diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c
index e272f06258ce..a3f0f5a47490 100644
--- a/drivers/input/mouse/vmmouse.c
+++ b/drivers/input/mouse/vmmouse.c
@@ -458,8 +458,6 @@ int vmmouse_init(struct psmouse *psmouse)
 	priv->abs_dev = abs_dev;
 	psmouse->private = priv;
 
-	input_set_capability(rel_dev, EV_REL, REL_WHEEL);
-
 	/* Set up and register absolute device */
 	snprintf(priv->phys, sizeof(priv->phys), "%s/input1",
 		 psmouse->ps2dev.serio->phys);
@@ -475,10 +473,6 @@ int vmmouse_init(struct psmouse *psmouse)
 	abs_dev->id.version = psmouse->model;
 	abs_dev->dev.parent = &psmouse->ps2dev.serio->dev;
 
-	error = input_register_device(priv->abs_dev);
-	if (error)
-		goto init_fail;
-
 	/* Set absolute device capabilities */
 	input_set_capability(abs_dev, EV_KEY, BTN_LEFT);
 	input_set_capability(abs_dev, EV_KEY, BTN_RIGHT);
@@ -488,6 +482,13 @@ int vmmouse_init(struct psmouse *psmouse)
 	input_set_abs_params(abs_dev, ABS_X, 0, VMMOUSE_MAX_X, 0, 0);
 	input_set_abs_params(abs_dev, ABS_Y, 0, VMMOUSE_MAX_Y, 0, 0);
 
+	error = input_register_device(priv->abs_dev);
+	if (error)
+		goto init_fail;
+
+	/* Add wheel capability to the relative device */
+	input_set_capability(rel_dev, EV_REL, REL_WHEEL);
+
 	psmouse->protocol_handler = vmmouse_process_byte;
 	psmouse->disconnect = vmmouse_disconnect;
 	psmouse->reconnect = vmmouse_reconnect;
diff --git a/drivers/input/serio/serio.c b/drivers/input/serio/serio.c
index 8f828975ab10..1ca7f551e2da 100644
--- a/drivers/input/serio/serio.c
+++ b/drivers/input/serio/serio.c
@@ -134,7 +134,7 @@ static void serio_find_driver(struct serio *serio)
 	int error;
 
 	error = device_attach(&serio->dev);
-	if (error < 0)
+	if (error < 0 && error != -EPROBE_DEFER)
 		dev_warn(&serio->dev,
 			 "device_attach() failed for %s (%s), error: %d\n",
 			 serio->phys, serio->name, error);
diff --git a/drivers/input/touchscreen/colibri-vf50-ts.c b/drivers/input/touchscreen/colibri-vf50-ts.c
index 5d4903a402cc..69828d015d45 100644
--- a/drivers/input/touchscreen/colibri-vf50-ts.c
+++ b/drivers/input/touchscreen/colibri-vf50-ts.c
@@ -21,6 +21,7 @@
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c
index 0b0f8c17f3f7..23fbe382da8b 100644
--- a/drivers/input/touchscreen/edt-ft5x06.c
+++ b/drivers/input/touchscreen/edt-ft5x06.c
@@ -822,16 +822,22 @@ static void edt_ft5x06_ts_get_defaults(struct device *dev,
 	int error;
 
 	error = device_property_read_u32(dev, "threshold", &val);
-	if (!error)
-		reg_addr->reg_threshold = val;
+	if (!error) {
+		edt_ft5x06_register_write(tsdata, reg_addr->reg_threshold, val);
+		tsdata->threshold = val;
+	}
 
 	error = device_property_read_u32(dev, "gain", &val);
-	if (!error)
-		reg_addr->reg_gain = val;
+	if (!error) {
+		edt_ft5x06_register_write(tsdata, reg_addr->reg_gain, val);
+		tsdata->gain = val;
+	}
 
 	error = device_property_read_u32(dev, "offset", &val);
-	if (!error)
-		reg_addr->reg_offset = val;
+	if (!error) {
+		edt_ft5x06_register_write(tsdata, reg_addr->reg_offset, val);
+		tsdata->offset = val;
+	}
 }
 
 static void
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index e5e223938eec..374c129219ef 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -114,6 +114,7 @@ struct kmem_cache *amd_iommu_irq_cache;
 
 static void update_domain(struct protection_domain *domain);
 static int protection_domain_init(struct protection_domain *domain);
+static void detach_device(struct device *dev);
 
 /*
  * For dynamic growth the aperture size is split into ranges of 128MB of
@@ -384,6 +385,9 @@ static void iommu_uninit_device(struct device *dev)
 	if (!dev_data)
 		return;
 
+	if (dev_data->domain)
+		detach_device(dev);
+
 	iommu_device_unlink(amd_iommu_rlookup_table[dev_data->devid]->iommu_dev,
 			    dev);
 
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 013bdfff2d4d..bf4959f4225b 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -228,6 +228,10 @@ static int amd_iommu_enable_interrupts(void);
 static int __init iommu_go_to_state(enum iommu_init_state state);
 static void init_device_table_dma(void);
 
+static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu,
+				    u8 bank, u8 cntr, u8 fxn,
+				    u64 *value, bool is_write);
+
 static inline void update_last_devid(u16 devid)
 {
 	if (devid > amd_iommu_last_bdf)
@@ -1016,6 +1020,34 @@ static void amd_iommu_erratum_746_workaround(struct amd_iommu *iommu)
 }
 
 /*
+ * Family15h Model 30h-3fh (IOMMU Mishandles ATS Write Permission)
+ * Workaround:
+ *     BIOS should enable ATS write permission check by setting
+ *     L2_DEBUG_3[AtsIgnoreIWDis](D0F2xF4_x47[0]) = 1b
+ */
+static void amd_iommu_ats_write_check_workaround(struct amd_iommu *iommu)
+{
+	u32 value;
+
+	if ((boot_cpu_data.x86 != 0x15) ||
+	    (boot_cpu_data.x86_model < 0x30) ||
+	    (boot_cpu_data.x86_model > 0x3f))
+		return;
+
+	/* Test L2_DEBUG_3[AtsIgnoreIWDis] == 1 */
+	value = iommu_read_l2(iommu, 0x47);
+
+	if (value & BIT(0))
+		return;
+
+	/* Set L2_DEBUG_3[AtsIgnoreIWDis] = 1 */
+	iommu_write_l2(iommu, 0x47, value | BIT(0));
+
+	pr_info("AMD-Vi: Applying ATS write check workaround for IOMMU at %s\n",
+		dev_name(&iommu->dev->dev));
+}
+
+/*
  * This function clues the initialization function for one IOMMU
  * together and also allocates the command buffer and programs the
  * hardware. It does NOT enable the IOMMU. This is done afterwards.
@@ -1142,8 +1174,8 @@ static void init_iommu_perf_ctr(struct amd_iommu *iommu)
 	amd_iommu_pc_present = true;
 
 	/* Check if the performance counters can be written to */
-	if ((0 != amd_iommu_pc_get_set_reg_val(0, 0, 0, 0, &val, true)) ||
-	    (0 != amd_iommu_pc_get_set_reg_val(0, 0, 0, 0, &val2, false)) ||
+	if ((0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val, true)) ||
+	    (0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val2, false)) ||
 	    (val != val2)) {
 		pr_err("AMD-Vi: Unable to write to IOMMU perf counter.\n");
 		amd_iommu_pc_present = false;
@@ -1284,6 +1316,7 @@ static int iommu_init_pci(struct amd_iommu *iommu)
 	}
 
 	amd_iommu_erratum_746_workaround(iommu);
+	amd_iommu_ats_write_check_workaround(iommu);
 
 	iommu->iommu_dev = iommu_device_create(&iommu->dev->dev, iommu,
 					       amd_iommu_groups, "ivhd%d",
@@ -2283,22 +2316,15 @@ u8 amd_iommu_pc_get_max_counters(u16 devid)
 }
 EXPORT_SYMBOL(amd_iommu_pc_get_max_counters);
 
-int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
+static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu,
+				    u8 bank, u8 cntr, u8 fxn,
 				    u64 *value, bool is_write)
 {
-	struct amd_iommu *iommu;
 	u32 offset;
 	u32 max_offset_lim;
 
-	/* Make sure the IOMMU PC resource is available */
-	if (!amd_iommu_pc_present)
-		return -ENODEV;
-
-	/* Locate the iommu associated with the device ID */
-	iommu = amd_iommu_rlookup_table[devid];
-
 	/* Check for valid iommu and pc register indexing */
-	if (WARN_ON((iommu == NULL) || (fxn > 0x28) || (fxn & 7)))
+	if (WARN_ON((fxn > 0x28) || (fxn & 7)))
 		return -ENODEV;
 
 	offset = (u32)(((0x40|bank) << 12) | (cntr << 8) | fxn);
@@ -2322,3 +2348,16 @@ int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
 	return 0;
 }
 EXPORT_SYMBOL(amd_iommu_pc_get_set_reg_val);
+
+int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
+				    u64 *value, bool is_write)
+{
+	struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+
+	/* Make sure the IOMMU PC resource is available */
+	if (!amd_iommu_pc_present || iommu == NULL)
+		return -ENODEV;
+
+	return iommu_pc_get_set_reg_val(iommu, bank, cntr, fxn,
+					value, is_write);
+}
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 62a400c5ba06..8ffd7568fc91 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -329,7 +329,8 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb,
 	/* Only care about add/remove events for physical functions */
 	if (pdev->is_virtfn)
 		return NOTIFY_DONE;
-	if (action != BUS_NOTIFY_ADD_DEVICE && action != BUS_NOTIFY_DEL_DEVICE)
+	if (action != BUS_NOTIFY_ADD_DEVICE &&
+	    action != BUS_NOTIFY_REMOVED_DEVICE)
 		return NOTIFY_DONE;
 
 	info = dmar_alloc_pci_notify_info(pdev, action);
@@ -339,7 +340,7 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb,
 	down_write(&dmar_global_lock);
 	if (action == BUS_NOTIFY_ADD_DEVICE)
 		dmar_pci_bus_add_dev(info);
-	else if (action == BUS_NOTIFY_DEL_DEVICE)
+	else if (action == BUS_NOTIFY_REMOVED_DEVICE)
 		dmar_pci_bus_del_dev(info);
 	up_write(&dmar_global_lock);
 
@@ -1353,7 +1354,7 @@ void dmar_disable_qi(struct intel_iommu *iommu)
 
 	raw_spin_lock_irqsave(&iommu->register_lock, flags);
 
-	sts =  dmar_readq(iommu->reg + DMAR_GSTS_REG);
+	sts =  readl(iommu->reg + DMAR_GSTS_REG);
 	if (!(sts & DMA_GSTS_QIES))
 		goto end;
 
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 986a53e3eb96..a2e1b7f14df2 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -4367,7 +4367,7 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
 				rmrru->devices_cnt);
 			if(ret < 0)
 				return ret;
-		} else if (info->event == BUS_NOTIFY_DEL_DEVICE) {
+		} else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) {
 			dmar_remove_dev_scope(info, rmrr->segment,
 				rmrru->devices, rmrru->devices_cnt);
 		}
@@ -4387,7 +4387,7 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
 				break;
 			else if(ret < 0)
 				return ret;
-		} else if (info->event == BUS_NOTIFY_DEL_DEVICE) {
+		} else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) {
 			if (dmar_remove_dev_scope(info, atsr->segment,
 					atsru->devices, atsru->devices_cnt))
 				break;
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index 50464833d0b8..d9939fa9b588 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -249,12 +249,30 @@ static void intel_flush_pasid_dev(struct intel_svm *svm, struct intel_svm_dev *s
 static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 {
 	struct intel_svm *svm = container_of(mn, struct intel_svm, notifier);
+	struct intel_svm_dev *sdev;
 
+	/* This might end up being called from exit_mmap(), *before* the page
+	 * tables are cleared. And __mmu_notifier_release() will delete us from
+	 * the list of notifiers so that our invalidate_range() callback doesn't
+	 * get called when the page tables are cleared. So we need to protect
+	 * against hardware accessing those page tables.
+	 *
+	 * We do it by clearing the entry in the PASID table and then flushing
+	 * the IOTLB and the PASID table caches. This might upset hardware;
+	 * perhaps we'll want to point the PASID to a dummy PGD (like the zero
+	 * page) so that we end up taking a fault that the hardware really
+	 * *has* to handle gracefully without affecting other processes.
+	 */
 	svm->iommu->pasid_table[svm->pasid].val = 0;
+	wmb();
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(sdev, &svm->devs, list) {
+		intel_flush_pasid_dev(svm, sdev, svm->pasid);
+		intel_flush_svm_range_dev(svm, sdev, 0, -1, 0, !svm->mm);
+	}
+	rcu_read_unlock();
 
-	/* There's no need to do any flush because we can't get here if there
-	 * are any devices left anyway. */
-	WARN_ON(!list_empty(&svm->devs));
 }
 
 static const struct mmu_notifier_ops intel_mmuops = {
@@ -379,7 +397,6 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 				goto out;
 			}
 			iommu->pasid_table[svm->pasid].val = (u64)__pa(mm->pgd) | 1;
-			mm = NULL;
 		} else
 			iommu->pasid_table[svm->pasid].val = (u64)__pa(init_mm.pgd) | 1 | (1ULL << 11);
 		wmb();
@@ -442,11 +459,11 @@ int intel_svm_unbind_mm(struct device *dev, int pasid)
 				kfree_rcu(sdev, rcu);
 
 				if (list_empty(&svm->devs)) {
-					mmu_notifier_unregister(&svm->notifier, svm->mm);
 
 					idr_remove(&svm->iommu->pasid_idr, svm->pasid);
 					if (svm->mm)
-						mmput(svm->mm);
+						mmu_notifier_unregister(&svm->notifier, svm->mm);
+
 					/* We mandate that no page faults may be outstanding
 					 * for the PASID when intel_svm_unbind_mm() is called.
 					 * If that is not obeyed, subtle errors will happen.
@@ -507,6 +524,10 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 	struct intel_svm *svm = NULL;
 	int head, tail, handled = 0;
 
+	/* Clear PPR bit before reading head/tail registers, to
+	 * ensure that we get a new interrupt if needed. */
+	writel(DMA_PRS_PPR, iommu->reg + DMAR_PRS_REG);
+
 	tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK;
 	head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK;
 	while (head != tail) {
@@ -551,6 +572,9 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 		 * any faults on kernel addresses. */
 		if (!svm->mm)
 			goto bad_req;
+		/* If the mm is already defunct, don't handle faults. */
+		if (!atomic_inc_not_zero(&svm->mm->mm_users))
+			goto bad_req;
 		down_read(&svm->mm->mmap_sem);
 		vma = find_extend_vma(svm->mm, address);
 		if (!vma || address < vma->vm_start)
@@ -567,6 +591,7 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 		result = QI_RESP_SUCCESS;
 	invalid:
 		up_read(&svm->mm->mmap_sem);
+		mmput(svm->mm);
 	bad_req:
 		/* Accounting for major/minor faults? */
 		rcu_read_lock();
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index c12ba4516df2..ac596928f6b4 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -629,7 +629,7 @@ static void iommu_disable_irq_remapping(struct intel_iommu *iommu)
 
 	raw_spin_lock_irqsave(&iommu->register_lock, flags);
 
-	sts = dmar_readq(iommu->reg + DMAR_GSTS_REG);
+	sts = readl(iommu->reg + DMAR_GSTS_REG);
 	if (!(sts & DMA_GSTS_IRES))
 		goto end;
 
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index fb50911b3940..7e8c441ff2de 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -60,6 +60,17 @@ config ARM_VIC_NR
 	  The maximum number of VICs available in the system, for
 	  power management.
 
+config ARMADA_370_XP_IRQ
+	bool
+	select GENERIC_IRQ_CHIP
+	select PCI_MSI_IRQ_DOMAIN if PCI_MSI
+
+config ALPINE_MSI
+	bool
+	depends on PCI && PCI_MSI
+	select GENERIC_IRQ_CHIP
+	select PCI_MSI_IRQ_DOMAIN
+
 config ATMEL_AIC_IRQ
 	bool
 	select GENERIC_IRQ_CHIP
@@ -78,6 +89,11 @@ config I8259
 	bool
 	select IRQ_DOMAIN
 
+config BCM6345_L1_IRQ
+	bool
+	select GENERIC_IRQ_CHIP
+	select IRQ_DOMAIN
+
 config BCM7038_L1_IRQ
 	bool
 	select GENERIC_IRQ_CHIP
@@ -151,6 +167,11 @@ config ST_IRQCHIP
 	help
 	  Enables SysCfg Controlled IRQs on STi based platforms.
 
+config TANGO_IRQ
+	bool
+	select IRQ_DOMAIN
+	select GENERIC_IRQ_CHIP
+
 config TB10X_IRQC
 	bool
 	select IRQ_DOMAIN
@@ -160,6 +181,7 @@ config TS4800_IRQ
 	tristate "TS-4800 IRQ controller"
 	select IRQ_DOMAIN
 	depends on HAS_IOMEM
+	depends on SOC_IMX51 || COMPILE_TEST
 	help
 	  Support for the TS-4800 FPGA IRQ controller
 
@@ -193,6 +215,8 @@ config KEYSTONE_IRQ
 
 config MIPS_GIC
 	bool
+	select GENERIC_IRQ_IPI
+	select IRQ_DOMAIN_HIERARCHY
 	select MIPS_CM
 
 config INGENIC_IRQ
@@ -218,3 +242,7 @@ config IRQ_MXS
 	def_bool y if MACH_ASM9260 || ARCH_MXS
 	select IRQ_DOMAIN
 	select STMP_DEVICE
+
+config MVEBU_ODMI
+	bool
+	select GENERIC_MSI_IRQ_DOMAIN
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 18caacb60d58..b03cfcbbac6b 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -1,11 +1,13 @@
 obj-$(CONFIG_IRQCHIP)			+= irqchip.o
 
+obj-$(CONFIG_ALPINE_MSI)		+= irq-alpine-msi.o
+obj-$(CONFIG_ATH79)			+= irq-ath79-cpu.o
+obj-$(CONFIG_ATH79)			+= irq-ath79-misc.o
 obj-$(CONFIG_ARCH_BCM2835)		+= irq-bcm2835.o
 obj-$(CONFIG_ARCH_BCM2835)		+= irq-bcm2836.o
 obj-$(CONFIG_ARCH_EXYNOS)		+= exynos-combiner.o
 obj-$(CONFIG_ARCH_HIP04)		+= irq-hip04.o
 obj-$(CONFIG_ARCH_MMP)			+= irq-mmp.o
-obj-$(CONFIG_ARCH_MVEBU)		+= irq-armada-370-xp.o
 obj-$(CONFIG_IRQ_MXS)			+= irq-mxs.o
 obj-$(CONFIG_ARCH_TEGRA)		+= irq-tegra.o
 obj-$(CONFIG_ARCH_S3C24XX)		+= irq-s3c24xx.o
@@ -28,6 +30,7 @@ obj-$(CONFIG_ARM_GIC_V3_ITS)		+= irq-gic-v3-its.o irq-gic-v3-its-pci-msi.o irq-g
 obj-$(CONFIG_HISILICON_IRQ_MBIGEN)	+= irq-mbigen.o
 obj-$(CONFIG_ARM_NVIC)			+= irq-nvic.o
 obj-$(CONFIG_ARM_VIC)			+= irq-vic.o
+obj-$(CONFIG_ARMADA_370_XP_IRQ)		+= irq-armada-370-xp.o
 obj-$(CONFIG_ATMEL_AIC_IRQ)		+= irq-atmel-aic-common.o irq-atmel-aic.o
 obj-$(CONFIG_ATMEL_AIC5_IRQ)	+= irq-atmel-aic-common.o irq-atmel-aic5.o
 obj-$(CONFIG_I8259)			+= irq-i8259.o
@@ -40,12 +43,14 @@ obj-$(CONFIG_VERSATILE_FPGA_IRQ)	+= irq-versatile-fpga.o
 obj-$(CONFIG_ARCH_NSPIRE)		+= irq-zevio.o
 obj-$(CONFIG_ARCH_VT8500)		+= irq-vt8500.o
 obj-$(CONFIG_ST_IRQCHIP)		+= irq-st.o
+obj-$(CONFIG_TANGO_IRQ)			+= irq-tango.o
 obj-$(CONFIG_TB10X_IRQC)		+= irq-tb10x.o
 obj-$(CONFIG_TS4800_IRQ)		+= irq-ts4800.o
 obj-$(CONFIG_XTENSA)			+= irq-xtensa-pic.o
 obj-$(CONFIG_XTENSA_MX)			+= irq-xtensa-mx.o
 obj-$(CONFIG_IRQ_CROSSBAR)		+= irq-crossbar.o
 obj-$(CONFIG_SOC_VF610)			+= irq-vf610-mscm-ir.o
+obj-$(CONFIG_BCM6345_L1_IRQ)		+= irq-bcm6345-l1.o
 obj-$(CONFIG_BCM7038_L1_IRQ)		+= irq-bcm7038-l1.o
 obj-$(CONFIG_BCM7120_L2_IRQ)		+= irq-bcm7120-l2.o
 obj-$(CONFIG_BRCMSTB_L2_IRQ)		+= irq-brcmstb-l2.o
@@ -59,3 +64,4 @@ obj-$(CONFIG_ARCH_SA1100)		+= irq-sa11x0.o
 obj-$(CONFIG_INGENIC_IRQ)		+= irq-ingenic.o
 obj-$(CONFIG_IMX_GPCV2)			+= irq-imx-gpcv2.o
 obj-$(CONFIG_PIC32_EVIC)		+= irq-pic32-evic.o
+obj-$(CONFIG_MVEBU_ODMI)		+= irq-mvebu-odmi.o
diff --git a/drivers/irqchip/irq-alpine-msi.c b/drivers/irqchip/irq-alpine-msi.c
new file mode 100644
index 000000000000..25384255b30f
--- /dev/null
+++ b/drivers/irqchip/irq-alpine-msi.c
@@ -0,0 +1,293 @@
+/*
+ * Annapurna Labs MSIX support services
+ *
+ * Copyright (C) 2016, Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ *
+ * Antoine Tenart <antoine.tenart@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/irqchip.h>
+#include <linux/irqchip/arm-gic.h>
+#include <linux/msi.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_pci.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+
+#include <asm/irq.h>
+#include <asm-generic/msi.h>
+
+/* MSIX message address format: local GIC target */
+#define ALPINE_MSIX_SPI_TARGET_CLUSTER0		BIT(16)
+
+struct alpine_msix_data {
+	spinlock_t msi_map_lock;
+	phys_addr_t addr;
+	u32 spi_first;		/* The SGI number that MSIs start */
+	u32 num_spis;		/* The number of SGIs for MSIs */
+	unsigned long *msi_map;
+};
+
+static void alpine_msix_mask_msi_irq(struct irq_data *d)
+{
+	pci_msi_mask_irq(d);
+	irq_chip_mask_parent(d);
+}
+
+static void alpine_msix_unmask_msi_irq(struct irq_data *d)
+{
+	pci_msi_unmask_irq(d);
+	irq_chip_unmask_parent(d);
+}
+
+static struct irq_chip alpine_msix_irq_chip = {
+	.name			= "MSIx",
+	.irq_mask		= alpine_msix_mask_msi_irq,
+	.irq_unmask		= alpine_msix_unmask_msi_irq,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+};
+
+static int alpine_msix_allocate_sgi(struct alpine_msix_data *priv, int num_req)
+{
+	int first;
+
+	spin_lock(&priv->msi_map_lock);
+
+	first = bitmap_find_next_zero_area(priv->msi_map, priv->num_spis, 0,
+					   num_req, 0);
+	if (first >= priv->num_spis) {
+		spin_unlock(&priv->msi_map_lock);
+		return -ENOSPC;
+	}
+
+	bitmap_set(priv->msi_map, first, num_req);
+
+	spin_unlock(&priv->msi_map_lock);
+
+	return priv->spi_first + first;
+}
+
+static void alpine_msix_free_sgi(struct alpine_msix_data *priv, unsigned sgi,
+				 int num_req)
+{
+	int first = sgi - priv->spi_first;
+
+	spin_lock(&priv->msi_map_lock);
+
+	bitmap_clear(priv->msi_map, first, num_req);
+
+	spin_unlock(&priv->msi_map_lock);
+}
+
+static void alpine_msix_compose_msi_msg(struct irq_data *data,
+					struct msi_msg *msg)
+{
+	struct alpine_msix_data *priv = irq_data_get_irq_chip_data(data);
+	phys_addr_t msg_addr = priv->addr;
+
+	msg_addr |= (data->hwirq << 3);
+
+	msg->address_hi = upper_32_bits(msg_addr);
+	msg->address_lo = lower_32_bits(msg_addr);
+	msg->data = 0;
+}
+
+static struct msi_domain_info alpine_msix_domain_info = {
+	.flags	= MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		  MSI_FLAG_PCI_MSIX,
+	.chip	= &alpine_msix_irq_chip,
+};
+
+static struct irq_chip middle_irq_chip = {
+	.name			= "alpine_msix_middle",
+	.irq_mask		= irq_chip_mask_parent,
+	.irq_unmask		= irq_chip_unmask_parent,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+	.irq_compose_msi_msg	= alpine_msix_compose_msi_msg,
+};
+
+static int alpine_msix_gic_domain_alloc(struct irq_domain *domain,
+					unsigned int virq, int sgi)
+{
+	struct irq_fwspec fwspec;
+	struct irq_data *d;
+	int ret;
+
+	if (!is_of_node(domain->parent->fwnode))
+		return -EINVAL;
+
+	fwspec.fwnode = domain->parent->fwnode;
+	fwspec.param_count = 3;
+	fwspec.param[0] = 0;
+	fwspec.param[1] = sgi;
+	fwspec.param[2] = IRQ_TYPE_EDGE_RISING;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec);
+	if (ret)
+		return ret;
+
+	d = irq_domain_get_irq_data(domain->parent, virq);
+	d->chip->irq_set_type(d, IRQ_TYPE_EDGE_RISING);
+
+	return 0;
+}
+
+static int alpine_msix_middle_domain_alloc(struct irq_domain *domain,
+					   unsigned int virq,
+					   unsigned int nr_irqs, void *args)
+{
+	struct alpine_msix_data *priv = domain->host_data;
+	int sgi, err, i;
+
+	sgi = alpine_msix_allocate_sgi(priv, nr_irqs);
+	if (sgi < 0)
+		return sgi;
+
+	for (i = 0; i < nr_irqs; i++) {
+		err = alpine_msix_gic_domain_alloc(domain, virq + i, sgi + i);
+		if (err)
+			goto err_sgi;
+
+		irq_domain_set_hwirq_and_chip(domain, virq + i, sgi + i,
+					      &middle_irq_chip, priv);
+	}
+
+	return 0;
+
+err_sgi:
+	while (--i >= 0)
+		irq_domain_free_irqs_parent(domain, virq, i);
+	alpine_msix_free_sgi(priv, sgi, nr_irqs);
+	return err;
+}
+
+static void alpine_msix_middle_domain_free(struct irq_domain *domain,
+					   unsigned int virq,
+					   unsigned int nr_irqs)
+{
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	struct alpine_msix_data *priv = irq_data_get_irq_chip_data(d);
+
+	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
+	alpine_msix_free_sgi(priv, d->hwirq, nr_irqs);
+}
+
+static const struct irq_domain_ops alpine_msix_middle_domain_ops = {
+	.alloc	= alpine_msix_middle_domain_alloc,
+	.free	= alpine_msix_middle_domain_free,
+};
+
+static int alpine_msix_init_domains(struct alpine_msix_data *priv,
+				    struct device_node *node)
+{
+	struct irq_domain *middle_domain, *msi_domain, *gic_domain;
+	struct device_node *gic_node;
+
+	gic_node = of_irq_find_parent(node);
+	if (!gic_node) {
+		pr_err("Failed to find the GIC node\n");
+		return -ENODEV;
+	}
+
+	gic_domain = irq_find_host(gic_node);
+	if (!gic_domain) {
+		pr_err("Failed to find the GIC domain\n");
+		return -ENXIO;
+	}
+
+	middle_domain = irq_domain_add_tree(NULL,
+					    &alpine_msix_middle_domain_ops,
+					    priv);
+	if (!middle_domain) {
+		pr_err("Failed to create the MSIX middle domain\n");
+		return -ENOMEM;
+	}
+
+	middle_domain->parent = gic_domain;
+
+	msi_domain = pci_msi_create_irq_domain(of_node_to_fwnode(node),
+					       &alpine_msix_domain_info,
+					       middle_domain);
+	if (!msi_domain) {
+		pr_err("Failed to create MSI domain\n");
+		irq_domain_remove(middle_domain);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int alpine_msix_init(struct device_node *node,
+			    struct device_node *parent)
+{
+	struct alpine_msix_data *priv;
+	struct resource res;
+	int ret;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	spin_lock_init(&priv->msi_map_lock);
+
+	ret = of_address_to_resource(node, 0, &res);
+	if (ret) {
+		pr_err("Failed to allocate resource\n");
+		goto err_priv;
+	}
+
+	/*
+	 * The 20 least significant bits of addr provide direct information
+	 * regarding the interrupt destination.
+	 *
+	 * To select the primary GIC as the target GIC, bits [18:17] must be set
+	 * to 0x0. In this case, bit 16 (SPI_TARGET_CLUSTER0) must be set.
+	 */
+	priv->addr = res.start & GENMASK_ULL(63,20);
+	priv->addr |= ALPINE_MSIX_SPI_TARGET_CLUSTER0;
+
+	if (of_property_read_u32(node, "al,msi-base-spi", &priv->spi_first)) {
+		pr_err("Unable to parse MSI base\n");
+		ret = -EINVAL;
+		goto err_priv;
+	}
+
+	if (of_property_read_u32(node, "al,msi-num-spis", &priv->num_spis)) {
+		pr_err("Unable to parse MSI numbers\n");
+		ret = -EINVAL;
+		goto err_priv;
+	}
+
+	priv->msi_map = kzalloc(sizeof(*priv->msi_map) * BITS_TO_LONGS(priv->num_spis),
+				GFP_KERNEL);
+	if (!priv->msi_map) {
+		ret = -ENOMEM;
+		goto err_priv;
+	}
+
+	pr_debug("Registering %d msixs, starting at %d\n",
+		 priv->num_spis, priv->spi_first);
+
+	ret = alpine_msix_init_domains(priv, node);
+	if (ret)
+		goto err_map;
+
+	return 0;
+
+err_map:
+	kfree(priv->msi_map);
+err_priv:
+	kfree(priv);
+	return ret;
+}
+IRQCHIP_DECLARE(alpine_msix, "al,alpine-msix", alpine_msix_init);
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index 3f3a8c3d2175..e7dc6cbda2a1 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -71,6 +71,7 @@ static u32 doorbell_mask_reg;
 static int parent_irq;
 #ifdef CONFIG_PCI_MSI
 static struct irq_domain *armada_370_xp_msi_domain;
+static struct irq_domain *armada_370_xp_msi_inner_domain;
 static DECLARE_BITMAP(msi_used, PCI_MSI_DOORBELL_NR);
 static DEFINE_MUTEX(msi_used_lock);
 static phys_addr_t msi_doorbell_addr;
@@ -115,127 +116,102 @@ static void armada_370_xp_irq_unmask(struct irq_data *d)
 
 #ifdef CONFIG_PCI_MSI
 
-static int armada_370_xp_alloc_msi(void)
-{
-	int hwirq;
+static struct irq_chip armada_370_xp_msi_irq_chip = {
+	.name = "MPIC MSI",
+	.irq_mask = pci_msi_mask_irq,
+	.irq_unmask = pci_msi_unmask_irq,
+};
 
-	mutex_lock(&msi_used_lock);
-	hwirq = find_first_zero_bit(&msi_used, PCI_MSI_DOORBELL_NR);
-	if (hwirq >= PCI_MSI_DOORBELL_NR)
-		hwirq = -ENOSPC;
-	else
-		set_bit(hwirq, msi_used);
-	mutex_unlock(&msi_used_lock);
+static struct msi_domain_info armada_370_xp_msi_domain_info = {
+	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		   MSI_FLAG_MULTI_PCI_MSI),
+	.chip	= &armada_370_xp_msi_irq_chip,
+};
 
-	return hwirq;
+static void armada_370_xp_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	msg->address_lo = lower_32_bits(msi_doorbell_addr);
+	msg->address_hi = upper_32_bits(msi_doorbell_addr);
+	msg->data = 0xf00 | (data->hwirq + PCI_MSI_DOORBELL_START);
 }
 
-static void armada_370_xp_free_msi(int hwirq)
+static int armada_370_xp_msi_set_affinity(struct irq_data *irq_data,
+					  const struct cpumask *mask, bool force)
 {
-	mutex_lock(&msi_used_lock);
-	if (!test_bit(hwirq, msi_used))
-		pr_err("trying to free unused MSI#%d\n", hwirq);
-	else
-		clear_bit(hwirq, msi_used);
-	mutex_unlock(&msi_used_lock);
+	 return -EINVAL;
 }
 
-static int armada_370_xp_setup_msi_irq(struct msi_controller *chip,
-				       struct pci_dev *pdev,
-				       struct msi_desc *desc)
-{
-	struct msi_msg msg;
-	int virq, hwirq;
+static struct irq_chip armada_370_xp_msi_bottom_irq_chip = {
+	.name			= "MPIC MSI",
+	.irq_compose_msi_msg	= armada_370_xp_compose_msi_msg,
+	.irq_set_affinity	= armada_370_xp_msi_set_affinity,
+};
 
-	/* We support MSI, but not MSI-X */
-	if (desc->msi_attrib.is_msix)
-		return -EINVAL;
+static int armada_370_xp_msi_alloc(struct irq_domain *domain, unsigned int virq,
+				   unsigned int nr_irqs, void *args)
+{
+	int hwirq, i;
 
-	hwirq = armada_370_xp_alloc_msi();
-	if (hwirq < 0)
-		return hwirq;
+	mutex_lock(&msi_used_lock);
 
-	virq = irq_create_mapping(armada_370_xp_msi_domain, hwirq);
-	if (!virq) {
-		armada_370_xp_free_msi(hwirq);
-		return -EINVAL;
+	hwirq = bitmap_find_next_zero_area(msi_used, PCI_MSI_DOORBELL_NR,
+					   0, nr_irqs, 0);
+	if (hwirq >= PCI_MSI_DOORBELL_NR) {
+		mutex_unlock(&msi_used_lock);
+		return -ENOSPC;
 	}
 
-	irq_set_msi_desc(virq, desc);
-
-	msg.address_lo = msi_doorbell_addr;
-	msg.address_hi = 0;
-	msg.data = 0xf00 | (hwirq + 16);
-
-	pci_write_msi_msg(virq, &msg);
-	return 0;
-}
+	bitmap_set(msi_used, hwirq, nr_irqs);
+	mutex_unlock(&msi_used_lock);
 
-static void armada_370_xp_teardown_msi_irq(struct msi_controller *chip,
-					   unsigned int irq)
-{
-	struct irq_data *d = irq_get_irq_data(irq);
-	unsigned long hwirq = d->hwirq;
+	for (i = 0; i < nr_irqs; i++) {
+		irq_domain_set_info(domain, virq + i, hwirq + i,
+				    &armada_370_xp_msi_bottom_irq_chip,
+				    domain->host_data, handle_simple_irq,
+				    NULL, NULL);
+	}
 
-	irq_dispose_mapping(irq);
-	armada_370_xp_free_msi(hwirq);
+	return hwirq;
 }
 
-static struct irq_chip armada_370_xp_msi_irq_chip = {
-	.name = "armada_370_xp_msi_irq",
-	.irq_enable = pci_msi_unmask_irq,
-	.irq_disable = pci_msi_mask_irq,
-	.irq_mask = pci_msi_mask_irq,
-	.irq_unmask = pci_msi_unmask_irq,
-};
-
-static int armada_370_xp_msi_map(struct irq_domain *domain, unsigned int virq,
-				 irq_hw_number_t hw)
+static void armada_370_xp_msi_free(struct irq_domain *domain,
+				   unsigned int virq, unsigned int nr_irqs)
 {
-	irq_set_chip_and_handler(virq, &armada_370_xp_msi_irq_chip,
-				 handle_simple_irq);
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
 
-	return 0;
+	mutex_lock(&msi_used_lock);
+	bitmap_clear(msi_used, d->hwirq, nr_irqs);
+	mutex_unlock(&msi_used_lock);
 }
 
-static const struct irq_domain_ops armada_370_xp_msi_irq_ops = {
-	.map = armada_370_xp_msi_map,
+static const struct irq_domain_ops armada_370_xp_msi_domain_ops = {
+	.alloc	= armada_370_xp_msi_alloc,
+	.free	= armada_370_xp_msi_free,
 };
 
 static int armada_370_xp_msi_init(struct device_node *node,
 				  phys_addr_t main_int_phys_base)
 {
-	struct msi_controller *msi_chip;
 	u32 reg;
-	int ret;
 
 	msi_doorbell_addr = main_int_phys_base +
 		ARMADA_370_XP_SW_TRIG_INT_OFFS;
 
-	msi_chip = kzalloc(sizeof(*msi_chip), GFP_KERNEL);
-	if (!msi_chip)
+	armada_370_xp_msi_inner_domain =
+		irq_domain_add_linear(NULL, PCI_MSI_DOORBELL_NR,
+				      &armada_370_xp_msi_domain_ops, NULL);
+	if (!armada_370_xp_msi_inner_domain)
 		return -ENOMEM;
 
-	msi_chip->setup_irq = armada_370_xp_setup_msi_irq;
-	msi_chip->teardown_irq = armada_370_xp_teardown_msi_irq;
-	msi_chip->of_node = node;
-
 	armada_370_xp_msi_domain =
-		irq_domain_add_linear(NULL, PCI_MSI_DOORBELL_NR,
-				      &armada_370_xp_msi_irq_ops,
-				      NULL);
+		pci_msi_create_irq_domain(of_node_to_fwnode(node),
+					  &armada_370_xp_msi_domain_info,
+					  armada_370_xp_msi_inner_domain);
 	if (!armada_370_xp_msi_domain) {
-		kfree(msi_chip);
+		irq_domain_remove(armada_370_xp_msi_inner_domain);
 		return -ENOMEM;
 	}
 
-	ret = of_pci_msi_chip_add(msi_chip);
-	if (ret < 0) {
-		irq_domain_remove(armada_370_xp_msi_domain);
-		kfree(msi_chip);
-		return ret;
-	}
-
 	reg = readl(per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS)
 		| PCI_MSI_DOORBELL_MASK;
 
@@ -280,7 +256,7 @@ static int armada_xp_set_affinity(struct irq_data *d,
 #endif
 
 static struct irq_chip armada_370_xp_irq_chip = {
-	.name		= "armada_370_xp_irq",
+	.name		= "MPIC",
 	.irq_mask       = armada_370_xp_irq_mask,
 	.irq_mask_ack   = armada_370_xp_irq_mask,
 	.irq_unmask     = armada_370_xp_irq_unmask,
@@ -427,12 +403,12 @@ static void armada_370_xp_handle_msi_irq(struct pt_regs *regs, bool is_chained)
 			continue;
 
 		if (is_chained) {
-			irq = irq_find_mapping(armada_370_xp_msi_domain,
-					       msinr - 16);
+			irq = irq_find_mapping(armada_370_xp_msi_inner_domain,
+					       msinr - PCI_MSI_DOORBELL_START);
 			generic_handle_irq(irq);
 		} else {
-			irq = msinr - 16;
-			handle_domain_irq(armada_370_xp_msi_domain,
+			irq = msinr - PCI_MSI_DOORBELL_START;
+			handle_domain_irq(armada_370_xp_msi_inner_domain,
 					  irq, regs);
 		}
 	}
@@ -604,8 +580,8 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 	armada_370_xp_mpic_domain =
 		irq_domain_add_linear(node, nr_irqs,
 				&armada_370_xp_mpic_irq_ops, NULL);
-
 	BUG_ON(!armada_370_xp_mpic_domain);
+	armada_370_xp_mpic_domain->bus_token = DOMAIN_BUS_WIRED;
 
 	/* Setup for the boot CPU */
 	armada_xp_mpic_perf_init();
diff --git a/drivers/irqchip/irq-ath79-cpu.c b/drivers/irqchip/irq-ath79-cpu.c
new file mode 100644
index 000000000000..befe93c5a51a
--- /dev/null
+++ b/drivers/irqchip/irq-ath79-cpu.c
@@ -0,0 +1,97 @@
+/*
+ *  Atheros AR71xx/AR724x/AR913x specific interrupt handling
+ *
+ *  Copyright (C) 2015 Alban Bedel <albeu@free.fr>
+ *  Copyright (C) 2010-2011 Jaiganesh Narayanan <jnarayanan@atheros.com>
+ *  Copyright (C) 2008-2011 Gabor Juhos <juhosg@openwrt.org>
+ *  Copyright (C) 2008 Imre Kaloz <kaloz@openwrt.org>
+ *
+ *  Parts of this file are based on Atheros' 2.6.15/2.6.31 BSP
+ *
+ *  This program is free software; you can redistribute it and/or modify it
+ *  under the terms of the GNU General Public License version 2 as published
+ *  by the Free Software Foundation.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/irqchip.h>
+#include <linux/of.h>
+
+#include <asm/irq_cpu.h>
+#include <asm/mach-ath79/ath79.h>
+
+/*
+ * The IP2/IP3 lines are tied to a PCI/WMAC/USB device. Drivers for
+ * these devices typically allocate coherent DMA memory, however the
+ * DMA controller may still have some unsynchronized data in the FIFO.
+ * Issue a flush in the handlers to ensure that the driver sees
+ * the update.
+ *
+ * This array map the interrupt lines to the DDR write buffer channels.
+ */
+
+static unsigned irq_wb_chan[8] = {
+	-1, -1, -1, -1, -1, -1, -1, -1,
+};
+
+asmlinkage void plat_irq_dispatch(void)
+{
+	unsigned long pending;
+	int irq;
+
+	pending = read_c0_status() & read_c0_cause() & ST0_IM;
+
+	if (!pending) {
+		spurious_interrupt();
+		return;
+	}
+
+	pending >>= CAUSEB_IP;
+	while (pending) {
+		irq = fls(pending) - 1;
+		if (irq < ARRAY_SIZE(irq_wb_chan) && irq_wb_chan[irq] != -1)
+			ath79_ddr_wb_flush(irq_wb_chan[irq]);
+		do_IRQ(MIPS_CPU_IRQ_BASE + irq);
+		pending &= ~BIT(irq);
+	}
+}
+
+static int __init ar79_cpu_intc_of_init(
+	struct device_node *node, struct device_node *parent)
+{
+	int err, i, count;
+
+	/* Fill the irq_wb_chan table */
+	count = of_count_phandle_with_args(
+		node, "qca,ddr-wb-channels", "#qca,ddr-wb-channel-cells");
+
+	for (i = 0; i < count; i++) {
+		struct of_phandle_args args;
+		u32 irq = i;
+
+		of_property_read_u32_index(
+			node, "qca,ddr-wb-channel-interrupts", i, &irq);
+		if (irq >= ARRAY_SIZE(irq_wb_chan))
+			continue;
+
+		err = of_parse_phandle_with_args(
+			node, "qca,ddr-wb-channels",
+			"#qca,ddr-wb-channel-cells",
+			i, &args);
+		if (err)
+			return err;
+
+		irq_wb_chan[irq] = args.args[0];
+	}
+
+	return mips_cpu_irq_of_init(node, parent);
+}
+IRQCHIP_DECLARE(ar79_cpu_intc, "qca,ar7100-cpu-intc",
+		ar79_cpu_intc_of_init);
+
+void __init ath79_cpu_irq_init(unsigned irq_wb_chan2, unsigned irq_wb_chan3)
+{
+	irq_wb_chan[2] = irq_wb_chan2;
+	irq_wb_chan[3] = irq_wb_chan3;
+	mips_cpu_irq_init();
+}
diff --git a/drivers/irqchip/irq-ath79-misc.c b/drivers/irqchip/irq-ath79-misc.c
new file mode 100644
index 000000000000..aa7290784636
--- /dev/null
+++ b/drivers/irqchip/irq-ath79-misc.c
@@ -0,0 +1,189 @@
+/*
+ *  Atheros AR71xx/AR724x/AR913x MISC interrupt controller
+ *
+ *  Copyright (C) 2015 Alban Bedel <albeu@free.fr>
+ *  Copyright (C) 2010-2011 Jaiganesh Narayanan <jnarayanan@atheros.com>
+ *  Copyright (C) 2008-2011 Gabor Juhos <juhosg@openwrt.org>
+ *  Copyright (C) 2008 Imre Kaloz <kaloz@openwrt.org>
+ *
+ *  Parts of this file are based on Atheros' 2.6.15/2.6.31 BSP
+ *
+ *  This program is free software; you can redistribute it and/or modify it
+ *  under the terms of the GNU General Public License version 2 as published
+ *  by the Free Software Foundation.
+ */
+
+#include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#define AR71XX_RESET_REG_MISC_INT_STATUS	0
+#define AR71XX_RESET_REG_MISC_INT_ENABLE	4
+
+#define ATH79_MISC_IRQ_COUNT			32
+
+static void ath79_misc_irq_handler(struct irq_desc *desc)
+{
+	struct irq_domain *domain = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	void __iomem *base = domain->host_data;
+	u32 pending;
+
+	chained_irq_enter(chip, desc);
+
+	pending = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_STATUS) &
+		  __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE);
+
+	if (!pending) {
+		spurious_interrupt();
+		chained_irq_exit(chip, desc);
+		return;
+	}
+
+	while (pending) {
+		int bit = __ffs(pending);
+
+		generic_handle_irq(irq_linear_revmap(domain, bit));
+		pending &= ~BIT(bit);
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static void ar71xx_misc_irq_unmask(struct irq_data *d)
+{
+	void __iomem *base = irq_data_get_irq_chip_data(d);
+	unsigned int irq = d->hwirq;
+	u32 t;
+
+	t = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE);
+	__raw_writel(t | BIT(irq), base + AR71XX_RESET_REG_MISC_INT_ENABLE);
+
+	/* flush write */
+	__raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE);
+}
+
+static void ar71xx_misc_irq_mask(struct irq_data *d)
+{
+	void __iomem *base = irq_data_get_irq_chip_data(d);
+	unsigned int irq = d->hwirq;
+	u32 t;
+
+	t = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE);
+	__raw_writel(t & ~BIT(irq), base + AR71XX_RESET_REG_MISC_INT_ENABLE);
+
+	/* flush write */
+	__raw_readl(base + AR71XX_RESET_REG_MISC_INT_ENABLE);
+}
+
+static void ar724x_misc_irq_ack(struct irq_data *d)
+{
+	void __iomem *base = irq_data_get_irq_chip_data(d);
+	unsigned int irq = d->hwirq;
+	u32 t;
+
+	t = __raw_readl(base + AR71XX_RESET_REG_MISC_INT_STATUS);
+	__raw_writel(t & ~BIT(irq), base + AR71XX_RESET_REG_MISC_INT_STATUS);
+
+	/* flush write */
+	__raw_readl(base + AR71XX_RESET_REG_MISC_INT_STATUS);
+}
+
+static struct irq_chip ath79_misc_irq_chip = {
+	.name		= "MISC",
+	.irq_unmask	= ar71xx_misc_irq_unmask,
+	.irq_mask	= ar71xx_misc_irq_mask,
+};
+
+static int misc_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw)
+{
+	irq_set_chip_and_handler(irq, &ath79_misc_irq_chip, handle_level_irq);
+	irq_set_chip_data(irq, d->host_data);
+	return 0;
+}
+
+static const struct irq_domain_ops misc_irq_domain_ops = {
+	.xlate = irq_domain_xlate_onecell,
+	.map = misc_map,
+};
+
+static void __init ath79_misc_intc_domain_init(
+	struct irq_domain *domain, int irq)
+{
+	void __iomem *base = domain->host_data;
+
+	/* Disable and clear all interrupts */
+	__raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_ENABLE);
+	__raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_STATUS);
+
+	irq_set_chained_handler_and_data(irq, ath79_misc_irq_handler, domain);
+}
+
+static int __init ath79_misc_intc_of_init(
+	struct device_node *node, struct device_node *parent)
+{
+	struct irq_domain *domain;
+	void __iomem *base;
+	int irq;
+
+	irq = irq_of_parse_and_map(node, 0);
+	if (!irq) {
+		pr_err("Failed to get MISC IRQ\n");
+		return -EINVAL;
+	}
+
+	base = of_iomap(node, 0);
+	if (!base) {
+		pr_err("Failed to get MISC IRQ registers\n");
+		return -ENOMEM;
+	}
+
+	domain = irq_domain_add_linear(node, ATH79_MISC_IRQ_COUNT,
+				&misc_irq_domain_ops, base);
+	if (!domain) {
+		pr_err("Failed to add MISC irqdomain\n");
+		return -EINVAL;
+	}
+
+	ath79_misc_intc_domain_init(domain, irq);
+	return 0;
+}
+
+static int __init ar7100_misc_intc_of_init(
+	struct device_node *node, struct device_node *parent)
+{
+	ath79_misc_irq_chip.irq_mask_ack = ar71xx_misc_irq_mask;
+	return ath79_misc_intc_of_init(node, parent);
+}
+
+IRQCHIP_DECLARE(ar7100_misc_intc, "qca,ar7100-misc-intc",
+		ar7100_misc_intc_of_init);
+
+static int __init ar7240_misc_intc_of_init(
+	struct device_node *node, struct device_node *parent)
+{
+	ath79_misc_irq_chip.irq_ack = ar724x_misc_irq_ack;
+	return ath79_misc_intc_of_init(node, parent);
+}
+
+IRQCHIP_DECLARE(ar7240_misc_intc, "qca,ar7240-misc-intc",
+		ar7240_misc_intc_of_init);
+
+void __init ath79_misc_irq_init(void __iomem *regs, int irq,
+				int irq_base, bool is_ar71xx)
+{
+	struct irq_domain *domain;
+
+	if (is_ar71xx)
+		ath79_misc_irq_chip.irq_mask_ack = ar71xx_misc_irq_mask;
+	else
+		ath79_misc_irq_chip.irq_ack = ar724x_misc_irq_ack;
+
+	domain = irq_domain_add_legacy(NULL, ATH79_MISC_IRQ_COUNT,
+			irq_base, 0, &misc_irq_domain_ops, regs);
+	if (!domain)
+		panic("Failed to create MISC irqdomain");
+
+	ath79_misc_intc_domain_init(domain, irq);
+}
diff --git a/drivers/irqchip/irq-atmel-aic-common.c b/drivers/irqchip/irq-atmel-aic-common.c
index 37199b9b2cfa..28b26c80f4cf 100644
--- a/drivers/irqchip/irq-atmel-aic-common.c
+++ b/drivers/irqchip/irq-atmel-aic-common.c
@@ -80,16 +80,10 @@ int aic_common_set_type(struct irq_data *d, unsigned type, unsigned *val)
 	return 0;
 }
 
-int aic_common_set_priority(int priority, unsigned *val)
+void aic_common_set_priority(int priority, unsigned *val)
 {
-	if (priority < AT91_AIC_IRQ_MIN_PRIORITY ||
-	    priority > AT91_AIC_IRQ_MAX_PRIORITY)
-		return -EINVAL;
-
 	*val &= ~AT91_AIC_PRIOR;
 	*val |= priority;
-
-	return 0;
 }
 
 int aic_common_irq_domain_xlate(struct irq_domain *d,
@@ -193,7 +187,7 @@ void __init aic_common_rtt_irq_fixup(struct device_node *root)
 	}
 }
 
-void __init aic_common_irq_fixup(const struct of_device_id *matches)
+static void __init aic_common_irq_fixup(const struct of_device_id *matches)
 {
 	struct device_node *root = of_find_node_by_path("/");
 	const struct of_device_id *match;
@@ -214,7 +208,8 @@ void __init aic_common_irq_fixup(const struct of_device_id *matches)
 
 struct irq_domain *__init aic_common_of_init(struct device_node *node,
 					     const struct irq_domain_ops *ops,
-					     const char *name, int nirqs)
+					     const char *name, int nirqs,
+					     const struct of_device_id *matches)
 {
 	struct irq_chip_generic *gc;
 	struct irq_domain *domain;
@@ -264,6 +259,7 @@ struct irq_domain *__init aic_common_of_init(struct device_node *node,
 	}
 
 	aic_common_ext_irq_of_init(domain);
+	aic_common_irq_fixup(matches);
 
 	return domain;
 
diff --git a/drivers/irqchip/irq-atmel-aic-common.h b/drivers/irqchip/irq-atmel-aic-common.h
index 603f0a9d5411..af60376d50de 100644
--- a/drivers/irqchip/irq-atmel-aic-common.h
+++ b/drivers/irqchip/irq-atmel-aic-common.h
@@ -19,7 +19,7 @@
 
 int aic_common_set_type(struct irq_data *d, unsigned type, unsigned *val);
 
-int aic_common_set_priority(int priority, unsigned *val);
+void aic_common_set_priority(int priority, unsigned *val);
 
 int aic_common_irq_domain_xlate(struct irq_domain *d,
 				struct device_node *ctrlr,
@@ -30,12 +30,11 @@ int aic_common_irq_domain_xlate(struct irq_domain *d,
 
 struct irq_domain *__init aic_common_of_init(struct device_node *node,
 					     const struct irq_domain_ops *ops,
-					     const char *name, int nirqs);
+					     const char *name, int nirqs,
+					     const struct of_device_id *matches);
 
 void __init aic_common_rtc_irq_fixup(struct device_node *root);
 
 void __init aic_common_rtt_irq_fixup(struct device_node *root);
 
-void __init aic_common_irq_fixup(const struct of_device_id *matches);
-
 #endif /* __IRQ_ATMEL_AIC_COMMON_H */
diff --git a/drivers/irqchip/irq-atmel-aic.c b/drivers/irqchip/irq-atmel-aic.c
index 8a0c7f288198..112e17c2768b 100644
--- a/drivers/irqchip/irq-atmel-aic.c
+++ b/drivers/irqchip/irq-atmel-aic.c
@@ -196,9 +196,8 @@ static int aic_irq_domain_xlate(struct irq_domain *d,
 
 	irq_gc_lock(gc);
 	smr = irq_reg_readl(gc, AT91_AIC_SMR(*out_hwirq));
-	ret = aic_common_set_priority(intspec[2], &smr);
-	if (!ret)
-		irq_reg_writel(gc, smr, AT91_AIC_SMR(*out_hwirq));
+	aic_common_set_priority(intspec[2], &smr);
+	irq_reg_writel(gc, smr, AT91_AIC_SMR(*out_hwirq));
 	irq_gc_unlock(gc);
 
 	return ret;
@@ -248,12 +247,10 @@ static int __init aic_of_init(struct device_node *node,
 		return -EEXIST;
 
 	domain = aic_common_of_init(node, &aic_irq_ops, "atmel-aic",
-				    NR_AIC_IRQS);
+				    NR_AIC_IRQS, aic_irq_fixups);
 	if (IS_ERR(domain))
 		return PTR_ERR(domain);
 
-	aic_common_irq_fixup(aic_irq_fixups);
-
 	aic_domain = domain;
 	gc = irq_get_domain_generic_chip(domain, 0);
 
diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c
index 62bb840c613f..4f0d068e1abe 100644
--- a/drivers/irqchip/irq-atmel-aic5.c
+++ b/drivers/irqchip/irq-atmel-aic5.c
@@ -272,9 +272,8 @@ static int aic5_irq_domain_xlate(struct irq_domain *d,
 	irq_gc_lock(bgc);
 	irq_reg_writel(bgc, *out_hwirq, AT91_AIC5_SSR);
 	smr = irq_reg_readl(bgc, AT91_AIC5_SMR);
-	ret = aic_common_set_priority(intspec[2], &smr);
-	if (!ret)
-		irq_reg_writel(bgc, intspec[2] | smr, AT91_AIC5_SMR);
+	aic_common_set_priority(intspec[2], &smr);
+	irq_reg_writel(bgc, smr, AT91_AIC5_SMR);
 	irq_gc_unlock(bgc);
 
 	return ret;
@@ -312,12 +311,10 @@ static int __init aic5_of_init(struct device_node *node,
 		return -EEXIST;
 
 	domain = aic_common_of_init(node, &aic5_irq_ops, "atmel-aic5",
-				    nirqs);
+				    nirqs, aic5_irq_fixups);
 	if (IS_ERR(domain))
 		return PTR_ERR(domain);
 
-	aic_common_irq_fixup(aic5_irq_fixups);
-
 	aic5_domain = domain;
 	nchips = aic5_domain->revmap_size / 32;
 	for (i = 0; i < nchips; i++) {
diff --git a/drivers/irqchip/irq-bcm2836.c b/drivers/irqchip/irq-bcm2836.c
index 963065a0d774..b6e950d4782a 100644
--- a/drivers/irqchip/irq-bcm2836.c
+++ b/drivers/irqchip/irq-bcm2836.c
@@ -229,7 +229,6 @@ int __init bcm2836_smp_boot_secondary(unsigned int cpu,
 	unsigned long secondary_startup_phys =
 		(unsigned long)virt_to_phys((void *)secondary_startup);
 
-	dsb();
 	writel(secondary_startup_phys,
 	       intc.base + LOCAL_MAILBOX3_SET0 + 16 * cpu);
 
diff --git a/drivers/irqchip/irq-bcm6345-l1.c b/drivers/irqchip/irq-bcm6345-l1.c
new file mode 100644
index 000000000000..b844c89a9506
--- /dev/null
+++ b/drivers/irqchip/irq-bcm6345-l1.c
@@ -0,0 +1,364 @@
+/*
+ * Broadcom BCM6345 style Level 1 interrupt controller driver
+ *
+ * Copyright (C) 2014 Broadcom Corporation
+ * Copyright 2015 Simon Arlott
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This is based on the BCM7038 (which supports SMP) but with a single
+ * enable register instead of separate mask/set/clear registers.
+ *
+ * The BCM3380 has a similar mask/status register layout, but each pair
+ * of words is at separate locations (and SMP is not supported).
+ *
+ * ENABLE/STATUS words are packed next to each other for each CPU:
+ *
+ * BCM6368:
+ *   0x1000_0020: CPU0_W0_ENABLE
+ *   0x1000_0024: CPU0_W1_ENABLE
+ *   0x1000_0028: CPU0_W0_STATUS		IRQs 31-63
+ *   0x1000_002c: CPU0_W1_STATUS		IRQs 0-31
+ *   0x1000_0030: CPU1_W0_ENABLE
+ *   0x1000_0034: CPU1_W1_ENABLE
+ *   0x1000_0038: CPU1_W0_STATUS		IRQs 31-63
+ *   0x1000_003c: CPU1_W1_STATUS		IRQs 0-31
+ *
+ * BCM63168:
+ *   0x1000_0020: CPU0_W0_ENABLE
+ *   0x1000_0024: CPU0_W1_ENABLE
+ *   0x1000_0028: CPU0_W2_ENABLE
+ *   0x1000_002c: CPU0_W3_ENABLE
+ *   0x1000_0030: CPU0_W0_STATUS	IRQs 96-127
+ *   0x1000_0034: CPU0_W1_STATUS	IRQs 64-95
+ *   0x1000_0038: CPU0_W2_STATUS	IRQs 32-63
+ *   0x1000_003c: CPU0_W3_STATUS	IRQs 0-31
+ *   0x1000_0040: CPU1_W0_ENABLE
+ *   0x1000_0044: CPU1_W1_ENABLE
+ *   0x1000_0048: CPU1_W2_ENABLE
+ *   0x1000_004c: CPU1_W3_ENABLE
+ *   0x1000_0050: CPU1_W0_STATUS	IRQs 96-127
+ *   0x1000_0054: CPU1_W1_STATUS	IRQs 64-95
+ *   0x1000_0058: CPU1_W2_STATUS	IRQs 32-63
+ *   0x1000_005c: CPU1_W3_STATUS	IRQs 0-31
+ *
+ * IRQs are numbered in CPU native endian order
+ * (which is big-endian in these examples)
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME	": " fmt
+
+#include <linux/bitops.h>
+#include <linux/cpumask.h>
+#include <linux/kconfig.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/types.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
+
+#define IRQS_PER_WORD		32
+#define REG_BYTES_PER_IRQ_WORD	(sizeof(u32) * 2)
+
+struct bcm6345_l1_cpu;
+
+struct bcm6345_l1_chip {
+	raw_spinlock_t		lock;
+	unsigned int		n_words;
+	struct irq_domain	*domain;
+	struct cpumask		cpumask;
+	struct bcm6345_l1_cpu	*cpus[NR_CPUS];
+};
+
+struct bcm6345_l1_cpu {
+	void __iomem		*map_base;
+	unsigned int		parent_irq;
+	u32			enable_cache[];
+};
+
+static inline unsigned int reg_enable(struct bcm6345_l1_chip *intc,
+					   unsigned int word)
+{
+#ifdef __BIG_ENDIAN
+	return (1 * intc->n_words - word - 1) * sizeof(u32);
+#else
+	return (0 * intc->n_words + word) * sizeof(u32);
+#endif
+}
+
+static inline unsigned int reg_status(struct bcm6345_l1_chip *intc,
+				      unsigned int word)
+{
+#ifdef __BIG_ENDIAN
+	return (2 * intc->n_words - word - 1) * sizeof(u32);
+#else
+	return (1 * intc->n_words + word) * sizeof(u32);
+#endif
+}
+
+static inline unsigned int cpu_for_irq(struct bcm6345_l1_chip *intc,
+					struct irq_data *d)
+{
+	return cpumask_first_and(&intc->cpumask, irq_data_get_affinity_mask(d));
+}
+
+static void bcm6345_l1_irq_handle(struct irq_desc *desc)
+{
+	struct bcm6345_l1_chip *intc = irq_desc_get_handler_data(desc);
+	struct bcm6345_l1_cpu *cpu;
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	unsigned int idx;
+
+#ifdef CONFIG_SMP
+	cpu = intc->cpus[cpu_logical_map(smp_processor_id())];
+#else
+	cpu = intc->cpus[0];
+#endif
+
+	chained_irq_enter(chip, desc);
+
+	for (idx = 0; idx < intc->n_words; idx++) {
+		int base = idx * IRQS_PER_WORD;
+		unsigned long pending;
+		irq_hw_number_t hwirq;
+		unsigned int irq;
+
+		pending = __raw_readl(cpu->map_base + reg_status(intc, idx));
+		pending &= __raw_readl(cpu->map_base + reg_enable(intc, idx));
+
+		for_each_set_bit(hwirq, &pending, IRQS_PER_WORD) {
+			irq = irq_linear_revmap(intc->domain, base + hwirq);
+			if (irq)
+				do_IRQ(irq);
+			else
+				spurious_interrupt();
+		}
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static inline void __bcm6345_l1_unmask(struct irq_data *d)
+{
+	struct bcm6345_l1_chip *intc = irq_data_get_irq_chip_data(d);
+	u32 word = d->hwirq / IRQS_PER_WORD;
+	u32 mask = BIT(d->hwirq % IRQS_PER_WORD);
+	unsigned int cpu_idx = cpu_for_irq(intc, d);
+
+	intc->cpus[cpu_idx]->enable_cache[word] |= mask;
+	__raw_writel(intc->cpus[cpu_idx]->enable_cache[word],
+		intc->cpus[cpu_idx]->map_base + reg_enable(intc, word));
+}
+
+static inline void __bcm6345_l1_mask(struct irq_data *d)
+{
+	struct bcm6345_l1_chip *intc = irq_data_get_irq_chip_data(d);
+	u32 word = d->hwirq / IRQS_PER_WORD;
+	u32 mask = BIT(d->hwirq % IRQS_PER_WORD);
+	unsigned int cpu_idx = cpu_for_irq(intc, d);
+
+	intc->cpus[cpu_idx]->enable_cache[word] &= ~mask;
+	__raw_writel(intc->cpus[cpu_idx]->enable_cache[word],
+		intc->cpus[cpu_idx]->map_base + reg_enable(intc, word));
+}
+
+static void bcm6345_l1_unmask(struct irq_data *d)
+{
+	struct bcm6345_l1_chip *intc = irq_data_get_irq_chip_data(d);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&intc->lock, flags);
+	__bcm6345_l1_unmask(d);
+	raw_spin_unlock_irqrestore(&intc->lock, flags);
+}
+
+static void bcm6345_l1_mask(struct irq_data *d)
+{
+	struct bcm6345_l1_chip *intc = irq_data_get_irq_chip_data(d);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&intc->lock, flags);
+	__bcm6345_l1_mask(d);
+	raw_spin_unlock_irqrestore(&intc->lock, flags);
+}
+
+static int bcm6345_l1_set_affinity(struct irq_data *d,
+				   const struct cpumask *dest,
+				   bool force)
+{
+	struct bcm6345_l1_chip *intc = irq_data_get_irq_chip_data(d);
+	u32 word = d->hwirq / IRQS_PER_WORD;
+	u32 mask = BIT(d->hwirq % IRQS_PER_WORD);
+	unsigned int old_cpu = cpu_for_irq(intc, d);
+	unsigned int new_cpu;
+	struct cpumask valid;
+	unsigned long flags;
+	bool enabled;
+
+	if (!cpumask_and(&valid, &intc->cpumask, dest))
+		return -EINVAL;
+
+	new_cpu = cpumask_any_and(&valid, cpu_online_mask);
+	if (new_cpu >= nr_cpu_ids)
+		return -EINVAL;
+
+	dest = cpumask_of(new_cpu);
+
+	raw_spin_lock_irqsave(&intc->lock, flags);
+	if (old_cpu != new_cpu) {
+		enabled = intc->cpus[old_cpu]->enable_cache[word] & mask;
+		if (enabled)
+			__bcm6345_l1_mask(d);
+		cpumask_copy(irq_data_get_affinity_mask(d), dest);
+		if (enabled)
+			__bcm6345_l1_unmask(d);
+	} else {
+		cpumask_copy(irq_data_get_affinity_mask(d), dest);
+	}
+	raw_spin_unlock_irqrestore(&intc->lock, flags);
+
+	return IRQ_SET_MASK_OK_NOCOPY;
+}
+
+static int __init bcm6345_l1_init_one(struct device_node *dn,
+				      unsigned int idx,
+				      struct bcm6345_l1_chip *intc)
+{
+	struct resource res;
+	resource_size_t sz;
+	struct bcm6345_l1_cpu *cpu;
+	unsigned int i, n_words;
+
+	if (of_address_to_resource(dn, idx, &res))
+		return -EINVAL;
+	sz = resource_size(&res);
+	n_words = sz / REG_BYTES_PER_IRQ_WORD;
+
+	if (!intc->n_words)
+		intc->n_words = n_words;
+	else if (intc->n_words != n_words)
+		return -EINVAL;
+
+	cpu = intc->cpus[idx] = kzalloc(sizeof(*cpu) + n_words * sizeof(u32),
+					GFP_KERNEL);
+	if (!cpu)
+		return -ENOMEM;
+
+	cpu->map_base = ioremap(res.start, sz);
+	if (!cpu->map_base)
+		return -ENOMEM;
+
+	for (i = 0; i < n_words; i++) {
+		cpu->enable_cache[i] = 0;
+		__raw_writel(0, cpu->map_base + reg_enable(intc, i));
+	}
+
+	cpu->parent_irq = irq_of_parse_and_map(dn, idx);
+	if (!cpu->parent_irq) {
+		pr_err("failed to map parent interrupt %d\n", cpu->parent_irq);
+		return -EINVAL;
+	}
+	irq_set_chained_handler_and_data(cpu->parent_irq,
+						bcm6345_l1_irq_handle, intc);
+
+	return 0;
+}
+
+static struct irq_chip bcm6345_l1_irq_chip = {
+	.name			= "bcm6345-l1",
+	.irq_mask		= bcm6345_l1_mask,
+	.irq_unmask		= bcm6345_l1_unmask,
+	.irq_set_affinity	= bcm6345_l1_set_affinity,
+};
+
+static int bcm6345_l1_map(struct irq_domain *d, unsigned int virq,
+			  irq_hw_number_t hw_irq)
+{
+	irq_set_chip_and_handler(virq,
+		&bcm6345_l1_irq_chip, handle_percpu_irq);
+	irq_set_chip_data(virq, d->host_data);
+	return 0;
+}
+
+static const struct irq_domain_ops bcm6345_l1_domain_ops = {
+	.xlate			= irq_domain_xlate_onecell,
+	.map			= bcm6345_l1_map,
+};
+
+static int __init bcm6345_l1_of_init(struct device_node *dn,
+			      struct device_node *parent)
+{
+	struct bcm6345_l1_chip *intc;
+	unsigned int idx;
+	int ret;
+
+	intc = kzalloc(sizeof(*intc), GFP_KERNEL);
+	if (!intc)
+		return -ENOMEM;
+
+	for_each_possible_cpu(idx) {
+		ret = bcm6345_l1_init_one(dn, idx, intc);
+		if (ret)
+			pr_err("failed to init intc L1 for cpu %d: %d\n",
+				idx, ret);
+		else
+			cpumask_set_cpu(idx, &intc->cpumask);
+	}
+
+	if (!cpumask_weight(&intc->cpumask)) {
+		ret = -ENODEV;
+		goto out_free;
+	}
+
+	raw_spin_lock_init(&intc->lock);
+
+	intc->domain = irq_domain_add_linear(dn, IRQS_PER_WORD * intc->n_words,
+					     &bcm6345_l1_domain_ops,
+					     intc);
+	if (!intc->domain) {
+		ret = -ENOMEM;
+		goto out_unmap;
+	}
+
+	pr_info("registered BCM6345 L1 intc (IRQs: %d)\n",
+			IRQS_PER_WORD * intc->n_words);
+	for_each_cpu(idx, &intc->cpumask) {
+		struct bcm6345_l1_cpu *cpu = intc->cpus[idx];
+
+		pr_info("  CPU%u at MMIO 0x%p (irq = %d)\n", idx,
+				cpu->map_base, cpu->parent_irq);
+	}
+
+	return 0;
+
+out_unmap:
+	for_each_possible_cpu(idx) {
+		struct bcm6345_l1_cpu *cpu = intc->cpus[idx];
+
+		if (cpu) {
+			if (cpu->map_base)
+				iounmap(cpu->map_base);
+			kfree(cpu);
+		}
+	}
+out_free:
+	kfree(intc);
+	return ret;
+}
+
+IRQCHIP_DECLARE(bcm6345_l1, "brcm,bcm6345-l1-intc", bcm6345_l1_of_init);
diff --git a/drivers/irqchip/irq-gic-realview.c b/drivers/irqchip/irq-gic-realview.c
index aa46eb280a7f..54c296401525 100644
--- a/drivers/irqchip/irq-gic-realview.c
+++ b/drivers/irqchip/irq-gic-realview.c
@@ -10,7 +10,8 @@
 #include <linux/irqchip/arm-gic.h>
 
 #define REALVIEW_SYS_LOCK_OFFSET	0x20
-#define REALVIEW_PB11MP_SYS_PLD_CTRL1	0x74
+#define REALVIEW_SYS_PLD_CTRL1		0x74
+#define REALVIEW_EB_REVB_SYS_PLD_CTRL1	0xD8
 #define VERSATILE_LOCK_VAL		0xA05F
 #define PLD_INTMODE_MASK		BIT(22)|BIT(23)|BIT(24)
 #define PLD_INTMODE_LEGACY		0x0
@@ -18,26 +19,57 @@
 #define PLD_INTMODE_NEW_NO_DCC		BIT(23)
 #define PLD_INTMODE_FIQ_ENABLE		BIT(24)
 
+/* For some reason RealView EB Rev B moved this register */
+static const struct of_device_id syscon_pldset_of_match[] = {
+	{
+		.compatible = "arm,realview-eb11mp-revb-syscon",
+		.data = (void *)REALVIEW_EB_REVB_SYS_PLD_CTRL1,
+	},
+	{
+		.compatible = "arm,realview-eb11mp-revc-syscon",
+		.data = (void *)REALVIEW_SYS_PLD_CTRL1,
+	},
+	{
+		.compatible = "arm,realview-eb-syscon",
+		.data = (void *)REALVIEW_SYS_PLD_CTRL1,
+	},
+	{
+		.compatible = "arm,realview-pb11mp-syscon",
+		.data = (void *)REALVIEW_SYS_PLD_CTRL1,
+	},
+	{},
+};
+
 static int __init
 realview_gic_of_init(struct device_node *node, struct device_node *parent)
 {
 	static struct regmap *map;
+	struct device_node *np;
+	const struct of_device_id *gic_id;
+	u32 pld1_ctrl;
+
+	np = of_find_matching_node_and_match(NULL, syscon_pldset_of_match,
+					     &gic_id);
+	if (!np)
+		return -ENODEV;
+	pld1_ctrl = (u32)gic_id->data;
 
 	/* The PB11MPCore GIC needs to be configured in the syscon */
-	map = syscon_regmap_lookup_by_compatible("arm,realview-pb11mp-syscon");
+	map = syscon_node_to_regmap(np);
 	if (!IS_ERR(map)) {
 		/* new irq mode with no DCC */
 		regmap_write(map, REALVIEW_SYS_LOCK_OFFSET,
 			     VERSATILE_LOCK_VAL);
-		regmap_update_bits(map, REALVIEW_PB11MP_SYS_PLD_CTRL1,
+		regmap_update_bits(map, pld1_ctrl,
 				   PLD_INTMODE_NEW_NO_DCC,
 				   PLD_INTMODE_MASK);
 		regmap_write(map, REALVIEW_SYS_LOCK_OFFSET, 0x0000);
-		pr_info("TC11MP GIC: set up interrupt controller to NEW mode, no DCC\n");
+		pr_info("RealView GIC: set up interrupt controller to NEW mode, no DCC\n");
 	} else {
-		pr_err("TC11MP GIC setup: could not find syscon\n");
-		return -ENXIO;
+		pr_err("RealView GIC setup: could not find syscon\n");
+		return -ENODEV;
 	}
 	return gic_of_init(node, parent);
 }
 IRQCHIP_DECLARE(armtc11mp_gic, "arm,tc11mp-gic", realview_gic_of_init);
+IRQCHIP_DECLARE(armeb11mp_gic, "arm,eb11mp-gic", realview_gic_of_init);
diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c
index c779f83e511d..28f047c61baa 100644
--- a/drivers/irqchip/irq-gic-v2m.c
+++ b/drivers/irqchip/irq-gic-v2m.c
@@ -92,18 +92,6 @@ static struct msi_domain_info gicv2m_msi_domain_info = {
 	.chip	= &gicv2m_msi_irq_chip,
 };
 
-static int gicv2m_set_affinity(struct irq_data *irq_data,
-			       const struct cpumask *mask, bool force)
-{
-	int ret;
-
-	ret = irq_chip_set_affinity_parent(irq_data, mask, force);
-	if (ret == IRQ_SET_MASK_OK)
-		ret = IRQ_SET_MASK_OK_DONE;
-
-	return ret;
-}
-
 static void gicv2m_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 {
 	struct v2m_data *v2m = irq_data_get_irq_chip_data(data);
@@ -122,7 +110,7 @@ static struct irq_chip gicv2m_irq_chip = {
 	.irq_mask		= irq_chip_mask_parent,
 	.irq_unmask		= irq_chip_unmask_parent,
 	.irq_eoi		= irq_chip_eoi_parent,
-	.irq_set_affinity	= gicv2m_set_affinity,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
 	.irq_compose_msi_msg	= gicv2m_compose_msi_msg,
 };
 
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 3447549fcc93..39261798c59f 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -66,7 +66,10 @@ struct its_node {
 	unsigned long		phys_base;
 	struct its_cmd_block	*cmd_base;
 	struct its_cmd_block	*cmd_write;
-	void			*tables[GITS_BASER_NR_REGS];
+	struct {
+		void		*base;
+		u32		order;
+	} tables[GITS_BASER_NR_REGS];
 	struct its_collection	*collections;
 	struct list_head	its_device_list;
 	u64			flags;
@@ -75,6 +78,9 @@ struct its_node {
 
 #define ITS_ITT_ALIGN		SZ_256
 
+/* Convert page order to size in bytes */
+#define PAGE_ORDER_TO_SIZE(o)	(PAGE_SIZE << (o))
+
 struct event_lpi_map {
 	unsigned long		*lpi_map;
 	u16			*col_map;
@@ -97,7 +103,6 @@ struct its_device {
 
 static LIST_HEAD(its_nodes);
 static DEFINE_SPINLOCK(its_lock);
-static struct device_node *gic_root_node;
 static struct rdists *gic_rdists;
 
 #define gic_data_rdist()		(raw_cpu_ptr(gic_rdists->rdist))
@@ -597,11 +602,6 @@ static void its_unmask_irq(struct irq_data *d)
 	lpi_set_config(d, true);
 }
 
-static void its_eoi_irq(struct irq_data *d)
-{
-	gic_write_eoir(d->hwirq);
-}
-
 static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
@@ -638,7 +638,7 @@ static struct irq_chip its_irq_chip = {
 	.name			= "ITS",
 	.irq_mask		= its_mask_irq,
 	.irq_unmask		= its_unmask_irq,
-	.irq_eoi		= its_eoi_irq,
+	.irq_eoi		= irq_chip_eoi_parent,
 	.irq_set_affinity	= its_set_affinity,
 	.irq_compose_msi_msg	= its_irq_compose_msi_msg,
 };
@@ -670,7 +670,7 @@ static int its_chunk_to_lpi(int chunk)
 	return (chunk << IRQS_PER_CHUNK_SHIFT) + 8192;
 }
 
-static int its_lpi_init(u32 id_bits)
+static int __init its_lpi_init(u32 id_bits)
 {
 	lpi_chunks = its_lpi_to_chunk(1UL << id_bits);
 
@@ -807,9 +807,10 @@ static void its_free_tables(struct its_node *its)
 	int i;
 
 	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
-		if (its->tables[i]) {
-			free_page((unsigned long)its->tables[i]);
-			its->tables[i] = NULL;
+		if (its->tables[i].base) {
+			free_pages((unsigned long)its->tables[i].base,
+				   its->tables[i].order);
+			its->tables[i].base = NULL;
 		}
 	}
 }
@@ -842,7 +843,6 @@ static int its_alloc_tables(const char *node_name, struct its_node *its)
 		u64 type = GITS_BASER_TYPE(val);
 		u64 entry_size = GITS_BASER_ENTRY_SIZE(val);
 		int order = get_order(psz);
-		int alloc_size;
 		int alloc_pages;
 		u64 tmp;
 		void *base;
@@ -874,9 +874,8 @@ static int its_alloc_tables(const char *node_name, struct its_node *its)
 			}
 		}
 
-		alloc_size = (1 << order) * PAGE_SIZE;
 retry_alloc_baser:
-		alloc_pages = (alloc_size / psz);
+		alloc_pages = (PAGE_ORDER_TO_SIZE(order) / psz);
 		if (alloc_pages > GITS_BASER_PAGES_MAX) {
 			alloc_pages = GITS_BASER_PAGES_MAX;
 			order = get_order(GITS_BASER_PAGES_MAX * psz);
@@ -890,7 +889,8 @@ retry_alloc_baser:
 			goto out_free;
 		}
 
-		its->tables[i] = base;
+		its->tables[i].base = base;
+		its->tables[i].order = order;
 
 retry_baser:
 		val = (virt_to_phys(base) 				 |
@@ -928,7 +928,7 @@ retry_baser:
 			shr = tmp & GITS_BASER_SHAREABILITY_MASK;
 			if (!shr) {
 				cache = GITS_BASER_nC;
-				__flush_dcache_area(base, alloc_size);
+				__flush_dcache_area(base, PAGE_ORDER_TO_SIZE(order));
 			}
 			goto retry_baser;
 		}
@@ -940,7 +940,7 @@ retry_baser:
 			 * something is horribly wrong...
 			 */
 			free_pages((unsigned long)base, order);
-			its->tables[i] = NULL;
+			its->tables[i].base = NULL;
 
 			switch (psz) {
 			case SZ_16K:
@@ -961,7 +961,7 @@ retry_baser:
 		}
 
 		pr_info("ITS: allocated %d %s @%lx (psz %dK, shr %d)\n",
-			(int)(alloc_size / entry_size),
+			(int)(PAGE_ORDER_TO_SIZE(order) / entry_size),
 			its_base_type_string[type],
 			(unsigned long)virt_to_phys(base),
 			psz / SZ_1K, (int)shr >> GITS_BASER_SHAREABILITY_SHIFT);
@@ -1429,7 +1429,8 @@ static void its_enable_quirks(struct its_node *its)
 	gic_enable_quirks(iidr, its_quirks, its);
 }
 
-static int its_probe(struct device_node *node, struct irq_domain *parent)
+static int __init its_probe(struct device_node *node,
+			    struct irq_domain *parent)
 {
 	struct resource res;
 	struct its_node *its;
@@ -1590,7 +1591,7 @@ static struct of_device_id its_device_id[] = {
 	{},
 };
 
-int its_init(struct device_node *node, struct rdists *rdists,
+int __init its_init(struct device_node *node, struct rdists *rdists,
 	     struct irq_domain *parent_domain)
 {
 	struct device_node *np;
@@ -1606,8 +1607,6 @@ int its_init(struct device_node *node, struct rdists *rdists,
 	}
 
 	gic_rdists = rdists;
-	gic_root_node = node;
-
 	its_alloc_lpi_tables();
 	its_lpi_init(rdists->id_bits);
 
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index d7be6ddc34f6..5b7d3c2129d8 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -15,10 +15,12 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/acpi.h>
 #include <linux/cpu.h>
 #include <linux/cpu_pm.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
+#include <linux/irqdomain.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
@@ -38,6 +40,7 @@
 struct redist_region {
 	void __iomem		*redist_base;
 	phys_addr_t		phys_base;
+	bool			single_redist;
 };
 
 struct gic_chip_data {
@@ -434,6 +437,9 @@ static int gic_populate_rdist(void)
 				return 0;
 			}
 
+			if (gic_data.redist_regions[i].single_redist)
+				break;
+
 			if (gic_data.redist_stride) {
 				ptr += gic_data.redist_stride;
 			} else {
@@ -634,7 +640,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	else
 		gic_dist_wait_for_rwp();
 
-	return IRQ_SET_MASK_OK;
+	return IRQ_SET_MASK_OK_DONE;
 }
 #else
 #define gic_set_affinity	NULL
@@ -764,6 +770,15 @@ static int gic_irq_domain_translate(struct irq_domain *d,
 		return 0;
 	}
 
+	if (is_fwnode_irqchip(fwspec->fwnode)) {
+		if(fwspec->param_count != 2)
+			return -EINVAL;
+
+		*hwirq = fwspec->param[0];
+		*type = fwspec->param[1];
+		return 0;
+	}
+
 	return -EINVAL;
 }
 
@@ -811,17 +826,88 @@ static void gicv3_enable_quirks(void)
 #endif
 }
 
+static int __init gic_init_bases(void __iomem *dist_base,
+				 struct redist_region *rdist_regs,
+				 u32 nr_redist_regions,
+				 u64 redist_stride,
+				 struct fwnode_handle *handle)
+{
+	struct device_node *node;
+	u32 typer;
+	int gic_irqs;
+	int err;
+
+	if (!is_hyp_mode_available())
+		static_key_slow_dec(&supports_deactivate);
+
+	if (static_key_true(&supports_deactivate))
+		pr_info("GIC: Using split EOI/Deactivate mode\n");
+
+	gic_data.dist_base = dist_base;
+	gic_data.redist_regions = rdist_regs;
+	gic_data.nr_redist_regions = nr_redist_regions;
+	gic_data.redist_stride = redist_stride;
+
+	gicv3_enable_quirks();
+
+	/*
+	 * Find out how many interrupts are supported.
+	 * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI)
+	 */
+	typer = readl_relaxed(gic_data.dist_base + GICD_TYPER);
+	gic_data.rdists.id_bits = GICD_TYPER_ID_BITS(typer);
+	gic_irqs = GICD_TYPER_IRQS(typer);
+	if (gic_irqs > 1020)
+		gic_irqs = 1020;
+	gic_data.irq_nr = gic_irqs;
+
+	gic_data.domain = irq_domain_create_tree(handle, &gic_irq_domain_ops,
+						 &gic_data);
+	gic_data.rdists.rdist = alloc_percpu(typeof(*gic_data.rdists.rdist));
+
+	if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdists.rdist)) {
+		err = -ENOMEM;
+		goto out_free;
+	}
+
+	set_handle_irq(gic_handle_irq);
+
+	node = to_of_node(handle);
+	if (IS_ENABLED(CONFIG_ARM_GIC_V3_ITS) && gic_dist_supports_lpis() &&
+	    node) /* Temp hack to prevent ITS init for ACPI */
+		its_init(node, &gic_data.rdists, gic_data.domain);
+
+	gic_smp_init();
+	gic_dist_init();
+	gic_cpu_init();
+	gic_cpu_pm_init();
+
+	return 0;
+
+out_free:
+	if (gic_data.domain)
+		irq_domain_remove(gic_data.domain);
+	free_percpu(gic_data.rdists.rdist);
+	return err;
+}
+
+static int __init gic_validate_dist_version(void __iomem *dist_base)
+{
+	u32 reg = readl_relaxed(dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK;
+
+	if (reg != GIC_PIDR2_ARCH_GICv3 && reg != GIC_PIDR2_ARCH_GICv4)
+		return -ENODEV;
+
+	return 0;
+}
+
 static int __init gic_of_init(struct device_node *node, struct device_node *parent)
 {
 	void __iomem *dist_base;
 	struct redist_region *rdist_regs;
 	u64 redist_stride;
 	u32 nr_redist_regions;
-	u32 typer;
-	u32 reg;
-	int gic_irqs;
-	int err;
-	int i;
+	int err, i;
 
 	dist_base = of_iomap(node, 0);
 	if (!dist_base) {
@@ -830,11 +916,10 @@ static int __init gic_of_init(struct device_node *node, struct device_node *pare
 		return -ENXIO;
 	}
 
-	reg = readl_relaxed(dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK;
-	if (reg != GIC_PIDR2_ARCH_GICv3 && reg != GIC_PIDR2_ARCH_GICv4) {
+	err = gic_validate_dist_version(dist_base);
+	if (err) {
 		pr_err("%s: no distributor detected, giving up\n",
 			node->full_name);
-		err = -ENODEV;
 		goto out_unmap_dist;
 	}
 
@@ -865,63 +950,229 @@ static int __init gic_of_init(struct device_node *node, struct device_node *pare
 	if (of_property_read_u64(node, "redistributor-stride", &redist_stride))
 		redist_stride = 0;
 
-	if (!is_hyp_mode_available())
-		static_key_slow_dec(&supports_deactivate);
+	err = gic_init_bases(dist_base, rdist_regs, nr_redist_regions,
+			     redist_stride, &node->fwnode);
+	if (!err)
+		return 0;
 
-	if (static_key_true(&supports_deactivate))
-		pr_info("GIC: Using split EOI/Deactivate mode\n");
+out_unmap_rdist:
+	for (i = 0; i < nr_redist_regions; i++)
+		if (rdist_regs[i].redist_base)
+			iounmap(rdist_regs[i].redist_base);
+	kfree(rdist_regs);
+out_unmap_dist:
+	iounmap(dist_base);
+	return err;
+}
 
-	gic_data.dist_base = dist_base;
-	gic_data.redist_regions = rdist_regs;
-	gic_data.nr_redist_regions = nr_redist_regions;
-	gic_data.redist_stride = redist_stride;
+IRQCHIP_DECLARE(gic_v3, "arm,gic-v3", gic_of_init);
 
-	gicv3_enable_quirks();
+#ifdef CONFIG_ACPI
+static void __iomem *dist_base;
+static struct redist_region *redist_regs __initdata;
+static u32 nr_redist_regions __initdata;
+static bool single_redist;
+
+static void __init
+gic_acpi_register_redist(phys_addr_t phys_base, void __iomem *redist_base)
+{
+	static int count = 0;
+
+	redist_regs[count].phys_base = phys_base;
+	redist_regs[count].redist_base = redist_base;
+	redist_regs[count].single_redist = single_redist;
+	count++;
+}
+
+static int __init
+gic_acpi_parse_madt_redist(struct acpi_subtable_header *header,
+			   const unsigned long end)
+{
+	struct acpi_madt_generic_redistributor *redist =
+			(struct acpi_madt_generic_redistributor *)header;
+	void __iomem *redist_base;
+
+	redist_base = ioremap(redist->base_address, redist->length);
+	if (!redist_base) {
+		pr_err("Couldn't map GICR region @%llx\n", redist->base_address);
+		return -ENOMEM;
+	}
+
+	gic_acpi_register_redist(redist->base_address, redist_base);
+	return 0;
+}
+
+static int __init
+gic_acpi_parse_madt_gicc(struct acpi_subtable_header *header,
+			 const unsigned long end)
+{
+	struct acpi_madt_generic_interrupt *gicc =
+				(struct acpi_madt_generic_interrupt *)header;
+	u32 reg = readl_relaxed(dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK;
+	u32 size = reg == GIC_PIDR2_ARCH_GICv4 ? SZ_64K * 4 : SZ_64K * 2;
+	void __iomem *redist_base;
+
+	redist_base = ioremap(gicc->gicr_base_address, size);
+	if (!redist_base)
+		return -ENOMEM;
+
+	gic_acpi_register_redist(gicc->gicr_base_address, redist_base);
+	return 0;
+}
+
+static int __init gic_acpi_collect_gicr_base(void)
+{
+	acpi_tbl_entry_handler redist_parser;
+	enum acpi_madt_type type;
+
+	if (single_redist) {
+		type = ACPI_MADT_TYPE_GENERIC_INTERRUPT;
+		redist_parser = gic_acpi_parse_madt_gicc;
+	} else {
+		type = ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR;
+		redist_parser = gic_acpi_parse_madt_redist;
+	}
+
+	/* Collect redistributor base addresses in GICR entries */
+	if (acpi_table_parse_madt(type, redist_parser, 0) > 0)
+		return 0;
+
+	pr_info("No valid GICR entries exist\n");
+	return -ENODEV;
+}
+
+static int __init gic_acpi_match_gicr(struct acpi_subtable_header *header,
+				  const unsigned long end)
+{
+	/* Subtable presence means that redist exists, that's it */
+	return 0;
+}
+
+static int __init gic_acpi_match_gicc(struct acpi_subtable_header *header,
+				      const unsigned long end)
+{
+	struct acpi_madt_generic_interrupt *gicc =
+				(struct acpi_madt_generic_interrupt *)header;
 
 	/*
-	 * Find out how many interrupts are supported.
-	 * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI)
+	 * If GICC is enabled and has valid gicr base address, then it means
+	 * GICR base is presented via GICC
 	 */
-	typer = readl_relaxed(gic_data.dist_base + GICD_TYPER);
-	gic_data.rdists.id_bits = GICD_TYPER_ID_BITS(typer);
-	gic_irqs = GICD_TYPER_IRQS(typer);
-	if (gic_irqs > 1020)
-		gic_irqs = 1020;
-	gic_data.irq_nr = gic_irqs;
+	if ((gicc->flags & ACPI_MADT_ENABLED) && gicc->gicr_base_address)
+		return 0;
 
-	gic_data.domain = irq_domain_add_tree(node, &gic_irq_domain_ops,
-					      &gic_data);
-	gic_data.rdists.rdist = alloc_percpu(typeof(*gic_data.rdists.rdist));
+	return -ENODEV;
+}
 
-	if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdists.rdist)) {
+static int __init gic_acpi_count_gicr_regions(void)
+{
+	int count;
+
+	/*
+	 * Count how many redistributor regions we have. It is not allowed
+	 * to mix redistributor description, GICR and GICC subtables have to be
+	 * mutually exclusive.
+	 */
+	count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR,
+				      gic_acpi_match_gicr, 0);
+	if (count > 0) {
+		single_redist = false;
+		return count;
+	}
+
+	count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
+				      gic_acpi_match_gicc, 0);
+	if (count > 0)
+		single_redist = true;
+
+	return count;
+}
+
+static bool __init acpi_validate_gic_table(struct acpi_subtable_header *header,
+					   struct acpi_probe_entry *ape)
+{
+	struct acpi_madt_generic_distributor *dist;
+	int count;
+
+	dist = (struct acpi_madt_generic_distributor *)header;
+	if (dist->version != ape->driver_data)
+		return false;
+
+	/* We need to do that exercise anyway, the sooner the better */
+	count = gic_acpi_count_gicr_regions();
+	if (count <= 0)
+		return false;
+
+	nr_redist_regions = count;
+	return true;
+}
+
+#define ACPI_GICV3_DIST_MEM_SIZE (SZ_64K)
+
+static int __init
+gic_acpi_init(struct acpi_subtable_header *header, const unsigned long end)
+{
+	struct acpi_madt_generic_distributor *dist;
+	struct fwnode_handle *domain_handle;
+	int i, err;
+
+	/* Get distributor base address */
+	dist = (struct acpi_madt_generic_distributor *)header;
+	dist_base = ioremap(dist->base_address, ACPI_GICV3_DIST_MEM_SIZE);
+	if (!dist_base) {
+		pr_err("Unable to map GICD registers\n");
+		return -ENOMEM;
+	}
+
+	err = gic_validate_dist_version(dist_base);
+	if (err) {
+		pr_err("No distributor detected at @%p, giving up", dist_base);
+		goto out_dist_unmap;
+	}
+
+	redist_regs = kzalloc(sizeof(*redist_regs) * nr_redist_regions,
+			      GFP_KERNEL);
+	if (!redist_regs) {
 		err = -ENOMEM;
-		goto out_free;
+		goto out_dist_unmap;
 	}
 
-	set_handle_irq(gic_handle_irq);
+	err = gic_acpi_collect_gicr_base();
+	if (err)
+		goto out_redist_unmap;
 
-	if (IS_ENABLED(CONFIG_ARM_GIC_V3_ITS) && gic_dist_supports_lpis())
-		its_init(node, &gic_data.rdists, gic_data.domain);
+	domain_handle = irq_domain_alloc_fwnode(dist_base);
+	if (!domain_handle) {
+		err = -ENOMEM;
+		goto out_redist_unmap;
+	}
 
-	gic_smp_init();
-	gic_dist_init();
-	gic_cpu_init();
-	gic_cpu_pm_init();
+	err = gic_init_bases(dist_base, redist_regs, nr_redist_regions, 0,
+			     domain_handle);
+	if (err)
+		goto out_fwhandle_free;
 
+	acpi_set_irq_model(ACPI_IRQ_MODEL_GIC, domain_handle);
 	return 0;
 
-out_free:
-	if (gic_data.domain)
-		irq_domain_remove(gic_data.domain);
-	free_percpu(gic_data.rdists.rdist);
-out_unmap_rdist:
+out_fwhandle_free:
+	irq_domain_free_fwnode(domain_handle);
+out_redist_unmap:
 	for (i = 0; i < nr_redist_regions; i++)
-		if (rdist_regs[i].redist_base)
-			iounmap(rdist_regs[i].redist_base);
-	kfree(rdist_regs);
-out_unmap_dist:
+		if (redist_regs[i].redist_base)
+			iounmap(redist_regs[i].redist_base);
+	kfree(redist_regs);
+out_dist_unmap:
 	iounmap(dist_base);
 	return err;
 }
-
-IRQCHIP_DECLARE(gic_v3, "arm,gic-v3", gic_of_init);
+IRQCHIP_ACPI_DECLARE(gic_v3, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR,
+		     acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_V3,
+		     gic_acpi_init);
+IRQCHIP_ACPI_DECLARE(gic_v4, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR,
+		     acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_V4,
+		     gic_acpi_init);
+IRQCHIP_ACPI_DECLARE(gic_v3_or_v4, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR,
+		     acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_NONE,
+		     gic_acpi_init);
+#endif
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 911758c056c1..282344b95ec2 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -319,7 +319,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	writel_relaxed(val | bit, reg);
 	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
 
-	return IRQ_SET_MASK_OK;
+	return IRQ_SET_MASK_OK_DONE;
 }
 #endif
 
@@ -384,9 +384,6 @@ static struct irq_chip gic_chip = {
 	.irq_unmask		= gic_unmask_irq,
 	.irq_eoi		= gic_eoi_irq,
 	.irq_set_type		= gic_set_type,
-#ifdef CONFIG_SMP
-	.irq_set_affinity	= gic_set_affinity,
-#endif
 	.irq_get_irqchip_state	= gic_irq_get_irqchip_state,
 	.irq_set_irqchip_state	= gic_irq_set_irqchip_state,
 	.flags			= IRQCHIP_SET_TYPE_MASKED |
@@ -400,9 +397,6 @@ static struct irq_chip gic_eoimode1_chip = {
 	.irq_unmask		= gic_unmask_irq,
 	.irq_eoi		= gic_eoimode1_eoi_irq,
 	.irq_set_type		= gic_set_type,
-#ifdef CONFIG_SMP
-	.irq_set_affinity	= gic_set_affinity,
-#endif
 	.irq_get_irqchip_state	= gic_irq_get_irqchip_state,
 	.irq_set_irqchip_state	= gic_irq_set_irqchip_state,
 	.irq_set_vcpu_affinity	= gic_irq_set_vcpu_affinity,
@@ -443,7 +437,7 @@ static void gic_cpu_if_up(struct gic_chip_data *gic)
 	u32 bypass = 0;
 	u32 mode = 0;
 
-	if (static_key_true(&supports_deactivate))
+	if (gic == &gic_data[0] && static_key_true(&supports_deactivate))
 		mode = GIC_CPU_CTRL_EOImodeNS;
 
 	/*
@@ -1039,6 +1033,11 @@ static void __init __gic_init_bases(unsigned int gic_nr, int irq_start,
 		gic->chip.name = kasprintf(GFP_KERNEL, "GIC-%d", gic_nr);
 	}
 
+#ifdef CONFIG_SMP
+	if (gic_nr == 0)
+		gic->chip.irq_set_affinity = gic_set_affinity;
+#endif
+
 #ifdef CONFIG_GIC_NON_BANKED
 	if (percpu_offset) { /* Frankein-GIC without banked registers... */
 		unsigned int cpu;
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 9e17ef27a183..94a30da0cfac 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -29,16 +29,32 @@ struct gic_pcpu_mask {
 	DECLARE_BITMAP(pcpu_mask, GIC_MAX_INTRS);
 };
 
+struct gic_irq_spec {
+	enum {
+		GIC_DEVICE,
+		GIC_IPI
+	} type;
+
+	union {
+		struct cpumask *ipimask;
+		unsigned int hwirq;
+	};
+};
+
 static unsigned long __gic_base_addr;
+
 static void __iomem *gic_base;
 static struct gic_pcpu_mask pcpu_masks[NR_CPUS];
 static DEFINE_SPINLOCK(gic_lock);
 static struct irq_domain *gic_irq_domain;
+static struct irq_domain *gic_dev_domain;
+static struct irq_domain *gic_ipi_domain;
 static int gic_shared_intrs;
 static int gic_vpes;
 static unsigned int gic_cpu_pin;
 static unsigned int timer_cpu_pin;
 static struct irq_chip gic_level_irq_controller, gic_edge_irq_controller;
+DECLARE_BITMAP(ipi_resrv, GIC_MAX_INTRS);
 
 static void __gic_irq_dispatch(void);
 
@@ -264,9 +280,11 @@ static void gic_bind_eic_interrupt(int irq, int set)
 		  GIC_VPE_EIC_SS(irq), set);
 }
 
-void gic_send_ipi(unsigned int intr)
+static void gic_send_ipi(struct irq_data *d, unsigned int cpu)
 {
-	gic_write(GIC_REG(SHARED, GIC_SH_WEDGE), GIC_SH_WEDGE_SET(intr));
+	irq_hw_number_t hwirq = GIC_HWIRQ_TO_SHARED(irqd_to_hwirq(d));
+
+	gic_write(GIC_REG(SHARED, GIC_SH_WEDGE), GIC_SH_WEDGE_SET(hwirq));
 }
 
 int gic_get_c0_compare_int(void)
@@ -449,7 +467,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *cpumask,
 	gic_map_to_vpe(irq, mips_cm_vp_id(cpumask_first(&tmp)));
 
 	/* Update the pcpu_masks */
-	for (i = 0; i < NR_CPUS; i++)
+	for (i = 0; i < gic_vpes; i++)
 		clear_bit(irq, pcpu_masks[i].pcpu_mask);
 	set_bit(irq, pcpu_masks[cpumask_first(&tmp)].pcpu_mask);
 
@@ -479,6 +497,7 @@ static struct irq_chip gic_edge_irq_controller = {
 #ifdef CONFIG_SMP
 	.irq_set_affinity	=	gic_set_affinity,
 #endif
+	.ipi_send_single	=	gic_send_ipi,
 };
 
 static void gic_handle_local_int(bool chained)
@@ -572,83 +591,6 @@ static void gic_irq_dispatch(struct irq_desc *desc)
 	gic_handle_shared_int(true);
 }
 
-#ifdef CONFIG_MIPS_GIC_IPI
-static int gic_resched_int_base;
-static int gic_call_int_base;
-
-unsigned int plat_ipi_resched_int_xlate(unsigned int cpu)
-{
-	return gic_resched_int_base + cpu;
-}
-
-unsigned int plat_ipi_call_int_xlate(unsigned int cpu)
-{
-	return gic_call_int_base + cpu;
-}
-
-static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
-{
-	scheduler_ipi();
-
-	return IRQ_HANDLED;
-}
-
-static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
-{
-	generic_smp_call_function_interrupt();
-
-	return IRQ_HANDLED;
-}
-
-static struct irqaction irq_resched = {
-	.handler	= ipi_resched_interrupt,
-	.flags		= IRQF_PERCPU,
-	.name		= "IPI resched"
-};
-
-static struct irqaction irq_call = {
-	.handler	= ipi_call_interrupt,
-	.flags		= IRQF_PERCPU,
-	.name		= "IPI call"
-};
-
-static __init void gic_ipi_init_one(unsigned int intr, int cpu,
-				    struct irqaction *action)
-{
-	int virq = irq_create_mapping(gic_irq_domain,
-				      GIC_SHARED_TO_HWIRQ(intr));
-	int i;
-
-	gic_map_to_vpe(intr, mips_cm_vp_id(cpu));
-	for (i = 0; i < NR_CPUS; i++)
-		clear_bit(intr, pcpu_masks[i].pcpu_mask);
-	set_bit(intr, pcpu_masks[cpu].pcpu_mask);
-
-	irq_set_irq_type(virq, IRQ_TYPE_EDGE_RISING);
-
-	irq_set_handler(virq, handle_percpu_irq);
-	setup_irq(virq, action);
-}
-
-static __init void gic_ipi_init(void)
-{
-	int i;
-
-	/* Use last 2 * NR_CPUS interrupts as IPIs */
-	gic_resched_int_base = gic_shared_intrs - nr_cpu_ids;
-	gic_call_int_base = gic_resched_int_base - nr_cpu_ids;
-
-	for (i = 0; i < nr_cpu_ids; i++) {
-		gic_ipi_init_one(gic_call_int_base + i, i, &irq_call);
-		gic_ipi_init_one(gic_resched_int_base + i, i, &irq_resched);
-	}
-}
-#else
-static inline void gic_ipi_init(void)
-{
-}
-#endif
-
 static void __init gic_basic_init(void)
 {
 	unsigned int i;
@@ -753,19 +695,21 @@ static int gic_local_irq_domain_map(struct irq_domain *d, unsigned int virq,
 }
 
 static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq,
-				     irq_hw_number_t hw)
+				     irq_hw_number_t hw, unsigned int vpe)
 {
 	int intr = GIC_HWIRQ_TO_SHARED(hw);
 	unsigned long flags;
+	int i;
 
 	irq_set_chip_and_handler(virq, &gic_level_irq_controller,
 				 handle_level_irq);
 
 	spin_lock_irqsave(&gic_lock, flags);
 	gic_map_to_pin(intr, gic_cpu_pin);
-	/* Map to VPE 0 by default */
-	gic_map_to_vpe(intr, 0);
-	set_bit(intr, pcpu_masks[0].pcpu_mask);
+	gic_map_to_vpe(intr, vpe);
+	for (i = 0; i < gic_vpes; i++)
+		clear_bit(intr, pcpu_masks[i].pcpu_mask);
+	set_bit(intr, pcpu_masks[vpe].pcpu_mask);
 	spin_unlock_irqrestore(&gic_lock, flags);
 
 	return 0;
@@ -776,10 +720,93 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq,
 {
 	if (GIC_HWIRQ_TO_LOCAL(hw) < GIC_NUM_LOCAL_INTRS)
 		return gic_local_irq_domain_map(d, virq, hw);
-	return gic_shared_irq_domain_map(d, virq, hw);
+	return gic_shared_irq_domain_map(d, virq, hw, 0);
 }
 
-static int gic_irq_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
+static int gic_irq_domain_alloc(struct irq_domain *d, unsigned int virq,
+				unsigned int nr_irqs, void *arg)
+{
+	struct gic_irq_spec *spec = arg;
+	irq_hw_number_t hwirq, base_hwirq;
+	int cpu, ret, i;
+
+	if (spec->type == GIC_DEVICE) {
+		/* verify that it doesn't conflict with an IPI irq */
+		if (test_bit(spec->hwirq, ipi_resrv))
+			return -EBUSY;
+	} else {
+		base_hwirq = find_first_bit(ipi_resrv, gic_shared_intrs);
+		if (base_hwirq == gic_shared_intrs) {
+			return -ENOMEM;
+		}
+
+		/* check that we have enough space */
+		for (i = base_hwirq; i < nr_irqs; i++) {
+			if (!test_bit(i, ipi_resrv))
+				return -EBUSY;
+		}
+		bitmap_clear(ipi_resrv, base_hwirq, nr_irqs);
+
+		/* map the hwirq for each cpu consecutively */
+		i = 0;
+		for_each_cpu(cpu, spec->ipimask) {
+			hwirq = GIC_SHARED_TO_HWIRQ(base_hwirq + i);
+
+			ret = irq_domain_set_hwirq_and_chip(d, virq + i, hwirq,
+							    &gic_edge_irq_controller,
+							    NULL);
+			if (ret)
+				goto error;
+
+			ret = gic_shared_irq_domain_map(d, virq + i, hwirq, cpu);
+			if (ret)
+				goto error;
+
+			i++;
+		}
+
+		/*
+		 * tell the parent about the base hwirq we allocated so it can
+		 * set its own domain data
+		 */
+		spec->hwirq = base_hwirq;
+	}
+
+	return 0;
+error:
+	bitmap_set(ipi_resrv, base_hwirq, nr_irqs);
+	return ret;
+}
+
+void gic_irq_domain_free(struct irq_domain *d, unsigned int virq,
+			 unsigned int nr_irqs)
+{
+	irq_hw_number_t base_hwirq;
+	struct irq_data *data;
+
+	data = irq_get_irq_data(virq);
+	if (!data)
+		return;
+
+	base_hwirq = GIC_HWIRQ_TO_SHARED(irqd_to_hwirq(data));
+	bitmap_set(ipi_resrv, base_hwirq, nr_irqs);
+}
+
+int gic_irq_domain_match(struct irq_domain *d, struct device_node *node,
+			 enum irq_domain_bus_token bus_token)
+{
+	/* this domain should'nt be accessed directly */
+	return 0;
+}
+
+static const struct irq_domain_ops gic_irq_domain_ops = {
+	.map = gic_irq_domain_map,
+	.alloc = gic_irq_domain_alloc,
+	.free = gic_irq_domain_free,
+	.match = gic_irq_domain_match,
+};
+
+static int gic_dev_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
 				const u32 *intspec, unsigned int intsize,
 				irq_hw_number_t *out_hwirq,
 				unsigned int *out_type)
@@ -798,9 +825,130 @@ static int gic_irq_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
 	return 0;
 }
 
-static const struct irq_domain_ops gic_irq_domain_ops = {
-	.map = gic_irq_domain_map,
-	.xlate = gic_irq_domain_xlate,
+static int gic_dev_domain_alloc(struct irq_domain *d, unsigned int virq,
+				unsigned int nr_irqs, void *arg)
+{
+	struct irq_fwspec *fwspec = arg;
+	struct gic_irq_spec spec = {
+		.type = GIC_DEVICE,
+		.hwirq = fwspec->param[1],
+	};
+	int i, ret;
+	bool is_shared = fwspec->param[0] == GIC_SHARED;
+
+	if (is_shared) {
+		ret = irq_domain_alloc_irqs_parent(d, virq, nr_irqs, &spec);
+		if (ret)
+			return ret;
+	}
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_hw_number_t hwirq;
+
+		if (is_shared)
+			hwirq = GIC_SHARED_TO_HWIRQ(spec.hwirq + i);
+		else
+			hwirq = GIC_LOCAL_TO_HWIRQ(spec.hwirq + i);
+
+		ret = irq_domain_set_hwirq_and_chip(d, virq + i,
+						    hwirq,
+						    &gic_level_irq_controller,
+						    NULL);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+void gic_dev_domain_free(struct irq_domain *d, unsigned int virq,
+			 unsigned int nr_irqs)
+{
+	/* no real allocation is done for dev irqs, so no need to free anything */
+	return;
+}
+
+static struct irq_domain_ops gic_dev_domain_ops = {
+	.xlate = gic_dev_domain_xlate,
+	.alloc = gic_dev_domain_alloc,
+	.free = gic_dev_domain_free,
+};
+
+static int gic_ipi_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
+				const u32 *intspec, unsigned int intsize,
+				irq_hw_number_t *out_hwirq,
+				unsigned int *out_type)
+{
+	/*
+	 * There's nothing to translate here. hwirq is dynamically allocated and
+	 * the irq type is always edge triggered.
+	 * */
+	*out_hwirq = 0;
+	*out_type = IRQ_TYPE_EDGE_RISING;
+
+	return 0;
+}
+
+static int gic_ipi_domain_alloc(struct irq_domain *d, unsigned int virq,
+				unsigned int nr_irqs, void *arg)
+{
+	struct cpumask *ipimask = arg;
+	struct gic_irq_spec spec = {
+		.type = GIC_IPI,
+		.ipimask = ipimask
+	};
+	int ret, i;
+
+	ret = irq_domain_alloc_irqs_parent(d, virq, nr_irqs, &spec);
+	if (ret)
+		return ret;
+
+	/* the parent should have set spec.hwirq to the base_hwirq it allocated */
+	for (i = 0; i < nr_irqs; i++) {
+		ret = irq_domain_set_hwirq_and_chip(d, virq + i,
+						    GIC_SHARED_TO_HWIRQ(spec.hwirq + i),
+						    &gic_edge_irq_controller,
+						    NULL);
+		if (ret)
+			goto error;
+
+		ret = irq_set_irq_type(virq + i, IRQ_TYPE_EDGE_RISING);
+		if (ret)
+			goto error;
+	}
+
+	return 0;
+error:
+	irq_domain_free_irqs_parent(d, virq, nr_irqs);
+	return ret;
+}
+
+void gic_ipi_domain_free(struct irq_domain *d, unsigned int virq,
+			 unsigned int nr_irqs)
+{
+	irq_domain_free_irqs_parent(d, virq, nr_irqs);
+}
+
+int gic_ipi_domain_match(struct irq_domain *d, struct device_node *node,
+			 enum irq_domain_bus_token bus_token)
+{
+	bool is_ipi;
+
+	switch (bus_token) {
+	case DOMAIN_BUS_IPI:
+		is_ipi = d->bus_token == bus_token;
+		return to_of_node(d->fwnode) == node && is_ipi;
+		break;
+	default:
+		return 0;
+	}
+}
+
+static struct irq_domain_ops gic_ipi_domain_ops = {
+	.xlate = gic_ipi_domain_xlate,
+	.alloc = gic_ipi_domain_alloc,
+	.free = gic_ipi_domain_free,
+	.match = gic_ipi_domain_match,
 };
 
 static void __init __gic_init(unsigned long gic_base_addr,
@@ -809,6 +957,7 @@ static void __init __gic_init(unsigned long gic_base_addr,
 			      struct device_node *node)
 {
 	unsigned int gicconfig;
+	unsigned int v[2];
 
 	__gic_base_addr = gic_base_addr;
 
@@ -864,9 +1013,32 @@ static void __init __gic_init(unsigned long gic_base_addr,
 	if (!gic_irq_domain)
 		panic("Failed to add GIC IRQ domain");
 
-	gic_basic_init();
+	gic_dev_domain = irq_domain_add_hierarchy(gic_irq_domain, 0,
+						  GIC_NUM_LOCAL_INTRS + gic_shared_intrs,
+						  node, &gic_dev_domain_ops, NULL);
+	if (!gic_dev_domain)
+		panic("Failed to add GIC DEV domain");
+
+	gic_ipi_domain = irq_domain_add_hierarchy(gic_irq_domain,
+						  IRQ_DOMAIN_FLAG_IPI_PER_CPU,
+						  GIC_NUM_LOCAL_INTRS + gic_shared_intrs,
+						  node, &gic_ipi_domain_ops, NULL);
+	if (!gic_ipi_domain)
+		panic("Failed to add GIC IPI domain");
 
-	gic_ipi_init();
+	gic_ipi_domain->bus_token = DOMAIN_BUS_IPI;
+
+	if (node &&
+	    !of_property_read_u32_array(node, "mti,reserved-ipi-vectors", v, 2)) {
+		bitmap_set(ipi_resrv, v[0], v[1]);
+	} else {
+		/* Make the last 2 * gic_vpes available for IPIs */
+		bitmap_set(ipi_resrv,
+			   gic_shared_intrs - 2 * gic_vpes,
+			   2 * gic_vpes);
+	}
+
+	gic_basic_init();
 }
 
 void __init gic_init(unsigned long gic_base_addr,
diff --git a/drivers/irqchip/irq-mvebu-odmi.c b/drivers/irqchip/irq-mvebu-odmi.c
new file mode 100644
index 000000000000..b4d367868dbb
--- /dev/null
+++ b/drivers/irqchip/irq-mvebu-odmi.c
@@ -0,0 +1,236 @@
+/*
+ * Copyright (C) 2016 Marvell
+ *
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#define pr_fmt(fmt) "GIC-ODMI: " fmt
+
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/msi.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+#define GICP_ODMIN_SET			0x40
+#define   GICP_ODMI_INT_NUM_SHIFT	12
+#define GICP_ODMIN_GM_EP_R0		0x110
+#define GICP_ODMIN_GM_EP_R1		0x114
+#define GICP_ODMIN_GM_EA_R0		0x108
+#define GICP_ODMIN_GM_EA_R1		0x118
+
+/*
+ * We don't support the group events, so we simply have 8 interrupts
+ * per frame.
+ */
+#define NODMIS_SHIFT		3
+#define NODMIS_PER_FRAME	(1 << NODMIS_SHIFT)
+#define NODMIS_MASK		(NODMIS_PER_FRAME - 1)
+
+struct odmi_data {
+	struct resource res;
+	void __iomem *base;
+	unsigned int spi_base;
+};
+
+static struct odmi_data *odmis;
+static unsigned long *odmis_bm;
+static unsigned int odmis_count;
+
+/* Protects odmis_bm */
+static DEFINE_SPINLOCK(odmis_bm_lock);
+
+static void odmi_compose_msi_msg(struct irq_data *d, struct msi_msg *msg)
+{
+	struct odmi_data *odmi;
+	phys_addr_t addr;
+	unsigned int odmin;
+
+	if (WARN_ON(d->hwirq >= odmis_count * NODMIS_PER_FRAME))
+		return;
+
+	odmi = &odmis[d->hwirq >> NODMIS_SHIFT];
+	odmin = d->hwirq & NODMIS_MASK;
+
+	addr = odmi->res.start + GICP_ODMIN_SET;
+
+	msg->address_hi = upper_32_bits(addr);
+	msg->address_lo = lower_32_bits(addr);
+	msg->data = odmin << GICP_ODMI_INT_NUM_SHIFT;
+}
+
+static struct irq_chip odmi_irq_chip = {
+	.name			= "ODMI",
+	.irq_mask		= irq_chip_mask_parent,
+	.irq_unmask		= irq_chip_unmask_parent,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+	.irq_compose_msi_msg	= odmi_compose_msi_msg,
+};
+
+static int odmi_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				 unsigned int nr_irqs, void *args)
+{
+	struct odmi_data *odmi = NULL;
+	struct irq_fwspec fwspec;
+	struct irq_data *d;
+	unsigned int hwirq, odmin;
+	int ret;
+
+	spin_lock(&odmis_bm_lock);
+	hwirq = find_first_zero_bit(odmis_bm, NODMIS_PER_FRAME * odmis_count);
+	if (hwirq >= NODMIS_PER_FRAME * odmis_count) {
+		spin_unlock(&odmis_bm_lock);
+		return -ENOSPC;
+	}
+
+	__set_bit(hwirq, odmis_bm);
+	spin_unlock(&odmis_bm_lock);
+
+	odmi = &odmis[hwirq >> NODMIS_SHIFT];
+	odmin = hwirq & NODMIS_MASK;
+
+	fwspec.fwnode = domain->parent->fwnode;
+	fwspec.param_count = 3;
+	fwspec.param[0] = GIC_SPI;
+	fwspec.param[1] = odmi->spi_base - 32 + odmin;
+	fwspec.param[2] = IRQ_TYPE_EDGE_RISING;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec);
+	if (ret) {
+		pr_err("Cannot allocate parent IRQ\n");
+		spin_lock(&odmis_bm_lock);
+		__clear_bit(odmin, odmis_bm);
+		spin_unlock(&odmis_bm_lock);
+		return ret;
+	}
+
+	/* Configure the interrupt line to be edge */
+	d = irq_domain_get_irq_data(domain->parent, virq);
+	d->chip->irq_set_type(d, IRQ_TYPE_EDGE_RISING);
+
+	irq_domain_set_hwirq_and_chip(domain, virq, hwirq,
+				      &odmi_irq_chip, NULL);
+
+	return 0;
+}
+
+static void odmi_irq_domain_free(struct irq_domain *domain,
+				 unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+
+	if (d->hwirq >= odmis_count * NODMIS_PER_FRAME) {
+		pr_err("Failed to teardown msi. Invalid hwirq %lu\n", d->hwirq);
+		return;
+	}
+
+	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
+
+	/* Actually free the MSI */
+	spin_lock(&odmis_bm_lock);
+	__clear_bit(d->hwirq, odmis_bm);
+	spin_unlock(&odmis_bm_lock);
+}
+
+static const struct irq_domain_ops odmi_domain_ops = {
+	.alloc	= odmi_irq_domain_alloc,
+	.free	= odmi_irq_domain_free,
+};
+
+static struct irq_chip odmi_msi_irq_chip = {
+	.name	= "ODMI",
+};
+
+static struct msi_domain_ops odmi_msi_ops = {
+};
+
+static struct msi_domain_info odmi_msi_domain_info = {
+	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS),
+	.ops	= &odmi_msi_ops,
+	.chip	= &odmi_msi_irq_chip,
+};
+
+static int __init mvebu_odmi_init(struct device_node *node,
+				  struct device_node *parent)
+{
+	struct irq_domain *inner_domain, *plat_domain;
+	int ret, i;
+
+	if (of_property_read_u32(node, "marvell,odmi-frames", &odmis_count))
+		return -EINVAL;
+
+	odmis = kcalloc(odmis_count, sizeof(struct odmi_data), GFP_KERNEL);
+	if (!odmis)
+		return -ENOMEM;
+
+	odmis_bm = kcalloc(BITS_TO_LONGS(odmis_count * NODMIS_PER_FRAME),
+			   sizeof(long), GFP_KERNEL);
+	if (!odmis_bm) {
+		ret = -ENOMEM;
+		goto err_alloc;
+	}
+
+	for (i = 0; i < odmis_count; i++) {
+		struct odmi_data *odmi = &odmis[i];
+
+		ret = of_address_to_resource(node, i, &odmi->res);
+		if (ret)
+			goto err_unmap;
+
+		odmi->base = of_io_request_and_map(node, i, "odmi");
+		if (IS_ERR(odmi->base)) {
+			ret = PTR_ERR(odmi->base);
+			goto err_unmap;
+		}
+
+		if (of_property_read_u32_index(node, "marvell,spi-base",
+					       i, &odmi->spi_base)) {
+			ret = -EINVAL;
+			goto err_unmap;
+		}
+	}
+
+	inner_domain = irq_domain_create_linear(of_node_to_fwnode(node),
+						odmis_count * NODMIS_PER_FRAME,
+						&odmi_domain_ops, NULL);
+	if (!inner_domain) {
+		ret = -ENOMEM;
+		goto err_unmap;
+	}
+
+	inner_domain->parent = irq_find_host(parent);
+
+	plat_domain = platform_msi_create_irq_domain(of_node_to_fwnode(node),
+						     &odmi_msi_domain_info,
+						     inner_domain);
+	if (!plat_domain) {
+		ret = -ENOMEM;
+		goto err_remove_inner;
+	}
+
+	return 0;
+
+err_remove_inner:
+	irq_domain_remove(inner_domain);
+err_unmap:
+	for (i = 0; i < odmis_count; i++) {
+		struct odmi_data *odmi = &odmis[i];
+
+		if (odmi->base && !IS_ERR(odmi->base))
+			iounmap(odmis[i].base);
+	}
+	kfree(odmis_bm);
+err_alloc:
+	kfree(odmis);
+	return ret;
+}
+
+IRQCHIP_DECLARE(mvebu_odmi, "marvell,odmi-controller", mvebu_odmi_init);
diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c
index efe50845939d..17304705f2cf 100644
--- a/drivers/irqchip/irq-mxs.c
+++ b/drivers/irqchip/irq-mxs.c
@@ -183,7 +183,7 @@ static void __iomem * __init icoll_init_iobase(struct device_node *np)
 	void __iomem *icoll_base;
 
 	icoll_base = of_io_request_and_map(np, 0, np->name);
-	if (!icoll_base)
+	if (IS_ERR(icoll_base))
 		panic("%s: unable to map resource", np->full_name);
 	return icoll_base;
 }
diff --git a/drivers/irqchip/irq-sun4i.c b/drivers/irqchip/irq-sun4i.c
index 0704362f4c82..376b28074e0d 100644
--- a/drivers/irqchip/irq-sun4i.c
+++ b/drivers/irqchip/irq-sun4i.c
@@ -22,7 +22,6 @@
 #include <linux/of_irq.h>
 
 #include <asm/exception.h>
-#include <asm/mach/irq.h>
 
 #define SUN4I_IRQ_VECTOR_REG		0x00
 #define SUN4I_IRQ_PROTECTION_REG	0x08
diff --git a/drivers/irqchip/irq-sunxi-nmi.c b/drivers/irqchip/irq-sunxi-nmi.c
index 0820f67cc9a7..668730c5cb66 100644
--- a/drivers/irqchip/irq-sunxi-nmi.c
+++ b/drivers/irqchip/irq-sunxi-nmi.c
@@ -160,9 +160,9 @@ static int __init sunxi_sc_nmi_irq_init(struct device_node *node,
 
 	gc = irq_get_domain_generic_chip(domain, 0);
 	gc->reg_base = of_io_request_and_map(node, 0, of_node_full_name(node));
-	if (!gc->reg_base) {
+	if (IS_ERR(gc->reg_base)) {
 		pr_err("unable to map resource\n");
-		ret = -ENOMEM;
+		ret = PTR_ERR(gc->reg_base);
 		goto fail_irqd_remove;
 	}
 
diff --git a/drivers/irqchip/irq-tango.c b/drivers/irqchip/irq-tango.c
new file mode 100644
index 000000000000..bdbb5c0ff7fe
--- /dev/null
+++ b/drivers/irqchip/irq-tango.c
@@ -0,0 +1,232 @@
+/*
+ * Copyright (C) 2014 Mans Rullgard <mans@mansr.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/ioport.h>
+#include <linux/io.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/slab.h>
+
+#define IRQ0_CTL_BASE		0x0000
+#define IRQ1_CTL_BASE		0x0100
+#define EDGE_CTL_BASE		0x0200
+#define IRQ2_CTL_BASE		0x0300
+
+#define IRQ_CTL_HI		0x18
+#define EDGE_CTL_HI		0x20
+
+#define IRQ_STATUS		0x00
+#define IRQ_RAWSTAT		0x04
+#define IRQ_EN_SET		0x08
+#define IRQ_EN_CLR		0x0c
+#define IRQ_SOFT_SET		0x10
+#define IRQ_SOFT_CLR		0x14
+
+#define EDGE_STATUS		0x00
+#define EDGE_RAWSTAT		0x04
+#define EDGE_CFG_RISE		0x08
+#define EDGE_CFG_FALL		0x0c
+#define EDGE_CFG_RISE_SET	0x10
+#define EDGE_CFG_RISE_CLR	0x14
+#define EDGE_CFG_FALL_SET	0x18
+#define EDGE_CFG_FALL_CLR	0x1c
+
+struct tangox_irq_chip {
+	void __iomem *base;
+	unsigned long ctl;
+};
+
+static inline u32 intc_readl(struct tangox_irq_chip *chip, int reg)
+{
+	return readl_relaxed(chip->base + reg);
+}
+
+static inline void intc_writel(struct tangox_irq_chip *chip, int reg, u32 val)
+{
+	writel_relaxed(val, chip->base + reg);
+}
+
+static void tangox_dispatch_irqs(struct irq_domain *dom, unsigned int status,
+				 int base)
+{
+	unsigned int hwirq;
+	unsigned int virq;
+
+	while (status) {
+		hwirq = __ffs(status);
+		virq = irq_find_mapping(dom, base + hwirq);
+		if (virq)
+			generic_handle_irq(virq);
+		status &= ~BIT(hwirq);
+	}
+}
+
+static void tangox_irq_handler(struct irq_desc *desc)
+{
+	struct irq_domain *dom = irq_desc_get_handler_data(desc);
+	struct irq_chip *host_chip = irq_desc_get_chip(desc);
+	struct tangox_irq_chip *chip = dom->host_data;
+	unsigned int status_lo, status_hi;
+
+	chained_irq_enter(host_chip, desc);
+
+	status_lo = intc_readl(chip, chip->ctl + IRQ_STATUS);
+	status_hi = intc_readl(chip, chip->ctl + IRQ_CTL_HI + IRQ_STATUS);
+
+	tangox_dispatch_irqs(dom, status_lo, 0);
+	tangox_dispatch_irqs(dom, status_hi, 32);
+
+	chained_irq_exit(host_chip, desc);
+}
+
+static int tangox_irq_set_type(struct irq_data *d, unsigned int flow_type)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	struct tangox_irq_chip *chip = gc->domain->host_data;
+	struct irq_chip_regs *regs = &gc->chip_types[0].regs;
+
+	switch (flow_type & IRQ_TYPE_SENSE_MASK) {
+	case IRQ_TYPE_EDGE_RISING:
+		intc_writel(chip, regs->type + EDGE_CFG_RISE_SET, d->mask);
+		intc_writel(chip, regs->type + EDGE_CFG_FALL_CLR, d->mask);
+		break;
+
+	case IRQ_TYPE_EDGE_FALLING:
+		intc_writel(chip, regs->type + EDGE_CFG_RISE_CLR, d->mask);
+		intc_writel(chip, regs->type + EDGE_CFG_FALL_SET, d->mask);
+		break;
+
+	case IRQ_TYPE_LEVEL_HIGH:
+		intc_writel(chip, regs->type + EDGE_CFG_RISE_CLR, d->mask);
+		intc_writel(chip, regs->type + EDGE_CFG_FALL_CLR, d->mask);
+		break;
+
+	case IRQ_TYPE_LEVEL_LOW:
+		intc_writel(chip, regs->type + EDGE_CFG_RISE_SET, d->mask);
+		intc_writel(chip, regs->type + EDGE_CFG_FALL_SET, d->mask);
+		break;
+
+	default:
+		pr_err("Invalid trigger mode %x for IRQ %d\n",
+		       flow_type, d->irq);
+		return -EINVAL;
+	}
+
+	return irq_setup_alt_chip(d, flow_type);
+}
+
+static void __init tangox_irq_init_chip(struct irq_chip_generic *gc,
+					unsigned long ctl_offs,
+					unsigned long edge_offs)
+{
+	struct tangox_irq_chip *chip = gc->domain->host_data;
+	struct irq_chip_type *ct = gc->chip_types;
+	unsigned long ctl_base = chip->ctl + ctl_offs;
+	unsigned long edge_base = EDGE_CTL_BASE + edge_offs;
+	int i;
+
+	gc->reg_base = chip->base;
+	gc->unused = 0;
+
+	for (i = 0; i < 2; i++) {
+		ct[i].chip.irq_ack = irq_gc_ack_set_bit;
+		ct[i].chip.irq_mask = irq_gc_mask_disable_reg;
+		ct[i].chip.irq_mask_ack = irq_gc_mask_disable_reg_and_ack;
+		ct[i].chip.irq_unmask = irq_gc_unmask_enable_reg;
+		ct[i].chip.irq_set_type = tangox_irq_set_type;
+		ct[i].chip.name = gc->domain->name;
+
+		ct[i].regs.enable = ctl_base + IRQ_EN_SET;
+		ct[i].regs.disable = ctl_base + IRQ_EN_CLR;
+		ct[i].regs.ack = edge_base + EDGE_RAWSTAT;
+		ct[i].regs.type = edge_base;
+	}
+
+	ct[0].type = IRQ_TYPE_LEVEL_MASK;
+	ct[0].handler = handle_level_irq;
+
+	ct[1].type = IRQ_TYPE_EDGE_BOTH;
+	ct[1].handler = handle_edge_irq;
+
+	intc_writel(chip, ct->regs.disable, 0xffffffff);
+	intc_writel(chip, ct->regs.ack, 0xffffffff);
+}
+
+static void __init tangox_irq_domain_init(struct irq_domain *dom)
+{
+	struct irq_chip_generic *gc;
+	int i;
+
+	for (i = 0; i < 2; i++) {
+		gc = irq_get_domain_generic_chip(dom, i * 32);
+		tangox_irq_init_chip(gc, i * IRQ_CTL_HI, i * EDGE_CTL_HI);
+	}
+}
+
+static int __init tangox_irq_init(void __iomem *base, struct resource *baseres,
+				  struct device_node *node)
+{
+	struct tangox_irq_chip *chip;
+	struct irq_domain *dom;
+	struct resource res;
+	int irq;
+	int err;
+
+	irq = irq_of_parse_and_map(node, 0);
+	if (!irq)
+		panic("%s: failed to get IRQ", node->name);
+
+	err = of_address_to_resource(node, 0, &res);
+	if (err)
+		panic("%s: failed to get address", node->name);
+
+	chip = kzalloc(sizeof(*chip), GFP_KERNEL);
+	chip->ctl = res.start - baseres->start;
+	chip->base = base;
+
+	dom = irq_domain_add_linear(node, 64, &irq_generic_chip_ops, chip);
+	if (!dom)
+		panic("%s: failed to create irqdomain", node->name);
+
+	err = irq_alloc_domain_generic_chips(dom, 32, 2, node->name,
+					     handle_level_irq, 0, 0, 0);
+	if (err)
+		panic("%s: failed to allocate irqchip", node->name);
+
+	tangox_irq_domain_init(dom);
+
+	irq_set_chained_handler(irq, tangox_irq_handler);
+	irq_set_handler_data(irq, dom);
+
+	return 0;
+}
+
+static int __init tangox_of_irq_init(struct device_node *node,
+				     struct device_node *parent)
+{
+	struct device_node *c;
+	struct resource res;
+	void __iomem *base;
+
+	base = of_iomap(node, 0);
+	if (!base)
+		panic("%s: of_iomap failed", node->name);
+
+	of_address_to_resource(node, 0, &res);
+
+	for_each_child_of_node(node, c)
+		tangox_irq_init(base, &res, c);
+
+	return 0;
+}
+IRQCHIP_DECLARE(tangox_intc, "sigma,smp8642-intc", tangox_of_irq_init);
diff --git a/drivers/irqchip/irq-ts4800.c b/drivers/irqchip/irq-ts4800.c
index 4192bdcd2734..2325fb3c482b 100644
--- a/drivers/irqchip/irq-ts4800.c
+++ b/drivers/irqchip/irq-ts4800.c
@@ -59,7 +59,7 @@ static int ts4800_irqdomain_map(struct irq_domain *d, unsigned int irq,
 	return 0;
 }
 
-struct irq_domain_ops ts4800_ic_ops = {
+static const struct irq_domain_ops ts4800_ic_ops = {
 	.map = ts4800_irqdomain_map,
 	.xlate = irq_domain_xlate_onecell,
 };
diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c
index 2a506fe0c8a4..d1f8ab915b15 100644
--- a/drivers/isdn/gigaset/ser-gigaset.c
+++ b/drivers/isdn/gigaset/ser-gigaset.c
@@ -373,13 +373,7 @@ static void gigaset_freecshw(struct cardstate *cs)
 
 static void gigaset_device_release(struct device *dev)
 {
-	struct cardstate *cs = dev_get_drvdata(dev);
-
-	if (!cs)
-		return;
-	dev_set_drvdata(dev, NULL);
-	kfree(cs->hw.ser);
-	cs->hw.ser = NULL;
+	kfree(container_of(dev, struct ser_cardstate, dev.dev));
 }
 
 /*
@@ -408,7 +402,6 @@ static int gigaset_initcshw(struct cardstate *cs)
 		cs->hw.ser = NULL;
 		return rc;
 	}
-	dev_set_drvdata(&cs->hw.ser->dev.dev, cs);
 
 	tasklet_init(&cs->write_tasklet,
 		     gigaset_modem_fill, (unsigned long) cs);
diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c
index 8e2944784e00..afde4edef9ae 100644
--- a/drivers/isdn/hardware/mISDN/netjet.c
+++ b/drivers/isdn/hardware/mISDN/netjet.c
@@ -392,7 +392,7 @@ read_dma(struct tiger_ch *bc, u32 idx, int cnt)
 	}
 	stat = bchannel_get_rxbuf(&bc->bch, cnt);
 	/* only transparent use the count here, HDLC overun is detected later */
-	if (stat == ENOMEM) {
+	if (stat == -ENOMEM) {
 		pr_warning("%s.B%d: No memory for %d bytes\n",
 			   card->name, bc->bch.nr, cnt);
 		return;
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 7f940c24a16b..1f6415168998 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -568,6 +568,14 @@ config LEDS_SEAD3
 	  This driver can also be built as a module. If so the module
 	  will be called leds-sead3.
 
+config LEDS_IS31FL32XX
+	tristate "LED support for ISSI IS31FL32XX I2C LED controller family"
+	depends on LEDS_CLASS && I2C && OF
+	help
+	  Say Y here to include support for ISSI IS31FL32XX and Si-En SN32xx
+	  LED controllers. They are I2C devices with multiple constant-current
+	  channels, each with independent 256-level PWM control.
+
 comment "LED driver for blink(1) USB RGB LED is under Special HID drivers (HID_THINGM)"
 
 config LEDS_BLINKM
diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile
index e9d53092765d..cb2013df52d9 100644
--- a/drivers/leds/Makefile
+++ b/drivers/leds/Makefile
@@ -66,6 +66,7 @@ obj-$(CONFIG_LEDS_MENF21BMC)		+= leds-menf21bmc.o
 obj-$(CONFIG_LEDS_KTD2692)		+= leds-ktd2692.o
 obj-$(CONFIG_LEDS_POWERNV)		+= leds-powernv.o
 obj-$(CONFIG_LEDS_SEAD3)		+= leds-sead3.o
+obj-$(CONFIG_LEDS_IS31FL32XX)		+= leds-is31fl32xx.o
 
 # LED SPI Drivers
 obj-$(CONFIG_LEDS_DAC124S085)		+= leds-dac124s085.o
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index 14139c337312..aa84e5b37593 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -245,6 +245,8 @@ void led_classdev_unregister(struct led_classdev *led_cdev)
 	up_write(&led_cdev->trigger_lock);
 #endif
 
+	led_cdev->flags |= LED_UNREGISTERING;
+
 	/* Stop blinking */
 	led_stop_software_blink(led_cdev);
 
diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c
index 19e1e60dfaa3..3495d5d6547f 100644
--- a/drivers/leds/led-core.c
+++ b/drivers/leds/led-core.c
@@ -25,6 +25,26 @@ EXPORT_SYMBOL_GPL(leds_list_lock);
 LIST_HEAD(leds_list);
 EXPORT_SYMBOL_GPL(leds_list);
 
+static int __led_set_brightness(struct led_classdev *led_cdev,
+				enum led_brightness value)
+{
+	if (!led_cdev->brightness_set)
+		return -ENOTSUPP;
+
+	led_cdev->brightness_set(led_cdev, value);
+
+	return 0;
+}
+
+static int __led_set_brightness_blocking(struct led_classdev *led_cdev,
+					 enum led_brightness value)
+{
+	if (!led_cdev->brightness_set_blocking)
+		return -ENOTSUPP;
+
+	return led_cdev->brightness_set_blocking(led_cdev, value);
+}
+
 static void led_timer_function(unsigned long data)
 {
 	struct led_classdev *led_cdev = (void *)data;
@@ -91,14 +111,14 @@ static void set_brightness_delayed(struct work_struct *ws)
 		led_cdev->flags &= ~LED_BLINK_DISABLE;
 	}
 
-	if (led_cdev->brightness_set)
-		led_cdev->brightness_set(led_cdev, led_cdev->delayed_set_value);
-	else if (led_cdev->brightness_set_blocking)
-		ret = led_cdev->brightness_set_blocking(led_cdev,
-						led_cdev->delayed_set_value);
-	else
-		ret = -ENOTSUPP;
-	if (ret < 0)
+	ret = __led_set_brightness(led_cdev, led_cdev->delayed_set_value);
+	if (ret == -ENOTSUPP)
+		ret = __led_set_brightness_blocking(led_cdev,
+					led_cdev->delayed_set_value);
+	if (ret < 0 &&
+	    /* LED HW might have been unplugged, therefore don't warn */
+	    !(ret == -ENODEV && (led_cdev->flags & LED_UNREGISTERING) &&
+	    (led_cdev->flags & LED_HW_PLUGGABLE)))
 		dev_err(led_cdev->dev,
 			"Setting an LED's brightness failed (%d)\n", ret);
 }
@@ -233,10 +253,8 @@ void led_set_brightness_nopm(struct led_classdev *led_cdev,
 			      enum led_brightness value)
 {
 	/* Use brightness_set op if available, it is guaranteed not to sleep */
-	if (led_cdev->brightness_set) {
-		led_cdev->brightness_set(led_cdev, value);
+	if (!__led_set_brightness(led_cdev, value))
 		return;
-	}
 
 	/* If brightness setting can sleep, delegate it to a work queue task */
 	led_cdev->delayed_set_value = value;
@@ -267,10 +285,7 @@ int led_set_brightness_sync(struct led_classdev *led_cdev,
 	if (led_cdev->flags & LED_SUSPENDED)
 		return 0;
 
-	if (led_cdev->brightness_set_blocking)
-		return led_cdev->brightness_set_blocking(led_cdev,
-							 led_cdev->brightness);
-	return -ENOTSUPP;
+	return __led_set_brightness_blocking(led_cdev, led_cdev->brightness);
 }
 EXPORT_SYMBOL_GPL(led_set_brightness_sync);
 
diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c
index e1e933424ac9..2181581795d3 100644
--- a/drivers/leds/led-triggers.c
+++ b/drivers/leds/led-triggers.c
@@ -34,9 +34,7 @@ ssize_t led_trigger_store(struct device *dev, struct device_attribute *attr,
 		const char *buf, size_t count)
 {
 	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	char trigger_name[TRIG_NAME_MAX];
 	struct led_trigger *trig;
-	size_t len;
 	int ret = count;
 
 	mutex_lock(&led_cdev->led_access);
@@ -46,21 +44,14 @@ ssize_t led_trigger_store(struct device *dev, struct device_attribute *attr,
 		goto unlock;
 	}
 
-	trigger_name[sizeof(trigger_name) - 1] = '\0';
-	strncpy(trigger_name, buf, sizeof(trigger_name) - 1);
-	len = strlen(trigger_name);
-
-	if (len && trigger_name[len - 1] == '\n')
-		trigger_name[len - 1] = '\0';
-
-	if (!strcmp(trigger_name, "none")) {
+	if (sysfs_streq(buf, "none")) {
 		led_trigger_remove(led_cdev);
 		goto unlock;
 	}
 
 	down_read(&triggers_list_lock);
 	list_for_each_entry(trig, &trigger_list, next_trig) {
-		if (!strcmp(trigger_name, trig->name)) {
+		if (sysfs_streq(buf, trig->name)) {
 			down_write(&led_cdev->trigger_lock);
 			led_trigger_set(led_cdev, trig);
 			up_write(&led_cdev->trigger_lock);
diff --git a/drivers/leds/leds-88pm860x.c b/drivers/leds/leds-88pm860x.c
index 1ad4d03a0a3c..77a104d2b124 100644
--- a/drivers/leds/leds-88pm860x.c
+++ b/drivers/leds/leds-88pm860x.c
@@ -195,7 +195,6 @@ static int pm860x_led_probe(struct platform_device *pdev)
 		sprintf(data->name, "led1-blue");
 		break;
 	}
-	platform_set_drvdata(pdev, data);
 	data->chip = chip;
 	data->i2c = (chip->id == CHIP_PM8606) ? chip->client : chip->companion;
 	data->port = pdev->id;
@@ -208,7 +207,7 @@ static int pm860x_led_probe(struct platform_device *pdev)
 	data->cdev.brightness_set_blocking = pm860x_led_set;
 	mutex_init(&data->lock);
 
-	ret = led_classdev_register(chip->dev, &data->cdev);
+	ret = devm_led_classdev_register(chip->dev, &data->cdev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Failed to register LED: %d\n", ret);
 		return ret;
@@ -217,21 +216,12 @@ static int pm860x_led_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int pm860x_led_remove(struct platform_device *pdev)
-{
-	struct pm860x_led *data = platform_get_drvdata(pdev);
-
-	led_classdev_unregister(&data->cdev);
-
-	return 0;
-}
 
 static struct platform_driver pm860x_led_driver = {
 	.driver	= {
 		.name	= "88pm860x-led",
 	},
 	.probe	= pm860x_led_probe,
-	.remove	= pm860x_led_remove,
 };
 
 module_platform_driver(pm860x_led_driver);
diff --git a/drivers/leds/leds-da903x.c b/drivers/leds/leds-da903x.c
index 4752a2b6ba2b..5ff7d72f73aa 100644
--- a/drivers/leds/leds-da903x.c
+++ b/drivers/leds/leds-da903x.c
@@ -113,21 +113,12 @@ static int da903x_led_probe(struct platform_device *pdev)
 	led->flags = pdata->flags;
 	led->master = pdev->dev.parent;
 
-	ret = led_classdev_register(led->master, &led->cdev);
+	ret = devm_led_classdev_register(led->master, &led->cdev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register LED %d\n", id);
 		return ret;
 	}
 
-	platform_set_drvdata(pdev, led);
-	return 0;
-}
-
-static int da903x_led_remove(struct platform_device *pdev)
-{
-	struct da903x_led *led = platform_get_drvdata(pdev);
-
-	led_classdev_unregister(&led->cdev);
 	return 0;
 }
 
@@ -136,7 +127,6 @@ static struct platform_driver da903x_led_driver = {
 		.name	= "da903x-led",
 	},
 	.probe		= da903x_led_probe,
-	.remove		= da903x_led_remove,
 };
 
 module_platform_driver(da903x_led_driver);
diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c
index 7bc53280dbfd..61143f55597e 100644
--- a/drivers/leds/leds-gpio.c
+++ b/drivers/leds/leds-gpio.c
@@ -86,7 +86,7 @@ static int create_gpio_led(const struct gpio_led *template,
 		 * still uses GPIO numbers. Ultimately we would like to get
 		 * rid of this block completely.
 		 */
-		unsigned long flags = 0;
+		unsigned long flags = GPIOF_OUT_INIT_LOW;
 
 		/* skip leds that aren't available */
 		if (!gpio_is_valid(template->gpio)) {
@@ -104,8 +104,8 @@ static int create_gpio_led(const struct gpio_led *template,
 			return ret;
 
 		led_dat->gpiod = gpio_to_desc(template->gpio);
-		if (IS_ERR(led_dat->gpiod))
-			return PTR_ERR(led_dat->gpiod);
+		if (!led_dat->gpiod)
+			return -EINVAL;
 	}
 
 	led_dat->cdev.name = template->name;
diff --git a/drivers/leds/leds-is31fl32xx.c b/drivers/leds/leds-is31fl32xx.c
new file mode 100644
index 000000000000..c901d132d80c
--- /dev/null
+++ b/drivers/leds/leds-is31fl32xx.c
@@ -0,0 +1,508 @@
+/*
+ * Driver for ISSI IS31FL32xx family of I2C LED controllers
+ *
+ * Copyright 2015 Allworx Corp.
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Datasheets:
+ *   http://www.issi.com/US/product-analog-fxled-driver.shtml
+ *   http://www.si-en.com/product.asp?parentid=890
+ */
+
+#include <linux/device.h>
+#include <linux/i2c.h>
+#include <linux/kernel.h>
+#include <linux/leds.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+
+/* Used to indicate a device has no such register */
+#define IS31FL32XX_REG_NONE 0xFF
+
+/* Software Shutdown bit in Shutdown Register */
+#define IS31FL32XX_SHUTDOWN_SSD_ENABLE  0
+#define IS31FL32XX_SHUTDOWN_SSD_DISABLE BIT(0)
+
+/* IS31FL3216 has a number of unique registers */
+#define IS31FL3216_CONFIG_REG 0x00
+#define IS31FL3216_LIGHTING_EFFECT_REG 0x03
+#define IS31FL3216_CHANNEL_CONFIG_REG 0x04
+
+/* Software Shutdown bit in 3216 Config Register */
+#define IS31FL3216_CONFIG_SSD_ENABLE  BIT(7)
+#define IS31FL3216_CONFIG_SSD_DISABLE 0
+
+struct is31fl32xx_priv;
+struct is31fl32xx_led_data {
+	struct led_classdev cdev;
+	u8 channel; /* 1-based, max priv->cdef->channels */
+	struct is31fl32xx_priv *priv;
+};
+
+struct is31fl32xx_priv {
+	const struct is31fl32xx_chipdef *cdef;
+	struct i2c_client *client;
+	unsigned int num_leds;
+	struct is31fl32xx_led_data leds[0];
+};
+
+/**
+ * struct is31fl32xx_chipdef - chip-specific attributes
+ * @channels            : Number of LED channels
+ * @shutdown_reg        : address of Shutdown register (optional)
+ * @pwm_update_reg      : address of PWM Update register
+ * @global_control_reg  : address of Global Control register (optional)
+ * @reset_reg           : address of Reset register (optional)
+ * @pwm_register_base   : address of first PWM register
+ * @pwm_registers_reversed: : true if PWM registers count down instead of up
+ * @led_control_register_base : address of first LED control register (optional)
+ * @enable_bits_per_led_control_register: number of LEDs enable bits in each
+ * @reset_func:         : pointer to reset function
+ *
+ * For all optional register addresses, the sentinel value %IS31FL32XX_REG_NONE
+ * indicates that this chip has no such register.
+ *
+ * If non-NULL, @reset_func will be called during probing to set all
+ * necessary registers to a known initialization state. This is needed
+ * for chips that do not have a @reset_reg.
+ *
+ * @enable_bits_per_led_control_register must be >=1 if
+ * @led_control_register_base != %IS31FL32XX_REG_NONE.
+ */
+struct is31fl32xx_chipdef {
+	u8	channels;
+	u8	shutdown_reg;
+	u8	pwm_update_reg;
+	u8	global_control_reg;
+	u8	reset_reg;
+	u8	pwm_register_base;
+	bool	pwm_registers_reversed;
+	u8	led_control_register_base;
+	u8	enable_bits_per_led_control_register;
+	int (*reset_func)(struct is31fl32xx_priv *priv);
+	int (*sw_shutdown_func)(struct is31fl32xx_priv *priv, bool enable);
+};
+
+static const struct is31fl32xx_chipdef is31fl3236_cdef = {
+	.channels				= 36,
+	.shutdown_reg				= 0x00,
+	.pwm_update_reg				= 0x25,
+	.global_control_reg			= 0x4a,
+	.reset_reg				= 0x4f,
+	.pwm_register_base			= 0x01,
+	.led_control_register_base		= 0x26,
+	.enable_bits_per_led_control_register	= 1,
+};
+
+static const struct is31fl32xx_chipdef is31fl3235_cdef = {
+	.channels				= 28,
+	.shutdown_reg				= 0x00,
+	.pwm_update_reg				= 0x25,
+	.global_control_reg			= 0x4a,
+	.reset_reg				= 0x4f,
+	.pwm_register_base			= 0x05,
+	.led_control_register_base		= 0x2a,
+	.enable_bits_per_led_control_register	= 1,
+};
+
+static const struct is31fl32xx_chipdef is31fl3218_cdef = {
+	.channels				= 18,
+	.shutdown_reg				= 0x00,
+	.pwm_update_reg				= 0x16,
+	.global_control_reg			= IS31FL32XX_REG_NONE,
+	.reset_reg				= 0x17,
+	.pwm_register_base			= 0x01,
+	.led_control_register_base		= 0x13,
+	.enable_bits_per_led_control_register	= 6,
+};
+
+static int is31fl3216_reset(struct is31fl32xx_priv *priv);
+static int is31fl3216_software_shutdown(struct is31fl32xx_priv *priv,
+					bool enable);
+static const struct is31fl32xx_chipdef is31fl3216_cdef = {
+	.channels				= 16,
+	.shutdown_reg				= IS31FL32XX_REG_NONE,
+	.pwm_update_reg				= 0xB0,
+	.global_control_reg			= IS31FL32XX_REG_NONE,
+	.reset_reg				= IS31FL32XX_REG_NONE,
+	.pwm_register_base			= 0x10,
+	.pwm_registers_reversed			= true,
+	.led_control_register_base		= 0x01,
+	.enable_bits_per_led_control_register	= 8,
+	.reset_func				= is31fl3216_reset,
+	.sw_shutdown_func			= is31fl3216_software_shutdown,
+};
+
+static int is31fl32xx_write(struct is31fl32xx_priv *priv, u8 reg, u8 val)
+{
+	int ret;
+
+	dev_dbg(&priv->client->dev, "writing register 0x%02X=0x%02X", reg, val);
+
+	ret =  i2c_smbus_write_byte_data(priv->client, reg, val);
+	if (ret) {
+		dev_err(&priv->client->dev,
+			"register write to 0x%02X failed (error %d)",
+			reg, ret);
+	}
+	return ret;
+}
+
+/*
+ * Custom reset function for IS31FL3216 because it does not have a RESET
+ * register the way that the other IS31FL32xx chips do. We don't bother
+ * writing the GPIO and animation registers, because the registers we
+ * do write ensure those will have no effect.
+ */
+static int is31fl3216_reset(struct is31fl32xx_priv *priv)
+{
+	unsigned int i;
+	int ret;
+
+	ret = is31fl32xx_write(priv, IS31FL3216_CONFIG_REG,
+			       IS31FL3216_CONFIG_SSD_ENABLE);
+	if (ret)
+		return ret;
+	for (i = 0; i < priv->cdef->channels; i++) {
+		ret = is31fl32xx_write(priv, priv->cdef->pwm_register_base+i,
+				       0x00);
+		if (ret)
+			return ret;
+	}
+	ret = is31fl32xx_write(priv, priv->cdef->pwm_update_reg, 0);
+	if (ret)
+		return ret;
+	ret = is31fl32xx_write(priv, IS31FL3216_LIGHTING_EFFECT_REG, 0x00);
+	if (ret)
+		return ret;
+	ret = is31fl32xx_write(priv, IS31FL3216_CHANNEL_CONFIG_REG, 0x00);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/*
+ * Custom Software-Shutdown function for IS31FL3216 because it does not have
+ * a SHUTDOWN register the way that the other IS31FL32xx chips do.
+ * We don't bother doing a read/modify/write on the CONFIG register because
+ * we only ever use a value of '0' for the other fields in that register.
+ */
+static int is31fl3216_software_shutdown(struct is31fl32xx_priv *priv,
+					bool enable)
+{
+	u8 value = enable ? IS31FL3216_CONFIG_SSD_ENABLE :
+			    IS31FL3216_CONFIG_SSD_DISABLE;
+
+	return is31fl32xx_write(priv, IS31FL3216_CONFIG_REG, value);
+}
+
+/*
+ * NOTE: A mutex is not needed in this function because:
+ * - All referenced data is read-only after probe()
+ * - The I2C core has a mutex on to protect the bus
+ * - There are no read/modify/write operations
+ * - Intervening operations between the write of the PWM register
+ *   and the Update register are harmless.
+ *
+ * Example:
+ *	PWM_REG_1 write 16
+ *	UPDATE_REG write 0
+ *	PWM_REG_2 write 128
+ *	UPDATE_REG write 0
+ *   vs:
+ *	PWM_REG_1 write 16
+ *	PWM_REG_2 write 128
+ *	UPDATE_REG write 0
+ *	UPDATE_REG write 0
+ * are equivalent. Poking the Update register merely applies all PWM
+ * register writes up to that point.
+ */
+static int is31fl32xx_brightness_set(struct led_classdev *led_cdev,
+				     enum led_brightness brightness)
+{
+	const struct is31fl32xx_led_data *led_data =
+		container_of(led_cdev, struct is31fl32xx_led_data, cdev);
+	const struct is31fl32xx_chipdef *cdef = led_data->priv->cdef;
+	u8 pwm_register_offset;
+	int ret;
+
+	dev_dbg(led_cdev->dev, "%s: %d\n", __func__, brightness);
+
+	/* NOTE: led_data->channel is 1-based */
+	if (cdef->pwm_registers_reversed)
+		pwm_register_offset = cdef->channels - led_data->channel;
+	else
+		pwm_register_offset = led_data->channel - 1;
+
+	ret = is31fl32xx_write(led_data->priv,
+			       cdef->pwm_register_base + pwm_register_offset,
+			       brightness);
+	if (ret)
+		return ret;
+
+	return is31fl32xx_write(led_data->priv, cdef->pwm_update_reg, 0);
+}
+
+static int is31fl32xx_reset_regs(struct is31fl32xx_priv *priv)
+{
+	const struct is31fl32xx_chipdef *cdef = priv->cdef;
+	int ret;
+
+	if (cdef->reset_reg != IS31FL32XX_REG_NONE) {
+		ret = is31fl32xx_write(priv, cdef->reset_reg, 0);
+		if (ret)
+			return ret;
+	}
+
+	if (cdef->reset_func)
+		return cdef->reset_func(priv);
+
+	return 0;
+}
+
+static int is31fl32xx_software_shutdown(struct is31fl32xx_priv *priv,
+					bool enable)
+{
+	const struct is31fl32xx_chipdef *cdef = priv->cdef;
+	int ret;
+
+	if (cdef->shutdown_reg != IS31FL32XX_REG_NONE) {
+		u8 value = enable ? IS31FL32XX_SHUTDOWN_SSD_ENABLE :
+				    IS31FL32XX_SHUTDOWN_SSD_DISABLE;
+		ret = is31fl32xx_write(priv, cdef->shutdown_reg, value);
+		if (ret)
+			return ret;
+	}
+
+	if (cdef->sw_shutdown_func)
+		return cdef->sw_shutdown_func(priv, enable);
+
+	return 0;
+}
+
+static int is31fl32xx_init_regs(struct is31fl32xx_priv *priv)
+{
+	const struct is31fl32xx_chipdef *cdef = priv->cdef;
+	int ret;
+
+	ret = is31fl32xx_reset_regs(priv);
+	if (ret)
+		return ret;
+
+	/*
+	 * Set enable bit for all channels.
+	 * We will control state with PWM registers alone.
+	 */
+	if (cdef->led_control_register_base != IS31FL32XX_REG_NONE) {
+		u8 value =
+		    GENMASK(cdef->enable_bits_per_led_control_register-1, 0);
+		u8 num_regs = cdef->channels /
+				cdef->enable_bits_per_led_control_register;
+		int i;
+
+		for (i = 0; i < num_regs; i++) {
+			ret = is31fl32xx_write(priv,
+					       cdef->led_control_register_base+i,
+					       value);
+			if (ret)
+				return ret;
+		}
+	}
+
+	ret = is31fl32xx_software_shutdown(priv, false);
+	if (ret)
+		return ret;
+
+	if (cdef->global_control_reg != IS31FL32XX_REG_NONE) {
+		ret = is31fl32xx_write(priv, cdef->global_control_reg, 0x00);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static inline size_t sizeof_is31fl32xx_priv(int num_leds)
+{
+	return sizeof(struct is31fl32xx_priv) +
+		      (sizeof(struct is31fl32xx_led_data) * num_leds);
+}
+
+static int is31fl32xx_parse_child_dt(const struct device *dev,
+				     const struct device_node *child,
+				     struct is31fl32xx_led_data *led_data)
+{
+	struct led_classdev *cdev = &led_data->cdev;
+	int ret = 0;
+	u32 reg;
+
+	if (of_property_read_string(child, "label", &cdev->name))
+		cdev->name = child->name;
+
+	ret = of_property_read_u32(child, "reg", &reg);
+	if (ret || reg < 1 || reg > led_data->priv->cdef->channels) {
+		dev_err(dev,
+			"Child node %s does not have a valid reg property\n",
+			child->full_name);
+		return -EINVAL;
+	}
+	led_data->channel = reg;
+
+	of_property_read_string(child, "linux,default-trigger",
+				&cdev->default_trigger);
+
+	cdev->brightness_set_blocking = is31fl32xx_brightness_set;
+
+	return 0;
+}
+
+static struct is31fl32xx_led_data *is31fl32xx_find_led_data(
+					struct is31fl32xx_priv *priv,
+					u8 channel)
+{
+	size_t i;
+
+	for (i = 0; i < priv->num_leds; i++) {
+		if (priv->leds[i].channel == channel)
+			return &priv->leds[i];
+	}
+
+	return NULL;
+}
+
+static int is31fl32xx_parse_dt(struct device *dev,
+			       struct is31fl32xx_priv *priv)
+{
+	struct device_node *child;
+	int ret = 0;
+
+	for_each_child_of_node(dev->of_node, child) {
+		struct is31fl32xx_led_data *led_data =
+			&priv->leds[priv->num_leds];
+		const struct is31fl32xx_led_data *other_led_data;
+
+		led_data->priv = priv;
+
+		ret = is31fl32xx_parse_child_dt(dev, child, led_data);
+		if (ret)
+			goto err;
+
+		/* Detect if channel is already in use by another child */
+		other_led_data = is31fl32xx_find_led_data(priv,
+							  led_data->channel);
+		if (other_led_data) {
+			dev_err(dev,
+				"%s and %s both attempting to use channel %d\n",
+				led_data->cdev.name,
+				other_led_data->cdev.name,
+				led_data->channel);
+			goto err;
+		}
+
+		ret = devm_led_classdev_register(dev, &led_data->cdev);
+		if (ret) {
+			dev_err(dev, "failed to register PWM led for %s: %d\n",
+				led_data->cdev.name, ret);
+			goto err;
+		}
+
+		priv->num_leds++;
+	}
+
+	return 0;
+
+err:
+	of_node_put(child);
+	return ret;
+}
+
+static const struct of_device_id of_is31fl31xx_match[] = {
+	{ .compatible = "issi,is31fl3236", .data = &is31fl3236_cdef, },
+	{ .compatible = "issi,is31fl3235", .data = &is31fl3235_cdef, },
+	{ .compatible = "issi,is31fl3218", .data = &is31fl3218_cdef, },
+	{ .compatible = "si-en,sn3218",    .data = &is31fl3218_cdef, },
+	{ .compatible = "issi,is31fl3216", .data = &is31fl3216_cdef, },
+	{ .compatible = "si-en,sn3216",    .data = &is31fl3216_cdef, },
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, of_is31fl31xx_match);
+
+static int is31fl32xx_probe(struct i2c_client *client,
+			    const struct i2c_device_id *id)
+{
+	const struct is31fl32xx_chipdef *cdef;
+	const struct of_device_id *of_dev_id;
+	struct device *dev = &client->dev;
+	struct is31fl32xx_priv *priv;
+	int count;
+	int ret = 0;
+
+	of_dev_id = of_match_device(of_is31fl31xx_match, dev);
+	if (!of_dev_id)
+		return -EINVAL;
+
+	cdef = of_dev_id->data;
+
+	count = of_get_child_count(dev->of_node);
+	if (!count)
+		return -EINVAL;
+
+	priv = devm_kzalloc(dev, sizeof_is31fl32xx_priv(count),
+			    GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->client = client;
+	priv->cdef = cdef;
+	i2c_set_clientdata(client, priv);
+
+	ret = is31fl32xx_init_regs(priv);
+	if (ret)
+		return ret;
+
+	ret = is31fl32xx_parse_dt(dev, priv);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int is31fl32xx_remove(struct i2c_client *client)
+{
+	struct is31fl32xx_priv *priv = i2c_get_clientdata(client);
+
+	return is31fl32xx_reset_regs(priv);
+}
+
+/*
+ * i2c-core requires that id_table be non-NULL, even though
+ * it is not used for DeviceTree based instantiation.
+ */
+static const struct i2c_device_id is31fl31xx_id[] = {
+	{},
+};
+
+MODULE_DEVICE_TABLE(i2c, is31fl31xx_id);
+
+static struct i2c_driver is31fl32xx_driver = {
+	.driver = {
+		.name	= "is31fl32xx",
+		.of_match_table = of_is31fl31xx_match,
+	},
+	.probe		= is31fl32xx_probe,
+	.remove		= is31fl32xx_remove,
+	.id_table	= is31fl31xx_id,
+};
+
+module_i2c_driver(is31fl32xx_driver);
+
+MODULE_AUTHOR("David Rivshin <drivshin@allworx.com>");
+MODULE_DESCRIPTION("ISSI IS31FL32xx LED driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/leds-lm3533.c b/drivers/leds/leds-lm3533.c
index 196dcb5e6004..5b529dc013d2 100644
--- a/drivers/leds/leds-lm3533.c
+++ b/drivers/leds/leds-lm3533.c
@@ -698,7 +698,7 @@ static int lm3533_led_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, led);
 
-	ret = led_classdev_register(pdev->dev.parent, &led->cdev);
+	ret = devm_led_classdev_register(pdev->dev.parent, &led->cdev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register LED %d\n", pdev->id);
 		return ret;
@@ -708,18 +708,13 @@ static int lm3533_led_probe(struct platform_device *pdev)
 
 	ret = lm3533_led_setup(led, pdata);
 	if (ret)
-		goto err_unregister;
+		return ret;
 
 	ret = lm3533_ctrlbank_enable(&led->cb);
 	if (ret)
-		goto err_unregister;
+		return ret;
 
 	return 0;
-
-err_unregister:
-	led_classdev_unregister(&led->cdev);
-
-	return ret;
 }
 
 static int lm3533_led_remove(struct platform_device *pdev)
@@ -729,7 +724,6 @@ static int lm3533_led_remove(struct platform_device *pdev)
 	dev_dbg(&pdev->dev, "%s\n", __func__);
 
 	lm3533_ctrlbank_disable(&led->cb);
-	led_classdev_unregister(&led->cdev);
 
 	return 0;
 }
diff --git a/drivers/leds/leds-lp3944.c b/drivers/leds/leds-lp3944.c
index 6c758aea1bbd..be60c181222a 100644
--- a/drivers/leds/leds-lp3944.c
+++ b/drivers/leds/leds-lp3944.c
@@ -199,8 +199,11 @@ static int lp3944_led_set(struct lp3944_led_data *led, u8 status)
 	if (status > LP3944_LED_STATUS_DIM1)
 		return -EINVAL;
 
-	/* invert only 0 and 1, leave unchanged the other values,
-	 * remember we are abusing status to set blink patterns
+	/*
+	 * Invert status only when it's < 2 (i.e. 0 or 1) which means it's
+	 * controlling the on/off state directly.
+	 * When, instead, status is >= 2 don't invert it because it would mean
+	 * to mess with the hardware blinking mode.
 	 */
 	if (led->type == LP3944_LED_TYPE_LED_INVERTED && status < 2)
 		status = 1 - status;
diff --git a/drivers/leds/leds-lp8788.c b/drivers/leds/leds-lp8788.c
index 0eee38fc0565..38c253a43700 100644
--- a/drivers/leds/leds-lp8788.c
+++ b/drivers/leds/leds-lp8788.c
@@ -146,15 +146,13 @@ static int lp8788_led_probe(struct platform_device *pdev)
 
 	mutex_init(&led->lock);
 
-	platform_set_drvdata(pdev, led);
-
 	ret = lp8788_led_init_device(led, led_pdata);
 	if (ret) {
 		dev_err(dev, "led init device err: %d\n", ret);
 		return ret;
 	}
 
-	ret = led_classdev_register(dev, &led->led_dev);
+	ret = devm_led_classdev_register(dev, &led->led_dev);
 	if (ret) {
 		dev_err(dev, "led register err: %d\n", ret);
 		return ret;
@@ -163,18 +161,8 @@ static int lp8788_led_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int lp8788_led_remove(struct platform_device *pdev)
-{
-	struct lp8788_led *led = platform_get_drvdata(pdev);
-
-	led_classdev_unregister(&led->led_dev);
-
-	return 0;
-}
-
 static struct platform_driver lp8788_led_driver = {
 	.probe = lp8788_led_probe,
-	.remove = lp8788_led_remove,
 	.driver = {
 		.name = LP8788_DEV_KEYLED,
 	},
diff --git a/drivers/leds/leds-max8997.c b/drivers/leds/leds-max8997.c
index 01b459069358..4edf74f1d6d4 100644
--- a/drivers/leds/leds-max8997.c
+++ b/drivers/leds/leds-max8997.c
@@ -281,30 +281,18 @@ static int max8997_led_probe(struct platform_device *pdev)
 
 	mutex_init(&led->mutex);
 
-	platform_set_drvdata(pdev, led);
-
-	ret = led_classdev_register(&pdev->dev, &led->cdev);
+	ret = devm_led_classdev_register(&pdev->dev, &led->cdev);
 	if (ret < 0)
 		return ret;
 
 	return 0;
 }
 
-static int max8997_led_remove(struct platform_device *pdev)
-{
-	struct max8997_led *led = platform_get_drvdata(pdev);
-
-	led_classdev_unregister(&led->cdev);
-
-	return 0;
-}
-
 static struct platform_driver max8997_led_driver = {
 	.driver = {
 		.name  = "max8997-led",
 	},
 	.probe  = max8997_led_probe,
-	.remove = max8997_led_remove,
 };
 
 module_platform_driver(max8997_led_driver);
diff --git a/drivers/leds/leds-s3c24xx.c b/drivers/leds/leds-s3c24xx.c
index 83641a7b299a..404da451cb88 100644
--- a/drivers/leds/leds-s3c24xx.c
+++ b/drivers/leds/leds-s3c24xx.c
@@ -29,11 +29,6 @@ struct s3c24xx_gpio_led {
 	struct s3c24xx_led_platdata	*pdata;
 };
 
-static inline struct s3c24xx_gpio_led *pdev_to_gpio(struct platform_device *dev)
-{
-	return platform_get_drvdata(dev);
-}
-
 static inline struct s3c24xx_gpio_led *to_gpio(struct led_classdev *led_cdev)
 {
 	return container_of(led_cdev, struct s3c24xx_gpio_led, cdev);
@@ -59,15 +54,6 @@ static void s3c24xx_led_set(struct led_classdev *led_cdev,
 	}
 }
 
-static int s3c24xx_led_remove(struct platform_device *dev)
-{
-	struct s3c24xx_gpio_led *led = pdev_to_gpio(dev);
-
-	led_classdev_unregister(&led->cdev);
-
-	return 0;
-}
-
 static int s3c24xx_led_probe(struct platform_device *dev)
 {
 	struct s3c24xx_led_platdata *pdata = dev_get_platdata(&dev->dev);
@@ -79,8 +65,6 @@ static int s3c24xx_led_probe(struct platform_device *dev)
 	if (!led)
 		return -ENOMEM;
 
-	platform_set_drvdata(dev, led);
-
 	led->cdev.brightness_set = s3c24xx_led_set;
 	led->cdev.default_trigger = pdata->def_trigger;
 	led->cdev.name = pdata->name;
@@ -104,7 +88,7 @@ static int s3c24xx_led_probe(struct platform_device *dev)
 
 	/* register our new led device */
 
-	ret = led_classdev_register(&dev->dev, &led->cdev);
+	ret = devm_led_classdev_register(&dev->dev, &led->cdev);
 	if (ret < 0)
 		dev_err(&dev->dev, "led_classdev_register failed\n");
 
@@ -113,7 +97,6 @@ static int s3c24xx_led_probe(struct platform_device *dev)
 
 static struct platform_driver s3c24xx_led_driver = {
 	.probe		= s3c24xx_led_probe,
-	.remove		= s3c24xx_led_remove,
 	.driver		= {
 		.name		= "s3c24xx_led",
 	},
diff --git a/drivers/leds/leds-wm831x-status.c b/drivers/leds/leds-wm831x-status.c
index 64a22263e7fc..be93b20e792a 100644
--- a/drivers/leds/leds-wm831x-status.c
+++ b/drivers/leds/leds-wm831x-status.c
@@ -239,7 +239,6 @@ static int wm831x_status_probe(struct platform_device *pdev)
 			       GFP_KERNEL);
 	if (!drvdata)
 		return -ENOMEM;
-	platform_set_drvdata(pdev, drvdata);
 
 	drvdata->wm831x = wm831x;
 	drvdata->reg = res->start;
@@ -284,7 +283,7 @@ static int wm831x_status_probe(struct platform_device *pdev)
 	drvdata->cdev.blink_set = wm831x_status_blink_set;
 	drvdata->cdev.groups = wm831x_status_groups;
 
-	ret = led_classdev_register(wm831x->dev, &drvdata->cdev);
+	ret = devm_led_classdev_register(wm831x->dev, &drvdata->cdev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Failed to register LED: %d\n", ret);
 		return ret;
@@ -293,21 +292,11 @@ static int wm831x_status_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int wm831x_status_remove(struct platform_device *pdev)
-{
-	struct wm831x_status *drvdata = platform_get_drvdata(pdev);
-
-	led_classdev_unregister(&drvdata->cdev);
-
-	return 0;
-}
-
 static struct platform_driver wm831x_status_driver = {
 	.driver = {
 		   .name = "wm831x-status",
 		   },
 	.probe = wm831x_status_probe,
-	.remove = wm831x_status_remove,
 };
 
 module_platform_driver(wm831x_status_driver);
diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index 33224cb91c5b..9f6acd5d1d2e 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -572,11 +572,13 @@ int nvm_register(struct request_queue *q, char *disk_name,
 		}
 	}
 
-	ret = nvm_get_sysblock(dev, &dev->sb);
-	if (!ret)
-		pr_err("nvm: device not initialized.\n");
-	else if (ret < 0)
-		pr_err("nvm: err (%d) on device initialization\n", ret);
+	if (dev->identity.cap & NVM_ID_DCAP_BBLKMGMT) {
+		ret = nvm_get_sysblock(dev, &dev->sb);
+		if (!ret)
+			pr_err("nvm: device not initialized.\n");
+		else if (ret < 0)
+			pr_err("nvm: err (%d) on device initialization\n", ret);
+	}
 
 	/* register device with a supported media manager */
 	down_write(&nvm_lock);
@@ -1055,9 +1057,11 @@ static long __nvm_ioctl_dev_init(struct nvm_ioctl_dev_init *init)
 	strncpy(info.mmtype, init->mmtype, NVM_MMTYPE_LEN);
 	info.fs_ppa.ppa = -1;
 
-	ret = nvm_init_sysblock(dev, &info);
-	if (ret)
-		return ret;
+	if (dev->identity.cap & NVM_ID_DCAP_BBLKMGMT) {
+		ret = nvm_init_sysblock(dev, &info);
+		if (ret)
+			return ret;
+	}
 
 	memcpy(&dev->sb, &info, sizeof(struct nvm_sb_info));
 
@@ -1117,7 +1121,10 @@ static long nvm_ioctl_dev_factory(struct file *file, void __user *arg)
 		dev->mt = NULL;
 	}
 
-	return nvm_dev_factory(dev, fact.flags);
+	if (dev->identity.cap & NVM_ID_DCAP_BBLKMGMT)
+		return nvm_dev_factory(dev, fact.flags);
+
+	return 0;
 }
 
 static long nvm_ctl_ioctl(struct file *file, uint cmd, unsigned long arg)
diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c
index d8c75958ced3..307db1ea22de 100644
--- a/drivers/lightnvm/rrpc.c
+++ b/drivers/lightnvm/rrpc.c
@@ -300,8 +300,10 @@ static int rrpc_move_valid_pages(struct rrpc *rrpc, struct rrpc_block *rblk)
 	}
 
 	page = mempool_alloc(rrpc->page_pool, GFP_NOIO);
-	if (!page)
+	if (!page) {
+		bio_put(bio);
 		return -ENOMEM;
+	}
 
 	while ((slot = find_first_zero_bit(rblk->invalid_pages,
 					    nr_pgs_per_blk)) < nr_pgs_per_blk) {
diff --git a/drivers/lightnvm/rrpc.h b/drivers/lightnvm/rrpc.h
index ef13ac7700c8..f7b37336353f 100644
--- a/drivers/lightnvm/rrpc.h
+++ b/drivers/lightnvm/rrpc.h
@@ -174,8 +174,7 @@ static inline sector_t rrpc_get_sector(sector_t laddr)
 static inline int request_intersects(struct rrpc_inflight_rq *r,
 				sector_t laddr_start, sector_t laddr_end)
 {
-	return (laddr_end >= r->l_start && laddr_end <= r->l_end) &&
-		(laddr_start >= r->l_start && laddr_start <= r->l_end);
+	return (laddr_end >= r->l_start) && (laddr_start <= r->l_end);
 }
 
 static int __rrpc_lock_laddr(struct rrpc *rrpc, sector_t laddr,
@@ -184,6 +183,8 @@ static int __rrpc_lock_laddr(struct rrpc *rrpc, sector_t laddr,
 	sector_t laddr_end = laddr + pages - 1;
 	struct rrpc_inflight_rq *rtmp;
 
+	WARN_ON(irqs_disabled());
+
 	spin_lock_irq(&rrpc->inflights.lock);
 	list_for_each_entry(rtmp, &rrpc->inflights.reqs, list) {
 		if (unlikely(request_intersects(rtmp, laddr, laddr_end))) {
diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c
index 4f12c6f01fe7..b6819f0fc608 100644
--- a/drivers/macintosh/macio_asic.c
+++ b/drivers/macintosh/macio_asic.c
@@ -31,7 +31,6 @@
 #include <asm/macio.h>
 #include <asm/pmac_feature.h>
 #include <asm/prom.h>
-#include <asm/pci-bridge.h>
 
 #undef DEBUG
 
diff --git a/drivers/mailbox/pcc.c b/drivers/mailbox/pcc.c
index 8f779a1ec99c..0ddf638d60f3 100644
--- a/drivers/mailbox/pcc.c
+++ b/drivers/mailbox/pcc.c
@@ -63,6 +63,7 @@
 #include <linux/platform_device.h>
 #include <linux/mailbox_controller.h>
 #include <linux/mailbox_client.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
 
 #include "mailbox.h"
 
@@ -70,6 +71,9 @@
 
 static struct mbox_chan *pcc_mbox_channels;
 
+/* Array of cached virtual address for doorbell registers */
+static void __iomem **pcc_doorbell_vaddr;
+
 static struct mbox_controller pcc_mbox_ctrl = {};
 /**
  * get_pcc_channel - Given a PCC subspace idx, get
@@ -160,6 +164,66 @@ void pcc_mbox_free_channel(struct mbox_chan *chan)
 }
 EXPORT_SYMBOL_GPL(pcc_mbox_free_channel);
 
+/*
+ * PCC can be used with perf critical drivers such as CPPC
+ * So it makes sense to locally cache the virtual address and
+ * use it to read/write to PCC registers such as doorbell register
+ *
+ * The below read_register and write_registers are used to read and
+ * write from perf critical registers such as PCC doorbell register
+ */
+static int read_register(void __iomem *vaddr, u64 *val, unsigned int bit_width)
+{
+	int ret_val = 0;
+
+	switch (bit_width) {
+	case 8:
+		*val = readb(vaddr);
+		break;
+	case 16:
+		*val = readw(vaddr);
+		break;
+	case 32:
+		*val = readl(vaddr);
+		break;
+	case 64:
+		*val = readq(vaddr);
+		break;
+	default:
+		pr_debug("Error: Cannot read register of %u bit width",
+			bit_width);
+		ret_val = -EFAULT;
+		break;
+	}
+	return ret_val;
+}
+
+static int write_register(void __iomem *vaddr, u64 val, unsigned int bit_width)
+{
+	int ret_val = 0;
+
+	switch (bit_width) {
+	case 8:
+		writeb(val, vaddr);
+		break;
+	case 16:
+		writew(val, vaddr);
+		break;
+	case 32:
+		writel(val, vaddr);
+		break;
+	case 64:
+		writeq(val, vaddr);
+		break;
+	default:
+		pr_debug("Error: Cannot write register of %u bit width",
+			bit_width);
+		ret_val = -EFAULT;
+		break;
+	}
+	return ret_val;
+}
+
 /**
  * pcc_send_data - Called from Mailbox Controller code. Used
  *		here only to ring the channel doorbell. The PCC client
@@ -175,21 +239,39 @@ EXPORT_SYMBOL_GPL(pcc_mbox_free_channel);
 static int pcc_send_data(struct mbox_chan *chan, void *data)
 {
 	struct acpi_pcct_hw_reduced *pcct_ss = chan->con_priv;
-	struct acpi_generic_address doorbell;
+	struct acpi_generic_address *doorbell;
 	u64 doorbell_preserve;
 	u64 doorbell_val;
 	u64 doorbell_write;
+	u32 id = chan - pcc_mbox_channels;
+	int ret = 0;
+
+	if (id >= pcc_mbox_ctrl.num_chans) {
+		pr_debug("pcc_send_data: Invalid mbox_chan passed\n");
+		return -ENOENT;
+	}
 
-	doorbell = pcct_ss->doorbell_register;
+	doorbell = &pcct_ss->doorbell_register;
 	doorbell_preserve = pcct_ss->preserve_mask;
 	doorbell_write = pcct_ss->write_mask;
 
 	/* Sync notification from OS to Platform. */
-	acpi_read(&doorbell_val, &doorbell);
-	acpi_write((doorbell_val & doorbell_preserve) | doorbell_write,
-			&doorbell);
-
-	return 0;
+	if (pcc_doorbell_vaddr[id]) {
+		ret = read_register(pcc_doorbell_vaddr[id], &doorbell_val,
+			doorbell->bit_width);
+		if (ret)
+			return ret;
+		ret = write_register(pcc_doorbell_vaddr[id],
+			(doorbell_val & doorbell_preserve) | doorbell_write,
+			doorbell->bit_width);
+	} else {
+		ret = acpi_read(&doorbell_val, doorbell);
+		if (ret)
+			return ret;
+		ret = acpi_write((doorbell_val & doorbell_preserve) | doorbell_write,
+			doorbell);
+	}
+	return ret;
 }
 
 static const struct mbox_chan_ops pcc_chan_ops = {
@@ -265,14 +347,29 @@ static int __init acpi_pcc_probe(void)
 		return -ENOMEM;
 	}
 
+	pcc_doorbell_vaddr = kcalloc(count, sizeof(void *), GFP_KERNEL);
+	if (!pcc_doorbell_vaddr) {
+		kfree(pcc_mbox_channels);
+		return -ENOMEM;
+	}
+
 	/* Point to the first PCC subspace entry */
 	pcct_entry = (struct acpi_subtable_header *) (
 		(unsigned long) pcct_tbl + sizeof(struct acpi_table_pcct));
 
 	for (i = 0; i < count; i++) {
+		struct acpi_generic_address *db_reg;
+		struct acpi_pcct_hw_reduced *pcct_ss;
 		pcc_mbox_channels[i].con_priv = pcct_entry;
 		pcct_entry = (struct acpi_subtable_header *)
 			((unsigned long) pcct_entry + pcct_entry->length);
+
+		/* If doorbell is in system memory cache the virt address */
+		pcct_ss = (struct acpi_pcct_hw_reduced *)pcct_entry;
+		db_reg = &pcct_ss->doorbell_register;
+		if (db_reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
+			pcc_doorbell_vaddr[i] = acpi_os_ioremap(db_reg->address,
+							db_reg->bit_width/8);
 	}
 
 	pcc_mbox_ctrl.num_chans = count;
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 0a2e7273db9e..02a5345a44a6 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -249,6 +249,7 @@ config DM_DEBUG_BLOCK_STACK_TRACING
 	 block manager locking used by thin provisioning and caching.
 
 	 If unsure, say N.
+
 config DM_BIO_PRISON
        tristate
        depends on BLK_DEV_DM
@@ -304,16 +305,6 @@ config DM_CACHE
          algorithms used to select which blocks are promoted, demoted,
          cleaned etc.  It supports writeback and writethrough modes.
 
-config DM_CACHE_MQ
-       tristate "MQ Cache Policy (EXPERIMENTAL)"
-       depends on DM_CACHE
-       default y
-       ---help---
-         A cache policy that uses a multiqueue ordered by recent hit
-         count to select which blocks should be promoted and demoted.
-         This is meant to be a general purpose policy.  It prioritises
-         reads over writes.
-
 config DM_CACHE_SMQ
        tristate "Stochastic MQ Cache Policy (EXPERIMENTAL)"
        depends on DM_CACHE
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 62a65764e8e0..52ba8dd82821 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -12,7 +12,6 @@ dm-log-userspace-y \
 		+= dm-log-userspace-base.o dm-log-userspace-transfer.o
 dm-thin-pool-y	+= dm-thin.o dm-thin-metadata.o
 dm-cache-y	+= dm-cache-target.o dm-cache-metadata.o dm-cache-policy.o
-dm-cache-mq-y   += dm-cache-policy-mq.o
 dm-cache-smq-y   += dm-cache-policy-smq.o
 dm-cache-cleaner-y += dm-cache-policy-cleaner.o
 dm-era-y	+= dm-era-target.o
@@ -55,7 +54,6 @@ obj-$(CONFIG_DM_RAID)	+= dm-raid.o
 obj-$(CONFIG_DM_THIN_PROVISIONING)	+= dm-thin-pool.o
 obj-$(CONFIG_DM_VERITY)		+= dm-verity.o
 obj-$(CONFIG_DM_CACHE)		+= dm-cache.o
-obj-$(CONFIG_DM_CACHE_MQ)	+= dm-cache-mq.o
 obj-$(CONFIG_DM_CACHE_SMQ)	+= dm-cache-smq.o
 obj-$(CONFIG_DM_CACHE_CLEANER)	+= dm-cache-cleaner.o
 obj-$(CONFIG_DM_ERA)		+= dm-era.o
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index f6543f3a970f..27f2ef300f8b 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -867,19 +867,40 @@ static int blocks_are_unmapped_or_clean(struct dm_cache_metadata *cmd,
 	return 0;
 }
 
-#define WRITE_LOCK(cmd) \
-	if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) \
+#define WRITE_LOCK(cmd)	\
+	down_write(&cmd->root_lock); \
+	if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) { \
+		up_write(&cmd->root_lock); \
 		return -EINVAL; \
-	down_write(&cmd->root_lock)
+	}
 
 #define WRITE_LOCK_VOID(cmd) \
-	if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) \
+	down_write(&cmd->root_lock); \
+	if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) { \
+		up_write(&cmd->root_lock); \
 		return; \
-	down_write(&cmd->root_lock)
+	}
 
 #define WRITE_UNLOCK(cmd) \
 	up_write(&cmd->root_lock)
 
+#define READ_LOCK(cmd) \
+	down_read(&cmd->root_lock); \
+	if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) { \
+		up_read(&cmd->root_lock); \
+		return -EINVAL; \
+	}
+
+#define READ_LOCK_VOID(cmd)	\
+	down_read(&cmd->root_lock); \
+	if (cmd->fail_io || dm_bm_is_read_only(cmd->bm)) { \
+		up_read(&cmd->root_lock); \
+		return; \
+	}
+
+#define READ_UNLOCK(cmd) \
+	up_read(&cmd->root_lock)
+
 int dm_cache_resize(struct dm_cache_metadata *cmd, dm_cblock_t new_cache_size)
 {
 	int r;
@@ -1015,22 +1036,20 @@ int dm_cache_load_discards(struct dm_cache_metadata *cmd,
 {
 	int r;
 
-	down_read(&cmd->root_lock);
+	READ_LOCK(cmd);
 	r = __load_discards(cmd, fn, context);
-	up_read(&cmd->root_lock);
+	READ_UNLOCK(cmd);
 
 	return r;
 }
 
-dm_cblock_t dm_cache_size(struct dm_cache_metadata *cmd)
+int dm_cache_size(struct dm_cache_metadata *cmd, dm_cblock_t *result)
 {
-	dm_cblock_t r;
+	READ_LOCK(cmd);
+	*result = cmd->cache_blocks;
+	READ_UNLOCK(cmd);
 
-	down_read(&cmd->root_lock);
-	r = cmd->cache_blocks;
-	up_read(&cmd->root_lock);
-
-	return r;
+	return 0;
 }
 
 static int __remove(struct dm_cache_metadata *cmd, dm_cblock_t cblock)
@@ -1188,9 +1207,9 @@ int dm_cache_load_mappings(struct dm_cache_metadata *cmd,
 {
 	int r;
 
-	down_read(&cmd->root_lock);
+	READ_LOCK(cmd);
 	r = __load_mappings(cmd, policy, fn, context);
-	up_read(&cmd->root_lock);
+	READ_UNLOCK(cmd);
 
 	return r;
 }
@@ -1215,18 +1234,18 @@ static int __dump_mappings(struct dm_cache_metadata *cmd)
 
 void dm_cache_dump(struct dm_cache_metadata *cmd)
 {
-	down_read(&cmd->root_lock);
+	READ_LOCK_VOID(cmd);
 	__dump_mappings(cmd);
-	up_read(&cmd->root_lock);
+	READ_UNLOCK(cmd);
 }
 
 int dm_cache_changed_this_transaction(struct dm_cache_metadata *cmd)
 {
 	int r;
 
-	down_read(&cmd->root_lock);
+	READ_LOCK(cmd);
 	r = cmd->changed;
-	up_read(&cmd->root_lock);
+	READ_UNLOCK(cmd);
 
 	return r;
 }
@@ -1276,9 +1295,9 @@ int dm_cache_set_dirty(struct dm_cache_metadata *cmd,
 void dm_cache_metadata_get_stats(struct dm_cache_metadata *cmd,
 				 struct dm_cache_statistics *stats)
 {
-	down_read(&cmd->root_lock);
+	READ_LOCK_VOID(cmd);
 	*stats = cmd->stats;
-	up_read(&cmd->root_lock);
+	READ_UNLOCK(cmd);
 }
 
 void dm_cache_metadata_set_stats(struct dm_cache_metadata *cmd,
@@ -1312,9 +1331,9 @@ int dm_cache_get_free_metadata_block_count(struct dm_cache_metadata *cmd,
 {
 	int r = -EINVAL;
 
-	down_read(&cmd->root_lock);
+	READ_LOCK(cmd);
 	r = dm_sm_get_nr_free(cmd->metadata_sm, result);
-	up_read(&cmd->root_lock);
+	READ_UNLOCK(cmd);
 
 	return r;
 }
@@ -1324,9 +1343,9 @@ int dm_cache_get_metadata_dev_size(struct dm_cache_metadata *cmd,
 {
 	int r = -EINVAL;
 
-	down_read(&cmd->root_lock);
+	READ_LOCK(cmd);
 	r = dm_sm_get_nr_blocks(cmd->metadata_sm, result);
-	up_read(&cmd->root_lock);
+	READ_UNLOCK(cmd);
 
 	return r;
 }
@@ -1417,7 +1436,13 @@ int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *
 
 int dm_cache_metadata_all_clean(struct dm_cache_metadata *cmd, bool *result)
 {
-	return blocks_are_unmapped_or_clean(cmd, 0, cmd->cache_blocks, result);
+	int r;
+
+	READ_LOCK(cmd);
+	r = blocks_are_unmapped_or_clean(cmd, 0, cmd->cache_blocks, result);
+	READ_UNLOCK(cmd);
+
+	return r;
 }
 
 void dm_cache_metadata_set_read_only(struct dm_cache_metadata *cmd)
@@ -1440,10 +1465,7 @@ int dm_cache_metadata_set_needs_check(struct dm_cache_metadata *cmd)
 	struct dm_block *sblock;
 	struct cache_disk_superblock *disk_super;
 
-	/*
-	 * We ignore fail_io for this function.
-	 */
-	down_write(&cmd->root_lock);
+	WRITE_LOCK(cmd);
 	set_bit(NEEDS_CHECK, &cmd->flags);
 
 	r = superblock_lock(cmd, &sblock);
@@ -1458,19 +1480,17 @@ int dm_cache_metadata_set_needs_check(struct dm_cache_metadata *cmd)
 	dm_bm_unlock(sblock);
 
 out:
-	up_write(&cmd->root_lock);
+	WRITE_UNLOCK(cmd);
 	return r;
 }
 
-bool dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd)
+int dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd, bool *result)
 {
-	bool needs_check;
+	READ_LOCK(cmd);
+	*result = !!test_bit(NEEDS_CHECK, &cmd->flags);
+	READ_UNLOCK(cmd);
 
-	down_read(&cmd->root_lock);
-	needs_check = !!test_bit(NEEDS_CHECK, &cmd->flags);
-	up_read(&cmd->root_lock);
-
-	return needs_check;
+	return 0;
 }
 
 int dm_cache_metadata_abort(struct dm_cache_metadata *cmd)
diff --git a/drivers/md/dm-cache-metadata.h b/drivers/md/dm-cache-metadata.h
index 2ffee21f318d..8528744195e5 100644
--- a/drivers/md/dm-cache-metadata.h
+++ b/drivers/md/dm-cache-metadata.h
@@ -66,7 +66,7 @@ void dm_cache_metadata_close(struct dm_cache_metadata *cmd);
  * origin blocks to map to.
  */
 int dm_cache_resize(struct dm_cache_metadata *cmd, dm_cblock_t new_cache_size);
-dm_cblock_t dm_cache_size(struct dm_cache_metadata *cmd);
+int dm_cache_size(struct dm_cache_metadata *cmd, dm_cblock_t *result);
 
 int dm_cache_discard_bitset_resize(struct dm_cache_metadata *cmd,
 				   sector_t discard_block_size,
@@ -137,7 +137,7 @@ int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *
  */
 int dm_cache_metadata_all_clean(struct dm_cache_metadata *cmd, bool *result);
 
-bool dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd);
+int dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd, bool *result);
 int dm_cache_metadata_set_needs_check(struct dm_cache_metadata *cmd);
 void dm_cache_metadata_set_read_only(struct dm_cache_metadata *cmd);
 void dm_cache_metadata_set_read_write(struct dm_cache_metadata *cmd);
diff --git a/drivers/md/dm-cache-policy-mq.c b/drivers/md/dm-cache-policy-mq.c
deleted file mode 100644
index ddb26980cd66..000000000000
--- a/drivers/md/dm-cache-policy-mq.c
+++ /dev/null
@@ -1,1473 +0,0 @@
-/*
- * Copyright (C) 2012 Red Hat. All rights reserved.
- *
- * This file is released under the GPL.
- */
-
-#include "dm-cache-policy.h"
-#include "dm.h"
-
-#include <linux/hash.h>
-#include <linux/jiffies.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/slab.h>
-#include <linux/vmalloc.h>
-
-#define DM_MSG_PREFIX "cache-policy-mq"
-
-static struct kmem_cache *mq_entry_cache;
-
-/*----------------------------------------------------------------*/
-
-static unsigned next_power(unsigned n, unsigned min)
-{
-	return roundup_pow_of_two(max(n, min));
-}
-
-/*----------------------------------------------------------------*/
-
-/*
- * Large, sequential ios are probably better left on the origin device since
- * spindles tend to have good bandwidth.
- *
- * The io_tracker tries to spot when the io is in one of these sequential
- * modes.
- *
- * Two thresholds to switch between random and sequential io mode are defaulting
- * as follows and can be adjusted via the constructor and message interfaces.
- */
-#define RANDOM_THRESHOLD_DEFAULT 4
-#define SEQUENTIAL_THRESHOLD_DEFAULT 512
-
-enum io_pattern {
-	PATTERN_SEQUENTIAL,
-	PATTERN_RANDOM
-};
-
-struct io_tracker {
-	enum io_pattern pattern;
-
-	unsigned nr_seq_samples;
-	unsigned nr_rand_samples;
-	unsigned thresholds[2];
-
-	dm_oblock_t last_end_oblock;
-};
-
-static void iot_init(struct io_tracker *t,
-		     int sequential_threshold, int random_threshold)
-{
-	t->pattern = PATTERN_RANDOM;
-	t->nr_seq_samples = 0;
-	t->nr_rand_samples = 0;
-	t->last_end_oblock = 0;
-	t->thresholds[PATTERN_RANDOM] = random_threshold;
-	t->thresholds[PATTERN_SEQUENTIAL] = sequential_threshold;
-}
-
-static enum io_pattern iot_pattern(struct io_tracker *t)
-{
-	return t->pattern;
-}
-
-static void iot_update_stats(struct io_tracker *t, struct bio *bio)
-{
-	if (bio->bi_iter.bi_sector == from_oblock(t->last_end_oblock) + 1)
-		t->nr_seq_samples++;
-	else {
-		/*
-		 * Just one non-sequential IO is enough to reset the
-		 * counters.
-		 */
-		if (t->nr_seq_samples) {
-			t->nr_seq_samples = 0;
-			t->nr_rand_samples = 0;
-		}
-
-		t->nr_rand_samples++;
-	}
-
-	t->last_end_oblock = to_oblock(bio_end_sector(bio) - 1);
-}
-
-static void iot_check_for_pattern_switch(struct io_tracker *t)
-{
-	switch (t->pattern) {
-	case PATTERN_SEQUENTIAL:
-		if (t->nr_rand_samples >= t->thresholds[PATTERN_RANDOM]) {
-			t->pattern = PATTERN_RANDOM;
-			t->nr_seq_samples = t->nr_rand_samples = 0;
-		}
-		break;
-
-	case PATTERN_RANDOM:
-		if (t->nr_seq_samples >= t->thresholds[PATTERN_SEQUENTIAL]) {
-			t->pattern = PATTERN_SEQUENTIAL;
-			t->nr_seq_samples = t->nr_rand_samples = 0;
-		}
-		break;
-	}
-}
-
-static void iot_examine_bio(struct io_tracker *t, struct bio *bio)
-{
-	iot_update_stats(t, bio);
-	iot_check_for_pattern_switch(t);
-}
-
-/*----------------------------------------------------------------*/
-
-
-/*
- * This queue is divided up into different levels.  Allowing us to push
- * entries to the back of any of the levels.  Think of it as a partially
- * sorted queue.
- */
-#define NR_QUEUE_LEVELS 16u
-#define NR_SENTINELS NR_QUEUE_LEVELS * 3
-
-#define WRITEBACK_PERIOD HZ
-
-struct queue {
-	unsigned nr_elts;
-	bool current_writeback_sentinels;
-	unsigned long next_writeback;
-	struct list_head qs[NR_QUEUE_LEVELS];
-	struct list_head sentinels[NR_SENTINELS];
-};
-
-static void queue_init(struct queue *q)
-{
-	unsigned i;
-
-	q->nr_elts = 0;
-	q->current_writeback_sentinels = false;
-	q->next_writeback = 0;
-	for (i = 0; i < NR_QUEUE_LEVELS; i++) {
-		INIT_LIST_HEAD(q->qs + i);
-		INIT_LIST_HEAD(q->sentinels + i);
-		INIT_LIST_HEAD(q->sentinels + NR_QUEUE_LEVELS + i);
-		INIT_LIST_HEAD(q->sentinels + (2 * NR_QUEUE_LEVELS) + i);
-	}
-}
-
-static unsigned queue_size(struct queue *q)
-{
-	return q->nr_elts;
-}
-
-static bool queue_empty(struct queue *q)
-{
-	return q->nr_elts == 0;
-}
-
-/*
- * Insert an entry to the back of the given level.
- */
-static void queue_push(struct queue *q, unsigned level, struct list_head *elt)
-{
-	q->nr_elts++;
-	list_add_tail(elt, q->qs + level);
-}
-
-static void queue_remove(struct queue *q, struct list_head *elt)
-{
-	q->nr_elts--;
-	list_del(elt);
-}
-
-static bool is_sentinel(struct queue *q, struct list_head *h)
-{
-	return (h >= q->sentinels) && (h < (q->sentinels + NR_SENTINELS));
-}
-
-/*
- * Gives us the oldest entry of the lowest popoulated level.  If the first
- * level is emptied then we shift down one level.
- */
-static struct list_head *queue_peek(struct queue *q)
-{
-	unsigned level;
-	struct list_head *h;
-
-	for (level = 0; level < NR_QUEUE_LEVELS; level++)
-		list_for_each(h, q->qs + level)
-			if (!is_sentinel(q, h))
-				return h;
-
-	return NULL;
-}
-
-static struct list_head *queue_pop(struct queue *q)
-{
-	struct list_head *r = queue_peek(q);
-
-	if (r) {
-		q->nr_elts--;
-		list_del(r);
-	}
-
-	return r;
-}
-
-/*
- * Pops an entry from a level that is not past a sentinel.
- */
-static struct list_head *queue_pop_old(struct queue *q)
-{
-	unsigned level;
-	struct list_head *h;
-
-	for (level = 0; level < NR_QUEUE_LEVELS; level++)
-		list_for_each(h, q->qs + level) {
-			if (is_sentinel(q, h))
-				break;
-
-			q->nr_elts--;
-			list_del(h);
-			return h;
-		}
-
-	return NULL;
-}
-
-static struct list_head *list_pop(struct list_head *lh)
-{
-	struct list_head *r = lh->next;
-
-	BUG_ON(!r);
-	list_del_init(r);
-
-	return r;
-}
-
-static struct list_head *writeback_sentinel(struct queue *q, unsigned level)
-{
-	if (q->current_writeback_sentinels)
-		return q->sentinels + NR_QUEUE_LEVELS + level;
-	else
-		return q->sentinels + 2 * NR_QUEUE_LEVELS + level;
-}
-
-static void queue_update_writeback_sentinels(struct queue *q)
-{
-	unsigned i;
-	struct list_head *h;
-
-	if (time_after(jiffies, q->next_writeback)) {
-		for (i = 0; i < NR_QUEUE_LEVELS; i++) {
-			h = writeback_sentinel(q, i);
-			list_del(h);
-			list_add_tail(h, q->qs + i);
-		}
-
-		q->next_writeback = jiffies + WRITEBACK_PERIOD;
-		q->current_writeback_sentinels = !q->current_writeback_sentinels;
-	}
-}
-
-/*
- * Sometimes we want to iterate through entries that have been pushed since
- * a certain event.  We use sentinel entries on the queues to delimit these
- * 'tick' events.
- */
-static void queue_tick(struct queue *q)
-{
-	unsigned i;
-
-	for (i = 0; i < NR_QUEUE_LEVELS; i++) {
-		list_del(q->sentinels + i);
-		list_add_tail(q->sentinels + i, q->qs + i);
-	}
-}
-
-typedef void (*iter_fn)(struct list_head *, void *);
-static void queue_iterate_tick(struct queue *q, iter_fn fn, void *context)
-{
-	unsigned i;
-	struct list_head *h;
-
-	for (i = 0; i < NR_QUEUE_LEVELS; i++) {
-		list_for_each_prev(h, q->qs + i) {
-			if (is_sentinel(q, h))
-				break;
-
-			fn(h, context);
-		}
-	}
-}
-
-/*----------------------------------------------------------------*/
-
-/*
- * Describes a cache entry.  Used in both the cache and the pre_cache.
- */
-struct entry {
-	struct hlist_node hlist;
-	struct list_head list;
-	dm_oblock_t oblock;
-
-	/*
-	 * FIXME: pack these better
-	 */
-	bool dirty:1;
-	unsigned hit_count;
-};
-
-/*
- * Rather than storing the cblock in an entry, we allocate all entries in
- * an array, and infer the cblock from the entry position.
- *
- * Free entries are linked together into a list.
- */
-struct entry_pool {
-	struct entry *entries, *entries_end;
-	struct list_head free;
-	unsigned nr_allocated;
-};
-
-static int epool_init(struct entry_pool *ep, unsigned nr_entries)
-{
-	unsigned i;
-
-	ep->entries = vzalloc(sizeof(struct entry) * nr_entries);
-	if (!ep->entries)
-		return -ENOMEM;
-
-	ep->entries_end = ep->entries + nr_entries;
-
-	INIT_LIST_HEAD(&ep->free);
-	for (i = 0; i < nr_entries; i++)
-		list_add(&ep->entries[i].list, &ep->free);
-
-	ep->nr_allocated = 0;
-
-	return 0;
-}
-
-static void epool_exit(struct entry_pool *ep)
-{
-	vfree(ep->entries);
-}
-
-static struct entry *alloc_entry(struct entry_pool *ep)
-{
-	struct entry *e;
-
-	if (list_empty(&ep->free))
-		return NULL;
-
-	e = list_entry(list_pop(&ep->free), struct entry, list);
-	INIT_LIST_HEAD(&e->list);
-	INIT_HLIST_NODE(&e->hlist);
-	ep->nr_allocated++;
-
-	return e;
-}
-
-/*
- * This assumes the cblock hasn't already been allocated.
- */
-static struct entry *alloc_particular_entry(struct entry_pool *ep, dm_cblock_t cblock)
-{
-	struct entry *e = ep->entries + from_cblock(cblock);
-
-	list_del_init(&e->list);
-	INIT_HLIST_NODE(&e->hlist);
-	ep->nr_allocated++;
-
-	return e;
-}
-
-static void free_entry(struct entry_pool *ep, struct entry *e)
-{
-	BUG_ON(!ep->nr_allocated);
-	ep->nr_allocated--;
-	INIT_HLIST_NODE(&e->hlist);
-	list_add(&e->list, &ep->free);
-}
-
-/*
- * Returns NULL if the entry is free.
- */
-static struct entry *epool_find(struct entry_pool *ep, dm_cblock_t cblock)
-{
-	struct entry *e = ep->entries + from_cblock(cblock);
-	return !hlist_unhashed(&e->hlist) ? e : NULL;
-}
-
-static bool epool_empty(struct entry_pool *ep)
-{
-	return list_empty(&ep->free);
-}
-
-static bool in_pool(struct entry_pool *ep, struct entry *e)
-{
-	return e >= ep->entries && e < ep->entries_end;
-}
-
-static dm_cblock_t infer_cblock(struct entry_pool *ep, struct entry *e)
-{
-	return to_cblock(e - ep->entries);
-}
-
-/*----------------------------------------------------------------*/
-
-struct mq_policy {
-	struct dm_cache_policy policy;
-
-	/* protects everything */
-	struct mutex lock;
-	dm_cblock_t cache_size;
-	struct io_tracker tracker;
-
-	/*
-	 * Entries come from two pools, one of pre-cache entries, and one
-	 * for the cache proper.
-	 */
-	struct entry_pool pre_cache_pool;
-	struct entry_pool cache_pool;
-
-	/*
-	 * We maintain three queues of entries.  The cache proper,
-	 * consisting of a clean and dirty queue, contains the currently
-	 * active mappings.  Whereas the pre_cache tracks blocks that
-	 * are being hit frequently and potential candidates for promotion
-	 * to the cache.
-	 */
-	struct queue pre_cache;
-	struct queue cache_clean;
-	struct queue cache_dirty;
-
-	/*
-	 * Keeps track of time, incremented by the core.  We use this to
-	 * avoid attributing multiple hits within the same tick.
-	 *
-	 * Access to tick_protected should be done with the spin lock held.
-	 * It's copied to tick at the start of the map function (within the
-	 * mutex).
-	 */
-	spinlock_t tick_lock;
-	unsigned tick_protected;
-	unsigned tick;
-
-	/*
-	 * A count of the number of times the map function has been called
-	 * and found an entry in the pre_cache or cache.  Currently used to
-	 * calculate the generation.
-	 */
-	unsigned hit_count;
-
-	/*
-	 * A generation is a longish period that is used to trigger some
-	 * book keeping effects.  eg, decrementing hit counts on entries.
-	 * This is needed to allow the cache to evolve as io patterns
-	 * change.
-	 */
-	unsigned generation;
-	unsigned generation_period; /* in lookups (will probably change) */
-
-	unsigned discard_promote_adjustment;
-	unsigned read_promote_adjustment;
-	unsigned write_promote_adjustment;
-
-	/*
-	 * The hash table allows us to quickly find an entry by origin
-	 * block.  Both pre_cache and cache entries are in here.
-	 */
-	unsigned nr_buckets;
-	dm_block_t hash_bits;
-	struct hlist_head *table;
-};
-
-#define DEFAULT_DISCARD_PROMOTE_ADJUSTMENT 1
-#define DEFAULT_READ_PROMOTE_ADJUSTMENT 4
-#define DEFAULT_WRITE_PROMOTE_ADJUSTMENT 8
-#define DISCOURAGE_DEMOTING_DIRTY_THRESHOLD 128
-
-/*----------------------------------------------------------------*/
-
-/*
- * Simple hash table implementation.  Should replace with the standard hash
- * table that's making its way upstream.
- */
-static void hash_insert(struct mq_policy *mq, struct entry *e)
-{
-	unsigned h = hash_64(from_oblock(e->oblock), mq->hash_bits);
-
-	hlist_add_head(&e->hlist, mq->table + h);
-}
-
-static struct entry *hash_lookup(struct mq_policy *mq, dm_oblock_t oblock)
-{
-	unsigned h = hash_64(from_oblock(oblock), mq->hash_bits);
-	struct hlist_head *bucket = mq->table + h;
-	struct entry *e;
-
-	hlist_for_each_entry(e, bucket, hlist)
-		if (e->oblock == oblock) {
-			hlist_del(&e->hlist);
-			hlist_add_head(&e->hlist, bucket);
-			return e;
-		}
-
-	return NULL;
-}
-
-static void hash_remove(struct entry *e)
-{
-	hlist_del(&e->hlist);
-}
-
-/*----------------------------------------------------------------*/
-
-static bool any_free_cblocks(struct mq_policy *mq)
-{
-	return !epool_empty(&mq->cache_pool);
-}
-
-static bool any_clean_cblocks(struct mq_policy *mq)
-{
-	return !queue_empty(&mq->cache_clean);
-}
-
-/*----------------------------------------------------------------*/
-
-/*
- * Now we get to the meat of the policy.  This section deals with deciding
- * when to to add entries to the pre_cache and cache, and move between
- * them.
- */
-
-/*
- * The queue level is based on the log2 of the hit count.
- */
-static unsigned queue_level(struct entry *e)
-{
-	return min((unsigned) ilog2(e->hit_count), NR_QUEUE_LEVELS - 1u);
-}
-
-static bool in_cache(struct mq_policy *mq, struct entry *e)
-{
-	return in_pool(&mq->cache_pool, e);
-}
-
-/*
- * Inserts the entry into the pre_cache or the cache.  Ensures the cache
- * block is marked as allocated if necc.  Inserts into the hash table.
- * Sets the tick which records when the entry was last moved about.
- */
-static void push(struct mq_policy *mq, struct entry *e)
-{
-	hash_insert(mq, e);
-
-	if (in_cache(mq, e))
-		queue_push(e->dirty ? &mq->cache_dirty : &mq->cache_clean,
-			   queue_level(e), &e->list);
-	else
-		queue_push(&mq->pre_cache, queue_level(e), &e->list);
-}
-
-/*
- * Removes an entry from pre_cache or cache.  Removes from the hash table.
- */
-static void del(struct mq_policy *mq, struct entry *e)
-{
-	if (in_cache(mq, e))
-		queue_remove(e->dirty ? &mq->cache_dirty : &mq->cache_clean, &e->list);
-	else
-		queue_remove(&mq->pre_cache, &e->list);
-
-	hash_remove(e);
-}
-
-/*
- * Like del, except it removes the first entry in the queue (ie. the least
- * recently used).
- */
-static struct entry *pop(struct mq_policy *mq, struct queue *q)
-{
-	struct entry *e;
-	struct list_head *h = queue_pop(q);
-
-	if (!h)
-		return NULL;
-
-	e = container_of(h, struct entry, list);
-	hash_remove(e);
-
-	return e;
-}
-
-static struct entry *pop_old(struct mq_policy *mq, struct queue *q)
-{
-	struct entry *e;
-	struct list_head *h = queue_pop_old(q);
-
-	if (!h)
-		return NULL;
-
-	e = container_of(h, struct entry, list);
-	hash_remove(e);
-
-	return e;
-}
-
-static struct entry *peek(struct queue *q)
-{
-	struct list_head *h = queue_peek(q);
-	return h ? container_of(h, struct entry, list) : NULL;
-}
-
-/*
- * The promotion threshold is adjusted every generation.  As are the counts
- * of the entries.
- *
- * At the moment the threshold is taken by averaging the hit counts of some
- * of the entries in the cache (the first 20 entries across all levels in
- * ascending order, giving preference to the clean entries at each level).
- *
- * We can be much cleverer than this though.  For example, each promotion
- * could bump up the threshold helping to prevent churn.  Much more to do
- * here.
- */
-
-#define MAX_TO_AVERAGE 20
-
-static void check_generation(struct mq_policy *mq)
-{
-	unsigned total = 0, nr = 0, count = 0, level;
-	struct list_head *head;
-	struct entry *e;
-
-	if ((mq->hit_count >= mq->generation_period) && (epool_empty(&mq->cache_pool))) {
-		mq->hit_count = 0;
-		mq->generation++;
-
-		for (level = 0; level < NR_QUEUE_LEVELS && count < MAX_TO_AVERAGE; level++) {
-			head = mq->cache_clean.qs + level;
-			list_for_each_entry(e, head, list) {
-				nr++;
-				total += e->hit_count;
-
-				if (++count >= MAX_TO_AVERAGE)
-					break;
-			}
-
-			head = mq->cache_dirty.qs + level;
-			list_for_each_entry(e, head, list) {
-				nr++;
-				total += e->hit_count;
-
-				if (++count >= MAX_TO_AVERAGE)
-					break;
-			}
-		}
-	}
-}
-
-/*
- * Whenever we use an entry we bump up it's hit counter, and push it to the
- * back to it's current level.
- */
-static void requeue(struct mq_policy *mq, struct entry *e)
-{
-	check_generation(mq);
-	del(mq, e);
-	push(mq, e);
-}
-
-/*
- * Demote the least recently used entry from the cache to the pre_cache.
- * Returns the new cache entry to use, and the old origin block it was
- * mapped to.
- *
- * We drop the hit count on the demoted entry back to 1 to stop it bouncing
- * straight back into the cache if it's subsequently hit.  There are
- * various options here, and more experimentation would be good:
- *
- * - just forget about the demoted entry completely (ie. don't insert it
-     into the pre_cache).
- * - divide the hit count rather that setting to some hard coded value.
- * - set the hit count to a hard coded value other than 1, eg, is it better
- *   if it goes in at level 2?
- */
-static int demote_cblock(struct mq_policy *mq,
-			 struct policy_locker *locker, dm_oblock_t *oblock)
-{
-	struct entry *demoted = peek(&mq->cache_clean);
-
-	if (!demoted)
-		/*
-		 * We could get a block from mq->cache_dirty, but that
-		 * would add extra latency to the triggering bio as it
-		 * waits for the writeback.  Better to not promote this
-		 * time and hope there's a clean block next time this block
-		 * is hit.
-		 */
-		return -ENOSPC;
-
-	if (locker->fn(locker, demoted->oblock))
-		/*
-		 * We couldn't lock the demoted block.
-		 */
-		return -EBUSY;
-
-	del(mq, demoted);
-	*oblock = demoted->oblock;
-	free_entry(&mq->cache_pool, demoted);
-
-	/*
-	 * We used to put the demoted block into the pre-cache, but I think
-	 * it's simpler to just let it work it's way up from zero again.
-	 * Stops blocks flickering in and out of the cache.
-	 */
-
-	return 0;
-}
-
-/*
- * Entries in the pre_cache whose hit count passes the promotion
- * threshold move to the cache proper.  Working out the correct
- * value for the promotion_threshold is crucial to this policy.
- */
-static unsigned promote_threshold(struct mq_policy *mq)
-{
-	struct entry *e;
-
-	if (any_free_cblocks(mq))
-		return 0;
-
-	e = peek(&mq->cache_clean);
-	if (e)
-		return e->hit_count;
-
-	e = peek(&mq->cache_dirty);
-	if (e)
-		return e->hit_count + DISCOURAGE_DEMOTING_DIRTY_THRESHOLD;
-
-	/* This should never happen */
-	return 0;
-}
-
-/*
- * We modify the basic promotion_threshold depending on the specific io.
- *
- * If the origin block has been discarded then there's no cost to copy it
- * to the cache.
- *
- * We bias towards reads, since they can be demoted at no cost if they
- * haven't been dirtied.
- */
-static unsigned adjusted_promote_threshold(struct mq_policy *mq,
-					   bool discarded_oblock, int data_dir)
-{
-	if (data_dir == READ)
-		return promote_threshold(mq) + mq->read_promote_adjustment;
-
-	if (discarded_oblock && (any_free_cblocks(mq) || any_clean_cblocks(mq))) {
-		/*
-		 * We don't need to do any copying at all, so give this a
-		 * very low threshold.
-		 */
-		return mq->discard_promote_adjustment;
-	}
-
-	return promote_threshold(mq) + mq->write_promote_adjustment;
-}
-
-static bool should_promote(struct mq_policy *mq, struct entry *e,
-			   bool discarded_oblock, int data_dir)
-{
-	return e->hit_count >=
-		adjusted_promote_threshold(mq, discarded_oblock, data_dir);
-}
-
-static int cache_entry_found(struct mq_policy *mq,
-			     struct entry *e,
-			     struct policy_result *result)
-{
-	requeue(mq, e);
-
-	if (in_cache(mq, e)) {
-		result->op = POLICY_HIT;
-		result->cblock = infer_cblock(&mq->cache_pool, e);
-	}
-
-	return 0;
-}
-
-/*
- * Moves an entry from the pre_cache to the cache.  The main work is
- * finding which cache block to use.
- */
-static int pre_cache_to_cache(struct mq_policy *mq, struct entry *e,
-			      struct policy_locker *locker,
-			      struct policy_result *result)
-{
-	int r;
-	struct entry *new_e;
-
-	/* Ensure there's a free cblock in the cache */
-	if (epool_empty(&mq->cache_pool)) {
-		result->op = POLICY_REPLACE;
-		r = demote_cblock(mq, locker, &result->old_oblock);
-		if (r) {
-			result->op = POLICY_MISS;
-			return 0;
-		}
-
-	} else
-		result->op = POLICY_NEW;
-
-	new_e = alloc_entry(&mq->cache_pool);
-	BUG_ON(!new_e);
-
-	new_e->oblock = e->oblock;
-	new_e->dirty = false;
-	new_e->hit_count = e->hit_count;
-
-	del(mq, e);
-	free_entry(&mq->pre_cache_pool, e);
-	push(mq, new_e);
-
-	result->cblock = infer_cblock(&mq->cache_pool, new_e);
-
-	return 0;
-}
-
-static int pre_cache_entry_found(struct mq_policy *mq, struct entry *e,
-				 bool can_migrate, bool discarded_oblock,
-				 int data_dir, struct policy_locker *locker,
-				 struct policy_result *result)
-{
-	int r = 0;
-
-	if (!should_promote(mq, e, discarded_oblock, data_dir)) {
-		requeue(mq, e);
-		result->op = POLICY_MISS;
-
-	} else if (!can_migrate)
-		r = -EWOULDBLOCK;
-
-	else {
-		requeue(mq, e);
-		r = pre_cache_to_cache(mq, e, locker, result);
-	}
-
-	return r;
-}
-
-static void insert_in_pre_cache(struct mq_policy *mq,
-				dm_oblock_t oblock)
-{
-	struct entry *e = alloc_entry(&mq->pre_cache_pool);
-
-	if (!e)
-		/*
-		 * There's no spare entry structure, so we grab the least
-		 * used one from the pre_cache.
-		 */
-		e = pop(mq, &mq->pre_cache);
-
-	if (unlikely(!e)) {
-		DMWARN("couldn't pop from pre cache");
-		return;
-	}
-
-	e->dirty = false;
-	e->oblock = oblock;
-	e->hit_count = 1;
-	push(mq, e);
-}
-
-static void insert_in_cache(struct mq_policy *mq, dm_oblock_t oblock,
-			    struct policy_locker *locker,
-			    struct policy_result *result)
-{
-	int r;
-	struct entry *e;
-
-	if (epool_empty(&mq->cache_pool)) {
-		result->op = POLICY_REPLACE;
-		r = demote_cblock(mq, locker, &result->old_oblock);
-		if (unlikely(r)) {
-			result->op = POLICY_MISS;
-			insert_in_pre_cache(mq, oblock);
-			return;
-		}
-
-		/*
-		 * This will always succeed, since we've just demoted.
-		 */
-		e = alloc_entry(&mq->cache_pool);
-		BUG_ON(!e);
-
-	} else {
-		e = alloc_entry(&mq->cache_pool);
-		result->op = POLICY_NEW;
-	}
-
-	e->oblock = oblock;
-	e->dirty = false;
-	e->hit_count = 1;
-	push(mq, e);
-
-	result->cblock = infer_cblock(&mq->cache_pool, e);
-}
-
-static int no_entry_found(struct mq_policy *mq, dm_oblock_t oblock,
-			  bool can_migrate, bool discarded_oblock,
-			  int data_dir, struct policy_locker *locker,
-			  struct policy_result *result)
-{
-	if (adjusted_promote_threshold(mq, discarded_oblock, data_dir) <= 1) {
-		if (can_migrate)
-			insert_in_cache(mq, oblock, locker, result);
-		else
-			return -EWOULDBLOCK;
-	} else {
-		insert_in_pre_cache(mq, oblock);
-		result->op = POLICY_MISS;
-	}
-
-	return 0;
-}
-
-/*
- * Looks the oblock up in the hash table, then decides whether to put in
- * pre_cache, or cache etc.
- */
-static int map(struct mq_policy *mq, dm_oblock_t oblock,
-	       bool can_migrate, bool discarded_oblock,
-	       int data_dir, struct policy_locker *locker,
-	       struct policy_result *result)
-{
-	int r = 0;
-	struct entry *e = hash_lookup(mq, oblock);
-
-	if (e && in_cache(mq, e))
-		r = cache_entry_found(mq, e, result);
-
-	else if (mq->tracker.thresholds[PATTERN_SEQUENTIAL] &&
-		 iot_pattern(&mq->tracker) == PATTERN_SEQUENTIAL)
-		result->op = POLICY_MISS;
-
-	else if (e)
-		r = pre_cache_entry_found(mq, e, can_migrate, discarded_oblock,
-					  data_dir, locker, result);
-
-	else
-		r = no_entry_found(mq, oblock, can_migrate, discarded_oblock,
-				   data_dir, locker, result);
-
-	if (r == -EWOULDBLOCK)
-		result->op = POLICY_MISS;
-
-	return r;
-}
-
-/*----------------------------------------------------------------*/
-
-/*
- * Public interface, via the policy struct.  See dm-cache-policy.h for a
- * description of these.
- */
-
-static struct mq_policy *to_mq_policy(struct dm_cache_policy *p)
-{
-	return container_of(p, struct mq_policy, policy);
-}
-
-static void mq_destroy(struct dm_cache_policy *p)
-{
-	struct mq_policy *mq = to_mq_policy(p);
-
-	vfree(mq->table);
-	epool_exit(&mq->cache_pool);
-	epool_exit(&mq->pre_cache_pool);
-	kfree(mq);
-}
-
-static void update_pre_cache_hits(struct list_head *h, void *context)
-{
-	struct entry *e = container_of(h, struct entry, list);
-	e->hit_count++;
-}
-
-static void update_cache_hits(struct list_head *h, void *context)
-{
-	struct mq_policy *mq = context;
-	struct entry *e = container_of(h, struct entry, list);
-	e->hit_count++;
-	mq->hit_count++;
-}
-
-static void copy_tick(struct mq_policy *mq)
-{
-	unsigned long flags, tick;
-
-	spin_lock_irqsave(&mq->tick_lock, flags);
-	tick = mq->tick_protected;
-	if (tick != mq->tick) {
-		queue_iterate_tick(&mq->pre_cache, update_pre_cache_hits, mq);
-		queue_iterate_tick(&mq->cache_dirty, update_cache_hits, mq);
-		queue_iterate_tick(&mq->cache_clean, update_cache_hits, mq);
-		mq->tick = tick;
-	}
-
-	queue_tick(&mq->pre_cache);
-	queue_tick(&mq->cache_dirty);
-	queue_tick(&mq->cache_clean);
-	queue_update_writeback_sentinels(&mq->cache_dirty);
-	spin_unlock_irqrestore(&mq->tick_lock, flags);
-}
-
-static int mq_map(struct dm_cache_policy *p, dm_oblock_t oblock,
-		  bool can_block, bool can_migrate, bool discarded_oblock,
-		  struct bio *bio, struct policy_locker *locker,
-		  struct policy_result *result)
-{
-	int r;
-	struct mq_policy *mq = to_mq_policy(p);
-
-	result->op = POLICY_MISS;
-
-	if (can_block)
-		mutex_lock(&mq->lock);
-	else if (!mutex_trylock(&mq->lock))
-		return -EWOULDBLOCK;
-
-	copy_tick(mq);
-
-	iot_examine_bio(&mq->tracker, bio);
-	r = map(mq, oblock, can_migrate, discarded_oblock,
-		bio_data_dir(bio), locker, result);
-
-	mutex_unlock(&mq->lock);
-
-	return r;
-}
-
-static int mq_lookup(struct dm_cache_policy *p, dm_oblock_t oblock, dm_cblock_t *cblock)
-{
-	int r;
-	struct mq_policy *mq = to_mq_policy(p);
-	struct entry *e;
-
-	if (!mutex_trylock(&mq->lock))
-		return -EWOULDBLOCK;
-
-	e = hash_lookup(mq, oblock);
-	if (e && in_cache(mq, e)) {
-		*cblock = infer_cblock(&mq->cache_pool, e);
-		r = 0;
-	} else
-		r = -ENOENT;
-
-	mutex_unlock(&mq->lock);
-
-	return r;
-}
-
-static void __mq_set_clear_dirty(struct mq_policy *mq, dm_oblock_t oblock, bool set)
-{
-	struct entry *e;
-
-	e = hash_lookup(mq, oblock);
-	BUG_ON(!e || !in_cache(mq, e));
-
-	del(mq, e);
-	e->dirty = set;
-	push(mq, e);
-}
-
-static void mq_set_dirty(struct dm_cache_policy *p, dm_oblock_t oblock)
-{
-	struct mq_policy *mq = to_mq_policy(p);
-
-	mutex_lock(&mq->lock);
-	__mq_set_clear_dirty(mq, oblock, true);
-	mutex_unlock(&mq->lock);
-}
-
-static void mq_clear_dirty(struct dm_cache_policy *p, dm_oblock_t oblock)
-{
-	struct mq_policy *mq = to_mq_policy(p);
-
-	mutex_lock(&mq->lock);
-	__mq_set_clear_dirty(mq, oblock, false);
-	mutex_unlock(&mq->lock);
-}
-
-static int mq_load_mapping(struct dm_cache_policy *p,
-			   dm_oblock_t oblock, dm_cblock_t cblock,
-			   uint32_t hint, bool hint_valid)
-{
-	struct mq_policy *mq = to_mq_policy(p);
-	struct entry *e;
-
-	e = alloc_particular_entry(&mq->cache_pool, cblock);
-	e->oblock = oblock;
-	e->dirty = false;	/* this gets corrected in a minute */
-	e->hit_count = hint_valid ? hint : 1;
-	push(mq, e);
-
-	return 0;
-}
-
-static int mq_save_hints(struct mq_policy *mq, struct queue *q,
-			 policy_walk_fn fn, void *context)
-{
-	int r;
-	unsigned level;
-	struct list_head *h;
-	struct entry *e;
-
-	for (level = 0; level < NR_QUEUE_LEVELS; level++)
-		list_for_each(h, q->qs + level) {
-			if (is_sentinel(q, h))
-				continue;
-
-			e = container_of(h, struct entry, list);
-			r = fn(context, infer_cblock(&mq->cache_pool, e),
-			       e->oblock, e->hit_count);
-			if (r)
-				return r;
-		}
-
-	return 0;
-}
-
-static int mq_walk_mappings(struct dm_cache_policy *p, policy_walk_fn fn,
-			    void *context)
-{
-	struct mq_policy *mq = to_mq_policy(p);
-	int r = 0;
-
-	mutex_lock(&mq->lock);
-
-	r = mq_save_hints(mq, &mq->cache_clean, fn, context);
-	if (!r)
-		r = mq_save_hints(mq, &mq->cache_dirty, fn, context);
-
-	mutex_unlock(&mq->lock);
-
-	return r;
-}
-
-static void __remove_mapping(struct mq_policy *mq, dm_oblock_t oblock)
-{
-	struct entry *e;
-
-	e = hash_lookup(mq, oblock);
-	BUG_ON(!e || !in_cache(mq, e));
-
-	del(mq, e);
-	free_entry(&mq->cache_pool, e);
-}
-
-static void mq_remove_mapping(struct dm_cache_policy *p, dm_oblock_t oblock)
-{
-	struct mq_policy *mq = to_mq_policy(p);
-
-	mutex_lock(&mq->lock);
-	__remove_mapping(mq, oblock);
-	mutex_unlock(&mq->lock);
-}
-
-static int __remove_cblock(struct mq_policy *mq, dm_cblock_t cblock)
-{
-	struct entry *e = epool_find(&mq->cache_pool, cblock);
-
-	if (!e)
-		return -ENODATA;
-
-	del(mq, e);
-	free_entry(&mq->cache_pool, e);
-
-	return 0;
-}
-
-static int mq_remove_cblock(struct dm_cache_policy *p, dm_cblock_t cblock)
-{
-	int r;
-	struct mq_policy *mq = to_mq_policy(p);
-
-	mutex_lock(&mq->lock);
-	r = __remove_cblock(mq, cblock);
-	mutex_unlock(&mq->lock);
-
-	return r;
-}
-
-#define CLEAN_TARGET_PERCENTAGE 25
-
-static bool clean_target_met(struct mq_policy *mq)
-{
-	/*
-	 * Cache entries may not be populated.  So we're cannot rely on the
-	 * size of the clean queue.
-	 */
-	unsigned nr_clean = from_cblock(mq->cache_size) - queue_size(&mq->cache_dirty);
-	unsigned target = from_cblock(mq->cache_size) * CLEAN_TARGET_PERCENTAGE / 100;
-
-	return nr_clean >= target;
-}
-
-static int __mq_writeback_work(struct mq_policy *mq, dm_oblock_t *oblock,
-			      dm_cblock_t *cblock)
-{
-	struct entry *e = pop_old(mq, &mq->cache_dirty);
-
-	if (!e && !clean_target_met(mq))
-		e = pop(mq, &mq->cache_dirty);
-
-	if (!e)
-		return -ENODATA;
-
-	*oblock = e->oblock;
-	*cblock = infer_cblock(&mq->cache_pool, e);
-	e->dirty = false;
-	push(mq, e);
-
-	return 0;
-}
-
-static int mq_writeback_work(struct dm_cache_policy *p, dm_oblock_t *oblock,
-			     dm_cblock_t *cblock, bool critical_only)
-{
-	int r;
-	struct mq_policy *mq = to_mq_policy(p);
-
-	mutex_lock(&mq->lock);
-	r = __mq_writeback_work(mq, oblock, cblock);
-	mutex_unlock(&mq->lock);
-
-	return r;
-}
-
-static void __force_mapping(struct mq_policy *mq,
-			    dm_oblock_t current_oblock, dm_oblock_t new_oblock)
-{
-	struct entry *e = hash_lookup(mq, current_oblock);
-
-	if (e && in_cache(mq, e)) {
-		del(mq, e);
-		e->oblock = new_oblock;
-		e->dirty = true;
-		push(mq, e);
-	}
-}
-
-static void mq_force_mapping(struct dm_cache_policy *p,
-			     dm_oblock_t current_oblock, dm_oblock_t new_oblock)
-{
-	struct mq_policy *mq = to_mq_policy(p);
-
-	mutex_lock(&mq->lock);
-	__force_mapping(mq, current_oblock, new_oblock);
-	mutex_unlock(&mq->lock);
-}
-
-static dm_cblock_t mq_residency(struct dm_cache_policy *p)
-{
-	dm_cblock_t r;
-	struct mq_policy *mq = to_mq_policy(p);
-
-	mutex_lock(&mq->lock);
-	r = to_cblock(mq->cache_pool.nr_allocated);
-	mutex_unlock(&mq->lock);
-
-	return r;
-}
-
-static void mq_tick(struct dm_cache_policy *p, bool can_block)
-{
-	struct mq_policy *mq = to_mq_policy(p);
-	unsigned long flags;
-
-	spin_lock_irqsave(&mq->tick_lock, flags);
-	mq->tick_protected++;
-	spin_unlock_irqrestore(&mq->tick_lock, flags);
-
-	if (can_block) {
-		mutex_lock(&mq->lock);
-		copy_tick(mq);
-		mutex_unlock(&mq->lock);
-	}
-}
-
-static int mq_set_config_value(struct dm_cache_policy *p,
-			       const char *key, const char *value)
-{
-	struct mq_policy *mq = to_mq_policy(p);
-	unsigned long tmp;
-
-	if (kstrtoul(value, 10, &tmp))
-		return -EINVAL;
-
-	if (!strcasecmp(key, "random_threshold")) {
-		mq->tracker.thresholds[PATTERN_RANDOM] = tmp;
-
-	} else if (!strcasecmp(key, "sequential_threshold")) {
-		mq->tracker.thresholds[PATTERN_SEQUENTIAL] = tmp;
-
-	} else if (!strcasecmp(key, "discard_promote_adjustment"))
-		mq->discard_promote_adjustment = tmp;
-
-	else if (!strcasecmp(key, "read_promote_adjustment"))
-		mq->read_promote_adjustment = tmp;
-
-	else if (!strcasecmp(key, "write_promote_adjustment"))
-		mq->write_promote_adjustment = tmp;
-
-	else
-		return -EINVAL;
-
-	return 0;
-}
-
-static int mq_emit_config_values(struct dm_cache_policy *p, char *result,
-				 unsigned maxlen, ssize_t *sz_ptr)
-{
-	ssize_t sz = *sz_ptr;
-	struct mq_policy *mq = to_mq_policy(p);
-
-	DMEMIT("10 random_threshold %u "
-	       "sequential_threshold %u "
-	       "discard_promote_adjustment %u "
-	       "read_promote_adjustment %u "
-	       "write_promote_adjustment %u ",
-	       mq->tracker.thresholds[PATTERN_RANDOM],
-	       mq->tracker.thresholds[PATTERN_SEQUENTIAL],
-	       mq->discard_promote_adjustment,
-	       mq->read_promote_adjustment,
-	       mq->write_promote_adjustment);
-
-	*sz_ptr = sz;
-	return 0;
-}
-
-/* Init the policy plugin interface function pointers. */
-static void init_policy_functions(struct mq_policy *mq)
-{
-	mq->policy.destroy = mq_destroy;
-	mq->policy.map = mq_map;
-	mq->policy.lookup = mq_lookup;
-	mq->policy.set_dirty = mq_set_dirty;
-	mq->policy.clear_dirty = mq_clear_dirty;
-	mq->policy.load_mapping = mq_load_mapping;
-	mq->policy.walk_mappings = mq_walk_mappings;
-	mq->policy.remove_mapping = mq_remove_mapping;
-	mq->policy.remove_cblock = mq_remove_cblock;
-	mq->policy.writeback_work = mq_writeback_work;
-	mq->policy.force_mapping = mq_force_mapping;
-	mq->policy.residency = mq_residency;
-	mq->policy.tick = mq_tick;
-	mq->policy.emit_config_values = mq_emit_config_values;
-	mq->policy.set_config_value = mq_set_config_value;
-}
-
-static struct dm_cache_policy *mq_create(dm_cblock_t cache_size,
-					 sector_t origin_size,
-					 sector_t cache_block_size)
-{
-	struct mq_policy *mq = kzalloc(sizeof(*mq), GFP_KERNEL);
-
-	if (!mq)
-		return NULL;
-
-	init_policy_functions(mq);
-	iot_init(&mq->tracker, SEQUENTIAL_THRESHOLD_DEFAULT, RANDOM_THRESHOLD_DEFAULT);
-	mq->cache_size = cache_size;
-
-	if (epool_init(&mq->pre_cache_pool, from_cblock(cache_size))) {
-		DMERR("couldn't initialize pool of pre-cache entries");
-		goto bad_pre_cache_init;
-	}
-
-	if (epool_init(&mq->cache_pool, from_cblock(cache_size))) {
-		DMERR("couldn't initialize pool of cache entries");
-		goto bad_cache_init;
-	}
-
-	mq->tick_protected = 0;
-	mq->tick = 0;
-	mq->hit_count = 0;
-	mq->generation = 0;
-	mq->discard_promote_adjustment = DEFAULT_DISCARD_PROMOTE_ADJUSTMENT;
-	mq->read_promote_adjustment = DEFAULT_READ_PROMOTE_ADJUSTMENT;
-	mq->write_promote_adjustment = DEFAULT_WRITE_PROMOTE_ADJUSTMENT;
-	mutex_init(&mq->lock);
-	spin_lock_init(&mq->tick_lock);
-
-	queue_init(&mq->pre_cache);
-	queue_init(&mq->cache_clean);
-	queue_init(&mq->cache_dirty);
-
-	mq->generation_period = max((unsigned) from_cblock(cache_size), 1024U);
-
-	mq->nr_buckets = next_power(from_cblock(cache_size) / 2, 16);
-	mq->hash_bits = __ffs(mq->nr_buckets);
-	mq->table = vzalloc(sizeof(*mq->table) * mq->nr_buckets);
-	if (!mq->table)
-		goto bad_alloc_table;
-
-	return &mq->policy;
-
-bad_alloc_table:
-	epool_exit(&mq->cache_pool);
-bad_cache_init:
-	epool_exit(&mq->pre_cache_pool);
-bad_pre_cache_init:
-	kfree(mq);
-
-	return NULL;
-}
-
-/*----------------------------------------------------------------*/
-
-static struct dm_cache_policy_type mq_policy_type = {
-	.name = "mq",
-	.version = {1, 4, 0},
-	.hint_size = 4,
-	.owner = THIS_MODULE,
-	.create = mq_create
-};
-
-static int __init mq_init(void)
-{
-	int r;
-
-	mq_entry_cache = kmem_cache_create("dm_mq_policy_cache_entry",
-					   sizeof(struct entry),
-					   __alignof__(struct entry),
-					   0, NULL);
-	if (!mq_entry_cache)
-		return -ENOMEM;
-
-	r = dm_cache_policy_register(&mq_policy_type);
-	if (r) {
-		DMERR("register failed %d", r);
-		kmem_cache_destroy(mq_entry_cache);
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-static void __exit mq_exit(void)
-{
-	dm_cache_policy_unregister(&mq_policy_type);
-
-	kmem_cache_destroy(mq_entry_cache);
-}
-
-module_init(mq_init);
-module_exit(mq_exit);
-
-MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("mq cache policy");
diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c
index 28d4586748d0..cf48a617a3a4 100644
--- a/drivers/md/dm-cache-policy-smq.c
+++ b/drivers/md/dm-cache-policy-smq.c
@@ -1567,8 +1567,48 @@ static void smq_tick(struct dm_cache_policy *p, bool can_block)
 	spin_unlock_irqrestore(&mq->lock, flags);
 }
 
+/*
+ * smq has no config values, but the old mq policy did.  To avoid breaking
+ * software we continue to accept these configurables for the mq policy,
+ * but they have no effect.
+ */
+static int mq_set_config_value(struct dm_cache_policy *p,
+			       const char *key, const char *value)
+{
+	unsigned long tmp;
+
+	if (kstrtoul(value, 10, &tmp))
+		return -EINVAL;
+
+	if (!strcasecmp(key, "random_threshold") ||
+	    !strcasecmp(key, "sequential_threshold") ||
+	    !strcasecmp(key, "discard_promote_adjustment") ||
+	    !strcasecmp(key, "read_promote_adjustment") ||
+	    !strcasecmp(key, "write_promote_adjustment")) {
+		DMWARN("tunable '%s' no longer has any effect, mq policy is now an alias for smq", key);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int mq_emit_config_values(struct dm_cache_policy *p, char *result,
+				 unsigned maxlen, ssize_t *sz_ptr)
+{
+	ssize_t sz = *sz_ptr;
+
+	DMEMIT("10 random_threshold 0 "
+	       "sequential_threshold 0 "
+	       "discard_promote_adjustment 0 "
+	       "read_promote_adjustment 0 "
+	       "write_promote_adjustment 0 ");
+
+	*sz_ptr = sz;
+	return 0;
+}
+
 /* Init the policy plugin interface function pointers. */
-static void init_policy_functions(struct smq_policy *mq)
+static void init_policy_functions(struct smq_policy *mq, bool mimic_mq)
 {
 	mq->policy.destroy = smq_destroy;
 	mq->policy.map = smq_map;
@@ -1583,6 +1623,11 @@ static void init_policy_functions(struct smq_policy *mq)
 	mq->policy.force_mapping = smq_force_mapping;
 	mq->policy.residency = smq_residency;
 	mq->policy.tick = smq_tick;
+
+	if (mimic_mq) {
+		mq->policy.set_config_value = mq_set_config_value;
+		mq->policy.emit_config_values = mq_emit_config_values;
+	}
 }
 
 static bool too_many_hotspot_blocks(sector_t origin_size,
@@ -1606,9 +1651,10 @@ static void calc_hotspot_params(sector_t origin_size,
 		*hotspot_block_size /= 2u;
 }
 
-static struct dm_cache_policy *smq_create(dm_cblock_t cache_size,
-					  sector_t origin_size,
-					  sector_t cache_block_size)
+static struct dm_cache_policy *__smq_create(dm_cblock_t cache_size,
+					    sector_t origin_size,
+					    sector_t cache_block_size,
+					    bool mimic_mq)
 {
 	unsigned i;
 	unsigned nr_sentinels_per_queue = 2u * NR_CACHE_LEVELS;
@@ -1618,7 +1664,7 @@ static struct dm_cache_policy *smq_create(dm_cblock_t cache_size,
 	if (!mq)
 		return NULL;
 
-	init_policy_functions(mq);
+	init_policy_functions(mq, mimic_mq);
 	mq->cache_size = cache_size;
 	mq->cache_block_size = cache_block_size;
 
@@ -1706,19 +1752,41 @@ bad_pool_init:
 	return NULL;
 }
 
+static struct dm_cache_policy *smq_create(dm_cblock_t cache_size,
+					  sector_t origin_size,
+					  sector_t cache_block_size)
+{
+	return __smq_create(cache_size, origin_size, cache_block_size, false);
+}
+
+static struct dm_cache_policy *mq_create(dm_cblock_t cache_size,
+					 sector_t origin_size,
+					 sector_t cache_block_size)
+{
+	return __smq_create(cache_size, origin_size, cache_block_size, true);
+}
+
 /*----------------------------------------------------------------*/
 
 static struct dm_cache_policy_type smq_policy_type = {
 	.name = "smq",
-	.version = {1, 0, 0},
+	.version = {1, 5, 0},
 	.hint_size = 4,
 	.owner = THIS_MODULE,
 	.create = smq_create
 };
 
+static struct dm_cache_policy_type mq_policy_type = {
+	.name = "mq",
+	.version = {1, 5, 0},
+	.hint_size = 4,
+	.owner = THIS_MODULE,
+	.create = mq_create,
+};
+
 static struct dm_cache_policy_type default_policy_type = {
 	.name = "default",
-	.version = {1, 4, 0},
+	.version = {1, 5, 0},
 	.hint_size = 4,
 	.owner = THIS_MODULE,
 	.create = smq_create,
@@ -1735,9 +1803,17 @@ static int __init smq_init(void)
 		return -ENOMEM;
 	}
 
+	r = dm_cache_policy_register(&mq_policy_type);
+	if (r) {
+		DMERR("register failed (as mq) %d", r);
+		dm_cache_policy_unregister(&smq_policy_type);
+		return -ENOMEM;
+	}
+
 	r = dm_cache_policy_register(&default_policy_type);
 	if (r) {
 		DMERR("register failed (as default) %d", r);
+		dm_cache_policy_unregister(&mq_policy_type);
 		dm_cache_policy_unregister(&smq_policy_type);
 		return -ENOMEM;
 	}
@@ -1748,6 +1824,7 @@ static int __init smq_init(void)
 static void __exit smq_exit(void)
 {
 	dm_cache_policy_unregister(&smq_policy_type);
+	dm_cache_policy_unregister(&mq_policy_type);
 	dm_cache_policy_unregister(&default_policy_type);
 }
 
@@ -1759,3 +1836,4 @@ MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("smq cache policy");
 
 MODULE_ALIAS("dm-cache-default");
+MODULE_ALIAS("dm-cache-mq");
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 5780accffa30..ee0510f9a85e 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -984,9 +984,14 @@ static void notify_mode_switch(struct cache *cache, enum cache_metadata_mode mod
 
 static void set_cache_mode(struct cache *cache, enum cache_metadata_mode new_mode)
 {
-	bool needs_check = dm_cache_metadata_needs_check(cache->cmd);
+	bool needs_check;
 	enum cache_metadata_mode old_mode = get_cache_mode(cache);
 
+	if (dm_cache_metadata_needs_check(cache->cmd, &needs_check)) {
+		DMERR("unable to read needs_check flag, setting failure mode");
+		new_mode = CM_FAIL;
+	}
+
 	if (new_mode == CM_WRITE && needs_check) {
 		DMERR("%s: unable to switch cache to write mode until repaired.",
 		      cache_device_name(cache));
@@ -2771,7 +2776,7 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 	ti->split_discard_bios = false;
 
 	cache->features = ca->features;
-	ti->per_bio_data_size = get_per_bio_data_size(cache);
+	ti->per_io_data_size = get_per_bio_data_size(cache);
 
 	cache->callbacks.congested_fn = cache_is_congested;
 	dm_table_add_target_callbacks(ti->table, &cache->callbacks);
@@ -3510,6 +3515,7 @@ static void cache_status(struct dm_target *ti, status_type_t type,
 	char buf[BDEVNAME_SIZE];
 	struct cache *cache = ti->private;
 	dm_cblock_t residency;
+	bool needs_check;
 
 	switch (type) {
 	case STATUSTYPE_INFO:
@@ -3583,7 +3589,9 @@ static void cache_status(struct dm_target *ti, status_type_t type,
 		else
 			DMEMIT("rw ");
 
-		if (dm_cache_metadata_needs_check(cache->cmd))
+		r = dm_cache_metadata_needs_check(cache->cmd, &needs_check);
+
+		if (r || needs_check)
 			DMEMIT("needs_check ");
 		else
 			DMEMIT("- ");
@@ -3806,7 +3814,7 @@ static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type cache_target = {
 	.name = "cache",
-	.version = {1, 8, 0},
+	.version = {1, 9, 0},
 	.module = THIS_MODULE,
 	.ctr = cache_ctr,
 	.dtr = cache_dtr,
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 3147c8d09ea8..4f3cb3554944 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -28,6 +28,7 @@
 #include <crypto/hash.h>
 #include <crypto/md5.h>
 #include <crypto/algapi.h>
+#include <crypto/skcipher.h>
 
 #include <linux/device-mapper.h>
 
@@ -44,7 +45,7 @@ struct convert_context {
 	struct bvec_iter iter_out;
 	sector_t cc_sector;
 	atomic_t cc_pending;
-	struct ablkcipher_request *req;
+	struct skcipher_request *req;
 };
 
 /*
@@ -86,7 +87,7 @@ struct crypt_iv_operations {
 };
 
 struct iv_essiv_private {
-	struct crypto_hash *hash_tfm;
+	struct crypto_ahash *hash_tfm;
 	u8 *salt;
 };
 
@@ -153,13 +154,13 @@ struct crypt_config {
 
 	/* ESSIV: struct crypto_cipher *essiv_tfm */
 	void *iv_private;
-	struct crypto_ablkcipher **tfms;
+	struct crypto_skcipher **tfms;
 	unsigned tfms_count;
 
 	/*
 	 * Layout of each crypto request:
 	 *
-	 *   struct ablkcipher_request
+	 *   struct skcipher_request
 	 *      context
 	 *      padding
 	 *   struct dm_crypt_request
@@ -189,7 +190,7 @@ static u8 *iv_of_dmreq(struct crypt_config *cc, struct dm_crypt_request *dmreq);
 /*
  * Use this to access cipher attributes that are the same for each CPU.
  */
-static struct crypto_ablkcipher *any_tfm(struct crypt_config *cc)
+static struct crypto_skcipher *any_tfm(struct crypt_config *cc)
 {
 	return cc->tfms[0];
 }
@@ -263,23 +264,25 @@ static int crypt_iv_plain64_gen(struct crypt_config *cc, u8 *iv,
 static int crypt_iv_essiv_init(struct crypt_config *cc)
 {
 	struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv;
-	struct hash_desc desc;
+	AHASH_REQUEST_ON_STACK(req, essiv->hash_tfm);
 	struct scatterlist sg;
 	struct crypto_cipher *essiv_tfm;
 	int err;
 
 	sg_init_one(&sg, cc->key, cc->key_size);
-	desc.tfm = essiv->hash_tfm;
-	desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	ahash_request_set_tfm(req, essiv->hash_tfm);
+	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
+	ahash_request_set_crypt(req, &sg, essiv->salt, cc->key_size);
 
-	err = crypto_hash_digest(&desc, &sg, cc->key_size, essiv->salt);
+	err = crypto_ahash_digest(req);
+	ahash_request_zero(req);
 	if (err)
 		return err;
 
 	essiv_tfm = cc->iv_private;
 
 	err = crypto_cipher_setkey(essiv_tfm, essiv->salt,
-			    crypto_hash_digestsize(essiv->hash_tfm));
+			    crypto_ahash_digestsize(essiv->hash_tfm));
 	if (err)
 		return err;
 
@@ -290,7 +293,7 @@ static int crypt_iv_essiv_init(struct crypt_config *cc)
 static int crypt_iv_essiv_wipe(struct crypt_config *cc)
 {
 	struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv;
-	unsigned salt_size = crypto_hash_digestsize(essiv->hash_tfm);
+	unsigned salt_size = crypto_ahash_digestsize(essiv->hash_tfm);
 	struct crypto_cipher *essiv_tfm;
 	int r, err = 0;
 
@@ -320,7 +323,7 @@ static struct crypto_cipher *setup_essiv_cpu(struct crypt_config *cc,
 	}
 
 	if (crypto_cipher_blocksize(essiv_tfm) !=
-	    crypto_ablkcipher_ivsize(any_tfm(cc))) {
+	    crypto_skcipher_ivsize(any_tfm(cc))) {
 		ti->error = "Block size of ESSIV cipher does "
 			    "not match IV size of block cipher";
 		crypto_free_cipher(essiv_tfm);
@@ -342,7 +345,7 @@ static void crypt_iv_essiv_dtr(struct crypt_config *cc)
 	struct crypto_cipher *essiv_tfm;
 	struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv;
 
-	crypto_free_hash(essiv->hash_tfm);
+	crypto_free_ahash(essiv->hash_tfm);
 	essiv->hash_tfm = NULL;
 
 	kzfree(essiv->salt);
@@ -360,7 +363,7 @@ static int crypt_iv_essiv_ctr(struct crypt_config *cc, struct dm_target *ti,
 			      const char *opts)
 {
 	struct crypto_cipher *essiv_tfm = NULL;
-	struct crypto_hash *hash_tfm = NULL;
+	struct crypto_ahash *hash_tfm = NULL;
 	u8 *salt = NULL;
 	int err;
 
@@ -370,14 +373,14 @@ static int crypt_iv_essiv_ctr(struct crypt_config *cc, struct dm_target *ti,
 	}
 
 	/* Allocate hash algorithm */
-	hash_tfm = crypto_alloc_hash(opts, 0, CRYPTO_ALG_ASYNC);
+	hash_tfm = crypto_alloc_ahash(opts, 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(hash_tfm)) {
 		ti->error = "Error initializing ESSIV hash";
 		err = PTR_ERR(hash_tfm);
 		goto bad;
 	}
 
-	salt = kzalloc(crypto_hash_digestsize(hash_tfm), GFP_KERNEL);
+	salt = kzalloc(crypto_ahash_digestsize(hash_tfm), GFP_KERNEL);
 	if (!salt) {
 		ti->error = "Error kmallocing salt storage in ESSIV";
 		err = -ENOMEM;
@@ -388,7 +391,7 @@ static int crypt_iv_essiv_ctr(struct crypt_config *cc, struct dm_target *ti,
 	cc->iv_gen_private.essiv.hash_tfm = hash_tfm;
 
 	essiv_tfm = setup_essiv_cpu(cc, ti, salt,
-				crypto_hash_digestsize(hash_tfm));
+				crypto_ahash_digestsize(hash_tfm));
 	if (IS_ERR(essiv_tfm)) {
 		crypt_iv_essiv_dtr(cc);
 		return PTR_ERR(essiv_tfm);
@@ -399,7 +402,7 @@ static int crypt_iv_essiv_ctr(struct crypt_config *cc, struct dm_target *ti,
 
 bad:
 	if (hash_tfm && !IS_ERR(hash_tfm))
-		crypto_free_hash(hash_tfm);
+		crypto_free_ahash(hash_tfm);
 	kfree(salt);
 	return err;
 }
@@ -419,7 +422,7 @@ static int crypt_iv_essiv_gen(struct crypt_config *cc, u8 *iv,
 static int crypt_iv_benbi_ctr(struct crypt_config *cc, struct dm_target *ti,
 			      const char *opts)
 {
-	unsigned bs = crypto_ablkcipher_blocksize(any_tfm(cc));
+	unsigned bs = crypto_skcipher_blocksize(any_tfm(cc));
 	int log = ilog2(bs);
 
 	/* we need to calculate how far we must shift the sector count
@@ -816,27 +819,27 @@ static void crypt_convert_init(struct crypt_config *cc,
 }
 
 static struct dm_crypt_request *dmreq_of_req(struct crypt_config *cc,
-					     struct ablkcipher_request *req)
+					     struct skcipher_request *req)
 {
 	return (struct dm_crypt_request *)((char *)req + cc->dmreq_start);
 }
 
-static struct ablkcipher_request *req_of_dmreq(struct crypt_config *cc,
+static struct skcipher_request *req_of_dmreq(struct crypt_config *cc,
 					       struct dm_crypt_request *dmreq)
 {
-	return (struct ablkcipher_request *)((char *)dmreq - cc->dmreq_start);
+	return (struct skcipher_request *)((char *)dmreq - cc->dmreq_start);
 }
 
 static u8 *iv_of_dmreq(struct crypt_config *cc,
 		       struct dm_crypt_request *dmreq)
 {
 	return (u8 *)ALIGN((unsigned long)(dmreq + 1),
-		crypto_ablkcipher_alignmask(any_tfm(cc)) + 1);
+		crypto_skcipher_alignmask(any_tfm(cc)) + 1);
 }
 
 static int crypt_convert_block(struct crypt_config *cc,
 			       struct convert_context *ctx,
-			       struct ablkcipher_request *req)
+			       struct skcipher_request *req)
 {
 	struct bio_vec bv_in = bio_iter_iovec(ctx->bio_in, ctx->iter_in);
 	struct bio_vec bv_out = bio_iter_iovec(ctx->bio_out, ctx->iter_out);
@@ -866,13 +869,13 @@ static int crypt_convert_block(struct crypt_config *cc,
 			return r;
 	}
 
-	ablkcipher_request_set_crypt(req, &dmreq->sg_in, &dmreq->sg_out,
-				     1 << SECTOR_SHIFT, iv);
+	skcipher_request_set_crypt(req, &dmreq->sg_in, &dmreq->sg_out,
+				   1 << SECTOR_SHIFT, iv);
 
 	if (bio_data_dir(ctx->bio_in) == WRITE)
-		r = crypto_ablkcipher_encrypt(req);
+		r = crypto_skcipher_encrypt(req);
 	else
-		r = crypto_ablkcipher_decrypt(req);
+		r = crypto_skcipher_decrypt(req);
 
 	if (!r && cc->iv_gen_ops && cc->iv_gen_ops->post)
 		r = cc->iv_gen_ops->post(cc, iv, dmreq);
@@ -891,23 +894,23 @@ static void crypt_alloc_req(struct crypt_config *cc,
 	if (!ctx->req)
 		ctx->req = mempool_alloc(cc->req_pool, GFP_NOIO);
 
-	ablkcipher_request_set_tfm(ctx->req, cc->tfms[key_index]);
+	skcipher_request_set_tfm(ctx->req, cc->tfms[key_index]);
 
 	/*
 	 * Use REQ_MAY_BACKLOG so a cipher driver internally backlogs
 	 * requests if driver request queue is full.
 	 */
-	ablkcipher_request_set_callback(ctx->req,
+	skcipher_request_set_callback(ctx->req,
 	    CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 	    kcryptd_async_done, dmreq_of_req(cc, ctx->req));
 }
 
 static void crypt_free_req(struct crypt_config *cc,
-			   struct ablkcipher_request *req, struct bio *base_bio)
+			   struct skcipher_request *req, struct bio *base_bio)
 {
 	struct dm_crypt_io *io = dm_per_bio_data(base_bio, cc->per_bio_data_size);
 
-	if ((struct ablkcipher_request *)(io + 1) != req)
+	if ((struct skcipher_request *)(io + 1) != req)
 		mempool_free(req, cc->req_pool);
 }
 
@@ -1437,7 +1440,7 @@ static void crypt_free_tfms(struct crypt_config *cc)
 
 	for (i = 0; i < cc->tfms_count; i++)
 		if (cc->tfms[i] && !IS_ERR(cc->tfms[i])) {
-			crypto_free_ablkcipher(cc->tfms[i]);
+			crypto_free_skcipher(cc->tfms[i]);
 			cc->tfms[i] = NULL;
 		}
 
@@ -1450,13 +1453,13 @@ static int crypt_alloc_tfms(struct crypt_config *cc, char *ciphermode)
 	unsigned i;
 	int err;
 
-	cc->tfms = kmalloc(cc->tfms_count * sizeof(struct crypto_ablkcipher *),
+	cc->tfms = kmalloc(cc->tfms_count * sizeof(struct crypto_skcipher *),
 			   GFP_KERNEL);
 	if (!cc->tfms)
 		return -ENOMEM;
 
 	for (i = 0; i < cc->tfms_count; i++) {
-		cc->tfms[i] = crypto_alloc_ablkcipher(ciphermode, 0, 0);
+		cc->tfms[i] = crypto_alloc_skcipher(ciphermode, 0, 0);
 		if (IS_ERR(cc->tfms[i])) {
 			err = PTR_ERR(cc->tfms[i]);
 			crypt_free_tfms(cc);
@@ -1476,9 +1479,9 @@ static int crypt_setkey_allcpus(struct crypt_config *cc)
 	subkey_size = (cc->key_size - cc->key_extra_size) >> ilog2(cc->tfms_count);
 
 	for (i = 0; i < cc->tfms_count; i++) {
-		r = crypto_ablkcipher_setkey(cc->tfms[i],
-					     cc->key + (i * subkey_size),
-					     subkey_size);
+		r = crypto_skcipher_setkey(cc->tfms[i],
+					   cc->key + (i * subkey_size),
+					   subkey_size);
 		if (r)
 			err = r;
 	}
@@ -1645,7 +1648,7 @@ static int crypt_ctr_cipher(struct dm_target *ti,
 	}
 
 	/* Initialize IV */
-	cc->iv_size = crypto_ablkcipher_ivsize(any_tfm(cc));
+	cc->iv_size = crypto_skcipher_ivsize(any_tfm(cc));
 	if (cc->iv_size)
 		/* at least a 64 bit sector number should fit in our buffer */
 		cc->iv_size = max(cc->iv_size,
@@ -1763,21 +1766,21 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	if (ret < 0)
 		goto bad;
 
-	cc->dmreq_start = sizeof(struct ablkcipher_request);
-	cc->dmreq_start += crypto_ablkcipher_reqsize(any_tfm(cc));
+	cc->dmreq_start = sizeof(struct skcipher_request);
+	cc->dmreq_start += crypto_skcipher_reqsize(any_tfm(cc));
 	cc->dmreq_start = ALIGN(cc->dmreq_start, __alignof__(struct dm_crypt_request));
 
-	if (crypto_ablkcipher_alignmask(any_tfm(cc)) < CRYPTO_MINALIGN) {
+	if (crypto_skcipher_alignmask(any_tfm(cc)) < CRYPTO_MINALIGN) {
 		/* Allocate the padding exactly */
 		iv_size_padding = -(cc->dmreq_start + sizeof(struct dm_crypt_request))
-				& crypto_ablkcipher_alignmask(any_tfm(cc));
+				& crypto_skcipher_alignmask(any_tfm(cc));
 	} else {
 		/*
 		 * If the cipher requires greater alignment than kmalloc
 		 * alignment, we don't know the exact position of the
 		 * initialization vector. We must assume worst case.
 		 */
-		iv_size_padding = crypto_ablkcipher_alignmask(any_tfm(cc));
+		iv_size_padding = crypto_skcipher_alignmask(any_tfm(cc));
 	}
 
 	ret = -ENOMEM;
@@ -1788,7 +1791,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad;
 	}
 
-	cc->per_bio_data_size = ti->per_bio_data_size =
+	cc->per_bio_data_size = ti->per_io_data_size =
 		ALIGN(sizeof(struct dm_crypt_io) + cc->dmreq_start +
 		      sizeof(struct dm_crypt_request) + iv_size_padding + cc->iv_size,
 		      ARCH_KMALLOC_MINALIGN);
@@ -1922,7 +1925,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
 
 	io = dm_per_bio_data(bio, cc->per_bio_data_size);
 	crypt_io_init(io, cc, bio, dm_target_offset(ti, bio->bi_iter.bi_sector));
-	io->ctx.req = (struct ablkcipher_request *)(io + 1);
+	io->ctx.req = (struct skcipher_request *)(io + 1);
 
 	if (bio_data_dir(io->base_bio) == READ) {
 		if (kcryptd_io_read(io, GFP_NOWAIT))
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index b4c356a21123..cc70871a6d29 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -204,7 +204,7 @@ out:
 
 	ti->num_flush_bios = 1;
 	ti->num_discard_bios = 1;
-	ti->per_bio_data_size = sizeof(struct dm_delay_info);
+	ti->per_io_data_size = sizeof(struct dm_delay_info);
 	ti->private = dc;
 	return 0;
 
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 09e2afcafd2d..b7341de87015 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -220,7 +220,7 @@ static int flakey_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	ti->num_flush_bios = 1;
 	ti->num_discard_bios = 1;
-	ti->per_bio_data_size = sizeof(struct per_bio_data);
+	ti->per_io_data_size = sizeof(struct per_bio_data);
 	ti->private = fc;
 	return 0;
 
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 80a439543259..2adf81d81fca 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1291,7 +1291,8 @@ static int table_load(struct dm_ioctl *param, size_t param_size)
 
 	immutable_target_type = dm_get_immutable_target_type(md);
 	if (immutable_target_type &&
-	    (immutable_target_type != dm_table_get_immutable_target_type(t))) {
+	    (immutable_target_type != dm_table_get_immutable_target_type(t)) &&
+	    !dm_table_get_wildcard_target(t)) {
 		DMWARN("can't replace immutable target type %s",
 		       immutable_target_type->name);
 		r = -EINVAL;
@@ -1303,7 +1304,7 @@ static int table_load(struct dm_ioctl *param, size_t param_size)
 		dm_set_md_type(md, dm_table_get_type(t));
 
 		/* setup md->queue to reflect md's type (may block) */
-		r = dm_setup_md_queue(md);
+		r = dm_setup_md_queue(md, t);
 		if (r) {
 			DMWARN("unable to set up device queue for new table.");
 			goto err_unlock_md_type;
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index 624589d51c2c..608302e222af 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -475,7 +475,7 @@ static int log_writes_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	ti->flush_supported = true;
 	ti->num_discard_bios = 1;
 	ti->discards_supported = true;
-	ti->per_bio_data_size = sizeof(struct per_bio_data);
+	ti->per_io_data_size = sizeof(struct per_bio_data);
 	ti->private = lc;
 	return 0;
 
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index cfa29f574c2a..677ba223e2ae 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -23,6 +23,7 @@
 #include <linux/delay.h>
 #include <scsi/scsi_dh.h>
 #include <linux/atomic.h>
+#include <linux/blk-mq.h>
 
 #define DM_MSG_PREFIX "multipath"
 #define DM_PG_INIT_DELAY_MSECS 2000
@@ -33,11 +34,12 @@ struct pgpath {
 	struct list_head list;
 
 	struct priority_group *pg;	/* Owning PG */
-	unsigned is_active;		/* Path status */
 	unsigned fail_count;		/* Cumulative failure count */
 
 	struct dm_path path;
 	struct delayed_work activate_path;
+
+	bool is_active:1;		/* Path status */
 };
 
 #define path_to_pgpath(__pgp) container_of((__pgp), struct pgpath, path)
@@ -53,10 +55,10 @@ struct priority_group {
 	struct path_selector ps;
 
 	unsigned pg_num;		/* Reference number */
-	unsigned bypassed;		/* Temporarily bypass this PG? */
-
 	unsigned nr_pgpaths;		/* Number of paths in PG */
 	struct list_head pgpaths;
+
+	bool bypassed:1;		/* Temporarily bypass this PG? */
 };
 
 /* Multipath context */
@@ -74,21 +76,20 @@ struct multipath {
 
 	wait_queue_head_t pg_init_wait;	/* Wait for pg_init completion */
 
-	unsigned pg_init_required;	/* pg_init needs calling? */
 	unsigned pg_init_in_progress;	/* Only one pg_init allowed at once */
-	unsigned pg_init_delay_retry;	/* Delay pg_init retry? */
 
 	unsigned nr_valid_paths;	/* Total number of usable paths */
 	struct pgpath *current_pgpath;
 	struct priority_group *current_pg;
 	struct priority_group *next_pg;	/* Switch to this PG if set */
-	unsigned repeat_count;		/* I/Os left before calling PS again */
 
-	unsigned queue_io:1;		/* Must we queue all I/O? */
-	unsigned queue_if_no_path:1;	/* Queue I/O if last path fails? */
-	unsigned saved_queue_if_no_path:1; /* Saved state during suspension */
-	unsigned retain_attached_hw_handler:1; /* If there's already a hw_handler present, don't change it. */
-	unsigned pg_init_disabled:1;	/* pg_init is not currently allowed */
+	bool queue_io:1;		/* Must we queue all I/O? */
+	bool queue_if_no_path:1;	/* Queue I/O if last path fails? */
+	bool saved_queue_if_no_path:1;	/* Saved state during suspension */
+	bool retain_attached_hw_handler:1; /* If there's already a hw_handler present, don't change it. */
+	bool pg_init_disabled:1;	/* pg_init is not currently allowed */
+	bool pg_init_required:1;	/* pg_init needs calling? */
+	bool pg_init_delay_retry:1;	/* Delay pg_init retry? */
 
 	unsigned pg_init_retries;	/* Number of times to retry pg_init */
 	unsigned pg_init_count;		/* Number of times pg_init called */
@@ -120,7 +121,6 @@ static struct kmem_cache *_mpio_cache;
 static struct workqueue_struct *kmultipathd, *kmpath_handlerd;
 static void trigger_event(struct work_struct *work);
 static void activate_path(struct work_struct *work);
-static int __pgpath_busy(struct pgpath *pgpath);
 
 
 /*-----------------------------------------------
@@ -132,7 +132,7 @@ static struct pgpath *alloc_pgpath(void)
 	struct pgpath *pgpath = kzalloc(sizeof(*pgpath), GFP_KERNEL);
 
 	if (pgpath) {
-		pgpath->is_active = 1;
+		pgpath->is_active = true;
 		INIT_DELAYED_WORK(&pgpath->activate_path, activate_path);
 	}
 
@@ -181,25 +181,31 @@ static void free_priority_group(struct priority_group *pg,
 	kfree(pg);
 }
 
-static struct multipath *alloc_multipath(struct dm_target *ti)
+static struct multipath *alloc_multipath(struct dm_target *ti, bool use_blk_mq)
 {
 	struct multipath *m;
-	unsigned min_ios = dm_get_reserved_rq_based_ios();
 
 	m = kzalloc(sizeof(*m), GFP_KERNEL);
 	if (m) {
 		INIT_LIST_HEAD(&m->priority_groups);
 		spin_lock_init(&m->lock);
-		m->queue_io = 1;
+		m->queue_io = true;
 		m->pg_init_delay_msecs = DM_PG_INIT_DELAY_DEFAULT;
 		INIT_WORK(&m->trigger_event, trigger_event);
 		init_waitqueue_head(&m->pg_init_wait);
 		mutex_init(&m->work_mutex);
-		m->mpio_pool = mempool_create_slab_pool(min_ios, _mpio_cache);
-		if (!m->mpio_pool) {
-			kfree(m);
-			return NULL;
+
+		m->mpio_pool = NULL;
+		if (!use_blk_mq) {
+			unsigned min_ios = dm_get_reserved_rq_based_ios();
+
+			m->mpio_pool = mempool_create_slab_pool(min_ios, _mpio_cache);
+			if (!m->mpio_pool) {
+				kfree(m);
+				return NULL;
+			}
 		}
+
 		m->ti = ti;
 		ti->private = m;
 	}
@@ -222,26 +228,41 @@ static void free_multipath(struct multipath *m)
 	kfree(m);
 }
 
-static int set_mapinfo(struct multipath *m, union map_info *info)
+static struct dm_mpath_io *get_mpio(union map_info *info)
+{
+	return info->ptr;
+}
+
+static struct dm_mpath_io *set_mpio(struct multipath *m, union map_info *info)
 {
 	struct dm_mpath_io *mpio;
 
+	if (!m->mpio_pool) {
+		/* Use blk-mq pdu memory requested via per_io_data_size */
+		mpio = get_mpio(info);
+		memset(mpio, 0, sizeof(*mpio));
+		return mpio;
+	}
+
 	mpio = mempool_alloc(m->mpio_pool, GFP_ATOMIC);
 	if (!mpio)
-		return -ENOMEM;
+		return NULL;
 
 	memset(mpio, 0, sizeof(*mpio));
 	info->ptr = mpio;
 
-	return 0;
+	return mpio;
 }
 
-static void clear_mapinfo(struct multipath *m, union map_info *info)
+static void clear_request_fn_mpio(struct multipath *m, union map_info *info)
 {
-	struct dm_mpath_io *mpio = info->ptr;
+	/* Only needed for non blk-mq (.request_fn) multipath */
+	if (m->mpio_pool) {
+		struct dm_mpath_io *mpio = info->ptr;
 
-	info->ptr = NULL;
-	mempool_free(mpio, m->mpio_pool);
+		info->ptr = NULL;
+		mempool_free(mpio, m->mpio_pool);
+	}
 }
 
 /*-----------------------------------------------
@@ -257,7 +278,7 @@ static int __pg_init_all_paths(struct multipath *m)
 		return 0;
 
 	m->pg_init_count++;
-	m->pg_init_required = 0;
+	m->pg_init_required = false;
 
 	/* Check here to reset pg_init_required */
 	if (!m->current_pg)
@@ -283,11 +304,11 @@ static void __switch_pg(struct multipath *m, struct pgpath *pgpath)
 
 	/* Must we initialise the PG first, and queue I/O till it's ready? */
 	if (m->hw_handler_name) {
-		m->pg_init_required = 1;
-		m->queue_io = 1;
+		m->pg_init_required = true;
+		m->queue_io = true;
 	} else {
-		m->pg_init_required = 0;
-		m->queue_io = 0;
+		m->pg_init_required = false;
+		m->queue_io = false;
 	}
 
 	m->pg_init_count = 0;
@@ -298,7 +319,7 @@ static int __choose_path_in_pg(struct multipath *m, struct priority_group *pg,
 {
 	struct dm_path *path;
 
-	path = pg->ps.type->select_path(&pg->ps, &m->repeat_count, nr_bytes);
+	path = pg->ps.type->select_path(&pg->ps, nr_bytes);
 	if (!path)
 		return -ENXIO;
 
@@ -313,10 +334,10 @@ static int __choose_path_in_pg(struct multipath *m, struct priority_group *pg,
 static void __choose_pgpath(struct multipath *m, size_t nr_bytes)
 {
 	struct priority_group *pg;
-	unsigned bypassed = 1;
+	bool bypassed = true;
 
 	if (!m->nr_valid_paths) {
-		m->queue_io = 0;
+		m->queue_io = false;
 		goto failed;
 	}
 
@@ -344,7 +365,7 @@ static void __choose_pgpath(struct multipath *m, size_t nr_bytes)
 				continue;
 			if (!__choose_path_in_pg(m, pg, nr_bytes)) {
 				if (!bypassed)
-					m->pg_init_delay_retry = 1;
+					m->pg_init_delay_retry = true;
 				return;
 			}
 		}
@@ -380,7 +401,7 @@ static int __multipath_map(struct dm_target *ti, struct request *clone,
 			   union map_info *map_context,
 			   struct request *rq, struct request **__clone)
 {
-	struct multipath *m = (struct multipath *) ti->private;
+	struct multipath *m = ti->private;
 	int r = DM_MAPIO_REQUEUE;
 	size_t nr_bytes = clone ? blk_rq_bytes(clone) : blk_rq_bytes(rq);
 	struct pgpath *pgpath;
@@ -390,8 +411,7 @@ static int __multipath_map(struct dm_target *ti, struct request *clone,
 	spin_lock_irq(&m->lock);
 
 	/* Do we need to select a new pgpath? */
-	if (!m->current_pgpath ||
-	    (!m->queue_io && (m->repeat_count && --m->repeat_count == 0)))
+	if (!m->current_pgpath || !m->queue_io)
 		__choose_pgpath(m, nr_bytes);
 
 	pgpath = m->current_pgpath;
@@ -405,11 +425,11 @@ static int __multipath_map(struct dm_target *ti, struct request *clone,
 		goto out_unlock;
 	}
 
-	if (set_mapinfo(m, map_context) < 0)
+	mpio = set_mpio(m, map_context);
+	if (!mpio)
 		/* ENOMEM, requeue */
 		goto out_unlock;
 
-	mpio = map_context->ptr;
 	mpio->pgpath = pgpath;
 	mpio->nr_bytes = nr_bytes;
 
@@ -418,17 +438,24 @@ static int __multipath_map(struct dm_target *ti, struct request *clone,
 	spin_unlock_irq(&m->lock);
 
 	if (clone) {
-		/* Old request-based interface: allocated clone is passed in */
+		/*
+		 * Old request-based interface: allocated clone is passed in.
+		 * Used by: .request_fn stacked on .request_fn path(s).
+		 */
 		clone->q = bdev_get_queue(bdev);
 		clone->rq_disk = bdev->bd_disk;
 		clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
 	} else {
-		/* blk-mq request-based interface */
-		*__clone = blk_get_request(bdev_get_queue(bdev),
-					   rq_data_dir(rq), GFP_ATOMIC);
+		/*
+		 * blk-mq request-based interface; used by both:
+		 * .request_fn stacked on blk-mq path(s) and
+		 * blk-mq stacked on blk-mq path(s).
+		 */
+		*__clone = blk_mq_alloc_request(bdev_get_queue(bdev),
+						rq_data_dir(rq), BLK_MQ_REQ_NOWAIT);
 		if (IS_ERR(*__clone)) {
 			/* ENOMEM, requeue */
-			clear_mapinfo(m, map_context);
+			clear_request_fn_mpio(m, map_context);
 			return r;
 		}
 		(*__clone)->bio = (*__clone)->biotail = NULL;
@@ -463,14 +490,14 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
 
 static void multipath_release_clone(struct request *clone)
 {
-	blk_put_request(clone);
+	blk_mq_free_request(clone);
 }
 
 /*
  * If we run out of usable paths, should we queue I/O or error it?
  */
-static int queue_if_no_path(struct multipath *m, unsigned queue_if_no_path,
-			    unsigned save_old_value)
+static int queue_if_no_path(struct multipath *m, bool queue_if_no_path,
+			    bool save_old_value)
 {
 	unsigned long flags;
 
@@ -776,12 +803,12 @@ static int parse_features(struct dm_arg_set *as, struct multipath *m)
 		argc--;
 
 		if (!strcasecmp(arg_name, "queue_if_no_path")) {
-			r = queue_if_no_path(m, 1, 0);
+			r = queue_if_no_path(m, true, false);
 			continue;
 		}
 
 		if (!strcasecmp(arg_name, "retain_attached_hw_handler")) {
-			m->retain_attached_hw_handler = 1;
+			m->retain_attached_hw_handler = true;
 			continue;
 		}
 
@@ -820,11 +847,12 @@ static int multipath_ctr(struct dm_target *ti, unsigned int argc,
 	struct dm_arg_set as;
 	unsigned pg_count = 0;
 	unsigned next_pg_num;
+	bool use_blk_mq = dm_use_blk_mq(dm_table_get_md(ti->table));
 
 	as.argc = argc;
 	as.argv = argv;
 
-	m = alloc_multipath(ti);
+	m = alloc_multipath(ti, use_blk_mq);
 	if (!m) {
 		ti->error = "can't allocate multipath";
 		return -EINVAL;
@@ -880,6 +908,8 @@ static int multipath_ctr(struct dm_target *ti, unsigned int argc,
 	ti->num_flush_bios = 1;
 	ti->num_discard_bios = 1;
 	ti->num_write_same_bios = 1;
+	if (use_blk_mq)
+		ti->per_io_data_size = sizeof(struct dm_mpath_io);
 
 	return 0;
 
@@ -917,7 +947,7 @@ static void flush_multipath_work(struct multipath *m)
 	unsigned long flags;
 
 	spin_lock_irqsave(&m->lock, flags);
-	m->pg_init_disabled = 1;
+	m->pg_init_disabled = true;
 	spin_unlock_irqrestore(&m->lock, flags);
 
 	flush_workqueue(kmpath_handlerd);
@@ -926,7 +956,7 @@ static void flush_multipath_work(struct multipath *m)
 	flush_work(&m->trigger_event);
 
 	spin_lock_irqsave(&m->lock, flags);
-	m->pg_init_disabled = 0;
+	m->pg_init_disabled = false;
 	spin_unlock_irqrestore(&m->lock, flags);
 }
 
@@ -954,7 +984,7 @@ static int fail_path(struct pgpath *pgpath)
 	DMWARN("Failing path %s.", pgpath->path.dev->name);
 
 	pgpath->pg->ps.type->fail_path(&pgpath->pg->ps, &pgpath->path);
-	pgpath->is_active = 0;
+	pgpath->is_active = false;
 	pgpath->fail_count++;
 
 	m->nr_valid_paths--;
@@ -987,18 +1017,13 @@ static int reinstate_path(struct pgpath *pgpath)
 	if (pgpath->is_active)
 		goto out;
 
-	if (!pgpath->pg->ps.type->reinstate_path) {
-		DMWARN("Reinstate path not supported by path selector %s",
-		       pgpath->pg->ps.type->name);
-		r = -EINVAL;
-		goto out;
-	}
+	DMWARN("Reinstating path %s.", pgpath->path.dev->name);
 
 	r = pgpath->pg->ps.type->reinstate_path(&pgpath->pg->ps, &pgpath->path);
 	if (r)
 		goto out;
 
-	pgpath->is_active = 1;
+	pgpath->is_active = true;
 
 	if (!m->nr_valid_paths++) {
 		m->current_pgpath = NULL;
@@ -1045,7 +1070,7 @@ static int action_dev(struct multipath *m, struct dm_dev *dev,
  * Temporarily try to avoid having to use the specified PG
  */
 static void bypass_pg(struct multipath *m, struct priority_group *pg,
-		      int bypassed)
+		      bool bypassed)
 {
 	unsigned long flags;
 
@@ -1078,7 +1103,7 @@ static int switch_pg_num(struct multipath *m, const char *pgstr)
 
 	spin_lock_irqsave(&m->lock, flags);
 	list_for_each_entry(pg, &m->priority_groups, list) {
-		pg->bypassed = 0;
+		pg->bypassed = false;
 		if (--pgnum)
 			continue;
 
@@ -1096,7 +1121,7 @@ static int switch_pg_num(struct multipath *m, const char *pgstr)
  * Set/clear bypassed status of a PG.
  * PGs are numbered upwards from 1 in the order they were declared.
  */
-static int bypass_pg_num(struct multipath *m, const char *pgstr, int bypassed)
+static int bypass_pg_num(struct multipath *m, const char *pgstr, bool bypassed)
 {
 	struct priority_group *pg;
 	unsigned pgnum;
@@ -1120,17 +1145,17 @@ static int bypass_pg_num(struct multipath *m, const char *pgstr, int bypassed)
 /*
  * Should we retry pg_init immediately?
  */
-static int pg_init_limit_reached(struct multipath *m, struct pgpath *pgpath)
+static bool pg_init_limit_reached(struct multipath *m, struct pgpath *pgpath)
 {
 	unsigned long flags;
-	int limit_reached = 0;
+	bool limit_reached = false;
 
 	spin_lock_irqsave(&m->lock, flags);
 
 	if (m->pg_init_count <= m->pg_init_retries && !m->pg_init_disabled)
-		m->pg_init_required = 1;
+		m->pg_init_required = true;
 	else
-		limit_reached = 1;
+		limit_reached = true;
 
 	spin_unlock_irqrestore(&m->lock, flags);
 
@@ -1143,7 +1168,7 @@ static void pg_init_done(void *data, int errors)
 	struct priority_group *pg = pgpath->pg;
 	struct multipath *m = pg->m;
 	unsigned long flags;
-	unsigned delay_retry = 0;
+	bool delay_retry = false;
 
 	/* device or driver problems */
 	switch (errors) {
@@ -1166,7 +1191,7 @@ static void pg_init_done(void *data, int errors)
 		 * Probably doing something like FW upgrade on the
 		 * controller so try the other pg.
 		 */
-		bypass_pg(m, pg, 1);
+		bypass_pg(m, pg, true);
 		break;
 	case SCSI_DH_RETRY:
 		/* Wait before retrying. */
@@ -1177,6 +1202,7 @@ static void pg_init_done(void *data, int errors)
 			fail_path(pgpath);
 		errors = 0;
 		break;
+	case SCSI_DH_DEV_OFFLINED:
 	default:
 		/*
 		 * We probably do not want to fail the path for a device
@@ -1194,7 +1220,7 @@ static void pg_init_done(void *data, int errors)
 			m->current_pg = NULL;
 		}
 	} else if (!m->pg_init_required)
-		pg->bypassed = 0;
+		pg->bypassed = false;
 
 	if (--m->pg_init_in_progress)
 		/* Activations of other paths are still on going */
@@ -1205,7 +1231,7 @@ static void pg_init_done(void *data, int errors)
 		if (__pg_init_all_paths(m))
 			goto out;
 	}
-	m->queue_io = 0;
+	m->queue_io = false;
 
 	/*
 	 * Wake up any thread waiting to suspend.
@@ -1291,21 +1317,21 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone,
 			    int error, union map_info *map_context)
 {
 	struct multipath *m = ti->private;
-	struct dm_mpath_io *mpio = map_context->ptr;
+	struct dm_mpath_io *mpio = get_mpio(map_context);
 	struct pgpath *pgpath;
 	struct path_selector *ps;
 	int r;
 
 	BUG_ON(!mpio);
 
-	r  = do_end_io(m, clone, error, mpio);
+	r = do_end_io(m, clone, error, mpio);
 	pgpath = mpio->pgpath;
 	if (pgpath) {
 		ps = &pgpath->pg->ps;
 		if (ps->type->end_io)
 			ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes);
 	}
-	clear_mapinfo(m, map_context);
+	clear_request_fn_mpio(m, map_context);
 
 	return r;
 }
@@ -1318,9 +1344,9 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone,
  */
 static void multipath_presuspend(struct dm_target *ti)
 {
-	struct multipath *m = (struct multipath *) ti->private;
+	struct multipath *m = ti->private;
 
-	queue_if_no_path(m, 0, 1);
+	queue_if_no_path(m, false, true);
 }
 
 static void multipath_postsuspend(struct dm_target *ti)
@@ -1337,7 +1363,7 @@ static void multipath_postsuspend(struct dm_target *ti)
  */
 static void multipath_resume(struct dm_target *ti)
 {
-	struct multipath *m = (struct multipath *) ti->private;
+	struct multipath *m = ti->private;
 	unsigned long flags;
 
 	spin_lock_irqsave(&m->lock, flags);
@@ -1366,7 +1392,7 @@ static void multipath_status(struct dm_target *ti, status_type_t type,
 {
 	int sz = 0;
 	unsigned long flags;
-	struct multipath *m = (struct multipath *) ti->private;
+	struct multipath *m = ti->private;
 	struct priority_group *pg;
 	struct pgpath *p;
 	unsigned pg_num;
@@ -1474,7 +1500,7 @@ static int multipath_message(struct dm_target *ti, unsigned argc, char **argv)
 {
 	int r = -EINVAL;
 	struct dm_dev *dev;
-	struct multipath *m = (struct multipath *) ti->private;
+	struct multipath *m = ti->private;
 	action_fn action;
 
 	mutex_lock(&m->work_mutex);
@@ -1486,10 +1512,10 @@ static int multipath_message(struct dm_target *ti, unsigned argc, char **argv)
 
 	if (argc == 1) {
 		if (!strcasecmp(argv[0], "queue_if_no_path")) {
-			r = queue_if_no_path(m, 1, 0);
+			r = queue_if_no_path(m, true, false);
 			goto out;
 		} else if (!strcasecmp(argv[0], "fail_if_no_path")) {
-			r = queue_if_no_path(m, 0, 0);
+			r = queue_if_no_path(m, false, false);
 			goto out;
 		}
 	}
@@ -1500,10 +1526,10 @@ static int multipath_message(struct dm_target *ti, unsigned argc, char **argv)
 	}
 
 	if (!strcasecmp(argv[0], "disable_group")) {
-		r = bypass_pg_num(m, argv[1], 1);
+		r = bypass_pg_num(m, argv[1], true);
 		goto out;
 	} else if (!strcasecmp(argv[0], "enable_group")) {
-		r = bypass_pg_num(m, argv[1], 0);
+		r = bypass_pg_num(m, argv[1], false);
 		goto out;
 	} else if (!strcasecmp(argv[0], "switch_group")) {
 		r = switch_pg_num(m, argv[1]);
@@ -1604,7 +1630,7 @@ out:
 	return ret;
 }
 
-static int __pgpath_busy(struct pgpath *pgpath)
+static int pgpath_busy(struct pgpath *pgpath)
 {
 	struct request_queue *q = bdev_get_queue(pgpath->path.dev->bdev);
 
@@ -1621,7 +1647,7 @@ static int __pgpath_busy(struct pgpath *pgpath)
  */
 static int multipath_busy(struct dm_target *ti)
 {
-	int busy = 0, has_active = 0;
+	bool busy = false, has_active = false;
 	struct multipath *m = ti->private;
 	struct priority_group *pg;
 	struct pgpath *pgpath;
@@ -1632,7 +1658,7 @@ static int multipath_busy(struct dm_target *ti)
 	/* pg_init in progress or no paths available */
 	if (m->pg_init_in_progress ||
 	    (!m->nr_valid_paths && m->queue_if_no_path)) {
-		busy = 1;
+		busy = true;
 		goto out;
 	}
 	/* Guess which priority_group will be used at next mapping time */
@@ -1654,13 +1680,12 @@ static int multipath_busy(struct dm_target *ti)
 	 * If there is one non-busy active path at least, the path selector
 	 * will be able to select it. So we consider such a pg as not busy.
 	 */
-	busy = 1;
+	busy = true;
 	list_for_each_entry(pgpath, &pg->pgpaths, list)
 		if (pgpath->is_active) {
-			has_active = 1;
-
-			if (!__pgpath_busy(pgpath)) {
-				busy = 0;
+			has_active = true;
+			if (!pgpath_busy(pgpath)) {
+				busy = false;
 				break;
 			}
 		}
@@ -1671,7 +1696,7 @@ static int multipath_busy(struct dm_target *ti)
 		 * the current_pg will be changed at next mapping time.
 		 * We need to try mapping to determine it.
 		 */
-		busy = 0;
+		busy = false;
 
 out:
 	spin_unlock_irqrestore(&m->lock, flags);
@@ -1684,7 +1709,8 @@ out:
  *---------------------------------------------------------------*/
 static struct target_type multipath_target = {
 	.name = "multipath",
-	.version = {1, 10, 0},
+	.version = {1, 11, 0},
+	.features = DM_TARGET_SINGLETON | DM_TARGET_IMMUTABLE,
 	.module = THIS_MODULE,
 	.ctr = multipath_ctr,
 	.dtr = multipath_dtr,
diff --git a/drivers/md/dm-path-selector.h b/drivers/md/dm-path-selector.h
index e7d1fa8b0459..b6eb5365b1a4 100644
--- a/drivers/md/dm-path-selector.h
+++ b/drivers/md/dm-path-selector.h
@@ -50,13 +50,8 @@ struct path_selector_type {
 	/*
 	 * Chooses a path for this io, if no paths are available then
 	 * NULL will be returned.
-	 *
-	 * repeat_count is the number of times to use the path before
-	 * calling the function again.  0 means don't call it again unless
-	 * the path fails.
 	 */
 	struct dm_path *(*select_path) (struct path_selector *ps,
-					unsigned *repeat_count,
 					size_t nr_bytes);
 
 	/*
diff --git a/drivers/md/dm-queue-length.c b/drivers/md/dm-queue-length.c
index 3941fae0de9f..23f178641794 100644
--- a/drivers/md/dm-queue-length.c
+++ b/drivers/md/dm-queue-length.c
@@ -23,12 +23,13 @@
 #include <linux/atomic.h>
 
 #define DM_MSG_PREFIX	"multipath queue-length"
-#define QL_MIN_IO	128
-#define QL_VERSION	"0.1.0"
+#define QL_MIN_IO	1
+#define QL_VERSION	"0.2.0"
 
 struct selector {
 	struct list_head	valid_paths;
 	struct list_head	failed_paths;
+	spinlock_t lock;
 };
 
 struct path_info {
@@ -45,6 +46,7 @@ static struct selector *alloc_selector(void)
 	if (s) {
 		INIT_LIST_HEAD(&s->valid_paths);
 		INIT_LIST_HEAD(&s->failed_paths);
+		spin_lock_init(&s->lock);
 	}
 
 	return s;
@@ -113,6 +115,7 @@ static int ql_add_path(struct path_selector *ps, struct dm_path *path,
 	struct path_info *pi;
 	unsigned repeat_count = QL_MIN_IO;
 	char dummy;
+	unsigned long flags;
 
 	/*
 	 * Arguments: [<repeat_count>]
@@ -129,6 +132,11 @@ static int ql_add_path(struct path_selector *ps, struct dm_path *path,
 		return -EINVAL;
 	}
 
+	if (repeat_count > 1) {
+		DMWARN_LIMIT("repeat_count > 1 is deprecated, using 1 instead");
+		repeat_count = 1;
+	}
+
 	/* Allocate the path information structure */
 	pi = kmalloc(sizeof(*pi), GFP_KERNEL);
 	if (!pi) {
@@ -142,7 +150,9 @@ static int ql_add_path(struct path_selector *ps, struct dm_path *path,
 
 	path->pscontext = pi;
 
+	spin_lock_irqsave(&s->lock, flags);
 	list_add_tail(&pi->list, &s->valid_paths);
+	spin_unlock_irqrestore(&s->lock, flags);
 
 	return 0;
 }
@@ -151,16 +161,22 @@ static void ql_fail_path(struct path_selector *ps, struct dm_path *path)
 {
 	struct selector *s = ps->context;
 	struct path_info *pi = path->pscontext;
+	unsigned long flags;
 
+	spin_lock_irqsave(&s->lock, flags);
 	list_move(&pi->list, &s->failed_paths);
+	spin_unlock_irqrestore(&s->lock, flags);
 }
 
 static int ql_reinstate_path(struct path_selector *ps, struct dm_path *path)
 {
 	struct selector *s = ps->context;
 	struct path_info *pi = path->pscontext;
+	unsigned long flags;
 
+	spin_lock_irqsave(&s->lock, flags);
 	list_move_tail(&pi->list, &s->valid_paths);
+	spin_unlock_irqrestore(&s->lock, flags);
 
 	return 0;
 }
@@ -168,14 +184,16 @@ static int ql_reinstate_path(struct path_selector *ps, struct dm_path *path)
 /*
  * Select a path having the minimum number of in-flight I/Os
  */
-static struct dm_path *ql_select_path(struct path_selector *ps,
-				      unsigned *repeat_count, size_t nr_bytes)
+static struct dm_path *ql_select_path(struct path_selector *ps, size_t nr_bytes)
 {
 	struct selector *s = ps->context;
 	struct path_info *pi = NULL, *best = NULL;
+	struct dm_path *ret = NULL;
+	unsigned long flags;
 
+	spin_lock_irqsave(&s->lock, flags);
 	if (list_empty(&s->valid_paths))
-		return NULL;
+		goto out;
 
 	/* Change preferred (first in list) path to evenly balance. */
 	list_move_tail(s->valid_paths.next, &s->valid_paths);
@@ -190,11 +208,12 @@ static struct dm_path *ql_select_path(struct path_selector *ps,
 	}
 
 	if (!best)
-		return NULL;
-
-	*repeat_count = best->repeat_count;
+		goto out;
 
-	return best->path;
+	ret = best->path;
+out:
+	spin_unlock_irqrestore(&s->lock, flags);
+	return ret;
 }
 
 static int ql_start_io(struct path_selector *ps, struct dm_path *path,
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index f2a363a89629..b3ccf1e0d4f2 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1121,7 +1121,7 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	ti->num_flush_bios = 1;
 	ti->num_discard_bios = 1;
-	ti->per_bio_data_size = sizeof(struct dm_raid1_bio_record);
+	ti->per_io_data_size = sizeof(struct dm_raid1_bio_record);
 	ti->discard_zeroes_data_unsupported = true;
 
 	ms->kmirrord_wq = alloc_workqueue("kmirrord", WQ_MEM_RECLAIM, 0);
diff --git a/drivers/md/dm-round-robin.c b/drivers/md/dm-round-robin.c
index 6ab1192cdd5f..4ace1da17db8 100644
--- a/drivers/md/dm-round-robin.c
+++ b/drivers/md/dm-round-robin.c
@@ -17,6 +17,8 @@
 #include <linux/module.h>
 
 #define DM_MSG_PREFIX "multipath round-robin"
+#define RR_MIN_IO     1000
+#define RR_VERSION    "1.1.0"
 
 /*-----------------------------------------------------------------
  * Path-handling code, paths are held in lists
@@ -41,23 +43,48 @@ static void free_paths(struct list_head *paths)
  * Round-robin selector
  *---------------------------------------------------------------*/
 
-#define RR_MIN_IO		1000
-
 struct selector {
 	struct list_head valid_paths;
 	struct list_head invalid_paths;
+	spinlock_t lock;
+	struct dm_path * __percpu *current_path;
+	struct percpu_counter repeat_count;
 };
 
+static void set_percpu_current_path(struct selector *s, struct dm_path *path)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		*per_cpu_ptr(s->current_path, cpu) = path;
+}
+
 static struct selector *alloc_selector(void)
 {
 	struct selector *s = kmalloc(sizeof(*s), GFP_KERNEL);
 
-	if (s) {
-		INIT_LIST_HEAD(&s->valid_paths);
-		INIT_LIST_HEAD(&s->invalid_paths);
-	}
+	if (!s)
+		return NULL;
+
+	INIT_LIST_HEAD(&s->valid_paths);
+	INIT_LIST_HEAD(&s->invalid_paths);
+	spin_lock_init(&s->lock);
+
+	s->current_path = alloc_percpu(struct dm_path *);
+	if (!s->current_path)
+		goto out_current_path;
+	set_percpu_current_path(s, NULL);
+
+	if (percpu_counter_init(&s->repeat_count, 0, GFP_KERNEL))
+		goto out_repeat_count;
 
 	return s;
+
+out_repeat_count:
+	free_percpu(s->current_path);
+out_current_path:
+	kfree(s);
+	return NULL;;
 }
 
 static int rr_create(struct path_selector *ps, unsigned argc, char **argv)
@@ -74,10 +101,12 @@ static int rr_create(struct path_selector *ps, unsigned argc, char **argv)
 
 static void rr_destroy(struct path_selector *ps)
 {
-	struct selector *s = (struct selector *) ps->context;
+	struct selector *s = ps->context;
 
 	free_paths(&s->valid_paths);
 	free_paths(&s->invalid_paths);
+	free_percpu(s->current_path);
+	percpu_counter_destroy(&s->repeat_count);
 	kfree(s);
 	ps->context = NULL;
 }
@@ -111,10 +140,11 @@ static int rr_status(struct path_selector *ps, struct dm_path *path,
 static int rr_add_path(struct path_selector *ps, struct dm_path *path,
 		       int argc, char **argv, char **error)
 {
-	struct selector *s = (struct selector *) ps->context;
+	struct selector *s = ps->context;
 	struct path_info *pi;
 	unsigned repeat_count = RR_MIN_IO;
 	char dummy;
+	unsigned long flags;
 
 	if (argc > 1) {
 		*error = "round-robin ps: incorrect number of arguments";
@@ -139,42 +169,65 @@ static int rr_add_path(struct path_selector *ps, struct dm_path *path,
 
 	path->pscontext = pi;
 
+	spin_lock_irqsave(&s->lock, flags);
 	list_add_tail(&pi->list, &s->valid_paths);
+	spin_unlock_irqrestore(&s->lock, flags);
 
 	return 0;
 }
 
 static void rr_fail_path(struct path_selector *ps, struct dm_path *p)
 {
-	struct selector *s = (struct selector *) ps->context;
+	unsigned long flags;
+	struct selector *s = ps->context;
 	struct path_info *pi = p->pscontext;
 
+	spin_lock_irqsave(&s->lock, flags);
+	if (p == *this_cpu_ptr(s->current_path))
+		set_percpu_current_path(s, NULL);
+
 	list_move(&pi->list, &s->invalid_paths);
+	spin_unlock_irqrestore(&s->lock, flags);
 }
 
 static int rr_reinstate_path(struct path_selector *ps, struct dm_path *p)
 {
-	struct selector *s = (struct selector *) ps->context;
+	unsigned long flags;
+	struct selector *s = ps->context;
 	struct path_info *pi = p->pscontext;
 
+	spin_lock_irqsave(&s->lock, flags);
 	list_move(&pi->list, &s->valid_paths);
+	spin_unlock_irqrestore(&s->lock, flags);
 
 	return 0;
 }
 
-static struct dm_path *rr_select_path(struct path_selector *ps,
-				      unsigned *repeat_count, size_t nr_bytes)
+static struct dm_path *rr_select_path(struct path_selector *ps, size_t nr_bytes)
 {
-	struct selector *s = (struct selector *) ps->context;
+	unsigned long flags;
+	struct selector *s = ps->context;
 	struct path_info *pi = NULL;
+	struct dm_path *current_path = NULL;
+
+	current_path = *this_cpu_ptr(s->current_path);
+	if (current_path) {
+		percpu_counter_dec(&s->repeat_count);
+		if (percpu_counter_read_positive(&s->repeat_count) > 0)
+			return current_path;
+	}
 
+	spin_lock_irqsave(&s->lock, flags);
 	if (!list_empty(&s->valid_paths)) {
 		pi = list_entry(s->valid_paths.next, struct path_info, list);
 		list_move_tail(&pi->list, &s->valid_paths);
-		*repeat_count = pi->repeat_count;
+		percpu_counter_set(&s->repeat_count, pi->repeat_count);
+		set_percpu_current_path(s, pi->path);
+		current_path = pi->path;
 	}
+	spin_unlock_irqrestore(&s->lock, flags);
 
-	return pi ? pi->path : NULL;
+	return current_path;
 }
 
 static struct path_selector_type rr_ps = {
@@ -198,7 +251,7 @@ static int __init dm_rr_init(void)
 	if (r < 0)
 		DMERR("register failed %d", r);
 
-	DMINFO("version 1.0.0 loaded");
+	DMINFO("version " RR_VERSION " loaded");
 
 	return r;
 }
diff --git a/drivers/md/dm-service-time.c b/drivers/md/dm-service-time.c
index 9df8f6bd6418..7b8642045c55 100644
--- a/drivers/md/dm-service-time.c
+++ b/drivers/md/dm-service-time.c
@@ -19,11 +19,12 @@
 #define ST_MAX_RELATIVE_THROUGHPUT	100
 #define ST_MAX_RELATIVE_THROUGHPUT_SHIFT	7
 #define ST_MAX_INFLIGHT_SIZE	((size_t)-1 >> ST_MAX_RELATIVE_THROUGHPUT_SHIFT)
-#define ST_VERSION	"0.2.0"
+#define ST_VERSION	"0.3.0"
 
 struct selector {
 	struct list_head valid_paths;
 	struct list_head failed_paths;
+	spinlock_t lock;
 };
 
 struct path_info {
@@ -41,6 +42,7 @@ static struct selector *alloc_selector(void)
 	if (s) {
 		INIT_LIST_HEAD(&s->valid_paths);
 		INIT_LIST_HEAD(&s->failed_paths);
+		spin_lock_init(&s->lock);
 	}
 
 	return s;
@@ -111,6 +113,7 @@ static int st_add_path(struct path_selector *ps, struct dm_path *path,
 	unsigned repeat_count = ST_MIN_IO;
 	unsigned relative_throughput = 1;
 	char dummy;
+	unsigned long flags;
 
 	/*
 	 * Arguments: [<repeat_count> [<relative_throughput>]]
@@ -134,6 +137,11 @@ static int st_add_path(struct path_selector *ps, struct dm_path *path,
 		return -EINVAL;
 	}
 
+	if (repeat_count > 1) {
+		DMWARN_LIMIT("repeat_count > 1 is deprecated, using 1 instead");
+		repeat_count = 1;
+	}
+
 	if ((argc == 2) &&
 	    (sscanf(argv[1], "%u%c", &relative_throughput, &dummy) != 1 ||
 	     relative_throughput > ST_MAX_RELATIVE_THROUGHPUT)) {
@@ -155,7 +163,9 @@ static int st_add_path(struct path_selector *ps, struct dm_path *path,
 
 	path->pscontext = pi;
 
+	spin_lock_irqsave(&s->lock, flags);
 	list_add_tail(&pi->list, &s->valid_paths);
+	spin_unlock_irqrestore(&s->lock, flags);
 
 	return 0;
 }
@@ -164,16 +174,22 @@ static void st_fail_path(struct path_selector *ps, struct dm_path *path)
 {
 	struct selector *s = ps->context;
 	struct path_info *pi = path->pscontext;
+	unsigned long flags;
 
+	spin_lock_irqsave(&s->lock, flags);
 	list_move(&pi->list, &s->failed_paths);
+	spin_unlock_irqrestore(&s->lock, flags);
 }
 
 static int st_reinstate_path(struct path_selector *ps, struct dm_path *path)
 {
 	struct selector *s = ps->context;
 	struct path_info *pi = path->pscontext;
+	unsigned long flags;
 
+	spin_lock_irqsave(&s->lock, flags);
 	list_move_tail(&pi->list, &s->valid_paths);
+	spin_unlock_irqrestore(&s->lock, flags);
 
 	return 0;
 }
@@ -255,14 +271,16 @@ static int st_compare_load(struct path_info *pi1, struct path_info *pi2,
 	return pi2->relative_throughput - pi1->relative_throughput;
 }
 
-static struct dm_path *st_select_path(struct path_selector *ps,
-				      unsigned *repeat_count, size_t nr_bytes)
+static struct dm_path *st_select_path(struct path_selector *ps, size_t nr_bytes)
 {
 	struct selector *s = ps->context;
 	struct path_info *pi = NULL, *best = NULL;
+	struct dm_path *ret = NULL;
+	unsigned long flags;
 
+	spin_lock_irqsave(&s->lock, flags);
 	if (list_empty(&s->valid_paths))
-		return NULL;
+		goto out;
 
 	/* Change preferred (first in list) path to evenly balance. */
 	list_move_tail(s->valid_paths.next, &s->valid_paths);
@@ -272,11 +290,12 @@ static struct dm_path *st_select_path(struct path_selector *ps,
 			best = pi;
 
 	if (!best)
-		return NULL;
-
-	*repeat_count = best->repeat_count;
+		goto out;
 
-	return best->path;
+	ret = best->path;
+out:
+	spin_unlock_irqrestore(&s->lock, flags);
+	return ret;
 }
 
 static int st_start_io(struct path_selector *ps, struct dm_path *path,
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 3766386080a4..70bb0e8b62ce 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1105,6 +1105,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	int i;
 	int r = -EINVAL;
 	char *origin_path, *cow_path;
+	dev_t origin_dev, cow_dev;
 	unsigned args_used, num_flush_bios = 1;
 	fmode_t origin_mode = FMODE_READ;
 
@@ -1135,11 +1136,19 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		ti->error = "Cannot get origin device";
 		goto bad_origin;
 	}
+	origin_dev = s->origin->bdev->bd_dev;
 
 	cow_path = argv[0];
 	argv++;
 	argc--;
 
+	cow_dev = dm_get_dev_t(cow_path);
+	if (cow_dev && cow_dev == origin_dev) {
+		ti->error = "COW device cannot be the same as origin device";
+		r = -EINVAL;
+		goto bad_cow;
+	}
+
 	r = dm_get_device(ti, cow_path, dm_table_get_mode(ti->table), &s->cow);
 	if (r) {
 		ti->error = "Cannot get COW device";
@@ -1201,7 +1210,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	ti->private = s;
 	ti->num_flush_bios = num_flush_bios;
-	ti->per_bio_data_size = sizeof(struct dm_snap_tracked_chunk);
+	ti->per_io_data_size = sizeof(struct dm_snap_tracked_chunk);
 
 	/* Add snapshot to the list of snapshots for this origin */
 	/* Exceptions aren't triggered till snapshot_resume() is called */
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 061152a43730..f9e8f0bef332 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -365,6 +365,26 @@ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
 }
 
 /*
+ * Convert the path to a device
+ */
+dev_t dm_get_dev_t(const char *path)
+{
+	dev_t uninitialized_var(dev);
+	struct block_device *bdev;
+
+	bdev = lookup_bdev(path);
+	if (IS_ERR(bdev))
+		dev = name_to_dev_t(path);
+	else {
+		dev = bdev->bd_dev;
+		bdput(bdev);
+	}
+
+	return dev;
+}
+EXPORT_SYMBOL_GPL(dm_get_dev_t);
+
+/*
  * Add a device to the list, or just increment the usage count if
  * it's already present.
  */
@@ -372,23 +392,15 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
 		  struct dm_dev **result)
 {
 	int r;
-	dev_t uninitialized_var(dev);
+	dev_t dev;
 	struct dm_dev_internal *dd;
 	struct dm_table *t = ti->table;
-	struct block_device *bdev;
 
 	BUG_ON(!t);
 
-	/* convert the path to a device */
-	bdev = lookup_bdev(path);
-	if (IS_ERR(bdev)) {
-		dev = name_to_dev_t(path);
-		if (!dev)
-			return -ENODEV;
-	} else {
-		dev = bdev->bd_dev;
-		bdput(bdev);
-	}
+	dev = dm_get_dev_t(path);
+	if (!dev)
+		return -ENODEV;
 
 	dd = find_device(&t->devices, dev);
 	if (!dd) {
@@ -920,6 +932,30 @@ struct target_type *dm_table_get_immutable_target_type(struct dm_table *t)
 	return t->immutable_target_type;
 }
 
+struct dm_target *dm_table_get_immutable_target(struct dm_table *t)
+{
+	/* Immutable target is implicitly a singleton */
+	if (t->num_targets > 1 ||
+	    !dm_target_is_immutable(t->targets[0].type))
+		return NULL;
+
+	return t->targets;
+}
+
+struct dm_target *dm_table_get_wildcard_target(struct dm_table *t)
+{
+	struct dm_target *uninitialized_var(ti);
+	unsigned i = 0;
+
+	while (i < dm_table_get_num_targets(t)) {
+		ti = dm_table_get_target(t, i++);
+		if (dm_target_is_wildcard(ti->type))
+			return ti;
+	}
+
+	return NULL;
+}
+
 bool dm_table_request_based(struct dm_table *t)
 {
 	return __table_type_request_based(dm_table_get_type(t));
@@ -933,7 +969,7 @@ bool dm_table_mq_request_based(struct dm_table *t)
 static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *md)
 {
 	unsigned type = dm_table_get_type(t);
-	unsigned per_bio_data_size = 0;
+	unsigned per_io_data_size = 0;
 	struct dm_target *tgt;
 	unsigned i;
 
@@ -945,10 +981,10 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *
 	if (type == DM_TYPE_BIO_BASED)
 		for (i = 0; i < t->num_targets; i++) {
 			tgt = t->targets + i;
-			per_bio_data_size = max(per_bio_data_size, tgt->per_bio_data_size);
+			per_io_data_size = max(per_io_data_size, tgt->per_io_data_size);
 		}
 
-	t->mempools = dm_alloc_md_mempools(md, type, t->integrity_supported, per_bio_data_size);
+	t->mempools = dm_alloc_md_mempools(md, type, t->integrity_supported, per_io_data_size);
 	if (!t->mempools)
 		return -ENOMEM;
 
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index 925ec1b15e75..a317dd884ba6 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -150,7 +150,8 @@ static void io_err_release_clone_rq(struct request *clone)
 
 static struct target_type error_target = {
 	.name = "error",
-	.version = {1, 3, 0},
+	.version = {1, 4, 0},
+	.features = DM_TARGET_WILDCARD,
 	.ctr  = io_err_ctr,
 	.dtr  = io_err_dtr,
 	.map  = io_err_map,
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index f962d6453afd..43824d73366d 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -344,7 +344,7 @@ static void subtree_dec(void *context, const void *value)
 	memcpy(&root_le, value, sizeof(root_le));
 	root = le64_to_cpu(root_le);
 	if (dm_btree_del(info, root))
-		DMERR("btree delete failed\n");
+		DMERR("btree delete failed");
 }
 
 static int subtree_equal(void *context, const void *value1_le, const void *value2_le)
@@ -1981,5 +1981,8 @@ bool dm_pool_metadata_needs_check(struct dm_pool_metadata *pmd)
 
 void dm_pool_issue_prefetches(struct dm_pool_metadata *pmd)
 {
-	dm_tm_issue_prefetches(pmd->tm);
+	down_read(&pmd->root_lock);
+	if (!pmd->fail_io)
+		dm_tm_issue_prefetches(pmd->tm);
+	up_read(&pmd->root_lock);
 }
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 72d91f477683..92237b6fa8cd 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -235,6 +235,7 @@ struct pool {
 	struct pool_features pf;
 	bool low_water_triggered:1;	/* A dm event has been sent */
 	bool suspended:1;
+	bool out_of_data_space:1;
 
 	struct dm_bio_prison *prison;
 	struct dm_kcopyd_client *copier;
@@ -461,9 +462,16 @@ static void cell_error_with_code(struct pool *pool,
 	dm_bio_prison_free_cell(pool->prison, cell);
 }
 
+static int get_pool_io_error_code(struct pool *pool)
+{
+	return pool->out_of_data_space ? -ENOSPC : -EIO;
+}
+
 static void cell_error(struct pool *pool, struct dm_bio_prison_cell *cell)
 {
-	cell_error_with_code(pool, cell, -EIO);
+	int error = get_pool_io_error_code(pool);
+
+	cell_error_with_code(pool, cell, error);
 }
 
 static void cell_success(struct pool *pool, struct dm_bio_prison_cell *cell)
@@ -622,7 +630,9 @@ static void error_retry_list_with_code(struct pool *pool, int error)
 
 static void error_retry_list(struct pool *pool)
 {
-	return error_retry_list_with_code(pool, -EIO);
+	int error = get_pool_io_error_code(pool);
+
+	return error_retry_list_with_code(pool, error);
 }
 
 /*
@@ -2419,6 +2429,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 		 */
 		if (old_mode != new_mode)
 			notify_of_pool_mode_change_to_oods(pool);
+		pool->out_of_data_space = true;
 		pool->process_bio = process_bio_read_only;
 		pool->process_discard = process_discard_bio;
 		pool->process_cell = process_cell_read_only;
@@ -2432,6 +2443,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 	case PM_WRITE:
 		if (old_mode != new_mode)
 			notify_of_pool_mode_change(pool, "write");
+		pool->out_of_data_space = false;
 		pool->pf.error_if_no_space = pt->requested_pf.error_if_no_space;
 		dm_pool_metadata_read_write(pool->pmd);
 		pool->process_bio = process_bio;
@@ -2832,6 +2844,7 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 	INIT_LIST_HEAD(&pool->active_thins);
 	pool->low_water_triggered = false;
 	pool->suspended = true;
+	pool->out_of_data_space = false;
 
 	pool->shared_read_ds = dm_deferred_set_create();
 	if (!pool->shared_read_ds) {
@@ -3886,7 +3899,7 @@ static struct target_type pool_target = {
 	.name = "thin-pool",
 	.features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE |
 		    DM_TARGET_IMMUTABLE,
-	.version = {1, 17, 0},
+	.version = {1, 18, 0},
 	.module = THIS_MODULE,
 	.ctr = pool_ctr,
 	.dtr = pool_dtr,
@@ -4037,7 +4050,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 
 	ti->num_flush_bios = 1;
 	ti->flush_supported = true;
-	ti->per_bio_data_size = sizeof(struct dm_thin_endio_hook);
+	ti->per_io_data_size = sizeof(struct dm_thin_endio_hook);
 
 	/* In case the pool supports discards, pass them on. */
 	ti->discard_zeroes_data_unsupported = true;
@@ -4260,7 +4273,7 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type thin_target = {
 	.name = "thin",
-	.version = {1, 17, 0},
+	.version = {1, 18, 0},
 	.module	= THIS_MODULE,
 	.ctr = thin_ctr,
 	.dtr = thin_dtr,
diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
index 1cc10c4de701..459a9f8905ed 100644
--- a/drivers/md/dm-verity-fec.c
+++ b/drivers/md/dm-verity-fec.c
@@ -812,7 +812,7 @@ int verity_fec_ctr(struct dm_verity *v)
 	}
 
 	/* Reserve space for our per-bio data */
-	ti->per_bio_data_size += sizeof(struct dm_verity_fec_io);
+	ti->per_io_data_size += sizeof(struct dm_verity_fec_io);
 
 	return 0;
 }
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 5c5d30cb6ec5..0aba34a7b3b3 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -354,7 +354,7 @@ int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io,
 				       size_t len))
 {
 	unsigned todo = 1 << v->data_dev_block_bits;
-	struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_bio_data_size);
+	struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size);
 
 	do {
 		int r;
@@ -460,7 +460,7 @@ static int verity_verify_io(struct dm_verity_io *io)
 static void verity_finish_io(struct dm_verity_io *io, int error)
 {
 	struct dm_verity *v = io->v;
-	struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_bio_data_size);
+	struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size);
 
 	bio->bi_end_io = io->orig_bi_end_io;
 	bio->bi_error = error;
@@ -574,7 +574,7 @@ static int verity_map(struct dm_target *ti, struct bio *bio)
 	if (bio_data_dir(bio) == WRITE)
 		return -EIO;
 
-	io = dm_per_bio_data(bio, ti->per_bio_data_size);
+	io = dm_per_bio_data(bio, ti->per_io_data_size);
 	io->v = v;
 	io->orig_bi_end_io = bio->bi_end_io;
 	io->block = bio->bi_iter.bi_sector >> (v->data_dev_block_bits - SECTOR_SHIFT);
@@ -1036,15 +1036,15 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		goto bad;
 	}
 
-	ti->per_bio_data_size = sizeof(struct dm_verity_io) +
+	ti->per_io_data_size = sizeof(struct dm_verity_io) +
 				v->shash_descsize + v->digest_size * 2;
 
 	r = verity_fec_ctr(v);
 	if (r)
 		goto bad;
 
-	ti->per_bio_data_size = roundup(ti->per_bio_data_size,
-					__alignof__(struct dm_verity_io));
+	ti->per_io_data_size = roundup(ti->per_io_data_size,
+				       __alignof__(struct dm_verity_io));
 
 	return 0;
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 5df40480228b..be4905769a45 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -106,14 +106,6 @@ struct dm_rq_clone_bio_info {
 	struct bio clone;
 };
 
-union map_info *dm_get_rq_mapinfo(struct request *rq)
-{
-	if (rq && rq->end_io_data)
-		return &((struct dm_rq_target_io *)rq->end_io_data)->info;
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(dm_get_rq_mapinfo);
-
 #define MINOR_ALLOCED ((void *)-1)
 
 /*
@@ -129,28 +121,18 @@ EXPORT_SYMBOL_GPL(dm_get_rq_mapinfo);
 #define DMF_SUSPENDED_INTERNALLY 7
 
 /*
- * A dummy definition to make RCU happy.
- * struct dm_table should never be dereferenced in this file.
- */
-struct dm_table {
-	int undefined__;
-};
-
-/*
  * Work processed by per-device workqueue.
  */
 struct mapped_device {
 	struct srcu_struct io_barrier;
 	struct mutex suspend_lock;
-	atomic_t holders;
-	atomic_t open_count;
 
 	/*
-	 * The current mapping.
+	 * The current mapping (struct dm_table *).
 	 * Use dm_get_live_table{_fast} or take suspend_lock for
 	 * dereference.
 	 */
-	struct dm_table __rcu *map;
+	void __rcu *map;
 
 	struct list_head table_devices;
 	struct mutex table_devices_lock;
@@ -158,10 +140,16 @@ struct mapped_device {
 	unsigned long flags;
 
 	struct request_queue *queue;
+	int numa_node_id;
+
 	unsigned type;
 	/* Protect queue and type against concurrent access. */
 	struct mutex type_lock;
 
+	atomic_t holders;
+	atomic_t open_count;
+
+	struct dm_target *immutable_target;
 	struct target_type *immutable_target_type;
 
 	struct gendisk *disk;
@@ -175,8 +163,20 @@ struct mapped_device {
 	atomic_t pending[2];
 	wait_queue_head_t wait;
 	struct work_struct work;
-	struct bio_list deferred;
 	spinlock_t deferred_lock;
+	struct bio_list deferred;
+
+	/*
+	 * Event handling.
+	 */
+	wait_queue_head_t eventq;
+	atomic_t event_nr;
+	atomic_t uevent_seq;
+	struct list_head uevent_list;
+	spinlock_t uevent_lock; /* Protect access to uevent_list */
+
+	/* the number of internal suspends */
+	unsigned internal_suspend_count;
 
 	/*
 	 * Processing queue (flush)
@@ -192,32 +192,21 @@ struct mapped_device {
 	struct bio_set *bs;
 
 	/*
-	 * Event handling.
-	 */
-	atomic_t event_nr;
-	wait_queue_head_t eventq;
-	atomic_t uevent_seq;
-	struct list_head uevent_list;
-	spinlock_t uevent_lock; /* Protect access to uevent_list */
-
-	/*
 	 * freeze/thaw support require holding onto a super block
 	 */
 	struct super_block *frozen_sb;
-	struct block_device *bdev;
 
 	/* forced geometry settings */
 	struct hd_geometry geometry;
 
+	struct block_device *bdev;
+
 	/* kobject and completion */
 	struct dm_kobject_holder kobj_holder;
 
 	/* zero-length flush that will be cloned and submitted to targets */
 	struct bio flush_bio;
 
-	/* the number of internal suspends */
-	unsigned internal_suspend_count;
-
 	struct dm_stats stats;
 
 	struct kthread_worker kworker;
@@ -230,8 +219,9 @@ struct mapped_device {
 	ktime_t last_rq_start_time;
 
 	/* for blk-mq request-based DM support */
-	struct blk_mq_tag_set tag_set;
-	bool use_blk_mq;
+	struct blk_mq_tag_set *tag_set;
+	bool use_blk_mq:1;
+	bool init_tio_pdu:1;
 };
 
 #ifdef CONFIG_DM_MQ_DEFAULT
@@ -240,10 +230,19 @@ static bool use_blk_mq = true;
 static bool use_blk_mq = false;
 #endif
 
+#define DM_MQ_NR_HW_QUEUES 1
+#define DM_MQ_QUEUE_DEPTH 2048
+#define DM_NUMA_NODE NUMA_NO_NODE
+
+static unsigned dm_mq_nr_hw_queues = DM_MQ_NR_HW_QUEUES;
+static unsigned dm_mq_queue_depth = DM_MQ_QUEUE_DEPTH;
+static int dm_numa_node = DM_NUMA_NODE;
+
 bool dm_use_blk_mq(struct mapped_device *md)
 {
 	return md->use_blk_mq;
 }
+EXPORT_SYMBOL_GPL(dm_use_blk_mq);
 
 /*
  * For mempools pre-allocation at the table loading time.
@@ -277,6 +276,27 @@ static unsigned reserved_bio_based_ios = RESERVED_BIO_BASED_IOS;
  */
 static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS;
 
+static int __dm_get_module_param_int(int *module_param, int min, int max)
+{
+	int param = ACCESS_ONCE(*module_param);
+	int modified_param = 0;
+	bool modified = true;
+
+	if (param < min)
+		modified_param = min;
+	else if (param > max)
+		modified_param = max;
+	else
+		modified = false;
+
+	if (modified) {
+		(void)cmpxchg(module_param, param, modified_param);
+		param = modified_param;
+	}
+
+	return param;
+}
+
 static unsigned __dm_get_module_param(unsigned *module_param,
 				      unsigned def, unsigned max)
 {
@@ -310,6 +330,23 @@ unsigned dm_get_reserved_rq_based_ios(void)
 }
 EXPORT_SYMBOL_GPL(dm_get_reserved_rq_based_ios);
 
+static unsigned dm_get_blk_mq_nr_hw_queues(void)
+{
+	return __dm_get_module_param(&dm_mq_nr_hw_queues, 1, 32);
+}
+
+static unsigned dm_get_blk_mq_queue_depth(void)
+{
+	return __dm_get_module_param(&dm_mq_queue_depth,
+				     DM_MQ_QUEUE_DEPTH, BLK_MQ_MAX_DEPTH);
+}
+
+static unsigned dm_get_numa_node(void)
+{
+	return __dm_get_module_param_int(&dm_numa_node,
+					 DM_NUMA_NODE, num_online_nodes() - 1);
+}
+
 static int __init local_init(void)
 {
 	int r = -ENOMEM;
@@ -323,7 +360,7 @@ static int __init local_init(void)
 	if (!_rq_tio_cache)
 		goto out_free_io_cache;
 
-	_rq_cache = kmem_cache_create("dm_clone_request", sizeof(struct request),
+	_rq_cache = kmem_cache_create("dm_old_clone_request", sizeof(struct request),
 				      __alignof__(struct request), 0, NULL);
 	if (!_rq_cache)
 		goto out_free_rq_tio_cache;
@@ -556,16 +593,17 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return dm_get_geometry(md, geo);
 }
 
-static int dm_get_live_table_for_ioctl(struct mapped_device *md,
-		struct dm_target **tgt, struct block_device **bdev,
-		fmode_t *mode, int *srcu_idx)
+static int dm_grab_bdev_for_ioctl(struct mapped_device *md,
+				  struct block_device **bdev,
+				  fmode_t *mode)
 {
+	struct dm_target *tgt;
 	struct dm_table *map;
-	int r;
+	int srcu_idx, r;
 
 retry:
 	r = -ENOTTY;
-	map = dm_get_live_table(md, srcu_idx);
+	map = dm_get_live_table(md, &srcu_idx);
 	if (!map || !dm_table_get_size(map))
 		goto out;
 
@@ -573,9 +611,8 @@ retry:
 	if (dm_table_get_num_targets(map) != 1)
 		goto out;
 
-	*tgt = dm_table_get_target(map, 0);
-
-	if (!(*tgt)->type->prepare_ioctl)
+	tgt = dm_table_get_target(map, 0);
+	if (!tgt->type->prepare_ioctl)
 		goto out;
 
 	if (dm_suspended_md(md)) {
@@ -583,14 +620,16 @@ retry:
 		goto out;
 	}
 
-	r = (*tgt)->type->prepare_ioctl(*tgt, bdev, mode);
+	r = tgt->type->prepare_ioctl(tgt, bdev, mode);
 	if (r < 0)
 		goto out;
 
+	bdgrab(*bdev);
+	dm_put_live_table(md, srcu_idx);
 	return r;
 
 out:
-	dm_put_live_table(md, *srcu_idx);
+	dm_put_live_table(md, srcu_idx);
 	if (r == -ENOTCONN && !fatal_signal_pending(current)) {
 		msleep(10);
 		goto retry;
@@ -602,11 +641,9 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
 			unsigned int cmd, unsigned long arg)
 {
 	struct mapped_device *md = bdev->bd_disk->private_data;
-	struct dm_target *tgt;
-	struct block_device *tgt_bdev = NULL;
-	int srcu_idx, r;
+	int r;
 
-	r = dm_get_live_table_for_ioctl(md, &tgt, &tgt_bdev, &mode, &srcu_idx);
+	r = dm_grab_bdev_for_ioctl(md, &bdev, &mode);
 	if (r < 0)
 		return r;
 
@@ -621,9 +658,9 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
 			goto out;
 	}
 
-	r =  __blkdev_driver_ioctl(tgt_bdev, mode, cmd, arg);
+	r =  __blkdev_driver_ioctl(bdev, mode, cmd, arg);
 out:
-	dm_put_live_table(md, srcu_idx);
+	bdput(bdev);
 	return r;
 }
 
@@ -642,24 +679,24 @@ static void free_tio(struct mapped_device *md, struct dm_target_io *tio)
 	bio_put(&tio->clone);
 }
 
-static struct dm_rq_target_io *alloc_rq_tio(struct mapped_device *md,
-					    gfp_t gfp_mask)
+static struct dm_rq_target_io *alloc_old_rq_tio(struct mapped_device *md,
+						gfp_t gfp_mask)
 {
 	return mempool_alloc(md->io_pool, gfp_mask);
 }
 
-static void free_rq_tio(struct dm_rq_target_io *tio)
+static void free_old_rq_tio(struct dm_rq_target_io *tio)
 {
 	mempool_free(tio, tio->md->io_pool);
 }
 
-static struct request *alloc_clone_request(struct mapped_device *md,
-					   gfp_t gfp_mask)
+static struct request *alloc_old_clone_request(struct mapped_device *md,
+					       gfp_t gfp_mask)
 {
 	return mempool_alloc(md->rq_pool, gfp_mask);
 }
 
-static void free_clone_request(struct mapped_device *md, struct request *rq)
+static void free_old_clone_request(struct mapped_device *md, struct request *rq)
 {
 	mempool_free(rq, md->rq_pool);
 }
@@ -827,7 +864,7 @@ int dm_get_table_device(struct mapped_device *md, dev_t dev, fmode_t mode,
 	mutex_lock(&md->table_devices_lock);
 	td = find_table_device(&md->table_devices, dev, mode);
 	if (!td) {
-		td = kmalloc(sizeof(*td), GFP_KERNEL);
+		td = kmalloc_node(sizeof(*td), GFP_KERNEL, md->numa_node_id);
 		if (!td) {
 			mutex_unlock(&md->table_devices_lock);
 			return -ENOMEM;
@@ -1109,12 +1146,8 @@ static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
 	 * back into ->request_fn() could deadlock attempting to grab the
 	 * queue lock again.
 	 */
-	if (run_queue) {
-		if (md->queue->mq_ops)
-			blk_mq_run_hw_queues(md->queue, true);
-		else
-			blk_run_queue_async(md->queue);
-	}
+	if (!md->queue->mq_ops && run_queue)
+		blk_run_queue_async(md->queue);
 
 	/*
 	 * dm_put() must be at the end of this function. See the comment above
@@ -1134,15 +1167,10 @@ static void free_rq_clone(struct request *clone)
 		tio->ti->type->release_clone_rq(clone);
 	else if (!md->queue->mq_ops)
 		/* request_fn queue stacked on request_fn queue(s) */
-		free_clone_request(md, clone);
-	/*
-	 * NOTE: for the blk-mq queue stacked on request_fn queue(s) case:
-	 * no need to call free_clone_request() because we leverage blk-mq by
-	 * allocating the clone at the end of the blk-mq pdu (see: clone_rq)
-	 */
+		free_old_clone_request(md, clone);
 
 	if (!md->queue->mq_ops)
-		free_rq_tio(tio);
+		free_old_rq_tio(tio);
 }
 
 /*
@@ -1191,12 +1219,14 @@ static void dm_unprep_request(struct request *rq)
 
 	if (clone)
 		free_rq_clone(clone);
+	else if (!tio->md->queue->mq_ops)
+		free_old_rq_tio(tio);
 }
 
 /*
  * Requeue the original request of a clone.
  */
-static void old_requeue_request(struct request *rq)
+static void dm_old_requeue_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 	unsigned long flags;
@@ -1207,45 +1237,57 @@ static void old_requeue_request(struct request *rq)
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
+static void dm_mq_requeue_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	unsigned long flags;
+
+	blk_mq_requeue_request(rq);
+	spin_lock_irqsave(q->queue_lock, flags);
+	if (!blk_queue_stopped(q))
+		blk_mq_kick_requeue_list(q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
 static void dm_requeue_original_request(struct mapped_device *md,
 					struct request *rq)
 {
 	int rw = rq_data_dir(rq);
 
+	rq_end_stats(md, rq);
 	dm_unprep_request(rq);
 
-	rq_end_stats(md, rq);
 	if (!rq->q->mq_ops)
-		old_requeue_request(rq);
-	else {
-		blk_mq_requeue_request(rq);
-		blk_mq_kick_requeue_list(rq->q);
-	}
+		dm_old_requeue_request(rq);
+	else
+		dm_mq_requeue_request(rq);
 
 	rq_completed(md, rw, false);
 }
 
-static void old_stop_queue(struct request_queue *q)
+static void dm_old_stop_queue(struct request_queue *q)
 {
 	unsigned long flags;
 
-	if (blk_queue_stopped(q))
+	spin_lock_irqsave(q->queue_lock, flags);
+	if (blk_queue_stopped(q)) {
+		spin_unlock_irqrestore(q->queue_lock, flags);
 		return;
+	}
 
-	spin_lock_irqsave(q->queue_lock, flags);
 	blk_stop_queue(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
-static void stop_queue(struct request_queue *q)
+static void dm_stop_queue(struct request_queue *q)
 {
 	if (!q->mq_ops)
-		old_stop_queue(q);
+		dm_old_stop_queue(q);
 	else
 		blk_mq_stop_hw_queues(q);
 }
 
-static void old_start_queue(struct request_queue *q)
+static void dm_old_start_queue(struct request_queue *q)
 {
 	unsigned long flags;
 
@@ -1255,12 +1297,14 @@ static void old_start_queue(struct request_queue *q)
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
-static void start_queue(struct request_queue *q)
+static void dm_start_queue(struct request_queue *q)
 {
 	if (!q->mq_ops)
-		old_start_queue(q);
-	else
+		dm_old_start_queue(q);
+	else {
 		blk_mq_start_stopped_hw_queues(q, true);
+		blk_mq_kick_requeue_list(q);
+	}
 }
 
 static void dm_done(struct request *clone, int error, bool mapped)
@@ -1311,7 +1355,7 @@ static void dm_softirq_done(struct request *rq)
 		if (!rq->q->mq_ops) {
 			blk_end_request_all(rq, tio->error);
 			rq_completed(tio->md, rw, false);
-			free_rq_tio(tio);
+			free_old_rq_tio(tio);
 		} else {
 			blk_mq_end_request(rq, tio->error);
 			rq_completed(tio->md, rw, false);
@@ -1334,7 +1378,10 @@ static void dm_complete_request(struct request *rq, int error)
 	struct dm_rq_target_io *tio = tio_from_request(rq);
 
 	tio->error = error;
-	blk_complete_request(rq);
+	if (!rq->q->mq_ops)
+		blk_complete_request(rq);
+	else
+		blk_mq_complete_request(rq, error);
 }
 
 /*
@@ -1350,7 +1397,7 @@ static void dm_kill_unmapped_request(struct request *rq, int error)
 }
 
 /*
- * Called with the clone's queue lock held (for non-blk-mq)
+ * Called with the clone's queue lock held (in the case of .request_fn)
  */
 static void end_clone_request(struct request *clone, int error)
 {
@@ -1520,21 +1567,26 @@ static void bio_setup_sector(struct bio *bio, sector_t sector, unsigned len)
 /*
  * Creates a bio that consists of range of complete bvecs.
  */
-static void clone_bio(struct dm_target_io *tio, struct bio *bio,
-		      sector_t sector, unsigned len)
+static int clone_bio(struct dm_target_io *tio, struct bio *bio,
+		     sector_t sector, unsigned len)
 {
 	struct bio *clone = &tio->clone;
 
 	__bio_clone_fast(clone, bio);
 
-	if (bio_integrity(bio))
-		bio_integrity_clone(clone, bio, GFP_NOIO);
+	if (bio_integrity(bio)) {
+		int r = bio_integrity_clone(clone, bio, GFP_NOIO);
+		if (r < 0)
+			return r;
+	}
 
 	bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector));
 	clone->bi_iter.bi_size = to_bytes(len);
 
 	if (bio_integrity(bio))
 		bio_integrity_trim(clone, 0, len);
+
+	return 0;
 }
 
 static struct dm_target_io *alloc_tio(struct clone_info *ci,
@@ -1591,13 +1643,14 @@ static int __send_empty_flush(struct clone_info *ci)
 	return 0;
 }
 
-static void __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti,
+static int __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti,
 				     sector_t sector, unsigned *len)
 {
 	struct bio *bio = ci->bio;
 	struct dm_target_io *tio;
 	unsigned target_bio_nr;
 	unsigned num_target_bios = 1;
+	int r = 0;
 
 	/*
 	 * Does the target want to receive duplicate copies of the bio?
@@ -1608,9 +1661,13 @@ static void __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti
 	for (target_bio_nr = 0; target_bio_nr < num_target_bios; target_bio_nr++) {
 		tio = alloc_tio(ci, ti, target_bio_nr);
 		tio->len_ptr = len;
-		clone_bio(tio, bio, sector, *len);
+		r = clone_bio(tio, bio, sector, *len);
+		if (r < 0)
+			break;
 		__map_bio(tio);
 	}
+
+	return r;
 }
 
 typedef unsigned (*get_num_bios_fn)(struct dm_target *ti);
@@ -1687,6 +1744,7 @@ static int __split_and_process_non_flush(struct clone_info *ci)
 	struct bio *bio = ci->bio;
 	struct dm_target *ti;
 	unsigned len;
+	int r;
 
 	if (unlikely(bio->bi_rw & REQ_DISCARD))
 		return __send_discard(ci);
@@ -1699,7 +1757,9 @@ static int __split_and_process_non_flush(struct clone_info *ci)
 
 	len = min_t(sector_t, max_io_len(ci->sector, ti), ci->sector_count);
 
-	__clone_and_map_data_bio(ci, ti, ci->sector, &len);
+	r = __clone_and_map_data_bio(ci, ti, ci->sector, &len);
+	if (r < 0)
+		return r;
 
 	ci->sector += len;
 	ci->sector_count -= len;
@@ -1837,28 +1897,22 @@ static int setup_clone(struct request *clone, struct request *rq,
 	return 0;
 }
 
-static struct request *clone_rq(struct request *rq, struct mapped_device *md,
-				struct dm_rq_target_io *tio, gfp_t gfp_mask)
+static struct request *clone_old_rq(struct request *rq, struct mapped_device *md,
+				    struct dm_rq_target_io *tio, gfp_t gfp_mask)
 {
 	/*
-	 * Do not allocate a clone if tio->clone was already set
-	 * (see: dm_mq_queue_rq).
+	 * Create clone for use with .request_fn request_queue
 	 */
-	bool alloc_clone = !tio->clone;
 	struct request *clone;
 
-	if (alloc_clone) {
-		clone = alloc_clone_request(md, gfp_mask);
-		if (!clone)
-			return NULL;
-	} else
-		clone = tio->clone;
+	clone = alloc_old_clone_request(md, gfp_mask);
+	if (!clone)
+		return NULL;
 
 	blk_rq_init(NULL, clone);
 	if (setup_clone(clone, rq, tio, gfp_mask)) {
 		/* -ENOMEM */
-		if (alloc_clone)
-			free_clone_request(md, clone);
+		free_old_clone_request(md, clone);
 		return NULL;
 	}
 
@@ -1875,29 +1929,40 @@ static void init_tio(struct dm_rq_target_io *tio, struct request *rq,
 	tio->clone = NULL;
 	tio->orig = rq;
 	tio->error = 0;
-	memset(&tio->info, 0, sizeof(tio->info));
+	/*
+	 * Avoid initializing info for blk-mq; it passes
+	 * target-specific data through info.ptr
+	 * (see: dm_mq_init_request)
+	 */
+	if (!md->init_tio_pdu)
+		memset(&tio->info, 0, sizeof(tio->info));
 	if (md->kworker_task)
 		init_kthread_work(&tio->work, map_tio_request);
 }
 
-static struct dm_rq_target_io *prep_tio(struct request *rq,
-					struct mapped_device *md, gfp_t gfp_mask)
+static struct dm_rq_target_io *dm_old_prep_tio(struct request *rq,
+					       struct mapped_device *md,
+					       gfp_t gfp_mask)
 {
 	struct dm_rq_target_io *tio;
 	int srcu_idx;
 	struct dm_table *table;
 
-	tio = alloc_rq_tio(md, gfp_mask);
+	tio = alloc_old_rq_tio(md, gfp_mask);
 	if (!tio)
 		return NULL;
 
 	init_tio(tio, rq, md);
 
 	table = dm_get_live_table(md, &srcu_idx);
+	/*
+	 * Must clone a request if this .request_fn DM device
+	 * is stacked on .request_fn device(s).
+	 */
 	if (!dm_table_mq_request_based(table)) {
-		if (!clone_rq(rq, md, tio, gfp_mask)) {
+		if (!clone_old_rq(rq, md, tio, gfp_mask)) {
 			dm_put_live_table(md, srcu_idx);
-			free_rq_tio(tio);
+			free_old_rq_tio(tio);
 			return NULL;
 		}
 	}
@@ -1909,7 +1974,7 @@ static struct dm_rq_target_io *prep_tio(struct request *rq,
 /*
  * Called with the queue lock held.
  */
-static int dm_prep_fn(struct request_queue *q, struct request *rq)
+static int dm_old_prep_fn(struct request_queue *q, struct request *rq)
 {
 	struct mapped_device *md = q->queuedata;
 	struct dm_rq_target_io *tio;
@@ -1919,7 +1984,7 @@ static int dm_prep_fn(struct request_queue *q, struct request *rq)
 		return BLKPREP_KILL;
 	}
 
-	tio = prep_tio(rq, md, GFP_ATOMIC);
+	tio = dm_old_prep_tio(rq, md, GFP_ATOMIC);
 	if (!tio)
 		return BLKPREP_DEFER;
 
@@ -2077,12 +2142,18 @@ static bool dm_request_peeked_before_merge_deadline(struct mapped_device *md)
 static void dm_request_fn(struct request_queue *q)
 {
 	struct mapped_device *md = q->queuedata;
-	int srcu_idx;
-	struct dm_table *map = dm_get_live_table(md, &srcu_idx);
-	struct dm_target *ti;
+	struct dm_target *ti = md->immutable_target;
 	struct request *rq;
 	struct dm_rq_target_io *tio;
-	sector_t pos;
+	sector_t pos = 0;
+
+	if (unlikely(!ti)) {
+		int srcu_idx;
+		struct dm_table *map = dm_get_live_table(md, &srcu_idx);
+
+		ti = dm_table_find_target(map, pos);
+		dm_put_live_table(md, srcu_idx);
+	}
 
 	/*
 	 * For suspend, check blk_queue_stopped() and increment
@@ -2093,33 +2164,21 @@ static void dm_request_fn(struct request_queue *q)
 	while (!blk_queue_stopped(q)) {
 		rq = blk_peek_request(q);
 		if (!rq)
-			goto out;
+			return;
 
 		/* always use block 0 to find the target for flushes for now */
 		pos = 0;
 		if (!(rq->cmd_flags & REQ_FLUSH))
 			pos = blk_rq_pos(rq);
 
-		ti = dm_table_find_target(map, pos);
-		if (!dm_target_is_valid(ti)) {
-			/*
-			 * Must perform setup, that rq_completed() requires,
-			 * before calling dm_kill_unmapped_request
-			 */
-			DMERR_LIMIT("request attempted access beyond the end of device");
-			dm_start_request(md, rq);
-			dm_kill_unmapped_request(rq, -EIO);
-			continue;
+		if ((dm_request_peeked_before_merge_deadline(md) &&
+		     md_in_flight(md) && rq->bio && rq->bio->bi_vcnt == 1 &&
+		     md->last_rq_pos == pos && md->last_rq_rw == rq_data_dir(rq)) ||
+		    (ti->type->busy && ti->type->busy(ti))) {
+			blk_delay_queue(q, HZ / 100);
+			return;
 		}
 
-		if (dm_request_peeked_before_merge_deadline(md) &&
-		    md_in_flight(md) && rq->bio && rq->bio->bi_vcnt == 1 &&
-		    md->last_rq_pos == pos && md->last_rq_rw == rq_data_dir(rq))
-			goto delay_and_out;
-
-		if (ti->type->busy && ti->type->busy(ti))
-			goto delay_and_out;
-
 		dm_start_request(md, rq);
 
 		tio = tio_from_request(rq);
@@ -2128,13 +2187,6 @@ static void dm_request_fn(struct request_queue *q)
 		queue_kthread_work(&md->kworker, &tio->work);
 		BUG_ON(!irqs_disabled());
 	}
-
-	goto out;
-
-delay_and_out:
-	blk_delay_queue(q, HZ / 100);
-out:
-	dm_put_live_table(md, srcu_idx);
 }
 
 static int dm_any_congested(void *congested_data, int bdi_bits)
@@ -2144,19 +2196,18 @@ static int dm_any_congested(void *congested_data, int bdi_bits)
 	struct dm_table *map;
 
 	if (!test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) {
-		map = dm_get_live_table_fast(md);
-		if (map) {
+		if (dm_request_based(md)) {
 			/*
-			 * Request-based dm cares about only own queue for
-			 * the query about congestion status of request_queue
+			 * With request-based DM we only need to check the
+			 * top-level queue for congestion.
 			 */
-			if (dm_request_based(md))
-				r = md->queue->backing_dev_info.wb.state &
-				    bdi_bits;
-			else
+			r = md->queue->backing_dev_info.wb.state & bdi_bits;
+		} else {
+			map = dm_get_live_table_fast(md);
+			if (map)
 				r = dm_table_any_congested(map, bdi_bits);
+			dm_put_live_table_fast(md);
 		}
-		dm_put_live_table_fast(md);
 	}
 
 	return r;
@@ -2236,7 +2287,7 @@ static void dm_init_md_queue(struct mapped_device *md)
 	md->queue->backing_dev_info.congested_data = md;
 }
 
-static void dm_init_old_md_queue(struct mapped_device *md)
+static void dm_init_normal_md_queue(struct mapped_device *md)
 {
 	md->use_blk_mq = false;
 	dm_init_md_queue(md);
@@ -2283,10 +2334,11 @@ static void cleanup_mapped_device(struct mapped_device *md)
  */
 static struct mapped_device *alloc_dev(int minor)
 {
-	int r;
-	struct mapped_device *md = kzalloc(sizeof(*md), GFP_KERNEL);
+	int r, numa_node_id = dm_get_numa_node();
+	struct mapped_device *md;
 	void *old_md;
 
+	md = kzalloc_node(sizeof(*md), GFP_KERNEL, numa_node_id);
 	if (!md) {
 		DMWARN("unable to allocate device, out of memory.");
 		return NULL;
@@ -2307,7 +2359,9 @@ static struct mapped_device *alloc_dev(int minor)
 	if (r < 0)
 		goto bad_io_barrier;
 
+	md->numa_node_id = numa_node_id;
 	md->use_blk_mq = use_blk_mq;
+	md->init_tio_pdu = false;
 	md->type = DM_TYPE_NONE;
 	mutex_init(&md->suspend_lock);
 	mutex_init(&md->type_lock);
@@ -2321,13 +2375,13 @@ static struct mapped_device *alloc_dev(int minor)
 	INIT_LIST_HEAD(&md->table_devices);
 	spin_lock_init(&md->uevent_lock);
 
-	md->queue = blk_alloc_queue(GFP_KERNEL);
+	md->queue = blk_alloc_queue_node(GFP_KERNEL, numa_node_id);
 	if (!md->queue)
 		goto bad;
 
 	dm_init_md_queue(md);
 
-	md->disk = alloc_disk(1);
+	md->disk = alloc_disk_node(1, numa_node_id);
 	if (!md->disk)
 		goto bad;
 
@@ -2391,8 +2445,10 @@ static void free_dev(struct mapped_device *md)
 	unlock_fs(md);
 
 	cleanup_mapped_device(md);
-	if (md->use_blk_mq)
-		blk_mq_free_tag_set(&md->tag_set);
+	if (md->tag_set) {
+		blk_mq_free_tag_set(md->tag_set);
+		kfree(md->tag_set);
+	}
 
 	free_table_devices(&md->table_devices);
 	dm_stats_cleanup(&md->stats);
@@ -2500,13 +2556,20 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 	 * This must be done before setting the queue restrictions,
 	 * because request-based dm may be run just after the setting.
 	 */
-	if (dm_table_request_based(t))
-		stop_queue(q);
+	if (dm_table_request_based(t)) {
+		dm_stop_queue(q);
+		/*
+		 * Leverage the fact that request-based DM targets are
+		 * immutable singletons and establish md->immutable_target
+		 * - used to optimize both dm_request_fn and dm_mq_queue_rq
+		 */
+		md->immutable_target = dm_table_get_immutable_target(t);
+	}
 
 	__bind_mempools(md, t);
 
 	old_map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock));
-	rcu_assign_pointer(md->map, t);
+	rcu_assign_pointer(md->map, (void *)t);
 	md->immutable_target_type = dm_table_get_immutable_target_type(t);
 
 	dm_table_set_restrictions(t, q, limits);
@@ -2572,7 +2635,6 @@ void dm_set_md_type(struct mapped_device *md, unsigned type)
 
 unsigned dm_get_md_type(struct mapped_device *md)
 {
-	BUG_ON(!mutex_is_locked(&md->type_lock));
 	return md->type;
 }
 
@@ -2592,7 +2654,7 @@ struct queue_limits *dm_get_queue_limits(struct mapped_device *md)
 }
 EXPORT_SYMBOL_GPL(dm_get_queue_limits);
 
-static void init_rq_based_worker_thread(struct mapped_device *md)
+static void dm_old_init_rq_based_worker_thread(struct mapped_device *md)
 {
 	/* Initialize the request-based DM worker thread */
 	init_kthread_worker(&md->kworker);
@@ -2601,26 +2663,22 @@ static void init_rq_based_worker_thread(struct mapped_device *md)
 }
 
 /*
- * Fully initialize a request-based queue (->elevator, ->request_fn, etc).
+ * Fully initialize a .request_fn request-based queue.
  */
-static int dm_init_request_based_queue(struct mapped_device *md)
+static int dm_old_init_request_queue(struct mapped_device *md)
 {
-	struct request_queue *q = NULL;
-
 	/* Fully initialize the queue */
-	q = blk_init_allocated_queue(md->queue, dm_request_fn, NULL);
-	if (!q)
+	if (!blk_init_allocated_queue(md->queue, dm_request_fn, NULL))
 		return -EINVAL;
 
 	/* disable dm_request_fn's merge heuristic by default */
 	md->seq_rq_merge_deadline_usecs = 0;
 
-	md->queue = q;
-	dm_init_old_md_queue(md);
+	dm_init_normal_md_queue(md);
 	blk_queue_softirq_done(md->queue, dm_softirq_done);
-	blk_queue_prep_rq(md->queue, dm_prep_fn);
+	blk_queue_prep_rq(md->queue, dm_old_prep_fn);
 
-	init_rq_based_worker_thread(md);
+	dm_old_init_rq_based_worker_thread(md);
 
 	elv_register_queue(md->queue);
 
@@ -2640,6 +2698,11 @@ static int dm_mq_init_request(void *data, struct request *rq,
 	 */
 	tio->md = md;
 
+	if (md->init_tio_pdu) {
+		/* target-specific per-io data is immediately after the tio */
+		tio->info.ptr = tio + 1;
+	}
+
 	return 0;
 }
 
@@ -2649,28 +2712,15 @@ static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct request *rq = bd->rq;
 	struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
 	struct mapped_device *md = tio->md;
-	int srcu_idx;
-	struct dm_table *map = dm_get_live_table(md, &srcu_idx);
-	struct dm_target *ti;
-	sector_t pos;
+	struct dm_target *ti = md->immutable_target;
 
-	/* always use block 0 to find the target for flushes for now */
-	pos = 0;
-	if (!(rq->cmd_flags & REQ_FLUSH))
-		pos = blk_rq_pos(rq);
+	if (unlikely(!ti)) {
+		int srcu_idx;
+		struct dm_table *map = dm_get_live_table(md, &srcu_idx);
 
-	ti = dm_table_find_target(map, pos);
-	if (!dm_target_is_valid(ti)) {
+		ti = dm_table_find_target(map, 0);
 		dm_put_live_table(md, srcu_idx);
-		DMERR_LIMIT("request attempted access beyond the end of device");
-		/*
-		 * Must perform setup, that rq_completed() requires,
-		 * before returning BLK_MQ_RQ_QUEUE_ERROR
-		 */
-		dm_start_request(md, rq);
-		return BLK_MQ_RQ_QUEUE_ERROR;
 	}
-	dm_put_live_table(md, srcu_idx);
 
 	if (ti->type->busy && ti->type->busy(ti))
 		return BLK_MQ_RQ_QUEUE_BUSY;
@@ -2686,20 +2736,12 @@ static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
 	 */
 	tio->ti = ti;
 
-	/* Clone the request if underlying devices aren't blk-mq */
-	if (dm_table_get_type(map) == DM_TYPE_REQUEST_BASED) {
-		/* clone request is allocated at the end of the pdu */
-		tio->clone = (void *)blk_mq_rq_to_pdu(rq) + sizeof(struct dm_rq_target_io);
-		(void) clone_rq(rq, md, tio, GFP_ATOMIC);
-		queue_kthread_work(&md->kworker, &tio->work);
-	} else {
-		/* Direct call is fine since .queue_rq allows allocations */
-		if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) {
-			/* Undo dm_start_request() before requeuing */
-			rq_end_stats(md, rq);
-			rq_completed(md, rq_data_dir(rq), false);
-			return BLK_MQ_RQ_QUEUE_BUSY;
-		}
+	/* Direct call is fine since .queue_rq allows allocations */
+	if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) {
+		/* Undo dm_start_request() before requeuing */
+		rq_end_stats(md, rq);
+		rq_completed(md, rq_data_dir(rq), false);
+		return BLK_MQ_RQ_QUEUE_BUSY;
 	}
 
 	return BLK_MQ_RQ_QUEUE_OK;
@@ -2712,47 +2754,56 @@ static struct blk_mq_ops dm_mq_ops = {
 	.init_request = dm_mq_init_request,
 };
 
-static int dm_init_request_based_blk_mq_queue(struct mapped_device *md)
+static int dm_mq_init_request_queue(struct mapped_device *md,
+				    struct dm_target *immutable_tgt)
 {
-	unsigned md_type = dm_get_md_type(md);
 	struct request_queue *q;
 	int err;
 
-	memset(&md->tag_set, 0, sizeof(md->tag_set));
-	md->tag_set.ops = &dm_mq_ops;
-	md->tag_set.queue_depth = BLKDEV_MAX_RQ;
-	md->tag_set.numa_node = NUMA_NO_NODE;
-	md->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
-	md->tag_set.nr_hw_queues = 1;
-	if (md_type == DM_TYPE_REQUEST_BASED) {
-		/* make the memory for non-blk-mq clone part of the pdu */
-		md->tag_set.cmd_size = sizeof(struct dm_rq_target_io) + sizeof(struct request);
-	} else
-		md->tag_set.cmd_size = sizeof(struct dm_rq_target_io);
-	md->tag_set.driver_data = md;
-
-	err = blk_mq_alloc_tag_set(&md->tag_set);
+	if (dm_get_md_type(md) == DM_TYPE_REQUEST_BASED) {
+		DMERR("request-based dm-mq may only be stacked on blk-mq device(s)");
+		return -EINVAL;
+	}
+
+	md->tag_set = kzalloc_node(sizeof(struct blk_mq_tag_set), GFP_KERNEL, md->numa_node_id);
+	if (!md->tag_set)
+		return -ENOMEM;
+
+	md->tag_set->ops = &dm_mq_ops;
+	md->tag_set->queue_depth = dm_get_blk_mq_queue_depth();
+	md->tag_set->numa_node = md->numa_node_id;
+	md->tag_set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
+	md->tag_set->nr_hw_queues = dm_get_blk_mq_nr_hw_queues();
+	md->tag_set->driver_data = md;
+
+	md->tag_set->cmd_size = sizeof(struct dm_rq_target_io);
+	if (immutable_tgt && immutable_tgt->per_io_data_size) {
+		/* any target-specific per-io data is immediately after the tio */
+		md->tag_set->cmd_size += immutable_tgt->per_io_data_size;
+		md->init_tio_pdu = true;
+	}
+
+	err = blk_mq_alloc_tag_set(md->tag_set);
 	if (err)
-		return err;
+		goto out_kfree_tag_set;
 
-	q = blk_mq_init_allocated_queue(&md->tag_set, md->queue);
+	q = blk_mq_init_allocated_queue(md->tag_set, md->queue);
 	if (IS_ERR(q)) {
 		err = PTR_ERR(q);
 		goto out_tag_set;
 	}
-	md->queue = q;
 	dm_init_md_queue(md);
 
 	/* backfill 'mq' sysfs registration normally done in blk_register_queue */
 	blk_mq_register_disk(md->disk);
 
-	if (md_type == DM_TYPE_REQUEST_BASED)
-		init_rq_based_worker_thread(md);
-
 	return 0;
 
 out_tag_set:
-	blk_mq_free_tag_set(&md->tag_set);
+	blk_mq_free_tag_set(md->tag_set);
+out_kfree_tag_set:
+	kfree(md->tag_set);
+
 	return err;
 }
 
@@ -2767,28 +2818,28 @@ static unsigned filter_md_type(unsigned type, struct mapped_device *md)
 /*
  * Setup the DM device's queue based on md's type
  */
-int dm_setup_md_queue(struct mapped_device *md)
+int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 {
 	int r;
 	unsigned md_type = filter_md_type(dm_get_md_type(md), md);
 
 	switch (md_type) {
 	case DM_TYPE_REQUEST_BASED:
-		r = dm_init_request_based_queue(md);
+		r = dm_old_init_request_queue(md);
 		if (r) {
-			DMWARN("Cannot initialize queue for request-based mapped device");
+			DMERR("Cannot initialize queue for request-based mapped device");
 			return r;
 		}
 		break;
 	case DM_TYPE_MQ_REQUEST_BASED:
-		r = dm_init_request_based_blk_mq_queue(md);
+		r = dm_mq_init_request_queue(md, dm_table_get_immutable_target(t));
 		if (r) {
-			DMWARN("Cannot initialize queue for request-based blk-mq mapped device");
+			DMERR("Cannot initialize queue for request-based dm-mq mapped device");
 			return r;
 		}
 		break;
 	case DM_TYPE_BIO_BASED:
-		dm_init_old_md_queue(md);
+		dm_init_normal_md_queue(md);
 		blk_queue_make_request(md->queue, dm_make_request);
 		/*
 		 * DM handles splitting bios as needed.  Free the bio_split bioset
@@ -3131,7 +3182,7 @@ static int __dm_suspend(struct mapped_device *md, struct dm_table *map,
 	 * dm defers requests to md->wq from md->queue.
 	 */
 	if (dm_request_based(md)) {
-		stop_queue(md->queue);
+		dm_stop_queue(md->queue);
 		if (md->kworker_task)
 			flush_kthread_worker(&md->kworker);
 	}
@@ -3155,7 +3206,7 @@ static int __dm_suspend(struct mapped_device *md, struct dm_table *map,
 		dm_queue_flush(md);
 
 		if (dm_request_based(md))
-			start_queue(md->queue);
+			dm_start_queue(md->queue);
 
 		unlock_fs(md);
 		dm_table_presuspend_undo_targets(map);
@@ -3234,7 +3285,7 @@ static int __dm_resume(struct mapped_device *md, struct dm_table *map)
 	 * Request-based dm is queueing the deferred I/Os in its request_queue.
 	 */
 	if (dm_request_based(md))
-		start_queue(md->queue);
+		dm_start_queue(md->queue);
 
 	unlock_fs(md);
 
@@ -3480,9 +3531,9 @@ int dm_noflush_suspending(struct dm_target *ti)
 EXPORT_SYMBOL_GPL(dm_noflush_suspending);
 
 struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned type,
-					    unsigned integrity, unsigned per_bio_data_size)
+					    unsigned integrity, unsigned per_io_data_size)
 {
-	struct dm_md_mempools *pools = kzalloc(sizeof(*pools), GFP_KERNEL);
+	struct dm_md_mempools *pools = kzalloc_node(sizeof(*pools), GFP_KERNEL, md->numa_node_id);
 	struct kmem_cache *cachep = NULL;
 	unsigned int pool_size = 0;
 	unsigned int front_pad;
@@ -3496,7 +3547,7 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned t
 	case DM_TYPE_BIO_BASED:
 		cachep = _io_cache;
 		pool_size = dm_get_reserved_bio_based_ios();
-		front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
+		front_pad = roundup(per_io_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
 		break;
 	case DM_TYPE_REQUEST_BASED:
 		cachep = _rq_tio_cache;
@@ -3509,8 +3560,7 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned t
 		if (!pool_size)
 			pool_size = dm_get_reserved_rq_based_ios();
 		front_pad = offsetof(struct dm_rq_clone_bio_info, clone);
-		/* per_bio_data_size is not used. See __bind_mempools(). */
-		WARN_ON(per_bio_data_size != 0);
+		/* per_io_data_size is used for blk-mq pdu at queue allocation */
 		break;
 	default:
 		BUG();
@@ -3552,15 +3602,14 @@ void dm_free_md_mempools(struct dm_md_mempools *pools)
 }
 
 static int dm_pr_register(struct block_device *bdev, u64 old_key, u64 new_key,
-		u32 flags)
+			  u32 flags)
 {
 	struct mapped_device *md = bdev->bd_disk->private_data;
 	const struct pr_ops *ops;
-	struct dm_target *tgt;
 	fmode_t mode;
-	int srcu_idx, r;
+	int r;
 
-	r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+	r = dm_grab_bdev_for_ioctl(md, &bdev, &mode);
 	if (r < 0)
 		return r;
 
@@ -3570,20 +3619,19 @@ static int dm_pr_register(struct block_device *bdev, u64 old_key, u64 new_key,
 	else
 		r = -EOPNOTSUPP;
 
-	dm_put_live_table(md, srcu_idx);
+	bdput(bdev);
 	return r;
 }
 
 static int dm_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type,
-		u32 flags)
+			 u32 flags)
 {
 	struct mapped_device *md = bdev->bd_disk->private_data;
 	const struct pr_ops *ops;
-	struct dm_target *tgt;
 	fmode_t mode;
-	int srcu_idx, r;
+	int r;
 
-	r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+	r = dm_grab_bdev_for_ioctl(md, &bdev, &mode);
 	if (r < 0)
 		return r;
 
@@ -3593,7 +3641,7 @@ static int dm_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type,
 	else
 		r = -EOPNOTSUPP;
 
-	dm_put_live_table(md, srcu_idx);
+	bdput(bdev);
 	return r;
 }
 
@@ -3601,11 +3649,10 @@ static int dm_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
 {
 	struct mapped_device *md = bdev->bd_disk->private_data;
 	const struct pr_ops *ops;
-	struct dm_target *tgt;
 	fmode_t mode;
-	int srcu_idx, r;
+	int r;
 
-	r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+	r = dm_grab_bdev_for_ioctl(md, &bdev, &mode);
 	if (r < 0)
 		return r;
 
@@ -3615,20 +3662,19 @@ static int dm_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
 	else
 		r = -EOPNOTSUPP;
 
-	dm_put_live_table(md, srcu_idx);
+	bdput(bdev);
 	return r;
 }
 
 static int dm_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key,
-		enum pr_type type, bool abort)
+			 enum pr_type type, bool abort)
 {
 	struct mapped_device *md = bdev->bd_disk->private_data;
 	const struct pr_ops *ops;
-	struct dm_target *tgt;
 	fmode_t mode;
-	int srcu_idx, r;
+	int r;
 
-	r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+	r = dm_grab_bdev_for_ioctl(md, &bdev, &mode);
 	if (r < 0)
 		return r;
 
@@ -3638,7 +3684,7 @@ static int dm_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key,
 	else
 		r = -EOPNOTSUPP;
 
-	dm_put_live_table(md, srcu_idx);
+	bdput(bdev);
 	return r;
 }
 
@@ -3646,11 +3692,10 @@ static int dm_pr_clear(struct block_device *bdev, u64 key)
 {
 	struct mapped_device *md = bdev->bd_disk->private_data;
 	const struct pr_ops *ops;
-	struct dm_target *tgt;
 	fmode_t mode;
-	int srcu_idx, r;
+	int r;
 
-	r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+	r = dm_grab_bdev_for_ioctl(md, &bdev, &mode);
 	if (r < 0)
 		return r;
 
@@ -3660,7 +3705,7 @@ static int dm_pr_clear(struct block_device *bdev, u64 key)
 	else
 		r = -EOPNOTSUPP;
 
-	dm_put_live_table(md, srcu_idx);
+	bdput(bdev);
 	return r;
 }
 
@@ -3699,6 +3744,15 @@ MODULE_PARM_DESC(reserved_rq_based_ios, "Reserved IOs in request-based mempools"
 module_param(use_blk_mq, bool, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(use_blk_mq, "Use block multiqueue for request-based DM devices");
 
+module_param(dm_mq_nr_hw_queues, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(dm_mq_nr_hw_queues, "Number of hardware queues for request-based dm-mq devices");
+
+module_param(dm_mq_queue_depth, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(dm_mq_queue_depth, "Queue depth for request-based dm-mq devices");
+
+module_param(dm_numa_node, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(dm_numa_node, "NUMA node for DM device memory allocations");
+
 MODULE_DESCRIPTION(DM_NAME " driver");
 MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 7edcf97dfa5a..13a758ec0f88 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -73,6 +73,8 @@ int dm_table_resume_targets(struct dm_table *t);
 int dm_table_any_congested(struct dm_table *t, int bdi_bits);
 unsigned dm_table_get_type(struct dm_table *t);
 struct target_type *dm_table_get_immutable_target_type(struct dm_table *t);
+struct dm_target *dm_table_get_immutable_target(struct dm_table *t);
+struct dm_target *dm_table_get_wildcard_target(struct dm_table *t);
 bool dm_table_request_based(struct dm_table *t);
 bool dm_table_mq_request_based(struct dm_table *t);
 void dm_table_free_md_mempools(struct dm_table *t);
@@ -84,7 +86,7 @@ void dm_set_md_type(struct mapped_device *md, unsigned type);
 unsigned dm_get_md_type(struct mapped_device *md);
 struct target_type *dm_get_immutable_target_type(struct mapped_device *md);
 
-int dm_setup_md_queue(struct mapped_device *md);
+int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t);
 
 /*
  * To check the return value from dm_table_find_target().
diff --git a/drivers/media/common/b2c2/flexcop-fe-tuner.c b/drivers/media/common/b2c2/flexcop-fe-tuner.c
index 9c59f4306883..f5956402fc69 100644
--- a/drivers/media/common/b2c2/flexcop-fe-tuner.c
+++ b/drivers/media/common/b2c2/flexcop-fe-tuner.c
@@ -38,7 +38,7 @@ static int flexcop_fe_request_firmware(struct dvb_frontend *fe,
 #endif
 
 /* lnb control */
-#if FE_SUPPORTED(MT312) || FE_SUPPORTED(STV0299)
+#if (FE_SUPPORTED(MT312) || FE_SUPPORTED(STV0299)) && FE_SUPPORTED(PLL)
 static int flexcop_set_voltage(struct dvb_frontend *fe,
 			       enum fe_sec_voltage voltage)
 {
@@ -68,7 +68,7 @@ static int flexcop_set_voltage(struct dvb_frontend *fe,
 #endif
 
 #if FE_SUPPORTED(S5H1420) || FE_SUPPORTED(STV0299) || FE_SUPPORTED(MT312)
-static int flexcop_sleep(struct dvb_frontend* fe)
+static int __maybe_unused flexcop_sleep(struct dvb_frontend* fe)
 {
 	struct flexcop_device *fc = fe->dvb->priv;
 	if (fc->fe_sleep)
diff --git a/drivers/media/common/b2c2/flexcop.c b/drivers/media/common/b2c2/flexcop.c
index 412c5daf2b48..0f5114d406f8 100644
--- a/drivers/media/common/b2c2/flexcop.c
+++ b/drivers/media/common/b2c2/flexcop.c
@@ -1,7 +1,7 @@
 /*
  * Linux driver for digital TV devices equipped with B2C2 FlexcopII(b)/III
  * flexcop.c - main module part
- * Copyright (C) 2004-9 Patrick Boettcher <patrick.boettcher@desy.de>
+ * Copyright (C) 2004-9 Patrick Boettcher <patrick.boettcher@posteo.de>
  * based on skystar2-driver Copyright (C) 2003 Vadim Catana, skystar@moldova.cc
  *
  * Acknowledgements:
@@ -34,7 +34,7 @@
 #include "flexcop.h"
 
 #define DRIVER_NAME "B2C2 FlexcopII/II(b)/III digital TV receiver chip"
-#define DRIVER_AUTHOR "Patrick Boettcher <patrick.boettcher@desy.de"
+#define DRIVER_AUTHOR "Patrick Boettcher <patrick.boettcher@posteo.de"
 
 #ifdef CONFIG_DVB_B2C2_FLEXCOP_DEBUG
 #define DEBSTATUS ""
diff --git a/drivers/media/common/cypress_firmware.c b/drivers/media/common/cypress_firmware.c
index 577e82058fdc..50e3f76d4847 100644
--- a/drivers/media/common/cypress_firmware.c
+++ b/drivers/media/common/cypress_firmware.c
@@ -1,6 +1,6 @@
 /*  cypress_firmware.c is part of the DVB USB library.
  *
- * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@posteo.de)
  * see dvb-usb-init.c for copyright information.
  *
  * This file contains functions for downloading the firmware to Cypress FX 1
diff --git a/drivers/media/common/cypress_firmware.h b/drivers/media/common/cypress_firmware.h
index e493cbc7a528..1e4f27356205 100644
--- a/drivers/media/common/cypress_firmware.h
+++ b/drivers/media/common/cypress_firmware.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@posteo.de)
  * see dvb-usb-init.c for copyright information.
  *
  * This file contains functions for downloading the firmware to Cypress FX 1
diff --git a/drivers/media/common/siano/smscoreapi.c b/drivers/media/common/siano/smscoreapi.c
index 2a8d9a36d6f0..f3a42834d7d6 100644
--- a/drivers/media/common/siano/smscoreapi.c
+++ b/drivers/media/common/siano/smscoreapi.c
@@ -1167,8 +1167,8 @@ static int smscore_load_firmware_from_file(struct smscore_device_t *coredev,
 		return rc;
 	}
 	pr_debug("read fw %s, buffer size=0x%zx\n", fw_filename, fw->size);
-	fw_buf = kmalloc(ALIGN(fw->size, SMS_ALLOC_ALIGNMENT),
-			 GFP_KERNEL | GFP_DMA);
+	fw_buf = kmalloc(ALIGN(fw->size + sizeof(struct sms_firmware),
+			 SMS_ALLOC_ALIGNMENT), GFP_KERNEL | GFP_DMA);
 	if (!fw_buf) {
 		pr_err("failed to allocate firmware buffer\n");
 		rc = -ENOMEM;
diff --git a/drivers/media/common/siano/smsdvb-main.c b/drivers/media/common/siano/smsdvb-main.c
index d31f468830cf..9148e14c9d07 100644
--- a/drivers/media/common/siano/smsdvb-main.c
+++ b/drivers/media/common/siano/smsdvb-main.c
@@ -1015,12 +1015,6 @@ static int smsdvb_set_frontend(struct dvb_frontend *fe)
 	}
 }
 
-/* Nothing to do here, as stats are automatically updated */
-static int smsdvb_get_frontend(struct dvb_frontend *fe)
-{
-	return 0;
-}
-
 static int smsdvb_init(struct dvb_frontend *fe)
 {
 	struct smsdvb_client_t *client =
@@ -1069,7 +1063,6 @@ static struct dvb_frontend_ops smsdvb_fe_ops = {
 	.release = smsdvb_release,
 
 	.set_frontend = smsdvb_set_frontend,
-	.get_frontend = smsdvb_get_frontend,
 	.get_tune_settings = smsdvb_get_tune_settings,
 
 	.read_status = smsdvb_read_status,
diff --git a/drivers/media/dvb-core/dvb-usb-ids.h b/drivers/media/dvb-core/dvb-usb-ids.h
index 1c1c298d2289..0afad395ef97 100644
--- a/drivers/media/dvb-core/dvb-usb-ids.h
+++ b/drivers/media/dvb-core/dvb-usb-ids.h
@@ -1,6 +1,6 @@
 /* dvb-usb-ids.h is part of the DVB USB library.
  *
- * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@desy.de) see
+ * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@posteo.de) see
  * dvb-usb-init.c for copyright information.
  *
  * a header file containing define's for the USB device supported by the
@@ -118,6 +118,7 @@
 #define USB_PID_DIBCOM_STK807XP				0x1f90
 #define USB_PID_DIBCOM_STK807XPVR			0x1f98
 #define USB_PID_DIBCOM_STK8096GP                        0x1fa0
+#define USB_PID_DIBCOM_STK8096PVR                       0x1faa
 #define USB_PID_DIBCOM_NIM8096MD                        0x1fa8
 #define USB_PID_DIBCOM_TFE8096P				0x1f9C
 #define USB_PID_DIBCOM_ANCHOR_2135_COLD			0x2131
@@ -241,12 +242,14 @@
 #define USB_PID_AVERMEDIA_1867				0x1867
 #define USB_PID_AVERMEDIA_A867				0xa867
 #define USB_PID_AVERMEDIA_H335				0x0335
+#define USB_PID_AVERMEDIA_TD110				0xa110
 #define USB_PID_AVERMEDIA_TWINSTAR			0x0825
 #define USB_PID_TECHNOTREND_CONNECT_S2400               0x3006
 #define USB_PID_TECHNOTREND_CONNECT_S2400_8KEEPROM	0x3009
 #define USB_PID_TECHNOTREND_CONNECT_CT3650		0x300d
 #define USB_PID_TECHNOTREND_CONNECT_S2_4600             0x3011
 #define USB_PID_TECHNOTREND_CONNECT_CT2_4650_CI		0x3012
+#define USB_PID_TECHNOTREND_CONNECT_CT2_4650_CI_2	0x3015
 #define USB_PID_TECHNOTREND_TVSTICK_CT2_4400		0x3014
 #define USB_PID_TERRATEC_CINERGY_DT_XS_DIVERSITY	0x005a
 #define USB_PID_TERRATEC_CINERGY_DT_XS_DIVERSITY_2	0x0081
@@ -255,6 +258,10 @@
 #define USB_PID_TERRATEC_CINERGY_T_EXPRESS		0x0062
 #define USB_PID_TERRATEC_CINERGY_T_XXS			0x0078
 #define USB_PID_TERRATEC_CINERGY_T_XXS_2		0x00ab
+#define USB_PID_TERRATEC_CINERGY_S2_R1			0x00a8
+#define USB_PID_TERRATEC_CINERGY_S2_R2			0x00b0
+#define USB_PID_TERRATEC_CINERGY_S2_R3			0x0102
+#define USB_PID_TERRATEC_CINERGY_S2_R4			0x0105
 #define USB_PID_TERRATEC_H7				0x10b4
 #define USB_PID_TERRATEC_H7_2				0x10a3
 #define USB_PID_TERRATEC_H7_3				0x10a5
diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c
index 40080645341e..c0142614c408 100644
--- a/drivers/media/dvb-core/dvb_frontend.c
+++ b/drivers/media/dvb-core/dvb_frontend.c
@@ -134,15 +134,17 @@ struct dvb_frontend_private {
 
 #if defined(CONFIG_MEDIA_CONTROLLER_DVB)
 	struct media_pipeline pipe;
-	struct media_entity *pipe_start_entity;
 #endif
 };
 
 static void dvb_frontend_wakeup(struct dvb_frontend *fe);
 static int dtv_get_frontend(struct dvb_frontend *fe,
+			    struct dtv_frontend_properties *c,
 			    struct dvb_frontend_parameters *p_out);
-static int dtv_property_legacy_params_sync(struct dvb_frontend *fe,
-					   struct dvb_frontend_parameters *p);
+static int
+dtv_property_legacy_params_sync(struct dvb_frontend *fe,
+				const struct dtv_frontend_properties *c,
+				struct dvb_frontend_parameters *p);
 
 static bool has_get_frontend(struct dvb_frontend *fe)
 {
@@ -202,6 +204,7 @@ static void dvb_frontend_add_event(struct dvb_frontend *fe,
 				   enum fe_status status)
 {
 	struct dvb_frontend_private *fepriv = fe->frontend_priv;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	struct dvb_fe_events *events = &fepriv->events;
 	struct dvb_frontend_event *e;
 	int wp;
@@ -209,7 +212,7 @@ static void dvb_frontend_add_event(struct dvb_frontend *fe,
 	dev_dbg(fe->dvb->device, "%s:\n", __func__);
 
 	if ((status & FE_HAS_LOCK) && has_get_frontend(fe))
-		dtv_get_frontend(fe, &fepriv->parameters_out);
+		dtv_get_frontend(fe, c, &fepriv->parameters_out);
 
 	mutex_lock(&events->mtx);
 
@@ -596,104 +599,13 @@ static void dvb_frontend_wakeup(struct dvb_frontend *fe)
 	wake_up_interruptible(&fepriv->wait_queue);
 }
 
-/**
- * dvb_enable_media_tuner() - tries to enable the DVB tuner
- *
- * @fe:		struct dvb_frontend pointer
- *
- * This function ensures that just one media tuner is enabled for a given
- * frontend. It has two different behaviors:
- * - For trivial devices with just one tuner:
- *   it just enables the existing tuner->fe link
- * - For devices with more than one tuner:
- *   It is up to the driver to implement the logic that will enable one tuner
- *   and disable the other ones. However, if more than one tuner is enabled for
- *   the same frontend, it will print an error message and return -EINVAL.
- *
- * At return, it will return the error code returned by media_entity_setup_link,
- * or 0 if everything is OK, if no tuner is linked to the frontend or if the
- * mdev is NULL.
- */
-#ifdef CONFIG_MEDIA_CONTROLLER_DVB
-static int dvb_enable_media_tuner(struct dvb_frontend *fe)
-{
-	struct dvb_frontend_private *fepriv = fe->frontend_priv;
-	struct dvb_adapter *adapter = fe->dvb;
-	struct media_device *mdev = adapter->mdev;
-	struct media_entity  *entity, *source;
-	struct media_link *link, *found_link = NULL;
-	int ret, n_links = 0, active_links = 0;
-
-	fepriv->pipe_start_entity = NULL;
-
-	if (!mdev)
-		return 0;
-
-	entity = fepriv->dvbdev->entity;
-	fepriv->pipe_start_entity = entity;
-
-	list_for_each_entry(link, &entity->links, list) {
-		if (link->sink->entity == entity) {
-			found_link = link;
-			n_links++;
-			if (link->flags & MEDIA_LNK_FL_ENABLED)
-				active_links++;
-		}
-	}
-
-	if (!n_links || active_links == 1 || !found_link)
-		return 0;
-
-	/*
-	 * If a frontend has more than one tuner linked, it is up to the driver
-	 * to select with one will be the active one, as the frontend core can't
-	 * guess. If the driver doesn't do that, it is a bug.
-	 */
-	if (n_links > 1 && active_links != 1) {
-		dev_err(fe->dvb->device,
-			"WARNING: there are %d active links among %d tuners. This is a driver's bug!\n",
-			active_links, n_links);
-		return -EINVAL;
-	}
-
-	source = found_link->source->entity;
-	fepriv->pipe_start_entity = source;
-	list_for_each_entry(link, &source->links, list) {
-		struct media_entity *sink;
-		int flags = 0;
-
-		sink = link->sink->entity;
-		if (sink == entity)
-			flags = MEDIA_LNK_FL_ENABLED;
-
-		ret = media_entity_setup_link(link, flags);
-		if (ret) {
-			dev_err(fe->dvb->device,
-				"Couldn't change link %s->%s to %s. Error %d\n",
-				source->name, sink->name,
-				flags ? "enabled" : "disabled",
-				ret);
-			return ret;
-		} else
-			dev_dbg(fe->dvb->device,
-				"link %s->%s was %s\n",
-				source->name, sink->name,
-				flags ? "ENABLED" : "disabled");
-	}
-	return 0;
-}
-#endif
-
 static int dvb_frontend_thread(void *data)
 {
 	struct dvb_frontend *fe = data;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	struct dvb_frontend_private *fepriv = fe->frontend_priv;
 	enum fe_status s;
 	enum dvbfe_algo algo;
-#ifdef CONFIG_MEDIA_CONTROLLER_DVB
-	int ret;
-#endif
-
 	bool re_tune = false;
 	bool semheld = false;
 
@@ -706,20 +618,6 @@ static int dvb_frontend_thread(void *data)
 	fepriv->wakeup = 0;
 	fepriv->reinitialise = 0;
 
-#ifdef CONFIG_MEDIA_CONTROLLER_DVB
-	ret = dvb_enable_media_tuner(fe);
-	if (ret) {
-		/* FIXME: return an error if it fails */
-		dev_info(fe->dvb->device,
-			"proceeding with FE task\n");
-	} else if (fepriv->pipe_start_entity) {
-		ret = media_entity_pipeline_start(fepriv->pipe_start_entity,
-						  &fepriv->pipe);
-		if (ret)
-			return ret;
-	}
-#endif
-
 	dvb_frontend_init(fe);
 
 	set_freezable();
@@ -807,7 +705,7 @@ restart:
 					fepriv->algo_status |= DVBFE_ALGO_SEARCH_AGAIN;
 					fepriv->delay = HZ / 2;
 				}
-				dtv_property_legacy_params_sync(fe, &fepriv->parameters_out);
+				dtv_property_legacy_params_sync(fe, c, &fepriv->parameters_out);
 				fe->ops.read_status(fe, &s);
 				if (s != fepriv->status) {
 					dvb_frontend_add_event(fe, s); /* update event list */
@@ -829,12 +727,6 @@ restart:
 		}
 	}
 
-#ifdef CONFIG_MEDIA_CONTROLLER_DVB
-	if (fepriv->pipe_start_entity)
-		media_entity_pipeline_stop(fepriv->pipe_start_entity);
-	fepriv->pipe_start_entity = NULL;
-#endif
-
 	if (dvb_powerdown_on_sleep) {
 		if (fe->ops.set_voltage)
 			fe->ops.set_voltage(fe, SEC_VOLTAGE_OFF);
@@ -899,10 +791,10 @@ void dvb_frontend_sleep_until(ktime_t *waketime, u32 add_usec)
 	s32 delta;
 
 	*waketime = ktime_add_us(*waketime, add_usec);
-	delta = ktime_us_delta(ktime_get_real(), *waketime);
+	delta = ktime_us_delta(ktime_get_boottime(), *waketime);
 	if (delta > 2500) {
 		msleep((delta - 1500) / 1000);
-		delta = ktime_us_delta(ktime_get_real(), *waketime);
+		delta = ktime_us_delta(ktime_get_boottime(), *waketime);
 	}
 	if (delta > 0)
 		udelay(delta);
@@ -1162,18 +1054,24 @@ static struct dtv_cmds_h dtv_cmds[DTV_MAX_COMMAND + 1] = {
 	_DTV_CMD(DTV_STAT_TOTAL_BLOCK_COUNT, 0, 0),
 };
 
-static void dtv_property_dump(struct dvb_frontend *fe, struct dtv_property *tvp)
+static void dtv_property_dump(struct dvb_frontend *fe,
+			      bool is_set,
+			      struct dtv_property *tvp)
 {
 	int i;
 
 	if (tvp->cmd <= 0 || tvp->cmd > DTV_MAX_COMMAND) {
-		dev_warn(fe->dvb->device, "%s: tvp.cmd = 0x%08x undefined\n",
-				__func__, tvp->cmd);
+		dev_warn(fe->dvb->device, "%s: %s tvp.cmd = 0x%08x undefined\n",
+				__func__,
+				is_set ? "SET" : "GET",
+				tvp->cmd);
 		return;
 	}
 
-	dev_dbg(fe->dvb->device, "%s: tvp.cmd    = 0x%08x (%s)\n", __func__,
-			tvp->cmd, dtv_cmds[tvp->cmd].name);
+	dev_dbg(fe->dvb->device, "%s: %s tvp.cmd    = 0x%08x (%s)\n", __func__,
+		is_set ? "SET" : "GET",
+		tvp->cmd,
+		dtv_cmds[tvp->cmd].name);
 
 	if (dtv_cmds[tvp->cmd].buffer) {
 		dev_dbg(fe->dvb->device, "%s: tvp.u.buffer.len = 0x%02x\n",
@@ -1268,11 +1166,11 @@ static int dtv_property_cache_sync(struct dvb_frontend *fe,
 /* Ensure the cached values are set correctly in the frontend
  * legacy tuning structures, for the advanced tuning API.
  */
-static int dtv_property_legacy_params_sync(struct dvb_frontend *fe,
-					    struct dvb_frontend_parameters *p)
+static int
+dtv_property_legacy_params_sync(struct dvb_frontend *fe,
+				const struct dtv_frontend_properties *c,
+				struct dvb_frontend_parameters *p)
 {
-	const struct dtv_frontend_properties *c = &fe->dtv_property_cache;
-
 	p->frequency = c->frequency;
 	p->inversion = c->inversion;
 
@@ -1344,16 +1242,17 @@ static int dtv_property_legacy_params_sync(struct dvb_frontend *fe,
  * If p_out is not null, it will update the DVBv3 params pointed by it.
  */
 static int dtv_get_frontend(struct dvb_frontend *fe,
+			    struct dtv_frontend_properties *c,
 			    struct dvb_frontend_parameters *p_out)
 {
 	int r;
 
 	if (fe->ops.get_frontend) {
-		r = fe->ops.get_frontend(fe);
+		r = fe->ops.get_frontend(fe, c);
 		if (unlikely(r < 0))
 			return r;
 		if (p_out)
-			dtv_property_legacy_params_sync(fe, p_out);
+			dtv_property_legacy_params_sync(fe, c, p_out);
 		return 0;
 	}
 
@@ -1589,7 +1488,7 @@ static int dtv_property_process_get(struct dvb_frontend *fe,
 			return r;
 	}
 
-	dtv_property_dump(fe, tvp);
+	dtv_property_dump(fe, false, tvp);
 
 	return 0;
 }
@@ -1830,6 +1729,8 @@ static int dtv_property_process_set(struct dvb_frontend *fe,
 			return r;
 	}
 
+	dtv_property_dump(fe, true, tvp);
+
 	switch(tvp->cmd) {
 	case DTV_CLEAR:
 		/*
@@ -2073,6 +1974,8 @@ static int dvb_frontend_ioctl_properties(struct file *file,
 			dev_dbg(fe->dvb->device, "%s: Property cache is full, tuning\n", __func__);
 
 	} else if (cmd == FE_GET_PROPERTY) {
+		struct dtv_frontend_properties getp = fe->dtv_property_cache;
+
 		dev_dbg(fe->dvb->device, "%s: properties.num = %d\n", __func__, tvps->num);
 		dev_dbg(fe->dvb->device, "%s: properties.props = %p\n", __func__, tvps->props);
 
@@ -2094,17 +1997,18 @@ static int dvb_frontend_ioctl_properties(struct file *file,
 		}
 
 		/*
-		 * Fills the cache out struct with the cache contents, plus
-		 * the data retrieved from get_frontend, if the frontend
-		 * is not idle. Otherwise, returns the cached content
+		 * Let's use our own copy of property cache, in order to
+		 * avoid mangling with DTV zigzag logic, as drivers might
+		 * return crap, if they don't check if the data is available
+		 * before updating the properties cache.
 		 */
 		if (fepriv->state != FESTATE_IDLE) {
-			err = dtv_get_frontend(fe, NULL);
+			err = dtv_get_frontend(fe, &getp, NULL);
 			if (err < 0)
 				goto out;
 		}
 		for (i = 0; i < tvps->num; i++) {
-			err = dtv_property_process_get(fe, c, tvp + i, file);
+			err = dtv_property_process_get(fe, &getp, tvp + i, file);
 			if (err < 0)
 				goto out;
 			(tvp + i)->result = err;
@@ -2139,7 +2043,7 @@ static int dtv_set_frontend(struct dvb_frontend *fe)
 	 * the user. FE_SET_FRONTEND triggers an initial frontend event
 	 * with status = 0, which copies output parameters to userspace.
 	 */
-	dtv_property_legacy_params_sync(fe, &fepriv->parameters_out);
+	dtv_property_legacy_params_sync(fe, c, &fepriv->parameters_out);
 
 	/*
 	 * Be sure that the bandwidth will be filled for all
@@ -2451,7 +2355,7 @@ static int dvb_frontend_ioctl_legacy(struct file *file,
 			u8 last = 1;
 			if (dvb_frontend_debug)
 				printk("%s switch command: 0x%04lx\n", __func__, swcmd);
-			nexttime = ktime_get_real();
+			nexttime = ktime_get_boottime();
 			if (dvb_frontend_debug)
 				tv[0] = nexttime;
 			/* before sending a command, initialize by sending
@@ -2462,7 +2366,7 @@ static int dvb_frontend_ioctl_legacy(struct file *file,
 
 			for (i = 0; i < 9; i++) {
 				if (dvb_frontend_debug)
-					tv[i+1] = ktime_get_real();
+					tv[i+1] = ktime_get_boottime();
 				if ((swcmd & 0x01) != last) {
 					/* set voltage to (last ? 13V : 18V) */
 					fe->ops.set_voltage(fe, (last) ? SEC_VOLTAGE_13 : SEC_VOLTAGE_18);
@@ -2509,10 +2413,18 @@ static int dvb_frontend_ioctl_legacy(struct file *file,
 		err = dvb_frontend_get_event (fe, parg, file->f_flags);
 		break;
 
-	case FE_GET_FRONTEND:
-		err = dtv_get_frontend(fe, parg);
-		break;
+	case FE_GET_FRONTEND: {
+		struct dtv_frontend_properties getp = fe->dtv_property_cache;
 
+		/*
+		 * Let's use our own copy of property cache, in order to
+		 * avoid mangling with DTV zigzag logic, as drivers might
+		 * return crap, if they don't check if the data is available
+		 * before updating the properties cache.
+		 */
+		err = dtv_get_frontend(fe, &getp, parg);
+		break;
+	}
 	case FE_SET_FRONTEND_TUNE_MODE:
 		fepriv->tune_mode_flags = (unsigned long) parg;
 		err = 0;
@@ -2612,9 +2524,20 @@ static int dvb_frontend_open(struct inode *inode, struct file *file)
 		fepriv->tone = -1;
 		fepriv->voltage = -1;
 
+#ifdef CONFIG_MEDIA_CONTROLLER_DVB
+		if (fe->dvb->mdev && fe->dvb->mdev->enable_source) {
+			ret = fe->dvb->mdev->enable_source(dvbdev->entity,
+							   &fepriv->pipe);
+			if (ret) {
+				dev_err(fe->dvb->device,
+					"Tuner is busy. Error %d\n", ret);
+				goto err2;
+			}
+		}
+#endif
 		ret = dvb_frontend_start (fe);
 		if (ret)
-			goto err2;
+			goto err3;
 
 		/*  empty event queue */
 		fepriv->events.eventr = fepriv->events.eventw = 0;
@@ -2624,7 +2547,12 @@ static int dvb_frontend_open(struct inode *inode, struct file *file)
 		mutex_unlock (&adapter->mfe_lock);
 	return ret;
 
+err3:
+#ifdef CONFIG_MEDIA_CONTROLLER_DVB
+	if (fe->dvb->mdev && fe->dvb->mdev->disable_source)
+		fe->dvb->mdev->disable_source(dvbdev->entity);
 err2:
+#endif
 	dvb_generic_release(inode, file);
 err1:
 	if (dvbdev->users == -1 && fe->ops.ts_bus_ctrl)
@@ -2653,6 +2581,10 @@ static int dvb_frontend_release(struct inode *inode, struct file *file)
 
 	if (dvbdev->users == -1) {
 		wake_up(&fepriv->wait_queue);
+#ifdef CONFIG_MEDIA_CONTROLLER_DVB
+		if (fe->dvb->mdev && fe->dvb->mdev->disable_source)
+			fe->dvb->mdev->disable_source(dvbdev->entity);
+#endif
 		if (fe->exit != DVB_FE_NO_EXIT)
 			wake_up(&dvbdev->wait_queue);
 		if (fe->ops.ts_bus_ctrl)
diff --git a/drivers/media/dvb-core/dvb_frontend.h b/drivers/media/dvb-core/dvb_frontend.h
index 458bcce20e38..9592573a0b41 100644
--- a/drivers/media/dvb-core/dvb_frontend.h
+++ b/drivers/media/dvb-core/dvb_frontend.h
@@ -449,7 +449,8 @@ struct dvb_frontend_ops {
 	int (*set_frontend)(struct dvb_frontend *fe);
 	int (*get_tune_settings)(struct dvb_frontend* fe, struct dvb_frontend_tune_settings* settings);
 
-	int (*get_frontend)(struct dvb_frontend *fe);
+	int (*get_frontend)(struct dvb_frontend *fe,
+			    struct dtv_frontend_properties *props);
 
 	int (*read_status)(struct dvb_frontend *fe, enum fe_status *status);
 	int (*read_ber)(struct dvb_frontend* fe, u32* ber);
diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c
index 560450a0b32a..e1684c570e2f 100644
--- a/drivers/media/dvb-core/dvbdev.c
+++ b/drivers/media/dvb-core/dvbdev.c
@@ -58,7 +58,7 @@ static const char * const dnames[] = {
 #define DVB_MAX_IDS		MAX_DVB_MINORS
 #else
 #define DVB_MAX_IDS		4
-#define nums2minor(num,type,id)	((num << 6) | (id << 4) | type)
+#define nums2minor(num, type, id)	((num << 6) | (id << 4) | type)
 #define MAX_DVB_MINORS		(DVB_MAX_ADAPTERS*64)
 #endif
 
@@ -85,7 +85,7 @@ static int dvb_device_open(struct inode *inode, struct file *file)
 		file->private_data = dvbdev;
 		replace_fops(file, new_fops);
 		if (file->f_op->open)
-			err = file->f_op->open(inode,file);
+			err = file->f_op->open(inode, file);
 		up_read(&minor_rwsem);
 		mutex_unlock(&dvbdev_mutex);
 		return err;
@@ -352,7 +352,7 @@ static int dvb_create_media_entity(struct dvb_device *dvbdev,
 	ret = media_device_register_entity(dvbdev->adapter->mdev,
 					   dvbdev->entity);
 	if (ret)
-		return (ret);
+		return ret;
 
 	printk(KERN_DEBUG "%s: media entity '%s' registered.\n",
 		__func__, dvbdev->entity->name);
@@ -620,8 +620,7 @@ int dvb_create_media_graph(struct dvb_adapter *adap,
 			return -ENOMEM;
 		adap->conn = conn;
 
-		adap->conn_pads = kcalloc(1, sizeof(*adap->conn_pads),
-					    GFP_KERNEL);
+		adap->conn_pads = kzalloc(sizeof(*adap->conn_pads), GFP_KERNEL);
 		if (!adap->conn_pads)
 			return -ENOMEM;
 
@@ -661,7 +660,7 @@ int dvb_create_media_graph(struct dvb_adapter *adap,
 	if (ntuner && ndemod) {
 		ret = media_create_pad_links(mdev,
 					     MEDIA_ENT_F_TUNER,
-					     tuner, TUNER_PAD_IF_OUTPUT,
+					     tuner, TUNER_PAD_OUTPUT,
 					     MEDIA_ENT_F_DTV_DEMOD,
 					     demod, 0, MEDIA_LNK_FL_ENABLED,
 					     false);
@@ -682,7 +681,7 @@ int dvb_create_media_graph(struct dvb_adapter *adap,
 	if (demux && ca) {
 		ret = media_create_pad_link(demux, 1, ca,
 					    0, MEDIA_LNK_FL_ENABLED);
-		if (!ret)
+		if (ret)
 			return -ENOMEM;
 	}
 
@@ -868,7 +867,7 @@ int dvb_usercopy(struct file *file,
 			parg = sbuf;
 		} else {
 			/* too big to allocate from stack */
-			mbuf = kmalloc(_IOC_SIZE(cmd),GFP_KERNEL);
+			mbuf = kmalloc(_IOC_SIZE(cmd), GFP_KERNEL);
 			if (NULL == mbuf)
 				return -ENOMEM;
 			parg = mbuf;
diff --git a/drivers/media/dvb-frontends/Kconfig b/drivers/media/dvb-frontends/Kconfig
index 310e4b8beae8..a82f77c49bd5 100644
--- a/drivers/media/dvb-frontends/Kconfig
+++ b/drivers/media/dvb-frontends/Kconfig
@@ -73,6 +73,14 @@ config DVB_SI2165
 
 	  Say Y when you want to support this frontend.
 
+config DVB_MN88473
+	tristate "Panasonic MN88473"
+	depends on DVB_CORE && I2C
+	select REGMAP_I2C
+	default m if !MEDIA_SUBDRV_AUTOSELECT
+	help
+	  Say Y when you want to support this frontend.
+
 comment "DVB-S (satellite) frontends"
 	depends on DVB_CORE
 
diff --git a/drivers/media/dvb-frontends/Makefile b/drivers/media/dvb-frontends/Makefile
index 37ef17b5b995..eb7191f4219d 100644
--- a/drivers/media/dvb-frontends/Makefile
+++ b/drivers/media/dvb-frontends/Makefile
@@ -95,6 +95,7 @@ obj-$(CONFIG_DVB_STV0900) += stv0900.o
 obj-$(CONFIG_DVB_STV090x) += stv090x.o
 obj-$(CONFIG_DVB_STV6110x) += stv6110x.o
 obj-$(CONFIG_DVB_M88DS3103) += m88ds3103.o
+obj-$(CONFIG_DVB_MN88473) += mn88473.o
 obj-$(CONFIG_DVB_ISL6423) += isl6423.o
 obj-$(CONFIG_DVB_EC100) += ec100.o
 obj-$(CONFIG_DVB_HD29L2) += hd29l2.o
diff --git a/drivers/media/dvb-frontends/af9013.c b/drivers/media/dvb-frontends/af9013.c
index e23197da84af..8bcde336ffd7 100644
--- a/drivers/media/dvb-frontends/af9013.c
+++ b/drivers/media/dvb-frontends/af9013.c
@@ -866,9 +866,9 @@ err:
 	return ret;
 }
 
-static int af9013_get_frontend(struct dvb_frontend *fe)
+static int af9013_get_frontend(struct dvb_frontend *fe,
+			       struct dtv_frontend_properties *c)
 {
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	struct af9013_state *state = fe->demodulator_priv;
 	int ret;
 	u8 buf[3];
@@ -1344,6 +1344,10 @@ err:
 static void af9013_release(struct dvb_frontend *fe)
 {
 	struct af9013_state *state = fe->demodulator_priv;
+
+	/* stop statistics polling */
+	cancel_delayed_work_sync(&state->statistics_work);
+
 	kfree(state);
 }
 
diff --git a/drivers/media/dvb-frontends/af9033.c b/drivers/media/dvb-frontends/af9033.c
index bc35206a0821..efebe5ce2429 100644
--- a/drivers/media/dvb-frontends/af9033.c
+++ b/drivers/media/dvb-frontends/af9033.c
@@ -691,10 +691,10 @@ err:
 	return ret;
 }
 
-static int af9033_get_frontend(struct dvb_frontend *fe)
+static int af9033_get_frontend(struct dvb_frontend *fe,
+			       struct dtv_frontend_properties *c)
 {
 	struct af9033_dev *dev = fe->demodulator_priv;
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret;
 	u8 buf[8];
 
@@ -1372,6 +1372,9 @@ static int af9033_remove(struct i2c_client *client)
 
 	dev_dbg(&dev->client->dev, "\n");
 
+	/* stop statistics polling */
+	cancel_delayed_work_sync(&dev->stat_work);
+
 	dev->fe.ops.release = NULL;
 	dev->fe.demodulator_priv = NULL;
 	kfree(dev);
diff --git a/drivers/media/dvb-frontends/as102_fe.c b/drivers/media/dvb-frontends/as102_fe.c
index 544c5f65d19a..9412fcd1bddb 100644
--- a/drivers/media/dvb-frontends/as102_fe.c
+++ b/drivers/media/dvb-frontends/as102_fe.c
@@ -190,10 +190,10 @@ static int as102_fe_set_frontend(struct dvb_frontend *fe)
 	return state->ops->set_tune(state->priv, &tune_args);
 }
 
-static int as102_fe_get_frontend(struct dvb_frontend *fe)
+static int as102_fe_get_frontend(struct dvb_frontend *fe,
+				 struct dtv_frontend_properties *c)
 {
 	struct as102_state *state = fe->demodulator_priv;
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret = 0;
 	struct as10x_tps tps = { 0 };
 
diff --git a/drivers/media/dvb-frontends/atbm8830.c b/drivers/media/dvb-frontends/atbm8830.c
index 8fe552e293ed..47248b868e38 100644
--- a/drivers/media/dvb-frontends/atbm8830.c
+++ b/drivers/media/dvb-frontends/atbm8830.c
@@ -297,9 +297,9 @@ static int atbm8830_set_fe(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int atbm8830_get_fe(struct dvb_frontend *fe)
+static int atbm8830_get_fe(struct dvb_frontend *fe,
+			   struct dtv_frontend_properties *c)
 {
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	dprintk("%s\n", __func__);
 
 	/* TODO: get real readings from device */
diff --git a/drivers/media/dvb-frontends/au8522.h b/drivers/media/dvb-frontends/au8522.h
index dde61582c158..78bf3f73e58d 100644
--- a/drivers/media/dvb-frontends/au8522.h
+++ b/drivers/media/dvb-frontends/au8522.h
@@ -89,5 +89,4 @@ enum au8522_audio_input {
 	AU8522_AUDIO_NONE,
 	AU8522_AUDIO_SIF,
 };
-
 #endif /* __AU8522_H__ */
diff --git a/drivers/media/dvb-frontends/au8522_decoder.c b/drivers/media/dvb-frontends/au8522_decoder.c
index 73612c5353d1..add246382806 100644
--- a/drivers/media/dvb-frontends/au8522_decoder.c
+++ b/drivers/media/dvb-frontends/au8522_decoder.c
@@ -763,9 +763,10 @@ static int au8522_probe(struct i2c_client *client,
 	v4l2_i2c_subdev_init(sd, client, &au8522_ops);
 #if defined(CONFIG_MEDIA_CONTROLLER)
 
-	state->pads[AU8522_PAD_INPUT].flags = MEDIA_PAD_FL_SINK;
-	state->pads[AU8522_PAD_VID_OUT].flags = MEDIA_PAD_FL_SOURCE;
-	state->pads[AU8522_PAD_VBI_OUT].flags = MEDIA_PAD_FL_SOURCE;
+	state->pads[DEMOD_PAD_IF_INPUT].flags = MEDIA_PAD_FL_SINK;
+	state->pads[DEMOD_PAD_VID_OUT].flags = MEDIA_PAD_FL_SOURCE;
+	state->pads[DEMOD_PAD_VBI_OUT].flags = MEDIA_PAD_FL_SOURCE;
+	state->pads[DEMOD_PAD_AUDIO_OUT].flags = MEDIA_PAD_FL_SOURCE;
 	sd->entity.function = MEDIA_ENT_F_ATV_DECODER;
 
 	ret = media_entity_pads_init(&sd->entity, ARRAY_SIZE(state->pads),
diff --git a/drivers/media/dvb-frontends/au8522_dig.c b/drivers/media/dvb-frontends/au8522_dig.c
index 6c1e97640f3f..e676b9461a59 100644
--- a/drivers/media/dvb-frontends/au8522_dig.c
+++ b/drivers/media/dvb-frontends/au8522_dig.c
@@ -816,9 +816,9 @@ static int au8522_read_ber(struct dvb_frontend *fe, u32 *ber)
 	return au8522_read_ucblocks(fe, ber);
 }
 
-static int au8522_get_frontend(struct dvb_frontend *fe)
+static int au8522_get_frontend(struct dvb_frontend *fe,
+			       struct dtv_frontend_properties *c)
 {
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	struct au8522_state *state = fe->demodulator_priv;
 
 	c->frequency = state->current_frequency;
diff --git a/drivers/media/dvb-frontends/au8522_priv.h b/drivers/media/dvb-frontends/au8522_priv.h
index 404a0cb0ed8d..f5a9438f6ce5 100644
--- a/drivers/media/dvb-frontends/au8522_priv.h
+++ b/drivers/media/dvb-frontends/au8522_priv.h
@@ -30,6 +30,7 @@
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ctrls.h>
+#include <media/v4l2-mc.h>
 #include <linux/i2c.h>
 #include "dvb_frontend.h"
 #include "au8522.h"
@@ -39,14 +40,6 @@
 #define AU8522_DIGITAL_MODE 1
 #define AU8522_SUSPEND_MODE 2
 
-enum au8522_media_pads {
-	AU8522_PAD_INPUT,
-	AU8522_PAD_VID_OUT,
-	AU8522_PAD_VBI_OUT,
-
-	AU8522_NUM_PADS
-};
-
 struct au8522_state {
 	struct i2c_client *c;
 	struct i2c_adapter *i2c;
@@ -78,7 +71,7 @@ struct au8522_state {
 	struct v4l2_ctrl_handler hdl;
 
 #ifdef CONFIG_MEDIA_CONTROLLER
-	struct media_pad pads[AU8522_NUM_PADS];
+	struct media_pad pads[DEMOD_NUM_PADS];
 #endif
 };
 
diff --git a/drivers/media/dvb-frontends/bcm3510.c b/drivers/media/dvb-frontends/bcm3510.c
index d30275f27644..bb698839e477 100644
--- a/drivers/media/dvb-frontends/bcm3510.c
+++ b/drivers/media/dvb-frontends/bcm3510.c
@@ -3,7 +3,7 @@
  *
  *  Copyright (C) 2001-5, B2C2 inc.
  *
- *  GPL/Linux driver written by Patrick Boettcher <patrick.boettcher@desy.de>
+ *  GPL/Linux driver written by Patrick Boettcher <patrick.boettcher@posteo.de>
  *
  *  This driver is "hard-coded" to be used with the 1st generation of
  *  Technisat/B2C2's Air2PC ATSC PCI/USB cards/boxes. The pll-programming
@@ -865,5 +865,5 @@ static struct dvb_frontend_ops bcm3510_ops = {
 };
 
 MODULE_DESCRIPTION("Broadcom BCM3510 ATSC (8VSB/16VSB & ITU J83 AnnexB FEC QAM64/256) demodulator driver");
-MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@desy.de>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/dvb-frontends/bcm3510.h b/drivers/media/dvb-frontends/bcm3510.h
index ff66492fb940..961c2eb87c68 100644
--- a/drivers/media/dvb-frontends/bcm3510.h
+++ b/drivers/media/dvb-frontends/bcm3510.h
@@ -3,7 +3,7 @@
  *
  *  Copyright (C) 2001-5, B2C2 inc.
  *
- *  GPL/Linux driver written by Patrick Boettcher <patrick.boettcher@desy.de>
+ *  GPL/Linux driver written by Patrick Boettcher <patrick.boettcher@posteo.de>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
diff --git a/drivers/media/dvb-frontends/bcm3510_priv.h b/drivers/media/dvb-frontends/bcm3510_priv.h
index 3bb1bc2a04f0..67f24686c31b 100644
--- a/drivers/media/dvb-frontends/bcm3510_priv.h
+++ b/drivers/media/dvb-frontends/bcm3510_priv.h
@@ -3,7 +3,7 @@
  *
  *  Copyright (C) 2001-5, B2C2 inc.
  *
- *  GPL/Linux driver written by Patrick Boettcher <patrick.boettcher@desy.de>
+ *  GPL/Linux driver written by Patrick Boettcher <patrick.boettcher@posteo.de>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
diff --git a/drivers/media/dvb-frontends/cx22700.c b/drivers/media/dvb-frontends/cx22700.c
index fd033cca6e11..5cad925609e0 100644
--- a/drivers/media/dvb-frontends/cx22700.c
+++ b/drivers/media/dvb-frontends/cx22700.c
@@ -345,9 +345,9 @@ static int cx22700_set_frontend(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int cx22700_get_frontend(struct dvb_frontend *fe)
+static int cx22700_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *c)
 {
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	struct cx22700_state* state = fe->demodulator_priv;
 	u8 reg09 = cx22700_readreg (state, 0x09);
 
diff --git a/drivers/media/dvb-frontends/cx22702.c b/drivers/media/dvb-frontends/cx22702.c
index d2d06dcd7683..c0e54c59cccf 100644
--- a/drivers/media/dvb-frontends/cx22702.c
+++ b/drivers/media/dvb-frontends/cx22702.c
@@ -562,9 +562,9 @@ static int cx22702_read_ucblocks(struct dvb_frontend *fe, u32 *ucblocks)
 	return 0;
 }
 
-static int cx22702_get_frontend(struct dvb_frontend *fe)
+static int cx22702_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *c)
 {
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	struct cx22702_state *state = fe->demodulator_priv;
 
 	u8 reg0C = cx22702_readreg(state, 0x0C);
diff --git a/drivers/media/dvb-frontends/cx24110.c b/drivers/media/dvb-frontends/cx24110.c
index cb36475e322b..6cb81ec12847 100644
--- a/drivers/media/dvb-frontends/cx24110.c
+++ b/drivers/media/dvb-frontends/cx24110.c
@@ -550,9 +550,9 @@ static int cx24110_set_frontend(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int cx24110_get_frontend(struct dvb_frontend *fe)
+static int cx24110_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct cx24110_state *state = fe->demodulator_priv;
 	s32 afc; unsigned sclk;
 
diff --git a/drivers/media/dvb-frontends/cx24117.c b/drivers/media/dvb-frontends/cx24117.c
index 5f77bc80a896..a3f7eb4e609d 100644
--- a/drivers/media/dvb-frontends/cx24117.c
+++ b/drivers/media/dvb-frontends/cx24117.c
@@ -1560,10 +1560,10 @@ static int cx24117_get_algo(struct dvb_frontend *fe)
 	return DVBFE_ALGO_HW;
 }
 
-static int cx24117_get_frontend(struct dvb_frontend *fe)
+static int cx24117_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *c)
 {
 	struct cx24117_state *state = fe->demodulator_priv;
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	struct cx24117_cmd cmd;
 	u8 reg, st, inv;
 	int ret, idx;
diff --git a/drivers/media/dvb-frontends/cx24120.c b/drivers/media/dvb-frontends/cx24120.c
index 3b0ef52bb834..066ee387bf25 100644
--- a/drivers/media/dvb-frontends/cx24120.c
+++ b/drivers/media/dvb-frontends/cx24120.c
@@ -1502,16 +1502,18 @@ static int cx24120_sleep(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int cx24120_get_frontend(struct dvb_frontend *fe)
+static int cx24120_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *c)
 {
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	struct cx24120_state *state = fe->demodulator_priv;
 	u8 freq1, freq2, freq3;
+	int status;
 
 	dev_dbg(&state->i2c->dev, "\n");
 
 	/* don't return empty data if we're not tuned in */
-	if ((state->fe_status & FE_HAS_LOCK) == 0)
+	status = cx24120_readreg(state, CX24120_REG_STATUS);
+	if (!(status & CX24120_HAS_LOCK))
 		return 0;
 
 	/* Get frequency */
diff --git a/drivers/media/dvb-frontends/cx24123.c b/drivers/media/dvb-frontends/cx24123.c
index 0fe7fb11124b..113b0949408a 100644
--- a/drivers/media/dvb-frontends/cx24123.c
+++ b/drivers/media/dvb-frontends/cx24123.c
@@ -945,9 +945,9 @@ static int cx24123_set_frontend(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int cx24123_get_frontend(struct dvb_frontend *fe)
+static int cx24123_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct cx24123_state *state = fe->demodulator_priv;
 
 	dprintk("\n");
diff --git a/drivers/media/dvb-frontends/cxd2820r_c.c b/drivers/media/dvb-frontends/cxd2820r_c.c
index 42fad6aa3958..a674a6312c38 100644
--- a/drivers/media/dvb-frontends/cxd2820r_c.c
+++ b/drivers/media/dvb-frontends/cxd2820r_c.c
@@ -101,10 +101,10 @@ error:
 	return ret;
 }
 
-int cxd2820r_get_frontend_c(struct dvb_frontend *fe)
+int cxd2820r_get_frontend_c(struct dvb_frontend *fe,
+			    struct dtv_frontend_properties *c)
 {
 	struct cxd2820r_priv *priv = fe->demodulator_priv;
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret;
 	u8 buf[2];
 
diff --git a/drivers/media/dvb-frontends/cxd2820r_core.c b/drivers/media/dvb-frontends/cxd2820r_core.c
index 24a457d9d803..314d3b8c1080 100644
--- a/drivers/media/dvb-frontends/cxd2820r_core.c
+++ b/drivers/media/dvb-frontends/cxd2820r_core.c
@@ -313,7 +313,8 @@ static int cxd2820r_read_status(struct dvb_frontend *fe, enum fe_status *status)
 	return ret;
 }
 
-static int cxd2820r_get_frontend(struct dvb_frontend *fe)
+static int cxd2820r_get_frontend(struct dvb_frontend *fe,
+				 struct dtv_frontend_properties *p)
 {
 	struct cxd2820r_priv *priv = fe->demodulator_priv;
 	int ret;
@@ -326,13 +327,13 @@ static int cxd2820r_get_frontend(struct dvb_frontend *fe)
 
 	switch (fe->dtv_property_cache.delivery_system) {
 	case SYS_DVBT:
-		ret = cxd2820r_get_frontend_t(fe);
+		ret = cxd2820r_get_frontend_t(fe, p);
 		break;
 	case SYS_DVBT2:
-		ret = cxd2820r_get_frontend_t2(fe);
+		ret = cxd2820r_get_frontend_t2(fe, p);
 		break;
 	case SYS_DVBC_ANNEX_A:
-		ret = cxd2820r_get_frontend_c(fe);
+		ret = cxd2820r_get_frontend_c(fe, p);
 		break;
 	default:
 		ret = -EINVAL;
@@ -606,8 +607,7 @@ static int cxd2820r_i2c_gate_ctrl(struct dvb_frontend *fe, int enable)
 static int cxd2820r_gpio_direction_output(struct gpio_chip *chip, unsigned nr,
 		int val)
 {
-	struct cxd2820r_priv *priv =
-			container_of(chip, struct cxd2820r_priv, gpio_chip);
+	struct cxd2820r_priv *priv = gpiochip_get_data(chip);
 	u8 gpio[GPIO_COUNT];
 
 	dev_dbg(&priv->i2c->dev, "%s: nr=%d val=%d\n", __func__, nr, val);
@@ -620,8 +620,7 @@ static int cxd2820r_gpio_direction_output(struct gpio_chip *chip, unsigned nr,
 
 static void cxd2820r_gpio_set(struct gpio_chip *chip, unsigned nr, int val)
 {
-	struct cxd2820r_priv *priv =
-			container_of(chip, struct cxd2820r_priv, gpio_chip);
+	struct cxd2820r_priv *priv = gpiochip_get_data(chip);
 	u8 gpio[GPIO_COUNT];
 
 	dev_dbg(&priv->i2c->dev, "%s: nr=%d val=%d\n", __func__, nr, val);
@@ -636,8 +635,7 @@ static void cxd2820r_gpio_set(struct gpio_chip *chip, unsigned nr, int val)
 
 static int cxd2820r_gpio_get(struct gpio_chip *chip, unsigned nr)
 {
-	struct cxd2820r_priv *priv =
-			container_of(chip, struct cxd2820r_priv, gpio_chip);
+	struct cxd2820r_priv *priv = gpiochip_get_data(chip);
 
 	dev_dbg(&priv->i2c->dev, "%s: nr=%d\n", __func__, nr);
 
@@ -731,7 +729,7 @@ struct dvb_frontend *cxd2820r_attach(const struct cxd2820r_config *cfg,
 		priv->gpio_chip.base = -1; /* dynamic allocation */
 		priv->gpio_chip.ngpio = GPIO_COUNT;
 		priv->gpio_chip.can_sleep = 1;
-		ret = gpiochip_add(&priv->gpio_chip);
+		ret = gpiochip_add_data(&priv->gpio_chip, priv);
 		if (ret)
 			goto error;
 
diff --git a/drivers/media/dvb-frontends/cxd2820r_priv.h b/drivers/media/dvb-frontends/cxd2820r_priv.h
index a0d53f01a8bf..e31c48e53097 100644
--- a/drivers/media/dvb-frontends/cxd2820r_priv.h
+++ b/drivers/media/dvb-frontends/cxd2820r_priv.h
@@ -76,7 +76,8 @@ int cxd2820r_rd_reg(struct cxd2820r_priv *priv, u32 reg, u8 *val);
 
 /* cxd2820r_c.c */
 
-int cxd2820r_get_frontend_c(struct dvb_frontend *fe);
+int cxd2820r_get_frontend_c(struct dvb_frontend *fe,
+			    struct dtv_frontend_properties *p);
 
 int cxd2820r_set_frontend_c(struct dvb_frontend *fe);
 
@@ -99,7 +100,8 @@ int cxd2820r_get_tune_settings_c(struct dvb_frontend *fe,
 
 /* cxd2820r_t.c */
 
-int cxd2820r_get_frontend_t(struct dvb_frontend *fe);
+int cxd2820r_get_frontend_t(struct dvb_frontend *fe,
+			    struct dtv_frontend_properties *p);
 
 int cxd2820r_set_frontend_t(struct dvb_frontend *fe);
 
@@ -122,7 +124,8 @@ int cxd2820r_get_tune_settings_t(struct dvb_frontend *fe,
 
 /* cxd2820r_t2.c */
 
-int cxd2820r_get_frontend_t2(struct dvb_frontend *fe);
+int cxd2820r_get_frontend_t2(struct dvb_frontend *fe,
+			     struct dtv_frontend_properties *p);
 
 int cxd2820r_set_frontend_t2(struct dvb_frontend *fe);
 
diff --git a/drivers/media/dvb-frontends/cxd2820r_t.c b/drivers/media/dvb-frontends/cxd2820r_t.c
index 21abf1b4ed4d..75ce7d8ded00 100644
--- a/drivers/media/dvb-frontends/cxd2820r_t.c
+++ b/drivers/media/dvb-frontends/cxd2820r_t.c
@@ -138,10 +138,10 @@ error:
 	return ret;
 }
 
-int cxd2820r_get_frontend_t(struct dvb_frontend *fe)
+int cxd2820r_get_frontend_t(struct dvb_frontend *fe,
+			    struct dtv_frontend_properties *c)
 {
 	struct cxd2820r_priv *priv = fe->demodulator_priv;
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret;
 	u8 buf[2];
 
diff --git a/drivers/media/dvb-frontends/cxd2820r_t2.c b/drivers/media/dvb-frontends/cxd2820r_t2.c
index 4e028b41c0d5..704475676234 100644
--- a/drivers/media/dvb-frontends/cxd2820r_t2.c
+++ b/drivers/media/dvb-frontends/cxd2820r_t2.c
@@ -23,8 +23,8 @@
 
 int cxd2820r_set_frontend_t2(struct dvb_frontend *fe)
 {
-	struct cxd2820r_priv *priv = fe->demodulator_priv;
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+	struct cxd2820r_priv *priv = fe->demodulator_priv;
 	int ret, i, bw_i;
 	u32 if_freq, if_ctl;
 	u64 num;
@@ -169,10 +169,10 @@ error:
 
 }
 
-int cxd2820r_get_frontend_t2(struct dvb_frontend *fe)
+int cxd2820r_get_frontend_t2(struct dvb_frontend *fe,
+			     struct dtv_frontend_properties *c)
 {
 	struct cxd2820r_priv *priv = fe->demodulator_priv;
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret;
 	u8 buf[2];
 
diff --git a/drivers/media/dvb-frontends/cxd2841er.c b/drivers/media/dvb-frontends/cxd2841er.c
index fdffb2f0ded8..900186ba8e62 100644
--- a/drivers/media/dvb-frontends/cxd2841er.c
+++ b/drivers/media/dvb-frontends/cxd2841er.c
@@ -2090,13 +2090,13 @@ static int cxd2841er_sleep_tc_to_active_c(struct cxd2841er_priv *priv,
 	return 0;
 }
 
-static int cxd2841er_get_frontend(struct dvb_frontend *fe)
+static int cxd2841er_get_frontend(struct dvb_frontend *fe,
+				  struct dtv_frontend_properties *p)
 {
 	enum fe_status status = 0;
 	u16 strength = 0, snr = 0;
 	u32 errors = 0, ber = 0;
 	struct cxd2841er_priv *priv = fe->demodulator_priv;
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 
 	dev_dbg(&priv->i2c->dev, "%s()\n", __func__);
 	if (priv->state == STATE_ACTIVE_S)
diff --git a/drivers/media/dvb-frontends/dib0070.c b/drivers/media/dvb-frontends/dib0070.c
index 0b8fb5dd1889..ee7d66997ccd 100644
--- a/drivers/media/dvb-frontends/dib0070.c
+++ b/drivers/media/dvb-frontends/dib0070.c
@@ -774,6 +774,6 @@ free_mem:
 }
 EXPORT_SYMBOL(dib0070_attach);
 
-MODULE_AUTHOR("Patrick Boettcher <pboettcher@dibcom.fr>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("Driver for the DiBcom 0070 base-band RF Tuner");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/dvb-frontends/dib0090.c b/drivers/media/dvb-frontends/dib0090.c
index 47cb72243b9d..dc2d41e144fd 100644
--- a/drivers/media/dvb-frontends/dib0090.c
+++ b/drivers/media/dvb-frontends/dib0090.c
@@ -1115,9 +1115,15 @@ void dib0090_pwm_gain_reset(struct dvb_frontend *fe)
 		dib0090_set_bbramp_pwm(state, bb_ramp);
 
 		/* activate the ramp generator using PWM control */
-		dprintk("ramp RF gain = %d BAND = %s version = %d", state->rf_ramp[0], (state->current_band == BAND_CBAND) ? "CBAND" : "NOT CBAND", state->identity.version & 0x1f);
-
-		if ((state->rf_ramp[0] == 0) || (state->current_band == BAND_CBAND && (state->identity.version & 0x1f) <= P1D_E_F)) {
+		if (state->rf_ramp)
+			dprintk("ramp RF gain = %d BAND = %s version = %d",
+				state->rf_ramp[0],
+				(state->current_band == BAND_CBAND) ? "CBAND" : "NOT CBAND",
+				state->identity.version & 0x1f);
+
+		if (rf_ramp && ((state->rf_ramp[0] == 0) ||
+		    (state->current_band == BAND_CBAND &&
+		    (state->identity.version & 0x1f) <= P1D_E_F))) {
 			dprintk("DE-Engage mux for direct gain reg control");
 			en_pwm_rf_mux = 0;
 		} else
@@ -2669,7 +2675,7 @@ free_mem:
 }
 EXPORT_SYMBOL(dib0090_fw_register);
 
-MODULE_AUTHOR("Patrick Boettcher <pboettcher@dibcom.fr>");
-MODULE_AUTHOR("Olivier Grenie <olivier.grenie@dibcom.fr>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
+MODULE_AUTHOR("Olivier Grenie <olivier.grenie@parrot.com>");
 MODULE_DESCRIPTION("Driver for the DiBcom 0090 base-band RF Tuner");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/dvb-frontends/dib3000.h b/drivers/media/dvb-frontends/dib3000.h
index 6ae9899b5b45..d5dfafb4ef13 100644
--- a/drivers/media/dvb-frontends/dib3000.h
+++ b/drivers/media/dvb-frontends/dib3000.h
@@ -2,11 +2,11 @@
  * public header file of the frontend drivers for mobile DVB-T demodulators
  * DiBcom 3000M-B and DiBcom 3000P/M-C (http://www.dibcom.fr/)
  *
- * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  * based on GPL code from DibCom, which has
  *
- * Copyright (C) 2004 Amaury Demol for DiBcom (ademol@dibcom.fr)
+ * Copyright (C) 2004 Amaury Demol for DiBcom
  *
  *	This program is free software; you can redistribute it and/or
  *	modify it under the terms of the GNU General Public License as
@@ -14,7 +14,7 @@
  *
  * Acknowledgements
  *
- *  Amaury Demol (ademol@dibcom.fr) from DiBcom for providing specs and driver
+ *  Amaury Demol from DiBcom for providing specs and driver
  *  sources, on which this driver (and the dvb-dibusb) are based.
  *
  * see Documentation/dvb/README.dvb-usb for more information
diff --git a/drivers/media/dvb-frontends/dib3000mb.c b/drivers/media/dvb-frontends/dib3000mb.c
index 7a61172d0d45..6821ecb53d63 100644
--- a/drivers/media/dvb-frontends/dib3000mb.c
+++ b/drivers/media/dvb-frontends/dib3000mb.c
@@ -2,11 +2,11 @@
  * Frontend driver for mobile DVB-T demodulator DiBcom 3000M-B
  * DiBcom (http://www.dibcom.fr/)
  *
- * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  * based on GPL code from DibCom, which has
  *
- * Copyright (C) 2004 Amaury Demol for DiBcom (ademol@dibcom.fr)
+ * Copyright (C) 2004 Amaury Demol for DiBcom
  *
  *	This program is free software; you can redistribute it and/or
  *	modify it under the terms of the GNU General Public License as
@@ -14,7 +14,7 @@
  *
  * Acknowledgements
  *
- *  Amaury Demol (ademol@dibcom.fr) from DiBcom for providing specs and driver
+ *  Amaury Demol from DiBcom for providing specs and driver
  *  sources, on which this driver (and the dvb-dibusb) are based.
  *
  * see Documentation/dvb/README.dvb-usb for more information
@@ -36,7 +36,7 @@
 /* Version information */
 #define DRIVER_VERSION "0.1"
 #define DRIVER_DESC "DiBcom 3000M-B DVB-T demodulator"
-#define DRIVER_AUTHOR "Patrick Boettcher, patrick.boettcher@desy.de"
+#define DRIVER_AUTHOR "Patrick Boettcher, patrick.boettcher@posteo.de"
 
 static int debug;
 module_param(debug, int, 0644);
@@ -112,7 +112,8 @@ static u16 dib3000_seq[2][2][2] =     /* fft,gua,   inv   */
 		}
 	};
 
-static int dib3000mb_get_frontend(struct dvb_frontend* fe);
+static int dib3000mb_get_frontend(struct dvb_frontend* fe,
+				  struct dtv_frontend_properties *c);
 
 static int dib3000mb_set_frontend(struct dvb_frontend *fe, int tuner)
 {
@@ -359,7 +360,7 @@ static int dib3000mb_set_frontend(struct dvb_frontend *fe, int tuner)
 		deb_setf("search_state after autosearch %d after %d checks\n",search_state,as_count);
 
 		if (search_state == 1) {
-			if (dib3000mb_get_frontend(fe) == 0) {
+			if (dib3000mb_get_frontend(fe, c) == 0) {
 				deb_setf("reading tuning data from frontend succeeded.\n");
 				return dib3000mb_set_frontend(fe, 0);
 			}
@@ -450,9 +451,9 @@ static int dib3000mb_fe_init(struct dvb_frontend* fe, int mobile_mode)
 	return 0;
 }
 
-static int dib3000mb_get_frontend(struct dvb_frontend* fe)
+static int dib3000mb_get_frontend(struct dvb_frontend* fe,
+				  struct dtv_frontend_properties *c)
 {
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	struct dib3000_state* state = fe->demodulator_priv;
 	enum fe_code_rate *cr;
 	u16 tps_val;
diff --git a/drivers/media/dvb-frontends/dib3000mb_priv.h b/drivers/media/dvb-frontends/dib3000mb_priv.h
index 9dc235aa44b7..0459d5c84314 100644
--- a/drivers/media/dvb-frontends/dib3000mb_priv.h
+++ b/drivers/media/dvb-frontends/dib3000mb_priv.h
@@ -1,7 +1,7 @@
 /*
  * dib3000mb_priv.h
  *
- * Copyright (C) 2004 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  *	This program is free software; you can redistribute it and/or
  *	modify it under the terms of the GNU General Public License as
diff --git a/drivers/media/dvb-frontends/dib3000mc.c b/drivers/media/dvb-frontends/dib3000mc.c
index 583d6b7fabed..da0f1dc5aaf7 100644
--- a/drivers/media/dvb-frontends/dib3000mc.c
+++ b/drivers/media/dvb-frontends/dib3000mc.c
@@ -2,7 +2,7 @@
  * Driver for DiBcom DiB3000MC/P-demodulator.
  *
  * Copyright (C) 2004-7 DiBcom (http://www.dibcom.fr/)
- * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  * This code is partially based on the previous dib3000mc.c .
  *
@@ -636,9 +636,9 @@ struct i2c_adapter * dib3000mc_get_tuner_i2c_master(struct dvb_frontend *demod,
 
 EXPORT_SYMBOL(dib3000mc_get_tuner_i2c_master);
 
-static int dib3000mc_get_frontend(struct dvb_frontend* fe)
+static int dib3000mc_get_frontend(struct dvb_frontend* fe,
+				  struct dtv_frontend_properties *fep)
 {
-	struct dtv_frontend_properties *fep = &fe->dtv_property_cache;
 	struct dib3000mc_state *state = fe->demodulator_priv;
 	u16 tps = dib3000mc_read_word(state,458);
 
@@ -726,7 +726,7 @@ static int dib3000mc_set_frontend(struct dvb_frontend *fe)
 		if (found == 0 || found == 1)
 			return 0; // no channel found
 
-		dib3000mc_get_frontend(fe);
+		dib3000mc_get_frontend(fe, fep);
 	}
 
 	ret = dib3000mc_tune(fe);
@@ -939,6 +939,6 @@ static struct dvb_frontend_ops dib3000mc_ops = {
 	.read_ucblocks        = dib3000mc_read_unc_blocks,
 };
 
-MODULE_AUTHOR("Patrick Boettcher <pboettcher@dibcom.fr>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("Driver for the DiBcom 3000MC/P COFDM demodulator");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/dvb-frontends/dib3000mc.h b/drivers/media/dvb-frontends/dib3000mc.h
index 74816f793611..b37e69e6a58c 100644
--- a/drivers/media/dvb-frontends/dib3000mc.h
+++ b/drivers/media/dvb-frontends/dib3000mc.h
@@ -2,7 +2,7 @@
  * Driver for DiBcom DiB3000MC/P-demodulator.
  *
  * Copyright (C) 2004-6 DiBcom (http://www.dibcom.fr/)
- * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher\@desy.de)
+ * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  * This code is partially based on the previous dib3000mc.c .
  *
diff --git a/drivers/media/dvb-frontends/dib7000m.c b/drivers/media/dvb-frontends/dib7000m.c
index 35eb71fe3c2b..b3ddae8885ac 100644
--- a/drivers/media/dvb-frontends/dib7000m.c
+++ b/drivers/media/dvb-frontends/dib7000m.c
@@ -1151,9 +1151,9 @@ static int dib7000m_identify(struct dib7000m_state *state)
 }
 
 
-static int dib7000m_get_frontend(struct dvb_frontend* fe)
+static int dib7000m_get_frontend(struct dvb_frontend* fe,
+				 struct dtv_frontend_properties *fep)
 {
-	struct dtv_frontend_properties *fep = &fe->dtv_property_cache;
 	struct dib7000m_state *state = fe->demodulator_priv;
 	u16 tps = dib7000m_read_word(state,480);
 
@@ -1246,7 +1246,7 @@ static int dib7000m_set_frontend(struct dvb_frontend *fe)
 		if (found == 0 || found == 1)
 			return 0; // no channel found
 
-		dib7000m_get_frontend(fe);
+		dib7000m_get_frontend(fe, fep);
 	}
 
 	ret = dib7000m_tune(fe);
@@ -1465,6 +1465,6 @@ static struct dvb_frontend_ops dib7000m_ops = {
 	.read_ucblocks        = dib7000m_read_unc_blocks,
 };
 
-MODULE_AUTHOR("Patrick Boettcher <pboettcher@dibcom.fr>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("Driver for the DiBcom 7000MA/MB/PA/PB/MC COFDM demodulator");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/dvb-frontends/dib7000p.c b/drivers/media/dvb-frontends/dib7000p.c
index 33be5d6b9e10..b861d4437f2a 100644
--- a/drivers/media/dvb-frontends/dib7000p.c
+++ b/drivers/media/dvb-frontends/dib7000p.c
@@ -1405,9 +1405,9 @@ static int dib7000p_identify(struct dib7000p_state *st)
 	return 0;
 }
 
-static int dib7000p_get_frontend(struct dvb_frontend *fe)
+static int dib7000p_get_frontend(struct dvb_frontend *fe,
+				 struct dtv_frontend_properties *fep)
 {
-	struct dtv_frontend_properties *fep = &fe->dtv_property_cache;
 	struct dib7000p_state *state = fe->demodulator_priv;
 	u16 tps = dib7000p_read_word(state, 463);
 
@@ -1540,7 +1540,7 @@ static int dib7000p_set_frontend(struct dvb_frontend *fe)
 		if (found == 0 || found == 1)
 			return 0;
 
-		dib7000p_get_frontend(fe);
+		dib7000p_get_frontend(fe, fep);
 	}
 
 	ret = dib7000p_tune(fe);
@@ -2834,7 +2834,7 @@ static struct dvb_frontend_ops dib7000p_ops = {
 	.read_ucblocks = dib7000p_read_unc_blocks,
 };
 
-MODULE_AUTHOR("Olivier Grenie <ogrenie@dibcom.fr>");
-MODULE_AUTHOR("Patrick Boettcher <pboettcher@dibcom.fr>");
+MODULE_AUTHOR("Olivier Grenie <olivie.grenie@parrot.com>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("Driver for the DiBcom 7000PC COFDM demodulator");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/dvb-frontends/dib8000.c b/drivers/media/dvb-frontends/dib8000.c
index 94c26270fff0..ddf9c44877a2 100644
--- a/drivers/media/dvb-frontends/dib8000.c
+++ b/drivers/media/dvb-frontends/dib8000.c
@@ -3382,14 +3382,15 @@ static int dib8000_sleep(struct dvb_frontend *fe)
 
 static int dib8000_read_status(struct dvb_frontend *fe, enum fe_status *stat);
 
-static int dib8000_get_frontend(struct dvb_frontend *fe)
+static int dib8000_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *c)
 {
 	struct dib8000_state *state = fe->demodulator_priv;
 	u16 i, val = 0;
 	enum fe_status stat = 0;
 	u8 index_frontend, sub_index_frontend;
 
-	fe->dtv_property_cache.bandwidth_hz = 6000000;
+	c->bandwidth_hz = 6000000;
 
 	/*
 	 * If called to early, get_frontend makes dib8000_tune to either
@@ -3406,7 +3407,7 @@ static int dib8000_get_frontend(struct dvb_frontend *fe)
 		if (stat&FE_HAS_SYNC) {
 			dprintk("TMCC lock on the slave%i", index_frontend);
 			/* synchronize the cache with the other frontends */
-			state->fe[index_frontend]->ops.get_frontend(state->fe[index_frontend]);
+			state->fe[index_frontend]->ops.get_frontend(state->fe[index_frontend], c);
 			for (sub_index_frontend = 0; (sub_index_frontend < MAX_NUMBER_OF_FRONTENDS) && (state->fe[sub_index_frontend] != NULL); sub_index_frontend++) {
 				if (sub_index_frontend != index_frontend) {
 					state->fe[sub_index_frontend]->dtv_property_cache.isdbt_sb_mode = state->fe[index_frontend]->dtv_property_cache.isdbt_sb_mode;
@@ -3426,57 +3427,57 @@ static int dib8000_get_frontend(struct dvb_frontend *fe)
 		}
 	}
 
-	fe->dtv_property_cache.isdbt_sb_mode = dib8000_read_word(state, 508) & 0x1;
+	c->isdbt_sb_mode = dib8000_read_word(state, 508) & 0x1;
 
 	if (state->revision == 0x8090)
 		val = dib8000_read_word(state, 572);
 	else
 		val = dib8000_read_word(state, 570);
-	fe->dtv_property_cache.inversion = (val & 0x40) >> 6;
+	c->inversion = (val & 0x40) >> 6;
 	switch ((val & 0x30) >> 4) {
 	case 1:
-		fe->dtv_property_cache.transmission_mode = TRANSMISSION_MODE_2K;
+		c->transmission_mode = TRANSMISSION_MODE_2K;
 		dprintk("dib8000_get_frontend: transmission mode 2K");
 		break;
 	case 2:
-		fe->dtv_property_cache.transmission_mode = TRANSMISSION_MODE_4K;
+		c->transmission_mode = TRANSMISSION_MODE_4K;
 		dprintk("dib8000_get_frontend: transmission mode 4K");
 		break;
 	case 3:
 	default:
-		fe->dtv_property_cache.transmission_mode = TRANSMISSION_MODE_8K;
+		c->transmission_mode = TRANSMISSION_MODE_8K;
 		dprintk("dib8000_get_frontend: transmission mode 8K");
 		break;
 	}
 
 	switch (val & 0x3) {
 	case 0:
-		fe->dtv_property_cache.guard_interval = GUARD_INTERVAL_1_32;
+		c->guard_interval = GUARD_INTERVAL_1_32;
 		dprintk("dib8000_get_frontend: Guard Interval = 1/32 ");
 		break;
 	case 1:
-		fe->dtv_property_cache.guard_interval = GUARD_INTERVAL_1_16;
+		c->guard_interval = GUARD_INTERVAL_1_16;
 		dprintk("dib8000_get_frontend: Guard Interval = 1/16 ");
 		break;
 	case 2:
 		dprintk("dib8000_get_frontend: Guard Interval = 1/8 ");
-		fe->dtv_property_cache.guard_interval = GUARD_INTERVAL_1_8;
+		c->guard_interval = GUARD_INTERVAL_1_8;
 		break;
 	case 3:
 		dprintk("dib8000_get_frontend: Guard Interval = 1/4 ");
-		fe->dtv_property_cache.guard_interval = GUARD_INTERVAL_1_4;
+		c->guard_interval = GUARD_INTERVAL_1_4;
 		break;
 	}
 
 	val = dib8000_read_word(state, 505);
-	fe->dtv_property_cache.isdbt_partial_reception = val & 1;
-	dprintk("dib8000_get_frontend: partial_reception = %d ", fe->dtv_property_cache.isdbt_partial_reception);
+	c->isdbt_partial_reception = val & 1;
+	dprintk("dib8000_get_frontend: partial_reception = %d ", c->isdbt_partial_reception);
 
 	for (i = 0; i < 3; i++) {
 		int show;
 
 		val = dib8000_read_word(state, 493 + i) & 0x0f;
-		fe->dtv_property_cache.layer[i].segment_count = val;
+		c->layer[i].segment_count = val;
 
 		if (val == 0 || val > 13)
 			show = 0;
@@ -3485,41 +3486,41 @@ static int dib8000_get_frontend(struct dvb_frontend *fe)
 
 		if (show)
 			dprintk("dib8000_get_frontend: Layer %d segments = %d ",
-				i, fe->dtv_property_cache.layer[i].segment_count);
+				i, c->layer[i].segment_count);
 
 		val = dib8000_read_word(state, 499 + i) & 0x3;
 		/* Interleaving can be 0, 1, 2 or 4 */
 		if (val == 3)
 			val = 4;
-		fe->dtv_property_cache.layer[i].interleaving = val;
+		c->layer[i].interleaving = val;
 		if (show)
 			dprintk("dib8000_get_frontend: Layer %d time_intlv = %d ",
-				i, fe->dtv_property_cache.layer[i].interleaving);
+				i, c->layer[i].interleaving);
 
 		val = dib8000_read_word(state, 481 + i);
 		switch (val & 0x7) {
 		case 1:
-			fe->dtv_property_cache.layer[i].fec = FEC_1_2;
+			c->layer[i].fec = FEC_1_2;
 			if (show)
 				dprintk("dib8000_get_frontend: Layer %d Code Rate = 1/2 ", i);
 			break;
 		case 2:
-			fe->dtv_property_cache.layer[i].fec = FEC_2_3;
+			c->layer[i].fec = FEC_2_3;
 			if (show)
 				dprintk("dib8000_get_frontend: Layer %d Code Rate = 2/3 ", i);
 			break;
 		case 3:
-			fe->dtv_property_cache.layer[i].fec = FEC_3_4;
+			c->layer[i].fec = FEC_3_4;
 			if (show)
 				dprintk("dib8000_get_frontend: Layer %d Code Rate = 3/4 ", i);
 			break;
 		case 5:
-			fe->dtv_property_cache.layer[i].fec = FEC_5_6;
+			c->layer[i].fec = FEC_5_6;
 			if (show)
 				dprintk("dib8000_get_frontend: Layer %d Code Rate = 5/6 ", i);
 			break;
 		default:
-			fe->dtv_property_cache.layer[i].fec = FEC_7_8;
+			c->layer[i].fec = FEC_7_8;
 			if (show)
 				dprintk("dib8000_get_frontend: Layer %d Code Rate = 7/8 ", i);
 			break;
@@ -3528,23 +3529,23 @@ static int dib8000_get_frontend(struct dvb_frontend *fe)
 		val = dib8000_read_word(state, 487 + i);
 		switch (val & 0x3) {
 		case 0:
-			fe->dtv_property_cache.layer[i].modulation = DQPSK;
+			c->layer[i].modulation = DQPSK;
 			if (show)
 				dprintk("dib8000_get_frontend: Layer %d DQPSK ", i);
 			break;
 		case 1:
-			fe->dtv_property_cache.layer[i].modulation = QPSK;
+			c->layer[i].modulation = QPSK;
 			if (show)
 				dprintk("dib8000_get_frontend: Layer %d QPSK ", i);
 			break;
 		case 2:
-			fe->dtv_property_cache.layer[i].modulation = QAM_16;
+			c->layer[i].modulation = QAM_16;
 			if (show)
 				dprintk("dib8000_get_frontend: Layer %d QAM16 ", i);
 			break;
 		case 3:
 		default:
-			fe->dtv_property_cache.layer[i].modulation = QAM_64;
+			c->layer[i].modulation = QAM_64;
 			if (show)
 				dprintk("dib8000_get_frontend: Layer %d QAM64 ", i);
 			break;
@@ -3553,16 +3554,16 @@ static int dib8000_get_frontend(struct dvb_frontend *fe)
 
 	/* synchronize the cache with the other frontends */
 	for (index_frontend = 1; (index_frontend < MAX_NUMBER_OF_FRONTENDS) && (state->fe[index_frontend] != NULL); index_frontend++) {
-		state->fe[index_frontend]->dtv_property_cache.isdbt_sb_mode = fe->dtv_property_cache.isdbt_sb_mode;
-		state->fe[index_frontend]->dtv_property_cache.inversion = fe->dtv_property_cache.inversion;
-		state->fe[index_frontend]->dtv_property_cache.transmission_mode = fe->dtv_property_cache.transmission_mode;
-		state->fe[index_frontend]->dtv_property_cache.guard_interval = fe->dtv_property_cache.guard_interval;
-		state->fe[index_frontend]->dtv_property_cache.isdbt_partial_reception = fe->dtv_property_cache.isdbt_partial_reception;
+		state->fe[index_frontend]->dtv_property_cache.isdbt_sb_mode = c->isdbt_sb_mode;
+		state->fe[index_frontend]->dtv_property_cache.inversion = c->inversion;
+		state->fe[index_frontend]->dtv_property_cache.transmission_mode = c->transmission_mode;
+		state->fe[index_frontend]->dtv_property_cache.guard_interval = c->guard_interval;
+		state->fe[index_frontend]->dtv_property_cache.isdbt_partial_reception = c->isdbt_partial_reception;
 		for (i = 0; i < 3; i++) {
-			state->fe[index_frontend]->dtv_property_cache.layer[i].segment_count = fe->dtv_property_cache.layer[i].segment_count;
-			state->fe[index_frontend]->dtv_property_cache.layer[i].interleaving = fe->dtv_property_cache.layer[i].interleaving;
-			state->fe[index_frontend]->dtv_property_cache.layer[i].fec = fe->dtv_property_cache.layer[i].fec;
-			state->fe[index_frontend]->dtv_property_cache.layer[i].modulation = fe->dtv_property_cache.layer[i].modulation;
+			state->fe[index_frontend]->dtv_property_cache.layer[i].segment_count = c->layer[i].segment_count;
+			state->fe[index_frontend]->dtv_property_cache.layer[i].interleaving = c->layer[i].interleaving;
+			state->fe[index_frontend]->dtv_property_cache.layer[i].fec = c->layer[i].fec;
+			state->fe[index_frontend]->dtv_property_cache.layer[i].modulation = c->layer[i].modulation;
 		}
 	}
 	return 0;
@@ -3671,7 +3672,7 @@ static int dib8000_set_frontend(struct dvb_frontend *fe)
 			if (state->channel_parameters_set == 0) { /* searching */
 				if ((dib8000_get_status(state->fe[index_frontend]) == FE_STATUS_DEMOD_SUCCESS) || (dib8000_get_status(state->fe[index_frontend]) == FE_STATUS_FFT_SUCCESS)) {
 					dprintk("autosearch succeeded on fe%i", index_frontend);
-					dib8000_get_frontend(state->fe[index_frontend]); /* we read the channel parameters from the frontend which was successful */
+					dib8000_get_frontend(state->fe[index_frontend], c); /* we read the channel parameters from the frontend which was successful */
 					state->channel_parameters_set = 1;
 
 					for (l = 0; (l < MAX_NUMBER_OF_FRONTENDS) && (state->fe[l] != NULL); l++) {
@@ -4516,6 +4517,6 @@ void *dib8000_attach(struct dib8000_ops *ops)
 }
 EXPORT_SYMBOL(dib8000_attach);
 
-MODULE_AUTHOR("Olivier Grenie <Olivier.Grenie@dibcom.fr, " "Patrick Boettcher <pboettcher@dibcom.fr>");
+MODULE_AUTHOR("Olivier Grenie <Olivier.Grenie@parrot.com, Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("Driver for the DiBcom 8000 ISDB-T demodulator");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/dvb-frontends/dib9000.c b/drivers/media/dvb-frontends/dib9000.c
index 8f92aca0b073..5897977d2d00 100644
--- a/drivers/media/dvb-frontends/dib9000.c
+++ b/drivers/media/dvb-frontends/dib9000.c
@@ -225,7 +225,7 @@ static u16 to_fw_output_mode(u16 mode)
 	}
 }
 
-static u16 dib9000_read16_attr(struct dib9000_state *state, u16 reg, u8 * b, u32 len, u16 attribute)
+static int dib9000_read16_attr(struct dib9000_state *state, u16 reg, u8 *b, u32 len, u16 attribute)
 {
 	u32 chunk_size = 126;
 	u32 l;
@@ -309,7 +309,7 @@ static inline u16 dib9000_read_word_attr(struct dib9000_state *state, u16 reg, u
 
 #define dib9000_read16_noinc_attr(state, reg, b, len, attribute) dib9000_read16_attr(state, reg, b, len, (attribute) | DATA_BUS_ACCESS_MODE_NO_ADDRESS_INCREMENT)
 
-static u16 dib9000_write16_attr(struct dib9000_state *state, u16 reg, const u8 * buf, u32 len, u16 attribute)
+static int dib9000_write16_attr(struct dib9000_state *state, u16 reg, const u8 *buf, u32 len, u16 attribute)
 {
 	u32 chunk_size = 126;
 	u32 l;
@@ -1889,7 +1889,8 @@ static int dib9000_fe_get_tune_settings(struct dvb_frontend *fe, struct dvb_fron
 	return 0;
 }
 
-static int dib9000_get_frontend(struct dvb_frontend *fe)
+static int dib9000_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *c)
 {
 	struct dib9000_state *state = fe->demodulator_priv;
 	u8 index_frontend, sub_index_frontend;
@@ -1909,7 +1910,7 @@ static int dib9000_get_frontend(struct dvb_frontend *fe)
 			dprintk("TPS lock on the slave%i", index_frontend);
 
 			/* synchronize the cache with the other frontends */
-			state->fe[index_frontend]->ops.get_frontend(state->fe[index_frontend]);
+			state->fe[index_frontend]->ops.get_frontend(state->fe[index_frontend], c);
 			for (sub_index_frontend = 0; (sub_index_frontend < MAX_NUMBER_OF_FRONTENDS) && (state->fe[sub_index_frontend] != NULL);
 			     sub_index_frontend++) {
 				if (sub_index_frontend != index_frontend) {
@@ -1943,14 +1944,14 @@ static int dib9000_get_frontend(struct dvb_frontend *fe)
 
 	/* synchronize the cache with the other frontends */
 	for (index_frontend = 1; (index_frontend < MAX_NUMBER_OF_FRONTENDS) && (state->fe[index_frontend] != NULL); index_frontend++) {
-		state->fe[index_frontend]->dtv_property_cache.inversion = fe->dtv_property_cache.inversion;
-		state->fe[index_frontend]->dtv_property_cache.transmission_mode = fe->dtv_property_cache.transmission_mode;
-		state->fe[index_frontend]->dtv_property_cache.guard_interval = fe->dtv_property_cache.guard_interval;
-		state->fe[index_frontend]->dtv_property_cache.modulation = fe->dtv_property_cache.modulation;
-		state->fe[index_frontend]->dtv_property_cache.hierarchy = fe->dtv_property_cache.hierarchy;
-		state->fe[index_frontend]->dtv_property_cache.code_rate_HP = fe->dtv_property_cache.code_rate_HP;
-		state->fe[index_frontend]->dtv_property_cache.code_rate_LP = fe->dtv_property_cache.code_rate_LP;
-		state->fe[index_frontend]->dtv_property_cache.rolloff = fe->dtv_property_cache.rolloff;
+		state->fe[index_frontend]->dtv_property_cache.inversion = c->inversion;
+		state->fe[index_frontend]->dtv_property_cache.transmission_mode = c->transmission_mode;
+		state->fe[index_frontend]->dtv_property_cache.guard_interval = c->guard_interval;
+		state->fe[index_frontend]->dtv_property_cache.modulation = c->modulation;
+		state->fe[index_frontend]->dtv_property_cache.hierarchy = c->hierarchy;
+		state->fe[index_frontend]->dtv_property_cache.code_rate_HP = c->code_rate_HP;
+		state->fe[index_frontend]->dtv_property_cache.code_rate_LP = c->code_rate_LP;
+		state->fe[index_frontend]->dtv_property_cache.rolloff = c->rolloff;
 	}
 	ret = 0;
 
@@ -2083,7 +2084,7 @@ static int dib9000_set_frontend(struct dvb_frontend *fe)
 
 	/* synchronize all the channel cache */
 	state->get_frontend_internal = 1;
-	dib9000_get_frontend(state->fe[0]);
+	dib9000_get_frontend(state->fe[0], &state->fe[0]->dtv_property_cache);
 	state->get_frontend_internal = 0;
 
 	/* retune the other frontends with the found channel */
@@ -2589,7 +2590,7 @@ static struct dvb_frontend_ops dib9000_ops = {
 	.read_ucblocks = dib9000_read_unc_blocks,
 };
 
-MODULE_AUTHOR("Patrick Boettcher <pboettcher@dibcom.fr>");
-MODULE_AUTHOR("Olivier Grenie <ogrenie@dibcom.fr>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
+MODULE_AUTHOR("Olivier Grenie <olivier.grenie@parrot.com>");
 MODULE_DESCRIPTION("Driver for the DiBcom 9000 COFDM demodulator");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/dvb-frontends/dibx000_common.c b/drivers/media/dvb-frontends/dibx000_common.c
index 43be7238311e..723358d7ca84 100644
--- a/drivers/media/dvb-frontends/dibx000_common.c
+++ b/drivers/media/dvb-frontends/dibx000_common.c
@@ -510,6 +510,6 @@ u32 systime(void)
 }
 EXPORT_SYMBOL(systime);
 
-MODULE_AUTHOR("Patrick Boettcher <pboettcher@dibcom.fr>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("Common function the DiBcom demodulator family");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/dvb-frontends/drx39xyj/drxj.c b/drivers/media/dvb-frontends/drx39xyj/drxj.c
index b28b5787b39a..e48b741d439e 100644
--- a/drivers/media/dvb-frontends/drx39xyj/drxj.c
+++ b/drivers/media/dvb-frontends/drx39xyj/drxj.c
@@ -4131,7 +4131,7 @@ int drxj_dap_scu_atomic_read_write_block(struct i2c_device_addr *dev_addr, u32 a
 {
 	struct drxjscu_cmd scu_cmd;
 	int rc;
-	u16 set_param_parameters[15];
+	u16 set_param_parameters[18];
 	u16 cmd_result[15];
 
 	/* Parameter check */
@@ -9597,12 +9597,13 @@ ctrl_get_qam_sig_quality(struct drx_demod_instance *demod)
 
 	   Precision errors still possible.
 	 */
-	e = post_bit_err_rs * 742686;
-	m = fec_oc_period * 100;
-	if (fec_oc_period == 0)
+	if (!fec_oc_period) {
 		qam_post_rs_ber = 0xFFFFFFFF;
-	else
+	} else {
+		e = post_bit_err_rs * 742686;
+		m = fec_oc_period * 100;
 		qam_post_rs_ber = e / m;
+	}
 
 	/* fill signal quality data structure */
 	p->pre_bit_count.stat[0].scale = FE_SCALE_COUNTER;
diff --git a/drivers/media/dvb-frontends/dvb_dummy_fe.c b/drivers/media/dvb-frontends/dvb_dummy_fe.c
index 14e996d45fac..e5bd8c62ad3a 100644
--- a/drivers/media/dvb-frontends/dvb_dummy_fe.c
+++ b/drivers/media/dvb-frontends/dvb_dummy_fe.c
@@ -70,9 +70,12 @@ static int dvb_dummy_fe_read_ucblocks(struct dvb_frontend* fe, u32* ucblocks)
 }
 
 /*
- * Only needed if it actually reads something from the hardware
+ * Should only be implemented if it actually reads something from the hardware.
+ * Also, it should check for the locks, in order to avoid report wrong data
+ * to userspace.
  */
-static int dvb_dummy_fe_get_frontend(struct dvb_frontend *fe)
+static int dvb_dummy_fe_get_frontend(struct dvb_frontend *fe,
+				     struct dtv_frontend_properties *p)
 {
 	return 0;
 }
diff --git a/drivers/media/dvb-frontends/hd29l2.c b/drivers/media/dvb-frontends/hd29l2.c
index 40e359f2d17d..1c7eb477e2cd 100644
--- a/drivers/media/dvb-frontends/hd29l2.c
+++ b/drivers/media/dvb-frontends/hd29l2.c
@@ -560,11 +560,11 @@ static int hd29l2_get_frontend_algo(struct dvb_frontend *fe)
 	return DVBFE_ALGO_CUSTOM;
 }
 
-static int hd29l2_get_frontend(struct dvb_frontend *fe)
+static int hd29l2_get_frontend(struct dvb_frontend *fe,
+			       struct dtv_frontend_properties *c)
 {
 	int ret;
 	struct hd29l2_priv *priv = fe->demodulator_priv;
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	u8 buf[3];
 	u32 if_ctl;
 	char *str_constellation, *str_code_rate, *str_constellation_code_rate,
diff --git a/drivers/media/dvb-frontends/l64781.c b/drivers/media/dvb-frontends/l64781.c
index 0977871232a2..2f3d0519e19b 100644
--- a/drivers/media/dvb-frontends/l64781.c
+++ b/drivers/media/dvb-frontends/l64781.c
@@ -243,9 +243,9 @@ static int apply_frontend_param(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int get_frontend(struct dvb_frontend *fe)
+static int get_frontend(struct dvb_frontend *fe,
+			struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct l64781_state* state = fe->demodulator_priv;
 	int tmp;
 
diff --git a/drivers/media/dvb-frontends/lg2160.c b/drivers/media/dvb-frontends/lg2160.c
index 7880f71ccd8a..f51a3a0b3949 100644
--- a/drivers/media/dvb-frontends/lg2160.c
+++ b/drivers/media/dvb-frontends/lg2160.c
@@ -942,101 +942,102 @@ static int lg216x_read_rs_err_count(struct lg216x_state *state, u16 *err)
 
 /* ------------------------------------------------------------------------ */
 
-static int lg216x_get_frontend(struct dvb_frontend *fe)
+static int lg216x_get_frontend(struct dvb_frontend *fe,
+			       struct dtv_frontend_properties *c)
 {
 	struct lg216x_state *state = fe->demodulator_priv;
 	int ret;
 
 	lg_dbg("\n");
 
-	fe->dtv_property_cache.modulation = VSB_8;
-	fe->dtv_property_cache.frequency = state->current_frequency;
-	fe->dtv_property_cache.delivery_system = SYS_ATSCMH;
+	c->modulation = VSB_8;
+	c->frequency = state->current_frequency;
+	c->delivery_system = SYS_ATSCMH;
 
 	ret = lg216x_get_fic_version(state,
-				     &fe->dtv_property_cache.atscmh_fic_ver);
+				     &c->atscmh_fic_ver);
 	if (lg_fail(ret))
 		goto fail;
-	if (state->fic_ver != fe->dtv_property_cache.atscmh_fic_ver) {
-		state->fic_ver = fe->dtv_property_cache.atscmh_fic_ver;
+	if (state->fic_ver != c->atscmh_fic_ver) {
+		state->fic_ver = c->atscmh_fic_ver;
 
 #if 0
 		ret = lg2160_get_parade_id(state,
-				&fe->dtv_property_cache.atscmh_parade_id);
+				&c->atscmh_parade_id);
 		if (lg_fail(ret))
 			goto fail;
 /* #else */
-		fe->dtv_property_cache.atscmh_parade_id = state->parade_id;
+		c->atscmh_parade_id = state->parade_id;
 #endif
 		ret = lg216x_get_nog(state,
-				     &fe->dtv_property_cache.atscmh_nog);
+				     &c->atscmh_nog);
 		if (lg_fail(ret))
 			goto fail;
 		ret = lg216x_get_tnog(state,
-				      &fe->dtv_property_cache.atscmh_tnog);
+				      &c->atscmh_tnog);
 		if (lg_fail(ret))
 			goto fail;
 		ret = lg216x_get_sgn(state,
-				     &fe->dtv_property_cache.atscmh_sgn);
+				     &c->atscmh_sgn);
 		if (lg_fail(ret))
 			goto fail;
 		ret = lg216x_get_prc(state,
-				     &fe->dtv_property_cache.atscmh_prc);
+				     &c->atscmh_prc);
 		if (lg_fail(ret))
 			goto fail;
 
 		ret = lg216x_get_rs_frame_mode(state,
 			(enum atscmh_rs_frame_mode *)
-			&fe->dtv_property_cache.atscmh_rs_frame_mode);
+			&c->atscmh_rs_frame_mode);
 		if (lg_fail(ret))
 			goto fail;
 		ret = lg216x_get_rs_frame_ensemble(state,
 			(enum atscmh_rs_frame_ensemble *)
-			&fe->dtv_property_cache.atscmh_rs_frame_ensemble);
+			&c->atscmh_rs_frame_ensemble);
 		if (lg_fail(ret))
 			goto fail;
 		ret = lg216x_get_rs_code_mode(state,
 			(enum atscmh_rs_code_mode *)
-			&fe->dtv_property_cache.atscmh_rs_code_mode_pri,
+			&c->atscmh_rs_code_mode_pri,
 			(enum atscmh_rs_code_mode *)
-			&fe->dtv_property_cache.atscmh_rs_code_mode_sec);
+			&c->atscmh_rs_code_mode_sec);
 		if (lg_fail(ret))
 			goto fail;
 		ret = lg216x_get_sccc_block_mode(state,
 			(enum atscmh_sccc_block_mode *)
-			&fe->dtv_property_cache.atscmh_sccc_block_mode);
+			&c->atscmh_sccc_block_mode);
 		if (lg_fail(ret))
 			goto fail;
 		ret = lg216x_get_sccc_code_mode(state,
 			(enum atscmh_sccc_code_mode *)
-			&fe->dtv_property_cache.atscmh_sccc_code_mode_a,
+			&c->atscmh_sccc_code_mode_a,
 			(enum atscmh_sccc_code_mode *)
-			&fe->dtv_property_cache.atscmh_sccc_code_mode_b,
+			&c->atscmh_sccc_code_mode_b,
 			(enum atscmh_sccc_code_mode *)
-			&fe->dtv_property_cache.atscmh_sccc_code_mode_c,
+			&c->atscmh_sccc_code_mode_c,
 			(enum atscmh_sccc_code_mode *)
-			&fe->dtv_property_cache.atscmh_sccc_code_mode_d);
+			&c->atscmh_sccc_code_mode_d);
 		if (lg_fail(ret))
 			goto fail;
 	}
 #if 0
 	ret = lg216x_read_fic_err_count(state,
-				(u8 *)&fe->dtv_property_cache.atscmh_fic_err);
+				(u8 *)&c->atscmh_fic_err);
 	if (lg_fail(ret))
 		goto fail;
 	ret = lg216x_read_crc_err_count(state,
-				&fe->dtv_property_cache.atscmh_crc_err);
+				&c->atscmh_crc_err);
 	if (lg_fail(ret))
 		goto fail;
 	ret = lg216x_read_rs_err_count(state,
-				&fe->dtv_property_cache.atscmh_rs_err);
+				&c->atscmh_rs_err);
 	if (lg_fail(ret))
 		goto fail;
 
 	switch (state->cfg->lg_chip) {
 	case LG2160:
-		if (((fe->dtv_property_cache.atscmh_rs_err >= 240) &&
-		     (fe->dtv_property_cache.atscmh_crc_err >= 240)) &&
+		if (((c->atscmh_rs_err >= 240) &&
+		     (c->atscmh_crc_err >= 240)) &&
 		    ((jiffies_to_msecs(jiffies) - state->last_reset) > 6000))
 			ret = lg216x_soft_reset(state);
 		break;
@@ -1054,14 +1055,17 @@ fail:
 static int lg216x_get_property(struct dvb_frontend *fe,
 			       struct dtv_property *tvp)
 {
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+
 	return (DTV_ATSCMH_FIC_VER == tvp->cmd) ?
-		lg216x_get_frontend(fe) : 0;
+		lg216x_get_frontend(fe, c) : 0;
 }
 
 
 static int lg2160_set_frontend(struct dvb_frontend *fe)
 {
 	struct lg216x_state *state = fe->demodulator_priv;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret;
 
 	lg_dbg("(%d)\n", fe->dtv_property_cache.frequency);
@@ -1129,7 +1133,7 @@ static int lg2160_set_frontend(struct dvb_frontend *fe)
 	ret = lg216x_enable_fic(state, 1);
 	lg_fail(ret);
 
-	lg216x_get_frontend(fe);
+	lg216x_get_frontend(fe, c);
 fail:
 	return ret;
 }
diff --git a/drivers/media/dvb-frontends/lgdt3305.c b/drivers/media/dvb-frontends/lgdt3305.c
index 47121866163d..4503e8852fd1 100644
--- a/drivers/media/dvb-frontends/lgdt3305.c
+++ b/drivers/media/dvb-frontends/lgdt3305.c
@@ -812,9 +812,9 @@ fail:
 	return ret;
 }
 
-static int lgdt3305_get_frontend(struct dvb_frontend *fe)
+static int lgdt3305_get_frontend(struct dvb_frontend *fe,
+				 struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct lgdt3305_state *state = fe->demodulator_priv;
 
 	lg_dbg("\n");
diff --git a/drivers/media/dvb-frontends/lgdt3306a.c b/drivers/media/dvb-frontends/lgdt3306a.c
index 721fbc07e9ee..179c26e5eb4e 100644
--- a/drivers/media/dvb-frontends/lgdt3306a.c
+++ b/drivers/media/dvb-frontends/lgdt3306a.c
@@ -1040,10 +1040,10 @@ fail:
 	return ret;
 }
 
-static int lgdt3306a_get_frontend(struct dvb_frontend *fe)
+static int lgdt3306a_get_frontend(struct dvb_frontend *fe,
+				  struct dtv_frontend_properties *p)
 {
 	struct lgdt3306a_state *state = fe->demodulator_priv;
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 
 	dbg_info("(%u, %d)\n",
 		 state->current_frequency, state->current_modulation);
diff --git a/drivers/media/dvb-frontends/lgdt330x.c b/drivers/media/dvb-frontends/lgdt330x.c
index cf3cc20510da..96bf254da21e 100644
--- a/drivers/media/dvb-frontends/lgdt330x.c
+++ b/drivers/media/dvb-frontends/lgdt330x.c
@@ -439,10 +439,11 @@ static int lgdt330x_set_parameters(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int lgdt330x_get_frontend(struct dvb_frontend *fe)
+static int lgdt330x_get_frontend(struct dvb_frontend *fe,
+				 struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct lgdt330x_state *state = fe->demodulator_priv;
+
 	p->frequency = state->current_frequency;
 	return 0;
 }
diff --git a/drivers/media/dvb-frontends/lgs8gl5.c b/drivers/media/dvb-frontends/lgs8gl5.c
index 7bbb2c18c2dd..fbfd87b5b803 100644
--- a/drivers/media/dvb-frontends/lgs8gl5.c
+++ b/drivers/media/dvb-frontends/lgs8gl5.c
@@ -336,10 +336,11 @@ lgs8gl5_set_frontend(struct dvb_frontend *fe)
 
 
 static int
-lgs8gl5_get_frontend(struct dvb_frontend *fe)
+lgs8gl5_get_frontend(struct dvb_frontend *fe,
+		     struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct lgs8gl5_state *state = fe->demodulator_priv;
+
 	u8 inv = lgs8gl5_read_reg(state, REG_INVERSION);
 
 	p->inversion = (inv & REG_INVERSION_ON) ? INVERSION_ON : INVERSION_OFF;
diff --git a/drivers/media/dvb-frontends/lgs8gxx.c b/drivers/media/dvb-frontends/lgs8gxx.c
index e2c191c8b196..919daeb96747 100644
--- a/drivers/media/dvb-frontends/lgs8gxx.c
+++ b/drivers/media/dvb-frontends/lgs8gxx.c
@@ -672,7 +672,7 @@ static int lgs8gxx_write(struct dvb_frontend *fe, const u8 buf[], int len)
 
 static int lgs8gxx_set_fe(struct dvb_frontend *fe)
 {
-
+	struct dtv_frontend_properties *fe_params = &fe->dtv_property_cache;
 	struct lgs8gxx_state *priv = fe->demodulator_priv;
 
 	dprintk("%s\n", __func__);
@@ -689,17 +689,7 @@ static int lgs8gxx_set_fe(struct dvb_frontend *fe)
 
 	msleep(10);
 
-	return 0;
-}
-
-static int lgs8gxx_get_fe(struct dvb_frontend *fe)
-{
-	struct dtv_frontend_properties *fe_params = &fe->dtv_property_cache;
-	dprintk("%s\n", __func__);
-
 	/* TODO: get real readings from device */
-	/* inversion status */
-	fe_params->inversion = INVERSION_OFF;
 
 	/* bandwidth */
 	fe_params->bandwidth_hz = 8000000;
@@ -1016,7 +1006,6 @@ static struct dvb_frontend_ops lgs8gxx_ops = {
 	.i2c_gate_ctrl = lgs8gxx_i2c_gate_ctrl,
 
 	.set_frontend = lgs8gxx_set_fe,
-	.get_frontend = lgs8gxx_get_fe,
 	.get_tune_settings = lgs8gxx_get_tune_settings,
 
 	.read_status = lgs8gxx_read_status,
diff --git a/drivers/media/dvb-frontends/m88ds3103.c b/drivers/media/dvb-frontends/m88ds3103.c
index ce73a5ec6036..76883600ec6f 100644
--- a/drivers/media/dvb-frontends/m88ds3103.c
+++ b/drivers/media/dvb-frontends/m88ds3103.c
@@ -791,11 +791,11 @@ err:
 	return ret;
 }
 
-static int m88ds3103_get_frontend(struct dvb_frontend *fe)
+static int m88ds3103_get_frontend(struct dvb_frontend *fe,
+				  struct dtv_frontend_properties *c)
 {
 	struct m88ds3103_dev *dev = fe->demodulator_priv;
 	struct i2c_client *client = dev->client;
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret;
 	u8 buf[3];
 
diff --git a/drivers/media/dvb-frontends/m88rs2000.c b/drivers/media/dvb-frontends/m88rs2000.c
index 9b6f464c48bd..a09b12313a73 100644
--- a/drivers/media/dvb-frontends/m88rs2000.c
+++ b/drivers/media/dvb-frontends/m88rs2000.c
@@ -708,10 +708,11 @@ static int m88rs2000_set_frontend(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int m88rs2000_get_frontend(struct dvb_frontend *fe)
+static int m88rs2000_get_frontend(struct dvb_frontend *fe,
+				  struct dtv_frontend_properties *c)
 {
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	struct m88rs2000_state *state = fe->demodulator_priv;
+
 	c->fec_inner = state->fec_inner;
 	c->frequency = state->tuner_frequency;
 	c->symbol_rate = state->symbol_rate;
diff --git a/drivers/media/dvb-frontends/mb86a20s.c b/drivers/media/dvb-frontends/mb86a20s.c
index cfc005ee11d8..fb88dddaf3a3 100644
--- a/drivers/media/dvb-frontends/mb86a20s.c
+++ b/drivers/media/dvb-frontends/mb86a20s.c
@@ -2028,16 +2028,6 @@ static int mb86a20s_read_signal_strength_from_cache(struct dvb_frontend *fe,
 	return 0;
 }
 
-static int mb86a20s_get_frontend_dummy(struct dvb_frontend *fe)
-{
-	/*
-	 * get_frontend is now handled together with other stats
-	 * retrival, when read_status() is called, as some statistics
-	 * will depend on the layers detection.
-	 */
-	return 0;
-};
-
 static int mb86a20s_tune(struct dvb_frontend *fe,
 			bool re_tune,
 			unsigned int mode_flags,
@@ -2136,7 +2126,6 @@ static struct dvb_frontend_ops mb86a20s_ops = {
 
 	.init = mb86a20s_initfe,
 	.set_frontend = mb86a20s_set_frontend,
-	.get_frontend = mb86a20s_get_frontend_dummy,
 	.read_status = mb86a20s_read_status_and_stats,
 	.read_signal_strength = mb86a20s_read_signal_strength_from_cache,
 	.tune = mb86a20s_tune,
diff --git a/drivers/staging/media/mn88473/mn88473.c b/drivers/media/dvb-frontends/mn88473.c
index a222e99935d2..6c5d592161d4 100644
--- a/drivers/staging/media/mn88473/mn88473.c
+++ b/drivers/media/dvb-frontends/mn88473.c
@@ -29,21 +29,17 @@ static int mn88473_set_frontend(struct dvb_frontend *fe)
 	struct mn88473_dev *dev = i2c_get_clientdata(client);
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret, i;
+	unsigned int uitmp;
 	u32 if_frequency;
-	u64 tmp;
-	u8 delivery_system_val, if_val[3], bw_val[7];
+	u8 delivery_system_val, if_val[3], *conf_val_ptr;
+	u8 reg_bank2_2d_val, reg_bank0_d2_val;
 
 	dev_dbg(&client->dev,
 		"delivery_system=%u modulation=%u frequency=%u bandwidth_hz=%u symbol_rate=%u inversion=%d stream_id=%d\n",
-		c->delivery_system,
-		c->modulation,
-		c->frequency,
-		c->bandwidth_hz,
-		c->symbol_rate,
-		c->inversion,
-		c->stream_id);
-
-	if (!dev->warm) {
+		c->delivery_system, c->modulation, c->frequency,
+		c->bandwidth_hz, c->symbol_rate, c->inversion, c->stream_id);
+
+	if (!dev->active) {
 		ret = -EAGAIN;
 		goto err;
 	}
@@ -51,30 +47,50 @@ static int mn88473_set_frontend(struct dvb_frontend *fe)
 	switch (c->delivery_system) {
 	case SYS_DVBT:
 		delivery_system_val = 0x02;
+		reg_bank2_2d_val = 0x23;
+		reg_bank0_d2_val = 0x2a;
 		break;
 	case SYS_DVBT2:
 		delivery_system_val = 0x03;
+		reg_bank2_2d_val = 0x3b;
+		reg_bank0_d2_val = 0x29;
 		break;
 	case SYS_DVBC_ANNEX_A:
 		delivery_system_val = 0x04;
+		reg_bank2_2d_val = 0x3b;
+		reg_bank0_d2_val = 0x29;
 		break;
 	default:
 		ret = -EINVAL;
 		goto err;
 	}
 
-	if (c->bandwidth_hz <= 6000000) {
-		memcpy(bw_val, "\xe9\x55\x55\x1c\x29\x1c\x29", 7);
-	} else if (c->bandwidth_hz <= 7000000) {
-		memcpy(bw_val, "\xc8\x00\x00\x17\x0a\x17\x0a", 7);
-	} else if (c->bandwidth_hz <= 8000000) {
-		memcpy(bw_val, "\xaf\x00\x00\x11\xec\x11\xec", 7);
-	} else {
-		ret = -EINVAL;
-		goto err;
+	switch (c->delivery_system) {
+	case SYS_DVBT:
+	case SYS_DVBT2:
+		switch (c->bandwidth_hz) {
+		case 6000000:
+			conf_val_ptr = "\xe9\x55\x55\x1c\x29\x1c\x29";
+			break;
+		case 7000000:
+			conf_val_ptr = "\xc8\x00\x00\x17\x0a\x17\x0a";
+			break;
+		case 8000000:
+			conf_val_ptr = "\xaf\x00\x00\x11\xec\x11\xec";
+			break;
+		default:
+			ret = -EINVAL;
+			goto err;
+		}
+		break;
+	case SYS_DVBC_ANNEX_A:
+		conf_val_ptr = "\x10\xab\x0d\xae\x1d\x9d";
+		break;
+	default:
+		break;
 	}
 
-	/* program tuner */
+	/* Program tuner */
 	if (fe->ops.tuner_ops.set_params) {
 		ret = fe->ops.tuner_ops.set_params(fe);
 		if (ret)
@@ -86,27 +102,45 @@ static int mn88473_set_frontend(struct dvb_frontend *fe)
 		if (ret)
 			goto err;
 
-		dev_dbg(&client->dev, "get_if_frequency=%d\n", if_frequency);
+		dev_dbg(&client->dev, "get_if_frequency=%u\n", if_frequency);
 	} else {
-		if_frequency = 0;
+		ret = -EINVAL;
+		goto err;
 	}
 
-	/* Calculate IF registers ( (1<<24)*IF / Xtal ) */
-	tmp =  div_u64(if_frequency * (u64)(1<<24) + (dev->xtal / 2),
-				   dev->xtal);
-	if_val[0] = ((tmp >> 16) & 0xff);
-	if_val[1] = ((tmp >>  8) & 0xff);
-	if_val[2] = ((tmp >>  0) & 0xff);
+	/* Calculate IF registers */
+	uitmp = DIV_ROUND_CLOSEST_ULL((u64) if_frequency * 0x1000000, dev->clk);
+	if_val[0] = (uitmp >> 16) & 0xff;
+	if_val[1] = (uitmp >>  8) & 0xff;
+	if_val[2] = (uitmp >>  0) & 0xff;
 
 	ret = regmap_write(dev->regmap[2], 0x05, 0x00);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[2], 0xfb, 0x13);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[2], 0xef, 0x13);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[2], 0xf9, 0x13);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[2], 0x00, 0x18);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[2], 0x01, 0x01);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[2], 0x02, 0x21);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[2], 0x03, delivery_system_val);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[2], 0x0b, 0x00);
+	if (ret)
+		goto err;
 
 	for (i = 0; i < sizeof(if_val); i++) {
 		ret = regmap_write(dev->regmap[2], 0x10 + i, if_val[i]);
@@ -114,52 +148,85 @@ static int mn88473_set_frontend(struct dvb_frontend *fe)
 			goto err;
 	}
 
-	for (i = 0; i < sizeof(bw_val); i++) {
-		ret = regmap_write(dev->regmap[2], 0x13 + i, bw_val[i]);
+	switch (c->delivery_system) {
+	case SYS_DVBT:
+	case SYS_DVBT2:
+		for (i = 0; i < 7; i++) {
+			ret = regmap_write(dev->regmap[2], 0x13 + i,
+					   conf_val_ptr[i]);
+			if (ret)
+				goto err;
+		}
+		break;
+	case SYS_DVBC_ANNEX_A:
+		ret = regmap_bulk_write(dev->regmap[1], 0x10, conf_val_ptr, 6);
 		if (ret)
 			goto err;
+		break;
+	default:
+		break;
 	}
 
-	ret = regmap_write(dev->regmap[2], 0x2d, 0x3b);
+	ret = regmap_write(dev->regmap[2], 0x2d, reg_bank2_2d_val);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[2], 0x2e, 0x00);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[2], 0x56, 0x0d);
-	ret = regmap_write(dev->regmap[0], 0x01, 0xba);
-	ret = regmap_write(dev->regmap[0], 0x02, 0x13);
-	ret = regmap_write(dev->regmap[0], 0x03, 0x80);
-	ret = regmap_write(dev->regmap[0], 0x04, 0xba);
-	ret = regmap_write(dev->regmap[0], 0x05, 0x91);
-	ret = regmap_write(dev->regmap[0], 0x07, 0xe7);
-	ret = regmap_write(dev->regmap[0], 0x08, 0x28);
+	if (ret)
+		goto err;
+	ret = regmap_bulk_write(dev->regmap[0], 0x01,
+				"\xba\x13\x80\xba\x91\xdd\xe7\x28", 8);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[0], 0x0a, 0x1a);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[0], 0x13, 0x1f);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[0], 0x19, 0x03);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[0], 0x1d, 0xb0);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[0], 0x2a, 0x72);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[0], 0x2d, 0x00);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[0], 0x3c, 0x00);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[0], 0x3f, 0xf8);
-	ret = regmap_write(dev->regmap[0], 0x40, 0xf4);
-	ret = regmap_write(dev->regmap[0], 0x41, 0x08);
-	ret = regmap_write(dev->regmap[0], 0xd2, 0x29);
+	if (ret)
+		goto err;
+	ret = regmap_bulk_write(dev->regmap[0], 0x40, "\xf4\x08", 2);
+	if (ret)
+		goto err;
+	ret = regmap_write(dev->regmap[0], 0xd2, reg_bank0_d2_val);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[0], 0xd4, 0x55);
-	ret = regmap_write(dev->regmap[1], 0x10, 0x10);
-	ret = regmap_write(dev->regmap[1], 0x11, 0xab);
-	ret = regmap_write(dev->regmap[1], 0x12, 0x0d);
-	ret = regmap_write(dev->regmap[1], 0x13, 0xae);
-	ret = regmap_write(dev->regmap[1], 0x14, 0x1d);
-	ret = regmap_write(dev->regmap[1], 0x15, 0x9d);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[1], 0xbe, 0x08);
-	ret = regmap_write(dev->regmap[2], 0x09, 0x08);
-	ret = regmap_write(dev->regmap[2], 0x08, 0x1d);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[0], 0xb2, 0x37);
+	if (ret)
+		goto err;
 	ret = regmap_write(dev->regmap[0], 0xd7, 0x04);
-	ret = regmap_write(dev->regmap[2], 0x32, 0x80);
-	ret = regmap_write(dev->regmap[2], 0x36, 0x00);
-	ret = regmap_write(dev->regmap[2], 0xf8, 0x9f);
 	if (ret)
 		goto err;
 
-	dev->delivery_system = c->delivery_system;
+	/* Reset FSM */
+	ret = regmap_write(dev->regmap[2], 0xf8, 0x9f);
+	if (ret)
+		goto err;
 
 	return 0;
 err:
@@ -173,51 +240,61 @@ static int mn88473_read_status(struct dvb_frontend *fe, enum fe_status *status)
 	struct mn88473_dev *dev = i2c_get_clientdata(client);
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret;
-	unsigned int utmp;
-	int lock = 0;
-
-	*status = 0;
+	unsigned int uitmp;
 
-	if (!dev->warm) {
+	if (!dev->active) {
 		ret = -EAGAIN;
 		goto err;
 	}
 
+	*status = 0;
+
 	switch (c->delivery_system) {
 	case SYS_DVBT:
-		ret = regmap_read(dev->regmap[0], 0x62, &utmp);
+		ret = regmap_read(dev->regmap[0], 0x62, &uitmp);
 		if (ret)
 			goto err;
-		if (!(utmp & 0xA0)) {
-			if ((utmp & 0xF) >= 0x03)
-				*status |= FE_HAS_SIGNAL;
-			if ((utmp & 0xF) >= 0x09)
-				lock = 1;
+
+		if (!(uitmp & 0xa0)) {
+			if ((uitmp & 0x0f) >= 0x09)
+				*status = FE_HAS_SIGNAL | FE_HAS_CARRIER |
+					  FE_HAS_VITERBI | FE_HAS_SYNC |
+					  FE_HAS_LOCK;
+			else if ((uitmp & 0x0f) >= 0x03)
+				*status = FE_HAS_SIGNAL | FE_HAS_CARRIER;
 		}
 		break;
 	case SYS_DVBT2:
-		ret = regmap_read(dev->regmap[2], 0x8B, &utmp);
+		ret = regmap_read(dev->regmap[2], 0x8b, &uitmp);
 		if (ret)
 			goto err;
-		if (!(utmp & 0x40)) {
-			if ((utmp & 0xF) >= 0x07)
-				*status |= FE_HAS_SIGNAL;
-			if ((utmp & 0xF) >= 0x0a)
-				*status |= FE_HAS_CARRIER;
-			if ((utmp & 0xF) >= 0x0d)
-				*status |= FE_HAS_VITERBI | FE_HAS_SYNC | FE_HAS_LOCK;
+
+		if (!(uitmp & 0x40)) {
+			if ((uitmp & 0x0f) >= 0x0d)
+				*status = FE_HAS_SIGNAL | FE_HAS_CARRIER |
+					  FE_HAS_VITERBI | FE_HAS_SYNC |
+					  FE_HAS_LOCK;
+			else if ((uitmp & 0x0f) >= 0x0a)
+				*status = FE_HAS_SIGNAL | FE_HAS_CARRIER |
+					  FE_HAS_VITERBI;
+			else if ((uitmp & 0x0f) >= 0x07)
+				*status = FE_HAS_SIGNAL | FE_HAS_CARRIER;
 		}
 		break;
 	case SYS_DVBC_ANNEX_A:
-		ret = regmap_read(dev->regmap[1], 0x85, &utmp);
+		ret = regmap_read(dev->regmap[1], 0x85, &uitmp);
 		if (ret)
 			goto err;
-		if (!(utmp & 0x40)) {
-			ret = regmap_read(dev->regmap[1], 0x89, &utmp);
+
+		if (!(uitmp & 0x40)) {
+			ret = regmap_read(dev->regmap[1], 0x89, &uitmp);
 			if (ret)
 				goto err;
-			if (utmp & 0x01)
-				lock = 1;
+
+			if (uitmp & 0x01)
+				*status = FE_HAS_SIGNAL | FE_HAS_CARRIER |
+					  FE_HAS_VITERBI | FE_HAS_SYNC |
+					  FE_HAS_LOCK;
 		}
 		break;
 	default:
@@ -225,10 +302,6 @@ static int mn88473_read_status(struct dvb_frontend *fe, enum fe_status *status)
 		goto err;
 	}
 
-	if (lock)
-		*status = FE_HAS_SIGNAL | FE_HAS_CARRIER | FE_HAS_VITERBI |
-				FE_HAS_SYNC | FE_HAS_LOCK;
-
 	return 0;
 err:
 	dev_dbg(&client->dev, "failed=%d\n", ret);
@@ -239,85 +312,76 @@ static int mn88473_init(struct dvb_frontend *fe)
 {
 	struct i2c_client *client = fe->demodulator_priv;
 	struct mn88473_dev *dev = i2c_get_clientdata(client);
-	int ret, len, remaining;
-	const struct firmware *fw = NULL;
-	u8 *fw_file = MN88473_FIRMWARE;
-	unsigned int tmp;
+	int ret, len, remain;
+	unsigned int uitmp;
+	const struct firmware *fw;
+	const char *name = MN88473_FIRMWARE;
 
 	dev_dbg(&client->dev, "\n");
 
-	/* set cold state by default */
-	dev->warm = false;
-
-	/* check if firmware is already running */
-	ret = regmap_read(dev->regmap[0], 0xf5, &tmp);
+	/* Check if firmware is already running */
+	ret = regmap_read(dev->regmap[0], 0xf5, &uitmp);
 	if (ret)
 		goto err;
 
-	if (!(tmp & 0x1)) {
-		dev_info(&client->dev, "firmware already running\n");
-		dev->warm = true;
-		return 0;
-	}
+	if (!(uitmp & 0x01))
+		goto warm;
 
-	/* request the firmware, this will block and timeout */
-	ret = request_firmware(&fw, fw_file, &client->dev);
+	/* Request the firmware, this will block and timeout */
+	ret = request_firmware(&fw, name, &client->dev);
 	if (ret) {
-		dev_err(&client->dev, "firmare file '%s' not found\n", fw_file);
-		goto err_request_firmware;
+		dev_err(&client->dev, "firmare file '%s' not found\n", name);
+		goto err;
 	}
 
-	dev_info(&client->dev, "downloading firmware from file '%s'\n",
-		 fw_file);
+	dev_info(&client->dev, "downloading firmware from file '%s'\n", name);
 
 	ret = regmap_write(dev->regmap[0], 0xf5, 0x03);
 	if (ret)
-		goto err;
-
-	for (remaining = fw->size; remaining > 0;
-			remaining -= (dev->i2c_wr_max - 1)) {
-		len = remaining;
-		if (len > (dev->i2c_wr_max - 1))
-			len = dev->i2c_wr_max - 1;
+		goto err_release_firmware;
 
+	for (remain = fw->size; remain > 0; remain -= (dev->i2c_wr_max - 1)) {
+		len = min(dev->i2c_wr_max - 1, remain);
 		ret = regmap_bulk_write(dev->regmap[0], 0xf6,
-					&fw->data[fw->size - remaining], len);
+					&fw->data[fw->size - remain], len);
 		if (ret) {
-			dev_err(&client->dev, "firmware download failed=%d\n",
+			dev_err(&client->dev, "firmware download failed %d\n",
 				ret);
-			goto err;
+			goto err_release_firmware;
 		}
 	}
 
-	/* parity check of firmware */
-	ret = regmap_read(dev->regmap[0], 0xf8, &tmp);
-	if (ret) {
-		dev_err(&client->dev,
-				"parity reg read failed=%d\n", ret);
+	release_firmware(fw);
+
+	/* Parity check of firmware */
+	ret = regmap_read(dev->regmap[0], 0xf8, &uitmp);
+	if (ret)
 		goto err;
-	}
-	if (tmp & 0x10) {
-		dev_err(&client->dev,
-				"firmware parity check failed=0x%x\n", tmp);
+
+	if (uitmp & 0x10) {
+		dev_err(&client->dev, "firmware parity check failed\n");
+		ret = -EINVAL;
 		goto err;
 	}
-	dev_err(&client->dev, "firmware parity check succeeded=0x%x\n", tmp);
 
 	ret = regmap_write(dev->regmap[0], 0xf5, 0x00);
 	if (ret)
 		goto err;
+warm:
+	/* TS config */
+	ret = regmap_write(dev->regmap[2], 0x09, 0x08);
+	if (ret)
+		goto err;
+	ret = regmap_write(dev->regmap[2], 0x08, 0x1d);
+	if (ret)
+		goto err;
 
-	release_firmware(fw);
-	fw = NULL;
-
-	/* warm state */
-	dev->warm = true;
+	dev->active = true;
 
 	return 0;
-
-err:
+err_release_firmware:
 	release_firmware(fw);
-err_request_firmware:
+err:
 	dev_dbg(&client->dev, "failed=%d\n", ret);
 	return ret;
 }
@@ -330,20 +394,20 @@ static int mn88473_sleep(struct dvb_frontend *fe)
 
 	dev_dbg(&client->dev, "\n");
 
+	dev->active = false;
+
 	ret = regmap_write(dev->regmap[2], 0x05, 0x3e);
 	if (ret)
 		goto err;
 
-	dev->delivery_system = SYS_UNDEFINED;
-
 	return 0;
 err:
 	dev_dbg(&client->dev, "failed=%d\n", ret);
 	return ret;
 }
 
-static struct dvb_frontend_ops mn88473_ops = {
-	.delsys = {SYS_DVBT, SYS_DVBT2, SYS_DVBC_ANNEX_AC},
+static const struct dvb_frontend_ops mn88473_ops = {
+	.delsys = {SYS_DVBT, SYS_DVBT2, SYS_DVBC_ANNEX_A},
 	.info = {
 		.name = "Panasonic MN88473",
 		.symbol_rate_min = 1000000,
@@ -365,8 +429,7 @@ static struct dvb_frontend_ops mn88473_ops = {
 			FE_CAN_GUARD_INTERVAL_AUTO     |
 			FE_CAN_HIERARCHY_AUTO          |
 			FE_CAN_MUTE_TS                 |
-			FE_CAN_2G_MODULATION           |
-			FE_CAN_MULTISTREAM
+			FE_CAN_2G_MODULATION
 	},
 
 	.get_tune_settings = mn88473_get_tune_settings,
@@ -385,7 +448,7 @@ static int mn88473_probe(struct i2c_client *client,
 	struct mn88473_config *config = client->dev.platform_data;
 	struct mn88473_dev *dev;
 	int ret;
-	unsigned int utmp;
+	unsigned int uitmp;
 	static const struct regmap_config regmap_config = {
 		.reg_bits = 8,
 		.val_bits = 8,
@@ -393,7 +456,7 @@ static int mn88473_probe(struct i2c_client *client,
 
 	dev_dbg(&client->dev, "\n");
 
-	/* Caller really need to provide pointer for frontend we create. */
+	/* Caller really need to provide pointer for frontend we create */
 	if (config->fe == NULL) {
 		dev_err(&client->dev, "frontend pointer not defined\n");
 		ret = -EINVAL;
@@ -406,11 +469,15 @@ static int mn88473_probe(struct i2c_client *client,
 		goto err;
 	}
 
-	dev->i2c_wr_max = config->i2c_wr_max;
-	if (!config->xtal)
-		dev->xtal = 25000000;
+	if (config->i2c_wr_max)
+		dev->i2c_wr_max = config->i2c_wr_max;
 	else
-		dev->xtal = config->xtal;
+		dev->i2c_wr_max = ~0;
+
+	if (config->xtal)
+		dev->clk = config->xtal;
+	else
+		dev->clk = 25000000;
 	dev->client[0] = client;
 	dev->regmap[0] = regmap_init_i2c(dev->client[0], &regmap_config);
 	if (IS_ERR(dev->regmap[0])) {
@@ -418,15 +485,25 @@ static int mn88473_probe(struct i2c_client *client,
 		goto err_kfree;
 	}
 
-	/* check demod answers to I2C */
-	ret = regmap_read(dev->regmap[0], 0x00, &utmp);
+	/* Check demod answers with correct chip id */
+	ret = regmap_read(dev->regmap[0], 0xff, &uitmp);
 	if (ret)
 		goto err_regmap_0_regmap_exit;
 
+	dev_dbg(&client->dev, "chip id=%02x\n", uitmp);
+
+	if (uitmp != 0x03) {
+		ret = -ENODEV;
+		goto err_regmap_0_regmap_exit;
+	}
+
 	/*
-	 * Chip has three I2C addresses for different register pages. Used
+	 * Chip has three I2C addresses for different register banks. Used
 	 * addresses are 0x18, 0x1a and 0x1c. We register two dummy clients,
-	 * 0x1a and 0x1c, in order to get own I2C client for each register page.
+	 * 0x1a and 0x1c, in order to get own I2C client for each register bank.
+	 *
+	 * Also, register bank 2 do not support sequential I/O. Only single
+	 * register write or read is allowed to that bank.
 	 */
 	dev->client[1] = i2c_new_dummy(client->adapter, 0x1a);
 	if (dev->client[1] == NULL) {
@@ -456,13 +533,19 @@ static int mn88473_probe(struct i2c_client *client,
 	}
 	i2c_set_clientdata(dev->client[2], dev);
 
-	/* create dvb_frontend */
-	memcpy(&dev->fe.ops, &mn88473_ops, sizeof(struct dvb_frontend_ops));
-	dev->fe.demodulator_priv = client;
-	*config->fe = &dev->fe;
+	/* Sleep because chip is active by default */
+	ret = regmap_write(dev->regmap[2], 0x05, 0x3e);
+	if (ret)
+		goto err_client_2_i2c_unregister_device;
+
+	/* Create dvb frontend */
+	memcpy(&dev->frontend.ops, &mn88473_ops, sizeof(dev->frontend.ops));
+	dev->frontend.demodulator_priv = client;
+	*config->fe = &dev->frontend;
 	i2c_set_clientdata(client, dev);
 
-	dev_info(&dev->client[0]->dev, "Panasonic MN88473 successfully attached\n");
+	dev_info(&client->dev, "Panasonic MN88473 successfully identified\n");
+
 	return 0;
 
 err_client_2_i2c_unregister_device:
@@ -507,7 +590,8 @@ MODULE_DEVICE_TABLE(i2c, mn88473_id_table);
 
 static struct i2c_driver mn88473_driver = {
 	.driver = {
-		.name	= "mn88473",
+		.name	             = "mn88473",
+		.suppress_bind_attrs = true,
 	},
 	.probe		= mn88473_probe,
 	.remove		= mn88473_remove,
diff --git a/drivers/media/dvb-frontends/mn88473.h b/drivers/media/dvb-frontends/mn88473.h
index c717ebed0e03..2aa5181f3033 100644
--- a/drivers/media/dvb-frontends/mn88473.h
+++ b/drivers/media/dvb-frontends/mn88473.h
@@ -22,10 +22,16 @@
 struct mn88473_config {
 	/*
 	 * Max num of bytes given I2C adapter could write at once.
-	 * Default: none
+	 * Default: unlimited
 	 */
 	u16 i2c_wr_max;
 
+	/*
+	 * Xtal frequency Hz.
+	 * Default: 25000000
+	 */
+	u32 xtal;
+
 
 	/* Everything after that is returned by the driver. */
 
@@ -33,12 +39,6 @@ struct mn88473_config {
 	 * DVB frontend.
 	 */
 	struct dvb_frontend **fe;
-
-	/*
-	 * Xtal frequency.
-	 * Hz
-	 */
-	u32 xtal;
 };
 
 #endif
diff --git a/drivers/staging/media/mn88473/mn88473_priv.h b/drivers/media/dvb-frontends/mn88473_priv.h
index 54beb4241ccf..e6c65893e451 100644
--- a/drivers/staging/media/mn88473/mn88473_priv.h
+++ b/drivers/media/dvb-frontends/mn88473_priv.h
@@ -27,11 +27,10 @@
 struct mn88473_dev {
 	struct i2c_client *client[3];
 	struct regmap *regmap[3];
-	struct dvb_frontend fe;
+	struct dvb_frontend frontend;
 	u16 i2c_wr_max;
-	enum fe_delivery_system delivery_system;
-	bool warm; /* FW running */
-	u32 xtal;
+	bool active;
+	u32 clk;
 };
 
 #endif
diff --git a/drivers/media/dvb-frontends/mt312.c b/drivers/media/dvb-frontends/mt312.c
index c36e6764eead..fc08429c99b7 100644
--- a/drivers/media/dvb-frontends/mt312.c
+++ b/drivers/media/dvb-frontends/mt312.c
@@ -647,9 +647,9 @@ static int mt312_set_frontend(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int mt312_get_frontend(struct dvb_frontend *fe)
+static int mt312_get_frontend(struct dvb_frontend *fe,
+			      struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct mt312_state *state = fe->demodulator_priv;
 	int ret;
 
diff --git a/drivers/media/dvb-frontends/mt352.c b/drivers/media/dvb-frontends/mt352.c
index 123bb2f8e4b6..c0bb6328956b 100644
--- a/drivers/media/dvb-frontends/mt352.c
+++ b/drivers/media/dvb-frontends/mt352.c
@@ -311,9 +311,9 @@ static int mt352_set_parameters(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int mt352_get_parameters(struct dvb_frontend* fe)
+static int mt352_get_parameters(struct dvb_frontend* fe,
+				struct dtv_frontend_properties *op)
 {
-	struct dtv_frontend_properties *op = &fe->dtv_property_cache;
 	struct mt352_state* state = fe->demodulator_priv;
 	u16 tps;
 	u16 div;
diff --git a/drivers/media/dvb-frontends/or51132.c b/drivers/media/dvb-frontends/or51132.c
index 35b1053b3640..a165af990672 100644
--- a/drivers/media/dvb-frontends/or51132.c
+++ b/drivers/media/dvb-frontends/or51132.c
@@ -375,9 +375,9 @@ static int or51132_set_parameters(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int or51132_get_parameters(struct dvb_frontend* fe)
+static int or51132_get_parameters(struct dvb_frontend* fe,
+				  struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct or51132_state* state = fe->demodulator_priv;
 	int status;
 	int retry = 1;
diff --git a/drivers/media/dvb-frontends/rtl2830.c b/drivers/media/dvb-frontends/rtl2830.c
index b792f305cf15..3f96429af0e5 100644
--- a/drivers/media/dvb-frontends/rtl2830.c
+++ b/drivers/media/dvb-frontends/rtl2830.c
@@ -279,11 +279,11 @@ err:
 	return ret;
 }
 
-static int rtl2830_get_frontend(struct dvb_frontend *fe)
+static int rtl2830_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *c)
 {
 	struct i2c_client *client = fe->demodulator_priv;
 	struct rtl2830_dev *dev = i2c_get_clientdata(client);
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret;
 	u8 buf[3];
 
@@ -900,6 +900,9 @@ static int rtl2830_remove(struct i2c_client *client)
 
 	dev_dbg(&client->dev, "\n");
 
+	/* stop statistics polling */
+	cancel_delayed_work_sync(&dev->stat_work);
+
 	i2c_del_mux_adapter(dev->adapter);
 	regmap_exit(dev->regmap);
 	kfree(dev);
diff --git a/drivers/media/dvb-frontends/rtl2832.c b/drivers/media/dvb-frontends/rtl2832.c
index 10f2119935da..7c96f7679669 100644
--- a/drivers/media/dvb-frontends/rtl2832.c
+++ b/drivers/media/dvb-frontends/rtl2832.c
@@ -347,6 +347,10 @@ static int rtl2832_init(struct dvb_frontend *fe)
 
 	dev_dbg(&client->dev, "\n");
 
+	ret = rtl2832_wr_demod_reg(dev, DVBT_SOFT_RST, 0x0);
+	if (ret)
+		goto err;
+
 	for (i = 0; i < ARRAY_SIZE(rtl2832_initial_regs); i++) {
 		ret = rtl2832_wr_demod_reg(dev, rtl2832_initial_regs[i].reg,
 			rtl2832_initial_regs[i].value);
@@ -404,8 +408,6 @@ static int rtl2832_init(struct dvb_frontend *fe)
 	c->post_bit_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
 	c->post_bit_count.len = 1;
 	c->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
-	/* start statistics polling */
-	schedule_delayed_work(&dev->stat_work, msecs_to_jiffies(2000));
 	dev->sleeping = false;
 
 	return 0;
@@ -423,8 +425,6 @@ static int rtl2832_sleep(struct dvb_frontend *fe)
 	dev_dbg(&client->dev, "\n");
 
 	dev->sleeping = true;
-	/* stop statistics polling */
-	cancel_delayed_work_sync(&dev->stat_work);
 	dev->fe_status = 0;
 
 	ret = rtl2832_wr_demod_reg(dev, DVBT_SOFT_RST, 0x1);
@@ -491,11 +491,6 @@ static int rtl2832_set_frontend(struct dvb_frontend *fe)
 	if (fe->ops.tuner_ops.set_params)
 		fe->ops.tuner_ops.set_params(fe);
 
-	/* PIP mode related */
-	ret = rtl2832_bulk_write(client, 0x192, "\x00\x0f\xff", 3);
-	if (ret)
-		goto err;
-
 	/* If the frontend has get_if_frequency(), use it */
 	if (fe->ops.tuner_ops.get_if_frequency) {
 		u32 if_freq;
@@ -575,11 +570,11 @@ err:
 	return ret;
 }
 
-static int rtl2832_get_frontend(struct dvb_frontend *fe)
+static int rtl2832_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *c)
 {
 	struct rtl2832_dev *dev = fe->demodulator_priv;
 	struct i2c_client *client = dev->client;
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret;
 	u8 buf[3];
 
@@ -692,8 +687,11 @@ static int rtl2832_read_status(struct dvb_frontend *fe, enum fe_status *status)
 {
 	struct rtl2832_dev *dev = fe->demodulator_priv;
 	struct i2c_client *client = dev->client;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret;
 	u32 uninitialized_var(tmp);
+	u8 u8tmp, buf[2];
+	u16 u16tmp;
 
 	dev_dbg(&client->dev, "\n");
 
@@ -714,45 +712,6 @@ static int rtl2832_read_status(struct dvb_frontend *fe, enum fe_status *status)
 	}
 
 	dev->fe_status = *status;
-	return 0;
-err:
-	dev_dbg(&client->dev, "failed=%d\n", ret);
-	return ret;
-}
-
-static int rtl2832_read_snr(struct dvb_frontend *fe, u16 *snr)
-{
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
-
-	/* report SNR in resolution of 0.1 dB */
-	if (c->cnr.stat[0].scale == FE_SCALE_DECIBEL)
-		*snr = div_s64(c->cnr.stat[0].svalue, 100);
-	else
-		*snr = 0;
-
-	return 0;
-}
-
-static int rtl2832_read_ber(struct dvb_frontend *fe, u32 *ber)
-{
-	struct rtl2832_dev *dev = fe->demodulator_priv;
-
-	*ber = (dev->post_bit_error - dev->post_bit_error_prev);
-	dev->post_bit_error_prev = dev->post_bit_error;
-
-	return 0;
-}
-
-static void rtl2832_stat_work(struct work_struct *work)
-{
-	struct rtl2832_dev *dev = container_of(work, struct rtl2832_dev, stat_work.work);
-	struct i2c_client *client = dev->client;
-	struct dtv_frontend_properties *c = &dev->fe.dtv_property_cache;
-	int ret, tmp;
-	u8 u8tmp, buf[2];
-	u16 u16tmp;
-
-	dev_dbg(&client->dev, "\n");
 
 	/* signal strength */
 	if (dev->fe_status & FE_HAS_SIGNAL) {
@@ -789,11 +748,11 @@ static void rtl2832_stat_work(struct work_struct *work)
 
 		constellation = (u8tmp >> 2) & 0x03; /* [3:2] */
 		if (constellation > CONSTELLATION_NUM - 1)
-			goto err_schedule_delayed_work;
+			goto err;
 
 		hierarchy = (u8tmp >> 4) & 0x07; /* [6:4] */
 		if (hierarchy > HIERARCHY_NUM - 1)
-			goto err_schedule_delayed_work;
+			goto err;
 
 		ret = rtl2832_bulk_read(client, 0x40c, buf, 2);
 		if (ret)
@@ -835,11 +794,33 @@ static void rtl2832_stat_work(struct work_struct *work)
 		c->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
 	}
 
-err_schedule_delayed_work:
-	schedule_delayed_work(&dev->stat_work, msecs_to_jiffies(2000));
-	return;
+	return 0;
 err:
 	dev_dbg(&client->dev, "failed=%d\n", ret);
+	return ret;
+}
+
+static int rtl2832_read_snr(struct dvb_frontend *fe, u16 *snr)
+{
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+
+	/* report SNR in resolution of 0.1 dB */
+	if (c->cnr.stat[0].scale == FE_SCALE_DECIBEL)
+		*snr = div_s64(c->cnr.stat[0].svalue, 100);
+	else
+		*snr = 0;
+
+	return 0;
+}
+
+static int rtl2832_read_ber(struct dvb_frontend *fe, u32 *ber)
+{
+	struct rtl2832_dev *dev = fe->demodulator_priv;
+
+	*ber = (dev->post_bit_error - dev->post_bit_error_prev);
+	dev->post_bit_error_prev = dev->post_bit_error;
+
+	return 0;
 }
 
 /*
@@ -1081,37 +1062,46 @@ static struct i2c_adapter *rtl2832_get_i2c_adapter(struct i2c_client *client)
 	return dev->i2c_adapter_tuner;
 }
 
-static int rtl2832_enable_slave_ts(struct i2c_client *client)
+static int rtl2832_slave_ts_ctrl(struct i2c_client *client, bool enable)
 {
 	struct rtl2832_dev *dev = i2c_get_clientdata(client);
 	int ret;
 
-	dev_dbg(&client->dev, "\n");
-
-	ret = rtl2832_bulk_write(client, 0x10c, "\x5f\xff", 2);
-	if (ret)
-		goto err;
-
-	ret = rtl2832_wr_demod_reg(dev, DVBT_PIP_ON, 0x1);
-	if (ret)
-		goto err;
+	dev_dbg(&client->dev, "enable=%d\n", enable);
 
-	ret = rtl2832_bulk_write(client, 0x0bc, "\x18", 1);
-	if (ret)
-		goto err;
-
-	ret = rtl2832_bulk_write(client, 0x192, "\x7f\xf7\xff", 3);
-	if (ret)
-		goto err;
-
-	/* soft reset */
-	ret = rtl2832_wr_demod_reg(dev, DVBT_SOFT_RST, 0x1);
-	if (ret)
-		goto err;
-
-	ret = rtl2832_wr_demod_reg(dev, DVBT_SOFT_RST, 0x0);
-	if (ret)
-		goto err;
+	if (enable) {
+		ret = rtl2832_wr_demod_reg(dev, DVBT_SOFT_RST, 0x0);
+		if (ret)
+			goto err;
+		ret = rtl2832_bulk_write(client, 0x10c, "\x5f\xff", 2);
+		if (ret)
+			goto err;
+		ret = rtl2832_wr_demod_reg(dev, DVBT_PIP_ON, 0x1);
+		if (ret)
+			goto err;
+		ret = rtl2832_bulk_write(client, 0x0bc, "\x18", 1);
+		if (ret)
+			goto err;
+		ret = rtl2832_bulk_write(client, 0x192, "\x7f\xf7\xff", 3);
+		if (ret)
+			goto err;
+	} else {
+		ret = rtl2832_bulk_write(client, 0x192, "\x00\x0f\xff", 3);
+		if (ret)
+			goto err;
+		ret = rtl2832_bulk_write(client, 0x0bc, "\x08", 1);
+		if (ret)
+			goto err;
+		ret = rtl2832_wr_demod_reg(dev, DVBT_PIP_ON, 0x0);
+		if (ret)
+			goto err;
+		ret = rtl2832_bulk_write(client, 0x10c, "\x00\x00", 2);
+		if (ret)
+			goto err;
+		ret = rtl2832_wr_demod_reg(dev, DVBT_SOFT_RST, 0x1);
+		if (ret)
+			goto err;
+	}
 
 	return 0;
 err:
@@ -1227,7 +1217,6 @@ static int rtl2832_probe(struct i2c_client *client,
 	dev->pdata = client->dev.platform_data;
 	dev->sleeping = true;
 	INIT_DELAYED_WORK(&dev->i2c_gate_work, rtl2832_i2c_gate_work);
-	INIT_DELAYED_WORK(&dev->stat_work, rtl2832_stat_work);
 	/* create regmap */
 	mutex_init(&dev->regmap_mutex);
 	dev->regmap_config.reg_bits =  8,
@@ -1267,7 +1256,7 @@ static int rtl2832_probe(struct i2c_client *client,
 	/* setup callbacks */
 	pdata->get_dvb_frontend = rtl2832_get_dvb_frontend;
 	pdata->get_i2c_adapter = rtl2832_get_i2c_adapter;
-	pdata->enable_slave_ts = rtl2832_enable_slave_ts;
+	pdata->slave_ts_ctrl = rtl2832_slave_ts_ctrl;
 	pdata->pid_filter = rtl2832_pid_filter;
 	pdata->pid_filter_ctrl = rtl2832_pid_filter_ctrl;
 	pdata->bulk_read = rtl2832_bulk_read;
diff --git a/drivers/media/dvb-frontends/rtl2832.h b/drivers/media/dvb-frontends/rtl2832.h
index c29a4c2bf71a..6390af64cf45 100644
--- a/drivers/media/dvb-frontends/rtl2832.h
+++ b/drivers/media/dvb-frontends/rtl2832.h
@@ -31,7 +31,7 @@
  * @tuner: Used tuner model.
  * @get_dvb_frontend: Get DVB frontend.
  * @get_i2c_adapter: Get I2C adapter.
- * @enable_slave_ts: Enable slave TS IF.
+ * @slave_ts_ctrl: Control slave TS interface.
  * @pid_filter: Set PID to PID filter.
  * @pid_filter_ctrl: Control PID filter.
  */
@@ -53,7 +53,7 @@ struct rtl2832_platform_data {
 
 	struct dvb_frontend* (*get_dvb_frontend)(struct i2c_client *);
 	struct i2c_adapter* (*get_i2c_adapter)(struct i2c_client *);
-	int (*enable_slave_ts)(struct i2c_client *);
+	int (*slave_ts_ctrl)(struct i2c_client *, bool);
 	int (*pid_filter)(struct dvb_frontend *, u8, u16, int);
 	int (*pid_filter_ctrl)(struct dvb_frontend *, int);
 /* private: Register access for SDR module use only */
diff --git a/drivers/media/dvb-frontends/rtl2832_priv.h b/drivers/media/dvb-frontends/rtl2832_priv.h
index 5dcd3a41d23f..6b875f462f8b 100644
--- a/drivers/media/dvb-frontends/rtl2832_priv.h
+++ b/drivers/media/dvb-frontends/rtl2832_priv.h
@@ -38,7 +38,6 @@ struct rtl2832_dev {
 	struct regmap *regmap;
 	struct i2c_adapter *i2c_adapter_tuner;
 	struct dvb_frontend fe;
-	struct delayed_work stat_work;
 	enum fe_status fe_status;
 	u64 post_bit_error_prev; /* for old DVBv3 read_ber() calculation */
 	u64 post_bit_error;
diff --git a/drivers/media/dvb-frontends/s5h1409.c b/drivers/media/dvb-frontends/s5h1409.c
index 10964848a2f1..c68965ad97c0 100644
--- a/drivers/media/dvb-frontends/s5h1409.c
+++ b/drivers/media/dvb-frontends/s5h1409.c
@@ -925,9 +925,9 @@ static int s5h1409_read_ber(struct dvb_frontend *fe, u32 *ber)
 	return s5h1409_read_ucblocks(fe, ber);
 }
 
-static int s5h1409_get_frontend(struct dvb_frontend *fe)
+static int s5h1409_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct s5h1409_state *state = fe->demodulator_priv;
 
 	p->frequency = state->current_frequency;
diff --git a/drivers/media/dvb-frontends/s5h1411.c b/drivers/media/dvb-frontends/s5h1411.c
index 9afc3f42290e..90f86e82b087 100644
--- a/drivers/media/dvb-frontends/s5h1411.c
+++ b/drivers/media/dvb-frontends/s5h1411.c
@@ -840,9 +840,9 @@ static int s5h1411_read_ber(struct dvb_frontend *fe, u32 *ber)
 	return s5h1411_read_ucblocks(fe, ber);
 }
 
-static int s5h1411_get_frontend(struct dvb_frontend *fe)
+static int s5h1411_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct s5h1411_state *state = fe->demodulator_priv;
 
 	p->frequency = state->current_frequency;
diff --git a/drivers/media/dvb-frontends/s5h1420.c b/drivers/media/dvb-frontends/s5h1420.c
index 9c22a4c70d87..d7d0b7d57ad7 100644
--- a/drivers/media/dvb-frontends/s5h1420.c
+++ b/drivers/media/dvb-frontends/s5h1420.c
@@ -756,9 +756,9 @@ static int s5h1420_set_frontend(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int s5h1420_get_frontend(struct dvb_frontend* fe)
+static int s5h1420_get_frontend(struct dvb_frontend* fe,
+				struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct s5h1420_state* state = fe->demodulator_priv;
 
 	p->frequency = state->tunedfreq + s5h1420_getfreqoffset(state);
diff --git a/drivers/media/dvb-frontends/s921.c b/drivers/media/dvb-frontends/s921.c
index d6a8fa63040b..b5e3d90eba5e 100644
--- a/drivers/media/dvb-frontends/s921.c
+++ b/drivers/media/dvb-frontends/s921.c
@@ -433,9 +433,9 @@ static int s921_set_frontend(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int s921_get_frontend(struct dvb_frontend *fe)
+static int s921_get_frontend(struct dvb_frontend *fe,
+			     struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct s921_state *state = fe->demodulator_priv;
 
 	/* FIXME: Probably it is possible to get it from regs f1 and f2 */
diff --git a/drivers/media/dvb-frontends/si2165.c b/drivers/media/dvb-frontends/si2165.c
index 2b93241d4bc1..8bf716a8ea58 100644
--- a/drivers/media/dvb-frontends/si2165.c
+++ b/drivers/media/dvb-frontends/si2165.c
@@ -225,22 +225,18 @@ static int si2165_writereg32(struct si2165_state *state, const u16 reg, u32 val)
 static int si2165_writereg_mask8(struct si2165_state *state, const u16 reg,
 				 u8 val, u8 mask)
 {
-	int ret;
-	u8 tmp;
-
 	if (mask != 0xff) {
-		ret = si2165_readreg8(state, reg, &tmp);
+		u8 tmp;
+		int ret = si2165_readreg8(state, reg, &tmp);
+
 		if (ret < 0)
-			goto err;
+			return ret;
 
 		val &= mask;
 		tmp &= ~mask;
 		val |= tmp;
 	}
-
-	ret = si2165_writereg8(state, reg, val);
-err:
-	return ret;
+	return si2165_writereg8(state, reg, val);
 }
 
 #define REG16(reg, val) { (reg), (val) & 0xff }, { (reg)+1, (val)>>8 & 0xff }
@@ -825,19 +821,19 @@ static int si2165_set_frontend_dvbt(struct dvb_frontend *fe)
 	struct si2165_state *state = fe->demodulator_priv;
 	u32 dvb_rate = 0;
 	u16 bw10k;
+	u32 bw_hz = p->bandwidth_hz;
 
 	dprintk("%s: called\n", __func__);
 
 	if (!state->has_dvbt)
 		return -EINVAL;
 
-	if (p->bandwidth_hz > 0) {
-		dvb_rate = p->bandwidth_hz * 8 / 7;
-		bw10k = p->bandwidth_hz / 10000;
-	} else {
-		dvb_rate = 8 * 8 / 7;
-		bw10k = 800;
-	}
+	/* no bandwidth auto-detection */
+	if (bw_hz == 0)
+		return -EINVAL;
+
+	dvb_rate = bw_hz * 8 / 7;
+	bw10k = bw_hz / 10000;
 
 	ret = si2165_adjust_pll_divl(state, 12);
 	if (ret < 0)
diff --git a/drivers/media/dvb-frontends/stb0899_drv.c b/drivers/media/dvb-frontends/stb0899_drv.c
index 756650f154ab..3d171b0e00c2 100644
--- a/drivers/media/dvb-frontends/stb0899_drv.c
+++ b/drivers/media/dvb-frontends/stb0899_drv.c
@@ -1568,9 +1568,9 @@ static enum dvbfe_search stb0899_search(struct dvb_frontend *fe)
 	return DVBFE_ALGO_SEARCH_ERROR;
 }
 
-static int stb0899_get_frontend(struct dvb_frontend *fe)
+static int stb0899_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct stb0899_state *state		= fe->demodulator_priv;
 	struct stb0899_internal *internal	= &state->internal;
 
diff --git a/drivers/media/dvb-frontends/stb6100.c b/drivers/media/dvb-frontends/stb6100.c
index c978c801c7aa..b9c2511bf019 100644
--- a/drivers/media/dvb-frontends/stb6100.c
+++ b/drivers/media/dvb-frontends/stb6100.c
@@ -346,7 +346,7 @@ static int stb6100_set_frequency(struct dvb_frontend *fe, u32 frequency)
 
 	if (fe->ops.get_frontend) {
 		dprintk(verbose, FE_DEBUG, 1, "Get frontend parameters");
-		fe->ops.get_frontend(fe);
+		fe->ops.get_frontend(fe, p);
 	}
 	srate = p->symbol_rate;
 
diff --git a/drivers/media/dvb-frontends/stv0297.c b/drivers/media/dvb-frontends/stv0297.c
index 75b4d8b25657..81b27b7c0c96 100644
--- a/drivers/media/dvb-frontends/stv0297.c
+++ b/drivers/media/dvb-frontends/stv0297.c
@@ -615,9 +615,9 @@ timeout:
 	return 0;
 }
 
-static int stv0297_get_frontend(struct dvb_frontend *fe)
+static int stv0297_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct stv0297_state *state = fe->demodulator_priv;
 	int reg_00, reg_83;
 
diff --git a/drivers/media/dvb-frontends/stv0299.c b/drivers/media/dvb-frontends/stv0299.c
index a8177807fb65..7927fa925f2f 100644
--- a/drivers/media/dvb-frontends/stv0299.c
+++ b/drivers/media/dvb-frontends/stv0299.c
@@ -422,7 +422,7 @@ static int stv0299_send_legacy_dish_cmd (struct dvb_frontend* fe, unsigned long
 	if (debug_legacy_dish_switch)
 		printk ("%s switch command: 0x%04lx\n",__func__, cmd);
 
-	nexttime = ktime_get_real();
+	nexttime = ktime_get_boottime();
 	if (debug_legacy_dish_switch)
 		tv[0] = nexttime;
 	stv0299_writeregI (state, 0x0c, reg0x0c | 0x50); /* set LNB to 18V */
@@ -431,7 +431,7 @@ static int stv0299_send_legacy_dish_cmd (struct dvb_frontend* fe, unsigned long
 
 	for (i=0; i<9; i++) {
 		if (debug_legacy_dish_switch)
-			tv[i+1] = ktime_get_real();
+			tv[i+1] = ktime_get_boottime();
 		if((cmd & 0x01) != last) {
 			/* set voltage to (last ? 13V : 18V) */
 			stv0299_writeregI (state, 0x0c, reg0x0c | (last ? lv_mask : 0x50));
@@ -602,9 +602,9 @@ static int stv0299_set_frontend(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int stv0299_get_frontend(struct dvb_frontend *fe)
+static int stv0299_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct stv0299_state* state = fe->demodulator_priv;
 	s32 derot_freq;
 	int invval;
diff --git a/drivers/media/dvb-frontends/stv0367.c b/drivers/media/dvb-frontends/stv0367.c
index 44cb73f68af6..abc379aea713 100644
--- a/drivers/media/dvb-frontends/stv0367.c
+++ b/drivers/media/dvb-frontends/stv0367.c
@@ -1938,9 +1938,9 @@ static int stv0367ter_read_ucblocks(struct dvb_frontend *fe, u32 *ucblocks)
 	return 0;
 }
 
-static int stv0367ter_get_frontend(struct dvb_frontend *fe)
+static int stv0367ter_get_frontend(struct dvb_frontend *fe,
+				   struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct stv0367_state *state = fe->demodulator_priv;
 	struct stv0367ter_state *ter_state = state->ter_state;
 	enum stv0367_ter_mode mode;
@@ -3146,9 +3146,9 @@ static int stv0367cab_set_frontend(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int stv0367cab_get_frontend(struct dvb_frontend *fe)
+static int stv0367cab_get_frontend(struct dvb_frontend *fe,
+				   struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct stv0367_state *state = fe->demodulator_priv;
 	struct stv0367cab_state *cab_state = state->cab_state;
 
diff --git a/drivers/media/dvb-frontends/stv0900_core.c b/drivers/media/dvb-frontends/stv0900_core.c
index fe31dd541955..f667005a6661 100644
--- a/drivers/media/dvb-frontends/stv0900_core.c
+++ b/drivers/media/dvb-frontends/stv0900_core.c
@@ -1087,7 +1087,7 @@ u8 stv0900_get_optim_carr_loop(s32 srate, enum fe_stv0900_modcode modcode,
 							s32 pilot, u8 chip_id)
 {
 	u8 aclc_value = 0x29;
-	s32 i;
+	s32 i, cllas2_size;
 	const struct stv0900_car_loop_optim *cls2, *cllqs2, *cllas2;
 
 	dprintk("%s\n", __func__);
@@ -1096,14 +1096,17 @@ u8 stv0900_get_optim_carr_loop(s32 srate, enum fe_stv0900_modcode modcode,
 		cls2 = FE_STV0900_S2CarLoop;
 		cllqs2 = FE_STV0900_S2LowQPCarLoopCut30;
 		cllas2 = FE_STV0900_S2APSKCarLoopCut30;
+		cllas2_size = ARRAY_SIZE(FE_STV0900_S2APSKCarLoopCut30);
 	} else if (chip_id == 0x20) {
 		cls2 = FE_STV0900_S2CarLoopCut20;
 		cllqs2 = FE_STV0900_S2LowQPCarLoopCut20;
 		cllas2 = FE_STV0900_S2APSKCarLoopCut20;
+		cllas2_size = ARRAY_SIZE(FE_STV0900_S2APSKCarLoopCut20);
 	} else {
 		cls2 = FE_STV0900_S2CarLoopCut30;
 		cllqs2 = FE_STV0900_S2LowQPCarLoopCut30;
 		cllas2 = FE_STV0900_S2APSKCarLoopCut30;
+		cllas2_size = ARRAY_SIZE(FE_STV0900_S2APSKCarLoopCut30);
 	}
 
 	if (modcode < STV0900_QPSK_12) {
@@ -1178,7 +1181,7 @@ u8 stv0900_get_optim_carr_loop(s32 srate, enum fe_stv0900_modcode modcode,
 				aclc_value = cls2[i].car_loop_pilots_off_30;
 		}
 
-	} else {
+	} else if (i < cllas2_size) {
 		if (srate <= 3000000)
 			aclc_value = cllas2[i].car_loop_pilots_on_2;
 		else if (srate <= 7000000)
@@ -1859,9 +1862,9 @@ static int stv0900_sleep(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int stv0900_get_frontend(struct dvb_frontend *fe)
+static int stv0900_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct stv0900_state *state = fe->demodulator_priv;
 	struct stv0900_internal *intp = state->internal;
 	enum fe_stv0900_demod_num demod = state->demod;
diff --git a/drivers/media/dvb-frontends/stv6110x.c b/drivers/media/dvb-frontends/stv6110x.c
index e66154e5c1d7..a62c01e454f5 100644
--- a/drivers/media/dvb-frontends/stv6110x.c
+++ b/drivers/media/dvb-frontends/stv6110x.c
@@ -355,7 +355,7 @@ static struct dvb_tuner_ops stv6110x_ops = {
 	.release		= stv6110x_release
 };
 
-static struct stv6110x_devctl stv6110x_ctl = {
+static const struct stv6110x_devctl stv6110x_ctl = {
 	.tuner_init		= stv6110x_init,
 	.tuner_sleep		= stv6110x_sleep,
 	.tuner_set_mode		= stv6110x_set_mode,
@@ -369,7 +369,7 @@ static struct stv6110x_devctl stv6110x_ctl = {
 	.tuner_get_status	= stv6110x_get_status,
 };
 
-struct stv6110x_devctl *stv6110x_attach(struct dvb_frontend *fe,
+const struct stv6110x_devctl *stv6110x_attach(struct dvb_frontend *fe,
 					const struct stv6110x_config *config,
 					struct i2c_adapter *i2c)
 {
diff --git a/drivers/media/dvb-frontends/stv6110x.h b/drivers/media/dvb-frontends/stv6110x.h
index 9f7eb251aec3..696b6e5b9e7b 100644
--- a/drivers/media/dvb-frontends/stv6110x.h
+++ b/drivers/media/dvb-frontends/stv6110x.h
@@ -55,12 +55,12 @@ struct stv6110x_devctl {
 
 #if IS_REACHABLE(CONFIG_DVB_STV6110x)
 
-extern struct stv6110x_devctl *stv6110x_attach(struct dvb_frontend *fe,
+extern const struct stv6110x_devctl *stv6110x_attach(struct dvb_frontend *fe,
 					       const struct stv6110x_config *config,
 					       struct i2c_adapter *i2c);
 
 #else
-static inline struct stv6110x_devctl *stv6110x_attach(struct dvb_frontend *fe,
+static inline const struct stv6110x_devctl *stv6110x_attach(struct dvb_frontend *fe,
 						      const struct stv6110x_config *config,
 						      struct i2c_adapter *i2c)
 {
diff --git a/drivers/media/dvb-frontends/stv6110x_priv.h b/drivers/media/dvb-frontends/stv6110x_priv.h
index 0ec936a660a7..a993aba27b7e 100644
--- a/drivers/media/dvb-frontends/stv6110x_priv.h
+++ b/drivers/media/dvb-frontends/stv6110x_priv.h
@@ -70,7 +70,7 @@ struct stv6110x_state {
 	const struct stv6110x_config	*config;
 	u8 				regs[8];
 
-	struct stv6110x_devctl		*devctl;
+	const struct stv6110x_devctl	*devctl;
 };
 
 #endif /* __STV6110x_PRIV_H */
diff --git a/drivers/media/dvb-frontends/tc90522.c b/drivers/media/dvb-frontends/tc90522.c
index 456cdc7fb1e7..31cd32532387 100644
--- a/drivers/media/dvb-frontends/tc90522.c
+++ b/drivers/media/dvb-frontends/tc90522.c
@@ -201,10 +201,10 @@ static const enum fe_code_rate fec_conv_sat[] = {
 	FEC_2_3, /* for 8PSK. (trellis code) */
 };
 
-static int tc90522s_get_frontend(struct dvb_frontend *fe)
+static int tc90522s_get_frontend(struct dvb_frontend *fe,
+				 struct dtv_frontend_properties *c)
 {
 	struct tc90522_state *state;
-	struct dtv_frontend_properties *c;
 	struct dtv_fe_stats *stats;
 	int ret, i;
 	int layers;
@@ -212,7 +212,6 @@ static int tc90522s_get_frontend(struct dvb_frontend *fe)
 	u32 cndat;
 
 	state = fe->demodulator_priv;
-	c = &fe->dtv_property_cache;
 	c->delivery_system = SYS_ISDBS;
 	c->symbol_rate = 28860000;
 
@@ -337,10 +336,10 @@ static const enum fe_modulation mod_conv[] = {
 	DQPSK, QPSK, QAM_16, QAM_64, 0, 0, 0, 0
 };
 
-static int tc90522t_get_frontend(struct dvb_frontend *fe)
+static int tc90522t_get_frontend(struct dvb_frontend *fe,
+				 struct dtv_frontend_properties *c)
 {
 	struct tc90522_state *state;
-	struct dtv_frontend_properties *c;
 	struct dtv_fe_stats *stats;
 	int ret, i;
 	int layers;
@@ -348,7 +347,6 @@ static int tc90522t_get_frontend(struct dvb_frontend *fe)
 	u32 cndat;
 
 	state = fe->demodulator_priv;
-	c = &fe->dtv_property_cache;
 	c->delivery_system = SYS_ISDBT;
 	c->bandwidth_hz = 6000000;
 	mode = 1;
diff --git a/drivers/media/dvb-frontends/tda10021.c b/drivers/media/dvb-frontends/tda10021.c
index a684424e665a..806c56691ca5 100644
--- a/drivers/media/dvb-frontends/tda10021.c
+++ b/drivers/media/dvb-frontends/tda10021.c
@@ -387,9 +387,9 @@ static int tda10021_read_ucblocks(struct dvb_frontend* fe, u32* ucblocks)
 	return 0;
 }
 
-static int tda10021_get_frontend(struct dvb_frontend *fe)
+static int tda10021_get_frontend(struct dvb_frontend *fe,
+				 struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct tda10021_state* state = fe->demodulator_priv;
 	int sync;
 	s8 afc = 0;
diff --git a/drivers/media/dvb-frontends/tda10023.c b/drivers/media/dvb-frontends/tda10023.c
index 44a55656093f..3b8c7e499d0d 100644
--- a/drivers/media/dvb-frontends/tda10023.c
+++ b/drivers/media/dvb-frontends/tda10023.c
@@ -457,9 +457,9 @@ static int tda10023_read_ucblocks(struct dvb_frontend* fe, u32* ucblocks)
 	return 0;
 }
 
-static int tda10023_get_frontend(struct dvb_frontend *fe)
+static int tda10023_get_frontend(struct dvb_frontend *fe,
+				 struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct tda10023_state* state = fe->demodulator_priv;
 	int sync,inv;
 	s8 afc = 0;
diff --git a/drivers/media/dvb-frontends/tda10048.c b/drivers/media/dvb-frontends/tda10048.c
index 8451086c563f..c2bf89d0b0b0 100644
--- a/drivers/media/dvb-frontends/tda10048.c
+++ b/drivers/media/dvb-frontends/tda10048.c
@@ -1028,9 +1028,9 @@ static int tda10048_read_ucblocks(struct dvb_frontend *fe, u32 *ucblocks)
 	return 0;
 }
 
-static int tda10048_get_frontend(struct dvb_frontend *fe)
+static int tda10048_get_frontend(struct dvb_frontend *fe,
+				 struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct tda10048_state *state = fe->demodulator_priv;
 
 	dprintk(1, "%s()\n", __func__);
diff --git a/drivers/media/dvb-frontends/tda1004x.c b/drivers/media/dvb-frontends/tda1004x.c
index c6abeb4fba9d..b89848313fb9 100644
--- a/drivers/media/dvb-frontends/tda1004x.c
+++ b/drivers/media/dvb-frontends/tda1004x.c
@@ -899,9 +899,9 @@ static int tda1004x_set_fe(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int tda1004x_get_fe(struct dvb_frontend *fe)
+static int tda1004x_get_fe(struct dvb_frontend *fe,
+			   struct dtv_frontend_properties *fe_params)
 {
-	struct dtv_frontend_properties *fe_params = &fe->dtv_property_cache;
 	struct tda1004x_state* state = fe->demodulator_priv;
 	int status;
 
diff --git a/drivers/media/dvb-frontends/tda10071.c b/drivers/media/dvb-frontends/tda10071.c
index 119d47596ac8..37ebeef2bbd0 100644
--- a/drivers/media/dvb-frontends/tda10071.c
+++ b/drivers/media/dvb-frontends/tda10071.c
@@ -701,11 +701,11 @@ error:
 	return ret;
 }
 
-static int tda10071_get_frontend(struct dvb_frontend *fe)
+static int tda10071_get_frontend(struct dvb_frontend *fe,
+				 struct dtv_frontend_properties *c)
 {
 	struct tda10071_dev *dev = fe->demodulator_priv;
 	struct i2c_client *client = dev->client;
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret, i;
 	u8 buf[5], tmp;
 
diff --git a/drivers/media/dvb-frontends/tda10086.c b/drivers/media/dvb-frontends/tda10086.c
index 95a33e187f8e..31d0acb54fe8 100644
--- a/drivers/media/dvb-frontends/tda10086.c
+++ b/drivers/media/dvb-frontends/tda10086.c
@@ -459,9 +459,9 @@ static int tda10086_set_frontend(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int tda10086_get_frontend(struct dvb_frontend *fe)
+static int tda10086_get_frontend(struct dvb_frontend *fe,
+				 struct dtv_frontend_properties *fe_params)
 {
-	struct dtv_frontend_properties *fe_params = &fe->dtv_property_cache;
 	struct tda10086_state* state = fe->demodulator_priv;
 	u8 val;
 	int tmp;
diff --git a/drivers/media/dvb-frontends/tda8083.c b/drivers/media/dvb-frontends/tda8083.c
index 796543fa2c8d..9072d6463094 100644
--- a/drivers/media/dvb-frontends/tda8083.c
+++ b/drivers/media/dvb-frontends/tda8083.c
@@ -342,9 +342,9 @@ static int tda8083_set_frontend(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int tda8083_get_frontend(struct dvb_frontend *fe)
+static int tda8083_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct tda8083_state* state = fe->demodulator_priv;
 
 	/*  FIXME: get symbolrate & frequency offset...*/
diff --git a/drivers/media/dvb-frontends/ts2020.c b/drivers/media/dvb-frontends/ts2020.c
index 7979e5d6498b..14b410ffe612 100644
--- a/drivers/media/dvb-frontends/ts2020.c
+++ b/drivers/media/dvb-frontends/ts2020.c
@@ -712,6 +712,10 @@ static int ts2020_remove(struct i2c_client *client)
 
 	dev_dbg(&client->dev, "\n");
 
+	/* stop statistics polling */
+	if (!dev->dont_poll)
+		cancel_delayed_work_sync(&dev->stat_work);
+
 	regmap_exit(dev->regmap);
 	kfree(dev);
 	return 0;
diff --git a/drivers/media/dvb-frontends/ves1820.c b/drivers/media/dvb-frontends/ves1820.c
index aacfdda3e005..b09fe88c40f8 100644
--- a/drivers/media/dvb-frontends/ves1820.c
+++ b/drivers/media/dvb-frontends/ves1820.c
@@ -312,9 +312,9 @@ static int ves1820_read_ucblocks(struct dvb_frontend* fe, u32* ucblocks)
 	return 0;
 }
 
-static int ves1820_get_frontend(struct dvb_frontend *fe)
+static int ves1820_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct ves1820_state* state = fe->demodulator_priv;
 	int sync;
 	s8 afc = 0;
diff --git a/drivers/media/dvb-frontends/ves1x93.c b/drivers/media/dvb-frontends/ves1x93.c
index 526952396422..ed113e216e14 100644
--- a/drivers/media/dvb-frontends/ves1x93.c
+++ b/drivers/media/dvb-frontends/ves1x93.c
@@ -406,9 +406,9 @@ static int ves1x93_set_frontend(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int ves1x93_get_frontend(struct dvb_frontend *fe)
+static int ves1x93_get_frontend(struct dvb_frontend *fe,
+				struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct ves1x93_state* state = fe->demodulator_priv;
 	int afc;
 
diff --git a/drivers/media/dvb-frontends/zl10353.c b/drivers/media/dvb-frontends/zl10353.c
index ef9764a02d4c..1832c2f7695c 100644
--- a/drivers/media/dvb-frontends/zl10353.c
+++ b/drivers/media/dvb-frontends/zl10353.c
@@ -371,9 +371,9 @@ static int zl10353_set_parameters(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int zl10353_get_parameters(struct dvb_frontend *fe)
+static int zl10353_get_parameters(struct dvb_frontend *fe,
+				  struct dtv_frontend_properties *c)
 {
-	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	struct zl10353_state *state = fe->demodulator_priv;
 	int s6, s9;
 	u16 tps;
diff --git a/drivers/media/i2c/adp1653.c b/drivers/media/i2c/adp1653.c
index 7e9cbf757e95..fb7ed730d932 100644
--- a/drivers/media/i2c/adp1653.c
+++ b/drivers/media/i2c/adp1653.c
@@ -497,7 +497,7 @@ static int adp1653_probe(struct i2c_client *client,
 		if (!client->dev.platform_data) {
 			dev_err(&client->dev,
 				"Neither DT not platform data provided\n");
-			return EINVAL;
+			return -EINVAL;
 		}
 		flash->platform_data = client->dev.platform_data;
 	}
diff --git a/drivers/media/i2c/adv7511.c b/drivers/media/i2c/adv7511.c
index 471fd23b5c5c..bd822f032b08 100644
--- a/drivers/media/i2c/adv7511.c
+++ b/drivers/media/i2c/adv7511.c
@@ -103,12 +103,14 @@ struct adv7511_state {
 	u32 ycbcr_enc;
 	u32 quantization;
 	u32 xfer_func;
+	u32 content_type;
 	/* controls */
 	struct v4l2_ctrl *hdmi_mode_ctrl;
 	struct v4l2_ctrl *hotplug_ctrl;
 	struct v4l2_ctrl *rx_sense_ctrl;
 	struct v4l2_ctrl *have_edid0_ctrl;
 	struct v4l2_ctrl *rgb_quantization_range_ctrl;
+	struct v4l2_ctrl *content_type_ctrl;
 	struct i2c_client *i2c_edid;
 	struct i2c_client *i2c_pktmem;
 	struct adv7511_state_edid edid;
@@ -400,6 +402,16 @@ static int adv7511_s_ctrl(struct v4l2_ctrl *ctrl)
 	}
 	if (state->rgb_quantization_range_ctrl == ctrl)
 		return adv7511_set_rgb_quantization_mode(sd, ctrl);
+	if (state->content_type_ctrl == ctrl) {
+		u8 itc, cn;
+
+		state->content_type = ctrl->val;
+		itc = state->content_type != V4L2_DV_IT_CONTENT_TYPE_NO_ITC;
+		cn = itc ? state->content_type : V4L2_DV_IT_CONTENT_TYPE_GRAPHICS;
+		adv7511_wr_and_or(sd, 0x57, 0x7f, itc << 7);
+		adv7511_wr_and_or(sd, 0x59, 0xcf, cn << 4);
+		return 0;
+	}
 
 	return -EINVAL;
 }
@@ -1002,6 +1014,8 @@ static int adv7511_set_fmt(struct v4l2_subdev *sd,
 	u8 y = HDMI_COLORSPACE_RGB;
 	u8 q = HDMI_QUANTIZATION_RANGE_DEFAULT;
 	u8 yq = HDMI_YCC_QUANTIZATION_RANGE_LIMITED;
+	u8 itc = state->content_type != V4L2_DV_IT_CONTENT_TYPE_NO_ITC;
+	u8 cn = itc ? state->content_type : V4L2_DV_IT_CONTENT_TYPE_GRAPHICS;
 
 	if (format->pad != 0)
 		return -EINVAL;
@@ -1115,8 +1129,8 @@ static int adv7511_set_fmt(struct v4l2_subdev *sd,
 	adv7511_wr_and_or(sd, 0x4a, 0xbf, 0);
 	adv7511_wr_and_or(sd, 0x55, 0x9f, y << 5);
 	adv7511_wr_and_or(sd, 0x56, 0x3f, c << 6);
-	adv7511_wr_and_or(sd, 0x57, 0x83, (ec << 4) | (q << 2));
-	adv7511_wr_and_or(sd, 0x59, 0x3f, yq << 6);
+	adv7511_wr_and_or(sd, 0x57, 0x83, (ec << 4) | (q << 2) | (itc << 7));
+	adv7511_wr_and_or(sd, 0x59, 0x0f, (yq << 6) | (cn << 4));
 	adv7511_wr_and_or(sd, 0x4a, 0xff, 1);
 
 	return 0;
@@ -1161,12 +1175,23 @@ static void adv7511_dbg_dump_edid(int lvl, int debug, struct v4l2_subdev *sd, in
 	}
 }
 
+static void adv7511_notify_no_edid(struct v4l2_subdev *sd)
+{
+	struct adv7511_state *state = get_adv7511_state(sd);
+	struct adv7511_edid_detect ed;
+
+	/* We failed to read the EDID, so send an event for this. */
+	ed.present = false;
+	ed.segment = adv7511_rd(sd, 0xc4);
+	v4l2_subdev_notify(sd, ADV7511_EDID_DETECT, (void *)&ed);
+	v4l2_ctrl_s_ctrl(state->have_edid0_ctrl, 0x0);
+}
+
 static void adv7511_edid_handler(struct work_struct *work)
 {
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct adv7511_state *state = container_of(dwork, struct adv7511_state, edid_handler);
 	struct v4l2_subdev *sd = &state->sd;
-	struct adv7511_edid_detect ed;
 
 	v4l2_dbg(1, debug, sd, "%s:\n", __func__);
 
@@ -1191,9 +1216,7 @@ static void adv7511_edid_handler(struct work_struct *work)
 	}
 
 	/* We failed to read the EDID, so send an event for this. */
-	ed.present = false;
-	ed.segment = adv7511_rd(sd, 0xc4);
-	v4l2_subdev_notify(sd, ADV7511_EDID_DETECT, (void *)&ed);
+	adv7511_notify_no_edid(sd);
 	v4l2_dbg(1, debug, sd, "%s: no edid found\n", __func__);
 }
 
@@ -1264,7 +1287,6 @@ static void adv7511_check_monitor_present_status(struct v4l2_subdev *sd)
 	/* update read only ctrls */
 	v4l2_ctrl_s_ctrl(state->hotplug_ctrl, adv7511_have_hotplug(sd) ? 0x1 : 0x0);
 	v4l2_ctrl_s_ctrl(state->rx_sense_ctrl, adv7511_have_rx_sense(sd) ? 0x1 : 0x0);
-	v4l2_ctrl_s_ctrl(state->have_edid0_ctrl, state->edid.segments ? 0x1 : 0x0);
 
 	if ((status & MASK_ADV7511_HPD_DETECT) && ((status & MASK_ADV7511_MSEN_DETECT) || state->edid.segments)) {
 		v4l2_dbg(1, debug, sd, "%s: hotplug and (rx-sense or edid)\n", __func__);
@@ -1294,6 +1316,7 @@ static void adv7511_check_monitor_present_status(struct v4l2_subdev *sd)
 		}
 		adv7511_s_power(sd, false);
 		memset(&state->edid, 0, sizeof(struct adv7511_state_edid));
+		adv7511_notify_no_edid(sd);
 	}
 }
 
@@ -1370,6 +1393,7 @@ static bool adv7511_check_edid_status(struct v4l2_subdev *sd)
 		}
 		/* one more segment read ok */
 		state->edid.segments = segment + 1;
+		v4l2_ctrl_s_ctrl(state->have_edid0_ctrl, 0x1);
 		if (((state->edid.data[0x7e] >> 1) + 1) > state->edid.segments) {
 			/* Request next EDID segment */
 			v4l2_dbg(1, debug, sd, "%s: request segment %d\n", __func__, state->edid.segments);
@@ -1389,7 +1413,6 @@ static bool adv7511_check_edid_status(struct v4l2_subdev *sd)
 		ed.present = true;
 		ed.segment = 0;
 		state->edid_detect_counter++;
-		v4l2_ctrl_s_ctrl(state->have_edid0_ctrl, state->edid.segments ? 0x1 : 0x0);
 		v4l2_subdev_notify(sd, ADV7511_EDID_DETECT, (void *)&ed);
 		return ed.present;
 	}
@@ -1470,6 +1493,10 @@ static int adv7511_probe(struct i2c_client *client, const struct i2c_device_id *
 		v4l2_ctrl_new_std_menu(hdl, &adv7511_ctrl_ops,
 			V4L2_CID_DV_TX_RGB_RANGE, V4L2_DV_RGB_RANGE_FULL,
 			0, V4L2_DV_RGB_RANGE_AUTO);
+	state->content_type_ctrl =
+		v4l2_ctrl_new_std_menu(hdl, &adv7511_ctrl_ops,
+			V4L2_CID_DV_TX_IT_CONTENT_TYPE, V4L2_DV_IT_CONTENT_TYPE_NO_ITC,
+			0, V4L2_DV_IT_CONTENT_TYPE_NO_ITC);
 	sd->ctrl_handler = hdl;
 	if (hdl->error) {
 		err = hdl->error;
diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c
index f8dd7505b529..41a1bfc5eaa7 100644
--- a/drivers/media/i2c/adv7604.c
+++ b/drivers/media/i2c/adv7604.c
@@ -207,71 +207,22 @@ static bool adv76xx_has_afe(struct adv76xx_state *state)
 	return state->info->has_afe;
 }
 
-/* Supported CEA and DMT timings */
-static const struct v4l2_dv_timings adv76xx_timings[] = {
-	V4L2_DV_BT_CEA_720X480P59_94,
-	V4L2_DV_BT_CEA_720X576P50,
-	V4L2_DV_BT_CEA_1280X720P24,
-	V4L2_DV_BT_CEA_1280X720P25,
-	V4L2_DV_BT_CEA_1280X720P50,
-	V4L2_DV_BT_CEA_1280X720P60,
-	V4L2_DV_BT_CEA_1920X1080P24,
-	V4L2_DV_BT_CEA_1920X1080P25,
-	V4L2_DV_BT_CEA_1920X1080P30,
-	V4L2_DV_BT_CEA_1920X1080P50,
-	V4L2_DV_BT_CEA_1920X1080P60,
-
-	/* sorted by DMT ID */
-	V4L2_DV_BT_DMT_640X350P85,
-	V4L2_DV_BT_DMT_640X400P85,
-	V4L2_DV_BT_DMT_720X400P85,
-	V4L2_DV_BT_DMT_640X480P60,
-	V4L2_DV_BT_DMT_640X480P72,
-	V4L2_DV_BT_DMT_640X480P75,
-	V4L2_DV_BT_DMT_640X480P85,
-	V4L2_DV_BT_DMT_800X600P56,
-	V4L2_DV_BT_DMT_800X600P60,
-	V4L2_DV_BT_DMT_800X600P72,
-	V4L2_DV_BT_DMT_800X600P75,
-	V4L2_DV_BT_DMT_800X600P85,
-	V4L2_DV_BT_DMT_848X480P60,
-	V4L2_DV_BT_DMT_1024X768P60,
-	V4L2_DV_BT_DMT_1024X768P70,
-	V4L2_DV_BT_DMT_1024X768P75,
-	V4L2_DV_BT_DMT_1024X768P85,
-	V4L2_DV_BT_DMT_1152X864P75,
-	V4L2_DV_BT_DMT_1280X768P60_RB,
-	V4L2_DV_BT_DMT_1280X768P60,
-	V4L2_DV_BT_DMT_1280X768P75,
-	V4L2_DV_BT_DMT_1280X768P85,
-	V4L2_DV_BT_DMT_1280X800P60_RB,
-	V4L2_DV_BT_DMT_1280X800P60,
-	V4L2_DV_BT_DMT_1280X800P75,
-	V4L2_DV_BT_DMT_1280X800P85,
-	V4L2_DV_BT_DMT_1280X960P60,
-	V4L2_DV_BT_DMT_1280X960P85,
-	V4L2_DV_BT_DMT_1280X1024P60,
-	V4L2_DV_BT_DMT_1280X1024P75,
-	V4L2_DV_BT_DMT_1280X1024P85,
-	V4L2_DV_BT_DMT_1360X768P60,
-	V4L2_DV_BT_DMT_1400X1050P60_RB,
-	V4L2_DV_BT_DMT_1400X1050P60,
-	V4L2_DV_BT_DMT_1400X1050P75,
-	V4L2_DV_BT_DMT_1400X1050P85,
-	V4L2_DV_BT_DMT_1440X900P60_RB,
-	V4L2_DV_BT_DMT_1440X900P60,
-	V4L2_DV_BT_DMT_1600X1200P60,
-	V4L2_DV_BT_DMT_1680X1050P60_RB,
-	V4L2_DV_BT_DMT_1680X1050P60,
-	V4L2_DV_BT_DMT_1792X1344P60,
-	V4L2_DV_BT_DMT_1856X1392P60,
-	V4L2_DV_BT_DMT_1920X1200P60_RB,
-	V4L2_DV_BT_DMT_1366X768P60_RB,
-	V4L2_DV_BT_DMT_1366X768P60,
-	V4L2_DV_BT_DMT_1920X1080P60,
-	{ },
+/* Unsupported timings. This device cannot support 720p30. */
+static const struct v4l2_dv_timings adv76xx_timings_exceptions[] = {
+	V4L2_DV_BT_CEA_1280X720P30,
+	{ }
 };
 
+static bool adv76xx_check_dv_timings(const struct v4l2_dv_timings *t, void *hdl)
+{
+	int i;
+
+	for (i = 0; adv76xx_timings_exceptions[i].bt.width; i++)
+		if (v4l2_match_dv_timings(t, adv76xx_timings_exceptions + i, 0, false))
+			return false;
+	return true;
+}
+
 struct adv76xx_video_standards {
 	struct v4l2_dv_timings timings;
 	u8 vid_std;
@@ -806,6 +757,36 @@ static inline bool is_digital_input(struct v4l2_subdev *sd)
 	       state->selected_input == ADV7604_PAD_HDMI_PORT_D;
 }
 
+static const struct v4l2_dv_timings_cap adv7604_timings_cap_analog = {
+	.type = V4L2_DV_BT_656_1120,
+	/* keep this initialization for compatibility with GCC < 4.4.6 */
+	.reserved = { 0 },
+	V4L2_INIT_BT_TIMINGS(0, 1920, 0, 1200, 25000000, 170000000,
+		V4L2_DV_BT_STD_CEA861 | V4L2_DV_BT_STD_DMT |
+			V4L2_DV_BT_STD_GTF | V4L2_DV_BT_STD_CVT,
+		V4L2_DV_BT_CAP_PROGRESSIVE | V4L2_DV_BT_CAP_REDUCED_BLANKING |
+			V4L2_DV_BT_CAP_CUSTOM)
+};
+
+static const struct v4l2_dv_timings_cap adv76xx_timings_cap_digital = {
+	.type = V4L2_DV_BT_656_1120,
+	/* keep this initialization for compatibility with GCC < 4.4.6 */
+	.reserved = { 0 },
+	V4L2_INIT_BT_TIMINGS(0, 1920, 0, 1200, 25000000, 225000000,
+		V4L2_DV_BT_STD_CEA861 | V4L2_DV_BT_STD_DMT |
+			V4L2_DV_BT_STD_GTF | V4L2_DV_BT_STD_CVT,
+		V4L2_DV_BT_CAP_PROGRESSIVE | V4L2_DV_BT_CAP_REDUCED_BLANKING |
+			V4L2_DV_BT_CAP_CUSTOM)
+};
+
+static inline const struct v4l2_dv_timings_cap *
+adv76xx_get_dv_timings_cap(struct v4l2_subdev *sd)
+{
+	return is_digital_input(sd) ? &adv76xx_timings_cap_digital :
+				      &adv7604_timings_cap_analog;
+}
+
+
 /* ----------------------------------------------------------------------- */
 
 #ifdef CONFIG_VIDEO_ADV_DEBUG
@@ -1216,6 +1197,20 @@ static int adv76xx_s_ctrl(struct v4l2_ctrl *ctrl)
 	return -EINVAL;
 }
 
+static int adv76xx_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct v4l2_subdev *sd =
+		&container_of(ctrl->handler, struct adv76xx_state, hdl)->sd;
+
+	if (ctrl->id == V4L2_CID_DV_RX_IT_CONTENT_TYPE) {
+		ctrl->val = V4L2_DV_IT_CONTENT_TYPE_NO_ITC;
+		if ((io_read(sd, 0x60) & 1) && (infoframe_read(sd, 0x03) & 0x80))
+			ctrl->val = (infoframe_read(sd, 0x05) >> 4) & 3;
+		return 0;
+	}
+	return -EINVAL;
+}
+
 /* ----------------------------------------------------------------------- */
 
 static inline bool no_power(struct v4l2_subdev *sd)
@@ -1330,17 +1325,23 @@ static int stdi2dv_timings(struct v4l2_subdev *sd,
 	u32 pix_clk;
 	int i;
 
-	for (i = 0; adv76xx_timings[i].bt.height; i++) {
-		if (vtotal(&adv76xx_timings[i].bt) != stdi->lcf + 1)
+	for (i = 0; v4l2_dv_timings_presets[i].bt.width; i++) {
+		const struct v4l2_bt_timings *bt = &v4l2_dv_timings_presets[i].bt;
+
+		if (!v4l2_valid_dv_timings(&v4l2_dv_timings_presets[i],
+					   adv76xx_get_dv_timings_cap(sd),
+					   adv76xx_check_dv_timings, NULL))
+			continue;
+		if (vtotal(bt) != stdi->lcf + 1)
 			continue;
-		if (adv76xx_timings[i].bt.vsync != stdi->lcvs)
+		if (bt->vsync != stdi->lcvs)
 			continue;
 
-		pix_clk = hfreq * htotal(&adv76xx_timings[i].bt);
+		pix_clk = hfreq * htotal(bt);
 
-		if ((pix_clk < adv76xx_timings[i].bt.pixelclock + 1000000) &&
-		    (pix_clk > adv76xx_timings[i].bt.pixelclock - 1000000)) {
-			*timings = adv76xx_timings[i];
+		if ((pix_clk < bt->pixelclock + 1000000) &&
+		    (pix_clk > bt->pixelclock - 1000000)) {
+			*timings = v4l2_dv_timings_presets[i];
 			return 0;
 		}
 	}
@@ -1425,15 +1426,11 @@ static int adv76xx_enum_dv_timings(struct v4l2_subdev *sd,
 {
 	struct adv76xx_state *state = to_state(sd);
 
-	if (timings->index >= ARRAY_SIZE(adv76xx_timings) - 1)
-		return -EINVAL;
-
 	if (timings->pad >= state->source_pad)
 		return -EINVAL;
 
-	memset(timings->reserved, 0, sizeof(timings->reserved));
-	timings->timings = adv76xx_timings[timings->index];
-	return 0;
+	return v4l2_enum_dv_timings_cap(timings,
+		adv76xx_get_dv_timings_cap(sd), adv76xx_check_dv_timings, NULL);
 }
 
 static int adv76xx_dv_timings_cap(struct v4l2_subdev *sd,
@@ -1444,29 +1441,7 @@ static int adv76xx_dv_timings_cap(struct v4l2_subdev *sd,
 	if (cap->pad >= state->source_pad)
 		return -EINVAL;
 
-	cap->type = V4L2_DV_BT_656_1120;
-	cap->bt.max_width = 1920;
-	cap->bt.max_height = 1200;
-	cap->bt.min_pixelclock = 25000000;
-
-	switch (cap->pad) {
-	case ADV76XX_PAD_HDMI_PORT_A:
-	case ADV7604_PAD_HDMI_PORT_B:
-	case ADV7604_PAD_HDMI_PORT_C:
-	case ADV7604_PAD_HDMI_PORT_D:
-		cap->bt.max_pixelclock = 225000000;
-		break;
-	case ADV7604_PAD_VGA_RGB:
-	case ADV7604_PAD_VGA_COMP:
-	default:
-		cap->bt.max_pixelclock = 170000000;
-		break;
-	}
-
-	cap->bt.standards = V4L2_DV_BT_STD_CEA861 | V4L2_DV_BT_STD_DMT |
-			 V4L2_DV_BT_STD_GTF | V4L2_DV_BT_STD_CVT;
-	cap->bt.capabilities = V4L2_DV_BT_CAP_PROGRESSIVE |
-		V4L2_DV_BT_CAP_REDUCED_BLANKING | V4L2_DV_BT_CAP_CUSTOM;
+	*cap = *adv76xx_get_dv_timings_cap(sd);
 	return 0;
 }
 
@@ -1475,15 +1450,9 @@ static int adv76xx_dv_timings_cap(struct v4l2_subdev *sd,
 static void adv76xx_fill_optional_dv_timings_fields(struct v4l2_subdev *sd,
 		struct v4l2_dv_timings *timings)
 {
-	int i;
-
-	for (i = 0; adv76xx_timings[i].bt.width; i++) {
-		if (v4l2_match_dv_timings(timings, &adv76xx_timings[i],
-				is_digital_input(sd) ? 250000 : 1000000, false)) {
-			*timings = adv76xx_timings[i];
-			break;
-		}
-	}
+	v4l2_find_dv_timings_cap(timings, adv76xx_get_dv_timings_cap(sd),
+			is_digital_input(sd) ? 250000 : 1000000,
+			adv76xx_check_dv_timings, NULL);
 }
 
 static unsigned int adv7604_read_hdmi_pixelclock(struct v4l2_subdev *sd)
@@ -1651,12 +1620,9 @@ static int adv76xx_s_dv_timings(struct v4l2_subdev *sd,
 
 	bt = &timings->bt;
 
-	if ((is_analog_input(sd) && bt->pixelclock > 170000000) ||
-			(is_digital_input(sd) && bt->pixelclock > 225000000)) {
-		v4l2_dbg(1, debug, sd, "%s: pixelclock out of range %d\n",
-				__func__, (u32)bt->pixelclock);
+	if (!v4l2_valid_dv_timings(timings, adv76xx_get_dv_timings_cap(sd),
+				   adv76xx_check_dv_timings, NULL))
 		return -ERANGE;
-	}
 
 	adv76xx_fill_optional_dv_timings_fields(sd, timings);
 
@@ -1884,6 +1850,26 @@ static int adv76xx_get_format(struct v4l2_subdev *sd,
 	return 0;
 }
 
+static int adv76xx_get_selection(struct v4l2_subdev *sd,
+				 struct v4l2_subdev_pad_config *cfg,
+				 struct v4l2_subdev_selection *sel)
+{
+	struct adv76xx_state *state = to_state(sd);
+
+	if (sel->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+	/* Only CROP, CROP_DEFAULT and CROP_BOUNDS are supported */
+	if (sel->target > V4L2_SEL_TGT_CROP_BOUNDS)
+		return -EINVAL;
+
+	sel->r.left	= 0;
+	sel->r.top	= 0;
+	sel->r.width	= state->timings.bt.width;
+	sel->r.height	= state->timings.bt.height;
+
+	return 0;
+}
+
 static int adv76xx_set_format(struct v4l2_subdev *sd,
 			      struct v4l2_subdev_pad_config *cfg,
 			      struct v4l2_subdev_format *format)
@@ -1960,10 +1946,9 @@ static int adv76xx_isr(struct v4l2_subdev *sd, u32 status, bool *handled)
 	}
 
 	/* tx 5v detect */
-	tx_5v = io_read(sd, 0x70) & info->cable_det_mask;
+	tx_5v = irq_reg_0x70 & info->cable_det_mask;
 	if (tx_5v) {
 		v4l2_dbg(1, debug, sd, "%s: tx_5v: 0x%x\n", __func__, tx_5v);
-		io_write(sd, 0x71, tx_5v);
 		adv76xx_s_detect_tx_5v_ctrl(sd);
 		if (handled)
 			*handled = true;
@@ -2110,7 +2095,8 @@ static int adv76xx_set_edid(struct v4l2_subdev *sd, struct v4l2_edid *edid)
 		rep_write(sd, 0x76, spa_loc & 0xff);
 		rep_write_clr_set(sd, 0x77, 0x40, (spa_loc & 0x100) >> 2);
 	} else {
-		/* FIXME: Where is the SPA location LSB register ? */
+		/* ADV7612 Software Manual Rev. A, p. 15 */
+		rep_write(sd, 0x70, spa_loc & 0xff);
 		rep_write_clr_set(sd, 0x71, 0x01, (spa_loc & 0x100) >> 8);
 	}
 
@@ -2381,6 +2367,7 @@ static int adv76xx_subscribe_event(struct v4l2_subdev *sd,
 
 static const struct v4l2_ctrl_ops adv76xx_ctrl_ops = {
 	.s_ctrl = adv76xx_s_ctrl,
+	.g_volatile_ctrl = adv76xx_g_volatile_ctrl,
 };
 
 static const struct v4l2_subdev_core_ops adv76xx_core_ops = {
@@ -2404,6 +2391,7 @@ static const struct v4l2_subdev_video_ops adv76xx_video_ops = {
 
 static const struct v4l2_subdev_pad_ops adv76xx_pad_ops = {
 	.enum_mbus_code = adv76xx_enum_mbus_code,
+	.get_selection = adv76xx_get_selection,
 	.get_fmt = adv76xx_get_format,
 	.set_fmt = adv76xx_set_format,
 	.get_edid = adv76xx_get_edid,
@@ -2799,6 +2787,7 @@ static int adv76xx_parse_dt(struct adv76xx_state *state)
 	struct device_node *endpoint;
 	struct device_node *np;
 	unsigned int flags;
+	int ret;
 	u32 v;
 
 	np = state->i2c_clients[ADV76XX_PAGE_IO]->dev.of_node;
@@ -2808,7 +2797,11 @@ static int adv76xx_parse_dt(struct adv76xx_state *state)
 	if (!endpoint)
 		return -EINVAL;
 
-	v4l2_of_parse_endpoint(endpoint, &bus_cfg);
+	ret = v4l2_of_parse_endpoint(endpoint, &bus_cfg);
+	if (ret) {
+		of_node_put(endpoint);
+		return ret;
+	}
 
 	if (!of_property_read_u32(endpoint, "default-input", &v))
 		state->pdata.default_input = v;
@@ -3010,6 +3003,7 @@ static int adv76xx_probe(struct i2c_client *client,
 		V4L2_DV_BT_CEA_640X480P59_94;
 	struct adv76xx_state *state;
 	struct v4l2_ctrl_handler *hdl;
+	struct v4l2_ctrl *ctrl;
 	struct v4l2_subdev *sd;
 	unsigned int i;
 	unsigned int val, val2;
@@ -3141,6 +3135,11 @@ static int adv76xx_probe(struct i2c_client *client,
 			V4L2_CID_SATURATION, 0, 255, 1, 128);
 	v4l2_ctrl_new_std(hdl, &adv76xx_ctrl_ops,
 			V4L2_CID_HUE, 0, 128, 1, 0);
+	ctrl = v4l2_ctrl_new_std_menu(hdl, &adv76xx_ctrl_ops,
+			V4L2_CID_DV_RX_IT_CONTENT_TYPE, V4L2_DV_IT_CONTENT_TYPE_NO_ITC,
+			0, V4L2_DV_IT_CONTENT_TYPE_NO_ITC);
+	if (ctrl)
+		ctrl->flags |= V4L2_CTRL_FLAG_VOLATILE;
 
 	/* private controls */
 	state->detect_tx_5v_ctrl = v4l2_ctrl_new_std(hdl, NULL,
diff --git a/drivers/media/i2c/adv7842.c b/drivers/media/i2c/adv7842.c
index 5fbb788e7b59..7ccb85d45224 100644
--- a/drivers/media/i2c/adv7842.c
+++ b/drivers/media/i2c/adv7842.c
@@ -1359,6 +1359,19 @@ static int adv7842_s_ctrl(struct v4l2_ctrl *ctrl)
 	return -EINVAL;
 }
 
+static int adv7842_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct v4l2_subdev *sd = to_sd(ctrl);
+
+	if (ctrl->id == V4L2_CID_DV_RX_IT_CONTENT_TYPE) {
+		ctrl->val = V4L2_DV_IT_CONTENT_TYPE_NO_ITC;
+		if ((io_read(sd, 0x60) & 1) && (infoframe_read(sd, 0x03) & 0x80))
+			ctrl->val = (infoframe_read(sd, 0x05) >> 4) & 3;
+		return 0;
+	}
+	return -EINVAL;
+}
+
 static inline bool no_power(struct v4l2_subdev *sd)
 {
 	return io_read(sd, 0x0c) & 0x24;
@@ -3022,6 +3035,7 @@ static int adv7842_subscribe_event(struct v4l2_subdev *sd,
 
 static const struct v4l2_ctrl_ops adv7842_ctrl_ops = {
 	.s_ctrl = adv7842_s_ctrl,
+	.g_volatile_ctrl = adv7842_g_volatile_ctrl,
 };
 
 static const struct v4l2_subdev_core_ops adv7842_core_ops = {
@@ -3196,6 +3210,7 @@ static int adv7842_probe(struct i2c_client *client,
 		V4L2_DV_BT_CEA_640X480P59_94;
 	struct adv7842_platform_data *pdata = client->dev.platform_data;
 	struct v4l2_ctrl_handler *hdl;
+	struct v4l2_ctrl *ctrl;
 	struct v4l2_subdev *sd;
 	u16 rev;
 	int err;
@@ -3261,6 +3276,11 @@ static int adv7842_probe(struct i2c_client *client,
 			  V4L2_CID_SATURATION, 0, 255, 1, 128);
 	v4l2_ctrl_new_std(hdl, &adv7842_ctrl_ops,
 			  V4L2_CID_HUE, 0, 128, 1, 0);
+	ctrl = v4l2_ctrl_new_std_menu(hdl, &adv7842_ctrl_ops,
+			V4L2_CID_DV_RX_IT_CONTENT_TYPE, V4L2_DV_IT_CONTENT_TYPE_NO_ITC,
+			0, V4L2_DV_IT_CONTENT_TYPE_NO_ITC);
+	if (ctrl)
+		ctrl->flags |= V4L2_CTRL_FLAG_VOLATILE;
 
 	/* custom controls */
 	state->detect_tx_5v_ctrl = v4l2_ctrl_new_std(hdl, NULL,
diff --git a/drivers/media/i2c/msp3400-driver.c b/drivers/media/i2c/msp3400-driver.c
index a84561d0d4a8..e016626ebf89 100644
--- a/drivers/media/i2c/msp3400-driver.c
+++ b/drivers/media/i2c/msp3400-driver.c
@@ -688,6 +688,9 @@ static int msp_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	int msp_revision;
 	int msp_product, msp_prod_hi, msp_prod_lo;
 	int msp_rom;
+#if defined(CONFIG_MEDIA_CONTROLLER)
+	int ret;
+#endif
 
 	if (!id)
 		strlcpy(client->name, "msp3400", sizeof(client->name));
@@ -704,6 +707,17 @@ static int msp_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	sd = &state->sd;
 	v4l2_i2c_subdev_init(sd, client, &msp_ops);
 
+#if defined(CONFIG_MEDIA_CONTROLLER)
+	state->pads[IF_AUD_DEC_PAD_IF_INPUT].flags = MEDIA_PAD_FL_SINK;
+	state->pads[IF_AUD_DEC_PAD_OUT].flags = MEDIA_PAD_FL_SOURCE;
+
+	sd->entity.function = MEDIA_ENT_F_IF_AUD_DECODER;
+
+	ret = media_entity_pads_init(&sd->entity, 2, state->pads);
+	if (ret < 0)
+		return ret;
+#endif
+
 	state->v4l2_std = V4L2_STD_NTSC;
 	state->detected_std = V4L2_STD_ALL;
 	state->audmode = V4L2_TUNER_MODE_STEREO;
diff --git a/drivers/media/i2c/msp3400-driver.h b/drivers/media/i2c/msp3400-driver.h
index 6cae21366ed5..a8702aca187a 100644
--- a/drivers/media/i2c/msp3400-driver.h
+++ b/drivers/media/i2c/msp3400-driver.h
@@ -7,6 +7,7 @@
 #include <media/drv-intf/msp3400.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ctrls.h>
+#include <media/v4l2-mc.h>
 
 /* ---------------------------------------------------------------------- */
 
@@ -102,6 +103,10 @@ struct msp_state {
 	wait_queue_head_t    wq;
 	unsigned int         restart:1;
 	unsigned int         watch_stereo:1;
+
+#if IS_ENABLED(CONFIG_MEDIA_CONTROLLER)
+	struct media_pad pads[IF_AUD_DEC_PAD_NUM_PADS];
+#endif
 };
 
 static inline struct msp_state *to_state(struct v4l2_subdev *sd)
diff --git a/drivers/media/i2c/mt9v011.c b/drivers/media/i2c/mt9v011.c
index b9fea11d6b0b..9ed1b26b6549 100644
--- a/drivers/media/i2c/mt9v011.c
+++ b/drivers/media/i2c/mt9v011.c
@@ -50,6 +50,9 @@ MODULE_PARM_DESC(debug, "Debug level (0-2)");
 
 struct mt9v011 {
 	struct v4l2_subdev sd;
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct media_pad pad;
+#endif
 	struct v4l2_ctrl_handler ctrls;
 	unsigned width, height;
 	unsigned xtal;
@@ -493,6 +496,9 @@ static int mt9v011_probe(struct i2c_client *c,
 	u16 version;
 	struct mt9v011 *core;
 	struct v4l2_subdev *sd;
+#ifdef CONFIG_MEDIA_CONTROLLER
+	int ret;
+#endif
 
 	/* Check if the adapter supports the needed features */
 	if (!i2c_check_functionality(c->adapter,
@@ -506,6 +512,15 @@ static int mt9v011_probe(struct i2c_client *c,
 	sd = &core->sd;
 	v4l2_i2c_subdev_init(sd, c, &mt9v011_ops);
 
+#ifdef CONFIG_MEDIA_CONTROLLER
+	core->pad.flags = MEDIA_PAD_FL_SOURCE;
+	sd->entity.function = MEDIA_ENT_F_CAM_SENSOR;
+
+	ret = media_entity_pads_init(&sd->entity, 1, &core->pad);
+	if (ret < 0)
+		return ret;
+#endif
+
 	/* Check if the sensor is really a MT9V011 */
 	version = mt9v011_read(sd, R00_MT9V011_CHIP_VERSION);
 	if ((version != MT9V011_VERSION) &&
diff --git a/drivers/media/i2c/mt9v032.c b/drivers/media/i2c/mt9v032.c
index 2e1d116a64e7..501b37039449 100644
--- a/drivers/media/i2c/mt9v032.c
+++ b/drivers/media/i2c/mt9v032.c
@@ -14,6 +14,7 @@
 
 #include <linux/clk.h>
 #include <linux/delay.h>
+#include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
 #include <linux/log2.h>
 #include <linux/mutex.h>
@@ -251,6 +252,8 @@ struct mt9v032 {
 
 	struct regmap *regmap;
 	struct clk *clk;
+	struct gpio_desc *reset_gpio;
+	struct gpio_desc *standby_gpio;
 
 	struct mt9v032_platform_data *pdata;
 	const struct mt9v032_model_info *model;
@@ -312,16 +315,31 @@ static int mt9v032_power_on(struct mt9v032 *mt9v032)
 	struct regmap *map = mt9v032->regmap;
 	int ret;
 
+	if (mt9v032->reset_gpio)
+		gpiod_set_value_cansleep(mt9v032->reset_gpio, 1);
+
 	ret = clk_set_rate(mt9v032->clk, mt9v032->sysclk);
 	if (ret < 0)
 		return ret;
 
+	/* System clock has to be enabled before releasing the reset */
 	ret = clk_prepare_enable(mt9v032->clk);
 	if (ret)
 		return ret;
 
 	udelay(1);
 
+	if (mt9v032->reset_gpio) {
+		gpiod_set_value_cansleep(mt9v032->reset_gpio, 0);
+
+		/* After releasing reset we need to wait 10 clock cycles
+		 * before accessing the sensor over I2C. As the minimum SYSCLK
+		 * frequency is 13MHz, waiting 1µs will be enough in the worst
+		 * case.
+		 */
+		udelay(1);
+	}
+
 	/* Reset the chip and stop data read out */
 	ret = regmap_write(map, MT9V032_RESET, 1);
 	if (ret < 0)
@@ -954,6 +972,16 @@ static int mt9v032_probe(struct i2c_client *client,
 	if (IS_ERR(mt9v032->clk))
 		return PTR_ERR(mt9v032->clk);
 
+	mt9v032->reset_gpio = devm_gpiod_get_optional(&client->dev, "reset",
+						      GPIOD_OUT_HIGH);
+	if (IS_ERR(mt9v032->reset_gpio))
+		return PTR_ERR(mt9v032->reset_gpio);
+
+	mt9v032->standby_gpio = devm_gpiod_get_optional(&client->dev, "standby",
+							GPIOD_OUT_LOW);
+	if (IS_ERR(mt9v032->standby_gpio))
+		return PTR_ERR(mt9v032->standby_gpio);
+
 	mutex_init(&mt9v032->power_lock);
 	mt9v032->pdata = pdata;
 	mt9v032->model = (const void *)did->driver_data;
diff --git a/drivers/media/i2c/ov2659.c b/drivers/media/i2c/ov2659.c
index 02b9a3440557..1f999e9c0118 100644
--- a/drivers/media/i2c/ov2659.c
+++ b/drivers/media/i2c/ov2659.c
@@ -1321,10 +1321,6 @@ static int ov2659_detect(struct v4l2_subdev *sd)
 	}
 	usleep_range(1000, 2000);
 
-	ret = ov2659_init(sd, 0);
-	if (ret < 0)
-		return ret;
-
 	/* Check sensor revision */
 	ret = ov2659_read(client, REG_SC_CHIP_ID_H, &pid);
 	if (!ret)
@@ -1338,8 +1334,10 @@ static int ov2659_detect(struct v4l2_subdev *sd)
 			dev_err(&client->dev,
 				"Sensor detection failed (%04X, %d)\n",
 				id, ret);
-		else
+		else {
 			dev_info(&client->dev, "Found OV%04X sensor\n", id);
+			ret = ov2659_init(sd, 0);
+		}
 	}
 
 	return ret;
diff --git a/drivers/media/i2c/ov9650.c b/drivers/media/i2c/ov9650.c
index a0b3c9bde53d..be5a7fd4f076 100644
--- a/drivers/media/i2c/ov9650.c
+++ b/drivers/media/i2c/ov9650.c
@@ -1046,8 +1046,8 @@ static int ov965x_initialize_controls(struct ov965x *ov965x)
 	ctrls->exposure->flags |= V4L2_CTRL_FLAG_VOLATILE;
 
 	v4l2_ctrl_auto_cluster(3, &ctrls->auto_wb, 0, false);
-	v4l2_ctrl_auto_cluster(3, &ctrls->auto_gain, 0, true);
-	v4l2_ctrl_auto_cluster(3, &ctrls->auto_exp, 1, true);
+	v4l2_ctrl_auto_cluster(2, &ctrls->auto_gain, 0, true);
+	v4l2_ctrl_auto_cluster(2, &ctrls->auto_exp, 1, true);
 	v4l2_ctrl_cluster(2, &ctrls->hflip);
 
 	ov965x->sd.ctrl_handler = hdl;
diff --git a/drivers/media/i2c/s5c73m3/s5c73m3-core.c b/drivers/media/i2c/s5c73m3/s5c73m3-core.c
index 57b3d27993a4..08af58fb8e7d 100644
--- a/drivers/media/i2c/s5c73m3/s5c73m3-core.c
+++ b/drivers/media/i2c/s5c73m3/s5c73m3-core.c
@@ -1639,8 +1639,10 @@ static int s5c73m3_get_platform_data(struct s5c73m3 *state)
 		return 0;
 	}
 
-	v4l2_of_parse_endpoint(node_ep, &ep);
+	ret = v4l2_of_parse_endpoint(node_ep, &ep);
 	of_node_put(node_ep);
+	if (ret)
+		return ret;
 
 	if (ep.bus_type != V4L2_MBUS_CSI2) {
 		dev_err(dev, "unsupported bus type\n");
diff --git a/drivers/media/i2c/s5c73m3/s5c73m3-spi.c b/drivers/media/i2c/s5c73m3/s5c73m3-spi.c
index 7d65b36434b1..72ef9f936e6c 100644
--- a/drivers/media/i2c/s5c73m3/s5c73m3-spi.c
+++ b/drivers/media/i2c/s5c73m3/s5c73m3-spi.c
@@ -37,7 +37,6 @@ enum spi_direction {
 	SPI_DIR_RX,
 	SPI_DIR_TX
 };
-MODULE_DEVICE_TABLE(of, s5c73m3_spi_ids);
 
 static int spi_xmit(struct spi_device *spi_dev, void *addr, const int len,
 							enum spi_direction dir)
diff --git a/drivers/media/i2c/s5k5baf.c b/drivers/media/i2c/s5k5baf.c
index fc3a5a8e6c9c..db82ed05792e 100644
--- a/drivers/media/i2c/s5k5baf.c
+++ b/drivers/media/i2c/s5k5baf.c
@@ -1868,8 +1868,11 @@ static int s5k5baf_parse_device_node(struct s5k5baf *state, struct device *dev)
 		return -EINVAL;
 	}
 
-	v4l2_of_parse_endpoint(node_ep, &ep);
+	ret = v4l2_of_parse_endpoint(node_ep, &ep);
 	of_node_put(node_ep);
+	if (ret)
+		return ret;
+
 	state->bus_type = ep.bus_type;
 
 	switch (state->bus_type) {
diff --git a/drivers/media/i2c/saa7115.c b/drivers/media/i2c/saa7115.c
index 24d2b76dbe97..d2a1ce2bc7f5 100644
--- a/drivers/media/i2c/saa7115.c
+++ b/drivers/media/i2c/saa7115.c
@@ -46,6 +46,7 @@
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ctrls.h>
+#include <media/v4l2-mc.h>
 #include <media/i2c/saa7115.h>
 #include <asm/div64.h>
 
@@ -74,6 +75,9 @@ enum saa711x_model {
 
 struct saa711x_state {
 	struct v4l2_subdev sd;
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct media_pad pads[DEMOD_NUM_PADS];
+#endif
 	struct v4l2_ctrl_handler hdl;
 
 	struct {
@@ -1809,6 +1813,9 @@ static int saa711x_probe(struct i2c_client *client,
 	struct saa7115_platform_data *pdata;
 	int ident;
 	char name[CHIP_VER_SIZE + 1];
+#if defined(CONFIG_MEDIA_CONTROLLER)
+	int ret;
+#endif
 
 	/* Check if the adapter supports the needed features */
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_BYTE_DATA))
@@ -1832,6 +1839,18 @@ static int saa711x_probe(struct i2c_client *client,
 	sd = &state->sd;
 	v4l2_i2c_subdev_init(sd, client, &saa711x_ops);
 
+#if defined(CONFIG_MEDIA_CONTROLLER)
+	state->pads[DEMOD_PAD_IF_INPUT].flags = MEDIA_PAD_FL_SINK;
+	state->pads[DEMOD_PAD_VID_OUT].flags = MEDIA_PAD_FL_SOURCE;
+	state->pads[DEMOD_PAD_VBI_OUT].flags = MEDIA_PAD_FL_SOURCE;
+
+	sd->entity.function = MEDIA_ENT_F_ATV_DECODER;
+
+	ret = media_entity_pads_init(&sd->entity, DEMOD_NUM_PADS, state->pads);
+	if (ret < 0)
+		return ret;
+#endif
+
 	v4l_info(client, "%s found @ 0x%x (%s)\n", name,
 		 client->addr << 1, client->adapter->name);
 	hdl = &state->hdl;
diff --git a/drivers/media/i2c/soc_camera/mt9m001.c b/drivers/media/i2c/soc_camera/mt9m001.c
index 2e14e52ba2e0..69becc358659 100644
--- a/drivers/media/i2c/soc_camera/mt9m001.c
+++ b/drivers/media/i2c/soc_camera/mt9m001.c
@@ -632,7 +632,7 @@ static struct v4l2_subdev_video_ops mt9m001_subdev_video_ops = {
 	.s_mbus_config	= mt9m001_s_mbus_config,
 };
 
-static struct v4l2_subdev_sensor_ops mt9m001_subdev_sensor_ops = {
+static const struct v4l2_subdev_sensor_ops mt9m001_subdev_sensor_ops = {
 	.g_skip_top_lines	= mt9m001_g_skip_top_lines,
 };
 
diff --git a/drivers/media/i2c/soc_camera/mt9t031.c b/drivers/media/i2c/soc_camera/mt9t031.c
index 3b6eeed2e2b9..5c8e3ffe3b27 100644
--- a/drivers/media/i2c/soc_camera/mt9t031.c
+++ b/drivers/media/i2c/soc_camera/mt9t031.c
@@ -728,7 +728,7 @@ static struct v4l2_subdev_video_ops mt9t031_subdev_video_ops = {
 	.s_mbus_config	= mt9t031_s_mbus_config,
 };
 
-static struct v4l2_subdev_sensor_ops mt9t031_subdev_sensor_ops = {
+static const struct v4l2_subdev_sensor_ops mt9t031_subdev_sensor_ops = {
 	.g_skip_top_lines	= mt9t031_g_skip_top_lines,
 };
 
diff --git a/drivers/media/i2c/soc_camera/mt9v022.c b/drivers/media/i2c/soc_camera/mt9v022.c
index c2ba1fb3694d..2721e583bfa0 100644
--- a/drivers/media/i2c/soc_camera/mt9v022.c
+++ b/drivers/media/i2c/soc_camera/mt9v022.c
@@ -860,7 +860,7 @@ static struct v4l2_subdev_video_ops mt9v022_subdev_video_ops = {
 	.s_mbus_config	= mt9v022_s_mbus_config,
 };
 
-static struct v4l2_subdev_sensor_ops mt9v022_subdev_sensor_ops = {
+static const struct v4l2_subdev_sensor_ops mt9v022_subdev_sensor_ops = {
 	.g_skip_top_lines	= mt9v022_g_skip_top_lines,
 };
 
diff --git a/drivers/media/i2c/tc358743.c b/drivers/media/i2c/tc358743.c
index 3397eb99c67b..972e0d47259d 100644
--- a/drivers/media/i2c/tc358743.c
+++ b/drivers/media/i2c/tc358743.c
@@ -59,8 +59,7 @@ MODULE_LICENSE("GPL");
 #define EDID_NUM_BLOCKS_MAX 8
 #define EDID_BLOCK_SIZE 128
 
-/* Max transfer size done by I2C transfer functions */
-#define MAX_XFER_SIZE  (EDID_NUM_BLOCKS_MAX * EDID_BLOCK_SIZE + 2)
+#define I2C_MAX_XFER_SIZE  (EDID_BLOCK_SIZE + 2)
 
 static const struct v4l2_dv_timings_cap tc358743_timings_cap = {
 	.type = V4L2_DV_BT_656_1120,
@@ -97,9 +96,6 @@ struct tc358743_state {
 	/* edid  */
 	u8 edid_blocks_written;
 
-	/* used by i2c_wr() */
-	u8 wr_data[MAX_XFER_SIZE];
-
 	struct v4l2_dv_timings timings;
 	u32 mbus_fmt_code;
 
@@ -149,13 +145,15 @@ static void i2c_wr(struct v4l2_subdev *sd, u16 reg, u8 *values, u32 n)
 {
 	struct tc358743_state *state = to_state(sd);
 	struct i2c_client *client = state->i2c_client;
-	u8 *data = state->wr_data;
 	int err, i;
 	struct i2c_msg msg;
+	u8 data[I2C_MAX_XFER_SIZE];
 
-	if ((2 + n) > sizeof(state->wr_data))
+	if ((2 + n) > I2C_MAX_XFER_SIZE) {
+		n = I2C_MAX_XFER_SIZE - 2;
 		v4l2_warn(sd, "i2c wr reg=%04x: len=%d is too big!\n",
 			  reg, 2 + n);
+	}
 
 	msg.addr = client->addr;
 	msg.buf = data;
@@ -859,15 +857,16 @@ static void tc358743_format_change(struct v4l2_subdev *sd)
 	if (tc358743_get_detected_timings(sd, &timings)) {
 		enable_stream(sd, false);
 
-		v4l2_dbg(1, debug, sd, "%s: Format changed. No signal\n",
+		v4l2_dbg(1, debug, sd, "%s: No signal\n",
 				__func__);
 	} else {
 		if (!v4l2_match_dv_timings(&state->timings, &timings, 0, false))
 			enable_stream(sd, false);
 
-		v4l2_print_dv_timings(sd->name,
-				"tc358743_format_change: Format changed. New format: ",
-				&timings, false);
+		if (debug)
+			v4l2_print_dv_timings(sd->name,
+					"tc358743_format_change: New format: ",
+					&timings, false);
 	}
 
 	if (sd->devnode)
@@ -1199,21 +1198,21 @@ static int tc358743_log_status(struct v4l2_subdev *sd)
 #ifdef CONFIG_VIDEO_ADV_DEBUG
 static void tc358743_print_register_map(struct v4l2_subdev *sd)
 {
-	v4l2_info(sd, "0x0000–0x00FF: Global Control Register\n");
-	v4l2_info(sd, "0x0100–0x01FF: CSI2-TX PHY Register\n");
-	v4l2_info(sd, "0x0200–0x03FF: CSI2-TX PPI Register\n");
-	v4l2_info(sd, "0x0400–0x05FF: Reserved\n");
-	v4l2_info(sd, "0x0600–0x06FF: CEC Register\n");
-	v4l2_info(sd, "0x0700–0x84FF: Reserved\n");
-	v4l2_info(sd, "0x8500–0x85FF: HDMIRX System Control Register\n");
-	v4l2_info(sd, "0x8600–0x86FF: HDMIRX Audio Control Register\n");
-	v4l2_info(sd, "0x8700–0x87FF: HDMIRX InfoFrame packet data Register\n");
-	v4l2_info(sd, "0x8800–0x88FF: HDMIRX HDCP Port Register\n");
-	v4l2_info(sd, "0x8900–0x89FF: HDMIRX Video Output Port & 3D Register\n");
-	v4l2_info(sd, "0x8A00–0x8BFF: Reserved\n");
-	v4l2_info(sd, "0x8C00–0x8FFF: HDMIRX EDID-RAM (1024bytes)\n");
-	v4l2_info(sd, "0x9000–0x90FF: HDMIRX GBD Extraction Control\n");
-	v4l2_info(sd, "0x9100–0x92FF: HDMIRX GBD RAM read\n");
+	v4l2_info(sd, "0x0000-0x00FF: Global Control Register\n");
+	v4l2_info(sd, "0x0100-0x01FF: CSI2-TX PHY Register\n");
+	v4l2_info(sd, "0x0200-0x03FF: CSI2-TX PPI Register\n");
+	v4l2_info(sd, "0x0400-0x05FF: Reserved\n");
+	v4l2_info(sd, "0x0600-0x06FF: CEC Register\n");
+	v4l2_info(sd, "0x0700-0x84FF: Reserved\n");
+	v4l2_info(sd, "0x8500-0x85FF: HDMIRX System Control Register\n");
+	v4l2_info(sd, "0x8600-0x86FF: HDMIRX Audio Control Register\n");
+	v4l2_info(sd, "0x8700-0x87FF: HDMIRX InfoFrame packet data Register\n");
+	v4l2_info(sd, "0x8800-0x88FF: HDMIRX HDCP Port Register\n");
+	v4l2_info(sd, "0x8900-0x89FF: HDMIRX Video Output Port & 3D Register\n");
+	v4l2_info(sd, "0x8A00-0x8BFF: Reserved\n");
+	v4l2_info(sd, "0x8C00-0x8FFF: HDMIRX EDID-RAM (1024bytes)\n");
+	v4l2_info(sd, "0x9000-0x90FF: HDMIRX GBD Extraction Control\n");
+	v4l2_info(sd, "0x9100-0x92FF: HDMIRX GBD RAM read\n");
 	v4l2_info(sd, "0x9300-      : Reserved\n");
 }
 
@@ -1581,6 +1580,7 @@ static int tc358743_s_edid(struct v4l2_subdev *sd,
 {
 	struct tc358743_state *state = to_state(sd);
 	u16 edid_len = edid->blocks * EDID_BLOCK_SIZE;
+	int i;
 
 	v4l2_dbg(2, debug, sd, "%s, pad %d, start block %d, blocks %d\n",
 		 __func__, edid->pad, edid->start_block, edid->blocks);
@@ -1606,7 +1606,8 @@ static int tc358743_s_edid(struct v4l2_subdev *sd,
 		return 0;
 	}
 
-	i2c_wr(sd, EDID_RAM, edid->edid, edid_len);
+	for (i = 0; i < edid_len; i += EDID_BLOCK_SIZE)
+		i2c_wr(sd, EDID_RAM + i, edid->edid + i, EDID_BLOCK_SIZE);
 
 	state->edid_blocks_written = edid->blocks;
 
diff --git a/drivers/media/i2c/tvp514x.c b/drivers/media/i2c/tvp514x.c
index 7fa5f1e4fe37..7cdd94842938 100644
--- a/drivers/media/i2c/tvp514x.c
+++ b/drivers/media/i2c/tvp514x.c
@@ -1001,7 +1001,7 @@ static struct tvp514x_decoder tvp514x_dev = {
 static struct tvp514x_platform_data *
 tvp514x_get_pdata(struct i2c_client *client)
 {
-	struct tvp514x_platform_data *pdata;
+	struct tvp514x_platform_data *pdata = NULL;
 	struct v4l2_of_endpoint bus_cfg;
 	struct device_node *endpoint;
 	unsigned int flags;
@@ -1013,11 +1013,13 @@ tvp514x_get_pdata(struct i2c_client *client)
 	if (!endpoint)
 		return NULL;
 
+	if (v4l2_of_parse_endpoint(endpoint, &bus_cfg))
+		goto done;
+
 	pdata = devm_kzalloc(&client->dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
 		goto done;
 
-	v4l2_of_parse_endpoint(endpoint, &bus_cfg);
 	flags = bus_cfg.bus.parallel.flags;
 
 	if (flags & V4L2_MBUS_HSYNC_ACTIVE_HIGH)
diff --git a/drivers/media/i2c/tvp5150.c b/drivers/media/i2c/tvp5150.c
index 6c3769d44b75..ff18444e19e4 100644
--- a/drivers/media/i2c/tvp5150.c
+++ b/drivers/media/i2c/tvp5150.c
@@ -1,19 +1,22 @@
 /*
- * tvp5150 - Texas Instruments TVP5150A/AM1 video decoder driver
+ * tvp5150 - Texas Instruments TVP5150A/AM1 and TVP5151 video decoder driver
  *
  * Copyright (c) 2005,2006 Mauro Carvalho Chehab (mchehab@infradead.org)
  * This code is placed under the terms of the GNU General Public License v2
  */
 
+#include <dt-bindings/media/tvp5150.h>
 #include <linux/i2c.h>
 #include <linux/slab.h>
 #include <linux/videodev2.h>
 #include <linux/delay.h>
+#include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <media/v4l2-async.h>
 #include <media/v4l2-device.h>
-#include <media/i2c/tvp5150.h>
 #include <media/v4l2-ctrls.h>
+#include <media/v4l2-of.h>
+#include <media/v4l2-mc.h>
 
 #include "tvp5150_reg.h"
 
@@ -24,7 +27,7 @@
 #define TVP5150_MAX_CROP_TOP	127
 #define TVP5150_CROP_SHIFT	2
 
-MODULE_DESCRIPTION("Texas Instruments TVP5150A video decoder driver");
+MODULE_DESCRIPTION("Texas Instruments TVP5150A/TVP5150AM1/TVP5151 video decoder driver");
 MODULE_AUTHOR("Mauro Carvalho Chehab");
 MODULE_LICENSE("GPL");
 
@@ -35,6 +38,11 @@ MODULE_PARM_DESC(debug, "Debug level (0-2)");
 
 struct tvp5150 {
 	struct v4l2_subdev sd;
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct media_pad pads[DEMOD_NUM_PADS];
+	struct media_entity input_ent[TVP5150_INPUT_NUM];
+	struct media_pad input_pad[TVP5150_INPUT_NUM];
+#endif
 	struct v4l2_ctrl_handler hdl;
 	struct v4l2_rect rect;
 
@@ -42,6 +50,11 @@ struct tvp5150 {
 	u32 input;
 	u32 output;
 	int enable;
+
+	u16 dev_id;
+	u16 rom_ver;
+
+	enum v4l2_mbus_type mbus_type;
 };
 
 static inline struct tvp5150 *to_tvp5150(struct v4l2_subdev *sd)
@@ -246,8 +259,12 @@ static inline void tvp5150_selmux(struct v4l2_subdev *sd)
 	int input = 0;
 	int val;
 
-	if ((decoder->output & TVP5150_BLACK_SCREEN) || !decoder->enable)
-		input = 8;
+	/* Only tvp5150am1 and tvp5151 have signal generator support */
+	if ((decoder->dev_id == 0x5150 && decoder->rom_ver == 0x0400) ||
+	    (decoder->dev_id == 0x5151 && decoder->rom_ver == 0x0100)) {
+		if (!decoder->enable)
+			input = 8;
+	}
 
 	switch (decoder->input) {
 	case TVP5150_COMPOSITE1:
@@ -772,12 +789,17 @@ static int tvp5150_reset(struct v4l2_subdev *sd, u32 val)
 	v4l2_ctrl_handler_setup(&decoder->hdl);
 
 	tvp5150_set_std(sd, decoder->norm);
+
+	if (decoder->mbus_type == V4L2_MBUS_PARALLEL)
+		tvp5150_write(sd, TVP5150_DATA_RATE_SEL, 0x40);
+
 	return 0;
 };
 
 static int tvp5150_s_ctrl(struct v4l2_ctrl *ctrl)
 {
 	struct v4l2_subdev *sd = to_sd(ctrl);
+	struct tvp5150 *decoder = to_tvp5150(sd);
 
 	switch (ctrl->id) {
 	case V4L2_CID_BRIGHTNESS:
@@ -791,6 +813,9 @@ static int tvp5150_s_ctrl(struct v4l2_ctrl *ctrl)
 		return 0;
 	case V4L2_CID_HUE:
 		tvp5150_write(sd, TVP5150_HUE_CTL, ctrl->val);
+	case V4L2_CID_TEST_PATTERN:
+		decoder->enable = ctrl->val ? false : true;
+		tvp5150_selmux(sd);
 		return 0;
 	}
 	return -EINVAL;
@@ -818,17 +843,6 @@ static v4l2_std_id tvp5150_read_std(struct v4l2_subdev *sd)
 	}
 }
 
-static int tvp5150_enum_mbus_code(struct v4l2_subdev *sd,
-		struct v4l2_subdev_pad_config *cfg,
-		struct v4l2_subdev_mbus_code_enum *code)
-{
-	if (code->pad || code->index)
-		return -EINVAL;
-
-	code->code = MEDIA_BUS_FMT_UYVY8_2X8;
-	return 0;
-}
-
 static int tvp5150_fill_fmt(struct v4l2_subdev *sd,
 		struct v4l2_subdev_pad_config *cfg,
 		struct v4l2_subdev_format *format)
@@ -844,10 +858,10 @@ static int tvp5150_fill_fmt(struct v4l2_subdev *sd,
 	tvp5150_reset(sd, 0);
 
 	f->width = decoder->rect.width;
-	f->height = decoder->rect.height;
+	f->height = decoder->rect.height / 2;
 
 	f->code = MEDIA_BUS_FMT_UYVY8_2X8;
-	f->field = V4L2_FIELD_SEQ_TB;
+	f->field = V4L2_FIELD_ALTERNATE;
 	f->colorspace = V4L2_COLORSPACE_SMPTE170M;
 
 	v4l2_dbg(1, debug, sd, "width = %d, height = %d\n", f->width,
@@ -948,10 +962,110 @@ static int tvp5150_cropcap(struct v4l2_subdev *sd, struct v4l2_cropcap *a)
 	return 0;
 }
 
+static int tvp5150_g_mbus_config(struct v4l2_subdev *sd,
+				 struct v4l2_mbus_config *cfg)
+{
+	struct tvp5150 *decoder = to_tvp5150(sd);
+
+	cfg->type = decoder->mbus_type;
+	cfg->flags = V4L2_MBUS_MASTER | V4L2_MBUS_PCLK_SAMPLE_RISING
+		   | V4L2_MBUS_FIELD_EVEN_LOW | V4L2_MBUS_DATA_ACTIVE_HIGH;
+
+	return 0;
+}
+
+/****************************************************************************
+			V4L2 subdev pad ops
+ ****************************************************************************/
+static int tvp5150_enum_mbus_code(struct v4l2_subdev *sd,
+		struct v4l2_subdev_pad_config *cfg,
+		struct v4l2_subdev_mbus_code_enum *code)
+{
+	if (code->pad || code->index)
+		return -EINVAL;
+
+	code->code = MEDIA_BUS_FMT_UYVY8_2X8;
+	return 0;
+}
+
+static int tvp5150_enum_frame_size(struct v4l2_subdev *sd,
+				   struct v4l2_subdev_pad_config *cfg,
+				   struct v4l2_subdev_frame_size_enum *fse)
+{
+	struct tvp5150 *decoder = to_tvp5150(sd);
+
+	if (fse->index >= 8 || fse->code != MEDIA_BUS_FMT_UYVY8_2X8)
+		return -EINVAL;
+
+	fse->code = MEDIA_BUS_FMT_UYVY8_2X8;
+	fse->min_width = decoder->rect.width;
+	fse->max_width = decoder->rect.width;
+	fse->min_height = decoder->rect.height / 2;
+	fse->max_height = decoder->rect.height / 2;
+
+	return 0;
+}
+
+/****************************************************************************
+			Media entity ops
+ ****************************************************************************/
+
+static int tvp5150_link_setup(struct media_entity *entity,
+			      const struct media_pad *local,
+			      const struct media_pad *remote, u32 flags)
+{
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct v4l2_subdev *sd = media_entity_to_v4l2_subdev(entity);
+	struct tvp5150 *decoder = to_tvp5150(sd);
+	int i;
+
+	for (i = 0; i < TVP5150_INPUT_NUM; i++) {
+		if (remote->entity == &decoder->input_ent[i])
+			break;
+	}
+
+	/* Do nothing for entities that are not input connectors */
+	if (i == TVP5150_INPUT_NUM)
+		return 0;
+
+	decoder->input = i;
+
+	tvp5150_selmux(sd);
+#endif
+
+	return 0;
+}
+
+static const struct media_entity_operations tvp5150_sd_media_ops = {
+	.link_setup = tvp5150_link_setup,
+};
+
 /****************************************************************************
 			I2C Command
  ****************************************************************************/
 
+static int tvp5150_s_stream(struct v4l2_subdev *sd, int enable)
+{
+	struct tvp5150 *decoder = to_tvp5150(sd);
+	/* Output format: 8-bit ITU-R BT.656 with embedded syncs */
+	int val = 0x09;
+
+	/* Output format: 8-bit 4:2:2 YUV with discrete sync */
+	if (decoder->mbus_type == V4L2_MBUS_PARALLEL)
+		val = 0x0d;
+
+	/* Initializes TVP5150 to its default values */
+	/* # set PCLK (27MHz) */
+	tvp5150_write(sd, TVP5150_CONF_SHARED_PIN, 0x00);
+
+	if (enable)
+		tvp5150_write(sd, TVP5150_MISC_CTL, val);
+	else
+		tvp5150_write(sd, TVP5150_MISC_CTL, 0x00);
+
+	return 0;
+}
+
 static int tvp5150_s_routing(struct v4l2_subdev *sd,
 			     u32 input, u32 output, u32 config)
 {
@@ -959,6 +1073,12 @@ static int tvp5150_s_routing(struct v4l2_subdev *sd,
 
 	decoder->input = input;
 	decoder->output = output;
+
+	if (output == TVP5150_BLACK_SCREEN)
+		decoder->enable = false;
+	else
+		decoder->enable = true;
+
 	tvp5150_selmux(sd);
 	return 0;
 }
@@ -1052,6 +1172,42 @@ static int tvp5150_g_tuner(struct v4l2_subdev *sd, struct v4l2_tuner *vt)
 	return 0;
 }
 
+static int tvp5150_registered_async(struct v4l2_subdev *sd)
+{
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct tvp5150 *decoder = to_tvp5150(sd);
+	int ret = 0;
+	int i;
+
+	for (i = 0; i < TVP5150_INPUT_NUM; i++) {
+		struct media_entity *input = &decoder->input_ent[i];
+		struct media_pad *pad = &decoder->input_pad[i];
+
+		if (!input->name)
+			continue;
+
+		decoder->input_pad[i].flags = MEDIA_PAD_FL_SOURCE;
+
+		ret = media_entity_pads_init(input, 1, pad);
+		if (ret < 0)
+			return ret;
+
+		ret = media_device_register_entity(sd->v4l2_dev->mdev, input);
+		if (ret < 0)
+			return ret;
+
+		ret = media_create_pad_link(input, 0, &sd->entity,
+					    DEMOD_PAD_IF_INPUT, 0);
+		if (ret < 0) {
+			media_device_unregister_entity(input);
+			return ret;
+		}
+	}
+#endif
+
+	return 0;
+}
+
 /* ----------------------------------------------------------------------- */
 
 static const struct v4l2_ctrl_ops tvp5150_ctrl_ops = {
@@ -1065,6 +1221,7 @@ static const struct v4l2_subdev_core_ops tvp5150_core_ops = {
 	.g_register = tvp5150_g_register,
 	.s_register = tvp5150_s_register,
 #endif
+	.registered_async = tvp5150_registered_async,
 };
 
 static const struct v4l2_subdev_tuner_ops tvp5150_tuner_ops = {
@@ -1073,10 +1230,12 @@ static const struct v4l2_subdev_tuner_ops tvp5150_tuner_ops = {
 
 static const struct v4l2_subdev_video_ops tvp5150_video_ops = {
 	.s_std = tvp5150_s_std,
+	.s_stream = tvp5150_s_stream,
 	.s_routing = tvp5150_s_routing,
 	.s_crop = tvp5150_s_crop,
 	.g_crop = tvp5150_g_crop,
 	.cropcap = tvp5150_cropcap,
+	.g_mbus_config = tvp5150_g_mbus_config,
 };
 
 static const struct v4l2_subdev_vbi_ops tvp5150_vbi_ops = {
@@ -1088,6 +1247,7 @@ static const struct v4l2_subdev_vbi_ops tvp5150_vbi_ops = {
 
 static const struct v4l2_subdev_pad_ops tvp5150_pad_ops = {
 	.enum_mbus_code = tvp5150_enum_mbus_code,
+	.enum_frame_size = tvp5150_enum_frame_size,
 	.set_fmt = tvp5150_fill_fmt,
 	.get_fmt = tvp5150_fill_fmt,
 };
@@ -1105,63 +1265,239 @@ static const struct v4l2_subdev_ops tvp5150_ops = {
 			I2C Client & Driver
  ****************************************************************************/
 
+static int tvp5150_detect_version(struct tvp5150 *core)
+{
+	struct v4l2_subdev *sd = &core->sd;
+	struct i2c_client *c = v4l2_get_subdevdata(sd);
+	unsigned int i;
+	u8 regs[4];
+	int res;
+
+	/*
+	 * Read consequent registers - TVP5150_MSB_DEV_ID, TVP5150_LSB_DEV_ID,
+	 * TVP5150_ROM_MAJOR_VER, TVP5150_ROM_MINOR_VER
+	 */
+	for (i = 0; i < 4; i++) {
+		res = tvp5150_read(sd, TVP5150_MSB_DEV_ID + i);
+		if (res < 0)
+			return res;
+		regs[i] = res;
+	}
+
+	core->dev_id = (regs[0] << 8) | regs[1];
+	core->rom_ver = (regs[2] << 8) | regs[3];
+
+	v4l2_info(sd, "tvp%04x (%u.%u) chip found @ 0x%02x (%s)\n",
+		  core->dev_id, regs[2], regs[3], c->addr << 1,
+		  c->adapter->name);
+
+	if (core->dev_id == 0x5150 && core->rom_ver == 0x0321) {
+		v4l2_info(sd, "tvp5150a detected.\n");
+	} else if (core->dev_id == 0x5150 && core->rom_ver == 0x0400) {
+		v4l2_info(sd, "tvp5150am1 detected.\n");
+
+		/* ITU-T BT.656.4 timing */
+		tvp5150_write(sd, TVP5150_REV_SELECT, 0);
+	} else if (core->dev_id == 0x5151 && core->rom_ver == 0x0100) {
+		v4l2_info(sd, "tvp5151 detected.\n");
+	} else {
+		v4l2_info(sd, "*** unknown tvp%04x chip detected.\n",
+			  core->dev_id);
+	}
+
+	return 0;
+}
+
+static int tvp5150_init(struct i2c_client *c)
+{
+	struct gpio_desc *pdn_gpio;
+	struct gpio_desc *reset_gpio;
+
+	pdn_gpio = devm_gpiod_get_optional(&c->dev, "pdn", GPIOD_OUT_HIGH);
+	if (IS_ERR(pdn_gpio))
+		return PTR_ERR(pdn_gpio);
+
+	if (pdn_gpio) {
+		gpiod_set_value_cansleep(pdn_gpio, 0);
+		/* Delay time between power supplies active and reset */
+		msleep(20);
+	}
+
+	reset_gpio = devm_gpiod_get_optional(&c->dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(reset_gpio))
+		return PTR_ERR(reset_gpio);
+
+	if (reset_gpio) {
+		/* RESETB pulse duration */
+		ndelay(500);
+		gpiod_set_value_cansleep(reset_gpio, 0);
+		/* Delay time between end of reset to I2C active */
+		usleep_range(200, 250);
+	}
+
+	return 0;
+}
+
+static int tvp5150_parse_dt(struct tvp5150 *decoder, struct device_node *np)
+{
+	struct v4l2_of_endpoint bus_cfg;
+	struct device_node *ep;
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct device_node *connectors, *child;
+	struct media_entity *input;
+	const char *name;
+	u32 input_type;
+#endif
+	unsigned int flags;
+	int ret = 0;
+
+	ep = of_graph_get_next_endpoint(np, NULL);
+	if (!ep)
+		return -EINVAL;
+
+	ret = v4l2_of_parse_endpoint(ep, &bus_cfg);
+	if (ret)
+		goto err;
+
+	flags = bus_cfg.bus.parallel.flags;
+
+	if (bus_cfg.bus_type == V4L2_MBUS_PARALLEL &&
+	    !(flags & V4L2_MBUS_HSYNC_ACTIVE_HIGH &&
+	      flags & V4L2_MBUS_VSYNC_ACTIVE_HIGH &&
+	      flags & V4L2_MBUS_FIELD_EVEN_LOW)) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	decoder->mbus_type = bus_cfg.bus_type;
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+	connectors = of_get_child_by_name(np, "connectors");
+
+	if (!connectors)
+		goto err;
+
+	for_each_available_child_of_node(connectors, child) {
+		ret = of_property_read_u32(child, "input", &input_type);
+		if (ret) {
+			v4l2_err(&decoder->sd,
+				 "missing type property in node %s\n",
+				 child->name);
+			goto err_connector;
+		}
+
+		if (input_type >= TVP5150_INPUT_NUM) {
+			ret = -EINVAL;
+			goto err_connector;
+		}
+
+		input = &decoder->input_ent[input_type];
+
+		/* Each input connector can only be defined once */
+		if (input->name) {
+			v4l2_err(&decoder->sd,
+				 "input %s with same type already exists\n",
+				 input->name);
+			ret = -EINVAL;
+			goto err_connector;
+		}
+
+		switch (input_type) {
+		case TVP5150_COMPOSITE0:
+		case TVP5150_COMPOSITE1:
+			input->function = MEDIA_ENT_F_CONN_COMPOSITE;
+			break;
+		case TVP5150_SVIDEO:
+			input->function = MEDIA_ENT_F_CONN_SVIDEO;
+			break;
+		}
+
+		input->flags = MEDIA_ENT_FL_CONNECTOR;
+
+		ret = of_property_read_string(child, "label", &name);
+		if (ret < 0) {
+			v4l2_err(&decoder->sd,
+				 "missing label property in node %s\n",
+				 child->name);
+			goto err_connector;
+		}
+
+		input->name = name;
+	}
+
+err_connector:
+	of_node_put(connectors);
+#endif
+err:
+	of_node_put(ep);
+	return ret;
+}
+
+static const char * const tvp5150_test_patterns[2] = {
+	"Disabled",
+	"Black screen"
+};
+
 static int tvp5150_probe(struct i2c_client *c,
 			 const struct i2c_device_id *id)
 {
 	struct tvp5150 *core;
 	struct v4l2_subdev *sd;
-	int tvp5150_id[4];
-	int i, res;
+	struct device_node *np = c->dev.of_node;
+	int res;
 
 	/* Check if the adapter supports the needed features */
 	if (!i2c_check_functionality(c->adapter,
 	     I2C_FUNC_SMBUS_READ_BYTE | I2C_FUNC_SMBUS_WRITE_BYTE_DATA))
 		return -EIO;
 
+	res = tvp5150_init(c);
+	if (res)
+		return res;
+
 	core = devm_kzalloc(&c->dev, sizeof(*core), GFP_KERNEL);
 	if (!core)
 		return -ENOMEM;
+
 	sd = &core->sd;
-	v4l2_i2c_subdev_init(sd, c, &tvp5150_ops);
 
-	/* 
-	 * Read consequent registers - TVP5150_MSB_DEV_ID, TVP5150_LSB_DEV_ID,
-	 * TVP5150_ROM_MAJOR_VER, TVP5150_ROM_MINOR_VER 
-	 */
-	for (i = 0; i < 4; i++) {
-		res = tvp5150_read(sd, TVP5150_MSB_DEV_ID + i);
-		if (res < 0)
+	if (IS_ENABLED(CONFIG_OF) && np) {
+		res = tvp5150_parse_dt(core, np);
+		if (res) {
+			v4l2_err(sd, "DT parsing error: %d\n", res);
 			return res;
-		tvp5150_id[i] = res;
+		}
+	} else {
+		/* Default to BT.656 embedded sync */
+		core->mbus_type = V4L2_MBUS_BT656;
 	}
 
-	v4l_info(c, "chip found @ 0x%02x (%s)\n",
-		 c->addr << 1, c->adapter->name);
+	v4l2_i2c_subdev_init(sd, c, &tvp5150_ops);
+	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 
-	if (tvp5150_id[2] == 4 && tvp5150_id[3] == 0) { /* Is TVP5150AM1 */
-		v4l2_info(sd, "tvp%02x%02xam1 detected.\n",
-			  tvp5150_id[0], tvp5150_id[1]);
+#if defined(CONFIG_MEDIA_CONTROLLER)
+	core->pads[DEMOD_PAD_IF_INPUT].flags = MEDIA_PAD_FL_SINK;
+	core->pads[DEMOD_PAD_VID_OUT].flags = MEDIA_PAD_FL_SOURCE;
+	core->pads[DEMOD_PAD_VBI_OUT].flags = MEDIA_PAD_FL_SOURCE;
 
-		/* ITU-T BT.656.4 timing */
-		tvp5150_write(sd, TVP5150_REV_SELECT, 0);
-	} else {
-		/* Is TVP5150A */
-		if (tvp5150_id[2] == 3 || tvp5150_id[3] == 0x21) {
-			v4l2_info(sd, "tvp%02x%02xa detected.\n",
-				  tvp5150_id[0], tvp5150_id[1]);
-		} else {
-			v4l2_info(sd, "*** unknown tvp%02x%02x chip detected.\n",
-				  tvp5150_id[0], tvp5150_id[1]);
-			v4l2_info(sd, "*** Rom ver is %d.%d\n",
-				  tvp5150_id[2], tvp5150_id[3]);
-		}
-	}
+	sd->entity.function = MEDIA_ENT_F_ATV_DECODER;
+
+	res = media_entity_pads_init(&sd->entity, DEMOD_NUM_PADS, core->pads);
+	if (res < 0)
+		return res;
+
+	sd->entity.ops = &tvp5150_sd_media_ops;
+#endif
+
+	res = tvp5150_detect_version(core);
+	if (res < 0)
+		return res;
 
 	core->norm = V4L2_STD_ALL;	/* Default is autodetect */
 	core->input = TVP5150_COMPOSITE1;
-	core->enable = 1;
+	core->enable = true;
 
-	v4l2_ctrl_handler_init(&core->hdl, 4);
+	v4l2_ctrl_handler_init(&core->hdl, 5);
 	v4l2_ctrl_new_std(&core->hdl, &tvp5150_ctrl_ops,
 			V4L2_CID_BRIGHTNESS, 0, 255, 1, 128);
 	v4l2_ctrl_new_std(&core->hdl, &tvp5150_ctrl_ops,
@@ -1170,6 +1506,13 @@ static int tvp5150_probe(struct i2c_client *c,
 			V4L2_CID_SATURATION, 0, 255, 1, 128);
 	v4l2_ctrl_new_std(&core->hdl, &tvp5150_ctrl_ops,
 			V4L2_CID_HUE, -128, 127, 1, 0);
+	v4l2_ctrl_new_std(&core->hdl, &tvp5150_ctrl_ops,
+			V4L2_CID_PIXEL_RATE, 27000000,
+			27000000, 1, 27000000);
+	v4l2_ctrl_new_std_menu_items(&core->hdl, &tvp5150_ctrl_ops,
+				     V4L2_CID_TEST_PATTERN,
+				     ARRAY_SIZE(tvp5150_test_patterns),
+				     0, 0, tvp5150_test_patterns);
 	sd->ctrl_handler = &core->hdl;
 	if (core->hdl.error) {
 		res = core->hdl.error;
@@ -1221,8 +1564,17 @@ static const struct i2c_device_id tvp5150_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, tvp5150_id);
 
+#if IS_ENABLED(CONFIG_OF)
+static const struct of_device_id tvp5150_of_match[] = {
+	{ .compatible = "ti,tvp5150", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, tvp5150_of_match);
+#endif
+
 static struct i2c_driver tvp5150_driver = {
 	.driver = {
+		.of_match_table = of_match_ptr(tvp5150_of_match),
 		.name	= "tvp5150",
 	},
 	.probe		= tvp5150_probe,
diff --git a/drivers/media/i2c/tvp7002.c b/drivers/media/i2c/tvp7002.c
index 83c79fa5f61d..4df640c3aa40 100644
--- a/drivers/media/i2c/tvp7002.c
+++ b/drivers/media/i2c/tvp7002.c
@@ -894,7 +894,7 @@ static struct tvp7002_config *
 tvp7002_get_pdata(struct i2c_client *client)
 {
 	struct v4l2_of_endpoint bus_cfg;
-	struct tvp7002_config *pdata;
+	struct tvp7002_config *pdata = NULL;
 	struct device_node *endpoint;
 	unsigned int flags;
 
@@ -905,11 +905,13 @@ tvp7002_get_pdata(struct i2c_client *client)
 	if (!endpoint)
 		return NULL;
 
+	if (v4l2_of_parse_endpoint(endpoint, &bus_cfg))
+		goto done;
+
 	pdata = devm_kzalloc(&client->dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
 		goto done;
 
-	v4l2_of_parse_endpoint(endpoint, &bus_cfg);
 	flags = bus_cfg.bus.parallel.flags;
 
 	if (flags & V4L2_MBUS_HSYNC_ACTIVE_HIGH)
diff --git a/drivers/media/i2c/vpx3220.c b/drivers/media/i2c/vpx3220.c
index 4b564f17f618..90b693f4e2ab 100644
--- a/drivers/media/i2c/vpx3220.c
+++ b/drivers/media/i2c/vpx3220.c
@@ -124,7 +124,7 @@ static int vpx3220_fp_write(struct v4l2_subdev *sd, u8 fpaddr, u16 data)
 	return 0;
 }
 
-static u16 vpx3220_fp_read(struct v4l2_subdev *sd, u16 fpaddr)
+static int vpx3220_fp_read(struct v4l2_subdev *sd, u16 fpaddr)
 {
 	struct i2c_client *client = v4l2_get_subdevdata(sd);
 	s16 data;
diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c
index 7dae0ac0f3ae..6e43c95629ea 100644
--- a/drivers/media/media-device.c
+++ b/drivers/media/media-device.c
@@ -20,6 +20,9 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+/* We need to access legacy defines from linux/media.h */
+#define __NEED_MEDIA_LEGACY_API
+
 #include <linux/compat.h>
 #include <linux/export.h>
 #include <linux/idr.h>
@@ -27,6 +30,8 @@
 #include <linux/media.h>
 #include <linux/slab.h>
 #include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/usb.h>
 
 #include <media/media-device.h>
 #include <media/media-devnode.h>
@@ -38,6 +43,11 @@
  * Userspace API
  */
 
+static inline void __user *media_get_uptr(__u64 arg)
+{
+	return (void __user *)(uintptr_t)arg;
+}
+
 static int media_device_open(struct file *filp)
 {
 	return 0;
@@ -55,7 +65,11 @@ static int media_device_get_info(struct media_device *dev,
 
 	memset(&info, 0, sizeof(info));
 
-	strlcpy(info.driver, dev->dev->driver->name, sizeof(info.driver));
+	if (dev->driver_name[0])
+		strlcpy(info.driver, dev->driver_name, sizeof(info.driver));
+	else
+		strlcpy(info.driver, dev->dev->driver->name, sizeof(info.driver));
+
 	strlcpy(info.model, dev->model, sizeof(info.model));
 	strlcpy(info.serial, dev->serial, sizeof(info.serial));
 	strlcpy(info.bus_info, dev->bus_info, sizeof(info.bus_info));
@@ -115,6 +129,26 @@ static long media_device_enum_entities(struct media_device *mdev,
 	u_ent.group_id = 0;		/* Unused */
 	u_ent.pads = ent->num_pads;
 	u_ent.links = ent->num_links - ent->num_backlinks;
+
+	/*
+	 * Workaround for a bug at media-ctl <= v1.10 that makes it to
+	 * do the wrong thing if the entity function doesn't belong to
+	 * either MEDIA_ENT_F_OLD_BASE or MEDIA_ENT_F_OLD_SUBDEV_BASE
+	 * Ranges.
+	 *
+	 * Non-subdevices are expected to be at the MEDIA_ENT_F_OLD_BASE,
+	 * or, otherwise, will be silently ignored by media-ctl when
+	 * printing the graphviz diagram. So, map them into the devnode
+	 * old range.
+	 */
+	if (ent->function < MEDIA_ENT_F_OLD_BASE ||
+	    ent->function > MEDIA_ENT_T_DEVNODE_UNKNOWN) {
+		if (is_media_entity_v4l2_subdev(ent))
+			u_ent.type = MEDIA_ENT_F_V4L2_SUBDEV_UNKNOWN;
+		else if (ent->function != MEDIA_ENT_F_IO_V4L)
+			u_ent.type = MEDIA_ENT_T_DEVNODE_UNKNOWN;
+	}
+
 	memcpy(&u_ent.raw, &ent->info, sizeof(ent->info));
 	if (copy_to_user(uent, &u_ent, sizeof(u_ent)))
 		return -EFAULT;
@@ -234,7 +268,6 @@ static long media_device_setup_link(struct media_device *mdev,
 	return ret;
 }
 
-#if 0 /* Let's postpone it to Kernel 4.6 */
 static long __media_device_get_topology(struct media_device *mdev,
 				      struct media_v2_topology *topo)
 {
@@ -242,10 +275,10 @@ static long __media_device_get_topology(struct media_device *mdev,
 	struct media_interface *intf;
 	struct media_pad *pad;
 	struct media_link *link;
-	struct media_v2_entity kentity, *uentity;
-	struct media_v2_interface kintf, *uintf;
-	struct media_v2_pad kpad, *upad;
-	struct media_v2_link klink, *ulink;
+	struct media_v2_entity kentity, __user *uentity;
+	struct media_v2_interface kintf, __user *uintf;
+	struct media_v2_pad kpad, __user *upad;
+	struct media_v2_link klink, __user *ulink;
 	unsigned int i;
 	int ret = 0;
 
@@ -390,7 +423,6 @@ static long media_device_get_topology(struct media_device *mdev,
 
 	return 0;
 }
-#endif
 
 static long media_device_ioctl(struct file *filp, unsigned int cmd,
 			       unsigned long arg)
@@ -424,14 +456,13 @@ static long media_device_ioctl(struct file *filp, unsigned int cmd,
 		mutex_unlock(&dev->graph_mutex);
 		break;
 
-#if 0 /* Let's postpone it to Kernel 4.6 */
 	case MEDIA_IOC_G_TOPOLOGY:
 		mutex_lock(&dev->graph_mutex);
 		ret = media_device_get_topology(dev,
 				(struct media_v2_topology __user *)arg);
 		mutex_unlock(&dev->graph_mutex);
 		break;
-#endif
+
 	default:
 		ret = -ENOIOCTLCMD;
 	}
@@ -480,9 +511,7 @@ static long media_device_compat_ioctl(struct file *filp, unsigned int cmd,
 	case MEDIA_IOC_DEVICE_INFO:
 	case MEDIA_IOC_ENUM_ENTITIES:
 	case MEDIA_IOC_SETUP_LINK:
-#if 0 /* Let's postpone it to Kernel 4.6 */
 	case MEDIA_IOC_G_TOPOLOGY:
-#endif
 		return media_device_ioctl(filp, cmd, arg);
 
 	case MEDIA_IOC_ENUM_LINKS32:
@@ -541,6 +570,7 @@ static void media_device_release(struct media_devnode *mdev)
 int __must_check media_device_register_entity(struct media_device *mdev,
 					      struct media_entity *entity)
 {
+	struct media_entity_notify *notify, *next;
 	unsigned int i;
 	int ret;
 
@@ -580,8 +610,33 @@ int __must_check media_device_register_entity(struct media_device *mdev,
 		media_gobj_create(mdev, MEDIA_GRAPH_PAD,
 			       &entity->pads[i].graph_obj);
 
+	/* invoke entity_notify callbacks */
+	list_for_each_entry_safe(notify, next, &mdev->entity_notify, list) {
+		(notify)->notify(entity, notify->notify_data);
+	}
+
 	spin_unlock(&mdev->lock);
 
+	mutex_lock(&mdev->graph_mutex);
+	if (mdev->entity_internal_idx_max
+	    >= mdev->pm_count_walk.ent_enum.idx_max) {
+		struct media_entity_graph new = { .top = 0 };
+
+		/*
+		 * Initialise the new graph walk before cleaning up
+		 * the old one in order not to spoil the graph walk
+		 * object of the media device if graph walk init fails.
+		 */
+		ret = media_entity_graph_walk_init(&new, mdev);
+		if (ret) {
+			mutex_unlock(&mdev->graph_mutex);
+			return ret;
+		}
+		media_entity_graph_walk_cleanup(&mdev->pm_count_walk);
+		mdev->pm_count_walk = new;
+	}
+	mutex_unlock(&mdev->graph_mutex);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(media_device_register_entity);
@@ -613,6 +668,8 @@ static void __media_device_unregister_entity(struct media_entity *entity)
 	/* Remove the entity */
 	media_gobj_destroy(&entity->graph_obj);
 
+	/* invoke entity_notify callbacks to handle entity removal?? */
+
 	entity->graph_obj.mdev = NULL;
 }
 
@@ -645,6 +702,7 @@ void media_device_init(struct media_device *mdev)
 	INIT_LIST_HEAD(&mdev->interfaces);
 	INIT_LIST_HEAD(&mdev->pads);
 	INIT_LIST_HEAD(&mdev->links);
+	INIT_LIST_HEAD(&mdev->entity_notify);
 	spin_lock_init(&mdev->lock);
 	mutex_init(&mdev->graph_mutex);
 	ida_init(&mdev->entity_internal_idx);
@@ -657,6 +715,7 @@ void media_device_cleanup(struct media_device *mdev)
 {
 	ida_destroy(&mdev->entity_internal_idx);
 	mdev->entity_internal_idx_max = 0;
+	media_entity_graph_walk_cleanup(&mdev->pm_count_walk);
 	mutex_destroy(&mdev->graph_mutex);
 }
 EXPORT_SYMBOL_GPL(media_device_cleanup);
@@ -690,11 +749,40 @@ int __must_check __media_device_register(struct media_device *mdev,
 }
 EXPORT_SYMBOL_GPL(__media_device_register);
 
+int __must_check media_device_register_entity_notify(struct media_device *mdev,
+					struct media_entity_notify *nptr)
+{
+	spin_lock(&mdev->lock);
+	list_add_tail(&nptr->list, &mdev->entity_notify);
+	spin_unlock(&mdev->lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(media_device_register_entity_notify);
+
+/*
+ * Note: Should be called with mdev->lock held.
+ */
+static void __media_device_unregister_entity_notify(struct media_device *mdev,
+					struct media_entity_notify *nptr)
+{
+	list_del(&nptr->list);
+}
+
+void media_device_unregister_entity_notify(struct media_device *mdev,
+					struct media_entity_notify *nptr)
+{
+	spin_lock(&mdev->lock);
+	__media_device_unregister_entity_notify(mdev, nptr);
+	spin_unlock(&mdev->lock);
+}
+EXPORT_SYMBOL_GPL(media_device_unregister_entity_notify);
+
 void media_device_unregister(struct media_device *mdev)
 {
 	struct media_entity *entity;
 	struct media_entity *next;
 	struct media_interface *intf, *tmp_intf;
+	struct media_entity_notify *notify, *nextp;
 
 	if (mdev == NULL)
 		return;
@@ -711,6 +799,10 @@ void media_device_unregister(struct media_device *mdev)
 	list_for_each_entry_safe(entity, next, &mdev->entities, graph_obj.list)
 		__media_device_unregister_entity(entity);
 
+	/* Remove all entity_notify callbacks from the media device */
+	list_for_each_entry_safe(notify, nextp, &mdev->entity_notify, list)
+		__media_device_unregister_entity_notify(mdev, notify);
+
 	/* Remove all interfaces from the media device */
 	list_for_each_entry_safe(intf, tmp_intf, &mdev->interfaces,
 				 graph_obj.list) {
@@ -754,4 +846,58 @@ struct media_device *media_device_find_devres(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(media_device_find_devres);
 
+void media_device_pci_init(struct media_device *mdev,
+			   struct pci_dev *pci_dev,
+			   const char *name)
+{
+#ifdef CONFIG_PCI
+	mdev->dev = &pci_dev->dev;
+
+	if (name)
+		strlcpy(mdev->model, name, sizeof(mdev->model));
+	else
+		strlcpy(mdev->model, pci_name(pci_dev), sizeof(mdev->model));
+
+	sprintf(mdev->bus_info, "PCI:%s", pci_name(pci_dev));
+
+	mdev->hw_revision = (pci_dev->subsystem_vendor << 16)
+			    | pci_dev->subsystem_device;
+
+	mdev->driver_version = LINUX_VERSION_CODE;
+
+	media_device_init(mdev);
+#endif
+}
+EXPORT_SYMBOL_GPL(media_device_pci_init);
+
+void __media_device_usb_init(struct media_device *mdev,
+			     struct usb_device *udev,
+			     const char *board_name,
+			     const char *driver_name)
+{
+#ifdef CONFIG_USB
+	mdev->dev = &udev->dev;
+
+	if (driver_name)
+		strlcpy(mdev->driver_name, driver_name,
+			sizeof(mdev->driver_name));
+
+	if (board_name)
+		strlcpy(mdev->model, board_name, sizeof(mdev->model));
+	else if (udev->product)
+		strlcpy(mdev->model, udev->product, sizeof(mdev->model));
+	else
+		strlcpy(mdev->model, "unknown model", sizeof(mdev->model));
+	if (udev->serial)
+		strlcpy(mdev->serial, udev->serial, sizeof(mdev->serial));
+	usb_make_path(udev, mdev->bus_info, sizeof(mdev->bus_info));
+	mdev->hw_revision = le16_to_cpu(udev->descriptor.bcdDevice);
+	mdev->driver_version = LINUX_VERSION_CODE;
+
+	media_device_init(mdev);
+#endif
+}
+EXPORT_SYMBOL_GPL(__media_device_usb_init);
+
+
 #endif /* CONFIG_MEDIA_CONTROLLER */
diff --git a/drivers/media/media-devnode.c b/drivers/media/media-devnode.c
index cea35bf20011..29409f440f1c 100644
--- a/drivers/media/media-devnode.c
+++ b/drivers/media/media-devnode.c
@@ -181,6 +181,7 @@ static int media_open(struct inode *inode, struct file *filp)
 		ret = mdev->fops->open(filp);
 		if (ret) {
 			put_device(&mdev->dev);
+			filp->private_data = NULL;
 			return ret;
 		}
 	}
diff --git a/drivers/media/media-entity.c b/drivers/media/media-entity.c
index e89d85a7d31b..e95070b3a3d4 100644
--- a/drivers/media/media-entity.c
+++ b/drivers/media/media-entity.c
@@ -46,25 +46,41 @@ static inline const char *intf_type(struct media_interface *intf)
 {
 	switch (intf->type) {
 	case MEDIA_INTF_T_DVB_FE:
-		return "frontend";
+		return "dvb-frontend";
 	case MEDIA_INTF_T_DVB_DEMUX:
-		return "demux";
+		return "dvb-demux";
 	case MEDIA_INTF_T_DVB_DVR:
-		return "DVR";
+		return "dvb-dvr";
 	case MEDIA_INTF_T_DVB_CA:
-		return  "CA";
+		return  "dvb-ca";
 	case MEDIA_INTF_T_DVB_NET:
-		return "dvbnet";
+		return "dvb-net";
 	case MEDIA_INTF_T_V4L_VIDEO:
-		return "video";
+		return "v4l-video";
 	case MEDIA_INTF_T_V4L_VBI:
-		return "vbi";
+		return "v4l-vbi";
 	case MEDIA_INTF_T_V4L_RADIO:
-		return "radio";
+		return "v4l-radio";
 	case MEDIA_INTF_T_V4L_SUBDEV:
-		return "v4l2-subdev";
+		return "v4l-subdev";
 	case MEDIA_INTF_T_V4L_SWRADIO:
-		return "swradio";
+		return "v4l-swradio";
+	case MEDIA_INTF_T_ALSA_PCM_CAPTURE:
+		return "alsa-pcm-capture";
+	case MEDIA_INTF_T_ALSA_PCM_PLAYBACK:
+		return "alsa-pcm-playback";
+	case MEDIA_INTF_T_ALSA_CONTROL:
+		return "alsa-control";
+	case MEDIA_INTF_T_ALSA_COMPRESS:
+		return "alsa-compress";
+	case MEDIA_INTF_T_ALSA_RAWMIDI:
+		return "alsa-rawmidi";
+	case MEDIA_INTF_T_ALSA_HWDEP:
+		return "alsa-hwdep";
+	case MEDIA_INTF_T_ALSA_SEQUENCER:
+		return "alsa-sequencer";
+	case MEDIA_INTF_T_ALSA_TIMER:
+		return "alsa-timer";
 	default:
 		return "unknown-intf";
 	}
@@ -73,8 +89,9 @@ static inline const char *intf_type(struct media_interface *intf)
 __must_check int __media_entity_enum_init(struct media_entity_enum *ent_enum,
 					  int idx_max)
 {
-	ent_enum->bmap = kcalloc(DIV_ROUND_UP(idx_max, BITS_PER_LONG),
-				 sizeof(long), GFP_KERNEL);
+	idx_max = ALIGN(idx_max, BITS_PER_LONG);
+	ent_enum->bmap = kcalloc(idx_max / BITS_PER_LONG, sizeof(long),
+				 GFP_KERNEL);
 	if (!ent_enum->bmap)
 		return -ENOMEM;
 
@@ -349,8 +366,8 @@ EXPORT_SYMBOL_GPL(media_entity_graph_walk_next);
  * Pipeline management
  */
 
-__must_check int media_entity_pipeline_start(struct media_entity *entity,
-					     struct media_pipeline *pipe)
+__must_check int __media_entity_pipeline_start(struct media_entity *entity,
+					       struct media_pipeline *pipe)
 {
 	struct media_device *mdev = entity->graph_obj.mdev;
 	struct media_entity_graph *graph = &pipe->graph;
@@ -358,8 +375,6 @@ __must_check int media_entity_pipeline_start(struct media_entity *entity,
 	struct media_link *link;
 	int ret;
 
-	mutex_lock(&mdev->graph_mutex);
-
 	if (!pipe->streaming_count++) {
 		ret = media_entity_graph_walk_init(&pipe->graph, mdev);
 		if (ret)
@@ -440,8 +455,6 @@ __must_check int media_entity_pipeline_start(struct media_entity *entity,
 		}
 	}
 
-	mutex_unlock(&mdev->graph_mutex);
-
 	return 0;
 
 error:
@@ -452,9 +465,12 @@ error:
 	media_entity_graph_walk_start(graph, entity_err);
 
 	while ((entity_err = media_entity_graph_walk_next(graph))) {
-		entity_err->stream_count--;
-		if (entity_err->stream_count == 0)
-			entity_err->pipe = NULL;
+		/* don't let the stream_count go negative */
+		if (entity->stream_count > 0) {
+			entity_err->stream_count--;
+			if (entity_err->stream_count == 0)
+				entity_err->pipe = NULL;
+		}
 
 		/*
 		 * We haven't increased stream_count further than this
@@ -468,32 +484,53 @@ error_graph_walk_start:
 	if (!--pipe->streaming_count)
 		media_entity_graph_walk_cleanup(graph);
 
-	mutex_unlock(&mdev->graph_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(__media_entity_pipeline_start);
 
+__must_check int media_entity_pipeline_start(struct media_entity *entity,
+					     struct media_pipeline *pipe)
+{
+	struct media_device *mdev = entity->graph_obj.mdev;
+	int ret;
+
+	mutex_lock(&mdev->graph_mutex);
+	ret = __media_entity_pipeline_start(entity, pipe);
+	mutex_unlock(&mdev->graph_mutex);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(media_entity_pipeline_start);
 
-void media_entity_pipeline_stop(struct media_entity *entity)
+void __media_entity_pipeline_stop(struct media_entity *entity)
 {
-	struct media_device *mdev = entity->graph_obj.mdev;
 	struct media_entity_graph *graph = &entity->pipe->graph;
 	struct media_pipeline *pipe = entity->pipe;
 
-	mutex_lock(&mdev->graph_mutex);
 
 	WARN_ON(!pipe->streaming_count);
 	media_entity_graph_walk_start(graph, entity);
 
 	while ((entity = media_entity_graph_walk_next(graph))) {
-		entity->stream_count--;
-		if (entity->stream_count == 0)
-			entity->pipe = NULL;
+		/* don't let the stream_count go negative */
+		if (entity->stream_count > 0) {
+			entity->stream_count--;
+			if (entity->stream_count == 0)
+				entity->pipe = NULL;
+		}
 	}
 
 	if (!--pipe->streaming_count)
 		media_entity_graph_walk_cleanup(graph);
 
+}
+EXPORT_SYMBOL_GPL(__media_entity_pipeline_stop);
+
+void media_entity_pipeline_stop(struct media_entity *entity)
+{
+	struct media_device *mdev = entity->graph_obj.mdev;
+
+	mutex_lock(&mdev->graph_mutex);
+	__media_entity_pipeline_stop(entity);
 	mutex_unlock(&mdev->graph_mutex);
 }
 EXPORT_SYMBOL_GPL(media_entity_pipeline_stop);
@@ -783,6 +820,7 @@ int __media_entity_setup_link(struct media_link *link, u32 flags)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(__media_entity_setup_link);
 
 int media_entity_setup_link(struct media_link *link, u32 flags)
 {
diff --git a/drivers/media/pci/b2c2/flexcop-pci.c b/drivers/media/pci/b2c2/flexcop-pci.c
index 8b5e0b3a92a0..4cac1fc233f2 100644
--- a/drivers/media/pci/b2c2/flexcop-pci.c
+++ b/drivers/media/pci/b2c2/flexcop-pci.c
@@ -39,7 +39,7 @@ MODULE_PARM_DESC(debug,
 
 #define DRIVER_VERSION "0.1"
 #define DRIVER_NAME "flexcop-pci"
-#define DRIVER_AUTHOR "Patrick Boettcher <patrick.boettcher@desy.de>"
+#define DRIVER_AUTHOR "Patrick Boettcher <patrick.boettcher@posteo.de>"
 
 struct flexcop_pci {
 	struct pci_dev *pdev;
diff --git a/drivers/media/pci/bt8xx/bttv-driver.c b/drivers/media/pci/bt8xx/bttv-driver.c
index 9400e996087b..df54e17ef864 100644
--- a/drivers/media/pci/bt8xx/bttv-driver.c
+++ b/drivers/media/pci/bt8xx/bttv-driver.c
@@ -186,7 +186,7 @@ MODULE_VERSION(BTTV_VERSION);
 static ssize_t show_card(struct device *cd,
 			 struct device_attribute *attr, char *buf)
 {
-	struct video_device *vfd = container_of(cd, struct video_device, dev);
+	struct video_device *vfd = to_video_device(cd);
 	struct bttv *btv = video_get_drvdata(vfd);
 	return sprintf(buf, "%d\n", btv ? btv->c.type : UNSET);
 }
@@ -1726,22 +1726,15 @@ static int bttv_s_std(struct file *file, void *priv, v4l2_std_id id)
 	struct bttv_fh *fh  = priv;
 	struct bttv *btv = fh->btv;
 	unsigned int i;
-	int err = 0;
 
 	for (i = 0; i < BTTV_TVNORMS; i++)
 		if (id & bttv_tvnorms[i].v4l2_id)
 			break;
-	if (i == BTTV_TVNORMS) {
-		err = -EINVAL;
-		goto err;
-	}
-
+	if (i == BTTV_TVNORMS)
+		return -EINVAL;
 	btv->std = id;
 	set_tvnorm(btv, i);
-
-err:
-
-	return err;
+	return 0;
 }
 
 static int bttv_g_std(struct file *file, void *priv, v4l2_std_id *id)
@@ -1770,12 +1763,9 @@ static int bttv_enum_input(struct file *file, void *priv,
 {
 	struct bttv_fh *fh = priv;
 	struct bttv *btv = fh->btv;
-	int rc = 0;
 
-	if (i->index >= bttv_tvcards[btv->c.type].video_inputs) {
-		rc = -EINVAL;
-		goto err;
-	}
+	if (i->index >= bttv_tvcards[btv->c.type].video_inputs)
+		return -EINVAL;
 
 	i->type     = V4L2_INPUT_TYPE_CAMERA;
 	i->audioset = 0;
@@ -1799,10 +1789,7 @@ static int bttv_enum_input(struct file *file, void *priv,
 	}
 
 	i->std = BTTV_NORMS;
-
-err:
-
-	return rc;
+	return 0;
 }
 
 static int bttv_g_input(struct file *file, void *priv, unsigned int *i)
@@ -2334,6 +2321,19 @@ static int bttv_g_fmt_vid_overlay(struct file *file, void *priv,
 	return 0;
 }
 
+static void bttv_get_width_mask_vid_cap(const struct bttv_format *fmt,
+					unsigned int *width_mask,
+					unsigned int *width_bias)
+{
+	if (fmt->flags & FORMAT_FLAGS_PLANAR) {
+		*width_mask = ~15; /* width must be a multiple of 16 pixels */
+		*width_bias = 8;   /* nearest */
+	} else {
+		*width_mask = ~3; /* width must be a multiple of 4 pixels */
+		*width_bias = 2;  /* nearest */
+	}
+}
+
 static int bttv_try_fmt_vid_cap(struct file *file, void *priv,
 						struct v4l2_format *f)
 {
@@ -2343,6 +2343,7 @@ static int bttv_try_fmt_vid_cap(struct file *file, void *priv,
 	enum v4l2_field field;
 	__s32 width, height;
 	__s32 height2;
+	unsigned int width_mask, width_bias;
 	int rc;
 
 	fmt = format_by_fourcc(f->fmt.pix.pixelformat);
@@ -2375,9 +2376,9 @@ static int bttv_try_fmt_vid_cap(struct file *file, void *priv,
 	width = f->fmt.pix.width;
 	height = f->fmt.pix.height;
 
+	bttv_get_width_mask_vid_cap(fmt, &width_mask, &width_bias);
 	rc = limit_scaled_size_lock(fh, &width, &height, field,
-			       /* width_mask: 4 pixels */ ~3,
-			       /* width_bias: nearest */ 2,
+			       width_mask, width_bias,
 			       /* adjust_size */ 1,
 			       /* adjust_crop */ 0);
 	if (0 != rc)
@@ -2410,6 +2411,7 @@ static int bttv_s_fmt_vid_cap(struct file *file, void *priv,
 	struct bttv_fh *fh = priv;
 	struct bttv *btv = fh->btv;
 	__s32 width, height;
+	unsigned int width_mask, width_bias;
 	enum v4l2_field field;
 
 	retval = bttv_switch_type(fh, f->type);
@@ -2424,9 +2426,10 @@ static int bttv_s_fmt_vid_cap(struct file *file, void *priv,
 	height = f->fmt.pix.height;
 	field = f->fmt.pix.field;
 
+	fmt = format_by_fourcc(f->fmt.pix.pixelformat);
+	bttv_get_width_mask_vid_cap(fmt, &width_mask, &width_bias);
 	retval = limit_scaled_size_lock(fh, &width, &height, f->fmt.pix.field,
-			       /* width_mask: 4 pixels */ ~3,
-			       /* width_bias: nearest */ 2,
+			       width_mask, width_bias,
 			       /* adjust_size */ 1,
 			       /* adjust_crop */ 1);
 	if (0 != retval)
@@ -2434,8 +2437,6 @@ static int bttv_s_fmt_vid_cap(struct file *file, void *priv,
 
 	f->fmt.pix.field = field;
 
-	fmt = format_by_fourcc(f->fmt.pix.pixelformat);
-
 	/* update our state informations */
 	fh->fmt              = fmt;
 	fh->cap.field        = f->fmt.pix.field;
diff --git a/drivers/media/pci/bt8xx/dst.c b/drivers/media/pci/bt8xx/dst.c
index 4a90eee5e3bb..35bc9b2287b4 100644
--- a/drivers/media/pci/bt8xx/dst.c
+++ b/drivers/media/pci/bt8xx/dst.c
@@ -1688,9 +1688,9 @@ static int dst_get_tuning_algo(struct dvb_frontend *fe)
 	return dst_algo ? DVBFE_ALGO_HW : DVBFE_ALGO_SW;
 }
 
-static int dst_get_frontend(struct dvb_frontend *fe)
+static int dst_get_frontend(struct dvb_frontend *fe,
+			    struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct dst_state *state = fe->demodulator_priv;
 
 	p->frequency = state->decode_freq;
diff --git a/drivers/media/pci/bt8xx/dvb-bt8xx.c b/drivers/media/pci/bt8xx/dvb-bt8xx.c
index d407244fd1bc..e69d338ab9be 100644
--- a/drivers/media/pci/bt8xx/dvb-bt8xx.c
+++ b/drivers/media/pci/bt8xx/dvb-bt8xx.c
@@ -318,7 +318,7 @@ static int microtune_mt7202dtf_request_firmware(struct dvb_frontend* fe, const s
 	return request_firmware(fw, name, &bt->bt->dev->dev);
 }
 
-static struct sp887x_config microtune_mt7202dtf_config = {
+static const struct sp887x_config microtune_mt7202dtf_config = {
 	.demod_address = 0x70,
 	.request_firmware = microtune_mt7202dtf_request_firmware,
 };
@@ -458,7 +458,7 @@ static void or51211_sleep(struct dvb_frontend * fe)
 	bttv_write_gpio(bt->bttv_nr, 0x0001, 0x0000);
 }
 
-static struct or51211_config or51211_config = {
+static const struct or51211_config or51211_config = {
 	.demod_address = 0x15,
 	.request_firmware = or51211_request_firmware,
 	.setmode = or51211_setmode,
diff --git a/drivers/media/pci/cx23885/cx23885-dvb.c b/drivers/media/pci/cx23885/cx23885-dvb.c
index 80319bb73d94..f041b6931ba8 100644
--- a/drivers/media/pci/cx23885/cx23885-dvb.c
+++ b/drivers/media/pci/cx23885/cx23885-dvb.c
@@ -1139,7 +1139,7 @@ static int dvb_register_ci_mac(struct cx23885_tsport *port)
 		u8 eeprom[256]; /* 24C02 i2c eeprom */
 		struct sp2_config sp2_config;
 		struct i2c_board_info info;
-		struct cx23885_i2c *i2c_bus2 = &dev->i2c_bus[1];
+		struct cx23885_i2c *i2c_bus = &dev->i2c_bus[0];
 
 		/* attach CI */
 		memset(&sp2_config, 0, sizeof(sp2_config));
@@ -1151,7 +1151,7 @@ static int dvb_register_ci_mac(struct cx23885_tsport *port)
 		info.addr = 0x40;
 		info.platform_data = &sp2_config;
 		request_module(info.type);
-		client_ci = i2c_new_device(&i2c_bus2->i2c_adap, &info);
+		client_ci = i2c_new_device(&i2c_bus->i2c_adap, &info);
 		if (client_ci == NULL || client_ci->dev.driver == NULL)
 			return -ENODEV;
 		if (!try_module_get(client_ci->dev.driver->owner)) {
@@ -1988,8 +1988,8 @@ static int dvb_register(struct cx23885_tsport *port)
 		break;
 	case CX23885_BOARD_DVBSKY_T980C:
 	case CX23885_BOARD_TT_CT2_4500_CI:
-		i2c_bus = &dev->i2c_bus[1];
-		i2c_bus2 = &dev->i2c_bus[0];
+		i2c_bus = &dev->i2c_bus[0];
+		i2c_bus2 = &dev->i2c_bus[1];
 
 		/* attach frontend */
 		memset(&si2168_config, 0, sizeof(si2168_config));
@@ -2001,7 +2001,7 @@ static int dvb_register(struct cx23885_tsport *port)
 		info.addr = 0x64;
 		info.platform_data = &si2168_config;
 		request_module(info.type);
-		client_demod = i2c_new_device(&i2c_bus->i2c_adap, &info);
+		client_demod = i2c_new_device(&i2c_bus2->i2c_adap, &info);
 		if (client_demod == NULL || client_demod->dev.driver == NULL)
 			goto frontend_detach;
 		if (!try_module_get(client_demod->dev.driver->owner)) {
@@ -2030,13 +2030,13 @@ static int dvb_register(struct cx23885_tsport *port)
 		port->i2c_client_tuner = client_tuner;
 		break;
 	case CX23885_BOARD_DVBSKY_S950C:
-		i2c_bus = &dev->i2c_bus[1];
-		i2c_bus2 = &dev->i2c_bus[0];
+		i2c_bus = &dev->i2c_bus[0];
+		i2c_bus2 = &dev->i2c_bus[1];
 
 		/* attach frontend */
 		fe0->dvb.frontend = dvb_attach(m88ds3103_attach,
 				&dvbsky_s950c_m88ds3103_config,
-				&i2c_bus->i2c_adap, &adapter);
+				&i2c_bus2->i2c_adap, &adapter);
 		if (fe0->dvb.frontend == NULL)
 			break;
 
@@ -2301,7 +2301,8 @@ static int dvb_register(struct cx23885_tsport *port)
 
 	/* register everything */
 	ret = vb2_dvb_register_bus(&port->frontends, THIS_MODULE, port,
-					&dev->pci->dev, adapter_nr, mfe_shared);
+				   &dev->pci->dev, NULL,
+				   adapter_nr, mfe_shared);
 	if (ret)
 		goto frontend_detach;
 
diff --git a/drivers/media/pci/cx88/cx88-dvb.c b/drivers/media/pci/cx88/cx88-dvb.c
index afb20756d7a5..851d2a9caed3 100644
--- a/drivers/media/pci/cx88/cx88-dvb.c
+++ b/drivers/media/pci/cx88/cx88-dvb.c
@@ -1642,7 +1642,8 @@ static int dvb_register(struct cx8802_dev *dev)
 
 	/* register everything */
 	res = vb2_dvb_register_bus(&dev->frontends, THIS_MODULE, dev,
-		&dev->pci->dev, adapter_nr, mfe_shared);
+				   &dev->pci->dev, NULL, adapter_nr,
+				   mfe_shared);
 	if (res)
 		goto frontend_detach;
 	return res;
diff --git a/drivers/media/pci/ddbridge/ddbridge-core.c b/drivers/media/pci/ddbridge/ddbridge-core.c
index 9d5b314142f1..6e995ef8c37e 100644
--- a/drivers/media/pci/ddbridge/ddbridge-core.c
+++ b/drivers/media/pci/ddbridge/ddbridge-core.c
@@ -690,7 +690,7 @@ static int tuner_attach_stv6110(struct ddb_input *input, int type)
 	struct stv090x_config *feconf = type ? &stv0900_aa : &stv0900;
 	struct stv6110x_config *tunerconf = (input->nr & 1) ?
 		&stv6110b : &stv6110a;
-	struct stv6110x_devctl *ctl;
+	const struct stv6110x_devctl *ctl;
 
 	ctl = dvb_attach(stv6110x_attach, input->fe, tunerconf, i2c);
 	if (!ctl) {
diff --git a/drivers/media/pci/ivtv/ivtv-queue.c b/drivers/media/pci/ivtv/ivtv-queue.c
index 7fde36e6d227..2128c2a8d7fd 100644
--- a/drivers/media/pci/ivtv/ivtv-queue.c
+++ b/drivers/media/pci/ivtv/ivtv-queue.c
@@ -141,7 +141,7 @@ int ivtv_queue_move(struct ivtv_stream *s, struct ivtv_queue *from, struct ivtv_
 		spin_unlock_irqrestore(&s->qlock, flags);
 		return -ENOMEM;
 	}
-	while (bytes_available < needed_bytes) {
+	while (steal && bytes_available < needed_bytes) {
 		struct ivtv_buffer *buf = list_entry(steal->list.prev, struct ivtv_buffer, list);
 		u16 dma_xfer_cnt = buf->dma_xfer_cnt;
 
diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c
index 525ebfefeee8..2b667b315913 100644
--- a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c
+++ b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c
@@ -462,8 +462,8 @@ static int netup_unidvb_dvb_init(struct netup_unidvb_dev *ndev,
 	}
 
 	if (vb2_dvb_register_bus(&ndev->frontends[num],
-			THIS_MODULE, NULL,
-			&ndev->pci_dev->dev, adapter_nr, 1)) {
+				 THIS_MODULE, NULL,
+				 &ndev->pci_dev->dev, NULL, adapter_nr, 1)) {
 		dev_dbg(&ndev->pci_dev->dev,
 			"%s(): unable to register DVB bus %d\n",
 			__func__, num);
@@ -771,10 +771,9 @@ static int netup_unidvb_initdev(struct pci_dev *pci_dev,
 
 	/* allocate device context */
 	ndev = kzalloc(sizeof(*ndev), GFP_KERNEL);
-
 	if (!ndev)
 		goto dev_alloc_err;
-	memset(ndev, 0, sizeof(*ndev));
+
 	ndev->old_fw = old_firmware;
 	ndev->wq = create_singlethread_workqueue(NETUP_UNIDVB_NAME);
 	if (!ndev->wq) {
diff --git a/drivers/media/pci/ngene/ngene-cards.c b/drivers/media/pci/ngene/ngene-cards.c
index 039bed3cc919..4e783a68bf4a 100644
--- a/drivers/media/pci/ngene/ngene-cards.c
+++ b/drivers/media/pci/ngene/ngene-cards.c
@@ -57,7 +57,7 @@ static int tuner_attach_stv6110(struct ngene_channel *chan)
 		chan->dev->card_info->fe_config[chan->number];
 	struct stv6110x_config *tunerconf = (struct stv6110x_config *)
 		chan->dev->card_info->tuner_config[chan->number];
-	struct stv6110x_devctl *ctl;
+	const struct stv6110x_devctl *ctl;
 
 	/* tuner 1+2: i2c adapter #0, tuner 3+4: i2c adapter #1 */
 	if (chan->number < 2)
diff --git a/drivers/media/pci/pt3/pt3.c b/drivers/media/pci/pt3/pt3.c
index 0d2e2b217121..eff5e9f51ace 100644
--- a/drivers/media/pci/pt3/pt3.c
+++ b/drivers/media/pci/pt3/pt3.c
@@ -395,7 +395,8 @@ static int pt3_attach_fe(struct pt3_board *pt3, int i)
 	if (!try_module_get(cl->dev.driver->owner))
 		goto err_demod_i2c_unregister_device;
 
-	if (!strncmp(cl->name, TC90522_I2C_DEV_SAT, sizeof(cl->name))) {
+	if (!strncmp(cl->name, TC90522_I2C_DEV_SAT,
+		     strlen(TC90522_I2C_DEV_SAT))) {
 		struct qm1d1c0042_config tcfg;
 
 		tcfg = adap_conf[i].tuner_cfg.qm1d1c0042;
diff --git a/drivers/media/pci/saa7134/saa7134-cards.c b/drivers/media/pci/saa7134/saa7134-cards.c
index 29d2094c42a0..c480a7e87593 100644
--- a/drivers/media/pci/saa7134/saa7134-cards.c
+++ b/drivers/media/pci/saa7134/saa7134-cards.c
@@ -36,17 +36,23 @@
 #include "xc5000.h"
 #include "s5h1411.h"
 
-/* commly used strings */
-static char name_mute[]    = "mute";
-static char name_radio[]   = "Radio";
-static char name_tv[]      = "Television";
-static char name_tv_mono[] = "TV (mono only)";
-static char name_comp[]    = "Composite";
-static char name_comp1[]   = "Composite1";
-static char name_comp2[]   = "Composite2";
-static char name_comp3[]   = "Composite3";
-static char name_comp4[]   = "Composite4";
-static char name_svideo[]  = "S-Video";
+/* Input names */
+const char * const saa7134_input_name[] = {
+	[SAA7134_INPUT_MUTE]       = "mute",
+	[SAA7134_INPUT_RADIO]      = "Radio",
+	[SAA7134_INPUT_TV]         = "Television",
+	[SAA7134_INPUT_TV_MONO]    = "TV (mono only)",
+	[SAA7134_INPUT_COMPOSITE]  = "Composite",
+	[SAA7134_INPUT_COMPOSITE0] = "Composite0",
+	[SAA7134_INPUT_COMPOSITE1] = "Composite1",
+	[SAA7134_INPUT_COMPOSITE2] = "Composite2",
+	[SAA7134_INPUT_COMPOSITE3] = "Composite3",
+	[SAA7134_INPUT_COMPOSITE4] = "Composite4",
+	[SAA7134_INPUT_SVIDEO]     = "S-Video",
+	[SAA7134_INPUT_SVIDEO0]    = "S-Video0",
+	[SAA7134_INPUT_SVIDEO1]    = "S-Video1",
+	[SAA7134_INPUT_COMPOSITE_OVER_SVIDEO] = "Composite over S-Video",
+};
 
 /* ------------------------------------------------------------------ */
 /* board config info                                                  */
@@ -69,7 +75,7 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 
 		.inputs         = {{
-			.name = "default",
+			.type = SAA7134_INPUT_COMPOSITE,
 			.vmux = 0,
 			.amux = LINE1,
 		}},
@@ -84,22 +90,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 
 		.inputs         = {{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE1,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -114,40 +118,38 @@ struct saa7134_board saa7134_boards[] = {
 
 		.gpiomask       = 0xe000,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
 			.gpio = 0x8000,
-			.tv   = 1,
 		},{
-			.name = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 1,
 			.amux = LINE2,
 			.gpio = 0x0000,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 			.gpio = 0x4000,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE2,
 			.gpio = 0x4000,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 			.gpio = 0x4000,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 			.gpio = 0x2000,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = TV,
 			.gpio = 0x8000,
 		},
@@ -163,34 +165,33 @@ struct saa7134_board saa7134_boards[] = {
 
 		.gpiomask       = 0xe000,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = LINE2,
 			.gpio = 0x0000,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 			.gpio = 0x4000,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE2,
 			.gpio = 0x4000,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 			.gpio = 0x4000,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 			.gpio = 0x2000,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE2,
 			.gpio = 0x8000,
 		},
@@ -205,20 +206,19 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,     /* Composite signal on S-Video input */
+			.type = SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
 			.vmux = 0,
 			.amux = LINE2,
 		},{
-			.name = name_comp2,	/* Composite input */
+			.type = SAA7134_INPUT_COMPOSITE,
 			.vmux = 3,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		}},
@@ -235,40 +235,38 @@ struct saa7134_board saa7134_boards[] = {
 
 		.gpiomask       = 0x1E000,	/* Set GP16 and unused 15,14,13 to Output */
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
 			.gpio = 0x10000,	/* GP16=1 selects TV input */
-			.tv   = 1,
 		},{
-/*			.name = name_tv_mono,
+/*			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 1,
 			.amux = LINE2,
 			.gpio = 0x0000,
-			.tv   = 1,
 		},{
-*/			.name = name_comp1,	/* Composite signal on S-Video input */
+*/			.type = SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
 			.vmux = 0,
 			.amux = LINE2,
 /*			.gpio = 0x4000,         */
 		},{
-			.name = name_comp2,	/* Composite input */
+			.type = SAA7134_INPUT_COMPOSITE,
 			.vmux = 3,
 			.amux = LINE2,
 /*			.gpio = 0x4000,         */
 		},{
-			.name = name_svideo,	/* S-Video signal on S-Video input */
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 /*			.gpio = 0x4000,         */
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x00000,	/* GP16=0 selects FM radio antenna */
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = TV,
 			.gpio = 0x10000,
 		},
@@ -285,40 +283,38 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask       = 0xe000,
 		.inputs         = { {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
 			.gpio = 0x8000,
-			.tv   = 1,
 		}, {
-			.name = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 1,
 			.amux = LINE2,
 			.gpio = 0x0000,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 			.gpio = 0x4000,
 		}, {
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE2,
 			.gpio = 0x4000,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 			.gpio = 0x4000,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 			.gpio = 0x2000,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = TV,
 			.gpio = 0x8000,
 		},
@@ -334,21 +330,20 @@ struct saa7134_board saa7134_boards[] = {
 		.empress_addr 	= 0x20,
 
 		.inputs         = {{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 		.mpeg      = SAA7134_MPEG_EMPRESS,
@@ -364,21 +359,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -390,35 +384,33 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
 			/* workaround for problems with normal TV sound */
-			.name = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE1,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	       .mute = {
-		       .name = name_mute,
+		       .type = SAA7134_INPUT_MUTE,
 		       .amux = TV,
 	       },
 	},
@@ -432,32 +424,30 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 1,
 			.amux   = LINE2,
-			.tv   = 1,
 		},{
 
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 		},{
 
-			.name = "CVid over SVid",
+			.type = SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
 			.vmux = 0,
 			.amux = LINE1,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -472,24 +462,23 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf	= TDA9887_PRESENT,
 		.gpiomask	= 0x820000,
 		.inputs		= {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x20000,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 			.gpio = 0x20000,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 			.gpio = 0x20000,
 		}},
 		.radio		= {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 			.gpio = 0x20000,
 		},
@@ -504,20 +493,19 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE,
 			.vmux = 4,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name = name_comp2, /* CVideo over SVideo Connector */
+			.type = SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
 			.vmux = 0,
 			.amux = LINE1,
 		}}
@@ -531,31 +519,29 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
 			/* workaround for problems with normal TV sound */
-			.name = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -567,18 +553,17 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		}},
 	},
 	[SAA7134_BOARD_CINERGY600] = {
@@ -590,25 +575,24 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 4,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name = name_comp2, /* CVideo over SVideo Connector */
+			.type = SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
 			.vmux = 0,
 			.amux = LINE1,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -622,25 +606,24 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 0,
 			.amux   = LINE1,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 		}},
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = LINE2,
 	       },
 	       .mute = {
-		       .name = name_mute,
+		       .type = SAA7134_INPUT_MUTE,
 		       .amux = TV,
 		},
 	},
@@ -655,21 +638,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 3,
 			.amux   = LINE1,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 		}},
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = LINE2,
 		},
 	},
@@ -681,18 +663,17 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 0,
 			.amux   = LINE1,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 4,
 			.amux = LINE2,
-			.tv   = 1,
 		}},
 	},
 	[SAA7134_BOARD_ELSA_500TV] = {
@@ -703,19 +684,17 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 7,
 			.amux = LINE1,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 8,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 8,
 			.amux = LINE2,
-			.tv   = 1,
 		}},
 	},
 	[SAA7134_BOARD_ELSA_700TV] = {
@@ -726,21 +705,20 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 4,
 			.amux = LINE2,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 6,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 7,
 			.amux = LINE1,
 		}},
 		.mute           = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = TV,
 		},
 	},
@@ -753,21 +731,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 4,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 6,
 			.amux = LINE2,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE1,
 		},
 	},
@@ -780,29 +757,28 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.gpiomask       = 0x200000,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
 			.gpio = 0x0000,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 4,
 			.amux = LINE2,
 			.gpio = 0x0000,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 6,
 			.amux = LINE2,
 			.gpio = 0x0000,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x200000,
 		},
 		.mute  = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.gpio = 0x0000,
 		},
 
@@ -815,18 +791,17 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		}},
 	},
 	[SAA7134_BOARD_10MOONSTVMASTER] = {
@@ -839,34 +814,33 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.gpiomask       = 0xe000,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = LINE2,
 			.gpio = 0x0000,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 			.gpio = 0x4000,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE2,
 			.gpio = 0x4000,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 			.gpio = 0x4000,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 			.gpio = 0x2000,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE2,
 			.gpio = 0x8000,
 		},
@@ -881,23 +855,23 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.empress_addr 	= 0x20,
 		.inputs         = {{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 4,
 			.amux = LINE1,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE1,
 		},{
-			.name = name_comp3,
+			.type = SAA7134_INPUT_COMPOSITE3,
 			.vmux = 0,
 			.amux = LINE1,
 		},{
-			.name = name_comp4,
+			.type = SAA7134_INPUT_COMPOSITE4,
 			.vmux = 1,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		}},
@@ -912,18 +886,17 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		}},
 	},
 	[SAA7134_BOARD_VIDEOMATE_TV_GOLD_PLUS] = {
@@ -935,21 +908,20 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 			.gpio = 0x06c00012,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 			.gpio = 0x0ac20012,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = LINE2,
 			.gpio = 0x08c20012,
-			.tv   = 1,
 		}},				/* radio and probably mute is missing */
 	},
 	[SAA7134_BOARD_CRONOS_PLUS] = {
@@ -968,23 +940,23 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.gpiomask       = 0xcf00,
 		.inputs         = {{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.gpio = 2 << 14,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 0,
 			.gpio = 1 << 14,
 		},{
-			.name = name_comp3,
+			.type = SAA7134_INPUT_COMPOSITE3,
 			.vmux = 0,
 			.gpio = 0 << 14,
 		},{
-			.name = name_comp4,
+			.type = SAA7134_INPUT_COMPOSITE4,
 			.vmux = 0,
 			.gpio = 3 << 14,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.gpio = 2 << 14,
 		}},
@@ -999,34 +971,33 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask	= 0x03,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x00,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 			.gpio = 0x02,
 		}, {
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 0,
 			.amux = LINE1,
 			.gpio = 0x02,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 			.gpio = 0x02,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE1,
 			.gpio = 0x01,
 		},
 		.mute  = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = TV,
 			.gpio = 0x00,
 		},
@@ -1041,18 +1012,17 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.empress_addr 	= 0x20,
 		.inputs         = {{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		}},
 		.mpeg      = SAA7134_MPEG_EMPRESS,
 		.video_out = CCIR656,
@@ -1068,22 +1038,21 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 4,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 6,
 			.amux = LINE2,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE1,
 		},
 	},
@@ -1096,20 +1065,19 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT | TDA9887_INTERCARRIER | TDA9887_PORT2_INACTIVE,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 1,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		}},
@@ -1123,21 +1091,20 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 1,
 			.amux   = LINE1,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = LINE2,
-			.tv   = 1,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -1150,21 +1117,20 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = LINE2,
-			.tv   = 1,
 		}},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE1,
 		},
 	},
@@ -1177,16 +1143,15 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		}},
@@ -1199,30 +1164,28 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 		},{
-			.name   = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux   = 1,
 			.amux   = LINE2,
-			.tv     = 1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 3,
 			.amux   = LINE1,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 		},{
-			.name   = "CVid over SVid",
+			.type = SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
 			.vmux   = 0,
 			.amux   = LINE1,
 		}},
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = LINE2,
 		},
 	},
@@ -1234,30 +1197,28 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 		},{
-			.name   = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux   = 1,
 			.amux   = LINE2,
-			.tv     = 1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 3,
 			.amux   = LINE1,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 		},{
-			.name   = "CVid over SVid",
+			.type = SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
 			.vmux   = 0,
 			.amux   = LINE1,
 		}},
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = LINE2,
 		},
 	},
@@ -1270,30 +1231,28 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 		},{
-			.name   = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux   = 1,
 			.amux   = LINE2,
-			.tv     = 1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 3,
 			.amux   = LINE1,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 		},{
-			.name   = "CVid over SVid",
+			.type = SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
 			.vmux   = 0,
 			.amux   = LINE1,
 		}},
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = LINE2,
 		},
 	},
@@ -1306,30 +1265,28 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 			.gpio = 0x200000,
 		},
@@ -1343,10 +1300,10 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 		}},
 	},
@@ -1360,10 +1317,9 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		 .mpeg           = SAA7134_MPEG_DVB,
 		 .inputs         = {{
-			 .name = name_tv,
+			 .type = SAA7134_INPUT_TV,
 			 .vmux = 1,
 			 .amux = TV,
-			 .tv   = 1,
 		 } },
 	},
 	[SAA7134_BOARD_NOVAC_PRIMETV7133] = {
@@ -1375,15 +1331,14 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 		}},
 	},
@@ -1396,29 +1351,28 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE1,
 		},
 	},
@@ -1432,29 +1386,28 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = { {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 		}, {
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE1,
 		},
 	},
@@ -1467,12 +1420,11 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 7,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 7,
 			.amux = LINE1,
 		}},
@@ -1486,21 +1438,20 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 1,
 			.amux   = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -1512,25 +1463,24 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 4,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name = name_comp2, /* CVideo over SVideo Connector */
+			.type = SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
 			.vmux = 0,
 			.amux = LINE1,
 		}},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE2,
 		},
 	},
@@ -1544,29 +1494,28 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.gpiomask	= 0x808c0080,
 		.inputs         = {{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 			.gpio = 0x00080,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 			.gpio = 0x00080,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = LINE2_LEFT,
-			.tv   = 1,
 			.gpio = 0x00080,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 			.gpio = 0x80000,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE2,
 			.gpio = 0x40000,
 		},
@@ -1580,21 +1529,20 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = LINE2,
-			.tv   = 1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		}},
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = LINE2,
 		},
 	},
@@ -1607,18 +1555,17 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		}},
 	},
 	[SAA7134_BOARD_EMPIRE_PCI_TV_RADIO_LE] = {
@@ -1631,29 +1578,28 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.gpiomask       = 0x4000,
 		.inputs         = {{
-			.name = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 1,
 			.amux = LINE2,
 			.gpio = 0x8000,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 			.gpio = 0x8000,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 6,
 			.amux = LINE1,
 			.gpio = 0x8000,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE1,
 			.gpio = 0x8000,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = TV,
 			.gpio =0x8000,
 		}
@@ -1672,29 +1618,28 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask       = 0x03,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x00,
 		},{
-			.name = name_comp,
+			.type = SAA7134_INPUT_COMPOSITE,
 			.vmux = 3,
 			.amux = LINE1,
 			.gpio = 0x02,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 			.gpio = 0x02,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE1,
 			.gpio = 0x01,
 		},
 		.mute  = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE1,
 			.gpio = 0x00,
 		},
@@ -1709,29 +1654,28 @@ struct saa7134_board saa7134_boards[] = {
 		.gpiomask       = 0x00300003,
 		/* .gpiomask       = 0x8c240003, */
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x01,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE1,
 			.gpio = 0x02,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 6,
 			.amux = LINE1,
 			.gpio = 0x02,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x00300001,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = TV,
 			.gpio = 0x01,
 		},
@@ -1745,21 +1689,20 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE1,
 		},
 	},
@@ -1774,24 +1717,23 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask       = 0x08000000,
 		.inputs         = { {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x08000000,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 			.gpio = 0x08000000,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 			.gpio = 0x08000000,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 			.gpio = 0x00000000,
 		},
@@ -1805,21 +1747,19 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		}},
@@ -1834,25 +1774,24 @@ struct saa7134_board saa7134_boards[] = {
 		.rds_addr 	= 0x10,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 4,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name = name_comp2, /* CVideo over SVideo Connector */
+			.type = SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
 			.vmux = 0,
 			.amux = LINE1,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -1866,29 +1805,28 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.gpiomask	= 0x1ce780,
 		.inputs		= {{
-			.name = name_svideo,
-			.vmux = 0,		/* CVideo over SVideo Connector - ok? */
+			.type = SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
+			.vmux = 0,
 			.amux = LINE1,
 			.gpio = 0x008080,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 			.gpio = 0x008080,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x008080,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 			.gpio = 0x80000,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE2,
 			.gpio = 0x0c8000,
 		},
@@ -1903,20 +1841,19 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT | TDA9887_INTERCARRIER | TDA9887_PORT2_INACTIVE,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 1,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		}},
@@ -1931,22 +1868,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE1,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -1961,25 +1896,24 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		}},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE1,
 		},
 	},
@@ -1995,26 +1929,25 @@ struct saa7134_board saa7134_boards[] = {
 		.gpiomask	= 0x00200000,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
 			.gpio = 0x200000,	/* GPIO21=High for TV input */
-			.tv   = 1,
 		},{
-			.name = name_comp1,	/* Composite signal on S-Video input */
+			.type = SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
 			.vmux = 0,
 			.amux = LINE2,
 		},{
-			.name = name_comp2,	/* Composite input */
+			.type = SAA7134_INPUT_COMPOSITE,
 			.vmux = 3,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,	/* S-Video signal on S-Video input */
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x000000,	/* GPIO21=Low for FM radio antenna */
 		},
@@ -2028,11 +1961,11 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs = {{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 0,
 			.amux   = LINE1,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 		}},
@@ -2049,20 +1982,19 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE1,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		}},
@@ -2075,16 +2007,15 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		}},
@@ -2098,29 +2029,28 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.gpiomask	= 0x0700,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 			.gpio   = 0x000,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 3,
 			.amux   = LINE1,
 			.gpio   = 0x200,		/* gpio by DScaler */
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 0,
 			.amux   = LINE1,
 			.gpio   = 0x200,
 		}},
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = LINE1,
 			.gpio   = 0x100,
 		},
 		.mute  = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = TV,
 			.gpio = 0x000,
 		},
@@ -2135,26 +2065,25 @@ struct saa7134_board saa7134_boards[] = {
 		.mpeg           = SAA7134_MPEG_DVB,
 		.gpiomask	= 0x00200000,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
 			.gpio = 0x200000,	/* GPIO21=High for TV input */
-			.tv   = 1,
 		},{
-			.name = name_svideo,	/* S-Video signal on S-Video input */
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		},{
-			.name = name_comp1,	/* Composite signal on S-Video input */
+			.type = SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
 			.vmux = 0,
 			.amux = LINE2,
 		},{
-			.name = name_comp2,	/* Composite input */
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE2,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x000000,	/* GPIO21=Low for FM radio antenna */
 		},
@@ -2168,29 +2097,28 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = 0x60,
 		.gpiomask       = 0x8c1880,
 		.inputs         = {{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 0,
 			.amux = LINE1,
 			.gpio = 0x800800,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 			.gpio = 0x801000,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x800000,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x880000,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE2,
 			.gpio = 0x840000,
 		},
@@ -2213,29 +2141,28 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= 0x60,
 		.gpiomask	= 0x0700,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 			.gpio   = 0x000,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 3,
 			.amux   = LINE1,
 			.gpio   = 0x200,		/* gpio by DScaler */
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 0,
 			.amux   = LINE1,
 			.gpio   = 0x200,
 		}},
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = LINE1,
 			.gpio   = 0x100,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = TV,
 			.gpio = 0x000,
 		},
@@ -2248,30 +2175,28 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		}},
 		.radio = {
-			.name = name_radio,		/* radio unconfirmed */
+			.type = SAA7134_INPUT_RADIO,		/* radio unconfirmed */
 			.amux = LINE2,
 		},
 	},
@@ -2286,24 +2211,23 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.gpiomask       = 1 << 21,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
 			.gpio = 0x0000000,
-			.tv   = 1,
 		},{
-			.name = name_comp1,     /* Composite input */
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE2,
 			.gpio = 0x0000000,
 		},{
-			.name = name_svideo,    /* S-Video input */
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 			.gpio = 0x0000000,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x0200000,
 		},
@@ -2322,29 +2246,28 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr= ADDR_UNSET,
 		.gpiomask       = 0x00010003,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x01,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 			.gpio = 0x02,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 6,
 			.amux = LINE2,
 			.gpio = 0x02,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE1,
 			.gpio = 0x00010003,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = TV,
 			.gpio = 0x01,
 		},
@@ -2362,21 +2285,20 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask       = 0x00008000,
 		.inputs         = {{
-			  .name = name_tv,
+			  .type = SAA7134_INPUT_TV,
 			  .vmux = 3,
 			  .amux = TV,
-			  .tv   = 1,
 		},{
-			  .name = name_comp1,
+			  .type = SAA7134_INPUT_COMPOSITE1,
 			  .vmux = 1,
 			  .amux = LINE1,
 		},{
-			  .name = name_svideo,
+			  .type = SAA7134_INPUT_SVIDEO,
 			  .vmux = 8,
 			  .amux = LINE1,
 		}},
 		.radio = {
-			  .name = name_radio,
+			  .type = SAA7134_INPUT_RADIO,
 			  .amux = LINE2,
 		},
 	},
@@ -2392,34 +2314,33 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf    = TDA9887_PRESENT,
 		.gpiomask        = 0x00200003,
 		.inputs          = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x00200003,
 		},{
-			.name = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 1,
 			.amux = LINE2,
 			.gpio = 0x00200003,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 			.gpio = 0x00200003,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 			.gpio = 0x00200003,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 			.gpio = 0x00200003,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = TV,
 			.gpio = 0x00200003,
 		},
@@ -2434,16 +2355,15 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT | TDA9887_PORT1_ACTIVE,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 3,
 			.amux   = TV,
-			.tv     = 1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 0,
 			.amux   = LINE2,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE2,
 		}},
@@ -2458,16 +2378,15 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT | TDA9887_PORT1_ACTIVE,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 3,
 			.amux   = TV,
-			.tv     = 1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 1,
 			.amux   = LINE2,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE2,
 		}},
@@ -2481,11 +2400,11 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs = {{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 0,
 			.amux   = LINE1,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 		}},
@@ -2499,27 +2418,28 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.empress_addr 	= 0x21,
 		.inputs		= {{
-			.name   = "Composite 0",
+			.type = SAA7134_INPUT_COMPOSITE0,
 			.vmux   = 0,
 			.amux   = LINE1,
 		},{
-			.name   = "Composite 1",
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 1,
 			.amux   = LINE2,
 		},{
-			.name   = "Composite 2",
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux   = 2,
 			.amux   = LINE1,
 		},{
-			.name   = "Composite 3",
+			.type = SAA7134_INPUT_COMPOSITE3,
 			.vmux   = 3,
 			.amux   = LINE2,
 		},{
-			.name   = "S-Video 0",
+			.type = SAA7134_INPUT_SVIDEO0,
+
 			.vmux   = 8,
 			.amux   = LINE1,
 		},{
-			.name   = "S-Video 1",
+			.type = SAA7134_INPUT_SVIDEO1,
 			.vmux   = 9,
 			.amux   = LINE2,
 		}},
@@ -2538,27 +2458,27 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs		= {{
-			.name   = "Composite 0",
+			.type = SAA7134_INPUT_COMPOSITE0,
 			.vmux   = 0,
 			.amux   = LINE1,
 		},{
-			.name   = "Composite 1",
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 1,
 			.amux   = LINE2,
 		},{
-			.name   = "Composite 2",
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux   = 2,
 			.amux   = LINE1,
 		},{
-			.name   = "Composite 3",
+			.type = SAA7134_INPUT_COMPOSITE3,
 			.vmux   = 3,
 			.amux   = LINE2,
 		},{
-			.name   = "S-Video 0",
+			.type = SAA7134_INPUT_SVIDEO0,
 			.vmux   = 8,
 			.amux   = LINE1,
 		},{
-			.name   = "S-Video 1",
+			.type = SAA7134_INPUT_SVIDEO1,
 			.vmux   = 9,
 			.amux   = LINE2,
 		}},
@@ -2572,20 +2492,19 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,     /* Composite signal on S-Video input */
+			.type = SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
 			.vmux = 0,
 			.amux = LINE2,
 		},{
-			.name = name_comp2,	/* Composite input */
+			.type = SAA7134_INPUT_COMPOSITE,
 			.vmux = 3,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		}},
@@ -2604,11 +2523,11 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = {{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		}},
@@ -2622,16 +2541,15 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 
 		.inputs         = {{
-			  .name = name_tv,
+			  .type = SAA7134_INPUT_TV,
 			  .vmux = 1,
 			  .amux = TV,
-			  .tv   = 1,
 		},{
-			  .name = name_comp1,
+			  .type = SAA7134_INPUT_COMPOSITE1,
 			  .vmux = 3,
 			  .amux = LINE1,
 		},{
-			  .name = name_svideo,
+			  .type = SAA7134_INPUT_SVIDEO,
 			  .vmux = 6,
 			  .amux = LINE1,
 		}},
@@ -2645,25 +2563,24 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.gpiomask       = 0x080200000,
 		.inputs         = { {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 4,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE2,
 		}, {
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 0,
 			.amux = LINE2,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x0200000,
 		},
@@ -2678,29 +2595,28 @@ struct saa7134_board saa7134_boards[] = {
 		.gpiomask	= 1 << 21,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x0000000,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE2,
 			.gpio = 0x0200000,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 0,
 			.amux = LINE2,
 			.gpio = 0x0200000,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 			.gpio = 0x0200000,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x0200000,
 		},
@@ -2717,21 +2633,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.gpiomask       = 0xe880c0,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 6,
 			.amux = LINE1,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -2745,16 +2660,15 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		}},
@@ -2770,21 +2684,20 @@ struct saa7134_board saa7134_boards[] = {
 		.mpeg           = SAA7134_MPEG_DVB,
 		.gpiomask       = 0x0200000,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 3,
 			.amux   = LINE1,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 		}},
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = TV,
 			.gpio   = 0x0200000,
 		},
@@ -2798,25 +2711,24 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.gpiomask       = 1 << 21,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE,
 			.vmux   = 3,
 			.amux   = LINE2,	/* unconfirmed, taken from Philips driver */
 		},{
-			.name   = name_comp2,
-			.vmux   = 0,		/* untested, Composite over S-Video */
+			.type = SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
+			.vmux   = 0,		/* untested */
 			.amux   = LINE2,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE2,
 		}},
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = TV,
 			.gpio   = 0x0200000,
 		},
@@ -2834,17 +2746,16 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.gpiomask       = 0x80200000,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_svideo,  /* NOT tested */
+			.type = SAA7134_INPUT_SVIDEO,  /* NOT tested */
 			.vmux = 8,
 			.amux = LINE1,
 		}},
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = TV,
 			.gpio   = 0x0200000,
 		},
@@ -2861,26 +2772,25 @@ struct saa7134_board saa7134_boards[] = {
 		.gpiomask	= 0x00200000,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = {{
-			.name = name_tv,	/* Analog broadcast/cable TV */
+			.type = SAA7134_INPUT_TV,	/* Analog broadcast/cable TV */
 			.vmux = 1,
 			.amux = TV,
 			.gpio = 0x200000,	/* GPIO21=High for TV input */
-			.tv   = 1,
 		},{
-			.name = name_svideo,	/* S-Video signal on S-Video input */
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		},{
-			.name = name_comp1,	/* Composite signal on S-Video input */
+			.type = SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
 			.vmux = 0,
 			.amux = LINE2,
 		},{
-			.name = name_comp2,	/* Composite input */
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE2,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x000000,	/* GPIO21=Low for FM radio antenna */
 		},
@@ -2894,11 +2804,11 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs = {{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 1,
 			.amux   = LINE1,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 		}},
@@ -2914,11 +2824,11 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = {{
-			.name = name_comp1,	/* Composite input */
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,	/* S-Video signal on S-Video input */
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		}},
@@ -2933,10 +2843,9 @@ struct saa7134_board saa7134_boards[] = {
 		.mpeg           = SAA7134_MPEG_DVB,
 		.gpiomask       = 0x00600000, /* Bit 21 0=Radio, Bit 22 0=TV */
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 			.gpio   = 0x00200000,
 		}},
 	},
@@ -2950,25 +2859,24 @@ struct saa7134_board saa7134_boards[] = {
 		.mpeg           = SAA7134_MPEG_DVB,
 		.gpiomask       = 1 << 21,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 3,
 			.amux   = LINE1,
 		},{
-			.name   = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux   = 0,
 			.amux   = LINE1,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 		}},
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = TV,
 			.gpio   = 0x0200000,
 		},
@@ -2983,21 +2891,20 @@ struct saa7134_board saa7134_boards[] = {
 		.mpeg           = SAA7134_MPEG_DVB,
 		.gpiomask       = 1 << 21,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 3,
 			.amux   = LINE1,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 		}},
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = TV,
 			.gpio   = 0x0200000,
 		},
@@ -3012,16 +2919,15 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		}},
@@ -3052,17 +2958,16 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask       = 0xca60000,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 4,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x04a61000,
 		},{
-			.name = name_comp2,  /*  Composite SVIDEO (B/W if signal is carried with SVIDEO) */
+			.type = SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
 			.vmux = 1,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 9,           /* 9 is correct as S-VIDEO1 according to a169.inf! */
 			.amux = LINE1,
 		}},
@@ -3086,26 +2991,25 @@ struct saa7134_board saa7134_boards[] = {
 		.mpeg           = SAA7134_MPEG_DVB,
 		.gpiomask       = 0x00600000, /* Bit 21 0=Radio, Bit 22 0=TV */
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
 			.gpio = 0x200000,	/* GPIO21=High for TV input */
-			.tv   = 1,
 		},{
-			.name = name_svideo,	/* S-Video signal on S-Video input */
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		},{
-			.name = name_comp1,	/* Composite signal on S-Video input */
+			.type = SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
 			.vmux = 0,
 			.amux = LINE2,
 		},{
-			.name = name_comp2,	/* Composite input */
+			.type = SAA7134_INPUT_COMPOSITE,
 			.vmux = 3,
 			.amux = LINE2,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x000000,	/* GPIO21=Low for FM radio antenna */
 		},
@@ -3121,40 +3025,38 @@ struct saa7134_board saa7134_boards[] = {
 
 		.gpiomask       = 0xe000,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
 			.gpio = 0x8000,
-			.tv   = 1,
 		},{
-			.name = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 1,
 			.amux = LINE2,
 			.gpio = 0x0000,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 			.gpio = 0x4000,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE2,
 			.gpio = 0x4000,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 			.gpio = 0x4000,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 			.gpio = 0x2000,
 		},
 			.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = TV,
 			.gpio = 0x8000,
 		},
@@ -3168,16 +3070,15 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 0,
 			.amux   = LINE1,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 		}},
@@ -3193,11 +3094,11 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = {{
-			.name = name_comp1,	/* Composite input */
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,	/* S-Video signal on S-Video input */
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		}},
@@ -3211,25 +3112,24 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		}},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE1,
 		},
 	},
@@ -3244,21 +3144,20 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE1,
 		},
 	},
@@ -3272,21 +3171,20 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT| TDA9887_PORT1_ACTIVE | TDA9887_PORT2_ACTIVE,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 3,
 			.amux   = TV,
-			.tv     = 1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 4,
 			.amux   = LINE2,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE2,
 		}},
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = LINE1,
 		},
 	},
@@ -3301,25 +3199,24 @@ struct saa7134_board saa7134_boards[] = {
 		.mpeg           = SAA7134_MPEG_DVB,
 		.gpiomask       = 0x000200000,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 4,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE2,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 0,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = TV,
 			.gpio   = 0x0200000,
 		},
@@ -3335,34 +3232,33 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask       = 0x03,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x00,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 			.gpio = 0x00,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE2,
 			.gpio = 0x00,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 			.gpio = 0x00,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 			.gpio = 0x01,
 		},
 		.mute  = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE1,
 			.gpio = 0x00,
 		},
@@ -3378,16 +3274,15 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT | TDA9887_PORT1_ACTIVE,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 3,
 			.amux   = TV,
-			.tv     = 1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 1,
 			.amux   = LINE2,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE2,
 		}},
@@ -3405,22 +3300,21 @@ struct saa7134_board saa7134_boards[] = {
 		.mpeg           = SAA7134_MPEG_DVB,
 		.gpiomask       = 0x0200100,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x0000100,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x0200100,
 		},
@@ -3438,22 +3332,21 @@ struct saa7134_board saa7134_boards[] = {
 		.ts_force_val   = 1,
 		.gpiomask       = 0x0800100, /* GPIO 21 is an INPUT */
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x0000100,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x0800100, /* GPIO 23 HI for FM */
 		},
@@ -3470,22 +3363,21 @@ struct saa7134_board saa7134_boards[] = {
 		.ts_type	= SAA7134_MPEG_TS_SERIAL,
 		.gpiomask       = 0x0800100, /* GPIO 21 is an INPUT */
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x0000100,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x0800100, /* GPIO 23 HI for FM */
 		},
@@ -3499,16 +3391,15 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 0,
 			.amux   = LINE1,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 6,
 			.amux   = LINE1,
 		}},
@@ -3523,33 +3414,31 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = 3,
-			.tv   = 1,
 		},{
-			.name = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 7,
 			.amux = 4,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = 2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 0,
 			.amux = 2,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 /*			.gpio = 0x00300001,*/
 			.gpio = 0x20000,
 
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = 0,
 		},
 	},
@@ -3562,32 +3451,30 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = 3,
-			.tv   = 1,
 		},{
-			.name = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 7,
 			.amux = 4,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = 2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 0,
 			.amux = 2,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 			.gpio = 0x20000,
 
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = 0,
 		},
 	},
@@ -3600,29 +3487,28 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.gpiomask	= 0x7000,
 		.inputs         = { {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = 1,
-			.tv   = 1,
 			.gpio = 0x50000,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = 2,
 			.gpio = 0x2000,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = 2,
 			.gpio = 0x2000,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.vmux = 1,
 			.amux = 1,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.gpio = 0xf000,
 			.amux = 0,
 		},
@@ -3635,26 +3521,25 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= 0x61,
 		.radio_addr	= 0x60,
 		.inputs         = { {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.vmux = 1,
 			.amux = LINE1,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE1,
 			.gpio = 0x43000,
 		},
@@ -3668,16 +3553,15 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 0,
 			.amux   = LINE1,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 6,
 			.amux   = LINE1,
 		}},
@@ -3693,21 +3577,20 @@ struct saa7134_board saa7134_boards[] = {
 		.mpeg           = SAA7134_MPEG_DVB,
 		.gpiomask       = 0x0200000,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 3,
 			.amux   = LINE1,
 		},{
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 		}},
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = TV,
 			.gpio   = 0x0200000,
 		},
@@ -3721,16 +3604,15 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.gpiomask       = 1<<21,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 6,
 			.amux = LINE2,
 		}},
@@ -3746,10 +3628,9 @@ struct saa7134_board saa7134_boards[] = {
 		.mpeg           = SAA7134_MPEG_DVB,
 		.gpiomask       = 0x0200000,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 			.gpio   = 0x0200000,
 		}},
 	},
@@ -3764,29 +3645,28 @@ struct saa7134_board saa7134_boards[] = {
 		.gpiomask	= 1 << 21,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x0000000,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE2,
 			.gpio = 0x0200000,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 0,
 			.amux = LINE2,
 			.gpio = 0x0200000,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 			.gpio = 0x0200000,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x0200000,
 		},
@@ -3800,26 +3680,25 @@ struct saa7134_board saa7134_boards[] = {
 	       .radio_addr     = ADDR_UNSET,
 	       .gpiomask       = 1 << 21,
 	       .inputs         = {{
-		       .name = name_tv,
+		       .type = SAA7134_INPUT_TV,
 		       .vmux = 1,
 		       .amux = TV,
-		       .tv   = 1,
 		       .gpio = 0x0000000,
 	       }, {
-		       .name = name_comp1,
+		       .type = SAA7134_INPUT_COMPOSITE1,
 		       .vmux = 3,
 		       .amux = LINE2,
 	       }, {
-		       .name = name_comp2,
+		       .type = SAA7134_INPUT_COMPOSITE2,
 		       .vmux = 0,
 		       .amux = LINE2,
 	       }, {
-		       .name = name_svideo,
+		       .type = SAA7134_INPUT_SVIDEO,
 		       .vmux = 8,
 		       .amux = LINE2,
 	       } },
 	       .radio = {
-		       .name = name_radio,
+		       .type = SAA7134_INPUT_RADIO,
 		       .amux = TV,
 		       .gpio = 0x0200000,
 	       },
@@ -3832,25 +3711,24 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 		},{
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 0,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		}},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = TV,
 		},
 	},
@@ -3864,24 +3742,23 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.gpiomask       = 0x7000,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = LINE2,
 			.gpio = 0x0000,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 			.gpio = 0x2000,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 			.gpio = 0x2000,
 		}},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE2,
 			.gpio = 0x3000,
 		},
@@ -3896,10 +3773,9 @@ struct saa7134_board saa7134_boards[] = {
 		.tda829x_conf   = { .lna_cfg = TDA8290_LNA_OFF },
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs = {{
-			.name   = name_tv, /* FIXME: analog tv untested */
+			.type = SAA7134_INPUT_TV, /* FIXME: analog tv untested */
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 		}},
 	},
 	[SAA7134_BOARD_AVERMEDIA_M135A] = {
@@ -3912,26 +3788,25 @@ struct saa7134_board saa7134_boards[] = {
 		.tda829x_conf   = { .lna_cfg = TDA8290_LNA_GP0_HIGH_OFF },
 		.gpiomask       = 0x020200000,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x00200000,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = TV,
 			.gpio = 0x01,
 		},
@@ -3946,26 +3821,25 @@ struct saa7134_board saa7134_boards[] = {
 		.tda829x_conf	= { .lna_cfg = TDA8290_LNA_OFF },
 		.gpiomask	= 0x020200000,
 		.inputs		= {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x00200000,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = TV,
 			.gpio = 0x01,
 		},
@@ -3981,21 +3855,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.gpiomask       = 0x00008000,
 		.inputs         = {{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = LINE2,
-			.tv   = 1,
 		}},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE1,
 		},
 	},
@@ -4010,18 +3883,17 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.gpiomask       = 0x00008000,
 		.inputs         = {{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 1,
 			.amux   = LINE1,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = LINE2,
-			.tv   = 1,
 		}},
 	},
 	[SAA7134_BOARD_BEHOLD_403FM] = {
@@ -4035,21 +3907,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.gpiomask       = 0x00008000,
 		.inputs         = {{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 1,
 			.amux   = LINE1,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = LINE2,
-			.tv   = 1,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -4065,18 +3936,17 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask       = 0x00008000,
 		.inputs         = {{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = LINE2,
-			.tv   = 1,
 		}},
 	},
 	[SAA7134_BOARD_BEHOLD_405FM] = {
@@ -4092,21 +3962,20 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask       = 0x00008000,
 		.inputs         = {{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = LINE2,
-			.tv   = 1,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -4122,20 +3991,19 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf 	= TDA9887_PRESENT,
 		.gpiomask       = 0x00008000,
 		.inputs = {{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 			.gpio = 0xc0c000,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 			.gpio = 0xc0c000,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv = 1,
 			.gpio = 0xc0c000,
 		}},
 	},
@@ -4151,24 +4019,23 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf 	= TDA9887_PRESENT,
 		.gpiomask       = 0x00008000,
 		.inputs = {{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 			.gpio = 0xc0c000,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 			.gpio = 0xc0c000,
 		},{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv = 1,
 			.gpio = 0xc0c000,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 			.gpio = 0xc0c000,
 		},
@@ -4185,16 +4052,15 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask       = 0x00008000,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		}},
@@ -4211,25 +4077,24 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask       = 0x00008000,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = LINE2,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE1,
 		},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -4246,25 +4111,24 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask       = 0x00008000,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = LINE2,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		}},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE1,
 		},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -4280,21 +4144,20 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask       = 0x00008000,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		}},
 			.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -4311,21 +4174,20 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask       = 0x00008000,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 			.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -4342,21 +4204,20 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask       = 0x00008000,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 			.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -4372,24 +4233,23 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask       = 0x000A8004,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x000A8004,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 			.gpio = 0x000A8000,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 			.gpio = 0x000A8000,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 			.gpio = 0x000A8000,
 		},
@@ -4404,21 +4264,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -4432,21 +4291,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -4460,21 +4318,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -4488,21 +4345,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -4517,21 +4373,20 @@ struct saa7134_board saa7134_boards[] = {
 		.rds_addr 	= 0x10,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -4546,21 +4401,20 @@ struct saa7134_board saa7134_boards[] = {
 		.rds_addr 	= 0x10,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -4575,21 +4429,20 @@ struct saa7134_board saa7134_boards[] = {
 		.rds_addr 	= 0x10,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -4604,21 +4457,20 @@ struct saa7134_board saa7134_boards[] = {
 		.rds_addr 	= 0x10,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		},{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		},{
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		}},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -4636,21 +4488,20 @@ struct saa7134_board saa7134_boards[] = {
 		.empress_addr 	= 0x20,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = { {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 		.mpeg  = SAA7134_MPEG_EMPRESS,
@@ -4673,21 +4524,20 @@ struct saa7134_board saa7134_boards[] = {
 		.empress_addr 	= 0x20,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = { {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 		.mpeg  = SAA7134_MPEG_EMPRESS,
@@ -4712,21 +4562,20 @@ struct saa7134_board saa7134_boards[] = {
 		.empress_addr 	= 0x20,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = { {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 		.mpeg  = SAA7134_MPEG_EMPRESS,
@@ -4747,21 +4596,20 @@ struct saa7134_board saa7134_boards[] = {
 		.mpeg           = SAA7134_MPEG_DVB,
 		.gpiomask       = 0x0200000,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 		}, {
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 3,
 			.amux   = LINE1,
 		}, {
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,		/* untested */
 			.amux   = LINE1,
 		} },
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = TV,
 			.gpio   = 0x0200000,
 		},
@@ -4776,30 +4624,28 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.gpiomask       = 0xf000,
 		.inputs         = {{
-			.name = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 1,
 			.amux = LINE2,
 			.gpio = 0x0000,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 			.gpio = 0x2000,
-			.tv = 1
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 			.gpio = 0x2000,
 	} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 			.gpio = 0x1000,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE2,
 			.gpio = 0x6000,
 		},
@@ -4813,11 +4659,11 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs = {{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 3,
 			.amux   = LINE1,
 		}, {
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 		} },
@@ -4832,16 +4678,15 @@ struct saa7134_board saa7134_boards[] = {
 		.tda829x_conf = { .lna_cfg = TDA8290_LNA_OFF },
 		.mpeg         = SAA7134_MPEG_DVB,
 		.inputs       = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
@@ -4857,21 +4702,20 @@ struct saa7134_board saa7134_boards[] = {
 		.mpeg           = SAA7134_MPEG_DVB,
 		.gpiomask       = 0x0200000,
 		.inputs = { {
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 		}, {
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 3,
 			.amux   = LINE1,
 		}, {
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 		} },
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = TV,
 			.gpio   = 0x0200000,
 		},
@@ -4885,21 +4729,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		 .mpeg           = SAA7134_MPEG_DVB,
 		 .inputs         = {{
-			 .name = name_tv,
+			 .type = SAA7134_INPUT_TV,
 			 .vmux = 1,
 			 .amux = TV,
-			 .tv   = 1,
 		 }, {
-			 .name = name_comp1,
+			 .type = SAA7134_INPUT_COMPOSITE1,
 			 .vmux = 3,
 			 .amux = LINE1,
 		 }, {
-			 .name = name_svideo,
+			 .type = SAA7134_INPUT_SVIDEO,
 			 .vmux = 8,
 			 .amux = LINE2,
 		 } },
 		 .radio = {
-			 .name = name_radio,
+			 .type = SAA7134_INPUT_RADIO,
 			 .amux = TV,
 		 },
 	},
@@ -4912,21 +4755,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		}, {
-			.name = name_comp,
+			.type = SAA7134_INPUT_COMPOSITE,
 			.vmux = 0,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 		},
 	},
@@ -4938,16 +4780,15 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		} },
@@ -4962,21 +4803,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 3,
 			.amux   = TV,
-			.tv     = 1,
 		}, {
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 1,
 			.amux   = LINE2,
 		}, {
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE2,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 		}
 	},
@@ -4990,11 +4830,11 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = { {
-			.name = name_comp,
+			.type = SAA7134_INPUT_COMPOSITE,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 6,
 			.amux = LINE1,
 		} },
@@ -5009,21 +4849,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = { {
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 4,
 			.amux   = TV,
-			.tv     = 1,
 		}, {
-			.name = name_comp,
+			.type = SAA7134_INPUT_COMPOSITE,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 6,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 		},
 	},
@@ -5038,21 +4877,20 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -5067,21 +4905,20 @@ struct saa7134_board saa7134_boards[] = {
 		.gpiomask       = 1 << 21,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp,
+			.type = SAA7134_INPUT_COMPOSITE,
 			.vmux = 0,
 			.amux = LINE2,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x0200000,
 		},
@@ -5097,21 +4934,20 @@ struct saa7134_board saa7134_boards[] = {
 		.gpiomask       = 1 << 21,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp,
+			.type = SAA7134_INPUT_COMPOSITE,
 			.vmux = 0,
 			.amux = LINE2,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x0200000,
 		},
@@ -5125,29 +4961,28 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.gpiomask       = 0x801a8087,
 		.inputs = { {
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 3,
 			.amux   = LINE2,
-			.tv     = 1,
 			.gpio   = 0x624000,
 		}, {
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 1,
 			.amux   = LINE1,
 			.gpio   = 0x624000,
 		}, {
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 1,
 			.amux   = LINE1,
 			.gpio   = 0x624000,
 		} },
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = LINE2,
 			.gpio   = 0x624001,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = TV,
 		},
 	},
@@ -5161,16 +4996,15 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = { {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp,
+			.type = SAA7134_INPUT_COMPOSITE,
 			.vmux = 4,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
@@ -5186,25 +5020,24 @@ struct saa7134_board saa7134_boards[] = {
 		.mpeg           = SAA7134_MPEG_DVB,
 		.gpiomask       = 0x0200000,
 		.inputs = { {
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 		}, {
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 3,
 			.amux   = LINE2,
 		}, {
-			.name   = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux   = 0,
 			.amux   = LINE2,
 		}, {
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE2,
 		} },
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = TV,
 			.gpio   = 0x0200000,
 		},
@@ -5218,30 +5051,29 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = 0x60,
 		.gpiomask       = 0x80000700,
 		.inputs = { {
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = LINE2,
-			.tv     = 1,
 			.gpio   = 0x100,
 		}, {
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 3,
 			.amux   = LINE1,
 			.gpio   = 0x200,
 		}, {
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 			.gpio   = 0x200,
 		} },
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.vmux   = 1,
 			.amux   = LINE1,
 			.gpio   = 0x100,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.vmux = 8,
 			.amux = 2,
 		},
@@ -5257,18 +5089,17 @@ struct saa7134_board saa7134_boards[] = {
 		.mpeg           = SAA7134_MPEG_DVB,
 		.ts_type	= SAA7134_MPEG_TS_PARALLEL,
 		.inputs = { {
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 #if 0	/* FIXME */
 		}, {
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 3,
 			.amux   = LINE1,
 			.gpio   = 0x200,
 		}, {
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 			.gpio   = 0x200,
@@ -5276,14 +5107,14 @@ struct saa7134_board saa7134_boards[] = {
 		} },
 #if 0
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.vmux   = 1,
 			.amux   = LINE1,
 			.gpio   = 0x100,
 		},
 #endif
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.vmux = 0,
 			.amux = TV,
 		},
@@ -5298,24 +5129,23 @@ struct saa7134_board saa7134_boards[] = {
 		.gpiomask       = 0x00300003,
 		/* .gpiomask       = 0x8c240003, */
 		.inputs         = { {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x01,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 6,
 			.amux = LINE1,
 			.gpio = 0x02,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x00300001,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = TV,
 			.gpio = 0x01,
 		},
@@ -5331,29 +5161,28 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask       = 0x03,
 		.inputs         = { {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 			.gpio = 0x00,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 			.gpio = 0x00,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 			.gpio = 0x00,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 			.gpio = 0x01,
 		},
 		.mute  = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE1,
 			.gpio = 0x00,
 		},
@@ -5368,11 +5197,11 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.mpeg		= SAA7134_MPEG_DVB,
 		.inputs = { {
-			.name	= name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux	= 0,
 			.amux	= LINE1,
 		}, {
-			.name	= name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux	= 8, /* Not tested */
 			.amux	= LINE1
 		} },
@@ -5387,21 +5216,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = { {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 2,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 9,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 		},
 	},
@@ -5416,13 +5244,12 @@ struct saa7134_board saa7134_boards[] = {
 		.mpeg           = SAA7134_MPEG_DVB,
 		.ts_type	= SAA7134_MPEG_TS_PARALLEL,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		} },
 		.radio = {	/* untested */
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 		},
 	},
@@ -5436,16 +5263,15 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT | TDA9887_PORT1_ACTIVE,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs = { {
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 3,
 			.amux   = TV,
-			.tv     = 1,
 		}, {
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 4,
 			.amux   = LINE2,
 		}, {
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE2,
 		} },
@@ -5459,10 +5285,10 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = { {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 		} },
 	},
@@ -5479,25 +5305,24 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.gpiomask       = 0x00008000,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = LINE2,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE1,
 		},
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE2,
 		},
 	},
@@ -5512,7 +5337,7 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr   = ADDR_UNSET,
 		.gpiomask      = 0x389c00,
 		.inputs       = {{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 			.gpio = 0x01fc00,
@@ -5529,21 +5354,20 @@ struct saa7134_board saa7134_boards[] = {
 		.mpeg           = SAA7134_MPEG_DVB,
 		.ts_type	= SAA7134_MPEG_TS_PARALLEL,
 		.inputs         = { {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 2,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 9,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 		},
 	},
@@ -5556,21 +5380,20 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
 		.inputs         = { {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 2,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 9,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 		},
 	},
@@ -5584,16 +5407,15 @@ struct saa7134_board saa7134_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT | TDA9887_PORT1_ACTIVE,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs = {{
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 3,
 			.amux   = TV,
-			.tv     = 1,
 		}, {
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 0,
 			.amux   = LINE2,
 		}, {
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE2,
 		} },
@@ -5607,25 +5429,24 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = 0x60,
 		.inputs         = { {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE2,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE1,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = TV,
 		},
 	},
@@ -5642,29 +5463,28 @@ struct saa7134_board saa7134_boards[] = {
 		.mpeg		= SAA7134_MPEG_DVB,
 		.ts_type	= SAA7134_MPEG_TS_PARALLEL,
 		.inputs		= { {
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 			.gpio   = 0x00050000,
 		}, {
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 3,
 			.amux   = LINE1,
 			.gpio   = 0x00050000,
 		}, {
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 			.gpio   = 0x00050000,
 		} },
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = TV,
 			.gpio   = 0x00050000,
 		},
 		.mute = {
-			.name   = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.vmux   = 0,
 			.amux   = TV,
 			.gpio   = 0x00050000,
@@ -5681,21 +5501,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.gpiomask       = 0x00008000,
 		.inputs         = { {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = LINE2,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE1,
 		},
 	},
@@ -5710,21 +5529,20 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.gpiomask       = 0x00008000,
 		.inputs         = { {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = LINE2,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 1,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE1,
 		},
 	},
@@ -5736,15 +5554,15 @@ struct saa7134_board saa7134_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.inputs		= {{
-			.name   = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux   = 0,
 			.amux   = LINE1,
 		}, {
-			.name   = name_comp3,
+			.type = SAA7134_INPUT_COMPOSITE3,
 			.vmux   = 2,
 			.amux   = LINE1,
 		}, {
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE1,
 		} },
@@ -5760,21 +5578,20 @@ struct saa7134_board saa7134_boards[] = {
 		.gpiomask       = 1 << 21,
 		.ts_type	= SAA7134_MPEG_TS_PARALLEL,
 		.inputs = { {
-			.name   = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux   = 1,
 			.amux   = TV,
-			.tv     = 1,
 		}, {
-			.name   = name_comp,
+			.type = SAA7134_INPUT_COMPOSITE,
 			.vmux   = 3,
 			.amux   = LINE1,
 		}, {
-			.name   = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux   = 8,
 			.amux   = LINE2,
 		} },
 		.radio = {
-			.name   = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux   = TV,
 			.gpio	= 0x0000000,
 		},
@@ -5790,7 +5607,7 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr   = ADDR_UNSET,
 		.gpiomask      = 0x618E700,
 		.inputs       = {{
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE1,
 			.gpio = 0x6010000,
@@ -5809,21 +5626,20 @@ struct saa7134_board saa7134_boards[] = {
 		.gpiomask       = 1 << 11,
 		.mpeg           = SAA7134_MPEG_DVB,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_comp,
+			.type = SAA7134_INPUT_COMPOSITE,
 			.vmux = 4,
 			.amux = LINE1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE1,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = TV,
 			.gpio = 0x0000800,
 		},
@@ -5837,16 +5653,15 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.mpeg		= SAA7134_MPEG_GO7007,
 		.inputs		= { {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 		}, {
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 3,
 			.amux = TV,
-			.tv   = 1,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 6,
 		.amux = LINE1,
 		} },
@@ -5862,25 +5677,24 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.inputs         = {{
-			.name = name_tv,
+			.type = SAA7134_INPUT_TV,
 			.vmux = 1,
 			.amux = LINE2,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 0,
 			.amux = LINE2,
 		}, {
-			.name = name_comp2,
+			.type = SAA7134_INPUT_COMPOSITE2,
 			.vmux = 3,
 			.amux = LINE2,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 		} },
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE1,
 		},
 	},
@@ -5893,34 +5707,62 @@ struct saa7134_board saa7134_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.gpiomask       = 0x0d,
 		.inputs         = {{
-			.name = name_tv_mono,
+			.type = SAA7134_INPUT_TV_MONO,
 			.vmux = 1,
 			.amux = LINE1,
 			.gpio = 0x00,
-			.tv   = 1,
 		}, {
-			.name = name_comp1,
+			.type = SAA7134_INPUT_COMPOSITE1,
 			.vmux = 3,
 			.amux = LINE2,
 			.gpio = 0x08,
 		}, {
-			.name = name_svideo,
+			.type = SAA7134_INPUT_SVIDEO,
 			.vmux = 8,
 			.amux = LINE2,
 			.gpio = 0x08,
 		} },
 		.radio = {
-			.name = name_radio,
+			.type = SAA7134_INPUT_RADIO,
 			.amux = LINE1,
 			.gpio = 0x04,
 		},
 		.mute = {
-			.name = name_mute,
+			.type = SAA7134_INPUT_MUTE,
 			.amux = LINE1,
 			.gpio = 0x08,
 		},
 	},
-
+	[SAA7134_BOARD_SNAZIO_TVPVR_PRO] = {
+		.name           = "SnaZio* TVPVR PRO",
+		.audio_clock    = 0x00187de7,
+		.tuner_type     = TUNER_PHILIPS_TDA8290,
+		.radio_type     = UNSET,
+		.tuner_addr     = ADDR_UNSET,
+		.radio_addr     = ADDR_UNSET,
+		.gpiomask       = 1 << 21,
+		.inputs         = { {
+			.type = SAA7134_INPUT_TV,
+			.vmux = 1,
+			.amux = TV,
+			.gpio = 0x0000000,
+		}, {
+			.type = SAA7134_INPUT_COMPOSITE1,
+			.vmux = 3,
+			.amux = LINE2,
+			.gpio = 0x0000000,
+		}, {
+			.type = SAA7134_INPUT_SVIDEO,
+			.vmux = 8,
+			.amux = LINE2,
+			.gpio = 0x0000000,
+		} },
+		.radio = {
+			.type = SAA7134_INPUT_RADIO,
+			.amux = TV,
+			.gpio = 0x0200000,
+		},
+	},
 };
 
 const unsigned int saa7134_bcount = ARRAY_SIZE(saa7134_boards);
@@ -7191,6 +7033,12 @@ struct pci_device_id saa7134_pci_tbl[] = {
 		.subdevice    = 0x6f3a,
 		.driver_data  = SAA7134_BOARD_LEADTEK_WINFAST_TV2100_FM,
 	}, {
+		.vendor       = PCI_VENDOR_ID_PHILIPS,
+		.device       = PCI_DEVICE_ID_PHILIPS_SAA7133,
+		.subvendor    = 0x1779, /* V One Multimedia PTE Ltd */
+		.subdevice    = 0x13cf,
+		.driver_data  = SAA7134_BOARD_SNAZIO_TVPVR_PRO,
+	}, {
 		/* --- boards without eeprom + subsystem ID --- */
 		.vendor       = PCI_VENDOR_ID_PHILIPS,
 		.device       = PCI_DEVICE_ID_PHILIPS_SAA7134,
@@ -7721,6 +7569,7 @@ int saa7134_board_init1(struct saa7134_dev *dev)
 	case SAA7134_BOARD_BEHOLD_H7:
 	case SAA7134_BOARD_BEHOLD_A7:
 	case SAA7134_BOARD_KWORLD_PC150U:
+	case SAA7134_BOARD_SNAZIO_TVPVR_PRO:
 		dev->has_remote = SAA7134_REMOTE_I2C;
 		break;
 	case SAA7134_BOARD_AVERMEDIA_A169_B:
diff --git a/drivers/media/pci/saa7134/saa7134-core.c b/drivers/media/pci/saa7134/saa7134-core.c
index e227b02cc122..c0e1780ec831 100644
--- a/drivers/media/pci/saa7134/saa7134-core.c
+++ b/drivers/media/pci/saa7134/saa7134-core.c
@@ -112,7 +112,7 @@ int (*saa7134_dmasound_exit)(struct saa7134_dev *dev);
 		printk(KERN_DEBUG pr_fmt("irq: " fmt), ## arg); \
 	} while (0)
 
-void saa7134_track_gpio(struct saa7134_dev *dev, char *msg)
+void saa7134_track_gpio(struct saa7134_dev *dev, const char *msg)
 {
 	unsigned long mode,status;
 
@@ -806,6 +806,154 @@ static void must_configure_manually(int has_eeprom)
 	}
 }
 
+static void saa7134_unregister_media_device(struct saa7134_dev *dev)
+{
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+	if (!dev->media_dev)
+		return;
+	media_device_unregister(dev->media_dev);
+	media_device_cleanup(dev->media_dev);
+	kfree(dev->media_dev);
+	dev->media_dev = NULL;
+#endif
+}
+
+static void saa7134_media_release(struct saa7134_dev *dev)
+{
+#ifdef CONFIG_MEDIA_CONTROLLER
+	int i;
+
+	for (i = 0; i < SAA7134_INPUT_MAX + 1; i++)
+		media_device_unregister_entity(&dev->input_ent[i]);
+#endif
+}
+
+#if defined(CONFIG_MEDIA_CONTROLLER)
+static void saa7134_create_entities(struct saa7134_dev *dev)
+{
+	int ret, i;
+	struct media_entity *entity;
+	struct media_entity *decoder = NULL;
+
+	/* Check if it is using an external analog TV demod */
+	media_device_for_each_entity(entity, dev->media_dev) {
+		if (entity->function == MEDIA_ENT_F_ATV_DECODER) {
+			decoder = entity;
+			break;
+		}
+	}
+
+	/*
+	 * saa713x is not using an external ATV demod.
+	 * Register the internal one
+	 */
+	if (!decoder) {
+		dev->demod.name = "saa713x";
+		dev->demod_pad[DEMOD_PAD_IF_INPUT].flags = MEDIA_PAD_FL_SINK;
+		dev->demod_pad[DEMOD_PAD_VID_OUT].flags = MEDIA_PAD_FL_SOURCE;
+		dev->demod_pad[DEMOD_PAD_VBI_OUT].flags = MEDIA_PAD_FL_SOURCE;
+		dev->demod.function = MEDIA_ENT_F_ATV_DECODER;
+
+		ret = media_entity_pads_init(&dev->demod, DEMOD_NUM_PADS,
+					     dev->demod_pad);
+		if (ret < 0)
+			pr_err("failed to initialize demod pad!\n");
+
+		ret = media_device_register_entity(dev->media_dev, &dev->demod);
+		if (ret < 0)
+			pr_err("failed to register demod entity!\n");
+
+		dev->decoder = &dev->demod;
+	} else {
+		dev->decoder = decoder;
+	}
+
+	/* Initialize Video, VBI and Radio pads */
+	dev->video_pad.flags = MEDIA_PAD_FL_SINK;
+	ret = media_entity_pads_init(&dev->video_dev->entity, 1,
+				     &dev->video_pad);
+	if (ret < 0)
+		pr_err("failed to initialize video media entity!\n");
+
+	dev->vbi_pad.flags = MEDIA_PAD_FL_SINK;
+	ret = media_entity_pads_init(&dev->vbi_dev->entity, 1,
+					&dev->vbi_pad);
+	if (ret < 0)
+		pr_err("failed to initialize vbi media entity!\n");
+
+	/* Create entities for each input connector */
+	for (i = 0; i < SAA7134_INPUT_MAX; i++) {
+		struct media_entity *ent = &dev->input_ent[i];
+		struct saa7134_input *in = &card_in(dev, i);
+
+		if (in->type == SAA7134_NO_INPUT)
+			break;
+
+		/* This input uses the S-Video connector */
+		if (in->type == SAA7134_INPUT_COMPOSITE_OVER_SVIDEO)
+			continue;
+
+		ent->name = saa7134_input_name[in->type];
+		ent->flags = MEDIA_ENT_FL_CONNECTOR;
+		dev->input_pad[i].flags = MEDIA_PAD_FL_SOURCE;
+
+		switch (in->type) {
+		case SAA7134_INPUT_COMPOSITE:
+		case SAA7134_INPUT_COMPOSITE0:
+		case SAA7134_INPUT_COMPOSITE1:
+		case SAA7134_INPUT_COMPOSITE2:
+		case SAA7134_INPUT_COMPOSITE3:
+		case SAA7134_INPUT_COMPOSITE4:
+			ent->function = MEDIA_ENT_F_CONN_COMPOSITE;
+			break;
+		case SAA7134_INPUT_SVIDEO:
+		case SAA7134_INPUT_SVIDEO0:
+		case SAA7134_INPUT_SVIDEO1:
+			ent->function = MEDIA_ENT_F_CONN_SVIDEO;
+			break;
+		default:
+			/*
+			 * SAA7134_INPUT_TV and SAA7134_INPUT_TV_MONO.
+			 *
+			 * Please notice that neither SAA7134_INPUT_MUTE or
+			 * SAA7134_INPUT_RADIO are defined at
+			 * saa7134_board.input.
+			 */
+			ent->function = MEDIA_ENT_F_CONN_RF;
+			break;
+		}
+
+		ret = media_entity_pads_init(ent, 1, &dev->input_pad[i]);
+		if (ret < 0)
+			pr_err("failed to initialize input pad[%d]!\n", i);
+
+		ret = media_device_register_entity(dev->media_dev, ent);
+		if (ret < 0)
+			pr_err("failed to register input entity %d!\n", i);
+	}
+
+	/* Create input for Radio RF connector */
+	if (card_has_radio(dev)) {
+		struct saa7134_input *in = &saa7134_boards[dev->board].radio;
+		struct media_entity *ent = &dev->input_ent[i];
+
+		ent->name = saa7134_input_name[in->type];
+		ent->flags = MEDIA_ENT_FL_CONNECTOR;
+		dev->input_pad[i].flags = MEDIA_PAD_FL_SOURCE;
+		ent->function = MEDIA_ENT_F_CONN_RF;
+
+		ret = media_entity_pads_init(ent, 1, &dev->input_pad[i]);
+		if (ret < 0)
+			pr_err("failed to initialize input pad[%d]!\n", i);
+
+		ret = media_device_register_entity(dev->media_dev, ent);
+		if (ret < 0)
+			pr_err("failed to register input entity %d!\n", i);
+	}
+}
+#endif
+
 static struct video_device *vdev_init(struct saa7134_dev *dev,
 				      struct video_device *template,
 				      char *type)
@@ -826,6 +974,8 @@ static struct video_device *vdev_init(struct saa7134_dev *dev,
 
 static void saa7134_unregister_video(struct saa7134_dev *dev)
 {
+	saa7134_media_release(dev);
+
 	if (dev->video_dev) {
 		if (video_is_registered(dev->video_dev))
 			video_unregister_device(dev->video_dev);
@@ -889,6 +1039,19 @@ static int saa7134_initdev(struct pci_dev *pci_dev,
 	if (NULL == dev)
 		return -ENOMEM;
 
+	dev->nr = saa7134_devcount;
+	sprintf(dev->name, "saa%x[%d]", pci_dev->device, dev->nr);
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+	dev->media_dev = kzalloc(sizeof(*dev->media_dev), GFP_KERNEL);
+	if (!dev->media_dev) {
+		err = -ENOMEM;
+		goto fail0;
+	}
+	media_device_pci_init(dev->media_dev, pci_dev, dev->name);
+	dev->v4l2_dev.mdev = dev->media_dev;
+#endif
+
 	err = v4l2_device_register(&pci_dev->dev, &dev->v4l2_dev);
 	if (err)
 		goto fail0;
@@ -900,9 +1063,6 @@ static int saa7134_initdev(struct pci_dev *pci_dev,
 		goto fail1;
 	}
 
-	dev->nr = saa7134_devcount;
-	sprintf(dev->name,"saa%x[%d]",pci_dev->device,dev->nr);
-
 	/* pci quirks */
 	if (pci_pci_problems) {
 		if (pci_pci_problems & PCIPCI_TRITON)
@@ -1102,6 +1262,15 @@ static int saa7134_initdev(struct pci_dev *pci_dev,
 		       dev->name, video_device_node_name(dev->radio_dev));
 	}
 
+#ifdef CONFIG_MEDIA_CONTROLLER
+	saa7134_create_entities(dev);
+
+	err = v4l2_mc_create_media_graph(dev->media_dev);
+	if (err) {
+		pr_err("failed to create media graph\n");
+		goto fail5;
+	}
+#endif
 	/* everything worked */
 	saa7134_devcount++;
 
@@ -1109,6 +1278,18 @@ static int saa7134_initdev(struct pci_dev *pci_dev,
 		saa7134_dmasound_init(dev);
 
 	request_submodules(dev);
+
+	/*
+	 * Do it at the end, to reduce dynamic configuration changes during
+	 * the device init. Yet, as request_modules() can be async, the
+	 * topology will likely change after load the saa7134 subdrivers.
+	 */
+#ifdef CONFIG_MEDIA_CONTROLLER
+	err = media_device_register(dev->media_dev);
+	if (err)
+		goto fail5;
+#endif
+
 	return 0;
 
  fail5:
@@ -1126,6 +1307,9 @@ static int saa7134_initdev(struct pci_dev *pci_dev,
  fail1:
 	v4l2_device_unregister(&dev->v4l2_dev);
  fail0:
+#ifdef CONFIG_MEDIA_CONTROLLER
+	kfree(dev->media_dev);
+#endif
 	kfree(dev);
 	return err;
 }
@@ -1188,9 +1372,10 @@ static void saa7134_finidev(struct pci_dev *pci_dev)
 	release_mem_region(pci_resource_start(pci_dev,0),
 			   pci_resource_len(pci_dev,0));
 
-
 	v4l2_device_unregister(&dev->v4l2_dev);
 
+	saa7134_unregister_media_device(dev);
+
 	/* free memory */
 	kfree(dev);
 }
diff --git a/drivers/media/pci/saa7134/saa7134-dvb.c b/drivers/media/pci/saa7134/saa7134-dvb.c
index 101ba8729416..db987e5b93eb 100644
--- a/drivers/media/pci/saa7134/saa7134-dvb.c
+++ b/drivers/media/pci/saa7134/saa7134-dvb.c
@@ -1883,8 +1883,15 @@ static int dvb_init(struct saa7134_dev *dev)
 	fe0->dvb.frontend->callback = saa7134_tuner_callback;
 
 	/* register everything else */
+#ifndef CONFIG_MEDIA_CONTROLLER_DVB
 	ret = vb2_dvb_register_bus(&dev->frontends, THIS_MODULE, dev,
-					&dev->pci->dev, adapter_nr, 0);
+				   &dev->pci->dev, NULL,
+				   adapter_nr, 0);
+#else
+	ret = vb2_dvb_register_bus(&dev->frontends, THIS_MODULE, dev,
+				   &dev->pci->dev, dev->media_dev,
+				   adapter_nr, 0);
+#endif
 
 	/* this sequence is necessary to make the tda1004x load its firmware
 	 * and to enter analog mode of hybrid boards
diff --git a/drivers/media/pci/saa7134/saa7134-empress.c b/drivers/media/pci/saa7134/saa7134-empress.c
index 56b932c97196..ca417a454d67 100644
--- a/drivers/media/pci/saa7134/saa7134-empress.c
+++ b/drivers/media/pci/saa7134/saa7134-empress.c
@@ -189,6 +189,7 @@ static const struct v4l2_ioctl_ops ts_ioctl_ops = {
 	.vidioc_querybuf		= vb2_ioctl_querybuf,
 	.vidioc_qbuf			= vb2_ioctl_qbuf,
 	.vidioc_dqbuf			= vb2_ioctl_dqbuf,
+	.vidioc_expbuf			= vb2_ioctl_expbuf,
 	.vidioc_streamon		= vb2_ioctl_streamon,
 	.vidioc_streamoff		= vb2_ioctl_streamoff,
 	.vidioc_g_frequency		= saa7134_g_frequency,
@@ -286,7 +287,7 @@ static int empress_init(struct saa7134_dev *dev)
 	 * transfers that do not start at the beginning of a page. A USERPTR
 	 * can start anywhere in a page, so USERPTR support is a no-go.
 	 */
-	q->io_modes = VB2_MMAP | VB2_READ;
+	q->io_modes = VB2_MMAP | VB2_DMABUF | VB2_READ;
 	q->drv_priv = &dev->ts_q;
 	q->ops = &saa7134_empress_qops;
 	q->gfp_flags = GFP_DMA32;
diff --git a/drivers/media/pci/saa7134/saa7134-go7007.c b/drivers/media/pci/saa7134/saa7134-go7007.c
index 8a2abb34186b..2799538e2d7e 100644
--- a/drivers/media/pci/saa7134/saa7134-go7007.c
+++ b/drivers/media/pci/saa7134/saa7134-go7007.c
@@ -378,7 +378,7 @@ static int saa7134_go7007_send_firmware(struct go7007 *go, u8 *data, int len)
 	return 0;
 }
 
-static struct go7007_hpi_ops saa7134_go7007_hpi_ops = {
+static const struct go7007_hpi_ops saa7134_go7007_hpi_ops = {
 	.interface_reset	= saa7134_go7007_interface_reset,
 	.write_interrupt	= saa7134_go7007_write_interrupt,
 	.read_interrupt		= saa7134_go7007_read_interrupt,
diff --git a/drivers/media/pci/saa7134/saa7134-input.c b/drivers/media/pci/saa7134/saa7134-input.c
index 69d32d3fa32c..c8042c3888cd 100644
--- a/drivers/media/pci/saa7134/saa7134-input.c
+++ b/drivers/media/pci/saa7134/saa7134-input.c
@@ -975,6 +975,27 @@ void saa7134_probe_i2c_ir(struct saa7134_dev *dev)
 			msg_msi.addr, dev->i2c_adap.name,
 			(1 == rc) ? "yes" : "no");
 		break;
+	case SAA7134_BOARD_SNAZIO_TVPVR_PRO:
+		dev->init_data.name = "SnaZio* TVPVR PRO";
+		dev->init_data.get_key = get_key_msi_tvanywhere_plus;
+		dev->init_data.ir_codes = RC_MAP_MSI_TVANYWHERE_PLUS;
+		/*
+		 * MSI TV@nyware Plus requires more frequent polling
+		 * otherwise it will miss some keypresses
+		 */
+		dev->init_data.polling_interval = 50;
+		info.addr = 0x30;
+		/*
+		 * MSI TV@nywhere Plus controller doesn't seem to
+		 *  respond to probes unless we read something from
+		 *  an existing device. Weird...
+		 * REVISIT: might no longer be needed
+		 */
+		rc = i2c_transfer(&dev->i2c_adap, &msg_msi, 1);
+		input_dbg("probe 0x%02x @ %s: %s\n",
+			msg_msi.addr, dev->i2c_adap.name,
+			(rc == 1) ? "yes" : "no");
+		break;
 	case SAA7134_BOARD_KWORLD_PC150U:
 		/* copied and modified from MSI TV@nywhere Plus */
 		dev->init_data.name = "Kworld PC150-U";
diff --git a/drivers/media/pci/saa7134/saa7134-tvaudio.c b/drivers/media/pci/saa7134/saa7134-tvaudio.c
index 21a579309575..38f94b742e28 100644
--- a/drivers/media/pci/saa7134/saa7134-tvaudio.c
+++ b/drivers/media/pci/saa7134/saa7134-tvaudio.c
@@ -192,7 +192,7 @@ static void mute_input_7134(struct saa7134_dev *dev)
 	in   = dev->input;
 	mute = (dev->ctl_mute ||
 		(dev->automute  &&  (&card(dev).radio) != in));
-	if (card(dev).mute.name) {
+	if (card(dev).mute.type) {
 		/*
 		 * 7130 - we'll mute using some unconnected audio input
 		 * 7134 - we'll probably should switch external mux with gpio
@@ -204,13 +204,14 @@ static void mute_input_7134(struct saa7134_dev *dev)
 	if (dev->hw_mute  == mute &&
 		dev->hw_input == in && !dev->insuspend) {
 		audio_dbg(1, "mute/input: nothing to do [mute=%d,input=%s]\n",
-			  mute, in->name);
+			  mute, saa7134_input_name[in->type]);
 		return;
 	}
 
 	audio_dbg(1, "ctl_mute=%d automute=%d input=%s  =>  mute=%d input=%s\n",
 		  dev->ctl_mute, dev->automute,
-		  dev->input->name, mute, in->name);
+		  saa7134_input_name[dev->input->type], mute,
+		  saa7134_input_name[in->type]);
 	dev->hw_mute  = mute;
 	dev->hw_input = in;
 
@@ -245,7 +246,7 @@ static void mute_input_7134(struct saa7134_dev *dev)
 	mask = card(dev).gpiomask;
 	saa_andorl(SAA7134_GPIO_GPMODE0 >> 2,   mask, mask);
 	saa_andorl(SAA7134_GPIO_GPSTATUS0 >> 2, mask, in->gpio);
-	saa7134_track_gpio(dev,in->name);
+	saa7134_track_gpio(dev, saa7134_input_name[in->type]);
 }
 
 static void tvaudio_setmode(struct saa7134_dev *dev,
@@ -756,14 +757,14 @@ static int mute_input_7133(struct saa7134_dev *dev)
 	if (0 != card(dev).gpiomask) {
 		mask = card(dev).gpiomask;
 
-		if (card(dev).mute.name && dev->ctl_mute)
+		if (card(dev).mute.type && dev->ctl_mute)
 			in = &card(dev).mute;
 		else
 			in = dev->input;
 
 		saa_andorl(SAA7134_GPIO_GPMODE0 >> 2,   mask, mask);
 		saa_andorl(SAA7134_GPIO_GPSTATUS0 >> 2, mask, in->gpio);
-		saa7134_track_gpio(dev,in->name);
+		saa7134_track_gpio(dev, saa7134_input_name[in->type]);
 	}
 
 	return 0;
diff --git a/drivers/media/pci/saa7134/saa7134-video.c b/drivers/media/pci/saa7134/saa7134-video.c
index a63c1366a64e..ffa39543eb65 100644
--- a/drivers/media/pci/saa7134/saa7134-video.c
+++ b/drivers/media/pci/saa7134/saa7134-video.c
@@ -409,7 +409,8 @@ static void set_tvnorm(struct saa7134_dev *dev, struct saa7134_tvnorm *norm)
 
 static void video_mux(struct saa7134_dev *dev, int input)
 {
-	video_dbg("video input = %d [%s]\n", input, card_in(dev, input).name);
+	video_dbg("video input = %d [%s]\n",
+		  input, saa7134_input_name[card_in(dev, input).type]);
 	dev->ctl_input = input;
 	set_tvnorm(dev, dev->tvnorm);
 	saa7134_tvaudio_setinput(dev, &card_in(dev, input));
@@ -478,8 +479,7 @@ void saa7134_set_tvnorm_hw(struct saa7134_dev *dev)
 {
 	saa7134_set_decoder(dev);
 
-	if (card_in(dev, dev->ctl_input).tv)
-		saa_call_all(dev, video, s_std, dev->tvnorm->id);
+	saa_call_all(dev, video, s_std, dev->tvnorm->id);
 	/* Set the correct norm for the saa6752hs. This function
 	   does nothing if there is no saa6752hs. */
 	saa_call_empress(dev, video, s_std, dev->tvnorm->id);
@@ -785,6 +785,63 @@ static int stop_preview(struct saa7134_dev *dev)
 	return 0;
 }
 
+/*
+ * Media Controller helper functions
+ */
+
+static int saa7134_enable_analog_tuner(struct saa7134_dev *dev)
+{
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct media_device *mdev = dev->media_dev;
+	struct media_entity *source;
+	struct media_link *link, *found_link = NULL;
+	int ret, active_links = 0;
+
+	if (!mdev || !dev->decoder)
+		return 0;
+
+	/*
+	 * This will find the tuner that is connected into the decoder.
+	 * Technically, this is not 100% correct, as the device may be
+	 * using an analog input instead of the tuner. However, as we can't
+	 * do DVB streaming while the DMA engine is being used for V4L2,
+	 * this should be enough for the actual needs.
+	 */
+	list_for_each_entry(link, &dev->decoder->links, list) {
+		if (link->sink->entity == dev->decoder) {
+			found_link = link;
+			if (link->flags & MEDIA_LNK_FL_ENABLED)
+				active_links++;
+			break;
+		}
+	}
+
+	if (active_links == 1 || !found_link)
+		return 0;
+
+	source = found_link->source->entity;
+	list_for_each_entry(link, &source->links, list) {
+		struct media_entity *sink;
+		int flags = 0;
+
+		sink = link->sink->entity;
+
+		if (sink == dev->decoder)
+			flags = MEDIA_LNK_FL_ENABLED;
+
+		ret = media_entity_setup_link(link, flags);
+		if (ret) {
+			pr_err("Couldn't change link %s->%s to %s. Error %d\n",
+			       source->name, sink->name,
+			       flags ? "enabled" : "disabled",
+			       ret);
+			return ret;
+		}
+	}
+#endif
+	return 0;
+}
+
 /* ------------------------------------------------------------------ */
 
 static int buffer_activate(struct saa7134_dev *dev,
@@ -924,6 +981,9 @@ static int queue_setup(struct vb2_queue *q,
 	*nplanes = 1;
 	sizes[0] = size;
 	alloc_ctxs[0] = dev->alloc_ctx;
+
+	saa7134_enable_analog_tuner(dev);
+
 	return 0;
 }
 
@@ -1219,10 +1279,13 @@ static int saa7134_g_fmt_vid_cap(struct file *file, void *priv,
 	f->fmt.pix.height       = dev->height;
 	f->fmt.pix.field        = dev->field;
 	f->fmt.pix.pixelformat  = dev->fmt->fourcc;
-	f->fmt.pix.bytesperline =
-		(f->fmt.pix.width * dev->fmt->depth) >> 3;
+	if (dev->fmt->planar)
+		f->fmt.pix.bytesperline = f->fmt.pix.width;
+	else
+		f->fmt.pix.bytesperline =
+			(f->fmt.pix.width * dev->fmt->depth) / 8;
 	f->fmt.pix.sizeimage =
-		f->fmt.pix.height * f->fmt.pix.bytesperline;
+		(f->fmt.pix.height * f->fmt.pix.width * dev->fmt->depth) / 8;
 	f->fmt.pix.colorspace   = V4L2_COLORSPACE_SMPTE170M;
 	return 0;
 }
@@ -1298,10 +1361,13 @@ static int saa7134_try_fmt_vid_cap(struct file *file, void *priv,
 	if (f->fmt.pix.height > maxh)
 		f->fmt.pix.height = maxh;
 	f->fmt.pix.width &= ~0x03;
-	f->fmt.pix.bytesperline =
-		(f->fmt.pix.width * fmt->depth) >> 3;
+	if (fmt->planar)
+		f->fmt.pix.bytesperline = f->fmt.pix.width;
+	else
+		f->fmt.pix.bytesperline =
+			(f->fmt.pix.width * fmt->depth) / 8;
 	f->fmt.pix.sizeimage =
-		f->fmt.pix.height * f->fmt.pix.bytesperline;
+		(f->fmt.pix.height * f->fmt.pix.width * fmt->depth) / 8;
 	f->fmt.pix.colorspace   = V4L2_COLORSPACE_SMPTE170M;
 
 	return 0;
@@ -1381,13 +1447,19 @@ int saa7134_enum_input(struct file *file, void *priv, struct v4l2_input *i)
 	n = i->index;
 	if (n >= SAA7134_INPUT_MAX)
 		return -EINVAL;
-	if (NULL == card_in(dev, i->index).name)
+	if (card_in(dev, i->index).type == SAA7134_NO_INPUT)
 		return -EINVAL;
 	i->index = n;
-	i->type  = V4L2_INPUT_TYPE_CAMERA;
-	strcpy(i->name, card_in(dev, n).name);
-	if (card_in(dev, n).tv)
+	strcpy(i->name, saa7134_input_name[card_in(dev, n).type]);
+	switch (card_in(dev, n).type) {
+	case SAA7134_INPUT_TV:
+	case SAA7134_INPUT_TV_MONO:
 		i->type = V4L2_INPUT_TYPE_TUNER;
+		break;
+	default:
+		i->type  = V4L2_INPUT_TYPE_CAMERA;
+		break;
+	}
 	if (n == dev->ctl_input) {
 		int v1 = saa_readb(SAA7134_STATUS_VIDEO1);
 		int v2 = saa_readb(SAA7134_STATUS_VIDEO2);
@@ -1419,7 +1491,7 @@ int saa7134_s_input(struct file *file, void *priv, unsigned int i)
 
 	if (i >= SAA7134_INPUT_MAX)
 		return -EINVAL;
-	if (NULL == card_in(dev, i).name)
+	if (card_in(dev, i).type == SAA7134_NO_INPUT)
 		return -EINVAL;
 	video_mux(dev, i);
 	return 0;
@@ -1656,12 +1728,13 @@ int saa7134_g_tuner(struct file *file, void *priv,
 		return -EINVAL;
 	memset(t, 0, sizeof(*t));
 	for (n = 0; n < SAA7134_INPUT_MAX; n++) {
-		if (card_in(dev, n).tv)
+		if (card_in(dev, n).type == SAA7134_INPUT_TV ||
+		    card_in(dev, n).type == SAA7134_INPUT_TV_MONO)
 			break;
 	}
 	if (n == SAA7134_INPUT_MAX)
 		return -EINVAL;
-	if (NULL != card_in(dev, n).name) {
+	if (card_in(dev, n).type != SAA7134_NO_INPUT) {
 		strcpy(t->name, "Television");
 		t->type = V4L2_TUNER_ANALOG_TV;
 		saa_call_all(dev, tuner, g_tuner, t);
@@ -1906,6 +1979,7 @@ static const struct v4l2_ioctl_ops video_ioctl_ops = {
 	.vidioc_querybuf		= vb2_ioctl_querybuf,
 	.vidioc_qbuf			= vb2_ioctl_qbuf,
 	.vidioc_dqbuf			= vb2_ioctl_dqbuf,
+	.vidioc_expbuf			= vb2_ioctl_expbuf,
 	.vidioc_s_std			= saa7134_s_std,
 	.vidioc_g_std			= saa7134_g_std,
 	.vidioc_querystd		= saa7134_querystd,
@@ -2089,7 +2163,7 @@ int saa7134_video_init1(struct saa7134_dev *dev)
 	 * USERPTR support is a no-go unless the application knows about these
 	 * limitations and has special support for this.
 	 */
-	q->io_modes = VB2_MMAP | VB2_READ;
+	q->io_modes = VB2_MMAP | VB2_DMABUF | VB2_READ;
 	if (saa7134_userptr)
 		q->io_modes |= VB2_USERPTR;
 	q->drv_priv = &dev->video_q;
diff --git a/drivers/media/pci/saa7134/saa7134.h b/drivers/media/pci/saa7134/saa7134.h
index 5938bc781999..69a9bbf22d4d 100644
--- a/drivers/media/pci/saa7134/saa7134.h
+++ b/drivers/media/pci/saa7134/saa7134.h
@@ -343,6 +343,7 @@ struct saa7134_card_ir {
 #define SAA7134_BOARD_WIS_VOYAGER           193
 #define SAA7134_BOARD_AVERMEDIA_505         194
 #define SAA7134_BOARD_LEADTEK_WINFAST_TV2100_FM 195
+#define SAA7134_BOARD_SNAZIO_TVPVR_PRO      196
 
 #define SAA7134_MAXBOARDS 32
 #define SAA7134_INPUT_MAX 8
@@ -361,12 +362,29 @@ struct saa7134_card_ir {
 #define SET_CLOCK_INVERTED			(1 << 2)
 #define SET_VSYNC_OFF				(1 << 3)
 
+enum saa7134_input_types {
+	SAA7134_NO_INPUT = 0,
+	SAA7134_INPUT_MUTE,
+	SAA7134_INPUT_RADIO,
+	SAA7134_INPUT_TV,
+	SAA7134_INPUT_TV_MONO,
+	SAA7134_INPUT_COMPOSITE,
+	SAA7134_INPUT_COMPOSITE0,
+	SAA7134_INPUT_COMPOSITE1,
+	SAA7134_INPUT_COMPOSITE2,
+	SAA7134_INPUT_COMPOSITE3,
+	SAA7134_INPUT_COMPOSITE4,
+	SAA7134_INPUT_SVIDEO,
+	SAA7134_INPUT_SVIDEO0,
+	SAA7134_INPUT_SVIDEO1,
+	SAA7134_INPUT_COMPOSITE_OVER_SVIDEO,
+};
+
 struct saa7134_input {
-	char                    *name;
-	unsigned int            vmux;
-	enum saa7134_audio_in   amux;
-	unsigned int            gpio;
-	unsigned int            tv:1;
+	enum saa7134_input_types type;
+	unsigned int             vmux;
+	enum saa7134_audio_in    amux;
+	unsigned int             gpio;
 };
 
 enum saa7134_mpeg_type {
@@ -410,7 +428,7 @@ struct saa7134_board {
 	unsigned int            ts_force_val:1;
 };
 
-#define card_has_radio(dev)   (NULL != saa7134_boards[dev->board].radio.name)
+#define card_has_radio(dev)   (SAA7134_NO_INPUT != saa7134_boards[dev->board].radio.type)
 #define card_is_empress(dev)  (SAA7134_MPEG_EMPRESS == saa7134_boards[dev->board].mpeg)
 #define card_is_dvb(dev)      (SAA7134_MPEG_DVB     == saa7134_boards[dev->board].mpeg)
 #define card_is_go7007(dev)   (SAA7134_MPEG_GO7007  == saa7134_boards[dev->board].mpeg)
@@ -654,6 +672,19 @@ struct saa7134_dev {
 	/* I2C keyboard data */
 	struct IR_i2c_init_data    init_data;
 
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct media_device *media_dev;
+
+	struct media_entity input_ent[SAA7134_INPUT_MAX + 1];
+	struct media_pad input_pad[SAA7134_INPUT_MAX + 1];
+
+	struct media_entity demod;
+	struct media_pad demod_pad[DEMOD_NUM_PADS];
+
+	struct media_pad video_pad, vbi_pad;
+	struct media_entity *decoder;
+#endif
+
 #if IS_ENABLED(CONFIG_VIDEO_SAA7134_DVB)
 	/* SAA7134_MPEG_DVB only */
 	struct vb2_dvb_frontends frontends;
@@ -727,7 +758,7 @@ extern struct mutex saa7134_devlist_lock;
 extern int saa7134_no_overlay;
 extern bool saa7134_userptr;
 
-void saa7134_track_gpio(struct saa7134_dev *dev, char *msg);
+void saa7134_track_gpio(struct saa7134_dev *dev, const char *msg);
 void saa7134_set_gpio(struct saa7134_dev *dev, int bit_no, int value);
 
 #define SAA7134_PGTABLE_SIZE 4096
@@ -760,6 +791,7 @@ extern int (*saa7134_dmasound_exit)(struct saa7134_dev *dev);
 /* saa7134-cards.c                                             */
 
 extern struct saa7134_board saa7134_boards[];
+extern const char * const saa7134_input_name[];
 extern const unsigned int saa7134_bcount;
 extern struct pci_device_id saa7134_pci_tbl[];
 
diff --git a/drivers/media/pci/ttpci/av7110.c b/drivers/media/pci/ttpci/av7110.c
index a69dc6a0752b..382caf200ba1 100644
--- a/drivers/media/pci/ttpci/av7110.c
+++ b/drivers/media/pci/ttpci/av7110.c
@@ -1739,7 +1739,7 @@ static int alps_tdlb7_request_firmware(struct dvb_frontend* fe, const struct fir
 #endif
 }
 
-static struct sp8870_config alps_tdlb7_config = {
+static const struct sp8870_config alps_tdlb7_config = {
 
 	.demod_address = 0x71,
 	.request_firmware = alps_tdlb7_request_firmware,
@@ -2198,13 +2198,18 @@ static int frontend_init(struct av7110 *av7110)
 			break;
 
 		case 0x0001: // Hauppauge/TT Nexus-T premium rev1.X
+		{
+			struct dvb_frontend *fe;
+
 			// try ALPS TDLB7 first, then Grundig 29504-401
-			av7110->fe = dvb_attach(sp8870_attach, &alps_tdlb7_config, &av7110->i2c_adap);
-			if (av7110->fe) {
-				av7110->fe->ops.tuner_ops.set_params = alps_tdlb7_tuner_set_params;
+			fe = dvb_attach(sp8870_attach, &alps_tdlb7_config, &av7110->i2c_adap);
+			if (fe) {
+				fe->ops.tuner_ops.set_params = alps_tdlb7_tuner_set_params;
+				av7110->fe = fe;
 				break;
 			}
-			/* fall-thru */
+		}
+		/* fall-thru */
 
 		case 0x0008: // Hauppauge/TT DVB-T
 			// Grundig 29504-401
diff --git a/drivers/media/pci/ttpci/budget.c b/drivers/media/pci/ttpci/budget.c
index de54310a2660..fb8ede5a1531 100644
--- a/drivers/media/pci/ttpci/budget.c
+++ b/drivers/media/pci/ttpci/budget.c
@@ -615,36 +615,50 @@ static void frontend_init(struct budget *budget)
 		break;
 
 	case 0x1016: // Hauppauge/TT Nova-S SE (samsung s5h1420/????(tda8260))
-		budget->dvb_frontend = dvb_attach(s5h1420_attach, &s5h1420_config, &budget->i2c_adap);
-		if (budget->dvb_frontend) {
-			budget->dvb_frontend->ops.tuner_ops.set_params = s5h1420_tuner_set_params;
-			if (dvb_attach(lnbp21_attach, budget->dvb_frontend, &budget->i2c_adap, 0, 0) == NULL) {
+	{
+		struct dvb_frontend *fe;
+
+		fe = dvb_attach(s5h1420_attach, &s5h1420_config, &budget->i2c_adap);
+		if (fe) {
+			fe->ops.tuner_ops.set_params = s5h1420_tuner_set_params;
+			budget->dvb_frontend = fe;
+			if (dvb_attach(lnbp21_attach, fe, &budget->i2c_adap,
+				       0, 0) == NULL) {
 				printk("%s: No LNBP21 found!\n", __func__);
 				goto error_out;
 			}
 			break;
 		}
-
+	}
+	/* fall through */
 	case 0x1018: // TT Budget-S-1401 (philips tda10086/philips tda8262)
+	{
+		struct dvb_frontend *fe;
+
 		// gpio2 is connected to CLB - reset it + leave it high
 		saa7146_setgpio(budget->dev, 2, SAA7146_GPIO_OUTLO);
 		msleep(1);
 		saa7146_setgpio(budget->dev, 2, SAA7146_GPIO_OUTHI);
 		msleep(1);
 
-		budget->dvb_frontend = dvb_attach(tda10086_attach, &tda10086_config, &budget->i2c_adap);
-		if (budget->dvb_frontend) {
-			if (dvb_attach(tda826x_attach, budget->dvb_frontend, 0x60, &budget->i2c_adap, 0) == NULL)
+		fe = dvb_attach(tda10086_attach, &tda10086_config, &budget->i2c_adap);
+		if (fe) {
+			budget->dvb_frontend = fe;
+			if (dvb_attach(tda826x_attach, fe, 0x60,
+				       &budget->i2c_adap, 0) == NULL)
 				printk("%s: No tda826x found!\n", __func__);
-			if (dvb_attach(lnbp21_attach, budget->dvb_frontend, &budget->i2c_adap, 0, 0) == NULL) {
+			if (dvb_attach(lnbp21_attach, fe,
+				       &budget->i2c_adap, 0, 0) == NULL) {
 				printk("%s: No LNBP21 found!\n", __func__);
 				goto error_out;
 			}
 			break;
 		}
+	}
+	/* fall through */
 
 	case 0x101c: { /* TT S2-1600 */
-			struct stv6110x_devctl *ctl;
+			const struct stv6110x_devctl *ctl;
 			saa7146_setgpio(budget->dev, 2, SAA7146_GPIO_OUTLO);
 			msleep(50);
 			saa7146_setgpio(budget->dev, 2, SAA7146_GPIO_OUTHI);
@@ -697,7 +711,7 @@ static void frontend_init(struct budget *budget)
 		break;
 
 	case 0x1020: { /* Omicom S2 */
-			struct stv6110x_devctl *ctl;
+			const struct stv6110x_devctl *ctl;
 			saa7146_setgpio(budget->dev, 2, SAA7146_GPIO_OUTLO);
 			msleep(50);
 			saa7146_setgpio(budget->dev, 2, SAA7146_GPIO_OUTHI);
diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 8b89ebe16d94..201f5c296a95 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -54,15 +54,6 @@ config VIDEO_VIU
 	  Say Y here if you want to enable VIU device on MPC5121e Rev2+.
 	  In doubt, say N.
 
-config VIDEO_TIMBERDALE
-	tristate "Support for timberdale Video In/LogiWIN"
-	depends on VIDEO_V4L2 && I2C && VIDEO_V4L2_SUBDEV_API && HAS_DMA
-	depends on (MFD_TIMBERDALE && TIMB_DMA) || COMPILE_TEST
-	select VIDEO_ADV7180
-	select VIDEOBUF_DMA_CONTIG
-	---help---
-	  Add support for the Video In peripherial of the timberdale FPGA.
-
 config VIDEO_M32R_AR
 	tristate "AR devices"
 	depends on VIDEO_V4L2
@@ -120,6 +111,19 @@ source "drivers/media/platform/s5p-tv/Kconfig"
 source "drivers/media/platform/am437x/Kconfig"
 source "drivers/media/platform/xilinx/Kconfig"
 
+config VIDEO_TI_CAL
+	tristate "TI CAL (Camera Adaptation Layer) driver"
+	depends on VIDEO_DEV && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
+	depends on SOC_DRA7XX || COMPILE_TEST
+	depends on HAS_DMA
+	select VIDEOBUF2_DMA_CONTIG
+	default n
+	---help---
+	  Support for the TI CAL (Camera Adaptation Layer) block
+	  found on DRA72X SoC.
+	  In TI Technical Reference Manual this module is referred as
+	  Camera Interface Subsystem (CAMSS).
+
 endif # V4L_PLATFORM_DRIVERS
 
 menuconfig V4L_MEM2MEM_DRIVERS
diff --git a/drivers/media/platform/Makefile b/drivers/media/platform/Makefile
index efa0295af87b..bbb7bd1eb268 100644
--- a/drivers/media/platform/Makefile
+++ b/drivers/media/platform/Makefile
@@ -2,7 +2,6 @@
 # Makefile for the video capture/playback device drivers.
 #
 
-obj-$(CONFIG_VIDEO_TIMBERDALE)	+= timblogiw.o
 obj-$(CONFIG_VIDEO_M32R_AR_M64278) += arv.o
 
 obj-$(CONFIG_VIDEO_VIA_CAMERA) += via-camera.o
@@ -18,6 +17,8 @@ obj-$(CONFIG_VIDEO_VIM2M)		+= vim2m.o
 
 obj-$(CONFIG_VIDEO_TI_VPE)		+= ti-vpe/
 
+obj-$(CONFIG_VIDEO_TI_CAL)		+= ti-vpe/
+
 obj-$(CONFIG_VIDEO_MX2_EMMAPRP)		+= mx2_emmaprp.o
 obj-$(CONFIG_VIDEO_CODA) 		+= coda/
 
diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index 7d28899f89ce..b6625047250d 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -1342,7 +1342,7 @@ static void coda_finish_encode(struct coda_ctx *ctx)
 
 	/* Calculate bytesused field */
 	if (dst_buf->sequence == 0) {
-		vb2_set_plane_payload(&dst_buf->vb2_buf, 0,
+		vb2_set_plane_payload(&dst_buf->vb2_buf, 0, wr_ptr - start_ptr +
 					ctx->vpu_header_size[0] +
 					ctx->vpu_header_size[1] +
 					ctx->vpu_header_size[2]);
@@ -1455,9 +1455,9 @@ static int coda_alloc_bitstream_buffer(struct coda_ctx *ctx,
 		return 0;
 
 	ctx->bitstream.size = roundup_pow_of_two(q_data->sizeimage * 2);
-	ctx->bitstream.vaddr = dma_alloc_writecombine(
-			&ctx->dev->plat_dev->dev, ctx->bitstream.size,
-			&ctx->bitstream.paddr, GFP_KERNEL);
+	ctx->bitstream.vaddr = dma_alloc_wc(&ctx->dev->plat_dev->dev,
+					    ctx->bitstream.size,
+					    &ctx->bitstream.paddr, GFP_KERNEL);
 	if (!ctx->bitstream.vaddr) {
 		v4l2_err(&ctx->dev->v4l2_dev,
 			 "failed to allocate bitstream ringbuffer");
@@ -1474,8 +1474,8 @@ static void coda_free_bitstream_buffer(struct coda_ctx *ctx)
 	if (ctx->bitstream.vaddr == NULL)
 		return;
 
-	dma_free_writecombine(&ctx->dev->plat_dev->dev, ctx->bitstream.size,
-			      ctx->bitstream.vaddr, ctx->bitstream.paddr);
+	dma_free_wc(&ctx->dev->plat_dev->dev, ctx->bitstream.size,
+		    ctx->bitstream.vaddr, ctx->bitstream.paddr);
 	ctx->bitstream.vaddr = NULL;
 	kfifo_init(&ctx->bitstream_fifo, NULL, 0);
 }
diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c
index 2d782ce94a67..133ab9f70f85 100644
--- a/drivers/media/platform/coda/coda-common.c
+++ b/drivers/media/platform/coda/coda-common.c
@@ -1950,16 +1950,76 @@ static int coda_register_device(struct coda_dev *dev, int i)
 	return video_register_device(vfd, VFL_TYPE_GRABBER, 0);
 }
 
+static void coda_copy_firmware(struct coda_dev *dev, const u8 * const buf,
+			       size_t size)
+{
+	u32 *src = (u32 *)buf;
+
+	/* Check if the firmware has a 16-byte Freescale header, skip it */
+	if (buf[0] == 'M' && buf[1] == 'X')
+		src += 4;
+	/*
+	 * Check whether the firmware is in native order or pre-reordered for
+	 * memory access. The first instruction opcode always is 0xe40e.
+	 */
+	if (__le16_to_cpup((__le16 *)src) == 0xe40e) {
+		u32 *dst = dev->codebuf.vaddr;
+		int i;
+
+		/* Firmware in native order, reorder while copying */
+		if (dev->devtype->product == CODA_DX6) {
+			for (i = 0; i < (size - 16) / 4; i++)
+				dst[i] = (src[i] << 16) | (src[i] >> 16);
+		} else {
+			for (i = 0; i < (size - 16) / 4; i += 2) {
+				dst[i] = (src[i + 1] << 16) | (src[i + 1] >> 16);
+				dst[i + 1] = (src[i] << 16) | (src[i] >> 16);
+			}
+		}
+	} else {
+		/* Copy the already reordered firmware image */
+		memcpy(dev->codebuf.vaddr, src, size);
+	}
+}
+
+static void coda_fw_callback(const struct firmware *fw, void *context);
+
+static int coda_firmware_request(struct coda_dev *dev)
+{
+	char *fw = dev->devtype->firmware[dev->firmware];
+
+	dev_dbg(&dev->plat_dev->dev, "requesting firmware '%s' for %s\n", fw,
+		coda_product_name(dev->devtype->product));
+
+	return request_firmware_nowait(THIS_MODULE, true, fw,
+				       &dev->plat_dev->dev, GFP_KERNEL, dev,
+				       coda_fw_callback);
+}
+
 static void coda_fw_callback(const struct firmware *fw, void *context)
 {
 	struct coda_dev *dev = context;
 	struct platform_device *pdev = dev->plat_dev;
 	int i, ret;
 
-	if (!fw) {
+	if (!fw && dev->firmware == 1) {
 		v4l2_err(&dev->v4l2_dev, "firmware request failed\n");
 		goto put_pm;
 	}
+	if (!fw) {
+		dev->firmware = 1;
+		coda_firmware_request(dev);
+		return;
+	}
+	if (dev->firmware == 1) {
+		/*
+		 * Since we can't suppress warnings for failed asynchronous
+		 * firmware requests, report that the fallback firmware was
+		 * found.
+		 */
+		dev_info(&pdev->dev, "Using fallback firmware %s\n",
+			 dev->devtype->firmware[dev->firmware]);
+	}
 
 	/* allocate auxiliary per-device code buffer for the BIT processor */
 	ret = coda_alloc_aux_buf(dev, &dev->codebuf, fw->size, "codebuf",
@@ -1967,8 +2027,7 @@ static void coda_fw_callback(const struct firmware *fw, void *context)
 	if (ret < 0)
 		goto put_pm;
 
-	/* Copy the whole firmware image to the code buffer */
-	memcpy(dev->codebuf.vaddr, fw->data, fw->size);
+	coda_copy_firmware(dev, fw->data, fw->size);
 	release_firmware(fw);
 
 	ret = coda_hw_init(dev);
@@ -2019,17 +2078,6 @@ put_pm:
 	pm_runtime_put_sync(&pdev->dev);
 }
 
-static int coda_firmware_request(struct coda_dev *dev)
-{
-	char *fw = dev->devtype->firmware;
-
-	dev_dbg(&dev->plat_dev->dev, "requesting firmware '%s' for %s\n", fw,
-		coda_product_name(dev->devtype->product));
-
-	return request_firmware_nowait(THIS_MODULE, true,
-		fw, &dev->plat_dev->dev, GFP_KERNEL, dev, coda_fw_callback);
-}
-
 enum coda_platform {
 	CODA_IMX27,
 	CODA_IMX53,
@@ -2039,7 +2087,10 @@ enum coda_platform {
 
 static const struct coda_devtype coda_devdata[] = {
 	[CODA_IMX27] = {
-		.firmware     = "v4l-codadx6-imx27.bin",
+		.firmware     = {
+			"vpu_fw_imx27_TO2.bin",
+			"v4l-codadx6-imx27.bin"
+		},
 		.product      = CODA_DX6,
 		.codecs       = codadx6_codecs,
 		.num_codecs   = ARRAY_SIZE(codadx6_codecs),
@@ -2049,7 +2100,10 @@ static const struct coda_devtype coda_devdata[] = {
 		.iram_size    = 0xb000,
 	},
 	[CODA_IMX53] = {
-		.firmware     = "v4l-coda7541-imx53.bin",
+		.firmware     = {
+			"vpu_fw_imx53.bin",
+			"v4l-coda7541-imx53.bin"
+		},
 		.product      = CODA_7541,
 		.codecs       = coda7_codecs,
 		.num_codecs   = ARRAY_SIZE(coda7_codecs),
@@ -2060,7 +2114,10 @@ static const struct coda_devtype coda_devdata[] = {
 		.iram_size    = 0x14000,
 	},
 	[CODA_IMX6Q] = {
-		.firmware     = "v4l-coda960-imx6q.bin",
+		.firmware     = {
+			"vpu_fw_imx6q.bin",
+			"v4l-coda960-imx6q.bin"
+		},
 		.product      = CODA_960,
 		.codecs       = coda9_codecs,
 		.num_codecs   = ARRAY_SIZE(coda9_codecs),
@@ -2071,7 +2128,10 @@ static const struct coda_devtype coda_devdata[] = {
 		.iram_size    = 0x21000,
 	},
 	[CODA_IMX6DL] = {
-		.firmware     = "v4l-coda960-imx6dl.bin",
+		.firmware     = {
+			"vpu_fw_imx6d.bin",
+			"v4l-coda960-imx6dl.bin"
+		},
 		.product      = CODA_960,
 		.codecs       = coda9_codecs,
 		.num_codecs   = ARRAY_SIZE(coda9_codecs),
@@ -2118,14 +2178,12 @@ static int coda_probe(struct platform_device *pdev)
 
 	pdev_id = of_id ? of_id->data : platform_get_device_id(pdev);
 
-	if (of_id) {
+	if (of_id)
 		dev->devtype = of_id->data;
-	} else if (pdev_id) {
+	else if (pdev_id)
 		dev->devtype = &coda_devdata[pdev_id->driver_data];
-	} else {
-		ret = -EINVAL;
-		goto err_v4l2_register;
-	}
+	else
+		return -EINVAL;
 
 	spin_lock_init(&dev->irqlock);
 	INIT_LIST_HEAD(&dev->instances);
diff --git a/drivers/media/platform/coda/coda.h b/drivers/media/platform/coda/coda.h
index d08e9843e9f2..8f2c71e06966 100644
--- a/drivers/media/platform/coda/coda.h
+++ b/drivers/media/platform/coda/coda.h
@@ -50,7 +50,7 @@ enum coda_product {
 struct coda_video_device;
 
 struct coda_devtype {
-	char			*firmware;
+	char			*firmware[2];
 	enum coda_product	product;
 	const struct coda_codec	*codecs;
 	unsigned int		num_codecs;
@@ -74,6 +74,7 @@ struct coda_dev {
 	struct video_device	vfd[5];
 	struct platform_device	*plat_dev;
 	const struct coda_devtype *devtype;
+	int			firmware;
 
 	void __iomem		*regs_base;
 	struct clk		*clk_per;
diff --git a/drivers/media/platform/davinci/dm644x_ccdc.c b/drivers/media/platform/davinci/dm644x_ccdc.c
index ffbefdff6b5e..6fba32bec974 100644
--- a/drivers/media/platform/davinci/dm644x_ccdc.c
+++ b/drivers/media/platform/davinci/dm644x_ccdc.c
@@ -261,7 +261,7 @@ static int ccdc_update_raw_params(struct ccdc_config_params_raw *raw_params)
 	 */
 	if (raw_params->fault_pxl.fp_num != config_params->fault_pxl.fp_num) {
 		if (fpc_physaddr != NULL) {
-			free_pages((unsigned long)fpc_physaddr,
+			free_pages((unsigned long)fpc_virtaddr,
 				   get_order
 				   (config_params->fault_pxl.fp_num *
 				   FP_NUM_BYTES));
diff --git a/drivers/media/platform/exynos-gsc/gsc-m2m.c b/drivers/media/platform/exynos-gsc/gsc-m2m.c
index 93782f15b825..a600e32e2543 100644
--- a/drivers/media/platform/exynos-gsc/gsc-m2m.c
+++ b/drivers/media/platform/exynos-gsc/gsc-m2m.c
@@ -700,7 +700,7 @@ static unsigned int gsc_m2m_poll(struct file *file,
 {
 	struct gsc_ctx *ctx = fh_to_ctx(file->private_data);
 	struct gsc_dev *gsc = ctx->gsc_dev;
-	int ret;
+	unsigned int ret;
 
 	if (mutex_lock_interruptible(&gsc->lock))
 		return -ERESTARTSYS;
diff --git a/drivers/media/platform/exynos4-is/fimc-lite.c b/drivers/media/platform/exynos4-is/fimc-lite.c
index e85649147dc8..dc1b929f7a33 100644
--- a/drivers/media/platform/exynos4-is/fimc-lite.c
+++ b/drivers/media/platform/exynos4-is/fimc-lite.c
@@ -992,10 +992,6 @@ static int fimc_lite_link_setup(struct media_entity *entity,
 
 	switch (local->index) {
 	case FLITE_SD_PAD_SINK:
-		if (!is_media_entity_v4l2_subdev(remote->entity)) {
-			ret = -EINVAL;
-			break;
-		}
 		if (flags & MEDIA_LNK_FL_ENABLED) {
 			if (fimc->source_subdev_grp_id == 0)
 				fimc->source_subdev_grp_id = sd->grp_id;
@@ -1010,19 +1006,15 @@ static int fimc_lite_link_setup(struct media_entity *entity,
 	case FLITE_SD_PAD_SOURCE_DMA:
 		if (!(flags & MEDIA_LNK_FL_ENABLED))
 			atomic_set(&fimc->out_path, FIMC_IO_NONE);
-		else if (is_media_entity_v4l2_io(remote->entity))
-			atomic_set(&fimc->out_path, FIMC_IO_DMA);
 		else
-			ret = -EINVAL;
+			atomic_set(&fimc->out_path, FIMC_IO_DMA);
 		break;
 
 	case FLITE_SD_PAD_SOURCE_ISP:
 		if (!(flags & MEDIA_LNK_FL_ENABLED))
 			atomic_set(&fimc->out_path, FIMC_IO_NONE);
-		else if (is_media_entity_v4l2_subdev(remote->entity))
-			atomic_set(&fimc->out_path, FIMC_IO_ISP);
 		else
-			ret = -EINVAL;
+			atomic_set(&fimc->out_path, FIMC_IO_ISP);
 		break;
 
 	default:
diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c
index e79ddbb1e14f..feb521f28e14 100644
--- a/drivers/media/platform/exynos4-is/media-dev.c
+++ b/drivers/media/platform/exynos4-is/media-dev.c
@@ -389,13 +389,19 @@ static int fimc_md_parse_port_node(struct fimc_md *fmd,
 	struct fimc_source_info *pd = &fmd->sensor[index].pdata;
 	struct device_node *rem, *ep, *np;
 	struct v4l2_of_endpoint endpoint;
+	int ret;
 
 	/* Assume here a port node can have only one endpoint node. */
 	ep = of_get_next_child(port, NULL);
 	if (!ep)
 		return 0;
 
-	v4l2_of_parse_endpoint(ep, &endpoint);
+	ret = v4l2_of_parse_endpoint(ep, &endpoint);
+	if (ret) {
+		of_node_put(ep);
+		return ret;
+	}
+
 	if (WARN_ON(endpoint.base.port == 0) || index >= FIMC_MAX_SENSORS)
 		return -EINVAL;
 
@@ -486,8 +492,10 @@ static int fimc_md_register_sensor_entities(struct fimc_md *fmd)
 			continue;
 
 		ret = fimc_md_parse_port_node(fmd, port, index);
-		if (ret < 0)
+		if (ret < 0) {
+			of_node_put(node);
 			goto rpm_put;
+		}
 		index++;
 	}
 
@@ -498,8 +506,10 @@ static int fimc_md_register_sensor_entities(struct fimc_md *fmd)
 
 	for_each_child_of_node(ports, node) {
 		ret = fimc_md_parse_port_node(fmd, node, index);
-		if (ret < 0)
+		if (ret < 0) {
+			of_node_put(node);
 			break;
+		}
 		index++;
 	}
 rpm_put:
@@ -707,8 +717,10 @@ static int fimc_md_register_platform_entities(struct fimc_md *fmd,
 			ret = fimc_md_register_platform_entity(fmd, pdev,
 							plat_entity);
 		put_device(&pdev->dev);
-		if (ret < 0)
+		if (ret < 0) {
+			of_node_put(node);
 			break;
+		}
 	}
 
 	return ret;
diff --git a/drivers/media/platform/exynos4-is/mipi-csis.c b/drivers/media/platform/exynos4-is/mipi-csis.c
index ac5e50e595be..bd5c46c3d4b7 100644
--- a/drivers/media/platform/exynos4-is/mipi-csis.c
+++ b/drivers/media/platform/exynos4-is/mipi-csis.c
@@ -736,6 +736,7 @@ static int s5pcsis_parse_dt(struct platform_device *pdev,
 {
 	struct device_node *node = pdev->dev.of_node;
 	struct v4l2_of_endpoint endpoint;
+	int ret;
 
 	if (of_property_read_u32(node, "clock-frequency",
 				 &state->clk_frequency))
@@ -751,7 +752,9 @@ static int s5pcsis_parse_dt(struct platform_device *pdev,
 		return -EINVAL;
 	}
 	/* Get port node and validate MIPI-CSI channel id. */
-	v4l2_of_parse_endpoint(node, &endpoint);
+	ret = v4l2_of_parse_endpoint(node, &endpoint);
+	if (ret)
+		goto err;
 
 	state->index = endpoint.base.port - FIMC_INPUT_MIPI_CSI2_0;
 	if (state->index >= CSIS_MAX_ENTITIES)
@@ -764,9 +767,10 @@ static int s5pcsis_parse_dt(struct platform_device *pdev,
 					"samsung,csis-wclk");
 
 	state->num_lanes = endpoint.bus.mipi_csi2.num_data_lanes;
-	of_node_put(node);
 
-	return 0;
+err:
+	of_node_put(node);
+	return ret;
 }
 
 static int s5pcsis_pm_resume(struct device *dev, bool runtime);
diff --git a/drivers/media/platform/omap3isp/isp.c b/drivers/media/platform/omap3isp/isp.c
index 0bcfa553c1aa..5d54e2c6c16b 100644
--- a/drivers/media/platform/omap3isp/isp.c
+++ b/drivers/media/platform/omap3isp/isp.c
@@ -64,6 +64,7 @@
 
 #include <media/v4l2-common.h>
 #include <media/v4l2-device.h>
+#include <media/v4l2-mc.h>
 #include <media/v4l2-of.h>
 
 #include "isp.h"
@@ -449,7 +450,7 @@ void omap3isp_configure_bridge(struct isp_device *isp,
 	case CCDC_INPUT_PARALLEL:
 		ispctrl_val |= ISPCTRL_PAR_SER_CLK_SEL_PARALLEL;
 		ispctrl_val |= parcfg->clk_pol << ISPCTRL_PAR_CLK_POL_SHIFT;
-		shift += parcfg->data_lane_shift * 2;
+		shift += parcfg->data_lane_shift;
 		break;
 
 	case CCDC_INPUT_CSI2A:
@@ -657,216 +658,6 @@ static irqreturn_t isp_isr(int irq, void *_isp)
 }
 
 /* -----------------------------------------------------------------------------
- * Pipeline power management
- *
- * Entities must be powered up when part of a pipeline that contains at least
- * one open video device node.
- *
- * To achieve this use the entity use_count field to track the number of users.
- * For entities corresponding to video device nodes the use_count field stores
- * the users count of the node. For entities corresponding to subdevs the
- * use_count field stores the total number of users of all video device nodes
- * in the pipeline.
- *
- * The omap3isp_pipeline_pm_use() function must be called in the open() and
- * close() handlers of video device nodes. It increments or decrements the use
- * count of all subdev entities in the pipeline.
- *
- * To react to link management on powered pipelines, the link setup notification
- * callback updates the use count of all entities in the source and sink sides
- * of the link.
- */
-
-/*
- * isp_pipeline_pm_use_count - Count the number of users of a pipeline
- * @entity: The entity
- *
- * Return the total number of users of all video device nodes in the pipeline.
- */
-static int isp_pipeline_pm_use_count(struct media_entity *entity,
-	struct media_entity_graph *graph)
-{
-	int use = 0;
-
-	media_entity_graph_walk_start(graph, entity);
-
-	while ((entity = media_entity_graph_walk_next(graph))) {
-		if (is_media_entity_v4l2_io(entity))
-			use += entity->use_count;
-	}
-
-	return use;
-}
-
-/*
- * isp_pipeline_pm_power_one - Apply power change to an entity
- * @entity: The entity
- * @change: Use count change
- *
- * Change the entity use count by @change. If the entity is a subdev update its
- * power state by calling the core::s_power operation when the use count goes
- * from 0 to != 0 or from != 0 to 0.
- *
- * Return 0 on success or a negative error code on failure.
- */
-static int isp_pipeline_pm_power_one(struct media_entity *entity, int change)
-{
-	struct v4l2_subdev *subdev;
-	int ret;
-
-	subdev = is_media_entity_v4l2_subdev(entity)
-	       ? media_entity_to_v4l2_subdev(entity) : NULL;
-
-	if (entity->use_count == 0 && change > 0 && subdev != NULL) {
-		ret = v4l2_subdev_call(subdev, core, s_power, 1);
-		if (ret < 0 && ret != -ENOIOCTLCMD)
-			return ret;
-	}
-
-	entity->use_count += change;
-	WARN_ON(entity->use_count < 0);
-
-	if (entity->use_count == 0 && change < 0 && subdev != NULL)
-		v4l2_subdev_call(subdev, core, s_power, 0);
-
-	return 0;
-}
-
-/*
- * isp_pipeline_pm_power - Apply power change to all entities in a pipeline
- * @entity: The entity
- * @change: Use count change
- *
- * Walk the pipeline to update the use count and the power state of all non-node
- * entities.
- *
- * Return 0 on success or a negative error code on failure.
- */
-static int isp_pipeline_pm_power(struct media_entity *entity, int change,
-	struct media_entity_graph *graph)
-{
-	struct media_entity *first = entity;
-	int ret = 0;
-
-	if (!change)
-		return 0;
-
-	media_entity_graph_walk_start(graph, entity);
-
-	while (!ret && (entity = media_entity_graph_walk_next(graph)))
-		if (is_media_entity_v4l2_subdev(entity))
-			ret = isp_pipeline_pm_power_one(entity, change);
-
-	if (!ret)
-		return ret;
-
-	media_entity_graph_walk_start(graph, first);
-
-	while ((first = media_entity_graph_walk_next(graph))
-	       && first != entity)
-		if (is_media_entity_v4l2_subdev(first))
-			isp_pipeline_pm_power_one(first, -change);
-
-	return ret;
-}
-
-/*
- * omap3isp_pipeline_pm_use - Update the use count of an entity
- * @entity: The entity
- * @use: Use (1) or stop using (0) the entity
- *
- * Update the use count of all entities in the pipeline and power entities on or
- * off accordingly.
- *
- * Return 0 on success or a negative error code on failure. Powering entities
- * off is assumed to never fail. No failure can occur when the use parameter is
- * set to 0.
- */
-int omap3isp_pipeline_pm_use(struct media_entity *entity, int use,
-			     struct media_entity_graph *graph)
-{
-	int change = use ? 1 : -1;
-	int ret;
-
-	mutex_lock(&entity->graph_obj.mdev->graph_mutex);
-
-	/* Apply use count to node. */
-	entity->use_count += change;
-	WARN_ON(entity->use_count < 0);
-
-	/* Apply power change to connected non-nodes. */
-	ret = isp_pipeline_pm_power(entity, change, graph);
-	if (ret < 0)
-		entity->use_count -= change;
-
-	mutex_unlock(&entity->graph_obj.mdev->graph_mutex);
-
-	return ret;
-}
-
-/*
- * isp_pipeline_link_notify - Link management notification callback
- * @link: The link
- * @flags: New link flags that will be applied
- * @notification: The link's state change notification type (MEDIA_DEV_NOTIFY_*)
- *
- * React to link management on powered pipelines by updating the use count of
- * all entities in the source and sink sides of the link. Entities are powered
- * on or off accordingly.
- *
- * Return 0 on success or a negative error code on failure. Powering entities
- * off is assumed to never fail. This function will not fail for disconnection
- * events.
- */
-static int isp_pipeline_link_notify(struct media_link *link, u32 flags,
-				    unsigned int notification)
-{
-	struct media_entity_graph *graph =
-		&container_of(link->graph_obj.mdev, struct isp_device,
-			      media_dev)->pm_count_graph;
-	struct media_entity *source = link->source->entity;
-	struct media_entity *sink = link->sink->entity;
-	int source_use;
-	int sink_use;
-	int ret = 0;
-
-	if (notification == MEDIA_DEV_NOTIFY_PRE_LINK_CH) {
-		ret = media_entity_graph_walk_init(graph,
-						   link->graph_obj.mdev);
-		if (ret)
-			return ret;
-	}
-
-	source_use = isp_pipeline_pm_use_count(source, graph);
-	sink_use = isp_pipeline_pm_use_count(sink, graph);
-
-	if (notification == MEDIA_DEV_NOTIFY_POST_LINK_CH &&
-	    !(flags & MEDIA_LNK_FL_ENABLED)) {
-		/* Powering off entities is assumed to never fail. */
-		isp_pipeline_pm_power(source, -sink_use, graph);
-		isp_pipeline_pm_power(sink, -source_use, graph);
-		return 0;
-	}
-
-	if (notification == MEDIA_DEV_NOTIFY_PRE_LINK_CH &&
-		(flags & MEDIA_LNK_FL_ENABLED)) {
-
-		ret = isp_pipeline_pm_power(source, sink_use, graph);
-		if (ret < 0)
-			return ret;
-
-		ret = isp_pipeline_pm_power(sink, source_use, graph);
-		if (ret < 0)
-			isp_pipeline_pm_power(source, -sink_use, graph);
-	}
-
-	if (notification == MEDIA_DEV_NOTIFY_POST_LINK_CH)
-		media_entity_graph_walk_cleanup(graph);
-
-	return ret;
-}
-
-/* -----------------------------------------------------------------------------
  * Pipeline stream management
  */
 
@@ -1889,7 +1680,7 @@ static int isp_register_entities(struct isp_device *isp)
 	strlcpy(isp->media_dev.model, "TI OMAP3 ISP",
 		sizeof(isp->media_dev.model));
 	isp->media_dev.hw_revision = isp->revision;
-	isp->media_dev.link_notify = isp_pipeline_link_notify;
+	isp->media_dev.link_notify = v4l2_pipeline_link_notify;
 	media_device_init(&isp->media_dev);
 
 	isp->v4l2_dev.mdev = &isp->media_dev;
@@ -2235,8 +2026,11 @@ static int isp_of_parse_node(struct device *dev, struct device_node *node,
 	struct isp_bus_cfg *buscfg = &isd->bus;
 	struct v4l2_of_endpoint vep;
 	unsigned int i;
+	int ret;
 
-	v4l2_of_parse_endpoint(node, &vep);
+	ret = v4l2_of_parse_endpoint(node, &vep);
+	if (ret)
+		return ret;
 
 	dev_dbg(dev, "parsing endpoint %s, interface %u\n", node->full_name,
 		vep.base.port);
@@ -2528,12 +2322,13 @@ static int isp_probe(struct platform_device *pdev)
 	}
 
 	/* Interrupt */
-	isp->irq_num = platform_get_irq(pdev, 0);
-	if (isp->irq_num <= 0) {
+	ret = platform_get_irq(pdev, 0);
+	if (ret <= 0) {
 		dev_err(isp->dev, "No IRQ resource\n");
 		ret = -ENODEV;
 		goto error_iommu;
 	}
+	isp->irq_num = ret;
 
 	if (devm_request_irq(isp->dev, isp->irq_num, isp_isr, IRQF_SHARED,
 			     "OMAP3 ISP", isp)) {
@@ -2599,6 +2394,7 @@ static const struct of_device_id omap3isp_of_table[] = {
 	{ .compatible = "ti,omap3-isp" },
 	{ },
 };
+MODULE_DEVICE_TABLE(of, omap3isp_of_table);
 
 static struct platform_driver omap3isp_driver = {
 	.probe = isp_probe,
diff --git a/drivers/media/platform/omap3isp/isp.h b/drivers/media/platform/omap3isp/isp.h
index 49b7f71ac968..7e6f6638433b 100644
--- a/drivers/media/platform/omap3isp/isp.h
+++ b/drivers/media/platform/omap3isp/isp.h
@@ -177,7 +177,6 @@ struct isp_device {
 	struct v4l2_device v4l2_dev;
 	struct v4l2_async_notifier notifier;
 	struct media_device media_dev;
-	struct media_entity_graph pm_count_graph;
 	struct device *dev;
 	u32 revision;
 
@@ -267,9 +266,6 @@ void omap3isp_subclk_enable(struct isp_device *isp,
 void omap3isp_subclk_disable(struct isp_device *isp,
 			     enum isp_subclk_resource res);
 
-int omap3isp_pipeline_pm_use(struct media_entity *entity, int use,
-			     struct media_entity_graph *graph);
-
 int omap3isp_register_entities(struct platform_device *pdev,
 			       struct v4l2_device *v4l2_dev);
 void omap3isp_unregister_entities(struct platform_device *pdev);
diff --git a/drivers/media/platform/omap3isp/ispccdc.c b/drivers/media/platform/omap3isp/ispccdc.c
index bb3974c98e37..882310eb45cc 100644
--- a/drivers/media/platform/omap3isp/ispccdc.c
+++ b/drivers/media/platform/omap3isp/ispccdc.c
@@ -2421,7 +2421,7 @@ static int ccdc_link_validate(struct v4l2_subdev *sd,
 			&((struct isp_bus_cfg *)
 			  media_entity_to_v4l2_subdev(link->source->entity)
 			  ->host_priv)->bus.parallel;
-		parallel_shift = parcfg->data_lane_shift * 2;
+		parallel_shift = parcfg->data_lane_shift;
 	} else {
 		parallel_shift = 0;
 	}
diff --git a/drivers/media/platform/omap3isp/isppreview.c b/drivers/media/platform/omap3isp/isppreview.c
index 84a96670e2e7..ac30a0f83780 100644
--- a/drivers/media/platform/omap3isp/isppreview.c
+++ b/drivers/media/platform/omap3isp/isppreview.c
@@ -1480,13 +1480,6 @@ static void preview_isr_buffer(struct isp_prev_device *prev)
 	struct isp_buffer *buffer;
 	int restart = 0;
 
-	if (prev->input == PREVIEW_INPUT_MEMORY) {
-		buffer = omap3isp_video_buffer_next(&prev->video_in);
-		if (buffer != NULL)
-			preview_set_inaddr(prev, buffer->dma);
-		pipe->state |= ISP_PIPELINE_IDLE_INPUT;
-	}
-
 	if (prev->output & PREVIEW_OUTPUT_MEMORY) {
 		buffer = omap3isp_video_buffer_next(&prev->video_out);
 		if (buffer != NULL) {
@@ -1496,6 +1489,13 @@ static void preview_isr_buffer(struct isp_prev_device *prev)
 		pipe->state |= ISP_PIPELINE_IDLE_OUTPUT;
 	}
 
+	if (prev->input == PREVIEW_INPUT_MEMORY) {
+		buffer = omap3isp_video_buffer_next(&prev->video_in);
+		if (buffer != NULL)
+			preview_set_inaddr(prev, buffer->dma);
+		pipe->state |= ISP_PIPELINE_IDLE_INPUT;
+	}
+
 	switch (prev->state) {
 	case ISP_PIPELINE_STREAM_SINGLESHOT:
 		if (isp_pipeline_ready(pipe))
diff --git a/drivers/media/platform/omap3isp/ispvideo.c b/drivers/media/platform/omap3isp/ispvideo.c
index 994dfc0813f6..ac76d2901501 100644
--- a/drivers/media/platform/omap3isp/ispvideo.c
+++ b/drivers/media/platform/omap3isp/ispvideo.c
@@ -22,8 +22,10 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+
 #include <media/v4l2-dev.h>
 #include <media/v4l2-ioctl.h>
+#include <media/v4l2-mc.h>
 #include <media/videobuf2-dma-contig.h>
 
 #include "ispvideo.h"
@@ -434,10 +436,68 @@ static void isp_video_buffer_queue(struct vb2_buffer *buf)
 	}
 }
 
+/*
+ * omap3isp_video_return_buffers - Return all queued buffers to videobuf2
+ * @video: ISP video object
+ * @state: new state for the returned buffers
+ *
+ * Return all buffers queued on the video node to videobuf2 in the given state.
+ * The buffer state should be VB2_BUF_STATE_QUEUED if called due to an error
+ * when starting the stream, or VB2_BUF_STATE_ERROR otherwise.
+ *
+ * The function must be called with the video irqlock held.
+ */
+static void omap3isp_video_return_buffers(struct isp_video *video,
+					  enum vb2_buffer_state state)
+{
+	while (!list_empty(&video->dmaqueue)) {
+		struct isp_buffer *buf;
+
+		buf = list_first_entry(&video->dmaqueue,
+				       struct isp_buffer, irqlist);
+		list_del(&buf->irqlist);
+		vb2_buffer_done(&buf->vb.vb2_buf, state);
+	}
+}
+
+static int isp_video_start_streaming(struct vb2_queue *queue,
+				     unsigned int count)
+{
+	struct isp_video_fh *vfh = vb2_get_drv_priv(queue);
+	struct isp_video *video = vfh->video;
+	struct isp_pipeline *pipe = to_isp_pipeline(&video->video.entity);
+	unsigned long flags;
+	int ret;
+
+	/* In sensor-to-memory mode, the stream can be started synchronously
+	 * to the stream on command. In memory-to-memory mode, it will be
+	 * started when buffers are queued on both the input and output.
+	 */
+	if (pipe->input)
+		return 0;
+
+	ret = omap3isp_pipeline_set_stream(pipe,
+					   ISP_PIPELINE_STREAM_CONTINUOUS);
+	if (ret < 0) {
+		spin_lock_irqsave(&video->irqlock, flags);
+		omap3isp_video_return_buffers(video, VB2_BUF_STATE_QUEUED);
+		spin_unlock_irqrestore(&video->irqlock, flags);
+		return ret;
+	}
+
+	spin_lock_irqsave(&video->irqlock, flags);
+	if (list_empty(&video->dmaqueue))
+		video->dmaqueue_flags |= ISP_VIDEO_DMAQUEUE_UNDERRUN;
+	spin_unlock_irqrestore(&video->irqlock, flags);
+
+	return 0;
+}
+
 static const struct vb2_ops isp_video_queue_ops = {
 	.queue_setup = isp_video_queue_setup,
 	.buf_prepare = isp_video_buffer_prepare,
 	.buf_queue = isp_video_buffer_queue,
+	.start_streaming = isp_video_start_streaming,
 };
 
 /*
@@ -459,7 +519,7 @@ static const struct vb2_ops isp_video_queue_ops = {
 struct isp_buffer *omap3isp_video_buffer_next(struct isp_video *video)
 {
 	struct isp_pipeline *pipe = to_isp_pipeline(&video->video.entity);
-	enum isp_pipeline_state state;
+	enum vb2_buffer_state vb_state;
 	struct isp_buffer *buf;
 	unsigned long flags;
 
@@ -495,17 +555,19 @@ struct isp_buffer *omap3isp_video_buffer_next(struct isp_video *video)
 
 	/* Report pipeline errors to userspace on the capture device side. */
 	if (video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE && pipe->error) {
-		state = VB2_BUF_STATE_ERROR;
+		vb_state = VB2_BUF_STATE_ERROR;
 		pipe->error = false;
 	} else {
-		state = VB2_BUF_STATE_DONE;
+		vb_state = VB2_BUF_STATE_DONE;
 	}
 
-	vb2_buffer_done(&buf->vb.vb2_buf, state);
+	vb2_buffer_done(&buf->vb.vb2_buf, vb_state);
 
 	spin_lock_irqsave(&video->irqlock, flags);
 
 	if (list_empty(&video->dmaqueue)) {
+		enum isp_pipeline_state state;
+
 		spin_unlock_irqrestore(&video->irqlock, flags);
 
 		if (video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
@@ -541,26 +603,16 @@ struct isp_buffer *omap3isp_video_buffer_next(struct isp_video *video)
  * omap3isp_video_cancel_stream - Cancel stream on a video node
  * @video: ISP video object
  *
- * Cancelling a stream mark all buffers on the video node as erroneous and makes
- * sure no new buffer can be queued.
+ * Cancelling a stream returns all buffers queued on the video node to videobuf2
+ * in the erroneous state and makes sure no new buffer can be queued.
  */
 void omap3isp_video_cancel_stream(struct isp_video *video)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&video->irqlock, flags);
-
-	while (!list_empty(&video->dmaqueue)) {
-		struct isp_buffer *buf;
-
-		buf = list_first_entry(&video->dmaqueue,
-				       struct isp_buffer, irqlist);
-		list_del(&buf->irqlist);
-		vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR);
-	}
-
+	omap3isp_video_return_buffers(video, VB2_BUF_STATE_ERROR);
 	video->error = true;
-
 	spin_unlock_irqrestore(&video->irqlock, flags);
 }
 
@@ -1087,29 +1139,10 @@ isp_video_streamon(struct file *file, void *fh, enum v4l2_buf_type type)
 	if (ret < 0)
 		goto err_check_format;
 
-	/* In sensor-to-memory mode, the stream can be started synchronously
-	 * to the stream on command. In memory-to-memory mode, it will be
-	 * started when buffers are queued on both the input and output.
-	 */
-	if (pipe->input == NULL) {
-		ret = omap3isp_pipeline_set_stream(pipe,
-					      ISP_PIPELINE_STREAM_CONTINUOUS);
-		if (ret < 0)
-			goto err_set_stream;
-		spin_lock_irqsave(&video->irqlock, flags);
-		if (list_empty(&video->dmaqueue))
-			video->dmaqueue_flags |= ISP_VIDEO_DMAQUEUE_UNDERRUN;
-		spin_unlock_irqrestore(&video->irqlock, flags);
-	}
-
 	mutex_unlock(&video->stream_lock);
 
 	return 0;
 
-err_set_stream:
-	mutex_lock(&video->queue_lock);
-	vb2_streamoff(&vfh->queue, type);
-	mutex_unlock(&video->queue_lock);
 err_check_format:
 	media_entity_pipeline_stop(&video->video.entity);
 err_pipeline_start:
@@ -1261,12 +1294,7 @@ static int isp_video_open(struct file *file)
 		goto done;
 	}
 
-	ret = media_entity_graph_walk_init(&handle->graph,
-					   &video->isp->media_dev);
-	if (ret)
-		goto done;
-
-	ret = omap3isp_pipeline_pm_use(&video->video.entity, 1, &handle->graph);
+	ret = v4l2_pipeline_pm_use(&video->video.entity, 1);
 	if (ret < 0) {
 		omap3isp_put(video->isp);
 		goto done;
@@ -1297,7 +1325,6 @@ static int isp_video_open(struct file *file)
 done:
 	if (ret < 0) {
 		v4l2_fh_del(&handle->vfh);
-		media_entity_graph_walk_cleanup(&handle->graph);
 		kfree(handle);
 	}
 
@@ -1317,8 +1344,7 @@ static int isp_video_release(struct file *file)
 	vb2_queue_release(&handle->queue);
 	mutex_unlock(&video->queue_lock);
 
-	omap3isp_pipeline_pm_use(&video->video.entity, 0, &handle->graph);
-	media_entity_graph_walk_cleanup(&handle->graph);
+	v4l2_pipeline_pm_use(&video->video.entity, 0);
 
 	/* Release the file handle. */
 	v4l2_fh_del(vfh);
diff --git a/drivers/media/platform/omap3isp/ispvideo.h b/drivers/media/platform/omap3isp/ispvideo.h
index 156429878d64..6a48d5879c56 100644
--- a/drivers/media/platform/omap3isp/ispvideo.h
+++ b/drivers/media/platform/omap3isp/ispvideo.h
@@ -189,7 +189,6 @@ struct isp_video_fh {
 	struct vb2_queue queue;
 	struct v4l2_format format;
 	struct v4l2_fract timeperframe;
-	struct media_entity_graph graph;
 };
 
 #define to_isp_video_fh(fh)	container_of(fh, struct isp_video_fh, vfh)
diff --git a/drivers/media/platform/omap3isp/omap3isp.h b/drivers/media/platform/omap3isp/omap3isp.h
index 190e259a6a2d..443e8f7673e2 100644
--- a/drivers/media/platform/omap3isp/omap3isp.h
+++ b/drivers/media/platform/omap3isp/omap3isp.h
@@ -33,9 +33,9 @@ enum isp_interface_type {
  * struct isp_parallel_cfg - Parallel interface configuration
  * @data_lane_shift: Data lane shifter
  *		0 - CAMEXT[13:0] -> CAM[13:0]
- *		1 - CAMEXT[13:2] -> CAM[11:0]
- *		2 - CAMEXT[13:4] -> CAM[9:0]
- *		3 - CAMEXT[13:6] -> CAM[7:0]
+ *		2 - CAMEXT[13:2] -> CAM[11:0]
+ *		4 - CAMEXT[13:4] -> CAM[9:0]
+ *		6 - CAMEXT[13:6] -> CAM[7:0]
  * @clk_pol: Pixel clock polarity
  *		0 - Sample on rising edge, 1 - Sample on falling edge
  * @hs_pol: Horizontal synchronization polarity
@@ -48,7 +48,7 @@ enum isp_interface_type {
  *		0 - Normal, 1 - One's complement
  */
 struct isp_parallel_cfg {
-	unsigned int data_lane_shift:2;
+	unsigned int data_lane_shift:3;
 	unsigned int clk_pol:1;
 	unsigned int hs_pol:1;
 	unsigned int vs_pol:1;
diff --git a/drivers/media/platform/rcar_jpu.c b/drivers/media/platform/rcar_jpu.c
index 485f5259acb0..552789a69c86 100644
--- a/drivers/media/platform/rcar_jpu.c
+++ b/drivers/media/platform/rcar_jpu.c
@@ -1613,6 +1613,7 @@ static const struct of_device_id jpu_dt_ids[] = {
 	{ .compatible = "renesas,jpu-r8a7791" }, /* M2-W */
 	{ .compatible = "renesas,jpu-r8a7792" }, /* V2H */
 	{ .compatible = "renesas,jpu-r8a7793" }, /* M2-N */
+	{ .compatible = "renesas,rcar-gen2-jpu" },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, jpu_dt_ids);
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
index 0434f02a7175..034b5c1d35a1 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
@@ -212,6 +212,14 @@ static struct mfc_control controls[] = {
 		.menu_skip_mask = 0,
 	},
 	{
+		.id = V4L2_CID_MPEG_VIDEO_FORCE_KEY_FRAME,
+		.type = V4L2_CTRL_TYPE_BUTTON,
+		.minimum = 0,
+		.maximum = 0,
+		.step = 0,
+		.default_value = 0,
+	},
+	{
 		.id = V4L2_CID_MPEG_VIDEO_VBV_SIZE,
 		.type = V4L2_CTRL_TYPE_INTEGER,
 		.minimum = 0,
@@ -1423,6 +1431,10 @@ static int s5p_mfc_enc_s_ctrl(struct v4l2_ctrl *ctrl)
 	case V4L2_CID_MPEG_MFC51_VIDEO_FORCE_FRAME_TYPE:
 		ctx->force_frame_type = ctrl->val;
 		break;
+	case V4L2_CID_MPEG_VIDEO_FORCE_KEY_FRAME:
+		ctx->force_frame_type =
+			V4L2_MPEG_MFC51_VIDEO_FORCE_FRAME_TYPE_I_FRAME;
+		break;
 	case V4L2_CID_MPEG_VIDEO_VBV_SIZE:
 		p->vbv_size = ctrl->val;
 		break;
diff --git a/drivers/media/platform/soc_camera/Kconfig b/drivers/media/platform/soc_camera/Kconfig
index f2776cd415ca..355298989dd8 100644
--- a/drivers/media/platform/soc_camera/Kconfig
+++ b/drivers/media/platform/soc_camera/Kconfig
@@ -17,19 +17,11 @@ config SOC_CAMERA_PLATFORM
 	help
 	  This is a generic SoC camera platform driver, useful for testing
 
-config VIDEO_MX3
-	tristate "i.MX3x Camera Sensor Interface driver"
-	depends on VIDEO_DEV && MX3_IPU && SOC_CAMERA
-	depends on MX3_IPU || COMPILE_TEST
-	depends on HAS_DMA
-	select VIDEOBUF2_DMA_CONTIG
-	---help---
-	  This is a v4l2 driver for the i.MX3x Camera Sensor Interface
-
 config VIDEO_PXA27x
 	tristate "PXA27x Quick Capture Interface driver"
 	depends on VIDEO_DEV && PXA27x && SOC_CAMERA
 	select VIDEOBUF_DMA_SG
+	select SG_SPLIT
 	---help---
 	  This is a v4l2 driver for the PXA27x Quick Capture Interface
 
@@ -60,25 +52,6 @@ config VIDEO_SH_MOBILE_CEU
 	---help---
 	  This is a v4l2 driver for the SuperH Mobile CEU Interface
 
-config VIDEO_OMAP1
-	tristate "OMAP1 Camera Interface driver"
-	depends on VIDEO_DEV && SOC_CAMERA
-	depends on ARCH_OMAP1
-	depends on HAS_DMA
-	select VIDEOBUF_DMA_CONTIG
-	select VIDEOBUF_DMA_SG
-	---help---
-	  This is a v4l2 driver for the TI OMAP1 camera interface
-
-config VIDEO_MX2
-	tristate "i.MX27 Camera Sensor Interface driver"
-	depends on VIDEO_DEV && SOC_CAMERA
-	depends on SOC_IMX27 || COMPILE_TEST
-	depends on HAS_DMA
-	select VIDEOBUF2_DMA_CONTIG
-	---help---
-	  This is a v4l2 driver for the i.MX27 Camera Sensor Interface
-
 config VIDEO_ATMEL_ISI
 	tristate "ATMEL Image Sensor Interface (ISI) support"
 	depends on VIDEO_DEV && SOC_CAMERA
diff --git a/drivers/media/platform/soc_camera/Makefile b/drivers/media/platform/soc_camera/Makefile
index 2826382dc9f8..7ee71ae231c7 100644
--- a/drivers/media/platform/soc_camera/Makefile
+++ b/drivers/media/platform/soc_camera/Makefile
@@ -7,9 +7,6 @@ obj-$(CONFIG_SOC_CAMERA_PLATFORM)	+= soc_camera_platform.o
 
 # soc-camera host drivers have to be linked after camera drivers
 obj-$(CONFIG_VIDEO_ATMEL_ISI)		+= atmel-isi.o
-obj-$(CONFIG_VIDEO_MX2)			+= mx2_camera.o
-obj-$(CONFIG_VIDEO_MX3)			+= mx3_camera.o
-obj-$(CONFIG_VIDEO_OMAP1)		+= omap1_camera.o
 obj-$(CONFIG_VIDEO_PXA27x)		+= pxa_camera.o
 obj-$(CONFIG_VIDEO_SH_MOBILE_CEU)	+= sh_mobile_ceu_camera.o
 obj-$(CONFIG_VIDEO_SH_MOBILE_CSI2)	+= sh_mobile_csi2.o
diff --git a/drivers/media/platform/soc_camera/atmel-isi.c b/drivers/media/platform/soc_camera/atmel-isi.c
index 1af779ee3c74..ab2d9b9b1f5d 100644
--- a/drivers/media/platform/soc_camera/atmel-isi.c
+++ b/drivers/media/platform/soc_camera/atmel-isi.c
@@ -1026,7 +1026,7 @@ static int atmel_isi_parse_dt(struct atmel_isi *isi,
 
 static int atmel_isi_probe(struct platform_device *pdev)
 {
-	unsigned int irq;
+	int irq;
 	struct atmel_isi *isi;
 	struct resource *regs;
 	int ret, i;
@@ -1086,7 +1086,7 @@ static int atmel_isi_probe(struct platform_device *pdev)
 		isi->width_flags |= 1 << 9;
 
 	irq = platform_get_irq(pdev, 0);
-	if (IS_ERR_VALUE(irq)) {
+	if (irq < 0) {
 		ret = irq;
 		goto err_req_irq;
 	}
diff --git a/drivers/media/platform/soc_camera/pxa_camera.c b/drivers/media/platform/soc_camera/pxa_camera.c
index 415f3bda60bf..2aaf4a8f71a0 100644
--- a/drivers/media/platform/soc_camera/pxa_camera.c
+++ b/drivers/media/platform/soc_camera/pxa_camera.c
@@ -28,6 +28,9 @@
 #include <linux/clk.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/dma/pxa-dma.h>
 
 #include <media/v4l2-common.h>
 #include <media/v4l2-dev.h>
@@ -38,7 +41,6 @@
 
 #include <linux/videodev2.h>
 
-#include <mach/dma.h>
 #include <linux/platform_data/media/camera-pxa.h>
 
 #define PXA_CAM_VERSION "0.0.6"
@@ -175,21 +177,16 @@ enum pxa_camera_active_dma {
 	DMA_V = 0x4,
 };
 
-/* descriptor needed for the PXA DMA engine */
-struct pxa_cam_dma {
-	dma_addr_t		sg_dma;
-	struct pxa_dma_desc	*sg_cpu;
-	size_t			sg_size;
-	int			sglen;
-};
-
 /* buffer for one video frame */
 struct pxa_buffer {
 	/* common v4l buffer stuff -- must be first */
 	struct videobuf_buffer		vb;
 	u32	code;
 	/* our descriptor lists for Y, U and V channels */
-	struct pxa_cam_dma		dmas[3];
+	struct dma_async_tx_descriptor	*descs[3];
+	dma_cookie_t			cookie[3];
+	struct scatterlist		*sg[3];
+	int				sg_len[3];
 	int				inwork;
 	enum pxa_camera_active_dma	active_dma;
 };
@@ -207,7 +204,7 @@ struct pxa_camera_dev {
 	void __iomem		*base;
 
 	int			channels;
-	unsigned int		dma_chans[3];
+	struct dma_chan		*dma_chans[3];
 
 	struct pxacamera_platform_data *pdata;
 	struct resource		*res;
@@ -222,7 +219,7 @@ struct pxa_camera_dev {
 	spinlock_t		lock;
 
 	struct pxa_buffer	*active;
-	struct pxa_dma_desc	*sg_tail[3];
+	struct tasklet_struct	task_eof;
 
 	u32			save_cicr[5];
 };
@@ -258,7 +255,6 @@ static int pxa_videobuf_setup(struct videobuf_queue *vq, unsigned int *count,
 static void free_buffer(struct videobuf_queue *vq, struct pxa_buffer *buf)
 {
 	struct soc_camera_device *icd = vq->priv_data;
-	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
 	struct videobuf_dmabuf *dma = videobuf_to_dma(&buf->vb);
 	int i;
 
@@ -272,42 +268,45 @@ static void free_buffer(struct videobuf_queue *vq, struct pxa_buffer *buf)
 	 * longer in STATE_QUEUED or STATE_ACTIVE
 	 */
 	videobuf_waiton(vq, &buf->vb, 0, 0);
-	videobuf_dma_unmap(vq->dev, dma);
-	videobuf_dma_free(dma);
 
-	for (i = 0; i < ARRAY_SIZE(buf->dmas); i++) {
-		if (buf->dmas[i].sg_cpu)
-			dma_free_coherent(ici->v4l2_dev.dev,
-					  buf->dmas[i].sg_size,
-					  buf->dmas[i].sg_cpu,
-					  buf->dmas[i].sg_dma);
-		buf->dmas[i].sg_cpu = NULL;
+	for (i = 0; i < 3 && buf->descs[i]; i++) {
+		dmaengine_desc_free(buf->descs[i]);
+		kfree(buf->sg[i]);
+		buf->descs[i] = NULL;
+		buf->sg[i] = NULL;
+		buf->sg_len[i] = 0;
 	}
+	videobuf_dma_unmap(vq->dev, dma);
+	videobuf_dma_free(dma);
 
 	buf->vb.state = VIDEOBUF_NEEDS_INIT;
+
+	dev_dbg(icd->parent, "%s end (vb=0x%p) 0x%08lx %d\n", __func__,
+		&buf->vb, buf->vb.baddr, buf->vb.bsize);
 }
 
-static int calculate_dma_sglen(struct scatterlist *sglist, int sglen,
-			       int sg_first_ofs, int size)
+static void pxa_camera_dma_irq(struct pxa_camera_dev *pcdev,
+			       enum pxa_camera_active_dma act_dma);
+
+static void pxa_camera_dma_irq_y(void *data)
 {
-	int i, offset, dma_len, xfer_len;
-	struct scatterlist *sg;
+	struct pxa_camera_dev *pcdev = data;
 
-	offset = sg_first_ofs;
-	for_each_sg(sglist, sg, sglen, i) {
-		dma_len = sg_dma_len(sg);
+	pxa_camera_dma_irq(pcdev, DMA_Y);
+}
 
-		/* PXA27x Developer's Manual 27.4.4.1: round up to 8 bytes */
-		xfer_len = roundup(min(dma_len - offset, size), 8);
+static void pxa_camera_dma_irq_u(void *data)
+{
+	struct pxa_camera_dev *pcdev = data;
 
-		size = max(0, size - xfer_len);
-		offset = 0;
-		if (size == 0)
-			break;
-	}
+	pxa_camera_dma_irq(pcdev, DMA_U);
+}
+
+static void pxa_camera_dma_irq_v(void *data)
+{
+	struct pxa_camera_dev *pcdev = data;
 
-	BUG_ON(size != 0);
-	return i + 1;
+	pxa_camera_dma_irq(pcdev, DMA_V);
 }
 
 /**
@@ -318,93 +317,53 @@ static int calculate_dma_sglen(struct scatterlist *sglist, int sglen,
  * @channel: dma channel (0 => 'Y', 1 => 'U', 2 => 'V')
  * @cibr: camera Receive Buffer Register
  * @size: bytes to transfer
- * @sg_first: first element of sg_list
- * @sg_first_ofs: offset in first element of sg_list
+ * @offset: offset in videobuffer of the first byte to transfer
  *
  * Prepares the pxa dma descriptors to transfer one camera channel.
- * Beware sg_first and sg_first_ofs are both input and output parameters.
  *
- * Returns 0 or -ENOMEM if no coherent memory is available
+ * Returns 0 if success or -ENOMEM if no memory is available
  */
 static int pxa_init_dma_channel(struct pxa_camera_dev *pcdev,
 				struct pxa_buffer *buf,
 				struct videobuf_dmabuf *dma, int channel,
-				int cibr, int size,
-				struct scatterlist **sg_first, int *sg_first_ofs)
+				int cibr, int size, int offset)
 {
-	struct pxa_cam_dma *pxa_dma = &buf->dmas[channel];
-	struct device *dev = pcdev->soc_host.v4l2_dev.dev;
-	struct scatterlist *sg;
-	int i, offset, sglen;
-	int dma_len = 0, xfer_len = 0;
-
-	if (pxa_dma->sg_cpu)
-		dma_free_coherent(dev, pxa_dma->sg_size,
-				  pxa_dma->sg_cpu, pxa_dma->sg_dma);
-
-	sglen = calculate_dma_sglen(*sg_first, dma->sglen,
-				    *sg_first_ofs, size);
-
-	pxa_dma->sg_size = (sglen + 1) * sizeof(struct pxa_dma_desc);
-	pxa_dma->sg_cpu = dma_alloc_coherent(dev, pxa_dma->sg_size,
-					     &pxa_dma->sg_dma, GFP_KERNEL);
-	if (!pxa_dma->sg_cpu)
-		return -ENOMEM;
-
-	pxa_dma->sglen = sglen;
-	offset = *sg_first_ofs;
-
-	dev_dbg(dev, "DMA: sg_first=%p, sglen=%d, ofs=%d, dma.desc=%x\n",
-		*sg_first, sglen, *sg_first_ofs, pxa_dma->sg_dma);
-
-
-	for_each_sg(*sg_first, sg, sglen, i) {
-		dma_len = sg_dma_len(sg);
-
-		/* PXA27x Developer's Manual 27.4.4.1: round up to 8 bytes */
-		xfer_len = roundup(min(dma_len - offset, size), 8);
-
-		size = max(0, size - xfer_len);
-
-		pxa_dma->sg_cpu[i].dsadr = pcdev->res->start + cibr;
-		pxa_dma->sg_cpu[i].dtadr = sg_dma_address(sg) + offset;
-		pxa_dma->sg_cpu[i].dcmd =
-			DCMD_FLOWSRC | DCMD_BURST8 | DCMD_INCTRGADDR | xfer_len;
-#ifdef DEBUG
-		if (!i)
-			pxa_dma->sg_cpu[i].dcmd |= DCMD_STARTIRQEN;
-#endif
-		pxa_dma->sg_cpu[i].ddadr =
-			pxa_dma->sg_dma + (i + 1) * sizeof(struct pxa_dma_desc);
-
-		dev_vdbg(dev, "DMA: desc.%08x->@phys=0x%08x, len=%d\n",
-			 pxa_dma->sg_dma + i * sizeof(struct pxa_dma_desc),
-			 sg_dma_address(sg) + offset, xfer_len);
-		offset = 0;
-
-		if (size == 0)
-			break;
+	struct dma_chan *dma_chan = pcdev->dma_chans[channel];
+	struct scatterlist *sg = buf->sg[channel];
+	int sglen = buf->sg_len[channel];
+	struct dma_async_tx_descriptor *tx;
+
+	tx = dmaengine_prep_slave_sg(dma_chan, sg, sglen, DMA_DEV_TO_MEM,
+				     DMA_PREP_INTERRUPT | DMA_CTRL_REUSE);
+	if (!tx) {
+		dev_err(pcdev->soc_host.v4l2_dev.dev,
+			"dmaengine_prep_slave_sg failed\n");
+		goto fail;
 	}
 
-	pxa_dma->sg_cpu[sglen].ddadr = DDADR_STOP;
-	pxa_dma->sg_cpu[sglen].dcmd  = DCMD_FLOWSRC | DCMD_BURST8 | DCMD_ENDIRQEN;
-
-	/*
-	 * Handle 1 special case :
-	 *  - in 3 planes (YUV422P format), we might finish with xfer_len equal
-	 *    to dma_len (end on PAGE boundary). In this case, the sg element
-	 *    for next plane should be the next after the last used to store the
-	 *    last scatter gather RAM page
-	 */
-	if (xfer_len >= dma_len) {
-		*sg_first_ofs = xfer_len - dma_len;
-		*sg_first = sg_next(sg);
-	} else {
-		*sg_first_ofs = xfer_len;
-		*sg_first = sg;
+	tx->callback_param = pcdev;
+	switch (channel) {
+	case 0:
+		tx->callback = pxa_camera_dma_irq_y;
+		break;
+	case 1:
+		tx->callback = pxa_camera_dma_irq_u;
+		break;
+	case 2:
+		tx->callback = pxa_camera_dma_irq_v;
+		break;
 	}
 
+	buf->descs[channel] = tx;
 	return 0;
+fail:
+	kfree(sg);
+
+	dev_dbg(pcdev->soc_host.v4l2_dev.dev,
+		"%s (vb=0x%p) dma_tx=%p\n",
+		__func__, &buf->vb, tx);
+
+	return -ENOMEM;
 }
 
 static void pxa_videobuf_set_actdma(struct pxa_camera_dev *pcdev,
@@ -431,6 +390,7 @@ static int pxa_videobuf_prepare(struct videobuf_queue *vq,
 	struct pxa_buffer *buf = container_of(vb, struct pxa_buffer, vb);
 	int ret;
 	int size_y, size_u = 0, size_v = 0;
+	size_t sizes[3];
 
 	dev_dbg(dev, "%s (vb=0x%p) 0x%08lx %d\n", __func__,
 		vb, vb->baddr, vb->bsize);
@@ -473,13 +433,11 @@ static int pxa_videobuf_prepare(struct videobuf_queue *vq,
 
 	if (vb->state == VIDEOBUF_NEEDS_INIT) {
 		int size = vb->size;
-		int next_ofs = 0;
 		struct videobuf_dmabuf *dma = videobuf_to_dma(vb);
-		struct scatterlist *sg;
 
 		ret = videobuf_iolock(vq, vb, NULL);
 		if (ret)
-			goto fail;
+			goto out;
 
 		if (pcdev->channels == 3) {
 			size_y = size / 2;
@@ -488,11 +446,19 @@ static int pxa_videobuf_prepare(struct videobuf_queue *vq,
 			size_y = size;
 		}
 
-		sg = dma->sglist;
+		sizes[0] = size_y;
+		sizes[1] = size_u;
+		sizes[2] = size_v;
+		ret = sg_split(dma->sglist, dma->sglen, 0, pcdev->channels,
+			       sizes, buf->sg, buf->sg_len, GFP_KERNEL);
+		if (ret < 0) {
+			dev_err(dev, "sg_split failed: %d\n", ret);
+			goto fail;
+		}
 
 		/* init DMA for Y channel */
-		ret = pxa_init_dma_channel(pcdev, buf, dma, 0, CIBR0, size_y,
-					   &sg, &next_ofs);
+		ret = pxa_init_dma_channel(pcdev, buf, dma, 0, CIBR0,
+					   size_y, 0);
 		if (ret) {
 			dev_err(dev, "DMA initialization for Y/RGB failed\n");
 			goto fail;
@@ -501,19 +467,19 @@ static int pxa_videobuf_prepare(struct videobuf_queue *vq,
 		/* init DMA for U channel */
 		if (size_u)
 			ret = pxa_init_dma_channel(pcdev, buf, dma, 1, CIBR1,
-						   size_u, &sg, &next_ofs);
+						   size_u, size_y);
 		if (ret) {
 			dev_err(dev, "DMA initialization for U failed\n");
-			goto fail_u;
+			goto fail;
 		}
 
 		/* init DMA for V channel */
 		if (size_v)
 			ret = pxa_init_dma_channel(pcdev, buf, dma, 2, CIBR2,
-						   size_v, &sg, &next_ofs);
+						   size_v, size_y + size_u);
 		if (ret) {
 			dev_err(dev, "DMA initialization for V failed\n");
-			goto fail_v;
+			goto fail;
 		}
 
 		vb->state = VIDEOBUF_PREPARED;
@@ -524,12 +490,6 @@ static int pxa_videobuf_prepare(struct videobuf_queue *vq,
 
 	return 0;
 
-fail_v:
-	dma_free_coherent(dev, buf->dmas[1].sg_size,
-			  buf->dmas[1].sg_cpu, buf->dmas[1].sg_dma);
-fail_u:
-	dma_free_coherent(dev, buf->dmas[0].sg_size,
-			  buf->dmas[0].sg_cpu, buf->dmas[0].sg_dma);
 fail:
 	free_buffer(vq, buf);
 out:
@@ -553,10 +513,8 @@ static void pxa_dma_start_channels(struct pxa_camera_dev *pcdev)
 
 	for (i = 0; i < pcdev->channels; i++) {
 		dev_dbg(pcdev->soc_host.v4l2_dev.dev,
-			"%s (channel=%d) ddadr=%08x\n", __func__,
-			i, active->dmas[i].sg_dma);
-		DDADR(pcdev->dma_chans[i]) = active->dmas[i].sg_dma;
-		DCSR(pcdev->dma_chans[i]) = DCSR_RUN;
+			"%s (channel=%d)\n", __func__, i);
+		dma_async_issue_pending(pcdev->dma_chans[i]);
 	}
 }
 
@@ -567,7 +525,7 @@ static void pxa_dma_stop_channels(struct pxa_camera_dev *pcdev)
 	for (i = 0; i < pcdev->channels; i++) {
 		dev_dbg(pcdev->soc_host.v4l2_dev.dev,
 			"%s (channel=%d)\n", __func__, i);
-		DCSR(pcdev->dma_chans[i]) = 0;
+		dmaengine_terminate_all(pcdev->dma_chans[i]);
 	}
 }
 
@@ -575,18 +533,12 @@ static void pxa_dma_add_tail_buf(struct pxa_camera_dev *pcdev,
 				 struct pxa_buffer *buf)
 {
 	int i;
-	struct pxa_dma_desc *buf_last_desc;
 
 	for (i = 0; i < pcdev->channels; i++) {
-		buf_last_desc = buf->dmas[i].sg_cpu + buf->dmas[i].sglen;
-		buf_last_desc->ddadr = DDADR_STOP;
-
-		if (pcdev->sg_tail[i])
-			/* Link the new buffer to the old tail */
-			pcdev->sg_tail[i]->ddadr = buf->dmas[i].sg_dma;
-
-		/* Update the channel tail */
-		pcdev->sg_tail[i] = buf_last_desc;
+		buf->cookie[i] = dmaengine_submit(buf->descs[i]);
+		dev_dbg(pcdev->soc_host.v4l2_dev.dev,
+			"%s (channel=%d) : submit vb=%p cookie=%d\n",
+			__func__, i, buf, buf->descs[i]->cookie);
 	}
 }
 
@@ -603,6 +555,7 @@ static void pxa_camera_start_capture(struct pxa_camera_dev *pcdev)
 	unsigned long cicr0;
 
 	dev_dbg(pcdev->soc_host.v4l2_dev.dev, "%s\n", __func__);
+	__raw_writel(__raw_readl(pcdev->base + CISR), pcdev->base + CISR);
 	/* Enable End-Of-Frame Interrupt */
 	cicr0 = __raw_readl(pcdev->base + CICR0) | CICR0_ENB;
 	cicr0 &= ~CICR0_EOFM;
@@ -677,8 +630,6 @@ static void pxa_camera_wakeup(struct pxa_camera_dev *pcdev,
 			      struct videobuf_buffer *vb,
 			      struct pxa_buffer *buf)
 {
-	int i;
-
 	/* _init is used to debug races, see comment in pxa_camera_reqbufs() */
 	list_del_init(&vb->queue);
 	vb->state = VIDEOBUF_DONE;
@@ -690,8 +641,6 @@ static void pxa_camera_wakeup(struct pxa_camera_dev *pcdev,
 
 	if (list_empty(&pcdev->capture)) {
 		pxa_camera_stop_capture(pcdev);
-		for (i = 0; i < pcdev->channels; i++)
-			pcdev->sg_tail[i] = NULL;
 		return;
 	}
 
@@ -715,50 +664,41 @@ static void pxa_camera_wakeup(struct pxa_camera_dev *pcdev,
  *
  * Context: should only be called within the dma irq handler
  */
-static void pxa_camera_check_link_miss(struct pxa_camera_dev *pcdev)
+static void pxa_camera_check_link_miss(struct pxa_camera_dev *pcdev,
+				       dma_cookie_t last_submitted,
+				       dma_cookie_t last_issued)
 {
-	int i, is_dma_stopped = 1;
+	bool is_dma_stopped = last_submitted != last_issued;
 
-	for (i = 0; i < pcdev->channels; i++)
-		if (DDADR(pcdev->dma_chans[i]) != DDADR_STOP)
-			is_dma_stopped = 0;
 	dev_dbg(pcdev->soc_host.v4l2_dev.dev,
-		"%s : top queued buffer=%p, dma_stopped=%d\n",
+		"%s : top queued buffer=%p, is_dma_stopped=%d\n",
 		__func__, pcdev->active, is_dma_stopped);
+
 	if (pcdev->active && is_dma_stopped)
 		pxa_camera_start_capture(pcdev);
 }
 
-static void pxa_camera_dma_irq(int channel, struct pxa_camera_dev *pcdev,
+static void pxa_camera_dma_irq(struct pxa_camera_dev *pcdev,
 			       enum pxa_camera_active_dma act_dma)
 {
 	struct device *dev = pcdev->soc_host.v4l2_dev.dev;
-	struct pxa_buffer *buf;
+	struct pxa_buffer *buf, *last_buf;
 	unsigned long flags;
-	u32 status, camera_status, overrun;
+	u32 camera_status, overrun;
+	int chan;
 	struct videobuf_buffer *vb;
+	enum dma_status last_status;
+	dma_cookie_t last_issued;
 
 	spin_lock_irqsave(&pcdev->lock, flags);
 
-	status = DCSR(channel);
-	DCSR(channel) = status;
-
 	camera_status = __raw_readl(pcdev->base + CISR);
+	dev_dbg(dev, "camera dma irq, cisr=0x%x dma=%d\n",
+		camera_status, act_dma);
 	overrun = CISR_IFO_0;
 	if (pcdev->channels == 3)
 		overrun |= CISR_IFO_1 | CISR_IFO_2;
 
-	if (status & DCSR_BUSERR) {
-		dev_err(dev, "DMA Bus Error IRQ!\n");
-		goto out;
-	}
-
-	if (!(status & (DCSR_ENDINTR | DCSR_STARTINTR))) {
-		dev_err(dev, "Unknown DMA IRQ source, status: 0x%08x\n",
-			status);
-		goto out;
-	}
-
 	/*
 	 * pcdev->active should not be NULL in DMA irq handler.
 	 *
@@ -778,52 +718,47 @@ static void pxa_camera_dma_irq(int channel, struct pxa_camera_dev *pcdev,
 	buf = container_of(vb, struct pxa_buffer, vb);
 	WARN_ON(buf->inwork || list_empty(&vb->queue));
 
-	dev_dbg(dev, "%s channel=%d %s%s(vb=0x%p) dma.desc=%x\n",
-		__func__, channel, status & DCSR_STARTINTR ? "SOF " : "",
-		status & DCSR_ENDINTR ? "EOF " : "", vb, DDADR(channel));
-
-	if (status & DCSR_ENDINTR) {
-		/*
-		 * It's normal if the last frame creates an overrun, as there
-		 * are no more DMA descriptors to fetch from QCI fifos
-		 */
-		if (camera_status & overrun &&
-		    !list_is_last(pcdev->capture.next, &pcdev->capture)) {
-			dev_dbg(dev, "FIFO overrun! CISR: %x\n",
-				camera_status);
-			pxa_camera_stop_capture(pcdev);
-			pxa_camera_start_capture(pcdev);
-			goto out;
-		}
-		buf->active_dma &= ~act_dma;
-		if (!buf->active_dma) {
-			pxa_camera_wakeup(pcdev, vb, buf);
-			pxa_camera_check_link_miss(pcdev);
-		}
+	/*
+	 * It's normal if the last frame creates an overrun, as there
+	 * are no more DMA descriptors to fetch from QCI fifos
+	 */
+	switch (act_dma) {
+	case DMA_U:
+		chan = 1;
+		break;
+	case DMA_V:
+		chan = 2;
+		break;
+	default:
+		chan = 0;
+		break;
+	}
+	last_buf = list_entry(pcdev->capture.prev,
+			      struct pxa_buffer, vb.queue);
+	last_status = dma_async_is_tx_complete(pcdev->dma_chans[chan],
+					       last_buf->cookie[chan],
+					       NULL, &last_issued);
+	if (camera_status & overrun &&
+	    last_status != DMA_COMPLETE) {
+		dev_dbg(dev, "FIFO overrun! CISR: %x\n",
+			camera_status);
+		pxa_camera_stop_capture(pcdev);
+		list_for_each_entry(buf, &pcdev->capture, vb.queue)
+			pxa_dma_add_tail_buf(pcdev, buf);
+		pxa_camera_start_capture(pcdev);
+		goto out;
+	}
+	buf->active_dma &= ~act_dma;
+	if (!buf->active_dma) {
+		pxa_camera_wakeup(pcdev, vb, buf);
+		pxa_camera_check_link_miss(pcdev, last_buf->cookie[chan],
+					   last_issued);
 	}
 
 out:
 	spin_unlock_irqrestore(&pcdev->lock, flags);
 }
 
-static void pxa_camera_dma_irq_y(int channel, void *data)
-{
-	struct pxa_camera_dev *pcdev = data;
-	pxa_camera_dma_irq(channel, pcdev, DMA_Y);
-}
-
-static void pxa_camera_dma_irq_u(int channel, void *data)
-{
-	struct pxa_camera_dev *pcdev = data;
-	pxa_camera_dma_irq(channel, pcdev, DMA_U);
-}
-
-static void pxa_camera_dma_irq_v(int channel, void *data)
-{
-	struct pxa_camera_dev *pcdev = data;
-	pxa_camera_dma_irq(channel, pcdev, DMA_V);
-}
-
 static struct videobuf_queue_ops pxa_videobuf_ops = {
 	.buf_setup      = pxa_videobuf_setup,
 	.buf_prepare    = pxa_videobuf_prepare,
@@ -920,13 +855,35 @@ static void pxa_camera_deactivate(struct pxa_camera_dev *pcdev)
 	clk_disable_unprepare(pcdev->clk);
 }
 
-static irqreturn_t pxa_camera_irq(int irq, void *data)
+static void pxa_camera_eof(unsigned long arg)
 {
-	struct pxa_camera_dev *pcdev = data;
-	unsigned long status, cifr, cicr0;
+	struct pxa_camera_dev *pcdev = (struct pxa_camera_dev *)arg;
+	unsigned long cifr;
 	struct pxa_buffer *buf;
 	struct videobuf_buffer *vb;
 
+	dev_dbg(pcdev->soc_host.v4l2_dev.dev,
+		"Camera interrupt status 0x%x\n",
+		__raw_readl(pcdev->base + CISR));
+
+	/* Reset the FIFOs */
+	cifr = __raw_readl(pcdev->base + CIFR) | CIFR_RESET_F;
+	__raw_writel(cifr, pcdev->base + CIFR);
+
+	pcdev->active = list_first_entry(&pcdev->capture,
+					 struct pxa_buffer, vb.queue);
+	vb = &pcdev->active->vb;
+	buf = container_of(vb, struct pxa_buffer, vb);
+	pxa_videobuf_set_actdma(pcdev, buf);
+
+	pxa_dma_start_channels(pcdev);
+}
+
+static irqreturn_t pxa_camera_irq(int irq, void *data)
+{
+	struct pxa_camera_dev *pcdev = data;
+	unsigned long status, cicr0;
+
 	status = __raw_readl(pcdev->base + CISR);
 	dev_dbg(pcdev->soc_host.v4l2_dev.dev,
 		"Camera interrupt status 0x%lx\n", status);
@@ -937,20 +894,9 @@ static irqreturn_t pxa_camera_irq(int irq, void *data)
 	__raw_writel(status, pcdev->base + CISR);
 
 	if (status & CISR_EOF) {
-		/* Reset the FIFOs */
-		cifr = __raw_readl(pcdev->base + CIFR) | CIFR_RESET_F;
-		__raw_writel(cifr, pcdev->base + CIFR);
-
-		pcdev->active = list_first_entry(&pcdev->capture,
-					   struct pxa_buffer, vb.queue);
-		vb = &pcdev->active->vb;
-		buf = container_of(vb, struct pxa_buffer, vb);
-		pxa_videobuf_set_actdma(pcdev, buf);
-
-		pxa_dma_start_channels(pcdev);
-
 		cicr0 = __raw_readl(pcdev->base + CICR0) | CICR0_EOFM;
 		__raw_writel(cicr0, pcdev->base + CICR0);
+		tasklet_schedule(&pcdev->task_eof);
 	}
 
 	return IRQ_HANDLED;
@@ -993,10 +939,7 @@ static void pxa_camera_clock_stop(struct soc_camera_host *ici)
 	__raw_writel(0x3ff, pcdev->base + CICR0);
 
 	/* Stop DMA engine */
-	DCSR(pcdev->dma_chans[0]) = 0;
-	DCSR(pcdev->dma_chans[1]) = 0;
-	DCSR(pcdev->dma_chans[2]) = 0;
-
+	pxa_dma_stop_channels(pcdev);
 	pxa_camera_deactivate(pcdev);
 }
 
@@ -1623,10 +1566,6 @@ static int pxa_camera_resume(struct device *dev)
 	struct pxa_camera_dev *pcdev = ici->priv;
 	int i = 0, ret = 0;
 
-	DRCMR(68) = pcdev->dma_chans[0] | DRCMR_MAPVLD;
-	DRCMR(69) = pcdev->dma_chans[1] | DRCMR_MAPVLD;
-	DRCMR(70) = pcdev->dma_chans[2] | DRCMR_MAPVLD;
-
 	__raw_writel(pcdev->save_cicr[i++] & ~CICR0_ENB, pcdev->base + CICR0);
 	__raw_writel(pcdev->save_cicr[i++], pcdev->base + CICR1);
 	__raw_writel(pcdev->save_cicr[i++], pcdev->base + CICR2);
@@ -1732,8 +1671,15 @@ static int pxa_camera_probe(struct platform_device *pdev)
 	struct pxa_camera_dev *pcdev;
 	struct resource *res;
 	void __iomem *base;
+	struct dma_slave_config config = {
+		.src_addr_width = 0,
+		.src_maxburst = 8,
+		.direction = DMA_DEV_TO_MEM,
+	};
+	dma_cap_mask_t mask;
+	struct pxad_param params;
 	int irq;
-	int err = 0;
+	int err = 0, i;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	irq = platform_get_irq(pdev, 0);
@@ -1801,36 +1747,47 @@ static int pxa_camera_probe(struct platform_device *pdev)
 	pcdev->base = base;
 
 	/* request dma */
-	err = pxa_request_dma("CI_Y", DMA_PRIO_HIGH,
-			      pxa_camera_dma_irq_y, pcdev);
-	if (err < 0) {
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+	dma_cap_set(DMA_PRIVATE, mask);
+
+	params.prio = 0;
+	params.drcmr = 68;
+	pcdev->dma_chans[0] =
+		dma_request_slave_channel_compat(mask, pxad_filter_fn,
+						 &params, &pdev->dev, "CI_Y");
+	if (!pcdev->dma_chans[0]) {
 		dev_err(&pdev->dev, "Can't request DMA for Y\n");
-		return err;
+		return -ENODEV;
 	}
-	pcdev->dma_chans[0] = err;
-	dev_dbg(&pdev->dev, "got DMA channel %d\n", pcdev->dma_chans[0]);
 
-	err = pxa_request_dma("CI_U", DMA_PRIO_HIGH,
-			      pxa_camera_dma_irq_u, pcdev);
-	if (err < 0) {
-		dev_err(&pdev->dev, "Can't request DMA for U\n");
+	params.drcmr = 69;
+	pcdev->dma_chans[1] =
+		dma_request_slave_channel_compat(mask, pxad_filter_fn,
+						 &params, &pdev->dev, "CI_U");
+	if (!pcdev->dma_chans[1]) {
+		dev_err(&pdev->dev, "Can't request DMA for Y\n");
 		goto exit_free_dma_y;
 	}
-	pcdev->dma_chans[1] = err;
-	dev_dbg(&pdev->dev, "got DMA channel (U) %d\n", pcdev->dma_chans[1]);
 
-	err = pxa_request_dma("CI_V", DMA_PRIO_HIGH,
-			      pxa_camera_dma_irq_v, pcdev);
-	if (err < 0) {
+	params.drcmr = 70;
+	pcdev->dma_chans[2] =
+		dma_request_slave_channel_compat(mask, pxad_filter_fn,
+						 &params, &pdev->dev, "CI_V");
+	if (!pcdev->dma_chans[2]) {
 		dev_err(&pdev->dev, "Can't request DMA for V\n");
 		goto exit_free_dma_u;
 	}
-	pcdev->dma_chans[2] = err;
-	dev_dbg(&pdev->dev, "got DMA channel (V) %d\n", pcdev->dma_chans[2]);
 
-	DRCMR(68) = pcdev->dma_chans[0] | DRCMR_MAPVLD;
-	DRCMR(69) = pcdev->dma_chans[1] | DRCMR_MAPVLD;
-	DRCMR(70) = pcdev->dma_chans[2] | DRCMR_MAPVLD;
+	for (i = 0; i < 3; i++) {
+		config.src_addr = pcdev->res->start + CIBR0 + i * 8;
+		err = dmaengine_slave_config(pcdev->dma_chans[i], &config);
+		if (err < 0) {
+			dev_err(&pdev->dev, "dma slave config failed: %d\n",
+				err);
+			goto exit_free_dma;
+		}
+	}
 
 	/* request irq */
 	err = devm_request_irq(&pdev->dev, pcdev->irq, pxa_camera_irq, 0,
@@ -1845,6 +1802,7 @@ static int pxa_camera_probe(struct platform_device *pdev)
 	pcdev->soc_host.priv		= pcdev;
 	pcdev->soc_host.v4l2_dev.dev	= &pdev->dev;
 	pcdev->soc_host.nr		= pdev->id;
+	tasklet_init(&pcdev->task_eof, pxa_camera_eof, (unsigned long)pcdev);
 
 	err = soc_camera_host_register(&pcdev->soc_host);
 	if (err)
@@ -1853,11 +1811,11 @@ static int pxa_camera_probe(struct platform_device *pdev)
 	return 0;
 
 exit_free_dma:
-	pxa_free_dma(pcdev->dma_chans[2]);
+	dma_release_channel(pcdev->dma_chans[2]);
 exit_free_dma_u:
-	pxa_free_dma(pcdev->dma_chans[1]);
+	dma_release_channel(pcdev->dma_chans[1]);
 exit_free_dma_y:
-	pxa_free_dma(pcdev->dma_chans[0]);
+	dma_release_channel(pcdev->dma_chans[0]);
 	return err;
 }
 
@@ -1867,9 +1825,9 @@ static int pxa_camera_remove(struct platform_device *pdev)
 	struct pxa_camera_dev *pcdev = container_of(soc_host,
 					struct pxa_camera_dev, soc_host);
 
-	pxa_free_dma(pcdev->dma_chans[0]);
-	pxa_free_dma(pcdev->dma_chans[1]);
-	pxa_free_dma(pcdev->dma_chans[2]);
+	dma_release_channel(pcdev->dma_chans[0]);
+	dma_release_channel(pcdev->dma_chans[1]);
+	dma_release_channel(pcdev->dma_chans[2]);
 
 	soc_camera_host_unregister(soc_host);
 
diff --git a/drivers/media/platform/soc_camera/rcar_vin.c b/drivers/media/platform/soc_camera/rcar_vin.c
index b7fd695b9ed5..3b8edf458964 100644
--- a/drivers/media/platform/soc_camera/rcar_vin.c
+++ b/drivers/media/platform/soc_camera/rcar_vin.c
@@ -124,7 +124,7 @@
 #define VNDMR_EXRGB		(1 << 8)
 #define VNDMR_BPSM		(1 << 4)
 #define VNDMR_DTMD_YCSEP	(1 << 1)
-#define VNDMR_DTMD_ARGB1555	(1 << 0)
+#define VNDMR_DTMD_ARGB		(1 << 0)
 
 /* Video n Data Mode Register 2 bits */
 #define VNDMR2_VPS		(1 << 30)
@@ -143,6 +143,7 @@
 #define RCAR_VIN_BT656			(1 << 3)
 
 enum chip_id {
+	RCAR_GEN3,
 	RCAR_GEN2,
 	RCAR_H1,
 	RCAR_M1,
@@ -642,21 +643,26 @@ static int rcar_vin_setup(struct rcar_vin_priv *priv)
 		output_is_yuv = true;
 		break;
 	case V4L2_PIX_FMT_RGB555X:
-		dmr = VNDMR_DTMD_ARGB1555;
+		dmr = VNDMR_DTMD_ARGB;
 		break;
 	case V4L2_PIX_FMT_RGB565:
 		dmr = 0;
 		break;
 	case V4L2_PIX_FMT_RGB32:
-		if (priv->chip == RCAR_GEN2 || priv->chip == RCAR_H1 ||
-		    priv->chip == RCAR_E1) {
-			dmr = VNDMR_EXRGB;
-			break;
-		}
+		if (priv->chip != RCAR_GEN2 && priv->chip != RCAR_H1 &&
+		    priv->chip != RCAR_E1)
+			goto e_format;
+
+		dmr = VNDMR_EXRGB;
+		break;
+	case V4L2_PIX_FMT_ARGB32:
+		if (priv->chip != RCAR_GEN3)
+			goto e_format;
+
+		dmr = VNDMR_EXRGB | VNDMR_DTMD_ARGB;
+		break;
 	default:
-		dev_warn(icd->parent, "Invalid fourcc format (0x%x)\n",
-			 icd->current_fmt->host_fmt->fourcc);
-		return -EINVAL;
+		goto e_format;
 	}
 
 	/* Always update on field change */
@@ -678,6 +684,11 @@ static int rcar_vin_setup(struct rcar_vin_priv *priv)
 	iowrite32(vnmc | VNMC_ME, priv->base + VNMC_REG);
 
 	return 0;
+
+e_format:
+	dev_warn(icd->parent, "Invalid fourcc format (0x%x)\n",
+		 icd->current_fmt->host_fmt->fourcc);
+	return -EINVAL;
 }
 
 static void rcar_vin_capture(struct rcar_vin_priv *priv)
@@ -1303,6 +1314,14 @@ static const struct soc_mbus_pixelfmt rcar_vin_formats[] = {
 		.order			= SOC_MBUS_ORDER_LE,
 		.layout			= SOC_MBUS_LAYOUT_PACKED,
 	},
+	{
+		.fourcc			= V4L2_PIX_FMT_ARGB32,
+		.name			= "ARGB8888",
+		.bits_per_sample	= 32,
+		.packing		= SOC_MBUS_PACKING_NONE,
+		.order			= SOC_MBUS_ORDER_LE,
+		.layout			= SOC_MBUS_LAYOUT_PACKED,
+	},
 };
 
 static int rcar_vin_get_formats(struct soc_camera_device *icd, unsigned int idx,
@@ -1610,6 +1629,7 @@ static int rcar_vin_set_fmt(struct soc_camera_device *icd,
 	case V4L2_PIX_FMT_RGB32:
 		can_scale = priv->chip != RCAR_E1;
 		break;
+	case V4L2_PIX_FMT_ARGB32:
 	case V4L2_PIX_FMT_UYVY:
 	case V4L2_PIX_FMT_YUYV:
 	case V4L2_PIX_FMT_RGB565:
@@ -1818,6 +1838,7 @@ static struct soc_camera_host_ops rcar_vin_host_ops = {
 
 #ifdef CONFIG_OF
 static const struct of_device_id rcar_vin_of_table[] = {
+	{ .compatible = "renesas,vin-r8a7795", .data = (void *)RCAR_GEN3 },
 	{ .compatible = "renesas,vin-r8a7794", .data = (void *)RCAR_GEN2 },
 	{ .compatible = "renesas,vin-r8a7793", .data = (void *)RCAR_GEN2 },
 	{ .compatible = "renesas,vin-r8a7791", .data = (void *)RCAR_GEN2 },
diff --git a/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c b/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c
index 90c87f2b4ec0..b9f369c0fb94 100644
--- a/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c
+++ b/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c
@@ -213,8 +213,7 @@ static int sh_mobile_ceu_videobuf_setup(struct vb2_queue *vq,
 			unsigned int *count, unsigned int *num_planes,
 			unsigned int sizes[], void *alloc_ctxs[])
 {
-	struct soc_camera_device *icd = container_of(vq,
-			struct soc_camera_device, vb2_vidq);
+	struct soc_camera_device *icd = soc_camera_from_vb2q(vq);
 	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
 	struct sh_mobile_ceu_dev *pcdev = ici->priv;
 
@@ -361,8 +360,7 @@ static int sh_mobile_ceu_videobuf_prepare(struct vb2_buffer *vb)
 static void sh_mobile_ceu_videobuf_queue(struct vb2_buffer *vb)
 {
 	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
-	struct soc_camera_device *icd = container_of(vb->vb2_queue,
-			struct soc_camera_device, vb2_vidq);
+	struct soc_camera_device *icd = soc_camera_from_vb2q(vb->vb2_queue);
 	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
 	struct sh_mobile_ceu_dev *pcdev = ici->priv;
 	struct sh_mobile_ceu_buffer *buf = to_ceu_vb(vbuf);
@@ -413,8 +411,7 @@ error:
 static void sh_mobile_ceu_videobuf_release(struct vb2_buffer *vb)
 {
 	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
-	struct soc_camera_device *icd = container_of(vb->vb2_queue,
-			struct soc_camera_device, vb2_vidq);
+	struct soc_camera_device *icd = soc_camera_from_vb2q(vb->vb2_queue);
 	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
 	struct sh_mobile_ceu_buffer *buf = to_ceu_vb(vbuf);
 	struct sh_mobile_ceu_dev *pcdev = ici->priv;
@@ -444,8 +441,7 @@ static void sh_mobile_ceu_videobuf_release(struct vb2_buffer *vb)
 static int sh_mobile_ceu_videobuf_init(struct vb2_buffer *vb)
 {
 	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
-	struct soc_camera_device *icd = container_of(vb->vb2_queue,
-			struct soc_camera_device, vb2_vidq);
+	struct soc_camera_device *icd = soc_camera_from_vb2q(vb->vb2_queue);
 	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
 	struct sh_mobile_ceu_dev *pcdev = ici->priv;
 
@@ -460,7 +456,7 @@ static int sh_mobile_ceu_videobuf_init(struct vb2_buffer *vb)
 
 static void sh_mobile_ceu_stop_streaming(struct vb2_queue *q)
 {
-	struct soc_camera_device *icd = container_of(q, struct soc_camera_device, vb2_vidq);
+	struct soc_camera_device *icd = soc_camera_from_vb2q(q);
 	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
 	struct sh_mobile_ceu_dev *pcdev = ici->priv;
 	struct list_head *buf_head, *tmp;
diff --git a/drivers/media/platform/sti/c8sectpfe/c8sectpfe-dvb.c b/drivers/media/platform/sti/c8sectpfe/c8sectpfe-dvb.c
index 69d7fe4471c2..2c0015b1264d 100644
--- a/drivers/media/platform/sti/c8sectpfe/c8sectpfe-dvb.c
+++ b/drivers/media/platform/sti/c8sectpfe/c8sectpfe-dvb.c
@@ -118,7 +118,7 @@ int c8sectpfe_frontend_attach(struct dvb_frontend **fe,
 		struct channel_info *tsin, int chan_num)
 {
 	struct tda18212_config *tda18212;
-	struct stv6110x_devctl *fe2;
+	const struct stv6110x_devctl *fe2;
 	struct i2c_client *client;
 	struct i2c_board_info tda18212_info = {
 		.type = "tda18212",
diff --git a/drivers/media/platform/ti-vpe/Makefile b/drivers/media/platform/ti-vpe/Makefile
index be680f839e77..e236059a60ad 100644
--- a/drivers/media/platform/ti-vpe/Makefile
+++ b/drivers/media/platform/ti-vpe/Makefile
@@ -3,3 +3,7 @@ obj-$(CONFIG_VIDEO_TI_VPE) += ti-vpe.o
 ti-vpe-y := vpe.o sc.o csc.o vpdma.o
 
 ccflags-$(CONFIG_VIDEO_TI_VPE_DEBUG) += -DDEBUG
+
+obj-$(CONFIG_VIDEO_TI_CAL) += ti-cal.o
+
+ti-cal-y := cal.o
diff --git a/drivers/media/platform/ti-vpe/cal.c b/drivers/media/platform/ti-vpe/cal.c
new file mode 100644
index 000000000000..82001e6b5553
--- /dev/null
+++ b/drivers/media/platform/ti-vpe/cal.c
@@ -0,0 +1,1947 @@
+/*
+ * TI CAL camera interface driver
+ *
+ * Copyright (c) 2015 Texas Instruments Inc.
+ * Benoit Parrot, <bparrot@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation
+ */
+
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/ioctl.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/delay.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <linux/videodev2.h>
+#include <linux/of_device.h>
+#include <linux/of_graph.h>
+
+#include <media/v4l2-of.h>
+#include <media/v4l2-async.h>
+#include <media/v4l2-common.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-ioctl.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-fh.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-common.h>
+#include <media/videobuf2-core.h>
+#include <media/videobuf2-dma-contig.h>
+#include "cal_regs.h"
+
+#define CAL_MODULE_NAME "cal"
+
+#define MAX_WIDTH 1920
+#define MAX_HEIGHT 1200
+
+#define CAL_VERSION "0.1.0"
+
+MODULE_DESCRIPTION("TI CAL driver");
+MODULE_AUTHOR("Benoit Parrot, <bparrot@ti.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_VERSION(CAL_VERSION);
+
+static unsigned video_nr = -1;
+module_param(video_nr, uint, 0644);
+MODULE_PARM_DESC(video_nr, "videoX start number, -1 is autodetect");
+
+static unsigned debug;
+module_param(debug, uint, 0644);
+MODULE_PARM_DESC(debug, "activates debug info");
+
+/* timeperframe: min/max and default */
+static const struct v4l2_fract
+	tpf_default = {.numerator = 1001,	.denominator = 30000};
+
+#define cal_dbg(level, caldev, fmt, arg...)	\
+		v4l2_dbg(level, debug, &caldev->v4l2_dev, fmt, ##arg)
+#define cal_info(caldev, fmt, arg...)	\
+		v4l2_info(&caldev->v4l2_dev, fmt, ##arg)
+#define cal_err(caldev, fmt, arg...)	\
+		v4l2_err(&caldev->v4l2_dev, fmt, ##arg)
+
+#define ctx_dbg(level, ctx, fmt, arg...)	\
+		v4l2_dbg(level, debug, &ctx->v4l2_dev, fmt, ##arg)
+#define ctx_info(ctx, fmt, arg...)	\
+		v4l2_info(&ctx->v4l2_dev, fmt, ##arg)
+#define ctx_err(ctx, fmt, arg...)	\
+		v4l2_err(&ctx->v4l2_dev, fmt, ##arg)
+
+#define CAL_NUM_INPUT 1
+#define CAL_NUM_CONTEXT 2
+
+#define bytes_per_line(pixel, bpp) (ALIGN(pixel * bpp, 16))
+
+#define reg_read(dev, offset) ioread32(dev->base + offset)
+#define reg_write(dev, offset, val) iowrite32(val, dev->base + offset)
+
+#define reg_read_field(dev, offset, mask) get_field(reg_read(dev, offset), \
+						    mask)
+#define reg_write_field(dev, offset, field, mask) { \
+	u32 val = reg_read(dev, offset); \
+	set_field(&val, field, mask); \
+	reg_write(dev, offset, val); }
+
+/* ------------------------------------------------------------------
+ *	Basic structures
+ * ------------------------------------------------------------------
+ */
+
+struct cal_fmt {
+	u32	fourcc;
+	u32	code;
+	u8	depth;
+};
+
+static struct cal_fmt cal_formats[] = {
+	{
+		.fourcc		= V4L2_PIX_FMT_YUYV,
+		.code		= MEDIA_BUS_FMT_YUYV8_2X8,
+		.depth		= 16,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_UYVY,
+		.code		= MEDIA_BUS_FMT_UYVY8_2X8,
+		.depth		= 16,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_YVYU,
+		.code		= MEDIA_BUS_FMT_YVYU8_2X8,
+		.depth		= 16,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_VYUY,
+		.code		= MEDIA_BUS_FMT_VYUY8_2X8,
+		.depth		= 16,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_RGB565, /* gggbbbbb rrrrrggg */
+		.code		= MEDIA_BUS_FMT_RGB565_2X8_LE,
+		.depth		= 16,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_RGB565X, /* rrrrrggg gggbbbbb */
+		.code		= MEDIA_BUS_FMT_RGB565_2X8_BE,
+		.depth		= 16,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_RGB555, /* gggbbbbb arrrrrgg */
+		.code		= MEDIA_BUS_FMT_RGB555_2X8_PADHI_LE,
+		.depth		= 16,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_RGB555X, /* arrrrrgg gggbbbbb */
+		.code		= MEDIA_BUS_FMT_RGB555_2X8_PADHI_BE,
+		.depth		= 16,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_RGB24, /* rgb */
+		.code		= MEDIA_BUS_FMT_RGB888_2X12_LE,
+		.depth		= 24,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_BGR24, /* bgr */
+		.code		= MEDIA_BUS_FMT_RGB888_2X12_BE,
+		.depth		= 24,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_RGB32, /* argb */
+		.code		= MEDIA_BUS_FMT_ARGB8888_1X32,
+		.depth		= 32,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_SBGGR8,
+		.code		= MEDIA_BUS_FMT_SBGGR8_1X8,
+		.depth		= 8,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_SGBRG8,
+		.code		= MEDIA_BUS_FMT_SGBRG8_1X8,
+		.depth		= 8,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_SGRBG8,
+		.code		= MEDIA_BUS_FMT_SGRBG8_1X8,
+		.depth		= 8,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_SRGGB8,
+		.code		= MEDIA_BUS_FMT_SRGGB8_1X8,
+		.depth		= 8,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_SBGGR10,
+		.code		= MEDIA_BUS_FMT_SBGGR10_1X10,
+		.depth		= 16,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_SGBRG10,
+		.code		= MEDIA_BUS_FMT_SGBRG10_1X10,
+		.depth		= 16,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_SGRBG10,
+		.code		= MEDIA_BUS_FMT_SGRBG10_1X10,
+		.depth		= 16,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_SRGGB10,
+		.code		= MEDIA_BUS_FMT_SRGGB10_1X10,
+		.depth		= 16,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_SBGGR12,
+		.code		= MEDIA_BUS_FMT_SBGGR12_1X12,
+		.depth		= 16,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_SGBRG12,
+		.code		= MEDIA_BUS_FMT_SGBRG12_1X12,
+		.depth		= 16,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_SGRBG12,
+		.code		= MEDIA_BUS_FMT_SGRBG12_1X12,
+		.depth		= 16,
+	}, {
+		.fourcc		= V4L2_PIX_FMT_SRGGB12,
+		.code		= MEDIA_BUS_FMT_SRGGB12_1X12,
+		.depth		= 16,
+	},
+};
+
+/*  Print Four-character-code (FOURCC) */
+static char *fourcc_to_str(u32 fmt)
+{
+	static char code[5];
+
+	code[0] = (unsigned char)(fmt & 0xff);
+	code[1] = (unsigned char)((fmt >> 8) & 0xff);
+	code[2] = (unsigned char)((fmt >> 16) & 0xff);
+	code[3] = (unsigned char)((fmt >> 24) & 0xff);
+	code[4] = '\0';
+
+	return code;
+}
+
+/* buffer for one video frame */
+struct cal_buffer {
+	/* common v4l buffer stuff -- must be first */
+	struct vb2_v4l2_buffer	vb;
+	struct list_head	list;
+	const struct cal_fmt	*fmt;
+};
+
+struct cal_dmaqueue {
+	struct list_head	active;
+
+	/* Counters to control fps rate */
+	int			frame;
+	int			ini_jiffies;
+};
+
+struct cm_data {
+	void __iomem		*base;
+	struct resource		*res;
+
+	unsigned int		camerrx_control;
+
+	struct platform_device *pdev;
+};
+
+struct cc_data {
+	void __iomem		*base;
+	struct resource		*res;
+
+	struct platform_device *pdev;
+};
+
+/*
+ * there is one cal_dev structure in the driver, it is shared by
+ * all instances.
+ */
+struct cal_dev {
+	int			irq;
+	void __iomem		*base;
+	struct resource		*res;
+	struct platform_device	*pdev;
+	struct v4l2_device	v4l2_dev;
+
+	/* Control Module handle */
+	struct cm_data		*cm;
+	/* Camera Core Module handle */
+	struct cc_data		*cc[CAL_NUM_CSI2_PORTS];
+
+	struct cal_ctx		*ctx[CAL_NUM_CONTEXT];
+};
+
+/*
+ * There is one cal_ctx structure for each camera core context.
+ */
+struct cal_ctx {
+	struct v4l2_device	v4l2_dev;
+	struct v4l2_ctrl_handler ctrl_handler;
+	struct video_device	vdev;
+	struct v4l2_async_notifier notifier;
+	struct v4l2_subdev	*sensor;
+	struct v4l2_of_endpoint	endpoint;
+
+	struct v4l2_async_subdev asd;
+	struct v4l2_async_subdev *asd_list[1];
+
+	struct v4l2_fh		fh;
+	struct cal_dev		*dev;
+	struct cc_data		*cc;
+
+	/* v4l2_ioctl mutex */
+	struct mutex		mutex;
+	/* v4l2 buffers lock */
+	spinlock_t		slock;
+
+	/* Several counters */
+	unsigned long		jiffies;
+
+	struct vb2_alloc_ctx	*alloc_ctx;
+	struct cal_dmaqueue	vidq;
+
+	/* Input Number */
+	int			input;
+
+	/* video capture */
+	const struct cal_fmt	*fmt;
+	/* Used to store current pixel format */
+	struct v4l2_format		v_fmt;
+	/* Used to store current mbus frame format */
+	struct v4l2_mbus_framefmt	m_fmt;
+
+	/* Current subdev enumerated format */
+	struct cal_fmt		*active_fmt[ARRAY_SIZE(cal_formats)];
+	int			num_active_fmt;
+
+	struct v4l2_fract	timeperframe;
+	unsigned int		sequence;
+	unsigned int		external_rate;
+	struct vb2_queue	vb_vidq;
+	unsigned int		seq_count;
+	unsigned int		csi2_port;
+	unsigned int		virtual_channel;
+
+	/* Pointer pointing to current v4l2_buffer */
+	struct cal_buffer	*cur_frm;
+	/* Pointer pointing to next v4l2_buffer */
+	struct cal_buffer	*next_frm;
+};
+
+static const struct cal_fmt *find_format_by_pix(struct cal_ctx *ctx,
+						u32 pixelformat)
+{
+	const struct cal_fmt *fmt;
+	unsigned int k;
+
+	for (k = 0; k < ctx->num_active_fmt; k++) {
+		fmt = ctx->active_fmt[k];
+		if (fmt->fourcc == pixelformat)
+			return fmt;
+	}
+
+	return NULL;
+}
+
+static const struct cal_fmt *find_format_by_code(struct cal_ctx *ctx,
+						 u32 code)
+{
+	const struct cal_fmt *fmt;
+	unsigned int k;
+
+	for (k = 0; k < ctx->num_active_fmt; k++) {
+		fmt = ctx->active_fmt[k];
+		if (fmt->code == code)
+			return fmt;
+	}
+
+	return NULL;
+}
+
+static inline struct cal_ctx *notifier_to_ctx(struct v4l2_async_notifier *n)
+{
+	return container_of(n, struct cal_ctx, notifier);
+}
+
+static inline int get_field(u32 value, u32 mask)
+{
+	return (value & mask) >> __ffs(mask);
+}
+
+static inline void set_field(u32 *valp, u32 field, u32 mask)
+{
+	u32 val = *valp;
+
+	val &= ~mask;
+	val |= (field << __ffs(mask)) & mask;
+	*valp = val;
+}
+
+/*
+ * Control Module block access
+ */
+static struct cm_data *cm_create(struct cal_dev *dev)
+{
+	struct platform_device *pdev = dev->pdev;
+	struct cm_data *cm;
+
+	cm = devm_kzalloc(&pdev->dev, sizeof(*cm), GFP_KERNEL);
+	if (!cm)
+		return ERR_PTR(-ENOMEM);
+
+	cm->res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						"camerrx_control");
+	cm->base = devm_ioremap_resource(&pdev->dev, cm->res);
+	if (IS_ERR(cm->base)) {
+		cal_err(dev, "failed to ioremap\n");
+		return ERR_CAST(cm->base);
+	}
+
+	cal_dbg(1, dev, "ioresource %s at %pa - %pa\n",
+		cm->res->name, &cm->res->start, &cm->res->end);
+
+	return cm;
+}
+
+static void camerarx_phy_enable(struct cal_ctx *ctx)
+{
+	u32 val;
+
+	if (!ctx->dev->cm->base) {
+		ctx_err(ctx, "cm not mapped\n");
+		return;
+	}
+
+	val = reg_read(ctx->dev->cm, CM_CTRL_CORE_CAMERRX_CONTROL);
+	if (ctx->csi2_port == 1) {
+		set_field(&val, 1, CM_CAMERRX_CTRL_CSI0_CTRLCLKEN_MASK);
+		set_field(&val, 0, CM_CAMERRX_CTRL_CSI0_CAMMODE_MASK);
+		/* enable all lanes by default */
+		set_field(&val, 0xf, CM_CAMERRX_CTRL_CSI0_LANEENABLE_MASK);
+		set_field(&val, 1, CM_CAMERRX_CTRL_CSI0_MODE_MASK);
+	} else if (ctx->csi2_port == 2) {
+		set_field(&val, 1, CM_CAMERRX_CTRL_CSI1_CTRLCLKEN_MASK);
+		set_field(&val, 0, CM_CAMERRX_CTRL_CSI1_CAMMODE_MASK);
+		/* enable all lanes by default */
+		set_field(&val, 0x3, CM_CAMERRX_CTRL_CSI1_LANEENABLE_MASK);
+		set_field(&val, 1, CM_CAMERRX_CTRL_CSI1_MODE_MASK);
+	}
+	reg_write(ctx->dev->cm, CM_CTRL_CORE_CAMERRX_CONTROL, val);
+}
+
+static void camerarx_phy_disable(struct cal_ctx *ctx)
+{
+	u32 val;
+
+	if (!ctx->dev->cm->base) {
+		ctx_err(ctx, "cm not mapped\n");
+		return;
+	}
+
+	val = reg_read(ctx->dev->cm, CM_CTRL_CORE_CAMERRX_CONTROL);
+	if (ctx->csi2_port == 1)
+		set_field(&val, 0x0, CM_CAMERRX_CTRL_CSI0_CTRLCLKEN_MASK);
+	else if (ctx->csi2_port == 2)
+		set_field(&val, 0x0, CM_CAMERRX_CTRL_CSI1_CTRLCLKEN_MASK);
+	reg_write(ctx->dev->cm, CM_CTRL_CORE_CAMERRX_CONTROL, val);
+}
+
+/*
+ * Camera Instance access block
+ */
+static struct cc_data *cc_create(struct cal_dev *dev, unsigned int core)
+{
+	struct platform_device *pdev = dev->pdev;
+	struct cc_data *cc;
+
+	cc = devm_kzalloc(&pdev->dev, sizeof(*cc), GFP_KERNEL);
+	if (!cc)
+		return ERR_PTR(-ENOMEM);
+
+	cc->res = platform_get_resource_byname(pdev,
+					       IORESOURCE_MEM,
+					       (core == 0) ?
+						"cal_rx_core0" :
+						"cal_rx_core1");
+	cc->base = devm_ioremap_resource(&pdev->dev, cc->res);
+	if (IS_ERR(cc->base)) {
+		cal_err(dev, "failed to ioremap\n");
+		return ERR_CAST(cc->base);
+	}
+
+	cal_dbg(1, dev, "ioresource %s at %pa - %pa\n",
+		cc->res->name, &cc->res->start, &cc->res->end);
+
+	return cc;
+}
+
+/*
+ * Get Revision and HW info
+ */
+static void cal_get_hwinfo(struct cal_dev *dev)
+{
+	u32 revision = 0;
+	u32 hwinfo = 0;
+
+	revision = reg_read(dev, CAL_HL_REVISION);
+	cal_dbg(3, dev, "CAL_HL_REVISION = 0x%08x (expecting 0x40000200)\n",
+		revision);
+
+	hwinfo = reg_read(dev, CAL_HL_HWINFO);
+	cal_dbg(3, dev, "CAL_HL_HWINFO = 0x%08x (expecting 0xA3C90469)\n",
+		hwinfo);
+}
+
+static inline int cal_runtime_get(struct cal_dev *dev)
+{
+	int r;
+
+	r = pm_runtime_get_sync(&dev->pdev->dev);
+
+	return r;
+}
+
+static inline void cal_runtime_put(struct cal_dev *dev)
+{
+	pm_runtime_put_sync(&dev->pdev->dev);
+}
+
+static void cal_quickdump_regs(struct cal_dev *dev)
+{
+	cal_info(dev, "CAL Registers @ 0x%pa:\n", &dev->res->start);
+	print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 16, 4,
+		       (__force const void *)dev->base,
+		       resource_size(dev->res), false);
+
+	if (dev->ctx[0]) {
+		cal_info(dev, "CSI2 Core 0 Registers @ %pa:\n",
+			 &dev->ctx[0]->cc->res->start);
+		print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 16, 4,
+			       (__force const void *)dev->ctx[0]->cc->base,
+			       resource_size(dev->ctx[0]->cc->res),
+			       false);
+	}
+
+	if (dev->ctx[1]) {
+		cal_info(dev, "CSI2 Core 1 Registers @ %pa:\n",
+			 &dev->ctx[1]->cc->res->start);
+		print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 16, 4,
+			       (__force const void *)dev->ctx[1]->cc->base,
+			       resource_size(dev->ctx[1]->cc->res),
+			       false);
+	}
+
+	cal_info(dev, "CAMERRX_Control Registers @ %pa:\n",
+		 &dev->cm->res->start);
+	print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 16, 4,
+		       (__force const void *)dev->cm->base,
+		       resource_size(dev->cm->res), false);
+}
+
+/*
+ * Enable the expected IRQ sources
+ */
+static void enable_irqs(struct cal_ctx *ctx)
+{
+	/* Enable IRQ_WDMA_END 0/1 */
+	reg_write_field(ctx->dev,
+			CAL_HL_IRQENABLE_SET(2),
+			CAL_HL_IRQ_ENABLE,
+			CAL_HL_IRQ_MASK(ctx->csi2_port));
+	/* Enable IRQ_WDMA_START 0/1 */
+	reg_write_field(ctx->dev,
+			CAL_HL_IRQENABLE_SET(3),
+			CAL_HL_IRQ_ENABLE,
+			CAL_HL_IRQ_MASK(ctx->csi2_port));
+	/* Todo: Add VC_IRQ and CSI2_COMPLEXIO_IRQ handling */
+	reg_write(ctx->dev, CAL_CSI2_VC_IRQENABLE(1), 0xFF000000);
+}
+
+static void disable_irqs(struct cal_ctx *ctx)
+{
+	/* Disable IRQ_WDMA_END 0/1 */
+	reg_write_field(ctx->dev,
+			CAL_HL_IRQENABLE_CLR(2),
+			CAL_HL_IRQ_CLEAR,
+			CAL_HL_IRQ_MASK(ctx->csi2_port));
+	/* Disable IRQ_WDMA_START 0/1 */
+	reg_write_field(ctx->dev,
+			CAL_HL_IRQENABLE_CLR(3),
+			CAL_HL_IRQ_CLEAR,
+			CAL_HL_IRQ_MASK(ctx->csi2_port));
+	/* Todo: Add VC_IRQ and CSI2_COMPLEXIO_IRQ handling */
+	reg_write(ctx->dev, CAL_CSI2_VC_IRQENABLE(1), 0);
+}
+
+static void csi2_init(struct cal_ctx *ctx)
+{
+	int i;
+	u32 val;
+
+	val = reg_read(ctx->dev, CAL_CSI2_TIMING(ctx->csi2_port));
+	set_field(&val, CAL_GEN_ENABLE,
+		  CAL_CSI2_TIMING_FORCE_RX_MODE_IO1_MASK);
+	set_field(&val, CAL_GEN_ENABLE,
+		  CAL_CSI2_TIMING_STOP_STATE_X16_IO1_MASK);
+	set_field(&val, CAL_GEN_DISABLE,
+		  CAL_CSI2_TIMING_STOP_STATE_X4_IO1_MASK);
+	set_field(&val, 407, CAL_CSI2_TIMING_STOP_STATE_COUNTER_IO1_MASK);
+	reg_write(ctx->dev, CAL_CSI2_TIMING(ctx->csi2_port), val);
+	ctx_dbg(3, ctx, "CAL_CSI2_TIMING(%d) = 0x%08x\n", ctx->csi2_port,
+		reg_read(ctx->dev, CAL_CSI2_TIMING(ctx->csi2_port)));
+
+	val = reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port));
+	set_field(&val, CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL_OPERATIONAL,
+		  CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL_MASK);
+	set_field(&val, CAL_CSI2_COMPLEXIO_CFG_PWR_CMD_STATE_ON,
+		  CAL_CSI2_COMPLEXIO_CFG_PWR_CMD_MASK);
+	reg_write(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port), val);
+	for (i = 0; i < 10; i++) {
+		if (reg_read_field(ctx->dev,
+				   CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port),
+				   CAL_CSI2_COMPLEXIO_CFG_PWR_STATUS_MASK) ==
+		    CAL_CSI2_COMPLEXIO_CFG_PWR_STATUS_STATE_ON)
+			break;
+		usleep_range(1000, 1100);
+	}
+	ctx_dbg(3, ctx, "CAL_CSI2_COMPLEXIO_CFG(%d) = 0x%08x\n", ctx->csi2_port,
+		reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port)));
+
+	val = reg_read(ctx->dev, CAL_CTRL);
+	set_field(&val, CAL_CTRL_BURSTSIZE_BURST128, CAL_CTRL_BURSTSIZE_MASK);
+	set_field(&val, 0xF, CAL_CTRL_TAGCNT_MASK);
+	set_field(&val, CAL_CTRL_POSTED_WRITES_NONPOSTED,
+		  CAL_CTRL_POSTED_WRITES_MASK);
+	set_field(&val, 0xFF, CAL_CTRL_MFLAGL_MASK);
+	set_field(&val, 0xFF, CAL_CTRL_MFLAGH_MASK);
+	reg_write(ctx->dev, CAL_CTRL, val);
+	ctx_dbg(3, ctx, "CAL_CTRL = 0x%08x\n", reg_read(ctx->dev, CAL_CTRL));
+}
+
+static void csi2_lane_config(struct cal_ctx *ctx)
+{
+	u32 val = reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port));
+	u32 lane_mask = CAL_CSI2_COMPLEXIO_CFG_CLOCK_POSITION_MASK;
+	u32 polarity_mask = CAL_CSI2_COMPLEXIO_CFG_CLOCK_POL_MASK;
+	struct v4l2_of_bus_mipi_csi2 *mipi_csi2 = &ctx->endpoint.bus.mipi_csi2;
+	int lane;
+
+	set_field(&val, mipi_csi2->clock_lane + 1, lane_mask);
+	set_field(&val, mipi_csi2->lane_polarities[0], polarity_mask);
+	for (lane = 0; lane < mipi_csi2->num_data_lanes; lane++) {
+		/*
+		 * Every lane are one nibble apart starting with the
+		 * clock followed by the data lanes so shift masks by 4.
+		 */
+		lane_mask <<= 4;
+		polarity_mask <<= 4;
+		set_field(&val, mipi_csi2->data_lanes[lane] + 1, lane_mask);
+		set_field(&val, mipi_csi2->lane_polarities[lane + 1],
+			  polarity_mask);
+	}
+
+	reg_write(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port), val);
+	ctx_dbg(3, ctx, "CAL_CSI2_COMPLEXIO_CFG(%d) = 0x%08x\n",
+		ctx->csi2_port, val);
+}
+
+static void csi2_ppi_enable(struct cal_ctx *ctx)
+{
+	reg_write_field(ctx->dev, CAL_CSI2_PPI_CTRL(ctx->csi2_port),
+			CAL_GEN_ENABLE, CAL_CSI2_PPI_CTRL_IF_EN_MASK);
+}
+
+static void csi2_ppi_disable(struct cal_ctx *ctx)
+{
+	reg_write_field(ctx->dev, CAL_CSI2_PPI_CTRL(ctx->csi2_port),
+			CAL_GEN_DISABLE, CAL_CSI2_PPI_CTRL_IF_EN_MASK);
+}
+
+static void csi2_ctx_config(struct cal_ctx *ctx)
+{
+	u32 val;
+
+	val = reg_read(ctx->dev, CAL_CSI2_CTX0(ctx->csi2_port));
+	set_field(&val, ctx->csi2_port, CAL_CSI2_CTX_CPORT_MASK);
+	/*
+	 * DT type: MIPI CSI-2 Specs
+	 *   0x1: All - DT filter is disabled
+	 *  0x24: RGB888 1 pixel  = 3 bytes
+	 *  0x2B: RAW10  4 pixels = 5 bytes
+	 *  0x2A: RAW8   1 pixel  = 1 byte
+	 *  0x1E: YUV422 2 pixels = 4 bytes
+	 */
+	set_field(&val, 0x1, CAL_CSI2_CTX_DT_MASK);
+	/* Virtual Channel from the CSI2 sensor usually 0! */
+	set_field(&val, ctx->virtual_channel, CAL_CSI2_CTX_VC_MASK);
+	/* NUM_LINES_PER_FRAME => 0 means auto detect */
+	set_field(&val, 0, CAL_CSI2_CTX_LINES_MASK);
+	set_field(&val, CAL_CSI2_CTX_ATT_PIX, CAL_CSI2_CTX_ATT_MASK);
+	set_field(&val, CAL_CSI2_CTX_PACK_MODE_LINE,
+		  CAL_CSI2_CTX_PACK_MODE_MASK);
+	reg_write(ctx->dev, CAL_CSI2_CTX0(ctx->csi2_port), val);
+	ctx_dbg(3, ctx, "CAL_CSI2_CTX0(%d) = 0x%08x\n", ctx->csi2_port,
+		reg_read(ctx->dev, CAL_CSI2_CTX0(ctx->csi2_port)));
+}
+
+static void pix_proc_config(struct cal_ctx *ctx)
+{
+	u32 val;
+
+	val = reg_read(ctx->dev, CAL_PIX_PROC(ctx->csi2_port));
+	set_field(&val, CAL_PIX_PROC_EXTRACT_B8, CAL_PIX_PROC_EXTRACT_MASK);
+	set_field(&val, CAL_PIX_PROC_DPCMD_BYPASS, CAL_PIX_PROC_DPCMD_MASK);
+	set_field(&val, CAL_PIX_PROC_DPCME_BYPASS, CAL_PIX_PROC_DPCME_MASK);
+	set_field(&val, CAL_PIX_PROC_PACK_B8, CAL_PIX_PROC_PACK_MASK);
+	set_field(&val, ctx->csi2_port, CAL_PIX_PROC_CPORT_MASK);
+	set_field(&val, CAL_GEN_ENABLE, CAL_PIX_PROC_EN_MASK);
+	reg_write(ctx->dev, CAL_PIX_PROC(ctx->csi2_port), val);
+	ctx_dbg(3, ctx, "CAL_PIX_PROC(%d) = 0x%08x\n", ctx->csi2_port,
+		reg_read(ctx->dev, CAL_PIX_PROC(ctx->csi2_port)));
+}
+
+static void cal_wr_dma_config(struct cal_ctx *ctx,
+			      unsigned int width)
+{
+	u32 val;
+
+	val = reg_read(ctx->dev, CAL_WR_DMA_CTRL(ctx->csi2_port));
+	set_field(&val, ctx->csi2_port, CAL_WR_DMA_CTRL_CPORT_MASK);
+	set_field(&val, CAL_WR_DMA_CTRL_DTAG_PIX_DAT,
+		  CAL_WR_DMA_CTRL_DTAG_MASK);
+	set_field(&val, CAL_WR_DMA_CTRL_MODE_CONST,
+		  CAL_WR_DMA_CTRL_MODE_MASK);
+	set_field(&val, CAL_WR_DMA_CTRL_PATTERN_LINEAR,
+		  CAL_WR_DMA_CTRL_PATTERN_MASK);
+	set_field(&val, CAL_GEN_ENABLE, CAL_WR_DMA_CTRL_STALL_RD_MASK);
+	reg_write(ctx->dev, CAL_WR_DMA_CTRL(ctx->csi2_port), val);
+	ctx_dbg(3, ctx, "CAL_WR_DMA_CTRL(%d) = 0x%08x\n", ctx->csi2_port,
+		reg_read(ctx->dev, CAL_WR_DMA_CTRL(ctx->csi2_port)));
+
+	/*
+	 * width/16 not sure but giving it a whirl.
+	 * zero does not work right
+	 */
+	reg_write_field(ctx->dev,
+			CAL_WR_DMA_OFST(ctx->csi2_port),
+			(width / 16),
+			CAL_WR_DMA_OFST_MASK);
+	ctx_dbg(3, ctx, "CAL_WR_DMA_OFST(%d) = 0x%08x\n", ctx->csi2_port,
+		reg_read(ctx->dev, CAL_WR_DMA_OFST(ctx->csi2_port)));
+
+	val = reg_read(ctx->dev, CAL_WR_DMA_XSIZE(ctx->csi2_port));
+	/* 64 bit word means no skipping */
+	set_field(&val, 0, CAL_WR_DMA_XSIZE_XSKIP_MASK);
+	/*
+	 * (width*8)/64 this should be size of an entire line
+	 * in 64bit word but 0 means all data until the end
+	 * is detected automagically
+	 */
+	set_field(&val, (width / 8), CAL_WR_DMA_XSIZE_MASK);
+	reg_write(ctx->dev, CAL_WR_DMA_XSIZE(ctx->csi2_port), val);
+	ctx_dbg(3, ctx, "CAL_WR_DMA_XSIZE(%d) = 0x%08x\n", ctx->csi2_port,
+		reg_read(ctx->dev, CAL_WR_DMA_XSIZE(ctx->csi2_port)));
+}
+
+static void cal_wr_dma_addr(struct cal_ctx *ctx, unsigned int dmaaddr)
+{
+	reg_write(ctx->dev, CAL_WR_DMA_ADDR(ctx->csi2_port), dmaaddr);
+}
+
+/*
+ * TCLK values are OK at their reset values
+ */
+#define TCLK_TERM	0
+#define TCLK_MISS	1
+#define TCLK_SETTLE	14
+#define THS_SETTLE	15
+
+static void csi2_phy_config(struct cal_ctx *ctx)
+{
+	unsigned int reg0, reg1;
+	unsigned int ths_term, ths_settle;
+	unsigned int ddrclkperiod_us;
+
+	/*
+	 * THS_TERM: Programmed value = floor(20 ns/DDRClk period) - 2.
+	 */
+	ddrclkperiod_us = ctx->external_rate / 2000000;
+	ddrclkperiod_us = 1000000 / ddrclkperiod_us;
+	ctx_dbg(1, ctx, "ddrclkperiod_us: %d\n", ddrclkperiod_us);
+
+	ths_term = 20000 / ddrclkperiod_us;
+	ths_term = (ths_term >= 2) ? ths_term - 2 : ths_term;
+	ctx_dbg(1, ctx, "ths_term: %d (0x%02x)\n", ths_term, ths_term);
+
+	/*
+	 * THS_SETTLE: Programmed value = floor(176.3 ns/CtrlClk period) - 1.
+	 *	Since CtrlClk is fixed at 96Mhz then we get
+	 *	ths_settle = floor(176.3 / 10.416) - 1 = 15
+	 * If we ever switch to a dynamic clock then this code might be useful
+	 *
+	 * unsigned int ctrlclkperiod_us;
+	 * ctrlclkperiod_us = 96000000 / 1000000;
+	 * ctrlclkperiod_us = 1000000 / ctrlclkperiod_us;
+	 * ctx_dbg(1, ctx, "ctrlclkperiod_us: %d\n", ctrlclkperiod_us);
+
+	 * ths_settle = 176300  / ctrlclkperiod_us;
+	 * ths_settle = (ths_settle > 1) ? ths_settle - 1 : ths_settle;
+	 */
+
+	ths_settle = THS_SETTLE;
+	ctx_dbg(1, ctx, "ths_settle: %d (0x%02x)\n", ths_settle, ths_settle);
+
+	reg0 = reg_read(ctx->cc, CAL_CSI2_PHY_REG0);
+	set_field(&reg0, CAL_CSI2_PHY_REG0_HSCLOCKCONFIG_DISABLE,
+		  CAL_CSI2_PHY_REG0_HSCLOCKCONFIG_MASK);
+	set_field(&reg0, ths_term, CAL_CSI2_PHY_REG0_THS_TERM_MASK);
+	set_field(&reg0, ths_settle, CAL_CSI2_PHY_REG0_THS_SETTLE_MASK);
+
+	ctx_dbg(1, ctx, "CSI2_%d_REG0 = 0x%08x\n", (ctx->csi2_port - 1), reg0);
+	reg_write(ctx->cc, CAL_CSI2_PHY_REG0, reg0);
+
+	reg1 = reg_read(ctx->cc, CAL_CSI2_PHY_REG1);
+	set_field(&reg1, TCLK_TERM, CAL_CSI2_PHY_REG1_TCLK_TERM_MASK);
+	set_field(&reg1, 0xb8, CAL_CSI2_PHY_REG1_DPHY_HS_SYNC_PATTERN_MASK);
+	set_field(&reg1, TCLK_MISS, CAL_CSI2_PHY_REG1_CTRLCLK_DIV_FACTOR_MASK);
+	set_field(&reg1, TCLK_SETTLE, CAL_CSI2_PHY_REG1_TCLK_SETTLE_MASK);
+
+	ctx_dbg(1, ctx, "CSI2_%d_REG1 = 0x%08x\n", (ctx->csi2_port - 1), reg1);
+	reg_write(ctx->cc, CAL_CSI2_PHY_REG1, reg1);
+}
+
+static int cal_get_external_info(struct cal_ctx *ctx)
+{
+	struct v4l2_ctrl *ctrl;
+
+	if (!ctx->sensor)
+		return -ENODEV;
+
+	ctrl = v4l2_ctrl_find(ctx->sensor->ctrl_handler, V4L2_CID_PIXEL_RATE);
+	if (!ctrl) {
+		ctx_err(ctx, "no pixel rate control in subdev: %s\n",
+			ctx->sensor->name);
+		return -EPIPE;
+	}
+
+	ctx->external_rate = v4l2_ctrl_g_ctrl_int64(ctrl);
+	ctx_dbg(3, ctx, "sensor Pixel Rate: %d\n", ctx->external_rate);
+
+	return 0;
+}
+
+static inline void cal_schedule_next_buffer(struct cal_ctx *ctx)
+{
+	struct cal_dmaqueue *dma_q = &ctx->vidq;
+	struct cal_buffer *buf;
+	unsigned long addr;
+
+	buf = list_entry(dma_q->active.next, struct cal_buffer, list);
+	ctx->next_frm = buf;
+	list_del(&buf->list);
+
+	addr = vb2_dma_contig_plane_dma_addr(&buf->vb.vb2_buf, 0);
+	cal_wr_dma_addr(ctx, addr);
+}
+
+static inline void cal_process_buffer_complete(struct cal_ctx *ctx)
+{
+	ctx->cur_frm->vb.vb2_buf.timestamp = ktime_get_ns();
+	ctx->cur_frm->vb.field = ctx->m_fmt.field;
+	ctx->cur_frm->vb.sequence = ctx->sequence++;
+
+	vb2_buffer_done(&ctx->cur_frm->vb.vb2_buf, VB2_BUF_STATE_DONE);
+	ctx->cur_frm = ctx->next_frm;
+}
+
+#define isvcirqset(irq, vc, ff) (irq & \
+	(CAL_CSI2_VC_IRQENABLE_ ##ff ##_IRQ_##vc ##_MASK))
+
+#define isportirqset(irq, port) (irq & CAL_HL_IRQ_MASK(port))
+
+static irqreturn_t cal_irq(int irq_cal, void *data)
+{
+	struct cal_dev *dev = (struct cal_dev *)data;
+	struct cal_ctx *ctx;
+	struct cal_dmaqueue *dma_q;
+	u32 irqst2, irqst3;
+
+	/* Check which DMA just finished */
+	irqst2 = reg_read(dev, CAL_HL_IRQSTATUS(2));
+	if (irqst2) {
+		/* Clear Interrupt status */
+		reg_write(dev, CAL_HL_IRQSTATUS(2), irqst2);
+
+		/* Need to check both port */
+		if (isportirqset(irqst2, 1)) {
+			ctx = dev->ctx[0];
+
+			if (ctx->cur_frm != ctx->next_frm)
+				cal_process_buffer_complete(ctx);
+		}
+
+		if (isportirqset(irqst2, 2)) {
+			ctx = dev->ctx[1];
+
+			if (ctx->cur_frm != ctx->next_frm)
+				cal_process_buffer_complete(ctx);
+		}
+	}
+
+	/* Check which DMA just started */
+	irqst3 = reg_read(dev, CAL_HL_IRQSTATUS(3));
+	if (irqst3) {
+		/* Clear Interrupt status */
+		reg_write(dev, CAL_HL_IRQSTATUS(3), irqst3);
+
+		/* Need to check both port */
+		if (isportirqset(irqst3, 1)) {
+			ctx = dev->ctx[0];
+			dma_q = &ctx->vidq;
+
+			spin_lock(&ctx->slock);
+			if (!list_empty(&dma_q->active) &&
+			    ctx->cur_frm == ctx->next_frm)
+				cal_schedule_next_buffer(ctx);
+			spin_unlock(&ctx->slock);
+		}
+
+		if (isportirqset(irqst3, 2)) {
+			ctx = dev->ctx[1];
+			dma_q = &ctx->vidq;
+
+			spin_lock(&ctx->slock);
+			if (!list_empty(&dma_q->active) &&
+			    ctx->cur_frm == ctx->next_frm)
+				cal_schedule_next_buffer(ctx);
+			spin_unlock(&ctx->slock);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * video ioctls
+ */
+static int cal_querycap(struct file *file, void *priv,
+			struct v4l2_capability *cap)
+{
+	struct cal_ctx *ctx = video_drvdata(file);
+
+	strlcpy(cap->driver, CAL_MODULE_NAME, sizeof(cap->driver));
+	strlcpy(cap->card, CAL_MODULE_NAME, sizeof(cap->card));
+
+	snprintf(cap->bus_info, sizeof(cap->bus_info),
+		 "platform:%s", ctx->v4l2_dev.name);
+	cap->device_caps = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_STREAMING |
+			    V4L2_CAP_READWRITE;
+	cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS;
+	return 0;
+}
+
+static int cal_enum_fmt_vid_cap(struct file *file, void  *priv,
+				struct v4l2_fmtdesc *f)
+{
+	struct cal_ctx *ctx = video_drvdata(file);
+	const struct cal_fmt *fmt = NULL;
+
+	if (f->index >= ctx->num_active_fmt)
+		return -EINVAL;
+
+	fmt = ctx->active_fmt[f->index];
+
+	f->pixelformat = fmt->fourcc;
+	f->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	return 0;
+}
+
+static int __subdev_get_format(struct cal_ctx *ctx,
+			       struct v4l2_mbus_framefmt *fmt)
+{
+	struct v4l2_subdev_format sd_fmt;
+	struct v4l2_mbus_framefmt *mbus_fmt = &sd_fmt.format;
+	int ret;
+
+	sd_fmt.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+	sd_fmt.pad = 0;
+
+	ret = v4l2_subdev_call(ctx->sensor, pad, get_fmt, NULL, &sd_fmt);
+	if (ret)
+		return ret;
+
+	*fmt = *mbus_fmt;
+
+	ctx_dbg(1, ctx, "%s %dx%d code:%04X\n", __func__,
+		fmt->width, fmt->height, fmt->code);
+
+	return 0;
+}
+
+static int __subdev_set_format(struct cal_ctx *ctx,
+			       struct v4l2_mbus_framefmt *fmt)
+{
+	struct v4l2_subdev_format sd_fmt;
+	struct v4l2_mbus_framefmt *mbus_fmt = &sd_fmt.format;
+	int ret;
+
+	sd_fmt.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+	sd_fmt.pad = 0;
+	*mbus_fmt = *fmt;
+
+	ret = v4l2_subdev_call(ctx->sensor, pad, set_fmt, NULL, &sd_fmt);
+	if (ret)
+		return ret;
+
+	ctx_dbg(1, ctx, "%s %dx%d code:%04X\n", __func__,
+		fmt->width, fmt->height, fmt->code);
+
+	return 0;
+}
+
+static int cal_calc_format_size(struct cal_ctx *ctx,
+				const struct cal_fmt *fmt,
+				struct v4l2_format *f)
+{
+	if (!fmt) {
+		ctx_dbg(3, ctx, "No cal_fmt provided!\n");
+		return -EINVAL;
+	}
+
+	v4l_bound_align_image(&f->fmt.pix.width, 48, MAX_WIDTH, 2,
+			      &f->fmt.pix.height, 32, MAX_HEIGHT, 0, 0);
+	f->fmt.pix.bytesperline = bytes_per_line(f->fmt.pix.width,
+						 fmt->depth >> 3);
+	f->fmt.pix.sizeimage = f->fmt.pix.height *
+			       f->fmt.pix.bytesperline;
+
+	ctx_dbg(3, ctx, "%s: fourcc: %s size: %dx%d bpl:%d img_size:%d\n",
+		__func__, fourcc_to_str(f->fmt.pix.pixelformat),
+		f->fmt.pix.width, f->fmt.pix.height,
+		f->fmt.pix.bytesperline, f->fmt.pix.sizeimage);
+
+	return 0;
+}
+
+static int cal_g_fmt_vid_cap(struct file *file, void *priv,
+			     struct v4l2_format *f)
+{
+	struct cal_ctx *ctx = video_drvdata(file);
+
+	*f = ctx->v_fmt;
+
+	return 0;
+}
+
+static int cal_try_fmt_vid_cap(struct file *file, void *priv,
+			       struct v4l2_format *f)
+{
+	struct cal_ctx *ctx = video_drvdata(file);
+	const struct cal_fmt *fmt;
+	struct v4l2_subdev_frame_size_enum fse;
+	int ret, found;
+
+	fmt = find_format_by_pix(ctx, f->fmt.pix.pixelformat);
+	if (!fmt) {
+		ctx_dbg(3, ctx, "Fourcc format (0x%08x) not found.\n",
+			f->fmt.pix.pixelformat);
+
+		/* Just get the first one enumerated */
+		fmt = ctx->active_fmt[0];
+		f->fmt.pix.pixelformat = fmt->fourcc;
+	}
+
+	f->fmt.pix.field = ctx->v_fmt.fmt.pix.field;
+
+	/* check for/find a valid width/height */
+	ret = 0;
+	found = false;
+	fse.pad = 0;
+	fse.code = fmt->code;
+	fse.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+	for (fse.index = 0; ; fse.index++) {
+		ret = v4l2_subdev_call(ctx->sensor, pad, enum_frame_size,
+				       NULL, &fse);
+		if (ret)
+			break;
+
+		if ((f->fmt.pix.width == fse.max_width) &&
+		    (f->fmt.pix.height == fse.max_height)) {
+			found = true;
+			break;
+		} else if ((f->fmt.pix.width >= fse.min_width) &&
+			 (f->fmt.pix.width <= fse.max_width) &&
+			 (f->fmt.pix.height >= fse.min_height) &&
+			 (f->fmt.pix.height <= fse.max_height)) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		/* use existing values as default */
+		f->fmt.pix.width = ctx->v_fmt.fmt.pix.width;
+		f->fmt.pix.height =  ctx->v_fmt.fmt.pix.height;
+	}
+
+	/*
+	 * Use current colorspace for now, it will get
+	 * updated properly during s_fmt
+	 */
+	f->fmt.pix.colorspace = ctx->v_fmt.fmt.pix.colorspace;
+	return cal_calc_format_size(ctx, fmt, f);
+}
+
+static int cal_s_fmt_vid_cap(struct file *file, void *priv,
+			     struct v4l2_format *f)
+{
+	struct cal_ctx *ctx = video_drvdata(file);
+	struct vb2_queue *q = &ctx->vb_vidq;
+	const struct cal_fmt *fmt;
+	struct v4l2_mbus_framefmt mbus_fmt;
+	int ret;
+
+	if (vb2_is_busy(q)) {
+		ctx_dbg(3, ctx, "%s device busy\n", __func__);
+		return -EBUSY;
+	}
+
+	ret = cal_try_fmt_vid_cap(file, priv, f);
+	if (ret < 0)
+		return ret;
+
+	fmt = find_format_by_pix(ctx, f->fmt.pix.pixelformat);
+
+	v4l2_fill_mbus_format(&mbus_fmt, &f->fmt.pix, fmt->code);
+
+	ret = __subdev_set_format(ctx, &mbus_fmt);
+	if (ret)
+		return ret;
+
+	/* Just double check nothing has gone wrong */
+	if (mbus_fmt.code != fmt->code) {
+		ctx_dbg(3, ctx,
+			"%s subdev changed format on us, this should not happen\n",
+			__func__);
+		return -EINVAL;
+	}
+
+	v4l2_fill_pix_format(&ctx->v_fmt.fmt.pix, &mbus_fmt);
+	ctx->v_fmt.type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	ctx->v_fmt.fmt.pix.pixelformat  = fmt->fourcc;
+	cal_calc_format_size(ctx, fmt, &ctx->v_fmt);
+	ctx->fmt = fmt;
+	ctx->m_fmt = mbus_fmt;
+	*f = ctx->v_fmt;
+
+	return 0;
+}
+
+static int cal_enum_framesizes(struct file *file, void *fh,
+			       struct v4l2_frmsizeenum *fsize)
+{
+	struct cal_ctx *ctx = video_drvdata(file);
+	const struct cal_fmt *fmt;
+	struct v4l2_subdev_frame_size_enum fse;
+	int ret;
+
+	/* check for valid format */
+	fmt = find_format_by_pix(ctx, fsize->pixel_format);
+	if (!fmt) {
+		ctx_dbg(3, ctx, "Invalid pixel code: %x\n",
+			fsize->pixel_format);
+		return -EINVAL;
+	}
+
+	fse.index = fsize->index;
+	fse.pad = 0;
+	fse.code = fmt->code;
+
+	ret = v4l2_subdev_call(ctx->sensor, pad, enum_frame_size, NULL, &fse);
+	if (ret)
+		return ret;
+
+	ctx_dbg(1, ctx, "%s: index: %d code: %x W:[%d,%d] H:[%d,%d]\n",
+		__func__, fse.index, fse.code, fse.min_width, fse.max_width,
+		fse.min_height, fse.max_height);
+
+	fsize->type = V4L2_FRMSIZE_TYPE_DISCRETE;
+	fsize->discrete.width = fse.max_width;
+	fsize->discrete.height = fse.max_height;
+
+	return 0;
+}
+
+static int cal_enum_input(struct file *file, void *priv,
+			  struct v4l2_input *inp)
+{
+	if (inp->index >= CAL_NUM_INPUT)
+		return -EINVAL;
+
+	inp->type = V4L2_INPUT_TYPE_CAMERA;
+	sprintf(inp->name, "Camera %u", inp->index);
+	return 0;
+}
+
+static int cal_g_input(struct file *file, void *priv, unsigned int *i)
+{
+	struct cal_ctx *ctx = video_drvdata(file);
+
+	*i = ctx->input;
+	return 0;
+}
+
+static int cal_s_input(struct file *file, void *priv, unsigned int i)
+{
+	struct cal_ctx *ctx = video_drvdata(file);
+
+	if (i >= CAL_NUM_INPUT)
+		return -EINVAL;
+
+	ctx->input = i;
+	return 0;
+}
+
+/* timeperframe is arbitrary and continuous */
+static int cal_enum_frameintervals(struct file *file, void *priv,
+				   struct v4l2_frmivalenum *fival)
+{
+	struct cal_ctx *ctx = video_drvdata(file);
+	const struct cal_fmt *fmt;
+	struct v4l2_subdev_frame_interval_enum fie = {
+		.index = fival->index,
+		.width = fival->width,
+		.height = fival->height,
+		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
+	};
+	int ret;
+
+	fmt = find_format_by_pix(ctx, fival->pixel_format);
+	if (!fmt)
+		return -EINVAL;
+
+	fie.code = fmt->code;
+	ret = v4l2_subdev_call(ctx->sensor, pad, enum_frame_interval,
+			       NULL, &fie);
+	if (ret)
+		return ret;
+	fival->type = V4L2_FRMIVAL_TYPE_DISCRETE;
+	fival->discrete = fie.interval;
+
+	return 0;
+}
+
+/*
+ * Videobuf operations
+ */
+static int cal_queue_setup(struct vb2_queue *vq,
+			   unsigned int *nbuffers, unsigned int *nplanes,
+			   unsigned int sizes[], void *alloc_ctxs[])
+{
+	struct cal_ctx *ctx = vb2_get_drv_priv(vq);
+	unsigned size = ctx->v_fmt.fmt.pix.sizeimage;
+
+	if (vq->num_buffers + *nbuffers < 3)
+		*nbuffers = 3 - vq->num_buffers;
+	alloc_ctxs[0] = ctx->alloc_ctx;
+
+	if (*nplanes) {
+		if (sizes[0] < size)
+			return -EINVAL;
+		size = sizes[0];
+	}
+
+	*nplanes = 1;
+	sizes[0] = size;
+
+	ctx_dbg(3, ctx, "nbuffers=%d, size=%d\n", *nbuffers, sizes[0]);
+
+	return 0;
+}
+
+static int cal_buffer_prepare(struct vb2_buffer *vb)
+{
+	struct cal_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+	struct cal_buffer *buf = container_of(vb, struct cal_buffer,
+					      vb.vb2_buf);
+	unsigned long size;
+
+	if (WARN_ON(!ctx->fmt))
+		return -EINVAL;
+
+	size = ctx->v_fmt.fmt.pix.sizeimage;
+	if (vb2_plane_size(vb, 0) < size) {
+		ctx_err(ctx,
+			"data will not fit into plane (%lu < %lu)\n",
+			vb2_plane_size(vb, 0), size);
+		return -EINVAL;
+	}
+
+	vb2_set_plane_payload(&buf->vb.vb2_buf, 0, size);
+	return 0;
+}
+
+static void cal_buffer_queue(struct vb2_buffer *vb)
+{
+	struct cal_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+	struct cal_buffer *buf = container_of(vb, struct cal_buffer,
+					      vb.vb2_buf);
+	struct cal_dmaqueue *vidq = &ctx->vidq;
+	unsigned long flags = 0;
+
+	/* recheck locking */
+	spin_lock_irqsave(&ctx->slock, flags);
+	list_add_tail(&buf->list, &vidq->active);
+	spin_unlock_irqrestore(&ctx->slock, flags);
+}
+
+static int cal_start_streaming(struct vb2_queue *vq, unsigned int count)
+{
+	struct cal_ctx *ctx = vb2_get_drv_priv(vq);
+	struct cal_dmaqueue *dma_q = &ctx->vidq;
+	struct cal_buffer *buf, *tmp;
+	unsigned long addr = 0;
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&ctx->slock, flags);
+	if (list_empty(&dma_q->active)) {
+		spin_unlock_irqrestore(&ctx->slock, flags);
+		ctx_dbg(3, ctx, "buffer queue is empty\n");
+		return -EIO;
+	}
+
+	buf = list_entry(dma_q->active.next, struct cal_buffer, list);
+	ctx->cur_frm = buf;
+	ctx->next_frm = buf;
+	list_del(&buf->list);
+	spin_unlock_irqrestore(&ctx->slock, flags);
+
+	addr = vb2_dma_contig_plane_dma_addr(&ctx->cur_frm->vb.vb2_buf, 0);
+	ctx->sequence = 0;
+
+	ret = cal_get_external_info(ctx);
+	if (ret < 0)
+		goto err;
+
+	cal_runtime_get(ctx->dev);
+
+	enable_irqs(ctx);
+	camerarx_phy_enable(ctx);
+	csi2_init(ctx);
+	csi2_phy_config(ctx);
+	csi2_lane_config(ctx);
+	csi2_ctx_config(ctx);
+	pix_proc_config(ctx);
+	cal_wr_dma_config(ctx, ctx->v_fmt.fmt.pix.bytesperline);
+	cal_wr_dma_addr(ctx, addr);
+	csi2_ppi_enable(ctx);
+
+	ret = v4l2_subdev_call(ctx->sensor, video, s_stream, 1);
+	if (ret) {
+		ctx_err(ctx, "stream on failed in subdev\n");
+		cal_runtime_put(ctx->dev);
+		goto err;
+	}
+
+	if (debug >= 4)
+		cal_quickdump_regs(ctx->dev);
+
+	return 0;
+
+err:
+	list_for_each_entry_safe(buf, tmp, &dma_q->active, list) {
+		list_del(&buf->list);
+		vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED);
+	}
+	return ret;
+}
+
+static void cal_stop_streaming(struct vb2_queue *vq)
+{
+	struct cal_ctx *ctx = vb2_get_drv_priv(vq);
+	struct cal_dmaqueue *dma_q = &ctx->vidq;
+	struct cal_buffer *buf, *tmp;
+	unsigned long flags;
+
+	if (v4l2_subdev_call(ctx->sensor, video, s_stream, 0))
+		ctx_err(ctx, "stream off failed in subdev\n");
+
+	csi2_ppi_disable(ctx);
+	disable_irqs(ctx);
+
+	/* Release all active buffers */
+	spin_lock_irqsave(&ctx->slock, flags);
+	list_for_each_entry_safe(buf, tmp, &dma_q->active, list) {
+		list_del(&buf->list);
+		vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR);
+	}
+
+	if (ctx->cur_frm == ctx->next_frm) {
+		vb2_buffer_done(&ctx->cur_frm->vb.vb2_buf, VB2_BUF_STATE_ERROR);
+	} else {
+		vb2_buffer_done(&ctx->cur_frm->vb.vb2_buf, VB2_BUF_STATE_ERROR);
+		vb2_buffer_done(&ctx->next_frm->vb.vb2_buf,
+				VB2_BUF_STATE_ERROR);
+	}
+	ctx->cur_frm = NULL;
+	ctx->next_frm = NULL;
+	spin_unlock_irqrestore(&ctx->slock, flags);
+
+	cal_runtime_put(ctx->dev);
+}
+
+static struct vb2_ops cal_video_qops = {
+	.queue_setup		= cal_queue_setup,
+	.buf_prepare		= cal_buffer_prepare,
+	.buf_queue		= cal_buffer_queue,
+	.start_streaming	= cal_start_streaming,
+	.stop_streaming		= cal_stop_streaming,
+	.wait_prepare		= vb2_ops_wait_prepare,
+	.wait_finish		= vb2_ops_wait_finish,
+};
+
+static const struct v4l2_file_operations cal_fops = {
+	.owner		= THIS_MODULE,
+	.open           = v4l2_fh_open,
+	.release        = vb2_fop_release,
+	.read           = vb2_fop_read,
+	.poll		= vb2_fop_poll,
+	.unlocked_ioctl = video_ioctl2, /* V4L2 ioctl handler */
+	.mmap           = vb2_fop_mmap,
+};
+
+static const struct v4l2_ioctl_ops cal_ioctl_ops = {
+	.vidioc_querycap      = cal_querycap,
+	.vidioc_enum_fmt_vid_cap  = cal_enum_fmt_vid_cap,
+	.vidioc_g_fmt_vid_cap     = cal_g_fmt_vid_cap,
+	.vidioc_try_fmt_vid_cap   = cal_try_fmt_vid_cap,
+	.vidioc_s_fmt_vid_cap     = cal_s_fmt_vid_cap,
+	.vidioc_enum_framesizes   = cal_enum_framesizes,
+	.vidioc_reqbufs       = vb2_ioctl_reqbufs,
+	.vidioc_create_bufs   = vb2_ioctl_create_bufs,
+	.vidioc_prepare_buf   = vb2_ioctl_prepare_buf,
+	.vidioc_querybuf      = vb2_ioctl_querybuf,
+	.vidioc_qbuf          = vb2_ioctl_qbuf,
+	.vidioc_dqbuf         = vb2_ioctl_dqbuf,
+	.vidioc_enum_input    = cal_enum_input,
+	.vidioc_g_input       = cal_g_input,
+	.vidioc_s_input       = cal_s_input,
+	.vidioc_enum_frameintervals = cal_enum_frameintervals,
+	.vidioc_streamon      = vb2_ioctl_streamon,
+	.vidioc_streamoff     = vb2_ioctl_streamoff,
+	.vidioc_log_status    = v4l2_ctrl_log_status,
+	.vidioc_subscribe_event = v4l2_ctrl_subscribe_event,
+	.vidioc_unsubscribe_event = v4l2_event_unsubscribe,
+};
+
+static struct video_device cal_videodev = {
+	.name		= CAL_MODULE_NAME,
+	.fops		= &cal_fops,
+	.ioctl_ops	= &cal_ioctl_ops,
+	.minor		= -1,
+	.release	= video_device_release_empty,
+};
+
+/* -----------------------------------------------------------------
+ *	Initialization and module stuff
+ * ------------------------------------------------------------------
+ */
+static int cal_complete_ctx(struct cal_ctx *ctx);
+
+static int cal_async_bound(struct v4l2_async_notifier *notifier,
+			   struct v4l2_subdev *subdev,
+			   struct v4l2_async_subdev *asd)
+{
+	struct cal_ctx *ctx = notifier_to_ctx(notifier);
+	struct v4l2_subdev_mbus_code_enum mbus_code;
+	int ret = 0;
+	int i, j, k;
+
+	if (ctx->sensor) {
+		ctx_info(ctx, "Rejecting subdev %s (Already set!!)",
+			 subdev->name);
+		return 0;
+	}
+
+	ctx->sensor = subdev;
+	ctx_dbg(1, ctx, "Using sensor %s for capture\n", subdev->name);
+
+	/* Enumerate sub device formats and enable all matching local formats */
+	ctx->num_active_fmt = 0;
+	for (j = 0, i = 0; ret != -EINVAL; ++j) {
+		struct cal_fmt *fmt;
+
+		memset(&mbus_code, 0, sizeof(mbus_code));
+		mbus_code.index = j;
+		ret = v4l2_subdev_call(subdev, pad, enum_mbus_code,
+				       NULL, &mbus_code);
+		if (ret)
+			continue;
+
+		ctx_dbg(2, ctx,
+			"subdev %s: code: %04x idx: %d\n",
+			subdev->name, mbus_code.code, j);
+
+		for (k = 0; k < ARRAY_SIZE(cal_formats); k++) {
+			fmt = &cal_formats[k];
+
+			if (mbus_code.code == fmt->code) {
+				ctx->active_fmt[i] = fmt;
+				ctx_dbg(2, ctx,
+					"matched fourcc: %s: code: %04x idx: %d\n",
+					fourcc_to_str(fmt->fourcc),
+					fmt->code, i);
+				ctx->num_active_fmt = ++i;
+			}
+		}
+	}
+
+	if (i == 0) {
+		ctx_err(ctx, "No suitable format reported by subdev %s\n",
+			subdev->name);
+		return -EINVAL;
+	}
+
+	cal_complete_ctx(ctx);
+
+	return 0;
+}
+
+static int cal_async_complete(struct v4l2_async_notifier *notifier)
+{
+	struct cal_ctx *ctx = notifier_to_ctx(notifier);
+	const struct cal_fmt *fmt;
+	struct v4l2_mbus_framefmt mbus_fmt;
+	int ret;
+
+	ret = __subdev_get_format(ctx, &mbus_fmt);
+	if (ret)
+		return ret;
+
+	fmt = find_format_by_code(ctx, mbus_fmt.code);
+	if (!fmt) {
+		ctx_dbg(3, ctx, "mbus code format (0x%08x) not found.\n",
+			mbus_fmt.code);
+		return -EINVAL;
+	}
+
+	/* Save current subdev format */
+	v4l2_fill_pix_format(&ctx->v_fmt.fmt.pix, &mbus_fmt);
+	ctx->v_fmt.type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	ctx->v_fmt.fmt.pix.pixelformat  = fmt->fourcc;
+	cal_calc_format_size(ctx, fmt, &ctx->v_fmt);
+	ctx->fmt = fmt;
+	ctx->m_fmt = mbus_fmt;
+
+	return 0;
+}
+
+static int cal_complete_ctx(struct cal_ctx *ctx)
+{
+	struct video_device *vfd;
+	struct vb2_queue *q;
+	int ret;
+
+	ctx->timeperframe = tpf_default;
+	ctx->external_rate = 192000000;
+
+	/* initialize locks */
+	spin_lock_init(&ctx->slock);
+	mutex_init(&ctx->mutex);
+
+	/* initialize queue */
+	q = &ctx->vb_vidq;
+	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	q->io_modes = VB2_MMAP | VB2_DMABUF | VB2_READ;
+	q->drv_priv = ctx;
+	q->buf_struct_size = sizeof(struct cal_buffer);
+	q->ops = &cal_video_qops;
+	q->mem_ops = &vb2_dma_contig_memops;
+	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	q->lock = &ctx->mutex;
+	q->min_buffers_needed = 3;
+
+	ret = vb2_queue_init(q);
+	if (ret)
+		return ret;
+
+	/* init video dma queues */
+	INIT_LIST_HEAD(&ctx->vidq.active);
+
+	vfd = &ctx->vdev;
+	*vfd = cal_videodev;
+	vfd->v4l2_dev = &ctx->v4l2_dev;
+	vfd->queue = q;
+
+	/*
+	 * Provide a mutex to v4l2 core. It will be used to protect
+	 * all fops and v4l2 ioctls.
+	 */
+	vfd->lock = &ctx->mutex;
+	video_set_drvdata(vfd, ctx);
+
+	ret = video_register_device(vfd, VFL_TYPE_GRABBER, video_nr);
+	if (ret < 0)
+		return ret;
+
+	v4l2_info(&ctx->v4l2_dev, "V4L2 device registered as %s\n",
+		  video_device_node_name(vfd));
+
+	ctx->alloc_ctx = vb2_dma_contig_init_ctx(vfd->v4l2_dev->dev);
+	if (IS_ERR(ctx->alloc_ctx)) {
+		ctx_err(ctx, "Failed to alloc vb2 context\n");
+		ret = PTR_ERR(ctx->alloc_ctx);
+		goto vdev_unreg;
+	}
+
+	return 0;
+
+vdev_unreg:
+	video_unregister_device(vfd);
+	return ret;
+}
+
+static struct device_node *
+of_get_next_port(const struct device_node *parent,
+		 struct device_node *prev)
+{
+	struct device_node *port = NULL;
+
+	if (!parent)
+		return NULL;
+
+	if (!prev) {
+		struct device_node *ports;
+		/*
+		 * It's the first call, we have to find a port subnode
+		 * within this node or within an optional 'ports' node.
+		 */
+		ports = of_get_child_by_name(parent, "ports");
+		if (ports)
+			parent = ports;
+
+		port = of_get_child_by_name(parent, "port");
+
+		/* release the 'ports' node */
+		of_node_put(ports);
+	} else {
+		struct device_node *ports;
+
+		ports = of_get_parent(prev);
+		if (!ports)
+			return NULL;
+
+		do {
+			port = of_get_next_child(ports, prev);
+			if (!port) {
+				of_node_put(ports);
+				return NULL;
+			}
+			prev = port;
+		} while (of_node_cmp(port->name, "port") != 0);
+	}
+
+	return port;
+}
+
+static struct device_node *
+of_get_next_endpoint(const struct device_node *parent,
+		     struct device_node *prev)
+{
+	struct device_node *ep = NULL;
+
+	if (!parent)
+		return NULL;
+
+	do {
+		ep = of_get_next_child(parent, prev);
+		if (!ep)
+			return NULL;
+		prev = ep;
+	} while (of_node_cmp(ep->name, "endpoint") != 0);
+
+	return ep;
+}
+
+static int of_cal_create_instance(struct cal_ctx *ctx, int inst)
+{
+	struct platform_device *pdev = ctx->dev->pdev;
+	struct device_node *ep_node, *port, *remote_ep,
+			*sensor_node, *parent;
+	struct v4l2_of_endpoint *endpoint;
+	struct v4l2_async_subdev *asd;
+	u32 regval = 0;
+	int ret, index, found_port = 0, lane;
+
+	parent = pdev->dev.of_node;
+
+	asd = &ctx->asd;
+	endpoint = &ctx->endpoint;
+
+	ep_node = NULL;
+	port = NULL;
+	remote_ep = NULL;
+	sensor_node = NULL;
+	ret = -EINVAL;
+
+	ctx_dbg(3, ctx, "Scanning Port node for csi2 port: %d\n", inst);
+	for (index = 0; index < CAL_NUM_CSI2_PORTS; index++) {
+		port = of_get_next_port(parent, port);
+		if (!port) {
+			ctx_dbg(1, ctx, "No port node found for csi2 port:%d\n",
+				index);
+			goto cleanup_exit;
+		}
+
+		/* Match the slice number with <REG> */
+		of_property_read_u32(port, "reg", &regval);
+		ctx_dbg(3, ctx, "port:%d inst:%d <reg>:%d\n",
+			index, inst, regval);
+		if ((regval == inst) && (index == inst)) {
+			found_port = 1;
+			break;
+		}
+	}
+
+	if (!found_port) {
+		ctx_dbg(1, ctx, "No port node matches csi2 port:%d\n",
+			inst);
+		goto cleanup_exit;
+	}
+
+	ctx_dbg(3, ctx, "Scanning sub-device for csi2 port: %d\n",
+		inst);
+
+	ep_node = of_get_next_endpoint(port, ep_node);
+	if (!ep_node) {
+		ctx_dbg(3, ctx, "can't get next endpoint\n");
+		goto cleanup_exit;
+	}
+
+	sensor_node = of_graph_get_remote_port_parent(ep_node);
+	if (!sensor_node) {
+		ctx_dbg(3, ctx, "can't get remote parent\n");
+		goto cleanup_exit;
+	}
+	asd->match_type = V4L2_ASYNC_MATCH_OF;
+	asd->match.of.node = sensor_node;
+
+	remote_ep = of_parse_phandle(ep_node, "remote-endpoint", 0);
+	if (!remote_ep) {
+		ctx_dbg(3, ctx, "can't get remote-endpoint\n");
+		goto cleanup_exit;
+	}
+	v4l2_of_parse_endpoint(remote_ep, endpoint);
+
+	if (endpoint->bus_type != V4L2_MBUS_CSI2) {
+		ctx_err(ctx, "Port:%d sub-device %s is not a CSI2 device\n",
+			inst, sensor_node->name);
+		goto cleanup_exit;
+	}
+
+	/* Store Virtual Channel number */
+	ctx->virtual_channel = endpoint->base.id;
+
+	ctx_dbg(3, ctx, "Port:%d v4l2-endpoint: CSI2\n", inst);
+	ctx_dbg(3, ctx, "Virtual Channel=%d\n", ctx->virtual_channel);
+	ctx_dbg(3, ctx, "flags=0x%08x\n", endpoint->bus.mipi_csi2.flags);
+	ctx_dbg(3, ctx, "clock_lane=%d\n", endpoint->bus.mipi_csi2.clock_lane);
+	ctx_dbg(3, ctx, "num_data_lanes=%d\n",
+		endpoint->bus.mipi_csi2.num_data_lanes);
+	ctx_dbg(3, ctx, "data_lanes= <\n");
+	for (lane = 0; lane < endpoint->bus.mipi_csi2.num_data_lanes; lane++)
+		ctx_dbg(3, ctx, "\t%d\n",
+			endpoint->bus.mipi_csi2.data_lanes[lane]);
+	ctx_dbg(3, ctx, "\t>\n");
+
+	ctx_dbg(1, ctx, "Port: %d found sub-device %s\n",
+		inst, sensor_node->name);
+
+	ctx->asd_list[0] = asd;
+	ctx->notifier.subdevs = ctx->asd_list;
+	ctx->notifier.num_subdevs = 1;
+	ctx->notifier.bound = cal_async_bound;
+	ctx->notifier.complete = cal_async_complete;
+	ret = v4l2_async_notifier_register(&ctx->v4l2_dev,
+					   &ctx->notifier);
+	if (ret) {
+		ctx_err(ctx, "Error registering async notifier\n");
+		ret = -EINVAL;
+	}
+
+cleanup_exit:
+	if (!remote_ep)
+		of_node_put(remote_ep);
+	if (!sensor_node)
+		of_node_put(sensor_node);
+	if (!ep_node)
+		of_node_put(ep_node);
+	if (!port)
+		of_node_put(port);
+
+	return ret;
+}
+
+static struct cal_ctx *cal_create_instance(struct cal_dev *dev, int inst)
+{
+	struct cal_ctx *ctx;
+	struct v4l2_ctrl_handler *hdl;
+	int ret;
+
+	ctx = devm_kzalloc(&dev->pdev->dev, sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return NULL;
+
+	/* save the cal_dev * for future ref */
+	ctx->dev = dev;
+
+	snprintf(ctx->v4l2_dev.name, sizeof(ctx->v4l2_dev.name),
+		 "%s-%03d", CAL_MODULE_NAME, inst);
+	ret = v4l2_device_register(&dev->pdev->dev, &ctx->v4l2_dev);
+	if (ret)
+		goto err_exit;
+
+	hdl = &ctx->ctrl_handler;
+	ret = v4l2_ctrl_handler_init(hdl, 11);
+	if (ret) {
+		ctx_err(ctx, "Failed to init ctrl handler\n");
+		goto unreg_dev;
+	}
+	ctx->v4l2_dev.ctrl_handler = hdl;
+
+	/* Make sure Camera Core H/W register area is available */
+	ctx->cc = dev->cc[inst];
+
+	/* Store the instance id */
+	ctx->csi2_port = inst + 1;
+
+	ret = of_cal_create_instance(ctx, inst);
+	if (ret) {
+		ret = -EINVAL;
+		goto free_hdl;
+	}
+	return ctx;
+
+free_hdl:
+	v4l2_ctrl_handler_free(hdl);
+unreg_dev:
+	v4l2_device_unregister(&ctx->v4l2_dev);
+err_exit:
+	return NULL;
+}
+
+static int cal_probe(struct platform_device *pdev)
+{
+	struct cal_dev *dev;
+	int ret;
+	int irq;
+
+	dev = devm_kzalloc(&pdev->dev, sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	/* set pseudo v4l2 device name so we can use v4l2_printk */
+	strlcpy(dev->v4l2_dev.name, CAL_MODULE_NAME,
+		sizeof(dev->v4l2_dev.name));
+
+	/* save pdev pointer */
+	dev->pdev = pdev;
+
+	dev->res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						"cal_top");
+	dev->base = devm_ioremap_resource(&pdev->dev, dev->res);
+	if (IS_ERR(dev->base))
+		return PTR_ERR(dev->base);
+
+	cal_dbg(1, dev, "ioresource %s at %pa - %pa\n",
+		dev->res->name, &dev->res->start, &dev->res->end);
+
+	irq = platform_get_irq(pdev, 0);
+	cal_dbg(1, dev, "got irq# %d\n", irq);
+	ret = devm_request_irq(&pdev->dev, irq, cal_irq, 0, CAL_MODULE_NAME,
+			       dev);
+	if (ret)
+		return ret;
+
+	platform_set_drvdata(pdev, dev);
+
+	dev->cm = cm_create(dev);
+	if (IS_ERR(dev->cm))
+		return PTR_ERR(dev->cm);
+
+	dev->cc[0] = cc_create(dev, 0);
+	if (IS_ERR(dev->cc[0]))
+		return PTR_ERR(dev->cc[0]);
+
+	dev->cc[1] = cc_create(dev, 1);
+	if (IS_ERR(dev->cc[1]))
+		return PTR_ERR(dev->cc[1]);
+
+	dev->ctx[0] = NULL;
+	dev->ctx[1] = NULL;
+
+	dev->ctx[0] = cal_create_instance(dev, 0);
+	dev->ctx[1] = cal_create_instance(dev, 1);
+	if (!dev->ctx[0] && !dev->ctx[1]) {
+		cal_err(dev, "Neither port is configured, no point in staying up\n");
+		return -ENODEV;
+	}
+
+	pm_runtime_enable(&pdev->dev);
+
+	ret = cal_runtime_get(dev);
+	if (ret)
+		goto runtime_disable;
+
+	/* Just check we can actually access the module */
+	cal_get_hwinfo(dev);
+
+	cal_runtime_put(dev);
+
+	return 0;
+
+runtime_disable:
+	pm_runtime_disable(&pdev->dev);
+	return ret;
+}
+
+static int cal_remove(struct platform_device *pdev)
+{
+	struct cal_dev *dev =
+		(struct cal_dev *)platform_get_drvdata(pdev);
+	struct cal_ctx *ctx;
+	int i;
+
+	cal_dbg(1, dev, "Removing %s\n", CAL_MODULE_NAME);
+
+	cal_runtime_get(dev);
+
+	for (i = 0; i < CAL_NUM_CONTEXT; i++) {
+		ctx = dev->ctx[i];
+		if (ctx) {
+			ctx_dbg(1, ctx, "unregistering %s\n",
+				video_device_node_name(&ctx->vdev));
+			camerarx_phy_disable(ctx);
+			v4l2_async_notifier_unregister(&ctx->notifier);
+			vb2_dma_contig_cleanup_ctx(ctx->alloc_ctx);
+			v4l2_ctrl_handler_free(&ctx->ctrl_handler);
+			v4l2_device_unregister(&ctx->v4l2_dev);
+			video_unregister_device(&ctx->vdev);
+		}
+	}
+
+	cal_runtime_put(dev);
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+#if defined(CONFIG_OF)
+static const struct of_device_id cal_of_match[] = {
+	{ .compatible = "ti,dra72-cal", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, cal_of_match);
+#endif
+
+static struct platform_driver cal_pdrv = {
+	.probe		= cal_probe,
+	.remove		= cal_remove,
+	.driver		= {
+		.name	= CAL_MODULE_NAME,
+		.of_match_table = of_match_ptr(cal_of_match),
+	},
+};
+
+module_platform_driver(cal_pdrv);
diff --git a/drivers/media/platform/ti-vpe/cal_regs.h b/drivers/media/platform/ti-vpe/cal_regs.h
new file mode 100644
index 000000000000..82b3dcf87128
--- /dev/null
+++ b/drivers/media/platform/ti-vpe/cal_regs.h
@@ -0,0 +1,479 @@
+/*
+ * TI CAL camera interface driver
+ *
+ * Copyright (c) 2015 Texas Instruments Inc.
+ *
+ * Benoit Parrot, <bparrot@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ */
+
+#ifndef __TI_CAL_REGS_H
+#define __TI_CAL_REGS_H
+
+#define CAL_NUM_CSI2_PORTS		2
+
+/* CAL register offsets */
+
+#define CAL_HL_REVISION			0x0000
+#define CAL_HL_HWINFO			0x0004
+#define CAL_HL_SYSCONFIG		0x0010
+#define CAL_HL_IRQ_EOI			0x001c
+#define CAL_HL_IRQSTATUS_RAW(m)		(0x20U + ((m-1) * 0x10U))
+#define CAL_HL_IRQSTATUS(m)		(0x24U + ((m-1) * 0x10U))
+#define CAL_HL_IRQENABLE_SET(m)		(0x28U + ((m-1) * 0x10U))
+#define CAL_HL_IRQENABLE_CLR(m)		(0x2cU + ((m-1) * 0x10U))
+#define CAL_PIX_PROC(m)			(0xc0U + ((m-1) * 0x4U))
+#define CAL_CTRL			0x100
+#define CAL_CTRL1			0x104
+#define CAL_LINE_NUMBER_EVT		0x108
+#define CAL_VPORT_CTRL1			0x120
+#define CAL_VPORT_CTRL2			0x124
+#define CAL_BYS_CTRL1			0x130
+#define CAL_BYS_CTRL2			0x134
+#define CAL_RD_DMA_CTRL			0x140
+#define CAL_RD_DMA_PIX_ADDR		0x144
+#define CAL_RD_DMA_PIX_OFST		0x148
+#define CAL_RD_DMA_XSIZE		0x14c
+#define CAL_RD_DMA_YSIZE		0x150
+#define CAL_RD_DMA_INIT_ADDR		0x154
+#define CAL_RD_DMA_INIT_OFST		0x168
+#define CAL_RD_DMA_CTRL2		0x16c
+#define CAL_WR_DMA_CTRL(m)		(0x200U + ((m-1) * 0x10U))
+#define CAL_WR_DMA_ADDR(m)		(0x204U + ((m-1) * 0x10U))
+#define CAL_WR_DMA_OFST(m)		(0x208U + ((m-1) * 0x10U))
+#define CAL_WR_DMA_XSIZE(m)		(0x20cU + ((m-1) * 0x10U))
+#define CAL_CSI2_PPI_CTRL(m)		(0x300U + ((m-1) * 0x80U))
+#define CAL_CSI2_COMPLEXIO_CFG(m)	(0x304U + ((m-1) * 0x80U))
+#define CAL_CSI2_COMPLEXIO_IRQSTATUS(m)	(0x308U + ((m-1) * 0x80U))
+#define CAL_CSI2_SHORT_PACKET(m)	(0x30cU + ((m-1) * 0x80U))
+#define CAL_CSI2_COMPLEXIO_IRQENABLE(m)	(0x310U + ((m-1) * 0x80U))
+#define CAL_CSI2_TIMING(m)		(0x314U + ((m-1) * 0x80U))
+#define CAL_CSI2_VC_IRQENABLE(m)	(0x318U + ((m-1) * 0x80U))
+#define CAL_CSI2_VC_IRQSTATUS(m)	(0x328U + ((m-1) * 0x80U))
+#define CAL_CSI2_CTX0(m)		(0x330U + ((m-1) * 0x80U))
+#define CAL_CSI2_CTX1(m)		(0x334U + ((m-1) * 0x80U))
+#define CAL_CSI2_CTX2(m)		(0x338U + ((m-1) * 0x80U))
+#define CAL_CSI2_CTX3(m)		(0x33cU + ((m-1) * 0x80U))
+#define CAL_CSI2_CTX4(m)		(0x340U + ((m-1) * 0x80U))
+#define CAL_CSI2_CTX5(m)		(0x344U + ((m-1) * 0x80U))
+#define CAL_CSI2_CTX6(m)		(0x348U + ((m-1) * 0x80U))
+#define CAL_CSI2_CTX7(m)		(0x34cU + ((m-1) * 0x80U))
+#define CAL_CSI2_STATUS0(m)		(0x350U + ((m-1) * 0x80U))
+#define CAL_CSI2_STATUS1(m)		(0x354U + ((m-1) * 0x80U))
+#define CAL_CSI2_STATUS2(m)		(0x358U + ((m-1) * 0x80U))
+#define CAL_CSI2_STATUS3(m)		(0x35cU + ((m-1) * 0x80U))
+#define CAL_CSI2_STATUS4(m)		(0x360U + ((m-1) * 0x80U))
+#define CAL_CSI2_STATUS5(m)		(0x364U + ((m-1) * 0x80U))
+#define CAL_CSI2_STATUS6(m)		(0x368U + ((m-1) * 0x80U))
+#define CAL_CSI2_STATUS7(m)		(0x36cU + ((m-1) * 0x80U))
+
+/* CAL CSI2 PHY register offsets */
+#define CAL_CSI2_PHY_REG0		0x000
+#define CAL_CSI2_PHY_REG1		0x004
+#define CAL_CSI2_PHY_REG2		0x008
+
+/* CAL Control Module Core Camerrx Control register offsets */
+#define CM_CTRL_CORE_CAMERRX_CONTROL	0x000
+
+/*********************************************************************
+* Generic value used in various field below
+*********************************************************************/
+
+#define CAL_GEN_DISABLE			0
+#define CAL_GEN_ENABLE			1
+#define CAL_GEN_FALSE			0
+#define CAL_GEN_TRUE			1
+
+/*********************************************************************
+* Field Definition Macros
+*********************************************************************/
+
+#define CAL_HL_REVISION_MINOR_MASK		GENMASK(5, 0)
+#define CAL_HL_REVISION_CUSTOM_MASK		GENMASK(7, 6)
+#define CAL_HL_REVISION_MAJOR_MASK		GENMASK(10, 8)
+#define CAL_HL_REVISION_RTL_MASK		GENMASK(15, 11)
+#define CAL_HL_REVISION_FUNC_MASK		GENMASK(27, 16)
+#define CAL_HL_REVISION_SCHEME_MASK		GENMASK(31, 30)
+#define CAL_HL_REVISION_SCHEME_H08			1
+#define CAL_HL_REVISION_SCHEME_LEGACY			0
+
+#define CAL_HL_HWINFO_WFIFO_MASK		GENMASK(3, 0)
+#define CAL_HL_HWINFO_RFIFO_MASK		GENMASK(7, 4)
+#define CAL_HL_HWINFO_PCTX_MASK			GENMASK(12, 8)
+#define CAL_HL_HWINFO_WCTX_MASK			GENMASK(18, 13)
+#define CAL_HL_HWINFO_VFIFO_MASK		GENMASK(22, 19)
+#define CAL_HL_HWINFO_NCPORT_MASK		GENMASK(27, 23)
+#define CAL_HL_HWINFO_NPPI_CTXS0_MASK		GENMASK(29, 28)
+#define CAL_HL_HWINFO_NPPI_CTXS1_MASK		GENMASK(31, 30)
+#define CAL_HL_HWINFO_NPPI_CONTEXTS_ZERO		0
+#define CAL_HL_HWINFO_NPPI_CONTEXTS_FOUR		1
+#define CAL_HL_HWINFO_NPPI_CONTEXTS_EIGHT		2
+#define CAL_HL_HWINFO_NPPI_CONTEXTS_RESERVED		3
+
+#define CAL_HL_SYSCONFIG_SOFTRESET_MASK		BIT_MASK(0)
+#define CAL_HL_SYSCONFIG_SOFTRESET_DONE			0x0
+#define CAL_HL_SYSCONFIG_SOFTRESET_PENDING		0x1
+#define CAL_HL_SYSCONFIG_SOFTRESET_NOACTION		0x0
+#define CAL_HL_SYSCONFIG_SOFTRESET_RESET		0x1
+#define CAL_HL_SYSCONFIG_IDLE_MASK		GENMASK(3, 2)
+#define CAL_HL_SYSCONFIG_IDLEMODE_FORCE			0
+#define CAL_HL_SYSCONFIG_IDLEMODE_NO			1
+#define CAL_HL_SYSCONFIG_IDLEMODE_SMART1		2
+#define CAL_HL_SYSCONFIG_IDLEMODE_SMART2		3
+
+#define CAL_HL_IRQ_EOI_LINE_NUMBER_MASK		BIT_MASK(0)
+#define CAL_HL_IRQ_EOI_LINE_NUMBER_READ0		0
+#define CAL_HL_IRQ_EOI_LINE_NUMBER_EOI0			0
+
+#define CAL_HL_IRQ_MASK(m)			BIT_MASK(m-1)
+#define CAL_HL_IRQ_NOACTION				0x0
+#define CAL_HL_IRQ_ENABLE				0x1
+#define CAL_HL_IRQ_CLEAR				0x1
+#define CAL_HL_IRQ_DISABLED				0x0
+#define CAL_HL_IRQ_ENABLED				0x1
+#define CAL_HL_IRQ_PENDING				0x1
+
+#define CAL_PIX_PROC_EN_MASK			BIT_MASK(0)
+#define CAL_PIX_PROC_EXTRACT_MASK		GENMASK(4, 1)
+#define CAL_PIX_PROC_EXTRACT_B6				0x0
+#define CAL_PIX_PROC_EXTRACT_B7				0x1
+#define CAL_PIX_PROC_EXTRACT_B8				0x2
+#define CAL_PIX_PROC_EXTRACT_B10			0x3
+#define CAL_PIX_PROC_EXTRACT_B10_MIPI			0x4
+#define CAL_PIX_PROC_EXTRACT_B12			0x5
+#define CAL_PIX_PROC_EXTRACT_B12_MIPI			0x6
+#define CAL_PIX_PROC_EXTRACT_B14			0x7
+#define CAL_PIX_PROC_EXTRACT_B14_MIPI			0x8
+#define CAL_PIX_PROC_EXTRACT_B16_BE			0x9
+#define CAL_PIX_PROC_EXTRACT_B16_LE			0xa
+#define CAL_PIX_PROC_DPCMD_MASK			GENMASK(9, 5)
+#define CAL_PIX_PROC_DPCMD_BYPASS			0x0
+#define CAL_PIX_PROC_DPCMD_DPCM_10_8_1			0x2
+#define CAL_PIX_PROC_DPCMD_DPCM_12_8_1			0x8
+#define CAL_PIX_PROC_DPCMD_DPCM_10_7_1			0x4
+#define CAL_PIX_PROC_DPCMD_DPCM_10_7_2			0x5
+#define CAL_PIX_PROC_DPCMD_DPCM_10_6_1			0x6
+#define CAL_PIX_PROC_DPCMD_DPCM_10_6_2			0x7
+#define CAL_PIX_PROC_DPCMD_DPCM_12_7_1			0xa
+#define CAL_PIX_PROC_DPCMD_DPCM_12_6_1			0xc
+#define CAL_PIX_PROC_DPCMD_DPCM_14_10			0xe
+#define CAL_PIX_PROC_DPCMD_DPCM_14_8_1			0x10
+#define CAL_PIX_PROC_DPCMD_DPCM_16_12_1			0x12
+#define CAL_PIX_PROC_DPCMD_DPCM_16_10_1			0x14
+#define CAL_PIX_PROC_DPCMD_DPCM_16_8_1			0x16
+#define CAL_PIX_PROC_DPCME_MASK			GENMASK(15, 11)
+#define CAL_PIX_PROC_DPCME_BYPASS			0x0
+#define CAL_PIX_PROC_DPCME_DPCM_10_8_1			0x2
+#define CAL_PIX_PROC_DPCME_DPCM_12_8_1			0x8
+#define CAL_PIX_PROC_DPCME_DPCM_14_10			0xe
+#define CAL_PIX_PROC_DPCME_DPCM_14_8_1			0x10
+#define CAL_PIX_PROC_DPCME_DPCM_16_12_1			0x12
+#define CAL_PIX_PROC_DPCME_DPCM_16_10_1			0x14
+#define CAL_PIX_PROC_DPCME_DPCM_16_8_1			0x16
+#define CAL_PIX_PROC_PACK_MASK			GENMASK(18, 16)
+#define CAL_PIX_PROC_PACK_B8				0x0
+#define CAL_PIX_PROC_PACK_B10_MIPI			0x2
+#define CAL_PIX_PROC_PACK_B12				0x3
+#define CAL_PIX_PROC_PACK_B12_MIPI			0x4
+#define CAL_PIX_PROC_PACK_B16				0x5
+#define CAL_PIX_PROC_PACK_ARGB				0x6
+#define CAL_PIX_PROC_CPORT_MASK			GENMASK(23, 19)
+
+#define CAL_CTRL_POSTED_WRITES_MASK		BIT_MASK(0)
+#define CAL_CTRL_POSTED_WRITES_NONPOSTED		0
+#define CAL_CTRL_POSTED_WRITES				1
+#define CAL_CTRL_TAGCNT_MASK			GENMASK(4, 1)
+#define CAL_CTRL_BURSTSIZE_MASK			GENMASK(6, 5)
+#define CAL_CTRL_BURSTSIZE_BURST16			0x0
+#define CAL_CTRL_BURSTSIZE_BURST32			0x1
+#define CAL_CTRL_BURSTSIZE_BURST64			0x2
+#define CAL_CTRL_BURSTSIZE_BURST128			0x3
+#define CAL_CTRL_LL_FORCE_STATE_MASK		GENMASK(12, 7)
+#define CAL_CTRL_MFLAGL_MASK			GENMASK(20, 13)
+#define CAL_CTRL_PWRSCPCLK_MASK			BIT_MASK(21)
+#define CAL_CTRL_PWRSCPCLK_AUTO				0
+#define CAL_CTRL_PWRSCPCLK_FORCE			1
+#define CAL_CTRL_RD_DMA_STALL_MASK		BIT_MASK(22)
+#define CAL_CTRL_MFLAGH_MASK			GENMASK(31, 24)
+
+#define CAL_CTRL1_PPI_GROUPING_MASK		GENMASK(1, 0)
+#define CAL_CTRL1_PPI_GROUPING_DISABLED			0
+#define CAL_CTRL1_PPI_GROUPING_RESERVED			1
+#define CAL_CTRL1_PPI_GROUPING_0			2
+#define CAL_CTRL1_PPI_GROUPING_1			3
+#define CAL_CTRL1_INTERLEAVE01_MASK		GENMASK(3, 2)
+#define CAL_CTRL1_INTERLEAVE01_DISABLED			0
+#define CAL_CTRL1_INTERLEAVE01_PIX1			1
+#define CAL_CTRL1_INTERLEAVE01_PIX4			2
+#define CAL_CTRL1_INTERLEAVE01_RESERVED			3
+#define CAL_CTRL1_INTERLEAVE23_MASK		GENMASK(5, 4)
+#define CAL_CTRL1_INTERLEAVE23_DISABLED			0
+#define CAL_CTRL1_INTERLEAVE23_PIX1			1
+#define CAL_CTRL1_INTERLEAVE23_PIX4			2
+#define CAL_CTRL1_INTERLEAVE23_RESERVED			3
+
+#define CAL_LINE_NUMBER_EVT_CPORT_MASK		GENMASK(4, 0)
+#define CAL_LINE_NUMBER_EVT_MASK		GENMASK(29, 16)
+
+#define CAL_VPORT_CTRL1_PCLK_MASK		GENMASK(16, 0)
+#define CAL_VPORT_CTRL1_XBLK_MASK		GENMASK(24, 17)
+#define CAL_VPORT_CTRL1_YBLK_MASK		GENMASK(30, 25)
+#define CAL_VPORT_CTRL1_WIDTH_MASK		BIT_MASK(31)
+#define CAL_VPORT_CTRL1_WIDTH_ONE			0
+#define CAL_VPORT_CTRL1_WIDTH_TWO			1
+
+#define CAL_VPORT_CTRL2_CPORT_MASK		GENMASK(4, 0)
+#define CAL_VPORT_CTRL2_FREERUNNING_MASK	BIT_MASK(15)
+#define CAL_VPORT_CTRL2_FREERUNNING_GATED		0
+#define CAL_VPORT_CTRL2_FREERUNNING_FREE		1
+#define CAL_VPORT_CTRL2_FS_RESETS_MASK		BIT_MASK(16)
+#define CAL_VPORT_CTRL2_FS_RESETS_NO			0
+#define CAL_VPORT_CTRL2_FS_RESETS_YES			1
+#define CAL_VPORT_CTRL2_FSM_RESET_MASK		BIT_MASK(17)
+#define CAL_VPORT_CTRL2_FSM_RESET_NOEFFECT		0
+#define CAL_VPORT_CTRL2_FSM_RESET			1
+#define CAL_VPORT_CTRL2_RDY_THR_MASK		GENMASK(31, 18)
+
+#define CAL_BYS_CTRL1_PCLK_MASK			GENMASK(16, 0)
+#define CAL_BYS_CTRL1_XBLK_MASK			GENMASK(24, 17)
+#define CAL_BYS_CTRL1_YBLK_MASK			GENMASK(30, 25)
+#define CAL_BYS_CTRL1_BYSINEN_MASK		BIT_MASK(31)
+
+#define CAL_BYS_CTRL2_CPORTIN_MASK		GENMASK(4, 0)
+#define CAL_BYS_CTRL2_CPORTOUT_MASK		GENMASK(9, 5)
+#define CAL_BYS_CTRL2_DUPLICATEDDATA_MASK	BIT_MASK(10)
+#define CAL_BYS_CTRL2_DUPLICATEDDATA_NO			0
+#define CAL_BYS_CTRL2_DUPLICATEDDATA_YES		1
+#define CAL_BYS_CTRL2_FREERUNNING_MASK		BIT_MASK(11)
+#define CAL_BYS_CTRL2_FREERUNNING_NO			0
+#define CAL_BYS_CTRL2_FREERUNNING_YES			1
+
+#define CAL_RD_DMA_CTRL_GO_MASK			BIT_MASK(0)
+#define CAL_RD_DMA_CTRL_GO_DIS				0
+#define CAL_RD_DMA_CTRL_GO_EN				1
+#define CAL_RD_DMA_CTRL_GO_IDLE				0
+#define CAL_RD_DMA_CTRL_GO_BUSY				1
+#define CAL_RD_DMA_CTRL_INIT_MASK		BIT_MASK(1)
+#define CAL_RD_DMA_CTRL_BW_LIMITER_MASK		GENMASK(10, 2)
+#define CAL_RD_DMA_CTRL_OCP_TAG_CNT_MASK	GENMASK(14, 11)
+#define CAL_RD_DMA_CTRL_PCLK_MASK		GENMASK(31, 15)
+
+#define CAL_RD_DMA_PIX_ADDR_MASK		GENMASK(31, 3)
+
+#define CAL_RD_DMA_PIX_OFST_MASK		GENMASK(31, 4)
+
+#define CAL_RD_DMA_XSIZE_MASK			GENMASK(31, 19)
+
+#define CAL_RD_DMA_YSIZE_MASK			GENMASK(29, 16)
+
+#define CAL_RD_DMA_INIT_ADDR_MASK		GENMASK(31, 3)
+
+#define CAL_RD_DMA_INIT_OFST_MASK		GENMASK(31, 3)
+
+#define CAL_RD_DMA_CTRL2_CIRC_MODE_MASK		GENMASK(2, 0)
+#define CAL_RD_DMA_CTRL2_CIRC_MODE_DIS			0
+#define CAL_RD_DMA_CTRL2_CIRC_MODE_ONE			1
+#define CAL_RD_DMA_CTRL2_CIRC_MODE_FOUR			2
+#define CAL_RD_DMA_CTRL2_CIRC_MODE_SIXTEEN		3
+#define CAL_RD_DMA_CTRL2_CIRC_MODE_SIXTYFOUR		4
+#define CAL_RD_DMA_CTRL2_CIRC_MODE_RESERVED		5
+#define CAL_RD_DMA_CTRL2_ICM_CSTART_MASK	BIT_MASK(3)
+#define CAL_RD_DMA_CTRL2_PATTERN_MASK		GENMASK(5, 4)
+#define CAL_RD_DMA_CTRL2_PATTERN_LINEAR			0
+#define CAL_RD_DMA_CTRL2_PATTERN_YUV420			1
+#define CAL_RD_DMA_CTRL2_PATTERN_RD2SKIP2		2
+#define CAL_RD_DMA_CTRL2_PATTERN_RD2SKIP4		3
+#define CAL_RD_DMA_CTRL2_BYSOUT_LE_WAIT_MASK	BIT_MASK(6)
+#define CAL_RD_DMA_CTRL2_BYSOUT_LE_WAIT_FREERUNNING	0
+#define CAL_RD_DMA_CTRL2_BYSOUT_LE_WAIT_WAITFORBYSOUT	1
+#define CAL_RD_DMA_CTRL2_CIRC_SIZE_MASK		GENMASK(29, 16)
+
+#define CAL_WR_DMA_CTRL_MODE_MASK		GENMASK(2, 0)
+#define CAL_WR_DMA_CTRL_MODE_DIS			0
+#define CAL_WR_DMA_CTRL_MODE_SHD			1
+#define CAL_WR_DMA_CTRL_MODE_CNT			2
+#define CAL_WR_DMA_CTRL_MODE_CNT_INIT			3
+#define CAL_WR_DMA_CTRL_MODE_CONST			4
+#define CAL_WR_DMA_CTRL_MODE_RESERVED			5
+#define CAL_WR_DMA_CTRL_PATTERN_MASK		GENMASK(4, 3)
+#define CAL_WR_DMA_CTRL_PATTERN_LINEAR			0
+#define CAL_WR_DMA_CTRL_PATTERN_WR2SKIP2		2
+#define CAL_WR_DMA_CTRL_PATTERN_WR2SKIP4		3
+#define CAL_WR_DMA_CTRL_PATTERN_RESERVED		1
+#define CAL_WR_DMA_CTRL_ICM_PSTART_MASK		BIT_MASK(5)
+#define CAL_WR_DMA_CTRL_DTAG_MASK		GENMASK(8, 6)
+#define CAL_WR_DMA_CTRL_DTAG_ATT_HDR			0
+#define CAL_WR_DMA_CTRL_DTAG_ATT_DAT			1
+#define CAL_WR_DMA_CTRL_DTAG				2
+#define CAL_WR_DMA_CTRL_DTAG_PIX_HDR			3
+#define CAL_WR_DMA_CTRL_DTAG_PIX_DAT			4
+#define CAL_WR_DMA_CTRL_DTAG_D5				5
+#define CAL_WR_DMA_CTRL_DTAG_D6				6
+#define CAL_WR_DMA_CTRL_DTAG_D7				7
+#define CAL_WR_DMA_CTRL_CPORT_MASK		GENMASK(13, 9)
+#define CAL_WR_DMA_CTRL_STALL_RD_MASK		BIT_MASK(14)
+#define CAL_WR_DMA_CTRL_YSIZE_MASK		GENMASK(31, 18)
+
+#define CAL_WR_DMA_ADDR_MASK			GENMASK(31, 4)
+
+#define CAL_WR_DMA_OFST_MASK			GENMASK(18, 4)
+#define CAL_WR_DMA_OFST_CIRC_MODE_MASK		GENMASK(23, 22)
+#define CAL_WR_DMA_OFST_CIRC_MODE_ONE			1
+#define CAL_WR_DMA_OFST_CIRC_MODE_FOUR			2
+#define CAL_WR_DMA_OFST_CIRC_MODE_SIXTYFOUR		3
+#define CAL_WR_DMA_OFST_CIRC_MODE_DISABLED		0
+#define CAL_WR_DMA_OFST_CIRC_SIZE_MASK		GENMASK(31, 24)
+
+#define CAL_WR_DMA_XSIZE_XSKIP_MASK		GENMASK(15, 3)
+#define CAL_WR_DMA_XSIZE_MASK			GENMASK(31, 19)
+
+#define CAL_CSI2_PPI_CTRL_IF_EN_MASK		BIT_MASK(0)
+#define CAL_CSI2_PPI_CTRL_ECC_EN_MASK		BIT_MASK(2)
+#define CAL_CSI2_PPI_CTRL_FRAME_MASK		BIT_MASK(3)
+#define CAL_CSI2_PPI_CTRL_FRAME_IMMEDIATE		0
+#define CAL_CSI2_PPI_CTRL_FRAME				1
+
+#define CAL_CSI2_COMPLEXIO_CFG_CLOCK_POSITION_MASK	GENMASK(2, 0)
+#define CAL_CSI2_COMPLEXIO_CFG_POSITION_5			5
+#define CAL_CSI2_COMPLEXIO_CFG_POSITION_4			4
+#define CAL_CSI2_COMPLEXIO_CFG_POSITION_3			3
+#define CAL_CSI2_COMPLEXIO_CFG_POSITION_2			2
+#define CAL_CSI2_COMPLEXIO_CFG_POSITION_1			1
+#define CAL_CSI2_COMPLEXIO_CFG_POSITION_NOT_USED		0
+#define CAL_CSI2_COMPLEXIO_CFG_CLOCK_POL_MASK		BIT_MASK(3)
+#define CAL_CSI2_COMPLEXIO_CFG_POL_PLUSMINUS			0
+#define CAL_CSI2_COMPLEXIO_CFG_POL_MINUSPLUS			1
+#define CAL_CSI2_COMPLEXIO_CFG_DATA1_POSITION_MASK	GENMASK(6, 4)
+#define CAL_CSI2_COMPLEXIO_CFG_DATA1_POL_MASK		BIT_MASK(7)
+#define CAL_CSI2_COMPLEXIO_CFG_DATA2_POSITION_MASK	GENMASK(10, 8)
+#define CAL_CSI2_COMPLEXIO_CFG_DATA2_POL_MASK		BIT_MASK(11)
+#define CAL_CSI2_COMPLEXIO_CFG_DATA3_POSITION_MASK	GENMASK(14, 12)
+#define CAL_CSI2_COMPLEXIO_CFG_DATA3_POL_MASK		BIT_MASK(15)
+#define CAL_CSI2_COMPLEXIO_CFG_DATA4_POSITION_MASK	GENMASK(18, 16)
+#define CAL_CSI2_COMPLEXIO_CFG_DATA4_POL_MASK		BIT_MASK(19)
+#define CAL_CSI2_COMPLEXIO_CFG_PWR_AUTO_MASK		BIT_MASK(24)
+#define CAL_CSI2_COMPLEXIO_CFG_PWR_STATUS_MASK		GENMASK(26, 25)
+#define CAL_CSI2_COMPLEXIO_CFG_PWR_STATUS_STATE_OFF		0
+#define CAL_CSI2_COMPLEXIO_CFG_PWR_STATUS_STATE_ON		1
+#define CAL_CSI2_COMPLEXIO_CFG_PWR_STATUS_STATE_ULP		2
+#define CAL_CSI2_COMPLEXIO_CFG_PWR_CMD_MASK		GENMASK(28, 27)
+#define CAL_CSI2_COMPLEXIO_CFG_PWR_CMD_STATE_OFF		0
+#define CAL_CSI2_COMPLEXIO_CFG_PWR_CMD_STATE_ON			1
+#define CAL_CSI2_COMPLEXIO_CFG_PWR_CMD_STATE_ULP		2
+#define CAL_CSI2_COMPLEXIO_CFG_RESET_DONE_MASK		BIT_MASK(29)
+#define CAL_CSI2_COMPLEXIO_CFG_RESET_DONE_RESETCOMPLETED	1
+#define CAL_CSI2_COMPLEXIO_CFG_RESET_DONE_RESETONGOING		0
+#define CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL_MASK		BIT_MASK(30)
+#define CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL			0
+#define CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL_OPERATIONAL		1
+
+#define CAL_CSI2_SHORT_PACKET_MASK	GENMASK(23, 0)
+
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTHS1_MASK		BIT_MASK(0)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTHS2_MASK		BIT_MASK(1)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTHS3_MASK		BIT_MASK(2)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTHS4_MASK		BIT_MASK(3)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTHS5_MASK		BIT_MASK(4)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTSYNCHS1_MASK	BIT_MASK(5)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTSYNCHS2_MASK	BIT_MASK(6)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTSYNCHS3_MASK	BIT_MASK(7)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTSYNCHS4_MASK	BIT_MASK(8)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTSYNCHS5_MASK	BIT_MASK(9)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRESC1_MASK		BIT_MASK(10)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRESC2_MASK		BIT_MASK(11)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRESC3_MASK		BIT_MASK(12)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRESC4_MASK		BIT_MASK(13)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRESC5_MASK		BIT_MASK(14)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRCONTROL1_MASK		BIT_MASK(15)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRCONTROL2_MASK		BIT_MASK(16)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRCONTROL3_MASK		BIT_MASK(17)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRCONTROL4_MASK		BIT_MASK(18)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRCONTROL5_MASK		BIT_MASK(19)
+#define CAL_CSI2_COMPLEXIO_IRQ_STATEULPM1_MASK		BIT_MASK(20)
+#define CAL_CSI2_COMPLEXIO_IRQ_STATEULPM2_MASK		BIT_MASK(21)
+#define CAL_CSI2_COMPLEXIO_IRQ_STATEULPM3_MASK		BIT_MASK(22)
+#define CAL_CSI2_COMPLEXIO_IRQ_STATEULPM4_MASK		BIT_MASK(23)
+#define CAL_CSI2_COMPLEXIO_IRQ_STATEULPM5_MASK		BIT_MASK(24)
+#define CAL_CSI2_COMPLEXIO_IRQ_STATEALLULPMENTER_MASK	BIT_MASK(25)
+#define CAL_CSI2_COMPLEXIO_IRQ_STATEALLULPMEXIT_MASK	BIT_MASK(26)
+#define CAL_CSI2_COMPLEXIO_IRQ_FIFO_OVR_MASK		BIT_MASK(27)
+#define CAL_CSI2_COMPLEXIO_IRQ_SHORT_PACKET_MASK	BIT_MASK(28)
+#define CAL_CSI2_COMPLEXIO_IRQ_ECC_NO_CORRECTION_MASK	BIT_MASK(30)
+
+#define CAL_CSI2_TIMING_STOP_STATE_COUNTER_IO1_MASK	GENMASK(12, 0)
+#define CAL_CSI2_TIMING_STOP_STATE_X4_IO1_MASK		BIT_MASK(13)
+#define CAL_CSI2_TIMING_STOP_STATE_X16_IO1_MASK		BIT_MASK(14)
+#define CAL_CSI2_TIMING_FORCE_RX_MODE_IO1_MASK		BIT_MASK(15)
+
+#define CAL_CSI2_VC_IRQ_FS_IRQ_0_MASK			BIT_MASK(0)
+#define CAL_CSI2_VC_IRQ_FE_IRQ_0_MASK			BIT_MASK(1)
+#define CAL_CSI2_VC_IRQ_LS_IRQ_0_MASK			BIT_MASK(2)
+#define CAL_CSI2_VC_IRQ_LE_IRQ_0_MASK			BIT_MASK(3)
+#define CAL_CSI2_VC_IRQ_CS_IRQ_0_MASK			BIT_MASK(4)
+#define CAL_CSI2_VC_IRQ_ECC_CORRECTION0_IRQ_0_MASK	BIT_MASK(5)
+#define CAL_CSI2_VC_IRQ_FS_IRQ_1_MASK			BIT_MASK(8)
+#define CAL_CSI2_VC_IRQ_FE_IRQ_1_MASK			BIT_MASK(9)
+#define CAL_CSI2_VC_IRQ_LS_IRQ_1_MASK			BIT_MASK(10)
+#define CAL_CSI2_VC_IRQ_LE_IRQ_1_MASK			BIT_MASK(11)
+#define CAL_CSI2_VC_IRQ_CS_IRQ_1_MASK			BIT_MASK(12)
+#define CAL_CSI2_VC_IRQ_ECC_CORRECTION0_IRQ_1_MASK	BIT_MASK(13)
+#define CAL_CSI2_VC_IRQ_FS_IRQ_2_MASK			BIT_MASK(16)
+#define CAL_CSI2_VC_IRQ_FE_IRQ_2_MASK			BIT_MASK(17)
+#define CAL_CSI2_VC_IRQ_LS_IRQ_2_MASK			BIT_MASK(18)
+#define CAL_CSI2_VC_IRQ_LE_IRQ_2_MASK			BIT_MASK(19)
+#define CAL_CSI2_VC_IRQ_CS_IRQ_2_MASK			BIT_MASK(20)
+#define CAL_CSI2_VC_IRQ_ECC_CORRECTION0_IRQ_2_MASK	BIT_MASK(21)
+#define CAL_CSI2_VC_IRQ_FS_IRQ_3_MASK			BIT_MASK(24)
+#define CAL_CSI2_VC_IRQ_FE_IRQ_3_MASK			BIT_MASK(25)
+#define CAL_CSI2_VC_IRQ_LS_IRQ_3_MASK			BIT_MASK(26)
+#define CAL_CSI2_VC_IRQ_LE_IRQ_3_MASK			BIT_MASK(27)
+#define CAL_CSI2_VC_IRQ_CS_IRQ_3_MASK			BIT_MASK(28)
+#define CAL_CSI2_VC_IRQ_ECC_CORRECTION0_IRQ_3_MASK	BIT_MASK(29)
+
+#define CAL_CSI2_CTX_DT_MASK		GENMASK(5, 0)
+#define CAL_CSI2_CTX_VC_MASK		GENMASK(7, 6)
+#define CAL_CSI2_CTX_CPORT_MASK		GENMASK(12, 8)
+#define CAL_CSI2_CTX_ATT_MASK		BIT_MASK(13)
+#define CAL_CSI2_CTX_ATT_PIX			0
+#define CAL_CSI2_CTX_ATT			1
+#define CAL_CSI2_CTX_PACK_MODE_MASK	BIT_MASK(14)
+#define CAL_CSI2_CTX_PACK_MODE_LINE		0
+#define CAL_CSI2_CTX_PACK_MODE_FRAME		1
+#define CAL_CSI2_CTX_LINES_MASK		GENMASK(29, 16)
+
+#define CAL_CSI2_STATUS_FRAME_MASK	GENMASK(15, 0)
+
+#define CAL_CSI2_PHY_REG0_THS_SETTLE_MASK	GENMASK(7, 0)
+#define CAL_CSI2_PHY_REG0_THS_TERM_MASK		GENMASK(15, 8)
+#define CAL_CSI2_PHY_REG0_HSCLOCKCONFIG_MASK	BIT_MASK(24)
+#define CAL_CSI2_PHY_REG0_HSCLOCKCONFIG_DISABLE		1
+#define CAL_CSI2_PHY_REG0_HSCLOCKCONFIG_ENABLE		0
+
+#define CAL_CSI2_PHY_REG1_TCLK_SETTLE_MASK			GENMASK(7, 0)
+#define CAL_CSI2_PHY_REG1_CTRLCLK_DIV_FACTOR_MASK		GENMASK(9, 8)
+#define CAL_CSI2_PHY_REG1_DPHY_HS_SYNC_PATTERN_MASK		GENMASK(17, 10)
+#define CAL_CSI2_PHY_REG1_TCLK_TERM_MASK			GENMASK(24, 18)
+#define CAL_CSI2_PHY_REG1_CLOCK_MISS_DETECTOR_STATUS_MASK	BIT_MASK(25)
+#define CAL_CSI2_PHY_REG1_CLOCK_MISS_DETECTOR_STATUS_ERROR		1
+#define CAL_CSI2_PHY_REG1_CLOCK_MISS_DETECTOR_STATUS_SUCCESS		0
+#define CAL_CSI2_PHY_REG1_RESET_DONE_STATUS_MASK		GENMASK(29, 28)
+
+#define CAL_CSI2_PHY_REG2_CCP2_SYNC_PATTERN_MASK		GENMASK(23, 0)
+#define CAL_CSI2_PHY_REG2_TRIGGER_CMD_RXTRIGESC3_MASK		GENMASK(25, 24)
+#define CAL_CSI2_PHY_REG2_TRIGGER_CMD_RXTRIGESC2_MASK		GENMASK(27, 26)
+#define CAL_CSI2_PHY_REG2_TRIGGER_CMD_RXTRIGESC1_MASK		GENMASK(29, 28)
+#define CAL_CSI2_PHY_REG2_TRIGGER_CMD_RXTRIGESC0_MASK		GENMASK(31, 30)
+
+#define CM_CAMERRX_CTRL_CSI1_CTRLCLKEN_MASK			BIT_MASK(0)
+#define CM_CAMERRX_CTRL_CSI1_CAMMODE_MASK			GENMASK(2, 1)
+#define CM_CAMERRX_CTRL_CSI1_LANEENABLE_MASK			GENMASK(4, 3)
+#define CM_CAMERRX_CTRL_CSI1_MODE_MASK				BIT_MASK(5)
+#define CM_CAMERRX_CTRL_CSI0_CTRLCLKEN_MASK			BIT_MASK(10)
+#define CM_CAMERRX_CTRL_CSI0_CAMMODE_MASK			GENMASK(12, 11)
+#define CM_CAMERRX_CTRL_CSI0_LANEENABLE_MASK			GENMASK(16, 13)
+#define CM_CAMERRX_CTRL_CSI0_MODE_MASK				BIT_MASK(17)
+
+#endif
diff --git a/drivers/media/platform/vim2m.c b/drivers/media/platform/vim2m.c
index 418113c99801..c4b5fab83666 100644
--- a/drivers/media/platform/vim2m.c
+++ b/drivers/media/platform/vim2m.c
@@ -1074,7 +1074,7 @@ static int __init vim2m_init(void)
 	if (ret)
 		platform_device_unregister(&vim2m_pdev);
 
-	return 0;
+	return ret;
 }
 
 module_init(vim2m_init);
diff --git a/drivers/media/platform/vivid/vivid-osd.c b/drivers/media/platform/vivid/vivid-osd.c
index e15eef6a94e5..bdc380b14e0c 100644
--- a/drivers/media/platform/vivid/vivid-osd.c
+++ b/drivers/media/platform/vivid/vivid-osd.c
@@ -360,7 +360,7 @@ void vivid_fb_release_buffers(struct vivid_dev *dev)
 
 	/* Release pseudo palette */
 	kfree(dev->fb_info.pseudo_palette);
-	kfree((void *)dev->video_vbase);
+	kfree(dev->video_vbase);
 }
 
 /* Initialize the specified card */
diff --git a/drivers/media/platform/vivid/vivid-tpg.c b/drivers/media/platform/vivid/vivid-tpg.c
index 14256141f905..da862bb2e5f8 100644
--- a/drivers/media/platform/vivid/vivid-tpg.c
+++ b/drivers/media/platform/vivid/vivid-tpg.c
@@ -251,6 +251,10 @@ bool tpg_s_fourcc(struct tpg_data *tpg, u32 fourcc)
 		tpg->planes = 3;
 		tpg->is_yuv = true;
 		break;
+	case V4L2_PIX_FMT_YUV422M:
+	case V4L2_PIX_FMT_YVU422M:
+		tpg->buffers = 3;
+		/* fall through */
 	case V4L2_PIX_FMT_YUV422P:
 		tpg->vdownsampling[1] = 1;
 		tpg->vdownsampling[2] = 1;
@@ -283,6 +287,16 @@ bool tpg_s_fourcc(struct tpg_data *tpg, u32 fourcc)
 		tpg->planes = 2;
 		tpg->is_yuv = true;
 		break;
+	case V4L2_PIX_FMT_YUV444M:
+	case V4L2_PIX_FMT_YVU444M:
+		tpg->buffers = 3;
+		tpg->planes = 3;
+		tpg->vdownsampling[1] = 1;
+		tpg->vdownsampling[2] = 1;
+		tpg->hdownsampling[1] = 1;
+		tpg->hdownsampling[2] = 1;
+		tpg->is_yuv = true;
+		break;
 	case V4L2_PIX_FMT_NV24:
 	case V4L2_PIX_FMT_NV42:
 		tpg->vdownsampling[1] = 1;
@@ -368,6 +382,10 @@ bool tpg_s_fourcc(struct tpg_data *tpg, u32 fourcc)
 		tpg->twopixelsize[0] = 4;
 		tpg->twopixelsize[1] = 4;
 		break;
+	case V4L2_PIX_FMT_YUV444M:
+	case V4L2_PIX_FMT_YVU444M:
+	case V4L2_PIX_FMT_YUV422M:
+	case V4L2_PIX_FMT_YVU422M:
 	case V4L2_PIX_FMT_YUV422P:
 	case V4L2_PIX_FMT_YUV420:
 	case V4L2_PIX_FMT_YVU420:
@@ -933,6 +951,7 @@ static void gen_twopix(struct tpg_data *tpg,
 		buf[0][offset] = r_y;
 		buf[0][offset+1] = r_y == 0xff ? r_y : 0;
 		break;
+	case V4L2_PIX_FMT_YUV422M:
 	case V4L2_PIX_FMT_YUV422P:
 	case V4L2_PIX_FMT_YUV420:
 	case V4L2_PIX_FMT_YUV420M:
@@ -947,6 +966,7 @@ static void gen_twopix(struct tpg_data *tpg,
 		buf[1][0] = g_u;
 		buf[2][0] = b_v;
 		break;
+	case V4L2_PIX_FMT_YVU422M:
 	case V4L2_PIX_FMT_YVU420:
 	case V4L2_PIX_FMT_YVU420M:
 		buf[0][offset] = r_y;
@@ -988,6 +1008,18 @@ static void gen_twopix(struct tpg_data *tpg,
 		buf[1][1] = g_u;
 		break;
 
+	case V4L2_PIX_FMT_YUV444M:
+		buf[0][offset] = r_y;
+		buf[1][offset] = g_u;
+		buf[2][offset] = b_v;
+		break;
+
+	case V4L2_PIX_FMT_YVU444M:
+		buf[0][offset] = r_y;
+		buf[1][offset] = b_v;
+		buf[2][offset] = g_u;
+		break;
+
 	case V4L2_PIX_FMT_NV24:
 		buf[0][offset] = r_y;
 		buf[1][2 * offset] = g_u;
diff --git a/drivers/media/platform/vivid/vivid-tpg.h b/drivers/media/platform/vivid/vivid-tpg.h
index 9baed6a10334..93fbaee69675 100644
--- a/drivers/media/platform/vivid/vivid-tpg.h
+++ b/drivers/media/platform/vivid/vivid-tpg.h
@@ -418,6 +418,8 @@ static inline void tpg_s_bytesperline(struct tpg_data *tpg, unsigned plane, unsi
 
 		tpg->bytesperline[p] = plane_w / tpg->hdownsampling[p];
 	}
+	if (tpg_g_interleaved(tpg))
+		tpg->bytesperline[1] = tpg->bytesperline[0];
 }
 
 
diff --git a/drivers/media/platform/vivid/vivid-vid-common.c b/drivers/media/platform/vivid/vivid-vid-common.c
index 1678b730dba2..b0d4e3a0acf0 100644
--- a/drivers/media/platform/vivid/vivid-vid-common.c
+++ b/drivers/media/platform/vivid/vivid-vid-common.c
@@ -445,6 +445,9 @@ struct vivid_fmt vivid_formats[] = {
 		.planes   = 1,
 		.buffers = 1,
 	},
+
+	/* Multiplanar formats */
+
 	{
 		.fourcc   = V4L2_PIX_FMT_NV16M,
 		.vdownsampling = { 1, 1 },
@@ -495,10 +498,42 @@ struct vivid_fmt vivid_formats[] = {
 		.planes   = 2,
 		.buffers = 2,
 	},
+	{
+		.fourcc   = V4L2_PIX_FMT_YUV422M,
+		.vdownsampling = { 1, 1, 1 },
+		.bit_depth = { 8, 4, 4 },
+		.is_yuv   = true,
+		.planes   = 3,
+		.buffers = 3,
+	},
+	{
+		.fourcc   = V4L2_PIX_FMT_YVU422M,
+		.vdownsampling = { 1, 1, 1 },
+		.bit_depth = { 8, 4, 4 },
+		.is_yuv   = true,
+		.planes   = 3,
+		.buffers = 3,
+	},
+	{
+		.fourcc   = V4L2_PIX_FMT_YUV444M,
+		.vdownsampling = { 1, 1, 1 },
+		.bit_depth = { 8, 8, 8 },
+		.is_yuv   = true,
+		.planes   = 3,
+		.buffers = 3,
+	},
+	{
+		.fourcc   = V4L2_PIX_FMT_YVU444M,
+		.vdownsampling = { 1, 1, 1 },
+		.bit_depth = { 8, 8, 8 },
+		.is_yuv   = true,
+		.planes   = 3,
+		.buffers = 3,
+	},
 };
 
-/* There are 6 multiplanar formats in the list */
-#define VIVID_MPLANAR_FORMATS 6
+/* There are this many multiplanar formats in the list */
+#define VIVID_MPLANAR_FORMATS 10
 
 const struct vivid_fmt *vivid_get_format(struct vivid_dev *dev, u32 pixelformat)
 {
diff --git a/drivers/media/platform/vsp1/Makefile b/drivers/media/platform/vsp1/Makefile
index 6a93f928dfde..95b3ac2ea7ef 100644
--- a/drivers/media/platform/vsp1/Makefile
+++ b/drivers/media/platform/vsp1/Makefile
@@ -1,4 +1,5 @@
-vsp1-y					:= vsp1_drv.o vsp1_entity.o vsp1_video.o
+vsp1-y					:= vsp1_drv.o vsp1_entity.o vsp1_pipe.o
+vsp1-y					+= vsp1_dl.o vsp1_drm.o vsp1_video.o
 vsp1-y					+= vsp1_rpf.o vsp1_rwpf.o vsp1_wpf.o
 vsp1-y					+= vsp1_hsit.o vsp1_lif.o vsp1_lut.o
 vsp1-y					+= vsp1_bru.o vsp1_sru.o vsp1_uds.o
diff --git a/drivers/media/platform/vsp1/vsp1.h b/drivers/media/platform/vsp1/vsp1.h
index 989e96f7e360..910d6b8e8b50 100644
--- a/drivers/media/platform/vsp1/vsp1.h
+++ b/drivers/media/platform/vsp1/vsp1.h
@@ -26,6 +26,9 @@
 struct clk;
 struct device;
 
+struct vsp1_dl;
+struct vsp1_drm;
+struct vsp1_entity;
 struct vsp1_platform_data;
 struct vsp1_bru;
 struct vsp1_hsit;
@@ -42,17 +45,21 @@ struct vsp1_uds;
 #define VSP1_HAS_LIF		(1 << 0)
 #define VSP1_HAS_LUT		(1 << 1)
 #define VSP1_HAS_SRU		(1 << 2)
+#define VSP1_HAS_BRU		(1 << 3)
 
-struct vsp1_platform_data {
+struct vsp1_device_info {
+	u32 version;
 	unsigned int features;
 	unsigned int rpf_count;
 	unsigned int uds_count;
 	unsigned int wpf_count;
+	unsigned int num_bru_inputs;
+	bool uapi;
 };
 
 struct vsp1_device {
 	struct device *dev;
-	struct vsp1_platform_data pdata;
+	const struct vsp1_device_info *info;
 
 	void __iomem *mmio;
 	struct clk *clock;
@@ -71,14 +78,22 @@ struct vsp1_device {
 	struct vsp1_rwpf *wpf[VSP1_MAX_WPF];
 
 	struct list_head entities;
+	struct list_head videos;
 
 	struct v4l2_device v4l2_dev;
 	struct media_device media_dev;
+	struct media_entity_operations media_ops;
+
+	struct vsp1_drm *drm;
+
+	bool use_dl;
 };
 
 int vsp1_device_get(struct vsp1_device *vsp1);
 void vsp1_device_put(struct vsp1_device *vsp1);
 
+int vsp1_reset_wpf(struct vsp1_device *vsp1, unsigned int index);
+
 static inline u32 vsp1_read(struct vsp1_device *vsp1, u32 reg)
 {
 	return ioread32(vsp1->mmio + reg);
@@ -89,4 +104,14 @@ static inline void vsp1_write(struct vsp1_device *vsp1, u32 reg, u32 data)
 	iowrite32(data, vsp1->mmio + reg);
 }
 
+#include "vsp1_dl.h"
+
+static inline void vsp1_mod_write(struct vsp1_entity *e, u32 reg, u32 data)
+{
+	if (e->vsp1->use_dl)
+		vsp1_dl_add(e, reg, data);
+	else
+		vsp1_write(e->vsp1, reg, data);
+}
+
 #endif /* __VSP1_H__ */
diff --git a/drivers/media/platform/vsp1/vsp1_bru.c b/drivers/media/platform/vsp1/vsp1_bru.c
index 7dd763311c0f..cb0dbc15ddad 100644
--- a/drivers/media/platform/vsp1/vsp1_bru.c
+++ b/drivers/media/platform/vsp1/vsp1_bru.c
@@ -19,6 +19,7 @@
 #include "vsp1.h"
 #include "vsp1_bru.h"
 #include "vsp1_rwpf.h"
+#include "vsp1_video.h"
 
 #define BRU_MIN_SIZE				1U
 #define BRU_MAX_SIZE				8190U
@@ -27,14 +28,9 @@
  * Device Access
  */
 
-static inline u32 vsp1_bru_read(struct vsp1_bru *bru, u32 reg)
-{
-	return vsp1_read(bru->entity.vsp1, reg);
-}
-
 static inline void vsp1_bru_write(struct vsp1_bru *bru, u32 reg, u32 data)
 {
-	vsp1_write(bru->entity.vsp1, reg, data);
+	vsp1_mod_write(&bru->entity, reg, data);
 }
 
 /* -----------------------------------------------------------------------------
@@ -83,7 +79,7 @@ static int bru_s_stream(struct v4l2_subdev *subdev, int enable)
 	if (!enable)
 		return 0;
 
-	format = &bru->entity.formats[BRU_PAD_SOURCE];
+	format = &bru->entity.formats[bru->entity.source_pad];
 
 	/* The hardware is extremely flexible but we have no userspace API to
 	 * expose all the parameters, nor is it clear whether we would have use
@@ -94,7 +90,7 @@ static int bru_s_stream(struct v4l2_subdev *subdev, int enable)
 	/* Disable dithering and enable color data normalization unless the
 	 * format at the pipeline output is premultiplied.
 	 */
-	flags = pipe->output ? pipe->output->video.format.flags : 0;
+	flags = pipe->output ? pipe->output->format.flags : 0;
 	vsp1_bru_write(bru, VI6_BRU_INCTRL,
 		       flags & V4L2_PIX_FMT_FLAG_PREMUL_ALPHA ?
 		       0 : VI6_BRU_INCTRL_NRM);
@@ -113,7 +109,7 @@ static int bru_s_stream(struct v4l2_subdev *subdev, int enable)
 		       VI6_BRU_ROP_CROP(VI6_ROP_NOP) |
 		       VI6_BRU_ROP_AROP(VI6_ROP_NOP));
 
-	for (i = 0; i < 4; ++i) {
+	for (i = 0; i < bru->entity.source_pad; ++i) {
 		bool premultiplied = false;
 		u32 ctrl = 0;
 
@@ -125,7 +121,7 @@ static int bru_s_stream(struct v4l2_subdev *subdev, int enable)
 		if (bru->inputs[i].rpf) {
 			ctrl |= VI6_BRU_CTRL_RBC;
 
-			premultiplied = bru->inputs[i].rpf->video.format.flags
+			premultiplied = bru->inputs[i].rpf->format.flags
 				      & V4L2_PIX_FMT_FLAG_PREMUL_ALPHA;
 		} else {
 			ctrl |= VI6_BRU_CTRL_CROP(VI6_ROP_NOP)
@@ -295,7 +291,7 @@ static int bru_set_format(struct v4l2_subdev *subdev, struct v4l2_subdev_pad_con
 	*format = fmt->format;
 
 	/* Reset the compose rectangle */
-	if (fmt->pad != BRU_PAD_SOURCE) {
+	if (fmt->pad != bru->entity.source_pad) {
 		struct v4l2_rect *compose;
 
 		compose = bru_get_compose(bru, cfg, fmt->pad, fmt->which);
@@ -309,7 +305,7 @@ static int bru_set_format(struct v4l2_subdev *subdev, struct v4l2_subdev_pad_con
 	if (fmt->pad == BRU_PAD_SINK(0)) {
 		unsigned int i;
 
-		for (i = 0; i <= BRU_PAD_SOURCE; ++i) {
+		for (i = 0; i <= bru->entity.source_pad; ++i) {
 			format = vsp1_entity_get_pad_format(&bru->entity, cfg,
 							    i, fmt->which);
 			format->code = fmt->format.code;
@@ -325,7 +321,7 @@ static int bru_get_selection(struct v4l2_subdev *subdev,
 {
 	struct vsp1_bru *bru = to_bru(subdev);
 
-	if (sel->pad == BRU_PAD_SOURCE)
+	if (sel->pad == bru->entity.source_pad)
 		return -EINVAL;
 
 	switch (sel->target) {
@@ -353,7 +349,7 @@ static int bru_set_selection(struct v4l2_subdev *subdev,
 	struct v4l2_mbus_framefmt *format;
 	struct v4l2_rect *compose;
 
-	if (sel->pad == BRU_PAD_SOURCE)
+	if (sel->pad == bru->entity.source_pad)
 		return -EINVAL;
 
 	if (sel->target != V4L2_SEL_TGT_COMPOSE)
@@ -362,8 +358,8 @@ static int bru_set_selection(struct v4l2_subdev *subdev,
 	/* The compose rectangle top left corner must be inside the output
 	 * frame.
 	 */
-	format = vsp1_entity_get_pad_format(&bru->entity, cfg, BRU_PAD_SOURCE,
-					    sel->which);
+	format = vsp1_entity_get_pad_format(&bru->entity, cfg,
+					    bru->entity.source_pad, sel->which);
 	sel->r.left = clamp_t(unsigned int, sel->r.left, 0, format->width - 1);
 	sel->r.top = clamp_t(unsigned int, sel->r.top, 0, format->height - 1);
 
@@ -419,7 +415,8 @@ struct vsp1_bru *vsp1_bru_create(struct vsp1_device *vsp1)
 
 	bru->entity.type = VSP1_ENTITY_BRU;
 
-	ret = vsp1_entity_init(vsp1, &bru->entity, 5);
+	ret = vsp1_entity_init(vsp1, &bru->entity,
+			       vsp1->info->num_bru_inputs + 1);
 	if (ret < 0)
 		return ERR_PTR(ret);
 
@@ -427,7 +424,7 @@ struct vsp1_bru *vsp1_bru_create(struct vsp1_device *vsp1)
 	subdev = &bru->entity.subdev;
 	v4l2_subdev_init(subdev, &bru_ops);
 
-	subdev->entity.ops = &vsp1_media_ops;
+	subdev->entity.ops = &vsp1->media_ops;
 	subdev->internal_ops = &vsp1_subdev_internal_ops;
 	snprintf(subdev->name, sizeof(subdev->name), "%s bru",
 		 dev_name(vsp1->dev));
diff --git a/drivers/media/platform/vsp1/vsp1_bru.h b/drivers/media/platform/vsp1/vsp1_bru.h
index 16b1c6554911..dbac9686ea69 100644
--- a/drivers/media/platform/vsp1/vsp1_bru.h
+++ b/drivers/media/platform/vsp1/vsp1_bru.h
@@ -23,7 +23,6 @@ struct vsp1_device;
 struct vsp1_rwpf;
 
 #define BRU_PAD_SINK(n)				(n)
-#define BRU_PAD_SOURCE				4
 
 struct vsp1_bru {
 	struct vsp1_entity entity;
@@ -33,7 +32,7 @@ struct vsp1_bru {
 	struct {
 		struct vsp1_rwpf *rpf;
 		struct v4l2_rect compose;
-	} inputs[4];
+	} inputs[VSP1_MAX_RPF];
 };
 
 static inline struct vsp1_bru *to_bru(struct v4l2_subdev *subdev)
diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c
new file mode 100644
index 000000000000..7dc27ac6bd02
--- /dev/null
+++ b/drivers/media/platform/vsp1/vsp1_dl.c
@@ -0,0 +1,305 @@
+/*
+ * vsp1_dl.h  --  R-Car VSP1 Display List
+ *
+ * Copyright (C) 2015 Renesas Corporation
+ *
+ * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+
+#include "vsp1.h"
+#include "vsp1_dl.h"
+#include "vsp1_pipe.h"
+
+/*
+ * Global resources
+ *
+ * - Display-related interrupts (can be used for vblank evasion ?)
+ * - Display-list enable
+ * - Header-less for WPF0
+ * - DL swap
+ */
+
+#define VSP1_DL_BODY_SIZE		(2 * 4 * 256)
+#define VSP1_DL_NUM_LISTS		3
+
+struct vsp1_dl_entry {
+	u32 addr;
+	u32 data;
+} __attribute__((__packed__));
+
+struct vsp1_dl_list {
+	size_t size;
+	int reg_count;
+
+	bool in_use;
+
+	struct vsp1_dl_entry *body;
+	dma_addr_t dma;
+};
+
+/**
+ * struct vsp1_dl - Display List manager
+ * @vsp1: the VSP1 device
+ * @lock: protects the active, queued and pending lists
+ * @lists.all: array of all allocate display lists
+ * @lists.active: list currently being processed (loaded) by hardware
+ * @lists.queued: list queued to the hardware (written to the DL registers)
+ * @lists.pending: list waiting to be queued to the hardware
+ * @lists.write: list being written to by software
+ */
+struct vsp1_dl {
+	struct vsp1_device *vsp1;
+
+	spinlock_t lock;
+
+	size_t size;
+	dma_addr_t dma;
+	void *mem;
+
+	struct {
+		struct vsp1_dl_list all[VSP1_DL_NUM_LISTS];
+
+		struct vsp1_dl_list *active;
+		struct vsp1_dl_list *queued;
+		struct vsp1_dl_list *pending;
+		struct vsp1_dl_list *write;
+	} lists;
+};
+
+/* -----------------------------------------------------------------------------
+ * Display List Transaction Management
+ */
+
+static void vsp1_dl_free_list(struct vsp1_dl_list *list)
+{
+	if (!list)
+		return;
+
+	list->in_use = false;
+}
+
+void vsp1_dl_reset(struct vsp1_dl *dl)
+{
+	unsigned int i;
+
+	dl->lists.active = NULL;
+	dl->lists.queued = NULL;
+	dl->lists.pending = NULL;
+	dl->lists.write = NULL;
+
+	for (i = 0; i < ARRAY_SIZE(dl->lists.all); ++i)
+		dl->lists.all[i].in_use = false;
+}
+
+void vsp1_dl_begin(struct vsp1_dl *dl)
+{
+	struct vsp1_dl_list *list = NULL;
+	unsigned long flags;
+	unsigned int i;
+
+	spin_lock_irqsave(&dl->lock, flags);
+
+	for (i = 0; i < ARRAY_SIZE(dl->lists.all); ++i) {
+		if (!dl->lists.all[i].in_use) {
+			list = &dl->lists.all[i];
+			break;
+		}
+	}
+
+	if (!list) {
+		list = dl->lists.pending;
+		dl->lists.pending = NULL;
+	}
+
+	spin_unlock_irqrestore(&dl->lock, flags);
+
+	dl->lists.write = list;
+
+	list->in_use = true;
+	list->reg_count = 0;
+}
+
+void vsp1_dl_add(struct vsp1_entity *e, u32 reg, u32 data)
+{
+	struct vsp1_pipeline *pipe = to_vsp1_pipeline(&e->subdev.entity);
+	struct vsp1_dl *dl = pipe->dl;
+	struct vsp1_dl_list *list = dl->lists.write;
+
+	list->body[list->reg_count].addr = reg;
+	list->body[list->reg_count].data = data;
+	list->reg_count++;
+}
+
+void vsp1_dl_commit(struct vsp1_dl *dl)
+{
+	struct vsp1_device *vsp1 = dl->vsp1;
+	struct vsp1_dl_list *list;
+	unsigned long flags;
+	bool update;
+
+	list = dl->lists.write;
+	dl->lists.write = NULL;
+
+	spin_lock_irqsave(&dl->lock, flags);
+
+	/* Once the UPD bit has been set the hardware can start processing the
+	 * display list at any time and we can't touch the address and size
+	 * registers. In that case mark the update as pending, it will be
+	 * queued up to the hardware by the frame end interrupt handler.
+	 */
+	update = !!(vsp1_read(vsp1, VI6_DL_BODY_SIZE) & VI6_DL_BODY_SIZE_UPD);
+	if (update) {
+		vsp1_dl_free_list(dl->lists.pending);
+		dl->lists.pending = list;
+		goto done;
+	}
+
+	/* Program the hardware with the display list body address and size.
+	 * The UPD bit will be cleared by the device when the display list is
+	 * processed.
+	 */
+	vsp1_write(vsp1, VI6_DL_HDR_ADDR(0), list->dma);
+	vsp1_write(vsp1, VI6_DL_BODY_SIZE, VI6_DL_BODY_SIZE_UPD |
+		   (list->reg_count * 8));
+
+	vsp1_dl_free_list(dl->lists.queued);
+	dl->lists.queued = list;
+
+done:
+	spin_unlock_irqrestore(&dl->lock, flags);
+}
+
+/* -----------------------------------------------------------------------------
+ * Interrupt Handling
+ */
+
+void vsp1_dl_irq_display_start(struct vsp1_dl *dl)
+{
+	spin_lock(&dl->lock);
+
+	/* The display start interrupt signals the end of the display list
+	 * processing by the device. The active display list, if any, won't be
+	 * accessed anymore and can be reused.
+	 */
+	if (dl->lists.active) {
+		vsp1_dl_free_list(dl->lists.active);
+		dl->lists.active = NULL;
+	}
+
+	spin_unlock(&dl->lock);
+}
+
+void vsp1_dl_irq_frame_end(struct vsp1_dl *dl)
+{
+	struct vsp1_device *vsp1 = dl->vsp1;
+
+	spin_lock(&dl->lock);
+
+	/* The UPD bit set indicates that the commit operation raced with the
+	 * interrupt and occurred after the frame end event and UPD clear but
+	 * before interrupt processing. The hardware hasn't taken the update
+	 * into account yet, we'll thus skip one frame and retry.
+	 */
+	if (vsp1_read(vsp1, VI6_DL_BODY_SIZE) & VI6_DL_BODY_SIZE_UPD)
+		goto done;
+
+	/* The device starts processing the queued display list right after the
+	 * frame end interrupt. The display list thus becomes active.
+	 */
+	if (dl->lists.queued) {
+		WARN_ON(dl->lists.active);
+		dl->lists.active = dl->lists.queued;
+		dl->lists.queued = NULL;
+	}
+
+	/* Now that the UPD bit has been cleared we can queue the next display
+	 * list to the hardware if one has been prepared.
+	 */
+	if (dl->lists.pending) {
+		struct vsp1_dl_list *list = dl->lists.pending;
+
+		vsp1_write(vsp1, VI6_DL_HDR_ADDR(0), list->dma);
+		vsp1_write(vsp1, VI6_DL_BODY_SIZE, VI6_DL_BODY_SIZE_UPD |
+			   (list->reg_count * 8));
+
+		dl->lists.queued = list;
+		dl->lists.pending = NULL;
+	}
+
+done:
+	spin_unlock(&dl->lock);
+}
+
+/* -----------------------------------------------------------------------------
+ * Hardware Setup
+ */
+
+void vsp1_dl_setup(struct vsp1_device *vsp1)
+{
+	u32 ctrl = (256 << VI6_DL_CTRL_AR_WAIT_SHIFT)
+		 | VI6_DL_CTRL_DC2 | VI6_DL_CTRL_DC1 | VI6_DL_CTRL_DC0
+		 | VI6_DL_CTRL_DLE;
+
+	/* The DRM pipeline operates with header-less display lists in
+	 * Continuous Frame Mode.
+	 */
+	if (vsp1->drm)
+		ctrl |= VI6_DL_CTRL_CFM0 | VI6_DL_CTRL_NH0;
+
+	vsp1_write(vsp1, VI6_DL_CTRL, ctrl);
+	vsp1_write(vsp1, VI6_DL_SWAP, VI6_DL_SWAP_LWS);
+}
+
+/* -----------------------------------------------------------------------------
+ * Initialization and Cleanup
+ */
+
+struct vsp1_dl *vsp1_dl_create(struct vsp1_device *vsp1)
+{
+	struct vsp1_dl *dl;
+	unsigned int i;
+
+	dl = kzalloc(sizeof(*dl), GFP_KERNEL);
+	if (!dl)
+		return NULL;
+
+	spin_lock_init(&dl->lock);
+
+	dl->vsp1 = vsp1;
+	dl->size = VSP1_DL_BODY_SIZE * ARRAY_SIZE(dl->lists.all);
+
+	dl->mem = dma_alloc_writecombine(vsp1->dev, dl->size, &dl->dma,
+					 GFP_KERNEL);
+	if (!dl->mem) {
+		kfree(dl);
+		return NULL;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(dl->lists.all); ++i) {
+		struct vsp1_dl_list *list = &dl->lists.all[i];
+
+		list->size = VSP1_DL_BODY_SIZE;
+		list->reg_count = 0;
+		list->in_use = false;
+		list->dma = dl->dma + VSP1_DL_BODY_SIZE * i;
+		list->body = dl->mem + VSP1_DL_BODY_SIZE * i;
+	}
+
+	return dl;
+}
+
+void vsp1_dl_destroy(struct vsp1_dl *dl)
+{
+	dma_free_writecombine(dl->vsp1->dev, dl->size, dl->mem, dl->dma);
+	kfree(dl);
+}
diff --git a/drivers/media/platform/vsp1/vsp1_dl.h b/drivers/media/platform/vsp1/vsp1_dl.h
new file mode 100644
index 000000000000..448c4250e54c
--- /dev/null
+++ b/drivers/media/platform/vsp1/vsp1_dl.h
@@ -0,0 +1,42 @@
+/*
+ * vsp1_dl.h  --  R-Car VSP1 Display List
+ *
+ * Copyright (C) 2015 Renesas Corporation
+ *
+ * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#ifndef __VSP1_DL_H__
+#define __VSP1_DL_H__
+
+#include "vsp1_entity.h"
+
+struct vsp1_device;
+struct vsp1_dl;
+
+struct vsp1_dl *vsp1_dl_create(struct vsp1_device *vsp1);
+void vsp1_dl_destroy(struct vsp1_dl *dl);
+
+void vsp1_dl_setup(struct vsp1_device *vsp1);
+
+void vsp1_dl_reset(struct vsp1_dl *dl);
+void vsp1_dl_begin(struct vsp1_dl *dl);
+void vsp1_dl_add(struct vsp1_entity *e, u32 reg, u32 data);
+void vsp1_dl_commit(struct vsp1_dl *dl);
+
+void vsp1_dl_irq_display_start(struct vsp1_dl *dl);
+void vsp1_dl_irq_frame_end(struct vsp1_dl *dl);
+
+static inline void vsp1_dl_mod_write(struct vsp1_entity *e, u32 reg, u32 data)
+{
+	if (e->vsp1->use_dl)
+		vsp1_dl_add(e, reg, data);
+	else
+		vsp1_write(e->vsp1, reg, data);
+}
+
+#endif /* __VSP1_DL_H__ */
diff --git a/drivers/media/platform/vsp1/vsp1_drm.c b/drivers/media/platform/vsp1/vsp1_drm.c
new file mode 100644
index 000000000000..021fe5778cd1
--- /dev/null
+++ b/drivers/media/platform/vsp1/vsp1_drm.c
@@ -0,0 +1,597 @@
+/*
+ * vsp1_drm.c  --  R-Car VSP1 DRM API
+ *
+ * Copyright (C) 2015 Renesas Electronics Corporation
+ *
+ * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/vsp1.h>
+
+#include <media/media-entity.h>
+#include <media/v4l2-subdev.h>
+
+#include "vsp1.h"
+#include "vsp1_bru.h"
+#include "vsp1_dl.h"
+#include "vsp1_drm.h"
+#include "vsp1_lif.h"
+#include "vsp1_pipe.h"
+#include "vsp1_rwpf.h"
+
+/* -----------------------------------------------------------------------------
+ * Runtime Handling
+ */
+
+static void vsp1_drm_pipeline_frame_end(struct vsp1_pipeline *pipe)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&pipe->irqlock, flags);
+	if (pipe->num_inputs)
+		vsp1_pipeline_run(pipe);
+	spin_unlock_irqrestore(&pipe->irqlock, flags);
+}
+
+/* -----------------------------------------------------------------------------
+ * DU Driver API
+ */
+
+int vsp1_du_init(struct device *dev)
+{
+	struct vsp1_device *vsp1 = dev_get_drvdata(dev);
+
+	if (!vsp1)
+		return -EPROBE_DEFER;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vsp1_du_init);
+
+/**
+ * vsp1_du_setup_lif - Setup the output part of the VSP pipeline
+ * @dev: the VSP device
+ * @width: output frame width in pixels
+ * @height: output frame height in pixels
+ *
+ * Configure the output part of VSP DRM pipeline for the given frame @width and
+ * @height. This sets up formats on the BRU source pad, the WPF0 sink and source
+ * pads, and the LIF sink pad.
+ *
+ * As the media bus code on the BRU source pad is conditioned by the
+ * configuration of the BRU sink 0 pad, we also set up the formats on all BRU
+ * sinks, even if the configuration will be overwritten later by
+ * vsp1_du_setup_rpf(). This ensures that the BRU configuration is set to a well
+ * defined state.
+ *
+ * Return 0 on success or a negative error code on failure.
+ */
+int vsp1_du_setup_lif(struct device *dev, unsigned int width,
+		      unsigned int height)
+{
+	struct vsp1_device *vsp1 = dev_get_drvdata(dev);
+	struct vsp1_pipeline *pipe = &vsp1->drm->pipe;
+	struct vsp1_bru *bru = vsp1->bru;
+	struct v4l2_subdev_format format;
+	unsigned int i;
+	int ret;
+
+	dev_dbg(vsp1->dev, "%s: configuring LIF with format %ux%u\n",
+		__func__, width, height);
+
+	if (width == 0 || height == 0) {
+		/* Zero width or height means the CRTC is being disabled, stop
+		 * the pipeline and turn the light off.
+		 */
+		ret = vsp1_pipeline_stop(pipe);
+		if (ret == -ETIMEDOUT)
+			dev_err(vsp1->dev, "DRM pipeline stop timeout\n");
+
+		media_entity_pipeline_stop(&pipe->output->entity.subdev.entity);
+
+		for (i = 0; i < bru->entity.source_pad; ++i) {
+			bru->inputs[i].rpf = NULL;
+			pipe->inputs[i] = NULL;
+		}
+
+		pipe->num_inputs = 0;
+
+		vsp1_device_put(vsp1);
+
+		dev_dbg(vsp1->dev, "%s: pipeline disabled\n", __func__);
+
+		return 0;
+	}
+
+	vsp1_dl_reset(vsp1->drm->dl);
+
+	/* Configure the format at the BRU sinks and propagate it through the
+	 * pipeline.
+	 */
+	memset(&format, 0, sizeof(format));
+	format.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+
+	for (i = 0; i < bru->entity.source_pad; ++i) {
+		format.pad = i;
+
+		format.format.width = width;
+		format.format.height = height;
+		format.format.code = MEDIA_BUS_FMT_ARGB8888_1X32;
+		format.format.field = V4L2_FIELD_NONE;
+
+		ret = v4l2_subdev_call(&bru->entity.subdev, pad,
+				       set_fmt, NULL, &format);
+		if (ret < 0)
+			return ret;
+
+		dev_dbg(vsp1->dev, "%s: set format %ux%u (%x) on BRU pad %u\n",
+			__func__, format.format.width, format.format.height,
+			format.format.code, i);
+	}
+
+	format.pad = bru->entity.source_pad;
+	format.format.width = width;
+	format.format.height = height;
+	format.format.code = MEDIA_BUS_FMT_ARGB8888_1X32;
+	format.format.field = V4L2_FIELD_NONE;
+
+	ret = v4l2_subdev_call(&bru->entity.subdev, pad, set_fmt, NULL,
+			       &format);
+	if (ret < 0)
+		return ret;
+
+	dev_dbg(vsp1->dev, "%s: set format %ux%u (%x) on BRU pad %u\n",
+		__func__, format.format.width, format.format.height,
+		format.format.code, i);
+
+	format.pad = RWPF_PAD_SINK;
+	ret = v4l2_subdev_call(&vsp1->wpf[0]->entity.subdev, pad, set_fmt, NULL,
+			       &format);
+	if (ret < 0)
+		return ret;
+
+	dev_dbg(vsp1->dev, "%s: set format %ux%u (%x) on WPF0 sink\n",
+		__func__, format.format.width, format.format.height,
+		format.format.code);
+
+	format.pad = RWPF_PAD_SOURCE;
+	ret = v4l2_subdev_call(&vsp1->wpf[0]->entity.subdev, pad, get_fmt, NULL,
+			       &format);
+	if (ret < 0)
+		return ret;
+
+	dev_dbg(vsp1->dev, "%s: got format %ux%u (%x) on WPF0 source\n",
+		__func__, format.format.width, format.format.height,
+		format.format.code);
+
+	format.pad = LIF_PAD_SINK;
+	ret = v4l2_subdev_call(&vsp1->lif->entity.subdev, pad, set_fmt, NULL,
+			       &format);
+	if (ret < 0)
+		return ret;
+
+	dev_dbg(vsp1->dev, "%s: set format %ux%u (%x) on LIF sink\n",
+		__func__, format.format.width, format.format.height,
+		format.format.code);
+
+	/* Verify that the format at the output of the pipeline matches the
+	 * requested frame size and media bus code.
+	 */
+	if (format.format.width != width || format.format.height != height ||
+	    format.format.code != MEDIA_BUS_FMT_ARGB8888_1X32) {
+		dev_dbg(vsp1->dev, "%s: format mismatch\n", __func__);
+		return -EPIPE;
+	}
+
+	/* Mark the pipeline as streaming and enable the VSP1. This will store
+	 * the pipeline pointer in all entities, which the s_stream handlers
+	 * will need. We don't start the entities themselves right at this point
+	 * as there's no plane configured yet, so we can't start processing
+	 * buffers.
+	 */
+	ret = vsp1_device_get(vsp1);
+	if (ret < 0)
+		return ret;
+
+	ret = media_entity_pipeline_start(&pipe->output->entity.subdev.entity,
+					  &pipe->pipe);
+	if (ret < 0) {
+		dev_dbg(vsp1->dev, "%s: pipeline start failed\n", __func__);
+		vsp1_device_put(vsp1);
+		return ret;
+	}
+
+	dev_dbg(vsp1->dev, "%s: pipeline enabled\n", __func__);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vsp1_du_setup_lif);
+
+/**
+ * vsp1_du_atomic_begin - Prepare for an atomic update
+ * @dev: the VSP device
+ */
+void vsp1_du_atomic_begin(struct device *dev)
+{
+	struct vsp1_device *vsp1 = dev_get_drvdata(dev);
+	struct vsp1_pipeline *pipe = &vsp1->drm->pipe;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pipe->irqlock, flags);
+
+	vsp1->drm->num_inputs = pipe->num_inputs;
+
+	spin_unlock_irqrestore(&pipe->irqlock, flags);
+
+	/* Prepare the display list. */
+	vsp1_dl_begin(vsp1->drm->dl);
+}
+EXPORT_SYMBOL_GPL(vsp1_du_atomic_begin);
+
+/**
+ * vsp1_du_atomic_update - Setup one RPF input of the VSP pipeline
+ * @dev: the VSP device
+ * @rpf_index: index of the RPF to setup (0-based)
+ * @pixelformat: V4L2 pixel format for the RPF memory input
+ * @pitch: number of bytes per line in the image stored in memory
+ * @mem: DMA addresses of the memory buffers (one per plane)
+ * @src: the source crop rectangle for the RPF
+ * @dst: the destination compose rectangle for the BRU input
+ *
+ * Configure the VSP to perform composition of the image referenced by @mem
+ * through RPF @rpf_index, using the @src crop rectangle and the @dst
+ * composition rectangle. The Z-order is fixed with RPF 0 at the bottom.
+ *
+ * Image format as stored in memory is expressed as a V4L2 @pixelformat value.
+ * As a special case, setting the pixel format to 0 will disable the RPF. The
+ * @pitch, @mem, @src and @dst parameters are ignored in that case. Calling the
+ * function on a disabled RPF is allowed.
+ *
+ * The memory pitch is configurable to allow for padding at end of lines, or
+ * simple for images that extend beyond the crop rectangle boundaries. The
+ * @pitch value is expressed in bytes and applies to all planes for multiplanar
+ * formats.
+ *
+ * The source memory buffer is referenced by the DMA address of its planes in
+ * the @mem array. Up to two planes are supported. The second plane DMA address
+ * is ignored for formats using a single plane.
+ *
+ * This function isn't reentrant, the caller needs to serialize calls.
+ *
+ * TODO: Implement Z-order control by decoupling the RPF index from the BRU
+ * input index.
+ *
+ * Return 0 on success or a negative error code on failure.
+ */
+int vsp1_du_atomic_update(struct device *dev, unsigned int rpf_index,
+			  u32 pixelformat, unsigned int pitch,
+			  dma_addr_t mem[2], const struct v4l2_rect *src,
+			  const struct v4l2_rect *dst)
+{
+	struct vsp1_device *vsp1 = dev_get_drvdata(dev);
+	struct vsp1_pipeline *pipe = &vsp1->drm->pipe;
+	const struct vsp1_format_info *fmtinfo;
+	struct v4l2_subdev_selection sel;
+	struct v4l2_subdev_format format;
+	struct vsp1_rwpf_memory memory;
+	struct vsp1_rwpf *rpf;
+	unsigned long flags;
+	int ret;
+
+	if (rpf_index >= vsp1->info->rpf_count)
+		return -EINVAL;
+
+	rpf = vsp1->rpf[rpf_index];
+
+	if (pixelformat == 0) {
+		dev_dbg(vsp1->dev, "%s: RPF%u: disable requested\n", __func__,
+			rpf_index);
+
+		spin_lock_irqsave(&pipe->irqlock, flags);
+
+		if (pipe->inputs[rpf_index]) {
+			/* Remove the RPF from the pipeline if it was previously
+			 * enabled.
+			 */
+			vsp1->bru->inputs[rpf_index].rpf = NULL;
+			pipe->inputs[rpf_index] = NULL;
+
+			pipe->num_inputs--;
+		}
+
+		spin_unlock_irqrestore(&pipe->irqlock, flags);
+
+		return 0;
+	}
+
+	dev_dbg(vsp1->dev,
+		"%s: RPF%u: (%u,%u)/%ux%u -> (%u,%u)/%ux%u (%08x), pitch %u dma { %pad, %pad }\n",
+		__func__, rpf_index,
+		src->left, src->top, src->width, src->height,
+		dst->left, dst->top, dst->width, dst->height,
+		pixelformat, pitch, &mem[0], &mem[1]);
+
+	/* Set the stride at the RPF input. */
+	fmtinfo = vsp1_get_format_info(pixelformat);
+	if (!fmtinfo) {
+		dev_dbg(vsp1->dev, "Unsupport pixel format %08x for RPF\n",
+			pixelformat);
+		return -EINVAL;
+	}
+
+	rpf->fmtinfo = fmtinfo;
+	rpf->format.num_planes = fmtinfo->planes;
+	rpf->format.plane_fmt[0].bytesperline = pitch;
+	rpf->format.plane_fmt[1].bytesperline = pitch;
+
+	/* Configure the format on the RPF sink pad and propagate it up to the
+	 * BRU sink pad.
+	 */
+	memset(&format, 0, sizeof(format));
+	format.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+	format.pad = RWPF_PAD_SINK;
+	format.format.width = src->width + src->left;
+	format.format.height = src->height + src->top;
+	format.format.code = fmtinfo->mbus;
+	format.format.field = V4L2_FIELD_NONE;
+
+	ret = v4l2_subdev_call(&rpf->entity.subdev, pad, set_fmt, NULL,
+			       &format);
+	if (ret < 0)
+		return ret;
+
+	dev_dbg(vsp1->dev,
+		"%s: set format %ux%u (%x) on RPF%u sink\n",
+		__func__, format.format.width, format.format.height,
+		format.format.code, rpf->entity.index);
+
+	memset(&sel, 0, sizeof(sel));
+	sel.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+	sel.pad = RWPF_PAD_SINK;
+	sel.target = V4L2_SEL_TGT_CROP;
+	sel.r = *src;
+
+	ret = v4l2_subdev_call(&rpf->entity.subdev, pad, set_selection, NULL,
+			       &sel);
+	if (ret < 0)
+		return ret;
+
+	dev_dbg(vsp1->dev,
+		"%s: set selection (%u,%u)/%ux%u on RPF%u sink\n",
+		__func__, sel.r.left, sel.r.top, sel.r.width, sel.r.height,
+		rpf->entity.index);
+
+	/* RPF source, hardcode the format to ARGB8888 to turn on format
+	 * conversion if needed.
+	 */
+	format.pad = RWPF_PAD_SOURCE;
+
+	ret = v4l2_subdev_call(&rpf->entity.subdev, pad, get_fmt, NULL,
+			       &format);
+	if (ret < 0)
+		return ret;
+
+	dev_dbg(vsp1->dev,
+		"%s: got format %ux%u (%x) on RPF%u source\n",
+		__func__, format.format.width, format.format.height,
+		format.format.code, rpf->entity.index);
+
+	format.format.code = MEDIA_BUS_FMT_ARGB8888_1X32;
+
+	ret = v4l2_subdev_call(&rpf->entity.subdev, pad, set_fmt, NULL,
+			       &format);
+	if (ret < 0)
+		return ret;
+
+	/* BRU sink, propagate the format from the RPF source. */
+	format.pad = rpf->entity.index;
+
+	ret = v4l2_subdev_call(&vsp1->bru->entity.subdev, pad, set_fmt, NULL,
+			       &format);
+	if (ret < 0)
+		return ret;
+
+	dev_dbg(vsp1->dev, "%s: set format %ux%u (%x) on BRU pad %u\n",
+		__func__, format.format.width, format.format.height,
+		format.format.code, format.pad);
+
+	sel.pad = rpf->entity.index;
+	sel.target = V4L2_SEL_TGT_COMPOSE;
+	sel.r = *dst;
+
+	ret = v4l2_subdev_call(&vsp1->bru->entity.subdev, pad, set_selection,
+			       NULL, &sel);
+	if (ret < 0)
+		return ret;
+
+	dev_dbg(vsp1->dev,
+		"%s: set selection (%u,%u)/%ux%u on BRU pad %u\n",
+		__func__, sel.r.left, sel.r.top, sel.r.width, sel.r.height,
+		sel.pad);
+
+	/* Store the compose rectangle coordinates in the RPF. */
+	rpf->location.left = dst->left;
+	rpf->location.top = dst->top;
+
+	/* Set the memory buffer address. */
+	memory.num_planes = fmtinfo->planes;
+	memory.addr[0] = mem[0];
+	memory.addr[1] = mem[1];
+
+	rpf->ops->set_memory(rpf, &memory);
+
+	spin_lock_irqsave(&pipe->irqlock, flags);
+
+	/* If the RPF was previously stopped set the BRU input to the RPF and
+	 * store the RPF in the pipeline inputs array.
+	 */
+	if (!pipe->inputs[rpf->entity.index]) {
+		vsp1->bru->inputs[rpf_index].rpf = rpf;
+		pipe->inputs[rpf->entity.index] = rpf;
+		pipe->num_inputs++;
+	}
+
+	spin_unlock_irqrestore(&pipe->irqlock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vsp1_du_atomic_update);
+
+/**
+ * vsp1_du_atomic_flush - Commit an atomic update
+ * @dev: the VSP device
+ */
+void vsp1_du_atomic_flush(struct device *dev)
+{
+	struct vsp1_device *vsp1 = dev_get_drvdata(dev);
+	struct vsp1_pipeline *pipe = &vsp1->drm->pipe;
+	struct vsp1_entity *entity;
+	unsigned long flags;
+	bool stop = false;
+	int ret;
+
+	list_for_each_entry(entity, &pipe->entities, list_pipe) {
+		/* Disconnect unused RPFs from the pipeline. */
+		if (entity->type == VSP1_ENTITY_RPF) {
+			struct vsp1_rwpf *rpf = to_rwpf(&entity->subdev);
+
+			if (!pipe->inputs[rpf->entity.index]) {
+				vsp1_mod_write(entity, entity->route->reg,
+					   VI6_DPR_NODE_UNUSED);
+				continue;
+			}
+		}
+
+		vsp1_entity_route_setup(entity);
+
+		ret = v4l2_subdev_call(&entity->subdev, video,
+				       s_stream, 1);
+		if (ret < 0) {
+			dev_err(vsp1->dev,
+				"DRM pipeline start failure on entity %s\n",
+				entity->subdev.name);
+			return;
+		}
+	}
+
+	vsp1_dl_commit(vsp1->drm->dl);
+
+	spin_lock_irqsave(&pipe->irqlock, flags);
+
+	/* Start or stop the pipeline if needed. */
+	if (!vsp1->drm->num_inputs && pipe->num_inputs) {
+		vsp1_write(vsp1, VI6_DISP_IRQ_STA, 0);
+		vsp1_write(vsp1, VI6_DISP_IRQ_ENB, VI6_DISP_IRQ_ENB_DSTE);
+		vsp1_pipeline_run(pipe);
+	} else if (vsp1->drm->num_inputs && !pipe->num_inputs) {
+		stop = true;
+	}
+
+	spin_unlock_irqrestore(&pipe->irqlock, flags);
+
+	if (stop) {
+		vsp1_write(vsp1, VI6_DISP_IRQ_ENB, 0);
+		vsp1_pipeline_stop(pipe);
+	}
+}
+EXPORT_SYMBOL_GPL(vsp1_du_atomic_flush);
+
+/* -----------------------------------------------------------------------------
+ * Initialization
+ */
+
+int vsp1_drm_create_links(struct vsp1_device *vsp1)
+{
+	const u32 flags = MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_IMMUTABLE;
+	unsigned int i;
+	int ret;
+
+	/* VSPD instances require a BRU to perform composition and a LIF to
+	 * output to the DU.
+	 */
+	if (!vsp1->bru || !vsp1->lif)
+		return -ENXIO;
+
+	for (i = 0; i < vsp1->info->rpf_count; ++i) {
+		struct vsp1_rwpf *rpf = vsp1->rpf[i];
+
+		ret = media_create_pad_link(&rpf->entity.subdev.entity,
+					    RWPF_PAD_SOURCE,
+					    &vsp1->bru->entity.subdev.entity,
+					    i, flags);
+		if (ret < 0)
+			return ret;
+
+		rpf->entity.sink = &vsp1->bru->entity.subdev.entity;
+		rpf->entity.sink_pad = i;
+	}
+
+	ret = media_create_pad_link(&vsp1->bru->entity.subdev.entity,
+				    vsp1->bru->entity.source_pad,
+				    &vsp1->wpf[0]->entity.subdev.entity,
+				    RWPF_PAD_SINK, flags);
+	if (ret < 0)
+		return ret;
+
+	vsp1->bru->entity.sink = &vsp1->wpf[0]->entity.subdev.entity;
+	vsp1->bru->entity.sink_pad = RWPF_PAD_SINK;
+
+	ret = media_create_pad_link(&vsp1->wpf[0]->entity.subdev.entity,
+				    RWPF_PAD_SOURCE,
+				    &vsp1->lif->entity.subdev.entity,
+				    LIF_PAD_SINK, flags);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+int vsp1_drm_init(struct vsp1_device *vsp1)
+{
+	struct vsp1_pipeline *pipe;
+	unsigned int i;
+
+	vsp1->drm = devm_kzalloc(vsp1->dev, sizeof(*vsp1->drm), GFP_KERNEL);
+	if (!vsp1->drm)
+		return -ENOMEM;
+
+	vsp1->drm->dl = vsp1_dl_create(vsp1);
+	if (!vsp1->drm->dl)
+		return -ENOMEM;
+
+	pipe = &vsp1->drm->pipe;
+
+	vsp1_pipeline_init(pipe);
+	pipe->frame_end = vsp1_drm_pipeline_frame_end;
+
+	/* The DRM pipeline is static, add entities manually. */
+	for (i = 0; i < vsp1->info->rpf_count; ++i) {
+		struct vsp1_rwpf *input = vsp1->rpf[i];
+
+		list_add_tail(&input->entity.list_pipe, &pipe->entities);
+	}
+
+	list_add_tail(&vsp1->bru->entity.list_pipe, &pipe->entities);
+	list_add_tail(&vsp1->wpf[0]->entity.list_pipe, &pipe->entities);
+	list_add_tail(&vsp1->lif->entity.list_pipe, &pipe->entities);
+
+	pipe->bru = &vsp1->bru->entity;
+	pipe->lif = &vsp1->lif->entity;
+	pipe->output = vsp1->wpf[0];
+
+	pipe->dl = vsp1->drm->dl;
+
+	return 0;
+}
+
+void vsp1_drm_cleanup(struct vsp1_device *vsp1)
+{
+	vsp1_dl_destroy(vsp1->drm->dl);
+}
diff --git a/drivers/media/platform/vsp1/vsp1_drm.h b/drivers/media/platform/vsp1/vsp1_drm.h
new file mode 100644
index 000000000000..f68056838319
--- /dev/null
+++ b/drivers/media/platform/vsp1/vsp1_drm.h
@@ -0,0 +1,49 @@
+/*
+ * vsp1_drm.h  --  R-Car VSP1 DRM/KMS Interface
+ *
+ * Copyright (C) 2015 Renesas Electronics Corporation
+ *
+ * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#ifndef __VSP1_DRM_H__
+#define __VSP1_DRM_H__
+
+#include "vsp1_pipe.h"
+
+struct vsp1_dl;
+
+/**
+ * vsp1_drm - State for the API exposed to the DRM driver
+ * @dl: display list for DRM pipeline operation
+ * @pipe: the VSP1 pipeline used for display
+ * @num_inputs: number of active pipeline inputs at the beginning of an update
+ * @update: the pipeline configuration has been updated
+ */
+struct vsp1_drm {
+	struct vsp1_dl *dl;
+	struct vsp1_pipeline pipe;
+	unsigned int num_inputs;
+	bool update;
+};
+
+int vsp1_drm_init(struct vsp1_device *vsp1);
+void vsp1_drm_cleanup(struct vsp1_device *vsp1);
+int vsp1_drm_create_links(struct vsp1_device *vsp1);
+
+int vsp1_du_init(struct device *dev);
+int vsp1_du_setup_lif(struct device *dev, unsigned int width,
+		      unsigned int height);
+void vsp1_du_atomic_begin(struct device *dev);
+int vsp1_du_atomic_update(struct device *dev, unsigned int rpf_index,
+			  u32 pixelformat, unsigned int pitch,
+			  dma_addr_t mem[2], const struct v4l2_rect *src,
+			  const struct v4l2_rect *dst);
+void vsp1_du_atomic_flush(struct device *dev);
+
+
+#endif /* __VSP1_DRM_H__ */
diff --git a/drivers/media/platform/vsp1/vsp1_drv.c b/drivers/media/platform/vsp1/vsp1_drv.c
index 533bc796391e..25750a0e4631 100644
--- a/drivers/media/platform/vsp1/vsp1_drv.c
+++ b/drivers/media/platform/vsp1/vsp1_drv.c
@@ -17,17 +17,23 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/videodev2.h>
 
+#include <media/v4l2-subdev.h>
+
 #include "vsp1.h"
 #include "vsp1_bru.h"
+#include "vsp1_dl.h"
+#include "vsp1_drm.h"
 #include "vsp1_hsit.h"
 #include "vsp1_lif.h"
 #include "vsp1_lut.h"
 #include "vsp1_rwpf.h"
 #include "vsp1_sru.h"
 #include "vsp1_uds.h"
+#include "vsp1_video.h"
 
 /* -----------------------------------------------------------------------------
  * Interrupt Handling
@@ -39,11 +45,11 @@ static irqreturn_t vsp1_irq_handler(int irq, void *data)
 	struct vsp1_device *vsp1 = data;
 	irqreturn_t ret = IRQ_NONE;
 	unsigned int i;
+	u32 status;
 
-	for (i = 0; i < vsp1->pdata.wpf_count; ++i) {
+	for (i = 0; i < vsp1->info->wpf_count; ++i) {
 		struct vsp1_rwpf *wpf = vsp1->wpf[i];
 		struct vsp1_pipeline *pipe;
-		u32 status;
 
 		if (wpf == NULL)
 			continue;
@@ -58,6 +64,21 @@ static irqreturn_t vsp1_irq_handler(int irq, void *data)
 		}
 	}
 
+	status = vsp1_read(vsp1, VI6_DISP_IRQ_STA);
+	vsp1_write(vsp1, VI6_DISP_IRQ_STA, ~status & VI6_DISP_IRQ_STA_DST);
+
+	if (status & VI6_DISP_IRQ_STA_DST) {
+		struct vsp1_rwpf *wpf = vsp1->wpf[0];
+		struct vsp1_pipeline *pipe;
+
+		if (wpf) {
+			pipe = to_vsp1_pipeline(&wpf->entity.subdev.entity);
+			vsp1_pipeline_display_start(pipe);
+		}
+
+		ret = IRQ_HANDLED;
+	}
+
 	return ret;
 }
 
@@ -66,7 +87,7 @@ static irqreturn_t vsp1_irq_handler(int irq, void *data)
  */
 
 /*
- * vsp1_create_links - Create links from all sources to the given sink
+ * vsp1_create_sink_links - Create links from all sources to the given sink
  *
  * This function creates media links from all valid sources to the given sink
  * pad. Links that would be invalid according to the VSP1 hardware capabilities
@@ -75,7 +96,8 @@ static irqreturn_t vsp1_irq_handler(int irq, void *data)
  * - from a UDS to a UDS (UDS entities can't be chained)
  * - from an entity to itself (no loops are allowed)
  */
-static int vsp1_create_links(struct vsp1_device *vsp1, struct vsp1_entity *sink)
+static int vsp1_create_sink_links(struct vsp1_device *vsp1,
+				  struct vsp1_entity *sink)
 {
 	struct media_entity *entity = &sink->subdev.entity;
 	struct vsp1_entity *source;
@@ -115,19 +137,86 @@ static int vsp1_create_links(struct vsp1_device *vsp1, struct vsp1_entity *sink)
 	return 0;
 }
 
-static void vsp1_destroy_entities(struct vsp1_device *vsp1)
+static int vsp1_uapi_create_links(struct vsp1_device *vsp1)
 {
 	struct vsp1_entity *entity;
-	struct vsp1_entity *next;
+	unsigned int i;
+	int ret;
+
+	list_for_each_entry(entity, &vsp1->entities, list_dev) {
+		if (entity->type == VSP1_ENTITY_LIF ||
+		    entity->type == VSP1_ENTITY_RPF)
+			continue;
+
+		ret = vsp1_create_sink_links(vsp1, entity);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (vsp1->info->features & VSP1_HAS_LIF) {
+		ret = media_create_pad_link(&vsp1->wpf[0]->entity.subdev.entity,
+					    RWPF_PAD_SOURCE,
+					    &vsp1->lif->entity.subdev.entity,
+					    LIF_PAD_SINK, 0);
+		if (ret < 0)
+			return ret;
+	}
+
+	for (i = 0; i < vsp1->info->rpf_count; ++i) {
+		struct vsp1_rwpf *rpf = vsp1->rpf[i];
 
-	list_for_each_entry_safe(entity, next, &vsp1->entities, list_dev) {
+		ret = media_create_pad_link(&rpf->video->video.entity, 0,
+					    &rpf->entity.subdev.entity,
+					    RWPF_PAD_SINK,
+					    MEDIA_LNK_FL_ENABLED |
+					    MEDIA_LNK_FL_IMMUTABLE);
+		if (ret < 0)
+			return ret;
+	}
+
+	for (i = 0; i < vsp1->info->wpf_count; ++i) {
+		/* Connect the video device to the WPF. All connections are
+		 * immutable except for the WPF0 source link if a LIF is
+		 * present.
+		 */
+		struct vsp1_rwpf *wpf = vsp1->wpf[i];
+		unsigned int flags = MEDIA_LNK_FL_ENABLED;
+
+		if (!(vsp1->info->features & VSP1_HAS_LIF) || i != 0)
+			flags |= MEDIA_LNK_FL_IMMUTABLE;
+
+		ret = media_create_pad_link(&wpf->entity.subdev.entity,
+					    RWPF_PAD_SOURCE,
+					    &wpf->video->video.entity, 0,
+					    flags);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void vsp1_destroy_entities(struct vsp1_device *vsp1)
+{
+	struct vsp1_entity *entity, *_entity;
+	struct vsp1_video *video, *_video;
+
+	list_for_each_entry_safe(entity, _entity, &vsp1->entities, list_dev) {
 		list_del(&entity->list_dev);
 		vsp1_entity_destroy(entity);
 	}
 
+	list_for_each_entry_safe(video, _video, &vsp1->videos, list) {
+		list_del(&video->list);
+		vsp1_video_cleanup(video);
+	}
+
 	v4l2_device_unregister(&vsp1->v4l2_dev);
 	media_device_unregister(&vsp1->media_dev);
 	media_device_cleanup(&vsp1->media_dev);
+
+	if (!vsp1->info->uapi)
+		vsp1_drm_cleanup(vsp1);
 }
 
 static int vsp1_create_entities(struct vsp1_device *vsp1)
@@ -144,6 +233,14 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		 dev_name(mdev->dev));
 	media_device_init(mdev);
 
+	vsp1->media_ops.link_setup = vsp1_entity_link_setup;
+	/* Don't perform link validation when the userspace API is disabled as
+	 * the pipeline is configured internally by the driver in that case, and
+	 * its configuration can thus be trusted.
+	 */
+	if (vsp1->info->uapi)
+		vsp1->media_ops.link_validate = v4l2_subdev_link_validate;
+
 	vdev->mdev = mdev;
 	ret = v4l2_device_register(vsp1->dev, vdev);
 	if (ret < 0) {
@@ -153,13 +250,15 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 	}
 
 	/* Instantiate all the entities. */
-	vsp1->bru = vsp1_bru_create(vsp1);
-	if (IS_ERR(vsp1->bru)) {
-		ret = PTR_ERR(vsp1->bru);
-		goto done;
-	}
+	if (vsp1->info->features & VSP1_HAS_BRU) {
+		vsp1->bru = vsp1_bru_create(vsp1);
+		if (IS_ERR(vsp1->bru)) {
+			ret = PTR_ERR(vsp1->bru);
+			goto done;
+		}
 
-	list_add_tail(&vsp1->bru->entity.list_dev, &vsp1->entities);
+		list_add_tail(&vsp1->bru->entity.list_dev, &vsp1->entities);
+	}
 
 	vsp1->hsi = vsp1_hsit_create(vsp1, true);
 	if (IS_ERR(vsp1->hsi)) {
@@ -177,7 +276,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 
 	list_add_tail(&vsp1->hst->entity.list_dev, &vsp1->entities);
 
-	if (vsp1->pdata.features & VSP1_HAS_LIF) {
+	if (vsp1->info->features & VSP1_HAS_LIF) {
 		vsp1->lif = vsp1_lif_create(vsp1);
 		if (IS_ERR(vsp1->lif)) {
 			ret = PTR_ERR(vsp1->lif);
@@ -187,7 +286,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		list_add_tail(&vsp1->lif->entity.list_dev, &vsp1->entities);
 	}
 
-	if (vsp1->pdata.features & VSP1_HAS_LUT) {
+	if (vsp1->info->features & VSP1_HAS_LUT) {
 		vsp1->lut = vsp1_lut_create(vsp1);
 		if (IS_ERR(vsp1->lut)) {
 			ret = PTR_ERR(vsp1->lut);
@@ -197,7 +296,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		list_add_tail(&vsp1->lut->entity.list_dev, &vsp1->entities);
 	}
 
-	for (i = 0; i < vsp1->pdata.rpf_count; ++i) {
+	for (i = 0; i < vsp1->info->rpf_count; ++i) {
 		struct vsp1_rwpf *rpf;
 
 		rpf = vsp1_rpf_create(vsp1, i);
@@ -208,9 +307,20 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 
 		vsp1->rpf[i] = rpf;
 		list_add_tail(&rpf->entity.list_dev, &vsp1->entities);
+
+		if (vsp1->info->uapi) {
+			struct vsp1_video *video = vsp1_video_create(vsp1, rpf);
+
+			if (IS_ERR(video)) {
+				ret = PTR_ERR(video);
+				goto done;
+			}
+
+			list_add_tail(&video->list, &vsp1->videos);
+		}
 	}
 
-	if (vsp1->pdata.features & VSP1_HAS_SRU) {
+	if (vsp1->info->features & VSP1_HAS_SRU) {
 		vsp1->sru = vsp1_sru_create(vsp1);
 		if (IS_ERR(vsp1->sru)) {
 			ret = PTR_ERR(vsp1->sru);
@@ -220,7 +330,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		list_add_tail(&vsp1->sru->entity.list_dev, &vsp1->entities);
 	}
 
-	for (i = 0; i < vsp1->pdata.uds_count; ++i) {
+	for (i = 0; i < vsp1->info->uds_count; ++i) {
 		struct vsp1_uds *uds;
 
 		uds = vsp1_uds_create(vsp1, i);
@@ -233,7 +343,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		list_add_tail(&uds->entity.list_dev, &vsp1->entities);
 	}
 
-	for (i = 0; i < vsp1->pdata.wpf_count; ++i) {
+	for (i = 0; i < vsp1->info->wpf_count; ++i) {
 		struct vsp1_rwpf *wpf;
 
 		wpf = vsp1_wpf_create(vsp1, i);
@@ -244,6 +354,18 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 
 		vsp1->wpf[i] = wpf;
 		list_add_tail(&wpf->entity.list_dev, &vsp1->entities);
+
+		if (vsp1->info->uapi) {
+			struct vsp1_video *video = vsp1_video_create(vsp1, wpf);
+
+			if (IS_ERR(video)) {
+				ret = PTR_ERR(video);
+				goto done;
+			}
+
+			list_add_tail(&video->list, &vsp1->videos);
+			wpf->entity.sink = &video->video.entity;
+		}
 	}
 
 	/* Register all subdevs. */
@@ -255,34 +377,23 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 	}
 
 	/* Create links. */
-	list_for_each_entry(entity, &vsp1->entities, list_dev) {
-		if (entity->type == VSP1_ENTITY_WPF) {
-			ret = vsp1_wpf_create_links(vsp1, entity);
-			if (ret < 0)
-				goto done;
-		} else if (entity->type == VSP1_ENTITY_RPF) {
-			ret = vsp1_rpf_create_links(vsp1, entity);
-			if (ret < 0)
-				goto done;
-		}
-
-		if (entity->type != VSP1_ENTITY_LIF &&
-		    entity->type != VSP1_ENTITY_RPF) {
-			ret = vsp1_create_links(vsp1, entity);
-			if (ret < 0)
-				goto done;
-		}
-	}
+	if (vsp1->info->uapi)
+		ret = vsp1_uapi_create_links(vsp1);
+	else
+		ret = vsp1_drm_create_links(vsp1);
+	if (ret < 0)
+		goto done;
 
-	if (vsp1->pdata.features & VSP1_HAS_LIF) {
-		ret = media_create_pad_link(
-			&vsp1->wpf[0]->entity.subdev.entity, RWPF_PAD_SOURCE,
-			&vsp1->lif->entity.subdev.entity, LIF_PAD_SINK, 0);
-		if (ret < 0)
-			return ret;
+	/* Register subdev nodes if the userspace API is enabled or initialize
+	 * the DRM pipeline otherwise.
+	 */
+	if (vsp1->info->uapi) {
+		vsp1->use_dl = false;
+		ret = v4l2_device_register_subdev_nodes(&vsp1->v4l2_dev);
+	} else {
+		vsp1->use_dl = true;
+		ret = vsp1_drm_init(vsp1);
 	}
-
-	ret = v4l2_device_register_subdev_nodes(&vsp1->v4l2_dev);
 	if (ret < 0)
 		goto done;
 
@@ -295,42 +406,51 @@ done:
 	return ret;
 }
 
-static int vsp1_device_init(struct vsp1_device *vsp1)
+int vsp1_reset_wpf(struct vsp1_device *vsp1, unsigned int index)
 {
-	unsigned int i;
+	unsigned int timeout;
 	u32 status;
 
-	/* Reset any channel that might be running. */
 	status = vsp1_read(vsp1, VI6_STATUS);
+	if (!(status & VI6_STATUS_SYS_ACT(index)))
+		return 0;
 
-	for (i = 0; i < vsp1->pdata.wpf_count; ++i) {
-		unsigned int timeout;
+	vsp1_write(vsp1, VI6_SRESET, VI6_SRESET_SRTS(index));
+	for (timeout = 10; timeout > 0; --timeout) {
+		status = vsp1_read(vsp1, VI6_STATUS);
+		if (!(status & VI6_STATUS_SYS_ACT(index)))
+			break;
 
-		if (!(status & VI6_STATUS_SYS_ACT(i)))
-			continue;
+		usleep_range(1000, 2000);
+	}
 
-		vsp1_write(vsp1, VI6_SRESET, VI6_SRESET_SRTS(i));
-		for (timeout = 10; timeout > 0; --timeout) {
-			status = vsp1_read(vsp1, VI6_STATUS);
-			if (!(status & VI6_STATUS_SYS_ACT(i)))
-				break;
+	if (!timeout) {
+		dev_err(vsp1->dev, "failed to reset wpf.%u\n", index);
+		return -ETIMEDOUT;
+	}
 
-			usleep_range(1000, 2000);
-		}
+	return 0;
+}
 
-		if (!timeout) {
-			dev_err(vsp1->dev, "failed to reset wpf.%u\n", i);
-			return -ETIMEDOUT;
-		}
+static int vsp1_device_init(struct vsp1_device *vsp1)
+{
+	unsigned int i;
+	int ret;
+
+	/* Reset any channel that might be running. */
+	for (i = 0; i < vsp1->info->wpf_count; ++i) {
+		ret = vsp1_reset_wpf(vsp1, i);
+		if (ret < 0)
+			return ret;
 	}
 
 	vsp1_write(vsp1, VI6_CLK_DCSWT, (8 << VI6_CLK_DCSWT_CSTPW_SHIFT) |
 		   (8 << VI6_CLK_DCSWT_CSTRW_SHIFT));
 
-	for (i = 0; i < vsp1->pdata.rpf_count; ++i)
+	for (i = 0; i < vsp1->info->rpf_count; ++i)
 		vsp1_write(vsp1, VI6_DPR_RPF_ROUTE(i), VI6_DPR_NODE_UNUSED);
 
-	for (i = 0; i < vsp1->pdata.uds_count; ++i)
+	for (i = 0; i < vsp1->info->uds_count; ++i)
 		vsp1_write(vsp1, VI6_DPR_UDS_ROUTE(i), VI6_DPR_NODE_UNUSED);
 
 	vsp1_write(vsp1, VI6_DPR_SRU_ROUTE, VI6_DPR_NODE_UNUSED);
@@ -345,6 +465,9 @@ static int vsp1_device_init(struct vsp1_device *vsp1)
 	vsp1_write(vsp1, VI6_DPR_HGT_SMPPT, (7 << VI6_DPR_SMPPT_TGW_SHIFT) |
 		   (VI6_DPR_NODE_UNUSED << VI6_DPR_SMPPT_PT_SHIFT));
 
+	if (vsp1->use_dl)
+		vsp1_dl_setup(vsp1);
+
 	return 0;
 }
 
@@ -444,48 +567,76 @@ static const struct dev_pm_ops vsp1_pm_ops = {
  * Platform Driver
  */
 
-static int vsp1_parse_dt(struct vsp1_device *vsp1)
-{
-	struct device_node *np = vsp1->dev->of_node;
-	struct vsp1_platform_data *pdata = &vsp1->pdata;
-
-	if (of_property_read_bool(np, "renesas,has-lif"))
-		pdata->features |= VSP1_HAS_LIF;
-	if (of_property_read_bool(np, "renesas,has-lut"))
-		pdata->features |= VSP1_HAS_LUT;
-	if (of_property_read_bool(np, "renesas,has-sru"))
-		pdata->features |= VSP1_HAS_SRU;
-
-	of_property_read_u32(np, "renesas,#rpf", &pdata->rpf_count);
-	of_property_read_u32(np, "renesas,#uds", &pdata->uds_count);
-	of_property_read_u32(np, "renesas,#wpf", &pdata->wpf_count);
-
-	if (pdata->rpf_count <= 0 || pdata->rpf_count > VSP1_MAX_RPF) {
-		dev_err(vsp1->dev, "invalid number of RPF (%u)\n",
-			pdata->rpf_count);
-		return -EINVAL;
-	}
-
-	if (pdata->uds_count <= 0 || pdata->uds_count > VSP1_MAX_UDS) {
-		dev_err(vsp1->dev, "invalid number of UDS (%u)\n",
-			pdata->uds_count);
-		return -EINVAL;
-	}
-
-	if (pdata->wpf_count <= 0 || pdata->wpf_count > VSP1_MAX_WPF) {
-		dev_err(vsp1->dev, "invalid number of WPF (%u)\n",
-			pdata->wpf_count);
-		return -EINVAL;
-	}
-
-	return 0;
-}
+static const struct vsp1_device_info vsp1_device_infos[] = {
+	{
+		.version = VI6_IP_VERSION_MODEL_VSPS_H2,
+		.features = VSP1_HAS_BRU | VSP1_HAS_LUT | VSP1_HAS_SRU,
+		.rpf_count = 5,
+		.uds_count = 3,
+		.wpf_count = 4,
+		.num_bru_inputs = 4,
+		.uapi = true,
+	}, {
+		.version = VI6_IP_VERSION_MODEL_VSPR_H2,
+		.features = VSP1_HAS_BRU | VSP1_HAS_SRU,
+		.rpf_count = 5,
+		.uds_count = 1,
+		.wpf_count = 4,
+		.num_bru_inputs = 4,
+		.uapi = true,
+	}, {
+		.version = VI6_IP_VERSION_MODEL_VSPD_GEN2,
+		.features = VSP1_HAS_BRU | VSP1_HAS_LIF | VSP1_HAS_LUT,
+		.rpf_count = 4,
+		.uds_count = 1,
+		.wpf_count = 4,
+		.num_bru_inputs = 4,
+		.uapi = true,
+	}, {
+		.version = VI6_IP_VERSION_MODEL_VSPS_M2,
+		.features = VSP1_HAS_BRU | VSP1_HAS_LUT | VSP1_HAS_SRU,
+		.rpf_count = 5,
+		.uds_count = 3,
+		.wpf_count = 4,
+		.num_bru_inputs = 4,
+		.uapi = true,
+	}, {
+		.version = VI6_IP_VERSION_MODEL_VSPI_GEN3,
+		.features = VSP1_HAS_LUT | VSP1_HAS_SRU,
+		.rpf_count = 1,
+		.uds_count = 1,
+		.wpf_count = 1,
+		.uapi = true,
+	}, {
+		.version = VI6_IP_VERSION_MODEL_VSPBD_GEN3,
+		.features = VSP1_HAS_BRU,
+		.rpf_count = 5,
+		.wpf_count = 1,
+		.num_bru_inputs = 5,
+		.uapi = true,
+	}, {
+		.version = VI6_IP_VERSION_MODEL_VSPBC_GEN3,
+		.features = VSP1_HAS_BRU | VSP1_HAS_LUT,
+		.rpf_count = 5,
+		.wpf_count = 1,
+		.num_bru_inputs = 5,
+		.uapi = true,
+	}, {
+		.version = VI6_IP_VERSION_MODEL_VSPD_GEN3,
+		.features = VSP1_HAS_BRU | VSP1_HAS_LIF | VSP1_HAS_LUT,
+		.rpf_count = 5,
+		.wpf_count = 2,
+		.num_bru_inputs = 5,
+	},
+};
 
 static int vsp1_probe(struct platform_device *pdev)
 {
 	struct vsp1_device *vsp1;
 	struct resource *irq;
 	struct resource *io;
+	unsigned int i;
+	u32 version;
 	int ret;
 
 	vsp1 = devm_kzalloc(&pdev->dev, sizeof(*vsp1), GFP_KERNEL);
@@ -495,10 +646,7 @@ static int vsp1_probe(struct platform_device *pdev)
 	vsp1->dev = &pdev->dev;
 	mutex_init(&vsp1->lock);
 	INIT_LIST_HEAD(&vsp1->entities);
-
-	ret = vsp1_parse_dt(vsp1);
-	if (ret < 0)
-		return ret;
+	INIT_LIST_HEAD(&vsp1->videos);
 
 	/* I/O, IRQ and clock resources */
 	io = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -525,6 +673,29 @@ static int vsp1_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	/* Configure device parameters based on the version register. */
+	ret = clk_prepare_enable(vsp1->clock);
+	if (ret < 0)
+		return ret;
+
+	version = vsp1_read(vsp1, VI6_IP_VERSION);
+	clk_disable_unprepare(vsp1->clock);
+
+	for (i = 0; i < ARRAY_SIZE(vsp1_device_infos); ++i) {
+		if ((version & VI6_IP_VERSION_MODEL_MASK) ==
+		    vsp1_device_infos[i].version) {
+			vsp1->info = &vsp1_device_infos[i];
+			break;
+		}
+	}
+
+	if (!vsp1->info) {
+		dev_err(&pdev->dev, "unsupported IP version 0x%08x\n", version);
+		return -ENXIO;
+	}
+
+	dev_dbg(&pdev->dev, "IP version 0x%08x\n", version);
+
 	/* Instanciate entities */
 	ret = vsp1_create_entities(vsp1);
 	if (ret < 0) {
@@ -548,6 +719,7 @@ static int vsp1_remove(struct platform_device *pdev)
 
 static const struct of_device_id vsp1_of_match[] = {
 	{ .compatible = "renesas,vsp1" },
+	{ .compatible = "renesas,vsp2" },
 	{ },
 };
 
diff --git a/drivers/media/platform/vsp1/vsp1_entity.c b/drivers/media/platform/vsp1/vsp1_entity.c
index d7308530952f..20a78fbd3691 100644
--- a/drivers/media/platform/vsp1/vsp1_entity.c
+++ b/drivers/media/platform/vsp1/vsp1_entity.c
@@ -20,7 +20,6 @@
 
 #include "vsp1.h"
 #include "vsp1_entity.h"
-#include "vsp1_video.h"
 
 bool vsp1_entity_is_streaming(struct vsp1_entity *entity)
 {
@@ -46,7 +45,7 @@ int vsp1_entity_set_streaming(struct vsp1_entity *entity, bool streaming)
 	if (!streaming)
 		return 0;
 
-	if (!entity->subdev.ctrl_handler)
+	if (!entity->vsp1->info->uapi || !entity->subdev.ctrl_handler)
 		return 0;
 
 	ret = v4l2_ctrl_handler_setup(entity->subdev.ctrl_handler);
@@ -59,6 +58,18 @@ int vsp1_entity_set_streaming(struct vsp1_entity *entity, bool streaming)
 	return ret;
 }
 
+void vsp1_entity_route_setup(struct vsp1_entity *source)
+{
+	struct vsp1_entity *sink;
+
+	if (source->route->reg == 0)
+		return;
+
+	sink = container_of(source->sink, struct vsp1_entity, subdev.entity);
+	vsp1_mod_write(source, source->route->reg,
+		       sink->route->inputs[source->sink_pad]);
+}
+
 /* -----------------------------------------------------------------------------
  * V4L2 Subdevice Operations
  */
@@ -120,9 +131,9 @@ const struct v4l2_subdev_internal_ops vsp1_subdev_internal_ops = {
  * Media Operations
  */
 
-static int vsp1_entity_link_setup(struct media_entity *entity,
-				  const struct media_pad *local,
-				  const struct media_pad *remote, u32 flags)
+int vsp1_entity_link_setup(struct media_entity *entity,
+			   const struct media_pad *local,
+			   const struct media_pad *remote, u32 flags)
 {
 	struct vsp1_entity *source;
 
@@ -147,11 +158,6 @@ static int vsp1_entity_link_setup(struct media_entity *entity,
 	return 0;
 }
 
-const struct media_entity_operations vsp1_media_ops = {
-	.link_setup = vsp1_entity_link_setup,
-	.link_validate = v4l2_subdev_link_validate,
-};
-
 /* -----------------------------------------------------------------------------
  * Initialization
  */
@@ -159,7 +165,8 @@ const struct media_entity_operations vsp1_media_ops = {
 static const struct vsp1_route vsp1_routes[] = {
 	{ VSP1_ENTITY_BRU, 0, VI6_DPR_BRU_ROUTE,
 	  { VI6_DPR_NODE_BRU_IN(0), VI6_DPR_NODE_BRU_IN(1),
-	    VI6_DPR_NODE_BRU_IN(2), VI6_DPR_NODE_BRU_IN(3), } },
+	    VI6_DPR_NODE_BRU_IN(2), VI6_DPR_NODE_BRU_IN(3),
+	    VI6_DPR_NODE_BRU_IN(4) } },
 	{ VSP1_ENTITY_HSI, 0, VI6_DPR_HSI_ROUTE, { VI6_DPR_NODE_HSI, } },
 	{ VSP1_ENTITY_HST, 0, VI6_DPR_HST_ROUTE, { VI6_DPR_NODE_HST, } },
 	{ VSP1_ENTITY_LIF, 0, 0, { VI6_DPR_NODE_LIF, } },
@@ -225,8 +232,6 @@ int vsp1_entity_init(struct vsp1_device *vsp1, struct vsp1_entity *entity,
 
 void vsp1_entity_destroy(struct vsp1_entity *entity)
 {
-	if (entity->video)
-		vsp1_video_cleanup(entity->video);
 	if (entity->subdev.ctrl_handler)
 		v4l2_ctrl_handler_free(entity->subdev.ctrl_handler);
 	media_entity_cleanup(&entity->subdev.entity);
diff --git a/drivers/media/platform/vsp1/vsp1_entity.h b/drivers/media/platform/vsp1/vsp1_entity.h
index 8867a5787c28..83570dfde8ec 100644
--- a/drivers/media/platform/vsp1/vsp1_entity.h
+++ b/drivers/media/platform/vsp1/vsp1_entity.h
@@ -19,7 +19,6 @@
 #include <media/v4l2-subdev.h>
 
 struct vsp1_device;
-struct vsp1_video;
 
 enum vsp1_entity_type {
 	VSP1_ENTITY_BRU,
@@ -33,6 +32,8 @@ enum vsp1_entity_type {
 	VSP1_ENTITY_WPF,
 };
 
+#define VSP1_ENTITY_MAX_INPUTS		5	/* For the BRU */
+
 /*
  * struct vsp1_route - Entity routing configuration
  * @type: Entity type this routing entry is associated with
@@ -49,7 +50,7 @@ struct vsp1_route {
 	enum vsp1_entity_type type;
 	unsigned int index;
 	unsigned int reg;
-	unsigned int inputs[4];
+	unsigned int inputs[VSP1_ENTITY_MAX_INPUTS];
 };
 
 struct vsp1_entity {
@@ -71,8 +72,6 @@ struct vsp1_entity {
 	struct v4l2_subdev subdev;
 	struct v4l2_mbus_framefmt *formats;
 
-	struct vsp1_video *video;
-
 	spinlock_t lock;		/* Protects the streaming field */
 	bool streaming;
 };
@@ -87,7 +86,10 @@ int vsp1_entity_init(struct vsp1_device *vsp1, struct vsp1_entity *entity,
 void vsp1_entity_destroy(struct vsp1_entity *entity);
 
 extern const struct v4l2_subdev_internal_ops vsp1_subdev_internal_ops;
-extern const struct media_entity_operations vsp1_media_ops;
+
+int vsp1_entity_link_setup(struct media_entity *entity,
+			   const struct media_pad *local,
+			   const struct media_pad *remote, u32 flags);
 
 struct v4l2_mbus_framefmt *
 vsp1_entity_get_pad_format(struct vsp1_entity *entity,
@@ -99,4 +101,6 @@ void vsp1_entity_init_formats(struct v4l2_subdev *subdev,
 bool vsp1_entity_is_streaming(struct vsp1_entity *entity);
 int vsp1_entity_set_streaming(struct vsp1_entity *entity, bool streaming);
 
+void vsp1_entity_route_setup(struct vsp1_entity *source);
+
 #endif /* __VSP1_ENTITY_H__ */
diff --git a/drivers/media/platform/vsp1/vsp1_hsit.c b/drivers/media/platform/vsp1/vsp1_hsit.c
index 8ffb817ae525..c1087cff31a0 100644
--- a/drivers/media/platform/vsp1/vsp1_hsit.c
+++ b/drivers/media/platform/vsp1/vsp1_hsit.c
@@ -203,7 +203,7 @@ struct vsp1_hsit *vsp1_hsit_create(struct vsp1_device *vsp1, bool inverse)
 	subdev = &hsit->entity.subdev;
 	v4l2_subdev_init(subdev, &hsit_ops);
 
-	subdev->entity.ops = &vsp1_media_ops;
+	subdev->entity.ops = &vsp1->media_ops;
 	subdev->internal_ops = &vsp1_subdev_internal_ops;
 	snprintf(subdev->name, sizeof(subdev->name), "%s %s",
 		 dev_name(vsp1->dev), inverse ? "hsi" : "hst");
diff --git a/drivers/media/platform/vsp1/vsp1_lif.c b/drivers/media/platform/vsp1/vsp1_lif.c
index 39fa5ef20fbb..433853ce8dbf 100644
--- a/drivers/media/platform/vsp1/vsp1_lif.c
+++ b/drivers/media/platform/vsp1/vsp1_lif.c
@@ -26,14 +26,9 @@
  * Device Access
  */
 
-static inline u32 vsp1_lif_read(struct vsp1_lif *lif, u32 reg)
-{
-	return vsp1_read(lif->entity.vsp1, reg);
-}
-
 static inline void vsp1_lif_write(struct vsp1_lif *lif, u32 reg, u32 data)
 {
-	vsp1_write(lif->entity.vsp1, reg, data);
+	vsp1_mod_write(&lif->entity, reg, data);
 }
 
 /* -----------------------------------------------------------------------------
@@ -49,7 +44,7 @@ static int lif_s_stream(struct v4l2_subdev *subdev, int enable)
 	unsigned int lbth = 200;
 
 	if (!enable) {
-		vsp1_lif_write(lif, VI6_LIF_CTRL, 0);
+		vsp1_write(lif->entity.vsp1, VI6_LIF_CTRL, 0);
 		return 0;
 	}
 
@@ -228,7 +223,7 @@ struct vsp1_lif *vsp1_lif_create(struct vsp1_device *vsp1)
 	subdev = &lif->entity.subdev;
 	v4l2_subdev_init(subdev, &lif_ops);
 
-	subdev->entity.ops = &vsp1_media_ops;
+	subdev->entity.ops = &vsp1->media_ops;
 	subdev->internal_ops = &vsp1_subdev_internal_ops;
 	snprintf(subdev->name, sizeof(subdev->name), "%s lif",
 		 dev_name(vsp1->dev));
diff --git a/drivers/media/platform/vsp1/vsp1_lut.c b/drivers/media/platform/vsp1/vsp1_lut.c
index 656ec272a414..4b89095e7b5f 100644
--- a/drivers/media/platform/vsp1/vsp1_lut.c
+++ b/drivers/media/platform/vsp1/vsp1_lut.c
@@ -27,11 +27,6 @@
  * Device Access
  */
 
-static inline u32 vsp1_lut_read(struct vsp1_lut *lut, u32 reg)
-{
-	return vsp1_read(lut->entity.vsp1, reg);
-}
-
 static inline void vsp1_lut_write(struct vsp1_lut *lut, u32 reg, u32 data)
 {
 	vsp1_write(lut->entity.vsp1, reg, data);
@@ -242,7 +237,7 @@ struct vsp1_lut *vsp1_lut_create(struct vsp1_device *vsp1)
 	subdev = &lut->entity.subdev;
 	v4l2_subdev_init(subdev, &lut_ops);
 
-	subdev->entity.ops = &vsp1_media_ops;
+	subdev->entity.ops = &vsp1->media_ops;
 	subdev->internal_ops = &vsp1_subdev_internal_ops;
 	snprintf(subdev->name, sizeof(subdev->name), "%s lut",
 		 dev_name(vsp1->dev));
diff --git a/drivers/media/platform/vsp1/vsp1_pipe.c b/drivers/media/platform/vsp1/vsp1_pipe.c
new file mode 100644
index 000000000000..6659f06b1643
--- /dev/null
+++ b/drivers/media/platform/vsp1/vsp1_pipe.c
@@ -0,0 +1,426 @@
+/*
+ * vsp1_pipe.c  --  R-Car VSP1 Pipeline
+ *
+ * Copyright (C) 2013-2015 Renesas Electronics Corporation
+ *
+ * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/delay.h>
+#include <linux/list.h>
+#include <linux/sched.h>
+#include <linux/wait.h>
+
+#include <media/media-entity.h>
+#include <media/v4l2-subdev.h>
+
+#include "vsp1.h"
+#include "vsp1_bru.h"
+#include "vsp1_dl.h"
+#include "vsp1_entity.h"
+#include "vsp1_pipe.h"
+#include "vsp1_rwpf.h"
+#include "vsp1_uds.h"
+
+/* -----------------------------------------------------------------------------
+ * Helper Functions
+ */
+
+static const struct vsp1_format_info vsp1_video_formats[] = {
+	{ V4L2_PIX_FMT_RGB332, MEDIA_BUS_FMT_ARGB8888_1X32,
+	  VI6_FMT_RGB_332, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  1, { 8, 0, 0 }, false, false, 1, 1, false },
+	{ V4L2_PIX_FMT_ARGB444, MEDIA_BUS_FMT_ARGB8888_1X32,
+	  VI6_FMT_ARGB_4444, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS,
+	  1, { 16, 0, 0 }, false, false, 1, 1, true },
+	{ V4L2_PIX_FMT_XRGB444, MEDIA_BUS_FMT_ARGB8888_1X32,
+	  VI6_FMT_XRGB_4444, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS,
+	  1, { 16, 0, 0 }, false, false, 1, 1, true },
+	{ V4L2_PIX_FMT_ARGB555, MEDIA_BUS_FMT_ARGB8888_1X32,
+	  VI6_FMT_ARGB_1555, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS,
+	  1, { 16, 0, 0 }, false, false, 1, 1, true },
+	{ V4L2_PIX_FMT_XRGB555, MEDIA_BUS_FMT_ARGB8888_1X32,
+	  VI6_FMT_XRGB_1555, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS,
+	  1, { 16, 0, 0 }, false, false, 1, 1, false },
+	{ V4L2_PIX_FMT_RGB565, MEDIA_BUS_FMT_ARGB8888_1X32,
+	  VI6_FMT_RGB_565, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS,
+	  1, { 16, 0, 0 }, false, false, 1, 1, false },
+	{ V4L2_PIX_FMT_BGR24, MEDIA_BUS_FMT_ARGB8888_1X32,
+	  VI6_FMT_BGR_888, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  1, { 24, 0, 0 }, false, false, 1, 1, false },
+	{ V4L2_PIX_FMT_RGB24, MEDIA_BUS_FMT_ARGB8888_1X32,
+	  VI6_FMT_RGB_888, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  1, { 24, 0, 0 }, false, false, 1, 1, false },
+	{ V4L2_PIX_FMT_ABGR32, MEDIA_BUS_FMT_ARGB8888_1X32,
+	  VI6_FMT_ARGB_8888, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS,
+	  1, { 32, 0, 0 }, false, false, 1, 1, true },
+	{ V4L2_PIX_FMT_XBGR32, MEDIA_BUS_FMT_ARGB8888_1X32,
+	  VI6_FMT_ARGB_8888, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS,
+	  1, { 32, 0, 0 }, false, false, 1, 1, false },
+	{ V4L2_PIX_FMT_ARGB32, MEDIA_BUS_FMT_ARGB8888_1X32,
+	  VI6_FMT_ARGB_8888, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  1, { 32, 0, 0 }, false, false, 1, 1, true },
+	{ V4L2_PIX_FMT_XRGB32, MEDIA_BUS_FMT_ARGB8888_1X32,
+	  VI6_FMT_ARGB_8888, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  1, { 32, 0, 0 }, false, false, 1, 1, false },
+	{ V4L2_PIX_FMT_UYVY, MEDIA_BUS_FMT_AYUV8_1X32,
+	  VI6_FMT_YUYV_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  1, { 16, 0, 0 }, false, false, 2, 1, false },
+	{ V4L2_PIX_FMT_VYUY, MEDIA_BUS_FMT_AYUV8_1X32,
+	  VI6_FMT_YUYV_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  1, { 16, 0, 0 }, false, true, 2, 1, false },
+	{ V4L2_PIX_FMT_YUYV, MEDIA_BUS_FMT_AYUV8_1X32,
+	  VI6_FMT_YUYV_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  1, { 16, 0, 0 }, true, false, 2, 1, false },
+	{ V4L2_PIX_FMT_YVYU, MEDIA_BUS_FMT_AYUV8_1X32,
+	  VI6_FMT_YUYV_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  1, { 16, 0, 0 }, true, true, 2, 1, false },
+	{ V4L2_PIX_FMT_NV12M, MEDIA_BUS_FMT_AYUV8_1X32,
+	  VI6_FMT_Y_UV_420, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  2, { 8, 16, 0 }, false, false, 2, 2, false },
+	{ V4L2_PIX_FMT_NV21M, MEDIA_BUS_FMT_AYUV8_1X32,
+	  VI6_FMT_Y_UV_420, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  2, { 8, 16, 0 }, false, true, 2, 2, false },
+	{ V4L2_PIX_FMT_NV16M, MEDIA_BUS_FMT_AYUV8_1X32,
+	  VI6_FMT_Y_UV_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  2, { 8, 16, 0 }, false, false, 2, 1, false },
+	{ V4L2_PIX_FMT_NV61M, MEDIA_BUS_FMT_AYUV8_1X32,
+	  VI6_FMT_Y_UV_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  2, { 8, 16, 0 }, false, true, 2, 1, false },
+	{ V4L2_PIX_FMT_YUV420M, MEDIA_BUS_FMT_AYUV8_1X32,
+	  VI6_FMT_Y_U_V_420, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  3, { 8, 8, 8 }, false, false, 2, 2, false },
+	{ V4L2_PIX_FMT_YVU420M, MEDIA_BUS_FMT_AYUV8_1X32,
+	  VI6_FMT_Y_U_V_420, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  3, { 8, 8, 8 }, false, true, 2, 2, false },
+	{ V4L2_PIX_FMT_YUV422M, MEDIA_BUS_FMT_AYUV8_1X32,
+	  VI6_FMT_Y_U_V_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  3, { 8, 8, 8 }, false, false, 2, 1, false },
+	{ V4L2_PIX_FMT_YVU422M, MEDIA_BUS_FMT_AYUV8_1X32,
+	  VI6_FMT_Y_U_V_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  3, { 8, 8, 8 }, false, true, 2, 1, false },
+	{ V4L2_PIX_FMT_YUV444M, MEDIA_BUS_FMT_AYUV8_1X32,
+	  VI6_FMT_Y_U_V_444, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  3, { 8, 8, 8 }, false, false, 1, 1, false },
+	{ V4L2_PIX_FMT_YVU444M, MEDIA_BUS_FMT_AYUV8_1X32,
+	  VI6_FMT_Y_U_V_444, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
+	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
+	  3, { 8, 8, 8 }, false, true, 1, 1, false },
+};
+
+/*
+ * vsp1_get_format_info - Retrieve format information for a 4CC
+ * @fourcc: the format 4CC
+ *
+ * Return a pointer to the format information structure corresponding to the
+ * given V4L2 format 4CC, or NULL if no corresponding format can be found.
+ */
+const struct vsp1_format_info *vsp1_get_format_info(u32 fourcc)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(vsp1_video_formats); ++i) {
+		const struct vsp1_format_info *info = &vsp1_video_formats[i];
+
+		if (info->fourcc == fourcc)
+			return info;
+	}
+
+	return NULL;
+}
+
+/* -----------------------------------------------------------------------------
+ * Pipeline Management
+ */
+
+void vsp1_pipeline_reset(struct vsp1_pipeline *pipe)
+{
+	unsigned int i;
+
+	if (pipe->bru) {
+		struct vsp1_bru *bru = to_bru(&pipe->bru->subdev);
+
+		for (i = 0; i < ARRAY_SIZE(bru->inputs); ++i)
+			bru->inputs[i].rpf = NULL;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(pipe->inputs); ++i)
+		pipe->inputs[i] = NULL;
+
+	INIT_LIST_HEAD(&pipe->entities);
+	pipe->state = VSP1_PIPELINE_STOPPED;
+	pipe->buffers_ready = 0;
+	pipe->num_inputs = 0;
+	pipe->output = NULL;
+	pipe->bru = NULL;
+	pipe->lif = NULL;
+	pipe->uds = NULL;
+}
+
+void vsp1_pipeline_init(struct vsp1_pipeline *pipe)
+{
+	mutex_init(&pipe->lock);
+	spin_lock_init(&pipe->irqlock);
+	init_waitqueue_head(&pipe->wq);
+
+	INIT_LIST_HEAD(&pipe->entities);
+	pipe->state = VSP1_PIPELINE_STOPPED;
+}
+
+void vsp1_pipeline_run(struct vsp1_pipeline *pipe)
+{
+	struct vsp1_device *vsp1 = pipe->output->entity.vsp1;
+
+	if (pipe->state == VSP1_PIPELINE_STOPPED) {
+		vsp1_write(vsp1, VI6_CMD(pipe->output->entity.index),
+			   VI6_CMD_STRCMD);
+		pipe->state = VSP1_PIPELINE_RUNNING;
+	}
+
+	pipe->buffers_ready = 0;
+}
+
+bool vsp1_pipeline_stopped(struct vsp1_pipeline *pipe)
+{
+	unsigned long flags;
+	bool stopped;
+
+	spin_lock_irqsave(&pipe->irqlock, flags);
+	stopped = pipe->state == VSP1_PIPELINE_STOPPED;
+	spin_unlock_irqrestore(&pipe->irqlock, flags);
+
+	return stopped;
+}
+
+int vsp1_pipeline_stop(struct vsp1_pipeline *pipe)
+{
+	struct vsp1_entity *entity;
+	unsigned long flags;
+	int ret;
+
+	if (pipe->dl) {
+		/* When using display lists in continuous frame mode the only
+		 * way to stop the pipeline is to reset the hardware.
+		 */
+		ret = vsp1_reset_wpf(pipe->output->entity.vsp1,
+				     pipe->output->entity.index);
+		if (ret == 0) {
+			spin_lock_irqsave(&pipe->irqlock, flags);
+			pipe->state = VSP1_PIPELINE_STOPPED;
+			spin_unlock_irqrestore(&pipe->irqlock, flags);
+		}
+	} else {
+		/* Otherwise just request a stop and wait. */
+		spin_lock_irqsave(&pipe->irqlock, flags);
+		if (pipe->state == VSP1_PIPELINE_RUNNING)
+			pipe->state = VSP1_PIPELINE_STOPPING;
+		spin_unlock_irqrestore(&pipe->irqlock, flags);
+
+		ret = wait_event_timeout(pipe->wq, vsp1_pipeline_stopped(pipe),
+					 msecs_to_jiffies(500));
+		ret = ret == 0 ? -ETIMEDOUT : 0;
+	}
+
+	list_for_each_entry(entity, &pipe->entities, list_pipe) {
+		if (entity->route && entity->route->reg)
+			vsp1_write(entity->vsp1, entity->route->reg,
+				   VI6_DPR_NODE_UNUSED);
+
+		v4l2_subdev_call(&entity->subdev, video, s_stream, 0);
+	}
+
+	return ret;
+}
+
+bool vsp1_pipeline_ready(struct vsp1_pipeline *pipe)
+{
+	unsigned int mask;
+
+	mask = ((1 << pipe->num_inputs) - 1) << 1;
+	if (!pipe->lif)
+		mask |= 1 << 0;
+
+	return pipe->buffers_ready == mask;
+}
+
+void vsp1_pipeline_display_start(struct vsp1_pipeline *pipe)
+{
+	if (pipe->dl)
+		vsp1_dl_irq_display_start(pipe->dl);
+}
+
+void vsp1_pipeline_frame_end(struct vsp1_pipeline *pipe)
+{
+	enum vsp1_pipeline_state state;
+	unsigned long flags;
+
+	if (pipe == NULL)
+		return;
+
+	if (pipe->dl)
+		vsp1_dl_irq_frame_end(pipe->dl);
+
+	/* Signal frame end to the pipeline handler. */
+	pipe->frame_end(pipe);
+
+	spin_lock_irqsave(&pipe->irqlock, flags);
+
+	state = pipe->state;
+
+	/* When using display lists in continuous frame mode the pipeline is
+	 * automatically restarted by the hardware.
+	 */
+	if (!pipe->dl)
+		pipe->state = VSP1_PIPELINE_STOPPED;
+
+	/* If a stop has been requested, mark the pipeline as stopped and
+	 * return.
+	 */
+	if (state == VSP1_PIPELINE_STOPPING) {
+		wake_up(&pipe->wq);
+		goto done;
+	}
+
+	/* Restart the pipeline if ready. */
+	if (vsp1_pipeline_ready(pipe))
+		vsp1_pipeline_run(pipe);
+
+done:
+	spin_unlock_irqrestore(&pipe->irqlock, flags);
+}
+
+/*
+ * Propagate the alpha value through the pipeline.
+ *
+ * As the UDS has restricted scaling capabilities when the alpha component needs
+ * to be scaled, we disable alpha scaling when the UDS input has a fixed alpha
+ * value. The UDS then outputs a fixed alpha value which needs to be programmed
+ * from the input RPF alpha.
+ */
+void vsp1_pipeline_propagate_alpha(struct vsp1_pipeline *pipe,
+				   struct vsp1_entity *input,
+				   unsigned int alpha)
+{
+	struct vsp1_entity *entity;
+	struct media_pad *pad;
+
+	pad = media_entity_remote_pad(&input->pads[RWPF_PAD_SOURCE]);
+
+	while (pad) {
+		if (!is_media_entity_v4l2_subdev(pad->entity))
+			break;
+
+		entity = to_vsp1_entity(media_entity_to_v4l2_subdev(pad->entity));
+
+		/* The BRU background color has a fixed alpha value set to 255,
+		 * the output alpha value is thus always equal to 255.
+		 */
+		if (entity->type == VSP1_ENTITY_BRU)
+			alpha = 255;
+
+		if (entity->type == VSP1_ENTITY_UDS) {
+			struct vsp1_uds *uds = to_uds(&entity->subdev);
+
+			vsp1_uds_set_alpha(uds, alpha);
+			break;
+		}
+
+		pad = &entity->pads[entity->source_pad];
+		pad = media_entity_remote_pad(pad);
+	}
+}
+
+void vsp1_pipelines_suspend(struct vsp1_device *vsp1)
+{
+	unsigned long flags;
+	unsigned int i;
+	int ret;
+
+	/* To avoid increasing the system suspend time needlessly, loop over the
+	 * pipelines twice, first to set them all to the stopping state, and
+	 * then to wait for the stop to complete.
+	 */
+	for (i = 0; i < vsp1->info->wpf_count; ++i) {
+		struct vsp1_rwpf *wpf = vsp1->wpf[i];
+		struct vsp1_pipeline *pipe;
+
+		if (wpf == NULL)
+			continue;
+
+		pipe = to_vsp1_pipeline(&wpf->entity.subdev.entity);
+		if (pipe == NULL)
+			continue;
+
+		spin_lock_irqsave(&pipe->irqlock, flags);
+		if (pipe->state == VSP1_PIPELINE_RUNNING)
+			pipe->state = VSP1_PIPELINE_STOPPING;
+		spin_unlock_irqrestore(&pipe->irqlock, flags);
+	}
+
+	for (i = 0; i < vsp1->info->wpf_count; ++i) {
+		struct vsp1_rwpf *wpf = vsp1->wpf[i];
+		struct vsp1_pipeline *pipe;
+
+		if (wpf == NULL)
+			continue;
+
+		pipe = to_vsp1_pipeline(&wpf->entity.subdev.entity);
+		if (pipe == NULL)
+			continue;
+
+		ret = wait_event_timeout(pipe->wq, vsp1_pipeline_stopped(pipe),
+					 msecs_to_jiffies(500));
+		if (ret == 0)
+			dev_warn(vsp1->dev, "pipeline %u stop timeout\n",
+				 wpf->entity.index);
+	}
+}
+
+void vsp1_pipelines_resume(struct vsp1_device *vsp1)
+{
+	unsigned int i;
+
+	/* Resume pipeline all running pipelines. */
+	for (i = 0; i < vsp1->info->wpf_count; ++i) {
+		struct vsp1_rwpf *wpf = vsp1->wpf[i];
+		struct vsp1_pipeline *pipe;
+
+		if (wpf == NULL)
+			continue;
+
+		pipe = to_vsp1_pipeline(&wpf->entity.subdev.entity);
+		if (pipe == NULL)
+			continue;
+
+		if (vsp1_pipeline_ready(pipe))
+			vsp1_pipeline_run(pipe);
+	}
+}
diff --git a/drivers/media/platform/vsp1/vsp1_pipe.h b/drivers/media/platform/vsp1/vsp1_pipe.h
new file mode 100644
index 000000000000..b2f3a8a896c9
--- /dev/null
+++ b/drivers/media/platform/vsp1/vsp1_pipe.h
@@ -0,0 +1,134 @@
+/*
+ * vsp1_pipe.h  --  R-Car VSP1 Pipeline
+ *
+ * Copyright (C) 2013-2015 Renesas Electronics Corporation
+ *
+ * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#ifndef __VSP1_PIPE_H__
+#define __VSP1_PIPE_H__
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/wait.h>
+
+#include <media/media-entity.h>
+
+struct vsp1_dl;
+struct vsp1_rwpf;
+
+/*
+ * struct vsp1_format_info - VSP1 video format description
+ * @mbus: media bus format code
+ * @fourcc: V4L2 pixel format FCC identifier
+ * @planes: number of planes
+ * @bpp: bits per pixel
+ * @hwfmt: VSP1 hardware format
+ * @swap_yc: the Y and C components are swapped (Y comes before C)
+ * @swap_uv: the U and V components are swapped (V comes before U)
+ * @hsub: horizontal subsampling factor
+ * @vsub: vertical subsampling factor
+ * @alpha: has an alpha channel
+ */
+struct vsp1_format_info {
+	u32 fourcc;
+	unsigned int mbus;
+	unsigned int hwfmt;
+	unsigned int swap;
+	unsigned int planes;
+	unsigned int bpp[3];
+	bool swap_yc;
+	bool swap_uv;
+	unsigned int hsub;
+	unsigned int vsub;
+	bool alpha;
+};
+
+enum vsp1_pipeline_state {
+	VSP1_PIPELINE_STOPPED,
+	VSP1_PIPELINE_RUNNING,
+	VSP1_PIPELINE_STOPPING,
+};
+
+/*
+ * struct vsp1_pipeline - A VSP1 hardware pipeline
+ * @pipe: the media pipeline
+ * @irqlock: protects the pipeline state
+ * @state: current state
+ * @wq: work queue to wait for state change completion
+ * @frame_end: frame end interrupt handler
+ * @lock: protects the pipeline use count and stream count
+ * @use_count: number of video nodes using the pipeline
+ * @stream_count: number of streaming video nodes
+ * @buffers_ready: bitmask of RPFs and WPFs with at least one buffer available
+ * @num_inputs: number of RPFs
+ * @inputs: array of RPFs in the pipeline (indexed by RPF index)
+ * @output: WPF at the output of the pipeline
+ * @bru: BRU entity, if present
+ * @lif: LIF entity, if present
+ * @uds: UDS entity, if present
+ * @uds_input: entity at the input of the UDS, if the UDS is present
+ * @entities: list of entities in the pipeline
+ * @dl: display list associated with the pipeline
+ */
+struct vsp1_pipeline {
+	struct media_pipeline pipe;
+
+	spinlock_t irqlock;
+	enum vsp1_pipeline_state state;
+	wait_queue_head_t wq;
+
+	void (*frame_end)(struct vsp1_pipeline *pipe);
+
+	struct mutex lock;
+	unsigned int use_count;
+	unsigned int stream_count;
+	unsigned int buffers_ready;
+
+	unsigned int num_inputs;
+	struct vsp1_rwpf *inputs[VSP1_MAX_RPF];
+	struct vsp1_rwpf *output;
+	struct vsp1_entity *bru;
+	struct vsp1_entity *lif;
+	struct vsp1_entity *uds;
+	struct vsp1_entity *uds_input;
+
+	struct list_head entities;
+
+	struct vsp1_dl *dl;
+};
+
+static inline struct vsp1_pipeline *to_vsp1_pipeline(struct media_entity *e)
+{
+	if (likely(e->pipe))
+		return container_of(e->pipe, struct vsp1_pipeline, pipe);
+	else
+		return NULL;
+}
+
+void vsp1_pipeline_reset(struct vsp1_pipeline *pipe);
+void vsp1_pipeline_init(struct vsp1_pipeline *pipe);
+
+void vsp1_pipeline_run(struct vsp1_pipeline *pipe);
+bool vsp1_pipeline_stopped(struct vsp1_pipeline *pipe);
+int vsp1_pipeline_stop(struct vsp1_pipeline *pipe);
+bool vsp1_pipeline_ready(struct vsp1_pipeline *pipe);
+
+void vsp1_pipeline_display_start(struct vsp1_pipeline *pipe);
+void vsp1_pipeline_frame_end(struct vsp1_pipeline *pipe);
+
+void vsp1_pipeline_propagate_alpha(struct vsp1_pipeline *pipe,
+				   struct vsp1_entity *input,
+				   unsigned int alpha);
+
+void vsp1_pipelines_suspend(struct vsp1_device *vsp1);
+void vsp1_pipelines_resume(struct vsp1_device *vsp1);
+
+const struct vsp1_format_info *vsp1_get_format_info(u32 fourcc);
+
+#endif /* __VSP1_PIPE_H__ */
diff --git a/drivers/media/platform/vsp1/vsp1_regs.h b/drivers/media/platform/vsp1/vsp1_regs.h
index 25b48738b147..069216f0eb44 100644
--- a/drivers/media/platform/vsp1/vsp1_regs.h
+++ b/drivers/media/platform/vsp1/vsp1_regs.h
@@ -46,7 +46,7 @@
 #define VI6_DISP_IRQ_ENB_LNEE(n)	(1 << (n))
 
 #define VI6_DISP_IRQ_STA		0x007c
-#define VI6_DISP_IRQ_STA_DSE		(1 << 8)
+#define VI6_DISP_IRQ_STA_DST		(1 << 8)
 #define VI6_DISP_IRQ_STA_MAE		(1 << 5)
 #define VI6_DISP_IRQ_STA_LNE(n)		(1 << (n))
 
@@ -322,7 +322,7 @@
 #define VI6_DPR_NODE_SRU		16
 #define VI6_DPR_NODE_UDS(n)		(17 + (n))
 #define VI6_DPR_NODE_LUT		22
-#define VI6_DPR_NODE_BRU_IN(n)		(23 + (n))
+#define VI6_DPR_NODE_BRU_IN(n)		(((n) <= 3) ? 23 + (n) : 49)
 #define VI6_DPR_NODE_BRU_OUT		27
 #define VI6_DPR_NODE_CLU		29
 #define VI6_DPR_NODE_HST		30
@@ -504,12 +504,12 @@
 #define VI6_BRU_VIRRPF_COL_BCB_MASK	(0xff << 0)
 #define VI6_BRU_VIRRPF_COL_BCB_SHIFT	0
 
-#define VI6_BRU_CTRL(n)			(0x2c10 + (n) * 8)
+#define VI6_BRU_CTRL(n)			(0x2c10 + (n) * 8 + ((n) <= 3 ? 0 : 4))
 #define VI6_BRU_CTRL_RBC		(1 << 31)
-#define VI6_BRU_CTRL_DSTSEL_BRUIN(n)	((n) << 20)
+#define VI6_BRU_CTRL_DSTSEL_BRUIN(n)	(((n) <= 3 ? (n) : (n)+1) << 20)
 #define VI6_BRU_CTRL_DSTSEL_VRPF	(4 << 20)
 #define VI6_BRU_CTRL_DSTSEL_MASK	(7 << 20)
-#define VI6_BRU_CTRL_SRCSEL_BRUIN(n)	((n) << 16)
+#define VI6_BRU_CTRL_SRCSEL_BRUIN(n)	(((n) <= 3 ? (n) : (n)+1) << 16)
 #define VI6_BRU_CTRL_SRCSEL_VRPF	(4 << 16)
 #define VI6_BRU_CTRL_SRCSEL_MASK	(7 << 16)
 #define VI6_BRU_CTRL_CROP(rop)		((rop) << 4)
@@ -517,7 +517,7 @@
 #define VI6_BRU_CTRL_AROP(rop)		((rop) << 0)
 #define VI6_BRU_CTRL_AROP_MASK		(0xf << 0)
 
-#define VI6_BRU_BLD(n)			(0x2c14 + (n) * 8)
+#define VI6_BRU_BLD(n)			(0x2c14 + (n) * 8 + ((n) <= 3 ? 0 : 4))
 #define VI6_BRU_BLD_CBES		(1 << 31)
 #define VI6_BRU_BLD_CCMDX_DST_A		(0 << 28)
 #define VI6_BRU_BLD_CCMDX_255_DST_A	(1 << 28)
@@ -551,7 +551,7 @@
 #define VI6_BRU_BLD_COEFY_SHIFT		0
 
 #define VI6_BRU_ROP			0x2c30
-#define VI6_BRU_ROP_DSTSEL_BRUIN(n)	((n) << 20)
+#define VI6_BRU_ROP_DSTSEL_BRUIN(n)	(((n) <= 3 ? (n) : (n)+1) << 20)
 #define VI6_BRU_ROP_DSTSEL_VRPF		(4 << 20)
 #define VI6_BRU_ROP_DSTSEL_MASK		(7 << 20)
 #define VI6_BRU_ROP_CROP(rop)		((rop) << 4)
@@ -625,6 +625,24 @@
 #define VI6_SECURITY_CTRL1		0x3d04
 
 /* -----------------------------------------------------------------------------
+ * IP Version Registers
+ */
+
+#define VI6_IP_VERSION			0x3f00
+#define VI6_IP_VERSION_MODEL_MASK	(0xff << 8)
+#define VI6_IP_VERSION_MODEL_VSPS_H2	(0x09 << 8)
+#define VI6_IP_VERSION_MODEL_VSPR_H2	(0x0a << 8)
+#define VI6_IP_VERSION_MODEL_VSPD_GEN2	(0x0b << 8)
+#define VI6_IP_VERSION_MODEL_VSPS_M2	(0x0c << 8)
+#define VI6_IP_VERSION_MODEL_VSPI_GEN3	(0x14 << 8)
+#define VI6_IP_VERSION_MODEL_VSPBD_GEN3	(0x15 << 8)
+#define VI6_IP_VERSION_MODEL_VSPBC_GEN3	(0x16 << 8)
+#define VI6_IP_VERSION_MODEL_VSPD_GEN3	(0x17 << 8)
+#define VI6_IP_VERSION_SOC_MASK		(0xff << 0)
+#define VI6_IP_VERSION_SOC_H		(0x01 << 0)
+#define VI6_IP_VERSION_SOC_M		(0x02 << 0)
+
+/* -----------------------------------------------------------------------------
  * RPF CLUT Registers
  */
 
diff --git a/drivers/media/platform/vsp1/vsp1_rpf.c b/drivers/media/platform/vsp1/vsp1_rpf.c
index 924538223d3e..5bc1d1574a43 100644
--- a/drivers/media/platform/vsp1/vsp1_rpf.c
+++ b/drivers/media/platform/vsp1/vsp1_rpf.c
@@ -26,16 +26,10 @@
  * Device Access
  */
 
-static inline u32 vsp1_rpf_read(struct vsp1_rwpf *rpf, u32 reg)
-{
-	return vsp1_read(rpf->entity.vsp1,
-			 reg + rpf->entity.index * VI6_RPF_OFFSET);
-}
-
 static inline void vsp1_rpf_write(struct vsp1_rwpf *rpf, u32 reg, u32 data)
 {
-	vsp1_write(rpf->entity.vsp1,
-		   reg + rpf->entity.index * VI6_RPF_OFFSET, data);
+	vsp1_mod_write(&rpf->entity, reg + rpf->entity.index * VI6_RPF_OFFSET,
+		       data);
 }
 
 /* -----------------------------------------------------------------------------
@@ -74,9 +68,11 @@ static const struct v4l2_ctrl_ops rpf_ctrl_ops = {
 
 static int rpf_s_stream(struct v4l2_subdev *subdev, int enable)
 {
+	struct vsp1_pipeline *pipe = to_vsp1_pipeline(&subdev->entity);
 	struct vsp1_rwpf *rpf = to_rwpf(subdev);
-	const struct vsp1_format_info *fmtinfo = rpf->video.fmtinfo;
-	const struct v4l2_pix_format_mplane *format = &rpf->video.format;
+	struct vsp1_device *vsp1 = rpf->entity.vsp1;
+	const struct vsp1_format_info *fmtinfo = rpf->fmtinfo;
+	const struct v4l2_pix_format_mplane *format = &rpf->format;
 	const struct v4l2_rect *crop = &rpf->crop;
 	u32 pstride;
 	u32 infmt;
@@ -154,6 +150,15 @@ static int rpf_s_stream(struct v4l2_subdev *subdev, int enable)
 	vsp1_rpf_write(rpf, VI6_RPF_ALPH_SEL, VI6_RPF_ALPH_SEL_AEXT_EXT |
 		       (fmtinfo->alpha ? VI6_RPF_ALPH_SEL_ASEL_PACKED
 				       : VI6_RPF_ALPH_SEL_ASEL_FIXED));
+
+	if (vsp1->info->uapi)
+		mutex_lock(rpf->ctrls.lock);
+	vsp1_rpf_write(rpf, VI6_RPF_VRTCOL_SET,
+		       rpf->alpha->cur.val << VI6_RPF_VRTCOL_SET_LAYA_SHIFT);
+	vsp1_pipeline_propagate_alpha(pipe, &rpf->entity, rpf->alpha->cur.val);
+	if (vsp1->info->uapi)
+		mutex_unlock(rpf->ctrls.lock);
+
 	vsp1_rpf_write(rpf, VI6_RPF_MSK_CTRL, 0);
 	vsp1_rpf_write(rpf, VI6_RPF_CKEY_CTRL, 0);
 
@@ -186,30 +191,28 @@ static struct v4l2_subdev_ops rpf_ops = {
  * Video Device Operations
  */
 
-static void rpf_vdev_queue(struct vsp1_video *video,
-			   struct vsp1_video_buffer *buf)
+static void rpf_set_memory(struct vsp1_rwpf *rpf, struct vsp1_rwpf_memory *mem)
 {
-	struct vsp1_rwpf *rpf = container_of(video, struct vsp1_rwpf, video);
 	unsigned int i;
 
 	for (i = 0; i < 3; ++i)
-		rpf->buf_addr[i] = buf->addr[i];
+		rpf->buf_addr[i] = mem->addr[i];
 
 	if (!vsp1_entity_is_streaming(&rpf->entity))
 		return;
 
 	vsp1_rpf_write(rpf, VI6_RPF_SRCM_ADDR_Y,
-		       buf->addr[0] + rpf->offsets[0]);
-	if (buf->buf.vb2_buf.num_planes > 1)
+		       mem->addr[0] + rpf->offsets[0]);
+	if (mem->num_planes > 1)
 		vsp1_rpf_write(rpf, VI6_RPF_SRCM_ADDR_C0,
-			       buf->addr[1] + rpf->offsets[1]);
-	if (buf->buf.vb2_buf.num_planes > 2)
+			       mem->addr[1] + rpf->offsets[1]);
+	if (mem->num_planes > 2)
 		vsp1_rpf_write(rpf, VI6_RPF_SRCM_ADDR_C1,
-			       buf->addr[2] + rpf->offsets[1]);
+			       mem->addr[2] + rpf->offsets[1]);
 }
 
-static const struct vsp1_video_operations rpf_vdev_ops = {
-	.queue = rpf_vdev_queue,
+static const struct vsp1_rwpf_operations rpf_vdev_ops = {
+	.set_memory = rpf_set_memory,
 };
 
 /* -----------------------------------------------------------------------------
@@ -219,7 +222,6 @@ static const struct vsp1_video_operations rpf_vdev_ops = {
 struct vsp1_rwpf *vsp1_rpf_create(struct vsp1_device *vsp1, unsigned int index)
 {
 	struct v4l2_subdev *subdev;
-	struct vsp1_video *video;
 	struct vsp1_rwpf *rpf;
 	int ret;
 
@@ -227,6 +229,8 @@ struct vsp1_rwpf *vsp1_rpf_create(struct vsp1_device *vsp1, unsigned int index)
 	if (rpf == NULL)
 		return ERR_PTR(-ENOMEM);
 
+	rpf->ops = &rpf_vdev_ops;
+
 	rpf->max_width = RPF_MAX_WIDTH;
 	rpf->max_height = RPF_MAX_HEIGHT;
 
@@ -241,7 +245,7 @@ struct vsp1_rwpf *vsp1_rpf_create(struct vsp1_device *vsp1, unsigned int index)
 	subdev = &rpf->entity.subdev;
 	v4l2_subdev_init(subdev, &rpf_ops);
 
-	subdev->entity.ops = &vsp1_media_ops;
+	subdev->entity.ops = &vsp1->media_ops;
 	subdev->internal_ops = &vsp1_subdev_internal_ops;
 	snprintf(subdev->name, sizeof(subdev->name), "%s rpf.%u",
 		 dev_name(vsp1->dev), index);
@@ -252,8 +256,9 @@ struct vsp1_rwpf *vsp1_rpf_create(struct vsp1_device *vsp1, unsigned int index)
 
 	/* Initialize the control handler. */
 	v4l2_ctrl_handler_init(&rpf->ctrls, 1);
-	v4l2_ctrl_new_std(&rpf->ctrls, &rpf_ctrl_ops, V4L2_CID_ALPHA_COMPONENT,
-			  0, 255, 1, 255);
+	rpf->alpha = v4l2_ctrl_new_std(&rpf->ctrls, &rpf_ctrl_ops,
+				       V4L2_CID_ALPHA_COMPONENT,
+				       0, 255, 1, 255);
 
 	rpf->entity.subdev.ctrl_handler = &rpf->ctrls;
 
@@ -264,42 +269,9 @@ struct vsp1_rwpf *vsp1_rpf_create(struct vsp1_device *vsp1, unsigned int index)
 		goto error;
 	}
 
-	/* Initialize the video device. */
-	video = &rpf->video;
-
-	video->type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
-	video->vsp1 = vsp1;
-	video->ops = &rpf_vdev_ops;
-
-	ret = vsp1_video_init(video, &rpf->entity);
-	if (ret < 0)
-		goto error;
-
-	rpf->entity.video = video;
-
 	return rpf;
 
 error:
 	vsp1_entity_destroy(&rpf->entity);
 	return ERR_PTR(ret);
 }
-
-/*
- * vsp1_rpf_create_links() - RPF pads links creation
- * @vsp1: Pointer to VSP1 device
- * @entity: Pointer to VSP1 entity
- *
- * return negative error code or zero on success
- */
-int vsp1_rpf_create_links(struct vsp1_device *vsp1,
-			       struct vsp1_entity *entity)
-{
-	struct vsp1_rwpf *rpf = to_rwpf(&entity->subdev);
-
-	/* Connect the video device to the RPF. */
-	return media_create_pad_link(&rpf->video.video.entity, 0,
-				     &rpf->entity.subdev.entity,
-				     RWPF_PAD_SINK,
-				     MEDIA_LNK_FL_ENABLED |
-				     MEDIA_LNK_FL_IMMUTABLE);
-}
diff --git a/drivers/media/platform/vsp1/vsp1_rwpf.h b/drivers/media/platform/vsp1/vsp1_rwpf.h
index 731d36e5258d..8e8235682ada 100644
--- a/drivers/media/platform/vsp1/vsp1_rwpf.h
+++ b/drivers/media/platform/vsp1/vsp1_rwpf.h
@@ -19,19 +19,39 @@
 
 #include "vsp1.h"
 #include "vsp1_entity.h"
-#include "vsp1_video.h"
 
 #define RWPF_PAD_SINK				0
 #define RWPF_PAD_SOURCE				1
 
+struct v4l2_ctrl;
+struct vsp1_rwpf;
+struct vsp1_video;
+
+struct vsp1_rwpf_memory {
+	unsigned int num_planes;
+	dma_addr_t addr[3];
+	unsigned int length[3];
+};
+
+struct vsp1_rwpf_operations {
+	void (*set_memory)(struct vsp1_rwpf *rwpf,
+			   struct vsp1_rwpf_memory *mem);
+};
+
 struct vsp1_rwpf {
 	struct vsp1_entity entity;
-	struct vsp1_video video;
 	struct v4l2_ctrl_handler ctrls;
+	struct v4l2_ctrl *alpha;
+
+	struct vsp1_video *video;
+
+	const struct vsp1_rwpf_operations *ops;
 
 	unsigned int max_width;
 	unsigned int max_height;
 
+	struct v4l2_pix_format_mplane format;
+	const struct vsp1_format_info *fmtinfo;
 	struct {
 		unsigned int left;
 		unsigned int top;
@@ -50,11 +70,6 @@ static inline struct vsp1_rwpf *to_rwpf(struct v4l2_subdev *subdev)
 struct vsp1_rwpf *vsp1_rpf_create(struct vsp1_device *vsp1, unsigned int index);
 struct vsp1_rwpf *vsp1_wpf_create(struct vsp1_device *vsp1, unsigned int index);
 
-int vsp1_rpf_create_links(struct vsp1_device *vsp1,
-			       struct vsp1_entity *entity);
-int vsp1_wpf_create_links(struct vsp1_device *vsp1,
-			       struct vsp1_entity *entity);
-
 int vsp1_rwpf_enum_mbus_code(struct v4l2_subdev *subdev,
 			     struct v4l2_subdev_pad_config *cfg,
 			     struct v4l2_subdev_mbus_code_enum *code);
diff --git a/drivers/media/platform/vsp1/vsp1_sru.c b/drivers/media/platform/vsp1/vsp1_sru.c
index 6310acab60e7..cc09efbfb24f 100644
--- a/drivers/media/platform/vsp1/vsp1_sru.c
+++ b/drivers/media/platform/vsp1/vsp1_sru.c
@@ -151,10 +151,13 @@ static int sru_s_stream(struct v4l2_subdev *subdev, int enable)
 	/* Take the control handler lock to ensure that the CTRL0 value won't be
 	 * changed behind our back by a set control operation.
 	 */
-	mutex_lock(sru->ctrls.lock);
+	if (sru->entity.vsp1->info->uapi)
+		mutex_lock(sru->ctrls.lock);
 	ctrl0 |= vsp1_sru_read(sru, VI6_SRU_CTRL0)
 	       & (VI6_SRU_CTRL0_PARAM0_MASK | VI6_SRU_CTRL0_PARAM1_MASK);
-	mutex_unlock(sru->ctrls.lock);
+	vsp1_sru_write(sru, VI6_SRU_CTRL0, ctrl0);
+	if (sru->entity.vsp1->info->uapi)
+		mutex_unlock(sru->ctrls.lock);
 
 	vsp1_sru_write(sru, VI6_SRU_CTRL1, VI6_SRU_CTRL1_PARAM5);
 
@@ -360,7 +363,7 @@ struct vsp1_sru *vsp1_sru_create(struct vsp1_device *vsp1)
 	subdev = &sru->entity.subdev;
 	v4l2_subdev_init(subdev, &sru_ops);
 
-	subdev->entity.ops = &vsp1_media_ops;
+	subdev->entity.ops = &vsp1->media_ops;
 	subdev->internal_ops = &vsp1_subdev_internal_ops;
 	snprintf(subdev->name, sizeof(subdev->name), "%s sru",
 		 dev_name(vsp1->dev));
diff --git a/drivers/media/platform/vsp1/vsp1_uds.c b/drivers/media/platform/vsp1/vsp1_uds.c
index ccc8243e3493..bba67770cf95 100644
--- a/drivers/media/platform/vsp1/vsp1_uds.c
+++ b/drivers/media/platform/vsp1/vsp1_uds.c
@@ -29,12 +29,6 @@
  * Device Access
  */
 
-static inline u32 vsp1_uds_read(struct vsp1_uds *uds, u32 reg)
-{
-	return vsp1_read(uds->entity.vsp1,
-			 reg + uds->entity.index * VI6_UDS_OFFSET);
-}
-
 static inline void vsp1_uds_write(struct vsp1_uds *uds, u32 reg, u32 data)
 {
 	vsp1_write(uds->entity.vsp1,
@@ -344,7 +338,7 @@ struct vsp1_uds *vsp1_uds_create(struct vsp1_device *vsp1, unsigned int index)
 	subdev = &uds->entity.subdev;
 	v4l2_subdev_init(subdev, &uds_ops);
 
-	subdev->entity.ops = &vsp1_media_ops;
+	subdev->entity.ops = &vsp1->media_ops;
 	subdev->internal_ops = &vsp1_subdev_internal_ops;
 	snprintf(subdev->name, sizeof(subdev->name), "%s uds.%u",
 		 dev_name(vsp1->dev), index);
diff --git a/drivers/media/platform/vsp1/vsp1_video.c b/drivers/media/platform/vsp1/vsp1_video.c
index b4dca57d1ae3..72cc7d3729f8 100644
--- a/drivers/media/platform/vsp1/vsp1_video.c
+++ b/drivers/media/platform/vsp1/vsp1_video.c
@@ -14,10 +14,10 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/v4l2-mediabus.h>
 #include <linux/videodev2.h>
+#include <linux/wait.h>
 
 #include <media/media-entity.h>
 #include <media/v4l2-dev.h>
@@ -30,6 +30,7 @@
 #include "vsp1.h"
 #include "vsp1_bru.h"
 #include "vsp1_entity.h"
+#include "vsp1_pipe.h"
 #include "vsp1_rwpf.h"
 #include "vsp1_uds.h"
 #include "vsp1_video.h"
@@ -47,113 +48,6 @@
  * Helper functions
  */
 
-static const struct vsp1_format_info vsp1_video_formats[] = {
-	{ V4L2_PIX_FMT_RGB332, MEDIA_BUS_FMT_ARGB8888_1X32,
-	  VI6_FMT_RGB_332, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
-	  1, { 8, 0, 0 }, false, false, 1, 1, false },
-	{ V4L2_PIX_FMT_ARGB444, MEDIA_BUS_FMT_ARGB8888_1X32,
-	  VI6_FMT_ARGB_4444, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS,
-	  1, { 16, 0, 0 }, false, false, 1, 1, true },
-	{ V4L2_PIX_FMT_XRGB444, MEDIA_BUS_FMT_ARGB8888_1X32,
-	  VI6_FMT_XRGB_4444, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS,
-	  1, { 16, 0, 0 }, false, false, 1, 1, true },
-	{ V4L2_PIX_FMT_ARGB555, MEDIA_BUS_FMT_ARGB8888_1X32,
-	  VI6_FMT_ARGB_1555, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS,
-	  1, { 16, 0, 0 }, false, false, 1, 1, true },
-	{ V4L2_PIX_FMT_XRGB555, MEDIA_BUS_FMT_ARGB8888_1X32,
-	  VI6_FMT_XRGB_1555, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS,
-	  1, { 16, 0, 0 }, false, false, 1, 1, false },
-	{ V4L2_PIX_FMT_RGB565, MEDIA_BUS_FMT_ARGB8888_1X32,
-	  VI6_FMT_RGB_565, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS,
-	  1, { 16, 0, 0 }, false, false, 1, 1, false },
-	{ V4L2_PIX_FMT_BGR24, MEDIA_BUS_FMT_ARGB8888_1X32,
-	  VI6_FMT_BGR_888, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
-	  1, { 24, 0, 0 }, false, false, 1, 1, false },
-	{ V4L2_PIX_FMT_RGB24, MEDIA_BUS_FMT_ARGB8888_1X32,
-	  VI6_FMT_RGB_888, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
-	  1, { 24, 0, 0 }, false, false, 1, 1, false },
-	{ V4L2_PIX_FMT_ABGR32, MEDIA_BUS_FMT_ARGB8888_1X32,
-	  VI6_FMT_ARGB_8888, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS,
-	  1, { 32, 0, 0 }, false, false, 1, 1, true },
-	{ V4L2_PIX_FMT_XBGR32, MEDIA_BUS_FMT_ARGB8888_1X32,
-	  VI6_FMT_ARGB_8888, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS,
-	  1, { 32, 0, 0 }, false, false, 1, 1, false },
-	{ V4L2_PIX_FMT_ARGB32, MEDIA_BUS_FMT_ARGB8888_1X32,
-	  VI6_FMT_ARGB_8888, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
-	  1, { 32, 0, 0 }, false, false, 1, 1, true },
-	{ V4L2_PIX_FMT_XRGB32, MEDIA_BUS_FMT_ARGB8888_1X32,
-	  VI6_FMT_ARGB_8888, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
-	  1, { 32, 0, 0 }, false, false, 1, 1, false },
-	{ V4L2_PIX_FMT_UYVY, MEDIA_BUS_FMT_AYUV8_1X32,
-	  VI6_FMT_YUYV_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
-	  1, { 16, 0, 0 }, false, false, 2, 1, false },
-	{ V4L2_PIX_FMT_VYUY, MEDIA_BUS_FMT_AYUV8_1X32,
-	  VI6_FMT_YUYV_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
-	  1, { 16, 0, 0 }, false, true, 2, 1, false },
-	{ V4L2_PIX_FMT_YUYV, MEDIA_BUS_FMT_AYUV8_1X32,
-	  VI6_FMT_YUYV_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
-	  1, { 16, 0, 0 }, true, false, 2, 1, false },
-	{ V4L2_PIX_FMT_YVYU, MEDIA_BUS_FMT_AYUV8_1X32,
-	  VI6_FMT_YUYV_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
-	  1, { 16, 0, 0 }, true, true, 2, 1, false },
-	{ V4L2_PIX_FMT_NV12M, MEDIA_BUS_FMT_AYUV8_1X32,
-	  VI6_FMT_Y_UV_420, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
-	  2, { 8, 16, 0 }, false, false, 2, 2, false },
-	{ V4L2_PIX_FMT_NV21M, MEDIA_BUS_FMT_AYUV8_1X32,
-	  VI6_FMT_Y_UV_420, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
-	  2, { 8, 16, 0 }, false, true, 2, 2, false },
-	{ V4L2_PIX_FMT_NV16M, MEDIA_BUS_FMT_AYUV8_1X32,
-	  VI6_FMT_Y_UV_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
-	  2, { 8, 16, 0 }, false, false, 2, 1, false },
-	{ V4L2_PIX_FMT_NV61M, MEDIA_BUS_FMT_AYUV8_1X32,
-	  VI6_FMT_Y_UV_422, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
-	  2, { 8, 16, 0 }, false, true, 2, 1, false },
-	{ V4L2_PIX_FMT_YUV420M, MEDIA_BUS_FMT_AYUV8_1X32,
-	  VI6_FMT_Y_U_V_420, VI6_RPF_DSWAP_P_LLS | VI6_RPF_DSWAP_P_LWS |
-	  VI6_RPF_DSWAP_P_WDS | VI6_RPF_DSWAP_P_BTS,
-	  3, { 8, 8, 8 }, false, false, 2, 2, false },
-};
-
-/*
- * vsp1_get_format_info - Retrieve format information for a 4CC
- * @fourcc: the format 4CC
- *
- * Return a pointer to the format information structure corresponding to the
- * given V4L2 format 4CC, or NULL if no corresponding format can be found.
- */
-static const struct vsp1_format_info *vsp1_get_format_info(u32 fourcc)
-{
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(vsp1_video_formats); ++i) {
-		const struct vsp1_format_info *info = &vsp1_video_formats[i];
-
-		if (info->fourcc == fourcc)
-			return info;
-	}
-
-	return NULL;
-}
-
-
 static struct v4l2_subdev *
 vsp1_video_remote_subdev(struct media_pad *local, u32 *pad)
 {
@@ -184,9 +78,9 @@ static int vsp1_video_verify_format(struct vsp1_video *video)
 	if (ret < 0)
 		return ret == -ENOIOCTLCMD ? -EINVAL : ret;
 
-	if (video->fmtinfo->mbus != fmt.format.code ||
-	    video->format.height != fmt.format.height ||
-	    video->format.width != fmt.format.width)
+	if (video->rwpf->fmtinfo->mbus != fmt.format.code ||
+	    video->rwpf->format.height != fmt.format.height ||
+	    video->rwpf->format.width != fmt.format.width)
 		return -EINVAL;
 
 	return 0;
@@ -277,9 +171,9 @@ static int __vsp1_video_try_format(struct vsp1_video *video,
  * Pipeline Management
  */
 
-static int vsp1_pipeline_validate_branch(struct vsp1_pipeline *pipe,
-					 struct vsp1_rwpf *input,
-					 struct vsp1_rwpf *output)
+static int vsp1_video_pipeline_validate_branch(struct vsp1_pipeline *pipe,
+					       struct vsp1_rwpf *input,
+					       struct vsp1_rwpf *output)
 {
 	struct vsp1_entity *entity;
 	struct media_entity_enum ent_enum;
@@ -370,29 +264,8 @@ out:
 	return rval;
 }
 
-static void __vsp1_pipeline_cleanup(struct vsp1_pipeline *pipe)
-{
-	if (pipe->bru) {
-		struct vsp1_bru *bru = to_bru(&pipe->bru->subdev);
-		unsigned int i;
-
-		for (i = 0; i < ARRAY_SIZE(bru->inputs); ++i)
-			bru->inputs[i].rpf = NULL;
-	}
-
-	INIT_LIST_HEAD(&pipe->entities);
-	pipe->state = VSP1_PIPELINE_STOPPED;
-	pipe->buffers_ready = 0;
-	pipe->num_video = 0;
-	pipe->num_inputs = 0;
-	pipe->output = NULL;
-	pipe->bru = NULL;
-	pipe->lif = NULL;
-	pipe->uds = NULL;
-}
-
-static int vsp1_pipeline_validate(struct vsp1_pipeline *pipe,
-				  struct vsp1_video *video)
+static int vsp1_video_pipeline_validate(struct vsp1_pipeline *pipe,
+					struct vsp1_video *video)
 {
 	struct media_entity_graph graph;
 	struct media_entity *entity = &video->video.entity;
@@ -416,10 +289,8 @@ static int vsp1_pipeline_validate(struct vsp1_pipeline *pipe,
 		struct vsp1_rwpf *rwpf;
 		struct vsp1_entity *e;
 
-		if (is_media_entity_v4l2_io(entity)) {
-			pipe->num_video++;
+		if (!is_media_entity_v4l2_subdev(entity))
 			continue;
-		}
 
 		subdev = media_entity_to_v4l2_subdev(entity);
 		e = to_vsp1_entity(subdev);
@@ -427,12 +298,12 @@ static int vsp1_pipeline_validate(struct vsp1_pipeline *pipe,
 
 		if (e->type == VSP1_ENTITY_RPF) {
 			rwpf = to_rwpf(subdev);
-			pipe->inputs[pipe->num_inputs++] = rwpf;
-			rwpf->video.pipe_index = pipe->num_inputs;
+			pipe->inputs[rwpf->entity.index] = rwpf;
+			rwpf->video->pipe_index = ++pipe->num_inputs;
 		} else if (e->type == VSP1_ENTITY_WPF) {
 			rwpf = to_rwpf(subdev);
-			pipe->output = to_rwpf(subdev);
-			rwpf->video.pipe_index = 0;
+			pipe->output = rwpf;
+			rwpf->video->pipe_index = 0;
 		} else if (e->type == VSP1_ENTITY_LIF) {
 			pipe->lif = e;
 		} else if (e->type == VSP1_ENTITY_BRU) {
@@ -453,9 +324,12 @@ static int vsp1_pipeline_validate(struct vsp1_pipeline *pipe,
 	/* Follow links downstream for each input and make sure the graph
 	 * contains no loop and that all branches end at the output WPF.
 	 */
-	for (i = 0; i < pipe->num_inputs; ++i) {
-		ret = vsp1_pipeline_validate_branch(pipe, pipe->inputs[i],
-						    pipe->output);
+	for (i = 0; i < video->vsp1->info->rpf_count; ++i) {
+		if (!pipe->inputs[i])
+			continue;
+
+		ret = vsp1_video_pipeline_validate_branch(pipe, pipe->inputs[i],
+							  pipe->output);
 		if (ret < 0)
 			goto error;
 	}
@@ -463,12 +337,12 @@ static int vsp1_pipeline_validate(struct vsp1_pipeline *pipe,
 	return 0;
 
 error:
-	__vsp1_pipeline_cleanup(pipe);
+	vsp1_pipeline_reset(pipe);
 	return ret;
 }
 
-static int vsp1_pipeline_init(struct vsp1_pipeline *pipe,
-			      struct vsp1_video *video)
+static int vsp1_video_pipeline_init(struct vsp1_pipeline *pipe,
+				    struct vsp1_video *video)
 {
 	int ret;
 
@@ -476,7 +350,7 @@ static int vsp1_pipeline_init(struct vsp1_pipeline *pipe,
 
 	/* If we're the first user validate and initialize the pipeline. */
 	if (pipe->use_count == 0) {
-		ret = vsp1_pipeline_validate(pipe, video);
+		ret = vsp1_video_pipeline_validate(pipe, video);
 		if (ret < 0)
 			goto done;
 	}
@@ -489,75 +363,17 @@ done:
 	return ret;
 }
 
-static void vsp1_pipeline_cleanup(struct vsp1_pipeline *pipe)
+static void vsp1_video_pipeline_cleanup(struct vsp1_pipeline *pipe)
 {
 	mutex_lock(&pipe->lock);
 
 	/* If we're the last user clean up the pipeline. */
 	if (--pipe->use_count == 0)
-		__vsp1_pipeline_cleanup(pipe);
+		vsp1_pipeline_reset(pipe);
 
 	mutex_unlock(&pipe->lock);
 }
 
-static void vsp1_pipeline_run(struct vsp1_pipeline *pipe)
-{
-	struct vsp1_device *vsp1 = pipe->output->entity.vsp1;
-
-	vsp1_write(vsp1, VI6_CMD(pipe->output->entity.index), VI6_CMD_STRCMD);
-	pipe->state = VSP1_PIPELINE_RUNNING;
-	pipe->buffers_ready = 0;
-}
-
-static bool vsp1_pipeline_stopped(struct vsp1_pipeline *pipe)
-{
-	unsigned long flags;
-	bool stopped;
-
-	spin_lock_irqsave(&pipe->irqlock, flags);
-	stopped = pipe->state == VSP1_PIPELINE_STOPPED;
-	spin_unlock_irqrestore(&pipe->irqlock, flags);
-
-	return stopped;
-}
-
-static int vsp1_pipeline_stop(struct vsp1_pipeline *pipe)
-{
-	struct vsp1_entity *entity;
-	unsigned long flags;
-	int ret;
-
-	spin_lock_irqsave(&pipe->irqlock, flags);
-	if (pipe->state == VSP1_PIPELINE_RUNNING)
-		pipe->state = VSP1_PIPELINE_STOPPING;
-	spin_unlock_irqrestore(&pipe->irqlock, flags);
-
-	ret = wait_event_timeout(pipe->wq, vsp1_pipeline_stopped(pipe),
-				 msecs_to_jiffies(500));
-	ret = ret == 0 ? -ETIMEDOUT : 0;
-
-	list_for_each_entry(entity, &pipe->entities, list_pipe) {
-		if (entity->route && entity->route->reg)
-			vsp1_write(entity->vsp1, entity->route->reg,
-				   VI6_DPR_NODE_UNUSED);
-
-		v4l2_subdev_call(&entity->subdev, video, s_stream, 0);
-	}
-
-	return ret;
-}
-
-static bool vsp1_pipeline_ready(struct vsp1_pipeline *pipe)
-{
-	unsigned int mask;
-
-	mask = ((1 << pipe->num_inputs) - 1) << 1;
-	if (!pipe->lif)
-		mask |= 1 << 0;
-
-	return pipe->buffers_ready == mask;
-}
-
 /*
  * vsp1_video_complete_buffer - Complete the current buffer
  * @video: the video node
@@ -572,12 +388,12 @@ static bool vsp1_pipeline_ready(struct vsp1_pipeline *pipe)
  *
  * Return the next queued buffer or NULL if the queue is empty.
  */
-static struct vsp1_video_buffer *
+static struct vsp1_vb2_buffer *
 vsp1_video_complete_buffer(struct vsp1_video *video)
 {
 	struct vsp1_pipeline *pipe = to_vsp1_pipeline(&video->video.entity);
-	struct vsp1_video_buffer *next = NULL;
-	struct vsp1_video_buffer *done;
+	struct vsp1_vb2_buffer *next = NULL;
+	struct vsp1_vb2_buffer *done;
 	unsigned long flags;
 	unsigned int i;
 
@@ -589,7 +405,7 @@ vsp1_video_complete_buffer(struct vsp1_video *video)
 	}
 
 	done = list_first_entry(&video->irqqueue,
-				struct vsp1_video_buffer, queue);
+				struct vsp1_vb2_buffer, queue);
 
 	/* In DU output mode reuse the buffer if the list is singular. */
 	if (pipe->lif && list_is_singular(&video->irqqueue)) {
@@ -601,23 +417,25 @@ vsp1_video_complete_buffer(struct vsp1_video *video)
 
 	if (!list_empty(&video->irqqueue))
 		next = list_first_entry(&video->irqqueue,
-					struct vsp1_video_buffer, queue);
+					struct vsp1_vb2_buffer, queue);
 
 	spin_unlock_irqrestore(&video->irqlock, flags);
 
 	done->buf.sequence = video->sequence++;
 	done->buf.vb2_buf.timestamp = ktime_get_ns();
 	for (i = 0; i < done->buf.vb2_buf.num_planes; ++i)
-		vb2_set_plane_payload(&done->buf.vb2_buf, i, done->length[i]);
+		vb2_set_plane_payload(&done->buf.vb2_buf, i,
+				      done->mem.length[i]);
 	vb2_buffer_done(&done->buf.vb2_buf, VB2_BUF_STATE_DONE);
 
 	return next;
 }
 
 static void vsp1_video_frame_end(struct vsp1_pipeline *pipe,
-				 struct vsp1_video *video)
+				 struct vsp1_rwpf *rwpf)
 {
-	struct vsp1_video_buffer *buf;
+	struct vsp1_video *video = rwpf->video;
+	struct vsp1_vb2_buffer *buf;
 	unsigned long flags;
 
 	buf = vsp1_video_complete_buffer(video);
@@ -626,155 +444,27 @@ static void vsp1_video_frame_end(struct vsp1_pipeline *pipe,
 
 	spin_lock_irqsave(&pipe->irqlock, flags);
 
-	video->ops->queue(video, buf);
+	video->rwpf->ops->set_memory(video->rwpf, &buf->mem);
 	pipe->buffers_ready |= 1 << video->pipe_index;
 
 	spin_unlock_irqrestore(&pipe->irqlock, flags);
 }
 
-void vsp1_pipeline_frame_end(struct vsp1_pipeline *pipe)
+static void vsp1_video_pipeline_frame_end(struct vsp1_pipeline *pipe)
 {
-	enum vsp1_pipeline_state state;
-	unsigned long flags;
+	struct vsp1_device *vsp1 = pipe->output->entity.vsp1;
 	unsigned int i;
 
-	if (pipe == NULL)
-		return;
-
 	/* Complete buffers on all video nodes. */
-	for (i = 0; i < pipe->num_inputs; ++i)
-		vsp1_video_frame_end(pipe, &pipe->inputs[i]->video);
-
-	if (!pipe->lif)
-		vsp1_video_frame_end(pipe, &pipe->output->video);
-
-	spin_lock_irqsave(&pipe->irqlock, flags);
-
-	state = pipe->state;
-	pipe->state = VSP1_PIPELINE_STOPPED;
-
-	/* If a stop has been requested, mark the pipeline as stopped and
-	 * return.
-	 */
-	if (state == VSP1_PIPELINE_STOPPING) {
-		wake_up(&pipe->wq);
-		goto done;
-	}
-
-	/* Restart the pipeline if ready. */
-	if (vsp1_pipeline_ready(pipe))
-		vsp1_pipeline_run(pipe);
-
-done:
-	spin_unlock_irqrestore(&pipe->irqlock, flags);
-}
-
-/*
- * Propagate the alpha value through the pipeline.
- *
- * As the UDS has restricted scaling capabilities when the alpha component needs
- * to be scaled, we disable alpha scaling when the UDS input has a fixed alpha
- * value. The UDS then outputs a fixed alpha value which needs to be programmed
- * from the input RPF alpha.
- */
-void vsp1_pipeline_propagate_alpha(struct vsp1_pipeline *pipe,
-				   struct vsp1_entity *input,
-				   unsigned int alpha)
-{
-	struct vsp1_entity *entity;
-	struct media_pad *pad;
-
-	pad = media_entity_remote_pad(&input->pads[RWPF_PAD_SOURCE]);
-
-	while (pad) {
-		if (!is_media_entity_v4l2_subdev(pad->entity))
-			break;
-
-		entity = to_vsp1_entity(media_entity_to_v4l2_subdev(pad->entity));
-
-		/* The BRU background color has a fixed alpha value set to 255,
-		 * the output alpha value is thus always equal to 255.
-		 */
-		if (entity->type == VSP1_ENTITY_BRU)
-			alpha = 255;
-
-		if (entity->type == VSP1_ENTITY_UDS) {
-			struct vsp1_uds *uds = to_uds(&entity->subdev);
-
-			vsp1_uds_set_alpha(uds, alpha);
-			break;
-		}
-
-		pad = &entity->pads[entity->source_pad];
-		pad = media_entity_remote_pad(pad);
-	}
-}
-
-void vsp1_pipelines_suspend(struct vsp1_device *vsp1)
-{
-	unsigned long flags;
-	unsigned int i;
-	int ret;
-
-	/* To avoid increasing the system suspend time needlessly, loop over the
-	 * pipelines twice, first to set them all to the stopping state, and then
-	 * to wait for the stop to complete.
-	 */
-	for (i = 0; i < vsp1->pdata.wpf_count; ++i) {
-		struct vsp1_rwpf *wpf = vsp1->wpf[i];
-		struct vsp1_pipeline *pipe;
-
-		if (wpf == NULL)
-			continue;
-
-		pipe = to_vsp1_pipeline(&wpf->entity.subdev.entity);
-		if (pipe == NULL)
-			continue;
-
-		spin_lock_irqsave(&pipe->irqlock, flags);
-		if (pipe->state == VSP1_PIPELINE_RUNNING)
-			pipe->state = VSP1_PIPELINE_STOPPING;
-		spin_unlock_irqrestore(&pipe->irqlock, flags);
-	}
-
-	for (i = 0; i < vsp1->pdata.wpf_count; ++i) {
-		struct vsp1_rwpf *wpf = vsp1->wpf[i];
-		struct vsp1_pipeline *pipe;
-
-		if (wpf == NULL)
-			continue;
-
-		pipe = to_vsp1_pipeline(&wpf->entity.subdev.entity);
-		if (pipe == NULL)
+	for (i = 0; i < vsp1->info->rpf_count; ++i) {
+		if (!pipe->inputs[i])
 			continue;
 
-		ret = wait_event_timeout(pipe->wq, vsp1_pipeline_stopped(pipe),
-					 msecs_to_jiffies(500));
-		if (ret == 0)
-			dev_warn(vsp1->dev, "pipeline %u stop timeout\n",
-				 wpf->entity.index);
+		vsp1_video_frame_end(pipe, pipe->inputs[i]);
 	}
-}
-
-void vsp1_pipelines_resume(struct vsp1_device *vsp1)
-{
-	unsigned int i;
-
-	/* Resume pipeline all running pipelines. */
-	for (i = 0; i < vsp1->pdata.wpf_count; ++i) {
-		struct vsp1_rwpf *wpf = vsp1->wpf[i];
-		struct vsp1_pipeline *pipe;
 
-		if (wpf == NULL)
-			continue;
-
-		pipe = to_vsp1_pipeline(&wpf->entity.subdev.entity);
-		if (pipe == NULL)
-			continue;
-
-		if (vsp1_pipeline_ready(pipe))
-			vsp1_pipeline_run(pipe);
-	}
+	if (!pipe->lif)
+		vsp1_video_frame_end(pipe, pipe->output);
 }
 
 /* -----------------------------------------------------------------------------
@@ -787,7 +477,7 @@ vsp1_video_queue_setup(struct vb2_queue *vq,
 		     unsigned int sizes[], void *alloc_ctxs[])
 {
 	struct vsp1_video *video = vb2_get_drv_priv(vq);
-	const struct v4l2_pix_format_mplane *format = &video->format;
+	const struct v4l2_pix_format_mplane *format = &video->rwpf->format;
 	unsigned int i;
 
 	if (*nplanes) {
@@ -816,18 +506,20 @@ static int vsp1_video_buffer_prepare(struct vb2_buffer *vb)
 {
 	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
 	struct vsp1_video *video = vb2_get_drv_priv(vb->vb2_queue);
-	struct vsp1_video_buffer *buf = to_vsp1_video_buffer(vbuf);
-	const struct v4l2_pix_format_mplane *format = &video->format;
+	struct vsp1_vb2_buffer *buf = to_vsp1_vb2_buffer(vbuf);
+	const struct v4l2_pix_format_mplane *format = &video->rwpf->format;
 	unsigned int i;
 
 	if (vb->num_planes < format->num_planes)
 		return -EINVAL;
 
+	buf->mem.num_planes = vb->num_planes;
+
 	for (i = 0; i < vb->num_planes; ++i) {
-		buf->addr[i] = vb2_dma_contig_plane_dma_addr(vb, i);
-		buf->length[i] = vb2_plane_size(vb, i);
+		buf->mem.addr[i] = vb2_dma_contig_plane_dma_addr(vb, i);
+		buf->mem.length[i] = vb2_plane_size(vb, i);
 
-		if (buf->length[i] < format->plane_fmt[i].sizeimage)
+		if (buf->mem.length[i] < format->plane_fmt[i].sizeimage)
 			return -EINVAL;
 	}
 
@@ -839,7 +531,7 @@ static void vsp1_video_buffer_queue(struct vb2_buffer *vb)
 	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
 	struct vsp1_video *video = vb2_get_drv_priv(vb->vb2_queue);
 	struct vsp1_pipeline *pipe = to_vsp1_pipeline(&video->video.entity);
-	struct vsp1_video_buffer *buf = to_vsp1_video_buffer(vbuf);
+	struct vsp1_vb2_buffer *buf = to_vsp1_vb2_buffer(vbuf);
 	unsigned long flags;
 	bool empty;
 
@@ -853,7 +545,7 @@ static void vsp1_video_buffer_queue(struct vb2_buffer *vb)
 
 	spin_lock_irqsave(&pipe->irqlock, flags);
 
-	video->ops->queue(video, buf);
+	video->rwpf->ops->set_memory(video->rwpf, &buf->mem);
 	pipe->buffers_ready |= 1 << video->pipe_index;
 
 	if (vb2_is_streaming(&video->queue) &&
@@ -863,18 +555,6 @@ static void vsp1_video_buffer_queue(struct vb2_buffer *vb)
 	spin_unlock_irqrestore(&pipe->irqlock, flags);
 }
 
-static void vsp1_entity_route_setup(struct vsp1_entity *source)
-{
-	struct vsp1_entity *sink;
-
-	if (source->route->reg == 0)
-		return;
-
-	sink = container_of(source->sink, struct vsp1_entity, subdev.entity);
-	vsp1_write(source->vsp1, source->route->reg,
-		   sink->route->inputs[source->sink_pad]);
-}
-
 static int vsp1_video_start_streaming(struct vb2_queue *vq, unsigned int count)
 {
 	struct vsp1_video *video = vb2_get_drv_priv(vq);
@@ -884,7 +564,7 @@ static int vsp1_video_start_streaming(struct vb2_queue *vq, unsigned int count)
 	int ret;
 
 	mutex_lock(&pipe->lock);
-	if (pipe->stream_count == pipe->num_video - 1) {
+	if (pipe->stream_count == pipe->num_inputs) {
 		if (pipe->uds) {
 			struct vsp1_uds *uds = to_uds(&pipe->uds->subdev);
 
@@ -900,7 +580,7 @@ static int vsp1_video_start_streaming(struct vb2_queue *vq, unsigned int count)
 				struct vsp1_rwpf *rpf =
 					to_rwpf(&pipe->uds_input->subdev);
 
-				uds->scale_alpha = rpf->video.fmtinfo->alpha;
+				uds->scale_alpha = rpf->fmtinfo->alpha;
 			}
 		}
 
@@ -931,7 +611,7 @@ static void vsp1_video_stop_streaming(struct vb2_queue *vq)
 {
 	struct vsp1_video *video = vb2_get_drv_priv(vq);
 	struct vsp1_pipeline *pipe = to_vsp1_pipeline(&video->video.entity);
-	struct vsp1_video_buffer *buffer;
+	struct vsp1_vb2_buffer *buffer;
 	unsigned long flags;
 	int ret;
 
@@ -944,7 +624,7 @@ static void vsp1_video_stop_streaming(struct vb2_queue *vq)
 	}
 	mutex_unlock(&pipe->lock);
 
-	vsp1_pipeline_cleanup(pipe);
+	vsp1_video_pipeline_cleanup(pipe);
 	media_entity_pipeline_stop(&video->video.entity);
 
 	/* Remove all buffers from the IRQ queue. */
@@ -1004,7 +684,7 @@ vsp1_video_get_format(struct file *file, void *fh, struct v4l2_format *format)
 		return -EINVAL;
 
 	mutex_lock(&video->lock);
-	format->fmt.pix_mp = video->format;
+	format->fmt.pix_mp = video->rwpf->format;
 	mutex_unlock(&video->lock);
 
 	return 0;
@@ -1044,8 +724,8 @@ vsp1_video_set_format(struct file *file, void *fh, struct v4l2_format *format)
 		goto done;
 	}
 
-	video->format = format->fmt.pix_mp;
-	video->fmtinfo = info;
+	video->rwpf->format = format->fmt.pix_mp;
+	video->rwpf->fmtinfo = info;
 
 done:
 	mutex_unlock(&video->lock);
@@ -1085,7 +765,7 @@ vsp1_video_streamon(struct file *file, void *fh, enum v4l2_buf_type type)
 	if (ret < 0)
 		goto err_stop;
 
-	ret = vsp1_pipeline_init(pipe, video);
+	ret = vsp1_video_pipeline_init(pipe, video);
 	if (ret < 0)
 		goto err_stop;
 
@@ -1097,7 +777,7 @@ vsp1_video_streamon(struct file *file, void *fh, enum v4l2_buf_type type)
 	return 0;
 
 err_cleanup:
-	vsp1_pipeline_cleanup(pipe);
+	vsp1_video_pipeline_cleanup(pipe);
 err_stop:
 	media_entity_pipeline_stop(&video->video.entity);
 	return ret;
@@ -1183,62 +863,64 @@ static struct v4l2_file_operations vsp1_video_fops = {
  * Initialization and Cleanup
  */
 
-int vsp1_video_init(struct vsp1_video *video, struct vsp1_entity *rwpf)
+struct vsp1_video *vsp1_video_create(struct vsp1_device *vsp1,
+				     struct vsp1_rwpf *rwpf)
 {
+	struct vsp1_video *video;
 	const char *direction;
 	int ret;
 
-	switch (video->type) {
-	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
-		direction = "output";
-		video->pad.flags = MEDIA_PAD_FL_SINK;
-		break;
+	video = devm_kzalloc(vsp1->dev, sizeof(*video), GFP_KERNEL);
+	if (!video)
+		return ERR_PTR(-ENOMEM);
+
+	rwpf->video = video;
+
+	video->vsp1 = vsp1;
+	video->rwpf = rwpf;
 
-	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+	if (rwpf->entity.type == VSP1_ENTITY_RPF) {
 		direction = "input";
+		video->type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
 		video->pad.flags = MEDIA_PAD_FL_SOURCE;
 		video->video.vfl_dir = VFL_DIR_TX;
-		break;
-
-	default:
-		return -EINVAL;
+	} else {
+		direction = "output";
+		video->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
+		video->pad.flags = MEDIA_PAD_FL_SINK;
+		video->video.vfl_dir = VFL_DIR_RX;
 	}
 
-	video->rwpf = rwpf;
-
 	mutex_init(&video->lock);
 	spin_lock_init(&video->irqlock);
 	INIT_LIST_HEAD(&video->irqqueue);
 
-	mutex_init(&video->pipe.lock);
-	spin_lock_init(&video->pipe.irqlock);
-	INIT_LIST_HEAD(&video->pipe.entities);
-	init_waitqueue_head(&video->pipe.wq);
-	video->pipe.state = VSP1_PIPELINE_STOPPED;
+	vsp1_pipeline_init(&video->pipe);
+	video->pipe.frame_end = vsp1_video_pipeline_frame_end;
 
 	/* Initialize the media entity... */
 	ret = media_entity_pads_init(&video->video.entity, 1, &video->pad);
 	if (ret < 0)
-		return ret;
+		return ERR_PTR(ret);
 
 	/* ... and the format ... */
-	video->fmtinfo = vsp1_get_format_info(VSP1_VIDEO_DEF_FORMAT);
-	video->format.pixelformat = video->fmtinfo->fourcc;
-	video->format.colorspace = V4L2_COLORSPACE_SRGB;
-	video->format.field = V4L2_FIELD_NONE;
-	video->format.width = VSP1_VIDEO_DEF_WIDTH;
-	video->format.height = VSP1_VIDEO_DEF_HEIGHT;
-	video->format.num_planes = 1;
-	video->format.plane_fmt[0].bytesperline =
-		video->format.width * video->fmtinfo->bpp[0] / 8;
-	video->format.plane_fmt[0].sizeimage =
-		video->format.plane_fmt[0].bytesperline * video->format.height;
+	rwpf->fmtinfo = vsp1_get_format_info(VSP1_VIDEO_DEF_FORMAT);
+	rwpf->format.pixelformat = rwpf->fmtinfo->fourcc;
+	rwpf->format.colorspace = V4L2_COLORSPACE_SRGB;
+	rwpf->format.field = V4L2_FIELD_NONE;
+	rwpf->format.width = VSP1_VIDEO_DEF_WIDTH;
+	rwpf->format.height = VSP1_VIDEO_DEF_HEIGHT;
+	rwpf->format.num_planes = 1;
+	rwpf->format.plane_fmt[0].bytesperline =
+		rwpf->format.width * rwpf->fmtinfo->bpp[0] / 8;
+	rwpf->format.plane_fmt[0].sizeimage =
+		rwpf->format.plane_fmt[0].bytesperline * rwpf->format.height;
 
 	/* ... and the video node... */
 	video->video.v4l2_dev = &video->vsp1->v4l2_dev;
 	video->video.fops = &vsp1_video_fops;
 	snprintf(video->video.name, sizeof(video->video.name), "%s %s",
-		 rwpf->subdev.name, direction);
+		 rwpf->entity.subdev.name, direction);
 	video->video.vfl_type = VFL_TYPE_GRABBER;
 	video->video.release = video_device_release_empty;
 	video->video.ioctl_ops = &vsp1_video_ioctl_ops;
@@ -1256,7 +938,7 @@ int vsp1_video_init(struct vsp1_video *video, struct vsp1_entity *rwpf)
 	video->queue.io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF;
 	video->queue.lock = &video->lock;
 	video->queue.drv_priv = video;
-	video->queue.buf_struct_size = sizeof(struct vsp1_video_buffer);
+	video->queue.buf_struct_size = sizeof(struct vsp1_vb2_buffer);
 	video->queue.ops = &vsp1_video_queue_qops;
 	video->queue.mem_ops = &vb2_dma_contig_memops;
 	video->queue.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
@@ -1274,12 +956,12 @@ int vsp1_video_init(struct vsp1_video *video, struct vsp1_entity *rwpf)
 		goto error;
 	}
 
-	return 0;
+	return video;
 
 error:
 	vb2_dma_contig_cleanup_ctx(video->alloc_ctx);
 	vsp1_video_cleanup(video);
-	return ret;
+	return ERR_PTR(ret);
 }
 
 void vsp1_video_cleanup(struct vsp1_video *video)
diff --git a/drivers/media/platform/vsp1/vsp1_video.h b/drivers/media/platform/vsp1/vsp1_video.h
index a929aa81cdbf..64abd39ee1e7 100644
--- a/drivers/media/platform/vsp1/vsp1_video.h
+++ b/drivers/media/platform/vsp1/vsp1_video.h
@@ -15,115 +15,34 @@
 
 #include <linux/list.h>
 #include <linux/spinlock.h>
-#include <linux/wait.h>
 
-#include <media/media-entity.h>
 #include <media/videobuf2-v4l2.h>
 
-struct vsp1_video;
+#include "vsp1_pipe.h"
+#include "vsp1_rwpf.h"
 
-/*
- * struct vsp1_format_info - VSP1 video format description
- * @mbus: media bus format code
- * @fourcc: V4L2 pixel format FCC identifier
- * @planes: number of planes
- * @bpp: bits per pixel
- * @hwfmt: VSP1 hardware format
- * @swap_yc: the Y and C components are swapped (Y comes before C)
- * @swap_uv: the U and V components are swapped (V comes before U)
- * @hsub: horizontal subsampling factor
- * @vsub: vertical subsampling factor
- * @alpha: has an alpha channel
- */
-struct vsp1_format_info {
-	u32 fourcc;
-	unsigned int mbus;
-	unsigned int hwfmt;
-	unsigned int swap;
-	unsigned int planes;
-	unsigned int bpp[3];
-	bool swap_yc;
-	bool swap_uv;
-	unsigned int hsub;
-	unsigned int vsub;
-	bool alpha;
-};
-
-enum vsp1_pipeline_state {
-	VSP1_PIPELINE_STOPPED,
-	VSP1_PIPELINE_RUNNING,
-	VSP1_PIPELINE_STOPPING,
-};
-
-/*
- * struct vsp1_pipeline - A VSP1 hardware pipeline
- * @media: the media pipeline
- * @irqlock: protects the pipeline state
- * @lock: protects the pipeline use count and stream count
- */
-struct vsp1_pipeline {
-	struct media_pipeline pipe;
-
-	spinlock_t irqlock;
-	enum vsp1_pipeline_state state;
-	wait_queue_head_t wq;
-
-	struct mutex lock;
-	unsigned int use_count;
-	unsigned int stream_count;
-	unsigned int buffers_ready;
-
-	unsigned int num_video;
-	unsigned int num_inputs;
-	struct vsp1_rwpf *inputs[VSP1_MAX_RPF];
-	struct vsp1_rwpf *output;
-	struct vsp1_entity *bru;
-	struct vsp1_entity *lif;
-	struct vsp1_entity *uds;
-	struct vsp1_entity *uds_input;
-
-	struct list_head entities;
-};
-
-static inline struct vsp1_pipeline *to_vsp1_pipeline(struct media_entity *e)
-{
-	if (likely(e->pipe))
-		return container_of(e->pipe, struct vsp1_pipeline, pipe);
-	else
-		return NULL;
-}
-
-struct vsp1_video_buffer {
+struct vsp1_vb2_buffer {
 	struct vb2_v4l2_buffer buf;
 	struct list_head queue;
-
-	dma_addr_t addr[3];
-	unsigned int length[3];
+	struct vsp1_rwpf_memory mem;
 };
 
-static inline struct vsp1_video_buffer *
-to_vsp1_video_buffer(struct vb2_v4l2_buffer *vbuf)
+static inline struct vsp1_vb2_buffer *
+to_vsp1_vb2_buffer(struct vb2_v4l2_buffer *vbuf)
 {
-	return container_of(vbuf, struct vsp1_video_buffer, buf);
+	return container_of(vbuf, struct vsp1_vb2_buffer, buf);
 }
 
-struct vsp1_video_operations {
-	void (*queue)(struct vsp1_video *video, struct vsp1_video_buffer *buf);
-};
-
 struct vsp1_video {
+	struct list_head list;
 	struct vsp1_device *vsp1;
-	struct vsp1_entity *rwpf;
-
-	const struct vsp1_video_operations *ops;
+	struct vsp1_rwpf *rwpf;
 
 	struct video_device video;
 	enum v4l2_buf_type type;
 	struct media_pad pad;
 
 	struct mutex lock;
-	struct v4l2_pix_format_mplane format;
-	const struct vsp1_format_info *fmtinfo;
 
 	struct vsp1_pipeline pipe;
 	unsigned int pipe_index;
@@ -140,16 +59,8 @@ static inline struct vsp1_video *to_vsp1_video(struct video_device *vdev)
 	return container_of(vdev, struct vsp1_video, video);
 }
 
-int vsp1_video_init(struct vsp1_video *video, struct vsp1_entity *rwpf);
+struct vsp1_video *vsp1_video_create(struct vsp1_device *vsp1,
+				     struct vsp1_rwpf *rwpf);
 void vsp1_video_cleanup(struct vsp1_video *video);
 
-void vsp1_pipeline_frame_end(struct vsp1_pipeline *pipe);
-
-void vsp1_pipeline_propagate_alpha(struct vsp1_pipeline *pipe,
-				   struct vsp1_entity *input,
-				   unsigned int alpha);
-
-void vsp1_pipelines_suspend(struct vsp1_device *vsp1);
-void vsp1_pipelines_resume(struct vsp1_device *vsp1);
-
 #endif /* __VSP1_VIDEO_H__ */
diff --git a/drivers/media/platform/vsp1/vsp1_wpf.c b/drivers/media/platform/vsp1/vsp1_wpf.c
index cbf514a6582d..c78d4af50fcf 100644
--- a/drivers/media/platform/vsp1/vsp1_wpf.c
+++ b/drivers/media/platform/vsp1/vsp1_wpf.c
@@ -34,8 +34,8 @@ static inline u32 vsp1_wpf_read(struct vsp1_rwpf *wpf, u32 reg)
 
 static inline void vsp1_wpf_write(struct vsp1_rwpf *wpf, u32 reg, u32 data)
 {
-	vsp1_write(wpf->entity.vsp1,
-		   reg + wpf->entity.index * VI6_WPF_OFFSET, data);
+	vsp1_mod_write(&wpf->entity,
+		       reg + wpf->entity.index * VI6_WPF_OFFSET, data);
 }
 
 /* -----------------------------------------------------------------------------
@@ -88,7 +88,8 @@ static int wpf_s_stream(struct v4l2_subdev *subdev, int enable)
 
 	if (!enable) {
 		vsp1_write(vsp1, VI6_WPF_IRQ_ENB(wpf->entity.index), 0);
-		vsp1_wpf_write(wpf, VI6_WPF_SRCRPF, 0);
+		vsp1_write(vsp1, wpf->entity.index * VI6_WPF_OFFSET +
+			   VI6_WPF_SRCRPF, 0);
 		return 0;
 	}
 
@@ -97,9 +98,12 @@ static int wpf_s_stream(struct v4l2_subdev *subdev, int enable)
 	 * inputs as sub-layers and select the virtual RPF as the master
 	 * layer.
 	 */
-	for (i = 0; i < pipe->num_inputs; ++i) {
+	for (i = 0; i < vsp1->info->rpf_count; ++i) {
 		struct vsp1_rwpf *input = pipe->inputs[i];
 
+		if (!input)
+			continue;
+
 		srcrpf |= (!pipe->bru && pipe->num_inputs == 1)
 			? VI6_WPF_SRCRPF_RPF_ACT_MST(input->entity.index)
 			: VI6_WPF_SRCRPF_RPF_ACT_SUB(input->entity.index);
@@ -112,7 +116,7 @@ static int wpf_s_stream(struct v4l2_subdev *subdev, int enable)
 
 	/* Destination stride. */
 	if (!pipe->lif) {
-		struct v4l2_pix_format_mplane *format = &wpf->video.format;
+		struct v4l2_pix_format_mplane *format = &wpf->format;
 
 		vsp1_wpf_write(wpf, VI6_WPF_DSTM_STRIDE_Y,
 			       format->plane_fmt[0].bytesperline);
@@ -130,7 +134,7 @@ static int wpf_s_stream(struct v4l2_subdev *subdev, int enable)
 
 	/* Format */
 	if (!pipe->lif) {
-		const struct vsp1_format_info *fmtinfo = wpf->video.fmtinfo;
+		const struct vsp1_format_info *fmtinfo = wpf->fmtinfo;
 
 		outfmt = fmtinfo->hwfmt << VI6_WPF_OUTFMT_WRFMT_SHIFT;
 
@@ -151,15 +155,17 @@ static int wpf_s_stream(struct v4l2_subdev *subdev, int enable)
 	/* Take the control handler lock to ensure that the PDV value won't be
 	 * changed behind our back by a set control operation.
 	 */
-	mutex_lock(wpf->ctrls.lock);
-	outfmt |= vsp1_wpf_read(wpf, VI6_WPF_OUTFMT) & VI6_WPF_OUTFMT_PDV_MASK;
+	if (vsp1->info->uapi)
+		mutex_lock(wpf->ctrls.lock);
+	outfmt |= wpf->alpha->cur.val << VI6_WPF_OUTFMT_PDV_SHIFT;
 	vsp1_wpf_write(wpf, VI6_WPF_OUTFMT, outfmt);
-	mutex_unlock(wpf->ctrls.lock);
+	if (vsp1->info->uapi)
+		mutex_unlock(wpf->ctrls.lock);
 
-	vsp1_write(vsp1, VI6_DPR_WPF_FPORCH(wpf->entity.index),
-		   VI6_DPR_WPF_FPORCH_FP_WPFN);
+	vsp1_mod_write(&wpf->entity, VI6_DPR_WPF_FPORCH(wpf->entity.index),
+		       VI6_DPR_WPF_FPORCH_FP_WPFN);
 
-	vsp1_write(vsp1, VI6_WPF_WRBCK_CTRL, 0);
+	vsp1_mod_write(&wpf->entity, VI6_WPF_WRBCK_CTRL, 0);
 
 	/* Enable interrupts */
 	vsp1_write(vsp1, VI6_WPF_IRQ_STA(wpf->entity.index), 0);
@@ -195,20 +201,17 @@ static struct v4l2_subdev_ops wpf_ops = {
  * Video Device Operations
  */
 
-static void wpf_vdev_queue(struct vsp1_video *video,
-			   struct vsp1_video_buffer *buf)
+static void wpf_set_memory(struct vsp1_rwpf *wpf, struct vsp1_rwpf_memory *mem)
 {
-	struct vsp1_rwpf *wpf = container_of(video, struct vsp1_rwpf, video);
-
-	vsp1_wpf_write(wpf, VI6_WPF_DSTM_ADDR_Y, buf->addr[0]);
-	if (buf->buf.vb2_buf.num_planes > 1)
-		vsp1_wpf_write(wpf, VI6_WPF_DSTM_ADDR_C0, buf->addr[1]);
-	if (buf->buf.vb2_buf.num_planes > 2)
-		vsp1_wpf_write(wpf, VI6_WPF_DSTM_ADDR_C1, buf->addr[2]);
+	vsp1_wpf_write(wpf, VI6_WPF_DSTM_ADDR_Y, mem->addr[0]);
+	if (mem->num_planes > 1)
+		vsp1_wpf_write(wpf, VI6_WPF_DSTM_ADDR_C0, mem->addr[1]);
+	if (mem->num_planes > 2)
+		vsp1_wpf_write(wpf, VI6_WPF_DSTM_ADDR_C1, mem->addr[2]);
 }
 
-static const struct vsp1_video_operations wpf_vdev_ops = {
-	.queue = wpf_vdev_queue,
+static const struct vsp1_rwpf_operations wpf_vdev_ops = {
+	.set_memory = wpf_set_memory,
 };
 
 /* -----------------------------------------------------------------------------
@@ -218,7 +221,6 @@ static const struct vsp1_video_operations wpf_vdev_ops = {
 struct vsp1_rwpf *vsp1_wpf_create(struct vsp1_device *vsp1, unsigned int index)
 {
 	struct v4l2_subdev *subdev;
-	struct vsp1_video *video;
 	struct vsp1_rwpf *wpf;
 	int ret;
 
@@ -226,6 +228,8 @@ struct vsp1_rwpf *vsp1_wpf_create(struct vsp1_device *vsp1, unsigned int index)
 	if (wpf == NULL)
 		return ERR_PTR(-ENOMEM);
 
+	wpf->ops = &wpf_vdev_ops;
+
 	wpf->max_width = WPF_MAX_WIDTH;
 	wpf->max_height = WPF_MAX_HEIGHT;
 
@@ -240,7 +244,7 @@ struct vsp1_rwpf *vsp1_wpf_create(struct vsp1_device *vsp1, unsigned int index)
 	subdev = &wpf->entity.subdev;
 	v4l2_subdev_init(subdev, &wpf_ops);
 
-	subdev->entity.ops = &vsp1_media_ops;
+	subdev->entity.ops = &vsp1->media_ops;
 	subdev->internal_ops = &vsp1_subdev_internal_ops;
 	snprintf(subdev->name, sizeof(subdev->name), "%s wpf.%u",
 		 dev_name(vsp1->dev), index);
@@ -251,8 +255,9 @@ struct vsp1_rwpf *vsp1_wpf_create(struct vsp1_device *vsp1, unsigned int index)
 
 	/* Initialize the control handler. */
 	v4l2_ctrl_handler_init(&wpf->ctrls, 1);
-	v4l2_ctrl_new_std(&wpf->ctrls, &wpf_ctrl_ops, V4L2_CID_ALPHA_COMPONENT,
-			  0, 255, 1, 255);
+	wpf->alpha = v4l2_ctrl_new_std(&wpf->ctrls, &wpf_ctrl_ops,
+				       V4L2_CID_ALPHA_COMPONENT,
+				       0, 255, 1, 255);
 
 	wpf->entity.subdev.ctrl_handler = &wpf->ctrls;
 
@@ -263,48 +268,9 @@ struct vsp1_rwpf *vsp1_wpf_create(struct vsp1_device *vsp1, unsigned int index)
 		goto error;
 	}
 
-	/* Initialize the video device. */
-	video = &wpf->video;
-
-	video->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
-	video->vsp1 = vsp1;
-	video->ops = &wpf_vdev_ops;
-
-	ret = vsp1_video_init(video, &wpf->entity);
-	if (ret < 0)
-		goto error;
-
-	wpf->entity.video = video;
-	wpf->entity.sink = &wpf->video.video.entity;
-
 	return wpf;
 
 error:
 	vsp1_entity_destroy(&wpf->entity);
 	return ERR_PTR(ret);
 }
-
-/*
- * vsp1_wpf_create_links() - RPF pads links creation
- * @vsp1: Pointer to VSP1 device
- * @entity: Pointer to VSP1 entity
- *
- * return negative error code or zero on success
- */
-int vsp1_wpf_create_links(struct vsp1_device *vsp1,
-			       struct vsp1_entity *entity)
-{
-	struct vsp1_rwpf *wpf = to_rwpf(&entity->subdev);
-	unsigned int flags;
-
-	/* Connect the video device to the WPF. All connections are immutable
-	 * except for the WPF0 source link if a LIF is present.
-	 */
-	flags = MEDIA_LNK_FL_ENABLED;
-	if (!(vsp1->pdata.features & VSP1_HAS_LIF) || entity->index != 0)
-		flags |= MEDIA_LNK_FL_IMMUTABLE;
-
-	return media_create_pad_link(&wpf->entity.subdev.entity,
-				     RWPF_PAD_SOURCE,
-				     &wpf->video.video.entity, 0, flags);
-}
diff --git a/drivers/media/radio/radio-si476x.c b/drivers/media/radio/radio-si476x.c
index 859f0c08ee05..271f725b17e8 100644
--- a/drivers/media/radio/radio-si476x.c
+++ b/drivers/media/radio/radio-si476x.c
@@ -1530,11 +1530,11 @@ static int si476x_radio_probe(struct platform_device *pdev)
 	if (si476x_core_has_diversity(radio->core)) {
 		si476x_ctrls[SI476X_IDX_DIVERSITY_MODE].def =
 			si476x_phase_diversity_mode_to_idx(radio->core->diversity_mode);
-		si476x_radio_add_new_custom(radio, SI476X_IDX_DIVERSITY_MODE);
+		rval = si476x_radio_add_new_custom(radio, SI476X_IDX_DIVERSITY_MODE);
 		if (rval < 0)
 			goto exit;
 
-		si476x_radio_add_new_custom(radio, SI476X_IDX_INTERCHIP_LINK);
+		rval = si476x_radio_add_new_custom(radio, SI476X_IDX_INTERCHIP_LINK);
 		if (rval < 0)
 			goto exit;
 	}
diff --git a/drivers/media/radio/tea575x.c b/drivers/media/radio/tea575x.c
index 3e08475af579..4dc2067bce14 100644
--- a/drivers/media/radio/tea575x.c
+++ b/drivers/media/radio/tea575x.c
@@ -14,10 +14,6 @@
  *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *   GNU General Public License for more details.
  *
- *   You should have received a copy of the GNU General Public License
- *   along with this program; if not, write to the Free Software
- *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
  */
 
 #include <linux/delay.h>
@@ -226,6 +222,7 @@ void snd_tea575x_set_freq(struct snd_tea575x *tea)
 	snd_tea575x_write(tea, tea->val);
 	tea->freq = snd_tea575x_val_to_freq(tea, tea->val);
 }
+EXPORT_SYMBOL(snd_tea575x_set_freq);
 
 /*
  * Linux Video interface
@@ -582,25 +579,11 @@ int snd_tea575x_init(struct snd_tea575x *tea, struct module *owner)
 
 	return 0;
 }
+EXPORT_SYMBOL(snd_tea575x_init);
 
 void snd_tea575x_exit(struct snd_tea575x *tea)
 {
 	video_unregister_device(&tea->vd);
 	v4l2_ctrl_handler_free(tea->vd.ctrl_handler);
 }
-
-static int __init alsa_tea575x_module_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_tea575x_module_exit(void)
-{
-}
-
-module_init(alsa_tea575x_module_init)
-module_exit(alsa_tea575x_module_exit)
-
-EXPORT_SYMBOL(snd_tea575x_init);
 EXPORT_SYMBOL(snd_tea575x_exit);
-EXPORT_SYMBOL(snd_tea575x_set_freq);
diff --git a/drivers/media/radio/wl128x/fmdrv_common.c b/drivers/media/radio/wl128x/fmdrv_common.c
index ebc73b034249..3f9e6df7d837 100644
--- a/drivers/media/radio/wl128x/fmdrv_common.c
+++ b/drivers/media/radio/wl128x/fmdrv_common.c
@@ -68,7 +68,7 @@ MODULE_PARM_DESC(default_radio_region, "Region: 0=Europe/US, 1=Japan");
 /* RDS buffer blocks */
 static u32 default_rds_buf = 300;
 module_param(default_rds_buf, uint, 0444);
-MODULE_PARM_DESC(rds_buf, "RDS buffer entries");
+MODULE_PARM_DESC(default_rds_buf, "RDS buffer entries");
 
 /* Radio Nr */
 static u32 radio_nr = -1;
diff --git a/drivers/media/rc/ati_remote.c b/drivers/media/rc/ati_remote.c
index a35631891cc0..3f61d77d4147 100644
--- a/drivers/media/rc/ati_remote.c
+++ b/drivers/media/rc/ati_remote.c
@@ -443,6 +443,21 @@ static int ati_remote_sendpacket(struct ati_remote *ati_remote, u16 cmd,
 	return retval;
 }
 
+struct accel_times {
+	const char	value;
+	unsigned int	msecs;
+};
+
+static const struct accel_times accel[] = {
+	{  1,  125 },
+	{  2,  250 },
+	{  4,  500 },
+	{  6, 1000 },
+	{  9, 1500 },
+	{ 13, 2000 },
+	{ 20,    0 },
+};
+
 /*
  * ati_remote_compute_accel
  *
@@ -454,30 +469,22 @@ static int ati_remote_sendpacket(struct ati_remote *ati_remote, u16 cmd,
  */
 static int ati_remote_compute_accel(struct ati_remote *ati_remote)
 {
-	static const char accel[] = { 1, 2, 4, 6, 9, 13, 20 };
-	unsigned long now = jiffies;
-	int acc;
+	unsigned long now = jiffies, reset_time;
+	int i;
+
+	reset_time = msecs_to_jiffies(250);
 
-	if (time_after(now, ati_remote->old_jiffies + msecs_to_jiffies(250))) {
-		acc = 1;
+	if (time_after(now, ati_remote->old_jiffies + reset_time)) {
 		ati_remote->acc_jiffies = now;
+		return 1;
 	}
-	else if (time_before(now, ati_remote->acc_jiffies + msecs_to_jiffies(125)))
-		acc = accel[0];
-	else if (time_before(now, ati_remote->acc_jiffies + msecs_to_jiffies(250)))
-		acc = accel[1];
-	else if (time_before(now, ati_remote->acc_jiffies + msecs_to_jiffies(500)))
-		acc = accel[2];
-	else if (time_before(now, ati_remote->acc_jiffies + msecs_to_jiffies(1000)))
-		acc = accel[3];
-	else if (time_before(now, ati_remote->acc_jiffies + msecs_to_jiffies(1500)))
-		acc = accel[4];
-	else if (time_before(now, ati_remote->acc_jiffies + msecs_to_jiffies(2000)))
-		acc = accel[5];
-	else
-		acc = accel[6];
+	for (i = 0; i < ARRAY_SIZE(accel) - 1; i++) {
+		unsigned long timeout = msecs_to_jiffies(accel[i].msecs);
 
-	return acc;
+		if (time_before(now, ati_remote->acc_jiffies + timeout))
+			return accel[i].value;
+	}
+	return accel[i].value;
 }
 
 /*
diff --git a/drivers/media/rc/igorplugusb.c b/drivers/media/rc/igorplugusb.c
index b36e51576f8e..e0c531fa01da 100644
--- a/drivers/media/rc/igorplugusb.c
+++ b/drivers/media/rc/igorplugusb.c
@@ -152,7 +152,7 @@ static int igorplugusb_probe(struct usb_interface *intf,
 	struct usb_endpoint_descriptor *ep;
 	struct igorplugusb *ir;
 	struct rc_dev *rc;
-	int ret;
+	int ret = -ENOMEM;
 
 	udev = interface_to_usbdev(intf);
 	idesc = intf->cur_altsetting;
@@ -182,7 +182,7 @@ static int igorplugusb_probe(struct usb_interface *intf,
 
 	ir->urb = usb_alloc_urb(0, GFP_KERNEL);
 	if (!ir->urb)
-		return -ENOMEM;
+		goto fail;
 
 	usb_fill_control_urb(ir->urb, udev,
 		usb_rcvctrlpipe(udev, 0), (uint8_t *)&ir->request,
@@ -191,6 +191,9 @@ static int igorplugusb_probe(struct usb_interface *intf,
 	usb_make_path(udev, ir->phys, sizeof(ir->phys));
 
 	rc = rc_allocate_device();
+	if (!rc)
+		goto fail;
+
 	rc->input_name = DRIVER_DESC;
 	rc->input_phys = ir->phys;
 	usb_to_input_id(udev, &rc->input_id);
@@ -214,9 +217,7 @@ static int igorplugusb_probe(struct usb_interface *intf,
 	ret = rc_register_device(rc);
 	if (ret) {
 		dev_err(&intf->dev, "failed to register rc device: %d", ret);
-		rc_free_device(rc);
-		usb_free_urb(ir->urb);
-		return ret;
+		goto fail;
 	}
 
 	usb_set_intfdata(intf, ir);
@@ -224,6 +225,12 @@ static int igorplugusb_probe(struct usb_interface *intf,
 	igorplugusb_cmd(ir, SET_INFRABUFFER_EMPTY);
 
 	return 0;
+fail:
+	rc_free_device(ir->rc);
+	usb_free_urb(ir->urb);
+	del_timer(&ir->timer);
+
+	return ret;
 }
 
 static void igorplugusb_disconnect(struct usb_interface *intf)
diff --git a/drivers/media/rc/keymaps/rc-avermedia-rm-ks.c b/drivers/media/rc/keymaps/rc-avermedia-rm-ks.c
index 8344bcc595be..2583400ca1b4 100644
--- a/drivers/media/rc/keymaps/rc-avermedia-rm-ks.c
+++ b/drivers/media/rc/keymaps/rc-avermedia-rm-ks.c
@@ -23,35 +23,35 @@
 
 /* Initial keytable is from Jose Alberto Reguero <jareguero@telefonica.net>
    and Felipe Morales Moreno <felipe.morales.moreno@gmail.com> */
-/* FIXME: mappings are not 100% correct? */
+/* Keytable fixed by Philippe Valembois <lephilousophe@users.sourceforge.net> */
 static struct rc_map_table avermedia_rm_ks[] = {
-	{ 0x0501, KEY_POWER2 },
-	{ 0x0502, KEY_CHANNELUP },
-	{ 0x0503, KEY_CHANNELDOWN },
-	{ 0x0504, KEY_VOLUMEUP },
-	{ 0x0505, KEY_VOLUMEDOWN },
-	{ 0x0506, KEY_MUTE },
-	{ 0x0507, KEY_RIGHT },
-	{ 0x0508, KEY_RED },
-	{ 0x0509, KEY_1 },
-	{ 0x050a, KEY_2 },
-	{ 0x050b, KEY_3 },
-	{ 0x050c, KEY_4 },
-	{ 0x050d, KEY_5 },
-	{ 0x050e, KEY_6 },
-	{ 0x050f, KEY_7 },
-	{ 0x0510, KEY_8 },
-	{ 0x0511, KEY_9 },
-	{ 0x0512, KEY_0 },
-	{ 0x0513, KEY_AUDIO },
-	{ 0x0515, KEY_EPG },
-	{ 0x0516, KEY_PLAY },
-	{ 0x0517, KEY_RECORD },
-	{ 0x0518, KEY_STOP },
-	{ 0x051c, KEY_BACK },
-	{ 0x051d, KEY_FORWARD },
-	{ 0x054d, KEY_LEFT },
-	{ 0x0556, KEY_ZOOM },
+	{ 0x0501, KEY_POWER2 }, /* Power (RED POWER BUTTON) */
+	{ 0x0502, KEY_CHANNELUP }, /* Channel+ */
+	{ 0x0503, KEY_CHANNELDOWN }, /* Channel- */
+	{ 0x0504, KEY_VOLUMEUP }, /* Volume+ */
+	{ 0x0505, KEY_VOLUMEDOWN }, /* Volume- */
+	{ 0x0506, KEY_MUTE }, /* Mute */
+	{ 0x0507, KEY_AGAIN }, /* Recall */
+	{ 0x0508, KEY_VIDEO }, /* Source */
+	{ 0x0509, KEY_1 }, /* 1 */
+	{ 0x050a, KEY_2 }, /* 2 */
+	{ 0x050b, KEY_3 }, /* 3 */
+	{ 0x050c, KEY_4 }, /* 4 */
+	{ 0x050d, KEY_5 }, /* 5 */
+	{ 0x050e, KEY_6 }, /* 6 */
+	{ 0x050f, KEY_7 }, /* 7 */
+	{ 0x0510, KEY_8 }, /* 8 */
+	{ 0x0511, KEY_9 }, /* 9 */
+	{ 0x0512, KEY_0 }, /* 0 */
+	{ 0x0513, KEY_AUDIO }, /* Audio */
+	{ 0x0515, KEY_EPG }, /* EPG */
+	{ 0x0516, KEY_PLAYPAUSE }, /* Play/Pause */
+	{ 0x0517, KEY_RECORD }, /* Record */
+	{ 0x0518, KEY_STOP }, /* Stop */
+	{ 0x051c, KEY_BACK }, /* << */
+	{ 0x051d, KEY_FORWARD }, /* >> */
+	{ 0x054d, KEY_INFO }, /* Display information */
+	{ 0x0556, KEY_ZOOM }, /* Fullscreen */
 };
 
 static struct rc_map_list avermedia_rm_ks_map = {
diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c
index 4de0e85af805..92ae1903c010 100644
--- a/drivers/media/rc/lirc_dev.c
+++ b/drivers/media/rc/lirc_dev.c
@@ -506,6 +506,7 @@ int lirc_dev_fop_close(struct inode *inode, struct file *file)
 {
 	struct irctl *ir = irctls[iminor(inode)];
 	struct cdev *cdev;
+	int ret;
 
 	if (!ir) {
 		printk(KERN_ERR "%s: called with invalid irctl\n", __func__);
@@ -516,7 +517,8 @@ int lirc_dev_fop_close(struct inode *inode, struct file *file)
 
 	dev_dbg(ir->d.dev, LOGHEAD "close called\n", ir->d.name, ir->d.minor);
 
-	WARN_ON(mutex_lock_killable(&lirc_dev_lock));
+	ret = mutex_lock_killable(&lirc_dev_lock);
+	WARN_ON(ret);
 
 	rc_close(ir->d.rdev);
 
@@ -532,7 +534,8 @@ int lirc_dev_fop_close(struct inode *inode, struct file *file)
 		kfree(ir);
 	}
 
-	mutex_unlock(&lirc_dev_lock);
+	if (!ret)
+		mutex_unlock(&lirc_dev_lock);
 
 	return 0;
 }
diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c
index 2cdb740cde48..35155ae500c7 100644
--- a/drivers/media/rc/mceusb.c
+++ b/drivers/media/rc/mceusb.c
@@ -587,9 +587,8 @@ static void mceusb_dev_printdata(struct mceusb_dev *ir, char *buf,
 			if (len == 2)
 				dev_dbg(dev, "Get hw/sw rev?");
 			else
-				dev_dbg(dev, "hw/sw rev 0x%02x 0x%02x 0x%02x 0x%02x",
-					 data1, data2,
-					 buf[start + 4], buf[start + 5]);
+				dev_dbg(dev, "hw/sw rev %*ph",
+					4, &buf[start + 2]);
 			break;
 		case MCE_CMD_RESUME:
 			dev_dbg(dev, "Device resume requested");
diff --git a/drivers/media/rc/nuvoton-cir.c b/drivers/media/rc/nuvoton-cir.c
index 18adf580f502..99b303b702ac 100644
--- a/drivers/media/rc/nuvoton-cir.c
+++ b/drivers/media/rc/nuvoton-cir.c
@@ -39,6 +39,8 @@
 
 #include "nuvoton-cir.h"
 
+static void nvt_clear_cir_wake_fifo(struct nvt_dev *nvt);
+
 static const struct nvt_chip nvt_chips[] = {
 	{ "w83667hg", NVT_W83667HG },
 	{ "NCT6775F", NVT_6775F },
@@ -80,17 +82,24 @@ static inline void nvt_clear_reg_bit(struct nvt_dev *nvt, u8 val, u8 reg)
 }
 
 /* enter extended function mode */
-static inline void nvt_efm_enable(struct nvt_dev *nvt)
+static inline int nvt_efm_enable(struct nvt_dev *nvt)
 {
+	if (!request_muxed_region(nvt->cr_efir, 2, NVT_DRIVER_NAME))
+		return -EBUSY;
+
 	/* Enabling Extended Function Mode explicitly requires writing 2x */
 	outb(EFER_EFM_ENABLE, nvt->cr_efir);
 	outb(EFER_EFM_ENABLE, nvt->cr_efir);
+
+	return 0;
 }
 
 /* exit extended function mode */
 static inline void nvt_efm_disable(struct nvt_dev *nvt)
 {
 	outb(EFER_EFM_DISABLE, nvt->cr_efir);
+
+	release_region(nvt->cr_efir, 2);
 }
 
 /*
@@ -100,8 +109,25 @@ static inline void nvt_efm_disable(struct nvt_dev *nvt)
  */
 static inline void nvt_select_logical_dev(struct nvt_dev *nvt, u8 ldev)
 {
-	outb(CR_LOGICAL_DEV_SEL, nvt->cr_efir);
-	outb(ldev, nvt->cr_efdr);
+	nvt_cr_write(nvt, ldev, CR_LOGICAL_DEV_SEL);
+}
+
+/* select and enable logical device with setting EFM mode*/
+static inline void nvt_enable_logical_dev(struct nvt_dev *nvt, u8 ldev)
+{
+	nvt_efm_enable(nvt);
+	nvt_select_logical_dev(nvt, ldev);
+	nvt_cr_write(nvt, LOGICAL_DEV_ENABLE, CR_LOGICAL_DEV_EN);
+	nvt_efm_disable(nvt);
+}
+
+/* select and disable logical device with setting EFM mode*/
+static inline void nvt_disable_logical_dev(struct nvt_dev *nvt, u8 ldev)
+{
+	nvt_efm_enable(nvt);
+	nvt_select_logical_dev(nvt, ldev);
+	nvt_cr_write(nvt, LOGICAL_DEV_DISABLE, CR_LOGICAL_DEV_EN);
+	nvt_efm_disable(nvt);
 }
 
 /* write val to cir config register */
@@ -137,6 +163,120 @@ static u8 nvt_cir_wake_reg_read(struct nvt_dev *nvt, u8 offset)
 	return val;
 }
 
+/* don't override io address if one is set already */
+static void nvt_set_ioaddr(struct nvt_dev *nvt, unsigned long *ioaddr)
+{
+	unsigned long old_addr;
+
+	old_addr = nvt_cr_read(nvt, CR_CIR_BASE_ADDR_HI) << 8;
+	old_addr |= nvt_cr_read(nvt, CR_CIR_BASE_ADDR_LO);
+
+	if (old_addr)
+		*ioaddr = old_addr;
+	else {
+		nvt_cr_write(nvt, *ioaddr >> 8, CR_CIR_BASE_ADDR_HI);
+		nvt_cr_write(nvt, *ioaddr & 0xff, CR_CIR_BASE_ADDR_LO);
+	}
+}
+
+static ssize_t wakeup_data_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	struct rc_dev *rc_dev = to_rc_dev(dev);
+	struct nvt_dev *nvt = rc_dev->priv;
+	int fifo_len, duration;
+	unsigned long flags;
+	ssize_t buf_len = 0;
+	int i;
+
+	spin_lock_irqsave(&nvt->nvt_lock, flags);
+
+	fifo_len = nvt_cir_wake_reg_read(nvt, CIR_WAKE_FIFO_COUNT);
+	fifo_len = min(fifo_len, WAKEUP_MAX_SIZE);
+
+	/* go to first element to be read */
+	while (nvt_cir_wake_reg_read(nvt, CIR_WAKE_RD_FIFO_ONLY_IDX))
+		nvt_cir_wake_reg_read(nvt, CIR_WAKE_RD_FIFO_ONLY);
+
+	for (i = 0; i < fifo_len; i++) {
+		duration = nvt_cir_wake_reg_read(nvt, CIR_WAKE_RD_FIFO_ONLY);
+		duration = (duration & BUF_LEN_MASK) * SAMPLE_PERIOD;
+		buf_len += snprintf(buf + buf_len, PAGE_SIZE - buf_len,
+				    "%d ", duration);
+	}
+	buf_len += snprintf(buf + buf_len, PAGE_SIZE - buf_len, "\n");
+
+	spin_unlock_irqrestore(&nvt->nvt_lock, flags);
+
+	return buf_len;
+}
+
+static ssize_t wakeup_data_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t len)
+{
+	struct rc_dev *rc_dev = to_rc_dev(dev);
+	struct nvt_dev *nvt = rc_dev->priv;
+	unsigned long flags;
+	u8 tolerance, config, wake_buf[WAKEUP_MAX_SIZE];
+	char **argv;
+	int i, count;
+	unsigned int val;
+	ssize_t ret;
+
+	argv = argv_split(GFP_KERNEL, buf, &count);
+	if (!argv)
+		return -ENOMEM;
+	if (!count || count > WAKEUP_MAX_SIZE) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	for (i = 0; i < count; i++) {
+		ret = kstrtouint(argv[i], 10, &val);
+		if (ret)
+			goto out;
+		val = DIV_ROUND_CLOSEST(val, SAMPLE_PERIOD);
+		if (!val || val > 0x7f) {
+			ret = -EINVAL;
+			goto out;
+		}
+		wake_buf[i] = val;
+		/* sequence must start with a pulse */
+		if (i % 2 == 0)
+			wake_buf[i] |= BUF_PULSE_BIT;
+	}
+
+	/* hardcode the tolerance to 10% */
+	tolerance = DIV_ROUND_UP(count, 10);
+
+	spin_lock_irqsave(&nvt->nvt_lock, flags);
+
+	nvt_clear_cir_wake_fifo(nvt);
+	nvt_cir_wake_reg_write(nvt, count, CIR_WAKE_FIFO_CMP_DEEP);
+	nvt_cir_wake_reg_write(nvt, tolerance, CIR_WAKE_FIFO_CMP_TOL);
+
+	config = nvt_cir_wake_reg_read(nvt, CIR_WAKE_IRCON);
+
+	/* enable writes to wake fifo */
+	nvt_cir_wake_reg_write(nvt, config | CIR_WAKE_IRCON_MODE1,
+			       CIR_WAKE_IRCON);
+
+	for (i = 0; i < count; i++)
+		nvt_cir_wake_reg_write(nvt, wake_buf[i], CIR_WAKE_WR_FIFO_DATA);
+
+	nvt_cir_wake_reg_write(nvt, config, CIR_WAKE_IRCON);
+
+	spin_unlock_irqrestore(&nvt->nvt_lock, flags);
+
+	ret = len;
+out:
+	argv_free(argv);
+	return ret;
+}
+static DEVICE_ATTR_RW(wakeup_data);
+
 /* dump current cir register contents */
 static void cir_dump_regs(struct nvt_dev *nvt)
 {
@@ -251,7 +391,7 @@ static inline const char *nvt_find_chip(struct nvt_dev *nvt, int id)
 
 
 /* detect hardware features */
-static void nvt_hw_detect(struct nvt_dev *nvt)
+static int nvt_hw_detect(struct nvt_dev *nvt)
 {
 	const char *chip_name;
 	int chip_id;
@@ -266,10 +406,17 @@ static void nvt_hw_detect(struct nvt_dev *nvt)
 		nvt_efm_enable(nvt);
 		nvt->chip_major = nvt_cr_read(nvt, CR_CHIP_ID_HI);
 	}
-
 	nvt->chip_minor = nvt_cr_read(nvt, CR_CHIP_ID_LO);
 
+	nvt_efm_disable(nvt);
+
 	chip_id = nvt->chip_major << 8 | nvt->chip_minor;
+	if (chip_id == NVT_INVALID) {
+		dev_err(&nvt->pdev->dev,
+			"No device found on either EFM port\n");
+		return -ENODEV;
+	}
+
 	chip_name = nvt_find_chip(nvt, chip_id);
 
 	/* warn, but still let the driver load, if we don't know this chip */
@@ -282,7 +429,7 @@ static void nvt_hw_detect(struct nvt_dev *nvt)
 			 "found %s or compatible: chip id: 0x%02x 0x%02x",
 			 chip_name, nvt->chip_major, nvt->chip_minor);
 
-	nvt_efm_disable(nvt);
+	return 0;
 }
 
 static void nvt_cir_ldev_init(struct nvt_dev *nvt)
@@ -305,12 +452,10 @@ static void nvt_cir_ldev_init(struct nvt_dev *nvt)
 	val |= psval;
 	nvt_cr_write(nvt, val, psreg);
 
-	/* Select CIR logical device and enable */
+	/* Select CIR logical device */
 	nvt_select_logical_dev(nvt, LOGICAL_DEV_CIR);
-	nvt_cr_write(nvt, LOGICAL_DEV_ENABLE, CR_LOGICAL_DEV_EN);
 
-	nvt_cr_write(nvt, nvt->cir_addr >> 8, CR_CIR_BASE_ADDR_HI);
-	nvt_cr_write(nvt, nvt->cir_addr & 0xff, CR_CIR_BASE_ADDR_LO);
+	nvt_set_ioaddr(nvt, &nvt->cir_addr);
 
 	nvt_cr_write(nvt, nvt->cir_irq, CR_CIR_IRQ_RSRC);
 
@@ -320,7 +465,7 @@ static void nvt_cir_ldev_init(struct nvt_dev *nvt)
 
 static void nvt_cir_wake_ldev_init(struct nvt_dev *nvt)
 {
-	/* Select ACPI logical device, enable it and CIR Wake */
+	/* Select ACPI logical device and anable it */
 	nvt_select_logical_dev(nvt, LOGICAL_DEV_ACPI);
 	nvt_cr_write(nvt, LOGICAL_DEV_ENABLE, CR_LOGICAL_DEV_EN);
 
@@ -330,12 +475,10 @@ static void nvt_cir_wake_ldev_init(struct nvt_dev *nvt)
 	/* enable pme interrupt of cir wakeup event */
 	nvt_set_reg_bit(nvt, PME_INTR_CIR_PASS_BIT, CR_ACPI_IRQ_EVENTS2);
 
-	/* Select CIR Wake logical device and enable */
+	/* Select CIR Wake logical device */
 	nvt_select_logical_dev(nvt, LOGICAL_DEV_CIR_WAKE);
-	nvt_cr_write(nvt, LOGICAL_DEV_ENABLE, CR_LOGICAL_DEV_EN);
 
-	nvt_cr_write(nvt, nvt->cir_wake_addr >> 8, CR_CIR_BASE_ADDR_HI);
-	nvt_cr_write(nvt, nvt->cir_wake_addr & 0xff, CR_CIR_BASE_ADDR_LO);
+	nvt_set_ioaddr(nvt, &nvt->cir_wake_addr);
 
 	nvt_cr_write(nvt, nvt->cir_wake_irq, CR_CIR_IRQ_RSRC);
 
@@ -355,11 +498,19 @@ static void nvt_clear_cir_fifo(struct nvt_dev *nvt)
 /* clear out the hardware's cir wake rx fifo */
 static void nvt_clear_cir_wake_fifo(struct nvt_dev *nvt)
 {
-	u8 val;
+	u8 val, config;
+
+	config = nvt_cir_wake_reg_read(nvt, CIR_WAKE_IRCON);
+
+	/* clearing wake fifo works in learning mode only */
+	nvt_cir_wake_reg_write(nvt, config & ~CIR_WAKE_IRCON_MODE0,
+			       CIR_WAKE_IRCON);
 
 	val = nvt_cir_wake_reg_read(nvt, CIR_WAKE_FIFOCON);
 	nvt_cir_wake_reg_write(nvt, val | CIR_WAKE_FIFOCON_RXFIFOCLR,
 			       CIR_WAKE_FIFOCON);
+
+	nvt_cir_wake_reg_write(nvt, config, CIR_WAKE_IRCON);
 }
 
 /* clear out the hardware's cir tx fifo */
@@ -408,6 +559,9 @@ static void nvt_cir_regs_init(struct nvt_dev *nvt)
 
 	/* and finally, enable interrupts */
 	nvt_set_cir_iren(nvt);
+
+	/* enable the CIR logical device */
+	nvt_enable_logical_dev(nvt, LOGICAL_DEV_CIR);
 }
 
 static void nvt_cir_wake_regs_init(struct nvt_dev *nvt)
@@ -442,10 +596,15 @@ static void nvt_cir_wake_regs_init(struct nvt_dev *nvt)
 
 	/* clear any and all stray interrupts */
 	nvt_cir_wake_reg_write(nvt, 0xff, CIR_WAKE_IRSTS);
+
+	/* enable the CIR WAKE logical device */
+	nvt_enable_logical_dev(nvt, LOGICAL_DEV_CIR_WAKE);
 }
 
 static void nvt_enable_wake(struct nvt_dev *nvt)
 {
+	unsigned long flags;
+
 	nvt_efm_enable(nvt);
 
 	nvt_select_logical_dev(nvt, LOGICAL_DEV_ACPI);
@@ -457,12 +616,16 @@ static void nvt_enable_wake(struct nvt_dev *nvt)
 
 	nvt_efm_disable(nvt);
 
+	spin_lock_irqsave(&nvt->nvt_lock, flags);
+
 	nvt_cir_wake_reg_write(nvt, CIR_WAKE_IRCON_MODE0 | CIR_WAKE_IRCON_RXEN |
 			       CIR_WAKE_IRCON_R | CIR_WAKE_IRCON_RXINV |
 			       CIR_WAKE_IRCON_SAMPLE_PERIOD_SEL,
 			       CIR_WAKE_IRCON);
 	nvt_cir_wake_reg_write(nvt, 0xff, CIR_WAKE_IRSTS);
 	nvt_cir_wake_reg_write(nvt, 0, CIR_WAKE_IREN);
+
+	spin_unlock_irqrestore(&nvt->nvt_lock, flags);
 }
 
 #if 0 /* Currently unused */
@@ -670,7 +833,6 @@ static void nvt_handle_rx_fifo_overrun(struct nvt_dev *nvt)
 /* copy data from hardware rx fifo into driver buffer */
 static void nvt_get_rx_ir_data(struct nvt_dev *nvt)
 {
-	unsigned long flags;
 	u8 fifocount, val;
 	unsigned int b_idx;
 	bool overrun = false;
@@ -689,8 +851,6 @@ static void nvt_get_rx_ir_data(struct nvt_dev *nvt)
 
 	nvt_dbg("attempting to fetch %u bytes from hw rx fifo", fifocount);
 
-	spin_lock_irqsave(&nvt->nvt_lock, flags);
-
 	b_idx = nvt->pkts;
 
 	/* This should never happen, but lets check anyway... */
@@ -712,8 +872,6 @@ static void nvt_get_rx_ir_data(struct nvt_dev *nvt)
 
 	if (overrun)
 		nvt_handle_rx_fifo_overrun(nvt);
-
-	spin_unlock_irqrestore(&nvt->nvt_lock, flags);
 }
 
 static void nvt_cir_log_irqs(u8 status, u8 iren)
@@ -736,16 +894,13 @@ static void nvt_cir_log_irqs(u8 status, u8 iren)
 static bool nvt_cir_tx_inactive(struct nvt_dev *nvt)
 {
 	unsigned long flags;
-	bool tx_inactive;
 	u8 tx_state;
 
 	spin_lock_irqsave(&nvt->tx.lock, flags);
 	tx_state = nvt->tx.tx_state;
 	spin_unlock_irqrestore(&nvt->tx.lock, flags);
 
-	tx_inactive = (tx_state == ST_TX_NONE);
-
-	return tx_inactive;
+	return tx_state == ST_TX_NONE;
 }
 
 /* interrupt service routine for incoming and outgoing CIR data */
@@ -757,9 +912,7 @@ static irqreturn_t nvt_cir_isr(int irq, void *data)
 
 	nvt_dbg_verbose("%s firing", __func__);
 
-	nvt_efm_enable(nvt);
-	nvt_select_logical_dev(nvt, LOGICAL_DEV_CIR);
-	nvt_efm_disable(nvt);
+	spin_lock_irqsave(&nvt->nvt_lock, flags);
 
 	/*
 	 * Get IR Status register contents. Write 1 to ack/clear
@@ -775,9 +928,14 @@ static irqreturn_t nvt_cir_isr(int irq, void *data)
 	 *   0: CIR_IRSTS_GH  - Min Length Detected
 	 */
 	status = nvt_cir_reg_read(nvt, CIR_IRSTS);
-	if (!status) {
+	iren = nvt_cir_reg_read(nvt, CIR_IREN);
+
+	/* IRQ may be shared with CIR WAKE, therefore check for each
+	 * status bit whether the related interrupt source is enabled
+	 */
+	if (!(status & iren)) {
+		spin_unlock_irqrestore(&nvt->nvt_lock, flags);
 		nvt_dbg_verbose("%s exiting, IRSTS 0x0", __func__);
-		nvt_cir_reg_write(nvt, 0xff, CIR_IRSTS);
 		return IRQ_NONE;
 	}
 
@@ -785,13 +943,6 @@ static irqreturn_t nvt_cir_isr(int irq, void *data)
 	nvt_cir_reg_write(nvt, status, CIR_IRSTS);
 	nvt_cir_reg_write(nvt, 0, CIR_IRSTS);
 
-	/* Interrupt may be shared with CIR Wake, bail if CIR not enabled */
-	iren = nvt_cir_reg_read(nvt, CIR_IREN);
-	if (!iren) {
-		nvt_dbg_verbose("%s exiting, CIR not enabled", __func__);
-		return IRQ_NONE;
-	}
-
 	nvt_cir_log_irqs(status, iren);
 
 	if (status & CIR_IRSTS_RTR) {
@@ -805,16 +956,14 @@ static irqreturn_t nvt_cir_isr(int irq, void *data)
 		if (nvt_cir_tx_inactive(nvt))
 			nvt_get_rx_ir_data(nvt);
 
-		spin_lock_irqsave(&nvt->nvt_lock, flags);
-
 		cur_state = nvt->study_state;
 
-		spin_unlock_irqrestore(&nvt->nvt_lock, flags);
-
 		if (cur_state == ST_STUDY_NONE)
 			nvt_clear_cir_fifo(nvt);
 	}
 
+	spin_unlock_irqrestore(&nvt->nvt_lock, flags);
+
 	if (status & CIR_IRSTS_TE)
 		nvt_clear_tx_fifo(nvt);
 
@@ -863,9 +1012,18 @@ static irqreturn_t nvt_cir_wake_isr(int irq, void *data)
 
 	nvt_dbg_wake("%s firing", __func__);
 
+	spin_lock_irqsave(&nvt->nvt_lock, flags);
+
 	status = nvt_cir_wake_reg_read(nvt, CIR_WAKE_IRSTS);
-	if (!status)
+	iren = nvt_cir_wake_reg_read(nvt, CIR_WAKE_IREN);
+
+	/* IRQ may be shared with CIR, therefore check for each
+	 * status bit whether the related interrupt source is enabled
+	 */
+	if (!(status & iren)) {
+		spin_unlock_irqrestore(&nvt->nvt_lock, flags);
 		return IRQ_NONE;
+	}
 
 	if (status & CIR_WAKE_IRSTS_IR_PENDING)
 		nvt_clear_cir_wake_fifo(nvt);
@@ -873,13 +1031,6 @@ static irqreturn_t nvt_cir_wake_isr(int irq, void *data)
 	nvt_cir_wake_reg_write(nvt, status, CIR_WAKE_IRSTS);
 	nvt_cir_wake_reg_write(nvt, 0, CIR_WAKE_IRSTS);
 
-	/* Interrupt may be shared with CIR, bail if Wake not enabled */
-	iren = nvt_cir_wake_reg_read(nvt, CIR_WAKE_IREN);
-	if (!iren) {
-		nvt_dbg_wake("%s exiting, wake not enabled", __func__);
-		return IRQ_HANDLED;
-	}
-
 	if ((status & CIR_WAKE_IRSTS_PE) &&
 	    (nvt->wake_state == ST_WAKE_START)) {
 		while (nvt_cir_wake_reg_read(nvt, CIR_WAKE_RD_FIFO_ONLY_IDX)) {
@@ -888,39 +1039,21 @@ static irqreturn_t nvt_cir_wake_isr(int irq, void *data)
 		}
 
 		nvt_cir_wake_reg_write(nvt, 0, CIR_WAKE_IREN);
-		spin_lock_irqsave(&nvt->nvt_lock, flags);
 		nvt->wake_state = ST_WAKE_FINISH;
-		spin_unlock_irqrestore(&nvt->nvt_lock, flags);
 	}
 
+	spin_unlock_irqrestore(&nvt->nvt_lock, flags);
+
 	nvt_dbg_wake("%s done", __func__);
 	return IRQ_HANDLED;
 }
 
-static void nvt_enable_cir(struct nvt_dev *nvt)
+static void nvt_disable_cir(struct nvt_dev *nvt)
 {
-	/* set function enable flags */
-	nvt_cir_reg_write(nvt, CIR_IRCON_TXEN | CIR_IRCON_RXEN |
-			  CIR_IRCON_RXINV | CIR_IRCON_SAMPLE_PERIOD_SEL,
-			  CIR_IRCON);
-
-	nvt_efm_enable(nvt);
-
-	/* enable the CIR logical device */
-	nvt_select_logical_dev(nvt, LOGICAL_DEV_CIR);
-	nvt_cr_write(nvt, LOGICAL_DEV_ENABLE, CR_LOGICAL_DEV_EN);
-
-	nvt_efm_disable(nvt);
-
-	/* clear all pending interrupts */
-	nvt_cir_reg_write(nvt, 0xff, CIR_IRSTS);
+	unsigned long flags;
 
-	/* enable interrupts */
-	nvt_set_cir_iren(nvt);
-}
+	spin_lock_irqsave(&nvt->nvt_lock, flags);
 
-static void nvt_disable_cir(struct nvt_dev *nvt)
-{
 	/* disable CIR interrupts */
 	nvt_cir_reg_write(nvt, 0, CIR_IREN);
 
@@ -934,13 +1067,10 @@ static void nvt_disable_cir(struct nvt_dev *nvt)
 	nvt_clear_cir_fifo(nvt);
 	nvt_clear_tx_fifo(nvt);
 
-	nvt_efm_enable(nvt);
+	spin_unlock_irqrestore(&nvt->nvt_lock, flags);
 
 	/* disable the CIR logical device */
-	nvt_select_logical_dev(nvt, LOGICAL_DEV_CIR);
-	nvt_cr_write(nvt, LOGICAL_DEV_DISABLE, CR_LOGICAL_DEV_EN);
-
-	nvt_efm_disable(nvt);
+	nvt_disable_logical_dev(nvt, LOGICAL_DEV_CIR);
 }
 
 static int nvt_open(struct rc_dev *dev)
@@ -949,20 +1079,31 @@ static int nvt_open(struct rc_dev *dev)
 	unsigned long flags;
 
 	spin_lock_irqsave(&nvt->nvt_lock, flags);
-	nvt_enable_cir(nvt);
+
+	/* set function enable flags */
+	nvt_cir_reg_write(nvt, CIR_IRCON_TXEN | CIR_IRCON_RXEN |
+			  CIR_IRCON_RXINV | CIR_IRCON_SAMPLE_PERIOD_SEL,
+			  CIR_IRCON);
+
+	/* clear all pending interrupts */
+	nvt_cir_reg_write(nvt, 0xff, CIR_IRSTS);
+
+	/* enable interrupts */
+	nvt_set_cir_iren(nvt);
+
 	spin_unlock_irqrestore(&nvt->nvt_lock, flags);
 
+	/* enable the CIR logical device */
+	nvt_enable_logical_dev(nvt, LOGICAL_DEV_CIR);
+
 	return 0;
 }
 
 static void nvt_close(struct rc_dev *dev)
 {
 	struct nvt_dev *nvt = dev->priv;
-	unsigned long flags;
 
-	spin_lock_irqsave(&nvt->nvt_lock, flags);
 	nvt_disable_cir(nvt);
-	spin_unlock_irqrestore(&nvt->nvt_lock, flags);
 }
 
 /* Allocate memory, probe hardware, and initialize everything */
@@ -1024,7 +1165,9 @@ static int nvt_probe(struct pnp_dev *pdev, const struct pnp_device_id *dev_id)
 
 	init_waitqueue_head(&nvt->tx.queue);
 
-	nvt_hw_detect(nvt);
+	ret = nvt_hw_detect(nvt);
+	if (ret)
+		goto exit_free_dev_rdev;
 
 	/* Initialize CIR & CIR Wake Logical Devices */
 	nvt_efm_enable(nvt);
@@ -1032,7 +1175,10 @@ static int nvt_probe(struct pnp_dev *pdev, const struct pnp_device_id *dev_id)
 	nvt_cir_wake_ldev_init(nvt);
 	nvt_efm_disable(nvt);
 
-	/* Initialize CIR & CIR Wake Config Registers */
+	/*
+	 * Initialize CIR & CIR Wake Config Registers
+	 * and enable logical devices
+	 */
 	nvt_cir_regs_init(nvt);
 	nvt_cir_wake_regs_init(nvt);
 
@@ -1079,12 +1225,16 @@ static int nvt_probe(struct pnp_dev *pdev, const struct pnp_device_id *dev_id)
 		goto exit_unregister_device;
 
 	if (!devm_request_region(&pdev->dev, nvt->cir_wake_addr,
-			    CIR_IOREG_LENGTH, NVT_DRIVER_NAME))
+			    CIR_IOREG_LENGTH, NVT_DRIVER_NAME "-wake"))
 		goto exit_unregister_device;
 
 	if (devm_request_irq(&pdev->dev, nvt->cir_wake_irq,
 			     nvt_cir_wake_isr, IRQF_SHARED,
-			     NVT_DRIVER_NAME, (void *)nvt))
+			     NVT_DRIVER_NAME "-wake", (void *)nvt))
+		goto exit_unregister_device;
+
+	ret = device_create_file(&rdev->dev, &dev_attr_wakeup_data);
+	if (ret)
 		goto exit_unregister_device;
 
 	device_init_wakeup(&pdev->dev, true);
@@ -1109,15 +1259,13 @@ exit_free_dev_rdev:
 static void nvt_remove(struct pnp_dev *pdev)
 {
 	struct nvt_dev *nvt = pnp_get_drvdata(pdev);
-	unsigned long flags;
 
-	spin_lock_irqsave(&nvt->nvt_lock, flags);
-	/* disable CIR */
-	nvt_cir_reg_write(nvt, 0, CIR_IREN);
+	device_remove_file(&nvt->rdev->dev, &dev_attr_wakeup_data);
+
 	nvt_disable_cir(nvt);
+
 	/* enable CIR Wake (for IR power-on) */
 	nvt_enable_wake(nvt);
-	spin_unlock_irqrestore(&nvt->nvt_lock, flags);
 
 	rc_unregister_device(nvt->rdev);
 }
@@ -1129,26 +1277,23 @@ static int nvt_suspend(struct pnp_dev *pdev, pm_message_t state)
 
 	nvt_dbg("%s called", __func__);
 
-	/* zero out misc state tracking */
-	spin_lock_irqsave(&nvt->nvt_lock, flags);
-	nvt->study_state = ST_STUDY_NONE;
-	nvt->wake_state = ST_WAKE_NONE;
-	spin_unlock_irqrestore(&nvt->nvt_lock, flags);
-
 	spin_lock_irqsave(&nvt->tx.lock, flags);
 	nvt->tx.tx_state = ST_TX_NONE;
 	spin_unlock_irqrestore(&nvt->tx.lock, flags);
 
+	spin_lock_irqsave(&nvt->nvt_lock, flags);
+
+	/* zero out misc state tracking */
+	nvt->study_state = ST_STUDY_NONE;
+	nvt->wake_state = ST_WAKE_NONE;
+
 	/* disable all CIR interrupts */
 	nvt_cir_reg_write(nvt, 0, CIR_IREN);
 
-	nvt_efm_enable(nvt);
+	spin_unlock_irqrestore(&nvt->nvt_lock, flags);
 
 	/* disable cir logical dev */
-	nvt_select_logical_dev(nvt, LOGICAL_DEV_CIR);
-	nvt_cr_write(nvt, LOGICAL_DEV_DISABLE, CR_LOGICAL_DEV_EN);
-
-	nvt_efm_disable(nvt);
+	nvt_disable_logical_dev(nvt, LOGICAL_DEV_CIR);
 
 	/* make sure wake is enabled */
 	nvt_enable_wake(nvt);
@@ -1162,16 +1307,6 @@ static int nvt_resume(struct pnp_dev *pdev)
 
 	nvt_dbg("%s called", __func__);
 
-	/* open interrupt */
-	nvt_set_cir_iren(nvt);
-
-	/* Enable CIR logical device */
-	nvt_efm_enable(nvt);
-	nvt_select_logical_dev(nvt, LOGICAL_DEV_CIR);
-	nvt_cr_write(nvt, LOGICAL_DEV_ENABLE, CR_LOGICAL_DEV_EN);
-
-	nvt_efm_disable(nvt);
-
 	nvt_cir_regs_init(nvt);
 	nvt_cir_wake_regs_init(nvt);
 
@@ -1181,6 +1316,7 @@ static int nvt_resume(struct pnp_dev *pdev)
 static void nvt_shutdown(struct pnp_dev *pdev)
 {
 	struct nvt_dev *nvt = pnp_get_drvdata(pdev);
+
 	nvt_enable_wake(nvt);
 }
 
diff --git a/drivers/media/rc/nuvoton-cir.h b/drivers/media/rc/nuvoton-cir.h
index 0ad15d34e9c9..c9c98ebb19ee 100644
--- a/drivers/media/rc/nuvoton-cir.h
+++ b/drivers/media/rc/nuvoton-cir.h
@@ -68,7 +68,8 @@ enum nvt_chip_ver {
 	NVT_W83667HG	= 0xa510,
 	NVT_6775F	= 0xb470,
 	NVT_6776F	= 0xc330,
-	NVT_6779D	= 0xc560
+	NVT_6779D	= 0xc560,
+	NVT_INVALID	= 0xffff,
 };
 
 struct nvt_chip {
@@ -157,8 +158,8 @@ struct nvt_dev {
 /* total length of CIR and CIR WAKE */
 #define CIR_IOREG_LENGTH	0x0f
 
-/* RX limit length, 8 high bits for SLCH, 8 low bits for SLCL (0x7d0 = 2000) */
-#define CIR_RX_LIMIT_COUNT	0x7d0
+/* RX limit length, 8 high bits for SLCH, 8 low bits for SLCL */
+#define CIR_RX_LIMIT_COUNT  (IR_DEFAULT_TIMEOUT / US_TO_NS(SAMPLE_PERIOD))
 
 /* CIR Regs */
 #define CIR_IRCON	0x00
@@ -292,10 +293,7 @@ struct nvt_dev {
 #define CIR_WAKE_IREN_RTR		0x40
 #define CIR_WAKE_IREN_PE		0x20
 #define CIR_WAKE_IREN_RFO		0x10
-#define CIR_WAKE_IREN_TE		0x08
-#define CIR_WAKE_IREN_TTR		0x04
-#define CIR_WAKE_IREN_TFU		0x02
-#define CIR_WAKE_IREN_GH		0x01
+#define CIR_WAKE_IREN_GH		0x08
 
 /* CIR WAKE FIFOCON settings */
 #define CIR_WAKE_FIFOCON_RXFIFOCLR	0x08
@@ -419,3 +417,6 @@ struct nvt_dev {
 /* as VISTA MCE definition, valid carrier value */
 #define MAX_CARRIER 60000
 #define MIN_CARRIER 30000
+
+/* max wakeup sequence length */
+#define WAKEUP_MAX_SIZE 65
diff --git a/drivers/media/rc/rc-core-priv.h b/drivers/media/rc/rc-core-priv.h
index 7359f3d03b64..585d5e52118d 100644
--- a/drivers/media/rc/rc-core-priv.h
+++ b/drivers/media/rc/rc-core-priv.h
@@ -16,6 +16,9 @@
 #ifndef _RC_CORE_PRIV
 #define _RC_CORE_PRIV
 
+/* Define the max number of pulse/space transitions to buffer */
+#define	MAX_IR_EVENT_SIZE	512
+
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <media/rc-core.h>
@@ -35,7 +38,8 @@ struct ir_raw_event_ctrl {
 	struct list_head		list;		/* to keep track of raw clients */
 	struct task_struct		*thread;
 	spinlock_t			lock;
-	struct kfifo_rec_ptr_1		kfifo;		/* fifo for the pulse/space durations */
+	/* fifo for the pulse/space durations */
+	DECLARE_KFIFO(kfifo, struct ir_raw_event, MAX_IR_EVENT_SIZE);
 	ktime_t				last_event;	/* when last event occurred */
 	enum raw_event_type		last_type;	/* last event type */
 	struct rc_dev			*dev;		/* pointer to the parent rc_dev */
diff --git a/drivers/media/rc/rc-ir-raw.c b/drivers/media/rc/rc-ir-raw.c
index c69807fe2fef..144304c94606 100644
--- a/drivers/media/rc/rc-ir-raw.c
+++ b/drivers/media/rc/rc-ir-raw.c
@@ -20,9 +20,6 @@
 #include <linux/freezer.h>
 #include "rc-core-priv.h"
 
-/* Define the max number of pulse/space transitions to buffer */
-#define MAX_IR_EVENT_SIZE      512
-
 /* Used to keep track of IR raw clients, protected by ir_raw_handler_lock */
 static LIST_HEAD(ir_raw_client_list);
 
@@ -36,14 +33,12 @@ static int ir_raw_event_thread(void *data)
 	struct ir_raw_event ev;
 	struct ir_raw_handler *handler;
 	struct ir_raw_event_ctrl *raw = (struct ir_raw_event_ctrl *)data;
-	int retval;
 
 	while (!kthread_should_stop()) {
 
 		spin_lock_irq(&raw->lock);
-		retval = kfifo_len(&raw->kfifo);
 
-		if (retval < sizeof(ev)) {
+		if (!kfifo_len(&raw->kfifo)) {
 			set_current_state(TASK_INTERRUPTIBLE);
 
 			if (kthread_should_stop())
@@ -54,7 +49,8 @@ static int ir_raw_event_thread(void *data)
 			continue;
 		}
 
-		retval = kfifo_out(&raw->kfifo, &ev, sizeof(ev));
+		if(!kfifo_out(&raw->kfifo, &ev, 1))
+			dev_err(&raw->dev->dev, "IR event FIFO is empty!\n");
 		spin_unlock_irq(&raw->lock);
 
 		mutex_lock(&ir_raw_handler_lock);
@@ -87,8 +83,10 @@ int ir_raw_event_store(struct rc_dev *dev, struct ir_raw_event *ev)
 	IR_dprintk(2, "sample: (%05dus %s)\n",
 		   TO_US(ev->duration), TO_STR(ev->pulse));
 
-	if (kfifo_in(&dev->raw->kfifo, ev, sizeof(*ev)) != sizeof(*ev))
-		return -ENOMEM;
+	if (!kfifo_put(&dev->raw->kfifo, *ev)) {
+		dev_err(&dev->dev, "IR event FIFO is full!\n");
+		return -ENOSPC;
+	}
 
 	return 0;
 }
@@ -273,11 +271,7 @@ int ir_raw_event_register(struct rc_dev *dev)
 
 	dev->raw->dev = dev;
 	dev->change_protocol = change_protocol;
-	rc = kfifo_alloc(&dev->raw->kfifo,
-			 sizeof(struct ir_raw_event) * MAX_IR_EVENT_SIZE,
-			 GFP_KERNEL);
-	if (rc < 0)
-		goto out;
+	INIT_KFIFO(dev->raw->kfifo);
 
 	spin_lock_init(&dev->raw->lock);
 	dev->raw->thread = kthread_run(ir_raw_event_thread, dev->raw,
@@ -319,7 +313,6 @@ void ir_raw_event_unregister(struct rc_dev *dev)
 			handler->raw_unregister(dev);
 	mutex_unlock(&ir_raw_handler_lock);
 
-	kfifo_free(&dev->raw->kfifo);
 	kfree(dev->raw);
 	dev->raw = NULL;
 }
diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c
index 1042fa331a07..4e9bbe735ae9 100644
--- a/drivers/media/rc/rc-main.c
+++ b/drivers/media/rc/rc-main.c
@@ -13,6 +13,7 @@
  */
 
 #include <media/rc-core.h>
+#include <linux/atomic.h>
 #include <linux/spinlock.h>
 #include <linux/delay.h>
 #include <linux/input.h>
@@ -723,6 +724,7 @@ int rc_open(struct rc_dev *rdev)
 		return -EINVAL;
 
 	mutex_lock(&rdev->lock);
+
 	if (!rdev->users++ && rdev->open != NULL)
 		rval = rdev->open(rdev);
 
@@ -873,6 +875,9 @@ static ssize_t show_protocols(struct device *device,
 	if (!dev)
 		return -EINVAL;
 
+	if (!atomic_read(&dev->initialized))
+		return -ERESTARTSYS;
+
 	mutex_lock(&dev->lock);
 
 	if (fattr->type == RC_FILTER_NORMAL) {
@@ -1054,6 +1059,9 @@ static ssize_t store_protocols(struct device *device,
 	if (!dev)
 		return -EINVAL;
 
+	if (!atomic_read(&dev->initialized))
+		return -ERESTARTSYS;
+
 	if (fattr->type == RC_FILTER_NORMAL) {
 		IR_dprintk(1, "Normal protocol change requested\n");
 		current_protocols = &dev->enabled_protocols;
@@ -1154,12 +1162,16 @@ static ssize_t show_filter(struct device *device,
 	if (!dev)
 		return -EINVAL;
 
+	if (!atomic_read(&dev->initialized))
+		return -ERESTARTSYS;
+
+	mutex_lock(&dev->lock);
+
 	if (fattr->type == RC_FILTER_NORMAL)
 		filter = &dev->scancode_filter;
 	else
 		filter = &dev->scancode_wakeup_filter;
 
-	mutex_lock(&dev->lock);
 	if (fattr->mask)
 		val = filter->mask;
 	else
@@ -1204,6 +1216,9 @@ static ssize_t store_filter(struct device *device,
 	if (!dev)
 		return -EINVAL;
 
+	if (!atomic_read(&dev->initialized))
+		return -ERESTARTSYS;
+
 	ret = kstrtoul(buf, 0, &val);
 	if (ret < 0)
 		return ret;
@@ -1408,6 +1423,7 @@ int rc_register_device(struct rc_dev *dev)
 	dev->minor = minor;
 	dev_set_name(&dev->dev, "rc%u", dev->minor);
 	dev_set_drvdata(&dev->dev, dev);
+	atomic_set(&dev->initialized, 0);
 
 	dev->dev.groups = dev->sysfs_groups;
 	dev->sysfs_groups[attr++] = &rc_dev_protocol_attr_grp;
@@ -1419,14 +1435,6 @@ int rc_register_device(struct rc_dev *dev)
 		dev->sysfs_groups[attr++] = &rc_dev_wakeup_protocol_attr_grp;
 	dev->sysfs_groups[attr++] = NULL;
 
-	/*
-	 * Take the lock here, as the device sysfs node will appear
-	 * when device_add() is called, which may trigger an ir-keytable udev
-	 * rule, which will in turn call show_protocols and access
-	 * dev->enabled_protocols before it has been initialized.
-	 */
-	mutex_lock(&dev->lock);
-
 	rc = device_add(&dev->dev);
 	if (rc)
 		goto out_unlock;
@@ -1440,16 +1448,6 @@ int rc_register_device(struct rc_dev *dev)
 	dev->input_dev->phys = dev->input_phys;
 	dev->input_dev->name = dev->input_name;
 
-	/* input_register_device can call ir_open, so unlock mutex here */
-	mutex_unlock(&dev->lock);
-
-	rc = input_register_device(dev->input_dev);
-
-	mutex_lock(&dev->lock);
-
-	if (rc)
-		goto out_table;
-
 	/*
 	 * Default delay of 250ms is too short for some protocols, especially
 	 * since the timeout is currently set to 250ms. Increase it to 500ms,
@@ -1465,6 +1463,11 @@ int rc_register_device(struct rc_dev *dev)
 	 */
 	dev->input_dev->rep[REP_PERIOD] = 125;
 
+	/* rc_open will be called here */
+	rc = input_register_device(dev->input_dev);
+	if (rc)
+		goto out_table;
+
 	path = kobject_get_path(&dev->dev.kobj, GFP_KERNEL);
 	dev_info(&dev->dev, "%s as %s\n",
 		dev->input_name ?: "Unspecified device", path ?: "N/A");
@@ -1475,10 +1478,7 @@ int rc_register_device(struct rc_dev *dev)
 			request_module_nowait("ir-lirc-codec");
 			raw_init = true;
 		}
-		/* calls ir_register_device so unlock mutex here*/
-		mutex_unlock(&dev->lock);
 		rc = ir_raw_event_register(dev);
-		mutex_lock(&dev->lock);
 		if (rc < 0)
 			goto out_input;
 	}
@@ -1491,6 +1491,9 @@ int rc_register_device(struct rc_dev *dev)
 		dev->enabled_protocols = rc_type;
 	}
 
+	/* Allow the RC sysfs nodes to be accessible */
+	mutex_lock(&dev->lock);
+	atomic_set(&dev->initialized, 1);
 	mutex_unlock(&dev->lock);
 
 	IR_dprintk(1, "Registered rc%u (driver: %s, remote: %s, mode %s)\n",
@@ -1512,7 +1515,6 @@ out_table:
 out_dev:
 	device_del(&dev->dev);
 out_unlock:
-	mutex_unlock(&dev->lock);
 	ida_simple_remove(&rc_ida, minor);
 	return rc;
 }
diff --git a/drivers/media/rc/sunxi-cir.c b/drivers/media/rc/sunxi-cir.c
index 40f77685cc4a..eaadc081760a 100644
--- a/drivers/media/rc/sunxi-cir.c
+++ b/drivers/media/rc/sunxi-cir.c
@@ -326,6 +326,7 @@ static const struct of_device_id sunxi_ir_match[] = {
 	{ .compatible = "allwinner,sun5i-a13-ir", },
 	{},
 };
+MODULE_DEVICE_TABLE(of, sunxi_ir_match);
 
 static struct platform_driver sunxi_ir_driver = {
 	.probe          = sunxi_ir_probe,
diff --git a/drivers/media/tuners/m88rs6000t.c b/drivers/media/tuners/m88rs6000t.c
index 504bfbc4027a..9f3e0fd4cad9 100644
--- a/drivers/media/tuners/m88rs6000t.c
+++ b/drivers/media/tuners/m88rs6000t.c
@@ -461,13 +461,12 @@ static int m88rs6000t_sleep(struct dvb_frontend *fe)
 	dev_dbg(&dev->client->dev, "%s:\n", __func__);
 
 	ret = regmap_write(dev->regmap, 0x07, 0x6d);
-	if (ret)
-		goto err;
-	usleep_range(5000, 10000);
-err:
-	if (ret)
+	if (ret) {
 		dev_dbg(&dev->client->dev, "failed=%d\n", ret);
-	return ret;
+		return ret;
+	}
+	usleep_range(5000, 10000);
+	return 0;
 }
 
 static int m88rs6000t_get_frequency(struct dvb_frontend *fe, u32 *frequency)
diff --git a/drivers/media/tuners/r820t.c b/drivers/media/tuners/r820t.c
index a7a8452e99d2..6ab35e315fe7 100644
--- a/drivers/media/tuners/r820t.c
+++ b/drivers/media/tuners/r820t.c
@@ -1295,7 +1295,7 @@ static int generic_set_freq(struct dvb_frontend *fe,
 			    v4l2_std_id std, u32 delsys)
 {
 	struct r820t_priv		*priv = fe->tuner_priv;
-	int				rc = -EINVAL;
+	int				rc;
 	u32				lo_freq;
 
 	tuner_dbg("should set frequency to %d kHz, bw %d MHz\n",
diff --git a/drivers/media/tuners/si2157.c b/drivers/media/tuners/si2157.c
index 0e1ca2b00e61..243ac3816028 100644
--- a/drivers/media/tuners/si2157.c
+++ b/drivers/media/tuners/si2157.c
@@ -364,8 +364,8 @@ static int si2157_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 static const struct dvb_tuner_ops si2157_ops = {
 	.info = {
 		.name           = "Silicon Labs Si2146/2147/2148/2157/2158",
-		.frequency_min  = 55000000,
-		.frequency_max  = 862000000,
+		.frequency_min  = 42000000,
+		.frequency_max  = 870000000,
 	},
 
 	.init = si2157_init,
@@ -403,7 +403,7 @@ err:
 }
 
 static int si2157_probe(struct i2c_client *client,
-		const struct i2c_device_id *id)
+			const struct i2c_device_id *id)
 {
 	struct si2157_config *cfg = client->dev.platform_data;
 	struct dvb_frontend *fe = cfg->fe;
@@ -438,6 +438,31 @@ static int si2157_probe(struct i2c_client *client,
 	memcpy(&fe->ops.tuner_ops, &si2157_ops, sizeof(struct dvb_tuner_ops));
 	fe->tuner_priv = client;
 
+#ifdef CONFIG_MEDIA_CONTROLLER
+	if (cfg->mdev) {
+		dev->mdev = cfg->mdev;
+
+		dev->ent.name = KBUILD_MODNAME;
+		dev->ent.function = MEDIA_ENT_F_TUNER;
+
+		dev->pad[TUNER_PAD_RF_INPUT].flags = MEDIA_PAD_FL_SINK;
+		dev->pad[TUNER_PAD_OUTPUT].flags = MEDIA_PAD_FL_SOURCE;
+		dev->pad[TUNER_PAD_AUD_OUT].flags = MEDIA_PAD_FL_SOURCE;
+
+		ret = media_entity_pads_init(&dev->ent, TUNER_NUM_PADS,
+					     &dev->pad[0]);
+
+		if (ret)
+			goto err_kfree;
+
+		ret = media_device_register_entity(cfg->mdev, &dev->ent);
+		if (ret) {
+			media_entity_cleanup(&dev->ent);
+			goto err_kfree;
+		}
+	}
+#endif
+
 	dev_info(&client->dev, "Silicon Labs %s successfully attached\n",
 			dev->chiptype == SI2157_CHIPTYPE_SI2146 ?
 			"Si2146" : "Si2147/2148/2157/2158");
@@ -458,6 +483,14 @@ static int si2157_remove(struct i2c_client *client)
 
 	dev_dbg(&client->dev, "\n");
 
+	/* stop statistics polling */
+	cancel_delayed_work_sync(&dev->stat_work);
+
+#ifdef CONFIG_MEDIA_CONTROLLER_DVB
+	if (dev->mdev)
+		media_device_unregister_entity(&dev->ent);
+#endif
+
 	memset(&fe->ops.tuner_ops, 0, sizeof(struct dvb_tuner_ops));
 	fe->tuner_priv = NULL;
 	kfree(dev);
diff --git a/drivers/media/tuners/si2157.h b/drivers/media/tuners/si2157.h
index 4db97ab744d6..5f1a60bf7ced 100644
--- a/drivers/media/tuners/si2157.h
+++ b/drivers/media/tuners/si2157.h
@@ -18,6 +18,7 @@
 #define SI2157_H
 
 #include <linux/kconfig.h>
+#include <media/media-device.h>
 #include "dvb_frontend.h"
 
 /*
@@ -30,6 +31,10 @@ struct si2157_config {
 	 */
 	struct dvb_frontend *fe;
 
+#if defined(CONFIG_MEDIA_CONTROLLER)
+	struct media_device *mdev;
+#endif
+
 	/*
 	 * Spectral Inversion
 	 */
diff --git a/drivers/media/tuners/si2157_priv.h b/drivers/media/tuners/si2157_priv.h
index ecc463db8f69..589d558d381c 100644
--- a/drivers/media/tuners/si2157_priv.h
+++ b/drivers/media/tuners/si2157_priv.h
@@ -18,6 +18,7 @@
 #define SI2157_PRIV_H
 
 #include <linux/firmware.h>
+#include <media/v4l2-mc.h>
 #include "si2157.h"
 
 /* state struct */
@@ -31,6 +32,13 @@ struct si2157_dev {
 	u8 if_port;
 	u32 if_frequency;
 	struct delayed_work stat_work;
+
+#if defined(CONFIG_MEDIA_CONTROLLER)
+	struct media_device	*mdev;
+	struct media_entity	ent;
+	struct media_pad	pad[TUNER_NUM_PADS];
+#endif
+
 };
 
 #define SI2157_CHIPTYPE_SI2157 0
diff --git a/drivers/media/tuners/tuner-xc2028.c b/drivers/media/tuners/tuner-xc2028.c
index 4e941f00b600..317ef63ee789 100644
--- a/drivers/media/tuners/tuner-xc2028.c
+++ b/drivers/media/tuners/tuner-xc2028.c
@@ -1403,11 +1403,14 @@ static int xc2028_set_config(struct dvb_frontend *fe, void *priv_cfg)
 	 * in order to avoid troubles during device release.
 	 */
 	kfree(priv->ctrl.fname);
+	priv->ctrl.fname = NULL;
 	memcpy(&priv->ctrl, p, sizeof(priv->ctrl));
 	if (p->fname) {
 		priv->ctrl.fname = kstrdup(p->fname, GFP_KERNEL);
-		if (priv->ctrl.fname == NULL)
+		if (priv->ctrl.fname == NULL) {
 			rc = -ENOMEM;
+			goto unlock;
+		}
 	}
 
 	/*
@@ -1439,6 +1442,7 @@ static int xc2028_set_config(struct dvb_frontend *fe, void *priv_cfg)
 		} else
 			priv->state = XC2028_WAITING_FIRMWARE;
 	}
+unlock:
 	mutex_unlock(&priv->lock);
 
 	return rc;
diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c
index 219ebafae70f..d95c7e082ccf 100644
--- a/drivers/media/tuners/xc4000.c
+++ b/drivers/media/tuners/xc4000.c
@@ -1508,7 +1508,7 @@ static int xc4000_get_signal(struct dvb_frontend *fe, u16 *strength)
 	if (value >= 0x2000) {
 		value = 0;
 	} else {
-		value = ~value << 3;
+		value = (~value << 3) & 0xffff;
 	}
 
 	goto ret;
diff --git a/drivers/media/usb/airspy/airspy.c b/drivers/media/usb/airspy/airspy.c
index 0d4ac5947f3a..87c12930416f 100644
--- a/drivers/media/usb/airspy/airspy.c
+++ b/drivers/media/usb/airspy/airspy.c
@@ -104,9 +104,8 @@ struct airspy_frame_buf {
 };
 
 struct airspy {
-#define POWER_ON           (1 << 1)
-#define URB_BUF            (1 << 2)
-#define USB_STATE_URB_BUF  (1 << 3)
+#define POWER_ON	   1
+#define USB_STATE_URB_BUF  2
 	unsigned long flags;
 
 	struct device *dev;
@@ -359,7 +358,7 @@ static int airspy_submit_urbs(struct airspy *s)
 
 static int airspy_free_stream_bufs(struct airspy *s)
 {
-	if (s->flags & USB_STATE_URB_BUF) {
+	if (test_bit(USB_STATE_URB_BUF, &s->flags)) {
 		while (s->buf_num) {
 			s->buf_num--;
 			dev_dbg(s->dev, "free buf=%d\n", s->buf_num);
@@ -368,7 +367,7 @@ static int airspy_free_stream_bufs(struct airspy *s)
 					  s->dma_addr[s->buf_num]);
 		}
 	}
-	s->flags &= ~USB_STATE_URB_BUF;
+	clear_bit(USB_STATE_URB_BUF, &s->flags);
 
 	return 0;
 }
@@ -394,7 +393,7 @@ static int airspy_alloc_stream_bufs(struct airspy *s)
 		dev_dbg(s->dev, "alloc buf=%d %p (dma %llu)\n", s->buf_num,
 				s->buf_list[s->buf_num],
 				(long long)s->dma_addr[s->buf_num]);
-		s->flags |= USB_STATE_URB_BUF;
+		set_bit(USB_STATE_URB_BUF, &s->flags);
 	}
 
 	return 0;
diff --git a/drivers/media/usb/as102/as102_drv.h b/drivers/media/usb/as102/as102_drv.h
index aee2d76e8dfc..8def19d9ab92 100644
--- a/drivers/media/usb/as102/as102_drv.h
+++ b/drivers/media/usb/as102/as102_drv.h
@@ -52,7 +52,7 @@ struct as10x_bus_adapter_t {
 	struct as10x_cmd_t *cmd, *rsp;
 
 	/* bus adapter private ops callback */
-	struct as102_priv_ops_t *ops;
+	const struct as102_priv_ops_t *ops;
 };
 
 struct as102_dev_t {
diff --git a/drivers/media/usb/as102/as102_usb_drv.c b/drivers/media/usb/as102/as102_usb_drv.c
index 3f669066ccf6..0e8030c071b8 100644
--- a/drivers/media/usb/as102/as102_usb_drv.c
+++ b/drivers/media/usb/as102/as102_usb_drv.c
@@ -189,7 +189,7 @@ static int as102_read_ep2(struct as10x_bus_adapter_t *bus_adap,
 	return actual_len;
 }
 
-static struct as102_priv_ops_t as102_priv_ops = {
+static const struct as102_priv_ops_t as102_priv_ops = {
 	.upload_fw_pkt	= as102_send_ep1,
 	.xfer_cmd	= as102_usb_xfer_cmd,
 	.as102_read_ep2	= as102_read_ep2,
diff --git a/drivers/media/usb/au0828/au0828-core.c b/drivers/media/usb/au0828/au0828-core.c
index 9e29e70a78d7..5dc82e8c8670 100644
--- a/drivers/media/usb/au0828/au0828-core.c
+++ b/drivers/media/usb/au0828/au0828-core.c
@@ -20,6 +20,7 @@
  */
 
 #include "au0828.h"
+#include "au8522.h"
 
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -134,16 +135,16 @@ static void au0828_unregister_media_device(struct au0828_dev *dev)
 {
 
 #ifdef CONFIG_MEDIA_CONTROLLER
-	if (dev->media_dev) {
+	if (dev->media_dev &&
+		media_devnode_is_registered(&dev->media_dev->devnode)) {
 		media_device_unregister(dev->media_dev);
 		media_device_cleanup(dev->media_dev);
-		kfree(dev->media_dev);
 		dev->media_dev = NULL;
 	}
 #endif
 }
 
-static void au0828_usb_release(struct au0828_dev *dev)
+void au0828_usb_release(struct au0828_dev *dev)
 {
 	au0828_unregister_media_device(dev);
 
@@ -153,33 +154,6 @@ static void au0828_usb_release(struct au0828_dev *dev)
 	kfree(dev);
 }
 
-#ifdef CONFIG_VIDEO_AU0828_V4L2
-
-static void au0828_usb_v4l2_media_release(struct au0828_dev *dev)
-{
-#ifdef CONFIG_MEDIA_CONTROLLER
-	int i;
-
-	for (i = 0; i < AU0828_MAX_INPUT; i++) {
-		if (AUVI_INPUT(i).type == AU0828_VMUX_UNDEFINED)
-			return;
-		media_device_unregister_entity(&dev->input_ent[i]);
-	}
-#endif
-}
-
-static void au0828_usb_v4l2_release(struct v4l2_device *v4l2_dev)
-{
-	struct au0828_dev *dev =
-		container_of(v4l2_dev, struct au0828_dev, v4l2_dev);
-
-	v4l2_ctrl_handler_free(&dev->v4l2_ctrl_hdl);
-	v4l2_device_unregister(&dev->v4l2_dev);
-	au0828_usb_v4l2_media_release(dev);
-	au0828_usb_release(dev);
-}
-#endif
-
 static void au0828_usb_disconnect(struct usb_interface *interface)
 {
 	struct au0828_dev *dev = usb_get_intfdata(interface);
@@ -202,18 +176,13 @@ static void au0828_usb_disconnect(struct usb_interface *interface)
 	mutex_lock(&dev->mutex);
 	dev->usbdev = NULL;
 	mutex_unlock(&dev->mutex);
-#ifdef CONFIG_VIDEO_AU0828_V4L2
-	if (AUVI_INPUT(0).type != AU0828_VMUX_UNDEFINED) {
-		au0828_analog_unregister(dev);
-		v4l2_device_disconnect(&dev->v4l2_dev);
-		v4l2_device_put(&dev->v4l2_dev);
+	if (au0828_analog_unregister(dev)) {
 		/*
 		 * No need to call au0828_usb_release() if V4L2 is enabled,
 		 * as this is already called via au0828_usb_v4l2_release()
 		 */
 		return;
 	}
-#endif
 	au0828_usb_release(dev);
 }
 
@@ -223,103 +192,334 @@ static int au0828_media_device_init(struct au0828_dev *dev,
 #ifdef CONFIG_MEDIA_CONTROLLER
 	struct media_device *mdev;
 
-	mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
+	mdev = media_device_get_devres(&udev->dev);
 	if (!mdev)
 		return -ENOMEM;
 
-	mdev->dev = &udev->dev;
-
-	if (!dev->board.name)
-		strlcpy(mdev->model, "unknown au0828", sizeof(mdev->model));
-	else
-		strlcpy(mdev->model, dev->board.name, sizeof(mdev->model));
-	if (udev->serial)
-		strlcpy(mdev->serial, udev->serial, sizeof(mdev->serial));
-	strcpy(mdev->bus_info, udev->devpath);
-	mdev->hw_revision = le16_to_cpu(udev->descriptor.bcdDevice);
-	mdev->driver_version = LINUX_VERSION_CODE;
-
-	media_device_init(mdev);
+	/* check if media device is already initialized */
+	if (!mdev->dev)
+		media_device_usb_init(mdev, udev, udev->product);
 
 	dev->media_dev = mdev;
 #endif
 	return 0;
 }
 
+#ifdef CONFIG_MEDIA_CONTROLLER
+static void au0828_media_graph_notify(struct media_entity *new,
+				      void *notify_data)
+{
+	struct au0828_dev *dev = (struct au0828_dev *) notify_data;
+	int ret;
+	struct media_entity *entity, *mixer = NULL, *decoder = NULL;
+
+	if (!new) {
+		/*
+		 * Called during au0828 probe time to connect
+		 * entites that were created prior to registering
+		 * the notify handler. Find mixer and decoder.
+		*/
+		media_device_for_each_entity(entity, dev->media_dev) {
+			if (entity->function == MEDIA_ENT_F_AUDIO_MIXER)
+				mixer = entity;
+			else if (entity->function == MEDIA_ENT_F_ATV_DECODER)
+				decoder = entity;
+		}
+		goto create_link;
+	}
+
+	switch (new->function) {
+	case MEDIA_ENT_F_AUDIO_MIXER:
+		mixer = new;
+		if (dev->decoder)
+			decoder = dev->decoder;
+		break;
+	case MEDIA_ENT_F_ATV_DECODER:
+		/* In case, Mixer is added first, find mixer and create link */
+		media_device_for_each_entity(entity, dev->media_dev) {
+			if (entity->function == MEDIA_ENT_F_AUDIO_MIXER)
+				mixer = entity;
+		}
+		decoder = new;
+		break;
+	default:
+		break;
+	}
+
+create_link:
+	if (decoder && mixer) {
+		ret = media_create_pad_link(decoder,
+					    DEMOD_PAD_AUDIO_OUT,
+					    mixer, 0,
+					    MEDIA_LNK_FL_ENABLED);
+		if (ret)
+			dev_err(&dev->usbdev->dev,
+				"Mixer Pad Link Create Error: %d\n", ret);
+	}
+}
 
-static int au0828_create_media_graph(struct au0828_dev *dev)
+static int au0828_enable_source(struct media_entity *entity,
+				struct media_pipeline *pipe)
 {
-#ifdef CONFIG_MEDIA_CONTROLLER
-	struct media_device *mdev = dev->media_dev;
-	struct media_entity *entity;
-	struct media_entity *tuner = NULL, *decoder = NULL;
-	int i, ret;
+	struct media_entity  *source, *find_source;
+	struct media_entity *sink;
+	struct media_link *link, *found_link = NULL;
+	int ret = 0;
+	struct media_device *mdev = entity->graph_obj.mdev;
+	struct au0828_dev *dev;
 
 	if (!mdev)
-		return 0;
+		return -ENODEV;
 
-	media_device_for_each_entity(entity, mdev) {
-		switch (entity->function) {
-		case MEDIA_ENT_F_TUNER:
-			tuner = entity;
-			break;
-		case MEDIA_ENT_F_ATV_DECODER:
-			decoder = entity;
+	mutex_lock(&mdev->graph_mutex);
+
+	dev = mdev->source_priv;
+
+	/*
+	 * For Audio and V4L2 entity, find the link to which decoder
+	 * is the sink. Look for an active link between decoder and
+	 * source (tuner/s-video/Composite), if one exists, nothing
+	 * to do. If not, look for any  active links between source
+	 * and any other entity. If one exists, source is busy. If
+	 * source is free, setup link and start pipeline from source.
+	 * For DVB FE entity, the source for the link is the tuner.
+	 * Check if tuner is available and setup link and start
+	 * pipeline.
+	*/
+	if (entity->function == MEDIA_ENT_F_DTV_DEMOD) {
+		sink = entity;
+		find_source = dev->tuner;
+	} else {
+		/* Analog isn't configured or register failed */
+		if (!dev->decoder) {
+			ret = -ENODEV;
+			goto end;
+		}
+
+		sink = dev->decoder;
+
+		/*
+		 * Default input is tuner and default input_type
+		 * is AU0828_VMUX_TELEVISION.
+		 * FIXME:
+		 * There is a problem when s_input is called to
+		 * change the default input. s_input will try to
+		 * enable_source before attempting to change the
+		 * input on the device, and will end up enabling
+		 * default source which is tuner.
+		 *
+		 * Additional logic is necessary in au0828
+		 * to detect that the input has changed and
+		 * enable the right source.
+		*/
+
+		if (dev->input_type == AU0828_VMUX_TELEVISION)
+			find_source = dev->tuner;
+		else if (dev->input_type == AU0828_VMUX_SVIDEO ||
+			 dev->input_type == AU0828_VMUX_COMPOSITE)
+			find_source = &dev->input_ent[dev->input_type];
+		else {
+			/* unknown input - let user select input */
+			ret = 0;
+			goto end;
+		}
+	}
+
+	/* Is an active link between sink and source */
+	if (dev->active_link) {
+		/*
+		 * If DVB is using the tuner and calling entity is
+		 * audio/video, the following check will be false,
+		 * since sink is different. Result is Busy.
+		 */
+		if (dev->active_link->sink->entity == sink &&
+		    dev->active_link->source->entity == find_source) {
+			/*
+			 * Either ALSA or Video own tuner. sink is
+			 * the same for both. Prevent Video stepping
+			 * on ALSA when ALSA owns the source.
+			*/
+			if (dev->active_link_owner != entity &&
+			    dev->active_link_owner->function ==
+						MEDIA_ENT_F_AUDIO_CAPTURE) {
+				pr_debug("ALSA has the tuner\n");
+				ret = -EBUSY;
+				goto end;
+			}
+			ret = 0;
+			goto end;
+		} else {
+			ret = -EBUSY;
+			goto end;
+		}
+	}
+
+	list_for_each_entry(link, &sink->links, list) {
+		/* Check sink, and source */
+		if (link->sink->entity == sink &&
+		    link->source->entity == find_source) {
+			found_link = link;
 			break;
 		}
 	}
 
-	/* Analog setup, using tuner as a link */
+	if (!found_link) {
+		ret = -ENODEV;
+		goto end;
+	}
 
-	/* Something bad happened! */
-	if (!decoder)
-		return -EINVAL;
+	/* activate link between source and sink and start pipeline */
+	source = found_link->source->entity;
+	ret = __media_entity_setup_link(found_link, MEDIA_LNK_FL_ENABLED);
+	if (ret) {
+		pr_err("Activate tuner link %s->%s. Error %d\n",
+			source->name, sink->name, ret);
+		goto end;
+	}
 
-	if (tuner) {
-		ret = media_create_pad_link(tuner, TUNER_PAD_IF_OUTPUT,
-					    decoder, 0,
-					    MEDIA_LNK_FL_ENABLED);
+	ret = __media_entity_pipeline_start(entity, pipe);
+	if (ret) {
+		pr_err("Start Pipeline: %s->%s Error %d\n",
+			source->name, entity->name, ret);
+		ret = __media_entity_setup_link(found_link, 0);
+		pr_err("Deactivate link Error %d\n", ret);
+		goto end;
+	}
+	/*
+	 * save active link and active link owner to avoid audio
+	 * deactivating video owned link from disable_source and
+	 * vice versa
+	*/
+	dev->active_link = found_link;
+	dev->active_link_owner = entity;
+	dev->active_source = source;
+	dev->active_sink = sink;
+
+	pr_debug("Enabled Source: %s->%s->%s Ret %d\n",
+		 dev->active_source->name, dev->active_sink->name,
+		 dev->active_link_owner->name, ret);
+end:
+	mutex_unlock(&mdev->graph_mutex);
+	pr_debug("au0828_enable_source() end %s %d %d\n",
+		 entity->name, entity->function, ret);
+	return ret;
+}
+
+static void au0828_disable_source(struct media_entity *entity)
+{
+	int ret = 0;
+	struct media_device *mdev = entity->graph_obj.mdev;
+	struct au0828_dev *dev;
+
+	if (!mdev)
+		return;
+
+	mutex_lock(&mdev->graph_mutex);
+	dev = mdev->source_priv;
+
+	if (!dev->active_link) {
+		ret = -ENODEV;
+		goto end;
+	}
+
+	/* link is active - stop pipeline from source (tuner) */
+	if (dev->active_link->sink->entity == dev->active_sink &&
+	    dev->active_link->source->entity == dev->active_source) {
+		/*
+		 * prevent video from deactivating link when audio
+		 * has active pipeline
+		*/
+		if (dev->active_link_owner != entity)
+			goto end;
+		__media_entity_pipeline_stop(entity);
+		ret = __media_entity_setup_link(dev->active_link, 0);
 		if (ret)
-			return ret;
+			pr_err("Deactivate link Error %d\n", ret);
+
+		pr_debug("Disabled Source: %s->%s->%s Ret %d\n",
+			 dev->active_source->name, dev->active_sink->name,
+			 dev->active_link_owner->name, ret);
+
+		dev->active_link = NULL;
+		dev->active_link_owner = NULL;
+		dev->active_source = NULL;
+		dev->active_sink = NULL;
 	}
-	ret = media_create_pad_link(decoder, 1, &dev->vdev.entity, 0,
-				    MEDIA_LNK_FL_ENABLED);
-	if (ret)
-		return ret;
-	ret = media_create_pad_link(decoder, 2, &dev->vbi_dev.entity, 0,
-				    MEDIA_LNK_FL_ENABLED);
-	if (ret)
-		return ret;
 
-	for (i = 0; i < AU0828_MAX_INPUT; i++) {
-		struct media_entity *ent = &dev->input_ent[i];
+end:
+	mutex_unlock(&mdev->graph_mutex);
+}
+#endif
 
-		if (AUVI_INPUT(i).type == AU0828_VMUX_UNDEFINED)
-			break;
+static int au0828_media_device_register(struct au0828_dev *dev,
+					struct usb_device *udev)
+{
+#ifdef CONFIG_MEDIA_CONTROLLER
+	int ret;
+	struct media_entity *entity, *demod = NULL, *tuner = NULL;
 
-		switch (AUVI_INPUT(i).type) {
-		case AU0828_VMUX_CABLE:
-		case AU0828_VMUX_TELEVISION:
-		case AU0828_VMUX_DVB:
-			if (!tuner)
-				break;
-
-			ret = media_create_pad_link(ent, 0, tuner,
-						    TUNER_PAD_RF_INPUT,
-						    MEDIA_LNK_FL_ENABLED);
-			if (ret)
-				return ret;
-			break;
-		case AU0828_VMUX_COMPOSITE:
-		case AU0828_VMUX_SVIDEO:
-		default: /* AU0828_VMUX_DEBUG */
-			/* FIXME: fix the decoder PAD */
-			ret = media_create_pad_link(ent, 0, decoder, 0, 0);
-			if (ret)
-				return ret;
-			break;
+	if (!dev->media_dev)
+		return 0;
+
+	if (!media_devnode_is_registered(&dev->media_dev->devnode)) {
+
+		/* register media device */
+		ret = media_device_register(dev->media_dev);
+		if (ret) {
+			dev_err(&udev->dev,
+				"Media Device Register Error: %d\n", ret);
+			return ret;
+		}
+	} else {
+		/*
+		 * Call au0828_media_graph_notify() to connect
+		 * audio graph to our graph. In this case, audio
+		 * driver registered the device and there is no
+		 * entity_notify to be called when new entities
+		 * are added. Invoke it now.
+		*/
+		au0828_media_graph_notify(NULL, (void *) dev);
+	}
+
+	/*
+	 * Find tuner and demod to disable the link between
+	 * the two to avoid disable step when tuner is requested
+	 * by video or audio. Note that this step can't be done
+	 * until dvb graph is created during dvb register.
+	*/
+	media_device_for_each_entity(entity, dev->media_dev) {
+		if (entity->function == MEDIA_ENT_F_DTV_DEMOD)
+			demod = entity;
+		else if (entity->function == MEDIA_ENT_F_TUNER)
+			tuner = entity;
+	}
+	/* Disable link between tuner and demod */
+	if (tuner && demod) {
+		struct media_link *link;
+
+		list_for_each_entry(link, &demod->links, list) {
+			if (link->sink->entity == demod &&
+			    link->source->entity == tuner) {
+				media_entity_setup_link(link, 0);
+			}
 		}
 	}
+
+	/* register entity_notify callback */
+	dev->entity_notify.notify_data = (void *) dev;
+	dev->entity_notify.notify = (void *) au0828_media_graph_notify;
+	ret = media_device_register_entity_notify(dev->media_dev,
+						  &dev->entity_notify);
+	if (ret) {
+		dev_err(&udev->dev,
+			"Media Device register entity_notify Error: %d\n",
+			ret);
+		return ret;
+	}
+	/* set enable_source */
+	dev->media_dev->source_priv = (void *) dev;
+	dev->media_dev->enable_source = au0828_enable_source;
+	dev->media_dev->disable_source = au0828_disable_source;
 #endif
 	return 0;
 }
@@ -378,32 +578,13 @@ static int au0828_usb_probe(struct usb_interface *interface,
 		return retval;
 	}
 
-#ifdef CONFIG_VIDEO_AU0828_V4L2
-	dev->v4l2_dev.release = au0828_usb_v4l2_release;
-
-	/* Create the v4l2_device */
-#ifdef CONFIG_MEDIA_CONTROLLER
-	dev->v4l2_dev.mdev = dev->media_dev;
-#endif
-	retval = v4l2_device_register(&interface->dev, &dev->v4l2_dev);
+	retval = au0828_v4l2_device_register(interface, dev);
 	if (retval) {
-		pr_err("%s() v4l2_device_register failed\n",
-		       __func__);
+		au0828_usb_v4l2_media_release(dev);
 		mutex_unlock(&dev->lock);
 		kfree(dev);
 		return retval;
 	}
-	/* This control handler will inherit the controls from au8522 */
-	retval = v4l2_ctrl_handler_init(&dev->v4l2_ctrl_hdl, 4);
-	if (retval) {
-		pr_err("%s() v4l2_ctrl_handler_init failed\n",
-		       __func__);
-		mutex_unlock(&dev->lock);
-		kfree(dev);
-		return retval;
-	}
-	dev->v4l2_dev.ctrl_handler = &dev->v4l2_ctrl_hdl;
-#endif
 
 	/* Power Up the bridge */
 	au0828_write(dev, REG_600, 1 << 4);
@@ -417,11 +598,13 @@ static int au0828_usb_probe(struct usb_interface *interface,
 	/* Setup */
 	au0828_card_setup(dev);
 
-#ifdef CONFIG_VIDEO_AU0828_V4L2
 	/* Analog TV */
-	if (AUVI_INPUT(0).type != AU0828_VMUX_UNDEFINED)
-		au0828_analog_register(dev, interface);
-#endif
+	retval = au0828_analog_register(dev, interface);
+	if (retval) {
+		pr_err("%s() au0282_dev_register failed to register on V4L2\n",
+			__func__);
+		goto done;
+	}
 
 	/* Digital TV */
 	retval = au0828_dvb_register(dev);
@@ -443,16 +626,7 @@ static int au0828_usb_probe(struct usb_interface *interface,
 
 	mutex_unlock(&dev->lock);
 
-	retval = au0828_create_media_graph(dev);
-	if (retval) {
-		pr_err("%s() au0282_dev_register failed to create graph\n",
-		       __func__);
-		goto done;
-	}
-
-#ifdef CONFIG_MEDIA_CONTROLLER
-	retval = media_device_register(dev->media_dev);
-#endif
+	retval = au0828_media_device_register(dev, usbdev);
 
 done:
 	if (retval < 0)
diff --git a/drivers/media/usb/au0828/au0828-dvb.c b/drivers/media/usb/au0828/au0828-dvb.c
index 94363a3ba400..0e174e860614 100644
--- a/drivers/media/usb/au0828/au0828-dvb.c
+++ b/drivers/media/usb/au0828/au0828-dvb.c
@@ -181,7 +181,7 @@ static int stop_urb_transfer(struct au0828_dev *dev)
 static int start_urb_transfer(struct au0828_dev *dev)
 {
 	struct urb *purb;
-	int i, ret = -ENOMEM;
+	int i, ret;
 
 	dprintk(2, "%s()\n", __func__);
 
@@ -194,7 +194,7 @@ static int start_urb_transfer(struct au0828_dev *dev)
 
 		dev->urbs[i] = usb_alloc_urb(0, GFP_KERNEL);
 		if (!dev->urbs[i])
-			goto err;
+			return -ENOMEM;
 
 		purb = dev->urbs[i];
 
@@ -207,9 +207,10 @@ static int start_urb_transfer(struct au0828_dev *dev)
 		if (!purb->transfer_buffer) {
 			usb_free_urb(purb);
 			dev->urbs[i] = NULL;
+			ret = -ENOMEM;
 			pr_err("%s: failed big buffer allocation, err = %d\n",
 			       __func__, ret);
-			goto err;
+			return ret;
 		}
 
 		purb->status = -EINPROGRESS;
@@ -235,10 +236,7 @@ static int start_urb_transfer(struct au0828_dev *dev)
 	}
 
 	dev->urb_streaming = true;
-	ret = 0;
-
-err:
-	return ret;
+	return 0;
 }
 
 static void au0828_start_transport(struct au0828_dev *dev)
diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c
index 8c54fd21022e..13f6dab9ccc2 100644
--- a/drivers/media/usb/au0828/au0828-video.c
+++ b/drivers/media/usb/au0828/au0828-video.c
@@ -28,12 +28,14 @@
  */
 
 #include "au0828.h"
+#include "au8522.h"
 
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/device.h>
 #include <media/v4l2-common.h>
+#include <media/v4l2-mc.h>
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-event.h>
 #include <media/tuner.h>
@@ -638,61 +640,64 @@ static inline int au0828_isoc_copy(struct au0828_dev *dev, struct urb *urb)
 	return rc;
 }
 
-static int au0828_enable_analog_tuner(struct au0828_dev *dev)
+void au0828_usb_v4l2_media_release(struct au0828_dev *dev)
 {
 #ifdef CONFIG_MEDIA_CONTROLLER
-	struct media_device *mdev = dev->media_dev;
-	struct media_entity *source;
-	struct media_link *link, *found_link = NULL;
-	int ret, active_links = 0;
-
-	if (!mdev || !dev->decoder)
-		return 0;
+	int i;
 
-	/*
-	 * This will find the tuner that is connected into the decoder.
-	 * Technically, this is not 100% correct, as the device may be
-	 * using an analog input instead of the tuner. However, as we can't
-	 * do DVB streaming while the DMA engine is being used for V4L2,
-	 * this should be enough for the actual needs.
-	 */
-	list_for_each_entry(link, &dev->decoder->links, list) {
-		if (link->sink->entity == dev->decoder) {
-			found_link = link;
-			if (link->flags & MEDIA_LNK_FL_ENABLED)
-				active_links++;
-			break;
-		}
+	for (i = 0; i < AU0828_MAX_INPUT; i++) {
+		if (AUVI_INPUT(i).type == AU0828_VMUX_UNDEFINED)
+			return;
+		media_device_unregister_entity(&dev->input_ent[i]);
 	}
+#endif
+}
 
-	if (active_links == 1 || !found_link)
-		return 0;
+static void au0828_usb_v4l2_release(struct v4l2_device *v4l2_dev)
+{
+	struct au0828_dev *dev =
+		container_of(v4l2_dev, struct au0828_dev, v4l2_dev);
+
+	v4l2_ctrl_handler_free(&dev->v4l2_ctrl_hdl);
+	v4l2_device_unregister(&dev->v4l2_dev);
+	au0828_usb_v4l2_media_release(dev);
+	au0828_usb_release(dev);
+}
 
-	source = found_link->source->entity;
-	list_for_each_entry(link, &source->links, list) {
-		struct media_entity *sink;
-		int flags = 0;
+int au0828_v4l2_device_register(struct usb_interface *interface,
+				struct au0828_dev *dev)
+{
+	int retval;
 
-		sink = link->sink->entity;
+	if (AUVI_INPUT(0).type == AU0828_VMUX_UNDEFINED)
+		return 0;
 
-		if (sink == dev->decoder)
-			flags = MEDIA_LNK_FL_ENABLED;
+	/* Create the v4l2_device */
+#ifdef CONFIG_MEDIA_CONTROLLER
+	dev->v4l2_dev.mdev = dev->media_dev;
+#endif
+	retval = v4l2_device_register(&interface->dev, &dev->v4l2_dev);
+	if (retval) {
+		pr_err("%s() v4l2_device_register failed\n",
+		       __func__);
+		mutex_unlock(&dev->lock);
+		kfree(dev);
+		return retval;
+	}
 
-		ret = media_entity_setup_link(link, flags);
-		if (ret) {
-			pr_err(
-				"Couldn't change link %s->%s to %s. Error %d\n",
-				source->name, sink->name,
-				flags ? "enabled" : "disabled",
-				ret);
-			return ret;
-		} else
-			au0828_isocdbg(
-				"link %s->%s was %s\n",
-				source->name, sink->name,
-				flags ? "ENABLED" : "disabled");
+	dev->v4l2_dev.release = au0828_usb_v4l2_release;
+
+	/* This control handler will inherit the controls from au8522 */
+	retval = v4l2_ctrl_handler_init(&dev->v4l2_ctrl_hdl, 4);
+	if (retval) {
+		pr_err("%s() v4l2_ctrl_handler_init failed\n",
+		       __func__);
+		mutex_unlock(&dev->lock);
+		kfree(dev);
+		return retval;
 	}
-#endif
+	dev->v4l2_dev.ctrl_handler = &dev->v4l2_ctrl_hdl;
+
 	return 0;
 }
 
@@ -707,9 +712,6 @@ static int queue_setup(struct vb2_queue *vq,
 		return sizes[0] < size ? -EINVAL : 0;
 	*nplanes = 1;
 	sizes[0] = size;
-
-	au0828_enable_analog_tuner(dev);
-
 	return 0;
 }
 
@@ -949,13 +951,23 @@ static struct vb2_ops au0828_video_qops = {
  * au0828_analog_unregister
  * unregister v4l2 devices
  */
-void au0828_analog_unregister(struct au0828_dev *dev)
+int au0828_analog_unregister(struct au0828_dev *dev)
 {
 	dprintk(1, "au0828_analog_unregister called\n");
+
+	/* No analog TV */
+	if (AUVI_INPUT(0).type == AU0828_VMUX_UNDEFINED)
+		return 0;
+
 	mutex_lock(&au0828_sysfs_lock);
 	video_unregister_device(&dev->vdev);
 	video_unregister_device(&dev->vbi_dev);
 	mutex_unlock(&au0828_sysfs_lock);
+
+	v4l2_device_disconnect(&dev->v4l2_dev);
+	v4l2_device_put(&dev->v4l2_dev);
+
+	return 1;
 }
 
 /* This function ensures that video frames continue to be delivered even if
@@ -1067,8 +1079,39 @@ static int au0828_v4l2_close(struct file *filp)
 		goto end;
 
 	if (dev->users == 1) {
-		/* Save some power by putting tuner to sleep */
-		v4l2_device_call_all(&dev->v4l2_dev, 0, core, s_power, 0);
+		/*
+		 * Avoid putting tuner in sleep if DVB or ALSA are
+		 * streaming.
+		 *
+		 * On most USB devices  like au0828 the tuner can
+		 * be safely put in sleep stare here if ALSA isn't
+		 * streaming. Exceptions are some very old USB tuner
+		 * models such as em28xx-based WinTV USB2 which have
+		 * a separate audio output jack. The devices that have
+		 * a separate audio output jack have analog tuners,
+		 * like Philips FM1236. Those devices are always on,
+		 * so the s_power callback are silently ignored.
+		 * So, the current logic here does the following:
+		 * Disable (put tuner to sleep) when
+		 * - ALSA and DVB aren't not streaming;
+		 * - the last V4L2 file handler is closed.
+		 *
+		 * FIXME:
+		 *
+		 * Additionally, this logic could be improved to
+		 * disable the media source if the above conditions
+		 * are met and if the device:
+		 * - doesn't have a separate audio out plug (or
+		 * - doesn't use a silicon tuner like xc2028/3028/4000/5000).
+		 *
+		 * Once this additional logic is in place, a callback
+		 * is needed to enable the media source and power on
+		 * the tuner, for radio to work.
+		*/
+		ret = v4l_enable_media_source(vdev);
+		if (ret == 0)
+			v4l2_device_call_all(&dev->v4l2_dev, 0, core,
+					     s_power, 0);
 		dev->std_set_in_tuner_core = 0;
 
 		/* When close the device, set the usb intf0 into alt0 to free
@@ -1312,7 +1355,6 @@ static int vidioc_enum_input(struct file *file, void *priv,
 		[AU0828_VMUX_CABLE] = "Cable TV",
 		[AU0828_VMUX_TELEVISION] = "Television",
 		[AU0828_VMUX_DVB] = "DVB",
-		[AU0828_VMUX_DEBUG] = "tv debug"
 	};
 
 	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
@@ -1375,9 +1417,11 @@ static void au0828_s_input(struct au0828_dev *dev, int index)
 	default:
 		dprintk(1, "unknown input type set [%d]\n",
 			AUVI_INPUT(index).type);
-		break;
+		return;
 	}
 
+	dev->ctrl_input = index;
+
 	v4l2_device_call_all(&dev->v4l2_dev, 0, video, s_routing,
 			AUVI_INPUT(index).vmux, 0, 0);
 
@@ -1409,6 +1453,7 @@ static void au0828_s_input(struct au0828_dev *dev, int index)
 static int vidioc_s_input(struct file *file, void *priv, unsigned int index)
 {
 	struct au0828_dev *dev = video_drvdata(file);
+	struct video_device *vfd = video_devdata(file);
 
 	dprintk(1, "VIDIOC_S_INPUT in function %s, input=%d\n", __func__,
 		index);
@@ -1416,9 +1461,19 @@ static int vidioc_s_input(struct file *file, void *priv, unsigned int index)
 		return -EINVAL;
 	if (AUVI_INPUT(index).type == 0)
 		return -EINVAL;
-	dev->ctrl_input = index;
+
+	if (dev->ctrl_input == index)
+		return 0;
+
 	au0828_s_input(dev, index);
-	return 0;
+
+	/*
+	 * Input has been changed. Disable the media source
+	 * associated with the old input and enable source
+	 * for the newly set input
+	 */
+	v4l_disable_media_source(vfd);
+	return v4l_enable_media_source(vfd);
 }
 
 static int vidioc_enumaudio(struct file *file, void *priv, struct v4l2_audio *a)
@@ -1469,10 +1524,16 @@ static int vidioc_s_audio(struct file *file, void *priv, const struct v4l2_audio
 static int vidioc_g_tuner(struct file *file, void *priv, struct v4l2_tuner *t)
 {
 	struct au0828_dev *dev = video_drvdata(file);
+	struct video_device *vfd = video_devdata(file);
+	int ret;
 
 	if (t->index != 0)
 		return -EINVAL;
 
+	ret = v4l_enable_media_source(vfd);
+	if (ret)
+		return ret;
+
 	dprintk(1, "%s called std_set %d dev_state %d\n", __func__,
 		dev->std_set_in_tuner_core, dev->dev_state);
 
@@ -1804,7 +1865,6 @@ static void au0828_analog_create_entities(struct au0828_dev *dev)
 		[AU0828_VMUX_CABLE] = "Cable TV",
 		[AU0828_VMUX_TELEVISION] = "Television",
 		[AU0828_VMUX_DVB] = "DVB",
-		[AU0828_VMUX_DEBUG] = "tv debug"
 	};
 	int ret, i;
 
@@ -1840,11 +1900,9 @@ static void au0828_analog_create_entities(struct au0828_dev *dev)
 		case AU0828_VMUX_CABLE:
 		case AU0828_VMUX_TELEVISION:
 		case AU0828_VMUX_DVB:
+		default: /* Just to shut up a warning */
 			ent->function = MEDIA_ENT_F_CONN_RF;
 			break;
-		default: /* AU0828_VMUX_DEBUG */
-			ent->function = MEDIA_ENT_F_CONN_TEST;
-			break;
 		}
 
 		ret = media_entity_pads_init(ent, 1, &dev->input_pad[i]);
@@ -1871,6 +1929,10 @@ int au0828_analog_register(struct au0828_dev *dev,
 	dprintk(1, "au0828_analog_register called for intf#%d!\n",
 		interface->cur_altsetting->desc.bInterfaceNumber);
 
+	/* No analog TV */
+	if (AUVI_INPUT(0).type == AU0828_VMUX_UNDEFINED)
+		return 0;
+
 	/* set au0828 usb interface0 to as5 */
 	retval = usb_set_interface(dev->usbdev,
 			interface->cur_altsetting->desc.bInterfaceNumber, 5);
@@ -1925,6 +1987,7 @@ int au0828_analog_register(struct au0828_dev *dev,
 	dev->ctrl_ainput = 0;
 	dev->ctrl_freq = 960;
 	dev->std = V4L2_STD_NTSC_M;
+	/* Default input is TV Tuner */
 	au0828_s_input(dev, 0);
 
 	mutex_init(&dev->vb_queue_lock);
@@ -1977,6 +2040,16 @@ int au0828_analog_register(struct au0828_dev *dev,
 		goto err_reg_vbi_dev;
 	}
 
+#ifdef CONFIG_MEDIA_CONTROLLER
+	retval = v4l2_mc_create_media_graph(dev->media_dev);
+	if (retval) {
+		pr_err("%s() au0282_dev_register failed to create graph\n",
+			__func__);
+		ret = -ENODEV;
+		goto err_reg_vbi_dev;
+	}
+#endif
+
 	dprintk(1, "%s completed!\n", __func__);
 
 	return 0;
diff --git a/drivers/media/usb/au0828/au0828.h b/drivers/media/usb/au0828/au0828.h
index 8276072bc55a..ff7f8510fb77 100644
--- a/drivers/media/usb/au0828/au0828.h
+++ b/drivers/media/usb/au0828/au0828.h
@@ -76,7 +76,6 @@ enum au0828_itype {
 	AU0828_VMUX_CABLE,
 	AU0828_VMUX_TELEVISION,
 	AU0828_VMUX_DVB,
-	AU0828_VMUX_DEBUG
 };
 
 struct au0828_input {
@@ -283,6 +282,12 @@ struct au0828_dev {
 	struct media_entity *decoder;
 	struct media_entity input_ent[AU0828_MAX_INPUT];
 	struct media_pad input_pad[AU0828_MAX_INPUT];
+	struct media_entity_notify entity_notify;
+	struct media_entity *tuner;
+	struct media_link *active_link;
+	struct media_entity *active_link_owner;
+	struct media_entity *active_source;
+	struct media_entity *active_sink;
 #endif
 };
 
@@ -301,6 +306,7 @@ struct au0828_dev {
 /* au0828-core.c */
 extern u32 au0828_read(struct au0828_dev *dev, u16 reg);
 extern u32 au0828_write(struct au0828_dev *dev, u16 reg, u32 val);
+extern void au0828_usb_release(struct au0828_dev *dev);
 extern int au0828_debug;
 
 /* ----------------------------------------------------------- */
@@ -319,16 +325,29 @@ extern int au0828_i2c_unregister(struct au0828_dev *dev);
 
 /* ----------------------------------------------------------- */
 /* au0828-video.c */
-extern int au0828_analog_register(struct au0828_dev *dev,
-			   struct usb_interface *interface);
-extern void au0828_analog_unregister(struct au0828_dev *dev);
 extern int au0828_start_analog_streaming(struct vb2_queue *vq,
 						unsigned int count);
 extern void au0828_stop_vbi_streaming(struct vb2_queue *vq);
 #ifdef CONFIG_VIDEO_AU0828_V4L2
+extern int au0828_v4l2_device_register(struct usb_interface *interface,
+				      struct au0828_dev *dev);
+
+extern int au0828_analog_register(struct au0828_dev *dev,
+			   struct usb_interface *interface);
+extern int au0828_analog_unregister(struct au0828_dev *dev);
+extern void au0828_usb_v4l2_media_release(struct au0828_dev *dev);
 extern void au0828_v4l2_suspend(struct au0828_dev *dev);
 extern void au0828_v4l2_resume(struct au0828_dev *dev);
 #else
+static inline int au0828_v4l2_device_register(struct usb_interface *interface,
+					      struct au0828_dev *dev)
+{ return 0; };
+static inline int au0828_analog_register(struct au0828_dev *dev,
+				     struct usb_interface *interface)
+{ return 0; };
+static inline int au0828_analog_unregister(struct au0828_dev *dev)
+{ return 0; };
+static inline void au0828_usb_v4l2_media_release(struct au0828_dev *dev) { };
 static inline void au0828_v4l2_suspend(struct au0828_dev *dev) { };
 static inline void au0828_v4l2_resume(struct au0828_dev *dev) { };
 #endif
diff --git a/drivers/media/usb/b2c2/flexcop-usb.c b/drivers/media/usb/b2c2/flexcop-usb.c
index 0bd969063392..d4bdba60b0f7 100644
--- a/drivers/media/usb/b2c2/flexcop-usb.c
+++ b/drivers/media/usb/b2c2/flexcop-usb.c
@@ -10,7 +10,7 @@
 /* Version information */
 #define DRIVER_VERSION "0.1"
 #define DRIVER_NAME "Technisat/B2C2 FlexCop II/IIb/III Digital TV USB Driver"
-#define DRIVER_AUTHOR "Patrick Boettcher <patrick.boettcher@desy.de>"
+#define DRIVER_AUTHOR "Patrick Boettcher <patrick.boettcher@posteo.de>"
 
 /* debug */
 #ifdef CONFIG_DVB_B2C2_FLEXCOP_DEBUG
diff --git a/drivers/media/usb/cpia2/cpia2_core.c b/drivers/media/usb/cpia2/cpia2_core.c
index 187012ce444b..0310fd6ed103 100644
--- a/drivers/media/usb/cpia2/cpia2_core.c
+++ b/drivers/media/usb/cpia2/cpia2_core.c
@@ -923,7 +923,7 @@ static int apply_vp_patch(struct camera_data *cam)
 	/* ... followed by the data payload */
 	for (i = 2; i < fw->size; i += 64) {
 		cmd.start = 0x0C; /* Data */
-		cmd.reg_count = min_t(int, 64, fw->size - i);
+		cmd.reg_count = min_t(uint, 64, fw->size - i);
 		memcpy(cmd.buffer.block_data, &fw->data[i], cmd.reg_count);
 		cpia2_send_command(cam, &cmd);
 	}
diff --git a/drivers/media/usb/cx231xx/cx231xx-417.c b/drivers/media/usb/cx231xx/cx231xx-417.c
index 48643b94e694..c9320d6c6131 100644
--- a/drivers/media/usb/cx231xx/cx231xx-417.c
+++ b/drivers/media/usb/cx231xx/cx231xx-417.c
@@ -1382,6 +1382,8 @@ static int cx231xx_bulk_copy(struct cx231xx *dev, struct urb *urb)
 	buffer_size = urb->actual_length;
 
 	buffer = kmalloc(buffer_size, GFP_ATOMIC);
+	if (!buffer)
+		return -ENOMEM;
 
 	memcpy(buffer, dma_q->ps_head, 3);
 	memcpy(buffer+3, p_buffer, buffer_size-3);
diff --git a/drivers/media/usb/cx231xx/cx231xx-audio.c b/drivers/media/usb/cx231xx/cx231xx-audio.c
index de4ae5eb4830..a6a9508418f8 100644
--- a/drivers/media/usb/cx231xx/cx231xx-audio.c
+++ b/drivers/media/usb/cx231xx/cx231xx-audio.c
@@ -499,6 +499,11 @@ static int snd_cx231xx_pcm_close(struct snd_pcm_substream *substream)
 	}
 
 	dev->adev.users--;
+	if (substream->runtime->dma_area) {
+		dev_dbg(dev->dev, "freeing\n");
+		vfree(substream->runtime->dma_area);
+		substream->runtime->dma_area = NULL;
+	}
 	mutex_unlock(&dev->lock);
 
 	if (dev->adev.users == 0 && dev->adev.shutdown == 1) {
diff --git a/drivers/media/usb/cx231xx/cx231xx-cards.c b/drivers/media/usb/cx231xx/cx231xx-cards.c
index 620b83d03f75..c63248a18823 100644
--- a/drivers/media/usb/cx231xx/cx231xx-cards.c
+++ b/drivers/media/usb/cx231xx/cx231xx-cards.c
@@ -1216,66 +1216,13 @@ static int cx231xx_media_device_init(struct cx231xx *dev,
 	if (!mdev)
 		return -ENOMEM;
 
-	mdev->dev = dev->dev;
-	strlcpy(mdev->model, dev->board.name, sizeof(mdev->model));
-	if (udev->serial)
-		strlcpy(mdev->serial, udev->serial, sizeof(mdev->serial));
-	strcpy(mdev->bus_info, udev->devpath);
-	mdev->hw_revision = le16_to_cpu(udev->descriptor.bcdDevice);
-	mdev->driver_version = LINUX_VERSION_CODE;
-
-	media_device_init(mdev);
+	media_device_usb_init(mdev, udev, dev->board.name);
 
 	dev->media_dev = mdev;
 #endif
 	return 0;
 }
 
-static int cx231xx_create_media_graph(struct cx231xx *dev)
-{
-#ifdef CONFIG_MEDIA_CONTROLLER
-	struct media_device *mdev = dev->media_dev;
-	struct media_entity *entity;
-	struct media_entity *tuner = NULL, *decoder = NULL;
-	int ret;
-
-	if (!mdev)
-		return 0;
-
-	media_device_for_each_entity(entity, mdev) {
-		switch (entity->function) {
-		case MEDIA_ENT_F_TUNER:
-			tuner = entity;
-			break;
-		case MEDIA_ENT_F_ATV_DECODER:
-			decoder = entity;
-			break;
-		}
-	}
-
-	/* Analog setup, using tuner as a link */
-
-	if (!decoder)
-		return 0;
-
-	if (tuner) {
-		ret = media_create_pad_link(tuner, TUNER_PAD_IF_OUTPUT, decoder, 0,
-					    MEDIA_LNK_FL_ENABLED);
-		if (ret < 0)
-			return ret;
-	}
-	ret = media_create_pad_link(decoder, 1, &dev->vdev.entity, 0,
-				    MEDIA_LNK_FL_ENABLED);
-	if (ret < 0)
-		return ret;
-	ret = media_create_pad_link(decoder, 2, &dev->vbi_dev.entity, 0,
-				    MEDIA_LNK_FL_ENABLED);
-	if (ret < 0)
-		return ret;
-#endif
-	return 0;
-}
-
 /*
  * cx231xx_init_dev()
  * allocates and inits the device structs, registers i2c bus and v4l device
@@ -1739,15 +1686,14 @@ static int cx231xx_usb_probe(struct usb_interface *interface,
 	/* load other modules required */
 	request_modules(dev);
 
-	retval = cx231xx_create_media_graph(dev);
-	if (retval < 0)
-		goto done;
-
 #ifdef CONFIG_MEDIA_CONTROLLER
-	retval = media_device_register(dev->media_dev);
-#endif
+	/* Init entities at the Media Controller */
+	cx231xx_v4l2_create_entities(dev);
 
-done:
+	retval = v4l2_mc_create_media_graph(dev->media_dev);
+	if (!retval)
+		retval = media_device_register(dev->media_dev);
+#endif
 	if (retval < 0)
 		cx231xx_release_resources(dev);
 	return retval;
diff --git a/drivers/media/usb/cx231xx/cx231xx-dvb.c b/drivers/media/usb/cx231xx/cx231xx-dvb.c
index b8d5b2be9293..ab2fb9fa0cd1 100644
--- a/drivers/media/usb/cx231xx/cx231xx-dvb.c
+++ b/drivers/media/usb/cx231xx/cx231xx-dvb.c
@@ -25,6 +25,7 @@
 
 #include <media/v4l2-common.h>
 #include <media/videobuf-vmalloc.h>
+#include <media/tuner.h>
 
 #include "xc5000.h"
 #include "s5h1432.h"
@@ -551,7 +552,8 @@ static int register_dvb(struct cx231xx_dvb *dvb,
 
 	/* register network adapter */
 	dvb_net_init(&dvb->adapter, &dvb->net, &dvb->demux.dmx);
-	result = dvb_create_media_graph(&dvb->adapter, false);
+	result = dvb_create_media_graph(&dvb->adapter,
+					dev->tuner_type == TUNER_ABSENT);
 	if (result < 0)
 		goto fail_create_graph;
 
@@ -801,6 +803,9 @@ static int dvb_init(struct cx231xx *dev)
 		/* attach tuner */
 		memset(&si2157_config, 0, sizeof(si2157_config));
 		si2157_config.fe = dev->dvb->frontend;
+#ifdef CONFIG_MEDIA_CONTROLLER_DVB
+		si2157_config.mdev = dev->media_dev;
+#endif
 		si2157_config.if_port = 1;
 		si2157_config.inversion = true;
 		strlcpy(info.type, "si2157", I2C_NAME_SIZE);
@@ -857,6 +862,9 @@ static int dvb_init(struct cx231xx *dev)
 		/* attach tuner */
 		memset(&si2157_config, 0, sizeof(si2157_config));
 		si2157_config.fe = dev->dvb->frontend;
+#ifdef CONFIG_MEDIA_CONTROLLER_DVB
+		si2157_config.mdev = dev->media_dev;
+#endif
 		si2157_config.if_port = 1;
 		si2157_config.inversion = true;
 		strlcpy(info.type, "si2157", I2C_NAME_SIZE);
diff --git a/drivers/media/usb/cx231xx/cx231xx-video.c b/drivers/media/usb/cx231xx/cx231xx-video.c
index 9b88cd8127ac..6414188ffdfa 100644
--- a/drivers/media/usb/cx231xx/cx231xx-video.c
+++ b/drivers/media/usb/cx231xx/cx231xx-video.c
@@ -1103,9 +1103,54 @@ static const char *iname[] = {
 	[CX231XX_VMUX_TELEVISION] = "Television",
 	[CX231XX_VMUX_CABLE]      = "Cable TV",
 	[CX231XX_VMUX_DVB]        = "DVB",
-	[CX231XX_VMUX_DEBUG]      = "for debug only",
 };
 
+void cx231xx_v4l2_create_entities(struct cx231xx *dev)
+{
+#if defined(CONFIG_MEDIA_CONTROLLER)
+	int ret, i;
+
+	/* Create entities for each input connector */
+	for (i = 0; i < MAX_CX231XX_INPUT; i++) {
+		struct media_entity *ent = &dev->input_ent[i];
+
+		if (!INPUT(i)->type)
+			break;
+
+		ent->name = iname[INPUT(i)->type];
+		ent->flags = MEDIA_ENT_FL_CONNECTOR;
+		dev->input_pad[i].flags = MEDIA_PAD_FL_SOURCE;
+
+		switch (INPUT(i)->type) {
+		case CX231XX_VMUX_COMPOSITE1:
+			ent->function = MEDIA_ENT_F_CONN_COMPOSITE;
+			break;
+		case CX231XX_VMUX_SVIDEO:
+			ent->function = MEDIA_ENT_F_CONN_SVIDEO;
+			break;
+		case CX231XX_VMUX_TELEVISION:
+		case CX231XX_VMUX_CABLE:
+		case CX231XX_VMUX_DVB:
+			/* The DVB core will handle it */
+			if (dev->tuner_type == TUNER_ABSENT)
+				continue;
+			/* fall though */
+		default: /* just to shut up a gcc warning */
+			ent->function = MEDIA_ENT_F_CONN_RF;
+			break;
+		}
+
+		ret = media_entity_pads_init(ent, 1, &dev->input_pad[i]);
+		if (ret < 0)
+			pr_err("failed to initialize input pad[%d]!\n", i);
+
+		ret = media_device_register_entity(dev->media_dev, ent);
+		if (ret < 0)
+			pr_err("failed to register input entity %d!\n", i);
+	}
+#endif
+}
+
 int cx231xx_enum_input(struct file *file, void *priv,
 			     struct v4l2_input *i)
 {
diff --git a/drivers/media/usb/cx231xx/cx231xx.h b/drivers/media/usb/cx231xx/cx231xx.h
index ec6d3f5bc36d..69f6d20870f5 100644
--- a/drivers/media/usb/cx231xx/cx231xx.h
+++ b/drivers/media/usb/cx231xx/cx231xx.h
@@ -281,7 +281,6 @@ enum cx231xx_itype {
 	CX231XX_VMUX_CABLE,
 	CX231XX_RADIO,
 	CX231XX_VMUX_DVB,
-	CX231XX_VMUX_DEBUG
 };
 
 enum cx231xx_v_input {
@@ -663,6 +662,8 @@ struct cx231xx {
 #if defined(CONFIG_MEDIA_CONTROLLER)
 	struct media_device *media_dev;
 	struct media_pad video_pad, vbi_pad;
+	struct media_entity input_ent[MAX_CX231XX_INPUT];
+	struct media_pad input_pad[MAX_CX231XX_INPUT];
 #endif
 
 	unsigned char eedata[256];
@@ -943,6 +944,7 @@ int cx231xx_register_extension(struct cx231xx_ops *dev);
 void cx231xx_unregister_extension(struct cx231xx_ops *dev);
 void cx231xx_init_extension(struct cx231xx *dev);
 void cx231xx_close_extension(struct cx231xx *dev);
+void cx231xx_v4l2_create_entities(struct cx231xx *dev);
 int cx231xx_querycap(struct file *file, void *priv,
 			   struct v4l2_capability *cap);
 int cx231xx_g_tuner(struct file *file, void *priv, struct v4l2_tuner *t);
diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c
index 6e02a15d39ce..2638e3251f2a 100644
--- a/drivers/media/usb/dvb-usb-v2/af9035.c
+++ b/drivers/media/usb/dvb-usb-v2/af9035.c
@@ -684,7 +684,7 @@ static int af9035_download_firmware(struct dvb_usb_device *d,
 	if (ret < 0)
 		goto err;
 
-	if (tmp == 1 || tmp == 3) {
+	if (tmp == 1 || tmp == 3 || tmp == 5) {
 		/* configure gpioh1, reset & power slave demod */
 		ret = af9035_wr_reg_mask(d, 0x00d8b0, 0x01, 0x01);
 		if (ret < 0)
@@ -823,7 +823,7 @@ static int af9035_read_config(struct dvb_usb_device *d)
 	if (ret < 0)
 		goto err;
 
-	if (tmp == 1 || tmp == 3)
+	if (tmp == 1 || tmp == 3 || tmp == 5)
 		state->dual_mode = true;
 
 	dev_dbg(&d->udev->dev, "%s: ts mode=%d dual mode=%d\n", __func__,
@@ -2053,6 +2053,8 @@ static const struct usb_device_id af9035_id_table[] = {
 		&af9035_props, "Avermedia A835B(3835)", RC_MAP_IT913X_V2) },
 	{ DVB_USB_DEVICE(USB_VID_AVERMEDIA, USB_PID_AVERMEDIA_A835B_4835,
 		&af9035_props, "Avermedia A835B(4835)",	RC_MAP_IT913X_V2) },
+	{ DVB_USB_DEVICE(USB_VID_AVERMEDIA, USB_PID_AVERMEDIA_TD110,
+		&af9035_props, "Avermedia AverTV Volar HD 2 (TD110)", RC_MAP_AVERMEDIA_RM_KS) },
 	{ DVB_USB_DEVICE(USB_VID_AVERMEDIA, USB_PID_AVERMEDIA_H335,
 		&af9035_props, "Avermedia H335", RC_MAP_IT913X_V2) },
 	{ DVB_USB_DEVICE(USB_VID_KWORLD_2, USB_PID_KWORLD_UB499_2T_T09,
diff --git a/drivers/media/usb/dvb-usb-v2/af9035.h b/drivers/media/usb/dvb-usb-v2/af9035.h
index 416a97f05ec8..df22001f9e41 100644
--- a/drivers/media/usb/dvb-usb-v2/af9035.h
+++ b/drivers/media/usb/dvb-usb-v2/af9035.h
@@ -112,9 +112,10 @@ static const u32 clock_lut_it9135[] = {
  * 0  TS
  * 1  DCA + PIP
  * 3  PIP
+ * 5  DCA + PIP
  * n  DCA
  *
- * Values 0 and 3 are seen to this day. 0 for single TS and 3 for dual TS.
+ * Values 0, 3 and 5 are seen to this day. 0 for single TS and 3/5 for dual TS.
  */
 
 #define EEPROM_BASE_AF9035        0x42fd
diff --git a/drivers/media/usb/dvb-usb-v2/dvb_usb.h b/drivers/media/usb/dvb-usb-v2/dvb_usb.h
index 023d91f7e654..35f27e2e4e28 100644
--- a/drivers/media/usb/dvb-usb-v2/dvb_usb.h
+++ b/drivers/media/usb/dvb-usb-v2/dvb_usb.h
@@ -1,7 +1,7 @@
 /*
  * DVB USB framework
  *
- * Copyright (C) 2004-6 Patrick Boettcher <patrick.boettcher@desy.de>
+ * Copyright (C) 2004-6 Patrick Boettcher <patrick.boettcher@posteo.de>
  * Copyright (C) 2012 Antti Palosaari <crope@iki.fi>
  *
  *    This program is free software; you can redistribute it and/or modify
diff --git a/drivers/media/usb/dvb-usb-v2/dvb_usb_common.h b/drivers/media/usb/dvb-usb-v2/dvb_usb_common.h
index 45f07090d431..a1622bda2a5e 100644
--- a/drivers/media/usb/dvb-usb-v2/dvb_usb_common.h
+++ b/drivers/media/usb/dvb-usb-v2/dvb_usb_common.h
@@ -1,7 +1,7 @@
 /*
  * DVB USB framework
  *
- * Copyright (C) 2004-6 Patrick Boettcher <patrick.boettcher@desy.de>
+ * Copyright (C) 2004-6 Patrick Boettcher <patrick.boettcher@posteo.de>
  * Copyright (C) 2012 Antti Palosaari <crope@iki.fi>
  *
  *    This program is free software; you can redistribute it and/or modify
diff --git a/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c b/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c
index f0565bf3673e..3fbb2cd19f5e 100644
--- a/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c
+++ b/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c
@@ -1,7 +1,7 @@
 /*
  * DVB USB framework
  *
- * Copyright (C) 2004-6 Patrick Boettcher <patrick.boettcher@desy.de>
+ * Copyright (C) 2004-6 Patrick Boettcher <patrick.boettcher@posteo.de>
  * Copyright (C) 2012 Antti Palosaari <crope@iki.fi>
  *
  *    This program is free software; you can redistribute it and/or modify
@@ -20,6 +20,7 @@
  */
 
 #include "dvb_usb_common.h"
+#include <media/media-device.h>
 
 static int dvb_usbv2_disable_rc_polling;
 module_param_named(disable_rc_polling, dvb_usbv2_disable_rc_polling, int, 0644);
@@ -411,15 +412,7 @@ static int dvb_usbv2_media_device_init(struct dvb_usb_adapter *adap)
 	if (!mdev)
 		return -ENOMEM;
 
-	mdev->dev = &udev->dev;
-	strlcpy(mdev->model, d->name, sizeof(mdev->model));
-	if (udev->serial)
-		strlcpy(mdev->serial, udev->serial, sizeof(mdev->serial));
-	strcpy(mdev->bus_info, udev->devpath);
-	mdev->hw_revision = le16_to_cpu(udev->descriptor.bcdDevice);
-	mdev->driver_version = LINUX_VERSION_CODE;
-
-	media_device_init(mdev);
+	media_device_usb_init(mdev, udev, d->name);
 
 	dvb_register_media_controller(&adap->dvb_adap, mdev);
 
@@ -1129,7 +1122,7 @@ int dvb_usbv2_reset_resume(struct usb_interface *intf)
 EXPORT_SYMBOL(dvb_usbv2_reset_resume);
 
 MODULE_VERSION("2.0");
-MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@desy.de>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_AUTHOR("Antti Palosaari <crope@iki.fi>");
 MODULE_DESCRIPTION("DVB USB common");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/usb/dvb-usb-v2/dvb_usb_urb.c b/drivers/media/usb/dvb-usb-v2/dvb_usb_urb.c
index 22bdce15ecf3..5bafeb6486be 100644
--- a/drivers/media/usb/dvb-usb-v2/dvb_usb_urb.c
+++ b/drivers/media/usb/dvb-usb-v2/dvb_usb_urb.c
@@ -1,7 +1,7 @@
 /*
  * DVB USB framework
  *
- * Copyright (C) 2004-6 Patrick Boettcher <patrick.boettcher@desy.de>
+ * Copyright (C) 2004-6 Patrick Boettcher <patrick.boettcher@posteo.de>
  * Copyright (C) 2012 Antti Palosaari <crope@iki.fi>
  *
  *    This program is free software; you can redistribute it and/or modify
diff --git a/drivers/media/usb/dvb-usb-v2/dvbsky.c b/drivers/media/usb/dvb-usb-v2/dvbsky.c
index 1dd962535f97..02dbc6c45423 100644
--- a/drivers/media/usb/dvb-usb-v2/dvbsky.c
+++ b/drivers/media/usb/dvb-usb-v2/dvbsky.c
@@ -847,10 +847,17 @@ static const struct usb_device_id dvbsky_id_table[] = {
 		USB_PID_TECHNOTREND_CONNECT_CT2_4650_CI,
 		&dvbsky_t680c_props, "TechnoTrend TT-connect CT2-4650 CI",
 		RC_MAP_TT_1500) },
+	{ DVB_USB_DEVICE(USB_VID_TECHNOTREND,
+		USB_PID_TECHNOTREND_CONNECT_CT2_4650_CI_2,
+		&dvbsky_t680c_props, "TechnoTrend TT-connect CT2-4650 CI v1.1",
+		RC_MAP_TT_1500) },
 	{ DVB_USB_DEVICE(USB_VID_TERRATEC,
 		USB_PID_TERRATEC_H7_3,
 		&dvbsky_t680c_props, "Terratec H7 Rev.4",
 		RC_MAP_TT_1500) },
+	{ DVB_USB_DEVICE(USB_VID_TERRATEC, USB_PID_TERRATEC_CINERGY_S2_R4,
+		&dvbsky_s960_props, "Terratec Cinergy S2 Rev.4",
+		RC_MAP_DVBSKY) },
 	{ }
 };
 MODULE_DEVICE_TABLE(usb, dvbsky_id_table);
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c
index 84f6de6fa07d..047a32fe43ea 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c
@@ -507,9 +507,9 @@ static int mxl111sf_demod_read_signal_strength(struct dvb_frontend *fe,
 	return 0;
 }
 
-static int mxl111sf_demod_get_frontend(struct dvb_frontend *fe)
+static int mxl111sf_demod_get_frontend(struct dvb_frontend *fe,
+				       struct dtv_frontend_properties *p)
 {
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct mxl111sf_demod_state *state = fe->demodulator_priv;
 
 	mxl_dbg("()");
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c
index 444579be0b77..7d16252dbb71 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c
@@ -36,7 +36,7 @@ MODULE_PARM_DESC(debug, "set debugging level (1=info (or-able)).");
 struct mxl111sf_tuner_state {
 	struct mxl111sf_state *mxl_state;
 
-	struct mxl111sf_tuner_config *cfg;
+	const struct mxl111sf_tuner_config *cfg;
 
 	enum mxl_if_freq if_freq;
 
@@ -489,8 +489,8 @@ static struct dvb_tuner_ops mxl111sf_tuner_tuner_ops = {
 };
 
 struct dvb_frontend *mxl111sf_tuner_attach(struct dvb_frontend *fe,
-					   struct mxl111sf_state *mxl_state,
-					   struct mxl111sf_tuner_config *cfg)
+				struct mxl111sf_state *mxl_state,
+				const struct mxl111sf_tuner_config *cfg)
 {
 	struct mxl111sf_tuner_state *state = NULL;
 
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h
index e6caab21a197..509b55071218 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h
@@ -63,13 +63,13 @@ struct mxl111sf_tuner_config {
 #if IS_ENABLED(CONFIG_DVB_USB_MXL111SF)
 extern
 struct dvb_frontend *mxl111sf_tuner_attach(struct dvb_frontend *fe,
-					   struct mxl111sf_state *mxl_state,
-					   struct mxl111sf_tuner_config *cfg);
+				struct mxl111sf_state *mxl_state,
+				const struct mxl111sf_tuner_config *cfg);
 #else
 static inline
 struct dvb_frontend *mxl111sf_tuner_attach(struct dvb_frontend *fe,
-					   struct mxl111sf_state *mxl_state,
-					   struct mxl111sf_tuner_config *cfg)
+				struct mxl111sf_state *mxl_state,
+				const struct mxl111sf_tuner_config *cfg)
 {
 	printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__);
 	return NULL;
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf.c b/drivers/media/usb/dvb-usb-v2/mxl111sf.c
index b669deccc34c..5d676b533a3a 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf.c
@@ -856,7 +856,7 @@ static int mxl111sf_ant_hunt(struct dvb_frontend *fe)
 	return 0;
 }
 
-static struct mxl111sf_tuner_config mxl_tuner_config = {
+static const struct mxl111sf_tuner_config mxl_tuner_config = {
 	.if_freq         = MXL_IF_6_0, /* applies to external IF output, only */
 	.invert_spectrum = 0,
 	.read_reg        = mxl111sf_read_reg,
@@ -888,7 +888,7 @@ static int mxl111sf_attach_tuner(struct dvb_usb_adapter *adap)
 	state->tuner.function = MEDIA_ENT_F_TUNER;
 	state->tuner.name = "mxl111sf tuner";
 	state->tuner_pads[TUNER_PAD_RF_INPUT].flags = MEDIA_PAD_FL_SINK;
-	state->tuner_pads[TUNER_PAD_IF_OUTPUT].flags = MEDIA_PAD_FL_SOURCE;
+	state->tuner_pads[TUNER_PAD_OUTPUT].flags = MEDIA_PAD_FL_SOURCE;
 
 	ret = media_entity_pads_init(&state->tuner,
 				     TUNER_NUM_PADS, state->tuner_pads);
diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
index eb5787a3191e..fa72642d41f3 100644
--- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
+++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
@@ -259,6 +259,10 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 		ret = -EOPNOTSUPP;
 	}
 
+	/* Retry failed I2C messages */
+	if (ret == -EPIPE)
+		ret = -EAGAIN;
+
 err_mutex_unlock:
 	mutex_unlock(&d->i2c_mutex);
 
@@ -619,6 +623,10 @@ static int rtl28xxu_identify_state(struct dvb_usb_device *d, const char **name)
 	}
 	dev_dbg(&d->intf->dev, "chip_id=%u\n", dev->chip_id);
 
+	/* Retry failed I2C messages */
+	d->i2c_adap.retries = 1;
+	d->i2c_adap.timeout = msecs_to_jiffies(10);
+
 	return WARM;
 err:
 	dev_dbg(&d->intf->dev, "failed=%d\n", ret);
@@ -1563,19 +1571,19 @@ static int rtl28xxu_frontend_ctrl(struct dvb_frontend *fe, int onoff)
 	if (dev->chip_id == CHIP_ID_RTL2831U)
 		return 0;
 
-	/* control internal demod ADC */
-	if (fe->id == 0 && onoff)
-		val = 0x48; /* enable ADC */
-	else
-		val = 0x00; /* disable ADC */
-
-	ret = rtl28xxu_wr_reg_mask(d, SYS_DEMOD_CTL, val, 0x48);
-	if (ret)
-		goto err;
+	if (fe->id == 0) {
+		/* control internal demod ADC */
+		if (onoff)
+			val = 0x48; /* enable ADC */
+		else
+			val = 0x00; /* disable ADC */
 
-	/* bypass slave demod TS through master demod */
-	if (fe->id == 1 && onoff) {
-		ret = pdata->enable_slave_ts(dev->i2c_client_demod);
+		ret = rtl28xxu_wr_reg_mask(d, SYS_DEMOD_CTL, val, 0x48);
+		if (ret)
+			goto err;
+	} else if (fe->id == 1) {
+		/* bypass slave demod TS through master demod */
+		ret = pdata->slave_ts_ctrl(dev->i2c_client_demod, onoff);
 		if (ret)
 			goto err;
 	}
diff --git a/drivers/media/usb/dvb-usb-v2/usb_urb.c b/drivers/media/usb/dvb-usb-v2/usb_urb.c
index ca8f3c2b1082..55136cde38f5 100644
--- a/drivers/media/usb/dvb-usb-v2/usb_urb.c
+++ b/drivers/media/usb/dvb-usb-v2/usb_urb.c
@@ -1,6 +1,6 @@
 /* usb-urb.c is part of the DVB USB library.
  *
- * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@posteo.de)
  * see dvb-usb-init.c for copyright information.
  *
  * This file keeps functions for initializing and handling the
diff --git a/drivers/media/usb/dvb-usb/a800.c b/drivers/media/usb/dvb-usb/a800.c
index 83684ed023cd..7ba975bea96a 100644
--- a/drivers/media/usb/dvb-usb/a800.c
+++ b/drivers/media/usb/dvb-usb/a800.c
@@ -1,7 +1,7 @@
 /* DVB USB framework compliant Linux driver for the AVerMedia AverTV DVB-T
  * USB2.0 (A800) DVB-T receiver.
  *
- * Copyright (C) 2005 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2005 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  * Thanks to
  *   - AVerMedia who kindly provided information and
@@ -185,7 +185,7 @@ static struct usb_driver a800_driver = {
 
 module_usb_driver(a800_driver);
 
-MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@desy.de>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("AVerMedia AverTV DVB-T USB 2.0 (A800)");
 MODULE_VERSION("1.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/usb/dvb-usb/af9005-fe.c b/drivers/media/usb/dvb-usb/af9005-fe.c
index ac97075d75f7..09db3d02bd82 100644
--- a/drivers/media/usb/dvb-usb/af9005-fe.c
+++ b/drivers/media/usb/dvb-usb/af9005-fe.c
@@ -1227,9 +1227,9 @@ static int af9005_fe_set_frontend(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int af9005_fe_get_frontend(struct dvb_frontend *fe)
+static int af9005_fe_get_frontend(struct dvb_frontend *fe,
+				  struct dtv_frontend_properties *fep)
 {
-	struct dtv_frontend_properties *fep = &fe->dtv_property_cache;
 	struct af9005_fe_state *state = fe->demodulator_priv;
 	int ret;
 	u8 temp;
diff --git a/drivers/media/usb/dvb-usb/cxusb.c b/drivers/media/usb/dvb-usb/cxusb.c
index ab7151181728..907ac01ae297 100644
--- a/drivers/media/usb/dvb-usb/cxusb.c
+++ b/drivers/media/usb/dvb-usb/cxusb.c
@@ -13,7 +13,7 @@
  *
  * TODO: Use the cx25840-driver for the analogue part
  *
- * Copyright (C) 2005 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2005 Patrick Boettcher (patrick.boettcher@posteo.de)
  * Copyright (C) 2006 Michael Krufky (mkrufky@linuxtv.org)
  * Copyright (C) 2006, 2007 Chris Pascoe (c.pascoe@itee.uq.edu.au)
  *
@@ -2314,7 +2314,7 @@ static struct usb_driver cxusb_driver = {
 
 module_usb_driver(cxusb_driver);
 
-MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@desy.de>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_AUTHOR("Michael Krufky <mkrufky@linuxtv.org>");
 MODULE_AUTHOR("Chris Pascoe <c.pascoe@itee.uq.edu.au>");
 MODULE_DESCRIPTION("Driver for Conexant USB2.0 hybrid reference design");
diff --git a/drivers/media/usb/dvb-usb/dib0700_core.c b/drivers/media/usb/dvb-usb/dib0700_core.c
index 0d248ce02a9b..c16f999b9d7c 100644
--- a/drivers/media/usb/dvb-usb/dib0700_core.c
+++ b/drivers/media/usb/dvb-usb/dib0700_core.c
@@ -881,7 +881,7 @@ static struct usb_driver dib0700_driver = {
 module_usb_driver(dib0700_driver);
 
 MODULE_FIRMWARE("dvb-usb-dib0700-1.20.fw");
-MODULE_AUTHOR("Patrick Boettcher <pboettcher@dibcom.fr>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("Driver for devices based on DiBcom DiB0700 - USB bridge");
 MODULE_VERSION("1.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/usb/dvb-usb/dib0700_devices.c b/drivers/media/usb/dvb-usb/dib0700_devices.c
index 7ed49646a699..ea0391e32d23 100644
--- a/drivers/media/usb/dvb-usb/dib0700_devices.c
+++ b/drivers/media/usb/dvb-usb/dib0700_devices.c
@@ -1736,8 +1736,13 @@ static int dib809x_tuner_attach(struct dvb_usb_adapter *adap)
 	struct dib0700_adapter_state *st = adap->priv;
 	struct i2c_adapter *tun_i2c = st->dib8000_ops.get_i2c_master(adap->fe_adap[0].fe, DIBX000_I2C_INTERFACE_TUNER, 1);
 
-	if (dvb_attach(dib0090_register, adap->fe_adap[0].fe, tun_i2c, &dib809x_dib0090_config) == NULL)
-		return -ENODEV;
+	if (adap->id == 0) {
+		if (dvb_attach(dib0090_register, adap->fe_adap[0].fe, tun_i2c, &dib809x_dib0090_config) == NULL)
+			return -ENODEV;
+	} else {
+		if (dvb_attach(dib0090_register, adap->fe_adap[0].fe, tun_i2c, &dib809x_dib0090_config) == NULL)
+			return -ENODEV;
+	}
 
 	st->set_param_save = adap->fe_adap[0].fe->ops.tuner_ops.set_params;
 	adap->fe_adap[0].fe->ops.tuner_ops.set_params = dib8096_set_param_override;
@@ -1773,6 +1778,20 @@ static int stk809x_frontend_attach(struct dvb_usb_adapter *adap)
 	return adap->fe_adap[0].fe == NULL ?  -ENODEV : 0;
 }
 
+static int stk809x_frontend1_attach(struct dvb_usb_adapter *adap)
+{
+	struct dib0700_adapter_state *state = adap->priv;
+
+	if (!dvb_attach(dib8000_attach, &state->dib8000_ops))
+		return -ENODEV;
+
+	state->dib8000_ops.i2c_enumeration(&adap->dev->i2c_adap, 1, 0x10, 0x82, 0);
+
+	adap->fe_adap[0].fe = state->dib8000_ops.init(&adap->dev->i2c_adap, 0x82, &dib809x_dib8000_config[1]);
+
+	return adap->fe_adap[0].fe == NULL ?  -ENODEV : 0;
+}
+
 static int nim8096md_tuner_attach(struct dvb_usb_adapter *adap)
 {
 	struct dib0700_adapter_state *st = adap->priv;
@@ -3794,6 +3813,7 @@ struct usb_device_id dib0700_usb_id_table[] = {
 /* 80 */{ USB_DEVICE(USB_VID_ELGATO,	USB_PID_ELGATO_EYETV_DTT_2) },
 	{ USB_DEVICE(USB_VID_PCTV,      USB_PID_PCTV_2002E) },
 	{ USB_DEVICE(USB_VID_PCTV,      USB_PID_PCTV_2002E_SE) },
+	{ USB_DEVICE(USB_VID_PCTV,      USB_PID_DIBCOM_STK8096PVR) },
 	{ 0 }		/* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, dib0700_usb_id_table);
@@ -4959,6 +4979,59 @@ struct dvb_usb_device_properties dib0700_devices[] = {
 					    RC_BIT_NEC,
 			.change_protocol  = dib0700_change_protocol,
 		},
+	}, { DIB0700_DEFAULT_DEVICE_PROPERTIES,
+		.num_adapters = 2,
+		.adapter = {
+			{
+				.num_frontends = 1,
+				.fe = {{
+					.caps  = DVB_USB_ADAP_HAS_PID_FILTER |
+						DVB_USB_ADAP_PID_FILTER_CAN_BE_TURNED_OFF,
+					.pid_filter_count = 32,
+					.pid_filter = stk80xx_pid_filter,
+					.pid_filter_ctrl = stk80xx_pid_filter_ctrl,
+					.frontend_attach  = stk809x_frontend_attach,
+					.tuner_attach     = dib809x_tuner_attach,
+
+					DIB0700_DEFAULT_STREAMING_CONFIG(0x02),
+				} },
+				.size_of_priv =
+					sizeof(struct dib0700_adapter_state),
+			}, {
+				.num_frontends = 1,
+				.fe = { {
+					.caps  = DVB_USB_ADAP_HAS_PID_FILTER |
+						DVB_USB_ADAP_PID_FILTER_CAN_BE_TURNED_OFF,
+					.pid_filter_count = 32,
+					.pid_filter = stk80xx_pid_filter,
+					.pid_filter_ctrl = stk80xx_pid_filter_ctrl,
+					.frontend_attach  = stk809x_frontend1_attach,
+					.tuner_attach     = dib809x_tuner_attach,
+
+					DIB0700_DEFAULT_STREAMING_CONFIG(0x03),
+				} },
+				.size_of_priv =
+					sizeof(struct dib0700_adapter_state),
+			},
+		},
+		.num_device_descs = 1,
+		.devices = {
+			{   "DiBcom STK8096-PVR reference design",
+				{ &dib0700_usb_id_table[83], NULL },
+				{ NULL },
+			},
+		},
+
+		.rc.core = {
+			.rc_interval      = DEFAULT_RC_INTERVAL,
+			.rc_codes         = RC_MAP_DIB0700_RC5_TABLE,
+			.module_name  = "dib0700",
+			.rc_query         = dib0700_rc_query_old_firmware,
+			.allowed_protos   = RC_BIT_RC5 |
+				RC_BIT_RC6_MCE |
+				RC_BIT_NEC,
+			.change_protocol  = dib0700_change_protocol,
+		},
 	},
 };
 
diff --git a/drivers/media/usb/dvb-usb/dibusb-common.c b/drivers/media/usb/dvb-usb/dibusb-common.c
index ef3a8f75f82e..35de6095926d 100644
--- a/drivers/media/usb/dvb-usb/dibusb-common.c
+++ b/drivers/media/usb/dvb-usb/dibusb-common.c
@@ -1,6 +1,6 @@
 /* Common methods for dibusb-based-receivers.
  *
- * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  *	This program is free software; you can redistribute it and/or modify it
  *	under the terms of the GNU General Public License as published by the Free
diff --git a/drivers/media/usb/dvb-usb/dibusb-mb.c b/drivers/media/usb/dvb-usb/dibusb-mb.c
index a4ac37e0e98b..a0057641cc86 100644
--- a/drivers/media/usb/dvb-usb/dibusb-mb.c
+++ b/drivers/media/usb/dvb-usb/dibusb-mb.c
@@ -1,10 +1,10 @@
 /* DVB USB compliant linux driver for mobile DVB-T USB devices based on
  * reference designs made by DiBcom (http://www.dibcom.fr/) (DiB3000M-B)
  *
- * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  * based on GPL code from DiBcom, which has
- * Copyright (C) 2004 Amaury Demol for DiBcom (ademol@dibcom.fr)
+ * Copyright (C) 2004 Amaury Demol for DiBcom
  *
  *	This program is free software; you can redistribute it and/or modify it
  *	under the terms of the GNU General Public License as published by the Free
@@ -465,7 +465,7 @@ static struct usb_driver dibusb_driver = {
 
 module_usb_driver(dibusb_driver);
 
-MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@desy.de>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("Driver for DiBcom USB DVB-T devices (DiB3000M-B based)");
 MODULE_VERSION("1.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/usb/dvb-usb/dibusb-mc.c b/drivers/media/usb/dvb-usb/dibusb-mc.c
index 9d1a59d09c52..08fb8a3f6e0c 100644
--- a/drivers/media/usb/dvb-usb/dibusb-mc.c
+++ b/drivers/media/usb/dvb-usb/dibusb-mc.c
@@ -1,10 +1,10 @@
 /* DVB USB compliant linux driver for mobile DVB-T USB devices based on
  * reference designs made by DiBcom (http://www.dibcom.fr/) (DiB3000M-C/P)
  *
- * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  * based on GPL code from DiBcom, which has
- * Copyright (C) 2004 Amaury Demol for DiBcom (ademol@dibcom.fr)
+ * Copyright (C) 2004 Amaury Demol for DiBcom
  *
  *	This program is free software; you can redistribute it and/or modify it
  *	under the terms of the GNU General Public License as published by the Free
@@ -143,7 +143,7 @@ static struct usb_driver dibusb_mc_driver = {
 
 module_usb_driver(dibusb_mc_driver);
 
-MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@desy.de>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("Driver for DiBcom USB2.0 DVB-T (DiB3000M-C/P based) devices");
 MODULE_VERSION("1.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/usb/dvb-usb/dibusb.h b/drivers/media/usb/dvb-usb/dibusb.h
index 32ab1392313f..3f82163d8ab8 100644
--- a/drivers/media/usb/dvb-usb/dibusb.h
+++ b/drivers/media/usb/dvb-usb/dibusb.h
@@ -1,6 +1,6 @@
 /* Header file for all dibusb-based-receivers.
  *
- * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  *	This program is free software; you can redistribute it and/or modify it
  *	under the terms of the GNU General Public License as published by the Free
diff --git a/drivers/media/usb/dvb-usb/digitv.c b/drivers/media/usb/dvb-usb/digitv.c
index 772bde3c5020..63134335c994 100644
--- a/drivers/media/usb/dvb-usb/digitv.c
+++ b/drivers/media/usb/dvb-usb/digitv.c
@@ -1,7 +1,7 @@
 /* DVB USB compliant linux driver for Nebula Electronics uDigiTV DVB-T USB2.0
  * receiver
  *
- * Copyright (C) 2005 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2005 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  * partly based on the SDK published by Nebula Electronics
  *
@@ -348,7 +348,7 @@ static struct usb_driver digitv_driver = {
 
 module_usb_driver(digitv_driver);
 
-MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@desy.de>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("Driver for Nebula Electronics uDigiTV DVB-T USB2.0");
 MODULE_VERSION("1.0-alpha");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/usb/dvb-usb/dtt200u-fe.c b/drivers/media/usb/dvb-usb/dtt200u-fe.c
index 8637ad1be6be..c09332bd99cb 100644
--- a/drivers/media/usb/dvb-usb/dtt200u-fe.c
+++ b/drivers/media/usb/dvb-usb/dtt200u-fe.c
@@ -1,7 +1,7 @@
 /* Frontend part of the Linux driver for the WideView/ Yakumo/ Hama/
  * Typhoon/ Yuan DVB-T USB2.0 receiver.
  *
- * Copyright (C) 2005 Patrick Boettcher <patrick.boettcher@desy.de>
+ * Copyright (C) 2005 Patrick Boettcher <patrick.boettcher@posteo.de>
  *
  *	This program is free software; you can redistribute it and/or modify it
  *	under the terms of the GNU General Public License as published by the Free
@@ -140,10 +140,11 @@ static int dtt200u_fe_set_frontend(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int dtt200u_fe_get_frontend(struct dvb_frontend* fe)
+static int dtt200u_fe_get_frontend(struct dvb_frontend* fe,
+				   struct dtv_frontend_properties *fep)
 {
-	struct dtv_frontend_properties *fep = &fe->dtv_property_cache;
 	struct dtt200u_fe_state *state = fe->demodulator_priv;
+
 	memcpy(fep, &state->fep, sizeof(struct dtv_frontend_properties));
 	return 0;
 }
diff --git a/drivers/media/usb/dvb-usb/dtt200u.c b/drivers/media/usb/dvb-usb/dtt200u.c
index c357fb3b0a88..ca3b69aa9688 100644
--- a/drivers/media/usb/dvb-usb/dtt200u.c
+++ b/drivers/media/usb/dvb-usb/dtt200u.c
@@ -1,7 +1,7 @@
 /* DVB USB library compliant Linux driver for the WideView/ Yakumo/ Hama/
  * Typhoon/ Yuan/ Miglia DVB-T USB2.0 receiver.
  *
- * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  * Thanks to Steve Chang from WideView for providing support for the WT-220U.
  *
@@ -362,7 +362,7 @@ static struct usb_driver dtt200u_usb_driver = {
 
 module_usb_driver(dtt200u_usb_driver);
 
-MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@desy.de>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("Driver for the WideView/Yakumo/Hama/Typhoon/Club3D/Miglia DVB-T USB2.0 devices");
 MODULE_VERSION("1.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/usb/dvb-usb/dtt200u.h b/drivers/media/usb/dvb-usb/dtt200u.h
index 005b0a7df358..efccc399b1cb 100644
--- a/drivers/media/usb/dvb-usb/dtt200u.h
+++ b/drivers/media/usb/dvb-usb/dtt200u.h
@@ -1,7 +1,7 @@
 /* Common header file of Linux driver for the WideView/ Yakumo/ Hama/
  * Typhoon/ Yuan DVB-T USB2.0 receiver.
  *
- * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  *	This program is free software; you can redistribute it and/or modify it
  *	under the terms of the GNU General Public License as published by the Free
diff --git a/drivers/media/usb/dvb-usb/dvb-usb-common.h b/drivers/media/usb/dvb-usb/dvb-usb-common.h
index 6b7b2a89242e..7e619d638809 100644
--- a/drivers/media/usb/dvb-usb/dvb-usb-common.h
+++ b/drivers/media/usb/dvb-usb/dvb-usb-common.h
@@ -1,6 +1,6 @@
 /* dvb-usb-common.h is part of the DVB USB library.
  *
- * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@posteo.de)
  * see dvb-usb-init.c for copyright information.
  *
  * a header file containing prototypes and types for internal use of the dvb-usb-lib
diff --git a/drivers/media/usb/dvb-usb/dvb-usb-dvb.c b/drivers/media/usb/dvb-usb/dvb-usb-dvb.c
index 9ddfcab268be..6477b04e95c7 100644
--- a/drivers/media/usb/dvb-usb/dvb-usb-dvb.c
+++ b/drivers/media/usb/dvb-usb/dvb-usb-dvb.c
@@ -1,12 +1,13 @@
 /* dvb-usb-dvb.c is part of the DVB USB library.
  *
- * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@posteo.de)
  * see dvb-usb-init.c for copyright information.
  *
  * This file contains functions for initializing and handling the
  * linux-dvb API.
  */
 #include "dvb-usb-common.h"
+#include <media/media-device.h>
 
 /* does the complete input transfer handling */
 static int dvb_usb_ctrl_feed(struct dvb_demux_feed *dvbdmxfeed, int onoff)
@@ -106,15 +107,7 @@ static int dvb_usb_media_device_init(struct dvb_usb_adapter *adap)
 	if (!mdev)
 		return -ENOMEM;
 
-	mdev->dev = &udev->dev;
-	strlcpy(mdev->model, d->desc->name, sizeof(mdev->model));
-	if (udev->serial)
-		strlcpy(mdev->serial, udev->serial, sizeof(mdev->serial));
-	strcpy(mdev->bus_info, udev->devpath);
-	mdev->hw_revision = le16_to_cpu(udev->descriptor.bcdDevice);
-	mdev->driver_version = LINUX_VERSION_CODE;
-
-	media_device_init(mdev);
+	media_device_usb_init(mdev, udev, d->desc->name);
 
 	dvb_register_media_controller(&adap->dvb_adap, mdev);
 
diff --git a/drivers/media/usb/dvb-usb/dvb-usb-firmware.c b/drivers/media/usb/dvb-usb/dvb-usb-firmware.c
index 733a7ff7b207..dd048a7c461c 100644
--- a/drivers/media/usb/dvb-usb/dvb-usb-firmware.c
+++ b/drivers/media/usb/dvb-usb/dvb-usb-firmware.c
@@ -1,6 +1,6 @@
 /* dvb-usb-firmware.c is part of the DVB USB library.
  *
- * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@posteo.de)
  * see dvb-usb-init.c for copyright information.
  *
  * This file contains functions for downloading the firmware to Cypress FX 1 and 2 based devices.
diff --git a/drivers/media/usb/dvb-usb/dvb-usb-i2c.c b/drivers/media/usb/dvb-usb/dvb-usb-i2c.c
index 88e4a62abc44..4f0b0adce7f5 100644
--- a/drivers/media/usb/dvb-usb/dvb-usb-i2c.c
+++ b/drivers/media/usb/dvb-usb/dvb-usb-i2c.c
@@ -1,6 +1,6 @@
 /* dvb-usb-i2c.c is part of the DVB USB library.
  *
- * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@posteo.de)
  * see dvb-usb-init.c for copyright information.
  *
  * This file contains functions for (de-)initializing an I2C adapter.
diff --git a/drivers/media/usb/dvb-usb/dvb-usb-init.c b/drivers/media/usb/dvb-usb/dvb-usb-init.c
index 1adf325012f7..3896ba9a4179 100644
--- a/drivers/media/usb/dvb-usb/dvb-usb-init.c
+++ b/drivers/media/usb/dvb-usb/dvb-usb-init.c
@@ -3,7 +3,7 @@
  *
  * dvb-usb-init.c
  *
- * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  *	This program is free software; you can redistribute it and/or modify it
  *	under the terms of the GNU General Public License as published by the Free
@@ -299,6 +299,6 @@ void dvb_usb_device_exit(struct usb_interface *intf)
 EXPORT_SYMBOL(dvb_usb_device_exit);
 
 MODULE_VERSION("1.0");
-MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@desy.de>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("A library module containing commonly used USB and DVB function USB DVB devices");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/usb/dvb-usb/dvb-usb-remote.c b/drivers/media/usb/dvb-usb/dvb-usb-remote.c
index 7b5dae3077f6..c259f9e43542 100644
--- a/drivers/media/usb/dvb-usb/dvb-usb-remote.c
+++ b/drivers/media/usb/dvb-usb/dvb-usb-remote.c
@@ -1,6 +1,6 @@
 /* dvb-usb-remote.c is part of the DVB USB library.
  *
- * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@posteo.de)
  * see dvb-usb-init.c for copyright information.
  *
  * This file contains functions for initializing the input-device and for handling remote-control-queries.
diff --git a/drivers/media/usb/dvb-usb/dvb-usb-urb.c b/drivers/media/usb/dvb-usb/dvb-usb-urb.c
index 5c8f651344fc..95f9097498cb 100644
--- a/drivers/media/usb/dvb-usb/dvb-usb-urb.c
+++ b/drivers/media/usb/dvb-usb/dvb-usb-urb.c
@@ -1,6 +1,6 @@
 /* dvb-usb-urb.c is part of the DVB USB library.
  *
- * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@posteo.de)
  * see dvb-usb-init.c for copyright information.
  *
  * This file keeps functions for initializing and handling the
diff --git a/drivers/media/usb/dvb-usb/dvb-usb.h b/drivers/media/usb/dvb-usb/dvb-usb.h
index ce4c4e3b58bb..639c4678c65b 100644
--- a/drivers/media/usb/dvb-usb/dvb-usb.h
+++ b/drivers/media/usb/dvb-usb/dvb-usb.h
@@ -1,6 +1,6 @@
 /* dvb-usb.h is part of the DVB USB library.
  *
- * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@posteo.de)
  * see dvb-usb-init.c for copyright information.
  *
  * the headerfile, all dvb-usb-drivers have to include.
diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c
index 14ef25dc6cd3..6d0dd859d684 100644
--- a/drivers/media/usb/dvb-usb/dw2102.c
+++ b/drivers/media/usb/dvb-usb/dw2102.c
@@ -1,9 +1,10 @@
 /* DVB USB framework compliant Linux driver for the
  *	DVBWorld DVB-S 2101, 2102, DVB-S2 2104, DVB-C 3101,
- *	TeVii S600, S630, S650, S660, S480, S421, S632
+ *	TeVii S421, S480, S482, S600, S630, S632, S650, S660, S662,
  *	Prof 1100, 7500,
  *	Geniatech SU3000, T220,
- *	TechnoTrend S2-4600 Cards
+ *	TechnoTrend S2-4600,
+ *	Terratec Cinergy S2 cards
  * Copyright (C) 2008-2012 Igor M. Liplianin (liplianin@me.by)
  *
  *	This program is free software; you can redistribute it and/or modify it
@@ -33,7 +34,6 @@
 #include "tda18271.h"
 #include "cxd2820r.h"
 #include "m88ds3103.h"
-#include "ts2020.h"
 
 /* Max transfer size done by I2C transfer functions */
 #define MAX_XFER_SIZE  64
@@ -66,6 +66,10 @@
 #define USB_PID_TEVII_S660 0xd660
 #endif
 
+#ifndef USB_PID_TEVII_S662
+#define USB_PID_TEVII_S662 0xd662
+#endif
+
 #ifndef USB_PID_TEVII_S480_1
 #define USB_PID_TEVII_S480_1 0xd481
 #endif
@@ -118,6 +122,7 @@
 struct dw2102_state {
 	u8 initialized;
 	u8 last_lock;
+	struct i2c_client *i2c_client_demod;
 	struct i2c_client *i2c_client_tuner;
 
 	/* fe hook functions*/
@@ -1141,22 +1146,6 @@ static struct tda18271_config tda18271_config = {
 	.gate = TDA18271_GATE_DIGITAL,
 };
 
-static const struct m88ds3103_config tt_s2_4600_m88ds3103_config = {
-	.i2c_addr = 0x68,
-	.clock = 27000000,
-	.i2c_wr_max = 33,
-	.ts_mode = M88DS3103_TS_CI,
-	.ts_clk = 16000,
-	.ts_clk_pol = 0,
-	.spec_inv = 0,
-	.agc_inv = 0,
-	.clock_out = M88DS3103_CLOCK_OUT_ENABLED,
-	.envelope_mode = 0,
-	.agc = 0x99,
-	.lnb_hv_pol = 1,
-	.lnb_en_pol = 0,
-};
-
 static u8 m88rs2000_inittab[] = {
 	DEMOD_WRITE, 0x9a, 0x30,
 	DEMOD_WRITE, 0x00, 0x01,
@@ -1509,7 +1498,8 @@ static int tt_s2_4600_frontend_attach(struct dvb_usb_adapter *adap)
 	u8 ibuf[] = { 0 };
 	struct i2c_adapter *i2c_adapter;
 	struct i2c_client *client;
-	struct i2c_board_info info;
+	struct i2c_board_info board_info;
+	struct m88ds3103_platform_data m88ds3103_pdata = {};
 	struct ts2020_config ts2020_config = {};
 
 	if (dvb_usb_generic_rw(d, obuf, 3, ibuf, 1, 0) < 0)
@@ -1542,22 +1532,44 @@ static int tt_s2_4600_frontend_attach(struct dvb_usb_adapter *adap)
 	if (dvb_usb_generic_rw(d, obuf, 1, ibuf, 1, 0) < 0)
 		err("command 0x51 transfer failed.");
 
-	memset(&info, 0, sizeof(struct i2c_board_info));
-
-	adap->fe_adap[0].fe = dvb_attach(m88ds3103_attach,
-					&tt_s2_4600_m88ds3103_config,
-					&d->i2c_adap,
-					&i2c_adapter);
-	if (adap->fe_adap[0].fe == NULL)
+	/* attach demod */
+	m88ds3103_pdata.clk = 27000000;
+	m88ds3103_pdata.i2c_wr_max = 33;
+	m88ds3103_pdata.ts_mode = M88DS3103_TS_CI;
+	m88ds3103_pdata.ts_clk = 16000;
+	m88ds3103_pdata.ts_clk_pol = 0;
+	m88ds3103_pdata.spec_inv = 0;
+	m88ds3103_pdata.agc = 0x99;
+	m88ds3103_pdata.agc_inv = 0;
+	m88ds3103_pdata.clk_out = M88DS3103_CLOCK_OUT_ENABLED;
+	m88ds3103_pdata.envelope_mode = 0;
+	m88ds3103_pdata.lnb_hv_pol = 1;
+	m88ds3103_pdata.lnb_en_pol = 0;
+	memset(&board_info, 0, sizeof(board_info));
+	strlcpy(board_info.type, "m88ds3103", I2C_NAME_SIZE);
+	board_info.addr = 0x68;
+	board_info.platform_data = &m88ds3103_pdata;
+	request_module("m88ds3103");
+	client = i2c_new_device(&d->i2c_adap, &board_info);
+	if (client == NULL || client->dev.driver == NULL)
 		return -ENODEV;
+	if (!try_module_get(client->dev.driver->owner)) {
+		i2c_unregister_device(client);
+		return -ENODEV;
+	}
+	adap->fe_adap[0].fe = m88ds3103_pdata.get_dvb_frontend(client);
+	i2c_adapter = m88ds3103_pdata.get_i2c_adapter(client);
+
+	state->i2c_client_demod = client;
 
 	/* attach tuner */
 	ts2020_config.fe = adap->fe_adap[0].fe;
-	strlcpy(info.type, "ts2022", I2C_NAME_SIZE);
-	info.addr = 0x60;
-	info.platform_data = &ts2020_config;
+	memset(&board_info, 0, sizeof(board_info));
+	strlcpy(board_info.type, "ts2022", I2C_NAME_SIZE);
+	board_info.addr = 0x60;
+	board_info.platform_data = &ts2020_config;
 	request_module("ts2020");
-	client = i2c_new_device(i2c_adapter, &info);
+	client = i2c_new_device(i2c_adapter, &board_info);
 
 	if (client == NULL || client->dev.driver == NULL) {
 		dvb_frontend_detach(adap->fe_adap[0].fe);
@@ -1688,6 +1700,8 @@ enum dw2102_table_entry {
 	TECHNOTREND_S2_4600,
 	TEVII_S482_1,
 	TEVII_S482_2,
+	TERRATEC_CINERGY_S2_BOX,
+	TEVII_S662
 };
 
 static struct usb_device_id dw2102_table[] = {
@@ -1702,19 +1716,21 @@ static struct usb_device_id dw2102_table[] = {
 	[TEVII_S660] = {USB_DEVICE(0x9022, USB_PID_TEVII_S660)},
 	[PROF_7500] = {USB_DEVICE(0x3034, 0x7500)},
 	[GENIATECH_SU3000] = {USB_DEVICE(0x1f4d, 0x3000)},
-	[TERRATEC_CINERGY_S2] = {USB_DEVICE(USB_VID_TERRATEC, 0x00a8)},
+	[TERRATEC_CINERGY_S2] = {USB_DEVICE(USB_VID_TERRATEC, USB_PID_TERRATEC_CINERGY_S2_R1)},
 	[TEVII_S480_1] = {USB_DEVICE(0x9022, USB_PID_TEVII_S480_1)},
 	[TEVII_S480_2] = {USB_DEVICE(0x9022, USB_PID_TEVII_S480_2)},
 	[X3M_SPC1400HD] = {USB_DEVICE(0x1f4d, 0x3100)},
 	[TEVII_S421] = {USB_DEVICE(0x9022, USB_PID_TEVII_S421)},
 	[TEVII_S632] = {USB_DEVICE(0x9022, USB_PID_TEVII_S632)},
-	[TERRATEC_CINERGY_S2_R2] = {USB_DEVICE(USB_VID_TERRATEC, 0x00b0)},
+	[TERRATEC_CINERGY_S2_R2] = {USB_DEVICE(USB_VID_TERRATEC, USB_PID_TERRATEC_CINERGY_S2_R2)},
 	[GOTVIEW_SAT_HD] = {USB_DEVICE(0x1FE1, USB_PID_GOTVIEW_SAT_HD)},
 	[GENIATECH_T220] = {USB_DEVICE(0x1f4d, 0xD220)},
 	[TECHNOTREND_S2_4600] = {USB_DEVICE(USB_VID_TECHNOTREND,
 		USB_PID_TECHNOTREND_CONNECT_S2_4600)},
 	[TEVII_S482_1] = {USB_DEVICE(0x9022, 0xd483)},
 	[TEVII_S482_2] = {USB_DEVICE(0x9022, 0xd484)},
+	[TERRATEC_CINERGY_S2_BOX] = {USB_DEVICE(USB_VID_TERRATEC, 0x0105)},
+	[TEVII_S662] = {USB_DEVICE(0x9022, USB_PID_TEVII_S662)},
 	{ }
 };
 
@@ -2232,7 +2248,7 @@ static struct dvb_usb_device_properties tt_s2_4600_properties = {
 		} },
 		}
 	},
-	.num_device_descs = 3,
+	.num_device_descs = 5,
 	.devices = {
 		{ "TechnoTrend TT-connect S2-4600",
 			{ &dw2102_table[TECHNOTREND_S2_4600], NULL },
@@ -2246,6 +2262,14 @@ static struct dvb_usb_device_properties tt_s2_4600_properties = {
 			{ &dw2102_table[TEVII_S482_2], NULL },
 			{ NULL },
 		},
+		{ "Terratec Cinergy S2 USB BOX",
+			{ &dw2102_table[TERRATEC_CINERGY_S2_BOX], NULL },
+			{ NULL },
+		},
+		{ "TeVii S662",
+			{ &dw2102_table[TEVII_S662], NULL },
+			{ NULL },
+		},
 	}
 };
 
@@ -2344,6 +2368,13 @@ static void dw2102_disconnect(struct usb_interface *intf)
 		i2c_unregister_device(client);
 	}
 
+	/* remove I2C client for demodulator */
+	client = st->i2c_client_demod;
+	if (client) {
+		module_put(client->dev.driver->owner);
+		i2c_unregister_device(client);
+	}
+
 	dvb_usb_device_exit(intf);
 }
 
@@ -2359,10 +2390,10 @@ module_usb_driver(dw2102_driver);
 MODULE_AUTHOR("Igor M. Liplianin (c) liplianin@me.by");
 MODULE_DESCRIPTION("Driver for DVBWorld DVB-S 2101, 2102, DVB-S2 2104,"
 			" DVB-C 3101 USB2.0,"
-			" TeVii S600, S630, S650, S660, S480, S421, S632"
-			" Prof 1100, 7500 USB2.0,"
+			" TeVii S421, S480, S482, S600, S630, S632, S650,"
+			" TeVii S660, S662, Prof 1100, 7500 USB2.0,"
 			" Geniatech SU3000, T220,"
-			" TechnoTrend S2-4600 devices");
+			" TechnoTrend S2-4600, Terratec Cinergy S2 devices");
 MODULE_VERSION("0.1");
 MODULE_LICENSE("GPL");
 MODULE_FIRMWARE(DW2101_FIRMWARE);
diff --git a/drivers/media/usb/dvb-usb/friio-fe.c b/drivers/media/usb/dvb-usb/friio-fe.c
index 8ec92fbeabad..979f05b4b87c 100644
--- a/drivers/media/usb/dvb-usb/friio-fe.c
+++ b/drivers/media/usb/dvb-usb/friio-fe.c
@@ -283,20 +283,6 @@ static int jdvbt90502_set_property(struct dvb_frontend *fe,
 	return r;
 }
 
-static int jdvbt90502_get_frontend(struct dvb_frontend *fe)
-{
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
-	p->inversion = INVERSION_AUTO;
-	p->bandwidth_hz = 6000000;
-	p->code_rate_HP = FEC_AUTO;
-	p->code_rate_LP = FEC_AUTO;
-	p->modulation = QAM_64;
-	p->transmission_mode = TRANSMISSION_MODE_AUTO;
-	p->guard_interval = GUARD_INTERVAL_AUTO;
-	p->hierarchy = HIERARCHY_AUTO;
-	return 0;
-}
-
 static int jdvbt90502_set_frontend(struct dvb_frontend *fe)
 {
 	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
@@ -312,8 +298,16 @@ static int jdvbt90502_set_frontend(struct dvb_frontend *fe)
 
 	deb_fe("%s: Freq:%d\n", __func__, p->frequency);
 
-	/* for recovery from DTV_CLEAN */
-	fe->dtv_property_cache.delivery_system = SYS_ISDBT;
+	/* This driver only works on auto mode */
+	p->inversion = INVERSION_AUTO;
+	p->bandwidth_hz = 6000000;
+	p->code_rate_HP = FEC_AUTO;
+	p->code_rate_LP = FEC_AUTO;
+	p->modulation = QAM_64;
+	p->transmission_mode = TRANSMISSION_MODE_AUTO;
+	p->guard_interval = GUARD_INTERVAL_AUTO;
+	p->hierarchy = HIERARCHY_AUTO;
+	p->delivery_system = SYS_ISDBT;
 
 	ret = jdvbt90502_pll_set_freq(state, p->frequency);
 	if (ret) {
@@ -466,7 +460,6 @@ static struct dvb_frontend_ops jdvbt90502_ops = {
 	.set_property = jdvbt90502_set_property,
 
 	.set_frontend = jdvbt90502_set_frontend,
-	.get_frontend = jdvbt90502_get_frontend,
 
 	.read_status = jdvbt90502_read_status,
 	.read_signal_strength = jdvbt90502_read_signal_strength,
diff --git a/drivers/media/usb/dvb-usb/nova-t-usb2.c b/drivers/media/usb/dvb-usb/nova-t-usb2.c
index 6c55384e2fca..fc7569e2728d 100644
--- a/drivers/media/usb/dvb-usb/nova-t-usb2.c
+++ b/drivers/media/usb/dvb-usb/nova-t-usb2.c
@@ -1,7 +1,7 @@
 /* DVB USB framework compliant Linux driver for the Hauppauge WinTV-NOVA-T usb2
  * DVB-T receiver.
  *
- * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  *	This program is free software; you can redistribute it and/or modify it
  *	under the terms of the GNU General Public License as published by the Free
@@ -227,7 +227,7 @@ static struct usb_driver nova_t_driver = {
 
 module_usb_driver(nova_t_driver);
 
-MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@desy.de>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("Hauppauge WinTV-NOVA-T usb2");
 MODULE_VERSION("1.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/usb/dvb-usb/technisat-usb2.c b/drivers/media/usb/dvb-usb/technisat-usb2.c
index 6c3c47722955..d9f3262bf071 100644
--- a/drivers/media/usb/dvb-usb/technisat-usb2.c
+++ b/drivers/media/usb/dvb-usb/technisat-usb2.c
@@ -60,6 +60,8 @@ struct technisat_usb2_state {
 	u8 power_state;
 
 	u16 last_scan_code;
+
+	u8 buf[64];
 };
 
 /* debug print helpers */
@@ -220,19 +222,19 @@ enum technisat_usb2_led_state {
 	TECH_LED_UNDEFINED
 };
 
-static int technisat_usb2_set_led(struct dvb_usb_device *d, int red, enum technisat_usb2_led_state state)
+static int technisat_usb2_set_led(struct dvb_usb_device *d, int red,
+				  enum technisat_usb2_led_state st)
 {
+	struct technisat_usb2_state *state = d->priv;
+	u8 *led = state->buf;
 	int ret;
 
-	u8 led[8] = {
-		red ? SET_RED_LED_VENDOR_REQUEST : SET_GREEN_LED_VENDOR_REQUEST,
-		0
-	};
+	led[0] = red ? SET_RED_LED_VENDOR_REQUEST : SET_GREEN_LED_VENDOR_REQUEST;
 
-	if (disable_led_control && state != TECH_LED_OFF)
+	if (disable_led_control && st != TECH_LED_OFF)
 		return 0;
 
-	switch (state) {
+	switch (st) {
 	case TECH_LED_ON:
 		led[1] = 0x82;
 		break;
@@ -263,7 +265,7 @@ static int technisat_usb2_set_led(struct dvb_usb_device *d, int red, enum techni
 		red ? SET_RED_LED_VENDOR_REQUEST : SET_GREEN_LED_VENDOR_REQUEST,
 		USB_TYPE_VENDOR | USB_DIR_OUT,
 		0, 0,
-		led, sizeof(led), 500);
+		led, 8, 500);
 
 	mutex_unlock(&d->i2c_mutex);
 	return ret;
@@ -271,8 +273,11 @@ static int technisat_usb2_set_led(struct dvb_usb_device *d, int red, enum techni
 
 static int technisat_usb2_set_led_timer(struct dvb_usb_device *d, u8 red, u8 green)
 {
+	struct technisat_usb2_state *state = d->priv;
+	u8 *b = state->buf;
 	int ret;
-	u8 b = 0;
+
+	b[0] = 0;
 
 	if (mutex_lock_interruptible(&d->i2c_mutex) < 0)
 		return -EAGAIN;
@@ -281,7 +286,7 @@ static int technisat_usb2_set_led_timer(struct dvb_usb_device *d, u8 red, u8 gre
 		SET_LED_TIMER_DIVIDER_VENDOR_REQUEST,
 		USB_TYPE_VENDOR | USB_DIR_OUT,
 		(red << 8) | green, 0,
-		&b, 1, 500);
+		b, 1, 500);
 
 	mutex_unlock(&d->i2c_mutex);
 
@@ -328,7 +333,11 @@ static int technisat_usb2_identify_state(struct usb_device *udev,
 		struct dvb_usb_device_description **desc, int *cold)
 {
 	int ret;
-	u8 version[3];
+	u8 *version;
+
+	version = kmalloc(3, GFP_KERNEL);
+	if (!version)
+		return -ENOMEM;
 
 	/* first select the interface */
 	if (usb_set_interface(udev, 0, 1) != 0)
@@ -342,7 +351,7 @@ static int technisat_usb2_identify_state(struct usb_device *udev,
 		GET_VERSION_INFO_VENDOR_REQUEST,
 		USB_TYPE_VENDOR | USB_DIR_IN,
 		0, 0,
-		version, sizeof(version), 500);
+		version, 3, 500);
 
 	if (ret < 0)
 		*cold = 1;
@@ -351,6 +360,8 @@ static int technisat_usb2_identify_state(struct usb_device *udev,
 		*cold = 0;
 	}
 
+	kfree(version);
+
 	return 0;
 }
 
@@ -512,7 +523,7 @@ static int technisat_usb2_frontend_attach(struct dvb_usb_adapter *a)
 			&a->dev->i2c_adap, STV090x_DEMODULATOR_0);
 
 	if (a->fe_adap[0].fe) {
-		struct stv6110x_devctl *ctl;
+		const struct stv6110x_devctl *ctl;
 
 		ctl = dvb_attach(stv6110x_attach,
 				a->fe_adap[0].fe,
@@ -594,7 +605,9 @@ static int technisat_usb2_frontend_attach(struct dvb_usb_adapter *a)
 
 static int technisat_usb2_get_ir(struct dvb_usb_device *d)
 {
-	u8 buf[62], *b;
+	struct technisat_usb2_state *state = d->priv;
+	u8 *buf = state->buf;
+	u8 *b;
 	int ret;
 	struct ir_raw_event ev;
 
@@ -620,7 +633,7 @@ static int technisat_usb2_get_ir(struct dvb_usb_device *d)
 			GET_IR_DATA_VENDOR_REQUEST,
 			USB_TYPE_VENDOR | USB_DIR_IN,
 			0x8080, 0,
-			buf, sizeof(buf), 500);
+			buf, 62, 500);
 
 unlock:
 	mutex_unlock(&d->i2c_mutex);
diff --git a/drivers/media/usb/dvb-usb/ttusb2.c b/drivers/media/usb/dvb-usb/ttusb2.c
index f10717311e05..ecc207fbaf3c 100644
--- a/drivers/media/usb/dvb-usb/ttusb2.c
+++ b/drivers/media/usb/dvb-usb/ttusb2.c
@@ -820,7 +820,7 @@ static struct usb_driver ttusb2_driver = {
 
 module_usb_driver(ttusb2_driver);
 
-MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@desy.de>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("Driver for Pinnacle PCTV 400e DVB-S USB2.0");
 MODULE_VERSION("1.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/usb/dvb-usb/umt-010.c b/drivers/media/usb/dvb-usb/umt-010.c
index 9b042292e788..58ad5b4f856c 100644
--- a/drivers/media/usb/dvb-usb/umt-010.c
+++ b/drivers/media/usb/dvb-usb/umt-010.c
@@ -1,7 +1,7 @@
 /* DVB USB framework compliant Linux driver for the HanfTek UMT-010 USB2.0
  * DVB-T receiver.
  *
- * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  *	This program is free software; you can redistribute it and/or modify it
  *	under the terms of the GNU General Public License as published by the Free
@@ -145,7 +145,7 @@ static struct usb_driver umt_driver = {
 
 module_usb_driver(umt_driver);
 
-MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@desy.de>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("Driver for HanfTek UMT 010 USB2.0 DVB-T device");
 MODULE_VERSION("1.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/usb/dvb-usb/usb-urb.c b/drivers/media/usb/dvb-usb/usb-urb.c
index d62ee0f5a165..89173603be67 100644
--- a/drivers/media/usb/dvb-usb/usb-urb.c
+++ b/drivers/media/usb/dvb-usb/usb-urb.c
@@ -1,6 +1,6 @@
 /* usb-urb.c is part of the DVB USB library.
  *
- * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-6 Patrick Boettcher (patrick.boettcher@posteo.de)
  * see dvb-usb-init.c for copyright information.
  *
  * This file keeps functions for initializing and handling the
diff --git a/drivers/media/usb/dvb-usb/vp702x-fe.c b/drivers/media/usb/dvb-usb/vp702x-fe.c
index d361a72ca0fa..27398c08c69d 100644
--- a/drivers/media/usb/dvb-usb/vp702x-fe.c
+++ b/drivers/media/usb/dvb-usb/vp702x-fe.c
@@ -4,7 +4,7 @@
  * Copyright (C) 2005 Ralph Metzler <rjkm@metzlerbros.de>
  *                    Metzler Brothers Systementwicklung GbR
  *
- * Copyright (C) 2005 Patrick Boettcher <patrick.boettcher@desy.de>
+ * Copyright (C) 2005 Patrick Boettcher <patrick.boettcher@posteo.de>
  *
  * Thanks to Twinhan who kindly provided hardware and information.
  *
diff --git a/drivers/media/usb/dvb-usb/vp702x.c b/drivers/media/usb/dvb-usb/vp702x.c
index ee1e19e36445..40de33de90a7 100644
--- a/drivers/media/usb/dvb-usb/vp702x.c
+++ b/drivers/media/usb/dvb-usb/vp702x.c
@@ -4,7 +4,7 @@
  * Copyright (C) 2005 Ralph Metzler <rjkm@metzlerbros.de>
  *                    Metzler Brothers Systementwicklung GbR
  *
- * Copyright (C) 2005 Patrick Boettcher <patrick.boettcher@desy.de>
+ * Copyright (C) 2005 Patrick Boettcher <patrick.boettcher@posteo.de>
  *
  * Thanks to Twinhan who kindly provided hardware and information.
  *
@@ -439,7 +439,7 @@ static struct usb_driver vp702x_usb_driver = {
 
 module_usb_driver(vp702x_usb_driver);
 
-MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@desy.de>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("Driver for Twinhan StarBox DVB-S USB2.0 and clones");
 MODULE_VERSION("1.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/usb/dvb-usb/vp7045-fe.c b/drivers/media/usb/dvb-usb/vp7045-fe.c
index e708afc6a57f..7765602ea658 100644
--- a/drivers/media/usb/dvb-usb/vp7045-fe.c
+++ b/drivers/media/usb/dvb-usb/vp7045-fe.c
@@ -1,7 +1,7 @@
 /* DVB frontend part of the Linux driver for TwinhanDTV Alpha/MagicBoxII USB2.0
  * DVB-T receiver.
  *
- * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  * Thanks to Twinhan who kindly provided hardware and information.
  *
diff --git a/drivers/media/usb/dvb-usb/vp7045.c b/drivers/media/usb/dvb-usb/vp7045.c
index d750724132ee..13340af0d39c 100644
--- a/drivers/media/usb/dvb-usb/vp7045.c
+++ b/drivers/media/usb/dvb-usb/vp7045.c
@@ -2,7 +2,7 @@
  *  - TwinhanDTV Alpha/MagicBoxII USB2.0 DVB-T receiver
  *  - DigitalNow TinyUSB2 DVB-t receiver
  *
- * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  * Thanks to Twinhan who kindly provided hardware and information.
  *
@@ -296,7 +296,7 @@ static struct usb_driver vp7045_usb_driver = {
 
 module_usb_driver(vp7045_usb_driver);
 
-MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@desy.de>");
+MODULE_AUTHOR("Patrick Boettcher <patrick.boettcher@posteo.de>");
 MODULE_DESCRIPTION("Driver for Twinhan MagicBox/Alpha and DNTV tinyUSB2 DVB-T USB2.0");
 MODULE_VERSION("1.0");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/usb/dvb-usb/vp7045.h b/drivers/media/usb/dvb-usb/vp7045.h
index cf5ec46f8bb1..66499932ca76 100644
--- a/drivers/media/usb/dvb-usb/vp7045.h
+++ b/drivers/media/usb/dvb-usb/vp7045.h
@@ -1,7 +1,7 @@
 /* Common header-file of the Linux driver for the TwinhanDTV Alpha/MagicBoxII
  * USB2.0 DVB-T receiver.
  *
- * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@desy.de)
+ * Copyright (C) 2004-5 Patrick Boettcher (patrick.boettcher@posteo.de)
  *
  * Thanks to Twinhan who kindly provided hardware and information.
  *
diff --git a/drivers/media/usb/em28xx/em28xx-camera.c b/drivers/media/usb/em28xx/em28xx-camera.c
index b58acd3fcd99..72f3f4d50253 100644
--- a/drivers/media/usb/em28xx/em28xx-camera.c
+++ b/drivers/media/usb/em28xx/em28xx-camera.c
@@ -64,6 +64,8 @@ static int em28xx_initialize_mt9m111(struct em28xx *dev)
 		i2c_master_send(&dev->i2c_client[dev->def_i2c_bus],
 				&regs[i][0], 3);
 
+	/* FIXME: This won't be creating a sensor at the media graph */
+
 	return 0;
 }
 
@@ -91,6 +93,8 @@ static int em28xx_initialize_mt9m001(struct em28xx *dev)
 		i2c_master_send(&dev->i2c_client[dev->def_i2c_bus],
 				&regs[i][0], 3);
 
+	/* FIXME: This won't be creating a sensor at the media graph */
+
 	return 0;
 }
 
diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c
index a1b6ef5894a6..930e3e3fc948 100644
--- a/drivers/media/usb/em28xx/em28xx-cards.c
+++ b/drivers/media/usb/em28xx/em28xx-cards.c
@@ -32,11 +32,12 @@
 #include <media/tuner.h>
 #include <media/drv-intf/msp3400.h>
 #include <media/i2c/saa7115.h>
-#include <media/i2c/tvp5150.h>
+#include <dt-bindings/media/tvp5150.h>
 #include <media/i2c/tvaudio.h>
 #include <media/i2c-addr.h>
 #include <media/tveeprom.h>
 #include <media/v4l2-common.h>
+#include <sound/ac97_codec.h>
 
 #include "em28xx.h"
 
@@ -560,6 +561,16 @@ static struct em28xx_led pctv_80e_leds[] = {
 	{-1, 0, 0, 0},
 };
 
+static struct em28xx_led terratec_grabby_leds[] = {
+	{
+		.role      = EM28XX_LED_ANALOG_CAPTURING,
+		.gpio_reg  = EM2820_R08_GPIO_CTRL,
+		.gpio_mask = EM_GPIO_3,
+		.inverted  = 1,
+	},
+	{-1, 0, 0, 0},
+};
+
 /*
  *  Board definitions
  */
@@ -570,7 +581,7 @@ struct em28xx_board em28xx_boards[] = {
 		.tuner_type    = TUNER_ABSENT,
 		.is_webcam     = 1,
 		.input         = { {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = 0,
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = silvercrest_reg_seq,
@@ -583,7 +594,7 @@ struct em28xx_board em28xx_boards[] = {
 		.decoder      = EM28XX_SAA711X,
 		.tuner_type   = TUNER_ABSENT,
 		.input        = { {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -605,7 +616,7 @@ struct em28xx_board em28xx_boards[] = {
 		.tuner_type    = TUNER_ABSENT,
 		.is_webcam     = 1,
 		.input         = { {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = 0,
 			.amux     = EM28XX_AMUX_VIDEO,
 		} },
@@ -616,7 +627,7 @@ struct em28xx_board em28xx_boards[] = {
 		.tda9887_conf = TDA9887_PRESENT,
 		.decoder      = EM28XX_SAA711X,
 		.input        = { {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -635,7 +646,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = SAA7115_COMPOSITE2,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -655,7 +666,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = SAA7115_COMPOSITE2,
 			.amux     = EM28XX_AMUX_VIDEO,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -675,7 +686,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = SAA7115_COMPOSITE2,
 			.amux     = EM28XX_AMUX_VIDEO,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -715,7 +726,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = SAA7115_COMPOSITE2,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -735,7 +746,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = SAA7115_COMPOSITE2,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -755,7 +766,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = SAA7115_COMPOSITE2,
 			.amux     = EM28XX_AMUX_VIDEO,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -775,7 +786,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = SAA7115_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -800,7 +811,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = SAA7115_COMPOSITE4,
 			.amux     = EM28XX_AMUX_AUX,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE5,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -819,7 +830,7 @@ struct em28xx_board em28xx_boards[] = {
 		.tuner_type   = TUNER_ABSENT,
 		.is_webcam    = 1,
 		.input        = { {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = 0,
 			.amux     = EM28XX_AMUX_VIDEO,
 		} },
@@ -829,7 +840,7 @@ struct em28xx_board em28xx_boards[] = {
 		.tuner_type   = TUNER_ABSENT,
 		.is_webcam    = 1,
 		.input        = { {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = 0,
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = silvercrest_reg_seq,
@@ -848,7 +859,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = SAA7115_COMPOSITE2,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_VIDEO,
 		}, {
@@ -863,7 +874,7 @@ struct em28xx_board em28xx_boards[] = {
 		.tuner_type   = TUNER_ABSENT,	/* Capture only device */
 		.decoder      = EM28XX_SAA711X,
 		.input        = { {
-			.type  = EM28XX_VMUX_COMPOSITE1,
+			.type  = EM28XX_VMUX_COMPOSITE,
 			.vmux  = SAA7115_COMPOSITE0,
 			.amux  = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -879,7 +890,7 @@ struct em28xx_board em28xx_boards[] = {
 		.tuner_type   = TUNER_ABSENT,
 		.is_webcam    = 1,
 		.input        = { {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = 0,
 			.amux     = EM28XX_AMUX_VIDEO,
 		} },
@@ -889,7 +900,7 @@ struct em28xx_board em28xx_boards[] = {
 		.decoder      = EM28XX_SAA711X,
 		.tuner_type   = TUNER_ABSENT,	/* Capture only device */
 		.input        = { {
-			.type  = EM28XX_VMUX_COMPOSITE1,
+			.type  = EM28XX_VMUX_COMPOSITE,
 			.vmux  = SAA7115_COMPOSITE0,
 			.amux  = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -909,7 +920,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = SAA7115_COMPOSITE2,
 			.amux     = EM28XX_AMUX_VIDEO,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -930,7 +941,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = SAA7115_COMPOSITE2,
 			.amux     = EM28XX_AMUX_VIDEO,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -952,7 +963,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
@@ -974,7 +985,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = TVP5150_COMPOSITE0,
 			.amux     = EM28XX_AMUX_VIDEO,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -992,7 +1003,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = TVP5150_COMPOSITE0,
 			.amux     = EM28XX_AMUX_VIDEO,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -1006,7 +1017,7 @@ struct em28xx_board em28xx_boards[] = {
 		.tuner_type    = TUNER_ABSENT,	/* Capture only device */
 		.decoder       = EM28XX_TVP5150,
 		.input         = { {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -1029,7 +1040,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = pinnacle_hybrid_pro_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = pinnacle_hybrid_pro_analog,
@@ -1100,7 +1111,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = terratec_cinergy_USB_XS_FR_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = terratec_cinergy_USB_XS_FR_analog,
@@ -1186,7 +1197,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
@@ -1213,7 +1224,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
@@ -1239,7 +1250,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
@@ -1265,7 +1276,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
@@ -1291,7 +1302,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
@@ -1317,7 +1328,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
@@ -1343,7 +1354,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = default_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = default_analog,
@@ -1368,7 +1379,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
@@ -1392,7 +1403,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux      = SAA7115_COMPOSITE4,
 			.amux      = EM28XX_AMUX_VIDEO,
 		}, {
-			.type      = EM28XX_VMUX_COMPOSITE1,
+			.type      = EM28XX_VMUX_COMPOSITE,
 			.vmux      = SAA7115_COMPOSITE0,
 			.amux      = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -1413,7 +1424,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = SAA7115_COMPOSITE2,
 			.amux     = EM28XX_AMUX_VIDEO,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -1428,7 +1439,7 @@ struct em28xx_board em28xx_boards[] = {
 		.decoder    = EM28XX_SAA711X,
 		.tuner_type = TUNER_ABSENT, /* capture only board */
 		.input      = { {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -1443,7 +1454,7 @@ struct em28xx_board em28xx_boards[] = {
 		.tuner_type   = TUNER_ABSENT,	/* Capture-only board */
 		.decoder      = EM28XX_SAA711X,
 		.input        = { {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = vc211a_enable,
@@ -1465,7 +1476,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = SAA7115_COMPOSITE2,
 			.amux     = EM28XX_AMUX_VIDEO,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -1485,7 +1496,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = SAA7115_COMPOSITE2,
 			.amux     = EM28XX_AMUX_VIDEO,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -1500,7 +1511,7 @@ struct em28xx_board em28xx_boards[] = {
 		.tuner_type   = TUNER_ABSENT, /* capture only board */
 		.decoder      = EM28XX_SAA711X,
 		.input        = { {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -1520,7 +1531,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = SAA7115_COMPOSITE2,
 			.amux     = EM28XX_AMUX_VIDEO,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -1541,7 +1552,7 @@ struct em28xx_board em28xx_boards[] = {
 			.aout     = EM28XX_AOUT_MONO |	/* I2S */
 				    EM28XX_AOUT_MASTER,	/* Line out pin */
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -1555,6 +1566,7 @@ struct em28xx_board em28xx_boards[] = {
 		.buttons = std_snapshot_button,
 		.tda9887_conf = TDA9887_PRESENT,
 		.tuner_type   = TUNER_YMEC_TVF_5533MF,
+		.tuner_addr   = 0x60,
 		.decoder      = EM28XX_SAA711X,
 		.input        = { {
 			.type     = EM28XX_VMUX_TELEVISION,
@@ -1563,7 +1575,7 @@ struct em28xx_board em28xx_boards[] = {
 			.aout     = EM28XX_AOUT_MONO |	/* I2S */
 				    EM28XX_AOUT_MASTER,	/* Line out pin */
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -1581,7 +1593,7 @@ struct em28xx_board em28xx_boards[] = {
 			.type     = EM28XX_VMUX_SVIDEO,
 			.vmux     = SAA7115_SVIDEO3,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 		} },
 	},
@@ -1610,7 +1622,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = em2880_msi_digivox_ad_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = em2880_msi_digivox_ad_analog,
@@ -1633,7 +1645,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = em2880_msi_digivox_ad_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = em2880_msi_digivox_ad_analog,
@@ -1654,7 +1666,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = TVP5150_COMPOSITE0,
 			.amux     = EM28XX_AMUX_VIDEO,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -1677,7 +1689,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = default_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = default_analog,
@@ -1708,7 +1720,7 @@ struct em28xx_board em28xx_boards[] = {
 			.gpio = em2882_kworld_315u_analog,
 			.aout = EM28XX_AOUT_PCM_IN | EM28XX_AOUT_PCM_STEREO,
 		}, {
-			.type = EM28XX_VMUX_COMPOSITE1,
+			.type = EM28XX_VMUX_COMPOSITE,
 			.vmux = SAA7115_COMPOSITE0,
 			.amux = EM28XX_AMUX_LINE_IN,
 			.gpio = em2882_kworld_315u_analog1,
@@ -1735,7 +1747,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux = EM28XX_AMUX_VIDEO,
 			.gpio = default_analog,
 		}, {
-			.type = EM28XX_VMUX_COMPOSITE1,
+			.type = EM28XX_VMUX_COMPOSITE,
 			.vmux = TVP5150_COMPOSITE1,
 			.amux = EM28XX_AMUX_LINE_IN,
 			.gpio = default_analog,
@@ -1758,7 +1770,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = default_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = default_analog,
@@ -1782,7 +1794,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = pinnacle_hybrid_pro_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = pinnacle_hybrid_pro_analog,
@@ -1808,7 +1820,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
@@ -1834,7 +1846,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = TVP5150_COMPOSITE0,
 			.amux     = EM28XX_AMUX_VIDEO,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -1859,7 +1871,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = hauppauge_wintv_hvr_900_analog,
@@ -1904,7 +1916,7 @@ struct em28xx_board em28xx_boards[] = {
 			.gpio     = kworld_330u_analog,
 			.aout     = EM28XX_AOUT_PCM_IN | EM28XX_AOUT_PCM_STEREO,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = kworld_330u_analog,
@@ -1951,7 +1963,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -1970,7 +1982,7 @@ struct em28xx_board em28xx_boards[] = {
 		.tuner_type   = TUNER_ABSENT,
 		.decoder      = EM28XX_SAA711X,
 		.input           = { {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -1990,7 +2002,7 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = TVP5150_COMPOSITE0,
 			.amux     = EM28XX_AMUX_VIDEO,
 		}, { /* Composite has not been tested yet */
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_VIDEO,
 		}, { /* S-video has not been tested yet */
@@ -2006,7 +2018,7 @@ struct em28xx_board em28xx_boards[] = {
 		.decoder         = EM28XX_SAA711X,
 		.xclk            = EM28XX_XCLK_FREQUENCY_12MHZ,
 		.input           = { {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -2014,6 +2026,8 @@ struct em28xx_board em28xx_boards[] = {
 			.vmux     = SAA7115_SVIDEO3,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		} },
+		.buttons         = std_snapshot_button,
+		.leds            = terratec_grabby_leds,
 	},
 	[EM2860_BOARD_TERRATEC_AV350] = {
 		.name            = "Terratec AV350",
@@ -2023,7 +2037,7 @@ struct em28xx_board em28xx_boards[] = {
 		.xclk            = EM28XX_XCLK_FREQUENCY_12MHZ,
 		.mute_gpio       = terratec_av350_mute_gpio,
 		.input           = { {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AUDIO_SRC_LINE,
 			.gpio     = terratec_av350_unmute_gpio,
@@ -2041,7 +2055,7 @@ struct em28xx_board em28xx_boards[] = {
 		.decoder      = EM28XX_SAA711X,
 		.tuner_type   = TUNER_ABSENT,   /* Capture only device */
 		.input        = { {
-			.type  = EM28XX_VMUX_COMPOSITE1,
+			.type  = EM28XX_VMUX_COMPOSITE,
 			.vmux  = SAA7115_COMPOSITE0,
 			.amux  = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -2067,7 +2081,7 @@ struct em28xx_board em28xx_boards[] = {
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = evga_indtube_analog,
 		}, {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 			.gpio     = evga_indtube_analog,
@@ -2125,7 +2139,7 @@ struct em28xx_board em28xx_boards[] = {
 		.tuner_type          = TUNER_ABSENT,
 		.decoder             = EM28XX_SAA711X,
 		.input               = { {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = SAA7115_COMPOSITE0,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -2238,7 +2252,7 @@ struct em28xx_board em28xx_boards[] = {
 		.tuner_type   = TUNER_ABSENT,
 		.is_webcam    = 1,
 		.input        = { {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.amux     = EM28XX_AMUX_VIDEO,
 			.gpio     = speedlink_vad_laplace_reg_seq,
 		} },
@@ -2272,7 +2286,7 @@ struct em28xx_board em28xx_boards[] = {
 		.tuner_type    = TUNER_ABSENT,	/* Capture only device */
 		.decoder       = EM28XX_TVP5150,
 		.input         = { {
-			.type     = EM28XX_VMUX_COMPOSITE1,
+			.type     = EM28XX_VMUX_COMPOSITE,
 			.vmux     = TVP5150_COMPOSITE1,
 			.amux     = EM28XX_AMUX_LINE_IN,
 		}, {
@@ -2550,6 +2564,36 @@ static inline void em28xx_set_model(struct em28xx *dev)
 	dev->def_i2c_bus = dev->board.def_i2c_bus;
 }
 
+/* Wait until AC97_RESET reports the expected value reliably before proceeding.
+ * We also check that two unrelated registers accesses don't return the same
+ * value to avoid premature return.
+ * This procedure helps ensuring AC97 register accesses are reliable.
+ */
+static int em28xx_wait_until_ac97_features_equals(struct em28xx *dev,
+						  int expected_feat)
+{
+	unsigned long timeout = jiffies + msecs_to_jiffies(2000);
+	int feat, powerdown;
+
+	while (time_is_after_jiffies(timeout)) {
+		feat = em28xx_read_ac97(dev, AC97_RESET);
+		if (feat < 0)
+			return feat;
+
+		powerdown = em28xx_read_ac97(dev, AC97_POWERDOWN);
+		if (powerdown < 0)
+			return powerdown;
+
+		if (feat == expected_feat && feat != powerdown)
+			return 0;
+
+		msleep(50);
+	}
+
+	em28xx_warn("AC97 registers access is not reliable !\n");
+	return -ETIMEDOUT;
+}
+
 /* Since em28xx_pre_card_setup() requires a proper dev->model,
  * this won't work for boards with generic PCI IDs
  */
@@ -2655,6 +2699,13 @@ static void em28xx_pre_card_setup(struct em28xx *dev)
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfd);
 		msleep(70);
 		break;
+
+	case EM2860_BOARD_TERRATEC_GRABBY:
+		/* HACK?: Ensure AC97 register reading is reliable before
+		 * proceeding. In practice, this will wait about 1.6 seconds.
+		 */
+		em28xx_wait_until_ac97_features_equals(dev, 0x6a90);
+		break;
 	}
 
 	em28xx_gpio_set(dev, dev->board.tuner_gpio);
@@ -3012,6 +3063,41 @@ static void flush_request_modules(struct em28xx *dev)
 	flush_work(&dev->request_module_wk);
 }
 
+static int em28xx_media_device_init(struct em28xx *dev,
+				    struct usb_device *udev)
+{
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct media_device *mdev;
+
+	mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
+	if (!mdev)
+		return -ENOMEM;
+
+	if (udev->product)
+		media_device_usb_init(mdev, udev, udev->product);
+	else if (udev->manufacturer)
+		media_device_usb_init(mdev, udev, udev->manufacturer);
+	else
+		media_device_usb_init(mdev, udev, dev->name);
+
+	dev->media_dev = mdev;
+#endif
+	return 0;
+}
+
+static void em28xx_unregister_media_device(struct em28xx *dev)
+{
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+	if (dev->media_dev) {
+		media_device_unregister(dev->media_dev);
+		media_device_cleanup(dev->media_dev);
+		kfree(dev->media_dev);
+		dev->media_dev = NULL;
+	}
+#endif
+}
+
 /*
  * em28xx_release_resources()
  * unregisters the v4l2,i2c and usb devices
@@ -3023,6 +3109,8 @@ static void em28xx_release_resources(struct em28xx *dev)
 
 	mutex_lock(&dev->lock);
 
+	em28xx_unregister_media_device(dev);
+
 	if (dev->def_i2c_bus)
 		em28xx_i2c_unregister(dev, 1);
 	em28xx_i2c_unregister(dev, 0);
@@ -3167,6 +3255,8 @@ static int em28xx_init_dev(struct em28xx *dev, struct usb_device *udev,
 	 */
 	snprintf(dev->name, sizeof(dev->name), "%s #%d", chip_name, dev->devno);
 
+	em28xx_media_device_init(dev, udev);
+
 	if (dev->is_audio_only) {
 		retval = em28xx_audio_setup(dev);
 		if (retval)
@@ -3467,7 +3557,7 @@ static int em28xx_usb_probe(struct usb_interface *interface,
 	/* save our data pointer in this interface device */
 	usb_set_intfdata(interface, dev);
 
-	/* allocate device struct */
+	/* allocate device struct and check if the device is a webcam */
 	mutex_init(&dev->lock);
 	retval = em28xx_init_dev(dev, udev, interface, nr);
 	if (retval) {
@@ -3483,6 +3573,15 @@ static int em28xx_usb_probe(struct usb_interface *interface,
 		try_bulk = usb_xfer_mode > 0;
 	}
 
+	/* Disable V4L2 if the device doesn't have a decoder */
+	if (has_video &&
+	    dev->board.decoder == EM28XX_NODECODER && !dev->board.is_webcam) {
+		printk(DRIVER_NAME
+		       ": Currently, V4L2 is not supported on this model\n");
+		has_video = false;
+		dev->has_video = false;
+	}
+
 	/* Select USB transfer types to use */
 	if (has_video) {
 		if (!dev->analog_ep_isoc || (try_bulk && dev->analog_ep_bulk))
@@ -3501,9 +3600,14 @@ static int em28xx_usb_probe(struct usb_interface *interface,
 
 	request_modules(dev);
 
-	/* Should be the last thing to do, to avoid newer udev's to
-	   open the device before fully initializing it
+	/*
+	 * Do it at the end, to reduce dynamic configuration changes during
+	 * the device init. Yet, as request_modules() can be async, the
+	 * topology will likely change after the load of the em28xx subdrivers.
 	 */
+#ifdef CONFIG_MEDIA_CONTROLLER
+	retval = media_device_register(dev->media_dev);
+#endif
 
 	return 0;
 
diff --git a/drivers/media/usb/em28xx/em28xx-dvb.c b/drivers/media/usb/em28xx/em28xx-dvb.c
index bf5c24467c65..5d209c7c54d5 100644
--- a/drivers/media/usb/em28xx/em28xx-dvb.c
+++ b/drivers/media/usb/em28xx/em28xx-dvb.c
@@ -905,6 +905,7 @@ static int em28xx_register_dvb(struct em28xx_dvb *dvb, struct module *module,
 			       struct em28xx *dev, struct device *device)
 {
 	int result;
+	bool create_rf_connector = false;
 
 	mutex_init(&dvb->lock);
 
@@ -916,6 +917,9 @@ static int em28xx_register_dvb(struct em28xx_dvb *dvb, struct module *module,
 		       dev->name, result);
 		goto fail_adapter;
 	}
+#ifdef CONFIG_MEDIA_CONTROLLER_DVB
+	dvb->adapter.mdev = dev->media_dev;
+#endif
 
 	/* Ensure all frontends negotiate bus access */
 	dvb->fe[0]->ops.ts_bus_ctrl = em28xx_dvb_bus_ctrl;
@@ -994,8 +998,19 @@ static int em28xx_register_dvb(struct em28xx_dvb *dvb, struct module *module,
 
 	/* register network adapter */
 	dvb_net_init(&dvb->adapter, &dvb->net, &dvb->demux.dmx);
+
+	/* If the analog part won't create RF connectors, DVB will do it */
+	if (!dev->has_video || (dev->tuner_type == TUNER_ABSENT))
+		create_rf_connector = true;
+
+	result = dvb_create_media_graph(&dvb->adapter, create_rf_connector);
+	if (result < 0)
+		goto fail_create_graph;
+
 	return 0;
 
+fail_create_graph:
+	dvb_net_release(&dvb->net);
 fail_fe_conn:
 	dvb->demux.dmx.remove_frontend(&dvb->demux.dmx, &dvb->fe_mem);
 fail_fe_mem:
@@ -1656,6 +1671,9 @@ static int em28xx_dvb_init(struct em28xx *dev)
 			memset(&si2157_config, 0, sizeof(si2157_config));
 			si2157_config.fe = dvb->fe[0];
 			si2157_config.if_port = 1;
+#ifdef CONFIG_MEDIA_CONTROLLER_DVB
+			si2157_config.mdev = dev->media_dev;
+#endif
 			memset(&info, 0, sizeof(struct i2c_board_info));
 			strlcpy(info.type, "si2157", I2C_NAME_SIZE);
 			info.addr = 0x60;
@@ -1717,6 +1735,9 @@ static int em28xx_dvb_init(struct em28xx *dev)
 			memset(&si2157_config, 0, sizeof(si2157_config));
 			si2157_config.fe = dvb->fe[0];
 			si2157_config.if_port = 0;
+#ifdef CONFIG_MEDIA_CONTROLLER_DVB
+			si2157_config.mdev = dev->media_dev;
+#endif
 			memset(&info, 0, sizeof(struct i2c_board_info));
 			strlcpy(info.type, "si2146", I2C_NAME_SIZE);
 			info.addr = 0x60;
diff --git a/drivers/media/usb/em28xx/em28xx-video.c b/drivers/media/usb/em28xx/em28xx-video.c
index 0e86ff423c49..44834b2eff55 100644
--- a/drivers/media/usb/em28xx/em28xx-video.c
+++ b/drivers/media/usb/em28xx/em28xx-video.c
@@ -196,7 +196,6 @@ static void em28xx_wake_i2c(struct em28xx *dev)
 	v4l2_device_call_all(v4l2_dev, 0, core,  reset, 0);
 	v4l2_device_call_all(v4l2_dev, 0, video, s_routing,
 			     INPUT(dev->ctl_input)->vmux, 0, 0);
-	v4l2_device_call_all(v4l2_dev, 0, video, s_stream, 0);
 }
 
 static int em28xx_colorlevels_set_default(struct em28xx *dev)
@@ -867,6 +866,147 @@ static void res_free(struct em28xx *dev, enum v4l2_buf_type f_type)
 	em28xx_videodbg("res: put %d\n", res_type);
 }
 
+static void em28xx_v4l2_media_release(struct em28xx *dev)
+{
+#ifdef CONFIG_MEDIA_CONTROLLER
+	int i;
+
+	for (i = 0; i < MAX_EM28XX_INPUT; i++) {
+		if (!INPUT(i)->type)
+			return;
+		media_device_unregister_entity(&dev->input_ent[i]);
+	}
+#endif
+}
+
+/*
+ * Media Controller helper functions
+ */
+
+static int em28xx_enable_analog_tuner(struct em28xx *dev)
+{
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct media_device *mdev = dev->media_dev;
+	struct em28xx_v4l2 *v4l2 = dev->v4l2;
+	struct media_entity *source;
+	struct media_link *link, *found_link = NULL;
+	int ret, active_links = 0;
+
+	if (!mdev || !v4l2->decoder)
+		return 0;
+
+	/*
+	 * This will find the tuner that is connected into the decoder.
+	 * Technically, this is not 100% correct, as the device may be
+	 * using an analog input instead of the tuner. However, as we can't
+	 * do DVB streaming while the DMA engine is being used for V4L2,
+	 * this should be enough for the actual needs.
+	 */
+	list_for_each_entry(link, &v4l2->decoder->links, list) {
+		if (link->sink->entity == v4l2->decoder) {
+			found_link = link;
+			if (link->flags & MEDIA_LNK_FL_ENABLED)
+				active_links++;
+			break;
+		}
+	}
+
+	if (active_links == 1 || !found_link)
+		return 0;
+
+	source = found_link->source->entity;
+	list_for_each_entry(link, &source->links, list) {
+		struct media_entity *sink;
+		int flags = 0;
+
+		sink = link->sink->entity;
+
+		if (sink == v4l2->decoder)
+			flags = MEDIA_LNK_FL_ENABLED;
+
+		ret = media_entity_setup_link(link, flags);
+		if (ret) {
+			pr_err("Couldn't change link %s->%s to %s. Error %d\n",
+			       source->name, sink->name,
+			       flags ? "enabled" : "disabled",
+			       ret);
+			return ret;
+		} else
+			em28xx_videodbg("link %s->%s was %s\n",
+					source->name, sink->name,
+					flags ? "ENABLED" : "disabled");
+	}
+#endif
+	return 0;
+}
+
+static const char * const iname[] = {
+	[EM28XX_VMUX_COMPOSITE]  = "Composite",
+	[EM28XX_VMUX_SVIDEO]     = "S-Video",
+	[EM28XX_VMUX_TELEVISION] = "Television",
+	[EM28XX_RADIO]           = "Radio",
+};
+
+static void em28xx_v4l2_create_entities(struct em28xx *dev)
+{
+#if defined(CONFIG_MEDIA_CONTROLLER)
+	struct em28xx_v4l2 *v4l2 = dev->v4l2;
+	int ret, i;
+
+	/* Initialize Video, VBI and Radio pads */
+	v4l2->video_pad.flags = MEDIA_PAD_FL_SINK;
+	ret = media_entity_pads_init(&v4l2->vdev.entity, 1, &v4l2->video_pad);
+	if (ret < 0)
+		pr_err("failed to initialize video media entity!\n");
+
+	if (em28xx_vbi_supported(dev)) {
+		v4l2->vbi_pad.flags = MEDIA_PAD_FL_SINK;
+		ret = media_entity_pads_init(&v4l2->vbi_dev.entity, 1,
+					     &v4l2->vbi_pad);
+		if (ret < 0)
+			pr_err("failed to initialize vbi media entity!\n");
+	}
+
+	/* Webcams don't have input connectors */
+	if (dev->board.is_webcam)
+		return;
+
+	/* Create entities for each input connector */
+	for (i = 0; i < MAX_EM28XX_INPUT; i++) {
+		struct media_entity *ent = &dev->input_ent[i];
+
+		if (!INPUT(i)->type)
+			break;
+
+		ent->name = iname[INPUT(i)->type];
+		ent->flags = MEDIA_ENT_FL_CONNECTOR;
+		dev->input_pad[i].flags = MEDIA_PAD_FL_SOURCE;
+
+		switch (INPUT(i)->type) {
+		case EM28XX_VMUX_COMPOSITE:
+			ent->function = MEDIA_ENT_F_CONN_COMPOSITE;
+			break;
+		case EM28XX_VMUX_SVIDEO:
+			ent->function = MEDIA_ENT_F_CONN_SVIDEO;
+			break;
+		default: /* EM28XX_VMUX_TELEVISION or EM28XX_RADIO */
+			if (dev->tuner_type != TUNER_ABSENT)
+				ent->function = MEDIA_ENT_F_CONN_RF;
+			break;
+		}
+
+		ret = media_entity_pads_init(ent, 1, &dev->input_pad[i]);
+		if (ret < 0)
+			pr_err("failed to initialize input pad[%d]!\n", i);
+
+		ret = media_device_register_entity(dev->media_dev, ent);
+		if (ret < 0)
+			pr_err("failed to register input entity %d!\n", i);
+	}
+#endif
+}
+
+
 /* ------------------------------------------------------------------
 	Videobuf2 operations
    ------------------------------------------------------------------*/
@@ -884,6 +1024,9 @@ static int queue_setup(struct vb2_queue *vq,
 		return sizes[0] < size ? -EINVAL : 0;
 	*nplanes = 1;
 	sizes[0] = size;
+
+	em28xx_enable_analog_tuner(dev);
+
 	return 0;
 }
 
@@ -962,6 +1105,9 @@ int em28xx_start_analog_streaming(struct vb2_queue *vq, unsigned int count)
 			f.type = V4L2_TUNER_ANALOG_TV;
 		v4l2_device_call_all(&v4l2->v4l2_dev,
 				     0, tuner, s_frequency, &f);
+
+		/* Enable video stream at TV decoder */
+		v4l2_device_call_all(&v4l2->v4l2_dev, 0, video, s_stream, 1);
 	}
 
 	v4l2->streaming_users++;
@@ -981,6 +1127,9 @@ static void em28xx_stop_streaming(struct vb2_queue *vq)
 	res_free(dev, vq->type);
 
 	if (v4l2->streaming_users-- == 1) {
+		/* Disable video stream at TV decoder */
+		v4l2_device_call_all(&v4l2->v4l2_dev, 0, video, s_stream, 0);
+
 		/* Last active user, so shutdown all the URBS */
 		em28xx_uninit_usb_xfer(dev, EM28XX_ANALOG_MODE);
 	}
@@ -1013,6 +1162,9 @@ void em28xx_stop_vbi_streaming(struct vb2_queue *vq)
 	res_free(dev, vq->type);
 
 	if (v4l2->streaming_users-- == 1) {
+		/* Disable video stream at TV decoder */
+		v4l2_device_call_all(&v4l2->v4l2_dev, 0, video, s_stream, 0);
+
 		/* Last active user, so shutdown all the URBS */
 		em28xx_uninit_usb_xfer(dev, EM28XX_ANALOG_MODE);
 	}
@@ -1224,6 +1376,12 @@ static void scale_to_size(struct em28xx *dev,
 
 	*width = (((unsigned long)maxw) << 12) / (hscale + 4096L);
 	*height = (((unsigned long)maxh) << 12) / (vscale + 4096L);
+
+	/* Don't let width or height to be zero */
+	if (*width < 1)
+		*width = 1;
+	if (*height < 1)
+		*height = 1;
 }
 
 /* ------------------------------------------------------------------
@@ -1299,6 +1457,11 @@ static int vidioc_try_fmt_vid_cap(struct file *file, void *priv,
 		v4l_bound_align_image(&width, 48, maxw, 1, &height, 32, maxh,
 				      1, 0);
 	}
+	/* Avoid division by zero at size_to_scale */
+	if (width < 1)
+		width = 1;
+	if (height < 1)
+		height = 1;
 
 	size_to_scale(dev, width, height, &hscale, &vscale);
 	scale_to_size(dev, hscale, vscale, &width, &height);
@@ -1434,18 +1597,6 @@ static int vidioc_s_parm(struct file *file, void *priv,
 					  0, video, s_parm, p);
 }
 
-static const char *iname[] = {
-	[EM28XX_VMUX_COMPOSITE1] = "Composite1",
-	[EM28XX_VMUX_COMPOSITE2] = "Composite2",
-	[EM28XX_VMUX_COMPOSITE3] = "Composite3",
-	[EM28XX_VMUX_COMPOSITE4] = "Composite4",
-	[EM28XX_VMUX_SVIDEO]     = "S-Video",
-	[EM28XX_VMUX_TELEVISION] = "Television",
-	[EM28XX_VMUX_CABLE]      = "Cable TV",
-	[EM28XX_VMUX_DVB]        = "DVB",
-	[EM28XX_VMUX_DEBUG]      = "for debug only",
-};
-
 static int vidioc_enum_input(struct file *file, void *priv,
 			     struct v4l2_input *i)
 {
@@ -1463,8 +1614,7 @@ static int vidioc_enum_input(struct file *file, void *priv,
 
 	strcpy(i->name, iname[INPUT(n)->type]);
 
-	if ((EM28XX_VMUX_TELEVISION == INPUT(n)->type) ||
-	    (EM28XX_VMUX_CABLE == INPUT(n)->type))
+	if ((EM28XX_VMUX_TELEVISION == INPUT(n)->type))
 		i->type = V4L2_INPUT_TYPE_TUNER;
 
 	i->std = dev->v4l2->vdev.tvnorms;
@@ -1961,6 +2111,8 @@ static int em28xx_v4l2_fini(struct em28xx *dev)
 
 	em28xx_uninit_usb_xfer(dev, EM28XX_ANALOG_MODE);
 
+	em28xx_v4l2_media_release(dev);
+
 	if (video_is_registered(&v4l2->radio_dev)) {
 		em28xx_info("V4L2 device %s deregistered\n",
 			    video_device_node_name(&v4l2->radio_dev));
@@ -2284,6 +2436,9 @@ static int em28xx_v4l2_init(struct em28xx *dev)
 	v4l2->dev = dev;
 	dev->v4l2 = v4l2;
 
+#ifdef CONFIG_MEDIA_CONTROLLER
+	v4l2->v4l2_dev.mdev = dev->media_dev;
+#endif
 	ret = v4l2_device_register(&dev->udev->dev, &v4l2->v4l2_dev);
 	if (ret < 0) {
 		em28xx_errdev("Call to v4l2_device_register() failed!\n");
@@ -2556,6 +2711,18 @@ static int em28xx_v4l2_init(struct em28xx *dev)
 			    video_device_node_name(&v4l2->radio_dev));
 	}
 
+	/* Init entities at the Media Controller */
+	em28xx_v4l2_create_entities(dev);
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+	ret = v4l2_mc_create_media_graph(dev->media_dev);
+	if (ret) {
+		em28xx_errdev("failed to create media graph\n");
+		em28xx_v4l2_media_release(dev);
+		goto unregister_dev;
+	}
+#endif
+
 	em28xx_info("V4L2 video device registered as %s\n",
 		    video_device_node_name(&v4l2->vdev));
 
@@ -2577,6 +2744,22 @@ static int em28xx_v4l2_init(struct em28xx *dev)
 	return 0;
 
 unregister_dev:
+	if (video_is_registered(&v4l2->radio_dev)) {
+		em28xx_info("V4L2 device %s deregistered\n",
+			    video_device_node_name(&v4l2->radio_dev));
+		video_unregister_device(&v4l2->radio_dev);
+	}
+	if (video_is_registered(&v4l2->vbi_dev)) {
+		em28xx_info("V4L2 device %s deregistered\n",
+			    video_device_node_name(&v4l2->vbi_dev));
+		video_unregister_device(&v4l2->vbi_dev);
+	}
+	if (video_is_registered(&v4l2->vdev)) {
+		em28xx_info("V4L2 device %s deregistered\n",
+			    video_device_node_name(&v4l2->vdev));
+		video_unregister_device(&v4l2->vdev);
+	}
+
 	v4l2_ctrl_handler_free(&v4l2->ctrl_handler);
 	v4l2_device_unregister(&v4l2->v4l2_dev);
 err:
diff --git a/drivers/media/usb/em28xx/em28xx.h b/drivers/media/usb/em28xx/em28xx.h
index 8ff066c977d9..267444961775 100644
--- a/drivers/media/usb/em28xx/em28xx.h
+++ b/drivers/media/usb/em28xx/em28xx.h
@@ -26,7 +26,7 @@
 #ifndef _EM28XX_H
 #define _EM28XX_H
 
-#define EM28XX_VERSION "0.2.1"
+#define EM28XX_VERSION "0.2.2"
 #define DRIVER_DESC    "Empia em28xx device driver"
 
 #include <linux/workqueue.h>
@@ -291,15 +291,9 @@ struct em28xx_dmaqueue {
 
 #define MAX_EM28XX_INPUT 4
 enum enum28xx_itype {
-	EM28XX_VMUX_COMPOSITE1 = 1,
-	EM28XX_VMUX_COMPOSITE2,
-	EM28XX_VMUX_COMPOSITE3,
-	EM28XX_VMUX_COMPOSITE4,
+	EM28XX_VMUX_COMPOSITE = 1,
 	EM28XX_VMUX_SVIDEO,
 	EM28XX_VMUX_TELEVISION,
-	EM28XX_VMUX_CABLE,
-	EM28XX_VMUX_DVB,
-	EM28XX_VMUX_DEBUG,
 	EM28XX_RADIO,
 };
 
@@ -558,6 +552,11 @@ struct em28xx_v4l2 {
 	bool top_field;
 	int vbi_read;
 	unsigned int field_count;
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct media_pad video_pad, vbi_pad;
+	struct media_entity *decoder;
+#endif
 };
 
 struct em28xx_audio {
@@ -718,6 +717,12 @@ struct em28xx {
 	/* Snapshot button input device */
 	char snapshot_button_path[30];	/* path of the input dev */
 	struct input_dev *sbutton_input_dev;
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct media_device *media_dev;
+	struct media_entity input_ent[MAX_EM28XX_INPUT];
+	struct media_pad input_pad[MAX_EM28XX_INPUT];
+#endif
 };
 
 #define kref_to_dev(d) container_of(d, struct em28xx, ref)
diff --git a/drivers/media/usb/go7007/go7007-priv.h b/drivers/media/usb/go7007/go7007-priv.h
index 745185eb060b..bebee8ca9981 100644
--- a/drivers/media/usb/go7007/go7007-priv.h
+++ b/drivers/media/usb/go7007/go7007-priv.h
@@ -250,7 +250,7 @@ struct go7007 {
 	struct i2c_adapter i2c_adapter;
 
 	/* HPI driver */
-	struct go7007_hpi_ops *hpi_ops;
+	const struct go7007_hpi_ops *hpi_ops;
 	void *hpi_context;
 	int interrupt_available;
 	wait_queue_head_t interrupt_waitq;
diff --git a/drivers/media/usb/go7007/go7007-usb.c b/drivers/media/usb/go7007/go7007-usb.c
index 3dbf14c85c5c..14d3f8c1ce4a 100644
--- a/drivers/media/usb/go7007/go7007-usb.c
+++ b/drivers/media/usb/go7007/go7007-usb.c
@@ -932,7 +932,7 @@ static void go7007_usb_release(struct go7007 *go)
 	kfree(go->hpi_context);
 }
 
-static struct go7007_hpi_ops go7007_usb_ezusb_hpi_ops = {
+static const struct go7007_hpi_ops go7007_usb_ezusb_hpi_ops = {
 	.interface_reset	= go7007_usb_interface_reset,
 	.write_interrupt	= go7007_usb_ezusb_write_interrupt,
 	.read_interrupt		= go7007_usb_read_interrupt,
@@ -942,7 +942,7 @@ static struct go7007_hpi_ops go7007_usb_ezusb_hpi_ops = {
 	.release		= go7007_usb_release,
 };
 
-static struct go7007_hpi_ops go7007_usb_onboard_hpi_ops = {
+static const struct go7007_hpi_ops go7007_usb_onboard_hpi_ops = {
 	.interface_reset	= go7007_usb_interface_reset,
 	.write_interrupt	= go7007_usb_onboard_write_interrupt,
 	.read_interrupt		= go7007_usb_read_interrupt,
diff --git a/drivers/media/usb/gspca/ov519.c b/drivers/media/usb/gspca/ov519.c
index c95f32a0c02b..965372a5ff2f 100644
--- a/drivers/media/usb/gspca/ov519.c
+++ b/drivers/media/usb/gspca/ov519.c
@@ -360,40 +360,6 @@ static const struct v4l2_pix_format ov511_sif_mode[] = {
 		.priv = 0},
 };
 
-static const struct v4l2_pix_format ovfx2_vga_mode[] = {
-	{320, 240, V4L2_PIX_FMT_SBGGR8, V4L2_FIELD_NONE,
-		.bytesperline = 320,
-		.sizeimage = 320 * 240,
-		.colorspace = V4L2_COLORSPACE_SRGB,
-		.priv = 1},
-	{640, 480, V4L2_PIX_FMT_SBGGR8, V4L2_FIELD_NONE,
-		.bytesperline = 640,
-		.sizeimage = 640 * 480,
-		.colorspace = V4L2_COLORSPACE_SRGB,
-		.priv = 0},
-};
-static const struct v4l2_pix_format ovfx2_cif_mode[] = {
-	{160, 120, V4L2_PIX_FMT_SBGGR8, V4L2_FIELD_NONE,
-		.bytesperline = 160,
-		.sizeimage = 160 * 120,
-		.colorspace = V4L2_COLORSPACE_SRGB,
-		.priv = 3},
-	{176, 144, V4L2_PIX_FMT_SBGGR8, V4L2_FIELD_NONE,
-		.bytesperline = 176,
-		.sizeimage = 176 * 144,
-		.colorspace = V4L2_COLORSPACE_SRGB,
-		.priv = 1},
-	{320, 240, V4L2_PIX_FMT_SBGGR8, V4L2_FIELD_NONE,
-		.bytesperline = 320,
-		.sizeimage = 320 * 240,
-		.colorspace = V4L2_COLORSPACE_SRGB,
-		.priv = 2},
-	{352, 288, V4L2_PIX_FMT_SBGGR8, V4L2_FIELD_NONE,
-		.bytesperline = 352,
-		.sizeimage = 352 * 288,
-		.colorspace = V4L2_COLORSPACE_SRGB,
-		.priv = 0},
-};
 static const struct v4l2_pix_format ovfx2_ov2610_mode[] = {
 	{800, 600, V4L2_PIX_FMT_SBGGR8, V4L2_FIELD_NONE,
 		.bytesperline = 800,
@@ -2042,6 +2008,9 @@ static void reg_w(struct sd *sd, u16 index, u16 value)
 	if (sd->gspca_dev.usb_err < 0)
 		return;
 
+	/* Avoid things going to fast for the bridge with a xhci host */
+	udelay(150);
+
 	switch (sd->bridge) {
 	case BRIDGE_OV511:
 	case BRIDGE_OV511PLUS:
@@ -2103,6 +2072,8 @@ static int reg_r(struct sd *sd, u16 index)
 		req = 1;
 	}
 
+	/* Avoid things going to fast for the bridge with a xhci host */
+	udelay(150);
 	ret = usb_control_msg(sd->gspca_dev.dev,
 			usb_rcvctrlpipe(sd->gspca_dev.dev, 0),
 			req,
@@ -2131,6 +2102,8 @@ static int reg_r8(struct sd *sd,
 	if (sd->gspca_dev.usb_err < 0)
 		return -1;
 
+	/* Avoid things going to fast for the bridge with a xhci host */
+	udelay(150);
 	ret = usb_control_msg(sd->gspca_dev.dev,
 			usb_rcvctrlpipe(sd->gspca_dev.dev, 0),
 			1,			/* REQ_IO */
@@ -2187,6 +2160,8 @@ static void ov518_reg_w32(struct sd *sd, u16 index, u32 value, int n)
 
 	*((__le32 *) sd->gspca_dev.usb_buf) = __cpu_to_le32(value);
 
+	/* Avoid things going to fast for the bridge with a xhci host */
+	udelay(150);
 	ret = usb_control_msg(sd->gspca_dev.dev,
 			usb_sndctrlpipe(sd->gspca_dev.dev, 0),
 			1 /* REG_IO */,
diff --git a/drivers/media/usb/gspca/touptek.c b/drivers/media/usb/gspca/touptek.c
index 7bac6bc96063..b8af4370d27c 100644
--- a/drivers/media/usb/gspca/touptek.c
+++ b/drivers/media/usb/gspca/touptek.c
@@ -203,7 +203,7 @@ static int val_reply(struct gspca_dev *gspca_dev, const char *reply, int rc)
 		return -EIO;
 	}
 	if (reply[0] != 0x08) {
-		PERR("Bad reply 0x%02X", reply[0]);
+		PERR("Bad reply 0x%02x", (int)reply[0]);
 		return -EIO;
 	}
 	return 0;
@@ -211,7 +211,7 @@ static int val_reply(struct gspca_dev *gspca_dev, const char *reply, int rc)
 
 static void reg_w(struct gspca_dev *gspca_dev, u16 value, u16 index)
 {
-	char buff[1];
+	char *buff = gspca_dev->usb_buf;
 	int rc;
 
 	PDEBUG(D_USBO,
@@ -219,7 +219,7 @@ static void reg_w(struct gspca_dev *gspca_dev, u16 value, u16 index)
 		value, index);
 	rc = usb_control_msg(gspca_dev->dev, usb_rcvctrlpipe(gspca_dev->dev, 0),
 		0x0B, 0xC0, value, index, buff, 1, 500);
-	PDEBUG(D_USBO, "rc=%d, ret={0x%02X}", rc, buff[0]);
+	PDEBUG(D_USBO, "rc=%d, ret={0x%02x}", rc, (int)buff[0]);
 	if (rc < 0) {
 		PERR("Failed reg_w(0x0B, 0xC0, 0x%04X, 0x%04X) w/ rc %d\n",
 			value, index, rc);
@@ -438,7 +438,7 @@ static void configure_encrypted(struct gspca_dev *gspca_dev)
 static int configure(struct gspca_dev *gspca_dev)
 {
 	int rc;
-	uint8_t buff[4];
+	char *buff = gspca_dev->usb_buf;
 
 	PDEBUG(D_STREAM, "configure()\n");
 
diff --git a/drivers/media/usb/gspca/w996Xcf.c b/drivers/media/usb/gspca/w996Xcf.c
index fb9fe2ef3a6f..896f1b2b9179 100644
--- a/drivers/media/usb/gspca/w996Xcf.c
+++ b/drivers/media/usb/gspca/w996Xcf.c
@@ -79,6 +79,8 @@ static void w9968cf_write_fsb(struct sd *sd, u16* data)
 	value = *data++;
 	memcpy(sd->gspca_dev.usb_buf, data, 6);
 
+	/* Avoid things going to fast for the bridge with a xhci host */
+	udelay(150);
 	ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0), 0,
 			      USB_TYPE_VENDOR | USB_DIR_OUT | USB_RECIP_DEVICE,
 			      value, 0x06, sd->gspca_dev.usb_buf, 6, 500);
@@ -99,6 +101,9 @@ static void w9968cf_write_sb(struct sd *sd, u16 value)
 	if (sd->gspca_dev.usb_err < 0)
 		return;
 
+	/* Avoid things going to fast for the bridge with a xhci host */
+	udelay(150);
+
 	/* We don't use reg_w here, as that would cause all writes when
 	   bitbanging i2c to be logged, making the logs impossible to read */
 	ret = usb_control_msg(sd->gspca_dev.dev,
@@ -126,6 +131,9 @@ static int w9968cf_read_sb(struct sd *sd)
 	if (sd->gspca_dev.usb_err < 0)
 		return -1;
 
+	/* Avoid things going to fast for the bridge with a xhci host */
+	udelay(150);
+
 	/* We don't use reg_r here, as the w9968cf is special and has 16
 	   bit registers instead of 8 bit */
 	ret = usb_control_msg(sd->gspca_dev.dev,
diff --git a/drivers/media/usb/hdpvr/hdpvr-core.c b/drivers/media/usb/hdpvr/hdpvr-core.c
index 3fc64197b4e6..08f0ca7aa012 100644
--- a/drivers/media/usb/hdpvr/hdpvr-core.c
+++ b/drivers/media/usb/hdpvr/hdpvr-core.c
@@ -273,7 +273,9 @@ static int hdpvr_probe(struct usb_interface *interface,
 	struct hdpvr_device *dev;
 	struct usb_host_interface *iface_desc;
 	struct usb_endpoint_descriptor *endpoint;
+#if IS_ENABLED(CONFIG_I2C)
 	struct i2c_client *client;
+#endif
 	size_t buffer_size;
 	int i;
 	int retval = -ENOMEM;
diff --git a/drivers/media/usb/hdpvr/hdpvr-video.c b/drivers/media/usb/hdpvr/hdpvr-video.c
index 7dee22deebf3..ba7f02270c83 100644
--- a/drivers/media/usb/hdpvr/hdpvr-video.c
+++ b/drivers/media/usb/hdpvr/hdpvr-video.c
@@ -462,10 +462,8 @@ static ssize_t hdpvr_read(struct file *file, char __user *buffer, size_t count,
 			}
 
 			if (wait_event_interruptible(dev->wait_data,
-					      buf->status == BUFSTAT_READY)) {
-				ret = -ERESTARTSYS;
-				goto err;
-			}
+					      buf->status == BUFSTAT_READY))
+				return -ERESTARTSYS;
 		}
 
 		if (buf->status != BUFSTAT_READY)
diff --git a/drivers/media/usb/msi2500/msi2500.c b/drivers/media/usb/msi2500/msi2500.c
index c104315fdc17..2d33033682af 100644
--- a/drivers/media/usb/msi2500/msi2500.c
+++ b/drivers/media/usb/msi2500/msi2500.c
@@ -839,8 +839,6 @@ static int msi2500_set_usb_adc(struct msi2500_dev *dev)
 		goto err;
 
 	ret = msi2500_ctrl_msg(dev, CMD_WREG, reg3);
-	if (ret)
-		goto err;
 err:
 	return ret;
 }
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-context.c b/drivers/media/usb/pvrusb2/pvrusb2-context.c
index fd888a604462..c45f30715dcd 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-context.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-context.c
@@ -196,7 +196,7 @@ int pvr2_context_global_init(void)
 	pvr2_context_thread_ptr = kthread_run(pvr2_context_thread_func,
 					      NULL,
 					      "pvrusb2-context");
-	return (pvr2_context_thread_ptr ? 0 : -ENOMEM);
+	return IS_ERR(pvr2_context_thread_ptr) ? -ENOMEM : 0;
 }
 
 
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-hdw.c b/drivers/media/usb/pvrusb2/pvrusb2-hdw.c
index 0533ef20decf..1a093e5953fd 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-hdw.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-hdw.c
@@ -4903,6 +4903,9 @@ static void pvr2_hdw_state_log_state(struct pvr2_hdw *hdw)
 		printk(KERN_INFO "%s %.*s\n",hdw->name,ccnt,buf);
 	}
 	ccnt = pvr2_hdw_report_clients(hdw, buf, sizeof(buf));
+	if (ccnt >= sizeof(buf))
+		ccnt = sizeof(buf);
+
 	ucnt = 0;
 	while (ucnt < ccnt) {
 		lcnt = 0;
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-io.c b/drivers/media/usb/pvrusb2/pvrusb2-io.c
index d860344de84e..e68ce24f27e3 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-io.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-io.c
@@ -473,7 +473,7 @@ static void buffer_complete(struct urb *urb)
 	}
 	spin_unlock_irqrestore(&sp->list_lock,irq_flags);
 	pvr2_buffer_set_ready(bp);
-	if (sp && sp->callback_func) {
+	if (sp->callback_func) {
 		sp->callback_func(sp->callback_data);
 	}
 }
diff --git a/drivers/media/usb/pwc/pwc-if.c b/drivers/media/usb/pwc/pwc-if.c
index 086cf1c7bd7d..18aed5dd325e 100644
--- a/drivers/media/usb/pwc/pwc-if.c
+++ b/drivers/media/usb/pwc/pwc-if.c
@@ -91,6 +91,7 @@ static const struct usb_device_id pwc_device_table [] = {
 	{ USB_DEVICE(0x0471, 0x0312) },
 	{ USB_DEVICE(0x0471, 0x0313) }, /* the 'new' 720K */
 	{ USB_DEVICE(0x0471, 0x0329) }, /* Philips SPC 900NC PC Camera */
+	{ USB_DEVICE(0x0471, 0x032C) }, /* Philips SPC 880NC PC Camera */
 	{ USB_DEVICE(0x069A, 0x0001) }, /* Askey */
 	{ USB_DEVICE(0x046D, 0x08B0) }, /* Logitech QuickCam Pro 3000 */
 	{ USB_DEVICE(0x046D, 0x08B1) }, /* Logitech QuickCam Notebook Pro */
@@ -810,6 +811,11 @@ static int usb_pwc_probe(struct usb_interface *intf, const struct usb_device_id
 			name = "Philips SPC 900NC webcam";
 			type_id = 740;
 			break;
+		case 0x032C:
+			PWC_INFO("Philips SPC 880NC USB webcam detected.\n");
+			name = "Philips SPC 880NC webcam";
+			type_id = 740;
+			break;
 		default:
 			return -ENODEV;
 			break;
diff --git a/drivers/media/usb/siano/smsusb.c b/drivers/media/usb/siano/smsusb.c
index 8abbd3cc8eba..c2e25876e93b 100644
--- a/drivers/media/usb/siano/smsusb.c
+++ b/drivers/media/usb/siano/smsusb.c
@@ -27,6 +27,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 #include <linux/firmware.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <media/media-device.h>
 
 #include "sms-cards.h"
 #include "smsendian.h"
@@ -51,6 +52,9 @@ struct smsusb_urb_t {
 	struct smsusb_device_t *dev;
 
 	struct urb urb;
+
+	/* For the bottom half */
+	struct work_struct wq;
 };
 
 struct smsusb_device_t {
@@ -71,6 +75,18 @@ static int smsusb_submit_urb(struct smsusb_device_t *dev,
 			     struct smsusb_urb_t *surb);
 
 /**
+ * Completing URB's callback handler - bottom half (proccess context)
+ * submits the URB prepared on smsusb_onresponse()
+ */
+static void do_submit_urb(struct work_struct *work)
+{
+	struct smsusb_urb_t *surb = container_of(work, struct smsusb_urb_t, wq);
+	struct smsusb_device_t *dev = surb->dev;
+
+	smsusb_submit_urb(dev, surb);
+}
+
+/**
  * Completing URB's callback handler - top half (interrupt context)
  * adds completing sms urb to the global surbs list and activtes the worker
  * thread the surb
@@ -138,13 +154,15 @@ static void smsusb_onresponse(struct urb *urb)
 
 
 exit_and_resubmit:
-	smsusb_submit_urb(dev, surb);
+	INIT_WORK(&surb->wq, do_submit_urb);
+	schedule_work(&surb->wq);
 }
 
 static int smsusb_submit_urb(struct smsusb_device_t *dev,
 			     struct smsusb_urb_t *surb)
 {
 	if (!surb->cb) {
+		/* This function can sleep */
 		surb->cb = smscore_getbuffer(dev->coredev);
 		if (!surb->cb) {
 			pr_err("smscore_getbuffer(...) returned NULL\n");
@@ -353,15 +371,7 @@ static void *siano_media_device_register(struct smsusb_device_t *dev,
 	if (!mdev)
 		return NULL;
 
-	mdev->dev = &udev->dev;
-	strlcpy(mdev->model, board->name, sizeof(mdev->model));
-	if (udev->serial)
-		strlcpy(mdev->serial, udev->serial, sizeof(mdev->serial));
-	strcpy(mdev->bus_info, udev->devpath);
-	mdev->hw_revision = le16_to_cpu(udev->descriptor.bcdDevice);
-	mdev->driver_version = LINUX_VERSION_CODE;
-
-	media_device_init(mdev);
+	media_device_usb_init(mdev, udev, board->name);
 
 	ret = media_device_register(mdev);
 	if (ret) {
diff --git a/drivers/media/usb/stk1160/stk1160-video.c b/drivers/media/usb/stk1160/stk1160-video.c
index 46191d5262eb..6ecb0b48423f 100644
--- a/drivers/media/usb/stk1160/stk1160-video.c
+++ b/drivers/media/usb/stk1160/stk1160-video.c
@@ -98,7 +98,6 @@ void stk1160_buffer_done(struct stk1160 *dev)
 
 	buf->vb.sequence = dev->sequence++;
 	buf->vb.field = V4L2_FIELD_INTERLACED;
-	buf->vb.vb2_buf.planes[0].bytesused = buf->bytesused;
 	buf->vb.vb2_buf.timestamp = ktime_get_ns();
 
 	vb2_set_plane_payload(&buf->vb.vb2_buf, 0, buf->bytesused);
diff --git a/drivers/media/usb/usbtv/usbtv-video.c b/drivers/media/usb/usbtv/usbtv-video.c
index 4ebb33943f9a..f6cfad46547e 100644
--- a/drivers/media/usb/usbtv/usbtv-video.c
+++ b/drivers/media/usb/usbtv/usbtv-video.c
@@ -312,20 +312,24 @@ static void usbtv_image_chunk(struct usbtv *usbtv, __be32 *chunk)
 	usbtv_chunk_to_vbuf(frame, &chunk[1], chunk_no, odd);
 	usbtv->chunks_done++;
 
-	/* Last chunk in a frame, signalling an end */
-	if (odd && chunk_no == usbtv->n_chunks-1) {
-		int size = vb2_plane_size(&buf->vb.vb2_buf, 0);
-		enum vb2_buffer_state state = usbtv->chunks_done ==
-						usbtv->n_chunks ?
-						VB2_BUF_STATE_DONE :
-						VB2_BUF_STATE_ERROR;
-
-		buf->vb.field = V4L2_FIELD_INTERLACED;
-		buf->vb.sequence = usbtv->sequence++;
-		buf->vb.vb2_buf.timestamp = ktime_get_ns();
-		vb2_set_plane_payload(&buf->vb.vb2_buf, 0, size);
-		vb2_buffer_done(&buf->vb.vb2_buf, state);
-		list_del(&buf->list);
+	/* Last chunk in a field */
+	if (chunk_no == usbtv->n_chunks-1) {
+		/* Last chunk in a frame, signalling an end */
+		if (odd && !usbtv->last_odd) {
+			int size = vb2_plane_size(&buf->vb.vb2_buf, 0);
+			enum vb2_buffer_state state = usbtv->chunks_done ==
+				usbtv->n_chunks ?
+				VB2_BUF_STATE_DONE :
+				VB2_BUF_STATE_ERROR;
+
+			buf->vb.field = V4L2_FIELD_INTERLACED;
+			buf->vb.sequence = usbtv->sequence++;
+			buf->vb.vb2_buf.timestamp = ktime_get_ns();
+			vb2_set_plane_payload(&buf->vb.vb2_buf, 0, size);
+			vb2_buffer_done(&buf->vb.vb2_buf, state);
+			list_del(&buf->list);
+		}
+		usbtv->last_odd = odd;
 	}
 
 	spin_unlock_irqrestore(&usbtv->buflock, flags);
@@ -389,6 +393,10 @@ static struct urb *usbtv_setup_iso_transfer(struct usbtv *usbtv)
 	ip->transfer_flags = URB_ISO_ASAP;
 	ip->transfer_buffer = kzalloc(size * USBTV_ISOC_PACKETS,
 						GFP_KERNEL);
+	if (!ip->transfer_buffer) {
+		usb_free_urb(ip);
+		return NULL;
+	}
 	ip->complete = usbtv_iso_cb;
 	ip->number_of_packets = USBTV_ISOC_PACKETS;
 	ip->transfer_buffer_length = size * USBTV_ISOC_PACKETS;
@@ -639,6 +647,7 @@ static int usbtv_start_streaming(struct vb2_queue *vq, unsigned int count)
 	if (usbtv->udev == NULL)
 		return -ENODEV;
 
+	usbtv->last_odd = 1;
 	usbtv->sequence = 0;
 	return usbtv_start(usbtv);
 }
diff --git a/drivers/media/usb/usbtv/usbtv.h b/drivers/media/usb/usbtv/usbtv.h
index 19cb8bf7c4e9..161b38d5cfa0 100644
--- a/drivers/media/usb/usbtv/usbtv.h
+++ b/drivers/media/usb/usbtv/usbtv.h
@@ -95,6 +95,7 @@ struct usbtv {
 	int width, height;
 	int n_chunks;
 	int iso_size;
+	int last_odd;
 	unsigned int sequence;
 	struct urb *isoc_urbs[USBTV_ISOC_TRANSFERS];
 
diff --git a/drivers/media/usb/usbvision/usbvision-video.c b/drivers/media/usb/usbvision/usbvision-video.c
index de9ff3bb8edd..12f5ebbd0436 100644
--- a/drivers/media/usb/usbvision/usbvision-video.c
+++ b/drivers/media/usb/usbvision/usbvision-video.c
@@ -162,8 +162,7 @@ MODULE_ALIAS(DRIVER_ALIAS);
 
 static inline struct usb_usbvision *cd_to_usbvision(struct device *cd)
 {
-	struct video_device *vdev =
-		container_of(cd, struct video_device, dev);
+	struct video_device *vdev = to_video_device(cd);
 	return video_get_drvdata(vdev);
 }
 
@@ -177,8 +176,7 @@ static DEVICE_ATTR(version, S_IRUGO, show_version, NULL);
 static ssize_t show_model(struct device *cd,
 			  struct device_attribute *attr, char *buf)
 {
-	struct video_device *vdev =
-		container_of(cd, struct video_device, dev);
+	struct video_device *vdev = to_video_device(cd);
 	struct usb_usbvision *usbvision = video_get_drvdata(vdev);
 	return sprintf(buf, "%s\n",
 		       usbvision_device_data[usbvision->dev_model].model_string);
@@ -188,8 +186,7 @@ static DEVICE_ATTR(model, S_IRUGO, show_model, NULL);
 static ssize_t show_hue(struct device *cd,
 			struct device_attribute *attr, char *buf)
 {
-	struct video_device *vdev =
-		container_of(cd, struct video_device, dev);
+	struct video_device *vdev = to_video_device(cd);
 	struct usb_usbvision *usbvision = video_get_drvdata(vdev);
 	struct v4l2_control ctrl;
 	ctrl.id = V4L2_CID_HUE;
@@ -203,8 +200,7 @@ static DEVICE_ATTR(hue, S_IRUGO, show_hue, NULL);
 static ssize_t show_contrast(struct device *cd,
 			     struct device_attribute *attr, char *buf)
 {
-	struct video_device *vdev =
-		container_of(cd, struct video_device, dev);
+	struct video_device *vdev = to_video_device(cd);
 	struct usb_usbvision *usbvision = video_get_drvdata(vdev);
 	struct v4l2_control ctrl;
 	ctrl.id = V4L2_CID_CONTRAST;
@@ -218,8 +214,7 @@ static DEVICE_ATTR(contrast, S_IRUGO, show_contrast, NULL);
 static ssize_t show_brightness(struct device *cd,
 			       struct device_attribute *attr, char *buf)
 {
-	struct video_device *vdev =
-		container_of(cd, struct video_device, dev);
+	struct video_device *vdev = to_video_device(cd);
 	struct usb_usbvision *usbvision = video_get_drvdata(vdev);
 	struct v4l2_control ctrl;
 	ctrl.id = V4L2_CID_BRIGHTNESS;
@@ -233,8 +228,7 @@ static DEVICE_ATTR(brightness, S_IRUGO, show_brightness, NULL);
 static ssize_t show_saturation(struct device *cd,
 			       struct device_attribute *attr, char *buf)
 {
-	struct video_device *vdev =
-		container_of(cd, struct video_device, dev);
+	struct video_device *vdev = to_video_device(cd);
 	struct usb_usbvision *usbvision = video_get_drvdata(vdev);
 	struct v4l2_control ctrl;
 	ctrl.id = V4L2_CID_SATURATION;
@@ -248,8 +242,7 @@ static DEVICE_ATTR(saturation, S_IRUGO, show_saturation, NULL);
 static ssize_t show_streaming(struct device *cd,
 			      struct device_attribute *attr, char *buf)
 {
-	struct video_device *vdev =
-		container_of(cd, struct video_device, dev);
+	struct video_device *vdev = to_video_device(cd);
 	struct usb_usbvision *usbvision = video_get_drvdata(vdev);
 	return sprintf(buf, "%s\n",
 		       YES_NO(usbvision->streaming == stream_on ? 1 : 0));
@@ -259,8 +252,7 @@ static DEVICE_ATTR(streaming, S_IRUGO, show_streaming, NULL);
 static ssize_t show_compression(struct device *cd,
 				struct device_attribute *attr, char *buf)
 {
-	struct video_device *vdev =
-		container_of(cd, struct video_device, dev);
+	struct video_device *vdev = to_video_device(cd);
 	struct usb_usbvision *usbvision = video_get_drvdata(vdev);
 	return sprintf(buf, "%s\n",
 		       YES_NO(usbvision->isoc_mode == ISOC_MODE_COMPRESS));
@@ -270,8 +262,7 @@ static DEVICE_ATTR(compression, S_IRUGO, show_compression, NULL);
 static ssize_t show_device_bridge(struct device *cd,
 				  struct device_attribute *attr, char *buf)
 {
-	struct video_device *vdev =
-		container_of(cd, struct video_device, dev);
+	struct video_device *vdev = to_video_device(cd);
 	struct usb_usbvision *usbvision = video_get_drvdata(vdev);
 	return sprintf(buf, "%d\n", usbvision->bridge_type);
 }
@@ -1156,6 +1147,7 @@ static int usbvision_radio_close(struct file *file)
 	usbvision_audio_off(usbvision);
 	usbvision->radio = 0;
 	usbvision->user--;
+	mutex_unlock(&usbvision->v4l2_lock);
 
 	if (usbvision->remove_pending) {
 		printk(KERN_INFO "%s: Final disconnect\n", __func__);
@@ -1164,7 +1156,6 @@ static int usbvision_radio_close(struct file *file)
 		return 0;
 	}
 
-	mutex_unlock(&usbvision->v4l2_lock);
 	PDEBUG(DBG_IO, "success");
 	return v4l2_fh_release(file);
 }
diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index 4e7148815a78..451e84e962e2 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -148,6 +148,26 @@ static struct uvc_format_desc uvc_fmts[] = {
 		.guid		= UVC_GUID_FORMAT_H264,
 		.fcc		= V4L2_PIX_FMT_H264,
 	},
+	{
+		.name		= "Greyscale 8 L/R (Y8I)",
+		.guid		= UVC_GUID_FORMAT_Y8I,
+		.fcc		= V4L2_PIX_FMT_Y8I,
+	},
+	{
+		.name		= "Greyscale 12 L/R (Y12I)",
+		.guid		= UVC_GUID_FORMAT_Y12I,
+		.fcc		= V4L2_PIX_FMT_Y12I,
+	},
+	{
+		.name		= "Depth data 16-bit (Z16)",
+		.guid		= UVC_GUID_FORMAT_Z16,
+		.fcc		= V4L2_PIX_FMT_Z16,
+	},
+	{
+		.name		= "Bayer 10-bit (SRGGB10P)",
+		.guid		= UVC_GUID_FORMAT_RW10,
+		.fcc		= V4L2_PIX_FMT_SRGGB10P,
+	},
 };
 
 /* ------------------------------------------------------------------------
diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h
index f0f2391e1b43..7e4d3eea371b 100644
--- a/drivers/media/usb/uvc/uvcvideo.h
+++ b/drivers/media/usb/uvc/uvcvideo.h
@@ -119,6 +119,18 @@
 #define UVC_GUID_FORMAT_H264 \
 	{ 'H',  '2',  '6',  '4', 0x00, 0x00, 0x10, 0x00, \
 	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
+#define UVC_GUID_FORMAT_Y8I \
+	{ 'Y',  '8',  'I',  ' ', 0x00, 0x00, 0x10, 0x00, \
+	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
+#define UVC_GUID_FORMAT_Y12I \
+	{ 'Y',  '1',  '2',  'I', 0x00, 0x00, 0x10, 0x00, \
+	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
+#define UVC_GUID_FORMAT_Z16 \
+	{ 'Z',  '1',  '6',  ' ', 0x00, 0x00, 0x10, 0x00, \
+	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
+#define UVC_GUID_FORMAT_RW10 \
+	{ 'R',  'W',  '1',  '0', 0x00, 0x00, 0x10, 0x00, \
+	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
 
 /* ------------------------------------------------------------------------
  * Driver specific constants.
diff --git a/drivers/media/v4l2-core/Kconfig b/drivers/media/v4l2-core/Kconfig
index 9beece00869b..29b3436d0910 100644
--- a/drivers/media/v4l2-core/Kconfig
+++ b/drivers/media/v4l2-core/Kconfig
@@ -37,7 +37,6 @@ config VIDEO_PCI_SKELETON
 # Used by drivers that need tuner.ko
 config VIDEO_TUNER
 	tristate
-	depends on MEDIA_TUNER
 
 # Used by drivers that need v4l2-mem2mem.ko
 config V4L2_MEM2MEM_DEV
diff --git a/drivers/media/v4l2-core/Makefile b/drivers/media/v4l2-core/Makefile
index 1dc8bba2b198..795a5352761d 100644
--- a/drivers/media/v4l2-core/Makefile
+++ b/drivers/media/v4l2-core/Makefile
@@ -16,6 +16,7 @@ endif
 ifeq ($(CONFIG_TRACEPOINTS),y)
   videodev-objs += vb2-trace.o v4l2-trace.o
 endif
+videodev-$(CONFIG_MEDIA_CONTROLLER) += v4l2-mc.o
 
 obj-$(CONFIG_VIDEO_V4L2) += videodev.o
 obj-$(CONFIG_VIDEO_V4L2) += v4l2-common.o
diff --git a/drivers/media/v4l2-core/tuner-core.c b/drivers/media/v4l2-core/tuner-core.c
index 76496fd282aa..731487be5baa 100644
--- a/drivers/media/v4l2-core/tuner-core.c
+++ b/drivers/media/v4l2-core/tuner-core.c
@@ -696,16 +696,32 @@ static int tuner_probe(struct i2c_client *client,
 	/* Should be just before return */
 register_client:
 #if defined(CONFIG_MEDIA_CONTROLLER)
-	t->pad[TUNER_PAD_RF_INPUT].flags = MEDIA_PAD_FL_SINK;
-	t->pad[TUNER_PAD_IF_OUTPUT].flags = MEDIA_PAD_FL_SOURCE;
-	t->sd.entity.function = MEDIA_ENT_F_TUNER;
 	t->sd.entity.name = t->name;
+	/*
+	 * Handle the special case where the tuner has actually
+	 * two stages: the PLL to tune into a frequency and the
+	 * IF-PLL demodulator (tda988x).
+	 */
+	if (t->type == TUNER_TDA9887) {
+		t->pad[IF_VID_DEC_PAD_IF_INPUT].flags = MEDIA_PAD_FL_SINK;
+		t->pad[IF_VID_DEC_PAD_OUT].flags = MEDIA_PAD_FL_SOURCE;
+		ret = media_entity_pads_init(&t->sd.entity,
+					     IF_VID_DEC_PAD_NUM_PADS,
+					     &t->pad[0]);
+		t->sd.entity.function = MEDIA_ENT_F_IF_VID_DECODER;
+	} else {
+		t->pad[TUNER_PAD_RF_INPUT].flags = MEDIA_PAD_FL_SINK;
+		t->pad[TUNER_PAD_OUTPUT].flags = MEDIA_PAD_FL_SOURCE;
+		t->pad[TUNER_PAD_AUD_OUT].flags = MEDIA_PAD_FL_SOURCE;
+		ret = media_entity_pads_init(&t->sd.entity, TUNER_NUM_PADS,
+					     &t->pad[0]);
+		t->sd.entity.function = MEDIA_ENT_F_TUNER;
+	}
 
-	ret = media_entity_pads_init(&t->sd.entity, TUNER_NUM_PADS, &t->pad[0]);
 	if (ret < 0) {
 		tuner_err("failed to initialize media entity!\n");
 		kfree(t);
-		return -ENODEV;
+		return ret;
 	}
 #endif
 	/* Sets a default mode */
diff --git a/drivers/media/v4l2-core/v4l2-async.c b/drivers/media/v4l2-core/v4l2-async.c
index 5bada202b2d3..a4b224d92572 100644
--- a/drivers/media/v4l2-core/v4l2-async.c
+++ b/drivers/media/v4l2-core/v4l2-async.c
@@ -119,6 +119,13 @@ static int v4l2_async_test_notify(struct v4l2_async_notifier *notifier,
 		return ret;
 	}
 
+	ret = v4l2_subdev_call(sd, core, registered_async);
+	if (ret < 0 && ret != -ENOIOCTLCMD) {
+		if (notifier->unbind)
+			notifier->unbind(notifier, sd, asd);
+		return ret;
+	}
+
 	if (list_empty(&notifier->waiting) && notifier->complete)
 		return notifier->complete(notifier);
 
diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
index 8fd84a67478a..019644ff627d 100644
--- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
+++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
@@ -415,7 +415,8 @@ static int get_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user
 		get_user(kp->index, &up->index) ||
 		get_user(kp->type, &up->type) ||
 		get_user(kp->flags, &up->flags) ||
-		get_user(kp->memory, &up->memory))
+		get_user(kp->memory, &up->memory) ||
+		get_user(kp->length, &up->length))
 			return -EFAULT;
 
 	if (V4L2_TYPE_IS_OUTPUT(kp->type))
@@ -427,9 +428,6 @@ static int get_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user
 			return -EFAULT;
 
 	if (V4L2_TYPE_IS_MULTIPLANAR(kp->type)) {
-		if (get_user(kp->length, &up->length))
-			return -EFAULT;
-
 		num_planes = kp->length;
 		if (num_planes == 0) {
 			kp->m.planes = NULL;
@@ -462,16 +460,14 @@ static int get_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user
 	} else {
 		switch (kp->memory) {
 		case V4L2_MEMORY_MMAP:
-			if (get_user(kp->length, &up->length) ||
-				get_user(kp->m.offset, &up->m.offset))
+			if (get_user(kp->m.offset, &up->m.offset))
 				return -EFAULT;
 			break;
 		case V4L2_MEMORY_USERPTR:
 			{
 			compat_long_t tmp;
 
-			if (get_user(kp->length, &up->length) ||
-			    get_user(tmp, &up->m.userptr))
+			if (get_user(tmp, &up->m.userptr))
 				return -EFAULT;
 
 			kp->m.userptr = (unsigned long)compat_ptr(tmp);
@@ -513,7 +509,8 @@ static int put_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user
 		copy_to_user(&up->timecode, &kp->timecode, sizeof(struct v4l2_timecode)) ||
 		put_user(kp->sequence, &up->sequence) ||
 		put_user(kp->reserved2, &up->reserved2) ||
-		put_user(kp->reserved, &up->reserved))
+		put_user(kp->reserved, &up->reserved) ||
+		put_user(kp->length, &up->length))
 			return -EFAULT;
 
 	if (V4L2_TYPE_IS_MULTIPLANAR(kp->type)) {
@@ -536,13 +533,11 @@ static int put_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user
 	} else {
 		switch (kp->memory) {
 		case V4L2_MEMORY_MMAP:
-			if (put_user(kp->length, &up->length) ||
-				put_user(kp->m.offset, &up->m.offset))
+			if (put_user(kp->m.offset, &up->m.offset))
 				return -EFAULT;
 			break;
 		case V4L2_MEMORY_USERPTR:
-			if (put_user(kp->length, &up->length) ||
-				put_user(kp->m.userptr, &up->m.userptr))
+			if (put_user(kp->m.userptr, &up->m.userptr))
 				return -EFAULT;
 			break;
 		case V4L2_MEMORY_OVERLAY:
diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index c9d5537b6af7..8b321e0aae62 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -462,6 +462,14 @@ const char * const *v4l2_ctrl_get_menu(u32 id)
 		"RGB full range (0-255)",
 		NULL,
 	};
+	static const char * const dv_it_content_type[] = {
+		"Graphics",
+		"Photo",
+		"Cinema",
+		"Game",
+		"No IT Content",
+		NULL,
+	};
 	static const char * const detect_md_mode[] = {
 		"Disabled",
 		"Global",
@@ -560,6 +568,9 @@ const char * const *v4l2_ctrl_get_menu(u32 id)
 	case V4L2_CID_DV_TX_RGB_RANGE:
 	case V4L2_CID_DV_RX_RGB_RANGE:
 		return dv_rgb_range;
+	case V4L2_CID_DV_TX_IT_CONTENT_TYPE:
+	case V4L2_CID_DV_RX_IT_CONTENT_TYPE:
+		return dv_it_content_type;
 	case V4L2_CID_DETECT_MD_MODE:
 		return detect_md_mode;
 
@@ -747,6 +758,7 @@ const char *v4l2_ctrl_get_name(u32 id)
 	case V4L2_CID_MPEG_VIDEO_MV_H_SEARCH_RANGE:		return "Horizontal MV Search Range";
 	case V4L2_CID_MPEG_VIDEO_MV_V_SEARCH_RANGE:		return "Vertical MV Search Range";
 	case V4L2_CID_MPEG_VIDEO_REPEAT_SEQ_HEADER:		return "Repeat Sequence Header";
+	case V4L2_CID_MPEG_VIDEO_FORCE_KEY_FRAME:		return "Force Key Frame";
 
 	/* VPX controls */
 	case V4L2_CID_MPEG_VIDEO_VPX_NUM_PARTITIONS:		return "VPX Number of Partitions";
@@ -881,8 +893,10 @@ const char *v4l2_ctrl_get_name(u32 id)
 	case V4L2_CID_DV_TX_EDID_PRESENT:	return "EDID Present";
 	case V4L2_CID_DV_TX_MODE:		return "Transmit Mode";
 	case V4L2_CID_DV_TX_RGB_RANGE:		return "Tx RGB Quantization Range";
+	case V4L2_CID_DV_TX_IT_CONTENT_TYPE:	return "Tx IT Content Type";
 	case V4L2_CID_DV_RX_POWER_PRESENT:	return "Power Present";
 	case V4L2_CID_DV_RX_RGB_RANGE:		return "Rx RGB Quantization Range";
+	case V4L2_CID_DV_RX_IT_CONTENT_TYPE:	return "Rx IT Content Type";
 
 	case V4L2_CID_FM_RX_CLASS:		return "FM Radio Receiver Controls";
 	case V4L2_CID_TUNE_DEEMPHASIS:		return "De-Emphasis";
@@ -985,6 +999,7 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type,
 	case V4L2_CID_MPEG_VIDEO_MV_V_SEARCH_RANGE:
 		*type = V4L2_CTRL_TYPE_INTEGER;
 		break;
+	case V4L2_CID_MPEG_VIDEO_FORCE_KEY_FRAME:
 	case V4L2_CID_PAN_RESET:
 	case V4L2_CID_TILT_RESET:
 	case V4L2_CID_FLASH_STROBE:
@@ -1038,7 +1053,9 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type,
 	case V4L2_CID_SCENE_MODE:
 	case V4L2_CID_DV_TX_MODE:
 	case V4L2_CID_DV_TX_RGB_RANGE:
+	case V4L2_CID_DV_TX_IT_CONTENT_TYPE:
 	case V4L2_CID_DV_RX_RGB_RANGE:
+	case V4L2_CID_DV_RX_IT_CONTENT_TYPE:
 	case V4L2_CID_TEST_PATTERN:
 	case V4L2_CID_TUNE_DEEMPHASIS:
 	case V4L2_CID_MPEG_VIDEO_VPX_GOLDEN_FRAME_SEL:
@@ -1185,6 +1202,7 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type,
 	case V4L2_CID_DV_TX_RXSENSE:
 	case V4L2_CID_DV_TX_EDID_PRESENT:
 	case V4L2_CID_DV_RX_POWER_PRESENT:
+	case V4L2_CID_DV_RX_IT_CONTENT_TYPE:
 	case V4L2_CID_RDS_RX_PTY:
 	case V4L2_CID_RDS_RX_PS_NAME:
 	case V4L2_CID_RDS_RX_RADIO_TEXT:
@@ -2211,22 +2229,6 @@ struct v4l2_ctrl *v4l2_ctrl_new_int_menu(struct v4l2_ctrl_handler *hdl,
 }
 EXPORT_SYMBOL(v4l2_ctrl_new_int_menu);
 
-/* Add a control from another handler to this handler */
-struct v4l2_ctrl *v4l2_ctrl_add_ctrl(struct v4l2_ctrl_handler *hdl,
-					  struct v4l2_ctrl *ctrl)
-{
-	if (hdl == NULL || hdl->error)
-		return NULL;
-	if (ctrl == NULL) {
-		handler_set_err(hdl, -EINVAL);
-		return NULL;
-	}
-	if (ctrl->handler == hdl)
-		return ctrl;
-	return handler_new_ref(hdl, ctrl) ? NULL : ctrl;
-}
-EXPORT_SYMBOL(v4l2_ctrl_add_ctrl);
-
 /* Add the controls from another handler to our own. */
 int v4l2_ctrl_add_handler(struct v4l2_ctrl_handler *hdl,
 			  struct v4l2_ctrl_handler *add,
diff --git a/drivers/media/v4l2-core/v4l2-dv-timings.c b/drivers/media/v4l2-core/v4l2-dv-timings.c
index ec258b73001a..889de0a32152 100644
--- a/drivers/media/v4l2-core/v4l2-dv-timings.c
+++ b/drivers/media/v4l2-core/v4l2-dv-timings.c
@@ -165,7 +165,8 @@ bool v4l2_valid_dv_timings(const struct v4l2_dv_timings *t,
 	    bt->width > cap->max_width ||
 	    bt->pixelclock < cap->min_pixelclock ||
 	    bt->pixelclock > cap->max_pixelclock ||
-	    (cap->standards && bt->standards &&
+	    (!(caps & V4L2_DV_BT_CAP_CUSTOM) &&
+	     cap->standards && bt->standards &&
 	     !(bt->standards & cap->standards)) ||
 	    (bt->interlaced && !(caps & V4L2_DV_BT_CAP_INTERLACED)) ||
 	    (!bt->interlaced && !(caps & V4L2_DV_BT_CAP_PROGRESSIVE)))
diff --git a/drivers/media/v4l2-core/v4l2-fh.c b/drivers/media/v4l2-core/v4l2-fh.c
index c97067a25bd2..c183f0996fa1 100644
--- a/drivers/media/v4l2-core/v4l2-fh.c
+++ b/drivers/media/v4l2-core/v4l2-fh.c
@@ -29,6 +29,7 @@
 #include <media/v4l2-fh.h>
 #include <media/v4l2-event.h>
 #include <media/v4l2-ioctl.h>
+#include <media/v4l2-mc.h>
 
 void v4l2_fh_init(struct v4l2_fh *fh, struct video_device *vdev)
 {
@@ -92,6 +93,7 @@ void v4l2_fh_exit(struct v4l2_fh *fh)
 {
 	if (fh->vdev == NULL)
 		return;
+	v4l_disable_media_source(fh->vdev);
 	v4l2_event_unsubscribe_all(fh);
 	fh->vdev = NULL;
 }
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index 8a018c6dd16a..170dd68d27f4 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -27,6 +27,7 @@
 #include <media/v4l2-event.h>
 #include <media/v4l2-device.h>
 #include <media/videobuf2-v4l2.h>
+#include <media/v4l2-mc.h>
 
 #include <trace/events/v4l2.h>
 
@@ -1041,6 +1042,12 @@ static int v4l_querycap(const struct v4l2_ioctl_ops *ops,
 static int v4l_s_input(const struct v4l2_ioctl_ops *ops,
 				struct file *file, void *fh, void *arg)
 {
+	struct video_device *vfd = video_devdata(file);
+	int ret;
+
+	ret = v4l_enable_media_source(vfd);
+	if (ret)
+		return ret;
 	return ops->vidioc_s_input(file, fh, *(unsigned int *)arg);
 }
 
@@ -1165,7 +1172,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt)
 	case V4L2_PIX_FMT_YVYU:		descr = "YVYU 4:2:2"; break;
 	case V4L2_PIX_FMT_UYVY:		descr = "UYVY 4:2:2"; break;
 	case V4L2_PIX_FMT_VYUY:		descr = "VYUY 4:2:2"; break;
-	case V4L2_PIX_FMT_YUV422P:	descr = "Planar YVU 4:2:2"; break;
+	case V4L2_PIX_FMT_YUV422P:	descr = "Planar YUV 4:2:2"; break;
 	case V4L2_PIX_FMT_YUV411P:	descr = "Planar YUV 4:1:1"; break;
 	case V4L2_PIX_FMT_Y41P:		descr = "YUV 4:1:1 (Packed)"; break;
 	case V4L2_PIX_FMT_YUV444:	descr = "16-bit A/XYUV 4-4-4-4"; break;
@@ -1191,6 +1198,10 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt)
 	case V4L2_PIX_FMT_NV12MT_16X16:	descr = "Y/CbCr 4:2:0 (16x16 MB, N-C)"; break;
 	case V4L2_PIX_FMT_YUV420M:	descr = "Planar YUV 4:2:0 (N-C)"; break;
 	case V4L2_PIX_FMT_YVU420M:	descr = "Planar YVU 4:2:0 (N-C)"; break;
+	case V4L2_PIX_FMT_YUV422M:	descr = "Planar YUV 4:2:2 (N-C)"; break;
+	case V4L2_PIX_FMT_YVU422M:	descr = "Planar YVU 4:2:2 (N-C)"; break;
+	case V4L2_PIX_FMT_YUV444M:	descr = "Planar YUV 4:4:4 (N-C)"; break;
+	case V4L2_PIX_FMT_YVU444M:	descr = "Planar YVU 4:4:4 (N-C)"; break;
 	case V4L2_PIX_FMT_SBGGR8:	descr = "8-bit Bayer BGBG/GRGR"; break;
 	case V4L2_PIX_FMT_SGBRG8:	descr = "8-bit Bayer GBGB/RGRG"; break;
 	case V4L2_PIX_FMT_SGRBG8:	descr = "8-bit Bayer GRGR/BGBG"; break;
@@ -1448,6 +1459,9 @@ static int v4l_s_fmt(const struct v4l2_ioctl_ops *ops,
 	bool is_tx = vfd->vfl_dir != VFL_DIR_RX;
 	int ret;
 
+	ret = v4l_enable_media_source(vfd);
+	if (ret)
+		return ret;
 	v4l_sanitize_format(p);
 
 	switch (p->type) {
@@ -1637,7 +1651,11 @@ static int v4l_s_tuner(const struct v4l2_ioctl_ops *ops,
 {
 	struct video_device *vfd = video_devdata(file);
 	struct v4l2_tuner *p = arg;
+	int ret;
 
+	ret = v4l_enable_media_source(vfd);
+	if (ret)
+		return ret;
 	p->type = (vfd->vfl_type == VFL_TYPE_RADIO) ?
 			V4L2_TUNER_RADIO : V4L2_TUNER_ANALOG_TV;
 	return ops->vidioc_s_tuner(file, fh, p);
@@ -1691,7 +1709,11 @@ static int v4l_s_frequency(const struct v4l2_ioctl_ops *ops,
 	struct video_device *vfd = video_devdata(file);
 	const struct v4l2_frequency *p = arg;
 	enum v4l2_tuner_type type;
+	int ret;
 
+	ret = v4l_enable_media_source(vfd);
+	if (ret)
+		return ret;
 	if (vfd->vfl_type == VFL_TYPE_SDR) {
 		if (p->type != V4L2_TUNER_SDR && p->type != V4L2_TUNER_RF)
 			return -EINVAL;
@@ -1746,7 +1768,11 @@ static int v4l_s_std(const struct v4l2_ioctl_ops *ops,
 {
 	struct video_device *vfd = video_devdata(file);
 	v4l2_std_id id = *(v4l2_std_id *)arg, norm;
+	int ret;
 
+	ret = v4l_enable_media_source(vfd);
+	if (ret)
+		return ret;
 	norm = id & vfd->tvnorms;
 	if (vfd->tvnorms && !norm)	/* Check if std is supported */
 		return -EINVAL;
@@ -1760,7 +1786,11 @@ static int v4l_querystd(const struct v4l2_ioctl_ops *ops,
 {
 	struct video_device *vfd = video_devdata(file);
 	v4l2_std_id *p = arg;
+	int ret;
 
+	ret = v4l_enable_media_source(vfd);
+	if (ret)
+		return ret;
 	/*
 	 * If no signal is detected, then the driver should return
 	 * V4L2_STD_UNKNOWN. Otherwise it should return tvnorms with
@@ -1779,7 +1809,11 @@ static int v4l_s_hw_freq_seek(const struct v4l2_ioctl_ops *ops,
 	struct video_device *vfd = video_devdata(file);
 	struct v4l2_hw_freq_seek *p = arg;
 	enum v4l2_tuner_type type;
+	int ret;
 
+	ret = v4l_enable_media_source(vfd);
+	if (ret)
+		return ret;
 	/* s_hw_freq_seek is not supported for SDR for now */
 	if (vfd->vfl_type == VFL_TYPE_SDR)
 		return -EINVAL;
diff --git a/drivers/media/v4l2-core/v4l2-mc.c b/drivers/media/v4l2-core/v4l2-mc.c
new file mode 100644
index 000000000000..2a7b79bc90fd
--- /dev/null
+++ b/drivers/media/v4l2-core/v4l2-mc.c
@@ -0,0 +1,403 @@
+/*
+ * Media Controller ancillary functions
+ *
+ * Copyright (c) 2016 Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+ * Copyright (C) 2016 Shuah Khan <shuahkh@osg.samsung.com>
+ * Copyright (C) 2006-2010 Nokia Corporation
+ * Copyright (c) 2016 Intel Corporation.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/usb.h>
+#include <media/media-device.h>
+#include <media/media-entity.h>
+#include <media/v4l2-fh.h>
+#include <media/v4l2-mc.h>
+#include <media/v4l2-subdev.h>
+#include <media/media-device.h>
+#include <media/v4l2-mc.h>
+#include <media/videobuf2-core.h>
+
+int v4l2_mc_create_media_graph(struct media_device *mdev)
+
+{
+	struct media_entity *entity;
+	struct media_entity *if_vid = NULL, *if_aud = NULL;
+	struct media_entity *tuner = NULL, *decoder = NULL, *dtv_demod = NULL;
+	struct media_entity *io_v4l = NULL, *io_vbi = NULL, *io_swradio = NULL;
+	bool is_webcam = false;
+	u32 flags;
+	int ret;
+
+	if (!mdev)
+		return 0;
+
+	media_device_for_each_entity(entity, mdev) {
+		switch (entity->function) {
+		case MEDIA_ENT_F_IF_VID_DECODER:
+			if_vid = entity;
+			break;
+		case MEDIA_ENT_F_IF_AUD_DECODER:
+			if_aud = entity;
+			break;
+		case MEDIA_ENT_F_TUNER:
+			tuner = entity;
+			break;
+		case MEDIA_ENT_F_ATV_DECODER:
+			decoder = entity;
+			break;
+		case MEDIA_ENT_F_IO_V4L:
+			io_v4l = entity;
+			break;
+		case MEDIA_ENT_F_IO_VBI:
+			io_vbi = entity;
+			break;
+		case MEDIA_ENT_F_IO_SWRADIO:
+			io_swradio = entity;
+			break;
+		case MEDIA_ENT_F_CAM_SENSOR:
+			is_webcam = true;
+			break;
+		}
+	}
+
+	/* It should have at least one I/O entity */
+	if (!io_v4l && !io_vbi && !io_swradio)
+		return -EINVAL;
+
+	/*
+	 * Here, webcams are modelled on a very simple way: the sensor is
+	 * connected directly to the I/O entity. All dirty details, like
+	 * scaler and crop HW are hidden. While such mapping is not enough
+	 * for mc-centric hardware, it is enough for v4l2 interface centric
+	 * PC-consumer's hardware.
+	 */
+	if (is_webcam) {
+		if (!io_v4l)
+			return -EINVAL;
+
+		media_device_for_each_entity(entity, mdev) {
+			if (entity->function != MEDIA_ENT_F_CAM_SENSOR)
+				continue;
+			ret = media_create_pad_link(entity, 0,
+						    io_v4l, 0,
+						    MEDIA_LNK_FL_ENABLED);
+			if (ret)
+				return ret;
+		}
+		if (!decoder)
+			return 0;
+	}
+
+	/* The device isn't a webcam. So, it should have a decoder */
+	if (!decoder)
+		return -EINVAL;
+
+	/* Link the tuner and IF video output pads */
+	if (tuner) {
+		if (if_vid) {
+			ret = media_create_pad_link(tuner, TUNER_PAD_OUTPUT,
+						    if_vid,
+						    IF_VID_DEC_PAD_IF_INPUT,
+						    MEDIA_LNK_FL_ENABLED);
+			if (ret)
+				return ret;
+			ret = media_create_pad_link(if_vid, IF_VID_DEC_PAD_OUT,
+						decoder, DEMOD_PAD_IF_INPUT,
+						MEDIA_LNK_FL_ENABLED);
+			if (ret)
+				return ret;
+		} else {
+			ret = media_create_pad_link(tuner, TUNER_PAD_OUTPUT,
+						decoder, DEMOD_PAD_IF_INPUT,
+						MEDIA_LNK_FL_ENABLED);
+			if (ret)
+				return ret;
+		}
+
+		if (if_aud) {
+			ret = media_create_pad_link(tuner, TUNER_PAD_AUD_OUT,
+						    if_aud,
+						    IF_AUD_DEC_PAD_IF_INPUT,
+						    MEDIA_LNK_FL_ENABLED);
+			if (ret)
+				return ret;
+		} else {
+			if_aud = tuner;
+		}
+
+	}
+
+	/* Create demod to V4L, VBI and SDR radio links */
+	if (io_v4l) {
+		ret = media_create_pad_link(decoder, DEMOD_PAD_VID_OUT,
+					io_v4l, 0,
+					MEDIA_LNK_FL_ENABLED);
+		if (ret)
+			return ret;
+	}
+
+	if (io_swradio) {
+		ret = media_create_pad_link(decoder, DEMOD_PAD_VID_OUT,
+					io_swradio, 0,
+					MEDIA_LNK_FL_ENABLED);
+		if (ret)
+			return ret;
+	}
+
+	if (io_vbi) {
+		ret = media_create_pad_link(decoder, DEMOD_PAD_VBI_OUT,
+					    io_vbi, 0,
+					    MEDIA_LNK_FL_ENABLED);
+		if (ret)
+			return ret;
+	}
+
+	/* Create links for the media connectors */
+	flags = MEDIA_LNK_FL_ENABLED;
+	media_device_for_each_entity(entity, mdev) {
+		switch (entity->function) {
+		case MEDIA_ENT_F_CONN_RF:
+			if (!tuner)
+				continue;
+
+			ret = media_create_pad_link(entity, 0, tuner,
+						    TUNER_PAD_RF_INPUT,
+						    flags);
+			break;
+		case MEDIA_ENT_F_CONN_SVIDEO:
+		case MEDIA_ENT_F_CONN_COMPOSITE:
+			ret = media_create_pad_link(entity, 0, decoder,
+						    DEMOD_PAD_IF_INPUT,
+						    flags);
+			break;
+		default:
+			continue;
+		}
+		if (ret)
+			return ret;
+
+		flags = 0;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(v4l2_mc_create_media_graph);
+
+int v4l_enable_media_source(struct video_device *vdev)
+{
+	struct media_device *mdev = vdev->entity.graph_obj.mdev;
+	int ret;
+
+	if (!mdev || !mdev->enable_source)
+		return 0;
+	ret = mdev->enable_source(&vdev->entity, &vdev->pipe);
+	if (ret)
+		return -EBUSY;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(v4l_enable_media_source);
+
+void v4l_disable_media_source(struct video_device *vdev)
+{
+	struct media_device *mdev = vdev->entity.graph_obj.mdev;
+
+	if (mdev && mdev->disable_source)
+		mdev->disable_source(&vdev->entity);
+}
+EXPORT_SYMBOL_GPL(v4l_disable_media_source);
+
+int v4l_vb2q_enable_media_source(struct vb2_queue *q)
+{
+	struct v4l2_fh *fh = q->owner;
+
+	if (fh && fh->vdev)
+		return v4l_enable_media_source(fh->vdev);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(v4l_vb2q_enable_media_source);
+
+/* -----------------------------------------------------------------------------
+ * Pipeline power management
+ *
+ * Entities must be powered up when part of a pipeline that contains at least
+ * one open video device node.
+ *
+ * To achieve this use the entity use_count field to track the number of users.
+ * For entities corresponding to video device nodes the use_count field stores
+ * the users count of the node. For entities corresponding to subdevs the
+ * use_count field stores the total number of users of all video device nodes
+ * in the pipeline.
+ *
+ * The v4l2_pipeline_pm_use() function must be called in the open() and
+ * close() handlers of video device nodes. It increments or decrements the use
+ * count of all subdev entities in the pipeline.
+ *
+ * To react to link management on powered pipelines, the link setup notification
+ * callback updates the use count of all entities in the source and sink sides
+ * of the link.
+ */
+
+/*
+ * pipeline_pm_use_count - Count the number of users of a pipeline
+ * @entity: The entity
+ *
+ * Return the total number of users of all video device nodes in the pipeline.
+ */
+static int pipeline_pm_use_count(struct media_entity *entity,
+	struct media_entity_graph *graph)
+{
+	int use = 0;
+
+	media_entity_graph_walk_start(graph, entity);
+
+	while ((entity = media_entity_graph_walk_next(graph))) {
+		if (is_media_entity_v4l2_io(entity))
+			use += entity->use_count;
+	}
+
+	return use;
+}
+
+/*
+ * pipeline_pm_power_one - Apply power change to an entity
+ * @entity: The entity
+ * @change: Use count change
+ *
+ * Change the entity use count by @change. If the entity is a subdev update its
+ * power state by calling the core::s_power operation when the use count goes
+ * from 0 to != 0 or from != 0 to 0.
+ *
+ * Return 0 on success or a negative error code on failure.
+ */
+static int pipeline_pm_power_one(struct media_entity *entity, int change)
+{
+	struct v4l2_subdev *subdev;
+	int ret;
+
+	subdev = is_media_entity_v4l2_subdev(entity)
+	       ? media_entity_to_v4l2_subdev(entity) : NULL;
+
+	if (entity->use_count == 0 && change > 0 && subdev != NULL) {
+		ret = v4l2_subdev_call(subdev, core, s_power, 1);
+		if (ret < 0 && ret != -ENOIOCTLCMD)
+			return ret;
+	}
+
+	entity->use_count += change;
+	WARN_ON(entity->use_count < 0);
+
+	if (entity->use_count == 0 && change < 0 && subdev != NULL)
+		v4l2_subdev_call(subdev, core, s_power, 0);
+
+	return 0;
+}
+
+/*
+ * pipeline_pm_power - Apply power change to all entities in a pipeline
+ * @entity: The entity
+ * @change: Use count change
+ *
+ * Walk the pipeline to update the use count and the power state of all non-node
+ * entities.
+ *
+ * Return 0 on success or a negative error code on failure.
+ */
+static int pipeline_pm_power(struct media_entity *entity, int change,
+	struct media_entity_graph *graph)
+{
+	struct media_entity *first = entity;
+	int ret = 0;
+
+	if (!change)
+		return 0;
+
+	media_entity_graph_walk_start(graph, entity);
+
+	while (!ret && (entity = media_entity_graph_walk_next(graph)))
+		if (is_media_entity_v4l2_subdev(entity))
+			ret = pipeline_pm_power_one(entity, change);
+
+	if (!ret)
+		return ret;
+
+	media_entity_graph_walk_start(graph, first);
+
+	while ((first = media_entity_graph_walk_next(graph))
+	       && first != entity)
+		if (is_media_entity_v4l2_subdev(first))
+			pipeline_pm_power_one(first, -change);
+
+	return ret;
+}
+
+int v4l2_pipeline_pm_use(struct media_entity *entity, int use)
+{
+	struct media_device *mdev = entity->graph_obj.mdev;
+	int change = use ? 1 : -1;
+	int ret;
+
+	mutex_lock(&mdev->graph_mutex);
+
+	/* Apply use count to node. */
+	entity->use_count += change;
+	WARN_ON(entity->use_count < 0);
+
+	/* Apply power change to connected non-nodes. */
+	ret = pipeline_pm_power(entity, change, &mdev->pm_count_walk);
+	if (ret < 0)
+		entity->use_count -= change;
+
+	mutex_unlock(&mdev->graph_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(v4l2_pipeline_pm_use);
+
+int v4l2_pipeline_link_notify(struct media_link *link, u32 flags,
+			      unsigned int notification)
+{
+	struct media_entity_graph *graph = &link->graph_obj.mdev->pm_count_walk;
+	struct media_entity *source = link->source->entity;
+	struct media_entity *sink = link->sink->entity;
+	int source_use;
+	int sink_use;
+	int ret = 0;
+
+	source_use = pipeline_pm_use_count(source, graph);
+	sink_use = pipeline_pm_use_count(sink, graph);
+
+	if (notification == MEDIA_DEV_NOTIFY_POST_LINK_CH &&
+	    !(flags & MEDIA_LNK_FL_ENABLED)) {
+		/* Powering off entities is assumed to never fail. */
+		pipeline_pm_power(source, -sink_use, graph);
+		pipeline_pm_power(sink, -source_use, graph);
+		return 0;
+	}
+
+	if (notification == MEDIA_DEV_NOTIFY_PRE_LINK_CH &&
+		(flags & MEDIA_LNK_FL_ENABLED)) {
+
+		ret = pipeline_pm_power(source, sink_use, graph);
+		if (ret < 0)
+			return ret;
+
+		ret = pipeline_pm_power(sink, source_use, graph);
+		if (ret < 0)
+			pipeline_pm_power(source, -sink_use, graph);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(v4l2_pipeline_link_notify);
diff --git a/drivers/media/v4l2-core/v4l2-of.c b/drivers/media/v4l2-core/v4l2-of.c
index b27cbb1f5afe..93b33681776c 100644
--- a/drivers/media/v4l2-core/v4l2-of.c
+++ b/drivers/media/v4l2-core/v4l2-of.c
@@ -146,7 +146,7 @@ static void v4l2_of_parse_parallel_bus(const struct device_node *node,
  * variable without a low fixed limit. Please use
  * v4l2_of_alloc_parse_endpoint() in new drivers instead.
  *
- * Return: 0.
+ * Return: 0 on success or a negative error code on failure.
  */
 int v4l2_of_parse_endpoint(const struct device_node *node,
 			   struct v4l2_of_endpoint *endpoint)
diff --git a/drivers/media/v4l2-core/videobuf-core.c b/drivers/media/v4l2-core/videobuf-core.c
index 6c02989ee33f..def84753c4c3 100644
--- a/drivers/media/v4l2-core/videobuf-core.c
+++ b/drivers/media/v4l2-core/videobuf-core.c
@@ -75,7 +75,8 @@ struct videobuf_buffer *videobuf_alloc_vb(struct videobuf_queue *q)
 }
 EXPORT_SYMBOL_GPL(videobuf_alloc_vb);
 
-static int is_state_active_or_queued(struct videobuf_queue *q, struct videobuf_buffer *vb)
+static int state_neither_active_nor_queued(struct videobuf_queue *q,
+					   struct videobuf_buffer *vb)
 {
 	unsigned long flags;
 	bool rc;
@@ -95,7 +96,7 @@ int videobuf_waiton(struct videobuf_queue *q, struct videobuf_buffer *vb,
 	MAGIC_CHECK(vb->magic, MAGIC_BUFFER);
 
 	if (non_blocking) {
-		if (is_state_active_or_queued(q, vb))
+		if (state_neither_active_nor_queued(q, vb))
 			return 0;
 		return -EAGAIN;
 	}
@@ -107,9 +108,10 @@ int videobuf_waiton(struct videobuf_queue *q, struct videobuf_buffer *vb,
 	if (is_ext_locked)
 		mutex_unlock(q->ext_lock);
 	if (intr)
-		ret = wait_event_interruptible(vb->done, is_state_active_or_queued(q, vb));
+		ret = wait_event_interruptible(vb->done,
+					state_neither_active_nor_queued(q, vb));
 	else
-		wait_event(vb->done, is_state_active_or_queued(q, vb));
+		wait_event(vb->done, state_neither_active_nor_queued(q, vb));
 	/* Relock */
 	if (is_ext_locked)
 		mutex_lock(q->ext_lock);
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index ff8953ae52d1..5d016f496e0e 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -25,6 +25,7 @@
 #include <linux/kthread.h>
 
 #include <media/videobuf2-core.h>
+#include <media/v4l2-mc.h>
 
 #include <trace/events/vb2.h>
 
@@ -1227,6 +1228,7 @@ static int __qbuf_dmabuf(struct vb2_buffer *vb, const void *pb)
 		if (planes[plane].length < vb->planes[plane].min_length) {
 			dprintk(1, "invalid dmabuf length for plane %d\n",
 				plane);
+			dma_buf_put(dbuf);
 			ret = -EINVAL;
 			goto err;
 		}
@@ -1886,6 +1888,9 @@ int vb2_core_streamon(struct vb2_queue *q, unsigned int type)
 	 * are available.
 	 */
 	if (q->queued_count >= q->min_buffers_needed) {
+		ret = v4l_vb2q_enable_media_source(q);
+		if (ret)
+			return ret;
 		ret = vb2_start_streaming(q);
 		if (ret) {
 			__vb2_queue_cancel(q);
diff --git a/drivers/media/v4l2-core/videobuf2-dvb.c b/drivers/media/v4l2-core/videobuf2-dvb.c
index d09269846b7e..9f38b4218c0d 100644
--- a/drivers/media/v4l2-core/videobuf2-dvb.c
+++ b/drivers/media/v4l2-core/videobuf2-dvb.c
@@ -77,6 +77,7 @@ static int vb2_dvb_register_adapter(struct vb2_dvb_frontends *fe,
 			  struct module *module,
 			  void *adapter_priv,
 			  struct device *device,
+			  struct media_device *mdev,
 			  char *adapter_name,
 			  short *adapter_nr,
 			  int mfe_shared)
@@ -94,7 +95,10 @@ static int vb2_dvb_register_adapter(struct vb2_dvb_frontends *fe,
 	}
 	fe->adapter.priv = adapter_priv;
 	fe->adapter.mfe_shared = mfe_shared;
-
+#ifdef CONFIG_MEDIA_CONTROLLER_DVB
+	if (mdev)
+		fe->adapter.mdev = mdev;
+#endif
 	return result;
 }
 
@@ -193,6 +197,7 @@ int vb2_dvb_register_bus(struct vb2_dvb_frontends *f,
 			 struct module *module,
 			 void *adapter_priv,
 			 struct device *device,
+			 struct media_device *mdev,
 			 short *adapter_nr,
 			 int mfe_shared)
 {
@@ -207,7 +212,7 @@ int vb2_dvb_register_bus(struct vb2_dvb_frontends *f,
 	}
 
 	/* Bring up the adapter */
-	res = vb2_dvb_register_adapter(f, module, adapter_priv, device,
+	res = vb2_dvb_register_adapter(f, module, adapter_priv, device, mdev,
 		fe->dvb.name, adapter_nr, mfe_shared);
 	if (res < 0) {
 		pr_warn("vb2_dvb_register_adapter failed (errno = %d)\n", res);
@@ -224,7 +229,11 @@ int vb2_dvb_register_bus(struct vb2_dvb_frontends *f,
 				fe->dvb.name, res);
 			goto err;
 		}
+		res = dvb_create_media_graph(&f->adapter, false);
+		if (res < 0)
+			goto err;
 	}
+
 	mutex_unlock(&f->lock);
 	return 0;
 
diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c
index 5dcc0313c38a..5537f8df8512 100644
--- a/drivers/message/fusion/mptbase.c
+++ b/drivers/message/fusion/mptbase.c
@@ -1801,8 +1801,7 @@ mpt_attach(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	ioc->pcidev = pdev;
 	if (mpt_mapresources(ioc)) {
-		kfree(ioc);
-		return r;
+		goto out_free_ioc;
 	}
 
 	/*
@@ -1871,9 +1870,8 @@ mpt_attach(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (!ioc->reset_work_q) {
 		printk(MYIOC_s_ERR_FMT "Insufficient memory to add adapter!\n",
 		    ioc->name);
-		pci_release_selected_regions(pdev, ioc->bars);
-		kfree(ioc);
-		return -ENOMEM;
+		r = -ENOMEM;
+		goto out_unmap_resources;
 	}
 
 	dinitprintk(ioc, printk(MYIOC_s_INFO_FMT "facts @ %p, pfacts[0] @ %p\n",
@@ -1995,16 +1993,27 @@ mpt_attach(struct pci_dev *pdev, const struct pci_device_id *id)
 	spin_lock_init(&ioc->fw_event_lock);
 	snprintf(ioc->fw_event_q_name, MPT_KOBJ_NAME_LEN, "mpt/%d", ioc->id);
 	ioc->fw_event_q = create_singlethread_workqueue(ioc->fw_event_q_name);
+	if (!ioc->fw_event_q) {
+		printk(MYIOC_s_ERR_FMT "Insufficient memory to add adapter!\n",
+		    ioc->name);
+		r = -ENOMEM;
+		goto out_remove_ioc;
+	}
 
 	if ((r = mpt_do_ioc_recovery(ioc, MPT_HOSTEVENT_IOC_BRINGUP,
 	    CAN_SLEEP)) != 0){
 		printk(MYIOC_s_ERR_FMT "didn't initialize properly! (%d)\n",
 		    ioc->name, r);
 
+		destroy_workqueue(ioc->fw_event_q);
+		ioc->fw_event_q = NULL;
+
 		list_del(&ioc->list);
 		if (ioc->alt_ioc)
 			ioc->alt_ioc->alt_ioc = NULL;
 		iounmap(ioc->memmap);
+		if (pci_is_enabled(pdev))
+			pci_disable_device(pdev);
 		if (r != -5)
 			pci_release_selected_regions(pdev, ioc->bars);
 
@@ -2012,7 +2021,6 @@ mpt_attach(struct pci_dev *pdev, const struct pci_device_id *id)
 		ioc->reset_work_q = NULL;
 
 		kfree(ioc);
-		pci_set_drvdata(pdev, NULL);
 		return r;
 	}
 
@@ -2040,6 +2048,24 @@ mpt_attach(struct pci_dev *pdev, const struct pci_device_id *id)
 			msecs_to_jiffies(MPT_POLLING_INTERVAL));
 
 	return 0;
+
+out_remove_ioc:
+	list_del(&ioc->list);
+	if (ioc->alt_ioc)
+		ioc->alt_ioc->alt_ioc = NULL;
+
+	destroy_workqueue(ioc->reset_work_q);
+	ioc->reset_work_q = NULL;
+
+out_unmap_resources:
+	iounmap(ioc->memmap);
+	pci_disable_device(pdev);
+	pci_release_selected_regions(pdev, ioc->bars);
+
+out_free_ioc:
+	kfree(ioc);
+
+	return r;
 }
 
 /*=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=*/
@@ -6229,7 +6255,7 @@ mpt_get_manufacturing_pg_0(MPT_ADAPTER *ioc)
 	memcpy(ioc->board_assembly, pbuf->BoardAssembly, sizeof(ioc->board_assembly));
 	memcpy(ioc->board_tracer, pbuf->BoardTracerNumber, sizeof(ioc->board_tracer));
 
-	out:
+out:
 
 	if (pbuf)
 		pci_free_consistent(ioc->pcidev, hdr.PageLength * 4, pbuf, buf_dma);
@@ -6848,6 +6874,7 @@ mpt_print_ioc_summary(MPT_ADAPTER *ioc, char *buffer, int *size, int len, int sh
 	*size = y;
 }
 
+#ifdef CONFIG_PROC_FS
 static void seq_mpt_print_ioc_summary(MPT_ADAPTER *ioc, struct seq_file *m, int showlan)
 {
 	char expVer[32];
@@ -6879,6 +6906,7 @@ static void seq_mpt_print_ioc_summary(MPT_ADAPTER *ioc, struct seq_file *m, int
 
 	seq_putc(m, '\n');
 }
+#endif
 
 /**
  *	mpt_set_taskmgmt_in_progress_flag - set flags associated with task management
diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c
index e6e4bacb09ee..12099b09a9a7 100644
--- a/drivers/mfd/db8500-prcmu.c
+++ b/drivers/mfd/db8500-prcmu.c
@@ -2048,6 +2048,7 @@ int db8500_prcmu_config_hotmon(u8 low, u8 high)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(db8500_prcmu_config_hotmon);
 
 static int config_hot_period(u16 val)
 {
@@ -2074,11 +2075,13 @@ int db8500_prcmu_start_temp_sense(u16 cycles32k)
 
 	return config_hot_period(cycles32k);
 }
+EXPORT_SYMBOL_GPL(db8500_prcmu_start_temp_sense);
 
 int db8500_prcmu_stop_temp_sense(void)
 {
 	return config_hot_period(0xFFFF);
 }
+EXPORT_SYMBOL_GPL(db8500_prcmu_stop_temp_sense);
 
 static int prcmu_a9wdog(u8 cmd, u8 d0, u8 d1, u8 d2, u8 d3)
 {
diff --git a/drivers/mfd/max77686.c b/drivers/mfd/max77686.c
index d959ebbb2194..98ecd136a21b 100644
--- a/drivers/mfd/max77686.c
+++ b/drivers/mfd/max77686.c
@@ -35,8 +35,6 @@
 #include <linux/err.h>
 #include <linux/of.h>
 
-#define I2C_ADDR_RTC	(0x0C >> 1)
-
 static const struct mfd_cell max77686_devs[] = {
 	{ .name = "max77686-pmic", },
 	{ .name = "max77686-rtc", },
@@ -116,11 +114,6 @@ static const struct regmap_config max77686_regmap_config = {
 	.val_bits = 8,
 };
 
-static const struct regmap_config max77686_rtc_regmap_config = {
-	.reg_bits = 8,
-	.val_bits = 8,
-};
-
 static const struct regmap_config max77802_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
@@ -156,25 +149,6 @@ static const struct regmap_irq_chip max77686_irq_chip = {
 	.num_irqs		= ARRAY_SIZE(max77686_irqs),
 };
 
-static const struct regmap_irq max77686_rtc_irqs[] = {
-	/* RTC interrupts */
-	{ .reg_offset = 0, .mask = MAX77686_RTCINT_RTC60S_MSK, },
-	{ .reg_offset = 0, .mask = MAX77686_RTCINT_RTCA1_MSK, },
-	{ .reg_offset = 0, .mask = MAX77686_RTCINT_RTCA2_MSK, },
-	{ .reg_offset = 0, .mask = MAX77686_RTCINT_SMPL_MSK, },
-	{ .reg_offset = 0, .mask = MAX77686_RTCINT_RTC1S_MSK, },
-	{ .reg_offset = 0, .mask = MAX77686_RTCINT_WTSR_MSK, },
-};
-
-static const struct regmap_irq_chip max77686_rtc_irq_chip = {
-	.name			= "max77686-rtc",
-	.status_base		= MAX77686_RTC_INT,
-	.mask_base		= MAX77686_RTC_INTM,
-	.num_regs		= 1,
-	.irqs			= max77686_rtc_irqs,
-	.num_irqs		= ARRAY_SIZE(max77686_rtc_irqs),
-};
-
 static const struct regmap_irq_chip max77802_irq_chip = {
 	.name			= "max77802-pmic",
 	.status_base		= MAX77802_REG_INT1,
@@ -184,15 +158,6 @@ static const struct regmap_irq_chip max77802_irq_chip = {
 	.num_irqs		= ARRAY_SIZE(max77686_irqs),
 };
 
-static const struct regmap_irq_chip max77802_rtc_irq_chip = {
-	.name			= "max77802-rtc",
-	.status_base		= MAX77802_RTC_INT,
-	.mask_base		= MAX77802_RTC_INTM,
-	.num_regs		= 1,
-	.irqs			= max77686_rtc_irqs, /* same masks as 77686 */
-	.num_irqs		= ARRAY_SIZE(max77686_rtc_irqs),
-};
-
 static const struct of_device_id max77686_pmic_dt_match[] = {
 	{
 		.compatible = "maxim,max77686",
@@ -214,8 +179,6 @@ static int max77686_i2c_probe(struct i2c_client *i2c,
 	int ret = 0;
 	const struct regmap_config *config;
 	const struct regmap_irq_chip *irq_chip;
-	const struct regmap_irq_chip *rtc_irq_chip;
-	struct regmap **rtc_regmap;
 	const struct mfd_cell *cells;
 	int n_devs;
 
@@ -242,15 +205,11 @@ static int max77686_i2c_probe(struct i2c_client *i2c,
 	if (max77686->type == TYPE_MAX77686) {
 		config = &max77686_regmap_config;
 		irq_chip = &max77686_irq_chip;
-		rtc_irq_chip = &max77686_rtc_irq_chip;
-		rtc_regmap = &max77686->rtc_regmap;
 		cells =  max77686_devs;
 		n_devs = ARRAY_SIZE(max77686_devs);
 	} else {
 		config = &max77802_regmap_config;
 		irq_chip = &max77802_irq_chip;
-		rtc_irq_chip = &max77802_rtc_irq_chip;
-		rtc_regmap = &max77686->regmap;
 		cells =  max77802_devs;
 		n_devs = ARRAY_SIZE(max77802_devs);
 	}
@@ -270,60 +229,25 @@ static int max77686_i2c_probe(struct i2c_client *i2c,
 		return -ENODEV;
 	}
 
-	if (max77686->type == TYPE_MAX77686) {
-		max77686->rtc = i2c_new_dummy(i2c->adapter, I2C_ADDR_RTC);
-		if (!max77686->rtc) {
-			dev_err(max77686->dev,
-				"Failed to allocate I2C device for RTC\n");
-			return -ENODEV;
-		}
-		i2c_set_clientdata(max77686->rtc, max77686);
-
-		max77686->rtc_regmap =
-			devm_regmap_init_i2c(max77686->rtc,
-					     &max77686_rtc_regmap_config);
-		if (IS_ERR(max77686->rtc_regmap)) {
-			ret = PTR_ERR(max77686->rtc_regmap);
-			dev_err(max77686->dev,
-				"failed to allocate RTC regmap: %d\n",
-				ret);
-			goto err_unregister_i2c;
-		}
-	}
-
 	ret = regmap_add_irq_chip(max77686->regmap, max77686->irq,
 				  IRQF_TRIGGER_FALLING | IRQF_ONESHOT |
 				  IRQF_SHARED, 0, irq_chip,
 				  &max77686->irq_data);
-	if (ret) {
+	if (ret < 0) {
 		dev_err(&i2c->dev, "failed to add PMIC irq chip: %d\n", ret);
-		goto err_unregister_i2c;
-	}
-
-	ret = regmap_add_irq_chip(*rtc_regmap, max77686->irq,
-				  IRQF_TRIGGER_FALLING | IRQF_ONESHOT |
-				  IRQF_SHARED, 0, rtc_irq_chip,
-				  &max77686->rtc_irq_data);
-	if (ret) {
-		dev_err(&i2c->dev, "failed to add RTC irq chip: %d\n", ret);
-		goto err_del_irqc;
+		return ret;
 	}
 
 	ret = mfd_add_devices(max77686->dev, -1, cells, n_devs, NULL, 0, NULL);
 	if (ret < 0) {
 		dev_err(&i2c->dev, "failed to add MFD devices: %d\n", ret);
-		goto err_del_rtc_irqc;
+		goto err_del_irqc;
 	}
 
 	return 0;
 
-err_del_rtc_irqc:
-	regmap_del_irq_chip(max77686->irq, max77686->rtc_irq_data);
 err_del_irqc:
 	regmap_del_irq_chip(max77686->irq, max77686->irq_data);
-err_unregister_i2c:
-	if (max77686->type == TYPE_MAX77686)
-		i2c_unregister_device(max77686->rtc);
 
 	return ret;
 }
@@ -334,12 +258,8 @@ static int max77686_i2c_remove(struct i2c_client *i2c)
 
 	mfd_remove_devices(max77686->dev);
 
-	regmap_del_irq_chip(max77686->irq, max77686->rtc_irq_data);
 	regmap_del_irq_chip(max77686->irq, max77686->irq_data);
 
-	if (max77686->type == TYPE_MAX77686)
-		i2c_unregister_device(max77686->rtc);
-
 	return 0;
 }
 
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 4c1903f781fc..a89608334ed5 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -19,7 +19,6 @@
 #include <linux/delay.h>
 #include <asm/opal.h>
 #include <asm/msi_bitmap.h>
-#include <asm/pci-bridge.h> /* for struct pci_controller */
 #include <asm/pnv-pci.h>
 #include <asm/io.h>
 
@@ -415,7 +414,7 @@ static int cxl_setup_psl_timebase(struct cxl *adapter, struct pci_dev *dev)
 		delta = mftb() - psl_tb;
 		if (delta < 0)
 			delta = -delta;
-	} while (cputime_to_usecs(delta) > 16);
+	} while (tb_to_ns(delta) > 16000);
 
 	return 0;
 }
diff --git a/drivers/misc/lkdtm.c b/drivers/misc/lkdtm.c
index 11fdadc68e53..2a6eaf1122b4 100644
--- a/drivers/misc/lkdtm.c
+++ b/drivers/misc/lkdtm.c
@@ -103,6 +103,7 @@ enum ctype {
 	CT_EXEC_USERSPACE,
 	CT_ACCESS_USERSPACE,
 	CT_WRITE_RO,
+	CT_WRITE_RO_AFTER_INIT,
 	CT_WRITE_KERN,
 };
 
@@ -140,6 +141,7 @@ static char* cp_type[] = {
 	"EXEC_USERSPACE",
 	"ACCESS_USERSPACE",
 	"WRITE_RO",
+	"WRITE_RO_AFTER_INIT",
 	"WRITE_KERN",
 };
 
@@ -162,6 +164,7 @@ static DEFINE_SPINLOCK(lock_me_up);
 static u8 data_area[EXEC_SIZE];
 
 static const unsigned long rodata = 0xAA55AA55;
+static unsigned long ro_after_init __ro_after_init = 0x55AA5500;
 
 module_param(recur_count, int, 0644);
 MODULE_PARM_DESC(recur_count, " Recursion level for the stack overflow test");
@@ -503,11 +506,28 @@ static void lkdtm_do_action(enum ctype which)
 		break;
 	}
 	case CT_WRITE_RO: {
-		unsigned long *ptr;
+		/* Explicitly cast away "const" for the test. */
+		unsigned long *ptr = (unsigned long *)&rodata;
 
-		ptr = (unsigned long *)&rodata;
+		pr_info("attempting bad rodata write at %p\n", ptr);
+		*ptr ^= 0xabcd1234;
 
-		pr_info("attempting bad write at %p\n", ptr);
+		break;
+	}
+	case CT_WRITE_RO_AFTER_INIT: {
+		unsigned long *ptr = &ro_after_init;
+
+		/*
+		 * Verify we were written to during init. Since an Oops
+		 * is considered a "success", a failure is to just skip the
+		 * real test.
+		 */
+		if ((*ptr & 0xAA) != 0xAA) {
+			pr_info("%p was NOT written during init!?\n", ptr);
+			break;
+		}
+
+		pr_info("attempting bad ro_after_init write at %p\n", ptr);
 		*ptr ^= 0xabcd1234;
 
 		break;
@@ -817,6 +837,9 @@ static int __init lkdtm_module_init(void)
 	int n_debugfs_entries = 1; /* Assume only the direct entry */
 	int i;
 
+	/* Make sure we can write to __ro_after_init values during __init */
+	ro_after_init |= 0xAA;
+
 	/* Register debugfs interface */
 	lkdtm_debugfs_root = debugfs_create_dir("provoke-crash", NULL);
 	if (!lkdtm_debugfs_root) {
diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c
index 677d0362f334..80f9afcb1382 100644
--- a/drivers/misc/mei/main.c
+++ b/drivers/misc/mei/main.c
@@ -458,7 +458,11 @@ static int mei_ioctl_client_notify_request(struct file *file, u32 request)
 {
 	struct mei_cl *cl = file->private_data;
 
-	return mei_cl_notify_request(cl, file, request);
+	if (request != MEI_HBM_NOTIFICATION_START &&
+	    request != MEI_HBM_NOTIFICATION_STOP)
+		return -EINVAL;
+
+	return mei_cl_notify_request(cl, file, (u8)request);
 }
 
 /**
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 5914263090fc..fe207e542032 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -47,13 +47,10 @@
 #include "queue.h"
 
 MODULE_ALIAS("mmc:block");
-
-#ifdef KERNEL
 #ifdef MODULE_PARAM_PREFIX
 #undef MODULE_PARAM_PREFIX
 #endif
 #define MODULE_PARAM_PREFIX "mmcblk."
-#endif
 
 #define INAND_CMD38_ARG_EXT_CSD  113
 #define INAND_CMD38_ARG_ERASE    0x00
@@ -655,8 +652,10 @@ static int mmc_blk_ioctl_multi_cmd(struct block_device *bdev,
 	}
 
 	md = mmc_blk_get(bdev->bd_disk);
-	if (!md)
+	if (!md) {
+		err = -EINVAL;
 		goto cmd_err;
+	}
 
 	card = md->queue.card;
 	if (IS_ERR(card)) {
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index 1c1b45ef3faf..3446097a43c0 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -925,6 +925,10 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd,
 
 			dma_addr = dma_map_page(dma_dev, sg_page(sg), 0,
 						PAGE_SIZE, dir);
+			if (dma_mapping_error(dma_dev, dma_addr)) {
+				data->error = -EFAULT;
+				break;
+			}
 			if (direction == DMA_TO_DEVICE)
 				t->tx_dma = dma_addr + sg->offset;
 			else
@@ -1393,10 +1397,12 @@ static int mmc_spi_probe(struct spi_device *spi)
 		host->dma_dev = dev;
 		host->ones_dma = dma_map_single(dev, ones,
 				MMC_SPI_BLOCKSIZE, DMA_TO_DEVICE);
+		if (dma_mapping_error(dev, host->ones_dma))
+			goto fail_ones_dma;
 		host->data_dma = dma_map_single(dev, host->data,
 				sizeof(*host->data), DMA_BIDIRECTIONAL);
-
-		/* REVISIT in theory those map operations can fail... */
+		if (dma_mapping_error(dev, host->data_dma))
+			goto fail_data_dma;
 
 		dma_sync_single_for_cpu(host->dma_dev,
 				host->data_dma, sizeof(*host->data),
@@ -1462,6 +1468,11 @@ fail_glue_init:
 	if (host->dma_dev)
 		dma_unmap_single(host->dma_dev, host->data_dma,
 				sizeof(*host->data), DMA_BIDIRECTIONAL);
+fail_data_dma:
+	if (host->dma_dev)
+		dma_unmap_single(host->dma_dev, host->ones_dma,
+				MMC_SPI_BLOCKSIZE, DMA_TO_DEVICE);
+fail_ones_dma:
 	kfree(host->data);
 
 fail_nobuf1:
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index b6639ea0bf18..f6e4d9718035 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -2232,6 +2232,7 @@ err_irq:
 		dma_release_channel(host->tx_chan);
 	if (host->rx_chan)
 		dma_release_channel(host->rx_chan);
+	pm_runtime_dont_use_autosuspend(host->dev);
 	pm_runtime_put_sync(host->dev);
 	pm_runtime_disable(host->dev);
 	if (host->dbclk)
@@ -2253,6 +2254,7 @@ static int omap_hsmmc_remove(struct platform_device *pdev)
 	dma_release_channel(host->tx_chan);
 	dma_release_channel(host->rx_chan);
 
+	pm_runtime_dont_use_autosuspend(host->dev);
 	pm_runtime_put_sync(host->dev);
 	pm_runtime_disable(host->dev);
 	device_init_wakeup(&pdev->dev, false);
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index ce08896b9d69..da824772bbb4 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -86,7 +86,7 @@ struct pxamci_host {
 static inline void pxamci_init_ocr(struct pxamci_host *host)
 {
 #ifdef CONFIG_REGULATOR
-	host->vcc = regulator_get_optional(mmc_dev(host->mmc), "vmmc");
+	host->vcc = devm_regulator_get_optional(mmc_dev(host->mmc), "vmmc");
 
 	if (IS_ERR(host->vcc))
 		host->vcc = NULL;
@@ -654,12 +654,8 @@ static int pxamci_probe(struct platform_device *pdev)
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	irq = platform_get_irq(pdev, 0);
-	if (!r || irq < 0)
-		return -ENXIO;
-
-	r = request_mem_region(r->start, SZ_4K, DRIVER_NAME);
-	if (!r)
-		return -EBUSY;
+	if (irq < 0)
+		return irq;
 
 	mmc = mmc_alloc_host(sizeof(struct pxamci_host), &pdev->dev);
 	if (!mmc) {
@@ -695,7 +691,7 @@ static int pxamci_probe(struct platform_device *pdev)
 	host->pdata = pdev->dev.platform_data;
 	host->clkrt = CLKRT_OFF;
 
-	host->clk = clk_get(&pdev->dev, NULL);
+	host->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(host->clk)) {
 		ret = PTR_ERR(host->clk);
 		host->clk = NULL;
@@ -727,9 +723,9 @@ static int pxamci_probe(struct platform_device *pdev)
 	host->irq = irq;
 	host->imask = MMC_I_MASK_ALL;
 
-	host->base = ioremap(r->start, SZ_4K);
-	if (!host->base) {
-		ret = -ENOMEM;
+	host->base = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(host->base)) {
+		ret = PTR_ERR(host->base);
 		goto out;
 	}
 
@@ -742,7 +738,8 @@ static int pxamci_probe(struct platform_device *pdev)
 	writel(64, host->base + MMC_RESTO);
 	writel(host->imask, host->base + MMC_I_MASK);
 
-	ret = request_irq(host->irq, pxamci_irq, 0, DRIVER_NAME, host);
+	ret = devm_request_irq(&pdev->dev, host->irq, pxamci_irq, 0,
+			       DRIVER_NAME, host);
 	if (ret)
 		goto out;
 
@@ -804,7 +801,7 @@ static int pxamci_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "Failed requesting gpio_ro %d\n", gpio_ro);
 		goto out;
 	} else {
-		mmc->caps |= host->pdata->gpio_card_ro_invert ?
+		mmc->caps2 |= host->pdata->gpio_card_ro_invert ?
 			0 : MMC_CAP2_RO_ACTIVE_HIGH;
 	}
 
@@ -833,14 +830,9 @@ out:
 			dma_release_channel(host->dma_chan_rx);
 		if (host->dma_chan_tx)
 			dma_release_channel(host->dma_chan_tx);
-		if (host->base)
-			iounmap(host->base);
-		if (host->clk)
-			clk_put(host->clk);
 	}
 	if (mmc)
 		mmc_free_host(mmc);
-	release_resource(r);
 	return ret;
 }
 
@@ -859,9 +851,6 @@ static int pxamci_remove(struct platform_device *pdev)
 			gpio_ro = host->pdata->gpio_card_ro;
 			gpio_power = host->pdata->gpio_power;
 		}
-		if (host->vcc)
-			regulator_put(host->vcc);
-
 		if (host->pdata && host->pdata->exit)
 			host->pdata->exit(&pdev->dev, mmc);
 
@@ -870,16 +859,10 @@ static int pxamci_remove(struct platform_device *pdev)
 		       END_CMD_RES|PRG_DONE|DATA_TRAN_DONE,
 		       host->base + MMC_I_MASK);
 
-		free_irq(host->irq, host);
 		dmaengine_terminate_all(host->dma_chan_rx);
 		dmaengine_terminate_all(host->dma_chan_tx);
 		dma_release_channel(host->dma_chan_rx);
 		dma_release_channel(host->dma_chan_tx);
-		iounmap(host->base);
-
-		clk_put(host->clk);
-
-		release_resource(host->res);
 
 		mmc_free_host(mmc);
 	}
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index f6047fc94062..a5cda926d38e 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -146,6 +146,33 @@ static const struct sdhci_acpi_chip sdhci_acpi_chip_int = {
 	.ops = &sdhci_acpi_ops_int,
 };
 
+static int bxt_get_cd(struct mmc_host *mmc)
+{
+	int gpio_cd = mmc_gpio_get_cd(mmc);
+	struct sdhci_host *host = mmc_priv(mmc);
+	unsigned long flags;
+	int ret = 0;
+
+	if (!gpio_cd)
+		return 0;
+
+	pm_runtime_get_sync(mmc->parent);
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	if (host->flags & SDHCI_DEVICE_DEAD)
+		goto out;
+
+	ret = !!(sdhci_readl(host, SDHCI_PRESENT_STATE) & SDHCI_CARD_PRESENT);
+out:
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	pm_runtime_mark_last_busy(mmc->parent);
+	pm_runtime_put_autosuspend(mmc->parent);
+
+	return ret;
+}
+
 static int sdhci_acpi_emmc_probe_slot(struct platform_device *pdev,
 				      const char *hid, const char *uid)
 {
@@ -196,6 +223,9 @@ static int sdhci_acpi_sd_probe_slot(struct platform_device *pdev,
 
 	/* Platform specific code during sd probe slot goes here */
 
+	if (hid && !strcmp(hid, "80865ACA"))
+		host->mmc_host_ops.get_cd = bxt_get_cd;
+
 	return 0;
 }
 
diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c
index 7e7d8f0c9438..9cb86fb25976 100644
--- a/drivers/mmc/host/sdhci-of-at91.c
+++ b/drivers/mmc/host/sdhci-of-at91.c
@@ -217,6 +217,7 @@ static int sdhci_at91_probe(struct platform_device *pdev)
 pm_runtime_disable:
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_set_suspended(&pdev->dev);
+	pm_runtime_put_noidle(&pdev->dev);
 clocks_disable_unprepare:
 	clk_disable_unprepare(priv->gck);
 	clk_disable_unprepare(priv->mainck);
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index cc851b065d0a..df3b8eced8c4 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -330,6 +330,33 @@ static void spt_read_drive_strength(struct sdhci_host *host)
 	sdhci_pci_spt_drive_strength = 0x10 | ((val >> 12) & 0xf);
 }
 
+static int bxt_get_cd(struct mmc_host *mmc)
+{
+	int gpio_cd = mmc_gpio_get_cd(mmc);
+	struct sdhci_host *host = mmc_priv(mmc);
+	unsigned long flags;
+	int ret = 0;
+
+	if (!gpio_cd)
+		return 0;
+
+	pm_runtime_get_sync(mmc->parent);
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	if (host->flags & SDHCI_DEVICE_DEAD)
+		goto out;
+
+	ret = !!(sdhci_readl(host, SDHCI_PRESENT_STATE) & SDHCI_CARD_PRESENT);
+out:
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	pm_runtime_mark_last_busy(mmc->parent);
+	pm_runtime_put_autosuspend(mmc->parent);
+
+	return ret;
+}
+
 static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
 {
 	slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE |
@@ -362,6 +389,10 @@ static int byt_sd_probe_slot(struct sdhci_pci_slot *slot)
 	slot->cd_con_id = NULL;
 	slot->cd_idx = 0;
 	slot->cd_override_level = true;
+	if (slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_BXT_SD ||
+	    slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_APL_SD)
+		slot->host->mmc_host_ops.get_cd = bxt_get_cd;
+
 	return 0;
 }
 
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index d622435d1bcc..add9fdfd1d8f 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1360,7 +1360,7 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	sdhci_runtime_pm_get(host);
 
 	/* Firstly check card presence */
-	present = sdhci_do_get_cd(host);
+	present = mmc->ops->get_cd(mmc);
 
 	spin_lock_irqsave(&host->lock, flags);
 
@@ -2849,6 +2849,8 @@ struct sdhci_host *sdhci_alloc_host(struct device *dev,
 
 	host = mmc_priv(mmc);
 	host->mmc = mmc;
+	host->mmc_host_ops = sdhci_ops;
+	mmc->ops = &host->mmc_host_ops;
 
 	return host;
 }
@@ -3037,7 +3039,6 @@ int sdhci_add_host(struct sdhci_host *host)
 	/*
 	 * Set host parameters.
 	 */
-	mmc->ops = &sdhci_ops;
 	max_clk = host->max_clk;
 
 	if (host->ops->get_min_clock)
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 7654ae5d2b4e..0115e9907bf8 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -430,6 +430,7 @@ struct sdhci_host {
 
 	/* Internal data */
 	struct mmc_host *mmc;	/* MMC structure */
+	struct mmc_host_ops mmc_host_ops;	/* MMC host ops */
 	u64 dma_mask;		/* custom DMA mask */
 
 #if defined(CONFIG_LEDS_CLASS) || defined(CONFIG_LEDS_CLASS_MODULE)
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index 1ca8a1359cbc..6234eab38ff3 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -445,7 +445,7 @@ static void sh_mmcif_request_dma(struct sh_mmcif_host *host)
 							pdata->slave_id_rx);
 	} else {
 		host->chan_tx = dma_request_slave_channel(dev, "tx");
-		host->chan_tx = dma_request_slave_channel(dev, "rx");
+		host->chan_rx = dma_request_slave_channel(dev, "rx");
 	}
 	dev_dbg(dev, "%s: got channel TX %p RX %p\n", __func__, host->chan_tx,
 		host->chan_rx);
diff --git a/drivers/mtd/tests/mtd_nandecctest.c b/drivers/mtd/tests/mtd_nandecctest.c
index 79316159eec6..88b6c81cebbe 100644
--- a/drivers/mtd/tests/mtd_nandecctest.c
+++ b/drivers/mtd/tests/mtd_nandecctest.c
@@ -187,7 +187,7 @@ static int double_bit_error_detect(void *error_data, void *error_ecc,
 	__nand_calculate_ecc(error_data, size, calc_ecc);
 	ret = __nand_correct_data(error_data, error_ecc, calc_ecc, size);
 
-	return (ret == -1) ? 0 : -EINVAL;
+	return (ret == -EBADMSG) ? 0 : -EINVAL;
 }
 
 static const struct nand_ecc_test nand_ecc_test[] = {
diff --git a/drivers/mtd/ubi/upd.c b/drivers/mtd/ubi/upd.c
index 2a1b6e037e1a..0134ba32a057 100644
--- a/drivers/mtd/ubi/upd.c
+++ b/drivers/mtd/ubi/upd.c
@@ -193,7 +193,7 @@ int ubi_start_leb_change(struct ubi_device *ubi, struct ubi_volume *vol,
 	vol->changing_leb = 1;
 	vol->ch_lnum = req->lnum;
 
-	vol->upd_buf = vmalloc(req->bytes);
+	vol->upd_buf = vmalloc(ALIGN((int)req->bytes, ubi->min_io_size));
 	if (!vol->upd_buf)
 		return -ENOMEM;
 
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 56b560558884..b7f1a9919033 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -214,6 +214,8 @@ static void bond_uninit(struct net_device *bond_dev);
 static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev,
 						struct rtnl_link_stats64 *stats);
 static void bond_slave_arr_handler(struct work_struct *work);
+static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
+				  int mod);
 
 /*---------------------------- General routines -----------------------------*/
 
@@ -2127,6 +2129,7 @@ static void bond_miimon_commit(struct bonding *bond)
 			continue;
 
 		case BOND_LINK_UP:
+			bond_update_speed_duplex(slave);
 			bond_set_slave_link_state(slave, BOND_LINK_UP,
 						  BOND_SLAVE_NOTIFY_NOW);
 			slave->last_link_up = jiffies;
@@ -2459,7 +2462,7 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
 		 struct slave *slave)
 {
 	struct arphdr *arp = (struct arphdr *)skb->data;
-	struct slave *curr_active_slave;
+	struct slave *curr_active_slave, *curr_arp_slave;
 	unsigned char *arp_ptr;
 	__be32 sip, tip;
 	int alen, is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP);
@@ -2506,26 +2509,41 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
 		     &sip, &tip);
 
 	curr_active_slave = rcu_dereference(bond->curr_active_slave);
+	curr_arp_slave = rcu_dereference(bond->current_arp_slave);
 
-	/* Backup slaves won't see the ARP reply, but do come through
-	 * here for each ARP probe (so we swap the sip/tip to validate
-	 * the probe).  In a "redundant switch, common router" type of
-	 * configuration, the ARP probe will (hopefully) travel from
-	 * the active, through one switch, the router, then the other
-	 * switch before reaching the backup.
+	/* We 'trust' the received ARP enough to validate it if:
+	 *
+	 * (a) the slave receiving the ARP is active (which includes the
+	 * current ARP slave, if any), or
+	 *
+	 * (b) the receiving slave isn't active, but there is a currently
+	 * active slave and it received valid arp reply(s) after it became
+	 * the currently active slave, or
+	 *
+	 * (c) there is an ARP slave that sent an ARP during the prior ARP
+	 * interval, and we receive an ARP reply on any slave.  We accept
+	 * these because switch FDB update delays may deliver the ARP
+	 * reply to a slave other than the sender of the ARP request.
 	 *
-	 * We 'trust' the arp requests if there is an active slave and
-	 * it received valid arp reply(s) after it became active. This
-	 * is done to avoid endless looping when we can't reach the
+	 * Note: for (b), backup slaves are receiving the broadcast ARP
+	 * request, not a reply.  This request passes from the sending
+	 * slave through the L2 switch(es) to the receiving slave.  Since
+	 * this is checking the request, sip/tip are swapped for
+	 * validation.
+	 *
+	 * This is done to avoid endless looping when we can't reach the
 	 * arp_ip_target and fool ourselves with our own arp requests.
 	 */
-
 	if (bond_is_active_slave(slave))
 		bond_validate_arp(bond, slave, sip, tip);
 	else if (curr_active_slave &&
 		 time_after(slave_last_rx(bond, curr_active_slave),
 			    curr_active_slave->last_link_up))
 		bond_validate_arp(bond, slave, tip, sip);
+	else if (curr_arp_slave && (arp->ar_op == htons(ARPOP_REPLY)) &&
+		 bond_time_in_interval(bond,
+				       dev_trans_start(curr_arp_slave->dev), 1))
+		bond_validate_arp(bond, slave, sip, tip);
 
 out_unlock:
 	if (arp != (struct arphdr *)skb->data)
diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index 575790e8a75a..74a7dfecee27 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -843,7 +843,7 @@ static irqreturn_t mcp251x_can_ist(int irq, void *dev_id)
 		if (clear_intf)
 			mcp251x_write_bits(spi, CANINTF, clear_intf, 0x00);
 
-		if (eflag)
+		if (eflag & (EFLG_RX0OVR | EFLG_RX1OVR))
 			mcp251x_write_bits(spi, EFLG, eflag, 0x00);
 
 		/* Update can state */
diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c
index fc5b75675cd8..eb7192fab593 100644
--- a/drivers/net/can/usb/ems_usb.c
+++ b/drivers/net/can/usb/ems_usb.c
@@ -117,6 +117,9 @@ MODULE_LICENSE("GPL v2");
  */
 #define EMS_USB_ARM7_CLOCK 8000000
 
+#define CPC_TX_QUEUE_TRIGGER_LOW	25
+#define CPC_TX_QUEUE_TRIGGER_HIGH	35
+
 /*
  * CAN-Message representation in a CPC_MSG. Message object type is
  * CPC_MSG_TYPE_CAN_FRAME or CPC_MSG_TYPE_RTR_FRAME or
@@ -278,6 +281,11 @@ static void ems_usb_read_interrupt_callback(struct urb *urb)
 	switch (urb->status) {
 	case 0:
 		dev->free_slots = dev->intr_in_buffer[1];
+		if(dev->free_slots > CPC_TX_QUEUE_TRIGGER_HIGH){
+			if (netif_queue_stopped(netdev)){
+				netif_wake_queue(netdev);
+			}
+		}
 		break;
 
 	case -ECONNRESET: /* unlink */
@@ -526,8 +534,6 @@ static void ems_usb_write_bulk_callback(struct urb *urb)
 	/* Release context */
 	context->echo_index = MAX_TX_URBS;
 
-	if (netif_queue_stopped(netdev))
-		netif_wake_queue(netdev);
 }
 
 /*
@@ -587,7 +593,7 @@ static int ems_usb_start(struct ems_usb *dev)
 	int err, i;
 
 	dev->intr_in_buffer[0] = 0;
-	dev->free_slots = 15; /* initial size */
+	dev->free_slots = 50; /* initial size */
 
 	for (i = 0; i < MAX_RX_URBS; i++) {
 		struct urb *urb = NULL;
@@ -835,7 +841,7 @@ static netdev_tx_t ems_usb_start_xmit(struct sk_buff *skb, struct net_device *ne
 
 		/* Slow down tx path */
 		if (atomic_read(&dev->active_tx_urbs) >= MAX_TX_URBS ||
-		    dev->free_slots < 5) {
+		    dev->free_slots < CPC_TX_QUEUE_TRIGGER_LOW) {
 			netif_stop_queue(netdev);
 		}
 	}
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 5eee62badf45..cbc99d5649af 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -826,9 +826,8 @@ static struct gs_can *gs_make_candev(unsigned int channel, struct usb_interface
 static void gs_destroy_candev(struct gs_can *dev)
 {
 	unregister_candev(dev->netdev);
-	free_candev(dev->netdev);
 	usb_kill_anchored_urbs(&dev->tx_submitted);
-	kfree(dev);
+	free_candev(dev->netdev);
 }
 
 static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id *id)
@@ -913,12 +912,15 @@ static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id *
 	for (i = 0; i < icount; i++) {
 		dev->canch[i] = gs_make_candev(i, intf);
 		if (IS_ERR_OR_NULL(dev->canch[i])) {
+			/* save error code to return later */
+			rc = PTR_ERR(dev->canch[i]);
+
 			/* on failure destroy previously created candevs */
 			icount = i;
-			for (i = 0; i < icount; i++) {
+			for (i = 0; i < icount; i++)
 				gs_destroy_candev(dev->canch[i]);
-				dev->canch[i] = NULL;
-			}
+
+			usb_kill_anchored_urbs(&dev->rx_submitted);
 			kfree(dev);
 			return rc;
 		}
@@ -939,16 +941,12 @@ static void gs_usb_disconnect(struct usb_interface *intf)
 		return;
 	}
 
-	for (i = 0; i < GS_MAX_INTF; i++) {
-		struct gs_can *can = dev->canch[i];
-
-		if (!can)
-			continue;
-
-		gs_destroy_candev(can);
-	}
+	for (i = 0; i < GS_MAX_INTF; i++)
+		if (dev->canch[i])
+			gs_destroy_candev(dev->canch[i]);
 
 	usb_kill_anchored_urbs(&dev->rx_submitted);
+	kfree(dev);
 }
 
 static const struct usb_device_id gs_usb_table[] = {
diff --git a/drivers/net/dsa/mv88e6352.c b/drivers/net/dsa/mv88e6352.c
index cc6c54553418..a47f52f44b0d 100644
--- a/drivers/net/dsa/mv88e6352.c
+++ b/drivers/net/dsa/mv88e6352.c
@@ -25,6 +25,7 @@
 static const struct mv88e6xxx_switch_id mv88e6352_table[] = {
 	{ PORT_SWITCH_ID_6172, "Marvell 88E6172" },
 	{ PORT_SWITCH_ID_6176, "Marvell 88E6176" },
+	{ PORT_SWITCH_ID_6240, "Marvell 88E6240" },
 	{ PORT_SWITCH_ID_6320, "Marvell 88E6320" },
 	{ PORT_SWITCH_ID_6320_A1, "Marvell 88E6320 (A1)" },
 	{ PORT_SWITCH_ID_6320_A2, "Marvell 88e6320 (A2)" },
diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c
index cf34681af4f6..512c8c0be1b4 100644
--- a/drivers/net/dsa/mv88e6xxx.c
+++ b/drivers/net/dsa/mv88e6xxx.c
@@ -1555,7 +1555,7 @@ static int _mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port, u16 vid)
 
 	if (vlan.vid != vid || !vlan.valid ||
 	    vlan.data[port] == GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER)
-		return -ENOENT;
+		return -EOPNOTSUPP;
 
 	vlan.data[port] = GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER;
 
@@ -1582,6 +1582,7 @@ int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port,
 			    const struct switchdev_obj_port_vlan *vlan)
 {
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	const u16 defpvid = 4000 + ds->index * DSA_MAX_PORTS + port;
 	u16 pvid, vid;
 	int err = 0;
 
@@ -1597,7 +1598,8 @@ int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port,
 			goto unlock;
 
 		if (vid == pvid) {
-			err = _mv88e6xxx_port_pvid_set(ds, port, 0);
+			/* restore reserved VLAN ID */
+			err = _mv88e6xxx_port_pvid_set(ds, port, defpvid);
 			if (err)
 				goto unlock;
 		}
@@ -1889,26 +1891,20 @@ unlock:
 
 int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port, u32 members)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
-	const u16 pvid = 4000 + ds->index * DSA_MAX_PORTS + port;
-	int err;
-
-	/* The port joined a bridge, so leave its reserved VLAN */
-	mutex_lock(&ps->smi_mutex);
-	err = _mv88e6xxx_port_vlan_del(ds, port, pvid);
-	if (!err)
-		err = _mv88e6xxx_port_pvid_set(ds, port, 0);
-	mutex_unlock(&ps->smi_mutex);
-	return err;
+	return 0;
 }
 
 int mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port, u32 members)
 {
+	return 0;
+}
+
+static int mv88e6xxx_setup_port_default_vlan(struct dsa_switch *ds, int port)
+{
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 	const u16 pvid = 4000 + ds->index * DSA_MAX_PORTS + port;
 	int err;
 
-	/* The port left the bridge, so join its reserved VLAN */
 	mutex_lock(&ps->smi_mutex);
 	err = _mv88e6xxx_port_vlan_add(ds, port, pvid, true);
 	if (!err)
@@ -2192,8 +2188,7 @@ int mv88e6xxx_setup_ports(struct dsa_switch *ds)
 		if (dsa_is_cpu_port(ds, i) || dsa_is_dsa_port(ds, i))
 			continue;
 
-		/* setup the unbridged state */
-		ret = mv88e6xxx_port_bridge_leave(ds, i, 0);
+		ret = mv88e6xxx_setup_port_default_vlan(ds, i);
 		if (ret < 0)
 			return ret;
 	}
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 79e1a0282163..17b2126075e0 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -2461,7 +2461,7 @@ boomerang_interrupt(int irq, void *dev_id)
 					int i;
 					pci_unmap_single(VORTEX_PCI(vp),
 							le32_to_cpu(vp->tx_ring[entry].frag[0].addr),
-							le32_to_cpu(vp->tx_ring[entry].frag[0].length),
+							le32_to_cpu(vp->tx_ring[entry].frag[0].length)&0xFFF,
 							PCI_DMA_TODEVICE);
 
 					for (i=1; i<=skb_shinfo(skb)->nr_frags; i++)
diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c
index 2777289a26c0..2f79d29f17f2 100644
--- a/drivers/net/ethernet/8390/pcnet_cs.c
+++ b/drivers/net/ethernet/8390/pcnet_cs.c
@@ -1501,6 +1501,7 @@ static const struct pcmcia_device_id pcnet_ids[] = {
 	PCMCIA_DEVICE_MANF_CARD(0x026f, 0x030a),
 	PCMCIA_DEVICE_MANF_CARD(0x0274, 0x1103),
 	PCMCIA_DEVICE_MANF_CARD(0x0274, 0x1121),
+	PCMCIA_DEVICE_MANF_CARD(0xc001, 0x0009),
 	PCMCIA_DEVICE_PROD_ID12("2408LAN", "Ethernet", 0x352fff7f, 0x00b2e941),
 	PCMCIA_DEVICE_PROD_ID1234("Socket", "CF 10/100 Ethernet Card", "Revision B", "05/11/06", 0xb38bcc2e, 0x4de88352, 0xeaca6c8d, 0x7e57c22e),
 	PCMCIA_DEVICE_PROD_ID123("Cardwell", "PCMCIA", "ETHERNET", 0x9533672e, 0x281f1c5d, 0x3ff7175b),
diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c
index 3f3bcbea15bd..0907ab6ff309 100644
--- a/drivers/net/ethernet/agere/et131x.c
+++ b/drivers/net/ethernet/agere/et131x.c
@@ -2380,7 +2380,7 @@ static int et131x_tx_dma_memory_alloc(struct et131x_adapter *adapter)
 						    sizeof(u32),
 						    &tx_ring->tx_status_pa,
 						    GFP_KERNEL);
-	if (!tx_ring->tx_status_pa) {
+	if (!tx_ring->tx_status) {
 		dev_err(&adapter->pdev->dev,
 			"Cannot alloc memory for Tx status block\n");
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c
index 17472851674f..f749e4d389eb 100644
--- a/drivers/net/ethernet/altera/altera_tse_main.c
+++ b/drivers/net/ethernet/altera/altera_tse_main.c
@@ -193,7 +193,6 @@ static void altera_tse_mdio_destroy(struct net_device *dev)
 			    priv->mdio->id);
 
 	mdiobus_unregister(priv->mdio);
-	kfree(priv->mdio->irq);
 	mdiobus_free(priv->mdio);
 	priv->mdio = NULL;
 }
diff --git a/drivers/net/ethernet/amd/am79c961a.c b/drivers/net/ethernet/amd/am79c961a.c
index 87e727b921dc..fcdf5dda448f 100644
--- a/drivers/net/ethernet/amd/am79c961a.c
+++ b/drivers/net/ethernet/amd/am79c961a.c
@@ -50,8 +50,8 @@ static const char version[] =
 static void write_rreg(u_long base, u_int reg, u_int val)
 {
 	asm volatile(
-	"str%?h	%1, [%2]	@ NET_RAP\n\t"
-	"str%?h	%0, [%2, #-4]	@ NET_RDP"
+	"strh	%1, [%2]	@ NET_RAP\n\t"
+	"strh	%0, [%2, #-4]	@ NET_RDP"
 	:
 	: "r" (val), "r" (reg), "r" (ISAIO_BASE + 0x0464));
 }
@@ -60,8 +60,8 @@ static inline unsigned short read_rreg(u_long base_addr, u_int reg)
 {
 	unsigned short v;
 	asm volatile(
-	"str%?h	%1, [%2]	@ NET_RAP\n\t"
-	"ldr%?h	%0, [%2, #-4]	@ NET_RDP"
+	"strh	%1, [%2]	@ NET_RAP\n\t"
+	"ldrh	%0, [%2, #-4]	@ NET_RDP"
 	: "=r" (v)
 	: "r" (reg), "r" (ISAIO_BASE + 0x0464));
 	return v;
@@ -70,8 +70,8 @@ static inline unsigned short read_rreg(u_long base_addr, u_int reg)
 static inline void write_ireg(u_long base, u_int reg, u_int val)
 {
 	asm volatile(
-	"str%?h	%1, [%2]	@ NET_RAP\n\t"
-	"str%?h	%0, [%2, #8]	@ NET_IDP"
+	"strh	%1, [%2]	@ NET_RAP\n\t"
+	"strh	%0, [%2, #8]	@ NET_IDP"
 	:
 	: "r" (val), "r" (reg), "r" (ISAIO_BASE + 0x0464));
 }
@@ -80,8 +80,8 @@ static inline unsigned short read_ireg(u_long base_addr, u_int reg)
 {
 	u_short v;
 	asm volatile(
-	"str%?h	%1, [%2]	@ NAT_RAP\n\t"
-	"ldr%?h	%0, [%2, #8]	@ NET_IDP\n\t"
+	"strh	%1, [%2]	@ NAT_RAP\n\t"
+	"ldrh	%0, [%2, #8]	@ NET_IDP\n\t"
 	: "=r" (v)
 	: "r" (reg), "r" (ISAIO_BASE + 0x0464));
 	return v;
@@ -96,7 +96,7 @@ am_writebuffer(struct net_device *dev, u_int offset, unsigned char *buf, unsigne
 	offset = ISAMEM_BASE + (offset << 1);
 	length = (length + 1) & ~1;
 	if ((int)buf & 2) {
-		asm volatile("str%?h	%2, [%0], #4"
+		asm volatile("strh	%2, [%0], #4"
 		 : "=&r" (offset) : "0" (offset), "r" (buf[0] | (buf[1] << 8)));
 		buf += 2;
 		length -= 2;
@@ -104,20 +104,20 @@ am_writebuffer(struct net_device *dev, u_int offset, unsigned char *buf, unsigne
 	while (length > 8) {
 		register unsigned int tmp asm("r2"), tmp2 asm("r3");
 		asm volatile(
-			"ldm%?ia	%0!, {%1, %2}"
+			"ldmia	%0!, {%1, %2}"
 			: "+r" (buf), "=&r" (tmp), "=&r" (tmp2));
 		length -= 8;
 		asm volatile(
-			"str%?h	%1, [%0], #4\n\t"
-			"mov%?	%1, %1, lsr #16\n\t"
-			"str%?h	%1, [%0], #4\n\t"
-			"str%?h	%2, [%0], #4\n\t"
-			"mov%?	%2, %2, lsr #16\n\t"
-			"str%?h	%2, [%0], #4"
+			"strh	%1, [%0], #4\n\t"
+			"mov	%1, %1, lsr #16\n\t"
+			"strh	%1, [%0], #4\n\t"
+			"strh	%2, [%0], #4\n\t"
+			"mov	%2, %2, lsr #16\n\t"
+			"strh	%2, [%0], #4"
 		: "+r" (offset), "=&r" (tmp), "=&r" (tmp2));
 	}
 	while (length > 0) {
-		asm volatile("str%?h	%2, [%0], #4"
+		asm volatile("strh	%2, [%0], #4"
 		 : "=&r" (offset) : "0" (offset), "r" (buf[0] | (buf[1] << 8)));
 		buf += 2;
 		length -= 2;
@@ -132,23 +132,23 @@ am_readbuffer(struct net_device *dev, u_int offset, unsigned char *buf, unsigned
 	if ((int)buf & 2) {
 		unsigned int tmp;
 		asm volatile(
-			"ldr%?h	%2, [%0], #4\n\t"
-			"str%?b	%2, [%1], #1\n\t"
-			"mov%?	%2, %2, lsr #8\n\t"
-			"str%?b	%2, [%1], #1"
+			"ldrh	%2, [%0], #4\n\t"
+			"strb	%2, [%1], #1\n\t"
+			"mov	%2, %2, lsr #8\n\t"
+			"strb	%2, [%1], #1"
 		: "=&r" (offset), "=&r" (buf), "=r" (tmp): "0" (offset), "1" (buf));
 		length -= 2;
 	}
 	while (length > 8) {
 		register unsigned int tmp asm("r2"), tmp2 asm("r3"), tmp3;
 		asm volatile(
-			"ldr%?h	%2, [%0], #4\n\t"
-			"ldr%?h	%4, [%0], #4\n\t"
-			"ldr%?h	%3, [%0], #4\n\t"
-			"orr%?	%2, %2, %4, lsl #16\n\t"
-			"ldr%?h	%4, [%0], #4\n\t"
-			"orr%?	%3, %3, %4, lsl #16\n\t"
-			"stm%?ia	%1!, {%2, %3}"
+			"ldrh	%2, [%0], #4\n\t"
+			"ldrh	%4, [%0], #4\n\t"
+			"ldrh	%3, [%0], #4\n\t"
+			"orr	%2, %2, %4, lsl #16\n\t"
+			"ldrh	%4, [%0], #4\n\t"
+			"orr	%3, %3, %4, lsl #16\n\t"
+			"stmia	%1!, {%2, %3}"
 		: "=&r" (offset), "=&r" (buf), "=r" (tmp), "=r" (tmp2), "=r" (tmp3)
 		: "0" (offset), "1" (buf));
 		length -= 8;
@@ -156,10 +156,10 @@ am_readbuffer(struct net_device *dev, u_int offset, unsigned char *buf, unsigned
 	while (length > 0) {
 		unsigned int tmp;
 		asm volatile(
-			"ldr%?h	%2, [%0], #4\n\t"
-			"str%?b	%2, [%1], #1\n\t"
-			"mov%?	%2, %2, lsr #8\n\t"
-			"str%?b	%2, [%1], #1"
+			"ldrh	%2, [%0], #4\n\t"
+			"strb	%2, [%1], #1\n\t"
+			"mov	%2, %2, lsr #8\n\t"
+			"strb	%2, [%1], #1"
 		: "=&r" (offset), "=&r" (buf), "=r" (tmp) : "0" (offset), "1" (buf));
 		length -= 2;
 	}
diff --git a/drivers/net/ethernet/amd/lance.c b/drivers/net/ethernet/amd/lance.c
index 256f590f6bb1..3a7ebfdda57d 100644
--- a/drivers/net/ethernet/amd/lance.c
+++ b/drivers/net/ethernet/amd/lance.c
@@ -547,8 +547,8 @@ static int __init lance_probe1(struct net_device *dev, int ioaddr, int irq, int
 	/* Make certain the data structures used by the LANCE are aligned and DMAble. */
 
 	lp = kzalloc(sizeof(*lp), GFP_DMA | GFP_KERNEL);
-	if(lp==NULL)
-		return -ENODEV;
+	if (!lp)
+		return -ENOMEM;
 	if (lance_debug > 6) printk(" (#0x%05lx)", (unsigned long)lp);
 	dev->ml_priv = lp;
 	lp->name = chipname;
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index abe1eabc0171..6446af1403f7 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -163,7 +163,7 @@ static void arc_emac_tx_clean(struct net_device *ndev)
 		struct sk_buff *skb = tx_buff->skb;
 		unsigned int info = le32_to_cpu(txbd->info);
 
-		if ((info & FOR_EMAC) || !txbd->data)
+		if ((info & FOR_EMAC) || !txbd->data || !skb)
 			break;
 
 		if (unlikely(info & (DROP | DEFR | LTCL | UFLO))) {
@@ -191,6 +191,7 @@ static void arc_emac_tx_clean(struct net_device *ndev)
 
 		txbd->data = 0;
 		txbd->info = 0;
+		tx_buff->skb = NULL;
 
 		*txbd_dirty = (*txbd_dirty + 1) % TX_BD_NUM;
 	}
@@ -446,6 +447,9 @@ static int arc_emac_open(struct net_device *ndev)
 		*last_rx_bd = (*last_rx_bd + 1) % RX_BD_NUM;
 	}
 
+	priv->txbd_curr = 0;
+	priv->txbd_dirty = 0;
+
 	/* Clean Tx BD's */
 	memset(priv->txbd, 0, TX_RING_SZ);
 
@@ -514,6 +518,64 @@ static void arc_emac_set_rx_mode(struct net_device *ndev)
 }
 
 /**
+ * arc_free_tx_queue - free skb from tx queue
+ * @ndev:	Pointer to the network device.
+ *
+ * This function must be called while EMAC disable
+ */
+static void arc_free_tx_queue(struct net_device *ndev)
+{
+	struct arc_emac_priv *priv = netdev_priv(ndev);
+	unsigned int i;
+
+	for (i = 0; i < TX_BD_NUM; i++) {
+		struct arc_emac_bd *txbd = &priv->txbd[i];
+		struct buffer_state *tx_buff = &priv->tx_buff[i];
+
+		if (tx_buff->skb) {
+			dma_unmap_single(&ndev->dev, dma_unmap_addr(tx_buff, addr),
+					 dma_unmap_len(tx_buff, len), DMA_TO_DEVICE);
+
+			/* return the sk_buff to system */
+			dev_kfree_skb_irq(tx_buff->skb);
+		}
+
+		txbd->info = 0;
+		txbd->data = 0;
+		tx_buff->skb = NULL;
+	}
+}
+
+/**
+ * arc_free_rx_queue - free skb from rx queue
+ * @ndev:	Pointer to the network device.
+ *
+ * This function must be called while EMAC disable
+ */
+static void arc_free_rx_queue(struct net_device *ndev)
+{
+	struct arc_emac_priv *priv = netdev_priv(ndev);
+	unsigned int i;
+
+	for (i = 0; i < RX_BD_NUM; i++) {
+		struct arc_emac_bd *rxbd = &priv->rxbd[i];
+		struct buffer_state *rx_buff = &priv->rx_buff[i];
+
+		if (rx_buff->skb) {
+			dma_unmap_single(&ndev->dev, dma_unmap_addr(rx_buff, addr),
+					dma_unmap_len(rx_buff, len), DMA_FROM_DEVICE);
+
+			/* return the sk_buff to system */
+			dev_kfree_skb_irq(rx_buff->skb);
+		}
+
+		rxbd->info = 0;
+		rxbd->data = 0;
+		rx_buff->skb = NULL;
+	}
+}
+
+/**
  * arc_emac_stop - Close the network device.
  * @ndev:	Pointer to the network device.
  *
@@ -534,6 +596,10 @@ static int arc_emac_stop(struct net_device *ndev)
 	/* Disable EMAC */
 	arc_reg_clr(priv, R_CTRL, EN_MASK);
 
+	/* Return the sk_buff to system */
+	arc_free_tx_queue(ndev);
+	arc_free_rx_queue(ndev);
+
 	return 0;
 }
 
@@ -610,7 +676,6 @@ static int arc_emac_tx(struct sk_buff *skb, struct net_device *ndev)
 	dma_unmap_addr_set(&priv->tx_buff[*txbd_curr], addr, addr);
 	dma_unmap_len_set(&priv->tx_buff[*txbd_curr], len, len);
 
-	priv->tx_buff[*txbd_curr].skb = skb;
 	priv->txbd[*txbd_curr].data = cpu_to_le32(addr);
 
 	/* Make sure pointer to data buffer is set */
@@ -620,6 +685,11 @@ static int arc_emac_tx(struct sk_buff *skb, struct net_device *ndev)
 
 	*info = cpu_to_le32(FOR_EMAC | FIRST_OR_LAST_MASK | len);
 
+	/* Make sure info word is set */
+	wmb();
+
+	priv->tx_buff[*txbd_curr].skb = skb;
+
 	/* Increment index to point to the next BD */
 	*txbd_curr = (*txbd_curr + 1) % TX_BD_NUM;
 
diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
index f71ab2647a3b..08a23e6b60e9 100644
--- a/drivers/net/ethernet/aurora/nb8800.c
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -1460,7 +1460,19 @@ static int nb8800_probe(struct platform_device *pdev)
 		goto err_disable_clk;
 	}
 
-	priv->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0);
+	if (of_phy_is_fixed_link(pdev->dev.of_node)) {
+		ret = of_phy_register_fixed_link(pdev->dev.of_node);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "bad fixed-link spec\n");
+			goto err_free_bus;
+		}
+		priv->phy_node = of_node_get(pdev->dev.of_node);
+	}
+
+	if (!priv->phy_node)
+		priv->phy_node = of_parse_phandle(pdev->dev.of_node,
+						  "phy-handle", 0);
+
 	if (!priv->phy_node) {
 		dev_err(&pdev->dev, "no PHY specified\n");
 		ret = -ENODEV;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
index 27aa0802d87d..91874d24fd56 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
@@ -4896,9 +4896,9 @@ struct c2s_pri_trans_table_entry {
  * cfc delete event data
  */
 struct cfc_del_event_data {
-	u32 cid;
-	u32 reserved0;
-	u32 reserved1;
+	__le32 cid;
+	__le32 reserved0;
+	__le32 reserved1;
 };
 
 
@@ -5114,15 +5114,9 @@ struct vf_pf_channel_zone_trigger {
  * zone that triggers the in-bound interrupt
  */
 struct trigger_vf_zone {
-#if defined(__BIG_ENDIAN)
-	u16 reserved1;
-	u8 reserved0;
-	struct vf_pf_channel_zone_trigger vf_pf_channel;
-#elif defined(__LITTLE_ENDIAN)
 	struct vf_pf_channel_zone_trigger vf_pf_channel;
 	u8 reserved0;
 	u16 reserved1;
-#endif
 	u32 reserved2;
 };
 
@@ -5207,9 +5201,9 @@ struct e2_integ_data {
  * set mac event data
  */
 struct eth_event_data {
-	u32 echo;
-	u32 reserved0;
-	u32 reserved1;
+	__le32 echo;
+	__le32 reserved0;
+	__le32 reserved1;
 };
 
 
@@ -5219,9 +5213,9 @@ struct eth_event_data {
 struct vf_pf_event_data {
 	u8 vf_id;
 	u8 reserved0;
-	u16 reserved1;
-	u32 msg_addr_lo;
-	u32 msg_addr_hi;
+	__le16 reserved1;
+	__le32 msg_addr_lo;
+	__le32 msg_addr_hi;
 };
 
 /*
@@ -5230,9 +5224,9 @@ struct vf_pf_event_data {
 struct vf_flr_event_data {
 	u8 vf_id;
 	u8 reserved0;
-	u16 reserved1;
-	u32 reserved2;
-	u32 reserved3;
+	__le16 reserved1;
+	__le32 reserved2;
+	__le32 reserved3;
 };
 
 /*
@@ -5241,9 +5235,9 @@ struct vf_flr_event_data {
 struct malicious_vf_event_data {
 	u8 vf_id;
 	u8 err_id;
-	u16 reserved1;
-	u32 reserved2;
-	u32 reserved3;
+	__le16 reserved1;
+	__le32 reserved2;
+	__le32 reserved3;
 };
 
 /*
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index d946bba43726..1fb80100e5e7 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -6185,26 +6185,80 @@ static int bnx2x_format_ver(u32 num, u8 *str, u16 *len)
 		shift -= 4;
 		digit = ((num & mask) >> shift);
 		if (digit == 0 && remove_leading_zeros) {
-			mask = mask >> 4;
-			continue;
-		} else if (digit < 0xa)
-			*str_ptr = digit + '0';
-		else
-			*str_ptr = digit - 0xa + 'a';
-		remove_leading_zeros = 0;
-		str_ptr++;
-		(*len)--;
+			*str_ptr = '0';
+		} else {
+			if (digit < 0xa)
+				*str_ptr = digit + '0';
+			else
+				*str_ptr = digit - 0xa + 'a';
+
+			remove_leading_zeros = 0;
+			str_ptr++;
+			(*len)--;
+		}
 		mask = mask >> 4;
 		if (shift == 4*4) {
+			if (remove_leading_zeros) {
+				str_ptr++;
+				(*len)--;
+			}
 			*str_ptr = '.';
 			str_ptr++;
 			(*len)--;
 			remove_leading_zeros = 1;
 		}
 	}
+	if (remove_leading_zeros)
+		(*len)--;
 	return 0;
 }
 
+static int bnx2x_3_seq_format_ver(u32 num, u8 *str, u16 *len)
+{
+	u8 *str_ptr = str;
+	u32 mask = 0x00f00000;
+	u8 shift = 8*3;
+	u8 digit;
+	u8 remove_leading_zeros = 1;
+
+	if (*len < 10) {
+		/* Need more than 10chars for this format */
+		*str_ptr = '\0';
+		(*len)--;
+		return -EINVAL;
+	}
+
+	while (shift > 0) {
+		shift -= 4;
+		digit = ((num & mask) >> shift);
+		if (digit == 0 && remove_leading_zeros) {
+			*str_ptr = '0';
+		} else {
+			if (digit < 0xa)
+				*str_ptr = digit + '0';
+			else
+				*str_ptr = digit - 0xa + 'a';
+
+			remove_leading_zeros = 0;
+			str_ptr++;
+			(*len)--;
+		}
+		mask = mask >> 4;
+		if ((shift == 4*4) || (shift == 4*2)) {
+			if (remove_leading_zeros) {
+				str_ptr++;
+				(*len)--;
+			}
+			*str_ptr = '.';
+			str_ptr++;
+			(*len)--;
+			remove_leading_zeros = 1;
+		}
+	}
+	if (remove_leading_zeros)
+		(*len)--;
+	return 0;
+}
 
 static int bnx2x_null_format_ver(u32 spirom_ver, u8 *str, u16 *len)
 {
@@ -9677,8 +9731,9 @@ static void bnx2x_save_848xx_spirom_version(struct bnx2x_phy *phy,
 
 	if (bnx2x_is_8483x_8485x(phy)) {
 		bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD, 0x400f, &fw_ver1);
-		bnx2x_save_spirom_version(bp, port, fw_ver1 & 0xfff,
-				phy->ver_addr);
+		if (phy->type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858)
+			fw_ver1 &= 0xfff;
+		bnx2x_save_spirom_version(bp, port, fw_ver1, phy->ver_addr);
 	} else {
 		/* For 32-bit registers in 848xx, access via MDIO2ARM i/f. */
 		/* (1) set reg 0xc200_0014(SPI_BRIDGE_CTRL_2) to 0x03000000 */
@@ -9732,16 +9787,32 @@ static void bnx2x_save_848xx_spirom_version(struct bnx2x_phy *phy,
 static void bnx2x_848xx_set_led(struct bnx2x *bp,
 				struct bnx2x_phy *phy)
 {
-	u16 val, offset, i;
+	u16 val, led3_blink_rate, offset, i;
 	static struct bnx2x_reg_set reg_set[] = {
 		{MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_LED1_MASK, 0x0080},
 		{MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_LED2_MASK, 0x0018},
 		{MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_LED3_MASK, 0x0006},
-		{MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_LED3_BLINK, 0x0000},
 		{MDIO_PMA_DEVAD, MDIO_PMA_REG_84823_CTL_SLOW_CLK_CNT_HIGH,
 			MDIO_PMA_REG_84823_BLINK_RATE_VAL_15P9HZ},
 		{MDIO_AN_DEVAD, 0xFFFB, 0xFFFD}
 	};
+
+	if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) {
+		/* Set LED5 source */
+		bnx2x_cl45_write(bp, phy,
+				 MDIO_PMA_DEVAD,
+				 MDIO_PMA_REG_8481_LED5_MASK,
+				 0x90);
+		led3_blink_rate = 0x000f;
+	} else {
+		led3_blink_rate = 0x0000;
+	}
+	/* Set LED3 BLINK */
+	bnx2x_cl45_write(bp, phy,
+			 MDIO_PMA_DEVAD,
+			 MDIO_PMA_REG_8481_LED3_BLINK,
+			 led3_blink_rate);
+
 	/* PHYC_CTL_LED_CTL */
 	bnx2x_cl45_read(bp, phy,
 			MDIO_PMA_DEVAD,
@@ -9749,6 +9820,9 @@ static void bnx2x_848xx_set_led(struct bnx2x *bp,
 	val &= 0xFE00;
 	val |= 0x0092;
 
+	if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858)
+		val |= 2 << 12; /* LED5 ON based on source */
+
 	bnx2x_cl45_write(bp, phy,
 			 MDIO_PMA_DEVAD,
 			 MDIO_PMA_REG_8481_LINK_SIGNAL, val);
@@ -9762,10 +9836,17 @@ static void bnx2x_848xx_set_led(struct bnx2x *bp,
 	else
 		offset = MDIO_PMA_REG_84823_CTL_LED_CTL_1;
 
-	/* stretch_en for LED3*/
+	if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858)
+		val = MDIO_PMA_REG_84858_ALLOW_GPHY_ACT |
+		      MDIO_PMA_REG_84823_LED3_STRETCH_EN;
+	else
+		val = MDIO_PMA_REG_84823_LED3_STRETCH_EN;
+
+	/* stretch_en for LEDs */
 	bnx2x_cl45_read_or_write(bp, phy,
-				 MDIO_PMA_DEVAD, offset,
-				 MDIO_PMA_REG_84823_LED3_STRETCH_EN);
+				 MDIO_PMA_DEVAD,
+				 offset,
+				 val);
 }
 
 static void bnx2x_848xx_specific_func(struct bnx2x_phy *phy,
@@ -9775,7 +9856,7 @@ static void bnx2x_848xx_specific_func(struct bnx2x_phy *phy,
 	struct bnx2x *bp = params->bp;
 	switch (action) {
 	case PHY_INIT:
-		if (!bnx2x_is_8483x_8485x(phy)) {
+		if (bnx2x_is_8483x_8485x(phy)) {
 			/* Save spirom version */
 			bnx2x_save_848xx_spirom_version(phy, bp, params->port);
 		}
@@ -10036,15 +10117,20 @@ static int bnx2x_84858_cmd_hdlr(struct bnx2x_phy *phy,
 
 static int bnx2x_84833_cmd_hdlr(struct bnx2x_phy *phy,
 				struct link_params *params, u16 fw_cmd,
-				u16 cmd_args[], int argc)
+				u16 cmd_args[], int argc, int process)
 {
 	int idx;
 	u16 val;
 	struct bnx2x *bp = params->bp;
-	/* Write CMD_OPEN_OVERRIDE to STATUS reg */
-	bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
-			MDIO_848xx_CMD_HDLR_STATUS,
-			PHY84833_STATUS_CMD_OPEN_OVERRIDE);
+	int rc = 0;
+
+	if (process == PHY84833_MB_PROCESS2) {
+		/* Write CMD_OPEN_OVERRIDE to STATUS reg */
+		bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
+				 MDIO_848xx_CMD_HDLR_STATUS,
+				 PHY84833_STATUS_CMD_OPEN_OVERRIDE);
+	}
+
 	for (idx = 0; idx < PHY848xx_CMDHDLR_WAIT; idx++) {
 		bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD,
 				MDIO_848xx_CMD_HDLR_STATUS, &val);
@@ -10054,15 +10140,27 @@ static int bnx2x_84833_cmd_hdlr(struct bnx2x_phy *phy,
 	}
 	if (idx >= PHY848xx_CMDHDLR_WAIT) {
 		DP(NETIF_MSG_LINK, "FW cmd: FW not ready.\n");
+		/* if the status is CMD_COMPLETE_PASS or CMD_COMPLETE_ERROR
+		 * clear the status to CMD_CLEAR_COMPLETE
+		 */
+		if (val == PHY84833_STATUS_CMD_COMPLETE_PASS ||
+		    val == PHY84833_STATUS_CMD_COMPLETE_ERROR) {
+			bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
+					 MDIO_848xx_CMD_HDLR_STATUS,
+					 PHY84833_STATUS_CMD_CLEAR_COMPLETE);
+		}
 		return -EINVAL;
 	}
-
-	/* Prepare argument(s) and issue command */
-	for (idx = 0; idx < argc; idx++) {
-		bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
-				MDIO_848xx_CMD_HDLR_DATA1 + idx,
-				cmd_args[idx]);
+	if (process == PHY84833_MB_PROCESS1 ||
+	    process == PHY84833_MB_PROCESS2) {
+		/* Prepare argument(s) */
+		for (idx = 0; idx < argc; idx++) {
+			bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
+					 MDIO_848xx_CMD_HDLR_DATA1 + idx,
+					 cmd_args[idx]);
+		}
 	}
+
 	bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
 			MDIO_848xx_CMD_HDLR_COMMAND, fw_cmd);
 	for (idx = 0; idx < PHY848xx_CMDHDLR_WAIT; idx++) {
@@ -10076,24 +10174,30 @@ static int bnx2x_84833_cmd_hdlr(struct bnx2x_phy *phy,
 	if ((idx >= PHY848xx_CMDHDLR_WAIT) ||
 	    (val == PHY84833_STATUS_CMD_COMPLETE_ERROR)) {
 		DP(NETIF_MSG_LINK, "FW cmd failed.\n");
-		return -EINVAL;
+		rc = -EINVAL;
 	}
-	/* Gather returning data */
-	for (idx = 0; idx < argc; idx++) {
-		bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD,
-				MDIO_848xx_CMD_HDLR_DATA1 + idx,
-				&cmd_args[idx]);
+	if (process == PHY84833_MB_PROCESS3 && rc == 0) {
+		/* Gather returning data */
+		for (idx = 0; idx < argc; idx++) {
+			bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD,
+					MDIO_848xx_CMD_HDLR_DATA1 + idx,
+					&cmd_args[idx]);
+		}
 	}
-	bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
-			MDIO_848xx_CMD_HDLR_STATUS,
-			PHY84833_STATUS_CMD_CLEAR_COMPLETE);
-	return 0;
+	if (val == PHY84833_STATUS_CMD_COMPLETE_ERROR ||
+	    val == PHY84833_STATUS_CMD_COMPLETE_PASS) {
+		bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
+				 MDIO_848xx_CMD_HDLR_STATUS,
+				 PHY84833_STATUS_CMD_CLEAR_COMPLETE);
+	}
+	return rc;
 }
 
 static int bnx2x_848xx_cmd_hdlr(struct bnx2x_phy *phy,
 				struct link_params *params,
 				u16 fw_cmd,
-				u16 cmd_args[], int argc)
+					   u16 cmd_args[], int argc,
+					   int process)
 {
 	struct bnx2x *bp = params->bp;
 
@@ -10106,7 +10210,7 @@ static int bnx2x_848xx_cmd_hdlr(struct bnx2x_phy *phy,
 					    argc);
 	} else {
 		return bnx2x_84833_cmd_hdlr(phy, params, fw_cmd, cmd_args,
-					    argc);
+					    argc, process);
 	}
 }
 
@@ -10133,7 +10237,7 @@ static int bnx2x_848xx_pair_swap_cfg(struct bnx2x_phy *phy,
 
 	status = bnx2x_848xx_cmd_hdlr(phy, params,
 				      PHY848xx_CMD_SET_PAIR_SWAP, data,
-				      PHY848xx_CMDHDLR_MAX_ARGS);
+				      2, PHY84833_MB_PROCESS2);
 	if (status == 0)
 		DP(NETIF_MSG_LINK, "Pairswap OK, val=0x%x\n", data[1]);
 
@@ -10222,8 +10326,8 @@ static int bnx2x_8483x_disable_eee(struct bnx2x_phy *phy,
 	DP(NETIF_MSG_LINK, "Don't Advertise 10GBase-T EEE\n");
 
 	/* Prevent Phy from working in EEE and advertising it */
-	rc = bnx2x_848xx_cmd_hdlr(phy, params,
-				  PHY848xx_CMD_SET_EEE_MODE, &cmd_args, 1);
+	rc = bnx2x_848xx_cmd_hdlr(phy, params, PHY848xx_CMD_SET_EEE_MODE,
+				  &cmd_args, 1, PHY84833_MB_PROCESS1);
 	if (rc) {
 		DP(NETIF_MSG_LINK, "EEE disable failed.\n");
 		return rc;
@@ -10240,8 +10344,8 @@ static int bnx2x_8483x_enable_eee(struct bnx2x_phy *phy,
 	struct bnx2x *bp = params->bp;
 	u16 cmd_args = 1;
 
-	rc = bnx2x_848xx_cmd_hdlr(phy, params,
-				  PHY848xx_CMD_SET_EEE_MODE, &cmd_args, 1);
+	rc = bnx2x_848xx_cmd_hdlr(phy, params, PHY848xx_CMD_SET_EEE_MODE,
+				  &cmd_args, 1, PHY84833_MB_PROCESS1);
 	if (rc) {
 		DP(NETIF_MSG_LINK, "EEE enable failed.\n");
 		return rc;
@@ -10362,7 +10466,7 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy,
 		cmd_args[3] = PHY84833_CONSTANT_LATENCY;
 		rc = bnx2x_848xx_cmd_hdlr(phy, params,
 					  PHY848xx_CMD_SET_EEE_MODE, cmd_args,
-					  PHY848xx_CMDHDLR_MAX_ARGS);
+					  4, PHY84833_MB_PROCESS1);
 		if (rc)
 			DP(NETIF_MSG_LINK, "Cfg AutogrEEEn failed.\n");
 	}
@@ -10416,6 +10520,32 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy,
 		vars->eee_status &= ~SHMEM_EEE_SUPPORTED_MASK;
 	}
 
+	if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) {
+		/* Additional settings for jumbo packets in 1000BASE-T mode */
+		/* Allow rx extended length */
+		bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD,
+				MDIO_AN_REG_8481_AUX_CTRL, &val);
+		val |= 0x4000;
+		bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD,
+				 MDIO_AN_REG_8481_AUX_CTRL, val);
+		/* TX FIFO Elasticity LSB */
+		bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD,
+				MDIO_AN_REG_8481_1G_100T_EXT_CTRL, &val);
+		val |= 0x1;
+		bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD,
+				 MDIO_AN_REG_8481_1G_100T_EXT_CTRL, val);
+		/* TX FIFO Elasticity MSB */
+		/* Enable expansion register 0x46 (Pattern Generator status) */
+		bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD,
+				 MDIO_AN_REG_8481_EXPANSION_REG_ACCESS, 0xf46);
+
+		bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD,
+				MDIO_AN_REG_8481_EXPANSION_REG_RD_RW, &val);
+		val |= 0x4000;
+		bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD,
+				 MDIO_AN_REG_8481_EXPANSION_REG_RD_RW, val);
+	}
+
 	if (bnx2x_is_8483x_8485x(phy)) {
 		/* Bring PHY out of super isolate mode as the final step. */
 		bnx2x_cl45_read_and_write(bp, phy,
@@ -10555,6 +10685,17 @@ static u8 bnx2x_848xx_read_status(struct bnx2x_phy *phy,
 	return link_up;
 }
 
+static int bnx2x_8485x_format_ver(u32 raw_ver, u8 *str, u16 *len)
+{
+	int status = 0;
+	u32 num;
+
+	num = ((raw_ver & 0xF80) >> 7) << 16 | ((raw_ver & 0x7F) << 8) |
+	      ((raw_ver & 0xF000) >> 12);
+	status = bnx2x_3_seq_format_ver(num, str, len);
+	return status;
+}
+
 static int bnx2x_848xx_format_ver(u32 raw_ver, u8 *str, u16 *len)
 {
 	int status = 0;
@@ -10651,10 +10792,25 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy,
 					0x0);
 
 		} else {
+			/* LED 1 OFF */
 			bnx2x_cl45_write(bp, phy,
 					 MDIO_PMA_DEVAD,
 					 MDIO_PMA_REG_8481_LED1_MASK,
 					 0x0);
+
+			if (phy->type ==
+				PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) {
+				/* LED 2 OFF */
+				bnx2x_cl45_write(bp, phy,
+						 MDIO_PMA_DEVAD,
+						 MDIO_PMA_REG_8481_LED2_MASK,
+						 0x0);
+				/* LED 3 OFF */
+				bnx2x_cl45_write(bp, phy,
+						 MDIO_PMA_DEVAD,
+						 MDIO_PMA_REG_8481_LED3_MASK,
+						 0x0);
+			}
 		}
 		break;
 	case LED_MODE_FRONT_PANEL_OFF:
@@ -10713,6 +10869,19 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy,
 						 MDIO_PMA_REG_8481_SIGNAL_MASK,
 						 0x0);
 			}
+			if (phy->type ==
+				PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) {
+				/* LED 2 OFF */
+				bnx2x_cl45_write(bp, phy,
+						 MDIO_PMA_DEVAD,
+						 MDIO_PMA_REG_8481_LED2_MASK,
+						 0x0);
+				/* LED 3 OFF */
+				bnx2x_cl45_write(bp, phy,
+						 MDIO_PMA_DEVAD,
+						 MDIO_PMA_REG_8481_LED3_MASK,
+						 0x0);
+			}
 		}
 		break;
 	case LED_MODE_ON:
@@ -10776,6 +10945,25 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy,
 						params->port*4,
 						NIG_MASK_MI_INT);
 				}
+			}
+			if (phy->type ==
+			    PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) {
+				/* Tell LED3 to constant on */
+				bnx2x_cl45_read(bp, phy,
+						MDIO_PMA_DEVAD,
+						MDIO_PMA_REG_8481_LINK_SIGNAL,
+						&val);
+				val &= ~(7<<6);
+				val |= (2<<6);  /* A83B[8:6]= 2 */
+				bnx2x_cl45_write(bp, phy,
+						 MDIO_PMA_DEVAD,
+						 MDIO_PMA_REG_8481_LINK_SIGNAL,
+						 val);
+				bnx2x_cl45_write(bp, phy,
+						 MDIO_PMA_DEVAD,
+						 MDIO_PMA_REG_8481_LED3_MASK,
+						 0x20);
+			} else {
 				bnx2x_cl45_write(bp, phy,
 						 MDIO_PMA_DEVAD,
 						 MDIO_PMA_REG_8481_SIGNAL_MASK,
@@ -10854,6 +11042,17 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy,
 					 MDIO_PMA_REG_8481_LINK_SIGNAL,
 					 val);
 			if (phy->type ==
+			    PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) {
+				bnx2x_cl45_write(bp, phy,
+						 MDIO_PMA_DEVAD,
+						 MDIO_PMA_REG_8481_LED2_MASK,
+						 0x18);
+				bnx2x_cl45_write(bp, phy,
+						 MDIO_PMA_DEVAD,
+						 MDIO_PMA_REG_8481_LED3_MASK,
+						 0x06);
+			}
+			if (phy->type ==
 			    PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84834) {
 				/* Restore LED4 source to external link,
 				 * and re-enable interrupts.
@@ -11982,7 +12181,7 @@ static const struct bnx2x_phy phy_84858 = {
 	.read_status	= (read_status_t)bnx2x_848xx_read_status,
 	.link_reset	= (link_reset_t)bnx2x_848x3_link_reset,
 	.config_loopback = (config_loopback_t)NULL,
-	.format_fw_ver	= (format_fw_ver_t)bnx2x_848xx_format_ver,
+	.format_fw_ver	= (format_fw_ver_t)bnx2x_8485x_format_ver,
 	.hw_reset	= (hw_reset_t)bnx2x_84833_hw_reset_phy,
 	.set_link_led	= (set_link_led_t)bnx2x_848xx_set_link_led,
 	.phy_specific_func = (phy_specific_func_t)bnx2x_848xx_specific_func
@@ -13807,8 +14006,10 @@ void bnx2x_period_func(struct link_params *params, struct link_vars *vars)
 	if (CHIP_IS_E3(bp)) {
 		struct bnx2x_phy *phy = &params->phy[INT_PHY];
 		bnx2x_set_aer_mmd(params, phy);
-		if ((phy->supported & SUPPORTED_20000baseKR2_Full) &&
-		    (phy->speed_cap_mask & PORT_HW_CFG_SPEED_CAPABILITY_D0_20G))
+		if (((phy->req_line_speed == SPEED_AUTO_NEG) &&
+		     (phy->speed_cap_mask &
+		      PORT_HW_CFG_SPEED_CAPABILITY_D0_20G)) ||
+		    (phy->req_line_speed == SPEED_20000))
 			bnx2x_check_kr2_wa(params, vars, phy);
 		bnx2x_check_over_curr(params, vars);
 		if (vars->rx_tx_asic_rst)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 6c4e3a69976f..2bf9c871144f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -5280,14 +5280,14 @@ static void bnx2x_handle_classification_eqe(struct bnx2x *bp,
 {
 	unsigned long ramrod_flags = 0;
 	int rc = 0;
-	u32 cid = elem->message.data.eth_event.echo & BNX2X_SWCID_MASK;
+	u32 echo = le32_to_cpu(elem->message.data.eth_event.echo);
+	u32 cid = echo & BNX2X_SWCID_MASK;
 	struct bnx2x_vlan_mac_obj *vlan_mac_obj;
 
 	/* Always push next commands out, don't wait here */
 	__set_bit(RAMROD_CONT, &ramrod_flags);
 
-	switch (le32_to_cpu((__force __le32)elem->message.data.eth_event.echo)
-			    >> BNX2X_SWCID_SHIFT) {
+	switch (echo >> BNX2X_SWCID_SHIFT) {
 	case BNX2X_FILTER_MAC_PENDING:
 		DP(BNX2X_MSG_SP, "Got SETUP_MAC completions\n");
 		if (CNIC_LOADED(bp) && (cid == BNX2X_ISCSI_ETH_CID(bp)))
@@ -5308,8 +5308,7 @@ static void bnx2x_handle_classification_eqe(struct bnx2x *bp,
 		bnx2x_handle_mcast_eqe(bp);
 		return;
 	default:
-		BNX2X_ERR("Unsupported classification command: %d\n",
-			  elem->message.data.eth_event.echo);
+		BNX2X_ERR("Unsupported classification command: 0x%x\n", echo);
 		return;
 	}
 
@@ -5478,9 +5477,6 @@ static void bnx2x_eq_int(struct bnx2x *bp)
 			goto next_spqe;
 		}
 
-		/* elem CID originates from FW; actually LE */
-		cid = SW_CID((__force __le32)
-			     elem->message.data.cfc_del_event.cid);
 		opcode = elem->message.opcode;
 
 		/* handle eq element */
@@ -5503,6 +5499,10 @@ static void bnx2x_eq_int(struct bnx2x *bp)
 			 * we may want to verify here that the bp state is
 			 * HALTING
 			 */
+
+			/* elem CID originates from FW; actually LE */
+			cid = SW_CID(elem->message.data.cfc_del_event.cid);
+
 			DP(BNX2X_MSG_SP,
 			   "got delete ramrod for MULTI[%d]\n", cid);
 
@@ -5596,10 +5596,8 @@ static void bnx2x_eq_int(struct bnx2x *bp)
 		      BNX2X_STATE_OPENING_WAIT4_PORT):
 		case (EVENT_RING_OPCODE_RSS_UPDATE_RULES |
 		      BNX2X_STATE_CLOSING_WAIT4_HALT):
-			cid = elem->message.data.eth_event.echo &
-				BNX2X_SWCID_MASK;
 			DP(BNX2X_MSG_SP, "got RSS_UPDATE ramrod. CID %d\n",
-			   cid);
+			   SW_CID(elem->message.data.eth_event.echo));
 			rss_raw->clear_pending(rss_raw);
 			break;
 
@@ -5684,7 +5682,7 @@ static void bnx2x_sp_task(struct work_struct *work)
 		if (status & BNX2X_DEF_SB_IDX) {
 			struct bnx2x_fastpath *fp = bnx2x_fcoe_fp(bp);
 
-		if (FCOE_INIT(bp) &&
+			if (FCOE_INIT(bp) &&
 			    (bnx2x_has_rx_work(fp) || bnx2x_has_tx_work(fp))) {
 				/* Prevent local bottom-halves from running as
 				 * we are going to change the local NAPI list.
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
index 4dead49bd5cb..a43dea259b12 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
@@ -7296,6 +7296,8 @@ Theotherbitsarereservedandshouldbezero*/
 #define MDIO_PMA_REG_84823_CTL_LED_CTL_1			0xa8e3
 #define MDIO_PMA_REG_84833_CTL_LED_CTL_1			0xa8ec
 #define MDIO_PMA_REG_84823_LED3_STRETCH_EN			0x0080
+/* BCM84858 only */
+#define MDIO_PMA_REG_84858_ALLOW_GPHY_ACT			0x8000
 
 /* BCM84833 only */
 #define MDIO_84833_TOP_CFG_FW_REV			0x400f
@@ -7337,6 +7339,10 @@ Theotherbitsarereservedandshouldbezero*/
 #define PHY84833_STATUS_CMD_NOT_OPEN_FOR_CMDS		0x0040
 #define PHY84833_STATUS_CMD_CLEAR_COMPLETE		0x0080
 #define PHY84833_STATUS_CMD_OPEN_OVERRIDE		0xa5a5
+/* Mailbox Process */
+#define PHY84833_MB_PROCESS1				1
+#define PHY84833_MB_PROCESS2				2
+#define PHY84833_MB_PROCESS3				3
 
 /* Mailbox status set used by 84858 only */
 #define PHY84858_STATUS_CMD_RECEIVED			0x0001
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 9d027348cd09..632daff117d3 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -1672,11 +1672,12 @@ void bnx2x_vf_handle_classification_eqe(struct bnx2x *bp,
 {
 	unsigned long ramrod_flags = 0;
 	int rc = 0;
+	u32 echo = le32_to_cpu(elem->message.data.eth_event.echo);
 
 	/* Always push next commands out, don't wait here */
 	set_bit(RAMROD_CONT, &ramrod_flags);
 
-	switch (elem->message.data.eth_event.echo >> BNX2X_SWCID_SHIFT) {
+	switch (echo >> BNX2X_SWCID_SHIFT) {
 	case BNX2X_FILTER_MAC_PENDING:
 		rc = vfq->mac_obj.complete(bp, &vfq->mac_obj, elem,
 					   &ramrod_flags);
@@ -1686,8 +1687,7 @@ void bnx2x_vf_handle_classification_eqe(struct bnx2x *bp,
 					    &ramrod_flags);
 		break;
 	default:
-		BNX2X_ERR("Unsupported classification command: %d\n",
-			  elem->message.data.eth_event.echo);
+		BNX2X_ERR("Unsupported classification command: 0x%x\n", echo);
 		return;
 	}
 	if (rc < 0)
@@ -1747,16 +1747,14 @@ int bnx2x_iov_eq_sp_event(struct bnx2x *bp, union event_ring_elem *elem)
 
 	switch (opcode) {
 	case EVENT_RING_OPCODE_CFC_DEL:
-		cid = SW_CID((__force __le32)
-			     elem->message.data.cfc_del_event.cid);
+		cid = SW_CID(elem->message.data.cfc_del_event.cid);
 		DP(BNX2X_MSG_IOV, "checking cfc-del comp cid=%d\n", cid);
 		break;
 	case EVENT_RING_OPCODE_CLASSIFICATION_RULES:
 	case EVENT_RING_OPCODE_MULTICAST_RULES:
 	case EVENT_RING_OPCODE_FILTERS_RULES:
 	case EVENT_RING_OPCODE_RSS_UPDATE_RULES:
-		cid = (elem->message.data.eth_event.echo &
-		       BNX2X_SWCID_MASK);
+		cid = SW_CID(elem->message.data.eth_event.echo);
 		DP(BNX2X_MSG_IOV, "checking filtering comp cid=%d\n", cid);
 		break;
 	case EVENT_RING_OPCODE_VF_FLR:
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 1374e5394a79..bfae300cf25f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -2187,8 +2187,10 @@ void bnx2x_vf_mbx_schedule(struct bnx2x *bp,
 
 	/* Update VFDB with current message and schedule its handling */
 	mutex_lock(&BP_VFDB(bp)->event_mutex);
-	BP_VF_MBX(bp, vf_idx)->vf_addr_hi = vfpf_event->msg_addr_hi;
-	BP_VF_MBX(bp, vf_idx)->vf_addr_lo = vfpf_event->msg_addr_lo;
+	BP_VF_MBX(bp, vf_idx)->vf_addr_hi =
+		le32_to_cpu(vfpf_event->msg_addr_hi);
+	BP_VF_MBX(bp, vf_idx)->vf_addr_lo =
+		le32_to_cpu(vfpf_event->msg_addr_lo);
 	BP_VFDB(bp)->event_occur |= (1ULL << vf_idx);
 	mutex_unlock(&BP_VFDB(bp)->event_mutex);
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 5dc89e527e7d..82f191382989 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -69,7 +69,7 @@ MODULE_VERSION(DRV_MODULE_VERSION);
 #define BNXT_RX_DMA_OFFSET NET_SKB_PAD
 #define BNXT_RX_COPY_THRESH 256
 
-#define BNXT_TX_PUSH_THRESH 92
+#define BNXT_TX_PUSH_THRESH 164
 
 enum board_idx {
 	BCM57301,
@@ -223,11 +223,12 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	if (free_size == bp->tx_ring_size && length <= bp->tx_push_thresh) {
-		struct tx_push_bd *push = txr->tx_push;
-		struct tx_bd *tx_push = &push->txbd1;
-		struct tx_bd_ext *tx_push1 = &push->txbd2;
-		void *pdata = tx_push1 + 1;
-		int j;
+		struct tx_push_buffer *tx_push_buf = txr->tx_push;
+		struct tx_push_bd *tx_push = &tx_push_buf->push_bd;
+		struct tx_bd_ext *tx_push1 = &tx_push->txbd2;
+		void *pdata = tx_push_buf->data;
+		u64 *end;
+		int j, push_len;
 
 		/* Set COAL_NOW to be ready quickly for the next push */
 		tx_push->tx_bd_len_flags_type =
@@ -247,6 +248,10 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		tx_push1->tx_bd_cfa_meta = cpu_to_le32(vlan_tag_flags);
 		tx_push1->tx_bd_cfa_action = cpu_to_le32(cfa_action);
 
+		end = pdata + length;
+		end = PTR_ALIGN(end, 8) - 1;
+		*end = 0;
+
 		skb_copy_from_linear_data(skb, pdata, len);
 		pdata += len;
 		for (j = 0; j < last_frag; j++) {
@@ -261,22 +266,29 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			pdata += skb_frag_size(frag);
 		}
 
-		memcpy(txbd, tx_push, sizeof(*txbd));
+		txbd->tx_bd_len_flags_type = tx_push->tx_bd_len_flags_type;
+		txbd->tx_bd_haddr = txr->data_mapping;
 		prod = NEXT_TX(prod);
 		txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
 		memcpy(txbd, tx_push1, sizeof(*txbd));
 		prod = NEXT_TX(prod);
-		push->doorbell =
+		tx_push->doorbell =
 			cpu_to_le32(DB_KEY_TX_PUSH | DB_LONG_TX_PUSH | prod);
 		txr->tx_prod = prod;
 
 		netdev_tx_sent_queue(txq, skb->len);
 
-		__iowrite64_copy(txr->tx_doorbell, push,
-				 (length + sizeof(*push) + 8) / 8);
+		push_len = (length + sizeof(*tx_push) + 7) / 8;
+		if (push_len > 16) {
+			__iowrite64_copy(txr->tx_doorbell, tx_push_buf, 16);
+			__iowrite64_copy(txr->tx_doorbell + 4, tx_push_buf + 1,
+					 push_len - 16);
+		} else {
+			__iowrite64_copy(txr->tx_doorbell, tx_push_buf,
+					 push_len);
+		}
 
 		tx_buf->is_push = 1;
-
 		goto tx_done;
 	}
 
@@ -1753,7 +1765,7 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp)
 		push_size  = L1_CACHE_ALIGN(sizeof(struct tx_push_bd) +
 					bp->tx_push_thresh);
 
-		if (push_size > 128) {
+		if (push_size > 256) {
 			push_size = 0;
 			bp->tx_push_thresh = 0;
 		}
@@ -1772,7 +1784,6 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp)
 			return rc;
 
 		if (bp->tx_push_size) {
-			struct tx_bd *txbd;
 			dma_addr_t mapping;
 
 			/* One pre-allocated DMA buffer to backup
@@ -1786,13 +1797,11 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp)
 			if (!txr->tx_push)
 				return -ENOMEM;
 
-			txbd = &txr->tx_push->txbd1;
-
 			mapping = txr->tx_push_mapping +
 				sizeof(struct tx_push_bd);
-			txbd->tx_bd_haddr = cpu_to_le64(mapping);
+			txr->data_mapping = cpu_to_le64(mapping);
 
-			memset(txbd + 1, 0, sizeof(struct tx_bd_ext));
+			memset(txr->tx_push, 0, sizeof(struct tx_push_bd));
 		}
 		ring->queue_id = bp->q_info[j].queue_id;
 		if (i % bp->tx_nr_rings_per_tc == (bp->tx_nr_rings_per_tc - 1))
@@ -4546,20 +4555,18 @@ static int bnxt_update_phy_setting(struct bnxt *bp)
 	if (!(link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL) &&
 	    link_info->force_pause_setting != link_info->req_flow_ctrl)
 		update_pause = true;
-	if (link_info->req_duplex != link_info->duplex_setting)
-		update_link = true;
 	if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) {
 		if (BNXT_AUTO_MODE(link_info->auto_mode))
 			update_link = true;
 		if (link_info->req_link_speed != link_info->force_link_speed)
 			update_link = true;
+		if (link_info->req_duplex != link_info->duplex_setting)
+			update_link = true;
 	} else {
 		if (link_info->auto_mode == BNXT_LINK_AUTO_NONE)
 			update_link = true;
 		if (link_info->advertising != link_info->auto_link_speeds)
 			update_link = true;
-		if (link_info->req_link_speed != link_info->auto_link_speed)
-			update_link = true;
 	}
 
 	if (update_link)
@@ -4636,7 +4643,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	if (link_re_init) {
 		rc = bnxt_update_phy_setting(bp);
 		if (rc)
-			goto open_err;
+			netdev_warn(bp->dev, "failed to update phy settings\n");
 	}
 
 	if (irq_re_init) {
@@ -4654,6 +4661,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	/* Enable TX queues */
 	bnxt_tx_enable(bp);
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
+	bnxt_update_link(bp, true);
 
 	return 0;
 
@@ -5670,22 +5678,16 @@ static int bnxt_probe_phy(struct bnxt *bp)
 	}
 
 	/*initialize the ethool setting copy with NVM settings */
-	if (BNXT_AUTO_MODE(link_info->auto_mode))
-		link_info->autoneg |= BNXT_AUTONEG_SPEED;
-
-	if (link_info->auto_pause_setting & BNXT_LINK_PAUSE_BOTH) {
-		if (link_info->auto_pause_setting == BNXT_LINK_PAUSE_BOTH)
-			link_info->autoneg |= BNXT_AUTONEG_FLOW_CTRL;
+	if (BNXT_AUTO_MODE(link_info->auto_mode)) {
+		link_info->autoneg = BNXT_AUTONEG_SPEED |
+				     BNXT_AUTONEG_FLOW_CTRL;
+		link_info->advertising = link_info->auto_link_speeds;
 		link_info->req_flow_ctrl = link_info->auto_pause_setting;
-	} else if (link_info->force_pause_setting & BNXT_LINK_PAUSE_BOTH) {
+	} else {
+		link_info->req_link_speed = link_info->force_link_speed;
+		link_info->req_duplex = link_info->duplex_setting;
 		link_info->req_flow_ctrl = link_info->force_pause_setting;
 	}
-	link_info->req_duplex = link_info->duplex_setting;
-	if (link_info->autoneg & BNXT_AUTONEG_SPEED)
-		link_info->req_link_speed = link_info->auto_link_speed;
-	else
-		link_info->req_link_speed = link_info->force_link_speed;
-	link_info->advertising = link_info->auto_link_speeds;
 	snprintf(phy_ver, PHY_VER_STR_LEN, " ph %d.%d.%d",
 		 link_info->phy_ver[0],
 		 link_info->phy_ver[1],
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 8af3ca8efcef..2be51b332652 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -411,8 +411,8 @@ struct rx_tpa_end_cmp_ext {
 
 #define BNXT_NUM_TESTS(bp)	0
 
-#define BNXT_DEFAULT_RX_RING_SIZE	1023
-#define BNXT_DEFAULT_TX_RING_SIZE	512
+#define BNXT_DEFAULT_RX_RING_SIZE	511
+#define BNXT_DEFAULT_TX_RING_SIZE	511
 
 #define MAX_TPA		64
 
@@ -523,10 +523,16 @@ struct bnxt_ring_struct {
 
 struct tx_push_bd {
 	__le32			doorbell;
-	struct tx_bd		txbd1;
+	__le32			tx_bd_len_flags_type;
+	u32			tx_bd_opaque;
 	struct tx_bd_ext	txbd2;
 };
 
+struct tx_push_buffer {
+	struct tx_push_bd	push_bd;
+	u32			data[25];
+};
+
 struct bnxt_tx_ring_info {
 	struct bnxt_napi	*bnapi;
 	u16			tx_prod;
@@ -538,8 +544,9 @@ struct bnxt_tx_ring_info {
 
 	dma_addr_t		tx_desc_mapping[MAX_TX_PAGES];
 
-	struct tx_push_bd	*tx_push;
+	struct tx_push_buffer	*tx_push;
 	dma_addr_t		tx_push_mapping;
+	__le64			data_mapping;
 
 #define BNXT_DEV_STATE_CLOSING	0x1
 	u32			dev_state;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 922b898e7a32..3238817dfd5f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -486,15 +486,8 @@ static u32 bnxt_fw_to_ethtool_support_spds(struct bnxt_link_info *link_info)
 		speed_mask |= SUPPORTED_2500baseX_Full;
 	if (fw_speeds & BNXT_LINK_SPEED_MSK_10GB)
 		speed_mask |= SUPPORTED_10000baseT_Full;
-	/* TODO: support 25GB, 50GB with different cable type */
-	if (fw_speeds & BNXT_LINK_SPEED_MSK_20GB)
-		speed_mask |= SUPPORTED_20000baseMLD2_Full |
-			SUPPORTED_20000baseKR2_Full;
 	if (fw_speeds & BNXT_LINK_SPEED_MSK_40GB)
-		speed_mask |= SUPPORTED_40000baseKR4_Full |
-			SUPPORTED_40000baseCR4_Full |
-			SUPPORTED_40000baseSR4_Full |
-			SUPPORTED_40000baseLR4_Full;
+		speed_mask |= SUPPORTED_40000baseCR4_Full;
 
 	return speed_mask;
 }
@@ -514,15 +507,8 @@ static u32 bnxt_fw_to_ethtool_advertised_spds(struct bnxt_link_info *link_info)
 		speed_mask |= ADVERTISED_2500baseX_Full;
 	if (fw_speeds & BNXT_LINK_SPEED_MSK_10GB)
 		speed_mask |= ADVERTISED_10000baseT_Full;
-	/* TODO: how to advertise 20, 25, 40, 50GB with different cable type ?*/
-	if (fw_speeds & BNXT_LINK_SPEED_MSK_20GB)
-		speed_mask |= ADVERTISED_20000baseMLD2_Full |
-			      ADVERTISED_20000baseKR2_Full;
 	if (fw_speeds & BNXT_LINK_SPEED_MSK_40GB)
-		speed_mask |= ADVERTISED_40000baseKR4_Full |
-			      ADVERTISED_40000baseCR4_Full |
-			      ADVERTISED_40000baseSR4_Full |
-			      ADVERTISED_40000baseLR4_Full;
+		speed_mask |= ADVERTISED_40000baseCR4_Full;
 	return speed_mask;
 }
 
@@ -557,11 +543,12 @@ static int bnxt_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 	u16 ethtool_speed;
 
 	cmd->supported = bnxt_fw_to_ethtool_support_spds(link_info);
+	cmd->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
 
 	if (link_info->auto_link_speeds)
 		cmd->supported |= SUPPORTED_Autoneg;
 
-	if (BNXT_AUTO_MODE(link_info->auto_mode)) {
+	if (link_info->autoneg) {
 		cmd->advertising =
 			bnxt_fw_to_ethtool_advertised_spds(link_info);
 		cmd->advertising |= ADVERTISED_Autoneg;
@@ -570,28 +557,16 @@ static int bnxt_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 		cmd->autoneg = AUTONEG_DISABLE;
 		cmd->advertising = 0;
 	}
-	if (link_info->auto_pause_setting & BNXT_LINK_PAUSE_BOTH) {
+	if (link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL) {
 		if ((link_info->auto_pause_setting & BNXT_LINK_PAUSE_BOTH) ==
 		    BNXT_LINK_PAUSE_BOTH) {
 			cmd->advertising |= ADVERTISED_Pause;
-			cmd->supported |= SUPPORTED_Pause;
 		} else {
 			cmd->advertising |= ADVERTISED_Asym_Pause;
-			cmd->supported |= SUPPORTED_Asym_Pause;
 			if (link_info->auto_pause_setting &
 			    BNXT_LINK_PAUSE_RX)
 				cmd->advertising |= ADVERTISED_Pause;
 		}
-	} else if (link_info->force_pause_setting & BNXT_LINK_PAUSE_BOTH) {
-		if ((link_info->force_pause_setting & BNXT_LINK_PAUSE_BOTH) ==
-		    BNXT_LINK_PAUSE_BOTH) {
-			cmd->supported |= SUPPORTED_Pause;
-		} else {
-			cmd->supported |= SUPPORTED_Asym_Pause;
-			if (link_info->force_pause_setting &
-			    BNXT_LINK_PAUSE_RX)
-				cmd->supported |= SUPPORTED_Pause;
-		}
 	}
 
 	cmd->port = PORT_NONE;
@@ -670,6 +645,9 @@ static u16 bnxt_get_fw_auto_link_speeds(u32 advertising)
 	if (advertising & ADVERTISED_10000baseT_Full)
 		fw_speed_mask |= BNXT_LINK_SPEED_MSK_10GB;
 
+	if (advertising & ADVERTISED_40000baseCR4_Full)
+		fw_speed_mask |= BNXT_LINK_SPEED_MSK_40GB;
+
 	return fw_speed_mask;
 }
 
@@ -729,7 +707,7 @@ static int bnxt_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 		speed = ethtool_cmd_speed(cmd);
 		link_info->req_link_speed = bnxt_get_fw_speed(dev, speed);
 		link_info->req_duplex = BNXT_LINK_DUPLEX_FULL;
-		link_info->autoneg &= ~BNXT_AUTONEG_SPEED;
+		link_info->autoneg = 0;
 		link_info->advertising = 0;
 	}
 
@@ -748,8 +726,7 @@ static void bnxt_get_pauseparam(struct net_device *dev,
 
 	if (BNXT_VF(bp))
 		return;
-	epause->autoneg = !!(link_info->auto_pause_setting &
-			     BNXT_LINK_PAUSE_BOTH);
+	epause->autoneg = !!(link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL);
 	epause->rx_pause = ((link_info->pause & BNXT_LINK_PAUSE_RX) != 0);
 	epause->tx_pause = ((link_info->pause & BNXT_LINK_PAUSE_TX) != 0);
 }
@@ -765,6 +742,9 @@ static int bnxt_set_pauseparam(struct net_device *dev,
 		return rc;
 
 	if (epause->autoneg) {
+		if (!(link_info->autoneg & BNXT_AUTONEG_SPEED))
+			return -EINVAL;
+
 		link_info->autoneg |= BNXT_AUTONEG_FLOW_CTRL;
 		link_info->req_flow_ctrl |= BNXT_LINK_PAUSE_BOTH;
 	} else {
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index b15a60d787c7..d7e01a74e927 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2445,8 +2445,7 @@ static void bcmgenet_irq_task(struct work_struct *work)
 	}
 
 	/* Link UP/DOWN event */
-	if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) &&
-	    (priv->irq0_stat & UMAC_IRQ_LINK_EVENT)) {
+	if (priv->irq0_stat & UMAC_IRQ_LINK_EVENT) {
 		phy_mac_interrupt(priv->phydev,
 				  !!(priv->irq0_stat & UMAC_IRQ_LINK_UP));
 		priv->irq0_stat &= ~UMAC_IRQ_LINK_EVENT;
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 49eea8981332..3010080cfeee 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -7831,6 +7831,14 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi,
 	return ret;
 }
 
+static bool tg3_tso_bug_gso_check(struct tg3_napi *tnapi, struct sk_buff *skb)
+{
+	/* Check if we will never have enough descriptors,
+	 * as gso_segs can be more than current ring size
+	 */
+	return skb_shinfo(skb)->gso_segs < tnapi->tx_pending / 3;
+}
+
 static netdev_tx_t tg3_start_xmit(struct sk_buff *, struct net_device *);
 
 /* Use GSO to workaround all TSO packets that meet HW bug conditions
@@ -7934,14 +7942,19 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		 * vlan encapsulated.
 		 */
 		if (skb->protocol == htons(ETH_P_8021Q) ||
-		    skb->protocol == htons(ETH_P_8021AD))
-			return tg3_tso_bug(tp, tnapi, txq, skb);
+		    skb->protocol == htons(ETH_P_8021AD)) {
+			if (tg3_tso_bug_gso_check(tnapi, skb))
+				return tg3_tso_bug(tp, tnapi, txq, skb);
+			goto drop;
+		}
 
 		if (!skb_is_gso_v6(skb)) {
 			if (unlikely((ETH_HLEN + hdr_len) > 80) &&
-			    tg3_flag(tp, TSO_BUG))
-				return tg3_tso_bug(tp, tnapi, txq, skb);
-
+			    tg3_flag(tp, TSO_BUG)) {
+				if (tg3_tso_bug_gso_check(tnapi, skb))
+					return tg3_tso_bug(tp, tnapi, txq, skb);
+				goto drop;
+			}
 			ip_csum = iph->check;
 			ip_tot_len = iph->tot_len;
 			iph->check = 0;
@@ -8073,7 +8086,7 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (would_hit_hwbug) {
 		tg3_tx_skb_unmap(tnapi, tnapi->tx_prod, i);
 
-		if (mss) {
+		if (mss && tg3_tso_bug_gso_check(tnapi, skb)) {
 			/* If it's a TSO packet, do GSO instead of
 			 * allocating and copying to a large linear SKB
 			 */
diff --git a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
index 04b0d16b210e..95bc470ae441 100644
--- a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
+++ b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
@@ -987,7 +987,7 @@ bna_rxf_ucast_cfg_apply(struct bna_rxf *rxf)
 	if (!list_empty(&rxf->ucast_pending_add_q)) {
 		mac = list_first_entry(&rxf->ucast_pending_add_q,
 				       struct bna_mac, qe);
-		list_add_tail(&mac->qe, &rxf->ucast_active_q);
+		list_move_tail(&mac->qe, &rxf->ucast_active_q);
 		bna_bfi_ucast_req(rxf, mac, BFI_ENET_H2I_MAC_UCAST_ADD_REQ);
 		return 1;
 	}
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 872765527081..34d269cd5579 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -1683,7 +1683,7 @@ static int octeon_setup_droq(struct octeon_device *oct, int q_no, int num_descs,
 	dev_dbg(&oct->pci_dev->dev, "Creating Droq: %d\n", q_no);
 	/* droq creation and local register settings. */
 	ret_val = octeon_create_droq(oct, q_no, num_descs, desc_size, app_ctx);
-	if (ret_val == -1)
+	if (ret_val < 0)
 		return ret_val;
 
 	if (ret_val == 1) {
@@ -2524,7 +2524,7 @@ static void handle_timestamp(struct octeon_device *oct,
 
 	octeon_swap_8B_data(&resp->timestamp, 1);
 
-	if (unlikely((skb_shinfo(skb)->tx_flags | SKBTX_IN_PROGRESS) != 0)) {
+	if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS) != 0)) {
 		struct skb_shared_hwtstamps ts;
 		u64 ns = resp->timestamp;
 
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
index 4dba86eaa045..174072b3740b 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
@@ -983,5 +983,5 @@ int octeon_create_droq(struct octeon_device *oct,
 
 create_droq_fail:
 	octeon_delete_droq(oct, q_no);
-	return -1;
+	return -ENOMEM;
 }
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index 688828865c48..34e9acea8747 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -116,6 +116,15 @@
 #define NIC_PF_INTR_ID_MBOX0		8
 #define NIC_PF_INTR_ID_MBOX1		9
 
+/* Minimum FIFO level before all packets for the CQ are dropped
+ *
+ * This value ensures that once a packet has been "accepted"
+ * for reception it will not get dropped due to non-availability
+ * of CQ descriptor. An errata in HW mandates this value to be
+ * atleast 0x100.
+ */
+#define NICPF_CQM_MIN_DROP_LEVEL       0x100
+
 /* Global timer for CQ timer thresh interrupts
  * Calculated for SCLK of 700Mhz
  * value written should be a 1/16th of what is expected
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 4dded90076c8..95f17f8cadac 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -304,6 +304,7 @@ static void nic_set_lmac_vf_mapping(struct nicpf *nic)
 static void nic_init_hw(struct nicpf *nic)
 {
 	int i;
+	u64 cqm_cfg;
 
 	/* Enable NIC HW block */
 	nic_reg_write(nic, NIC_PF_CFG, 0x3);
@@ -340,6 +341,11 @@ static void nic_init_hw(struct nicpf *nic)
 	/* Enable VLAN ethertype matching and stripping */
 	nic_reg_write(nic, NIC_PF_RX_ETYPE_0_7,
 		      (2 << 19) | (ETYPE_ALG_VLAN_STRIP << 16) | ETH_P_8021Q);
+
+	/* Check if HW expected value is higher (could be in future chips) */
+	cqm_cfg = nic_reg_read(nic, NIC_PF_CQM_CFG);
+	if (cqm_cfg < NICPF_CQM_MIN_DROP_LEVEL)
+		nic_reg_write(nic, NIC_PF_CQM_CFG, NICPF_CQM_MIN_DROP_LEVEL);
 }
 
 /* Channel parse index configuration */
diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h
index dd536be20193..afb10e326b4f 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_reg.h
+++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h
@@ -21,7 +21,7 @@
 #define   NIC_PF_TCP_TIMER			(0x0060)
 #define   NIC_PF_BP_CFG				(0x0080)
 #define   NIC_PF_RRM_CFG			(0x0088)
-#define   NIC_PF_CQM_CF				(0x00A0)
+#define   NIC_PF_CQM_CFG			(0x00A0)
 #define   NIC_PF_CNM_CF				(0x00A8)
 #define   NIC_PF_CNM_STATUS			(0x00B0)
 #define   NIC_PF_CQ_AVG_CFG			(0x00C0)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index c24cb2a86a42..a009bc30dc4d 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -574,8 +574,7 @@ static inline void nicvf_set_rxhash(struct net_device *netdev,
 
 static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 				  struct napi_struct *napi,
-				  struct cmp_queue *cq,
-				  struct cqe_rx_t *cqe_rx, int cqe_type)
+				  struct cqe_rx_t *cqe_rx)
 {
 	struct sk_buff *skb;
 	struct nicvf *nic = netdev_priv(netdev);
@@ -591,7 +590,7 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 	}
 
 	/* Check for errors */
-	err = nicvf_check_cqe_rx_errs(nic, cq, cqe_rx);
+	err = nicvf_check_cqe_rx_errs(nic, cqe_rx);
 	if (err && !cqe_rx->rb_cnt)
 		return;
 
@@ -682,8 +681,7 @@ loop:
 			   cq_idx, cq_desc->cqe_type);
 		switch (cq_desc->cqe_type) {
 		case CQE_TYPE_RX:
-			nicvf_rcv_pkt_handler(netdev, napi, cq,
-					      cq_desc, CQE_TYPE_RX);
+			nicvf_rcv_pkt_handler(netdev, napi, cq_desc);
 			work_done++;
 		break;
 		case CQE_TYPE_SEND:
@@ -1125,7 +1123,6 @@ int nicvf_stop(struct net_device *netdev)
 
 	/* Clear multiqset info */
 	nic->pnicvf = nic;
-	nic->sqs_count = 0;
 
 	return 0;
 }
@@ -1354,6 +1351,9 @@ void nicvf_update_stats(struct nicvf *nic)
 	drv_stats->tx_frames_ok = stats->tx_ucast_frames_ok +
 				  stats->tx_bcast_frames_ok +
 				  stats->tx_mcast_frames_ok;
+	drv_stats->rx_frames_ok = stats->rx_ucast_frames +
+				  stats->rx_bcast_frames +
+				  stats->rx_mcast_frames;
 	drv_stats->rx_drops = stats->rx_drop_red +
 			      stats->rx_drop_overrun;
 	drv_stats->tx_drops = stats->tx_drops;
@@ -1538,6 +1538,9 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	nicvf_send_vf_struct(nic);
 
+	if (!pass1_silicon(nic->pdev))
+		nic->hw_tso = true;
+
 	/* Check if this VF is in QS only mode */
 	if (nic->sqs_mode)
 		return 0;
@@ -1557,9 +1560,6 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	netdev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
 
-	if (!pass1_silicon(nic->pdev))
-		nic->hw_tso = true;
-
 	netdev->netdev_ops = &nicvf_netdev_ops;
 	netdev->watchdog_timeo = NICVF_TX_TIMEOUT;
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index d0d1b5490061..767347b1f631 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -1329,16 +1329,12 @@ void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx)
 }
 
 /* Check for errors in the receive cmp.queue entry */
-int nicvf_check_cqe_rx_errs(struct nicvf *nic,
-			    struct cmp_queue *cq, struct cqe_rx_t *cqe_rx)
+int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 {
 	struct nicvf_hw_stats *stats = &nic->hw_stats;
-	struct nicvf_drv_stats *drv_stats = &nic->drv_stats;
 
-	if (!cqe_rx->err_level && !cqe_rx->err_opcode) {
-		drv_stats->rx_frames_ok++;
+	if (!cqe_rx->err_level && !cqe_rx->err_opcode)
 		return 0;
-	}
 
 	if (netif_msg_rx_err(nic))
 		netdev_err(nic->netdev,
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
index c5030a7f213a..6673e1133523 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -338,8 +338,7 @@ u64  nicvf_queue_reg_read(struct nicvf *nic,
 /* Stats */
 void nicvf_update_rq_stats(struct nicvf *nic, int rq_idx);
 void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx);
-int nicvf_check_cqe_rx_errs(struct nicvf *nic,
-			    struct cmp_queue *cq, struct cqe_rx_t *cqe_rx);
+int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx);
 int nicvf_check_cqe_tx_errs(struct nicvf *nic,
 			    struct cmp_queue *cq, struct cqe_send_t *cqe_tx);
 #endif /* NICVF_QUEUES_H */
diff --git a/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c b/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c
index ee04caa6c4d8..a89721fad633 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c
@@ -681,6 +681,24 @@ int t3_seeprom_wp(struct adapter *adapter, int enable)
 	return t3_seeprom_write(adapter, EEPROM_STAT_ADDR, enable ? 0xc : 0);
 }
 
+static int vpdstrtouint(char *s, int len, unsigned int base, unsigned int *val)
+{
+	char tok[len + 1];
+
+	memcpy(tok, s, len);
+	tok[len] = 0;
+	return kstrtouint(strim(tok), base, val);
+}
+
+static int vpdstrtou16(char *s, int len, unsigned int base, u16 *val)
+{
+	char tok[len + 1];
+
+	memcpy(tok, s, len);
+	tok[len] = 0;
+	return kstrtou16(strim(tok), base, val);
+}
+
 /**
  *	get_vpd_params - read VPD parameters from VPD EEPROM
  *	@adapter: adapter to read
@@ -709,19 +727,19 @@ static int get_vpd_params(struct adapter *adapter, struct vpd_params *p)
 			return ret;
 	}
 
-	ret = kstrtouint(vpd.cclk_data, 10, &p->cclk);
+	ret = vpdstrtouint(vpd.cclk_data, vpd.cclk_len, 10, &p->cclk);
 	if (ret)
 		return ret;
-	ret = kstrtouint(vpd.mclk_data, 10, &p->mclk);
+	ret = vpdstrtouint(vpd.mclk_data, vpd.mclk_len, 10, &p->mclk);
 	if (ret)
 		return ret;
-	ret = kstrtouint(vpd.uclk_data, 10, &p->uclk);
+	ret = vpdstrtouint(vpd.uclk_data, vpd.uclk_len, 10, &p->uclk);
 	if (ret)
 		return ret;
-	ret = kstrtouint(vpd.mdc_data, 10, &p->mdc);
+	ret = vpdstrtouint(vpd.mdc_data, vpd.mdc_len, 10, &p->mdc);
 	if (ret)
 		return ret;
-	ret = kstrtouint(vpd.mt_data, 10, &p->mem_timing);
+	ret = vpdstrtouint(vpd.mt_data, vpd.mt_len, 10, &p->mem_timing);
 	if (ret)
 		return ret;
 	memcpy(p->sn, vpd.sn_data, SERNUM_LEN);
@@ -733,10 +751,12 @@ static int get_vpd_params(struct adapter *adapter, struct vpd_params *p)
 	} else {
 		p->port_type[0] = hex_to_bin(vpd.port0_data[0]);
 		p->port_type[1] = hex_to_bin(vpd.port1_data[0]);
-		ret = kstrtou16(vpd.xaui0cfg_data, 16, &p->xauicfg[0]);
+		ret = vpdstrtou16(vpd.xaui0cfg_data, vpd.xaui0cfg_len, 16,
+				  &p->xauicfg[0]);
 		if (ret)
 			return ret;
-		ret = kstrtou16(vpd.xaui1cfg_data, 16, &p->xauicfg[1]);
+		ret = vpdstrtou16(vpd.xaui1cfg_data, vpd.xaui1cfg_len, 16,
+				  &p->xauicfg[1]);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
index a8dda635456d..06bc2d2e7a73 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
@@ -165,6 +165,7 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
 	CH_PCI_ID_TABLE_FENTRY(0x5098),	/* Custom 2x40G QSFP */
 	CH_PCI_ID_TABLE_FENTRY(0x5099),	/* Custom 2x40G QSFP */
 	CH_PCI_ID_TABLE_FENTRY(0x509a),	/* Custom T520-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x509b),	/* Custom T540-CR LOM */
 
 	/* T6 adapters:
 	 */
diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index 1671fa3332c2..7ba6d530b0c0 100644
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -33,7 +33,7 @@
 
 #define DRV_NAME		"enic"
 #define DRV_DESCRIPTION		"Cisco VIC Ethernet NIC Driver"
-#define DRV_VERSION		"2.3.0.12"
+#define DRV_VERSION		"2.3.0.20"
 #define DRV_COPYRIGHT		"Copyright 2008-2013 Cisco Systems, Inc"
 
 #define ENIC_BARS_MAX		6
diff --git a/drivers/net/ethernet/cisco/enic/vnic_dev.c b/drivers/net/ethernet/cisco/enic/vnic_dev.c
index 1ffd1050860b..1fdf5fe12a95 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_dev.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_dev.c
@@ -298,7 +298,8 @@ static int _vnic_dev_cmd2(struct vnic_dev *vdev, enum vnic_devcmd_cmd cmd,
 			  int wait)
 {
 	struct devcmd2_controller *dc2c = vdev->devcmd2;
-	struct devcmd2_result *result = dc2c->result + dc2c->next_result;
+	struct devcmd2_result *result;
+	u8 color;
 	unsigned int i;
 	int delay, err;
 	u32 fetch_index, new_posted;
@@ -336,13 +337,17 @@ static int _vnic_dev_cmd2(struct vnic_dev *vdev, enum vnic_devcmd_cmd cmd,
 	if (dc2c->cmd_ring[posted].flags & DEVCMD2_FNORESULT)
 		return 0;
 
+	result = dc2c->result + dc2c->next_result;
+	color = dc2c->color;
+
+	dc2c->next_result++;
+	if (dc2c->next_result == dc2c->result_size) {
+		dc2c->next_result = 0;
+		dc2c->color = dc2c->color ? 0 : 1;
+	}
+
 	for (delay = 0; delay < wait; delay++) {
-		if (result->color == dc2c->color) {
-			dc2c->next_result++;
-			if (dc2c->next_result == dc2c->result_size) {
-				dc2c->next_result = 0;
-				dc2c->color = dc2c->color ? 0 : 1;
-			}
+		if (result->color == color) {
 			if (result->error) {
 				err = result->error;
 				if (err != ERR_ECMDUNKNOWN ||
diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index cf94b72dbacd..48d91941408d 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -128,7 +128,6 @@ struct board_info {
 	struct resource *data_res;
 	struct resource	*addr_req;   /* resources requested */
 	struct resource *data_req;
-	struct resource *irq_res;
 
 	int		 irq_wake;
 
@@ -1300,22 +1299,16 @@ static int
 dm9000_open(struct net_device *dev)
 {
 	struct board_info *db = netdev_priv(dev);
-	unsigned long irqflags = db->irq_res->flags & IRQF_TRIGGER_MASK;
 
 	if (netif_msg_ifup(db))
 		dev_dbg(db->dev, "enabling %s\n", dev->name);
 
-	/* If there is no IRQ type specified, default to something that
-	 * may work, and tell the user that this is a problem */
-
-	if (irqflags == IRQF_TRIGGER_NONE)
-		irqflags = irq_get_trigger_type(dev->irq);
-
-	if (irqflags == IRQF_TRIGGER_NONE)
+	/* If there is no IRQ type specified, tell the user that this is a
+	 * problem
+	 */
+	if (irq_get_trigger_type(dev->irq) == IRQF_TRIGGER_NONE)
 		dev_warn(db->dev, "WARNING: no IRQ resource flags set.\n");
 
-	irqflags |= IRQF_SHARED;
-
 	/* GPIO0 on pre-activate PHY, Reg 1F is not set by reset */
 	iow(db, DM9000_GPR, 0);	/* REG_1F bit0 activate phyxcer */
 	mdelay(1); /* delay needs by DM9000B */
@@ -1323,7 +1316,8 @@ dm9000_open(struct net_device *dev)
 	/* Initialize DM9000 board */
 	dm9000_init_dm9000(dev);
 
-	if (request_irq(dev->irq, dm9000_interrupt, irqflags, dev->name, dev))
+	if (request_irq(dev->irq, dm9000_interrupt, IRQF_SHARED,
+			dev->name, dev))
 		return -EAGAIN;
 	/* Now that we have an interrupt handler hooked up we can unmask
 	 * our interrupts
@@ -1500,15 +1494,22 @@ dm9000_probe(struct platform_device *pdev)
 
 	db->addr_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	db->data_res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	db->irq_res  = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 
-	if (db->addr_res == NULL || db->data_res == NULL ||
-	    db->irq_res == NULL) {
-		dev_err(db->dev, "insufficient resources\n");
+	if (!db->addr_res || !db->data_res) {
+		dev_err(db->dev, "insufficient resources addr=%p data=%p\n",
+			db->addr_res, db->data_res);
 		ret = -ENOENT;
 		goto out;
 	}
 
+	ndev->irq = platform_get_irq(pdev, 0);
+	if (ndev->irq < 0) {
+		dev_err(db->dev, "interrupt resource unavailable: %d\n",
+			ndev->irq);
+		ret = ndev->irq;
+		goto out;
+	}
+
 	db->irq_wake = platform_get_irq(pdev, 1);
 	if (db->irq_wake >= 0) {
 		dev_dbg(db->dev, "wakeup irq %d\n", db->irq_wake);
@@ -1570,7 +1571,6 @@ dm9000_probe(struct platform_device *pdev)
 
 	/* fill in parameters for net-dev structure */
 	ndev->base_addr = (unsigned long)db->io_addr;
-	ndev->irq	= db->irq_res->start;
 
 	/* ensure at least we have a default set of IO routines */
 	dm9000_set_io(db, iosize);
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index cf837831304b..f9751294ece7 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -531,6 +531,7 @@ struct be_adapter {
 
 	struct delayed_work be_err_detection_work;
 	u8 err_flags;
+	bool pcicfg_mapped;	/* pcicfg obtained via pci_iomap() */
 	u32 flags;
 	u32 cmd_privileges;
 	/* Ethtool knobs and info */
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index 241819b36ca7..6d9a8d78e8ad 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -622,10 +622,13 @@ enum be_if_flags {
 					 BE_IF_FLAGS_VLAN_PROMISCUOUS |\
 					 BE_IF_FLAGS_MCAST_PROMISCUOUS)
 
-#define BE_IF_EN_FLAGS	(BE_IF_FLAGS_BROADCAST | BE_IF_FLAGS_PASS_L3L4_ERRORS |\
-			BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_UNTAGGED)
+#define BE_IF_FILT_FLAGS_BASIC (BE_IF_FLAGS_BROADCAST | \
+				BE_IF_FLAGS_PASS_L3L4_ERRORS | \
+				BE_IF_FLAGS_UNTAGGED)
 
-#define BE_IF_ALL_FILT_FLAGS	(BE_IF_EN_FLAGS | BE_IF_FLAGS_ALL_PROMISCUOUS)
+#define BE_IF_ALL_FILT_FLAGS	(BE_IF_FILT_FLAGS_BASIC | \
+				 BE_IF_FLAGS_MULTICAST | \
+				 BE_IF_FLAGS_ALL_PROMISCUOUS)
 
 /* An RX interface is an object with one or more MAC addresses and
  * filtering capabilities. */
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index f99de3657ce3..d1cf1274fc2f 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -125,6 +125,11 @@ static const char * const ue_status_hi_desc[] = {
 	"Unknown"
 };
 
+#define BE_VF_IF_EN_FLAGS	(BE_IF_FLAGS_UNTAGGED | \
+				 BE_IF_FLAGS_BROADCAST | \
+				 BE_IF_FLAGS_MULTICAST | \
+				 BE_IF_FLAGS_PASS_L3L4_ERRORS)
+
 static void be_queue_free(struct be_adapter *adapter, struct be_queue_info *q)
 {
 	struct be_dma_mem *mem = &q->dma_mem;
@@ -3537,7 +3542,7 @@ static int be_enable_if_filters(struct be_adapter *adapter)
 {
 	int status;
 
-	status = be_cmd_rx_filter(adapter, BE_IF_EN_FLAGS, ON);
+	status = be_cmd_rx_filter(adapter, BE_IF_FILT_FLAGS_BASIC, ON);
 	if (status)
 		return status;
 
@@ -3857,8 +3862,7 @@ static int be_vfs_if_create(struct be_adapter *adapter)
 	int status;
 
 	/* If a FW profile exists, then cap_flags are updated */
-	cap_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST |
-		    BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS;
+	cap_flags = BE_VF_IF_EN_FLAGS;
 
 	for_all_vfs(adapter, vf_cfg, vf) {
 		if (!BE3_chip(adapter)) {
@@ -3874,10 +3878,8 @@ static int be_vfs_if_create(struct be_adapter *adapter)
 			}
 		}
 
-		en_flags = cap_flags & (BE_IF_FLAGS_UNTAGGED |
-					BE_IF_FLAGS_BROADCAST |
-					BE_IF_FLAGS_MULTICAST |
-					BE_IF_FLAGS_PASS_L3L4_ERRORS);
+		/* PF should enable IF flags during proxy if_create call */
+		en_flags = cap_flags & BE_VF_IF_EN_FLAGS;
 		status = be_cmd_if_create(adapter, cap_flags, en_flags,
 					  &vf_cfg->if_handle, vf + 1);
 		if (status)
@@ -4968,6 +4970,8 @@ static void be_unmap_pci_bars(struct be_adapter *adapter)
 		pci_iounmap(adapter->pdev, adapter->csr);
 	if (adapter->db)
 		pci_iounmap(adapter->pdev, adapter->db);
+	if (adapter->pcicfg && adapter->pcicfg_mapped)
+		pci_iounmap(adapter->pdev, adapter->pcicfg);
 }
 
 static int db_bar(struct be_adapter *adapter)
@@ -5019,8 +5023,10 @@ static int be_map_pci_bars(struct be_adapter *adapter)
 			if (!addr)
 				goto pci_map_err;
 			adapter->pcicfg = addr;
+			adapter->pcicfg_mapped = true;
 		} else {
 			adapter->pcicfg = adapter->db + SRIOV_VF_PCICFG_OFFSET;
+			adapter->pcicfg_mapped = false;
 		}
 	}
 
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index 62fa136554ac..41b010645100 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -1265,7 +1265,6 @@ static int ethoc_remove(struct platform_device *pdev)
 
 		if (priv->mdio) {
 			mdiobus_unregister(priv->mdio);
-			kfree(priv->mdio->irq);
 			mdiobus_free(priv->mdio);
 		}
 		if (priv->clk)
diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c
index 623aa1c8ebc6..79a210aaf0bb 100644
--- a/drivers/net/ethernet/freescale/fman/fman.c
+++ b/drivers/net/ethernet/freescale/fman/fman.c
@@ -2791,6 +2791,8 @@ static struct fman *read_dts_node(struct platform_device *of_dev)
 		goto fman_free;
 	}
 
+	fman->dev = &of_dev->dev;
+
 	return fman;
 
 fman_node_put:
@@ -2845,8 +2847,6 @@ static int fman_probe(struct platform_device *of_dev)
 
 	dev_set_drvdata(dev, fman);
 
-	fman->dev = dev;
-
 	dev_dbg(dev, "FMan%d probed\n", fman->dts_params.id);
 
 	return 0;
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 2aa7b401cc3b..b9ecf197ad11 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -1111,8 +1111,10 @@ static void __gfar_detect_errata_85xx(struct gfar_private *priv)
 
 	if ((SVR_SOC_VER(svr) == SVR_8548) && (SVR_REV(svr) == 0x20))
 		priv->errata |= GFAR_ERRATA_12;
+	/* P2020/P1010 Rev 1; MPC8548 Rev 2 */
 	if (((SVR_SOC_VER(svr) == SVR_P2020) && (SVR_REV(svr) < 0x20)) ||
-	    ((SVR_SOC_VER(svr) == SVR_P2010) && (SVR_REV(svr) < 0x20)))
+	    ((SVR_SOC_VER(svr) == SVR_P2010) && (SVR_REV(svr) < 0x20)) ||
+	    ((SVR_SOC_VER(svr) == SVR_8548) && (SVR_REV(svr) < 0x31)))
 		priv->errata |= GFAR_ERRATA_76; /* aka eTSEC 20 */
 }
 #endif
diff --git a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
index a7139f588ad2..678f5018d0be 100644
--- a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
+++ b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
@@ -469,8 +469,8 @@ static int fmvj18x_config(struct pcmcia_device *link)
 		    goto failed;
 	    }
 	    /* Read MACID from CIS */
-	    for (i = 5; i < 11; i++)
-		    dev->dev_addr[i] = buf[i];
+	    for (i = 0; i < 6; i++)
+		    dev->dev_addr[i] = buf[i + 5];
 	    kfree(buf);
 	} else {
 	    if (pcmcia_get_mac_from_cis(link, dev))
diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index 74beb1867230..4ccc032633c4 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -25,6 +25,7 @@ config HIX5HD2_GMAC
 
 config HIP04_ETH
 	tristate "HISILICON P04 Ethernet support"
+	depends on HAS_IOMEM	# For MFD_SYSCON
 	select MARVELL_PHY
 	select MFD_SYSCON
 	select HNS_MDIO
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
index a0070d0e740d..d4f92ed322d6 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
@@ -675,8 +675,12 @@ static int hns_ae_config_loopback(struct hnae_handle *handle,
 {
 	int ret;
 	struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle);
+	struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle);
 
 	switch (loop) {
+	case MAC_INTERNALLOOP_PHY:
+		ret = 0;
+		break;
 	case MAC_INTERNALLOOP_SERDES:
 		ret = hns_mac_config_sds_loopback(vf_cb->mac_cb, en);
 		break;
@@ -686,6 +690,10 @@ static int hns_ae_config_loopback(struct hnae_handle *handle,
 	default:
 		ret = -EINVAL;
 	}
+
+	if (!ret)
+		hns_dsaf_set_inner_lb(mac_cb->dsaf_dev, mac_cb->mac_id, en);
+
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index 9439f04962e1..38fc5be3870c 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -230,6 +230,30 @@ static void hns_dsaf_mix_def_qid_cfg(struct dsaf_device *dsaf_dev)
 	}
 }
 
+static void hns_dsaf_inner_qid_cfg(struct dsaf_device *dsaf_dev)
+{
+	u16 max_q_per_vf, max_vfn;
+	u32 q_id, q_num_per_port;
+	u32 mac_id;
+
+	if (AE_IS_VER1(dsaf_dev->dsaf_ver))
+		return;
+
+	hns_rcb_get_queue_mode(dsaf_dev->dsaf_mode,
+			       HNS_DSAF_COMM_SERVICE_NW_IDX,
+			       &max_vfn, &max_q_per_vf);
+	q_num_per_port = max_vfn * max_q_per_vf;
+
+	for (mac_id = 0, q_id = 0; mac_id < DSAF_SERVICE_NW_NUM; mac_id++) {
+		dsaf_set_dev_field(dsaf_dev,
+				   DSAFV2_SERDES_LBK_0_REG + 4 * mac_id,
+				   DSAFV2_SERDES_LBK_QID_M,
+				   DSAFV2_SERDES_LBK_QID_S,
+				   q_id);
+		q_id += q_num_per_port;
+	}
+}
+
 /**
  * hns_dsaf_sw_port_type_cfg - cfg sw type
  * @dsaf_id: dsa fabric id
@@ -691,6 +715,16 @@ void hns_dsaf_set_promisc_mode(struct dsaf_device *dsaf_dev, u32 en)
 	dsaf_set_dev_bit(dsaf_dev, DSAF_CFG_0_REG, DSAF_CFG_MIX_MODE_S, !!en);
 }
 
+void hns_dsaf_set_inner_lb(struct dsaf_device *dsaf_dev, u32 mac_id, u32 en)
+{
+	if (AE_IS_VER1(dsaf_dev->dsaf_ver) ||
+	    dsaf_dev->mac_cb[mac_id].mac_type == HNAE_PORT_DEBUG)
+		return;
+
+	dsaf_set_dev_bit(dsaf_dev, DSAFV2_SERDES_LBK_0_REG + 4 * mac_id,
+			 DSAFV2_SERDES_LBK_EN_B, !!en);
+}
+
 /**
  * hns_dsaf_tbl_stat_en - tbl
  * @dsaf_id: dsa fabric id
@@ -1022,6 +1056,9 @@ static void hns_dsaf_comm_init(struct dsaf_device *dsaf_dev)
 	/* set promisc def queue id */
 	hns_dsaf_mix_def_qid_cfg(dsaf_dev);
 
+	/* set inner loopback queue id */
+	hns_dsaf_inner_qid_cfg(dsaf_dev);
+
 	/* in non switch mode, set all port to access mode */
 	hns_dsaf_sw_port_type_cfg(dsaf_dev, DSAF_SW_PORT_TYPE_NON_VLAN);
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
index 40205b910f80..5fea226efaf3 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
@@ -417,5 +417,6 @@ void hns_dsaf_get_strings(int stringset, u8 *data, int port);
 void hns_dsaf_get_regs(struct dsaf_device *ddev, u32 port, void *data);
 int hns_dsaf_get_regs_count(void);
 void hns_dsaf_set_promisc_mode(struct dsaf_device *dsaf_dev, u32 en);
+void hns_dsaf_set_inner_lb(struct dsaf_device *dsaf_dev, u32 mac_id, u32 en);
 
 #endif /* __HNS_DSAF_MAIN_H__ */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
index f0c4f9b09d5b..60d695daa471 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
@@ -134,6 +134,7 @@
 #define DSAF_XGE_INT_STS_0_REG		0x1C0
 #define DSAF_PPE_INT_STS_0_REG		0x1E0
 #define DSAF_ROCEE_INT_STS_0_REG	0x200
+#define DSAFV2_SERDES_LBK_0_REG         0x220
 #define DSAF_PPE_QID_CFG_0_REG		0x300
 #define DSAF_SW_PORT_TYPE_0_REG		0x320
 #define DSAF_STP_PORT_TYPE_0_REG	0x340
@@ -857,6 +858,10 @@
 #define PPEV2_CFG_RSS_TBL_4N3_S	24
 #define PPEV2_CFG_RSS_TBL_4N3_M	(((1UL << 5) - 1) << PPEV2_CFG_RSS_TBL_4N3_S)
 
+#define DSAFV2_SERDES_LBK_EN_B  8
+#define DSAFV2_SERDES_LBK_QID_S 0
+#define DSAFV2_SERDES_LBK_QID_M	(((1UL << 8) - 1) << DSAFV2_SERDES_LBK_QID_S)
+
 #define PPE_CNT_CLR_CE_B	0
 #define PPE_CNT_CLR_SNAP_EN_B	1
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 3df22840fcd1..3c4a3bc31a89 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -295,8 +295,10 @@ static int __lb_setup(struct net_device *ndev,
 
 	switch (loop) {
 	case MAC_INTERNALLOOP_PHY:
-		if ((phy_dev) && (!phy_dev->is_c45))
+		if ((phy_dev) && (!phy_dev->is_c45)) {
 			ret = hns_nic_config_phy_loopback(phy_dev, 0x1);
+			ret |= h->dev->ops->set_loopback(h, loop, 0x1);
+		}
 		break;
 	case MAC_INTERNALLOOP_MAC:
 		if ((h->dev->ops->set_loopback) &&
@@ -376,6 +378,7 @@ static void __lb_other_process(struct hns_nic_ring_data *ring_data,
 			       struct sk_buff *skb)
 {
 	struct net_device *ndev;
+	struct hns_nic_priv *priv;
 	struct hnae_ring *ring;
 	struct netdev_queue *dev_queue;
 	struct sk_buff *new_skb;
@@ -385,8 +388,17 @@ static void __lb_other_process(struct hns_nic_ring_data *ring_data,
 	char buff[33]; /* 32B data and the last character '\0' */
 
 	if (!ring_data) { /* Just for doing create frame*/
+		ndev = skb->dev;
+		priv = netdev_priv(ndev);
+
 		frame_size = skb->len;
 		memset(skb->data, 0xFF, frame_size);
+		if ((!AE_IS_VER1(priv->enet_ver)) &&
+		    (priv->ae_handle->port_type == HNAE_PORT_SERVICE)) {
+			memcpy(skb->data, ndev->dev_addr, 6);
+			skb->data[5] += 0x1f;
+		}
+
 		frame_size &= ~1ul;
 		memset(&skb->data[frame_size / 2], 0xAA, frame_size / 2 - 1);
 		memset(&skb->data[frame_size / 2 + 10], 0xBE,
@@ -486,6 +498,7 @@ static int __lb_run_test(struct net_device *ndev,
 
 	/* place data into test skb */
 	(void)skb_put(skb, size);
+	skb->dev = ndev;
 	__lb_other_process(NULL, skb);
 	skb->queue_mapping = NIC_LB_TEST_RING_ID;
 
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 335417b4756b..ebe60719e489 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1166,7 +1166,10 @@ map_failed:
 	if (!firmware_has_feature(FW_FEATURE_CMO))
 		netdev_err(netdev, "tx: unable to map xmit buffer\n");
 	adapter->tx_map_failed++;
-	skb_linearize(skb);
+	if (skb_linearize(skb)) {
+		netdev->stats.tx_dropped++;
+		goto out;
+	}
 	force_bounce = 1;
 	goto retry_bounce;
 }
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 7d6570843723..6e9e16eee5d0 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1348,44 +1348,44 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry)
 	crq.request_capability.cmd = REQUEST_CAPABILITY;
 
 	crq.request_capability.capability = cpu_to_be16(REQ_TX_QUEUES);
-	crq.request_capability.number = cpu_to_be32(adapter->req_tx_queues);
+	crq.request_capability.number = cpu_to_be64(adapter->req_tx_queues);
 	ibmvnic_send_crq(adapter, &crq);
 
 	crq.request_capability.capability = cpu_to_be16(REQ_RX_QUEUES);
-	crq.request_capability.number = cpu_to_be32(adapter->req_rx_queues);
+	crq.request_capability.number = cpu_to_be64(adapter->req_rx_queues);
 	ibmvnic_send_crq(adapter, &crq);
 
 	crq.request_capability.capability = cpu_to_be16(REQ_RX_ADD_QUEUES);
-	crq.request_capability.number = cpu_to_be32(adapter->req_rx_add_queues);
+	crq.request_capability.number = cpu_to_be64(adapter->req_rx_add_queues);
 	ibmvnic_send_crq(adapter, &crq);
 
 	crq.request_capability.capability =
 	    cpu_to_be16(REQ_TX_ENTRIES_PER_SUBCRQ);
 	crq.request_capability.number =
-	    cpu_to_be32(adapter->req_tx_entries_per_subcrq);
+	    cpu_to_be64(adapter->req_tx_entries_per_subcrq);
 	ibmvnic_send_crq(adapter, &crq);
 
 	crq.request_capability.capability =
 	    cpu_to_be16(REQ_RX_ADD_ENTRIES_PER_SUBCRQ);
 	crq.request_capability.number =
-	    cpu_to_be32(adapter->req_rx_add_entries_per_subcrq);
+	    cpu_to_be64(adapter->req_rx_add_entries_per_subcrq);
 	ibmvnic_send_crq(adapter, &crq);
 
 	crq.request_capability.capability = cpu_to_be16(REQ_MTU);
-	crq.request_capability.number = cpu_to_be32(adapter->req_mtu);
+	crq.request_capability.number = cpu_to_be64(adapter->req_mtu);
 	ibmvnic_send_crq(adapter, &crq);
 
 	if (adapter->netdev->flags & IFF_PROMISC) {
 		if (adapter->promisc_supported) {
 			crq.request_capability.capability =
 			    cpu_to_be16(PROMISC_REQUESTED);
-			crq.request_capability.number = cpu_to_be32(1);
+			crq.request_capability.number = cpu_to_be64(1);
 			ibmvnic_send_crq(adapter, &crq);
 		}
 	} else {
 		crq.request_capability.capability =
 		    cpu_to_be16(PROMISC_REQUESTED);
-		crq.request_capability.number = cpu_to_be32(0);
+		crq.request_capability.number = cpu_to_be64(0);
 		ibmvnic_send_crq(adapter, &crq);
 	}
 
@@ -2312,93 +2312,93 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq,
 	switch (be16_to_cpu(crq->query_capability.capability)) {
 	case MIN_TX_QUEUES:
 		adapter->min_tx_queues =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "min_tx_queues = %lld\n",
 			   adapter->min_tx_queues);
 		break;
 	case MIN_RX_QUEUES:
 		adapter->min_rx_queues =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "min_rx_queues = %lld\n",
 			   adapter->min_rx_queues);
 		break;
 	case MIN_RX_ADD_QUEUES:
 		adapter->min_rx_add_queues =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "min_rx_add_queues = %lld\n",
 			   adapter->min_rx_add_queues);
 		break;
 	case MAX_TX_QUEUES:
 		adapter->max_tx_queues =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "max_tx_queues = %lld\n",
 			   adapter->max_tx_queues);
 		break;
 	case MAX_RX_QUEUES:
 		adapter->max_rx_queues =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "max_rx_queues = %lld\n",
 			   adapter->max_rx_queues);
 		break;
 	case MAX_RX_ADD_QUEUES:
 		adapter->max_rx_add_queues =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "max_rx_add_queues = %lld\n",
 			   adapter->max_rx_add_queues);
 		break;
 	case MIN_TX_ENTRIES_PER_SUBCRQ:
 		adapter->min_tx_entries_per_subcrq =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "min_tx_entries_per_subcrq = %lld\n",
 			   adapter->min_tx_entries_per_subcrq);
 		break;
 	case MIN_RX_ADD_ENTRIES_PER_SUBCRQ:
 		adapter->min_rx_add_entries_per_subcrq =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "min_rx_add_entrs_per_subcrq = %lld\n",
 			   adapter->min_rx_add_entries_per_subcrq);
 		break;
 	case MAX_TX_ENTRIES_PER_SUBCRQ:
 		adapter->max_tx_entries_per_subcrq =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "max_tx_entries_per_subcrq = %lld\n",
 			   adapter->max_tx_entries_per_subcrq);
 		break;
 	case MAX_RX_ADD_ENTRIES_PER_SUBCRQ:
 		adapter->max_rx_add_entries_per_subcrq =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "max_rx_add_entrs_per_subcrq = %lld\n",
 			   adapter->max_rx_add_entries_per_subcrq);
 		break;
 	case TCP_IP_OFFLOAD:
 		adapter->tcp_ip_offload =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "tcp_ip_offload = %lld\n",
 			   adapter->tcp_ip_offload);
 		break;
 	case PROMISC_SUPPORTED:
 		adapter->promisc_supported =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "promisc_supported = %lld\n",
 			   adapter->promisc_supported);
 		break;
 	case MIN_MTU:
-		adapter->min_mtu = be32_to_cpu(crq->query_capability.number);
+		adapter->min_mtu = be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "min_mtu = %lld\n", adapter->min_mtu);
 		break;
 	case MAX_MTU:
-		adapter->max_mtu = be32_to_cpu(crq->query_capability.number);
+		adapter->max_mtu = be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "max_mtu = %lld\n", adapter->max_mtu);
 		break;
 	case MAX_MULTICAST_FILTERS:
 		adapter->max_multicast_filters =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "max_multicast_filters = %lld\n",
 			   adapter->max_multicast_filters);
 		break;
 	case VLAN_HEADER_INSERTION:
 		adapter->vlan_header_insertion =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		if (adapter->vlan_header_insertion)
 			netdev->features |= NETIF_F_HW_VLAN_STAG_TX;
 		netdev_dbg(netdev, "vlan_header_insertion = %lld\n",
@@ -2406,43 +2406,43 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq,
 		break;
 	case MAX_TX_SG_ENTRIES:
 		adapter->max_tx_sg_entries =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "max_tx_sg_entries = %lld\n",
 			   adapter->max_tx_sg_entries);
 		break;
 	case RX_SG_SUPPORTED:
 		adapter->rx_sg_supported =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "rx_sg_supported = %lld\n",
 			   adapter->rx_sg_supported);
 		break;
 	case OPT_TX_COMP_SUB_QUEUES:
 		adapter->opt_tx_comp_sub_queues =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "opt_tx_comp_sub_queues = %lld\n",
 			   adapter->opt_tx_comp_sub_queues);
 		break;
 	case OPT_RX_COMP_QUEUES:
 		adapter->opt_rx_comp_queues =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "opt_rx_comp_queues = %lld\n",
 			   adapter->opt_rx_comp_queues);
 		break;
 	case OPT_RX_BUFADD_Q_PER_RX_COMP_Q:
 		adapter->opt_rx_bufadd_q_per_rx_comp_q =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "opt_rx_bufadd_q_per_rx_comp_q = %lld\n",
 			   adapter->opt_rx_bufadd_q_per_rx_comp_q);
 		break;
 	case OPT_TX_ENTRIES_PER_SUBCRQ:
 		adapter->opt_tx_entries_per_subcrq =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "opt_tx_entries_per_subcrq = %lld\n",
 			   adapter->opt_tx_entries_per_subcrq);
 		break;
 	case OPT_RXBA_ENTRIES_PER_SUBCRQ:
 		adapter->opt_rxba_entries_per_subcrq =
-		    be32_to_cpu(crq->query_capability.number);
+		    be64_to_cpu(crq->query_capability.number);
 		netdev_dbg(netdev, "opt_rxba_entries_per_subcrq = %lld\n",
 			   adapter->opt_rxba_entries_per_subcrq);
 		break;
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index 1242925ad34c..1a9993cc79b5 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -319,10 +319,8 @@ struct ibmvnic_capability {
 	u8 first;
 	u8 cmd;
 	__be16 capability; /* one of ibmvnic_capabilities */
+	__be64 number;
 	struct ibmvnic_rc rc;
-	__be32 number; /*FIX: should be __be64, but I'm getting the least
-			* significant word first
-			*/
 } __packed __aligned(8);
 
 struct ibmvnic_login {
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index fa593dd3efe1..3772f3ac956e 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -83,6 +83,15 @@ config E1000E
 	  To compile this driver as a module, choose M here. The module
 	  will be called e1000e.
 
+config E1000E_HWTS
+	bool "Support HW cross-timestamp on PCH devices"
+	default y
+	depends on E1000E && X86
+	---help---
+	 Say Y to enable hardware supported cross-timestamping on PCH
+	 devices. The cross-timestamp is available through the PTP clock
+	 driver precise cross-timestamp ioctl (PTP_SYS_OFFSET_PRECISE).
+
 config IGB
 	tristate "Intel(R) 82575/82576 PCI-Express Gigabit Ethernet support"
 	depends on PCI
diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h
index f7c7804d79e5..0641c0098738 100644
--- a/drivers/net/ethernet/intel/e1000e/defines.h
+++ b/drivers/net/ethernet/intel/e1000e/defines.h
@@ -528,6 +528,11 @@
 #define E1000_RXCW_C          0x20000000        /* Receive config */
 #define E1000_RXCW_SYNCH      0x40000000        /* Receive config synch */
 
+/* HH Time Sync */
+#define E1000_TSYNCTXCTL_MAX_ALLOWED_DLY_MASK	0x0000F000 /* max delay */
+#define E1000_TSYNCTXCTL_SYNC_COMP		0x40000000 /* sync complete */
+#define E1000_TSYNCTXCTL_START_SYNC		0x80000000 /* initiate sync */
+
 #define E1000_TSYNCTXCTL_VALID		0x00000001 /* Tx timestamp valid */
 #define E1000_TSYNCTXCTL_ENABLED	0x00000010 /* enable Tx timestamping */
 
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index 25a0ad5102d6..e2ff3ef75d5d 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -26,6 +26,12 @@
 
 #include "e1000.h"
 
+#ifdef CONFIG_E1000E_HWTS
+#include <linux/clocksource.h>
+#include <linux/ktime.h>
+#include <asm/tsc.h>
+#endif
+
 /**
  * e1000e_phc_adjfreq - adjust the frequency of the hardware clock
  * @ptp: ptp clock structure
@@ -98,6 +104,78 @@ static int e1000e_phc_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	return 0;
 }
 
+#ifdef CONFIG_E1000E_HWTS
+#define MAX_HW_WAIT_COUNT (3)
+
+/**
+ * e1000e_phc_get_syncdevicetime - Callback given to timekeeping code reads system/device registers
+ * @device: current device time
+ * @system: system counter value read synchronously with device time
+ * @ctx: context provided by timekeeping code
+ *
+ * Read device and system (ART) clock simultaneously and return the corrected
+ * clock values in ns.
+ **/
+static int e1000e_phc_get_syncdevicetime(ktime_t *device,
+					 struct system_counterval_t *system,
+					 void *ctx)
+{
+	struct e1000_adapter *adapter = (struct e1000_adapter *)ctx;
+	struct e1000_hw *hw = &adapter->hw;
+	unsigned long flags;
+	int i;
+	u32 tsync_ctrl;
+	cycle_t dev_cycles;
+	cycle_t sys_cycles;
+
+	tsync_ctrl = er32(TSYNCTXCTL);
+	tsync_ctrl |= E1000_TSYNCTXCTL_START_SYNC |
+		E1000_TSYNCTXCTL_MAX_ALLOWED_DLY_MASK;
+	ew32(TSYNCTXCTL, tsync_ctrl);
+	for (i = 0; i < MAX_HW_WAIT_COUNT; ++i) {
+		udelay(1);
+		tsync_ctrl = er32(TSYNCTXCTL);
+		if (tsync_ctrl & E1000_TSYNCTXCTL_SYNC_COMP)
+			break;
+	}
+
+	if (i == MAX_HW_WAIT_COUNT)
+		return -ETIMEDOUT;
+
+	dev_cycles = er32(SYSSTMPH);
+	dev_cycles <<= 32;
+	dev_cycles |= er32(SYSSTMPL);
+	spin_lock_irqsave(&adapter->systim_lock, flags);
+	*device = ns_to_ktime(timecounter_cyc2time(&adapter->tc, dev_cycles));
+	spin_unlock_irqrestore(&adapter->systim_lock, flags);
+
+	sys_cycles = er32(PLTSTMPH);
+	sys_cycles <<= 32;
+	sys_cycles |= er32(PLTSTMPL);
+	*system = convert_art_to_tsc(sys_cycles);
+
+	return 0;
+}
+
+/**
+ * e1000e_phc_getsynctime - Reads the current system/device cross timestamp
+ * @ptp: ptp clock structure
+ * @cts: structure containing timestamp
+ *
+ * Read device and system (ART) clock simultaneously and return the scaled
+ * clock values in ns.
+ **/
+static int e1000e_phc_getcrosststamp(struct ptp_clock_info *ptp,
+				     struct system_device_crosststamp *xtstamp)
+{
+	struct e1000_adapter *adapter = container_of(ptp, struct e1000_adapter,
+						     ptp_clock_info);
+
+	return get_device_system_crosststamp(e1000e_phc_get_syncdevicetime,
+						adapter, NULL, xtstamp);
+}
+#endif/*CONFIG_E1000E_HWTS*/
+
 /**
  * e1000e_phc_gettime - Reads the current time from the hardware clock
  * @ptp: ptp clock structure
@@ -236,6 +314,13 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
 		break;
 	}
 
+#ifdef CONFIG_E1000E_HWTS
+	/* CPU must have ART and GBe must be from Sunrise Point or greater */
+	if (hw->mac.type >= e1000_pch_spt && boot_cpu_has(X86_FEATURE_ART))
+		adapter->ptp_clock_info.getcrosststamp =
+			e1000e_phc_getcrosststamp;
+#endif/*CONFIG_E1000E_HWTS*/
+
 	INIT_DELAYED_WORK(&adapter->systim_overflow_work,
 			  e1000e_systim_overflow_work);
 
diff --git a/drivers/net/ethernet/intel/e1000e/regs.h b/drivers/net/ethernet/intel/e1000e/regs.h
index 1d5e0b77062a..0cb4d365e5ad 100644
--- a/drivers/net/ethernet/intel/e1000e/regs.h
+++ b/drivers/net/ethernet/intel/e1000e/regs.h
@@ -245,6 +245,10 @@
 #define E1000_SYSTIML	0x0B600	/* System time register Low - RO */
 #define E1000_SYSTIMH	0x0B604	/* System time register High - RO */
 #define E1000_TIMINCA	0x0B608	/* Increment attributes register - RW */
+#define E1000_SYSSTMPL  0x0B648 /* HH Timesync system stamp low register */
+#define E1000_SYSSTMPH  0x0B64C /* HH Timesync system stamp hi register */
+#define E1000_PLTSTMPL  0x0B640 /* HH Timesync platform stamp low register */
+#define E1000_PLTSTMPH  0x0B644 /* HH Timesync platform stamp hi register */
 #define E1000_RXMTRL	0x0B634	/* Time sync Rx EtherType and Msg Type - RW */
 #define E1000_RXUDP	0x0B638	/* Time Sync Rx UDP Port - RW */
 
diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index b1de7afd4116..3ddf657bc10b 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -270,11 +270,17 @@ jme_reset_mac_processor(struct jme_adapter *jme)
 }
 
 static inline void
-jme_clear_pm(struct jme_adapter *jme)
+jme_clear_pm_enable_wol(struct jme_adapter *jme)
 {
 	jwrite32(jme, JME_PMCS, PMCS_STMASK | jme->reg_pmcs);
 }
 
+static inline void
+jme_clear_pm_disable_wol(struct jme_adapter *jme)
+{
+	jwrite32(jme, JME_PMCS, PMCS_STMASK);
+}
+
 static int
 jme_reload_eeprom(struct jme_adapter *jme)
 {
@@ -1853,7 +1859,7 @@ jme_open(struct net_device *netdev)
 	struct jme_adapter *jme = netdev_priv(netdev);
 	int rc;
 
-	jme_clear_pm(jme);
+	jme_clear_pm_disable_wol(jme);
 	JME_NAPI_ENABLE(jme);
 
 	tasklet_init(&jme->linkch_task, jme_link_change_tasklet,
@@ -1925,11 +1931,11 @@ jme_wait_link(struct jme_adapter *jme)
 static void
 jme_powersave_phy(struct jme_adapter *jme)
 {
-	if (jme->reg_pmcs) {
+	if (jme->reg_pmcs && device_may_wakeup(&jme->pdev->dev)) {
 		jme_set_100m_half(jme);
 		if (jme->reg_pmcs & (PMCS_LFEN | PMCS_LREN))
 			jme_wait_link(jme);
-		jme_clear_pm(jme);
+		jme_clear_pm_enable_wol(jme);
 	} else {
 		jme_phy_off(jme);
 	}
@@ -2646,9 +2652,6 @@ jme_set_wol(struct net_device *netdev,
 	if (wol->wolopts & WAKE_MAGIC)
 		jme->reg_pmcs |= PMCS_MFEN;
 
-	jwrite32(jme, JME_PMCS, jme->reg_pmcs);
-	device_set_wakeup_enable(&jme->pdev->dev, !!(jme->reg_pmcs));
-
 	return 0;
 }
 
@@ -3172,8 +3175,8 @@ jme_init_one(struct pci_dev *pdev,
 	jme->mii_if.mdio_read = jme_mdio_read;
 	jme->mii_if.mdio_write = jme_mdio_write;
 
-	jme_clear_pm(jme);
-	device_set_wakeup_enable(&pdev->dev, true);
+	jme_clear_pm_disable_wol(jme);
+	device_init_wakeup(&pdev->dev, true);
 
 	jme_set_phyfifo_5level(jme);
 	jme->pcirev = pdev->revision;
@@ -3304,7 +3307,7 @@ jme_resume(struct device *dev)
 	if (!netif_running(netdev))
 		return 0;
 
-	jme_clear_pm(jme);
+	jme_clear_pm_disable_wol(jme);
 	jme_phy_on(jme);
 	if (test_bit(JME_FLAG_SSET, &jme->flags))
 		jme_set_settings(netdev, &jme->old_ecmd);
@@ -3312,13 +3315,14 @@ jme_resume(struct device *dev)
 		jme_reset_phy_processor(jme);
 	jme_phy_calibration(jme);
 	jme_phy_setEA(jme);
-	jme_start_irq(jme);
 	netif_device_attach(netdev);
 
 	atomic_inc(&jme->link_changing);
 
 	jme_reset_link(jme);
 
+	jme_start_irq(jme);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 662c2ee268c7..b0ae69f84493 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -370,6 +370,11 @@ struct mvneta_port {
 	struct net_device *dev;
 	struct notifier_block cpu_notifier;
 	int rxq_def;
+	/* Protect the access to the percpu interrupt registers,
+	 * ensuring that the configuration remains coherent.
+	 */
+	spinlock_t lock;
+	bool is_stopped;
 
 	/* Core clock */
 	struct clk *clk;
@@ -1038,6 +1043,43 @@ static void mvneta_set_autoneg(struct mvneta_port *pp, int enable)
 	}
 }
 
+static void mvneta_percpu_unmask_interrupt(void *arg)
+{
+	struct mvneta_port *pp = arg;
+
+	/* All the queue are unmasked, but actually only the ones
+	 * mapped to this CPU will be unmasked
+	 */
+	mvreg_write(pp, MVNETA_INTR_NEW_MASK,
+		    MVNETA_RX_INTR_MASK_ALL |
+		    MVNETA_TX_INTR_MASK_ALL |
+		    MVNETA_MISCINTR_INTR_MASK);
+}
+
+static void mvneta_percpu_mask_interrupt(void *arg)
+{
+	struct mvneta_port *pp = arg;
+
+	/* All the queue are masked, but actually only the ones
+	 * mapped to this CPU will be masked
+	 */
+	mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
+	mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
+	mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
+}
+
+static void mvneta_percpu_clear_intr_cause(void *arg)
+{
+	struct mvneta_port *pp = arg;
+
+	/* All the queue are cleared, but actually only the ones
+	 * mapped to this CPU will be cleared
+	 */
+	mvreg_write(pp, MVNETA_INTR_NEW_CAUSE, 0);
+	mvreg_write(pp, MVNETA_INTR_MISC_CAUSE, 0);
+	mvreg_write(pp, MVNETA_INTR_OLD_CAUSE, 0);
+}
+
 /* This method sets defaults to the NETA port:
  *	Clears interrupt Cause and Mask registers.
  *	Clears all MAC tables.
@@ -1055,14 +1097,10 @@ static void mvneta_defaults_set(struct mvneta_port *pp)
 	int max_cpu = num_present_cpus();
 
 	/* Clear all Cause registers */
-	mvreg_write(pp, MVNETA_INTR_NEW_CAUSE, 0);
-	mvreg_write(pp, MVNETA_INTR_OLD_CAUSE, 0);
-	mvreg_write(pp, MVNETA_INTR_MISC_CAUSE, 0);
+	on_each_cpu(mvneta_percpu_clear_intr_cause, pp, true);
 
 	/* Mask all interrupts */
-	mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
-	mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
-	mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
+	on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
 	mvreg_write(pp, MVNETA_INTR_ENABLE, 0);
 
 	/* Enable MBUS Retry bit16 */
@@ -2528,34 +2566,9 @@ static int mvneta_setup_txqs(struct mvneta_port *pp)
 	return 0;
 }
 
-static void mvneta_percpu_unmask_interrupt(void *arg)
-{
-	struct mvneta_port *pp = arg;
-
-	/* All the queue are unmasked, but actually only the ones
-	 * maped to this CPU will be unmasked
-	 */
-	mvreg_write(pp, MVNETA_INTR_NEW_MASK,
-		    MVNETA_RX_INTR_MASK_ALL |
-		    MVNETA_TX_INTR_MASK_ALL |
-		    MVNETA_MISCINTR_INTR_MASK);
-}
-
-static void mvneta_percpu_mask_interrupt(void *arg)
-{
-	struct mvneta_port *pp = arg;
-
-	/* All the queue are masked, but actually only the ones
-	 * maped to this CPU will be masked
-	 */
-	mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
-	mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
-	mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
-}
-
 static void mvneta_start_dev(struct mvneta_port *pp)
 {
-	unsigned int cpu;
+	int cpu;
 
 	mvneta_max_rx_size_set(pp, pp->pkt_size);
 	mvneta_txq_max_tx_size_set(pp, pp->pkt_size);
@@ -2564,16 +2577,15 @@ static void mvneta_start_dev(struct mvneta_port *pp)
 	mvneta_port_enable(pp);
 
 	/* Enable polling on the port */
-	for_each_present_cpu(cpu) {
+	for_each_online_cpu(cpu) {
 		struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
 
 		napi_enable(&port->napi);
 	}
 
 	/* Unmask interrupts. It has to be done from each CPU */
-	for_each_online_cpu(cpu)
-		smp_call_function_single(cpu, mvneta_percpu_unmask_interrupt,
-					 pp, true);
+	on_each_cpu(mvneta_percpu_unmask_interrupt, pp, true);
+
 	mvreg_write(pp, MVNETA_INTR_MISC_MASK,
 		    MVNETA_CAUSE_PHY_STATUS_CHANGE |
 		    MVNETA_CAUSE_LINK_CHANGE |
@@ -2589,7 +2601,7 @@ static void mvneta_stop_dev(struct mvneta_port *pp)
 
 	phy_stop(pp->phy_dev);
 
-	for_each_present_cpu(cpu) {
+	for_each_online_cpu(cpu) {
 		struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
 
 		napi_disable(&port->napi);
@@ -2604,13 +2616,10 @@ static void mvneta_stop_dev(struct mvneta_port *pp)
 	mvneta_port_disable(pp);
 
 	/* Clear all ethernet port interrupts */
-	mvreg_write(pp, MVNETA_INTR_MISC_CAUSE, 0);
-	mvreg_write(pp, MVNETA_INTR_OLD_CAUSE, 0);
+	on_each_cpu(mvneta_percpu_clear_intr_cause, pp, true);
 
 	/* Mask all ethernet port interrupts */
-	mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
-	mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
-	mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
+	on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
 
 	mvneta_tx_reset(pp);
 	mvneta_rx_reset(pp);
@@ -2847,11 +2856,20 @@ static void mvneta_percpu_disable(void *arg)
 	disable_percpu_irq(pp->dev->irq);
 }
 
+/* Electing a CPU must be done in an atomic way: it should be done
+ * after or before the removal/insertion of a CPU and this function is
+ * not reentrant.
+ */
 static void mvneta_percpu_elect(struct mvneta_port *pp)
 {
-	int online_cpu_idx, max_cpu, cpu, i = 0;
+	int elected_cpu = 0, max_cpu, cpu, i = 0;
+
+	/* Use the cpu associated to the rxq when it is online, in all
+	 * the other cases, use the cpu 0 which can't be offline.
+	 */
+	if (cpu_online(pp->rxq_def))
+		elected_cpu = pp->rxq_def;
 
-	online_cpu_idx = pp->rxq_def % num_online_cpus();
 	max_cpu = num_present_cpus();
 
 	for_each_online_cpu(cpu) {
@@ -2862,7 +2880,7 @@ static void mvneta_percpu_elect(struct mvneta_port *pp)
 			if ((rxq % max_cpu) == cpu)
 				rxq_map |= MVNETA_CPU_RXQ_ACCESS(rxq);
 
-		if (i == online_cpu_idx)
+		if (cpu == elected_cpu)
 			/* Map the default receive queue queue to the
 			 * elected CPU
 			 */
@@ -2873,7 +2891,7 @@ static void mvneta_percpu_elect(struct mvneta_port *pp)
 		 * the CPU bound to the default RX queue
 		 */
 		if (txq_number == 1)
-			txq_map = (i == online_cpu_idx) ?
+			txq_map = (cpu == elected_cpu) ?
 				MVNETA_CPU_TXQ_ACCESS(1) : 0;
 		else
 			txq_map = mvreg_read(pp, MVNETA_CPU_MAP(cpu)) &
@@ -2902,6 +2920,14 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb,
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
+		spin_lock(&pp->lock);
+		/* Configuring the driver for a new CPU while the
+		 * driver is stopping is racy, so just avoid it.
+		 */
+		if (pp->is_stopped) {
+			spin_unlock(&pp->lock);
+			break;
+		}
 		netif_tx_stop_all_queues(pp->dev);
 
 		/* We have to synchronise on tha napi of each CPU
@@ -2917,9 +2943,7 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb,
 		}
 
 		/* Mask all ethernet port interrupts */
-		mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
-		mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
-		mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
+		on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
 		napi_enable(&port->napi);
 
 
@@ -2934,27 +2958,25 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb,
 		 */
 		mvneta_percpu_elect(pp);
 
-		/* Unmask all ethernet port interrupts, as this
-		 * notifier is called for each CPU then the CPU to
-		 * Queue mapping is applied
-		 */
-		mvreg_write(pp, MVNETA_INTR_NEW_MASK,
-			MVNETA_RX_INTR_MASK(rxq_number) |
-			MVNETA_TX_INTR_MASK(txq_number) |
-			MVNETA_MISCINTR_INTR_MASK);
+		/* Unmask all ethernet port interrupts */
+		on_each_cpu(mvneta_percpu_unmask_interrupt, pp, true);
 		mvreg_write(pp, MVNETA_INTR_MISC_MASK,
 			MVNETA_CAUSE_PHY_STATUS_CHANGE |
 			MVNETA_CAUSE_LINK_CHANGE |
 			MVNETA_CAUSE_PSC_SYNC_CHANGE);
 		netif_tx_start_all_queues(pp->dev);
+		spin_unlock(&pp->lock);
 		break;
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
 		netif_tx_stop_all_queues(pp->dev);
+		/* Thanks to this lock we are sure that any pending
+		 * cpu election is done
+		 */
+		spin_lock(&pp->lock);
 		/* Mask all ethernet port interrupts */
-		mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
-		mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
-		mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
+		on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
+		spin_unlock(&pp->lock);
 
 		napi_synchronize(&port->napi);
 		napi_disable(&port->napi);
@@ -2968,12 +2990,11 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb,
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		/* Check if a new CPU must be elected now this on is down */
+		spin_lock(&pp->lock);
 		mvneta_percpu_elect(pp);
+		spin_unlock(&pp->lock);
 		/* Unmask all ethernet port interrupts */
-		mvreg_write(pp, MVNETA_INTR_NEW_MASK,
-			MVNETA_RX_INTR_MASK(rxq_number) |
-			MVNETA_TX_INTR_MASK(txq_number) |
-			MVNETA_MISCINTR_INTR_MASK);
+		on_each_cpu(mvneta_percpu_unmask_interrupt, pp, true);
 		mvreg_write(pp, MVNETA_INTR_MISC_MASK,
 			MVNETA_CAUSE_PHY_STATUS_CHANGE |
 			MVNETA_CAUSE_LINK_CHANGE |
@@ -2988,7 +3009,7 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb,
 static int mvneta_open(struct net_device *dev)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
-	int ret, cpu;
+	int ret;
 
 	pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu);
 	pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) +
@@ -3010,22 +3031,12 @@ static int mvneta_open(struct net_device *dev)
 		goto err_cleanup_txqs;
 	}
 
-	/* Even though the documentation says that request_percpu_irq
-	 * doesn't enable the interrupts automatically, it actually
-	 * does so on the local CPU.
-	 *
-	 * Make sure it's disabled.
-	 */
-	mvneta_percpu_disable(pp);
-
 	/* Enable per-CPU interrupt on all the CPU to handle our RX
 	 * queue interrupts
 	 */
-	for_each_online_cpu(cpu)
-		smp_call_function_single(cpu, mvneta_percpu_enable,
-					 pp, true);
-
+	on_each_cpu(mvneta_percpu_enable, pp, true);
 
+	pp->is_stopped = false;
 	/* Register a CPU notifier to handle the case where our CPU
 	 * might be taken offline.
 	 */
@@ -3057,13 +3068,20 @@ err_cleanup_rxqs:
 static int mvneta_stop(struct net_device *dev)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
-	int cpu;
 
+	/* Inform that we are stopping so we don't want to setup the
+	 * driver for new CPUs in the notifiers
+	 */
+	spin_lock(&pp->lock);
+	pp->is_stopped = true;
 	mvneta_stop_dev(pp);
 	mvneta_mdio_remove(pp);
 	unregister_cpu_notifier(&pp->cpu_notifier);
-	for_each_present_cpu(cpu)
-		smp_call_function_single(cpu, mvneta_percpu_disable, pp, true);
+	/* Now that the notifier are unregistered, we can release le
+	 * lock
+	 */
+	spin_unlock(&pp->lock);
+	on_each_cpu(mvneta_percpu_disable, pp, true);
 	free_percpu_irq(dev->irq, pp->ports);
 	mvneta_cleanup_rxqs(pp);
 	mvneta_cleanup_txqs(pp);
@@ -3312,9 +3330,7 @@ static int  mvneta_config_rss(struct mvneta_port *pp)
 
 	netif_tx_stop_all_queues(pp->dev);
 
-	for_each_online_cpu(cpu)
-		smp_call_function_single(cpu, mvneta_percpu_mask_interrupt,
-					 pp, true);
+	on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
 
 	/* We have to synchronise on the napi of each CPU */
 	for_each_online_cpu(cpu) {
@@ -3335,7 +3351,9 @@ static int  mvneta_config_rss(struct mvneta_port *pp)
 	mvreg_write(pp, MVNETA_PORT_CONFIG, val);
 
 	/* Update the elected CPU matching the new rxq_def */
+	spin_lock(&pp->lock);
 	mvneta_percpu_elect(pp);
+	spin_unlock(&pp->lock);
 
 	/* We have to synchronise on the napi of each CPU */
 	for_each_online_cpu(cpu) {
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index a4beccf1fd46..c797971aefab 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -3061,7 +3061,7 @@ static int mvpp2_prs_mac_da_accept(struct mvpp2 *priv, int port,
 
 		pe = kzalloc(sizeof(*pe), GFP_KERNEL);
 		if (!pe)
-			return -1;
+			return -ENOMEM;
 		mvpp2_prs_tcam_lu_set(pe, MVPP2_PRS_LU_MAC);
 		pe->index = tid;
 
@@ -3077,7 +3077,7 @@ static int mvpp2_prs_mac_da_accept(struct mvpp2 *priv, int port,
 	if (pmap == 0) {
 		if (add) {
 			kfree(pe);
-			return -1;
+			return -EINVAL;
 		}
 		mvpp2_prs_hw_inv(priv, pe->index);
 		priv->prs_shadow[pe->index].valid = false;
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index 715de8affcc9..c7e939945259 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -182,10 +182,17 @@ void mlx4_enter_error_state(struct mlx4_dev_persistent *persist)
 		err = mlx4_reset_slave(dev);
 	else
 		err = mlx4_reset_master(dev);
-	BUG_ON(err != 0);
 
+	if (!err) {
+		mlx4_err(dev, "device was reset successfully\n");
+	} else {
+		/* EEH could have disabled the PCI channel during reset. That's
+		 * recoverable and the PCI error flow will handle it.
+		 */
+		if (!pci_channel_offline(dev->persist->pdev))
+			BUG_ON(1);
+	}
 	dev->persist->state |= MLX4_DEVICE_STATE_INTERNAL_ERROR;
-	mlx4_err(dev, "device was reset successfully\n");
 	mutex_unlock(&persist->device_state_mutex);
 
 	/* At that step HW was already reset, now notify clients */
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index d48d5793407d..e94ca1c3fc7c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2429,7 +2429,7 @@ err_thread:
 	flush_workqueue(priv->mfunc.master.comm_wq);
 	destroy_workqueue(priv->mfunc.master.comm_wq);
 err_slaves:
-	while (--i) {
+	while (i--) {
 		for (port = 1; port <= MLX4_MAX_PORTS; port++)
 			kfree(priv->mfunc.master.slave_state[i].vlan_filter[port]);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index 3348e646db70..a849da92f857 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -318,7 +318,9 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 	if (timestamp_en)
 		cq_context->flags  |= cpu_to_be32(1 << 19);
 
-	cq_context->logsize_usrpage = cpu_to_be32((ilog2(nent) << 24) | uar->index);
+	cq_context->logsize_usrpage =
+		cpu_to_be32((ilog2(nent) << 24) |
+			    mlx4_to_hw_uar_index(dev, uar->index));
 	cq_context->comp_eqn	    = priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].eqn;
 	cq_context->log_page_size   = mtt->page_shift - MLX4_ICM_PAGE_SHIFT;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index 038f9ce391e6..1494997c4f7e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -236,6 +236,24 @@ static const struct ptp_clock_info mlx4_en_ptp_clock_info = {
 	.enable		= mlx4_en_phc_enable,
 };
 
+#define MLX4_EN_WRAP_AROUND_SEC	10ULL
+
+/* This function calculates the max shift that enables the user range
+ * of MLX4_EN_WRAP_AROUND_SEC values in the cycles register.
+ */
+static u32 freq_to_shift(u16 freq)
+{
+	u32 freq_khz = freq * 1000;
+	u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC;
+	u64 max_val_cycles_rounded = is_power_of_2(max_val_cycles + 1) ?
+		max_val_cycles : roundup_pow_of_two(max_val_cycles) - 1;
+	/* calculate max possible multiplier in order to fit in 64bit */
+	u64 max_mul = div_u64(0xffffffffffffffffULL, max_val_cycles_rounded);
+
+	/* This comes from the reverse of clocksource_khz2mult */
+	return ilog2(div_u64(max_mul * freq_khz, 1000000));
+}
+
 void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
 {
 	struct mlx4_dev *dev = mdev->dev;
@@ -254,12 +272,7 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
 	memset(&mdev->cycles, 0, sizeof(mdev->cycles));
 	mdev->cycles.read = mlx4_en_read_clock;
 	mdev->cycles.mask = CLOCKSOURCE_MASK(48);
-	/* Using shift to make calculation more accurate. Since current HW
-	 * clock frequency is 427 MHz, and cycles are given using a 48 bits
-	 * register, the biggest shift when calculating using u64, is 14
-	 * (max_cycles * multiplier < 2^64)
-	 */
-	mdev->cycles.shift = 14;
+	mdev->cycles.shift = freq_to_shift(dev->caps.hca_core_clock);
 	mdev->cycles.mult =
 		clocksource_khz2mult(1000 * dev->caps.hca_core_clock, mdev->cycles.shift);
 	mdev->nominal_c_mult = mdev->cycles.mult;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 0c7e3f69a73b..21e2c0960271 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2245,7 +2245,7 @@ static int mlx4_en_set_vf_mac(struct net_device *dev, int queue, u8 *mac)
 	struct mlx4_en_dev *mdev = en_priv->mdev;
 	u64 mac_u64 = mlx4_mac_to_u64(mac);
 
-	if (!is_valid_ether_addr(mac))
+	if (is_multicast_ether_addr(mac))
 		return -EINVAL;
 
 	return mlx4_set_vf_mac(mdev->dev, en_priv->port, queue, mac_u64);
@@ -2344,8 +2344,6 @@ out:
 	/* set offloads */
 	priv->dev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
 				      NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL;
-	priv->dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
-	priv->dev->features    |= NETIF_F_GSO_UDP_TUNNEL;
 }
 
 static void mlx4_en_del_vxlan_offloads(struct work_struct *work)
@@ -2356,8 +2354,6 @@ static void mlx4_en_del_vxlan_offloads(struct work_struct *work)
 	/* unset offloads */
 	priv->dev->hw_enc_features &= ~(NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
 				      NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL);
-	priv->dev->hw_features &= ~NETIF_F_GSO_UDP_TUNNEL;
-	priv->dev->features    &= ~NETIF_F_GSO_UDP_TUNNEL;
 
 	ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port,
 				  VXLAN_STEER_BY_OUTER_MAC, 0);
@@ -2980,6 +2976,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 		priv->rss_hash_fn = ETH_RSS_HASH_TOP;
 	}
 
+	if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) {
+		dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
+		dev->features    |= NETIF_F_GSO_UDP_TUNNEL;
+	}
+
 	mdev->pndev[port] = dev;
 	mdev->upper[port] = NULL;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index ee99e67187f5..3904b5fc0b7c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -238,11 +238,11 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 	stats->collisions = 0;
 	stats->rx_dropped = be32_to_cpu(mlx4_en_stats->RDROP);
 	stats->rx_length_errors = be32_to_cpu(mlx4_en_stats->RdropLength);
-	stats->rx_over_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw);
+	stats->rx_over_errors = 0;
 	stats->rx_crc_errors = be32_to_cpu(mlx4_en_stats->RCRC);
 	stats->rx_frame_errors = 0;
 	stats->rx_fifo_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw);
-	stats->rx_missed_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw);
+	stats->rx_missed_errors = 0;
 	stats->tx_aborted_errors = 0;
 	stats->tx_carrier_errors = 0;
 	stats->tx_fifo_errors = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
index 12aab5a659d3..02e925d6f734 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
@@ -58,7 +58,8 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride,
 	} else {
 		context->sq_size_stride = ilog2(TXBB_SIZE) - 4;
 	}
-	context->usr_page = cpu_to_be32(mdev->priv_uar.index);
+	context->usr_page = cpu_to_be32(mlx4_to_hw_uar_index(mdev->dev,
+					mdev->priv_uar.index));
 	context->local_qpn = cpu_to_be32(qpn);
 	context->pri_path.ackto = 1 & 0x07;
 	context->pri_path.sched_queue = 0x83 | (priv->port - 1) << 6;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 4421bf5463f6..e0946ab22010 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -213,7 +213,9 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
 	mlx4_en_fill_qp_context(priv, ring->size, ring->stride, 1, 0, ring->qpn,
 				ring->cqn, user_prio, &ring->context);
 	if (ring->bf_alloced)
-		ring->context.usr_page = cpu_to_be32(ring->bf.uar->index);
+		ring->context.usr_page =
+			cpu_to_be32(mlx4_to_hw_uar_index(mdev->dev,
+							 ring->bf.uar->index));
 
 	err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, &ring->context,
 			       &ring->qp, &ring->qp_state);
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 4696053165f8..f613977455e0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -940,9 +940,10 @@ static void __iomem *mlx4_get_eq_uar(struct mlx4_dev *dev, struct mlx4_eq *eq)
 
 	if (!priv->eq_table.uar_map[index]) {
 		priv->eq_table.uar_map[index] =
-			ioremap(pci_resource_start(dev->persist->pdev, 2) +
-				((eq->eqn / 4) << PAGE_SHIFT),
-				PAGE_SIZE);
+			ioremap(
+				pci_resource_start(dev->persist->pdev, 2) +
+				((eq->eqn / 4) << (dev->uar_page_shift)),
+				(1 << (dev->uar_page_shift)));
 		if (!priv->eq_table.uar_map[index]) {
 			mlx4_err(dev, "Couldn't map EQ doorbell for EQN 0x%06x\n",
 				 eq->eqn);
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index f1b6d219e445..f8674ae62752 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -168,6 +168,20 @@ struct mlx4_port_config {
 
 static atomic_t pf_loading = ATOMIC_INIT(0);
 
+static inline void mlx4_set_num_reserved_uars(struct mlx4_dev *dev,
+					      struct mlx4_dev_cap *dev_cap)
+{
+	/* The reserved_uars is calculated by system page size unit.
+	 * Therefore, adjustment is added when the uar page size is less
+	 * than the system page size
+	 */
+	dev->caps.reserved_uars	=
+		max_t(int,
+		      mlx4_get_num_reserved_uar(dev),
+		      dev_cap->reserved_uars /
+			(1 << (PAGE_SHIFT - dev->uar_page_shift)));
+}
+
 int mlx4_check_port_params(struct mlx4_dev *dev,
 			   enum mlx4_port_type *port_type)
 {
@@ -386,8 +400,6 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.reserved_mtts      = dev_cap->reserved_mtts;
 	dev->caps.reserved_mrws	     = dev_cap->reserved_mrws;
 
-	/* The first 128 UARs are used for EQ doorbells */
-	dev->caps.reserved_uars	     = max_t(int, 128, dev_cap->reserved_uars);
 	dev->caps.reserved_pds	     = dev_cap->reserved_pds;
 	dev->caps.reserved_xrcds     = (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) ?
 					dev_cap->reserved_xrcds : 0;
@@ -405,6 +417,15 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.max_gso_sz	     = dev_cap->max_gso_sz;
 	dev->caps.max_rss_tbl_sz     = dev_cap->max_rss_tbl_sz;
 
+	/* Save uar page shift */
+	if (!mlx4_is_slave(dev)) {
+		/* Virtual PCI function needs to determine UAR page size from
+		 * firmware. Only master PCI function can set the uar page size
+		 */
+		dev->uar_page_shift = DEFAULT_UAR_PAGE_SHIFT;
+		mlx4_set_num_reserved_uars(dev, dev_cap);
+	}
+
 	if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PHV_EN) {
 		struct mlx4_init_hca_param hca_param;
 
@@ -815,16 +836,25 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 		return -ENODEV;
 	}
 
-	/* slave gets uar page size from QUERY_HCA fw command */
-	dev->caps.uar_page_size = 1 << (hca_param.uar_page_sz + 12);
+	/* Set uar_page_shift for VF */
+	dev->uar_page_shift = hca_param.uar_page_sz + 12;
 
-	/* TODO: relax this assumption */
-	if (dev->caps.uar_page_size != PAGE_SIZE) {
-		mlx4_err(dev, "UAR size:%d != kernel PAGE_SIZE of %ld\n",
-			 dev->caps.uar_page_size, PAGE_SIZE);
-		return -ENODEV;
+	/* Make sure the master uar page size is valid */
+	if (dev->uar_page_shift > PAGE_SHIFT) {
+		mlx4_err(dev,
+			 "Invalid configuration: uar page size is larger than system page size\n");
+		return  -ENODEV;
 	}
 
+	/* Set reserved_uars based on the uar_page_shift */
+	mlx4_set_num_reserved_uars(dev, &dev_cap);
+
+	/* Although uar page size in FW differs from system page size,
+	 * upper software layers (mlx4_ib, mlx4_en and part of mlx4_core)
+	 * still works with assumption that uar page size == system page size
+	 */
+	dev->caps.uar_page_size = PAGE_SIZE;
+
 	memset(&func_cap, 0, sizeof(func_cap));
 	err = mlx4_QUERY_FUNC_CAP(dev, 0, &func_cap);
 	if (err) {
@@ -1226,6 +1256,7 @@ err_set_port:
 static int mlx4_mf_bond(struct mlx4_dev *dev)
 {
 	int err = 0;
+	int nvfs;
 	struct mlx4_slaves_pport slaves_port1;
 	struct mlx4_slaves_pport slaves_port2;
 	DECLARE_BITMAP(slaves_port_1_2, MLX4_MFUNC_MAX);
@@ -1242,11 +1273,18 @@ static int mlx4_mf_bond(struct mlx4_dev *dev)
 		return -EINVAL;
 	}
 
+	/* number of virtual functions is number of total functions minus one
+	 * physical function for each port.
+	 */
+	nvfs = bitmap_weight(slaves_port1.slaves, dev->persist->num_vfs + 1) +
+		bitmap_weight(slaves_port2.slaves, dev->persist->num_vfs + 1) - 2;
+
 	/* limit on maximum allowed VFs */
-	if ((bitmap_weight(slaves_port1.slaves, dev->persist->num_vfs + 1) +
-	    bitmap_weight(slaves_port2.slaves, dev->persist->num_vfs + 1)) >
-	    MAX_MF_BOND_ALLOWED_SLAVES)
+	if (nvfs > MAX_MF_BOND_ALLOWED_SLAVES) {
+		mlx4_warn(dev, "HA mode is not supported for %d VFs (max %d are allowed)\n",
+			  nvfs, MAX_MF_BOND_ALLOWED_SLAVES);
 		return -EINVAL;
+	}
 
 	if (dev->caps.steering_mode != MLX4_STEERING_MODE_DEVICE_MANAGED) {
 		mlx4_warn(dev, "HA mode unsupported for NON DMFS steering\n");
@@ -2179,8 +2217,12 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 
 		dev->caps.max_fmr_maps = (1 << (32 - ilog2(dev->caps.num_mpts))) - 1;
 
-		init_hca.log_uar_sz = ilog2(dev->caps.num_uars);
-		init_hca.uar_page_sz = PAGE_SHIFT - 12;
+		/* Always set UAR page size 4KB, set log_uar_sz accordingly */
+		init_hca.log_uar_sz = ilog2(dev->caps.num_uars) +
+				      PAGE_SHIFT -
+				      DEFAULT_UAR_PAGE_SHIFT;
+		init_hca.uar_page_sz = DEFAULT_UAR_PAGE_SHIFT - 12;
+
 		init_hca.mw_enabled = 0;
 		if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW ||
 		    dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN)
diff --git a/drivers/net/ethernet/mellanox/mlx4/pd.c b/drivers/net/ethernet/mellanox/mlx4/pd.c
index 609c59dc854e..b3cc3ab63799 100644
--- a/drivers/net/ethernet/mellanox/mlx4/pd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/pd.c
@@ -269,9 +269,15 @@ EXPORT_SYMBOL_GPL(mlx4_bf_free);
 
 int mlx4_init_uar_table(struct mlx4_dev *dev)
 {
-	if (dev->caps.num_uars <= 128) {
-		mlx4_err(dev, "Only %d UAR pages (need more than 128)\n",
-			 dev->caps.num_uars);
+	int num_reserved_uar = mlx4_get_num_reserved_uar(dev);
+
+	mlx4_dbg(dev, "uar_page_shift = %d", dev->uar_page_shift);
+	mlx4_dbg(dev, "Effective reserved_uars=%d", dev->caps.reserved_uars);
+
+	if (dev->caps.num_uars <= num_reserved_uar) {
+		mlx4_err(
+			dev, "Only %d UAR pages (need more than %d)\n",
+			dev->caps.num_uars, num_reserved_uar);
 		mlx4_err(dev, "Increase firmware log2_uar_bar_megabytes?\n");
 		return -ENODEV;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 787b7bb54d52..211c65087997 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -193,10 +193,10 @@ int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac)
 	if (need_mf_bond) {
 		if (port == 1) {
 			mutex_lock(&table->mutex);
-			mutex_lock(&dup_table->mutex);
+			mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING);
 		} else {
 			mutex_lock(&dup_table->mutex);
-			mutex_lock(&table->mutex);
+			mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING);
 		}
 	} else {
 		mutex_lock(&table->mutex);
@@ -389,10 +389,10 @@ void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac)
 	if (dup) {
 		if (port == 1) {
 			mutex_lock(&table->mutex);
-			mutex_lock(&dup_table->mutex);
+			mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING);
 		} else {
 			mutex_lock(&dup_table->mutex);
-			mutex_lock(&table->mutex);
+			mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING);
 		}
 	} else {
 		mutex_lock(&table->mutex);
@@ -479,10 +479,10 @@ int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac)
 	if (dup) {
 		if (port == 1) {
 			mutex_lock(&table->mutex);
-			mutex_lock(&dup_table->mutex);
+			mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING);
 		} else {
 			mutex_lock(&dup_table->mutex);
-			mutex_lock(&table->mutex);
+			mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING);
 		}
 	} else {
 		mutex_lock(&table->mutex);
@@ -588,10 +588,10 @@ int __mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan,
 	if (need_mf_bond) {
 		if (port == 1) {
 			mutex_lock(&table->mutex);
-			mutex_lock(&dup_table->mutex);
+			mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING);
 		} else {
 			mutex_lock(&dup_table->mutex);
-			mutex_lock(&table->mutex);
+			mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING);
 		}
 	} else {
 		mutex_lock(&table->mutex);
@@ -764,10 +764,10 @@ void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan)
 	if (dup) {
 		if (port == 1) {
 			mutex_lock(&table->mutex);
-			mutex_lock(&dup_table->mutex);
+			mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING);
 		} else {
 			mutex_lock(&dup_table->mutex);
-			mutex_lock(&table->mutex);
+			mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING);
 		}
 	} else {
 		mutex_lock(&table->mutex);
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index b46dbe29ef6c..25ce1b030a00 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -915,11 +915,13 @@ static int handle_existing_counter(struct mlx4_dev *dev, u8 slave, int port,
 
 	spin_lock_irq(mlx4_tlock(dev));
 	r = find_res(dev, counter_index, RES_COUNTER);
-	if (!r || r->owner != slave)
+	if (!r || r->owner != slave) {
 		ret = -EINVAL;
-	counter = container_of(r, struct res_counter, com);
-	if (!counter->port)
-		counter->port = port;
+	} else {
+		counter = container_of(r, struct res_counter, com);
+		if (!counter->port)
+			counter->port = port;
+	}
 
 	spin_unlock_irq(mlx4_tlock(dev));
 	return ret;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index aac071a7e830..5b1753233c5d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -223,6 +223,7 @@ struct mlx5e_pport_stats {
 
 static const char rq_stats_strings[][ETH_GSTRING_LEN] = {
 	"packets",
+	"bytes",
 	"csum_none",
 	"csum_sw",
 	"lro_packets",
@@ -232,16 +233,18 @@ static const char rq_stats_strings[][ETH_GSTRING_LEN] = {
 
 struct mlx5e_rq_stats {
 	u64 packets;
+	u64 bytes;
 	u64 csum_none;
 	u64 csum_sw;
 	u64 lro_packets;
 	u64 lro_bytes;
 	u64 wqe_err;
-#define NUM_RQ_STATS 6
+#define NUM_RQ_STATS 7
 };
 
 static const char sq_stats_strings[][ETH_GSTRING_LEN] = {
 	"packets",
+	"bytes",
 	"tso_packets",
 	"tso_bytes",
 	"csum_offload_none",
@@ -253,6 +256,7 @@ static const char sq_stats_strings[][ETH_GSTRING_LEN] = {
 
 struct mlx5e_sq_stats {
 	u64 packets;
+	u64 bytes;
 	u64 tso_packets;
 	u64 tso_bytes;
 	u64 csum_offload_none;
@@ -260,7 +264,7 @@ struct mlx5e_sq_stats {
 	u64 wake;
 	u64 dropped;
 	u64 nop;
-#define NUM_SQ_STATS 8
+#define NUM_SQ_STATS 9
 };
 
 struct mlx5e_stats {
@@ -304,14 +308,9 @@ enum {
 	MLX5E_RQ_STATE_POST_WQES_ENABLE,
 };
 
-enum cq_flags {
-	MLX5E_CQ_HAS_CQES = 1,
-};
-
 struct mlx5e_cq {
 	/* data path - accessed per cqe */
 	struct mlx5_cqwq           wq;
-	unsigned long              flags;
 
 	/* data path - accessed per napi poll */
 	struct napi_struct        *napi;
@@ -452,6 +451,8 @@ enum mlx5e_traffic_types {
 	MLX5E_NUM_TT,
 };
 
+#define IS_HASHING_TT(tt) (tt != MLX5E_TT_ANY)
+
 enum mlx5e_rqt_ix {
 	MLX5E_INDIRECTION_RQT,
 	MLX5E_SINGLE_RQ_RQT,
@@ -618,9 +619,12 @@ void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv);
 void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv);
 
 int mlx5e_redirect_rqt(struct mlx5e_priv *priv, enum mlx5e_rqt_ix rqt_ix);
+void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv);
 
 int mlx5e_open_locked(struct net_device *netdev);
 int mlx5e_close_locked(struct net_device *netdev);
+void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len,
+				   int num_channels);
 
 static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq,
 				      struct mlx5e_tx_wqe *wqe, int bf_sz)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
index be6543570b2b..2018eebe1531 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
@@ -62,10 +62,11 @@ static void mlx5e_timestamp_overflow(struct work_struct *work)
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct mlx5e_tstamp *tstamp = container_of(dwork, struct mlx5e_tstamp,
 						   overflow_work);
+	unsigned long flags;
 
-	write_lock(&tstamp->lock);
+	write_lock_irqsave(&tstamp->lock, flags);
 	timecounter_read(&tstamp->clock);
-	write_unlock(&tstamp->lock);
+	write_unlock_irqrestore(&tstamp->lock, flags);
 	schedule_delayed_work(&tstamp->overflow_work, tstamp->overflow_period);
 }
 
@@ -136,10 +137,11 @@ static int mlx5e_ptp_settime(struct ptp_clock_info *ptp,
 	struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp,
 						   ptp_info);
 	u64 ns = timespec64_to_ns(ts);
+	unsigned long flags;
 
-	write_lock(&tstamp->lock);
+	write_lock_irqsave(&tstamp->lock, flags);
 	timecounter_init(&tstamp->clock, &tstamp->cycles, ns);
-	write_unlock(&tstamp->lock);
+	write_unlock_irqrestore(&tstamp->lock, flags);
 
 	return 0;
 }
@@ -150,10 +152,11 @@ static int mlx5e_ptp_gettime(struct ptp_clock_info *ptp,
 	struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp,
 						   ptp_info);
 	u64 ns;
+	unsigned long flags;
 
-	write_lock(&tstamp->lock);
+	write_lock_irqsave(&tstamp->lock, flags);
 	ns = timecounter_read(&tstamp->clock);
-	write_unlock(&tstamp->lock);
+	write_unlock_irqrestore(&tstamp->lock, flags);
 
 	*ts = ns_to_timespec64(ns);
 
@@ -164,10 +167,11 @@ static int mlx5e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 {
 	struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp,
 						   ptp_info);
+	unsigned long flags;
 
-	write_lock(&tstamp->lock);
+	write_lock_irqsave(&tstamp->lock, flags);
 	timecounter_adjtime(&tstamp->clock, delta);
-	write_unlock(&tstamp->lock);
+	write_unlock_irqrestore(&tstamp->lock, flags);
 
 	return 0;
 }
@@ -176,6 +180,7 @@ static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta)
 {
 	u64 adj;
 	u32 diff;
+	unsigned long flags;
 	int neg_adj = 0;
 	struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp,
 						  ptp_info);
@@ -189,11 +194,11 @@ static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta)
 	adj *= delta;
 	diff = div_u64(adj, 1000000000ULL);
 
-	write_lock(&tstamp->lock);
+	write_lock_irqsave(&tstamp->lock, flags);
 	timecounter_read(&tstamp->clock);
 	tstamp->cycles.mult = neg_adj ? tstamp->nominal_c_mult - diff :
 					tstamp->nominal_c_mult + diff;
-	write_unlock(&tstamp->lock);
+	write_unlock_irqrestore(&tstamp->lock, flags);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 65624ac65b4c..5abeb00fceb8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -385,6 +385,8 @@ static int mlx5e_set_channels(struct net_device *dev,
 		mlx5e_close_locked(dev);
 
 	priv->params.num_channels = count;
+	mlx5e_build_default_indir_rqt(priv->params.indirection_rqt,
+				      MLX5E_INDIR_RQT_SIZE, count);
 
 	if (was_opened)
 		err = mlx5e_open_locked(dev);
@@ -703,18 +705,36 @@ static int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 	return 0;
 }
 
+static void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx);
+	int i;
+
+	MLX5_SET(modify_tir_in, in, bitmask.hash, 1);
+	mlx5e_build_tir_ctx_hash(tirc, priv);
+
+	for (i = 0; i < MLX5E_NUM_TT; i++)
+		if (IS_HASHING_TT(i))
+			mlx5_core_modify_tir(mdev, priv->tirn[i], in, inlen);
+}
+
 static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 			  const u8 *key, const u8 hfunc)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	bool close_open;
-	int err = 0;
+	int inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
+	void *in;
 
 	if ((hfunc != ETH_RSS_HASH_NO_CHANGE) &&
 	    (hfunc != ETH_RSS_HASH_XOR) &&
 	    (hfunc != ETH_RSS_HASH_TOP))
 		return -EINVAL;
 
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
 	mutex_lock(&priv->state_lock);
 
 	if (indir) {
@@ -723,11 +743,6 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 		mlx5e_redirect_rqt(priv, MLX5E_INDIRECTION_RQT);
 	}
 
-	close_open = (key || (hfunc != ETH_RSS_HASH_NO_CHANGE)) &&
-		     test_bit(MLX5E_STATE_OPENED, &priv->state);
-	if (close_open)
-		mlx5e_close_locked(dev);
-
 	if (key)
 		memcpy(priv->params.toeplitz_hash_key, key,
 		       sizeof(priv->params.toeplitz_hash_key));
@@ -735,12 +750,13 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 	if (hfunc != ETH_RSS_HASH_NO_CHANGE)
 		priv->params.rss_hfunc = hfunc;
 
-	if (close_open)
-		err = mlx5e_open_locked(priv->netdev);
+	mlx5e_modify_tirs_hash(priv, in, inlen);
 
 	mutex_unlock(&priv->state_lock);
 
-	return err;
+	kvfree(in);
+
+	return 0;
 }
 
 static int mlx5e_get_rxnfc(struct net_device *netdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 6a3e430f1062..402994bf7e16 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -141,6 +141,10 @@ void mlx5e_update_stats(struct mlx5e_priv *priv)
 		return;
 
 	/* Collect firts the SW counters and then HW for consistency */
+	s->rx_packets		= 0;
+	s->rx_bytes		= 0;
+	s->tx_packets		= 0;
+	s->tx_bytes		= 0;
 	s->tso_packets		= 0;
 	s->tso_bytes		= 0;
 	s->tx_queue_stopped	= 0;
@@ -155,6 +159,8 @@ void mlx5e_update_stats(struct mlx5e_priv *priv)
 	for (i = 0; i < priv->params.num_channels; i++) {
 		rq_stats = &priv->channel[i]->rq.stats;
 
+		s->rx_packets	+= rq_stats->packets;
+		s->rx_bytes	+= rq_stats->bytes;
 		s->lro_packets	+= rq_stats->lro_packets;
 		s->lro_bytes	+= rq_stats->lro_bytes;
 		s->rx_csum_none	+= rq_stats->csum_none;
@@ -164,6 +170,8 @@ void mlx5e_update_stats(struct mlx5e_priv *priv)
 		for (j = 0; j < priv->params.num_tc; j++) {
 			sq_stats = &priv->channel[i]->sq[j].stats;
 
+			s->tx_packets		+= sq_stats->packets;
+			s->tx_bytes		+= sq_stats->bytes;
 			s->tso_packets		+= sq_stats->tso_packets;
 			s->tso_bytes		+= sq_stats->tso_bytes;
 			s->tx_queue_stopped	+= sq_stats->stopped;
@@ -225,23 +233,6 @@ void mlx5e_update_stats(struct mlx5e_priv *priv)
 	s->tx_broadcast_bytes   =
 		MLX5_GET_CTR(out, transmitted_eth_broadcast.octets);
 
-	s->rx_packets =
-		s->rx_unicast_packets +
-		s->rx_multicast_packets +
-		s->rx_broadcast_packets;
-	s->rx_bytes =
-		s->rx_unicast_bytes +
-		s->rx_multicast_bytes +
-		s->rx_broadcast_bytes;
-	s->tx_packets =
-		s->tx_unicast_packets +
-		s->tx_multicast_packets +
-		s->tx_broadcast_packets;
-	s->tx_bytes =
-		s->tx_unicast_bytes +
-		s->tx_multicast_bytes +
-		s->tx_broadcast_bytes;
-
 	/* Update calculated offload counters */
 	s->tx_csum_offload = s->tx_packets - tx_offload_none;
 	s->rx_csum_good    = s->rx_packets - s->rx_csum_none -
@@ -1199,7 +1190,6 @@ static void mlx5e_fill_indir_rqt_rqns(struct mlx5e_priv *priv, void *rqtc)
 			ix = mlx5e_bits_invert(i, MLX5E_LOG_INDIR_RQT_SIZE);
 
 		ix = priv->params.indirection_rqt[ix];
-		ix = ix % priv->params.num_channels;
 		MLX5_SET(rqtc, rqtc, rq_num[i],
 			 test_bit(MLX5E_STATE_OPENED, &priv->state) ?
 			 priv->channel[ix]->rq.rqn :
@@ -1317,7 +1307,22 @@ static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv)
 			      lro_timer_supported_periods[2]));
 }
 
-static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt)
+void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv)
+{
+	MLX5_SET(tirc, tirc, rx_hash_fn,
+		 mlx5e_rx_hash_fn(priv->params.rss_hfunc));
+	if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) {
+		void *rss_key = MLX5_ADDR_OF(tirc, tirc,
+					     rx_hash_toeplitz_key);
+		size_t len = MLX5_FLD_SZ_BYTES(tirc,
+					       rx_hash_toeplitz_key);
+
+		MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
+		memcpy(rss_key, priv->params.toeplitz_hash_key, len);
+	}
+}
+
+static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 
@@ -1325,6 +1330,7 @@ static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt)
 	void *tirc;
 	int inlen;
 	int err;
+	int tt;
 
 	inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
 	in = mlx5_vzalloc(inlen);
@@ -1336,7 +1342,11 @@ static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt)
 
 	mlx5e_build_tir_ctx_lro(tirc, priv);
 
-	err = mlx5_core_modify_tir(mdev, priv->tirn[tt], in, inlen);
+	for (tt = 0; tt < MLX5E_NUM_TT; tt++) {
+		err = mlx5_core_modify_tir(mdev, priv->tirn[tt], in, inlen);
+		if (err)
+			break;
+	}
 
 	kvfree(in);
 
@@ -1672,17 +1682,7 @@ static void mlx5e_build_tir_ctx(struct mlx5e_priv *priv, u32 *tirc, int tt)
 	default:
 		MLX5_SET(tirc, tirc, indirect_table,
 			 priv->rqtn[MLX5E_INDIRECTION_RQT]);
-		MLX5_SET(tirc, tirc, rx_hash_fn,
-			 mlx5e_rx_hash_fn(priv->params.rss_hfunc));
-		if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) {
-			void *rss_key = MLX5_ADDR_OF(tirc, tirc,
-						     rx_hash_toeplitz_key);
-			size_t len = MLX5_FLD_SZ_BYTES(tirc,
-						       rx_hash_toeplitz_key);
-
-			MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
-			memcpy(rss_key, priv->params.toeplitz_hash_key, len);
-		}
+		mlx5e_build_tir_ctx_hash(tirc, priv);
 		break;
 	}
 
@@ -1885,8 +1885,10 @@ static int mlx5e_set_features(struct net_device *netdev,
 			mlx5e_close_locked(priv->netdev);
 
 		priv->params.lro_en = !!(features & NETIF_F_LRO);
-		mlx5e_modify_tir_lro(priv, MLX5E_TT_IPV4_TCP);
-		mlx5e_modify_tir_lro(priv, MLX5E_TT_IPV6_TCP);
+		err = mlx5e_modify_tirs_lro(priv);
+		if (err)
+			mlx5_core_warn(priv->mdev, "lro modify failed, %d\n",
+				       err);
 
 		if (was_opened)
 			err = mlx5e_open_locked(priv->netdev);
@@ -2024,18 +2026,37 @@ static int mlx5e_get_vf_stats(struct net_device *dev,
 					    vf_stats);
 }
 
-static struct net_device_ops mlx5e_netdev_ops = {
+static const struct net_device_ops mlx5e_netdev_ops_basic = {
+	.ndo_open                = mlx5e_open,
+	.ndo_stop                = mlx5e_close,
+	.ndo_start_xmit          = mlx5e_xmit,
+	.ndo_get_stats64         = mlx5e_get_stats,
+	.ndo_set_rx_mode         = mlx5e_set_rx_mode,
+	.ndo_set_mac_address     = mlx5e_set_mac,
+	.ndo_vlan_rx_add_vid     = mlx5e_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid    = mlx5e_vlan_rx_kill_vid,
+	.ndo_set_features        = mlx5e_set_features,
+	.ndo_change_mtu          = mlx5e_change_mtu,
+	.ndo_do_ioctl            = mlx5e_ioctl,
+};
+
+static const struct net_device_ops mlx5e_netdev_ops_sriov = {
 	.ndo_open                = mlx5e_open,
 	.ndo_stop                = mlx5e_close,
 	.ndo_start_xmit          = mlx5e_xmit,
 	.ndo_get_stats64         = mlx5e_get_stats,
 	.ndo_set_rx_mode         = mlx5e_set_rx_mode,
 	.ndo_set_mac_address     = mlx5e_set_mac,
-	.ndo_vlan_rx_add_vid	 = mlx5e_vlan_rx_add_vid,
-	.ndo_vlan_rx_kill_vid	 = mlx5e_vlan_rx_kill_vid,
+	.ndo_vlan_rx_add_vid     = mlx5e_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid    = mlx5e_vlan_rx_kill_vid,
 	.ndo_set_features        = mlx5e_set_features,
-	.ndo_change_mtu		 = mlx5e_change_mtu,
-	.ndo_do_ioctl		 = mlx5e_ioctl,
+	.ndo_change_mtu          = mlx5e_change_mtu,
+	.ndo_do_ioctl            = mlx5e_ioctl,
+	.ndo_set_vf_mac          = mlx5e_set_vf_mac,
+	.ndo_set_vf_vlan         = mlx5e_set_vf_vlan,
+	.ndo_get_vf_config       = mlx5e_get_vf_config,
+	.ndo_set_vf_link_state   = mlx5e_set_vf_link_state,
+	.ndo_get_vf_stats        = mlx5e_get_vf_stats,
 };
 
 static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev)
@@ -2070,12 +2091,20 @@ u16 mlx5e_get_max_inline_cap(struct mlx5_core_dev *mdev)
 	       2 /*sizeof(mlx5e_tx_wqe.inline_hdr_start)*/;
 }
 
+void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len,
+				   int num_channels)
+{
+	int i;
+
+	for (i = 0; i < len; i++)
+		indirection_rqt[i] = i % num_channels;
+}
+
 static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev,
 				    struct net_device *netdev,
 				    int num_channels)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	int i;
 
 	priv->params.log_sq_size           =
 		MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
@@ -2099,8 +2128,8 @@ static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev,
 	netdev_rss_key_fill(priv->params.toeplitz_hash_key,
 			    sizeof(priv->params.toeplitz_hash_key));
 
-	for (i = 0; i < MLX5E_INDIR_RQT_SIZE; i++)
-		priv->params.indirection_rqt[i] = i % num_channels;
+	mlx5e_build_default_indir_rqt(priv->params.indirection_rqt,
+				      MLX5E_INDIR_RQT_SIZE, num_channels);
 
 	priv->params.lro_wqe_sz            =
 		MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
@@ -2137,18 +2166,11 @@ static void mlx5e_build_netdev(struct net_device *netdev)
 
 	SET_NETDEV_DEV(netdev, &mdev->pdev->dev);
 
-	if (priv->params.num_tc > 1)
-		mlx5e_netdev_ops.ndo_select_queue = mlx5e_select_queue;
-
-	if (MLX5_CAP_GEN(mdev, vport_group_manager)) {
-		mlx5e_netdev_ops.ndo_set_vf_mac = mlx5e_set_vf_mac;
-		mlx5e_netdev_ops.ndo_set_vf_vlan = mlx5e_set_vf_vlan;
-		mlx5e_netdev_ops.ndo_get_vf_config = mlx5e_get_vf_config;
-		mlx5e_netdev_ops.ndo_set_vf_link_state = mlx5e_set_vf_link_state;
-		mlx5e_netdev_ops.ndo_get_vf_stats = mlx5e_get_vf_stats;
-	}
+	if (MLX5_CAP_GEN(mdev, vport_group_manager))
+		netdev->netdev_ops = &mlx5e_netdev_ops_sriov;
+	else
+		netdev->netdev_ops = &mlx5e_netdev_ops_basic;
 
-	netdev->netdev_ops        = &mlx5e_netdev_ops;
 	netdev->watchdog_timeo    = 15 * HZ;
 
 	netdev->ethtool_ops	  = &mlx5e_ethtool_ops;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index dd959d929aad..59658b9d05d1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -230,10 +230,6 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
 	int work_done;
 
-	/* avoid accessing cq (dma coherent memory) if not needed */
-	if (!test_and_clear_bit(MLX5E_CQ_HAS_CQES, &cq->flags))
-		return 0;
-
 	for (work_done = 0; work_done < budget; work_done++) {
 		struct mlx5e_rx_wqe *wqe;
 		struct mlx5_cqe64 *cqe;
@@ -267,6 +263,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 
 		mlx5e_build_rx_skb(cqe, rq, skb);
 		rq->stats.packets++;
+		rq->stats.bytes += be32_to_cpu(cqe->byte_cnt);
 		napi_gro_receive(cq->napi, skb);
 
 wq_ll_pop:
@@ -279,8 +276,5 @@ wq_ll_pop:
 	/* ensure cq space is freed before enabling more cqes */
 	wmb();
 
-	if (work_done == budget)
-		set_bit(MLX5E_CQ_HAS_CQES, &cq->flags);
-
 	return work_done;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 2c3fba0fff54..bb4eeeb007de 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -179,6 +179,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 	unsigned int skb_len = skb->len;
 	u8  opcode = MLX5_OPCODE_SEND;
 	dma_addr_t dma_addr = 0;
+	unsigned int num_bytes;
 	bool bf = false;
 	u16 headlen;
 	u16 ds_cnt;
@@ -204,8 +205,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 		opcode       = MLX5_OPCODE_LSO;
 		ihs          = skb_transport_offset(skb) + tcp_hdrlen(skb);
 		payload_len  = skb->len - ihs;
-		wi->num_bytes = skb->len +
-				(skb_shinfo(skb)->gso_segs - 1) * ihs;
+		num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
 		sq->stats.tso_packets++;
 		sq->stats.tso_bytes += payload_len;
 	} else {
@@ -213,9 +213,11 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 		     !skb->xmit_more &&
 		     !skb_shinfo(skb)->nr_frags;
 		ihs = mlx5e_get_inline_hdr_size(sq, skb, bf);
-		wi->num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
+		num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
 	}
 
+	wi->num_bytes = num_bytes;
+
 	if (skb_vlan_tag_present(skb)) {
 		mlx5e_insert_vlan(eseg->inline_hdr_start, skb, ihs, &skb_data,
 				  &skb_len);
@@ -307,6 +309,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
 	sq->bf_budget = bf ? sq->bf_budget - 1 : 0;
 
 	sq->stats.packets++;
+	sq->stats.bytes += num_bytes;
 	return NETDEV_TX_OK;
 
 dma_unmap_wqe_err:
@@ -335,10 +338,6 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq)
 	u16 sqcc;
 	int i;
 
-	/* avoid accessing cq (dma coherent memory) if not needed */
-	if (!test_and_clear_bit(MLX5E_CQ_HAS_CQES, &cq->flags))
-		return false;
-
 	sq = container_of(cq, struct mlx5e_sq, cq);
 
 	npkts = 0;
@@ -422,10 +421,6 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq)
 				netif_tx_wake_queue(sq->txq);
 				sq->stats.wake++;
 	}
-	if (i == MLX5E_TX_CQ_POLL_BUDGET) {
-		set_bit(MLX5E_CQ_HAS_CQES, &cq->flags);
-		return true;
-	}
 
-	return false;
+	return (i == MLX5E_TX_CQ_POLL_BUDGET);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 4ac8d716dbdd..66d51a77609e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -88,7 +88,6 @@ void mlx5e_completion_event(struct mlx5_core_cq *mcq)
 {
 	struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq);
 
-	set_bit(MLX5E_CQ_HAS_CQES, &cq->flags);
 	set_bit(MLX5E_CHANNEL_NAPI_SCHED, &cq->channel->flags);
 	barrier();
 	napi_schedule(cq->napi);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index c071077aafbd..7992c553c1f5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -215,7 +215,7 @@ mlxsw_pci_queue_elem_info_producer_get(struct mlxsw_pci_queue *q)
 {
 	int index = q->producer_counter & (q->count - 1);
 
-	if ((q->producer_counter - q->consumer_counter) == q->count)
+	if ((u16) (q->producer_counter - q->consumer_counter) == q->count)
 		return NULL;
 	return mlxsw_pci_queue_elem_info_get(q, index);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/port.h b/drivers/net/ethernet/mellanox/mlxsw/port.h
index 726f5435b32f..ae65b9940aed 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/port.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/port.h
@@ -49,7 +49,7 @@
 #define MLXSW_PORT_MID			0xd000
 
 #define MLXSW_PORT_MAX_PHY_PORTS	0x40
-#define MLXSW_PORT_MAX_PORTS		MLXSW_PORT_MAX_PHY_PORTS
+#define MLXSW_PORT_MAX_PORTS		(MLXSW_PORT_MAX_PHY_PORTS + 1)
 
 #define MLXSW_PORT_DEVID_BITS_OFFSET	10
 #define MLXSW_PORT_PHY_BITS_OFFSET	4
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index bb77e2207804..ffe4c0305733 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -873,6 +873,62 @@ static inline void mlxsw_reg_spvm_pack(char *payload, u8 local_port,
 	}
 }
 
+/* SPAFT - Switch Port Acceptable Frame Types
+ * ------------------------------------------
+ * The Switch Port Acceptable Frame Types register configures the frame
+ * admittance of the port.
+ */
+#define MLXSW_REG_SPAFT_ID 0x2010
+#define MLXSW_REG_SPAFT_LEN 0x08
+
+static const struct mlxsw_reg_info mlxsw_reg_spaft = {
+	.id = MLXSW_REG_SPAFT_ID,
+	.len = MLXSW_REG_SPAFT_LEN,
+};
+
+/* reg_spaft_local_port
+ * Local port number.
+ * Access: Index
+ *
+ * Note: CPU port is not supported (all tag types are allowed).
+ */
+MLXSW_ITEM32(reg, spaft, local_port, 0x00, 16, 8);
+
+/* reg_spaft_sub_port
+ * Virtual port within the physical port.
+ * Should be set to 0 when virtual ports are not enabled on the port.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, spaft, sub_port, 0x00, 8, 8);
+
+/* reg_spaft_allow_untagged
+ * When set, untagged frames on the ingress are allowed (default).
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, spaft, allow_untagged, 0x04, 31, 1);
+
+/* reg_spaft_allow_prio_tagged
+ * When set, priority tagged frames on the ingress are allowed (default).
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, spaft, allow_prio_tagged, 0x04, 30, 1);
+
+/* reg_spaft_allow_tagged
+ * When set, tagged frames on the ingress are allowed (default).
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, spaft, allow_tagged, 0x04, 29, 1);
+
+static inline void mlxsw_reg_spaft_pack(char *payload, u8 local_port,
+					bool allow_untagged)
+{
+	MLXSW_REG_ZERO(spaft, payload);
+	mlxsw_reg_spaft_local_port_set(payload, local_port);
+	mlxsw_reg_spaft_allow_untagged_set(payload, allow_untagged);
+	mlxsw_reg_spaft_allow_prio_tagged_set(payload, true);
+	mlxsw_reg_spaft_allow_tagged_set(payload, true);
+}
+
 /* SFGC - Switch Flooding Group Configuration
  * ------------------------------------------
  * The following register controls the association of flooding tables and MIDs
@@ -3203,6 +3259,8 @@ static inline const char *mlxsw_reg_id_str(u16 reg_id)
 		return "SPVID";
 	case MLXSW_REG_SPVM_ID:
 		return "SPVM";
+	case MLXSW_REG_SPAFT_ID:
+		return "SPAFT";
 	case MLXSW_REG_SFGC_ID:
 		return "SFGC";
 	case MLXSW_REG_SFTR_ID:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 217856bdd400..a94daa8c346c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -2123,6 +2123,8 @@ static int mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (flush_fdb && mlxsw_sp_port_fdb_flush(mlxsw_sp_port))
 		netdev_err(mlxsw_sp_port->dev, "Failed to flush FDB\n");
 
+	mlxsw_sp_port_pvid_set(mlxsw_sp_port, 1);
+
 	mlxsw_sp_port->learning = 0;
 	mlxsw_sp_port->learning_sync = 0;
 	mlxsw_sp_port->uc_flood = 0;
@@ -2356,9 +2358,7 @@ static int mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (mlxsw_sp_port->bridged) {
 		mlxsw_sp_port_active_vlans_del(mlxsw_sp_port);
 		mlxsw_sp_port_bridge_leave(mlxsw_sp_port, false);
-
-		if (lag->ref_count == 1)
-			mlxsw_sp_master_bridge_dec(mlxsw_sp, NULL);
+		mlxsw_sp_master_bridge_dec(mlxsw_sp, NULL);
 	}
 
 	if (lag->ref_count == 1) {
@@ -2746,6 +2746,13 @@ static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport,
 		goto err_vport_flood_set;
 	}
 
+	err = mlxsw_sp_port_stp_state_set(mlxsw_sp_vport, vid,
+					  MLXSW_REG_SPMS_STATE_FORWARDING);
+	if (err) {
+		netdev_err(dev, "Failed to set STP state\n");
+		goto err_port_stp_state_set;
+	}
+
 	if (flush_fdb && mlxsw_sp_vport_fdb_flush(mlxsw_sp_vport))
 		netdev_err(dev, "Failed to flush FDB\n");
 
@@ -2763,6 +2770,7 @@ static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport,
 
 	return 0;
 
+err_port_stp_state_set:
 err_vport_flood_set:
 err_port_vid_learning_set:
 err_port_vid_to_fid_validate:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 7f42eb1c320e..3b89ed2f3c76 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -254,5 +254,6 @@ int mlxsw_sp_port_kill_vid(struct net_device *dev,
 int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 vfid,
 			     bool set, bool only_uc);
 void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port);
+int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index e492ca2cdecd..7b56098acc58 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -370,7 +370,8 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev,
 	return err;
 }
 
-static int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
+static int __mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port,
+				    u16 vid)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	char spvid_pl[MLXSW_REG_SPVID_LEN];
@@ -379,6 +380,53 @@ static int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spvid), spvid_pl);
 }
 
+static int mlxsw_sp_port_allow_untagged_set(struct mlxsw_sp_port *mlxsw_sp_port,
+					    bool allow)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char spaft_pl[MLXSW_REG_SPAFT_LEN];
+
+	mlxsw_reg_spaft_pack(spaft_pl, mlxsw_sp_port->local_port, allow);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spaft), spaft_pl);
+}
+
+int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
+{
+	struct net_device *dev = mlxsw_sp_port->dev;
+	int err;
+
+	if (!vid) {
+		err = mlxsw_sp_port_allow_untagged_set(mlxsw_sp_port, false);
+		if (err) {
+			netdev_err(dev, "Failed to disallow untagged traffic\n");
+			return err;
+		}
+	} else {
+		err = __mlxsw_sp_port_pvid_set(mlxsw_sp_port, vid);
+		if (err) {
+			netdev_err(dev, "Failed to set PVID\n");
+			return err;
+		}
+
+		/* Only allow if not already allowed. */
+		if (!mlxsw_sp_port->pvid) {
+			err = mlxsw_sp_port_allow_untagged_set(mlxsw_sp_port,
+							       true);
+			if (err) {
+				netdev_err(dev, "Failed to allow untagged traffic\n");
+				goto err_port_allow_untagged_set;
+			}
+		}
+	}
+
+	mlxsw_sp_port->pvid = vid;
+	return 0;
+
+err_port_allow_untagged_set:
+	__mlxsw_sp_port_pvid_set(mlxsw_sp_port, mlxsw_sp_port->pvid);
+	return err;
+}
+
 static int mlxsw_sp_fid_create(struct mlxsw_sp *mlxsw_sp, u16 fid)
 {
 	char sfmr_pl[MLXSW_REG_SFMR_LEN];
@@ -540,7 +588,12 @@ static int __mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 			netdev_err(dev, "Unable to add PVID %d\n", vid_begin);
 			goto err_port_pvid_set;
 		}
-		mlxsw_sp_port->pvid = vid_begin;
+	} else if (!flag_pvid && old_pvid >= vid_begin && old_pvid <= vid_end) {
+		err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, 0);
+		if (err) {
+			netdev_err(dev, "Unable to del PVID\n");
+			goto err_port_pvid_set;
+		}
 	}
 
 	/* Changing activity bits only if HW operation succeded */
@@ -892,20 +945,18 @@ static int __mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port,
 		return err;
 	}
 
+	if (init)
+		goto out;
+
 	pvid = mlxsw_sp_port->pvid;
-	if (pvid >= vid_begin && pvid <= vid_end && pvid != 1) {
-		/* Default VLAN is always 1 */
-		err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, 1);
+	if (pvid >= vid_begin && pvid <= vid_end) {
+		err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, 0);
 		if (err) {
 			netdev_err(dev, "Unable to del PVID %d\n", pvid);
 			return err;
 		}
-		mlxsw_sp_port->pvid = 1;
 	}
 
-	if (init)
-		goto out;
-
 	err = __mlxsw_sp_port_flood_set(mlxsw_sp_port, vid_begin, vid_end,
 					false, false);
 	if (err) {
diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index 00cfd95ca59d..3e67f451f2ab 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -474,9 +474,9 @@ static int moxart_mac_probe(struct platform_device *pdev)
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	ndev->base_addr = res->start;
 	priv->base = devm_ioremap_resource(p_dev, res);
-	ret = IS_ERR(priv->base);
-	if (ret) {
+	if (IS_ERR(priv->base)) {
 		dev_err(p_dev, "devm_ioremap_resource failed\n");
+		ret = PTR_ERR(priv->base);
 		goto init_fail;
 	}
 
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 689a4a5c8dcf..1ef03939d25f 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -811,7 +811,7 @@ qcaspi_netdev_setup(struct net_device *dev)
 	dev->netdev_ops = &qcaspi_netdev_ops;
 	qcaspi_set_ethtool_ops(dev);
 	dev->watchdog_timeo = QCASPI_TX_TIMEOUT;
-	dev->flags = IFF_MULTICAST;
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->tx_queue_len = 100;
 
 	qca = netdev_priv(dev);
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 17d5571d0432..dd2cf3738b73 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -4933,8 +4933,6 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp)
 		RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST);
 		break;
 	case RTL_GIGA_MAC_VER_40:
-		RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF);
-		break;
 	case RTL_GIGA_MAC_VER_41:
 	case RTL_GIGA_MAC_VER_42:
 	case RTL_GIGA_MAC_VER_43:
@@ -4943,8 +4941,6 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_46:
 	case RTL_GIGA_MAC_VER_47:
 	case RTL_GIGA_MAC_VER_48:
-		RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST | RX_EARLY_OFF);
-		break;
 	case RTL_GIGA_MAC_VER_49:
 	case RTL_GIGA_MAC_VER_50:
 	case RTL_GIGA_MAC_VER_51:
@@ -6137,28 +6133,28 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 		sw_cnt_1ms_ini = 16000000/rg_saw_cnt;
 		sw_cnt_1ms_ini &= 0x0fff;
 		data = r8168_mac_ocp_read(tp, 0xd412);
-		data &= 0x0fff;
+		data &= ~0x0fff;
 		data |= sw_cnt_1ms_ini;
 		r8168_mac_ocp_write(tp, 0xd412, data);
 	}
 
 	data = r8168_mac_ocp_read(tp, 0xe056);
-	data &= 0xf0;
-	data |= 0x07;
+	data &= ~0xf0;
+	data |= 0x70;
 	r8168_mac_ocp_write(tp, 0xe056, data);
 
 	data = r8168_mac_ocp_read(tp, 0xe052);
-	data &= 0x8008;
-	data |= 0x6000;
+	data &= ~0x6000;
+	data |= 0x8008;
 	r8168_mac_ocp_write(tp, 0xe052, data);
 
 	data = r8168_mac_ocp_read(tp, 0xe0d6);
-	data &= 0x01ff;
+	data &= ~0x01ff;
 	data |= 0x017f;
 	r8168_mac_ocp_write(tp, 0xe0d6, data);
 
 	data = r8168_mac_ocp_read(tp, 0xd420);
-	data &= 0x0fff;
+	data &= ~0x0fff;
 	data |= 0x047f;
 	r8168_mac_ocp_write(tp, 0xd420, data);
 
@@ -7730,10 +7726,13 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 	void __iomem *ioaddr = tp->mmio_addr;
+	struct pci_dev *pdev = tp->pci_dev;
 	struct rtl8169_counters *counters = tp->counters;
 	unsigned int start;
 
-	if (netif_running(dev))
+	pm_runtime_get_noresume(&pdev->dev);
+
+	if (netif_running(dev) && pm_runtime_active(&pdev->dev))
 		rtl8169_rx_missed(dev, ioaddr);
 
 	do {
@@ -7761,7 +7760,8 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	 * Fetch additonal counter values missing in stats collected by driver
 	 * from tally counters.
 	 */
-	rtl8169_update_counters(dev);
+	if (pm_runtime_active(&pdev->dev))
+		rtl8169_update_counters(dev);
 
 	/*
 	 * Subtract values fetched during initalization.
@@ -7774,6 +7774,8 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	stats->tx_aborted_errors = le16_to_cpu(counters->tx_aborted) -
 		le16_to_cpu(tp->tc_offset.tx_aborted);
 
+	pm_runtime_put_noidle(&pdev->dev);
+
 	return stats;
 }
 
@@ -7853,6 +7855,10 @@ static int rtl8169_runtime_suspend(struct device *device)
 
 	rtl8169_net_suspend(dev);
 
+	/* Update counters before going runtime suspend */
+	rtl8169_rx_missed(dev, tp->mmio_addr);
+	rtl8169_update_counters(dev);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index ac43ed914fcf..86449c357168 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1139,7 +1139,8 @@ static int ravb_set_ringparam(struct net_device *ndev,
 	if (netif_running(ndev)) {
 		netif_device_detach(ndev);
 		/* Stop PTP Clock driver */
-		ravb_ptp_stop(ndev);
+		if (priv->chip_id == RCAR_GEN2)
+			ravb_ptp_stop(ndev);
 		/* Wait for DMA stopping */
 		error = ravb_stop_dma(ndev);
 		if (error) {
@@ -1170,7 +1171,8 @@ static int ravb_set_ringparam(struct net_device *ndev,
 		ravb_emac_init(ndev);
 
 		/* Initialise PTP Clock driver */
-		ravb_ptp_init(ndev, priv->pdev);
+		if (priv->chip_id == RCAR_GEN2)
+			ravb_ptp_init(ndev, priv->pdev);
 
 		netif_device_attach(ndev);
 	}
@@ -1298,7 +1300,8 @@ static void ravb_tx_timeout_work(struct work_struct *work)
 	netif_tx_stop_all_queues(ndev);
 
 	/* Stop PTP Clock driver */
-	ravb_ptp_stop(ndev);
+	if (priv->chip_id == RCAR_GEN2)
+		ravb_ptp_stop(ndev);
 
 	/* Wait for DMA stopping */
 	ravb_stop_dma(ndev);
@@ -1311,7 +1314,8 @@ static void ravb_tx_timeout_work(struct work_struct *work)
 	ravb_emac_init(ndev);
 
 	/* Initialise PTP Clock driver */
-	ravb_ptp_init(ndev, priv->pdev);
+	if (priv->chip_id == RCAR_GEN2)
+		ravb_ptp_init(ndev, priv->pdev);
 
 	netif_tx_start_all_queues(ndev);
 }
@@ -1718,7 +1722,6 @@ static int ravb_set_gti(struct net_device *ndev)
 static int ravb_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
-	const struct of_device_id *match;
 	struct ravb_private *priv;
 	enum ravb_chip_id chip_id;
 	struct net_device *ndev;
@@ -1750,8 +1753,7 @@ static int ravb_probe(struct platform_device *pdev)
 	ndev->base_addr = res->start;
 	ndev->dma = -1;
 
-	match = of_match_device(of_match_ptr(ravb_match_table), &pdev->dev);
-	chip_id = (enum ravb_chip_id)match->data;
+	chip_id = (enum ravb_chip_id)of_device_get_match_data(&pdev->dev);
 
 	if (chip_id == RCAR_GEN3)
 		irq = platform_get_irq_byname(pdev, "ch22");
@@ -1814,10 +1816,6 @@ static int ravb_probe(struct platform_device *pdev)
 			   CCC_OPC_CONFIG | CCC_GAC | CCC_CSEL_HPB, CCC);
 	}
 
-	/* Set CSEL value */
-	ravb_write(ndev, (ravb_read(ndev, CCC) & ~CCC_CSEL) | CCC_CSEL_HPB,
-		   CCC);
-
 	/* Set GTI value */
 	error = ravb_set_gti(ndev);
 	if (error)
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index dfa9e59c9442..738449992876 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -3061,15 +3061,11 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
 	mdp->ether_link_active_low = pd->ether_link_active_low;
 
 	/* set cpu data */
-	if (id) {
+	if (id)
 		mdp->cd = (struct sh_eth_cpu_data *)id->driver_data;
-	} else	{
-		const struct of_device_id *match;
+	else
+		mdp->cd = (struct sh_eth_cpu_data *)of_device_get_match_data(&pdev->dev);
 
-		match = of_match_device(of_match_ptr(sh_eth_match_table),
-					&pdev->dev);
-		mdp->cd = (struct sh_eth_cpu_data *)match->data;
-	}
 	mdp->reg_offset = sh_eth_get_register_offset(mdp->cd->register_type);
 	if (!mdp->reg_offset) {
 		dev_err(&pdev->dev, "Unknown register type (%d)\n",
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index 0e2fc1a844ab..db7db8ac4ca3 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -2342,8 +2342,8 @@ static int smc_drv_probe(struct platform_device *pdev)
 	}
 
 	ndev->irq = platform_get_irq(pdev, 0);
-	if (ndev->irq <= 0) {
-		ret = -ENODEV;
+	if (ndev->irq < 0) {
+		ret = ndev->irq;
 		goto out_release_io;
 	}
 	/*
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index 0faf16336035..efb54f356a67 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -199,21 +199,12 @@ int stmmac_mdio_register(struct net_device *ndev)
 	struct stmmac_priv *priv = netdev_priv(ndev);
 	struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data;
 	int addr, found;
-	struct device_node *mdio_node = NULL;
-	struct device_node *child_node = NULL;
+	struct device_node *mdio_node = priv->plat->mdio_node;
 
 	if (!mdio_bus_data)
 		return 0;
 
 	if (IS_ENABLED(CONFIG_OF)) {
-		for_each_child_of_node(priv->device->of_node, child_node) {
-			if (of_device_is_compatible(child_node,
-						    "snps,dwmac-mdio")) {
-				mdio_node = child_node;
-				break;
-			}
-		}
-
 		if (mdio_node) {
 			netdev_dbg(ndev, "FOUND MDIO subnode\n");
 		} else {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 6a52fa18cbf2..4514ba73d961 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -110,6 +110,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 	struct device_node *np = pdev->dev.of_node;
 	struct plat_stmmacenet_data *plat;
 	struct stmmac_dma_cfg *dma_cfg;
+	struct device_node *child_node = NULL;
 
 	plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL);
 	if (!plat)
@@ -140,13 +141,19 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 		plat->phy_node = of_node_get(np);
 	}
 
+	for_each_child_of_node(np, child_node)
+		if (of_device_is_compatible(child_node,	"snps,dwmac-mdio")) {
+			plat->mdio_node = child_node;
+			break;
+		}
+
 	/* "snps,phy-addr" is not a standard property. Mark it as deprecated
 	 * and warn of its use. Remove this when phy node support is added.
 	 */
 	if (of_property_read_u32(np, "snps,phy-addr", &plat->phy_addr) == 0)
 		dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n");
 
-	if ((plat->phy_node && !of_phy_is_fixed_link(np)) || plat->phy_bus_name)
+	if ((plat->phy_node && !of_phy_is_fixed_link(np)) || !plat->mdio_node)
 		plat->mdio_bus_data = NULL;
 	else
 		plat->mdio_bus_data =
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index e23a642357e7..2437227712dc 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -51,7 +51,6 @@
 #endif
 
 #ifdef CONFIG_PPC_PMAC
-#include <asm/pci-bridge.h>
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/pmac_feature.h>
diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
index 70814b7386b3..af11ed1e0bcc 100644
--- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c
+++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
@@ -426,7 +426,7 @@
 #define DWC_MMC_RXOCTETCOUNT_GB          0x0784
 #define DWC_MMC_RXPACKETCOUNT_GB         0x0780
 
-static int debug = 3;
+static int debug = -1;
 module_param(debug, int, 0);
 MODULE_PARM_DESC(debug, "DWC_eth_qos debug level (0=none,...,16=all)");
 
@@ -650,6 +650,11 @@ struct net_local {
 	u32 mmc_tx_counters_mask;
 
 	struct dwceqos_flowcontrol flowcontrol;
+
+	/* Tracks the intermediate state of phy started but hardware
+	 * init not finished yet.
+	 */
+	bool phy_defer;
 };
 
 static void dwceqos_read_mmc_counters(struct net_local *lp, u32 rx_mask,
@@ -901,6 +906,9 @@ static void dwceqos_adjust_link(struct net_device *ndev)
 	struct phy_device *phydev = lp->phy_dev;
 	int status_change = 0;
 
+	if (lp->phy_defer)
+		return;
+
 	if (phydev->link) {
 		if ((lp->speed != phydev->speed) ||
 		    (lp->duplex != phydev->duplex)) {
@@ -1113,7 +1121,7 @@ static int dwceqos_descriptor_init(struct net_local *lp)
 	/* Allocate DMA descriptors */
 	size = DWCEQOS_RX_DCNT * sizeof(struct dwceqos_dma_desc);
 	lp->rx_descs = dma_alloc_coherent(lp->ndev->dev.parent, size,
-			&lp->rx_descs_addr, 0);
+			&lp->rx_descs_addr, GFP_KERNEL);
 	if (!lp->rx_descs)
 		goto err_out;
 	lp->rx_descs_tail_addr = lp->rx_descs_addr +
@@ -1121,7 +1129,7 @@ static int dwceqos_descriptor_init(struct net_local *lp)
 
 	size = DWCEQOS_TX_DCNT * sizeof(struct dwceqos_dma_desc);
 	lp->tx_descs = dma_alloc_coherent(lp->ndev->dev.parent, size,
-			&lp->tx_descs_addr, 0);
+			&lp->tx_descs_addr, GFP_KERNEL);
 	if (!lp->tx_descs)
 		goto err_out;
 	lp->tx_descs_tail_addr = lp->tx_descs_addr +
@@ -1635,6 +1643,12 @@ static void dwceqos_init_hw(struct net_local *lp)
 	regval = dwceqos_read(lp, REG_DWCEQOS_MAC_CFG);
 	dwceqos_write(lp, REG_DWCEQOS_MAC_CFG,
 		      regval | DWCEQOS_MAC_CFG_TE | DWCEQOS_MAC_CFG_RE);
+
+	lp->phy_defer = false;
+	mutex_lock(&lp->phy_dev->lock);
+	phy_read_status(lp->phy_dev);
+	dwceqos_adjust_link(lp->ndev);
+	mutex_unlock(&lp->phy_dev->lock);
 }
 
 static void dwceqos_tx_reclaim(unsigned long data)
@@ -1880,9 +1894,13 @@ static int dwceqos_open(struct net_device *ndev)
 	}
 	netdev_reset_queue(ndev);
 
-	napi_enable(&lp->napi);
+	/* The dwceqos reset state machine requires all phy clocks to complete,
+	 * hence the unusual init order with phy_start first.
+	 */
+	lp->phy_defer = true;
 	phy_start(lp->phy_dev);
 	dwceqos_init_hw(lp);
+	napi_enable(&lp->napi);
 
 	netif_start_queue(ndev);
 	tasklet_enable(&lp->tx_bdreclaim_tasklet);
@@ -1915,18 +1933,19 @@ static int dwceqos_stop(struct net_device *ndev)
 {
 	struct net_local *lp = netdev_priv(ndev);
 
-	phy_stop(lp->phy_dev);
-
 	tasklet_disable(&lp->tx_bdreclaim_tasklet);
-	netif_stop_queue(ndev);
 	napi_disable(&lp->napi);
 
-	dwceqos_drain_dma(lp);
+	/* Stop all tx before we drain the tx dma. */
+	netif_tx_lock_bh(lp->ndev);
+	netif_stop_queue(ndev);
+	netif_tx_unlock_bh(lp->ndev);
 
-	netif_tx_lock(lp->ndev);
+	dwceqos_drain_dma(lp);
 	dwceqos_reset_hw(lp);
+	phy_stop(lp->phy_dev);
+
 	dwceqos_descriptor_free(lp);
-	netif_tx_unlock(lp->ndev);
 
 	return 0;
 }
@@ -2178,12 +2197,10 @@ static int dwceqos_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		((trans.initial_descriptor + trans.nr_descriptors) %
 		 DWCEQOS_TX_DCNT));
 
-	dwceqos_tx_finalize(skb, lp, &trans);
-
-	netdev_sent_queue(ndev, skb->len);
-
 	spin_lock_bh(&lp->tx_lock);
 	lp->tx_free -= trans.nr_descriptors;
+	dwceqos_tx_finalize(skb, lp, &trans);
+	netdev_sent_queue(ndev, skb->len);
 	spin_unlock_bh(&lp->tx_lock);
 
 	ndev->trans_start = jiffies;
diff --git a/drivers/net/ethernet/ti/cpsw-phy-sel.c b/drivers/net/ethernet/ti/cpsw-phy-sel.c
index e9cc61e1ec74..c3e85acfdc70 100644
--- a/drivers/net/ethernet/ti/cpsw-phy-sel.c
+++ b/drivers/net/ethernet/ti/cpsw-phy-sel.c
@@ -63,8 +63,12 @@ static void cpsw_gmii_sel_am3352(struct cpsw_phy_sel_priv *priv,
 		mode = AM33XX_GMII_SEL_MODE_RGMII;
 		break;
 
-	case PHY_INTERFACE_MODE_MII:
 	default:
+		dev_warn(priv->dev,
+			 "Unsupported PHY mode: \"%s\". Defaulting to MII.\n",
+			phy_modes(phy_mode));
+		/* fallthrough */
+	case PHY_INTERFACE_MODE_MII:
 		mode = AM33XX_GMII_SEL_MODE_MII;
 		break;
 	};
@@ -106,8 +110,12 @@ static void cpsw_gmii_sel_dra7xx(struct cpsw_phy_sel_priv *priv,
 		mode = AM33XX_GMII_SEL_MODE_RGMII;
 		break;
 
-	case PHY_INTERFACE_MODE_MII:
 	default:
+		dev_warn(priv->dev,
+			 "Unsupported PHY mode: \"%s\". Defaulting to MII.\n",
+			phy_modes(phy_mode));
+		/* fallthrough */
+	case PHY_INTERFACE_MODE_MII:
 		mode = AM33XX_GMII_SEL_MODE_MII;
 		break;
 	};
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index c61d66d38634..029841f98c32 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -117,21 +117,17 @@ static void get_pkt_info(dma_addr_t *buff, u32 *buff_len, dma_addr_t *ndesc,
 	*ndesc = le32_to_cpu(desc->next_desc);
 }
 
-static void get_pad_info(u32 *pad0, u32 *pad1, u32 *pad2, struct knav_dma_desc *desc)
+static u32 get_sw_data(int index, struct knav_dma_desc *desc)
 {
-	*pad0 = le32_to_cpu(desc->pad[0]);
-	*pad1 = le32_to_cpu(desc->pad[1]);
-	*pad2 = le32_to_cpu(desc->pad[2]);
+	/* No Endian conversion needed as this data is untouched by hw */
+	return desc->sw_data[index];
 }
 
-static void get_pad_ptr(void **padptr, struct knav_dma_desc *desc)
-{
-	u64 pad64;
-
-	pad64 = le32_to_cpu(desc->pad[0]) +
-		((u64)le32_to_cpu(desc->pad[1]) << 32);
-	*padptr = (void *)(uintptr_t)pad64;
-}
+/* use these macros to get sw data */
+#define GET_SW_DATA0(desc) get_sw_data(0, desc)
+#define GET_SW_DATA1(desc) get_sw_data(1, desc)
+#define GET_SW_DATA2(desc) get_sw_data(2, desc)
+#define GET_SW_DATA3(desc) get_sw_data(3, desc)
 
 static void get_org_pkt_info(dma_addr_t *buff, u32 *buff_len,
 			     struct knav_dma_desc *desc)
@@ -163,13 +159,18 @@ static void set_desc_info(u32 desc_info, u32 pkt_info,
 	desc->packet_info = cpu_to_le32(pkt_info);
 }
 
-static void set_pad_info(u32 pad0, u32 pad1, u32 pad2, struct knav_dma_desc *desc)
+static void set_sw_data(int index, u32 data, struct knav_dma_desc *desc)
 {
-	desc->pad[0] = cpu_to_le32(pad0);
-	desc->pad[1] = cpu_to_le32(pad1);
-	desc->pad[2] = cpu_to_le32(pad1);
+	/* No Endian conversion needed as this data is untouched by hw */
+	desc->sw_data[index] = data;
 }
 
+/* use these macros to set sw data */
+#define SET_SW_DATA0(data, desc) set_sw_data(0, data, desc)
+#define SET_SW_DATA1(data, desc) set_sw_data(1, data, desc)
+#define SET_SW_DATA2(data, desc) set_sw_data(2, data, desc)
+#define SET_SW_DATA3(data, desc) set_sw_data(3, data, desc)
+
 static void set_org_pkt_info(dma_addr_t buff, u32 buff_len,
 			     struct knav_dma_desc *desc)
 {
@@ -581,7 +582,6 @@ static void netcp_free_rx_desc_chain(struct netcp_intf *netcp,
 	dma_addr_t dma_desc, dma_buf;
 	unsigned int buf_len, dma_sz = sizeof(*ndesc);
 	void *buf_ptr;
-	u32 pad[2];
 	u32 tmp;
 
 	get_words(&dma_desc, 1, &desc->next_desc);
@@ -593,14 +593,20 @@ static void netcp_free_rx_desc_chain(struct netcp_intf *netcp,
 			break;
 		}
 		get_pkt_info(&dma_buf, &tmp, &dma_desc, ndesc);
-		get_pad_ptr(&buf_ptr, ndesc);
+		/* warning!!!! We are retrieving the virtual ptr in the sw_data
+		 * field as a 32bit value. Will not work on 64bit machines
+		 */
+		buf_ptr = (void *)GET_SW_DATA0(ndesc);
+		buf_len = (int)GET_SW_DATA1(desc);
 		dma_unmap_page(netcp->dev, dma_buf, PAGE_SIZE, DMA_FROM_DEVICE);
 		__free_page(buf_ptr);
 		knav_pool_desc_put(netcp->rx_pool, desc);
 	}
-
-	get_pad_info(&pad[0], &pad[1], &buf_len, desc);
-	buf_ptr = (void *)(uintptr_t)(pad[0] + ((u64)pad[1] << 32));
+	/* warning!!!! We are retrieving the virtual ptr in the sw_data
+	 * field as a 32bit value. Will not work on 64bit machines
+	 */
+	buf_ptr = (void *)GET_SW_DATA0(desc);
+	buf_len = (int)GET_SW_DATA1(desc);
 
 	if (buf_ptr)
 		netcp_frag_free(buf_len <= PAGE_SIZE, buf_ptr);
@@ -639,7 +645,6 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp)
 	dma_addr_t dma_desc, dma_buff;
 	struct netcp_packet p_info;
 	struct sk_buff *skb;
-	u32 pad[2];
 	void *org_buf_ptr;
 
 	dma_desc = knav_queue_pop(netcp->rx_queue, &dma_sz);
@@ -653,8 +658,11 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp)
 	}
 
 	get_pkt_info(&dma_buff, &buf_len, &dma_desc, desc);
-	get_pad_info(&pad[0], &pad[1], &org_buf_len, desc);
-	org_buf_ptr = (void *)(uintptr_t)(pad[0] + ((u64)pad[1] << 32));
+	/* warning!!!! We are retrieving the virtual ptr in the sw_data
+	 * field as a 32bit value. Will not work on 64bit machines
+	 */
+	org_buf_ptr = (void *)GET_SW_DATA0(desc);
+	org_buf_len = (int)GET_SW_DATA1(desc);
 
 	if (unlikely(!org_buf_ptr)) {
 		dev_err(netcp->ndev_dev, "NULL bufptr in desc\n");
@@ -679,7 +687,6 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp)
 	/* Fill in the page fragment list */
 	while (dma_desc) {
 		struct page *page;
-		void *ptr;
 
 		ndesc = knav_pool_desc_unmap(netcp->rx_pool, dma_desc, dma_sz);
 		if (unlikely(!ndesc)) {
@@ -688,8 +695,10 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp)
 		}
 
 		get_pkt_info(&dma_buff, &buf_len, &dma_desc, ndesc);
-		get_pad_ptr(&ptr, ndesc);
-		page = ptr;
+		/* warning!!!! We are retrieving the virtual ptr in the sw_data
+		 * field as a 32bit value. Will not work on 64bit machines
+		 */
+		page = (struct page *)GET_SW_DATA0(desc);
 
 		if (likely(dma_buff && buf_len && page)) {
 			dma_unmap_page(netcp->dev, dma_buff, PAGE_SIZE,
@@ -777,7 +786,10 @@ static void netcp_free_rx_buf(struct netcp_intf *netcp, int fdq)
 		}
 
 		get_org_pkt_info(&dma, &buf_len, desc);
-		get_pad_ptr(&buf_ptr, desc);
+		/* warning!!!! We are retrieving the virtual ptr in the sw_data
+		 * field as a 32bit value. Will not work on 64bit machines
+		 */
+		buf_ptr = (void *)GET_SW_DATA0(desc);
 
 		if (unlikely(!dma)) {
 			dev_err(netcp->ndev_dev, "NULL orig_buff in desc\n");
@@ -829,7 +841,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
 	struct page *page;
 	dma_addr_t dma;
 	void *bufptr;
-	u32 pad[3];
+	u32 sw_data[2];
 
 	/* Allocate descriptor */
 	hwdesc = knav_pool_desc_get(netcp->rx_pool);
@@ -846,7 +858,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
 				SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 		bufptr = netdev_alloc_frag(primary_buf_len);
-		pad[2] = primary_buf_len;
+		sw_data[1] = primary_buf_len;
 
 		if (unlikely(!bufptr)) {
 			dev_warn_ratelimited(netcp->ndev_dev,
@@ -858,9 +870,10 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
 		if (unlikely(dma_mapping_error(netcp->dev, dma)))
 			goto fail;
 
-		pad[0] = lower_32_bits((uintptr_t)bufptr);
-		pad[1] = upper_32_bits((uintptr_t)bufptr);
-
+		/* warning!!!! We are saving the virtual ptr in the sw_data
+		 * field as a 32bit value. Will not work on 64bit machines
+		 */
+		sw_data[0] = (u32)bufptr;
 	} else {
 		/* Allocate a secondary receive queue entry */
 		page = alloc_page(GFP_ATOMIC | GFP_DMA | __GFP_COLD);
@@ -870,9 +883,11 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
 		}
 		buf_len = PAGE_SIZE;
 		dma = dma_map_page(netcp->dev, page, 0, buf_len, DMA_TO_DEVICE);
-		pad[0] = lower_32_bits(dma);
-		pad[1] = upper_32_bits(dma);
-		pad[2] = 0;
+		/* warning!!!! We are saving the virtual ptr in the sw_data
+		 * field as a 32bit value. Will not work on 64bit machines
+		 */
+		sw_data[0] = (u32)page;
+		sw_data[1] = 0;
 	}
 
 	desc_info =  KNAV_DMA_DESC_PS_INFO_IN_DESC;
@@ -882,7 +897,8 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq)
 	pkt_info |= (netcp->rx_queue_id & KNAV_DMA_DESC_RETQ_MASK) <<
 		    KNAV_DMA_DESC_RETQ_SHIFT;
 	set_org_pkt_info(dma, buf_len, hwdesc);
-	set_pad_info(pad[0], pad[1], pad[2], hwdesc);
+	SET_SW_DATA0(sw_data[0], hwdesc);
+	SET_SW_DATA1(sw_data[1], hwdesc);
 	set_desc_info(desc_info, pkt_info, hwdesc);
 
 	/* Push to FDQs */
@@ -971,7 +987,6 @@ static int netcp_process_tx_compl_packets(struct netcp_intf *netcp,
 					  unsigned int budget)
 {
 	struct knav_dma_desc *desc;
-	void *ptr;
 	struct sk_buff *skb;
 	unsigned int dma_sz;
 	dma_addr_t dma;
@@ -988,8 +1003,10 @@ static int netcp_process_tx_compl_packets(struct netcp_intf *netcp,
 			continue;
 		}
 
-		get_pad_ptr(&ptr, desc);
-		skb = ptr;
+		/* warning!!!! We are retrieving the virtual ptr in the sw_data
+		 * field as a 32bit value. Will not work on 64bit machines
+		 */
+		skb = (struct sk_buff *)GET_SW_DATA0(desc);
 		netcp_free_tx_desc_chain(netcp, desc, dma_sz);
 		if (!skb) {
 			dev_err(netcp->ndev_dev, "No skb in Tx desc\n");
@@ -1194,10 +1211,10 @@ static int netcp_tx_submit_skb(struct netcp_intf *netcp,
 	}
 
 	set_words(&tmp, 1, &desc->packet_info);
-	tmp = lower_32_bits((uintptr_t)&skb);
-	set_words(&tmp, 1, &desc->pad[0]);
-	tmp = upper_32_bits((uintptr_t)&skb);
-	set_words(&tmp, 1, &desc->pad[1]);
+	/* warning!!!! We are saving the virtual ptr in the sw_data
+	 * field as a 32bit value. Will not work on 64bit machines
+	 */
+	SET_SW_DATA0((u32)skb, desc);
 
 	if (tx_pipe->flags & SWITCH_TO_PORT_IN_TAGINFO) {
 		tmp = tx_pipe->switch_to_port;
diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c
index 3c54a2cae5df..67610270d171 100644
--- a/drivers/net/ethernet/toshiba/spider_net.c
+++ b/drivers/net/ethernet/toshiba/spider_net.c
@@ -48,7 +48,6 @@
 #include <linux/wait.h>
 #include <linux/workqueue.h>
 #include <linux/bitops.h>
-#include <asm/pci-bridge.h>
 #include <net/checksum.h>
 
 #include "spider_net.h"
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 0b14ac3b8d11..0bf7edd99573 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1039,6 +1039,34 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
 	return geneve_xmit_skb(skb, dev, info);
 }
 
+static int __geneve_change_mtu(struct net_device *dev, int new_mtu, bool strict)
+{
+	/* The max_mtu calculation does not take account of GENEVE
+	 * options, to avoid excluding potentially valid
+	 * configurations.
+	 */
+	int max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - sizeof(struct iphdr)
+		- dev->hard_header_len;
+
+	if (new_mtu < 68)
+		return -EINVAL;
+
+	if (new_mtu > max_mtu) {
+		if (strict)
+			return -EINVAL;
+
+		new_mtu = max_mtu;
+	}
+
+	dev->mtu = new_mtu;
+	return 0;
+}
+
+static int geneve_change_mtu(struct net_device *dev, int new_mtu)
+{
+	return __geneve_change_mtu(dev, new_mtu, true);
+}
+
 static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 {
 	struct ip_tunnel_info *info = skb_tunnel_info(skb);
@@ -1083,7 +1111,7 @@ static const struct net_device_ops geneve_netdev_ops = {
 	.ndo_stop		= geneve_stop,
 	.ndo_start_xmit		= geneve_xmit,
 	.ndo_get_stats64	= ip_tunnel_get_stats64,
-	.ndo_change_mtu		= eth_change_mtu,
+	.ndo_change_mtu		= geneve_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_fill_metadata_dst	= geneve_fill_metadata_dst,
@@ -1150,6 +1178,7 @@ static void geneve_setup(struct net_device *dev)
 	dev->hw_features |= NETIF_F_GSO_SOFTWARE;
 
 	netif_keep_dst(dev);
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
 	eth_hw_addr_random(dev);
 }
@@ -1441,12 +1470,23 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 		return dev;
 
 	err = geneve_configure(net, dev, &geneve_remote_unspec,
-			       0, 0, 0, htons(dst_port), true, 0);
-	if (err) {
-		free_netdev(dev);
-		return ERR_PTR(err);
-	}
+			       0, 0, 0, htons(dst_port), true,
+			       GENEVE_F_UDP_ZERO_CSUM6_RX);
+	if (err)
+		goto err;
+
+	/* openvswitch users expect packet sizes to be unrestricted,
+	 * so set the largest MTU we can.
+	 */
+	err = __geneve_change_mtu(dev, IP_MAX_MTU, false);
+	if (err)
+		goto err;
+
 	return dev;
+
+ err:
+	free_netdev(dev);
+	return ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(geneve_dev_create_fb);
 
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 1d3a66563bac..98e34fee45c7 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1089,6 +1089,9 @@ static int netvsc_probe(struct hv_device *dev,
 	net->ethtool_ops = &ethtool_ops;
 	SET_NETDEV_DEV(net, &dev->device);
 
+	/* We always need headroom for rndis header */
+	net->needed_headroom = RNDIS_AND_PPI_SIZE;
+
 	/* Notify the netvsc driver of the new device */
 	memset(&device_info, 0, sizeof(device_info));
 	device_info.ring_size = ring_size;
diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index bf241a3ec5e5..db507e3bcab9 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -250,10 +250,6 @@ static int bcm7xxx_config_init(struct phy_device *phydev)
 	phy_write(phydev, MII_BCM7XXX_AUX_MODE, MII_BCM7XX_64CLK_MDIO);
 	phy_read(phydev, MII_BCM7XXX_AUX_MODE);
 
-	/* Workaround only required for 100Mbits/sec capable PHYs */
-	if (phydev->supported & PHY_GBIT_FEATURES)
-		return 0;
-
 	/* set shadow mode 2 */
 	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST,
 			MII_BCM7XXX_SHD_MODE_2, MII_BCM7XXX_SHD_MODE_2);
@@ -270,7 +266,7 @@ static int bcm7xxx_config_init(struct phy_device *phydev)
 	phy_write(phydev, MII_BCM7XXX_100TX_FALSE_CAR, 0x7555);
 
 	/* reset shadow mode 2 */
-	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, MII_BCM7XXX_SHD_MODE_2, 0);
+	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0, MII_BCM7XXX_SHD_MODE_2);
 	if (ret < 0)
 		return ret;
 
@@ -307,11 +303,6 @@ static int bcm7xxx_suspend(struct phy_device *phydev)
 	return 0;
 }
 
-static int bcm7xxx_dummy_config_init(struct phy_device *phydev)
-{
-	return 0;
-}
-
 #define BCM7XXX_28NM_GPHY(_oui, _name)					\
 {									\
 	.phy_id		= (_oui),					\
@@ -337,7 +328,7 @@ static struct phy_driver bcm7xxx_driver[] = {
 	.phy_id         = PHY_ID_BCM7425,
 	.phy_id_mask    = 0xfffffff0,
 	.name           = "Broadcom BCM7425",
-	.features       = PHY_GBIT_FEATURES |
+	.features       = PHY_BASIC_FEATURES |
 			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
 	.flags          = PHY_IS_INTERNAL,
 	.config_init    = bcm7xxx_config_init,
@@ -349,7 +340,7 @@ static struct phy_driver bcm7xxx_driver[] = {
 	.phy_id         = PHY_ID_BCM7429,
 	.phy_id_mask    = 0xfffffff0,
 	.name           = "Broadcom BCM7429",
-	.features       = PHY_GBIT_FEATURES |
+	.features       = PHY_BASIC_FEATURES |
 			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
 	.flags          = PHY_IS_INTERNAL,
 	.config_init    = bcm7xxx_config_init,
@@ -361,7 +352,7 @@ static struct phy_driver bcm7xxx_driver[] = {
 	.phy_id         = PHY_ID_BCM7435,
 	.phy_id_mask    = 0xfffffff0,
 	.name           = "Broadcom BCM7435",
-	.features       = PHY_GBIT_FEATURES |
+	.features       = PHY_BASIC_FEATURES |
 			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
 	.flags          = PHY_IS_INTERNAL,
 	.config_init    = bcm7xxx_config_init,
@@ -369,30 +360,6 @@ static struct phy_driver bcm7xxx_driver[] = {
 	.read_status    = genphy_read_status,
 	.suspend        = bcm7xxx_suspend,
 	.resume         = bcm7xxx_config_init,
-}, {
-	.phy_id		= PHY_BCM_OUI_4,
-	.phy_id_mask	= 0xffff0000,
-	.name		= "Broadcom BCM7XXX 40nm",
-	.features	= PHY_GBIT_FEATURES |
-			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
-	.flags		= PHY_IS_INTERNAL,
-	.config_init	= bcm7xxx_config_init,
-	.config_aneg	= genphy_config_aneg,
-	.read_status	= genphy_read_status,
-	.suspend	= bcm7xxx_suspend,
-	.resume		= bcm7xxx_config_init,
-}, {
-	.phy_id		= PHY_BCM_OUI_5,
-	.phy_id_mask	= 0xffffff00,
-	.name		= "Broadcom BCM7XXX 65nm",
-	.features	= PHY_BASIC_FEATURES |
-			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
-	.flags		= PHY_IS_INTERNAL,
-	.config_init	= bcm7xxx_dummy_config_init,
-	.config_aneg	= genphy_config_aneg,
-	.read_status	= genphy_read_status,
-	.suspend	= bcm7xxx_suspend,
-	.resume		= bcm7xxx_config_init,
 } };
 
 static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = {
@@ -404,8 +371,6 @@ static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = {
 	{ PHY_ID_BCM7439, 0xfffffff0, },
 	{ PHY_ID_BCM7435, 0xfffffff0, },
 	{ PHY_ID_BCM7445, 0xfffffff0, },
-	{ PHY_BCM_OUI_4, 0xffff0000 },
-	{ PHY_BCM_OUI_5, 0xffffff00 },
 	{ }
 };
 
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index e3eb96443c97..ab1d0fcaf1d9 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -446,6 +446,12 @@ static int m88e1510_config_aneg(struct phy_device *phydev)
 	if (err < 0)
 		return err;
 
+	return 0;
+}
+
+static int marvell_config_init(struct phy_device *phydev)
+{
+	/* Set registers from marvell,reg-init DT property */
 	return marvell_of_reg_init(phydev);
 }
 
@@ -495,7 +501,7 @@ static int m88e1116r_config_init(struct phy_device *phydev)
 
 	mdelay(500);
 
-	return 0;
+	return marvell_config_init(phydev);
 }
 
 static int m88e3016_config_init(struct phy_device *phydev)
@@ -514,7 +520,7 @@ static int m88e3016_config_init(struct phy_device *phydev)
 	if (reg < 0)
 		return reg;
 
-	return 0;
+	return marvell_config_init(phydev);
 }
 
 static int m88e1111_config_init(struct phy_device *phydev)
@@ -1078,6 +1084,7 @@ static struct phy_driver marvell_drivers[] = {
 		.features = PHY_GBIT_FEATURES,
 		.probe = marvell_probe,
 		.flags = PHY_HAS_INTERRUPT,
+		.config_init = &marvell_config_init,
 		.config_aneg = &marvell_config_aneg,
 		.read_status = &genphy_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
@@ -1149,6 +1156,7 @@ static struct phy_driver marvell_drivers[] = {
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
+		.config_init = &marvell_config_init,
 		.config_aneg = &m88e1121_config_aneg,
 		.read_status = &marvell_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
@@ -1167,6 +1175,7 @@ static struct phy_driver marvell_drivers[] = {
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
+		.config_init = &marvell_config_init,
 		.config_aneg = &m88e1318_config_aneg,
 		.read_status = &marvell_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
@@ -1259,6 +1268,7 @@ static struct phy_driver marvell_drivers[] = {
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
+		.config_init = &marvell_config_init,
 		.config_aneg = &m88e1510_config_aneg,
 		.read_status = &marvell_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
@@ -1277,6 +1287,7 @@ static struct phy_driver marvell_drivers[] = {
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = marvell_probe,
+		.config_init = &marvell_config_init,
 		.config_aneg = &m88e1510_config_aneg,
 		.read_status = &marvell_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 03833dbfca67..dc85f7095e51 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -297,6 +297,17 @@ static int kszphy_config_init(struct phy_device *phydev)
 	if (priv->led_mode >= 0)
 		kszphy_setup_led(phydev, type->led_mode_reg, priv->led_mode);
 
+	if (phy_interrupt_is_valid(phydev)) {
+		int ctl = phy_read(phydev, MII_BMCR);
+
+		if (ctl < 0)
+			return ctl;
+
+		ret = phy_write(phydev, MII_BMCR, ctl & ~BMCR_ANENABLE);
+		if (ret < 0)
+			return ret;
+	}
+
 	return 0;
 }
 
@@ -635,6 +646,21 @@ static void kszphy_get_stats(struct phy_device *phydev,
 		data[i] = kszphy_get_stat(phydev, i);
 }
 
+static int kszphy_resume(struct phy_device *phydev)
+{
+	int value;
+
+	mutex_lock(&phydev->lock);
+
+	value = phy_read(phydev, MII_BMCR);
+	phy_write(phydev, MII_BMCR, value & ~BMCR_PDOWN);
+
+	kszphy_config_intr(phydev);
+	mutex_unlock(&phydev->lock);
+
+	return 0;
+}
+
 static int kszphy_probe(struct phy_device *phydev)
 {
 	const struct kszphy_type *type = phydev->drv->driver_data;
@@ -844,7 +870,7 @@ static struct phy_driver ksphy_driver[] = {
 	.get_strings	= kszphy_get_strings,
 	.get_stats	= kszphy_get_stats,
 	.suspend	= genphy_suspend,
-	.resume		= genphy_resume,
+	.resume		= kszphy_resume,
 }, {
 	.phy_id		= PHY_ID_KSZ8061,
 	.name		= "Micrel KSZ8061",
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index bad3f005faee..e551f3a89cfd 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1410,7 +1410,7 @@ int genphy_config_init(struct phy_device *phydev)
 
 	features = (SUPPORTED_TP | SUPPORTED_MII
 			| SUPPORTED_AUI | SUPPORTED_FIBRE |
-			SUPPORTED_BNC);
+			SUPPORTED_BNC | SUPPORTED_Pause | SUPPORTED_Asym_Pause);
 
 	/* Do we support autonegotiation? */
 	val = phy_read(phydev, MII_BMSR);
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index fc8ad001bc94..d61da9ece3ba 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -443,9 +443,14 @@ static ssize_t ppp_read(struct file *file, char __user *buf,
 			 * network traffic (demand mode).
 			 */
 			struct ppp *ppp = PF_TO_PPP(pf);
+
+			ppp_recv_lock(ppp);
 			if (ppp->n_channels == 0 &&
-			    (ppp->flags & SC_LOOP_TRAFFIC) == 0)
+			    (ppp->flags & SC_LOOP_TRAFFIC) == 0) {
+				ppp_recv_unlock(ppp);
 				break;
+			}
+			ppp_recv_unlock(ppp);
 		}
 		ret = -EAGAIN;
 		if (file->f_flags & O_NONBLOCK)
@@ -532,9 +537,12 @@ static unsigned int ppp_poll(struct file *file, poll_table *wait)
 	else if (pf->kind == INTERFACE) {
 		/* see comment in ppp_read */
 		struct ppp *ppp = PF_TO_PPP(pf);
+
+		ppp_recv_lock(ppp);
 		if (ppp->n_channels == 0 &&
 		    (ppp->flags & SC_LOOP_TRAFFIC) == 0)
 			mask |= POLLIN | POLLRDNORM;
+		ppp_recv_unlock(ppp);
 	}
 
 	return mask;
@@ -2808,6 +2816,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit,
 
 out2:
 	mutex_unlock(&pn->all_ppp_mutex);
+	rtnl_unlock();
 	free_netdev(dev);
 out1:
 	*retp = ret;
diff --git a/drivers/net/ppp/ppp_mppe.c b/drivers/net/ppp/ppp_mppe.c
index 05005c660d4d..f60f7660b451 100644
--- a/drivers/net/ppp/ppp_mppe.c
+++ b/drivers/net/ppp/ppp_mppe.c
@@ -42,6 +42,8 @@
  *                    deprecated in 2.6
  */
 
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -49,7 +51,6 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/string.h>
-#include <linux/crypto.h>
 #include <linux/mm.h>
 #include <linux/ppp_defs.h>
 #include <linux/ppp-comp.h>
@@ -94,8 +95,8 @@ static inline void sha_pad_init(struct sha_pad *shapad)
  * State for an MPPE (de)compressor.
  */
 struct ppp_mppe_state {
-	struct crypto_blkcipher *arc4;
-	struct crypto_hash *sha1;
+	struct crypto_skcipher *arc4;
+	struct crypto_ahash *sha1;
 	unsigned char *sha1_digest;
 	unsigned char master_key[MPPE_MAX_KEY_LEN];
 	unsigned char session_key[MPPE_MAX_KEY_LEN];
@@ -135,7 +136,7 @@ struct ppp_mppe_state {
  */
 static void get_new_key_from_sha(struct ppp_mppe_state * state)
 {
-	struct hash_desc desc;
+	AHASH_REQUEST_ON_STACK(req, state->sha1);
 	struct scatterlist sg[4];
 	unsigned int nbytes;
 
@@ -148,10 +149,12 @@ static void get_new_key_from_sha(struct ppp_mppe_state * state)
 	nbytes += setup_sg(&sg[3], sha_pad->sha_pad2,
 			   sizeof(sha_pad->sha_pad2));
 
-	desc.tfm = state->sha1;
-	desc.flags = 0;
+	ahash_request_set_tfm(req, state->sha1);
+	ahash_request_set_callback(req, 0, NULL, NULL);
+	ahash_request_set_crypt(req, sg, state->sha1_digest, nbytes);
 
-	crypto_hash_digest(&desc, sg, nbytes, state->sha1_digest);
+	crypto_ahash_digest(req);
+	ahash_request_zero(req);
 }
 
 /*
@@ -161,20 +164,23 @@ static void get_new_key_from_sha(struct ppp_mppe_state * state)
 static void mppe_rekey(struct ppp_mppe_state * state, int initial_key)
 {
 	struct scatterlist sg_in[1], sg_out[1];
-	struct blkcipher_desc desc = { .tfm = state->arc4 };
+	SKCIPHER_REQUEST_ON_STACK(req, state->arc4);
+
+	skcipher_request_set_tfm(req, state->arc4);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
 
 	get_new_key_from_sha(state);
 	if (!initial_key) {
-		crypto_blkcipher_setkey(state->arc4, state->sha1_digest,
-					state->keylen);
+		crypto_skcipher_setkey(state->arc4, state->sha1_digest,
+				       state->keylen);
 		sg_init_table(sg_in, 1);
 		sg_init_table(sg_out, 1);
 		setup_sg(sg_in, state->sha1_digest, state->keylen);
 		setup_sg(sg_out, state->session_key, state->keylen);
-		if (crypto_blkcipher_encrypt(&desc, sg_out, sg_in,
-					     state->keylen) != 0) {
+		skcipher_request_set_crypt(req, sg_in, sg_out, state->keylen,
+					   NULL);
+		if (crypto_skcipher_encrypt(req))
     		    printk(KERN_WARNING "mppe_rekey: cipher_encrypt failed\n");
-		}
 	} else {
 		memcpy(state->session_key, state->sha1_digest, state->keylen);
 	}
@@ -184,7 +190,8 @@ static void mppe_rekey(struct ppp_mppe_state * state, int initial_key)
 		state->session_key[1] = 0x26;
 		state->session_key[2] = 0x9e;
 	}
-	crypto_blkcipher_setkey(state->arc4, state->session_key, state->keylen);
+	crypto_skcipher_setkey(state->arc4, state->session_key, state->keylen);
+	skcipher_request_zero(req);
 }
 
 /*
@@ -204,19 +211,19 @@ static void *mppe_alloc(unsigned char *options, int optlen)
 		goto out;
 
 
-	state->arc4 = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
+	state->arc4 = crypto_alloc_skcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(state->arc4)) {
 		state->arc4 = NULL;
 		goto out_free;
 	}
 
-	state->sha1 = crypto_alloc_hash("sha1", 0, CRYPTO_ALG_ASYNC);
+	state->sha1 = crypto_alloc_ahash("sha1", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(state->sha1)) {
 		state->sha1 = NULL;
 		goto out_free;
 	}
 
-	digestsize = crypto_hash_digestsize(state->sha1);
+	digestsize = crypto_ahash_digestsize(state->sha1);
 	if (digestsize < MPPE_MAX_KEY_LEN)
 		goto out_free;
 
@@ -237,15 +244,12 @@ static void *mppe_alloc(unsigned char *options, int optlen)
 
 	return (void *)state;
 
-	out_free:
-	    if (state->sha1_digest)
-		kfree(state->sha1_digest);
-	    if (state->sha1)
-		crypto_free_hash(state->sha1);
-	    if (state->arc4)
-		crypto_free_blkcipher(state->arc4);
-	    kfree(state);
-	out:
+out_free:
+	kfree(state->sha1_digest);
+	crypto_free_ahash(state->sha1);
+	crypto_free_skcipher(state->arc4);
+	kfree(state);
+out:
 	return NULL;
 }
 
@@ -256,13 +260,10 @@ static void mppe_free(void *arg)
 {
 	struct ppp_mppe_state *state = (struct ppp_mppe_state *) arg;
 	if (state) {
-	    if (state->sha1_digest)
 		kfree(state->sha1_digest);
-	    if (state->sha1)
-		crypto_free_hash(state->sha1);
-	    if (state->arc4)
-		crypto_free_blkcipher(state->arc4);
-	    kfree(state);
+		crypto_free_ahash(state->sha1);
+		crypto_free_skcipher(state->arc4);
+		kfree(state);
 	}
 }
 
@@ -368,8 +369,9 @@ mppe_compress(void *arg, unsigned char *ibuf, unsigned char *obuf,
 	      int isize, int osize)
 {
 	struct ppp_mppe_state *state = (struct ppp_mppe_state *) arg;
-	struct blkcipher_desc desc = { .tfm = state->arc4 };
+	SKCIPHER_REQUEST_ON_STACK(req, state->arc4);
 	int proto;
+	int err;
 	struct scatterlist sg_in[1], sg_out[1];
 
 	/*
@@ -426,7 +428,13 @@ mppe_compress(void *arg, unsigned char *ibuf, unsigned char *obuf,
 	sg_init_table(sg_out, 1);
 	setup_sg(sg_in, ibuf, isize);
 	setup_sg(sg_out, obuf, osize);
-	if (crypto_blkcipher_encrypt(&desc, sg_out, sg_in, isize) != 0) {
+
+	skcipher_request_set_tfm(req, state->arc4);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, sg_in, sg_out, isize, NULL);
+	err = crypto_skcipher_encrypt(req);
+	skcipher_request_zero(req);
+	if (err) {
 		printk(KERN_DEBUG "crypto_cypher_encrypt failed\n");
 		return -1;
 	}
@@ -475,7 +483,7 @@ mppe_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf,
 		int osize)
 {
 	struct ppp_mppe_state *state = (struct ppp_mppe_state *) arg;
-	struct blkcipher_desc desc = { .tfm = state->arc4 };
+	SKCIPHER_REQUEST_ON_STACK(req, state->arc4);
 	unsigned ccount;
 	int flushed = MPPE_BITS(ibuf) & MPPE_BIT_FLUSHED;
 	struct scatterlist sg_in[1], sg_out[1];
@@ -609,9 +617,14 @@ mppe_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf,
 	sg_init_table(sg_out, 1);
 	setup_sg(sg_in, ibuf, 1);
 	setup_sg(sg_out, obuf, 1);
-	if (crypto_blkcipher_decrypt(&desc, sg_out, sg_in, 1) != 0) {
+
+	skcipher_request_set_tfm(req, state->arc4);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, sg_in, sg_out, 1, NULL);
+	if (crypto_skcipher_decrypt(req)) {
 		printk(KERN_DEBUG "crypto_cypher_decrypt failed\n");
-		return DECOMP_ERROR;
+		osize = DECOMP_ERROR;
+		goto out_zap_req;
 	}
 
 	/*
@@ -629,9 +642,11 @@ mppe_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf,
 	/* And finally, decrypt the rest of the packet. */
 	setup_sg(sg_in, ibuf + 1, isize - 1);
 	setup_sg(sg_out, obuf + 1, osize - 1);
-	if (crypto_blkcipher_decrypt(&desc, sg_out, sg_in, isize - 1)) {
+	skcipher_request_set_crypt(req, sg_in, sg_out, isize - 1, NULL);
+	if (crypto_skcipher_decrypt(req)) {
 		printk(KERN_DEBUG "crypto_cypher_decrypt failed\n");
-		return DECOMP_ERROR;
+		osize = DECOMP_ERROR;
+		goto out_zap_req;
 	}
 
 	state->stats.unc_bytes += osize;
@@ -642,6 +657,8 @@ mppe_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf,
 	/* good packet credit */
 	state->sanity_errors >>= 1;
 
+out_zap_req:
+	skcipher_request_zero(req);
 	return osize;
 
 sanity_error:
@@ -714,8 +731,8 @@ static struct compressor ppp_mppe = {
 static int __init ppp_mppe_init(void)
 {
 	int answer;
-	if (!(crypto_has_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC) &&
-	      crypto_has_hash("sha1", 0, CRYPTO_ALG_ASYNC)))
+	if (!(crypto_has_skcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC) &&
+	      crypto_has_ahash("sha1", 0, CRYPTO_ALG_ASYNC)))
 		return -ENODEV;
 
 	sha_pad = kmalloc(sizeof(struct sha_pad), GFP_KERNEL);
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index f3c63022eb3c..4ddae8118c85 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -395,6 +395,8 @@ static int pppoe_rcv_core(struct sock *sk, struct sk_buff *skb)
 
 		if (!__pppoe_xmit(sk_pppox(relay_po), skb))
 			goto abort_put;
+
+		sock_put(sk_pppox(relay_po));
 	} else {
 		if (sock_queue_rcv_skb(sk, skb))
 			goto abort_kfree;
diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index 7f83504dfa69..cdde59089f72 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -395,6 +395,10 @@ config USB_NET_RNDIS_HOST
 	  The protocol specification is incomplete, and is controlled by
 	  (and for) Microsoft; it isn't an "Open" ecosystem or market.
 
+config USB_NET_CDC_SUBSET_ENABLE
+	tristate
+	depends on USB_NET_CDC_SUBSET
+
 config USB_NET_CDC_SUBSET
 	tristate "Simple USB Network Links (CDC Ethernet subset)"
 	depends on USB_USBNET
@@ -413,6 +417,7 @@ config USB_NET_CDC_SUBSET
 config USB_ALI_M5632
 	bool "ALi M5632 based 'USB 2.0 Data Link' cables"
 	depends on USB_NET_CDC_SUBSET
+	select USB_NET_CDC_SUBSET_ENABLE
 	help
 	  Choose this option if you're using a host-to-host cable
 	  based on this design, which supports USB 2.0 high speed.
@@ -420,6 +425,7 @@ config USB_ALI_M5632
 config USB_AN2720
 	bool "AnchorChips 2720 based cables (Xircom PGUNET, ...)"
 	depends on USB_NET_CDC_SUBSET
+	select USB_NET_CDC_SUBSET_ENABLE
 	help
 	  Choose this option if you're using a host-to-host cable
 	  based on this design.  Note that AnchorChips is now a
@@ -428,6 +434,7 @@ config USB_AN2720
 config USB_BELKIN
 	bool "eTEK based host-to-host cables (Advance, Belkin, ...)"
 	depends on USB_NET_CDC_SUBSET
+	select USB_NET_CDC_SUBSET_ENABLE
 	default y
 	help
 	  Choose this option if you're using a host-to-host cable
@@ -437,6 +444,7 @@ config USB_BELKIN
 config USB_ARMLINUX
 	bool "Embedded ARM Linux links (iPaq, ...)"
 	depends on USB_NET_CDC_SUBSET
+	select USB_NET_CDC_SUBSET_ENABLE
 	default y
 	help
 	  Choose this option to support the "usb-eth" networking driver
@@ -454,6 +462,7 @@ config USB_ARMLINUX
 config USB_EPSON2888
 	bool "Epson 2888 based firmware (DEVELOPMENT)"
 	depends on USB_NET_CDC_SUBSET
+	select USB_NET_CDC_SUBSET_ENABLE
 	help
 	  Choose this option to support the usb networking links used
 	  by some sample firmware from Epson.
@@ -461,6 +470,7 @@ config USB_EPSON2888
 config USB_KC2190
 	bool "KT Technology KC2190 based cables (InstaNet)"
 	depends on USB_NET_CDC_SUBSET
+	select USB_NET_CDC_SUBSET_ENABLE
 	help
 	  Choose this option if you're using a host-to-host cable
 	  with one of these chips.
diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile
index b5f04068dbe4..37fb46aee341 100644
--- a/drivers/net/usb/Makefile
+++ b/drivers/net/usb/Makefile
@@ -23,7 +23,7 @@ obj-$(CONFIG_USB_NET_GL620A)	+= gl620a.o
 obj-$(CONFIG_USB_NET_NET1080)	+= net1080.o
 obj-$(CONFIG_USB_NET_PLUSB)	+= plusb.o
 obj-$(CONFIG_USB_NET_RNDIS_HOST)	+= rndis_host.o
-obj-$(CONFIG_USB_NET_CDC_SUBSET)	+= cdc_subset.o
+obj-$(CONFIG_USB_NET_CDC_SUBSET_ENABLE)	+= cdc_subset.o
 obj-$(CONFIG_USB_NET_ZAURUS)	+= zaurus.o
 obj-$(CONFIG_USB_NET_MCS7830)	+= mcs7830.o
 obj-$(CONFIG_USB_USBNET)	+= usbnet.o
diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c
index 224e7d82de6d..cf77f2dffa69 100644
--- a/drivers/net/usb/ax88172a.c
+++ b/drivers/net/usb/ax88172a.c
@@ -134,7 +134,6 @@ static void ax88172a_remove_mdio(struct usbnet *dev)
 
 	netdev_info(dev->net, "deregistering mdio bus %s\n", priv->mdio->id);
 	mdiobus_unregister(priv->mdio);
-	kfree(priv->mdio->irq);
 	mdiobus_free(priv->mdio);
 }
 
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index dc0212c3cc28..86ba30ba35e8 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -837,7 +837,11 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 
 	iface_no = ctx->data->cur_altsetting->desc.bInterfaceNumber;
 
-	/* reset data interface */
+	/* Reset data interface. Some devices will not reset properly
+	 * unless they are configured first.  Toggle the altsetting to
+	 * force a reset
+	 */
+	usb_set_interface(dev->udev, iface_no, data_altsetting);
 	temp = usb_set_interface(dev->udev, iface_no, 0);
 	if (temp) {
 		dev_dbg(&intf->dev, "set interface failed\n");
@@ -984,8 +988,6 @@ EXPORT_SYMBOL_GPL(cdc_ncm_select_altsetting);
 
 static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf)
 {
-	int ret;
-
 	/* MBIM backwards compatible function? */
 	if (cdc_ncm_select_altsetting(intf) != CDC_NCM_COMM_ALTSETTING_NCM)
 		return -ENODEV;
@@ -994,16 +996,7 @@ static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf)
 	 * Additionally, generic NCM devices are assumed to accept arbitrarily
 	 * placed NDP.
 	 */
-	ret = cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0);
-
-	/*
-	 * We should get an event when network connection is "connected" or
-	 * "disconnected". Set network connection in "disconnected" state
-	 * (carrier is OFF) during attach, so the IP network stack does not
-	 * start IPv6 negotiation and more.
-	 */
-	usbnet_link_change(dev, 0, 0);
-	return ret;
+	return cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0);
 }
 
 static void cdc_ncm_align_tail(struct sk_buff *skb, size_t modulus, size_t remainder, size_t max)
@@ -1586,7 +1579,8 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb)
 
 static const struct driver_info cdc_ncm_info = {
 	.description = "CDC NCM",
-	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET,
+	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
+			| FLAG_LINK_INTR,
 	.bind = cdc_ncm_bind,
 	.unbind = cdc_ncm_unbind,
 	.manage_power = usbnet_manage_power,
@@ -1599,7 +1593,7 @@ static const struct driver_info cdc_ncm_info = {
 static const struct driver_info wwan_info = {
 	.description = "Mobile Broadband Network Device",
 	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
-			| FLAG_WWAN,
+			| FLAG_LINK_INTR | FLAG_WWAN,
 	.bind = cdc_ncm_bind,
 	.unbind = cdc_ncm_unbind,
 	.manage_power = usbnet_manage_power,
@@ -1612,7 +1606,7 @@ static const struct driver_info wwan_info = {
 static const struct driver_info wwan_noarp_info = {
 	.description = "Mobile Broadband Network Device (NO ARP)",
 	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
-			| FLAG_WWAN | FLAG_NOARP,
+			| FLAG_LINK_INTR | FLAG_WWAN | FLAG_NOARP,
 	.bind = cdc_ncm_bind,
 	.unbind = cdc_ncm_unbind,
 	.manage_power = usbnet_manage_power,
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 23e9880791fc..a3a4ccf7cf52 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -637,6 +637,7 @@ static const struct usb_device_id products[] = {
 
 	/* 3. Combined interface devices matching on interface number */
 	{QMI_FIXED_INTF(0x0408, 0xea42, 4)},	/* Yota / Megafon M100-1 */
+	{QMI_FIXED_INTF(0x05c6, 0x6001, 3)},	/* 4G LTE usb-modem U901 */
 	{QMI_FIXED_INTF(0x05c6, 0x7000, 0)},
 	{QMI_FIXED_INTF(0x05c6, 0x7001, 1)},
 	{QMI_FIXED_INTF(0x05c6, 0x7002, 1)},
@@ -860,8 +861,10 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9056, 8)},	/* Sierra Wireless Modem */
 	{QMI_FIXED_INTF(0x1199, 0x9057, 8)},
 	{QMI_FIXED_INTF(0x1199, 0x9061, 8)},	/* Sierra Wireless Modem */
-	{QMI_FIXED_INTF(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx/EM74xx */
-	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx/EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9071, 8)},	/* Sierra Wireless MC74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9071, 10)},	/* Sierra Wireless MC74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9079, 8)},	/* Sierra Wireless EM74xx */
+	{QMI_FIXED_INTF(0x1199, 0x9079, 10)},	/* Sierra Wireless EM74xx */
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
@@ -884,6 +887,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81a8, 8)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81a9, 8)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81b1, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */
+	{QMI_FIXED_INTF(0x413c, 0x81b3, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
 	{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)},	/* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
 	{QMI_FIXED_INTF(0x22de, 0x9061, 3)},	/* WeTelecom WPD-600N */
 	{QMI_FIXED_INTF(0x1e0e, 0x9001, 5)},	/* SIMCom 7230E */
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 0b0ba7ef14e4..10798128c03f 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1769,6 +1769,13 @@ out3:
 	if (info->unbind)
 		info->unbind (dev, udev);
 out1:
+	/* subdrivers must undo all they did in bind() if they
+	 * fail it, but we may fail later and a deferred kevent
+	 * may trigger an error resubmitting itself and, worse,
+	 * schedule a timer. So we kill it all just in case.
+	 */
+	cancel_work_sync(&dev->kevent);
+	del_timer_sync(&dev->delay);
 	free_netdev(net);
 out:
 	return status;
diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h b/drivers/net/vmxnet3/vmxnet3_defs.h
index 221a53025fd0..72ba8ae7f09a 100644
--- a/drivers/net/vmxnet3/vmxnet3_defs.h
+++ b/drivers/net/vmxnet3/vmxnet3_defs.h
@@ -377,7 +377,7 @@ union Vmxnet3_GenericDesc {
 #define VMXNET3_TX_RING_MAX_SIZE   4096
 #define VMXNET3_TC_RING_MAX_SIZE   4096
 #define VMXNET3_RX_RING_MAX_SIZE   4096
-#define VMXNET3_RX_RING2_MAX_SIZE  2048
+#define VMXNET3_RX_RING2_MAX_SIZE  4096
 #define VMXNET3_RC_RING_MAX_SIZE   8192
 
 /* a list of reasons for queue stop */
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 0cbf520cea77..fc895d0e85d9 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -814,7 +814,7 @@ vmxnet3_tq_init_all(struct vmxnet3_adapter *adapter)
 
 
 /*
- *    parse and copy relevant protocol headers:
+ *    parse relevant protocol headers:
  *      For a tso pkt, relevant headers are L2/3/4 including options
  *      For a pkt requesting csum offloading, they are L2/3 and may include L4
  *      if it's a TCP/UDP pkt
@@ -827,15 +827,14 @@ vmxnet3_tq_init_all(struct vmxnet3_adapter *adapter)
  * Other effects:
  *    1. related *ctx fields are updated.
  *    2. ctx->copy_size is # of bytes copied
- *    3. the portion copied is guaranteed to be in the linear part
+ *    3. the portion to be copied is guaranteed to be in the linear part
  *
  */
 static int
-vmxnet3_parse_and_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
-			   struct vmxnet3_tx_ctx *ctx,
-			   struct vmxnet3_adapter *adapter)
+vmxnet3_parse_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
+		  struct vmxnet3_tx_ctx *ctx,
+		  struct vmxnet3_adapter *adapter)
 {
-	struct Vmxnet3_TxDataDesc *tdd;
 	u8 protocol = 0;
 
 	if (ctx->mss) {	/* TSO */
@@ -892,16 +891,34 @@ vmxnet3_parse_and_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 		return 0;
 	}
 
+	return 1;
+err:
+	return -1;
+}
+
+/*
+ *    copy relevant protocol headers to the transmit ring:
+ *      For a tso pkt, relevant headers are L2/3/4 including options
+ *      For a pkt requesting csum offloading, they are L2/3 and may include L4
+ *      if it's a TCP/UDP pkt
+ *
+ *
+ *    Note that this requires that vmxnet3_parse_hdr be called first to set the
+ *      appropriate bits in ctx first
+ */
+static void
+vmxnet3_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
+		 struct vmxnet3_tx_ctx *ctx,
+		 struct vmxnet3_adapter *adapter)
+{
+	struct Vmxnet3_TxDataDesc *tdd;
+
 	tdd = tq->data_ring.base + tq->tx_ring.next2fill;
 
 	memcpy(tdd->data, skb->data, ctx->copy_size);
 	netdev_dbg(adapter->netdev,
 		"copy %u bytes to dataRing[%u]\n",
 		ctx->copy_size, tq->tx_ring.next2fill);
-	return 1;
-
-err:
-	return -1;
 }
 
 
@@ -998,22 +1015,7 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 		}
 	}
 
-	spin_lock_irqsave(&tq->tx_lock, flags);
-
-	if (count > vmxnet3_cmd_ring_desc_avail(&tq->tx_ring)) {
-		tq->stats.tx_ring_full++;
-		netdev_dbg(adapter->netdev,
-			"tx queue stopped on %s, next2comp %u"
-			" next2fill %u\n", adapter->netdev->name,
-			tq->tx_ring.next2comp, tq->tx_ring.next2fill);
-
-		vmxnet3_tq_stop(tq, adapter);
-		spin_unlock_irqrestore(&tq->tx_lock, flags);
-		return NETDEV_TX_BUSY;
-	}
-
-
-	ret = vmxnet3_parse_and_copy_hdr(skb, tq, &ctx, adapter);
+	ret = vmxnet3_parse_hdr(skb, tq, &ctx, adapter);
 	if (ret >= 0) {
 		BUG_ON(ret <= 0 && ctx.copy_size != 0);
 		/* hdrs parsed, check against other limits */
@@ -1033,9 +1035,26 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 		}
 	} else {
 		tq->stats.drop_hdr_inspect_err++;
-		goto unlock_drop_pkt;
+		goto drop_pkt;
 	}
 
+	spin_lock_irqsave(&tq->tx_lock, flags);
+
+	if (count > vmxnet3_cmd_ring_desc_avail(&tq->tx_ring)) {
+		tq->stats.tx_ring_full++;
+		netdev_dbg(adapter->netdev,
+			"tx queue stopped on %s, next2comp %u"
+			" next2fill %u\n", adapter->netdev->name,
+			tq->tx_ring.next2comp, tq->tx_ring.next2fill);
+
+		vmxnet3_tq_stop(tq, adapter);
+		spin_unlock_irqrestore(&tq->tx_lock, flags);
+		return NETDEV_TX_BUSY;
+	}
+
+
+	vmxnet3_copy_hdr(skb, tq, &ctx, adapter);
+
 	/* fill tx descs related to addr & len */
 	if (vmxnet3_map_pkt(skb, &ctx, tq, adapter->pdev, adapter))
 		goto unlock_drop_pkt;
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index bdb8a6c0f8aa..729c344e6774 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -69,10 +69,10 @@
 /*
  * Version numbers
  */
-#define VMXNET3_DRIVER_VERSION_STRING   "1.4.5.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING   "1.4.6.0-k"
 
 /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */
-#define VMXNET3_DRIVER_VERSION_NUM      0x01040500
+#define VMXNET3_DRIVER_VERSION_NUM      0x01040600
 
 #if defined(CONFIG_PCI_MSI)
 	/* RSS only makes sense if MSI-X is supported. */
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 66addb7a7911..bdcf617a9d52 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -104,20 +104,23 @@ static struct dst_ops vrf_dst_ops = {
 #if IS_ENABLED(CONFIG_IPV6)
 static bool check_ipv6_frame(const struct sk_buff *skb)
 {
-	const struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb->data;
-	size_t hlen = sizeof(*ipv6h);
+	const struct ipv6hdr *ipv6h;
+	struct ipv6hdr _ipv6h;
 	bool rc = true;
 
-	if (skb->len < hlen)
+	ipv6h = skb_header_pointer(skb, 0, sizeof(_ipv6h), &_ipv6h);
+	if (!ipv6h)
 		goto out;
 
 	if (ipv6h->nexthdr == NEXTHDR_ICMP) {
 		const struct icmp6hdr *icmph;
+		struct icmp6hdr _icmph;
 
-		if (skb->len < hlen + sizeof(*icmph))
+		icmph = skb_header_pointer(skb, sizeof(_ipv6h),
+					   sizeof(_icmph), &_icmph);
+		if (!icmph)
 			goto out;
 
-		icmph = (struct icmp6hdr *)(skb->data + sizeof(*ipv6h));
 		switch (icmph->icmp6_type) {
 		case NDISC_ROUTER_SOLICITATION:
 		case NDISC_ROUTER_ADVERTISEMENT:
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 65439188c582..1c32bd104797 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -931,8 +931,10 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 						     cb->nlh->nlmsg_seq,
 						     RTM_NEWNEIGH,
 						     NLM_F_MULTI, rd);
-				if (err < 0)
+				if (err < 0) {
+					cb->args[1] = err;
 					goto out;
+				}
 skip:
 				++idx;
 			}
@@ -1306,8 +1308,10 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 		gbp = (struct vxlanhdr_gbp *)vxh;
 		md->gbp = ntohs(gbp->policy_id);
 
-		if (tun_dst)
+		if (tun_dst) {
 			tun_dst->u.tun_info.key.tun_flags |= TUNNEL_VXLAN_OPT;
+			tun_dst->u.tun_info.options_len = sizeof(*md);
+		}
 
 		if (gbp->dont_learn)
 			md->gbp |= VXLAN_GBP_DONT_LEARN;
@@ -2171,9 +2175,11 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 #endif
 	}
 
-	if (vxlan->flags & VXLAN_F_COLLECT_METADATA &&
-	    info && info->mode & IP_TUNNEL_INFO_TX) {
-		vxlan_xmit_one(skb, dev, NULL, false);
+	if (vxlan->flags & VXLAN_F_COLLECT_METADATA) {
+		if (info && info->mode & IP_TUNNEL_INFO_TX)
+			vxlan_xmit_one(skb, dev, NULL, false);
+		else
+			kfree_skb(skb);
 		return NETDEV_TX_OK;
 	}
 
@@ -2367,29 +2373,43 @@ static void vxlan_set_multicast_list(struct net_device *dev)
 {
 }
 
-static int vxlan_change_mtu(struct net_device *dev, int new_mtu)
+static int __vxlan_change_mtu(struct net_device *dev,
+			      struct net_device *lowerdev,
+			      struct vxlan_rdst *dst, int new_mtu, bool strict)
 {
-	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct vxlan_rdst *dst = &vxlan->default_dst;
-	struct net_device *lowerdev;
-	int max_mtu;
+	int max_mtu = IP_MAX_MTU;
 
-	lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex);
-	if (lowerdev == NULL)
-		return eth_change_mtu(dev, new_mtu);
+	if (lowerdev)
+		max_mtu = lowerdev->mtu;
 
 	if (dst->remote_ip.sa.sa_family == AF_INET6)
-		max_mtu = lowerdev->mtu - VXLAN6_HEADROOM;
+		max_mtu -= VXLAN6_HEADROOM;
 	else
-		max_mtu = lowerdev->mtu - VXLAN_HEADROOM;
+		max_mtu -= VXLAN_HEADROOM;
 
-	if (new_mtu < 68 || new_mtu > max_mtu)
+	if (new_mtu < 68)
 		return -EINVAL;
 
+	if (new_mtu > max_mtu) {
+		if (strict)
+			return -EINVAL;
+
+		new_mtu = max_mtu;
+	}
+
 	dev->mtu = new_mtu;
 	return 0;
 }
 
+static int vxlan_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_rdst *dst = &vxlan->default_dst;
+	struct net_device *lowerdev = __dev_get_by_index(vxlan->net,
+							 dst->remote_ifindex);
+	return __vxlan_change_mtu(dev, lowerdev, dst, new_mtu, true);
+}
+
 static int egress_ipv4_tun_info(struct net_device *dev, struct sk_buff *skb,
 				struct ip_tunnel_info *info,
 				__be16 sport, __be16 dport)
@@ -2523,6 +2543,7 @@ static void vxlan_setup(struct net_device *dev)
 	dev->hw_features |= NETIF_F_GSO_SOFTWARE;
 	dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
 	netif_keep_dst(dev);
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
 
 	INIT_LIST_HEAD(&vxlan->next);
@@ -2765,6 +2786,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 	int err;
 	bool use_ipv6 = false;
 	__be16 default_port = vxlan->cfg.dst_port;
+	struct net_device *lowerdev = NULL;
 
 	vxlan->net = src_net;
 
@@ -2785,9 +2807,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 	}
 
 	if (conf->remote_ifindex) {
-		struct net_device *lowerdev
-			 = __dev_get_by_index(src_net, conf->remote_ifindex);
-
+		lowerdev = __dev_get_by_index(src_net, conf->remote_ifindex);
 		dst->remote_ifindex = conf->remote_ifindex;
 
 		if (!lowerdev) {
@@ -2811,6 +2831,12 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 		needed_headroom = lowerdev->hard_header_len;
 	}
 
+	if (conf->mtu) {
+		err = __vxlan_change_mtu(dev, lowerdev, dst, conf->mtu, false);
+		if (err)
+			return err;
+	}
+
 	if (use_ipv6 || conf->flags & VXLAN_F_COLLECT_METADATA)
 		needed_headroom += VXLAN6_HEADROOM;
 	else
diff --git a/drivers/net/wan/dscc4.c b/drivers/net/wan/dscc4.c
index 7a72407208b1..629225980463 100644
--- a/drivers/net/wan/dscc4.c
+++ b/drivers/net/wan/dscc4.c
@@ -1626,7 +1626,7 @@ try:
 		if (state & Xpr) {
 			void __iomem *scc_addr;
 			unsigned long ring;
-			int i;
+			unsigned int i;
 
 			/*
 			 * - the busy condition happens (sometimes);
diff --git a/drivers/net/wireless/intel/iwlwifi/Kconfig b/drivers/net/wireless/intel/iwlwifi/Kconfig
index 866067789330..7438fbeef744 100644
--- a/drivers/net/wireless/intel/iwlwifi/Kconfig
+++ b/drivers/net/wireless/intel/iwlwifi/Kconfig
@@ -53,7 +53,6 @@ config IWLWIFI_LEDS
 
 config IWLDVM
 	tristate "Intel Wireless WiFi DVM Firmware support"
-	depends on m
 	help
 	  This is the driver that supports the DVM firmware. The list
 	  of the devices that use this firmware is available here:
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-8000.c b/drivers/net/wireless/intel/iwlwifi/iwl-8000.c
index c84a0299d43e..bce9b3420a13 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-8000.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-8000.c
@@ -7,6 +7,7 @@
  *
  * Copyright(c) 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2014 - 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2016 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -70,12 +71,15 @@
 
 /* Highest firmware API version supported */
 #define IWL8000_UCODE_API_MAX	20
+#define IWL8265_UCODE_API_MAX	20
 
 /* Oldest version we won't warn about */
 #define IWL8000_UCODE_API_OK	13
+#define IWL8265_UCODE_API_OK	20
 
 /* Lowest firmware API version supported */
 #define IWL8000_UCODE_API_MIN	13
+#define IWL8265_UCODE_API_MIN	20
 
 /* NVM versions */
 #define IWL8000_NVM_VERSION		0x0a1d
@@ -93,6 +97,10 @@
 #define IWL8000_MODULE_FIRMWARE(api) \
 	IWL8000_FW_PRE "-" __stringify(api) ".ucode"
 
+#define IWL8265_FW_PRE "iwlwifi-8265-"
+#define IWL8265_MODULE_FIRMWARE(api) \
+	IWL8265_FW_PRE __stringify(api) ".ucode"
+
 #define NVM_HW_SECTION_NUM_FAMILY_8000		10
 #define DEFAULT_NVM_FILE_FAMILY_8000B		"nvmData-8000B"
 #define DEFAULT_NVM_FILE_FAMILY_8000C		"nvmData-8000C"
@@ -144,10 +152,7 @@ static const struct iwl_tt_params iwl8000_tt_params = {
 	.support_tx_backoff = true,
 };
 
-#define IWL_DEVICE_8000							\
-	.ucode_api_max = IWL8000_UCODE_API_MAX,				\
-	.ucode_api_ok = IWL8000_UCODE_API_OK,				\
-	.ucode_api_min = IWL8000_UCODE_API_MIN,				\
+#define IWL_DEVICE_8000_COMMON						\
 	.device_family = IWL_DEVICE_FAMILY_8000,			\
 	.max_inst_size = IWL60_RTC_INST_SIZE,				\
 	.max_data_size = IWL60_RTC_DATA_SIZE,				\
@@ -167,10 +172,28 @@ static const struct iwl_tt_params iwl8000_tt_params = {
 	.thermal_params = &iwl8000_tt_params,				\
 	.apmg_not_supported = true
 
+#define IWL_DEVICE_8000							\
+	IWL_DEVICE_8000_COMMON,						\
+	.ucode_api_max = IWL8000_UCODE_API_MAX,				\
+	.ucode_api_ok = IWL8000_UCODE_API_OK,				\
+	.ucode_api_min = IWL8000_UCODE_API_MIN				\
+
+#define IWL_DEVICE_8260							\
+	IWL_DEVICE_8000_COMMON,						\
+	.ucode_api_max = IWL8000_UCODE_API_MAX,				\
+	.ucode_api_ok = IWL8000_UCODE_API_OK,				\
+	.ucode_api_min = IWL8000_UCODE_API_MIN				\
+
+#define IWL_DEVICE_8265							\
+	IWL_DEVICE_8000_COMMON,						\
+	.ucode_api_max = IWL8265_UCODE_API_MAX,				\
+	.ucode_api_ok = IWL8265_UCODE_API_OK,				\
+	.ucode_api_min = IWL8265_UCODE_API_MIN				\
+
 const struct iwl_cfg iwl8260_2n_cfg = {
 	.name = "Intel(R) Dual Band Wireless N 8260",
 	.fw_name_pre = IWL8000_FW_PRE,
-	IWL_DEVICE_8000,
+	IWL_DEVICE_8260,
 	.ht_params = &iwl8000_ht_params,
 	.nvm_ver = IWL8000_NVM_VERSION,
 	.nvm_calib_ver = IWL8000_TX_POWER_VERSION,
@@ -179,7 +202,7 @@ const struct iwl_cfg iwl8260_2n_cfg = {
 const struct iwl_cfg iwl8260_2ac_cfg = {
 	.name = "Intel(R) Dual Band Wireless AC 8260",
 	.fw_name_pre = IWL8000_FW_PRE,
-	IWL_DEVICE_8000,
+	IWL_DEVICE_8260,
 	.ht_params = &iwl8000_ht_params,
 	.nvm_ver = IWL8000_NVM_VERSION,
 	.nvm_calib_ver = IWL8000_TX_POWER_VERSION,
@@ -188,8 +211,8 @@ const struct iwl_cfg iwl8260_2ac_cfg = {
 
 const struct iwl_cfg iwl8265_2ac_cfg = {
 	.name = "Intel(R) Dual Band Wireless AC 8265",
-	.fw_name_pre = IWL8000_FW_PRE,
-	IWL_DEVICE_8000,
+	.fw_name_pre = IWL8265_FW_PRE,
+	IWL_DEVICE_8265,
 	.ht_params = &iwl8000_ht_params,
 	.nvm_ver = IWL8000_NVM_VERSION,
 	.nvm_calib_ver = IWL8000_TX_POWER_VERSION,
@@ -209,7 +232,7 @@ const struct iwl_cfg iwl4165_2ac_cfg = {
 const struct iwl_cfg iwl8260_2ac_sdio_cfg = {
 	.name = "Intel(R) Dual Band Wireless-AC 8260",
 	.fw_name_pre = IWL8000_FW_PRE,
-	IWL_DEVICE_8000,
+	IWL_DEVICE_8260,
 	.ht_params = &iwl8000_ht_params,
 	.nvm_ver = IWL8000_NVM_VERSION,
 	.nvm_calib_ver = IWL8000_TX_POWER_VERSION,
@@ -236,3 +259,4 @@ const struct iwl_cfg iwl4165_2ac_sdio_cfg = {
 };
 
 MODULE_FIRMWARE(IWL8000_MODULE_FIRMWARE(IWL8000_UCODE_API_OK));
+MODULE_FIRMWARE(IWL8265_MODULE_FIRMWARE(IWL8265_UCODE_API_OK));
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index 7acb49075683..ab4c2a0470b2 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -243,8 +243,10 @@ static int iwl_request_firmware(struct iwl_drv *drv, bool first)
 	if (drv->trans->cfg->device_family == IWL_DEVICE_FAMILY_8000) {
 		char rev_step = 'A' + CSR_HW_REV_STEP(drv->trans->hw_rev);
 
-		snprintf(drv->firmware_name, sizeof(drv->firmware_name),
-			 "%s%c-%s.ucode", name_pre, rev_step, tag);
+		if (rev_step != 'A')
+			snprintf(drv->firmware_name,
+				 sizeof(drv->firmware_name), "%s%c-%s.ucode",
+				 name_pre, rev_step, tag);
 	}
 
 	IWL_DEBUG_INFO(drv, "attempting to load firmware %s'%s'\n",
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 4ed5180c547b..0ccc697fef76 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -107,7 +107,7 @@ static int iwl_send_tx_ant_cfg(struct iwl_mvm *mvm, u8 valid_tx_ant)
 				    sizeof(tx_ant_cmd), &tx_ant_cmd);
 }
 
-static void iwl_free_fw_paging(struct iwl_mvm *mvm)
+void iwl_free_fw_paging(struct iwl_mvm *mvm)
 {
 	int i;
 
@@ -127,6 +127,8 @@ static void iwl_free_fw_paging(struct iwl_mvm *mvm)
 			     get_order(mvm->fw_paging_db[i].fw_paging_size));
 	}
 	kfree(mvm->trans->paging_download_buf);
+	mvm->trans->paging_download_buf = NULL;
+
 	memset(mvm->fw_paging_db, 0, sizeof(mvm->fw_paging_db));
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 5f3ac8cccf49..ff7c6df9f941 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1225,6 +1225,9 @@ void iwl_mvm_rx_umac_scan_complete_notif(struct iwl_mvm *mvm,
 void iwl_mvm_rx_umac_scan_iter_complete_notif(struct iwl_mvm *mvm,
 					      struct iwl_rx_cmd_buffer *rxb);
 
+/* Paging */
+void iwl_free_fw_paging(struct iwl_mvm *mvm);
+
 /* MVM debugfs */
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 int iwl_mvm_dbgfs_register(struct iwl_mvm *mvm, struct dentry *dbgfs_dir);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 89ea70deeb84..e80be9a59520 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -684,6 +684,8 @@ static void iwl_op_mode_mvm_stop(struct iwl_op_mode *op_mode)
 	for (i = 0; i < NVM_MAX_NUM_SECTIONS; i++)
 		kfree(mvm->nvm_sections[i].data);
 
+	iwl_free_fw_paging(mvm);
+
 	iwl_mvm_tof_clean(mvm);
 
 	ieee80211_free_hw(mvm->hw);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index 9a15642f80dd..ea1e177c2ea1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -1298,6 +1298,10 @@ int iwl_mvm_sched_scan_start(struct iwl_mvm *mvm,
 		return -EBUSY;
 	}
 
+	/* we don't support "match all" in the firmware */
+	if (!req->n_match_sets)
+		return -EOPNOTSUPP;
+
 	ret = iwl_mvm_check_running_scans(mvm, type);
 	if (ret)
 		return ret;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index 0914ec2fd574..a040edc55057 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -423,6 +423,15 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb)
 		return -1;
 	}
 
+	/*
+	 * Increase the pending frames counter, so that later when a reply comes
+	 * in and the counter is decreased - we don't start getting negative
+	 * values.
+	 * Note that we don't need to make sure it isn't agg'd, since we're
+	 * TXing non-sta
+	 */
+	atomic_inc(&mvm->pending_frames[sta_id]);
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index cc3888e2700d..73c95594eabe 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -490,6 +490,15 @@ static inline void iwl_enable_interrupts(struct iwl_trans *trans)
 	iwl_write32(trans, CSR_INT_MASK, trans_pcie->inta_mask);
 }
 
+static inline void iwl_enable_fw_load_int(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+
+	IWL_DEBUG_ISR(trans, "Enabling FW load interrupt\n");
+	trans_pcie->inta_mask = CSR_INT_BIT_FH_TX;
+	iwl_write32(trans, CSR_INT_MASK, trans_pcie->inta_mask);
+}
+
 static inline void iwl_enable_rfkill_int(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index ccafbd8cf4b3..152cf9ad9566 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -1438,9 +1438,11 @@ irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id)
 			 inta & ~trans_pcie->inta_mask);
 	}
 
-	/* Re-enable all interrupts */
-	/* only Re-enable if disabled by irq */
-	if (test_bit(STATUS_INT_ENABLED, &trans->status))
+	/* we are loading the firmware, enable FH_TX interrupt only */
+	if (handled & CSR_INT_BIT_FH_TX)
+		iwl_enable_fw_load_int(trans);
+	/* only Re-enable all interrupt if disabled by irq */
+	else if (test_bit(STATUS_INT_ENABLED, &trans->status))
 		iwl_enable_interrupts(trans);
 	/* Re-enable RF_KILL if it occurred */
 	else if (handled & CSR_INT_BIT_RF_KILL)
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index d60a467a983c..5a854c609477 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -1021,82 +1021,6 @@ static int iwl_pcie_load_given_ucode_8000(struct iwl_trans *trans,
 					       &first_ucode_section);
 }
 
-static int iwl_trans_pcie_start_fw(struct iwl_trans *trans,
-				   const struct fw_img *fw, bool run_in_rfkill)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	bool hw_rfkill;
-	int ret;
-
-	mutex_lock(&trans_pcie->mutex);
-
-	/* Someone called stop_device, don't try to start_fw */
-	if (trans_pcie->is_down) {
-		IWL_WARN(trans,
-			 "Can't start_fw since the HW hasn't been started\n");
-		ret = EIO;
-		goto out;
-	}
-
-	/* This may fail if AMT took ownership of the device */
-	if (iwl_pcie_prepare_card_hw(trans)) {
-		IWL_WARN(trans, "Exit HW not ready\n");
-		ret = -EIO;
-		goto out;
-	}
-
-	iwl_enable_rfkill_int(trans);
-
-	/* If platform's RF_KILL switch is NOT set to KILL */
-	hw_rfkill = iwl_is_rfkill_set(trans);
-	if (hw_rfkill)
-		set_bit(STATUS_RFKILL, &trans->status);
-	else
-		clear_bit(STATUS_RFKILL, &trans->status);
-	iwl_trans_pcie_rf_kill(trans, hw_rfkill);
-	if (hw_rfkill && !run_in_rfkill) {
-		ret = -ERFKILL;
-		goto out;
-	}
-
-	iwl_write32(trans, CSR_INT, 0xFFFFFFFF);
-
-	ret = iwl_pcie_nic_init(trans);
-	if (ret) {
-		IWL_ERR(trans, "Unable to init nic\n");
-		goto out;
-	}
-
-	/* make sure rfkill handshake bits are cleared */
-	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL);
-	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR,
-		    CSR_UCODE_DRV_GP1_BIT_CMD_BLOCKED);
-
-	/* clear (again), then enable host interrupts */
-	iwl_write32(trans, CSR_INT, 0xFFFFFFFF);
-	iwl_enable_interrupts(trans);
-
-	/* really make sure rfkill handshake bits are cleared */
-	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL);
-	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL);
-
-	/* Load the given image to the HW */
-	if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000)
-		ret = iwl_pcie_load_given_ucode_8000(trans, fw);
-	else
-		ret = iwl_pcie_load_given_ucode(trans, fw);
-
-out:
-	mutex_unlock(&trans_pcie->mutex);
-	return ret;
-}
-
-static void iwl_trans_pcie_fw_alive(struct iwl_trans *trans, u32 scd_addr)
-{
-	iwl_pcie_reset_ict(trans);
-	iwl_pcie_tx_start(trans, scd_addr);
-}
-
 static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool low_power)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -1127,7 +1051,8 @@ static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool low_power)
 	 * already dead.
 	 */
 	if (test_and_clear_bit(STATUS_DEVICE_ENABLED, &trans->status)) {
-		IWL_DEBUG_INFO(trans, "DEVICE_ENABLED bit was set and is now cleared\n");
+		IWL_DEBUG_INFO(trans,
+			       "DEVICE_ENABLED bit was set and is now cleared\n");
 		iwl_pcie_tx_stop(trans);
 		iwl_pcie_rx_stop(trans);
 
@@ -1161,7 +1086,6 @@ static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool low_power)
 	iwl_disable_interrupts(trans);
 	spin_unlock(&trans_pcie->irq_lock);
 
-
 	/* clear all status bits */
 	clear_bit(STATUS_SYNC_HCMD_ACTIVE, &trans->status);
 	clear_bit(STATUS_INT_ENABLED, &trans->status);
@@ -1194,10 +1118,116 @@ static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool low_power)
 	if (hw_rfkill != was_hw_rfkill)
 		iwl_trans_pcie_rf_kill(trans, hw_rfkill);
 
-	/* re-take ownership to prevent other users from stealing the deivce */
+	/* re-take ownership to prevent other users from stealing the device */
 	iwl_pcie_prepare_card_hw(trans);
 }
 
+static int iwl_trans_pcie_start_fw(struct iwl_trans *trans,
+				   const struct fw_img *fw, bool run_in_rfkill)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	bool hw_rfkill;
+	int ret;
+
+	/* This may fail if AMT took ownership of the device */
+	if (iwl_pcie_prepare_card_hw(trans)) {
+		IWL_WARN(trans, "Exit HW not ready\n");
+		ret = -EIO;
+		goto out;
+	}
+
+	iwl_enable_rfkill_int(trans);
+
+	iwl_write32(trans, CSR_INT, 0xFFFFFFFF);
+
+	/*
+	 * We enabled the RF-Kill interrupt and the handler may very
+	 * well be running. Disable the interrupts to make sure no other
+	 * interrupt can be fired.
+	 */
+	iwl_disable_interrupts(trans);
+
+	/* Make sure it finished running */
+	synchronize_irq(trans_pcie->pci_dev->irq);
+
+	mutex_lock(&trans_pcie->mutex);
+
+	/* If platform's RF_KILL switch is NOT set to KILL */
+	hw_rfkill = iwl_is_rfkill_set(trans);
+	if (hw_rfkill)
+		set_bit(STATUS_RFKILL, &trans->status);
+	else
+		clear_bit(STATUS_RFKILL, &trans->status);
+	iwl_trans_pcie_rf_kill(trans, hw_rfkill);
+	if (hw_rfkill && !run_in_rfkill) {
+		ret = -ERFKILL;
+		goto out;
+	}
+
+	/* Someone called stop_device, don't try to start_fw */
+	if (trans_pcie->is_down) {
+		IWL_WARN(trans,
+			 "Can't start_fw since the HW hasn't been started\n");
+		ret = -EIO;
+		goto out;
+	}
+
+	/* make sure rfkill handshake bits are cleared */
+	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL);
+	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR,
+		    CSR_UCODE_DRV_GP1_BIT_CMD_BLOCKED);
+
+	/* clear (again), then enable host interrupts */
+	iwl_write32(trans, CSR_INT, 0xFFFFFFFF);
+
+	ret = iwl_pcie_nic_init(trans);
+	if (ret) {
+		IWL_ERR(trans, "Unable to init nic\n");
+		goto out;
+	}
+
+	/*
+	 * Now, we load the firmware and don't want to be interrupted, even
+	 * by the RF-Kill interrupt (hence mask all the interrupt besides the
+	 * FH_TX interrupt which is needed to load the firmware). If the
+	 * RF-Kill switch is toggled, we will find out after having loaded
+	 * the firmware and return the proper value to the caller.
+	 */
+	iwl_enable_fw_load_int(trans);
+
+	/* really make sure rfkill handshake bits are cleared */
+	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL);
+	iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL);
+
+	/* Load the given image to the HW */
+	if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000)
+		ret = iwl_pcie_load_given_ucode_8000(trans, fw);
+	else
+		ret = iwl_pcie_load_given_ucode(trans, fw);
+	iwl_enable_interrupts(trans);
+
+	/* re-check RF-Kill state since we may have missed the interrupt */
+	hw_rfkill = iwl_is_rfkill_set(trans);
+	if (hw_rfkill)
+		set_bit(STATUS_RFKILL, &trans->status);
+	else
+		clear_bit(STATUS_RFKILL, &trans->status);
+
+	iwl_trans_pcie_rf_kill(trans, hw_rfkill);
+	if (hw_rfkill && !run_in_rfkill)
+		ret = -ERFKILL;
+
+out:
+	mutex_unlock(&trans_pcie->mutex);
+	return ret;
+}
+
+static void iwl_trans_pcie_fw_alive(struct iwl_trans *trans, u32 scd_addr)
+{
+	iwl_pcie_reset_ict(trans);
+	iwl_pcie_tx_start(trans, scd_addr);
+}
+
 static void iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool low_power)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
diff --git a/drivers/net/wireless/intersil/orinoco/mic.c b/drivers/net/wireless/intersil/orinoco/mic.c
index fce4a843e656..bc7397d709d3 100644
--- a/drivers/net/wireless/intersil/orinoco/mic.c
+++ b/drivers/net/wireless/intersil/orinoco/mic.c
@@ -6,7 +6,7 @@
 #include <linux/string.h>
 #include <linux/if_ether.h>
 #include <linux/scatterlist.h>
-#include <linux/crypto.h>
+#include <crypto/hash.h>
 
 #include "orinoco.h"
 #include "mic.h"
@@ -16,7 +16,8 @@
 /********************************************************************/
 int orinoco_mic_init(struct orinoco_private *priv)
 {
-	priv->tx_tfm_mic = crypto_alloc_hash("michael_mic", 0, 0);
+	priv->tx_tfm_mic = crypto_alloc_ahash("michael_mic", 0,
+					      CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->tx_tfm_mic)) {
 		printk(KERN_DEBUG "orinoco_mic_init: could not allocate "
 		       "crypto API michael_mic\n");
@@ -24,7 +25,8 @@ int orinoco_mic_init(struct orinoco_private *priv)
 		return -ENOMEM;
 	}
 
-	priv->rx_tfm_mic = crypto_alloc_hash("michael_mic", 0, 0);
+	priv->rx_tfm_mic = crypto_alloc_ahash("michael_mic", 0,
+					      CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->rx_tfm_mic)) {
 		printk(KERN_DEBUG "orinoco_mic_init: could not allocate "
 		       "crypto API michael_mic\n");
@@ -38,18 +40,19 @@ int orinoco_mic_init(struct orinoco_private *priv)
 void orinoco_mic_free(struct orinoco_private *priv)
 {
 	if (priv->tx_tfm_mic)
-		crypto_free_hash(priv->tx_tfm_mic);
+		crypto_free_ahash(priv->tx_tfm_mic);
 	if (priv->rx_tfm_mic)
-		crypto_free_hash(priv->rx_tfm_mic);
+		crypto_free_ahash(priv->rx_tfm_mic);
 }
 
-int orinoco_mic(struct crypto_hash *tfm_michael, u8 *key,
+int orinoco_mic(struct crypto_ahash *tfm_michael, u8 *key,
 		u8 *da, u8 *sa, u8 priority,
 		u8 *data, size_t data_len, u8 *mic)
 {
-	struct hash_desc desc;
+	AHASH_REQUEST_ON_STACK(req, tfm_michael);
 	struct scatterlist sg[2];
 	u8 hdr[ETH_HLEN + 2]; /* size of header + padding */
+	int err;
 
 	if (tfm_michael == NULL) {
 		printk(KERN_WARNING "orinoco_mic: tfm_michael == NULL\n");
@@ -69,11 +72,13 @@ int orinoco_mic(struct crypto_hash *tfm_michael, u8 *key,
 	sg_set_buf(&sg[0], hdr, sizeof(hdr));
 	sg_set_buf(&sg[1], data, data_len);
 
-	if (crypto_hash_setkey(tfm_michael, key, MIC_KEYLEN))
+	if (crypto_ahash_setkey(tfm_michael, key, MIC_KEYLEN))
 		return -1;
 
-	desc.tfm = tfm_michael;
-	desc.flags = 0;
-	return crypto_hash_digest(&desc, sg, data_len + sizeof(hdr),
-				  mic);
+	ahash_request_set_tfm(req, tfm_michael);
+	ahash_request_set_callback(req, 0, NULL, NULL);
+	ahash_request_set_crypt(req, sg, mic, data_len + sizeof(hdr));
+	err = crypto_ahash_digest(req);
+	ahash_request_zero(req);
+	return err;
 }
diff --git a/drivers/net/wireless/intersil/orinoco/mic.h b/drivers/net/wireless/intersil/orinoco/mic.h
index 04d05bc566d6..ce731d05cc98 100644
--- a/drivers/net/wireless/intersil/orinoco/mic.h
+++ b/drivers/net/wireless/intersil/orinoco/mic.h
@@ -11,11 +11,11 @@
 
 /* Forward declarations */
 struct orinoco_private;
-struct crypto_hash;
+struct crypto_ahash;
 
 int orinoco_mic_init(struct orinoco_private *priv);
 void orinoco_mic_free(struct orinoco_private *priv);
-int orinoco_mic(struct crypto_hash *tfm_michael, u8 *key,
+int orinoco_mic(struct crypto_ahash *tfm_michael, u8 *key,
 		u8 *da, u8 *sa, u8 priority,
 		u8 *data, size_t data_len, u8 *mic);
 
diff --git a/drivers/net/wireless/intersil/orinoco/orinoco.h b/drivers/net/wireless/intersil/orinoco/orinoco.h
index eebd2be21ee9..2f0c84b1c440 100644
--- a/drivers/net/wireless/intersil/orinoco/orinoco.h
+++ b/drivers/net/wireless/intersil/orinoco/orinoco.h
@@ -152,8 +152,8 @@ struct orinoco_private {
 	u8 *wpa_ie;
 	int wpa_ie_len;
 
-	struct crypto_hash *rx_tfm_mic;
-	struct crypto_hash *tx_tfm_mic;
+	struct crypto_ahash *rx_tfm_mic;
+	struct crypto_ahash *tx_tfm_mic;
 
 	unsigned int wpa_enabled:1;
 	unsigned int tkip_cm_active:1;
diff --git a/drivers/net/wireless/realtek/rtlwifi/rc.c b/drivers/net/wireless/realtek/rtlwifi/rc.c
index 74c14ce28238..28f7010e7108 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rc.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rc.c
@@ -138,6 +138,11 @@ static void _rtl_rc_rate_set_series(struct rtl_priv *rtlpriv,
 		    ((wireless_mode == WIRELESS_MODE_N_5G) ||
 		     (wireless_mode == WIRELESS_MODE_N_24G)))
 			rate->flags |= IEEE80211_TX_RC_MCS;
+		if (sta && sta->vht_cap.vht_supported &&
+		    (wireless_mode == WIRELESS_MODE_AC_5G ||
+		     wireless_mode == WIRELESS_MODE_AC_24G ||
+		     wireless_mode == WIRELESS_MODE_AC_ONLY))
+			rate->flags |= IEEE80211_TX_RC_VHT_MCS;
 	}
 }
 
diff --git a/drivers/net/wireless/ti/wlcore/io.c b/drivers/net/wireless/ti/wlcore/io.c
index 9ac118e727e9..564ca750c5ee 100644
--- a/drivers/net/wireless/ti/wlcore/io.c
+++ b/drivers/net/wireless/ti/wlcore/io.c
@@ -175,14 +175,14 @@ int wlcore_set_partition(struct wl1271 *wl,
 	if (ret < 0)
 		goto out;
 
+	/* We don't need the size of the last partition, as it is
+	 * automatically calculated based on the total memory size and
+	 * the sizes of the previous partitions.
+	 */
 	ret = wlcore_raw_write32(wl, HW_PART3_START_ADDR, p->mem3.start);
 	if (ret < 0)
 		goto out;
 
-	ret = wlcore_raw_write32(wl, HW_PART3_SIZE_ADDR, p->mem3.size);
-	if (ret < 0)
-		goto out;
-
 out:
 	return ret;
 }
diff --git a/drivers/net/wireless/ti/wlcore/io.h b/drivers/net/wireless/ti/wlcore/io.h
index 6c257b54f415..10cf3747694d 100644
--- a/drivers/net/wireless/ti/wlcore/io.h
+++ b/drivers/net/wireless/ti/wlcore/io.h
@@ -36,8 +36,8 @@
 #define HW_PART1_START_ADDR             (HW_PARTITION_REGISTERS_ADDR + 12)
 #define HW_PART2_SIZE_ADDR              (HW_PARTITION_REGISTERS_ADDR + 16)
 #define HW_PART2_START_ADDR             (HW_PARTITION_REGISTERS_ADDR + 20)
-#define HW_PART3_SIZE_ADDR              (HW_PARTITION_REGISTERS_ADDR + 24)
-#define HW_PART3_START_ADDR             (HW_PARTITION_REGISTERS_ADDR + 28)
+#define HW_PART3_START_ADDR             (HW_PARTITION_REGISTERS_ADDR + 24)
+
 #define HW_ACCESS_REGISTER_SIZE         4
 
 #define HW_ACCESS_PRAM_MAX_RANGE	0x3c000
diff --git a/drivers/nfc/s3fwrn5/firmware.c b/drivers/nfc/s3fwrn5/firmware.c
index 64a90252c57f..5f97da1947e3 100644
--- a/drivers/nfc/s3fwrn5/firmware.c
+++ b/drivers/nfc/s3fwrn5/firmware.c
@@ -19,7 +19,7 @@
 
 #include <linux/completion.h>
 #include <linux/firmware.h>
-#include <linux/crypto.h>
+#include <crypto/hash.h>
 #include <crypto/sha.h>
 
 #include "s3fwrn5.h"
@@ -429,8 +429,7 @@ int s3fwrn5_fw_download(struct s3fwrn5_fw_info *fw_info)
 {
 	struct s3fwrn5_fw_image *fw = &fw_info->fw;
 	u8 hash_data[SHA1_DIGEST_SIZE];
-	struct scatterlist sg;
-	struct hash_desc desc;
+	struct crypto_shash *tfm;
 	u32 image_size, off;
 	int ret;
 
@@ -438,12 +437,31 @@ int s3fwrn5_fw_download(struct s3fwrn5_fw_info *fw_info)
 
 	/* Compute SHA of firmware data */
 
-	sg_init_one(&sg, fw->image, image_size);
-	desc.tfm = crypto_alloc_hash("sha1", 0, CRYPTO_ALG_ASYNC);
-	crypto_hash_init(&desc);
-	crypto_hash_update(&desc, &sg, image_size);
-	crypto_hash_final(&desc, hash_data);
-	crypto_free_hash(desc.tfm);
+	tfm = crypto_alloc_shash("sha1", 0, 0);
+	if (IS_ERR(tfm)) {
+		ret = PTR_ERR(tfm);
+		dev_err(&fw_info->ndev->nfc_dev->dev,
+			"Cannot allocate shash (code=%d)\n", ret);
+		goto out;
+	}
+
+	{
+		SHASH_DESC_ON_STACK(desc, tfm);
+
+		desc->tfm = tfm;
+		desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+		ret = crypto_shash_digest(desc, fw->image, image_size,
+					  hash_data);
+		shash_desc_zero(desc);
+	}
+
+	crypto_free_shash(tfm);
+	if (ret) {
+		dev_err(&fw_info->ndev->nfc_dev->dev,
+			"Cannot compute hash (code=%d)\n", ret);
+		goto out;
+	}
 
 	/* Firmware update process */
 
diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c
index 91a336ea8c4f..e9ff9229d942 100644
--- a/drivers/nvdimm/blk.c
+++ b/drivers/nvdimm/blk.c
@@ -31,8 +31,6 @@ struct nd_blk_device {
 	u32 internal_lbasize;
 };
 
-static int nd_blk_major;
-
 static u32 nd_blk_meta_size(struct nd_blk_device *blk_dev)
 {
 	return blk_dev->nsblk->lbasize - blk_dev->sector_size;
@@ -264,7 +262,6 @@ static int nd_blk_attach_disk(struct nd_namespace_common *ndns,
 	}
 
 	disk->driverfs_dev	= &ndns->dev;
-	disk->major		= nd_blk_major;
 	disk->first_minor	= 0;
 	disk->fops		= &nd_blk_fops;
 	disk->private_data	= blk_dev;
@@ -358,25 +355,12 @@ static struct nd_device_driver nd_blk_driver = {
 
 static int __init nd_blk_init(void)
 {
-	int rc;
-
-	rc = register_blkdev(0, "nd_blk");
-	if (rc < 0)
-		return rc;
-
-	nd_blk_major = rc;
-	rc = nd_driver_register(&nd_blk_driver);
-
-	if (rc < 0)
-		unregister_blkdev(nd_blk_major, "nd_blk");
-
-	return rc;
+	return nd_driver_register(&nd_blk_driver);
 }
 
 static void __exit nd_blk_exit(void)
 {
 	driver_unregister(&nd_blk_driver.drv);
-	unregister_blkdev(nd_blk_major, "nd_blk");
 }
 
 MODULE_AUTHOR("Ross Zwisler <ross.zwisler@linux.intel.com>");
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index efb2c1ceef98..c32cbb593600 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -31,8 +31,6 @@ enum log_ent_request {
 	LOG_OLD_ENT
 };
 
-static int btt_major;
-
 static int arena_read_bytes(struct arena_info *arena, resource_size_t offset,
 		void *buf, size_t n)
 {
@@ -1246,7 +1244,6 @@ static int btt_blk_init(struct btt *btt)
 
 	nvdimm_namespace_disk_name(ndns, btt->btt_disk->disk_name);
 	btt->btt_disk->driverfs_dev = &btt->nd_btt->dev;
-	btt->btt_disk->major = btt_major;
 	btt->btt_disk->first_minor = 0;
 	btt->btt_disk->fops = &btt_fops;
 	btt->btt_disk->private_data = btt;
@@ -1423,22 +1420,11 @@ EXPORT_SYMBOL(nvdimm_namespace_detach_btt);
 
 static int __init nd_btt_init(void)
 {
-	int rc;
-
-	btt_major = register_blkdev(0, "btt");
-	if (btt_major < 0)
-		return btt_major;
+	int rc = 0;
 
 	debugfs_root = debugfs_create_dir("btt", NULL);
-	if (IS_ERR_OR_NULL(debugfs_root)) {
+	if (IS_ERR_OR_NULL(debugfs_root))
 		rc = -ENXIO;
-		goto err_debugfs;
-	}
-
-	return 0;
-
- err_debugfs:
-	unregister_blkdev(btt_major, "btt");
 
 	return rc;
 }
@@ -1446,7 +1432,6 @@ static int __init nd_btt_init(void)
 static void __exit nd_btt_exit(void)
 {
 	debugfs_remove_recursive(debugfs_root);
-	unregister_blkdev(btt_major, "btt");
 }
 
 MODULE_ALIAS_ND_DEVICE(ND_DEVICE_BTT);
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 7e2c43f701bc..33557481d452 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -133,6 +133,78 @@ static int nvdimm_bus_remove(struct device *dev)
 	return rc;
 }
 
+void nd_device_notify(struct device *dev, enum nvdimm_event event)
+{
+	device_lock(dev);
+	if (dev->driver) {
+		struct nd_device_driver *nd_drv;
+
+		nd_drv = to_nd_device_driver(dev->driver);
+		if (nd_drv->notify)
+			nd_drv->notify(dev, event);
+	}
+	device_unlock(dev);
+}
+EXPORT_SYMBOL(nd_device_notify);
+
+void nvdimm_region_notify(struct nd_region *nd_region, enum nvdimm_event event)
+{
+	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
+
+	if (!nvdimm_bus)
+		return;
+
+	/* caller is responsible for holding a reference on the device */
+	nd_device_notify(&nd_region->dev, event);
+}
+EXPORT_SYMBOL_GPL(nvdimm_region_notify);
+
+long nvdimm_clear_poison(struct device *dev, phys_addr_t phys,
+		unsigned int len)
+{
+	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
+	struct nvdimm_bus_descriptor *nd_desc;
+	struct nd_cmd_clear_error clear_err;
+	struct nd_cmd_ars_cap ars_cap;
+	u32 clear_err_unit, mask;
+	int cmd_rc, rc;
+
+	if (!nvdimm_bus)
+		return -ENXIO;
+
+	nd_desc = nvdimm_bus->nd_desc;
+	if (!nd_desc->ndctl)
+		return -ENXIO;
+
+	memset(&ars_cap, 0, sizeof(ars_cap));
+	ars_cap.address = phys;
+	ars_cap.length = len;
+	rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_CAP, &ars_cap,
+			sizeof(ars_cap), &cmd_rc);
+	if (rc < 0)
+		return rc;
+	if (cmd_rc < 0)
+		return cmd_rc;
+	clear_err_unit = ars_cap.clear_err_unit;
+	if (!clear_err_unit || !is_power_of_2(clear_err_unit))
+		return -ENXIO;
+
+	mask = clear_err_unit - 1;
+	if ((phys | len) & mask)
+		return -ENXIO;
+	memset(&clear_err, 0, sizeof(clear_err));
+	clear_err.address = phys;
+	clear_err.length = len;
+	rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_CLEAR_ERROR, &clear_err,
+			sizeof(clear_err), &cmd_rc);
+	if (rc < 0)
+		return rc;
+	if (cmd_rc < 0)
+		return cmd_rc;
+	return clear_err.cleared;
+}
+EXPORT_SYMBOL_GPL(nvdimm_clear_poison);
+
 static struct bus_type nvdimm_bus_type = {
 	.name = "nd",
 	.uevent = nvdimm_bus_uevent,
@@ -382,18 +454,24 @@ static const struct nd_cmd_desc __nd_cmd_bus_descs[] = {
 	[ND_CMD_ARS_CAP] = {
 		.in_num = 2,
 		.in_sizes = { 8, 8, },
-		.out_num = 2,
-		.out_sizes = { 4, 4, },
+		.out_num = 4,
+		.out_sizes = { 4, 4, 4, 4, },
 	},
 	[ND_CMD_ARS_START] = {
-		.in_num = 4,
-		.in_sizes = { 8, 8, 2, 6, },
-		.out_num = 1,
-		.out_sizes = { 4, },
+		.in_num = 5,
+		.in_sizes = { 8, 8, 2, 1, 5, },
+		.out_num = 2,
+		.out_sizes = { 4, 4, },
 	},
 	[ND_CMD_ARS_STATUS] = {
-		.out_num = 2,
-		.out_sizes = { 4, UINT_MAX, },
+		.out_num = 3,
+		.out_sizes = { 4, 4, UINT_MAX, },
+	},
+	[ND_CMD_CLEAR_ERROR] = {
+		.in_num = 2,
+		.in_sizes = { 8, 8, },
+		.out_num = 3,
+		.out_sizes = { 4, 4, 8, },
 	},
 };
 
@@ -442,8 +520,8 @@ u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd,
 		return in_field[1];
 	else if (nvdimm && cmd == ND_CMD_VENDOR && idx == 2)
 		return out_field[1];
-	else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 1)
-		return ND_CMD_ARS_STATUS_MAX;
+	else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 2)
+		return out_field[1] - 8;
 
 	return UINT_MAX;
 }
@@ -463,17 +541,37 @@ void wait_nvdimm_bus_probe_idle(struct device *dev)
 	} while (true);
 }
 
+static int pmem_active(struct device *dev, void *data)
+{
+	if (is_nd_pmem(dev) && dev->driver)
+		return -EBUSY;
+	return 0;
+}
+
 /* set_config requires an idle interleave set */
-static int nd_cmd_clear_to_send(struct nvdimm *nvdimm, unsigned int cmd)
+static int nd_cmd_clear_to_send(struct nvdimm_bus *nvdimm_bus,
+		struct nvdimm *nvdimm, unsigned int cmd)
 {
-	struct nvdimm_bus *nvdimm_bus;
+	struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
+
+	/* ask the bus provider if it would like to block this request */
+	if (nd_desc->clear_to_send) {
+		int rc = nd_desc->clear_to_send(nd_desc, nvdimm, cmd);
+
+		if (rc)
+			return rc;
+	}
+
+	/* require clear error to go through the pmem driver */
+	if (!nvdimm && cmd == ND_CMD_CLEAR_ERROR)
+		return device_for_each_child(&nvdimm_bus->dev, NULL,
+				pmem_active);
 
 	if (!nvdimm || cmd != ND_CMD_SET_CONFIG_DATA)
 		return 0;
 
-	nvdimm_bus = walk_to_nvdimm_bus(&nvdimm->dev);
+	/* prevent label manipulation while the kernel owns label updates */
 	wait_nvdimm_bus_probe_idle(&nvdimm_bus->dev);
-
 	if (atomic_read(&nvdimm->busy))
 		return -EBUSY;
 	return 0;
@@ -513,10 +611,11 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 
 	/* fail write commands (when read-only) */
 	if (read_only)
-		switch (ioctl_cmd) {
-		case ND_IOCTL_VENDOR:
-		case ND_IOCTL_SET_CONFIG_DATA:
-		case ND_IOCTL_ARS_START:
+		switch (cmd) {
+		case ND_CMD_VENDOR:
+		case ND_CMD_SET_CONFIG_DATA:
+		case ND_CMD_ARS_START:
+		case ND_CMD_CLEAR_ERROR:
 			dev_dbg(&nvdimm_bus->dev, "'%s' command while read-only.\n",
 					nvdimm ? nvdimm_cmd_name(cmd)
 					: nvdimm_bus_cmd_name(cmd));
@@ -583,11 +682,11 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 	}
 
 	nvdimm_bus_lock(&nvdimm_bus->dev);
-	rc = nd_cmd_clear_to_send(nvdimm, cmd);
+	rc = nd_cmd_clear_to_send(nvdimm_bus, nvdimm, cmd);
 	if (rc)
 		goto out_unlock;
 
-	rc = nd_desc->ndctl(nd_desc, nvdimm, cmd, buf, buf_len);
+	rc = nd_desc->ndctl(nd_desc, nvdimm, cmd, buf, buf_len, NULL);
 	if (rc < 0)
 		goto out_unlock;
 	if (copy_to_user(p, buf, buf_len))
@@ -602,14 +701,14 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 static long nd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	long id = (long) file->private_data;
-	int rc = -ENXIO, read_only;
+	int rc = -ENXIO, ro;
 	struct nvdimm_bus *nvdimm_bus;
 
-	read_only = (O_RDWR != (file->f_flags & O_ACCMODE));
+	ro = ((file->f_flags & O_ACCMODE) == O_RDONLY);
 	mutex_lock(&nvdimm_bus_list_mutex);
 	list_for_each_entry(nvdimm_bus, &nvdimm_bus_list, list) {
 		if (nvdimm_bus->id == id) {
-			rc = __nd_ioctl(nvdimm_bus, NULL, read_only, cmd, arg);
+			rc = __nd_ioctl(nvdimm_bus, NULL, ro, cmd, arg);
 			break;
 		}
 	}
@@ -633,10 +732,10 @@ static int match_dimm(struct device *dev, void *data)
 
 static long nvdimm_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
-	int rc = -ENXIO, read_only;
+	int rc = -ENXIO, ro;
 	struct nvdimm_bus *nvdimm_bus;
 
-	read_only = (O_RDWR != (file->f_flags & O_ACCMODE));
+	ro = ((file->f_flags & O_ACCMODE) == O_RDONLY);
 	mutex_lock(&nvdimm_bus_list_mutex);
 	list_for_each_entry(nvdimm_bus, &nvdimm_bus_list, list) {
 		struct device *dev = device_find_child(&nvdimm_bus->dev,
@@ -647,7 +746,7 @@ static long nvdimm_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			continue;
 
 		nvdimm = to_nvdimm(dev);
-		rc = __nd_ioctl(nvdimm_bus, nvdimm, read_only, cmd, arg);
+		rc = __nd_ioctl(nvdimm_bus, nvdimm, ro, cmd, arg);
 		put_device(dev);
 		break;
 	}
diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index 2e2832b83c93..79646d0c3277 100644
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -298,6 +298,15 @@ static int flush_regions_dimms(struct device *dev, void *data)
 static ssize_t wait_probe_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
+	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
+	struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
+	int rc;
+
+	if (nd_desc->flush_probe) {
+		rc = nd_desc->flush_probe(nd_desc);
+		if (rc)
+			return rc;
+	}
 	nd_synchronize();
 	device_for_each_child(dev, NULL, flush_regions_dimms);
 	return sprintf(buf, "1\n");
@@ -408,33 +417,11 @@ static void __add_badblock_range(struct badblocks *bb, u64 ns_offset, u64 len)
 		set_badblock(bb, start_sector, num_sectors);
 }
 
-/**
- * nvdimm_namespace_add_poison() - Convert a list of poison ranges to badblocks
- * @ndns:	the namespace containing poison ranges
- * @bb:		badblocks instance to populate
- * @offset:	offset at the start of the namespace before 'sector 0'
- *
- * The poison list generated during NFIT initialization may contain multiple,
- * possibly overlapping ranges in the SPA (System Physical Address) space.
- * Compare each of these ranges to the namespace currently being initialized,
- * and add badblocks to the gendisk for all matching sub-ranges
- */
-void nvdimm_namespace_add_poison(struct nd_namespace_common *ndns,
-		struct badblocks *bb, resource_size_t offset)
+static void namespace_add_poison(struct list_head *poison_list,
+		struct badblocks *bb, struct resource *res)
 {
-	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
-	struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
-	struct nvdimm_bus *nvdimm_bus;
-	struct list_head *poison_list;
-	u64 ns_start, ns_end, ns_size;
 	struct nd_poison *pl;
 
-	ns_size = nvdimm_namespace_capacity(ndns) - offset;
-	ns_start = nsio->res.start + offset;
-	ns_end = nsio->res.end;
-
-	nvdimm_bus = to_nvdimm_bus(nd_region->dev.parent);
-	poison_list = &nvdimm_bus->poison_list;
 	if (list_empty(poison_list))
 		return;
 
@@ -442,37 +429,69 @@ void nvdimm_namespace_add_poison(struct nd_namespace_common *ndns,
 		u64 pl_end = pl->start + pl->length - 1;
 
 		/* Discard intervals with no intersection */
-		if (pl_end < ns_start)
+		if (pl_end < res->start)
 			continue;
-		if (pl->start > ns_end)
+		if (pl->start >  res->end)
 			continue;
 		/* Deal with any overlap after start of the namespace */
-		if (pl->start >= ns_start) {
+		if (pl->start >= res->start) {
 			u64 start = pl->start;
 			u64 len;
 
-			if (pl_end <= ns_end)
+			if (pl_end <= res->end)
 				len = pl->length;
 			else
-				len = ns_start + ns_size - pl->start;
-			__add_badblock_range(bb, start - ns_start, len);
+				len = res->start + resource_size(res)
+					- pl->start;
+			__add_badblock_range(bb, start - res->start, len);
 			continue;
 		}
 		/* Deal with overlap for poison starting before the namespace */
-		if (pl->start < ns_start) {
+		if (pl->start < res->start) {
 			u64 len;
 
-			if (pl_end < ns_end)
-				len = pl->start + pl->length - ns_start;
+			if (pl_end < res->end)
+				len = pl->start + pl->length - res->start;
 			else
-				len = ns_size;
+				len = resource_size(res);
 			__add_badblock_range(bb, 0, len);
 		}
 	}
 }
+
+/**
+ * nvdimm_namespace_add_poison() - Convert a list of poison ranges to badblocks
+ * @ndns:	the namespace containing poison ranges
+ * @bb:		badblocks instance to populate
+ * @offset:	offset at the start of the namespace before 'sector 0'
+ *
+ * The poison list generated during NFIT initialization may contain multiple,
+ * possibly overlapping ranges in the SPA (System Physical Address) space.
+ * Compare each of these ranges to the namespace currently being initialized,
+ * and add badblocks to the gendisk for all matching sub-ranges
+ */
+void nvdimm_namespace_add_poison(struct nd_namespace_common *ndns,
+		struct badblocks *bb, resource_size_t offset)
+{
+	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
+	struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
+	struct nvdimm_bus *nvdimm_bus;
+	struct list_head *poison_list;
+	struct resource res = {
+		.start = nsio->res.start + offset,
+		.end = nsio->res.end,
+	};
+
+	nvdimm_bus = to_nvdimm_bus(nd_region->dev.parent);
+	poison_list = &nvdimm_bus->poison_list;
+
+	nvdimm_bus_lock(&nvdimm_bus->dev);
+	namespace_add_poison(poison_list, bb, &res);
+	nvdimm_bus_unlock(&nvdimm_bus->dev);
+}
 EXPORT_SYMBOL_GPL(nvdimm_namespace_add_poison);
 
-static int __add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
+static int add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
 {
 	struct nd_poison *pl;
 
@@ -487,12 +506,12 @@ static int __add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
 	return 0;
 }
 
-int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
+static int bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
 {
 	struct nd_poison *pl;
 
 	if (list_empty(&nvdimm_bus->poison_list))
-		return __add_poison(nvdimm_bus, addr, length);
+		return add_poison(nvdimm_bus, addr, length);
 
 	/*
 	 * There is a chance this is a duplicate, check for those first.
@@ -512,7 +531,18 @@ int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
 	 * as any overlapping ranges will get resolved when the list is consumed
 	 * and converted to badblocks
 	 */
-	return __add_poison(nvdimm_bus, addr, length);
+	return add_poison(nvdimm_bus, addr, length);
+}
+
+int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
+{
+	int rc;
+
+	nvdimm_bus_lock(&nvdimm_bus->dev);
+	rc = bus_add_poison(nvdimm_bus, addr, length);
+	nvdimm_bus_unlock(&nvdimm_bus->dev);
+
+	return rc;
 }
 EXPORT_SYMBOL_GPL(nvdimm_bus_add_poison);
 
@@ -553,7 +583,11 @@ void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus)
 
 	nd_synchronize();
 	device_for_each_child(&nvdimm_bus->dev, NULL, child_unregister);
+
+	nvdimm_bus_lock(&nvdimm_bus->dev);
 	free_poison_list(&nvdimm_bus->poison_list);
+	nvdimm_bus_unlock(&nvdimm_bus->dev);
+
 	nvdimm_bus_destroy_ndctl(nvdimm_bus);
 
 	device_unregister(&nvdimm_bus->dev);
diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c
index 651b8d19d324..c56f88217924 100644
--- a/drivers/nvdimm/dimm_devs.c
+++ b/drivers/nvdimm/dimm_devs.c
@@ -75,7 +75,7 @@ int nvdimm_init_nsarea(struct nvdimm_drvdata *ndd)
 	memset(cmd, 0, sizeof(*cmd));
 	nd_desc = nvdimm_bus->nd_desc;
 	return nd_desc->ndctl(nd_desc, to_nvdimm(ndd->dev),
-			ND_CMD_GET_CONFIG_SIZE, cmd, sizeof(*cmd));
+			ND_CMD_GET_CONFIG_SIZE, cmd, sizeof(*cmd), NULL);
 }
 
 int nvdimm_init_config_data(struct nvdimm_drvdata *ndd)
@@ -120,7 +120,7 @@ int nvdimm_init_config_data(struct nvdimm_drvdata *ndd)
 		cmd->in_offset = offset;
 		rc = nd_desc->ndctl(nd_desc, to_nvdimm(ndd->dev),
 				ND_CMD_GET_CONFIG_DATA, cmd,
-				cmd->in_length + sizeof(*cmd));
+				cmd->in_length + sizeof(*cmd), NULL);
 		if (rc || cmd->status) {
 			rc = -ENXIO;
 			break;
@@ -171,7 +171,7 @@ int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset,
 		status = ((void *) cmd) + cmd_size - sizeof(u32);
 
 		rc = nd_desc->ndctl(nd_desc, to_nvdimm(ndd->dev),
-				ND_CMD_SET_CONFIG_DATA, cmd, cmd_size);
+				ND_CMD_SET_CONFIG_DATA, cmd, cmd_size, NULL);
 		if (rc || *status) {
 			rc = rc ? rc : -ENXIO;
 			break;
diff --git a/drivers/nvdimm/e820.c b/drivers/nvdimm/e820.c
index b0045a505dc8..95825b38559a 100644
--- a/drivers/nvdimm/e820.c
+++ b/drivers/nvdimm/e820.c
@@ -55,7 +55,7 @@ static int e820_pmem_probe(struct platform_device *pdev)
 	for (p = iomem_resource.child; p ; p = p->sibling) {
 		struct nd_region_desc ndr_desc;
 
-		if (strncmp(p->name, "Persistent Memory (legacy)", 26) != 0)
+		if (p->desc != IORES_DESC_PERSISTENT_MEMORY_LEGACY)
 			continue;
 
 		memset(&ndr_desc, 0, sizeof(ndr_desc));
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index 9edf7eb7d17c..f5cb88601359 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -133,6 +133,7 @@ bool nd_is_uuid_unique(struct device *dev, u8 *uuid)
 bool pmem_should_map_pages(struct device *dev)
 {
 	struct nd_region *nd_region = to_nd_region(dev->parent);
+	struct nd_namespace_io *nsio;
 
 	if (!IS_ENABLED(CONFIG_ZONE_DEVICE))
 		return false;
@@ -143,6 +144,12 @@ bool pmem_should_map_pages(struct device *dev)
 	if (is_nd_pfn(dev) || is_nd_btt(dev))
 		return false;
 
+	nsio = to_nd_namespace_io(dev);
+	if (region_intersects(nsio->res.start, resource_size(&nsio->res),
+				IORESOURCE_SYSTEM_RAM,
+				IORES_DESC_NONE) == REGION_MIXED)
+		return false;
+
 #ifdef ARCH_MEMREMAP_PMEM
 	return ARCH_MEMREMAP_PMEM == MEMREMAP_WB;
 #else
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index ba1633b9da31..1799bd97a9ce 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -18,6 +18,7 @@
 #include <linux/mutex.h>
 #include <linux/ndctl.h>
 #include <linux/types.h>
+#include <linux/nd.h>
 #include "label.h"
 
 enum {
@@ -168,6 +169,7 @@ int nd_integrity_init(struct gendisk *disk, unsigned long meta_size);
 void wait_nvdimm_bus_probe_idle(struct device *dev);
 void nd_device_register(struct device *dev);
 void nd_device_unregister(struct device *dev, enum nd_async_mode mode);
+void nd_device_notify(struct device *dev, enum nvdimm_event event);
 int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf,
 		size_t len);
 ssize_t nd_sector_size_show(unsigned long current_lbasize,
@@ -184,6 +186,8 @@ int nvdimm_init_nsarea(struct nvdimm_drvdata *ndd);
 int nvdimm_init_config_data(struct nvdimm_drvdata *ndd);
 int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset,
 		void *buf, size_t len);
+long nvdimm_clear_poison(struct device *dev, phys_addr_t phys,
+		unsigned int len);
 struct nd_btt *to_nd_btt(struct device *dev);
 
 struct nd_gen_sb {
diff --git a/drivers/nvdimm/pfn.h b/drivers/nvdimm/pfn.h
index cc243754acef..8e343a3ca873 100644
--- a/drivers/nvdimm/pfn.h
+++ b/drivers/nvdimm/pfn.h
@@ -15,6 +15,7 @@
 #define __NVDIMM_PFN_H
 
 #include <linux/types.h>
+#include <linux/mmzone.h>
 
 #define PFN_SIG_LEN 16
 #define PFN_SIG "NVDIMM_PFN_INFO\0"
@@ -26,10 +27,28 @@ struct nd_pfn_sb {
 	__le32 flags;
 	__le16 version_major;
 	__le16 version_minor;
-	__le64 dataoff;
+	__le64 dataoff; /* relative to namespace_base + start_pad */
 	__le64 npfns;
 	__le32 mode;
-	u8 padding[4012];
+	/* minor-version-1 additions for section alignment */
+	__le32 start_pad;
+	__le32 end_trunc;
+	u8 padding[4004];
 	__le64 checksum;
 };
+
+#ifdef CONFIG_SPARSEMEM
+#define PFN_SECTION_ALIGN_DOWN(x) SECTION_ALIGN_DOWN(x)
+#define PFN_SECTION_ALIGN_UP(x) SECTION_ALIGN_UP(x)
+#else
+/*
+ * In this case ZONE_DEVICE=n and we will disable 'pfn' device support,
+ * but we still want pmem to compile.
+ */
+#define PFN_SECTION_ALIGN_DOWN(x) (x)
+#define PFN_SECTION_ALIGN_UP(x) (x)
+#endif
+
+#define PHYS_SECTION_ALIGN_DOWN(x) PFN_PHYS(PFN_SECTION_ALIGN_DOWN(PHYS_PFN(x)))
+#define PHYS_SECTION_ALIGN_UP(x) PFN_PHYS(PFN_SECTION_ALIGN_UP(PHYS_PFN(x)))
 #endif /* __NVDIMM_PFN_H */
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index ae81a2f1da50..254d3bc13f70 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -205,11 +205,67 @@ static ssize_t namespace_store(struct device *dev,
 }
 static DEVICE_ATTR_RW(namespace);
 
+static ssize_t resource_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	ssize_t rc;
+
+	device_lock(dev);
+	if (dev->driver) {
+		struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
+		u64 offset = __le64_to_cpu(pfn_sb->dataoff);
+		struct nd_namespace_common *ndns = nd_pfn->ndns;
+		u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
+		struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
+
+		rc = sprintf(buf, "%#llx\n", (unsigned long long) nsio->res.start
+				+ start_pad + offset);
+	} else {
+		/* no address to convey if the pfn instance is disabled */
+		rc = -ENXIO;
+	}
+	device_unlock(dev);
+
+	return rc;
+}
+static DEVICE_ATTR_RO(resource);
+
+static ssize_t size_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	ssize_t rc;
+
+	device_lock(dev);
+	if (dev->driver) {
+		struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
+		u64 offset = __le64_to_cpu(pfn_sb->dataoff);
+		struct nd_namespace_common *ndns = nd_pfn->ndns;
+		u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
+		u32 end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
+		struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
+
+		rc = sprintf(buf, "%llu\n", (unsigned long long)
+				resource_size(&nsio->res) - start_pad
+				- end_trunc - offset);
+	} else {
+		/* no size to convey if the pfn instance is disabled */
+		rc = -ENXIO;
+	}
+	device_unlock(dev);
+
+	return rc;
+}
+static DEVICE_ATTR_RO(size);
+
 static struct attribute *nd_pfn_attributes[] = {
 	&dev_attr_mode.attr,
 	&dev_attr_namespace.attr,
 	&dev_attr_uuid.attr,
 	&dev_attr_align.attr,
+	&dev_attr_resource.attr,
+	&dev_attr_size.attr,
 	NULL,
 };
 
@@ -299,6 +355,11 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn)
 	if (memcmp(pfn_sb->parent_uuid, parent_uuid, 16) != 0)
 		return -ENODEV;
 
+	if (__le16_to_cpu(pfn_sb->version_minor) < 1) {
+		pfn_sb->start_pad = 0;
+		pfn_sb->end_trunc = 0;
+	}
+
 	switch (le32_to_cpu(pfn_sb->mode)) {
 	case PFN_MODE_RAM:
 	case PFN_MODE_PMEM:
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 7edf31671dab..ca5721c306bb 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -41,14 +41,15 @@ struct pmem_device {
 	phys_addr_t		phys_addr;
 	/* when non-zero this device is hosting a 'pfn' instance */
 	phys_addr_t		data_offset;
-	unsigned long		pfn_flags;
+	u64			pfn_flags;
 	void __pmem		*virt_addr;
+	/* immutable base size of the namespace */
 	size_t			size;
+	/* trim size when namespace capacity has been section aligned */
+	u32			pfn_pad;
 	struct badblocks	bb;
 };
 
-static int pmem_major;
-
 static bool is_bad_pmem(struct badblocks *bb, sector_t sector, unsigned int len)
 {
 	if (bb->count) {
@@ -62,26 +63,56 @@ static bool is_bad_pmem(struct badblocks *bb, sector_t sector, unsigned int len)
 	return false;
 }
 
+static void pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset,
+		unsigned int len)
+{
+	struct device *dev = disk_to_dev(pmem->pmem_disk);
+	sector_t sector;
+	long cleared;
+
+	sector = (offset - pmem->data_offset) / 512;
+	cleared = nvdimm_clear_poison(dev, pmem->phys_addr + offset, len);
+
+	if (cleared > 0 && cleared / 512) {
+		dev_dbg(dev, "%s: %llx clear %ld sector%s\n",
+				__func__, (unsigned long long) sector,
+				cleared / 512, cleared / 512 > 1 ? "s" : "");
+		badblocks_clear(&pmem->bb, sector, cleared / 512);
+	}
+	invalidate_pmem(pmem->virt_addr + offset, len);
+}
+
 static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 			unsigned int len, unsigned int off, int rw,
 			sector_t sector)
 {
+	int rc = 0;
+	bool bad_pmem = false;
 	void *mem = kmap_atomic(page);
 	phys_addr_t pmem_off = sector * 512 + pmem->data_offset;
 	void __pmem *pmem_addr = pmem->virt_addr + pmem_off;
 
+	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
+		bad_pmem = true;
+
 	if (rw == READ) {
-		if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
-			return -EIO;
-		memcpy_from_pmem(mem + off, pmem_addr, len);
-		flush_dcache_page(page);
+		if (unlikely(bad_pmem))
+			rc = -EIO;
+		else {
+			memcpy_from_pmem(mem + off, pmem_addr, len);
+			flush_dcache_page(page);
+		}
 	} else {
 		flush_dcache_page(page);
 		memcpy_to_pmem(pmem_addr, mem + off, len);
+		if (unlikely(bad_pmem)) {
+			pmem_clear_poison(pmem, pmem_off, len);
+			memcpy_to_pmem(pmem_addr, mem + off, len);
+		}
 	}
 
 	kunmap_atomic(mem);
-	return 0;
+	return rc;
 }
 
 static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
@@ -145,7 +176,7 @@ static long pmem_direct_access(struct block_device *bdev, sector_t sector,
 	*kaddr = pmem->virt_addr + offset;
 	*pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);
 
-	return pmem->size - offset;
+	return pmem->size - pmem->pfn_pad - offset;
 }
 
 static const struct block_device_operations pmem_fops = {
@@ -228,15 +259,14 @@ static int pmem_attach_disk(struct device *dev,
 		return -ENOMEM;
 	}
 
-	disk->major		= pmem_major;
-	disk->first_minor	= 0;
 	disk->fops		= &pmem_fops;
 	disk->private_data	= pmem;
 	disk->queue		= pmem->pmem_queue;
 	disk->flags		= GENHD_FL_EXT_DEVT;
 	nvdimm_namespace_disk_name(ndns, disk->disk_name);
 	disk->driverfs_dev = dev;
-	set_capacity(disk, (pmem->size - pmem->data_offset) / 512);
+	set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset)
+			/ 512);
 	pmem->pmem_disk = disk;
 	devm_exit_badblocks(dev, &pmem->bb);
 	if (devm_init_badblocks(dev, &pmem->bb))
@@ -279,6 +309,9 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 	struct nd_pfn_sb *pfn_sb = kzalloc(sizeof(*pfn_sb), GFP_KERNEL);
 	struct pmem_device *pmem = dev_get_drvdata(&nd_pfn->dev);
 	struct nd_namespace_common *ndns = nd_pfn->ndns;
+	u32 start_pad = 0, end_trunc = 0;
+	resource_size_t start, size;
+	struct nd_namespace_io *nsio;
 	struct nd_region *nd_region;
 	unsigned long npfns;
 	phys_addr_t offset;
@@ -304,21 +337,56 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 	}
 
 	memset(pfn_sb, 0, sizeof(*pfn_sb));
-	npfns = (pmem->size - SZ_8K) / SZ_4K;
+
+	/*
+	 * Check if pmem collides with 'System RAM' when section aligned and
+	 * trim it accordingly
+	 */
+	nsio = to_nd_namespace_io(&ndns->dev);
+	start = PHYS_SECTION_ALIGN_DOWN(nsio->res.start);
+	size = resource_size(&nsio->res);
+	if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM,
+				IORES_DESC_NONE) == REGION_MIXED) {
+
+		start = nsio->res.start;
+		start_pad = PHYS_SECTION_ALIGN_UP(start) - start;
+	}
+
+	start = nsio->res.start;
+	size = PHYS_SECTION_ALIGN_UP(start + size) - start;
+	if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM,
+				IORES_DESC_NONE) == REGION_MIXED) {
+		size = resource_size(&nsio->res);
+		end_trunc = start + size - PHYS_SECTION_ALIGN_DOWN(start + size);
+	}
+
+	if (start_pad + end_trunc)
+		dev_info(&nd_pfn->dev, "%s section collision, truncate %d bytes\n",
+				dev_name(&ndns->dev), start_pad + end_trunc);
+
 	/*
 	 * Note, we use 64 here for the standard size of struct page,
 	 * debugging options may cause it to be larger in which case the
 	 * implementation will limit the pfns advertised through
 	 * ->direct_access() to those that are included in the memmap.
 	 */
+	start += start_pad;
+	npfns = (pmem->size - start_pad - end_trunc - SZ_8K) / SZ_4K;
 	if (nd_pfn->mode == PFN_MODE_PMEM)
-		offset = ALIGN(SZ_8K + 64 * npfns, nd_pfn->align);
+		offset = ALIGN(start + SZ_8K + 64 * npfns, nd_pfn->align)
+			- start;
 	else if (nd_pfn->mode == PFN_MODE_RAM)
-		offset = ALIGN(SZ_8K, nd_pfn->align);
+		offset = ALIGN(start + SZ_8K, nd_pfn->align) - start;
 	else
 		goto err;
 
-	npfns = (pmem->size - offset) / SZ_4K;
+	if (offset + start_pad + end_trunc >= pmem->size) {
+		dev_err(&nd_pfn->dev, "%s unable to satisfy requested alignment\n",
+				dev_name(&ndns->dev));
+		goto err;
+	}
+
+	npfns = (pmem->size - offset - start_pad - end_trunc) / SZ_4K;
 	pfn_sb->mode = cpu_to_le32(nd_pfn->mode);
 	pfn_sb->dataoff = cpu_to_le64(offset);
 	pfn_sb->npfns = cpu_to_le64(npfns);
@@ -326,6 +394,9 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 	memcpy(pfn_sb->uuid, nd_pfn->uuid, 16);
 	memcpy(pfn_sb->parent_uuid, nd_dev_to_uuid(&ndns->dev), 16);
 	pfn_sb->version_major = cpu_to_le16(1);
+	pfn_sb->version_minor = cpu_to_le16(1);
+	pfn_sb->start_pad = cpu_to_le32(start_pad);
+	pfn_sb->end_trunc = cpu_to_le32(end_trunc);
 	checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
 	pfn_sb->checksum = cpu_to_le64(checksum);
 
@@ -356,41 +427,56 @@ static int nvdimm_namespace_detach_pfn(struct nd_namespace_common *ndns)
 	return 0;
 }
 
-static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
+/*
+ * We hotplug memory at section granularity, pad the reserved area from
+ * the previous section base to the namespace base address.
+ */
+static unsigned long init_altmap_base(resource_size_t base)
+{
+	unsigned long base_pfn = PHYS_PFN(base);
+
+	return PFN_SECTION_ALIGN_DOWN(base_pfn);
+}
+
+static unsigned long init_altmap_reserve(resource_size_t base)
+{
+	unsigned long reserve = PHYS_PFN(SZ_8K);
+	unsigned long base_pfn = PHYS_PFN(base);
+
+	reserve += base_pfn - PFN_SECTION_ALIGN_DOWN(base_pfn);
+	return reserve;
+}
+
+static int __nvdimm_namespace_attach_pfn(struct nd_pfn *nd_pfn)
 {
-	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
-	struct nd_pfn *nd_pfn = to_nd_pfn(ndns->claim);
-	struct device *dev = &nd_pfn->dev;
-	struct nd_region *nd_region;
-	struct vmem_altmap *altmap;
-	struct nd_pfn_sb *pfn_sb;
-	struct pmem_device *pmem;
-	struct request_queue *q;
-	phys_addr_t offset;
 	int rc;
+	struct resource res;
+	struct request_queue *q;
+	struct pmem_device *pmem;
+	struct vmem_altmap *altmap;
+	struct device *dev = &nd_pfn->dev;
+	struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
+	struct nd_namespace_common *ndns = nd_pfn->ndns;
+	u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
+	u32 end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
+	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
+	resource_size_t base = nsio->res.start + start_pad;
 	struct vmem_altmap __altmap = {
-		.base_pfn = __phys_to_pfn(nsio->res.start),
-		.reserve = __phys_to_pfn(SZ_8K),
+		.base_pfn = init_altmap_base(base),
+		.reserve = init_altmap_reserve(base),
 	};
 
-	if (!nd_pfn->uuid || !nd_pfn->ndns)
-		return -ENODEV;
-
-	nd_region = to_nd_region(dev->parent);
-	rc = nd_pfn_init(nd_pfn);
-	if (rc)
-		return rc;
-
-	pfn_sb = nd_pfn->pfn_sb;
-	offset = le64_to_cpu(pfn_sb->dataoff);
+	pmem = dev_get_drvdata(dev);
+	pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
+	pmem->pfn_pad = start_pad + end_trunc;
 	nd_pfn->mode = le32_to_cpu(nd_pfn->pfn_sb->mode);
 	if (nd_pfn->mode == PFN_MODE_RAM) {
-		if (offset < SZ_8K)
+		if (pmem->data_offset < SZ_8K)
 			return -EINVAL;
 		nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
 		altmap = NULL;
 	} else if (nd_pfn->mode == PFN_MODE_PMEM) {
-		nd_pfn->npfns = (resource_size(&nsio->res) - offset)
+		nd_pfn->npfns = (pmem->size - pmem->pfn_pad - pmem->data_offset)
 			/ PAGE_SIZE;
 		if (le64_to_cpu(nd_pfn->pfn_sb->npfns) > nd_pfn->npfns)
 			dev_info(&nd_pfn->dev,
@@ -398,7 +484,7 @@ static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
 					le64_to_cpu(nd_pfn->pfn_sb->npfns),
 					nd_pfn->npfns);
 		altmap = & __altmap;
-		altmap->free = __phys_to_pfn(offset - SZ_8K);
+		altmap->free = PHYS_PFN(pmem->data_offset - SZ_8K);
 		altmap->alloc = 0;
 	} else {
 		rc = -ENXIO;
@@ -406,10 +492,12 @@ static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
 	}
 
 	/* establish pfn range for lookup, and switch to direct map */
-	pmem = dev_get_drvdata(dev);
 	q = pmem->pmem_queue;
+	memcpy(&res, &nsio->res, sizeof(res));
+	res.start += start_pad;
+	res.end -= end_trunc;
 	devm_memunmap(dev, (void __force *) pmem->virt_addr);
-	pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, &nsio->res,
+	pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, &res,
 			&q->q_usage_counter, altmap);
 	pmem->pfn_flags |= PFN_MAP;
 	if (IS_ERR(pmem->virt_addr)) {
@@ -418,7 +506,6 @@ static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
 	}
 
 	/* attach pmem disk in "pfn-mode" */
-	pmem->data_offset = offset;
 	rc = pmem_attach_disk(dev, ndns, pmem);
 	if (rc)
 		goto err;
@@ -427,6 +514,22 @@ static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
  err:
 	nvdimm_namespace_detach_pfn(ndns);
 	return rc;
+
+}
+
+static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
+{
+	struct nd_pfn *nd_pfn = to_nd_pfn(ndns->claim);
+	int rc;
+
+	if (!nd_pfn->uuid || !nd_pfn->ndns)
+		return -ENODEV;
+
+	rc = nd_pfn_init(nd_pfn);
+	if (rc)
+		return rc;
+	/* we need a valid pfn_sb before we can init a vmem_altmap */
+	return __nvdimm_namespace_attach_pfn(nd_pfn);
 }
 
 static int nd_pmem_probe(struct device *dev)
@@ -488,12 +591,27 @@ static int nd_pmem_remove(struct device *dev)
 	return 0;
 }
 
+static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
+{
+	struct pmem_device *pmem = dev_get_drvdata(dev);
+	struct nd_namespace_common *ndns = pmem->ndns;
+
+	if (event != NVDIMM_REVALIDATE_POISON)
+		return;
+
+	if (is_nd_btt(dev))
+		nvdimm_namespace_add_poison(ndns, &pmem->bb, 0);
+	else
+		nvdimm_namespace_add_poison(ndns, &pmem->bb, pmem->data_offset);
+}
+
 MODULE_ALIAS("pmem");
 MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_IO);
 MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_PMEM);
 static struct nd_device_driver nd_pmem_driver = {
 	.probe = nd_pmem_probe,
 	.remove = nd_pmem_remove,
+	.notify = nd_pmem_notify,
 	.drv = {
 		.name = "nd_pmem",
 	},
@@ -502,26 +620,13 @@ static struct nd_device_driver nd_pmem_driver = {
 
 static int __init pmem_init(void)
 {
-	int error;
-
-	pmem_major = register_blkdev(0, "pmem");
-	if (pmem_major < 0)
-		return pmem_major;
-
-	error = nd_driver_register(&nd_pmem_driver);
-	if (error) {
-		unregister_blkdev(pmem_major, "pmem");
-		return error;
-	}
-
-	return 0;
+	return nd_driver_register(&nd_pmem_driver);
 }
 module_init(pmem_init);
 
 static void pmem_exit(void)
 {
 	driver_unregister(&nd_pmem_driver.drv);
-	unregister_blkdev(pmem_major, "pmem");
 }
 module_exit(pmem_exit);
 
diff --git a/drivers/nvdimm/region.c b/drivers/nvdimm/region.c
index 7da63eac78ee..4b7715e29cff 100644
--- a/drivers/nvdimm/region.c
+++ b/drivers/nvdimm/region.c
@@ -93,9 +93,21 @@ static int nd_region_remove(struct device *dev)
 	return 0;
 }
 
+static int child_notify(struct device *dev, void *data)
+{
+	nd_device_notify(dev, *(enum nvdimm_event *) data);
+	return 0;
+}
+
+static void nd_region_notify(struct device *dev, enum nvdimm_event event)
+{
+	device_for_each_child(dev, &event, child_notify);
+}
+
 static struct nd_device_driver nd_region_driver = {
 	.probe = nd_region_probe,
 	.remove = nd_region_remove,
+	.notify = nd_region_notify,
 	.drv = {
 		.name = "nd_region",
 	},
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index 5d6237391dcd..b586d84f2518 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -17,5 +17,6 @@ config BLK_DEV_NVME_SCSI
 	  and block devices nodes, as well a a translation for a small
 	  number of selected SCSI commands to NVMe commands to the NVMe
 	  driver.  If you don't know what this means you probably want
-	  to say N here, and if you know what it means you probably
-	  want to say N as well.
+	  to say N here, unless you run a distro that abuses the SCSI
+	  emulation to provide stable device names for mount by id, like
+	  some OpenSuSE and SLES versions.
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index c5bf001af559..03c46412fff4 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -55,8 +55,9 @@ static void nvme_free_ns(struct kref *kref)
 	ns->disk->private_data = NULL;
 	spin_unlock(&dev_list_lock);
 
-	nvme_put_ctrl(ns->ctrl);
 	put_disk(ns->disk);
+	ida_simple_remove(&ns->ctrl->ns_ida, ns->instance);
+	nvme_put_ctrl(ns->ctrl);
 	kfree(ns);
 }
 
@@ -183,7 +184,7 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
 			goto out_unmap;
 		}
 
-		if (meta_buffer) {
+		if (meta_buffer && meta_len) {
 			struct bio_integrity_payload *bip;
 
 			meta = kmalloc(meta_len, GFP_KERNEL);
@@ -373,6 +374,8 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 
 	if (copy_from_user(&io, uio, sizeof(io)))
 		return -EFAULT;
+	if (io.flags)
+		return -EINVAL;
 
 	switch (io.opcode) {
 	case nvme_cmd_write:
@@ -424,6 +427,8 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 		return -EACCES;
 	if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
 		return -EFAULT;
+	if (cmd.flags)
+		return -EINVAL;
 
 	memset(&c, 0, sizeof(c));
 	c.common.opcode = cmd.opcode;
@@ -556,6 +561,10 @@ static int nvme_revalidate_disk(struct gendisk *disk)
 	u16 old_ms;
 	unsigned short bs;
 
+	if (test_bit(NVME_NS_DEAD, &ns->flags)) {
+		set_capacity(disk, 0);
+		return -ENODEV;
+	}
 	if (nvme_identify_ns(ns->ctrl, ns->ns_id, &id)) {
 		dev_warn(ns->ctrl->dev, "%s: Identify failure nvme%dn%d\n",
 				__func__, ns->ctrl->instance, ns->ns_id);
@@ -831,6 +840,23 @@ int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl)
 	return ret;
 }
 
+static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
+		struct request_queue *q)
+{
+	if (ctrl->max_hw_sectors) {
+		u32 max_segments =
+			(ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1;
+
+		blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors);
+		blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
+	}
+	if (ctrl->stripe_size)
+		blk_queue_chunk_sectors(q, ctrl->stripe_size >> 9);
+	if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
+		blk_queue_flush(q, REQ_FLUSH | REQ_FUA);
+	blk_queue_virt_boundary(q, ctrl->page_size - 1);
+}
+
 /*
  * Initialize the cached copies of the Identify data and various controller
  * register in our nvme_ctrl structure.  This should be called as soon as
@@ -888,6 +914,8 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		}
 	}
 
+	nvme_set_queue_limits(ctrl, ctrl->admin_q);
+
 	kfree(id);
 	return 0;
 }
@@ -1118,10 +1146,13 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	if (!ns)
 		return;
 
+	ns->instance = ida_simple_get(&ctrl->ns_ida, 1, 0, GFP_KERNEL);
+	if (ns->instance < 0)
+		goto out_free_ns;
+
 	ns->queue = blk_mq_init_queue(ctrl->tagset);
 	if (IS_ERR(ns->queue))
-		goto out_free_ns;
-	queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, ns->queue);
+		goto out_release_instance;
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue);
 	ns->queue->queuedata = ns;
 	ns->ctrl = ctrl;
@@ -1135,17 +1166,9 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	ns->disk = disk;
 	ns->lba_shift = 9; /* set to a default value for 512 until disk is validated */
 
+
 	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
-	if (ctrl->max_hw_sectors) {
-		blk_queue_max_hw_sectors(ns->queue, ctrl->max_hw_sectors);
-		blk_queue_max_segments(ns->queue,
-			(ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1);
-	}
-	if (ctrl->stripe_size)
-		blk_queue_chunk_sectors(ns->queue, ctrl->stripe_size >> 9);
-	if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
-		blk_queue_flush(ns->queue, REQ_FLUSH | REQ_FUA);
-	blk_queue_virt_boundary(ns->queue, ctrl->page_size - 1);
+	nvme_set_queue_limits(ctrl, ns->queue);
 
 	disk->major = nvme_major;
 	disk->first_minor = 0;
@@ -1154,7 +1177,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	disk->queue = ns->queue;
 	disk->driverfs_dev = ctrl->device;
 	disk->flags = GENHD_FL_EXT_DEVT;
-	sprintf(disk->disk_name, "nvme%dn%d", ctrl->instance, nsid);
+	sprintf(disk->disk_name, "nvme%dn%d", ctrl->instance, ns->instance);
 
 	if (nvme_revalidate_disk(ns->disk))
 		goto out_free_disk;
@@ -1174,40 +1197,29 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	kfree(disk);
  out_free_queue:
 	blk_cleanup_queue(ns->queue);
+ out_release_instance:
+	ida_simple_remove(&ctrl->ns_ida, ns->instance);
  out_free_ns:
 	kfree(ns);
 }
 
 static void nvme_ns_remove(struct nvme_ns *ns)
 {
-	bool kill = nvme_io_incapable(ns->ctrl) &&
-			!blk_queue_dying(ns->queue);
-
-	lockdep_assert_held(&ns->ctrl->namespaces_mutex);
-
-	if (kill) {
-		blk_set_queue_dying(ns->queue);
+	if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
+		return;
 
-		/*
-		 * The controller was shutdown first if we got here through
-		 * device removal. The shutdown may requeue outstanding
-		 * requests. These need to be aborted immediately so
-		 * del_gendisk doesn't block indefinitely for their completion.
-		 */
-		blk_mq_abort_requeue_list(ns->queue);
-	}
 	if (ns->disk->flags & GENHD_FL_UP) {
 		if (blk_get_integrity(ns->disk))
 			blk_integrity_unregister(ns->disk);
 		sysfs_remove_group(&disk_to_dev(ns->disk)->kobj,
 					&nvme_ns_attr_group);
 		del_gendisk(ns->disk);
-	}
-	if (kill || !blk_queue_dying(ns->queue)) {
 		blk_mq_abort_requeue_list(ns->queue);
 		blk_cleanup_queue(ns->queue);
 	}
+	mutex_lock(&ns->ctrl->namespaces_mutex);
 	list_del_init(&ns->list);
+	mutex_unlock(&ns->ctrl->namespaces_mutex);
 	nvme_put_ns(ns);
 }
 
@@ -1301,10 +1313,8 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns, *next;
 
-	mutex_lock(&ctrl->namespaces_mutex);
 	list_for_each_entry_safe(ns, next, &ctrl->namespaces, list)
 		nvme_ns_remove(ns);
-	mutex_unlock(&ctrl->namespaces_mutex);
 }
 
 static DEFINE_IDA(nvme_instance_ida);
@@ -1351,6 +1361,7 @@ static void nvme_free_ctrl(struct kref *kref)
 
 	put_device(ctrl->device);
 	nvme_release_instance(ctrl);
+	ida_destroy(&ctrl->ns_ida);
 
 	ctrl->ops->free_ctrl(ctrl);
 }
@@ -1391,6 +1402,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	}
 	get_device(ctrl->device);
 	dev_set_drvdata(ctrl->device, ctrl);
+	ida_init(&ctrl->ns_ida);
 
 	spin_lock(&dev_list_lock);
 	list_add_tail(&ctrl->node, &nvme_ctrl_list);
@@ -1403,6 +1415,38 @@ out:
 	return ret;
 }
 
+/**
+ * nvme_kill_queues(): Ends all namespace queues
+ * @ctrl: the dead controller that needs to end
+ *
+ * Call this function when the driver determines it is unable to get the
+ * controller in a state capable of servicing IO.
+ */
+void nvme_kill_queues(struct nvme_ctrl *ctrl)
+{
+	struct nvme_ns *ns;
+
+	mutex_lock(&ctrl->namespaces_mutex);
+	list_for_each_entry(ns, &ctrl->namespaces, list) {
+		if (!kref_get_unless_zero(&ns->kref))
+			continue;
+
+		/*
+		 * Revalidating a dead namespace sets capacity to 0. This will
+		 * end buffered writers dirtying pages that can't be synced.
+		 */
+		if (!test_and_set_bit(NVME_NS_DEAD, &ns->flags))
+			revalidate_disk(ns->disk);
+
+		blk_set_queue_dying(ns->queue);
+		blk_mq_abort_requeue_list(ns->queue);
+		blk_mq_start_stopped_hw_queues(ns->queue, true);
+
+		nvme_put_ns(ns);
+	}
+	mutex_unlock(&ctrl->namespaces_mutex);
+}
+
 void nvme_stop_queues(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 5cd3725e2fa4..6bb15e4926dc 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -146,9 +146,10 @@ struct nvme_nvm_command {
 	};
 };
 
+#define NVME_NVM_LP_MLC_PAIRS 886
 struct nvme_nvm_lp_mlc {
 	__u16			num_pairs;
-	__u8			pairs[886];
+	__u8			pairs[NVME_NVM_LP_MLC_PAIRS];
 };
 
 struct nvme_nvm_lp_tbl {
@@ -282,9 +283,14 @@ static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id)
 			memcpy(dst->lptbl.id, src->lptbl.id, 8);
 			dst->lptbl.mlc.num_pairs =
 					le16_to_cpu(src->lptbl.mlc.num_pairs);
-			/* 4 bits per pair */
+
+			if (dst->lptbl.mlc.num_pairs > NVME_NVM_LP_MLC_PAIRS) {
+				pr_err("nvm: number of MLC pairs not supported\n");
+				return -EINVAL;
+			}
+
 			memcpy(dst->lptbl.mlc.pairs, src->lptbl.mlc.pairs,
-						dst->lptbl.mlc.num_pairs >> 1);
+						dst->lptbl.mlc.num_pairs);
 		}
 	}
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 4fb5bb737868..fb15ba5f5d19 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -72,6 +72,7 @@ struct nvme_ctrl {
 	struct mutex namespaces_mutex;
 	struct device *device;	/* char device */
 	struct list_head node;
+	struct ida ns_ida;
 
 	char name[12];
 	char serial[20];
@@ -102,6 +103,7 @@ struct nvme_ns {
 	struct request_queue *queue;
 	struct gendisk *disk;
 	struct kref kref;
+	int instance;
 
 	u8 eui[8];
 	u8 uuid[16];
@@ -112,6 +114,11 @@ struct nvme_ns {
 	bool ext;
 	u8 pi_type;
 	int type;
+	unsigned long flags;
+
+#define NVME_NS_REMOVING 0
+#define NVME_NS_DEAD     1
+
 	u64 mode_select_num_blocks;
 	u32 mode_select_block_len;
 };
@@ -139,9 +146,9 @@ static inline bool nvme_io_incapable(struct nvme_ctrl *ctrl)
 	u32 val = 0;
 
 	if (ctrl->ops->io_incapable(ctrl))
-		return false;
+		return true;
 	if (ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &val))
-		return false;
+		return true;
 	return val & NVME_CSTS_CFS;
 }
 
@@ -240,6 +247,7 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl);
 
 void nvme_stop_queues(struct nvme_ctrl *ctrl);
 void nvme_start_queues(struct nvme_ctrl *ctrl);
+void nvme_kill_queues(struct nvme_ctrl *ctrl);
 
 struct request *nvme_alloc_request(struct request_queue *q,
 		struct nvme_command *cmd, unsigned int flags);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 72ef8322d32a..680f5780750c 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -86,7 +86,6 @@ struct nvme_queue;
 
 static int nvme_reset(struct nvme_dev *dev);
 static void nvme_process_cq(struct nvme_queue *nvmeq);
-static void nvme_remove_dead_ctrl(struct nvme_dev *dev);
 static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown);
 
 /*
@@ -120,6 +119,7 @@ struct nvme_dev {
 	unsigned long flags;
 
 #define NVME_CTRL_RESETTING    0
+#define NVME_CTRL_REMOVING     1
 
 	struct nvme_ctrl ctrl;
 	struct completion ioq_wait;
@@ -286,6 +286,17 @@ static int nvme_init_request(void *data, struct request *req,
 	return 0;
 }
 
+static void nvme_queue_scan(struct nvme_dev *dev)
+{
+	/*
+	 * Do not queue new scan work when a controller is reset during
+	 * removal.
+	 */
+	if (test_bit(NVME_CTRL_REMOVING, &dev->flags))
+		return;
+	queue_work(nvme_workq, &dev->scan_work);
+}
+
 static void nvme_complete_async_event(struct nvme_dev *dev,
 		struct nvme_completion *cqe)
 {
@@ -300,7 +311,7 @@ static void nvme_complete_async_event(struct nvme_dev *dev,
 	switch (result & 0xff07) {
 	case NVME_AER_NOTICE_NS_CHANGED:
 		dev_info(dev->dev, "rescanning\n");
-		queue_work(nvme_workq, &dev->scan_work);
+		nvme_queue_scan(dev);
 	default:
 		dev_warn(dev->dev, "async event result %08x\n", result);
 	}
@@ -678,6 +689,14 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	blk_mq_start_request(req);
 
 	spin_lock_irq(&nvmeq->q_lock);
+	if (unlikely(nvmeq->cq_vector < 0)) {
+		if (ns && !test_bit(NVME_NS_DEAD, &ns->flags))
+			ret = BLK_MQ_RQ_QUEUE_BUSY;
+		else
+			ret = BLK_MQ_RQ_QUEUE_ERROR;
+		spin_unlock_irq(&nvmeq->q_lock);
+		goto out;
+	}
 	__nvme_submit_cmd(nvmeq, &cmnd);
 	nvme_process_cq(nvmeq);
 	spin_unlock_irq(&nvmeq->q_lock);
@@ -999,7 +1018,7 @@ static void nvme_cancel_queue_ios(struct request *req, void *data, bool reserved
 	if (!blk_mq_request_started(req))
 		return;
 
-	dev_warn(nvmeq->q_dmadev,
+	dev_dbg_ratelimited(nvmeq->q_dmadev,
 		 "Cancelling I/O %d QID %d\n", req->tag, nvmeq->qid);
 
 	status = NVME_SC_ABORT_REQ;
@@ -1245,6 +1264,12 @@ static struct blk_mq_ops nvme_mq_ops = {
 static void nvme_dev_remove_admin(struct nvme_dev *dev)
 {
 	if (dev->ctrl.admin_q && !blk_queue_dying(dev->ctrl.admin_q)) {
+		/*
+		 * If the controller was reset during removal, it's possible
+		 * user requests may be waiting on a stopped queue. Start the
+		 * queue to flush these to completion.
+		 */
+		blk_mq_start_stopped_hw_queues(dev->ctrl.admin_q, true);
 		blk_cleanup_queue(dev->ctrl.admin_q);
 		blk_mq_free_tag_set(&dev->admin_tagset);
 	}
@@ -1685,14 +1710,14 @@ static int nvme_dev_add(struct nvme_dev *dev)
 			return 0;
 		dev->ctrl.tagset = &dev->tagset;
 	}
-	queue_work(nvme_workq, &dev->scan_work);
+	nvme_queue_scan(dev);
 	return 0;
 }
 
-static int nvme_dev_map(struct nvme_dev *dev)
+static int nvme_pci_enable(struct nvme_dev *dev)
 {
 	u64 cap;
-	int bars, result = -ENOMEM;
+	int result = -ENOMEM;
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
 	if (pci_enable_device_mem(pdev))
@@ -1700,24 +1725,14 @@ static int nvme_dev_map(struct nvme_dev *dev)
 
 	dev->entry[0].vector = pdev->irq;
 	pci_set_master(pdev);
-	bars = pci_select_bars(pdev, IORESOURCE_MEM);
-	if (!bars)
-		goto disable_pci;
-
-	if (pci_request_selected_regions(pdev, bars, "nvme"))
-		goto disable_pci;
 
 	if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)) &&
 	    dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(32)))
 		goto disable;
 
-	dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
-	if (!dev->bar)
-		goto disable;
-
 	if (readl(dev->bar + NVME_REG_CSTS) == -1) {
 		result = -ENODEV;
-		goto unmap;
+		goto disable;
 	}
 
 	/*
@@ -1727,7 +1742,7 @@ static int nvme_dev_map(struct nvme_dev *dev)
 	if (!pdev->irq) {
 		result = pci_enable_msix(pdev, dev->entry, 1);
 		if (result < 0)
-			goto unmap;
+			goto disable;
 	}
 
 	cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
@@ -1754,18 +1769,20 @@ static int nvme_dev_map(struct nvme_dev *dev)
 	pci_save_state(pdev);
 	return 0;
 
- unmap:
-	iounmap(dev->bar);
-	dev->bar = NULL;
  disable:
-	pci_release_regions(pdev);
- disable_pci:
 	pci_disable_device(pdev);
 	return result;
 }
 
 static void nvme_dev_unmap(struct nvme_dev *dev)
 {
+	if (dev->bar)
+		iounmap(dev->bar);
+	pci_release_regions(to_pci_dev(dev->dev));
+}
+
+static void nvme_pci_disable(struct nvme_dev *dev)
+{
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
 	if (pdev->msi_enabled)
@@ -1773,12 +1790,6 @@ static void nvme_dev_unmap(struct nvme_dev *dev)
 	else if (pdev->msix_enabled)
 		pci_disable_msix(pdev);
 
-	if (dev->bar) {
-		iounmap(dev->bar);
-		dev->bar = NULL;
-		pci_release_regions(pdev);
-	}
-
 	if (pci_is_enabled(pdev)) {
 		pci_disable_pcie_error_reporting(pdev);
 		pci_disable_device(pdev);
@@ -1837,7 +1848,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 	nvme_dev_list_remove(dev);
 
 	mutex_lock(&dev->shutdown_lock);
-	if (dev->bar) {
+	if (pci_is_enabled(to_pci_dev(dev->dev))) {
 		nvme_stop_queues(&dev->ctrl);
 		csts = readl(dev->bar + NVME_REG_CSTS);
 	}
@@ -1850,7 +1861,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 		nvme_disable_io_queues(dev);
 		nvme_disable_admin_queue(dev, shutdown);
 	}
-	nvme_dev_unmap(dev);
+	nvme_pci_disable(dev);
 
 	for (i = dev->queue_count - 1; i >= 0; i--)
 		nvme_clear_queue(dev->queues[i]);
@@ -1894,10 +1905,20 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
 	kfree(dev);
 }
 
+static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status)
+{
+	dev_warn(dev->dev, "Removing after probe failure status: %d\n", status);
+
+	kref_get(&dev->ctrl.kref);
+	nvme_dev_disable(dev, false);
+	if (!schedule_work(&dev->remove_work))
+		nvme_put_ctrl(&dev->ctrl);
+}
+
 static void nvme_reset_work(struct work_struct *work)
 {
 	struct nvme_dev *dev = container_of(work, struct nvme_dev, reset_work);
-	int result;
+	int result = -ENODEV;
 
 	if (WARN_ON(test_bit(NVME_CTRL_RESETTING, &dev->flags)))
 		goto out;
@@ -1906,37 +1927,37 @@ static void nvme_reset_work(struct work_struct *work)
 	 * If we're called to reset a live controller first shut it down before
 	 * moving on.
 	 */
-	if (dev->bar)
+	if (dev->ctrl.ctrl_config & NVME_CC_ENABLE)
 		nvme_dev_disable(dev, false);
 
 	set_bit(NVME_CTRL_RESETTING, &dev->flags);
 
-	result = nvme_dev_map(dev);
+	result = nvme_pci_enable(dev);
 	if (result)
 		goto out;
 
 	result = nvme_configure_admin_queue(dev);
 	if (result)
-		goto unmap;
+		goto out;
 
 	nvme_init_queue(dev->queues[0], 0);
 	result = nvme_alloc_admin_tags(dev);
 	if (result)
-		goto disable;
+		goto out;
 
 	result = nvme_init_identify(&dev->ctrl);
 	if (result)
-		goto free_tags;
+		goto out;
 
 	result = nvme_setup_io_queues(dev);
 	if (result)
-		goto free_tags;
+		goto out;
 
 	dev->ctrl.event_limit = NVME_NR_AEN_COMMANDS;
 
 	result = nvme_dev_list_add(dev);
 	if (result)
-		goto remove;
+		goto out;
 
 	/*
 	 * Keep the controller around but remove all namespaces if we don't have
@@ -1953,19 +1974,8 @@ static void nvme_reset_work(struct work_struct *work)
 	clear_bit(NVME_CTRL_RESETTING, &dev->flags);
 	return;
 
- remove:
-	nvme_dev_list_remove(dev);
- free_tags:
-	nvme_dev_remove_admin(dev);
-	blk_put_queue(dev->ctrl.admin_q);
-	dev->ctrl.admin_q = NULL;
-	dev->queues[0]->tags = NULL;
- disable:
-	nvme_disable_admin_queue(dev, false);
- unmap:
-	nvme_dev_unmap(dev);
  out:
-	nvme_remove_dead_ctrl(dev);
+	nvme_remove_dead_ctrl(dev, result);
 }
 
 static void nvme_remove_dead_ctrl_work(struct work_struct *work)
@@ -1973,19 +1983,12 @@ static void nvme_remove_dead_ctrl_work(struct work_struct *work)
 	struct nvme_dev *dev = container_of(work, struct nvme_dev, remove_work);
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
+	nvme_kill_queues(&dev->ctrl);
 	if (pci_get_drvdata(pdev))
 		pci_stop_and_remove_bus_device_locked(pdev);
 	nvme_put_ctrl(&dev->ctrl);
 }
 
-static void nvme_remove_dead_ctrl(struct nvme_dev *dev)
-{
-	dev_warn(dev->dev, "Removing after probe failure\n");
-	kref_get(&dev->ctrl.kref);
-	if (!schedule_work(&dev->remove_work))
-		nvme_put_ctrl(&dev->ctrl);
-}
-
 static int nvme_reset(struct nvme_dev *dev)
 {
 	if (!dev->ctrl.admin_q || blk_queue_dying(dev->ctrl.admin_q))
@@ -2037,6 +2040,27 @@ static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
 	.free_ctrl		= nvme_pci_free_ctrl,
 };
 
+static int nvme_dev_map(struct nvme_dev *dev)
+{
+	int bars;
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
+
+	bars = pci_select_bars(pdev, IORESOURCE_MEM);
+	if (!bars)
+		return -ENODEV;
+	if (pci_request_selected_regions(pdev, bars, "nvme"))
+		return -ENODEV;
+
+	dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
+	if (!dev->bar)
+		goto release;
+
+       return 0;
+  release:
+       pci_release_regions(pdev);
+       return -ENODEV;
+}
+
 static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	int node, result = -ENOMEM;
@@ -2061,6 +2085,10 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	dev->dev = get_device(&pdev->dev);
 	pci_set_drvdata(pdev, dev);
 
+	result = nvme_dev_map(dev);
+	if (result)
+		goto free;
+
 	INIT_LIST_HEAD(&dev->node);
 	INIT_WORK(&dev->scan_work, nvme_dev_scan);
 	INIT_WORK(&dev->reset_work, nvme_reset_work);
@@ -2084,6 +2112,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	nvme_release_prp_pools(dev);
  put_pci:
 	put_device(dev->dev);
+	nvme_dev_unmap(dev);
  free:
 	kfree(dev->queues);
 	kfree(dev->entry);
@@ -2107,24 +2136,27 @@ static void nvme_shutdown(struct pci_dev *pdev)
 	nvme_dev_disable(dev, true);
 }
 
+/*
+ * The driver's remove may be called on a device in a partially initialized
+ * state. This function must not have any dependencies on the device state in
+ * order to proceed.
+ */
 static void nvme_remove(struct pci_dev *pdev)
 {
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
 
-	spin_lock(&dev_list_lock);
-	list_del_init(&dev->node);
-	spin_unlock(&dev_list_lock);
-
+	set_bit(NVME_CTRL_REMOVING, &dev->flags);
 	pci_set_drvdata(pdev, NULL);
-	flush_work(&dev->reset_work);
 	flush_work(&dev->scan_work);
 	nvme_remove_namespaces(&dev->ctrl);
 	nvme_uninit_ctrl(&dev->ctrl);
 	nvme_dev_disable(dev, true);
+	flush_work(&dev->reset_work);
 	nvme_dev_remove_admin(dev);
 	nvme_free_queues(dev, 0);
 	nvme_release_cmb(dev);
 	nvme_release_prp_pools(dev);
+	nvme_dev_unmap(dev);
 	nvme_put_ctrl(&dev->ctrl);
 }
 
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index 6fd4e5a5ef4a..9d11d9837312 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -70,6 +70,9 @@ static ssize_t bin_attr_nvmem_read(struct file *filp, struct kobject *kobj,
 	if (pos >= nvmem->size)
 		return 0;
 
+	if (count < nvmem->word_size)
+		return -EINVAL;
+
 	if (pos + count > nvmem->size)
 		count = nvmem->size - pos;
 
@@ -95,6 +98,9 @@ static ssize_t bin_attr_nvmem_write(struct file *filp, struct kobject *kobj,
 	if (pos >= nvmem->size)
 		return 0;
 
+	if (count < nvmem->word_size)
+		return -EINVAL;
+
 	if (pos + count > nvmem->size)
 		count = nvmem->size - pos;
 
diff --git a/drivers/nvmem/qfprom.c b/drivers/nvmem/qfprom.c
index afb67e7eeee4..3829e5fbf8c3 100644
--- a/drivers/nvmem/qfprom.c
+++ b/drivers/nvmem/qfprom.c
@@ -21,6 +21,7 @@ static struct regmap_config qfprom_regmap_config = {
 	.reg_bits = 32,
 	.val_bits = 8,
 	.reg_stride = 1,
+	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 static struct nvmem_config econfig = {
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 7ee21ae305ae..e7bfc175b8e1 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -635,6 +635,13 @@ static u32 __of_msi_map_rid(struct device *dev, struct device_node **np,
 		msi_base = be32_to_cpup(msi_map + 2);
 		rid_len = be32_to_cpup(msi_map + 3);
 
+		if (rid_base & ~map_mask) {
+			dev_err(parent_dev,
+				"Invalid msi-map translation - msi-map-mask (0x%x) ignores rid-base (0x%x)\n",
+				map_mask, rid_base);
+			return rid_out;
+		}
+
 		msi_controller_node = of_find_node_by_phandle(phandle);
 
 		matched = (masked_rid >= rid_base &&
@@ -654,7 +661,7 @@ static u32 __of_msi_map_rid(struct device *dev, struct device_node **np,
 	if (!matched)
 		return rid_out;
 
-	rid_out = masked_rid + msi_base;
+	rid_out = masked_rid - rid_base + msi_base;
 	dev_dbg(dev,
 		"msi-map at: %s, using mask %08x, rid-base: %08x, msi-base: %08x, length: %08x, rid: %08x -> %08x\n",
 		dev_name(parent_dev), map_mask, rid_base, msi_base,
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index 5648317d355f..365dc7e83ab4 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -154,6 +154,7 @@ static const struct of_device_id whitelist_phys[] = {
 	{ .compatible = "marvell,88E1111", },
 	{ .compatible = "marvell,88e1116", },
 	{ .compatible = "marvell,88e1118", },
+	{ .compatible = "marvell,88e1145", },
 	{ .compatible = "marvell,88e1149r", },
 	{ .compatible = "marvell,88e1310", },
 	{ .compatible = "marvell,88E1510", },
@@ -304,6 +305,7 @@ EXPORT_SYMBOL(of_phy_find_device);
  * @dev: pointer to net_device claiming the phy
  * @phy_np: Pointer to device tree node for the PHY
  * @hndlr: Link state callback for the network device
+ * @flags: flags to pass to the PHY
  * @iface: PHY data interface type
  *
  * If successful, returns a pointer to the phy_device with the embedded
diff --git a/drivers/of/of_pci.c b/drivers/of/of_pci.c
index b1449f71601c..13f4fed38048 100644
--- a/drivers/of/of_pci.c
+++ b/drivers/of/of_pci.c
@@ -5,7 +5,6 @@
 #include <linux/of_device.h>
 #include <linux/of_pci.h>
 #include <linux/slab.h>
-#include <asm-generic/pci-bridge.h>
 
 static inline int __of_pci_pci_compare(struct device_node *node,
 				       unsigned int data)
diff --git a/drivers/parisc/Kconfig b/drivers/parisc/Kconfig
index 592de566e72f..3a102a84d637 100644
--- a/drivers/parisc/Kconfig
+++ b/drivers/parisc/Kconfig
@@ -110,8 +110,6 @@ config IOMMU_HELPER
 
 source "drivers/pcmcia/Kconfig"
 
-source "drivers/pci/hotplug/Kconfig"
-
 endmenu
 
 menu "PA-RISC specific drivers"
diff --git a/drivers/parisc/eisa_enumerator.c b/drivers/parisc/eisa_enumerator.c
index a656d9e83343..21905fef2cbf 100644
--- a/drivers/parisc/eisa_enumerator.c
+++ b/drivers/parisc/eisa_enumerator.c
@@ -91,7 +91,7 @@ static int configure_memory(const unsigned char *buf,
 	for (i=0;i<HPEE_MEMORY_MAX_ENT;i++) {
 		c = get_8(buf+len);
 		
-		if (NULL != (res = kmalloc(sizeof(struct resource), GFP_KERNEL))) {
+		if (NULL != (res = kzalloc(sizeof(struct resource), GFP_KERNEL))) {
 			int result;
 			
 			res->name = name;
@@ -183,7 +183,7 @@ static int configure_port(const unsigned char *buf, struct resource *io_parent,
 	for (i=0;i<HPEE_PORT_MAX_ENT;i++) {
 		c = get_8(buf+len);
 		
-		if (NULL != (res = kmalloc(sizeof(struct resource), GFP_KERNEL))) {
+		if (NULL != (res = kzalloc(sizeof(struct resource), GFP_KERNEL))) {
 			res->name = board;
 			res->start = get_16(buf+len+1);
 			res->end = get_16(buf+len+1)+(c&HPEE_PORT_SIZE_MASK)+1;
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 73de4efcbe6e..a1f37db745ab 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -1,6 +1,9 @@
 #
 # PCI configuration
 #
+
+source "drivers/pci/pcie/Kconfig"
+
 config PCI_BUS_ADDR_T_64BIT
 	def_bool y if (ARCH_DMA_ADDR_T_64BIT || 64BIT)
 	depends on PCI
@@ -118,4 +121,11 @@ config PCI_LABEL
 	def_bool y if (DMI || ACPI)
 	select NLS
 
+config PCI_HYPERV
+        tristate "Hyper-V PCI Frontend"
+        depends on PCI && X86 && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN && X86_64
+        help
+          The PCI device frontend driver allows the kernel to import arbitrary
+          PCI devices from a PCI backend to support PCI driver domains.
+
 source "drivers/pci/host/Kconfig"
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index be3f631c3f75..2154092ddee8 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -32,6 +32,7 @@ obj-$(CONFIG_PCI_IOV) += iov.o
 # Some architectures use the generic PCI setup functions
 #
 obj-$(CONFIG_ALPHA) += setup-irq.o
+obj-$(CONFIG_ARC) += setup-irq.o
 obj-$(CONFIG_ARM) += setup-irq.o
 obj-$(CONFIG_ARM64) += setup-irq.o
 obj-$(CONFIG_UNICORE32) += setup-irq.o
diff --git a/drivers/pci/access.c b/drivers/pci/access.c
index 8c05b5ceeaec..01b9d0a00abc 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -174,38 +174,6 @@ struct pci_ops *pci_bus_set_ops(struct pci_bus *bus, struct pci_ops *ops)
 }
 EXPORT_SYMBOL(pci_bus_set_ops);
 
-/**
- * pci_read_vpd - Read one entry from Vital Product Data
- * @dev:	pci device struct
- * @pos:	offset in vpd space
- * @count:	number of bytes to read
- * @buf:	pointer to where to store result
- *
- */
-ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf)
-{
-	if (!dev->vpd || !dev->vpd->ops)
-		return -ENODEV;
-	return dev->vpd->ops->read(dev, pos, count, buf);
-}
-EXPORT_SYMBOL(pci_read_vpd);
-
-/**
- * pci_write_vpd - Write entry to Vital Product Data
- * @dev:	pci device struct
- * @pos:	offset in vpd space
- * @count:	number of bytes to write
- * @buf:	buffer containing write data
- *
- */
-ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void *buf)
-{
-	if (!dev->vpd || !dev->vpd->ops)
-		return -ENODEV;
-	return dev->vpd->ops->write(dev, pos, count, buf);
-}
-EXPORT_SYMBOL(pci_write_vpd);
-
 /*
  * The following routines are to prevent the user from accessing PCI config
  * space when it's unsafe to do so.  Some devices require this during BIST and
@@ -277,15 +245,91 @@ PCI_USER_WRITE_CONFIG(dword, u32)
 
 /* VPD access through PCI 2.2+ VPD capability */
 
-#define PCI_VPD_PCI22_SIZE (PCI_VPD_ADDR_MASK + 1)
+/**
+ * pci_read_vpd - Read one entry from Vital Product Data
+ * @dev:	pci device struct
+ * @pos:	offset in vpd space
+ * @count:	number of bytes to read
+ * @buf:	pointer to where to store result
+ */
+ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf)
+{
+	if (!dev->vpd || !dev->vpd->ops)
+		return -ENODEV;
+	return dev->vpd->ops->read(dev, pos, count, buf);
+}
+EXPORT_SYMBOL(pci_read_vpd);
 
-struct pci_vpd_pci22 {
-	struct pci_vpd base;
-	struct mutex lock;
-	u16	flag;
-	bool	busy;
-	u8	cap;
-};
+/**
+ * pci_write_vpd - Write entry to Vital Product Data
+ * @dev:	pci device struct
+ * @pos:	offset in vpd space
+ * @count:	number of bytes to write
+ * @buf:	buffer containing write data
+ */
+ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void *buf)
+{
+	if (!dev->vpd || !dev->vpd->ops)
+		return -ENODEV;
+	return dev->vpd->ops->write(dev, pos, count, buf);
+}
+EXPORT_SYMBOL(pci_write_vpd);
+
+#define PCI_VPD_MAX_SIZE (PCI_VPD_ADDR_MASK + 1)
+
+/**
+ * pci_vpd_size - determine actual size of Vital Product Data
+ * @dev:	pci device struct
+ * @old_size:	current assumed size, also maximum allowed size
+ */
+static size_t pci_vpd_size(struct pci_dev *dev, size_t old_size)
+{
+	size_t off = 0;
+	unsigned char header[1+2];	/* 1 byte tag, 2 bytes length */
+
+	while (off < old_size &&
+	       pci_read_vpd(dev, off, 1, header) == 1) {
+		unsigned char tag;
+
+		if (header[0] & PCI_VPD_LRDT) {
+			/* Large Resource Data Type Tag */
+			tag = pci_vpd_lrdt_tag(header);
+			/* Only read length from known tag items */
+			if ((tag == PCI_VPD_LTIN_ID_STRING) ||
+			    (tag == PCI_VPD_LTIN_RO_DATA) ||
+			    (tag == PCI_VPD_LTIN_RW_DATA)) {
+				if (pci_read_vpd(dev, off+1, 2,
+						 &header[1]) != 2) {
+					dev_warn(&dev->dev,
+						 "invalid large VPD tag %02x size at offset %zu",
+						 tag, off + 1);
+					return 0;
+				}
+				off += PCI_VPD_LRDT_TAG_SIZE +
+					pci_vpd_lrdt_size(header);
+			}
+		} else {
+			/* Short Resource Data Type Tag */
+			off += PCI_VPD_SRDT_TAG_SIZE +
+				pci_vpd_srdt_size(header);
+			tag = pci_vpd_srdt_tag(header);
+		}
+
+		if (tag == PCI_VPD_STIN_END)	/* End tag descriptor */
+			return off;
+
+		if ((tag != PCI_VPD_LTIN_ID_STRING) &&
+		    (tag != PCI_VPD_LTIN_RO_DATA) &&
+		    (tag != PCI_VPD_LTIN_RW_DATA)) {
+			dev_warn(&dev->dev,
+				 "invalid %s VPD tag %02x at offset %zu",
+				 (header[0] & PCI_VPD_LRDT) ? "large" : "short",
+				 tag, off);
+			return 0;
+		}
+	}
+	return 0;
+}
 
 /*
  * Wait for last operation to complete.
@@ -295,55 +339,71 @@ struct pci_vpd_pci22 {
  *
  * Returns 0 on success, negative values indicate error.
  */
-static int pci_vpd_pci22_wait(struct pci_dev *dev)
+static int pci_vpd_wait(struct pci_dev *dev)
 {
-	struct pci_vpd_pci22 *vpd =
-		container_of(dev->vpd, struct pci_vpd_pci22, base);
-	unsigned long timeout = jiffies + HZ/20 + 2;
+	struct pci_vpd *vpd = dev->vpd;
+	unsigned long timeout = jiffies + msecs_to_jiffies(50);
+	unsigned long max_sleep = 16;
 	u16 status;
 	int ret;
 
 	if (!vpd->busy)
 		return 0;
 
-	for (;;) {
+	while (time_before(jiffies, timeout)) {
 		ret = pci_user_read_config_word(dev, vpd->cap + PCI_VPD_ADDR,
 						&status);
 		if (ret < 0)
 			return ret;
 
 		if ((status & PCI_VPD_ADDR_F) == vpd->flag) {
-			vpd->busy = false;
+			vpd->busy = 0;
 			return 0;
 		}
 
-		if (time_after(jiffies, timeout)) {
-			dev_printk(KERN_DEBUG, &dev->dev, "vpd r/w failed.  This is likely a firmware bug on this device.  Contact the card vendor for a firmware update\n");
-			return -ETIMEDOUT;
-		}
 		if (fatal_signal_pending(current))
 			return -EINTR;
-		if (!cond_resched())
-			udelay(10);
+
+		usleep_range(10, max_sleep);
+		if (max_sleep < 1024)
+			max_sleep *= 2;
 	}
+
+	dev_warn(&dev->dev, "VPD access failed.  This is likely a firmware bug on this device.  Contact the card vendor for a firmware update\n");
+	return -ETIMEDOUT;
 }
 
-static ssize_t pci_vpd_pci22_read(struct pci_dev *dev, loff_t pos, size_t count,
-				  void *arg)
+static ssize_t pci_vpd_read(struct pci_dev *dev, loff_t pos, size_t count,
+			    void *arg)
 {
-	struct pci_vpd_pci22 *vpd =
-		container_of(dev->vpd, struct pci_vpd_pci22, base);
+	struct pci_vpd *vpd = dev->vpd;
 	int ret;
 	loff_t end = pos + count;
 	u8 *buf = arg;
 
-	if (pos < 0 || pos > vpd->base.len || end > vpd->base.len)
+	if (pos < 0)
 		return -EINVAL;
 
+	if (!vpd->valid) {
+		vpd->valid = 1;
+		vpd->len = pci_vpd_size(dev, vpd->len);
+	}
+
+	if (vpd->len == 0)
+		return -EIO;
+
+	if (pos > vpd->len)
+		return 0;
+
+	if (end > vpd->len) {
+		end = vpd->len;
+		count = end - pos;
+	}
+
 	if (mutex_lock_killable(&vpd->lock))
 		return -EINTR;
 
-	ret = pci_vpd_pci22_wait(dev);
+	ret = pci_vpd_wait(dev);
 	if (ret < 0)
 		goto out;
 
@@ -355,9 +415,9 @@ static ssize_t pci_vpd_pci22_read(struct pci_dev *dev, loff_t pos, size_t count,
 						 pos & ~3);
 		if (ret < 0)
 			break;
-		vpd->busy = true;
+		vpd->busy = 1;
 		vpd->flag = PCI_VPD_ADDR_F;
-		ret = pci_vpd_pci22_wait(dev);
+		ret = pci_vpd_wait(dev);
 		if (ret < 0)
 			break;
 
@@ -380,22 +440,32 @@ out:
 	return ret ? ret : count;
 }
 
-static ssize_t pci_vpd_pci22_write(struct pci_dev *dev, loff_t pos, size_t count,
-				   const void *arg)
+static ssize_t pci_vpd_write(struct pci_dev *dev, loff_t pos, size_t count,
+			     const void *arg)
 {
-	struct pci_vpd_pci22 *vpd =
-		container_of(dev->vpd, struct pci_vpd_pci22, base);
+	struct pci_vpd *vpd = dev->vpd;
 	const u8 *buf = arg;
 	loff_t end = pos + count;
 	int ret = 0;
 
-	if (pos < 0 || (pos & 3) || (count & 3) || end > vpd->base.len)
+	if (pos < 0 || (pos & 3) || (count & 3))
+		return -EINVAL;
+
+	if (!vpd->valid) {
+		vpd->valid = 1;
+		vpd->len = pci_vpd_size(dev, vpd->len);
+	}
+
+	if (vpd->len == 0)
+		return -EIO;
+
+	if (end > vpd->len)
 		return -EINVAL;
 
 	if (mutex_lock_killable(&vpd->lock))
 		return -EINTR;
 
-	ret = pci_vpd_pci22_wait(dev);
+	ret = pci_vpd_wait(dev);
 	if (ret < 0)
 		goto out;
 
@@ -415,9 +485,9 @@ static ssize_t pci_vpd_pci22_write(struct pci_dev *dev, loff_t pos, size_t count
 		if (ret < 0)
 			break;
 
-		vpd->busy = true;
+		vpd->busy = 1;
 		vpd->flag = 0;
-		ret = pci_vpd_pci22_wait(dev);
+		ret = pci_vpd_wait(dev);
 		if (ret < 0)
 			break;
 
@@ -428,15 +498,9 @@ out:
 	return ret ? ret : count;
 }
 
-static void pci_vpd_pci22_release(struct pci_dev *dev)
-{
-	kfree(container_of(dev->vpd, struct pci_vpd_pci22, base));
-}
-
-static const struct pci_vpd_ops pci_vpd_pci22_ops = {
-	.read = pci_vpd_pci22_read,
-	.write = pci_vpd_pci22_write,
-	.release = pci_vpd_pci22_release,
+static const struct pci_vpd_ops pci_vpd_ops = {
+	.read = pci_vpd_read,
+	.write = pci_vpd_write,
 };
 
 static ssize_t pci_vpd_f0_read(struct pci_dev *dev, loff_t pos, size_t count,
@@ -472,12 +536,11 @@ static ssize_t pci_vpd_f0_write(struct pci_dev *dev, loff_t pos, size_t count,
 static const struct pci_vpd_ops pci_vpd_f0_ops = {
 	.read = pci_vpd_f0_read,
 	.write = pci_vpd_f0_write,
-	.release = pci_vpd_pci22_release,
 };
 
-int pci_vpd_pci22_init(struct pci_dev *dev)
+int pci_vpd_init(struct pci_dev *dev)
 {
-	struct pci_vpd_pci22 *vpd;
+	struct pci_vpd *vpd;
 	u8 cap;
 
 	cap = pci_find_capability(dev, PCI_CAP_ID_VPD);
@@ -488,18 +551,24 @@ int pci_vpd_pci22_init(struct pci_dev *dev)
 	if (!vpd)
 		return -ENOMEM;
 
-	vpd->base.len = PCI_VPD_PCI22_SIZE;
+	vpd->len = PCI_VPD_MAX_SIZE;
 	if (dev->dev_flags & PCI_DEV_FLAGS_VPD_REF_F0)
-		vpd->base.ops = &pci_vpd_f0_ops;
+		vpd->ops = &pci_vpd_f0_ops;
 	else
-		vpd->base.ops = &pci_vpd_pci22_ops;
+		vpd->ops = &pci_vpd_ops;
 	mutex_init(&vpd->lock);
 	vpd->cap = cap;
-	vpd->busy = false;
-	dev->vpd = &vpd->base;
+	vpd->busy = 0;
+	vpd->valid = 0;
+	dev->vpd = vpd;
 	return 0;
 }
 
+void pci_vpd_release(struct pci_dev *dev)
+{
+	kfree(dev->vpd);
+}
+
 /**
  * pci_cfg_access_lock - Lock PCI config reads/writes
  * @dev:	pci device struct
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 89b3befc7155..f2187d491475 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -291,7 +291,12 @@ void pci_bus_add_device(struct pci_dev *dev)
 
 	dev->match_driver = true;
 	retval = device_attach(&dev->dev);
-	WARN_ON(retval < 0);
+	if (retval < 0) {
+		dev_warn(&dev->dev, "device attach failed (%d)\n", retval);
+		pci_proc_detach_device(dev);
+		pci_remove_sysfs_dev_files(dev);
+		return;
+	}
 
 	dev->is_added = 1;
 }
diff --git a/drivers/pci/host/Kconfig b/drivers/pci/host/Kconfig
index 75a605426538..c5014bf95a20 100644
--- a/drivers/pci/host/Kconfig
+++ b/drivers/pci/host/Kconfig
@@ -14,8 +14,31 @@ config PCI_DRA7XX
 config PCI_MVEBU
 	bool "Marvell EBU PCIe controller"
 	depends on ARCH_MVEBU || ARCH_DOVE
+	depends on ARM
 	depends on OF
 
+
+config PCIE_XILINX_NWL
+	bool "NWL PCIe Core"
+	depends on ARCH_ZYNQMP
+	select PCI_MSI_IRQ_DOMAIN if PCI_MSI
+	help
+	 Say 'Y' here if you want kernel support for Xilinx
+	 NWL PCIe controller. The controller can act as Root Port
+	 or End Point. The current option selection will only
+	 support root port enabling.
+
+config PCIE_DW_PLAT
+	bool "Platform bus based DesignWare PCIe Controller"
+	select PCIE_DW
+	---help---
+	 This selects the DesignWare PCIe controller support. Select this if
+	 you have a PCIe controller on Platform bus.
+
+	 If you have a controller with this interface, say Y or M here.
+
+	 If unsure, say N.
+
 config PCIE_DW
 	bool
 
@@ -41,7 +64,7 @@ config PCI_TEGRA
 config PCI_RCAR_GEN2
 	bool "Renesas R-Car Gen2 Internal PCI controller"
 	depends on ARM
-	depends on ARCH_SHMOBILE || COMPILE_TEST
+	depends on ARCH_RENESAS || COMPILE_TEST
 	help
 	  Say Y here if you want internal PCI support on R-Car Gen2 SoC.
 	  There are 3 internal PCI controllers available with a single
@@ -49,13 +72,17 @@ config PCI_RCAR_GEN2
 
 config PCI_RCAR_GEN2_PCIE
 	bool "Renesas R-Car PCIe controller"
-	depends on ARCH_SHMOBILE || (ARM && COMPILE_TEST)
+	depends on ARCH_RENESAS || (ARM && COMPILE_TEST)
 	help
 	  Say Y here if you want PCIe controller support on R-Car Gen2 SoCs.
 
+config PCI_HOST_COMMON
+	bool
+
 config PCI_HOST_GENERIC
 	bool "Generic PCI host controller"
 	depends on (ARM || ARM64) && OF
+	select PCI_HOST_COMMON
 	help
 	  Say Y here if you want to support a simple generic PCI host
 	  controller, such as the one emulated by kvmtool.
@@ -81,7 +108,7 @@ config PCI_KEYSTONE
 
 config PCIE_XILINX
 	bool "Xilinx AXI PCIe host bridge support"
-	depends on ARCH_ZYNQ
+	depends on ARCH_ZYNQ || MICROBLAZE
 	help
 	  Say 'Y' here if you want kernel to support the Xilinx AXI PCIe
 	  Host Bridge driver.
@@ -191,4 +218,18 @@ config PCIE_QCOM
 	  PCIe controller uses the Designware core plus Qualcomm-specific
 	  hardware wrappers.
 
+config PCI_HOST_THUNDER_PEM
+	bool "Cavium Thunder PCIe controller to off-chip devices"
+	depends on OF && ARM64
+	select PCI_HOST_COMMON
+	help
+	  Say Y here if you want PCIe support for CN88XX Cavium Thunder SoCs.
+
+config PCI_HOST_THUNDER_ECAM
+	bool "Cavium Thunder ECAM controller to on-chip devices on pass-1.x silicon"
+	depends on OF && ARM64
+	select PCI_HOST_COMMON
+	help
+	  Say Y here if you want ECAM support for CN88XX-Pass-1.x Cavium Thunder SoCs.
+
 endmenu
diff --git a/drivers/pci/host/Makefile b/drivers/pci/host/Makefile
index 7b2f20c6ccc6..d85b5faf9bbc 100644
--- a/drivers/pci/host/Makefile
+++ b/drivers/pci/host/Makefile
@@ -1,15 +1,19 @@
 obj-$(CONFIG_PCIE_DW) += pcie-designware.o
+obj-$(CONFIG_PCIE_DW_PLAT) += pcie-designware-plat.o
 obj-$(CONFIG_PCI_DRA7XX) += pci-dra7xx.o
 obj-$(CONFIG_PCI_EXYNOS) += pci-exynos.o
 obj-$(CONFIG_PCI_IMX6) += pci-imx6.o
+obj-$(CONFIG_PCI_HYPERV) += pci-hyperv.o
 obj-$(CONFIG_PCI_MVEBU) += pci-mvebu.o
 obj-$(CONFIG_PCI_TEGRA) += pci-tegra.o
 obj-$(CONFIG_PCI_RCAR_GEN2) += pci-rcar-gen2.o
 obj-$(CONFIG_PCI_RCAR_GEN2_PCIE) += pcie-rcar.o
+obj-$(CONFIG_PCI_HOST_COMMON) += pci-host-common.o
 obj-$(CONFIG_PCI_HOST_GENERIC) += pci-host-generic.o
 obj-$(CONFIG_PCIE_SPEAR13XX) += pcie-spear13xx.o
 obj-$(CONFIG_PCI_KEYSTONE) += pci-keystone-dw.o pci-keystone.o
 obj-$(CONFIG_PCIE_XILINX) += pcie-xilinx.o
+obj-$(CONFIG_PCIE_XILINX_NWL) += pcie-xilinx-nwl.o
 obj-$(CONFIG_PCI_XGENE) += pci-xgene.o
 obj-$(CONFIG_PCI_XGENE_MSI) += pci-xgene-msi.o
 obj-$(CONFIG_PCI_LAYERSCAPE) += pci-layerscape.o
@@ -22,3 +26,5 @@ obj-$(CONFIG_PCIE_ALTERA) += pcie-altera.o
 obj-$(CONFIG_PCIE_ALTERA_MSI) += pcie-altera-msi.o
 obj-$(CONFIG_PCI_HISI) += pcie-hisi.o
 obj-$(CONFIG_PCIE_QCOM) += pcie-qcom.o
+obj-$(CONFIG_PCI_HOST_THUNDER_ECAM) += pci-thunder-ecam.o
+obj-$(CONFIG_PCI_HOST_THUNDER_PEM) += pci-thunder-pem.o
diff --git a/drivers/pci/host/pci-dra7xx.c b/drivers/pci/host/pci-dra7xx.c
index 923607bdabc5..2ca3a1f30ebf 100644
--- a/drivers/pci/host/pci-dra7xx.c
+++ b/drivers/pci/host/pci-dra7xx.c
@@ -10,7 +10,6 @@
  * published by the Free Software Foundation.
  */
 
-#include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
@@ -108,7 +107,6 @@ static int dra7xx_pcie_establish_link(struct pcie_port *pp)
 {
 	struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pp);
 	u32 reg;
-	unsigned int retries;
 
 	if (dw_pcie_link_up(pp)) {
 		dev_err(pp->dev, "link is already up\n");
@@ -119,14 +117,7 @@ static int dra7xx_pcie_establish_link(struct pcie_port *pp)
 	reg |= LTSSM_EN;
 	dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_DEVICE_CMD, reg);
 
-	for (retries = 0; retries < 1000; retries++) {
-		if (dw_pcie_link_up(pp))
-			return 0;
-		usleep_range(10, 20);
-	}
-
-	dev_err(pp->dev, "link is not up\n");
-	return -EINVAL;
+	return dw_pcie_wait_for_link(pp);
 }
 
 static void dra7xx_pcie_enable_interrupts(struct pcie_port *pp)
diff --git a/drivers/pci/host/pci-exynos.c b/drivers/pci/host/pci-exynos.c
index d997d22d4231..219976103efc 100644
--- a/drivers/pci/host/pci-exynos.c
+++ b/drivers/pci/host/pci-exynos.c
@@ -318,7 +318,6 @@ static int exynos_pcie_establish_link(struct pcie_port *pp)
 {
 	struct exynos_pcie *exynos_pcie = to_exynos_pcie(pp);
 	u32 val;
-	unsigned int retries;
 
 	if (dw_pcie_link_up(pp)) {
 		dev_err(pp->dev, "Link already up\n");
@@ -357,13 +356,8 @@ static int exynos_pcie_establish_link(struct pcie_port *pp)
 			  PCIE_APP_LTSSM_ENABLE);
 
 	/* check if the link is up or not */
-	for (retries = 0; retries < 10; retries++) {
-		if (dw_pcie_link_up(pp)) {
-			dev_info(pp->dev, "Link up\n");
-			return 0;
-		}
-		mdelay(100);
-	}
+	if (!dw_pcie_wait_for_link(pp))
+		return 0;
 
 	while (exynos_phy_readl(exynos_pcie, PCIE_PHY_PLL_LOCKED) == 0) {
 		val = exynos_blk_readl(exynos_pcie, PCIE_PHY_PLL_LOCKED);
@@ -372,8 +366,7 @@ static int exynos_pcie_establish_link(struct pcie_port *pp)
 	/* power off phy */
 	exynos_pcie_power_off_phy(pp);
 
-	dev_err(pp->dev, "PCIe Link Fail\n");
-	return -EINVAL;
+	return -ETIMEDOUT;
 }
 
 static void exynos_pcie_clear_irq_pulse(struct pcie_port *pp)
diff --git a/drivers/pci/host/pci-host-common.c b/drivers/pci/host/pci-host-common.c
new file mode 100644
index 000000000000..e9f850f07968
--- /dev/null
+++ b/drivers/pci/host/pci-host-common.c
@@ -0,0 +1,194 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * Copyright (C) 2014 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_pci.h>
+#include <linux/platform_device.h>
+
+#include "pci-host-common.h"
+
+static void gen_pci_release_of_pci_ranges(struct gen_pci *pci)
+{
+	pci_free_resource_list(&pci->resources);
+}
+
+static int gen_pci_parse_request_of_pci_ranges(struct gen_pci *pci)
+{
+	int err, res_valid = 0;
+	struct device *dev = pci->host.dev.parent;
+	struct device_node *np = dev->of_node;
+	resource_size_t iobase;
+	struct resource_entry *win;
+
+	err = of_pci_get_host_bridge_resources(np, 0, 0xff, &pci->resources,
+					       &iobase);
+	if (err)
+		return err;
+
+	resource_list_for_each_entry(win, &pci->resources) {
+		struct resource *parent, *res = win->res;
+
+		switch (resource_type(res)) {
+		case IORESOURCE_IO:
+			parent = &ioport_resource;
+			err = pci_remap_iospace(res, iobase);
+			if (err) {
+				dev_warn(dev, "error %d: failed to map resource %pR\n",
+					 err, res);
+				continue;
+			}
+			break;
+		case IORESOURCE_MEM:
+			parent = &iomem_resource;
+			res_valid |= !(res->flags & IORESOURCE_PREFETCH);
+			break;
+		case IORESOURCE_BUS:
+			pci->cfg.bus_range = res;
+		default:
+			continue;
+		}
+
+		err = devm_request_resource(dev, parent, res);
+		if (err)
+			goto out_release_res;
+	}
+
+	if (!res_valid) {
+		dev_err(dev, "non-prefetchable memory resource required\n");
+		err = -EINVAL;
+		goto out_release_res;
+	}
+
+	return 0;
+
+out_release_res:
+	gen_pci_release_of_pci_ranges(pci);
+	return err;
+}
+
+static int gen_pci_parse_map_cfg_windows(struct gen_pci *pci)
+{
+	int err;
+	u8 bus_max;
+	resource_size_t busn;
+	struct resource *bus_range;
+	struct device *dev = pci->host.dev.parent;
+	struct device_node *np = dev->of_node;
+	u32 sz = 1 << pci->cfg.ops->bus_shift;
+
+	err = of_address_to_resource(np, 0, &pci->cfg.res);
+	if (err) {
+		dev_err(dev, "missing \"reg\" property\n");
+		return err;
+	}
+
+	/* Limit the bus-range to fit within reg */
+	bus_max = pci->cfg.bus_range->start +
+		  (resource_size(&pci->cfg.res) >> pci->cfg.ops->bus_shift) - 1;
+	pci->cfg.bus_range->end = min_t(resource_size_t,
+					pci->cfg.bus_range->end, bus_max);
+
+	pci->cfg.win = devm_kcalloc(dev, resource_size(pci->cfg.bus_range),
+				    sizeof(*pci->cfg.win), GFP_KERNEL);
+	if (!pci->cfg.win)
+		return -ENOMEM;
+
+	/* Map our Configuration Space windows */
+	if (!devm_request_mem_region(dev, pci->cfg.res.start,
+				     resource_size(&pci->cfg.res),
+				     "Configuration Space"))
+		return -ENOMEM;
+
+	bus_range = pci->cfg.bus_range;
+	for (busn = bus_range->start; busn <= bus_range->end; ++busn) {
+		u32 idx = busn - bus_range->start;
+
+		pci->cfg.win[idx] = devm_ioremap(dev,
+						 pci->cfg.res.start + idx * sz,
+						 sz);
+		if (!pci->cfg.win[idx])
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+int pci_host_common_probe(struct platform_device *pdev,
+			  struct gen_pci *pci)
+{
+	int err;
+	const char *type;
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct pci_bus *bus, *child;
+
+	type = of_get_property(np, "device_type", NULL);
+	if (!type || strcmp(type, "pci")) {
+		dev_err(dev, "invalid \"device_type\" %s\n", type);
+		return -EINVAL;
+	}
+
+	of_pci_check_probe_only();
+
+	pci->host.dev.parent = dev;
+	INIT_LIST_HEAD(&pci->host.windows);
+	INIT_LIST_HEAD(&pci->resources);
+
+	/* Parse our PCI ranges and request their resources */
+	err = gen_pci_parse_request_of_pci_ranges(pci);
+	if (err)
+		return err;
+
+	/* Parse and map our Configuration Space windows */
+	err = gen_pci_parse_map_cfg_windows(pci);
+	if (err) {
+		gen_pci_release_of_pci_ranges(pci);
+		return err;
+	}
+
+	/* Do not reassign resources if probe only */
+	if (!pci_has_flag(PCI_PROBE_ONLY))
+		pci_add_flags(PCI_REASSIGN_ALL_RSRC | PCI_REASSIGN_ALL_BUS);
+
+
+	bus = pci_scan_root_bus(dev, pci->cfg.bus_range->start,
+				&pci->cfg.ops->ops, pci, &pci->resources);
+	if (!bus) {
+		dev_err(dev, "Scanning rootbus failed");
+		return -ENODEV;
+	}
+
+	pci_fixup_irqs(pci_common_swizzle, of_irq_parse_and_map_pci);
+
+	if (!pci_has_flag(PCI_PROBE_ONLY)) {
+		pci_bus_size_bridges(bus);
+		pci_bus_assign_resources(bus);
+
+		list_for_each_entry(child, &bus->children, node)
+			pcie_bus_configure_settings(child);
+	}
+
+	pci_bus_add_devices(bus);
+	return 0;
+}
+
+MODULE_DESCRIPTION("Generic PCI host driver common code");
+MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/host/pci-host-common.h b/drivers/pci/host/pci-host-common.h
new file mode 100644
index 000000000000..09f3fa0a55d7
--- /dev/null
+++ b/drivers/pci/host/pci-host-common.h
@@ -0,0 +1,47 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * Copyright (C) 2014 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#ifndef _PCI_HOST_COMMON_H
+#define _PCI_HOST_COMMON_H
+
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+
+struct gen_pci_cfg_bus_ops {
+	u32 bus_shift;
+	struct pci_ops ops;
+};
+
+struct gen_pci_cfg_windows {
+	struct resource				res;
+	struct resource				*bus_range;
+	void __iomem				**win;
+
+	struct gen_pci_cfg_bus_ops		*ops;
+};
+
+struct gen_pci {
+	struct pci_host_bridge			host;
+	struct gen_pci_cfg_windows		cfg;
+	struct list_head			resources;
+};
+
+int pci_host_common_probe(struct platform_device *pdev,
+			  struct gen_pci *pci);
+
+#endif /* _PCI_HOST_COMMON_H */
diff --git a/drivers/pci/host/pci-host-generic.c b/drivers/pci/host/pci-host-generic.c
index 1652bc70b145..e8aa78faa16d 100644
--- a/drivers/pci/host/pci-host-generic.c
+++ b/drivers/pci/host/pci-host-generic.c
@@ -25,24 +25,7 @@
 #include <linux/of_pci.h>
 #include <linux/platform_device.h>
 
-struct gen_pci_cfg_bus_ops {
-	u32 bus_shift;
-	struct pci_ops ops;
-};
-
-struct gen_pci_cfg_windows {
-	struct resource				res;
-	struct resource				*bus_range;
-	void __iomem				**win;
-
-	struct gen_pci_cfg_bus_ops		*ops;
-};
-
-struct gen_pci {
-	struct pci_host_bridge			host;
-	struct gen_pci_cfg_windows		cfg;
-	struct list_head			resources;
-};
+#include "pci-host-common.h"
 
 static void __iomem *gen_pci_map_cfg_bus_cam(struct pci_bus *bus,
 					     unsigned int devfn,
@@ -93,175 +76,19 @@ static const struct of_device_id gen_pci_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, gen_pci_of_match);
 
-static void gen_pci_release_of_pci_ranges(struct gen_pci *pci)
-{
-	pci_free_resource_list(&pci->resources);
-}
-
-static int gen_pci_parse_request_of_pci_ranges(struct gen_pci *pci)
-{
-	int err, res_valid = 0;
-	struct device *dev = pci->host.dev.parent;
-	struct device_node *np = dev->of_node;
-	resource_size_t iobase;
-	struct resource_entry *win;
-
-	err = of_pci_get_host_bridge_resources(np, 0, 0xff, &pci->resources,
-					       &iobase);
-	if (err)
-		return err;
-
-	resource_list_for_each_entry(win, &pci->resources) {
-		struct resource *parent, *res = win->res;
-
-		switch (resource_type(res)) {
-		case IORESOURCE_IO:
-			parent = &ioport_resource;
-			err = pci_remap_iospace(res, iobase);
-			if (err) {
-				dev_warn(dev, "error %d: failed to map resource %pR\n",
-					 err, res);
-				continue;
-			}
-			break;
-		case IORESOURCE_MEM:
-			parent = &iomem_resource;
-			res_valid |= !(res->flags & IORESOURCE_PREFETCH);
-			break;
-		case IORESOURCE_BUS:
-			pci->cfg.bus_range = res;
-		default:
-			continue;
-		}
-
-		err = devm_request_resource(dev, parent, res);
-		if (err)
-			goto out_release_res;
-	}
-
-	if (!res_valid) {
-		dev_err(dev, "non-prefetchable memory resource required\n");
-		err = -EINVAL;
-		goto out_release_res;
-	}
-
-	return 0;
-
-out_release_res:
-	gen_pci_release_of_pci_ranges(pci);
-	return err;
-}
-
-static int gen_pci_parse_map_cfg_windows(struct gen_pci *pci)
-{
-	int err;
-	u8 bus_max;
-	resource_size_t busn;
-	struct resource *bus_range;
-	struct device *dev = pci->host.dev.parent;
-	struct device_node *np = dev->of_node;
-	u32 sz = 1 << pci->cfg.ops->bus_shift;
-
-	err = of_address_to_resource(np, 0, &pci->cfg.res);
-	if (err) {
-		dev_err(dev, "missing \"reg\" property\n");
-		return err;
-	}
-
-	/* Limit the bus-range to fit within reg */
-	bus_max = pci->cfg.bus_range->start +
-		  (resource_size(&pci->cfg.res) >> pci->cfg.ops->bus_shift) - 1;
-	pci->cfg.bus_range->end = min_t(resource_size_t,
-					pci->cfg.bus_range->end, bus_max);
-
-	pci->cfg.win = devm_kcalloc(dev, resource_size(pci->cfg.bus_range),
-				    sizeof(*pci->cfg.win), GFP_KERNEL);
-	if (!pci->cfg.win)
-		return -ENOMEM;
-
-	/* Map our Configuration Space windows */
-	if (!devm_request_mem_region(dev, pci->cfg.res.start,
-				     resource_size(&pci->cfg.res),
-				     "Configuration Space"))
-		return -ENOMEM;
-
-	bus_range = pci->cfg.bus_range;
-	for (busn = bus_range->start; busn <= bus_range->end; ++busn) {
-		u32 idx = busn - bus_range->start;
-
-		pci->cfg.win[idx] = devm_ioremap(dev,
-						 pci->cfg.res.start + idx * sz,
-						 sz);
-		if (!pci->cfg.win[idx])
-			return -ENOMEM;
-	}
-
-	return 0;
-}
-
 static int gen_pci_probe(struct platform_device *pdev)
 {
-	int err;
-	const char *type;
-	const struct of_device_id *of_id;
 	struct device *dev = &pdev->dev;
-	struct device_node *np = dev->of_node;
+	const struct of_device_id *of_id;
 	struct gen_pci *pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL);
-	struct pci_bus *bus, *child;
 
 	if (!pci)
 		return -ENOMEM;
 
-	type = of_get_property(np, "device_type", NULL);
-	if (!type || strcmp(type, "pci")) {
-		dev_err(dev, "invalid \"device_type\" %s\n", type);
-		return -EINVAL;
-	}
-
-	of_pci_check_probe_only();
-
-	of_id = of_match_node(gen_pci_of_match, np);
+	of_id = of_match_node(gen_pci_of_match, dev->of_node);
 	pci->cfg.ops = (struct gen_pci_cfg_bus_ops *)of_id->data;
-	pci->host.dev.parent = dev;
-	INIT_LIST_HEAD(&pci->host.windows);
-	INIT_LIST_HEAD(&pci->resources);
-
-	/* Parse our PCI ranges and request their resources */
-	err = gen_pci_parse_request_of_pci_ranges(pci);
-	if (err)
-		return err;
-
-	/* Parse and map our Configuration Space windows */
-	err = gen_pci_parse_map_cfg_windows(pci);
-	if (err) {
-		gen_pci_release_of_pci_ranges(pci);
-		return err;
-	}
-
-	/* Do not reassign resources if probe only */
-	if (!pci_has_flag(PCI_PROBE_ONLY))
-		pci_add_flags(PCI_REASSIGN_ALL_RSRC | PCI_REASSIGN_ALL_BUS);
-
-
-	bus = pci_scan_root_bus(dev, pci->cfg.bus_range->start,
-				&pci->cfg.ops->ops, pci, &pci->resources);
-	if (!bus) {
-		dev_err(dev, "Scanning rootbus failed");
-		return -ENODEV;
-	}
-
-	pci_fixup_irqs(pci_common_swizzle, of_irq_parse_and_map_pci);
-
-	if (!pci_has_flag(PCI_PROBE_ONLY)) {
-		pci_bus_size_bridges(bus);
-		pci_bus_assign_resources(bus);
-
-		list_for_each_entry(child, &bus->children, node)
-			pcie_bus_configure_settings(child);
-	}
 
-	pci_bus_add_devices(bus);
-	return 0;
+	return pci_host_common_probe(pdev, pci);
 }
 
 static struct platform_driver gen_pci_driver = {
diff --git a/drivers/pci/host/pci-hyperv.c b/drivers/pci/host/pci-hyperv.c
new file mode 100644
index 000000000000..ed651baa7c50
--- /dev/null
+++ b/drivers/pci/host/pci-hyperv.c
@@ -0,0 +1,2346 @@
+/*
+ * Copyright (c) Microsoft Corporation.
+ *
+ * Author:
+ *   Jake Oshins <jakeo@microsoft.com>
+ *
+ * This driver acts as a paravirtual front-end for PCI Express root buses.
+ * When a PCI Express function (either an entire device or an SR-IOV
+ * Virtual Function) is being passed through to the VM, this driver exposes
+ * a new bus to the guest VM.  This is modeled as a root PCI bus because
+ * no bridges are being exposed to the VM.  In fact, with a "Generation 2"
+ * VM within Hyper-V, there may seem to be no PCI bus at all in the VM
+ * until a device as been exposed using this driver.
+ *
+ * Each root PCI bus has its own PCI domain, which is called "Segment" in
+ * the PCI Firmware Specifications.  Thus while each device passed through
+ * to the VM using this front-end will appear at "device 0", the domain will
+ * be unique.  Typically, each bus will have one PCI function on it, though
+ * this driver does support more than one.
+ *
+ * In order to map the interrupts from the device through to the guest VM,
+ * this driver also implements an IRQ Domain, which handles interrupts (either
+ * MSI or MSI-X) associated with the functions on the bus.  As interrupts are
+ * set up, torn down, or reaffined, this driver communicates with the
+ * underlying hypervisor to adjust the mappings in the I/O MMU so that each
+ * interrupt will be delivered to the correct virtual processor at the right
+ * vector.  This driver does not support level-triggered (line-based)
+ * interrupts, and will report that the Interrupt Line register in the
+ * function's configuration space is zero.
+ *
+ * The rest of this driver mostly maps PCI concepts onto underlying Hyper-V
+ * facilities.  For instance, the configuration space of a function exposed
+ * by Hyper-V is mapped into a single page of memory space, and the
+ * read and write handlers for config space must be aware of this mechanism.
+ * Similarly, device setup and teardown involves messages sent to and from
+ * the PCI back-end driver in Hyper-V.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/semaphore.h>
+#include <linux/irqdomain.h>
+#include <asm/irqdomain.h>
+#include <asm/apic.h>
+#include <linux/msi.h>
+#include <linux/hyperv.h>
+#include <asm/mshyperv.h>
+
+/*
+ * Protocol versions. The low word is the minor version, the high word the
+ * major version.
+ */
+
+#define PCI_MAKE_VERSION(major, minor) ((u32)(((major) << 16) | (major)))
+#define PCI_MAJOR_VERSION(version) ((u32)(version) >> 16)
+#define PCI_MINOR_VERSION(version) ((u32)(version) & 0xff)
+
+enum {
+	PCI_PROTOCOL_VERSION_1_1 = PCI_MAKE_VERSION(1, 1),
+	PCI_PROTOCOL_VERSION_CURRENT = PCI_PROTOCOL_VERSION_1_1
+};
+
+#define PCI_CONFIG_MMIO_LENGTH	0x2000
+#define CFG_PAGE_OFFSET 0x1000
+#define CFG_PAGE_SIZE (PCI_CONFIG_MMIO_LENGTH - CFG_PAGE_OFFSET)
+
+#define MAX_SUPPORTED_MSI_MESSAGES 0x400
+
+/*
+ * Message Types
+ */
+
+enum pci_message_type {
+	/*
+	 * Version 1.1
+	 */
+	PCI_MESSAGE_BASE                = 0x42490000,
+	PCI_BUS_RELATIONS               = PCI_MESSAGE_BASE + 0,
+	PCI_QUERY_BUS_RELATIONS         = PCI_MESSAGE_BASE + 1,
+	PCI_POWER_STATE_CHANGE          = PCI_MESSAGE_BASE + 4,
+	PCI_QUERY_RESOURCE_REQUIREMENTS = PCI_MESSAGE_BASE + 5,
+	PCI_QUERY_RESOURCE_RESOURCES    = PCI_MESSAGE_BASE + 6,
+	PCI_BUS_D0ENTRY                 = PCI_MESSAGE_BASE + 7,
+	PCI_BUS_D0EXIT                  = PCI_MESSAGE_BASE + 8,
+	PCI_READ_BLOCK                  = PCI_MESSAGE_BASE + 9,
+	PCI_WRITE_BLOCK                 = PCI_MESSAGE_BASE + 0xA,
+	PCI_EJECT                       = PCI_MESSAGE_BASE + 0xB,
+	PCI_QUERY_STOP                  = PCI_MESSAGE_BASE + 0xC,
+	PCI_REENABLE                    = PCI_MESSAGE_BASE + 0xD,
+	PCI_QUERY_STOP_FAILED           = PCI_MESSAGE_BASE + 0xE,
+	PCI_EJECTION_COMPLETE           = PCI_MESSAGE_BASE + 0xF,
+	PCI_RESOURCES_ASSIGNED          = PCI_MESSAGE_BASE + 0x10,
+	PCI_RESOURCES_RELEASED          = PCI_MESSAGE_BASE + 0x11,
+	PCI_INVALIDATE_BLOCK            = PCI_MESSAGE_BASE + 0x12,
+	PCI_QUERY_PROTOCOL_VERSION      = PCI_MESSAGE_BASE + 0x13,
+	PCI_CREATE_INTERRUPT_MESSAGE    = PCI_MESSAGE_BASE + 0x14,
+	PCI_DELETE_INTERRUPT_MESSAGE    = PCI_MESSAGE_BASE + 0x15,
+	PCI_MESSAGE_MAXIMUM
+};
+
+/*
+ * Structures defining the virtual PCI Express protocol.
+ */
+
+union pci_version {
+	struct {
+		u16 minor_version;
+		u16 major_version;
+	} parts;
+	u32 version;
+} __packed;
+
+/*
+ * Function numbers are 8-bits wide on Express, as interpreted through ARI,
+ * which is all this driver does.  This representation is the one used in
+ * Windows, which is what is expected when sending this back and forth with
+ * the Hyper-V parent partition.
+ */
+union win_slot_encoding {
+	struct {
+		u32	func:8;
+		u32	reserved:24;
+	} bits;
+	u32 slot;
+} __packed;
+
+/*
+ * Pretty much as defined in the PCI Specifications.
+ */
+struct pci_function_description {
+	u16	v_id;	/* vendor ID */
+	u16	d_id;	/* device ID */
+	u8	rev;
+	u8	prog_intf;
+	u8	subclass;
+	u8	base_class;
+	u32	subsystem_id;
+	union win_slot_encoding win_slot;
+	u32	ser;	/* serial number */
+} __packed;
+
+/**
+ * struct hv_msi_desc
+ * @vector:		IDT entry
+ * @delivery_mode:	As defined in Intel's Programmer's
+ *			Reference Manual, Volume 3, Chapter 8.
+ * @vector_count:	Number of contiguous entries in the
+ *			Interrupt Descriptor Table that are
+ *			occupied by this Message-Signaled
+ *			Interrupt. For "MSI", as first defined
+ *			in PCI 2.2, this can be between 1 and
+ *			32. For "MSI-X," as first defined in PCI
+ *			3.0, this must be 1, as each MSI-X table
+ *			entry would have its own descriptor.
+ * @reserved:		Empty space
+ * @cpu_mask:		All the target virtual processors.
+ */
+struct hv_msi_desc {
+	u8	vector;
+	u8	delivery_mode;
+	u16	vector_count;
+	u32	reserved;
+	u64	cpu_mask;
+} __packed;
+
+/**
+ * struct tran_int_desc
+ * @reserved:		unused, padding
+ * @vector_count:	same as in hv_msi_desc
+ * @data:		This is the "data payload" value that is
+ *			written by the device when it generates
+ *			a message-signaled interrupt, either MSI
+ *			or MSI-X.
+ * @address:		This is the address to which the data
+ *			payload is written on interrupt
+ *			generation.
+ */
+struct tran_int_desc {
+	u16	reserved;
+	u16	vector_count;
+	u32	data;
+	u64	address;
+} __packed;
+
+/*
+ * A generic message format for virtual PCI.
+ * Specific message formats are defined later in the file.
+ */
+
+struct pci_message {
+	u32 message_type;
+} __packed;
+
+struct pci_child_message {
+	u32 message_type;
+	union win_slot_encoding wslot;
+} __packed;
+
+struct pci_incoming_message {
+	struct vmpacket_descriptor hdr;
+	struct pci_message message_type;
+} __packed;
+
+struct pci_response {
+	struct vmpacket_descriptor hdr;
+	s32 status;			/* negative values are failures */
+} __packed;
+
+struct pci_packet {
+	void (*completion_func)(void *context, struct pci_response *resp,
+				int resp_packet_size);
+	void *compl_ctxt;
+	struct pci_message message;
+};
+
+/*
+ * Specific message types supporting the PCI protocol.
+ */
+
+/*
+ * Version negotiation message. Sent from the guest to the host.
+ * The guest is free to try different versions until the host
+ * accepts the version.
+ *
+ * pci_version: The protocol version requested.
+ * is_last_attempt: If TRUE, this is the last version guest will request.
+ * reservedz: Reserved field, set to zero.
+ */
+
+struct pci_version_request {
+	struct pci_message message_type;
+	enum pci_message_type protocol_version;
+} __packed;
+
+/*
+ * Bus D0 Entry.  This is sent from the guest to the host when the virtual
+ * bus (PCI Express port) is ready for action.
+ */
+
+struct pci_bus_d0_entry {
+	struct pci_message message_type;
+	u32 reserved;
+	u64 mmio_base;
+} __packed;
+
+struct pci_bus_relations {
+	struct pci_incoming_message incoming;
+	u32 device_count;
+	struct pci_function_description func[1];
+} __packed;
+
+struct pci_q_res_req_response {
+	struct vmpacket_descriptor hdr;
+	s32 status;			/* negative values are failures */
+	u32 probed_bar[6];
+} __packed;
+
+struct pci_set_power {
+	struct pci_message message_type;
+	union win_slot_encoding wslot;
+	u32 power_state;		/* In Windows terms */
+	u32 reserved;
+} __packed;
+
+struct pci_set_power_response {
+	struct vmpacket_descriptor hdr;
+	s32 status;			/* negative values are failures */
+	union win_slot_encoding wslot;
+	u32 resultant_state;		/* In Windows terms */
+	u32 reserved;
+} __packed;
+
+struct pci_resources_assigned {
+	struct pci_message message_type;
+	union win_slot_encoding wslot;
+	u8 memory_range[0x14][6];	/* not used here */
+	u32 msi_descriptors;
+	u32 reserved[4];
+} __packed;
+
+struct pci_create_interrupt {
+	struct pci_message message_type;
+	union win_slot_encoding wslot;
+	struct hv_msi_desc int_desc;
+} __packed;
+
+struct pci_create_int_response {
+	struct pci_response response;
+	u32 reserved;
+	struct tran_int_desc int_desc;
+} __packed;
+
+struct pci_delete_interrupt {
+	struct pci_message message_type;
+	union win_slot_encoding wslot;
+	struct tran_int_desc int_desc;
+} __packed;
+
+struct pci_dev_incoming {
+	struct pci_incoming_message incoming;
+	union win_slot_encoding wslot;
+} __packed;
+
+struct pci_eject_response {
+	u32 message_type;
+	union win_slot_encoding wslot;
+	u32 status;
+} __packed;
+
+static int pci_ring_size = (4 * PAGE_SIZE);
+
+/*
+ * Definitions or interrupt steering hypercall.
+ */
+#define HV_PARTITION_ID_SELF		((u64)-1)
+#define HVCALL_RETARGET_INTERRUPT	0x7e
+
+struct retarget_msi_interrupt {
+	u64	partition_id;		/* use "self" */
+	u64	device_id;
+	u32	source;			/* 1 for MSI(-X) */
+	u32	reserved1;
+	u32	address;
+	u32	data;
+	u64	reserved2;
+	u32	vector;
+	u32	flags;
+	u64	vp_mask;
+} __packed;
+
+/*
+ * Driver specific state.
+ */
+
+enum hv_pcibus_state {
+	hv_pcibus_init = 0,
+	hv_pcibus_probed,
+	hv_pcibus_installed,
+	hv_pcibus_maximum
+};
+
+struct hv_pcibus_device {
+	struct pci_sysdata sysdata;
+	enum hv_pcibus_state state;
+	atomic_t remove_lock;
+	struct hv_device *hdev;
+	resource_size_t low_mmio_space;
+	resource_size_t high_mmio_space;
+	struct resource *mem_config;
+	struct resource *low_mmio_res;
+	struct resource *high_mmio_res;
+	struct completion *survey_event;
+	struct completion remove_event;
+	struct pci_bus *pci_bus;
+	spinlock_t config_lock;	/* Avoid two threads writing index page */
+	spinlock_t device_list_lock;	/* Protect lists below */
+	void __iomem *cfg_addr;
+
+	struct semaphore enum_sem;
+	struct list_head resources_for_children;
+
+	struct list_head children;
+	struct list_head dr_list;
+	struct work_struct wrk;
+
+	struct msi_domain_info msi_info;
+	struct msi_controller msi_chip;
+	struct irq_domain *irq_domain;
+};
+
+/*
+ * Tracks "Device Relations" messages from the host, which must be both
+ * processed in order and deferred so that they don't run in the context
+ * of the incoming packet callback.
+ */
+struct hv_dr_work {
+	struct work_struct wrk;
+	struct hv_pcibus_device *bus;
+};
+
+struct hv_dr_state {
+	struct list_head list_entry;
+	u32 device_count;
+	struct pci_function_description func[1];
+};
+
+enum hv_pcichild_state {
+	hv_pcichild_init = 0,
+	hv_pcichild_requirements,
+	hv_pcichild_resourced,
+	hv_pcichild_ejecting,
+	hv_pcichild_maximum
+};
+
+enum hv_pcidev_ref_reason {
+	hv_pcidev_ref_invalid = 0,
+	hv_pcidev_ref_initial,
+	hv_pcidev_ref_by_slot,
+	hv_pcidev_ref_packet,
+	hv_pcidev_ref_pnp,
+	hv_pcidev_ref_childlist,
+	hv_pcidev_irqdata,
+	hv_pcidev_ref_max
+};
+
+struct hv_pci_dev {
+	/* List protected by pci_rescan_remove_lock */
+	struct list_head list_entry;
+	atomic_t refs;
+	enum hv_pcichild_state state;
+	struct pci_function_description desc;
+	bool reported_missing;
+	struct hv_pcibus_device *hbus;
+	struct work_struct wrk;
+
+	/*
+	 * What would be observed if one wrote 0xFFFFFFFF to a BAR and then
+	 * read it back, for each of the BAR offsets within config space.
+	 */
+	u32 probed_bar[6];
+};
+
+struct hv_pci_compl {
+	struct completion host_event;
+	s32 completion_status;
+};
+
+/**
+ * hv_pci_generic_compl() - Invoked for a completion packet
+ * @context:		Set up by the sender of the packet.
+ * @resp:		The response packet
+ * @resp_packet_size:	Size in bytes of the packet
+ *
+ * This function is used to trigger an event and report status
+ * for any message for which the completion packet contains a
+ * status and nothing else.
+ */
+static
+void
+hv_pci_generic_compl(void *context, struct pci_response *resp,
+		     int resp_packet_size)
+{
+	struct hv_pci_compl *comp_pkt = context;
+
+	if (resp_packet_size >= offsetofend(struct pci_response, status))
+		comp_pkt->completion_status = resp->status;
+	complete(&comp_pkt->host_event);
+}
+
+static struct hv_pci_dev *get_pcichild_wslot(struct hv_pcibus_device *hbus,
+						u32 wslot);
+static void get_pcichild(struct hv_pci_dev *hv_pcidev,
+			 enum hv_pcidev_ref_reason reason);
+static void put_pcichild(struct hv_pci_dev *hv_pcidev,
+			 enum hv_pcidev_ref_reason reason);
+
+static void get_hvpcibus(struct hv_pcibus_device *hv_pcibus);
+static void put_hvpcibus(struct hv_pcibus_device *hv_pcibus);
+
+/**
+ * devfn_to_wslot() - Convert from Linux PCI slot to Windows
+ * @devfn:	The Linux representation of PCI slot
+ *
+ * Windows uses a slightly different representation of PCI slot.
+ *
+ * Return: The Windows representation
+ */
+static u32 devfn_to_wslot(int devfn)
+{
+	union win_slot_encoding wslot;
+
+	wslot.slot = 0;
+	wslot.bits.func = PCI_SLOT(devfn) | (PCI_FUNC(devfn) << 5);
+
+	return wslot.slot;
+}
+
+/**
+ * wslot_to_devfn() - Convert from Windows PCI slot to Linux
+ * @wslot:	The Windows representation of PCI slot
+ *
+ * Windows uses a slightly different representation of PCI slot.
+ *
+ * Return: The Linux representation
+ */
+static int wslot_to_devfn(u32 wslot)
+{
+	union win_slot_encoding slot_no;
+
+	slot_no.slot = wslot;
+	return PCI_DEVFN(0, slot_no.bits.func);
+}
+
+/*
+ * PCI Configuration Space for these root PCI buses is implemented as a pair
+ * of pages in memory-mapped I/O space.  Writing to the first page chooses
+ * the PCI function being written or read.  Once the first page has been
+ * written to, the following page maps in the entire configuration space of
+ * the function.
+ */
+
+/**
+ * _hv_pcifront_read_config() - Internal PCI config read
+ * @hpdev:	The PCI driver's representation of the device
+ * @where:	Offset within config space
+ * @size:	Size of the transfer
+ * @val:	Pointer to the buffer receiving the data
+ */
+static void _hv_pcifront_read_config(struct hv_pci_dev *hpdev, int where,
+				     int size, u32 *val)
+{
+	unsigned long flags;
+	void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + where;
+
+	/*
+	 * If the attempt is to read the IDs or the ROM BAR, simulate that.
+	 */
+	if (where + size <= PCI_COMMAND) {
+		memcpy(val, ((u8 *)&hpdev->desc.v_id) + where, size);
+	} else if (where >= PCI_CLASS_REVISION && where + size <=
+		   PCI_CACHE_LINE_SIZE) {
+		memcpy(val, ((u8 *)&hpdev->desc.rev) + where -
+		       PCI_CLASS_REVISION, size);
+	} else if (where >= PCI_SUBSYSTEM_VENDOR_ID && where + size <=
+		   PCI_ROM_ADDRESS) {
+		memcpy(val, (u8 *)&hpdev->desc.subsystem_id + where -
+		       PCI_SUBSYSTEM_VENDOR_ID, size);
+	} else if (where >= PCI_ROM_ADDRESS && where + size <=
+		   PCI_CAPABILITY_LIST) {
+		/* ROM BARs are unimplemented */
+		*val = 0;
+	} else if (where >= PCI_INTERRUPT_LINE && where + size <=
+		   PCI_INTERRUPT_PIN) {
+		/*
+		 * Interrupt Line and Interrupt PIN are hard-wired to zero
+		 * because this front-end only supports message-signaled
+		 * interrupts.
+		 */
+		*val = 0;
+	} else if (where + size <= CFG_PAGE_SIZE) {
+		spin_lock_irqsave(&hpdev->hbus->config_lock, flags);
+		/* Choose the function to be read. (See comment above) */
+		writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr);
+		/* Read from that function's config space. */
+		switch (size) {
+		case 1:
+			*val = readb(addr);
+			break;
+		case 2:
+			*val = readw(addr);
+			break;
+		default:
+			*val = readl(addr);
+			break;
+		}
+		spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags);
+	} else {
+		dev_err(&hpdev->hbus->hdev->device,
+			"Attempt to read beyond a function's config space.\n");
+	}
+}
+
+/**
+ * _hv_pcifront_write_config() - Internal PCI config write
+ * @hpdev:	The PCI driver's representation of the device
+ * @where:	Offset within config space
+ * @size:	Size of the transfer
+ * @val:	The data being transferred
+ */
+static void _hv_pcifront_write_config(struct hv_pci_dev *hpdev, int where,
+				      int size, u32 val)
+{
+	unsigned long flags;
+	void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + where;
+
+	if (where >= PCI_SUBSYSTEM_VENDOR_ID &&
+	    where + size <= PCI_CAPABILITY_LIST) {
+		/* SSIDs and ROM BARs are read-only */
+	} else if (where >= PCI_COMMAND && where + size <= CFG_PAGE_SIZE) {
+		spin_lock_irqsave(&hpdev->hbus->config_lock, flags);
+		/* Choose the function to be written. (See comment above) */
+		writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr);
+		/* Write to that function's config space. */
+		switch (size) {
+		case 1:
+			writeb(val, addr);
+			break;
+		case 2:
+			writew(val, addr);
+			break;
+		default:
+			writel(val, addr);
+			break;
+		}
+		spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags);
+	} else {
+		dev_err(&hpdev->hbus->hdev->device,
+			"Attempt to write beyond a function's config space.\n");
+	}
+}
+
+/**
+ * hv_pcifront_read_config() - Read configuration space
+ * @bus: PCI Bus structure
+ * @devfn: Device/function
+ * @where: Offset from base
+ * @size: Byte/word/dword
+ * @val: Value to be read
+ *
+ * Return: PCIBIOS_SUCCESSFUL on success
+ *	   PCIBIOS_DEVICE_NOT_FOUND on failure
+ */
+static int hv_pcifront_read_config(struct pci_bus *bus, unsigned int devfn,
+				   int where, int size, u32 *val)
+{
+	struct hv_pcibus_device *hbus =
+		container_of(bus->sysdata, struct hv_pcibus_device, sysdata);
+	struct hv_pci_dev *hpdev;
+
+	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(devfn));
+	if (!hpdev)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	_hv_pcifront_read_config(hpdev, where, size, val);
+
+	put_pcichild(hpdev, hv_pcidev_ref_by_slot);
+	return PCIBIOS_SUCCESSFUL;
+}
+
+/**
+ * hv_pcifront_write_config() - Write configuration space
+ * @bus: PCI Bus structure
+ * @devfn: Device/function
+ * @where: Offset from base
+ * @size: Byte/word/dword
+ * @val: Value to be written to device
+ *
+ * Return: PCIBIOS_SUCCESSFUL on success
+ *	   PCIBIOS_DEVICE_NOT_FOUND on failure
+ */
+static int hv_pcifront_write_config(struct pci_bus *bus, unsigned int devfn,
+				    int where, int size, u32 val)
+{
+	struct hv_pcibus_device *hbus =
+	    container_of(bus->sysdata, struct hv_pcibus_device, sysdata);
+	struct hv_pci_dev *hpdev;
+
+	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(devfn));
+	if (!hpdev)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	_hv_pcifront_write_config(hpdev, where, size, val);
+
+	put_pcichild(hpdev, hv_pcidev_ref_by_slot);
+	return PCIBIOS_SUCCESSFUL;
+}
+
+/* PCIe operations */
+static struct pci_ops hv_pcifront_ops = {
+	.read  = hv_pcifront_read_config,
+	.write = hv_pcifront_write_config,
+};
+
+/* Interrupt management hooks */
+static void hv_int_desc_free(struct hv_pci_dev *hpdev,
+			     struct tran_int_desc *int_desc)
+{
+	struct pci_delete_interrupt *int_pkt;
+	struct {
+		struct pci_packet pkt;
+		u8 buffer[sizeof(struct pci_delete_interrupt) -
+			  sizeof(struct pci_message)];
+	} ctxt;
+
+	memset(&ctxt, 0, sizeof(ctxt));
+	int_pkt = (struct pci_delete_interrupt *)&ctxt.pkt.message;
+	int_pkt->message_type.message_type =
+		PCI_DELETE_INTERRUPT_MESSAGE;
+	int_pkt->wslot.slot = hpdev->desc.win_slot.slot;
+	int_pkt->int_desc = *int_desc;
+	vmbus_sendpacket(hpdev->hbus->hdev->channel, int_pkt, sizeof(*int_pkt),
+			 (unsigned long)&ctxt.pkt, VM_PKT_DATA_INBAND, 0);
+	kfree(int_desc);
+}
+
+/**
+ * hv_msi_free() - Free the MSI.
+ * @domain:	The interrupt domain pointer
+ * @info:	Extra MSI-related context
+ * @irq:	Identifies the IRQ.
+ *
+ * The Hyper-V parent partition and hypervisor are tracking the
+ * messages that are in use, keeping the interrupt redirection
+ * table up to date.  This callback sends a message that frees
+ * the IRT entry and related tracking nonsense.
+ */
+static void hv_msi_free(struct irq_domain *domain, struct msi_domain_info *info,
+			unsigned int irq)
+{
+	struct hv_pcibus_device *hbus;
+	struct hv_pci_dev *hpdev;
+	struct pci_dev *pdev;
+	struct tran_int_desc *int_desc;
+	struct irq_data *irq_data = irq_domain_get_irq_data(domain, irq);
+	struct msi_desc *msi = irq_data_get_msi_desc(irq_data);
+
+	pdev = msi_desc_to_pci_dev(msi);
+	hbus = info->data;
+	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn));
+	if (!hpdev)
+		return;
+
+	int_desc = irq_data_get_irq_chip_data(irq_data);
+	if (int_desc) {
+		irq_data->chip_data = NULL;
+		hv_int_desc_free(hpdev, int_desc);
+	}
+
+	put_pcichild(hpdev, hv_pcidev_ref_by_slot);
+}
+
+static int hv_set_affinity(struct irq_data *data, const struct cpumask *dest,
+			   bool force)
+{
+	struct irq_data *parent = data->parent_data;
+
+	return parent->chip->irq_set_affinity(parent, dest, force);
+}
+
+void hv_irq_mask(struct irq_data *data)
+{
+	pci_msi_mask_irq(data);
+}
+
+/**
+ * hv_irq_unmask() - "Unmask" the IRQ by setting its current
+ * affinity.
+ * @data:	Describes the IRQ
+ *
+ * Build new a destination for the MSI and make a hypercall to
+ * update the Interrupt Redirection Table. "Device Logical ID"
+ * is built out of this PCI bus's instance GUID and the function
+ * number of the device.
+ */
+void hv_irq_unmask(struct irq_data *data)
+{
+	struct msi_desc *msi_desc = irq_data_get_msi_desc(data);
+	struct irq_cfg *cfg = irqd_cfg(data);
+	struct retarget_msi_interrupt params;
+	struct hv_pcibus_device *hbus;
+	struct cpumask *dest;
+	struct pci_bus *pbus;
+	struct pci_dev *pdev;
+	int cpu;
+
+	dest = irq_data_get_affinity_mask(data);
+	pdev = msi_desc_to_pci_dev(msi_desc);
+	pbus = pdev->bus;
+	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
+
+	memset(&params, 0, sizeof(params));
+	params.partition_id = HV_PARTITION_ID_SELF;
+	params.source = 1; /* MSI(-X) */
+	params.address = msi_desc->msg.address_lo;
+	params.data = msi_desc->msg.data;
+	params.device_id = (hbus->hdev->dev_instance.b[5] << 24) |
+			   (hbus->hdev->dev_instance.b[4] << 16) |
+			   (hbus->hdev->dev_instance.b[7] << 8) |
+			   (hbus->hdev->dev_instance.b[6] & 0xf8) |
+			   PCI_FUNC(pdev->devfn);
+	params.vector = cfg->vector;
+
+	for_each_cpu_and(cpu, dest, cpu_online_mask)
+		params.vp_mask |= (1ULL << vmbus_cpu_number_to_vp_number(cpu));
+
+	hv_do_hypercall(HVCALL_RETARGET_INTERRUPT, &params, NULL);
+
+	pci_msi_unmask_irq(data);
+}
+
+struct compose_comp_ctxt {
+	struct hv_pci_compl comp_pkt;
+	struct tran_int_desc int_desc;
+};
+
+static void hv_pci_compose_compl(void *context, struct pci_response *resp,
+				 int resp_packet_size)
+{
+	struct compose_comp_ctxt *comp_pkt = context;
+	struct pci_create_int_response *int_resp =
+		(struct pci_create_int_response *)resp;
+
+	comp_pkt->comp_pkt.completion_status = resp->status;
+	comp_pkt->int_desc = int_resp->int_desc;
+	complete(&comp_pkt->comp_pkt.host_event);
+}
+
+/**
+ * hv_compose_msi_msg() - Supplies a valid MSI address/data
+ * @data:	Everything about this MSI
+ * @msg:	Buffer that is filled in by this function
+ *
+ * This function unpacks the IRQ looking for target CPU set, IDT
+ * vector and mode and sends a message to the parent partition
+ * asking for a mapping for that tuple in this partition.  The
+ * response supplies a data value and address to which that data
+ * should be written to trigger that interrupt.
+ */
+static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	struct irq_cfg *cfg = irqd_cfg(data);
+	struct hv_pcibus_device *hbus;
+	struct hv_pci_dev *hpdev;
+	struct pci_bus *pbus;
+	struct pci_dev *pdev;
+	struct pci_create_interrupt *int_pkt;
+	struct compose_comp_ctxt comp;
+	struct tran_int_desc *int_desc;
+	struct cpumask *affinity;
+	struct {
+		struct pci_packet pkt;
+		u8 buffer[sizeof(struct pci_create_interrupt) -
+			  sizeof(struct pci_message)];
+	} ctxt;
+	int cpu;
+	int ret;
+
+	pdev = msi_desc_to_pci_dev(irq_data_get_msi_desc(data));
+	pbus = pdev->bus;
+	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
+	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn));
+	if (!hpdev)
+		goto return_null_message;
+
+	/* Free any previous message that might have already been composed. */
+	if (data->chip_data) {
+		int_desc = data->chip_data;
+		data->chip_data = NULL;
+		hv_int_desc_free(hpdev, int_desc);
+	}
+
+	int_desc = kzalloc(sizeof(*int_desc), GFP_KERNEL);
+	if (!int_desc)
+		goto drop_reference;
+
+	memset(&ctxt, 0, sizeof(ctxt));
+	init_completion(&comp.comp_pkt.host_event);
+	ctxt.pkt.completion_func = hv_pci_compose_compl;
+	ctxt.pkt.compl_ctxt = &comp;
+	int_pkt = (struct pci_create_interrupt *)&ctxt.pkt.message;
+	int_pkt->message_type.message_type = PCI_CREATE_INTERRUPT_MESSAGE;
+	int_pkt->wslot.slot = hpdev->desc.win_slot.slot;
+	int_pkt->int_desc.vector = cfg->vector;
+	int_pkt->int_desc.vector_count = 1;
+	int_pkt->int_desc.delivery_mode =
+		(apic->irq_delivery_mode == dest_LowestPrio) ? 1 : 0;
+
+	/*
+	 * This bit doesn't have to work on machines with more than 64
+	 * processors because Hyper-V only supports 64 in a guest.
+	 */
+	affinity = irq_data_get_affinity_mask(data);
+	for_each_cpu_and(cpu, affinity, cpu_online_mask) {
+		int_pkt->int_desc.cpu_mask |=
+			(1ULL << vmbus_cpu_number_to_vp_number(cpu));
+	}
+
+	ret = vmbus_sendpacket(hpdev->hbus->hdev->channel, int_pkt,
+			       sizeof(*int_pkt), (unsigned long)&ctxt.pkt,
+			       VM_PKT_DATA_INBAND,
+			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+	if (!ret)
+		wait_for_completion(&comp.comp_pkt.host_event);
+
+	if (comp.comp_pkt.completion_status < 0) {
+		dev_err(&hbus->hdev->device,
+			"Request for interrupt failed: 0x%x",
+			comp.comp_pkt.completion_status);
+		goto free_int_desc;
+	}
+
+	/*
+	 * Record the assignment so that this can be unwound later. Using
+	 * irq_set_chip_data() here would be appropriate, but the lock it takes
+	 * is already held.
+	 */
+	*int_desc = comp.int_desc;
+	data->chip_data = int_desc;
+
+	/* Pass up the result. */
+	msg->address_hi = comp.int_desc.address >> 32;
+	msg->address_lo = comp.int_desc.address & 0xffffffff;
+	msg->data = comp.int_desc.data;
+
+	put_pcichild(hpdev, hv_pcidev_ref_by_slot);
+	return;
+
+free_int_desc:
+	kfree(int_desc);
+drop_reference:
+	put_pcichild(hpdev, hv_pcidev_ref_by_slot);
+return_null_message:
+	msg->address_hi = 0;
+	msg->address_lo = 0;
+	msg->data = 0;
+}
+
+/* HW Interrupt Chip Descriptor */
+static struct irq_chip hv_msi_irq_chip = {
+	.name			= "Hyper-V PCIe MSI",
+	.irq_compose_msi_msg	= hv_compose_msi_msg,
+	.irq_set_affinity	= hv_set_affinity,
+	.irq_ack		= irq_chip_ack_parent,
+	.irq_mask		= hv_irq_mask,
+	.irq_unmask		= hv_irq_unmask,
+};
+
+static irq_hw_number_t hv_msi_domain_ops_get_hwirq(struct msi_domain_info *info,
+						   msi_alloc_info_t *arg)
+{
+	return arg->msi_hwirq;
+}
+
+static struct msi_domain_ops hv_msi_ops = {
+	.get_hwirq	= hv_msi_domain_ops_get_hwirq,
+	.msi_prepare	= pci_msi_prepare,
+	.set_desc	= pci_msi_set_desc,
+	.msi_free	= hv_msi_free,
+};
+
+/**
+ * hv_pcie_init_irq_domain() - Initialize IRQ domain
+ * @hbus:	The root PCI bus
+ *
+ * This function creates an IRQ domain which will be used for
+ * interrupts from devices that have been passed through.  These
+ * devices only support MSI and MSI-X, not line-based interrupts
+ * or simulations of line-based interrupts through PCIe's
+ * fabric-layer messages.  Because interrupts are remapped, we
+ * can support multi-message MSI here.
+ *
+ * Return: '0' on success and error value on failure
+ */
+static int hv_pcie_init_irq_domain(struct hv_pcibus_device *hbus)
+{
+	hbus->msi_info.chip = &hv_msi_irq_chip;
+	hbus->msi_info.ops = &hv_msi_ops;
+	hbus->msi_info.flags = (MSI_FLAG_USE_DEF_DOM_OPS |
+		MSI_FLAG_USE_DEF_CHIP_OPS | MSI_FLAG_MULTI_PCI_MSI |
+		MSI_FLAG_PCI_MSIX);
+	hbus->msi_info.handler = handle_edge_irq;
+	hbus->msi_info.handler_name = "edge";
+	hbus->msi_info.data = hbus;
+	hbus->irq_domain = pci_msi_create_irq_domain(hbus->sysdata.fwnode,
+						     &hbus->msi_info,
+						     x86_vector_domain);
+	if (!hbus->irq_domain) {
+		dev_err(&hbus->hdev->device,
+			"Failed to build an MSI IRQ domain\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+/**
+ * get_bar_size() - Get the address space consumed by a BAR
+ * @bar_val:	Value that a BAR returned after -1 was written
+ *              to it.
+ *
+ * This function returns the size of the BAR, rounded up to 1
+ * page.  It has to be rounded up because the hypervisor's page
+ * table entry that maps the BAR into the VM can't specify an
+ * offset within a page.  The invariant is that the hypervisor
+ * must place any BARs of smaller than page length at the
+ * beginning of a page.
+ *
+ * Return:	Size in bytes of the consumed MMIO space.
+ */
+static u64 get_bar_size(u64 bar_val)
+{
+	return round_up((1 + ~(bar_val & PCI_BASE_ADDRESS_MEM_MASK)),
+			PAGE_SIZE);
+}
+
+/**
+ * survey_child_resources() - Total all MMIO requirements
+ * @hbus:	Root PCI bus, as understood by this driver
+ */
+static void survey_child_resources(struct hv_pcibus_device *hbus)
+{
+	struct list_head *iter;
+	struct hv_pci_dev *hpdev;
+	resource_size_t bar_size = 0;
+	unsigned long flags;
+	struct completion *event;
+	u64 bar_val;
+	int i;
+
+	/* If nobody is waiting on the answer, don't compute it. */
+	event = xchg(&hbus->survey_event, NULL);
+	if (!event)
+		return;
+
+	/* If the answer has already been computed, go with it. */
+	if (hbus->low_mmio_space || hbus->high_mmio_space) {
+		complete(event);
+		return;
+	}
+
+	spin_lock_irqsave(&hbus->device_list_lock, flags);
+
+	/*
+	 * Due to an interesting quirk of the PCI spec, all memory regions
+	 * for a child device are a power of 2 in size and aligned in memory,
+	 * so it's sufficient to just add them up without tracking alignment.
+	 */
+	list_for_each(iter, &hbus->children) {
+		hpdev = container_of(iter, struct hv_pci_dev, list_entry);
+		for (i = 0; i < 6; i++) {
+			if (hpdev->probed_bar[i] & PCI_BASE_ADDRESS_SPACE_IO)
+				dev_err(&hbus->hdev->device,
+					"There's an I/O BAR in this list!\n");
+
+			if (hpdev->probed_bar[i] != 0) {
+				/*
+				 * A probed BAR has all the upper bits set that
+				 * can be changed.
+				 */
+
+				bar_val = hpdev->probed_bar[i];
+				if (bar_val & PCI_BASE_ADDRESS_MEM_TYPE_64)
+					bar_val |=
+					((u64)hpdev->probed_bar[++i] << 32);
+				else
+					bar_val |= 0xffffffff00000000ULL;
+
+				bar_size = get_bar_size(bar_val);
+
+				if (bar_val & PCI_BASE_ADDRESS_MEM_TYPE_64)
+					hbus->high_mmio_space += bar_size;
+				else
+					hbus->low_mmio_space += bar_size;
+			}
+		}
+	}
+
+	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
+	complete(event);
+}
+
+/**
+ * prepopulate_bars() - Fill in BARs with defaults
+ * @hbus:	Root PCI bus, as understood by this driver
+ *
+ * The core PCI driver code seems much, much happier if the BARs
+ * for a device have values upon first scan. So fill them in.
+ * The algorithm below works down from large sizes to small,
+ * attempting to pack the assignments optimally. The assumption,
+ * enforced in other parts of the code, is that the beginning of
+ * the memory-mapped I/O space will be aligned on the largest
+ * BAR size.
+ */
+static void prepopulate_bars(struct hv_pcibus_device *hbus)
+{
+	resource_size_t high_size = 0;
+	resource_size_t low_size = 0;
+	resource_size_t high_base = 0;
+	resource_size_t low_base = 0;
+	resource_size_t bar_size;
+	struct hv_pci_dev *hpdev;
+	struct list_head *iter;
+	unsigned long flags;
+	u64 bar_val;
+	u32 command;
+	bool high;
+	int i;
+
+	if (hbus->low_mmio_space) {
+		low_size = 1ULL << (63 - __builtin_clzll(hbus->low_mmio_space));
+		low_base = hbus->low_mmio_res->start;
+	}
+
+	if (hbus->high_mmio_space) {
+		high_size = 1ULL <<
+			(63 - __builtin_clzll(hbus->high_mmio_space));
+		high_base = hbus->high_mmio_res->start;
+	}
+
+	spin_lock_irqsave(&hbus->device_list_lock, flags);
+
+	/* Pick addresses for the BARs. */
+	do {
+		list_for_each(iter, &hbus->children) {
+			hpdev = container_of(iter, struct hv_pci_dev,
+					     list_entry);
+			for (i = 0; i < 6; i++) {
+				bar_val = hpdev->probed_bar[i];
+				if (bar_val == 0)
+					continue;
+				high = bar_val & PCI_BASE_ADDRESS_MEM_TYPE_64;
+				if (high) {
+					bar_val |=
+						((u64)hpdev->probed_bar[i + 1]
+						 << 32);
+				} else {
+					bar_val |= 0xffffffffULL << 32;
+				}
+				bar_size = get_bar_size(bar_val);
+				if (high) {
+					if (high_size != bar_size) {
+						i++;
+						continue;
+					}
+					_hv_pcifront_write_config(hpdev,
+						PCI_BASE_ADDRESS_0 + (4 * i),
+						4,
+						(u32)(high_base & 0xffffff00));
+					i++;
+					_hv_pcifront_write_config(hpdev,
+						PCI_BASE_ADDRESS_0 + (4 * i),
+						4, (u32)(high_base >> 32));
+					high_base += bar_size;
+				} else {
+					if (low_size != bar_size)
+						continue;
+					_hv_pcifront_write_config(hpdev,
+						PCI_BASE_ADDRESS_0 + (4 * i),
+						4,
+						(u32)(low_base & 0xffffff00));
+					low_base += bar_size;
+				}
+			}
+			if (high_size <= 1 && low_size <= 1) {
+				/* Set the memory enable bit. */
+				_hv_pcifront_read_config(hpdev, PCI_COMMAND, 2,
+							 &command);
+				command |= PCI_COMMAND_MEMORY;
+				_hv_pcifront_write_config(hpdev, PCI_COMMAND, 2,
+							  command);
+				break;
+			}
+		}
+
+		high_size >>= 1;
+		low_size >>= 1;
+	}  while (high_size || low_size);
+
+	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
+}
+
+/**
+ * create_root_hv_pci_bus() - Expose a new root PCI bus
+ * @hbus:	Root PCI bus, as understood by this driver
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int create_root_hv_pci_bus(struct hv_pcibus_device *hbus)
+{
+	/* Register the device */
+	hbus->pci_bus = pci_create_root_bus(&hbus->hdev->device,
+					    0, /* bus number is always zero */
+					    &hv_pcifront_ops,
+					    &hbus->sysdata,
+					    &hbus->resources_for_children);
+	if (!hbus->pci_bus)
+		return -ENODEV;
+
+	hbus->pci_bus->msi = &hbus->msi_chip;
+	hbus->pci_bus->msi->dev = &hbus->hdev->device;
+
+	pci_scan_child_bus(hbus->pci_bus);
+	pci_bus_assign_resources(hbus->pci_bus);
+	pci_bus_add_devices(hbus->pci_bus);
+	hbus->state = hv_pcibus_installed;
+	return 0;
+}
+
+struct q_res_req_compl {
+	struct completion host_event;
+	struct hv_pci_dev *hpdev;
+};
+
+/**
+ * q_resource_requirements() - Query Resource Requirements
+ * @context:		The completion context.
+ * @resp:		The response that came from the host.
+ * @resp_packet_size:	The size in bytes of resp.
+ *
+ * This function is invoked on completion of a Query Resource
+ * Requirements packet.
+ */
+static void q_resource_requirements(void *context, struct pci_response *resp,
+				    int resp_packet_size)
+{
+	struct q_res_req_compl *completion = context;
+	struct pci_q_res_req_response *q_res_req =
+		(struct pci_q_res_req_response *)resp;
+	int i;
+
+	if (resp->status < 0) {
+		dev_err(&completion->hpdev->hbus->hdev->device,
+			"query resource requirements failed: %x\n",
+			resp->status);
+	} else {
+		for (i = 0; i < 6; i++) {
+			completion->hpdev->probed_bar[i] =
+				q_res_req->probed_bar[i];
+		}
+	}
+
+	complete(&completion->host_event);
+}
+
+static void get_pcichild(struct hv_pci_dev *hpdev,
+			    enum hv_pcidev_ref_reason reason)
+{
+	atomic_inc(&hpdev->refs);
+}
+
+static void put_pcichild(struct hv_pci_dev *hpdev,
+			    enum hv_pcidev_ref_reason reason)
+{
+	if (atomic_dec_and_test(&hpdev->refs))
+		kfree(hpdev);
+}
+
+/**
+ * new_pcichild_device() - Create a new child device
+ * @hbus:	The internal struct tracking this root PCI bus.
+ * @desc:	The information supplied so far from the host
+ *              about the device.
+ *
+ * This function creates the tracking structure for a new child
+ * device and kicks off the process of figuring out what it is.
+ *
+ * Return: Pointer to the new tracking struct
+ */
+static struct hv_pci_dev *new_pcichild_device(struct hv_pcibus_device *hbus,
+		struct pci_function_description *desc)
+{
+	struct hv_pci_dev *hpdev;
+	struct pci_child_message *res_req;
+	struct q_res_req_compl comp_pkt;
+	union {
+	struct pci_packet init_packet;
+		u8 buffer[0x100];
+	} pkt;
+	unsigned long flags;
+	int ret;
+
+	hpdev = kzalloc(sizeof(*hpdev), GFP_ATOMIC);
+	if (!hpdev)
+		return NULL;
+
+	hpdev->hbus = hbus;
+
+	memset(&pkt, 0, sizeof(pkt));
+	init_completion(&comp_pkt.host_event);
+	comp_pkt.hpdev = hpdev;
+	pkt.init_packet.compl_ctxt = &comp_pkt;
+	pkt.init_packet.completion_func = q_resource_requirements;
+	res_req = (struct pci_child_message *)&pkt.init_packet.message;
+	res_req->message_type = PCI_QUERY_RESOURCE_REQUIREMENTS;
+	res_req->wslot.slot = desc->win_slot.slot;
+
+	ret = vmbus_sendpacket(hbus->hdev->channel, res_req,
+			       sizeof(struct pci_child_message),
+			       (unsigned long)&pkt.init_packet,
+			       VM_PKT_DATA_INBAND,
+			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+	if (ret)
+		goto error;
+
+	wait_for_completion(&comp_pkt.host_event);
+
+	hpdev->desc = *desc;
+	get_pcichild(hpdev, hv_pcidev_ref_initial);
+	get_pcichild(hpdev, hv_pcidev_ref_childlist);
+	spin_lock_irqsave(&hbus->device_list_lock, flags);
+	list_add_tail(&hpdev->list_entry, &hbus->children);
+	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
+	return hpdev;
+
+error:
+	kfree(hpdev);
+	return NULL;
+}
+
+/**
+ * get_pcichild_wslot() - Find device from slot
+ * @hbus:	Root PCI bus, as understood by this driver
+ * @wslot:	Location on the bus
+ *
+ * This function looks up a PCI device and returns the internal
+ * representation of it.  It acquires a reference on it, so that
+ * the device won't be deleted while somebody is using it.  The
+ * caller is responsible for calling put_pcichild() to release
+ * this reference.
+ *
+ * Return:	Internal representation of a PCI device
+ */
+static struct hv_pci_dev *get_pcichild_wslot(struct hv_pcibus_device *hbus,
+					     u32 wslot)
+{
+	unsigned long flags;
+	struct hv_pci_dev *iter, *hpdev = NULL;
+
+	spin_lock_irqsave(&hbus->device_list_lock, flags);
+	list_for_each_entry(iter, &hbus->children, list_entry) {
+		if (iter->desc.win_slot.slot == wslot) {
+			hpdev = iter;
+			get_pcichild(hpdev, hv_pcidev_ref_by_slot);
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
+
+	return hpdev;
+}
+
+/**
+ * pci_devices_present_work() - Handle new list of child devices
+ * @work:	Work struct embedded in struct hv_dr_work
+ *
+ * "Bus Relations" is the Windows term for "children of this
+ * bus."  The terminology is preserved here for people trying to
+ * debug the interaction between Hyper-V and Linux.  This
+ * function is called when the parent partition reports a list
+ * of functions that should be observed under this PCI Express
+ * port (bus).
+ *
+ * This function updates the list, and must tolerate being
+ * called multiple times with the same information.  The typical
+ * number of child devices is one, with very atypical cases
+ * involving three or four, so the algorithms used here can be
+ * simple and inefficient.
+ *
+ * It must also treat the omission of a previously observed device as
+ * notification that the device no longer exists.
+ *
+ * Note that this function is a work item, and it may not be
+ * invoked in the order that it was queued.  Back to back
+ * updates of the list of present devices may involve queuing
+ * multiple work items, and this one may run before ones that
+ * were sent later. As such, this function only does something
+ * if is the last one in the queue.
+ */
+static void pci_devices_present_work(struct work_struct *work)
+{
+	u32 child_no;
+	bool found;
+	struct list_head *iter;
+	struct pci_function_description *new_desc;
+	struct hv_pci_dev *hpdev;
+	struct hv_pcibus_device *hbus;
+	struct list_head removed;
+	struct hv_dr_work *dr_wrk;
+	struct hv_dr_state *dr = NULL;
+	unsigned long flags;
+
+	dr_wrk = container_of(work, struct hv_dr_work, wrk);
+	hbus = dr_wrk->bus;
+	kfree(dr_wrk);
+
+	INIT_LIST_HEAD(&removed);
+
+	if (down_interruptible(&hbus->enum_sem)) {
+		put_hvpcibus(hbus);
+		return;
+	}
+
+	/* Pull this off the queue and process it if it was the last one. */
+	spin_lock_irqsave(&hbus->device_list_lock, flags);
+	while (!list_empty(&hbus->dr_list)) {
+		dr = list_first_entry(&hbus->dr_list, struct hv_dr_state,
+				      list_entry);
+		list_del(&dr->list_entry);
+
+		/* Throw this away if the list still has stuff in it. */
+		if (!list_empty(&hbus->dr_list)) {
+			kfree(dr);
+			continue;
+		}
+	}
+	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
+
+	if (!dr) {
+		up(&hbus->enum_sem);
+		put_hvpcibus(hbus);
+		return;
+	}
+
+	/* First, mark all existing children as reported missing. */
+	spin_lock_irqsave(&hbus->device_list_lock, flags);
+	list_for_each(iter, &hbus->children) {
+			hpdev = container_of(iter, struct hv_pci_dev,
+					     list_entry);
+			hpdev->reported_missing = true;
+	}
+	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
+
+	/* Next, add back any reported devices. */
+	for (child_no = 0; child_no < dr->device_count; child_no++) {
+		found = false;
+		new_desc = &dr->func[child_no];
+
+		spin_lock_irqsave(&hbus->device_list_lock, flags);
+		list_for_each(iter, &hbus->children) {
+			hpdev = container_of(iter, struct hv_pci_dev,
+					     list_entry);
+			if ((hpdev->desc.win_slot.slot ==
+			     new_desc->win_slot.slot) &&
+			    (hpdev->desc.v_id == new_desc->v_id) &&
+			    (hpdev->desc.d_id == new_desc->d_id) &&
+			    (hpdev->desc.ser == new_desc->ser)) {
+				hpdev->reported_missing = false;
+				found = true;
+			}
+		}
+		spin_unlock_irqrestore(&hbus->device_list_lock, flags);
+
+		if (!found) {
+			hpdev = new_pcichild_device(hbus, new_desc);
+			if (!hpdev)
+				dev_err(&hbus->hdev->device,
+					"couldn't record a child device.\n");
+		}
+	}
+
+	/* Move missing children to a list on the stack. */
+	spin_lock_irqsave(&hbus->device_list_lock, flags);
+	do {
+		found = false;
+		list_for_each(iter, &hbus->children) {
+			hpdev = container_of(iter, struct hv_pci_dev,
+					     list_entry);
+			if (hpdev->reported_missing) {
+				found = true;
+				put_pcichild(hpdev, hv_pcidev_ref_childlist);
+				list_del(&hpdev->list_entry);
+				list_add_tail(&hpdev->list_entry, &removed);
+				break;
+			}
+		}
+	} while (found);
+	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
+
+	/* Delete everything that should no longer exist. */
+	while (!list_empty(&removed)) {
+		hpdev = list_first_entry(&removed, struct hv_pci_dev,
+					 list_entry);
+		list_del(&hpdev->list_entry);
+		put_pcichild(hpdev, hv_pcidev_ref_initial);
+	}
+
+	/* Tell the core to rescan bus because there may have been changes. */
+	if (hbus->state == hv_pcibus_installed) {
+		pci_lock_rescan_remove();
+		pci_scan_child_bus(hbus->pci_bus);
+		pci_unlock_rescan_remove();
+	} else {
+		survey_child_resources(hbus);
+	}
+
+	up(&hbus->enum_sem);
+	put_hvpcibus(hbus);
+	kfree(dr);
+}
+
+/**
+ * hv_pci_devices_present() - Handles list of new children
+ * @hbus:	Root PCI bus, as understood by this driver
+ * @relations:	Packet from host listing children
+ *
+ * This function is invoked whenever a new list of devices for
+ * this bus appears.
+ */
+static void hv_pci_devices_present(struct hv_pcibus_device *hbus,
+				   struct pci_bus_relations *relations)
+{
+	struct hv_dr_state *dr;
+	struct hv_dr_work *dr_wrk;
+	unsigned long flags;
+
+	dr_wrk = kzalloc(sizeof(*dr_wrk), GFP_NOWAIT);
+	if (!dr_wrk)
+		return;
+
+	dr = kzalloc(offsetof(struct hv_dr_state, func) +
+		     (sizeof(struct pci_function_description) *
+		      (relations->device_count)), GFP_NOWAIT);
+	if (!dr)  {
+		kfree(dr_wrk);
+		return;
+	}
+
+	INIT_WORK(&dr_wrk->wrk, pci_devices_present_work);
+	dr_wrk->bus = hbus;
+	dr->device_count = relations->device_count;
+	if (dr->device_count != 0) {
+		memcpy(dr->func, relations->func,
+		       sizeof(struct pci_function_description) *
+		       dr->device_count);
+	}
+
+	spin_lock_irqsave(&hbus->device_list_lock, flags);
+	list_add_tail(&dr->list_entry, &hbus->dr_list);
+	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
+
+	get_hvpcibus(hbus);
+	schedule_work(&dr_wrk->wrk);
+}
+
+/**
+ * hv_eject_device_work() - Asynchronously handles ejection
+ * @work:	Work struct embedded in internal device struct
+ *
+ * This function handles ejecting a device.  Windows will
+ * attempt to gracefully eject a device, waiting 60 seconds to
+ * hear back from the guest OS that this completed successfully.
+ * If this timer expires, the device will be forcibly removed.
+ */
+static void hv_eject_device_work(struct work_struct *work)
+{
+	struct pci_eject_response *ejct_pkt;
+	struct hv_pci_dev *hpdev;
+	struct pci_dev *pdev;
+	unsigned long flags;
+	int wslot;
+	struct {
+		struct pci_packet pkt;
+		u8 buffer[sizeof(struct pci_eject_response) -
+			  sizeof(struct pci_message)];
+	} ctxt;
+
+	hpdev = container_of(work, struct hv_pci_dev, wrk);
+
+	if (hpdev->state != hv_pcichild_ejecting) {
+		put_pcichild(hpdev, hv_pcidev_ref_pnp);
+		return;
+	}
+
+	/*
+	 * Ejection can come before or after the PCI bus has been set up, so
+	 * attempt to find it and tear down the bus state, if it exists.  This
+	 * must be done without constructs like pci_domain_nr(hbus->pci_bus)
+	 * because hbus->pci_bus may not exist yet.
+	 */
+	wslot = wslot_to_devfn(hpdev->desc.win_slot.slot);
+	pdev = pci_get_domain_bus_and_slot(hpdev->hbus->sysdata.domain, 0,
+					   wslot);
+	if (pdev) {
+		pci_stop_and_remove_bus_device(pdev);
+		pci_dev_put(pdev);
+	}
+
+	memset(&ctxt, 0, sizeof(ctxt));
+	ejct_pkt = (struct pci_eject_response *)&ctxt.pkt.message;
+	ejct_pkt->message_type = PCI_EJECTION_COMPLETE;
+	ejct_pkt->wslot.slot = hpdev->desc.win_slot.slot;
+	vmbus_sendpacket(hpdev->hbus->hdev->channel, ejct_pkt,
+			 sizeof(*ejct_pkt), (unsigned long)&ctxt.pkt,
+			 VM_PKT_DATA_INBAND, 0);
+
+	spin_lock_irqsave(&hpdev->hbus->device_list_lock, flags);
+	list_del(&hpdev->list_entry);
+	spin_unlock_irqrestore(&hpdev->hbus->device_list_lock, flags);
+
+	put_pcichild(hpdev, hv_pcidev_ref_childlist);
+	put_pcichild(hpdev, hv_pcidev_ref_pnp);
+	put_hvpcibus(hpdev->hbus);
+}
+
+/**
+ * hv_pci_eject_device() - Handles device ejection
+ * @hpdev:	Internal device tracking struct
+ *
+ * This function is invoked when an ejection packet arrives.  It
+ * just schedules work so that we don't re-enter the packet
+ * delivery code handling the ejection.
+ */
+static void hv_pci_eject_device(struct hv_pci_dev *hpdev)
+{
+	hpdev->state = hv_pcichild_ejecting;
+	get_pcichild(hpdev, hv_pcidev_ref_pnp);
+	INIT_WORK(&hpdev->wrk, hv_eject_device_work);
+	get_hvpcibus(hpdev->hbus);
+	schedule_work(&hpdev->wrk);
+}
+
+/**
+ * hv_pci_onchannelcallback() - Handles incoming packets
+ * @context:	Internal bus tracking struct
+ *
+ * This function is invoked whenever the host sends a packet to
+ * this channel (which is private to this root PCI bus).
+ */
+static void hv_pci_onchannelcallback(void *context)
+{
+	const int packet_size = 0x100;
+	int ret;
+	struct hv_pcibus_device *hbus = context;
+	u32 bytes_recvd;
+	u64 req_id;
+	struct vmpacket_descriptor *desc;
+	unsigned char *buffer;
+	int bufferlen = packet_size;
+	struct pci_packet *comp_packet;
+	struct pci_response *response;
+	struct pci_incoming_message *new_message;
+	struct pci_bus_relations *bus_rel;
+	struct pci_dev_incoming *dev_message;
+	struct hv_pci_dev *hpdev;
+
+	buffer = kmalloc(bufferlen, GFP_ATOMIC);
+	if (!buffer)
+		return;
+
+	while (1) {
+		ret = vmbus_recvpacket_raw(hbus->hdev->channel, buffer,
+					   bufferlen, &bytes_recvd, &req_id);
+
+		if (ret == -ENOBUFS) {
+			kfree(buffer);
+			/* Handle large packet */
+			bufferlen = bytes_recvd;
+			buffer = kmalloc(bytes_recvd, GFP_ATOMIC);
+			if (!buffer)
+				return;
+			continue;
+		}
+
+		/*
+		 * All incoming packets must be at least as large as a
+		 * response.
+		 */
+		if (bytes_recvd <= sizeof(struct pci_response)) {
+			kfree(buffer);
+			return;
+		}
+		desc = (struct vmpacket_descriptor *)buffer;
+
+		switch (desc->type) {
+		case VM_PKT_COMP:
+
+			/*
+			 * The host is trusted, and thus it's safe to interpret
+			 * this transaction ID as a pointer.
+			 */
+			comp_packet = (struct pci_packet *)req_id;
+			response = (struct pci_response *)buffer;
+			comp_packet->completion_func(comp_packet->compl_ctxt,
+						     response,
+						     bytes_recvd);
+			kfree(buffer);
+			return;
+
+		case VM_PKT_DATA_INBAND:
+
+			new_message = (struct pci_incoming_message *)buffer;
+			switch (new_message->message_type.message_type) {
+			case PCI_BUS_RELATIONS:
+
+				bus_rel = (struct pci_bus_relations *)buffer;
+				if (bytes_recvd <
+				    offsetof(struct pci_bus_relations, func) +
+				    (sizeof(struct pci_function_description) *
+				     (bus_rel->device_count))) {
+					dev_err(&hbus->hdev->device,
+						"bus relations too small\n");
+					break;
+				}
+
+				hv_pci_devices_present(hbus, bus_rel);
+				break;
+
+			case PCI_EJECT:
+
+				dev_message = (struct pci_dev_incoming *)buffer;
+				hpdev = get_pcichild_wslot(hbus,
+						      dev_message->wslot.slot);
+				if (hpdev) {
+					hv_pci_eject_device(hpdev);
+					put_pcichild(hpdev,
+							hv_pcidev_ref_by_slot);
+				}
+				break;
+
+			default:
+				dev_warn(&hbus->hdev->device,
+					"Unimplemented protocol message %x\n",
+					new_message->message_type.message_type);
+				break;
+			}
+			break;
+
+		default:
+			dev_err(&hbus->hdev->device,
+				"unhandled packet type %d, tid %llx len %d\n",
+				desc->type, req_id, bytes_recvd);
+			break;
+		}
+		break;
+	}
+}
+
+/**
+ * hv_pci_protocol_negotiation() - Set up protocol
+ * @hdev:	VMBus's tracking struct for this root PCI bus
+ *
+ * This driver is intended to support running on Windows 10
+ * (server) and later versions. It will not run on earlier
+ * versions, as they assume that many of the operations which
+ * Linux needs accomplished with a spinlock held were done via
+ * asynchronous messaging via VMBus.  Windows 10 increases the
+ * surface area of PCI emulation so that these actions can take
+ * place by suspending a virtual processor for their duration.
+ *
+ * This function negotiates the channel protocol version,
+ * failing if the host doesn't support the necessary protocol
+ * level.
+ */
+static int hv_pci_protocol_negotiation(struct hv_device *hdev)
+{
+	struct pci_version_request *version_req;
+	struct hv_pci_compl comp_pkt;
+	struct pci_packet *pkt;
+	int ret;
+
+	/*
+	 * Initiate the handshake with the host and negotiate
+	 * a version that the host can support. We start with the
+	 * highest version number and go down if the host cannot
+	 * support it.
+	 */
+	pkt = kzalloc(sizeof(*pkt) + sizeof(*version_req), GFP_KERNEL);
+	if (!pkt)
+		return -ENOMEM;
+
+	init_completion(&comp_pkt.host_event);
+	pkt->completion_func = hv_pci_generic_compl;
+	pkt->compl_ctxt = &comp_pkt;
+	version_req = (struct pci_version_request *)&pkt->message;
+	version_req->message_type.message_type = PCI_QUERY_PROTOCOL_VERSION;
+	version_req->protocol_version = PCI_PROTOCOL_VERSION_CURRENT;
+
+	ret = vmbus_sendpacket(hdev->channel, version_req,
+			       sizeof(struct pci_version_request),
+			       (unsigned long)pkt, VM_PKT_DATA_INBAND,
+			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+	if (ret)
+		goto exit;
+
+	wait_for_completion(&comp_pkt.host_event);
+
+	if (comp_pkt.completion_status < 0) {
+		dev_err(&hdev->device,
+			"PCI Pass-through VSP failed version request %x\n",
+			comp_pkt.completion_status);
+		ret = -EPROTO;
+		goto exit;
+	}
+
+	ret = 0;
+
+exit:
+	kfree(pkt);
+	return ret;
+}
+
+/**
+ * hv_pci_free_bridge_windows() - Release memory regions for the
+ * bus
+ * @hbus:	Root PCI bus, as understood by this driver
+ */
+static void hv_pci_free_bridge_windows(struct hv_pcibus_device *hbus)
+{
+	/*
+	 * Set the resources back to the way they looked when they
+	 * were allocated by setting IORESOURCE_BUSY again.
+	 */
+
+	if (hbus->low_mmio_space && hbus->low_mmio_res) {
+		hbus->low_mmio_res->flags |= IORESOURCE_BUSY;
+		release_mem_region(hbus->low_mmio_res->start,
+				   resource_size(hbus->low_mmio_res));
+	}
+
+	if (hbus->high_mmio_space && hbus->high_mmio_res) {
+		hbus->high_mmio_res->flags |= IORESOURCE_BUSY;
+		release_mem_region(hbus->high_mmio_res->start,
+				   resource_size(hbus->high_mmio_res));
+	}
+}
+
+/**
+ * hv_pci_allocate_bridge_windows() - Allocate memory regions
+ * for the bus
+ * @hbus:	Root PCI bus, as understood by this driver
+ *
+ * This function calls vmbus_allocate_mmio(), which is itself a
+ * bit of a compromise.  Ideally, we might change the pnp layer
+ * in the kernel such that it comprehends either PCI devices
+ * which are "grandchildren of ACPI," with some intermediate bus
+ * node (in this case, VMBus) or change it such that it
+ * understands VMBus.  The pnp layer, however, has been declared
+ * deprecated, and not subject to change.
+ *
+ * The workaround, implemented here, is to ask VMBus to allocate
+ * MMIO space for this bus.  VMBus itself knows which ranges are
+ * appropriate by looking at its own ACPI objects.  Then, after
+ * these ranges are claimed, they're modified to look like they
+ * would have looked if the ACPI and pnp code had allocated
+ * bridge windows.  These descriptors have to exist in this form
+ * in order to satisfy the code which will get invoked when the
+ * endpoint PCI function driver calls request_mem_region() or
+ * request_mem_region_exclusive().
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int hv_pci_allocate_bridge_windows(struct hv_pcibus_device *hbus)
+{
+	resource_size_t align;
+	int ret;
+
+	if (hbus->low_mmio_space) {
+		align = 1ULL << (63 - __builtin_clzll(hbus->low_mmio_space));
+		ret = vmbus_allocate_mmio(&hbus->low_mmio_res, hbus->hdev, 0,
+					  (u64)(u32)0xffffffff,
+					  hbus->low_mmio_space,
+					  align, false);
+		if (ret) {
+			dev_err(&hbus->hdev->device,
+				"Need %#llx of low MMIO space. Consider reconfiguring the VM.\n",
+				hbus->low_mmio_space);
+			return ret;
+		}
+
+		/* Modify this resource to become a bridge window. */
+		hbus->low_mmio_res->flags |= IORESOURCE_WINDOW;
+		hbus->low_mmio_res->flags &= ~IORESOURCE_BUSY;
+		pci_add_resource(&hbus->resources_for_children,
+				 hbus->low_mmio_res);
+	}
+
+	if (hbus->high_mmio_space) {
+		align = 1ULL << (63 - __builtin_clzll(hbus->high_mmio_space));
+		ret = vmbus_allocate_mmio(&hbus->high_mmio_res, hbus->hdev,
+					  0x100000000, -1,
+					  hbus->high_mmio_space, align,
+					  false);
+		if (ret) {
+			dev_err(&hbus->hdev->device,
+				"Need %#llx of high MMIO space. Consider reconfiguring the VM.\n",
+				hbus->high_mmio_space);
+			goto release_low_mmio;
+		}
+
+		/* Modify this resource to become a bridge window. */
+		hbus->high_mmio_res->flags |= IORESOURCE_WINDOW;
+		hbus->high_mmio_res->flags &= ~IORESOURCE_BUSY;
+		pci_add_resource(&hbus->resources_for_children,
+				 hbus->high_mmio_res);
+	}
+
+	return 0;
+
+release_low_mmio:
+	if (hbus->low_mmio_res) {
+		release_mem_region(hbus->low_mmio_res->start,
+				   resource_size(hbus->low_mmio_res));
+	}
+
+	return ret;
+}
+
+/**
+ * hv_allocate_config_window() - Find MMIO space for PCI Config
+ * @hbus:	Root PCI bus, as understood by this driver
+ *
+ * This function claims memory-mapped I/O space for accessing
+ * configuration space for the functions on this bus.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int hv_allocate_config_window(struct hv_pcibus_device *hbus)
+{
+	int ret;
+
+	/*
+	 * Set up a region of MMIO space to use for accessing configuration
+	 * space.
+	 */
+	ret = vmbus_allocate_mmio(&hbus->mem_config, hbus->hdev, 0, -1,
+				  PCI_CONFIG_MMIO_LENGTH, 0x1000, false);
+	if (ret)
+		return ret;
+
+	/*
+	 * vmbus_allocate_mmio() gets used for allocating both device endpoint
+	 * resource claims (those which cannot be overlapped) and the ranges
+	 * which are valid for the children of this bus, which are intended
+	 * to be overlapped by those children.  Set the flag on this claim
+	 * meaning that this region can't be overlapped.
+	 */
+
+	hbus->mem_config->flags |= IORESOURCE_BUSY;
+
+	return 0;
+}
+
+static void hv_free_config_window(struct hv_pcibus_device *hbus)
+{
+	release_mem_region(hbus->mem_config->start, PCI_CONFIG_MMIO_LENGTH);
+}
+
+/**
+ * hv_pci_enter_d0() - Bring the "bus" into the D0 power state
+ * @hdev:	VMBus's tracking struct for this root PCI bus
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int hv_pci_enter_d0(struct hv_device *hdev)
+{
+	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
+	struct pci_bus_d0_entry *d0_entry;
+	struct hv_pci_compl comp_pkt;
+	struct pci_packet *pkt;
+	int ret;
+
+	/*
+	 * Tell the host that the bus is ready to use, and moved into the
+	 * powered-on state.  This includes telling the host which region
+	 * of memory-mapped I/O space has been chosen for configuration space
+	 * access.
+	 */
+	pkt = kzalloc(sizeof(*pkt) + sizeof(*d0_entry), GFP_KERNEL);
+	if (!pkt)
+		return -ENOMEM;
+
+	init_completion(&comp_pkt.host_event);
+	pkt->completion_func = hv_pci_generic_compl;
+	pkt->compl_ctxt = &comp_pkt;
+	d0_entry = (struct pci_bus_d0_entry *)&pkt->message;
+	d0_entry->message_type.message_type = PCI_BUS_D0ENTRY;
+	d0_entry->mmio_base = hbus->mem_config->start;
+
+	ret = vmbus_sendpacket(hdev->channel, d0_entry, sizeof(*d0_entry),
+			       (unsigned long)pkt, VM_PKT_DATA_INBAND,
+			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+	if (ret)
+		goto exit;
+
+	wait_for_completion(&comp_pkt.host_event);
+
+	if (comp_pkt.completion_status < 0) {
+		dev_err(&hdev->device,
+			"PCI Pass-through VSP failed D0 Entry with status %x\n",
+			comp_pkt.completion_status);
+		ret = -EPROTO;
+		goto exit;
+	}
+
+	ret = 0;
+
+exit:
+	kfree(pkt);
+	return ret;
+}
+
+/**
+ * hv_pci_query_relations() - Ask host to send list of child
+ * devices
+ * @hdev:	VMBus's tracking struct for this root PCI bus
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int hv_pci_query_relations(struct hv_device *hdev)
+{
+	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
+	struct pci_message message;
+	struct completion comp;
+	int ret;
+
+	/* Ask the host to send along the list of child devices */
+	init_completion(&comp);
+	if (cmpxchg(&hbus->survey_event, NULL, &comp))
+		return -ENOTEMPTY;
+
+	memset(&message, 0, sizeof(message));
+	message.message_type = PCI_QUERY_BUS_RELATIONS;
+
+	ret = vmbus_sendpacket(hdev->channel, &message, sizeof(message),
+			       0, VM_PKT_DATA_INBAND, 0);
+	if (ret)
+		return ret;
+
+	wait_for_completion(&comp);
+	return 0;
+}
+
+/**
+ * hv_send_resources_allocated() - Report local resource choices
+ * @hdev:	VMBus's tracking struct for this root PCI bus
+ *
+ * The host OS is expecting to be sent a request as a message
+ * which contains all the resources that the device will use.
+ * The response contains those same resources, "translated"
+ * which is to say, the values which should be used by the
+ * hardware, when it delivers an interrupt.  (MMIO resources are
+ * used in local terms.)  This is nice for Windows, and lines up
+ * with the FDO/PDO split, which doesn't exist in Linux.  Linux
+ * is deeply expecting to scan an emulated PCI configuration
+ * space.  So this message is sent here only to drive the state
+ * machine on the host forward.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int hv_send_resources_allocated(struct hv_device *hdev)
+{
+	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
+	struct pci_resources_assigned *res_assigned;
+	struct hv_pci_compl comp_pkt;
+	struct hv_pci_dev *hpdev;
+	struct pci_packet *pkt;
+	u32 wslot;
+	int ret;
+
+	pkt = kmalloc(sizeof(*pkt) + sizeof(*res_assigned), GFP_KERNEL);
+	if (!pkt)
+		return -ENOMEM;
+
+	ret = 0;
+
+	for (wslot = 0; wslot < 256; wslot++) {
+		hpdev = get_pcichild_wslot(hbus, wslot);
+		if (!hpdev)
+			continue;
+
+		memset(pkt, 0, sizeof(*pkt) + sizeof(*res_assigned));
+		init_completion(&comp_pkt.host_event);
+		pkt->completion_func = hv_pci_generic_compl;
+		pkt->compl_ctxt = &comp_pkt;
+		pkt->message.message_type = PCI_RESOURCES_ASSIGNED;
+		res_assigned = (struct pci_resources_assigned *)&pkt->message;
+		res_assigned->wslot.slot = hpdev->desc.win_slot.slot;
+
+		put_pcichild(hpdev, hv_pcidev_ref_by_slot);
+
+		ret = vmbus_sendpacket(
+			hdev->channel, &pkt->message,
+			sizeof(*res_assigned),
+			(unsigned long)pkt,
+			VM_PKT_DATA_INBAND,
+			VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+		if (ret)
+			break;
+
+		wait_for_completion(&comp_pkt.host_event);
+
+		if (comp_pkt.completion_status < 0) {
+			ret = -EPROTO;
+			dev_err(&hdev->device,
+				"resource allocated returned 0x%x",
+				comp_pkt.completion_status);
+			break;
+		}
+	}
+
+	kfree(pkt);
+	return ret;
+}
+
+/**
+ * hv_send_resources_released() - Report local resources
+ * released
+ * @hdev:	VMBus's tracking struct for this root PCI bus
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int hv_send_resources_released(struct hv_device *hdev)
+{
+	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
+	struct pci_child_message pkt;
+	struct hv_pci_dev *hpdev;
+	u32 wslot;
+	int ret;
+
+	for (wslot = 0; wslot < 256; wslot++) {
+		hpdev = get_pcichild_wslot(hbus, wslot);
+		if (!hpdev)
+			continue;
+
+		memset(&pkt, 0, sizeof(pkt));
+		pkt.message_type = PCI_RESOURCES_RELEASED;
+		pkt.wslot.slot = hpdev->desc.win_slot.slot;
+
+		put_pcichild(hpdev, hv_pcidev_ref_by_slot);
+
+		ret = vmbus_sendpacket(hdev->channel, &pkt, sizeof(pkt), 0,
+				       VM_PKT_DATA_INBAND, 0);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void get_hvpcibus(struct hv_pcibus_device *hbus)
+{
+	atomic_inc(&hbus->remove_lock);
+}
+
+static void put_hvpcibus(struct hv_pcibus_device *hbus)
+{
+	if (atomic_dec_and_test(&hbus->remove_lock))
+		complete(&hbus->remove_event);
+}
+
+/**
+ * hv_pci_probe() - New VMBus channel probe, for a root PCI bus
+ * @hdev:	VMBus's tracking struct for this root PCI bus
+ * @dev_id:	Identifies the device itself
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int hv_pci_probe(struct hv_device *hdev,
+			const struct hv_vmbus_device_id *dev_id)
+{
+	struct hv_pcibus_device *hbus;
+	int ret;
+
+	hbus = kzalloc(sizeof(*hbus), GFP_KERNEL);
+	if (!hbus)
+		return -ENOMEM;
+
+	/*
+	 * The PCI bus "domain" is what is called "segment" in ACPI and
+	 * other specs.  Pull it from the instance ID, to get something
+	 * unique.  Bytes 8 and 9 are what is used in Windows guests, so
+	 * do the same thing for consistency.  Note that, since this code
+	 * only runs in a Hyper-V VM, Hyper-V can (and does) guarantee
+	 * that (1) the only domain in use for something that looks like
+	 * a physical PCI bus (which is actually emulated by the
+	 * hypervisor) is domain 0 and (2) there will be no overlap
+	 * between domains derived from these instance IDs in the same
+	 * VM.
+	 */
+	hbus->sysdata.domain = hdev->dev_instance.b[9] |
+			       hdev->dev_instance.b[8] << 8;
+
+	hbus->hdev = hdev;
+	atomic_inc(&hbus->remove_lock);
+	INIT_LIST_HEAD(&hbus->children);
+	INIT_LIST_HEAD(&hbus->dr_list);
+	INIT_LIST_HEAD(&hbus->resources_for_children);
+	spin_lock_init(&hbus->config_lock);
+	spin_lock_init(&hbus->device_list_lock);
+	sema_init(&hbus->enum_sem, 1);
+	init_completion(&hbus->remove_event);
+
+	ret = vmbus_open(hdev->channel, pci_ring_size, pci_ring_size, NULL, 0,
+			 hv_pci_onchannelcallback, hbus);
+	if (ret)
+		goto free_bus;
+
+	hv_set_drvdata(hdev, hbus);
+
+	ret = hv_pci_protocol_negotiation(hdev);
+	if (ret)
+		goto close;
+
+	ret = hv_allocate_config_window(hbus);
+	if (ret)
+		goto close;
+
+	hbus->cfg_addr = ioremap(hbus->mem_config->start,
+				 PCI_CONFIG_MMIO_LENGTH);
+	if (!hbus->cfg_addr) {
+		dev_err(&hdev->device,
+			"Unable to map a virtual address for config space\n");
+		ret = -ENOMEM;
+		goto free_config;
+	}
+
+	hbus->sysdata.fwnode = irq_domain_alloc_fwnode(hbus);
+	if (!hbus->sysdata.fwnode) {
+		ret = -ENOMEM;
+		goto unmap;
+	}
+
+	ret = hv_pcie_init_irq_domain(hbus);
+	if (ret)
+		goto free_fwnode;
+
+	ret = hv_pci_query_relations(hdev);
+	if (ret)
+		goto free_irq_domain;
+
+	ret = hv_pci_enter_d0(hdev);
+	if (ret)
+		goto free_irq_domain;
+
+	ret = hv_pci_allocate_bridge_windows(hbus);
+	if (ret)
+		goto free_irq_domain;
+
+	ret = hv_send_resources_allocated(hdev);
+	if (ret)
+		goto free_windows;
+
+	prepopulate_bars(hbus);
+
+	hbus->state = hv_pcibus_probed;
+
+	ret = create_root_hv_pci_bus(hbus);
+	if (ret)
+		goto free_windows;
+
+	return 0;
+
+free_windows:
+	hv_pci_free_bridge_windows(hbus);
+free_irq_domain:
+	irq_domain_remove(hbus->irq_domain);
+free_fwnode:
+	irq_domain_free_fwnode(hbus->sysdata.fwnode);
+unmap:
+	iounmap(hbus->cfg_addr);
+free_config:
+	hv_free_config_window(hbus);
+close:
+	vmbus_close(hdev->channel);
+free_bus:
+	kfree(hbus);
+	return ret;
+}
+
+/**
+ * hv_pci_remove() - Remove routine for this VMBus channel
+ * @hdev:	VMBus's tracking struct for this root PCI bus
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int hv_pci_remove(struct hv_device *hdev)
+{
+	int ret;
+	struct hv_pcibus_device *hbus;
+	union {
+		struct pci_packet teardown_packet;
+		u8 buffer[0x100];
+	} pkt;
+	struct pci_bus_relations relations;
+	struct hv_pci_compl comp_pkt;
+
+	hbus = hv_get_drvdata(hdev);
+
+	ret = hv_send_resources_released(hdev);
+	if (ret)
+		dev_err(&hdev->device,
+			"Couldn't send resources released packet(s)\n");
+
+	memset(&pkt.teardown_packet, 0, sizeof(pkt.teardown_packet));
+	init_completion(&comp_pkt.host_event);
+	pkt.teardown_packet.completion_func = hv_pci_generic_compl;
+	pkt.teardown_packet.compl_ctxt = &comp_pkt;
+	pkt.teardown_packet.message.message_type = PCI_BUS_D0EXIT;
+
+	ret = vmbus_sendpacket(hdev->channel, &pkt.teardown_packet.message,
+			       sizeof(struct pci_message),
+			       (unsigned long)&pkt.teardown_packet,
+			       VM_PKT_DATA_INBAND,
+			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+	if (!ret)
+		wait_for_completion_timeout(&comp_pkt.host_event, 10 * HZ);
+
+	if (hbus->state == hv_pcibus_installed) {
+		/* Remove the bus from PCI's point of view. */
+		pci_lock_rescan_remove();
+		pci_stop_root_bus(hbus->pci_bus);
+		pci_remove_root_bus(hbus->pci_bus);
+		pci_unlock_rescan_remove();
+	}
+
+	vmbus_close(hdev->channel);
+
+	/* Delete any children which might still exist. */
+	memset(&relations, 0, sizeof(relations));
+	hv_pci_devices_present(hbus, &relations);
+
+	iounmap(hbus->cfg_addr);
+	hv_free_config_window(hbus);
+	pci_free_resource_list(&hbus->resources_for_children);
+	hv_pci_free_bridge_windows(hbus);
+	irq_domain_remove(hbus->irq_domain);
+	irq_domain_free_fwnode(hbus->sysdata.fwnode);
+	put_hvpcibus(hbus);
+	wait_for_completion(&hbus->remove_event);
+	kfree(hbus);
+	return 0;
+}
+
+static const struct hv_vmbus_device_id hv_pci_id_table[] = {
+	/* PCI Pass-through Class ID */
+	/* 44C4F61D-4444-4400-9D52-802E27EDE19F */
+	{ HV_PCIE_GUID, },
+	{ },
+};
+
+MODULE_DEVICE_TABLE(vmbus, hv_pci_id_table);
+
+static struct hv_driver hv_pci_drv = {
+	.name		= "hv_pci",
+	.id_table	= hv_pci_id_table,
+	.probe		= hv_pci_probe,
+	.remove		= hv_pci_remove,
+};
+
+static void __exit exit_hv_pci_drv(void)
+{
+	vmbus_driver_unregister(&hv_pci_drv);
+}
+
+static int __init init_hv_pci_drv(void)
+{
+	return vmbus_driver_register(&hv_pci_drv);
+}
+
+module_init(init_hv_pci_drv);
+module_exit(exit_hv_pci_drv);
+
+MODULE_DESCRIPTION("Hyper-V PCI");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/host/pci-imx6.c b/drivers/pci/host/pci-imx6.c
index fe600964fa50..eb5a2755a164 100644
--- a/drivers/pci/host/pci-imx6.c
+++ b/drivers/pci/host/pci-imx6.c
@@ -39,6 +39,11 @@ struct imx6_pcie {
 	struct pcie_port	pp;
 	struct regmap		*iomuxc_gpr;
 	void __iomem		*mem_base;
+	u32			tx_deemph_gen1;
+	u32			tx_deemph_gen2_3p5db;
+	u32			tx_deemph_gen2_6db;
+	u32			tx_swing_full;
+	u32			tx_swing_low;
 };
 
 /* PCIe Root Complex registers (memory-mapped) */
@@ -202,6 +207,23 @@ static int pcie_phy_write(void __iomem *dbi_base, int addr, int data)
 	return 0;
 }
 
+static void imx6_pcie_reset_phy(struct pcie_port *pp)
+{
+	u32 tmp;
+
+	pcie_phy_read(pp->dbi_base, PHY_RX_OVRD_IN_LO, &tmp);
+	tmp |= (PHY_RX_OVRD_IN_LO_RX_DATA_EN |
+		PHY_RX_OVRD_IN_LO_RX_PLL_EN);
+	pcie_phy_write(pp->dbi_base, PHY_RX_OVRD_IN_LO, tmp);
+
+	usleep_range(2000, 3000);
+
+	pcie_phy_read(pp->dbi_base, PHY_RX_OVRD_IN_LO, &tmp);
+	tmp &= ~(PHY_RX_OVRD_IN_LO_RX_DATA_EN |
+		  PHY_RX_OVRD_IN_LO_RX_PLL_EN);
+	pcie_phy_write(pp->dbi_base, PHY_RX_OVRD_IN_LO, tmp);
+}
+
 /*  Added for PCI abort handling */
 static int imx6q_pcie_abort_handler(unsigned long addr,
 		unsigned int fsr, struct pt_regs *regs)
@@ -317,32 +339,32 @@ static void imx6_pcie_init_phy(struct pcie_port *pp)
 			IMX6Q_GPR12_LOS_LEVEL, 9 << 4);
 
 	regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8,
-			IMX6Q_GPR8_TX_DEEMPH_GEN1, 0 << 0);
+			   IMX6Q_GPR8_TX_DEEMPH_GEN1,
+			   imx6_pcie->tx_deemph_gen1 << 0);
 	regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8,
-			IMX6Q_GPR8_TX_DEEMPH_GEN2_3P5DB, 0 << 6);
+			   IMX6Q_GPR8_TX_DEEMPH_GEN2_3P5DB,
+			   imx6_pcie->tx_deemph_gen2_3p5db << 6);
 	regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8,
-			IMX6Q_GPR8_TX_DEEMPH_GEN2_6DB, 20 << 12);
+			   IMX6Q_GPR8_TX_DEEMPH_GEN2_6DB,
+			   imx6_pcie->tx_deemph_gen2_6db << 12);
 	regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8,
-			IMX6Q_GPR8_TX_SWING_FULL, 127 << 18);
+			   IMX6Q_GPR8_TX_SWING_FULL,
+			   imx6_pcie->tx_swing_full << 18);
 	regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8,
-			IMX6Q_GPR8_TX_SWING_LOW, 127 << 25);
+			   IMX6Q_GPR8_TX_SWING_LOW,
+			   imx6_pcie->tx_swing_low << 25);
 }
 
 static int imx6_pcie_wait_for_link(struct pcie_port *pp)
 {
-	unsigned int retries;
-
-	for (retries = 0; retries < 200; retries++) {
-		if (dw_pcie_link_up(pp))
-			return 0;
-		usleep_range(100, 1000);
-	}
+	/* check if the link is up or not */
+	if (!dw_pcie_wait_for_link(pp))
+		return 0;
 
-	dev_err(pp->dev, "phy link never came up\n");
 	dev_dbg(pp->dev, "DEBUG_R0: 0x%08x, DEBUG_R1: 0x%08x\n",
 		readl(pp->dbi_base + PCIE_PHY_DEBUG_R0),
 		readl(pp->dbi_base + PCIE_PHY_DEBUG_R1));
-	return -EINVAL;
+	return -ETIMEDOUT;
 }
 
 static int imx6_pcie_wait_for_speed_change(struct pcie_port *pp)
@@ -390,8 +412,10 @@ static int imx6_pcie_establish_link(struct pcie_port *pp)
 			IMX6Q_GPR12_PCIE_CTL_2, 1 << 10);
 
 	ret = imx6_pcie_wait_for_link(pp);
-	if (ret)
-		return ret;
+	if (ret) {
+		dev_info(pp->dev, "Link never came up\n");
+		goto err_reset_phy;
+	}
 
 	/* Allow Gen2 mode after the link is up. */
 	tmp = readl(pp->dbi_base + PCIE_RC_LCR);
@@ -410,19 +434,28 @@ static int imx6_pcie_establish_link(struct pcie_port *pp)
 	ret = imx6_pcie_wait_for_speed_change(pp);
 	if (ret) {
 		dev_err(pp->dev, "Failed to bring link up!\n");
-		return ret;
+		goto err_reset_phy;
 	}
 
 	/* Make sure link training is finished as well! */
 	ret = imx6_pcie_wait_for_link(pp);
 	if (ret) {
 		dev_err(pp->dev, "Failed to bring link up!\n");
-		return ret;
+		goto err_reset_phy;
 	}
 
 	tmp = readl(pp->dbi_base + PCIE_RC_LCSR);
 	dev_dbg(pp->dev, "Link up, Gen=%i\n", (tmp >> 16) & 0xf);
+
 	return 0;
+
+err_reset_phy:
+	dev_dbg(pp->dev, "PHY DEBUG_R0=0x%08x DEBUG_R1=0x%08x\n",
+		readl(pp->dbi_base + PCIE_PHY_DEBUG_R0),
+		readl(pp->dbi_base + PCIE_PHY_DEBUG_R1));
+	imx6_pcie_reset_phy(pp);
+
+	return ret;
 }
 
 static void imx6_pcie_host_init(struct pcie_port *pp)
@@ -441,81 +474,10 @@ static void imx6_pcie_host_init(struct pcie_port *pp)
 		dw_pcie_msi_init(pp);
 }
 
-static void imx6_pcie_reset_phy(struct pcie_port *pp)
-{
-	u32 tmp;
-
-	pcie_phy_read(pp->dbi_base, PHY_RX_OVRD_IN_LO, &tmp);
-	tmp |= (PHY_RX_OVRD_IN_LO_RX_DATA_EN |
-		PHY_RX_OVRD_IN_LO_RX_PLL_EN);
-	pcie_phy_write(pp->dbi_base, PHY_RX_OVRD_IN_LO, tmp);
-
-	usleep_range(2000, 3000);
-
-	pcie_phy_read(pp->dbi_base, PHY_RX_OVRD_IN_LO, &tmp);
-	tmp &= ~(PHY_RX_OVRD_IN_LO_RX_DATA_EN |
-		  PHY_RX_OVRD_IN_LO_RX_PLL_EN);
-	pcie_phy_write(pp->dbi_base, PHY_RX_OVRD_IN_LO, tmp);
-}
-
 static int imx6_pcie_link_up(struct pcie_port *pp)
 {
-	u32 rc, debug_r0, rx_valid;
-	int count = 5;
-
-	/*
-	 * Test if the PHY reports that the link is up and also that the LTSSM
-	 * training finished. There are three possible states of the link when
-	 * this code is called:
-	 * 1) The link is DOWN (unlikely)
-	 *     The link didn't come up yet for some reason. This usually means
-	 *     we have a real problem somewhere. Reset the PHY and exit. This
-	 *     state calls for inspection of the DEBUG registers.
-	 * 2) The link is UP, but still in LTSSM training
-	 *     Wait for the training to finish, which should take a very short
-	 *     time. If the training does not finish, we have a problem and we
-	 *     need to inspect the DEBUG registers. If the training does finish,
-	 *     the link is up and operating correctly.
-	 * 3) The link is UP and no longer in LTSSM training
-	 *     The link is up and operating correctly.
-	 */
-	while (1) {
-		rc = readl(pp->dbi_base + PCIE_PHY_DEBUG_R1);
-		if (!(rc & PCIE_PHY_DEBUG_R1_XMLH_LINK_UP))
-			break;
-		if (!(rc & PCIE_PHY_DEBUG_R1_XMLH_LINK_IN_TRAINING))
-			return 1;
-		if (!count--)
-			break;
-		dev_dbg(pp->dev, "Link is up, but still in training\n");
-		/*
-		 * Wait a little bit, then re-check if the link finished
-		 * the training.
-		 */
-		usleep_range(1000, 2000);
-	}
-	/*
-	 * From L0, initiate MAC entry to gen2 if EP/RC supports gen2.
-	 * Wait 2ms (LTSSM timeout is 24ms, PHY lock is ~5us in gen2).
-	 * If (MAC/LTSSM.state == Recovery.RcvrLock)
-	 * && (PHY/rx_valid==0) then pulse PHY/rx_reset. Transition
-	 * to gen2 is stuck
-	 */
-	pcie_phy_read(pp->dbi_base, PCIE_PHY_RX_ASIC_OUT, &rx_valid);
-	debug_r0 = readl(pp->dbi_base + PCIE_PHY_DEBUG_R0);
-
-	if (rx_valid & PCIE_PHY_RX_ASIC_OUT_VALID)
-		return 0;
-
-	if ((debug_r0 & 0x3f) != 0x0d)
-		return 0;
-
-	dev_err(pp->dev, "transition to gen2 is stuck, reset PHY!\n");
-	dev_dbg(pp->dev, "debug_r0=%08x debug_r1=%08x\n", debug_r0, rc);
-
-	imx6_pcie_reset_phy(pp);
-
-	return 0;
+	return readl(pp->dbi_base + PCIE_PHY_DEBUG_R1) &
+			PCIE_PHY_DEBUG_R1_XMLH_LINK_UP;
 }
 
 static struct pcie_host_ops imx6_pcie_host_ops = {
@@ -562,6 +524,7 @@ static int __init imx6_pcie_probe(struct platform_device *pdev)
 	struct imx6_pcie *imx6_pcie;
 	struct pcie_port *pp;
 	struct resource *dbi_base;
+	struct device_node *node = pdev->dev.of_node;
 	int ret;
 
 	imx6_pcie = devm_kzalloc(&pdev->dev, sizeof(*imx6_pcie), GFP_KERNEL);
@@ -614,6 +577,27 @@ static int __init imx6_pcie_probe(struct platform_device *pdev)
 		return PTR_ERR(imx6_pcie->iomuxc_gpr);
 	}
 
+	/* Grab PCIe PHY Tx Settings */
+	if (of_property_read_u32(node, "fsl,tx-deemph-gen1",
+				 &imx6_pcie->tx_deemph_gen1))
+		imx6_pcie->tx_deemph_gen1 = 0;
+
+	if (of_property_read_u32(node, "fsl,tx-deemph-gen2-3p5db",
+				 &imx6_pcie->tx_deemph_gen2_3p5db))
+		imx6_pcie->tx_deemph_gen2_3p5db = 0;
+
+	if (of_property_read_u32(node, "fsl,tx-deemph-gen2-6db",
+				 &imx6_pcie->tx_deemph_gen2_6db))
+		imx6_pcie->tx_deemph_gen2_6db = 20;
+
+	if (of_property_read_u32(node, "fsl,tx-swing-full",
+				 &imx6_pcie->tx_swing_full))
+		imx6_pcie->tx_swing_full = 127;
+
+	if (of_property_read_u32(node, "fsl,tx-swing-low",
+				 &imx6_pcie->tx_swing_low))
+		imx6_pcie->tx_swing_low = 127;
+
 	ret = imx6_add_pcie_port(pp, pdev);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/pci/host/pci-keystone-dw.c b/drivers/pci/host/pci-keystone-dw.c
index ed34c9520a02..6153853ca9c3 100644
--- a/drivers/pci/host/pci-keystone-dw.c
+++ b/drivers/pci/host/pci-keystone-dw.c
@@ -58,11 +58,6 @@
 
 #define to_keystone_pcie(x)	container_of(x, struct keystone_pcie, pp)
 
-static inline struct pcie_port *sys_to_pcie(struct pci_sys_data *sys)
-{
-	return sys->private_data;
-}
-
 static inline void update_reg_offset_bit_pos(u32 offset, u32 *reg_offset,
 					     u32 *bit_pos)
 {
@@ -108,7 +103,7 @@ static void ks_dw_pcie_msi_irq_ack(struct irq_data *d)
 	struct pcie_port *pp;
 
 	msi = irq_data_get_msi_desc(d);
-	pp = sys_to_pcie(msi_desc_to_pci_sysdata(msi));
+	pp = (struct pcie_port *) msi_desc_to_pci_sysdata(msi);
 	ks_pcie = to_keystone_pcie(pp);
 	offset = d->irq - irq_linear_revmap(pp->irq_domain, 0);
 	update_reg_offset_bit_pos(offset, &reg_offset, &bit_pos);
@@ -146,7 +141,7 @@ static void ks_dw_pcie_msi_irq_mask(struct irq_data *d)
 	u32 offset;
 
 	msi = irq_data_get_msi_desc(d);
-	pp = sys_to_pcie(msi_desc_to_pci_sysdata(msi));
+	pp = (struct pcie_port *) msi_desc_to_pci_sysdata(msi);
 	ks_pcie = to_keystone_pcie(pp);
 	offset = d->irq - irq_linear_revmap(pp->irq_domain, 0);
 
@@ -167,7 +162,7 @@ static void ks_dw_pcie_msi_irq_unmask(struct irq_data *d)
 	u32 offset;
 
 	msi = irq_data_get_msi_desc(d);
-	pp = sys_to_pcie(msi_desc_to_pci_sysdata(msi));
+	pp = (struct pcie_port *) msi_desc_to_pci_sysdata(msi);
 	ks_pcie = to_keystone_pcie(pp);
 	offset = d->irq - irq_linear_revmap(pp->irq_domain, 0);
 
diff --git a/drivers/pci/host/pci-keystone.c b/drivers/pci/host/pci-keystone.c
index 0aa81bd3de12..b71f55bb0315 100644
--- a/drivers/pci/host/pci-keystone.c
+++ b/drivers/pci/host/pci-keystone.c
@@ -97,17 +97,15 @@ static int ks_pcie_establish_link(struct keystone_pcie *ks_pcie)
 		return 0;
 	}
 
-	ks_dw_pcie_initiate_link_train(ks_pcie);
 	/* check if the link is up or not */
-	for (retries = 0; retries < 200; retries++) {
-		if (dw_pcie_link_up(pp))
-			return 0;
-		usleep_range(100, 1000);
+	for (retries = 0; retries < 5; retries++) {
 		ks_dw_pcie_initiate_link_train(ks_pcie);
+		if (!dw_pcie_wait_for_link(pp))
+			return 0;
 	}
 
 	dev_err(pp->dev, "phy link never came up\n");
-	return -EINVAL;
+	return -ETIMEDOUT;
 }
 
 static void ks_pcie_msi_irq_handler(struct irq_desc *desc)
@@ -359,6 +357,9 @@ static int __init ks_pcie_probe(struct platform_device *pdev)
 
 	/* initialize SerDes Phy if present */
 	phy = devm_phy_get(dev, "pcie-phy");
+	if (PTR_ERR_OR_ZERO(phy) == -EPROBE_DEFER)
+		return PTR_ERR(phy);
+
 	if (!IS_ERR_OR_NULL(phy)) {
 		ret = phy_init(phy);
 		if (ret < 0)
diff --git a/drivers/pci/host/pci-layerscape.c b/drivers/pci/host/pci-layerscape.c
index 3923bed93c7e..a21e229d95e0 100644
--- a/drivers/pci/host/pci-layerscape.c
+++ b/drivers/pci/host/pci-layerscape.c
@@ -77,6 +77,16 @@ static void ls_pcie_fix_class(struct ls_pcie *pcie)
 	iowrite16(PCI_CLASS_BRIDGE_PCI, pcie->dbi + PCI_CLASS_DEVICE);
 }
 
+/* Drop MSG TLP except for Vendor MSG */
+static void ls_pcie_drop_msg_tlp(struct ls_pcie *pcie)
+{
+	u32 val;
+
+	val = ioread32(pcie->dbi + PCIE_STRFMR1);
+	val &= 0xDFFFFFFF;
+	iowrite32(val, pcie->dbi + PCIE_STRFMR1);
+}
+
 static int ls1021_pcie_link_up(struct pcie_port *pp)
 {
 	u32 state;
@@ -97,7 +107,7 @@ static int ls1021_pcie_link_up(struct pcie_port *pp)
 static void ls1021_pcie_host_init(struct pcie_port *pp)
 {
 	struct ls_pcie *pcie = to_ls_pcie(pp);
-	u32 val, index[2];
+	u32 index[2];
 
 	pcie->scfg = syscon_regmap_lookup_by_phandle(pp->dev->of_node,
 						     "fsl,pcie-scfg");
@@ -116,13 +126,7 @@ static void ls1021_pcie_host_init(struct pcie_port *pp)
 
 	dw_pcie_setup_rc(pp);
 
-	/*
-	 * LS1021A Workaround for internal TKT228622
-	 * to fix the INTx hang issue
-	 */
-	val = ioread32(pcie->dbi + PCIE_STRFMR1);
-	val &= 0xffff;
-	iowrite32(val, pcie->dbi + PCIE_STRFMR1);
+	ls_pcie_drop_msg_tlp(pcie);
 }
 
 static int ls_pcie_link_up(struct pcie_port *pp)
@@ -147,6 +151,7 @@ static void ls_pcie_host_init(struct pcie_port *pp)
 	iowrite32(1, pcie->dbi + PCIE_DBI_RO_WR_EN);
 	ls_pcie_fix_class(pcie);
 	ls_pcie_clear_multifunction(pcie);
+	ls_pcie_drop_msg_tlp(pcie);
 	iowrite32(0, pcie->dbi + PCIE_DBI_RO_WR_EN);
 }
 
@@ -203,6 +208,7 @@ static const struct of_device_id ls_pcie_of_match[] = {
 	{ .compatible = "fsl,ls1021a-pcie", .data = &ls1021_drvdata },
 	{ .compatible = "fsl,ls1043a-pcie", .data = &ls1043_drvdata },
 	{ .compatible = "fsl,ls2080a-pcie", .data = &ls2080_drvdata },
+	{ .compatible = "fsl,ls2085a-pcie", .data = &ls2080_drvdata },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, ls_pcie_of_match);
diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c
index 30323114c53c..68d1f41b3cbf 100644
--- a/drivers/pci/host/pci-tegra.c
+++ b/drivers/pci/host/pci-tegra.c
@@ -281,6 +281,11 @@ struct tegra_pcie {
 	struct resource prefetch;
 	struct resource busn;
 
+	struct {
+		resource_size_t mem;
+		resource_size_t io;
+	} offset;
+
 	struct clk *pex_clk;
 	struct clk *afi_clk;
 	struct clk *pll_e;
@@ -295,7 +300,6 @@ struct tegra_pcie {
 	struct tegra_msi msi;
 
 	struct list_head ports;
-	unsigned int num_ports;
 	u32 xbar_config;
 
 	struct regulator_bulk_data *supplies;
@@ -426,31 +430,38 @@ free:
 	return ERR_PTR(err);
 }
 
-/*
- * Look up a virtual address mapping for the specified bus number. If no such
- * mapping exists, try to create one.
- */
-static void __iomem *tegra_pcie_bus_map(struct tegra_pcie *pcie,
-					unsigned int busnr)
+static int tegra_pcie_add_bus(struct pci_bus *bus)
 {
-	struct tegra_pcie_bus *bus;
+	struct tegra_pcie *pcie = sys_to_pcie(bus->sysdata);
+	struct tegra_pcie_bus *b;
 
-	list_for_each_entry(bus, &pcie->buses, list)
-		if (bus->nr == busnr)
-			return (void __iomem *)bus->area->addr;
+	b = tegra_pcie_bus_alloc(pcie, bus->number);
+	if (IS_ERR(b))
+		return PTR_ERR(b);
 
-	bus = tegra_pcie_bus_alloc(pcie, busnr);
-	if (IS_ERR(bus))
-		return NULL;
+	list_add_tail(&b->list, &pcie->buses);
 
-	list_add_tail(&bus->list, &pcie->buses);
+	return 0;
+}
 
-	return (void __iomem *)bus->area->addr;
+static void tegra_pcie_remove_bus(struct pci_bus *child)
+{
+	struct tegra_pcie *pcie = sys_to_pcie(child->sysdata);
+	struct tegra_pcie_bus *bus, *tmp;
+
+	list_for_each_entry_safe(bus, tmp, &pcie->buses, list) {
+		if (bus->nr == child->number) {
+			vunmap(bus->area->addr);
+			list_del(&bus->list);
+			kfree(bus);
+			break;
+		}
+	}
 }
 
-static void __iomem *tegra_pcie_conf_address(struct pci_bus *bus,
-					     unsigned int devfn,
-					     int where)
+static void __iomem *tegra_pcie_map_bus(struct pci_bus *bus,
+					unsigned int devfn,
+					int where)
 {
 	struct tegra_pcie *pcie = sys_to_pcie(bus->sysdata);
 	void __iomem *addr = NULL;
@@ -466,7 +477,12 @@ static void __iomem *tegra_pcie_conf_address(struct pci_bus *bus,
 			}
 		}
 	} else {
-		addr = tegra_pcie_bus_map(pcie, bus->number);
+		struct tegra_pcie_bus *b;
+
+		list_for_each_entry(b, &pcie->buses, list)
+			if (b->nr == bus->number)
+				addr = (void __iomem *)b->area->addr;
+
 		if (!addr) {
 			dev_err(pcie->dev,
 				"failed to map cfg. space for bus %u\n",
@@ -481,7 +497,9 @@ static void __iomem *tegra_pcie_conf_address(struct pci_bus *bus,
 }
 
 static struct pci_ops tegra_pcie_ops = {
-	.map_bus = tegra_pcie_conf_address,
+	.add_bus = tegra_pcie_add_bus,
+	.remove_bus = tegra_pcie_remove_bus,
+	.map_bus = tegra_pcie_map_bus,
 	.read = pci_generic_config_read32,
 	.write = pci_generic_config_write32,
 };
@@ -598,6 +616,17 @@ static int tegra_pcie_setup(int nr, struct pci_sys_data *sys)
 	struct tegra_pcie *pcie = sys_to_pcie(sys);
 	int err;
 
+	sys->mem_offset = pcie->offset.mem;
+	sys->io_offset = pcie->offset.io;
+
+	err = devm_request_resource(pcie->dev, &pcie->all, &pcie->io);
+	if (err < 0)
+		return err;
+
+	err = devm_request_resource(pcie->dev, &ioport_resource, &pcie->pio);
+	if (err < 0)
+		return err;
+
 	err = devm_request_resource(pcie->dev, &pcie->all, &pcie->mem);
 	if (err < 0)
 		return err;
@@ -606,6 +635,7 @@ static int tegra_pcie_setup(int nr, struct pci_sys_data *sys)
 	if (err)
 		return err;
 
+	pci_add_resource_offset(&sys->resources, &pcie->pio, sys->io_offset);
 	pci_add_resource_offset(&sys->resources, &pcie->mem, sys->mem_offset);
 	pci_add_resource_offset(&sys->resources, &pcie->prefetch,
 				sys->mem_offset);
@@ -741,7 +771,7 @@ static void tegra_pcie_setup_translations(struct tegra_pcie *pcie)
 	afi_writel(pcie, 0, AFI_FPCI_BAR5);
 
 	/* map all upstream transactions as uncached */
-	afi_writel(pcie, PHYS_OFFSET, AFI_CACHE_BAR0_ST);
+	afi_writel(pcie, 0, AFI_CACHE_BAR0_ST);
 	afi_writel(pcie, 0, AFI_CACHE_BAR0_SZ);
 	afi_writel(pcie, 0, AFI_CACHE_BAR1_ST);
 	afi_writel(pcie, 0, AFI_CACHE_BAR1_SZ);
@@ -1601,6 +1631,9 @@ static int tegra_pcie_parse_dt(struct tegra_pcie *pcie)
 
 		switch (res.flags & IORESOURCE_TYPE_BITS) {
 		case IORESOURCE_IO:
+			/* Track the bus -> CPU I/O mapping offset. */
+			pcie->offset.io = res.start - range.pci_addr;
+
 			memcpy(&pcie->pio, &res, sizeof(res));
 			pcie->pio.name = np->full_name;
 
@@ -1621,6 +1654,14 @@ static int tegra_pcie_parse_dt(struct tegra_pcie *pcie)
 			break;
 
 		case IORESOURCE_MEM:
+			/*
+			 * Track the bus -> CPU memory mapping offset. This
+			 * assumes that the prefetchable and non-prefetchable
+			 * regions will be the last of type IORESOURCE_MEM in
+			 * the ranges property.
+			 * */
+			pcie->offset.mem = res.start - range.pci_addr;
+
 			if (res.flags & IORESOURCE_PREFETCH) {
 				memcpy(&pcie->prefetch, &res, sizeof(res));
 				pcie->prefetch.name = "prefetchable";
diff --git a/drivers/pci/host/pci-thunder-ecam.c b/drivers/pci/host/pci-thunder-ecam.c
new file mode 100644
index 000000000000..d71935cb2678
--- /dev/null
+++ b/drivers/pci/host/pci-thunder-ecam.c
@@ -0,0 +1,403 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2015, 2016 Cavium, Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/ioport.h>
+#include <linux/of_pci.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include "pci-host-common.h"
+
+/* Mapping is standard ECAM */
+static void __iomem *thunder_ecam_map_bus(struct pci_bus *bus,
+					  unsigned int devfn,
+					  int where)
+{
+	struct gen_pci *pci = bus->sysdata;
+	resource_size_t idx = bus->number - pci->cfg.bus_range->start;
+
+	return pci->cfg.win[idx] + ((devfn << 12) | where);
+}
+
+static void set_val(u32 v, int where, int size, u32 *val)
+{
+	int shift = (where & 3) * 8;
+
+	pr_debug("set_val %04x: %08x\n", (unsigned)(where & ~3), v);
+	v >>= shift;
+	if (size == 1)
+		v &= 0xff;
+	else if (size == 2)
+		v &= 0xffff;
+	*val = v;
+}
+
+static int handle_ea_bar(u32 e0, int bar, struct pci_bus *bus,
+			 unsigned int devfn, int where, int size, u32 *val)
+{
+	void __iomem *addr;
+	u32 v;
+
+	/* Entries are 16-byte aligned; bits[2,3] select word in entry */
+	int where_a = where & 0xc;
+
+	if (where_a == 0) {
+		set_val(e0, where, size, val);
+		return PCIBIOS_SUCCESSFUL;
+	}
+	if (where_a == 0x4) {
+		addr = bus->ops->map_bus(bus, devfn, bar); /* BAR 0 */
+		if (!addr) {
+			*val = ~0;
+			return PCIBIOS_DEVICE_NOT_FOUND;
+		}
+		v = readl(addr);
+		v &= ~0xf;
+		v |= 2; /* EA entry-1. Base-L */
+		set_val(v, where, size, val);
+		return PCIBIOS_SUCCESSFUL;
+	}
+	if (where_a == 0x8) {
+		u32 barl_orig;
+		u32 barl_rb;
+
+		addr = bus->ops->map_bus(bus, devfn, bar); /* BAR 0 */
+		if (!addr) {
+			*val = ~0;
+			return PCIBIOS_DEVICE_NOT_FOUND;
+		}
+		barl_orig = readl(addr + 0);
+		writel(0xffffffff, addr + 0);
+		barl_rb = readl(addr + 0);
+		writel(barl_orig, addr + 0);
+		/* zeros in unsettable bits */
+		v = ~barl_rb & ~3;
+		v |= 0xc; /* EA entry-2. Offset-L */
+		set_val(v, where, size, val);
+		return PCIBIOS_SUCCESSFUL;
+	}
+	if (where_a == 0xc) {
+		addr = bus->ops->map_bus(bus, devfn, bar + 4); /* BAR 1 */
+		if (!addr) {
+			*val = ~0;
+			return PCIBIOS_DEVICE_NOT_FOUND;
+		}
+		v = readl(addr); /* EA entry-3. Base-H */
+		set_val(v, where, size, val);
+		return PCIBIOS_SUCCESSFUL;
+	}
+	return PCIBIOS_DEVICE_NOT_FOUND;
+}
+
+static int thunder_ecam_p2_config_read(struct pci_bus *bus, unsigned int devfn,
+				       int where, int size, u32 *val)
+{
+	struct gen_pci *pci = bus->sysdata;
+	int where_a = where & ~3;
+	void __iomem *addr;
+	u32 node_bits;
+	u32 v;
+
+	/* EA Base[63:32] may be missing some bits ... */
+	switch (where_a) {
+	case 0xa8:
+	case 0xbc:
+	case 0xd0:
+	case 0xe4:
+		break;
+	default:
+		return pci_generic_config_read(bus, devfn, where, size, val);
+	}
+
+	addr = bus->ops->map_bus(bus, devfn, where_a);
+	if (!addr) {
+		*val = ~0;
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	}
+
+	v = readl(addr);
+
+	/*
+	 * Bit 44 of the 64-bit Base must match the same bit in
+	 * the config space access window.  Since we are working with
+	 * the high-order 32 bits, shift everything down by 32 bits.
+	 */
+	node_bits = (pci->cfg.res.start >> 32) & (1 << 12);
+
+	v |= node_bits;
+	set_val(v, where, size, val);
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int thunder_ecam_config_read(struct pci_bus *bus, unsigned int devfn,
+				    int where, int size, u32 *val)
+{
+	u32 v;
+	u32 vendor_device;
+	u32 class_rev;
+	void __iomem *addr;
+	int cfg_type;
+	int where_a = where & ~3;
+
+	addr = bus->ops->map_bus(bus, devfn, 0xc);
+	if (!addr) {
+		*val = ~0;
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	}
+
+	v = readl(addr);
+
+	/* Check for non type-00 header */
+	cfg_type = (v >> 16) & 0x7f;
+
+	addr = bus->ops->map_bus(bus, devfn, 8);
+	if (!addr) {
+		*val = ~0;
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	}
+
+	class_rev = readl(addr);
+	if (class_rev == 0xffffffff)
+		goto no_emulation;
+
+	if ((class_rev & 0xff) >= 8) {
+		/* Pass-2 handling */
+		if (cfg_type)
+			goto no_emulation;
+		return thunder_ecam_p2_config_read(bus, devfn, where,
+						   size, val);
+	}
+
+	/*
+	 * All BARs have fixed addresses specified by the EA
+	 * capability; they must return zero on read.
+	 */
+	if (cfg_type == 0 &&
+	    ((where >= 0x10 && where < 0x2c) ||
+	     (where >= 0x1a4 && where < 0x1bc))) {
+		/* BAR or SR-IOV BAR */
+		*val = 0;
+		return PCIBIOS_SUCCESSFUL;
+	}
+
+	addr = bus->ops->map_bus(bus, devfn, 0);
+	if (!addr) {
+		*val = ~0;
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	}
+
+	vendor_device = readl(addr);
+	if (vendor_device == 0xffffffff)
+		goto no_emulation;
+
+	pr_debug("%04x:%04x - Fix pass#: %08x, where: %03x, devfn: %03x\n",
+		 vendor_device & 0xffff, vendor_device >> 16, class_rev,
+		 (unsigned) where, devfn);
+
+	/* Check for non type-00 header */
+	if (cfg_type == 0) {
+		bool has_msix;
+		bool is_nic = (vendor_device == 0xa01e177d);
+		bool is_tns = (vendor_device == 0xa01f177d);
+
+		addr = bus->ops->map_bus(bus, devfn, 0x70);
+		if (!addr) {
+			*val = ~0;
+			return PCIBIOS_DEVICE_NOT_FOUND;
+		}
+		/* E_CAP */
+		v = readl(addr);
+		has_msix = (v & 0xff00) != 0;
+
+		if (!has_msix && where_a == 0x70) {
+			v |= 0xbc00; /* next capability is EA at 0xbc */
+			set_val(v, where, size, val);
+			return PCIBIOS_SUCCESSFUL;
+		}
+		if (where_a == 0xb0) {
+			addr = bus->ops->map_bus(bus, devfn, where_a);
+			if (!addr) {
+				*val = ~0;
+				return PCIBIOS_DEVICE_NOT_FOUND;
+			}
+			v = readl(addr);
+			if (v & 0xff00)
+				pr_err("Bad MSIX cap header: %08x\n", v);
+			v |= 0xbc00; /* next capability is EA at 0xbc */
+			set_val(v, where, size, val);
+			return PCIBIOS_SUCCESSFUL;
+		}
+		if (where_a == 0xbc) {
+			if (is_nic)
+				v = 0x40014; /* EA last in chain, 4 entries */
+			else if (is_tns)
+				v = 0x30014; /* EA last in chain, 3 entries */
+			else if (has_msix)
+				v = 0x20014; /* EA last in chain, 2 entries */
+			else
+				v = 0x10014; /* EA last in chain, 1 entry */
+			set_val(v, where, size, val);
+			return PCIBIOS_SUCCESSFUL;
+		}
+		if (where_a >= 0xc0 && where_a < 0xd0)
+			/* EA entry-0. PP=0, BAR0 Size:3 */
+			return handle_ea_bar(0x80ff0003,
+					     0x10, bus, devfn, where,
+					     size, val);
+		if (where_a >= 0xd0 && where_a < 0xe0 && has_msix)
+			 /* EA entry-1. PP=0, BAR4 Size:3 */
+			return handle_ea_bar(0x80ff0043,
+					     0x20, bus, devfn, where,
+					     size, val);
+		if (where_a >= 0xe0 && where_a < 0xf0 && is_tns)
+			/* EA entry-2. PP=0, BAR2, Size:3 */
+			return handle_ea_bar(0x80ff0023,
+					     0x18, bus, devfn, where,
+					     size, val);
+		if (where_a >= 0xe0 && where_a < 0xf0 && is_nic)
+			/* EA entry-2. PP=4, VF_BAR0 (9), Size:3 */
+			return handle_ea_bar(0x80ff0493,
+					     0x1a4, bus, devfn, where,
+					     size, val);
+		if (where_a >= 0xf0 && where_a < 0x100 && is_nic)
+			/* EA entry-3. PP=4, VF_BAR4 (d), Size:3 */
+			return handle_ea_bar(0x80ff04d3,
+					     0x1b4, bus, devfn, where,
+					     size, val);
+	} else if (cfg_type == 1) {
+		bool is_rsl_bridge = devfn == 0x08;
+		bool is_rad_bridge = devfn == 0xa0;
+		bool is_zip_bridge = devfn == 0xa8;
+		bool is_dfa_bridge = devfn == 0xb0;
+		bool is_nic_bridge = devfn == 0x10;
+
+		if (where_a == 0x70) {
+			addr = bus->ops->map_bus(bus, devfn, where_a);
+			if (!addr) {
+				*val = ~0;
+				return PCIBIOS_DEVICE_NOT_FOUND;
+			}
+			v = readl(addr);
+			if (v & 0xff00)
+				pr_err("Bad PCIe cap header: %08x\n", v);
+			v |= 0xbc00; /* next capability is EA at 0xbc */
+			set_val(v, where, size, val);
+			return PCIBIOS_SUCCESSFUL;
+		}
+		if (where_a == 0xbc) {
+			if (is_nic_bridge)
+				v = 0x10014; /* EA last in chain, 1 entry */
+			else
+				v = 0x00014; /* EA last in chain, no entries */
+			set_val(v, where, size, val);
+			return PCIBIOS_SUCCESSFUL;
+		}
+		if (where_a == 0xc0) {
+			if (is_rsl_bridge || is_nic_bridge)
+				v = 0x0101; /* subordinate:secondary = 1:1 */
+			else if (is_rad_bridge)
+				v = 0x0202; /* subordinate:secondary = 2:2 */
+			else if (is_zip_bridge)
+				v = 0x0303; /* subordinate:secondary = 3:3 */
+			else if (is_dfa_bridge)
+				v = 0x0404; /* subordinate:secondary = 4:4 */
+			set_val(v, where, size, val);
+			return PCIBIOS_SUCCESSFUL;
+		}
+		if (where_a == 0xc4 && is_nic_bridge) {
+			/* Enabled, not-Write, SP=ff, PP=05, BEI=6, ES=4 */
+			v = 0x80ff0564;
+			set_val(v, where, size, val);
+			return PCIBIOS_SUCCESSFUL;
+		}
+		if (where_a == 0xc8 && is_nic_bridge) {
+			v = 0x00000002; /* Base-L 64-bit */
+			set_val(v, where, size, val);
+			return PCIBIOS_SUCCESSFUL;
+		}
+		if (where_a == 0xcc && is_nic_bridge) {
+			v = 0xfffffffe; /* MaxOffset-L 64-bit */
+			set_val(v, where, size, val);
+			return PCIBIOS_SUCCESSFUL;
+		}
+		if (where_a == 0xd0 && is_nic_bridge) {
+			v = 0x00008430; /* NIC Base-H */
+			set_val(v, where, size, val);
+			return PCIBIOS_SUCCESSFUL;
+		}
+		if (where_a == 0xd4 && is_nic_bridge) {
+			v = 0x0000000f; /* MaxOffset-H */
+			set_val(v, where, size, val);
+			return PCIBIOS_SUCCESSFUL;
+		}
+	}
+no_emulation:
+	return pci_generic_config_read(bus, devfn, where, size, val);
+}
+
+static int thunder_ecam_config_write(struct pci_bus *bus, unsigned int devfn,
+				     int where, int size, u32 val)
+{
+	/*
+	 * All BARs have fixed addresses; ignore BAR writes so they
+	 * don't get corrupted.
+	 */
+	if ((where >= 0x10 && where < 0x2c) ||
+	    (where >= 0x1a4 && where < 0x1bc))
+		/* BAR or SR-IOV BAR */
+		return PCIBIOS_SUCCESSFUL;
+
+	return pci_generic_config_write(bus, devfn, where, size, val);
+}
+
+static struct gen_pci_cfg_bus_ops thunder_ecam_bus_ops = {
+	.bus_shift	= 20,
+	.ops		= {
+		.map_bus        = thunder_ecam_map_bus,
+		.read           = thunder_ecam_config_read,
+		.write          = thunder_ecam_config_write,
+	}
+};
+
+static const struct of_device_id thunder_ecam_of_match[] = {
+	{ .compatible = "cavium,pci-host-thunder-ecam",
+	  .data = &thunder_ecam_bus_ops },
+
+	{ },
+};
+MODULE_DEVICE_TABLE(of, thunder_ecam_of_match);
+
+static int thunder_ecam_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct of_device_id *of_id;
+	struct gen_pci *pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL);
+
+	if (!pci)
+		return -ENOMEM;
+
+	of_id = of_match_node(thunder_ecam_of_match, dev->of_node);
+	pci->cfg.ops = (struct gen_pci_cfg_bus_ops *)of_id->data;
+
+	return pci_host_common_probe(pdev, pci);
+}
+
+static struct platform_driver thunder_ecam_driver = {
+	.driver = {
+		.name = KBUILD_MODNAME,
+		.of_match_table = thunder_ecam_of_match,
+	},
+	.probe = thunder_ecam_probe,
+};
+module_platform_driver(thunder_ecam_driver);
+
+MODULE_DESCRIPTION("Thunder ECAM PCI host driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/host/pci-thunder-pem.c b/drivers/pci/host/pci-thunder-pem.c
new file mode 100644
index 000000000000..cabb92a514ac
--- /dev/null
+++ b/drivers/pci/host/pci-thunder-pem.c
@@ -0,0 +1,346 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * Copyright (C) 2015 - 2016 Cavium, Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_pci.h>
+#include <linux/platform_device.h>
+
+#include "pci-host-common.h"
+
+#define PEM_CFG_WR 0x28
+#define PEM_CFG_RD 0x30
+
+struct thunder_pem_pci {
+	struct gen_pci	gen_pci;
+	u32		ea_entry[3];
+	void __iomem	*pem_reg_base;
+};
+
+static void __iomem *thunder_pem_map_bus(struct pci_bus *bus,
+					 unsigned int devfn, int where)
+{
+	struct gen_pci *pci = bus->sysdata;
+	resource_size_t idx = bus->number - pci->cfg.bus_range->start;
+
+	return pci->cfg.win[idx] + ((devfn << 16) | where);
+}
+
+static int thunder_pem_bridge_read(struct pci_bus *bus, unsigned int devfn,
+				   int where, int size, u32 *val)
+{
+	u64 read_val;
+	struct thunder_pem_pci *pem_pci;
+	struct gen_pci *pci = bus->sysdata;
+
+	pem_pci = container_of(pci, struct thunder_pem_pci, gen_pci);
+
+	if (devfn != 0 || where >= 2048) {
+		*val = ~0;
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	}
+
+	/*
+	 * 32-bit accesses only.  Write the address to the low order
+	 * bits of PEM_CFG_RD, then trigger the read by reading back.
+	 * The config data lands in the upper 32-bits of PEM_CFG_RD.
+	 */
+	read_val = where & ~3ull;
+	writeq(read_val, pem_pci->pem_reg_base + PEM_CFG_RD);
+	read_val = readq(pem_pci->pem_reg_base + PEM_CFG_RD);
+	read_val >>= 32;
+
+	/*
+	 * The config space contains some garbage, fix it up.  Also
+	 * synthesize an EA capability for the BAR used by MSI-X.
+	 */
+	switch (where & ~3) {
+	case 0x40:
+		read_val &= 0xffff00ff;
+		read_val |= 0x00007000; /* Skip MSI CAP */
+		break;
+	case 0x70: /* Express Cap */
+		/* PME interrupt on vector 2*/
+		read_val |= (2u << 25);
+		break;
+	case 0xb0: /* MSI-X Cap */
+		/* TableSize=4, Next Cap is EA */
+		read_val &= 0xc00000ff;
+		read_val |= 0x0003bc00;
+		break;
+	case 0xb4:
+		/* Table offset=0, BIR=0 */
+		read_val = 0x00000000;
+		break;
+	case 0xb8:
+		/* BPA offset=0xf0000, BIR=0 */
+		read_val = 0x000f0000;
+		break;
+	case 0xbc:
+		/* EA, 1 entry, no next Cap */
+		read_val = 0x00010014;
+		break;
+	case 0xc0:
+		/* DW2 for type-1 */
+		read_val = 0x00000000;
+		break;
+	case 0xc4:
+		/* Entry BEI=0, PP=0x00, SP=0xff, ES=3 */
+		read_val = 0x80ff0003;
+		break;
+	case 0xc8:
+		read_val = pem_pci->ea_entry[0];
+		break;
+	case 0xcc:
+		read_val = pem_pci->ea_entry[1];
+		break;
+	case 0xd0:
+		read_val = pem_pci->ea_entry[2];
+		break;
+	default:
+		break;
+	}
+	read_val >>= (8 * (where & 3));
+	switch (size) {
+	case 1:
+		read_val &= 0xff;
+		break;
+	case 2:
+		read_val &= 0xffff;
+		break;
+	default:
+		break;
+	}
+	*val = read_val;
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int thunder_pem_config_read(struct pci_bus *bus, unsigned int devfn,
+				   int where, int size, u32 *val)
+{
+	struct gen_pci *pci = bus->sysdata;
+
+	if (bus->number < pci->cfg.bus_range->start ||
+	    bus->number > pci->cfg.bus_range->end)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	/*
+	 * The first device on the bus is the PEM PCIe bridge.
+	 * Special case its config access.
+	 */
+	if (bus->number == pci->cfg.bus_range->start)
+		return thunder_pem_bridge_read(bus, devfn, where, size, val);
+
+	return pci_generic_config_read(bus, devfn, where, size, val);
+}
+
+/*
+ * Some of the w1c_bits below also include read-only or non-writable
+ * reserved bits, this makes the code simpler and is OK as the bits
+ * are not affected by writing zeros to them.
+ */
+static u32 thunder_pem_bridge_w1c_bits(int where)
+{
+	u32 w1c_bits = 0;
+
+	switch (where & ~3) {
+	case 0x04: /* Command/Status */
+	case 0x1c: /* Base and I/O Limit/Secondary Status */
+		w1c_bits = 0xff000000;
+		break;
+	case 0x44: /* Power Management Control and Status */
+		w1c_bits = 0xfffffe00;
+		break;
+	case 0x78: /* Device Control/Device Status */
+	case 0x80: /* Link Control/Link Status */
+	case 0x88: /* Slot Control/Slot Status */
+	case 0x90: /* Root Status */
+	case 0xa0: /* Link Control 2 Registers/Link Status 2 */
+		w1c_bits = 0xffff0000;
+		break;
+	case 0x104: /* Uncorrectable Error Status */
+	case 0x110: /* Correctable Error Status */
+	case 0x130: /* Error Status */
+	case 0x160: /* Link Control 4 */
+		w1c_bits = 0xffffffff;
+		break;
+	default:
+		break;
+	}
+	return w1c_bits;
+}
+
+static int thunder_pem_bridge_write(struct pci_bus *bus, unsigned int devfn,
+				    int where, int size, u32 val)
+{
+	struct gen_pci *pci = bus->sysdata;
+	struct thunder_pem_pci *pem_pci;
+	u64 write_val, read_val;
+	u32 mask = 0;
+
+	pem_pci = container_of(pci, struct thunder_pem_pci, gen_pci);
+
+	if (devfn != 0 || where >= 2048)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	/*
+	 * 32-bit accesses only.  If the write is for a size smaller
+	 * than 32-bits, we must first read the 32-bit value and merge
+	 * in the desired bits and then write the whole 32-bits back
+	 * out.
+	 */
+	switch (size) {
+	case 1:
+		read_val = where & ~3ull;
+		writeq(read_val, pem_pci->pem_reg_base + PEM_CFG_RD);
+		read_val = readq(pem_pci->pem_reg_base + PEM_CFG_RD);
+		read_val >>= 32;
+		mask = ~(0xff << (8 * (where & 3)));
+		read_val &= mask;
+		val = (val & 0xff) << (8 * (where & 3));
+		val |= (u32)read_val;
+		break;
+	case 2:
+		read_val = where & ~3ull;
+		writeq(read_val, pem_pci->pem_reg_base + PEM_CFG_RD);
+		read_val = readq(pem_pci->pem_reg_base + PEM_CFG_RD);
+		read_val >>= 32;
+		mask = ~(0xffff << (8 * (where & 3)));
+		read_val &= mask;
+		val = (val & 0xffff) << (8 * (where & 3));
+		val |= (u32)read_val;
+		break;
+	default:
+		break;
+	}
+
+	/*
+	 * By expanding the write width to 32 bits, we may
+	 * inadvertently hit some W1C bits that were not intended to
+	 * be written.  Calculate the mask that must be applied to the
+	 * data to be written to avoid these cases.
+	 */
+	if (mask) {
+		u32 w1c_bits = thunder_pem_bridge_w1c_bits(where);
+
+		if (w1c_bits) {
+			mask &= w1c_bits;
+			val &= ~mask;
+		}
+	}
+
+	/*
+	 * Low order bits are the config address, the high order 32
+	 * bits are the data to be written.
+	 */
+	write_val = where & ~3ull;
+	write_val |= (((u64)val) << 32);
+	writeq(write_val, pem_pci->pem_reg_base + PEM_CFG_WR);
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int thunder_pem_config_write(struct pci_bus *bus, unsigned int devfn,
+				    int where, int size, u32 val)
+{
+	struct gen_pci *pci = bus->sysdata;
+
+	if (bus->number < pci->cfg.bus_range->start ||
+	    bus->number > pci->cfg.bus_range->end)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	/*
+	 * The first device on the bus is the PEM PCIe bridge.
+	 * Special case its config access.
+	 */
+	if (bus->number == pci->cfg.bus_range->start)
+		return thunder_pem_bridge_write(bus, devfn, where, size, val);
+
+
+	return pci_generic_config_write(bus, devfn, where, size, val);
+}
+
+static struct gen_pci_cfg_bus_ops thunder_pem_bus_ops = {
+	.bus_shift	= 24,
+	.ops		= {
+		.map_bus	= thunder_pem_map_bus,
+		.read		= thunder_pem_config_read,
+		.write		= thunder_pem_config_write,
+	}
+};
+
+static const struct of_device_id thunder_pem_of_match[] = {
+	{ .compatible = "cavium,pci-host-thunder-pem",
+	  .data = &thunder_pem_bus_ops },
+
+	{ },
+};
+MODULE_DEVICE_TABLE(of, thunder_pem_of_match);
+
+static int thunder_pem_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct of_device_id *of_id;
+	resource_size_t bar4_start;
+	struct resource *res_pem;
+	struct thunder_pem_pci *pem_pci;
+
+	pem_pci = devm_kzalloc(dev, sizeof(*pem_pci), GFP_KERNEL);
+	if (!pem_pci)
+		return -ENOMEM;
+
+	of_id = of_match_node(thunder_pem_of_match, dev->of_node);
+	pem_pci->gen_pci.cfg.ops = (struct gen_pci_cfg_bus_ops *)of_id->data;
+
+	/*
+	 * The second register range is the PEM bridge to the PCIe
+	 * bus.  It has a different config access method than those
+	 * devices behind the bridge.
+	 */
+	res_pem = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (!res_pem) {
+		dev_err(dev, "missing \"reg[1]\"property\n");
+		return -EINVAL;
+	}
+
+	pem_pci->pem_reg_base = devm_ioremap(dev, res_pem->start, 0x10000);
+	if (!pem_pci->pem_reg_base)
+		return -ENOMEM;
+
+	/*
+	 * The MSI-X BAR for the PEM and AER interrupts is located at
+	 * a fixed offset from the PEM register base.  Generate a
+	 * fragment of the synthesized Enhanced Allocation capability
+	 * structure here for the BAR.
+	 */
+	bar4_start = res_pem->start + 0xf00000;
+	pem_pci->ea_entry[0] = (u32)bar4_start | 2;
+	pem_pci->ea_entry[1] = (u32)(res_pem->end - bar4_start) & ~3u;
+	pem_pci->ea_entry[2] = (u32)(bar4_start >> 32);
+
+	return pci_host_common_probe(pdev, &pem_pci->gen_pci);
+}
+
+static struct platform_driver thunder_pem_driver = {
+	.driver = {
+		.name = KBUILD_MODNAME,
+		.of_match_table = thunder_pem_of_match,
+	},
+	.probe = thunder_pem_probe,
+};
+module_platform_driver(thunder_pem_driver);
+
+MODULE_DESCRIPTION("Thunder PEM PCIe host driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/host/pcie-altera.c b/drivers/pci/host/pcie-altera.c
index 99da549d5d06..dbac6fb3f0bd 100644
--- a/drivers/pci/host/pcie-altera.c
+++ b/drivers/pci/host/pcie-altera.c
@@ -40,6 +40,7 @@
 #define P2A_INT_ENABLE			0x3070
 #define P2A_INT_ENA_ALL			0xf
 #define RP_LTSSM			0x3c64
+#define RP_LTSSM_MASK			0x1f
 #define LTSSM_L0			0xf
 
 /* TLP configuration type 0 and 1 */
@@ -140,7 +141,7 @@ static void tlp_write_tx(struct altera_pcie *pcie,
 
 static bool altera_pcie_link_is_up(struct altera_pcie *pcie)
 {
-	return !!(cra_readl(pcie, RP_LTSSM) & LTSSM_L0);
+	return !!((cra_readl(pcie, RP_LTSSM) & RP_LTSSM_MASK) == LTSSM_L0);
 }
 
 static bool altera_pcie_valid_config(struct altera_pcie *pcie,
diff --git a/drivers/pci/host/pcie-designware-plat.c b/drivers/pci/host/pcie-designware-plat.c
new file mode 100644
index 000000000000..b3500994d08a
--- /dev/null
+++ b/drivers/pci/host/pcie-designware-plat.c
@@ -0,0 +1,138 @@
+/*
+ * PCIe RC driver for Synopsys DesignWare Core
+ *
+ * Copyright (C) 2015-2016 Synopsys, Inc. (www.synopsys.com)
+ *
+ * Authors: Joao Pinto <jpinto@synopsys.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/gpio.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_gpio.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/resource.h>
+#include <linux/signal.h>
+#include <linux/types.h>
+
+#include "pcie-designware.h"
+
+struct dw_plat_pcie {
+	void __iomem		*mem_base;
+	struct pcie_port	pp;
+};
+
+static irqreturn_t dw_plat_pcie_msi_irq_handler(int irq, void *arg)
+{
+	struct pcie_port *pp = arg;
+
+	return dw_handle_msi_irq(pp);
+}
+
+static void dw_plat_pcie_host_init(struct pcie_port *pp)
+{
+	dw_pcie_setup_rc(pp);
+	dw_pcie_wait_for_link(pp);
+
+	if (IS_ENABLED(CONFIG_PCI_MSI))
+		dw_pcie_msi_init(pp);
+}
+
+static struct pcie_host_ops dw_plat_pcie_host_ops = {
+	.host_init = dw_plat_pcie_host_init,
+};
+
+static int dw_plat_add_pcie_port(struct pcie_port *pp,
+				 struct platform_device *pdev)
+{
+	int ret;
+
+	pp->irq = platform_get_irq(pdev, 1);
+	if (pp->irq < 0)
+		return pp->irq;
+
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+		pp->msi_irq = platform_get_irq(pdev, 0);
+		if (pp->msi_irq < 0)
+			return pp->msi_irq;
+
+		ret = devm_request_irq(&pdev->dev, pp->msi_irq,
+					dw_plat_pcie_msi_irq_handler,
+					IRQF_SHARED, "dw-plat-pcie-msi", pp);
+		if (ret) {
+			dev_err(&pdev->dev, "failed to request MSI IRQ\n");
+			return ret;
+		}
+	}
+
+	pp->root_bus_nr = -1;
+	pp->ops = &dw_plat_pcie_host_ops;
+
+	ret = dw_pcie_host_init(pp);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to initialize host\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int dw_plat_pcie_probe(struct platform_device *pdev)
+{
+	struct dw_plat_pcie *dw_plat_pcie;
+	struct pcie_port *pp;
+	struct resource *res;  /* Resource from DT */
+	int ret;
+
+	dw_plat_pcie = devm_kzalloc(&pdev->dev, sizeof(*dw_plat_pcie),
+					GFP_KERNEL);
+	if (!dw_plat_pcie)
+		return -ENOMEM;
+
+	pp = &dw_plat_pcie->pp;
+	pp->dev = &pdev->dev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENODEV;
+
+	dw_plat_pcie->mem_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(dw_plat_pcie->mem_base))
+		return PTR_ERR(dw_plat_pcie->mem_base);
+
+	pp->dbi_base = dw_plat_pcie->mem_base;
+
+	ret = dw_plat_add_pcie_port(pp, pdev);
+	if (ret < 0)
+		return ret;
+
+	platform_set_drvdata(pdev, dw_plat_pcie);
+	return 0;
+}
+
+static const struct of_device_id dw_plat_pcie_of_match[] = {
+	{ .compatible = "snps,dw-pcie", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, dw_plat_pcie_of_match);
+
+static struct platform_driver dw_plat_pcie_driver = {
+	.driver = {
+		.name	= "dw-pcie",
+		.of_match_table = dw_plat_pcie_of_match,
+	},
+	.probe = dw_plat_pcie_probe,
+};
+
+module_platform_driver(dw_plat_pcie_driver);
+
+MODULE_AUTHOR("Joao Pinto <Joao.Pinto@synopsys.com>");
+MODULE_DESCRIPTION("Synopsys PCIe host controller glue platform driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index 21716827847a..a4cccd356304 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -22,6 +22,7 @@
 #include <linux/pci_regs.h>
 #include <linux/platform_device.h>
 #include <linux/types.h>
+#include <linux/delay.h>
 
 #include "pcie-designware.h"
 
@@ -69,6 +70,11 @@
 #define PCIE_ATU_FUNC(x)		(((x) & 0x7) << 16)
 #define PCIE_ATU_UPPER_TARGET		0x91C
 
+/* PCIe Port Logic registers */
+#define PLR_OFFSET			0x700
+#define PCIE_PHY_DEBUG_R1		(PLR_OFFSET + 0x2c)
+#define PCIE_PHY_DEBUG_R1_LINK_UP	0x00000010
+
 static struct pci_ops dw_pcie_ops;
 
 int dw_pcie_cfg_read(void __iomem *addr, int size, u32 *val)
@@ -380,12 +386,33 @@ static struct msi_controller dw_pcie_msi_chip = {
 	.teardown_irq = dw_msi_teardown_irq,
 };
 
+int dw_pcie_wait_for_link(struct pcie_port *pp)
+{
+	int retries;
+
+	/* check if the link is up or not */
+	for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) {
+		if (dw_pcie_link_up(pp)) {
+			dev_info(pp->dev, "link up\n");
+			return 0;
+		}
+		usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX);
+	}
+
+	dev_err(pp->dev, "phy link never came up\n");
+
+	return -ETIMEDOUT;
+}
+
 int dw_pcie_link_up(struct pcie_port *pp)
 {
+	u32 val;
+
 	if (pp->ops->link_up)
 		return pp->ops->link_up(pp);
 
-	return 0;
+	val = readl(pp->dbi_base + PCIE_PHY_DEBUG_R1);
+	return val & PCIE_PHY_DEBUG_R1_LINK_UP;
 }
 
 static int dw_pcie_msi_map(struct irq_domain *domain, unsigned int irq,
@@ -517,6 +544,11 @@ int dw_pcie_host_init(struct pcie_port *pp)
 	if (pp->ops->host_init)
 		pp->ops->host_init(pp);
 
+	/*
+	 * If the platform provides ->rd_other_conf, it means the platform
+	 * uses its own address translation component rather than ATU, so
+	 * we should not program the ATU here.
+	 */
 	if (!pp->ops->rd_other_conf)
 		dw_pcie_prog_outbound_atu(pp, PCIE_ATU_REGION_INDEX1,
 					  PCIE_ATU_TYPE_MEM, pp->mem_base,
@@ -551,13 +583,11 @@ int dw_pcie_host_init(struct pcie_port *pp)
 	pci_fixup_irqs(pci_common_swizzle, of_irq_parse_and_map_pci);
 #endif
 
-	if (!pci_has_flag(PCI_PROBE_ONLY)) {
-		pci_bus_size_bridges(bus);
-		pci_bus_assign_resources(bus);
+	pci_bus_size_bridges(bus);
+	pci_bus_assign_resources(bus);
 
-		list_for_each_entry(child, &bus->children, node)
-			pcie_bus_configure_settings(child);
-	}
+	list_for_each_entry(child, &bus->children, node)
+		pcie_bus_configure_settings(child);
 
 	pci_bus_add_devices(bus);
 	return 0;
diff --git a/drivers/pci/host/pcie-designware.h b/drivers/pci/host/pcie-designware.h
index 2356d29e8527..f437f9b5be04 100644
--- a/drivers/pci/host/pcie-designware.h
+++ b/drivers/pci/host/pcie-designware.h
@@ -22,6 +22,11 @@
 #define MAX_MSI_IRQS			32
 #define MAX_MSI_CTRLS			(MAX_MSI_IRQS / 32)
 
+/* Parameters for the waiting for link up routine */
+#define LINK_WAIT_MAX_RETRIES		10
+#define LINK_WAIT_USLEEP_MIN		90000
+#define LINK_WAIT_USLEEP_MAX		100000
+
 struct pcie_port {
 	struct device		*dev;
 	u8			root_bus_nr;
@@ -76,6 +81,7 @@ int dw_pcie_cfg_read(void __iomem *addr, int size, u32 *val);
 int dw_pcie_cfg_write(void __iomem *addr, int size, u32 val);
 irqreturn_t dw_handle_msi_irq(struct pcie_port *pp);
 void dw_pcie_msi_init(struct pcie_port *pp);
+int dw_pcie_wait_for_link(struct pcie_port *pp);
 int dw_pcie_link_up(struct pcie_port *pp);
 void dw_pcie_setup_rc(struct pcie_port *pp);
 int dw_pcie_host_init(struct pcie_port *pp);
diff --git a/drivers/pci/host/pcie-iproc.c b/drivers/pci/host/pcie-iproc.c
index 5816bceddb65..a576aeeb22da 100644
--- a/drivers/pci/host/pcie-iproc.c
+++ b/drivers/pci/host/pcie-iproc.c
@@ -64,7 +64,6 @@
 #define OARR_SIZE_CFG                BIT(OARR_SIZE_CFG_SHIFT)
 
 #define MAX_NUM_OB_WINDOWS           2
-#define MAX_NUM_PAXC_PF              4
 
 #define IPROC_PCIE_REG_INVALID 0xffff
 
@@ -170,20 +169,6 @@ static inline void iproc_pcie_ob_write(struct iproc_pcie *pcie,
 	writel(val, pcie->base + offset + (window * 8));
 }
 
-static inline bool iproc_pcie_device_is_valid(struct iproc_pcie *pcie,
-					      unsigned int slot,
-					      unsigned int fn)
-{
-	if (slot > 0)
-		return false;
-
-	/* PAXC can only support limited number of functions */
-	if (pcie->type == IPROC_PCIE_PAXC && fn >= MAX_NUM_PAXC_PF)
-		return false;
-
-	return true;
-}
-
 /**
  * Note access to the configuration registers are protected at the higher layer
  * by 'pci_lock' in drivers/pci/access.c
@@ -199,11 +184,11 @@ static void __iomem *iproc_pcie_map_cfg_bus(struct pci_bus *bus,
 	u32 val;
 	u16 offset;
 
-	if (!iproc_pcie_device_is_valid(pcie, slot, fn))
-		return NULL;
-
 	/* root complex access */
 	if (busno == 0) {
+		if (slot > 0 || fn > 0)
+			return NULL;
+
 		iproc_pcie_write_reg(pcie, IPROC_PCIE_CFG_IND_ADDR,
 				     where & CFG_IND_ADDR_MASK);
 		offset = iproc_pcie_reg_offset(pcie, IPROC_PCIE_CFG_IND_DATA);
@@ -213,6 +198,14 @@ static void __iomem *iproc_pcie_map_cfg_bus(struct pci_bus *bus,
 			return (pcie->base + offset);
 	}
 
+	/*
+	 * PAXC is connected to an internally emulated EP within the SoC.  It
+	 * allows only one device.
+	 */
+	if (pcie->type == IPROC_PCIE_PAXC)
+		if (slot > 0)
+			return NULL;
+
 	/* EP device access */
 	val = (busno << CFG_ADDR_BUS_NUM_SHIFT) |
 		(slot << CFG_ADDR_DEV_NUM_SHIFT) |
diff --git a/drivers/pci/host/pcie-qcom.c b/drivers/pci/host/pcie-qcom.c
index e845fba19632..f2f90c50f75d 100644
--- a/drivers/pci/host/pcie-qcom.c
+++ b/drivers/pci/host/pcie-qcom.c
@@ -116,8 +116,6 @@ static irqreturn_t qcom_pcie_msi_irq_handler(int irq, void *arg)
 
 static int qcom_pcie_establish_link(struct qcom_pcie *pcie)
 {
-	struct device *dev = pcie->dev;
-	unsigned int retries = 0;
 	u32 val;
 
 	if (dw_pcie_link_up(&pcie->pp))
@@ -128,15 +126,7 @@ static int qcom_pcie_establish_link(struct qcom_pcie *pcie)
 	val |= PCIE20_ELBI_SYS_CTRL_LT_ENABLE;
 	writel(val, pcie->elbi + PCIE20_ELBI_SYS_CTRL);
 
-	do {
-		if (dw_pcie_link_up(&pcie->pp))
-			return 0;
-		usleep_range(250, 1000);
-	} while (retries < 200);
-
-	dev_warn(dev, "phy link never came up\n");
-
-	return -ETIMEDOUT;
+	return dw_pcie_wait_for_link(&pcie->pp);
 }
 
 static int qcom_pcie_get_resources_v0(struct qcom_pcie *pcie)
diff --git a/drivers/pci/host/pcie-rcar.c b/drivers/pci/host/pcie-rcar.c
index 4edb5181f4e2..35092188039b 100644
--- a/drivers/pci/host/pcie-rcar.c
+++ b/drivers/pci/host/pcie-rcar.c
@@ -390,9 +390,7 @@ static int rcar_pcie_enable(struct rcar_pcie *pcie)
 
 	rcar_pcie_setup(&res, pcie);
 
-	/* Do not reassign resources if probe only */
-	if (!pci_has_flag(PCI_PROBE_ONLY))
-		pci_add_flags(PCI_REASSIGN_ALL_RSRC | PCI_REASSIGN_ALL_BUS);
+	pci_add_flags(PCI_REASSIGN_ALL_RSRC | PCI_REASSIGN_ALL_BUS);
 
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		bus = pci_scan_root_bus_msi(pcie->dev, pcie->root_bus_nr,
@@ -408,13 +406,11 @@ static int rcar_pcie_enable(struct rcar_pcie *pcie)
 
 	pci_fixup_irqs(pci_common_swizzle, of_irq_parse_and_map_pci);
 
-	if (!pci_has_flag(PCI_PROBE_ONLY)) {
-		pci_bus_size_bridges(bus);
-		pci_bus_assign_resources(bus);
+	pci_bus_size_bridges(bus);
+	pci_bus_assign_resources(bus);
 
-		list_for_each_entry(child, &bus->children, node)
-			pcie_bus_configure_settings(child);
-	}
+	list_for_each_entry(child, &bus->children, node)
+		pcie_bus_configure_settings(child);
 
 	pci_bus_add_devices(bus);
 
diff --git a/drivers/pci/host/pcie-spear13xx.c b/drivers/pci/host/pcie-spear13xx.c
index a6cd8233e8c0..a4060b85ab23 100644
--- a/drivers/pci/host/pcie-spear13xx.c
+++ b/drivers/pci/host/pcie-spear13xx.c
@@ -13,7 +13,6 @@
  */
 
 #include <linux/clk.h>
-#include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -149,7 +148,6 @@ static int spear13xx_pcie_establish_link(struct pcie_port *pp)
 	struct spear13xx_pcie *spear13xx_pcie = to_spear13xx_pcie(pp);
 	struct pcie_app_reg *app_reg = spear13xx_pcie->app_base;
 	u32 exp_cap_off = EXP_CAP_ID_OFFSET;
-	unsigned int retries;
 
 	if (dw_pcie_link_up(pp)) {
 		dev_err(pp->dev, "link already up\n");
@@ -200,17 +198,7 @@ static int spear13xx_pcie_establish_link(struct pcie_port *pp)
 			| ((u32)1 << REG_TRANSLATION_ENABLE),
 			&app_reg->app_ctrl_0);
 
-	/* check if the link is up or not */
-	for (retries = 0; retries < 10; retries++) {
-		if (dw_pcie_link_up(pp)) {
-			dev_info(pp->dev, "link up\n");
-			return 0;
-		}
-		mdelay(100);
-	}
-
-	dev_err(pp->dev, "link Fail\n");
-	return -EINVAL;
+	return dw_pcie_wait_for_link(pp);
 }
 
 static irqreturn_t spear13xx_pcie_irq_handler(int irq, void *arg)
diff --git a/drivers/pci/host/pcie-xilinx-nwl.c b/drivers/pci/host/pcie-xilinx-nwl.c
new file mode 100644
index 000000000000..5139e6443bbd
--- /dev/null
+++ b/drivers/pci/host/pcie-xilinx-nwl.c
@@ -0,0 +1,881 @@
+/*
+ * PCIe host controller driver for NWL PCIe Bridge
+ * Based on pcie-xilinx.c, pci-tegra.c
+ *
+ * (C) Copyright 2014 - 2015, Xilinx, Inc.
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/msi.h>
+#include <linux/of_address.h>
+#include <linux/of_pci.h>
+#include <linux/of_platform.h>
+#include <linux/of_irq.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/irqchip/chained_irq.h>
+
+/* Bridge core config registers */
+#define BRCFG_PCIE_RX0			0x00000000
+#define BRCFG_INTERRUPT			0x00000010
+#define BRCFG_PCIE_RX_MSG_FILTER	0x00000020
+
+/* Egress - Bridge translation registers */
+#define E_BREG_CAPABILITIES		0x00000200
+#define E_BREG_CONTROL			0x00000208
+#define E_BREG_BASE_LO			0x00000210
+#define E_BREG_BASE_HI			0x00000214
+#define E_ECAM_CAPABILITIES		0x00000220
+#define E_ECAM_CONTROL			0x00000228
+#define E_ECAM_BASE_LO			0x00000230
+#define E_ECAM_BASE_HI			0x00000234
+
+/* Ingress - address translations */
+#define I_MSII_CAPABILITIES		0x00000300
+#define I_MSII_CONTROL			0x00000308
+#define I_MSII_BASE_LO			0x00000310
+#define I_MSII_BASE_HI			0x00000314
+
+#define I_ISUB_CONTROL			0x000003E8
+#define SET_ISUB_CONTROL		BIT(0)
+/* Rxed msg fifo  - Interrupt status registers */
+#define MSGF_MISC_STATUS		0x00000400
+#define MSGF_MISC_MASK			0x00000404
+#define MSGF_LEG_STATUS			0x00000420
+#define MSGF_LEG_MASK			0x00000424
+#define MSGF_MSI_STATUS_LO		0x00000440
+#define MSGF_MSI_STATUS_HI		0x00000444
+#define MSGF_MSI_MASK_LO		0x00000448
+#define MSGF_MSI_MASK_HI		0x0000044C
+
+/* Msg filter mask bits */
+#define CFG_ENABLE_PM_MSG_FWD		BIT(1)
+#define CFG_ENABLE_INT_MSG_FWD		BIT(2)
+#define CFG_ENABLE_ERR_MSG_FWD		BIT(3)
+#define CFG_ENABLE_SLT_MSG_FWD		BIT(5)
+#define CFG_ENABLE_VEN_MSG_FWD		BIT(7)
+#define CFG_ENABLE_OTH_MSG_FWD		BIT(13)
+#define CFG_ENABLE_VEN_MSG_EN		BIT(14)
+#define CFG_ENABLE_VEN_MSG_VEN_INV	BIT(15)
+#define CFG_ENABLE_VEN_MSG_VEN_ID	GENMASK(31, 16)
+#define CFG_ENABLE_MSG_FILTER_MASK	(CFG_ENABLE_PM_MSG_FWD | \
+					CFG_ENABLE_INT_MSG_FWD | \
+					CFG_ENABLE_ERR_MSG_FWD | \
+					CFG_ENABLE_SLT_MSG_FWD | \
+					CFG_ENABLE_VEN_MSG_FWD | \
+					CFG_ENABLE_OTH_MSG_FWD | \
+					CFG_ENABLE_VEN_MSG_EN | \
+					CFG_ENABLE_VEN_MSG_VEN_INV | \
+					CFG_ENABLE_VEN_MSG_VEN_ID)
+
+/* Misc interrupt status mask bits */
+#define MSGF_MISC_SR_RXMSG_AVAIL	BIT(0)
+#define MSGF_MISC_SR_RXMSG_OVER		BIT(1)
+#define MSGF_MISC_SR_SLAVE_ERR		BIT(4)
+#define MSGF_MISC_SR_MASTER_ERR		BIT(5)
+#define MSGF_MISC_SR_I_ADDR_ERR		BIT(6)
+#define MSGF_MISC_SR_E_ADDR_ERR		BIT(7)
+#define MSGF_MISC_SR_UR_DETECT          BIT(20)
+
+#define MSGF_MISC_SR_PCIE_CORE		GENMASK(18, 16)
+#define MSGF_MISC_SR_PCIE_CORE_ERR	GENMASK(31, 22)
+
+#define MSGF_MISC_SR_MASKALL		(MSGF_MISC_SR_RXMSG_AVAIL | \
+					MSGF_MISC_SR_RXMSG_OVER | \
+					MSGF_MISC_SR_SLAVE_ERR | \
+					MSGF_MISC_SR_MASTER_ERR | \
+					MSGF_MISC_SR_I_ADDR_ERR | \
+					MSGF_MISC_SR_E_ADDR_ERR | \
+					MSGF_MISC_SR_UR_DETECT | \
+					MSGF_MISC_SR_PCIE_CORE | \
+					MSGF_MISC_SR_PCIE_CORE_ERR)
+
+/* Legacy interrupt status mask bits */
+#define MSGF_LEG_SR_INTA		BIT(0)
+#define MSGF_LEG_SR_INTB		BIT(1)
+#define MSGF_LEG_SR_INTC		BIT(2)
+#define MSGF_LEG_SR_INTD		BIT(3)
+#define MSGF_LEG_SR_MASKALL		(MSGF_LEG_SR_INTA | MSGF_LEG_SR_INTB | \
+					MSGF_LEG_SR_INTC | MSGF_LEG_SR_INTD)
+
+/* MSI interrupt status mask bits */
+#define MSGF_MSI_SR_LO_MASK		BIT(0)
+#define MSGF_MSI_SR_HI_MASK		BIT(0)
+
+#define MSII_PRESENT			BIT(0)
+#define MSII_ENABLE			BIT(0)
+#define MSII_STATUS_ENABLE		BIT(15)
+
+/* Bridge config interrupt mask */
+#define BRCFG_INTERRUPT_MASK		BIT(0)
+#define BREG_PRESENT			BIT(0)
+#define BREG_ENABLE			BIT(0)
+#define BREG_ENABLE_FORCE		BIT(1)
+
+/* E_ECAM status mask bits */
+#define E_ECAM_PRESENT			BIT(0)
+#define E_ECAM_CR_ENABLE		BIT(0)
+#define E_ECAM_SIZE_LOC			GENMASK(20, 16)
+#define E_ECAM_SIZE_SHIFT		16
+#define ECAM_BUS_LOC_SHIFT		20
+#define ECAM_DEV_LOC_SHIFT		12
+#define NWL_ECAM_VALUE_DEFAULT		12
+
+#define CFG_DMA_REG_BAR			GENMASK(2, 0)
+
+#define INT_PCI_MSI_NR			(2 * 32)
+#define INTX_NUM			4
+
+/* Readin the PS_LINKUP */
+#define PS_LINKUP_OFFSET		0x00000238
+#define PCIE_PHY_LINKUP_BIT		BIT(0)
+#define PHY_RDY_LINKUP_BIT		BIT(1)
+
+/* Parameters for the waiting for link up routine */
+#define LINK_WAIT_MAX_RETRIES          10
+#define LINK_WAIT_USLEEP_MIN           90000
+#define LINK_WAIT_USLEEP_MAX           100000
+
+struct nwl_msi {			/* MSI information */
+	struct irq_domain *msi_domain;
+	unsigned long *bitmap;
+	struct irq_domain *dev_domain;
+	struct mutex lock;		/* protect bitmap variable */
+	int irq_msi0;
+	int irq_msi1;
+};
+
+struct nwl_pcie {
+	struct device *dev;
+	void __iomem *breg_base;
+	void __iomem *pcireg_base;
+	void __iomem *ecam_base;
+	phys_addr_t phys_breg_base;	/* Physical Bridge Register Base */
+	phys_addr_t phys_pcie_reg_base;	/* Physical PCIe Controller Base */
+	phys_addr_t phys_ecam_base;	/* Physical Configuration Base */
+	u32 breg_size;
+	u32 pcie_reg_size;
+	u32 ecam_size;
+	int irq_intx;
+	int irq_misc;
+	u32 ecam_value;
+	u8 last_busno;
+	u8 root_busno;
+	struct nwl_msi msi;
+	struct irq_domain *legacy_irq_domain;
+};
+
+static inline u32 nwl_bridge_readl(struct nwl_pcie *pcie, u32 off)
+{
+	return readl(pcie->breg_base + off);
+}
+
+static inline void nwl_bridge_writel(struct nwl_pcie *pcie, u32 val, u32 off)
+{
+	writel(val, pcie->breg_base + off);
+}
+
+static bool nwl_pcie_link_up(struct nwl_pcie *pcie)
+{
+	if (readl(pcie->pcireg_base + PS_LINKUP_OFFSET) & PCIE_PHY_LINKUP_BIT)
+		return true;
+	return false;
+}
+
+static bool nwl_phy_link_up(struct nwl_pcie *pcie)
+{
+	if (readl(pcie->pcireg_base + PS_LINKUP_OFFSET) & PHY_RDY_LINKUP_BIT)
+		return true;
+	return false;
+}
+
+static int nwl_wait_for_link(struct nwl_pcie *pcie)
+{
+	int retries;
+
+	/* check if the link is up or not */
+	for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) {
+		if (nwl_phy_link_up(pcie))
+			return 0;
+		usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX);
+	}
+
+	dev_err(pcie->dev, "PHY link never came up\n");
+	return -ETIMEDOUT;
+}
+
+static bool nwl_pcie_valid_device(struct pci_bus *bus, unsigned int devfn)
+{
+	struct nwl_pcie *pcie = bus->sysdata;
+
+	/* Check link before accessing downstream ports */
+	if (bus->number != pcie->root_busno) {
+		if (!nwl_pcie_link_up(pcie))
+			return false;
+	}
+
+	/* Only one device down on each root port */
+	if (bus->number == pcie->root_busno && devfn > 0)
+		return false;
+
+	return true;
+}
+
+/**
+ * nwl_pcie_map_bus - Get configuration base
+ *
+ * @bus: Bus structure of current bus
+ * @devfn: Device/function
+ * @where: Offset from base
+ *
+ * Return: Base address of the configuration space needed to be
+ *	   accessed.
+ */
+static void __iomem *nwl_pcie_map_bus(struct pci_bus *bus, unsigned int devfn,
+				      int where)
+{
+	struct nwl_pcie *pcie = bus->sysdata;
+	int relbus;
+
+	if (!nwl_pcie_valid_device(bus, devfn))
+		return NULL;
+
+	relbus = (bus->number << ECAM_BUS_LOC_SHIFT) |
+			(devfn << ECAM_DEV_LOC_SHIFT);
+
+	return pcie->ecam_base + relbus + where;
+}
+
+/* PCIe operations */
+static struct pci_ops nwl_pcie_ops = {
+	.map_bus = nwl_pcie_map_bus,
+	.read  = pci_generic_config_read,
+	.write = pci_generic_config_write,
+};
+
+static irqreturn_t nwl_pcie_misc_handler(int irq, void *data)
+{
+	struct nwl_pcie *pcie = data;
+	u32 misc_stat;
+
+	/* Checking for misc interrupts */
+	misc_stat = nwl_bridge_readl(pcie, MSGF_MISC_STATUS) &
+				     MSGF_MISC_SR_MASKALL;
+	if (!misc_stat)
+		return IRQ_NONE;
+
+	if (misc_stat & MSGF_MISC_SR_RXMSG_OVER)
+		dev_err(pcie->dev, "Received Message FIFO Overflow\n");
+
+	if (misc_stat & MSGF_MISC_SR_SLAVE_ERR)
+		dev_err(pcie->dev, "Slave error\n");
+
+	if (misc_stat & MSGF_MISC_SR_MASTER_ERR)
+		dev_err(pcie->dev, "Master error\n");
+
+	if (misc_stat & MSGF_MISC_SR_I_ADDR_ERR)
+		dev_err(pcie->dev,
+			"In Misc Ingress address translation error\n");
+
+	if (misc_stat & MSGF_MISC_SR_E_ADDR_ERR)
+		dev_err(pcie->dev,
+			"In Misc Egress address translation error\n");
+
+	if (misc_stat & MSGF_MISC_SR_PCIE_CORE_ERR)
+		dev_err(pcie->dev, "PCIe Core error\n");
+
+	/* Clear misc interrupt status */
+	nwl_bridge_writel(pcie, misc_stat, MSGF_MISC_STATUS);
+
+	return IRQ_HANDLED;
+}
+
+static void nwl_pcie_leg_handler(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct nwl_pcie *pcie;
+	unsigned long status;
+	u32 bit;
+	u32 virq;
+
+	chained_irq_enter(chip, desc);
+	pcie = irq_desc_get_handler_data(desc);
+
+	while ((status = nwl_bridge_readl(pcie, MSGF_LEG_STATUS) &
+				MSGF_LEG_SR_MASKALL) != 0) {
+		for_each_set_bit(bit, &status, INTX_NUM) {
+			virq = irq_find_mapping(pcie->legacy_irq_domain,
+						bit + 1);
+			if (virq)
+				generic_handle_irq(virq);
+		}
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static void nwl_pcie_handle_msi_irq(struct nwl_pcie *pcie, u32 status_reg)
+{
+	struct nwl_msi *msi;
+	unsigned long status;
+	u32 bit;
+	u32 virq;
+
+	msi = &pcie->msi;
+
+	while ((status = nwl_bridge_readl(pcie, status_reg)) != 0) {
+		for_each_set_bit(bit, &status, 32) {
+			nwl_bridge_writel(pcie, 1 << bit, status_reg);
+			virq = irq_find_mapping(msi->dev_domain, bit);
+			if (virq)
+				generic_handle_irq(virq);
+		}
+	}
+}
+
+static void nwl_pcie_msi_handler_high(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct nwl_pcie *pcie = irq_desc_get_handler_data(desc);
+
+	chained_irq_enter(chip, desc);
+	nwl_pcie_handle_msi_irq(pcie, MSGF_MSI_STATUS_HI);
+	chained_irq_exit(chip, desc);
+}
+
+static void nwl_pcie_msi_handler_low(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct nwl_pcie *pcie = irq_desc_get_handler_data(desc);
+
+	chained_irq_enter(chip, desc);
+	nwl_pcie_handle_msi_irq(pcie, MSGF_MSI_STATUS_LO);
+	chained_irq_exit(chip, desc);
+}
+
+static int nwl_legacy_map(struct irq_domain *domain, unsigned int irq,
+			  irq_hw_number_t hwirq)
+{
+	irq_set_chip_and_handler(irq, &dummy_irq_chip, handle_simple_irq);
+	irq_set_chip_data(irq, domain->host_data);
+
+	return 0;
+}
+
+static const struct irq_domain_ops legacy_domain_ops = {
+	.map = nwl_legacy_map,
+};
+
+#ifdef CONFIG_PCI_MSI
+static struct irq_chip nwl_msi_irq_chip = {
+	.name = "nwl_pcie:msi",
+	.irq_enable = unmask_msi_irq,
+	.irq_disable = mask_msi_irq,
+	.irq_mask = mask_msi_irq,
+	.irq_unmask = unmask_msi_irq,
+
+};
+
+static struct msi_domain_info nwl_msi_domain_info = {
+	.flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		  MSI_FLAG_MULTI_PCI_MSI),
+	.chip = &nwl_msi_irq_chip,
+};
+#endif
+
+static void nwl_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	struct nwl_pcie *pcie = irq_data_get_irq_chip_data(data);
+	phys_addr_t msi_addr = pcie->phys_pcie_reg_base;
+
+	msg->address_lo = lower_32_bits(msi_addr);
+	msg->address_hi = upper_32_bits(msi_addr);
+	msg->data = data->hwirq;
+}
+
+static int nwl_msi_set_affinity(struct irq_data *irq_data,
+				const struct cpumask *mask, bool force)
+{
+	return -EINVAL;
+}
+
+static struct irq_chip nwl_irq_chip = {
+	.name = "Xilinx MSI",
+	.irq_compose_msi_msg = nwl_compose_msi_msg,
+	.irq_set_affinity = nwl_msi_set_affinity,
+};
+
+static int nwl_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				unsigned int nr_irqs, void *args)
+{
+	struct nwl_pcie *pcie = domain->host_data;
+	struct nwl_msi *msi = &pcie->msi;
+	int bit;
+	int i;
+
+	mutex_lock(&msi->lock);
+	bit = bitmap_find_next_zero_area(msi->bitmap, INT_PCI_MSI_NR, 0,
+					 nr_irqs, 0);
+	if (bit >= INT_PCI_MSI_NR) {
+		mutex_unlock(&msi->lock);
+		return -ENOSPC;
+	}
+
+	bitmap_set(msi->bitmap, bit, nr_irqs);
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_domain_set_info(domain, virq + i, bit + i, &nwl_irq_chip,
+				domain->host_data, handle_simple_irq,
+				NULL, NULL);
+	}
+	mutex_unlock(&msi->lock);
+	return 0;
+}
+
+static void nwl_irq_domain_free(struct irq_domain *domain, unsigned int virq,
+					unsigned int nr_irqs)
+{
+	struct irq_data *data = irq_domain_get_irq_data(domain, virq);
+	struct nwl_pcie *pcie = irq_data_get_irq_chip_data(data);
+	struct nwl_msi *msi = &pcie->msi;
+
+	mutex_lock(&msi->lock);
+	bitmap_clear(msi->bitmap, data->hwirq, nr_irqs);
+	mutex_unlock(&msi->lock);
+}
+
+static const struct irq_domain_ops dev_msi_domain_ops = {
+	.alloc  = nwl_irq_domain_alloc,
+	.free   = nwl_irq_domain_free,
+};
+
+static void nwl_msi_free_irq_domain(struct nwl_pcie *pcie)
+{
+	struct nwl_msi *msi = &pcie->msi;
+
+	if (msi->irq_msi0)
+		irq_set_chained_handler_and_data(msi->irq_msi0, NULL, NULL);
+	if (msi->irq_msi1)
+		irq_set_chained_handler_and_data(msi->irq_msi1, NULL, NULL);
+
+	if (msi->msi_domain)
+		irq_domain_remove(msi->msi_domain);
+	if (msi->dev_domain)
+		irq_domain_remove(msi->dev_domain);
+
+	kfree(msi->bitmap);
+	msi->bitmap = NULL;
+}
+
+static void nwl_pcie_free_irq_domain(struct nwl_pcie *pcie)
+{
+	int i;
+	u32 irq;
+
+	for (i = 0; i < INTX_NUM; i++) {
+		irq = irq_find_mapping(pcie->legacy_irq_domain, i + 1);
+		if (irq > 0)
+			irq_dispose_mapping(irq);
+	}
+	if (pcie->legacy_irq_domain)
+		irq_domain_remove(pcie->legacy_irq_domain);
+
+	nwl_msi_free_irq_domain(pcie);
+}
+
+static int nwl_pcie_init_msi_irq_domain(struct nwl_pcie *pcie)
+{
+#ifdef CONFIG_PCI_MSI
+	struct fwnode_handle *fwnode = of_node_to_fwnode(pcie->dev->of_node);
+	struct nwl_msi *msi = &pcie->msi;
+
+	msi->dev_domain = irq_domain_add_linear(NULL, INT_PCI_MSI_NR,
+						&dev_msi_domain_ops, pcie);
+	if (!msi->dev_domain) {
+		dev_err(pcie->dev, "failed to create dev IRQ domain\n");
+		return -ENOMEM;
+	}
+	msi->msi_domain = pci_msi_create_irq_domain(fwnode,
+						    &nwl_msi_domain_info,
+						    msi->dev_domain);
+	if (!msi->msi_domain) {
+		dev_err(pcie->dev, "failed to create msi IRQ domain\n");
+		irq_domain_remove(msi->dev_domain);
+		return -ENOMEM;
+	}
+#endif
+	return 0;
+}
+
+static int nwl_pcie_init_irq_domain(struct nwl_pcie *pcie)
+{
+	struct device_node *node = pcie->dev->of_node;
+	struct device_node *legacy_intc_node;
+
+	legacy_intc_node = of_get_next_child(node, NULL);
+	if (!legacy_intc_node) {
+		dev_err(pcie->dev, "No legacy intc node found\n");
+		return -EINVAL;
+	}
+
+	pcie->legacy_irq_domain = irq_domain_add_linear(legacy_intc_node,
+							INTX_NUM,
+							&legacy_domain_ops,
+							pcie);
+
+	if (!pcie->legacy_irq_domain) {
+		dev_err(pcie->dev, "failed to create IRQ domain\n");
+		return -ENOMEM;
+	}
+
+	nwl_pcie_init_msi_irq_domain(pcie);
+	return 0;
+}
+
+static int nwl_pcie_enable_msi(struct nwl_pcie *pcie, struct pci_bus *bus)
+{
+	struct platform_device *pdev = to_platform_device(pcie->dev);
+	struct nwl_msi *msi = &pcie->msi;
+	unsigned long base;
+	int ret;
+	int size = BITS_TO_LONGS(INT_PCI_MSI_NR) * sizeof(long);
+
+	mutex_init(&msi->lock);
+
+	msi->bitmap = kzalloc(size, GFP_KERNEL);
+	if (!msi->bitmap)
+		return -ENOMEM;
+
+	/* Get msi_1 IRQ number */
+	msi->irq_msi1 = platform_get_irq_byname(pdev, "msi1");
+	if (msi->irq_msi1 < 0) {
+		dev_err(&pdev->dev, "failed to get IRQ#%d\n", msi->irq_msi1);
+		ret = -EINVAL;
+		goto err;
+	}
+
+	irq_set_chained_handler_and_data(msi->irq_msi1,
+					 nwl_pcie_msi_handler_high, pcie);
+
+	/* Get msi_0 IRQ number */
+	msi->irq_msi0 = platform_get_irq_byname(pdev, "msi0");
+	if (msi->irq_msi0 < 0) {
+		dev_err(&pdev->dev, "failed to get IRQ#%d\n", msi->irq_msi0);
+		ret = -EINVAL;
+		goto err;
+	}
+
+	irq_set_chained_handler_and_data(msi->irq_msi0,
+					 nwl_pcie_msi_handler_low, pcie);
+
+	/* Check for msii_present bit */
+	ret = nwl_bridge_readl(pcie, I_MSII_CAPABILITIES) & MSII_PRESENT;
+	if (!ret) {
+		dev_err(pcie->dev, "MSI not present\n");
+		ret = -EIO;
+		goto err;
+	}
+
+	/* Enable MSII */
+	nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, I_MSII_CONTROL) |
+			  MSII_ENABLE, I_MSII_CONTROL);
+
+	/* Enable MSII status */
+	nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, I_MSII_CONTROL) |
+			  MSII_STATUS_ENABLE, I_MSII_CONTROL);
+
+	/* setup AFI/FPCI range */
+	base = pcie->phys_pcie_reg_base;
+	nwl_bridge_writel(pcie, lower_32_bits(base), I_MSII_BASE_LO);
+	nwl_bridge_writel(pcie, upper_32_bits(base), I_MSII_BASE_HI);
+
+	/*
+	 * For high range MSI interrupts: disable, clear any pending,
+	 * and enable
+	 */
+	nwl_bridge_writel(pcie, (u32)~MSGF_MSI_SR_HI_MASK, MSGF_MSI_MASK_HI);
+
+	nwl_bridge_writel(pcie, nwl_bridge_readl(pcie,  MSGF_MSI_STATUS_HI) &
+			  MSGF_MSI_SR_HI_MASK, MSGF_MSI_STATUS_HI);
+
+	nwl_bridge_writel(pcie, MSGF_MSI_SR_HI_MASK, MSGF_MSI_MASK_HI);
+
+	/*
+	 * For low range MSI interrupts: disable, clear any pending,
+	 * and enable
+	 */
+	nwl_bridge_writel(pcie, (u32)~MSGF_MSI_SR_LO_MASK, MSGF_MSI_MASK_LO);
+
+	nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, MSGF_MSI_STATUS_LO) &
+			  MSGF_MSI_SR_LO_MASK, MSGF_MSI_STATUS_LO);
+
+	nwl_bridge_writel(pcie, MSGF_MSI_SR_LO_MASK, MSGF_MSI_MASK_LO);
+
+	return 0;
+err:
+	kfree(msi->bitmap);
+	msi->bitmap = NULL;
+	return ret;
+}
+
+static int nwl_pcie_bridge_init(struct nwl_pcie *pcie)
+{
+	struct platform_device *pdev = to_platform_device(pcie->dev);
+	u32 breg_val, ecam_val, first_busno = 0;
+	int err;
+
+	breg_val = nwl_bridge_readl(pcie, E_BREG_CAPABILITIES) & BREG_PRESENT;
+	if (!breg_val) {
+		dev_err(pcie->dev, "BREG is not present\n");
+		return breg_val;
+	}
+
+	/* Write bridge_off to breg base */
+	nwl_bridge_writel(pcie, lower_32_bits(pcie->phys_breg_base),
+			  E_BREG_BASE_LO);
+	nwl_bridge_writel(pcie, upper_32_bits(pcie->phys_breg_base),
+			  E_BREG_BASE_HI);
+
+	/* Enable BREG */
+	nwl_bridge_writel(pcie, ~BREG_ENABLE_FORCE & BREG_ENABLE,
+			  E_BREG_CONTROL);
+
+	/* Disable DMA channel registers */
+	nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, BRCFG_PCIE_RX0) |
+			  CFG_DMA_REG_BAR, BRCFG_PCIE_RX0);
+
+	/* Enable Ingress subtractive decode translation */
+	nwl_bridge_writel(pcie, SET_ISUB_CONTROL, I_ISUB_CONTROL);
+
+	/* Enable msg filtering details */
+	nwl_bridge_writel(pcie, CFG_ENABLE_MSG_FILTER_MASK,
+			  BRCFG_PCIE_RX_MSG_FILTER);
+
+	err = nwl_wait_for_link(pcie);
+	if (err)
+		return err;
+
+	ecam_val = nwl_bridge_readl(pcie, E_ECAM_CAPABILITIES) & E_ECAM_PRESENT;
+	if (!ecam_val) {
+		dev_err(pcie->dev, "ECAM is not present\n");
+		return ecam_val;
+	}
+
+	/* Enable ECAM */
+	nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, E_ECAM_CONTROL) |
+			  E_ECAM_CR_ENABLE, E_ECAM_CONTROL);
+
+	nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, E_ECAM_CONTROL) |
+			  (pcie->ecam_value << E_ECAM_SIZE_SHIFT),
+			  E_ECAM_CONTROL);
+
+	nwl_bridge_writel(pcie, lower_32_bits(pcie->phys_ecam_base),
+			  E_ECAM_BASE_LO);
+	nwl_bridge_writel(pcie, upper_32_bits(pcie->phys_ecam_base),
+			  E_ECAM_BASE_HI);
+
+	/* Get bus range */
+	ecam_val = nwl_bridge_readl(pcie, E_ECAM_CONTROL);
+	pcie->last_busno = (ecam_val & E_ECAM_SIZE_LOC) >> E_ECAM_SIZE_SHIFT;
+	/* Write primary, secondary and subordinate bus numbers */
+	ecam_val = first_busno;
+	ecam_val |= (first_busno + 1) << 8;
+	ecam_val |= (pcie->last_busno << E_ECAM_SIZE_SHIFT);
+	writel(ecam_val, (pcie->ecam_base + PCI_PRIMARY_BUS));
+
+	if (nwl_pcie_link_up(pcie))
+		dev_info(pcie->dev, "Link is UP\n");
+	else
+		dev_info(pcie->dev, "Link is DOWN\n");
+
+	/* Get misc IRQ number */
+	pcie->irq_misc = platform_get_irq_byname(pdev, "misc");
+	if (pcie->irq_misc < 0) {
+		dev_err(&pdev->dev, "failed to get misc IRQ %d\n",
+			pcie->irq_misc);
+		return -EINVAL;
+	}
+
+	err = devm_request_irq(pcie->dev, pcie->irq_misc,
+			       nwl_pcie_misc_handler, IRQF_SHARED,
+			       "nwl_pcie:misc", pcie);
+	if (err) {
+		dev_err(pcie->dev, "fail to register misc IRQ#%d\n",
+			pcie->irq_misc);
+		return err;
+	}
+
+	/* Disable all misc interrupts */
+	nwl_bridge_writel(pcie, (u32)~MSGF_MISC_SR_MASKALL, MSGF_MISC_MASK);
+
+	/* Clear pending misc interrupts */
+	nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, MSGF_MISC_STATUS) &
+			  MSGF_MISC_SR_MASKALL, MSGF_MISC_STATUS);
+
+	/* Enable all misc interrupts */
+	nwl_bridge_writel(pcie, MSGF_MISC_SR_MASKALL, MSGF_MISC_MASK);
+
+
+	/* Disable all legacy interrupts */
+	nwl_bridge_writel(pcie, (u32)~MSGF_LEG_SR_MASKALL, MSGF_LEG_MASK);
+
+	/* Clear pending legacy interrupts */
+	nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, MSGF_LEG_STATUS) &
+			  MSGF_LEG_SR_MASKALL, MSGF_LEG_STATUS);
+
+	/* Enable all legacy interrupts */
+	nwl_bridge_writel(pcie, MSGF_LEG_SR_MASKALL, MSGF_LEG_MASK);
+
+	/* Enable the bridge config interrupt */
+	nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, BRCFG_INTERRUPT) |
+			  BRCFG_INTERRUPT_MASK, BRCFG_INTERRUPT);
+
+	return 0;
+}
+
+static int nwl_pcie_parse_dt(struct nwl_pcie *pcie,
+			     struct platform_device *pdev)
+{
+	struct device_node *node = pcie->dev->of_node;
+	struct resource *res;
+	const char *type;
+
+	/* Check for device type */
+	type = of_get_property(node, "device_type", NULL);
+	if (!type || strcmp(type, "pci")) {
+		dev_err(pcie->dev, "invalid \"device_type\" %s\n", type);
+		return -EINVAL;
+	}
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "breg");
+	pcie->breg_base = devm_ioremap_resource(pcie->dev, res);
+	if (IS_ERR(pcie->breg_base))
+		return PTR_ERR(pcie->breg_base);
+	pcie->phys_breg_base = res->start;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "pcireg");
+	pcie->pcireg_base = devm_ioremap_resource(pcie->dev, res);
+	if (IS_ERR(pcie->pcireg_base))
+		return PTR_ERR(pcie->pcireg_base);
+	pcie->phys_pcie_reg_base = res->start;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cfg");
+	pcie->ecam_base = devm_ioremap_resource(pcie->dev, res);
+	if (IS_ERR(pcie->ecam_base))
+		return PTR_ERR(pcie->ecam_base);
+	pcie->phys_ecam_base = res->start;
+
+	/* Get intx IRQ number */
+	pcie->irq_intx = platform_get_irq_byname(pdev, "intx");
+	if (pcie->irq_intx < 0) {
+		dev_err(&pdev->dev, "failed to get intx IRQ %d\n",
+			pcie->irq_intx);
+		return -EINVAL;
+	}
+
+	irq_set_chained_handler_and_data(pcie->irq_intx,
+					 nwl_pcie_leg_handler, pcie);
+
+	return 0;
+}
+
+static const struct of_device_id nwl_pcie_of_match[] = {
+	{ .compatible = "xlnx,nwl-pcie-2.11", },
+	{}
+};
+
+static int nwl_pcie_probe(struct platform_device *pdev)
+{
+	struct device_node *node = pdev->dev.of_node;
+	struct nwl_pcie *pcie;
+	struct pci_bus *bus;
+	struct pci_bus *child;
+	int err;
+	resource_size_t iobase = 0;
+	LIST_HEAD(res);
+
+	pcie = devm_kzalloc(&pdev->dev, sizeof(*pcie), GFP_KERNEL);
+	if (!pcie)
+		return -ENOMEM;
+
+	pcie->dev = &pdev->dev;
+	pcie->ecam_value = NWL_ECAM_VALUE_DEFAULT;
+
+	err = nwl_pcie_parse_dt(pcie, pdev);
+	if (err) {
+		dev_err(pcie->dev, "Parsing DT failed\n");
+		return err;
+	}
+
+	err = nwl_pcie_bridge_init(pcie);
+	if (err) {
+		dev_err(pcie->dev, "HW Initalization failed\n");
+		return err;
+	}
+
+	err = of_pci_get_host_bridge_resources(node, 0, 0xff, &res, &iobase);
+	if (err) {
+		pr_err("Getting bridge resources failed\n");
+		return err;
+	}
+
+	err = nwl_pcie_init_irq_domain(pcie);
+	if (err) {
+		dev_err(pcie->dev, "Failed creating IRQ Domain\n");
+		return err;
+	}
+
+	bus = pci_create_root_bus(&pdev->dev, pcie->root_busno,
+				  &nwl_pcie_ops, pcie, &res);
+	if (!bus)
+		return -ENOMEM;
+
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+		err = nwl_pcie_enable_msi(pcie, bus);
+		if (err < 0) {
+			dev_err(&pdev->dev,
+				"failed to enable MSI support: %d\n", err);
+			return err;
+		}
+	}
+	pci_scan_child_bus(bus);
+	pci_assign_unassigned_bus_resources(bus);
+	list_for_each_entry(child, &bus->children, node)
+		pcie_bus_configure_settings(child);
+	pci_bus_add_devices(bus);
+	platform_set_drvdata(pdev, pcie);
+	return 0;
+}
+
+static int nwl_pcie_remove(struct platform_device *pdev)
+{
+	struct nwl_pcie *pcie = platform_get_drvdata(pdev);
+
+	nwl_pcie_free_irq_domain(pcie);
+	platform_set_drvdata(pdev, NULL);
+	return 0;
+}
+
+static struct platform_driver nwl_pcie_driver = {
+	.driver = {
+		.name = "nwl-pcie",
+		.of_match_table = nwl_pcie_of_match,
+	},
+	.probe = nwl_pcie_probe,
+	.remove = nwl_pcie_remove,
+};
+module_platform_driver(nwl_pcie_driver);
+
+MODULE_AUTHOR("Xilinx, Inc");
+MODULE_DESCRIPTION("NWL PCIe driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/pci/host/pcie-xilinx.c b/drivers/pci/host/pcie-xilinx.c
index 4cfa46360d12..65f0fe0c2eaf 100644
--- a/drivers/pci/host/pcie-xilinx.c
+++ b/drivers/pci/host/pcie-xilinx.c
@@ -94,9 +94,6 @@
 /* Number of MSI IRQs */
 #define XILINX_NUM_MSI_IRQS		128
 
-/* Number of Memory Resources */
-#define XILINX_MAX_NUM_RESOURCES	3
-
 /**
  * struct xilinx_pcie_port - PCIe port information
  * @reg_base: IO Mapped Register Base
@@ -105,7 +102,6 @@
  * @root_busno: Root Bus number
  * @dev: Device pointer
  * @irq_domain: IRQ domain pointer
- * @bus_range: Bus range
  * @resources: Bus Resources
  */
 struct xilinx_pcie_port {
@@ -115,17 +111,11 @@ struct xilinx_pcie_port {
 	u8 root_busno;
 	struct device *dev;
 	struct irq_domain *irq_domain;
-	struct resource bus_range;
 	struct list_head resources;
 };
 
 static DECLARE_BITMAP(msi_irq_in_use, XILINX_NUM_MSI_IRQS);
 
-static inline struct xilinx_pcie_port *sys_to_pcie(struct pci_sys_data *sys)
-{
-	return sys->private_data;
-}
-
 static inline u32 pcie_read(struct xilinx_pcie_port *port, u32 reg)
 {
 	return readl(port->reg_base + reg);
@@ -167,7 +157,7 @@ static void xilinx_pcie_clear_err_interrupts(struct xilinx_pcie_port *port)
  */
 static bool xilinx_pcie_valid_device(struct pci_bus *bus, unsigned int devfn)
 {
-	struct xilinx_pcie_port *port = sys_to_pcie(bus->sysdata);
+	struct xilinx_pcie_port *port = bus->sysdata;
 
 	/* Check if link is up when trying to access downstream ports */
 	if (bus->number != port->root_busno)
@@ -200,7 +190,7 @@ static bool xilinx_pcie_valid_device(struct pci_bus *bus, unsigned int devfn)
 static void __iomem *xilinx_pcie_map_bus(struct pci_bus *bus,
 					 unsigned int devfn, int where)
 {
-	struct xilinx_pcie_port *port = sys_to_pcie(bus->sysdata);
+	struct xilinx_pcie_port *port = bus->sysdata;
 	int relbus;
 
 	if (!xilinx_pcie_valid_device(bus, devfn))
@@ -232,7 +222,7 @@ static void xilinx_pcie_destroy_msi(unsigned int irq)
 
 	if (!test_bit(irq, msi_irq_in_use)) {
 		msi = irq_get_msi_desc(irq);
-		port = sys_to_pcie(msi_desc_to_pci_sysdata(msi));
+		port = msi_desc_to_pci_sysdata(msi);
 		dev_err(port->dev, "Trying to free unused MSI#%d\n", irq);
 	} else {
 		clear_bit(irq, msi_irq_in_use);
@@ -281,7 +271,7 @@ static int xilinx_pcie_msi_setup_irq(struct msi_controller *chip,
 				     struct pci_dev *pdev,
 				     struct msi_desc *desc)
 {
-	struct xilinx_pcie_port *port = sys_to_pcie(pdev->bus->sysdata);
+	struct xilinx_pcie_port *port = pdev->bus->sysdata;
 	unsigned int irq;
 	int hwirq;
 	struct msi_msg msg;
@@ -618,138 +608,6 @@ static void xilinx_pcie_init_port(struct xilinx_pcie_port *port)
 }
 
 /**
- * xilinx_pcie_setup - Setup memory resources
- * @nr: Bus number
- * @sys: Per controller structure
- *
- * Return: '1' on success and error value on failure
- */
-static int xilinx_pcie_setup(int nr, struct pci_sys_data *sys)
-{
-	struct xilinx_pcie_port *port = sys_to_pcie(sys);
-
-	list_splice_init(&port->resources, &sys->resources);
-
-	return 1;
-}
-
-/**
- * xilinx_pcie_scan_bus - Scan PCIe bus for devices
- * @nr: Bus number
- * @sys: Per controller structure
- *
- * Return: Valid Bus pointer on success and NULL on failure
- */
-static struct pci_bus *xilinx_pcie_scan_bus(int nr, struct pci_sys_data *sys)
-{
-	struct xilinx_pcie_port *port = sys_to_pcie(sys);
-	struct pci_bus *bus;
-
-	port->root_busno = sys->busnr;
-
-	if (IS_ENABLED(CONFIG_PCI_MSI))
-		bus = pci_scan_root_bus_msi(port->dev, sys->busnr,
-					    &xilinx_pcie_ops, sys,
-					    &sys->resources,
-					    &xilinx_pcie_msi_chip);
-	else
-		bus = pci_scan_root_bus(port->dev, sys->busnr,
-					&xilinx_pcie_ops, sys, &sys->resources);
-	return bus;
-}
-
-/**
- * xilinx_pcie_parse_and_add_res - Add resources by parsing ranges
- * @port: PCIe port information
- *
- * Return: '0' on success and error value on failure
- */
-static int xilinx_pcie_parse_and_add_res(struct xilinx_pcie_port *port)
-{
-	struct device *dev = port->dev;
-	struct device_node *node = dev->of_node;
-	struct resource *mem;
-	resource_size_t offset;
-	struct of_pci_range_parser parser;
-	struct of_pci_range range;
-	struct resource_entry *win;
-	int err = 0, mem_resno = 0;
-
-	/* Get the ranges */
-	if (of_pci_range_parser_init(&parser, node)) {
-		dev_err(dev, "missing \"ranges\" property\n");
-		return -EINVAL;
-	}
-
-	/* Parse the ranges and add the resources found to the list */
-	for_each_of_pci_range(&parser, &range) {
-
-		if (mem_resno >= XILINX_MAX_NUM_RESOURCES) {
-			dev_err(dev, "Maximum memory resources exceeded\n");
-			return -EINVAL;
-		}
-
-		mem = devm_kmalloc(dev, sizeof(*mem), GFP_KERNEL);
-		if (!mem) {
-			err = -ENOMEM;
-			goto free_resources;
-		}
-
-		of_pci_range_to_resource(&range, node, mem);
-
-		switch (mem->flags & IORESOURCE_TYPE_BITS) {
-		case IORESOURCE_MEM:
-			offset = range.cpu_addr - range.pci_addr;
-			mem_resno++;
-			break;
-		default:
-			err = -EINVAL;
-			break;
-		}
-
-		if (err < 0) {
-			dev_warn(dev, "Invalid resource found %pR\n", mem);
-			continue;
-		}
-
-		err = request_resource(&iomem_resource, mem);
-		if (err)
-			goto free_resources;
-
-		pci_add_resource_offset(&port->resources, mem, offset);
-	}
-
-	/* Get the bus range */
-	if (of_pci_parse_bus_range(node, &port->bus_range)) {
-		u32 val = pcie_read(port, XILINX_PCIE_REG_BIR);
-		u8 last;
-
-		last = (val & XILINX_PCIE_BIR_ECAM_SZ_MASK) >>
-			XILINX_PCIE_BIR_ECAM_SZ_SHIFT;
-
-		port->bus_range = (struct resource) {
-			.name	= node->name,
-			.start	= 0,
-			.end	= last,
-			.flags	= IORESOURCE_BUS,
-		};
-	}
-
-	/* Register bus resource */
-	pci_add_resource(&port->resources, &port->bus_range);
-
-	return 0;
-
-free_resources:
-	release_child_resources(&iomem_resource);
-	resource_list_for_each_entry(win, &port->resources)
-		devm_kfree(dev, win->res);
-	pci_free_resource_list(&port->resources);
-
-	return err;
-}
-
-/**
  * xilinx_pcie_parse_dt - Parse Device tree
  * @port: PCIe port information
  *
@@ -800,9 +658,12 @@ static int xilinx_pcie_parse_dt(struct xilinx_pcie_port *port)
 static int xilinx_pcie_probe(struct platform_device *pdev)
 {
 	struct xilinx_pcie_port *port;
-	struct hw_pci hw;
 	struct device *dev = &pdev->dev;
+	struct pci_bus *bus;
+
 	int err;
+	resource_size_t iobase = 0;
+	LIST_HEAD(res);
 
 	if (!dev->of_node)
 		return -ENODEV;
@@ -827,34 +688,28 @@ static int xilinx_pcie_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	/*
-	 * Parse PCI ranges, configuration bus range and
-	 * request their resources
-	 */
-	INIT_LIST_HEAD(&port->resources);
-	err = xilinx_pcie_parse_and_add_res(port);
+	err = of_pci_get_host_bridge_resources(dev->of_node, 0, 0xff, &res,
+					       &iobase);
 	if (err) {
-		dev_err(dev, "Failed adding resources\n");
+		dev_err(dev, "Getting bridge resources failed\n");
 		return err;
 	}
-
-	platform_set_drvdata(pdev, port);
-
-	/* Register the device */
-	memset(&hw, 0, sizeof(hw));
-	hw = (struct hw_pci) {
-		.nr_controllers	= 1,
-		.private_data	= (void **)&port,
-		.setup		= xilinx_pcie_setup,
-		.map_irq	= of_irq_parse_and_map_pci,
-		.scan		= xilinx_pcie_scan_bus,
-		.ops		= &xilinx_pcie_ops,
-	};
+	bus = pci_create_root_bus(&pdev->dev, 0,
+				  &xilinx_pcie_ops, port, &res);
+	if (!bus)
+		return -ENOMEM;
 
 #ifdef CONFIG_PCI_MSI
 	xilinx_pcie_msi_chip.dev = port->dev;
+	bus->msi = &xilinx_pcie_msi_chip;
 #endif
-	pci_common_init_dev(dev, &hw);
+	pci_scan_child_bus(bus);
+	pci_assign_unassigned_bus_resources(bus);
+#ifndef CONFIG_MICROBLAZE
+	pci_fixup_irqs(pci_common_swizzle, of_irq_parse_and_map_pci);
+#endif
+	pci_bus_add_devices(bus);
+	platform_set_drvdata(pdev, port);
 
 	return 0;
 }
diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c
index eb5efaef06ea..50b8b7d54416 100644
--- a/drivers/pci/hotplug/s390_pci_hpc.c
+++ b/drivers/pci/hotplug/s390_pci_hpc.c
@@ -93,13 +93,17 @@ out_deconfigure:
 static int disable_slot(struct hotplug_slot *hotplug_slot)
 {
 	struct slot *slot = hotplug_slot->private;
+	struct pci_dev *pdev;
 	int rc;
 
 	if (!zpci_fn_configured(slot->zdev->state))
 		return -EIO;
 
-	if (slot->zdev->pdev)
-		pci_stop_and_remove_bus_device_locked(slot->zdev->pdev);
+	pdev = pci_get_slot(slot->zdev->bus, ZPCI_DEVFN);
+	if (pdev) {
+		pci_stop_and_remove_bus_device_locked(pdev);
+		pci_dev_put(pdev);
+	}
 
 	rc = zpci_disable_device(slot->zdev);
 	if (rc)
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 31f31d460fc9..fe4bd0aa91a6 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -387,10 +387,6 @@ static int sriov_init(struct pci_dev *dev, int pos)
 	struct resource *res;
 	struct pci_dev *pdev;
 
-	if (pci_pcie_type(dev) != PCI_EXP_TYPE_RC_END &&
-	    pci_pcie_type(dev) != PCI_EXP_TYPE_ENDPOINT)
-		return -ENODEV;
-
 	pci_read_config_word(dev, pos + PCI_SRIOV_CTRL, &ctrl);
 	if (ctrl & PCI_SRIOV_CTRL_VFE) {
 		pci_write_config_word(dev, pos + PCI_SRIOV_CTRL, 0);
diff --git a/drivers/pci/pci-label.c b/drivers/pci/pci-label.c
index 0ae74d96ed85..51357377efbc 100644
--- a/drivers/pci/pci-label.c
+++ b/drivers/pci/pci-label.c
@@ -16,7 +16,7 @@
  * the instance number and string from the type 41 record and exports
  * it to sysfs.
  *
- * Please see http://linux.dell.com/wiki/index.php/Oss/libnetdevname for more
+ * Please see http://linux.dell.com/files/biosdevname/ for more
  * information.
  */
 
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 95d9e7bd933b..e982010f0ed1 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -769,10 +769,12 @@ static ssize_t read_vpd_attr(struct file *filp, struct kobject *kobj,
 {
 	struct pci_dev *dev = to_pci_dev(kobj_to_dev(kobj));
 
-	if (off > bin_attr->size)
-		count = 0;
-	else if (count > bin_attr->size - off)
-		count = bin_attr->size - off;
+	if (bin_attr->size > 0) {
+		if (off > bin_attr->size)
+			count = 0;
+		else if (count > bin_attr->size - off)
+			count = bin_attr->size - off;
+	}
 
 	return pci_read_vpd(dev, off, count, buf);
 }
@@ -783,10 +785,12 @@ static ssize_t write_vpd_attr(struct file *filp, struct kobject *kobj,
 {
 	struct pci_dev *dev = to_pci_dev(kobj_to_dev(kobj));
 
-	if (off > bin_attr->size)
-		count = 0;
-	else if (count > bin_attr->size - off)
-		count = bin_attr->size - off;
+	if (bin_attr->size > 0) {
+		if (off > bin_attr->size)
+			count = 0;
+		else if (count > bin_attr->size - off)
+			count = bin_attr->size - off;
+	}
 
 	return pci_write_vpd(dev, off, count, buf);
 }
@@ -1134,33 +1138,36 @@ static int pci_create_attr(struct pci_dev *pdev, int num, int write_combine)
 	/* allocate attribute structure, piggyback attribute name */
 	int name_len = write_combine ? 13 : 10;
 	struct bin_attribute *res_attr;
+	char *res_attr_name;
 	int retval;
 
 	res_attr = kzalloc(sizeof(*res_attr) + name_len, GFP_ATOMIC);
-	if (res_attr) {
-		char *res_attr_name = (char *)(res_attr + 1);
-
-		sysfs_bin_attr_init(res_attr);
-		if (write_combine) {
-			pdev->res_attr_wc[num] = res_attr;
-			sprintf(res_attr_name, "resource%d_wc", num);
-			res_attr->mmap = pci_mmap_resource_wc;
-		} else {
-			pdev->res_attr[num] = res_attr;
-			sprintf(res_attr_name, "resource%d", num);
-			res_attr->mmap = pci_mmap_resource_uc;
-		}
-		if (pci_resource_flags(pdev, num) & IORESOURCE_IO) {
-			res_attr->read = pci_read_resource_io;
-			res_attr->write = pci_write_resource_io;
-		}
-		res_attr->attr.name = res_attr_name;
-		res_attr->attr.mode = S_IRUSR | S_IWUSR;
-		res_attr->size = pci_resource_len(pdev, num);
-		res_attr->private = &pdev->resource[num];
-		retval = sysfs_create_bin_file(&pdev->dev.kobj, res_attr);
-	} else
-		retval = -ENOMEM;
+	if (!res_attr)
+		return -ENOMEM;
+
+	res_attr_name = (char *)(res_attr + 1);
+
+	sysfs_bin_attr_init(res_attr);
+	if (write_combine) {
+		pdev->res_attr_wc[num] = res_attr;
+		sprintf(res_attr_name, "resource%d_wc", num);
+		res_attr->mmap = pci_mmap_resource_wc;
+	} else {
+		pdev->res_attr[num] = res_attr;
+		sprintf(res_attr_name, "resource%d", num);
+		res_attr->mmap = pci_mmap_resource_uc;
+	}
+	if (pci_resource_flags(pdev, num) & IORESOURCE_IO) {
+		res_attr->read = pci_read_resource_io;
+		res_attr->write = pci_write_resource_io;
+	}
+	res_attr->attr.name = res_attr_name;
+	res_attr->attr.mode = S_IRUSR | S_IWUSR;
+	res_attr->size = pci_resource_len(pdev, num);
+	res_attr->private = &pdev->resource[num];
+	retval = sysfs_create_bin_file(&pdev->dev.kobj, res_attr);
+	if (retval)
+		kfree(res_attr);
 
 	return retval;
 }
@@ -1319,7 +1326,7 @@ static int pci_create_capabilities_sysfs(struct pci_dev *dev)
 			return -ENOMEM;
 
 		sysfs_bin_attr_init(attr);
-		attr->size = dev->vpd->len;
+		attr->size = 0;
 		attr->attr.name = "vpd";
 		attr->attr.mode = S_IRUSR | S_IWUSR;
 		attr->read = read_vpd_attr;
@@ -1356,7 +1363,7 @@ error:
 int __must_check pci_create_sysfs_dev_files(struct pci_dev *pdev)
 {
 	int retval;
-	int rom_size = 0;
+	int rom_size;
 	struct bin_attribute *attr;
 
 	if (!sysfs_initialized)
@@ -1373,12 +1380,8 @@ int __must_check pci_create_sysfs_dev_files(struct pci_dev *pdev)
 	if (retval)
 		goto err_config_file;
 
-	if (pci_resource_len(pdev, PCI_ROM_RESOURCE))
-		rom_size = pci_resource_len(pdev, PCI_ROM_RESOURCE);
-	else if (pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW)
-		rom_size = 0x20000;
-
 	/* If the device has a ROM, try to expose it in sysfs. */
+	rom_size = pci_resource_len(pdev, PCI_ROM_RESOURCE);
 	if (rom_size) {
 		attr = kzalloc(sizeof(*attr), GFP_ATOMIC);
 		if (!attr) {
@@ -1409,7 +1412,7 @@ int __must_check pci_create_sysfs_dev_files(struct pci_dev *pdev)
 	return 0;
 
 err_rom_file:
-	if (rom_size) {
+	if (pdev->rom_attr) {
 		sysfs_remove_bin_file(&pdev->dev.kobj, pdev->rom_attr);
 		kfree(pdev->rom_attr);
 		pdev->rom_attr = NULL;
@@ -1447,8 +1450,6 @@ static void pci_remove_capabilities_sysfs(struct pci_dev *dev)
  */
 void pci_remove_sysfs_dev_files(struct pci_dev *pdev)
 {
-	int rom_size = 0;
-
 	if (!sysfs_initialized)
 		return;
 
@@ -1461,18 +1462,13 @@ void pci_remove_sysfs_dev_files(struct pci_dev *pdev)
 
 	pci_remove_resource_files(pdev);
 
-	if (pci_resource_len(pdev, PCI_ROM_RESOURCE))
-		rom_size = pci_resource_len(pdev, PCI_ROM_RESOURCE);
-	else if (pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW)
-		rom_size = 0x20000;
-
-	if (rom_size && pdev->rom_attr) {
+	if (pdev->rom_attr) {
 		sysfs_remove_bin_file(&pdev->dev.kobj, pdev->rom_attr);
 		kfree(pdev->rom_attr);
+		pdev->rom_attr = NULL;
 	}
 
 	pci_remove_firmware_label_files(pdev);
-
 }
 
 static int __init pci_sysfs_init(void)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 602eb4223510..25e0327d4429 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -25,7 +25,6 @@
 #include <linux/device.h>
 #include <linux/pm_runtime.h>
 #include <linux/pci_hotplug.h>
-#include <asm-generic/pci-bridge.h>
 #include <asm/setup.h>
 #include <linux/aer.h>
 #include "pci.h"
@@ -3386,18 +3385,6 @@ bool pci_check_and_unmask_intx(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(pci_check_and_unmask_intx);
 
-int pci_set_dma_max_seg_size(struct pci_dev *dev, unsigned int size)
-{
-	return dma_set_max_seg_size(&dev->dev, size);
-}
-EXPORT_SYMBOL(pci_set_dma_max_seg_size);
-
-int pci_set_dma_seg_boundary(struct pci_dev *dev, unsigned long mask)
-{
-	return dma_set_seg_boundary(&dev->dev, mask);
-}
-EXPORT_SYMBOL(pci_set_dma_seg_boundary);
-
 /**
  * pci_wait_for_pending_transaction - waits for pending transaction
  * @dev: the PCI device to operate on
@@ -3414,6 +3401,29 @@ int pci_wait_for_pending_transaction(struct pci_dev *dev)
 }
 EXPORT_SYMBOL(pci_wait_for_pending_transaction);
 
+/*
+ * We should only need to wait 100ms after FLR, but some devices take longer.
+ * Wait for up to 1000ms for config space to return something other than -1.
+ * Intel IGD requires this when an LCD panel is attached.  We read the 2nd
+ * dword because VFs don't implement the 1st dword.
+ */
+static void pci_flr_wait(struct pci_dev *dev)
+{
+	int i = 0;
+	u32 id;
+
+	do {
+		msleep(100);
+		pci_read_config_dword(dev, PCI_COMMAND, &id);
+	} while (i++ < 10 && id == ~0);
+
+	if (id == ~0)
+		dev_warn(&dev->dev, "Failed to return from FLR\n");
+	else if (i > 1)
+		dev_info(&dev->dev, "Required additional %dms to return from FLR\n",
+			 (i - 1) * 100);
+}
+
 static int pcie_flr(struct pci_dev *dev, int probe)
 {
 	u32 cap;
@@ -3429,7 +3439,7 @@ static int pcie_flr(struct pci_dev *dev, int probe)
 		dev_err(&dev->dev, "timed out waiting for pending transaction; performing function level reset anyway\n");
 
 	pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_BCR_FLR);
-	msleep(100);
+	pci_flr_wait(dev);
 	return 0;
 }
 
@@ -3459,7 +3469,7 @@ static int pci_af_flr(struct pci_dev *dev, int probe)
 		dev_err(&dev->dev, "timed out waiting for pending transaction; performing AF function level reset anyway\n");
 
 	pci_write_config_byte(dev, pos + PCI_AF_CTRL, PCI_AF_CTRL_FLR);
-	msleep(100);
+	pci_flr_wait(dev);
 	return 0;
 }
 
@@ -4772,8 +4782,10 @@ int pci_get_new_domain_nr(void)
 void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent)
 {
 	static int use_dt_domains = -1;
-	int domain = of_get_pci_domain_nr(parent->of_node);
+	int domain = -1;
 
+	if (parent)
+		domain = of_get_pci_domain_nr(parent->of_node);
 	/*
 	 * Check DT domain and use_dt_domains values.
 	 *
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 9a1660f592ef..d0fb93481573 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -97,21 +97,21 @@ static inline bool pci_has_subordinate(struct pci_dev *pci_dev)
 struct pci_vpd_ops {
 	ssize_t (*read)(struct pci_dev *dev, loff_t pos, size_t count, void *buf);
 	ssize_t (*write)(struct pci_dev *dev, loff_t pos, size_t count, const void *buf);
-	void (*release)(struct pci_dev *dev);
 };
 
 struct pci_vpd {
-	unsigned int len;
 	const struct pci_vpd_ops *ops;
 	struct bin_attribute *attr; /* descriptor for sysfs VPD entry */
+	struct mutex	lock;
+	unsigned int	len;
+	u16		flag;
+	u8		cap;
+	u8		busy:1;
+	u8		valid:1;
 };
 
-int pci_vpd_pci22_init(struct pci_dev *dev);
-static inline void pci_vpd_release(struct pci_dev *dev)
-{
-	if (dev->vpd)
-		dev->vpd->ops->release(dev);
-}
+int pci_vpd_init(struct pci_dev *dev);
+void pci_vpd_release(struct pci_dev *dev);
 
 /* PCI /proc functions */
 #ifdef CONFIG_PROC_FS
diff --git a/drivers/pci/pcie/Kconfig b/drivers/pci/pcie/Kconfig
index e294713c8143..72db7f4209ca 100644
--- a/drivers/pci/pcie/Kconfig
+++ b/drivers/pci/pcie/Kconfig
@@ -44,6 +44,7 @@ config PCIEASPM
 	  /sys/module/pcie_aspm/parameters/policy
 
 	  When in doubt, say Y.
+
 config PCIEASPM_DEBUG
 	bool "Debug PCI Express ASPM"
 	depends on PCIEASPM
@@ -58,20 +59,20 @@ choice
 	depends on PCIEASPM
 
 config PCIEASPM_DEFAULT
-        bool "BIOS default"
+	bool "BIOS default"
 	depends on PCIEASPM
 	help
 	  Use the BIOS defaults for PCI Express ASPM.
 
 config PCIEASPM_POWERSAVE
-        bool "Powersave"
+	bool "Powersave"
 	depends on PCIEASPM
 	help
 	  Enable PCI Express ASPM L0s and L1 where possible, even if the
 	  BIOS did not.
 
 config PCIEASPM_PERFORMANCE
-        bool "Performance"
+	bool "Performance"
 	depends on PCIEASPM
 	help
 	  Disable PCI Express ASPM L0s and L1, even if the BIOS enabled them.
diff --git a/drivers/pci/pcie/aer/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c
index 20db790465dd..db553dc22c8e 100644
--- a/drivers/pci/pcie/aer/aer_inject.c
+++ b/drivers/pci/pcie/aer/aer_inject.c
@@ -25,6 +25,7 @@
 #include <linux/fs.h>
 #include <linux/uaccess.h>
 #include <linux/stddef.h>
+#include <linux/device.h>
 #include "aerdrv.h"
 
 /* Override the existing corrected and uncorrected error masks */
@@ -124,16 +125,13 @@ static struct pci_ops *__find_pci_bus_ops(struct pci_bus *bus)
 static struct pci_bus_ops *pci_bus_ops_pop(void)
 {
 	unsigned long flags;
-	struct pci_bus_ops *bus_ops = NULL;
+	struct pci_bus_ops *bus_ops;
 
 	spin_lock_irqsave(&inject_lock, flags);
-	if (list_empty(&pci_bus_ops_list))
-		bus_ops = NULL;
-	else {
-		struct list_head *lh = pci_bus_ops_list.next;
-		list_del(lh);
-		bus_ops = list_entry(lh, struct pci_bus_ops, list);
-	}
+	bus_ops = list_first_entry_or_null(&pci_bus_ops_list,
+					   struct pci_bus_ops, list);
+	if (bus_ops)
+		list_del(&bus_ops->list);
 	spin_unlock_irqrestore(&inject_lock, flags);
 	return bus_ops;
 }
@@ -181,14 +179,16 @@ static u32 *find_pci_config_dword(struct aer_error *err, int where,
 	return target;
 }
 
-static int pci_read_aer(struct pci_bus *bus, unsigned int devfn, int where,
-			int size, u32 *val)
+static int aer_inj_read_config(struct pci_bus *bus, unsigned int devfn,
+			       int where, int size, u32 *val)
 {
 	u32 *sim;
 	struct aer_error *err;
 	unsigned long flags;
 	struct pci_ops *ops;
+	struct pci_ops *my_ops;
 	int domain;
+	int rv;
 
 	spin_lock_irqsave(&inject_lock, flags);
 	if (size != sizeof(u32))
@@ -208,19 +208,32 @@ static int pci_read_aer(struct pci_bus *bus, unsigned int devfn, int where,
 	}
 out:
 	ops = __find_pci_bus_ops(bus);
+	/*
+	 * pci_lock must already be held, so we can directly
+	 * manipulate bus->ops.  Many config access functions,
+	 * including pci_generic_config_read() require the original
+	 * bus->ops be installed to function, so temporarily put them
+	 * back.
+	 */
+	my_ops = bus->ops;
+	bus->ops = ops;
+	rv = ops->read(bus, devfn, where, size, val);
+	bus->ops = my_ops;
 	spin_unlock_irqrestore(&inject_lock, flags);
-	return ops->read(bus, devfn, where, size, val);
+	return rv;
 }
 
-static int pci_write_aer(struct pci_bus *bus, unsigned int devfn, int where,
-			 int size, u32 val)
+static int aer_inj_write_config(struct pci_bus *bus, unsigned int devfn,
+				int where, int size, u32 val)
 {
 	u32 *sim;
 	struct aer_error *err;
 	unsigned long flags;
 	int rw1cs;
 	struct pci_ops *ops;
+	struct pci_ops *my_ops;
 	int domain;
+	int rv;
 
 	spin_lock_irqsave(&inject_lock, flags);
 	if (size != sizeof(u32))
@@ -243,13 +256,24 @@ static int pci_write_aer(struct pci_bus *bus, unsigned int devfn, int where,
 	}
 out:
 	ops = __find_pci_bus_ops(bus);
+	/*
+	 * pci_lock must already be held, so we can directly
+	 * manipulate bus->ops.  Many config access functions,
+	 * including pci_generic_config_write() require the original
+	 * bus->ops be installed to function, so temporarily put them
+	 * back.
+	 */
+	my_ops = bus->ops;
+	bus->ops = ops;
+	rv = ops->write(bus, devfn, where, size, val);
+	bus->ops = my_ops;
 	spin_unlock_irqrestore(&inject_lock, flags);
-	return ops->write(bus, devfn, where, size, val);
+	return rv;
 }
 
-static struct pci_ops pci_ops_aer = {
-	.read = pci_read_aer,
-	.write = pci_write_aer,
+static struct pci_ops aer_inj_pci_ops = {
+	.read = aer_inj_read_config,
+	.write = aer_inj_write_config,
 };
 
 static void pci_bus_ops_init(struct pci_bus_ops *bus_ops,
@@ -270,9 +294,9 @@ static int pci_bus_set_aer_ops(struct pci_bus *bus)
 	bus_ops = kmalloc(sizeof(*bus_ops), GFP_KERNEL);
 	if (!bus_ops)
 		return -ENOMEM;
-	ops = pci_bus_set_ops(bus, &pci_ops_aer);
+	ops = pci_bus_set_ops(bus, &aer_inj_pci_ops);
 	spin_lock_irqsave(&inject_lock, flags);
-	if (ops == &pci_ops_aer)
+	if (ops == &aer_inj_pci_ops)
 		goto out;
 	pci_bus_ops_init(bus_ops, bus, ops);
 	list_add(&bus_ops->list, &pci_bus_ops_list);
@@ -334,13 +358,15 @@ static int aer_inject(struct aer_error_inj *einj)
 		return -ENODEV;
 	rpdev = pcie_find_root_port(dev);
 	if (!rpdev) {
+		dev_err(&dev->dev, "aer_inject: Root port not found\n");
 		ret = -ENODEV;
 		goto out_put;
 	}
 
 	pos_cap_err = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
 	if (!pos_cap_err) {
-		ret = -EPERM;
+		dev_err(&dev->dev, "aer_inject: Device doesn't support AER\n");
+		ret = -EPROTONOSUPPORT;
 		goto out_put;
 	}
 	pci_read_config_dword(dev, pos_cap_err + PCI_ERR_UNCOR_SEVER, &sever);
@@ -350,7 +376,9 @@ static int aer_inject(struct aer_error_inj *einj)
 
 	rp_pos_cap_err = pci_find_ext_capability(rpdev, PCI_EXT_CAP_ID_ERR);
 	if (!rp_pos_cap_err) {
-		ret = -EPERM;
+		dev_err(&rpdev->dev,
+			"aer_inject: Root port doesn't support AER\n");
+		ret = -EPROTONOSUPPORT;
 		goto out_put;
 	}
 
@@ -397,14 +425,16 @@ static int aer_inject(struct aer_error_inj *einj)
 	if (!aer_mask_override && einj->cor_status &&
 	    !(einj->cor_status & ~cor_mask)) {
 		ret = -EINVAL;
-		printk(KERN_WARNING "The correctable error(s) is masked by device\n");
+		dev_warn(&dev->dev,
+			 "aer_inject: The correctable error(s) is masked by device\n");
 		spin_unlock_irqrestore(&inject_lock, flags);
 		goto out_put;
 	}
 	if (!aer_mask_override && einj->uncor_status &&
 	    !(einj->uncor_status & ~uncor_mask)) {
 		ret = -EINVAL;
-		printk(KERN_WARNING "The uncorrectable error(s) is masked by device\n");
+		dev_warn(&dev->dev,
+			 "aer_inject: The uncorrectable error(s) is masked by device\n");
 		spin_unlock_irqrestore(&inject_lock, flags);
 		goto out_put;
 	}
@@ -457,13 +487,19 @@ static int aer_inject(struct aer_error_inj *einj)
 
 	if (find_aer_device(rpdev, &edev)) {
 		if (!get_service_data(edev)) {
-			printk(KERN_WARNING "AER service is not initialized\n");
-			ret = -EINVAL;
+			dev_warn(&edev->device,
+				 "aer_inject: AER service is not initialized\n");
+			ret = -EPROTONOSUPPORT;
 			goto out_put;
 		}
+		dev_info(&edev->device,
+			 "aer_inject: Injecting errors %08x/%08x into device %s\n",
+			 einj->cor_status, einj->uncor_status, pci_name(dev));
 		aer_irq(-1, edev);
-	} else
-		ret = -EINVAL;
+	} else {
+		dev_err(&rpdev->dev, "aer_inject: AER device not found\n");
+		ret = -ENODEV;
+	}
 out_put:
 	kfree(err_alloc);
 	kfree(rperr_alloc);
diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c
index 0bf82a20a0fb..48d21e0edd56 100644
--- a/drivers/pci/pcie/aer/aerdrv.c
+++ b/drivers/pci/pcie/aer/aerdrv.c
@@ -262,7 +262,6 @@ static struct aer_rpc *aer_alloc_rpc(struct pcie_device *dev)
 	rpc->rpd = dev;
 	INIT_WORK(&rpc->dpc_handler, aer_isr);
 	mutex_init(&rpc->rpc_mutex);
-	init_waitqueue_head(&rpc->wait_release);
 
 	/* Use PCIe bus function to store rpc into PCIe device */
 	set_service_data(dev, rpc);
@@ -285,8 +284,7 @@ static void aer_remove(struct pcie_device *dev)
 		if (rpc->isr)
 			free_irq(dev->irq, dev);
 
-		wait_event(rpc->wait_release, rpc->prod_idx == rpc->cons_idx);
-
+		flush_work(&rpc->dpc_handler);
 		aer_disable_rootport(rpc);
 		kfree(rpc);
 		set_service_data(dev, NULL);
diff --git a/drivers/pci/pcie/aer/aerdrv.h b/drivers/pci/pcie/aer/aerdrv.h
index 84420b7c9456..945c939a86c5 100644
--- a/drivers/pci/pcie/aer/aerdrv.h
+++ b/drivers/pci/pcie/aer/aerdrv.h
@@ -72,7 +72,6 @@ struct aer_rpc {
 					 * recovery on the same
 					 * root port hierarchy
 					 */
-	wait_queue_head_t wait_release;
 };
 
 struct aer_broadcast_data {
diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
index 712392504ed9..521e39c1b66d 100644
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -811,8 +811,6 @@ void aer_isr(struct work_struct *work)
 	while (get_e_source(rpc, &e_src))
 		aer_isr_one_error(p_device, &e_src);
 	mutex_unlock(&rpc->rpc_mutex);
-
-	wake_up(&rpc->wait_release);
 }
 
 /**
diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c
index 63fc63911295..1ae4c73e7a3c 100644
--- a/drivers/pci/pcie/pme.c
+++ b/drivers/pci/pcie/pme.c
@@ -396,7 +396,7 @@ static int pcie_pme_suspend(struct pcie_device *srv)
 {
 	struct pcie_pme_service_data *data = get_service_data(srv);
 	struct pci_dev *port = srv->port;
-	bool wakeup;
+	bool wakeup, wake_irq_enabled = false;
 	int ret;
 
 	if (device_may_wakeup(&port->dev)) {
@@ -409,11 +409,12 @@ static int pcie_pme_suspend(struct pcie_device *srv)
 	spin_lock_irq(&data->lock);
 	if (wakeup) {
 		ret = enable_irq_wake(srv->irq);
-		data->suspend_level = PME_SUSPEND_WAKEUP;
+		if (ret == 0) {
+			data->suspend_level = PME_SUSPEND_WAKEUP;
+			wake_irq_enabled = true;
+		}
 	}
-	if (!wakeup || ret) {
-		struct pci_dev *port = srv->port;
-
+	if (!wake_irq_enabled) {
 		pcie_pme_interrupt_enable(port, false);
 		pcie_clear_root_pme_status(port);
 		data->suspend_level = PME_SUSPEND_NOIRQ;
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 6d7ab9bb0d5a..8004f67c57ec 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -15,7 +15,7 @@
 #include <linux/pci-aspm.h>
 #include <linux/aer.h>
 #include <linux/acpi.h>
-#include <asm-generic/pci-bridge.h>
+#include <linux/irqdomain.h>
 #include "pci.h"
 
 #define CARDBUS_LATENCY_TIMER	176	/* secondary latency timer */
@@ -179,6 +179,9 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 	u16 orig_cmd;
 	struct pci_bus_region region, inverted_region;
 
+	if (dev->non_compliant_bars)
+		return 0;
+
 	mask = type ? PCI_ROM_ADDRESS_MASK : ~0;
 
 	/* No printks while decoding is disabled! */
@@ -675,6 +678,20 @@ static struct irq_domain *pci_host_bridge_msi_domain(struct pci_bus *bus)
 	if (!d)
 		d = pci_host_bridge_acpi_msi_domain(bus);
 
+#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
+	/*
+	 * If no IRQ domain was found via the OF tree, try looking it up
+	 * directly through the fwnode_handle.
+	 */
+	if (!d) {
+		struct fwnode_handle *fwnode = pci_root_bus_fwnode(bus);
+
+		if (fwnode)
+			d = irq_find_matching_fwnode(fwnode,
+						     DOMAIN_BUS_PCI_MSI);
+	}
+#endif
+
 	return d;
 }
 
@@ -758,6 +775,12 @@ add_dev:
 
 	pcibios_add_bus(child);
 
+	if (child->ops->add_bus) {
+		ret = child->ops->add_bus(child);
+		if (WARN_ON(ret < 0))
+			dev_err(&child->dev, "failed to add bus: %d\n", ret);
+	}
+
 	/* Create legacy_io and legacy_mem files for this bus */
 	pci_create_legacy_files(child);
 
@@ -1171,6 +1194,7 @@ static void pci_msi_setup_pci_dev(struct pci_dev *dev)
 int pci_setup_device(struct pci_dev *dev)
 {
 	u32 class;
+	u16 cmd;
 	u8 hdr_type;
 	int pos = 0;
 	struct pci_bus_region region;
@@ -1214,6 +1238,16 @@ int pci_setup_device(struct pci_dev *dev)
 	/* device class may be changed after fixup */
 	class = dev->class >> 8;
 
+	if (dev->non_compliant_bars) {
+		pci_read_config_word(dev, PCI_COMMAND, &cmd);
+		if (cmd & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) {
+			dev_info(&dev->dev, "device has non-compliant BARs; disabling IO/MEM decoding\n");
+			cmd &= ~PCI_COMMAND_IO;
+			cmd &= ~PCI_COMMAND_MEMORY;
+			pci_write_config_word(dev, PCI_COMMAND, cmd);
+		}
+	}
+
 	switch (dev->hdr_type) {		    /* header type */
 	case PCI_HEADER_TYPE_NORMAL:		    /* standard header */
 		if (class == PCI_CLASS_BRIDGE_PCI)
@@ -1608,7 +1642,7 @@ static void pci_init_capabilities(struct pci_dev *dev)
 	pci_pm_init(dev);
 
 	/* Vital Product Data */
-	pci_vpd_pci22_init(dev);
+	pci_vpd_init(dev);
 
 	/* Alternative Routing-ID Forwarding */
 	pci_configure_ari(dev);
@@ -1803,6 +1837,13 @@ static int only_one_child(struct pci_bus *bus)
 		return 0;
 	if (pci_pcie_type(parent) == PCI_EXP_TYPE_ROOT_PORT)
 		return 1;
+
+	/*
+	 * PCIe downstream ports are bridges that normally lead to only a
+	 * device 0, but if PCI_SCAN_ALL_PCIE_DEVS is set, scan all
+	 * possible devices, not just device 0.  See PCIe spec r3.0,
+	 * sec 7.3.1.
+	 */
 	if (parent->has_secondary_link &&
 	    !pci_has_flag(PCI_SCAN_ALL_PCIE_DEVS))
 		return 1;
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 0575a1e026b4..8e678027b900 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -438,7 +438,7 @@ static void quirk_amd_nl_class(struct pci_dev *pdev)
 	u32 class = pdev->class;
 
 	/* Use "USB Device (not host controller)" class */
-	pdev->class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe;
+	pdev->class = PCI_CLASS_SERIAL_USB_DEVICE;
 	dev_info(&pdev->dev, "PCI class overridden (%#08x -> %#08x) so dwc3 driver can claim this instead of xhci\n",
 		 class, pdev->class);
 }
@@ -2135,6 +2135,35 @@ static void quirk_via_cx700_pci_parking_caching(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, 0x324e, quirk_via_cx700_pci_parking_caching);
 
 /*
+ * If a device follows the VPD format spec, the PCI core will not read or
+ * write past the VPD End Tag.  But some vendors do not follow the VPD
+ * format spec, so we can't tell how much data is safe to access.  Devices
+ * may behave unpredictably if we access too much.  Blacklist these devices
+ * so we don't touch VPD at all.
+ */
+static void quirk_blacklist_vpd(struct pci_dev *dev)
+{
+	if (dev->vpd) {
+		dev->vpd->len = 0;
+		dev_warn(&dev->dev, FW_BUG "VPD access disabled\n");
+	}
+}
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x0060, quirk_blacklist_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x007c, quirk_blacklist_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x0413, quirk_blacklist_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x0078, quirk_blacklist_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x0079, quirk_blacklist_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x0073, quirk_blacklist_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x0071, quirk_blacklist_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x005b, quirk_blacklist_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x002f, quirk_blacklist_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x005d, quirk_blacklist_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LSI_LOGIC, 0x005f, quirk_blacklist_vpd);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATTANSIC, PCI_ANY_ID,
+		quirk_blacklist_vpd);
+
+/*
  * For Broadcom 5706, 5708, 5709 rev. A nics, any read beyond the
  * VPD end tag will hang the device.  This problem was initially
  * observed when a vpd entry was created in sysfs
@@ -3832,6 +3861,19 @@ static int pci_quirk_amd_sb_acs(struct pci_dev *dev, u16 acs_flags)
 #endif
 }
 
+static int pci_quirk_cavium_acs(struct pci_dev *dev, u16 acs_flags)
+{
+	/*
+	 * Cavium devices matching this quirk do not perform peer-to-peer
+	 * with other functions, allowing masking out these bits as if they
+	 * were unimplemented in the ACS capability.
+	 */
+	acs_flags &= ~(PCI_ACS_SV | PCI_ACS_TB | PCI_ACS_RR |
+		       PCI_ACS_CR | PCI_ACS_UF | PCI_ACS_DT);
+
+	return acs_flags ? 0 : 1;
+}
+
 /*
  * Many Intel PCH root ports do provide ACS-like features to disable peer
  * transactions and validate bus numbers in requests, but do not provide an
@@ -3984,6 +4026,8 @@ static const struct pci_dev_acs_enabled {
 	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_quirk_intel_pch_acs },
 	{ 0x19a2, 0x710, pci_quirk_mf_endpoint_acs }, /* Emulex BE3-R */
 	{ 0x10df, 0x720, pci_quirk_mf_endpoint_acs }, /* Emulex Skyhawk-R */
+	/* Cavium ThunderX */
+	{ PCI_VENDOR_ID_CAVIUM, PCI_ANY_ID, pci_quirk_cavium_acs },
 	{ 0 }
 };
 
diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
index 8a280e9c2ad1..8982026637d5 100644
--- a/drivers/pci/remove.c
+++ b/drivers/pci/remove.c
@@ -7,7 +7,6 @@ static void pci_free_resources(struct pci_dev *dev)
 {
 	int i;
 
-	pci_cleanup_rom(dev);
 	for (i = 0; i < PCI_NUM_RESOURCES; i++) {
 		struct resource *res = dev->resource + i;
 		if (res->parent)
@@ -54,6 +53,10 @@ void pci_remove_bus(struct pci_bus *bus)
 	pci_bus_release_busn_res(bus);
 	up_write(&pci_bus_sem);
 	pci_remove_legacy_files(bus);
+
+	if (bus->ops->remove_bus)
+		bus->ops->remove_bus(bus);
+
 	pcibios_remove_bus(bus);
 	device_unregister(&bus->dev);
 }
diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c
index 9eaca39ef38d..06663d391b39 100644
--- a/drivers/pci/rom.c
+++ b/drivers/pci/rom.c
@@ -24,13 +24,17 @@
  */
 int pci_enable_rom(struct pci_dev *pdev)
 {
-	struct resource *res = pdev->resource + PCI_ROM_RESOURCE;
+	struct resource *res = &pdev->resource[PCI_ROM_RESOURCE];
 	struct pci_bus_region region;
 	u32 rom_addr;
 
 	if (!res->flags)
 		return -1;
 
+	/* Nothing to enable if we're using a shadow copy in RAM */
+	if (res->flags & IORESOURCE_ROM_SHADOW)
+		return 0;
+
 	pcibios_resource_to_bus(pdev->bus, &region, res);
 	pci_read_config_dword(pdev, pdev->rom_base_reg, &rom_addr);
 	rom_addr &= ~PCI_ROM_ADDRESS_MASK;
@@ -49,7 +53,12 @@ EXPORT_SYMBOL_GPL(pci_enable_rom);
  */
 void pci_disable_rom(struct pci_dev *pdev)
 {
+	struct resource *res = &pdev->resource[PCI_ROM_RESOURCE];
 	u32 rom_addr;
+
+	if (res->flags & IORESOURCE_ROM_SHADOW)
+		return;
+
 	pci_read_config_dword(pdev, pdev->rom_base_reg, &rom_addr);
 	rom_addr &= ~PCI_ROM_ADDRESS_ENABLE;
 	pci_write_config_dword(pdev, pdev->rom_base_reg, rom_addr);
@@ -119,43 +128,23 @@ void __iomem *pci_map_rom(struct pci_dev *pdev, size_t *size)
 	loff_t start;
 	void __iomem *rom;
 
-	/*
-	 * IORESOURCE_ROM_SHADOW set on x86, x86_64 and IA64 supports legacy
-	 * memory map if the VGA enable bit of the Bridge Control register is
-	 * set for embedded VGA.
-	 */
-	if (res->flags & IORESOURCE_ROM_SHADOW) {
-		/* primary video rom always starts here */
-		start = (loff_t)0xC0000;
-		*size = 0x20000; /* cover C000:0 through E000:0 */
-	} else {
-		if (res->flags &
-			(IORESOURCE_ROM_COPY | IORESOURCE_ROM_BIOS_COPY)) {
-			*size = pci_resource_len(pdev, PCI_ROM_RESOURCE);
-			return (void __iomem *)(unsigned long)
-				pci_resource_start(pdev, PCI_ROM_RESOURCE);
-		} else {
-			/* assign the ROM an address if it doesn't have one */
-			if (res->parent == NULL &&
-			    pci_assign_resource(pdev, PCI_ROM_RESOURCE))
-				return NULL;
-			start = pci_resource_start(pdev, PCI_ROM_RESOURCE);
-			*size = pci_resource_len(pdev, PCI_ROM_RESOURCE);
-			if (*size == 0)
-				return NULL;
-
-			/* Enable ROM space decodes */
-			if (pci_enable_rom(pdev))
-				return NULL;
-		}
-	}
+	/* assign the ROM an address if it doesn't have one */
+	if (res->parent == NULL && pci_assign_resource(pdev, PCI_ROM_RESOURCE))
+		return NULL;
+
+	start = pci_resource_start(pdev, PCI_ROM_RESOURCE);
+	*size = pci_resource_len(pdev, PCI_ROM_RESOURCE);
+	if (*size == 0)
+		return NULL;
+
+	/* Enable ROM space decodes */
+	if (pci_enable_rom(pdev))
+		return NULL;
 
 	rom = ioremap(start, *size);
 	if (!rom) {
 		/* restore enable if ioremap fails */
-		if (!(res->flags & (IORESOURCE_ROM_ENABLE |
-				    IORESOURCE_ROM_SHADOW |
-				    IORESOURCE_ROM_COPY)))
+		if (!(res->flags & IORESOURCE_ROM_ENABLE))
 			pci_disable_rom(pdev);
 		return NULL;
 	}
@@ -181,37 +170,15 @@ void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom)
 {
 	struct resource *res = &pdev->resource[PCI_ROM_RESOURCE];
 
-	if (res->flags & (IORESOURCE_ROM_COPY | IORESOURCE_ROM_BIOS_COPY))
-		return;
-
 	iounmap(rom);
 
-	/* Disable again before continuing, leave enabled if pci=rom */
-	if (!(res->flags & (IORESOURCE_ROM_ENABLE | IORESOURCE_ROM_SHADOW)))
+	/* Disable again before continuing */
+	if (!(res->flags & IORESOURCE_ROM_ENABLE))
 		pci_disable_rom(pdev);
 }
 EXPORT_SYMBOL(pci_unmap_rom);
 
 /**
- * pci_cleanup_rom - free the ROM copy created by pci_map_rom_copy
- * @pdev: pointer to pci device struct
- *
- * Free the copied ROM if we allocated one.
- */
-void pci_cleanup_rom(struct pci_dev *pdev)
-{
-	struct resource *res = &pdev->resource[PCI_ROM_RESOURCE];
-
-	if (res->flags & IORESOURCE_ROM_COPY) {
-		kfree((void *)(unsigned long)res->start);
-		res->flags |= IORESOURCE_UNSET;
-		res->flags &= ~IORESOURCE_ROM_COPY;
-		res->start = 0;
-		res->end = 0;
-	}
-}
-
-/**
  * pci_platform_rom - provides a pointer to any ROM image provided by the
  * platform
  * @pdev: pointer to pci device struct
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 7796d0a5befa..55641a39a3e9 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -25,7 +25,6 @@
 #include <linux/ioport.h>
 #include <linux/cache.h>
 #include <linux/slab.h>
-#include <asm-generic/pci-bridge.h>
 #include "pci.h"
 
 unsigned int pci_flags;
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index 604011e047d6..66c4d8f42233 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -276,6 +276,9 @@ int pci_assign_resource(struct pci_dev *dev, int resno)
 	resource_size_t align, size;
 	int ret;
 
+	if (res->flags & IORESOURCE_PCI_FIXED)
+		return 0;
+
 	res->flags |= IORESOURCE_UNSET;
 	align = pci_resource_alignment(dev, res);
 	if (!align) {
@@ -321,6 +324,9 @@ int pci_reassign_resource(struct pci_dev *dev, int resno, resource_size_t addsiz
 	resource_size_t new_size;
 	int ret;
 
+	if (res->flags & IORESOURCE_PCI_FIXED)
+		return 0;
+
 	flags = res->flags;
 	res->flags |= IORESOURCE_UNSET;
 	if (!res->parent) {
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index c777b97207d5..5f70fee59a94 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -53,7 +53,7 @@ struct pcifront_device {
 };
 
 struct pcifront_sd {
-	int domain;
+	struct pci_sysdata sd;
 	struct pcifront_device *pdev;
 };
 
@@ -67,7 +67,9 @@ static inline void pcifront_init_sd(struct pcifront_sd *sd,
 				    unsigned int domain, unsigned int bus,
 				    struct pcifront_device *pdev)
 {
-	sd->domain = domain;
+	/* Because we do not expose that information via XenBus. */
+	sd->sd.node = first_online_node;
+	sd->sd.domain = domain;
 	sd->pdev = pdev;
 }
 
@@ -468,8 +470,8 @@ static int pcifront_scan_root(struct pcifront_device *pdev,
 	dev_info(&pdev->xdev->dev, "Creating PCI Frontend Bus %04x:%02x\n",
 		 domain, bus);
 
-	bus_entry = kmalloc(sizeof(*bus_entry), GFP_KERNEL);
-	sd = kmalloc(sizeof(*sd), GFP_KERNEL);
+	bus_entry = kzalloc(sizeof(*bus_entry), GFP_KERNEL);
+	sd = kzalloc(sizeof(*sd), GFP_KERNEL);
 	if (!bus_entry || !sd) {
 		err = -ENOMEM;
 		goto err_out;
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index e7e117d5dbbe..0124d17bd9fe 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -224,6 +224,7 @@ config PHY_MT65XX_USB3
 
 config PHY_HI6220_USB
 	tristate "hi6220 USB PHY support"
+	depends on (ARCH_HISI && ARM64) || COMPILE_TEST
 	select GENERIC_PHY
 	select MFD_SYSCON
 	help
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 8c7f27db6ad3..e7e574dc667a 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -275,20 +275,21 @@ EXPORT_SYMBOL_GPL(phy_exit);
 
 int phy_power_on(struct phy *phy)
 {
-	int ret;
+	int ret = 0;
 
 	if (!phy)
-		return 0;
+		goto out;
 
 	if (phy->pwr) {
 		ret = regulator_enable(phy->pwr);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	ret = phy_pm_runtime_get_sync(phy);
 	if (ret < 0 && ret != -ENOTSUPP)
-		return ret;
+		goto err_pm_sync;
+
 	ret = 0; /* Override possible ret == -ENOTSUPP */
 
 	mutex_lock(&phy->mutex);
@@ -296,19 +297,20 @@ int phy_power_on(struct phy *phy)
 		ret = phy->ops->power_on(phy);
 		if (ret < 0) {
 			dev_err(&phy->dev, "phy poweron failed --> %d\n", ret);
-			goto out;
+			goto err_pwr_on;
 		}
 	}
 	++phy->power_count;
 	mutex_unlock(&phy->mutex);
 	return 0;
 
-out:
+err_pwr_on:
 	mutex_unlock(&phy->mutex);
 	phy_pm_runtime_put_sync(phy);
+err_pm_sync:
 	if (phy->pwr)
 		regulator_disable(phy->pwr);
-
+out:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(phy_power_on);
diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c
index 4a3fc6e59f8e..840f3eae428b 100644
--- a/drivers/phy/phy-twl4030-usb.c
+++ b/drivers/phy/phy-twl4030-usb.c
@@ -715,6 +715,7 @@ static int twl4030_usb_probe(struct platform_device *pdev)
 	pm_runtime_use_autosuspend(&pdev->dev);
 	pm_runtime_set_autosuspend_delay(&pdev->dev, 2000);
 	pm_runtime_enable(&pdev->dev);
+	pm_runtime_get_sync(&pdev->dev);
 
 	/* Our job is to use irqs and status from the power module
 	 * to keep the transceiver disabled when nothing's connected.
@@ -750,6 +751,7 @@ static int twl4030_usb_remove(struct platform_device *pdev)
 	struct twl4030_usb *twl = platform_get_drvdata(pdev);
 	int val;
 
+	usb_remove_phy(&twl->phy);
 	pm_runtime_get_sync(twl->dev);
 	cancel_delayed_work(&twl->id_workaround_work);
 	device_remove_file(twl->dev, &dev_attr_vbus);
@@ -757,6 +759,13 @@ static int twl4030_usb_remove(struct platform_device *pdev)
 	/* set transceiver mode to power on defaults */
 	twl4030_usb_set_mode(twl, -1);
 
+	/* idle ulpi before powering off */
+	if (cable_present(twl->linkstat))
+		pm_runtime_put_noidle(twl->dev);
+	pm_runtime_mark_last_busy(twl->dev);
+	pm_runtime_put_sync_suspend(twl->dev);
+	pm_runtime_disable(twl->dev);
+
 	/* autogate 60MHz ULPI clock,
 	 * clear dpll clock request for i2c access,
 	 * disable 32KHz
@@ -771,11 +780,6 @@ static int twl4030_usb_remove(struct platform_device *pdev)
 	/* disable complete OTG block */
 	twl4030_usb_clear_bits(twl, POWER_CTRL, POWER_CTRL_OTG_ENAB);
 
-	if (cable_present(twl->linkstat))
-		pm_runtime_put_noidle(twl->dev);
-	pm_runtime_mark_last_busy(twl->dev);
-	pm_runtime_put(twl->dev);
-
 	return 0;
 }
 
diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index 99a4c10ed43f..fb8200b8e8ec 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -79,7 +79,7 @@ config PINCTRL_AT91PIO4
 	  controller available on sama5d2 SoC.
 
 config PINCTRL_AMD
-	bool "AMD GPIO pin control"
+	tristate "AMD GPIO pin control"
 	depends on GPIOLIB
 	select GPIOLIB_IRQCHIP
 	select PINCONF
@@ -168,37 +168,6 @@ config PINCTRL_ST
 	select PINCONF
 	select GPIOLIB_IRQCHIP
 
-config PINCTRL_TEGRA
-	bool
-	select PINMUX
-	select PINCONF
-
-config PINCTRL_TEGRA20
-	bool
-	select PINCTRL_TEGRA
-
-config PINCTRL_TEGRA30
-	bool
-	select PINCTRL_TEGRA
-
-config PINCTRL_TEGRA114
-	bool
-	select PINCTRL_TEGRA
-
-config PINCTRL_TEGRA124
-	bool
-	select PINCTRL_TEGRA
-
-config PINCTRL_TEGRA210
-	bool
-	select PINCTRL_TEGRA
-
-config PINCTRL_TEGRA_XUSB
-	def_bool y if ARCH_TEGRA
-	select GENERIC_PHY
-	select PINCONF
-	select PINMUX
-
 config PINCTRL_TZ1090
 	bool "Toumaz Xenif TZ1090 pin control driver"
 	depends on SOC_TZ1090
@@ -238,6 +207,23 @@ config PINCTRL_PALMAS
 	  open drain configuration for the Palmas series devices like
 	  TPS65913, TPS80036 etc.
 
+config PINCTRL_PIC32
+	bool "Microchip PIC32 pin controller driver"
+	depends on OF
+	depends on MACH_PIC32
+	select PINMUX
+	select GENERIC_PINCONF
+	select GPIOLIB_IRQCHIP
+	select OF_GPIO
+	help
+	  This is the pin controller and gpio driver for Microchip PIC32
+	  microcontrollers. This option is selected automatically when specific
+	  machine and arch are selected to build.
+
+config PINCTRL_PIC32MZDA
+	def_bool y if PIC32MZDA
+	select PINCTRL_PIC32
+
 config PINCTRL_ZYNQ
 	bool "Pinctrl driver for Xilinx Zynq"
 	depends on ARCH_ZYNQ
@@ -257,7 +243,9 @@ source "drivers/pinctrl/qcom/Kconfig"
 source "drivers/pinctrl/samsung/Kconfig"
 source "drivers/pinctrl/sh-pfc/Kconfig"
 source "drivers/pinctrl/spear/Kconfig"
+source "drivers/pinctrl/stm32/Kconfig"
 source "drivers/pinctrl/sunxi/Kconfig"
+source "drivers/pinctrl/tegra/Kconfig"
 source "drivers/pinctrl/uniphier/Kconfig"
 source "drivers/pinctrl/vt8500/Kconfig"
 source "drivers/pinctrl/mediatek/Kconfig"
diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile
index bf1b5ca5180b..e4bc1151e04f 100644
--- a/drivers/pinctrl/Makefile
+++ b/drivers/pinctrl/Makefile
@@ -18,17 +18,12 @@ obj-$(CONFIG_PINCTRL_DIGICOLOR)	+= pinctrl-digicolor.o
 obj-$(CONFIG_PINCTRL_FALCON)	+= pinctrl-falcon.o
 obj-$(CONFIG_PINCTRL_MESON)	+= meson/
 obj-$(CONFIG_PINCTRL_PALMAS)	+= pinctrl-palmas.o
+obj-$(CONFIG_PINCTRL_PIC32)	+= pinctrl-pic32.o
 obj-$(CONFIG_PINCTRL_PISTACHIO)	+= pinctrl-pistachio.o
 obj-$(CONFIG_PINCTRL_ROCKCHIP)	+= pinctrl-rockchip.o
 obj-$(CONFIG_PINCTRL_SINGLE)	+= pinctrl-single.o
 obj-$(CONFIG_PINCTRL_SIRF)	+= sirf/
-obj-$(CONFIG_PINCTRL_TEGRA)	+= pinctrl-tegra.o
-obj-$(CONFIG_PINCTRL_TEGRA20)	+= pinctrl-tegra20.o
-obj-$(CONFIG_PINCTRL_TEGRA30)	+= pinctrl-tegra30.o
-obj-$(CONFIG_PINCTRL_TEGRA114)	+= pinctrl-tegra114.o
-obj-$(CONFIG_PINCTRL_TEGRA124)	+= pinctrl-tegra124.o
-obj-$(CONFIG_PINCTRL_TEGRA210)	+= pinctrl-tegra210.o
-obj-$(CONFIG_PINCTRL_TEGRA_XUSB)	+= pinctrl-tegra-xusb.o
+obj-$(CONFIG_PINCTRL_TEGRA)	+= tegra/
 obj-$(CONFIG_PINCTRL_TZ1090)	+= pinctrl-tz1090.o
 obj-$(CONFIG_PINCTRL_TZ1090_PDC)	+= pinctrl-tz1090-pdc.o
 obj-$(CONFIG_PINCTRL_U300)	+= pinctrl-u300.o
@@ -46,12 +41,13 @@ obj-y				+= freescale/
 obj-$(CONFIG_X86)		+= intel/
 obj-$(CONFIG_PINCTRL_MVEBU)	+= mvebu/
 obj-y				+= nomadik/
-obj-$(CONFIG_ARCH_PXA)		+= pxa/
+obj-$(CONFIG_PINCTRL_PXA)	+= pxa/
 obj-$(CONFIG_ARCH_QCOM)		+= qcom/
 obj-$(CONFIG_PINCTRL_SAMSUNG)	+= samsung/
 obj-$(CONFIG_PINCTRL_SH_PFC)	+= sh-pfc/
 obj-$(CONFIG_PINCTRL_SPEAR)	+= spear/
-obj-$(CONFIG_ARCH_SUNXI)	+= sunxi/
+obj-$(CONFIG_PINCTRL_STM32)	+= stm32/
+obj-$(CONFIG_PINCTRL_SUNXI)	+= sunxi/
 obj-$(CONFIG_PINCTRL_UNIPHIER)	+= uniphier/
 obj-$(CONFIG_ARCH_VT8500)	+= vt8500/
-obj-$(CONFIG_ARCH_MEDIATEK)	+= mediatek/
+obj-$(CONFIG_PINCTRL_MTK)	+= mediatek/
diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c
index 0f5997ceb494..08b1d93da9fe 100644
--- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c
+++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c
@@ -779,7 +779,7 @@ static int bcm2835_pctl_dt_node_to_map(struct pinctrl_dev *pctldev,
 		}
 		if (num_pulls) {
 			err = of_property_read_u32_index(np, "brcm,pull",
-					(num_funcs > 1) ? i : 0, &pull);
+					(num_pulls > 1) ? i : 0, &pull);
 			if (err)
 				goto out;
 			err = bcm2835_pctl_dt_node_to_map_pull(pc, np, pin,
diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index 2686a4450dfc..f67a8b7a4e18 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -481,18 +481,12 @@ int pinctrl_get_group_pins(struct pinctrl_dev *pctldev, const char *pin_group,
 }
 EXPORT_SYMBOL_GPL(pinctrl_get_group_pins);
 
-/**
- * pinctrl_find_gpio_range_from_pin() - locate the GPIO range for a pin
- * @pctldev: the pin controller device to look in
- * @pin: a controller-local number to find the range for
- */
 struct pinctrl_gpio_range *
-pinctrl_find_gpio_range_from_pin(struct pinctrl_dev *pctldev,
-				 unsigned int pin)
+pinctrl_find_gpio_range_from_pin_nolock(struct pinctrl_dev *pctldev,
+					unsigned int pin)
 {
 	struct pinctrl_gpio_range *range;
 
-	mutex_lock(&pctldev->mutex);
 	/* Loop over the ranges */
 	list_for_each_entry(range, &pctldev->gpio_ranges, node) {
 		/* Check if we're in the valid range */
@@ -500,15 +494,32 @@ pinctrl_find_gpio_range_from_pin(struct pinctrl_dev *pctldev,
 			int a;
 			for (a = 0; a < range->npins; a++) {
 				if (range->pins[a] == pin)
-					goto out;
+					return range;
 			}
 		} else if (pin >= range->pin_base &&
 			   pin < range->pin_base + range->npins)
-			goto out;
+			return range;
 	}
-	range = NULL;
-out:
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(pinctrl_find_gpio_range_from_pin_nolock);
+
+/**
+ * pinctrl_find_gpio_range_from_pin() - locate the GPIO range for a pin
+ * @pctldev: the pin controller device to look in
+ * @pin: a controller-local number to find the range for
+ */
+struct pinctrl_gpio_range *
+pinctrl_find_gpio_range_from_pin(struct pinctrl_dev *pctldev,
+				 unsigned int pin)
+{
+	struct pinctrl_gpio_range *range;
+
+	mutex_lock(&pctldev->mutex);
+	range = pinctrl_find_gpio_range_from_pin_nolock(pctldev, pin);
 	mutex_unlock(&pctldev->mutex);
+
 	return range;
 }
 EXPORT_SYMBOL_GPL(pinctrl_find_gpio_range_from_pin);
diff --git a/drivers/pinctrl/core.h b/drivers/pinctrl/core.h
index b24ea846c867..ca08723b9ee1 100644
--- a/drivers/pinctrl/core.h
+++ b/drivers/pinctrl/core.h
@@ -182,6 +182,10 @@ static inline struct pin_desc *pin_desc_get(struct pinctrl_dev *pctldev,
 	return radix_tree_lookup(&pctldev->pin_desc_tree, pin);
 }
 
+extern struct pinctrl_gpio_range *
+pinctrl_find_gpio_range_from_pin_nolock(struct pinctrl_dev *pctldev,
+					unsigned int pin);
+
 int pinctrl_register_map(struct pinctrl_map const *maps, unsigned num_maps,
 			 bool dup);
 void pinctrl_unregister_map(struct pinctrl_map const *map);
diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index a5bb93987378..46210512d8ec 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -15,6 +15,7 @@
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/io.h>
+#include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
@@ -24,6 +25,7 @@
 #include <linux/pinctrl/pinctrl.h>
 #include <linux/pinctrl/pinmux.h>
 #include <linux/slab.h>
+#include <linux/regmap.h>
 
 #include "../core.h"
 #include "pinctrl-imx.h"
@@ -341,6 +343,31 @@ mux_pin:
 	return 0;
 }
 
+static void imx_pmx_gpio_disable_free(struct pinctrl_dev *pctldev,
+			struct pinctrl_gpio_range *range, unsigned offset)
+{
+	struct imx_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev);
+	const struct imx_pinctrl_soc_info *info = ipctl->info;
+	const struct imx_pin_reg *pin_reg;
+	u32 reg;
+
+	/*
+	 * Only Vybrid has the input/output buffer enable flags (IBE/OBE)
+	 * They are part of the shared mux/conf register.
+	 */
+	if (!(info->flags & SHARE_MUX_CONF_REG))
+		return;
+
+	pin_reg = &info->pin_regs[offset];
+	if (pin_reg->mux_reg == -1)
+		return;
+
+	/* Clear IBE/OBE/PUE to disable the pin (Hi-Z) */
+	reg = readl(ipctl->base + pin_reg->mux_reg);
+	reg &= ~0x7;
+	writel(reg, ipctl->base + pin_reg->mux_reg);
+}
+
 static int imx_pmx_gpio_set_direction(struct pinctrl_dev *pctldev,
 	   struct pinctrl_gpio_range *range, unsigned offset, bool input)
 {
@@ -377,6 +404,7 @@ static const struct pinmux_ops imx_pmx_ops = {
 	.get_function_groups = imx_pmx_get_groups,
 	.set_mux = imx_pmx_set,
 	.gpio_request_enable = imx_pmx_gpio_request_enable,
+	.gpio_disable_free = imx_pmx_gpio_disable_free,
 	.gpio_set_direction = imx_pmx_gpio_set_direction,
 };
 
@@ -692,10 +720,12 @@ static int imx_pinctrl_probe_dt(struct platform_device *pdev,
 int imx_pinctrl_probe(struct platform_device *pdev,
 		      struct imx_pinctrl_soc_info *info)
 {
+	struct regmap_config config = { .name = "gpr" };
 	struct device_node *dev_np = pdev->dev.of_node;
 	struct device_node *np;
 	struct imx_pinctrl *ipctl;
 	struct resource *res;
+	struct regmap *gpr;
 	int ret, i;
 
 	if (!info || !info->pins || !info->npins) {
@@ -704,6 +734,12 @@ int imx_pinctrl_probe(struct platform_device *pdev,
 	}
 	info->dev = &pdev->dev;
 
+	if (info->gpr_compatible) {
+		gpr = syscon_regmap_lookup_by_compatible(info->gpr_compatible);
+		if (!IS_ERR(gpr))
+			regmap_attach_dev(&pdev->dev, gpr, &config);
+	}
+
 	/* Create state holders etc for this driver */
 	ipctl = devm_kzalloc(&pdev->dev, sizeof(*ipctl), GFP_KERNEL);
 	if (!ipctl)
diff --git a/drivers/pinctrl/freescale/pinctrl-imx.h b/drivers/pinctrl/freescale/pinctrl-imx.h
index 2a592f657c18..3b8bd81a39a4 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.h
+++ b/drivers/pinctrl/freescale/pinctrl-imx.h
@@ -82,6 +82,7 @@ struct imx_pinctrl_soc_info {
 	struct imx_pmx_func *functions;
 	unsigned int nfunctions;
 	unsigned int flags;
+	const char *gpr_compatible;
 };
 
 #define SHARE_MUX_CONF_REG	0x1
diff --git a/drivers/pinctrl/freescale/pinctrl-imx50.c b/drivers/pinctrl/freescale/pinctrl-imx50.c
index 51b31df96273..8acc4d960cfa 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx50.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx50.c
@@ -389,6 +389,7 @@ static const struct pinctrl_pin_desc imx50_pinctrl_pads[] = {
 static struct imx_pinctrl_soc_info imx50_pinctrl_info = {
 	.pins = imx50_pinctrl_pads,
 	.npins = ARRAY_SIZE(imx50_pinctrl_pads),
+	.gpr_compatible = "fsl,imx50-iomuxc-gpr",
 };
 
 static const struct of_device_id imx50_pinctrl_of_match[] = {
diff --git a/drivers/pinctrl/freescale/pinctrl-imx53.c b/drivers/pinctrl/freescale/pinctrl-imx53.c
index 7344d340013c..d39dfd6a3a44 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx53.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx53.c
@@ -452,6 +452,7 @@ static const struct pinctrl_pin_desc imx53_pinctrl_pads[] = {
 static struct imx_pinctrl_soc_info imx53_pinctrl_info = {
 	.pins = imx53_pinctrl_pads,
 	.npins = ARRAY_SIZE(imx53_pinctrl_pads),
+	.gpr_compatible = "fsl,imx53-iomuxc-gpr",
 };
 
 static const struct of_device_id imx53_pinctrl_of_match[] = {
diff --git a/drivers/pinctrl/freescale/pinctrl-imx6dl.c b/drivers/pinctrl/freescale/pinctrl-imx6dl.c
index 6805c678c3b2..5a2cdb0549ce 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx6dl.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx6dl.c
@@ -458,6 +458,7 @@ static const struct pinctrl_pin_desc imx6dl_pinctrl_pads[] = {
 static struct imx_pinctrl_soc_info imx6dl_pinctrl_info = {
 	.pins = imx6dl_pinctrl_pads,
 	.npins = ARRAY_SIZE(imx6dl_pinctrl_pads),
+	.gpr_compatible = "fsl,imx6q-iomuxc-gpr",
 };
 
 static const struct of_device_id imx6dl_pinctrl_of_match[] = {
diff --git a/drivers/pinctrl/freescale/pinctrl-imx6q.c b/drivers/pinctrl/freescale/pinctrl-imx6q.c
index 4d1fcb861ac1..7d50a36b1086 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx6q.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx6q.c
@@ -464,6 +464,7 @@ static const struct pinctrl_pin_desc imx6q_pinctrl_pads[] = {
 static struct imx_pinctrl_soc_info imx6q_pinctrl_info = {
 	.pins = imx6q_pinctrl_pads,
 	.npins = ARRAY_SIZE(imx6q_pinctrl_pads),
+	.gpr_compatible = "fsl,imx6q-iomuxc-gpr",
 };
 
 static const struct of_device_id imx6q_pinctrl_of_match[] = {
diff --git a/drivers/pinctrl/freescale/pinctrl-imx6sl.c b/drivers/pinctrl/freescale/pinctrl-imx6sl.c
index 83fa5f19ae89..e27d17fdc69d 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx6sl.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx6sl.c
@@ -364,6 +364,7 @@ static const struct pinctrl_pin_desc imx6sl_pinctrl_pads[] = {
 static struct imx_pinctrl_soc_info imx6sl_pinctrl_info = {
 	.pins = imx6sl_pinctrl_pads,
 	.npins = ARRAY_SIZE(imx6sl_pinctrl_pads),
+	.gpr_compatible = "fsl,imx6sl-iomuxc-gpr",
 };
 
 static const struct of_device_id imx6sl_pinctrl_of_match[] = {
diff --git a/drivers/pinctrl/freescale/pinctrl-imx6sx.c b/drivers/pinctrl/freescale/pinctrl-imx6sx.c
index 0d78fe690818..117180c26c50 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx6sx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx6sx.c
@@ -368,6 +368,7 @@ static const struct pinctrl_pin_desc imx6sx_pinctrl_pads[] = {
 static struct imx_pinctrl_soc_info imx6sx_pinctrl_info = {
 	.pins = imx6sx_pinctrl_pads,
 	.npins = ARRAY_SIZE(imx6sx_pinctrl_pads),
+	.gpr_compatible = "fsl,imx6sx-iomuxc-gpr",
 };
 
 static const struct of_device_id imx6sx_pinctrl_of_match[] = {
diff --git a/drivers/pinctrl/freescale/pinctrl-imx6ul.c b/drivers/pinctrl/freescale/pinctrl-imx6ul.c
index 08e75764e7be..78627c70c6ba 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx6ul.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx6ul.c
@@ -284,6 +284,7 @@ static const struct pinctrl_pin_desc imx6ul_pinctrl_pads[] = {
 static struct imx_pinctrl_soc_info imx6ul_pinctrl_info = {
 	.pins = imx6ul_pinctrl_pads,
 	.npins = ARRAY_SIZE(imx6ul_pinctrl_pads),
+	.gpr_compatible = "fsl,imx6ul-iomuxc-gpr",
 };
 
 static struct of_device_id imx6ul_pinctrl_of_match[] = {
diff --git a/drivers/pinctrl/freescale/pinctrl-imx7d.c b/drivers/pinctrl/freescale/pinctrl-imx7d.c
index 16dc925117de..1c89613eb4b7 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx7d.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx7d.c
@@ -359,6 +359,7 @@ static const struct pinctrl_pin_desc imx7d_lpsr_pinctrl_pads[] = {
 static struct imx_pinctrl_soc_info imx7d_pinctrl_info = {
 	.pins = imx7d_pinctrl_pads,
 	.npins = ARRAY_SIZE(imx7d_pinctrl_pads),
+	.gpr_compatible = "fsl,imx7d-iomuxc-gpr",
 };
 
 static struct imx_pinctrl_soc_info imx7d_lpsr_pinctrl_info = {
diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index c0f5586218c4..85536b467c25 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -11,13 +11,9 @@
  */
 
 #include <linux/module.h>
-#include <linux/init.h>
 #include <linux/interrupt.h>
-#include <linux/acpi.h>
-#include <linux/gpio.h>
 #include <linux/gpio/driver.h>
 #include <linux/platform_device.h>
-#include <linux/pm.h>
 #include <linux/pinctrl/pinctrl.h>
 #include <linux/pinctrl/pinmux.h>
 #include <linux/pinctrl/pinconf.h>
diff --git a/drivers/pinctrl/mediatek/Kconfig b/drivers/pinctrl/mediatek/Kconfig
index 02f6f92df86c..4f0bc8a103f4 100644
--- a/drivers/pinctrl/mediatek/Kconfig
+++ b/drivers/pinctrl/mediatek/Kconfig
@@ -1,6 +1,6 @@
 if ARCH_MEDIATEK || COMPILE_TEST
 
-config PINCTRL_MTK_COMMON
+config PINCTRL_MTK
 	bool
 	depends on OF
 	select PINMUX
@@ -9,17 +9,29 @@ config PINCTRL_MTK_COMMON
 	select OF_GPIO
 
 # For ARMv7 SoCs
+config PINCTRL_MT2701
+	bool "Mediatek MT2701 pin control" if COMPILE_TEST && !MACH_MT2701
+	depends on OF
+	default MACH_MT2701
+	select PINCTRL_MTK
+
+config PINCTRL_MT7623
+	bool "Mediatek MT7623 pin control" if COMPILE_TEST && !MACH_MT7623
+	depends on OF
+	default MACH_MT7623
+	select PINCTRL_MTK_COMMON
+
 config PINCTRL_MT8135
 	bool "Mediatek MT8135 pin control" if COMPILE_TEST && !MACH_MT8135
 	depends on OF
 	default MACH_MT8135
-	select PINCTRL_MTK_COMMON
+	select PINCTRL_MTK
 
 config PINCTRL_MT8127
 	bool "Mediatek MT8127 pin control" if COMPILE_TEST && !MACH_MT8127
 	depends on OF
 	default MACH_MT8127
-	select PINCTRL_MTK_COMMON
+	select PINCTRL_MTK
 
 # For ARMv8 SoCs
 config PINCTRL_MT8173
@@ -27,13 +39,13 @@ config PINCTRL_MT8173
 	depends on OF
 	depends on ARM64 || COMPILE_TEST
 	default ARM64 && ARCH_MEDIATEK
-	select PINCTRL_MTK_COMMON
+	select PINCTRL_MTK
 
 # For PMIC
 config PINCTRL_MT6397
 	bool "Mediatek MT6397 pin control" if COMPILE_TEST && !MFD_MT6397
 	depends on OF
 	default MFD_MT6397
-	select PINCTRL_MTK_COMMON
+	select PINCTRL_MTK
 
 endif
diff --git a/drivers/pinctrl/mediatek/Makefile b/drivers/pinctrl/mediatek/Makefile
index eb923d64d387..3e3390a14716 100644
--- a/drivers/pinctrl/mediatek/Makefile
+++ b/drivers/pinctrl/mediatek/Makefile
@@ -1,8 +1,10 @@
 # Core
-obj-$(CONFIG_PINCTRL_MTK_COMMON)	+= pinctrl-mtk-common.o
+obj-y				+= pinctrl-mtk-common.o
 
 # SoC Drivers
-obj-$(CONFIG_PINCTRL_MT8135)		+= pinctrl-mt8135.o
-obj-$(CONFIG_PINCTRL_MT8127)		+= pinctrl-mt8127.o
-obj-$(CONFIG_PINCTRL_MT8173)		+= pinctrl-mt8173.o
-obj-$(CONFIG_PINCTRL_MT6397)		+= pinctrl-mt6397.o
+obj-$(CONFIG_PINCTRL_MT2701)	+= pinctrl-mt2701.o
+obj-$(CONFIG_PINCTRL_MT7623)	+= pinctrl-mt7623.o
+obj-$(CONFIG_PINCTRL_MT8135)	+= pinctrl-mt8135.o
+obj-$(CONFIG_PINCTRL_MT8127)	+= pinctrl-mt8127.o
+obj-$(CONFIG_PINCTRL_MT8173)	+= pinctrl-mt8173.o
+obj-$(CONFIG_PINCTRL_MT6397)	+= pinctrl-mt6397.o
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt2701.c b/drivers/pinctrl/mediatek/pinctrl-mt2701.c
new file mode 100644
index 000000000000..8d802fa7decd
--- /dev/null
+++ b/drivers/pinctrl/mediatek/pinctrl-mt2701.c
@@ -0,0 +1,585 @@
+/*
+ * Copyright (c) 2015 MediaTek Inc.
+ * Author: Biao Huang <biao.huang@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <dt-bindings/pinctrl/mt65xx.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/regmap.h>
+
+#include "pinctrl-mtk-common.h"
+#include "pinctrl-mtk-mt2701.h"
+
+/**
+ * struct mtk_spec_pinmux_set
+ * - For special pins' mode setting
+ * @pin: The pin number.
+ * @offset: The offset of extra setting register.
+ * @bit: The bit of extra setting register.
+ */
+struct mtk_spec_pinmux_set {
+	unsigned short pin;
+	unsigned short offset;
+	unsigned char bit;
+};
+
+#define MTK_PINMUX_SPEC(_pin, _offset, _bit)	\
+	{					\
+		.pin = _pin,			\
+		.offset = _offset,		\
+		.bit = _bit,			\
+	}
+
+static const struct mtk_drv_group_desc mt2701_drv_grp[] =  {
+	/* 0E4E8SR 4/8/12/16 */
+	MTK_DRV_GRP(4, 16, 1, 2, 4),
+	/* 0E2E4SR  2/4/6/8 */
+	MTK_DRV_GRP(2, 8, 1, 2, 2),
+	/* E8E4E2  2/4/6/8/10/12/14/16 */
+	MTK_DRV_GRP(2, 16, 0, 2, 2)
+};
+
+static const struct mtk_pin_drv_grp mt2701_pin_drv[] = {
+	MTK_PIN_DRV_GRP(0, 0xf50, 0, 1),
+	MTK_PIN_DRV_GRP(1, 0xf50, 0, 1),
+	MTK_PIN_DRV_GRP(2, 0xf50, 0, 1),
+	MTK_PIN_DRV_GRP(3, 0xf50, 0, 1),
+	MTK_PIN_DRV_GRP(4, 0xf50, 0, 1),
+	MTK_PIN_DRV_GRP(5, 0xf50, 0, 1),
+	MTK_PIN_DRV_GRP(6, 0xf50, 0, 1),
+	MTK_PIN_DRV_GRP(7, 0xf50, 4, 1),
+	MTK_PIN_DRV_GRP(8, 0xf50, 4, 1),
+	MTK_PIN_DRV_GRP(9, 0xf50, 4, 1),
+	MTK_PIN_DRV_GRP(10, 0xf50, 8, 1),
+	MTK_PIN_DRV_GRP(11, 0xf50, 8, 1),
+	MTK_PIN_DRV_GRP(12, 0xf50, 8, 1),
+	MTK_PIN_DRV_GRP(13, 0xf50, 8, 1),
+	MTK_PIN_DRV_GRP(14, 0xf50, 12, 0),
+	MTK_PIN_DRV_GRP(15, 0xf50, 12, 0),
+	MTK_PIN_DRV_GRP(16, 0xf60, 0, 0),
+	MTK_PIN_DRV_GRP(17, 0xf60, 0, 0),
+	MTK_PIN_DRV_GRP(18, 0xf60, 4, 0),
+	MTK_PIN_DRV_GRP(19, 0xf60, 4, 0),
+	MTK_PIN_DRV_GRP(20, 0xf60, 4, 0),
+	MTK_PIN_DRV_GRP(21, 0xf60, 4, 0),
+	MTK_PIN_DRV_GRP(22, 0xf60, 8, 0),
+	MTK_PIN_DRV_GRP(23, 0xf60, 8, 0),
+	MTK_PIN_DRV_GRP(24, 0xf60, 8, 0),
+	MTK_PIN_DRV_GRP(25, 0xf60, 8, 0),
+	MTK_PIN_DRV_GRP(26, 0xf60, 8, 0),
+	MTK_PIN_DRV_GRP(27, 0xf60, 12, 0),
+	MTK_PIN_DRV_GRP(28, 0xf60, 12, 0),
+	MTK_PIN_DRV_GRP(29, 0xf60, 12, 0),
+	MTK_PIN_DRV_GRP(30, 0xf60, 0, 0),
+	MTK_PIN_DRV_GRP(31, 0xf60, 0, 0),
+	MTK_PIN_DRV_GRP(32, 0xf60, 0, 0),
+	MTK_PIN_DRV_GRP(33, 0xf70, 0, 0),
+	MTK_PIN_DRV_GRP(34, 0xf70, 0, 0),
+	MTK_PIN_DRV_GRP(35, 0xf70, 0, 0),
+	MTK_PIN_DRV_GRP(36, 0xf70, 0, 0),
+	MTK_PIN_DRV_GRP(37, 0xf70, 0, 0),
+	MTK_PIN_DRV_GRP(38, 0xf70, 4, 0),
+	MTK_PIN_DRV_GRP(39, 0xf70, 8, 1),
+	MTK_PIN_DRV_GRP(40, 0xf70, 8, 1),
+	MTK_PIN_DRV_GRP(41, 0xf70, 8, 1),
+	MTK_PIN_DRV_GRP(42, 0xf70, 8, 1),
+	MTK_PIN_DRV_GRP(43, 0xf70, 12, 0),
+	MTK_PIN_DRV_GRP(44, 0xf70, 12, 0),
+	MTK_PIN_DRV_GRP(45, 0xf70, 12, 0),
+	MTK_PIN_DRV_GRP(47, 0xf80, 0, 0),
+	MTK_PIN_DRV_GRP(48, 0xf80, 0, 0),
+	MTK_PIN_DRV_GRP(49, 0xf80, 4, 0),
+	MTK_PIN_DRV_GRP(50, 0xf70, 4, 0),
+	MTK_PIN_DRV_GRP(51, 0xf70, 4, 0),
+	MTK_PIN_DRV_GRP(52, 0xf70, 4, 0),
+	MTK_PIN_DRV_GRP(53, 0xf80, 12, 0),
+	MTK_PIN_DRV_GRP(54, 0xf80, 12, 0),
+	MTK_PIN_DRV_GRP(55, 0xf80, 12, 0),
+	MTK_PIN_DRV_GRP(56, 0xf80, 12, 0),
+	MTK_PIN_DRV_GRP(60, 0xf90, 8, 1),
+	MTK_PIN_DRV_GRP(61, 0xf90, 8, 1),
+	MTK_PIN_DRV_GRP(62, 0xf90, 8, 1),
+	MTK_PIN_DRV_GRP(63, 0xf90, 12, 1),
+	MTK_PIN_DRV_GRP(64, 0xf90, 12, 1),
+	MTK_PIN_DRV_GRP(65, 0xf90, 12, 1),
+	MTK_PIN_DRV_GRP(66, 0xfa0, 0, 1),
+	MTK_PIN_DRV_GRP(67, 0xfa0, 0, 1),
+	MTK_PIN_DRV_GRP(68, 0xfa0, 0, 1),
+	MTK_PIN_DRV_GRP(69, 0xfa0, 0, 1),
+	MTK_PIN_DRV_GRP(70, 0xfa0, 0, 1),
+	MTK_PIN_DRV_GRP(71, 0xfa0, 0, 1),
+	MTK_PIN_DRV_GRP(72, 0xf80, 4, 0),
+	MTK_PIN_DRV_GRP(73, 0xf80, 4, 0),
+	MTK_PIN_DRV_GRP(74, 0xf80, 4, 0),
+	MTK_PIN_DRV_GRP(85, 0xda0, 0, 2),
+	MTK_PIN_DRV_GRP(86, 0xd90, 0, 2),
+	MTK_PIN_DRV_GRP(87, 0xdb0, 0, 2),
+	MTK_PIN_DRV_GRP(88, 0xdb0, 0, 2),
+	MTK_PIN_DRV_GRP(89, 0xdb0, 0, 2),
+	MTK_PIN_DRV_GRP(90, 0xdb0, 0, 2),
+	MTK_PIN_DRV_GRP(105, 0xd40, 0, 2),
+	MTK_PIN_DRV_GRP(106, 0xd30, 0, 2),
+	MTK_PIN_DRV_GRP(107, 0xd50, 0, 2),
+	MTK_PIN_DRV_GRP(108, 0xd50, 0, 2),
+	MTK_PIN_DRV_GRP(109, 0xd50, 0, 2),
+	MTK_PIN_DRV_GRP(110, 0xd50, 0, 2),
+	MTK_PIN_DRV_GRP(111, 0xce0, 0, 2),
+	MTK_PIN_DRV_GRP(112, 0xce0, 0, 2),
+	MTK_PIN_DRV_GRP(113, 0xce0, 0, 2),
+	MTK_PIN_DRV_GRP(114, 0xce0, 0, 2),
+	MTK_PIN_DRV_GRP(115, 0xce0, 0, 2),
+	MTK_PIN_DRV_GRP(116, 0xcd0, 0, 2),
+	MTK_PIN_DRV_GRP(117, 0xcc0, 0, 2),
+	MTK_PIN_DRV_GRP(118, 0xce0, 0, 2),
+	MTK_PIN_DRV_GRP(119, 0xce0, 0, 2),
+	MTK_PIN_DRV_GRP(120, 0xce0, 0, 2),
+	MTK_PIN_DRV_GRP(121, 0xce0, 0, 2),
+	MTK_PIN_DRV_GRP(126, 0xf80, 4, 0),
+	MTK_PIN_DRV_GRP(188, 0xf70, 4, 0),
+	MTK_PIN_DRV_GRP(189, 0xfe0, 8, 0),
+	MTK_PIN_DRV_GRP(190, 0xfe0, 8, 0),
+	MTK_PIN_DRV_GRP(191, 0xfe0, 8, 0),
+	MTK_PIN_DRV_GRP(192, 0xfe0, 8, 0),
+	MTK_PIN_DRV_GRP(193, 0xfe0, 8, 0),
+	MTK_PIN_DRV_GRP(194, 0xfe0, 12, 0),
+	MTK_PIN_DRV_GRP(195, 0xfe0, 12, 0),
+	MTK_PIN_DRV_GRP(196, 0xfe0, 12, 0),
+	MTK_PIN_DRV_GRP(197, 0xfe0, 12, 0),
+	MTK_PIN_DRV_GRP(198, 0xfe0, 12, 0),
+	MTK_PIN_DRV_GRP(199, 0xf50, 4, 1),
+	MTK_PIN_DRV_GRP(200, 0xfd0, 0, 0),
+	MTK_PIN_DRV_GRP(201, 0xfd0, 0, 0),
+	MTK_PIN_DRV_GRP(202, 0xfd0, 0, 0),
+	MTK_PIN_DRV_GRP(203, 0xfd0, 4, 0),
+	MTK_PIN_DRV_GRP(204, 0xfd0, 4, 0),
+	MTK_PIN_DRV_GRP(205, 0xfd0, 4, 0),
+	MTK_PIN_DRV_GRP(206, 0xfd0, 4, 0),
+	MTK_PIN_DRV_GRP(207, 0xfd0, 4, 0),
+	MTK_PIN_DRV_GRP(208, 0xfd0, 8, 0),
+	MTK_PIN_DRV_GRP(209, 0xfd0, 8, 0),
+	MTK_PIN_DRV_GRP(210, 0xfd0, 12, 1),
+	MTK_PIN_DRV_GRP(211, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(212, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(213, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(214, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(215, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(216, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(217, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(218, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(219, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(220, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(221, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(222, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(223, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(224, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(225, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(226, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(227, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(228, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(229, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(230, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(231, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(232, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(233, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(234, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(235, 0xff0, 0, 1),
+	MTK_PIN_DRV_GRP(236, 0xff0, 4, 0),
+	MTK_PIN_DRV_GRP(237, 0xff0, 4, 0),
+	MTK_PIN_DRV_GRP(238, 0xff0, 4, 0),
+	MTK_PIN_DRV_GRP(239, 0xff0, 4, 0),
+	MTK_PIN_DRV_GRP(240, 0xff0, 4, 0),
+	MTK_PIN_DRV_GRP(241, 0xff0, 4, 0),
+	MTK_PIN_DRV_GRP(242, 0xff0, 8, 0),
+	MTK_PIN_DRV_GRP(243, 0xff0, 8, 0),
+	MTK_PIN_DRV_GRP(248, 0xf00, 0, 0),
+	MTK_PIN_DRV_GRP(249, 0xfc0, 0, 2),
+	MTK_PIN_DRV_GRP(250, 0xfc0, 0, 2),
+	MTK_PIN_DRV_GRP(251, 0xfc0, 0, 2),
+	MTK_PIN_DRV_GRP(252, 0xfc0, 0, 2),
+	MTK_PIN_DRV_GRP(253, 0xfc0, 0, 2),
+	MTK_PIN_DRV_GRP(254, 0xfc0, 0, 2),
+	MTK_PIN_DRV_GRP(255, 0xfc0, 0, 2),
+	MTK_PIN_DRV_GRP(256, 0xfc0, 0, 2),
+	MTK_PIN_DRV_GRP(257, 0xce0, 0, 2),
+	MTK_PIN_DRV_GRP(258, 0xcb0, 0, 2),
+	MTK_PIN_DRV_GRP(259, 0xc90, 0, 2),
+	MTK_PIN_DRV_GRP(260, 0x3a0, 0, 2),
+	MTK_PIN_DRV_GRP(261, 0xd50, 0, 2),
+	MTK_PIN_DRV_GRP(262, 0xf00, 8, 0),
+	MTK_PIN_DRV_GRP(263, 0xf00, 8, 0),
+	MTK_PIN_DRV_GRP(264, 0xf00, 8, 0),
+	MTK_PIN_DRV_GRP(265, 0xf00, 8, 0),
+	MTK_PIN_DRV_GRP(266, 0xf00, 8, 0),
+	MTK_PIN_DRV_GRP(267, 0xf00, 8, 0),
+	MTK_PIN_DRV_GRP(268, 0xf00, 8, 0),
+	MTK_PIN_DRV_GRP(269, 0xf00, 8, 0),
+	MTK_PIN_DRV_GRP(270, 0xf00, 8, 0),
+	MTK_PIN_DRV_GRP(271, 0xf00, 8, 0),
+	MTK_PIN_DRV_GRP(272, 0xf00, 8, 0),
+	MTK_PIN_DRV_GRP(273, 0xf00, 8, 0),
+	MTK_PIN_DRV_GRP(274, 0xf00, 8, 0),
+	MTK_PIN_DRV_GRP(275, 0xf00, 8, 0),
+	MTK_PIN_DRV_GRP(276, 0xf00, 8, 0),
+	MTK_PIN_DRV_GRP(277, 0xf00, 8, 0),
+	MTK_PIN_DRV_GRP(278, 0xf70, 8, 1),
+};
+
+static const struct mtk_pin_spec_pupd_set_samereg mt2701_spec_pupd[] = {
+	MTK_PIN_PUPD_SPEC_SR(111, 0xd00, 12, 13, 14),	/* ms0 data7 */
+	MTK_PIN_PUPD_SPEC_SR(112, 0xd00, 8, 9, 10),	/* ms0 data6 */
+	MTK_PIN_PUPD_SPEC_SR(113, 0xd00, 4, 5, 6),	/* ms0 data5 */
+	MTK_PIN_PUPD_SPEC_SR(114, 0xd00, 0, 1, 2),	/* ms0 data4 */
+	MTK_PIN_PUPD_SPEC_SR(115, 0xd10, 0, 1, 2),	/* ms0 rstb */
+	MTK_PIN_PUPD_SPEC_SR(116, 0xcd0, 8, 9, 10),	/* ms0 cmd */
+	MTK_PIN_PUPD_SPEC_SR(117, 0xcc0, 8, 9, 10),	/* ms0 clk */
+	MTK_PIN_PUPD_SPEC_SR(118, 0xcf0, 12, 13, 14),	/* ms0 data3 */
+	MTK_PIN_PUPD_SPEC_SR(119, 0xcf0, 8, 9, 10),	/* ms0 data2 */
+	MTK_PIN_PUPD_SPEC_SR(120, 0xcf0, 4, 5, 6),	/* ms0 data1 */
+	MTK_PIN_PUPD_SPEC_SR(121, 0xcf0, 0, 1, 2),	/* ms0 data0 */
+
+	MTK_PIN_PUPD_SPEC_SR(105, 0xd40, 8, 9, 10),	/* ms1 cmd */
+	MTK_PIN_PUPD_SPEC_SR(106, 0xd30, 8, 9, 10),	/* ms1 clk */
+	MTK_PIN_PUPD_SPEC_SR(107, 0xd60, 0, 1, 2),	/* ms1 dat0 */
+	MTK_PIN_PUPD_SPEC_SR(108, 0xd60, 10, 9, 8),	/* ms1 dat1 */
+	MTK_PIN_PUPD_SPEC_SR(109, 0xd60, 4, 5, 6),	/* ms1 dat2 */
+	MTK_PIN_PUPD_SPEC_SR(110, 0xc60, 12, 13, 14),	/* ms1 dat3 */
+
+	MTK_PIN_PUPD_SPEC_SR(85, 0xda0, 8, 9, 10),	/* ms2 cmd */
+	MTK_PIN_PUPD_SPEC_SR(86, 0xd90, 8, 9, 10),	/* ms2 clk */
+	MTK_PIN_PUPD_SPEC_SR(87, 0xdc0, 0, 1, 2),	/* ms2 dat0 */
+	MTK_PIN_PUPD_SPEC_SR(88, 0xdc0, 10, 9, 8),	/* ms2 dat1 */
+	MTK_PIN_PUPD_SPEC_SR(89, 0xdc0, 4, 5, 6),	/* ms2 dat2 */
+	MTK_PIN_PUPD_SPEC_SR(90, 0xdc0, 12, 13, 14),	/* ms2 dat3 */
+
+	MTK_PIN_PUPD_SPEC_SR(249, 0x140, 0, 1, 2),	/* ms0e rstb */
+	MTK_PIN_PUPD_SPEC_SR(250, 0x130, 12, 13, 14),	/* ms0e dat7 */
+	MTK_PIN_PUPD_SPEC_SR(251, 0x130, 8, 9, 10),	/* ms0e dat6 */
+	MTK_PIN_PUPD_SPEC_SR(252, 0x130, 4, 5, 6),	/* ms0e dat5 */
+	MTK_PIN_PUPD_SPEC_SR(253, 0x130, 0, 1, 2),	/* ms0e dat4 */
+	MTK_PIN_PUPD_SPEC_SR(254, 0xf40, 12, 13, 14),	/* ms0e dat3 */
+	MTK_PIN_PUPD_SPEC_SR(255, 0xf40, 8, 9, 10),	/* ms0e dat2 */
+	MTK_PIN_PUPD_SPEC_SR(256, 0xf40, 4, 5, 6),	/* ms0e dat1 */
+	MTK_PIN_PUPD_SPEC_SR(257, 0xf40, 0, 1, 2),	/* ms0e dat0 */
+	MTK_PIN_PUPD_SPEC_SR(258, 0xcb0, 8, 9, 10),	/* ms0e cmd */
+	MTK_PIN_PUPD_SPEC_SR(259, 0xc90, 8, 9, 10),	/* ms0e clk */
+	MTK_PIN_PUPD_SPEC_SR(261, 0x140, 8, 9, 10),	/* ms1 ins */
+};
+
+static int mt2701_spec_pull_set(struct regmap *regmap, unsigned int pin,
+		unsigned char align, bool isup, unsigned int r1r0)
+{
+	return mtk_pctrl_spec_pull_set_samereg(regmap, mt2701_spec_pupd,
+		ARRAY_SIZE(mt2701_spec_pupd), pin, align, isup, r1r0);
+}
+
+static const struct mtk_pin_ies_smt_set mt2701_ies_set[] = {
+	MTK_PIN_IES_SMT_SPEC(0, 6, 0xb20, 0),
+	MTK_PIN_IES_SMT_SPEC(7, 9, 0xb20, 1),
+	MTK_PIN_IES_SMT_SPEC(10, 13, 0xb30, 3),
+	MTK_PIN_IES_SMT_SPEC(14, 15, 0xb30, 13),
+	MTK_PIN_IES_SMT_SPEC(16, 17, 0xb40, 7),
+	MTK_PIN_IES_SMT_SPEC(18, 21, 0xb40, 13),
+	MTK_PIN_IES_SMT_SPEC(22, 26, 0xb40, 13),
+	MTK_PIN_IES_SMT_SPEC(27, 29, 0xb40, 13),
+	MTK_PIN_IES_SMT_SPEC(30, 32, 0xb40, 7),
+	MTK_PIN_IES_SMT_SPEC(33, 37, 0xb40, 13),
+	MTK_PIN_IES_SMT_SPEC(38, 38, 0xb20, 13),
+	MTK_PIN_IES_SMT_SPEC(39, 42, 0xb40, 13),
+	MTK_PIN_IES_SMT_SPEC(43, 45, 0xb20, 10),
+	MTK_PIN_IES_SMT_SPEC(47, 48, 0xb20, 11),
+	MTK_PIN_IES_SMT_SPEC(49, 49, 0xb20, 12),
+	MTK_PIN_IES_SMT_SPEC(50, 52, 0xb20, 13),
+	MTK_PIN_IES_SMT_SPEC(53, 56, 0xb20, 14),
+	MTK_PIN_IES_SMT_SPEC(57, 58, 0xb20, 15),
+	MTK_PIN_IES_SMT_SPEC(59, 59, 0xb30, 10),
+	MTK_PIN_IES_SMT_SPEC(60, 62, 0xb30, 0),
+	MTK_PIN_IES_SMT_SPEC(63, 65, 0xb30, 1),
+	MTK_PIN_IES_SMT_SPEC(66, 71, 0xb30, 2),
+	MTK_PIN_IES_SMT_SPEC(72, 74, 0xb20, 12),
+	MTK_PIN_IES_SMT_SPEC(75, 76, 0xb30, 3),
+	MTK_PIN_IES_SMT_SPEC(77, 78, 0xb30, 4),
+	MTK_PIN_IES_SMT_SPEC(79, 82, 0xb30, 5),
+	MTK_PIN_IES_SMT_SPEC(83, 84, 0xb30, 2),
+	MTK_PIN_IES_SMT_SPEC(85, 85, 0xda0, 4),
+	MTK_PIN_IES_SMT_SPEC(86, 86, 0xd90, 4),
+	MTK_PIN_IES_SMT_SPEC(87, 90, 0xdb0, 4),
+	MTK_PIN_IES_SMT_SPEC(101, 104, 0xb30, 6),
+	MTK_PIN_IES_SMT_SPEC(105, 105, 0xd40, 4),
+	MTK_PIN_IES_SMT_SPEC(106, 106, 0xd30, 4),
+	MTK_PIN_IES_SMT_SPEC(107, 110, 0xd50, 4),
+	MTK_PIN_IES_SMT_SPEC(111, 115, 0xce0, 4),
+	MTK_PIN_IES_SMT_SPEC(116, 116, 0xcd0, 4),
+	MTK_PIN_IES_SMT_SPEC(117, 117, 0xcc0, 4),
+	MTK_PIN_IES_SMT_SPEC(118, 121, 0xce0, 4),
+	MTK_PIN_IES_SMT_SPEC(122, 125, 0xb30, 7),
+	MTK_PIN_IES_SMT_SPEC(126, 126, 0xb20, 12),
+	MTK_PIN_IES_SMT_SPEC(127, 142, 0xb30, 9),
+	MTK_PIN_IES_SMT_SPEC(143, 160, 0xb30, 10),
+	MTK_PIN_IES_SMT_SPEC(161, 168, 0xb30, 12),
+	MTK_PIN_IES_SMT_SPEC(169, 183, 0xb30, 10),
+	MTK_PIN_IES_SMT_SPEC(184, 186, 0xb30, 9),
+	MTK_PIN_IES_SMT_SPEC(187, 187, 0xb30, 14),
+	MTK_PIN_IES_SMT_SPEC(188, 188, 0xb20, 13),
+	MTK_PIN_IES_SMT_SPEC(189, 193, 0xb30, 15),
+	MTK_PIN_IES_SMT_SPEC(194, 198, 0xb40, 0),
+	MTK_PIN_IES_SMT_SPEC(199, 199, 0xb20, 1),
+	MTK_PIN_IES_SMT_SPEC(200, 202, 0xb40, 1),
+	MTK_PIN_IES_SMT_SPEC(203, 207, 0xb40, 2),
+	MTK_PIN_IES_SMT_SPEC(208, 209, 0xb40, 3),
+	MTK_PIN_IES_SMT_SPEC(210, 210, 0xb40, 4),
+	MTK_PIN_IES_SMT_SPEC(211, 235, 0xb40, 5),
+	MTK_PIN_IES_SMT_SPEC(236, 241, 0xb40, 6),
+	MTK_PIN_IES_SMT_SPEC(242, 243, 0xb40, 7),
+	MTK_PIN_IES_SMT_SPEC(244, 247, 0xb40, 8),
+	MTK_PIN_IES_SMT_SPEC(248, 248, 0xb40, 9),
+	MTK_PIN_IES_SMT_SPEC(249, 257, 0xfc0, 4),
+	MTK_PIN_IES_SMT_SPEC(258, 258, 0xcb0, 4),
+	MTK_PIN_IES_SMT_SPEC(259, 259, 0xc90, 4),
+	MTK_PIN_IES_SMT_SPEC(260, 260, 0x3a0, 4),
+	MTK_PIN_IES_SMT_SPEC(261, 261, 0xd50, 4),
+	MTK_PIN_IES_SMT_SPEC(262, 277, 0xb40, 12),
+	MTK_PIN_IES_SMT_SPEC(278, 278, 0xb40, 13),
+};
+
+static const struct mtk_pin_ies_smt_set mt2701_smt_set[] = {
+	MTK_PIN_IES_SMT_SPEC(0, 6, 0xb50, 0),
+	MTK_PIN_IES_SMT_SPEC(7, 9, 0xb50, 1),
+	MTK_PIN_IES_SMT_SPEC(10, 13, 0xb60, 3),
+	MTK_PIN_IES_SMT_SPEC(14, 15, 0xb60, 13),
+	MTK_PIN_IES_SMT_SPEC(16, 17, 0xb70, 7),
+	MTK_PIN_IES_SMT_SPEC(18, 21, 0xb70, 13),
+	MTK_PIN_IES_SMT_SPEC(22, 26, 0xb70, 13),
+	MTK_PIN_IES_SMT_SPEC(27, 29, 0xb70, 13),
+	MTK_PIN_IES_SMT_SPEC(30, 32, 0xb70, 7),
+	MTK_PIN_IES_SMT_SPEC(33, 37, 0xb70, 13),
+	MTK_PIN_IES_SMT_SPEC(38, 38, 0xb50, 13),
+	MTK_PIN_IES_SMT_SPEC(39, 42, 0xb70, 13),
+	MTK_PIN_IES_SMT_SPEC(43, 45, 0xb50, 10),
+	MTK_PIN_IES_SMT_SPEC(47, 48, 0xb50, 11),
+	MTK_PIN_IES_SMT_SPEC(49, 49, 0xb50, 12),
+	MTK_PIN_IES_SMT_SPEC(50, 52, 0xb50, 13),
+	MTK_PIN_IES_SMT_SPEC(53, 56, 0xb50, 14),
+	MTK_PIN_IES_SMT_SPEC(57, 58, 0xb50, 15),
+	MTK_PIN_IES_SMT_SPEC(59, 59, 0xb60, 10),
+	MTK_PIN_IES_SMT_SPEC(60, 62, 0xb60, 0),
+	MTK_PIN_IES_SMT_SPEC(63, 65, 0xb60, 1),
+	MTK_PIN_IES_SMT_SPEC(66, 71, 0xb60, 2),
+	MTK_PIN_IES_SMT_SPEC(72, 74, 0xb50, 12),
+	MTK_PIN_IES_SMT_SPEC(75, 76, 0xb60, 3),
+	MTK_PIN_IES_SMT_SPEC(77, 78, 0xb60, 4),
+	MTK_PIN_IES_SMT_SPEC(79, 82, 0xb60, 5),
+	MTK_PIN_IES_SMT_SPEC(83, 84, 0xb60, 2),
+	MTK_PIN_IES_SMT_SPEC(85, 85, 0xda0, 11),
+	MTK_PIN_IES_SMT_SPEC(86, 86, 0xd90, 11),
+	MTK_PIN_IES_SMT_SPEC(87, 87, 0xdc0, 3),
+	MTK_PIN_IES_SMT_SPEC(88, 88, 0xdc0, 7),
+	MTK_PIN_IES_SMT_SPEC(89, 89, 0xdc0, 11),
+	MTK_PIN_IES_SMT_SPEC(90, 90, 0xdc0, 15),
+	MTK_PIN_IES_SMT_SPEC(101, 104, 0xb60, 6),
+	MTK_PIN_IES_SMT_SPEC(105, 105, 0xd40, 11),
+	MTK_PIN_IES_SMT_SPEC(106, 106, 0xd30, 11),
+	MTK_PIN_IES_SMT_SPEC(107, 107, 0xd60, 3),
+	MTK_PIN_IES_SMT_SPEC(108, 108, 0xd60, 7),
+	MTK_PIN_IES_SMT_SPEC(109, 109, 0xd60, 11),
+	MTK_PIN_IES_SMT_SPEC(110, 110, 0xd60, 15),
+	MTK_PIN_IES_SMT_SPEC(111, 111, 0xd00, 15),
+	MTK_PIN_IES_SMT_SPEC(112, 112, 0xd00, 11),
+	MTK_PIN_IES_SMT_SPEC(113, 113, 0xd00, 7),
+	MTK_PIN_IES_SMT_SPEC(114, 114, 0xd00, 3),
+	MTK_PIN_IES_SMT_SPEC(115, 115, 0xd10, 3),
+	MTK_PIN_IES_SMT_SPEC(116, 116, 0xcd0, 11),
+	MTK_PIN_IES_SMT_SPEC(117, 117, 0xcc0, 11),
+	MTK_PIN_IES_SMT_SPEC(118, 118, 0xcf0, 15),
+	MTK_PIN_IES_SMT_SPEC(119, 119, 0xcf0, 11),
+	MTK_PIN_IES_SMT_SPEC(120, 120, 0xcf0, 7),
+	MTK_PIN_IES_SMT_SPEC(121, 121, 0xcf0, 3),
+	MTK_PIN_IES_SMT_SPEC(122, 125, 0xb60, 7),
+	MTK_PIN_IES_SMT_SPEC(126, 126, 0xb50, 12),
+	MTK_PIN_IES_SMT_SPEC(127, 142, 0xb60, 9),
+	MTK_PIN_IES_SMT_SPEC(143, 160, 0xb60, 10),
+	MTK_PIN_IES_SMT_SPEC(161, 168, 0xb60, 12),
+	MTK_PIN_IES_SMT_SPEC(169, 183, 0xb60, 10),
+	MTK_PIN_IES_SMT_SPEC(184, 186, 0xb60, 9),
+	MTK_PIN_IES_SMT_SPEC(187, 187, 0xb60, 14),
+	MTK_PIN_IES_SMT_SPEC(188, 188, 0xb50, 13),
+	MTK_PIN_IES_SMT_SPEC(189, 193, 0xb60, 15),
+	MTK_PIN_IES_SMT_SPEC(194, 198, 0xb70, 0),
+	MTK_PIN_IES_SMT_SPEC(199, 199, 0xb50, 1),
+	MTK_PIN_IES_SMT_SPEC(200, 202, 0xb70, 1),
+	MTK_PIN_IES_SMT_SPEC(203, 207, 0xb70, 2),
+	MTK_PIN_IES_SMT_SPEC(208, 209, 0xb70, 3),
+	MTK_PIN_IES_SMT_SPEC(210, 210, 0xb70, 4),
+	MTK_PIN_IES_SMT_SPEC(211, 235, 0xb70, 5),
+	MTK_PIN_IES_SMT_SPEC(236, 241, 0xb70, 6),
+	MTK_PIN_IES_SMT_SPEC(242, 243, 0xb70, 7),
+	MTK_PIN_IES_SMT_SPEC(244, 247, 0xb70, 8),
+	MTK_PIN_IES_SMT_SPEC(248, 248, 0xb70, 9),
+	MTK_PIN_IES_SMT_SPEC(249, 249, 0x140, 3),
+	MTK_PIN_IES_SMT_SPEC(250, 250, 0x130, 15),
+	MTK_PIN_IES_SMT_SPEC(251, 251, 0x130, 11),
+	MTK_PIN_IES_SMT_SPEC(252, 252, 0x130, 7),
+	MTK_PIN_IES_SMT_SPEC(253, 253, 0x130, 3),
+	MTK_PIN_IES_SMT_SPEC(254, 254, 0xf40, 15),
+	MTK_PIN_IES_SMT_SPEC(255, 255, 0xf40, 11),
+	MTK_PIN_IES_SMT_SPEC(256, 256, 0xf40, 7),
+	MTK_PIN_IES_SMT_SPEC(257, 257, 0xf40, 3),
+	MTK_PIN_IES_SMT_SPEC(258, 258, 0xcb0, 11),
+	MTK_PIN_IES_SMT_SPEC(259, 259, 0xc90, 11),
+	MTK_PIN_IES_SMT_SPEC(260, 260, 0x3a0, 11),
+	MTK_PIN_IES_SMT_SPEC(261, 261, 0x0b0, 3),
+	MTK_PIN_IES_SMT_SPEC(262, 277, 0xb70, 12),
+	MTK_PIN_IES_SMT_SPEC(278, 278, 0xb70, 13),
+};
+
+static int mt2701_ies_smt_set(struct regmap *regmap, unsigned int pin,
+		unsigned char align, int value, enum pin_config_param arg)
+{
+	if (arg == PIN_CONFIG_INPUT_ENABLE)
+		return mtk_pconf_spec_set_ies_smt_range(regmap, mt2701_ies_set,
+			ARRAY_SIZE(mt2701_ies_set), pin, align, value);
+	else if (arg == PIN_CONFIG_INPUT_SCHMITT_ENABLE)
+		return mtk_pconf_spec_set_ies_smt_range(regmap, mt2701_smt_set,
+			ARRAY_SIZE(mt2701_smt_set), pin, align, value);
+	return -EINVAL;
+}
+
+static const struct mtk_spec_pinmux_set mt2701_spec_pinmux[] = {
+	MTK_PINMUX_SPEC(22, 0xb10, 3),
+	MTK_PINMUX_SPEC(23, 0xb10, 4),
+	MTK_PINMUX_SPEC(24, 0xb10, 5),
+	MTK_PINMUX_SPEC(29, 0xb10, 9),
+	MTK_PINMUX_SPEC(208, 0xb10, 7),
+	MTK_PINMUX_SPEC(209, 0xb10, 8),
+	MTK_PINMUX_SPEC(203, 0xf20, 0),
+	MTK_PINMUX_SPEC(204, 0xf20, 1),
+	MTK_PINMUX_SPEC(249, 0xef0, 0),
+	MTK_PINMUX_SPEC(250, 0xef0, 0),
+	MTK_PINMUX_SPEC(251, 0xef0, 0),
+	MTK_PINMUX_SPEC(252, 0xef0, 0),
+	MTK_PINMUX_SPEC(253, 0xef0, 0),
+	MTK_PINMUX_SPEC(254, 0xef0, 0),
+	MTK_PINMUX_SPEC(255, 0xef0, 0),
+	MTK_PINMUX_SPEC(256, 0xef0, 0),
+	MTK_PINMUX_SPEC(257, 0xef0, 0),
+	MTK_PINMUX_SPEC(258, 0xef0, 0),
+	MTK_PINMUX_SPEC(259, 0xef0, 0),
+	MTK_PINMUX_SPEC(260, 0xef0, 0),
+};
+
+static void mt2701_spec_pinmux_set(struct regmap *reg, unsigned int pin,
+			unsigned int mode)
+{
+	unsigned int i, value, mask;
+	unsigned int info_num = ARRAY_SIZE(mt2701_spec_pinmux);
+	unsigned int spec_flag;
+
+	for (i = 0; i < info_num; i++) {
+		if (pin == mt2701_spec_pinmux[i].pin)
+			break;
+	}
+
+	if (i == info_num)
+		return;
+
+	spec_flag = (mode >> 3);
+	mask = BIT(mt2701_spec_pinmux[i].bit);
+	if (!spec_flag)
+		value = mask;
+	else
+		value = 0;
+	regmap_update_bits(reg, mt2701_spec_pinmux[i].offset, mask, value);
+}
+
+static void mt2701_spec_dir_set(unsigned int *reg_addr, unsigned int pin)
+{
+	if (pin > 175)
+		*reg_addr += 0x10;
+}
+
+static const struct mtk_pinctrl_devdata mt2701_pinctrl_data = {
+	.pins = mtk_pins_mt2701,
+	.npins = ARRAY_SIZE(mtk_pins_mt2701),
+	.grp_desc = mt2701_drv_grp,
+	.n_grp_cls = ARRAY_SIZE(mt2701_drv_grp),
+	.pin_drv_grp = mt2701_pin_drv,
+	.n_pin_drv_grps = ARRAY_SIZE(mt2701_pin_drv),
+	.spec_pull_set = mt2701_spec_pull_set,
+	.spec_ies_smt_set = mt2701_ies_smt_set,
+	.spec_pinmux_set = mt2701_spec_pinmux_set,
+	.spec_dir_set = mt2701_spec_dir_set,
+	.dir_offset = 0x0000,
+	.pullen_offset = 0x0150,
+	.pullsel_offset = 0x0280,
+	.dout_offset = 0x0500,
+	.din_offset = 0x0630,
+	.pinmux_offset = 0x0760,
+	.type1_start = 280,
+	.type1_end = 280,
+	.port_shf = 4,
+	.port_mask = 0x1f,
+	.port_align = 4,
+	.eint_offsets = {
+		.name = "mt2701_eint",
+		.stat      = 0x000,
+		.ack       = 0x040,
+		.mask      = 0x080,
+		.mask_set  = 0x0c0,
+		.mask_clr  = 0x100,
+		.sens      = 0x140,
+		.sens_set  = 0x180,
+		.sens_clr  = 0x1c0,
+		.soft      = 0x200,
+		.soft_set  = 0x240,
+		.soft_clr  = 0x280,
+		.pol       = 0x300,
+		.pol_set   = 0x340,
+		.pol_clr   = 0x380,
+		.dom_en    = 0x400,
+		.dbnc_ctrl = 0x500,
+		.dbnc_set  = 0x600,
+		.dbnc_clr  = 0x700,
+		.port_mask = 6,
+		.ports     = 6,
+	},
+	.ap_num = 169,
+	.db_cnt = 16,
+};
+
+static int mt2701_pinctrl_probe(struct platform_device *pdev)
+{
+	return mtk_pctrl_init(pdev, &mt2701_pinctrl_data, NULL);
+}
+
+static const struct of_device_id mt2701_pctrl_match[] = {
+	{ .compatible = "mediatek,mt2701-pinctrl", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, mt2701_pctrl_match);
+
+static struct platform_driver mtk_pinctrl_driver = {
+	.probe = mt2701_pinctrl_probe,
+	.driver = {
+		.name = "mediatek-mt2701-pinctrl",
+		.of_match_table = mt2701_pctrl_match,
+		.pm = &mtk_eint_pm_ops,
+	},
+};
+
+static int __init mtk_pinctrl_init(void)
+{
+	return platform_driver_register(&mtk_pinctrl_driver);
+}
+arch_initcall(mtk_pinctrl_init);
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt6397.c b/drivers/pinctrl/mediatek/pinctrl-mt6397.c
index f9751ae28e32..6eccb85c02cd 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt6397.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt6397.c
@@ -12,7 +12,7 @@
  * GNU General Public License for more details.
  */
 
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
@@ -55,7 +55,6 @@ static const struct of_device_id mt6397_pctrl_match[] = {
 	{ .compatible = "mediatek,mt6397-pinctrl", },
 	{ }
 };
-MODULE_DEVICE_TABLE(of, mt6397_pctrl_match);
 
 static struct platform_driver mtk_pinctrl_driver = {
 	.probe = mt6397_pinctrl_probe,
@@ -69,9 +68,4 @@ static int __init mtk_pinctrl_init(void)
 {
 	return platform_driver_register(&mtk_pinctrl_driver);
 }
-
-module_init(mtk_pinctrl_init);
-
-MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("MediaTek MT6397 Pinctrl Driver");
-MODULE_AUTHOR("Hongzhou Yang <hongzhou.yang@mediatek.com>");
+device_initcall(mtk_pinctrl_init);
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt7623.c b/drivers/pinctrl/mediatek/pinctrl-mt7623.c
new file mode 100644
index 000000000000..67895f8234e3
--- /dev/null
+++ b/drivers/pinctrl/mediatek/pinctrl-mt7623.c
@@ -0,0 +1,379 @@
+/*
+ * Copyright (c) 2016 John Crispin <blogic@openwrt.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <dt-bindings/pinctrl/mt65xx.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/regmap.h>
+
+#include "pinctrl-mtk-common.h"
+#include "pinctrl-mtk-mt7623.h"
+
+static const struct mtk_drv_group_desc mt7623_drv_grp[] =  {
+	/* 0E4E8SR 4/8/12/16 */
+	MTK_DRV_GRP(4, 16, 1, 2, 4),
+	/* 0E2E4SR  2/4/6/8 */
+	MTK_DRV_GRP(2, 8, 1, 2, 2),
+	/* E8E4E2  2/4/6/8/10/12/14/16 */
+	MTK_DRV_GRP(2, 16, 0, 2, 2)
+};
+
+#define DRV_SEL0	0xf50
+#define DRV_SEL1	0xf60
+#define DRV_SEL2	0xf70
+#define DRV_SEL3	0xf80
+#define DRV_SEL4	0xf90
+#define DRV_SEL5	0xfa0
+#define DRV_SEL6	0xfb0
+#define DRV_SEL7	0xfe0
+#define DRV_SEL8	0xfd0
+#define DRV_SEL9	0xff0
+#define DRV_SEL10	0xf00
+
+#define MSDC0_CTRL0	0xcc0
+#define MSDC0_CTRL1	0xcd0
+#define MSDC0_CTRL2	0xce0
+#define MSDC0_CTRL3	0xcf0
+#define MSDC0_CTRL4	0xd00
+#define MSDC0_CTRL5	0xd10
+#define MSDC0_CTRL6	0xd20
+#define MSDC1_CTRL0	0xd30
+#define MSDC1_CTRL1	0xd40
+#define MSDC1_CTRL2	0xd50
+#define MSDC1_CTRL3	0xd60
+#define MSDC1_CTRL4	0xd70
+#define MSDC1_CTRL5	0xd80
+#define MSDC1_CTRL6	0xd90
+
+#define IES_EN0		0xb20
+#define IES_EN1		0xb30
+#define IES_EN2		0xb40
+
+#define SMT_EN0		0xb50
+#define SMT_EN1		0xb60
+#define SMT_EN2		0xb70
+
+static const struct mtk_pin_drv_grp mt7623_pin_drv[] = {
+	MTK_PIN_DRV_GRP(0, DRV_SEL0, 0, 1),
+	MTK_PIN_DRV_GRP(1, DRV_SEL0, 0, 1),
+	MTK_PIN_DRV_GRP(2, DRV_SEL0, 0, 1),
+	MTK_PIN_DRV_GRP(3, DRV_SEL0, 0, 1),
+	MTK_PIN_DRV_GRP(4, DRV_SEL0, 0, 1),
+	MTK_PIN_DRV_GRP(5, DRV_SEL0, 0, 1),
+	MTK_PIN_DRV_GRP(6, DRV_SEL0, 0, 1),
+	MTK_PIN_DRV_GRP(7, DRV_SEL0, 4, 1),
+	MTK_PIN_DRV_GRP(8, DRV_SEL0, 4, 1),
+	MTK_PIN_DRV_GRP(9, DRV_SEL0, 4, 1),
+	MTK_PIN_DRV_GRP(10, DRV_SEL0, 8, 1),
+	MTK_PIN_DRV_GRP(11, DRV_SEL0, 8, 1),
+	MTK_PIN_DRV_GRP(12, DRV_SEL0, 8, 1),
+	MTK_PIN_DRV_GRP(13, DRV_SEL0, 8, 1),
+	MTK_PIN_DRV_GRP(14, DRV_SEL0, 12, 0),
+	MTK_PIN_DRV_GRP(15, DRV_SEL0, 12, 0),
+	MTK_PIN_DRV_GRP(18, DRV_SEL1, 4, 0),
+	MTK_PIN_DRV_GRP(19, DRV_SEL1, 4, 0),
+	MTK_PIN_DRV_GRP(20, DRV_SEL1, 4, 0),
+	MTK_PIN_DRV_GRP(21, DRV_SEL1, 4, 0),
+	MTK_PIN_DRV_GRP(22, DRV_SEL1, 8, 0),
+	MTK_PIN_DRV_GRP(23, DRV_SEL1, 8, 0),
+	MTK_PIN_DRV_GRP(24, DRV_SEL1, 8, 0),
+	MTK_PIN_DRV_GRP(25, DRV_SEL1, 8, 0),
+	MTK_PIN_DRV_GRP(26, DRV_SEL1, 8, 0),
+	MTK_PIN_DRV_GRP(27, DRV_SEL1, 12, 0),
+	MTK_PIN_DRV_GRP(28, DRV_SEL1, 12, 0),
+	MTK_PIN_DRV_GRP(29, DRV_SEL1, 12, 0),
+	MTK_PIN_DRV_GRP(33, DRV_SEL2, 0, 0),
+	MTK_PIN_DRV_GRP(34, DRV_SEL2, 0, 0),
+	MTK_PIN_DRV_GRP(35, DRV_SEL2, 0, 0),
+	MTK_PIN_DRV_GRP(36, DRV_SEL2, 0, 0),
+	MTK_PIN_DRV_GRP(37, DRV_SEL2, 0, 0),
+	MTK_PIN_DRV_GRP(39, DRV_SEL2, 8, 1),
+	MTK_PIN_DRV_GRP(40, DRV_SEL2, 8, 1),
+	MTK_PIN_DRV_GRP(41, DRV_SEL2, 8, 1),
+	MTK_PIN_DRV_GRP(42, DRV_SEL2, 8, 1),
+	MTK_PIN_DRV_GRP(43, DRV_SEL2, 12, 0),
+	MTK_PIN_DRV_GRP(44, DRV_SEL2, 12, 0),
+	MTK_PIN_DRV_GRP(45, DRV_SEL2, 12, 0),
+	MTK_PIN_DRV_GRP(47, DRV_SEL3, 0, 0),
+	MTK_PIN_DRV_GRP(48, DRV_SEL3, 0, 0),
+	MTK_PIN_DRV_GRP(49, DRV_SEL3, 4, 0),
+	MTK_PIN_DRV_GRP(53, DRV_SEL3, 12, 0),
+	MTK_PIN_DRV_GRP(54, DRV_SEL3, 12, 0),
+	MTK_PIN_DRV_GRP(55, DRV_SEL3, 12, 0),
+	MTK_PIN_DRV_GRP(56, DRV_SEL3, 12, 0),
+	MTK_PIN_DRV_GRP(60, DRV_SEL4, 8, 1),
+	MTK_PIN_DRV_GRP(61, DRV_SEL4, 8, 1),
+	MTK_PIN_DRV_GRP(62, DRV_SEL4, 8, 1),
+	MTK_PIN_DRV_GRP(63, DRV_SEL4, 12, 1),
+	MTK_PIN_DRV_GRP(64, DRV_SEL4, 12, 1),
+	MTK_PIN_DRV_GRP(65, DRV_SEL4, 12, 1),
+	MTK_PIN_DRV_GRP(66, DRV_SEL5, 0, 1),
+	MTK_PIN_DRV_GRP(67, DRV_SEL5, 0, 1),
+	MTK_PIN_DRV_GRP(68, DRV_SEL5, 0, 1),
+	MTK_PIN_DRV_GRP(69, DRV_SEL5, 0, 1),
+	MTK_PIN_DRV_GRP(70, DRV_SEL5, 0, 1),
+	MTK_PIN_DRV_GRP(71, DRV_SEL5, 0, 1),
+	MTK_PIN_DRV_GRP(72, DRV_SEL3, 4, 0),
+	MTK_PIN_DRV_GRP(73, DRV_SEL3, 4, 0),
+	MTK_PIN_DRV_GRP(74, DRV_SEL3, 4, 0),
+	MTK_PIN_DRV_GRP(83, DRV_SEL5, 0, 1),
+	MTK_PIN_DRV_GRP(84, DRV_SEL5, 0, 1),
+	MTK_PIN_DRV_GRP(105, MSDC1_CTRL1, 0, 1),
+	MTK_PIN_DRV_GRP(106, MSDC1_CTRL0, 0, 1),
+	MTK_PIN_DRV_GRP(107, MSDC1_CTRL2, 0, 1),
+	MTK_PIN_DRV_GRP(108, MSDC1_CTRL2, 0, 1),
+	MTK_PIN_DRV_GRP(109, MSDC1_CTRL2, 0, 1),
+	MTK_PIN_DRV_GRP(110, MSDC1_CTRL2, 0, 1),
+	MTK_PIN_DRV_GRP(111, MSDC0_CTRL2, 0, 1),
+	MTK_PIN_DRV_GRP(112, MSDC0_CTRL2, 0, 1),
+	MTK_PIN_DRV_GRP(113, MSDC0_CTRL2, 0, 1),
+	MTK_PIN_DRV_GRP(114, MSDC0_CTRL2, 0, 1),
+	MTK_PIN_DRV_GRP(115, MSDC0_CTRL2, 0, 1),
+	MTK_PIN_DRV_GRP(116, MSDC0_CTRL1, 0, 1),
+	MTK_PIN_DRV_GRP(117, MSDC0_CTRL0, 0, 1),
+	MTK_PIN_DRV_GRP(118, MSDC0_CTRL2, 0, 1),
+	MTK_PIN_DRV_GRP(119, MSDC0_CTRL2, 0, 1),
+	MTK_PIN_DRV_GRP(120, MSDC0_CTRL2, 0, 1),
+	MTK_PIN_DRV_GRP(121, MSDC0_CTRL2, 0, 1),
+	MTK_PIN_DRV_GRP(126, DRV_SEL3, 4, 0),
+	MTK_PIN_DRV_GRP(199, DRV_SEL0, 4, 1),
+	MTK_PIN_DRV_GRP(200, DRV_SEL8, 0, 0),
+	MTK_PIN_DRV_GRP(201, DRV_SEL8, 0, 0),
+	MTK_PIN_DRV_GRP(203, DRV_SEL8, 4, 0),
+	MTK_PIN_DRV_GRP(204, DRV_SEL8, 4, 0),
+	MTK_PIN_DRV_GRP(205, DRV_SEL8, 4, 0),
+	MTK_PIN_DRV_GRP(206, DRV_SEL8, 4, 0),
+	MTK_PIN_DRV_GRP(207, DRV_SEL8, 4, 0),
+	MTK_PIN_DRV_GRP(208, DRV_SEL8, 8, 0),
+	MTK_PIN_DRV_GRP(209, DRV_SEL8, 8, 0),
+	MTK_PIN_DRV_GRP(236, DRV_SEL9, 4, 0),
+	MTK_PIN_DRV_GRP(237, DRV_SEL9, 4, 0),
+	MTK_PIN_DRV_GRP(238, DRV_SEL9, 4, 0),
+	MTK_PIN_DRV_GRP(239, DRV_SEL9, 4, 0),
+	MTK_PIN_DRV_GRP(240, DRV_SEL9, 4, 0),
+	MTK_PIN_DRV_GRP(241, DRV_SEL9, 4, 0),
+	MTK_PIN_DRV_GRP(242, DRV_SEL9, 8, 0),
+	MTK_PIN_DRV_GRP(243, DRV_SEL9, 8, 0),
+	MTK_PIN_DRV_GRP(257, MSDC0_CTRL2, 0, 1),
+	MTK_PIN_DRV_GRP(261, MSDC1_CTRL2, 0, 1),
+	MTK_PIN_DRV_GRP(262, DRV_SEL10, 8, 0),
+	MTK_PIN_DRV_GRP(263, DRV_SEL10, 8, 0),
+	MTK_PIN_DRV_GRP(264, DRV_SEL10, 8, 0),
+	MTK_PIN_DRV_GRP(265, DRV_SEL10, 8, 0),
+	MTK_PIN_DRV_GRP(266, DRV_SEL10, 8, 0),
+	MTK_PIN_DRV_GRP(267, DRV_SEL10, 8, 0),
+	MTK_PIN_DRV_GRP(268, DRV_SEL10, 8, 0),
+	MTK_PIN_DRV_GRP(269, DRV_SEL10, 8, 0),
+	MTK_PIN_DRV_GRP(270, DRV_SEL10, 8, 0),
+	MTK_PIN_DRV_GRP(271, DRV_SEL10, 8, 0),
+	MTK_PIN_DRV_GRP(272, DRV_SEL10, 8, 0),
+	MTK_PIN_DRV_GRP(274, DRV_SEL10, 8, 0),
+	MTK_PIN_DRV_GRP(275, DRV_SEL10, 8, 0),
+	MTK_PIN_DRV_GRP(276, DRV_SEL10, 8, 0),
+	MTK_PIN_DRV_GRP(278, DRV_SEL2, 8, 1),
+};
+
+static const struct mtk_pin_spec_pupd_set_samereg mt7623_spec_pupd[] = {
+	MTK_PIN_PUPD_SPEC_SR(105, MSDC1_CTRL1, 8, 9, 10),
+	MTK_PIN_PUPD_SPEC_SR(106, MSDC1_CTRL0, 8, 9, 10),
+	MTK_PIN_PUPD_SPEC_SR(107, MSDC1_CTRL3, 0, 1, 2),
+	MTK_PIN_PUPD_SPEC_SR(108, MSDC1_CTRL3, 4, 5, 6),
+	MTK_PIN_PUPD_SPEC_SR(109, MSDC1_CTRL3, 8, 9, 10),
+	MTK_PIN_PUPD_SPEC_SR(110, MSDC1_CTRL3, 12, 13, 14),
+	MTK_PIN_PUPD_SPEC_SR(111, MSDC0_CTRL4, 12, 13, 14),
+	MTK_PIN_PUPD_SPEC_SR(112, MSDC0_CTRL4, 8, 9, 10),
+	MTK_PIN_PUPD_SPEC_SR(113, MSDC0_CTRL4, 4, 5, 6),
+	MTK_PIN_PUPD_SPEC_SR(114, MSDC0_CTRL4, 0, 1, 2),
+	MTK_PIN_PUPD_SPEC_SR(115, MSDC0_CTRL5, 0, 1, 2),
+	MTK_PIN_PUPD_SPEC_SR(116, MSDC0_CTRL1, 8, 9, 10),
+	MTK_PIN_PUPD_SPEC_SR(117, MSDC0_CTRL0, 8, 9, 10),
+	MTK_PIN_PUPD_SPEC_SR(118, MSDC0_CTRL3, 12, 13, 14),
+	MTK_PIN_PUPD_SPEC_SR(119, MSDC0_CTRL3, 8, 9, 10),
+	MTK_PIN_PUPD_SPEC_SR(120, MSDC0_CTRL3, 4, 5, 6),
+	MTK_PIN_PUPD_SPEC_SR(121, MSDC0_CTRL3, 0, 1, 2),
+};
+
+static int mt7623_spec_pull_set(struct regmap *regmap, unsigned int pin,
+		unsigned char align, bool isup, unsigned int r1r0)
+{
+	return mtk_pctrl_spec_pull_set_samereg(regmap, mt7623_spec_pupd,
+		ARRAY_SIZE(mt7623_spec_pupd), pin, align, isup, r1r0);
+}
+
+static const struct mtk_pin_ies_smt_set mt7623_ies_set[] = {
+	MTK_PIN_IES_SMT_SPEC(0, 6, IES_EN0, 0),
+	MTK_PIN_IES_SMT_SPEC(7, 9, IES_EN0, 1),
+	MTK_PIN_IES_SMT_SPEC(10, 13, IES_EN0, 2),
+	MTK_PIN_IES_SMT_SPEC(14, 15, IES_EN0, 3),
+	MTK_PIN_IES_SMT_SPEC(18, 21, IES_EN0, 5),
+	MTK_PIN_IES_SMT_SPEC(22, 26, IES_EN0, 6),
+	MTK_PIN_IES_SMT_SPEC(27, 29, IES_EN0, 7),
+	MTK_PIN_IES_SMT_SPEC(33, 37, IES_EN0, 8),
+	MTK_PIN_IES_SMT_SPEC(39, 42, IES_EN0, 9),
+	MTK_PIN_IES_SMT_SPEC(43, 45, IES_EN0, 10),
+	MTK_PIN_IES_SMT_SPEC(47, 48, IES_EN0, 11),
+	MTK_PIN_IES_SMT_SPEC(49, 49, IES_EN0, 12),
+	MTK_PIN_IES_SMT_SPEC(53, 56, IES_EN0, 14),
+	MTK_PIN_IES_SMT_SPEC(60, 62, IES_EN1, 0),
+	MTK_PIN_IES_SMT_SPEC(63, 65, IES_EN1, 1),
+	MTK_PIN_IES_SMT_SPEC(66, 71, IES_EN1, 2),
+	MTK_PIN_IES_SMT_SPEC(72, 74, IES_EN0, 12),
+	MTK_PIN_IES_SMT_SPEC(75, 76, IES_EN1, 3),
+	MTK_PIN_IES_SMT_SPEC(83, 84, IES_EN1, 2),
+	MTK_PIN_IES_SMT_SPEC(105, 121, MSDC1_CTRL1, 4),
+	MTK_PIN_IES_SMT_SPEC(122, 125, IES_EN1, 7),
+	MTK_PIN_IES_SMT_SPEC(126, 126, IES_EN0, 12),
+	MTK_PIN_IES_SMT_SPEC(199, 201, IES_EN0, 1),
+	MTK_PIN_IES_SMT_SPEC(203, 207, IES_EN2, 2),
+	MTK_PIN_IES_SMT_SPEC(208, 209, IES_EN2, 3),
+	MTK_PIN_IES_SMT_SPEC(236, 241, IES_EN2, 6),
+	MTK_PIN_IES_SMT_SPEC(242, 243, IES_EN2, 7),
+	MTK_PIN_IES_SMT_SPEC(261, 261, MSDC1_CTRL2, 4),
+	MTK_PIN_IES_SMT_SPEC(262, 272, IES_EN2, 12),
+	MTK_PIN_IES_SMT_SPEC(274, 276, IES_EN2, 12),
+	MTK_PIN_IES_SMT_SPEC(278, 278, IES_EN2, 13),
+};
+
+static const struct mtk_pin_ies_smt_set mt7623_smt_set[] = {
+	MTK_PIN_IES_SMT_SPEC(0, 6, SMT_EN0, 0),
+	MTK_PIN_IES_SMT_SPEC(7, 9, SMT_EN0, 1),
+	MTK_PIN_IES_SMT_SPEC(10, 13, SMT_EN0, 2),
+	MTK_PIN_IES_SMT_SPEC(14, 15, SMT_EN0, 3),
+	MTK_PIN_IES_SMT_SPEC(18, 21, SMT_EN0, 5),
+	MTK_PIN_IES_SMT_SPEC(22, 26, SMT_EN0, 6),
+	MTK_PIN_IES_SMT_SPEC(27, 29, SMT_EN0, 7),
+	MTK_PIN_IES_SMT_SPEC(33, 37, SMT_EN0, 8),
+	MTK_PIN_IES_SMT_SPEC(39, 42, SMT_EN0, 9),
+	MTK_PIN_IES_SMT_SPEC(43, 45, SMT_EN0, 10),
+	MTK_PIN_IES_SMT_SPEC(47, 48, SMT_EN0, 11),
+	MTK_PIN_IES_SMT_SPEC(49, 49, SMT_EN0, 12),
+	MTK_PIN_IES_SMT_SPEC(53, 56, SMT_EN0, 14),
+	MTK_PIN_IES_SMT_SPEC(60, 62, SMT_EN1, 0),
+	MTK_PIN_IES_SMT_SPEC(63, 65, SMT_EN1, 1),
+	MTK_PIN_IES_SMT_SPEC(66, 71, SMT_EN1, 2),
+	MTK_PIN_IES_SMT_SPEC(72, 74, SMT_EN0, 12),
+	MTK_PIN_IES_SMT_SPEC(75, 76, SMT_EN1, 3),
+	MTK_PIN_IES_SMT_SPEC(83, 84, SMT_EN1, 2),
+	MTK_PIN_IES_SMT_SPEC(105, 106, MSDC1_CTRL1, 11),
+	MTK_PIN_IES_SMT_SPEC(107, 107, MSDC1_CTRL3, 3),
+	MTK_PIN_IES_SMT_SPEC(108, 108, MSDC1_CTRL3, 7),
+	MTK_PIN_IES_SMT_SPEC(109, 109, MSDC1_CTRL3, 11),
+	MTK_PIN_IES_SMT_SPEC(110, 111, MSDC1_CTRL3, 15),
+	MTK_PIN_IES_SMT_SPEC(112, 112, MSDC0_CTRL4, 11),
+	MTK_PIN_IES_SMT_SPEC(113, 113, MSDC0_CTRL4, 7),
+	MTK_PIN_IES_SMT_SPEC(114, 115, MSDC0_CTRL4, 3),
+	MTK_PIN_IES_SMT_SPEC(116, 117, MSDC0_CTRL1, 11),
+	MTK_PIN_IES_SMT_SPEC(118, 118, MSDC0_CTRL3, 15),
+	MTK_PIN_IES_SMT_SPEC(119, 119, MSDC0_CTRL3, 11),
+	MTK_PIN_IES_SMT_SPEC(120, 120, MSDC0_CTRL3, 7),
+	MTK_PIN_IES_SMT_SPEC(121, 121, MSDC0_CTRL3, 3),
+	MTK_PIN_IES_SMT_SPEC(122, 125, SMT_EN1, 7),
+	MTK_PIN_IES_SMT_SPEC(126, 126, SMT_EN0, 12),
+	MTK_PIN_IES_SMT_SPEC(199, 201, SMT_EN0, 1),
+	MTK_PIN_IES_SMT_SPEC(203, 207, SMT_EN2, 2),
+	MTK_PIN_IES_SMT_SPEC(208, 209, SMT_EN2, 3),
+	MTK_PIN_IES_SMT_SPEC(236, 241, SMT_EN2, 6),
+	MTK_PIN_IES_SMT_SPEC(242, 243, SMT_EN2, 7),
+	MTK_PIN_IES_SMT_SPEC(261, 261, MSDC1_CTRL6, 3),
+	MTK_PIN_IES_SMT_SPEC(262, 272, SMT_EN2, 12),
+	MTK_PIN_IES_SMT_SPEC(274, 276, SMT_EN2, 12),
+	MTK_PIN_IES_SMT_SPEC(278, 278, SMT_EN2, 13),
+};
+
+static int mt7623_ies_smt_set(struct regmap *regmap, unsigned int pin,
+		unsigned char align, int value, enum pin_config_param arg)
+{
+	if (arg == PIN_CONFIG_INPUT_ENABLE)
+		return mtk_pconf_spec_set_ies_smt_range(regmap, mt7623_ies_set,
+			ARRAY_SIZE(mt7623_ies_set), pin, align, value);
+	else if (arg == PIN_CONFIG_INPUT_SCHMITT_ENABLE)
+		return mtk_pconf_spec_set_ies_smt_range(regmap, mt7623_smt_set,
+			ARRAY_SIZE(mt7623_smt_set), pin, align, value);
+	return -EINVAL;
+}
+
+static const struct mtk_pinctrl_devdata mt7623_pinctrl_data = {
+	.pins = mtk_pins_mt7623,
+	.npins = ARRAY_SIZE(mtk_pins_mt7623),
+	.grp_desc = mt7623_drv_grp,
+	.n_grp_cls = ARRAY_SIZE(mt7623_drv_grp),
+	.pin_drv_grp = mt7623_pin_drv,
+	.n_pin_drv_grps = ARRAY_SIZE(mt7623_pin_drv),
+	.spec_pull_set = mt7623_spec_pull_set,
+	.spec_ies_smt_set = mt7623_ies_smt_set,
+	.dir_offset = 0x0000,
+	.pullen_offset = 0x0150,
+	.pullsel_offset = 0x0280,
+	.dout_offset = 0x0500,
+	.din_offset = 0x0630,
+	.pinmux_offset = 0x0760,
+	.type1_start = 280,
+	.type1_end = 280,
+	.port_shf = 4,
+	.port_mask = 0x1f,
+	.port_align = 4,
+	.eint_offsets = {
+		.name = "mt7623_eint",
+		.stat      = 0x000,
+		.ack       = 0x040,
+		.mask      = 0x080,
+		.mask_set  = 0x0c0,
+		.mask_clr  = 0x100,
+		.sens      = 0x140,
+		.sens_set  = 0x180,
+		.sens_clr  = 0x1c0,
+		.soft      = 0x200,
+		.soft_set  = 0x240,
+		.soft_clr  = 0x280,
+		.pol       = 0x300,
+		.pol_set   = 0x340,
+		.pol_clr   = 0x380,
+		.dom_en    = 0x400,
+		.dbnc_ctrl = 0x500,
+		.dbnc_set  = 0x600,
+		.dbnc_clr  = 0x700,
+		.port_mask = 6,
+		.ports     = 6,
+	},
+	.ap_num = 169,
+	.db_cnt = 16,
+};
+
+static int mt7623_pinctrl_probe(struct platform_device *pdev)
+{
+	return mtk_pctrl_init(pdev, &mt7623_pinctrl_data, NULL);
+}
+
+static const struct of_device_id mt7623_pctrl_match[] = {
+	{ .compatible = "mediatek,mt7623-pinctrl", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, mt7623_pctrl_match);
+
+static struct platform_driver mtk_pinctrl_driver = {
+	.probe = mt7623_pinctrl_probe,
+	.driver = {
+		.name = "mediatek-mt7623-pinctrl",
+		.of_match_table = mt7623_pctrl_match,
+	},
+};
+
+static int __init mtk_pinctrl_init(void)
+{
+	return platform_driver_register(&mtk_pinctrl_driver);
+}
+
+arch_initcall(mtk_pinctrl_init);
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8127.c b/drivers/pinctrl/mediatek/pinctrl-mt8127.c
index 98e0bebfdf92..d76491574841 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8127.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8127.c
@@ -13,7 +13,7 @@
  * GNU General Public License for more details.
  */
 
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
@@ -336,7 +336,6 @@ static const struct of_device_id mt8127_pctrl_match[] = {
 	{ .compatible = "mediatek,mt8127-pinctrl", },
 	{ }
 };
-MODULE_DEVICE_TABLE(of, mt8127_pctrl_match);
 
 static struct platform_driver mtk_pinctrl_driver = {
 	.probe = mt8127_pinctrl_probe,
@@ -350,9 +349,4 @@ static int __init mtk_pinctrl_init(void)
 {
 	return platform_driver_register(&mtk_pinctrl_driver);
 }
-
 arch_initcall(mtk_pinctrl_init);
-
-MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("MediaTek MT8127 Pinctrl Driver");
-MODULE_AUTHOR("Yingjoe Chen <yingjoe.chen@mediatek.com>");
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8135.c b/drivers/pinctrl/mediatek/pinctrl-mt8135.c
index 1c153b860f36..d8c645f16f21 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8135.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8135.c
@@ -12,7 +12,7 @@
  * GNU General Public License for more details.
  */
 
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
@@ -351,7 +351,6 @@ static const struct of_device_id mt8135_pctrl_match[] = {
 	},
 	{ }
 };
-MODULE_DEVICE_TABLE(of, mt8135_pctrl_match);
 
 static struct platform_driver mtk_pinctrl_driver = {
 	.probe = mt8135_pinctrl_probe,
@@ -365,9 +364,4 @@ static int __init mtk_pinctrl_init(void)
 {
 	return platform_driver_register(&mtk_pinctrl_driver);
 }
-
 arch_initcall(mtk_pinctrl_init);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("MediaTek Pinctrl Driver");
-MODULE_AUTHOR("Hongzhou Yang <hongzhou.yang@mediatek.com>");
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8173.c b/drivers/pinctrl/mediatek/pinctrl-mt8173.c
index a62514eb2129..8bfd427b9135 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt8173.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt8173.c
@@ -12,7 +12,7 @@
  * GNU General Public License for more details.
  */
 
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
@@ -378,7 +378,6 @@ static const struct of_device_id mt8173_pctrl_match[] = {
 	},
 	{ }
 };
-MODULE_DEVICE_TABLE(of, mt8173_pctrl_match);
 
 static struct platform_driver mtk_pinctrl_driver = {
 	.probe = mt8173_pinctrl_probe,
@@ -393,9 +392,4 @@ static int __init mtk_pinctrl_init(void)
 {
 	return platform_driver_register(&mtk_pinctrl_driver);
 }
-
 arch_initcall(mtk_pinctrl_init);
-
-MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("MediaTek Pinctrl Driver");
-MODULE_AUTHOR("Hongzhou Yang <hongzhou.yang@mediatek.com>");
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
index 16d48a4ed225..2bbe6f7964a7 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
@@ -43,10 +43,13 @@
 
 #define MAX_GPIO_MODE_PER_REG 5
 #define GPIO_MODE_BITS        3
+#define GPIO_MODE_PREFIX "GPIO"
 
 static const char * const mtk_gpio_functions[] = {
 	"func0", "func1", "func2", "func3",
 	"func4", "func5", "func6", "func7",
+	"func8", "func9", "func10", "func11",
+	"func12", "func13", "func14", "func15",
 };
 
 /*
@@ -81,6 +84,9 @@ static int mtk_pmx_gpio_set_direction(struct pinctrl_dev *pctldev,
 	reg_addr = mtk_get_port(pctl, offset) + pctl->devdata->dir_offset;
 	bit = BIT(offset & 0xf);
 
+	if (pctl->devdata->spec_dir_set)
+		pctl->devdata->spec_dir_set(&reg_addr, offset);
+
 	if (input)
 		/* Different SoC has different alignment offset. */
 		reg_addr = CLR_ADDR(reg_addr, pctl);
@@ -347,6 +353,7 @@ static int mtk_pconf_parse_conf(struct pinctrl_dev *pctldev,
 		ret = mtk_pconf_set_pull_select(pctl, pin, true, false, arg);
 		break;
 	case PIN_CONFIG_INPUT_ENABLE:
+		mtk_pmx_gpio_set_direction(pctldev, NULL, pin, true);
 		ret = mtk_pconf_set_ies_smt(pctl, pin, arg, param);
 		break;
 	case PIN_CONFIG_OUTPUT:
@@ -354,6 +361,7 @@ static int mtk_pconf_parse_conf(struct pinctrl_dev *pctldev,
 		ret = mtk_pmx_gpio_set_direction(pctldev, NULL, pin, false);
 		break;
 	case PIN_CONFIG_INPUT_SCHMITT_ENABLE:
+		mtk_pmx_gpio_set_direction(pctldev, NULL, pin, true);
 		ret = mtk_pconf_set_ies_smt(pctl, pin, arg, param);
 		break;
 	case PIN_CONFIG_DRIVE_STRENGTH:
@@ -675,9 +683,14 @@ static int mtk_pmx_set_mode(struct pinctrl_dev *pctldev,
 	unsigned int mask = (1L << GPIO_MODE_BITS) - 1;
 	struct mtk_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
 
+	if (pctl->devdata->spec_pinmux_set)
+		pctl->devdata->spec_pinmux_set(mtk_get_regmap(pctl, pin),
+					pin, mode);
+
 	reg_addr = ((pin / MAX_GPIO_MODE_PER_REG) << pctl->devdata->port_shf)
 			+ pctl->devdata->pinmux_offset;
 
+	mode &= mask;
 	bit = pin % MAX_GPIO_MODE_PER_REG;
 	mask <<= (GPIO_MODE_BITS * bit);
 	val = (mode << (GPIO_MODE_BITS * bit));
@@ -723,12 +736,48 @@ static int mtk_pmx_set_mux(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
+static int mtk_pmx_find_gpio_mode(struct mtk_pinctrl *pctl,
+				unsigned offset)
+{
+	const struct mtk_desc_pin *pin = pctl->devdata->pins + offset;
+	const struct mtk_desc_function *func = pin->functions;
+
+	while (func && func->name) {
+		if (!strncmp(func->name, GPIO_MODE_PREFIX,
+			sizeof(GPIO_MODE_PREFIX)-1))
+			return func->muxval;
+		func++;
+	}
+	return -EINVAL;
+}
+
+static int mtk_pmx_gpio_request_enable(struct pinctrl_dev *pctldev,
+				    struct pinctrl_gpio_range *range,
+				    unsigned offset)
+{
+	int muxval;
+	struct mtk_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+
+	muxval = mtk_pmx_find_gpio_mode(pctl, offset);
+
+	if (muxval < 0) {
+		dev_err(pctl->dev, "invalid gpio pin %d.\n", offset);
+		return -EINVAL;
+	}
+
+	mtk_pmx_set_mode(pctldev, offset, muxval);
+	mtk_pconf_set_ies_smt(pctl, offset, 1, PIN_CONFIG_INPUT_ENABLE);
+
+	return 0;
+}
+
 static const struct pinmux_ops mtk_pmx_ops = {
 	.get_functions_count	= mtk_pmx_get_funcs_cnt,
 	.get_function_name	= mtk_pmx_get_func_name,
 	.get_function_groups	= mtk_pmx_get_func_groups,
 	.set_mux		= mtk_pmx_set_mux,
 	.gpio_set_direction	= mtk_pmx_gpio_set_direction,
+	.gpio_request_enable	= mtk_pmx_gpio_request_enable,
 };
 
 static int mtk_gpio_direction_input(struct gpio_chip *chip,
@@ -754,6 +803,10 @@ static int mtk_gpio_get_direction(struct gpio_chip *chip, unsigned offset)
 
 	reg_addr =  mtk_get_port(pctl, offset) + pctl->devdata->dir_offset;
 	bit = BIT(offset & 0xf);
+
+	if (pctl->devdata->spec_dir_set)
+		pctl->devdata->spec_dir_set(&reg_addr, offset);
+
 	regmap_read(pctl->regmap1, reg_addr, &read_val);
 	return !(read_val & bit);
 }
@@ -812,6 +865,10 @@ static int mtk_pinctrl_irq_request_resources(struct irq_data *d)
 
 	/* set mux to INT mode */
 	mtk_pmx_set_mode(pctl->pctl_dev, pin->pin.number, pin->eint.eintmux);
+	/* set gpio direction to input */
+	mtk_pmx_gpio_set_direction(pctl->pctl_dev, NULL, pin->pin.number, true);
+	/* set input-enable */
+	mtk_pconf_set_ies_smt(pctl, pin->pin.number, 1, PIN_CONFIG_INPUT_ENABLE);
 
 	return 0;
 }
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.h b/drivers/pinctrl/mediatek/pinctrl-mtk-common.h
index 55a534338931..8543bc478a1e 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.h
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.h
@@ -209,7 +209,14 @@ struct mtk_eint_offsets {
  * means when user set smt, input enable is set at the same time. So they
  * also need special control. If special control is success, this should
  * return 0, otherwise return non-zero value.
- *
+ * @spec_pinmux_set: In some cases, there are two pinmux functions share
+ * the same value in the same segment of pinmux control register. If user
+ * want to use one of the two functions, they need an extra bit setting to
+ * select the right one.
+ * @spec_dir_set: In very few SoCs, direction control registers are not
+ * arranged continuously, they may be cut to parts. So they need special
+ * dir setting.
+
  * @dir_offset: The direction register offset.
  * @pullen_offset: The pull-up/pull-down enable register offset.
  * @pinmux_offset: The pinmux register offset.
@@ -234,6 +241,9 @@ struct mtk_pinctrl_devdata {
 			unsigned char align, bool isup, unsigned int arg);
 	int (*spec_ies_smt_set)(struct regmap *reg, unsigned int pin,
 			unsigned char align, int value, enum pin_config_param arg);
+	void (*spec_pinmux_set)(struct regmap *reg, unsigned int pin,
+			unsigned int mode);
+	void (*spec_dir_set)(unsigned int *reg_addr, unsigned int pin);
 	unsigned int dir_offset;
 	unsigned int ies_offset;
 	unsigned int smt_offset;
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-mt2701.h b/drivers/pinctrl/mediatek/pinctrl-mtk-mt2701.h
new file mode 100644
index 000000000000..f90642078c31
--- /dev/null
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-mt2701.h
@@ -0,0 +1,2323 @@
+/*
+ * Copyright (c) 2015 MediaTek Inc.
+ * Author: Biao Huang <biao.huang@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __PINCTRL_MTK_MT2701_H
+#define __PINCTRL_MTK_MT2701_H
+
+#include <linux/pinctrl/pinctrl.h>
+#include "pinctrl-mtk-common.h"
+
+static const struct mtk_desc_pin mtk_pins_mt2701[] = {
+	MTK_PIN(
+		PINCTRL_PIN(0, "PWRAP_SPI0_MI"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 148),
+		MTK_FUNCTION(0, "GPIO0"),
+		MTK_FUNCTION(1, "PWRAP_SPIDO"),
+		MTK_FUNCTION(2, "PWRAP_SPIDI")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(1, "PWRAP_SPI0_MO"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 149),
+		MTK_FUNCTION(0, "GPIO1"),
+		MTK_FUNCTION(1, "PWRAP_SPIDI"),
+		MTK_FUNCTION(2, "PWRAP_SPIDO")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(2, "PWRAP_INT"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 150),
+		MTK_FUNCTION(0, "GPIO2"),
+		MTK_FUNCTION(1, "PWRAP_INT")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(3, "PWRAP_SPI0_CK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 151),
+		MTK_FUNCTION(0, "GPIO3"),
+		MTK_FUNCTION(1, "PWRAP_SPICK_I")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(4, "PWRAP_SPI0_CSN"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 152),
+		MTK_FUNCTION(0, "GPIO4"),
+		MTK_FUNCTION(1, "PWRAP_SPICS_B_I")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(5, "PWRAP_SPI0_CK2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 153),
+		MTK_FUNCTION(0, "GPIO5"),
+		MTK_FUNCTION(1, "PWRAP_SPICK2_I"),
+		MTK_FUNCTION(5, "ANT_SEL1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(6, "PWRAP_SPI0_CSN2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 154),
+		MTK_FUNCTION(0, "GPIO6"),
+		MTK_FUNCTION(1, "PWRAP_SPICS2_B_I"),
+		MTK_FUNCTION(5, "ANT_SEL0"),
+		MTK_FUNCTION(7, "DBG_MON_A[0]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(7, "SPI1_CSN"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 155),
+		MTK_FUNCTION(0, "GPIO7"),
+		MTK_FUNCTION(1, "SPI1_CS"),
+		MTK_FUNCTION(4, "KCOL0"),
+		MTK_FUNCTION(7, "DBG_MON_B[12]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(8, "SPI1_MI"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 156),
+		MTK_FUNCTION(0, "GPIO8"),
+		MTK_FUNCTION(1, "SPI1_MI"),
+		MTK_FUNCTION(2, "SPI1_MO"),
+		MTK_FUNCTION(4, "KCOL1"),
+		MTK_FUNCTION(7, "DBG_MON_B[13]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(9, "SPI1_MO"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 157),
+		MTK_FUNCTION(0, "GPIO9"),
+		MTK_FUNCTION(1, "SPI1_MO"),
+		MTK_FUNCTION(2, "SPI1_MI"),
+		MTK_FUNCTION(3, "EXT_FRAME_SYNC"),
+		MTK_FUNCTION(4, "KCOL2"),
+		MTK_FUNCTION(7, "DBG_MON_B[14]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(10, "RTC32K_CK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 158),
+		MTK_FUNCTION(0, "GPIO10"),
+		MTK_FUNCTION(1, "RTC32K_CK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(11, "WATCHDOG"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 159),
+		MTK_FUNCTION(0, "GPIO11"),
+		MTK_FUNCTION(1, "WATCHDOG")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(12, "SRCLKENA"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 160),
+		MTK_FUNCTION(0, "GPIO12"),
+		MTK_FUNCTION(1, "SRCLKENA")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(13, "SRCLKENAI"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 161),
+		MTK_FUNCTION(0, "GPIO13"),
+		MTK_FUNCTION(1, "SRCLKENAI")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(14, "URXD2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 162),
+		MTK_FUNCTION(0, "GPIO14"),
+		MTK_FUNCTION(1, "URXD2"),
+		MTK_FUNCTION(2, "UTXD2"),
+		MTK_FUNCTION(5, "SRCCLKENAI2"),
+		MTK_FUNCTION(7, "DBG_MON_B[30]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(15, "UTXD2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 163),
+		MTK_FUNCTION(0, "GPIO15"),
+		MTK_FUNCTION(1, "UTXD2"),
+		MTK_FUNCTION(2, "URXD2"),
+		MTK_FUNCTION(7, "DBG_MON_B[31]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(16, "I2S5_DATA_IN"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 164),
+		MTK_FUNCTION(0, "GPIO16"),
+		MTK_FUNCTION(1, "I2S5_DATA_IN"),
+		MTK_FUNCTION(3, "PCM_RX"),
+		MTK_FUNCTION(4, "ANT_SEL4")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(17, "I2S5_BCK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 165),
+		MTK_FUNCTION(0, "GPIO17"),
+		MTK_FUNCTION(1, "I2S5_BCK"),
+		MTK_FUNCTION(3, "PCM_CLK0"),
+		MTK_FUNCTION(4, "ANT_SEL2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(18, "PCM_CLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 166),
+		MTK_FUNCTION(0, "GPIO18"),
+		MTK_FUNCTION(1, "PCM_CLK0"),
+		MTK_FUNCTION(2, "MRG_CLK"),
+		MTK_FUNCTION(4, "MM_TEST_CK"),
+		MTK_FUNCTION(5, "CONN_DSP_JCK"),
+		MTK_FUNCTION(6, "WCN_PCM_CLKO"),
+		MTK_FUNCTION(7, "DBG_MON_A[3]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(19, "PCM_SYNC"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 167),
+		MTK_FUNCTION(0, "GPIO19"),
+		MTK_FUNCTION(1, "PCM_SYNC"),
+		MTK_FUNCTION(2, "MRG_SYNC"),
+		MTK_FUNCTION(5, "CONN_DSP_JINTP"),
+		MTK_FUNCTION(6, "WCN_PCM_SYNC"),
+		MTK_FUNCTION(7, "DBG_MON_A[5]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(20, "PCM_RX"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO20"),
+		MTK_FUNCTION(1, "PCM_RX"),
+		MTK_FUNCTION(2, "MRG_RX"),
+		MTK_FUNCTION(3, "MRG_TX"),
+		MTK_FUNCTION(4, "PCM_TX"),
+		MTK_FUNCTION(5, "CONN_DSP_JDI"),
+		MTK_FUNCTION(6, "WCN_PCM_RX"),
+		MTK_FUNCTION(7, "DBG_MON_A[4]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(21, "PCM_TX"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO21"),
+		MTK_FUNCTION(1, "PCM_TX"),
+		MTK_FUNCTION(2, "MRG_TX"),
+		MTK_FUNCTION(3, "MRG_RX"),
+		MTK_FUNCTION(4, "PCM_RX"),
+		MTK_FUNCTION(5, "CONN_DSP_JMS"),
+		MTK_FUNCTION(6, "WCN_PCM_TX"),
+		MTK_FUNCTION(7, "DBG_MON_A[2]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(22, "EINT0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 0),
+		MTK_FUNCTION(0, "GPIO22"),
+		MTK_FUNCTION(1, "UCTS0"),
+		MTK_FUNCTION(3, "KCOL3"),
+		MTK_FUNCTION(4, "CONN_DSP_JDO"),
+		MTK_FUNCTION(5, "EXT_FRAME_SYNC"),
+		MTK_FUNCTION(7, "DBG_MON_A[30]"),
+		MTK_FUNCTION(10, "PCIE0_PERST_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(23, "EINT1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 1),
+		MTK_FUNCTION(0, "GPIO23"),
+		MTK_FUNCTION(1, "URTS0"),
+		MTK_FUNCTION(3, "KCOL2"),
+		MTK_FUNCTION(4, "CONN_MCU_TDO"),
+		MTK_FUNCTION(5, "EXT_FRAME_SYNC"),
+		MTK_FUNCTION(7, "DBG_MON_A[29]"),
+		MTK_FUNCTION(10, "PCIE1_PERST_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(24, "EINT2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 2),
+		MTK_FUNCTION(0, "GPIO24"),
+		MTK_FUNCTION(1, "UCTS1"),
+		MTK_FUNCTION(3, "KCOL1"),
+		MTK_FUNCTION(4, "CONN_MCU_DBGACK_N"),
+		MTK_FUNCTION(7, "DBG_MON_A[28]"),
+		MTK_FUNCTION(10, "PCIE2_PERST_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(25, "EINT3"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 3),
+		MTK_FUNCTION(0, "GPIO25"),
+		MTK_FUNCTION(1, "URTS1"),
+		MTK_FUNCTION(3, "KCOL0"),
+		MTK_FUNCTION(4, "CONN_MCU_DBGI_N"),
+		MTK_FUNCTION(7, "DBG_MON_A[27]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(26, "EINT4"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 4),
+		MTK_FUNCTION(0, "GPIO26"),
+		MTK_FUNCTION(1, "UCTS3"),
+		MTK_FUNCTION(2, "DRV_VBUS_P1"),
+		MTK_FUNCTION(3, "KROW3"),
+		MTK_FUNCTION(4, "CONN_MCU_TCK0"),
+		MTK_FUNCTION(5, "CONN_MCU_AICE_JCKC"),
+		MTK_FUNCTION(6, "PCIE2_WAKE_N"),
+		MTK_FUNCTION(7, "DBG_MON_A[26]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(27, "EINT5"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 5),
+		MTK_FUNCTION(0, "GPIO27"),
+		MTK_FUNCTION(1, "URTS3"),
+		MTK_FUNCTION(2, "IDDIG_P1"),
+		MTK_FUNCTION(3, "KROW2"),
+		MTK_FUNCTION(4, "CONN_MCU_TDI"),
+		MTK_FUNCTION(6, "PCIE1_WAKE_N"),
+		MTK_FUNCTION(7, "DBG_MON_A[25]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(28, "EINT6"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 6),
+		MTK_FUNCTION(0, "GPIO28"),
+		MTK_FUNCTION(1, "DRV_VBUS"),
+		MTK_FUNCTION(3, "KROW1"),
+		MTK_FUNCTION(4, "CONN_MCU_TRST_B"),
+		MTK_FUNCTION(6, "PCIE0_WAKE_N"),
+		MTK_FUNCTION(7, "DBG_MON_A[24]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(29, "EINT7"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 7),
+		MTK_FUNCTION(0, "GPIO29"),
+		MTK_FUNCTION(1, "IDDIG"),
+		MTK_FUNCTION(2, "MSDC1_WP"),
+		MTK_FUNCTION(3, "KROW0"),
+		MTK_FUNCTION(4, "CONN_MCU_TMS"),
+		MTK_FUNCTION(5, "CONN_MCU_AICE_JMSC"),
+		MTK_FUNCTION(7, "DBG_MON_A[23]"),
+		MTK_FUNCTION(14, "PCIE2_PERST_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(30, "I2S5_LRCK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 12),
+		MTK_FUNCTION(0, "GPIO30"),
+		MTK_FUNCTION(1, "I2S5_LRCK"),
+		MTK_FUNCTION(3, "PCM_SYNC"),
+		MTK_FUNCTION(4, "ANT_SEL1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(31, "I2S5_MCLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 13),
+		MTK_FUNCTION(0, "GPIO31"),
+		MTK_FUNCTION(1, "I2S5_MCLK"),
+		MTK_FUNCTION(4, "ANT_SEL0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(32, "I2S5_DATA"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 14),
+		MTK_FUNCTION(0, "GPIO32"),
+		MTK_FUNCTION(1, "I2S5_DATA"),
+		MTK_FUNCTION(2, "I2S5_DATA_BYPS"),
+		MTK_FUNCTION(3, "PCM_TX"),
+		MTK_FUNCTION(4, "ANT_SEL3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(33, "I2S1_DATA"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 15),
+		MTK_FUNCTION(0, "GPIO33"),
+		MTK_FUNCTION(1, "I2S1_DATA"),
+		MTK_FUNCTION(2, "I2S1_DATA_BYPS"),
+		MTK_FUNCTION(3, "PCM_TX"),
+		MTK_FUNCTION(4, "IMG_TEST_CK"),
+		MTK_FUNCTION(5, "G1_RXD0"),
+		MTK_FUNCTION(6, "WCN_PCM_TX"),
+		MTK_FUNCTION(7, "DBG_MON_B[8]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(34, "I2S1_DATA_IN"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 16),
+		MTK_FUNCTION(0, "GPIO34"),
+		MTK_FUNCTION(1, "I2S1_DATA_IN"),
+		MTK_FUNCTION(3, "PCM_RX"),
+		MTK_FUNCTION(4, "VDEC_TEST_CK"),
+		MTK_FUNCTION(5, "G1_RXD1"),
+		MTK_FUNCTION(6, "WCN_PCM_RX"),
+		MTK_FUNCTION(7, "DBG_MON_B[7]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(35, "I2S1_BCK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 17),
+		MTK_FUNCTION(0, "GPIO35"),
+		MTK_FUNCTION(1, "I2S1_BCK"),
+		MTK_FUNCTION(3, "PCM_CLK0"),
+		MTK_FUNCTION(5, "G1_RXD2"),
+		MTK_FUNCTION(6, "WCN_PCM_CLKO"),
+		MTK_FUNCTION(7, "DBG_MON_B[9]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(36, "I2S1_LRCK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 18),
+		MTK_FUNCTION(0, "GPIO36"),
+		MTK_FUNCTION(1, "I2S1_LRCK"),
+		MTK_FUNCTION(3, "PCM_SYNC"),
+		MTK_FUNCTION(5, "G1_RXD3"),
+		MTK_FUNCTION(6, "WCN_PCM_SYNC"),
+		MTK_FUNCTION(7, "DBG_MON_B[10]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(37, "I2S1_MCLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 19),
+		MTK_FUNCTION(0, "GPIO37"),
+		MTK_FUNCTION(1, "I2S1_MCLK"),
+		MTK_FUNCTION(5, "G1_RXDV"),
+		MTK_FUNCTION(7, "DBG_MON_B[11]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(38, "I2S2_DATA"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 20),
+		MTK_FUNCTION(0, "GPIO38"),
+		MTK_FUNCTION(2, "I2S2_DATA_BYPS"),
+		MTK_FUNCTION(3, "PCM_TX"),
+		MTK_FUNCTION(4, "DMIC_DAT0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(39, "JTMS"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 21),
+		MTK_FUNCTION(0, "GPIO39"),
+		MTK_FUNCTION(1, "JTMS"),
+		MTK_FUNCTION(2, "CONN_MCU_TMS"),
+		MTK_FUNCTION(3, "CONN_MCU_AICE_JMSC"),
+		MTK_FUNCTION(4, "DFD_TMS_XI")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(40, "JTCK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 22),
+		MTK_FUNCTION(0, "GPIO40"),
+		MTK_FUNCTION(1, "JTCK"),
+		MTK_FUNCTION(2, "CONN_MCU_TCK1"),
+		MTK_FUNCTION(3, "CONN_MCU_AICE_JCKC"),
+		MTK_FUNCTION(4, "DFD_TCK_XI")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(41, "JTDI"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 23),
+		MTK_FUNCTION(0, "GPIO41"),
+		MTK_FUNCTION(1, "JTDI"),
+		MTK_FUNCTION(2, "CONN_MCU_TDI"),
+		MTK_FUNCTION(4, "DFD_TDI_XI")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(42, "JTDO"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 24),
+		MTK_FUNCTION(0, "GPIO42"),
+		MTK_FUNCTION(1, "JTDO"),
+		MTK_FUNCTION(2, "CONN_MCU_TDO"),
+		MTK_FUNCTION(4, "DFD_TDO")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(43, "NCLE"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 25),
+		MTK_FUNCTION(0, "GPIO43"),
+		MTK_FUNCTION(1, "NCLE"),
+		MTK_FUNCTION(2, "EXT_XCS2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(44, "NCEB1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 26),
+		MTK_FUNCTION(0, "GPIO44"),
+		MTK_FUNCTION(1, "NCEB1"),
+		MTK_FUNCTION(2, "IDDIG")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(45, "NCEB0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 27),
+		MTK_FUNCTION(0, "GPIO45"),
+		MTK_FUNCTION(1, "NCEB0"),
+		MTK_FUNCTION(2, "DRV_VBUS")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(46, "IR"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 28),
+		MTK_FUNCTION(0, "GPIO46"),
+		MTK_FUNCTION(1, "IR")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(47, "NREB"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 29),
+		MTK_FUNCTION(0, "GPIO47"),
+		MTK_FUNCTION(1, "NREB"),
+		MTK_FUNCTION(2, "IDDIG_P1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(48, "NRNB"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 30),
+		MTK_FUNCTION(0, "GPIO48"),
+		MTK_FUNCTION(1, "NRNB"),
+		MTK_FUNCTION(2, "DRV_VBUS_P1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(49, "I2S0_DATA"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 31),
+		MTK_FUNCTION(0, "GPIO49"),
+		MTK_FUNCTION(1, "I2S0_DATA"),
+		MTK_FUNCTION(2, "I2S0_DATA_BYPS"),
+		MTK_FUNCTION(3, "PCM_TX"),
+		MTK_FUNCTION(6, "WCN_I2S_DO"),
+		MTK_FUNCTION(7, "DBG_MON_B[3]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(50, "I2S2_BCK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 32),
+		MTK_FUNCTION(0, "GPIO50"),
+		MTK_FUNCTION(1, "I2S2_BCK"),
+		MTK_FUNCTION(3, "PCM_CLK0"),
+		MTK_FUNCTION(4, "DMIC_SCK1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(51, "I2S2_DATA_IN"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 33),
+		MTK_FUNCTION(0, "GPIO51"),
+		MTK_FUNCTION(1, "I2S2_DATA_IN"),
+		MTK_FUNCTION(3, "PCM_RX"),
+		MTK_FUNCTION(4, "DMIC_SCK0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(52, "I2S2_LRCK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 34),
+		MTK_FUNCTION(0, "GPIO52"),
+		MTK_FUNCTION(1, "I2S2_LRCK"),
+		MTK_FUNCTION(3, "PCM_SYNC"),
+		MTK_FUNCTION(4, "DMIC_DAT1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(53, "SPI0_CSN"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 35),
+		MTK_FUNCTION(0, "GPIO53"),
+		MTK_FUNCTION(1, "SPI0_CS"),
+		MTK_FUNCTION(3, "SPDIF"),
+		MTK_FUNCTION(4, "ADC_CK"),
+		MTK_FUNCTION(5, "PWM1"),
+		MTK_FUNCTION(7, "DBG_MON_A[7]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(54, "SPI0_CK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 36),
+		MTK_FUNCTION(0, "GPIO54"),
+		MTK_FUNCTION(1, "SPI0_CK"),
+		MTK_FUNCTION(3, "SPDIF_IN1"),
+		MTK_FUNCTION(4, "ADC_DAT_IN"),
+		MTK_FUNCTION(7, "DBG_MON_A[10]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(55, "SPI0_MI"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 37),
+		MTK_FUNCTION(0, "GPIO55"),
+		MTK_FUNCTION(1, "SPI0_MI"),
+		MTK_FUNCTION(2, "SPI0_MO"),
+		MTK_FUNCTION(3, "MSDC1_WP"),
+		MTK_FUNCTION(4, "ADC_WS"),
+		MTK_FUNCTION(5, "PWM2"),
+		MTK_FUNCTION(7, "DBG_MON_A[8]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(56, "SPI0_MO"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 38),
+		MTK_FUNCTION(0, "GPIO56"),
+		MTK_FUNCTION(1, "SPI0_MO"),
+		MTK_FUNCTION(2, "SPI0_MI"),
+		MTK_FUNCTION(3, "SPDIF_IN0"),
+		MTK_FUNCTION(7, "DBG_MON_A[9]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(57, "SDA1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 39),
+		MTK_FUNCTION(0, "GPIO57"),
+		MTK_FUNCTION(1, "SDA1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(58, "SCL1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 40),
+		MTK_FUNCTION(0, "GPIO58"),
+		MTK_FUNCTION(1, "SCL1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(59, "RAMBUF_I_CLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO59"),
+		MTK_FUNCTION(1, "RAMBUF_I_CLK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(60, "WB_RSTB"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 41),
+		MTK_FUNCTION(0, "GPIO60"),
+		MTK_FUNCTION(1, "WB_RSTB"),
+		MTK_FUNCTION(7, "DBG_MON_A[11]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(61, "F2W_DATA"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 42),
+		MTK_FUNCTION(0, "GPIO61"),
+		MTK_FUNCTION(1, "F2W_DATA"),
+		MTK_FUNCTION(7, "DBG_MON_A[16]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(62, "F2W_CLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 43),
+		MTK_FUNCTION(0, "GPIO62"),
+		MTK_FUNCTION(1, "F2W_CK"),
+		MTK_FUNCTION(7, "DBG_MON_A[15]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(63, "WB_SCLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 44),
+		MTK_FUNCTION(0, "GPIO63"),
+		MTK_FUNCTION(1, "WB_SCLK"),
+		MTK_FUNCTION(7, "DBG_MON_A[13]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(64, "WB_SDATA"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 45),
+		MTK_FUNCTION(0, "GPIO64"),
+		MTK_FUNCTION(1, "WB_SDATA"),
+		MTK_FUNCTION(7, "DBG_MON_A[12]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(65, "WB_SEN"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 46),
+		MTK_FUNCTION(0, "GPIO65"),
+		MTK_FUNCTION(1, "WB_SEN"),
+		MTK_FUNCTION(7, "DBG_MON_A[14]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(66, "WB_CRTL0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 47),
+		MTK_FUNCTION(0, "GPIO66"),
+		MTK_FUNCTION(1, "WB_CRTL0"),
+		MTK_FUNCTION(5, "DFD_NTRST_XI"),
+		MTK_FUNCTION(7, "DBG_MON_A[17]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(67, "WB_CRTL1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 48),
+		MTK_FUNCTION(0, "GPIO67"),
+		MTK_FUNCTION(1, "WB_CRTL1"),
+		MTK_FUNCTION(5, "DFD_TMS_XI"),
+		MTK_FUNCTION(7, "DBG_MON_A[18]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(68, "WB_CRTL2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 49),
+		MTK_FUNCTION(0, "GPIO68"),
+		MTK_FUNCTION(1, "WB_CRTL2"),
+		MTK_FUNCTION(5, "DFD_TCK_XI"),
+		MTK_FUNCTION(7, "DBG_MON_A[19]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(69, "WB_CRTL3"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 50),
+		MTK_FUNCTION(0, "GPIO69"),
+		MTK_FUNCTION(1, "WB_CRTL3"),
+		MTK_FUNCTION(5, "DFD_TDI_XI"),
+		MTK_FUNCTION(7, "DBG_MON_A[20]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(70, "WB_CRTL4"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 51),
+		MTK_FUNCTION(0, "GPIO70"),
+		MTK_FUNCTION(1, "WB_CRTL4"),
+		MTK_FUNCTION(5, "DFD_TDO"),
+		MTK_FUNCTION(7, "DBG_MON_A[21]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(71, "WB_CRTL5"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 52),
+		MTK_FUNCTION(0, "GPIO71"),
+		MTK_FUNCTION(1, "WB_CRTL5"),
+		MTK_FUNCTION(7, "DBG_MON_A[22]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(72, "I2S0_DATA_IN"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 53),
+		MTK_FUNCTION(0, "GPIO72"),
+		MTK_FUNCTION(1, "I2S0_DATA_IN"),
+		MTK_FUNCTION(3, "PCM_RX"),
+		MTK_FUNCTION(4, "PWM0"),
+		MTK_FUNCTION(5, "DISP_PWM"),
+		MTK_FUNCTION(6, "WCN_I2S_DI"),
+		MTK_FUNCTION(7, "DBG_MON_B[2]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(73, "I2S0_LRCK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 54),
+		MTK_FUNCTION(0, "GPIO73"),
+		MTK_FUNCTION(1, "I2S0_LRCK"),
+		MTK_FUNCTION(3, "PCM_SYNC"),
+		MTK_FUNCTION(6, "WCN_I2S_LRCK"),
+		MTK_FUNCTION(7, "DBG_MON_B[5]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(74, "I2S0_BCK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 55),
+		MTK_FUNCTION(0, "GPIO74"),
+		MTK_FUNCTION(1, "I2S0_BCK"),
+		MTK_FUNCTION(3, "PCM_CLK0"),
+		MTK_FUNCTION(6, "WCN_I2S_BCK"),
+		MTK_FUNCTION(7, "DBG_MON_B[4]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(75, "SDA0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 56),
+		MTK_FUNCTION(0, "GPIO75"),
+		MTK_FUNCTION(1, "SDA0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(76, "SCL0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 57),
+		MTK_FUNCTION(0, "GPIO76"),
+		MTK_FUNCTION(1, "SCL0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(77, "SDA2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 58),
+		MTK_FUNCTION(0, "GPIO77"),
+		MTK_FUNCTION(1, "SDA2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(78, "SCL2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 59),
+		MTK_FUNCTION(0, "GPIO78"),
+		MTK_FUNCTION(1, "SCL2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(79, "URXD0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 60),
+		MTK_FUNCTION(0, "GPIO79"),
+		MTK_FUNCTION(1, "URXD0"),
+		MTK_FUNCTION(2, "UTXD0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(80, "UTXD0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 61),
+		MTK_FUNCTION(0, "GPIO80"),
+		MTK_FUNCTION(1, "UTXD0"),
+		MTK_FUNCTION(2, "URXD0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(81, "URXD1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 62),
+		MTK_FUNCTION(0, "GPIO81"),
+		MTK_FUNCTION(1, "URXD1"),
+		MTK_FUNCTION(2, "UTXD1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(82, "UTXD1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 63),
+		MTK_FUNCTION(0, "GPIO82"),
+		MTK_FUNCTION(1, "UTXD1"),
+		MTK_FUNCTION(2, "URXD1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(83, "LCM_RST"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 64),
+		MTK_FUNCTION(0, "GPIO83"),
+		MTK_FUNCTION(1, "LCM_RST"),
+		MTK_FUNCTION(2, "VDAC_CK_XI"),
+		MTK_FUNCTION(7, "DBG_MON_B[1]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(84, "DSI_TE"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 65),
+		MTK_FUNCTION(0, "GPIO84"),
+		MTK_FUNCTION(1, "DSI_TE"),
+		MTK_FUNCTION(7, "DBG_MON_B[0]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(85, "MSDC2_CMD"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 66),
+		MTK_FUNCTION(0, "GPIO85"),
+		MTK_FUNCTION(1, "MSDC2_CMD"),
+		MTK_FUNCTION(2, "ANT_SEL0"),
+		MTK_FUNCTION(3, "SDA1"),
+		MTK_FUNCTION(6, "I2SOUT_BCK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(86, "MSDC2_CLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 67),
+		MTK_FUNCTION(0, "GPIO86"),
+		MTK_FUNCTION(1, "MSDC2_CLK"),
+		MTK_FUNCTION(2, "ANT_SEL1"),
+		MTK_FUNCTION(3, "SCL1"),
+		MTK_FUNCTION(6, "I2SOUT_LRCK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(87, "MSDC2_DAT0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 68),
+		MTK_FUNCTION(0, "GPIO87"),
+		MTK_FUNCTION(1, "MSDC2_DAT0"),
+		MTK_FUNCTION(2, "ANT_SEL2"),
+		MTK_FUNCTION(5, "UTXD0"),
+		MTK_FUNCTION(6, "I2SOUT_DATA_OUT")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(88, "MSDC2_DAT1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 71),
+		MTK_FUNCTION(0, "GPIO88"),
+		MTK_FUNCTION(1, "MSDC2_DAT1"),
+		MTK_FUNCTION(2, "ANT_SEL3"),
+		MTK_FUNCTION(3, "PWM0"),
+		MTK_FUNCTION(5, "URXD0"),
+		MTK_FUNCTION(6, "PWM1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(89, "MSDC2_DAT2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 72),
+		MTK_FUNCTION(0, "GPIO89"),
+		MTK_FUNCTION(1, "MSDC2_DAT2"),
+		MTK_FUNCTION(2, "ANT_SEL4"),
+		MTK_FUNCTION(3, "SDA2"),
+		MTK_FUNCTION(5, "UTXD1"),
+		MTK_FUNCTION(6, "PWM2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(90, "MSDC2_DAT3"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 73),
+		MTK_FUNCTION(0, "GPIO90"),
+		MTK_FUNCTION(1, "MSDC2_DAT3"),
+		MTK_FUNCTION(2, "ANT_SEL5"),
+		MTK_FUNCTION(3, "SCL2"),
+		MTK_FUNCTION(4, "EXT_FRAME_SYNC"),
+		MTK_FUNCTION(5, "URXD1"),
+		MTK_FUNCTION(6, "PWM3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(91, "TDN3"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPI91"),
+		MTK_FUNCTION(1, "TDN3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(92, "TDP3"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPI92"),
+		MTK_FUNCTION(1, "TDP3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(93, "TDN2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPI93"),
+		MTK_FUNCTION(1, "TDN2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(94, "TDP2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPI94"),
+		MTK_FUNCTION(1, "TDP2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(95, "TCN"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPI95"),
+		MTK_FUNCTION(1, "TCN")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(96, "TCP"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPI96"),
+		MTK_FUNCTION(1, "TCP")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(97, "TDN1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPI97"),
+		MTK_FUNCTION(1, "TDN1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(98, "TDP1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPI98"),
+		MTK_FUNCTION(1, "TDP1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(99, "TDN0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPI99"),
+		MTK_FUNCTION(1, "TDN0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(100, "TDP0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPI100"),
+		MTK_FUNCTION(1, "TDP0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(101, "SPI2_CSN"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 74),
+		MTK_FUNCTION(0, "GPIO101"),
+		MTK_FUNCTION(1, "SPI2_CS"),
+		MTK_FUNCTION(3, "SCL3"),
+		MTK_FUNCTION(4, "KROW0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(102, "SPI2_MI"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 75),
+		MTK_FUNCTION(0, "GPIO102"),
+		MTK_FUNCTION(1, "SPI2_MI"),
+		MTK_FUNCTION(2, "SPI2_MO"),
+		MTK_FUNCTION(3, "SDA3"),
+		MTK_FUNCTION(4, "KROW1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(103, "SPI2_MO"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 76),
+		MTK_FUNCTION(0, "GPIO103"),
+		MTK_FUNCTION(1, "SPI2_MO"),
+		MTK_FUNCTION(2, "SPI2_MI"),
+		MTK_FUNCTION(3, "SCL3"),
+		MTK_FUNCTION(4, "KROW2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(104, "SPI2_CLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 77),
+		MTK_FUNCTION(0, "GPIO104"),
+		MTK_FUNCTION(1, "SPI2_CK"),
+		MTK_FUNCTION(3, "SDA3"),
+		MTK_FUNCTION(4, "KROW3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(105, "MSDC1_CMD"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 78),
+		MTK_FUNCTION(0, "GPIO105"),
+		MTK_FUNCTION(1, "MSDC1_CMD"),
+		MTK_FUNCTION(2, "ANT_SEL0"),
+		MTK_FUNCTION(3, "SDA1"),
+		MTK_FUNCTION(6, "I2SOUT_BCK"),
+		MTK_FUNCTION(7, "DBG_MON_B[27]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(106, "MSDC1_CLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 79),
+		MTK_FUNCTION(0, "GPIO106"),
+		MTK_FUNCTION(1, "MSDC1_CLK"),
+		MTK_FUNCTION(2, "ANT_SEL1"),
+		MTK_FUNCTION(3, "SCL1"),
+		MTK_FUNCTION(6, "I2SOUT_LRCK"),
+		MTK_FUNCTION(7, "DBG_MON_B[28]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(107, "MSDC1_DAT0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 80),
+		MTK_FUNCTION(0, "GPIO107"),
+		MTK_FUNCTION(1, "MSDC1_DAT0"),
+		MTK_FUNCTION(2, "ANT_SEL2"),
+		MTK_FUNCTION(5, "UTXD0"),
+		MTK_FUNCTION(6, "I2SOUT_DATA_OUT"),
+		MTK_FUNCTION(7, "DBG_MON_B[26]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(108, "MSDC1_DAT1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 81),
+		MTK_FUNCTION(0, "GPIO108"),
+		MTK_FUNCTION(1, "MSDC1_DAT1"),
+		MTK_FUNCTION(2, "ANT_SEL3"),
+		MTK_FUNCTION(3, "PWM0"),
+		MTK_FUNCTION(5, "URXD0"),
+		MTK_FUNCTION(6, "PWM1"),
+		MTK_FUNCTION(7, "DBG_MON_B[25]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(109, "MSDC1_DAT2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 82),
+		MTK_FUNCTION(0, "GPIO109"),
+		MTK_FUNCTION(1, "MSDC1_DAT2"),
+		MTK_FUNCTION(2, "ANT_SEL4"),
+		MTK_FUNCTION(3, "SDA2"),
+		MTK_FUNCTION(5, "UTXD1"),
+		MTK_FUNCTION(6, "PWM2"),
+		MTK_FUNCTION(7, "DBG_MON_B[24]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(110, "MSDC1_DAT3"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 83),
+		MTK_FUNCTION(0, "GPIO110"),
+		MTK_FUNCTION(1, "MSDC1_DAT3"),
+		MTK_FUNCTION(2, "ANT_SEL5"),
+		MTK_FUNCTION(3, "SCL2"),
+		MTK_FUNCTION(4, "EXT_FRAME_SYNC"),
+		MTK_FUNCTION(5, "URXD1"),
+		MTK_FUNCTION(6, "PWM3"),
+		MTK_FUNCTION(7, "DBG_MON_B[23]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(111, "MSDC0_DAT7"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 84),
+		MTK_FUNCTION(0, "GPIO111"),
+		MTK_FUNCTION(1, "MSDC0_DAT7"),
+		MTK_FUNCTION(4, "NLD7")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(112, "MSDC0_DAT6"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 85),
+		MTK_FUNCTION(0, "GPIO112"),
+		MTK_FUNCTION(1, "MSDC0_DAT6"),
+		MTK_FUNCTION(4, "NLD6")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(113, "MSDC0_DAT5"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 86),
+		MTK_FUNCTION(0, "GPIO113"),
+		MTK_FUNCTION(1, "MSDC0_DAT5"),
+		MTK_FUNCTION(4, "NLD5")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(114, "MSDC0_DAT4"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 87),
+		MTK_FUNCTION(0, "GPIO114"),
+		MTK_FUNCTION(1, "MSDC0_DAT4"),
+		MTK_FUNCTION(4, "NLD4")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(115, "MSDC0_RSTB"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 88),
+		MTK_FUNCTION(0, "GPIO115"),
+		MTK_FUNCTION(1, "MSDC0_RSTB"),
+		MTK_FUNCTION(4, "NLD8")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(116, "MSDC0_CMD"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 89),
+		MTK_FUNCTION(0, "GPIO116"),
+		MTK_FUNCTION(1, "MSDC0_CMD"),
+		MTK_FUNCTION(4, "NALE")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(117, "MSDC0_CLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 90),
+		MTK_FUNCTION(0, "GPIO117"),
+		MTK_FUNCTION(1, "MSDC0_CLK"),
+		MTK_FUNCTION(4, "NWEB")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(118, "MSDC0_DAT3"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 91),
+		MTK_FUNCTION(0, "GPIO118"),
+		MTK_FUNCTION(1, "MSDC0_DAT3"),
+		MTK_FUNCTION(4, "NLD3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(119, "MSDC0_DAT2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 92),
+		MTK_FUNCTION(0, "GPIO119"),
+		MTK_FUNCTION(1, "MSDC0_DAT2"),
+		MTK_FUNCTION(4, "NLD2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(120, "MSDC0_DAT1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 93),
+		MTK_FUNCTION(0, "GPIO120"),
+		MTK_FUNCTION(1, "MSDC0_DAT1"),
+		MTK_FUNCTION(4, "NLD1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(121, "MSDC0_DAT0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 94),
+		MTK_FUNCTION(0, "GPIO121"),
+		MTK_FUNCTION(1, "MSDC0_DAT0"),
+		MTK_FUNCTION(4, "NLD0"),
+		MTK_FUNCTION(5, "WATCHDOG")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(122, "CEC"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 95),
+		MTK_FUNCTION(0, "GPIO122"),
+		MTK_FUNCTION(1, "CEC"),
+		MTK_FUNCTION(4, "SDA2"),
+		MTK_FUNCTION(5, "URXD0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(123, "HTPLG"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 96),
+		MTK_FUNCTION(0, "GPIO123"),
+		MTK_FUNCTION(1, "HTPLG"),
+		MTK_FUNCTION(4, "SCL2"),
+		MTK_FUNCTION(5, "UTXD0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(124, "HDMISCK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 97),
+		MTK_FUNCTION(0, "GPIO124"),
+		MTK_FUNCTION(1, "HDMISCK"),
+		MTK_FUNCTION(4, "SDA1"),
+		MTK_FUNCTION(5, "PWM3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(125, "HDMISD"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 98),
+		MTK_FUNCTION(0, "GPIO125"),
+		MTK_FUNCTION(1, "HDMISD"),
+		MTK_FUNCTION(4, "SCL1"),
+		MTK_FUNCTION(5, "PWM4")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(126, "I2S0_MCLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 99),
+		MTK_FUNCTION(0, "GPIO126"),
+		MTK_FUNCTION(1, "I2S0_MCLK"),
+		MTK_FUNCTION(6, "WCN_I2S_MCLK"),
+		MTK_FUNCTION(7, "DBG_MON_B[6]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(127, "RAMBUF_IDATA0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO127"),
+		MTK_FUNCTION(1, "RAMBUF_IDATA0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(128, "RAMBUF_IDATA1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO128"),
+		MTK_FUNCTION(1, "RAMBUF_IDATA1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(129, "RAMBUF_IDATA2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO129"),
+		MTK_FUNCTION(1, "RAMBUF_IDATA2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(130, "RAMBUF_IDATA3"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO130"),
+		MTK_FUNCTION(1, "RAMBUF_IDATA3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(131, "RAMBUF_IDATA4"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO131"),
+		MTK_FUNCTION(1, "RAMBUF_IDATA4")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(132, "RAMBUF_IDATA5"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO132"),
+		MTK_FUNCTION(1, "RAMBUF_IDATA5")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(133, "RAMBUF_IDATA6"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO133"),
+		MTK_FUNCTION(1, "RAMBUF_IDATA6")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(134, "RAMBUF_IDATA7"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO134"),
+		MTK_FUNCTION(1, "RAMBUF_IDATA7")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(135, "RAMBUF_IDATA8"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO135"),
+		MTK_FUNCTION(1, "RAMBUF_IDATA8")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(136, "RAMBUF_IDATA9"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO136"),
+		MTK_FUNCTION(1, "RAMBUF_IDATA9")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(137, "RAMBUF_IDATA10"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO137"),
+		MTK_FUNCTION(1, "RAMBUF_IDATA10")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(138, "RAMBUF_IDATA11"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO138"),
+		MTK_FUNCTION(1, "RAMBUF_IDATA11")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(139, "RAMBUF_IDATA12"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO139"),
+		MTK_FUNCTION(1, "RAMBUF_IDATA12")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(140, "RAMBUF_IDATA13"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO140"),
+		MTK_FUNCTION(1, "RAMBUF_IDATA13")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(141, "RAMBUF_IDATA14"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO141"),
+		MTK_FUNCTION(1, "RAMBUF_IDATA14")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(142, "RAMBUF_IDATA15"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO142"),
+		MTK_FUNCTION(1, "RAMBUF_IDATA15")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(143, "RAMBUF_ODATA0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO143"),
+		MTK_FUNCTION(1, "RAMBUF_ODATA0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(144, "RAMBUF_ODATA1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO144"),
+		MTK_FUNCTION(1, "RAMBUF_ODATA1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(145, "RAMBUF_ODATA2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO145"),
+		MTK_FUNCTION(1, "RAMBUF_ODATA2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(146, "RAMBUF_ODATA3"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO146"),
+		MTK_FUNCTION(1, "RAMBUF_ODATA3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(147, "RAMBUF_ODATA4"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO147"),
+		MTK_FUNCTION(1, "RAMBUF_ODATA4")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(148, "RAMBUF_ODATA5"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO148"),
+		MTK_FUNCTION(1, "RAMBUF_ODATA5")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(149, "RAMBUF_ODATA6"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO149"),
+		MTK_FUNCTION(1, "RAMBUF_ODATA6")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(150, "RAMBUF_ODATA7"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO150"),
+		MTK_FUNCTION(1, "RAMBUF_ODATA7")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(151, "RAMBUF_ODATA8"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO151"),
+		MTK_FUNCTION(1, "RAMBUF_ODATA8")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(152, "RAMBUF_ODATA9"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO152"),
+		MTK_FUNCTION(1, "RAMBUF_ODATA9")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(153, "RAMBUF_ODATA10"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO153"),
+		MTK_FUNCTION(1, "RAMBUF_ODATA10")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(154, "RAMBUF_ODATA11"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO154"),
+		MTK_FUNCTION(1, "RAMBUF_ODATA11")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(155, "RAMBUF_ODATA12"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO155"),
+		MTK_FUNCTION(1, "RAMBUF_ODATA12")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(156, "RAMBUF_ODATA13"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO156"),
+		MTK_FUNCTION(1, "RAMBUF_ODATA13")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(157, "RAMBUF_ODATA14"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO157"),
+		MTK_FUNCTION(1, "RAMBUF_ODATA14")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(158, "RAMBUF_ODATA15"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO158"),
+		MTK_FUNCTION(1, "RAMBUF_ODATA15")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(159, "RAMBUF_BE0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO159"),
+		MTK_FUNCTION(1, "RAMBUF_BE0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(160, "RAMBUF_BE1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO160"),
+		MTK_FUNCTION(1, "RAMBUF_BE1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(161, "AP2PT_INT"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO161"),
+		MTK_FUNCTION(1, "AP2PT_INT")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(162, "AP2PT_INT_CLR"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO162"),
+		MTK_FUNCTION(1, "AP2PT_INT_CLR")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(163, "PT2AP_INT"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO163"),
+		MTK_FUNCTION(1, "PT2AP_INT")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(164, "PT2AP_INT_CLR"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO164"),
+		MTK_FUNCTION(1, "PT2AP_INT_CLR")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(165, "AP2UP_INT"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO165"),
+		MTK_FUNCTION(1, "AP2UP_INT")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(166, "AP2UP_INT_CLR"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO166"),
+		MTK_FUNCTION(1, "AP2UP_INT_CLR")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(167, "UP2AP_INT"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO167"),
+		MTK_FUNCTION(1, "UP2AP_INT")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(168, "UP2AP_INT_CLR"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO168"),
+		MTK_FUNCTION(1, "UP2AP_INT_CLR")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(169, "RAMBUF_ADDR0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO169"),
+		MTK_FUNCTION(1, "RAMBUF_ADDR0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(170, "RAMBUF_ADDR1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO170"),
+		MTK_FUNCTION(1, "RAMBUF_ADDR1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(171, "RAMBUF_ADDR2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO171"),
+		MTK_FUNCTION(1, "RAMBUF_ADDR2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(172, "RAMBUF_ADDR3"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO172"),
+		MTK_FUNCTION(1, "RAMBUF_ADDR3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(173, "RAMBUF_ADDR4"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO173"),
+		MTK_FUNCTION(1, "RAMBUF_ADDR4")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(174, "RAMBUF_ADDR5"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO174"),
+		MTK_FUNCTION(1, "RAMBUF_ADDR5")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(175, "RAMBUF_ADDR6"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO175"),
+		MTK_FUNCTION(1, "RAMBUF_ADDR6")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(176, "RAMBUF_ADDR7"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO176"),
+		MTK_FUNCTION(1, "RAMBUF_ADDR7")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(177, "RAMBUF_ADDR8"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO177"),
+		MTK_FUNCTION(1, "RAMBUF_ADDR8")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(178, "RAMBUF_ADDR9"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO178"),
+		MTK_FUNCTION(1, "RAMBUF_ADDR9")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(179, "RAMBUF_ADDR10"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO179"),
+		MTK_FUNCTION(1, "RAMBUF_ADDR10")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(180, "RAMBUF_RW"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO180"),
+		MTK_FUNCTION(1, "RAMBUF_RW")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(181, "RAMBUF_LAST"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO181"),
+		MTK_FUNCTION(1, "RAMBUF_LAST")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(182, "RAMBUF_HP"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO182"),
+		MTK_FUNCTION(1, "RAMBUF_HP")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(183, "RAMBUF_REQ"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO183"),
+		MTK_FUNCTION(1, "RAMBUF_REQ")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(184, "RAMBUF_ALE"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO184"),
+		MTK_FUNCTION(1, "RAMBUF_ALE")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(185, "RAMBUF_DLE"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO185"),
+		MTK_FUNCTION(1, "RAMBUF_DLE")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(186, "RAMBUF_WDLE"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO186"),
+		MTK_FUNCTION(1, "RAMBUF_WDLE")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(187, "RAMBUF_O_CLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO187"),
+		MTK_FUNCTION(1, "RAMBUF_O_CLK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(188, "I2S2_MCLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 100),
+		MTK_FUNCTION(0, "GPIO188"),
+		MTK_FUNCTION(1, "I2S2_MCLK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(189, "I2S3_DATA"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 101),
+		MTK_FUNCTION(0, "GPIO189"),
+		MTK_FUNCTION(2, "I2S3_DATA_BYPS"),
+		MTK_FUNCTION(3, "PCM_TX")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(190, "I2S3_DATA_IN"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 102),
+		MTK_FUNCTION(0, "GPIO190"),
+		MTK_FUNCTION(1, "I2S3_DATA_IN"),
+		MTK_FUNCTION(3, "PCM_RX")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(191, "I2S3_BCK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 103),
+		MTK_FUNCTION(0, "GPIO191"),
+		MTK_FUNCTION(1, "I2S3_BCK"),
+		MTK_FUNCTION(3, "PCM_CLK0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(192, "I2S3_LRCK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 104),
+		MTK_FUNCTION(0, "GPIO192"),
+		MTK_FUNCTION(1, "I2S3_LRCK"),
+		MTK_FUNCTION(3, "PCM_SYNC")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(193, "I2S3_MCLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 105),
+		MTK_FUNCTION(0, "GPIO193"),
+		MTK_FUNCTION(1, "I2S3_MCLK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(194, "I2S4_DATA"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 106),
+		MTK_FUNCTION(0, "GPIO194"),
+		MTK_FUNCTION(1, "I2S4_DATA"),
+		MTK_FUNCTION(2, "I2S4_DATA_BYPS"),
+		MTK_FUNCTION(3, "PCM_TX")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(195, "I2S4_DATA_IN"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 107),
+		MTK_FUNCTION(0, "GPIO195"),
+		MTK_FUNCTION(1, "I2S4_DATA_IN"),
+		MTK_FUNCTION(3, "PCM_RX")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(196, "I2S4_BCK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 108),
+		MTK_FUNCTION(0, "GPIO196"),
+		MTK_FUNCTION(1, "I2S4_BCK"),
+		MTK_FUNCTION(3, "PCM_CLK0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(197, "I2S4_LRCK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 109),
+		MTK_FUNCTION(0, "GPIO197"),
+		MTK_FUNCTION(1, "I2S4_LRCK"),
+		MTK_FUNCTION(3, "PCM_SYNC")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(198, "I2S4_MCLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 110),
+		MTK_FUNCTION(0, "GPIO198"),
+		MTK_FUNCTION(1, "I2S4_MCLK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(199, "SPI1_CLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 111),
+		MTK_FUNCTION(0, "GPIO199"),
+		MTK_FUNCTION(1, "SPI1_CK"),
+		MTK_FUNCTION(3, "EXT_FRAME_SYNC"),
+		MTK_FUNCTION(4, "KCOL3"),
+		MTK_FUNCTION(7, "DBG_MON_B[15]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(200, "SPDIF_OUT"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 112),
+		MTK_FUNCTION(0, "GPIO200"),
+		MTK_FUNCTION(1, "SPDIF_OUT"),
+		MTK_FUNCTION(5, "G1_TXD3"),
+		MTK_FUNCTION(6, "URXD2"),
+		MTK_FUNCTION(7, "DBG_MON_B[16]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(201, "SPDIF_IN0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 113),
+		MTK_FUNCTION(0, "GPIO201"),
+		MTK_FUNCTION(1, "SPDIF_IN0"),
+		MTK_FUNCTION(5, "G1_TXEN"),
+		MTK_FUNCTION(6, "UTXD2"),
+		MTK_FUNCTION(7, "DBG_MON_B[17]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(202, "SPDIF_IN1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 114),
+		MTK_FUNCTION(0, "GPIO202"),
+		MTK_FUNCTION(1, "SPDIF_IN1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(203, "PWM0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 115),
+		MTK_FUNCTION(0, "GPIO203"),
+		MTK_FUNCTION(1, "PWM0"),
+		MTK_FUNCTION(2, "DISP_PWM"),
+		MTK_FUNCTION(5, "G1_TXD2"),
+		MTK_FUNCTION(7, "DBG_MON_B[18]"),
+		MTK_FUNCTION(9, "I2S2_DATA")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(204, "PWM1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 116),
+		MTK_FUNCTION(0, "GPIO204"),
+		MTK_FUNCTION(1, "PWM1"),
+		MTK_FUNCTION(2, "CLKM3"),
+		MTK_FUNCTION(5, "G1_TXD1"),
+		MTK_FUNCTION(7, "DBG_MON_B[19]"),
+		MTK_FUNCTION(9, "I2S3_DATA")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(205, "PWM2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 117),
+		MTK_FUNCTION(0, "GPIO205"),
+		MTK_FUNCTION(1, "PWM2"),
+		MTK_FUNCTION(2, "CLKM2"),
+		MTK_FUNCTION(5, "G1_TXD0"),
+		MTK_FUNCTION(7, "DBG_MON_B[20]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(206, "PWM3"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 118),
+		MTK_FUNCTION(0, "GPIO206"),
+		MTK_FUNCTION(1, "PWM3"),
+		MTK_FUNCTION(2, "CLKM1"),
+		MTK_FUNCTION(3, "EXT_FRAME_SYNC"),
+		MTK_FUNCTION(5, "G1_TXC"),
+		MTK_FUNCTION(7, "DBG_MON_B[21]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(207, "PWM4"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 119),
+		MTK_FUNCTION(0, "GPIO207"),
+		MTK_FUNCTION(1, "PWM4"),
+		MTK_FUNCTION(2, "CLKM0"),
+		MTK_FUNCTION(3, "EXT_FRAME_SYNC"),
+		MTK_FUNCTION(5, "G1_RXC"),
+		MTK_FUNCTION(7, "DBG_MON_B[22]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(208, "AUD_EXT_CK1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 120),
+		MTK_FUNCTION(0, "GPIO208"),
+		MTK_FUNCTION(1, "AUD_EXT_CK1"),
+		MTK_FUNCTION(2, "PWM0"),
+		MTK_FUNCTION(4, "ANT_SEL5"),
+		MTK_FUNCTION(5, "DISP_PWM"),
+		MTK_FUNCTION(7, "DBG_MON_A[31]"),
+		MTK_FUNCTION(11, "PCIE0_PERST_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(209, "AUD_EXT_CK2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 121),
+		MTK_FUNCTION(0, "GPIO209"),
+		MTK_FUNCTION(1, "AUD_EXT_CK2"),
+		MTK_FUNCTION(2, "MSDC1_WP"),
+		MTK_FUNCTION(5, "PWM1"),
+		MTK_FUNCTION(7, "DBG_MON_A[32]"),
+		MTK_FUNCTION(11, "PCIE1_PERST_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(210, "AUD_CLOCK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO210"),
+		MTK_FUNCTION(1, "AUD_CLOCK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(211, "DVP_RESET"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO211"),
+		MTK_FUNCTION(1, "DVP_RESET")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(212, "DVP_CLOCK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO212"),
+		MTK_FUNCTION(1, "DVP_CLOCK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(213, "DVP_CS"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO213"),
+		MTK_FUNCTION(1, "DVP_CS")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(214, "DVP_CK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO214"),
+		MTK_FUNCTION(1, "DVP_CK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(215, "DVP_DI"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO215"),
+		MTK_FUNCTION(1, "DVP_DI")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(216, "DVP_DO"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO216"),
+		MTK_FUNCTION(1, "DVP_DO")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(217, "AP_CS"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO217"),
+		MTK_FUNCTION(1, "AP_CS")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(218, "AP_CK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO218"),
+		MTK_FUNCTION(1, "AP_CK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(219, "AP_DI"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO219"),
+		MTK_FUNCTION(1, "AP_DI")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(220, "AP_DO"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO220"),
+		MTK_FUNCTION(1, "AP_DO")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(221, "DVD_BCLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO221"),
+		MTK_FUNCTION(1, "DVD_BCLK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(222, "T8032_CLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO222"),
+		MTK_FUNCTION(1, "T8032_CLK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(223, "AP_BCLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO223"),
+		MTK_FUNCTION(1, "AP_BCLK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(224, "HOST_CS"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO224"),
+		MTK_FUNCTION(1, "HOST_CS")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(225, "HOST_CK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO225"),
+		MTK_FUNCTION(1, "HOST_CK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(226, "HOST_DO0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO226"),
+		MTK_FUNCTION(1, "HOST_DO0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(227, "HOST_DO1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO227"),
+		MTK_FUNCTION(1, "HOST_DO1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(228, "SLV_CS"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO228"),
+		MTK_FUNCTION(1, "SLV_CS")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(229, "SLV_CK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO229"),
+		MTK_FUNCTION(1, "SLV_CK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(230, "SLV_DI0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO230"),
+		MTK_FUNCTION(1, "SLV_DI0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(231, "SLV_DI1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO231"),
+		MTK_FUNCTION(1, "SLV_DI1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(232, "AP2DSP_INT"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO232"),
+		MTK_FUNCTION(1, "AP2DSP_INT")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(233, "AP2DSP_INT_CLR"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO233"),
+		MTK_FUNCTION(1, "AP2DSP_INT_CLR")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(234, "DSP2AP_INT"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO234"),
+		MTK_FUNCTION(1, "DSP2AP_INT")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(235, "DSP2AP_INT_CLR"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO235"),
+		MTK_FUNCTION(1, "DSP2AP_INT_CLR")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(236, "EXT_SDIO3"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 122),
+		MTK_FUNCTION(0, "GPIO236"),
+		MTK_FUNCTION(1, "EXT_SDIO3"),
+		MTK_FUNCTION(2, "IDDIG"),
+		MTK_FUNCTION(7, "DBG_MON_A[1]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(237, "EXT_SDIO2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 123),
+		MTK_FUNCTION(0, "GPIO237"),
+		MTK_FUNCTION(1, "EXT_SDIO2"),
+		MTK_FUNCTION(2, "DRV_VBUS")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(238, "EXT_SDIO1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 124),
+		MTK_FUNCTION(0, "GPIO238"),
+		MTK_FUNCTION(1, "EXT_SDIO1"),
+		MTK_FUNCTION(2, "IDDIG_P1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(239, "EXT_SDIO0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 125),
+		MTK_FUNCTION(0, "GPIO239"),
+		MTK_FUNCTION(1, "EXT_SDIO0"),
+		MTK_FUNCTION(2, "DRV_VBUS_P1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(240, "EXT_XCS"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 126),
+		MTK_FUNCTION(0, "GPIO240"),
+		MTK_FUNCTION(1, "EXT_XCS")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(241, "EXT_SCK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 127),
+		MTK_FUNCTION(0, "GPIO241"),
+		MTK_FUNCTION(1, "EXT_SCK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(242, "URTS2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 128),
+		MTK_FUNCTION(0, "GPIO242"),
+		MTK_FUNCTION(1, "URTS2"),
+		MTK_FUNCTION(2, "UTXD3"),
+		MTK_FUNCTION(3, "URXD3"),
+		MTK_FUNCTION(4, "SCL1"),
+		MTK_FUNCTION(7, "DBG_MON_B[32]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(243, "UCTS2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 129),
+		MTK_FUNCTION(0, "GPIO243"),
+		MTK_FUNCTION(1, "UCTS2"),
+		MTK_FUNCTION(2, "URXD3"),
+		MTK_FUNCTION(3, "UTXD3"),
+		MTK_FUNCTION(4, "SDA1"),
+		MTK_FUNCTION(7, "DBG_MON_A[6]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(244, "HDMI_SDA_RX"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 130),
+		MTK_FUNCTION(0, "GPIO244"),
+		MTK_FUNCTION(1, "HDMI_SDA_RX")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(245, "HDMI_SCL_RX"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 131),
+		MTK_FUNCTION(0, "GPIO245"),
+		MTK_FUNCTION(1, "HDMI_SCL_RX")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(246, "MHL_SENCE"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 132),
+		MTK_FUNCTION(0, "GPIO246")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(247, "HDMI_HPD_CBUS_RX"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 69),
+		MTK_FUNCTION(0, "GPIO247"),
+		MTK_FUNCTION(1, "HDMI_HPD_RX")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(248, "HDMI_TESTOUTP_RX"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 133),
+		MTK_FUNCTION(0, "GPIO248"),
+		MTK_FUNCTION(1, "HDMI_TESTOUTP_RX")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(249, "MSDC0E_RSTB"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 134),
+		MTK_FUNCTION(0, "GPIO249"),
+		MTK_FUNCTION(1, "MSDC0E_RSTB")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(250, "MSDC0E_DAT7"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 135),
+		MTK_FUNCTION(0, "GPIO250"),
+		MTK_FUNCTION(1, "MSDC3_DAT7"),
+		MTK_FUNCTION(6, "PCIE0_CLKREQ_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(251, "MSDC0E_DAT6"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 136),
+		MTK_FUNCTION(0, "GPIO251"),
+		MTK_FUNCTION(1, "MSDC3_DAT6"),
+		MTK_FUNCTION(6, "PCIE0_WAKE_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(252, "MSDC0E_DAT5"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 137),
+		MTK_FUNCTION(0, "GPIO252"),
+		MTK_FUNCTION(1, "MSDC3_DAT5"),
+		MTK_FUNCTION(6, "PCIE1_CLKREQ_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(253, "MSDC0E_DAT4"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 138),
+		MTK_FUNCTION(0, "GPIO253"),
+		MTK_FUNCTION(1, "MSDC3_DAT4"),
+		MTK_FUNCTION(6, "PCIE1_WAKE_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(254, "MSDC0E_DAT3"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 139),
+		MTK_FUNCTION(0, "GPIO254"),
+		MTK_FUNCTION(1, "MSDC3_DAT3"),
+		MTK_FUNCTION(6, "PCIE2_CLKREQ_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(255, "MSDC0E_DAT2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 140),
+		MTK_FUNCTION(0, "GPIO255"),
+		MTK_FUNCTION(1, "MSDC3_DAT2"),
+		MTK_FUNCTION(6, "PCIE2_WAKE_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(256, "MSDC0E_DAT1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 141),
+		MTK_FUNCTION(0, "GPIO256"),
+		MTK_FUNCTION(1, "MSDC3_DAT1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(257, "MSDC0E_DAT0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 142),
+		MTK_FUNCTION(0, "GPIO257"),
+		MTK_FUNCTION(1, "MSDC3_DAT0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(258, "MSDC0E_CMD"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 143),
+		MTK_FUNCTION(0, "GPIO258"),
+		MTK_FUNCTION(1, "MSDC3_CMD")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(259, "MSDC0E_CLK"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 144),
+		MTK_FUNCTION(0, "GPIO259"),
+		MTK_FUNCTION(1, "MSDC3_CLK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(260, "MSDC0E_DSL"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 145),
+		MTK_FUNCTION(0, "GPIO260"),
+		MTK_FUNCTION(1, "MSDC3_DSL")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(261, "MSDC1_INS"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 146),
+		MTK_FUNCTION(0, "GPIO261"),
+		MTK_FUNCTION(1, "MSDC1_INS"),
+		MTK_FUNCTION(7, "DBG_MON_B[29]")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(262, "G2_TXEN"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 8),
+		MTK_FUNCTION(0, "GPIO262"),
+		MTK_FUNCTION(1, "G2_TXEN")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(263, "G2_TXD3"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 9),
+		MTK_FUNCTION(0, "GPIO263"),
+		MTK_FUNCTION(1, "G2_TXD3"),
+		MTK_FUNCTION(6, "ANT_SEL5")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(264, "G2_TXD2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 10),
+		MTK_FUNCTION(0, "GPIO264"),
+		MTK_FUNCTION(1, "G2_TXD2"),
+		MTK_FUNCTION(6, "ANT_SEL4")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(265, "G2_TXD1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 11),
+		MTK_FUNCTION(0, "GPIO265"),
+		MTK_FUNCTION(1, "G2_TXD1"),
+		MTK_FUNCTION(6, "ANT_SEL3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(266, "G2_TXD0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO266"),
+		MTK_FUNCTION(1, "G2_TXD0"),
+		MTK_FUNCTION(6, "ANT_SEL2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(267, "G2_TXC"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO267"),
+		MTK_FUNCTION(1, "G2_TXC")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(268, "G2_RXC"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO268"),
+		MTK_FUNCTION(1, "G2_RXC")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(269, "G2_RXD0"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO269"),
+		MTK_FUNCTION(1, "G2_RXD0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(270, "G2_RXD1"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO270"),
+		MTK_FUNCTION(1, "G2_RXD1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(271, "G2_RXD2"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO271"),
+		MTK_FUNCTION(1, "G2_RXD2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(272, "G2_RXD3"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO272"),
+		MTK_FUNCTION(1, "G2_RXD3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(273, "ESW_INT"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 168),
+		MTK_FUNCTION(0, "GPIO273"),
+		MTK_FUNCTION(1, "ESW_INT")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(274, "G2_RXDV"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO274"),
+		MTK_FUNCTION(1, "G2_RXDV")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(275, "MDC"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO275"),
+		MTK_FUNCTION(1, "MDC"),
+		MTK_FUNCTION(6, "ANT_SEL0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(276, "MDIO"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO276"),
+		MTK_FUNCTION(1, "MDIO"),
+		MTK_FUNCTION(6, "ANT_SEL1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(277, "ESW_RST"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO277"),
+		MTK_FUNCTION(1, "ESW_RST")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(278, "JTAG_RESET"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(0, 147),
+		MTK_FUNCTION(0, "GPIO278"),
+		MTK_FUNCTION(1, "JTAG_RESET")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(279, "USB3_RES_BOND"),
+		NULL, "mt2701",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO279"),
+		MTK_FUNCTION(1, "USB3_RES_BOND")
+	),
+};
+
+#endif /* __PINCTRL_MTK_MT2701_H */
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-mt7623.h b/drivers/pinctrl/mediatek/pinctrl-mtk-mt7623.h
new file mode 100644
index 000000000000..3472a76ad422
--- /dev/null
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-mt7623.h
@@ -0,0 +1,1936 @@
+/*
+ * Copyright (c) 2016 John Crispin <blogic@openwrt.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __PINCTRL_MTK_MT7623_H
+#define __PINCTRL_MTK_MT7623_H
+
+#include <linux/pinctrl/pinctrl.h>
+#include "pinctrl-mtk-common.h"
+
+static const struct mtk_desc_pin mtk_pins_mt7623[] = {
+	MTK_PIN(
+		PINCTRL_PIN(0, "PWRAP_SPI0_MI"),
+		"J20", "mt7623",
+		MTK_EINT_FUNCTION(0, 148),
+		MTK_FUNCTION(0, "GPIO0"),
+		MTK_FUNCTION(1, "PWRAP_SPIDO"),
+		MTK_FUNCTION(2, "PWRAP_SPIDI")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(1, "PWRAP_SPI0_MO"),
+		"D10", "mt7623",
+		MTK_EINT_FUNCTION(0, 149),
+		MTK_FUNCTION(0, "GPIO1"),
+		MTK_FUNCTION(1, "PWRAP_SPIDI"),
+		MTK_FUNCTION(2, "PWRAP_SPIDO")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(2, "PWRAP_INT"),
+		"E11", "mt7623",
+		MTK_EINT_FUNCTION(0, 150),
+		MTK_FUNCTION(0, "GPIO2"),
+		MTK_FUNCTION(1, "PWRAP_INT")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(3, "PWRAP_SPI0_CK"),
+		"H12", "mt7623",
+		MTK_EINT_FUNCTION(0, 151),
+		MTK_FUNCTION(0, "GPIO3"),
+		MTK_FUNCTION(1, "PWRAP_SPICK_I")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(4, "PWRAP_SPI0_CSN"),
+		"E12", "mt7623",
+		MTK_EINT_FUNCTION(0, 152),
+		MTK_FUNCTION(0, "GPIO4"),
+		MTK_FUNCTION(1, "PWRAP_SPICS_B_I")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(5, "PWRAP_SPI0_CK2"),
+		"H11", "mt7623",
+		MTK_EINT_FUNCTION(0, 155),
+		MTK_FUNCTION(0, "GPIO5"),
+		MTK_FUNCTION(1, "PWRAP_SPICK2_I")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(6, "PWRAP_SPI0_CSN2"),
+		"G11", "mt7623",
+		MTK_EINT_FUNCTION(0, 156),
+		MTK_FUNCTION(0, "GPIO6"),
+		MTK_FUNCTION(1, "PWRAP_SPICS2_B_I")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(7, "SPI1_CSN"),
+		"G19", "mt7623",
+		MTK_EINT_FUNCTION(0, 153),
+		MTK_FUNCTION(0, "GPIO7"),
+		MTK_FUNCTION(1, "SPI1_CS")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(8, "SPI1_MI"),
+		"F19", "mt7623",
+		MTK_EINT_FUNCTION(0, 154),
+		MTK_FUNCTION(0, "GPIO8"),
+		MTK_FUNCTION(1, "SPI1_MI"),
+		MTK_FUNCTION(2, "SPI1_MO")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(9, "SPI1_MO"),
+		"G20", "mt7623",
+		MTK_EINT_FUNCTION(0, 157),
+		MTK_FUNCTION(0, "GPIO9"),
+		MTK_FUNCTION(1, "SPI1_MO"),
+		MTK_FUNCTION(2, "SPI1_MI")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(10, "RTC32K_CK"),
+		"A13", "mt7623",
+		MTK_EINT_FUNCTION(0, 158),
+		MTK_FUNCTION(0, "GPIO10"),
+		MTK_FUNCTION(1, "RTC32K_CK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(11, "WATCHDOG"),
+		"D14", "mt7623",
+		MTK_EINT_FUNCTION(0, 159),
+		MTK_FUNCTION(0, "GPIO11"),
+		MTK_FUNCTION(1, "WATCHDOG")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(12, "SRCLKENA"),
+		"C13", "mt7623",
+		MTK_EINT_FUNCTION(0, 169),
+		MTK_FUNCTION(0, "GPIO12"),
+		MTK_FUNCTION(1, "SRCLKENA")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(13, "SRCLKENAI"),
+		"B13", "mt7623",
+		MTK_EINT_FUNCTION(0, 161),
+		MTK_FUNCTION(0, "GPIO13"),
+		MTK_FUNCTION(1, "SRCLKENAI")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(14, "GPIO14"),
+		"E18", "mt7623",
+		MTK_EINT_FUNCTION(0, 162),
+		MTK_FUNCTION(0, "GPIO14"),
+		MTK_FUNCTION(1, "URXD2"),
+		MTK_FUNCTION(2, "UTXD2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(15, "GPIO15"),
+		"E17", "mt7623",
+		MTK_EINT_FUNCTION(0, 163),
+		MTK_FUNCTION(0, "GPIO15"),
+		MTK_FUNCTION(1, "UTXD2"),
+		MTK_FUNCTION(2, "URXD2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(16, "GPIO16"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO16")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(17, "GPIO17"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO17")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(18, "PCM_CLK"),
+		"C19", "mt7623",
+		MTK_EINT_FUNCTION(0, 166),
+		MTK_FUNCTION(0, "GPIO18"),
+		MTK_FUNCTION(1, "PCM_CLK0"),
+		MTK_FUNCTION(6, "AP_PCM_CLKO")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(19, "PCM_SYNC"),
+		"D19", "mt7623",
+		MTK_EINT_FUNCTION(0, 167),
+		MTK_FUNCTION(0, "GPIO19"),
+		MTK_FUNCTION(1, "PCM_SYNC"),
+		MTK_FUNCTION(6, "AP_PCM_SYNC")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(20, "PCM_RX"),
+		"D18", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO20"),
+		MTK_FUNCTION(1, "PCM_RX"),
+		MTK_FUNCTION(4, "PCM_TX"),
+		MTK_FUNCTION(6, "AP_PCM_RX")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(21, "PCM_TX"),
+		"C18", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO21"),
+		MTK_FUNCTION(1, "PCM_TX"),
+		MTK_FUNCTION(4, "PCM_RX"),
+		MTK_FUNCTION(6, "AP_PCM_TX")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(22, "EINT0"),
+		"H15", "mt7623",
+		MTK_EINT_FUNCTION(0, 0),
+		MTK_FUNCTION(0, "GPIO22"),
+		MTK_FUNCTION(1, "UCTS0"),
+		MTK_FUNCTION(2, "PCIE0_PERST_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(23, "EINT1"),
+		"J16", "mt7623",
+		MTK_EINT_FUNCTION(0, 1),
+		MTK_FUNCTION(0, "GPIO23"),
+		MTK_FUNCTION(1, "URTS0"),
+		MTK_FUNCTION(2, "PCIE1_PERST_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(24, "EINT2"),
+		"H16", "mt7623",
+		MTK_EINT_FUNCTION(0, 2),
+		MTK_FUNCTION(0, "GPIO24"),
+		MTK_FUNCTION(1, "UCTS1"),
+		MTK_FUNCTION(2, "PCIE2_PERST_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(25, "EINT3"),
+		"K15", "mt7623",
+		MTK_EINT_FUNCTION(0, 3),
+		MTK_FUNCTION(0, "GPIO25"),
+		MTK_FUNCTION(1, "URTS1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(26, "EINT4"),
+		"G15", "mt7623",
+		MTK_EINT_FUNCTION(0, 4),
+		MTK_FUNCTION(0, "GPIO26"),
+		MTK_FUNCTION(1, "UCTS3"),
+		MTK_FUNCTION(6, "PCIE2_WAKE_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(27, "EINT5"),
+		"F15", "mt7623",
+		MTK_EINT_FUNCTION(0, 5),
+		MTK_FUNCTION(0, "GPIO27"),
+		MTK_FUNCTION(1, "URTS3"),
+		MTK_FUNCTION(6, "PCIE1_WAKE_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(28, "EINT6"),
+		"J15", "mt7623",
+		MTK_EINT_FUNCTION(0, 6),
+		MTK_FUNCTION(0, "GPIO28"),
+		MTK_FUNCTION(1, "DRV_VBUS"),
+		MTK_FUNCTION(6, "PCIE0_WAKE_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(29, "EINT7"),
+		"E15", "mt7623",
+		MTK_EINT_FUNCTION(0, 7),
+		MTK_FUNCTION(0, "GPIO29"),
+		MTK_FUNCTION(1, "IDDIG"),
+		MTK_FUNCTION(2, "MSDC1_WP"),
+		MTK_FUNCTION(6, "PCIE2_PERST_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(30, "GPIO30"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO30")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(31, "GPIO31"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO31")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(32, "GPIO32"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO32")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(33, "I2S1_DATA"),
+		"Y18", "mt7623",
+		MTK_EINT_FUNCTION(0, 15),
+		MTK_FUNCTION(0, "GPIO33"),
+		MTK_FUNCTION(1, "I2S1_DATA"),
+		MTK_FUNCTION(3, "PCM_TX"),
+		MTK_FUNCTION(6, "AP_PCM_TX")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(34, "I2S1_DATA_IN"),
+		"Y17", "mt7623",
+		MTK_EINT_FUNCTION(0, 16),
+		MTK_FUNCTION(0, "GPIO34"),
+		MTK_FUNCTION(1, "I2S1_DATA_IN"),
+		MTK_FUNCTION(3, "PCM_RX"),
+		MTK_FUNCTION(6, "AP_PCM_RX")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(35, "I2S1_BCK"),
+		"V17", "mt7623",
+		MTK_EINT_FUNCTION(0, 17),
+		MTK_FUNCTION(0, "GPIO35"),
+		MTK_FUNCTION(1, "I2S1_BCK"),
+		MTK_FUNCTION(3, "PCM_CLK0"),
+		MTK_FUNCTION(6, "AP_PCM_CLKO")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(36, "I2S1_LRCK"),
+		"W17", "mt7623",
+		MTK_EINT_FUNCTION(0, 18),
+		MTK_FUNCTION(0, "GPIO36"),
+		MTK_FUNCTION(1, "I2S1_LRCK"),
+		MTK_FUNCTION(3, "PCM_SYNC"),
+		MTK_FUNCTION(6, "AP_PCM_SYNC")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(37, "I2S1_MCLK"),
+		"AA18", "mt7623",
+		MTK_EINT_FUNCTION(0, 19),
+		MTK_FUNCTION(0, "GPIO37"),
+		MTK_FUNCTION(1, "I2S1_MCLK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(38, "GPIO38"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO38")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(39, "JTMS"),
+		"G21", "mt7623",
+		MTK_EINT_FUNCTION(0, 21),
+		MTK_FUNCTION(0, "GPIO39"),
+		MTK_FUNCTION(1, "JTMS")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(40, "GPIO40"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO40")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(41, "JTDI"),
+		"H22", "mt7623",
+		MTK_EINT_FUNCTION(0, 23),
+		MTK_FUNCTION(0, "GPIO41"),
+		MTK_FUNCTION(1, "JTDI")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(42, "JTDO"),
+		"H21", "mt7623",
+		MTK_EINT_FUNCTION(0, 24),
+		MTK_FUNCTION(0, "GPIO42"),
+		MTK_FUNCTION(1, "JTDO")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(43, "NCLE"),
+		"C7", "mt7623",
+		MTK_EINT_FUNCTION(0, 25),
+		MTK_FUNCTION(0, "GPIO43"),
+		MTK_FUNCTION(1, "NCLE"),
+		MTK_FUNCTION(2, "EXT_XCS2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(44, "NCEB1"),
+		"C6", "mt7623",
+		MTK_EINT_FUNCTION(0, 26),
+		MTK_FUNCTION(0, "GPIO44"),
+		MTK_FUNCTION(1, "NCEB1"),
+		MTK_FUNCTION(2, "IDDIG")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(45, "NCEB0"),
+		"D7", "mt7623",
+		MTK_EINT_FUNCTION(0, 27),
+		MTK_FUNCTION(0, "GPIO45"),
+		MTK_FUNCTION(1, "NCEB0"),
+		MTK_FUNCTION(2, "DRV_VBUS")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(46, "IR"),
+		"D15", "mt7623",
+		MTK_EINT_FUNCTION(0, 28),
+		MTK_FUNCTION(0, "GPIO46"),
+		MTK_FUNCTION(1, "IR")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(47, "NREB"),
+		"A6", "mt7623",
+		MTK_EINT_FUNCTION(0, 29),
+		MTK_FUNCTION(0, "GPIO47"),
+		MTK_FUNCTION(1, "NREB")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(48, "NRNB"),
+		"B6", "mt7623",
+		MTK_EINT_FUNCTION(0, 30),
+		MTK_FUNCTION(0, "GPIO48"),
+		MTK_FUNCTION(1, "NRNB")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(49, "I2S0_DATA"),
+		"AB18", "mt7623",
+		MTK_EINT_FUNCTION(0, 31),
+		MTK_FUNCTION(0, "GPIO49"),
+		MTK_FUNCTION(1, "I2S0_DATA"),
+		MTK_FUNCTION(3, "PCM_TX"),
+		MTK_FUNCTION(6, "AP_I2S_DO")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(50, "GPIO50"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO50")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(51, "GPIO51"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO51")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(52, "GPIO52"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO52")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(53, "SPI0_CSN"),
+		"E7", "mt7623",
+		MTK_EINT_FUNCTION(0, 35),
+		MTK_FUNCTION(0, "GPIO53"),
+		MTK_FUNCTION(1, "SPI0_CS"),
+		MTK_FUNCTION(5, "PWM1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(54, "SPI0_CK"),
+		"F7", "mt7623",
+		MTK_EINT_FUNCTION(0, 36),
+		MTK_FUNCTION(0, "GPIO54"),
+		MTK_FUNCTION(1, "SPI0_CK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(55, "SPI0_MI"),
+		"E6", "mt7623",
+		MTK_EINT_FUNCTION(0, 37),
+		MTK_FUNCTION(0, "GPIO55"),
+		MTK_FUNCTION(1, "SPI0_MI"),
+		MTK_FUNCTION(2, "SPI0_MO"),
+		MTK_FUNCTION(3, "MSDC1_WP"),
+		MTK_FUNCTION(5, "PWM2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(56, "SPI0_MO"),
+		"G7", "mt7623",
+		MTK_EINT_FUNCTION(0, 38),
+		MTK_FUNCTION(0, "GPIO56"),
+		MTK_FUNCTION(1, "SPI0_MO"),
+		MTK_FUNCTION(2, "SPI0_MI")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(57, "GPIO57"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO57")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(58, "GPIO58"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO58")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(59, "GPIO59"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO59")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(60, "WB_RSTB"),
+		"Y21", "mt7623",
+		MTK_EINT_FUNCTION(0, 41),
+		MTK_FUNCTION(0, "GPIO60"),
+		MTK_FUNCTION(1, "WB_RSTB")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(61, "GPIO61"),
+		"AA21", "mt7623",
+		MTK_EINT_FUNCTION(0, 42),
+		MTK_FUNCTION(0, "GPIO61"),
+		MTK_FUNCTION(1, "TEST_FD")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(62, "GPIO62"),
+		"AB22", "mt7623",
+		MTK_EINT_FUNCTION(0, 43),
+		MTK_FUNCTION(0, "GPIO62"),
+		MTK_FUNCTION(1, "TEST_FC")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(63, "WB_SCLK"),
+		"AC23", "mt7623",
+		MTK_EINT_FUNCTION(0, 44),
+		MTK_FUNCTION(0, "GPIO63"),
+		MTK_FUNCTION(1, "WB_SCLK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(64, "WB_SDATA"),
+		"AB21", "mt7623",
+		MTK_EINT_FUNCTION(0, 45),
+		MTK_FUNCTION(0, "GPIO64"),
+		MTK_FUNCTION(1, "WB_SDATA")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(65, "WB_SEN"),
+		"AB24", "mt7623",
+		MTK_EINT_FUNCTION(0, 46),
+		MTK_FUNCTION(0, "GPIO65"),
+		MTK_FUNCTION(1, "WB_SEN")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(66, "WB_CRTL0"),
+		"AB20", "mt7623",
+		MTK_EINT_FUNCTION(0, 47),
+		MTK_FUNCTION(0, "GPIO66"),
+		MTK_FUNCTION(1, "WB_CRTL0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(67, "WB_CRTL1"),
+		"AC20", "mt7623",
+		MTK_EINT_FUNCTION(0, 48),
+		MTK_FUNCTION(0, "GPIO67"),
+		MTK_FUNCTION(1, "WB_CRTL1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(68, "WB_CRTL2"),
+		"AB19", "mt7623",
+		MTK_EINT_FUNCTION(0, 49),
+		MTK_FUNCTION(0, "GPIO68"),
+		MTK_FUNCTION(1, "WB_CRTL2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(69, "WB_CRTL3"),
+		"AC19", "mt7623",
+		MTK_EINT_FUNCTION(0, 50),
+		MTK_FUNCTION(0, "GPIO69"),
+		MTK_FUNCTION(1, "WB_CRTL3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(70, "WB_CRTL4"),
+		"AD19", "mt7623",
+		MTK_EINT_FUNCTION(0, 51),
+		MTK_FUNCTION(0, "GPIO70"),
+		MTK_FUNCTION(1, "WB_CRTL4")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(71, "WB_CRTL5"),
+		"AE19", "mt7623",
+		MTK_EINT_FUNCTION(0, 52),
+		MTK_FUNCTION(0, "GPIO71"),
+		MTK_FUNCTION(1, "WB_CRTL5")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(72, "I2S0_DATA_IN"),
+		"AA20", "mt7623",
+		MTK_EINT_FUNCTION(0, 53),
+		MTK_FUNCTION(0, "GPIO72"),
+		MTK_FUNCTION(1, "I2S0_DATA_IN"),
+		MTK_FUNCTION(3, "PCM_RX"),
+		MTK_FUNCTION(4, "PWM0"),
+		MTK_FUNCTION(5, "DISP_PWM"),
+		MTK_FUNCTION(6, "AP_I2S_DI")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(73, "I2S0_LRCK"),
+		"Y20", "mt7623",
+		MTK_EINT_FUNCTION(0, 54),
+		MTK_FUNCTION(0, "GPIO73"),
+		MTK_FUNCTION(1, "I2S0_LRCK"),
+		MTK_FUNCTION(3, "PCM_SYNC"),
+		MTK_FUNCTION(6, "AP_I2S_LRCK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(74, "I2S0_BCK"),
+		"Y19", "mt7623",
+		MTK_EINT_FUNCTION(0, 55),
+		MTK_FUNCTION(0, "GPIO74"),
+		MTK_FUNCTION(1, "I2S0_BCK"),
+		MTK_FUNCTION(3, "PCM_CLK0"),
+		MTK_FUNCTION(6, "AP_I2S_BCK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(75, "SDA0"),
+		"K19", "mt7623",
+		MTK_EINT_FUNCTION(0, 56),
+		MTK_FUNCTION(0, "GPIO75"),
+		MTK_FUNCTION(1, "SDA0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(76, "SCL0"),
+		"K20", "mt7623",
+		MTK_EINT_FUNCTION(0, 57),
+		MTK_FUNCTION(0, "GPIO76"),
+		MTK_FUNCTION(1, "SCL0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(77, "GPIO77"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO77")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(78, "GPIO78"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO78")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(79, "GPIO79"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO79")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(80, "GPIO80"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO80")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(81, "GPIO81"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO81")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(82, "GPIO82"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO82")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(83, "LCM_RST"),
+		"V16", "mt7623",
+		MTK_EINT_FUNCTION(0, 64),
+		MTK_FUNCTION(0, "GPIO83"),
+		MTK_FUNCTION(1, "LCM_RST")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(84, "DSI_TE"),
+		"V14", "mt7623",
+		MTK_EINT_FUNCTION(0, 65),
+		MTK_FUNCTION(0, "GPIO84"),
+		MTK_FUNCTION(1, "DSI_TE")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(85, "GPIO85"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO85")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(86, "GPIO86"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO86")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(87, "GPIO87"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO87")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(88, "GPIO88"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO88")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(89, "GPIO89"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO89")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(90, "GPIO90"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO90")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(91, "GPIO91"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO91")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(92, "GPIO92"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO92")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(93, "GPIO93"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO93")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(94, "GPIO94"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO94")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(95, "MIPI_TCN"),
+		"AB14", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO95"),
+		MTK_FUNCTION(1, "TCN")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(96, "MIPI_TCP"),
+		"AC14", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO96"),
+		MTK_FUNCTION(1, "TCP")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(97, "MIPI_TDN1"),
+		"AE15", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO97"),
+		MTK_FUNCTION(1, "TDN1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(98, "MIPI_TDP1"),
+		"AD15", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO98"),
+		MTK_FUNCTION(1, "TDP1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(99, "MIPI_TDN0"),
+		"AB15", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO99"),
+		MTK_FUNCTION(1, "TDN0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(100, "MIPI_TDP0"),
+		"AC15", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO100"),
+		MTK_FUNCTION(1, "TDP0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(101, "GPIO101"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO101")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(102, "GPIO102"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO102")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(103, "GPIO103"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO103")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(104, "GPIO104"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO104")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(105, "MSDC1_CMD"),
+		"AD2", "mt7623",
+		MTK_EINT_FUNCTION(0, 78),
+		MTK_FUNCTION(0, "GPIO105"),
+		MTK_FUNCTION(1, "MSDC1_CMD"),
+		MTK_FUNCTION(3, "SDA1"),
+		MTK_FUNCTION(6, "I2SOUT_BCK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(106, "MSDC1_CLK"),
+		"AD3", "mt7623",
+		MTK_EINT_FUNCTION(0, 79),
+		MTK_FUNCTION(0, "GPIO106"),
+		MTK_FUNCTION(1, "MSDC1_CLK"),
+		MTK_FUNCTION(3, "SCL1"),
+		MTK_FUNCTION(6, "I2SOUT_LRCK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(107, "MSDC1_DAT0"),
+		"AE2", "mt7623",
+		MTK_EINT_FUNCTION(0, 80),
+		MTK_FUNCTION(0, "GPIO107"),
+		MTK_FUNCTION(1, "MSDC1_DAT0"),
+		MTK_FUNCTION(5, "UTXD0"),
+		MTK_FUNCTION(6, "I2SOUT_DATA_OUT")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(108, "MSDC1_DAT1"),
+		"AC1", "mt7623",
+		MTK_EINT_FUNCTION(0, 81),
+		MTK_FUNCTION(0, "GPIO108"),
+		MTK_FUNCTION(1, "MSDC1_DAT1"),
+		MTK_FUNCTION(3, "PWM0"),
+		MTK_FUNCTION(5, "URXD0"),
+		MTK_FUNCTION(6, "PWM1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(109, "MSDC1_DAT2"),
+		"AC3", "mt7623",
+		MTK_EINT_FUNCTION(0, 82),
+		MTK_FUNCTION(0, "GPIO109"),
+		MTK_FUNCTION(1, "MSDC1_DAT2"),
+		MTK_FUNCTION(3, "SDA2"),
+		MTK_FUNCTION(5, "UTXD1"),
+		MTK_FUNCTION(6, "PWM2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(110, "MSDC1_DAT3"),
+		"AC4", "mt7623",
+		MTK_EINT_FUNCTION(0, 83),
+		MTK_FUNCTION(0, "GPIO110"),
+		MTK_FUNCTION(1, "MSDC1_DAT3"),
+		MTK_FUNCTION(3, "SCL2"),
+		MTK_FUNCTION(5, "URXD1"),
+		MTK_FUNCTION(6, "PWM3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(111, "MSDC0_DAT7"),
+		"A2", "mt7623",
+		MTK_EINT_FUNCTION(0, 84),
+		MTK_FUNCTION(0, "GPIO111"),
+		MTK_FUNCTION(1, "MSDC0_DAT7"),
+		MTK_FUNCTION(4, "NLD7")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(112, "MSDC0_DAT6"),
+		"B3", "mt7623",
+		MTK_EINT_FUNCTION(0, 85),
+		MTK_FUNCTION(0, "GPIO112"),
+		MTK_FUNCTION(1, "MSDC0_DAT6"),
+		MTK_FUNCTION(4, "NLD6")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(113, "MSDC0_DAT5"),
+		"C4", "mt7623",
+		MTK_EINT_FUNCTION(0, 86),
+		MTK_FUNCTION(0, "GPIO113"),
+		MTK_FUNCTION(1, "MSDC0_DAT5"),
+		MTK_FUNCTION(4, "NLD5")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(114, "MSDC0_DAT4"),
+		"A4", "mt7623",
+		MTK_EINT_FUNCTION(0, 87),
+		MTK_FUNCTION(0, "GPIO114"),
+		MTK_FUNCTION(1, "MSDC0_DAT4"),
+		MTK_FUNCTION(4, "NLD4")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(115, "MSDC0_RSTB"),
+		"C5", "mt7623",
+		MTK_EINT_FUNCTION(0, 88),
+		MTK_FUNCTION(0, "GPIO115"),
+		MTK_FUNCTION(1, "MSDC0_RSTB"),
+		MTK_FUNCTION(4, "NLD8")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(116, "MSDC0_CMD"),
+		"D5", "mt7623",
+		MTK_EINT_FUNCTION(0, 89),
+		MTK_FUNCTION(0, "GPIO116"),
+		MTK_FUNCTION(1, "MSDC0_CMD"),
+		MTK_FUNCTION(4, "NALE")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(117, "MSDC0_CLK"),
+		"B1", "mt7623",
+		MTK_EINT_FUNCTION(0, 90),
+		MTK_FUNCTION(0, "GPIO117"),
+		MTK_FUNCTION(1, "MSDC0_CLK"),
+		MTK_FUNCTION(4, "NWEB")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(118, "MSDC0_DAT3"),
+		"D6", "mt7623",
+		MTK_EINT_FUNCTION(0, 91),
+		MTK_FUNCTION(0, "GPIO118"),
+		MTK_FUNCTION(1, "MSDC0_DAT3"),
+		MTK_FUNCTION(4, "NLD3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(119, "MSDC0_DAT2"),
+		"B2", "mt7623",
+		MTK_EINT_FUNCTION(0, 92),
+		MTK_FUNCTION(0, "GPIO119"),
+		MTK_FUNCTION(1, "MSDC0_DAT2"),
+		MTK_FUNCTION(4, "NLD2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(120, "MSDC0_DAT1"),
+		"A3", "mt7623",
+		MTK_EINT_FUNCTION(0, 93),
+		MTK_FUNCTION(0, "GPIO120"),
+		MTK_FUNCTION(1, "MSDC0_DAT1"),
+		MTK_FUNCTION(4, "NLD1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(121, "MSDC0_DAT0"),
+		"B4", "mt7623",
+		MTK_EINT_FUNCTION(0, 94),
+		MTK_FUNCTION(0, "GPIO121"),
+		MTK_FUNCTION(1, "MSDC0_DAT0"),
+		MTK_FUNCTION(4, "NLD0"),
+		MTK_FUNCTION(5, "WATCHDOG")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(122, "GPIO122"),
+		"H17", "mt7623",
+		MTK_EINT_FUNCTION(0, 95),
+		MTK_FUNCTION(0, "GPIO122"),
+		MTK_FUNCTION(1, "TEST"),
+		MTK_FUNCTION(4, "SDA2"),
+		MTK_FUNCTION(5, "URXD0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(123, "GPIO123"),
+		"F17", "mt7623",
+		MTK_EINT_FUNCTION(0, 96),
+		MTK_FUNCTION(0, "GPIO123"),
+		MTK_FUNCTION(1, "TEST"),
+		MTK_FUNCTION(4, "SCL2"),
+		MTK_FUNCTION(5, "UTXD0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(124, "GPIO124"),
+		"H18", "mt7623",
+		MTK_EINT_FUNCTION(0, 97),
+		MTK_FUNCTION(0, "GPIO124"),
+		MTK_FUNCTION(1, "TEST"),
+		MTK_FUNCTION(4, "SDA1"),
+		MTK_FUNCTION(5, "PWM3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(125, "GPIO125"),
+		"G17", "mt7623",
+		MTK_EINT_FUNCTION(0, 98),
+		MTK_FUNCTION(0, "GPIO125"),
+		MTK_FUNCTION(1, "TEST"),
+		MTK_FUNCTION(4, "SCL1"),
+		MTK_FUNCTION(5, "PWM4")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(126, "I2S0_MCLK"),
+		"AA19", "mt7623",
+		MTK_EINT_FUNCTION(0, 99),
+		MTK_FUNCTION(0, "GPIO126"),
+		MTK_FUNCTION(1, "I2S0_MCLK"),
+		MTK_FUNCTION(6, "AP_I2S_MCLK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(127, "GPIO127"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO127")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(128, "GPIO128"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO128")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(129, "GPIO129"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO129")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(130, "GPIO130"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO130")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(131, "GPIO131"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO131")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(132, "GPIO132"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO132")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(133, "GPIO133"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO133")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(134, "GPIO134"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO134")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(135, "GPIO135"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO135")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(136, "GPIO136"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO136")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(137, "GPIO137"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO137")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(138, "GPIO138"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO138")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(139, "GPIO139"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO139")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(140, "GPIO140"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO140")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(141, "GPIO141"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO141")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(142, "GPIO142"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO142")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(143, "GPIO143"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO143")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(144, "GPIO144"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO144")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(145, "GPIO145"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO145")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(146, "GPIO146"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO146")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(147, "GPIO147"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO147")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(148, "GPIO148"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO148")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(149, "GPIO149"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO149")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(150, "GPIO150"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO150")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(151, "GPIO151"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO151")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(152, "GPIO152"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO152")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(153, "GPIO153"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO153")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(154, "GPIO154"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO154")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(155, "GPIO155"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO155")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(156, "GPIO156"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO156")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(157, "GPIO157"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO157")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(158, "GPIO158"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO158")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(159, "GPIO159"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO159")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(160, "GPIO160"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO160")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(161, "GPIO161"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO161")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(162, "GPIO162"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO162")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(163, "GPIO163"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO163")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(164, "GPIO164"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO164")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(165, "GPIO165"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO165")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(166, "GPIO166"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO166")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(167, "GPIO167"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO167")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(168, "GPIO168"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO168")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(169, "GPIO169"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO169")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(170, "GPIO170"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO170")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(171, "GPIO171"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO171")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(172, "GPIO172"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO172")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(173, "GPIO173"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO173")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(174, "GPIO174"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO174")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(175, "GPIO175"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO175")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(176, "GPIO176"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO176")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(177, "GPIO177"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO177")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(178, "GPIO178"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO178")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(179, "GPIO179"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO179")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(180, "GPIO180"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO180")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(181, "GPIO181"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO181")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(182, "GPIO182"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO182")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(183, "GPIO183"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO183")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(184, "GPIO184"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO184")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(185, "GPIO185"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO185")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(186, "GPIO186"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO186")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(187, "GPIO187"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO187")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(188, "GPIO188"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO188")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(189, "GPIO189"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO189")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(190, "GPIO190"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO190")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(191, "GPIO191"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO191")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(192, "GPIO192"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO192")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(193, "GPIO193"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO193")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(194, "GPIO194"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO194")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(195, "GPIO195"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO195")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(196, "GPIO196"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO196")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(197, "GPIO197"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO197")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(198, "GPIO198"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO198")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(199, "SPI1_CK"),
+		"E19", "mt7623",
+		MTK_EINT_FUNCTION(0, 111),
+		MTK_FUNCTION(0, "GPIO199"),
+		MTK_FUNCTION(1, "SPI1_CK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(200, "URXD2"),
+		"K18", "mt7623",
+		MTK_EINT_FUNCTION(0, 112),
+		MTK_FUNCTION(0, "GPIO200"),
+		MTK_FUNCTION(6, "URXD2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(201, "UTXD2"),
+		"L18", "mt7623",
+		MTK_EINT_FUNCTION(0, 113),
+		MTK_FUNCTION(0, "GPIO201"),
+		MTK_FUNCTION(6, "UTXD2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(202, "GPIO202"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO202")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(203, "PWM0"),
+		"AA16", "mt7623",
+		MTK_EINT_FUNCTION(0, 115),
+		MTK_FUNCTION(0, "GPIO203"),
+		MTK_FUNCTION(1, "PWM0"),
+		MTK_FUNCTION(2, "DISP_PWM")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(204, "PWM1"),
+		"Y16", "mt7623",
+		MTK_EINT_FUNCTION(0, 116),
+		MTK_FUNCTION(0, "GPIO204"),
+		MTK_FUNCTION(1, "PWM1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(205, "PWM2"),
+		"AA15", "mt7623",
+		MTK_EINT_FUNCTION(0, 117),
+		MTK_FUNCTION(0, "GPIO205"),
+		MTK_FUNCTION(1, "PWM2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(206, "PWM3"),
+		"AA17", "mt7623",
+		MTK_EINT_FUNCTION(0, 118),
+		MTK_FUNCTION(0, "GPIO206"),
+		MTK_FUNCTION(1, "PWM3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(207, "PWM4"),
+		"Y15", "mt7623",
+		MTK_EINT_FUNCTION(0, 119),
+		MTK_FUNCTION(0, "GPIO207"),
+		MTK_FUNCTION(1, "PWM4")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(208, "AUD_EXT_CK1"),
+		"W14", "mt7623",
+		MTK_EINT_FUNCTION(0, 120),
+		MTK_FUNCTION(0, "GPIO208"),
+		MTK_FUNCTION(1, "AUD_EXT_CK1"),
+		MTK_FUNCTION(2, "PWM0"),
+		MTK_FUNCTION(3, "PCIE0_PERST_N"),
+		MTK_FUNCTION(5, "DISP_PWM")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(209, "AUD_EXT_CK2"),
+		"V15", "mt7623",
+		MTK_EINT_FUNCTION(0, 121),
+		MTK_FUNCTION(0, "GPIO209"),
+		MTK_FUNCTION(1, "AUD_EXT_CK2"),
+		MTK_FUNCTION(2, "MSDC1_WP"),
+		MTK_FUNCTION(3, "PCIE1_PERST_N"),
+		MTK_FUNCTION(5, "PWM1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(210, "GPIO210"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO210")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(211, "GPIO211"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO211")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(212, "GPIO212"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO212")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(213, "GPIO213"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO213")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(214, "GPIO214"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO214")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(215, "GPIO215"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO215")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(216, "GPIO216"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO216")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(217, "GPIO217"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO217")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(218, "GPIO218"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO218")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(219, "GPIO219"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO219")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(220, "GPIO220"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO220")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(221, "GPIO221"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO221")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(222, "GPIO222"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO222")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(223, "GPIO223"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO223")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(224, "GPIO224"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO224")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(225, "GPIO225"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO225")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(226, "GPIO226"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO226")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(227, "GPIO227"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO227")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(228, "GPIO228"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO228")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(229, "GPIO229"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO229")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(230, "GPIO230"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO230")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(231, "GPIO231"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO231")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(232, "GPIO232"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO232")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(233, "GPIO233"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO233")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(234, "GPIO234"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO234")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(235, "GPIO235"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO235")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(236, "EXT_SDIO3"),
+		"A8", "mt7623",
+		MTK_EINT_FUNCTION(0, 122),
+		MTK_FUNCTION(0, "GPIO236"),
+		MTK_FUNCTION(1, "EXT_SDIO3"),
+		MTK_FUNCTION(2, "IDDIG")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(237, "EXT_SDIO2"),
+		"D8", "mt7623",
+		MTK_EINT_FUNCTION(0, 123),
+		MTK_FUNCTION(0, "GPIO237"),
+		MTK_FUNCTION(1, "EXT_SDIO2"),
+		MTK_FUNCTION(2, "DRV_VBUS")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(238, "EXT_SDIO1"),
+		"D9", "mt7623",
+		MTK_EINT_FUNCTION(0, 124),
+		MTK_FUNCTION(0, "GPIO238"),
+		MTK_FUNCTION(1, "EXT_SDIO1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(239, "EXT_SDIO0"),
+		"B8", "mt7623",
+		MTK_EINT_FUNCTION(0, 125),
+		MTK_FUNCTION(0, "GPIO239"),
+		MTK_FUNCTION(1, "EXT_SDIO0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(240, "EXT_XCS"),
+		"C9", "mt7623",
+		MTK_EINT_FUNCTION(0, 126),
+		MTK_FUNCTION(0, "GPIO240"),
+		MTK_FUNCTION(1, "EXT_XCS")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(241, "EXT_SCK"),
+		"C8", "mt7623",
+		MTK_EINT_FUNCTION(0, 127),
+		MTK_FUNCTION(0, "GPIO241"),
+		MTK_FUNCTION(1, "EXT_SCK")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(242, "URTS2"),
+		"G18", "mt7623",
+		MTK_EINT_FUNCTION(0, 128),
+		MTK_FUNCTION(0, "GPIO242"),
+		MTK_FUNCTION(1, "URTS2"),
+		MTK_FUNCTION(2, "UTXD3"),
+		MTK_FUNCTION(3, "URXD3"),
+		MTK_FUNCTION(4, "SCL1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(243, "UCTS2"),
+		"H19", "mt7623",
+		MTK_EINT_FUNCTION(0, 129),
+		MTK_FUNCTION(0, "GPIO243"),
+		MTK_FUNCTION(1, "UCTS2"),
+		MTK_FUNCTION(2, "URXD3"),
+		MTK_FUNCTION(3, "UTXD3"),
+		MTK_FUNCTION(4, "SDA1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(244, "GPIO244"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO244")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(245, "GPIO245"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO245")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(246, "GPIO246"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO246")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(247, "GPIO247"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO247")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(248, "GPIO248"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO248")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(249, "GPIO249"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO249")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(250, "GPIO250"),
+		"A15", "mt7623",
+		MTK_EINT_FUNCTION(0, 135),
+		MTK_FUNCTION(0, "GPIO250"),
+		MTK_FUNCTION(1, "TEST_MD7"),
+		MTK_FUNCTION(6, "PCIE0_CLKREQ_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(251, "GPIO251"),
+		"B15", "mt7623",
+		MTK_EINT_FUNCTION(0, 136),
+		MTK_FUNCTION(0, "GPIO251"),
+		MTK_FUNCTION(1, "TEST_MD6"),
+		MTK_FUNCTION(6, "PCIE0_WAKE_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(252, "GPIO252"),
+		"C16", "mt7623",
+		MTK_EINT_FUNCTION(0, 137),
+		MTK_FUNCTION(0, "GPIO252"),
+		MTK_FUNCTION(1, "TEST_MD5"),
+		MTK_FUNCTION(6, "PCIE1_CLKREQ_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(253, "GPIO253"),
+		"D17", "mt7623",
+		MTK_EINT_FUNCTION(0, 138),
+		MTK_FUNCTION(0, "GPIO253"),
+		MTK_FUNCTION(1, "TEST_MD4"),
+		MTK_FUNCTION(6, "PCIE1_WAKE_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(254, "GPIO254"),
+		"D16", "mt7623",
+		MTK_EINT_FUNCTION(0, 139),
+		MTK_FUNCTION(0, "GPIO254"),
+		MTK_FUNCTION(1, "TEST_MD3"),
+		MTK_FUNCTION(6, "PCIE2_CLKREQ_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(255, "GPIO255"),
+		"C17", "mt7623",
+		MTK_EINT_FUNCTION(0, 140),
+		MTK_FUNCTION(0, "GPIO255"),
+		MTK_FUNCTION(1, "TEST_MD2"),
+		MTK_FUNCTION(6, "PCIE2_WAKE_N")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(256, "GPIO256"),
+		"B17", "mt7623",
+		MTK_EINT_FUNCTION(0, 141),
+		MTK_FUNCTION(0, "GPIO256"),
+		MTK_FUNCTION(1, "TEST_MD1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(257, "GPIO257"),
+		"C15", "mt7623",
+		MTK_EINT_FUNCTION(0, 142),
+		MTK_FUNCTION(0, "GPIO257"),
+		MTK_FUNCTION(1, "TEST_MD0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(258, "GPIO258"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO258")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(259, "GPIO259"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO259")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(260, "GPIO260"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO260")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(261, "MSDC1_INS"),
+		"AD1", "mt7623",
+		MTK_EINT_FUNCTION(0, 146),
+		MTK_FUNCTION(0, "GPIO261"),
+		MTK_FUNCTION(1, "MSDC1_INS")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(262, "G2_TXEN"),
+		"A23", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO262"),
+		MTK_FUNCTION(1, "G2_TXEN")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(263, "G2_TXD3"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO263"),
+		MTK_FUNCTION(1, "G2_TXD3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(264, "G2_TXD2"),
+		"C24", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO264"),
+		MTK_FUNCTION(1, "G2_TXD2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(265, "G2_TXD1"),
+		"B25", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO265"),
+		MTK_FUNCTION(1, "G2_TXD1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(266, "G2_TXD0"),
+		"A24", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO266"),
+		MTK_FUNCTION(1, "G2_TXD0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(267, "G2_TXCLK"),
+		"C23", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO267"),
+		MTK_FUNCTION(1, "G2_TXC")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(268, "G2_RXCLK"),
+		"B23", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO268"),
+		MTK_FUNCTION(1, "G2_RXC")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(269, "G2_RXD0"),
+		"D21", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO269"),
+		MTK_FUNCTION(1, "G2_RXD0")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(270, "G2_RXD1"),
+		"B22", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO270"),
+		MTK_FUNCTION(1, "G2_RXD1")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(271, "G2_RXD2"),
+		"A22", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO271"),
+		MTK_FUNCTION(1, "G2_RXD2")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(272, "G2_RXD3"),
+		"C22", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO272"),
+		MTK_FUNCTION(1, "G2_RXD3")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(273, "GPIO273"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO273")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(274, "G2_RXDV"),
+		"C21", "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO274"),
+		MTK_FUNCTION(1, "G2_RXDV")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(275, "G2_MDC"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO275"),
+		MTK_FUNCTION(1, "MDC")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(276, "G2_MDIO"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO276"),
+		MTK_FUNCTION(1, "MDIO")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(277, "GPIO277"),
+		NULL, "mt7623",
+		MTK_EINT_FUNCTION(NO_EINT_SUPPORT, NO_EINT_SUPPORT),
+		MTK_FUNCTION(0, "GPIO277")
+	),
+	MTK_PIN(
+		PINCTRL_PIN(278, "JTAG_RESET"),
+		"H20", "mt7623",
+		MTK_EINT_FUNCTION(0, 147),
+		MTK_FUNCTION(0, "GPIO278"),
+		MTK_FUNCTION(1, "JTAG_RESET")
+	),
+};
+
+#endif /* __PINCTRL_MTK_MT7623_H */
diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c
index 50cab27c64d4..0bdb8fd3afd1 100644
--- a/drivers/pinctrl/meson/pinctrl-meson.c
+++ b/drivers/pinctrl/meson/pinctrl-meson.c
@@ -49,7 +49,6 @@
 #include <linux/gpio.h>
 #include <linux/init.h>
 #include <linux/io.h>
-#include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/pinctrl/pinconf-generic.h>
@@ -104,15 +103,13 @@ static int meson_get_domain_and_bank(struct meson_pinctrl *pc, unsigned int pin,
 				     struct meson_bank **bank)
 {
 	struct meson_domain *d;
-	int i;
 
-	for (i = 0; i < pc->data->num_domains; i++) {
-		d = &pc->domains[i];
-		if (pin >= d->data->pin_base &&
-		    pin < d->data->pin_base + d->data->num_pins) {
-			*domain = d;
-			return meson_get_bank(d, pin, bank);
-		}
+	d = pc->domain;
+
+	if (pin >= d->data->pin_base &&
+	    pin < d->data->pin_base + d->data->num_pins) {
+		*domain = d;
+		return meson_get_bank(d, pin, bank);
 	}
 
 	return -EINVAL;
@@ -204,7 +201,7 @@ static void meson_pmx_disable_other_groups(struct meson_pinctrl *pc,
 		for (j = 0; j < group->num_pins; j++) {
 			if (group->pins[j] == pin) {
 				/* We have found a group using the pin */
-				domain = &pc->domains[group->domain];
+				domain = pc->domain;
 				regmap_update_bits(domain->reg_mux,
 						   group->reg * 4,
 						   BIT(group->bit), 0);
@@ -219,7 +216,7 @@ static int meson_pmx_set_mux(struct pinctrl_dev *pcdev, unsigned func_num,
 	struct meson_pinctrl *pc = pinctrl_dev_get_drvdata(pcdev);
 	struct meson_pmx_func *func = &pc->data->funcs[func_num];
 	struct meson_pmx_group *group = &pc->data->groups[group_num];
-	struct meson_domain *domain = &pc->domains[group->domain];
+	struct meson_domain *domain = pc->domain;
 	int i, ret = 0;
 
 	dev_dbg(pc->dev, "enable function %s, group %s\n", func->name,
@@ -537,76 +534,67 @@ static int meson_gpio_get(struct gpio_chip *chip, unsigned gpio)
 
 static const struct of_device_id meson_pinctrl_dt_match[] = {
 	{
-		.compatible = "amlogic,meson8-pinctrl",
-		.data = &meson8_pinctrl_data,
+		.compatible = "amlogic,meson8-cbus-pinctrl",
+		.data = &meson8_cbus_pinctrl_data,
+	},
+	{
+		.compatible = "amlogic,meson8b-cbus-pinctrl",
+		.data = &meson8b_cbus_pinctrl_data,
+	},
+	{
+		.compatible = "amlogic,meson8-aobus-pinctrl",
+		.data = &meson8_aobus_pinctrl_data,
 	},
 	{
-		.compatible = "amlogic,meson8b-pinctrl",
-		.data = &meson8b_pinctrl_data,
+		.compatible = "amlogic,meson8b-aobus-pinctrl",
+		.data = &meson8b_aobus_pinctrl_data,
 	},
 	{ },
 };
-MODULE_DEVICE_TABLE(of, meson_pinctrl_dt_match);
 
 static int meson_gpiolib_register(struct meson_pinctrl *pc)
 {
 	struct meson_domain *domain;
-	int i, ret;
+	int ret;
 
-	for (i = 0; i < pc->data->num_domains; i++) {
-		domain = &pc->domains[i];
-
-		domain->chip.label = domain->data->name;
-		domain->chip.parent = pc->dev;
-		domain->chip.request = meson_gpio_request;
-		domain->chip.free = meson_gpio_free;
-		domain->chip.direction_input = meson_gpio_direction_input;
-		domain->chip.direction_output = meson_gpio_direction_output;
-		domain->chip.get = meson_gpio_get;
-		domain->chip.set = meson_gpio_set;
-		domain->chip.base = domain->data->pin_base;
-		domain->chip.ngpio = domain->data->num_pins;
-		domain->chip.can_sleep = false;
-		domain->chip.of_node = domain->of_node;
-		domain->chip.of_gpio_n_cells = 2;
-
-		ret = gpiochip_add_data(&domain->chip, domain);
-		if (ret) {
-			dev_err(pc->dev, "can't add gpio chip %s\n",
-				domain->data->name);
-			goto fail;
-		}
+	domain = pc->domain;
+
+	domain->chip.label = domain->data->name;
+	domain->chip.parent = pc->dev;
+	domain->chip.request = meson_gpio_request;
+	domain->chip.free = meson_gpio_free;
+	domain->chip.direction_input = meson_gpio_direction_input;
+	domain->chip.direction_output = meson_gpio_direction_output;
+	domain->chip.get = meson_gpio_get;
+	domain->chip.set = meson_gpio_set;
+	domain->chip.base = domain->data->pin_base;
+	domain->chip.ngpio = domain->data->num_pins;
+	domain->chip.can_sleep = false;
+	domain->chip.of_node = domain->of_node;
+	domain->chip.of_gpio_n_cells = 2;
+
+	ret = gpiochip_add_data(&domain->chip, domain);
+	if (ret) {
+		dev_err(pc->dev, "can't add gpio chip %s\n",
+			domain->data->name);
+		goto fail;
+	}
 
-		ret = gpiochip_add_pin_range(&domain->chip, dev_name(pc->dev),
-					     0, domain->data->pin_base,
-					     domain->chip.ngpio);
-		if (ret) {
-			dev_err(pc->dev, "can't add pin range\n");
-			goto fail;
-		}
+	ret = gpiochip_add_pin_range(&domain->chip, dev_name(pc->dev),
+				     0, domain->data->pin_base,
+				     domain->chip.ngpio);
+	if (ret) {
+		dev_err(pc->dev, "can't add pin range\n");
+		goto fail;
 	}
 
 	return 0;
 fail:
-	for (i--; i >= 0; i--)
-		gpiochip_remove(&pc->domains[i].chip);
+	gpiochip_remove(&pc->domain->chip);
 
 	return ret;
 }
 
-static struct meson_domain_data *meson_get_domain_data(struct meson_pinctrl *pc,
-						       struct device_node *np)
-{
-	int i;
-
-	for (i = 0; i < pc->data->num_domains; i++) {
-		if (!strcmp(np->name, pc->data->domain_data[i].name))
-			return &pc->data->domain_data[i];
-	}
-
-	return NULL;
-}
-
 static struct regmap_config meson_regmap_config = {
 	.reg_bits = 32,
 	.val_bits = 32,
@@ -643,7 +631,7 @@ static int meson_pinctrl_parse_dt(struct meson_pinctrl *pc,
 {
 	struct device_node *np;
 	struct meson_domain *domain;
-	int i = 0, num_domains = 0;
+	int num_domains = 0;
 
 	for_each_child_of_node(node, np) {
 		if (!of_find_property(np, "gpio-controller", NULL))
@@ -651,29 +639,22 @@ static int meson_pinctrl_parse_dt(struct meson_pinctrl *pc,
 		num_domains++;
 	}
 
-	if (num_domains != pc->data->num_domains) {
+	if (num_domains != 1) {
 		dev_err(pc->dev, "wrong number of subnodes\n");
 		return -EINVAL;
 	}
 
-	pc->domains = devm_kzalloc(pc->dev, num_domains *
-				   sizeof(struct meson_domain), GFP_KERNEL);
-	if (!pc->domains)
+	pc->domain = devm_kzalloc(pc->dev, sizeof(struct meson_domain), GFP_KERNEL);
+	if (!pc->domain)
 		return -ENOMEM;
 
+	domain = pc->domain;
+	domain->data = pc->data->domain_data;
+
 	for_each_child_of_node(node, np) {
 		if (!of_find_property(np, "gpio-controller", NULL))
 			continue;
 
-		domain = &pc->domains[i];
-
-		domain->data = meson_get_domain_data(pc, np);
-		if (!domain->data) {
-			dev_err(pc->dev, "domain data not found for node %s\n",
-				np->name);
-			return -ENODEV;
-		}
-
 		domain->of_node = np;
 
 		domain->reg_mux = meson_map_resource(pc, np, "mux");
@@ -699,7 +680,7 @@ static int meson_pinctrl_parse_dt(struct meson_pinctrl *pc,
 			return PTR_ERR(domain->reg_gpio);
 		}
 
-		i++;
+		break;
 	}
 
 	return 0;
@@ -718,7 +699,7 @@ static int meson_pinctrl_probe(struct platform_device *pdev)
 
 	pc->dev = dev;
 	match = of_match_node(meson_pinctrl_dt_match, pdev->dev.of_node);
-	pc->data = (struct meson_pinctrl_data *)match->data;
+	pc->data = (struct meson_pinctrl_data *) match->data;
 
 	ret = meson_pinctrl_parse_dt(pc, pdev->dev.of_node);
 	if (ret)
@@ -754,8 +735,4 @@ static struct platform_driver meson_pinctrl_driver = {
 		.of_match_table = meson_pinctrl_dt_match,
 	},
 };
-module_platform_driver(meson_pinctrl_driver);
-
-MODULE_AUTHOR("Beniamino Galvani <b.galvani@gmail.com>");
-MODULE_DESCRIPTION("Amlogic Meson pinctrl driver");
-MODULE_LICENSE("GPL v2");
+builtin_platform_driver(meson_pinctrl_driver);
diff --git a/drivers/pinctrl/meson/pinctrl-meson.h b/drivers/pinctrl/meson/pinctrl-meson.h
index 0fe7d53849ce..9c93e0d494a3 100644
--- a/drivers/pinctrl/meson/pinctrl-meson.h
+++ b/drivers/pinctrl/meson/pinctrl-meson.h
@@ -34,7 +34,6 @@ struct meson_pmx_group {
 	bool is_gpio;
 	unsigned int reg;
 	unsigned int bit;
-	unsigned int domain;
 };
 
 /**
@@ -144,7 +143,6 @@ struct meson_pinctrl_data {
 	unsigned int num_pins;
 	unsigned int num_groups;
 	unsigned int num_funcs;
-	unsigned int num_domains;
 };
 
 struct meson_pinctrl {
@@ -152,7 +150,7 @@ struct meson_pinctrl {
 	struct pinctrl_dev *pcdev;
 	struct pinctrl_desc desc;
 	struct meson_pinctrl_data *data;
-	struct meson_domain *domains;
+	struct meson_domain *domain;
 };
 
 #define PIN(x, b)	(b + x)
@@ -164,7 +162,6 @@ struct meson_pinctrl {
 		.num_pins = ARRAY_SIZE(grp ## _pins),			\
 		.reg = r,						\
 		.bit = b,						\
-		.domain = 0,						\
 	 }
 
 #define GPIO_GROUP(gpio, b)						\
@@ -175,16 +172,6 @@ struct meson_pinctrl {
 		.is_gpio = true,					\
 	 }
 
-#define GROUP_AO(grp, r, b)						\
-	{								\
-		.name = #grp,						\
-		.pins = grp ## _pins,					\
-		.num_pins = ARRAY_SIZE(grp ## _pins),			\
-		.reg = r,						\
-		.bit = b,						\
-		.domain = 1,						\
-	 }
-
 #define FUNCTION(fn)							\
 	{								\
 		.name = #fn,						\
@@ -208,5 +195,7 @@ struct meson_pinctrl {
 
 #define MESON_PIN(x, b) PINCTRL_PIN(PIN(x, b), #x)
 
-extern struct meson_pinctrl_data meson8_pinctrl_data;
-extern struct meson_pinctrl_data meson8b_pinctrl_data;
+extern struct meson_pinctrl_data meson8_cbus_pinctrl_data;
+extern struct meson_pinctrl_data meson8_aobus_pinctrl_data;
+extern struct meson_pinctrl_data meson8b_cbus_pinctrl_data;
+extern struct meson_pinctrl_data meson8b_aobus_pinctrl_data;
diff --git a/drivers/pinctrl/meson/pinctrl-meson8.c b/drivers/pinctrl/meson/pinctrl-meson8.c
index 7b1cc91733ef..32de191e0807 100644
--- a/drivers/pinctrl/meson/pinctrl-meson8.c
+++ b/drivers/pinctrl/meson/pinctrl-meson8.c
@@ -16,7 +16,7 @@
 
 #define AO_OFF	120
 
-static const struct pinctrl_pin_desc meson8_pins[] = {
+static const struct pinctrl_pin_desc meson8_cbus_pins[] = {
 	MESON_PIN(GPIOX_0, 0),
 	MESON_PIN(GPIOX_1, 0),
 	MESON_PIN(GPIOX_2, 0),
@@ -137,6 +137,9 @@ static const struct pinctrl_pin_desc meson8_pins[] = {
 	MESON_PIN(BOOT_16, 0),
 	MESON_PIN(BOOT_17, 0),
 	MESON_PIN(BOOT_18, 0),
+};
+
+static const struct pinctrl_pin_desc meson8_aobus_pins[] = {
 	MESON_PIN(GPIOAO_0, AO_OFF),
 	MESON_PIN(GPIOAO_1, AO_OFF),
 	MESON_PIN(GPIOAO_2, AO_OFF),
@@ -379,7 +382,7 @@ static const unsigned int uart_rx_ao_b1_pins[] = { PIN(GPIOAO_5, AO_OFF) };
 static const unsigned int i2c_mst_sck_ao_pins[] = { PIN(GPIOAO_4, AO_OFF) };
 static const unsigned int i2c_mst_sda_ao_pins[] = { PIN(GPIOAO_5, AO_OFF) };
 
-static struct meson_pmx_group meson8_groups[] = {
+static struct meson_pmx_group meson8_cbus_groups[] = {
 	GPIO_GROUP(GPIOX_0, 0),
 	GPIO_GROUP(GPIOX_1, 0),
 	GPIO_GROUP(GPIOX_2, 0),
@@ -474,22 +477,6 @@ static struct meson_pmx_group meson8_groups[] = {
 	GPIO_GROUP(GPIOZ_12, 0),
 	GPIO_GROUP(GPIOZ_13, 0),
 	GPIO_GROUP(GPIOZ_14, 0),
-	GPIO_GROUP(GPIOAO_0, AO_OFF),
-	GPIO_GROUP(GPIOAO_1, AO_OFF),
-	GPIO_GROUP(GPIOAO_2, AO_OFF),
-	GPIO_GROUP(GPIOAO_3, AO_OFF),
-	GPIO_GROUP(GPIOAO_4, AO_OFF),
-	GPIO_GROUP(GPIOAO_5, AO_OFF),
-	GPIO_GROUP(GPIOAO_6, AO_OFF),
-	GPIO_GROUP(GPIOAO_7, AO_OFF),
-	GPIO_GROUP(GPIOAO_8, AO_OFF),
-	GPIO_GROUP(GPIOAO_9, AO_OFF),
-	GPIO_GROUP(GPIOAO_10, AO_OFF),
-	GPIO_GROUP(GPIOAO_11, AO_OFF),
-	GPIO_GROUP(GPIOAO_12, AO_OFF),
-	GPIO_GROUP(GPIOAO_13, AO_OFF),
-	GPIO_GROUP(GPIO_BSD_EN, AO_OFF),
-	GPIO_GROUP(GPIO_TEST_N, AO_OFF),
 
 	/* bank X */
 	GROUP(sd_d0_a,		8,	5),
@@ -675,26 +662,45 @@ static struct meson_pmx_group meson8_groups[] = {
 	GROUP(sdxc_d0_b,	2,	7),
 	GROUP(sdxc_clk_b,	2,	5),
 	GROUP(sdxc_cmd_b,	2,	4),
+};
+
+static struct meson_pmx_group meson8_aobus_groups[] = {
+	GPIO_GROUP(GPIOAO_0, AO_OFF),
+	GPIO_GROUP(GPIOAO_1, AO_OFF),
+	GPIO_GROUP(GPIOAO_2, AO_OFF),
+	GPIO_GROUP(GPIOAO_3, AO_OFF),
+	GPIO_GROUP(GPIOAO_4, AO_OFF),
+	GPIO_GROUP(GPIOAO_5, AO_OFF),
+	GPIO_GROUP(GPIOAO_6, AO_OFF),
+	GPIO_GROUP(GPIOAO_7, AO_OFF),
+	GPIO_GROUP(GPIOAO_8, AO_OFF),
+	GPIO_GROUP(GPIOAO_9, AO_OFF),
+	GPIO_GROUP(GPIOAO_10, AO_OFF),
+	GPIO_GROUP(GPIOAO_11, AO_OFF),
+	GPIO_GROUP(GPIOAO_12, AO_OFF),
+	GPIO_GROUP(GPIOAO_13, AO_OFF),
+	GPIO_GROUP(GPIO_BSD_EN, AO_OFF),
+	GPIO_GROUP(GPIO_TEST_N, AO_OFF),
 
 	/* bank AO */
-	GROUP_AO(uart_tx_ao_a,		0,	12),
-	GROUP_AO(uart_rx_ao_a,		0,	11),
-	GROUP_AO(uart_cts_ao_a,		0,	10),
-	GROUP_AO(uart_rts_ao_a,		0,	9),
+	GROUP(uart_tx_ao_a,		0,	12),
+	GROUP(uart_rx_ao_a,		0,	11),
+	GROUP(uart_cts_ao_a,		0,	10),
+	GROUP(uart_rts_ao_a,		0,	9),
 
-	GROUP_AO(remote_input,		0,	0),
+	GROUP(remote_input,		0,	0),
 
-	GROUP_AO(i2c_slave_sck_ao,	0,	2),
-	GROUP_AO(i2c_slave_sda_ao,	0,	1),
+	GROUP(i2c_slave_sck_ao,		0,	2),
+	GROUP(i2c_slave_sda_ao,		0,	1),
 
-	GROUP_AO(uart_tx_ao_b0,		0,	26),
-	GROUP_AO(uart_rx_ao_b0,		0,	25),
+	GROUP(uart_tx_ao_b0,		0,	26),
+	GROUP(uart_rx_ao_b0,		0,	25),
 
-	GROUP_AO(uart_tx_ao_b1,		0,	24),
-	GROUP_AO(uart_rx_ao_b1,		0,	23),
+	GROUP(uart_tx_ao_b1,		0,	24),
+	GROUP(uart_rx_ao_b1,		0,	23),
 
-	GROUP_AO(i2c_mst_sck_ao,	0,	6),
-	GROUP_AO(i2c_mst_sda_ao,	0,	5),
+	GROUP(i2c_mst_sck_ao,		0,	6),
+	GROUP(i2c_mst_sda_ao,		0,	5),
 };
 
 static const char * const gpio_groups[] = {
@@ -872,7 +878,7 @@ static const char * const i2c_mst_ao_groups[] = {
 	"i2c_mst_sck_ao", "i2c_mst_sda_ao"
 };
 
-static struct meson_pmx_func meson8_functions[] = {
+static struct meson_pmx_func meson8_cbus_functions[] = {
 	FUNCTION(gpio),
 	FUNCTION(sd_a),
 	FUNCTION(sdxc_a),
@@ -899,6 +905,9 @@ static struct meson_pmx_func meson8_functions[] = {
 	FUNCTION(nor),
 	FUNCTION(sd_b),
 	FUNCTION(sdxc_b),
+};
+
+static struct meson_pmx_func meson8_aobus_functions[] = {
 	FUNCTION(uart_ao),
 	FUNCTION(remote),
 	FUNCTION(i2c_slave_ao),
@@ -906,7 +915,7 @@ static struct meson_pmx_func meson8_functions[] = {
 	FUNCTION(i2c_mst_ao),
 };
 
-static struct meson_bank meson8_banks[] = {
+static struct meson_bank meson8_cbus_banks[] = {
 	/*   name    first             last                 pullen  pull    dir     out     in  */
 	BANK("X",    PIN(GPIOX_0, 0),  PIN(GPIOX_21, 0),    4,  0,  4,  0,  0,  0,  1,  0,  2,  0),
 	BANK("Y",    PIN(GPIOY_0, 0),  PIN(GPIOY_16, 0),    3,  0,  3,  0,  3,  0,  4,  0,  5,  0),
@@ -917,35 +926,43 @@ static struct meson_bank meson8_banks[] = {
 	BANK("BOOT", PIN(BOOT_0, 0),   PIN(BOOT_18, 0),     2,  0,  2,  0,  9,  0, 10,  0, 11,  0),
 };
 
-static struct meson_bank meson8_ao_banks[] = {
+static struct meson_bank meson8_aobus_banks[] = {
 	/*   name    first                  last                      pullen  pull    dir     out     in  */
 	BANK("AO",   PIN(GPIOAO_0, AO_OFF), PIN(GPIO_TEST_N, AO_OFF), 0,  0,  0, 16,  0,  0,  0, 16,  1,  0),
 };
 
-static struct meson_domain_data meson8_domain_data[] = {
-	{
-		.name		= "banks",
-		.banks		= meson8_banks,
-		.num_banks	= ARRAY_SIZE(meson8_banks),
-		.pin_base	= 0,
-		.num_pins	= 120,
-	},
-	{
-		.name		= "ao-bank",
-		.banks		= meson8_ao_banks,
-		.num_banks	= ARRAY_SIZE(meson8_ao_banks),
-		.pin_base	= 120,
-		.num_pins	= 16,
-	},
-};
-
-struct meson_pinctrl_data meson8_pinctrl_data = {
-	.pins		= meson8_pins,
-	.groups		= meson8_groups,
-	.funcs		= meson8_functions,
-	.domain_data	= meson8_domain_data,
-	.num_pins	= ARRAY_SIZE(meson8_pins),
-	.num_groups	= ARRAY_SIZE(meson8_groups),
-	.num_funcs	= ARRAY_SIZE(meson8_functions),
-	.num_domains	= ARRAY_SIZE(meson8_domain_data),
+static struct meson_domain_data meson8_cbus_domain_data = {
+	.name		= "cbus-banks",
+	.banks		= meson8_cbus_banks,
+	.num_banks	= ARRAY_SIZE(meson8_cbus_banks),
+	.pin_base	= 0,
+	.num_pins	= 120,
+};
+
+static struct meson_domain_data meson8_aobus_domain_data = {
+	.name		= "ao-bank",
+	.banks		= meson8_aobus_banks,
+	.num_banks	= ARRAY_SIZE(meson8_aobus_banks),
+	.pin_base	= 120,
+	.num_pins	= 16,
+};
+
+struct meson_pinctrl_data meson8_cbus_pinctrl_data = {
+	.pins		= meson8_cbus_pins,
+	.groups		= meson8_cbus_groups,
+	.funcs		= meson8_cbus_functions,
+	.domain_data	= &meson8_cbus_domain_data,
+	.num_pins	= ARRAY_SIZE(meson8_cbus_pins),
+	.num_groups	= ARRAY_SIZE(meson8_cbus_groups),
+	.num_funcs	= ARRAY_SIZE(meson8_cbus_functions),
+};
+
+struct meson_pinctrl_data meson8_aobus_pinctrl_data = {
+	.pins		= meson8_aobus_pins,
+	.groups		= meson8_aobus_groups,
+	.funcs		= meson8_aobus_functions,
+	.domain_data	= &meson8_aobus_domain_data,
+	.num_pins	= ARRAY_SIZE(meson8_aobus_pins),
+	.num_groups	= ARRAY_SIZE(meson8_aobus_groups),
+	.num_funcs	= ARRAY_SIZE(meson8_aobus_functions),
 };
diff --git a/drivers/pinctrl/meson/pinctrl-meson8b.c b/drivers/pinctrl/meson/pinctrl-meson8b.c
index 9677807db364..a100bcf4b17f 100644
--- a/drivers/pinctrl/meson/pinctrl-meson8b.c
+++ b/drivers/pinctrl/meson/pinctrl-meson8b.c
@@ -17,7 +17,7 @@
 
 #define AO_OFF	130
 
-static const struct pinctrl_pin_desc meson8b_pins[] = {
+static const struct pinctrl_pin_desc meson8b_cbus_pins[] = {
 	MESON_PIN(GPIOX_0, 0),
 	MESON_PIN(GPIOX_1, 0),
 	MESON_PIN(GPIOX_2, 0),
@@ -107,7 +107,9 @@ static const struct pinctrl_pin_desc meson8b_pins[] = {
 	MESON_PIN(DIF_3_N, 0),
 	MESON_PIN(DIF_4_P, 0),
 	MESON_PIN(DIF_4_N, 0),
+};
 
+static const struct pinctrl_pin_desc meson8b_aobus_pins[] = {
 	MESON_PIN(GPIOAO_0, AO_OFF),
 	MESON_PIN(GPIOAO_1, AO_OFF),
 	MESON_PIN(GPIOAO_2, AO_OFF),
@@ -346,7 +348,7 @@ static const unsigned int eth_ref_clk_pins[]	= { PIN(DIF_3_N, 0) };
 static const unsigned int eth_mdc_pins[]	= { PIN(DIF_4_P, 0) };
 static const unsigned int eth_mdio_en_pins[]	= { PIN(DIF_4_N, 0) };
 
-static struct meson_pmx_group meson8b_groups[] = {
+static struct meson_pmx_group meson8b_cbus_groups[] = {
 	GPIO_GROUP(GPIOX_0, 0),
 	GPIO_GROUP(GPIOX_1, 0),
 	GPIO_GROUP(GPIOX_2, 0),
@@ -409,23 +411,6 @@ static struct meson_pmx_group meson8b_groups[] = {
 	GPIO_GROUP(DIF_4_P, 0),
 	GPIO_GROUP(DIF_4_N, 0),
 
-	GPIO_GROUP(GPIOAO_0, AO_OFF),
-	GPIO_GROUP(GPIOAO_1, AO_OFF),
-	GPIO_GROUP(GPIOAO_2, AO_OFF),
-	GPIO_GROUP(GPIOAO_3, AO_OFF),
-	GPIO_GROUP(GPIOAO_4, AO_OFF),
-	GPIO_GROUP(GPIOAO_5, AO_OFF),
-	GPIO_GROUP(GPIOAO_6, AO_OFF),
-	GPIO_GROUP(GPIOAO_7, AO_OFF),
-	GPIO_GROUP(GPIOAO_8, AO_OFF),
-	GPIO_GROUP(GPIOAO_9, AO_OFF),
-	GPIO_GROUP(GPIOAO_10, AO_OFF),
-	GPIO_GROUP(GPIOAO_11, AO_OFF),
-	GPIO_GROUP(GPIOAO_12, AO_OFF),
-	GPIO_GROUP(GPIOAO_13, AO_OFF),
-	GPIO_GROUP(GPIO_BSD_EN, AO_OFF),
-	GPIO_GROUP(GPIO_TEST_N, AO_OFF),
-
 	/* bank X */
 	GROUP(sd_d0_a,		8,	5),
 	GROUP(sd_d1_a,		8,	4),
@@ -572,6 +557,37 @@ static struct meson_pmx_group meson8b_groups[] = {
 	GROUP(sdxc_clk_b,	2,	5),
 	GROUP(sdxc_cmd_b,	2,	4),
 
+	/* bank DIF */
+	GROUP(eth_rxd1,		6,	0),
+	GROUP(eth_rxd0,		6,	1),
+	GROUP(eth_rx_dv,	6,	2),
+	GROUP(eth_rx_clk,	6,	3),
+	GROUP(eth_txd0_1,	6,	4),
+	GROUP(eth_txd1_1,	6,	5),
+	GROUP(eth_tx_en,	6,	0),
+	GROUP(eth_ref_clk,	6,	8),
+	GROUP(eth_mdc,		6,	9),
+	GROUP(eth_mdio_en,	6,	10),
+};
+
+static struct meson_pmx_group meson8b_aobus_groups[] = {
+	GPIO_GROUP(GPIOAO_0, AO_OFF),
+	GPIO_GROUP(GPIOAO_1, AO_OFF),
+	GPIO_GROUP(GPIOAO_2, AO_OFF),
+	GPIO_GROUP(GPIOAO_3, AO_OFF),
+	GPIO_GROUP(GPIOAO_4, AO_OFF),
+	GPIO_GROUP(GPIOAO_5, AO_OFF),
+	GPIO_GROUP(GPIOAO_6, AO_OFF),
+	GPIO_GROUP(GPIOAO_7, AO_OFF),
+	GPIO_GROUP(GPIOAO_8, AO_OFF),
+	GPIO_GROUP(GPIOAO_9, AO_OFF),
+	GPIO_GROUP(GPIOAO_10, AO_OFF),
+	GPIO_GROUP(GPIOAO_11, AO_OFF),
+	GPIO_GROUP(GPIOAO_12, AO_OFF),
+	GPIO_GROUP(GPIOAO_13, AO_OFF),
+	GPIO_GROUP(GPIO_BSD_EN, AO_OFF),
+	GPIO_GROUP(GPIO_TEST_N, AO_OFF),
+
 	/* bank AO */
 	GROUP(uart_tx_ao_a,	0,	12),
 	GROUP(uart_rx_ao_a,	0,	11),
@@ -601,18 +617,6 @@ static struct meson_pmx_group meson8b_groups[] = {
 	GROUP(i2s_in_ch01,	0,	13),
 	GROUP(i2s_ao_clk_in,	0,	15),
 	GROUP(i2s_lr_clk_in,	0,	14),
-
-	/* bank DIF */
-	GROUP(eth_rxd1,		6,	0),
-	GROUP(eth_rxd0,		6,	1),
-	GROUP(eth_rx_dv,	6,	2),
-	GROUP(eth_rx_clk,	6,	3),
-	GROUP(eth_txd0_1,	6,	4),
-	GROUP(eth_txd1_1,	6,	5),
-	GROUP(eth_tx_en,	6,	0),
-	GROUP(eth_ref_clk,	6,	8),
-	GROUP(eth_mdc,		6,	9),
-	GROUP(eth_mdio_en,	6,	10),
 };
 
 static const char * const gpio_groups[] = {
@@ -694,7 +698,10 @@ static const char * const i2c_c_groups[] = {
 };
 
 static const char * const hdmi_groups[] = {
-	"hdmi_hpd", "hdmi_sda", "hdmi_scl", "hdmi_cec_0",
+	"hdmi_hpd", "hdmi_sda", "hdmi_scl", "hdmi_cec_0"
+};
+
+static const char * const hdmi_cec_groups[] = {
 	"hdmi_cec_1"
 };
 
@@ -770,12 +777,20 @@ static const char * const i2c_mst_ao_groups[] = {
 	"i2c_mst_sck_ao", "i2c_mst_sda_ao"
 };
 
-static const char * const clk_groups[] = {
-	"clk_24m_out", "clk_32k_in_out"
+static const char * const clk_24m_groups[] = {
+	"clk_24m_out"
 };
 
-static const char * const spdif_groups[] = {
-	"spdif_out_1", "spdif_out_0"
+static const char * const clk_32k_groups[] = {
+	"clk_32k_in_out"
+};
+
+static const char * const spdif_0_groups[] = {
+	"spdif_out_0"
+};
+
+static const char * const spdif_1_groups[] = {
+	"spdif_out_1"
 };
 
 static const char * const i2s_groups[] = {
@@ -789,7 +804,11 @@ static const char * const pwm_b_groups[] = {
 };
 
 static const char * const pwm_c_groups[] = {
-	"pwm_c0", "pwm_c1", "pwm_c2"
+	"pwm_c0", "pwm_c1"
+};
+
+static const char * const pwm_c_ao_groups[] = {
+	"pwm_c2"
 };
 
 static const char * const pwm_d_groups[] = {
@@ -814,7 +833,7 @@ static const char * const tsin_b_groups[] = {
 	"tsin_d0_b", "tsin_clk_b", "tsin_sop_b", "tsin_d_valid_b"
 };
 
-static struct meson_pmx_func meson8b_functions[] = {
+static struct meson_pmx_func meson8b_cbus_functions[] = {
 	FUNCTION(gpio),
 	FUNCTION(sd_a),
 	FUNCTION(sdxc_a),
@@ -837,14 +856,7 @@ static struct meson_pmx_func meson8b_functions[] = {
 	FUNCTION(nor),
 	FUNCTION(sd_b),
 	FUNCTION(sdxc_b),
-	FUNCTION(uart_ao),
-	FUNCTION(remote),
-	FUNCTION(i2c_slave_ao),
-	FUNCTION(uart_ao_b),
-	FUNCTION(i2c_mst_ao),
-	FUNCTION(clk),
-	FUNCTION(spdif),
-	FUNCTION(i2s),
+	FUNCTION(spdif_0),
 	FUNCTION(pwm_b),
 	FUNCTION(pwm_c),
 	FUNCTION(pwm_d),
@@ -852,9 +864,23 @@ static struct meson_pmx_func meson8b_functions[] = {
 	FUNCTION(pwm_vs),
 	FUNCTION(tsin_a),
 	FUNCTION(tsin_b),
+	FUNCTION(clk_24m),
+};
+
+static struct meson_pmx_func meson8b_aobus_functions[] = {
+	FUNCTION(uart_ao),
+	FUNCTION(uart_ao_b),
+	FUNCTION(i2c_slave_ao),
+	FUNCTION(i2c_mst_ao),
+	FUNCTION(i2s),
+	FUNCTION(remote),
+	FUNCTION(clk_32k),
+	FUNCTION(pwm_c_ao),
+	FUNCTION(spdif_1),
+	FUNCTION(hdmi_cec),
 };
 
-static struct meson_bank meson8b_banks[] = {
+static struct meson_bank meson8b_cbus_banks[] = {
 	/*   name    first                      last                   pullen  pull    dir     out     in  */
 	BANK("X",    PIN(GPIOX_0, 0),		PIN(GPIOX_21, 0),      4,  0,  4,  0,  0,  0,  1,  0,  2,  0),
 	BANK("Y",    PIN(GPIOY_0, 0),		PIN(GPIOY_14, 0),      3,  0,  3,  0,  3,  0,  4,  0,  5,  0),
@@ -865,35 +891,43 @@ static struct meson_bank meson8b_banks[] = {
 	BANK("DIF",  PIN(DIF_0_P, 0),		PIN(DIF_4_N, 0),       5,  8,  5,  8, 12, 12, 13, 12, 14, 12),
 };
 
-static struct meson_bank meson8b_ao_banks[] = {
+static struct meson_bank meson8b_aobus_banks[] = {
 	/*   name    first                  last                      pullen  pull    dir     out     in  */
 	BANK("AO",   PIN(GPIOAO_0, AO_OFF), PIN(GPIO_TEST_N, AO_OFF), 0,  0,  0, 16,  0,  0,  0, 16,  1,  0),
 };
 
-static struct meson_domain_data meson8b_domain_data[] = {
-	{
-		.name		= "banks",
-		.banks		= meson8b_banks,
-		.num_banks	= ARRAY_SIZE(meson8b_banks),
-		.pin_base	= 0,
-		.num_pins	= 130,
-	},
-	{
-		.name		= "ao-bank",
-		.banks		= meson8b_ao_banks,
-		.num_banks	= ARRAY_SIZE(meson8b_ao_banks),
-		.pin_base	= 130,
-		.num_pins	= 16,
-	},
-};
-
-struct meson_pinctrl_data meson8b_pinctrl_data = {
-	.pins		= meson8b_pins,
-	.groups		= meson8b_groups,
-	.funcs		= meson8b_functions,
-	.domain_data	= meson8b_domain_data,
-	.num_pins	= ARRAY_SIZE(meson8b_pins),
-	.num_groups	= ARRAY_SIZE(meson8b_groups),
-	.num_funcs	= ARRAY_SIZE(meson8b_functions),
-	.num_domains	= ARRAY_SIZE(meson8b_domain_data),
+static struct meson_domain_data meson8b_cbus_domain_data = {
+	.name		= "cbus-banks",
+	.banks		= meson8b_cbus_banks,
+	.num_banks	= ARRAY_SIZE(meson8b_cbus_banks),
+	.pin_base	= 0,
+	.num_pins	= 130,
+};
+
+static struct meson_domain_data meson8b_aobus_domain_data = {
+	.name		= "aobus-banks",
+	.banks		= meson8b_aobus_banks,
+	.num_banks	= ARRAY_SIZE(meson8b_aobus_banks),
+	.pin_base	= 130,
+	.num_pins	= 16,
+};
+
+struct meson_pinctrl_data meson8b_cbus_pinctrl_data = {
+	.pins		= meson8b_cbus_pins,
+	.groups		= meson8b_cbus_groups,
+	.funcs		= meson8b_cbus_functions,
+	.domain_data	= &meson8b_cbus_domain_data,
+	.num_pins	= ARRAY_SIZE(meson8b_cbus_pins),
+	.num_groups	= ARRAY_SIZE(meson8b_cbus_groups),
+	.num_funcs	= ARRAY_SIZE(meson8b_cbus_functions),
+};
+
+struct meson_pinctrl_data meson8b_aobus_pinctrl_data = {
+	.pins		= meson8b_aobus_pins,
+	.groups		= meson8b_aobus_groups,
+	.funcs		= meson8b_aobus_functions,
+	.domain_data	= &meson8b_aobus_domain_data,
+	.num_pins	= ARRAY_SIZE(meson8b_aobus_pins),
+	.num_groups	= ARRAY_SIZE(meson8b_aobus_groups),
+	.num_funcs	= ARRAY_SIZE(meson8b_aobus_functions),
 };
diff --git a/drivers/pinctrl/mvebu/pinctrl-mvebu.c b/drivers/pinctrl/mvebu/pinctrl-mvebu.c
index e4d473811bb3..3ef798fac81b 100644
--- a/drivers/pinctrl/mvebu/pinctrl-mvebu.c
+++ b/drivers/pinctrl/mvebu/pinctrl-mvebu.c
@@ -666,16 +666,19 @@ int mvebu_pinctrl_probe(struct platform_device *pdev)
 		struct mvebu_mpp_ctrl_setting *set = &mode->settings[0];
 		struct mvebu_pinctrl_group *grp;
 		unsigned num_settings;
+		unsigned supp_settings;
 
-		for (num_settings = 0; ; set++) {
+		for (num_settings = 0, supp_settings = 0; ; set++) {
 			if (!set->name)
 				break;
 
+			num_settings++;
+
 			/* skip unsupported settings for this variant */
 			if (pctl->variant && !(pctl->variant & set->variant))
 				continue;
 
-			num_settings++;
+			supp_settings++;
 
 			/* find gpio/gpo/gpi settings */
 			if (strcmp(set->name, "gpio") == 0)
@@ -688,7 +691,7 @@ int mvebu_pinctrl_probe(struct platform_device *pdev)
 		}
 
 		/* skip modes with no settings for this variant */
-		if (!num_settings)
+		if (!supp_settings)
 			continue;
 
 		grp = mvebu_pinctrl_find_group_by_pid(pctl, mode->pid);
diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c
index 085e60106ec2..1f7469c9857d 100644
--- a/drivers/pinctrl/nomadik/pinctrl-abx500.c
+++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c
@@ -191,6 +191,7 @@ static void abx500_gpio_set(struct gpio_chip *chip, unsigned offset, int val)
 		dev_err(pct->dev, "%s write failed (%d)\n", __func__, ret);
 }
 
+#ifdef CONFIG_DEBUG_FS
 static int abx500_get_pull_updown(struct abx500_pinctrl *pct, int offset,
 				  enum abx500_gpio_pull_updown *pull_updown)
 {
@@ -226,6 +227,7 @@ out:
 
 	return ret;
 }
+#endif
 
 static int abx500_set_pull_updown(struct abx500_pinctrl *pct,
 				  int offset, enum abx500_gpio_pull_updown val)
@@ -468,6 +470,7 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_DEBUG_FS
 static int abx500_get_mode(struct pinctrl_dev *pctldev, struct gpio_chip *chip,
 			  unsigned gpio)
 {
@@ -553,8 +556,6 @@ out:
 	return ret;
 }
 
-#ifdef CONFIG_DEBUG_FS
-
 #include <linux/seq_file.h>
 
 static void abx500_gpio_dbg_show_one(struct seq_file *s,
diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik-stn8815.c b/drivers/pinctrl/nomadik/pinctrl-nomadik-stn8815.c
index 587b222f12f3..e852048c4c04 100644
--- a/drivers/pinctrl/nomadik/pinctrl-nomadik-stn8815.c
+++ b/drivers/pinctrl/nomadik/pinctrl-nomadik-stn8815.c
@@ -287,6 +287,10 @@ static const unsigned i2c0_a_1_pins[] = { STN8815_PIN_D3, STN8815_PIN_D2 };
 /* Altfunction B */
 static const unsigned u1_b_1_pins[] = { STN8815_PIN_B16, STN8815_PIN_A16 };
 static const unsigned i2cusb_b_1_pins[] = { STN8815_PIN_C21, STN8815_PIN_C20 };
+static const unsigned clcd_16_23_b_1_pins[] = { STN8815_PIN_AB6,
+	STN8815_PIN_AA6, STN8815_PIN_Y6, STN8815_PIN_Y5, STN8815_PIN_AA5,
+	STN8815_PIN_AB5, STN8815_PIN_AB4, STN8815_PIN_Y4 };
+
 
 #define STN8815_PIN_GROUP(a, b) { .name = #a, .pins = a##_pins,		\
 			.npins = ARRAY_SIZE(a##_pins), .altsetting = b }
@@ -302,6 +306,7 @@ static const struct nmk_pingroup nmk_stn8815_groups[] = {
 	STN8815_PIN_GROUP(i2c0_a_1, NMK_GPIO_ALT_A),
 	STN8815_PIN_GROUP(u1_b_1, NMK_GPIO_ALT_B),
 	STN8815_PIN_GROUP(i2cusb_b_1, NMK_GPIO_ALT_B),
+	STN8815_PIN_GROUP(clcd_16_23_b_1, NMK_GPIO_ALT_B),
 };
 
 /* We use this macro to define the groups applicable to a function */
@@ -314,6 +319,7 @@ STN8815_FUNC_GROUPS(u1, "u1_a_1", "u1_b_1");
 STN8815_FUNC_GROUPS(i2c1, "i2c1_a_1");
 STN8815_FUNC_GROUPS(i2c0, "i2c0_a_1");
 STN8815_FUNC_GROUPS(i2cusb, "i2cusb_b_1");
+STN8815_FUNC_GROUPS(clcd, "clcd_16_23_b_1");
 
 #define FUNCTION(fname)					\
 	{						\
@@ -329,6 +335,7 @@ static const struct nmk_function nmk_stn8815_functions[] = {
 	FUNCTION(i2c1),
 	FUNCTION(i2c0),
 	FUNCTION(i2cusb),
+	FUNCTION(clcd),
 };
 
 static const struct nmk_pinctrl_soc_data nmk_stn8815_soc = {
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 657449431301..5c025f5b5048 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -753,8 +753,8 @@ static int amd_gpio_probe(struct platform_device *pdev)
 
 	gpio_dev->base = devm_ioremap_nocache(&pdev->dev, res->start,
 						resource_size(res));
-	if (IS_ERR(gpio_dev->base))
-		return PTR_ERR(gpio_dev->base);
+	if (!gpio_dev->base)
+		return -ENOMEM;
 
 	irq_base = platform_get_irq(pdev, 0);
 	if (irq_base < 0) {
diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c
index ee69db6ae1c7..4429312e848d 100644
--- a/drivers/pinctrl/pinctrl-at91-pio4.c
+++ b/drivers/pinctrl/pinctrl-at91-pio4.c
@@ -824,7 +824,7 @@ static struct pinctrl_desc atmel_pinctrl_desc = {
 	.pmxops		= &atmel_pmxops,
 };
 
-static int atmel_pctrl_suspend(struct device *dev)
+static int __maybe_unused atmel_pctrl_suspend(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct atmel_pioctrl *atmel_pioctrl = platform_get_drvdata(pdev);
@@ -844,7 +844,7 @@ static int atmel_pctrl_suspend(struct device *dev)
 	return 0;
 }
 
-static int atmel_pctrl_resume(struct device *dev)
+static int __maybe_unused atmel_pctrl_resume(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct atmel_pioctrl *atmel_pioctrl = platform_get_drvdata(pdev);
diff --git a/drivers/pinctrl/pinctrl-coh901.c b/drivers/pinctrl/pinctrl-coh901.c
index cf7788df0f95..741b39eaeb8b 100644
--- a/drivers/pinctrl/pinctrl-coh901.c
+++ b/drivers/pinctrl/pinctrl-coh901.c
@@ -127,7 +127,7 @@ struct u300_gpio_confdata {
 }
 
 /* Initial configuration */
-static const struct __initconst u300_gpio_confdata
+static const struct u300_gpio_confdata __initconst
 bs335_gpio_config[U300_GPIO_NUM_PORTS][U300_GPIO_PINS_PER_PORT] = {
 	/* Port 0, pins 0-7 */
 	{
diff --git a/drivers/pinctrl/pinctrl-lpc18xx.c b/drivers/pinctrl/pinctrl-lpc18xx.c
index f0bebbe0682b..b1767f7e45d1 100644
--- a/drivers/pinctrl/pinctrl-lpc18xx.c
+++ b/drivers/pinctrl/pinctrl-lpc18xx.c
@@ -49,6 +49,18 @@
 
 #define LPC18XX_SCU_FUNC_PER_PIN	8
 
+/* LPC18XX SCU pin interrupt select registers */
+#define LPC18XX_SCU_PINTSEL0		0xe00
+#define LPC18XX_SCU_PINTSEL1		0xe04
+#define LPC18XX_SCU_PINTSEL_VAL_MASK	0xff
+#define LPC18XX_SCU_PINTSEL_PORT_SHIFT	5
+#define LPC18XX_SCU_IRQ_PER_PINTSEL	4
+#define LPC18XX_GPIO_PINS_PER_PORT	32
+#define LPC18XX_GPIO_PIN_INT_MAX	8
+
+#define LPC18XX_SCU_PINTSEL_VAL(val, n) \
+	((val) << (((n) % LPC18XX_SCU_IRQ_PER_PINTSEL) * 8))
+
 /* LPC18xx pin types */
 enum {
 	TYPE_ND,	/* Normal-drive */
@@ -618,6 +630,25 @@ static const struct pinctrl_pin_desc lpc18xx_pins[] = {
 	LPC18XX_PIN(i2c0_sda, PIN_I2C0_SDA),
 };
 
+/**
+ * enum lpc18xx_pin_config_param - possible pin configuration parameters
+ * @PIN_CONFIG_GPIO_PIN_INT: route gpio to the gpio pin interrupt
+ * 	controller.
+ */
+enum lpc18xx_pin_config_param {
+	PIN_CONFIG_GPIO_PIN_INT = PIN_CONFIG_END + 1,
+};
+
+static const struct pinconf_generic_params lpc18xx_params[] = {
+	{"nxp,gpio-pin-interrupt", PIN_CONFIG_GPIO_PIN_INT, 0},
+};
+
+#ifdef CONFIG_DEBUG_FS
+static const struct pin_config_item lpc18xx_conf_items[ARRAY_SIZE(lpc18xx_params)] = {
+	PCONFDUMP(PIN_CONFIG_GPIO_PIN_INT, "gpio pin int", NULL, true),
+};
+#endif
+
 static int lpc18xx_pconf_get_usb1(enum pin_config_param param, int *arg, u32 reg)
 {
 	switch (param) {
@@ -693,7 +724,71 @@ static int lpc18xx_pconf_get_i2c0(enum pin_config_param param, int *arg, u32 reg
 	return 0;
 }
 
-static int lpc18xx_pconf_get_pin(enum pin_config_param param, int *arg, u32 reg,
+static int lpc18xx_pin_to_gpio(struct pinctrl_dev *pctldev, unsigned pin)
+{
+	struct pinctrl_gpio_range *range;
+
+	range = pinctrl_find_gpio_range_from_pin_nolock(pctldev, pin);
+	if (!range)
+		return -EINVAL;
+
+	return pin - range->pin_base + range->base;
+}
+
+static int lpc18xx_get_pintsel(void __iomem *addr, u32 val, int *arg)
+{
+	u32 reg_val;
+	int i;
+
+	reg_val = readl(addr);
+	for (i = 0; i < LPC18XX_SCU_IRQ_PER_PINTSEL; i++) {
+		if ((reg_val & LPC18XX_SCU_PINTSEL_VAL_MASK) == val)
+			return 0;
+
+		reg_val >>= BITS_PER_BYTE;
+		*arg += 1;
+	}
+
+	return -EINVAL;
+}
+
+static u32 lpc18xx_gpio_to_pintsel_val(int gpio)
+{
+	unsigned int gpio_port, gpio_pin;
+
+	gpio_port = gpio / LPC18XX_GPIO_PINS_PER_PORT;
+	gpio_pin  = gpio % LPC18XX_GPIO_PINS_PER_PORT;
+
+	return gpio_pin | (gpio_port << LPC18XX_SCU_PINTSEL_PORT_SHIFT);
+}
+
+static int lpc18xx_pconf_get_gpio_pin_int(struct pinctrl_dev *pctldev,
+					  int *arg, unsigned pin)
+{
+	struct lpc18xx_scu_data *scu = pinctrl_dev_get_drvdata(pctldev);
+	int gpio, ret;
+	u32 val;
+
+	gpio = lpc18xx_pin_to_gpio(pctldev, pin);
+	if (gpio < 0)
+		return -ENOTSUPP;
+
+	val = lpc18xx_gpio_to_pintsel_val(gpio);
+
+	/*
+	 * Check if this pin has been enabled as a interrupt in any of the two
+	 * PINTSEL registers. *arg indicates which interrupt number (0-7).
+	 */
+	*arg = 0;
+	ret = lpc18xx_get_pintsel(scu->base + LPC18XX_SCU_PINTSEL0, val, arg);
+	if (ret == 0)
+		return ret;
+
+	return lpc18xx_get_pintsel(scu->base + LPC18XX_SCU_PINTSEL1, val, arg);
+}
+
+static int lpc18xx_pconf_get_pin(struct pinctrl_dev *pctldev, unsigned param,
+				 int *arg, u32 reg, unsigned pin,
 				 struct lpc18xx_pin_caps *pin_cap)
 {
 	switch (param) {
@@ -755,6 +850,9 @@ static int lpc18xx_pconf_get_pin(enum pin_config_param param, int *arg, u32 reg,
 		}
 		break;
 
+	case PIN_CONFIG_GPIO_PIN_INT:
+		return lpc18xx_pconf_get_gpio_pin_int(pctldev, arg, pin);
+
 	default:
 		return -ENOTSUPP;
 	}
@@ -794,7 +892,7 @@ static int lpc18xx_pconf_get(struct pinctrl_dev *pctldev, unsigned pin,
 	else if (pin_cap->type == TYPE_USB1)
 		ret = lpc18xx_pconf_get_usb1(param, &arg, reg);
 	else
-		ret = lpc18xx_pconf_get_pin(param, &arg, reg, pin_cap);
+		ret = lpc18xx_pconf_get_pin(pctldev, param, &arg, reg, pin, pin_cap);
 
 	if (ret < 0)
 		return ret;
@@ -883,9 +981,34 @@ static int lpc18xx_pconf_set_i2c0(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
-static int lpc18xx_pconf_set_pin(struct pinctrl_dev *pctldev,
-				 enum pin_config_param param,
-				 u16 param_val, u32 *reg,
+static int lpc18xx_pconf_set_gpio_pin_int(struct pinctrl_dev *pctldev,
+					  u16 param_val, unsigned pin)
+{
+	struct lpc18xx_scu_data *scu = pinctrl_dev_get_drvdata(pctldev);
+	u32 val, reg_val, reg_offset = LPC18XX_SCU_PINTSEL0;
+	int gpio;
+
+	if (param_val >= LPC18XX_GPIO_PIN_INT_MAX)
+		return -EINVAL;
+
+	gpio = lpc18xx_pin_to_gpio(pctldev, pin);
+	if (gpio < 0)
+		return -ENOTSUPP;
+
+	val = lpc18xx_gpio_to_pintsel_val(gpio);
+
+	reg_offset += (param_val / LPC18XX_SCU_IRQ_PER_PINTSEL) * sizeof(u32);
+
+	reg_val = readl(scu->base + reg_offset);
+	reg_val &= ~LPC18XX_SCU_PINTSEL_VAL(LPC18XX_SCU_PINTSEL_VAL_MASK, param_val);
+	reg_val |= LPC18XX_SCU_PINTSEL_VAL(val, param_val);
+	writel(reg_val, scu->base + reg_offset);
+
+	return 0;
+}
+
+static int lpc18xx_pconf_set_pin(struct pinctrl_dev *pctldev, unsigned param,
+				 u16 param_val, u32 *reg, unsigned pin,
 				 struct lpc18xx_pin_caps *pin_cap)
 {
 	switch (param) {
@@ -948,6 +1071,9 @@ static int lpc18xx_pconf_set_pin(struct pinctrl_dev *pctldev,
 		*reg |= param_val << LPC18XX_SCU_PIN_EHD_POS;
 		break;
 
+	case PIN_CONFIG_GPIO_PIN_INT:
+		return lpc18xx_pconf_set_gpio_pin_int(pctldev, param_val, pin);
+
 	default:
 		dev_err(pctldev->dev, "Property not supported\n");
 		return -ENOTSUPP;
@@ -982,7 +1108,7 @@ static int lpc18xx_pconf_set(struct pinctrl_dev *pctldev, unsigned pin,
 		else if (pin_cap->type == TYPE_USB1)
 			ret = lpc18xx_pconf_set_usb1(pctldev, param, param_val, &reg);
 		else
-			ret = lpc18xx_pconf_set_pin(pctldev, param, param_val, &reg, pin_cap);
+			ret = lpc18xx_pconf_set_pin(pctldev, param, param_val, &reg, pin, pin_cap);
 
 		if (ret)
 			return ret;
@@ -1136,6 +1262,11 @@ static struct pinctrl_desc lpc18xx_scu_desc = {
 	.pctlops = &lpc18xx_pctl_ops,
 	.pmxops = &lpc18xx_pmx_ops,
 	.confops = &lpc18xx_pconf_ops,
+	.num_custom_params = ARRAY_SIZE(lpc18xx_params),
+	.custom_params = lpc18xx_params,
+#ifdef CONFIG_DEBUG_FS
+	.custom_conf_items = lpc18xx_conf_items,
+#endif
 	.owner = THIS_MODULE,
 };
 
@@ -1170,9 +1301,8 @@ static int lpc18xx_create_group_func_map(struct device *dev,
 	u16 pins[ARRAY_SIZE(lpc18xx_pins)];
 	int func, ngroups, i;
 
-	for (func = 0; func < FUNC_MAX; ngroups = 0, func++) {
-
-		for (i = 0; i < ARRAY_SIZE(lpc18xx_pins); i++) {
+	for (func = 0; func < FUNC_MAX; func++) {
+		for (ngroups = 0, i = 0; i < ARRAY_SIZE(lpc18xx_pins); i++) {
 			if (lpc18xx_valid_pin_function(i, func))
 				pins[ngroups++] = i;
 		}
diff --git a/drivers/pinctrl/pinctrl-pic32.c b/drivers/pinctrl/pinctrl-pic32.c
new file mode 100644
index 000000000000..0b07d4bdab95
--- /dev/null
+++ b/drivers/pinctrl/pinctrl-pic32.c
@@ -0,0 +1,2312 @@
+/*
+ * PIC32 pinctrl driver
+ *
+ * Joshua Henderson, <joshua.henderson@microchip.com>
+ * Copyright (C) 2015 Microchip Technology Inc.  All rights reserved.
+ *
+ * This program is free software; you can distribute it and/or modify it
+ * under the terms of the GNU General Public License (Version 2) as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ * for more details.
+ */
+#include <linux/clk.h>
+#include <linux/gpio/driver.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pinctrl/pinconf.h>
+#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinmux.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include <asm/mach-pic32/pic32.h>
+
+#include "pinctrl-utils.h"
+#include "pinctrl-pic32.h"
+
+#define PINS_PER_BANK		16
+
+#define PIC32_CNCON_EDGE	11
+#define PIC32_CNCON_ON		15
+
+#define PIN_CONFIG_MICROCHIP_DIGITAL	(PIN_CONFIG_END + 1)
+#define PIN_CONFIG_MICROCHIP_ANALOG	(PIN_CONFIG_END + 2)
+
+static const struct pinconf_generic_params pic32_mpp_bindings[] = {
+	{"microchip,digital",	PIN_CONFIG_MICROCHIP_DIGITAL,	0},
+	{"microchip,analog",	PIN_CONFIG_MICROCHIP_ANALOG,	0},
+};
+
+#define GPIO_BANK_START(bank)		((bank) * PINS_PER_BANK)
+
+struct pic32_function {
+	const char *name;
+	const char * const *groups;
+	unsigned int ngroups;
+};
+
+struct pic32_pin_group {
+	const char *name;
+	unsigned int pin;
+	struct pic32_desc_function *functions;
+};
+
+struct pic32_desc_function {
+	const char *name;
+	u32 muxreg;
+	u32 muxval;
+};
+
+struct pic32_gpio_bank {
+	void __iomem *reg_base;
+	struct gpio_chip gpio_chip;
+	struct irq_chip irq_chip;
+	struct clk *clk;
+};
+
+struct pic32_pinctrl {
+	void __iomem *reg_base;
+	struct device *dev;
+	struct pinctrl_dev *pctldev;
+	const struct pinctrl_pin_desc *pins;
+	unsigned int npins;
+	const struct pic32_function *functions;
+	unsigned int nfunctions;
+	const struct pic32_pin_group *groups;
+	unsigned int ngroups;
+	struct pic32_gpio_bank *gpio_banks;
+	unsigned int nbanks;
+	struct clk *clk;
+};
+
+static const struct pinctrl_pin_desc pic32_pins[] = {
+	PINCTRL_PIN(0, "A0"),
+	PINCTRL_PIN(1, "A1"),
+	PINCTRL_PIN(2, "A2"),
+	PINCTRL_PIN(3, "A3"),
+	PINCTRL_PIN(4, "A4"),
+	PINCTRL_PIN(5, "A5"),
+	PINCTRL_PIN(6, "A6"),
+	PINCTRL_PIN(7, "A7"),
+	PINCTRL_PIN(8, "A8"),
+	PINCTRL_PIN(9, "A9"),
+	PINCTRL_PIN(10, "A10"),
+	PINCTRL_PIN(11, "A11"),
+	PINCTRL_PIN(12, "A12"),
+	PINCTRL_PIN(13, "A13"),
+	PINCTRL_PIN(14, "A14"),
+	PINCTRL_PIN(15, "A15"),
+	PINCTRL_PIN(16, "B0"),
+	PINCTRL_PIN(17, "B1"),
+	PINCTRL_PIN(18, "B2"),
+	PINCTRL_PIN(19, "B3"),
+	PINCTRL_PIN(20, "B4"),
+	PINCTRL_PIN(21, "B5"),
+	PINCTRL_PIN(22, "B6"),
+	PINCTRL_PIN(23, "B7"),
+	PINCTRL_PIN(24, "B8"),
+	PINCTRL_PIN(25, "B9"),
+	PINCTRL_PIN(26, "B10"),
+	PINCTRL_PIN(27, "B11"),
+	PINCTRL_PIN(28, "B12"),
+	PINCTRL_PIN(29, "B13"),
+	PINCTRL_PIN(30, "B14"),
+	PINCTRL_PIN(31, "B15"),
+	PINCTRL_PIN(33, "C1"),
+	PINCTRL_PIN(34, "C2"),
+	PINCTRL_PIN(35, "C3"),
+	PINCTRL_PIN(36, "C4"),
+	PINCTRL_PIN(44, "C12"),
+	PINCTRL_PIN(45, "C13"),
+	PINCTRL_PIN(46, "C14"),
+	PINCTRL_PIN(47, "C15"),
+	PINCTRL_PIN(48, "D0"),
+	PINCTRL_PIN(49, "D1"),
+	PINCTRL_PIN(50, "D2"),
+	PINCTRL_PIN(51, "D3"),
+	PINCTRL_PIN(52, "D4"),
+	PINCTRL_PIN(53, "D5"),
+	PINCTRL_PIN(54, "D6"),
+	PINCTRL_PIN(55, "D7"),
+	PINCTRL_PIN(57, "D9"),
+	PINCTRL_PIN(58, "D10"),
+	PINCTRL_PIN(59, "D11"),
+	PINCTRL_PIN(60, "D12"),
+	PINCTRL_PIN(61, "D13"),
+	PINCTRL_PIN(62, "D14"),
+	PINCTRL_PIN(63, "D15"),
+	PINCTRL_PIN(64, "E0"),
+	PINCTRL_PIN(65, "E1"),
+	PINCTRL_PIN(66, "E2"),
+	PINCTRL_PIN(67, "E3"),
+	PINCTRL_PIN(68, "E4"),
+	PINCTRL_PIN(69, "E5"),
+	PINCTRL_PIN(70, "E6"),
+	PINCTRL_PIN(71, "E7"),
+	PINCTRL_PIN(72, "E8"),
+	PINCTRL_PIN(73, "E9"),
+	PINCTRL_PIN(80, "F0"),
+	PINCTRL_PIN(81, "F1"),
+	PINCTRL_PIN(82, "F2"),
+	PINCTRL_PIN(83, "F3"),
+	PINCTRL_PIN(84, "F4"),
+	PINCTRL_PIN(85, "F5"),
+	PINCTRL_PIN(88, "F8"),
+	PINCTRL_PIN(92, "F12"),
+	PINCTRL_PIN(93, "F13"),
+	PINCTRL_PIN(96, "G0"),
+	PINCTRL_PIN(97, "G1"),
+	PINCTRL_PIN(102, "G6"),
+	PINCTRL_PIN(103, "G7"),
+	PINCTRL_PIN(104, "G8"),
+	PINCTRL_PIN(105, "G9"),
+	PINCTRL_PIN(108, "G12"),
+	PINCTRL_PIN(109, "G13"),
+	PINCTRL_PIN(110, "G14"),
+	PINCTRL_PIN(111, "G15"),
+	PINCTRL_PIN(112, "H0"),
+	PINCTRL_PIN(113, "H1"),
+	PINCTRL_PIN(114, "H2"),
+	PINCTRL_PIN(115, "H3"),
+	PINCTRL_PIN(116, "H4"),
+	PINCTRL_PIN(117, "H5"),
+	PINCTRL_PIN(118, "H6"),
+	PINCTRL_PIN(119, "H7"),
+	PINCTRL_PIN(120, "H8"),
+	PINCTRL_PIN(121, "H9"),
+	PINCTRL_PIN(122, "H10"),
+	PINCTRL_PIN(123, "H11"),
+	PINCTRL_PIN(124, "H12"),
+	PINCTRL_PIN(125, "H13"),
+	PINCTRL_PIN(126, "H14"),
+	PINCTRL_PIN(127, "H15"),
+	PINCTRL_PIN(128, "J0"),
+	PINCTRL_PIN(129, "J1"),
+	PINCTRL_PIN(130, "J2"),
+	PINCTRL_PIN(131, "J3"),
+	PINCTRL_PIN(132, "J4"),
+	PINCTRL_PIN(133, "J5"),
+	PINCTRL_PIN(134, "J6"),
+	PINCTRL_PIN(135, "J7"),
+	PINCTRL_PIN(136, "J8"),
+	PINCTRL_PIN(137, "J9"),
+	PINCTRL_PIN(138, "J10"),
+	PINCTRL_PIN(139, "J11"),
+	PINCTRL_PIN(140, "J12"),
+	PINCTRL_PIN(141, "J13"),
+	PINCTRL_PIN(142, "J14"),
+	PINCTRL_PIN(143, "J15"),
+	PINCTRL_PIN(144, "K0"),
+	PINCTRL_PIN(145, "K1"),
+	PINCTRL_PIN(146, "K2"),
+	PINCTRL_PIN(147, "K3"),
+	PINCTRL_PIN(148, "K4"),
+	PINCTRL_PIN(149, "K5"),
+	PINCTRL_PIN(150, "K6"),
+	PINCTRL_PIN(151, "K7"),
+};
+
+static const char * const pic32_input0_group[] = {
+	"D2", "G8", "F4", "F1", "B9", "B10", "C14", "B5",
+	"C1", "D14", "G1", "A14", "D6",
+};
+
+static const char * const pic32_input1_group[] = {
+	"D3", "G7", "F5", "D11", "F0", "B1", "E5", "C13",
+	"B3", "C4", "G0", "A15", "D7",
+};
+
+static const char * const pic32_input2_group[] = {
+	"D9", "G6", "B8", "B15", "D4", "B0", "E3", "B7",
+	"F12", "D12", "F8", "C3", "E9",
+};
+
+static const char * const pic32_input3_group[] = {
+	"G9", "B14", "D0", "B6", "D5", "B2", "F3", "F13",
+	"F2", "C2", "E8",
+};
+
+static const char * const pic32_output0_group[] = {
+	"D2", "G8", "F4", "D10", "F1", "B9", "B10", "C14",
+	"B5", "C1", "D14", "G1", "A14", "D6",
+};
+
+static const char * const pic32_output0_1_group[] = {
+	"D2", "G8", "F4", "D10", "F1", "B9", "B10", "C14",
+	"B5", "C1", "D14", "G1", "A14", "D6",
+	"D3", "G7", "F5", "D11", "F0", "B1", "E5", "C13",
+	"B3", "C4", "D15", "G0", "A15", "D7",
+};
+
+static const char *const pic32_output1_group[] = {
+	"D3", "G7", "F5", "D11", "F0", "B1", "E5", "C13",
+	"B3", "C4", "D15", "G0", "A15", "D7",
+};
+
+static const char *const pic32_output1_3_group[] = {
+	"D3", "G7", "F5", "D11", "F0", "B1", "E5", "C13",
+	"B3", "C4", "D15", "G0", "A15", "D7",
+	"G9", "B14", "D0", "B6", "D5", "B2", "F3", "F13",
+	"C2", "E8", "F2",
+};
+
+static const char * const pic32_output2_group[] = {
+	"D9", "G6", "B8", "B15", "D4", "B0", "E3", "B7",
+	"F12", "D12", "F8", "C3", "E9",
+};
+
+static const char * const pic32_output2_3_group[] = {
+	"D9", "G6", "B8", "B15", "D4", "B0", "E3", "B7",
+	"F12", "D12", "F8", "C3", "E9",
+	"G9", "B14", "D0", "B6", "D5", "B2", "F3", "F13",
+	"C2", "E8", "F2",
+};
+
+static const char * const pic32_output3_group[] = {
+	"G9", "B14", "D0", "B6", "D5", "B2", "F3", "F13",
+	"C2", "E8", "F2",
+};
+
+#define FUNCTION(_name, _gr)					\
+	{							\
+		.name = #_name,					\
+		.groups = pic32_##_gr##_group,			\
+		.ngroups = ARRAY_SIZE(pic32_##_gr##_group),	\
+	}
+
+static const struct pic32_function pic32_functions[] = {
+	FUNCTION(INT3, input0),
+	FUNCTION(T2CK, input0),
+	FUNCTION(T6CK, input0),
+	FUNCTION(IC3, input0),
+	FUNCTION(IC7, input0),
+	FUNCTION(U1RX, input0),
+	FUNCTION(U2CTS, input0),
+	FUNCTION(U5RX, input0),
+	FUNCTION(U6CTS, input0),
+	FUNCTION(SDI1, input0),
+	FUNCTION(SDI3, input0),
+	FUNCTION(SDI5, input0),
+	FUNCTION(SS6IN, input0),
+	FUNCTION(REFCLKI1, input0),
+	FUNCTION(INT4, input1),
+	FUNCTION(T5CK, input1),
+	FUNCTION(T7CK, input1),
+	FUNCTION(IC4, input1),
+	FUNCTION(IC8, input1),
+	FUNCTION(U3RX, input1),
+	FUNCTION(U4CTS, input1),
+	FUNCTION(SDI2, input1),
+	FUNCTION(SDI4, input1),
+	FUNCTION(C1RX, input1),
+	FUNCTION(REFCLKI4, input1),
+	FUNCTION(INT2, input2),
+	FUNCTION(T3CK, input2),
+	FUNCTION(T8CK, input2),
+	FUNCTION(IC2, input2),
+	FUNCTION(IC5, input2),
+	FUNCTION(IC9, input2),
+	FUNCTION(U1CTS, input2),
+	FUNCTION(U2RX, input2),
+	FUNCTION(U5CTS, input2),
+	FUNCTION(SS1IN, input2),
+	FUNCTION(SS3IN, input2),
+	FUNCTION(SS4IN, input2),
+	FUNCTION(SS5IN, input2),
+	FUNCTION(C2RX, input2),
+	FUNCTION(INT1, input3),
+	FUNCTION(T4CK, input3),
+	FUNCTION(T9CK, input3),
+	FUNCTION(IC1, input3),
+	FUNCTION(IC6, input3),
+	FUNCTION(U3CTS, input3),
+	FUNCTION(U4RX, input3),
+	FUNCTION(U6RX, input3),
+	FUNCTION(SS2IN, input3),
+	FUNCTION(SDI6, input3),
+	FUNCTION(OCFA, input3),
+	FUNCTION(REFCLKI3, input3),
+	FUNCTION(U3TX, output0),
+	FUNCTION(U4RTS, output0),
+	FUNCTION(SDO1, output0_1),
+	FUNCTION(SDO2, output0_1),
+	FUNCTION(SDO3, output0_1),
+	FUNCTION(SDO5, output0_1),
+	FUNCTION(SS6OUT, output0),
+	FUNCTION(OC3, output0),
+	FUNCTION(OC6, output0),
+	FUNCTION(REFCLKO4, output0),
+	FUNCTION(C2OUT, output0),
+	FUNCTION(C1TX, output0),
+	FUNCTION(U1TX, output1),
+	FUNCTION(U2RTS, output1),
+	FUNCTION(U5TX, output1),
+	FUNCTION(U6RTS, output1),
+	FUNCTION(SDO4, output1_3),
+	FUNCTION(OC4, output1),
+	FUNCTION(OC7, output1),
+	FUNCTION(REFCLKO1, output1),
+	FUNCTION(U3RTS, output2),
+	FUNCTION(U4TX, output2),
+	FUNCTION(U6TX, output2_3),
+	FUNCTION(SS1OUT, output2),
+	FUNCTION(SS3OUT, output2),
+	FUNCTION(SS4OUT, output2),
+	FUNCTION(SS5OUT, output2),
+	FUNCTION(SDO6, output2_3),
+	FUNCTION(OC5, output2),
+	FUNCTION(OC8, output2),
+	FUNCTION(C1OUT, output2),
+	FUNCTION(REFCLKO3, output2),
+	FUNCTION(U1RTS, output3),
+	FUNCTION(U2TX, output3),
+	FUNCTION(U5RTS, output3),
+	FUNCTION(SS2OUT, output3),
+	FUNCTION(OC2, output3),
+	FUNCTION(OC1, output3),
+	FUNCTION(OC9, output3),
+	FUNCTION(C2TX, output3),
+};
+
+#define PIC32_PINCTRL_GROUP(_pin, _name, ...)				\
+	{								\
+		.name = #_name,						\
+		.pin = _pin,						\
+		.functions = (struct pic32_desc_function[]){		\
+			__VA_ARGS__, { } },				\
+	}
+
+#define PIC32_PINCTRL_FUNCTION(_name, _muxreg, _muxval)	\
+	{						\
+		.name = #_name,				\
+		.muxreg = _muxreg,			\
+		.muxval = _muxval,			\
+	}
+
+static const struct pic32_pin_group pic32_groups[] = {
+	PIC32_PINCTRL_GROUP(14, A14,
+			PIC32_PINCTRL_FUNCTION(INT3, INT3R, 13),
+			PIC32_PINCTRL_FUNCTION(T2CK, T2CKR, 13),
+			PIC32_PINCTRL_FUNCTION(T6CK, T6CKR, 13),
+			PIC32_PINCTRL_FUNCTION(IC3, IC3R, 13),
+			PIC32_PINCTRL_FUNCTION(IC7, IC7R, 13),
+			PIC32_PINCTRL_FUNCTION(U1RX, U1RXR, 13),
+			PIC32_PINCTRL_FUNCTION(U2CTS, U2CTSR, 13),
+			PIC32_PINCTRL_FUNCTION(U5RX, U5RXR, 13),
+			PIC32_PINCTRL_FUNCTION(U6CTS, U6CTSR, 13),
+			PIC32_PINCTRL_FUNCTION(SDI1, SDI1R, 13),
+			PIC32_PINCTRL_FUNCTION(SDI3, SDI3R, 13),
+			PIC32_PINCTRL_FUNCTION(SDI5, SDI5R, 13),
+			PIC32_PINCTRL_FUNCTION(SS6IN, SS6INR, 13),
+			PIC32_PINCTRL_FUNCTION(REFCLKI1, REFCLKI1R, 13),
+			PIC32_PINCTRL_FUNCTION(U3TX, RPA14R, 1),
+			PIC32_PINCTRL_FUNCTION(U4RTS, RPA14R, 2),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPA14R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPA14R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPA14R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPA14R, 9),
+			PIC32_PINCTRL_FUNCTION(SS6OUT, RPA14R, 10),
+			PIC32_PINCTRL_FUNCTION(OC3, RPA14R, 11),
+			PIC32_PINCTRL_FUNCTION(OC6, RPA14R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO4, RPA14R, 13),
+			PIC32_PINCTRL_FUNCTION(C2OUT, RPA14R, 14),
+			PIC32_PINCTRL_FUNCTION(C1TX, RPA14R, 15)),
+	PIC32_PINCTRL_GROUP(15, A15,
+			PIC32_PINCTRL_FUNCTION(INT4, INT4R, 13),
+			PIC32_PINCTRL_FUNCTION(T5CK, T5CKR, 13),
+			PIC32_PINCTRL_FUNCTION(T7CK, T7CKR, 13),
+			PIC32_PINCTRL_FUNCTION(IC4, IC4R, 13),
+			PIC32_PINCTRL_FUNCTION(IC8, IC8R, 13),
+			PIC32_PINCTRL_FUNCTION(U3RX, U3RXR, 13),
+			PIC32_PINCTRL_FUNCTION(U4CTS, U4CTSR, 13),
+			PIC32_PINCTRL_FUNCTION(SDI2, SDI2R, 13),
+			PIC32_PINCTRL_FUNCTION(SDI4, SDI4R, 13),
+			PIC32_PINCTRL_FUNCTION(C1RX, C1RXR, 13),
+			PIC32_PINCTRL_FUNCTION(REFCLKI4, REFCLKI4R, 13),
+			PIC32_PINCTRL_FUNCTION(U1TX, RPA15R, 1),
+			PIC32_PINCTRL_FUNCTION(U2RTS, RPA15R, 2),
+			PIC32_PINCTRL_FUNCTION(U5TX, RPA15R, 3),
+			PIC32_PINCTRL_FUNCTION(U6RTS, RPA15R, 4),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPA15R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPA15R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPA15R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPA15R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPA15R, 9),
+			PIC32_PINCTRL_FUNCTION(OC4, RPA15R, 11),
+			PIC32_PINCTRL_FUNCTION(OC7, RPA15R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO1, RPA15R, 15)),
+	PIC32_PINCTRL_GROUP(16, B0,
+			PIC32_PINCTRL_FUNCTION(INT2, INT2R, 5),
+			PIC32_PINCTRL_FUNCTION(T3CK, T3CKR, 5),
+			PIC32_PINCTRL_FUNCTION(T8CK, T8CKR, 5),
+			PIC32_PINCTRL_FUNCTION(IC2, IC2R, 5),
+			PIC32_PINCTRL_FUNCTION(IC5, IC5R, 5),
+			PIC32_PINCTRL_FUNCTION(IC9, IC9R, 5),
+			PIC32_PINCTRL_FUNCTION(U1CTS, U1CTSR, 5),
+			PIC32_PINCTRL_FUNCTION(U2RX, U2RXR, 5),
+			PIC32_PINCTRL_FUNCTION(U5CTS, U5CTSR, 5),
+			PIC32_PINCTRL_FUNCTION(SS1IN, SS1INR, 5),
+			PIC32_PINCTRL_FUNCTION(SS3IN, SS3INR, 5),
+			PIC32_PINCTRL_FUNCTION(SS4IN, SS4INR, 5),
+			PIC32_PINCTRL_FUNCTION(SS5IN, SS5INR, 5),
+			PIC32_PINCTRL_FUNCTION(C2RX, C2RXR, 5),
+			PIC32_PINCTRL_FUNCTION(U3RTS, RPB0R, 1),
+			PIC32_PINCTRL_FUNCTION(U4TX, RPB0R, 2),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPB0R, 4),
+			PIC32_PINCTRL_FUNCTION(SS1OUT, RPB0R, 5),
+			PIC32_PINCTRL_FUNCTION(SS3OUT, RPB0R, 7),
+			PIC32_PINCTRL_FUNCTION(SS4OUT, RPB0R, 8),
+			PIC32_PINCTRL_FUNCTION(SS5OUT, RPB0R, 9),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPB0R, 10),
+			PIC32_PINCTRL_FUNCTION(OC5, RPB0R, 11),
+			PIC32_PINCTRL_FUNCTION(OC8, RPB0R, 12),
+			PIC32_PINCTRL_FUNCTION(C1OUT, RPB0R, 14),
+			PIC32_PINCTRL_FUNCTION(REFCLKO3, RPB0R, 15)),
+	PIC32_PINCTRL_GROUP(17, B1,
+			PIC32_PINCTRL_FUNCTION(INT4, INT4R, 5),
+			PIC32_PINCTRL_FUNCTION(T5CK, T5CKR, 5),
+			PIC32_PINCTRL_FUNCTION(T7CK, T7CKR, 5),
+			PIC32_PINCTRL_FUNCTION(IC4, IC4R, 5),
+			PIC32_PINCTRL_FUNCTION(IC8, IC8R, 5),
+			PIC32_PINCTRL_FUNCTION(U3RX, U3RXR, 5),
+			PIC32_PINCTRL_FUNCTION(U4CTS, U4CTSR, 5),
+			PIC32_PINCTRL_FUNCTION(SDI2, SDI2R, 5),
+			PIC32_PINCTRL_FUNCTION(SDI4, SDI4R, 5),
+			PIC32_PINCTRL_FUNCTION(C1RX, C1RXR, 5),
+			PIC32_PINCTRL_FUNCTION(REFCLKI4, REFCLKI4R, 5),
+			PIC32_PINCTRL_FUNCTION(U1TX, RPB1R, 1),
+			PIC32_PINCTRL_FUNCTION(U2RTS, RPB1R, 2),
+			PIC32_PINCTRL_FUNCTION(U5TX, RPB1R, 3),
+			PIC32_PINCTRL_FUNCTION(U6RTS, RPB1R, 4),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPB1R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPB1R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPB1R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPB1R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPB1R, 9),
+			PIC32_PINCTRL_FUNCTION(OC4, RPB1R, 11),
+			PIC32_PINCTRL_FUNCTION(OC7, RPB1R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO1, RPB1R, 15)),
+	PIC32_PINCTRL_GROUP(18, B2,
+			PIC32_PINCTRL_FUNCTION(INT1, INT1R, 7),
+			PIC32_PINCTRL_FUNCTION(T4CK, T4CKR, 7),
+			PIC32_PINCTRL_FUNCTION(T9CK, T9CKR, 7),
+			PIC32_PINCTRL_FUNCTION(IC1, IC1R, 7),
+			PIC32_PINCTRL_FUNCTION(IC6, IC6R, 7),
+			PIC32_PINCTRL_FUNCTION(U3CTS, U3CTSR, 7),
+			PIC32_PINCTRL_FUNCTION(U4RX, U4RXR, 7),
+			PIC32_PINCTRL_FUNCTION(U6RX, U6RXR, 7),
+			PIC32_PINCTRL_FUNCTION(SS2IN, SS2INR, 7),
+			PIC32_PINCTRL_FUNCTION(SDI6, SDI6R, 7),
+			PIC32_PINCTRL_FUNCTION(OCFA, OCFAR, 7),
+			PIC32_PINCTRL_FUNCTION(REFCLKI3, REFCLKI3R, 7),
+			PIC32_PINCTRL_FUNCTION(U1RTS, RPB2R, 1),
+			PIC32_PINCTRL_FUNCTION(U2TX, RPB2R, 2),
+			PIC32_PINCTRL_FUNCTION(U5RTS, RPB2R, 3),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPB2R, 4),
+			PIC32_PINCTRL_FUNCTION(SS2OUT, RPB2R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPB2R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPB2R, 10),
+			PIC32_PINCTRL_FUNCTION(OC2, RPB2R, 11),
+			PIC32_PINCTRL_FUNCTION(OC1, RPB2R, 12),
+			PIC32_PINCTRL_FUNCTION(OC9, RPB2R, 13),
+			PIC32_PINCTRL_FUNCTION(C2TX, RPB2R, 15)),
+	PIC32_PINCTRL_GROUP(19, B3,
+			PIC32_PINCTRL_FUNCTION(INT4, INT4R, 8),
+			PIC32_PINCTRL_FUNCTION(T5CK, T5CKR, 8),
+			PIC32_PINCTRL_FUNCTION(T7CK, T7CKR, 8),
+			PIC32_PINCTRL_FUNCTION(IC4, IC4R, 8),
+			PIC32_PINCTRL_FUNCTION(IC8, IC8R, 8),
+			PIC32_PINCTRL_FUNCTION(U3RX, U3RXR, 8),
+			PIC32_PINCTRL_FUNCTION(U4CTS, U4CTSR, 8),
+			PIC32_PINCTRL_FUNCTION(SDI2, SDI2R, 8),
+			PIC32_PINCTRL_FUNCTION(SDI4, SDI4R, 8),
+			PIC32_PINCTRL_FUNCTION(C1RX, C1RXR, 8),
+			PIC32_PINCTRL_FUNCTION(REFCLKI4, REFCLKI4R, 8),
+			PIC32_PINCTRL_FUNCTION(U1TX, RPB3R, 1),
+			PIC32_PINCTRL_FUNCTION(U2RTS, RPB3R, 2),
+			PIC32_PINCTRL_FUNCTION(U5TX, RPB3R, 3),
+			PIC32_PINCTRL_FUNCTION(U6RTS, RPB3R, 4),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPB3R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPB3R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPB3R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPB3R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPB3R, 9),
+			PIC32_PINCTRL_FUNCTION(OC4, RPB3R, 11),
+			PIC32_PINCTRL_FUNCTION(OC7, RPB3R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO1, RPB3R, 15)),
+	PIC32_PINCTRL_GROUP(21, B5,
+			PIC32_PINCTRL_FUNCTION(INT3, INT3R, 8),
+			PIC32_PINCTRL_FUNCTION(T2CK, T2CKR, 8),
+			PIC32_PINCTRL_FUNCTION(T6CK, T6CKR, 8),
+			PIC32_PINCTRL_FUNCTION(IC3, IC3R, 8),
+			PIC32_PINCTRL_FUNCTION(IC7, IC7R, 8),
+			PIC32_PINCTRL_FUNCTION(U1RX, U1RXR, 8),
+			PIC32_PINCTRL_FUNCTION(U2CTS, U2CTSR, 8),
+			PIC32_PINCTRL_FUNCTION(U5RX, U5RXR, 8),
+			PIC32_PINCTRL_FUNCTION(U6CTS, U6CTSR, 8),
+			PIC32_PINCTRL_FUNCTION(SDI1, SDI1R, 8),
+			PIC32_PINCTRL_FUNCTION(SDI3, SDI3R, 8),
+			PIC32_PINCTRL_FUNCTION(SDI5, SDI5R, 8),
+			PIC32_PINCTRL_FUNCTION(SS6IN, SS6INR, 8),
+			PIC32_PINCTRL_FUNCTION(REFCLKI1, REFCLKI1R, 8),
+			PIC32_PINCTRL_FUNCTION(U3TX, RPB5R, 1),
+			PIC32_PINCTRL_FUNCTION(U4RTS, RPB5R, 2),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPB5R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPB5R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPB5R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPB5R, 9),
+			PIC32_PINCTRL_FUNCTION(SS6OUT, RPB5R, 10),
+			PIC32_PINCTRL_FUNCTION(OC3, RPB5R, 11),
+			PIC32_PINCTRL_FUNCTION(OC6, RPB5R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO4, RPB5R, 13),
+			PIC32_PINCTRL_FUNCTION(C2OUT, RPB5R, 14),
+			PIC32_PINCTRL_FUNCTION(C1TX, RPB5R, 15)),
+	PIC32_PINCTRL_GROUP(22, B6,
+			PIC32_PINCTRL_FUNCTION(INT1, INT1R, 4),
+			PIC32_PINCTRL_FUNCTION(T4CK, T4CKR, 4),
+			PIC32_PINCTRL_FUNCTION(T9CK, T9CKR, 4),
+			PIC32_PINCTRL_FUNCTION(IC1, IC1R, 4),
+			PIC32_PINCTRL_FUNCTION(IC6, IC6R, 4),
+			PIC32_PINCTRL_FUNCTION(U3CTS, U3CTSR, 4),
+			PIC32_PINCTRL_FUNCTION(U4RX, U4RXR, 4),
+			PIC32_PINCTRL_FUNCTION(U6RX, U6RXR, 4),
+			PIC32_PINCTRL_FUNCTION(SS2IN, SS2INR, 4),
+			PIC32_PINCTRL_FUNCTION(SDI6, SDI6R, 4),
+			PIC32_PINCTRL_FUNCTION(OCFA, OCFAR, 4),
+			PIC32_PINCTRL_FUNCTION(REFCLKI3, REFCLKI3R, 4),
+			PIC32_PINCTRL_FUNCTION(U1RTS, RPB6R, 1),
+			PIC32_PINCTRL_FUNCTION(U2TX, RPB6R, 2),
+			PIC32_PINCTRL_FUNCTION(U5RTS, RPB6R, 3),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPB6R, 4),
+			PIC32_PINCTRL_FUNCTION(SS2OUT, RPB6R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPB6R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPB6R, 10),
+			PIC32_PINCTRL_FUNCTION(OC2, RPB6R, 11),
+			PIC32_PINCTRL_FUNCTION(OC1, RPB6R, 12),
+			PIC32_PINCTRL_FUNCTION(OC9, RPB6R, 13),
+			PIC32_PINCTRL_FUNCTION(C2TX, RPB6R, 15)),
+	PIC32_PINCTRL_GROUP(23, B7,
+			PIC32_PINCTRL_FUNCTION(INT2, INT2R, 7),
+			PIC32_PINCTRL_FUNCTION(T3CK, T3CKR, 7),
+			PIC32_PINCTRL_FUNCTION(T8CK, T8CKR, 7),
+			PIC32_PINCTRL_FUNCTION(IC2, IC2R, 7),
+			PIC32_PINCTRL_FUNCTION(IC5, IC5R, 7),
+			PIC32_PINCTRL_FUNCTION(IC9, IC9R, 7),
+			PIC32_PINCTRL_FUNCTION(U1CTS, U1CTSR, 7),
+			PIC32_PINCTRL_FUNCTION(U2RX, U2RXR, 7),
+			PIC32_PINCTRL_FUNCTION(U5CTS, U5CTSR, 7),
+			PIC32_PINCTRL_FUNCTION(SS1IN, SS1INR, 7),
+			PIC32_PINCTRL_FUNCTION(SS3IN, SS3INR, 7),
+			PIC32_PINCTRL_FUNCTION(SS4IN, SS4INR, 7),
+			PIC32_PINCTRL_FUNCTION(SS5IN, SS5INR, 7),
+			PIC32_PINCTRL_FUNCTION(C2RX, C2RXR, 7),
+			PIC32_PINCTRL_FUNCTION(U3RTS, RPB7R, 1),
+			PIC32_PINCTRL_FUNCTION(U4TX, RPB7R, 2),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPB7R, 4),
+			PIC32_PINCTRL_FUNCTION(SS1OUT, RPB7R, 5),
+			PIC32_PINCTRL_FUNCTION(SS3OUT, RPB7R, 7),
+			PIC32_PINCTRL_FUNCTION(SS4OUT, RPB7R, 8),
+			PIC32_PINCTRL_FUNCTION(SS5OUT, RPB7R, 9),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPB7R, 10),
+			PIC32_PINCTRL_FUNCTION(OC5, RPB7R, 11),
+			PIC32_PINCTRL_FUNCTION(OC8, RPB7R, 12),
+			PIC32_PINCTRL_FUNCTION(C1OUT, RPB7R, 14),
+			PIC32_PINCTRL_FUNCTION(REFCLKO3, RPB7R, 15)),
+	PIC32_PINCTRL_GROUP(24, B8,
+			PIC32_PINCTRL_FUNCTION(INT2, INT2R, 2),
+			PIC32_PINCTRL_FUNCTION(T3CK, T3CKR, 2),
+			PIC32_PINCTRL_FUNCTION(T8CK, T8CKR, 2),
+			PIC32_PINCTRL_FUNCTION(IC2, IC2R, 2),
+			PIC32_PINCTRL_FUNCTION(IC5, IC5R, 2),
+			PIC32_PINCTRL_FUNCTION(IC9, IC9R, 2),
+			PIC32_PINCTRL_FUNCTION(U1CTS, U1CTSR, 2),
+			PIC32_PINCTRL_FUNCTION(U2RX, U2RXR, 2),
+			PIC32_PINCTRL_FUNCTION(U5CTS, U5CTSR, 2),
+			PIC32_PINCTRL_FUNCTION(SS1IN, SS1INR, 2),
+			PIC32_PINCTRL_FUNCTION(SS3IN, SS3INR, 2),
+			PIC32_PINCTRL_FUNCTION(SS4IN, SS4INR, 2),
+			PIC32_PINCTRL_FUNCTION(SS5IN, SS5INR, 2),
+			PIC32_PINCTRL_FUNCTION(C2RX, C2RXR, 2),
+			PIC32_PINCTRL_FUNCTION(U3RTS, RPB8R, 1),
+			PIC32_PINCTRL_FUNCTION(U4TX, RPB8R, 2),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPB8R, 4),
+			PIC32_PINCTRL_FUNCTION(SS1OUT, RPB8R, 5),
+			PIC32_PINCTRL_FUNCTION(SS3OUT, RPB8R, 7),
+			PIC32_PINCTRL_FUNCTION(SS4OUT, RPB8R, 8),
+			PIC32_PINCTRL_FUNCTION(SS5OUT, RPB8R, 9),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPB8R, 10),
+			PIC32_PINCTRL_FUNCTION(OC5, RPB8R, 11),
+			PIC32_PINCTRL_FUNCTION(OC8, RPB8R, 12),
+			PIC32_PINCTRL_FUNCTION(C1OUT, RPB8R, 14),
+			PIC32_PINCTRL_FUNCTION(REFCLKO3, RPB8R, 15)),
+	PIC32_PINCTRL_GROUP(25, B9,
+			PIC32_PINCTRL_FUNCTION(INT3, INT3R, 5),
+			PIC32_PINCTRL_FUNCTION(T2CK, T2CKR, 5),
+			PIC32_PINCTRL_FUNCTION(T6CK, T6CKR, 5),
+			PIC32_PINCTRL_FUNCTION(IC3, IC3R, 5),
+			PIC32_PINCTRL_FUNCTION(IC7, IC7R, 5),
+			PIC32_PINCTRL_FUNCTION(U1RX, U1RXR, 5),
+			PIC32_PINCTRL_FUNCTION(U2CTS, U2CTSR, 5),
+			PIC32_PINCTRL_FUNCTION(U5RX, U5RXR, 5),
+			PIC32_PINCTRL_FUNCTION(U6CTS, U6CTSR, 5),
+			PIC32_PINCTRL_FUNCTION(SDI1, SDI1R, 5),
+			PIC32_PINCTRL_FUNCTION(SDI3, SDI3R, 5),
+			PIC32_PINCTRL_FUNCTION(SDI5, SDI5R, 5),
+			PIC32_PINCTRL_FUNCTION(SS6IN, SS6INR, 5),
+			PIC32_PINCTRL_FUNCTION(REFCLKI1, REFCLKI1R, 5),
+			PIC32_PINCTRL_FUNCTION(U3TX, RPB9R, 1),
+			PIC32_PINCTRL_FUNCTION(U4RTS, RPB9R, 2),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPB9R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPB9R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPB9R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPB9R, 9),
+			PIC32_PINCTRL_FUNCTION(SS6OUT, RPB9R, 10),
+			PIC32_PINCTRL_FUNCTION(OC3, RPB9R, 11),
+			PIC32_PINCTRL_FUNCTION(OC6, RPB9R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO4, RPB9R, 13),
+			PIC32_PINCTRL_FUNCTION(C2OUT, RPB9R, 14),
+			PIC32_PINCTRL_FUNCTION(C1TX, RPB9R, 15)),
+	PIC32_PINCTRL_GROUP(26, B10,
+			PIC32_PINCTRL_FUNCTION(INT3, INT3R, 6),
+			PIC32_PINCTRL_FUNCTION(T2CK, T2CKR, 6),
+			PIC32_PINCTRL_FUNCTION(T6CK, T6CKR, 6),
+			PIC32_PINCTRL_FUNCTION(IC3, IC3R, 6),
+			PIC32_PINCTRL_FUNCTION(IC7, IC7R, 6),
+			PIC32_PINCTRL_FUNCTION(U1RX, U1RXR, 6),
+			PIC32_PINCTRL_FUNCTION(U2CTS, U2CTSR, 6),
+			PIC32_PINCTRL_FUNCTION(U5RX, U5RXR, 6),
+			PIC32_PINCTRL_FUNCTION(U6CTS, U6CTSR, 6),
+			PIC32_PINCTRL_FUNCTION(SDI1, SDI1R, 6),
+			PIC32_PINCTRL_FUNCTION(SDI3, SDI3R, 6),
+			PIC32_PINCTRL_FUNCTION(SDI5, SDI5R, 6),
+			PIC32_PINCTRL_FUNCTION(SS6IN, SS6INR, 6),
+			PIC32_PINCTRL_FUNCTION(REFCLKI1, REFCLKI1R, 6),
+			PIC32_PINCTRL_FUNCTION(U3TX, RPB10R, 1),
+			PIC32_PINCTRL_FUNCTION(U4RTS, RPB10R, 2),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPB10R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPB10R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPB10R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPB10R, 9),
+			PIC32_PINCTRL_FUNCTION(SS6OUT, RPB10R, 10),
+			PIC32_PINCTRL_FUNCTION(OC3, RPB10R, 11),
+			PIC32_PINCTRL_FUNCTION(OC6, RPB10R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO4, RPB10R, 13),
+			PIC32_PINCTRL_FUNCTION(C2OUT, RPB10R, 14),
+			PIC32_PINCTRL_FUNCTION(C1TX, RPB10R, 15)),
+	PIC32_PINCTRL_GROUP(30, B14,
+			PIC32_PINCTRL_FUNCTION(INT1, INT1R, 2),
+			PIC32_PINCTRL_FUNCTION(T4CK, T4CKR, 2),
+			PIC32_PINCTRL_FUNCTION(T9CK, T9CKR, 2),
+			PIC32_PINCTRL_FUNCTION(IC1, IC1R, 2),
+			PIC32_PINCTRL_FUNCTION(IC6, IC6R, 2),
+			PIC32_PINCTRL_FUNCTION(U3CTS, U3CTSR, 2),
+			PIC32_PINCTRL_FUNCTION(U4RX, U4RXR, 2),
+			PIC32_PINCTRL_FUNCTION(U6RX, U6RXR, 2),
+			PIC32_PINCTRL_FUNCTION(SS2IN, SS2INR, 2),
+			PIC32_PINCTRL_FUNCTION(SDI6, SDI6R, 2),
+			PIC32_PINCTRL_FUNCTION(OCFA, OCFAR, 2),
+			PIC32_PINCTRL_FUNCTION(REFCLKI3, REFCLKI3R, 2),
+			PIC32_PINCTRL_FUNCTION(U1RTS, RPB14R, 1),
+			PIC32_PINCTRL_FUNCTION(U2TX, RPB14R, 2),
+			PIC32_PINCTRL_FUNCTION(U5RTS, RPB14R, 3),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPB14R, 4),
+			PIC32_PINCTRL_FUNCTION(SS2OUT, RPB14R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPB14R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPB14R, 10),
+			PIC32_PINCTRL_FUNCTION(OC2, RPB14R, 11),
+			PIC32_PINCTRL_FUNCTION(OC1, RPB14R, 12),
+			PIC32_PINCTRL_FUNCTION(OC9, RPB14R, 13),
+			PIC32_PINCTRL_FUNCTION(C2TX, RPB14R, 15)),
+	PIC32_PINCTRL_GROUP(31, B15,
+			PIC32_PINCTRL_FUNCTION(INT2, INT2R, 3),
+			PIC32_PINCTRL_FUNCTION(T3CK, T3CKR, 3),
+			PIC32_PINCTRL_FUNCTION(T8CK, T8CKR, 3),
+			PIC32_PINCTRL_FUNCTION(IC2, IC2R, 3),
+			PIC32_PINCTRL_FUNCTION(IC5, IC5R, 3),
+			PIC32_PINCTRL_FUNCTION(IC9, IC9R, 3),
+			PIC32_PINCTRL_FUNCTION(U1CTS, U1CTSR, 3),
+			PIC32_PINCTRL_FUNCTION(U2RX, U2RXR, 3),
+			PIC32_PINCTRL_FUNCTION(U5CTS, U5CTSR, 3),
+			PIC32_PINCTRL_FUNCTION(SS1IN, SS1INR, 3),
+			PIC32_PINCTRL_FUNCTION(SS3IN, SS3INR, 3),
+			PIC32_PINCTRL_FUNCTION(SS4IN, SS4INR, 3),
+			PIC32_PINCTRL_FUNCTION(SS5IN, SS5INR, 3),
+			PIC32_PINCTRL_FUNCTION(C2RX, C2RXR, 3),
+			PIC32_PINCTRL_FUNCTION(U3RTS, RPB15R, 1),
+			PIC32_PINCTRL_FUNCTION(U4TX, RPB15R, 2),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPB15R, 4),
+			PIC32_PINCTRL_FUNCTION(SS1OUT, RPB15R, 5),
+			PIC32_PINCTRL_FUNCTION(SS3OUT, RPB15R, 7),
+			PIC32_PINCTRL_FUNCTION(SS4OUT, RPB15R, 8),
+			PIC32_PINCTRL_FUNCTION(SS5OUT, RPB15R, 9),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPB15R, 10),
+			PIC32_PINCTRL_FUNCTION(OC5, RPB15R, 11),
+			PIC32_PINCTRL_FUNCTION(OC8, RPB15R, 12),
+			PIC32_PINCTRL_FUNCTION(C1OUT, RPB15R, 14),
+			PIC32_PINCTRL_FUNCTION(REFCLKO3, RPB15R, 15)),
+	PIC32_PINCTRL_GROUP(33, C1,
+			PIC32_PINCTRL_FUNCTION(INT3, INT3R, 10),
+			PIC32_PINCTRL_FUNCTION(T2CK, T2CKR, 10),
+			PIC32_PINCTRL_FUNCTION(T6CK, T6CKR, 10),
+			PIC32_PINCTRL_FUNCTION(IC3, IC3R, 10),
+			PIC32_PINCTRL_FUNCTION(IC7, IC7R, 10),
+			PIC32_PINCTRL_FUNCTION(U1RX, U1RXR, 10),
+			PIC32_PINCTRL_FUNCTION(U2CTS, U2CTSR, 10),
+			PIC32_PINCTRL_FUNCTION(U5RX, U5RXR, 10),
+			PIC32_PINCTRL_FUNCTION(U6CTS, U6CTSR, 10),
+			PIC32_PINCTRL_FUNCTION(SDI1, SDI1R, 10),
+			PIC32_PINCTRL_FUNCTION(SDI3, SDI3R, 10),
+			PIC32_PINCTRL_FUNCTION(SDI5, SDI5R, 10),
+			PIC32_PINCTRL_FUNCTION(SS6IN, SS6INR, 10),
+			PIC32_PINCTRL_FUNCTION(REFCLKI1, REFCLKI1R, 10),
+			PIC32_PINCTRL_FUNCTION(U3TX, RPC1R, 1),
+			PIC32_PINCTRL_FUNCTION(U4RTS, RPC1R, 2),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPC1R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPC1R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPC1R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPC1R, 9),
+			PIC32_PINCTRL_FUNCTION(SS6OUT, RPC1R, 10),
+			PIC32_PINCTRL_FUNCTION(OC3, RPC1R, 11),
+			PIC32_PINCTRL_FUNCTION(OC6, RPC1R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO4, RPC1R, 13),
+			PIC32_PINCTRL_FUNCTION(C2OUT, RPC1R, 14),
+			PIC32_PINCTRL_FUNCTION(C1TX, RPC1R, 15)),
+	PIC32_PINCTRL_GROUP(34, C2,
+			PIC32_PINCTRL_FUNCTION(INT1, INT1R, 12),
+			PIC32_PINCTRL_FUNCTION(T4CK, T4CKR, 12),
+			PIC32_PINCTRL_FUNCTION(T9CK, T9CKR, 12),
+			PIC32_PINCTRL_FUNCTION(IC1, IC1R, 12),
+			PIC32_PINCTRL_FUNCTION(IC6, IC6R, 12),
+			PIC32_PINCTRL_FUNCTION(U3CTS, U3CTSR, 12),
+			PIC32_PINCTRL_FUNCTION(U4RX, U4RXR, 12),
+			PIC32_PINCTRL_FUNCTION(U6RX, U6RXR, 12),
+			PIC32_PINCTRL_FUNCTION(SS2IN, SS2INR, 12),
+			PIC32_PINCTRL_FUNCTION(SDI6, SDI6R, 12),
+			PIC32_PINCTRL_FUNCTION(OCFA, OCFAR, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKI3, REFCLKI3R, 12),
+			PIC32_PINCTRL_FUNCTION(U1RTS, RPC2R, 1),
+			PIC32_PINCTRL_FUNCTION(U2TX, RPC2R, 2),
+			PIC32_PINCTRL_FUNCTION(U5RTS, RPC2R, 3),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPC2R, 4),
+			PIC32_PINCTRL_FUNCTION(SS2OUT, RPC2R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPC2R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPC2R, 10),
+			PIC32_PINCTRL_FUNCTION(OC2, RPC2R, 11),
+			PIC32_PINCTRL_FUNCTION(OC1, RPC2R, 12),
+			PIC32_PINCTRL_FUNCTION(OC9, RPC2R, 13),
+			PIC32_PINCTRL_FUNCTION(C2TX, RPC2R, 15)),
+	PIC32_PINCTRL_GROUP(35, C3,
+			PIC32_PINCTRL_FUNCTION(INT2, INT2R, 12),
+			PIC32_PINCTRL_FUNCTION(T3CK, T3CKR, 12),
+			PIC32_PINCTRL_FUNCTION(T8CK, T8CKR, 12),
+			PIC32_PINCTRL_FUNCTION(IC2, IC2R, 12),
+			PIC32_PINCTRL_FUNCTION(IC5, IC5R, 12),
+			PIC32_PINCTRL_FUNCTION(IC9, IC9R, 12),
+			PIC32_PINCTRL_FUNCTION(U1CTS, U1CTSR, 12),
+			PIC32_PINCTRL_FUNCTION(U2RX, U2RXR, 12),
+			PIC32_PINCTRL_FUNCTION(U5CTS, U5CTSR, 12),
+			PIC32_PINCTRL_FUNCTION(SS1IN, SS1INR, 12),
+			PIC32_PINCTRL_FUNCTION(SS3IN, SS3INR, 12),
+			PIC32_PINCTRL_FUNCTION(SS4IN, SS4INR, 12),
+			PIC32_PINCTRL_FUNCTION(SS5IN, SS5INR, 12),
+			PIC32_PINCTRL_FUNCTION(C2RX, C2RXR, 12),
+			PIC32_PINCTRL_FUNCTION(U3RTS, RPC3R, 1),
+			PIC32_PINCTRL_FUNCTION(U4TX, RPC3R, 2),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPC3R, 4),
+			PIC32_PINCTRL_FUNCTION(SS1OUT, RPC3R, 5),
+			PIC32_PINCTRL_FUNCTION(SS3OUT, RPC3R, 7),
+			PIC32_PINCTRL_FUNCTION(SS4OUT, RPC3R, 8),
+			PIC32_PINCTRL_FUNCTION(SS5OUT, RPC3R, 9),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPC3R, 10),
+			PIC32_PINCTRL_FUNCTION(OC5, RPC3R, 11),
+			PIC32_PINCTRL_FUNCTION(OC8, RPC3R, 12),
+			PIC32_PINCTRL_FUNCTION(C1OUT, RPC3R, 14),
+			PIC32_PINCTRL_FUNCTION(REFCLKO3, RPC3R, 15)),
+	PIC32_PINCTRL_GROUP(36, C4,
+			PIC32_PINCTRL_FUNCTION(INT4, INT4R, 10),
+			PIC32_PINCTRL_FUNCTION(T5CK, T5CKR, 10),
+			PIC32_PINCTRL_FUNCTION(T7CK, T7CKR, 10),
+			PIC32_PINCTRL_FUNCTION(IC4, IC4R, 10),
+			PIC32_PINCTRL_FUNCTION(IC8, IC8R, 10),
+			PIC32_PINCTRL_FUNCTION(U3RX, U3RXR, 10),
+			PIC32_PINCTRL_FUNCTION(U4CTS, U4CTSR, 10),
+			PIC32_PINCTRL_FUNCTION(SDI2, SDI2R, 10),
+			PIC32_PINCTRL_FUNCTION(SDI4, SDI4R, 10),
+			PIC32_PINCTRL_FUNCTION(C1RX, C1RXR, 10),
+			PIC32_PINCTRL_FUNCTION(REFCLKI4, REFCLKI4R, 10),
+			PIC32_PINCTRL_FUNCTION(U1TX, RPC4R, 1),
+			PIC32_PINCTRL_FUNCTION(U2RTS, RPC4R, 2),
+			PIC32_PINCTRL_FUNCTION(U5TX, RPC4R, 3),
+			PIC32_PINCTRL_FUNCTION(U6RTS, RPC4R, 4),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPC4R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPC4R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPC4R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPC4R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPC4R, 9),
+			PIC32_PINCTRL_FUNCTION(OC4, RPC4R, 11),
+			PIC32_PINCTRL_FUNCTION(OC7, RPC4R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO1, RPC4R, 15)),
+	PIC32_PINCTRL_GROUP(45, C13,
+			PIC32_PINCTRL_FUNCTION(INT4, INT4R, 7),
+			PIC32_PINCTRL_FUNCTION(T5CK, T5CKR, 7),
+			PIC32_PINCTRL_FUNCTION(T7CK, T7CKR, 7),
+			PIC32_PINCTRL_FUNCTION(IC4, IC4R, 7),
+			PIC32_PINCTRL_FUNCTION(IC8, IC8R, 7),
+			PIC32_PINCTRL_FUNCTION(U3RX, U3RXR, 7),
+			PIC32_PINCTRL_FUNCTION(U4CTS, U4CTSR, 7),
+			PIC32_PINCTRL_FUNCTION(SDI2, SDI2R, 7),
+			PIC32_PINCTRL_FUNCTION(SDI4, SDI4R, 7),
+			PIC32_PINCTRL_FUNCTION(C1RX, C1RXR, 7),
+			PIC32_PINCTRL_FUNCTION(REFCLKI4, REFCLKI4R, 7),
+			PIC32_PINCTRL_FUNCTION(U1TX, RPC13R, 1),
+			PIC32_PINCTRL_FUNCTION(U2RTS, RPC13R, 2),
+			PIC32_PINCTRL_FUNCTION(U5TX, RPC13R, 3),
+			PIC32_PINCTRL_FUNCTION(U6RTS, RPC13R, 4),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPC13R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPC13R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPC13R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPC13R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPC13R, 9),
+			PIC32_PINCTRL_FUNCTION(OC4, RPC13R, 11),
+			PIC32_PINCTRL_FUNCTION(OC7, RPC13R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO1, RPC13R, 15)),
+	PIC32_PINCTRL_GROUP(46, C14,
+			PIC32_PINCTRL_FUNCTION(INT3, INT3R, 7),
+			PIC32_PINCTRL_FUNCTION(T2CK, T2CKR, 7),
+			PIC32_PINCTRL_FUNCTION(T6CK, T6CKR, 7),
+			PIC32_PINCTRL_FUNCTION(IC3, IC3R, 7),
+			PIC32_PINCTRL_FUNCTION(IC7, IC7R, 7),
+			PIC32_PINCTRL_FUNCTION(U1RX, U1RXR, 7),
+			PIC32_PINCTRL_FUNCTION(U2CTS, U2CTSR, 7),
+			PIC32_PINCTRL_FUNCTION(U5RX, U5RXR, 7),
+			PIC32_PINCTRL_FUNCTION(U6CTS, U6CTSR, 7),
+			PIC32_PINCTRL_FUNCTION(SDI1, SDI1R, 7),
+			PIC32_PINCTRL_FUNCTION(SDI3, SDI3R, 7),
+			PIC32_PINCTRL_FUNCTION(SDI5, SDI5R, 7),
+			PIC32_PINCTRL_FUNCTION(SS6IN, SS6INR, 7),
+			PIC32_PINCTRL_FUNCTION(REFCLKI1, REFCLKI1R, 7),
+			PIC32_PINCTRL_FUNCTION(U3TX, RPC14R, 1),
+			PIC32_PINCTRL_FUNCTION(U4RTS, RPC14R, 2),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPC14R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPC14R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPC14R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPC14R, 9),
+			PIC32_PINCTRL_FUNCTION(SS6OUT, RPC14R, 10),
+			PIC32_PINCTRL_FUNCTION(OC3, RPC14R, 11),
+			PIC32_PINCTRL_FUNCTION(OC6, RPC14R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO4, RPC14R, 13),
+			PIC32_PINCTRL_FUNCTION(C2OUT, RPC14R, 14),
+			PIC32_PINCTRL_FUNCTION(C1TX, RPC14R, 15)),
+	PIC32_PINCTRL_GROUP(48, D0,
+			PIC32_PINCTRL_FUNCTION(INT1, INT1R, 3),
+			PIC32_PINCTRL_FUNCTION(T4CK, T4CKR, 3),
+			PIC32_PINCTRL_FUNCTION(T9CK, T9CKR, 3),
+			PIC32_PINCTRL_FUNCTION(IC1, IC1R, 3),
+			PIC32_PINCTRL_FUNCTION(IC6, IC6R, 3),
+			PIC32_PINCTRL_FUNCTION(U3CTS, U3CTSR, 3),
+			PIC32_PINCTRL_FUNCTION(U4RX, U4RXR, 3),
+			PIC32_PINCTRL_FUNCTION(U6RX, U6RXR, 3),
+			PIC32_PINCTRL_FUNCTION(SS2IN, SS2INR, 3),
+			PIC32_PINCTRL_FUNCTION(SDI6, SDI6R, 3),
+			PIC32_PINCTRL_FUNCTION(OCFA, OCFAR, 3),
+			PIC32_PINCTRL_FUNCTION(REFCLKI3, REFCLKI3R, 3),
+			PIC32_PINCTRL_FUNCTION(U1RTS, RPD0R, 1),
+			PIC32_PINCTRL_FUNCTION(U2TX, RPD0R, 2),
+			PIC32_PINCTRL_FUNCTION(U5RTS, RPD0R, 3),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPD0R, 4),
+			PIC32_PINCTRL_FUNCTION(SS2OUT, RPD0R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPD0R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPD0R, 10),
+			PIC32_PINCTRL_FUNCTION(OC2, RPD0R, 11),
+			PIC32_PINCTRL_FUNCTION(OC1, RPD0R, 12),
+			PIC32_PINCTRL_FUNCTION(OC9, RPD0R, 13),
+			PIC32_PINCTRL_FUNCTION(C2TX, RPD0R, 15)),
+	PIC32_PINCTRL_GROUP(50, D2,
+			PIC32_PINCTRL_FUNCTION(INT3, INT3R, 0),
+			PIC32_PINCTRL_FUNCTION(T2CK, T2CKR, 0),
+			PIC32_PINCTRL_FUNCTION(T6CK, T6CKR, 0),
+			PIC32_PINCTRL_FUNCTION(IC3, IC3R, 0),
+			PIC32_PINCTRL_FUNCTION(IC7, IC7R, 0),
+			PIC32_PINCTRL_FUNCTION(U1RX, U1RXR, 0),
+			PIC32_PINCTRL_FUNCTION(U2CTS, U2CTSR, 0),
+			PIC32_PINCTRL_FUNCTION(U5RX, U5RXR, 0),
+			PIC32_PINCTRL_FUNCTION(U6CTS, U6CTSR, 0),
+			PIC32_PINCTRL_FUNCTION(SDI1, SDI1R, 0),
+			PIC32_PINCTRL_FUNCTION(SDI3, SDI3R, 0),
+			PIC32_PINCTRL_FUNCTION(SDI5, SDI5R, 0),
+			PIC32_PINCTRL_FUNCTION(SS6IN, SS6INR, 0),
+			PIC32_PINCTRL_FUNCTION(REFCLKI1, REFCLKI1R, 0),
+			PIC32_PINCTRL_FUNCTION(U3TX, RPD2R, 1),
+			PIC32_PINCTRL_FUNCTION(U4RTS, RPD2R, 2),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPD2R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPD2R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPD2R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPD2R, 9),
+			PIC32_PINCTRL_FUNCTION(SS6OUT, RPD2R, 10),
+			PIC32_PINCTRL_FUNCTION(OC3, RPD2R, 11),
+			PIC32_PINCTRL_FUNCTION(OC6, RPD2R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO4, RPD2R, 13),
+			PIC32_PINCTRL_FUNCTION(C2OUT, RPD2R, 14),
+			PIC32_PINCTRL_FUNCTION(C1TX, RPD2R, 15)),
+	PIC32_PINCTRL_GROUP(51, D3,
+			PIC32_PINCTRL_FUNCTION(INT4, INT4R, 0),
+			PIC32_PINCTRL_FUNCTION(T5CK, T5CKR, 0),
+			PIC32_PINCTRL_FUNCTION(T7CK, T7CKR, 0),
+			PIC32_PINCTRL_FUNCTION(IC4, IC4R, 0),
+			PIC32_PINCTRL_FUNCTION(IC8, IC8R, 0),
+			PIC32_PINCTRL_FUNCTION(U3RX, U3RXR, 0),
+			PIC32_PINCTRL_FUNCTION(U4CTS, U4CTSR, 0),
+			PIC32_PINCTRL_FUNCTION(SDI2, SDI2R, 0),
+			PIC32_PINCTRL_FUNCTION(SDI4, SDI4R, 0),
+			PIC32_PINCTRL_FUNCTION(C1RX, C1RXR, 0),
+			PIC32_PINCTRL_FUNCTION(REFCLKI4, REFCLKI4R, 0),
+			PIC32_PINCTRL_FUNCTION(U1TX, RPD3R, 1),
+			PIC32_PINCTRL_FUNCTION(U2RTS, RPD3R, 2),
+			PIC32_PINCTRL_FUNCTION(U5TX, RPD3R, 3),
+			PIC32_PINCTRL_FUNCTION(U6RTS, RPD3R, 4),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPD3R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPD3R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPD3R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPD3R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPD3R, 9),
+			PIC32_PINCTRL_FUNCTION(OC4, RPD3R, 11),
+			PIC32_PINCTRL_FUNCTION(OC7, RPD3R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO1, RPD3R, 15)),
+	PIC32_PINCTRL_GROUP(52, D4,
+			PIC32_PINCTRL_FUNCTION(INT2, INT2R, 4),
+			PIC32_PINCTRL_FUNCTION(T3CK, T3CKR, 4),
+			PIC32_PINCTRL_FUNCTION(T8CK, T8CKR, 4),
+			PIC32_PINCTRL_FUNCTION(IC2, IC2R, 4),
+			PIC32_PINCTRL_FUNCTION(IC5, IC5R, 4),
+			PIC32_PINCTRL_FUNCTION(IC9, IC9R, 4),
+			PIC32_PINCTRL_FUNCTION(U1CTS, U1CTSR, 4),
+			PIC32_PINCTRL_FUNCTION(U2RX, U2RXR, 4),
+			PIC32_PINCTRL_FUNCTION(U5CTS, U5CTSR, 4),
+			PIC32_PINCTRL_FUNCTION(SS1IN, SS1INR, 4),
+			PIC32_PINCTRL_FUNCTION(SS3IN, SS3INR, 4),
+			PIC32_PINCTRL_FUNCTION(SS4IN, SS4INR, 4),
+			PIC32_PINCTRL_FUNCTION(SS5IN, SS5INR, 4),
+			PIC32_PINCTRL_FUNCTION(C2RX, C2RXR, 4),
+			PIC32_PINCTRL_FUNCTION(U3RTS, RPD4R, 1),
+			PIC32_PINCTRL_FUNCTION(U4TX, RPD4R, 2),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPD4R, 4),
+			PIC32_PINCTRL_FUNCTION(SS1OUT, RPD4R, 5),
+			PIC32_PINCTRL_FUNCTION(SS3OUT, RPD4R, 7),
+			PIC32_PINCTRL_FUNCTION(SS4OUT, RPD4R, 8),
+			PIC32_PINCTRL_FUNCTION(SS5OUT, RPD4R, 9),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPD4R, 10),
+			PIC32_PINCTRL_FUNCTION(OC5, RPD4R, 11),
+			PIC32_PINCTRL_FUNCTION(OC8, RPD4R, 12),
+			PIC32_PINCTRL_FUNCTION(C1OUT, RPD4R, 14),
+			PIC32_PINCTRL_FUNCTION(REFCLKO3, RPD4R, 15)),
+	PIC32_PINCTRL_GROUP(53, D5,
+			PIC32_PINCTRL_FUNCTION(INT1, INT1R, 6),
+			PIC32_PINCTRL_FUNCTION(T4CK, T4CKR, 6),
+			PIC32_PINCTRL_FUNCTION(T9CK, T9CKR, 6),
+			PIC32_PINCTRL_FUNCTION(IC1, IC1R, 6),
+			PIC32_PINCTRL_FUNCTION(IC6, IC6R, 6),
+			PIC32_PINCTRL_FUNCTION(U3CTS, U3CTSR, 6),
+			PIC32_PINCTRL_FUNCTION(U4RX, U4RXR, 6),
+			PIC32_PINCTRL_FUNCTION(U6RX, U6RXR, 6),
+			PIC32_PINCTRL_FUNCTION(SS2IN, SS2INR, 6),
+			PIC32_PINCTRL_FUNCTION(SDI6, SDI6R, 6),
+			PIC32_PINCTRL_FUNCTION(OCFA, OCFAR, 6),
+			PIC32_PINCTRL_FUNCTION(REFCLKI3, REFCLKI3R, 6),
+			PIC32_PINCTRL_FUNCTION(U1RTS, RPD5R, 1),
+			PIC32_PINCTRL_FUNCTION(U2TX, RPD5R, 2),
+			PIC32_PINCTRL_FUNCTION(U5RTS, RPD5R, 3),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPD5R, 4),
+			PIC32_PINCTRL_FUNCTION(SS2OUT, RPD5R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPD5R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPD5R, 10),
+			PIC32_PINCTRL_FUNCTION(OC2, RPD5R, 11),
+			PIC32_PINCTRL_FUNCTION(OC1, RPD5R, 12),
+			PIC32_PINCTRL_FUNCTION(OC9, RPD5R, 13),
+			PIC32_PINCTRL_FUNCTION(C2TX, RPD5R, 15)),
+	PIC32_PINCTRL_GROUP(54, D6,
+			PIC32_PINCTRL_FUNCTION(INT3, INT3R, 14),
+			PIC32_PINCTRL_FUNCTION(T2CK, T2CKR, 14),
+			PIC32_PINCTRL_FUNCTION(T6CK, T6CKR, 14),
+			PIC32_PINCTRL_FUNCTION(IC3, IC3R, 14),
+			PIC32_PINCTRL_FUNCTION(IC7, IC7R, 14),
+			PIC32_PINCTRL_FUNCTION(U1RX, U1RXR, 14),
+			PIC32_PINCTRL_FUNCTION(U2CTS, U2CTSR, 14),
+			PIC32_PINCTRL_FUNCTION(U5RX, U5RXR, 14),
+			PIC32_PINCTRL_FUNCTION(U6CTS, U6CTSR, 14),
+			PIC32_PINCTRL_FUNCTION(SDI1, SDI1R, 14),
+			PIC32_PINCTRL_FUNCTION(SDI3, SDI3R, 14),
+			PIC32_PINCTRL_FUNCTION(SDI5, SDI5R, 14),
+			PIC32_PINCTRL_FUNCTION(SS6IN, SS6INR, 14),
+			PIC32_PINCTRL_FUNCTION(REFCLKI1, REFCLKI1R, 14),
+			PIC32_PINCTRL_FUNCTION(U3TX, RPD6R, 1),
+			PIC32_PINCTRL_FUNCTION(U4RTS, RPD6R, 2),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPD6R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPD6R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPD6R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPD6R, 9),
+			PIC32_PINCTRL_FUNCTION(SS6OUT, RPD6R, 10),
+			PIC32_PINCTRL_FUNCTION(OC3, RPD6R, 11),
+			PIC32_PINCTRL_FUNCTION(OC6, RPD6R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO4, RPD6R, 13),
+			PIC32_PINCTRL_FUNCTION(C2OUT, RPD6R, 14),
+			PIC32_PINCTRL_FUNCTION(C1TX, RPD6R, 15)),
+	PIC32_PINCTRL_GROUP(55, D7,
+			PIC32_PINCTRL_FUNCTION(INT4, INT4R, 14),
+			PIC32_PINCTRL_FUNCTION(T5CK, T5CKR, 14),
+			PIC32_PINCTRL_FUNCTION(T7CK, T7CKR, 14),
+			PIC32_PINCTRL_FUNCTION(IC4, IC4R, 14),
+			PIC32_PINCTRL_FUNCTION(IC8, IC8R, 14),
+			PIC32_PINCTRL_FUNCTION(U3RX, U3RXR, 14),
+			PIC32_PINCTRL_FUNCTION(U4CTS, U4CTSR, 14),
+			PIC32_PINCTRL_FUNCTION(SDI2, SDI2R, 14),
+			PIC32_PINCTRL_FUNCTION(SDI4, SDI4R, 14),
+			PIC32_PINCTRL_FUNCTION(C1RX, C1RXR, 14),
+			PIC32_PINCTRL_FUNCTION(REFCLKI4, REFCLKI4R, 14),
+			PIC32_PINCTRL_FUNCTION(U1TX, RPD7R, 1),
+			PIC32_PINCTRL_FUNCTION(U2RTS, RPD7R, 2),
+			PIC32_PINCTRL_FUNCTION(U5TX, RPD7R, 3),
+			PIC32_PINCTRL_FUNCTION(U6RTS, RPD7R, 4),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPD7R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPD7R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPD7R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPD7R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPD7R, 9),
+			PIC32_PINCTRL_FUNCTION(OC4, RPD7R, 11),
+			PIC32_PINCTRL_FUNCTION(OC7, RPD7R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO1, RPD7R, 15)),
+	PIC32_PINCTRL_GROUP(57, D9,
+			PIC32_PINCTRL_FUNCTION(INT2, INT2R, 0),
+			PIC32_PINCTRL_FUNCTION(T3CK, T3CKR, 0),
+			PIC32_PINCTRL_FUNCTION(T8CK, T8CKR, 0),
+			PIC32_PINCTRL_FUNCTION(IC2, IC2R, 0),
+			PIC32_PINCTRL_FUNCTION(IC5, IC5R, 0),
+			PIC32_PINCTRL_FUNCTION(IC9, IC9R, 0),
+			PIC32_PINCTRL_FUNCTION(U1CTS, U1CTSR, 0),
+			PIC32_PINCTRL_FUNCTION(U2RX, U2RXR, 0),
+			PIC32_PINCTRL_FUNCTION(U5CTS, U5CTSR, 0),
+			PIC32_PINCTRL_FUNCTION(SS1IN, SS1INR, 0),
+			PIC32_PINCTRL_FUNCTION(SS3IN, SS3INR, 0),
+			PIC32_PINCTRL_FUNCTION(SS4IN, SS4INR, 0),
+			PIC32_PINCTRL_FUNCTION(SS5IN, SS5INR, 0),
+			PIC32_PINCTRL_FUNCTION(C2RX, C2RXR, 0),
+			PIC32_PINCTRL_FUNCTION(U3RTS, RPD9R, 1),
+			PIC32_PINCTRL_FUNCTION(U4TX, RPD9R, 2),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPD9R, 4),
+			PIC32_PINCTRL_FUNCTION(SS1OUT, RPD9R, 5),
+			PIC32_PINCTRL_FUNCTION(SS3OUT, RPD9R, 7),
+			PIC32_PINCTRL_FUNCTION(SS4OUT, RPD9R, 8),
+			PIC32_PINCTRL_FUNCTION(SS5OUT, RPD9R, 9),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPD9R, 10),
+			PIC32_PINCTRL_FUNCTION(OC5, RPD9R, 11),
+			PIC32_PINCTRL_FUNCTION(OC8, RPD9R, 12),
+			PIC32_PINCTRL_FUNCTION(C1OUT, RPD9R, 14),
+			PIC32_PINCTRL_FUNCTION(REFCLKO3, RPD9R, 15)),
+	PIC32_PINCTRL_GROUP(58, D10,
+			PIC32_PINCTRL_FUNCTION(U3TX, RPD10R, 1),
+			PIC32_PINCTRL_FUNCTION(U4RTS, RPD10R, 2),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPD10R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPD10R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPD10R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPD10R, 9),
+			PIC32_PINCTRL_FUNCTION(SS6OUT, RPD10R, 10),
+			PIC32_PINCTRL_FUNCTION(OC3, RPD10R, 11),
+			PIC32_PINCTRL_FUNCTION(OC6, RPD10R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO4, RPD10R, 13),
+			PIC32_PINCTRL_FUNCTION(C2OUT, RPD10R, 14),
+			PIC32_PINCTRL_FUNCTION(C1TX, RPD10R, 15)),
+	PIC32_PINCTRL_GROUP(59, D11,
+			PIC32_PINCTRL_FUNCTION(INT4, INT4R, 3),
+			PIC32_PINCTRL_FUNCTION(T5CK, T5CKR, 3),
+			PIC32_PINCTRL_FUNCTION(T7CK, T7CKR, 3),
+			PIC32_PINCTRL_FUNCTION(IC4, IC4R, 3),
+			PIC32_PINCTRL_FUNCTION(IC8, IC8R, 3),
+			PIC32_PINCTRL_FUNCTION(U3RX, U3RXR, 3),
+			PIC32_PINCTRL_FUNCTION(U4CTS, U4CTSR, 3),
+			PIC32_PINCTRL_FUNCTION(SDI2, SDI2R, 3),
+			PIC32_PINCTRL_FUNCTION(SDI4, SDI4R, 3),
+			PIC32_PINCTRL_FUNCTION(C1RX, C1RXR, 3),
+			PIC32_PINCTRL_FUNCTION(REFCLKI4, REFCLKI4R, 3),
+			PIC32_PINCTRL_FUNCTION(U1TX, RPD11R, 1),
+			PIC32_PINCTRL_FUNCTION(U2RTS, RPD11R, 2),
+			PIC32_PINCTRL_FUNCTION(U5TX, RPD11R, 3),
+			PIC32_PINCTRL_FUNCTION(U6RTS, RPD11R, 4),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPD11R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPD11R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPD11R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPD11R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPD11R, 9),
+			PIC32_PINCTRL_FUNCTION(OC4, RPD11R, 11),
+			PIC32_PINCTRL_FUNCTION(OC7, RPD11R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO1, RPD11R, 15)),
+	PIC32_PINCTRL_GROUP(60, D12,
+			PIC32_PINCTRL_FUNCTION(INT2, INT2R, 10),
+			PIC32_PINCTRL_FUNCTION(T3CK, T3CKR, 10),
+			PIC32_PINCTRL_FUNCTION(T8CK, T8CKR, 10),
+			PIC32_PINCTRL_FUNCTION(IC2, IC2R, 10),
+			PIC32_PINCTRL_FUNCTION(IC5, IC5R, 10),
+			PIC32_PINCTRL_FUNCTION(IC9, IC9R, 10),
+			PIC32_PINCTRL_FUNCTION(U1CTS, U1CTSR, 10),
+			PIC32_PINCTRL_FUNCTION(U2RX, U2RXR, 10),
+			PIC32_PINCTRL_FUNCTION(U5CTS, U5CTSR, 10),
+			PIC32_PINCTRL_FUNCTION(SS1IN, SS1INR, 10),
+			PIC32_PINCTRL_FUNCTION(SS3IN, SS3INR, 10),
+			PIC32_PINCTRL_FUNCTION(SS4IN, SS4INR, 10),
+			PIC32_PINCTRL_FUNCTION(SS5IN, SS5INR, 10),
+			PIC32_PINCTRL_FUNCTION(C2RX, C2RXR, 10),
+			PIC32_PINCTRL_FUNCTION(U3RTS, RPD12R, 1),
+			PIC32_PINCTRL_FUNCTION(U4TX, RPD12R, 2),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPD12R, 4),
+			PIC32_PINCTRL_FUNCTION(SS1OUT, RPD12R, 5),
+			PIC32_PINCTRL_FUNCTION(SS3OUT, RPD12R, 7),
+			PIC32_PINCTRL_FUNCTION(SS4OUT, RPD12R, 8),
+			PIC32_PINCTRL_FUNCTION(SS5OUT, RPD12R, 9),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPD12R, 10),
+			PIC32_PINCTRL_FUNCTION(OC5, RPD12R, 11),
+			PIC32_PINCTRL_FUNCTION(OC8, RPD12R, 12),
+			PIC32_PINCTRL_FUNCTION(C1OUT, RPD12R, 14),
+			PIC32_PINCTRL_FUNCTION(REFCLKO3, RPD12R, 15)),
+	PIC32_PINCTRL_GROUP(62, D14,
+			PIC32_PINCTRL_FUNCTION(INT3, INT3R, 11),
+			PIC32_PINCTRL_FUNCTION(T2CK, T2CKR, 11),
+			PIC32_PINCTRL_FUNCTION(T6CK, T6CKR, 11),
+			PIC32_PINCTRL_FUNCTION(IC3, IC3R, 11),
+			PIC32_PINCTRL_FUNCTION(IC7, IC7R, 11),
+			PIC32_PINCTRL_FUNCTION(U1RX, U1RXR, 11),
+			PIC32_PINCTRL_FUNCTION(U2CTS, U2CTSR, 11),
+			PIC32_PINCTRL_FUNCTION(U5RX, U5RXR, 11),
+			PIC32_PINCTRL_FUNCTION(U6CTS, U6CTSR, 11),
+			PIC32_PINCTRL_FUNCTION(SDI1, SDI1R, 11),
+			PIC32_PINCTRL_FUNCTION(SDI3, SDI3R, 11),
+			PIC32_PINCTRL_FUNCTION(SDI5, SDI5R, 11),
+			PIC32_PINCTRL_FUNCTION(SS6IN, SS6INR, 11),
+			PIC32_PINCTRL_FUNCTION(REFCLKI1, REFCLKI1R, 11),
+			PIC32_PINCTRL_FUNCTION(U3TX, RPD14R, 1),
+			PIC32_PINCTRL_FUNCTION(U4RTS, RPD14R, 2),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPD14R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPD14R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPD14R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPD14R, 9),
+			PIC32_PINCTRL_FUNCTION(SS6OUT, RPD14R, 10),
+			PIC32_PINCTRL_FUNCTION(OC3, RPD14R, 11),
+			PIC32_PINCTRL_FUNCTION(OC6, RPD14R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO4, RPD14R, 13),
+			PIC32_PINCTRL_FUNCTION(C2OUT, RPD14R, 14),
+			PIC32_PINCTRL_FUNCTION(C1TX, RPD14R, 15)),
+	PIC32_PINCTRL_GROUP(63, D15,
+			PIC32_PINCTRL_FUNCTION(U1TX, RPD15R, 1),
+			PIC32_PINCTRL_FUNCTION(U2RTS, RPD15R, 2),
+			PIC32_PINCTRL_FUNCTION(U5TX, RPD15R, 3),
+			PIC32_PINCTRL_FUNCTION(U6RTS, RPD15R, 4),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPD15R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPD15R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPD15R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPD15R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPD15R, 9),
+			PIC32_PINCTRL_FUNCTION(OC4, RPD15R, 11),
+			PIC32_PINCTRL_FUNCTION(OC7, RPD15R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO1, RPD15R, 15)),
+	PIC32_PINCTRL_GROUP(67, E3,
+			PIC32_PINCTRL_FUNCTION(INT2, INT2R, 6),
+			PIC32_PINCTRL_FUNCTION(T3CK, T3CKR, 6),
+			PIC32_PINCTRL_FUNCTION(T8CK, T8CKR, 6),
+			PIC32_PINCTRL_FUNCTION(IC2, IC2R, 6),
+			PIC32_PINCTRL_FUNCTION(IC5, IC5R, 6),
+			PIC32_PINCTRL_FUNCTION(IC9, IC9R, 6),
+			PIC32_PINCTRL_FUNCTION(U1CTS, U1CTSR, 6),
+			PIC32_PINCTRL_FUNCTION(U2RX, U2RXR, 6),
+			PIC32_PINCTRL_FUNCTION(U5CTS, U5CTSR, 6),
+			PIC32_PINCTRL_FUNCTION(SS1IN, SS1INR, 6),
+			PIC32_PINCTRL_FUNCTION(SS3IN, SS3INR, 6),
+			PIC32_PINCTRL_FUNCTION(SS4IN, SS4INR, 6),
+			PIC32_PINCTRL_FUNCTION(SS5IN, SS5INR, 6),
+			PIC32_PINCTRL_FUNCTION(C2RX, C2RXR, 6),
+			PIC32_PINCTRL_FUNCTION(U3RTS, RPE3R, 1),
+			PIC32_PINCTRL_FUNCTION(U4TX, RPE3R, 2),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPE3R, 4),
+			PIC32_PINCTRL_FUNCTION(SS1OUT, RPE3R, 5),
+			PIC32_PINCTRL_FUNCTION(SS3OUT, RPE3R, 7),
+			PIC32_PINCTRL_FUNCTION(SS4OUT, RPE3R, 8),
+			PIC32_PINCTRL_FUNCTION(SS5OUT, RPE3R, 9),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPE3R, 10),
+			PIC32_PINCTRL_FUNCTION(OC5, RPE3R, 11),
+			PIC32_PINCTRL_FUNCTION(OC8, RPE3R, 12),
+			PIC32_PINCTRL_FUNCTION(C1OUT, RPE3R, 14),
+			PIC32_PINCTRL_FUNCTION(REFCLKO3, RPE3R, 15)),
+	PIC32_PINCTRL_GROUP(69, E5,
+			PIC32_PINCTRL_FUNCTION(INT4, INT4R, 6),
+			PIC32_PINCTRL_FUNCTION(T5CK, T5CKR, 6),
+			PIC32_PINCTRL_FUNCTION(T7CK, T7CKR, 6),
+			PIC32_PINCTRL_FUNCTION(IC4, IC4R, 6),
+			PIC32_PINCTRL_FUNCTION(IC8, IC8R, 6),
+			PIC32_PINCTRL_FUNCTION(U3RX, U3RXR, 6),
+			PIC32_PINCTRL_FUNCTION(U4CTS, U4CTSR, 6),
+			PIC32_PINCTRL_FUNCTION(SDI2, SDI2R, 6),
+			PIC32_PINCTRL_FUNCTION(SDI4, SDI4R, 6),
+			PIC32_PINCTRL_FUNCTION(C1RX, C1RXR, 6),
+			PIC32_PINCTRL_FUNCTION(REFCLKI4, REFCLKI4R, 6),
+			PIC32_PINCTRL_FUNCTION(U1TX, RPE5R, 1),
+			PIC32_PINCTRL_FUNCTION(U2RTS, RPE5R, 2),
+			PIC32_PINCTRL_FUNCTION(U5TX, RPE5R, 3),
+			PIC32_PINCTRL_FUNCTION(U6RTS, RPE5R, 4),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPE5R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPE5R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPE5R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPE5R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPE5R, 9),
+			PIC32_PINCTRL_FUNCTION(OC4, RPE5R, 11),
+			PIC32_PINCTRL_FUNCTION(OC7, RPE5R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO1, RPE5R, 15)),
+	PIC32_PINCTRL_GROUP(72, E8,
+			PIC32_PINCTRL_FUNCTION(INT1, INT1R, 13),
+			PIC32_PINCTRL_FUNCTION(T4CK, T4CKR, 13),
+			PIC32_PINCTRL_FUNCTION(T9CK, T9CKR, 13),
+			PIC32_PINCTRL_FUNCTION(IC1, IC1R, 13),
+			PIC32_PINCTRL_FUNCTION(IC6, IC6R, 13),
+			PIC32_PINCTRL_FUNCTION(U3CTS, U3CTSR, 13),
+			PIC32_PINCTRL_FUNCTION(U4RX, U4RXR, 13),
+			PIC32_PINCTRL_FUNCTION(U6RX, U6RXR, 13),
+			PIC32_PINCTRL_FUNCTION(SS2IN, SS2INR, 13),
+			PIC32_PINCTRL_FUNCTION(SDI6, SDI6R, 13),
+			PIC32_PINCTRL_FUNCTION(OCFA, OCFAR, 13),
+			PIC32_PINCTRL_FUNCTION(REFCLKI3, REFCLKI3R, 13),
+			PIC32_PINCTRL_FUNCTION(U1RTS, RPE8R, 1),
+			PIC32_PINCTRL_FUNCTION(U2TX, RPE8R, 2),
+			PIC32_PINCTRL_FUNCTION(U5RTS, RPE8R, 3),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPE8R, 4),
+			PIC32_PINCTRL_FUNCTION(SS2OUT, RPE8R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPE8R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPE8R, 10),
+			PIC32_PINCTRL_FUNCTION(OC2, RPE8R, 11),
+			PIC32_PINCTRL_FUNCTION(OC1, RPE8R, 12),
+			PIC32_PINCTRL_FUNCTION(OC9, RPE8R, 13),
+			PIC32_PINCTRL_FUNCTION(C2TX, RPE8R, 15)),
+	PIC32_PINCTRL_GROUP(73, E9,
+			PIC32_PINCTRL_FUNCTION(INT2, INT2R, 13),
+			PIC32_PINCTRL_FUNCTION(T3CK, T3CKR, 13),
+			PIC32_PINCTRL_FUNCTION(T8CK, T8CKR, 13),
+			PIC32_PINCTRL_FUNCTION(IC2, IC2R, 13),
+			PIC32_PINCTRL_FUNCTION(IC5, IC5R, 13),
+			PIC32_PINCTRL_FUNCTION(IC9, IC9R, 13),
+			PIC32_PINCTRL_FUNCTION(U1CTS, U1CTSR, 13),
+			PIC32_PINCTRL_FUNCTION(U2RX, U2RXR, 13),
+			PIC32_PINCTRL_FUNCTION(U5CTS, U5CTSR, 13),
+			PIC32_PINCTRL_FUNCTION(SS1IN, SS1INR, 13),
+			PIC32_PINCTRL_FUNCTION(SS3IN, SS3INR, 13),
+			PIC32_PINCTRL_FUNCTION(SS4IN, SS4INR, 13),
+			PIC32_PINCTRL_FUNCTION(SS5IN, SS5INR, 13),
+			PIC32_PINCTRL_FUNCTION(C2RX, C2RXR, 13),
+			PIC32_PINCTRL_FUNCTION(U3RTS, RPE9R, 1),
+			PIC32_PINCTRL_FUNCTION(U4TX, RPE9R, 2),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPE9R, 4),
+			PIC32_PINCTRL_FUNCTION(SS1OUT, RPE9R, 5),
+			PIC32_PINCTRL_FUNCTION(SS3OUT, RPE9R, 7),
+			PIC32_PINCTRL_FUNCTION(SS4OUT, RPE9R, 8),
+			PIC32_PINCTRL_FUNCTION(SS5OUT, RPE9R, 9),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPE9R, 10),
+			PIC32_PINCTRL_FUNCTION(OC5, RPE9R, 11),
+			PIC32_PINCTRL_FUNCTION(OC8, RPE9R, 12),
+			PIC32_PINCTRL_FUNCTION(C1OUT, RPE9R, 14),
+			PIC32_PINCTRL_FUNCTION(REFCLKO3, RPE9R, 15)),
+	PIC32_PINCTRL_GROUP(80, F0,
+			PIC32_PINCTRL_FUNCTION(INT4, INT4R, 4),
+			PIC32_PINCTRL_FUNCTION(T5CK, T5CKR, 4),
+			PIC32_PINCTRL_FUNCTION(T7CK, T7CKR, 4),
+			PIC32_PINCTRL_FUNCTION(IC4, IC4R, 4),
+			PIC32_PINCTRL_FUNCTION(IC8, IC8R, 4),
+			PIC32_PINCTRL_FUNCTION(U3RX, U3RXR, 4),
+			PIC32_PINCTRL_FUNCTION(U4CTS, U4CTSR, 4),
+			PIC32_PINCTRL_FUNCTION(SDI2, SDI2R, 4),
+			PIC32_PINCTRL_FUNCTION(SDI4, SDI4R, 4),
+			PIC32_PINCTRL_FUNCTION(C1RX, C1RXR, 4),
+			PIC32_PINCTRL_FUNCTION(REFCLKI4, REFCLKI4R, 4),
+			PIC32_PINCTRL_FUNCTION(U1TX, RPF0R, 1),
+			PIC32_PINCTRL_FUNCTION(U2RTS, RPF0R, 2),
+			PIC32_PINCTRL_FUNCTION(U5TX, RPF0R, 3),
+			PIC32_PINCTRL_FUNCTION(U6RTS, RPF0R, 4),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPF0R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPF0R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPF0R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPF0R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPF0R, 9),
+			PIC32_PINCTRL_FUNCTION(OC4, RPF0R, 11),
+			PIC32_PINCTRL_FUNCTION(OC7, RPF0R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO1, RPF0R, 15)),
+	PIC32_PINCTRL_GROUP(81, F1,
+			PIC32_PINCTRL_FUNCTION(INT3, INT3R, 4),
+			PIC32_PINCTRL_FUNCTION(T2CK, T2CKR, 4),
+			PIC32_PINCTRL_FUNCTION(T6CK, T6CKR, 4),
+			PIC32_PINCTRL_FUNCTION(IC3, IC3R, 4),
+			PIC32_PINCTRL_FUNCTION(IC7, IC7R, 4),
+			PIC32_PINCTRL_FUNCTION(U1RX, U1RXR, 4),
+			PIC32_PINCTRL_FUNCTION(U2CTS, U2CTSR, 4),
+			PIC32_PINCTRL_FUNCTION(U5RX, U5RXR, 4),
+			PIC32_PINCTRL_FUNCTION(U6CTS, U6CTSR, 4),
+			PIC32_PINCTRL_FUNCTION(SDI1, SDI1R, 4),
+			PIC32_PINCTRL_FUNCTION(SDI3, SDI3R, 4),
+			PIC32_PINCTRL_FUNCTION(SDI5, SDI5R, 4),
+			PIC32_PINCTRL_FUNCTION(SS6IN, SS6INR, 4),
+			PIC32_PINCTRL_FUNCTION(REFCLKI1, REFCLKI1R, 4),
+			PIC32_PINCTRL_FUNCTION(U3TX, RPF1R, 1),
+			PIC32_PINCTRL_FUNCTION(U4RTS, RPF1R, 2),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPF1R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPF1R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPF1R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPF1R, 9),
+			PIC32_PINCTRL_FUNCTION(SS6OUT, RPF1R, 10),
+			PIC32_PINCTRL_FUNCTION(OC3, RPF1R, 11),
+			PIC32_PINCTRL_FUNCTION(OC6, RPF1R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO4, RPF1R, 13),
+			PIC32_PINCTRL_FUNCTION(C2OUT, RPF1R, 14),
+			PIC32_PINCTRL_FUNCTION(C1TX, RPF1R, 15)),
+	PIC32_PINCTRL_GROUP(82, F2,
+			PIC32_PINCTRL_FUNCTION(INT1, INT1R, 11),
+			PIC32_PINCTRL_FUNCTION(T4CK, T4CKR, 11),
+			PIC32_PINCTRL_FUNCTION(T9CK, T9CKR, 11),
+			PIC32_PINCTRL_FUNCTION(IC1, IC1R, 11),
+			PIC32_PINCTRL_FUNCTION(IC6, IC6R, 11),
+			PIC32_PINCTRL_FUNCTION(U3CTS, U3CTSR, 11),
+			PIC32_PINCTRL_FUNCTION(U4RX, U4RXR, 11),
+			PIC32_PINCTRL_FUNCTION(U6RX, U6RXR, 11),
+			PIC32_PINCTRL_FUNCTION(SS2IN, SS2INR, 11),
+			PIC32_PINCTRL_FUNCTION(SDI6, SDI6R, 11),
+			PIC32_PINCTRL_FUNCTION(OCFA, OCFAR, 11),
+			PIC32_PINCTRL_FUNCTION(REFCLKI3, REFCLKI3R, 11),
+			PIC32_PINCTRL_FUNCTION(U1RTS, RPF2R, 1),
+			PIC32_PINCTRL_FUNCTION(U2TX, RPF2R, 2),
+			PIC32_PINCTRL_FUNCTION(U5RTS, RPF2R, 3),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPF2R, 4),
+			PIC32_PINCTRL_FUNCTION(SS2OUT, RPF2R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPF2R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPF2R, 10),
+			PIC32_PINCTRL_FUNCTION(OC2, RPF2R, 11),
+			PIC32_PINCTRL_FUNCTION(OC1, RPF2R, 12),
+			PIC32_PINCTRL_FUNCTION(OC9, RPF2R, 13),
+			PIC32_PINCTRL_FUNCTION(C2TX, RPF2R, 15)),
+	PIC32_PINCTRL_GROUP(83, F3,
+			PIC32_PINCTRL_FUNCTION(INT1, INT1R, 8),
+			PIC32_PINCTRL_FUNCTION(T4CK, T4CKR, 8),
+			PIC32_PINCTRL_FUNCTION(T9CK, T9CKR, 8),
+			PIC32_PINCTRL_FUNCTION(IC1, IC1R, 8),
+			PIC32_PINCTRL_FUNCTION(IC6, IC6R, 8),
+			PIC32_PINCTRL_FUNCTION(U3CTS, U3CTSR, 8),
+			PIC32_PINCTRL_FUNCTION(U4RX, U4RXR, 8),
+			PIC32_PINCTRL_FUNCTION(U6RX, U6RXR, 8),
+			PIC32_PINCTRL_FUNCTION(SS2IN, SS2INR, 8),
+			PIC32_PINCTRL_FUNCTION(SDI6, SDI6R, 8),
+			PIC32_PINCTRL_FUNCTION(OCFA, OCFAR, 8),
+			PIC32_PINCTRL_FUNCTION(REFCLKI3, REFCLKI3R, 8),
+			PIC32_PINCTRL_FUNCTION(U1RTS, RPF3R, 1),
+			PIC32_PINCTRL_FUNCTION(U2TX, RPF3R, 2),
+			PIC32_PINCTRL_FUNCTION(U5RTS, RPF3R, 3),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPF3R, 4),
+			PIC32_PINCTRL_FUNCTION(SS2OUT, RPF3R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPF3R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPF3R, 10),
+			PIC32_PINCTRL_FUNCTION(OC2, RPF3R, 11),
+			PIC32_PINCTRL_FUNCTION(OC1, RPF3R, 12),
+			PIC32_PINCTRL_FUNCTION(OC9, RPF3R, 13),
+			PIC32_PINCTRL_FUNCTION(C2TX, RPF3R, 15)),
+	PIC32_PINCTRL_GROUP(84, F4,
+			PIC32_PINCTRL_FUNCTION(INT3, INT3R, 2),
+			PIC32_PINCTRL_FUNCTION(T2CK, T2CKR, 2),
+			PIC32_PINCTRL_FUNCTION(T6CK, T6CKR, 2),
+			PIC32_PINCTRL_FUNCTION(IC3, IC3R, 2),
+			PIC32_PINCTRL_FUNCTION(IC7, IC7R, 2),
+			PIC32_PINCTRL_FUNCTION(U1RX, U1RXR, 2),
+			PIC32_PINCTRL_FUNCTION(U2CTS, U2CTSR, 2),
+			PIC32_PINCTRL_FUNCTION(U5RX, U5RXR, 2),
+			PIC32_PINCTRL_FUNCTION(U6CTS, U6CTSR, 2),
+			PIC32_PINCTRL_FUNCTION(SDI1, SDI1R, 2),
+			PIC32_PINCTRL_FUNCTION(SDI3, SDI3R, 2),
+			PIC32_PINCTRL_FUNCTION(SDI5, SDI5R, 2),
+			PIC32_PINCTRL_FUNCTION(SS6IN, SS6INR, 2),
+			PIC32_PINCTRL_FUNCTION(REFCLKI1, REFCLKI1R, 2),
+			PIC32_PINCTRL_FUNCTION(U3TX, RPF4R, 1),
+			PIC32_PINCTRL_FUNCTION(U4RTS, RPF4R, 2),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPF4R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPF4R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPF4R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPF4R, 9),
+			PIC32_PINCTRL_FUNCTION(SS6OUT, RPF4R, 10),
+			PIC32_PINCTRL_FUNCTION(OC3, RPF4R, 11),
+			PIC32_PINCTRL_FUNCTION(OC6, RPF4R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO4, RPF4R, 13),
+			PIC32_PINCTRL_FUNCTION(C2OUT, RPF4R, 14),
+			PIC32_PINCTRL_FUNCTION(C1TX, RPF4R, 15)),
+	PIC32_PINCTRL_GROUP(85, F5,
+			PIC32_PINCTRL_FUNCTION(INT4, INT4R, 2),
+			PIC32_PINCTRL_FUNCTION(T5CK, T5CKR, 2),
+			PIC32_PINCTRL_FUNCTION(T7CK, T7CKR, 2),
+			PIC32_PINCTRL_FUNCTION(IC4, IC4R, 2),
+			PIC32_PINCTRL_FUNCTION(IC8, IC8R, 2),
+			PIC32_PINCTRL_FUNCTION(U3RX, U3RXR, 2),
+			PIC32_PINCTRL_FUNCTION(U4CTS, U4CTSR, 2),
+			PIC32_PINCTRL_FUNCTION(SDI2, SDI2R, 2),
+			PIC32_PINCTRL_FUNCTION(SDI4, SDI4R, 2),
+			PIC32_PINCTRL_FUNCTION(C1RX, C1RXR, 2),
+			PIC32_PINCTRL_FUNCTION(REFCLKI4, REFCLKI4R, 2),
+			PIC32_PINCTRL_FUNCTION(U1TX, RPF5R, 1),
+			PIC32_PINCTRL_FUNCTION(U2RTS, RPF5R, 2),
+			PIC32_PINCTRL_FUNCTION(U5TX, RPF5R, 3),
+			PIC32_PINCTRL_FUNCTION(U6RTS, RPF5R, 4),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPF5R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPF5R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPF5R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPF5R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPF5R, 9),
+			PIC32_PINCTRL_FUNCTION(OC4, RPF5R, 11),
+			PIC32_PINCTRL_FUNCTION(OC7, RPF5R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO1, RPF5R, 15)),
+	PIC32_PINCTRL_GROUP(88, F8,
+			PIC32_PINCTRL_FUNCTION(INT2, INT2R, 11),
+			PIC32_PINCTRL_FUNCTION(T3CK, T3CKR, 11),
+			PIC32_PINCTRL_FUNCTION(T8CK, T8CKR, 11),
+			PIC32_PINCTRL_FUNCTION(IC2, IC2R, 11),
+			PIC32_PINCTRL_FUNCTION(IC5, IC5R, 11),
+			PIC32_PINCTRL_FUNCTION(IC9, IC9R, 11),
+			PIC32_PINCTRL_FUNCTION(U1CTS, U1CTSR, 11),
+			PIC32_PINCTRL_FUNCTION(U2RX, U2RXR, 11),
+			PIC32_PINCTRL_FUNCTION(U5CTS, U5CTSR, 11),
+			PIC32_PINCTRL_FUNCTION(SS1IN, SS1INR, 11),
+			PIC32_PINCTRL_FUNCTION(SS3IN, SS3INR, 11),
+			PIC32_PINCTRL_FUNCTION(SS4IN, SS4INR, 11),
+			PIC32_PINCTRL_FUNCTION(SS5IN, SS5INR, 11),
+			PIC32_PINCTRL_FUNCTION(C2RX, C2RXR, 11),
+			PIC32_PINCTRL_FUNCTION(U3RTS, RPF8R, 1),
+			PIC32_PINCTRL_FUNCTION(U4TX, RPF8R, 2),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPF8R, 4),
+			PIC32_PINCTRL_FUNCTION(SS1OUT, RPF8R, 5),
+			PIC32_PINCTRL_FUNCTION(SS3OUT, RPF8R, 7),
+			PIC32_PINCTRL_FUNCTION(SS4OUT, RPF8R, 8),
+			PIC32_PINCTRL_FUNCTION(SS5OUT, RPF8R, 9),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPF8R, 10),
+			PIC32_PINCTRL_FUNCTION(OC5, RPF8R, 11),
+			PIC32_PINCTRL_FUNCTION(OC8, RPF8R, 12),
+			PIC32_PINCTRL_FUNCTION(C1OUT, RPF8R, 14),
+			PIC32_PINCTRL_FUNCTION(REFCLKO3, RPF8R, 15)),
+	PIC32_PINCTRL_GROUP(92, F12,
+			PIC32_PINCTRL_FUNCTION(INT2, INT2R, 9),
+			PIC32_PINCTRL_FUNCTION(T3CK, T3CKR, 9),
+			PIC32_PINCTRL_FUNCTION(T8CK, T8CKR, 9),
+			PIC32_PINCTRL_FUNCTION(IC2, IC2R, 9),
+			PIC32_PINCTRL_FUNCTION(IC5, IC5R, 9),
+			PIC32_PINCTRL_FUNCTION(IC9, IC9R, 9),
+			PIC32_PINCTRL_FUNCTION(U1CTS, U1CTSR, 9),
+			PIC32_PINCTRL_FUNCTION(U2RX, U2RXR, 9),
+			PIC32_PINCTRL_FUNCTION(U5CTS, U5CTSR, 9),
+			PIC32_PINCTRL_FUNCTION(SS1IN, SS1INR, 9),
+			PIC32_PINCTRL_FUNCTION(SS3IN, SS3INR, 9),
+			PIC32_PINCTRL_FUNCTION(SS4IN, SS4INR, 9),
+			PIC32_PINCTRL_FUNCTION(SS5IN, SS5INR, 9),
+			PIC32_PINCTRL_FUNCTION(C2RX, C2RXR, 9),
+			PIC32_PINCTRL_FUNCTION(U3RTS, RPF12R, 1),
+			PIC32_PINCTRL_FUNCTION(U4TX, RPF12R, 2),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPF12R, 4),
+			PIC32_PINCTRL_FUNCTION(SS1OUT, RPF12R, 5),
+			PIC32_PINCTRL_FUNCTION(SS3OUT, RPF12R, 7),
+			PIC32_PINCTRL_FUNCTION(SS4OUT, RPF12R, 8),
+			PIC32_PINCTRL_FUNCTION(SS5OUT, RPF12R, 9),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPF12R, 10),
+			PIC32_PINCTRL_FUNCTION(OC5, RPF12R, 11),
+			PIC32_PINCTRL_FUNCTION(OC8, RPF12R, 12),
+			PIC32_PINCTRL_FUNCTION(C1OUT, RPF12R, 14),
+			PIC32_PINCTRL_FUNCTION(REFCLKO3, RPF12R, 15)),
+	PIC32_PINCTRL_GROUP(93, F13,
+			PIC32_PINCTRL_FUNCTION(INT1, INT1R, 9),
+			PIC32_PINCTRL_FUNCTION(T4CK, T4CKR, 9),
+			PIC32_PINCTRL_FUNCTION(T9CK, T9CKR, 9),
+			PIC32_PINCTRL_FUNCTION(IC1, IC1R, 9),
+			PIC32_PINCTRL_FUNCTION(IC6, IC6R, 9),
+			PIC32_PINCTRL_FUNCTION(U3CTS, U3CTSR, 9),
+			PIC32_PINCTRL_FUNCTION(U4RX, U4RXR, 9),
+			PIC32_PINCTRL_FUNCTION(U6RX, U6RXR, 9),
+			PIC32_PINCTRL_FUNCTION(SS2IN, SS2INR, 9),
+			PIC32_PINCTRL_FUNCTION(SDI6, SDI6R, 9),
+			PIC32_PINCTRL_FUNCTION(OCFA, OCFAR, 9),
+			PIC32_PINCTRL_FUNCTION(REFCLKI3, REFCLKI3R, 9),
+			PIC32_PINCTRL_FUNCTION(U1RTS, RPF13R, 1),
+			PIC32_PINCTRL_FUNCTION(U2TX, RPF13R, 2),
+			PIC32_PINCTRL_FUNCTION(U5RTS, RPF13R, 3),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPF13R, 4),
+			PIC32_PINCTRL_FUNCTION(SS2OUT, RPF13R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPF13R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPF13R, 10),
+			PIC32_PINCTRL_FUNCTION(OC2, RPF13R, 11),
+			PIC32_PINCTRL_FUNCTION(OC1, RPF13R, 12),
+			PIC32_PINCTRL_FUNCTION(OC9, RPF13R, 13),
+			PIC32_PINCTRL_FUNCTION(C2TX, RPF13R, 15)),
+	PIC32_PINCTRL_GROUP(96, G0,
+			PIC32_PINCTRL_FUNCTION(INT4, INT4R, 12),
+			PIC32_PINCTRL_FUNCTION(T5CK, T5CKR, 12),
+			PIC32_PINCTRL_FUNCTION(T7CK, T7CKR, 12),
+			PIC32_PINCTRL_FUNCTION(IC4, IC4R, 12),
+			PIC32_PINCTRL_FUNCTION(IC8, IC8R, 12),
+			PIC32_PINCTRL_FUNCTION(U3RX, U3RXR, 12),
+			PIC32_PINCTRL_FUNCTION(U4CTS, U4CTSR, 12),
+			PIC32_PINCTRL_FUNCTION(SDI2, SDI2R, 12),
+			PIC32_PINCTRL_FUNCTION(SDI4, SDI4R, 12),
+			PIC32_PINCTRL_FUNCTION(C1RX, C1RXR, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKI4, REFCLKI4R, 12),
+			PIC32_PINCTRL_FUNCTION(U1TX, RPG0R, 1),
+			PIC32_PINCTRL_FUNCTION(U2RTS, RPG0R, 2),
+			PIC32_PINCTRL_FUNCTION(U5TX, RPG0R, 3),
+			PIC32_PINCTRL_FUNCTION(U6RTS, RPG0R, 4),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPG0R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPG0R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPG0R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPG0R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPG0R, 9),
+			PIC32_PINCTRL_FUNCTION(OC4, RPG0R, 11),
+			PIC32_PINCTRL_FUNCTION(OC7, RPG0R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO1, RPG0R, 15)),
+	PIC32_PINCTRL_GROUP(97, G1,
+			PIC32_PINCTRL_FUNCTION(INT3, INT3R, 12),
+			PIC32_PINCTRL_FUNCTION(T2CK, T2CKR, 12),
+			PIC32_PINCTRL_FUNCTION(T6CK, T6CKR, 12),
+			PIC32_PINCTRL_FUNCTION(IC3, IC3R, 12),
+			PIC32_PINCTRL_FUNCTION(IC7, IC7R, 12),
+			PIC32_PINCTRL_FUNCTION(U1RX, U1RXR, 12),
+			PIC32_PINCTRL_FUNCTION(U2CTS, U2CTSR, 12),
+			PIC32_PINCTRL_FUNCTION(U5RX, U5RXR, 12),
+			PIC32_PINCTRL_FUNCTION(U6CTS, U6CTSR, 12),
+			PIC32_PINCTRL_FUNCTION(SDI1, SDI1R, 12),
+			PIC32_PINCTRL_FUNCTION(SDI3, SDI3R, 12),
+			PIC32_PINCTRL_FUNCTION(SDI5, SDI5R, 12),
+			PIC32_PINCTRL_FUNCTION(SS6IN, SS6INR, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKI1, REFCLKI1R, 12),
+			PIC32_PINCTRL_FUNCTION(U3TX, RPG1R, 1),
+			PIC32_PINCTRL_FUNCTION(U4RTS, RPG1R, 2),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPG1R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPG1R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPG1R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPG1R, 9),
+			PIC32_PINCTRL_FUNCTION(SS6OUT, RPG1R, 10),
+			PIC32_PINCTRL_FUNCTION(OC3, RPG1R, 11),
+			PIC32_PINCTRL_FUNCTION(OC6, RPG1R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO4, RPG1R, 13),
+			PIC32_PINCTRL_FUNCTION(C2OUT, RPG1R, 14),
+			PIC32_PINCTRL_FUNCTION(C1TX, RPG1R, 15)),
+	PIC32_PINCTRL_GROUP(102, G6,
+			PIC32_PINCTRL_FUNCTION(INT2, INT2R, 1),
+			PIC32_PINCTRL_FUNCTION(T3CK, T3CKR, 1),
+			PIC32_PINCTRL_FUNCTION(T8CK, T8CKR, 1),
+			PIC32_PINCTRL_FUNCTION(IC2, IC2R, 1),
+			PIC32_PINCTRL_FUNCTION(IC5, IC5R, 1),
+			PIC32_PINCTRL_FUNCTION(IC9, IC9R, 1),
+			PIC32_PINCTRL_FUNCTION(U1CTS, U1CTSR, 1),
+			PIC32_PINCTRL_FUNCTION(U2RX, U2RXR, 1),
+			PIC32_PINCTRL_FUNCTION(U5CTS, U5CTSR, 1),
+			PIC32_PINCTRL_FUNCTION(SS1IN, SS1INR, 1),
+			PIC32_PINCTRL_FUNCTION(SS3IN, SS3INR, 1),
+			PIC32_PINCTRL_FUNCTION(SS4IN, SS4INR, 1),
+			PIC32_PINCTRL_FUNCTION(SS5IN, SS5INR, 1),
+			PIC32_PINCTRL_FUNCTION(C2RX, C2RXR, 1),
+			PIC32_PINCTRL_FUNCTION(U3RTS, RPG6R, 1),
+			PIC32_PINCTRL_FUNCTION(U4TX, RPG6R, 2),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPG6R, 4),
+			PIC32_PINCTRL_FUNCTION(SS1OUT, RPG6R, 5),
+			PIC32_PINCTRL_FUNCTION(SS3OUT, RPG6R, 7),
+			PIC32_PINCTRL_FUNCTION(SS4OUT, RPG6R, 8),
+			PIC32_PINCTRL_FUNCTION(SS5OUT, RPG6R, 9),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPG6R, 10),
+			PIC32_PINCTRL_FUNCTION(OC5, RPG6R, 11),
+			PIC32_PINCTRL_FUNCTION(OC8, RPG6R, 12),
+			PIC32_PINCTRL_FUNCTION(C1OUT, RPG6R, 14),
+			PIC32_PINCTRL_FUNCTION(REFCLKO3, RPG6R, 15)),
+	PIC32_PINCTRL_GROUP(103, G7,
+			PIC32_PINCTRL_FUNCTION(INT4, INT4R, 1),
+			PIC32_PINCTRL_FUNCTION(T5CK, T5CKR, 1),
+			PIC32_PINCTRL_FUNCTION(T7CK, T7CKR, 1),
+			PIC32_PINCTRL_FUNCTION(IC4, IC4R, 1),
+			PIC32_PINCTRL_FUNCTION(IC8, IC8R, 1),
+			PIC32_PINCTRL_FUNCTION(U3RX, U3RXR, 1),
+			PIC32_PINCTRL_FUNCTION(U4CTS, U4CTSR, 1),
+			PIC32_PINCTRL_FUNCTION(SDI2, SDI2R, 1),
+			PIC32_PINCTRL_FUNCTION(SDI4, SDI4R, 1),
+			PIC32_PINCTRL_FUNCTION(C1RX, C1RXR, 1),
+			PIC32_PINCTRL_FUNCTION(REFCLKI4, REFCLKI4R, 1),
+			PIC32_PINCTRL_FUNCTION(U1TX, RPG7R, 1),
+			PIC32_PINCTRL_FUNCTION(U2RTS, RPG7R, 2),
+			PIC32_PINCTRL_FUNCTION(U5TX, RPG7R, 3),
+			PIC32_PINCTRL_FUNCTION(U6RTS, RPG7R, 4),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPG7R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPG7R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPG7R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPG7R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPG7R, 9),
+			PIC32_PINCTRL_FUNCTION(OC4, RPG7R, 11),
+			PIC32_PINCTRL_FUNCTION(OC7, RPG7R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO1, RPG7R, 15)),
+	PIC32_PINCTRL_GROUP(104, G8,
+			PIC32_PINCTRL_FUNCTION(INT3, INT3R, 1),
+			PIC32_PINCTRL_FUNCTION(T2CK, T2CKR, 1),
+			PIC32_PINCTRL_FUNCTION(T6CK, T6CKR, 1),
+			PIC32_PINCTRL_FUNCTION(IC3, IC3R, 1),
+			PIC32_PINCTRL_FUNCTION(IC7, IC7R, 1),
+			PIC32_PINCTRL_FUNCTION(U1RX, U1RXR, 1),
+			PIC32_PINCTRL_FUNCTION(U2CTS, U2CTSR, 1),
+			PIC32_PINCTRL_FUNCTION(U5RX, U5RXR, 1),
+			PIC32_PINCTRL_FUNCTION(U6CTS, U6CTSR, 1),
+			PIC32_PINCTRL_FUNCTION(SDI1, SDI1R, 1),
+			PIC32_PINCTRL_FUNCTION(SDI3, SDI3R, 1),
+			PIC32_PINCTRL_FUNCTION(SDI5, SDI5R, 1),
+			PIC32_PINCTRL_FUNCTION(SS6IN, SS6INR, 1),
+			PIC32_PINCTRL_FUNCTION(REFCLKI1, REFCLKI1R, 1),
+			PIC32_PINCTRL_FUNCTION(U3TX, RPG8R, 1),
+			PIC32_PINCTRL_FUNCTION(U4RTS, RPG8R, 2),
+			PIC32_PINCTRL_FUNCTION(SDO1, RPG8R, 5),
+			PIC32_PINCTRL_FUNCTION(SDO2, RPG8R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO3, RPG8R, 7),
+			PIC32_PINCTRL_FUNCTION(SDO5, RPG8R, 9),
+			PIC32_PINCTRL_FUNCTION(SS6OUT, RPG8R, 10),
+			PIC32_PINCTRL_FUNCTION(OC3, RPG8R, 11),
+			PIC32_PINCTRL_FUNCTION(OC6, RPG8R, 12),
+			PIC32_PINCTRL_FUNCTION(REFCLKO4, RPG8R, 13),
+			PIC32_PINCTRL_FUNCTION(C2OUT, RPG8R, 14),
+			PIC32_PINCTRL_FUNCTION(C1TX, RPG8R, 15)),
+	PIC32_PINCTRL_GROUP(105, G9,
+			PIC32_PINCTRL_FUNCTION(INT1, INT1R, 1),
+			PIC32_PINCTRL_FUNCTION(T4CK, T4CKR, 1),
+			PIC32_PINCTRL_FUNCTION(T9CK, T9CKR, 1),
+			PIC32_PINCTRL_FUNCTION(IC1, IC1R, 1),
+			PIC32_PINCTRL_FUNCTION(IC6, IC6R, 1),
+			PIC32_PINCTRL_FUNCTION(U3CTS, U3CTSR, 1),
+			PIC32_PINCTRL_FUNCTION(U4RX, U4RXR, 1),
+			PIC32_PINCTRL_FUNCTION(U6RX, U6RXR, 1),
+			PIC32_PINCTRL_FUNCTION(SS2IN, SS2INR, 1),
+			PIC32_PINCTRL_FUNCTION(SDI6, SDI6R, 1),
+			PIC32_PINCTRL_FUNCTION(OCFA, OCFAR, 1),
+			PIC32_PINCTRL_FUNCTION(REFCLKI3, REFCLKI3R, 1),
+			PIC32_PINCTRL_FUNCTION(U1RTS, RPG9R, 1),
+			PIC32_PINCTRL_FUNCTION(U2TX, RPG9R, 2),
+			PIC32_PINCTRL_FUNCTION(U5RTS, RPG9R, 3),
+			PIC32_PINCTRL_FUNCTION(U6TX, RPG9R, 4),
+			PIC32_PINCTRL_FUNCTION(SS2OUT, RPG9R, 6),
+			PIC32_PINCTRL_FUNCTION(SDO4, RPG9R, 8),
+			PIC32_PINCTRL_FUNCTION(SDO6, RPG9R, 10),
+			PIC32_PINCTRL_FUNCTION(OC2, RPG9R, 11),
+			PIC32_PINCTRL_FUNCTION(OC1, RPG9R, 12),
+			PIC32_PINCTRL_FUNCTION(OC9, RPG9R, 13),
+			PIC32_PINCTRL_FUNCTION(C2TX, RPG9R, 15)),
+};
+
+static inline struct pic32_gpio_bank *irqd_to_bank(struct irq_data *d)
+{
+	return gpiochip_get_data(irq_data_get_irq_chip_data(d));
+}
+
+static inline struct pic32_gpio_bank *pctl_to_bank(struct pic32_pinctrl *pctl,
+						unsigned pin)
+{
+	return &pctl->gpio_banks[pin / PINS_PER_BANK];
+}
+
+static int pic32_pinctrl_get_groups_count(struct pinctrl_dev *pctldev)
+{
+	struct pic32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+
+	return pctl->ngroups;
+}
+
+static const char *pic32_pinctrl_get_group_name(struct pinctrl_dev *pctldev,
+						    unsigned group)
+{
+	struct pic32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+
+	return pctl->groups[group].name;
+}
+
+static int pic32_pinctrl_get_group_pins(struct pinctrl_dev *pctldev,
+					    unsigned group,
+					    const unsigned **pins,
+					    unsigned *num_pins)
+{
+	struct pic32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+
+	*pins = &pctl->groups[group].pin;
+	*num_pins = 1;
+
+	return 0;
+}
+
+static const struct pinctrl_ops pic32_pinctrl_ops = {
+	.get_groups_count = pic32_pinctrl_get_groups_count,
+	.get_group_name = pic32_pinctrl_get_group_name,
+	.get_group_pins = pic32_pinctrl_get_group_pins,
+	.dt_node_to_map = pinconf_generic_dt_node_to_map_pin,
+	.dt_free_map = pinctrl_utils_dt_free_map,
+};
+
+static int pic32_pinmux_get_functions_count(struct pinctrl_dev *pctldev)
+{
+	struct pic32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+
+	return pctl->nfunctions;
+}
+
+static const char *
+pic32_pinmux_get_function_name(struct pinctrl_dev *pctldev, unsigned func)
+{
+	struct pic32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+
+	return pctl->functions[func].name;
+}
+
+static int pic32_pinmux_get_function_groups(struct pinctrl_dev *pctldev,
+						unsigned func,
+						const char * const **groups,
+						unsigned * const num_groups)
+{
+	struct pic32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+
+	*groups = pctl->functions[func].groups;
+	*num_groups = pctl->functions[func].ngroups;
+
+	return 0;
+}
+
+static int pic32_pinmux_enable(struct pinctrl_dev *pctldev,
+				   unsigned func, unsigned group)
+{
+	struct pic32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+	const struct pic32_pin_group *pg = &pctl->groups[group];
+	const struct pic32_function *pf = &pctl->functions[func];
+	const char *fname = pf->name;
+	struct pic32_desc_function *functions = pg->functions;
+
+	while (functions->name) {
+		if (!strcmp(functions->name, fname)) {
+			dev_dbg(pctl->dev,
+				"setting function %s reg 0x%x = %d\n",
+				fname, functions->muxreg, functions->muxval);
+
+			writel(functions->muxval, pctl->reg_base + functions->muxreg);
+
+			return 0;
+		}
+
+		functions++;
+	}
+
+	dev_err(pctl->dev, "cannot mux pin %u to function %u\n", group, func);
+
+	return -EINVAL;
+}
+
+static int pic32_gpio_request_enable(struct pinctrl_dev *pctldev,
+				     struct pinctrl_gpio_range *range,
+				     unsigned offset)
+{
+	struct pic32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+	struct pic32_gpio_bank *bank = gpiochip_get_data(range->gc);
+	u32 mask = BIT(offset - bank->gpio_chip.base);
+
+	dev_dbg(pctl->dev, "requesting gpio %d in bank %d with mask 0x%x\n",
+		offset, bank->gpio_chip.base, mask);
+
+	writel(mask, bank->reg_base + PIC32_CLR(ANSEL_REG));
+
+	return 0;
+}
+
+static int pic32_gpio_direction_input(struct gpio_chip *chip,
+					  unsigned offset)
+{
+	struct pic32_gpio_bank *bank = gpiochip_get_data(chip);
+	u32 mask = BIT(offset);
+
+	writel(mask, bank->reg_base + PIC32_SET(TRIS_REG));
+
+	return 0;
+}
+
+static int pic32_gpio_get(struct gpio_chip *chip, unsigned offset)
+{
+	struct pic32_gpio_bank *bank = gpiochip_get_data(chip);
+
+	return !!(readl(bank->reg_base + PORT_REG) & BIT(offset));
+}
+
+static void pic32_gpio_set(struct gpio_chip *chip, unsigned offset,
+			       int value)
+{
+	struct pic32_gpio_bank *bank = gpiochip_get_data(chip);
+	u32 mask = BIT(offset);
+
+	if (value)
+		writel(mask, bank->reg_base + PIC32_SET(PORT_REG));
+	else
+		writel(mask, bank->reg_base + PIC32_CLR(PORT_REG));
+}
+
+static int pic32_gpio_direction_output(struct gpio_chip *chip,
+					   unsigned offset, int value)
+{
+	struct pic32_gpio_bank *bank = gpiochip_get_data(chip);
+	u32 mask = BIT(offset);
+
+	pic32_gpio_set(chip, offset, value);
+	writel(mask, bank->reg_base + PIC32_CLR(TRIS_REG));
+
+	return 0;
+}
+
+static int pic32_gpio_set_direction(struct pinctrl_dev *pctldev,
+					      struct pinctrl_gpio_range *range,
+					      unsigned offset, bool input)
+{
+	struct gpio_chip *chip = range->gc;
+
+	if (input)
+		pic32_gpio_direction_input(chip, offset);
+	else
+		pic32_gpio_direction_output(chip, offset, 0);
+
+	return 0;
+}
+
+static const struct pinmux_ops pic32_pinmux_ops = {
+	.get_functions_count = pic32_pinmux_get_functions_count,
+	.get_function_name = pic32_pinmux_get_function_name,
+	.get_function_groups = pic32_pinmux_get_function_groups,
+	.set_mux = pic32_pinmux_enable,
+	.gpio_request_enable = pic32_gpio_request_enable,
+	.gpio_set_direction = pic32_gpio_set_direction,
+};
+
+static int pic32_pinconf_get(struct pinctrl_dev *pctldev, unsigned pin,
+				 unsigned long *config)
+{
+	struct pic32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+	struct pic32_gpio_bank *bank = pctl_to_bank(pctl, pin);
+	unsigned param = pinconf_to_config_param(*config);
+	u32 mask = BIT(pin - bank->gpio_chip.base);
+	u32 arg;
+
+	switch (param) {
+	case PIN_CONFIG_BIAS_PULL_UP:
+		arg = !!(readl(bank->reg_base + CNPU_REG) & mask);
+		break;
+	case PIN_CONFIG_BIAS_PULL_DOWN:
+		arg = !!(readl(bank->reg_base + CNPD_REG) & mask);
+		break;
+	case PIN_CONFIG_MICROCHIP_DIGITAL:
+		arg = !(readl(bank->reg_base + ANSEL_REG) & mask);
+		break;
+	case PIN_CONFIG_MICROCHIP_ANALOG:
+		arg = !!(readl(bank->reg_base + ANSEL_REG) & mask);
+		break;
+	case PIN_CONFIG_DRIVE_OPEN_DRAIN:
+		arg = !!(readl(bank->reg_base + ODCU_REG) & mask);
+		break;
+	case PIN_CONFIG_INPUT_ENABLE:
+		arg = !!(readl(bank->reg_base + TRIS_REG) & mask);
+		break;
+	case PIN_CONFIG_OUTPUT:
+		arg = !(readl(bank->reg_base + TRIS_REG) & mask);
+		break;
+	default:
+		dev_err(pctl->dev, "Property %u not supported\n", param);
+		return -ENOTSUPP;
+	}
+
+	*config = pinconf_to_config_packed(param, arg);
+
+	return 0;
+}
+
+static int pic32_pinconf_set(struct pinctrl_dev *pctldev, unsigned pin,
+				 unsigned long *configs, unsigned num_configs)
+{
+	struct pic32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+	struct pic32_gpio_bank *bank = pctl_to_bank(pctl, pin);
+	unsigned param;
+	u32 arg;
+	unsigned int i;
+	u32 offset = pin - bank->gpio_chip.base;
+	u32 mask = BIT(offset);
+
+	dev_dbg(pctl->dev, "setting pin %d bank %d mask 0x%x\n",
+		pin, bank->gpio_chip.base, mask);
+
+	for (i = 0; i < num_configs; i++) {
+		param = pinconf_to_config_param(configs[i]);
+		arg = pinconf_to_config_argument(configs[i]);
+
+		switch (param) {
+		case PIN_CONFIG_BIAS_PULL_UP:
+			dev_dbg(pctl->dev, "   pullup\n");
+			writel(mask, bank->reg_base +PIC32_SET(CNPU_REG));
+			break;
+		case PIN_CONFIG_BIAS_PULL_DOWN:
+			dev_dbg(pctl->dev, "   pulldown\n");
+			writel(mask, bank->reg_base + PIC32_SET(CNPD_REG));
+			break;
+		case PIN_CONFIG_MICROCHIP_DIGITAL:
+			dev_dbg(pctl->dev, "   digital\n");
+			writel(mask, bank->reg_base + PIC32_CLR(ANSEL_REG));
+			break;
+		case PIN_CONFIG_MICROCHIP_ANALOG:
+			dev_dbg(pctl->dev, "   analog\n");
+			writel(mask, bank->reg_base + PIC32_SET(ANSEL_REG));
+			break;
+		case PIN_CONFIG_DRIVE_OPEN_DRAIN:
+			dev_dbg(pctl->dev, "   opendrain\n");
+			writel(mask, bank->reg_base + PIC32_SET(ODCU_REG));
+			break;
+		case PIN_CONFIG_INPUT_ENABLE:
+			pic32_gpio_direction_input(&bank->gpio_chip, offset);
+			break;
+		case PIN_CONFIG_OUTPUT:
+			pic32_gpio_direction_output(&bank->gpio_chip,
+						    offset, arg);
+			break;
+		default:
+			dev_err(pctl->dev, "Property %u not supported\n",
+				param);
+			return -ENOTSUPP;
+		}
+	}
+
+	return 0;
+}
+
+static const struct pinconf_ops pic32_pinconf_ops = {
+	.pin_config_get = pic32_pinconf_get,
+	.pin_config_set = pic32_pinconf_set,
+	.is_generic = true,
+};
+
+static struct pinctrl_desc pic32_pinctrl_desc = {
+	.name = "pic32-pinctrl",
+	.pctlops = &pic32_pinctrl_ops,
+	.pmxops = &pic32_pinmux_ops,
+	.confops = &pic32_pinconf_ops,
+	.owner = THIS_MODULE,
+};
+
+static int pic32_gpio_get_direction(struct gpio_chip *chip, unsigned offset)
+{
+	struct pic32_gpio_bank *bank = gpiochip_get_data(chip);
+
+	return !!(readl(bank->reg_base + TRIS_REG) & BIT(offset));
+}
+
+static void pic32_gpio_irq_ack(struct irq_data *data)
+{
+	struct pic32_gpio_bank *bank = irqd_to_bank(data);
+
+	writel(0, bank->reg_base + CNF_REG);
+}
+
+static void pic32_gpio_irq_mask(struct irq_data *data)
+{
+	struct pic32_gpio_bank *bank = irqd_to_bank(data);
+
+	writel(BIT(PIC32_CNCON_ON), bank->reg_base + PIC32_CLR(CNCON_REG));
+}
+
+static void pic32_gpio_irq_unmask(struct irq_data *data)
+{
+	struct pic32_gpio_bank *bank = irqd_to_bank(data);
+
+	writel(BIT(PIC32_CNCON_ON), bank->reg_base + PIC32_SET(CNCON_REG));
+}
+
+static unsigned int pic32_gpio_irq_startup(struct irq_data *data)
+{
+	struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
+
+	pic32_gpio_direction_input(chip, data->hwirq);
+	pic32_gpio_irq_unmask(data);
+
+	return 0;
+}
+
+static int pic32_gpio_irq_set_type(struct irq_data *data, unsigned int type)
+{
+	struct pic32_gpio_bank *bank = irqd_to_bank(data);
+	u32 mask = BIT(data->hwirq);
+
+	switch (type & IRQ_TYPE_SENSE_MASK) {
+	case IRQ_TYPE_EDGE_RISING:
+		/* enable RISE */
+		writel(mask, bank->reg_base + PIC32_SET(CNEN_REG));
+		/* disable FALL */
+		writel(mask, bank->reg_base + PIC32_CLR(CNNE_REG));
+		/* enable EDGE */
+		writel(BIT(PIC32_CNCON_EDGE), bank->reg_base + PIC32_SET(CNCON_REG));
+		break;
+	case IRQ_TYPE_EDGE_FALLING:
+		/* disable RISE */
+		writel(mask, bank->reg_base + PIC32_CLR(CNEN_REG));
+		/* enable FALL */
+		writel(mask, bank->reg_base + PIC32_SET(CNNE_REG));
+		/* enable EDGE */
+		writel(BIT(PIC32_CNCON_EDGE), bank->reg_base + PIC32_SET(CNCON_REG));
+		break;
+	case IRQ_TYPE_EDGE_BOTH:
+		/* enable RISE */
+		writel(mask, bank->reg_base + PIC32_SET(CNEN_REG));
+		/* enable FALL */
+		writel(mask, bank->reg_base + PIC32_SET(CNNE_REG));
+		/* enable EDGE */
+		writel(BIT(PIC32_CNCON_EDGE), bank->reg_base + PIC32_SET(CNCON_REG));
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	irq_set_handler_locked(data, handle_edge_irq);
+
+	return 0;
+}
+
+static u32 pic32_gpio_get_pending(struct gpio_chip *gc, unsigned long status)
+{
+	struct pic32_gpio_bank *bank = gpiochip_get_data(gc);
+	u32 pending = 0;
+	u32 cnen_rise, cnne_fall;
+	u32 pin;
+
+	cnen_rise = readl(bank->reg_base + CNEN_REG);
+	cnne_fall = readl(bank->reg_base + CNNE_REG);
+
+	for_each_set_bit(pin, &status, BITS_PER_LONG) {
+		u32 mask = BIT(pin);
+
+		if ((mask & cnen_rise) || (mask && cnne_fall))
+			pending |= mask;
+	}
+
+	return pending;
+}
+
+static void pic32_gpio_irq_handler(struct irq_desc *desc)
+{
+	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
+	struct pic32_gpio_bank *bank = gpiochip_get_data(gc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	unsigned long pending;
+	unsigned int pin;
+	u32 stat;
+
+	chained_irq_enter(chip, desc);
+
+	stat = readl(bank->reg_base + CNF_REG);
+	pending = pic32_gpio_get_pending(gc, stat);
+
+	for_each_set_bit(pin, &pending, BITS_PER_LONG)
+		generic_handle_irq(irq_linear_revmap(gc->irqdomain, pin));
+
+	chained_irq_exit(chip, desc);
+}
+
+#define GPIO_BANK(_bank, _npins)					\
+	{								\
+		.gpio_chip = {						\
+			.label = "GPIO" #_bank,				\
+			.request = gpiochip_generic_request,		\
+			.free = gpiochip_generic_free,			\
+			.get_direction = pic32_gpio_get_direction,	\
+			.direction_input = pic32_gpio_direction_input,	\
+			.direction_output = pic32_gpio_direction_output, \
+			.get = pic32_gpio_get,				\
+			.set = pic32_gpio_set,				\
+			.ngpio = _npins,				\
+			.base = GPIO_BANK_START(_bank),			\
+			.owner = THIS_MODULE,				\
+			.can_sleep = 0,					\
+		},							\
+		.irq_chip = {						\
+			.name = "GPIO" #_bank,				\
+			.irq_startup = pic32_gpio_irq_startup,	\
+			.irq_ack = pic32_gpio_irq_ack,		\
+			.irq_mask = pic32_gpio_irq_mask,		\
+			.irq_unmask = pic32_gpio_irq_unmask,		\
+			.irq_set_type = pic32_gpio_irq_set_type,	\
+		},							\
+	}
+
+static struct pic32_gpio_bank pic32_gpio_banks[] = {
+	GPIO_BANK(0, PINS_PER_BANK),
+	GPIO_BANK(1, PINS_PER_BANK),
+	GPIO_BANK(2, PINS_PER_BANK),
+	GPIO_BANK(3, PINS_PER_BANK),
+	GPIO_BANK(4, PINS_PER_BANK),
+	GPIO_BANK(5, PINS_PER_BANK),
+	GPIO_BANK(6, PINS_PER_BANK),
+	GPIO_BANK(7, PINS_PER_BANK),
+	GPIO_BANK(8, PINS_PER_BANK),
+	GPIO_BANK(9, PINS_PER_BANK),
+};
+
+static int pic32_pinctrl_probe(struct platform_device *pdev)
+{
+	struct pic32_pinctrl *pctl;
+	struct resource *res;
+	int ret;
+
+	pctl = devm_kzalloc(&pdev->dev, sizeof(*pctl), GFP_KERNEL);
+	if (!pctl)
+		return -ENOMEM;
+	pctl->dev = &pdev->dev;
+	dev_set_drvdata(&pdev->dev, pctl);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	pctl->reg_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(pctl->reg_base))
+		return PTR_ERR(pctl->reg_base);
+
+	pctl->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(pctl->clk)) {
+		ret = PTR_ERR(pctl->clk);
+		dev_err(&pdev->dev, "clk get failed\n");
+		return ret;
+	}
+
+	ret = clk_prepare_enable(pctl->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "clk enable failed\n");
+		return ret;
+	}
+
+	pctl->pins = pic32_pins;
+	pctl->npins = ARRAY_SIZE(pic32_pins);
+	pctl->functions = pic32_functions;
+	pctl->nfunctions = ARRAY_SIZE(pic32_functions);
+	pctl->groups = pic32_groups;
+	pctl->ngroups = ARRAY_SIZE(pic32_groups);
+	pctl->gpio_banks = pic32_gpio_banks;
+	pctl->nbanks = ARRAY_SIZE(pic32_gpio_banks);
+
+	pic32_pinctrl_desc.pins = pctl->pins;
+	pic32_pinctrl_desc.npins = pctl->npins;
+	pic32_pinctrl_desc.custom_params = pic32_mpp_bindings;
+	pic32_pinctrl_desc.num_custom_params = ARRAY_SIZE(pic32_mpp_bindings);
+
+	pctl->pctldev = pinctrl_register(&pic32_pinctrl_desc, &pdev->dev, pctl);
+	if (IS_ERR(pctl->pctldev)) {
+		dev_err(&pdev->dev, "Failed to register pinctrl device\n");
+		return PTR_ERR(pctl->pctldev);
+	}
+
+	return 0;
+}
+
+static int pic32_gpio_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct pic32_gpio_bank *bank;
+	u32 id;
+	int irq, ret;
+	struct resource *res;
+
+	if (of_property_read_u32(np, "microchip,gpio-bank", &id)) {
+		dev_err(&pdev->dev, "microchip,gpio-bank property not found\n");
+		return -EINVAL;
+	}
+
+	if (id >= ARRAY_SIZE(pic32_gpio_banks)) {
+		dev_err(&pdev->dev, "invalid microchip,gpio-bank property\n");
+		return -EINVAL;
+	}
+
+	bank = &pic32_gpio_banks[id];
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	bank->reg_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(bank->reg_base))
+		return PTR_ERR(bank->reg_base);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "irq get failed\n");
+		return irq;
+	}
+
+	bank->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(bank->clk)) {
+		ret = PTR_ERR(bank->clk);
+		dev_err(&pdev->dev, "clk get failed\n");
+		return ret;
+	}
+
+	ret = clk_prepare_enable(bank->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "clk enable failed\n");
+		return ret;
+	}
+
+	bank->gpio_chip.parent = &pdev->dev;
+	bank->gpio_chip.of_node = np;
+	ret = gpiochip_add_data(&bank->gpio_chip, bank);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to add GPIO chip %u: %d\n",
+			id, ret);
+		return ret;
+	}
+
+	ret = gpiochip_irqchip_add(&bank->gpio_chip, &bank->irq_chip,
+				0, handle_level_irq, IRQ_TYPE_NONE);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to add IRQ chip %u: %d\n",
+			id, ret);
+		gpiochip_remove(&bank->gpio_chip);
+		return ret;
+	}
+
+	gpiochip_set_chained_irqchip(&bank->gpio_chip, &bank->irq_chip,
+				     irq, pic32_gpio_irq_handler);
+
+	return 0;
+}
+
+static const struct of_device_id pic32_pinctrl_of_match[] = {
+	{ .compatible = "microchip,pic32mzda-pinctrl", },
+	{ },
+};
+
+static struct platform_driver pic32_pinctrl_driver = {
+	.driver = {
+		.name = "pic32-pinctrl",
+		.of_match_table = pic32_pinctrl_of_match,
+		.suppress_bind_attrs = true,
+	},
+	.probe = pic32_pinctrl_probe,
+};
+
+static const struct of_device_id pic32_gpio_of_match[] = {
+	{ .compatible = "microchip,pic32mzda-gpio", },
+	{ },
+};
+
+static struct platform_driver pic32_gpio_driver = {
+	.driver = {
+		.name = "pic32-gpio",
+		.of_match_table = pic32_gpio_of_match,
+		.suppress_bind_attrs = true,
+	},
+	.probe = pic32_gpio_probe,
+};
+
+static int __init pic32_gpio_register(void)
+{
+	return platform_driver_register(&pic32_gpio_driver);
+}
+arch_initcall(pic32_gpio_register);
+
+static int __init pic32_pinctrl_register(void)
+{
+	return platform_driver_register(&pic32_pinctrl_driver);
+}
+arch_initcall(pic32_pinctrl_register);
diff --git a/drivers/pinctrl/pinctrl-pic32.h b/drivers/pinctrl/pinctrl-pic32.h
new file mode 100644
index 000000000000..12826267dc96
--- /dev/null
+++ b/drivers/pinctrl/pinctrl-pic32.h
@@ -0,0 +1,141 @@
+/*
+ * PIC32 pinctrl driver
+ *
+ * Joshua Henderson, <joshua.henderson@microchip.com>
+ * Copyright (C) 2015 Microchip Technology Inc.  All rights reserved.
+ *
+ * This program is free software; you can distribute it and/or modify it
+ * under the terms of the GNU General Public License (Version 2) as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ * for more details.
+ */
+#ifndef PINCTRL_PINCTRL_PIC32_H
+#define PINCTRL_PINCTRL_PIC32_H
+
+/* PORT Registers */
+#define ANSEL_REG	0x00
+#define TRIS_REG	0x10
+#define PORT_REG	0x20
+#define LAT_REG		0x30
+#define ODCU_REG	0x40
+#define CNPU_REG	0x50
+#define CNPD_REG	0x60
+#define CNCON_REG	0x70
+#define CNEN_REG	0x80
+#define CNSTAT_REG	0x90
+#define CNNE_REG	0xA0
+#define CNF_REG		0xB0
+
+/* Input PPS Registers */
+#define INT1R 0x04
+#define INT2R 0x08
+#define INT3R 0x0C
+#define INT4R 0x10
+#define T2CKR 0x18
+#define T3CKR 0x1C
+#define T4CKR 0x20
+#define T5CKR 0x24
+#define T6CKR 0x28
+#define T7CKR 0x2C
+#define T8CKR 0x30
+#define T9CKR 0x34
+#define IC1R 0x38
+#define IC2R 0x3C
+#define IC3R 0x40
+#define IC4R 0x44
+#define IC5R 0x48
+#define IC6R 0x4C
+#define IC7R 0x50
+#define IC8R 0x54
+#define IC9R 0x58
+#define OCFAR 0x60
+#define U1RXR 0x68
+#define U1CTSR 0x6C
+#define U2RXR 0x70
+#define U2CTSR 0x74
+#define U3RXR 0x78
+#define U3CTSR 0x7C
+#define U4RXR 0x80
+#define U4CTSR 0x84
+#define U5RXR 0x88
+#define U5CTSR 0x8C
+#define U6RXR 0x90
+#define U6CTSR 0x94
+#define SDI1R 0x9C
+#define SS1INR 0xA0
+#define SDI2R 0xA8
+#define SS2INR 0xAC
+#define SDI3R 0xB4
+#define SS3INR 0xB8
+#define SDI4R 0xC0
+#define SS4INR 0xC4
+#define SDI5R 0xCC
+#define SS5INR 0xD0
+#define SDI6R 0xD8
+#define SS6INR 0xDC
+#define C1RXR 0xE0
+#define C2RXR 0xE4
+#define REFCLKI1R 0xE8
+#define REFCLKI3R 0xF0
+#define REFCLKI4R 0xF4
+
+/* Output PPS Registers */
+#define RPA14R 0x138
+#define RPA15R 0x13C
+#define RPB0R 0x140
+#define RPB1R 0x144
+#define RPB2R 0x148
+#define RPB3R 0x14C
+#define RPB5R 0x154
+#define RPB6R 0x158
+#define RPB7R 0x15C
+#define RPB8R 0x160
+#define RPB9R 0x164
+#define RPB10R 0x168
+#define RPB14R 0x178
+#define RPB15R 0x17C
+#define RPC1R 0x184
+#define RPC2R 0x188
+#define RPC3R 0x18C
+#define RPC4R 0x190
+#define RPC13R 0x1B4
+#define RPC14R 0x1B8
+#define RPD0R 0x1C0
+#define RPD1R 0x1C4
+#define RPD2R 0x1C8
+#define RPD3R 0x1CC
+#define RPD4R 0x1D0
+#define RPD5R 0x1D4
+#define RPD6R 0x1D8
+#define RPD7R 0x1DC
+#define RPD9R 0x1E4
+#define RPD10R 0x1E8
+#define RPD11R 0x1EC
+#define RPD12R 0x1F0
+#define RPD14R 0x1F8
+#define RPD15R 0x1FC
+#define RPE3R 0x20C
+#define RPE5R 0x214
+#define RPE8R 0x220
+#define RPE9R 0x224
+#define RPF0R 0x240
+#define RPF1R 0x244
+#define RPF2R 0x248
+#define RPF3R 0x24C
+#define RPF4R 0x250
+#define RPF5R 0x254
+#define RPF8R 0x260
+#define RPF12R 0x270
+#define RPF13R 0x274
+#define RPG0R 0x280
+#define RPG1R 0x284
+#define RPG6R 0x298
+#define RPG7R 0x29C
+#define RPG8R 0x2A0
+#define RPG9R 0x2A4
+
+#endif  /* PINCTRL_PINCTRL_PIC32_H */
diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index 183545a068ad..bf032b9b4c57 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -64,6 +64,7 @@ enum rockchip_pinctrl_type {
 	RK3188,
 	RK3288,
 	RK3368,
+	RK3399,
 };
 
 /**
@@ -86,6 +87,31 @@ struct rockchip_iomux {
 };
 
 /**
+ * enum type index corresponding to rockchip_perpin_drv_list arrays index.
+ */
+enum rockchip_pin_drv_type {
+	DRV_TYPE_IO_DEFAULT = 0,
+	DRV_TYPE_IO_1V8_OR_3V0,
+	DRV_TYPE_IO_1V8_ONLY,
+	DRV_TYPE_IO_1V8_3V0_AUTO,
+	DRV_TYPE_IO_3V3_ONLY,
+	DRV_TYPE_MAX
+};
+
+/**
+ * @drv_type: drive strength variant using rockchip_perpin_drv_type
+ * @offset: if initialized to -1 it will be autocalculated, by specifying
+ *	    an initial offset value the relevant source offset can be reset
+ *	    to a new value for autocalculating the following drive strength
+ *	    registers. if used chips own cal_drv func instead to calculate
+ *	    registers offset, the variant could be ignored.
+ */
+struct rockchip_drv {
+	enum rockchip_pin_drv_type	drv_type;
+	int				offset;
+};
+
+/**
  * @reg_base: register base of the gpio bank
  * @reg_pull: optional separate register for additional pull settings
  * @clk: clock of the gpio bank
@@ -96,6 +122,7 @@ struct rockchip_iomux {
  * @name: name of the bank
  * @bank_num: number of the bank, to account for holes
  * @iomux: array describing the 4 iomux sources of the bank
+ * @drv: array describing the 4 drive strength sources of the bank
  * @valid: are all necessary informations present
  * @of_node: dt node of this bank
  * @drvdata: common pinctrl basedata
@@ -115,6 +142,7 @@ struct rockchip_pin_bank {
 	char				*name;
 	u8				bank_num;
 	struct rockchip_iomux		iomux[4];
+	struct rockchip_drv		drv[4];
 	bool				valid;
 	struct device_node		*of_node;
 	struct rockchip_pinctrl		*drvdata;
@@ -151,6 +179,47 @@ struct rockchip_pin_bank {
 		},							\
 	}
 
+#define PIN_BANK_DRV_FLAGS(id, pins, label, type0, type1, type2, type3) \
+	{								\
+		.bank_num	= id,					\
+		.nr_pins	= pins,					\
+		.name		= label,				\
+		.iomux		= {					\
+			{ .offset = -1 },				\
+			{ .offset = -1 },				\
+			{ .offset = -1 },				\
+			{ .offset = -1 },				\
+		},							\
+		.drv		= {					\
+			{ .drv_type = type0, .offset = -1 },		\
+			{ .drv_type = type1, .offset = -1 },		\
+			{ .drv_type = type2, .offset = -1 },		\
+			{ .drv_type = type3, .offset = -1 },		\
+		},							\
+	}
+
+#define PIN_BANK_IOMUX_DRV_FLAGS_OFFSET(id, pins, label, iom0, iom1,	\
+					iom2, iom3, drv0, drv1, drv2,	\
+					drv3, offset0, offset1,		\
+					offset2, offset3)		\
+	{								\
+		.bank_num	= id,					\
+		.nr_pins	= pins,					\
+		.name		= label,				\
+		.iomux		= {					\
+			{ .type = iom0, .offset = -1 },			\
+			{ .type = iom1, .offset = -1 },			\
+			{ .type = iom2, .offset = -1 },			\
+			{ .type = iom3, .offset = -1 },			\
+		},							\
+		.drv		= {					\
+			{ .drv_type = drv0, .offset = offset0 },	\
+			{ .drv_type = drv1, .offset = offset1 },	\
+			{ .drv_type = drv2, .offset = offset2 },	\
+			{ .drv_type = drv3, .offset = offset3 },	\
+		},							\
+	}
+
 /**
  */
 struct rockchip_pin_ctrl {
@@ -161,6 +230,9 @@ struct rockchip_pin_ctrl {
 	enum rockchip_pinctrl_type	type;
 	int				grf_mux_offset;
 	int				pmu_mux_offset;
+	int				grf_drv_offset;
+	int				pmu_drv_offset;
+
 	void	(*pull_calc_reg)(struct rockchip_pin_bank *bank,
 				    int pin_num, struct regmap **regmap,
 				    int *reg, u8 *bit);
@@ -705,7 +777,68 @@ static void rk3368_calc_drv_reg_and_bit(struct rockchip_pin_bank *bank,
 	}
 }
 
-static int rockchip_perpin_drv_list[] = { 2, 4, 8, 12 };
+#define RK3399_PULL_GRF_OFFSET		0xe040
+#define RK3399_PULL_PMU_OFFSET		0x40
+#define RK3399_DRV_3BITS_PER_PIN	3
+
+static void rk3399_calc_pull_reg_and_bit(struct rockchip_pin_bank *bank,
+					 int pin_num, struct regmap **regmap,
+					 int *reg, u8 *bit)
+{
+	struct rockchip_pinctrl *info = bank->drvdata;
+
+	/* The bank0:16 and bank1:32 pins are located in PMU */
+	if ((bank->bank_num == 0) || (bank->bank_num == 1)) {
+		*regmap = info->regmap_pmu;
+		*reg = RK3399_PULL_PMU_OFFSET;
+
+		*reg += bank->bank_num * RK3188_PULL_BANK_STRIDE;
+
+		*reg += ((pin_num / RK3188_PULL_PINS_PER_REG) * 4);
+		*bit = pin_num % RK3188_PULL_PINS_PER_REG;
+		*bit *= RK3188_PULL_BITS_PER_PIN;
+	} else {
+		*regmap = info->regmap_base;
+		*reg = RK3399_PULL_GRF_OFFSET;
+
+		/* correct the offset, as we're starting with the 3rd bank */
+		*reg -= 0x20;
+		*reg += bank->bank_num * RK3188_PULL_BANK_STRIDE;
+		*reg += ((pin_num / RK3188_PULL_PINS_PER_REG) * 4);
+
+		*bit = (pin_num % RK3188_PULL_PINS_PER_REG);
+		*bit *= RK3188_PULL_BITS_PER_PIN;
+	}
+}
+
+static void rk3399_calc_drv_reg_and_bit(struct rockchip_pin_bank *bank,
+					int pin_num, struct regmap **regmap,
+					int *reg, u8 *bit)
+{
+	struct rockchip_pinctrl *info = bank->drvdata;
+	int drv_num = (pin_num / 8);
+
+	/*  The bank0:16 and bank1:32 pins are located in PMU */
+	if ((bank->bank_num == 0) || (bank->bank_num == 1))
+		*regmap = info->regmap_pmu;
+	else
+		*regmap = info->regmap_base;
+
+	*reg = bank->drv[drv_num].offset;
+	if ((bank->drv[drv_num].drv_type == DRV_TYPE_IO_1V8_3V0_AUTO) ||
+	    (bank->drv[drv_num].drv_type == DRV_TYPE_IO_3V3_ONLY))
+		*bit = (pin_num % 8) * 3;
+	else
+		*bit = (pin_num % 8) * 2;
+}
+
+static int rockchip_perpin_drv_list[DRV_TYPE_MAX][8] = {
+	{ 2, 4, 8, 12, -1, -1, -1, -1 },
+	{ 3, 6, 9, 12, -1, -1, -1, -1 },
+	{ 5, 10, 15, 20, -1, -1, -1, -1 },
+	{ 4, 6, 8, 10, 12, 14, 16, 18 },
+	{ 4, 7, 10, 13, 16, 19, 22, 26 }
+};
 
 static int rockchip_get_drive_perpin(struct rockchip_pin_bank *bank,
 				     int pin_num)
@@ -714,19 +847,74 @@ static int rockchip_get_drive_perpin(struct rockchip_pin_bank *bank,
 	struct rockchip_pin_ctrl *ctrl = info->ctrl;
 	struct regmap *regmap;
 	int reg, ret;
-	u32 data;
+	u32 data, temp, rmask_bits;
 	u8 bit;
+	int drv_type = bank->drv[pin_num / 8].drv_type;
 
 	ctrl->drv_calc_reg(bank, pin_num, &regmap, &reg, &bit);
 
+	switch (drv_type) {
+	case DRV_TYPE_IO_1V8_3V0_AUTO:
+	case DRV_TYPE_IO_3V3_ONLY:
+		rmask_bits = RK3399_DRV_3BITS_PER_PIN;
+		switch (bit) {
+		case 0 ... 12:
+			/* regular case, nothing to do */
+			break;
+		case 15:
+			/*
+			 * drive-strength offset is special, as it is
+			 * spread over 2 registers
+			 */
+			ret = regmap_read(regmap, reg, &data);
+			if (ret)
+				return ret;
+
+			ret = regmap_read(regmap, reg + 0x4, &temp);
+			if (ret)
+				return ret;
+
+			/*
+			 * the bit data[15] contains bit 0 of the value
+			 * while temp[1:0] contains bits 2 and 1
+			 */
+			data >>= 15;
+			temp &= 0x3;
+			temp <<= 1;
+			data |= temp;
+
+			return rockchip_perpin_drv_list[drv_type][data];
+		case 18 ... 21:
+			/* setting fully enclosed in the second register */
+			reg += 4;
+			bit -= 16;
+			break;
+		default:
+			dev_err(info->dev, "unsupported bit: %d for pinctrl drive type: %d\n",
+				bit, drv_type);
+			return -EINVAL;
+		}
+
+		break;
+	case DRV_TYPE_IO_DEFAULT:
+	case DRV_TYPE_IO_1V8_OR_3V0:
+	case DRV_TYPE_IO_1V8_ONLY:
+		rmask_bits = RK3288_DRV_BITS_PER_PIN;
+		break;
+	default:
+		dev_err(info->dev, "unsupported pinctrl drive type: %d\n",
+			drv_type);
+		return -EINVAL;
+	}
+
 	ret = regmap_read(regmap, reg, &data);
 	if (ret)
 		return ret;
 
 	data >>= bit;
-	data &= (1 << RK3288_DRV_BITS_PER_PIN) - 1;
+	data &= (1 << rmask_bits) - 1;
 
-	return rockchip_perpin_drv_list[data];
+	return rockchip_perpin_drv_list[drv_type][data];
 }
 
 static int rockchip_set_drive_perpin(struct rockchip_pin_bank *bank,
@@ -737,16 +925,23 @@ static int rockchip_set_drive_perpin(struct rockchip_pin_bank *bank,
 	struct regmap *regmap;
 	unsigned long flags;
 	int reg, ret, i;
-	u32 data, rmask;
+	u32 data, rmask, rmask_bits, temp;
 	u8 bit;
+	int drv_type = bank->drv[pin_num / 8].drv_type;
+
+	dev_dbg(info->dev, "setting drive of GPIO%d-%d to %d\n",
+		bank->bank_num, pin_num, strength);
 
 	ctrl->drv_calc_reg(bank, pin_num, &regmap, &reg, &bit);
 
 	ret = -EINVAL;
-	for (i = 0; i < ARRAY_SIZE(rockchip_perpin_drv_list); i++) {
-		if (rockchip_perpin_drv_list[i] == strength) {
+	for (i = 0; i < ARRAY_SIZE(rockchip_perpin_drv_list[drv_type]); i++) {
+		if (rockchip_perpin_drv_list[drv_type][i] == strength) {
 			ret = i;
 			break;
+		} else if (rockchip_perpin_drv_list[drv_type][i] < 0) {
+			ret = rockchip_perpin_drv_list[drv_type][i];
+			break;
 		}
 	}
 
@@ -758,8 +953,64 @@ static int rockchip_set_drive_perpin(struct rockchip_pin_bank *bank,
 
 	spin_lock_irqsave(&bank->slock, flags);
 
+	switch (drv_type) {
+	case DRV_TYPE_IO_1V8_3V0_AUTO:
+	case DRV_TYPE_IO_3V3_ONLY:
+		rmask_bits = RK3399_DRV_3BITS_PER_PIN;
+		switch (bit) {
+		case 0 ... 12:
+			/* regular case, nothing to do */
+			break;
+		case 15:
+			/*
+			 * drive-strength offset is special, as it is spread
+			 * over 2 registers, the bit data[15] contains bit 0
+			 * of the value while temp[1:0] contains bits 2 and 1
+			 */
+			data = (ret & 0x1) << 15;
+			temp = (ret >> 0x1) & 0x3;
+
+			rmask = BIT(15) | BIT(31);
+			data |= BIT(31);
+			ret = regmap_update_bits(regmap, reg, rmask, data);
+			if (ret) {
+				spin_unlock_irqrestore(&bank->slock, flags);
+				return ret;
+			}
+
+			rmask = 0x3 | (0x3 << 16);
+			temp |= (0x3 << 16);
+			reg += 0x4;
+			ret = regmap_update_bits(regmap, reg, rmask, temp);
+
+			spin_unlock_irqrestore(&bank->slock, flags);
+			return ret;
+		case 18 ... 21:
+			/* setting fully enclosed in the second register */
+			reg += 4;
+			bit -= 16;
+			break;
+		default:
+			spin_unlock_irqrestore(&bank->slock, flags);
+			dev_err(info->dev, "unsupported bit: %d for pinctrl drive type: %d\n",
+				bit, drv_type);
+			return -EINVAL;
+		}
+		break;
+	case DRV_TYPE_IO_DEFAULT:
+	case DRV_TYPE_IO_1V8_OR_3V0:
+	case DRV_TYPE_IO_1V8_ONLY:
+		rmask_bits = RK3288_DRV_BITS_PER_PIN;
+		break;
+	default:
+		spin_unlock_irqrestore(&bank->slock, flags);
+		dev_err(info->dev, "unsupported pinctrl drive type: %d\n",
+			drv_type);
+		return -EINVAL;
+	}
+
 	/* enable the write to the equivalent lower bits */
-	data = ((1 << RK3288_DRV_BITS_PER_PIN) - 1) << (bit + 16);
+	data = ((1 << rmask_bits) - 1) << (bit + 16);
 	rmask = data | (data >> 16);
 	data |= (ret << bit);
 
@@ -796,6 +1047,7 @@ static int rockchip_get_pull(struct rockchip_pin_bank *bank, int pin_num)
 	case RK3188:
 	case RK3288:
 	case RK3368:
+	case RK3399:
 		data >>= bit;
 		data &= (1 << RK3188_PULL_BITS_PER_PIN) - 1;
 
@@ -852,6 +1104,7 @@ static int rockchip_set_pull(struct rockchip_pin_bank *bank,
 	case RK3188:
 	case RK3288:
 	case RK3368:
+	case RK3399:
 		spin_lock_irqsave(&bank->slock, flags);
 
 		/* enable the write to the equivalent lower bits */
@@ -1032,6 +1285,7 @@ static bool rockchip_pinconf_pull_valid(struct rockchip_pin_ctrl *ctrl,
 	case RK3188:
 	case RK3288:
 	case RK3368:
+	case RK3399:
 		return (pull != PIN_CONFIG_BIAS_PULL_PIN_DEFAULT);
 	}
 
@@ -1892,7 +2146,7 @@ static struct rockchip_pin_ctrl *rockchip_pinctrl_get_soc_data(
 	struct device_node *np;
 	struct rockchip_pin_ctrl *ctrl;
 	struct rockchip_pin_bank *bank;
-	int grf_offs, pmu_offs, i, j;
+	int grf_offs, pmu_offs, drv_grf_offs, drv_pmu_offs, i, j;
 
 	match = of_match_node(rockchip_pinctrl_dt_match, node);
 	ctrl = (struct rockchip_pin_ctrl *)match->data;
@@ -1916,6 +2170,8 @@ static struct rockchip_pin_ctrl *rockchip_pinctrl_get_soc_data(
 
 	grf_offs = ctrl->grf_mux_offset;
 	pmu_offs = ctrl->pmu_mux_offset;
+	drv_pmu_offs = ctrl->pmu_drv_offset;
+	drv_grf_offs = ctrl->grf_drv_offset;
 	bank = ctrl->pin_banks;
 	for (i = 0; i < ctrl->nr_banks; ++i, ++bank) {
 		int bank_pins = 0;
@@ -1925,27 +2181,39 @@ static struct rockchip_pin_ctrl *rockchip_pinctrl_get_soc_data(
 		bank->pin_base = ctrl->nr_pins;
 		ctrl->nr_pins += bank->nr_pins;
 
-		/* calculate iomux offsets */
+		/* calculate iomux and drv offsets */
 		for (j = 0; j < 4; j++) {
 			struct rockchip_iomux *iom = &bank->iomux[j];
+			struct rockchip_drv *drv = &bank->drv[j];
 			int inc;
 
 			if (bank_pins >= bank->nr_pins)
 				break;
 
-			/* preset offset value, set new start value */
+			/* preset iomux offset value, set new start value */
 			if (iom->offset >= 0) {
 				if (iom->type & IOMUX_SOURCE_PMU)
 					pmu_offs = iom->offset;
 				else
 					grf_offs = iom->offset;
-			} else { /* set current offset */
+			} else { /* set current iomux offset */
 				iom->offset = (iom->type & IOMUX_SOURCE_PMU) ?
 							pmu_offs : grf_offs;
 			}
 
-			dev_dbg(d->dev, "bank %d, iomux %d has offset 0x%x\n",
-				 i, j, iom->offset);
+			/* preset drv offset value, set new start value */
+			if (drv->offset >= 0) {
+				if (iom->type & IOMUX_SOURCE_PMU)
+					drv_pmu_offs = drv->offset;
+				else
+					drv_grf_offs = drv->offset;
+			} else { /* set current drv offset */
+				drv->offset = (iom->type & IOMUX_SOURCE_PMU) ?
+						drv_pmu_offs : drv_grf_offs;
+			}
+
+			dev_dbg(d->dev, "bank %d, iomux %d has iom_offset 0x%x drv_offset 0x%x\n",
+				i, j, iom->offset, drv->offset);
 
 			/*
 			 * Increase offset according to iomux width.
@@ -1957,6 +2225,21 @@ static struct rockchip_pin_ctrl *rockchip_pinctrl_get_soc_data(
 			else
 				grf_offs += inc;
 
+			/*
+			 * Increase offset according to drv width.
+			 * 3bit drive-strenth'es are spread over two registers.
+			 */
+			if ((drv->drv_type == DRV_TYPE_IO_1V8_3V0_AUTO) ||
+			    (drv->drv_type == DRV_TYPE_IO_3V3_ONLY))
+				inc = 8;
+			else
+				inc = 4;
+
+			if (iom->type & IOMUX_SOURCE_PMU)
+				drv_pmu_offs += inc;
+			else
+				drv_grf_offs += inc;
+
 			bank_pins += 8;
 		}
 	}
@@ -2257,6 +2540,62 @@ static struct rockchip_pin_ctrl rk3368_pin_ctrl = {
 		.drv_calc_reg		= rk3368_calc_drv_reg_and_bit,
 };
 
+static struct rockchip_pin_bank rk3399_pin_banks[] = {
+	PIN_BANK_IOMUX_DRV_FLAGS_OFFSET(0, 32, "gpio0", IOMUX_SOURCE_PMU,
+					IOMUX_SOURCE_PMU,
+					IOMUX_SOURCE_PMU,
+					IOMUX_SOURCE_PMU,
+					DRV_TYPE_IO_1V8_ONLY,
+					DRV_TYPE_IO_1V8_ONLY,
+					DRV_TYPE_IO_DEFAULT,
+					DRV_TYPE_IO_DEFAULT,
+					0x0,
+					0x8,
+					-1,
+					-1
+					),
+	PIN_BANK_IOMUX_DRV_FLAGS_OFFSET(1, 32, "gpio1", IOMUX_SOURCE_PMU,
+					IOMUX_SOURCE_PMU,
+					IOMUX_SOURCE_PMU,
+					IOMUX_SOURCE_PMU,
+					DRV_TYPE_IO_1V8_OR_3V0,
+					DRV_TYPE_IO_1V8_OR_3V0,
+					DRV_TYPE_IO_1V8_OR_3V0,
+					DRV_TYPE_IO_1V8_OR_3V0,
+					0x20,
+					0x28,
+					0x30,
+					0x38
+					),
+	PIN_BANK_DRV_FLAGS(2, 32, "gpio2", DRV_TYPE_IO_1V8_OR_3V0,
+			   DRV_TYPE_IO_1V8_OR_3V0,
+			   DRV_TYPE_IO_1V8_ONLY,
+			   DRV_TYPE_IO_1V8_ONLY
+			   ),
+	PIN_BANK_DRV_FLAGS(3, 32, "gpio3", DRV_TYPE_IO_3V3_ONLY,
+			   DRV_TYPE_IO_3V3_ONLY,
+			   DRV_TYPE_IO_3V3_ONLY,
+			   DRV_TYPE_IO_1V8_OR_3V0
+			   ),
+	PIN_BANK_DRV_FLAGS(4, 32, "gpio4", DRV_TYPE_IO_1V8_OR_3V0,
+			   DRV_TYPE_IO_1V8_3V0_AUTO,
+			   DRV_TYPE_IO_1V8_OR_3V0,
+			   DRV_TYPE_IO_1V8_OR_3V0
+			   ),
+};
+
+static struct rockchip_pin_ctrl rk3399_pin_ctrl = {
+		.pin_banks		= rk3399_pin_banks,
+		.nr_banks		= ARRAY_SIZE(rk3399_pin_banks),
+		.label			= "RK3399-GPIO",
+		.type			= RK3399,
+		.grf_mux_offset		= 0xe000,
+		.pmu_mux_offset		= 0x0,
+		.grf_drv_offset		= 0xe100,
+		.pmu_drv_offset		= 0x80,
+		.pull_calc_reg		= rk3399_calc_pull_reg_and_bit,
+		.drv_calc_reg		= rk3399_calc_drv_reg_and_bit,
+};
 
 static const struct of_device_id rockchip_pinctrl_dt_match[] = {
 	{ .compatible = "rockchip,rk2928-pinctrl",
@@ -2275,6 +2614,8 @@ static const struct of_device_id rockchip_pinctrl_dt_match[] = {
 		.data = (void *)&rk3288_pin_ctrl },
 	{ .compatible = "rockchip,rk3368-pinctrl",
 		.data = (void *)&rk3368_pin_ctrl },
+	{ .compatible = "rockchip,rk3399-pinctrl",
+		.data = (void *)&rk3399_pin_ctrl },
 	{},
 };
 MODULE_DEVICE_TABLE(of, rockchip_pinctrl_dt_match);
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index d24e5f1d1525..fb126d56ad40 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -255,6 +255,13 @@ static enum pin_config_param pcs_bias[] = {
 };
 
 /*
+ * This lock class tells lockdep that irqchip core that this single
+ * pinctrl can be in a different category than its parents, so it won't
+ * report false recursion.
+ */
+static struct lock_class_key pcs_lock_class;
+
+/*
  * REVISIT: Reads and writes could eventually use regmap or something
  * generic. But at least on omaps, some mux registers are performance
  * critical as they may need to be remuxed every time before and after
@@ -1713,6 +1720,7 @@ static int pcs_irqdomain_map(struct irq_domain *d, unsigned int irq,
 	irq_set_chip_data(irq, pcs_soc);
 	irq_set_chip_and_handler(irq, &pcs->chip,
 				 handle_level_irq);
+	irq_set_lockdep_class(irq, &pcs_lock_class);
 	irq_set_noprobe(irq);
 
 	return 0;
diff --git a/drivers/pinctrl/pinctrl-st.c b/drivers/pinctrl/pinctrl-st.c
index fac844a85cb4..cab66c64149f 100644
--- a/drivers/pinctrl/pinctrl-st.c
+++ b/drivers/pinctrl/pinctrl-st.c
@@ -985,6 +985,7 @@ static struct pinmux_ops st_pmxops = {
 	.get_function_groups	= st_pmx_get_groups,
 	.set_mux		= st_pmx_set_mux,
 	.gpio_set_direction	= st_pmx_set_gpio_direction,
+	.strict			= true,
 };
 
 /* Pinconf  */
diff --git a/drivers/pinctrl/pinctrl-zynq.c b/drivers/pinctrl/pinctrl-zynq.c
index d57b5eca7b98..76f1abd71e31 100644
--- a/drivers/pinctrl/pinctrl-zynq.c
+++ b/drivers/pinctrl/pinctrl-zynq.c
@@ -590,7 +590,7 @@ static const char * const usb1_groups[] = {"usb1_0_grp"};
 static const char * const mdio0_groups[] = {"mdio0_0_grp"};
 static const char * const mdio1_groups[] = {"mdio1_0_grp"};
 static const char * const qspi0_groups[] = {"qspi0_0_grp"};
-static const char * const qspi1_groups[] = {"qspi0_1_grp"};
+static const char * const qspi1_groups[] = {"qspi1_0_grp"};
 static const char * const qspi_fbclk_groups[] = {"qspi_fbclk_grp"};
 static const char * const qspi_cs1_groups[] = {"qspi_cs1_grp"};
 static const char * const spi0_groups[] = {"spi0_0_grp", "spi0_1_grp",
diff --git a/drivers/pinctrl/pxa/pinctrl-pxa2xx.c b/drivers/pinctrl/pxa/pinctrl-pxa2xx.c
index d90e205cf809..f553313bc2ef 100644
--- a/drivers/pinctrl/pxa/pinctrl-pxa2xx.c
+++ b/drivers/pinctrl/pxa/pinctrl-pxa2xx.c
@@ -426,6 +426,7 @@ int pxa2xx_pinctrl_init(struct platform_device *pdev,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pxa2xx_pinctrl_init);
 
 int pxa2xx_pinctrl_exit(struct platform_device *pdev)
 {
@@ -434,3 +435,4 @@ int pxa2xx_pinctrl_exit(struct platform_device *pdev)
 	pinctrl_unregister(pctl->pctl_dev);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pxa2xx_pinctrl_exit);
diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig
index eeac8cba8a21..67bc70dcda64 100644
--- a/drivers/pinctrl/qcom/Kconfig
+++ b/drivers/pinctrl/qcom/Kconfig
@@ -23,6 +23,14 @@ config PINCTRL_APQ8084
 	  This is the pinctrl, pinmux, pinconf and gpiolib driver for the
 	  Qualcomm TLMM block found in the Qualcomm APQ8084 platform.
 
+config PINCTRL_IPQ4019
+	tristate "Qualcomm IPQ4019 pin controller driver"
+	depends on GPIOLIB && OF
+	select PINCTRL_MSM
+	help
+	  This is the pinctrl, pinmux, pinconf and gpiolib driver for the
+	  Qualcomm TLMM block found in the Qualcomm IPQ4019 platform.
+
 config PINCTRL_IPQ8064
 	tristate "Qualcomm IPQ8064 pin controller driver"
 	depends on GPIOLIB && OF
diff --git a/drivers/pinctrl/qcom/Makefile b/drivers/pinctrl/qcom/Makefile
index dfb50a9fe04a..c964a2c4b90a 100644
--- a/drivers/pinctrl/qcom/Makefile
+++ b/drivers/pinctrl/qcom/Makefile
@@ -2,6 +2,7 @@
 obj-$(CONFIG_PINCTRL_MSM)	+= pinctrl-msm.o
 obj-$(CONFIG_PINCTRL_APQ8064)	+= pinctrl-apq8064.o
 obj-$(CONFIG_PINCTRL_APQ8084)	+= pinctrl-apq8084.o
+obj-$(CONFIG_PINCTRL_IPQ4019)	+= pinctrl-ipq4019.o
 obj-$(CONFIG_PINCTRL_IPQ8064)	+= pinctrl-ipq8064.o
 obj-$(CONFIG_PINCTRL_MSM8660)	+= pinctrl-msm8660.o
 obj-$(CONFIG_PINCTRL_MSM8960)	+= pinctrl-msm8960.o
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq4019.c b/drivers/pinctrl/qcom/pinctrl-ipq4019.c
new file mode 100644
index 000000000000..b5d81ced6ce6
--- /dev/null
+++ b/drivers/pinctrl/qcom/pinctrl-ipq4019.c
@@ -0,0 +1,453 @@
+/*
+ * Copyright (c) 2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pinctrl/pinctrl.h>
+
+#include "pinctrl-msm.h"
+
+static const struct pinctrl_pin_desc ipq4019_pins[] = {
+	PINCTRL_PIN(0, "GPIO_0"),
+	PINCTRL_PIN(1, "GPIO_1"),
+	PINCTRL_PIN(2, "GPIO_2"),
+	PINCTRL_PIN(3, "GPIO_3"),
+	PINCTRL_PIN(4, "GPIO_4"),
+	PINCTRL_PIN(5, "GPIO_5"),
+	PINCTRL_PIN(6, "GPIO_6"),
+	PINCTRL_PIN(7, "GPIO_7"),
+	PINCTRL_PIN(8, "GPIO_8"),
+	PINCTRL_PIN(9, "GPIO_9"),
+	PINCTRL_PIN(10, "GPIO_10"),
+	PINCTRL_PIN(11, "GPIO_11"),
+	PINCTRL_PIN(12, "GPIO_12"),
+	PINCTRL_PIN(13, "GPIO_13"),
+	PINCTRL_PIN(14, "GPIO_14"),
+	PINCTRL_PIN(15, "GPIO_15"),
+	PINCTRL_PIN(16, "GPIO_16"),
+	PINCTRL_PIN(17, "GPIO_17"),
+	PINCTRL_PIN(18, "GPIO_18"),
+	PINCTRL_PIN(19, "GPIO_19"),
+	PINCTRL_PIN(20, "GPIO_20"),
+	PINCTRL_PIN(21, "GPIO_21"),
+	PINCTRL_PIN(22, "GPIO_22"),
+	PINCTRL_PIN(23, "GPIO_23"),
+	PINCTRL_PIN(24, "GPIO_24"),
+	PINCTRL_PIN(25, "GPIO_25"),
+	PINCTRL_PIN(26, "GPIO_26"),
+	PINCTRL_PIN(27, "GPIO_27"),
+	PINCTRL_PIN(28, "GPIO_28"),
+	PINCTRL_PIN(29, "GPIO_29"),
+	PINCTRL_PIN(30, "GPIO_30"),
+	PINCTRL_PIN(31, "GPIO_31"),
+	PINCTRL_PIN(32, "GPIO_32"),
+	PINCTRL_PIN(33, "GPIO_33"),
+	PINCTRL_PIN(34, "GPIO_34"),
+	PINCTRL_PIN(35, "GPIO_35"),
+	PINCTRL_PIN(36, "GPIO_36"),
+	PINCTRL_PIN(37, "GPIO_37"),
+	PINCTRL_PIN(38, "GPIO_38"),
+	PINCTRL_PIN(39, "GPIO_39"),
+	PINCTRL_PIN(40, "GPIO_40"),
+	PINCTRL_PIN(41, "GPIO_41"),
+	PINCTRL_PIN(42, "GPIO_42"),
+	PINCTRL_PIN(43, "GPIO_43"),
+	PINCTRL_PIN(44, "GPIO_44"),
+	PINCTRL_PIN(45, "GPIO_45"),
+	PINCTRL_PIN(46, "GPIO_46"),
+	PINCTRL_PIN(47, "GPIO_47"),
+	PINCTRL_PIN(48, "GPIO_48"),
+	PINCTRL_PIN(49, "GPIO_49"),
+	PINCTRL_PIN(50, "GPIO_50"),
+	PINCTRL_PIN(51, "GPIO_51"),
+	PINCTRL_PIN(52, "GPIO_52"),
+	PINCTRL_PIN(53, "GPIO_53"),
+	PINCTRL_PIN(54, "GPIO_54"),
+	PINCTRL_PIN(55, "GPIO_55"),
+	PINCTRL_PIN(56, "GPIO_56"),
+	PINCTRL_PIN(57, "GPIO_57"),
+	PINCTRL_PIN(58, "GPIO_58"),
+	PINCTRL_PIN(59, "GPIO_59"),
+	PINCTRL_PIN(60, "GPIO_60"),
+	PINCTRL_PIN(61, "GPIO_61"),
+	PINCTRL_PIN(62, "GPIO_62"),
+	PINCTRL_PIN(63, "GPIO_63"),
+	PINCTRL_PIN(64, "GPIO_64"),
+	PINCTRL_PIN(65, "GPIO_65"),
+	PINCTRL_PIN(66, "GPIO_66"),
+	PINCTRL_PIN(67, "GPIO_67"),
+	PINCTRL_PIN(68, "GPIO_68"),
+	PINCTRL_PIN(69, "GPIO_69"),
+	PINCTRL_PIN(70, "GPIO_70"),
+	PINCTRL_PIN(71, "GPIO_71"),
+	PINCTRL_PIN(72, "GPIO_72"),
+	PINCTRL_PIN(73, "GPIO_73"),
+	PINCTRL_PIN(74, "GPIO_74"),
+	PINCTRL_PIN(75, "GPIO_75"),
+	PINCTRL_PIN(76, "GPIO_76"),
+	PINCTRL_PIN(77, "GPIO_77"),
+	PINCTRL_PIN(78, "GPIO_78"),
+	PINCTRL_PIN(79, "GPIO_79"),
+	PINCTRL_PIN(80, "GPIO_80"),
+	PINCTRL_PIN(81, "GPIO_81"),
+	PINCTRL_PIN(82, "GPIO_82"),
+	PINCTRL_PIN(83, "GPIO_83"),
+	PINCTRL_PIN(84, "GPIO_84"),
+	PINCTRL_PIN(85, "GPIO_85"),
+	PINCTRL_PIN(86, "GPIO_86"),
+	PINCTRL_PIN(87, "GPIO_87"),
+	PINCTRL_PIN(88, "GPIO_88"),
+	PINCTRL_PIN(89, "GPIO_89"),
+	PINCTRL_PIN(90, "GPIO_90"),
+	PINCTRL_PIN(91, "GPIO_91"),
+	PINCTRL_PIN(92, "GPIO_92"),
+	PINCTRL_PIN(93, "GPIO_93"),
+	PINCTRL_PIN(94, "GPIO_94"),
+	PINCTRL_PIN(95, "GPIO_95"),
+	PINCTRL_PIN(96, "GPIO_96"),
+	PINCTRL_PIN(97, "GPIO_97"),
+	PINCTRL_PIN(98, "GPIO_98"),
+	PINCTRL_PIN(99, "GPIO_99"),
+};
+
+#define DECLARE_QCA_GPIO_PINS(pin) \
+	static const unsigned int gpio##pin##_pins[] = { pin }
+DECLARE_QCA_GPIO_PINS(0);
+DECLARE_QCA_GPIO_PINS(1);
+DECLARE_QCA_GPIO_PINS(2);
+DECLARE_QCA_GPIO_PINS(3);
+DECLARE_QCA_GPIO_PINS(4);
+DECLARE_QCA_GPIO_PINS(5);
+DECLARE_QCA_GPIO_PINS(6);
+DECLARE_QCA_GPIO_PINS(7);
+DECLARE_QCA_GPIO_PINS(8);
+DECLARE_QCA_GPIO_PINS(9);
+DECLARE_QCA_GPIO_PINS(10);
+DECLARE_QCA_GPIO_PINS(11);
+DECLARE_QCA_GPIO_PINS(12);
+DECLARE_QCA_GPIO_PINS(13);
+DECLARE_QCA_GPIO_PINS(14);
+DECLARE_QCA_GPIO_PINS(15);
+DECLARE_QCA_GPIO_PINS(16);
+DECLARE_QCA_GPIO_PINS(17);
+DECLARE_QCA_GPIO_PINS(18);
+DECLARE_QCA_GPIO_PINS(19);
+DECLARE_QCA_GPIO_PINS(20);
+DECLARE_QCA_GPIO_PINS(21);
+DECLARE_QCA_GPIO_PINS(22);
+DECLARE_QCA_GPIO_PINS(23);
+DECLARE_QCA_GPIO_PINS(24);
+DECLARE_QCA_GPIO_PINS(25);
+DECLARE_QCA_GPIO_PINS(26);
+DECLARE_QCA_GPIO_PINS(27);
+DECLARE_QCA_GPIO_PINS(28);
+DECLARE_QCA_GPIO_PINS(29);
+DECLARE_QCA_GPIO_PINS(30);
+DECLARE_QCA_GPIO_PINS(31);
+DECLARE_QCA_GPIO_PINS(32);
+DECLARE_QCA_GPIO_PINS(33);
+DECLARE_QCA_GPIO_PINS(34);
+DECLARE_QCA_GPIO_PINS(35);
+DECLARE_QCA_GPIO_PINS(36);
+DECLARE_QCA_GPIO_PINS(37);
+DECLARE_QCA_GPIO_PINS(38);
+DECLARE_QCA_GPIO_PINS(39);
+DECLARE_QCA_GPIO_PINS(40);
+DECLARE_QCA_GPIO_PINS(41);
+DECLARE_QCA_GPIO_PINS(42);
+DECLARE_QCA_GPIO_PINS(43);
+DECLARE_QCA_GPIO_PINS(44);
+DECLARE_QCA_GPIO_PINS(45);
+DECLARE_QCA_GPIO_PINS(46);
+DECLARE_QCA_GPIO_PINS(47);
+DECLARE_QCA_GPIO_PINS(48);
+DECLARE_QCA_GPIO_PINS(49);
+DECLARE_QCA_GPIO_PINS(50);
+DECLARE_QCA_GPIO_PINS(51);
+DECLARE_QCA_GPIO_PINS(52);
+DECLARE_QCA_GPIO_PINS(53);
+DECLARE_QCA_GPIO_PINS(54);
+DECLARE_QCA_GPIO_PINS(55);
+DECLARE_QCA_GPIO_PINS(56);
+DECLARE_QCA_GPIO_PINS(57);
+DECLARE_QCA_GPIO_PINS(58);
+DECLARE_QCA_GPIO_PINS(59);
+DECLARE_QCA_GPIO_PINS(60);
+DECLARE_QCA_GPIO_PINS(61);
+DECLARE_QCA_GPIO_PINS(62);
+DECLARE_QCA_GPIO_PINS(63);
+DECLARE_QCA_GPIO_PINS(64);
+DECLARE_QCA_GPIO_PINS(65);
+DECLARE_QCA_GPIO_PINS(66);
+DECLARE_QCA_GPIO_PINS(67);
+DECLARE_QCA_GPIO_PINS(68);
+DECLARE_QCA_GPIO_PINS(69);
+DECLARE_QCA_GPIO_PINS(70);
+DECLARE_QCA_GPIO_PINS(71);
+DECLARE_QCA_GPIO_PINS(72);
+DECLARE_QCA_GPIO_PINS(73);
+DECLARE_QCA_GPIO_PINS(74);
+DECLARE_QCA_GPIO_PINS(75);
+DECLARE_QCA_GPIO_PINS(76);
+DECLARE_QCA_GPIO_PINS(77);
+DECLARE_QCA_GPIO_PINS(78);
+DECLARE_QCA_GPIO_PINS(79);
+DECLARE_QCA_GPIO_PINS(80);
+DECLARE_QCA_GPIO_PINS(81);
+DECLARE_QCA_GPIO_PINS(82);
+DECLARE_QCA_GPIO_PINS(83);
+DECLARE_QCA_GPIO_PINS(84);
+DECLARE_QCA_GPIO_PINS(85);
+DECLARE_QCA_GPIO_PINS(86);
+DECLARE_QCA_GPIO_PINS(87);
+DECLARE_QCA_GPIO_PINS(88);
+DECLARE_QCA_GPIO_PINS(89);
+DECLARE_QCA_GPIO_PINS(90);
+DECLARE_QCA_GPIO_PINS(91);
+DECLARE_QCA_GPIO_PINS(92);
+DECLARE_QCA_GPIO_PINS(93);
+DECLARE_QCA_GPIO_PINS(94);
+DECLARE_QCA_GPIO_PINS(95);
+DECLARE_QCA_GPIO_PINS(96);
+DECLARE_QCA_GPIO_PINS(97);
+DECLARE_QCA_GPIO_PINS(98);
+DECLARE_QCA_GPIO_PINS(99);
+
+#define FUNCTION(fname)			                \
+	[qca_mux_##fname] = {		                \
+		.name = #fname,				\
+		.groups = fname##_groups,               \
+		.ngroups = ARRAY_SIZE(fname##_groups),	\
+	}
+
+#define PINGROUP(id, f1, f2, f3, f4, f5, f6, f7, f8, f9, f10, f11, f12, f13, f14) \
+	{					        \
+		.name = "gpio" #id,			\
+		.pins = gpio##id##_pins,		\
+		.npins = (unsigned)ARRAY_SIZE(gpio##id##_pins),	\
+		.funcs = (int[]){			\
+			qca_mux_NA, /* gpio mode */	\
+			qca_mux_##f1,			\
+			qca_mux_##f2,			\
+			qca_mux_##f3,			\
+			qca_mux_##f4,			\
+			qca_mux_##f5,			\
+			qca_mux_##f6,			\
+			qca_mux_##f7,			\
+			qca_mux_##f8,			\
+			qca_mux_##f9,			\
+			qca_mux_##f10,			\
+			qca_mux_##f11,			\
+			qca_mux_##f12,			\
+			qca_mux_##f13,			\
+			qca_mux_##f14			\
+		},				        \
+		.nfuncs = 15,				\
+		.ctl_reg = 0x1000 + 0x10 * id,		\
+		.io_reg = 0x1004 + 0x10 * id,		\
+		.intr_cfg_reg = 0x1008 + 0x10 * id,	\
+		.intr_status_reg = 0x100c + 0x10 * id,	\
+		.intr_target_reg = 0x400 + 0x4 * id,	\
+		.mux_bit = 2,			\
+		.pull_bit = 0,			\
+		.drv_bit = 6,			\
+		.oe_bit = 9,			\
+		.in_bit = 0,			\
+		.out_bit = 1,			\
+		.intr_enable_bit = 0,		\
+		.intr_status_bit = 0,		\
+		.intr_target_bit = 5,		\
+		.intr_raw_status_bit = 4,	\
+		.intr_polarity_bit = 1,		\
+		.intr_detection_bit = 2,	\
+		.intr_detection_width = 2,	\
+	}
+
+
+enum ipq4019_functions {
+	qca_mux_gpio,
+	qca_mux_blsp_uart1,
+	qca_mux_blsp_i2c0,
+	qca_mux_blsp_i2c1,
+	qca_mux_blsp_uart0,
+	qca_mux_blsp_spi1,
+	qca_mux_blsp_spi0,
+	qca_mux_NA,
+};
+
+static const char * const gpio_groups[] = {
+	"gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7",
+	"gpio8", "gpio9", "gpio10", "gpio11", "gpio12", "gpio13", "gpio14",
+	"gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21",
+	"gpio22", "gpio23", "gpio24", "gpio25", "gpio26", "gpio27", "gpio28",
+	"gpio29", "gpio30", "gpio31", "gpio32", "gpio33", "gpio34", "gpio35",
+	"gpio36", "gpio37", "gpio38", "gpio39", "gpio40", "gpio41", "gpio42",
+	"gpio43", "gpio44", "gpio45", "gpio46", "gpio47", "gpio48", "gpio49",
+	"gpio50", "gpio51", "gpio52", "gpio53", "gpio54", "gpio55", "gpio56",
+	"gpio57", "gpio58", "gpio59", "gpio60", "gpio61", "gpio62", "gpio63",
+	"gpio64", "gpio65", "gpio66", "gpio67", "gpio68", "gpio69", "gpio70",
+	"gpio71", "gpio72", "gpio73", "gpio74", "gpio75", "gpio76", "gpio77",
+	"gpio78", "gpio79", "gpio80", "gpio81", "gpio82", "gpio83", "gpio84",
+	"gpio85", "gpio86", "gpio87", "gpio88", "gpio89", "gpio90", "gpio91",
+	"gpio92", "gpio93", "gpio94", "gpio95", "gpio96", "gpio97", "gpio98",
+	"gpio99",
+};
+
+static const char * const blsp_uart1_groups[] = {
+	"gpio8", "gpio9", "gpio10", "gpio11",
+};
+static const char * const blsp_i2c0_groups[] = {
+	"gpio10", "gpio11", "gpio20", "gpio21", "gpio58", "gpio59",
+};
+static const char * const blsp_spi0_groups[] = {
+	"gpio12", "gpio13", "gpio14", "gpio15", "gpio45",
+	"gpio54", "gpio55", "gpio56", "gpio57",
+};
+static const char * const blsp_i2c1_groups[] = {
+	"gpio12", "gpio13", "gpio34", "gpio35",
+};
+static const char * const blsp_uart0_groups[] = {
+	"gpio16", "gpio17", "gpio60", "gpio61",
+};
+static const char * const blsp_spi1_groups[] = {
+	"gpio44", "gpio45", "gpio46", "gpio47",
+};
+
+static const struct msm_function ipq4019_functions[] = {
+	FUNCTION(gpio),
+	FUNCTION(blsp_uart1),
+	FUNCTION(blsp_i2c0),
+	FUNCTION(blsp_i2c1),
+	FUNCTION(blsp_uart0),
+	FUNCTION(blsp_spi1),
+	FUNCTION(blsp_spi0),
+};
+
+static const struct msm_pingroup ipq4019_groups[] = {
+	PINGROUP(0, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(1, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(2, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(3, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(4, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(5, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(6, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(7, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(8, blsp_uart1, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(9, blsp_uart1, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(10, blsp_uart1, NA, NA, blsp_i2c0, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(11, blsp_uart1, NA, NA, blsp_i2c0, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(12, blsp_spi0, blsp_i2c1, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(13, blsp_spi0, blsp_i2c1, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(14, blsp_spi0, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(15, blsp_spi0, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(16, blsp_uart0, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(17, blsp_uart0, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(18, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(19, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(20, blsp_i2c0, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(21, blsp_i2c0, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(22, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(23, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(24, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(25, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(26, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(27, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(28, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(29, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(30, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(31, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(32, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(33, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(34, blsp_i2c1, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(35, blsp_i2c1, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(36, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(37, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(38, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(39, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(40, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(41, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(42, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(43, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(44, NA, blsp_spi1, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(45, NA, blsp_spi1, blsp_spi0, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(46, NA, blsp_spi1, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(47, NA, blsp_spi1, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(48, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(49, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(50, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(51, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(52, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(53, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(54, NA, blsp_spi0, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(55, NA, blsp_spi0, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(56, NA, blsp_spi0, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(57, NA, blsp_spi0, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(58, NA, NA, blsp_i2c0, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(59, NA, blsp_i2c0, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(60, NA, blsp_uart0, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(61, NA, blsp_uart0, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(62, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(63, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(64, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(65, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(66, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(67, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(68, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+	PINGROUP(69, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
+};
+
+static const struct msm_pinctrl_soc_data ipq4019_pinctrl = {
+	.pins = ipq4019_pins,
+	.npins = ARRAY_SIZE(ipq4019_pins),
+	.functions = ipq4019_functions,
+	.nfunctions = ARRAY_SIZE(ipq4019_functions),
+	.groups = ipq4019_groups,
+	.ngroups = ARRAY_SIZE(ipq4019_groups),
+	.ngpios = 70,
+};
+
+static int ipq4019_pinctrl_probe(struct platform_device *pdev)
+{
+	return msm_pinctrl_probe(pdev, &ipq4019_pinctrl);
+}
+
+static const struct of_device_id ipq4019_pinctrl_of_match[] = {
+	{ .compatible = "qcom,ipq4019-pinctrl", },
+	{ },
+};
+
+static struct platform_driver ipq4019_pinctrl_driver = {
+	.driver = {
+		.name = "ipq4019-pinctrl",
+		.of_match_table = ipq4019_pinctrl_of_match,
+	},
+	.probe = ipq4019_pinctrl_probe,
+	.remove = msm_pinctrl_remove,
+};
+
+static int __init ipq4019_pinctrl_init(void)
+{
+	return platform_driver_register(&ipq4019_pinctrl_driver);
+}
+arch_initcall(ipq4019_pinctrl_init);
+
+static void __exit ipq4019_pinctrl_exit(void)
+{
+	platform_driver_unregister(&ipq4019_pinctrl_driver);
+}
+module_exit(ipq4019_pinctrl_exit);
+
+MODULE_DESCRIPTION("Qualcomm ipq4019 pinctrl driver");
+MODULE_LICENSE("GPL v2");
+MODULE_DEVICE_TABLE(of, ipq4019_pinctrl_of_match);
diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c b/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c
index 2f18323571a6..2a3e5490a483 100644
--- a/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c
+++ b/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c
@@ -117,6 +117,7 @@
  * @output_enabled: Set to true if MPP output logic is enabled.
  * @input_enabled: Set to true if MPP input buffer logic is enabled.
  * @paired: Pin operates in paired mode
+ * @has_pullup: Pin has support to configure pullup
  * @num_sources: Number of power-sources supported by this MPP.
  * @power_source: Current power-source used.
  * @amux_input: Set the source for analog input.
@@ -134,6 +135,7 @@ struct pmic_mpp_pad {
 	bool		output_enabled;
 	bool		input_enabled;
 	bool		paired;
+	bool		has_pullup;
 	unsigned int	num_sources;
 	unsigned int	power_source;
 	unsigned int	amux_input;
@@ -477,11 +479,14 @@ static int pmic_mpp_config_set(struct pinctrl_dev *pctldev, unsigned int pin,
 	if (ret < 0)
 		return ret;
 
-	val = pad->pullup << PMIC_MPP_REG_PULL_SHIFT;
+	if (pad->has_pullup) {
+		val = pad->pullup << PMIC_MPP_REG_PULL_SHIFT;
 
-	ret = pmic_mpp_write(state, pad, PMIC_MPP_REG_DIG_PULL_CTL, val);
-	if (ret < 0)
-		return ret;
+		ret = pmic_mpp_write(state, pad, PMIC_MPP_REG_DIG_PULL_CTL,
+				     val);
+		if (ret < 0)
+			return ret;
+	}
 
 	val = pad->amux_input & PMIC_MPP_REG_AIN_ROUTE_MASK;
 
@@ -534,7 +539,8 @@ static void pmic_mpp_config_dbg_show(struct pinctrl_dev *pctldev,
 		seq_printf(s, " %-7s", pmic_mpp_functions[pad->function]);
 		seq_printf(s, " vin-%d", pad->power_source);
 		seq_printf(s, " %d", pad->aout_level);
-		seq_printf(s, " %-8s", biases[pad->pullup]);
+		if (pad->has_pullup)
+			seq_printf(s, " %-8s", biases[pad->pullup]);
 		seq_printf(s, " %-4s", pad->out_value ? "high" : "low");
 		if (pad->dtest)
 			seq_printf(s, " dtest%d", pad->dtest);
@@ -748,12 +754,16 @@ static int pmic_mpp_populate(struct pmic_mpp_state *state,
 	pad->power_source = val >> PMIC_MPP_REG_VIN_SHIFT;
 	pad->power_source &= PMIC_MPP_REG_VIN_MASK;
 
-	val = pmic_mpp_read(state, pad, PMIC_MPP_REG_DIG_PULL_CTL);
-	if (val < 0)
-		return val;
+	if (subtype != PMIC_MPP_SUBTYPE_ULT_4CH_NO_ANA_OUT &&
+	    subtype != PMIC_MPP_SUBTYPE_ULT_4CH_NO_SINK) {
+		val = pmic_mpp_read(state, pad, PMIC_MPP_REG_DIG_PULL_CTL);
+		if (val < 0)
+			return val;
 
-	pad->pullup = val >> PMIC_MPP_REG_PULL_SHIFT;
-	pad->pullup &= PMIC_MPP_REG_PULL_MASK;
+		pad->pullup = val >> PMIC_MPP_REG_PULL_SHIFT;
+		pad->pullup &= PMIC_MPP_REG_PULL_MASK;
+		pad->has_pullup = true;
+	}
 
 	val = pmic_mpp_read(state, pad, PMIC_MPP_REG_AIN_CTL);
 	if (val < 0)
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c
index f67b1e958589..5cc97f85db02 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.c
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.c
@@ -514,25 +514,35 @@ static const struct pinconf_ops samsung_pinconf_ops = {
 	.pin_config_group_set	= samsung_pinconf_group_set,
 };
 
-/* gpiolib gpio_set callback function */
-static void samsung_gpio_set(struct gpio_chip *gc, unsigned offset, int value)
+/*
+ * The samsung_gpio_set_vlaue() should be called with "bank->slock" held
+ * to avoid race condition.
+ */
+static void samsung_gpio_set_value(struct gpio_chip *gc,
+					  unsigned offset, int value)
 {
 	struct samsung_pin_bank *bank = gpiochip_get_data(gc);
 	const struct samsung_pin_bank_type *type = bank->type;
-	unsigned long flags;
 	void __iomem *reg;
 	u32 data;
 
 	reg = bank->drvdata->virt_base + bank->pctl_offset;
 
-	spin_lock_irqsave(&bank->slock, flags);
-
 	data = readl(reg + type->reg_offset[PINCFG_TYPE_DAT]);
 	data &= ~(1 << offset);
 	if (value)
 		data |= 1 << offset;
 	writel(data, reg + type->reg_offset[PINCFG_TYPE_DAT]);
+}
+
+/* gpiolib gpio_set callback function */
+static void samsung_gpio_set(struct gpio_chip *gc, unsigned offset, int value)
+{
+	struct samsung_pin_bank *bank = gpiochip_get_data(gc);
+	unsigned long flags;
 
+	spin_lock_irqsave(&bank->slock, flags);
+	samsung_gpio_set_value(gc, offset, value);
 	spin_unlock_irqrestore(&bank->slock, flags);
 }
 
@@ -553,6 +563,8 @@ static int samsung_gpio_get(struct gpio_chip *gc, unsigned offset)
 }
 
 /*
+ * The samsung_gpio_set_direction() should be called with "bank->slock" held
+ * to avoid race condition.
  * The calls to gpio_direction_output() and gpio_direction_input()
  * leads to this function call.
  */
@@ -564,7 +576,6 @@ static int samsung_gpio_set_direction(struct gpio_chip *gc,
 	struct samsung_pinctrl_drv_data *drvdata;
 	void __iomem *reg;
 	u32 data, mask, shift;
-	unsigned long flags;
 
 	bank = gpiochip_get_data(gc);
 	type = bank->type;
@@ -581,31 +592,42 @@ static int samsung_gpio_set_direction(struct gpio_chip *gc,
 		reg += 4;
 	}
 
-	spin_lock_irqsave(&bank->slock, flags);
-
 	data = readl(reg);
 	data &= ~(mask << shift);
 	if (!input)
 		data |= FUNC_OUTPUT << shift;
 	writel(data, reg);
 
-	spin_unlock_irqrestore(&bank->slock, flags);
-
 	return 0;
 }
 
 /* gpiolib gpio_direction_input callback function. */
 static int samsung_gpio_direction_input(struct gpio_chip *gc, unsigned offset)
 {
-	return samsung_gpio_set_direction(gc, offset, true);
+	struct samsung_pin_bank *bank = gpiochip_get_data(gc);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&bank->slock, flags);
+	ret = samsung_gpio_set_direction(gc, offset, true);
+	spin_unlock_irqrestore(&bank->slock, flags);
+	return ret;
 }
 
 /* gpiolib gpio_direction_output callback function. */
 static int samsung_gpio_direction_output(struct gpio_chip *gc, unsigned offset,
 							int value)
 {
-	samsung_gpio_set(gc, offset, value);
-	return samsung_gpio_set_direction(gc, offset, false);
+	struct samsung_pin_bank *bank = gpiochip_get_data(gc);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&bank->slock, flags);
+	samsung_gpio_set_value(gc, offset, value);
+	ret = samsung_gpio_set_direction(gc, offset, false);
+	spin_unlock_irqrestore(&bank->slock, flags);
+
+	return ret;
 }
 
 /*
diff --git a/drivers/pinctrl/sh-pfc/Kconfig b/drivers/pinctrl/sh-pfc/Kconfig
index 35d6e95fa21f..415dd8023063 100644
--- a/drivers/pinctrl/sh-pfc/Kconfig
+++ b/drivers/pinctrl/sh-pfc/Kconfig
@@ -2,10 +2,9 @@
 # Renesas SH and SH Mobile PINCTRL drivers
 #
 
-if ARCH_SHMOBILE || SUPERH
+if ARCH_RENESAS || SUPERH
 
 config PINCTRL_SH_PFC
-	select GPIO_SH_PFC if ARCH_REQUIRE_GPIOLIB
 	select PINMUX
 	select PINCONF
 	select GENERIC_PINCONF
@@ -13,12 +12,12 @@ config PINCTRL_SH_PFC
 	help
 	  This enables pin control drivers for SH and SH Mobile platforms
 
-config GPIO_SH_PFC
-	bool "SuperH PFC GPIO support"
-	depends on PINCTRL_SH_PFC && GPIOLIB
+config PINCTRL_SH_PFC_GPIO
+	select GPIOLIB
+	select PINCTRL_SH_PFC
+	bool
 	help
-	  This enables support for GPIOs within the SoC's pin function
-	  controller.
+	  This enables pin control and GPIO drivers for SH/SH Mobile platforms
 
 config PINCTRL_PFC_EMEV2
 	def_bool y
@@ -28,12 +27,12 @@ config PINCTRL_PFC_EMEV2
 config PINCTRL_PFC_R8A73A4
 	def_bool y
 	depends on ARCH_R8A73A4
-	select PINCTRL_SH_PFC
+	select PINCTRL_SH_PFC_GPIO
 
 config PINCTRL_PFC_R8A7740
 	def_bool y
 	depends on ARCH_R8A7740
-	select PINCTRL_SH_PFC
+	select PINCTRL_SH_PFC_GPIO
 
 config PINCTRL_PFC_R8A7778
 	def_bool y
@@ -73,79 +72,66 @@ config PINCTRL_PFC_R8A7795
 config PINCTRL_PFC_SH7203
 	def_bool y
 	depends on CPU_SUBTYPE_SH7203
-	depends on GPIOLIB
-	select PINCTRL_SH_PFC
+	select PINCTRL_SH_PFC_GPIO
 
 config PINCTRL_PFC_SH7264
 	def_bool y
 	depends on CPU_SUBTYPE_SH7264
-	depends on GPIOLIB
-	select PINCTRL_SH_PFC
+	select PINCTRL_SH_PFC_GPIO
 
 config PINCTRL_PFC_SH7269
 	def_bool y
 	depends on CPU_SUBTYPE_SH7269
-	depends on GPIOLIB
-	select PINCTRL_SH_PFC
+	select PINCTRL_SH_PFC_GPIO
 
 config PINCTRL_PFC_SH73A0
 	def_bool y
 	depends on ARCH_SH73A0
-	select PINCTRL_SH_PFC
+	select PINCTRL_SH_PFC_GPIO
 	select REGULATOR
 
 config PINCTRL_PFC_SH7720
 	def_bool y
 	depends on CPU_SUBTYPE_SH7720
-	depends on GPIOLIB
-	select PINCTRL_SH_PFC
+	select PINCTRL_SH_PFC_GPIO
 
 config PINCTRL_PFC_SH7722
 	def_bool y
 	depends on CPU_SUBTYPE_SH7722
-	depends on GPIOLIB
-	select PINCTRL_SH_PFC
+	select PINCTRL_SH_PFC_GPIO
 
 config PINCTRL_PFC_SH7723
 	def_bool y
 	depends on CPU_SUBTYPE_SH7723
-	depends on GPIOLIB
-	select PINCTRL_SH_PFC
+	select PINCTRL_SH_PFC_GPIO
 
 config PINCTRL_PFC_SH7724
 	def_bool y
 	depends on CPU_SUBTYPE_SH7724
-	depends on GPIOLIB
-	select PINCTRL_SH_PFC
+	select PINCTRL_SH_PFC_GPIO
 
 config PINCTRL_PFC_SH7734
 	def_bool y
 	depends on CPU_SUBTYPE_SH7734
-	depends on GPIOLIB
-	select PINCTRL_SH_PFC
+	select PINCTRL_SH_PFC_GPIO
 
 config PINCTRL_PFC_SH7757
 	def_bool y
 	depends on CPU_SUBTYPE_SH7757
-	depends on GPIOLIB
-	select PINCTRL_SH_PFC
+	select PINCTRL_SH_PFC_GPIO
 
 config PINCTRL_PFC_SH7785
 	def_bool y
 	depends on CPU_SUBTYPE_SH7785
-	depends on GPIOLIB
-	select PINCTRL_SH_PFC
+	select PINCTRL_SH_PFC_GPIO
 
 config PINCTRL_PFC_SH7786
 	def_bool y
 	depends on CPU_SUBTYPE_SH7786
-	depends on GPIOLIB
-	select PINCTRL_SH_PFC
+	select PINCTRL_SH_PFC_GPIO
 
 config PINCTRL_PFC_SHX3
 	def_bool y
 	depends on CPU_SUBTYPE_SHX3
-	depends on GPIOLIB
-	select PINCTRL_SH_PFC
-
+	select PINCTRL_SH_PFC_GPIO
 endif
diff --git a/drivers/pinctrl/sh-pfc/Makefile b/drivers/pinctrl/sh-pfc/Makefile
index 173305fa3811..8a2c8710fc93 100644
--- a/drivers/pinctrl/sh-pfc/Makefile
+++ b/drivers/pinctrl/sh-pfc/Makefile
@@ -1,8 +1,5 @@
-sh-pfc-objs			= core.o pinctrl.o
-ifeq ($(CONFIG_GPIO_SH_PFC),y)
-sh-pfc-objs			+= gpio.o
-endif
-obj-$(CONFIG_PINCTRL_SH_PFC)	+= sh-pfc.o
+obj-$(CONFIG_PINCTRL_SH_PFC)	+= core.o pinctrl.o
+obj-$(CONFIG_PINCTRL_SH_PFC_GPIO)	+= gpio.o
 obj-$(CONFIG_PINCTRL_PFC_EMEV2)	+= pfc-emev2.o
 obj-$(CONFIG_PINCTRL_PFC_R8A73A4)	+= pfc-r8a73a4.o
 obj-$(CONFIG_PINCTRL_PFC_R8A7740)	+= pfc-r8a7740.o
diff --git a/drivers/pinctrl/sh-pfc/core.c b/drivers/pinctrl/sh-pfc/core.c
index 181ea98a63b7..dc3609f0c60b 100644
--- a/drivers/pinctrl/sh-pfc/core.c
+++ b/drivers/pinctrl/sh-pfc/core.c
@@ -1,5 +1,7 @@
 /*
- * SuperH Pin Function Controller support.
+ * Pin Control and GPIO driver for SuperH Pin Function Controller.
+ *
+ * Authors: Magnus Damm, Paul Mundt, Laurent Pinchart
  *
  * Copyright (C) 2008 Magnus Damm
  * Copyright (C) 2009 - 2012 Paul Mundt
@@ -17,7 +19,7 @@
 #include <linux/io.h>
 #include <linux/ioport.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/pinctrl/machine.h>
@@ -503,7 +505,6 @@ static const struct of_device_id sh_pfc_of_table[] = {
 #endif
 	{ },
 };
-MODULE_DEVICE_TABLE(of, sh_pfc_of_table);
 #endif
 
 static int sh_pfc_probe(struct platform_device *pdev)
@@ -518,7 +519,7 @@ static int sh_pfc_probe(struct platform_device *pdev)
 
 #ifdef CONFIG_OF
 	if (np)
-		info = of_match_device(sh_pfc_of_table, &pdev->dev)->data;
+		info = of_device_get_match_data(&pdev->dev);
 	else
 #endif
 		info = platid ? (const void *)platid->driver_data : NULL;
@@ -558,7 +559,7 @@ static int sh_pfc_probe(struct platform_device *pdev)
 	if (unlikely(ret != 0))
 		return ret;
 
-#ifdef CONFIG_GPIO_SH_PFC
+#ifdef CONFIG_PINCTRL_SH_PFC_GPIO
 	/*
 	 * Then the GPIO chip
 	 */
@@ -584,7 +585,7 @@ static int sh_pfc_remove(struct platform_device *pdev)
 {
 	struct sh_pfc *pfc = platform_get_drvdata(pdev);
 
-#ifdef CONFIG_GPIO_SH_PFC
+#ifdef CONFIG_PINCTRL_SH_PFC_GPIO
 	sh_pfc_unregister_gpiochip(pfc);
 #endif
 	sh_pfc_unregister_pinctrl(pfc);
@@ -632,7 +633,6 @@ static const struct platform_device_id sh_pfc_id_table[] = {
 	{ "sh-pfc", 0 },
 	{ },
 };
-MODULE_DEVICE_TABLE(platform, sh_pfc_id_table);
 
 static struct platform_driver sh_pfc_driver = {
 	.probe		= sh_pfc_probe,
@@ -649,13 +649,3 @@ static int __init sh_pfc_init(void)
 	return platform_driver_register(&sh_pfc_driver);
 }
 postcore_initcall(sh_pfc_init);
-
-static void __exit sh_pfc_exit(void)
-{
-	platform_driver_unregister(&sh_pfc_driver);
-}
-module_exit(sh_pfc_exit);
-
-MODULE_AUTHOR("Magnus Damm, Paul Mundt, Laurent Pinchart");
-MODULE_DESCRIPTION("Pin Control and GPIO driver for SuperH pin function controller");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7778.c b/drivers/pinctrl/sh-pfc/pfc-r8a7778.c
index ad09a670c2ff..411d0887ba19 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7778.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7778.c
@@ -561,82 +561,82 @@ static const u16 pinmux_data[] = {
 	PINMUX_SINGLE(AVS2),
 
 	/* IPSR0 */
-	PINMUX_IPSR_DATA(IP0_1_0,	PRESETOUT),
-	PINMUX_IPSR_DATA(IP0_1_0,	PWM1),
+	PINMUX_IPSR_GPSR(IP0_1_0,	PRESETOUT),
+	PINMUX_IPSR_GPSR(IP0_1_0,	PWM1),
 
-	PINMUX_IPSR_DATA(IP0_4_2,	AUDATA0),
-	PINMUX_IPSR_DATA(IP0_4_2,	ARM_TRACEDATA_0),
+	PINMUX_IPSR_GPSR(IP0_4_2,	AUDATA0),
+	PINMUX_IPSR_GPSR(IP0_4_2,	ARM_TRACEDATA_0),
 	PINMUX_IPSR_MSEL(IP0_4_2,	GPSCLK_C,	SEL_GPS_C),
-	PINMUX_IPSR_DATA(IP0_4_2,	USB_OVC0),
-	PINMUX_IPSR_DATA(IP0_4_2,	TX2_E),
+	PINMUX_IPSR_GPSR(IP0_4_2,	USB_OVC0),
+	PINMUX_IPSR_GPSR(IP0_4_2,	TX2_E),
 	PINMUX_IPSR_MSEL(IP0_4_2,	SDA2_B,		SEL_I2C2_B),
 
-	PINMUX_IPSR_DATA(IP0_7_5,	AUDATA1),
-	PINMUX_IPSR_DATA(IP0_7_5,	ARM_TRACEDATA_1),
+	PINMUX_IPSR_GPSR(IP0_7_5,	AUDATA1),
+	PINMUX_IPSR_GPSR(IP0_7_5,	ARM_TRACEDATA_1),
 	PINMUX_IPSR_MSEL(IP0_7_5,	GPSIN_C,	SEL_GPS_C),
-	PINMUX_IPSR_DATA(IP0_7_5,	USB_OVC1),
+	PINMUX_IPSR_GPSR(IP0_7_5,	USB_OVC1),
 	PINMUX_IPSR_MSEL(IP0_7_5,	RX2_E,		SEL_SCIF2_E),
 	PINMUX_IPSR_MSEL(IP0_7_5,	SCL2_B,		SEL_I2C2_B),
 
 	PINMUX_IPSR_MSEL(IP0_11_8,	SD1_DAT2_A,	SEL_SD1_A),
-	PINMUX_IPSR_DATA(IP0_11_8,	MMC_D2),
-	PINMUX_IPSR_DATA(IP0_11_8,	BS),
-	PINMUX_IPSR_DATA(IP0_11_8,	ATADIR0_A),
-	PINMUX_IPSR_DATA(IP0_11_8,	SDSELF_A),
-	PINMUX_IPSR_DATA(IP0_11_8,	PWM4_B),
+	PINMUX_IPSR_GPSR(IP0_11_8,	MMC_D2),
+	PINMUX_IPSR_GPSR(IP0_11_8,	BS),
+	PINMUX_IPSR_GPSR(IP0_11_8,	ATADIR0_A),
+	PINMUX_IPSR_GPSR(IP0_11_8,	SDSELF_A),
+	PINMUX_IPSR_GPSR(IP0_11_8,	PWM4_B),
 
 	PINMUX_IPSR_MSEL(IP0_14_12,	SD1_DAT3_A,	SEL_SD1_A),
-	PINMUX_IPSR_DATA(IP0_14_12,	MMC_D3),
-	PINMUX_IPSR_DATA(IP0_14_12,	A0),
-	PINMUX_IPSR_DATA(IP0_14_12,	ATAG0_A),
+	PINMUX_IPSR_GPSR(IP0_14_12,	MMC_D3),
+	PINMUX_IPSR_GPSR(IP0_14_12,	A0),
+	PINMUX_IPSR_GPSR(IP0_14_12,	ATAG0_A),
 	PINMUX_IPSR_MSEL(IP0_14_12,	REMOCON_B,	SEL_REMOCON_B),
 
-	PINMUX_IPSR_DATA(IP0_15,	A4),
-	PINMUX_IPSR_DATA(IP0_16,	A5),
-	PINMUX_IPSR_DATA(IP0_17,	A6),
-	PINMUX_IPSR_DATA(IP0_18,	A7),
-	PINMUX_IPSR_DATA(IP0_19,	A8),
-	PINMUX_IPSR_DATA(IP0_20,	A9),
-	PINMUX_IPSR_DATA(IP0_21,	A10),
-	PINMUX_IPSR_DATA(IP0_22,	A11),
-	PINMUX_IPSR_DATA(IP0_23,	A12),
-	PINMUX_IPSR_DATA(IP0_24,	A13),
-	PINMUX_IPSR_DATA(IP0_25,	A14),
-	PINMUX_IPSR_DATA(IP0_26,	A15),
-	PINMUX_IPSR_DATA(IP0_27,	A16),
-	PINMUX_IPSR_DATA(IP0_28,	A17),
-	PINMUX_IPSR_DATA(IP0_29,	A18),
-	PINMUX_IPSR_DATA(IP0_30,	A19),
+	PINMUX_IPSR_GPSR(IP0_15,	A4),
+	PINMUX_IPSR_GPSR(IP0_16,	A5),
+	PINMUX_IPSR_GPSR(IP0_17,	A6),
+	PINMUX_IPSR_GPSR(IP0_18,	A7),
+	PINMUX_IPSR_GPSR(IP0_19,	A8),
+	PINMUX_IPSR_GPSR(IP0_20,	A9),
+	PINMUX_IPSR_GPSR(IP0_21,	A10),
+	PINMUX_IPSR_GPSR(IP0_22,	A11),
+	PINMUX_IPSR_GPSR(IP0_23,	A12),
+	PINMUX_IPSR_GPSR(IP0_24,	A13),
+	PINMUX_IPSR_GPSR(IP0_25,	A14),
+	PINMUX_IPSR_GPSR(IP0_26,	A15),
+	PINMUX_IPSR_GPSR(IP0_27,	A16),
+	PINMUX_IPSR_GPSR(IP0_28,	A17),
+	PINMUX_IPSR_GPSR(IP0_29,	A18),
+	PINMUX_IPSR_GPSR(IP0_30,	A19),
 
 	/* IPSR1 */
-	PINMUX_IPSR_DATA(IP1_0,		A20),
+	PINMUX_IPSR_GPSR(IP1_0,		A20),
 	PINMUX_IPSR_MSEL(IP1_0,		HSPI_CS1_B,	SEL_HSPI1_B),
 
-	PINMUX_IPSR_DATA(IP1_1,		A21),
+	PINMUX_IPSR_GPSR(IP1_1,		A21),
 	PINMUX_IPSR_MSEL(IP1_1,		HSPI_CLK1_B,	SEL_HSPI1_B),
 
-	PINMUX_IPSR_DATA(IP1_4_2,	A22),
+	PINMUX_IPSR_GPSR(IP1_4_2,	A22),
 	PINMUX_IPSR_MSEL(IP1_4_2,	HRTS0_B,	SEL_HSCIF0_B),
 	PINMUX_IPSR_MSEL(IP1_4_2,	RX2_B,		SEL_SCIF2_B),
 	PINMUX_IPSR_MSEL(IP1_4_2,	DREQ2_A,	SEL_DREQ2_A),
 
-	PINMUX_IPSR_DATA(IP1_7_5,	A23),
-	PINMUX_IPSR_DATA(IP1_7_5,	HTX0_B),
-	PINMUX_IPSR_DATA(IP1_7_5,	TX2_B),
-	PINMUX_IPSR_DATA(IP1_7_5,	DACK2_A),
+	PINMUX_IPSR_GPSR(IP1_7_5,	A23),
+	PINMUX_IPSR_GPSR(IP1_7_5,	HTX0_B),
+	PINMUX_IPSR_GPSR(IP1_7_5,	TX2_B),
+	PINMUX_IPSR_GPSR(IP1_7_5,	DACK2_A),
 	PINMUX_IPSR_MSEL(IP1_7_5,	TS_SDEN0_A,	SEL_TSIF0_A),
 
 	PINMUX_IPSR_MSEL(IP1_10_8,	SD1_CD_A,	SEL_SD1_A),
-	PINMUX_IPSR_DATA(IP1_10_8,	MMC_D6),
-	PINMUX_IPSR_DATA(IP1_10_8,	A24),
+	PINMUX_IPSR_GPSR(IP1_10_8,	MMC_D6),
+	PINMUX_IPSR_GPSR(IP1_10_8,	A24),
 	PINMUX_IPSR_MSEL(IP1_10_8,	DREQ1_A,	SEL_DREQ1_A),
 	PINMUX_IPSR_MSEL(IP1_10_8,	HRX0_B,		SEL_HSCIF0_B),
 	PINMUX_IPSR_MSEL(IP1_10_8,	TS_SPSYNC0_A,	SEL_TSIF0_A),
 
 	PINMUX_IPSR_MSEL(IP1_14_11,	SD1_WP_A,	SEL_SD1_A),
-	PINMUX_IPSR_DATA(IP1_14_11,	MMC_D7),
-	PINMUX_IPSR_DATA(IP1_14_11,	A25),
-	PINMUX_IPSR_DATA(IP1_14_11,	DACK1_A),
+	PINMUX_IPSR_GPSR(IP1_14_11,	MMC_D7),
+	PINMUX_IPSR_GPSR(IP1_14_11,	A25),
+	PINMUX_IPSR_GPSR(IP1_14_11,	DACK1_A),
 	PINMUX_IPSR_MSEL(IP1_14_11,	HCTS0_B,	SEL_HSCIF0_B),
 	PINMUX_IPSR_MSEL(IP1_14_11,	RX3_C,		SEL_SCIF3_C),
 	PINMUX_IPSR_MSEL(IP1_14_11,	TS_SDAT0_A,	SEL_TSIF0_A),
@@ -654,54 +654,54 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_NOGM(IP1_20_18,	SDA2_A,		SEL_I2C2_A),
 	PINMUX_IPSR_NOGM(IP1_20_18,	SCK2_B,		SEL_SCIF2_B),
 
-	PINMUX_IPSR_DATA(IP1_23_21,	MMC_D5),
-	PINMUX_IPSR_DATA(IP1_23_21,	ATADIR0_B),
-	PINMUX_IPSR_DATA(IP1_23_21,	RD_WR),
+	PINMUX_IPSR_GPSR(IP1_23_21,	MMC_D5),
+	PINMUX_IPSR_GPSR(IP1_23_21,	ATADIR0_B),
+	PINMUX_IPSR_GPSR(IP1_23_21,	RD_WR),
 
-	PINMUX_IPSR_DATA(IP1_24,	WE1),
-	PINMUX_IPSR_DATA(IP1_24,	ATAWR0_B),
+	PINMUX_IPSR_GPSR(IP1_24,	WE1),
+	PINMUX_IPSR_GPSR(IP1_24,	ATAWR0_B),
 
 	PINMUX_IPSR_MSEL(IP1_27_25,	SSI_WS1_B,	SEL_SSI1_B),
-	PINMUX_IPSR_DATA(IP1_27_25,	EX_CS0),
+	PINMUX_IPSR_GPSR(IP1_27_25,	EX_CS0),
 	PINMUX_IPSR_MSEL(IP1_27_25,	SCL2_A,		SEL_I2C2_A),
-	PINMUX_IPSR_DATA(IP1_27_25,	TX3_C),
+	PINMUX_IPSR_GPSR(IP1_27_25,	TX3_C),
 	PINMUX_IPSR_MSEL(IP1_27_25,	TS_SCK0_A,	SEL_TSIF0_A),
 
-	PINMUX_IPSR_DATA(IP1_29_28,	EX_CS1),
-	PINMUX_IPSR_DATA(IP1_29_28,	MMC_D4),
+	PINMUX_IPSR_GPSR(IP1_29_28,	EX_CS1),
+	PINMUX_IPSR_GPSR(IP1_29_28,	MMC_D4),
 
 	/* IPSR2 */
-	PINMUX_IPSR_DATA(IP2_2_0,	SD1_CLK_A),
-	PINMUX_IPSR_DATA(IP2_2_0,	MMC_CLK),
-	PINMUX_IPSR_DATA(IP2_2_0,	ATACS00),
-	PINMUX_IPSR_DATA(IP2_2_0,	EX_CS2),
+	PINMUX_IPSR_GPSR(IP2_2_0,	SD1_CLK_A),
+	PINMUX_IPSR_GPSR(IP2_2_0,	MMC_CLK),
+	PINMUX_IPSR_GPSR(IP2_2_0,	ATACS00),
+	PINMUX_IPSR_GPSR(IP2_2_0,	EX_CS2),
 
 	PINMUX_IPSR_MSEL(IP2_5_3,	SD1_CMD_A,	SEL_SD1_A),
-	PINMUX_IPSR_DATA(IP2_5_3,	MMC_CMD),
-	PINMUX_IPSR_DATA(IP2_5_3,	ATACS10),
-	PINMUX_IPSR_DATA(IP2_5_3,	EX_CS3),
+	PINMUX_IPSR_GPSR(IP2_5_3,	MMC_CMD),
+	PINMUX_IPSR_GPSR(IP2_5_3,	ATACS10),
+	PINMUX_IPSR_GPSR(IP2_5_3,	EX_CS3),
 
 	PINMUX_IPSR_MSEL(IP2_8_6,	SD1_DAT0_A,	SEL_SD1_A),
-	PINMUX_IPSR_DATA(IP2_8_6,	MMC_D0),
-	PINMUX_IPSR_DATA(IP2_8_6,	ATARD0),
-	PINMUX_IPSR_DATA(IP2_8_6,	EX_CS4),
+	PINMUX_IPSR_GPSR(IP2_8_6,	MMC_D0),
+	PINMUX_IPSR_GPSR(IP2_8_6,	ATARD0),
+	PINMUX_IPSR_GPSR(IP2_8_6,	EX_CS4),
 	PINMUX_IPSR_MSEL(IP2_8_6,	EX_WAIT1_A,	SEL_WAIT1_A),
 
 	PINMUX_IPSR_MSEL(IP2_11_9,	SD1_DAT1_A,	SEL_SD1_A),
-	PINMUX_IPSR_DATA(IP2_11_9,	MMC_D1),
-	PINMUX_IPSR_DATA(IP2_11_9,	ATAWR0_A),
-	PINMUX_IPSR_DATA(IP2_11_9,	EX_CS5),
+	PINMUX_IPSR_GPSR(IP2_11_9,	MMC_D1),
+	PINMUX_IPSR_GPSR(IP2_11_9,	ATAWR0_A),
+	PINMUX_IPSR_GPSR(IP2_11_9,	EX_CS5),
 	PINMUX_IPSR_MSEL(IP2_11_9,	EX_WAIT2_A,	SEL_WAIT2_A),
 
 	PINMUX_IPSR_MSEL(IP2_13_12,	DREQ0_A,	SEL_DREQ0_A),
 	PINMUX_IPSR_MSEL(IP2_13_12,	RX3_A,		SEL_SCIF3_A),
 
-	PINMUX_IPSR_DATA(IP2_16_14,	DACK0),
-	PINMUX_IPSR_DATA(IP2_16_14,	TX3_A),
-	PINMUX_IPSR_DATA(IP2_16_14,	DRACK0),
+	PINMUX_IPSR_GPSR(IP2_16_14,	DACK0),
+	PINMUX_IPSR_GPSR(IP2_16_14,	TX3_A),
+	PINMUX_IPSR_GPSR(IP2_16_14,	DRACK0),
 
-	PINMUX_IPSR_DATA(IP2_17,	EX_WAIT0),
-	PINMUX_IPSR_DATA(IP2_17,	PWM0_C),
+	PINMUX_IPSR_GPSR(IP2_17,	EX_WAIT0),
+	PINMUX_IPSR_GPSR(IP2_17,	PWM0_C),
 
 	PINMUX_IPSR_NOGP(IP2_18,	D0),
 	PINMUX_IPSR_NOGP(IP2_19,	D1),
@@ -716,33 +716,33 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_NOGP(IP2_28,	D10),
 	PINMUX_IPSR_NOGP(IP2_29,	D11),
 
-	PINMUX_IPSR_DATA(IP2_30,	RD_WR_B),
-	PINMUX_IPSR_DATA(IP2_30,	IRQ0),
+	PINMUX_IPSR_GPSR(IP2_30,	RD_WR_B),
+	PINMUX_IPSR_GPSR(IP2_30,	IRQ0),
 
-	PINMUX_IPSR_DATA(IP2_31,	MLB_CLK),
+	PINMUX_IPSR_GPSR(IP2_31,	MLB_CLK),
 	PINMUX_IPSR_MSEL(IP2_31,	IRQ1_A,		SEL_IRQ1_A),
 
 	/* IPSR3 */
-	PINMUX_IPSR_DATA(IP3_1_0,	MLB_SIG),
+	PINMUX_IPSR_GPSR(IP3_1_0,	MLB_SIG),
 	PINMUX_IPSR_MSEL(IP3_1_0,	RX5_B,		SEL_SCIF5_B),
 	PINMUX_IPSR_MSEL(IP3_1_0,	SDA3_A,		SEL_I2C3_A),
 	PINMUX_IPSR_MSEL(IP3_1_0,	IRQ2_A,		SEL_IRQ2_A),
 
-	PINMUX_IPSR_DATA(IP3_4_2,	MLB_DAT),
-	PINMUX_IPSR_DATA(IP3_4_2,	TX5_B),
+	PINMUX_IPSR_GPSR(IP3_4_2,	MLB_DAT),
+	PINMUX_IPSR_GPSR(IP3_4_2,	TX5_B),
 	PINMUX_IPSR_MSEL(IP3_4_2,	SCL3_A,		SEL_I2C3_A),
 	PINMUX_IPSR_MSEL(IP3_4_2,	IRQ3_A,		SEL_IRQ3_A),
-	PINMUX_IPSR_DATA(IP3_4_2,	SDSELF_B),
+	PINMUX_IPSR_GPSR(IP3_4_2,	SDSELF_B),
 
 	PINMUX_IPSR_MSEL(IP3_7_5,	SD1_CMD_B,	SEL_SD1_B),
-	PINMUX_IPSR_DATA(IP3_7_5,	SCIF_CLK),
-	PINMUX_IPSR_DATA(IP3_7_5,	AUDIO_CLKOUT_B),
+	PINMUX_IPSR_GPSR(IP3_7_5,	SCIF_CLK),
+	PINMUX_IPSR_GPSR(IP3_7_5,	AUDIO_CLKOUT_B),
 	PINMUX_IPSR_MSEL(IP3_7_5,	CAN_CLK_B,	SEL_CANCLK_B),
 	PINMUX_IPSR_MSEL(IP3_7_5,	SDA3_B,		SEL_I2C3_B),
 
-	PINMUX_IPSR_DATA(IP3_9_8,	SD1_CLK_B),
-	PINMUX_IPSR_DATA(IP3_9_8,	HTX0_A),
-	PINMUX_IPSR_DATA(IP3_9_8,	TX0_A),
+	PINMUX_IPSR_GPSR(IP3_9_8,	SD1_CLK_B),
+	PINMUX_IPSR_GPSR(IP3_9_8,	HTX0_A),
+	PINMUX_IPSR_GPSR(IP3_9_8,	TX0_A),
 
 	PINMUX_IPSR_MSEL(IP3_12_10,	SD1_DAT0_B,	SEL_SD1_B),
 	PINMUX_IPSR_MSEL(IP3_12_10,	HRX0_A,		SEL_HSCIF0_A),
@@ -750,513 +750,513 @@ static const u16 pinmux_data[] = {
 
 	PINMUX_IPSR_MSEL(IP3_15_13,	SD1_DAT1_B,	SEL_SD1_B),
 	PINMUX_IPSR_MSEL(IP3_15_13,	HSCK0,		SEL_HSCIF0_A),
-	PINMUX_IPSR_DATA(IP3_15_13,	SCK0),
+	PINMUX_IPSR_GPSR(IP3_15_13,	SCK0),
 	PINMUX_IPSR_MSEL(IP3_15_13,	SCL3_B,		SEL_I2C3_B),
 
 	PINMUX_IPSR_MSEL(IP3_18_16,	SD1_DAT2_B,	SEL_SD1_B),
 	PINMUX_IPSR_MSEL(IP3_18_16,	HCTS0_A,	SEL_HSCIF0_A),
-	PINMUX_IPSR_DATA(IP3_18_16,	CTS0),
+	PINMUX_IPSR_GPSR(IP3_18_16,	CTS0),
 
 	PINMUX_IPSR_MSEL(IP3_20_19,	SD1_DAT3_B,	SEL_SD1_B),
 	PINMUX_IPSR_MSEL(IP3_20_19,	HRTS0_A,	SEL_HSCIF0_A),
-	PINMUX_IPSR_DATA(IP3_20_19,	RTS0),
+	PINMUX_IPSR_GPSR(IP3_20_19,	RTS0),
 
-	PINMUX_IPSR_DATA(IP3_23_21,	SSI_SCK4),
-	PINMUX_IPSR_DATA(IP3_23_21,	DU0_DR0),
-	PINMUX_IPSR_DATA(IP3_23_21,	LCDOUT0),
-	PINMUX_IPSR_DATA(IP3_23_21,	AUDATA2),
-	PINMUX_IPSR_DATA(IP3_23_21,	ARM_TRACEDATA_2),
+	PINMUX_IPSR_GPSR(IP3_23_21,	SSI_SCK4),
+	PINMUX_IPSR_GPSR(IP3_23_21,	DU0_DR0),
+	PINMUX_IPSR_GPSR(IP3_23_21,	LCDOUT0),
+	PINMUX_IPSR_GPSR(IP3_23_21,	AUDATA2),
+	PINMUX_IPSR_GPSR(IP3_23_21,	ARM_TRACEDATA_2),
 	PINMUX_IPSR_MSEL(IP3_23_21,	SDA3_C,		SEL_I2C3_C),
-	PINMUX_IPSR_DATA(IP3_23_21,	ADICHS1),
+	PINMUX_IPSR_GPSR(IP3_23_21,	ADICHS1),
 	PINMUX_IPSR_MSEL(IP3_23_21,	TS_SDEN0_B,	SEL_TSIF0_B),
 
-	PINMUX_IPSR_DATA(IP3_26_24,	SSI_WS4),
-	PINMUX_IPSR_DATA(IP3_26_24,	DU0_DR1),
-	PINMUX_IPSR_DATA(IP3_26_24,	LCDOUT1),
-	PINMUX_IPSR_DATA(IP3_26_24,	AUDATA3),
-	PINMUX_IPSR_DATA(IP3_26_24,	ARM_TRACEDATA_3),
+	PINMUX_IPSR_GPSR(IP3_26_24,	SSI_WS4),
+	PINMUX_IPSR_GPSR(IP3_26_24,	DU0_DR1),
+	PINMUX_IPSR_GPSR(IP3_26_24,	LCDOUT1),
+	PINMUX_IPSR_GPSR(IP3_26_24,	AUDATA3),
+	PINMUX_IPSR_GPSR(IP3_26_24,	ARM_TRACEDATA_3),
 	PINMUX_IPSR_MSEL(IP3_26_24,	SCL3_C,		SEL_I2C3_C),
-	PINMUX_IPSR_DATA(IP3_26_24,	ADICHS2),
+	PINMUX_IPSR_GPSR(IP3_26_24,	ADICHS2),
 	PINMUX_IPSR_MSEL(IP3_26_24,	TS_SPSYNC0_B,	SEL_TSIF0_B),
 
-	PINMUX_IPSR_DATA(IP3_27,	DU0_DR2),
-	PINMUX_IPSR_DATA(IP3_27,	LCDOUT2),
+	PINMUX_IPSR_GPSR(IP3_27,	DU0_DR2),
+	PINMUX_IPSR_GPSR(IP3_27,	LCDOUT2),
 
-	PINMUX_IPSR_DATA(IP3_28,	DU0_DR3),
-	PINMUX_IPSR_DATA(IP3_28,	LCDOUT3),
+	PINMUX_IPSR_GPSR(IP3_28,	DU0_DR3),
+	PINMUX_IPSR_GPSR(IP3_28,	LCDOUT3),
 
-	PINMUX_IPSR_DATA(IP3_29,	DU0_DR4),
-	PINMUX_IPSR_DATA(IP3_29,	LCDOUT4),
+	PINMUX_IPSR_GPSR(IP3_29,	DU0_DR4),
+	PINMUX_IPSR_GPSR(IP3_29,	LCDOUT4),
 
-	PINMUX_IPSR_DATA(IP3_30,	DU0_DR5),
-	PINMUX_IPSR_DATA(IP3_30,	LCDOUT5),
+	PINMUX_IPSR_GPSR(IP3_30,	DU0_DR5),
+	PINMUX_IPSR_GPSR(IP3_30,	LCDOUT5),
 
-	PINMUX_IPSR_DATA(IP3_31,	DU0_DR6),
-	PINMUX_IPSR_DATA(IP3_31,	LCDOUT6),
+	PINMUX_IPSR_GPSR(IP3_31,	DU0_DR6),
+	PINMUX_IPSR_GPSR(IP3_31,	LCDOUT6),
 
 	/* IPSR4 */
-	PINMUX_IPSR_DATA(IP4_0,		DU0_DR7),
-	PINMUX_IPSR_DATA(IP4_0,		LCDOUT7),
-
-	PINMUX_IPSR_DATA(IP4_3_1,	DU0_DG0),
-	PINMUX_IPSR_DATA(IP4_3_1,	LCDOUT8),
-	PINMUX_IPSR_DATA(IP4_3_1,	AUDATA4),
-	PINMUX_IPSR_DATA(IP4_3_1,	ARM_TRACEDATA_4),
-	PINMUX_IPSR_DATA(IP4_3_1,	TX1_D),
-	PINMUX_IPSR_DATA(IP4_3_1,	CAN0_TX_A),
-	PINMUX_IPSR_DATA(IP4_3_1,	ADICHS0),
-
-	PINMUX_IPSR_DATA(IP4_6_4,	DU0_DG1),
-	PINMUX_IPSR_DATA(IP4_6_4,	LCDOUT9),
-	PINMUX_IPSR_DATA(IP4_6_4,	AUDATA5),
-	PINMUX_IPSR_DATA(IP4_6_4,	ARM_TRACEDATA_5),
+	PINMUX_IPSR_GPSR(IP4_0,		DU0_DR7),
+	PINMUX_IPSR_GPSR(IP4_0,		LCDOUT7),
+
+	PINMUX_IPSR_GPSR(IP4_3_1,	DU0_DG0),
+	PINMUX_IPSR_GPSR(IP4_3_1,	LCDOUT8),
+	PINMUX_IPSR_GPSR(IP4_3_1,	AUDATA4),
+	PINMUX_IPSR_GPSR(IP4_3_1,	ARM_TRACEDATA_4),
+	PINMUX_IPSR_GPSR(IP4_3_1,	TX1_D),
+	PINMUX_IPSR_GPSR(IP4_3_1,	CAN0_TX_A),
+	PINMUX_IPSR_GPSR(IP4_3_1,	ADICHS0),
+
+	PINMUX_IPSR_GPSR(IP4_6_4,	DU0_DG1),
+	PINMUX_IPSR_GPSR(IP4_6_4,	LCDOUT9),
+	PINMUX_IPSR_GPSR(IP4_6_4,	AUDATA5),
+	PINMUX_IPSR_GPSR(IP4_6_4,	ARM_TRACEDATA_5),
 	PINMUX_IPSR_MSEL(IP4_6_4,	RX1_D,		SEL_SCIF1_D),
 	PINMUX_IPSR_MSEL(IP4_6_4,	CAN0_RX_A,	SEL_CAN0_A),
-	PINMUX_IPSR_DATA(IP4_6_4,	ADIDATA),
+	PINMUX_IPSR_GPSR(IP4_6_4,	ADIDATA),
 
-	PINMUX_IPSR_DATA(IP4_7,		DU0_DG2),
-	PINMUX_IPSR_DATA(IP4_7,		LCDOUT10),
+	PINMUX_IPSR_GPSR(IP4_7,		DU0_DG2),
+	PINMUX_IPSR_GPSR(IP4_7,		LCDOUT10),
 
-	PINMUX_IPSR_DATA(IP4_8,		DU0_DG3),
-	PINMUX_IPSR_DATA(IP4_8,		LCDOUT11),
+	PINMUX_IPSR_GPSR(IP4_8,		DU0_DG3),
+	PINMUX_IPSR_GPSR(IP4_8,		LCDOUT11),
 
-	PINMUX_IPSR_DATA(IP4_10_9,	DU0_DG4),
-	PINMUX_IPSR_DATA(IP4_10_9,	LCDOUT12),
+	PINMUX_IPSR_GPSR(IP4_10_9,	DU0_DG4),
+	PINMUX_IPSR_GPSR(IP4_10_9,	LCDOUT12),
 	PINMUX_IPSR_MSEL(IP4_10_9,	RX0_B,		SEL_SCIF0_B),
 
-	PINMUX_IPSR_DATA(IP4_12_11,	DU0_DG5),
-	PINMUX_IPSR_DATA(IP4_12_11,	LCDOUT13),
-	PINMUX_IPSR_DATA(IP4_12_11,	TX0_B),
+	PINMUX_IPSR_GPSR(IP4_12_11,	DU0_DG5),
+	PINMUX_IPSR_GPSR(IP4_12_11,	LCDOUT13),
+	PINMUX_IPSR_GPSR(IP4_12_11,	TX0_B),
 
-	PINMUX_IPSR_DATA(IP4_14_13,	DU0_DG6),
-	PINMUX_IPSR_DATA(IP4_14_13,	LCDOUT14),
+	PINMUX_IPSR_GPSR(IP4_14_13,	DU0_DG6),
+	PINMUX_IPSR_GPSR(IP4_14_13,	LCDOUT14),
 	PINMUX_IPSR_MSEL(IP4_14_13,	RX4_A,		SEL_SCIF4_A),
 
-	PINMUX_IPSR_DATA(IP4_16_15,	DU0_DG7),
-	PINMUX_IPSR_DATA(IP4_16_15,	LCDOUT15),
-	PINMUX_IPSR_DATA(IP4_16_15,	TX4_A),
+	PINMUX_IPSR_GPSR(IP4_16_15,	DU0_DG7),
+	PINMUX_IPSR_GPSR(IP4_16_15,	LCDOUT15),
+	PINMUX_IPSR_GPSR(IP4_16_15,	TX4_A),
 
 	PINMUX_IPSR_MSEL(IP4_20_17,	SSI_SCK2_B,	SEL_SSI2_B),
 	PINMUX_DATA(VI0_R0_B_MARK,	FN_IP4_20_17,	FN_VI0_R0_B,	FN_SEL_VI0_B), /* see sel_vi0 */
 	PINMUX_DATA(VI0_R0_D_MARK,	FN_IP4_20_17,	FN_VI0_R0_B,	FN_SEL_VI0_D), /* see sel_vi0 */
-	PINMUX_IPSR_DATA(IP4_20_17,	DU0_DB0),
-	PINMUX_IPSR_DATA(IP4_20_17,	LCDOUT16),
-	PINMUX_IPSR_DATA(IP4_20_17,	AUDATA6),
-	PINMUX_IPSR_DATA(IP4_20_17,	ARM_TRACEDATA_6),
+	PINMUX_IPSR_GPSR(IP4_20_17,	DU0_DB0),
+	PINMUX_IPSR_GPSR(IP4_20_17,	LCDOUT16),
+	PINMUX_IPSR_GPSR(IP4_20_17,	AUDATA6),
+	PINMUX_IPSR_GPSR(IP4_20_17,	ARM_TRACEDATA_6),
 	PINMUX_IPSR_MSEL(IP4_20_17,	GPSCLK_A,	SEL_GPS_A),
-	PINMUX_IPSR_DATA(IP4_20_17,	PWM0_A),
-	PINMUX_IPSR_DATA(IP4_20_17,	ADICLK),
+	PINMUX_IPSR_GPSR(IP4_20_17,	PWM0_A),
+	PINMUX_IPSR_GPSR(IP4_20_17,	ADICLK),
 	PINMUX_IPSR_MSEL(IP4_20_17,	TS_SDAT0_B,	SEL_TSIF0_B),
 
-	PINMUX_IPSR_DATA(IP4_24_21,	AUDIO_CLKC),
+	PINMUX_IPSR_GPSR(IP4_24_21,	AUDIO_CLKC),
 	PINMUX_DATA(VI0_R1_B_MARK,	FN_IP4_24_21,	FN_VI0_R1_B,	FN_SEL_VI0_B), /* see sel_vi0 */
 	PINMUX_DATA(VI0_R1_D_MARK,	FN_IP4_24_21,	FN_VI0_R1_B,	FN_SEL_VI0_D), /* see sel_vi0 */
-	PINMUX_IPSR_DATA(IP4_24_21,	DU0_DB1),
-	PINMUX_IPSR_DATA(IP4_24_21,	LCDOUT17),
-	PINMUX_IPSR_DATA(IP4_24_21,	AUDATA7),
-	PINMUX_IPSR_DATA(IP4_24_21,	ARM_TRACEDATA_7),
+	PINMUX_IPSR_GPSR(IP4_24_21,	DU0_DB1),
+	PINMUX_IPSR_GPSR(IP4_24_21,	LCDOUT17),
+	PINMUX_IPSR_GPSR(IP4_24_21,	AUDATA7),
+	PINMUX_IPSR_GPSR(IP4_24_21,	ARM_TRACEDATA_7),
 	PINMUX_IPSR_MSEL(IP4_24_21,	GPSIN_A,	SEL_GPS_A),
-	PINMUX_IPSR_DATA(IP4_24_21,	ADICS_SAMP),
+	PINMUX_IPSR_GPSR(IP4_24_21,	ADICS_SAMP),
 	PINMUX_IPSR_MSEL(IP4_24_21,	TS_SCK0_B,	SEL_TSIF0_B),
 
 	PINMUX_DATA(VI0_R2_B_MARK,	FN_IP4_26_25,	FN_VI0_R2_B,	FN_SEL_VI0_B), /* see sel_vi0 */
 	PINMUX_DATA(VI0_R2_D_MARK,	FN_IP4_26_25,	FN_VI0_R2_B,	FN_SEL_VI0_D), /* see sel_vi0 */
-	PINMUX_IPSR_DATA(IP4_26_25,	DU0_DB2),
-	PINMUX_IPSR_DATA(IP4_26_25,	LCDOUT18),
+	PINMUX_IPSR_GPSR(IP4_26_25,	DU0_DB2),
+	PINMUX_IPSR_GPSR(IP4_26_25,	LCDOUT18),
 
 	PINMUX_IPSR_MSEL(IP4_28_27,	VI0_R3_B,	SEL_VI0_B),
-	PINMUX_IPSR_DATA(IP4_28_27,	DU0_DB3),
-	PINMUX_IPSR_DATA(IP4_28_27,	LCDOUT19),
+	PINMUX_IPSR_GPSR(IP4_28_27,	DU0_DB3),
+	PINMUX_IPSR_GPSR(IP4_28_27,	LCDOUT19),
 
 	PINMUX_DATA(VI0_R4_B_MARK,	FN_IP4_30_29,	FN_VI0_R4_B,	FN_SEL_VI0_B), /* see sel_vi0 */
 	PINMUX_DATA(VI0_R4_D_MARK,	FN_IP4_30_29,	FN_VI0_R4_B,	FN_SEL_VI0_D), /* see sel_vi0 */
-	PINMUX_IPSR_DATA(IP4_30_29,	DU0_DB4),
-	PINMUX_IPSR_DATA(IP4_30_29,	LCDOUT20),
+	PINMUX_IPSR_GPSR(IP4_30_29,	DU0_DB4),
+	PINMUX_IPSR_GPSR(IP4_30_29,	LCDOUT20),
 
 	/* IPSR5 */
 	PINMUX_DATA(VI0_R5_B_MARK,	FN_IP5_1_0,	FN_VI0_R5_B,	FN_SEL_VI0_B), /* see sel_vi0 */
 	PINMUX_DATA(VI0_R5_D_MARK,	FN_IP5_1_0,	FN_VI0_R5_B,	FN_SEL_VI0_D), /* see sel_vi0 */
-	PINMUX_IPSR_DATA(IP5_1_0,	DU0_DB5),
-	PINMUX_IPSR_DATA(IP5_1_0,	LCDOUT21),
+	PINMUX_IPSR_GPSR(IP5_1_0,	DU0_DB5),
+	PINMUX_IPSR_GPSR(IP5_1_0,	LCDOUT21),
 
 	PINMUX_IPSR_MSEL(IP5_3_2,	VI1_DATA10_B,	SEL_VI1_B),
-	PINMUX_IPSR_DATA(IP5_3_2,	DU0_DB6),
-	PINMUX_IPSR_DATA(IP5_3_2,	LCDOUT22),
+	PINMUX_IPSR_GPSR(IP5_3_2,	DU0_DB6),
+	PINMUX_IPSR_GPSR(IP5_3_2,	LCDOUT22),
 
 	PINMUX_IPSR_MSEL(IP5_5_4,	VI1_DATA11_B,	SEL_VI1_B),
-	PINMUX_IPSR_DATA(IP5_5_4,	DU0_DB7),
-	PINMUX_IPSR_DATA(IP5_5_4,	LCDOUT23),
+	PINMUX_IPSR_GPSR(IP5_5_4,	DU0_DB7),
+	PINMUX_IPSR_GPSR(IP5_5_4,	LCDOUT23),
 
-	PINMUX_IPSR_DATA(IP5_6,		DU0_DOTCLKIN),
-	PINMUX_IPSR_DATA(IP5_6,		QSTVA_QVS),
+	PINMUX_IPSR_GPSR(IP5_6,		DU0_DOTCLKIN),
+	PINMUX_IPSR_GPSR(IP5_6,		QSTVA_QVS),
 
-	PINMUX_IPSR_DATA(IP5_7,		DU0_DOTCLKO_UT0),
-	PINMUX_IPSR_DATA(IP5_7,		QCLK),
+	PINMUX_IPSR_GPSR(IP5_7,		DU0_DOTCLKO_UT0),
+	PINMUX_IPSR_GPSR(IP5_7,		QCLK),
 
-	PINMUX_IPSR_DATA(IP5_9_8,	DU0_DOTCLKO_UT1),
-	PINMUX_IPSR_DATA(IP5_9_8,	QSTVB_QVE),
-	PINMUX_IPSR_DATA(IP5_9_8,	AUDIO_CLKOUT_A),
+	PINMUX_IPSR_GPSR(IP5_9_8,	DU0_DOTCLKO_UT1),
+	PINMUX_IPSR_GPSR(IP5_9_8,	QSTVB_QVE),
+	PINMUX_IPSR_GPSR(IP5_9_8,	AUDIO_CLKOUT_A),
 	PINMUX_IPSR_MSEL(IP5_9_8,	REMOCON_C,	SEL_REMOCON_C),
 
 	PINMUX_IPSR_MSEL(IP5_11_10,	SSI_WS2_B,	SEL_SSI2_B),
-	PINMUX_IPSR_DATA(IP5_11_10,	DU0_EXHSYNC_DU0_HSYNC),
-	PINMUX_IPSR_DATA(IP5_11_10,	QSTH_QHS),
+	PINMUX_IPSR_GPSR(IP5_11_10,	DU0_EXHSYNC_DU0_HSYNC),
+	PINMUX_IPSR_GPSR(IP5_11_10,	QSTH_QHS),
 
-	PINMUX_IPSR_DATA(IP5_12,	DU0_EXVSYNC_DU0_VSYNC),
-	PINMUX_IPSR_DATA(IP5_12,	QSTB_QHE),
+	PINMUX_IPSR_GPSR(IP5_12,	DU0_EXVSYNC_DU0_VSYNC),
+	PINMUX_IPSR_GPSR(IP5_12,	QSTB_QHE),
 
-	PINMUX_IPSR_DATA(IP5_14_13,	DU0_EXODDF_DU0_ODDF_DISP_CDE),
-	PINMUX_IPSR_DATA(IP5_14_13,	QCPV_QDE),
+	PINMUX_IPSR_GPSR(IP5_14_13,	DU0_EXODDF_DU0_ODDF_DISP_CDE),
+	PINMUX_IPSR_GPSR(IP5_14_13,	QCPV_QDE),
 	PINMUX_IPSR_MSEL(IP5_14_13,	FMCLK_D,	SEL_FM_D),
 
 	PINMUX_IPSR_MSEL(IP5_17_15,	SSI_SCK1_A,	SEL_SSI1_A),
-	PINMUX_IPSR_DATA(IP5_17_15,	DU0_DISP),
-	PINMUX_IPSR_DATA(IP5_17_15,	QPOLA),
-	PINMUX_IPSR_DATA(IP5_17_15,	AUDCK),
-	PINMUX_IPSR_DATA(IP5_17_15,	ARM_TRACECLK),
-	PINMUX_IPSR_DATA(IP5_17_15,	BPFCLK_D),
+	PINMUX_IPSR_GPSR(IP5_17_15,	DU0_DISP),
+	PINMUX_IPSR_GPSR(IP5_17_15,	QPOLA),
+	PINMUX_IPSR_GPSR(IP5_17_15,	AUDCK),
+	PINMUX_IPSR_GPSR(IP5_17_15,	ARM_TRACECLK),
+	PINMUX_IPSR_GPSR(IP5_17_15,	BPFCLK_D),
 
 	PINMUX_IPSR_MSEL(IP5_20_18,	SSI_WS1_A,	SEL_SSI1_A),
-	PINMUX_IPSR_DATA(IP5_20_18,	DU0_CDE),
-	PINMUX_IPSR_DATA(IP5_20_18,	QPOLB),
-	PINMUX_IPSR_DATA(IP5_20_18,	AUDSYNC),
-	PINMUX_IPSR_DATA(IP5_20_18,	ARM_TRACECTL),
+	PINMUX_IPSR_GPSR(IP5_20_18,	DU0_CDE),
+	PINMUX_IPSR_GPSR(IP5_20_18,	QPOLB),
+	PINMUX_IPSR_GPSR(IP5_20_18,	AUDSYNC),
+	PINMUX_IPSR_GPSR(IP5_20_18,	ARM_TRACECTL),
 	PINMUX_IPSR_MSEL(IP5_20_18,	FMIN_D,		SEL_FM_D),
 
 	PINMUX_IPSR_MSEL(IP5_22_21,	SD1_CD_B,	SEL_SD1_B),
-	PINMUX_IPSR_DATA(IP5_22_21,	SSI_SCK78),
+	PINMUX_IPSR_GPSR(IP5_22_21,	SSI_SCK78),
 	PINMUX_IPSR_MSEL(IP5_22_21,	HSPI_RX0_B,	SEL_HSPI0_B),
-	PINMUX_IPSR_DATA(IP5_22_21,	TX1_B),
+	PINMUX_IPSR_GPSR(IP5_22_21,	TX1_B),
 
 	PINMUX_IPSR_MSEL(IP5_25_23,	SD1_WP_B,	SEL_SD1_B),
-	PINMUX_IPSR_DATA(IP5_25_23,	SSI_WS78),
+	PINMUX_IPSR_GPSR(IP5_25_23,	SSI_WS78),
 	PINMUX_IPSR_MSEL(IP5_25_23,	HSPI_CLK0_B,	SEL_HSPI0_B),
 	PINMUX_IPSR_MSEL(IP5_25_23,	RX1_B,		SEL_SCIF1_B),
 	PINMUX_IPSR_MSEL(IP5_25_23,	CAN_CLK_D,	SEL_CANCLK_D),
 
-	PINMUX_IPSR_DATA(IP5_28_26,	SSI_SDATA8),
+	PINMUX_IPSR_GPSR(IP5_28_26,	SSI_SDATA8),
 	PINMUX_IPSR_MSEL(IP5_28_26,	SSI_SCK2_A,	SEL_SSI2_A),
 	PINMUX_IPSR_MSEL(IP5_28_26,	HSPI_CS0_B,	SEL_HSPI0_B),
-	PINMUX_IPSR_DATA(IP5_28_26,	TX2_A),
-	PINMUX_IPSR_DATA(IP5_28_26,	CAN0_TX_B),
+	PINMUX_IPSR_GPSR(IP5_28_26,	TX2_A),
+	PINMUX_IPSR_GPSR(IP5_28_26,	CAN0_TX_B),
 
-	PINMUX_IPSR_DATA(IP5_30_29,	SSI_SDATA7),
-	PINMUX_IPSR_DATA(IP5_30_29,	HSPI_TX0_B),
+	PINMUX_IPSR_GPSR(IP5_30_29,	SSI_SDATA7),
+	PINMUX_IPSR_GPSR(IP5_30_29,	HSPI_TX0_B),
 	PINMUX_IPSR_MSEL(IP5_30_29,	RX2_A,		SEL_SCIF2_A),
 	PINMUX_IPSR_MSEL(IP5_30_29,	CAN0_RX_B,	SEL_CAN0_B),
 
 	/* IPSR6 */
-	PINMUX_IPSR_DATA(IP6_1_0,	SSI_SCK6),
+	PINMUX_IPSR_GPSR(IP6_1_0,	SSI_SCK6),
 	PINMUX_IPSR_MSEL(IP6_1_0,	HSPI_RX2_A,	SEL_HSPI2_A),
 	PINMUX_IPSR_MSEL(IP6_1_0,	FMCLK_B,	SEL_FM_B),
-	PINMUX_IPSR_DATA(IP6_1_0,	CAN1_TX_B),
+	PINMUX_IPSR_GPSR(IP6_1_0,	CAN1_TX_B),
 
-	PINMUX_IPSR_DATA(IP6_4_2,	SSI_WS6),
+	PINMUX_IPSR_GPSR(IP6_4_2,	SSI_WS6),
 	PINMUX_IPSR_MSEL(IP6_4_2,	HSPI_CLK2_A,	SEL_HSPI2_A),
-	PINMUX_IPSR_DATA(IP6_4_2,	BPFCLK_B),
+	PINMUX_IPSR_GPSR(IP6_4_2,	BPFCLK_B),
 	PINMUX_IPSR_MSEL(IP6_4_2,	CAN1_RX_B,	SEL_CAN1_B),
 
-	PINMUX_IPSR_DATA(IP6_6_5,	SSI_SDATA6),
-	PINMUX_IPSR_DATA(IP6_6_5,	HSPI_TX2_A),
+	PINMUX_IPSR_GPSR(IP6_6_5,	SSI_SDATA6),
+	PINMUX_IPSR_GPSR(IP6_6_5,	HSPI_TX2_A),
 	PINMUX_IPSR_MSEL(IP6_6_5,	FMIN_B,		SEL_FM_B),
 
-	PINMUX_IPSR_DATA(IP6_7,		SSI_SCK5),
+	PINMUX_IPSR_GPSR(IP6_7,		SSI_SCK5),
 	PINMUX_IPSR_MSEL(IP6_7,		RX4_C,		SEL_SCIF4_C),
 
-	PINMUX_IPSR_DATA(IP6_8,		SSI_WS5),
-	PINMUX_IPSR_DATA(IP6_8,		TX4_C),
+	PINMUX_IPSR_GPSR(IP6_8,		SSI_WS5),
+	PINMUX_IPSR_GPSR(IP6_8,		TX4_C),
 
-	PINMUX_IPSR_DATA(IP6_9,		SSI_SDATA5),
+	PINMUX_IPSR_GPSR(IP6_9,		SSI_SDATA5),
 	PINMUX_IPSR_MSEL(IP6_9,		RX0_D,		SEL_SCIF0_D),
 
-	PINMUX_IPSR_DATA(IP6_10,	SSI_WS34),
-	PINMUX_IPSR_DATA(IP6_10,	ARM_TRACEDATA_8),
+	PINMUX_IPSR_GPSR(IP6_10,	SSI_WS34),
+	PINMUX_IPSR_GPSR(IP6_10,	ARM_TRACEDATA_8),
 
-	PINMUX_IPSR_DATA(IP6_12_11,	SSI_SDATA4),
+	PINMUX_IPSR_GPSR(IP6_12_11,	SSI_SDATA4),
 	PINMUX_IPSR_MSEL(IP6_12_11,	SSI_WS2_A,	SEL_SSI2_A),
-	PINMUX_IPSR_DATA(IP6_12_11,	ARM_TRACEDATA_9),
+	PINMUX_IPSR_GPSR(IP6_12_11,	ARM_TRACEDATA_9),
 
-	PINMUX_IPSR_DATA(IP6_13,	SSI_SDATA3),
-	PINMUX_IPSR_DATA(IP6_13,	ARM_TRACEDATA_10),
+	PINMUX_IPSR_GPSR(IP6_13,	SSI_SDATA3),
+	PINMUX_IPSR_GPSR(IP6_13,	ARM_TRACEDATA_10),
 
-	PINMUX_IPSR_DATA(IP6_15_14,	SSI_SCK012),
-	PINMUX_IPSR_DATA(IP6_15_14,	ARM_TRACEDATA_11),
-	PINMUX_IPSR_DATA(IP6_15_14,	TX0_D),
+	PINMUX_IPSR_GPSR(IP6_15_14,	SSI_SCK012),
+	PINMUX_IPSR_GPSR(IP6_15_14,	ARM_TRACEDATA_11),
+	PINMUX_IPSR_GPSR(IP6_15_14,	TX0_D),
 
-	PINMUX_IPSR_DATA(IP6_16,	SSI_WS012),
-	PINMUX_IPSR_DATA(IP6_16,	ARM_TRACEDATA_12),
+	PINMUX_IPSR_GPSR(IP6_16,	SSI_WS012),
+	PINMUX_IPSR_GPSR(IP6_16,	ARM_TRACEDATA_12),
 
-	PINMUX_IPSR_DATA(IP6_18_17,	SSI_SDATA2),
+	PINMUX_IPSR_GPSR(IP6_18_17,	SSI_SDATA2),
 	PINMUX_IPSR_MSEL(IP6_18_17,	HSPI_CS2_A,	SEL_HSPI2_A),
-	PINMUX_IPSR_DATA(IP6_18_17,	ARM_TRACEDATA_13),
+	PINMUX_IPSR_GPSR(IP6_18_17,	ARM_TRACEDATA_13),
 	PINMUX_IPSR_MSEL(IP6_18_17,	SDA1_A,		SEL_I2C1_A),
 
-	PINMUX_IPSR_DATA(IP6_20_19,	SSI_SDATA1),
-	PINMUX_IPSR_DATA(IP6_20_19,	ARM_TRACEDATA_14),
+	PINMUX_IPSR_GPSR(IP6_20_19,	SSI_SDATA1),
+	PINMUX_IPSR_GPSR(IP6_20_19,	ARM_TRACEDATA_14),
 	PINMUX_IPSR_MSEL(IP6_20_19,	SCL1_A,		SEL_I2C1_A),
 	PINMUX_IPSR_MSEL(IP6_20_19,	SCK2_A,		SEL_SCIF2_A),
 
-	PINMUX_IPSR_DATA(IP6_21,	SSI_SDATA0),
-	PINMUX_IPSR_DATA(IP6_21,	ARM_TRACEDATA_15),
+	PINMUX_IPSR_GPSR(IP6_21,	SSI_SDATA0),
+	PINMUX_IPSR_GPSR(IP6_21,	ARM_TRACEDATA_15),
 
-	PINMUX_IPSR_DATA(IP6_23_22,	SD0_CLK),
-	PINMUX_IPSR_DATA(IP6_23_22,	SUB_TDO),
+	PINMUX_IPSR_GPSR(IP6_23_22,	SD0_CLK),
+	PINMUX_IPSR_GPSR(IP6_23_22,	SUB_TDO),
 
-	PINMUX_IPSR_DATA(IP6_25_24,	SD0_CMD),
-	PINMUX_IPSR_DATA(IP6_25_24,	SUB_TRST),
+	PINMUX_IPSR_GPSR(IP6_25_24,	SD0_CMD),
+	PINMUX_IPSR_GPSR(IP6_25_24,	SUB_TRST),
 
-	PINMUX_IPSR_DATA(IP6_27_26,	SD0_DAT0),
-	PINMUX_IPSR_DATA(IP6_27_26,	SUB_TMS),
+	PINMUX_IPSR_GPSR(IP6_27_26,	SD0_DAT0),
+	PINMUX_IPSR_GPSR(IP6_27_26,	SUB_TMS),
 
-	PINMUX_IPSR_DATA(IP6_29_28,	SD0_DAT1),
-	PINMUX_IPSR_DATA(IP6_29_28,	SUB_TCK),
+	PINMUX_IPSR_GPSR(IP6_29_28,	SD0_DAT1),
+	PINMUX_IPSR_GPSR(IP6_29_28,	SUB_TCK),
 
-	PINMUX_IPSR_DATA(IP6_31_30,	SD0_DAT2),
-	PINMUX_IPSR_DATA(IP6_31_30,	SUB_TDI),
+	PINMUX_IPSR_GPSR(IP6_31_30,	SD0_DAT2),
+	PINMUX_IPSR_GPSR(IP6_31_30,	SUB_TDI),
 
 	/* IPSR7 */
-	PINMUX_IPSR_DATA(IP7_1_0,	SD0_DAT3),
+	PINMUX_IPSR_GPSR(IP7_1_0,	SD0_DAT3),
 	PINMUX_IPSR_MSEL(IP7_1_0,	IRQ1_B,		SEL_IRQ1_B),
 
-	PINMUX_IPSR_DATA(IP7_3_2,	SD0_CD),
-	PINMUX_IPSR_DATA(IP7_3_2,	TX5_A),
+	PINMUX_IPSR_GPSR(IP7_3_2,	SD0_CD),
+	PINMUX_IPSR_GPSR(IP7_3_2,	TX5_A),
 
-	PINMUX_IPSR_DATA(IP7_5_4,	SD0_WP),
+	PINMUX_IPSR_GPSR(IP7_5_4,	SD0_WP),
 	PINMUX_IPSR_MSEL(IP7_5_4,	RX5_A,		SEL_SCIF5_A),
 
-	PINMUX_IPSR_DATA(IP7_8_6,	VI1_CLKENB),
+	PINMUX_IPSR_GPSR(IP7_8_6,	VI1_CLKENB),
 	PINMUX_IPSR_MSEL(IP7_8_6,	HSPI_CLK0_A,	SEL_HSPI0_A),
-	PINMUX_IPSR_DATA(IP7_8_6,	HTX1_A),
+	PINMUX_IPSR_GPSR(IP7_8_6,	HTX1_A),
 	PINMUX_IPSR_MSEL(IP7_8_6,	RTS1_C,		SEL_SCIF1_C),
 
-	PINMUX_IPSR_DATA(IP7_11_9,	VI1_FIELD),
+	PINMUX_IPSR_GPSR(IP7_11_9,	VI1_FIELD),
 	PINMUX_IPSR_MSEL(IP7_11_9,	HSPI_CS0_A,	SEL_HSPI0_A),
 	PINMUX_IPSR_MSEL(IP7_11_9,	HRX1_A,		SEL_HSCIF1_A),
 	PINMUX_IPSR_MSEL(IP7_11_9,	SCK1_C,		SEL_SCIF1_C),
 
-	PINMUX_IPSR_DATA(IP7_14_12,	VI1_HSYNC),
+	PINMUX_IPSR_GPSR(IP7_14_12,	VI1_HSYNC),
 	PINMUX_IPSR_MSEL(IP7_14_12,	HSPI_RX0_A,	SEL_HSPI0_A),
 	PINMUX_IPSR_MSEL(IP7_14_12,	HRTS1_A,	SEL_HSCIF1_A),
 	PINMUX_IPSR_MSEL(IP7_14_12,	FMCLK_A,	SEL_FM_A),
 	PINMUX_IPSR_MSEL(IP7_14_12,	RX1_C,		SEL_SCIF1_C),
 
-	PINMUX_IPSR_DATA(IP7_17_15,	VI1_VSYNC),
-	PINMUX_IPSR_DATA(IP7_17_15,	HSPI_TX0),
+	PINMUX_IPSR_GPSR(IP7_17_15,	VI1_VSYNC),
+	PINMUX_IPSR_GPSR(IP7_17_15,	HSPI_TX0),
 	PINMUX_IPSR_MSEL(IP7_17_15,	HCTS1_A,	SEL_HSCIF1_A),
-	PINMUX_IPSR_DATA(IP7_17_15,	BPFCLK_A),
-	PINMUX_IPSR_DATA(IP7_17_15,	TX1_C),
+	PINMUX_IPSR_GPSR(IP7_17_15,	BPFCLK_A),
+	PINMUX_IPSR_GPSR(IP7_17_15,	TX1_C),
 
-	PINMUX_IPSR_DATA(IP7_20_18,	TCLK0),
+	PINMUX_IPSR_GPSR(IP7_20_18,	TCLK0),
 	PINMUX_IPSR_MSEL(IP7_20_18,	HSCK1_A,	SEL_HSCIF1_A),
 	PINMUX_IPSR_MSEL(IP7_20_18,	FMIN_A,		SEL_FM_A),
 	PINMUX_IPSR_MSEL(IP7_20_18,	IRQ2_C,		SEL_IRQ2_C),
 	PINMUX_IPSR_MSEL(IP7_20_18,	CTS1_C,		SEL_SCIF1_C),
-	PINMUX_IPSR_DATA(IP7_20_18,	SPEEDIN),
+	PINMUX_IPSR_GPSR(IP7_20_18,	SPEEDIN),
 
-	PINMUX_IPSR_DATA(IP7_21,	VI0_CLK),
+	PINMUX_IPSR_GPSR(IP7_21,	VI0_CLK),
 	PINMUX_IPSR_MSEL(IP7_21,	CAN_CLK_A,	SEL_CANCLK_A),
 
-	PINMUX_IPSR_DATA(IP7_24_22,	VI0_CLKENB),
+	PINMUX_IPSR_GPSR(IP7_24_22,	VI0_CLKENB),
 	PINMUX_IPSR_MSEL(IP7_24_22,	SD2_DAT2_B,	SEL_SD2_B),
-	PINMUX_IPSR_DATA(IP7_24_22,	VI1_DATA0),
-	PINMUX_IPSR_DATA(IP7_24_22,	DU1_DG6),
+	PINMUX_IPSR_GPSR(IP7_24_22,	VI1_DATA0),
+	PINMUX_IPSR_GPSR(IP7_24_22,	DU1_DG6),
 	PINMUX_IPSR_MSEL(IP7_24_22,	HSPI_RX1_A,	SEL_HSPI1_A),
 	PINMUX_IPSR_MSEL(IP7_24_22,	RX4_B,		SEL_SCIF4_B),
 
-	PINMUX_IPSR_DATA(IP7_28_25,	VI0_FIELD),
+	PINMUX_IPSR_GPSR(IP7_28_25,	VI0_FIELD),
 	PINMUX_IPSR_MSEL(IP7_28_25,	SD2_DAT3_B,	SEL_SD2_B),
 	PINMUX_DATA(VI0_R3_C_MARK,	FN_IP7_28_25,	FN_VI0_R3_C,	FN_SEL_VI0_C), /* see sel_vi0 */
 	PINMUX_DATA(VI0_R3_D_MARK,	FN_IP7_28_25,	FN_VI0_R3_C,	FN_SEL_VI0_D), /* see sel_vi0 */
-	PINMUX_IPSR_DATA(IP7_28_25,	VI1_DATA1),
-	PINMUX_IPSR_DATA(IP7_28_25,	DU1_DG7),
+	PINMUX_IPSR_GPSR(IP7_28_25,	VI1_DATA1),
+	PINMUX_IPSR_GPSR(IP7_28_25,	DU1_DG7),
 	PINMUX_IPSR_MSEL(IP7_28_25,	HSPI_CLK1_A,	SEL_HSPI1_A),
-	PINMUX_IPSR_DATA(IP7_28_25,	TX4_B),
+	PINMUX_IPSR_GPSR(IP7_28_25,	TX4_B),
 
-	PINMUX_IPSR_DATA(IP7_31_29,	VI0_HSYNC),
+	PINMUX_IPSR_GPSR(IP7_31_29,	VI0_HSYNC),
 	PINMUX_IPSR_MSEL(IP7_31_29,	SD2_CD_B,	SEL_SD2_B),
-	PINMUX_IPSR_DATA(IP7_31_29,	VI1_DATA2),
-	PINMUX_IPSR_DATA(IP7_31_29,	DU1_DR2),
+	PINMUX_IPSR_GPSR(IP7_31_29,	VI1_DATA2),
+	PINMUX_IPSR_GPSR(IP7_31_29,	DU1_DR2),
 	PINMUX_IPSR_MSEL(IP7_31_29,	HSPI_CS1_A,	SEL_HSPI1_A),
 	PINMUX_IPSR_MSEL(IP7_31_29,	RX3_B,		SEL_SCIF3_B),
 
 	/* IPSR8 */
-	PINMUX_IPSR_DATA(IP8_2_0,	VI0_VSYNC),
+	PINMUX_IPSR_GPSR(IP8_2_0,	VI0_VSYNC),
 	PINMUX_IPSR_MSEL(IP8_2_0,	SD2_WP_B,	SEL_SD2_B),
-	PINMUX_IPSR_DATA(IP8_2_0,	VI1_DATA3),
-	PINMUX_IPSR_DATA(IP8_2_0,	DU1_DR3),
-	PINMUX_IPSR_DATA(IP8_2_0,	HSPI_TX1_A),
-	PINMUX_IPSR_DATA(IP8_2_0,	TX3_B),
+	PINMUX_IPSR_GPSR(IP8_2_0,	VI1_DATA3),
+	PINMUX_IPSR_GPSR(IP8_2_0,	DU1_DR3),
+	PINMUX_IPSR_GPSR(IP8_2_0,	HSPI_TX1_A),
+	PINMUX_IPSR_GPSR(IP8_2_0,	TX3_B),
 
-	PINMUX_IPSR_DATA(IP8_5_3,	VI0_DATA0_VI0_B0),
-	PINMUX_IPSR_DATA(IP8_5_3,	DU1_DG2),
+	PINMUX_IPSR_GPSR(IP8_5_3,	VI0_DATA0_VI0_B0),
+	PINMUX_IPSR_GPSR(IP8_5_3,	DU1_DG2),
 	PINMUX_IPSR_MSEL(IP8_5_3,	IRQ2_B,		SEL_IRQ2_B),
 	PINMUX_IPSR_MSEL(IP8_5_3,	RX3_D,		SEL_SCIF3_D),
 
-	PINMUX_IPSR_DATA(IP8_8_6,	VI0_DATA1_VI0_B1),
-	PINMUX_IPSR_DATA(IP8_8_6,	DU1_DG3),
+	PINMUX_IPSR_GPSR(IP8_8_6,	VI0_DATA1_VI0_B1),
+	PINMUX_IPSR_GPSR(IP8_8_6,	DU1_DG3),
 	PINMUX_IPSR_MSEL(IP8_8_6,	IRQ3_B,		SEL_IRQ3_B),
-	PINMUX_IPSR_DATA(IP8_8_6,	TX3_D),
+	PINMUX_IPSR_GPSR(IP8_8_6,	TX3_D),
 
-	PINMUX_IPSR_DATA(IP8_10_9,	VI0_DATA2_VI0_B2),
-	PINMUX_IPSR_DATA(IP8_10_9,	DU1_DG4),
+	PINMUX_IPSR_GPSR(IP8_10_9,	VI0_DATA2_VI0_B2),
+	PINMUX_IPSR_GPSR(IP8_10_9,	DU1_DG4),
 	PINMUX_IPSR_MSEL(IP8_10_9,	RX0_C,		SEL_SCIF0_C),
 
-	PINMUX_IPSR_DATA(IP8_13_11,	VI0_DATA3_VI0_B3),
-	PINMUX_IPSR_DATA(IP8_13_11,	DU1_DG5),
-	PINMUX_IPSR_DATA(IP8_13_11,	TX1_A),
-	PINMUX_IPSR_DATA(IP8_13_11,	TX0_C),
+	PINMUX_IPSR_GPSR(IP8_13_11,	VI0_DATA3_VI0_B3),
+	PINMUX_IPSR_GPSR(IP8_13_11,	DU1_DG5),
+	PINMUX_IPSR_GPSR(IP8_13_11,	TX1_A),
+	PINMUX_IPSR_GPSR(IP8_13_11,	TX0_C),
 
-	PINMUX_IPSR_DATA(IP8_15_14,	VI0_DATA4_VI0_B4),
-	PINMUX_IPSR_DATA(IP8_15_14,	DU1_DB2),
+	PINMUX_IPSR_GPSR(IP8_15_14,	VI0_DATA4_VI0_B4),
+	PINMUX_IPSR_GPSR(IP8_15_14,	DU1_DB2),
 	PINMUX_IPSR_MSEL(IP8_15_14,	RX1_A,		SEL_SCIF1_A),
 
-	PINMUX_IPSR_DATA(IP8_18_16,	VI0_DATA5_VI0_B5),
-	PINMUX_IPSR_DATA(IP8_18_16,	DU1_DB3),
+	PINMUX_IPSR_GPSR(IP8_18_16,	VI0_DATA5_VI0_B5),
+	PINMUX_IPSR_GPSR(IP8_18_16,	DU1_DB3),
 	PINMUX_IPSR_MSEL(IP8_18_16,	SCK1_A,		SEL_SCIF1_A),
-	PINMUX_IPSR_DATA(IP8_18_16,	PWM4),
+	PINMUX_IPSR_GPSR(IP8_18_16,	PWM4),
 	PINMUX_IPSR_MSEL(IP8_18_16,	HSCK1_B,	SEL_HSCIF1_B),
 
-	PINMUX_IPSR_DATA(IP8_21_19,	VI0_DATA6_VI0_G0),
-	PINMUX_IPSR_DATA(IP8_21_19,	DU1_DB4),
+	PINMUX_IPSR_GPSR(IP8_21_19,	VI0_DATA6_VI0_G0),
+	PINMUX_IPSR_GPSR(IP8_21_19,	DU1_DB4),
 	PINMUX_IPSR_MSEL(IP8_21_19,	CTS1_A,		SEL_SCIF1_A),
-	PINMUX_IPSR_DATA(IP8_21_19,	PWM5),
+	PINMUX_IPSR_GPSR(IP8_21_19,	PWM5),
 
-	PINMUX_IPSR_DATA(IP8_23_22,	VI0_DATA7_VI0_G1),
-	PINMUX_IPSR_DATA(IP8_23_22,	DU1_DB5),
+	PINMUX_IPSR_GPSR(IP8_23_22,	VI0_DATA7_VI0_G1),
+	PINMUX_IPSR_GPSR(IP8_23_22,	DU1_DB5),
 	PINMUX_IPSR_MSEL(IP8_23_22,	RTS1_A,		SEL_SCIF1_A),
 
-	PINMUX_IPSR_DATA(IP8_26_24,	VI0_G2),
-	PINMUX_IPSR_DATA(IP8_26_24,	SD2_CLK_B),
-	PINMUX_IPSR_DATA(IP8_26_24,	VI1_DATA4),
-	PINMUX_IPSR_DATA(IP8_26_24,	DU1_DR4),
-	PINMUX_IPSR_DATA(IP8_26_24,	HTX1_B),
+	PINMUX_IPSR_GPSR(IP8_26_24,	VI0_G2),
+	PINMUX_IPSR_GPSR(IP8_26_24,	SD2_CLK_B),
+	PINMUX_IPSR_GPSR(IP8_26_24,	VI1_DATA4),
+	PINMUX_IPSR_GPSR(IP8_26_24,	DU1_DR4),
+	PINMUX_IPSR_GPSR(IP8_26_24,	HTX1_B),
 
-	PINMUX_IPSR_DATA(IP8_29_27,	VI0_G3),
+	PINMUX_IPSR_GPSR(IP8_29_27,	VI0_G3),
 	PINMUX_IPSR_MSEL(IP8_29_27,	SD2_CMD_B,	SEL_SD2_B),
-	PINMUX_IPSR_DATA(IP8_29_27,	VI1_DATA5),
-	PINMUX_IPSR_DATA(IP8_29_27,	DU1_DR5),
+	PINMUX_IPSR_GPSR(IP8_29_27,	VI1_DATA5),
+	PINMUX_IPSR_GPSR(IP8_29_27,	DU1_DR5),
 	PINMUX_IPSR_MSEL(IP8_29_27,	HRX1_B,		SEL_HSCIF1_B),
 
 	/* IPSR9 */
-	PINMUX_IPSR_DATA(IP9_2_0,	VI0_G4),
+	PINMUX_IPSR_GPSR(IP9_2_0,	VI0_G4),
 	PINMUX_IPSR_MSEL(IP9_2_0,	SD2_DAT0_B,	SEL_SD2_B),
-	PINMUX_IPSR_DATA(IP9_2_0,	VI1_DATA6),
-	PINMUX_IPSR_DATA(IP9_2_0,	DU1_DR6),
+	PINMUX_IPSR_GPSR(IP9_2_0,	VI1_DATA6),
+	PINMUX_IPSR_GPSR(IP9_2_0,	DU1_DR6),
 	PINMUX_IPSR_MSEL(IP9_2_0,	HRTS1_B,	SEL_HSCIF1_B),
 
-	PINMUX_IPSR_DATA(IP9_5_3,	VI0_G5),
+	PINMUX_IPSR_GPSR(IP9_5_3,	VI0_G5),
 	PINMUX_IPSR_MSEL(IP9_5_3,	SD2_DAT1_B,	SEL_SD2_B),
-	PINMUX_IPSR_DATA(IP9_5_3,	VI1_DATA7),
-	PINMUX_IPSR_DATA(IP9_5_3,	DU1_DR7),
+	PINMUX_IPSR_GPSR(IP9_5_3,	VI1_DATA7),
+	PINMUX_IPSR_GPSR(IP9_5_3,	DU1_DR7),
 	PINMUX_IPSR_MSEL(IP9_5_3,	HCTS1_B,	SEL_HSCIF1_B),
 
 	PINMUX_DATA(VI0_R0_A_MARK,	FN_IP9_8_6,	FN_VI0_R0_A,	FN_SEL_VI0_A), /* see sel_vi0 */
 	PINMUX_DATA(VI0_R0_C_MARK,	FN_IP9_8_6,	FN_VI0_R0_A,	FN_SEL_VI0_C), /* see sel_vi0 */
-	PINMUX_IPSR_DATA(IP9_8_6,	VI1_CLK),
-	PINMUX_IPSR_DATA(IP9_8_6,	ETH_REF_CLK),
-	PINMUX_IPSR_DATA(IP9_8_6,	DU1_DOTCLKIN),
+	PINMUX_IPSR_GPSR(IP9_8_6,	VI1_CLK),
+	PINMUX_IPSR_GPSR(IP9_8_6,	ETH_REF_CLK),
+	PINMUX_IPSR_GPSR(IP9_8_6,	DU1_DOTCLKIN),
 
 	PINMUX_DATA(VI0_R1_A_MARK,	FN_IP9_11_9,	FN_VI0_R1_A,	FN_SEL_VI0_A), /* see sel_vi0 */
 	PINMUX_DATA(VI0_R1_C_MARK,	FN_IP9_11_9,	FN_VI0_R1_A,	FN_SEL_VI0_C), /* see sel_vi0 */
-	PINMUX_IPSR_DATA(IP9_11_9,	VI1_DATA8),
-	PINMUX_IPSR_DATA(IP9_11_9,	DU1_DB6),
-	PINMUX_IPSR_DATA(IP9_11_9,	ETH_TXD0),
-	PINMUX_IPSR_DATA(IP9_11_9,	PWM2),
-	PINMUX_IPSR_DATA(IP9_11_9,	TCLK1),
+	PINMUX_IPSR_GPSR(IP9_11_9,	VI1_DATA8),
+	PINMUX_IPSR_GPSR(IP9_11_9,	DU1_DB6),
+	PINMUX_IPSR_GPSR(IP9_11_9,	ETH_TXD0),
+	PINMUX_IPSR_GPSR(IP9_11_9,	PWM2),
+	PINMUX_IPSR_GPSR(IP9_11_9,	TCLK1),
 
 	PINMUX_DATA(VI0_R2_A_MARK,	FN_IP9_14_12,	FN_VI0_R2_A,	FN_SEL_VI0_A), /* see sel_vi0 */
 	PINMUX_DATA(VI0_R2_C_MARK,	FN_IP9_14_12,	FN_VI0_R2_A,	FN_SEL_VI0_C), /* see sel_vi0 */
-	PINMUX_IPSR_DATA(IP9_14_12,	VI1_DATA9),
-	PINMUX_IPSR_DATA(IP9_14_12,	DU1_DB7),
-	PINMUX_IPSR_DATA(IP9_14_12,	ETH_TXD1),
-	PINMUX_IPSR_DATA(IP9_14_12,	PWM3),
+	PINMUX_IPSR_GPSR(IP9_14_12,	VI1_DATA9),
+	PINMUX_IPSR_GPSR(IP9_14_12,	DU1_DB7),
+	PINMUX_IPSR_GPSR(IP9_14_12,	ETH_TXD1),
+	PINMUX_IPSR_GPSR(IP9_14_12,	PWM3),
 
 	PINMUX_IPSR_MSEL(IP9_17_15,	VI0_R3_A,	SEL_VI0_A),
-	PINMUX_IPSR_DATA(IP9_17_15,	ETH_CRS_DV),
-	PINMUX_IPSR_DATA(IP9_17_15,	IECLK),
+	PINMUX_IPSR_GPSR(IP9_17_15,	ETH_CRS_DV),
+	PINMUX_IPSR_GPSR(IP9_17_15,	IECLK),
 	PINMUX_IPSR_MSEL(IP9_17_15,	SCK2_C,		SEL_SCIF2_C),
 
 	PINMUX_DATA(VI0_R4_A_MARK,	FN_IP9_20_18,	FN_VI0_R4_A,	FN_SEL_VI0_A), /* see sel_vi0 */
 	PINMUX_DATA(VI0_R3_C_MARK,	FN_IP9_20_18,	FN_VI0_R4_A,	FN_SEL_VI0_C), /* see sel_vi0 */
-	PINMUX_IPSR_DATA(IP9_20_18,	ETH_TX_EN),
-	PINMUX_IPSR_DATA(IP9_20_18,	IETX),
-	PINMUX_IPSR_DATA(IP9_20_18,	TX2_C),
+	PINMUX_IPSR_GPSR(IP9_20_18,	ETH_TX_EN),
+	PINMUX_IPSR_GPSR(IP9_20_18,	IETX),
+	PINMUX_IPSR_GPSR(IP9_20_18,	TX2_C),
 
 	PINMUX_DATA(VI0_R5_A_MARK,	FN_IP9_23_21,	FN_VI0_R5_A,	FN_SEL_VI0_A), /* see sel_vi0 */
 	PINMUX_DATA(VI0_R5_C_MARK,	FN_IP9_23_21,	FN_VI0_R5_A,	FN_SEL_VI0_C), /* see sel_vi0 */
-	PINMUX_IPSR_DATA(IP9_23_21,	ETH_RX_ER),
+	PINMUX_IPSR_GPSR(IP9_23_21,	ETH_RX_ER),
 	PINMUX_IPSR_MSEL(IP9_23_21,	FMCLK_C,	SEL_FM_C),
-	PINMUX_IPSR_DATA(IP9_23_21,	IERX),
+	PINMUX_IPSR_GPSR(IP9_23_21,	IERX),
 	PINMUX_IPSR_MSEL(IP9_23_21,	RX2_C,		SEL_SCIF2_C),
 
 	PINMUX_IPSR_MSEL(IP9_26_24,	VI1_DATA10_A,	SEL_VI1_A),
-	PINMUX_IPSR_DATA(IP9_26_24,	DU1_DOTCLKOUT),
-	PINMUX_IPSR_DATA(IP9_26_24,	ETH_RXD0),
-	PINMUX_IPSR_DATA(IP9_26_24,	BPFCLK_C),
-	PINMUX_IPSR_DATA(IP9_26_24,	TX2_D),
+	PINMUX_IPSR_GPSR(IP9_26_24,	DU1_DOTCLKOUT),
+	PINMUX_IPSR_GPSR(IP9_26_24,	ETH_RXD0),
+	PINMUX_IPSR_GPSR(IP9_26_24,	BPFCLK_C),
+	PINMUX_IPSR_GPSR(IP9_26_24,	TX2_D),
 	PINMUX_IPSR_MSEL(IP9_26_24,	SDA2_C,		SEL_I2C2_C),
 
 	PINMUX_IPSR_MSEL(IP9_29_27,	VI1_DATA11_A,	SEL_VI1_A),
-	PINMUX_IPSR_DATA(IP9_29_27,	DU1_EXHSYNC_DU1_HSYNC),
-	PINMUX_IPSR_DATA(IP9_29_27,	ETH_RXD1),
+	PINMUX_IPSR_GPSR(IP9_29_27,	DU1_EXHSYNC_DU1_HSYNC),
+	PINMUX_IPSR_GPSR(IP9_29_27,	ETH_RXD1),
 	PINMUX_IPSR_MSEL(IP9_29_27,	FMIN_C,		SEL_FM_C),
 	PINMUX_IPSR_MSEL(IP9_29_27,	RX2_D,		SEL_SCIF2_D),
 	PINMUX_IPSR_MSEL(IP9_29_27,	SCL2_C,		SEL_I2C2_C),
 
 	/* IPSR10 */
-	PINMUX_IPSR_DATA(IP10_2_0,	SD2_CLK_A),
-	PINMUX_IPSR_DATA(IP10_2_0,	DU1_EXVSYNC_DU1_VSYNC),
-	PINMUX_IPSR_DATA(IP10_2_0,	ATARD1),
-	PINMUX_IPSR_DATA(IP10_2_0,	ETH_MDC),
+	PINMUX_IPSR_GPSR(IP10_2_0,	SD2_CLK_A),
+	PINMUX_IPSR_GPSR(IP10_2_0,	DU1_EXVSYNC_DU1_VSYNC),
+	PINMUX_IPSR_GPSR(IP10_2_0,	ATARD1),
+	PINMUX_IPSR_GPSR(IP10_2_0,	ETH_MDC),
 	PINMUX_IPSR_MSEL(IP10_2_0,	SDA1_B,		SEL_I2C1_B),
 
 	PINMUX_IPSR_MSEL(IP10_5_3,	SD2_CMD_A,	SEL_SD2_A),
-	PINMUX_IPSR_DATA(IP10_5_3,	DU1_EXODDF_DU1_ODDF_DISP_CDE),
-	PINMUX_IPSR_DATA(IP10_5_3,	ATAWR1),
-	PINMUX_IPSR_DATA(IP10_5_3,	ETH_MDIO),
+	PINMUX_IPSR_GPSR(IP10_5_3,	DU1_EXODDF_DU1_ODDF_DISP_CDE),
+	PINMUX_IPSR_GPSR(IP10_5_3,	ATAWR1),
+	PINMUX_IPSR_GPSR(IP10_5_3,	ETH_MDIO),
 	PINMUX_IPSR_MSEL(IP10_5_3,	SCL1_B,		SEL_I2C1_B),
 
 	PINMUX_IPSR_MSEL(IP10_8_6,	SD2_DAT0_A,	SEL_SD2_A),
-	PINMUX_IPSR_DATA(IP10_8_6,	DU1_DISP),
-	PINMUX_IPSR_DATA(IP10_8_6,	ATACS01),
+	PINMUX_IPSR_GPSR(IP10_8_6,	DU1_DISP),
+	PINMUX_IPSR_GPSR(IP10_8_6,	ATACS01),
 	PINMUX_IPSR_MSEL(IP10_8_6,	DREQ1_B,	SEL_DREQ1_B),
-	PINMUX_IPSR_DATA(IP10_8_6,	ETH_LINK),
+	PINMUX_IPSR_GPSR(IP10_8_6,	ETH_LINK),
 	PINMUX_IPSR_MSEL(IP10_8_6,	CAN1_RX_A,	SEL_CAN1_A),
 
 	PINMUX_IPSR_MSEL(IP10_12_9,	SD2_DAT1_A,	SEL_SD2_A),
-	PINMUX_IPSR_DATA(IP10_12_9,	DU1_CDE),
-	PINMUX_IPSR_DATA(IP10_12_9,	ATACS11),
-	PINMUX_IPSR_DATA(IP10_12_9,	DACK1_B),
-	PINMUX_IPSR_DATA(IP10_12_9,	ETH_MAGIC),
-	PINMUX_IPSR_DATA(IP10_12_9,	CAN1_TX_A),
-	PINMUX_IPSR_DATA(IP10_12_9,	PWM6),
+	PINMUX_IPSR_GPSR(IP10_12_9,	DU1_CDE),
+	PINMUX_IPSR_GPSR(IP10_12_9,	ATACS11),
+	PINMUX_IPSR_GPSR(IP10_12_9,	DACK1_B),
+	PINMUX_IPSR_GPSR(IP10_12_9,	ETH_MAGIC),
+	PINMUX_IPSR_GPSR(IP10_12_9,	CAN1_TX_A),
+	PINMUX_IPSR_GPSR(IP10_12_9,	PWM6),
 
 	PINMUX_IPSR_MSEL(IP10_15_13,	SD2_DAT2_A,	SEL_SD2_A),
-	PINMUX_IPSR_DATA(IP10_15_13,	VI1_DATA12),
+	PINMUX_IPSR_GPSR(IP10_15_13,	VI1_DATA12),
 	PINMUX_IPSR_MSEL(IP10_15_13,	DREQ2_B,	SEL_DREQ2_B),
-	PINMUX_IPSR_DATA(IP10_15_13,	ATADIR1),
+	PINMUX_IPSR_GPSR(IP10_15_13,	ATADIR1),
 	PINMUX_IPSR_MSEL(IP10_15_13,	HSPI_CLK2_B,	SEL_HSPI2_B),
 	PINMUX_IPSR_MSEL(IP10_15_13,	GPSCLK_B,	SEL_GPS_B),
 
 	PINMUX_IPSR_MSEL(IP10_18_16,	SD2_DAT3_A,	SEL_SD2_A),
-	PINMUX_IPSR_DATA(IP10_18_16,	VI1_DATA13),
-	PINMUX_IPSR_DATA(IP10_18_16,	DACK2_B),
-	PINMUX_IPSR_DATA(IP10_18_16,	ATAG1),
+	PINMUX_IPSR_GPSR(IP10_18_16,	VI1_DATA13),
+	PINMUX_IPSR_GPSR(IP10_18_16,	DACK2_B),
+	PINMUX_IPSR_GPSR(IP10_18_16,	ATAG1),
 	PINMUX_IPSR_MSEL(IP10_18_16,	HSPI_CS2_B,	SEL_HSPI2_B),
 	PINMUX_IPSR_MSEL(IP10_18_16,	GPSIN_B,	SEL_GPS_B),
 
 	PINMUX_IPSR_MSEL(IP10_21_19,	SD2_CD_A,	SEL_SD2_A),
-	PINMUX_IPSR_DATA(IP10_21_19,	VI1_DATA14),
+	PINMUX_IPSR_GPSR(IP10_21_19,	VI1_DATA14),
 	PINMUX_IPSR_MSEL(IP10_21_19,	EX_WAIT1_B,	SEL_WAIT1_B),
 	PINMUX_IPSR_MSEL(IP10_21_19,	DREQ0_B,	SEL_DREQ0_B),
 	PINMUX_IPSR_MSEL(IP10_21_19,	HSPI_RX2_B,	SEL_HSPI2_B),
 	PINMUX_IPSR_MSEL(IP10_21_19,	REMOCON_A,	SEL_REMOCON_A),
 
 	PINMUX_IPSR_MSEL(IP10_24_22,	SD2_WP_A,	SEL_SD2_A),
-	PINMUX_IPSR_DATA(IP10_24_22,	VI1_DATA15),
+	PINMUX_IPSR_GPSR(IP10_24_22,	VI1_DATA15),
 	PINMUX_IPSR_MSEL(IP10_24_22,	EX_WAIT2_B,	SEL_WAIT2_B),
-	PINMUX_IPSR_DATA(IP10_24_22,	DACK0_B),
-	PINMUX_IPSR_DATA(IP10_24_22,	HSPI_TX2_B),
+	PINMUX_IPSR_GPSR(IP10_24_22,	DACK0_B),
+	PINMUX_IPSR_GPSR(IP10_24_22,	HSPI_TX2_B),
 	PINMUX_IPSR_MSEL(IP10_24_22,	CAN_CLK_C,	SEL_CANCLK_C),
 };
 
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7779.c b/drivers/pinctrl/sh-pfc/pfc-r8a7779.c
index bd17eccb6a89..5bef934f823d 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7779.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7779.c
@@ -611,577 +611,577 @@ static const u16 pinmux_data[] = {
 	PINMUX_SINGLE(USB_PENC0),
 	PINMUX_SINGLE(USB_PENC1),
 
-	PINMUX_IPSR_DATA(IP0_2_0, USB_PENC2),
+	PINMUX_IPSR_GPSR(IP0_2_0, USB_PENC2),
 	PINMUX_IPSR_MSEL(IP0_2_0, SCK0, SEL_SCIF0_0),
-	PINMUX_IPSR_DATA(IP0_2_0, PWM1),
+	PINMUX_IPSR_GPSR(IP0_2_0, PWM1),
 	PINMUX_IPSR_MSEL(IP0_2_0, PWMFSW0, SEL_PWMFSW_0),
 	PINMUX_IPSR_MSEL(IP0_2_0, SCIF_CLK, SEL_SCIF_0),
 	PINMUX_IPSR_MSEL(IP0_2_0, TCLK0_C, SEL_TMU0_2),
-	PINMUX_IPSR_DATA(IP0_5_3, BS),
-	PINMUX_IPSR_DATA(IP0_5_3, SD1_DAT2),
-	PINMUX_IPSR_DATA(IP0_5_3, MMC0_D2),
-	PINMUX_IPSR_DATA(IP0_5_3, FD2),
-	PINMUX_IPSR_DATA(IP0_5_3, ATADIR0),
-	PINMUX_IPSR_DATA(IP0_5_3, SDSELF),
+	PINMUX_IPSR_GPSR(IP0_5_3, BS),
+	PINMUX_IPSR_GPSR(IP0_5_3, SD1_DAT2),
+	PINMUX_IPSR_GPSR(IP0_5_3, MMC0_D2),
+	PINMUX_IPSR_GPSR(IP0_5_3, FD2),
+	PINMUX_IPSR_GPSR(IP0_5_3, ATADIR0),
+	PINMUX_IPSR_GPSR(IP0_5_3, SDSELF),
 	PINMUX_IPSR_MSEL(IP0_5_3, HCTS1, SEL_HSCIF1_0),
-	PINMUX_IPSR_DATA(IP0_5_3, TX4_C),
-	PINMUX_IPSR_DATA(IP0_7_6, A0),
-	PINMUX_IPSR_DATA(IP0_7_6, SD1_DAT3),
-	PINMUX_IPSR_DATA(IP0_7_6, MMC0_D3),
-	PINMUX_IPSR_DATA(IP0_7_6, FD3),
-	PINMUX_IPSR_DATA(IP0_9_8, A20),
-	PINMUX_IPSR_DATA(IP0_9_8, TX5_D),
-	PINMUX_IPSR_DATA(IP0_9_8, HSPI_TX2_B),
-	PINMUX_IPSR_DATA(IP0_11_10, A21),
+	PINMUX_IPSR_GPSR(IP0_5_3, TX4_C),
+	PINMUX_IPSR_GPSR(IP0_7_6, A0),
+	PINMUX_IPSR_GPSR(IP0_7_6, SD1_DAT3),
+	PINMUX_IPSR_GPSR(IP0_7_6, MMC0_D3),
+	PINMUX_IPSR_GPSR(IP0_7_6, FD3),
+	PINMUX_IPSR_GPSR(IP0_9_8, A20),
+	PINMUX_IPSR_GPSR(IP0_9_8, TX5_D),
+	PINMUX_IPSR_GPSR(IP0_9_8, HSPI_TX2_B),
+	PINMUX_IPSR_GPSR(IP0_11_10, A21),
 	PINMUX_IPSR_MSEL(IP0_11_10, SCK5_D, SEL_SCIF5_3),
 	PINMUX_IPSR_MSEL(IP0_11_10, HSPI_CLK2_B, SEL_HSPI2_1),
-	PINMUX_IPSR_DATA(IP0_13_12, A22),
+	PINMUX_IPSR_GPSR(IP0_13_12, A22),
 	PINMUX_IPSR_MSEL(IP0_13_12, RX5_D, SEL_SCIF5_3),
 	PINMUX_IPSR_MSEL(IP0_13_12, HSPI_RX2_B, SEL_HSPI2_1),
-	PINMUX_IPSR_DATA(IP0_13_12, VI1_R0),
-	PINMUX_IPSR_DATA(IP0_15_14, A23),
-	PINMUX_IPSR_DATA(IP0_15_14, FCLE),
+	PINMUX_IPSR_GPSR(IP0_13_12, VI1_R0),
+	PINMUX_IPSR_GPSR(IP0_15_14, A23),
+	PINMUX_IPSR_GPSR(IP0_15_14, FCLE),
 	PINMUX_IPSR_MSEL(IP0_15_14, HSPI_CLK2, SEL_HSPI2_0),
-	PINMUX_IPSR_DATA(IP0_15_14, VI1_R1),
-	PINMUX_IPSR_DATA(IP0_18_16, A24),
-	PINMUX_IPSR_DATA(IP0_18_16, SD1_CD),
-	PINMUX_IPSR_DATA(IP0_18_16, MMC0_D4),
-	PINMUX_IPSR_DATA(IP0_18_16, FD4),
+	PINMUX_IPSR_GPSR(IP0_15_14, VI1_R1),
+	PINMUX_IPSR_GPSR(IP0_18_16, A24),
+	PINMUX_IPSR_GPSR(IP0_18_16, SD1_CD),
+	PINMUX_IPSR_GPSR(IP0_18_16, MMC0_D4),
+	PINMUX_IPSR_GPSR(IP0_18_16, FD4),
 	PINMUX_IPSR_MSEL(IP0_18_16, HSPI_CS2, SEL_HSPI2_0),
-	PINMUX_IPSR_DATA(IP0_18_16, VI1_R2),
+	PINMUX_IPSR_GPSR(IP0_18_16, VI1_R2),
 	PINMUX_IPSR_MSEL(IP0_18_16, SSI_WS78_B, SEL_SSI7_1),
-	PINMUX_IPSR_DATA(IP0_22_19, A25),
-	PINMUX_IPSR_DATA(IP0_22_19, SD1_WP),
-	PINMUX_IPSR_DATA(IP0_22_19, MMC0_D5),
-	PINMUX_IPSR_DATA(IP0_22_19, FD5),
+	PINMUX_IPSR_GPSR(IP0_22_19, A25),
+	PINMUX_IPSR_GPSR(IP0_22_19, SD1_WP),
+	PINMUX_IPSR_GPSR(IP0_22_19, MMC0_D5),
+	PINMUX_IPSR_GPSR(IP0_22_19, FD5),
 	PINMUX_IPSR_MSEL(IP0_22_19, HSPI_RX2, SEL_HSPI2_0),
-	PINMUX_IPSR_DATA(IP0_22_19, VI1_R3),
-	PINMUX_IPSR_DATA(IP0_22_19, TX5_B),
+	PINMUX_IPSR_GPSR(IP0_22_19, VI1_R3),
+	PINMUX_IPSR_GPSR(IP0_22_19, TX5_B),
 	PINMUX_IPSR_MSEL(IP0_22_19, SSI_SDATA7_B, SEL_SSI7_1),
 	PINMUX_IPSR_MSEL(IP0_22_19, CTS0_B, SEL_SCIF0_1),
-	PINMUX_IPSR_DATA(IP0_24_23, CLKOUT),
-	PINMUX_IPSR_DATA(IP0_24_23, TX3C_IRDA_TX_C),
-	PINMUX_IPSR_DATA(IP0_24_23, PWM0_B),
-	PINMUX_IPSR_DATA(IP0_25, CS0),
+	PINMUX_IPSR_GPSR(IP0_24_23, CLKOUT),
+	PINMUX_IPSR_GPSR(IP0_24_23, TX3C_IRDA_TX_C),
+	PINMUX_IPSR_GPSR(IP0_24_23, PWM0_B),
+	PINMUX_IPSR_GPSR(IP0_25, CS0),
 	PINMUX_IPSR_MSEL(IP0_25, HSPI_CS2_B, SEL_HSPI2_1),
-	PINMUX_IPSR_DATA(IP0_27_26, CS1_A26),
-	PINMUX_IPSR_DATA(IP0_27_26, HSPI_TX2),
-	PINMUX_IPSR_DATA(IP0_27_26, SDSELF_B),
-	PINMUX_IPSR_DATA(IP0_30_28, RD_WR),
-	PINMUX_IPSR_DATA(IP0_30_28, FWE),
-	PINMUX_IPSR_DATA(IP0_30_28, ATAG0),
-	PINMUX_IPSR_DATA(IP0_30_28, VI1_R7),
+	PINMUX_IPSR_GPSR(IP0_27_26, CS1_A26),
+	PINMUX_IPSR_GPSR(IP0_27_26, HSPI_TX2),
+	PINMUX_IPSR_GPSR(IP0_27_26, SDSELF_B),
+	PINMUX_IPSR_GPSR(IP0_30_28, RD_WR),
+	PINMUX_IPSR_GPSR(IP0_30_28, FWE),
+	PINMUX_IPSR_GPSR(IP0_30_28, ATAG0),
+	PINMUX_IPSR_GPSR(IP0_30_28, VI1_R7),
 	PINMUX_IPSR_MSEL(IP0_30_28, HRTS1, SEL_HSCIF1_0),
 	PINMUX_IPSR_MSEL(IP0_30_28, RX4_C, SEL_SCIF4_2),
 
-	PINMUX_IPSR_DATA(IP1_1_0, EX_CS0),
+	PINMUX_IPSR_GPSR(IP1_1_0, EX_CS0),
 	PINMUX_IPSR_MSEL(IP1_1_0, RX3_C_IRDA_RX_C, SEL_SCIF3_2),
-	PINMUX_IPSR_DATA(IP1_1_0, MMC0_D6),
-	PINMUX_IPSR_DATA(IP1_1_0, FD6),
-	PINMUX_IPSR_DATA(IP1_3_2, EX_CS1),
-	PINMUX_IPSR_DATA(IP1_3_2, MMC0_D7),
-	PINMUX_IPSR_DATA(IP1_3_2, FD7),
-	PINMUX_IPSR_DATA(IP1_6_4, EX_CS2),
-	PINMUX_IPSR_DATA(IP1_6_4, SD1_CLK),
-	PINMUX_IPSR_DATA(IP1_6_4, MMC0_CLK),
-	PINMUX_IPSR_DATA(IP1_6_4, FALE),
-	PINMUX_IPSR_DATA(IP1_6_4, ATACS00),
-	PINMUX_IPSR_DATA(IP1_10_7, EX_CS3),
-	PINMUX_IPSR_DATA(IP1_10_7, SD1_CMD),
-	PINMUX_IPSR_DATA(IP1_10_7, MMC0_CMD),
-	PINMUX_IPSR_DATA(IP1_10_7, FRE),
-	PINMUX_IPSR_DATA(IP1_10_7, ATACS10),
-	PINMUX_IPSR_DATA(IP1_10_7, VI1_R4),
+	PINMUX_IPSR_GPSR(IP1_1_0, MMC0_D6),
+	PINMUX_IPSR_GPSR(IP1_1_0, FD6),
+	PINMUX_IPSR_GPSR(IP1_3_2, EX_CS1),
+	PINMUX_IPSR_GPSR(IP1_3_2, MMC0_D7),
+	PINMUX_IPSR_GPSR(IP1_3_2, FD7),
+	PINMUX_IPSR_GPSR(IP1_6_4, EX_CS2),
+	PINMUX_IPSR_GPSR(IP1_6_4, SD1_CLK),
+	PINMUX_IPSR_GPSR(IP1_6_4, MMC0_CLK),
+	PINMUX_IPSR_GPSR(IP1_6_4, FALE),
+	PINMUX_IPSR_GPSR(IP1_6_4, ATACS00),
+	PINMUX_IPSR_GPSR(IP1_10_7, EX_CS3),
+	PINMUX_IPSR_GPSR(IP1_10_7, SD1_CMD),
+	PINMUX_IPSR_GPSR(IP1_10_7, MMC0_CMD),
+	PINMUX_IPSR_GPSR(IP1_10_7, FRE),
+	PINMUX_IPSR_GPSR(IP1_10_7, ATACS10),
+	PINMUX_IPSR_GPSR(IP1_10_7, VI1_R4),
 	PINMUX_IPSR_MSEL(IP1_10_7, RX5_B, SEL_SCIF5_1),
 	PINMUX_IPSR_MSEL(IP1_10_7, HSCK1, SEL_HSCIF1_0),
 	PINMUX_IPSR_MSEL(IP1_10_7, SSI_SDATA8_B, SEL_SSI8_1),
 	PINMUX_IPSR_MSEL(IP1_10_7, RTS0_B_TANS_B, SEL_SCIF0_1),
 	PINMUX_IPSR_MSEL(IP1_10_7, SSI_SDATA9, SEL_SSI9_0),
-	PINMUX_IPSR_DATA(IP1_14_11, EX_CS4),
-	PINMUX_IPSR_DATA(IP1_14_11, SD1_DAT0),
-	PINMUX_IPSR_DATA(IP1_14_11, MMC0_D0),
-	PINMUX_IPSR_DATA(IP1_14_11, FD0),
-	PINMUX_IPSR_DATA(IP1_14_11, ATARD0),
-	PINMUX_IPSR_DATA(IP1_14_11, VI1_R5),
+	PINMUX_IPSR_GPSR(IP1_14_11, EX_CS4),
+	PINMUX_IPSR_GPSR(IP1_14_11, SD1_DAT0),
+	PINMUX_IPSR_GPSR(IP1_14_11, MMC0_D0),
+	PINMUX_IPSR_GPSR(IP1_14_11, FD0),
+	PINMUX_IPSR_GPSR(IP1_14_11, ATARD0),
+	PINMUX_IPSR_GPSR(IP1_14_11, VI1_R5),
 	PINMUX_IPSR_MSEL(IP1_14_11, SCK5_B, SEL_SCIF5_1),
-	PINMUX_IPSR_DATA(IP1_14_11, HTX1),
-	PINMUX_IPSR_DATA(IP1_14_11, TX2_E),
-	PINMUX_IPSR_DATA(IP1_14_11, TX0_B),
+	PINMUX_IPSR_GPSR(IP1_14_11, HTX1),
+	PINMUX_IPSR_GPSR(IP1_14_11, TX2_E),
+	PINMUX_IPSR_GPSR(IP1_14_11, TX0_B),
 	PINMUX_IPSR_MSEL(IP1_14_11, SSI_SCK9, SEL_SSI9_0),
-	PINMUX_IPSR_DATA(IP1_18_15, EX_CS5),
-	PINMUX_IPSR_DATA(IP1_18_15, SD1_DAT1),
-	PINMUX_IPSR_DATA(IP1_18_15, MMC0_D1),
-	PINMUX_IPSR_DATA(IP1_18_15, FD1),
-	PINMUX_IPSR_DATA(IP1_18_15, ATAWR0),
-	PINMUX_IPSR_DATA(IP1_18_15, VI1_R6),
+	PINMUX_IPSR_GPSR(IP1_18_15, EX_CS5),
+	PINMUX_IPSR_GPSR(IP1_18_15, SD1_DAT1),
+	PINMUX_IPSR_GPSR(IP1_18_15, MMC0_D1),
+	PINMUX_IPSR_GPSR(IP1_18_15, FD1),
+	PINMUX_IPSR_GPSR(IP1_18_15, ATAWR0),
+	PINMUX_IPSR_GPSR(IP1_18_15, VI1_R6),
 	PINMUX_IPSR_MSEL(IP1_18_15, HRX1, SEL_HSCIF1_0),
 	PINMUX_IPSR_MSEL(IP1_18_15, RX2_E, SEL_SCIF2_4),
 	PINMUX_IPSR_MSEL(IP1_18_15, RX0_B, SEL_SCIF0_1),
 	PINMUX_IPSR_MSEL(IP1_18_15, SSI_WS9, SEL_SSI9_0),
-	PINMUX_IPSR_DATA(IP1_20_19, MLB_CLK),
-	PINMUX_IPSR_DATA(IP1_20_19, PWM2),
+	PINMUX_IPSR_GPSR(IP1_20_19, MLB_CLK),
+	PINMUX_IPSR_GPSR(IP1_20_19, PWM2),
 	PINMUX_IPSR_MSEL(IP1_20_19, SCK4, SEL_SCIF4_0),
-	PINMUX_IPSR_DATA(IP1_22_21, MLB_SIG),
-	PINMUX_IPSR_DATA(IP1_22_21, PWM3),
-	PINMUX_IPSR_DATA(IP1_22_21, TX4),
-	PINMUX_IPSR_DATA(IP1_24_23, MLB_DAT),
-	PINMUX_IPSR_DATA(IP1_24_23, PWM4),
+	PINMUX_IPSR_GPSR(IP1_22_21, MLB_SIG),
+	PINMUX_IPSR_GPSR(IP1_22_21, PWM3),
+	PINMUX_IPSR_GPSR(IP1_22_21, TX4),
+	PINMUX_IPSR_GPSR(IP1_24_23, MLB_DAT),
+	PINMUX_IPSR_GPSR(IP1_24_23, PWM4),
 	PINMUX_IPSR_MSEL(IP1_24_23, RX4, SEL_SCIF4_0),
-	PINMUX_IPSR_DATA(IP1_28_25, HTX0),
-	PINMUX_IPSR_DATA(IP1_28_25, TX1),
-	PINMUX_IPSR_DATA(IP1_28_25, SDATA),
+	PINMUX_IPSR_GPSR(IP1_28_25, HTX0),
+	PINMUX_IPSR_GPSR(IP1_28_25, TX1),
+	PINMUX_IPSR_GPSR(IP1_28_25, SDATA),
 	PINMUX_IPSR_MSEL(IP1_28_25, CTS0_C, SEL_SCIF0_2),
-	PINMUX_IPSR_DATA(IP1_28_25, SUB_TCK),
-	PINMUX_IPSR_DATA(IP1_28_25, CC5_STATE2),
-	PINMUX_IPSR_DATA(IP1_28_25, CC5_STATE10),
-	PINMUX_IPSR_DATA(IP1_28_25, CC5_STATE18),
-	PINMUX_IPSR_DATA(IP1_28_25, CC5_STATE26),
-	PINMUX_IPSR_DATA(IP1_28_25, CC5_STATE34),
+	PINMUX_IPSR_GPSR(IP1_28_25, SUB_TCK),
+	PINMUX_IPSR_GPSR(IP1_28_25, CC5_STATE2),
+	PINMUX_IPSR_GPSR(IP1_28_25, CC5_STATE10),
+	PINMUX_IPSR_GPSR(IP1_28_25, CC5_STATE18),
+	PINMUX_IPSR_GPSR(IP1_28_25, CC5_STATE26),
+	PINMUX_IPSR_GPSR(IP1_28_25, CC5_STATE34),
 
 	PINMUX_IPSR_MSEL(IP2_3_0, HRX0, SEL_HSCIF0_0),
 	PINMUX_IPSR_MSEL(IP2_3_0, RX1, SEL_SCIF1_0),
-	PINMUX_IPSR_DATA(IP2_3_0, SCKZ),
+	PINMUX_IPSR_GPSR(IP2_3_0, SCKZ),
 	PINMUX_IPSR_MSEL(IP2_3_0, RTS0_C_TANS_C, SEL_SCIF0_2),
-	PINMUX_IPSR_DATA(IP2_3_0, SUB_TDI),
-	PINMUX_IPSR_DATA(IP2_3_0, CC5_STATE3),
-	PINMUX_IPSR_DATA(IP2_3_0, CC5_STATE11),
-	PINMUX_IPSR_DATA(IP2_3_0, CC5_STATE19),
-	PINMUX_IPSR_DATA(IP2_3_0, CC5_STATE27),
-	PINMUX_IPSR_DATA(IP2_3_0, CC5_STATE35),
+	PINMUX_IPSR_GPSR(IP2_3_0, SUB_TDI),
+	PINMUX_IPSR_GPSR(IP2_3_0, CC5_STATE3),
+	PINMUX_IPSR_GPSR(IP2_3_0, CC5_STATE11),
+	PINMUX_IPSR_GPSR(IP2_3_0, CC5_STATE19),
+	PINMUX_IPSR_GPSR(IP2_3_0, CC5_STATE27),
+	PINMUX_IPSR_GPSR(IP2_3_0, CC5_STATE35),
 	PINMUX_IPSR_MSEL(IP2_7_4, HSCK0, SEL_HSCIF0_0),
 	PINMUX_IPSR_MSEL(IP2_7_4, SCK1, SEL_SCIF1_0),
-	PINMUX_IPSR_DATA(IP2_7_4, MTS),
-	PINMUX_IPSR_DATA(IP2_7_4, PWM5),
+	PINMUX_IPSR_GPSR(IP2_7_4, MTS),
+	PINMUX_IPSR_GPSR(IP2_7_4, PWM5),
 	PINMUX_IPSR_MSEL(IP2_7_4, SCK0_C, SEL_SCIF0_2),
 	PINMUX_IPSR_MSEL(IP2_7_4, SSI_SDATA9_B, SEL_SSI9_1),
-	PINMUX_IPSR_DATA(IP2_7_4, SUB_TDO),
-	PINMUX_IPSR_DATA(IP2_7_4, CC5_STATE0),
-	PINMUX_IPSR_DATA(IP2_7_4, CC5_STATE8),
-	PINMUX_IPSR_DATA(IP2_7_4, CC5_STATE16),
-	PINMUX_IPSR_DATA(IP2_7_4, CC5_STATE24),
-	PINMUX_IPSR_DATA(IP2_7_4, CC5_STATE32),
+	PINMUX_IPSR_GPSR(IP2_7_4, SUB_TDO),
+	PINMUX_IPSR_GPSR(IP2_7_4, CC5_STATE0),
+	PINMUX_IPSR_GPSR(IP2_7_4, CC5_STATE8),
+	PINMUX_IPSR_GPSR(IP2_7_4, CC5_STATE16),
+	PINMUX_IPSR_GPSR(IP2_7_4, CC5_STATE24),
+	PINMUX_IPSR_GPSR(IP2_7_4, CC5_STATE32),
 	PINMUX_IPSR_MSEL(IP2_11_8, HCTS0, SEL_HSCIF0_0),
 	PINMUX_IPSR_MSEL(IP2_11_8, CTS1, SEL_SCIF1_0),
-	PINMUX_IPSR_DATA(IP2_11_8, STM),
-	PINMUX_IPSR_DATA(IP2_11_8, PWM0_D),
+	PINMUX_IPSR_GPSR(IP2_11_8, STM),
+	PINMUX_IPSR_GPSR(IP2_11_8, PWM0_D),
 	PINMUX_IPSR_MSEL(IP2_11_8, RX0_C, SEL_SCIF0_2),
 	PINMUX_IPSR_MSEL(IP2_11_8, SCIF_CLK_C, SEL_SCIF_2),
-	PINMUX_IPSR_DATA(IP2_11_8, SUB_TRST),
+	PINMUX_IPSR_GPSR(IP2_11_8, SUB_TRST),
 	PINMUX_IPSR_MSEL(IP2_11_8, TCLK1_B, SEL_TMU1_1),
-	PINMUX_IPSR_DATA(IP2_11_8, CC5_OSCOUT),
+	PINMUX_IPSR_GPSR(IP2_11_8, CC5_OSCOUT),
 	PINMUX_IPSR_MSEL(IP2_15_12, HRTS0, SEL_HSCIF0_0),
 	PINMUX_IPSR_MSEL(IP2_15_12, RTS1_TANS, SEL_SCIF1_0),
-	PINMUX_IPSR_DATA(IP2_15_12, MDATA),
-	PINMUX_IPSR_DATA(IP2_15_12, TX0_C),
-	PINMUX_IPSR_DATA(IP2_15_12, SUB_TMS),
-	PINMUX_IPSR_DATA(IP2_15_12, CC5_STATE1),
-	PINMUX_IPSR_DATA(IP2_15_12, CC5_STATE9),
-	PINMUX_IPSR_DATA(IP2_15_12, CC5_STATE17),
-	PINMUX_IPSR_DATA(IP2_15_12, CC5_STATE25),
-	PINMUX_IPSR_DATA(IP2_15_12, CC5_STATE33),
-	PINMUX_IPSR_DATA(IP2_18_16, DU0_DR0),
-	PINMUX_IPSR_DATA(IP2_18_16, LCDOUT0),
+	PINMUX_IPSR_GPSR(IP2_15_12, MDATA),
+	PINMUX_IPSR_GPSR(IP2_15_12, TX0_C),
+	PINMUX_IPSR_GPSR(IP2_15_12, SUB_TMS),
+	PINMUX_IPSR_GPSR(IP2_15_12, CC5_STATE1),
+	PINMUX_IPSR_GPSR(IP2_15_12, CC5_STATE9),
+	PINMUX_IPSR_GPSR(IP2_15_12, CC5_STATE17),
+	PINMUX_IPSR_GPSR(IP2_15_12, CC5_STATE25),
+	PINMUX_IPSR_GPSR(IP2_15_12, CC5_STATE33),
+	PINMUX_IPSR_GPSR(IP2_18_16, DU0_DR0),
+	PINMUX_IPSR_GPSR(IP2_18_16, LCDOUT0),
 	PINMUX_IPSR_MSEL(IP2_18_16, DREQ0, SEL_EXBUS0_0),
 	PINMUX_IPSR_MSEL(IP2_18_16, GPS_CLK_B, SEL_GPS_1),
-	PINMUX_IPSR_DATA(IP2_18_16, AUDATA0),
-	PINMUX_IPSR_DATA(IP2_18_16, TX5_C),
-	PINMUX_IPSR_DATA(IP2_21_19, DU0_DR1),
-	PINMUX_IPSR_DATA(IP2_21_19, LCDOUT1),
-	PINMUX_IPSR_DATA(IP2_21_19, DACK0),
-	PINMUX_IPSR_DATA(IP2_21_19, DRACK0),
+	PINMUX_IPSR_GPSR(IP2_18_16, AUDATA0),
+	PINMUX_IPSR_GPSR(IP2_18_16, TX5_C),
+	PINMUX_IPSR_GPSR(IP2_21_19, DU0_DR1),
+	PINMUX_IPSR_GPSR(IP2_21_19, LCDOUT1),
+	PINMUX_IPSR_GPSR(IP2_21_19, DACK0),
+	PINMUX_IPSR_GPSR(IP2_21_19, DRACK0),
 	PINMUX_IPSR_MSEL(IP2_21_19, GPS_SIGN_B, SEL_GPS_1),
-	PINMUX_IPSR_DATA(IP2_21_19, AUDATA1),
+	PINMUX_IPSR_GPSR(IP2_21_19, AUDATA1),
 	PINMUX_IPSR_MSEL(IP2_21_19, RX5_C, SEL_SCIF5_2),
-	PINMUX_IPSR_DATA(IP2_22, DU0_DR2),
-	PINMUX_IPSR_DATA(IP2_22, LCDOUT2),
-	PINMUX_IPSR_DATA(IP2_23, DU0_DR3),
-	PINMUX_IPSR_DATA(IP2_23, LCDOUT3),
-	PINMUX_IPSR_DATA(IP2_24, DU0_DR4),
-	PINMUX_IPSR_DATA(IP2_24, LCDOUT4),
-	PINMUX_IPSR_DATA(IP2_25, DU0_DR5),
-	PINMUX_IPSR_DATA(IP2_25, LCDOUT5),
-	PINMUX_IPSR_DATA(IP2_26, DU0_DR6),
-	PINMUX_IPSR_DATA(IP2_26, LCDOUT6),
-	PINMUX_IPSR_DATA(IP2_27, DU0_DR7),
-	PINMUX_IPSR_DATA(IP2_27, LCDOUT7),
-	PINMUX_IPSR_DATA(IP2_30_28, DU0_DG0),
-	PINMUX_IPSR_DATA(IP2_30_28, LCDOUT8),
+	PINMUX_IPSR_GPSR(IP2_22, DU0_DR2),
+	PINMUX_IPSR_GPSR(IP2_22, LCDOUT2),
+	PINMUX_IPSR_GPSR(IP2_23, DU0_DR3),
+	PINMUX_IPSR_GPSR(IP2_23, LCDOUT3),
+	PINMUX_IPSR_GPSR(IP2_24, DU0_DR4),
+	PINMUX_IPSR_GPSR(IP2_24, LCDOUT4),
+	PINMUX_IPSR_GPSR(IP2_25, DU0_DR5),
+	PINMUX_IPSR_GPSR(IP2_25, LCDOUT5),
+	PINMUX_IPSR_GPSR(IP2_26, DU0_DR6),
+	PINMUX_IPSR_GPSR(IP2_26, LCDOUT6),
+	PINMUX_IPSR_GPSR(IP2_27, DU0_DR7),
+	PINMUX_IPSR_GPSR(IP2_27, LCDOUT7),
+	PINMUX_IPSR_GPSR(IP2_30_28, DU0_DG0),
+	PINMUX_IPSR_GPSR(IP2_30_28, LCDOUT8),
 	PINMUX_IPSR_MSEL(IP2_30_28, DREQ1, SEL_EXBUS1_0),
 	PINMUX_IPSR_MSEL(IP2_30_28, SCL2, SEL_I2C2_0),
-	PINMUX_IPSR_DATA(IP2_30_28, AUDATA2),
+	PINMUX_IPSR_GPSR(IP2_30_28, AUDATA2),
 
-	PINMUX_IPSR_DATA(IP3_2_0, DU0_DG1),
-	PINMUX_IPSR_DATA(IP3_2_0, LCDOUT9),
-	PINMUX_IPSR_DATA(IP3_2_0, DACK1),
+	PINMUX_IPSR_GPSR(IP3_2_0, DU0_DG1),
+	PINMUX_IPSR_GPSR(IP3_2_0, LCDOUT9),
+	PINMUX_IPSR_GPSR(IP3_2_0, DACK1),
 	PINMUX_IPSR_MSEL(IP3_2_0, SDA2, SEL_I2C2_0),
-	PINMUX_IPSR_DATA(IP3_2_0, AUDATA3),
-	PINMUX_IPSR_DATA(IP3_3, DU0_DG2),
-	PINMUX_IPSR_DATA(IP3_3, LCDOUT10),
-	PINMUX_IPSR_DATA(IP3_4, DU0_DG3),
-	PINMUX_IPSR_DATA(IP3_4, LCDOUT11),
-	PINMUX_IPSR_DATA(IP3_5, DU0_DG4),
-	PINMUX_IPSR_DATA(IP3_5, LCDOUT12),
-	PINMUX_IPSR_DATA(IP3_6, DU0_DG5),
-	PINMUX_IPSR_DATA(IP3_6, LCDOUT13),
-	PINMUX_IPSR_DATA(IP3_7, DU0_DG6),
-	PINMUX_IPSR_DATA(IP3_7, LCDOUT14),
-	PINMUX_IPSR_DATA(IP3_8, DU0_DG7),
-	PINMUX_IPSR_DATA(IP3_8, LCDOUT15),
-	PINMUX_IPSR_DATA(IP3_11_9, DU0_DB0),
-	PINMUX_IPSR_DATA(IP3_11_9, LCDOUT16),
-	PINMUX_IPSR_DATA(IP3_11_9, EX_WAIT1),
+	PINMUX_IPSR_GPSR(IP3_2_0, AUDATA3),
+	PINMUX_IPSR_GPSR(IP3_3, DU0_DG2),
+	PINMUX_IPSR_GPSR(IP3_3, LCDOUT10),
+	PINMUX_IPSR_GPSR(IP3_4, DU0_DG3),
+	PINMUX_IPSR_GPSR(IP3_4, LCDOUT11),
+	PINMUX_IPSR_GPSR(IP3_5, DU0_DG4),
+	PINMUX_IPSR_GPSR(IP3_5, LCDOUT12),
+	PINMUX_IPSR_GPSR(IP3_6, DU0_DG5),
+	PINMUX_IPSR_GPSR(IP3_6, LCDOUT13),
+	PINMUX_IPSR_GPSR(IP3_7, DU0_DG6),
+	PINMUX_IPSR_GPSR(IP3_7, LCDOUT14),
+	PINMUX_IPSR_GPSR(IP3_8, DU0_DG7),
+	PINMUX_IPSR_GPSR(IP3_8, LCDOUT15),
+	PINMUX_IPSR_GPSR(IP3_11_9, DU0_DB0),
+	PINMUX_IPSR_GPSR(IP3_11_9, LCDOUT16),
+	PINMUX_IPSR_GPSR(IP3_11_9, EX_WAIT1),
 	PINMUX_IPSR_MSEL(IP3_11_9, SCL1, SEL_I2C1_0),
 	PINMUX_IPSR_MSEL(IP3_11_9, TCLK1, SEL_TMU1_0),
-	PINMUX_IPSR_DATA(IP3_11_9, AUDATA4),
-	PINMUX_IPSR_DATA(IP3_14_12, DU0_DB1),
-	PINMUX_IPSR_DATA(IP3_14_12, LCDOUT17),
-	PINMUX_IPSR_DATA(IP3_14_12, EX_WAIT2),
+	PINMUX_IPSR_GPSR(IP3_11_9, AUDATA4),
+	PINMUX_IPSR_GPSR(IP3_14_12, DU0_DB1),
+	PINMUX_IPSR_GPSR(IP3_14_12, LCDOUT17),
+	PINMUX_IPSR_GPSR(IP3_14_12, EX_WAIT2),
 	PINMUX_IPSR_MSEL(IP3_14_12, SDA1, SEL_I2C1_0),
 	PINMUX_IPSR_MSEL(IP3_14_12, GPS_MAG_B, SEL_GPS_1),
-	PINMUX_IPSR_DATA(IP3_14_12, AUDATA5),
+	PINMUX_IPSR_GPSR(IP3_14_12, AUDATA5),
 	PINMUX_IPSR_MSEL(IP3_14_12, SCK5_C, SEL_SCIF5_2),
-	PINMUX_IPSR_DATA(IP3_15, DU0_DB2),
-	PINMUX_IPSR_DATA(IP3_15, LCDOUT18),
-	PINMUX_IPSR_DATA(IP3_16, DU0_DB3),
-	PINMUX_IPSR_DATA(IP3_16, LCDOUT19),
-	PINMUX_IPSR_DATA(IP3_17, DU0_DB4),
-	PINMUX_IPSR_DATA(IP3_17, LCDOUT20),
-	PINMUX_IPSR_DATA(IP3_18, DU0_DB5),
-	PINMUX_IPSR_DATA(IP3_18, LCDOUT21),
-	PINMUX_IPSR_DATA(IP3_19, DU0_DB6),
-	PINMUX_IPSR_DATA(IP3_19, LCDOUT22),
-	PINMUX_IPSR_DATA(IP3_20, DU0_DB7),
-	PINMUX_IPSR_DATA(IP3_20, LCDOUT23),
-	PINMUX_IPSR_DATA(IP3_22_21, DU0_DOTCLKIN),
-	PINMUX_IPSR_DATA(IP3_22_21, QSTVA_QVS),
-	PINMUX_IPSR_DATA(IP3_22_21, TX3_D_IRDA_TX_D),
+	PINMUX_IPSR_GPSR(IP3_15, DU0_DB2),
+	PINMUX_IPSR_GPSR(IP3_15, LCDOUT18),
+	PINMUX_IPSR_GPSR(IP3_16, DU0_DB3),
+	PINMUX_IPSR_GPSR(IP3_16, LCDOUT19),
+	PINMUX_IPSR_GPSR(IP3_17, DU0_DB4),
+	PINMUX_IPSR_GPSR(IP3_17, LCDOUT20),
+	PINMUX_IPSR_GPSR(IP3_18, DU0_DB5),
+	PINMUX_IPSR_GPSR(IP3_18, LCDOUT21),
+	PINMUX_IPSR_GPSR(IP3_19, DU0_DB6),
+	PINMUX_IPSR_GPSR(IP3_19, LCDOUT22),
+	PINMUX_IPSR_GPSR(IP3_20, DU0_DB7),
+	PINMUX_IPSR_GPSR(IP3_20, LCDOUT23),
+	PINMUX_IPSR_GPSR(IP3_22_21, DU0_DOTCLKIN),
+	PINMUX_IPSR_GPSR(IP3_22_21, QSTVA_QVS),
+	PINMUX_IPSR_GPSR(IP3_22_21, TX3_D_IRDA_TX_D),
 	PINMUX_IPSR_MSEL(IP3_22_21, SCL3_B, SEL_I2C3_1),
-	PINMUX_IPSR_DATA(IP3_23, DU0_DOTCLKOUT0),
-	PINMUX_IPSR_DATA(IP3_23, QCLK),
-	PINMUX_IPSR_DATA(IP3_26_24, DU0_DOTCLKOUT1),
-	PINMUX_IPSR_DATA(IP3_26_24, QSTVB_QVE),
+	PINMUX_IPSR_GPSR(IP3_23, DU0_DOTCLKOUT0),
+	PINMUX_IPSR_GPSR(IP3_23, QCLK),
+	PINMUX_IPSR_GPSR(IP3_26_24, DU0_DOTCLKOUT1),
+	PINMUX_IPSR_GPSR(IP3_26_24, QSTVB_QVE),
 	PINMUX_IPSR_MSEL(IP3_26_24, RX3_D_IRDA_RX_D, SEL_SCIF3_3),
 	PINMUX_IPSR_MSEL(IP3_26_24, SDA3_B, SEL_I2C3_1),
 	PINMUX_IPSR_MSEL(IP3_26_24, SDA2_C, SEL_I2C2_2),
-	PINMUX_IPSR_DATA(IP3_26_24, DACK0_B),
-	PINMUX_IPSR_DATA(IP3_26_24, DRACK0_B),
-	PINMUX_IPSR_DATA(IP3_27, DU0_EXHSYNC_DU0_HSYNC),
-	PINMUX_IPSR_DATA(IP3_27, QSTH_QHS),
-	PINMUX_IPSR_DATA(IP3_28, DU0_EXVSYNC_DU0_VSYNC),
-	PINMUX_IPSR_DATA(IP3_28, QSTB_QHE),
-	PINMUX_IPSR_DATA(IP3_31_29, DU0_EXODDF_DU0_ODDF_DISP_CDE),
-	PINMUX_IPSR_DATA(IP3_31_29, QCPV_QDE),
-	PINMUX_IPSR_DATA(IP3_31_29, CAN1_TX),
-	PINMUX_IPSR_DATA(IP3_31_29, TX2_C),
+	PINMUX_IPSR_GPSR(IP3_26_24, DACK0_B),
+	PINMUX_IPSR_GPSR(IP3_26_24, DRACK0_B),
+	PINMUX_IPSR_GPSR(IP3_27, DU0_EXHSYNC_DU0_HSYNC),
+	PINMUX_IPSR_GPSR(IP3_27, QSTH_QHS),
+	PINMUX_IPSR_GPSR(IP3_28, DU0_EXVSYNC_DU0_VSYNC),
+	PINMUX_IPSR_GPSR(IP3_28, QSTB_QHE),
+	PINMUX_IPSR_GPSR(IP3_31_29, DU0_EXODDF_DU0_ODDF_DISP_CDE),
+	PINMUX_IPSR_GPSR(IP3_31_29, QCPV_QDE),
+	PINMUX_IPSR_GPSR(IP3_31_29, CAN1_TX),
+	PINMUX_IPSR_GPSR(IP3_31_29, TX2_C),
 	PINMUX_IPSR_MSEL(IP3_31_29, SCL2_C, SEL_I2C2_2),
-	PINMUX_IPSR_DATA(IP3_31_29, REMOCON),
+	PINMUX_IPSR_GPSR(IP3_31_29, REMOCON),
 
-	PINMUX_IPSR_DATA(IP4_1_0, DU0_DISP),
-	PINMUX_IPSR_DATA(IP4_1_0, QPOLA),
+	PINMUX_IPSR_GPSR(IP4_1_0, DU0_DISP),
+	PINMUX_IPSR_GPSR(IP4_1_0, QPOLA),
 	PINMUX_IPSR_MSEL(IP4_1_0, CAN_CLK_C, SEL_CANCLK_2),
 	PINMUX_IPSR_MSEL(IP4_1_0, SCK2_C, SEL_SCIF2_2),
-	PINMUX_IPSR_DATA(IP4_4_2, DU0_CDE),
-	PINMUX_IPSR_DATA(IP4_4_2, QPOLB),
-	PINMUX_IPSR_DATA(IP4_4_2, CAN1_RX),
+	PINMUX_IPSR_GPSR(IP4_4_2, DU0_CDE),
+	PINMUX_IPSR_GPSR(IP4_4_2, QPOLB),
+	PINMUX_IPSR_GPSR(IP4_4_2, CAN1_RX),
 	PINMUX_IPSR_MSEL(IP4_4_2, RX2_C, SEL_SCIF2_2),
 	PINMUX_IPSR_MSEL(IP4_4_2, DREQ0_B, SEL_EXBUS0_1),
 	PINMUX_IPSR_MSEL(IP4_4_2, SSI_SCK78_B, SEL_SSI7_1),
 	PINMUX_IPSR_MSEL(IP4_4_2, SCK0_B, SEL_SCIF0_1),
-	PINMUX_IPSR_DATA(IP4_7_5, DU1_DR0),
-	PINMUX_IPSR_DATA(IP4_7_5, VI2_DATA0_VI2_B0),
-	PINMUX_IPSR_DATA(IP4_7_5, PWM6),
-	PINMUX_IPSR_DATA(IP4_7_5, SD3_CLK),
-	PINMUX_IPSR_DATA(IP4_7_5, TX3_E_IRDA_TX_E),
-	PINMUX_IPSR_DATA(IP4_7_5, AUDCK),
+	PINMUX_IPSR_GPSR(IP4_7_5, DU1_DR0),
+	PINMUX_IPSR_GPSR(IP4_7_5, VI2_DATA0_VI2_B0),
+	PINMUX_IPSR_GPSR(IP4_7_5, PWM6),
+	PINMUX_IPSR_GPSR(IP4_7_5, SD3_CLK),
+	PINMUX_IPSR_GPSR(IP4_7_5, TX3_E_IRDA_TX_E),
+	PINMUX_IPSR_GPSR(IP4_7_5, AUDCK),
 	PINMUX_IPSR_MSEL(IP4_7_5, PWMFSW0_B, SEL_PWMFSW_1),
-	PINMUX_IPSR_DATA(IP4_10_8, DU1_DR1),
-	PINMUX_IPSR_DATA(IP4_10_8, VI2_DATA1_VI2_B1),
-	PINMUX_IPSR_DATA(IP4_10_8, PWM0),
-	PINMUX_IPSR_DATA(IP4_10_8, SD3_CMD),
+	PINMUX_IPSR_GPSR(IP4_10_8, DU1_DR1),
+	PINMUX_IPSR_GPSR(IP4_10_8, VI2_DATA1_VI2_B1),
+	PINMUX_IPSR_GPSR(IP4_10_8, PWM0),
+	PINMUX_IPSR_GPSR(IP4_10_8, SD3_CMD),
 	PINMUX_IPSR_MSEL(IP4_10_8, RX3_E_IRDA_RX_E, SEL_SCIF3_4),
-	PINMUX_IPSR_DATA(IP4_10_8, AUDSYNC),
+	PINMUX_IPSR_GPSR(IP4_10_8, AUDSYNC),
 	PINMUX_IPSR_MSEL(IP4_10_8, CTS0_D, SEL_SCIF0_3),
-	PINMUX_IPSR_DATA(IP4_11, DU1_DR2),
-	PINMUX_IPSR_DATA(IP4_11, VI2_G0),
-	PINMUX_IPSR_DATA(IP4_12, DU1_DR3),
-	PINMUX_IPSR_DATA(IP4_12, VI2_G1),
-	PINMUX_IPSR_DATA(IP4_13, DU1_DR4),
-	PINMUX_IPSR_DATA(IP4_13, VI2_G2),
-	PINMUX_IPSR_DATA(IP4_14, DU1_DR5),
-	PINMUX_IPSR_DATA(IP4_14, VI2_G3),
-	PINMUX_IPSR_DATA(IP4_15, DU1_DR6),
-	PINMUX_IPSR_DATA(IP4_15, VI2_G4),
-	PINMUX_IPSR_DATA(IP4_16, DU1_DR7),
-	PINMUX_IPSR_DATA(IP4_16, VI2_G5),
-	PINMUX_IPSR_DATA(IP4_19_17, DU1_DG0),
-	PINMUX_IPSR_DATA(IP4_19_17, VI2_DATA2_VI2_B2),
+	PINMUX_IPSR_GPSR(IP4_11, DU1_DR2),
+	PINMUX_IPSR_GPSR(IP4_11, VI2_G0),
+	PINMUX_IPSR_GPSR(IP4_12, DU1_DR3),
+	PINMUX_IPSR_GPSR(IP4_12, VI2_G1),
+	PINMUX_IPSR_GPSR(IP4_13, DU1_DR4),
+	PINMUX_IPSR_GPSR(IP4_13, VI2_G2),
+	PINMUX_IPSR_GPSR(IP4_14, DU1_DR5),
+	PINMUX_IPSR_GPSR(IP4_14, VI2_G3),
+	PINMUX_IPSR_GPSR(IP4_15, DU1_DR6),
+	PINMUX_IPSR_GPSR(IP4_15, VI2_G4),
+	PINMUX_IPSR_GPSR(IP4_16, DU1_DR7),
+	PINMUX_IPSR_GPSR(IP4_16, VI2_G5),
+	PINMUX_IPSR_GPSR(IP4_19_17, DU1_DG0),
+	PINMUX_IPSR_GPSR(IP4_19_17, VI2_DATA2_VI2_B2),
 	PINMUX_IPSR_MSEL(IP4_19_17, SCL1_B, SEL_I2C1_1),
-	PINMUX_IPSR_DATA(IP4_19_17, SD3_DAT2),
+	PINMUX_IPSR_GPSR(IP4_19_17, SD3_DAT2),
 	PINMUX_IPSR_MSEL(IP4_19_17, SCK3_E, SEL_SCIF3_4),
-	PINMUX_IPSR_DATA(IP4_19_17, AUDATA6),
-	PINMUX_IPSR_DATA(IP4_19_17, TX0_D),
-	PINMUX_IPSR_DATA(IP4_22_20, DU1_DG1),
-	PINMUX_IPSR_DATA(IP4_22_20, VI2_DATA3_VI2_B3),
+	PINMUX_IPSR_GPSR(IP4_19_17, AUDATA6),
+	PINMUX_IPSR_GPSR(IP4_19_17, TX0_D),
+	PINMUX_IPSR_GPSR(IP4_22_20, DU1_DG1),
+	PINMUX_IPSR_GPSR(IP4_22_20, VI2_DATA3_VI2_B3),
 	PINMUX_IPSR_MSEL(IP4_22_20, SDA1_B, SEL_I2C1_1),
-	PINMUX_IPSR_DATA(IP4_22_20, SD3_DAT3),
+	PINMUX_IPSR_GPSR(IP4_22_20, SD3_DAT3),
 	PINMUX_IPSR_MSEL(IP4_22_20, SCK5, SEL_SCIF5_0),
-	PINMUX_IPSR_DATA(IP4_22_20, AUDATA7),
+	PINMUX_IPSR_GPSR(IP4_22_20, AUDATA7),
 	PINMUX_IPSR_MSEL(IP4_22_20, RX0_D, SEL_SCIF0_3),
-	PINMUX_IPSR_DATA(IP4_23, DU1_DG2),
-	PINMUX_IPSR_DATA(IP4_23, VI2_G6),
-	PINMUX_IPSR_DATA(IP4_24, DU1_DG3),
-	PINMUX_IPSR_DATA(IP4_24, VI2_G7),
-	PINMUX_IPSR_DATA(IP4_25, DU1_DG4),
-	PINMUX_IPSR_DATA(IP4_25, VI2_R0),
-	PINMUX_IPSR_DATA(IP4_26, DU1_DG5),
-	PINMUX_IPSR_DATA(IP4_26, VI2_R1),
-	PINMUX_IPSR_DATA(IP4_27, DU1_DG6),
-	PINMUX_IPSR_DATA(IP4_27, VI2_R2),
-	PINMUX_IPSR_DATA(IP4_28, DU1_DG7),
-	PINMUX_IPSR_DATA(IP4_28, VI2_R3),
-	PINMUX_IPSR_DATA(IP4_31_29, DU1_DB0),
-	PINMUX_IPSR_DATA(IP4_31_29, VI2_DATA4_VI2_B4),
+	PINMUX_IPSR_GPSR(IP4_23, DU1_DG2),
+	PINMUX_IPSR_GPSR(IP4_23, VI2_G6),
+	PINMUX_IPSR_GPSR(IP4_24, DU1_DG3),
+	PINMUX_IPSR_GPSR(IP4_24, VI2_G7),
+	PINMUX_IPSR_GPSR(IP4_25, DU1_DG4),
+	PINMUX_IPSR_GPSR(IP4_25, VI2_R0),
+	PINMUX_IPSR_GPSR(IP4_26, DU1_DG5),
+	PINMUX_IPSR_GPSR(IP4_26, VI2_R1),
+	PINMUX_IPSR_GPSR(IP4_27, DU1_DG6),
+	PINMUX_IPSR_GPSR(IP4_27, VI2_R2),
+	PINMUX_IPSR_GPSR(IP4_28, DU1_DG7),
+	PINMUX_IPSR_GPSR(IP4_28, VI2_R3),
+	PINMUX_IPSR_GPSR(IP4_31_29, DU1_DB0),
+	PINMUX_IPSR_GPSR(IP4_31_29, VI2_DATA4_VI2_B4),
 	PINMUX_IPSR_MSEL(IP4_31_29, SCL2_B, SEL_I2C2_1),
-	PINMUX_IPSR_DATA(IP4_31_29, SD3_DAT0),
-	PINMUX_IPSR_DATA(IP4_31_29, TX5),
+	PINMUX_IPSR_GPSR(IP4_31_29, SD3_DAT0),
+	PINMUX_IPSR_GPSR(IP4_31_29, TX5),
 	PINMUX_IPSR_MSEL(IP4_31_29, SCK0_D, SEL_SCIF0_3),
 
-	PINMUX_IPSR_DATA(IP5_2_0, DU1_DB1),
-	PINMUX_IPSR_DATA(IP5_2_0, VI2_DATA5_VI2_B5),
+	PINMUX_IPSR_GPSR(IP5_2_0, DU1_DB1),
+	PINMUX_IPSR_GPSR(IP5_2_0, VI2_DATA5_VI2_B5),
 	PINMUX_IPSR_MSEL(IP5_2_0, SDA2_B, SEL_I2C2_1),
-	PINMUX_IPSR_DATA(IP5_2_0, SD3_DAT1),
+	PINMUX_IPSR_GPSR(IP5_2_0, SD3_DAT1),
 	PINMUX_IPSR_MSEL(IP5_2_0, RX5, SEL_SCIF5_0),
 	PINMUX_IPSR_MSEL(IP5_2_0, RTS0_D_TANS_D, SEL_SCIF0_3),
-	PINMUX_IPSR_DATA(IP5_3, DU1_DB2),
-	PINMUX_IPSR_DATA(IP5_3, VI2_R4),
-	PINMUX_IPSR_DATA(IP5_4, DU1_DB3),
-	PINMUX_IPSR_DATA(IP5_4, VI2_R5),
-	PINMUX_IPSR_DATA(IP5_5, DU1_DB4),
-	PINMUX_IPSR_DATA(IP5_5, VI2_R6),
-	PINMUX_IPSR_DATA(IP5_6, DU1_DB5),
-	PINMUX_IPSR_DATA(IP5_6, VI2_R7),
-	PINMUX_IPSR_DATA(IP5_7, DU1_DB6),
+	PINMUX_IPSR_GPSR(IP5_3, DU1_DB2),
+	PINMUX_IPSR_GPSR(IP5_3, VI2_R4),
+	PINMUX_IPSR_GPSR(IP5_4, DU1_DB3),
+	PINMUX_IPSR_GPSR(IP5_4, VI2_R5),
+	PINMUX_IPSR_GPSR(IP5_5, DU1_DB4),
+	PINMUX_IPSR_GPSR(IP5_5, VI2_R6),
+	PINMUX_IPSR_GPSR(IP5_6, DU1_DB5),
+	PINMUX_IPSR_GPSR(IP5_6, VI2_R7),
+	PINMUX_IPSR_GPSR(IP5_7, DU1_DB6),
 	PINMUX_IPSR_MSEL(IP5_7, SCL2_D, SEL_I2C2_3),
-	PINMUX_IPSR_DATA(IP5_8, DU1_DB7),
+	PINMUX_IPSR_GPSR(IP5_8, DU1_DB7),
 	PINMUX_IPSR_MSEL(IP5_8, SDA2_D, SEL_I2C2_3),
-	PINMUX_IPSR_DATA(IP5_10_9, DU1_DOTCLKIN),
-	PINMUX_IPSR_DATA(IP5_10_9, VI2_CLKENB),
+	PINMUX_IPSR_GPSR(IP5_10_9, DU1_DOTCLKIN),
+	PINMUX_IPSR_GPSR(IP5_10_9, VI2_CLKENB),
 	PINMUX_IPSR_MSEL(IP5_10_9, HSPI_CS1, SEL_HSPI1_0),
 	PINMUX_IPSR_MSEL(IP5_10_9, SCL1_D, SEL_I2C1_3),
-	PINMUX_IPSR_DATA(IP5_12_11, DU1_DOTCLKOUT),
-	PINMUX_IPSR_DATA(IP5_12_11, VI2_FIELD),
+	PINMUX_IPSR_GPSR(IP5_12_11, DU1_DOTCLKOUT),
+	PINMUX_IPSR_GPSR(IP5_12_11, VI2_FIELD),
 	PINMUX_IPSR_MSEL(IP5_12_11, SDA1_D, SEL_I2C1_3),
-	PINMUX_IPSR_DATA(IP5_14_13, DU1_EXHSYNC_DU1_HSYNC),
-	PINMUX_IPSR_DATA(IP5_14_13, VI2_HSYNC),
-	PINMUX_IPSR_DATA(IP5_14_13, VI3_HSYNC),
-	PINMUX_IPSR_DATA(IP5_16_15, DU1_EXVSYNC_DU1_VSYNC),
-	PINMUX_IPSR_DATA(IP5_16_15, VI2_VSYNC),
-	PINMUX_IPSR_DATA(IP5_16_15, VI3_VSYNC),
-	PINMUX_IPSR_DATA(IP5_20_17, DU1_EXODDF_DU1_ODDF_DISP_CDE),
-	PINMUX_IPSR_DATA(IP5_20_17, VI2_CLK),
-	PINMUX_IPSR_DATA(IP5_20_17, TX3_B_IRDA_TX_B),
-	PINMUX_IPSR_DATA(IP5_20_17, SD3_CD),
-	PINMUX_IPSR_DATA(IP5_20_17, HSPI_TX1),
-	PINMUX_IPSR_DATA(IP5_20_17, VI1_CLKENB),
-	PINMUX_IPSR_DATA(IP5_20_17, VI3_CLKENB),
-	PINMUX_IPSR_DATA(IP5_20_17, AUDIO_CLKC),
-	PINMUX_IPSR_DATA(IP5_20_17, TX2_D),
-	PINMUX_IPSR_DATA(IP5_20_17, SPEEDIN),
+	PINMUX_IPSR_GPSR(IP5_14_13, DU1_EXHSYNC_DU1_HSYNC),
+	PINMUX_IPSR_GPSR(IP5_14_13, VI2_HSYNC),
+	PINMUX_IPSR_GPSR(IP5_14_13, VI3_HSYNC),
+	PINMUX_IPSR_GPSR(IP5_16_15, DU1_EXVSYNC_DU1_VSYNC),
+	PINMUX_IPSR_GPSR(IP5_16_15, VI2_VSYNC),
+	PINMUX_IPSR_GPSR(IP5_16_15, VI3_VSYNC),
+	PINMUX_IPSR_GPSR(IP5_20_17, DU1_EXODDF_DU1_ODDF_DISP_CDE),
+	PINMUX_IPSR_GPSR(IP5_20_17, VI2_CLK),
+	PINMUX_IPSR_GPSR(IP5_20_17, TX3_B_IRDA_TX_B),
+	PINMUX_IPSR_GPSR(IP5_20_17, SD3_CD),
+	PINMUX_IPSR_GPSR(IP5_20_17, HSPI_TX1),
+	PINMUX_IPSR_GPSR(IP5_20_17, VI1_CLKENB),
+	PINMUX_IPSR_GPSR(IP5_20_17, VI3_CLKENB),
+	PINMUX_IPSR_GPSR(IP5_20_17, AUDIO_CLKC),
+	PINMUX_IPSR_GPSR(IP5_20_17, TX2_D),
+	PINMUX_IPSR_GPSR(IP5_20_17, SPEEDIN),
 	PINMUX_IPSR_MSEL(IP5_20_17, GPS_SIGN_D, SEL_GPS_3),
-	PINMUX_IPSR_DATA(IP5_23_21, DU1_DISP),
-	PINMUX_IPSR_DATA(IP5_23_21, VI2_DATA6_VI2_B6),
+	PINMUX_IPSR_GPSR(IP5_23_21, DU1_DISP),
+	PINMUX_IPSR_GPSR(IP5_23_21, VI2_DATA6_VI2_B6),
 	PINMUX_IPSR_MSEL(IP5_23_21, TCLK0, SEL_TMU0_0),
-	PINMUX_IPSR_DATA(IP5_23_21, QSTVA_B_QVS_B),
+	PINMUX_IPSR_GPSR(IP5_23_21, QSTVA_B_QVS_B),
 	PINMUX_IPSR_MSEL(IP5_23_21, HSPI_CLK1, SEL_HSPI1_0),
 	PINMUX_IPSR_MSEL(IP5_23_21, SCK2_D, SEL_SCIF2_3),
-	PINMUX_IPSR_DATA(IP5_23_21, AUDIO_CLKOUT_B),
+	PINMUX_IPSR_GPSR(IP5_23_21, AUDIO_CLKOUT_B),
 	PINMUX_IPSR_MSEL(IP5_23_21, GPS_MAG_D, SEL_GPS_3),
-	PINMUX_IPSR_DATA(IP5_27_24, DU1_CDE),
-	PINMUX_IPSR_DATA(IP5_27_24, VI2_DATA7_VI2_B7),
+	PINMUX_IPSR_GPSR(IP5_27_24, DU1_CDE),
+	PINMUX_IPSR_GPSR(IP5_27_24, VI2_DATA7_VI2_B7),
 	PINMUX_IPSR_MSEL(IP5_27_24, RX3_B_IRDA_RX_B, SEL_SCIF3_1),
-	PINMUX_IPSR_DATA(IP5_27_24, SD3_WP),
+	PINMUX_IPSR_GPSR(IP5_27_24, SD3_WP),
 	PINMUX_IPSR_MSEL(IP5_27_24, HSPI_RX1, SEL_HSPI1_0),
-	PINMUX_IPSR_DATA(IP5_27_24, VI1_FIELD),
-	PINMUX_IPSR_DATA(IP5_27_24, VI3_FIELD),
-	PINMUX_IPSR_DATA(IP5_27_24, AUDIO_CLKOUT),
+	PINMUX_IPSR_GPSR(IP5_27_24, VI1_FIELD),
+	PINMUX_IPSR_GPSR(IP5_27_24, VI3_FIELD),
+	PINMUX_IPSR_GPSR(IP5_27_24, AUDIO_CLKOUT),
 	PINMUX_IPSR_MSEL(IP5_27_24, RX2_D, SEL_SCIF2_3),
 	PINMUX_IPSR_MSEL(IP5_27_24, GPS_CLK_C, SEL_GPS_2),
 	PINMUX_IPSR_MSEL(IP5_27_24, GPS_CLK_D, SEL_GPS_3),
-	PINMUX_IPSR_DATA(IP5_28, AUDIO_CLKA),
-	PINMUX_IPSR_DATA(IP5_28, CAN_TXCLK),
-	PINMUX_IPSR_DATA(IP5_30_29, AUDIO_CLKB),
-	PINMUX_IPSR_DATA(IP5_30_29, USB_OVC2),
-	PINMUX_IPSR_DATA(IP5_30_29, CAN_DEBUGOUT0),
-	PINMUX_IPSR_DATA(IP5_30_29, MOUT0),
-
-	PINMUX_IPSR_DATA(IP6_1_0, SSI_SCK0129),
-	PINMUX_IPSR_DATA(IP6_1_0, CAN_DEBUGOUT1),
-	PINMUX_IPSR_DATA(IP6_1_0, MOUT1),
-	PINMUX_IPSR_DATA(IP6_3_2, SSI_WS0129),
-	PINMUX_IPSR_DATA(IP6_3_2, CAN_DEBUGOUT2),
-	PINMUX_IPSR_DATA(IP6_3_2, MOUT2),
-	PINMUX_IPSR_DATA(IP6_5_4, SSI_SDATA0),
-	PINMUX_IPSR_DATA(IP6_5_4, CAN_DEBUGOUT3),
-	PINMUX_IPSR_DATA(IP6_5_4, MOUT5),
-	PINMUX_IPSR_DATA(IP6_7_6, SSI_SDATA1),
-	PINMUX_IPSR_DATA(IP6_7_6, CAN_DEBUGOUT4),
-	PINMUX_IPSR_DATA(IP6_7_6, MOUT6),
-	PINMUX_IPSR_DATA(IP6_8, SSI_SDATA2),
-	PINMUX_IPSR_DATA(IP6_8, CAN_DEBUGOUT5),
-	PINMUX_IPSR_DATA(IP6_11_9, SSI_SCK34),
-	PINMUX_IPSR_DATA(IP6_11_9, CAN_DEBUGOUT6),
-	PINMUX_IPSR_DATA(IP6_11_9, CAN0_TX_B),
+	PINMUX_IPSR_GPSR(IP5_28, AUDIO_CLKA),
+	PINMUX_IPSR_GPSR(IP5_28, CAN_TXCLK),
+	PINMUX_IPSR_GPSR(IP5_30_29, AUDIO_CLKB),
+	PINMUX_IPSR_GPSR(IP5_30_29, USB_OVC2),
+	PINMUX_IPSR_GPSR(IP5_30_29, CAN_DEBUGOUT0),
+	PINMUX_IPSR_GPSR(IP5_30_29, MOUT0),
+
+	PINMUX_IPSR_GPSR(IP6_1_0, SSI_SCK0129),
+	PINMUX_IPSR_GPSR(IP6_1_0, CAN_DEBUGOUT1),
+	PINMUX_IPSR_GPSR(IP6_1_0, MOUT1),
+	PINMUX_IPSR_GPSR(IP6_3_2, SSI_WS0129),
+	PINMUX_IPSR_GPSR(IP6_3_2, CAN_DEBUGOUT2),
+	PINMUX_IPSR_GPSR(IP6_3_2, MOUT2),
+	PINMUX_IPSR_GPSR(IP6_5_4, SSI_SDATA0),
+	PINMUX_IPSR_GPSR(IP6_5_4, CAN_DEBUGOUT3),
+	PINMUX_IPSR_GPSR(IP6_5_4, MOUT5),
+	PINMUX_IPSR_GPSR(IP6_7_6, SSI_SDATA1),
+	PINMUX_IPSR_GPSR(IP6_7_6, CAN_DEBUGOUT4),
+	PINMUX_IPSR_GPSR(IP6_7_6, MOUT6),
+	PINMUX_IPSR_GPSR(IP6_8, SSI_SDATA2),
+	PINMUX_IPSR_GPSR(IP6_8, CAN_DEBUGOUT5),
+	PINMUX_IPSR_GPSR(IP6_11_9, SSI_SCK34),
+	PINMUX_IPSR_GPSR(IP6_11_9, CAN_DEBUGOUT6),
+	PINMUX_IPSR_GPSR(IP6_11_9, CAN0_TX_B),
 	PINMUX_IPSR_MSEL(IP6_11_9, IERX, SEL_IE_0),
 	PINMUX_IPSR_MSEL(IP6_11_9, SSI_SCK9_C, SEL_SSI9_2),
-	PINMUX_IPSR_DATA(IP6_14_12, SSI_WS34),
-	PINMUX_IPSR_DATA(IP6_14_12, CAN_DEBUGOUT7),
+	PINMUX_IPSR_GPSR(IP6_14_12, SSI_WS34),
+	PINMUX_IPSR_GPSR(IP6_14_12, CAN_DEBUGOUT7),
 	PINMUX_IPSR_MSEL(IP6_14_12, CAN0_RX_B, SEL_CAN0_1),
-	PINMUX_IPSR_DATA(IP6_14_12, IETX),
+	PINMUX_IPSR_GPSR(IP6_14_12, IETX),
 	PINMUX_IPSR_MSEL(IP6_14_12, SSI_WS9_C, SEL_SSI9_2),
-	PINMUX_IPSR_DATA(IP6_17_15, SSI_SDATA3),
-	PINMUX_IPSR_DATA(IP6_17_15, PWM0_C),
-	PINMUX_IPSR_DATA(IP6_17_15, CAN_DEBUGOUT8),
+	PINMUX_IPSR_GPSR(IP6_17_15, SSI_SDATA3),
+	PINMUX_IPSR_GPSR(IP6_17_15, PWM0_C),
+	PINMUX_IPSR_GPSR(IP6_17_15, CAN_DEBUGOUT8),
 	PINMUX_IPSR_MSEL(IP6_17_15, CAN_CLK_B, SEL_CANCLK_1),
 	PINMUX_IPSR_MSEL(IP6_17_15, IECLK, SEL_IE_0),
 	PINMUX_IPSR_MSEL(IP6_17_15, SCIF_CLK_B, SEL_SCIF_1),
 	PINMUX_IPSR_MSEL(IP6_17_15, TCLK0_B, SEL_TMU0_1),
-	PINMUX_IPSR_DATA(IP6_19_18, SSI_SDATA4),
-	PINMUX_IPSR_DATA(IP6_19_18, CAN_DEBUGOUT9),
+	PINMUX_IPSR_GPSR(IP6_19_18, SSI_SDATA4),
+	PINMUX_IPSR_GPSR(IP6_19_18, CAN_DEBUGOUT9),
 	PINMUX_IPSR_MSEL(IP6_19_18, SSI_SDATA9_C, SEL_SSI9_2),
-	PINMUX_IPSR_DATA(IP6_22_20, SSI_SCK5),
-	PINMUX_IPSR_DATA(IP6_22_20, ADICLK),
-	PINMUX_IPSR_DATA(IP6_22_20, CAN_DEBUGOUT10),
+	PINMUX_IPSR_GPSR(IP6_22_20, SSI_SCK5),
+	PINMUX_IPSR_GPSR(IP6_22_20, ADICLK),
+	PINMUX_IPSR_GPSR(IP6_22_20, CAN_DEBUGOUT10),
 	PINMUX_IPSR_MSEL(IP6_22_20, SCK3, SEL_SCIF3_0),
 	PINMUX_IPSR_MSEL(IP6_22_20, TCLK0_D, SEL_TMU0_3),
-	PINMUX_IPSR_DATA(IP6_24_23, SSI_WS5),
+	PINMUX_IPSR_GPSR(IP6_24_23, SSI_WS5),
 	PINMUX_IPSR_MSEL(IP6_24_23, ADICS_SAMP, SEL_ADI_0),
-	PINMUX_IPSR_DATA(IP6_24_23, CAN_DEBUGOUT11),
-	PINMUX_IPSR_DATA(IP6_24_23, TX3_IRDA_TX),
-	PINMUX_IPSR_DATA(IP6_26_25, SSI_SDATA5),
+	PINMUX_IPSR_GPSR(IP6_24_23, CAN_DEBUGOUT11),
+	PINMUX_IPSR_GPSR(IP6_24_23, TX3_IRDA_TX),
+	PINMUX_IPSR_GPSR(IP6_26_25, SSI_SDATA5),
 	PINMUX_IPSR_MSEL(IP6_26_25, ADIDATA, SEL_ADI_0),
-	PINMUX_IPSR_DATA(IP6_26_25, CAN_DEBUGOUT12),
+	PINMUX_IPSR_GPSR(IP6_26_25, CAN_DEBUGOUT12),
 	PINMUX_IPSR_MSEL(IP6_26_25, RX3_IRDA_RX, SEL_SCIF3_0),
-	PINMUX_IPSR_DATA(IP6_30_29, SSI_SCK6),
-	PINMUX_IPSR_DATA(IP6_30_29, ADICHS0),
-	PINMUX_IPSR_DATA(IP6_30_29, CAN0_TX),
+	PINMUX_IPSR_GPSR(IP6_30_29, SSI_SCK6),
+	PINMUX_IPSR_GPSR(IP6_30_29, ADICHS0),
+	PINMUX_IPSR_GPSR(IP6_30_29, CAN0_TX),
 	PINMUX_IPSR_MSEL(IP6_30_29, IERX_B, SEL_IE_1),
 
-	PINMUX_IPSR_DATA(IP7_1_0, SSI_WS6),
-	PINMUX_IPSR_DATA(IP7_1_0, ADICHS1),
+	PINMUX_IPSR_GPSR(IP7_1_0, SSI_WS6),
+	PINMUX_IPSR_GPSR(IP7_1_0, ADICHS1),
 	PINMUX_IPSR_MSEL(IP7_1_0, CAN0_RX, SEL_CAN0_0),
-	PINMUX_IPSR_DATA(IP7_1_0, IETX_B),
-	PINMUX_IPSR_DATA(IP7_3_2, SSI_SDATA6),
-	PINMUX_IPSR_DATA(IP7_3_2, ADICHS2),
+	PINMUX_IPSR_GPSR(IP7_1_0, IETX_B),
+	PINMUX_IPSR_GPSR(IP7_3_2, SSI_SDATA6),
+	PINMUX_IPSR_GPSR(IP7_3_2, ADICHS2),
 	PINMUX_IPSR_MSEL(IP7_3_2, CAN_CLK, SEL_CANCLK_0),
 	PINMUX_IPSR_MSEL(IP7_3_2, IECLK_B, SEL_IE_1),
 	PINMUX_IPSR_MSEL(IP7_6_4, SSI_SCK78, SEL_SSI7_0),
-	PINMUX_IPSR_DATA(IP7_6_4, CAN_DEBUGOUT13),
+	PINMUX_IPSR_GPSR(IP7_6_4, CAN_DEBUGOUT13),
 	PINMUX_IPSR_MSEL(IP7_6_4, IRQ0_B, SEL_INT0_1),
 	PINMUX_IPSR_MSEL(IP7_6_4, SSI_SCK9_B, SEL_SSI9_1),
 	PINMUX_IPSR_MSEL(IP7_6_4, HSPI_CLK1_C, SEL_HSPI1_2),
 	PINMUX_IPSR_MSEL(IP7_9_7, SSI_WS78, SEL_SSI7_0),
-	PINMUX_IPSR_DATA(IP7_9_7, CAN_DEBUGOUT14),
+	PINMUX_IPSR_GPSR(IP7_9_7, CAN_DEBUGOUT14),
 	PINMUX_IPSR_MSEL(IP7_9_7, IRQ1_B, SEL_INT1_1),
 	PINMUX_IPSR_MSEL(IP7_9_7, SSI_WS9_B, SEL_SSI9_1),
 	PINMUX_IPSR_MSEL(IP7_9_7, HSPI_CS1_C, SEL_HSPI1_2),
 	PINMUX_IPSR_MSEL(IP7_12_10, SSI_SDATA7, SEL_SSI7_0),
-	PINMUX_IPSR_DATA(IP7_12_10, CAN_DEBUGOUT15),
+	PINMUX_IPSR_GPSR(IP7_12_10, CAN_DEBUGOUT15),
 	PINMUX_IPSR_MSEL(IP7_12_10, IRQ2_B, SEL_INT2_1),
 	PINMUX_IPSR_MSEL(IP7_12_10, TCLK1_C, SEL_TMU1_2),
-	PINMUX_IPSR_DATA(IP7_12_10, HSPI_TX1_C),
+	PINMUX_IPSR_GPSR(IP7_12_10, HSPI_TX1_C),
 	PINMUX_IPSR_MSEL(IP7_14_13, SSI_SDATA8, SEL_SSI8_0),
-	PINMUX_IPSR_DATA(IP7_14_13, VSP),
+	PINMUX_IPSR_GPSR(IP7_14_13, VSP),
 	PINMUX_IPSR_MSEL(IP7_14_13, IRQ3_B, SEL_INT3_1),
 	PINMUX_IPSR_MSEL(IP7_14_13, HSPI_RX1_C, SEL_HSPI1_2),
-	PINMUX_IPSR_DATA(IP7_16_15, SD0_CLK),
-	PINMUX_IPSR_DATA(IP7_16_15, ATACS01),
+	PINMUX_IPSR_GPSR(IP7_16_15, SD0_CLK),
+	PINMUX_IPSR_GPSR(IP7_16_15, ATACS01),
 	PINMUX_IPSR_MSEL(IP7_16_15, SCK1_B, SEL_SCIF1_1),
-	PINMUX_IPSR_DATA(IP7_18_17, SD0_CMD),
-	PINMUX_IPSR_DATA(IP7_18_17, ATACS11),
-	PINMUX_IPSR_DATA(IP7_18_17, TX1_B),
-	PINMUX_IPSR_DATA(IP7_18_17, CC5_TDO),
-	PINMUX_IPSR_DATA(IP7_20_19, SD0_DAT0),
-	PINMUX_IPSR_DATA(IP7_20_19, ATADIR1),
+	PINMUX_IPSR_GPSR(IP7_18_17, SD0_CMD),
+	PINMUX_IPSR_GPSR(IP7_18_17, ATACS11),
+	PINMUX_IPSR_GPSR(IP7_18_17, TX1_B),
+	PINMUX_IPSR_GPSR(IP7_18_17, CC5_TDO),
+	PINMUX_IPSR_GPSR(IP7_20_19, SD0_DAT0),
+	PINMUX_IPSR_GPSR(IP7_20_19, ATADIR1),
 	PINMUX_IPSR_MSEL(IP7_20_19, RX1_B, SEL_SCIF1_1),
-	PINMUX_IPSR_DATA(IP7_20_19, CC5_TRST),
-	PINMUX_IPSR_DATA(IP7_22_21, SD0_DAT1),
-	PINMUX_IPSR_DATA(IP7_22_21, ATAG1),
+	PINMUX_IPSR_GPSR(IP7_20_19, CC5_TRST),
+	PINMUX_IPSR_GPSR(IP7_22_21, SD0_DAT1),
+	PINMUX_IPSR_GPSR(IP7_22_21, ATAG1),
 	PINMUX_IPSR_MSEL(IP7_22_21, SCK2_B, SEL_SCIF2_1),
-	PINMUX_IPSR_DATA(IP7_22_21, CC5_TMS),
-	PINMUX_IPSR_DATA(IP7_24_23, SD0_DAT2),
-	PINMUX_IPSR_DATA(IP7_24_23, ATARD1),
-	PINMUX_IPSR_DATA(IP7_24_23, TX2_B),
-	PINMUX_IPSR_DATA(IP7_24_23, CC5_TCK),
-	PINMUX_IPSR_DATA(IP7_26_25, SD0_DAT3),
-	PINMUX_IPSR_DATA(IP7_26_25, ATAWR1),
+	PINMUX_IPSR_GPSR(IP7_22_21, CC5_TMS),
+	PINMUX_IPSR_GPSR(IP7_24_23, SD0_DAT2),
+	PINMUX_IPSR_GPSR(IP7_24_23, ATARD1),
+	PINMUX_IPSR_GPSR(IP7_24_23, TX2_B),
+	PINMUX_IPSR_GPSR(IP7_24_23, CC5_TCK),
+	PINMUX_IPSR_GPSR(IP7_26_25, SD0_DAT3),
+	PINMUX_IPSR_GPSR(IP7_26_25, ATAWR1),
 	PINMUX_IPSR_MSEL(IP7_26_25, RX2_B, SEL_SCIF2_1),
-	PINMUX_IPSR_DATA(IP7_26_25, CC5_TDI),
-	PINMUX_IPSR_DATA(IP7_28_27, SD0_CD),
+	PINMUX_IPSR_GPSR(IP7_26_25, CC5_TDI),
+	PINMUX_IPSR_GPSR(IP7_28_27, SD0_CD),
 	PINMUX_IPSR_MSEL(IP7_28_27, DREQ2, SEL_EXBUS2_0),
 	PINMUX_IPSR_MSEL(IP7_28_27, RTS1_B_TANS_B, SEL_SCIF1_1),
-	PINMUX_IPSR_DATA(IP7_30_29, SD0_WP),
-	PINMUX_IPSR_DATA(IP7_30_29, DACK2),
+	PINMUX_IPSR_GPSR(IP7_30_29, SD0_WP),
+	PINMUX_IPSR_GPSR(IP7_30_29, DACK2),
 	PINMUX_IPSR_MSEL(IP7_30_29, CTS1_B, SEL_SCIF1_1),
 
-	PINMUX_IPSR_DATA(IP8_3_0, HSPI_CLK0),
+	PINMUX_IPSR_GPSR(IP8_3_0, HSPI_CLK0),
 	PINMUX_IPSR_MSEL(IP8_3_0, CTS0, SEL_SCIF0_0),
-	PINMUX_IPSR_DATA(IP8_3_0, USB_OVC0),
-	PINMUX_IPSR_DATA(IP8_3_0, AD_CLK),
-	PINMUX_IPSR_DATA(IP8_3_0, CC5_STATE4),
-	PINMUX_IPSR_DATA(IP8_3_0, CC5_STATE12),
-	PINMUX_IPSR_DATA(IP8_3_0, CC5_STATE20),
-	PINMUX_IPSR_DATA(IP8_3_0, CC5_STATE28),
-	PINMUX_IPSR_DATA(IP8_3_0, CC5_STATE36),
-	PINMUX_IPSR_DATA(IP8_7_4, HSPI_CS0),
+	PINMUX_IPSR_GPSR(IP8_3_0, USB_OVC0),
+	PINMUX_IPSR_GPSR(IP8_3_0, AD_CLK),
+	PINMUX_IPSR_GPSR(IP8_3_0, CC5_STATE4),
+	PINMUX_IPSR_GPSR(IP8_3_0, CC5_STATE12),
+	PINMUX_IPSR_GPSR(IP8_3_0, CC5_STATE20),
+	PINMUX_IPSR_GPSR(IP8_3_0, CC5_STATE28),
+	PINMUX_IPSR_GPSR(IP8_3_0, CC5_STATE36),
+	PINMUX_IPSR_GPSR(IP8_7_4, HSPI_CS0),
 	PINMUX_IPSR_MSEL(IP8_7_4, RTS0_TANS, SEL_SCIF0_0),
-	PINMUX_IPSR_DATA(IP8_7_4, USB_OVC1),
-	PINMUX_IPSR_DATA(IP8_7_4, AD_DI),
-	PINMUX_IPSR_DATA(IP8_7_4, CC5_STATE5),
-	PINMUX_IPSR_DATA(IP8_7_4, CC5_STATE13),
-	PINMUX_IPSR_DATA(IP8_7_4, CC5_STATE21),
-	PINMUX_IPSR_DATA(IP8_7_4, CC5_STATE29),
-	PINMUX_IPSR_DATA(IP8_7_4, CC5_STATE37),
-	PINMUX_IPSR_DATA(IP8_11_8, HSPI_TX0),
-	PINMUX_IPSR_DATA(IP8_11_8, TX0),
-	PINMUX_IPSR_DATA(IP8_11_8, CAN_DEBUG_HW_TRIGGER),
-	PINMUX_IPSR_DATA(IP8_11_8, AD_DO),
-	PINMUX_IPSR_DATA(IP8_11_8, CC5_STATE6),
-	PINMUX_IPSR_DATA(IP8_11_8, CC5_STATE14),
-	PINMUX_IPSR_DATA(IP8_11_8, CC5_STATE22),
-	PINMUX_IPSR_DATA(IP8_11_8, CC5_STATE30),
-	PINMUX_IPSR_DATA(IP8_11_8, CC5_STATE38),
-	PINMUX_IPSR_DATA(IP8_15_12, HSPI_RX0),
+	PINMUX_IPSR_GPSR(IP8_7_4, USB_OVC1),
+	PINMUX_IPSR_GPSR(IP8_7_4, AD_DI),
+	PINMUX_IPSR_GPSR(IP8_7_4, CC5_STATE5),
+	PINMUX_IPSR_GPSR(IP8_7_4, CC5_STATE13),
+	PINMUX_IPSR_GPSR(IP8_7_4, CC5_STATE21),
+	PINMUX_IPSR_GPSR(IP8_7_4, CC5_STATE29),
+	PINMUX_IPSR_GPSR(IP8_7_4, CC5_STATE37),
+	PINMUX_IPSR_GPSR(IP8_11_8, HSPI_TX0),
+	PINMUX_IPSR_GPSR(IP8_11_8, TX0),
+	PINMUX_IPSR_GPSR(IP8_11_8, CAN_DEBUG_HW_TRIGGER),
+	PINMUX_IPSR_GPSR(IP8_11_8, AD_DO),
+	PINMUX_IPSR_GPSR(IP8_11_8, CC5_STATE6),
+	PINMUX_IPSR_GPSR(IP8_11_8, CC5_STATE14),
+	PINMUX_IPSR_GPSR(IP8_11_8, CC5_STATE22),
+	PINMUX_IPSR_GPSR(IP8_11_8, CC5_STATE30),
+	PINMUX_IPSR_GPSR(IP8_11_8, CC5_STATE38),
+	PINMUX_IPSR_GPSR(IP8_15_12, HSPI_RX0),
 	PINMUX_IPSR_MSEL(IP8_15_12, RX0, SEL_SCIF0_0),
-	PINMUX_IPSR_DATA(IP8_15_12, CAN_STEP0),
-	PINMUX_IPSR_DATA(IP8_15_12, AD_NCS),
-	PINMUX_IPSR_DATA(IP8_15_12, CC5_STATE7),
-	PINMUX_IPSR_DATA(IP8_15_12, CC5_STATE15),
-	PINMUX_IPSR_DATA(IP8_15_12, CC5_STATE23),
-	PINMUX_IPSR_DATA(IP8_15_12, CC5_STATE31),
-	PINMUX_IPSR_DATA(IP8_15_12, CC5_STATE39),
-	PINMUX_IPSR_DATA(IP8_17_16, FMCLK),
-	PINMUX_IPSR_DATA(IP8_17_16, RDS_CLK),
-	PINMUX_IPSR_DATA(IP8_17_16, PCMOE),
-	PINMUX_IPSR_DATA(IP8_18, BPFCLK),
-	PINMUX_IPSR_DATA(IP8_18, PCMWE),
-	PINMUX_IPSR_DATA(IP8_19, FMIN),
-	PINMUX_IPSR_DATA(IP8_19, RDS_DATA),
-	PINMUX_IPSR_DATA(IP8_20, VI0_CLK),
-	PINMUX_IPSR_DATA(IP8_20, MMC1_CLK),
-	PINMUX_IPSR_DATA(IP8_22_21, VI0_CLKENB),
-	PINMUX_IPSR_DATA(IP8_22_21, TX1_C),
-	PINMUX_IPSR_DATA(IP8_22_21, HTX1_B),
-	PINMUX_IPSR_DATA(IP8_22_21, MT1_SYNC),
-	PINMUX_IPSR_DATA(IP8_24_23, VI0_FIELD),
+	PINMUX_IPSR_GPSR(IP8_15_12, CAN_STEP0),
+	PINMUX_IPSR_GPSR(IP8_15_12, AD_NCS),
+	PINMUX_IPSR_GPSR(IP8_15_12, CC5_STATE7),
+	PINMUX_IPSR_GPSR(IP8_15_12, CC5_STATE15),
+	PINMUX_IPSR_GPSR(IP8_15_12, CC5_STATE23),
+	PINMUX_IPSR_GPSR(IP8_15_12, CC5_STATE31),
+	PINMUX_IPSR_GPSR(IP8_15_12, CC5_STATE39),
+	PINMUX_IPSR_GPSR(IP8_17_16, FMCLK),
+	PINMUX_IPSR_GPSR(IP8_17_16, RDS_CLK),
+	PINMUX_IPSR_GPSR(IP8_17_16, PCMOE),
+	PINMUX_IPSR_GPSR(IP8_18, BPFCLK),
+	PINMUX_IPSR_GPSR(IP8_18, PCMWE),
+	PINMUX_IPSR_GPSR(IP8_19, FMIN),
+	PINMUX_IPSR_GPSR(IP8_19, RDS_DATA),
+	PINMUX_IPSR_GPSR(IP8_20, VI0_CLK),
+	PINMUX_IPSR_GPSR(IP8_20, MMC1_CLK),
+	PINMUX_IPSR_GPSR(IP8_22_21, VI0_CLKENB),
+	PINMUX_IPSR_GPSR(IP8_22_21, TX1_C),
+	PINMUX_IPSR_GPSR(IP8_22_21, HTX1_B),
+	PINMUX_IPSR_GPSR(IP8_22_21, MT1_SYNC),
+	PINMUX_IPSR_GPSR(IP8_24_23, VI0_FIELD),
 	PINMUX_IPSR_MSEL(IP8_24_23, RX1_C, SEL_SCIF1_2),
 	PINMUX_IPSR_MSEL(IP8_24_23, HRX1_B, SEL_HSCIF1_1),
-	PINMUX_IPSR_DATA(IP8_27_25, VI0_HSYNC),
+	PINMUX_IPSR_GPSR(IP8_27_25, VI0_HSYNC),
 	PINMUX_IPSR_MSEL(IP8_27_25, VI0_DATA0_B_VI0_B0_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP8_27_25, CTS1_C, SEL_SCIF1_2),
-	PINMUX_IPSR_DATA(IP8_27_25, TX4_D),
-	PINMUX_IPSR_DATA(IP8_27_25, MMC1_CMD),
+	PINMUX_IPSR_GPSR(IP8_27_25, TX4_D),
+	PINMUX_IPSR_GPSR(IP8_27_25, MMC1_CMD),
 	PINMUX_IPSR_MSEL(IP8_27_25, HSCK1_B, SEL_HSCIF1_1),
-	PINMUX_IPSR_DATA(IP8_30_28, VI0_VSYNC),
+	PINMUX_IPSR_GPSR(IP8_30_28, VI0_VSYNC),
 	PINMUX_IPSR_MSEL(IP8_30_28, VI0_DATA1_B_VI0_B1_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP8_30_28, RTS1_C_TANS_C, SEL_SCIF1_2),
 	PINMUX_IPSR_MSEL(IP8_30_28, RX4_D, SEL_SCIF4_3),
@@ -1189,216 +1189,216 @@ static const u16 pinmux_data[] = {
 
 	PINMUX_IPSR_MSEL(IP9_1_0, VI0_DATA0_VI0_B0, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP9_1_0, HRTS1_B, SEL_HSCIF1_1),
-	PINMUX_IPSR_DATA(IP9_1_0, MT1_VCXO),
+	PINMUX_IPSR_GPSR(IP9_1_0, MT1_VCXO),
 	PINMUX_IPSR_MSEL(IP9_3_2, VI0_DATA1_VI0_B1, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP9_3_2, HCTS1_B, SEL_HSCIF1_1),
-	PINMUX_IPSR_DATA(IP9_3_2, MT1_PWM),
-	PINMUX_IPSR_DATA(IP9_4, VI0_DATA2_VI0_B2),
-	PINMUX_IPSR_DATA(IP9_4, MMC1_D0),
-	PINMUX_IPSR_DATA(IP9_5, VI0_DATA3_VI0_B3),
-	PINMUX_IPSR_DATA(IP9_5, MMC1_D1),
-	PINMUX_IPSR_DATA(IP9_6, VI0_DATA4_VI0_B4),
-	PINMUX_IPSR_DATA(IP9_6, MMC1_D2),
-	PINMUX_IPSR_DATA(IP9_7, VI0_DATA5_VI0_B5),
-	PINMUX_IPSR_DATA(IP9_7, MMC1_D3),
-	PINMUX_IPSR_DATA(IP9_9_8, VI0_DATA6_VI0_B6),
-	PINMUX_IPSR_DATA(IP9_9_8, MMC1_D4),
-	PINMUX_IPSR_DATA(IP9_9_8, ARM_TRACEDATA_0),
-	PINMUX_IPSR_DATA(IP9_11_10, VI0_DATA7_VI0_B7),
-	PINMUX_IPSR_DATA(IP9_11_10, MMC1_D5),
-	PINMUX_IPSR_DATA(IP9_11_10, ARM_TRACEDATA_1),
-	PINMUX_IPSR_DATA(IP9_13_12, VI0_G0),
+	PINMUX_IPSR_GPSR(IP9_3_2, MT1_PWM),
+	PINMUX_IPSR_GPSR(IP9_4, VI0_DATA2_VI0_B2),
+	PINMUX_IPSR_GPSR(IP9_4, MMC1_D0),
+	PINMUX_IPSR_GPSR(IP9_5, VI0_DATA3_VI0_B3),
+	PINMUX_IPSR_GPSR(IP9_5, MMC1_D1),
+	PINMUX_IPSR_GPSR(IP9_6, VI0_DATA4_VI0_B4),
+	PINMUX_IPSR_GPSR(IP9_6, MMC1_D2),
+	PINMUX_IPSR_GPSR(IP9_7, VI0_DATA5_VI0_B5),
+	PINMUX_IPSR_GPSR(IP9_7, MMC1_D3),
+	PINMUX_IPSR_GPSR(IP9_9_8, VI0_DATA6_VI0_B6),
+	PINMUX_IPSR_GPSR(IP9_9_8, MMC1_D4),
+	PINMUX_IPSR_GPSR(IP9_9_8, ARM_TRACEDATA_0),
+	PINMUX_IPSR_GPSR(IP9_11_10, VI0_DATA7_VI0_B7),
+	PINMUX_IPSR_GPSR(IP9_11_10, MMC1_D5),
+	PINMUX_IPSR_GPSR(IP9_11_10, ARM_TRACEDATA_1),
+	PINMUX_IPSR_GPSR(IP9_13_12, VI0_G0),
 	PINMUX_IPSR_MSEL(IP9_13_12, SSI_SCK78_C, SEL_SSI7_2),
 	PINMUX_IPSR_MSEL(IP9_13_12, IRQ0, SEL_INT0_0),
-	PINMUX_IPSR_DATA(IP9_13_12, ARM_TRACEDATA_2),
-	PINMUX_IPSR_DATA(IP9_15_14, VI0_G1),
+	PINMUX_IPSR_GPSR(IP9_13_12, ARM_TRACEDATA_2),
+	PINMUX_IPSR_GPSR(IP9_15_14, VI0_G1),
 	PINMUX_IPSR_MSEL(IP9_15_14, SSI_WS78_C, SEL_SSI7_2),
 	PINMUX_IPSR_MSEL(IP9_15_14, IRQ1, SEL_INT1_0),
-	PINMUX_IPSR_DATA(IP9_15_14, ARM_TRACEDATA_3),
-	PINMUX_IPSR_DATA(IP9_18_16, VI0_G2),
-	PINMUX_IPSR_DATA(IP9_18_16, ETH_TXD1),
-	PINMUX_IPSR_DATA(IP9_18_16, MMC1_D6),
-	PINMUX_IPSR_DATA(IP9_18_16, ARM_TRACEDATA_4),
-	PINMUX_IPSR_DATA(IP9_18_16, TS_SPSYNC0),
-	PINMUX_IPSR_DATA(IP9_21_19, VI0_G3),
-	PINMUX_IPSR_DATA(IP9_21_19, ETH_CRS_DV),
-	PINMUX_IPSR_DATA(IP9_21_19, MMC1_D7),
-	PINMUX_IPSR_DATA(IP9_21_19, ARM_TRACEDATA_5),
-	PINMUX_IPSR_DATA(IP9_21_19, TS_SDAT0),
-	PINMUX_IPSR_DATA(IP9_23_22, VI0_G4),
-	PINMUX_IPSR_DATA(IP9_23_22, ETH_TX_EN),
+	PINMUX_IPSR_GPSR(IP9_15_14, ARM_TRACEDATA_3),
+	PINMUX_IPSR_GPSR(IP9_18_16, VI0_G2),
+	PINMUX_IPSR_GPSR(IP9_18_16, ETH_TXD1),
+	PINMUX_IPSR_GPSR(IP9_18_16, MMC1_D6),
+	PINMUX_IPSR_GPSR(IP9_18_16, ARM_TRACEDATA_4),
+	PINMUX_IPSR_GPSR(IP9_18_16, TS_SPSYNC0),
+	PINMUX_IPSR_GPSR(IP9_21_19, VI0_G3),
+	PINMUX_IPSR_GPSR(IP9_21_19, ETH_CRS_DV),
+	PINMUX_IPSR_GPSR(IP9_21_19, MMC1_D7),
+	PINMUX_IPSR_GPSR(IP9_21_19, ARM_TRACEDATA_5),
+	PINMUX_IPSR_GPSR(IP9_21_19, TS_SDAT0),
+	PINMUX_IPSR_GPSR(IP9_23_22, VI0_G4),
+	PINMUX_IPSR_GPSR(IP9_23_22, ETH_TX_EN),
 	PINMUX_IPSR_MSEL(IP9_23_22, SD2_DAT0_B, SEL_SD2_1),
-	PINMUX_IPSR_DATA(IP9_23_22, ARM_TRACEDATA_6),
-	PINMUX_IPSR_DATA(IP9_25_24, VI0_G5),
-	PINMUX_IPSR_DATA(IP9_25_24, ETH_RX_ER),
+	PINMUX_IPSR_GPSR(IP9_23_22, ARM_TRACEDATA_6),
+	PINMUX_IPSR_GPSR(IP9_25_24, VI0_G5),
+	PINMUX_IPSR_GPSR(IP9_25_24, ETH_RX_ER),
 	PINMUX_IPSR_MSEL(IP9_25_24, SD2_DAT1_B, SEL_SD2_1),
-	PINMUX_IPSR_DATA(IP9_25_24, ARM_TRACEDATA_7),
-	PINMUX_IPSR_DATA(IP9_27_26, VI0_G6),
-	PINMUX_IPSR_DATA(IP9_27_26, ETH_RXD0),
+	PINMUX_IPSR_GPSR(IP9_25_24, ARM_TRACEDATA_7),
+	PINMUX_IPSR_GPSR(IP9_27_26, VI0_G6),
+	PINMUX_IPSR_GPSR(IP9_27_26, ETH_RXD0),
 	PINMUX_IPSR_MSEL(IP9_27_26, SD2_DAT2_B, SEL_SD2_1),
-	PINMUX_IPSR_DATA(IP9_27_26, ARM_TRACEDATA_8),
-	PINMUX_IPSR_DATA(IP9_29_28, VI0_G7),
-	PINMUX_IPSR_DATA(IP9_29_28, ETH_RXD1),
+	PINMUX_IPSR_GPSR(IP9_27_26, ARM_TRACEDATA_8),
+	PINMUX_IPSR_GPSR(IP9_29_28, VI0_G7),
+	PINMUX_IPSR_GPSR(IP9_29_28, ETH_RXD1),
 	PINMUX_IPSR_MSEL(IP9_29_28, SD2_DAT3_B, SEL_SD2_1),
-	PINMUX_IPSR_DATA(IP9_29_28, ARM_TRACEDATA_9),
+	PINMUX_IPSR_GPSR(IP9_29_28, ARM_TRACEDATA_9),
 
-	PINMUX_IPSR_DATA(IP10_2_0, VI0_R0),
+	PINMUX_IPSR_GPSR(IP10_2_0, VI0_R0),
 	PINMUX_IPSR_MSEL(IP10_2_0, SSI_SDATA7_C, SEL_SSI7_2),
 	PINMUX_IPSR_MSEL(IP10_2_0, SCK1_C, SEL_SCIF1_2),
 	PINMUX_IPSR_MSEL(IP10_2_0, DREQ1_B, SEL_EXBUS1_0),
-	PINMUX_IPSR_DATA(IP10_2_0, ARM_TRACEDATA_10),
+	PINMUX_IPSR_GPSR(IP10_2_0, ARM_TRACEDATA_10),
 	PINMUX_IPSR_MSEL(IP10_2_0, DREQ0_C, SEL_EXBUS0_2),
-	PINMUX_IPSR_DATA(IP10_5_3, VI0_R1),
+	PINMUX_IPSR_GPSR(IP10_5_3, VI0_R1),
 	PINMUX_IPSR_MSEL(IP10_5_3, SSI_SDATA8_C, SEL_SSI8_2),
-	PINMUX_IPSR_DATA(IP10_5_3, DACK1_B),
-	PINMUX_IPSR_DATA(IP10_5_3, ARM_TRACEDATA_11),
-	PINMUX_IPSR_DATA(IP10_5_3, DACK0_C),
-	PINMUX_IPSR_DATA(IP10_5_3, DRACK0_C),
-	PINMUX_IPSR_DATA(IP10_8_6, VI0_R2),
-	PINMUX_IPSR_DATA(IP10_8_6, ETH_LINK),
-	PINMUX_IPSR_DATA(IP10_8_6, SD2_CLK_B),
+	PINMUX_IPSR_GPSR(IP10_5_3, DACK1_B),
+	PINMUX_IPSR_GPSR(IP10_5_3, ARM_TRACEDATA_11),
+	PINMUX_IPSR_GPSR(IP10_5_3, DACK0_C),
+	PINMUX_IPSR_GPSR(IP10_5_3, DRACK0_C),
+	PINMUX_IPSR_GPSR(IP10_8_6, VI0_R2),
+	PINMUX_IPSR_GPSR(IP10_8_6, ETH_LINK),
+	PINMUX_IPSR_GPSR(IP10_8_6, SD2_CLK_B),
 	PINMUX_IPSR_MSEL(IP10_8_6, IRQ2, SEL_INT2_0),
-	PINMUX_IPSR_DATA(IP10_8_6, ARM_TRACEDATA_12),
-	PINMUX_IPSR_DATA(IP10_11_9, VI0_R3),
-	PINMUX_IPSR_DATA(IP10_11_9, ETH_MAGIC),
+	PINMUX_IPSR_GPSR(IP10_8_6, ARM_TRACEDATA_12),
+	PINMUX_IPSR_GPSR(IP10_11_9, VI0_R3),
+	PINMUX_IPSR_GPSR(IP10_11_9, ETH_MAGIC),
 	PINMUX_IPSR_MSEL(IP10_11_9, SD2_CMD_B, SEL_SD2_1),
 	PINMUX_IPSR_MSEL(IP10_11_9, IRQ3, SEL_INT3_0),
-	PINMUX_IPSR_DATA(IP10_11_9, ARM_TRACEDATA_13),
-	PINMUX_IPSR_DATA(IP10_14_12, VI0_R4),
-	PINMUX_IPSR_DATA(IP10_14_12, ETH_REFCLK),
+	PINMUX_IPSR_GPSR(IP10_11_9, ARM_TRACEDATA_13),
+	PINMUX_IPSR_GPSR(IP10_14_12, VI0_R4),
+	PINMUX_IPSR_GPSR(IP10_14_12, ETH_REFCLK),
 	PINMUX_IPSR_MSEL(IP10_14_12, SD2_CD_B, SEL_SD2_1),
 	PINMUX_IPSR_MSEL(IP10_14_12, HSPI_CLK1_B, SEL_HSPI1_1),
-	PINMUX_IPSR_DATA(IP10_14_12, ARM_TRACEDATA_14),
-	PINMUX_IPSR_DATA(IP10_14_12, MT1_CLK),
-	PINMUX_IPSR_DATA(IP10_14_12, TS_SCK0),
-	PINMUX_IPSR_DATA(IP10_17_15, VI0_R5),
-	PINMUX_IPSR_DATA(IP10_17_15, ETH_TXD0),
+	PINMUX_IPSR_GPSR(IP10_14_12, ARM_TRACEDATA_14),
+	PINMUX_IPSR_GPSR(IP10_14_12, MT1_CLK),
+	PINMUX_IPSR_GPSR(IP10_14_12, TS_SCK0),
+	PINMUX_IPSR_GPSR(IP10_17_15, VI0_R5),
+	PINMUX_IPSR_GPSR(IP10_17_15, ETH_TXD0),
 	PINMUX_IPSR_MSEL(IP10_17_15, SD2_WP_B, SEL_SD2_1),
 	PINMUX_IPSR_MSEL(IP10_17_15, HSPI_CS1_B, SEL_HSPI1_1),
-	PINMUX_IPSR_DATA(IP10_17_15, ARM_TRACEDATA_15),
-	PINMUX_IPSR_DATA(IP10_17_15, MT1_D),
-	PINMUX_IPSR_DATA(IP10_17_15, TS_SDEN0),
-	PINMUX_IPSR_DATA(IP10_20_18, VI0_R6),
-	PINMUX_IPSR_DATA(IP10_20_18, ETH_MDC),
+	PINMUX_IPSR_GPSR(IP10_17_15, ARM_TRACEDATA_15),
+	PINMUX_IPSR_GPSR(IP10_17_15, MT1_D),
+	PINMUX_IPSR_GPSR(IP10_17_15, TS_SDEN0),
+	PINMUX_IPSR_GPSR(IP10_20_18, VI0_R6),
+	PINMUX_IPSR_GPSR(IP10_20_18, ETH_MDC),
 	PINMUX_IPSR_MSEL(IP10_20_18, DREQ2_C, SEL_EXBUS2_2),
-	PINMUX_IPSR_DATA(IP10_20_18, HSPI_TX1_B),
-	PINMUX_IPSR_DATA(IP10_20_18, TRACECLK),
-	PINMUX_IPSR_DATA(IP10_20_18, MT1_BEN),
+	PINMUX_IPSR_GPSR(IP10_20_18, HSPI_TX1_B),
+	PINMUX_IPSR_GPSR(IP10_20_18, TRACECLK),
+	PINMUX_IPSR_GPSR(IP10_20_18, MT1_BEN),
 	PINMUX_IPSR_MSEL(IP10_20_18, PWMFSW0_D, SEL_PWMFSW_3),
-	PINMUX_IPSR_DATA(IP10_23_21, VI0_R7),
-	PINMUX_IPSR_DATA(IP10_23_21, ETH_MDIO),
-	PINMUX_IPSR_DATA(IP10_23_21, DACK2_C),
+	PINMUX_IPSR_GPSR(IP10_23_21, VI0_R7),
+	PINMUX_IPSR_GPSR(IP10_23_21, ETH_MDIO),
+	PINMUX_IPSR_GPSR(IP10_23_21, DACK2_C),
 	PINMUX_IPSR_MSEL(IP10_23_21, HSPI_RX1_B, SEL_HSPI1_1),
 	PINMUX_IPSR_MSEL(IP10_23_21, SCIF_CLK_D, SEL_SCIF_3),
-	PINMUX_IPSR_DATA(IP10_23_21, TRACECTL),
-	PINMUX_IPSR_DATA(IP10_23_21, MT1_PEN),
-	PINMUX_IPSR_DATA(IP10_25_24, VI1_CLK),
+	PINMUX_IPSR_GPSR(IP10_23_21, TRACECTL),
+	PINMUX_IPSR_GPSR(IP10_23_21, MT1_PEN),
+	PINMUX_IPSR_GPSR(IP10_25_24, VI1_CLK),
 	PINMUX_IPSR_MSEL(IP10_25_24, SIM_D, SEL_SIM_0),
 	PINMUX_IPSR_MSEL(IP10_25_24, SDA3, SEL_I2C3_0),
-	PINMUX_IPSR_DATA(IP10_28_26, VI1_HSYNC),
-	PINMUX_IPSR_DATA(IP10_28_26, VI3_CLK),
-	PINMUX_IPSR_DATA(IP10_28_26, SSI_SCK4),
+	PINMUX_IPSR_GPSR(IP10_28_26, VI1_HSYNC),
+	PINMUX_IPSR_GPSR(IP10_28_26, VI3_CLK),
+	PINMUX_IPSR_GPSR(IP10_28_26, SSI_SCK4),
 	PINMUX_IPSR_MSEL(IP10_28_26, GPS_SIGN_C, SEL_GPS_2),
 	PINMUX_IPSR_MSEL(IP10_28_26, PWMFSW0_E, SEL_PWMFSW_4),
-	PINMUX_IPSR_DATA(IP10_31_29, VI1_VSYNC),
-	PINMUX_IPSR_DATA(IP10_31_29, AUDIO_CLKOUT_C),
-	PINMUX_IPSR_DATA(IP10_31_29, SSI_WS4),
-	PINMUX_IPSR_DATA(IP10_31_29, SIM_CLK),
+	PINMUX_IPSR_GPSR(IP10_31_29, VI1_VSYNC),
+	PINMUX_IPSR_GPSR(IP10_31_29, AUDIO_CLKOUT_C),
+	PINMUX_IPSR_GPSR(IP10_31_29, SSI_WS4),
+	PINMUX_IPSR_GPSR(IP10_31_29, SIM_CLK),
 	PINMUX_IPSR_MSEL(IP10_31_29, GPS_MAG_C, SEL_GPS_2),
-	PINMUX_IPSR_DATA(IP10_31_29, SPV_TRST),
+	PINMUX_IPSR_GPSR(IP10_31_29, SPV_TRST),
 	PINMUX_IPSR_MSEL(IP10_31_29, SCL3, SEL_I2C3_0),
 
-	PINMUX_IPSR_DATA(IP11_2_0, VI1_DATA0_VI1_B0),
+	PINMUX_IPSR_GPSR(IP11_2_0, VI1_DATA0_VI1_B0),
 	PINMUX_IPSR_MSEL(IP11_2_0, SD2_DAT0, SEL_SD2_0),
-	PINMUX_IPSR_DATA(IP11_2_0, SIM_RST),
-	PINMUX_IPSR_DATA(IP11_2_0, SPV_TCK),
-	PINMUX_IPSR_DATA(IP11_2_0, ADICLK_B),
-	PINMUX_IPSR_DATA(IP11_5_3, VI1_DATA1_VI1_B1),
+	PINMUX_IPSR_GPSR(IP11_2_0, SIM_RST),
+	PINMUX_IPSR_GPSR(IP11_2_0, SPV_TCK),
+	PINMUX_IPSR_GPSR(IP11_2_0, ADICLK_B),
+	PINMUX_IPSR_GPSR(IP11_5_3, VI1_DATA1_VI1_B1),
 	PINMUX_IPSR_MSEL(IP11_5_3, SD2_DAT1, SEL_SD2_0),
-	PINMUX_IPSR_DATA(IP11_5_3, MT0_CLK),
-	PINMUX_IPSR_DATA(IP11_5_3, SPV_TMS),
+	PINMUX_IPSR_GPSR(IP11_5_3, MT0_CLK),
+	PINMUX_IPSR_GPSR(IP11_5_3, SPV_TMS),
 	PINMUX_IPSR_MSEL(IP11_5_3, ADICS_B_SAMP_B, SEL_ADI_1),
-	PINMUX_IPSR_DATA(IP11_8_6, VI1_DATA2_VI1_B2),
+	PINMUX_IPSR_GPSR(IP11_8_6, VI1_DATA2_VI1_B2),
 	PINMUX_IPSR_MSEL(IP11_8_6, SD2_DAT2, SEL_SD2_0),
-	PINMUX_IPSR_DATA(IP11_8_6, MT0_D),
-	PINMUX_IPSR_DATA(IP11_8_6, SPVTDI),
+	PINMUX_IPSR_GPSR(IP11_8_6, MT0_D),
+	PINMUX_IPSR_GPSR(IP11_8_6, SPVTDI),
 	PINMUX_IPSR_MSEL(IP11_8_6, ADIDATA_B, SEL_ADI_1),
-	PINMUX_IPSR_DATA(IP11_11_9, VI1_DATA3_VI1_B3),
+	PINMUX_IPSR_GPSR(IP11_11_9, VI1_DATA3_VI1_B3),
 	PINMUX_IPSR_MSEL(IP11_11_9, SD2_DAT3, SEL_SD2_0),
-	PINMUX_IPSR_DATA(IP11_11_9, MT0_BEN),
-	PINMUX_IPSR_DATA(IP11_11_9, SPV_TDO),
-	PINMUX_IPSR_DATA(IP11_11_9, ADICHS0_B),
-	PINMUX_IPSR_DATA(IP11_14_12, VI1_DATA4_VI1_B4),
-	PINMUX_IPSR_DATA(IP11_14_12, SD2_CLK),
-	PINMUX_IPSR_DATA(IP11_14_12, MT0_PEN),
-	PINMUX_IPSR_DATA(IP11_14_12, SPA_TRST),
+	PINMUX_IPSR_GPSR(IP11_11_9, MT0_BEN),
+	PINMUX_IPSR_GPSR(IP11_11_9, SPV_TDO),
+	PINMUX_IPSR_GPSR(IP11_11_9, ADICHS0_B),
+	PINMUX_IPSR_GPSR(IP11_14_12, VI1_DATA4_VI1_B4),
+	PINMUX_IPSR_GPSR(IP11_14_12, SD2_CLK),
+	PINMUX_IPSR_GPSR(IP11_14_12, MT0_PEN),
+	PINMUX_IPSR_GPSR(IP11_14_12, SPA_TRST),
 	PINMUX_IPSR_MSEL(IP11_14_12, HSPI_CLK1_D, SEL_HSPI1_3),
-	PINMUX_IPSR_DATA(IP11_14_12, ADICHS1_B),
-	PINMUX_IPSR_DATA(IP11_17_15, VI1_DATA5_VI1_B5),
+	PINMUX_IPSR_GPSR(IP11_14_12, ADICHS1_B),
+	PINMUX_IPSR_GPSR(IP11_17_15, VI1_DATA5_VI1_B5),
 	PINMUX_IPSR_MSEL(IP11_17_15, SD2_CMD, SEL_SD2_0),
-	PINMUX_IPSR_DATA(IP11_17_15, MT0_SYNC),
-	PINMUX_IPSR_DATA(IP11_17_15, SPA_TCK),
+	PINMUX_IPSR_GPSR(IP11_17_15, MT0_SYNC),
+	PINMUX_IPSR_GPSR(IP11_17_15, SPA_TCK),
 	PINMUX_IPSR_MSEL(IP11_17_15, HSPI_CS1_D, SEL_HSPI1_3),
-	PINMUX_IPSR_DATA(IP11_17_15, ADICHS2_B),
-	PINMUX_IPSR_DATA(IP11_20_18, VI1_DATA6_VI1_B6),
+	PINMUX_IPSR_GPSR(IP11_17_15, ADICHS2_B),
+	PINMUX_IPSR_GPSR(IP11_20_18, VI1_DATA6_VI1_B6),
 	PINMUX_IPSR_MSEL(IP11_20_18, SD2_CD, SEL_SD2_0),
-	PINMUX_IPSR_DATA(IP11_20_18, MT0_VCXO),
-	PINMUX_IPSR_DATA(IP11_20_18, SPA_TMS),
-	PINMUX_IPSR_DATA(IP11_20_18, HSPI_TX1_D),
-	PINMUX_IPSR_DATA(IP11_23_21, VI1_DATA7_VI1_B7),
+	PINMUX_IPSR_GPSR(IP11_20_18, MT0_VCXO),
+	PINMUX_IPSR_GPSR(IP11_20_18, SPA_TMS),
+	PINMUX_IPSR_GPSR(IP11_20_18, HSPI_TX1_D),
+	PINMUX_IPSR_GPSR(IP11_23_21, VI1_DATA7_VI1_B7),
 	PINMUX_IPSR_MSEL(IP11_23_21, SD2_WP, SEL_SD2_0),
-	PINMUX_IPSR_DATA(IP11_23_21, MT0_PWM),
-	PINMUX_IPSR_DATA(IP11_23_21, SPA_TDI),
+	PINMUX_IPSR_GPSR(IP11_23_21, MT0_PWM),
+	PINMUX_IPSR_GPSR(IP11_23_21, SPA_TDI),
 	PINMUX_IPSR_MSEL(IP11_23_21, HSPI_RX1_D, SEL_HSPI1_3),
-	PINMUX_IPSR_DATA(IP11_26_24, VI1_G0),
-	PINMUX_IPSR_DATA(IP11_26_24, VI3_DATA0),
-	PINMUX_IPSR_DATA(IP11_26_24, TS_SCK1),
+	PINMUX_IPSR_GPSR(IP11_26_24, VI1_G0),
+	PINMUX_IPSR_GPSR(IP11_26_24, VI3_DATA0),
+	PINMUX_IPSR_GPSR(IP11_26_24, TS_SCK1),
 	PINMUX_IPSR_MSEL(IP11_26_24, DREQ2_B, SEL_EXBUS2_1),
-	PINMUX_IPSR_DATA(IP11_26_24, TX2),
-	PINMUX_IPSR_DATA(IP11_26_24, SPA_TDO),
+	PINMUX_IPSR_GPSR(IP11_26_24, TX2),
+	PINMUX_IPSR_GPSR(IP11_26_24, SPA_TDO),
 	PINMUX_IPSR_MSEL(IP11_26_24, HCTS0_B, SEL_HSCIF0_1),
-	PINMUX_IPSR_DATA(IP11_29_27, VI1_G1),
-	PINMUX_IPSR_DATA(IP11_29_27, VI3_DATA1),
-	PINMUX_IPSR_DATA(IP11_29_27, SSI_SCK1),
-	PINMUX_IPSR_DATA(IP11_29_27, TS_SDEN1),
-	PINMUX_IPSR_DATA(IP11_29_27, DACK2_B),
+	PINMUX_IPSR_GPSR(IP11_29_27, VI1_G1),
+	PINMUX_IPSR_GPSR(IP11_29_27, VI3_DATA1),
+	PINMUX_IPSR_GPSR(IP11_29_27, SSI_SCK1),
+	PINMUX_IPSR_GPSR(IP11_29_27, TS_SDEN1),
+	PINMUX_IPSR_GPSR(IP11_29_27, DACK2_B),
 	PINMUX_IPSR_MSEL(IP11_29_27, RX2, SEL_SCIF2_0),
 	PINMUX_IPSR_MSEL(IP11_29_27, HRTS0_B, SEL_HSCIF0_1),
 
-	PINMUX_IPSR_DATA(IP12_2_0, VI1_G2),
-	PINMUX_IPSR_DATA(IP12_2_0, VI3_DATA2),
-	PINMUX_IPSR_DATA(IP12_2_0, SSI_WS1),
-	PINMUX_IPSR_DATA(IP12_2_0, TS_SPSYNC1),
+	PINMUX_IPSR_GPSR(IP12_2_0, VI1_G2),
+	PINMUX_IPSR_GPSR(IP12_2_0, VI3_DATA2),
+	PINMUX_IPSR_GPSR(IP12_2_0, SSI_WS1),
+	PINMUX_IPSR_GPSR(IP12_2_0, TS_SPSYNC1),
 	PINMUX_IPSR_MSEL(IP12_2_0, SCK2, SEL_SCIF2_0),
 	PINMUX_IPSR_MSEL(IP12_2_0, HSCK0_B, SEL_HSCIF0_1),
-	PINMUX_IPSR_DATA(IP12_5_3, VI1_G3),
-	PINMUX_IPSR_DATA(IP12_5_3, VI3_DATA3),
-	PINMUX_IPSR_DATA(IP12_5_3, SSI_SCK2),
-	PINMUX_IPSR_DATA(IP12_5_3, TS_SDAT1),
+	PINMUX_IPSR_GPSR(IP12_5_3, VI1_G3),
+	PINMUX_IPSR_GPSR(IP12_5_3, VI3_DATA3),
+	PINMUX_IPSR_GPSR(IP12_5_3, SSI_SCK2),
+	PINMUX_IPSR_GPSR(IP12_5_3, TS_SDAT1),
 	PINMUX_IPSR_MSEL(IP12_5_3, SCL1_C, SEL_I2C1_2),
-	PINMUX_IPSR_DATA(IP12_5_3, HTX0_B),
-	PINMUX_IPSR_DATA(IP12_8_6, VI1_G4),
-	PINMUX_IPSR_DATA(IP12_8_6, VI3_DATA4),
-	PINMUX_IPSR_DATA(IP12_8_6, SSI_WS2),
+	PINMUX_IPSR_GPSR(IP12_5_3, HTX0_B),
+	PINMUX_IPSR_GPSR(IP12_8_6, VI1_G4),
+	PINMUX_IPSR_GPSR(IP12_8_6, VI3_DATA4),
+	PINMUX_IPSR_GPSR(IP12_8_6, SSI_WS2),
 	PINMUX_IPSR_MSEL(IP12_8_6, SDA1_C, SEL_I2C1_2),
-	PINMUX_IPSR_DATA(IP12_8_6, SIM_RST_B),
+	PINMUX_IPSR_GPSR(IP12_8_6, SIM_RST_B),
 	PINMUX_IPSR_MSEL(IP12_8_6, HRX0_B, SEL_HSCIF0_1),
-	PINMUX_IPSR_DATA(IP12_11_9, VI1_G5),
-	PINMUX_IPSR_DATA(IP12_11_9, VI3_DATA5),
+	PINMUX_IPSR_GPSR(IP12_11_9, VI1_G5),
+	PINMUX_IPSR_GPSR(IP12_11_9, VI3_DATA5),
 	PINMUX_IPSR_MSEL(IP12_11_9, GPS_CLK, SEL_GPS_0),
-	PINMUX_IPSR_DATA(IP12_11_9, FSE),
-	PINMUX_IPSR_DATA(IP12_11_9, TX4_B),
+	PINMUX_IPSR_GPSR(IP12_11_9, FSE),
+	PINMUX_IPSR_GPSR(IP12_11_9, TX4_B),
 	PINMUX_IPSR_MSEL(IP12_11_9, SIM_D_B, SEL_SIM_1),
-	PINMUX_IPSR_DATA(IP12_14_12, VI1_G6),
-	PINMUX_IPSR_DATA(IP12_14_12, VI3_DATA6),
+	PINMUX_IPSR_GPSR(IP12_14_12, VI1_G6),
+	PINMUX_IPSR_GPSR(IP12_14_12, VI3_DATA6),
 	PINMUX_IPSR_MSEL(IP12_14_12, GPS_SIGN, SEL_GPS_0),
-	PINMUX_IPSR_DATA(IP12_14_12, FRB),
+	PINMUX_IPSR_GPSR(IP12_14_12, FRB),
 	PINMUX_IPSR_MSEL(IP12_14_12, RX4_B, SEL_SCIF4_1),
-	PINMUX_IPSR_DATA(IP12_14_12, SIM_CLK_B),
-	PINMUX_IPSR_DATA(IP12_17_15, VI1_G7),
-	PINMUX_IPSR_DATA(IP12_17_15, VI3_DATA7),
+	PINMUX_IPSR_GPSR(IP12_14_12, SIM_CLK_B),
+	PINMUX_IPSR_GPSR(IP12_17_15, VI1_G7),
+	PINMUX_IPSR_GPSR(IP12_17_15, VI3_DATA7),
 	PINMUX_IPSR_MSEL(IP12_17_15, GPS_MAG, SEL_GPS_0),
-	PINMUX_IPSR_DATA(IP12_17_15, FCE),
+	PINMUX_IPSR_GPSR(IP12_17_15, FCE),
 	PINMUX_IPSR_MSEL(IP12_17_15, SCK4_B, SEL_SCIF4_1),
 };
 
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7790.c b/drivers/pinctrl/sh-pfc/pfc-r8a7790.c
index a8b629bc7a55..0f4d48f9400b 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7790.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7790.c
@@ -799,47 +799,47 @@ static const u16 pinmux_data[] = {
 	PINMUX_SINGLE(DU_DOTCLKIN0),
 	PINMUX_SINGLE(DU_DOTCLKIN2),
 
-	PINMUX_IPSR_DATA(IP0_2_0, D0),
+	PINMUX_IPSR_GPSR(IP0_2_0, D0),
 	PINMUX_IPSR_MSEL(IP0_2_0, MSIOF3_SCK_B, SEL_SOF3_1),
 	PINMUX_IPSR_MSEL(IP0_2_0, VI3_DATA0, SEL_VI3_0),
 	PINMUX_IPSR_MSEL(IP0_2_0, VI0_G4, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP0_2_0, VI0_G4_B, SEL_VI0_1),
-	PINMUX_IPSR_DATA(IP0_5_3, D1),
+	PINMUX_IPSR_GPSR(IP0_5_3, D1),
 	PINMUX_IPSR_MSEL(IP0_5_3, MSIOF3_SYNC_B, SEL_SOF3_1),
 	PINMUX_IPSR_MSEL(IP0_5_3, VI3_DATA1, SEL_VI3_0),
 	PINMUX_IPSR_MSEL(IP0_5_3, VI0_G5, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP0_5_3, VI0_G5_B, SEL_VI0_1),
-	PINMUX_IPSR_DATA(IP0_8_6, D2),
+	PINMUX_IPSR_GPSR(IP0_8_6, D2),
 	PINMUX_IPSR_MSEL(IP0_8_6, MSIOF3_RXD_B, SEL_SOF3_1),
 	PINMUX_IPSR_MSEL(IP0_8_6, VI3_DATA2, SEL_VI3_0),
 	PINMUX_IPSR_MSEL(IP0_8_6, VI0_G6, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP0_8_6, VI0_G6_B, SEL_VI0_1),
-	PINMUX_IPSR_DATA(IP0_11_9, D3),
+	PINMUX_IPSR_GPSR(IP0_11_9, D3),
 	PINMUX_IPSR_MSEL(IP0_11_9, MSIOF3_TXD_B, SEL_SOF3_1),
 	PINMUX_IPSR_MSEL(IP0_11_9, VI3_DATA3, SEL_VI3_0),
 	PINMUX_IPSR_MSEL(IP0_11_9, VI0_G7, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP0_11_9, VI0_G7_B, SEL_VI0_1),
-	PINMUX_IPSR_DATA(IP0_15_12, D4),
+	PINMUX_IPSR_GPSR(IP0_15_12, D4),
 	PINMUX_IPSR_MSEL(IP0_15_12, SCIFB1_RXD_F, SEL_SCIFB1_5),
 	PINMUX_IPSR_MSEL(IP0_15_12, SCIFB0_RXD_C, SEL_SCIFB_2),
 	PINMUX_IPSR_MSEL(IP0_15_12, VI3_DATA4, SEL_VI3_0),
 	PINMUX_IPSR_MSEL(IP0_15_12, VI0_R0, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP0_15_12, VI0_R0_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP0_15_12, RX0_B, SEL_SCIF0_1),
-	PINMUX_IPSR_DATA(IP0_19_16, D5),
+	PINMUX_IPSR_GPSR(IP0_19_16, D5),
 	PINMUX_IPSR_MSEL(IP0_19_16, SCIFB1_TXD_F, SEL_SCIFB1_5),
 	PINMUX_IPSR_MSEL(IP0_19_16, SCIFB0_TXD_C, SEL_SCIFB_2),
 	PINMUX_IPSR_MSEL(IP0_19_16, VI3_DATA5, SEL_VI3_0),
 	PINMUX_IPSR_MSEL(IP0_19_16, VI0_R1, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP0_19_16, VI0_R1_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP0_19_16, TX0_B, SEL_SCIF0_1),
-	PINMUX_IPSR_DATA(IP0_22_20, D6),
+	PINMUX_IPSR_GPSR(IP0_22_20, D6),
 	PINMUX_IPSR_MSEL(IP0_22_20, IIC2_SCL_C, SEL_IIC2_2),
 	PINMUX_IPSR_MSEL(IP0_22_20, VI3_DATA6, SEL_VI3_0),
 	PINMUX_IPSR_MSEL(IP0_22_20, VI0_R2, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP0_22_20, VI0_R2_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP0_22_20, I2C2_SCL_C, SEL_I2C2_2),
-	PINMUX_IPSR_DATA(IP0_26_23, D7),
+	PINMUX_IPSR_GPSR(IP0_26_23, D7),
 	PINMUX_IPSR_MSEL(IP0_26_23, AD_DI_B, SEL_ADI_1),
 	PINMUX_IPSR_MSEL(IP0_26_23, IIC2_SDA_C, SEL_IIC2_2),
 	PINMUX_IPSR_MSEL(IP0_26_23, VI3_DATA7, SEL_VI3_0),
@@ -847,81 +847,81 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP0_26_23, VI0_R3_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP0_26_23, I2C2_SDA_C, SEL_I2C2_2),
 	PINMUX_IPSR_MSEL(IP0_26_23, TCLK1, SEL_TMU1_0),
-	PINMUX_IPSR_DATA(IP0_30_27, D8),
+	PINMUX_IPSR_GPSR(IP0_30_27, D8),
 	PINMUX_IPSR_MSEL(IP0_30_27, SCIFA1_SCK_C, SEL_SCIFA1_2),
-	PINMUX_IPSR_DATA(IP0_30_27, AVB_TXD0),
+	PINMUX_IPSR_GPSR(IP0_30_27, AVB_TXD0),
 	PINMUX_IPSR_MSEL(IP0_30_27, VI0_G0, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP0_30_27, VI0_G0_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP0_30_27, VI2_DATA0_VI2_B0, SEL_VI2_0),
 
-	PINMUX_IPSR_DATA(IP1_3_0, D9),
+	PINMUX_IPSR_GPSR(IP1_3_0, D9),
 	PINMUX_IPSR_MSEL(IP1_3_0, SCIFA1_RXD_C, SEL_SCIFA1_2),
-	PINMUX_IPSR_DATA(IP1_3_0, AVB_TXD1),
+	PINMUX_IPSR_GPSR(IP1_3_0, AVB_TXD1),
 	PINMUX_IPSR_MSEL(IP1_3_0, VI0_G1, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP1_3_0, VI0_G1_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP1_3_0, VI2_DATA1_VI2_B1, SEL_VI2_0),
-	PINMUX_IPSR_DATA(IP1_7_4, D10),
+	PINMUX_IPSR_GPSR(IP1_7_4, D10),
 	PINMUX_IPSR_MSEL(IP1_7_4, SCIFA1_TXD_C, SEL_SCIFA1_2),
-	PINMUX_IPSR_DATA(IP1_7_4, AVB_TXD2),
+	PINMUX_IPSR_GPSR(IP1_7_4, AVB_TXD2),
 	PINMUX_IPSR_MSEL(IP1_7_4, VI0_G2, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP1_7_4, VI0_G2_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP1_7_4, VI2_DATA2_VI2_B2, SEL_VI2_0),
-	PINMUX_IPSR_DATA(IP1_11_8, D11),
+	PINMUX_IPSR_GPSR(IP1_11_8, D11),
 	PINMUX_IPSR_MSEL(IP1_11_8, SCIFA1_CTS_N_C, SEL_SCIFA1_2),
-	PINMUX_IPSR_DATA(IP1_11_8, AVB_TXD3),
+	PINMUX_IPSR_GPSR(IP1_11_8, AVB_TXD3),
 	PINMUX_IPSR_MSEL(IP1_11_8, VI0_G3, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP1_11_8, VI0_G3_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP1_11_8, VI2_DATA3_VI2_B3, SEL_VI2_0),
-	PINMUX_IPSR_DATA(IP1_14_12, D12),
+	PINMUX_IPSR_GPSR(IP1_14_12, D12),
 	PINMUX_IPSR_MSEL(IP1_14_12, SCIFA1_RTS_N_C, SEL_SCIFA1_2),
-	PINMUX_IPSR_DATA(IP1_14_12, AVB_TXD4),
+	PINMUX_IPSR_GPSR(IP1_14_12, AVB_TXD4),
 	PINMUX_IPSR_MSEL(IP1_14_12, VI0_HSYNC_N, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP1_14_12, VI0_HSYNC_N_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP1_14_12, VI2_DATA4_VI2_B4, SEL_VI2_0),
-	PINMUX_IPSR_DATA(IP1_17_15, D13),
-	PINMUX_IPSR_DATA(IP1_17_15, AVB_TXD5),
+	PINMUX_IPSR_GPSR(IP1_17_15, D13),
+	PINMUX_IPSR_GPSR(IP1_17_15, AVB_TXD5),
 	PINMUX_IPSR_MSEL(IP1_17_15, VI0_VSYNC_N, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP1_17_15, VI0_VSYNC_N_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP1_17_15, VI2_DATA5_VI2_B5, SEL_VI2_0),
-	PINMUX_IPSR_DATA(IP1_21_18, D14),
+	PINMUX_IPSR_GPSR(IP1_21_18, D14),
 	PINMUX_IPSR_MSEL(IP1_21_18, SCIFB1_RXD_C, SEL_SCIFB1_2),
-	PINMUX_IPSR_DATA(IP1_21_18, AVB_TXD6),
+	PINMUX_IPSR_GPSR(IP1_21_18, AVB_TXD6),
 	PINMUX_IPSR_MSEL(IP1_21_18, RX1_B, SEL_SCIF1_1),
 	PINMUX_IPSR_MSEL(IP1_21_18, VI0_CLKENB, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP1_21_18, VI0_CLKENB_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP1_21_18, VI2_DATA6_VI2_B6, SEL_VI2_0),
-	PINMUX_IPSR_DATA(IP1_25_22, D15),
+	PINMUX_IPSR_GPSR(IP1_25_22, D15),
 	PINMUX_IPSR_MSEL(IP1_25_22, SCIFB1_TXD_C, SEL_SCIFB1_2),
-	PINMUX_IPSR_DATA(IP1_25_22, AVB_TXD7),
+	PINMUX_IPSR_GPSR(IP1_25_22, AVB_TXD7),
 	PINMUX_IPSR_MSEL(IP1_25_22, TX1_B, SEL_SCIF1_1),
 	PINMUX_IPSR_MSEL(IP1_25_22, VI0_FIELD, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP1_25_22, VI0_FIELD_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP1_25_22, VI2_DATA7_VI2_B7, SEL_VI2_0),
-	PINMUX_IPSR_DATA(IP1_27_26, A0),
-	PINMUX_IPSR_DATA(IP1_27_26, PWM3),
-	PINMUX_IPSR_DATA(IP1_29_28, A1),
-	PINMUX_IPSR_DATA(IP1_29_28, PWM4),
+	PINMUX_IPSR_GPSR(IP1_27_26, A0),
+	PINMUX_IPSR_GPSR(IP1_27_26, PWM3),
+	PINMUX_IPSR_GPSR(IP1_29_28, A1),
+	PINMUX_IPSR_GPSR(IP1_29_28, PWM4),
 
-	PINMUX_IPSR_DATA(IP2_2_0, A2),
-	PINMUX_IPSR_DATA(IP2_2_0, PWM5),
+	PINMUX_IPSR_GPSR(IP2_2_0, A2),
+	PINMUX_IPSR_GPSR(IP2_2_0, PWM5),
 	PINMUX_IPSR_MSEL(IP2_2_0, MSIOF1_SS1_B, SEL_SOF1_1),
-	PINMUX_IPSR_DATA(IP2_5_3, A3),
-	PINMUX_IPSR_DATA(IP2_5_3, PWM6),
+	PINMUX_IPSR_GPSR(IP2_5_3, A3),
+	PINMUX_IPSR_GPSR(IP2_5_3, PWM6),
 	PINMUX_IPSR_MSEL(IP2_5_3, MSIOF1_SS2_B, SEL_SOF1_1),
-	PINMUX_IPSR_DATA(IP2_8_6, A4),
+	PINMUX_IPSR_GPSR(IP2_8_6, A4),
 	PINMUX_IPSR_MSEL(IP2_8_6, MSIOF1_TXD_B, SEL_SOF1_1),
-	PINMUX_IPSR_DATA(IP2_8_6, TPU0TO0),
-	PINMUX_IPSR_DATA(IP2_11_9, A5),
+	PINMUX_IPSR_GPSR(IP2_8_6, TPU0TO0),
+	PINMUX_IPSR_GPSR(IP2_11_9, A5),
 	PINMUX_IPSR_MSEL(IP2_11_9, SCIFA1_TXD_B, SEL_SCIFA1_1),
-	PINMUX_IPSR_DATA(IP2_11_9, TPU0TO1),
-	PINMUX_IPSR_DATA(IP2_14_12, A6),
+	PINMUX_IPSR_GPSR(IP2_11_9, TPU0TO1),
+	PINMUX_IPSR_GPSR(IP2_14_12, A6),
 	PINMUX_IPSR_MSEL(IP2_14_12, SCIFA1_RTS_N_B, SEL_SCIFA1_1),
-	PINMUX_IPSR_DATA(IP2_14_12, TPU0TO2),
-	PINMUX_IPSR_DATA(IP2_17_15, A7),
+	PINMUX_IPSR_GPSR(IP2_14_12, TPU0TO2),
+	PINMUX_IPSR_GPSR(IP2_17_15, A7),
 	PINMUX_IPSR_MSEL(IP2_17_15, SCIFA1_SCK_B, SEL_SCIFA1_1),
-	PINMUX_IPSR_DATA(IP2_17_15, AUDIO_CLKOUT_B),
-	PINMUX_IPSR_DATA(IP2_17_15, TPU0TO3),
-	PINMUX_IPSR_DATA(IP2_21_18, A8),
+	PINMUX_IPSR_GPSR(IP2_17_15, AUDIO_CLKOUT_B),
+	PINMUX_IPSR_GPSR(IP2_17_15, TPU0TO3),
+	PINMUX_IPSR_GPSR(IP2_21_18, A8),
 	PINMUX_IPSR_MSEL(IP2_21_18, SCIFA1_RXD_B, SEL_SCIFA1_1),
 	PINMUX_IPSR_MSEL(IP2_21_18, SSI_SCK5_B, SEL_SSI5_1),
 	PINMUX_IPSR_MSEL(IP2_21_18, VI0_R4, SEL_VI0_0),
@@ -929,7 +929,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP2_21_18, SCIFB2_RXD_C, SEL_SCIFB2_2),
 	PINMUX_IPSR_MSEL(IP2_21_18, RX2_B, SEL_SCIF2_1),
 	PINMUX_IPSR_MSEL(IP2_21_18, VI2_DATA0_VI2_B0_B, SEL_VI2_1),
-	PINMUX_IPSR_DATA(IP2_25_22, A9),
+	PINMUX_IPSR_GPSR(IP2_25_22, A9),
 	PINMUX_IPSR_MSEL(IP2_25_22, SCIFA1_CTS_N_B, SEL_SCIFA1_1),
 	PINMUX_IPSR_MSEL(IP2_25_22, SSI_WS5_B, SEL_SSI5_1),
 	PINMUX_IPSR_MSEL(IP2_25_22, VI0_R5, SEL_VI0_0),
@@ -937,392 +937,392 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP2_25_22, SCIFB2_TXD_C, SEL_SCIFB2_2),
 	PINMUX_IPSR_MSEL(IP2_25_22, TX2_B, SEL_SCIF2_1),
 	PINMUX_IPSR_MSEL(IP2_25_22, VI2_DATA1_VI2_B1_B, SEL_VI2_1),
-	PINMUX_IPSR_DATA(IP2_28_26, A10),
+	PINMUX_IPSR_GPSR(IP2_28_26, A10),
 	PINMUX_IPSR_MSEL(IP2_28_26, SSI_SDATA5_B, SEL_SSI5_1),
-	PINMUX_IPSR_DATA(IP2_28_26, MSIOF2_SYNC),
+	PINMUX_IPSR_GPSR(IP2_28_26, MSIOF2_SYNC),
 	PINMUX_IPSR_MSEL(IP2_28_26, VI0_R6, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP2_28_26, VI0_R6_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP2_28_26, VI2_DATA2_VI2_B2_B, SEL_VI2_1),
 
-	PINMUX_IPSR_DATA(IP3_3_0, A11),
+	PINMUX_IPSR_GPSR(IP3_3_0, A11),
 	PINMUX_IPSR_MSEL(IP3_3_0, SCIFB2_CTS_N_B, SEL_SCIFB2_1),
-	PINMUX_IPSR_DATA(IP3_3_0, MSIOF2_SCK),
+	PINMUX_IPSR_GPSR(IP3_3_0, MSIOF2_SCK),
 	PINMUX_IPSR_MSEL(IP3_3_0, VI1_R0, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP3_3_0, VI1_R0_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP3_3_0, VI2_G0),
+	PINMUX_IPSR_GPSR(IP3_3_0, VI2_G0),
 	PINMUX_IPSR_MSEL(IP3_3_0, VI2_DATA3_VI2_B3_B, SEL_VI2_1),
-	PINMUX_IPSR_DATA(IP3_7_4, A12),
+	PINMUX_IPSR_GPSR(IP3_7_4, A12),
 	PINMUX_IPSR_MSEL(IP3_7_4, SCIFB2_RXD_B, SEL_SCIFB2_1),
-	PINMUX_IPSR_DATA(IP3_7_4, MSIOF2_TXD),
+	PINMUX_IPSR_GPSR(IP3_7_4, MSIOF2_TXD),
 	PINMUX_IPSR_MSEL(IP3_7_4, VI1_R1, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP3_7_4, VI1_R1_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP3_7_4, VI2_G1),
+	PINMUX_IPSR_GPSR(IP3_7_4, VI2_G1),
 	PINMUX_IPSR_MSEL(IP3_7_4, VI2_DATA4_VI2_B4_B, SEL_VI2_1),
-	PINMUX_IPSR_DATA(IP3_11_8, A13),
+	PINMUX_IPSR_GPSR(IP3_11_8, A13),
 	PINMUX_IPSR_MSEL(IP3_11_8, SCIFB2_RTS_N_B, SEL_SCIFB2_1),
-	PINMUX_IPSR_DATA(IP3_11_8, EX_WAIT2),
-	PINMUX_IPSR_DATA(IP3_11_8, MSIOF2_RXD),
+	PINMUX_IPSR_GPSR(IP3_11_8, EX_WAIT2),
+	PINMUX_IPSR_GPSR(IP3_11_8, MSIOF2_RXD),
 	PINMUX_IPSR_MSEL(IP3_11_8, VI1_R2, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP3_11_8, VI1_R2_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP3_11_8, VI2_G2),
+	PINMUX_IPSR_GPSR(IP3_11_8, VI2_G2),
 	PINMUX_IPSR_MSEL(IP3_11_8, VI2_DATA5_VI2_B5_B, SEL_VI2_1),
-	PINMUX_IPSR_DATA(IP3_14_12, A14),
+	PINMUX_IPSR_GPSR(IP3_14_12, A14),
 	PINMUX_IPSR_MSEL(IP3_14_12, SCIFB2_TXD_B, SEL_SCIFB2_1),
-	PINMUX_IPSR_DATA(IP3_14_12, ATACS11_N),
-	PINMUX_IPSR_DATA(IP3_14_12, MSIOF2_SS1),
-	PINMUX_IPSR_DATA(IP3_17_15, A15),
+	PINMUX_IPSR_GPSR(IP3_14_12, ATACS11_N),
+	PINMUX_IPSR_GPSR(IP3_14_12, MSIOF2_SS1),
+	PINMUX_IPSR_GPSR(IP3_17_15, A15),
 	PINMUX_IPSR_MSEL(IP3_17_15, SCIFB2_SCK_B, SEL_SCIFB2_1),
-	PINMUX_IPSR_DATA(IP3_17_15, ATARD1_N),
-	PINMUX_IPSR_DATA(IP3_17_15, MSIOF2_SS2),
-	PINMUX_IPSR_DATA(IP3_19_18, A16),
-	PINMUX_IPSR_DATA(IP3_19_18, ATAWR1_N),
-	PINMUX_IPSR_DATA(IP3_22_20, A17),
+	PINMUX_IPSR_GPSR(IP3_17_15, ATARD1_N),
+	PINMUX_IPSR_GPSR(IP3_17_15, MSIOF2_SS2),
+	PINMUX_IPSR_GPSR(IP3_19_18, A16),
+	PINMUX_IPSR_GPSR(IP3_19_18, ATAWR1_N),
+	PINMUX_IPSR_GPSR(IP3_22_20, A17),
 	PINMUX_IPSR_MSEL(IP3_22_20, AD_DO_B, SEL_ADI_1),
-	PINMUX_IPSR_DATA(IP3_22_20, ATADIR1_N),
-	PINMUX_IPSR_DATA(IP3_25_23, A18),
+	PINMUX_IPSR_GPSR(IP3_22_20, ATADIR1_N),
+	PINMUX_IPSR_GPSR(IP3_25_23, A18),
 	PINMUX_IPSR_MSEL(IP3_25_23, AD_CLK_B, SEL_ADI_1),
-	PINMUX_IPSR_DATA(IP3_25_23, ATAG1_N),
-	PINMUX_IPSR_DATA(IP3_28_26, A19),
+	PINMUX_IPSR_GPSR(IP3_25_23, ATAG1_N),
+	PINMUX_IPSR_GPSR(IP3_28_26, A19),
 	PINMUX_IPSR_MSEL(IP3_28_26, AD_NCS_N_B, SEL_ADI_1),
-	PINMUX_IPSR_DATA(IP3_28_26, ATACS01_N),
+	PINMUX_IPSR_GPSR(IP3_28_26, ATACS01_N),
 	PINMUX_IPSR_MSEL(IP3_28_26, EX_WAIT0_B, SEL_LBS_1),
-	PINMUX_IPSR_DATA(IP3_31_29, A20),
-	PINMUX_IPSR_DATA(IP3_31_29, SPCLK),
+	PINMUX_IPSR_GPSR(IP3_31_29, A20),
+	PINMUX_IPSR_GPSR(IP3_31_29, SPCLK),
 	PINMUX_IPSR_MSEL(IP3_31_29, VI1_R3, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP3_31_29, VI1_R3_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP3_31_29, VI2_G4),
+	PINMUX_IPSR_GPSR(IP3_31_29, VI2_G4),
 
-	PINMUX_IPSR_DATA(IP4_2_0, A21),
-	PINMUX_IPSR_DATA(IP4_2_0, MOSI_IO0),
+	PINMUX_IPSR_GPSR(IP4_2_0, A21),
+	PINMUX_IPSR_GPSR(IP4_2_0, MOSI_IO0),
 	PINMUX_IPSR_MSEL(IP4_2_0, VI1_R4, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP4_2_0, VI1_R4_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP4_2_0, VI2_G5),
-	PINMUX_IPSR_DATA(IP4_5_3, A22),
-	PINMUX_IPSR_DATA(IP4_5_3, MISO_IO1),
+	PINMUX_IPSR_GPSR(IP4_2_0, VI2_G5),
+	PINMUX_IPSR_GPSR(IP4_5_3, A22),
+	PINMUX_IPSR_GPSR(IP4_5_3, MISO_IO1),
 	PINMUX_IPSR_MSEL(IP4_5_3, VI1_R5, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP4_5_3, VI1_R5_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP4_5_3, VI2_G6),
-	PINMUX_IPSR_DATA(IP4_8_6, A23),
-	PINMUX_IPSR_DATA(IP4_8_6, IO2),
+	PINMUX_IPSR_GPSR(IP4_5_3, VI2_G6),
+	PINMUX_IPSR_GPSR(IP4_8_6, A23),
+	PINMUX_IPSR_GPSR(IP4_8_6, IO2),
 	PINMUX_IPSR_MSEL(IP4_8_6, VI1_G7, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP4_8_6, VI1_G7_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP4_8_6, VI2_G7),
-	PINMUX_IPSR_DATA(IP4_11_9, A24),
-	PINMUX_IPSR_DATA(IP4_11_9, IO3),
+	PINMUX_IPSR_GPSR(IP4_8_6, VI2_G7),
+	PINMUX_IPSR_GPSR(IP4_11_9, A24),
+	PINMUX_IPSR_GPSR(IP4_11_9, IO3),
 	PINMUX_IPSR_MSEL(IP4_11_9, VI1_R7, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP4_11_9, VI1_R7_B, SEL_VI1_1),
 	PINMUX_IPSR_MSEL(IP4_11_9, VI2_CLKENB, SEL_VI2_0),
 	PINMUX_IPSR_MSEL(IP4_11_9, VI2_CLKENB_B, SEL_VI2_1),
-	PINMUX_IPSR_DATA(IP4_14_12, A25),
-	PINMUX_IPSR_DATA(IP4_14_12, SSL),
+	PINMUX_IPSR_GPSR(IP4_14_12, A25),
+	PINMUX_IPSR_GPSR(IP4_14_12, SSL),
 	PINMUX_IPSR_MSEL(IP4_14_12, VI1_G6, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP4_14_12, VI1_G6_B, SEL_VI1_1),
 	PINMUX_IPSR_MSEL(IP4_14_12, VI2_FIELD, SEL_VI2_0),
 	PINMUX_IPSR_MSEL(IP4_14_12, VI2_FIELD_B, SEL_VI2_1),
-	PINMUX_IPSR_DATA(IP4_17_15, CS0_N),
+	PINMUX_IPSR_GPSR(IP4_17_15, CS0_N),
 	PINMUX_IPSR_MSEL(IP4_17_15, VI1_R6, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP4_17_15, VI1_R6_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP4_17_15, VI2_G3),
+	PINMUX_IPSR_GPSR(IP4_17_15, VI2_G3),
 	PINMUX_IPSR_MSEL(IP4_17_15, MSIOF0_SS2_B, SEL_SOF0_1),
-	PINMUX_IPSR_DATA(IP4_20_18, CS1_N_A26),
-	PINMUX_IPSR_DATA(IP4_20_18, SPEEDIN),
+	PINMUX_IPSR_GPSR(IP4_20_18, CS1_N_A26),
+	PINMUX_IPSR_GPSR(IP4_20_18, SPEEDIN),
 	PINMUX_IPSR_MSEL(IP4_20_18, VI0_R7, SEL_VI0_0),
 	PINMUX_IPSR_MSEL(IP4_20_18, VI0_R7_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP4_20_18, VI2_CLK, SEL_VI2_0),
 	PINMUX_IPSR_MSEL(IP4_20_18, VI2_CLK_B, SEL_VI2_1),
-	PINMUX_IPSR_DATA(IP4_23_21, EX_CS0_N),
+	PINMUX_IPSR_GPSR(IP4_23_21, EX_CS0_N),
 	PINMUX_IPSR_MSEL(IP4_23_21, HRX1_B, SEL_HSCIF1_1),
 	PINMUX_IPSR_MSEL(IP4_23_21, VI1_G5, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP4_23_21, VI1_G5_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP4_23_21, VI2_R0),
+	PINMUX_IPSR_GPSR(IP4_23_21, VI2_R0),
 	PINMUX_IPSR_MSEL(IP4_23_21, HTX0_B, SEL_HSCIF0_1),
 	PINMUX_IPSR_MSEL(IP4_23_21, MSIOF0_SS1_B, SEL_SOF0_1),
-	PINMUX_IPSR_DATA(IP4_26_24, EX_CS1_N),
-	PINMUX_IPSR_DATA(IP4_26_24, GPS_CLK),
+	PINMUX_IPSR_GPSR(IP4_26_24, EX_CS1_N),
+	PINMUX_IPSR_GPSR(IP4_26_24, GPS_CLK),
 	PINMUX_IPSR_MSEL(IP4_26_24, HCTS1_N_B, SEL_HSCIF1_1),
 	PINMUX_IPSR_MSEL(IP4_26_24, VI1_FIELD, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP4_26_24, VI1_FIELD_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP4_26_24, VI2_R1),
-	PINMUX_IPSR_DATA(IP4_29_27, EX_CS2_N),
-	PINMUX_IPSR_DATA(IP4_29_27, GPS_SIGN),
+	PINMUX_IPSR_GPSR(IP4_26_24, VI2_R1),
+	PINMUX_IPSR_GPSR(IP4_29_27, EX_CS2_N),
+	PINMUX_IPSR_GPSR(IP4_29_27, GPS_SIGN),
 	PINMUX_IPSR_MSEL(IP4_29_27, HRTS1_N_B, SEL_HSCIF1_1),
-	PINMUX_IPSR_DATA(IP4_29_27, VI3_CLKENB),
+	PINMUX_IPSR_GPSR(IP4_29_27, VI3_CLKENB),
 	PINMUX_IPSR_MSEL(IP4_29_27, VI1_G0, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP4_29_27, VI1_G0_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP4_29_27, VI2_R2),
+	PINMUX_IPSR_GPSR(IP4_29_27, VI2_R2),
 
-	PINMUX_IPSR_DATA(IP5_2_0, EX_CS3_N),
-	PINMUX_IPSR_DATA(IP5_2_0, GPS_MAG),
-	PINMUX_IPSR_DATA(IP5_2_0, VI3_FIELD),
+	PINMUX_IPSR_GPSR(IP5_2_0, EX_CS3_N),
+	PINMUX_IPSR_GPSR(IP5_2_0, GPS_MAG),
+	PINMUX_IPSR_GPSR(IP5_2_0, VI3_FIELD),
 	PINMUX_IPSR_MSEL(IP5_2_0, VI1_G1, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP5_2_0, VI1_G1_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP5_2_0, VI2_R3),
-	PINMUX_IPSR_DATA(IP5_5_3, EX_CS4_N),
+	PINMUX_IPSR_GPSR(IP5_2_0, VI2_R3),
+	PINMUX_IPSR_GPSR(IP5_5_3, EX_CS4_N),
 	PINMUX_IPSR_MSEL(IP5_5_3, MSIOF1_SCK_B, SEL_SOF1_1),
-	PINMUX_IPSR_DATA(IP5_5_3, VI3_HSYNC_N),
+	PINMUX_IPSR_GPSR(IP5_5_3, VI3_HSYNC_N),
 	PINMUX_IPSR_MSEL(IP5_5_3, VI2_HSYNC_N, SEL_VI2_0),
 	PINMUX_IPSR_MSEL(IP5_5_3, IIC1_SCL, SEL_IIC1_0),
 	PINMUX_IPSR_MSEL(IP5_5_3, VI2_HSYNC_N_B, SEL_VI2_1),
-	PINMUX_IPSR_DATA(IP5_5_3, INTC_EN0_N),
+	PINMUX_IPSR_GPSR(IP5_5_3, INTC_EN0_N),
 	PINMUX_IPSR_MSEL(IP5_5_3, I2C1_SCL, SEL_I2C1_0),
-	PINMUX_IPSR_DATA(IP5_9_6, EX_CS5_N),
+	PINMUX_IPSR_GPSR(IP5_9_6, EX_CS5_N),
 	PINMUX_IPSR_MSEL(IP5_9_6, CAN0_RX, SEL_CAN0_0),
 	PINMUX_IPSR_MSEL(IP5_9_6, MSIOF1_RXD_B, SEL_SOF1_1),
-	PINMUX_IPSR_DATA(IP5_9_6, VI3_VSYNC_N),
+	PINMUX_IPSR_GPSR(IP5_9_6, VI3_VSYNC_N),
 	PINMUX_IPSR_MSEL(IP5_9_6, VI1_G2, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP5_9_6, VI1_G2_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP5_9_6, VI2_R4),
+	PINMUX_IPSR_GPSR(IP5_9_6, VI2_R4),
 	PINMUX_IPSR_MSEL(IP5_9_6, IIC1_SDA, SEL_IIC1_0),
-	PINMUX_IPSR_DATA(IP5_9_6, INTC_EN1_N),
+	PINMUX_IPSR_GPSR(IP5_9_6, INTC_EN1_N),
 	PINMUX_IPSR_MSEL(IP5_9_6, I2C1_SDA, SEL_I2C1_0),
-	PINMUX_IPSR_DATA(IP5_12_10, BS_N),
+	PINMUX_IPSR_GPSR(IP5_12_10, BS_N),
 	PINMUX_IPSR_MSEL(IP5_12_10, IETX, SEL_IEB_0),
 	PINMUX_IPSR_MSEL(IP5_12_10, HTX1_B, SEL_HSCIF1_1),
 	PINMUX_IPSR_MSEL(IP5_12_10, CAN1_TX, SEL_CAN1_0),
-	PINMUX_IPSR_DATA(IP5_12_10, DRACK0),
+	PINMUX_IPSR_GPSR(IP5_12_10, DRACK0),
 	PINMUX_IPSR_MSEL(IP5_12_10, IETX_C, SEL_IEB_2),
-	PINMUX_IPSR_DATA(IP5_14_13, RD_N),
+	PINMUX_IPSR_GPSR(IP5_14_13, RD_N),
 	PINMUX_IPSR_MSEL(IP5_14_13, CAN0_TX, SEL_CAN0_0),
 	PINMUX_IPSR_MSEL(IP5_14_13, SCIFA0_SCK_B, SEL_SCFA_1),
-	PINMUX_IPSR_DATA(IP5_17_15, RD_WR_N),
+	PINMUX_IPSR_GPSR(IP5_17_15, RD_WR_N),
 	PINMUX_IPSR_MSEL(IP5_17_15, VI1_G3, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP5_17_15, VI1_G3_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP5_17_15, VI2_R5),
+	PINMUX_IPSR_GPSR(IP5_17_15, VI2_R5),
 	PINMUX_IPSR_MSEL(IP5_17_15, SCIFA0_RXD_B, SEL_SCFA_1),
-	PINMUX_IPSR_DATA(IP5_17_15, INTC_IRQ4_N),
-	PINMUX_IPSR_DATA(IP5_20_18, WE0_N),
+	PINMUX_IPSR_GPSR(IP5_17_15, INTC_IRQ4_N),
+	PINMUX_IPSR_GPSR(IP5_20_18, WE0_N),
 	PINMUX_IPSR_MSEL(IP5_20_18, IECLK, SEL_IEB_0),
 	PINMUX_IPSR_MSEL(IP5_20_18, CAN_CLK, SEL_CANCLK_0),
 	PINMUX_IPSR_MSEL(IP5_20_18, VI2_VSYNC_N, SEL_VI2_0),
 	PINMUX_IPSR_MSEL(IP5_20_18, SCIFA0_TXD_B, SEL_SCFA_1),
 	PINMUX_IPSR_MSEL(IP5_20_18, VI2_VSYNC_N_B, SEL_VI2_1),
-	PINMUX_IPSR_DATA(IP5_23_21, WE1_N),
+	PINMUX_IPSR_GPSR(IP5_23_21, WE1_N),
 	PINMUX_IPSR_MSEL(IP5_23_21, IERX, SEL_IEB_0),
 	PINMUX_IPSR_MSEL(IP5_23_21, CAN1_RX, SEL_CAN1_0),
 	PINMUX_IPSR_MSEL(IP5_23_21, VI1_G4, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP5_23_21, VI1_G4_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP5_23_21, VI2_R6),
+	PINMUX_IPSR_GPSR(IP5_23_21, VI2_R6),
 	PINMUX_IPSR_MSEL(IP5_23_21, SCIFA0_CTS_N_B, SEL_SCFA_1),
 	PINMUX_IPSR_MSEL(IP5_23_21, IERX_C, SEL_IEB_2),
 	PINMUX_IPSR_MSEL(IP5_26_24, EX_WAIT0, SEL_LBS_0),
-	PINMUX_IPSR_DATA(IP5_26_24, IRQ3),
-	PINMUX_IPSR_DATA(IP5_26_24, INTC_IRQ3_N),
+	PINMUX_IPSR_GPSR(IP5_26_24, IRQ3),
+	PINMUX_IPSR_GPSR(IP5_26_24, INTC_IRQ3_N),
 	PINMUX_IPSR_MSEL(IP5_26_24, VI3_CLK, SEL_VI3_0),
 	PINMUX_IPSR_MSEL(IP5_26_24, SCIFA0_RTS_N_B, SEL_SCFA_1),
 	PINMUX_IPSR_MSEL(IP5_26_24, HRX0_B, SEL_HSCIF0_1),
 	PINMUX_IPSR_MSEL(IP5_26_24, MSIOF0_SCK_B, SEL_SOF0_1),
-	PINMUX_IPSR_DATA(IP5_29_27, DREQ0_N),
+	PINMUX_IPSR_GPSR(IP5_29_27, DREQ0_N),
 	PINMUX_IPSR_MSEL(IP5_29_27, VI1_HSYNC_N, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP5_29_27, VI1_HSYNC_N_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP5_29_27, VI2_R7),
+	PINMUX_IPSR_GPSR(IP5_29_27, VI2_R7),
 	PINMUX_IPSR_MSEL(IP5_29_27, SSI_SCK78_C, SEL_SSI7_2),
 	PINMUX_IPSR_MSEL(IP5_29_27, SSI_WS78_B, SEL_SSI7_1),
 
-	PINMUX_IPSR_DATA(IP6_2_0, DACK0),
-	PINMUX_IPSR_DATA(IP6_2_0, IRQ0),
-	PINMUX_IPSR_DATA(IP6_2_0, INTC_IRQ0_N),
+	PINMUX_IPSR_GPSR(IP6_2_0, DACK0),
+	PINMUX_IPSR_GPSR(IP6_2_0, IRQ0),
+	PINMUX_IPSR_GPSR(IP6_2_0, INTC_IRQ0_N),
 	PINMUX_IPSR_MSEL(IP6_2_0, SSI_SCK6_B, SEL_SSI6_1),
 	PINMUX_IPSR_MSEL(IP6_2_0, VI1_VSYNC_N, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP6_2_0, VI1_VSYNC_N_B, SEL_VI1_1),
 	PINMUX_IPSR_MSEL(IP6_2_0, SSI_WS78_C, SEL_SSI7_2),
-	PINMUX_IPSR_DATA(IP6_5_3, DREQ1_N),
+	PINMUX_IPSR_GPSR(IP6_5_3, DREQ1_N),
 	PINMUX_IPSR_MSEL(IP6_5_3, VI1_CLKENB, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP6_5_3, VI1_CLKENB_B, SEL_VI1_1),
 	PINMUX_IPSR_MSEL(IP6_5_3, SSI_SDATA7_C, SEL_SSI7_2),
 	PINMUX_IPSR_MSEL(IP6_5_3, SSI_SCK78_B, SEL_SSI7_1),
-	PINMUX_IPSR_DATA(IP6_8_6, DACK1),
-	PINMUX_IPSR_DATA(IP6_8_6, IRQ1),
-	PINMUX_IPSR_DATA(IP6_8_6, INTC_IRQ1_N),
+	PINMUX_IPSR_GPSR(IP6_8_6, DACK1),
+	PINMUX_IPSR_GPSR(IP6_8_6, IRQ1),
+	PINMUX_IPSR_GPSR(IP6_8_6, INTC_IRQ1_N),
 	PINMUX_IPSR_MSEL(IP6_8_6, SSI_WS6_B, SEL_SSI6_1),
 	PINMUX_IPSR_MSEL(IP6_8_6, SSI_SDATA8_C, SEL_SSI8_2),
-	PINMUX_IPSR_DATA(IP6_10_9, DREQ2_N),
+	PINMUX_IPSR_GPSR(IP6_10_9, DREQ2_N),
 	PINMUX_IPSR_MSEL(IP6_10_9, HSCK1_B, SEL_HSCIF1_1),
 	PINMUX_IPSR_MSEL(IP6_10_9, HCTS0_N_B, SEL_HSCIF0_1),
 	PINMUX_IPSR_MSEL(IP6_10_9, MSIOF0_TXD_B, SEL_SOF0_1),
-	PINMUX_IPSR_DATA(IP6_13_11, DACK2),
-	PINMUX_IPSR_DATA(IP6_13_11, IRQ2),
-	PINMUX_IPSR_DATA(IP6_13_11, INTC_IRQ2_N),
+	PINMUX_IPSR_GPSR(IP6_13_11, DACK2),
+	PINMUX_IPSR_GPSR(IP6_13_11, IRQ2),
+	PINMUX_IPSR_GPSR(IP6_13_11, INTC_IRQ2_N),
 	PINMUX_IPSR_MSEL(IP6_13_11, SSI_SDATA6_B, SEL_SSI6_1),
 	PINMUX_IPSR_MSEL(IP6_13_11, HRTS0_N_B, SEL_HSCIF0_1),
 	PINMUX_IPSR_MSEL(IP6_13_11, MSIOF0_RXD_B, SEL_SOF0_1),
-	PINMUX_IPSR_DATA(IP6_16_14, ETH_CRS_DV),
+	PINMUX_IPSR_GPSR(IP6_16_14, ETH_CRS_DV),
 	PINMUX_IPSR_MSEL(IP6_16_14, STP_ISCLK_0_B, SEL_SSP_1),
 	PINMUX_IPSR_MSEL(IP6_16_14, TS_SDEN0_D, SEL_TSIF0_3),
 	PINMUX_IPSR_MSEL(IP6_16_14, GLO_Q0_C, SEL_GPS_2),
 	PINMUX_IPSR_MSEL(IP6_16_14, IIC2_SCL_E, SEL_IIC2_4),
 	PINMUX_IPSR_MSEL(IP6_16_14, I2C2_SCL_E, SEL_I2C2_4),
-	PINMUX_IPSR_DATA(IP6_19_17, ETH_RX_ER),
+	PINMUX_IPSR_GPSR(IP6_19_17, ETH_RX_ER),
 	PINMUX_IPSR_MSEL(IP6_19_17, STP_ISD_0_B, SEL_SSP_1),
 	PINMUX_IPSR_MSEL(IP6_19_17, TS_SPSYNC0_D, SEL_TSIF0_3),
 	PINMUX_IPSR_MSEL(IP6_19_17, GLO_Q1_C, SEL_GPS_2),
 	PINMUX_IPSR_MSEL(IP6_19_17, IIC2_SDA_E, SEL_IIC2_4),
 	PINMUX_IPSR_MSEL(IP6_19_17, I2C2_SDA_E, SEL_I2C2_4),
-	PINMUX_IPSR_DATA(IP6_22_20, ETH_RXD0),
+	PINMUX_IPSR_GPSR(IP6_22_20, ETH_RXD0),
 	PINMUX_IPSR_MSEL(IP6_22_20, STP_ISEN_0_B, SEL_SSP_1),
 	PINMUX_IPSR_MSEL(IP6_22_20, TS_SDAT0_D, SEL_TSIF0_3),
 	PINMUX_IPSR_MSEL(IP6_22_20, GLO_I0_C, SEL_GPS_2),
 	PINMUX_IPSR_MSEL(IP6_22_20, SCIFB1_SCK_G, SEL_SCIFB1_6),
 	PINMUX_IPSR_MSEL(IP6_22_20, SCK1_E, SEL_SCIF1_4),
-	PINMUX_IPSR_DATA(IP6_25_23, ETH_RXD1),
+	PINMUX_IPSR_GPSR(IP6_25_23, ETH_RXD1),
 	PINMUX_IPSR_MSEL(IP6_25_23, HRX0_E, SEL_HSCIF0_4),
 	PINMUX_IPSR_MSEL(IP6_25_23, STP_ISSYNC_0_B, SEL_SSP_1),
 	PINMUX_IPSR_MSEL(IP6_25_23, TS_SCK0_D, SEL_TSIF0_3),
 	PINMUX_IPSR_MSEL(IP6_25_23, GLO_I1_C, SEL_GPS_2),
 	PINMUX_IPSR_MSEL(IP6_25_23, SCIFB1_RXD_G, SEL_SCIFB1_6),
 	PINMUX_IPSR_MSEL(IP6_25_23, RX1_E, SEL_SCIF1_4),
-	PINMUX_IPSR_DATA(IP6_28_26, ETH_LINK),
+	PINMUX_IPSR_GPSR(IP6_28_26, ETH_LINK),
 	PINMUX_IPSR_MSEL(IP6_28_26, HTX0_E, SEL_HSCIF0_4),
 	PINMUX_IPSR_MSEL(IP6_28_26, STP_IVCXO27_0_B, SEL_SSP_1),
 	PINMUX_IPSR_MSEL(IP6_28_26, SCIFB1_TXD_G, SEL_SCIFB1_6),
 	PINMUX_IPSR_MSEL(IP6_28_26, TX1_E, SEL_SCIF1_4),
-	PINMUX_IPSR_DATA(IP6_31_29, ETH_REF_CLK),
+	PINMUX_IPSR_GPSR(IP6_31_29, ETH_REF_CLK),
 	PINMUX_IPSR_MSEL(IP6_31_29, HCTS0_N_E, SEL_HSCIF0_4),
 	PINMUX_IPSR_MSEL(IP6_31_29, STP_IVCXO27_1_B, SEL_SSP_1),
 	PINMUX_IPSR_MSEL(IP6_31_29, HRX0_F, SEL_HSCIF0_5),
 
-	PINMUX_IPSR_DATA(IP7_2_0, ETH_MDIO),
+	PINMUX_IPSR_GPSR(IP7_2_0, ETH_MDIO),
 	PINMUX_IPSR_MSEL(IP7_2_0, HRTS0_N_E, SEL_HSCIF0_4),
 	PINMUX_IPSR_MSEL(IP7_2_0, SIM0_D_C, SEL_SIM_2),
 	PINMUX_IPSR_MSEL(IP7_2_0, HCTS0_N_F, SEL_HSCIF0_5),
-	PINMUX_IPSR_DATA(IP7_5_3, ETH_TXD1),
+	PINMUX_IPSR_GPSR(IP7_5_3, ETH_TXD1),
 	PINMUX_IPSR_MSEL(IP7_5_3, HTX0_F, SEL_HSCIF0_5),
 	PINMUX_IPSR_MSEL(IP7_5_3, BPFCLK_G, SEL_FM_6),
-	PINMUX_IPSR_DATA(IP7_7_6, ETH_TX_EN),
+	PINMUX_IPSR_GPSR(IP7_7_6, ETH_TX_EN),
 	PINMUX_IPSR_MSEL(IP7_7_6, SIM0_CLK_C, SEL_SIM_2),
 	PINMUX_IPSR_MSEL(IP7_7_6, HRTS0_N_F, SEL_HSCIF0_5),
-	PINMUX_IPSR_DATA(IP7_9_8, ETH_MAGIC),
+	PINMUX_IPSR_GPSR(IP7_9_8, ETH_MAGIC),
 	PINMUX_IPSR_MSEL(IP7_9_8, SIM0_RST_C, SEL_SIM_2),
-	PINMUX_IPSR_DATA(IP7_12_10, ETH_TXD0),
+	PINMUX_IPSR_GPSR(IP7_12_10, ETH_TXD0),
 	PINMUX_IPSR_MSEL(IP7_12_10, STP_ISCLK_1_B, SEL_SSP_1),
 	PINMUX_IPSR_MSEL(IP7_12_10, TS_SDEN1_C, SEL_TSIF1_2),
 	PINMUX_IPSR_MSEL(IP7_12_10, GLO_SCLK_C, SEL_GPS_2),
-	PINMUX_IPSR_DATA(IP7_15_13, ETH_MDC),
+	PINMUX_IPSR_GPSR(IP7_15_13, ETH_MDC),
 	PINMUX_IPSR_MSEL(IP7_15_13, STP_ISD_1_B, SEL_SSP_1),
 	PINMUX_IPSR_MSEL(IP7_15_13, TS_SPSYNC1_C, SEL_TSIF1_2),
 	PINMUX_IPSR_MSEL(IP7_15_13, GLO_SDATA_C, SEL_GPS_2),
-	PINMUX_IPSR_DATA(IP7_18_16, PWM0),
+	PINMUX_IPSR_GPSR(IP7_18_16, PWM0),
 	PINMUX_IPSR_MSEL(IP7_18_16, SCIFA2_SCK_C, SEL_SCIFA2_2),
 	PINMUX_IPSR_MSEL(IP7_18_16, STP_ISEN_1_B, SEL_SSP_1),
 	PINMUX_IPSR_MSEL(IP7_18_16, TS_SDAT1_C, SEL_TSIF1_2),
 	PINMUX_IPSR_MSEL(IP7_18_16, GLO_SS_C, SEL_GPS_2),
-	PINMUX_IPSR_DATA(IP7_21_19, PWM1),
+	PINMUX_IPSR_GPSR(IP7_21_19, PWM1),
 	PINMUX_IPSR_MSEL(IP7_21_19, SCIFA2_TXD_C, SEL_SCIFA2_2),
 	PINMUX_IPSR_MSEL(IP7_21_19, STP_ISSYNC_1_B, SEL_SSP_1),
 	PINMUX_IPSR_MSEL(IP7_21_19, TS_SCK1_C, SEL_TSIF1_2),
 	PINMUX_IPSR_MSEL(IP7_21_19, GLO_RFON_C, SEL_GPS_2),
-	PINMUX_IPSR_DATA(IP7_21_19, PCMOE_N),
-	PINMUX_IPSR_DATA(IP7_24_22, PWM2),
-	PINMUX_IPSR_DATA(IP7_24_22, PWMFSW0),
+	PINMUX_IPSR_GPSR(IP7_21_19, PCMOE_N),
+	PINMUX_IPSR_GPSR(IP7_24_22, PWM2),
+	PINMUX_IPSR_GPSR(IP7_24_22, PWMFSW0),
 	PINMUX_IPSR_MSEL(IP7_24_22, SCIFA2_RXD_C, SEL_SCIFA2_2),
-	PINMUX_IPSR_DATA(IP7_24_22, PCMWE_N),
+	PINMUX_IPSR_GPSR(IP7_24_22, PCMWE_N),
 	PINMUX_IPSR_MSEL(IP7_24_22, IECLK_C, SEL_IEB_2),
-	PINMUX_IPSR_DATA(IP7_26_25, DU_DOTCLKIN1),
-	PINMUX_IPSR_DATA(IP7_26_25, AUDIO_CLKC),
-	PINMUX_IPSR_DATA(IP7_26_25, AUDIO_CLKOUT_C),
+	PINMUX_IPSR_GPSR(IP7_26_25, DU_DOTCLKIN1),
+	PINMUX_IPSR_GPSR(IP7_26_25, AUDIO_CLKC),
+	PINMUX_IPSR_GPSR(IP7_26_25, AUDIO_CLKOUT_C),
 	PINMUX_IPSR_MSEL(IP7_28_27, VI0_CLK, SEL_VI0_0),
-	PINMUX_IPSR_DATA(IP7_28_27, ATACS00_N),
-	PINMUX_IPSR_DATA(IP7_28_27, AVB_RXD1),
+	PINMUX_IPSR_GPSR(IP7_28_27, ATACS00_N),
+	PINMUX_IPSR_GPSR(IP7_28_27, AVB_RXD1),
 	PINMUX_IPSR_MSEL(IP7_30_29, VI0_DATA0_VI0_B0, SEL_VI0_0),
-	PINMUX_IPSR_DATA(IP7_30_29, ATACS10_N),
-	PINMUX_IPSR_DATA(IP7_30_29, AVB_RXD2),
+	PINMUX_IPSR_GPSR(IP7_30_29, ATACS10_N),
+	PINMUX_IPSR_GPSR(IP7_30_29, AVB_RXD2),
 
 	PINMUX_IPSR_MSEL(IP8_1_0, VI0_DATA1_VI0_B1, SEL_VI0_0),
-	PINMUX_IPSR_DATA(IP8_1_0, ATARD0_N),
-	PINMUX_IPSR_DATA(IP8_1_0, AVB_RXD3),
+	PINMUX_IPSR_GPSR(IP8_1_0, ATARD0_N),
+	PINMUX_IPSR_GPSR(IP8_1_0, AVB_RXD3),
 	PINMUX_IPSR_MSEL(IP8_3_2, VI0_DATA2_VI0_B2, SEL_VI0_0),
-	PINMUX_IPSR_DATA(IP8_3_2, ATAWR0_N),
-	PINMUX_IPSR_DATA(IP8_3_2, AVB_RXD4),
+	PINMUX_IPSR_GPSR(IP8_3_2, ATAWR0_N),
+	PINMUX_IPSR_GPSR(IP8_3_2, AVB_RXD4),
 	PINMUX_IPSR_MSEL(IP8_5_4, VI0_DATA3_VI0_B3, SEL_VI0_0),
-	PINMUX_IPSR_DATA(IP8_5_4, ATADIR0_N),
-	PINMUX_IPSR_DATA(IP8_5_4, AVB_RXD5),
+	PINMUX_IPSR_GPSR(IP8_5_4, ATADIR0_N),
+	PINMUX_IPSR_GPSR(IP8_5_4, AVB_RXD5),
 	PINMUX_IPSR_MSEL(IP8_7_6, VI0_DATA4_VI0_B4, SEL_VI0_0),
-	PINMUX_IPSR_DATA(IP8_7_6, ATAG0_N),
-	PINMUX_IPSR_DATA(IP8_7_6, AVB_RXD6),
+	PINMUX_IPSR_GPSR(IP8_7_6, ATAG0_N),
+	PINMUX_IPSR_GPSR(IP8_7_6, AVB_RXD6),
 	PINMUX_IPSR_MSEL(IP8_9_8, VI0_DATA5_VI0_B5, SEL_VI0_0),
-	PINMUX_IPSR_DATA(IP8_9_8, EX_WAIT1),
-	PINMUX_IPSR_DATA(IP8_9_8, AVB_RXD7),
+	PINMUX_IPSR_GPSR(IP8_9_8, EX_WAIT1),
+	PINMUX_IPSR_GPSR(IP8_9_8, AVB_RXD7),
 	PINMUX_IPSR_MSEL(IP8_11_10, VI0_DATA6_VI0_B6, SEL_VI0_0),
-	PINMUX_IPSR_DATA(IP8_11_10, AVB_RX_ER),
+	PINMUX_IPSR_GPSR(IP8_11_10, AVB_RX_ER),
 	PINMUX_IPSR_MSEL(IP8_13_12, VI0_DATA7_VI0_B7, SEL_VI0_0),
-	PINMUX_IPSR_DATA(IP8_13_12, AVB_RX_CLK),
+	PINMUX_IPSR_GPSR(IP8_13_12, AVB_RX_CLK),
 	PINMUX_IPSR_MSEL(IP8_15_14, VI1_CLK, SEL_VI1_0),
-	PINMUX_IPSR_DATA(IP8_15_14, AVB_RX_DV),
+	PINMUX_IPSR_GPSR(IP8_15_14, AVB_RX_DV),
 	PINMUX_IPSR_MSEL(IP8_17_16, VI1_DATA0_VI1_B0, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP8_17_16, SCIFA1_SCK_D, SEL_SCIFA1_3),
-	PINMUX_IPSR_DATA(IP8_17_16, AVB_CRS),
+	PINMUX_IPSR_GPSR(IP8_17_16, AVB_CRS),
 	PINMUX_IPSR_MSEL(IP8_19_18, VI1_DATA1_VI1_B1, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP8_19_18, SCIFA1_RXD_D, SEL_SCIFA1_3),
-	PINMUX_IPSR_DATA(IP8_19_18, AVB_MDC),
+	PINMUX_IPSR_GPSR(IP8_19_18, AVB_MDC),
 	PINMUX_IPSR_MSEL(IP8_21_20, VI1_DATA2_VI1_B2, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP8_21_20, SCIFA1_TXD_D, SEL_SCIFA1_3),
-	PINMUX_IPSR_DATA(IP8_21_20, AVB_MDIO),
+	PINMUX_IPSR_GPSR(IP8_21_20, AVB_MDIO),
 	PINMUX_IPSR_MSEL(IP8_23_22, VI1_DATA3_VI1_B3, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP8_23_22, SCIFA1_CTS_N_D, SEL_SCIFA1_3),
-	PINMUX_IPSR_DATA(IP8_23_22, AVB_GTX_CLK),
+	PINMUX_IPSR_GPSR(IP8_23_22, AVB_GTX_CLK),
 	PINMUX_IPSR_MSEL(IP8_25_24, VI1_DATA4_VI1_B4, SEL_VI1_0),
 	PINMUX_IPSR_MSEL(IP8_25_24, SCIFA1_RTS_N_D, SEL_SCIFA1_3),
-	PINMUX_IPSR_DATA(IP8_25_24, AVB_MAGIC),
+	PINMUX_IPSR_GPSR(IP8_25_24, AVB_MAGIC),
 	PINMUX_IPSR_MSEL(IP8_26, VI1_DATA5_VI1_B5, SEL_VI1_0),
-	PINMUX_IPSR_DATA(IP8_26, AVB_PHY_INT),
+	PINMUX_IPSR_GPSR(IP8_26, AVB_PHY_INT),
 	PINMUX_IPSR_MSEL(IP8_27, VI1_DATA6_VI1_B6, SEL_VI1_0),
-	PINMUX_IPSR_DATA(IP8_27, AVB_GTXREFCLK),
-	PINMUX_IPSR_DATA(IP8_28, SD0_CLK),
+	PINMUX_IPSR_GPSR(IP8_27, AVB_GTXREFCLK),
+	PINMUX_IPSR_GPSR(IP8_28, SD0_CLK),
 	PINMUX_IPSR_MSEL(IP8_28, VI1_DATA0_VI1_B0_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP8_30_29, SD0_CMD),
+	PINMUX_IPSR_GPSR(IP8_30_29, SD0_CMD),
 	PINMUX_IPSR_MSEL(IP8_30_29, SCIFB1_SCK_B, SEL_SCIFB1_1),
 	PINMUX_IPSR_MSEL(IP8_30_29, VI1_DATA1_VI1_B1_B, SEL_VI1_1),
 
-	PINMUX_IPSR_DATA(IP9_1_0, SD0_DAT0),
+	PINMUX_IPSR_GPSR(IP9_1_0, SD0_DAT0),
 	PINMUX_IPSR_MSEL(IP9_1_0, SCIFB1_RXD_B, SEL_SCIFB1_1),
 	PINMUX_IPSR_MSEL(IP9_1_0, VI1_DATA2_VI1_B2_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP9_3_2, SD0_DAT1),
+	PINMUX_IPSR_GPSR(IP9_3_2, SD0_DAT1),
 	PINMUX_IPSR_MSEL(IP9_3_2, SCIFB1_TXD_B, SEL_SCIFB1_1),
 	PINMUX_IPSR_MSEL(IP9_3_2, VI1_DATA3_VI1_B3_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP9_5_4, SD0_DAT2),
+	PINMUX_IPSR_GPSR(IP9_5_4, SD0_DAT2),
 	PINMUX_IPSR_MSEL(IP9_5_4, SCIFB1_CTS_N_B, SEL_SCIFB1_1),
 	PINMUX_IPSR_MSEL(IP9_5_4, VI1_DATA4_VI1_B4_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP9_7_6, SD0_DAT3),
+	PINMUX_IPSR_GPSR(IP9_7_6, SD0_DAT3),
 	PINMUX_IPSR_MSEL(IP9_7_6, SCIFB1_RTS_N_B, SEL_SCIFB1_1),
 	PINMUX_IPSR_MSEL(IP9_7_6, VI1_DATA5_VI1_B5_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP9_11_8, SD0_CD),
-	PINMUX_IPSR_DATA(IP9_11_8, MMC0_D6),
+	PINMUX_IPSR_GPSR(IP9_11_8, SD0_CD),
+	PINMUX_IPSR_GPSR(IP9_11_8, MMC0_D6),
 	PINMUX_IPSR_MSEL(IP9_11_8, TS_SDEN0_B, SEL_TSIF0_1),
-	PINMUX_IPSR_DATA(IP9_11_8, USB0_EXTP),
+	PINMUX_IPSR_GPSR(IP9_11_8, USB0_EXTP),
 	PINMUX_IPSR_MSEL(IP9_11_8, GLO_SCLK, SEL_GPS_0),
 	PINMUX_IPSR_MSEL(IP9_11_8, VI1_DATA6_VI1_B6_B, SEL_VI1_1),
 	PINMUX_IPSR_MSEL(IP9_11_8, IIC1_SCL_B, SEL_IIC1_1),
 	PINMUX_IPSR_MSEL(IP9_11_8, I2C1_SCL_B, SEL_I2C1_1),
 	PINMUX_IPSR_MSEL(IP9_11_8, VI2_DATA6_VI2_B6_B, SEL_VI2_1),
-	PINMUX_IPSR_DATA(IP9_15_12, SD0_WP),
-	PINMUX_IPSR_DATA(IP9_15_12, MMC0_D7),
+	PINMUX_IPSR_GPSR(IP9_15_12, SD0_WP),
+	PINMUX_IPSR_GPSR(IP9_15_12, MMC0_D7),
 	PINMUX_IPSR_MSEL(IP9_15_12, TS_SPSYNC0_B, SEL_TSIF0_1),
-	PINMUX_IPSR_DATA(IP9_15_12, USB0_IDIN),
+	PINMUX_IPSR_GPSR(IP9_15_12, USB0_IDIN),
 	PINMUX_IPSR_MSEL(IP9_15_12, GLO_SDATA, SEL_GPS_0),
 	PINMUX_IPSR_MSEL(IP9_15_12, VI1_DATA7_VI1_B7_B, SEL_VI1_1),
 	PINMUX_IPSR_MSEL(IP9_15_12, IIC1_SDA_B, SEL_IIC1_1),
 	PINMUX_IPSR_MSEL(IP9_15_12, I2C1_SDA_B, SEL_I2C1_1),
 	PINMUX_IPSR_MSEL(IP9_15_12, VI2_DATA7_VI2_B7_B, SEL_VI2_1),
-	PINMUX_IPSR_DATA(IP9_17_16, SD1_CLK),
-	PINMUX_IPSR_DATA(IP9_17_16, AVB_TX_EN),
-	PINMUX_IPSR_DATA(IP9_19_18, SD1_CMD),
-	PINMUX_IPSR_DATA(IP9_19_18, AVB_TX_ER),
+	PINMUX_IPSR_GPSR(IP9_17_16, SD1_CLK),
+	PINMUX_IPSR_GPSR(IP9_17_16, AVB_TX_EN),
+	PINMUX_IPSR_GPSR(IP9_19_18, SD1_CMD),
+	PINMUX_IPSR_GPSR(IP9_19_18, AVB_TX_ER),
 	PINMUX_IPSR_MSEL(IP9_19_18, SCIFB0_SCK_B, SEL_SCIFB_1),
-	PINMUX_IPSR_DATA(IP9_21_20, SD1_DAT0),
-	PINMUX_IPSR_DATA(IP9_21_20, AVB_TX_CLK),
+	PINMUX_IPSR_GPSR(IP9_21_20, SD1_DAT0),
+	PINMUX_IPSR_GPSR(IP9_21_20, AVB_TX_CLK),
 	PINMUX_IPSR_MSEL(IP9_21_20, SCIFB0_RXD_B, SEL_SCIFB_1),
-	PINMUX_IPSR_DATA(IP9_23_22, SD1_DAT1),
-	PINMUX_IPSR_DATA(IP9_23_22, AVB_LINK),
+	PINMUX_IPSR_GPSR(IP9_23_22, SD1_DAT1),
+	PINMUX_IPSR_GPSR(IP9_23_22, AVB_LINK),
 	PINMUX_IPSR_MSEL(IP9_23_22, SCIFB0_TXD_B, SEL_SCIFB_1),
-	PINMUX_IPSR_DATA(IP9_25_24, SD1_DAT2),
-	PINMUX_IPSR_DATA(IP9_25_24, AVB_COL),
+	PINMUX_IPSR_GPSR(IP9_25_24, SD1_DAT2),
+	PINMUX_IPSR_GPSR(IP9_25_24, AVB_COL),
 	PINMUX_IPSR_MSEL(IP9_25_24, SCIFB0_CTS_N_B, SEL_SCIFB_1),
-	PINMUX_IPSR_DATA(IP9_27_26, SD1_DAT3),
-	PINMUX_IPSR_DATA(IP9_27_26, AVB_RXD0),
+	PINMUX_IPSR_GPSR(IP9_27_26, SD1_DAT3),
+	PINMUX_IPSR_GPSR(IP9_27_26, AVB_RXD0),
 	PINMUX_IPSR_MSEL(IP9_27_26, SCIFB0_RTS_N_B, SEL_SCIFB_1),
-	PINMUX_IPSR_DATA(IP9_31_28, SD1_CD),
-	PINMUX_IPSR_DATA(IP9_31_28, MMC1_D6),
+	PINMUX_IPSR_GPSR(IP9_31_28, SD1_CD),
+	PINMUX_IPSR_GPSR(IP9_31_28, MMC1_D6),
 	PINMUX_IPSR_MSEL(IP9_31_28, TS_SDEN1, SEL_TSIF1_0),
-	PINMUX_IPSR_DATA(IP9_31_28, USB1_EXTP),
+	PINMUX_IPSR_GPSR(IP9_31_28, USB1_EXTP),
 	PINMUX_IPSR_MSEL(IP9_31_28, GLO_SS, SEL_GPS_0),
 	PINMUX_IPSR_MSEL(IP9_31_28, VI0_CLK_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP9_31_28, IIC2_SCL_D, SEL_IIC2_3),
@@ -1330,24 +1330,24 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP9_31_28, SIM0_CLK_B, SEL_SIM_1),
 	PINMUX_IPSR_MSEL(IP9_31_28, VI3_CLK_B, SEL_VI3_1),
 
-	PINMUX_IPSR_DATA(IP10_3_0, SD1_WP),
-	PINMUX_IPSR_DATA(IP10_3_0, MMC1_D7),
+	PINMUX_IPSR_GPSR(IP10_3_0, SD1_WP),
+	PINMUX_IPSR_GPSR(IP10_3_0, MMC1_D7),
 	PINMUX_IPSR_MSEL(IP10_3_0, TS_SPSYNC1, SEL_TSIF1_0),
-	PINMUX_IPSR_DATA(IP10_3_0, USB1_IDIN),
+	PINMUX_IPSR_GPSR(IP10_3_0, USB1_IDIN),
 	PINMUX_IPSR_MSEL(IP10_3_0, GLO_RFON, SEL_GPS_0),
 	PINMUX_IPSR_MSEL(IP10_3_0, VI1_CLK_B, SEL_VI1_1),
 	PINMUX_IPSR_MSEL(IP10_3_0, IIC2_SDA_D, SEL_IIC2_3),
 	PINMUX_IPSR_MSEL(IP10_3_0, I2C2_SDA_D, SEL_I2C2_3),
 	PINMUX_IPSR_MSEL(IP10_3_0, SIM0_D_B, SEL_SIM_1),
-	PINMUX_IPSR_DATA(IP10_6_4, SD2_CLK),
-	PINMUX_IPSR_DATA(IP10_6_4, MMC0_CLK),
+	PINMUX_IPSR_GPSR(IP10_6_4, SD2_CLK),
+	PINMUX_IPSR_GPSR(IP10_6_4, MMC0_CLK),
 	PINMUX_IPSR_MSEL(IP10_6_4, SIM0_CLK, SEL_SIM_0),
 	PINMUX_IPSR_MSEL(IP10_6_4, VI0_DATA0_VI0_B0_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP10_6_4, TS_SDEN0_C, SEL_TSIF0_2),
 	PINMUX_IPSR_MSEL(IP10_6_4, GLO_SCLK_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP10_6_4, VI3_DATA0_B, SEL_VI3_1),
-	PINMUX_IPSR_DATA(IP10_10_7, SD2_CMD),
-	PINMUX_IPSR_DATA(IP10_10_7, MMC0_CMD),
+	PINMUX_IPSR_GPSR(IP10_10_7, SD2_CMD),
+	PINMUX_IPSR_GPSR(IP10_10_7, MMC0_CMD),
 	PINMUX_IPSR_MSEL(IP10_10_7, SIM0_D, SEL_SIM_0),
 	PINMUX_IPSR_MSEL(IP10_10_7, VI0_DATA1_VI0_B1_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP10_10_7, SCIFB1_SCK_E, SEL_SCIFB1_4),
@@ -1355,8 +1355,8 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP10_10_7, TS_SPSYNC0_C, SEL_TSIF0_2),
 	PINMUX_IPSR_MSEL(IP10_10_7, GLO_SDATA_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP10_10_7, VI3_DATA1_B, SEL_VI3_1),
-	PINMUX_IPSR_DATA(IP10_14_11, SD2_DAT0),
-	PINMUX_IPSR_DATA(IP10_14_11, MMC0_D0),
+	PINMUX_IPSR_GPSR(IP10_14_11, SD2_DAT0),
+	PINMUX_IPSR_GPSR(IP10_14_11, MMC0_D0),
 	PINMUX_IPSR_MSEL(IP10_14_11, FMCLK_B, SEL_FM_1),
 	PINMUX_IPSR_MSEL(IP10_14_11, VI0_DATA2_VI0_B2_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP10_14_11, SCIFB1_RXD_E, SEL_SCIFB1_4),
@@ -1364,8 +1364,8 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP10_14_11, TS_SDAT0_C, SEL_TSIF0_2),
 	PINMUX_IPSR_MSEL(IP10_14_11, GLO_SS_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP10_14_11, VI3_DATA2_B, SEL_VI3_1),
-	PINMUX_IPSR_DATA(IP10_18_15, SD2_DAT1),
-	PINMUX_IPSR_DATA(IP10_18_15, MMC0_D1),
+	PINMUX_IPSR_GPSR(IP10_18_15, SD2_DAT1),
+	PINMUX_IPSR_GPSR(IP10_18_15, MMC0_D1),
 	PINMUX_IPSR_MSEL(IP10_18_15, FMIN_B, SEL_FM_1),
 	PINMUX_IPSR_MSEL(IP10_18_15, VI0_DATA3_VI0_B3_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP10_18_15, SCIFB1_TXD_E, SEL_SCIFB1_4),
@@ -1373,26 +1373,26 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP10_18_15, TS_SCK0_C, SEL_TSIF0_2),
 	PINMUX_IPSR_MSEL(IP10_18_15, GLO_RFON_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP10_18_15, VI3_DATA3_B, SEL_VI3_1),
-	PINMUX_IPSR_DATA(IP10_22_19, SD2_DAT2),
-	PINMUX_IPSR_DATA(IP10_22_19, MMC0_D2),
+	PINMUX_IPSR_GPSR(IP10_22_19, SD2_DAT2),
+	PINMUX_IPSR_GPSR(IP10_22_19, MMC0_D2),
 	PINMUX_IPSR_MSEL(IP10_22_19, BPFCLK_B, SEL_FM_1),
 	PINMUX_IPSR_MSEL(IP10_22_19, VI0_DATA4_VI0_B4_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP10_22_19, HRX0_D, SEL_HSCIF0_3),
 	PINMUX_IPSR_MSEL(IP10_22_19, TS_SDEN1_B, SEL_TSIF1_1),
 	PINMUX_IPSR_MSEL(IP10_22_19, GLO_Q0_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP10_22_19, VI3_DATA4_B, SEL_VI3_1),
-	PINMUX_IPSR_DATA(IP10_25_23, SD2_DAT3),
-	PINMUX_IPSR_DATA(IP10_25_23, MMC0_D3),
+	PINMUX_IPSR_GPSR(IP10_25_23, SD2_DAT3),
+	PINMUX_IPSR_GPSR(IP10_25_23, MMC0_D3),
 	PINMUX_IPSR_MSEL(IP10_25_23, SIM0_RST, SEL_SIM_0),
 	PINMUX_IPSR_MSEL(IP10_25_23, VI0_DATA5_VI0_B5_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP10_25_23, HTX0_D, SEL_HSCIF0_3),
 	PINMUX_IPSR_MSEL(IP10_25_23, TS_SPSYNC1_B, SEL_TSIF1_1),
 	PINMUX_IPSR_MSEL(IP10_25_23, GLO_Q1_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP10_25_23, VI3_DATA5_B, SEL_VI3_1),
-	PINMUX_IPSR_DATA(IP10_29_26, SD2_CD),
-	PINMUX_IPSR_DATA(IP10_29_26, MMC0_D4),
+	PINMUX_IPSR_GPSR(IP10_29_26, SD2_CD),
+	PINMUX_IPSR_GPSR(IP10_29_26, MMC0_D4),
 	PINMUX_IPSR_MSEL(IP10_29_26, TS_SDAT0_B, SEL_TSIF0_1),
-	PINMUX_IPSR_DATA(IP10_29_26, USB2_EXTP),
+	PINMUX_IPSR_GPSR(IP10_29_26, USB2_EXTP),
 	PINMUX_IPSR_MSEL(IP10_29_26, GLO_I0, SEL_GPS_0),
 	PINMUX_IPSR_MSEL(IP10_29_26, VI0_DATA6_VI0_B6_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP10_29_26, HCTS0_N_D, SEL_HSCIF0_3),
@@ -1400,164 +1400,164 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP10_29_26, GLO_I0_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP10_29_26, VI3_DATA6_B, SEL_VI3_1),
 
-	PINMUX_IPSR_DATA(IP11_3_0, SD2_WP),
-	PINMUX_IPSR_DATA(IP11_3_0, MMC0_D5),
+	PINMUX_IPSR_GPSR(IP11_3_0, SD2_WP),
+	PINMUX_IPSR_GPSR(IP11_3_0, MMC0_D5),
 	PINMUX_IPSR_MSEL(IP11_3_0, TS_SCK0_B, SEL_TSIF0_1),
-	PINMUX_IPSR_DATA(IP11_3_0, USB2_IDIN),
+	PINMUX_IPSR_GPSR(IP11_3_0, USB2_IDIN),
 	PINMUX_IPSR_MSEL(IP11_3_0, GLO_I1, SEL_GPS_0),
 	PINMUX_IPSR_MSEL(IP11_3_0, VI0_DATA7_VI0_B7_B, SEL_VI0_1),
 	PINMUX_IPSR_MSEL(IP11_3_0, HRTS0_N_D, SEL_HSCIF0_3),
 	PINMUX_IPSR_MSEL(IP11_3_0, TS_SCK1_B, SEL_TSIF1_1),
 	PINMUX_IPSR_MSEL(IP11_3_0, GLO_I1_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP11_3_0, VI3_DATA7_B, SEL_VI3_1),
-	PINMUX_IPSR_DATA(IP11_4, SD3_CLK),
-	PINMUX_IPSR_DATA(IP11_4, MMC1_CLK),
-	PINMUX_IPSR_DATA(IP11_6_5, SD3_CMD),
-	PINMUX_IPSR_DATA(IP11_6_5, MMC1_CMD),
-	PINMUX_IPSR_DATA(IP11_6_5, MTS_N),
-	PINMUX_IPSR_DATA(IP11_8_7, SD3_DAT0),
-	PINMUX_IPSR_DATA(IP11_8_7, MMC1_D0),
-	PINMUX_IPSR_DATA(IP11_8_7, STM_N),
-	PINMUX_IPSR_DATA(IP11_10_9, SD3_DAT1),
-	PINMUX_IPSR_DATA(IP11_10_9, MMC1_D1),
-	PINMUX_IPSR_DATA(IP11_10_9, MDATA),
-	PINMUX_IPSR_DATA(IP11_12_11, SD3_DAT2),
-	PINMUX_IPSR_DATA(IP11_12_11, MMC1_D2),
-	PINMUX_IPSR_DATA(IP11_12_11, SDATA),
-	PINMUX_IPSR_DATA(IP11_14_13, SD3_DAT3),
-	PINMUX_IPSR_DATA(IP11_14_13, MMC1_D3),
-	PINMUX_IPSR_DATA(IP11_14_13, SCKZ),
-	PINMUX_IPSR_DATA(IP11_17_15, SD3_CD),
-	PINMUX_IPSR_DATA(IP11_17_15, MMC1_D4),
+	PINMUX_IPSR_GPSR(IP11_4, SD3_CLK),
+	PINMUX_IPSR_GPSR(IP11_4, MMC1_CLK),
+	PINMUX_IPSR_GPSR(IP11_6_5, SD3_CMD),
+	PINMUX_IPSR_GPSR(IP11_6_5, MMC1_CMD),
+	PINMUX_IPSR_GPSR(IP11_6_5, MTS_N),
+	PINMUX_IPSR_GPSR(IP11_8_7, SD3_DAT0),
+	PINMUX_IPSR_GPSR(IP11_8_7, MMC1_D0),
+	PINMUX_IPSR_GPSR(IP11_8_7, STM_N),
+	PINMUX_IPSR_GPSR(IP11_10_9, SD3_DAT1),
+	PINMUX_IPSR_GPSR(IP11_10_9, MMC1_D1),
+	PINMUX_IPSR_GPSR(IP11_10_9, MDATA),
+	PINMUX_IPSR_GPSR(IP11_12_11, SD3_DAT2),
+	PINMUX_IPSR_GPSR(IP11_12_11, MMC1_D2),
+	PINMUX_IPSR_GPSR(IP11_12_11, SDATA),
+	PINMUX_IPSR_GPSR(IP11_14_13, SD3_DAT3),
+	PINMUX_IPSR_GPSR(IP11_14_13, MMC1_D3),
+	PINMUX_IPSR_GPSR(IP11_14_13, SCKZ),
+	PINMUX_IPSR_GPSR(IP11_17_15, SD3_CD),
+	PINMUX_IPSR_GPSR(IP11_17_15, MMC1_D4),
 	PINMUX_IPSR_MSEL(IP11_17_15, TS_SDAT1, SEL_TSIF1_0),
-	PINMUX_IPSR_DATA(IP11_17_15, VSP),
+	PINMUX_IPSR_GPSR(IP11_17_15, VSP),
 	PINMUX_IPSR_MSEL(IP11_17_15, GLO_Q0, SEL_GPS_0),
 	PINMUX_IPSR_MSEL(IP11_17_15, SIM0_RST_B, SEL_SIM_1),
-	PINMUX_IPSR_DATA(IP11_21_18, SD3_WP),
-	PINMUX_IPSR_DATA(IP11_21_18, MMC1_D5),
+	PINMUX_IPSR_GPSR(IP11_21_18, SD3_WP),
+	PINMUX_IPSR_GPSR(IP11_21_18, MMC1_D5),
 	PINMUX_IPSR_MSEL(IP11_21_18, TS_SCK1, SEL_TSIF1_0),
 	PINMUX_IPSR_MSEL(IP11_21_18, GLO_Q1, SEL_GPS_0),
 	PINMUX_IPSR_MSEL(IP11_21_18, FMIN_C, SEL_FM_2),
 	PINMUX_IPSR_MSEL(IP11_21_18, FMIN_E, SEL_FM_4),
 	PINMUX_IPSR_MSEL(IP11_21_18, FMIN_F, SEL_FM_5),
-	PINMUX_IPSR_DATA(IP11_23_22, MLB_CLK),
+	PINMUX_IPSR_GPSR(IP11_23_22, MLB_CLK),
 	PINMUX_IPSR_MSEL(IP11_23_22, IIC2_SCL_B, SEL_IIC2_1),
 	PINMUX_IPSR_MSEL(IP11_23_22, I2C2_SCL_B, SEL_I2C2_1),
-	PINMUX_IPSR_DATA(IP11_26_24, MLB_SIG),
+	PINMUX_IPSR_GPSR(IP11_26_24, MLB_SIG),
 	PINMUX_IPSR_MSEL(IP11_26_24, SCIFB1_RXD_D, SEL_SCIFB1_3),
 	PINMUX_IPSR_MSEL(IP11_26_24, RX1_C, SEL_SCIF1_2),
 	PINMUX_IPSR_MSEL(IP11_26_24, IIC2_SDA_B, SEL_IIC2_1),
 	PINMUX_IPSR_MSEL(IP11_26_24, I2C2_SDA_B, SEL_I2C2_1),
-	PINMUX_IPSR_DATA(IP11_29_27, MLB_DAT),
+	PINMUX_IPSR_GPSR(IP11_29_27, MLB_DAT),
 	PINMUX_IPSR_MSEL(IP11_29_27, SCIFB1_TXD_D, SEL_SCIFB1_3),
 	PINMUX_IPSR_MSEL(IP11_29_27, TX1_C, SEL_SCIF1_2),
 	PINMUX_IPSR_MSEL(IP11_29_27, BPFCLK_C, SEL_FM_2),
-	PINMUX_IPSR_DATA(IP11_31_30, SSI_SCK0129),
+	PINMUX_IPSR_GPSR(IP11_31_30, SSI_SCK0129),
 	PINMUX_IPSR_MSEL(IP11_31_30, CAN_CLK_B, SEL_CANCLK_1),
-	PINMUX_IPSR_DATA(IP11_31_30, MOUT0),
+	PINMUX_IPSR_GPSR(IP11_31_30, MOUT0),
 
-	PINMUX_IPSR_DATA(IP12_1_0, SSI_WS0129),
+	PINMUX_IPSR_GPSR(IP12_1_0, SSI_WS0129),
 	PINMUX_IPSR_MSEL(IP12_1_0, CAN0_TX_B, SEL_CAN0_1),
-	PINMUX_IPSR_DATA(IP12_1_0, MOUT1),
-	PINMUX_IPSR_DATA(IP12_3_2, SSI_SDATA0),
+	PINMUX_IPSR_GPSR(IP12_1_0, MOUT1),
+	PINMUX_IPSR_GPSR(IP12_3_2, SSI_SDATA0),
 	PINMUX_IPSR_MSEL(IP12_3_2, CAN0_RX_B, SEL_CAN0_1),
-	PINMUX_IPSR_DATA(IP12_3_2, MOUT2),
-	PINMUX_IPSR_DATA(IP12_5_4, SSI_SDATA1),
+	PINMUX_IPSR_GPSR(IP12_3_2, MOUT2),
+	PINMUX_IPSR_GPSR(IP12_5_4, SSI_SDATA1),
 	PINMUX_IPSR_MSEL(IP12_5_4, CAN1_TX_B, SEL_CAN1_1),
-	PINMUX_IPSR_DATA(IP12_5_4, MOUT5),
-	PINMUX_IPSR_DATA(IP12_7_6, SSI_SDATA2),
+	PINMUX_IPSR_GPSR(IP12_5_4, MOUT5),
+	PINMUX_IPSR_GPSR(IP12_7_6, SSI_SDATA2),
 	PINMUX_IPSR_MSEL(IP12_7_6, CAN1_RX_B, SEL_CAN1_1),
-	PINMUX_IPSR_DATA(IP12_7_6, SSI_SCK1),
-	PINMUX_IPSR_DATA(IP12_7_6, MOUT6),
-	PINMUX_IPSR_DATA(IP12_10_8, SSI_SCK34),
-	PINMUX_IPSR_DATA(IP12_10_8, STP_OPWM_0),
+	PINMUX_IPSR_GPSR(IP12_7_6, SSI_SCK1),
+	PINMUX_IPSR_GPSR(IP12_7_6, MOUT6),
+	PINMUX_IPSR_GPSR(IP12_10_8, SSI_SCK34),
+	PINMUX_IPSR_GPSR(IP12_10_8, STP_OPWM_0),
 	PINMUX_IPSR_MSEL(IP12_10_8, SCIFB0_SCK, SEL_SCIFB_0),
 	PINMUX_IPSR_MSEL(IP12_10_8, MSIOF1_SCK, SEL_SOF1_0),
-	PINMUX_IPSR_DATA(IP12_10_8, CAN_DEBUG_HW_TRIGGER),
-	PINMUX_IPSR_DATA(IP12_13_11, SSI_WS34),
+	PINMUX_IPSR_GPSR(IP12_10_8, CAN_DEBUG_HW_TRIGGER),
+	PINMUX_IPSR_GPSR(IP12_13_11, SSI_WS34),
 	PINMUX_IPSR_MSEL(IP12_13_11, STP_IVCXO27_0, SEL_SSP_0),
 	PINMUX_IPSR_MSEL(IP12_13_11, SCIFB0_RXD, SEL_SCIFB_0),
-	PINMUX_IPSR_DATA(IP12_13_11, MSIOF1_SYNC),
-	PINMUX_IPSR_DATA(IP12_13_11, CAN_STEP0),
-	PINMUX_IPSR_DATA(IP12_16_14, SSI_SDATA3),
+	PINMUX_IPSR_GPSR(IP12_13_11, MSIOF1_SYNC),
+	PINMUX_IPSR_GPSR(IP12_13_11, CAN_STEP0),
+	PINMUX_IPSR_GPSR(IP12_16_14, SSI_SDATA3),
 	PINMUX_IPSR_MSEL(IP12_16_14, STP_ISCLK_0, SEL_SSP_0),
 	PINMUX_IPSR_MSEL(IP12_16_14, SCIFB0_TXD, SEL_SCIFB_0),
 	PINMUX_IPSR_MSEL(IP12_16_14, MSIOF1_SS1, SEL_SOF1_0),
-	PINMUX_IPSR_DATA(IP12_16_14, CAN_TXCLK),
-	PINMUX_IPSR_DATA(IP12_19_17, SSI_SCK4),
+	PINMUX_IPSR_GPSR(IP12_16_14, CAN_TXCLK),
+	PINMUX_IPSR_GPSR(IP12_19_17, SSI_SCK4),
 	PINMUX_IPSR_MSEL(IP12_19_17, STP_ISD_0, SEL_SSP_0),
 	PINMUX_IPSR_MSEL(IP12_19_17, SCIFB0_CTS_N, SEL_SCIFB_0),
 	PINMUX_IPSR_MSEL(IP12_19_17, MSIOF1_SS2, SEL_SOF1_0),
 	PINMUX_IPSR_MSEL(IP12_19_17, SSI_SCK5_C, SEL_SSI5_2),
-	PINMUX_IPSR_DATA(IP12_19_17, CAN_DEBUGOUT0),
-	PINMUX_IPSR_DATA(IP12_22_20, SSI_WS4),
+	PINMUX_IPSR_GPSR(IP12_19_17, CAN_DEBUGOUT0),
+	PINMUX_IPSR_GPSR(IP12_22_20, SSI_WS4),
 	PINMUX_IPSR_MSEL(IP12_22_20, STP_ISEN_0, SEL_SSP_0),
 	PINMUX_IPSR_MSEL(IP12_22_20, SCIFB0_RTS_N, SEL_SCIFB_0),
 	PINMUX_IPSR_MSEL(IP12_22_20, MSIOF1_TXD, SEL_SOF1_0),
 	PINMUX_IPSR_MSEL(IP12_22_20, SSI_WS5_C, SEL_SSI5_2),
-	PINMUX_IPSR_DATA(IP12_22_20, CAN_DEBUGOUT1),
-	PINMUX_IPSR_DATA(IP12_24_23, SSI_SDATA4),
+	PINMUX_IPSR_GPSR(IP12_22_20, CAN_DEBUGOUT1),
+	PINMUX_IPSR_GPSR(IP12_24_23, SSI_SDATA4),
 	PINMUX_IPSR_MSEL(IP12_24_23, STP_ISSYNC_0, SEL_SSP_0),
 	PINMUX_IPSR_MSEL(IP12_24_23, MSIOF1_RXD, SEL_SOF1_0),
-	PINMUX_IPSR_DATA(IP12_24_23, CAN_DEBUGOUT2),
+	PINMUX_IPSR_GPSR(IP12_24_23, CAN_DEBUGOUT2),
 	PINMUX_IPSR_MSEL(IP12_27_25, SSI_SCK5, SEL_SSI5_0),
 	PINMUX_IPSR_MSEL(IP12_27_25, SCIFB1_SCK, SEL_SCIFB1_0),
 	PINMUX_IPSR_MSEL(IP12_27_25, IERX_B, SEL_IEB_1),
-	PINMUX_IPSR_DATA(IP12_27_25, DU2_EXHSYNC_DU2_HSYNC),
-	PINMUX_IPSR_DATA(IP12_27_25, QSTH_QHS),
-	PINMUX_IPSR_DATA(IP12_27_25, CAN_DEBUGOUT3),
+	PINMUX_IPSR_GPSR(IP12_27_25, DU2_EXHSYNC_DU2_HSYNC),
+	PINMUX_IPSR_GPSR(IP12_27_25, QSTH_QHS),
+	PINMUX_IPSR_GPSR(IP12_27_25, CAN_DEBUGOUT3),
 	PINMUX_IPSR_MSEL(IP12_30_28, SSI_WS5, SEL_SSI5_0),
 	PINMUX_IPSR_MSEL(IP12_30_28, SCIFB1_RXD, SEL_SCIFB1_0),
 	PINMUX_IPSR_MSEL(IP12_30_28, IECLK_B, SEL_IEB_1),
-	PINMUX_IPSR_DATA(IP12_30_28, DU2_EXVSYNC_DU2_VSYNC),
-	PINMUX_IPSR_DATA(IP12_30_28, QSTB_QHE),
-	PINMUX_IPSR_DATA(IP12_30_28, CAN_DEBUGOUT4),
+	PINMUX_IPSR_GPSR(IP12_30_28, DU2_EXVSYNC_DU2_VSYNC),
+	PINMUX_IPSR_GPSR(IP12_30_28, QSTB_QHE),
+	PINMUX_IPSR_GPSR(IP12_30_28, CAN_DEBUGOUT4),
 
 	PINMUX_IPSR_MSEL(IP13_2_0, SSI_SDATA5, SEL_SSI5_0),
 	PINMUX_IPSR_MSEL(IP13_2_0, SCIFB1_TXD, SEL_SCIFB1_0),
 	PINMUX_IPSR_MSEL(IP13_2_0, IETX_B, SEL_IEB_1),
-	PINMUX_IPSR_DATA(IP13_2_0, DU2_DR2),
-	PINMUX_IPSR_DATA(IP13_2_0, LCDOUT2),
-	PINMUX_IPSR_DATA(IP13_2_0, CAN_DEBUGOUT5),
+	PINMUX_IPSR_GPSR(IP13_2_0, DU2_DR2),
+	PINMUX_IPSR_GPSR(IP13_2_0, LCDOUT2),
+	PINMUX_IPSR_GPSR(IP13_2_0, CAN_DEBUGOUT5),
 	PINMUX_IPSR_MSEL(IP13_6_3, SSI_SCK6, SEL_SSI6_0),
 	PINMUX_IPSR_MSEL(IP13_6_3, SCIFB1_CTS_N, SEL_SCIFB1_0),
 	PINMUX_IPSR_MSEL(IP13_6_3, BPFCLK_D, SEL_FM_3),
-	PINMUX_IPSR_DATA(IP13_6_3, DU2_DR3),
-	PINMUX_IPSR_DATA(IP13_6_3, LCDOUT3),
-	PINMUX_IPSR_DATA(IP13_6_3, CAN_DEBUGOUT6),
+	PINMUX_IPSR_GPSR(IP13_6_3, DU2_DR3),
+	PINMUX_IPSR_GPSR(IP13_6_3, LCDOUT3),
+	PINMUX_IPSR_GPSR(IP13_6_3, CAN_DEBUGOUT6),
 	PINMUX_IPSR_MSEL(IP13_6_3, BPFCLK_F, SEL_FM_5),
 	PINMUX_IPSR_MSEL(IP13_9_7, SSI_WS6, SEL_SSI6_0),
 	PINMUX_IPSR_MSEL(IP13_9_7, SCIFB1_RTS_N, SEL_SCIFB1_0),
 	PINMUX_IPSR_MSEL(IP13_9_7, CAN0_TX_D, SEL_CAN0_3),
-	PINMUX_IPSR_DATA(IP13_9_7, DU2_DR4),
-	PINMUX_IPSR_DATA(IP13_9_7, LCDOUT4),
-	PINMUX_IPSR_DATA(IP13_9_7, CAN_DEBUGOUT7),
+	PINMUX_IPSR_GPSR(IP13_9_7, DU2_DR4),
+	PINMUX_IPSR_GPSR(IP13_9_7, LCDOUT4),
+	PINMUX_IPSR_GPSR(IP13_9_7, CAN_DEBUGOUT7),
 	PINMUX_IPSR_MSEL(IP13_12_10, SSI_SDATA6, SEL_SSI6_0),
 	PINMUX_IPSR_MSEL(IP13_12_10, FMIN_D, SEL_FM_3),
-	PINMUX_IPSR_DATA(IP13_12_10, DU2_DR5),
-	PINMUX_IPSR_DATA(IP13_12_10, LCDOUT5),
-	PINMUX_IPSR_DATA(IP13_12_10, CAN_DEBUGOUT8),
+	PINMUX_IPSR_GPSR(IP13_12_10, DU2_DR5),
+	PINMUX_IPSR_GPSR(IP13_12_10, LCDOUT5),
+	PINMUX_IPSR_GPSR(IP13_12_10, CAN_DEBUGOUT8),
 	PINMUX_IPSR_MSEL(IP13_15_13, SSI_SCK78, SEL_SSI7_0),
 	PINMUX_IPSR_MSEL(IP13_15_13, STP_IVCXO27_1, SEL_SSP_0),
 	PINMUX_IPSR_MSEL(IP13_15_13, SCK1, SEL_SCIF1_0),
 	PINMUX_IPSR_MSEL(IP13_15_13, SCIFA1_SCK, SEL_SCIFA1_0),
-	PINMUX_IPSR_DATA(IP13_15_13, DU2_DR6),
-	PINMUX_IPSR_DATA(IP13_15_13, LCDOUT6),
-	PINMUX_IPSR_DATA(IP13_15_13, CAN_DEBUGOUT9),
+	PINMUX_IPSR_GPSR(IP13_15_13, DU2_DR6),
+	PINMUX_IPSR_GPSR(IP13_15_13, LCDOUT6),
+	PINMUX_IPSR_GPSR(IP13_15_13, CAN_DEBUGOUT9),
 	PINMUX_IPSR_MSEL(IP13_18_16, SSI_WS78, SEL_SSI7_0),
 	PINMUX_IPSR_MSEL(IP13_18_16, STP_ISCLK_1, SEL_SSP_0),
 	PINMUX_IPSR_MSEL(IP13_18_16, SCIFB2_SCK, SEL_SCIFB2_0),
-	PINMUX_IPSR_DATA(IP13_18_16, SCIFA2_CTS_N),
-	PINMUX_IPSR_DATA(IP13_18_16, DU2_DR7),
-	PINMUX_IPSR_DATA(IP13_18_16, LCDOUT7),
-	PINMUX_IPSR_DATA(IP13_18_16, CAN_DEBUGOUT10),
+	PINMUX_IPSR_GPSR(IP13_18_16, SCIFA2_CTS_N),
+	PINMUX_IPSR_GPSR(IP13_18_16, DU2_DR7),
+	PINMUX_IPSR_GPSR(IP13_18_16, LCDOUT7),
+	PINMUX_IPSR_GPSR(IP13_18_16, CAN_DEBUGOUT10),
 	PINMUX_IPSR_MSEL(IP13_22_19, SSI_SDATA7, SEL_SSI7_0),
 	PINMUX_IPSR_MSEL(IP13_22_19, STP_ISD_1, SEL_SSP_0),
 	PINMUX_IPSR_MSEL(IP13_22_19, SCIFB2_RXD, SEL_SCIFB2_0),
-	PINMUX_IPSR_DATA(IP13_22_19, SCIFA2_RTS_N),
-	PINMUX_IPSR_DATA(IP13_22_19, TCLK2),
-	PINMUX_IPSR_DATA(IP13_22_19, QSTVA_QVS),
-	PINMUX_IPSR_DATA(IP13_22_19, CAN_DEBUGOUT11),
+	PINMUX_IPSR_GPSR(IP13_22_19, SCIFA2_RTS_N),
+	PINMUX_IPSR_GPSR(IP13_22_19, TCLK2),
+	PINMUX_IPSR_GPSR(IP13_22_19, QSTVA_QVS),
+	PINMUX_IPSR_GPSR(IP13_22_19, CAN_DEBUGOUT11),
 	PINMUX_IPSR_MSEL(IP13_22_19, BPFCLK_E, SEL_FM_4),
 	PINMUX_IPSR_MSEL(IP13_22_19, SSI_SDATA7_B, SEL_SSI7_1),
 	PINMUX_IPSR_MSEL(IP13_22_19, FMIN_G, SEL_FM_6),
@@ -1565,161 +1565,161 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP13_25_23, STP_ISEN_1, SEL_SSP_0),
 	PINMUX_IPSR_MSEL(IP13_25_23, SCIFB2_TXD, SEL_SCIFB2_0),
 	PINMUX_IPSR_MSEL(IP13_25_23, CAN0_TX_C, SEL_CAN0_2),
-	PINMUX_IPSR_DATA(IP13_25_23, CAN_DEBUGOUT12),
+	PINMUX_IPSR_GPSR(IP13_25_23, CAN_DEBUGOUT12),
 	PINMUX_IPSR_MSEL(IP13_25_23, SSI_SDATA8_B, SEL_SSI8_1),
-	PINMUX_IPSR_DATA(IP13_28_26, SSI_SDATA9),
+	PINMUX_IPSR_GPSR(IP13_28_26, SSI_SDATA9),
 	PINMUX_IPSR_MSEL(IP13_28_26, STP_ISSYNC_1, SEL_SSP_0),
 	PINMUX_IPSR_MSEL(IP13_28_26, SCIFB2_CTS_N, SEL_SCIFB2_0),
-	PINMUX_IPSR_DATA(IP13_28_26, SSI_WS1),
+	PINMUX_IPSR_GPSR(IP13_28_26, SSI_WS1),
 	PINMUX_IPSR_MSEL(IP13_28_26, SSI_SDATA5_C, SEL_SSI5_2),
-	PINMUX_IPSR_DATA(IP13_28_26, CAN_DEBUGOUT13),
-	PINMUX_IPSR_DATA(IP13_30_29, AUDIO_CLKA),
+	PINMUX_IPSR_GPSR(IP13_28_26, CAN_DEBUGOUT13),
+	PINMUX_IPSR_GPSR(IP13_30_29, AUDIO_CLKA),
 	PINMUX_IPSR_MSEL(IP13_30_29, SCIFB2_RTS_N, SEL_SCIFB2_0),
-	PINMUX_IPSR_DATA(IP13_30_29, CAN_DEBUGOUT14),
+	PINMUX_IPSR_GPSR(IP13_30_29, CAN_DEBUGOUT14),
 
-	PINMUX_IPSR_DATA(IP14_2_0, AUDIO_CLKB),
+	PINMUX_IPSR_GPSR(IP14_2_0, AUDIO_CLKB),
 	PINMUX_IPSR_MSEL(IP14_2_0, SCIF_CLK, SEL_SCIFCLK_0),
 	PINMUX_IPSR_MSEL(IP14_2_0, CAN0_RX_D, SEL_CAN0_3),
-	PINMUX_IPSR_DATA(IP14_2_0, DVC_MUTE),
+	PINMUX_IPSR_GPSR(IP14_2_0, DVC_MUTE),
 	PINMUX_IPSR_MSEL(IP14_2_0, CAN0_RX_C, SEL_CAN0_2),
-	PINMUX_IPSR_DATA(IP14_2_0, CAN_DEBUGOUT15),
-	PINMUX_IPSR_DATA(IP14_2_0, REMOCON),
+	PINMUX_IPSR_GPSR(IP14_2_0, CAN_DEBUGOUT15),
+	PINMUX_IPSR_GPSR(IP14_2_0, REMOCON),
 	PINMUX_IPSR_MSEL(IP14_5_3, SCIFA0_SCK, SEL_SCFA_0),
 	PINMUX_IPSR_MSEL(IP14_5_3, HSCK1, SEL_HSCIF1_0),
-	PINMUX_IPSR_DATA(IP14_5_3, SCK0),
-	PINMUX_IPSR_DATA(IP14_5_3, MSIOF3_SS2),
-	PINMUX_IPSR_DATA(IP14_5_3, DU2_DG2),
-	PINMUX_IPSR_DATA(IP14_5_3, LCDOUT10),
+	PINMUX_IPSR_GPSR(IP14_5_3, SCK0),
+	PINMUX_IPSR_GPSR(IP14_5_3, MSIOF3_SS2),
+	PINMUX_IPSR_GPSR(IP14_5_3, DU2_DG2),
+	PINMUX_IPSR_GPSR(IP14_5_3, LCDOUT10),
 	PINMUX_IPSR_MSEL(IP14_5_3, IIC1_SDA_C, SEL_IIC1_2),
 	PINMUX_IPSR_MSEL(IP14_5_3, I2C1_SDA_C, SEL_I2C1_2),
 	PINMUX_IPSR_MSEL(IP14_8_6, SCIFA0_RXD, SEL_SCFA_0),
 	PINMUX_IPSR_MSEL(IP14_8_6, HRX1, SEL_HSCIF1_0),
 	PINMUX_IPSR_MSEL(IP14_8_6, RX0, SEL_SCIF0_0),
-	PINMUX_IPSR_DATA(IP14_8_6, DU2_DR0),
-	PINMUX_IPSR_DATA(IP14_8_6, LCDOUT0),
+	PINMUX_IPSR_GPSR(IP14_8_6, DU2_DR0),
+	PINMUX_IPSR_GPSR(IP14_8_6, LCDOUT0),
 	PINMUX_IPSR_MSEL(IP14_11_9, SCIFA0_TXD, SEL_SCFA_0),
 	PINMUX_IPSR_MSEL(IP14_11_9, HTX1, SEL_HSCIF1_0),
 	PINMUX_IPSR_MSEL(IP14_11_9, TX0, SEL_SCIF0_0),
-	PINMUX_IPSR_DATA(IP14_11_9, DU2_DR1),
-	PINMUX_IPSR_DATA(IP14_11_9, LCDOUT1),
+	PINMUX_IPSR_GPSR(IP14_11_9, DU2_DR1),
+	PINMUX_IPSR_GPSR(IP14_11_9, LCDOUT1),
 	PINMUX_IPSR_MSEL(IP14_15_12, SCIFA0_CTS_N, SEL_SCFA_0),
 	PINMUX_IPSR_MSEL(IP14_15_12, HCTS1_N, SEL_HSCIF1_0),
-	PINMUX_IPSR_DATA(IP14_15_12, CTS0_N),
+	PINMUX_IPSR_GPSR(IP14_15_12, CTS0_N),
 	PINMUX_IPSR_MSEL(IP14_15_12, MSIOF3_SYNC, SEL_SOF3_0),
-	PINMUX_IPSR_DATA(IP14_15_12, DU2_DG3),
-	PINMUX_IPSR_DATA(IP14_15_12, LCDOUT11),
-	PINMUX_IPSR_DATA(IP14_15_12, PWM0_B),
+	PINMUX_IPSR_GPSR(IP14_15_12, DU2_DG3),
+	PINMUX_IPSR_GPSR(IP14_15_12, LCDOUT11),
+	PINMUX_IPSR_GPSR(IP14_15_12, PWM0_B),
 	PINMUX_IPSR_MSEL(IP14_15_12, IIC1_SCL_C, SEL_IIC1_2),
 	PINMUX_IPSR_MSEL(IP14_15_12, I2C1_SCL_C, SEL_I2C1_2),
 	PINMUX_IPSR_MSEL(IP14_18_16, SCIFA0_RTS_N, SEL_SCFA_0),
 	PINMUX_IPSR_MSEL(IP14_18_16, HRTS1_N, SEL_HSCIF1_0),
-	PINMUX_IPSR_DATA(IP14_18_16, RTS0_N),
-	PINMUX_IPSR_DATA(IP14_18_16, MSIOF3_SS1),
-	PINMUX_IPSR_DATA(IP14_18_16, DU2_DG0),
-	PINMUX_IPSR_DATA(IP14_18_16, LCDOUT8),
-	PINMUX_IPSR_DATA(IP14_18_16, PWM1_B),
+	PINMUX_IPSR_GPSR(IP14_18_16, RTS0_N),
+	PINMUX_IPSR_GPSR(IP14_18_16, MSIOF3_SS1),
+	PINMUX_IPSR_GPSR(IP14_18_16, DU2_DG0),
+	PINMUX_IPSR_GPSR(IP14_18_16, LCDOUT8),
+	PINMUX_IPSR_GPSR(IP14_18_16, PWM1_B),
 	PINMUX_IPSR_MSEL(IP14_21_19, SCIFA1_RXD, SEL_SCIFA1_0),
 	PINMUX_IPSR_MSEL(IP14_21_19, AD_DI, SEL_ADI_0),
 	PINMUX_IPSR_MSEL(IP14_21_19, RX1, SEL_SCIF1_0),
-	PINMUX_IPSR_DATA(IP14_21_19, DU2_EXODDF_DU2_ODDF_DISP_CDE),
-	PINMUX_IPSR_DATA(IP14_21_19, QCPV_QDE),
+	PINMUX_IPSR_GPSR(IP14_21_19, DU2_EXODDF_DU2_ODDF_DISP_CDE),
+	PINMUX_IPSR_GPSR(IP14_21_19, QCPV_QDE),
 	PINMUX_IPSR_MSEL(IP14_24_22, SCIFA1_TXD, SEL_SCIFA1_0),
 	PINMUX_IPSR_MSEL(IP14_24_22, AD_DO, SEL_ADI_0),
 	PINMUX_IPSR_MSEL(IP14_24_22, TX1, SEL_SCIF1_0),
-	PINMUX_IPSR_DATA(IP14_24_22, DU2_DG1),
-	PINMUX_IPSR_DATA(IP14_24_22, LCDOUT9),
+	PINMUX_IPSR_GPSR(IP14_24_22, DU2_DG1),
+	PINMUX_IPSR_GPSR(IP14_24_22, LCDOUT9),
 	PINMUX_IPSR_MSEL(IP14_27_25, SCIFA1_CTS_N, SEL_SCIFA1_0),
 	PINMUX_IPSR_MSEL(IP14_27_25, AD_CLK, SEL_ADI_0),
-	PINMUX_IPSR_DATA(IP14_27_25, CTS1_N),
+	PINMUX_IPSR_GPSR(IP14_27_25, CTS1_N),
 	PINMUX_IPSR_MSEL(IP14_27_25, MSIOF3_RXD, SEL_SOF3_0),
-	PINMUX_IPSR_DATA(IP14_27_25, DU0_DOTCLKOUT),
-	PINMUX_IPSR_DATA(IP14_27_25, QCLK),
+	PINMUX_IPSR_GPSR(IP14_27_25, DU0_DOTCLKOUT),
+	PINMUX_IPSR_GPSR(IP14_27_25, QCLK),
 	PINMUX_IPSR_MSEL(IP14_30_28, SCIFA1_RTS_N, SEL_SCIFA1_0),
 	PINMUX_IPSR_MSEL(IP14_30_28, AD_NCS_N, SEL_ADI_0),
-	PINMUX_IPSR_DATA(IP14_30_28, RTS1_N),
+	PINMUX_IPSR_GPSR(IP14_30_28, RTS1_N),
 	PINMUX_IPSR_MSEL(IP14_30_28, MSIOF3_TXD, SEL_SOF3_0),
-	PINMUX_IPSR_DATA(IP14_30_28, DU1_DOTCLKOUT),
-	PINMUX_IPSR_DATA(IP14_30_28, QSTVB_QVE),
+	PINMUX_IPSR_GPSR(IP14_30_28, DU1_DOTCLKOUT),
+	PINMUX_IPSR_GPSR(IP14_30_28, QSTVB_QVE),
 	PINMUX_IPSR_MSEL(IP14_30_28, HRTS0_N_C, SEL_HSCIF0_2),
 
 	PINMUX_IPSR_MSEL(IP15_2_0, SCIFA2_SCK, SEL_SCIFA2_0),
 	PINMUX_IPSR_MSEL(IP15_2_0, FMCLK, SEL_FM_0),
-	PINMUX_IPSR_DATA(IP15_2_0, SCK2),
+	PINMUX_IPSR_GPSR(IP15_2_0, SCK2),
 	PINMUX_IPSR_MSEL(IP15_2_0, MSIOF3_SCK, SEL_SOF3_0),
-	PINMUX_IPSR_DATA(IP15_2_0, DU2_DG7),
-	PINMUX_IPSR_DATA(IP15_2_0, LCDOUT15),
+	PINMUX_IPSR_GPSR(IP15_2_0, DU2_DG7),
+	PINMUX_IPSR_GPSR(IP15_2_0, LCDOUT15),
 	PINMUX_IPSR_MSEL(IP15_2_0, SCIF_CLK_B, SEL_SCIFCLK_1),
 	PINMUX_IPSR_MSEL(IP15_5_3, SCIFA2_RXD, SEL_SCIFA2_0),
 	PINMUX_IPSR_MSEL(IP15_5_3, FMIN, SEL_FM_0),
 	PINMUX_IPSR_MSEL(IP15_5_3, TX2, SEL_SCIF2_0),
-	PINMUX_IPSR_DATA(IP15_5_3, DU2_DB0),
-	PINMUX_IPSR_DATA(IP15_5_3, LCDOUT16),
+	PINMUX_IPSR_GPSR(IP15_5_3, DU2_DB0),
+	PINMUX_IPSR_GPSR(IP15_5_3, LCDOUT16),
 	PINMUX_IPSR_MSEL(IP15_5_3, IIC2_SCL, SEL_IIC2_0),
 	PINMUX_IPSR_MSEL(IP15_5_3, I2C2_SCL, SEL_I2C2_0),
 	PINMUX_IPSR_MSEL(IP15_8_6, SCIFA2_TXD, SEL_SCIFA2_0),
 	PINMUX_IPSR_MSEL(IP15_8_6, BPFCLK, SEL_FM_0),
 	PINMUX_IPSR_MSEL(IP15_8_6, RX2, SEL_SCIF2_0),
-	PINMUX_IPSR_DATA(IP15_8_6, DU2_DB1),
-	PINMUX_IPSR_DATA(IP15_8_6, LCDOUT17),
+	PINMUX_IPSR_GPSR(IP15_8_6, DU2_DB1),
+	PINMUX_IPSR_GPSR(IP15_8_6, LCDOUT17),
 	PINMUX_IPSR_MSEL(IP15_8_6, IIC2_SDA, SEL_IIC2_0),
 	PINMUX_IPSR_MSEL(IP15_8_6, I2C2_SDA, SEL_I2C2_0),
-	PINMUX_IPSR_DATA(IP15_11_9, HSCK0),
+	PINMUX_IPSR_GPSR(IP15_11_9, HSCK0),
 	PINMUX_IPSR_MSEL(IP15_11_9, TS_SDEN0, SEL_TSIF0_0),
-	PINMUX_IPSR_DATA(IP15_11_9, DU2_DG4),
-	PINMUX_IPSR_DATA(IP15_11_9, LCDOUT12),
+	PINMUX_IPSR_GPSR(IP15_11_9, DU2_DG4),
+	PINMUX_IPSR_GPSR(IP15_11_9, LCDOUT12),
 	PINMUX_IPSR_MSEL(IP15_11_9, HCTS0_N_C, SEL_HSCIF0_2),
 	PINMUX_IPSR_MSEL(IP15_13_12, HRX0, SEL_HSCIF0_0),
-	PINMUX_IPSR_DATA(IP15_13_12, DU2_DB2),
-	PINMUX_IPSR_DATA(IP15_13_12, LCDOUT18),
+	PINMUX_IPSR_GPSR(IP15_13_12, DU2_DB2),
+	PINMUX_IPSR_GPSR(IP15_13_12, LCDOUT18),
 	PINMUX_IPSR_MSEL(IP15_15_14, HTX0, SEL_HSCIF0_0),
-	PINMUX_IPSR_DATA(IP15_15_14, DU2_DB3),
-	PINMUX_IPSR_DATA(IP15_15_14, LCDOUT19),
+	PINMUX_IPSR_GPSR(IP15_15_14, DU2_DB3),
+	PINMUX_IPSR_GPSR(IP15_15_14, LCDOUT19),
 	PINMUX_IPSR_MSEL(IP15_17_16, HCTS0_N, SEL_HSCIF0_0),
-	PINMUX_IPSR_DATA(IP15_17_16, SSI_SCK9),
-	PINMUX_IPSR_DATA(IP15_17_16, DU2_DB4),
-	PINMUX_IPSR_DATA(IP15_17_16, LCDOUT20),
+	PINMUX_IPSR_GPSR(IP15_17_16, SSI_SCK9),
+	PINMUX_IPSR_GPSR(IP15_17_16, DU2_DB4),
+	PINMUX_IPSR_GPSR(IP15_17_16, LCDOUT20),
 	PINMUX_IPSR_MSEL(IP15_19_18, HRTS0_N, SEL_HSCIF0_0),
-	PINMUX_IPSR_DATA(IP15_19_18, SSI_WS9),
-	PINMUX_IPSR_DATA(IP15_19_18, DU2_DB5),
-	PINMUX_IPSR_DATA(IP15_19_18, LCDOUT21),
+	PINMUX_IPSR_GPSR(IP15_19_18, SSI_WS9),
+	PINMUX_IPSR_GPSR(IP15_19_18, DU2_DB5),
+	PINMUX_IPSR_GPSR(IP15_19_18, LCDOUT21),
 	PINMUX_IPSR_MSEL(IP15_22_20, MSIOF0_SCK, SEL_SOF0_0),
 	PINMUX_IPSR_MSEL(IP15_22_20, TS_SDAT0, SEL_TSIF0_0),
-	PINMUX_IPSR_DATA(IP15_22_20, ADICLK),
-	PINMUX_IPSR_DATA(IP15_22_20, DU2_DB6),
-	PINMUX_IPSR_DATA(IP15_22_20, LCDOUT22),
-	PINMUX_IPSR_DATA(IP15_25_23, MSIOF0_SYNC),
+	PINMUX_IPSR_GPSR(IP15_22_20, ADICLK),
+	PINMUX_IPSR_GPSR(IP15_22_20, DU2_DB6),
+	PINMUX_IPSR_GPSR(IP15_22_20, LCDOUT22),
+	PINMUX_IPSR_GPSR(IP15_25_23, MSIOF0_SYNC),
 	PINMUX_IPSR_MSEL(IP15_25_23, TS_SCK0, SEL_TSIF0_0),
-	PINMUX_IPSR_DATA(IP15_25_23, SSI_SCK2),
-	PINMUX_IPSR_DATA(IP15_25_23, ADIDATA),
-	PINMUX_IPSR_DATA(IP15_25_23, DU2_DB7),
-	PINMUX_IPSR_DATA(IP15_25_23, LCDOUT23),
+	PINMUX_IPSR_GPSR(IP15_25_23, SSI_SCK2),
+	PINMUX_IPSR_GPSR(IP15_25_23, ADIDATA),
+	PINMUX_IPSR_GPSR(IP15_25_23, DU2_DB7),
+	PINMUX_IPSR_GPSR(IP15_25_23, LCDOUT23),
 	PINMUX_IPSR_MSEL(IP15_25_23, HRX0_C, SEL_SCIFA2_1),
 	PINMUX_IPSR_MSEL(IP15_27_26, MSIOF0_SS1, SEL_SOF0_0),
-	PINMUX_IPSR_DATA(IP15_27_26, ADICHS0),
-	PINMUX_IPSR_DATA(IP15_27_26, DU2_DG5),
-	PINMUX_IPSR_DATA(IP15_27_26, LCDOUT13),
+	PINMUX_IPSR_GPSR(IP15_27_26, ADICHS0),
+	PINMUX_IPSR_GPSR(IP15_27_26, DU2_DG5),
+	PINMUX_IPSR_GPSR(IP15_27_26, LCDOUT13),
 	PINMUX_IPSR_MSEL(IP15_29_28, MSIOF0_TXD, SEL_SOF0_0),
-	PINMUX_IPSR_DATA(IP15_29_28, ADICHS1),
-	PINMUX_IPSR_DATA(IP15_29_28, DU2_DG6),
-	PINMUX_IPSR_DATA(IP15_29_28, LCDOUT14),
+	PINMUX_IPSR_GPSR(IP15_29_28, ADICHS1),
+	PINMUX_IPSR_GPSR(IP15_29_28, DU2_DG6),
+	PINMUX_IPSR_GPSR(IP15_29_28, LCDOUT14),
 
 	PINMUX_IPSR_MSEL(IP16_2_0, MSIOF0_SS2, SEL_SOF0_0),
-	PINMUX_IPSR_DATA(IP16_2_0, AUDIO_CLKOUT),
-	PINMUX_IPSR_DATA(IP16_2_0, ADICHS2),
-	PINMUX_IPSR_DATA(IP16_2_0, DU2_DISP),
-	PINMUX_IPSR_DATA(IP16_2_0, QPOLA),
+	PINMUX_IPSR_GPSR(IP16_2_0, AUDIO_CLKOUT),
+	PINMUX_IPSR_GPSR(IP16_2_0, ADICHS2),
+	PINMUX_IPSR_GPSR(IP16_2_0, DU2_DISP),
+	PINMUX_IPSR_GPSR(IP16_2_0, QPOLA),
 	PINMUX_IPSR_MSEL(IP16_2_0, HTX0_C, SEL_HSCIF0_2),
 	PINMUX_IPSR_MSEL(IP16_2_0, SCIFA2_TXD_B, SEL_SCIFA2_1),
 	PINMUX_IPSR_MSEL(IP16_5_3, MSIOF0_RXD, SEL_SOF0_0),
 	PINMUX_IPSR_MSEL(IP16_5_3, TS_SPSYNC0, SEL_TSIF0_0),
-	PINMUX_IPSR_DATA(IP16_5_3, SSI_WS2),
-	PINMUX_IPSR_DATA(IP16_5_3, ADICS_SAMP),
-	PINMUX_IPSR_DATA(IP16_5_3, DU2_CDE),
-	PINMUX_IPSR_DATA(IP16_5_3, QPOLB),
+	PINMUX_IPSR_GPSR(IP16_5_3, SSI_WS2),
+	PINMUX_IPSR_GPSR(IP16_5_3, ADICS_SAMP),
+	PINMUX_IPSR_GPSR(IP16_5_3, DU2_CDE),
+	PINMUX_IPSR_GPSR(IP16_5_3, QPOLB),
 	PINMUX_IPSR_MSEL(IP16_5_3, SCIFA2_RXD_B, SEL_HSCIF0_2),
-	PINMUX_IPSR_DATA(IP16_6, USB1_PWEN),
-	PINMUX_IPSR_DATA(IP16_6, AUDIO_CLKOUT_D),
-	PINMUX_IPSR_DATA(IP16_7, USB1_OVC),
+	PINMUX_IPSR_GPSR(IP16_6, USB1_PWEN),
+	PINMUX_IPSR_GPSR(IP16_6, AUDIO_CLKOUT_D),
+	PINMUX_IPSR_GPSR(IP16_7, USB1_OVC),
 	PINMUX_IPSR_MSEL(IP16_7, TCLK1_B, SEL_TMU1_1),
 
 	PINMUX_DATA(IIC0_SCL_MARK, FN_SEL_IIC0_0),
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
index 4cfbb94ad5d0..01abbd5b4e49 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
@@ -792,171 +792,171 @@ static const u16 pinmux_data[] = {
 	PINMUX_SINGLE(SD1_CLK),
 
 	/* IPSR0 */
-	PINMUX_IPSR_DATA(IP0_0, D0),
-	PINMUX_IPSR_DATA(IP0_1, D1),
-	PINMUX_IPSR_DATA(IP0_2, D2),
-	PINMUX_IPSR_DATA(IP0_3, D3),
-	PINMUX_IPSR_DATA(IP0_4, D4),
-	PINMUX_IPSR_DATA(IP0_5, D5),
-	PINMUX_IPSR_DATA(IP0_6, D6),
-	PINMUX_IPSR_DATA(IP0_7, D7),
-	PINMUX_IPSR_DATA(IP0_8, D8),
-	PINMUX_IPSR_DATA(IP0_9, D9),
-	PINMUX_IPSR_DATA(IP0_10, D10),
-	PINMUX_IPSR_DATA(IP0_11, D11),
-	PINMUX_IPSR_DATA(IP0_12, D12),
-	PINMUX_IPSR_DATA(IP0_13, D13),
-	PINMUX_IPSR_DATA(IP0_14, D14),
-	PINMUX_IPSR_DATA(IP0_15, D15),
-	PINMUX_IPSR_DATA(IP0_18_16, A0),
+	PINMUX_IPSR_GPSR(IP0_0, D0),
+	PINMUX_IPSR_GPSR(IP0_1, D1),
+	PINMUX_IPSR_GPSR(IP0_2, D2),
+	PINMUX_IPSR_GPSR(IP0_3, D3),
+	PINMUX_IPSR_GPSR(IP0_4, D4),
+	PINMUX_IPSR_GPSR(IP0_5, D5),
+	PINMUX_IPSR_GPSR(IP0_6, D6),
+	PINMUX_IPSR_GPSR(IP0_7, D7),
+	PINMUX_IPSR_GPSR(IP0_8, D8),
+	PINMUX_IPSR_GPSR(IP0_9, D9),
+	PINMUX_IPSR_GPSR(IP0_10, D10),
+	PINMUX_IPSR_GPSR(IP0_11, D11),
+	PINMUX_IPSR_GPSR(IP0_12, D12),
+	PINMUX_IPSR_GPSR(IP0_13, D13),
+	PINMUX_IPSR_GPSR(IP0_14, D14),
+	PINMUX_IPSR_GPSR(IP0_15, D15),
+	PINMUX_IPSR_GPSR(IP0_18_16, A0),
 	PINMUX_IPSR_MSEL(IP0_18_16, ATAWR0_N_C, SEL_LBS_2),
 	PINMUX_IPSR_MSEL(IP0_18_16, MSIOF0_SCK_B, SEL_SOF0_1),
 	PINMUX_IPSR_MSEL(IP0_18_16, SCL0_C, SEL_IIC0_2),
-	PINMUX_IPSR_DATA(IP0_18_16, PWM2_B),
-	PINMUX_IPSR_DATA(IP0_20_19, A1),
+	PINMUX_IPSR_GPSR(IP0_18_16, PWM2_B),
+	PINMUX_IPSR_GPSR(IP0_20_19, A1),
 	PINMUX_IPSR_MSEL(IP0_20_19, MSIOF0_SYNC_B, SEL_SOF0_1),
-	PINMUX_IPSR_DATA(IP0_22_21, A2),
+	PINMUX_IPSR_GPSR(IP0_22_21, A2),
 	PINMUX_IPSR_MSEL(IP0_22_21, MSIOF0_SS1_B, SEL_SOF0_1),
-	PINMUX_IPSR_DATA(IP0_24_23, A3),
+	PINMUX_IPSR_GPSR(IP0_24_23, A3),
 	PINMUX_IPSR_MSEL(IP0_24_23, MSIOF0_SS2_B, SEL_SOF0_1),
-	PINMUX_IPSR_DATA(IP0_26_25, A4),
+	PINMUX_IPSR_GPSR(IP0_26_25, A4),
 	PINMUX_IPSR_MSEL(IP0_26_25, MSIOF0_TXD_B, SEL_SOF0_1),
-	PINMUX_IPSR_DATA(IP0_28_27, A5),
+	PINMUX_IPSR_GPSR(IP0_28_27, A5),
 	PINMUX_IPSR_MSEL(IP0_28_27, MSIOF0_RXD_B, SEL_SOF0_1),
-	PINMUX_IPSR_DATA(IP0_30_29, A6),
+	PINMUX_IPSR_GPSR(IP0_30_29, A6),
 	PINMUX_IPSR_MSEL(IP0_30_29, MSIOF1_SCK, SEL_SOF1_0),
 
 	/* IPSR1 */
-	PINMUX_IPSR_DATA(IP1_1_0, A7),
+	PINMUX_IPSR_GPSR(IP1_1_0, A7),
 	PINMUX_IPSR_MSEL(IP1_1_0, MSIOF1_SYNC, SEL_SOF1_0),
-	PINMUX_IPSR_DATA(IP1_3_2, A8),
+	PINMUX_IPSR_GPSR(IP1_3_2, A8),
 	PINMUX_IPSR_MSEL(IP1_3_2, MSIOF1_SS1, SEL_SOF1_0),
 	PINMUX_IPSR_MSEL(IP1_3_2, SCL0, SEL_IIC0_0),
-	PINMUX_IPSR_DATA(IP1_5_4, A9),
+	PINMUX_IPSR_GPSR(IP1_5_4, A9),
 	PINMUX_IPSR_MSEL(IP1_5_4, MSIOF1_SS2, SEL_SOF1_0),
 	PINMUX_IPSR_MSEL(IP1_5_4, SDA0, SEL_IIC0_0),
-	PINMUX_IPSR_DATA(IP1_7_6, A10),
+	PINMUX_IPSR_GPSR(IP1_7_6, A10),
 	PINMUX_IPSR_MSEL(IP1_7_6, MSIOF1_TXD, SEL_SOF1_0),
 	PINMUX_IPSR_MSEL(IP1_7_6, MSIOF1_TXD_D, SEL_SOF1_3),
-	PINMUX_IPSR_DATA(IP1_10_8, A11),
+	PINMUX_IPSR_GPSR(IP1_10_8, A11),
 	PINMUX_IPSR_MSEL(IP1_10_8, MSIOF1_RXD, SEL_SOF1_0),
 	PINMUX_IPSR_MSEL(IP1_10_8, SCL3_D, SEL_IIC3_3),
 	PINMUX_IPSR_MSEL(IP1_10_8, MSIOF1_RXD_D, SEL_SOF1_3),
-	PINMUX_IPSR_DATA(IP1_13_11, A12),
+	PINMUX_IPSR_GPSR(IP1_13_11, A12),
 	PINMUX_IPSR_MSEL(IP1_13_11, FMCLK, SEL_FM_0),
 	PINMUX_IPSR_MSEL(IP1_13_11, SDA3_D, SEL_IIC3_3),
 	PINMUX_IPSR_MSEL(IP1_13_11, MSIOF1_SCK_D, SEL_SOF1_3),
-	PINMUX_IPSR_DATA(IP1_16_14, A13),
+	PINMUX_IPSR_GPSR(IP1_16_14, A13),
 	PINMUX_IPSR_MSEL(IP1_16_14, ATAG0_N_C, SEL_LBS_2),
 	PINMUX_IPSR_MSEL(IP1_16_14, BPFCLK, SEL_FM_0),
 	PINMUX_IPSR_MSEL(IP1_16_14, MSIOF1_SS1_D, SEL_SOF1_3),
-	PINMUX_IPSR_DATA(IP1_19_17, A14),
+	PINMUX_IPSR_GPSR(IP1_19_17, A14),
 	PINMUX_IPSR_MSEL(IP1_19_17, ATADIR0_N_C, SEL_LBS_2),
 	PINMUX_IPSR_MSEL(IP1_19_17, FMIN, SEL_FM_0),
 	PINMUX_IPSR_MSEL(IP1_19_17, FMIN_C, SEL_FM_2),
 	PINMUX_IPSR_MSEL(IP1_19_17, MSIOF1_SYNC_D, SEL_SOF1_3),
-	PINMUX_IPSR_DATA(IP1_22_20, A15),
+	PINMUX_IPSR_GPSR(IP1_22_20, A15),
 	PINMUX_IPSR_MSEL(IP1_22_20, BPFCLK_C, SEL_FM_2),
-	PINMUX_IPSR_DATA(IP1_25_23, A16),
+	PINMUX_IPSR_GPSR(IP1_25_23, A16),
 	PINMUX_IPSR_MSEL(IP1_25_23, DREQ2_B, SEL_LBS_1),
 	PINMUX_IPSR_MSEL(IP1_25_23, FMCLK_C, SEL_FM_2),
 	PINMUX_IPSR_MSEL(IP1_25_23, SCIFA1_SCK_B, SEL_SCIFA1_1),
-	PINMUX_IPSR_DATA(IP1_28_26, A17),
+	PINMUX_IPSR_GPSR(IP1_28_26, A17),
 	PINMUX_IPSR_MSEL(IP1_28_26, DACK2_B, SEL_LBS_1),
 	PINMUX_IPSR_MSEL(IP1_28_26, SDA0_C, SEL_IIC0_2),
-	PINMUX_IPSR_DATA(IP1_31_29, A18),
+	PINMUX_IPSR_GPSR(IP1_31_29, A18),
 	PINMUX_IPSR_MSEL(IP1_31_29, DREQ1, SEL_LBS_0),
 	PINMUX_IPSR_MSEL(IP1_31_29, SCIFA1_RXD_C, SEL_SCIFA1_2),
 	PINMUX_IPSR_MSEL(IP1_31_29, SCIFB1_RXD_C, SEL_SCIFB1_2),
 
 	/* IPSR2 */
-	PINMUX_IPSR_DATA(IP2_2_0, A19),
-	PINMUX_IPSR_DATA(IP2_2_0, DACK1),
+	PINMUX_IPSR_GPSR(IP2_2_0, A19),
+	PINMUX_IPSR_GPSR(IP2_2_0, DACK1),
 	PINMUX_IPSR_MSEL(IP2_2_0, SCIFA1_TXD_C, SEL_SCIFA1_2),
 	PINMUX_IPSR_MSEL(IP2_2_0, SCIFB1_TXD_C, SEL_SCIFB1_2),
 	PINMUX_IPSR_MSEL(IP2_2_0, SCIFB1_SCK_B, SEL_SCIFB1_1),
-	PINMUX_IPSR_DATA(IP2_2_0, A20),
+	PINMUX_IPSR_GPSR(IP2_2_0, A20),
 	PINMUX_IPSR_MSEL(IP2_4_3, SPCLK, SEL_QSP_0),
-	PINMUX_IPSR_DATA(IP2_6_5, A21),
+	PINMUX_IPSR_GPSR(IP2_6_5, A21),
 	PINMUX_IPSR_MSEL(IP2_6_5, ATAWR0_N_B, SEL_LBS_1),
 	PINMUX_IPSR_MSEL(IP2_6_5, MOSI_IO0, SEL_QSP_0),
-	PINMUX_IPSR_DATA(IP2_9_7, A22),
+	PINMUX_IPSR_GPSR(IP2_9_7, A22),
 	PINMUX_IPSR_MSEL(IP2_9_7, MISO_IO1, SEL_QSP_0),
 	PINMUX_IPSR_MSEL(IP2_9_7, FMCLK_B, SEL_FM_1),
 	PINMUX_IPSR_MSEL(IP2_9_7, TX0, SEL_SCIF0_0),
 	PINMUX_IPSR_MSEL(IP2_9_7, SCIFA0_TXD, SEL_SCFA_0),
-	PINMUX_IPSR_DATA(IP2_12_10, A23),
+	PINMUX_IPSR_GPSR(IP2_12_10, A23),
 	PINMUX_IPSR_MSEL(IP2_12_10, IO2, SEL_QSP_0),
 	PINMUX_IPSR_MSEL(IP2_12_10, BPFCLK_B, SEL_FM_1),
 	PINMUX_IPSR_MSEL(IP2_12_10, RX0, SEL_SCIF0_0),
 	PINMUX_IPSR_MSEL(IP2_12_10, SCIFA0_RXD, SEL_SCFA_0),
-	PINMUX_IPSR_DATA(IP2_15_13, A24),
+	PINMUX_IPSR_GPSR(IP2_15_13, A24),
 	PINMUX_IPSR_MSEL(IP2_15_13, DREQ2, SEL_LBS_0),
 	PINMUX_IPSR_MSEL(IP2_15_13, IO3, SEL_QSP_0),
 	PINMUX_IPSR_MSEL(IP2_15_13, TX1, SEL_SCIF1_0),
 	PINMUX_IPSR_MSEL(IP2_15_13, SCIFA1_TXD, SEL_SCIFA1_0),
-	PINMUX_IPSR_DATA(IP2_18_16, A25),
+	PINMUX_IPSR_GPSR(IP2_18_16, A25),
 	PINMUX_IPSR_MSEL(IP2_18_16, DACK2, SEL_LBS_0),
 	PINMUX_IPSR_MSEL(IP2_18_16, SSL, SEL_QSP_0),
 	PINMUX_IPSR_MSEL(IP2_18_16, DREQ1_C, SEL_LBS_2),
 	PINMUX_IPSR_MSEL(IP2_18_16, RX1, SEL_SCIF1_0),
 	PINMUX_IPSR_MSEL(IP2_18_16, SCIFA1_RXD, SEL_SCIFA1_0),
-	PINMUX_IPSR_DATA(IP2_20_19, CS0_N),
+	PINMUX_IPSR_GPSR(IP2_20_19, CS0_N),
 	PINMUX_IPSR_MSEL(IP2_20_19, ATAG0_N_B, SEL_LBS_1),
 	PINMUX_IPSR_MSEL(IP2_20_19, SCL1, SEL_IIC1_0),
-	PINMUX_IPSR_DATA(IP2_22_21, CS1_N_A26),
+	PINMUX_IPSR_GPSR(IP2_22_21, CS1_N_A26),
 	PINMUX_IPSR_MSEL(IP2_22_21, ATADIR0_N_B, SEL_LBS_1),
 	PINMUX_IPSR_MSEL(IP2_22_21, SDA1, SEL_IIC1_0),
-	PINMUX_IPSR_DATA(IP2_24_23, EX_CS1_N),
+	PINMUX_IPSR_GPSR(IP2_24_23, EX_CS1_N),
 	PINMUX_IPSR_MSEL(IP2_24_23, MSIOF2_SCK, SEL_SOF2_0),
-	PINMUX_IPSR_DATA(IP2_26_25, EX_CS2_N),
+	PINMUX_IPSR_GPSR(IP2_26_25, EX_CS2_N),
 	PINMUX_IPSR_MSEL(IP2_26_25, ATAWR0_N, SEL_LBS_0),
 	PINMUX_IPSR_MSEL(IP2_26_25, MSIOF2_SYNC, SEL_SOF2_0),
-	PINMUX_IPSR_DATA(IP2_29_27, EX_CS3_N),
+	PINMUX_IPSR_GPSR(IP2_29_27, EX_CS3_N),
 	PINMUX_IPSR_MSEL(IP2_29_27, ATADIR0_N, SEL_LBS_0),
 	PINMUX_IPSR_MSEL(IP2_29_27, MSIOF2_TXD, SEL_SOF2_0),
 	PINMUX_IPSR_MSEL(IP2_29_27, ATAG0_N, SEL_LBS_0),
-	PINMUX_IPSR_DATA(IP2_29_27, EX_WAIT1),
+	PINMUX_IPSR_GPSR(IP2_29_27, EX_WAIT1),
 
 	/* IPSR3 */
-	PINMUX_IPSR_DATA(IP3_2_0, EX_CS4_N),
+	PINMUX_IPSR_GPSR(IP3_2_0, EX_CS4_N),
 	PINMUX_IPSR_MSEL(IP3_2_0, ATARD0_N, SEL_LBS_0),
 	PINMUX_IPSR_MSEL(IP3_2_0, MSIOF2_RXD, SEL_SOF2_0),
-	PINMUX_IPSR_DATA(IP3_2_0, EX_WAIT2),
-	PINMUX_IPSR_DATA(IP3_5_3, EX_CS5_N),
-	PINMUX_IPSR_DATA(IP3_5_3, ATACS00_N),
+	PINMUX_IPSR_GPSR(IP3_2_0, EX_WAIT2),
+	PINMUX_IPSR_GPSR(IP3_5_3, EX_CS5_N),
+	PINMUX_IPSR_GPSR(IP3_5_3, ATACS00_N),
 	PINMUX_IPSR_MSEL(IP3_5_3, MSIOF2_SS1, SEL_SOF2_0),
 	PINMUX_IPSR_MSEL(IP3_5_3, HRX1_B, SEL_HSCIF1_1),
 	PINMUX_IPSR_MSEL(IP3_5_3, SCIFB1_RXD_B, SEL_SCIFB1_1),
-	PINMUX_IPSR_DATA(IP3_5_3, PWM1),
-	PINMUX_IPSR_DATA(IP3_5_3, TPU_TO1),
-	PINMUX_IPSR_DATA(IP3_8_6, BS_N),
-	PINMUX_IPSR_DATA(IP3_8_6, ATACS10_N),
+	PINMUX_IPSR_GPSR(IP3_5_3, PWM1),
+	PINMUX_IPSR_GPSR(IP3_5_3, TPU_TO1),
+	PINMUX_IPSR_GPSR(IP3_8_6, BS_N),
+	PINMUX_IPSR_GPSR(IP3_8_6, ATACS10_N),
 	PINMUX_IPSR_MSEL(IP3_8_6, MSIOF2_SS2, SEL_SOF2_0),
 	PINMUX_IPSR_MSEL(IP3_8_6, HTX1_B, SEL_HSCIF1_1),
 	PINMUX_IPSR_MSEL(IP3_8_6, SCIFB1_TXD_B, SEL_SCIFB1_1),
-	PINMUX_IPSR_DATA(IP3_8_6, PWM2),
-	PINMUX_IPSR_DATA(IP3_8_6, TPU_TO2),
-	PINMUX_IPSR_DATA(IP3_11_9, RD_WR_N),
+	PINMUX_IPSR_GPSR(IP3_8_6, PWM2),
+	PINMUX_IPSR_GPSR(IP3_8_6, TPU_TO2),
+	PINMUX_IPSR_GPSR(IP3_11_9, RD_WR_N),
 	PINMUX_IPSR_MSEL(IP3_11_9, HRX2_B, SEL_HSCIF2_1),
 	PINMUX_IPSR_MSEL(IP3_11_9, FMIN_B, SEL_FM_1),
 	PINMUX_IPSR_MSEL(IP3_11_9, SCIFB0_RXD_B, SEL_SCIFB_1),
 	PINMUX_IPSR_MSEL(IP3_11_9, DREQ1_D, SEL_LBS_1),
-	PINMUX_IPSR_DATA(IP3_13_12, WE0_N),
+	PINMUX_IPSR_GPSR(IP3_13_12, WE0_N),
 	PINMUX_IPSR_MSEL(IP3_13_12, HCTS2_N_B, SEL_HSCIF2_1),
 	PINMUX_IPSR_MSEL(IP3_13_12, SCIFB0_TXD_B, SEL_SCIFB_1),
-	PINMUX_IPSR_DATA(IP3_15_14, WE1_N),
+	PINMUX_IPSR_GPSR(IP3_15_14, WE1_N),
 	PINMUX_IPSR_MSEL(IP3_15_14, ATARD0_N_B, SEL_LBS_1),
 	PINMUX_IPSR_MSEL(IP3_15_14, HTX2_B, SEL_HSCIF2_1),
 	PINMUX_IPSR_MSEL(IP3_15_14, SCIFB0_RTS_N_B, SEL_SCIFB_1),
-	PINMUX_IPSR_DATA(IP3_17_16, EX_WAIT0),
+	PINMUX_IPSR_GPSR(IP3_17_16, EX_WAIT0),
 	PINMUX_IPSR_MSEL(IP3_17_16, HRTS2_N_B, SEL_HSCIF2_1),
 	PINMUX_IPSR_MSEL(IP3_17_16, SCIFB0_CTS_N_B, SEL_SCIFB_1),
-	PINMUX_IPSR_DATA(IP3_19_18, DREQ0),
-	PINMUX_IPSR_DATA(IP3_19_18, PWM3),
-	PINMUX_IPSR_DATA(IP3_19_18, TPU_TO3),
-	PINMUX_IPSR_DATA(IP3_21_20, DACK0),
-	PINMUX_IPSR_DATA(IP3_21_20, DRACK0),
+	PINMUX_IPSR_GPSR(IP3_19_18, DREQ0),
+	PINMUX_IPSR_GPSR(IP3_19_18, PWM3),
+	PINMUX_IPSR_GPSR(IP3_19_18, TPU_TO3),
+	PINMUX_IPSR_GPSR(IP3_21_20, DACK0),
+	PINMUX_IPSR_GPSR(IP3_21_20, DRACK0),
 	PINMUX_IPSR_MSEL(IP3_21_20, REMOCON, SEL_RCN_0),
 	PINMUX_IPSR_MSEL(IP3_24_22, SPEEDIN, SEL_RSP_0),
 	PINMUX_IPSR_MSEL(IP3_24_22, HSCK0_C, SEL_HSCIF0_2),
@@ -995,61 +995,61 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP4_9_8, SDA1_B, SEL_IIC1_1),
 	PINMUX_IPSR_MSEL(IP4_9_8, SDA8_B, SEL_IIC8_1),
 	PINMUX_IPSR_MSEL(IP4_9_8, MSIOF2_RXD_C, SEL_SOF2_2),
-	PINMUX_IPSR_DATA(IP4_12_10, SSI_SCK2),
+	PINMUX_IPSR_GPSR(IP4_12_10, SSI_SCK2),
 	PINMUX_IPSR_MSEL(IP4_12_10, SCL2, SEL_IIC2_0),
 	PINMUX_IPSR_MSEL(IP4_12_10, GPS_CLK_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP4_12_10, GLO_Q0_D, SEL_GPS_3),
-	PINMUX_IPSR_DATA(IP4_15_13, SSI_WS2),
+	PINMUX_IPSR_GPSR(IP4_15_13, SSI_WS2),
 	PINMUX_IPSR_MSEL(IP4_15_13, SDA2, SEL_IIC2_0),
 	PINMUX_IPSR_MSEL(IP4_15_13, GPS_SIGN_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP4_15_13, RX2_E, SEL_SCIF2_4),
 	PINMUX_IPSR_MSEL(IP4_15_13, GLO_Q1_D, SEL_GPS_3),
-	PINMUX_IPSR_DATA(IP4_18_16, SSI_SDATA2),
+	PINMUX_IPSR_GPSR(IP4_18_16, SSI_SDATA2),
 	PINMUX_IPSR_MSEL(IP4_18_16, GPS_MAG_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP4_18_16, TX2_E, SEL_SCIF2_4),
-	PINMUX_IPSR_DATA(IP4_19, SSI_SCK34),
-	PINMUX_IPSR_DATA(IP4_20, SSI_WS34),
-	PINMUX_IPSR_DATA(IP4_21, SSI_SDATA3),
-	PINMUX_IPSR_DATA(IP4_23_22, SSI_SCK4),
+	PINMUX_IPSR_GPSR(IP4_19, SSI_SCK34),
+	PINMUX_IPSR_GPSR(IP4_20, SSI_WS34),
+	PINMUX_IPSR_GPSR(IP4_21, SSI_SDATA3),
+	PINMUX_IPSR_GPSR(IP4_23_22, SSI_SCK4),
 	PINMUX_IPSR_MSEL(IP4_23_22, GLO_SS_D, SEL_GPS_3),
-	PINMUX_IPSR_DATA(IP4_25_24, SSI_WS4),
+	PINMUX_IPSR_GPSR(IP4_25_24, SSI_WS4),
 	PINMUX_IPSR_MSEL(IP4_25_24, GLO_RFON_D, SEL_GPS_3),
-	PINMUX_IPSR_DATA(IP4_27_26, SSI_SDATA4),
+	PINMUX_IPSR_GPSR(IP4_27_26, SSI_SDATA4),
 	PINMUX_IPSR_MSEL(IP4_27_26, MSIOF2_SCK_D, SEL_SOF2_3),
-	PINMUX_IPSR_DATA(IP4_30_28, SSI_SCK5),
+	PINMUX_IPSR_GPSR(IP4_30_28, SSI_SCK5),
 	PINMUX_IPSR_MSEL(IP4_30_28, MSIOF1_SCK_C, SEL_SOF1_2),
 	PINMUX_IPSR_MSEL(IP4_30_28, TS_SDATA0, SEL_TSIF0_0),
 	PINMUX_IPSR_MSEL(IP4_30_28, GLO_I0, SEL_GPS_0),
 	PINMUX_IPSR_MSEL(IP4_30_28, MSIOF2_SYNC_D, SEL_SOF2_3),
-	PINMUX_IPSR_DATA(IP4_30_28, VI1_R2_B),
+	PINMUX_IPSR_GPSR(IP4_30_28, VI1_R2_B),
 
 	/* IPSR5 */
-	PINMUX_IPSR_DATA(IP5_2_0, SSI_WS5),
+	PINMUX_IPSR_GPSR(IP5_2_0, SSI_WS5),
 	PINMUX_IPSR_MSEL(IP5_2_0, MSIOF1_SYNC_C, SEL_SOF1_2),
 	PINMUX_IPSR_MSEL(IP5_2_0, TS_SCK0, SEL_TSIF0_0),
 	PINMUX_IPSR_MSEL(IP5_2_0, GLO_I1, SEL_GPS_0),
 	PINMUX_IPSR_MSEL(IP5_2_0, MSIOF2_TXD_D, SEL_SOF2_3),
-	PINMUX_IPSR_DATA(IP5_2_0, VI1_R3_B),
-	PINMUX_IPSR_DATA(IP5_5_3, SSI_SDATA5),
+	PINMUX_IPSR_GPSR(IP5_2_0, VI1_R3_B),
+	PINMUX_IPSR_GPSR(IP5_5_3, SSI_SDATA5),
 	PINMUX_IPSR_MSEL(IP5_5_3, MSIOF1_TXD_C, SEL_SOF1_2),
 	PINMUX_IPSR_MSEL(IP5_5_3, TS_SDEN0, SEL_TSIF0_0),
 	PINMUX_IPSR_MSEL(IP5_5_3, GLO_Q0, SEL_GPS_0),
 	PINMUX_IPSR_MSEL(IP5_5_3, MSIOF2_SS1_D, SEL_SOF2_3),
-	PINMUX_IPSR_DATA(IP5_5_3, VI1_R4_B),
-	PINMUX_IPSR_DATA(IP5_8_6, SSI_SCK6),
+	PINMUX_IPSR_GPSR(IP5_5_3, VI1_R4_B),
+	PINMUX_IPSR_GPSR(IP5_8_6, SSI_SCK6),
 	PINMUX_IPSR_MSEL(IP5_8_6, MSIOF1_RXD_C, SEL_SOF1_2),
 	PINMUX_IPSR_MSEL(IP5_8_6, TS_SPSYNC0, SEL_TSIF0_0),
 	PINMUX_IPSR_MSEL(IP5_8_6, GLO_Q1, SEL_GPS_0),
 	PINMUX_IPSR_MSEL(IP5_8_6, MSIOF2_RXD_D, SEL_SOF2_3),
-	PINMUX_IPSR_DATA(IP5_8_6, VI1_R5_B),
-	PINMUX_IPSR_DATA(IP5_11_9, SSI_WS6),
+	PINMUX_IPSR_GPSR(IP5_8_6, VI1_R5_B),
+	PINMUX_IPSR_GPSR(IP5_11_9, SSI_WS6),
 	PINMUX_IPSR_MSEL(IP5_11_9, GLO_SCLK, SEL_GPS_0),
 	PINMUX_IPSR_MSEL(IP5_11_9, MSIOF2_SS2_D, SEL_SOF2_3),
-	PINMUX_IPSR_DATA(IP5_11_9, VI1_R6_B),
-	PINMUX_IPSR_DATA(IP5_14_12, SSI_SDATA6),
+	PINMUX_IPSR_GPSR(IP5_11_9, VI1_R6_B),
+	PINMUX_IPSR_GPSR(IP5_14_12, SSI_SDATA6),
 	PINMUX_IPSR_MSEL(IP5_14_12, STP_IVCXO27_0_B, SEL_SSP_1),
 	PINMUX_IPSR_MSEL(IP5_14_12, GLO_SDATA, SEL_GPS_0),
-	PINMUX_IPSR_DATA(IP5_14_12, VI1_R7_B),
+	PINMUX_IPSR_GPSR(IP5_14_12, VI1_R7_B),
 	PINMUX_IPSR_MSEL(IP5_16_15, SSI_SCK78, SEL_SSI7_0),
 	PINMUX_IPSR_MSEL(IP5_16_15, STP_ISCLK_0_B, SEL_SSP_1),
 	PINMUX_IPSR_MSEL(IP5_16_15, GLO_SS, SEL_GPS_0),
@@ -1080,307 +1080,307 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP6_2_0, MSIOF1_SCK_B, SEL_SOF1_1),
 	PINMUX_IPSR_MSEL(IP6_2_0, SCIF_CLK, SEL_SCIF_0),
 	PINMUX_IPSR_MSEL(IP6_2_0, BPFCLK_E, SEL_FM_4),
-	PINMUX_IPSR_DATA(IP6_5_3, AUDIO_CLKC),
+	PINMUX_IPSR_GPSR(IP6_5_3, AUDIO_CLKC),
 	PINMUX_IPSR_MSEL(IP6_5_3, SCIFB0_SCK_C, SEL_SCIFB_2),
 	PINMUX_IPSR_MSEL(IP6_5_3, MSIOF1_SYNC_B, SEL_SOF1_1),
 	PINMUX_IPSR_MSEL(IP6_5_3, RX2, SEL_SCIF2_0),
 	PINMUX_IPSR_MSEL(IP6_5_3, SCIFA2_RXD, SEL_SCIFA2_0),
 	PINMUX_IPSR_MSEL(IP6_5_3, FMIN_E, SEL_FM_4),
-	PINMUX_IPSR_DATA(IP6_7_6, AUDIO_CLKOUT),
+	PINMUX_IPSR_GPSR(IP6_7_6, AUDIO_CLKOUT),
 	PINMUX_IPSR_MSEL(IP6_7_6, MSIOF1_SS1_B, SEL_SOF1_1),
 	PINMUX_IPSR_MSEL(IP6_5_3, TX2, SEL_SCIF2_0),
 	PINMUX_IPSR_MSEL(IP6_7_6, SCIFA2_TXD, SEL_SCIFA2_0),
-	PINMUX_IPSR_DATA(IP6_9_8, IRQ0),
+	PINMUX_IPSR_GPSR(IP6_9_8, IRQ0),
 	PINMUX_IPSR_MSEL(IP6_9_8, SCIFB1_RXD_D, SEL_SCIFB1_3),
-	PINMUX_IPSR_DATA(IP6_9_8, INTC_IRQ0_N),
-	PINMUX_IPSR_DATA(IP6_11_10, IRQ1),
+	PINMUX_IPSR_GPSR(IP6_9_8, INTC_IRQ0_N),
+	PINMUX_IPSR_GPSR(IP6_11_10, IRQ1),
 	PINMUX_IPSR_MSEL(IP6_11_10, SCIFB1_SCK_C, SEL_SCIFB1_2),
-	PINMUX_IPSR_DATA(IP6_11_10, INTC_IRQ1_N),
-	PINMUX_IPSR_DATA(IP6_13_12, IRQ2),
+	PINMUX_IPSR_GPSR(IP6_11_10, INTC_IRQ1_N),
+	PINMUX_IPSR_GPSR(IP6_13_12, IRQ2),
 	PINMUX_IPSR_MSEL(IP6_13_12, SCIFB1_TXD_D, SEL_SCIFB1_3),
-	PINMUX_IPSR_DATA(IP6_13_12, INTC_IRQ2_N),
-	PINMUX_IPSR_DATA(IP6_15_14, IRQ3),
+	PINMUX_IPSR_GPSR(IP6_13_12, INTC_IRQ2_N),
+	PINMUX_IPSR_GPSR(IP6_15_14, IRQ3),
 	PINMUX_IPSR_MSEL(IP6_15_14, SCL4_C, SEL_IIC4_2),
 	PINMUX_IPSR_MSEL(IP6_15_14, MSIOF2_TXD_E, SEL_SOF2_4),
-	PINMUX_IPSR_DATA(IP6_15_14, INTC_IRQ4_N),
-	PINMUX_IPSR_DATA(IP6_18_16, IRQ4),
+	PINMUX_IPSR_GPSR(IP6_15_14, INTC_IRQ4_N),
+	PINMUX_IPSR_GPSR(IP6_18_16, IRQ4),
 	PINMUX_IPSR_MSEL(IP6_18_16, HRX1_C, SEL_HSCIF1_2),
 	PINMUX_IPSR_MSEL(IP6_18_16, SDA4_C, SEL_IIC4_2),
 	PINMUX_IPSR_MSEL(IP6_18_16, MSIOF2_RXD_E, SEL_SOF2_4),
-	PINMUX_IPSR_DATA(IP6_18_16, INTC_IRQ4_N),
-	PINMUX_IPSR_DATA(IP6_20_19, IRQ5),
+	PINMUX_IPSR_GPSR(IP6_18_16, INTC_IRQ4_N),
+	PINMUX_IPSR_GPSR(IP6_20_19, IRQ5),
 	PINMUX_IPSR_MSEL(IP6_20_19, HTX1_C, SEL_HSCIF1_2),
 	PINMUX_IPSR_MSEL(IP6_20_19, SCL1_E, SEL_IIC1_4),
 	PINMUX_IPSR_MSEL(IP6_20_19, MSIOF2_SCK_E, SEL_SOF2_4),
-	PINMUX_IPSR_DATA(IP6_23_21, IRQ6),
+	PINMUX_IPSR_GPSR(IP6_23_21, IRQ6),
 	PINMUX_IPSR_MSEL(IP6_23_21, HSCK1_C, SEL_HSCIF1_2),
 	PINMUX_IPSR_MSEL(IP6_23_21, MSIOF1_SS2_B, SEL_SOF1_1),
 	PINMUX_IPSR_MSEL(IP6_23_21, SDA1_E, SEL_IIC1_4),
 	PINMUX_IPSR_MSEL(IP6_23_21, MSIOF2_SYNC_E, SEL_SOF2_4),
-	PINMUX_IPSR_DATA(IP6_26_24, IRQ7),
+	PINMUX_IPSR_GPSR(IP6_26_24, IRQ7),
 	PINMUX_IPSR_MSEL(IP6_26_24, HCTS1_N_C, SEL_HSCIF1_2),
 	PINMUX_IPSR_MSEL(IP6_26_24, MSIOF1_TXD_B, SEL_SOF1_1),
 	PINMUX_IPSR_MSEL(IP6_26_24, GPS_CLK_C, SEL_GPS_2),
 	PINMUX_IPSR_MSEL(IP6_26_24, GPS_CLK_D, SEL_GPS_3),
-	PINMUX_IPSR_DATA(IP6_29_27, IRQ8),
+	PINMUX_IPSR_GPSR(IP6_29_27, IRQ8),
 	PINMUX_IPSR_MSEL(IP6_29_27, HRTS1_N_C, SEL_HSCIF1_2),
 	PINMUX_IPSR_MSEL(IP6_29_27, MSIOF1_RXD_B, SEL_SOF1_1),
 	PINMUX_IPSR_MSEL(IP6_29_27, GPS_SIGN_C, SEL_GPS_2),
 	PINMUX_IPSR_MSEL(IP6_29_27, GPS_SIGN_D, SEL_GPS_3),
 
 	/* IPSR7 */
-	PINMUX_IPSR_DATA(IP7_2_0, IRQ9),
+	PINMUX_IPSR_GPSR(IP7_2_0, IRQ9),
 	PINMUX_IPSR_MSEL(IP7_2_0, DU1_DOTCLKIN_B, SEL_DIS_1),
 	PINMUX_IPSR_MSEL(IP7_2_0, CAN_CLK_D, SEL_CANCLK_3),
 	PINMUX_IPSR_MSEL(IP7_2_0, GPS_MAG_C, SEL_GPS_2),
 	PINMUX_IPSR_MSEL(IP7_2_0, SCIF_CLK_B, SEL_SCIF_1),
 	PINMUX_IPSR_MSEL(IP7_2_0, GPS_MAG_D, SEL_GPS_3),
-	PINMUX_IPSR_DATA(IP7_5_3, DU1_DR0),
-	PINMUX_IPSR_DATA(IP7_5_3, LCDOUT0),
+	PINMUX_IPSR_GPSR(IP7_5_3, DU1_DR0),
+	PINMUX_IPSR_GPSR(IP7_5_3, LCDOUT0),
 	PINMUX_IPSR_MSEL(IP7_5_3, VI1_DATA0_B, SEL_VI1_1),
 	PINMUX_IPSR_MSEL(IP7_5_3, TX0_B, SEL_SCIF0_1),
 	PINMUX_IPSR_MSEL(IP7_5_3, SCIFA0_TXD_B, SEL_SCFA_1),
 	PINMUX_IPSR_MSEL(IP7_5_3, MSIOF2_SCK_B, SEL_SOF2_1),
-	PINMUX_IPSR_DATA(IP7_8_6, DU1_DR1),
-	PINMUX_IPSR_DATA(IP7_8_6, LCDOUT1),
+	PINMUX_IPSR_GPSR(IP7_8_6, DU1_DR1),
+	PINMUX_IPSR_GPSR(IP7_8_6, LCDOUT1),
 	PINMUX_IPSR_MSEL(IP7_8_6, VI1_DATA1_B, SEL_VI1_1),
 	PINMUX_IPSR_MSEL(IP7_8_6, RX0_B, SEL_SCIF0_1),
 	PINMUX_IPSR_MSEL(IP7_8_6, SCIFA0_RXD_B, SEL_SCFA_1),
 	PINMUX_IPSR_MSEL(IP7_8_6, MSIOF2_SYNC_B, SEL_SOF2_1),
-	PINMUX_IPSR_DATA(IP7_10_9, DU1_DR2),
-	PINMUX_IPSR_DATA(IP7_10_9, LCDOUT2),
+	PINMUX_IPSR_GPSR(IP7_10_9, DU1_DR2),
+	PINMUX_IPSR_GPSR(IP7_10_9, LCDOUT2),
 	PINMUX_IPSR_MSEL(IP7_10_9, SSI_SCK0129_B, SEL_SSI0_1),
-	PINMUX_IPSR_DATA(IP7_12_11, DU1_DR3),
-	PINMUX_IPSR_DATA(IP7_12_11, LCDOUT3),
+	PINMUX_IPSR_GPSR(IP7_12_11, DU1_DR3),
+	PINMUX_IPSR_GPSR(IP7_12_11, LCDOUT3),
 	PINMUX_IPSR_MSEL(IP7_12_11, SSI_WS0129_B, SEL_SSI0_1),
-	PINMUX_IPSR_DATA(IP7_14_13, DU1_DR4),
-	PINMUX_IPSR_DATA(IP7_14_13, LCDOUT4),
+	PINMUX_IPSR_GPSR(IP7_14_13, DU1_DR4),
+	PINMUX_IPSR_GPSR(IP7_14_13, LCDOUT4),
 	PINMUX_IPSR_MSEL(IP7_14_13, SSI_SDATA0_B, SEL_SSI0_1),
-	PINMUX_IPSR_DATA(IP7_16_15, DU1_DR5),
-	PINMUX_IPSR_DATA(IP7_16_15, LCDOUT5),
+	PINMUX_IPSR_GPSR(IP7_16_15, DU1_DR5),
+	PINMUX_IPSR_GPSR(IP7_16_15, LCDOUT5),
 	PINMUX_IPSR_MSEL(IP7_16_15, SSI_SCK1_B, SEL_SSI1_1),
-	PINMUX_IPSR_DATA(IP7_18_17, DU1_DR6),
-	PINMUX_IPSR_DATA(IP7_18_17, LCDOUT6),
+	PINMUX_IPSR_GPSR(IP7_18_17, DU1_DR6),
+	PINMUX_IPSR_GPSR(IP7_18_17, LCDOUT6),
 	PINMUX_IPSR_MSEL(IP7_18_17, SSI_WS1_B, SEL_SSI1_1),
-	PINMUX_IPSR_DATA(IP7_20_19, DU1_DR7),
-	PINMUX_IPSR_DATA(IP7_20_19, LCDOUT7),
+	PINMUX_IPSR_GPSR(IP7_20_19, DU1_DR7),
+	PINMUX_IPSR_GPSR(IP7_20_19, LCDOUT7),
 	PINMUX_IPSR_MSEL(IP7_20_19, SSI_SDATA1_B, SEL_SSI1_1),
-	PINMUX_IPSR_DATA(IP7_23_21, DU1_DG0),
-	PINMUX_IPSR_DATA(IP7_23_21, LCDOUT8),
+	PINMUX_IPSR_GPSR(IP7_23_21, DU1_DG0),
+	PINMUX_IPSR_GPSR(IP7_23_21, LCDOUT8),
 	PINMUX_IPSR_MSEL(IP7_23_21, VI1_DATA2_B, SEL_VI1_1),
 	PINMUX_IPSR_MSEL(IP7_23_21, TX1_B, SEL_SCIF1_1),
 	PINMUX_IPSR_MSEL(IP7_23_21, SCIFA1_TXD_B, SEL_SCIFA1_1),
 	PINMUX_IPSR_MSEL(IP7_23_21, MSIOF2_SS1_B, SEL_SOF2_1),
-	PINMUX_IPSR_DATA(IP7_26_24, DU1_DG1),
-	PINMUX_IPSR_DATA(IP7_26_24, LCDOUT9),
+	PINMUX_IPSR_GPSR(IP7_26_24, DU1_DG1),
+	PINMUX_IPSR_GPSR(IP7_26_24, LCDOUT9),
 	PINMUX_IPSR_MSEL(IP7_26_24, VI1_DATA3_B, SEL_VI1_1),
 	PINMUX_IPSR_MSEL(IP7_26_24, RX1_B, SEL_SCIF1_1),
 	PINMUX_IPSR_MSEL(IP7_26_24, SCIFA1_RXD_B, SEL_SCIFA1_1),
 	PINMUX_IPSR_MSEL(IP7_26_24, MSIOF2_SS2_B, SEL_SOF2_1),
-	PINMUX_IPSR_DATA(IP7_29_27, DU1_DG2),
-	PINMUX_IPSR_DATA(IP7_29_27, LCDOUT10),
+	PINMUX_IPSR_GPSR(IP7_29_27, DU1_DG2),
+	PINMUX_IPSR_GPSR(IP7_29_27, LCDOUT10),
 	PINMUX_IPSR_MSEL(IP7_29_27, VI1_DATA4_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP7_29_27, SCIF1_SCK_B),
+	PINMUX_IPSR_GPSR(IP7_29_27, SCIF1_SCK_B),
 	PINMUX_IPSR_MSEL(IP7_29_27, SCIFA1_SCK, SEL_SCIFA1_0),
 	PINMUX_IPSR_MSEL(IP7_29_27, SSI_SCK78_B, SEL_SSI7_1),
 
 	/* IPSR8 */
-	PINMUX_IPSR_DATA(IP8_2_0, DU1_DG3),
-	PINMUX_IPSR_DATA(IP8_2_0, LCDOUT11),
+	PINMUX_IPSR_GPSR(IP8_2_0, DU1_DG3),
+	PINMUX_IPSR_GPSR(IP8_2_0, LCDOUT11),
 	PINMUX_IPSR_MSEL(IP8_2_0, VI1_DATA5_B, SEL_VI1_1),
 	PINMUX_IPSR_MSEL(IP8_2_0, SSI_WS78_B, SEL_SSI7_1),
-	PINMUX_IPSR_DATA(IP8_5_3, DU1_DG4),
-	PINMUX_IPSR_DATA(IP8_5_3, LCDOUT12),
+	PINMUX_IPSR_GPSR(IP8_5_3, DU1_DG4),
+	PINMUX_IPSR_GPSR(IP8_5_3, LCDOUT12),
 	PINMUX_IPSR_MSEL(IP8_5_3, VI1_DATA6_B, SEL_VI1_1),
 	PINMUX_IPSR_MSEL(IP8_5_3, HRX0_B, SEL_HSCIF0_1),
 	PINMUX_IPSR_MSEL(IP8_5_3, SCIFB2_RXD_B, SEL_SCIFB2_1),
 	PINMUX_IPSR_MSEL(IP8_5_3, SSI_SDATA7_B, SEL_SSI7_1),
-	PINMUX_IPSR_DATA(IP8_8_6, DU1_DG5),
-	PINMUX_IPSR_DATA(IP8_8_6, LCDOUT13),
+	PINMUX_IPSR_GPSR(IP8_8_6, DU1_DG5),
+	PINMUX_IPSR_GPSR(IP8_8_6, LCDOUT13),
 	PINMUX_IPSR_MSEL(IP8_8_6, VI1_DATA7_B, SEL_VI1_1),
 	PINMUX_IPSR_MSEL(IP8_8_6, HCTS0_N_B, SEL_HSCIF0_1),
 	PINMUX_IPSR_MSEL(IP8_8_6, SCIFB2_TXD_B, SEL_SCIFB2_1),
 	PINMUX_IPSR_MSEL(IP8_8_6, SSI_SDATA8_B, SEL_SSI8_1),
-	PINMUX_IPSR_DATA(IP8_11_9, DU1_DG6),
-	PINMUX_IPSR_DATA(IP8_11_9, LCDOUT14),
+	PINMUX_IPSR_GPSR(IP8_11_9, DU1_DG6),
+	PINMUX_IPSR_GPSR(IP8_11_9, LCDOUT14),
 	PINMUX_IPSR_MSEL(IP8_11_9, HRTS0_N_B, SEL_HSCIF0_1),
 	PINMUX_IPSR_MSEL(IP8_11_9, SCIFB2_CTS_N_B, SEL_SCIFB2_1),
 	PINMUX_IPSR_MSEL(IP8_11_9, SSI_SCK9_B, SEL_SSI9_1),
-	PINMUX_IPSR_DATA(IP8_14_12, DU1_DG7),
-	PINMUX_IPSR_DATA(IP8_14_12, LCDOUT15),
+	PINMUX_IPSR_GPSR(IP8_14_12, DU1_DG7),
+	PINMUX_IPSR_GPSR(IP8_14_12, LCDOUT15),
 	PINMUX_IPSR_MSEL(IP8_14_12, HTX0_B, SEL_HSCIF0_1),
 	PINMUX_IPSR_MSEL(IP8_14_12, SCIFB2_RTS_N_B, SEL_SCIFB2_1),
 	PINMUX_IPSR_MSEL(IP8_14_12, SSI_WS9_B, SEL_SSI9_1),
-	PINMUX_IPSR_DATA(IP8_17_15, DU1_DB0),
-	PINMUX_IPSR_DATA(IP8_17_15, LCDOUT16),
+	PINMUX_IPSR_GPSR(IP8_17_15, DU1_DB0),
+	PINMUX_IPSR_GPSR(IP8_17_15, LCDOUT16),
 	PINMUX_IPSR_MSEL(IP8_17_15, VI1_CLK_B, SEL_VI1_1),
 	PINMUX_IPSR_MSEL(IP8_17_15, TX2_B, SEL_SCIF2_1),
 	PINMUX_IPSR_MSEL(IP8_17_15, SCIFA2_TXD_B, SEL_SCIFA2_1),
 	PINMUX_IPSR_MSEL(IP8_17_15, MSIOF2_TXD_B, SEL_SOF2_1),
-	PINMUX_IPSR_DATA(IP8_20_18, DU1_DB1),
-	PINMUX_IPSR_DATA(IP8_20_18, LCDOUT17),
+	PINMUX_IPSR_GPSR(IP8_20_18, DU1_DB1),
+	PINMUX_IPSR_GPSR(IP8_20_18, LCDOUT17),
 	PINMUX_IPSR_MSEL(IP8_20_18, VI1_HSYNC_N_B, SEL_VI1_1),
 	PINMUX_IPSR_MSEL(IP8_20_18, RX2_B, SEL_SCIF2_1),
 	PINMUX_IPSR_MSEL(IP8_20_18, SCIFA2_RXD_B, SEL_SCIFA2_1),
 	PINMUX_IPSR_MSEL(IP8_20_18, MSIOF2_RXD_B, SEL_SOF2_1),
-	PINMUX_IPSR_DATA(IP8_23_21, DU1_DB2),
-	PINMUX_IPSR_DATA(IP8_23_21, LCDOUT18),
+	PINMUX_IPSR_GPSR(IP8_23_21, DU1_DB2),
+	PINMUX_IPSR_GPSR(IP8_23_21, LCDOUT18),
 	PINMUX_IPSR_MSEL(IP8_23_21, VI1_VSYNC_N_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP8_23_21, SCIF2_SCK_B),
+	PINMUX_IPSR_GPSR(IP8_23_21, SCIF2_SCK_B),
 	PINMUX_IPSR_MSEL(IP8_23_21, SCIFA2_SCK, SEL_SCIFA2_1),
 	PINMUX_IPSR_MSEL(IP8_23_21, SSI_SDATA9_B, SEL_SSI9_1),
-	PINMUX_IPSR_DATA(IP8_25_24, DU1_DB3),
-	PINMUX_IPSR_DATA(IP8_25_24, LCDOUT19),
+	PINMUX_IPSR_GPSR(IP8_25_24, DU1_DB3),
+	PINMUX_IPSR_GPSR(IP8_25_24, LCDOUT19),
 	PINMUX_IPSR_MSEL(IP8_25_24, VI1_CLKENB_B, SEL_VI1_1),
-	PINMUX_IPSR_DATA(IP8_27_26, DU1_DB4),
-	PINMUX_IPSR_DATA(IP8_27_26, LCDOUT20),
+	PINMUX_IPSR_GPSR(IP8_27_26, DU1_DB4),
+	PINMUX_IPSR_GPSR(IP8_27_26, LCDOUT20),
 	PINMUX_IPSR_MSEL(IP8_27_26, VI1_FIELD_B, SEL_VI1_1),
 	PINMUX_IPSR_MSEL(IP8_27_26, CAN1_RX, SEL_CAN1_0),
-	PINMUX_IPSR_DATA(IP8_30_28, DU1_DB5),
-	PINMUX_IPSR_DATA(IP8_30_28, LCDOUT21),
+	PINMUX_IPSR_GPSR(IP8_30_28, DU1_DB5),
+	PINMUX_IPSR_GPSR(IP8_30_28, LCDOUT21),
 	PINMUX_IPSR_MSEL(IP8_30_28, TX3, SEL_SCIF3_0),
 	PINMUX_IPSR_MSEL(IP8_30_28, SCIFA3_TXD, SEL_SCIFA3_0),
 	PINMUX_IPSR_MSEL(IP8_30_28, CAN1_TX, SEL_CAN1_0),
 
 	/* IPSR9 */
-	PINMUX_IPSR_DATA(IP9_2_0, DU1_DB6),
-	PINMUX_IPSR_DATA(IP9_2_0, LCDOUT22),
+	PINMUX_IPSR_GPSR(IP9_2_0, DU1_DB6),
+	PINMUX_IPSR_GPSR(IP9_2_0, LCDOUT22),
 	PINMUX_IPSR_MSEL(IP9_2_0, SCL3_C, SEL_IIC3_2),
 	PINMUX_IPSR_MSEL(IP9_2_0, RX3, SEL_SCIF3_0),
 	PINMUX_IPSR_MSEL(IP9_2_0, SCIFA3_RXD, SEL_SCIFA3_0),
-	PINMUX_IPSR_DATA(IP9_5_3, DU1_DB7),
-	PINMUX_IPSR_DATA(IP9_5_3, LCDOUT23),
+	PINMUX_IPSR_GPSR(IP9_5_3, DU1_DB7),
+	PINMUX_IPSR_GPSR(IP9_5_3, LCDOUT23),
 	PINMUX_IPSR_MSEL(IP9_5_3, SDA3_C, SEL_IIC3_2),
 	PINMUX_IPSR_MSEL(IP9_5_3, SCIF3_SCK, SEL_SCIF3_0),
 	PINMUX_IPSR_MSEL(IP9_5_3, SCIFA3_SCK, SEL_SCIFA3_0),
 	PINMUX_IPSR_MSEL(IP9_6, DU1_DOTCLKIN, SEL_DIS_0),
-	PINMUX_IPSR_DATA(IP9_6, QSTVA_QVS),
-	PINMUX_IPSR_DATA(IP9_7, DU1_DOTCLKOUT0),
-	PINMUX_IPSR_DATA(IP9_7, QCLK),
-	PINMUX_IPSR_DATA(IP9_10_8, DU1_DOTCLKOUT1),
-	PINMUX_IPSR_DATA(IP9_10_8, QSTVB_QVE),
+	PINMUX_IPSR_GPSR(IP9_6, QSTVA_QVS),
+	PINMUX_IPSR_GPSR(IP9_7, DU1_DOTCLKOUT0),
+	PINMUX_IPSR_GPSR(IP9_7, QCLK),
+	PINMUX_IPSR_GPSR(IP9_10_8, DU1_DOTCLKOUT1),
+	PINMUX_IPSR_GPSR(IP9_10_8, QSTVB_QVE),
 	PINMUX_IPSR_MSEL(IP9_10_8, CAN0_TX, SEL_CAN0_0),
 	PINMUX_IPSR_MSEL(IP9_10_8, TX3_B, SEL_SCIF3_1),
 	PINMUX_IPSR_MSEL(IP9_10_8, SCL2_B, SEL_IIC2_1),
-	PINMUX_IPSR_DATA(IP9_10_8, PWM4),
-	PINMUX_IPSR_DATA(IP9_11, DU1_EXHSYNC_DU1_HSYNC),
-	PINMUX_IPSR_DATA(IP9_11, QSTH_QHS),
-	PINMUX_IPSR_DATA(IP9_12, DU1_EXVSYNC_DU1_VSYNC),
-	PINMUX_IPSR_DATA(IP9_12, QSTB_QHE),
-	PINMUX_IPSR_DATA(IP9_15_13, DU1_EXODDF_DU1_ODDF_DISP_CDE),
-	PINMUX_IPSR_DATA(IP9_15_13, QCPV_QDE),
+	PINMUX_IPSR_GPSR(IP9_10_8, PWM4),
+	PINMUX_IPSR_GPSR(IP9_11, DU1_EXHSYNC_DU1_HSYNC),
+	PINMUX_IPSR_GPSR(IP9_11, QSTH_QHS),
+	PINMUX_IPSR_GPSR(IP9_12, DU1_EXVSYNC_DU1_VSYNC),
+	PINMUX_IPSR_GPSR(IP9_12, QSTB_QHE),
+	PINMUX_IPSR_GPSR(IP9_15_13, DU1_EXODDF_DU1_ODDF_DISP_CDE),
+	PINMUX_IPSR_GPSR(IP9_15_13, QCPV_QDE),
 	PINMUX_IPSR_MSEL(IP9_15_13, CAN0_RX, SEL_CAN0_0),
 	PINMUX_IPSR_MSEL(IP9_15_13, RX3_B, SEL_SCIF3_1),
 	PINMUX_IPSR_MSEL(IP9_15_13, SDA2_B, SEL_IIC2_1),
-	PINMUX_IPSR_DATA(IP9_16, DU1_DISP),
-	PINMUX_IPSR_DATA(IP9_16, QPOLA),
-	PINMUX_IPSR_DATA(IP9_18_17, DU1_CDE),
-	PINMUX_IPSR_DATA(IP9_18_17, QPOLB),
-	PINMUX_IPSR_DATA(IP9_18_17, PWM4_B),
-	PINMUX_IPSR_DATA(IP9_20_19, VI0_CLKENB),
+	PINMUX_IPSR_GPSR(IP9_16, DU1_DISP),
+	PINMUX_IPSR_GPSR(IP9_16, QPOLA),
+	PINMUX_IPSR_GPSR(IP9_18_17, DU1_CDE),
+	PINMUX_IPSR_GPSR(IP9_18_17, QPOLB),
+	PINMUX_IPSR_GPSR(IP9_18_17, PWM4_B),
+	PINMUX_IPSR_GPSR(IP9_20_19, VI0_CLKENB),
 	PINMUX_IPSR_MSEL(IP9_20_19, TX4, SEL_SCIF4_0),
 	PINMUX_IPSR_MSEL(IP9_20_19, SCIFA4_TXD, SEL_SCIFA4_0),
 	PINMUX_IPSR_MSEL(IP9_20_19, TS_SDATA0_D, SEL_TSIF0_3),
-	PINMUX_IPSR_DATA(IP9_22_21, VI0_FIELD),
+	PINMUX_IPSR_GPSR(IP9_22_21, VI0_FIELD),
 	PINMUX_IPSR_MSEL(IP9_22_21, RX4, SEL_SCIF4_0),
 	PINMUX_IPSR_MSEL(IP9_22_21, SCIFA4_RXD, SEL_SCIFA4_0),
 	PINMUX_IPSR_MSEL(IP9_22_21, TS_SCK0_D, SEL_TSIF0_3),
-	PINMUX_IPSR_DATA(IP9_24_23, VI0_HSYNC_N),
+	PINMUX_IPSR_GPSR(IP9_24_23, VI0_HSYNC_N),
 	PINMUX_IPSR_MSEL(IP9_24_23, TX5, SEL_SCIF5_0),
 	PINMUX_IPSR_MSEL(IP9_24_23, SCIFA5_TXD, SEL_SCIFA5_0),
 	PINMUX_IPSR_MSEL(IP9_24_23, TS_SDEN0_D, SEL_TSIF0_3),
-	PINMUX_IPSR_DATA(IP9_26_25, VI0_VSYNC_N),
+	PINMUX_IPSR_GPSR(IP9_26_25, VI0_VSYNC_N),
 	PINMUX_IPSR_MSEL(IP9_26_25, RX5, SEL_SCIF5_0),
 	PINMUX_IPSR_MSEL(IP9_26_25, SCIFA5_RXD, SEL_SCIFA5_0),
 	PINMUX_IPSR_MSEL(IP9_26_25, TS_SPSYNC0_D, SEL_TSIF0_3),
-	PINMUX_IPSR_DATA(IP9_28_27, VI0_DATA3_VI0_B3),
+	PINMUX_IPSR_GPSR(IP9_28_27, VI0_DATA3_VI0_B3),
 	PINMUX_IPSR_MSEL(IP9_28_27, SCIF3_SCK_B, SEL_SCIF3_1),
 	PINMUX_IPSR_MSEL(IP9_28_27, SCIFA3_SCK_B, SEL_SCIFA3_1),
-	PINMUX_IPSR_DATA(IP9_31_29, VI0_G0),
+	PINMUX_IPSR_GPSR(IP9_31_29, VI0_G0),
 	PINMUX_IPSR_MSEL(IP9_31_29, SCL8, SEL_IIC8_0),
 	PINMUX_IPSR_MSEL(IP9_31_29, STP_IVCXO27_0_C, SEL_SSP_2),
 	PINMUX_IPSR_MSEL(IP9_31_29, SCL4, SEL_IIC4_0),
 	PINMUX_IPSR_MSEL(IP9_31_29, HCTS2_N, SEL_HSCIF2_0),
 	PINMUX_IPSR_MSEL(IP9_31_29, SCIFB2_CTS_N, SEL_SCIFB2_0),
-	PINMUX_IPSR_DATA(IP9_31_29, ATAWR1_N),
+	PINMUX_IPSR_GPSR(IP9_31_29, ATAWR1_N),
 
 	/* IPSR10 */
-	PINMUX_IPSR_DATA(IP10_2_0, VI0_G1),
+	PINMUX_IPSR_GPSR(IP10_2_0, VI0_G1),
 	PINMUX_IPSR_MSEL(IP10_2_0, SDA8, SEL_IIC8_0),
 	PINMUX_IPSR_MSEL(IP10_2_0, STP_ISCLK_0_C, SEL_SSP_2),
 	PINMUX_IPSR_MSEL(IP10_2_0, SDA4, SEL_IIC4_0),
 	PINMUX_IPSR_MSEL(IP10_2_0, HRTS2_N, SEL_HSCIF2_0),
 	PINMUX_IPSR_MSEL(IP10_2_0, SCIFB2_RTS_N, SEL_SCIFB2_0),
-	PINMUX_IPSR_DATA(IP10_2_0, ATADIR1_N),
-	PINMUX_IPSR_DATA(IP10_5_3, VI0_G2),
-	PINMUX_IPSR_DATA(IP10_5_3, VI2_HSYNC_N),
+	PINMUX_IPSR_GPSR(IP10_2_0, ATADIR1_N),
+	PINMUX_IPSR_GPSR(IP10_5_3, VI0_G2),
+	PINMUX_IPSR_GPSR(IP10_5_3, VI2_HSYNC_N),
 	PINMUX_IPSR_MSEL(IP10_5_3, STP_ISD_0_C, SEL_SSP_2),
 	PINMUX_IPSR_MSEL(IP10_5_3, SCL3_B, SEL_IIC3_1),
 	PINMUX_IPSR_MSEL(IP10_5_3, HSCK2, SEL_HSCIF2_0),
 	PINMUX_IPSR_MSEL(IP10_5_3, SCIFB2_SCK, SEL_SCIFB2_0),
-	PINMUX_IPSR_DATA(IP10_5_3, ATARD1_N),
-	PINMUX_IPSR_DATA(IP10_8_6, VI0_G3),
-	PINMUX_IPSR_DATA(IP10_8_6, VI2_VSYNC_N),
+	PINMUX_IPSR_GPSR(IP10_5_3, ATARD1_N),
+	PINMUX_IPSR_GPSR(IP10_8_6, VI0_G3),
+	PINMUX_IPSR_GPSR(IP10_8_6, VI2_VSYNC_N),
 	PINMUX_IPSR_MSEL(IP10_8_6, STP_ISEN_0_C, SEL_SSP_2),
 	PINMUX_IPSR_MSEL(IP10_8_6, SDA3_B, SEL_IIC3_1),
 	PINMUX_IPSR_MSEL(IP10_8_6, HRX2, SEL_HSCIF2_0),
 	PINMUX_IPSR_MSEL(IP10_8_6, SCIFB2_RXD, SEL_SCIFB2_0),
-	PINMUX_IPSR_DATA(IP10_8_6, ATACS01_N),
-	PINMUX_IPSR_DATA(IP10_11_9, VI0_G4),
-	PINMUX_IPSR_DATA(IP10_11_9, VI2_CLKENB),
+	PINMUX_IPSR_GPSR(IP10_8_6, ATACS01_N),
+	PINMUX_IPSR_GPSR(IP10_11_9, VI0_G4),
+	PINMUX_IPSR_GPSR(IP10_11_9, VI2_CLKENB),
 	PINMUX_IPSR_MSEL(IP10_11_9, STP_ISSYNC_0_C, SEL_SSP_2),
 	PINMUX_IPSR_MSEL(IP10_11_9, HTX2, SEL_HSCIF2_0),
 	PINMUX_IPSR_MSEL(IP10_11_9, SCIFB2_TXD, SEL_SCIFB2_0),
 	PINMUX_IPSR_MSEL(IP10_11_9, SCIFB0_SCK_D, SEL_SCIFB_3),
-	PINMUX_IPSR_DATA(IP10_14_12, VI0_G5),
-	PINMUX_IPSR_DATA(IP10_14_12, VI2_FIELD),
+	PINMUX_IPSR_GPSR(IP10_14_12, VI0_G5),
+	PINMUX_IPSR_GPSR(IP10_14_12, VI2_FIELD),
 	PINMUX_IPSR_MSEL(IP10_14_12, STP_OPWM_0_C, SEL_SSP_2),
 	PINMUX_IPSR_MSEL(IP10_14_12, FMCLK_D, SEL_FM_3),
 	PINMUX_IPSR_MSEL(IP10_14_12, CAN0_TX_E, SEL_CAN0_4),
 	PINMUX_IPSR_MSEL(IP10_14_12, HTX1_D, SEL_HSCIF1_3),
 	PINMUX_IPSR_MSEL(IP10_14_12, SCIFB0_TXD_D, SEL_SCIFB_3),
-	PINMUX_IPSR_DATA(IP10_16_15, VI0_G6),
-	PINMUX_IPSR_DATA(IP10_16_15, VI2_CLK),
+	PINMUX_IPSR_GPSR(IP10_16_15, VI0_G6),
+	PINMUX_IPSR_GPSR(IP10_16_15, VI2_CLK),
 	PINMUX_IPSR_MSEL(IP10_16_15, BPFCLK_D, SEL_FM_3),
-	PINMUX_IPSR_DATA(IP10_18_17, VI0_G7),
-	PINMUX_IPSR_DATA(IP10_18_17, VI2_DATA0),
+	PINMUX_IPSR_GPSR(IP10_18_17, VI0_G7),
+	PINMUX_IPSR_GPSR(IP10_18_17, VI2_DATA0),
 	PINMUX_IPSR_MSEL(IP10_18_17, FMIN_D, SEL_FM_3),
-	PINMUX_IPSR_DATA(IP10_21_19, VI0_R0),
-	PINMUX_IPSR_DATA(IP10_21_19, VI2_DATA1),
+	PINMUX_IPSR_GPSR(IP10_21_19, VI0_R0),
+	PINMUX_IPSR_GPSR(IP10_21_19, VI2_DATA1),
 	PINMUX_IPSR_MSEL(IP10_21_19, GLO_I0_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP10_21_19, TS_SDATA0_C, SEL_TSIF0_2),
-	PINMUX_IPSR_DATA(IP10_21_19, ATACS11_N),
-	PINMUX_IPSR_DATA(IP10_24_22, VI0_R1),
-	PINMUX_IPSR_DATA(IP10_24_22, VI2_DATA2),
+	PINMUX_IPSR_GPSR(IP10_21_19, ATACS11_N),
+	PINMUX_IPSR_GPSR(IP10_24_22, VI0_R1),
+	PINMUX_IPSR_GPSR(IP10_24_22, VI2_DATA2),
 	PINMUX_IPSR_MSEL(IP10_24_22, GLO_I1_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP10_24_22, TS_SCK0_C, SEL_TSIF0_2),
-	PINMUX_IPSR_DATA(IP10_24_22, ATAG1_N),
-	PINMUX_IPSR_DATA(IP10_26_25, VI0_R2),
-	PINMUX_IPSR_DATA(IP10_26_25, VI2_DATA3),
+	PINMUX_IPSR_GPSR(IP10_24_22, ATAG1_N),
+	PINMUX_IPSR_GPSR(IP10_26_25, VI0_R2),
+	PINMUX_IPSR_GPSR(IP10_26_25, VI2_DATA3),
 	PINMUX_IPSR_MSEL(IP10_26_25, GLO_Q0_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP10_26_25, TS_SDEN0_C, SEL_TSIF0_2),
-	PINMUX_IPSR_DATA(IP10_28_27, VI0_R3),
-	PINMUX_IPSR_DATA(IP10_28_27, VI2_DATA4),
+	PINMUX_IPSR_GPSR(IP10_28_27, VI0_R3),
+	PINMUX_IPSR_GPSR(IP10_28_27, VI2_DATA4),
 	PINMUX_IPSR_MSEL(IP10_28_27, GLO_Q1_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP10_28_27, TS_SPSYNC0_C, SEL_TSIF0_2),
-	PINMUX_IPSR_DATA(IP10_31_29, VI0_R4),
-	PINMUX_IPSR_DATA(IP10_31_29, VI2_DATA5),
+	PINMUX_IPSR_GPSR(IP10_31_29, VI0_R4),
+	PINMUX_IPSR_GPSR(IP10_31_29, VI2_DATA5),
 	PINMUX_IPSR_MSEL(IP10_31_29, GLO_SCLK_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP10_31_29, TX0_C, SEL_SCIF0_2),
 	PINMUX_IPSR_MSEL(IP10_31_29, SCL1_D, SEL_IIC1_3),
 
 	/* IPSR11 */
-	PINMUX_IPSR_DATA(IP11_2_0, VI0_R5),
-	PINMUX_IPSR_DATA(IP11_2_0, VI2_DATA6),
+	PINMUX_IPSR_GPSR(IP11_2_0, VI0_R5),
+	PINMUX_IPSR_GPSR(IP11_2_0, VI2_DATA6),
 	PINMUX_IPSR_MSEL(IP11_2_0, GLO_SDATA_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP11_2_0, RX0_C, SEL_SCIF0_2),
 	PINMUX_IPSR_MSEL(IP11_2_0, SDA1_D, SEL_IIC1_3),
-	PINMUX_IPSR_DATA(IP11_5_3, VI0_R6),
-	PINMUX_IPSR_DATA(IP11_5_3, VI2_DATA7),
+	PINMUX_IPSR_GPSR(IP11_5_3, VI0_R6),
+	PINMUX_IPSR_GPSR(IP11_5_3, VI2_DATA7),
 	PINMUX_IPSR_MSEL(IP11_5_3, GLO_SS_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP11_5_3, TX1_C, SEL_SCIF1_2),
 	PINMUX_IPSR_MSEL(IP11_5_3, SCL4_B, SEL_IIC4_1),
-	PINMUX_IPSR_DATA(IP11_8_6, VI0_R7),
+	PINMUX_IPSR_GPSR(IP11_8_6, VI0_R7),
 	PINMUX_IPSR_MSEL(IP11_8_6, GLO_RFON_B, SEL_GPS_1),
 	PINMUX_IPSR_MSEL(IP11_8_6, RX1_C, SEL_SCIF1_2),
 	PINMUX_IPSR_MSEL(IP11_8_6, CAN0_RX_E, SEL_CAN0_4),
@@ -1388,180 +1388,180 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP11_8_6, HRX1_D, SEL_HSCIF1_3),
 	PINMUX_IPSR_MSEL(IP11_8_6, SCIFB0_RXD_D, SEL_SCIFB_3),
 	PINMUX_IPSR_MSEL(IP11_11_9, VI1_HSYNC_N, SEL_VI1_0),
-	PINMUX_IPSR_DATA(IP11_11_9, AVB_RXD0),
+	PINMUX_IPSR_GPSR(IP11_11_9, AVB_RXD0),
 	PINMUX_IPSR_MSEL(IP11_11_9, TS_SDATA0_B, SEL_TSIF0_1),
 	PINMUX_IPSR_MSEL(IP11_11_9, TX4_B, SEL_SCIF4_1),
 	PINMUX_IPSR_MSEL(IP11_11_9, SCIFA4_TXD_B, SEL_SCIFA4_1),
 	PINMUX_IPSR_MSEL(IP11_14_12, VI1_VSYNC_N, SEL_VI1_0),
-	PINMUX_IPSR_DATA(IP11_14_12, AVB_RXD1),
+	PINMUX_IPSR_GPSR(IP11_14_12, AVB_RXD1),
 	PINMUX_IPSR_MSEL(IP11_14_12, TS_SCK0_B, SEL_TSIF0_1),
 	PINMUX_IPSR_MSEL(IP11_14_12, RX4_B, SEL_SCIF4_1),
 	PINMUX_IPSR_MSEL(IP11_14_12, SCIFA4_RXD_B, SEL_SCIFA4_1),
 	PINMUX_IPSR_MSEL(IP11_16_15, VI1_CLKENB, SEL_VI1_0),
-	PINMUX_IPSR_DATA(IP11_16_15, AVB_RXD2),
+	PINMUX_IPSR_GPSR(IP11_16_15, AVB_RXD2),
 	PINMUX_IPSR_MSEL(IP11_16_15, TS_SDEN0_B, SEL_TSIF0_1),
 	PINMUX_IPSR_MSEL(IP11_18_17, VI1_FIELD, SEL_VI1_0),
-	PINMUX_IPSR_DATA(IP11_18_17, AVB_RXD3),
+	PINMUX_IPSR_GPSR(IP11_18_17, AVB_RXD3),
 	PINMUX_IPSR_MSEL(IP11_18_17, TS_SPSYNC0_B, SEL_TSIF0_1),
 	PINMUX_IPSR_MSEL(IP11_19, VI1_CLK, SEL_VI1_0),
-	PINMUX_IPSR_DATA(IP11_19, AVB_RXD4),
+	PINMUX_IPSR_GPSR(IP11_19, AVB_RXD4),
 	PINMUX_IPSR_MSEL(IP11_20, VI1_DATA0, SEL_VI1_0),
-	PINMUX_IPSR_DATA(IP11_20, AVB_RXD5),
+	PINMUX_IPSR_GPSR(IP11_20, AVB_RXD5),
 	PINMUX_IPSR_MSEL(IP11_21, VI1_DATA1, SEL_VI1_0),
-	PINMUX_IPSR_DATA(IP11_21, AVB_RXD6),
+	PINMUX_IPSR_GPSR(IP11_21, AVB_RXD6),
 	PINMUX_IPSR_MSEL(IP11_22, VI1_DATA2, SEL_VI1_0),
-	PINMUX_IPSR_DATA(IP11_22, AVB_RXD7),
+	PINMUX_IPSR_GPSR(IP11_22, AVB_RXD7),
 	PINMUX_IPSR_MSEL(IP11_23, VI1_DATA3, SEL_VI1_0),
-	PINMUX_IPSR_DATA(IP11_23, AVB_RX_ER),
+	PINMUX_IPSR_GPSR(IP11_23, AVB_RX_ER),
 	PINMUX_IPSR_MSEL(IP11_24, VI1_DATA4, SEL_VI1_0),
-	PINMUX_IPSR_DATA(IP11_24, AVB_MDIO),
+	PINMUX_IPSR_GPSR(IP11_24, AVB_MDIO),
 	PINMUX_IPSR_MSEL(IP11_25, VI1_DATA5, SEL_VI1_0),
-	PINMUX_IPSR_DATA(IP11_25, AVB_RX_DV),
+	PINMUX_IPSR_GPSR(IP11_25, AVB_RX_DV),
 	PINMUX_IPSR_MSEL(IP11_26, VI1_DATA6, SEL_VI1_0),
-	PINMUX_IPSR_DATA(IP11_26, AVB_MAGIC),
+	PINMUX_IPSR_GPSR(IP11_26, AVB_MAGIC),
 	PINMUX_IPSR_MSEL(IP11_27, VI1_DATA7, SEL_VI1_0),
-	PINMUX_IPSR_DATA(IP11_27, AVB_MDC),
-	PINMUX_IPSR_DATA(IP11_29_28, ETH_MDIO),
-	PINMUX_IPSR_DATA(IP11_29_28, AVB_RX_CLK),
+	PINMUX_IPSR_GPSR(IP11_27, AVB_MDC),
+	PINMUX_IPSR_GPSR(IP11_29_28, ETH_MDIO),
+	PINMUX_IPSR_GPSR(IP11_29_28, AVB_RX_CLK),
 	PINMUX_IPSR_MSEL(IP11_29_28, SCL2_C, SEL_IIC2_2),
-	PINMUX_IPSR_DATA(IP11_31_30, ETH_CRS_DV),
-	PINMUX_IPSR_DATA(IP11_31_30, AVB_LINK),
+	PINMUX_IPSR_GPSR(IP11_31_30, ETH_CRS_DV),
+	PINMUX_IPSR_GPSR(IP11_31_30, AVB_LINK),
 	PINMUX_IPSR_MSEL(IP11_31_30, SDA2_C, SEL_IIC2_2),
 
 	/* IPSR12 */
-	PINMUX_IPSR_DATA(IP12_1_0, ETH_RX_ER),
-	PINMUX_IPSR_DATA(IP12_1_0, AVB_CRS),
+	PINMUX_IPSR_GPSR(IP12_1_0, ETH_RX_ER),
+	PINMUX_IPSR_GPSR(IP12_1_0, AVB_CRS),
 	PINMUX_IPSR_MSEL(IP12_1_0, SCL3, SEL_IIC3_0),
 	PINMUX_IPSR_MSEL(IP12_1_0, SCL7, SEL_IIC7_0),
-	PINMUX_IPSR_DATA(IP12_3_2, ETH_RXD0),
-	PINMUX_IPSR_DATA(IP12_3_2, AVB_PHY_INT),
+	PINMUX_IPSR_GPSR(IP12_3_2, ETH_RXD0),
+	PINMUX_IPSR_GPSR(IP12_3_2, AVB_PHY_INT),
 	PINMUX_IPSR_MSEL(IP12_3_2, SDA3, SEL_IIC3_0),
 	PINMUX_IPSR_MSEL(IP12_3_2, SDA7, SEL_IIC7_0),
-	PINMUX_IPSR_DATA(IP12_6_4, ETH_RXD1),
-	PINMUX_IPSR_DATA(IP12_6_4, AVB_GTXREFCLK),
+	PINMUX_IPSR_GPSR(IP12_6_4, ETH_RXD1),
+	PINMUX_IPSR_GPSR(IP12_6_4, AVB_GTXREFCLK),
 	PINMUX_IPSR_MSEL(IP12_6_4, CAN0_TX_C, SEL_CAN0_2),
 	PINMUX_IPSR_MSEL(IP12_6_4, SCL2_D, SEL_IIC2_3),
 	PINMUX_IPSR_MSEL(IP12_6_4, MSIOF1_RXD_E, SEL_SOF1_4),
-	PINMUX_IPSR_DATA(IP12_9_7, ETH_LINK),
-	PINMUX_IPSR_DATA(IP12_9_7, AVB_TXD0),
+	PINMUX_IPSR_GPSR(IP12_9_7, ETH_LINK),
+	PINMUX_IPSR_GPSR(IP12_9_7, AVB_TXD0),
 	PINMUX_IPSR_MSEL(IP12_9_7, CAN0_RX_C, SEL_CAN0_2),
 	PINMUX_IPSR_MSEL(IP12_9_7, SDA2_D, SEL_IIC2_3),
 	PINMUX_IPSR_MSEL(IP12_9_7, MSIOF1_SCK_E, SEL_SOF1_4),
-	PINMUX_IPSR_DATA(IP12_12_10, ETH_REFCLK),
-	PINMUX_IPSR_DATA(IP12_12_10, AVB_TXD1),
+	PINMUX_IPSR_GPSR(IP12_12_10, ETH_REFCLK),
+	PINMUX_IPSR_GPSR(IP12_12_10, AVB_TXD1),
 	PINMUX_IPSR_MSEL(IP12_12_10, SCIFA3_RXD_B, SEL_SCIFA3_1),
 	PINMUX_IPSR_MSEL(IP12_12_10, CAN1_RX_C, SEL_CAN1_2),
 	PINMUX_IPSR_MSEL(IP12_12_10, MSIOF1_SYNC_E, SEL_SOF1_4),
-	PINMUX_IPSR_DATA(IP12_15_13, ETH_TXD1),
-	PINMUX_IPSR_DATA(IP12_15_13, AVB_TXD2),
+	PINMUX_IPSR_GPSR(IP12_15_13, ETH_TXD1),
+	PINMUX_IPSR_GPSR(IP12_15_13, AVB_TXD2),
 	PINMUX_IPSR_MSEL(IP12_15_13, SCIFA3_TXD_B, SEL_SCIFA3_1),
 	PINMUX_IPSR_MSEL(IP12_15_13, CAN1_TX_C, SEL_CAN1_2),
 	PINMUX_IPSR_MSEL(IP12_15_13, MSIOF1_TXD_E, SEL_SOF1_4),
-	PINMUX_IPSR_DATA(IP12_17_16, ETH_TX_EN),
-	PINMUX_IPSR_DATA(IP12_17_16, AVB_TXD3),
+	PINMUX_IPSR_GPSR(IP12_17_16, ETH_TX_EN),
+	PINMUX_IPSR_GPSR(IP12_17_16, AVB_TXD3),
 	PINMUX_IPSR_MSEL(IP12_17_16, TCLK1_B, SEL_TMU1_0),
 	PINMUX_IPSR_MSEL(IP12_17_16, CAN_CLK_B, SEL_CANCLK_1),
-	PINMUX_IPSR_DATA(IP12_19_18, ETH_MAGIC),
-	PINMUX_IPSR_DATA(IP12_19_18, AVB_TXD4),
+	PINMUX_IPSR_GPSR(IP12_19_18, ETH_MAGIC),
+	PINMUX_IPSR_GPSR(IP12_19_18, AVB_TXD4),
 	PINMUX_IPSR_MSEL(IP12_19_18, IETX_C, SEL_IEB_2),
-	PINMUX_IPSR_DATA(IP12_21_20, ETH_TXD0),
-	PINMUX_IPSR_DATA(IP12_21_20, AVB_TXD5),
+	PINMUX_IPSR_GPSR(IP12_21_20, ETH_TXD0),
+	PINMUX_IPSR_GPSR(IP12_21_20, AVB_TXD5),
 	PINMUX_IPSR_MSEL(IP12_21_20, IECLK_C, SEL_IEB_2),
-	PINMUX_IPSR_DATA(IP12_23_22, ETH_MDC),
-	PINMUX_IPSR_DATA(IP12_23_22, AVB_TXD6),
+	PINMUX_IPSR_GPSR(IP12_23_22, ETH_MDC),
+	PINMUX_IPSR_GPSR(IP12_23_22, AVB_TXD6),
 	PINMUX_IPSR_MSEL(IP12_23_22, IERX_C, SEL_IEB_2),
 	PINMUX_IPSR_MSEL(IP12_26_24, STP_IVCXO27_0, SEL_SSP_0),
-	PINMUX_IPSR_DATA(IP12_26_24, AVB_TXD7),
+	PINMUX_IPSR_GPSR(IP12_26_24, AVB_TXD7),
 	PINMUX_IPSR_MSEL(IP12_26_24, SCIFB2_TXD_D, SEL_SCIFB2_3),
 	PINMUX_IPSR_MSEL(IP12_26_24, ADIDATA_B, SEL_RAD_1),
 	PINMUX_IPSR_MSEL(IP12_26_24, MSIOF0_SYNC_C, SEL_SOF0_2),
 	PINMUX_IPSR_MSEL(IP12_29_27, STP_ISCLK_0, SEL_SSP_0),
-	PINMUX_IPSR_DATA(IP12_29_27, AVB_TX_EN),
+	PINMUX_IPSR_GPSR(IP12_29_27, AVB_TX_EN),
 	PINMUX_IPSR_MSEL(IP12_29_27, SCIFB2_RXD_D, SEL_SCIFB2_3),
 	PINMUX_IPSR_MSEL(IP12_29_27, ADICS_SAMP_B, SEL_RAD_1),
 	PINMUX_IPSR_MSEL(IP12_29_27, MSIOF0_SCK_C, SEL_SOF0_2),
 
 	/* IPSR13 */
 	PINMUX_IPSR_MSEL(IP13_2_0, STP_ISD_0, SEL_SSP_0),
-	PINMUX_IPSR_DATA(IP13_2_0, AVB_TX_ER),
+	PINMUX_IPSR_GPSR(IP13_2_0, AVB_TX_ER),
 	PINMUX_IPSR_MSEL(IP13_2_0, SCIFB2_SCK_C, SEL_SCIFB2_2),
 	PINMUX_IPSR_MSEL(IP13_2_0, ADICLK_B, SEL_RAD_1),
 	PINMUX_IPSR_MSEL(IP13_2_0, MSIOF0_SS1_C, SEL_SOF0_2),
 	PINMUX_IPSR_MSEL(IP13_4_3, STP_ISEN_0, SEL_SSP_0),
-	PINMUX_IPSR_DATA(IP13_4_3, AVB_TX_CLK),
+	PINMUX_IPSR_GPSR(IP13_4_3, AVB_TX_CLK),
 	PINMUX_IPSR_MSEL(IP13_4_3, ADICHS0_B, SEL_RAD_1),
 	PINMUX_IPSR_MSEL(IP13_4_3, MSIOF0_SS2_C, SEL_SOF0_2),
 	PINMUX_IPSR_MSEL(IP13_6_5, STP_ISSYNC_0, SEL_SSP_0),
-	PINMUX_IPSR_DATA(IP13_6_5, AVB_COL),
+	PINMUX_IPSR_GPSR(IP13_6_5, AVB_COL),
 	PINMUX_IPSR_MSEL(IP13_6_5, ADICHS1_B, SEL_RAD_1),
 	PINMUX_IPSR_MSEL(IP13_6_5, MSIOF0_RXD_C, SEL_SOF0_2),
 	PINMUX_IPSR_MSEL(IP13_9_7, STP_OPWM_0, SEL_SSP_0),
-	PINMUX_IPSR_DATA(IP13_9_7, AVB_GTX_CLK),
-	PINMUX_IPSR_DATA(IP13_9_7, PWM0_B),
+	PINMUX_IPSR_GPSR(IP13_9_7, AVB_GTX_CLK),
+	PINMUX_IPSR_GPSR(IP13_9_7, PWM0_B),
 	PINMUX_IPSR_MSEL(IP13_9_7, ADICHS2_B, SEL_RAD_1),
 	PINMUX_IPSR_MSEL(IP13_9_7, MSIOF0_TXD_C, SEL_SOF0_2),
-	PINMUX_IPSR_DATA(IP13_10, SD0_CLK),
+	PINMUX_IPSR_GPSR(IP13_10, SD0_CLK),
 	PINMUX_IPSR_MSEL(IP13_10, SPCLK_B, SEL_QSP_1),
-	PINMUX_IPSR_DATA(IP13_11, SD0_CMD),
+	PINMUX_IPSR_GPSR(IP13_11, SD0_CMD),
 	PINMUX_IPSR_MSEL(IP13_11, MOSI_IO0_B, SEL_QSP_1),
-	PINMUX_IPSR_DATA(IP13_12, SD0_DATA0),
+	PINMUX_IPSR_GPSR(IP13_12, SD0_DATA0),
 	PINMUX_IPSR_MSEL(IP13_12, MISO_IO1_B, SEL_QSP_1),
-	PINMUX_IPSR_DATA(IP13_13, SD0_DATA1),
+	PINMUX_IPSR_GPSR(IP13_13, SD0_DATA1),
 	PINMUX_IPSR_MSEL(IP13_13, IO2_B, SEL_QSP_1),
-	PINMUX_IPSR_DATA(IP13_14, SD0_DATA2),
+	PINMUX_IPSR_GPSR(IP13_14, SD0_DATA2),
 	PINMUX_IPSR_MSEL(IP13_14, IO3_B, SEL_QSP_1),
-	PINMUX_IPSR_DATA(IP13_15, SD0_DATA3),
+	PINMUX_IPSR_GPSR(IP13_15, SD0_DATA3),
 	PINMUX_IPSR_MSEL(IP13_15, SSL_B, SEL_QSP_1),
-	PINMUX_IPSR_DATA(IP13_18_16, SD0_CD),
+	PINMUX_IPSR_GPSR(IP13_18_16, SD0_CD),
 	PINMUX_IPSR_MSEL(IP13_18_16, MMC_D6_B, SEL_MMC_1),
 	PINMUX_IPSR_MSEL(IP13_18_16, SIM0_RST_B, SEL_SIM_1),
 	PINMUX_IPSR_MSEL(IP13_18_16, CAN0_RX_F, SEL_CAN0_5),
 	PINMUX_IPSR_MSEL(IP13_18_16, SCIFA5_TXD_B, SEL_SCIFA5_1),
 	PINMUX_IPSR_MSEL(IP13_18_16, TX3_C, SEL_SCIF3_2),
-	PINMUX_IPSR_DATA(IP13_21_19, SD0_WP),
+	PINMUX_IPSR_GPSR(IP13_21_19, SD0_WP),
 	PINMUX_IPSR_MSEL(IP13_21_19, MMC_D7_B, SEL_MMC_1),
 	PINMUX_IPSR_MSEL(IP13_21_19, SIM0_D_B, SEL_SIM_1),
 	PINMUX_IPSR_MSEL(IP13_21_19, CAN0_TX_F, SEL_CAN0_5),
 	PINMUX_IPSR_MSEL(IP13_21_19, SCIFA5_RXD_B, SEL_SCIFA5_1),
 	PINMUX_IPSR_MSEL(IP13_21_19, RX3_C, SEL_SCIF3_2),
-	PINMUX_IPSR_DATA(IP13_22, SD1_CMD),
+	PINMUX_IPSR_GPSR(IP13_22, SD1_CMD),
 	PINMUX_IPSR_MSEL(IP13_22, REMOCON_B, SEL_RCN_1),
-	PINMUX_IPSR_DATA(IP13_24_23, SD1_DATA0),
+	PINMUX_IPSR_GPSR(IP13_24_23, SD1_DATA0),
 	PINMUX_IPSR_MSEL(IP13_24_23, SPEEDIN_B, SEL_RSP_1),
-	PINMUX_IPSR_DATA(IP13_25, SD1_DATA1),
+	PINMUX_IPSR_GPSR(IP13_25, SD1_DATA1),
 	PINMUX_IPSR_MSEL(IP13_25, IETX_B, SEL_IEB_1),
-	PINMUX_IPSR_DATA(IP13_26, SD1_DATA2),
+	PINMUX_IPSR_GPSR(IP13_26, SD1_DATA2),
 	PINMUX_IPSR_MSEL(IP13_26, IECLK_B, SEL_IEB_1),
-	PINMUX_IPSR_DATA(IP13_27, SD1_DATA3),
+	PINMUX_IPSR_GPSR(IP13_27, SD1_DATA3),
 	PINMUX_IPSR_MSEL(IP13_27, IERX_B, SEL_IEB_1),
-	PINMUX_IPSR_DATA(IP13_30_28, SD1_CD),
-	PINMUX_IPSR_DATA(IP13_30_28, PWM0),
-	PINMUX_IPSR_DATA(IP13_30_28, TPU_TO0),
+	PINMUX_IPSR_GPSR(IP13_30_28, SD1_CD),
+	PINMUX_IPSR_GPSR(IP13_30_28, PWM0),
+	PINMUX_IPSR_GPSR(IP13_30_28, TPU_TO0),
 	PINMUX_IPSR_MSEL(IP13_30_28, SCL1_C, SEL_IIC1_2),
 
 	/* IPSR14 */
-	PINMUX_IPSR_DATA(IP14_1_0, SD1_WP),
-	PINMUX_IPSR_DATA(IP14_1_0, PWM1_B),
+	PINMUX_IPSR_GPSR(IP14_1_0, SD1_WP),
+	PINMUX_IPSR_GPSR(IP14_1_0, PWM1_B),
 	PINMUX_IPSR_MSEL(IP14_1_0, SDA1_C, SEL_IIC1_2),
-	PINMUX_IPSR_DATA(IP14_2, SD2_CLK),
-	PINMUX_IPSR_DATA(IP14_2, MMC_CLK),
-	PINMUX_IPSR_DATA(IP14_3, SD2_CMD),
-	PINMUX_IPSR_DATA(IP14_3, MMC_CMD),
-	PINMUX_IPSR_DATA(IP14_4, SD2_DATA0),
-	PINMUX_IPSR_DATA(IP14_4, MMC_D0),
-	PINMUX_IPSR_DATA(IP14_5, SD2_DATA1),
-	PINMUX_IPSR_DATA(IP14_5, MMC_D1),
-	PINMUX_IPSR_DATA(IP14_6, SD2_DATA2),
-	PINMUX_IPSR_DATA(IP14_6, MMC_D2),
-	PINMUX_IPSR_DATA(IP14_7, SD2_DATA3),
-	PINMUX_IPSR_DATA(IP14_7, MMC_D3),
-	PINMUX_IPSR_DATA(IP14_10_8, SD2_CD),
-	PINMUX_IPSR_DATA(IP14_10_8, MMC_D4),
+	PINMUX_IPSR_GPSR(IP14_2, SD2_CLK),
+	PINMUX_IPSR_GPSR(IP14_2, MMC_CLK),
+	PINMUX_IPSR_GPSR(IP14_3, SD2_CMD),
+	PINMUX_IPSR_GPSR(IP14_3, MMC_CMD),
+	PINMUX_IPSR_GPSR(IP14_4, SD2_DATA0),
+	PINMUX_IPSR_GPSR(IP14_4, MMC_D0),
+	PINMUX_IPSR_GPSR(IP14_5, SD2_DATA1),
+	PINMUX_IPSR_GPSR(IP14_5, MMC_D1),
+	PINMUX_IPSR_GPSR(IP14_6, SD2_DATA2),
+	PINMUX_IPSR_GPSR(IP14_6, MMC_D2),
+	PINMUX_IPSR_GPSR(IP14_7, SD2_DATA3),
+	PINMUX_IPSR_GPSR(IP14_7, MMC_D3),
+	PINMUX_IPSR_GPSR(IP14_10_8, SD2_CD),
+	PINMUX_IPSR_GPSR(IP14_10_8, MMC_D4),
 	PINMUX_IPSR_MSEL(IP14_10_8, SCL8_C, SEL_IIC8_2),
 	PINMUX_IPSR_MSEL(IP14_10_8, TX5_B, SEL_SCIF5_1),
 	PINMUX_IPSR_MSEL(IP14_10_8, SCIFA5_TXD_C, SEL_SCIFA5_2),
-	PINMUX_IPSR_DATA(IP14_13_11, SD2_WP),
-	PINMUX_IPSR_DATA(IP14_13_11, MMC_D5),
+	PINMUX_IPSR_GPSR(IP14_13_11, SD2_WP),
+	PINMUX_IPSR_GPSR(IP14_13_11, MMC_D5),
 	PINMUX_IPSR_MSEL(IP14_13_11, SDA8_C, SEL_IIC8_2),
 	PINMUX_IPSR_MSEL(IP14_13_11, RX5_B, SEL_SCIF5_1),
 	PINMUX_IPSR_MSEL(IP14_13_11, SCIFA5_RXD_C, SEL_SCIFA5_2),
@@ -1569,40 +1569,40 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP14_16_14, RX2_C, SEL_SCIF2_2),
 	PINMUX_IPSR_MSEL(IP14_16_14, ADIDATA, SEL_RAD_0),
 	PINMUX_IPSR_MSEL(IP14_16_14, VI1_CLK_C, SEL_VI1_2),
-	PINMUX_IPSR_DATA(IP14_16_14, VI1_G0_B),
+	PINMUX_IPSR_GPSR(IP14_16_14, VI1_G0_B),
 	PINMUX_IPSR_MSEL(IP14_19_17, MSIOF0_SYNC, SEL_SOF0_0),
 	PINMUX_IPSR_MSEL(IP14_19_17, TX2_C, SEL_SCIF2_2),
 	PINMUX_IPSR_MSEL(IP14_19_17, ADICS_SAMP, SEL_RAD_0),
 	PINMUX_IPSR_MSEL(IP14_19_17, VI1_CLKENB_C, SEL_VI1_2),
-	PINMUX_IPSR_DATA(IP14_19_17, VI1_G1_B),
+	PINMUX_IPSR_GPSR(IP14_19_17, VI1_G1_B),
 	PINMUX_IPSR_MSEL(IP14_22_20, MSIOF0_TXD, SEL_SOF0_0),
 	PINMUX_IPSR_MSEL(IP14_22_20, ADICLK, SEL_RAD_0),
 	PINMUX_IPSR_MSEL(IP14_22_20, VI1_FIELD_C, SEL_VI1_2),
-	PINMUX_IPSR_DATA(IP14_22_20, VI1_G2_B),
+	PINMUX_IPSR_GPSR(IP14_22_20, VI1_G2_B),
 	PINMUX_IPSR_MSEL(IP14_25_23, MSIOF0_RXD, SEL_SOF0_0),
 	PINMUX_IPSR_MSEL(IP14_25_23, ADICHS0, SEL_RAD_0),
 	PINMUX_IPSR_MSEL(IP14_25_23, VI1_DATA0_C, SEL_VI1_2),
-	PINMUX_IPSR_DATA(IP14_25_23, VI1_G3_B),
+	PINMUX_IPSR_GPSR(IP14_25_23, VI1_G3_B),
 	PINMUX_IPSR_MSEL(IP14_28_26, MSIOF0_SS1, SEL_SOF0_0),
 	PINMUX_IPSR_MSEL(IP14_28_26, MMC_D6, SEL_MMC_0),
 	PINMUX_IPSR_MSEL(IP14_28_26, ADICHS1, SEL_RAD_0),
 	PINMUX_IPSR_MSEL(IP14_28_26, TX0_E, SEL_SCIF0_4),
 	PINMUX_IPSR_MSEL(IP14_28_26, VI1_HSYNC_N_C, SEL_VI1_2),
 	PINMUX_IPSR_MSEL(IP14_28_26, SCL7_C, SEL_IIC7_2),
-	PINMUX_IPSR_DATA(IP14_28_26, VI1_G4_B),
+	PINMUX_IPSR_GPSR(IP14_28_26, VI1_G4_B),
 	PINMUX_IPSR_MSEL(IP14_31_29, MSIOF0_SS2, SEL_SOF0_0),
 	PINMUX_IPSR_MSEL(IP14_31_29, MMC_D7, SEL_MMC_0),
 	PINMUX_IPSR_MSEL(IP14_31_29, ADICHS2, SEL_RAD_0),
 	PINMUX_IPSR_MSEL(IP14_31_29, RX0_E, SEL_SCIF0_4),
 	PINMUX_IPSR_MSEL(IP14_31_29, VI1_VSYNC_N_C, SEL_VI1_2),
 	PINMUX_IPSR_MSEL(IP14_31_29, SDA7_C, SEL_IIC7_2),
-	PINMUX_IPSR_DATA(IP14_31_29, VI1_G5_B),
+	PINMUX_IPSR_GPSR(IP14_31_29, VI1_G5_B),
 
 	/* IPSR15 */
 	PINMUX_IPSR_MSEL(IP15_1_0, SIM0_RST, SEL_SIM_0),
 	PINMUX_IPSR_MSEL(IP15_1_0, IETX, SEL_IEB_0),
 	PINMUX_IPSR_MSEL(IP15_1_0, CAN1_TX_D, SEL_CAN1_3),
-	PINMUX_IPSR_DATA(IP15_3_2, SIM0_CLK),
+	PINMUX_IPSR_GPSR(IP15_3_2, SIM0_CLK),
 	PINMUX_IPSR_MSEL(IP15_3_2, IECLK, SEL_IEB_0),
 	PINMUX_IPSR_MSEL(IP15_3_2, CAN_CLK_C, SEL_CANCLK_2),
 	PINMUX_IPSR_MSEL(IP15_5_4, SIM0_D, SEL_SIM_0),
@@ -1611,19 +1611,19 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP15_8_6, GPS_CLK, SEL_GPS_0),
 	PINMUX_IPSR_MSEL(IP15_8_6, DU1_DOTCLKIN_C, SEL_DIS_2),
 	PINMUX_IPSR_MSEL(IP15_8_6, AUDIO_CLKB_B, SEL_ADG_1),
-	PINMUX_IPSR_DATA(IP15_8_6, PWM5_B),
+	PINMUX_IPSR_GPSR(IP15_8_6, PWM5_B),
 	PINMUX_IPSR_MSEL(IP15_8_6, SCIFA3_TXD_C, SEL_SCIFA3_2),
 	PINMUX_IPSR_MSEL(IP15_11_9, GPS_SIGN, SEL_GPS_0),
 	PINMUX_IPSR_MSEL(IP15_11_9, TX4_C, SEL_SCIF4_2),
 	PINMUX_IPSR_MSEL(IP15_11_9, SCIFA4_TXD_C, SEL_SCIFA4_2),
-	PINMUX_IPSR_DATA(IP15_11_9, PWM5),
-	PINMUX_IPSR_DATA(IP15_11_9, VI1_G6_B),
+	PINMUX_IPSR_GPSR(IP15_11_9, PWM5),
+	PINMUX_IPSR_GPSR(IP15_11_9, VI1_G6_B),
 	PINMUX_IPSR_MSEL(IP15_11_9, SCIFA3_RXD_C, SEL_SCIFA3_2),
 	PINMUX_IPSR_MSEL(IP15_14_12, GPS_MAG, SEL_GPS_0),
 	PINMUX_IPSR_MSEL(IP15_14_12, RX4_C, SEL_SCIF4_2),
 	PINMUX_IPSR_MSEL(IP15_14_12, SCIFA4_RXD_C, SEL_SCIFA4_2),
-	PINMUX_IPSR_DATA(IP15_14_12, PWM6),
-	PINMUX_IPSR_DATA(IP15_14_12, VI1_G7_B),
+	PINMUX_IPSR_GPSR(IP15_14_12, PWM6),
+	PINMUX_IPSR_GPSR(IP15_14_12, VI1_G7_B),
 	PINMUX_IPSR_MSEL(IP15_14_12, SCIFA3_SCK_C, SEL_SCIFA3_2),
 	PINMUX_IPSR_MSEL(IP15_17_15, HCTS0_N, SEL_HSCIF0_0),
 	PINMUX_IPSR_MSEL(IP15_17_15, SCIFB0_CTS_N, SEL_SCIFB_0),
@@ -1638,7 +1638,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP15_23_21, SCIFB0_SCK, SEL_SCIFB_0),
 	PINMUX_IPSR_MSEL(IP15_23_21, GLO_Q0_C, SEL_GPS_2),
 	PINMUX_IPSR_MSEL(IP15_23_21, CAN_CLK, SEL_CANCLK_0),
-	PINMUX_IPSR_DATA(IP15_23_21, TCLK2),
+	PINMUX_IPSR_GPSR(IP15_23_21, TCLK2),
 	PINMUX_IPSR_MSEL(IP15_23_21, VI1_DATA3_C, SEL_VI1_2),
 	PINMUX_IPSR_MSEL(IP15_26_24, HRX0, SEL_HSCIF0_0),
 	PINMUX_IPSR_MSEL(IP15_26_24, SCIFB0_RXD, SEL_SCIFB_0),
@@ -1654,25 +1654,25 @@ static const u16 pinmux_data[] = {
 	/* IPSR16 */
 	PINMUX_IPSR_MSEL(IP16_2_0, HRX1, SEL_HSCIF1_0),
 	PINMUX_IPSR_MSEL(IP16_2_0, SCIFB1_RXD, SEL_SCIFB1_0),
-	PINMUX_IPSR_DATA(IP16_2_0, VI1_R0_B),
+	PINMUX_IPSR_GPSR(IP16_2_0, VI1_R0_B),
 	PINMUX_IPSR_MSEL(IP16_2_0, GLO_SDATA_C, SEL_GPS_2),
 	PINMUX_IPSR_MSEL(IP16_2_0, VI1_DATA6_C, SEL_VI1_2),
 	PINMUX_IPSR_MSEL(IP16_5_3, HTX1, SEL_HSCIF1_0),
 	PINMUX_IPSR_MSEL(IP16_5_3, SCIFB1_TXD, SEL_SCIFB1_0),
-	PINMUX_IPSR_DATA(IP16_5_3, VI1_R1_B),
+	PINMUX_IPSR_GPSR(IP16_5_3, VI1_R1_B),
 	PINMUX_IPSR_MSEL(IP16_5_3, GLO_SS_C, SEL_GPS_2),
 	PINMUX_IPSR_MSEL(IP16_5_3, VI1_DATA7_C, SEL_VI1_2),
 	PINMUX_IPSR_MSEL(IP16_7_6, HSCK1, SEL_HSCIF1_0),
 	PINMUX_IPSR_MSEL(IP16_7_6, SCIFB1_SCK, SEL_SCIFB1_0),
-	PINMUX_IPSR_DATA(IP16_7_6, MLB_CLK),
+	PINMUX_IPSR_GPSR(IP16_7_6, MLB_CLK),
 	PINMUX_IPSR_MSEL(IP16_7_6, GLO_RFON_C, SEL_GPS_2),
 	PINMUX_IPSR_MSEL(IP16_9_8, HCTS1_N, SEL_HSCIF1_0),
-	PINMUX_IPSR_DATA(IP16_9_8, SCIFB1_CTS_N),
-	PINMUX_IPSR_DATA(IP16_9_8, MLB_SIG),
+	PINMUX_IPSR_GPSR(IP16_9_8, SCIFB1_CTS_N),
+	PINMUX_IPSR_GPSR(IP16_9_8, MLB_SIG),
 	PINMUX_IPSR_MSEL(IP16_9_8, CAN1_TX_B, SEL_CAN1_1),
 	PINMUX_IPSR_MSEL(IP16_11_10, HRTS1_N, SEL_HSCIF1_0),
-	PINMUX_IPSR_DATA(IP16_11_10, SCIFB1_RTS_N),
-	PINMUX_IPSR_DATA(IP16_11_10, MLB_DAT),
+	PINMUX_IPSR_GPSR(IP16_11_10, SCIFB1_RTS_N),
+	PINMUX_IPSR_GPSR(IP16_11_10, MLB_DAT),
 	PINMUX_IPSR_MSEL(IP16_11_10, CAN1_RX_B, SEL_CAN1_1),
 };
 
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7794.c b/drivers/pinctrl/sh-pfc/pfc-r8a7794.c
index 3718c7846bfd..38912cff597b 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7794.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7794.c
@@ -1,9 +1,9 @@
 /*
  * r8a7794 processor support - PFC hardware block.
  *
- * Copyright (C) 2014 Renesas Electronics Corporation
+ * Copyright (C) 2014-2015 Renesas Electronics Corporation
  * Copyright (C) 2015 Renesas Solutions Corp.
- * Copyright (C) 2015 Cogent  Embedded, Inc., <source@cogentembedded.com>
+ * Copyright (C) 2015-2016 Cogent Embedded, Inc., <source@cogentembedded.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2
@@ -623,848 +623,848 @@ static const u16 pinmux_data[] = {
 	PINMUX_SINGLE(SD1_DATA3),
 
 	/* IPSR0 */
-	PINMUX_IPSR_DATA(IP0_0, SD1_CD),
+	PINMUX_IPSR_GPSR(IP0_0, SD1_CD),
 	PINMUX_IPSR_MSEL(IP0_0, CAN0_RX, SEL_CAN0_0),
-	PINMUX_IPSR_DATA(IP0_9_8, SD1_WP),
-	PINMUX_IPSR_DATA(IP0_9_8, IRQ7),
+	PINMUX_IPSR_GPSR(IP0_9_8, SD1_WP),
+	PINMUX_IPSR_GPSR(IP0_9_8, IRQ7),
 	PINMUX_IPSR_MSEL(IP0_9_8, CAN0_TX, SEL_CAN0_0),
-	PINMUX_IPSR_DATA(IP0_10, MMC_CLK),
-	PINMUX_IPSR_DATA(IP0_10, SD2_CLK),
-	PINMUX_IPSR_DATA(IP0_11, MMC_CMD),
-	PINMUX_IPSR_DATA(IP0_11, SD2_CMD),
-	PINMUX_IPSR_DATA(IP0_12, MMC_D0),
-	PINMUX_IPSR_DATA(IP0_12, SD2_DATA0),
-	PINMUX_IPSR_DATA(IP0_13, MMC_D1),
-	PINMUX_IPSR_DATA(IP0_13, SD2_DATA1),
-	PINMUX_IPSR_DATA(IP0_14, MMC_D2),
-	PINMUX_IPSR_DATA(IP0_14, SD2_DATA2),
-	PINMUX_IPSR_DATA(IP0_15, MMC_D3),
-	PINMUX_IPSR_DATA(IP0_15, SD2_DATA3),
-	PINMUX_IPSR_DATA(IP0_16, MMC_D4),
-	PINMUX_IPSR_DATA(IP0_16, SD2_CD),
-	PINMUX_IPSR_DATA(IP0_17, MMC_D5),
-	PINMUX_IPSR_DATA(IP0_17, SD2_WP),
-	PINMUX_IPSR_DATA(IP0_19_18, MMC_D6),
+	PINMUX_IPSR_GPSR(IP0_10, MMC_CLK),
+	PINMUX_IPSR_GPSR(IP0_10, SD2_CLK),
+	PINMUX_IPSR_GPSR(IP0_11, MMC_CMD),
+	PINMUX_IPSR_GPSR(IP0_11, SD2_CMD),
+	PINMUX_IPSR_GPSR(IP0_12, MMC_D0),
+	PINMUX_IPSR_GPSR(IP0_12, SD2_DATA0),
+	PINMUX_IPSR_GPSR(IP0_13, MMC_D1),
+	PINMUX_IPSR_GPSR(IP0_13, SD2_DATA1),
+	PINMUX_IPSR_GPSR(IP0_14, MMC_D2),
+	PINMUX_IPSR_GPSR(IP0_14, SD2_DATA2),
+	PINMUX_IPSR_GPSR(IP0_15, MMC_D3),
+	PINMUX_IPSR_GPSR(IP0_15, SD2_DATA3),
+	PINMUX_IPSR_GPSR(IP0_16, MMC_D4),
+	PINMUX_IPSR_GPSR(IP0_16, SD2_CD),
+	PINMUX_IPSR_GPSR(IP0_17, MMC_D5),
+	PINMUX_IPSR_GPSR(IP0_17, SD2_WP),
+	PINMUX_IPSR_GPSR(IP0_19_18, MMC_D6),
 	PINMUX_IPSR_MSEL(IP0_19_18, SCIF0_RXD, SEL_SCIF0_0),
 	PINMUX_IPSR_MSEL(IP0_19_18, I2C2_SCL_B, SEL_I2C02_1),
 	PINMUX_IPSR_MSEL(IP0_19_18, CAN1_RX, SEL_CAN1_0),
-	PINMUX_IPSR_DATA(IP0_21_20, MMC_D7),
+	PINMUX_IPSR_GPSR(IP0_21_20, MMC_D7),
 	PINMUX_IPSR_MSEL(IP0_21_20, SCIF0_TXD, SEL_SCIF0_0),
 	PINMUX_IPSR_MSEL(IP0_21_20, I2C2_SDA_B, SEL_I2C02_1),
 	PINMUX_IPSR_MSEL(IP0_21_20, CAN1_TX, SEL_CAN1_0),
-	PINMUX_IPSR_DATA(IP0_23_22, D0),
+	PINMUX_IPSR_GPSR(IP0_23_22, D0),
 	PINMUX_IPSR_MSEL(IP0_23_22, SCIFA3_SCK_B, SEL_SCIFA3_1),
-	PINMUX_IPSR_DATA(IP0_23_22, IRQ4),
-	PINMUX_IPSR_DATA(IP0_24, D1),
+	PINMUX_IPSR_GPSR(IP0_23_22, IRQ4),
+	PINMUX_IPSR_GPSR(IP0_24, D1),
 	PINMUX_IPSR_MSEL(IP0_24, SCIFA3_RXD_B, SEL_SCIFA3_1),
-	PINMUX_IPSR_DATA(IP0_25, D2),
+	PINMUX_IPSR_GPSR(IP0_25, D2),
 	PINMUX_IPSR_MSEL(IP0_25, SCIFA3_TXD_B, SEL_SCIFA3_1),
-	PINMUX_IPSR_DATA(IP0_27_26, D3),
+	PINMUX_IPSR_GPSR(IP0_27_26, D3),
 	PINMUX_IPSR_MSEL(IP0_27_26, I2C3_SCL_B, SEL_I2C03_1),
 	PINMUX_IPSR_MSEL(IP0_27_26, SCIF5_RXD_B, SEL_SCIF5_1),
-	PINMUX_IPSR_DATA(IP0_29_28, D4),
+	PINMUX_IPSR_GPSR(IP0_29_28, D4),
 	PINMUX_IPSR_MSEL(IP0_29_28, I2C3_SDA_B, SEL_I2C03_1),
 	PINMUX_IPSR_MSEL(IP0_29_28, SCIF5_TXD_B, SEL_SCIF5_1),
-	PINMUX_IPSR_DATA(IP0_31_30, D5),
+	PINMUX_IPSR_GPSR(IP0_31_30, D5),
 	PINMUX_IPSR_MSEL(IP0_31_30, SCIF4_RXD_B, SEL_SCIF4_1),
 	PINMUX_IPSR_MSEL(IP0_31_30, I2C0_SCL_D, SEL_I2C00_3),
 
 	/* IPSR1 */
-	PINMUX_IPSR_DATA(IP1_1_0, D6),
+	PINMUX_IPSR_GPSR(IP1_1_0, D6),
 	PINMUX_IPSR_MSEL(IP1_1_0, SCIF4_TXD_B, SEL_SCIF4_1),
 	PINMUX_IPSR_MSEL(IP1_1_0, I2C0_SDA_D, SEL_I2C00_3),
-	PINMUX_IPSR_DATA(IP1_3_2, D7),
-	PINMUX_IPSR_DATA(IP1_3_2, IRQ3),
+	PINMUX_IPSR_GPSR(IP1_3_2, D7),
+	PINMUX_IPSR_GPSR(IP1_3_2, IRQ3),
 	PINMUX_IPSR_MSEL(IP1_3_2, TCLK1, SEL_TMU_0),
-	PINMUX_IPSR_DATA(IP1_3_2, PWM6_B),
-	PINMUX_IPSR_DATA(IP1_5_4, D8),
-	PINMUX_IPSR_DATA(IP1_5_4, HSCIF2_HRX),
+	PINMUX_IPSR_GPSR(IP1_3_2, PWM6_B),
+	PINMUX_IPSR_GPSR(IP1_5_4, D8),
+	PINMUX_IPSR_GPSR(IP1_5_4, HSCIF2_HRX),
 	PINMUX_IPSR_MSEL(IP1_5_4, I2C1_SCL_B, SEL_I2C01_1),
-	PINMUX_IPSR_DATA(IP1_7_6, D9),
-	PINMUX_IPSR_DATA(IP1_7_6, HSCIF2_HTX),
+	PINMUX_IPSR_GPSR(IP1_7_6, D9),
+	PINMUX_IPSR_GPSR(IP1_7_6, HSCIF2_HTX),
 	PINMUX_IPSR_MSEL(IP1_7_6, I2C1_SDA_B, SEL_I2C01_1),
-	PINMUX_IPSR_DATA(IP1_10_8, D10),
-	PINMUX_IPSR_DATA(IP1_10_8, HSCIF2_HSCK),
+	PINMUX_IPSR_GPSR(IP1_10_8, D10),
+	PINMUX_IPSR_GPSR(IP1_10_8, HSCIF2_HSCK),
 	PINMUX_IPSR_MSEL(IP1_10_8, SCIF1_SCK_C, SEL_SCIF1_2),
-	PINMUX_IPSR_DATA(IP1_10_8, IRQ6),
-	PINMUX_IPSR_DATA(IP1_10_8, PWM5_C),
-	PINMUX_IPSR_DATA(IP1_12_11, D11),
-	PINMUX_IPSR_DATA(IP1_12_11, HSCIF2_HCTS_N),
+	PINMUX_IPSR_GPSR(IP1_10_8, IRQ6),
+	PINMUX_IPSR_GPSR(IP1_10_8, PWM5_C),
+	PINMUX_IPSR_GPSR(IP1_12_11, D11),
+	PINMUX_IPSR_GPSR(IP1_12_11, HSCIF2_HCTS_N),
 	PINMUX_IPSR_MSEL(IP1_12_11, SCIF1_RXD_C, SEL_SCIF1_2),
 	PINMUX_IPSR_MSEL(IP1_12_11, I2C1_SCL_D, SEL_I2C01_3),
-	PINMUX_IPSR_DATA(IP1_14_13, D12),
-	PINMUX_IPSR_DATA(IP1_14_13, HSCIF2_HRTS_N),
+	PINMUX_IPSR_GPSR(IP1_14_13, D12),
+	PINMUX_IPSR_GPSR(IP1_14_13, HSCIF2_HRTS_N),
 	PINMUX_IPSR_MSEL(IP1_14_13, SCIF1_TXD_C, SEL_SCIF1_2),
 	PINMUX_IPSR_MSEL(IP1_14_13, I2C1_SDA_D, SEL_I2C01_3),
-	PINMUX_IPSR_DATA(IP1_17_15, D13),
+	PINMUX_IPSR_GPSR(IP1_17_15, D13),
 	PINMUX_IPSR_MSEL(IP1_17_15, SCIFA1_SCK, SEL_SCIFA1_0),
-	PINMUX_IPSR_DATA(IP1_17_15, TANS1),
-	PINMUX_IPSR_DATA(IP1_17_15, PWM2_C),
+	PINMUX_IPSR_GPSR(IP1_17_15, TANS1),
+	PINMUX_IPSR_GPSR(IP1_17_15, PWM2_C),
 	PINMUX_IPSR_MSEL(IP1_17_15, TCLK2_B, SEL_TMU_1),
-	PINMUX_IPSR_DATA(IP1_19_18, D14),
+	PINMUX_IPSR_GPSR(IP1_19_18, D14),
 	PINMUX_IPSR_MSEL(IP1_19_18, SCIFA1_RXD, SEL_SCIFA1_0),
 	PINMUX_IPSR_MSEL(IP1_19_18, IIC0_SCL_B, SEL_IIC00_1),
-	PINMUX_IPSR_DATA(IP1_21_20, D15),
+	PINMUX_IPSR_GPSR(IP1_21_20, D15),
 	PINMUX_IPSR_MSEL(IP1_21_20, SCIFA1_TXD, SEL_SCIFA1_0),
 	PINMUX_IPSR_MSEL(IP1_21_20, IIC0_SDA_B, SEL_IIC00_1),
-	PINMUX_IPSR_DATA(IP1_23_22, A0),
-	PINMUX_IPSR_DATA(IP1_23_22, SCIFB1_SCK),
-	PINMUX_IPSR_DATA(IP1_23_22, PWM3_B),
-	PINMUX_IPSR_DATA(IP1_24, A1),
-	PINMUX_IPSR_DATA(IP1_24, SCIFB1_TXD),
-	PINMUX_IPSR_DATA(IP1_26, A3),
-	PINMUX_IPSR_DATA(IP1_26, SCIFB0_SCK),
-	PINMUX_IPSR_DATA(IP1_27, A4),
-	PINMUX_IPSR_DATA(IP1_27, SCIFB0_TXD),
-	PINMUX_IPSR_DATA(IP1_29_28, A5),
-	PINMUX_IPSR_DATA(IP1_29_28, SCIFB0_RXD),
-	PINMUX_IPSR_DATA(IP1_29_28, PWM4_B),
-	PINMUX_IPSR_DATA(IP1_29_28, TPUTO3_C),
-	PINMUX_IPSR_DATA(IP1_31_30, A6),
-	PINMUX_IPSR_DATA(IP1_31_30, SCIFB0_CTS_N),
+	PINMUX_IPSR_GPSR(IP1_23_22, A0),
+	PINMUX_IPSR_GPSR(IP1_23_22, SCIFB1_SCK),
+	PINMUX_IPSR_GPSR(IP1_23_22, PWM3_B),
+	PINMUX_IPSR_GPSR(IP1_24, A1),
+	PINMUX_IPSR_GPSR(IP1_24, SCIFB1_TXD),
+	PINMUX_IPSR_GPSR(IP1_26, A3),
+	PINMUX_IPSR_GPSR(IP1_26, SCIFB0_SCK),
+	PINMUX_IPSR_GPSR(IP1_27, A4),
+	PINMUX_IPSR_GPSR(IP1_27, SCIFB0_TXD),
+	PINMUX_IPSR_GPSR(IP1_29_28, A5),
+	PINMUX_IPSR_GPSR(IP1_29_28, SCIFB0_RXD),
+	PINMUX_IPSR_GPSR(IP1_29_28, PWM4_B),
+	PINMUX_IPSR_GPSR(IP1_29_28, TPUTO3_C),
+	PINMUX_IPSR_GPSR(IP1_31_30, A6),
+	PINMUX_IPSR_GPSR(IP1_31_30, SCIFB0_CTS_N),
 	PINMUX_IPSR_MSEL(IP1_31_30, SCIFA4_RXD_B, SEL_SCIFA4_1),
-	PINMUX_IPSR_DATA(IP1_31_30, TPUTO2_C),
+	PINMUX_IPSR_GPSR(IP1_31_30, TPUTO2_C),
 
 	/* IPSR2 */
-	PINMUX_IPSR_DATA(IP2_1_0, A7),
-	PINMUX_IPSR_DATA(IP2_1_0, SCIFB0_RTS_N),
+	PINMUX_IPSR_GPSR(IP2_1_0, A7),
+	PINMUX_IPSR_GPSR(IP2_1_0, SCIFB0_RTS_N),
 	PINMUX_IPSR_MSEL(IP2_1_0, SCIFA4_TXD_B, SEL_SCIFA4_1),
-	PINMUX_IPSR_DATA(IP2_3_2, A8),
+	PINMUX_IPSR_GPSR(IP2_3_2, A8),
 	PINMUX_IPSR_MSEL(IP2_3_2, MSIOF1_RXD, SEL_MSI1_0),
 	PINMUX_IPSR_MSEL(IP2_3_2, SCIFA0_RXD_B, SEL_SCIFA0_1),
-	PINMUX_IPSR_DATA(IP2_5_4, A9),
+	PINMUX_IPSR_GPSR(IP2_5_4, A9),
 	PINMUX_IPSR_MSEL(IP2_5_4, MSIOF1_TXD, SEL_MSI1_0),
 	PINMUX_IPSR_MSEL(IP2_5_4, SCIFA0_TXD_B, SEL_SCIFA0_1),
-	PINMUX_IPSR_DATA(IP2_7_6, A10),
+	PINMUX_IPSR_GPSR(IP2_7_6, A10),
 	PINMUX_IPSR_MSEL(IP2_7_6, MSIOF1_SCK, SEL_MSI1_0),
 	PINMUX_IPSR_MSEL(IP2_7_6, IIC1_SCL_B, SEL_IIC01_1),
-	PINMUX_IPSR_DATA(IP2_9_8, A11),
+	PINMUX_IPSR_GPSR(IP2_9_8, A11),
 	PINMUX_IPSR_MSEL(IP2_9_8, MSIOF1_SYNC, SEL_MSI1_0),
 	PINMUX_IPSR_MSEL(IP2_9_8, IIC1_SDA_B, SEL_IIC01_1),
-	PINMUX_IPSR_DATA(IP2_11_10, A12),
+	PINMUX_IPSR_GPSR(IP2_11_10, A12),
 	PINMUX_IPSR_MSEL(IP2_11_10, MSIOF1_SS1, SEL_MSI1_0),
 	PINMUX_IPSR_MSEL(IP2_11_10, SCIFA5_RXD_B, SEL_SCIFA5_1),
-	PINMUX_IPSR_DATA(IP2_13_12, A13),
+	PINMUX_IPSR_GPSR(IP2_13_12, A13),
 	PINMUX_IPSR_MSEL(IP2_13_12, MSIOF1_SS2, SEL_MSI1_0),
 	PINMUX_IPSR_MSEL(IP2_13_12, SCIFA5_TXD_B, SEL_SCIFA5_1),
-	PINMUX_IPSR_DATA(IP2_15_14, A14),
+	PINMUX_IPSR_GPSR(IP2_15_14, A14),
 	PINMUX_IPSR_MSEL(IP2_15_14, MSIOF2_RXD, SEL_MSI2_0),
 	PINMUX_IPSR_MSEL(IP2_15_14, HSCIF0_HRX_B, SEL_HSCIF0_1),
 	PINMUX_IPSR_MSEL(IP2_15_14, DREQ1_N, SEL_LBS_0),
-	PINMUX_IPSR_DATA(IP2_17_16, A15),
+	PINMUX_IPSR_GPSR(IP2_17_16, A15),
 	PINMUX_IPSR_MSEL(IP2_17_16, MSIOF2_TXD, SEL_MSI2_0),
 	PINMUX_IPSR_MSEL(IP2_17_16, HSCIF0_HTX_B, SEL_HSCIF0_1),
 	PINMUX_IPSR_MSEL(IP2_17_16, DACK1, SEL_LBS_0),
-	PINMUX_IPSR_DATA(IP2_20_18, A16),
+	PINMUX_IPSR_GPSR(IP2_20_18, A16),
 	PINMUX_IPSR_MSEL(IP2_20_18, MSIOF2_SCK, SEL_MSI2_0),
 	PINMUX_IPSR_MSEL(IP2_20_18, HSCIF0_HSCK_B, SEL_HSCIF0_1),
 	PINMUX_IPSR_MSEL(IP2_20_18, SPEEDIN, SEL_RSP_0),
 	PINMUX_IPSR_MSEL(IP2_20_18, VSP, SEL_SPDM_0),
 	PINMUX_IPSR_MSEL(IP2_20_18, CAN_CLK_C, SEL_CAN_2),
-	PINMUX_IPSR_DATA(IP2_20_18, TPUTO2_B),
-	PINMUX_IPSR_DATA(IP2_23_21, A17),
+	PINMUX_IPSR_GPSR(IP2_20_18, TPUTO2_B),
+	PINMUX_IPSR_GPSR(IP2_23_21, A17),
 	PINMUX_IPSR_MSEL(IP2_23_21, MSIOF2_SYNC, SEL_MSI2_0),
 	PINMUX_IPSR_MSEL(IP2_23_21, SCIF4_RXD_E, SEL_SCIF4_4),
 	PINMUX_IPSR_MSEL(IP2_23_21, CAN1_RX_B, SEL_CAN1_1),
 	PINMUX_IPSR_MSEL(IP2_23_21, AVB_AVTP_CAPTURE_B, SEL_AVB_1),
-	PINMUX_IPSR_DATA(IP2_26_24, A18),
+	PINMUX_IPSR_GPSR(IP2_26_24, A18),
 	PINMUX_IPSR_MSEL(IP2_26_24, MSIOF2_SS1, SEL_MSI2_0),
 	PINMUX_IPSR_MSEL(IP2_26_24, SCIF4_TXD_E, SEL_SCIF4_4),
 	PINMUX_IPSR_MSEL(IP2_26_24, CAN1_TX_B, SEL_CAN1_1),
 	PINMUX_IPSR_MSEL(IP2_26_24, AVB_AVTP_MATCH_B, SEL_AVB_1),
-	PINMUX_IPSR_DATA(IP2_29_27, A19),
+	PINMUX_IPSR_GPSR(IP2_29_27, A19),
 	PINMUX_IPSR_MSEL(IP2_29_27, MSIOF2_SS2, SEL_MSI2_0),
-	PINMUX_IPSR_DATA(IP2_29_27, PWM4),
-	PINMUX_IPSR_DATA(IP2_29_27, TPUTO2),
-	PINMUX_IPSR_DATA(IP2_29_27, MOUT0),
-	PINMUX_IPSR_DATA(IP2_31_30, A20),
-	PINMUX_IPSR_DATA(IP2_31_30, SPCLK),
-	PINMUX_IPSR_DATA(IP2_29_27, MOUT1),
+	PINMUX_IPSR_GPSR(IP2_29_27, PWM4),
+	PINMUX_IPSR_GPSR(IP2_29_27, TPUTO2),
+	PINMUX_IPSR_GPSR(IP2_29_27, MOUT0),
+	PINMUX_IPSR_GPSR(IP2_31_30, A20),
+	PINMUX_IPSR_GPSR(IP2_31_30, SPCLK),
+	PINMUX_IPSR_GPSR(IP2_29_27, MOUT1),
 
 	/* IPSR3 */
-	PINMUX_IPSR_DATA(IP3_1_0, A21),
-	PINMUX_IPSR_DATA(IP3_1_0, MOSI_IO0),
-	PINMUX_IPSR_DATA(IP3_1_0, MOUT2),
-	PINMUX_IPSR_DATA(IP3_3_2, A22),
-	PINMUX_IPSR_DATA(IP3_3_2, MISO_IO1),
-	PINMUX_IPSR_DATA(IP3_3_2, MOUT5),
-	PINMUX_IPSR_DATA(IP3_3_2, ATADIR1_N),
-	PINMUX_IPSR_DATA(IP3_5_4, A23),
-	PINMUX_IPSR_DATA(IP3_5_4, IO2),
-	PINMUX_IPSR_DATA(IP3_5_4, MOUT6),
-	PINMUX_IPSR_DATA(IP3_5_4, ATAWR1_N),
-	PINMUX_IPSR_DATA(IP3_7_6, A24),
-	PINMUX_IPSR_DATA(IP3_7_6, IO3),
-	PINMUX_IPSR_DATA(IP3_7_6, EX_WAIT2),
-	PINMUX_IPSR_DATA(IP3_9_8, A25),
-	PINMUX_IPSR_DATA(IP3_9_8, SSL),
-	PINMUX_IPSR_DATA(IP3_9_8, ATARD1_N),
-	PINMUX_IPSR_DATA(IP3_10, CS0_N),
-	PINMUX_IPSR_DATA(IP3_10, VI1_DATA8),
-	PINMUX_IPSR_DATA(IP3_11, CS1_N_A26),
-	PINMUX_IPSR_DATA(IP3_11, VI1_DATA9),
-	PINMUX_IPSR_DATA(IP3_12, EX_CS0_N),
-	PINMUX_IPSR_DATA(IP3_12, VI1_DATA10),
-	PINMUX_IPSR_DATA(IP3_14_13, EX_CS1_N),
-	PINMUX_IPSR_DATA(IP3_14_13, TPUTO3_B),
-	PINMUX_IPSR_DATA(IP3_14_13, SCIFB2_RXD),
-	PINMUX_IPSR_DATA(IP3_14_13, VI1_DATA11),
-	PINMUX_IPSR_DATA(IP3_17_15, EX_CS2_N),
-	PINMUX_IPSR_DATA(IP3_17_15, PWM0),
+	PINMUX_IPSR_GPSR(IP3_1_0, A21),
+	PINMUX_IPSR_GPSR(IP3_1_0, MOSI_IO0),
+	PINMUX_IPSR_GPSR(IP3_1_0, MOUT2),
+	PINMUX_IPSR_GPSR(IP3_3_2, A22),
+	PINMUX_IPSR_GPSR(IP3_3_2, MISO_IO1),
+	PINMUX_IPSR_GPSR(IP3_3_2, MOUT5),
+	PINMUX_IPSR_GPSR(IP3_3_2, ATADIR1_N),
+	PINMUX_IPSR_GPSR(IP3_5_4, A23),
+	PINMUX_IPSR_GPSR(IP3_5_4, IO2),
+	PINMUX_IPSR_GPSR(IP3_5_4, MOUT6),
+	PINMUX_IPSR_GPSR(IP3_5_4, ATAWR1_N),
+	PINMUX_IPSR_GPSR(IP3_7_6, A24),
+	PINMUX_IPSR_GPSR(IP3_7_6, IO3),
+	PINMUX_IPSR_GPSR(IP3_7_6, EX_WAIT2),
+	PINMUX_IPSR_GPSR(IP3_9_8, A25),
+	PINMUX_IPSR_GPSR(IP3_9_8, SSL),
+	PINMUX_IPSR_GPSR(IP3_9_8, ATARD1_N),
+	PINMUX_IPSR_GPSR(IP3_10, CS0_N),
+	PINMUX_IPSR_GPSR(IP3_10, VI1_DATA8),
+	PINMUX_IPSR_GPSR(IP3_11, CS1_N_A26),
+	PINMUX_IPSR_GPSR(IP3_11, VI1_DATA9),
+	PINMUX_IPSR_GPSR(IP3_12, EX_CS0_N),
+	PINMUX_IPSR_GPSR(IP3_12, VI1_DATA10),
+	PINMUX_IPSR_GPSR(IP3_14_13, EX_CS1_N),
+	PINMUX_IPSR_GPSR(IP3_14_13, TPUTO3_B),
+	PINMUX_IPSR_GPSR(IP3_14_13, SCIFB2_RXD),
+	PINMUX_IPSR_GPSR(IP3_14_13, VI1_DATA11),
+	PINMUX_IPSR_GPSR(IP3_17_15, EX_CS2_N),
+	PINMUX_IPSR_GPSR(IP3_17_15, PWM0),
 	PINMUX_IPSR_MSEL(IP3_17_15, SCIF4_RXD_C, SEL_SCIF4_2),
 	PINMUX_IPSR_MSEL(IP3_17_15, TS_SDATA_B, SEL_TSIF0_1),
 	PINMUX_IPSR_MSEL(IP3_17_15, RIF0_SYNC, SEL_DR0_0),
-	PINMUX_IPSR_DATA(IP3_17_15, TPUTO3),
-	PINMUX_IPSR_DATA(IP3_17_15, SCIFB2_TXD),
+	PINMUX_IPSR_GPSR(IP3_17_15, TPUTO3),
+	PINMUX_IPSR_GPSR(IP3_17_15, SCIFB2_TXD),
 	PINMUX_IPSR_MSEL(IP3_17_15, SDATA_B, SEL_FSN_1),
-	PINMUX_IPSR_DATA(IP3_20_18, EX_CS3_N),
+	PINMUX_IPSR_GPSR(IP3_20_18, EX_CS3_N),
 	PINMUX_IPSR_MSEL(IP3_20_18, SCIFA2_SCK, SEL_SCIFA2_0),
 	PINMUX_IPSR_MSEL(IP3_20_18, SCIF4_TXD_C, SEL_SCIF4_2),
 	PINMUX_IPSR_MSEL(IP3_20_18, TS_SCK_B, SEL_TSIF0_1),
 	PINMUX_IPSR_MSEL(IP3_20_18, RIF0_CLK, SEL_DR0_0),
 	PINMUX_IPSR_MSEL(IP3_20_18, BPFCLK, SEL_DARC_0),
-	PINMUX_IPSR_DATA(IP3_20_18, SCIFB2_SCK),
+	PINMUX_IPSR_GPSR(IP3_20_18, SCIFB2_SCK),
 	PINMUX_IPSR_MSEL(IP3_20_18, MDATA_B, SEL_FSN_1),
-	PINMUX_IPSR_DATA(IP3_23_21, EX_CS4_N),
+	PINMUX_IPSR_GPSR(IP3_23_21, EX_CS4_N),
 	PINMUX_IPSR_MSEL(IP3_23_21, SCIFA2_RXD, SEL_SCIFA2_0),
 	PINMUX_IPSR_MSEL(IP3_23_21, I2C2_SCL_E, SEL_I2C02_4),
 	PINMUX_IPSR_MSEL(IP3_23_21, TS_SDEN_B, SEL_TSIF0_1),
 	PINMUX_IPSR_MSEL(IP3_23_21, RIF0_D0, SEL_DR0_0),
 	PINMUX_IPSR_MSEL(IP3_23_21, FMCLK, SEL_DARC_0),
-	PINMUX_IPSR_DATA(IP3_23_21, SCIFB2_CTS_N),
+	PINMUX_IPSR_GPSR(IP3_23_21, SCIFB2_CTS_N),
 	PINMUX_IPSR_MSEL(IP3_23_21, SCKZ_B, SEL_FSN_1),
-	PINMUX_IPSR_DATA(IP3_26_24, EX_CS5_N),
+	PINMUX_IPSR_GPSR(IP3_26_24, EX_CS5_N),
 	PINMUX_IPSR_MSEL(IP3_26_24, SCIFA2_TXD, SEL_SCIFA2_0),
 	PINMUX_IPSR_MSEL(IP3_26_24, I2C2_SDA_E, SEL_I2C02_4),
 	PINMUX_IPSR_MSEL(IP3_26_24, TS_SPSYNC_B, SEL_TSIF0_1),
 	PINMUX_IPSR_MSEL(IP3_26_24, RIF0_D1, SEL_DR1_0),
 	PINMUX_IPSR_MSEL(IP3_26_24, FMIN, SEL_DARC_0),
-	PINMUX_IPSR_DATA(IP3_26_24, SCIFB2_RTS_N),
+	PINMUX_IPSR_GPSR(IP3_26_24, SCIFB2_RTS_N),
 	PINMUX_IPSR_MSEL(IP3_26_24, STM_N_B, SEL_FSN_1),
-	PINMUX_IPSR_DATA(IP3_29_27, BS_N),
-	PINMUX_IPSR_DATA(IP3_29_27, DRACK0),
-	PINMUX_IPSR_DATA(IP3_29_27, PWM1_C),
-	PINMUX_IPSR_DATA(IP3_29_27, TPUTO0_C),
-	PINMUX_IPSR_DATA(IP3_29_27, ATACS01_N),
+	PINMUX_IPSR_GPSR(IP3_29_27, BS_N),
+	PINMUX_IPSR_GPSR(IP3_29_27, DRACK0),
+	PINMUX_IPSR_GPSR(IP3_29_27, PWM1_C),
+	PINMUX_IPSR_GPSR(IP3_29_27, TPUTO0_C),
+	PINMUX_IPSR_GPSR(IP3_29_27, ATACS01_N),
 	PINMUX_IPSR_MSEL(IP3_29_27, MTS_N_B, SEL_FSN_1),
-	PINMUX_IPSR_DATA(IP3_30, RD_N),
-	PINMUX_IPSR_DATA(IP3_30, ATACS11_N),
-	PINMUX_IPSR_DATA(IP3_31, RD_WR_N),
-	PINMUX_IPSR_DATA(IP3_31, ATAG1_N),
+	PINMUX_IPSR_GPSR(IP3_30, RD_N),
+	PINMUX_IPSR_GPSR(IP3_30, ATACS11_N),
+	PINMUX_IPSR_GPSR(IP3_31, RD_WR_N),
+	PINMUX_IPSR_GPSR(IP3_31, ATAG1_N),
 
 	/* IPSR4 */
-	PINMUX_IPSR_DATA(IP4_1_0, EX_WAIT0),
+	PINMUX_IPSR_GPSR(IP4_1_0, EX_WAIT0),
 	PINMUX_IPSR_MSEL(IP4_1_0, CAN_CLK_B, SEL_CAN_1),
 	PINMUX_IPSR_MSEL(IP4_1_0, SCIF_CLK, SEL_SCIF0_0),
-	PINMUX_IPSR_DATA(IP4_1_0, PWMFSW0),
-	PINMUX_IPSR_DATA(IP4_4_2, DU0_DR0),
-	PINMUX_IPSR_DATA(IP4_4_2, LCDOUT16),
+	PINMUX_IPSR_GPSR(IP4_1_0, PWMFSW0),
+	PINMUX_IPSR_GPSR(IP4_4_2, DU0_DR0),
+	PINMUX_IPSR_GPSR(IP4_4_2, LCDOUT16),
 	PINMUX_IPSR_MSEL(IP4_4_2, SCIF5_RXD_C, SEL_SCIF5_2),
 	PINMUX_IPSR_MSEL(IP4_4_2, I2C2_SCL_D, SEL_I2C02_3),
-	PINMUX_IPSR_DATA(IP4_4_2, CC50_STATE0),
-	PINMUX_IPSR_DATA(IP4_7_5, DU0_DR1),
-	PINMUX_IPSR_DATA(IP4_7_5, LCDOUT17),
+	PINMUX_IPSR_GPSR(IP4_4_2, CC50_STATE0),
+	PINMUX_IPSR_GPSR(IP4_7_5, DU0_DR1),
+	PINMUX_IPSR_GPSR(IP4_7_5, LCDOUT17),
 	PINMUX_IPSR_MSEL(IP4_7_5, SCIF5_TXD_C, SEL_SCIF5_2),
 	PINMUX_IPSR_MSEL(IP4_7_5, I2C2_SDA_D, SEL_I2C02_3),
-	PINMUX_IPSR_DATA(IP4_9_8, CC50_STATE1),
-	PINMUX_IPSR_DATA(IP4_9_8, DU0_DR2),
-	PINMUX_IPSR_DATA(IP4_9_8, LCDOUT18),
-	PINMUX_IPSR_DATA(IP4_9_8, CC50_STATE2),
-	PINMUX_IPSR_DATA(IP4_11_10, DU0_DR3),
-	PINMUX_IPSR_DATA(IP4_11_10, LCDOUT19),
-	PINMUX_IPSR_DATA(IP4_11_10, CC50_STATE3),
-	PINMUX_IPSR_DATA(IP4_13_12, DU0_DR4),
-	PINMUX_IPSR_DATA(IP4_13_12, LCDOUT20),
-	PINMUX_IPSR_DATA(IP4_13_12, CC50_STATE4),
-	PINMUX_IPSR_DATA(IP4_15_14, DU0_DR5),
-	PINMUX_IPSR_DATA(IP4_15_14, LCDOUT21),
-	PINMUX_IPSR_DATA(IP4_15_14, CC50_STATE5),
-	PINMUX_IPSR_DATA(IP4_17_16, DU0_DR6),
-	PINMUX_IPSR_DATA(IP4_17_16, LCDOUT22),
-	PINMUX_IPSR_DATA(IP4_17_16, CC50_STATE6),
-	PINMUX_IPSR_DATA(IP4_19_18, DU0_DR7),
-	PINMUX_IPSR_DATA(IP4_19_18, LCDOUT23),
-	PINMUX_IPSR_DATA(IP4_19_18, CC50_STATE7),
-	PINMUX_IPSR_DATA(IP4_22_20, DU0_DG0),
-	PINMUX_IPSR_DATA(IP4_22_20, LCDOUT8),
+	PINMUX_IPSR_GPSR(IP4_9_8, CC50_STATE1),
+	PINMUX_IPSR_GPSR(IP4_9_8, DU0_DR2),
+	PINMUX_IPSR_GPSR(IP4_9_8, LCDOUT18),
+	PINMUX_IPSR_GPSR(IP4_9_8, CC50_STATE2),
+	PINMUX_IPSR_GPSR(IP4_11_10, DU0_DR3),
+	PINMUX_IPSR_GPSR(IP4_11_10, LCDOUT19),
+	PINMUX_IPSR_GPSR(IP4_11_10, CC50_STATE3),
+	PINMUX_IPSR_GPSR(IP4_13_12, DU0_DR4),
+	PINMUX_IPSR_GPSR(IP4_13_12, LCDOUT20),
+	PINMUX_IPSR_GPSR(IP4_13_12, CC50_STATE4),
+	PINMUX_IPSR_GPSR(IP4_15_14, DU0_DR5),
+	PINMUX_IPSR_GPSR(IP4_15_14, LCDOUT21),
+	PINMUX_IPSR_GPSR(IP4_15_14, CC50_STATE5),
+	PINMUX_IPSR_GPSR(IP4_17_16, DU0_DR6),
+	PINMUX_IPSR_GPSR(IP4_17_16, LCDOUT22),
+	PINMUX_IPSR_GPSR(IP4_17_16, CC50_STATE6),
+	PINMUX_IPSR_GPSR(IP4_19_18, DU0_DR7),
+	PINMUX_IPSR_GPSR(IP4_19_18, LCDOUT23),
+	PINMUX_IPSR_GPSR(IP4_19_18, CC50_STATE7),
+	PINMUX_IPSR_GPSR(IP4_22_20, DU0_DG0),
+	PINMUX_IPSR_GPSR(IP4_22_20, LCDOUT8),
 	PINMUX_IPSR_MSEL(IP4_22_20, SCIFA0_RXD_C, SEL_SCIFA0_2),
 	PINMUX_IPSR_MSEL(IP4_22_20, I2C3_SCL_D, SEL_I2C03_3),
-	PINMUX_IPSR_DATA(IP4_22_20, CC50_STATE8),
-	PINMUX_IPSR_DATA(IP4_25_23, DU0_DG1),
-	PINMUX_IPSR_DATA(IP4_25_23, LCDOUT9),
+	PINMUX_IPSR_GPSR(IP4_22_20, CC50_STATE8),
+	PINMUX_IPSR_GPSR(IP4_25_23, DU0_DG1),
+	PINMUX_IPSR_GPSR(IP4_25_23, LCDOUT9),
 	PINMUX_IPSR_MSEL(IP4_25_23, SCIFA0_TXD_C, SEL_SCIFA0_2),
 	PINMUX_IPSR_MSEL(IP4_25_23, I2C3_SDA_D, SEL_I2C03_3),
-	PINMUX_IPSR_DATA(IP4_25_23, CC50_STATE9),
-	PINMUX_IPSR_DATA(IP4_27_26, DU0_DG2),
-	PINMUX_IPSR_DATA(IP4_27_26, LCDOUT10),
-	PINMUX_IPSR_DATA(IP4_27_26, CC50_STATE10),
-	PINMUX_IPSR_DATA(IP4_29_28, DU0_DG3),
-	PINMUX_IPSR_DATA(IP4_29_28, LCDOUT11),
-	PINMUX_IPSR_DATA(IP4_29_28, CC50_STATE11),
-	PINMUX_IPSR_DATA(IP4_31_30, DU0_DG4),
-	PINMUX_IPSR_DATA(IP4_31_30, LCDOUT12),
-	PINMUX_IPSR_DATA(IP4_31_30, CC50_STATE12),
+	PINMUX_IPSR_GPSR(IP4_25_23, CC50_STATE9),
+	PINMUX_IPSR_GPSR(IP4_27_26, DU0_DG2),
+	PINMUX_IPSR_GPSR(IP4_27_26, LCDOUT10),
+	PINMUX_IPSR_GPSR(IP4_27_26, CC50_STATE10),
+	PINMUX_IPSR_GPSR(IP4_29_28, DU0_DG3),
+	PINMUX_IPSR_GPSR(IP4_29_28, LCDOUT11),
+	PINMUX_IPSR_GPSR(IP4_29_28, CC50_STATE11),
+	PINMUX_IPSR_GPSR(IP4_31_30, DU0_DG4),
+	PINMUX_IPSR_GPSR(IP4_31_30, LCDOUT12),
+	PINMUX_IPSR_GPSR(IP4_31_30, CC50_STATE12),
 
 	/* IPSR5 */
-	PINMUX_IPSR_DATA(IP5_1_0, DU0_DG5),
-	PINMUX_IPSR_DATA(IP5_1_0, LCDOUT13),
-	PINMUX_IPSR_DATA(IP5_1_0, CC50_STATE13),
-	PINMUX_IPSR_DATA(IP5_3_2, DU0_DG6),
-	PINMUX_IPSR_DATA(IP5_3_2, LCDOUT14),
-	PINMUX_IPSR_DATA(IP5_3_2, CC50_STATE14),
-	PINMUX_IPSR_DATA(IP5_5_4, DU0_DG7),
-	PINMUX_IPSR_DATA(IP5_5_4, LCDOUT15),
-	PINMUX_IPSR_DATA(IP5_5_4, CC50_STATE15),
-	PINMUX_IPSR_DATA(IP5_8_6, DU0_DB0),
-	PINMUX_IPSR_DATA(IP5_8_6, LCDOUT0),
+	PINMUX_IPSR_GPSR(IP5_1_0, DU0_DG5),
+	PINMUX_IPSR_GPSR(IP5_1_0, LCDOUT13),
+	PINMUX_IPSR_GPSR(IP5_1_0, CC50_STATE13),
+	PINMUX_IPSR_GPSR(IP5_3_2, DU0_DG6),
+	PINMUX_IPSR_GPSR(IP5_3_2, LCDOUT14),
+	PINMUX_IPSR_GPSR(IP5_3_2, CC50_STATE14),
+	PINMUX_IPSR_GPSR(IP5_5_4, DU0_DG7),
+	PINMUX_IPSR_GPSR(IP5_5_4, LCDOUT15),
+	PINMUX_IPSR_GPSR(IP5_5_4, CC50_STATE15),
+	PINMUX_IPSR_GPSR(IP5_8_6, DU0_DB0),
+	PINMUX_IPSR_GPSR(IP5_8_6, LCDOUT0),
 	PINMUX_IPSR_MSEL(IP5_8_6, SCIFA4_RXD_C, SEL_SCIFA4_2),
 	PINMUX_IPSR_MSEL(IP5_8_6, I2C4_SCL_D, SEL_I2C04_3),
 	PINMUX_IPSR_MSEL(IP7_8_6, CAN0_RX_C, SEL_CAN0_2),
-	PINMUX_IPSR_DATA(IP5_8_6, CC50_STATE16),
-	PINMUX_IPSR_DATA(IP5_11_9, DU0_DB1),
-	PINMUX_IPSR_DATA(IP5_11_9, LCDOUT1),
+	PINMUX_IPSR_GPSR(IP5_8_6, CC50_STATE16),
+	PINMUX_IPSR_GPSR(IP5_11_9, DU0_DB1),
+	PINMUX_IPSR_GPSR(IP5_11_9, LCDOUT1),
 	PINMUX_IPSR_MSEL(IP5_11_9, SCIFA4_TXD_C, SEL_SCIFA4_2),
 	PINMUX_IPSR_MSEL(IP5_11_9, I2C4_SDA_D, SEL_I2C04_3),
 	PINMUX_IPSR_MSEL(IP5_11_9, CAN0_TX_C, SEL_CAN0_2),
-	PINMUX_IPSR_DATA(IP5_11_9, CC50_STATE17),
-	PINMUX_IPSR_DATA(IP5_13_12, DU0_DB2),
-	PINMUX_IPSR_DATA(IP5_13_12, LCDOUT2),
-	PINMUX_IPSR_DATA(IP5_13_12, CC50_STATE18),
-	PINMUX_IPSR_DATA(IP5_15_14, DU0_DB3),
-	PINMUX_IPSR_DATA(IP5_15_14, LCDOUT3),
-	PINMUX_IPSR_DATA(IP5_15_14, CC50_STATE19),
-	PINMUX_IPSR_DATA(IP5_17_16, DU0_DB4),
-	PINMUX_IPSR_DATA(IP5_17_16, LCDOUT4),
-	PINMUX_IPSR_DATA(IP5_17_16, CC50_STATE20),
-	PINMUX_IPSR_DATA(IP5_19_18, DU0_DB5),
-	PINMUX_IPSR_DATA(IP5_19_18, LCDOUT5),
-	PINMUX_IPSR_DATA(IP5_19_18, CC50_STATE21),
-	PINMUX_IPSR_DATA(IP5_21_20, DU0_DB6),
-	PINMUX_IPSR_DATA(IP5_21_20, LCDOUT6),
-	PINMUX_IPSR_DATA(IP5_21_20, CC50_STATE22),
-	PINMUX_IPSR_DATA(IP5_23_22, DU0_DB7),
-	PINMUX_IPSR_DATA(IP5_23_22, LCDOUT7),
-	PINMUX_IPSR_DATA(IP5_23_22, CC50_STATE23),
-	PINMUX_IPSR_DATA(IP5_25_24, DU0_DOTCLKIN),
-	PINMUX_IPSR_DATA(IP5_25_24, QSTVA_QVS),
-	PINMUX_IPSR_DATA(IP5_25_24, CC50_STATE24),
-	PINMUX_IPSR_DATA(IP5_27_26, DU0_DOTCLKOUT0),
-	PINMUX_IPSR_DATA(IP5_27_26, QCLK),
-	PINMUX_IPSR_DATA(IP5_27_26, CC50_STATE25),
-	PINMUX_IPSR_DATA(IP5_29_28, DU0_DOTCLKOUT1),
-	PINMUX_IPSR_DATA(IP5_29_28, QSTVB_QVE),
-	PINMUX_IPSR_DATA(IP5_29_28, CC50_STATE26),
-	PINMUX_IPSR_DATA(IP5_31_30, DU0_EXHSYNC_DU0_HSYNC),
-	PINMUX_IPSR_DATA(IP5_31_30, QSTH_QHS),
-	PINMUX_IPSR_DATA(IP5_31_30, CC50_STATE27),
+	PINMUX_IPSR_GPSR(IP5_11_9, CC50_STATE17),
+	PINMUX_IPSR_GPSR(IP5_13_12, DU0_DB2),
+	PINMUX_IPSR_GPSR(IP5_13_12, LCDOUT2),
+	PINMUX_IPSR_GPSR(IP5_13_12, CC50_STATE18),
+	PINMUX_IPSR_GPSR(IP5_15_14, DU0_DB3),
+	PINMUX_IPSR_GPSR(IP5_15_14, LCDOUT3),
+	PINMUX_IPSR_GPSR(IP5_15_14, CC50_STATE19),
+	PINMUX_IPSR_GPSR(IP5_17_16, DU0_DB4),
+	PINMUX_IPSR_GPSR(IP5_17_16, LCDOUT4),
+	PINMUX_IPSR_GPSR(IP5_17_16, CC50_STATE20),
+	PINMUX_IPSR_GPSR(IP5_19_18, DU0_DB5),
+	PINMUX_IPSR_GPSR(IP5_19_18, LCDOUT5),
+	PINMUX_IPSR_GPSR(IP5_19_18, CC50_STATE21),
+	PINMUX_IPSR_GPSR(IP5_21_20, DU0_DB6),
+	PINMUX_IPSR_GPSR(IP5_21_20, LCDOUT6),
+	PINMUX_IPSR_GPSR(IP5_21_20, CC50_STATE22),
+	PINMUX_IPSR_GPSR(IP5_23_22, DU0_DB7),
+	PINMUX_IPSR_GPSR(IP5_23_22, LCDOUT7),
+	PINMUX_IPSR_GPSR(IP5_23_22, CC50_STATE23),
+	PINMUX_IPSR_GPSR(IP5_25_24, DU0_DOTCLKIN),
+	PINMUX_IPSR_GPSR(IP5_25_24, QSTVA_QVS),
+	PINMUX_IPSR_GPSR(IP5_25_24, CC50_STATE24),
+	PINMUX_IPSR_GPSR(IP5_27_26, DU0_DOTCLKOUT0),
+	PINMUX_IPSR_GPSR(IP5_27_26, QCLK),
+	PINMUX_IPSR_GPSR(IP5_27_26, CC50_STATE25),
+	PINMUX_IPSR_GPSR(IP5_29_28, DU0_DOTCLKOUT1),
+	PINMUX_IPSR_GPSR(IP5_29_28, QSTVB_QVE),
+	PINMUX_IPSR_GPSR(IP5_29_28, CC50_STATE26),
+	PINMUX_IPSR_GPSR(IP5_31_30, DU0_EXHSYNC_DU0_HSYNC),
+	PINMUX_IPSR_GPSR(IP5_31_30, QSTH_QHS),
+	PINMUX_IPSR_GPSR(IP5_31_30, CC50_STATE27),
 
 	/* IPSR6 */
-	PINMUX_IPSR_DATA(IP6_1_0, DU0_EXVSYNC_DU0_VSYNC),
-	PINMUX_IPSR_DATA(IP6_1_0, QSTB_QHE),
-	PINMUX_IPSR_DATA(IP6_1_0, CC50_STATE28),
-	PINMUX_IPSR_DATA(IP6_3_2, DU0_EXODDF_DU0_ODDF_DISP_CDE),
-	PINMUX_IPSR_DATA(IP6_3_2, QCPV_QDE),
-	PINMUX_IPSR_DATA(IP6_3_2, CC50_STATE29),
-	PINMUX_IPSR_DATA(IP6_5_4, DU0_DISP),
-	PINMUX_IPSR_DATA(IP6_5_4, QPOLA),
-	PINMUX_IPSR_DATA(IP6_5_4, CC50_STATE30),
-	PINMUX_IPSR_DATA(IP6_7_6, DU0_CDE),
-	PINMUX_IPSR_DATA(IP6_7_6, QPOLB),
-	PINMUX_IPSR_DATA(IP6_7_6, CC50_STATE31),
-	PINMUX_IPSR_DATA(IP6_8, VI0_CLK),
-	PINMUX_IPSR_DATA(IP6_8, AVB_RX_CLK),
-	PINMUX_IPSR_DATA(IP6_9, VI0_DATA0_VI0_B0),
-	PINMUX_IPSR_DATA(IP6_9, AVB_RX_DV),
-	PINMUX_IPSR_DATA(IP6_10, VI0_DATA1_VI0_B1),
-	PINMUX_IPSR_DATA(IP6_10, AVB_RXD0),
-	PINMUX_IPSR_DATA(IP6_11, VI0_DATA2_VI0_B2),
-	PINMUX_IPSR_DATA(IP6_11, AVB_RXD1),
-	PINMUX_IPSR_DATA(IP6_12, VI0_DATA3_VI0_B3),
-	PINMUX_IPSR_DATA(IP6_12, AVB_RXD2),
-	PINMUX_IPSR_DATA(IP6_13, VI0_DATA4_VI0_B4),
-	PINMUX_IPSR_DATA(IP6_13, AVB_RXD3),
-	PINMUX_IPSR_DATA(IP6_14, VI0_DATA5_VI0_B5),
-	PINMUX_IPSR_DATA(IP6_14, AVB_RXD4),
-	PINMUX_IPSR_DATA(IP6_15, VI0_DATA6_VI0_B6),
-	PINMUX_IPSR_DATA(IP6_15, AVB_RXD5),
-	PINMUX_IPSR_DATA(IP6_16, VI0_DATA7_VI0_B7),
-	PINMUX_IPSR_DATA(IP6_16, AVB_RXD6),
-	PINMUX_IPSR_DATA(IP6_19_17, VI0_CLKENB),
+	PINMUX_IPSR_GPSR(IP6_1_0, DU0_EXVSYNC_DU0_VSYNC),
+	PINMUX_IPSR_GPSR(IP6_1_0, QSTB_QHE),
+	PINMUX_IPSR_GPSR(IP6_1_0, CC50_STATE28),
+	PINMUX_IPSR_GPSR(IP6_3_2, DU0_EXODDF_DU0_ODDF_DISP_CDE),
+	PINMUX_IPSR_GPSR(IP6_3_2, QCPV_QDE),
+	PINMUX_IPSR_GPSR(IP6_3_2, CC50_STATE29),
+	PINMUX_IPSR_GPSR(IP6_5_4, DU0_DISP),
+	PINMUX_IPSR_GPSR(IP6_5_4, QPOLA),
+	PINMUX_IPSR_GPSR(IP6_5_4, CC50_STATE30),
+	PINMUX_IPSR_GPSR(IP6_7_6, DU0_CDE),
+	PINMUX_IPSR_GPSR(IP6_7_6, QPOLB),
+	PINMUX_IPSR_GPSR(IP6_7_6, CC50_STATE31),
+	PINMUX_IPSR_GPSR(IP6_8, VI0_CLK),
+	PINMUX_IPSR_GPSR(IP6_8, AVB_RX_CLK),
+	PINMUX_IPSR_GPSR(IP6_9, VI0_DATA0_VI0_B0),
+	PINMUX_IPSR_GPSR(IP6_9, AVB_RX_DV),
+	PINMUX_IPSR_GPSR(IP6_10, VI0_DATA1_VI0_B1),
+	PINMUX_IPSR_GPSR(IP6_10, AVB_RXD0),
+	PINMUX_IPSR_GPSR(IP6_11, VI0_DATA2_VI0_B2),
+	PINMUX_IPSR_GPSR(IP6_11, AVB_RXD1),
+	PINMUX_IPSR_GPSR(IP6_12, VI0_DATA3_VI0_B3),
+	PINMUX_IPSR_GPSR(IP6_12, AVB_RXD2),
+	PINMUX_IPSR_GPSR(IP6_13, VI0_DATA4_VI0_B4),
+	PINMUX_IPSR_GPSR(IP6_13, AVB_RXD3),
+	PINMUX_IPSR_GPSR(IP6_14, VI0_DATA5_VI0_B5),
+	PINMUX_IPSR_GPSR(IP6_14, AVB_RXD4),
+	PINMUX_IPSR_GPSR(IP6_15, VI0_DATA6_VI0_B6),
+	PINMUX_IPSR_GPSR(IP6_15, AVB_RXD5),
+	PINMUX_IPSR_GPSR(IP6_16, VI0_DATA7_VI0_B7),
+	PINMUX_IPSR_GPSR(IP6_16, AVB_RXD6),
+	PINMUX_IPSR_GPSR(IP6_19_17, VI0_CLKENB),
 	PINMUX_IPSR_MSEL(IP6_19_17, I2C3_SCL, SEL_I2C03_0),
 	PINMUX_IPSR_MSEL(IP6_19_17, SCIFA5_RXD_C, SEL_SCIFA5_2),
 	PINMUX_IPSR_MSEL(IP6_19_17, IETX_C, SEL_IEB_2),
-	PINMUX_IPSR_DATA(IP6_19_17, AVB_RXD7),
-	PINMUX_IPSR_DATA(IP6_22_20, VI0_FIELD),
+	PINMUX_IPSR_GPSR(IP6_19_17, AVB_RXD7),
+	PINMUX_IPSR_GPSR(IP6_22_20, VI0_FIELD),
 	PINMUX_IPSR_MSEL(IP6_22_20, I2C3_SDA, SEL_I2C03_0),
 	PINMUX_IPSR_MSEL(IP6_22_20, SCIFA5_TXD_C, SEL_SCIFA5_2),
 	PINMUX_IPSR_MSEL(IP6_22_20, IECLK_C, SEL_IEB_2),
-	PINMUX_IPSR_DATA(IP6_22_20, AVB_RX_ER),
-	PINMUX_IPSR_DATA(IP6_25_23, VI0_HSYNC_N),
+	PINMUX_IPSR_GPSR(IP6_22_20, AVB_RX_ER),
+	PINMUX_IPSR_GPSR(IP6_25_23, VI0_HSYNC_N),
 	PINMUX_IPSR_MSEL(IP6_25_23, SCIF0_RXD_B, SEL_SCIF0_1),
 	PINMUX_IPSR_MSEL(IP6_25_23, I2C0_SCL_C, SEL_I2C00_2),
 	PINMUX_IPSR_MSEL(IP6_25_23, IERX_C, SEL_IEB_2),
-	PINMUX_IPSR_DATA(IP6_25_23, AVB_COL),
-	PINMUX_IPSR_DATA(IP6_28_26, VI0_VSYNC_N),
+	PINMUX_IPSR_GPSR(IP6_25_23, AVB_COL),
+	PINMUX_IPSR_GPSR(IP6_28_26, VI0_VSYNC_N),
 	PINMUX_IPSR_MSEL(IP6_28_26, SCIF0_TXD_B, SEL_SCIF0_1),
 	PINMUX_IPSR_MSEL(IP6_28_26, I2C0_SDA_C, SEL_I2C00_2),
 	PINMUX_IPSR_MSEL(IP6_28_26, AUDIO_CLKOUT_B, SEL_ADG_1),
-	PINMUX_IPSR_DATA(IP6_28_26, AVB_TX_EN),
+	PINMUX_IPSR_GPSR(IP6_28_26, AVB_TX_EN),
 	PINMUX_IPSR_MSEL(IP6_31_29, ETH_MDIO, SEL_ETH_0),
-	PINMUX_IPSR_DATA(IP6_31_29, VI0_G0),
+	PINMUX_IPSR_GPSR(IP6_31_29, VI0_G0),
 	PINMUX_IPSR_MSEL(IP6_31_29, MSIOF2_RXD_B, SEL_MSI2_1),
 	PINMUX_IPSR_MSEL(IP6_31_29, IIC0_SCL_D, SEL_IIC00_3),
-	PINMUX_IPSR_DATA(IP6_31_29, AVB_TX_CLK),
+	PINMUX_IPSR_GPSR(IP6_31_29, AVB_TX_CLK),
 	PINMUX_IPSR_MSEL(IP6_31_29, ADIDATA, SEL_RAD_0),
 	PINMUX_IPSR_MSEL(IP6_31_29, AD_DI, SEL_ADI_0),
 
 	/* IPSR7 */
 	PINMUX_IPSR_MSEL(IP7_2_0, ETH_CRS_DV, SEL_ETH_0),
-	PINMUX_IPSR_DATA(IP7_2_0, VI0_G1),
+	PINMUX_IPSR_GPSR(IP7_2_0, VI0_G1),
 	PINMUX_IPSR_MSEL(IP7_2_0, MSIOF2_TXD_B, SEL_MSI2_1),
 	PINMUX_IPSR_MSEL(IP7_2_0, IIC0_SDA_D, SEL_IIC00_3),
-	PINMUX_IPSR_DATA(IP7_2_0, AVB_TXD0),
+	PINMUX_IPSR_GPSR(IP7_2_0, AVB_TXD0),
 	PINMUX_IPSR_MSEL(IP7_2_0, ADICS_SAMP, SEL_RAD_0),
 	PINMUX_IPSR_MSEL(IP7_2_0, AD_DO, SEL_ADI_0),
 	PINMUX_IPSR_MSEL(IP7_5_3, ETH_RX_ER, SEL_ETH_0),
-	PINMUX_IPSR_DATA(IP7_5_3, VI0_G2),
+	PINMUX_IPSR_GPSR(IP7_5_3, VI0_G2),
 	PINMUX_IPSR_MSEL(IP7_5_3, MSIOF2_SCK_B, SEL_MSI2_1),
 	PINMUX_IPSR_MSEL(IP7_5_3, CAN0_RX_B, SEL_CAN0_1),
-	PINMUX_IPSR_DATA(IP7_5_3, AVB_TXD1),
+	PINMUX_IPSR_GPSR(IP7_5_3, AVB_TXD1),
 	PINMUX_IPSR_MSEL(IP7_5_3, ADICLK, SEL_RAD_0),
 	PINMUX_IPSR_MSEL(IP7_5_3, AD_CLK, SEL_ADI_0),
 	PINMUX_IPSR_MSEL(IP7_8_6, ETH_RXD0, SEL_ETH_0),
-	PINMUX_IPSR_DATA(IP7_8_6, VI0_G3),
+	PINMUX_IPSR_GPSR(IP7_8_6, VI0_G3),
 	PINMUX_IPSR_MSEL(IP7_8_6, MSIOF2_SYNC_B, SEL_MSI2_1),
 	PINMUX_IPSR_MSEL(IP7_8_6, CAN0_TX_B, SEL_CAN0_1),
-	PINMUX_IPSR_DATA(IP7_8_6, AVB_TXD2),
+	PINMUX_IPSR_GPSR(IP7_8_6, AVB_TXD2),
 	PINMUX_IPSR_MSEL(IP7_8_6, ADICHS0, SEL_RAD_0),
 	PINMUX_IPSR_MSEL(IP7_8_6, AD_NCS_N, SEL_ADI_0),
 	PINMUX_IPSR_MSEL(IP7_11_9, ETH_RXD1, SEL_ETH_0),
-	PINMUX_IPSR_DATA(IP7_11_9, VI0_G4),
+	PINMUX_IPSR_GPSR(IP7_11_9, VI0_G4),
 	PINMUX_IPSR_MSEL(IP7_11_9, MSIOF2_SS1_B, SEL_MSI2_1),
 	PINMUX_IPSR_MSEL(IP7_11_9, SCIF4_RXD_D, SEL_SCIF4_3),
-	PINMUX_IPSR_DATA(IP7_11_9, AVB_TXD3),
+	PINMUX_IPSR_GPSR(IP7_11_9, AVB_TXD3),
 	PINMUX_IPSR_MSEL(IP7_11_9, ADICHS1, SEL_RAD_0),
 	PINMUX_IPSR_MSEL(IP7_14_12, ETH_LINK, SEL_ETH_0),
-	PINMUX_IPSR_DATA(IP7_14_12, VI0_G5),
+	PINMUX_IPSR_GPSR(IP7_14_12, VI0_G5),
 	PINMUX_IPSR_MSEL(IP7_14_12, MSIOF2_SS2_B, SEL_MSI2_1),
 	PINMUX_IPSR_MSEL(IP7_14_12, SCIF4_TXD_D, SEL_SCIF4_3),
-	PINMUX_IPSR_DATA(IP7_14_12, AVB_TXD4),
+	PINMUX_IPSR_GPSR(IP7_14_12, AVB_TXD4),
 	PINMUX_IPSR_MSEL(IP7_14_12, ADICHS2, SEL_RAD_0),
 	PINMUX_IPSR_MSEL(IP7_17_15, ETH_REFCLK, SEL_ETH_0),
-	PINMUX_IPSR_DATA(IP7_17_15, VI0_G6),
+	PINMUX_IPSR_GPSR(IP7_17_15, VI0_G6),
 	PINMUX_IPSR_MSEL(IP7_17_15, SCIF2_SCK_C, SEL_SCIF2_2),
-	PINMUX_IPSR_DATA(IP7_17_15, AVB_TXD5),
+	PINMUX_IPSR_GPSR(IP7_17_15, AVB_TXD5),
 	PINMUX_IPSR_MSEL(IP7_17_15, SSI_SCK5_B, SEL_SSI5_1),
 	PINMUX_IPSR_MSEL(IP7_20_18, ETH_TXD1, SEL_ETH_0),
-	PINMUX_IPSR_DATA(IP7_20_18, VI0_G7),
+	PINMUX_IPSR_GPSR(IP7_20_18, VI0_G7),
 	PINMUX_IPSR_MSEL(IP7_20_18, SCIF2_RXD_C, SEL_SCIF2_2),
 	PINMUX_IPSR_MSEL(IP7_20_18, IIC1_SCL_D, SEL_IIC01_3),
-	PINMUX_IPSR_DATA(IP7_20_18, AVB_TXD6),
+	PINMUX_IPSR_GPSR(IP7_20_18, AVB_TXD6),
 	PINMUX_IPSR_MSEL(IP7_20_18, SSI_WS5_B, SEL_SSI5_1),
 	PINMUX_IPSR_MSEL(IP7_23_21, ETH_TX_EN, SEL_ETH_0),
-	PINMUX_IPSR_DATA(IP7_23_21, VI0_R0),
+	PINMUX_IPSR_GPSR(IP7_23_21, VI0_R0),
 	PINMUX_IPSR_MSEL(IP7_23_21, SCIF2_TXD_C, SEL_SCIF2_2),
 	PINMUX_IPSR_MSEL(IP7_23_21, IIC1_SDA_D, SEL_IIC01_3),
-	PINMUX_IPSR_DATA(IP7_23_21, AVB_TXD7),
+	PINMUX_IPSR_GPSR(IP7_23_21, AVB_TXD7),
 	PINMUX_IPSR_MSEL(IP7_23_21, SSI_SDATA5_B, SEL_SSI5_1),
 	PINMUX_IPSR_MSEL(IP7_26_24, ETH_MAGIC, SEL_ETH_0),
-	PINMUX_IPSR_DATA(IP7_26_24, VI0_R1),
+	PINMUX_IPSR_GPSR(IP7_26_24, VI0_R1),
 	PINMUX_IPSR_MSEL(IP7_26_24, SCIF3_SCK_B, SEL_SCIF3_1),
-	PINMUX_IPSR_DATA(IP7_26_24, AVB_TX_ER),
+	PINMUX_IPSR_GPSR(IP7_26_24, AVB_TX_ER),
 	PINMUX_IPSR_MSEL(IP7_26_24, SSI_SCK6_B, SEL_SSI6_1),
 	PINMUX_IPSR_MSEL(IP7_29_27, ETH_TXD0, SEL_ETH_0),
-	PINMUX_IPSR_DATA(IP7_29_27, VI0_R2),
+	PINMUX_IPSR_GPSR(IP7_29_27, VI0_R2),
 	PINMUX_IPSR_MSEL(IP7_29_27, SCIF3_RXD_B, SEL_SCIF3_1),
 	PINMUX_IPSR_MSEL(IP7_29_27, I2C4_SCL_E, SEL_I2C04_4),
-	PINMUX_IPSR_DATA(IP7_29_27, AVB_GTX_CLK),
+	PINMUX_IPSR_GPSR(IP7_29_27, AVB_GTX_CLK),
 	PINMUX_IPSR_MSEL(IP7_29_27, SSI_WS6_B, SEL_SSI6_1),
-	PINMUX_IPSR_DATA(IP7_31, DREQ0_N),
-	PINMUX_IPSR_DATA(IP7_31, SCIFB1_RXD),
+	PINMUX_IPSR_GPSR(IP7_31, DREQ0_N),
+	PINMUX_IPSR_GPSR(IP7_31, SCIFB1_RXD),
 
 	/* IPSR8 */
 	PINMUX_IPSR_MSEL(IP8_2_0, ETH_MDC, SEL_ETH_0),
-	PINMUX_IPSR_DATA(IP8_2_0, VI0_R3),
+	PINMUX_IPSR_GPSR(IP8_2_0, VI0_R3),
 	PINMUX_IPSR_MSEL(IP8_2_0, SCIF3_TXD_B, SEL_SCIF3_1),
 	PINMUX_IPSR_MSEL(IP8_2_0, I2C4_SDA_E, SEL_I2C04_4),
-	PINMUX_IPSR_DATA(IP8_2_0, AVB_MDC),
+	PINMUX_IPSR_GPSR(IP8_2_0, AVB_MDC),
 	PINMUX_IPSR_MSEL(IP8_2_0, SSI_SDATA6_B, SEL_SSI6_1),
 	PINMUX_IPSR_MSEL(IP8_5_3, HSCIF0_HRX, SEL_HSCIF0_0),
-	PINMUX_IPSR_DATA(IP8_5_3, VI0_R4),
+	PINMUX_IPSR_GPSR(IP8_5_3, VI0_R4),
 	PINMUX_IPSR_MSEL(IP8_5_3, I2C1_SCL_C, SEL_I2C01_2),
 	PINMUX_IPSR_MSEL(IP8_5_3, AUDIO_CLKA_B, SEL_ADG_1),
-	PINMUX_IPSR_DATA(IP8_5_3, AVB_MDIO),
+	PINMUX_IPSR_GPSR(IP8_5_3, AVB_MDIO),
 	PINMUX_IPSR_MSEL(IP8_5_3, SSI_SCK78_B, SEL_SSI7_1),
 	PINMUX_IPSR_MSEL(IP8_8_6, HSCIF0_HTX, SEL_HSCIF0_0),
-	PINMUX_IPSR_DATA(IP8_8_6, VI0_R5),
+	PINMUX_IPSR_GPSR(IP8_8_6, VI0_R5),
 	PINMUX_IPSR_MSEL(IP8_8_6, I2C1_SDA_C, SEL_I2C01_2),
 	PINMUX_IPSR_MSEL(IP8_8_6, AUDIO_CLKB_B, SEL_ADG_1),
-	PINMUX_IPSR_DATA(IP8_5_3, AVB_LINK),
+	PINMUX_IPSR_GPSR(IP8_5_3, AVB_LINK),
 	PINMUX_IPSR_MSEL(IP8_8_6, SSI_WS78_B, SEL_SSI7_1),
-	PINMUX_IPSR_DATA(IP8_11_9, HSCIF0_HCTS_N),
-	PINMUX_IPSR_DATA(IP8_11_9, VI0_R6),
+	PINMUX_IPSR_GPSR(IP8_11_9, HSCIF0_HCTS_N),
+	PINMUX_IPSR_GPSR(IP8_11_9, VI0_R6),
 	PINMUX_IPSR_MSEL(IP8_11_9, SCIF0_RXD_D, SEL_SCIF0_3),
 	PINMUX_IPSR_MSEL(IP8_11_9, I2C0_SCL_E, SEL_I2C00_4),
-	PINMUX_IPSR_DATA(IP8_11_9, AVB_MAGIC),
+	PINMUX_IPSR_GPSR(IP8_11_9, AVB_MAGIC),
 	PINMUX_IPSR_MSEL(IP8_11_9, SSI_SDATA7_B, SEL_SSI7_1),
-	PINMUX_IPSR_DATA(IP8_14_12, HSCIF0_HRTS_N),
-	PINMUX_IPSR_DATA(IP8_14_12, VI0_R7),
+	PINMUX_IPSR_GPSR(IP8_14_12, HSCIF0_HRTS_N),
+	PINMUX_IPSR_GPSR(IP8_14_12, VI0_R7),
 	PINMUX_IPSR_MSEL(IP8_14_12, SCIF0_TXD_D, SEL_SCIF0_3),
 	PINMUX_IPSR_MSEL(IP8_14_12, I2C0_SDA_E, SEL_I2C00_4),
-	PINMUX_IPSR_DATA(IP8_14_12, AVB_PHY_INT),
+	PINMUX_IPSR_GPSR(IP8_14_12, AVB_PHY_INT),
 	PINMUX_IPSR_MSEL(IP8_14_12, SSI_SDATA8_B, SEL_SSI8_1),
 	PINMUX_IPSR_MSEL(IP8_16_15, HSCIF0_HSCK, SEL_HSCIF0_0),
 	PINMUX_IPSR_MSEL(IP8_16_15, SCIF_CLK_B, SEL_SCIF0_1),
-	PINMUX_IPSR_DATA(IP8_16_15, AVB_CRS),
+	PINMUX_IPSR_GPSR(IP8_16_15, AVB_CRS),
 	PINMUX_IPSR_MSEL(IP8_16_15, AUDIO_CLKC_B, SEL_ADG_1),
 	PINMUX_IPSR_MSEL(IP8_19_17, I2C0_SCL, SEL_I2C00_0),
 	PINMUX_IPSR_MSEL(IP8_19_17, SCIF0_RXD_C, SEL_SCIF0_2),
-	PINMUX_IPSR_DATA(IP8_19_17, PWM5),
+	PINMUX_IPSR_GPSR(IP8_19_17, PWM5),
 	PINMUX_IPSR_MSEL(IP8_19_17, TCLK1_B, SEL_TMU_1),
-	PINMUX_IPSR_DATA(IP8_19_17, AVB_GTXREFCLK),
+	PINMUX_IPSR_GPSR(IP8_19_17, AVB_GTXREFCLK),
 	PINMUX_IPSR_MSEL(IP8_19_17, CAN1_RX_D, SEL_CAN1_3),
-	PINMUX_IPSR_DATA(IP8_19_17, TPUTO0_B),
+	PINMUX_IPSR_GPSR(IP8_19_17, TPUTO0_B),
 	PINMUX_IPSR_MSEL(IP8_22_20, I2C0_SDA, SEL_I2C00_0),
 	PINMUX_IPSR_MSEL(IP8_22_20, SCIF0_TXD_C, SEL_SCIF0_2),
-	PINMUX_IPSR_DATA(IP8_22_20, TPUTO0),
+	PINMUX_IPSR_GPSR(IP8_22_20, TPUTO0),
 	PINMUX_IPSR_MSEL(IP8_22_20, CAN_CLK, SEL_CAN_0),
-	PINMUX_IPSR_DATA(IP8_22_20, DVC_MUTE),
+	PINMUX_IPSR_GPSR(IP8_22_20, DVC_MUTE),
 	PINMUX_IPSR_MSEL(IP8_22_20, CAN1_TX_D, SEL_CAN1_3),
 	PINMUX_IPSR_MSEL(IP8_25_23, I2C1_SCL, SEL_I2C01_0),
 	PINMUX_IPSR_MSEL(IP8_25_23, SCIF4_RXD, SEL_SCIF4_0),
-	PINMUX_IPSR_DATA(IP8_25_23, PWM5_B),
-	PINMUX_IPSR_DATA(IP8_25_23, DU1_DR0),
+	PINMUX_IPSR_GPSR(IP8_25_23, PWM5_B),
+	PINMUX_IPSR_GPSR(IP8_25_23, DU1_DR0),
 	PINMUX_IPSR_MSEL(IP8_25_23, RIF1_SYNC_B, SEL_DR2_1),
 	PINMUX_IPSR_MSEL(IP8_25_23, TS_SDATA_D, SEL_TSIF0_3),
-	PINMUX_IPSR_DATA(IP8_25_23, TPUTO1_B),
+	PINMUX_IPSR_GPSR(IP8_25_23, TPUTO1_B),
 	PINMUX_IPSR_MSEL(IP8_28_26, I2C1_SDA, SEL_I2C01_0),
 	PINMUX_IPSR_MSEL(IP8_28_26, SCIF4_TXD, SEL_SCIF4_0),
-	PINMUX_IPSR_DATA(IP8_28_26, IRQ5),
-	PINMUX_IPSR_DATA(IP8_28_26, DU1_DR1),
+	PINMUX_IPSR_GPSR(IP8_28_26, IRQ5),
+	PINMUX_IPSR_GPSR(IP8_28_26, DU1_DR1),
 	PINMUX_IPSR_MSEL(IP8_28_26, RIF1_CLK_B, SEL_DR2_1),
 	PINMUX_IPSR_MSEL(IP8_28_26, TS_SCK_D, SEL_TSIF0_3),
 	PINMUX_IPSR_MSEL(IP8_28_26, BPFCLK_C, SEL_DARC_2),
-	PINMUX_IPSR_DATA(IP8_31_29, MSIOF0_RXD),
+	PINMUX_IPSR_GPSR(IP8_31_29, MSIOF0_RXD),
 	PINMUX_IPSR_MSEL(IP8_31_29, SCIF5_RXD, SEL_SCIF5_0),
 	PINMUX_IPSR_MSEL(IP8_31_29, I2C2_SCL_C, SEL_I2C02_2),
-	PINMUX_IPSR_DATA(IP8_31_29, DU1_DR2),
+	PINMUX_IPSR_GPSR(IP8_31_29, DU1_DR2),
 	PINMUX_IPSR_MSEL(IP8_31_29, RIF1_D0_B, SEL_DR2_1),
 	PINMUX_IPSR_MSEL(IP8_31_29, TS_SDEN_D, SEL_TSIF0_3),
 	PINMUX_IPSR_MSEL(IP8_31_29, FMCLK_C, SEL_DARC_2),
 	PINMUX_IPSR_MSEL(IP8_31_29, RDS_CLK, SEL_RDS_0),
 
 	/* IPSR9 */
-	PINMUX_IPSR_DATA(IP9_2_0, MSIOF0_TXD),
+	PINMUX_IPSR_GPSR(IP9_2_0, MSIOF0_TXD),
 	PINMUX_IPSR_MSEL(IP9_2_0, SCIF5_TXD, SEL_SCIF5_0),
 	PINMUX_IPSR_MSEL(IP9_2_0, I2C2_SDA_C, SEL_I2C02_2),
-	PINMUX_IPSR_DATA(IP9_2_0, DU1_DR3),
+	PINMUX_IPSR_GPSR(IP9_2_0, DU1_DR3),
 	PINMUX_IPSR_MSEL(IP9_2_0, RIF1_D1_B, SEL_DR3_1),
 	PINMUX_IPSR_MSEL(IP9_2_0, TS_SPSYNC_D, SEL_TSIF0_3),
 	PINMUX_IPSR_MSEL(IP9_2_0, FMIN_C, SEL_DARC_2),
 	PINMUX_IPSR_MSEL(IP9_2_0, RDS_DATA, SEL_RDS_0),
-	PINMUX_IPSR_DATA(IP9_5_3, MSIOF0_SCK),
-	PINMUX_IPSR_DATA(IP9_5_3, IRQ0),
+	PINMUX_IPSR_GPSR(IP9_5_3, MSIOF0_SCK),
+	PINMUX_IPSR_GPSR(IP9_5_3, IRQ0),
 	PINMUX_IPSR_MSEL(IP9_5_3, TS_SDATA, SEL_TSIF0_0),
-	PINMUX_IPSR_DATA(IP9_5_3, DU1_DR4),
+	PINMUX_IPSR_GPSR(IP9_5_3, DU1_DR4),
 	PINMUX_IPSR_MSEL(IP9_5_3, RIF1_SYNC, SEL_DR2_0),
-	PINMUX_IPSR_DATA(IP9_5_3, TPUTO1_C),
-	PINMUX_IPSR_DATA(IP9_8_6, MSIOF0_SYNC),
-	PINMUX_IPSR_DATA(IP9_8_6, PWM1),
+	PINMUX_IPSR_GPSR(IP9_5_3, TPUTO1_C),
+	PINMUX_IPSR_GPSR(IP9_8_6, MSIOF0_SYNC),
+	PINMUX_IPSR_GPSR(IP9_8_6, PWM1),
 	PINMUX_IPSR_MSEL(IP9_8_6, TS_SCK, SEL_TSIF0_0),
-	PINMUX_IPSR_DATA(IP9_8_6, DU1_DR5),
+	PINMUX_IPSR_GPSR(IP9_8_6, DU1_DR5),
 	PINMUX_IPSR_MSEL(IP9_8_6, RIF1_CLK, SEL_DR2_0),
 	PINMUX_IPSR_MSEL(IP9_8_6, BPFCLK_B, SEL_DARC_1),
-	PINMUX_IPSR_DATA(IP9_11_9, MSIOF0_SS1),
+	PINMUX_IPSR_GPSR(IP9_11_9, MSIOF0_SS1),
 	PINMUX_IPSR_MSEL(IP9_11_9, SCIFA0_RXD, SEL_SCIFA0_0),
 	PINMUX_IPSR_MSEL(IP9_11_9, TS_SDEN, SEL_TSIF0_0),
-	PINMUX_IPSR_DATA(IP9_11_9, DU1_DR6),
+	PINMUX_IPSR_GPSR(IP9_11_9, DU1_DR6),
 	PINMUX_IPSR_MSEL(IP9_11_9, RIF1_D0, SEL_DR2_0),
 	PINMUX_IPSR_MSEL(IP9_11_9, FMCLK_B, SEL_DARC_1),
 	PINMUX_IPSR_MSEL(IP9_11_9, RDS_CLK_B, SEL_RDS_1),
-	PINMUX_IPSR_DATA(IP9_14_12, MSIOF0_SS2),
+	PINMUX_IPSR_GPSR(IP9_14_12, MSIOF0_SS2),
 	PINMUX_IPSR_MSEL(IP9_14_12, SCIFA0_TXD, SEL_SCIFA0_0),
 	PINMUX_IPSR_MSEL(IP9_14_12, TS_SPSYNC, SEL_TSIF0_0),
-	PINMUX_IPSR_DATA(IP9_14_12, DU1_DR7),
+	PINMUX_IPSR_GPSR(IP9_14_12, DU1_DR7),
 	PINMUX_IPSR_MSEL(IP9_14_12, RIF1_D1, SEL_DR3_0),
 	PINMUX_IPSR_MSEL(IP9_14_12, FMIN_B, SEL_DARC_1),
 	PINMUX_IPSR_MSEL(IP9_14_12, RDS_DATA_B, SEL_RDS_1),
 	PINMUX_IPSR_MSEL(IP9_16_15, HSCIF1_HRX, SEL_HSCIF1_0),
 	PINMUX_IPSR_MSEL(IP9_16_15, I2C4_SCL, SEL_I2C04_0),
-	PINMUX_IPSR_DATA(IP9_16_15, PWM6),
-	PINMUX_IPSR_DATA(IP9_16_15, DU1_DG0),
+	PINMUX_IPSR_GPSR(IP9_16_15, PWM6),
+	PINMUX_IPSR_GPSR(IP9_16_15, DU1_DG0),
 	PINMUX_IPSR_MSEL(IP9_18_17, HSCIF1_HTX, SEL_HSCIF1_0),
 	PINMUX_IPSR_MSEL(IP9_18_17, I2C4_SDA, SEL_I2C04_0),
-	PINMUX_IPSR_DATA(IP9_18_17, TPUTO1),
-	PINMUX_IPSR_DATA(IP9_18_17, DU1_DG1),
-	PINMUX_IPSR_DATA(IP9_21_19, HSCIF1_HSCK),
-	PINMUX_IPSR_DATA(IP9_21_19, PWM2),
+	PINMUX_IPSR_GPSR(IP9_18_17, TPUTO1),
+	PINMUX_IPSR_GPSR(IP9_18_17, DU1_DG1),
+	PINMUX_IPSR_GPSR(IP9_21_19, HSCIF1_HSCK),
+	PINMUX_IPSR_GPSR(IP9_21_19, PWM2),
 	PINMUX_IPSR_MSEL(IP9_21_19, IETX, SEL_IEB_0),
-	PINMUX_IPSR_DATA(IP9_21_19, DU1_DG2),
+	PINMUX_IPSR_GPSR(IP9_21_19, DU1_DG2),
 	PINMUX_IPSR_MSEL(IP9_21_19, REMOCON_B, SEL_RCN_1),
 	PINMUX_IPSR_MSEL(IP9_21_19, SPEEDIN_B, SEL_RSP_1),
 	PINMUX_IPSR_MSEL(IP9_21_19, VSP_B, SEL_SPDM_1),
 	PINMUX_IPSR_MSEL(IP9_24_22, HSCIF1_HCTS_N, SEL_HSCIF1_0),
 	PINMUX_IPSR_MSEL(IP9_24_22, SCIFA4_RXD, SEL_SCIFA4_0),
 	PINMUX_IPSR_MSEL(IP9_24_22, IECLK, SEL_IEB_0),
-	PINMUX_IPSR_DATA(IP9_24_22, DU1_DG3),
+	PINMUX_IPSR_GPSR(IP9_24_22, DU1_DG3),
 	PINMUX_IPSR_MSEL(IP9_24_22, SSI_SCK1_B, SEL_SSI1_1),
-	PINMUX_IPSR_DATA(IP9_24_22, CAN_DEBUG_HW_TRIGGER),
-	PINMUX_IPSR_DATA(IP9_24_22, CC50_STATE32),
+	PINMUX_IPSR_GPSR(IP9_24_22, CAN_DEBUG_HW_TRIGGER),
+	PINMUX_IPSR_GPSR(IP9_24_22, CC50_STATE32),
 	PINMUX_IPSR_MSEL(IP9_27_25, HSCIF1_HRTS_N, SEL_HSCIF1_0),
 	PINMUX_IPSR_MSEL(IP9_27_25, SCIFA4_TXD, SEL_SCIFA4_0),
 	PINMUX_IPSR_MSEL(IP9_27_25, IERX, SEL_IEB_0),
-	PINMUX_IPSR_DATA(IP9_27_25, DU1_DG4),
+	PINMUX_IPSR_GPSR(IP9_27_25, DU1_DG4),
 	PINMUX_IPSR_MSEL(IP9_27_25, SSI_WS1_B, SEL_SSI1_1),
-	PINMUX_IPSR_DATA(IP9_27_25, CAN_STEP0),
-	PINMUX_IPSR_DATA(IP9_27_25, CC50_STATE33),
+	PINMUX_IPSR_GPSR(IP9_27_25, CAN_STEP0),
+	PINMUX_IPSR_GPSR(IP9_27_25, CC50_STATE33),
 	PINMUX_IPSR_MSEL(IP9_30_28, SCIF1_SCK, SEL_SCIF1_0),
-	PINMUX_IPSR_DATA(IP9_30_28, PWM3),
+	PINMUX_IPSR_GPSR(IP9_30_28, PWM3),
 	PINMUX_IPSR_MSEL(IP9_30_28, TCLK2, SEL_TMU_0),
-	PINMUX_IPSR_DATA(IP9_30_28, DU1_DG5),
+	PINMUX_IPSR_GPSR(IP9_30_28, DU1_DG5),
 	PINMUX_IPSR_MSEL(IP9_30_28, SSI_SDATA1_B, SEL_SSI1_1),
-	PINMUX_IPSR_DATA(IP9_30_28, CAN_TXCLK),
-	PINMUX_IPSR_DATA(IP9_30_28, CC50_STATE34),
+	PINMUX_IPSR_GPSR(IP9_30_28, CAN_TXCLK),
+	PINMUX_IPSR_GPSR(IP9_30_28, CC50_STATE34),
 
 	/* IPSR10 */
 	PINMUX_IPSR_MSEL(IP10_2_0, SCIF1_RXD, SEL_SCIF1_0),
 	PINMUX_IPSR_MSEL(IP10_2_0, IIC0_SCL, SEL_IIC00_0),
-	PINMUX_IPSR_DATA(IP10_2_0, DU1_DG6),
+	PINMUX_IPSR_GPSR(IP10_2_0, DU1_DG6),
 	PINMUX_IPSR_MSEL(IP10_2_0, SSI_SCK2_B, SEL_SSI2_1),
-	PINMUX_IPSR_DATA(IP10_2_0, CAN_DEBUGOUT0),
-	PINMUX_IPSR_DATA(IP10_2_0, CC50_STATE35),
+	PINMUX_IPSR_GPSR(IP10_2_0, CAN_DEBUGOUT0),
+	PINMUX_IPSR_GPSR(IP10_2_0, CC50_STATE35),
 	PINMUX_IPSR_MSEL(IP10_5_3, SCIF1_TXD, SEL_SCIF1_0),
 	PINMUX_IPSR_MSEL(IP10_5_3, IIC0_SDA, SEL_IIC00_0),
-	PINMUX_IPSR_DATA(IP10_5_3, DU1_DG7),
+	PINMUX_IPSR_GPSR(IP10_5_3, DU1_DG7),
 	PINMUX_IPSR_MSEL(IP10_5_3, SSI_WS2_B, SEL_SSI2_1),
-	PINMUX_IPSR_DATA(IP10_5_3, CAN_DEBUGOUT1),
-	PINMUX_IPSR_DATA(IP10_5_3, CC50_STATE36),
+	PINMUX_IPSR_GPSR(IP10_5_3, CAN_DEBUGOUT1),
+	PINMUX_IPSR_GPSR(IP10_5_3, CC50_STATE36),
 	PINMUX_IPSR_MSEL(IP10_8_6, SCIF2_RXD, SEL_SCIF2_0),
 	PINMUX_IPSR_MSEL(IP10_8_6, IIC1_SCL, SEL_IIC01_0),
-	PINMUX_IPSR_DATA(IP10_8_6, DU1_DB0),
+	PINMUX_IPSR_GPSR(IP10_8_6, DU1_DB0),
 	PINMUX_IPSR_MSEL(IP10_8_6, SSI_SDATA2_B, SEL_SSI2_1),
-	PINMUX_IPSR_DATA(IP10_8_6, USB0_EXTLP),
-	PINMUX_IPSR_DATA(IP10_8_6, CAN_DEBUGOUT2),
-	PINMUX_IPSR_DATA(IP10_8_6, CC50_STATE37),
+	PINMUX_IPSR_GPSR(IP10_8_6, USB0_EXTLP),
+	PINMUX_IPSR_GPSR(IP10_8_6, CAN_DEBUGOUT2),
+	PINMUX_IPSR_GPSR(IP10_8_6, CC50_STATE37),
 	PINMUX_IPSR_MSEL(IP10_11_9, SCIF2_TXD, SEL_SCIF2_0),
 	PINMUX_IPSR_MSEL(IP10_11_9, IIC1_SDA, SEL_IIC01_0),
-	PINMUX_IPSR_DATA(IP10_11_9, DU1_DB1),
+	PINMUX_IPSR_GPSR(IP10_11_9, DU1_DB1),
 	PINMUX_IPSR_MSEL(IP10_11_9, SSI_SCK9_B, SEL_SSI9_1),
-	PINMUX_IPSR_DATA(IP10_11_9, USB0_OVC1),
-	PINMUX_IPSR_DATA(IP10_11_9, CAN_DEBUGOUT3),
-	PINMUX_IPSR_DATA(IP10_11_9, CC50_STATE38),
+	PINMUX_IPSR_GPSR(IP10_11_9, USB0_OVC1),
+	PINMUX_IPSR_GPSR(IP10_11_9, CAN_DEBUGOUT3),
+	PINMUX_IPSR_GPSR(IP10_11_9, CC50_STATE38),
 	PINMUX_IPSR_MSEL(IP10_14_12, SCIF2_SCK, SEL_SCIF2_0),
-	PINMUX_IPSR_DATA(IP10_14_12, IRQ1),
-	PINMUX_IPSR_DATA(IP10_14_12, DU1_DB2),
+	PINMUX_IPSR_GPSR(IP10_14_12, IRQ1),
+	PINMUX_IPSR_GPSR(IP10_14_12, DU1_DB2),
 	PINMUX_IPSR_MSEL(IP10_14_12, SSI_WS9_B, SEL_SSI9_1),
-	PINMUX_IPSR_DATA(IP10_14_12, USB0_IDIN),
-	PINMUX_IPSR_DATA(IP10_14_12, CAN_DEBUGOUT4),
-	PINMUX_IPSR_DATA(IP10_14_12, CC50_STATE39),
+	PINMUX_IPSR_GPSR(IP10_14_12, USB0_IDIN),
+	PINMUX_IPSR_GPSR(IP10_14_12, CAN_DEBUGOUT4),
+	PINMUX_IPSR_GPSR(IP10_14_12, CC50_STATE39),
 	PINMUX_IPSR_MSEL(IP10_17_15, SCIF3_SCK, SEL_SCIF3_0),
-	PINMUX_IPSR_DATA(IP10_17_15, IRQ2),
+	PINMUX_IPSR_GPSR(IP10_17_15, IRQ2),
 	PINMUX_IPSR_MSEL(IP10_17_15, BPFCLK_D, SEL_DARC_3),
-	PINMUX_IPSR_DATA(IP10_17_15, DU1_DB3),
+	PINMUX_IPSR_GPSR(IP10_17_15, DU1_DB3),
 	PINMUX_IPSR_MSEL(IP10_17_15, SSI_SDATA9_B, SEL_SSI9_1),
-	PINMUX_IPSR_DATA(IP10_17_15, TANS2),
-	PINMUX_IPSR_DATA(IP10_17_15, CAN_DEBUGOUT5),
-	PINMUX_IPSR_DATA(IP10_17_15, CC50_OSCOUT),
+	PINMUX_IPSR_GPSR(IP10_17_15, TANS2),
+	PINMUX_IPSR_GPSR(IP10_17_15, CAN_DEBUGOUT5),
+	PINMUX_IPSR_GPSR(IP10_17_15, CC50_OSCOUT),
 	PINMUX_IPSR_MSEL(IP10_20_18, SCIF3_RXD, SEL_SCIF3_0),
 	PINMUX_IPSR_MSEL(IP10_20_18, I2C1_SCL_E, SEL_I2C01_4),
 	PINMUX_IPSR_MSEL(IP10_20_18, FMCLK_D, SEL_DARC_3),
-	PINMUX_IPSR_DATA(IP10_20_18, DU1_DB4),
+	PINMUX_IPSR_GPSR(IP10_20_18, DU1_DB4),
 	PINMUX_IPSR_MSEL(IP10_20_18, AUDIO_CLKA_C, SEL_ADG_2),
 	PINMUX_IPSR_MSEL(IP10_20_18, SSI_SCK4_B, SEL_SSI4_1),
-	PINMUX_IPSR_DATA(IP10_20_18, CAN_DEBUGOUT6),
+	PINMUX_IPSR_GPSR(IP10_20_18, CAN_DEBUGOUT6),
 	PINMUX_IPSR_MSEL(IP10_20_18, RDS_CLK_C, SEL_RDS_2),
 	PINMUX_IPSR_MSEL(IP10_23_21, SCIF3_TXD, SEL_SCIF3_0),
 	PINMUX_IPSR_MSEL(IP10_23_21, I2C1_SDA_E, SEL_I2C01_4),
 	PINMUX_IPSR_MSEL(IP10_23_21, FMIN_D, SEL_DARC_3),
-	PINMUX_IPSR_DATA(IP10_23_21, DU1_DB5),
+	PINMUX_IPSR_GPSR(IP10_23_21, DU1_DB5),
 	PINMUX_IPSR_MSEL(IP10_23_21, AUDIO_CLKB_C, SEL_ADG_2),
 	PINMUX_IPSR_MSEL(IP10_23_21, SSI_WS4_B, SEL_SSI4_1),
-	PINMUX_IPSR_DATA(IP10_23_21, CAN_DEBUGOUT7),
+	PINMUX_IPSR_GPSR(IP10_23_21, CAN_DEBUGOUT7),
 	PINMUX_IPSR_MSEL(IP10_23_21, RDS_DATA_C, SEL_RDS_2),
 	PINMUX_IPSR_MSEL(IP10_26_24, I2C2_SCL, SEL_I2C02_0),
 	PINMUX_IPSR_MSEL(IP10_26_24, SCIFA5_RXD, SEL_SCIFA5_0),
-	PINMUX_IPSR_DATA(IP10_26_24, DU1_DB6),
+	PINMUX_IPSR_GPSR(IP10_26_24, DU1_DB6),
 	PINMUX_IPSR_MSEL(IP10_26_24, AUDIO_CLKC_C, SEL_ADG_2),
 	PINMUX_IPSR_MSEL(IP10_26_24, SSI_SDATA4_B, SEL_SSI4_1),
-	PINMUX_IPSR_DATA(IP10_26_24, CAN_DEBUGOUT8),
+	PINMUX_IPSR_GPSR(IP10_26_24, CAN_DEBUGOUT8),
 	PINMUX_IPSR_MSEL(IP10_29_27, I2C2_SDA, SEL_I2C02_0),
 	PINMUX_IPSR_MSEL(IP10_29_27, SCIFA5_TXD, SEL_SCIFA5_0),
-	PINMUX_IPSR_DATA(IP10_29_27, DU1_DB7),
+	PINMUX_IPSR_GPSR(IP10_29_27, DU1_DB7),
 	PINMUX_IPSR_MSEL(IP10_29_27, AUDIO_CLKOUT_C, SEL_ADG_2),
-	PINMUX_IPSR_DATA(IP10_29_27, CAN_DEBUGOUT9),
+	PINMUX_IPSR_GPSR(IP10_29_27, CAN_DEBUGOUT9),
 	PINMUX_IPSR_MSEL(IP10_31_30, SSI_SCK5, SEL_SSI5_0),
 	PINMUX_IPSR_MSEL(IP10_31_30, SCIFA3_SCK, SEL_SCIFA3_0),
-	PINMUX_IPSR_DATA(IP10_31_30, DU1_DOTCLKIN),
-	PINMUX_IPSR_DATA(IP10_31_30, CAN_DEBUGOUT10),
+	PINMUX_IPSR_GPSR(IP10_31_30, DU1_DOTCLKIN),
+	PINMUX_IPSR_GPSR(IP10_31_30, CAN_DEBUGOUT10),
 
 	/* IPSR11 */
 	PINMUX_IPSR_MSEL(IP11_2_0, SSI_WS5, SEL_SSI5_0),
 	PINMUX_IPSR_MSEL(IP11_2_0, SCIFA3_RXD, SEL_SCIFA3_0),
 	PINMUX_IPSR_MSEL(IP11_2_0, I2C3_SCL_C, SEL_I2C03_2),
-	PINMUX_IPSR_DATA(IP11_2_0, DU1_DOTCLKOUT0),
-	PINMUX_IPSR_DATA(IP11_2_0, CAN_DEBUGOUT11),
+	PINMUX_IPSR_GPSR(IP11_2_0, DU1_DOTCLKOUT0),
+	PINMUX_IPSR_GPSR(IP11_2_0, CAN_DEBUGOUT11),
 	PINMUX_IPSR_MSEL(IP11_5_3, SSI_SDATA5, SEL_SSI5_0),
 	PINMUX_IPSR_MSEL(IP11_5_3, SCIFA3_TXD, SEL_SCIFA3_0),
 	PINMUX_IPSR_MSEL(IP11_5_3, I2C3_SDA_C, SEL_I2C03_2),
-	PINMUX_IPSR_DATA(IP11_5_3, DU1_DOTCLKOUT1),
-	PINMUX_IPSR_DATA(IP11_5_3, CAN_DEBUGOUT12),
+	PINMUX_IPSR_GPSR(IP11_5_3, DU1_DOTCLKOUT1),
+	PINMUX_IPSR_GPSR(IP11_5_3, CAN_DEBUGOUT12),
 	PINMUX_IPSR_MSEL(IP11_7_6, SSI_SCK6, SEL_SSI6_0),
 	PINMUX_IPSR_MSEL(IP11_7_6, SCIFA1_SCK_B, SEL_SCIFA1_1),
-	PINMUX_IPSR_DATA(IP11_7_6, DU1_EXHSYNC_DU1_HSYNC),
-	PINMUX_IPSR_DATA(IP11_7_6, CAN_DEBUGOUT13),
+	PINMUX_IPSR_GPSR(IP11_7_6, DU1_EXHSYNC_DU1_HSYNC),
+	PINMUX_IPSR_GPSR(IP11_7_6, CAN_DEBUGOUT13),
 	PINMUX_IPSR_MSEL(IP11_10_8, SSI_WS6, SEL_SSI6_0),
 	PINMUX_IPSR_MSEL(IP11_10_8, SCIFA1_RXD_B, SEL_SCIFA1_1),
 	PINMUX_IPSR_MSEL(IP11_10_8, I2C4_SCL_C, SEL_I2C04_2),
-	PINMUX_IPSR_DATA(IP11_10_8, DU1_EXVSYNC_DU1_VSYNC),
-	PINMUX_IPSR_DATA(IP11_10_8, CAN_DEBUGOUT14),
+	PINMUX_IPSR_GPSR(IP11_10_8, DU1_EXVSYNC_DU1_VSYNC),
+	PINMUX_IPSR_GPSR(IP11_10_8, CAN_DEBUGOUT14),
 	PINMUX_IPSR_MSEL(IP11_13_11, SSI_SDATA6, SEL_SSI6_0),
 	PINMUX_IPSR_MSEL(IP11_13_11, SCIFA1_TXD_B, SEL_SCIFA1_1),
 	PINMUX_IPSR_MSEL(IP11_13_11, I2C4_SDA_C, SEL_I2C04_2),
-	PINMUX_IPSR_DATA(IP11_13_11, DU1_EXODDF_DU1_ODDF_DISP_CDE),
-	PINMUX_IPSR_DATA(IP11_13_11, CAN_DEBUGOUT15),
+	PINMUX_IPSR_GPSR(IP11_13_11, DU1_EXODDF_DU1_ODDF_DISP_CDE),
+	PINMUX_IPSR_GPSR(IP11_13_11, CAN_DEBUGOUT15),
 	PINMUX_IPSR_MSEL(IP11_15_14, SSI_SCK78, SEL_SSI7_0),
 	PINMUX_IPSR_MSEL(IP11_15_14, SCIFA2_SCK_B, SEL_SCIFA2_1),
 	PINMUX_IPSR_MSEL(IP11_15_14, IIC0_SDA_C, SEL_IIC00_2),
-	PINMUX_IPSR_DATA(IP11_15_14, DU1_DISP),
+	PINMUX_IPSR_GPSR(IP11_15_14, DU1_DISP),
 	PINMUX_IPSR_MSEL(IP11_17_16, SSI_WS78, SEL_SSI7_0),
 	PINMUX_IPSR_MSEL(IP11_17_16, SCIFA2_RXD_B, SEL_SCIFA2_1),
 	PINMUX_IPSR_MSEL(IP11_17_16, IIC0_SCL_C, SEL_IIC00_2),
-	PINMUX_IPSR_DATA(IP11_17_16, DU1_CDE),
+	PINMUX_IPSR_GPSR(IP11_17_16, DU1_CDE),
 	PINMUX_IPSR_MSEL(IP11_20_18, SSI_SDATA7, SEL_SSI7_0),
 	PINMUX_IPSR_MSEL(IP11_20_18, SCIFA2_TXD_B, SEL_SCIFA2_1),
-	PINMUX_IPSR_DATA(IP11_20_18, IRQ8),
+	PINMUX_IPSR_GPSR(IP11_20_18, IRQ8),
 	PINMUX_IPSR_MSEL(IP11_20_18, AUDIO_CLKA_D, SEL_ADG_3),
 	PINMUX_IPSR_MSEL(IP11_20_18, CAN_CLK_D, SEL_CAN_3),
-	PINMUX_IPSR_DATA(IP11_20_18, PCMOE_N),
-	PINMUX_IPSR_DATA(IP11_23_21, SSI_SCK0129),
+	PINMUX_IPSR_GPSR(IP11_20_18, PCMOE_N),
+	PINMUX_IPSR_GPSR(IP11_23_21, SSI_SCK0129),
 	PINMUX_IPSR_MSEL(IP11_23_21, MSIOF1_RXD_B, SEL_MSI1_1),
 	PINMUX_IPSR_MSEL(IP11_23_21, SCIF5_RXD_D, SEL_SCIF5_3),
 	PINMUX_IPSR_MSEL(IP11_23_21, ADIDATA_B, SEL_RAD_1),
 	PINMUX_IPSR_MSEL(IP11_23_21, AD_DI_B, SEL_ADI_1),
-	PINMUX_IPSR_DATA(IP11_23_21, PCMWE_N),
-	PINMUX_IPSR_DATA(IP11_26_24, SSI_WS0129),
+	PINMUX_IPSR_GPSR(IP11_23_21, PCMWE_N),
+	PINMUX_IPSR_GPSR(IP11_26_24, SSI_WS0129),
 	PINMUX_IPSR_MSEL(IP11_26_24, MSIOF1_TXD_B, SEL_MSI1_1),
 	PINMUX_IPSR_MSEL(IP11_26_24, SCIF5_TXD_D, SEL_SCIF5_3),
 	PINMUX_IPSR_MSEL(IP11_26_24, ADICS_SAMP_B, SEL_RAD_1),
 	PINMUX_IPSR_MSEL(IP11_26_24, AD_DO_B, SEL_ADI_1),
-	PINMUX_IPSR_DATA(IP11_29_27, SSI_SDATA0),
+	PINMUX_IPSR_GPSR(IP11_29_27, SSI_SDATA0),
 	PINMUX_IPSR_MSEL(IP11_29_27, MSIOF1_SCK_B, SEL_MSI1_1),
-	PINMUX_IPSR_DATA(IP11_29_27, PWM0_B),
+	PINMUX_IPSR_GPSR(IP11_29_27, PWM0_B),
 	PINMUX_IPSR_MSEL(IP11_29_27, ADICLK_B, SEL_RAD_1),
 	PINMUX_IPSR_MSEL(IP11_29_27, AD_CLK_B, SEL_ADI_1),
 
 	/* IPSR12 */
-	PINMUX_IPSR_DATA(IP12_2_0, SSI_SCK34),
+	PINMUX_IPSR_GPSR(IP12_2_0, SSI_SCK34),
 	PINMUX_IPSR_MSEL(IP12_2_0, MSIOF1_SYNC_B, SEL_MSI1_1),
 	PINMUX_IPSR_MSEL(IP12_2_0, SCIFA1_SCK_C, SEL_SCIFA1_2),
 	PINMUX_IPSR_MSEL(IP12_2_0, ADICHS0_B, SEL_RAD_1),
 	PINMUX_IPSR_MSEL(IP12_2_0, AD_NCS_N_B, SEL_ADI_1),
 	PINMUX_IPSR_MSEL(IP12_2_0, DREQ1_N_B, SEL_LBS_1),
-	PINMUX_IPSR_DATA(IP12_5_3, SSI_WS34),
+	PINMUX_IPSR_GPSR(IP12_5_3, SSI_WS34),
 	PINMUX_IPSR_MSEL(IP12_5_3, MSIOF1_SS1_B, SEL_MSI1_1),
 	PINMUX_IPSR_MSEL(IP12_5_3, SCIFA1_RXD_C, SEL_SCIFA1_2),
 	PINMUX_IPSR_MSEL(IP12_5_3, ADICHS1_B, SEL_RAD_1),
 	PINMUX_IPSR_MSEL(IP12_5_3, CAN1_RX_C, SEL_CAN1_2),
 	PINMUX_IPSR_MSEL(IP12_5_3, DACK1_B, SEL_LBS_1),
-	PINMUX_IPSR_DATA(IP12_8_6, SSI_SDATA3),
+	PINMUX_IPSR_GPSR(IP12_8_6, SSI_SDATA3),
 	PINMUX_IPSR_MSEL(IP12_8_6, MSIOF1_SS2_B, SEL_MSI1_1),
 	PINMUX_IPSR_MSEL(IP12_8_6, SCIFA1_TXD_C, SEL_SCIFA1_2),
 	PINMUX_IPSR_MSEL(IP12_8_6, ADICHS2_B, SEL_RAD_1),
 	PINMUX_IPSR_MSEL(IP12_8_6, CAN1_TX_C, SEL_CAN1_2),
-	PINMUX_IPSR_DATA(IP12_8_6, DREQ2_N),
+	PINMUX_IPSR_GPSR(IP12_8_6, DREQ2_N),
 	PINMUX_IPSR_MSEL(IP12_10_9, SSI_SCK4, SEL_SSI4_0),
-	PINMUX_IPSR_DATA(IP12_10_9, MLB_CLK),
+	PINMUX_IPSR_GPSR(IP12_10_9, MLB_CLK),
 	PINMUX_IPSR_MSEL(IP12_10_9, IETX_B, SEL_IEB_1),
-	PINMUX_IPSR_DATA(IP12_10_9, IRD_TX),
+	PINMUX_IPSR_GPSR(IP12_10_9, IRD_TX),
 	PINMUX_IPSR_MSEL(IP12_12_11, SSI_WS4, SEL_SSI4_0),
-	PINMUX_IPSR_DATA(IP12_12_11, MLB_SIG),
+	PINMUX_IPSR_GPSR(IP12_12_11, MLB_SIG),
 	PINMUX_IPSR_MSEL(IP12_12_11, IECLK_B, SEL_IEB_1),
-	PINMUX_IPSR_DATA(IP12_12_11, IRD_RX),
+	PINMUX_IPSR_GPSR(IP12_12_11, IRD_RX),
 	PINMUX_IPSR_MSEL(IP12_14_13, SSI_SDATA4, SEL_SSI4_0),
-	PINMUX_IPSR_DATA(IP12_14_13, MLB_DAT),
+	PINMUX_IPSR_GPSR(IP12_14_13, MLB_DAT),
 	PINMUX_IPSR_MSEL(IP12_14_13, IERX_B, SEL_IEB_1),
-	PINMUX_IPSR_DATA(IP12_14_13, IRD_SCK),
+	PINMUX_IPSR_GPSR(IP12_14_13, IRD_SCK),
 	PINMUX_IPSR_MSEL(IP12_17_15, SSI_SDATA8, SEL_SSI8_0),
 	PINMUX_IPSR_MSEL(IP12_17_15, SCIF1_SCK_B, SEL_SCIF1_1),
-	PINMUX_IPSR_DATA(IP12_17_15, PWM1_B),
-	PINMUX_IPSR_DATA(IP12_17_15, IRQ9),
+	PINMUX_IPSR_GPSR(IP12_17_15, PWM1_B),
+	PINMUX_IPSR_GPSR(IP12_17_15, IRQ9),
 	PINMUX_IPSR_MSEL(IP12_17_15, REMOCON, SEL_RCN_0),
-	PINMUX_IPSR_DATA(IP12_17_15, DACK2),
+	PINMUX_IPSR_GPSR(IP12_17_15, DACK2),
 	PINMUX_IPSR_MSEL(IP12_17_15, ETH_MDIO_B, SEL_ETH_1),
 	PINMUX_IPSR_MSEL(IP12_20_18, SSI_SCK1, SEL_SSI1_0),
 	PINMUX_IPSR_MSEL(IP12_20_18, SCIF1_RXD_B, SEL_SCIF1_1),
 	PINMUX_IPSR_MSEL(IP12_20_18, IIC1_SCL_C, SEL_IIC01_2),
-	PINMUX_IPSR_DATA(IP12_20_18, VI1_CLK),
+	PINMUX_IPSR_GPSR(IP12_20_18, VI1_CLK),
 	PINMUX_IPSR_MSEL(IP12_20_18, CAN0_RX_D, SEL_CAN0_3),
 	PINMUX_IPSR_MSEL(IP12_20_18, AVB_AVTP_CAPTURE, SEL_AVB_0),
 	PINMUX_IPSR_MSEL(IP12_20_18, ETH_CRS_DV_B, SEL_ETH_1),
 	PINMUX_IPSR_MSEL(IP12_23_21, SSI_WS1, SEL_SSI1_0),
 	PINMUX_IPSR_MSEL(IP12_23_21, SCIF1_TXD_B, SEL_SCIF1_1),
 	PINMUX_IPSR_MSEL(IP12_23_21, IIC1_SDA_C, SEL_IIC01_2),
-	PINMUX_IPSR_DATA(IP12_23_21, VI1_DATA0),
+	PINMUX_IPSR_GPSR(IP12_23_21, VI1_DATA0),
 	PINMUX_IPSR_MSEL(IP12_23_21, CAN0_TX_D, SEL_CAN0_3),
 	PINMUX_IPSR_MSEL(IP12_23_21, AVB_AVTP_MATCH, SEL_AVB_0),
 	PINMUX_IPSR_MSEL(IP12_23_21, ETH_RX_ER_B, SEL_ETH_1),
 	PINMUX_IPSR_MSEL(IP12_26_24, SSI_SDATA1, SEL_SSI1_0),
 	PINMUX_IPSR_MSEL(IP12_26_24, HSCIF1_HRX_B, SEL_HSCIF1_1),
-	PINMUX_IPSR_DATA(IP12_26_24, VI1_DATA1),
+	PINMUX_IPSR_GPSR(IP12_26_24, VI1_DATA1),
 	PINMUX_IPSR_MSEL(IP12_26_24, SDATA, SEL_FSN_0),
-	PINMUX_IPSR_DATA(IP12_26_24, ATAG0_N),
+	PINMUX_IPSR_GPSR(IP12_26_24, ATAG0_N),
 	PINMUX_IPSR_MSEL(IP12_26_24, ETH_RXD0_B, SEL_ETH_1),
 	PINMUX_IPSR_MSEL(IP12_29_27, SSI_SCK2, SEL_SSI2_0),
 	PINMUX_IPSR_MSEL(IP12_29_27, HSCIF1_HTX_B, SEL_HSCIF1_1),
-	PINMUX_IPSR_DATA(IP12_29_27, VI1_DATA2),
+	PINMUX_IPSR_GPSR(IP12_29_27, VI1_DATA2),
 	PINMUX_IPSR_MSEL(IP12_29_27, MDATA, SEL_FSN_0),
-	PINMUX_IPSR_DATA(IP12_29_27, ATAWR0_N),
+	PINMUX_IPSR_GPSR(IP12_29_27, ATAWR0_N),
 	PINMUX_IPSR_MSEL(IP12_29_27, ETH_RXD1_B, SEL_ETH_1),
 
 	/* IPSR13 */
 	PINMUX_IPSR_MSEL(IP13_2_0, SSI_WS2, SEL_SSI2_0),
 	PINMUX_IPSR_MSEL(IP13_2_0, HSCIF1_HCTS_N_B, SEL_HSCIF1_1),
 	PINMUX_IPSR_MSEL(IP13_2_0, SCIFA0_RXD_D, SEL_SCIFA0_3),
-	PINMUX_IPSR_DATA(IP13_2_0, VI1_DATA3),
+	PINMUX_IPSR_GPSR(IP13_2_0, VI1_DATA3),
 	PINMUX_IPSR_MSEL(IP13_2_0, SCKZ, SEL_FSN_0),
-	PINMUX_IPSR_DATA(IP13_2_0, ATACS00_N),
+	PINMUX_IPSR_GPSR(IP13_2_0, ATACS00_N),
 	PINMUX_IPSR_MSEL(IP13_2_0, ETH_LINK_B, SEL_ETH_1),
 	PINMUX_IPSR_MSEL(IP13_5_3, SSI_SDATA2, SEL_SSI2_0),
 	PINMUX_IPSR_MSEL(IP13_5_3, HSCIF1_HRTS_N_B, SEL_HSCIF1_1),
 	PINMUX_IPSR_MSEL(IP13_5_3, SCIFA0_TXD_D, SEL_SCIFA0_3),
-	PINMUX_IPSR_DATA(IP13_5_3, VI1_DATA4),
+	PINMUX_IPSR_GPSR(IP13_5_3, VI1_DATA4),
 	PINMUX_IPSR_MSEL(IP13_5_3, STM_N, SEL_FSN_0),
-	PINMUX_IPSR_DATA(IP13_5_3, ATACS10_N),
+	PINMUX_IPSR_GPSR(IP13_5_3, ATACS10_N),
 	PINMUX_IPSR_MSEL(IP13_5_3, ETH_REFCLK_B, SEL_ETH_1),
 	PINMUX_IPSR_MSEL(IP13_8_6, SSI_SCK9, SEL_SSI9_0),
 	PINMUX_IPSR_MSEL(IP13_8_6, SCIF2_SCK_B, SEL_SCIF2_1),
-	PINMUX_IPSR_DATA(IP13_8_6, PWM2_B),
-	PINMUX_IPSR_DATA(IP13_8_6, VI1_DATA5),
+	PINMUX_IPSR_GPSR(IP13_8_6, PWM2_B),
+	PINMUX_IPSR_GPSR(IP13_8_6, VI1_DATA5),
 	PINMUX_IPSR_MSEL(IP13_8_6, MTS_N, SEL_FSN_0),
-	PINMUX_IPSR_DATA(IP13_8_6, EX_WAIT1),
+	PINMUX_IPSR_GPSR(IP13_8_6, EX_WAIT1),
 	PINMUX_IPSR_MSEL(IP13_8_6, ETH_TXD1_B, SEL_ETH_1),
 	PINMUX_IPSR_MSEL(IP13_11_9, SSI_WS9, SEL_SSI9_0),
 	PINMUX_IPSR_MSEL(IP13_11_9, SCIF2_RXD_B, SEL_SCIF2_1),
 	PINMUX_IPSR_MSEL(IP13_11_9, I2C3_SCL_E, SEL_I2C03_4),
-	PINMUX_IPSR_DATA(IP13_11_9, VI1_DATA6),
-	PINMUX_IPSR_DATA(IP13_11_9, ATARD0_N),
+	PINMUX_IPSR_GPSR(IP13_11_9, VI1_DATA6),
+	PINMUX_IPSR_GPSR(IP13_11_9, ATARD0_N),
 	PINMUX_IPSR_MSEL(IP13_11_9, ETH_TX_EN_B, SEL_ETH_1),
 	PINMUX_IPSR_MSEL(IP13_14_12, SSI_SDATA9, SEL_SSI9_0),
 	PINMUX_IPSR_MSEL(IP13_14_12, SCIF2_TXD_B, SEL_SCIF2_1),
 	PINMUX_IPSR_MSEL(IP13_14_12, I2C3_SDA_E, SEL_I2C03_4),
-	PINMUX_IPSR_DATA(IP13_14_12, VI1_DATA7),
-	PINMUX_IPSR_DATA(IP13_14_12, ATADIR0_N),
+	PINMUX_IPSR_GPSR(IP13_14_12, VI1_DATA7),
+	PINMUX_IPSR_GPSR(IP13_14_12, ATADIR0_N),
 	PINMUX_IPSR_MSEL(IP13_14_12, ETH_MAGIC_B, SEL_ETH_1),
 	PINMUX_IPSR_MSEL(IP13_17_15, AUDIO_CLKA, SEL_ADG_0),
 	PINMUX_IPSR_MSEL(IP13_17_15, I2C0_SCL_B, SEL_I2C00_1),
 	PINMUX_IPSR_MSEL(IP13_17_15, SCIFA4_RXD_D, SEL_SCIFA4_3),
-	PINMUX_IPSR_DATA(IP13_17_15, VI1_CLKENB),
+	PINMUX_IPSR_GPSR(IP13_17_15, VI1_CLKENB),
 	PINMUX_IPSR_MSEL(IP13_17_15, TS_SDATA_C, SEL_TSIF0_2),
 	PINMUX_IPSR_MSEL(IP13_17_15, RIF0_SYNC_B, SEL_DR0_1),
 	PINMUX_IPSR_MSEL(IP13_17_15, ETH_TXD0_B, SEL_ETH_1),
 	PINMUX_IPSR_MSEL(IP13_20_18, AUDIO_CLKB, SEL_ADG_0),
 	PINMUX_IPSR_MSEL(IP13_20_18, I2C0_SDA_B, SEL_I2C00_1),
 	PINMUX_IPSR_MSEL(IP13_20_18, SCIFA4_TXD_D, SEL_SCIFA4_3),
-	PINMUX_IPSR_DATA(IP13_20_18, VI1_FIELD),
+	PINMUX_IPSR_GPSR(IP13_20_18, VI1_FIELD),
 	PINMUX_IPSR_MSEL(IP13_20_18, TS_SCK_C, SEL_TSIF0_2),
 	PINMUX_IPSR_MSEL(IP13_20_18, RIF0_CLK_B, SEL_DR0_1),
 	PINMUX_IPSR_MSEL(IP13_20_18, BPFCLK_E, SEL_DARC_4),
@@ -1472,7 +1472,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP13_23_21, AUDIO_CLKC, SEL_ADG_0),
 	PINMUX_IPSR_MSEL(IP13_23_21, I2C4_SCL_B, SEL_I2C04_1),
 	PINMUX_IPSR_MSEL(IP13_23_21, SCIFA5_RXD_D, SEL_SCIFA5_3),
-	PINMUX_IPSR_DATA(IP13_23_21, VI1_HSYNC_N),
+	PINMUX_IPSR_GPSR(IP13_23_21, VI1_HSYNC_N),
 	PINMUX_IPSR_MSEL(IP13_23_21, TS_SDEN_C, SEL_TSIF0_2),
 	PINMUX_IPSR_MSEL(IP13_23_21, RIF0_D0_B, SEL_DR0_1),
 	PINMUX_IPSR_MSEL(IP13_23_21, FMCLK_E, SEL_DARC_4),
@@ -1480,7 +1480,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP13_26_24, AUDIO_CLKOUT, SEL_ADG_0),
 	PINMUX_IPSR_MSEL(IP13_26_24, I2C4_SDA_B, SEL_I2C04_1),
 	PINMUX_IPSR_MSEL(IP13_26_24, SCIFA5_TXD_D, SEL_SCIFA5_3),
-	PINMUX_IPSR_DATA(IP13_26_24, VI1_VSYNC_N),
+	PINMUX_IPSR_GPSR(IP13_26_24, VI1_VSYNC_N),
 	PINMUX_IPSR_MSEL(IP13_26_24, TS_SPSYNC_C, SEL_TSIF0_2),
 	PINMUX_IPSR_MSEL(IP13_26_24, RIF0_D1_B, SEL_DR1_1),
 	PINMUX_IPSR_MSEL(IP13_26_24, FMIN_E, SEL_DARC_4),
@@ -1491,6 +1491,197 @@ static const struct sh_pfc_pin pinmux_pins[] = {
 	PINMUX_GPIO_GP_ALL(),
 };
 
+/* - Audio Clock ------------------------------------------------------------ */
+static const unsigned int audio_clka_pins[] = {
+	/* CLKA */
+	RCAR_GP_PIN(5, 20),
+};
+static const unsigned int audio_clka_mux[] = {
+	AUDIO_CLKA_MARK,
+};
+static const unsigned int audio_clka_b_pins[] = {
+	/* CLKA */
+	RCAR_GP_PIN(3, 25),
+};
+static const unsigned int audio_clka_b_mux[] = {
+	AUDIO_CLKA_B_MARK,
+};
+static const unsigned int audio_clka_c_pins[] = {
+	/* CLKA */
+	RCAR_GP_PIN(4, 20),
+};
+static const unsigned int audio_clka_c_mux[] = {
+	AUDIO_CLKA_C_MARK,
+};
+static const unsigned int audio_clka_d_pins[] = {
+	/* CLKA */
+	RCAR_GP_PIN(5, 0),
+};
+static const unsigned int audio_clka_d_mux[] = {
+	AUDIO_CLKA_D_MARK,
+};
+static const unsigned int audio_clkb_pins[] = {
+	/* CLKB */
+	RCAR_GP_PIN(5, 21),
+};
+static const unsigned int audio_clkb_mux[] = {
+	AUDIO_CLKB_MARK,
+};
+static const unsigned int audio_clkb_b_pins[] = {
+	/* CLKB */
+	RCAR_GP_PIN(3, 26),
+};
+static const unsigned int audio_clkb_b_mux[] = {
+	AUDIO_CLKB_B_MARK,
+};
+static const unsigned int audio_clkb_c_pins[] = {
+	/* CLKB */
+	RCAR_GP_PIN(4, 21),
+};
+static const unsigned int audio_clkb_c_mux[] = {
+	AUDIO_CLKB_C_MARK,
+};
+static const unsigned int audio_clkc_pins[] = {
+	/* CLKC */
+	RCAR_GP_PIN(5, 22),
+};
+static const unsigned int audio_clkc_mux[] = {
+	AUDIO_CLKC_MARK,
+};
+static const unsigned int audio_clkc_b_pins[] = {
+	/* CLKC */
+	RCAR_GP_PIN(3, 29),
+};
+static const unsigned int audio_clkc_b_mux[] = {
+	AUDIO_CLKC_B_MARK,
+};
+static const unsigned int audio_clkc_c_pins[] = {
+	/* CLKC */
+	RCAR_GP_PIN(4, 22),
+};
+static const unsigned int audio_clkc_c_mux[] = {
+	AUDIO_CLKC_C_MARK,
+};
+static const unsigned int audio_clkout_pins[] = {
+	/* CLKOUT */
+	RCAR_GP_PIN(5, 23),
+};
+static const unsigned int audio_clkout_mux[] = {
+	AUDIO_CLKOUT_MARK,
+};
+static const unsigned int audio_clkout_b_pins[] = {
+	/* CLKOUT */
+	RCAR_GP_PIN(3, 12),
+};
+static const unsigned int audio_clkout_b_mux[] = {
+	AUDIO_CLKOUT_B_MARK,
+};
+static const unsigned int audio_clkout_c_pins[] = {
+	/* CLKOUT */
+	RCAR_GP_PIN(4, 23),
+};
+static const unsigned int audio_clkout_c_mux[] = {
+	AUDIO_CLKOUT_C_MARK,
+};
+/* - AVB -------------------------------------------------------------------- */
+static const unsigned int avb_link_pins[] = {
+	RCAR_GP_PIN(3, 26),
+};
+static const unsigned int avb_link_mux[] = {
+	AVB_LINK_MARK,
+};
+static const unsigned int avb_magic_pins[] = {
+	RCAR_GP_PIN(3, 27),
+};
+static const unsigned int avb_magic_mux[] = {
+	AVB_MAGIC_MARK,
+};
+static const unsigned int avb_phy_int_pins[] = {
+	RCAR_GP_PIN(3, 28),
+};
+static const unsigned int avb_phy_int_mux[] = {
+	AVB_PHY_INT_MARK,
+};
+static const unsigned int avb_mdio_pins[] = {
+	RCAR_GP_PIN(3, 24), RCAR_GP_PIN(3, 25),
+};
+static const unsigned int avb_mdio_mux[] = {
+	AVB_MDC_MARK, AVB_MDIO_MARK,
+};
+static const unsigned int avb_mii_pins[] = {
+	RCAR_GP_PIN(3, 14), RCAR_GP_PIN(3, 15), RCAR_GP_PIN(3, 16),
+	RCAR_GP_PIN(3, 17),
+
+	RCAR_GP_PIN(3, 2), RCAR_GP_PIN(3, 3), RCAR_GP_PIN(3, 4),
+	RCAR_GP_PIN(3, 5),
+
+	RCAR_GP_PIN(3, 10), RCAR_GP_PIN(3, 0), RCAR_GP_PIN(3, 1),
+	RCAR_GP_PIN(3, 29), RCAR_GP_PIN(3, 12), RCAR_GP_PIN(3, 22),
+	RCAR_GP_PIN(3, 13), RCAR_GP_PIN(3, 11),
+};
+static const unsigned int avb_mii_mux[] = {
+	AVB_TXD0_MARK, AVB_TXD1_MARK, AVB_TXD2_MARK,
+	AVB_TXD3_MARK,
+
+	AVB_RXD0_MARK, AVB_RXD1_MARK, AVB_RXD2_MARK,
+	AVB_RXD3_MARK,
+
+	AVB_RX_ER_MARK, AVB_RX_CLK_MARK, AVB_RX_DV_MARK,
+	AVB_CRS_MARK, AVB_TX_EN_MARK, AVB_TX_ER_MARK,
+	AVB_TX_CLK_MARK, AVB_COL_MARK,
+};
+static const unsigned int avb_gmii_pins[] = {
+	RCAR_GP_PIN(3, 14), RCAR_GP_PIN(3, 15), RCAR_GP_PIN(3, 16),
+	RCAR_GP_PIN(3, 17), RCAR_GP_PIN(3, 18), RCAR_GP_PIN(3, 19),
+	RCAR_GP_PIN(3, 20), RCAR_GP_PIN(3, 21),
+
+	RCAR_GP_PIN(3, 2), RCAR_GP_PIN(3, 3), RCAR_GP_PIN(3, 4),
+	RCAR_GP_PIN(3, 5), RCAR_GP_PIN(3, 6), RCAR_GP_PIN(3, 7),
+	RCAR_GP_PIN(3, 8), RCAR_GP_PIN(3, 9),
+
+	RCAR_GP_PIN(3, 10), RCAR_GP_PIN(3, 0), RCAR_GP_PIN(3, 1),
+	RCAR_GP_PIN(3, 29), RCAR_GP_PIN(3, 23), RCAR_GP_PIN(3, 30),
+	RCAR_GP_PIN(3, 12), RCAR_GP_PIN(3, 22), RCAR_GP_PIN(3, 13),
+	RCAR_GP_PIN(3, 11),
+};
+static const unsigned int avb_gmii_mux[] = {
+	AVB_TXD0_MARK, AVB_TXD1_MARK, AVB_TXD2_MARK,
+	AVB_TXD3_MARK, AVB_TXD4_MARK, AVB_TXD5_MARK,
+	AVB_TXD6_MARK, AVB_TXD7_MARK,
+
+	AVB_RXD0_MARK, AVB_RXD1_MARK, AVB_RXD2_MARK,
+	AVB_RXD3_MARK, AVB_RXD4_MARK, AVB_RXD5_MARK,
+	AVB_RXD6_MARK, AVB_RXD7_MARK,
+
+	AVB_RX_ER_MARK, AVB_RX_CLK_MARK, AVB_RX_DV_MARK,
+	AVB_CRS_MARK, AVB_GTX_CLK_MARK, AVB_GTXREFCLK_MARK,
+	AVB_TX_EN_MARK, AVB_TX_ER_MARK, AVB_TX_CLK_MARK,
+	AVB_COL_MARK,
+};
+static const unsigned int avb_avtp_capture_pins[] = {
+	RCAR_GP_PIN(5, 11),
+};
+static const unsigned int avb_avtp_capture_mux[] = {
+	AVB_AVTP_CAPTURE_MARK,
+};
+static const unsigned int avb_avtp_match_pins[] = {
+	RCAR_GP_PIN(5, 12),
+};
+static const unsigned int avb_avtp_match_mux[] = {
+	AVB_AVTP_MATCH_MARK,
+};
+static const unsigned int avb_avtp_capture_b_pins[] = {
+	RCAR_GP_PIN(1, 1),
+};
+static const unsigned int avb_avtp_capture_b_mux[] = {
+	AVB_AVTP_CAPTURE_B_MARK,
+};
+static const unsigned int avb_avtp_match_b_pins[] = {
+	RCAR_GP_PIN(1, 2),
+};
+static const unsigned int avb_avtp_match_b_mux[] = {
+	AVB_AVTP_MATCH_B_MARK,
+};
 /* - ETH -------------------------------------------------------------------- */
 static const unsigned int eth_link_pins[] = {
 	/* LINK */
@@ -2751,6 +2942,245 @@ static const unsigned int sdhi2_wp_pins[] = {
 static const unsigned int sdhi2_wp_mux[] = {
 	SD2_WP_MARK,
 };
+/* - SSI -------------------------------------------------------------------- */
+static const unsigned int ssi0_data_pins[] = {
+	/* SDATA0 */
+	RCAR_GP_PIN(5, 3),
+};
+static const unsigned int ssi0_data_mux[] = {
+	SSI_SDATA0_MARK,
+};
+static const unsigned int ssi0129_ctrl_pins[] = {
+	/* SCK0129, WS0129 */
+	RCAR_GP_PIN(5, 1), RCAR_GP_PIN(5, 2),
+};
+static const unsigned int ssi0129_ctrl_mux[] = {
+	SSI_SCK0129_MARK, SSI_WS0129_MARK,
+};
+static const unsigned int ssi1_data_pins[] = {
+	/* SDATA1 */
+	RCAR_GP_PIN(5, 13),
+};
+static const unsigned int ssi1_data_mux[] = {
+	SSI_SDATA1_MARK,
+};
+static const unsigned int ssi1_ctrl_pins[] = {
+	/* SCK1, WS1 */
+	RCAR_GP_PIN(5, 11), RCAR_GP_PIN(5, 12),
+};
+static const unsigned int ssi1_ctrl_mux[] = {
+	SSI_SCK1_MARK, SSI_WS1_MARK,
+};
+static const unsigned int ssi1_data_b_pins[] = {
+	/* SDATA1 */
+	RCAR_GP_PIN(4, 13),
+};
+static const unsigned int ssi1_data_b_mux[] = {
+	SSI_SDATA1_B_MARK,
+};
+static const unsigned int ssi1_ctrl_b_pins[] = {
+	/* SCK1, WS1 */
+	RCAR_GP_PIN(4, 11), RCAR_GP_PIN(4, 12),
+};
+static const unsigned int ssi1_ctrl_b_mux[] = {
+	SSI_SCK1_B_MARK, SSI_WS1_B_MARK,
+};
+static const unsigned int ssi2_data_pins[] = {
+	/* SDATA2 */
+	RCAR_GP_PIN(5, 16),
+};
+static const unsigned int ssi2_data_mux[] = {
+	SSI_SDATA2_MARK,
+};
+static const unsigned int ssi2_ctrl_pins[] = {
+	/* SCK2, WS2 */
+	RCAR_GP_PIN(5, 14), RCAR_GP_PIN(5, 15),
+};
+static const unsigned int ssi2_ctrl_mux[] = {
+	SSI_SCK2_MARK, SSI_WS2_MARK,
+};
+static const unsigned int ssi2_data_b_pins[] = {
+	/* SDATA2 */
+	RCAR_GP_PIN(4, 16),
+};
+static const unsigned int ssi2_data_b_mux[] = {
+	SSI_SDATA2_B_MARK,
+};
+static const unsigned int ssi2_ctrl_b_pins[] = {
+	/* SCK2, WS2 */
+	RCAR_GP_PIN(4, 14), RCAR_GP_PIN(4, 15),
+};
+static const unsigned int ssi2_ctrl_b_mux[] = {
+	SSI_SCK2_B_MARK, SSI_WS2_B_MARK,
+};
+static const unsigned int ssi3_data_pins[] = {
+	/* SDATA3 */
+	RCAR_GP_PIN(5, 6),
+};
+static const unsigned int ssi3_data_mux[] = {
+	SSI_SDATA3_MARK
+};
+static const unsigned int ssi34_ctrl_pins[] = {
+	/* SCK34, WS34 */
+	RCAR_GP_PIN(5, 4), RCAR_GP_PIN(5, 5),
+};
+static const unsigned int ssi34_ctrl_mux[] = {
+	SSI_SCK34_MARK, SSI_WS34_MARK,
+};
+static const unsigned int ssi4_data_pins[] = {
+	/* SDATA4 */
+	RCAR_GP_PIN(5, 9),
+};
+static const unsigned int ssi4_data_mux[] = {
+	SSI_SDATA4_MARK,
+};
+static const unsigned int ssi4_ctrl_pins[] = {
+	/* SCK4, WS4 */
+	RCAR_GP_PIN(5, 7), RCAR_GP_PIN(5, 8),
+};
+static const unsigned int ssi4_ctrl_mux[] = {
+	SSI_SCK4_MARK, SSI_WS4_MARK,
+};
+static const unsigned int ssi4_data_b_pins[] = {
+	/* SDATA4 */
+	RCAR_GP_PIN(4, 22),
+};
+static const unsigned int ssi4_data_b_mux[] = {
+	SSI_SDATA4_B_MARK,
+};
+static const unsigned int ssi4_ctrl_b_pins[] = {
+	/* SCK4, WS4 */
+	RCAR_GP_PIN(4, 20), RCAR_GP_PIN(4, 21),
+};
+static const unsigned int ssi4_ctrl_b_mux[] = {
+	SSI_SCK4_B_MARK, SSI_WS4_B_MARK,
+};
+static const unsigned int ssi5_data_pins[] = {
+	/* SDATA5 */
+	RCAR_GP_PIN(4, 26),
+};
+static const unsigned int ssi5_data_mux[] = {
+	SSI_SDATA5_MARK,
+};
+static const unsigned int ssi5_ctrl_pins[] = {
+	/* SCK5, WS5 */
+	RCAR_GP_PIN(4, 24), RCAR_GP_PIN(4, 25),
+};
+static const unsigned int ssi5_ctrl_mux[] = {
+	SSI_SCK5_MARK, SSI_WS5_MARK,
+};
+static const unsigned int ssi5_data_b_pins[] = {
+	/* SDATA5 */
+	RCAR_GP_PIN(3, 21),
+};
+static const unsigned int ssi5_data_b_mux[] = {
+	SSI_SDATA5_B_MARK,
+};
+static const unsigned int ssi5_ctrl_b_pins[] = {
+	/* SCK5, WS5 */
+	RCAR_GP_PIN(3, 19), RCAR_GP_PIN(3, 20),
+};
+static const unsigned int ssi5_ctrl_b_mux[] = {
+	SSI_SCK5_B_MARK, SSI_WS5_B_MARK,
+};
+static const unsigned int ssi6_data_pins[] = {
+	/* SDATA6 */
+	RCAR_GP_PIN(4, 29),
+};
+static const unsigned int ssi6_data_mux[] = {
+	SSI_SDATA6_MARK,
+};
+static const unsigned int ssi6_ctrl_pins[] = {
+	/* SCK6, WS6 */
+	RCAR_GP_PIN(4, 27), RCAR_GP_PIN(4, 28),
+};
+static const unsigned int ssi6_ctrl_mux[] = {
+	SSI_SCK6_MARK, SSI_WS6_MARK,
+};
+static const unsigned int ssi6_data_b_pins[] = {
+	/* SDATA6 */
+	RCAR_GP_PIN(3, 24),
+};
+static const unsigned int ssi6_data_b_mux[] = {
+	SSI_SDATA6_B_MARK,
+};
+static const unsigned int ssi6_ctrl_b_pins[] = {
+	/* SCK6, WS6 */
+	RCAR_GP_PIN(3, 22), RCAR_GP_PIN(3, 23),
+};
+static const unsigned int ssi6_ctrl_b_mux[] = {
+	SSI_SCK6_B_MARK, SSI_WS6_B_MARK,
+};
+static const unsigned int ssi7_data_pins[] = {
+	/* SDATA7 */
+	RCAR_GP_PIN(5, 0),
+};
+static const unsigned int ssi7_data_mux[] = {
+	SSI_SDATA7_MARK,
+};
+static const unsigned int ssi78_ctrl_pins[] = {
+	/* SCK78, WS78 */
+	RCAR_GP_PIN(4, 30), RCAR_GP_PIN(4, 31),
+};
+static const unsigned int ssi78_ctrl_mux[] = {
+	SSI_SCK78_MARK, SSI_WS78_MARK,
+};
+static const unsigned int ssi7_data_b_pins[] = {
+	/* SDATA7 */
+	RCAR_GP_PIN(3, 27),
+};
+static const unsigned int ssi7_data_b_mux[] = {
+	SSI_SDATA7_B_MARK,
+};
+static const unsigned int ssi78_ctrl_b_pins[] = {
+	/* SCK78, WS78 */
+	RCAR_GP_PIN(3, 25), RCAR_GP_PIN(3, 26),
+};
+static const unsigned int ssi78_ctrl_b_mux[] = {
+	SSI_SCK78_B_MARK, SSI_WS78_B_MARK,
+};
+static const unsigned int ssi8_data_pins[] = {
+	/* SDATA8 */
+	RCAR_GP_PIN(5, 10),
+};
+static const unsigned int ssi8_data_mux[] = {
+	SSI_SDATA8_MARK,
+};
+static const unsigned int ssi8_data_b_pins[] = {
+	/* SDATA8 */
+	RCAR_GP_PIN(3, 28),
+};
+static const unsigned int ssi8_data_b_mux[] = {
+	SSI_SDATA8_B_MARK,
+};
+static const unsigned int ssi9_data_pins[] = {
+	/* SDATA9 */
+	RCAR_GP_PIN(5, 19),
+};
+static const unsigned int ssi9_data_mux[] = {
+	SSI_SDATA9_MARK,
+};
+static const unsigned int ssi9_ctrl_pins[] = {
+	/* SCK9, WS9 */
+	RCAR_GP_PIN(5, 17), RCAR_GP_PIN(5, 18),
+};
+static const unsigned int ssi9_ctrl_mux[] = {
+	SSI_SCK9_MARK, SSI_WS9_MARK,
+};
+static const unsigned int ssi9_data_b_pins[] = {
+	/* SDATA9 */
+	RCAR_GP_PIN(4, 19),
+};
+static const unsigned int ssi9_data_b_mux[] = {
+	SSI_SDATA9_B_MARK,
+};
+static const unsigned int ssi9_ctrl_b_pins[] = {
+	/* SCK9, WS9 */
+	RCAR_GP_PIN(4, 17), RCAR_GP_PIN(4, 18),
+};
+static const unsigned int ssi9_ctrl_b_mux[] = {
+	SSI_SCK9_B_MARK, SSI_WS9_B_MARK,
+};
 /* - USB0 ------------------------------------------------------------------- */
 static const unsigned int usb0_pins[] = {
 	RCAR_GP_PIN(5, 24), /* PWEN */
@@ -2911,6 +3341,29 @@ static const unsigned int vin1_clk_mux[] = {
 };
 
 static const struct sh_pfc_pin_group pinmux_groups[] = {
+	SH_PFC_PIN_GROUP(audio_clka),
+	SH_PFC_PIN_GROUP(audio_clka_b),
+	SH_PFC_PIN_GROUP(audio_clka_c),
+	SH_PFC_PIN_GROUP(audio_clka_d),
+	SH_PFC_PIN_GROUP(audio_clkb),
+	SH_PFC_PIN_GROUP(audio_clkb_b),
+	SH_PFC_PIN_GROUP(audio_clkb_c),
+	SH_PFC_PIN_GROUP(audio_clkc),
+	SH_PFC_PIN_GROUP(audio_clkc_b),
+	SH_PFC_PIN_GROUP(audio_clkc_c),
+	SH_PFC_PIN_GROUP(audio_clkout),
+	SH_PFC_PIN_GROUP(audio_clkout_b),
+	SH_PFC_PIN_GROUP(audio_clkout_c),
+	SH_PFC_PIN_GROUP(avb_link),
+	SH_PFC_PIN_GROUP(avb_magic),
+	SH_PFC_PIN_GROUP(avb_phy_int),
+	SH_PFC_PIN_GROUP(avb_mdio),
+	SH_PFC_PIN_GROUP(avb_mii),
+	SH_PFC_PIN_GROUP(avb_gmii),
+	SH_PFC_PIN_GROUP(avb_avtp_capture),
+	SH_PFC_PIN_GROUP(avb_avtp_match),
+	SH_PFC_PIN_GROUP(avb_avtp_capture_b),
+	SH_PFC_PIN_GROUP(avb_avtp_match_b),
 	SH_PFC_PIN_GROUP(eth_link),
 	SH_PFC_PIN_GROUP(eth_magic),
 	SH_PFC_PIN_GROUP(eth_mdio),
@@ -3084,6 +3537,40 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(sdhi2_ctrl),
 	SH_PFC_PIN_GROUP(sdhi2_cd),
 	SH_PFC_PIN_GROUP(sdhi2_wp),
+	SH_PFC_PIN_GROUP(ssi0_data),
+	SH_PFC_PIN_GROUP(ssi0129_ctrl),
+	SH_PFC_PIN_GROUP(ssi1_data),
+	SH_PFC_PIN_GROUP(ssi1_ctrl),
+	SH_PFC_PIN_GROUP(ssi1_data_b),
+	SH_PFC_PIN_GROUP(ssi1_ctrl_b),
+	SH_PFC_PIN_GROUP(ssi2_data),
+	SH_PFC_PIN_GROUP(ssi2_ctrl),
+	SH_PFC_PIN_GROUP(ssi2_data_b),
+	SH_PFC_PIN_GROUP(ssi2_ctrl_b),
+	SH_PFC_PIN_GROUP(ssi3_data),
+	SH_PFC_PIN_GROUP(ssi34_ctrl),
+	SH_PFC_PIN_GROUP(ssi4_data),
+	SH_PFC_PIN_GROUP(ssi4_ctrl),
+	SH_PFC_PIN_GROUP(ssi4_data_b),
+	SH_PFC_PIN_GROUP(ssi4_ctrl_b),
+	SH_PFC_PIN_GROUP(ssi5_data),
+	SH_PFC_PIN_GROUP(ssi5_ctrl),
+	SH_PFC_PIN_GROUP(ssi5_data_b),
+	SH_PFC_PIN_GROUP(ssi5_ctrl_b),
+	SH_PFC_PIN_GROUP(ssi6_data),
+	SH_PFC_PIN_GROUP(ssi6_ctrl),
+	SH_PFC_PIN_GROUP(ssi6_data_b),
+	SH_PFC_PIN_GROUP(ssi6_ctrl_b),
+	SH_PFC_PIN_GROUP(ssi7_data),
+	SH_PFC_PIN_GROUP(ssi78_ctrl),
+	SH_PFC_PIN_GROUP(ssi7_data_b),
+	SH_PFC_PIN_GROUP(ssi78_ctrl_b),
+	SH_PFC_PIN_GROUP(ssi8_data),
+	SH_PFC_PIN_GROUP(ssi8_data_b),
+	SH_PFC_PIN_GROUP(ssi9_data),
+	SH_PFC_PIN_GROUP(ssi9_ctrl),
+	SH_PFC_PIN_GROUP(ssi9_data_b),
+	SH_PFC_PIN_GROUP(ssi9_ctrl_b),
 	SH_PFC_PIN_GROUP(usb0),
 	SH_PFC_PIN_GROUP(usb1),
 	VIN_DATA_PIN_GROUP(vin0_data, 24),
@@ -3106,6 +3593,35 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(vin1_clk),
 };
 
+static const char * const audio_clk_groups[] = {
+	"audio_clka",
+	"audio_clka_b",
+	"audio_clka_c",
+	"audio_clka_d",
+	"audio_clkb",
+	"audio_clkb_b",
+	"audio_clkb_c",
+	"audio_clkc",
+	"audio_clkc_b",
+	"audio_clkc_c",
+	"audio_clkout",
+	"audio_clkout_b",
+	"audio_clkout_c",
+};
+
+static const char * const avb_groups[] = {
+	"avb_link",
+	"avb_magic",
+	"avb_phy_int",
+	"avb_mdio",
+	"avb_mii",
+	"avb_gmii",
+	"avb_avtp_capture",
+	"avb_avtp_match",
+	"avb_avtp_capture_b",
+	"avb_avtp_match_b",
+};
+
 static const char * const eth_groups[] = {
 	"eth_link",
 	"eth_magic",
@@ -3381,6 +3897,43 @@ static const char * const sdhi2_groups[] = {
 	"sdhi2_wp",
 };
 
+static const char * const ssi_groups[] = {
+	"ssi0_data",
+	"ssi0129_ctrl",
+	"ssi1_data",
+	"ssi1_ctrl",
+	"ssi1_data_b",
+	"ssi1_ctrl_b",
+	"ssi2_data",
+	"ssi2_ctrl",
+	"ssi2_data_b",
+	"ssi2_ctrl_b",
+	"ssi3_data",
+	"ssi34_ctrl",
+	"ssi4_data",
+	"ssi4_ctrl",
+	"ssi4_data_b",
+	"ssi4_ctrl_b",
+	"ssi5_data",
+	"ssi5_ctrl",
+	"ssi5_data_b",
+	"ssi5_ctrl_b",
+	"ssi6_data",
+	"ssi6_ctrl",
+	"ssi6_data_b",
+	"ssi6_ctrl_b",
+	"ssi7_data",
+	"ssi78_ctrl",
+	"ssi7_data_b",
+	"ssi78_ctrl_b",
+	"ssi8_data",
+	"ssi8_data_b",
+	"ssi9_data",
+	"ssi9_ctrl",
+	"ssi9_data_b",
+	"ssi9_ctrl_b",
+};
+
 static const char * const usb0_groups[] = {
 	"usb0",
 };
@@ -3414,6 +3967,8 @@ static const char * const vin1_groups[] = {
 };
 
 static const struct sh_pfc_function pinmux_functions[] = {
+	SH_PFC_FUNCTION(audio_clk),
+	SH_PFC_FUNCTION(avb),
 	SH_PFC_FUNCTION(eth),
 	SH_PFC_FUNCTION(hscif0),
 	SH_PFC_FUNCTION(hscif1),
@@ -3448,6 +4003,7 @@ static const struct sh_pfc_function pinmux_functions[] = {
 	SH_PFC_FUNCTION(sdhi0),
 	SH_PFC_FUNCTION(sdhi1),
 	SH_PFC_FUNCTION(sdhi2),
+	SH_PFC_FUNCTION(ssi),
 	SH_PFC_FUNCTION(usb0),
 	SH_PFC_FUNCTION(usb1),
 	SH_PFC_FUNCTION(vin0),
@@ -3974,6 +4530,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = {
 		FN_DU0_DISP, FN_QPOLA, FN_CC50_STATE30, 0,
 		/* IP6_3_2 [2] */
 		FN_DU0_EXODDF_DU0_ODDF_DISP_CDE, FN_QCPV_QDE, FN_CC50_STATE29,
+		0,
 		/* IP6_1_0 [2] */
 		FN_DU0_EXVSYNC_DU0_VSYNC, FN_QSTB_QHE, FN_CC50_STATE28, 0, }
 	},
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7795.c b/drivers/pinctrl/sh-pfc/pfc-r8a7795.c
index ce4f5cdb0579..5979dabc02fa 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7795.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7795.c
@@ -189,8 +189,8 @@
 #define GPSR6_4		F_(SSI_SDATA2_A,	IP14_7_4)
 #define GPSR6_3		F_(SSI_SDATA1_A,	IP14_3_0)
 #define GPSR6_2		F_(SSI_SDATA0,		IP13_31_28)
-#define GPSR6_1		F_(SSI_WS0129,		IP13_27_24)
-#define GPSR6_0		F_(SSI_SCK0129,		IP13_23_20)
+#define GPSR6_1		F_(SSI_WS01239,		IP13_27_24)
+#define GPSR6_0		F_(SSI_SCK01239,	IP13_23_20)
 
 /* GPSR7 */
 #define GPSR7_3		FM(HDMI1_CEC)
@@ -315,8 +315,8 @@
 #define IP13_11_8	FM(MLB_CLK)		F_(0, 0)	FM(MSIOF1_SCK_F)	F_(0, 0)			FM(SCL1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP13_15_12	FM(MLB_SIG)		FM(RX1_B)	FM(MSIOF1_SYNC_F)	F_(0, 0)			FM(SDA1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP13_19_16	FM(MLB_DAT)		FM(TX1_B)	FM(MSIOF1_RXD_F)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP13_23_20	FM(SSI_SCK0129)		F_(0, 0)	FM(MSIOF1_TXD_F)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP13_27_24	FM(SSI_WS0129)		F_(0, 0)	FM(MSIOF1_SS1_F)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP13_23_20	FM(SSI_SCK01239)	F_(0, 0)	FM(MSIOF1_TXD_F)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP13_27_24	FM(SSI_WS01239)		F_(0, 0)	FM(MSIOF1_SS1_F)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP13_31_28	FM(SSI_SDATA0)		F_(0, 0)	FM(MSIOF1_SS2_F)	F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP14_3_0	FM(SSI_SDATA1_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)			F_(0, 0)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP14_7_4	FM(SSI_SDATA2_A)	F_(0, 0)	F_(0, 0)		F_(0, 0)			FM(SSI_SCK1_B)	F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
@@ -478,7 +478,6 @@ FM(IP16_31_28)	IP16_31_28
 #define MOD_SEL2_31		FM(I2C_SEL_5_0)		FM(I2C_SEL_5_1)
 #define MOD_SEL2_30		FM(I2C_SEL_3_0)		FM(I2C_SEL_3_1)
 #define MOD_SEL2_29		FM(I2C_SEL_0_0)		FM(I2C_SEL_0_1)
-#define MOD_SEL2_2_1		FM(SEL_VSP_0)		FM(SEL_VSP_1)		FM(SEL_VSP_2)		FM(SEL_VSP_3)
 #define MOD_SEL2_0		FM(SEL_VIN4_0)		FM(SEL_VIN4_1)
 
 #define PINMUX_MOD_SELS\
@@ -512,7 +511,7 @@ MOD_SEL0_7_6 \
 MOD_SEL0_5_4		MOD_SEL1_5 \
 			MOD_SEL1_4 \
 MOD_SEL0_3		MOD_SEL1_3 \
-MOD_SEL0_2_1		MOD_SEL1_2		MOD_SEL2_2_1 \
+MOD_SEL0_2_1		MOD_SEL1_2 \
 			MOD_SEL1_1 \
 			MOD_SEL1_0		MOD_SEL2_0
 
@@ -569,18 +568,18 @@ static const u16 pinmux_data[] = {
 	PINMUX_SINGLE(SSI_WS5),
 
 	/* IPSR0 */
-	PINMUX_IPSR_DATA(IP0_3_0,	AVB_MDC),
+	PINMUX_IPSR_GPSR(IP0_3_0,	AVB_MDC),
 	PINMUX_IPSR_MSEL(IP0_3_0,	MSIOF2_SS2_C,		SEL_MSIOF2_2),
 
-	PINMUX_IPSR_DATA(IP0_7_4,	AVB_MAGIC),
+	PINMUX_IPSR_GPSR(IP0_7_4,	AVB_MAGIC),
 	PINMUX_IPSR_MSEL(IP0_7_4,	MSIOF2_SS1_C,		SEL_MSIOF2_2),
 	PINMUX_IPSR_MSEL(IP0_7_4,	SCK4_A,			SEL_SCIF4_0),
 
-	PINMUX_IPSR_DATA(IP0_11_8,	AVB_PHY_INT),
+	PINMUX_IPSR_GPSR(IP0_11_8,	AVB_PHY_INT),
 	PINMUX_IPSR_MSEL(IP0_11_8,	MSIOF2_SYNC_C,		SEL_MSIOF2_2),
 	PINMUX_IPSR_MSEL(IP0_11_8,	RX4_A,			SEL_SCIF4_0),
 
-	PINMUX_IPSR_DATA(IP0_15_12,	AVB_LINK),
+	PINMUX_IPSR_GPSR(IP0_15_12,	AVB_LINK),
 	PINMUX_IPSR_MSEL(IP0_15_12,	MSIOF2_SCK_C,		SEL_MSIOF2_2),
 	PINMUX_IPSR_MSEL(IP0_15_12,	TX4_A,			SEL_SCIF4_0),
 
@@ -592,126 +591,126 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP0_23_20,	MSIOF2_TXD_C,		SEL_MSIOF2_2),
 	PINMUX_IPSR_MSEL(IP0_23_20,	RTS4_N_TANS_A,		SEL_SCIF4_0),
 
-	PINMUX_IPSR_DATA(IP0_27_24,	IRQ0),
-	PINMUX_IPSR_DATA(IP0_27_24,	QPOLB),
-	PINMUX_IPSR_DATA(IP0_27_24,	DU_CDE),
+	PINMUX_IPSR_GPSR(IP0_27_24,	IRQ0),
+	PINMUX_IPSR_GPSR(IP0_27_24,	QPOLB),
+	PINMUX_IPSR_GPSR(IP0_27_24,	DU_CDE),
 	PINMUX_IPSR_MSEL(IP0_27_24,	VI4_DATA0_B,		SEL_VIN4_1),
 	PINMUX_IPSR_MSEL(IP0_27_24,	CAN0_TX_B,		SEL_RCAN0_1),
 	PINMUX_IPSR_MSEL(IP0_27_24,	CANFD0_TX_B,		SEL_CANFD0_1),
 
-	PINMUX_IPSR_DATA(IP0_31_28,	IRQ1),
-	PINMUX_IPSR_DATA(IP0_31_28,	QPOLA),
-	PINMUX_IPSR_DATA(IP0_31_28,	DU_DISP),
+	PINMUX_IPSR_GPSR(IP0_31_28,	IRQ1),
+	PINMUX_IPSR_GPSR(IP0_31_28,	QPOLA),
+	PINMUX_IPSR_GPSR(IP0_31_28,	DU_DISP),
 	PINMUX_IPSR_MSEL(IP0_31_28,	VI4_DATA1_B,		SEL_VIN4_1),
 	PINMUX_IPSR_MSEL(IP0_31_28,	CAN0_RX_B,		SEL_RCAN0_1),
 	PINMUX_IPSR_MSEL(IP0_31_28,	CANFD0_RX_B,		SEL_CANFD0_1),
 
 	/* IPSR1 */
-	PINMUX_IPSR_DATA(IP1_3_0,	IRQ2),
-	PINMUX_IPSR_DATA(IP1_3_0,	QCPV_QDE),
-	PINMUX_IPSR_DATA(IP1_3_0,	DU_EXODDF_DU_ODDF_DISP_CDE),
+	PINMUX_IPSR_GPSR(IP1_3_0,	IRQ2),
+	PINMUX_IPSR_GPSR(IP1_3_0,	QCPV_QDE),
+	PINMUX_IPSR_GPSR(IP1_3_0,	DU_EXODDF_DU_ODDF_DISP_CDE),
 	PINMUX_IPSR_MSEL(IP1_3_0,	VI4_DATA2_B,		SEL_VIN4_1),
 	PINMUX_IPSR_MSEL(IP1_3_0,	PWM3_B,			SEL_PWM3_1),
 
-	PINMUX_IPSR_DATA(IP1_7_4,	IRQ3),
-	PINMUX_IPSR_DATA(IP1_7_4,	QSTVB_QVE),
-	PINMUX_IPSR_DATA(IP1_7_4,	A25),
-	PINMUX_IPSR_DATA(IP1_7_4,	DU_DOTCLKOUT1),
+	PINMUX_IPSR_GPSR(IP1_7_4,	IRQ3),
+	PINMUX_IPSR_GPSR(IP1_7_4,	QSTVB_QVE),
+	PINMUX_IPSR_GPSR(IP1_7_4,	A25),
+	PINMUX_IPSR_GPSR(IP1_7_4,	DU_DOTCLKOUT1),
 	PINMUX_IPSR_MSEL(IP1_7_4,	VI4_DATA3_B,		SEL_VIN4_1),
 	PINMUX_IPSR_MSEL(IP1_7_4,	PWM4_B,			SEL_PWM4_1),
 
-	PINMUX_IPSR_DATA(IP1_11_8,	IRQ4),
-	PINMUX_IPSR_DATA(IP1_11_8,	QSTH_QHS),
-	PINMUX_IPSR_DATA(IP1_11_8,	A24),
-	PINMUX_IPSR_DATA(IP1_11_8,	DU_EXHSYNC_DU_HSYNC),
+	PINMUX_IPSR_GPSR(IP1_11_8,	IRQ4),
+	PINMUX_IPSR_GPSR(IP1_11_8,	QSTH_QHS),
+	PINMUX_IPSR_GPSR(IP1_11_8,	A24),
+	PINMUX_IPSR_GPSR(IP1_11_8,	DU_EXHSYNC_DU_HSYNC),
 	PINMUX_IPSR_MSEL(IP1_11_8,	VI4_DATA4_B,		SEL_VIN4_1),
 	PINMUX_IPSR_MSEL(IP1_11_8,	PWM5_B,			SEL_PWM5_1),
 
-	PINMUX_IPSR_DATA(IP1_15_12,	IRQ5),
-	PINMUX_IPSR_DATA(IP1_15_12,	QSTB_QHE),
-	PINMUX_IPSR_DATA(IP1_15_12,	A23),
-	PINMUX_IPSR_DATA(IP1_15_12,	DU_EXVSYNC_DU_VSYNC),
+	PINMUX_IPSR_GPSR(IP1_15_12,	IRQ5),
+	PINMUX_IPSR_GPSR(IP1_15_12,	QSTB_QHE),
+	PINMUX_IPSR_GPSR(IP1_15_12,	A23),
+	PINMUX_IPSR_GPSR(IP1_15_12,	DU_EXVSYNC_DU_VSYNC),
 	PINMUX_IPSR_MSEL(IP1_15_12,	VI4_DATA5_B,		SEL_VIN4_1),
 	PINMUX_IPSR_MSEL(IP1_15_12,	PWM6_B,			SEL_PWM6_1),
 
-	PINMUX_IPSR_DATA(IP1_19_16,	PWM0),
-	PINMUX_IPSR_DATA(IP1_19_16,	AVB_AVTP_PPS),
-	PINMUX_IPSR_DATA(IP1_19_16,	A22),
+	PINMUX_IPSR_GPSR(IP1_19_16,	PWM0),
+	PINMUX_IPSR_GPSR(IP1_19_16,	AVB_AVTP_PPS),
+	PINMUX_IPSR_GPSR(IP1_19_16,	A22),
 	PINMUX_IPSR_MSEL(IP1_19_16,	VI4_DATA6_B,		SEL_VIN4_1),
 	PINMUX_IPSR_MSEL(IP1_19_16,	IECLK_B,		SEL_IEBUS_1),
 
 	PINMUX_IPSR_MSEL(IP1_23_20,	PWM1_A,			SEL_PWM1_0),
-	PINMUX_IPSR_DATA(IP1_23_20,	A21),
+	PINMUX_IPSR_GPSR(IP1_23_20,	A21),
 	PINMUX_IPSR_MSEL(IP1_23_20,	HRX3_D,			SEL_HSCIF3_3),
 	PINMUX_IPSR_MSEL(IP1_23_20,	VI4_DATA7_B,		SEL_VIN4_1),
 	PINMUX_IPSR_MSEL(IP1_23_20,	IERX_B,			SEL_IEBUS_1),
 
 	PINMUX_IPSR_MSEL(IP1_27_24,	PWM2_A,			SEL_PWM2_0),
-	PINMUX_IPSR_DATA(IP1_27_24,	A20),
+	PINMUX_IPSR_GPSR(IP1_27_24,	A20),
 	PINMUX_IPSR_MSEL(IP1_27_24,	HTX3_D,			SEL_HSCIF3_3),
 	PINMUX_IPSR_MSEL(IP1_27_24,	IETX_B,			SEL_IEBUS_1),
 
-	PINMUX_IPSR_DATA(IP1_31_28,	A0),
-	PINMUX_IPSR_DATA(IP1_31_28,	LCDOUT16),
+	PINMUX_IPSR_GPSR(IP1_31_28,	A0),
+	PINMUX_IPSR_GPSR(IP1_31_28,	LCDOUT16),
 	PINMUX_IPSR_MSEL(IP1_31_28,	MSIOF3_SYNC_B,		SEL_MSIOF3_1),
-	PINMUX_IPSR_DATA(IP1_31_28,	VI4_DATA8),
-	PINMUX_IPSR_DATA(IP1_31_28,	DU_DB0),
+	PINMUX_IPSR_GPSR(IP1_31_28,	VI4_DATA8),
+	PINMUX_IPSR_GPSR(IP1_31_28,	DU_DB0),
 	PINMUX_IPSR_MSEL(IP1_31_28,	PWM3_A,			SEL_PWM3_0),
 
 	/* IPSR2 */
-	PINMUX_IPSR_DATA(IP2_3_0,	A1),
-	PINMUX_IPSR_DATA(IP2_3_0,	LCDOUT17),
+	PINMUX_IPSR_GPSR(IP2_3_0,	A1),
+	PINMUX_IPSR_GPSR(IP2_3_0,	LCDOUT17),
 	PINMUX_IPSR_MSEL(IP2_3_0,	MSIOF3_TXD_B,		SEL_MSIOF3_1),
-	PINMUX_IPSR_DATA(IP2_3_0,	VI4_DATA9),
-	PINMUX_IPSR_DATA(IP2_3_0,	DU_DB1),
+	PINMUX_IPSR_GPSR(IP2_3_0,	VI4_DATA9),
+	PINMUX_IPSR_GPSR(IP2_3_0,	DU_DB1),
 	PINMUX_IPSR_MSEL(IP2_3_0,	PWM4_A,			SEL_PWM4_0),
 
-	PINMUX_IPSR_DATA(IP2_7_4,	A2),
-	PINMUX_IPSR_DATA(IP2_7_4,	LCDOUT18),
+	PINMUX_IPSR_GPSR(IP2_7_4,	A2),
+	PINMUX_IPSR_GPSR(IP2_7_4,	LCDOUT18),
 	PINMUX_IPSR_MSEL(IP2_7_4,	MSIOF3_SCK_B,		SEL_MSIOF3_1),
-	PINMUX_IPSR_DATA(IP2_7_4,	VI4_DATA10),
-	PINMUX_IPSR_DATA(IP2_7_4,	DU_DB2),
+	PINMUX_IPSR_GPSR(IP2_7_4,	VI4_DATA10),
+	PINMUX_IPSR_GPSR(IP2_7_4,	DU_DB2),
 	PINMUX_IPSR_MSEL(IP2_7_4,	PWM5_A,			SEL_PWM5_0),
 
-	PINMUX_IPSR_DATA(IP2_11_8,	A3),
-	PINMUX_IPSR_DATA(IP2_11_8,	LCDOUT19),
+	PINMUX_IPSR_GPSR(IP2_11_8,	A3),
+	PINMUX_IPSR_GPSR(IP2_11_8,	LCDOUT19),
 	PINMUX_IPSR_MSEL(IP2_11_8,	MSIOF3_RXD_B,		SEL_MSIOF3_1),
-	PINMUX_IPSR_DATA(IP2_11_8,	VI4_DATA11),
-	PINMUX_IPSR_DATA(IP2_11_8,	DU_DB3),
+	PINMUX_IPSR_GPSR(IP2_11_8,	VI4_DATA11),
+	PINMUX_IPSR_GPSR(IP2_11_8,	DU_DB3),
 	PINMUX_IPSR_MSEL(IP2_11_8,	PWM6_A,			SEL_PWM6_0),
 
-	PINMUX_IPSR_DATA(IP2_15_12,	A4),
-	PINMUX_IPSR_DATA(IP2_15_12,	LCDOUT20),
+	PINMUX_IPSR_GPSR(IP2_15_12,	A4),
+	PINMUX_IPSR_GPSR(IP2_15_12,	LCDOUT20),
 	PINMUX_IPSR_MSEL(IP2_15_12,	MSIOF3_SS1_B,		SEL_MSIOF3_1),
-	PINMUX_IPSR_DATA(IP2_15_12,	VI4_DATA12),
-	PINMUX_IPSR_DATA(IP2_15_12,	VI5_DATA12),
-	PINMUX_IPSR_DATA(IP2_15_12,	DU_DB4),
+	PINMUX_IPSR_GPSR(IP2_15_12,	VI4_DATA12),
+	PINMUX_IPSR_GPSR(IP2_15_12,	VI5_DATA12),
+	PINMUX_IPSR_GPSR(IP2_15_12,	DU_DB4),
 
-	PINMUX_IPSR_DATA(IP2_19_16,	A5),
-	PINMUX_IPSR_DATA(IP2_19_16,	LCDOUT21),
+	PINMUX_IPSR_GPSR(IP2_19_16,	A5),
+	PINMUX_IPSR_GPSR(IP2_19_16,	LCDOUT21),
 	PINMUX_IPSR_MSEL(IP2_19_16,	MSIOF3_SS2_B,		SEL_MSIOF3_1),
 	PINMUX_IPSR_MSEL(IP2_19_16,	SCK4_B,			SEL_SCIF4_1),
-	PINMUX_IPSR_DATA(IP2_19_16,	VI4_DATA13),
-	PINMUX_IPSR_DATA(IP2_19_16,	VI5_DATA13),
-	PINMUX_IPSR_DATA(IP2_19_16,	DU_DB5),
+	PINMUX_IPSR_GPSR(IP2_19_16,	VI4_DATA13),
+	PINMUX_IPSR_GPSR(IP2_19_16,	VI5_DATA13),
+	PINMUX_IPSR_GPSR(IP2_19_16,	DU_DB5),
 
-	PINMUX_IPSR_DATA(IP2_23_20,	A6),
-	PINMUX_IPSR_DATA(IP2_23_20,	LCDOUT22),
+	PINMUX_IPSR_GPSR(IP2_23_20,	A6),
+	PINMUX_IPSR_GPSR(IP2_23_20,	LCDOUT22),
 	PINMUX_IPSR_MSEL(IP2_23_20,	MSIOF2_SS1_A,		SEL_MSIOF2_0),
 	PINMUX_IPSR_MSEL(IP2_23_20,	RX4_B,			SEL_SCIF4_1),
-	PINMUX_IPSR_DATA(IP2_23_20,	VI4_DATA14),
-	PINMUX_IPSR_DATA(IP2_23_20,	VI5_DATA14),
-	PINMUX_IPSR_DATA(IP2_23_20,	DU_DB6),
+	PINMUX_IPSR_GPSR(IP2_23_20,	VI4_DATA14),
+	PINMUX_IPSR_GPSR(IP2_23_20,	VI5_DATA14),
+	PINMUX_IPSR_GPSR(IP2_23_20,	DU_DB6),
 
-	PINMUX_IPSR_DATA(IP2_27_24,	A7),
-	PINMUX_IPSR_DATA(IP2_27_24,	LCDOUT23),
+	PINMUX_IPSR_GPSR(IP2_27_24,	A7),
+	PINMUX_IPSR_GPSR(IP2_27_24,	LCDOUT23),
 	PINMUX_IPSR_MSEL(IP2_27_24,	MSIOF2_SS2_A,		SEL_MSIOF2_0),
 	PINMUX_IPSR_MSEL(IP2_27_24,	TX4_B,			SEL_SCIF4_1),
-	PINMUX_IPSR_DATA(IP2_27_24,	VI4_DATA15),
-	PINMUX_IPSR_DATA(IP2_27_24,	VI5_DATA15),
-	PINMUX_IPSR_DATA(IP2_27_24,	DU_DB7),
+	PINMUX_IPSR_GPSR(IP2_27_24,	VI4_DATA15),
+	PINMUX_IPSR_GPSR(IP2_27_24,	VI5_DATA15),
+	PINMUX_IPSR_GPSR(IP2_27_24,	DU_DB7),
 
-	PINMUX_IPSR_DATA(IP2_31_28,	A8),
+	PINMUX_IPSR_GPSR(IP2_31_28,	A8),
 	PINMUX_IPSR_MSEL(IP2_31_28,	RX3_B,			SEL_SCIF3_1),
 	PINMUX_IPSR_MSEL(IP2_31_28,	MSIOF2_SYNC_A,		SEL_MSIOF2_0),
 	PINMUX_IPSR_MSEL(IP2_31_28,	HRX4_B,			SEL_HSCIF4_1),
@@ -720,99 +719,99 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP2_31_28,	PWM1_B,			SEL_PWM1_1),
 
 	/* IPSR3 */
-	PINMUX_IPSR_DATA(IP3_3_0,	A9),
+	PINMUX_IPSR_GPSR(IP3_3_0,	A9),
 	PINMUX_IPSR_MSEL(IP3_3_0,	MSIOF2_SCK_A,		SEL_MSIOF2_0),
 	PINMUX_IPSR_MSEL(IP3_3_0,	CTS4_N_B,		SEL_SCIF4_1),
-	PINMUX_IPSR_DATA(IP3_3_0,	VI5_VSYNC_N),
+	PINMUX_IPSR_GPSR(IP3_3_0,	VI5_VSYNC_N),
 
-	PINMUX_IPSR_DATA(IP3_7_4,	A10),
+	PINMUX_IPSR_GPSR(IP3_7_4,	A10),
 	PINMUX_IPSR_MSEL(IP3_7_4,	MSIOF2_RXD_A,		SEL_MSIOF2_0),
 	PINMUX_IPSR_MSEL(IP3_7_4,	RTS4_N_TANS_B,		SEL_SCIF4_1),
-	PINMUX_IPSR_DATA(IP3_7_4,	VI5_HSYNC_N),
+	PINMUX_IPSR_GPSR(IP3_7_4,	VI5_HSYNC_N),
 
-	PINMUX_IPSR_DATA(IP3_11_8,	A11),
+	PINMUX_IPSR_GPSR(IP3_11_8,	A11),
 	PINMUX_IPSR_MSEL(IP3_11_8,	TX3_B,			SEL_SCIF3_1),
 	PINMUX_IPSR_MSEL(IP3_11_8,	MSIOF2_TXD_A,		SEL_MSIOF2_0),
 	PINMUX_IPSR_MSEL(IP3_11_8,	HTX4_B,			SEL_HSCIF4_1),
-	PINMUX_IPSR_DATA(IP3_11_8,	HSCK4),
-	PINMUX_IPSR_DATA(IP3_11_8,	VI5_FIELD),
+	PINMUX_IPSR_GPSR(IP3_11_8,	HSCK4),
+	PINMUX_IPSR_GPSR(IP3_11_8,	VI5_FIELD),
 	PINMUX_IPSR_MSEL(IP3_11_8,	SCL6_A,			SEL_I2C6_0),
 	PINMUX_IPSR_MSEL(IP3_11_8,	AVB_AVTP_CAPTURE_B,	SEL_ETHERAVB_1),
 	PINMUX_IPSR_MSEL(IP3_11_8,	PWM2_B,			SEL_PWM2_1),
 
-	PINMUX_IPSR_DATA(IP3_15_12,	A12),
-	PINMUX_IPSR_DATA(IP3_15_12,	LCDOUT12),
+	PINMUX_IPSR_GPSR(IP3_15_12,	A12),
+	PINMUX_IPSR_GPSR(IP3_15_12,	LCDOUT12),
 	PINMUX_IPSR_MSEL(IP3_15_12,	MSIOF3_SCK_C,		SEL_MSIOF3_2),
 	PINMUX_IPSR_MSEL(IP3_15_12,	HRX4_A,			SEL_HSCIF4_0),
-	PINMUX_IPSR_DATA(IP3_15_12,	VI5_DATA8),
-	PINMUX_IPSR_DATA(IP3_15_12,	DU_DG4),
+	PINMUX_IPSR_GPSR(IP3_15_12,	VI5_DATA8),
+	PINMUX_IPSR_GPSR(IP3_15_12,	DU_DG4),
 
-	PINMUX_IPSR_DATA(IP3_19_16,	A13),
-	PINMUX_IPSR_DATA(IP3_19_16,	LCDOUT13),
+	PINMUX_IPSR_GPSR(IP3_19_16,	A13),
+	PINMUX_IPSR_GPSR(IP3_19_16,	LCDOUT13),
 	PINMUX_IPSR_MSEL(IP3_19_16,	MSIOF3_SYNC_C,		SEL_MSIOF3_2),
 	PINMUX_IPSR_MSEL(IP3_19_16,	HTX4_A,			SEL_HSCIF4_0),
-	PINMUX_IPSR_DATA(IP3_19_16,	VI5_DATA9),
-	PINMUX_IPSR_DATA(IP3_19_16,	DU_DG5),
+	PINMUX_IPSR_GPSR(IP3_19_16,	VI5_DATA9),
+	PINMUX_IPSR_GPSR(IP3_19_16,	DU_DG5),
 
-	PINMUX_IPSR_DATA(IP3_23_20,	A14),
-	PINMUX_IPSR_DATA(IP3_23_20,	LCDOUT14),
+	PINMUX_IPSR_GPSR(IP3_23_20,	A14),
+	PINMUX_IPSR_GPSR(IP3_23_20,	LCDOUT14),
 	PINMUX_IPSR_MSEL(IP3_23_20,	MSIOF3_RXD_C,		SEL_MSIOF3_2),
-	PINMUX_IPSR_DATA(IP3_23_20,	HCTS4_N),
-	PINMUX_IPSR_DATA(IP3_23_20,	VI5_DATA10),
-	PINMUX_IPSR_DATA(IP3_23_20,	DU_DG6),
+	PINMUX_IPSR_GPSR(IP3_23_20,	HCTS4_N),
+	PINMUX_IPSR_GPSR(IP3_23_20,	VI5_DATA10),
+	PINMUX_IPSR_GPSR(IP3_23_20,	DU_DG6),
 
-	PINMUX_IPSR_DATA(IP3_27_24,	A15),
-	PINMUX_IPSR_DATA(IP3_27_24,	LCDOUT15),
+	PINMUX_IPSR_GPSR(IP3_27_24,	A15),
+	PINMUX_IPSR_GPSR(IP3_27_24,	LCDOUT15),
 	PINMUX_IPSR_MSEL(IP3_27_24,	MSIOF3_TXD_C,		SEL_MSIOF3_2),
-	PINMUX_IPSR_DATA(IP3_27_24,	HRTS4_N),
-	PINMUX_IPSR_DATA(IP3_27_24,	VI5_DATA11),
-	PINMUX_IPSR_DATA(IP3_27_24,	DU_DG7),
+	PINMUX_IPSR_GPSR(IP3_27_24,	HRTS4_N),
+	PINMUX_IPSR_GPSR(IP3_27_24,	VI5_DATA11),
+	PINMUX_IPSR_GPSR(IP3_27_24,	DU_DG7),
 
-	PINMUX_IPSR_DATA(IP3_31_28,	A16),
-	PINMUX_IPSR_DATA(IP3_31_28,	LCDOUT8),
-	PINMUX_IPSR_DATA(IP3_31_28,	VI4_FIELD),
-	PINMUX_IPSR_DATA(IP3_31_28,	DU_DG0),
+	PINMUX_IPSR_GPSR(IP3_31_28,	A16),
+	PINMUX_IPSR_GPSR(IP3_31_28,	LCDOUT8),
+	PINMUX_IPSR_GPSR(IP3_31_28,	VI4_FIELD),
+	PINMUX_IPSR_GPSR(IP3_31_28,	DU_DG0),
 
 	/* IPSR4 */
-	PINMUX_IPSR_DATA(IP4_3_0,	A17),
-	PINMUX_IPSR_DATA(IP4_3_0,	LCDOUT9),
-	PINMUX_IPSR_DATA(IP4_3_0,	VI4_VSYNC_N),
-	PINMUX_IPSR_DATA(IP4_3_0,	DU_DG1),
-
-	PINMUX_IPSR_DATA(IP4_7_4,	A18),
-	PINMUX_IPSR_DATA(IP4_7_4,	LCDOUT10),
-	PINMUX_IPSR_DATA(IP4_7_4,	VI4_HSYNC_N),
-	PINMUX_IPSR_DATA(IP4_7_4,	DU_DG2),
-
-	PINMUX_IPSR_DATA(IP4_11_8,	A19),
-	PINMUX_IPSR_DATA(IP4_11_8,	LCDOUT11),
-	PINMUX_IPSR_DATA(IP4_11_8,	VI4_CLKENB),
-	PINMUX_IPSR_DATA(IP4_11_8,	DU_DG3),
-
-	PINMUX_IPSR_DATA(IP4_15_12,	CS0_N),
-	PINMUX_IPSR_DATA(IP4_15_12,	VI5_CLKENB),
-
-	PINMUX_IPSR_DATA(IP4_19_16,	CS1_N_A26),
-	PINMUX_IPSR_DATA(IP4_19_16,	VI5_CLK),
+	PINMUX_IPSR_GPSR(IP4_3_0,	A17),
+	PINMUX_IPSR_GPSR(IP4_3_0,	LCDOUT9),
+	PINMUX_IPSR_GPSR(IP4_3_0,	VI4_VSYNC_N),
+	PINMUX_IPSR_GPSR(IP4_3_0,	DU_DG1),
+
+	PINMUX_IPSR_GPSR(IP4_7_4,	A18),
+	PINMUX_IPSR_GPSR(IP4_7_4,	LCDOUT10),
+	PINMUX_IPSR_GPSR(IP4_7_4,	VI4_HSYNC_N),
+	PINMUX_IPSR_GPSR(IP4_7_4,	DU_DG2),
+
+	PINMUX_IPSR_GPSR(IP4_11_8,	A19),
+	PINMUX_IPSR_GPSR(IP4_11_8,	LCDOUT11),
+	PINMUX_IPSR_GPSR(IP4_11_8,	VI4_CLKENB),
+	PINMUX_IPSR_GPSR(IP4_11_8,	DU_DG3),
+
+	PINMUX_IPSR_GPSR(IP4_15_12,	CS0_N),
+	PINMUX_IPSR_GPSR(IP4_15_12,	VI5_CLKENB),
+
+	PINMUX_IPSR_GPSR(IP4_19_16,	CS1_N_A26),
+	PINMUX_IPSR_GPSR(IP4_19_16,	VI5_CLK),
 	PINMUX_IPSR_MSEL(IP4_19_16,	EX_WAIT0_B,		SEL_LBSC_1),
 
-	PINMUX_IPSR_DATA(IP4_23_20,	BS_N),
-	PINMUX_IPSR_DATA(IP4_23_20,	QSTVA_QVS),
+	PINMUX_IPSR_GPSR(IP4_23_20,	BS_N),
+	PINMUX_IPSR_GPSR(IP4_23_20,	QSTVA_QVS),
 	PINMUX_IPSR_MSEL(IP4_23_20,	MSIOF3_SCK_D,		SEL_MSIOF3_3),
-	PINMUX_IPSR_DATA(IP4_23_20,	SCK3),
-	PINMUX_IPSR_DATA(IP4_23_20,	HSCK3),
-	PINMUX_IPSR_DATA(IP4_23_20,	CAN1_TX),
-	PINMUX_IPSR_DATA(IP4_23_20,	CANFD1_TX),
+	PINMUX_IPSR_GPSR(IP4_23_20,	SCK3),
+	PINMUX_IPSR_GPSR(IP4_23_20,	HSCK3),
+	PINMUX_IPSR_GPSR(IP4_23_20,	CAN1_TX),
+	PINMUX_IPSR_GPSR(IP4_23_20,	CANFD1_TX),
 	PINMUX_IPSR_MSEL(IP4_23_20,	IETX_A,			SEL_IEBUS_0),
 
-	PINMUX_IPSR_DATA(IP4_27_24,	RD_N),
+	PINMUX_IPSR_GPSR(IP4_27_24,	RD_N),
 	PINMUX_IPSR_MSEL(IP4_27_24,	MSIOF3_SYNC_D,		SEL_MSIOF3_3),
 	PINMUX_IPSR_MSEL(IP4_27_24,	RX3_A,			SEL_SCIF3_0),
 	PINMUX_IPSR_MSEL(IP4_27_24,	HRX3_A,			SEL_HSCIF3_0),
 	PINMUX_IPSR_MSEL(IP4_27_24,	CAN0_TX_A,		SEL_RCAN0_0),
 	PINMUX_IPSR_MSEL(IP4_27_24,	CANFD0_TX_A,		SEL_CANFD0_0),
 
-	PINMUX_IPSR_DATA(IP4_31_28,	RD_WR_N),
+	PINMUX_IPSR_GPSR(IP4_31_28,	RD_WR_N),
 	PINMUX_IPSR_MSEL(IP4_31_28,	MSIOF3_RXD_D,		SEL_MSIOF3_3),
 	PINMUX_IPSR_MSEL(IP4_31_28,	TX3_A,			SEL_SCIF3_0),
 	PINMUX_IPSR_MSEL(IP4_31_28,	HTX3_A,			SEL_HSCIF3_0),
@@ -820,236 +819,236 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP4_31_28,	CANFD0_RX_A,		SEL_CANFD0_0),
 
 	/* IPSR5 */
-	PINMUX_IPSR_DATA(IP5_3_0,	WE0_N),
+	PINMUX_IPSR_GPSR(IP5_3_0,	WE0_N),
 	PINMUX_IPSR_MSEL(IP5_3_0,	MSIOF3_TXD_D,		SEL_MSIOF3_3),
-	PINMUX_IPSR_DATA(IP5_3_0,	CTS3_N),
-	PINMUX_IPSR_DATA(IP5_3_0,	HCTS3_N),
+	PINMUX_IPSR_GPSR(IP5_3_0,	CTS3_N),
+	PINMUX_IPSR_GPSR(IP5_3_0,	HCTS3_N),
 	PINMUX_IPSR_MSEL(IP5_3_0,	SCL6_B,			SEL_I2C6_1),
-	PINMUX_IPSR_DATA(IP5_3_0,	CAN_CLK),
+	PINMUX_IPSR_GPSR(IP5_3_0,	CAN_CLK),
 	PINMUX_IPSR_MSEL(IP5_3_0,	IECLK_A,		SEL_IEBUS_0),
 
-	PINMUX_IPSR_DATA(IP5_7_4,	WE1_N),
+	PINMUX_IPSR_GPSR(IP5_7_4,	WE1_N),
 	PINMUX_IPSR_MSEL(IP5_7_4,	MSIOF3_SS1_D,		SEL_MSIOF3_3),
-	PINMUX_IPSR_DATA(IP5_7_4,	RTS3_N_TANS),
-	PINMUX_IPSR_DATA(IP5_7_4,	HRTS3_N),
+	PINMUX_IPSR_GPSR(IP5_7_4,	RTS3_N_TANS),
+	PINMUX_IPSR_GPSR(IP5_7_4,	HRTS3_N),
 	PINMUX_IPSR_MSEL(IP5_7_4,	SDA6_B,			SEL_I2C6_1),
-	PINMUX_IPSR_DATA(IP5_7_4,	CAN1_RX),
-	PINMUX_IPSR_DATA(IP5_7_4,	CANFD1_RX),
+	PINMUX_IPSR_GPSR(IP5_7_4,	CAN1_RX),
+	PINMUX_IPSR_GPSR(IP5_7_4,	CANFD1_RX),
 	PINMUX_IPSR_MSEL(IP5_7_4,	IERX_A,			SEL_IEBUS_0),
 
 	PINMUX_IPSR_MSEL(IP5_11_8,	EX_WAIT0_A,		SEL_LBSC_0),
-	PINMUX_IPSR_DATA(IP5_11_8,	QCLK),
-	PINMUX_IPSR_DATA(IP5_11_8,	VI4_CLK),
-	PINMUX_IPSR_DATA(IP5_11_8,	DU_DOTCLKOUT0),
+	PINMUX_IPSR_GPSR(IP5_11_8,	QCLK),
+	PINMUX_IPSR_GPSR(IP5_11_8,	VI4_CLK),
+	PINMUX_IPSR_GPSR(IP5_11_8,	DU_DOTCLKOUT0),
 
-	PINMUX_IPSR_DATA(IP5_15_12,	D0),
+	PINMUX_IPSR_GPSR(IP5_15_12,	D0),
 	PINMUX_IPSR_MSEL(IP5_15_12,	MSIOF2_SS1_B,		SEL_MSIOF2_1),
 	PINMUX_IPSR_MSEL(IP5_15_12,	MSIOF3_SCK_A,		SEL_MSIOF3_0),
-	PINMUX_IPSR_DATA(IP5_15_12,	VI4_DATA16),
-	PINMUX_IPSR_DATA(IP5_15_12,	VI5_DATA0),
+	PINMUX_IPSR_GPSR(IP5_15_12,	VI4_DATA16),
+	PINMUX_IPSR_GPSR(IP5_15_12,	VI5_DATA0),
 
-	PINMUX_IPSR_DATA(IP5_19_16,	D1),
+	PINMUX_IPSR_GPSR(IP5_19_16,	D1),
 	PINMUX_IPSR_MSEL(IP5_19_16,	MSIOF2_SS2_B,		SEL_MSIOF2_1),
 	PINMUX_IPSR_MSEL(IP5_19_16,	MSIOF3_SYNC_A,		SEL_MSIOF3_0),
-	PINMUX_IPSR_DATA(IP5_19_16,	VI4_DATA17),
-	PINMUX_IPSR_DATA(IP5_19_16,	VI5_DATA1),
+	PINMUX_IPSR_GPSR(IP5_19_16,	VI4_DATA17),
+	PINMUX_IPSR_GPSR(IP5_19_16,	VI5_DATA1),
 
-	PINMUX_IPSR_DATA(IP5_23_20,	D2),
+	PINMUX_IPSR_GPSR(IP5_23_20,	D2),
 	PINMUX_IPSR_MSEL(IP5_23_20,	MSIOF3_RXD_A,		SEL_MSIOF3_0),
-	PINMUX_IPSR_DATA(IP5_23_20,	VI4_DATA18),
-	PINMUX_IPSR_DATA(IP5_23_20,	VI5_DATA2),
+	PINMUX_IPSR_GPSR(IP5_23_20,	VI4_DATA18),
+	PINMUX_IPSR_GPSR(IP5_23_20,	VI5_DATA2),
 
-	PINMUX_IPSR_DATA(IP5_27_24,	D3),
+	PINMUX_IPSR_GPSR(IP5_27_24,	D3),
 	PINMUX_IPSR_MSEL(IP5_27_24,	MSIOF3_TXD_A,		SEL_MSIOF3_0),
-	PINMUX_IPSR_DATA(IP5_27_24,	VI4_DATA19),
-	PINMUX_IPSR_DATA(IP5_27_24,	VI5_DATA3),
+	PINMUX_IPSR_GPSR(IP5_27_24,	VI4_DATA19),
+	PINMUX_IPSR_GPSR(IP5_27_24,	VI5_DATA3),
 
-	PINMUX_IPSR_DATA(IP5_31_28,	D4),
+	PINMUX_IPSR_GPSR(IP5_31_28,	D4),
 	PINMUX_IPSR_MSEL(IP5_31_28,	MSIOF2_SCK_B,		SEL_MSIOF2_1),
-	PINMUX_IPSR_DATA(IP5_31_28,	VI4_DATA20),
-	PINMUX_IPSR_DATA(IP5_31_28,	VI5_DATA4),
+	PINMUX_IPSR_GPSR(IP5_31_28,	VI4_DATA20),
+	PINMUX_IPSR_GPSR(IP5_31_28,	VI5_DATA4),
 
 	/* IPSR6 */
-	PINMUX_IPSR_DATA(IP6_3_0,	D5),
+	PINMUX_IPSR_GPSR(IP6_3_0,	D5),
 	PINMUX_IPSR_MSEL(IP6_3_0,	MSIOF2_SYNC_B,		SEL_MSIOF2_1),
-	PINMUX_IPSR_DATA(IP6_3_0,	VI4_DATA21),
-	PINMUX_IPSR_DATA(IP6_3_0,	VI5_DATA5),
+	PINMUX_IPSR_GPSR(IP6_3_0,	VI4_DATA21),
+	PINMUX_IPSR_GPSR(IP6_3_0,	VI5_DATA5),
 
-	PINMUX_IPSR_DATA(IP6_7_4,	D6),
+	PINMUX_IPSR_GPSR(IP6_7_4,	D6),
 	PINMUX_IPSR_MSEL(IP6_7_4,	MSIOF2_RXD_B,		SEL_MSIOF2_1),
-	PINMUX_IPSR_DATA(IP6_7_4,	VI4_DATA22),
-	PINMUX_IPSR_DATA(IP6_7_4,	VI5_DATA6),
+	PINMUX_IPSR_GPSR(IP6_7_4,	VI4_DATA22),
+	PINMUX_IPSR_GPSR(IP6_7_4,	VI5_DATA6),
 
-	PINMUX_IPSR_DATA(IP6_11_8,	D7),
+	PINMUX_IPSR_GPSR(IP6_11_8,	D7),
 	PINMUX_IPSR_MSEL(IP6_11_8,	MSIOF2_TXD_B,		SEL_MSIOF2_1),
-	PINMUX_IPSR_DATA(IP6_11_8,	VI4_DATA23),
-	PINMUX_IPSR_DATA(IP6_11_8,	VI5_DATA7),
+	PINMUX_IPSR_GPSR(IP6_11_8,	VI4_DATA23),
+	PINMUX_IPSR_GPSR(IP6_11_8,	VI5_DATA7),
 
-	PINMUX_IPSR_DATA(IP6_15_12,	D8),
-	PINMUX_IPSR_DATA(IP6_15_12,	LCDOUT0),
+	PINMUX_IPSR_GPSR(IP6_15_12,	D8),
+	PINMUX_IPSR_GPSR(IP6_15_12,	LCDOUT0),
 	PINMUX_IPSR_MSEL(IP6_15_12,	MSIOF2_SCK_D,		SEL_MSIOF2_3),
 	PINMUX_IPSR_MSEL(IP6_15_12,	SCK4_C,			SEL_SCIF4_2),
 	PINMUX_IPSR_MSEL(IP6_15_12,	VI4_DATA0_A,		SEL_VIN4_0),
-	PINMUX_IPSR_DATA(IP6_15_12,	DU_DR0),
+	PINMUX_IPSR_GPSR(IP6_15_12,	DU_DR0),
 
-	PINMUX_IPSR_DATA(IP6_19_16,	D9),
-	PINMUX_IPSR_DATA(IP6_19_16,	LCDOUT1),
+	PINMUX_IPSR_GPSR(IP6_19_16,	D9),
+	PINMUX_IPSR_GPSR(IP6_19_16,	LCDOUT1),
 	PINMUX_IPSR_MSEL(IP6_19_16,	MSIOF2_SYNC_D,		SEL_MSIOF2_3),
 	PINMUX_IPSR_MSEL(IP6_19_16,	VI4_DATA1_A,		SEL_VIN4_0),
-	PINMUX_IPSR_DATA(IP6_19_16,	DU_DR1),
+	PINMUX_IPSR_GPSR(IP6_19_16,	DU_DR1),
 
-	PINMUX_IPSR_DATA(IP6_23_20,	D10),
-	PINMUX_IPSR_DATA(IP6_23_20,	LCDOUT2),
+	PINMUX_IPSR_GPSR(IP6_23_20,	D10),
+	PINMUX_IPSR_GPSR(IP6_23_20,	LCDOUT2),
 	PINMUX_IPSR_MSEL(IP6_23_20,	MSIOF2_RXD_D,		SEL_MSIOF2_3),
 	PINMUX_IPSR_MSEL(IP6_23_20,	HRX3_B,			SEL_HSCIF3_1),
 	PINMUX_IPSR_MSEL(IP6_23_20,	VI4_DATA2_A,		SEL_VIN4_0),
 	PINMUX_IPSR_MSEL(IP6_23_20,	CTS4_N_C,		SEL_SCIF4_2),
-	PINMUX_IPSR_DATA(IP6_23_20,	DU_DR2),
+	PINMUX_IPSR_GPSR(IP6_23_20,	DU_DR2),
 
-	PINMUX_IPSR_DATA(IP6_27_24,	D11),
-	PINMUX_IPSR_DATA(IP6_27_24,	LCDOUT3),
+	PINMUX_IPSR_GPSR(IP6_27_24,	D11),
+	PINMUX_IPSR_GPSR(IP6_27_24,	LCDOUT3),
 	PINMUX_IPSR_MSEL(IP6_27_24,	MSIOF2_TXD_D,		SEL_MSIOF2_3),
 	PINMUX_IPSR_MSEL(IP6_27_24,	HTX3_B,			SEL_HSCIF3_1),
 	PINMUX_IPSR_MSEL(IP6_27_24,	VI4_DATA3_A,		SEL_VIN4_0),
 	PINMUX_IPSR_MSEL(IP6_27_24,	RTS4_N_TANS_C,		SEL_SCIF4_2),
-	PINMUX_IPSR_DATA(IP6_27_24,	DU_DR3),
+	PINMUX_IPSR_GPSR(IP6_27_24,	DU_DR3),
 
-	PINMUX_IPSR_DATA(IP6_31_28,	D12),
-	PINMUX_IPSR_DATA(IP6_31_28,	LCDOUT4),
+	PINMUX_IPSR_GPSR(IP6_31_28,	D12),
+	PINMUX_IPSR_GPSR(IP6_31_28,	LCDOUT4),
 	PINMUX_IPSR_MSEL(IP6_31_28,	MSIOF2_SS1_D,		SEL_MSIOF2_3),
 	PINMUX_IPSR_MSEL(IP6_31_28,	RX4_C,			SEL_SCIF4_2),
 	PINMUX_IPSR_MSEL(IP6_31_28,	VI4_DATA4_A,		SEL_VIN4_0),
-	PINMUX_IPSR_DATA(IP6_31_28,	DU_DR4),
+	PINMUX_IPSR_GPSR(IP6_31_28,	DU_DR4),
 
 	/* IPSR7 */
-	PINMUX_IPSR_DATA(IP7_3_0,	D13),
-	PINMUX_IPSR_DATA(IP7_3_0,	LCDOUT5),
+	PINMUX_IPSR_GPSR(IP7_3_0,	D13),
+	PINMUX_IPSR_GPSR(IP7_3_0,	LCDOUT5),
 	PINMUX_IPSR_MSEL(IP7_3_0,	MSIOF2_SS2_D,		SEL_MSIOF2_3),
 	PINMUX_IPSR_MSEL(IP7_3_0,	TX4_C,			SEL_SCIF4_2),
 	PINMUX_IPSR_MSEL(IP7_3_0,	VI4_DATA5_A,		SEL_VIN4_0),
-	PINMUX_IPSR_DATA(IP7_3_0,	DU_DR5),
+	PINMUX_IPSR_GPSR(IP7_3_0,	DU_DR5),
 
-	PINMUX_IPSR_DATA(IP7_7_4,	D14),
-	PINMUX_IPSR_DATA(IP7_7_4,	LCDOUT6),
+	PINMUX_IPSR_GPSR(IP7_7_4,	D14),
+	PINMUX_IPSR_GPSR(IP7_7_4,	LCDOUT6),
 	PINMUX_IPSR_MSEL(IP7_7_4,	MSIOF3_SS1_A,		SEL_MSIOF3_0),
 	PINMUX_IPSR_MSEL(IP7_7_4,	HRX3_C,			SEL_HSCIF3_2),
 	PINMUX_IPSR_MSEL(IP7_7_4,	VI4_DATA6_A,		SEL_VIN4_0),
-	PINMUX_IPSR_DATA(IP7_7_4,	DU_DR6),
+	PINMUX_IPSR_GPSR(IP7_7_4,	DU_DR6),
 	PINMUX_IPSR_MSEL(IP7_7_4,	SCL6_C,			SEL_I2C6_2),
 
-	PINMUX_IPSR_DATA(IP7_11_8,	D15),
-	PINMUX_IPSR_DATA(IP7_11_8,	LCDOUT7),
+	PINMUX_IPSR_GPSR(IP7_11_8,	D15),
+	PINMUX_IPSR_GPSR(IP7_11_8,	LCDOUT7),
 	PINMUX_IPSR_MSEL(IP7_11_8,	MSIOF3_SS2_A,		SEL_MSIOF3_0),
 	PINMUX_IPSR_MSEL(IP7_11_8,	HTX3_C,			SEL_HSCIF3_2),
 	PINMUX_IPSR_MSEL(IP7_11_8,	VI4_DATA7_A,		SEL_VIN4_0),
-	PINMUX_IPSR_DATA(IP7_11_8,	DU_DR7),
+	PINMUX_IPSR_GPSR(IP7_11_8,	DU_DR7),
 	PINMUX_IPSR_MSEL(IP7_11_8,	SDA6_C,			SEL_I2C6_2),
 
-	PINMUX_IPSR_DATA(IP7_15_12,	FSCLKST),
+	PINMUX_IPSR_GPSR(IP7_15_12,	FSCLKST),
 
-	PINMUX_IPSR_DATA(IP7_19_16,	SD0_CLK),
+	PINMUX_IPSR_GPSR(IP7_19_16,	SD0_CLK),
 	PINMUX_IPSR_MSEL(IP7_19_16,	MSIOF1_SCK_E,		SEL_MSIOF1_4),
 	PINMUX_IPSR_MSEL(IP7_19_16,	STP_OPWM_0_B,		SEL_SSP1_0_1),
 
-	PINMUX_IPSR_DATA(IP7_23_20,	SD0_CMD),
+	PINMUX_IPSR_GPSR(IP7_23_20,	SD0_CMD),
 	PINMUX_IPSR_MSEL(IP7_23_20,	MSIOF1_SYNC_E,		SEL_MSIOF1_4),
 	PINMUX_IPSR_MSEL(IP7_23_20,	STP_IVCXO27_0_B,	SEL_SSP1_0_1),
 
-	PINMUX_IPSR_DATA(IP7_27_24,	SD0_DAT0),
+	PINMUX_IPSR_GPSR(IP7_27_24,	SD0_DAT0),
 	PINMUX_IPSR_MSEL(IP7_27_24,	MSIOF1_RXD_E,		SEL_MSIOF1_4),
 	PINMUX_IPSR_MSEL(IP7_27_24,	TS_SCK0_B,		SEL_TSIF0_1),
 	PINMUX_IPSR_MSEL(IP7_27_24,	STP_ISCLK_0_B,		SEL_SSP1_0_1),
 
-	PINMUX_IPSR_DATA(IP7_31_28,	SD0_DAT1),
+	PINMUX_IPSR_GPSR(IP7_31_28,	SD0_DAT1),
 	PINMUX_IPSR_MSEL(IP7_31_28,	MSIOF1_TXD_E,		SEL_MSIOF1_4),
 	PINMUX_IPSR_MSEL(IP7_31_28,	TS_SPSYNC0_B,		SEL_TSIF0_1),
 	PINMUX_IPSR_MSEL(IP7_31_28,	STP_ISSYNC_0_B,		SEL_SSP1_0_1),
 
 	/* IPSR8 */
-	PINMUX_IPSR_DATA(IP8_3_0,	SD0_DAT2),
+	PINMUX_IPSR_GPSR(IP8_3_0,	SD0_DAT2),
 	PINMUX_IPSR_MSEL(IP8_3_0,	MSIOF1_SS1_E,		SEL_MSIOF1_4),
 	PINMUX_IPSR_MSEL(IP8_3_0,	TS_SDAT0_B,		SEL_TSIF0_1),
 	PINMUX_IPSR_MSEL(IP8_3_0,	STP_ISD_0_B,		SEL_SSP1_0_1),
 
-	PINMUX_IPSR_DATA(IP8_7_4,	SD0_DAT3),
+	PINMUX_IPSR_GPSR(IP8_7_4,	SD0_DAT3),
 	PINMUX_IPSR_MSEL(IP8_7_4,	MSIOF1_SS2_E,		SEL_MSIOF1_4),
 	PINMUX_IPSR_MSEL(IP8_7_4,	TS_SDEN0_B,		SEL_TSIF0_1),
 	PINMUX_IPSR_MSEL(IP8_7_4,	STP_ISEN_0_B,		SEL_SSP1_0_1),
 
-	PINMUX_IPSR_DATA(IP8_11_8,	SD1_CLK),
+	PINMUX_IPSR_GPSR(IP8_11_8,	SD1_CLK),
 	PINMUX_IPSR_MSEL(IP8_11_8,	MSIOF1_SCK_G,		SEL_MSIOF1_6),
 	PINMUX_IPSR_MSEL(IP8_11_8,	SIM0_CLK_A,		SEL_SIMCARD_0),
 
-	PINMUX_IPSR_DATA(IP8_15_12,	SD1_CMD),
+	PINMUX_IPSR_GPSR(IP8_15_12,	SD1_CMD),
 	PINMUX_IPSR_MSEL(IP8_15_12,	MSIOF1_SYNC_G,		SEL_MSIOF1_6),
 	PINMUX_IPSR_MSEL(IP8_15_12,	SIM0_D_A,		SEL_SIMCARD_0),
 	PINMUX_IPSR_MSEL(IP8_15_12,	STP_IVCXO27_1_B,	SEL_SSP1_1_1),
 
-	PINMUX_IPSR_DATA(IP8_19_16,	SD1_DAT0),
-	PINMUX_IPSR_DATA(IP8_19_16,	SD2_DAT4),
+	PINMUX_IPSR_GPSR(IP8_19_16,	SD1_DAT0),
+	PINMUX_IPSR_GPSR(IP8_19_16,	SD2_DAT4),
 	PINMUX_IPSR_MSEL(IP8_19_16,	MSIOF1_RXD_G,		SEL_MSIOF1_6),
 	PINMUX_IPSR_MSEL(IP8_19_16,	TS_SCK1_B,		SEL_TSIF1_1),
 	PINMUX_IPSR_MSEL(IP8_19_16,	STP_ISCLK_1_B,		SEL_SSP1_1_1),
 
-	PINMUX_IPSR_DATA(IP8_23_20,	SD1_DAT1),
-	PINMUX_IPSR_DATA(IP8_23_20,	SD2_DAT5),
+	PINMUX_IPSR_GPSR(IP8_23_20,	SD1_DAT1),
+	PINMUX_IPSR_GPSR(IP8_23_20,	SD2_DAT5),
 	PINMUX_IPSR_MSEL(IP8_23_20,	MSIOF1_TXD_G,		SEL_MSIOF1_6),
 	PINMUX_IPSR_MSEL(IP8_23_20,	TS_SPSYNC1_B,		SEL_TSIF1_1),
 	PINMUX_IPSR_MSEL(IP8_23_20,	STP_ISSYNC_1_B,		SEL_SSP1_1_1),
 
-	PINMUX_IPSR_DATA(IP8_27_24,	SD1_DAT2),
-	PINMUX_IPSR_DATA(IP8_27_24,	SD2_DAT6),
+	PINMUX_IPSR_GPSR(IP8_27_24,	SD1_DAT2),
+	PINMUX_IPSR_GPSR(IP8_27_24,	SD2_DAT6),
 	PINMUX_IPSR_MSEL(IP8_27_24,	MSIOF1_SS1_G,		SEL_MSIOF1_6),
 	PINMUX_IPSR_MSEL(IP8_27_24,	TS_SDAT1_B,		SEL_TSIF1_1),
 	PINMUX_IPSR_MSEL(IP8_27_24,	STP_ISD_1_B,		SEL_SSP1_1_1),
 
-	PINMUX_IPSR_DATA(IP8_31_28,	SD1_DAT3),
-	PINMUX_IPSR_DATA(IP8_31_28,	SD2_DAT7),
+	PINMUX_IPSR_GPSR(IP8_31_28,	SD1_DAT3),
+	PINMUX_IPSR_GPSR(IP8_31_28,	SD2_DAT7),
 	PINMUX_IPSR_MSEL(IP8_31_28,	MSIOF1_SS2_G,		SEL_MSIOF1_6),
 	PINMUX_IPSR_MSEL(IP8_31_28,	TS_SDEN1_B,		SEL_TSIF1_1),
 	PINMUX_IPSR_MSEL(IP8_31_28,	STP_ISEN_1_B,		SEL_SSP1_1_1),
 
 	/* IPSR9 */
-	PINMUX_IPSR_DATA(IP9_3_0,	SD2_CLK),
+	PINMUX_IPSR_GPSR(IP9_3_0,	SD2_CLK),
 
-	PINMUX_IPSR_DATA(IP9_7_4,	SD2_DAT0),
+	PINMUX_IPSR_GPSR(IP9_7_4,	SD2_DAT0),
 
-	PINMUX_IPSR_DATA(IP9_11_8,	SD2_DAT1),
+	PINMUX_IPSR_GPSR(IP9_11_8,	SD2_DAT1),
 
-	PINMUX_IPSR_DATA(IP9_15_12,	SD2_DAT2),
+	PINMUX_IPSR_GPSR(IP9_15_12,	SD2_DAT2),
 
-	PINMUX_IPSR_DATA(IP9_19_16,	SD2_DAT3),
+	PINMUX_IPSR_GPSR(IP9_19_16,	SD2_DAT3),
 
-	PINMUX_IPSR_DATA(IP9_23_20,	SD2_DS),
+	PINMUX_IPSR_GPSR(IP9_23_20,	SD2_DS),
 	PINMUX_IPSR_MSEL(IP9_23_20,	SATA_DEVSLP_B,		SEL_SATA_1),
 
-	PINMUX_IPSR_DATA(IP9_27_24,	SD3_DAT4),
+	PINMUX_IPSR_GPSR(IP9_27_24,	SD3_DAT4),
 	PINMUX_IPSR_MSEL(IP9_27_24,	SD2_CD_A,		SEL_SDHI2_0),
 
-	PINMUX_IPSR_DATA(IP9_31_28,	SD3_DAT5),
+	PINMUX_IPSR_GPSR(IP9_31_28,	SD3_DAT5),
 	PINMUX_IPSR_MSEL(IP9_31_28,	SD2_WP_A,		SEL_SDHI2_0),
 
 	/* IPSR10 */
-	PINMUX_IPSR_DATA(IP10_3_0,	SD3_DAT6),
-	PINMUX_IPSR_DATA(IP10_3_0,	SD3_CD),
+	PINMUX_IPSR_GPSR(IP10_3_0,	SD3_DAT6),
+	PINMUX_IPSR_GPSR(IP10_3_0,	SD3_CD),
 
-	PINMUX_IPSR_DATA(IP10_7_4,	SD3_DAT7),
-	PINMUX_IPSR_DATA(IP10_7_4,	SD3_WP),
+	PINMUX_IPSR_GPSR(IP10_7_4,	SD3_DAT7),
+	PINMUX_IPSR_GPSR(IP10_7_4,	SD3_WP),
 
-	PINMUX_IPSR_DATA(IP10_11_8,	SD0_CD),
+	PINMUX_IPSR_GPSR(IP10_11_8,	SD0_CD),
 	PINMUX_IPSR_MSEL(IP10_11_8,	SCL2_B,			SEL_I2C2_1),
 	PINMUX_IPSR_MSEL(IP10_11_8,	SIM0_RST_A,		SEL_SIMCARD_0),
 
-	PINMUX_IPSR_DATA(IP10_15_12,	SD0_WP),
+	PINMUX_IPSR_GPSR(IP10_15_12,	SD0_WP),
 	PINMUX_IPSR_MSEL(IP10_15_12,	SDA2_B,			SEL_I2C2_1),
 
-	PINMUX_IPSR_DATA(IP10_19_16,	SD1_CD),
+	PINMUX_IPSR_GPSR(IP10_19_16,	SD1_CD),
 	PINMUX_IPSR_MSEL(IP10_19_16,	SIM0_CLK_B,		SEL_SIMCARD_1),
 
-	PINMUX_IPSR_DATA(IP10_23_20,	SD1_WP),
+	PINMUX_IPSR_GPSR(IP10_23_20,	SD1_WP),
 	PINMUX_IPSR_MSEL(IP10_23_20,	SIM0_D_B,		SEL_SIMCARD_1),
 
-	PINMUX_IPSR_DATA(IP10_27_24,	SCK0),
+	PINMUX_IPSR_GPSR(IP10_27_24,	SCK0),
 	PINMUX_IPSR_MSEL(IP10_27_24,	HSCK1_B,		SEL_HSCIF1_1),
 	PINMUX_IPSR_MSEL(IP10_27_24,	MSIOF1_SS2_B,		SEL_MSIOF1_1),
 	PINMUX_IPSR_MSEL(IP10_27_24,	AUDIO_CLKC_B,		SEL_ADG_1),
@@ -1057,38 +1056,38 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP10_27_24,	SIM0_RST_B,		SEL_SIMCARD_1),
 	PINMUX_IPSR_MSEL(IP10_27_24,	STP_OPWM_0_C,		SEL_SSP1_0_2),
 	PINMUX_IPSR_MSEL(IP10_27_24,	RIF0_CLK_B,		SEL_DRIF0_1),
-	PINMUX_IPSR_DATA(IP10_27_24,	ADICHS2),
+	PINMUX_IPSR_GPSR(IP10_27_24,	ADICHS2),
 
-	PINMUX_IPSR_DATA(IP10_31_28,	RX0),
+	PINMUX_IPSR_GPSR(IP10_31_28,	RX0),
 	PINMUX_IPSR_MSEL(IP10_31_28,	HRX1_B,			SEL_HSCIF1_1),
 	PINMUX_IPSR_MSEL(IP10_31_28,	TS_SCK0_C,		SEL_TSIF0_2),
 	PINMUX_IPSR_MSEL(IP10_31_28,	STP_ISCLK_0_C,		SEL_SSP1_0_2),
 	PINMUX_IPSR_MSEL(IP10_31_28,	RIF0_D0_B,		SEL_DRIF0_1),
 
 	/* IPSR11 */
-	PINMUX_IPSR_DATA(IP11_3_0,	TX0),
+	PINMUX_IPSR_GPSR(IP11_3_0,	TX0),
 	PINMUX_IPSR_MSEL(IP11_3_0,	HTX1_B,			SEL_HSCIF1_1),
 	PINMUX_IPSR_MSEL(IP11_3_0,	TS_SPSYNC0_C,		SEL_TSIF0_2),
 	PINMUX_IPSR_MSEL(IP11_3_0,	STP_ISSYNC_0_C,		SEL_SSP1_0_2),
 	PINMUX_IPSR_MSEL(IP11_3_0,	RIF0_D1_B,		SEL_DRIF0_1),
 
-	PINMUX_IPSR_DATA(IP11_7_4,	CTS0_N),
+	PINMUX_IPSR_GPSR(IP11_7_4,	CTS0_N),
 	PINMUX_IPSR_MSEL(IP11_7_4,	HCTS1_N_B,		SEL_HSCIF1_1),
 	PINMUX_IPSR_MSEL(IP11_7_4,	MSIOF1_SYNC_B,		SEL_MSIOF1_1),
 	PINMUX_IPSR_MSEL(IP11_7_4,	TS_SPSYNC1_C,		SEL_TSIF1_2),
 	PINMUX_IPSR_MSEL(IP11_7_4,	STP_ISSYNC_1_C,		SEL_SSP1_1_2),
 	PINMUX_IPSR_MSEL(IP11_7_4,	RIF1_SYNC_B,		SEL_DRIF1_1),
 	PINMUX_IPSR_MSEL(IP11_7_4,	AUDIO_CLKOUT_C,		SEL_ADG_2),
-	PINMUX_IPSR_DATA(IP11_7_4,	ADICS_SAMP),
+	PINMUX_IPSR_GPSR(IP11_7_4,	ADICS_SAMP),
 
-	PINMUX_IPSR_DATA(IP11_11_8,	RTS0_N_TANS),
+	PINMUX_IPSR_GPSR(IP11_11_8,	RTS0_N_TANS),
 	PINMUX_IPSR_MSEL(IP11_11_8,	HRTS1_N_B,		SEL_HSCIF1_1),
 	PINMUX_IPSR_MSEL(IP11_11_8,	MSIOF1_SS1_B,		SEL_MSIOF1_1),
 	PINMUX_IPSR_MSEL(IP11_11_8,	AUDIO_CLKA_B,		SEL_ADG_1),
 	PINMUX_IPSR_MSEL(IP11_11_8,	SCL2_A,			SEL_I2C2_0),
 	PINMUX_IPSR_MSEL(IP11_11_8,	STP_IVCXO27_1_C,	SEL_SSP1_1_2),
 	PINMUX_IPSR_MSEL(IP11_11_8,	RIF0_SYNC_B,		SEL_DRIF0_1),
-	PINMUX_IPSR_DATA(IP11_11_8,	ADICHS1),
+	PINMUX_IPSR_GPSR(IP11_11_8,	ADICHS1),
 
 	PINMUX_IPSR_MSEL(IP11_15_12,	RX1_A,			SEL_SCIF1_0),
 	PINMUX_IPSR_MSEL(IP11_15_12,	HRX1_A,			SEL_HSCIF1_0),
@@ -1102,29 +1101,29 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP11_19_16,	STP_ISEN_0_C,		SEL_SSP1_0_2),
 	PINMUX_IPSR_MSEL(IP11_19_16,	RIF1_D0_C,		SEL_DRIF1_2),
 
-	PINMUX_IPSR_DATA(IP11_23_20,	CTS1_N),
+	PINMUX_IPSR_GPSR(IP11_23_20,	CTS1_N),
 	PINMUX_IPSR_MSEL(IP11_23_20,	HCTS1_N_A,		SEL_HSCIF1_0),
 	PINMUX_IPSR_MSEL(IP11_23_20,	MSIOF1_RXD_B,		SEL_MSIOF1_1),
 	PINMUX_IPSR_MSEL(IP11_23_20,	TS_SDEN1_C,		SEL_TSIF1_2),
 	PINMUX_IPSR_MSEL(IP11_23_20,	STP_ISEN_1_C,		SEL_SSP1_1_2),
 	PINMUX_IPSR_MSEL(IP11_23_20,	RIF1_D0_B,		SEL_DRIF1_1),
-	PINMUX_IPSR_DATA(IP11_23_20,	ADIDATA),
+	PINMUX_IPSR_GPSR(IP11_23_20,	ADIDATA),
 
-	PINMUX_IPSR_DATA(IP11_27_24,	RTS1_N_TANS),
+	PINMUX_IPSR_GPSR(IP11_27_24,	RTS1_N_TANS),
 	PINMUX_IPSR_MSEL(IP11_27_24,	HRTS1_N_A,		SEL_HSCIF1_0),
 	PINMUX_IPSR_MSEL(IP11_27_24,	MSIOF1_TXD_B,		SEL_MSIOF1_1),
 	PINMUX_IPSR_MSEL(IP11_27_24,	TS_SDAT1_C,		SEL_TSIF1_2),
 	PINMUX_IPSR_MSEL(IP11_27_24,	STP_ISD_1_C,		SEL_SSP1_1_2),
 	PINMUX_IPSR_MSEL(IP11_27_24,	RIF1_D1_B,		SEL_DRIF1_1),
-	PINMUX_IPSR_DATA(IP11_27_24,	ADICHS0),
+	PINMUX_IPSR_GPSR(IP11_27_24,	ADICHS0),
 
-	PINMUX_IPSR_DATA(IP11_31_28,	SCK2),
+	PINMUX_IPSR_GPSR(IP11_31_28,	SCK2),
 	PINMUX_IPSR_MSEL(IP11_31_28,	SCIF_CLK_B,		SEL_SCIF1_1),
 	PINMUX_IPSR_MSEL(IP11_31_28,	MSIOF1_SCK_B,		SEL_MSIOF1_1),
 	PINMUX_IPSR_MSEL(IP11_31_28,	TS_SCK1_C,		SEL_TSIF1_2),
 	PINMUX_IPSR_MSEL(IP11_31_28,	STP_ISCLK_1_C,		SEL_SSP1_1_2),
 	PINMUX_IPSR_MSEL(IP11_31_28,	RIF1_CLK_B,		SEL_DRIF1_1),
-	PINMUX_IPSR_DATA(IP11_31_28,	ADICLK),
+	PINMUX_IPSR_GPSR(IP11_31_28,	ADICLK),
 
 	/* IPSR12 */
 	PINMUX_IPSR_MSEL(IP12_3_0,	TX2_A,			SEL_SCIF2_0),
@@ -1141,7 +1140,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP12_7_4,	RIF1_SYNC_C,		SEL_DRIF1_2),
 	PINMUX_IPSR_MSEL(IP12_7_4,	FSO_CFE_1_B,		SEL_FSO_1),
 
-	PINMUX_IPSR_DATA(IP12_11_8,	HSCK0),
+	PINMUX_IPSR_GPSR(IP12_11_8,	HSCK0),
 	PINMUX_IPSR_MSEL(IP12_11_8,	MSIOF1_SCK_D,		SEL_MSIOF1_3),
 	PINMUX_IPSR_MSEL(IP12_11_8,	AUDIO_CLKB_A,		SEL_ADG_0),
 	PINMUX_IPSR_MSEL(IP12_11_8,	SSI_SDATA1_B,		SEL_SSI_1),
@@ -1149,21 +1148,21 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP12_11_8,	STP_ISCLK_0_D,		SEL_SSP1_0_3),
 	PINMUX_IPSR_MSEL(IP12_11_8,	RIF0_CLK_C,		SEL_DRIF0_2),
 
-	PINMUX_IPSR_DATA(IP12_15_12,	HRX0),
+	PINMUX_IPSR_GPSR(IP12_15_12,	HRX0),
 	PINMUX_IPSR_MSEL(IP12_15_12,	MSIOF1_RXD_D,		SEL_MSIOF1_3),
 	PINMUX_IPSR_MSEL(IP12_15_12,	SSI_SDATA2_B,		SEL_SSI_1),
 	PINMUX_IPSR_MSEL(IP12_15_12,	TS_SDEN0_D,		SEL_TSIF0_3),
 	PINMUX_IPSR_MSEL(IP12_15_12,	STP_ISEN_0_D,		SEL_SSP1_0_3),
 	PINMUX_IPSR_MSEL(IP12_15_12,	RIF0_D0_C,		SEL_DRIF0_2),
 
-	PINMUX_IPSR_DATA(IP12_19_16,	HTX0),
+	PINMUX_IPSR_GPSR(IP12_19_16,	HTX0),
 	PINMUX_IPSR_MSEL(IP12_19_16,	MSIOF1_TXD_D,		SEL_MSIOF1_3),
 	PINMUX_IPSR_MSEL(IP12_19_16,	SSI_SDATA9_B,		SEL_SSI_1),
 	PINMUX_IPSR_MSEL(IP12_19_16,	TS_SDAT0_D,		SEL_TSIF0_3),
 	PINMUX_IPSR_MSEL(IP12_19_16,	STP_ISD_0_D,		SEL_SSP1_0_3),
 	PINMUX_IPSR_MSEL(IP12_19_16,	RIF0_D1_C,		SEL_DRIF0_2),
 
-	PINMUX_IPSR_DATA(IP12_23_20,	HCTS0_N),
+	PINMUX_IPSR_GPSR(IP12_23_20,	HCTS0_N),
 	PINMUX_IPSR_MSEL(IP12_23_20,	RX2_B,			SEL_SCIF2_1),
 	PINMUX_IPSR_MSEL(IP12_23_20,	MSIOF1_SYNC_D,		SEL_MSIOF1_3),
 	PINMUX_IPSR_MSEL(IP12_23_20,	SSI_SCK9_A,		SEL_SSI_0),
@@ -1172,7 +1171,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP12_23_20,	RIF0_SYNC_C,		SEL_DRIF0_2),
 	PINMUX_IPSR_MSEL(IP12_23_20,	AUDIO_CLKOUT1_A,	SEL_ADG_0),
 
-	PINMUX_IPSR_DATA(IP12_27_24,	HRTS0_N),
+	PINMUX_IPSR_GPSR(IP12_27_24,	HRTS0_N),
 	PINMUX_IPSR_MSEL(IP12_27_24,	TX2_B,			SEL_SCIF2_1),
 	PINMUX_IPSR_MSEL(IP12_27_24,	MSIOF1_SS1_D,		SEL_MSIOF1_3),
 	PINMUX_IPSR_MSEL(IP12_27_24,	SSI_WS9_A,		SEL_SSI_0),
@@ -1180,20 +1179,20 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP12_27_24,	BPFCLK_A,		SEL_FM_0),
 	PINMUX_IPSR_MSEL(IP12_27_24,	AUDIO_CLKOUT2_A,	SEL_ADG_0),
 
-	PINMUX_IPSR_DATA(IP12_31_28,	MSIOF0_SYNC),
+	PINMUX_IPSR_GPSR(IP12_31_28,	MSIOF0_SYNC),
 	PINMUX_IPSR_MSEL(IP12_31_28,	AUDIO_CLKOUT_A,		SEL_ADG_0),
 
 	/* IPSR13 */
-	PINMUX_IPSR_DATA(IP13_3_0,	MSIOF0_SS1),
-	PINMUX_IPSR_DATA(IP13_3_0,	RX5),
+	PINMUX_IPSR_GPSR(IP13_3_0,	MSIOF0_SS1),
+	PINMUX_IPSR_GPSR(IP13_3_0,	RX5),
 	PINMUX_IPSR_MSEL(IP13_3_0,	AUDIO_CLKA_C,		SEL_ADG_2),
 	PINMUX_IPSR_MSEL(IP13_3_0,	SSI_SCK2_A,		SEL_SSI_0),
 	PINMUX_IPSR_MSEL(IP13_3_0,	STP_IVCXO27_0_C,	SEL_SSP1_0_2),
 	PINMUX_IPSR_MSEL(IP13_3_0,	AUDIO_CLKOUT3_A,	SEL_ADG_0),
 	PINMUX_IPSR_MSEL(IP13_3_0,	TCLK1_B,		SEL_TIMER_TMU_1),
 
-	PINMUX_IPSR_DATA(IP13_7_4,	MSIOF0_SS2),
-	PINMUX_IPSR_DATA(IP13_7_4,	TX5),
+	PINMUX_IPSR_GPSR(IP13_7_4,	MSIOF0_SS2),
+	PINMUX_IPSR_GPSR(IP13_7_4,	TX5),
 	PINMUX_IPSR_MSEL(IP13_7_4,	MSIOF1_SS2_D,		SEL_MSIOF1_3),
 	PINMUX_IPSR_MSEL(IP13_7_4,	AUDIO_CLKC_A,		SEL_ADG_0),
 	PINMUX_IPSR_MSEL(IP13_7_4,	SSI_WS2_A,		SEL_SSI_0),
@@ -1201,26 +1200,26 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP13_7_4,	AUDIO_CLKOUT_D,		SEL_ADG_3),
 	PINMUX_IPSR_MSEL(IP13_7_4,	SPEEDIN_B,		SEL_SPEED_PULSE_1),
 
-	PINMUX_IPSR_DATA(IP13_11_8,	MLB_CLK),
+	PINMUX_IPSR_GPSR(IP13_11_8,	MLB_CLK),
 	PINMUX_IPSR_MSEL(IP13_11_8,	MSIOF1_SCK_F,		SEL_MSIOF1_5),
 	PINMUX_IPSR_MSEL(IP13_11_8,	SCL1_B,			SEL_I2C1_1),
 
-	PINMUX_IPSR_DATA(IP13_15_12,	MLB_SIG),
+	PINMUX_IPSR_GPSR(IP13_15_12,	MLB_SIG),
 	PINMUX_IPSR_MSEL(IP13_15_12,	RX1_B,			SEL_SCIF1_1),
 	PINMUX_IPSR_MSEL(IP13_15_12,	MSIOF1_SYNC_F,		SEL_MSIOF1_5),
 	PINMUX_IPSR_MSEL(IP13_15_12,	SDA1_B,			SEL_I2C1_1),
 
-	PINMUX_IPSR_DATA(IP13_19_16,	MLB_DAT),
+	PINMUX_IPSR_GPSR(IP13_19_16,	MLB_DAT),
 	PINMUX_IPSR_MSEL(IP13_19_16,	TX1_B,			SEL_SCIF1_1),
 	PINMUX_IPSR_MSEL(IP13_19_16,	MSIOF1_RXD_F,		SEL_MSIOF1_5),
 
-	PINMUX_IPSR_DATA(IP13_23_20,	SSI_SCK0129),
+	PINMUX_IPSR_GPSR(IP13_23_20,	SSI_SCK01239),
 	PINMUX_IPSR_MSEL(IP13_23_20,	MSIOF1_TXD_F,		SEL_MSIOF1_5),
 
-	PINMUX_IPSR_DATA(IP13_27_24,	SSI_WS0129),
+	PINMUX_IPSR_GPSR(IP13_27_24,	SSI_WS01239),
 	PINMUX_IPSR_MSEL(IP13_27_24,	MSIOF1_SS1_F,		SEL_MSIOF1_5),
 
-	PINMUX_IPSR_DATA(IP13_31_28,	SSI_SDATA0),
+	PINMUX_IPSR_GPSR(IP13_31_28,	SSI_SDATA0),
 	PINMUX_IPSR_MSEL(IP13_31_28,	MSIOF1_SS2_F,		SEL_MSIOF1_5),
 
 	/* IPSR14 */
@@ -1229,16 +1228,16 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP14_7_4,	SSI_SDATA2_A,		SEL_SSI_0),
 	PINMUX_IPSR_MSEL(IP14_7_4,	SSI_SCK1_B,		SEL_SSI_1),
 
-	PINMUX_IPSR_DATA(IP14_11_8,	SSI_SCK34),
+	PINMUX_IPSR_GPSR(IP14_11_8,	SSI_SCK34),
 	PINMUX_IPSR_MSEL(IP14_11_8,	MSIOF1_SS1_A,		SEL_MSIOF1_0),
 	PINMUX_IPSR_MSEL(IP14_11_8,	STP_OPWM_0_A,		SEL_SSP1_0_0),
 
-	PINMUX_IPSR_DATA(IP14_15_12,	SSI_WS34),
+	PINMUX_IPSR_GPSR(IP14_15_12,	SSI_WS34),
 	PINMUX_IPSR_MSEL(IP14_15_12,	HCTS2_N_A,		SEL_HSCIF2_0),
 	PINMUX_IPSR_MSEL(IP14_15_12,	MSIOF1_SS2_A,		SEL_MSIOF1_0),
 	PINMUX_IPSR_MSEL(IP14_15_12,	STP_IVCXO27_0_A,	SEL_SSP1_0_0),
 
-	PINMUX_IPSR_DATA(IP14_19_16,	SSI_SDATA3),
+	PINMUX_IPSR_GPSR(IP14_19_16,	SSI_SDATA3),
 	PINMUX_IPSR_MSEL(IP14_19_16,	HRTS2_N_A,		SEL_HSCIF2_0),
 	PINMUX_IPSR_MSEL(IP14_19_16,	MSIOF1_TXD_A,		SEL_MSIOF1_0),
 	PINMUX_IPSR_MSEL(IP14_19_16,	TS_SCK0_A,		SEL_TSIF0_0),
@@ -1246,7 +1245,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP14_19_16,	RIF0_D1_A,		SEL_DRIF0_0),
 	PINMUX_IPSR_MSEL(IP14_19_16,	RIF2_D0_A,		SEL_DRIF2_0),
 
-	PINMUX_IPSR_DATA(IP14_23_20,	SSI_SCK4),
+	PINMUX_IPSR_GPSR(IP14_23_20,	SSI_SCK4),
 	PINMUX_IPSR_MSEL(IP14_23_20,	HRX2_A,			SEL_HSCIF2_0),
 	PINMUX_IPSR_MSEL(IP14_23_20,	MSIOF1_SCK_A,		SEL_MSIOF1_0),
 	PINMUX_IPSR_MSEL(IP14_23_20,	TS_SDAT0_A,		SEL_TSIF0_0),
@@ -1254,7 +1253,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP14_23_20,	RIF0_CLK_A,		SEL_DRIF0_0),
 	PINMUX_IPSR_MSEL(IP14_23_20,	RIF2_CLK_A,		SEL_DRIF2_0),
 
-	PINMUX_IPSR_DATA(IP14_27_24,	SSI_WS4),
+	PINMUX_IPSR_GPSR(IP14_27_24,	SSI_WS4),
 	PINMUX_IPSR_MSEL(IP14_27_24,	HTX2_A,			SEL_HSCIF2_0),
 	PINMUX_IPSR_MSEL(IP14_27_24,	MSIOF1_SYNC_A,		SEL_MSIOF1_0),
 	PINMUX_IPSR_MSEL(IP14_27_24,	TS_SDEN0_A,		SEL_TSIF0_0),
@@ -1262,7 +1261,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP14_27_24,	RIF0_SYNC_A,		SEL_DRIF0_0),
 	PINMUX_IPSR_MSEL(IP14_27_24,	RIF2_SYNC_A,		SEL_DRIF2_0),
 
-	PINMUX_IPSR_DATA(IP14_31_28,	SSI_SDATA4),
+	PINMUX_IPSR_GPSR(IP14_31_28,	SSI_SDATA4),
 	PINMUX_IPSR_MSEL(IP14_31_28,	HSCK2_A,		SEL_HSCIF2_0),
 	PINMUX_IPSR_MSEL(IP14_31_28,	MSIOF1_RXD_A,		SEL_MSIOF1_0),
 	PINMUX_IPSR_MSEL(IP14_31_28,	TS_SPSYNC0_A,		SEL_TSIF0_0),
@@ -1271,19 +1270,19 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP14_31_28,	RIF2_D1_A,		SEL_DRIF2_0),
 
 	/* IPSR15 */
-	PINMUX_IPSR_DATA(IP15_3_0,	SSI_SCK6),
-	PINMUX_IPSR_DATA(IP15_3_0,	USB2_PWEN),
+	PINMUX_IPSR_GPSR(IP15_3_0,	SSI_SCK6),
+	PINMUX_IPSR_GPSR(IP15_3_0,	USB2_PWEN),
 	PINMUX_IPSR_MSEL(IP15_3_0,	SIM0_RST_D,		SEL_SIMCARD_3),
 
-	PINMUX_IPSR_DATA(IP15_7_4,	SSI_WS6),
-	PINMUX_IPSR_DATA(IP15_7_4,	USB2_OVC),
+	PINMUX_IPSR_GPSR(IP15_7_4,	SSI_WS6),
+	PINMUX_IPSR_GPSR(IP15_7_4,	USB2_OVC),
 	PINMUX_IPSR_MSEL(IP15_7_4,	SIM0_D_D,		SEL_SIMCARD_3),
 
-	PINMUX_IPSR_DATA(IP15_11_8,	SSI_SDATA6),
+	PINMUX_IPSR_GPSR(IP15_11_8,	SSI_SDATA6),
 	PINMUX_IPSR_MSEL(IP15_11_8,	SIM0_CLK_D,		SEL_SIMCARD_3),
 	PINMUX_IPSR_MSEL(IP15_11_8,	SATA_DEVSLP_A,		SEL_SATA_0),
 
-	PINMUX_IPSR_DATA(IP15_15_12,	SSI_SCK78),
+	PINMUX_IPSR_GPSR(IP15_15_12,	SSI_SCK78),
 	PINMUX_IPSR_MSEL(IP15_15_12,	HRX2_B,			SEL_HSCIF2_1),
 	PINMUX_IPSR_MSEL(IP15_15_12,	MSIOF1_SCK_C,		SEL_MSIOF1_2),
 	PINMUX_IPSR_MSEL(IP15_15_12,	TS_SCK1_A,		SEL_TSIF1_0),
@@ -1291,7 +1290,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP15_15_12,	RIF1_CLK_A,		SEL_DRIF1_0),
 	PINMUX_IPSR_MSEL(IP15_15_12,	RIF3_CLK_A,		SEL_DRIF3_0),
 
-	PINMUX_IPSR_DATA(IP15_19_16,	SSI_WS78),
+	PINMUX_IPSR_GPSR(IP15_19_16,	SSI_WS78),
 	PINMUX_IPSR_MSEL(IP15_19_16,	HTX2_B,			SEL_HSCIF2_1),
 	PINMUX_IPSR_MSEL(IP15_19_16,	MSIOF1_SYNC_C,		SEL_MSIOF1_2),
 	PINMUX_IPSR_MSEL(IP15_19_16,	TS_SDAT1_A,		SEL_TSIF1_0),
@@ -1299,7 +1298,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP15_19_16,	RIF1_SYNC_A,		SEL_DRIF1_0),
 	PINMUX_IPSR_MSEL(IP15_19_16,	RIF3_SYNC_A,		SEL_DRIF3_0),
 
-	PINMUX_IPSR_DATA(IP15_23_20,	SSI_SDATA7),
+	PINMUX_IPSR_GPSR(IP15_23_20,	SSI_SDATA7),
 	PINMUX_IPSR_MSEL(IP15_23_20,	HCTS2_N_B,		SEL_HSCIF2_1),
 	PINMUX_IPSR_MSEL(IP15_23_20,	MSIOF1_RXD_C,		SEL_MSIOF1_2),
 	PINMUX_IPSR_MSEL(IP15_23_20,	TS_SDEN1_A,		SEL_TSIF1_0),
@@ -1308,7 +1307,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP15_23_20,	RIF3_D0_A,		SEL_DRIF3_0),
 	PINMUX_IPSR_MSEL(IP15_23_20,	TCLK2_A,		SEL_TIMER_TMU_0),
 
-	PINMUX_IPSR_DATA(IP15_27_24,	SSI_SDATA8),
+	PINMUX_IPSR_GPSR(IP15_27_24,	SSI_SDATA8),
 	PINMUX_IPSR_MSEL(IP15_27_24,	HRTS2_N_B,		SEL_HSCIF2_1),
 	PINMUX_IPSR_MSEL(IP15_27_24,	MSIOF1_TXD_C,		SEL_MSIOF1_2),
 	PINMUX_IPSR_MSEL(IP15_27_24,	TS_SPSYNC1_A,		SEL_TSIF1_0),
@@ -1321,13 +1320,13 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP15_31_28,	MSIOF1_SS1_C,		SEL_MSIOF1_2),
 	PINMUX_IPSR_MSEL(IP15_31_28,	HSCK1_A,		SEL_HSCIF1_0),
 	PINMUX_IPSR_MSEL(IP15_31_28,	SSI_WS1_B,		SEL_SSI_1),
-	PINMUX_IPSR_DATA(IP15_31_28,	SCK1),
+	PINMUX_IPSR_GPSR(IP15_31_28,	SCK1),
 	PINMUX_IPSR_MSEL(IP15_31_28,	STP_IVCXO27_1_A,	SEL_SSP1_1_0),
-	PINMUX_IPSR_DATA(IP15_31_28,	SCK5),
+	PINMUX_IPSR_GPSR(IP15_31_28,	SCK5),
 
 	/* IPSR16 */
 	PINMUX_IPSR_MSEL(IP16_3_0,	AUDIO_CLKA_A,		SEL_ADG_0),
-	PINMUX_IPSR_DATA(IP16_3_0,	CC5_OSCOUT),
+	PINMUX_IPSR_GPSR(IP16_3_0,	CC5_OSCOUT),
 
 	PINMUX_IPSR_MSEL(IP16_7_4,	AUDIO_CLKB_B,		SEL_ADG_1),
 	PINMUX_IPSR_MSEL(IP16_7_4,	SCIF_CLK_A,		SEL_SCIF1_0),
@@ -1335,20 +1334,20 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP16_7_4,	REMOCON_A,		SEL_REMOCON_0),
 	PINMUX_IPSR_MSEL(IP16_7_4,	TCLK1_A,		SEL_TIMER_TMU_0),
 
-	PINMUX_IPSR_DATA(IP16_11_8,	USB0_PWEN),
+	PINMUX_IPSR_GPSR(IP16_11_8,	USB0_PWEN),
 	PINMUX_IPSR_MSEL(IP16_11_8,	SIM0_RST_C,		SEL_SIMCARD_2),
 	PINMUX_IPSR_MSEL(IP16_11_8,	TS_SCK1_D,		SEL_TSIF1_3),
 	PINMUX_IPSR_MSEL(IP16_11_8,	STP_ISCLK_1_D,		SEL_SSP1_1_3),
 	PINMUX_IPSR_MSEL(IP16_11_8,	BPFCLK_B,		SEL_FM_1),
 	PINMUX_IPSR_MSEL(IP16_11_8,	RIF3_CLK_B,		SEL_DRIF3_1),
 
-	PINMUX_IPSR_DATA(IP16_15_12,	USB0_OVC),
+	PINMUX_IPSR_GPSR(IP16_15_12,	USB0_OVC),
 	PINMUX_IPSR_MSEL(IP16_11_8,	SIM0_D_C,		SEL_SIMCARD_2),
 	PINMUX_IPSR_MSEL(IP16_11_8,	TS_SDAT1_D,		SEL_TSIF1_3),
 	PINMUX_IPSR_MSEL(IP16_11_8,	STP_ISD_1_D,		SEL_SSP1_1_3),
 	PINMUX_IPSR_MSEL(IP16_11_8,	RIF3_SYNC_B,		SEL_DRIF3_1),
 
-	PINMUX_IPSR_DATA(IP16_19_16,	USB1_PWEN),
+	PINMUX_IPSR_GPSR(IP16_19_16,	USB1_PWEN),
 	PINMUX_IPSR_MSEL(IP16_19_16,	SIM0_CLK_C,		SEL_SIMCARD_2),
 	PINMUX_IPSR_MSEL(IP16_19_16,	SSI_SCK1_A,		SEL_SSI_0),
 	PINMUX_IPSR_MSEL(IP16_19_16,	TS_SCK0_E,		SEL_TSIF0_4),
@@ -1357,7 +1356,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP16_19_16,	RIF2_CLK_B,		SEL_DRIF2_1),
 	PINMUX_IPSR_MSEL(IP16_19_16,	SPEEDIN_A,		SEL_SPEED_PULSE_0),
 
-	PINMUX_IPSR_DATA(IP16_23_20,	USB1_OVC),
+	PINMUX_IPSR_GPSR(IP16_23_20,	USB1_OVC),
 	PINMUX_IPSR_MSEL(IP16_23_20,	MSIOF1_SS2_C,		SEL_MSIOF1_2),
 	PINMUX_IPSR_MSEL(IP16_23_20,	SSI_WS1_A,		SEL_SSI_0),
 	PINMUX_IPSR_MSEL(IP16_23_20,	TS_SDAT0_E,		SEL_TSIF0_4),
@@ -1366,7 +1365,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP16_23_20,	RIF2_SYNC_B,		SEL_DRIF2_1),
 	PINMUX_IPSR_MSEL(IP16_23_20,	REMOCON_B,		SEL_REMOCON_1),
 
-	PINMUX_IPSR_DATA(IP16_27_24,	USB30_PWEN),
+	PINMUX_IPSR_GPSR(IP16_27_24,	USB30_PWEN),
 	PINMUX_IPSR_MSEL(IP16_27_24,	AUDIO_CLKOUT_B,		SEL_ADG_1),
 	PINMUX_IPSR_MSEL(IP16_27_24,	SSI_SCK2_B,		SEL_SSI_1),
 	PINMUX_IPSR_MSEL(IP16_27_24,	TS_SDEN1_D,		SEL_TSIF1_3),
@@ -1374,9 +1373,9 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP16_27_24,	STP_OPWM_0_E,		SEL_SSP1_0_4),
 	PINMUX_IPSR_MSEL(IP16_27_24,	RIF3_D0_B,		SEL_DRIF3_1),
 	PINMUX_IPSR_MSEL(IP16_27_24,	TCLK2_B,		SEL_TIMER_TMU_1),
-	PINMUX_IPSR_DATA(IP16_27_24,	TPU0TO0),
+	PINMUX_IPSR_GPSR(IP16_27_24,	TPU0TO0),
 
-	PINMUX_IPSR_DATA(IP16_31_28,	USB30_OVC),
+	PINMUX_IPSR_GPSR(IP16_31_28,	USB30_OVC),
 	PINMUX_IPSR_MSEL(IP16_31_28,	AUDIO_CLKOUT1_B,	SEL_ADG_1),
 	PINMUX_IPSR_MSEL(IP16_31_28,	SSI_WS2_B,		SEL_SSI_1),
 	PINMUX_IPSR_MSEL(IP16_31_28,	TS_SPSYNC1_D,		SEL_TSIF1_3),
@@ -1384,24 +1383,24 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP16_31_28,	STP_IVCXO27_0_E,	SEL_SSP1_0_4),
 	PINMUX_IPSR_MSEL(IP16_31_28,	RIF3_D1_B,		SEL_DRIF3_1),
 	PINMUX_IPSR_MSEL(IP16_31_28,	FSO_TOE_B,		SEL_FSO_1),
-	PINMUX_IPSR_DATA(IP16_31_28,	TPU0TO1),
+	PINMUX_IPSR_GPSR(IP16_31_28,	TPU0TO1),
 
 	/* IPSR17 */
-	PINMUX_IPSR_DATA(IP17_3_0,	USB31_PWEN),
+	PINMUX_IPSR_GPSR(IP17_3_0,	USB31_PWEN),
 	PINMUX_IPSR_MSEL(IP17_3_0,	AUDIO_CLKOUT2_B,	SEL_ADG_1),
 	PINMUX_IPSR_MSEL(IP17_3_0,	SSI_SCK9_B,		SEL_SSI_1),
 	PINMUX_IPSR_MSEL(IP17_3_0,	TS_SDEN0_E,		SEL_TSIF0_4),
 	PINMUX_IPSR_MSEL(IP17_3_0,	STP_ISEN_0_E,		SEL_SSP1_0_4),
 	PINMUX_IPSR_MSEL(IP17_3_0,	RIF2_D0_B,		SEL_DRIF2_1),
-	PINMUX_IPSR_DATA(IP17_3_0,	TPU0TO2),
+	PINMUX_IPSR_GPSR(IP17_3_0,	TPU0TO2),
 
-	PINMUX_IPSR_DATA(IP17_7_4,	USB31_OVC),
+	PINMUX_IPSR_GPSR(IP17_7_4,	USB31_OVC),
 	PINMUX_IPSR_MSEL(IP17_7_4,	AUDIO_CLKOUT3_B,	SEL_ADG_1),
 	PINMUX_IPSR_MSEL(IP17_7_4,	SSI_WS9_B,		SEL_SSI_1),
 	PINMUX_IPSR_MSEL(IP17_7_4,	TS_SPSYNC0_E,		SEL_TSIF0_4),
 	PINMUX_IPSR_MSEL(IP17_7_4,	STP_ISSYNC_0_E,		SEL_SSP1_0_4),
 	PINMUX_IPSR_MSEL(IP17_7_4,	RIF2_D1_B,		SEL_DRIF2_1),
-	PINMUX_IPSR_DATA(IP17_7_4,	TPU0TO3),
+	PINMUX_IPSR_GPSR(IP17_7_4,	TPU0TO3),
 
 	/* I2C */
 	PINMUX_IPSR_NOGP(0,		I2C_SEL_0_1),
@@ -1600,6 +1599,61 @@ static const unsigned int avb_avtp_capture_b_mux[] = {
 	AVB_AVTP_CAPTURE_B_MARK,
 };
 
+/* - CAN ------------------------------------------------------------------ */
+static const unsigned int can0_data_a_pins[] = {
+	/* TX, RX */
+	RCAR_GP_PIN(1, 23),	RCAR_GP_PIN(1, 24),
+};
+static const unsigned int can0_data_a_mux[] = {
+	CAN0_TX_A_MARK,		CAN0_RX_A_MARK,
+};
+static const unsigned int can0_data_b_pins[] = {
+	/* TX, RX */
+	RCAR_GP_PIN(2, 0),	RCAR_GP_PIN(2, 1),
+};
+static const unsigned int can0_data_b_mux[] = {
+	CAN0_TX_B_MARK,		CAN0_RX_B_MARK,
+};
+static const unsigned int can1_data_pins[] = {
+	/* TX, RX */
+	RCAR_GP_PIN(1, 22),	RCAR_GP_PIN(1, 26),
+};
+static const unsigned int can1_data_mux[] = {
+	CAN1_TX_MARK,		CAN1_RX_MARK,
+};
+
+/* - CAN Clock -------------------------------------------------------------- */
+static const unsigned int can_clk_pins[] = {
+	/* CLK */
+	RCAR_GP_PIN(1, 25),
+};
+static const unsigned int can_clk_mux[] = {
+	CAN_CLK_MARK,
+};
+
+/* - CAN FD --------------------------------------------------------------- */
+static const unsigned int canfd0_data_a_pins[] = {
+	/* TX, RX */
+	RCAR_GP_PIN(1, 23),     RCAR_GP_PIN(1, 24),
+};
+static const unsigned int canfd0_data_a_mux[] = {
+	CANFD0_TX_A_MARK,       CANFD0_RX_A_MARK,
+};
+static const unsigned int canfd0_data_b_pins[] = {
+	/* TX, RX */
+	RCAR_GP_PIN(2, 0),      RCAR_GP_PIN(2, 1),
+};
+static const unsigned int canfd0_data_b_mux[] = {
+	CANFD0_TX_B_MARK,       CANFD0_RX_B_MARK,
+};
+static const unsigned int canfd1_data_pins[] = {
+	/* TX, RX */
+	RCAR_GP_PIN(1, 22),     RCAR_GP_PIN(1, 26),
+};
+static const unsigned int canfd1_data_mux[] = {
+	CANFD1_TX_MARK,         CANFD1_RX_MARK,
+};
+
 /* - HSCIF0 ----------------------------------------------------------------- */
 static const unsigned int hscif0_data_pins[] = {
 	/* RX, TX */
@@ -1836,6 +1890,50 @@ static const unsigned int i2c6_c_mux[] = {
 	SDA6_C_MARK, SCL6_C_MARK,
 };
 
+/* - INTC-EX ---------------------------------------------------------------- */
+static const unsigned int intc_ex_irq0_pins[] = {
+	/* IRQ0 */
+	RCAR_GP_PIN(2, 0),
+};
+static const unsigned int intc_ex_irq0_mux[] = {
+	IRQ0_MARK,
+};
+static const unsigned int intc_ex_irq1_pins[] = {
+	/* IRQ1 */
+	RCAR_GP_PIN(2, 1),
+};
+static const unsigned int intc_ex_irq1_mux[] = {
+	IRQ1_MARK,
+};
+static const unsigned int intc_ex_irq2_pins[] = {
+	/* IRQ2 */
+	RCAR_GP_PIN(2, 2),
+};
+static const unsigned int intc_ex_irq2_mux[] = {
+	IRQ2_MARK,
+};
+static const unsigned int intc_ex_irq3_pins[] = {
+	/* IRQ3 */
+	RCAR_GP_PIN(2, 3),
+};
+static const unsigned int intc_ex_irq3_mux[] = {
+	IRQ3_MARK,
+};
+static const unsigned int intc_ex_irq4_pins[] = {
+	/* IRQ4 */
+	RCAR_GP_PIN(2, 4),
+};
+static const unsigned int intc_ex_irq4_mux[] = {
+	IRQ4_MARK,
+};
+static const unsigned int intc_ex_irq5_pins[] = {
+	/* IRQ5 */
+	RCAR_GP_PIN(2, 5),
+};
+static const unsigned int intc_ex_irq5_mux[] = {
+	IRQ5_MARK,
+};
+
 /* - MSIOF0 ----------------------------------------------------------------- */
 static const unsigned int msiof0_clk_pins[] = {
 	/* SCK */
@@ -2492,6 +2590,105 @@ static const unsigned int msiof3_rxd_d_mux[] = {
 	MSIOF3_RXD_D_MARK,
 };
 
+/* - PWM0 --------------------------------------------------------------------*/
+static const unsigned int pwm0_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(2, 6),
+};
+static const unsigned int pwm0_mux[] = {
+	PWM0_MARK,
+};
+/* - PWM1 --------------------------------------------------------------------*/
+static const unsigned int pwm1_a_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(2, 7),
+};
+static const unsigned int pwm1_a_mux[] = {
+	PWM1_A_MARK,
+};
+static const unsigned int pwm1_b_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(1, 8),
+};
+static const unsigned int pwm1_b_mux[] = {
+	PWM1_B_MARK,
+};
+/* - PWM2 --------------------------------------------------------------------*/
+static const unsigned int pwm2_a_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(2, 8),
+};
+static const unsigned int pwm2_a_mux[] = {
+	PWM2_A_MARK,
+};
+static const unsigned int pwm2_b_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(1, 11),
+};
+static const unsigned int pwm2_b_mux[] = {
+	PWM2_B_MARK,
+};
+/* - PWM3 --------------------------------------------------------------------*/
+static const unsigned int pwm3_a_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(1, 0),
+};
+static const unsigned int pwm3_a_mux[] = {
+	PWM3_A_MARK,
+};
+static const unsigned int pwm3_b_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(2, 2),
+};
+static const unsigned int pwm3_b_mux[] = {
+	PWM3_B_MARK,
+};
+/* - PWM4 --------------------------------------------------------------------*/
+static const unsigned int pwm4_a_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(1, 1),
+};
+static const unsigned int pwm4_a_mux[] = {
+	PWM4_A_MARK,
+};
+static const unsigned int pwm4_b_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(2, 3),
+};
+static const unsigned int pwm4_b_mux[] = {
+	PWM4_B_MARK,
+};
+/* - PWM5 --------------------------------------------------------------------*/
+static const unsigned int pwm5_a_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(1, 2),
+};
+static const unsigned int pwm5_a_mux[] = {
+	PWM5_A_MARK,
+};
+static const unsigned int pwm5_b_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(2, 4),
+};
+static const unsigned int pwm5_b_mux[] = {
+	PWM5_B_MARK,
+};
+/* - PWM6 --------------------------------------------------------------------*/
+static const unsigned int pwm6_a_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(1, 3),
+};
+static const unsigned int pwm6_a_mux[] = {
+	PWM6_A_MARK,
+};
+static const unsigned int pwm6_b_pins[] = {
+	/* PWM */
+	RCAR_GP_PIN(2, 5),
+};
+static const unsigned int pwm6_b_mux[] = {
+	PWM6_B_MARK,
+};
+
 /* - SATA --------------------------------------------------------------------*/
 static const unsigned int sata0_devslp_a_pins[] = {
 	/* DEVSLP */
@@ -2926,7 +3123,7 @@ static const unsigned int ssi01239_ctrl_pins[] = {
 	RCAR_GP_PIN(6, 0), RCAR_GP_PIN(6, 1),
 };
 static const unsigned int ssi01239_ctrl_mux[] = {
-	SSI_SCK0129_MARK, SSI_WS0129_MARK,
+	SSI_SCK01239_MARK, SSI_WS01239_MARK,
 };
 static const unsigned int ssi1_data_a_pins[] = {
 	/* SDATA */
@@ -3090,6 +3287,31 @@ static const unsigned int ssi9_ctrl_b_mux[] = {
 	SSI_SCK9_B_MARK, SSI_WS9_B_MARK,
 };
 
+/* - USB0 ------------------------------------------------------------------- */
+static const unsigned int usb0_pins[] = {
+	/* PWEN, OVC */
+	RCAR_GP_PIN(6, 24), RCAR_GP_PIN(6, 25),
+};
+static const unsigned int usb0_mux[] = {
+	USB0_PWEN_MARK, USB0_OVC_MARK,
+};
+/* - USB1 ------------------------------------------------------------------- */
+static const unsigned int usb1_pins[] = {
+	/* PWEN, OVC */
+	RCAR_GP_PIN(6, 26), RCAR_GP_PIN(6, 27),
+};
+static const unsigned int usb1_mux[] = {
+	USB1_PWEN_MARK, USB1_OVC_MARK,
+};
+/* - USB2 ------------------------------------------------------------------- */
+static const unsigned int usb2_pins[] = {
+	/* PWEN, OVC */
+	RCAR_GP_PIN(6, 14), RCAR_GP_PIN(6, 15),
+};
+static const unsigned int usb2_mux[] = {
+	USB2_PWEN_MARK, USB2_OVC_MARK,
+};
+
 static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(audio_clk_a_a),
 	SH_PFC_PIN_GROUP(audio_clk_a_b),
@@ -3117,6 +3339,13 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(avb_avtp_capture_a),
 	SH_PFC_PIN_GROUP(avb_avtp_match_b),
 	SH_PFC_PIN_GROUP(avb_avtp_capture_b),
+	SH_PFC_PIN_GROUP(can0_data_a),
+	SH_PFC_PIN_GROUP(can0_data_b),
+	SH_PFC_PIN_GROUP(can1_data),
+	SH_PFC_PIN_GROUP(can_clk),
+	SH_PFC_PIN_GROUP(canfd0_data_a),
+	SH_PFC_PIN_GROUP(canfd0_data_b),
+	SH_PFC_PIN_GROUP(canfd1_data),
 	SH_PFC_PIN_GROUP(hscif0_data),
 	SH_PFC_PIN_GROUP(hscif0_clk),
 	SH_PFC_PIN_GROUP(hscif0_ctrl),
@@ -3149,6 +3378,12 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(i2c6_a),
 	SH_PFC_PIN_GROUP(i2c6_b),
 	SH_PFC_PIN_GROUP(i2c6_c),
+	SH_PFC_PIN_GROUP(intc_ex_irq0),
+	SH_PFC_PIN_GROUP(intc_ex_irq1),
+	SH_PFC_PIN_GROUP(intc_ex_irq2),
+	SH_PFC_PIN_GROUP(intc_ex_irq3),
+	SH_PFC_PIN_GROUP(intc_ex_irq4),
+	SH_PFC_PIN_GROUP(intc_ex_irq5),
 	SH_PFC_PIN_GROUP(msiof0_clk),
 	SH_PFC_PIN_GROUP(msiof0_sync),
 	SH_PFC_PIN_GROUP(msiof0_ss1),
@@ -3242,6 +3477,19 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(msiof3_ss1_d),
 	SH_PFC_PIN_GROUP(msiof3_txd_d),
 	SH_PFC_PIN_GROUP(msiof3_rxd_d),
+	SH_PFC_PIN_GROUP(pwm0),
+	SH_PFC_PIN_GROUP(pwm1_a),
+	SH_PFC_PIN_GROUP(pwm1_b),
+	SH_PFC_PIN_GROUP(pwm2_a),
+	SH_PFC_PIN_GROUP(pwm2_b),
+	SH_PFC_PIN_GROUP(pwm3_a),
+	SH_PFC_PIN_GROUP(pwm3_b),
+	SH_PFC_PIN_GROUP(pwm4_a),
+	SH_PFC_PIN_GROUP(pwm4_b),
+	SH_PFC_PIN_GROUP(pwm5_a),
+	SH_PFC_PIN_GROUP(pwm5_b),
+	SH_PFC_PIN_GROUP(pwm6_a),
+	SH_PFC_PIN_GROUP(pwm6_b),
 	SH_PFC_PIN_GROUP(sata0_devslp_a),
 	SH_PFC_PIN_GROUP(sata0_devslp_b),
 	SH_PFC_PIN_GROUP(scif0_data),
@@ -3322,6 +3570,9 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(ssi9_data_b),
 	SH_PFC_PIN_GROUP(ssi9_ctrl_a),
 	SH_PFC_PIN_GROUP(ssi9_ctrl_b),
+	SH_PFC_PIN_GROUP(usb0),
+	SH_PFC_PIN_GROUP(usb1),
+	SH_PFC_PIN_GROUP(usb2),
 };
 
 static const char * const audio_clk_groups[] = {
@@ -3356,6 +3607,28 @@ static const char * const avb_groups[] = {
 	"avb_avtp_capture_b",
 };
 
+static const char * const can0_groups[] = {
+	"can0_data_a",
+	"can0_data_b",
+};
+
+static const char * const can1_groups[] = {
+	"can1_data",
+};
+
+static const char * const can_clk_groups[] = {
+	"can_clk",
+};
+
+static const char * const canfd0_groups[] = {
+	"canfd0_data_a",
+	"canfd0_data_b",
+};
+
+static const char * const canfd1_groups[] = {
+	"canfd1_data",
+};
+
 static const char * const hscif0_groups[] = {
 	"hscif0_data",
 	"hscif0_clk",
@@ -3412,6 +3685,15 @@ static const char * const i2c6_groups[] = {
 	"i2c6_c",
 };
 
+static const char * const intc_ex_groups[] = {
+	"intc_ex_irq0",
+	"intc_ex_irq1",
+	"intc_ex_irq2",
+	"intc_ex_irq3",
+	"intc_ex_irq4",
+	"intc_ex_irq5",
+};
+
 static const char * const msiof0_groups[] = {
 	"msiof0_clk",
 	"msiof0_sync",
@@ -3517,6 +3799,40 @@ static const char * const msiof3_groups[] = {
 	"msiof3_rxd_d",
 };
 
+static const char * const pwm0_groups[] = {
+	"pwm0",
+};
+
+static const char * const pwm1_groups[] = {
+	"pwm1_a",
+	"pwm1_b",
+};
+
+static const char * const pwm2_groups[] = {
+	"pwm2_a",
+	"pwm2_b",
+};
+
+static const char * const pwm3_groups[] = {
+	"pwm3_a",
+	"pwm3_b",
+};
+
+static const char * const pwm4_groups[] = {
+	"pwm4_a",
+	"pwm4_b",
+};
+
+static const char * const pwm5_groups[] = {
+	"pwm5_a",
+	"pwm5_b",
+};
+
+static const char * const pwm6_groups[] = {
+	"pwm6_a",
+	"pwm6_b",
+};
+
 static const char * const sata0_groups[] = {
 	"sata0_devslp_a",
 	"sata0_devslp_b",
@@ -3636,9 +3952,26 @@ static const char * const ssi_groups[] = {
 	"ssi9_ctrl_b",
 };
 
+static const char * const usb0_groups[] = {
+	"usb0",
+};
+
+static const char * const usb1_groups[] = {
+	"usb1",
+};
+
+static const char * const usb2_groups[] = {
+	"usb2",
+};
+
 static const struct sh_pfc_function pinmux_functions[] = {
 	SH_PFC_FUNCTION(audio_clk),
 	SH_PFC_FUNCTION(avb),
+	SH_PFC_FUNCTION(can0),
+	SH_PFC_FUNCTION(can1),
+	SH_PFC_FUNCTION(can_clk),
+	SH_PFC_FUNCTION(canfd0),
+	SH_PFC_FUNCTION(canfd1),
 	SH_PFC_FUNCTION(hscif0),
 	SH_PFC_FUNCTION(hscif1),
 	SH_PFC_FUNCTION(hscif2),
@@ -3647,10 +3980,18 @@ static const struct sh_pfc_function pinmux_functions[] = {
 	SH_PFC_FUNCTION(i2c1),
 	SH_PFC_FUNCTION(i2c2),
 	SH_PFC_FUNCTION(i2c6),
+	SH_PFC_FUNCTION(intc_ex),
 	SH_PFC_FUNCTION(msiof0),
 	SH_PFC_FUNCTION(msiof1),
 	SH_PFC_FUNCTION(msiof2),
 	SH_PFC_FUNCTION(msiof3),
+	SH_PFC_FUNCTION(pwm0),
+	SH_PFC_FUNCTION(pwm1),
+	SH_PFC_FUNCTION(pwm2),
+	SH_PFC_FUNCTION(pwm3),
+	SH_PFC_FUNCTION(pwm4),
+	SH_PFC_FUNCTION(pwm5),
+	SH_PFC_FUNCTION(pwm6),
 	SH_PFC_FUNCTION(sata0),
 	SH_PFC_FUNCTION(scif0),
 	SH_PFC_FUNCTION(scif1),
@@ -3664,6 +4005,9 @@ static const struct sh_pfc_function pinmux_functions[] = {
 	SH_PFC_FUNCTION(sdhi2),
 	SH_PFC_FUNCTION(sdhi3),
 	SH_PFC_FUNCTION(ssi),
+	SH_PFC_FUNCTION(usb0),
+	SH_PFC_FUNCTION(usb1),
+	SH_PFC_FUNCTION(usb2),
 };
 
 static const struct pinmux_cfg_reg pinmux_config_regs[] = {
@@ -4213,7 +4557,8 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = {
 		0, 0, 0, 0, 0, 0, 0, 0,
 		/* RESERVED 3 */
 		0, 0,
-		MOD_SEL2_2_1
+		/* RESERVED 2, 1 */
+		0, 0, 0, 0,
 		MOD_SEL2_0 }
 	},
 	{ },
diff --git a/drivers/pinctrl/sh-pfc/pfc-sh7734.c b/drivers/pinctrl/sh-pfc/pfc-sh7734.c
index b0b328b3130b..6502e676d368 100644
--- a/drivers/pinctrl/sh-pfc/pfc-sh7734.c
+++ b/drivers/pinctrl/sh-pfc/pfc-sh7734.c
@@ -591,547 +591,547 @@ static const u16 pinmux_data[] = {
 	PINMUX_SINGLE(IRQ3_B),
 
 	/* IPSR0 */
-	PINMUX_IPSR_DATA(IP0_1_0, A0),
-	PINMUX_IPSR_DATA(IP0_1_0, ST0_CLKIN),
+	PINMUX_IPSR_GPSR(IP0_1_0, A0),
+	PINMUX_IPSR_GPSR(IP0_1_0, ST0_CLKIN),
 	PINMUX_IPSR_MSEL(IP0_1_0, LCD_DATA0_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP0_1_0, TCLKA_C, SEL_MTU2_CLK_1),
 
-	PINMUX_IPSR_DATA(IP0_3_2, A1),
-	PINMUX_IPSR_DATA(IP0_3_2, ST0_REQ),
+	PINMUX_IPSR_GPSR(IP0_3_2, A1),
+	PINMUX_IPSR_GPSR(IP0_3_2, ST0_REQ),
 	PINMUX_IPSR_MSEL(IP0_3_2, LCD_DATA1_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP0_3_2, TCLKB_C, SEL_MTU2_CLK_1),
 
-	PINMUX_IPSR_DATA(IP0_5_4, A2),
-	PINMUX_IPSR_DATA(IP0_5_4, ST0_SYC),
+	PINMUX_IPSR_GPSR(IP0_5_4, A2),
+	PINMUX_IPSR_GPSR(IP0_5_4, ST0_SYC),
 	PINMUX_IPSR_MSEL(IP0_5_4, LCD_DATA2_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP0_5_4, TCLKC_C, SEL_MTU2_CLK_1),
 
-	PINMUX_IPSR_DATA(IP0_7_6, A3),
-	PINMUX_IPSR_DATA(IP0_7_6, ST0_VLD),
+	PINMUX_IPSR_GPSR(IP0_7_6, A3),
+	PINMUX_IPSR_GPSR(IP0_7_6, ST0_VLD),
 	PINMUX_IPSR_MSEL(IP0_7_6, LCD_DATA3_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP0_7_6, TCLKD_C, SEL_MTU2_CLK_1),
 
-	PINMUX_IPSR_DATA(IP0_9_8, A4),
-	PINMUX_IPSR_DATA(IP0_9_8, ST0_D0),
+	PINMUX_IPSR_GPSR(IP0_9_8, A4),
+	PINMUX_IPSR_GPSR(IP0_9_8, ST0_D0),
 	PINMUX_IPSR_MSEL(IP0_9_8, LCD_DATA4_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP0_9_8, TIOC0A_C, SEL_MTU2_CH0_1),
 
-	PINMUX_IPSR_DATA(IP0_11_10, A5),
-	PINMUX_IPSR_DATA(IP0_11_10, ST0_D1),
+	PINMUX_IPSR_GPSR(IP0_11_10, A5),
+	PINMUX_IPSR_GPSR(IP0_11_10, ST0_D1),
 	PINMUX_IPSR_MSEL(IP0_11_10, LCD_DATA5_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP0_11_10, TIOC0B_C, SEL_MTU2_CH0_1),
 
-	PINMUX_IPSR_DATA(IP0_13_12, A6),
-	PINMUX_IPSR_DATA(IP0_13_12, ST0_D2),
+	PINMUX_IPSR_GPSR(IP0_13_12, A6),
+	PINMUX_IPSR_GPSR(IP0_13_12, ST0_D2),
 	PINMUX_IPSR_MSEL(IP0_13_12, LCD_DATA6_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP0_13_12, TIOC0C_C, SEL_MTU2_CH0_1),
 
-	PINMUX_IPSR_DATA(IP0_15_14, A7),
-	PINMUX_IPSR_DATA(IP0_15_14, ST0_D3),
+	PINMUX_IPSR_GPSR(IP0_15_14, A7),
+	PINMUX_IPSR_GPSR(IP0_15_14, ST0_D3),
 	PINMUX_IPSR_MSEL(IP0_15_14, LCD_DATA7_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP0_15_14, TIOC0D_C, SEL_MTU2_CH0_1),
 
-	PINMUX_IPSR_DATA(IP0_17_16, A8),
-	PINMUX_IPSR_DATA(IP0_17_16, ST0_D4),
+	PINMUX_IPSR_GPSR(IP0_17_16, A8),
+	PINMUX_IPSR_GPSR(IP0_17_16, ST0_D4),
 	PINMUX_IPSR_MSEL(IP0_17_16, LCD_DATA8_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP0_17_16, TIOC1A_C, SEL_MTU2_CH1_2),
 
-	PINMUX_IPSR_DATA(IP0_19_18, A9),
-	PINMUX_IPSR_DATA(IP0_19_18, ST0_D5),
+	PINMUX_IPSR_GPSR(IP0_19_18, A9),
+	PINMUX_IPSR_GPSR(IP0_19_18, ST0_D5),
 	PINMUX_IPSR_MSEL(IP0_19_18, LCD_DATA9_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP0_19_18, TIOC1B_C, SEL_MTU2_CH1_2),
 
-	PINMUX_IPSR_DATA(IP0_21_20, A10),
-	PINMUX_IPSR_DATA(IP0_21_20, ST0_D6),
+	PINMUX_IPSR_GPSR(IP0_21_20, A10),
+	PINMUX_IPSR_GPSR(IP0_21_20, ST0_D6),
 	PINMUX_IPSR_MSEL(IP0_21_20, LCD_DATA10_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP0_21_20, TIOC2A_C, SEL_MTU2_CH2_2),
 
-	PINMUX_IPSR_DATA(IP0_23_22, A11),
-	PINMUX_IPSR_DATA(IP0_23_22, ST0_D7),
+	PINMUX_IPSR_GPSR(IP0_23_22, A11),
+	PINMUX_IPSR_GPSR(IP0_23_22, ST0_D7),
 	PINMUX_IPSR_MSEL(IP0_23_22, LCD_DATA11_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP0_23_22, TIOC2B_C, SEL_MTU2_CH2_2),
 
-	PINMUX_IPSR_DATA(IP0_25_24, A12),
+	PINMUX_IPSR_GPSR(IP0_25_24, A12),
 	PINMUX_IPSR_MSEL(IP0_25_24, LCD_DATA12_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP0_25_24, TIOC3A_C, SEL_MTU2_CH3_1),
 
-	PINMUX_IPSR_DATA(IP0_27_26, A13),
+	PINMUX_IPSR_GPSR(IP0_27_26, A13),
 	PINMUX_IPSR_MSEL(IP0_27_26, LCD_DATA13_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP0_27_26, TIOC3B_C, SEL_MTU2_CH3_1),
 
-	PINMUX_IPSR_DATA(IP0_29_28, A14),
+	PINMUX_IPSR_GPSR(IP0_29_28, A14),
 	PINMUX_IPSR_MSEL(IP0_29_28, LCD_DATA14_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP0_29_28, TIOC3C_C, SEL_MTU2_CH3_1),
 
-	PINMUX_IPSR_DATA(IP0_31_30, A15),
-	PINMUX_IPSR_DATA(IP0_31_30, ST0_VCO_CLKIN),
+	PINMUX_IPSR_GPSR(IP0_31_30, A15),
+	PINMUX_IPSR_GPSR(IP0_31_30, ST0_VCO_CLKIN),
 	PINMUX_IPSR_MSEL(IP0_31_30, LCD_DATA15_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP0_31_30, TIOC3D_C, SEL_MTU2_CH3_1),
 
 
 	/* IPSR1 */
-	PINMUX_IPSR_DATA(IP1_1_0, A16),
-	PINMUX_IPSR_DATA(IP1_1_0, ST0_PWM),
+	PINMUX_IPSR_GPSR(IP1_1_0, A16),
+	PINMUX_IPSR_GPSR(IP1_1_0, ST0_PWM),
 	PINMUX_IPSR_MSEL(IP1_1_0, LCD_DON_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP1_1_0, TIOC4A_C, SEL_MTU2_CH4_1),
 
-	PINMUX_IPSR_DATA(IP1_3_2, A17),
-	PINMUX_IPSR_DATA(IP1_3_2, ST1_VCO_CLKIN),
+	PINMUX_IPSR_GPSR(IP1_3_2, A17),
+	PINMUX_IPSR_GPSR(IP1_3_2, ST1_VCO_CLKIN),
 	PINMUX_IPSR_MSEL(IP1_3_2, LCD_CL1_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP1_3_2, TIOC4B_C, SEL_MTU2_CH4_1),
 
-	PINMUX_IPSR_DATA(IP1_5_4, A18),
-	PINMUX_IPSR_DATA(IP1_5_4, ST1_PWM),
+	PINMUX_IPSR_GPSR(IP1_5_4, A18),
+	PINMUX_IPSR_GPSR(IP1_5_4, ST1_PWM),
 	PINMUX_IPSR_MSEL(IP1_5_4, LCD_CL2_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP1_5_4, TIOC4C_C, SEL_MTU2_CH4_1),
 
-	PINMUX_IPSR_DATA(IP1_7_6, A19),
-	PINMUX_IPSR_DATA(IP1_7_6, ST1_CLKIN),
+	PINMUX_IPSR_GPSR(IP1_7_6, A19),
+	PINMUX_IPSR_GPSR(IP1_7_6, ST1_CLKIN),
 	PINMUX_IPSR_MSEL(IP1_7_6, LCD_CLK_A, SEL_LCDC_0),
 	PINMUX_IPSR_MSEL(IP1_7_6, TIOC4D_C, SEL_MTU2_CH4_1),
 
-	PINMUX_IPSR_DATA(IP1_9_8, A20),
-	PINMUX_IPSR_DATA(IP1_9_8, ST1_REQ),
+	PINMUX_IPSR_GPSR(IP1_9_8, A20),
+	PINMUX_IPSR_GPSR(IP1_9_8, ST1_REQ),
 	PINMUX_IPSR_MSEL(IP1_9_8, LCD_FLM_A, SEL_LCDC_0),
 
-	PINMUX_IPSR_DATA(IP1_11_10, A21),
-	PINMUX_IPSR_DATA(IP1_11_10, ST1_SYC),
+	PINMUX_IPSR_GPSR(IP1_11_10, A21),
+	PINMUX_IPSR_GPSR(IP1_11_10, ST1_SYC),
 	PINMUX_IPSR_MSEL(IP1_11_10, LCD_VCPWC_A, SEL_LCDC_0),
 
-	PINMUX_IPSR_DATA(IP1_13_12, A22),
-	PINMUX_IPSR_DATA(IP1_13_12, ST1_VLD),
+	PINMUX_IPSR_GPSR(IP1_13_12, A22),
+	PINMUX_IPSR_GPSR(IP1_13_12, ST1_VLD),
 	PINMUX_IPSR_MSEL(IP1_13_12, LCD_VEPWC_A, SEL_LCDC_0),
 
-	PINMUX_IPSR_DATA(IP1_15_14, A23),
-	PINMUX_IPSR_DATA(IP1_15_14, ST1_D0),
+	PINMUX_IPSR_GPSR(IP1_15_14, A23),
+	PINMUX_IPSR_GPSR(IP1_15_14, ST1_D0),
 	PINMUX_IPSR_MSEL(IP1_15_14, LCD_M_DISP_A, SEL_LCDC_0),
 
-	PINMUX_IPSR_DATA(IP1_17_16, A24),
+	PINMUX_IPSR_GPSR(IP1_17_16, A24),
 	PINMUX_IPSR_MSEL(IP1_17_16, RX2_D, SEL_SCIF2_3),
-	PINMUX_IPSR_DATA(IP1_17_16, ST1_D1),
+	PINMUX_IPSR_GPSR(IP1_17_16, ST1_D1),
 
-	PINMUX_IPSR_DATA(IP1_19_18, A25),
+	PINMUX_IPSR_GPSR(IP1_19_18, A25),
 	PINMUX_IPSR_MSEL(IP1_17_16, RX2_D, SEL_SCIF2_3),
-	PINMUX_IPSR_DATA(IP1_17_16, ST1_D2),
+	PINMUX_IPSR_GPSR(IP1_17_16, ST1_D2),
 
-	PINMUX_IPSR_DATA(IP1_22_20, D0),
+	PINMUX_IPSR_GPSR(IP1_22_20, D0),
 	PINMUX_IPSR_MSEL(IP1_22_20, SD0_DAT0_A, SEL_SDHI0_0),
 	PINMUX_IPSR_MSEL(IP1_22_20, MMC_D0_A, SEL_MMC_0),
-	PINMUX_IPSR_DATA(IP1_22_20, ST1_D3),
+	PINMUX_IPSR_GPSR(IP1_22_20, ST1_D3),
 	PINMUX_IPSR_MSEL(IP1_22_20, FD0_A, SEL_FLCTL_0),
 
-	PINMUX_IPSR_DATA(IP1_25_23, D1),
+	PINMUX_IPSR_GPSR(IP1_25_23, D1),
 	PINMUX_IPSR_MSEL(IP1_25_23, SD0_DAT0_A, SEL_SDHI0_0),
 	PINMUX_IPSR_MSEL(IP1_25_23, MMC_D1_A, SEL_MMC_0),
-	PINMUX_IPSR_DATA(IP1_25_23, ST1_D4),
+	PINMUX_IPSR_GPSR(IP1_25_23, ST1_D4),
 	PINMUX_IPSR_MSEL(IP1_25_23, FD1_A, SEL_FLCTL_0),
 
-	PINMUX_IPSR_DATA(IP1_28_26, D2),
+	PINMUX_IPSR_GPSR(IP1_28_26, D2),
 	PINMUX_IPSR_MSEL(IP1_28_26, SD0_DAT0_A, SEL_SDHI0_0),
 	PINMUX_IPSR_MSEL(IP1_28_26, MMC_D2_A, SEL_MMC_0),
-	PINMUX_IPSR_DATA(IP1_28_26, ST1_D5),
+	PINMUX_IPSR_GPSR(IP1_28_26, ST1_D5),
 	PINMUX_IPSR_MSEL(IP1_28_26, FD2_A, SEL_FLCTL_0),
 
-	PINMUX_IPSR_DATA(IP1_31_29, D3),
+	PINMUX_IPSR_GPSR(IP1_31_29, D3),
 	PINMUX_IPSR_MSEL(IP1_31_29, SD0_DAT0_A, SEL_SDHI0_0),
 	PINMUX_IPSR_MSEL(IP1_31_29, MMC_D3_A, SEL_MMC_0),
-	PINMUX_IPSR_DATA(IP1_31_29, ST1_D6),
+	PINMUX_IPSR_GPSR(IP1_31_29, ST1_D6),
 	PINMUX_IPSR_MSEL(IP1_31_29, FD3_A, SEL_FLCTL_0),
 
 	/* IPSR2 */
-	PINMUX_IPSR_DATA(IP2_2_0, D4),
+	PINMUX_IPSR_GPSR(IP2_2_0, D4),
 	PINMUX_IPSR_MSEL(IP2_2_0, SD0_CD_A, SEL_SDHI0_0),
 	PINMUX_IPSR_MSEL(IP2_2_0, MMC_D4_A, SEL_MMC_0),
-	PINMUX_IPSR_DATA(IP2_2_0, ST1_D7),
+	PINMUX_IPSR_GPSR(IP2_2_0, ST1_D7),
 	PINMUX_IPSR_MSEL(IP2_2_0, FD4_A, SEL_FLCTL_0),
 
-	PINMUX_IPSR_DATA(IP2_4_3, D5),
+	PINMUX_IPSR_GPSR(IP2_4_3, D5),
 	PINMUX_IPSR_MSEL(IP2_4_3, SD0_WP_A, SEL_SDHI0_0),
 	PINMUX_IPSR_MSEL(IP2_4_3, MMC_D5_A, SEL_MMC_0),
 	PINMUX_IPSR_MSEL(IP2_4_3, FD5_A, SEL_FLCTL_0),
 
-	PINMUX_IPSR_DATA(IP2_7_5, D6),
+	PINMUX_IPSR_GPSR(IP2_7_5, D6),
 	PINMUX_IPSR_MSEL(IP2_7_5, RSPI_RSPCK_A, SEL_RSPI_0),
 	PINMUX_IPSR_MSEL(IP2_7_5, MMC_D6_A, SEL_MMC_0),
 	PINMUX_IPSR_MSEL(IP2_7_5, QSPCLK_A, SEL_RQSPI_0),
 	PINMUX_IPSR_MSEL(IP2_7_5, FD6_A, SEL_FLCTL_0),
 
-	PINMUX_IPSR_DATA(IP2_10_8, D7),
+	PINMUX_IPSR_GPSR(IP2_10_8, D7),
 	PINMUX_IPSR_MSEL(IP2_10_8, RSPI_SSL_A, SEL_RSPI_0),
 	PINMUX_IPSR_MSEL(IP2_10_8, MMC_D7_A, SEL_MMC_0),
 	PINMUX_IPSR_MSEL(IP2_10_8, QSSL_A, SEL_RQSPI_0),
 	PINMUX_IPSR_MSEL(IP2_10_8, FD7_A, SEL_FLCTL_0),
 
-	PINMUX_IPSR_DATA(IP2_13_11, D8),
+	PINMUX_IPSR_GPSR(IP2_13_11, D8),
 	PINMUX_IPSR_MSEL(IP2_13_11, SD0_CLK_A, SEL_SDHI0_0),
 	PINMUX_IPSR_MSEL(IP2_13_11, MMC_CLK_A, SEL_MMC_0),
 	PINMUX_IPSR_MSEL(IP2_13_11, QIO2_A, SEL_RQSPI_0),
 	PINMUX_IPSR_MSEL(IP2_13_11, FCE_A, SEL_FLCTL_0),
 	PINMUX_IPSR_MSEL(IP2_13_11, ET0_GTX_CLK_B, SEL_ET0_1),
 
-	PINMUX_IPSR_DATA(IP2_16_14, D9),
+	PINMUX_IPSR_GPSR(IP2_16_14, D9),
 	PINMUX_IPSR_MSEL(IP2_16_14, SD0_CMD_A, SEL_SDHI0_0),
 	PINMUX_IPSR_MSEL(IP2_16_14, MMC_CMD_A, SEL_MMC_0),
 	PINMUX_IPSR_MSEL(IP2_16_14, QIO3_A, SEL_RQSPI_0),
 	PINMUX_IPSR_MSEL(IP2_16_14, FCLE_A, SEL_FLCTL_0),
 	PINMUX_IPSR_MSEL(IP2_16_14, ET0_ETXD1_B, SEL_ET0_1),
 
-	PINMUX_IPSR_DATA(IP2_19_17, D10),
+	PINMUX_IPSR_GPSR(IP2_19_17, D10),
 	PINMUX_IPSR_MSEL(IP2_19_17, RSPI_MOSI_A, SEL_RSPI_0),
 	PINMUX_IPSR_MSEL(IP2_19_17, QMO_QIO0_A, SEL_RQSPI_0),
 	PINMUX_IPSR_MSEL(IP2_19_17, FALE_A, SEL_FLCTL_0),
 	PINMUX_IPSR_MSEL(IP2_19_17, ET0_ETXD2_B, SEL_ET0_1),
 
-	PINMUX_IPSR_DATA(IP2_22_20, D11),
+	PINMUX_IPSR_GPSR(IP2_22_20, D11),
 	PINMUX_IPSR_MSEL(IP2_22_20, RSPI_MISO_A, SEL_RSPI_0),
 	PINMUX_IPSR_MSEL(IP2_22_20, QMI_QIO1_A, SEL_RQSPI_0),
 	PINMUX_IPSR_MSEL(IP2_22_20, FRE_A, SEL_FLCTL_0),
 
-	PINMUX_IPSR_DATA(IP2_24_23, D12),
+	PINMUX_IPSR_GPSR(IP2_24_23, D12),
 	PINMUX_IPSR_MSEL(IP2_24_23, FWE_A, SEL_FLCTL_0),
 	PINMUX_IPSR_MSEL(IP2_24_23, ET0_ETXD5_B, SEL_ET0_1),
 
-	PINMUX_IPSR_DATA(IP2_27_25, D13),
+	PINMUX_IPSR_GPSR(IP2_27_25, D13),
 	PINMUX_IPSR_MSEL(IP2_27_25, RX2_B, SEL_SCIF2_1),
 	PINMUX_IPSR_MSEL(IP2_27_25, FRB_A, SEL_FLCTL_0),
 	PINMUX_IPSR_MSEL(IP2_27_25, ET0_ETXD6_B, SEL_ET0_1),
 
-	PINMUX_IPSR_DATA(IP2_30_28, D14),
+	PINMUX_IPSR_GPSR(IP2_30_28, D14),
 	PINMUX_IPSR_MSEL(IP2_30_28, TX2_B, SEL_SCIF2_1),
 	PINMUX_IPSR_MSEL(IP2_30_28, FSE_A, SEL_FLCTL_0),
 	PINMUX_IPSR_MSEL(IP2_30_28, ET0_TX_CLK_B, SEL_ET0_1),
 
 	/* IPSR3 */
-	PINMUX_IPSR_DATA(IP3_1_0, D15),
+	PINMUX_IPSR_GPSR(IP3_1_0, D15),
 	PINMUX_IPSR_MSEL(IP3_1_0, SCK2_B, SEL_SCIF2_1),
 
-	PINMUX_IPSR_DATA(IP3_2, CS1_A26),
+	PINMUX_IPSR_GPSR(IP3_2, CS1_A26),
 	PINMUX_IPSR_MSEL(IP3_2, QIO3_B, SEL_RQSPI_1),
 
-	PINMUX_IPSR_DATA(IP3_5_3, EX_CS1),
+	PINMUX_IPSR_GPSR(IP3_5_3, EX_CS1),
 	PINMUX_IPSR_MSEL(IP3_5_3, RX3_B, SEL_SCIF2_1),
-	PINMUX_IPSR_DATA(IP3_5_3, ATACS0),
+	PINMUX_IPSR_GPSR(IP3_5_3, ATACS0),
 	PINMUX_IPSR_MSEL(IP3_5_3, QIO2_B, SEL_RQSPI_1),
-	PINMUX_IPSR_DATA(IP3_5_3, ET0_ETXD0),
+	PINMUX_IPSR_GPSR(IP3_5_3, ET0_ETXD0),
 
-	PINMUX_IPSR_DATA(IP3_8_6, EX_CS2),
+	PINMUX_IPSR_GPSR(IP3_8_6, EX_CS2),
 	PINMUX_IPSR_MSEL(IP3_8_6, TX3_B, SEL_SCIF3_1),
-	PINMUX_IPSR_DATA(IP3_8_6, ATACS1),
+	PINMUX_IPSR_GPSR(IP3_8_6, ATACS1),
 	PINMUX_IPSR_MSEL(IP3_8_6, QSPCLK_B, SEL_RQSPI_1),
 	PINMUX_IPSR_MSEL(IP3_8_6, ET0_GTX_CLK_A, SEL_ET0_0),
 
-	PINMUX_IPSR_DATA(IP3_11_9, EX_CS3),
+	PINMUX_IPSR_GPSR(IP3_11_9, EX_CS3),
 	PINMUX_IPSR_MSEL(IP3_11_9, SD1_CD_A, SEL_SDHI1_0),
-	PINMUX_IPSR_DATA(IP3_11_9, ATARD),
+	PINMUX_IPSR_GPSR(IP3_11_9, ATARD),
 	PINMUX_IPSR_MSEL(IP3_11_9, QMO_QIO0_B, SEL_RQSPI_1),
 	PINMUX_IPSR_MSEL(IP3_11_9, ET0_ETXD1_A, SEL_ET0_0),
 
-	PINMUX_IPSR_DATA(IP3_14_12, EX_CS4),
+	PINMUX_IPSR_GPSR(IP3_14_12, EX_CS4),
 	PINMUX_IPSR_MSEL(IP3_14_12, SD1_WP_A, SEL_SDHI1_0),
-	PINMUX_IPSR_DATA(IP3_14_12, ATAWR),
+	PINMUX_IPSR_GPSR(IP3_14_12, ATAWR),
 	PINMUX_IPSR_MSEL(IP3_14_12, QMI_QIO1_B, SEL_RQSPI_1),
 	PINMUX_IPSR_MSEL(IP3_14_12, ET0_ETXD2_A, SEL_ET0_0),
 
-	PINMUX_IPSR_DATA(IP3_17_15, EX_CS5),
+	PINMUX_IPSR_GPSR(IP3_17_15, EX_CS5),
 	PINMUX_IPSR_MSEL(IP3_17_15, SD1_CMD_A, SEL_SDHI1_0),
-	PINMUX_IPSR_DATA(IP3_17_15, ATADIR),
+	PINMUX_IPSR_GPSR(IP3_17_15, ATADIR),
 	PINMUX_IPSR_MSEL(IP3_17_15, QSSL_B, SEL_RQSPI_1),
 	PINMUX_IPSR_MSEL(IP3_17_15, ET0_ETXD3_A, SEL_ET0_0),
 
-	PINMUX_IPSR_DATA(IP3_19_18, RD_WR),
-	PINMUX_IPSR_DATA(IP3_19_18, TCLK0),
+	PINMUX_IPSR_GPSR(IP3_19_18, RD_WR),
+	PINMUX_IPSR_GPSR(IP3_19_18, TCLK0),
 	PINMUX_IPSR_MSEL(IP3_19_18, CAN_CLK_B, SEL_RCAN_CLK_1),
-	PINMUX_IPSR_DATA(IP3_19_18, ET0_ETXD4),
+	PINMUX_IPSR_GPSR(IP3_19_18, ET0_ETXD4),
 
-	PINMUX_IPSR_DATA(IP3_20, EX_WAIT0),
+	PINMUX_IPSR_GPSR(IP3_20, EX_WAIT0),
 	PINMUX_IPSR_MSEL(IP3_20, TCLK1_B, SEL_TMU_1),
 
-	PINMUX_IPSR_DATA(IP3_23_21, EX_WAIT1),
+	PINMUX_IPSR_GPSR(IP3_23_21, EX_WAIT1),
 	PINMUX_IPSR_MSEL(IP3_23_21, SD1_DAT0_A, SEL_SDHI1_0),
-	PINMUX_IPSR_DATA(IP3_23_21, DREQ2),
+	PINMUX_IPSR_GPSR(IP3_23_21, DREQ2),
 	PINMUX_IPSR_MSEL(IP3_23_21, CAN1_TX_C, SEL_RCAN1_2),
 	PINMUX_IPSR_MSEL(IP3_23_21, ET0_LINK_C, SEL_ET0_CTL_2),
 	PINMUX_IPSR_MSEL(IP3_23_21, ET0_ETXD5_A, SEL_ET0_0),
 
-	PINMUX_IPSR_DATA(IP3_26_24, EX_WAIT2),
+	PINMUX_IPSR_GPSR(IP3_26_24, EX_WAIT2),
 	PINMUX_IPSR_MSEL(IP3_26_24, SD1_DAT1_A, SEL_SDHI1_0),
-	PINMUX_IPSR_DATA(IP3_26_24, DACK2),
+	PINMUX_IPSR_GPSR(IP3_26_24, DACK2),
 	PINMUX_IPSR_MSEL(IP3_26_24, CAN1_RX_C, SEL_RCAN1_2),
 	PINMUX_IPSR_MSEL(IP3_26_24, ET0_MAGIC_C, SEL_ET0_CTL_2),
 	PINMUX_IPSR_MSEL(IP3_26_24, ET0_ETXD6_A, SEL_ET0_0),
 
-	PINMUX_IPSR_DATA(IP3_29_27, DRACK0),
+	PINMUX_IPSR_GPSR(IP3_29_27, DRACK0),
 	PINMUX_IPSR_MSEL(IP3_29_27, SD1_DAT2_A, SEL_SDHI1_0),
-	PINMUX_IPSR_DATA(IP3_29_27, ATAG),
+	PINMUX_IPSR_GPSR(IP3_29_27, ATAG),
 	PINMUX_IPSR_MSEL(IP3_29_27, TCLK1_A, SEL_TMU_0),
-	PINMUX_IPSR_DATA(IP3_29_27, ET0_ETXD7),
+	PINMUX_IPSR_GPSR(IP3_29_27, ET0_ETXD7),
 
 	/* IPSR4 */
 	PINMUX_IPSR_MSEL(IP4_2_0, HCTS0_A, SEL_HSCIF_0),
 	PINMUX_IPSR_MSEL(IP4_2_0, CTS1_A, SEL_SCIF1_0),
-	PINMUX_IPSR_DATA(IP4_2_0, VI0_FIELD),
+	PINMUX_IPSR_GPSR(IP4_2_0, VI0_FIELD),
 	PINMUX_IPSR_MSEL(IP4_2_0, RMII0_RXD1_A, SEL_RMII_0),
-	PINMUX_IPSR_DATA(IP4_2_0, ET0_ERXD7),
+	PINMUX_IPSR_GPSR(IP4_2_0, ET0_ERXD7),
 
 	PINMUX_IPSR_MSEL(IP4_5_3, HRTS0_A, SEL_HSCIF_0),
 	PINMUX_IPSR_MSEL(IP4_5_3, RTS1_A, SEL_SCIF1_0),
-	PINMUX_IPSR_DATA(IP4_5_3, VI0_HSYNC),
+	PINMUX_IPSR_GPSR(IP4_5_3, VI0_HSYNC),
 	PINMUX_IPSR_MSEL(IP4_5_3, RMII0_TXD_EN_A, SEL_RMII_0),
-	PINMUX_IPSR_DATA(IP4_5_3, ET0_RX_DV),
+	PINMUX_IPSR_GPSR(IP4_5_3, ET0_RX_DV),
 
 	PINMUX_IPSR_MSEL(IP4_8_6, HSCK0_A, SEL_HSCIF_0),
 	PINMUX_IPSR_MSEL(IP4_8_6, SCK1_A, SEL_SCIF1_0),
-	PINMUX_IPSR_DATA(IP4_8_6, VI0_VSYNC),
+	PINMUX_IPSR_GPSR(IP4_8_6, VI0_VSYNC),
 	PINMUX_IPSR_MSEL(IP4_8_6, RMII0_RX_ER_A, SEL_RMII_0),
-	PINMUX_IPSR_DATA(IP4_8_6, ET0_RX_ER),
+	PINMUX_IPSR_GPSR(IP4_8_6, ET0_RX_ER),
 
 	PINMUX_IPSR_MSEL(IP4_11_9, HRX0_A, SEL_HSCIF_0),
 	PINMUX_IPSR_MSEL(IP4_11_9, RX1_A, SEL_SCIF1_0),
-	PINMUX_IPSR_DATA(IP4_11_9, VI0_DATA0_VI0_B0),
+	PINMUX_IPSR_GPSR(IP4_11_9, VI0_DATA0_VI0_B0),
 	PINMUX_IPSR_MSEL(IP4_11_9, RMII0_CRS_DV_A, SEL_RMII_0),
-	PINMUX_IPSR_DATA(IP4_11_9, ET0_CRS),
+	PINMUX_IPSR_GPSR(IP4_11_9, ET0_CRS),
 
 	PINMUX_IPSR_MSEL(IP4_14_12, HTX0_A, SEL_HSCIF_0),
 	PINMUX_IPSR_MSEL(IP4_14_12, TX1_A, SEL_SCIF1_0),
-	PINMUX_IPSR_DATA(IP4_14_12, VI0_DATA1_VI0_B1),
+	PINMUX_IPSR_GPSR(IP4_14_12, VI0_DATA1_VI0_B1),
 	PINMUX_IPSR_MSEL(IP4_14_12, RMII0_MDC_A, SEL_RMII_0),
-	PINMUX_IPSR_DATA(IP4_14_12, ET0_COL),
+	PINMUX_IPSR_GPSR(IP4_14_12, ET0_COL),
 
 	PINMUX_IPSR_MSEL(IP4_17_15, CTS0_B, SEL_SCIF0_1),
-	PINMUX_IPSR_DATA(IP4_17_15, VI0_DATA2_VI0_B2),
+	PINMUX_IPSR_GPSR(IP4_17_15, VI0_DATA2_VI0_B2),
 	PINMUX_IPSR_MSEL(IP4_17_15, RMII0_MDIO_A, SEL_RMII_0),
-	PINMUX_IPSR_DATA(IP4_17_15, ET0_MDC),
+	PINMUX_IPSR_GPSR(IP4_17_15, ET0_MDC),
 
 	PINMUX_IPSR_MSEL(IP4_19_18, RTS0_B, SEL_SCIF0_1),
-	PINMUX_IPSR_DATA(IP4_19_18, VI0_DATA3_VI0_B3),
+	PINMUX_IPSR_GPSR(IP4_19_18, VI0_DATA3_VI0_B3),
 	PINMUX_IPSR_MSEL(IP4_19_18, ET0_MDIO_A, SEL_ET0_0),
 
 	PINMUX_IPSR_MSEL(IP4_21_20, SCK1_B, SEL_SCIF1_1),
-	PINMUX_IPSR_DATA(IP4_21_20, VI0_DATA4_VI0_B4),
+	PINMUX_IPSR_GPSR(IP4_21_20, VI0_DATA4_VI0_B4),
 	PINMUX_IPSR_MSEL(IP4_21_20, ET0_LINK_A, SEL_ET0_CTL_0),
 
 	PINMUX_IPSR_MSEL(IP4_23_22, RX1_B, SEL_SCIF1_1),
-	PINMUX_IPSR_DATA(IP4_23_22, VI0_DATA5_VI0_B5),
+	PINMUX_IPSR_GPSR(IP4_23_22, VI0_DATA5_VI0_B5),
 	PINMUX_IPSR_MSEL(IP4_23_22, ET0_MAGIC_A, SEL_ET0_CTL_0),
 
 	PINMUX_IPSR_MSEL(IP4_25_24, TX1_B, SEL_SCIF1_1),
-	PINMUX_IPSR_DATA(IP4_25_24, VI0_DATA6_VI0_G0),
+	PINMUX_IPSR_GPSR(IP4_25_24, VI0_DATA6_VI0_G0),
 	PINMUX_IPSR_MSEL(IP4_25_24, ET0_PHY_INT_A, SEL_ET0_CTL_0),
 
 	PINMUX_IPSR_MSEL(IP4_27_26, CTS1_B, SEL_SCIF1_1),
-	PINMUX_IPSR_DATA(IP4_27_26, VI0_DATA7_VI0_G1),
+	PINMUX_IPSR_GPSR(IP4_27_26, VI0_DATA7_VI0_G1),
 
 	PINMUX_IPSR_MSEL(IP4_29_28, RTS1_B, SEL_SCIF1_1),
-	PINMUX_IPSR_DATA(IP4_29_28, VI0_G2),
+	PINMUX_IPSR_GPSR(IP4_29_28, VI0_G2),
 
 	PINMUX_IPSR_MSEL(IP4_31_30, SCK2_A, SEL_SCIF2_0),
-	PINMUX_IPSR_DATA(IP4_31_30, VI0_G3),
+	PINMUX_IPSR_GPSR(IP4_31_30, VI0_G3),
 
 	/* IPSR5 */
 	PINMUX_IPSR_MSEL(IP5_2_0, SD2_CLK_A, SEL_SDHI2_0),
 	PINMUX_IPSR_MSEL(IP5_2_0, RX2_A, SEL_SCIF2_0),
-	PINMUX_IPSR_DATA(IP5_2_0, VI0_G4),
+	PINMUX_IPSR_GPSR(IP5_2_0, VI0_G4),
 	PINMUX_IPSR_MSEL(IP5_2_0, ET0_RX_CLK_B, SEL_ET0_1),
 
 	PINMUX_IPSR_MSEL(IP5_5_3, SD2_CMD_A, SEL_SDHI2_0),
 	PINMUX_IPSR_MSEL(IP5_5_3, TX2_A, SEL_SCIF2_0),
-	PINMUX_IPSR_DATA(IP5_5_3, VI0_G5),
+	PINMUX_IPSR_GPSR(IP5_5_3, VI0_G5),
 	PINMUX_IPSR_MSEL(IP5_5_3, ET0_ERXD2_B, SEL_ET0_1),
 
 	PINMUX_IPSR_MSEL(IP5_8_6, SD2_DAT0_A, SEL_SDHI2_0),
 	PINMUX_IPSR_MSEL(IP5_8_6, RX3_A, SEL_SCIF3_0),
-	PINMUX_IPSR_DATA(IP4_8_6, VI0_R0),
+	PINMUX_IPSR_GPSR(IP4_8_6, VI0_R0),
 	PINMUX_IPSR_MSEL(IP4_8_6, ET0_ERXD2_B, SEL_ET0_1),
 
 	PINMUX_IPSR_MSEL(IP5_11_9, SD2_DAT1_A, SEL_SDHI2_0),
 	PINMUX_IPSR_MSEL(IP5_11_9, TX3_A, SEL_SCIF3_0),
-	PINMUX_IPSR_DATA(IP5_11_9, VI0_R1),
+	PINMUX_IPSR_GPSR(IP5_11_9, VI0_R1),
 	PINMUX_IPSR_MSEL(IP5_11_9, ET0_MDIO_B, SEL_ET0_1),
 
 	PINMUX_IPSR_MSEL(IP5_14_12, SD2_DAT2_A, SEL_SDHI2_0),
 	PINMUX_IPSR_MSEL(IP5_14_12, RX4_A, SEL_SCIF4_0),
-	PINMUX_IPSR_DATA(IP5_14_12, VI0_R2),
+	PINMUX_IPSR_GPSR(IP5_14_12, VI0_R2),
 	PINMUX_IPSR_MSEL(IP5_14_12, ET0_LINK_B, SEL_ET0_CTL_1),
 
 	PINMUX_IPSR_MSEL(IP5_17_15, SD2_DAT3_A, SEL_SDHI2_0),
 	PINMUX_IPSR_MSEL(IP5_17_15, TX4_A, SEL_SCIF4_0),
-	PINMUX_IPSR_DATA(IP5_17_15, VI0_R3),
+	PINMUX_IPSR_GPSR(IP5_17_15, VI0_R3),
 	PINMUX_IPSR_MSEL(IP5_17_15, ET0_MAGIC_B, SEL_ET0_CTL_1),
 
 	PINMUX_IPSR_MSEL(IP5_20_18, SD2_CD_A, SEL_SDHI2_0),
 	PINMUX_IPSR_MSEL(IP5_20_18, RX5_A, SEL_SCIF5_0),
-	PINMUX_IPSR_DATA(IP5_20_18, VI0_R4),
+	PINMUX_IPSR_GPSR(IP5_20_18, VI0_R4),
 	PINMUX_IPSR_MSEL(IP5_20_18, ET0_PHY_INT_B, SEL_ET0_CTL_1),
 
 	PINMUX_IPSR_MSEL(IP5_22_21, SD2_WP_A, SEL_SDHI2_0),
 	PINMUX_IPSR_MSEL(IP5_22_21, TX5_A, SEL_SCIF5_0),
-	PINMUX_IPSR_DATA(IP5_22_21, VI0_R5),
+	PINMUX_IPSR_GPSR(IP5_22_21, VI0_R5),
 
-	PINMUX_IPSR_DATA(IP5_24_23, REF125CK),
-	PINMUX_IPSR_DATA(IP5_24_23, ADTRG),
+	PINMUX_IPSR_GPSR(IP5_24_23, REF125CK),
+	PINMUX_IPSR_GPSR(IP5_24_23, ADTRG),
 	PINMUX_IPSR_MSEL(IP5_24_23, RX5_C, SEL_SCIF5_2),
-	PINMUX_IPSR_DATA(IP5_26_25, REF50CK),
+	PINMUX_IPSR_GPSR(IP5_26_25, REF50CK),
 	PINMUX_IPSR_MSEL(IP5_26_25, CTS1_E, SEL_SCIF1_3),
 	PINMUX_IPSR_MSEL(IP5_26_25, HCTS0_D, SEL_HSCIF_3),
 
 	/* IPSR6 */
-	PINMUX_IPSR_DATA(IP6_2_0, DU0_DR0),
+	PINMUX_IPSR_GPSR(IP6_2_0, DU0_DR0),
 	PINMUX_IPSR_MSEL(IP6_2_0, SCIF_CLK_B, SEL_SCIF_CLK_1),
 	PINMUX_IPSR_MSEL(IP6_2_0, HRX0_D, SEL_HSCIF_3),
 	PINMUX_IPSR_MSEL(IP6_2_0, IETX_A, SEL_IEBUS_0),
 	PINMUX_IPSR_MSEL(IP6_2_0, TCLKA_A, SEL_MTU2_CLK_0),
-	PINMUX_IPSR_DATA(IP6_2_0, HIFD00),
+	PINMUX_IPSR_GPSR(IP6_2_0, HIFD00),
 
-	PINMUX_IPSR_DATA(IP6_5_3, DU0_DR1),
+	PINMUX_IPSR_GPSR(IP6_5_3, DU0_DR1),
 	PINMUX_IPSR_MSEL(IP6_5_3, SCK0_B, SEL_SCIF0_1),
 	PINMUX_IPSR_MSEL(IP6_5_3, HTX0_D, SEL_HSCIF_3),
 	PINMUX_IPSR_MSEL(IP6_5_3, IERX_A, SEL_IEBUS_0),
 	PINMUX_IPSR_MSEL(IP6_5_3, TCLKB_A, SEL_MTU2_CLK_0),
-	PINMUX_IPSR_DATA(IP6_5_3, HIFD01),
+	PINMUX_IPSR_GPSR(IP6_5_3, HIFD01),
 
-	PINMUX_IPSR_DATA(IP6_7_6, DU0_DR2),
+	PINMUX_IPSR_GPSR(IP6_7_6, DU0_DR2),
 	PINMUX_IPSR_MSEL(IP6_7_6, RX0_B, SEL_SCIF0_1),
 	PINMUX_IPSR_MSEL(IP6_7_6, TCLKC_A, SEL_MTU2_CLK_0),
-	PINMUX_IPSR_DATA(IP6_7_6, HIFD02),
+	PINMUX_IPSR_GPSR(IP6_7_6, HIFD02),
 
-	PINMUX_IPSR_DATA(IP6_9_8, DU0_DR3),
+	PINMUX_IPSR_GPSR(IP6_9_8, DU0_DR3),
 	PINMUX_IPSR_MSEL(IP6_9_8, TX0_B, SEL_SCIF0_1),
 	PINMUX_IPSR_MSEL(IP6_9_8, TCLKD_A, SEL_MTU2_CLK_0),
-	PINMUX_IPSR_DATA(IP6_9_8, HIFD03),
+	PINMUX_IPSR_GPSR(IP6_9_8, HIFD03),
 
-	PINMUX_IPSR_DATA(IP6_11_10, DU0_DR4),
+	PINMUX_IPSR_GPSR(IP6_11_10, DU0_DR4),
 	PINMUX_IPSR_MSEL(IP6_11_10, CTS0_C, SEL_SCIF0_2),
 	PINMUX_IPSR_MSEL(IP6_11_10, TIOC0A_A, SEL_MTU2_CH0_0),
-	PINMUX_IPSR_DATA(IP6_11_10, HIFD04),
+	PINMUX_IPSR_GPSR(IP6_11_10, HIFD04),
 
-	PINMUX_IPSR_DATA(IP6_13_12, DU0_DR5),
+	PINMUX_IPSR_GPSR(IP6_13_12, DU0_DR5),
 	PINMUX_IPSR_MSEL(IP6_13_12, RTS0_C, SEL_SCIF0_1),
 	PINMUX_IPSR_MSEL(IP6_13_12, TIOC0B_A, SEL_MTU2_CH0_0),
-	PINMUX_IPSR_DATA(IP6_13_12, HIFD05),
+	PINMUX_IPSR_GPSR(IP6_13_12, HIFD05),
 
-	PINMUX_IPSR_DATA(IP6_15_14, DU0_DR6),
+	PINMUX_IPSR_GPSR(IP6_15_14, DU0_DR6),
 	PINMUX_IPSR_MSEL(IP6_15_14, SCK1_C, SEL_SCIF1_2),
 	PINMUX_IPSR_MSEL(IP6_15_14, TIOC0C_A, SEL_MTU2_CH0_0),
-	PINMUX_IPSR_DATA(IP6_15_14, HIFD06),
+	PINMUX_IPSR_GPSR(IP6_15_14, HIFD06),
 
-	PINMUX_IPSR_DATA(IP6_17_16, DU0_DR7),
+	PINMUX_IPSR_GPSR(IP6_17_16, DU0_DR7),
 	PINMUX_IPSR_MSEL(IP6_17_16, RX1_C, SEL_SCIF1_2),
 	PINMUX_IPSR_MSEL(IP6_17_16, TIOC0D_A, SEL_MTU2_CH0_0),
-	PINMUX_IPSR_DATA(IP6_17_16, HIFD07),
+	PINMUX_IPSR_GPSR(IP6_17_16, HIFD07),
 
-	PINMUX_IPSR_DATA(IP6_20_18, DU0_DG0),
+	PINMUX_IPSR_GPSR(IP6_20_18, DU0_DG0),
 	PINMUX_IPSR_MSEL(IP6_20_18, TX1_C, SEL_SCIF1_2),
 	PINMUX_IPSR_MSEL(IP6_20_18, HSCK0_D, SEL_HSCIF_3),
 	PINMUX_IPSR_MSEL(IP6_20_18, IECLK_A, SEL_IEBUS_0),
 	PINMUX_IPSR_MSEL(IP6_20_18, TIOC1A_A, SEL_MTU2_CH1_0),
-	PINMUX_IPSR_DATA(IP6_20_18, HIFD08),
+	PINMUX_IPSR_GPSR(IP6_20_18, HIFD08),
 
-	PINMUX_IPSR_DATA(IP6_23_21, DU0_DG1),
+	PINMUX_IPSR_GPSR(IP6_23_21, DU0_DG1),
 	PINMUX_IPSR_MSEL(IP6_23_21, CTS1_C, SEL_SCIF1_2),
 	PINMUX_IPSR_MSEL(IP6_23_21, HRTS0_D, SEL_HSCIF_3),
 	PINMUX_IPSR_MSEL(IP6_23_21, TIOC1B_A, SEL_MTU2_CH1_0),
-	PINMUX_IPSR_DATA(IP6_23_21, HIFD09),
+	PINMUX_IPSR_GPSR(IP6_23_21, HIFD09),
 
 	/* IPSR7 */
-	PINMUX_IPSR_DATA(IP7_2_0, DU0_DG2),
+	PINMUX_IPSR_GPSR(IP7_2_0, DU0_DG2),
 	PINMUX_IPSR_MSEL(IP7_2_0, RTS1_C, SEL_SCIF1_2),
 	PINMUX_IPSR_MSEL(IP7_2_0, RMII0_MDC_B, SEL_RMII_1),
 	PINMUX_IPSR_MSEL(IP7_2_0, TIOC2A_A, SEL_MTU2_CH2_0),
-	PINMUX_IPSR_DATA(IP7_2_0, HIFD10),
+	PINMUX_IPSR_GPSR(IP7_2_0, HIFD10),
 
-	PINMUX_IPSR_DATA(IP7_5_3, DU0_DG3),
+	PINMUX_IPSR_GPSR(IP7_5_3, DU0_DG3),
 	PINMUX_IPSR_MSEL(IP7_5_3, SCK2_C, SEL_SCIF2_2),
 	PINMUX_IPSR_MSEL(IP7_5_3, RMII0_MDIO_B, SEL_RMII_1),
 	PINMUX_IPSR_MSEL(IP7_5_3, TIOC2B_A, SEL_MTU2_CH2_0),
-	PINMUX_IPSR_DATA(IP7_5_3, HIFD11),
+	PINMUX_IPSR_GPSR(IP7_5_3, HIFD11),
 
-	PINMUX_IPSR_DATA(IP7_8_6, DU0_DG4),
+	PINMUX_IPSR_GPSR(IP7_8_6, DU0_DG4),
 	PINMUX_IPSR_MSEL(IP7_8_6, RX2_C, SEL_SCIF2_2),
 	PINMUX_IPSR_MSEL(IP7_8_6, RMII0_CRS_DV_B, SEL_RMII_1),
 	PINMUX_IPSR_MSEL(IP7_8_6, TIOC3A_A, SEL_MTU2_CH3_0),
-	PINMUX_IPSR_DATA(IP7_8_6, HIFD12),
+	PINMUX_IPSR_GPSR(IP7_8_6, HIFD12),
 
-	PINMUX_IPSR_DATA(IP7_11_9, DU0_DG5),
+	PINMUX_IPSR_GPSR(IP7_11_9, DU0_DG5),
 	PINMUX_IPSR_MSEL(IP7_11_9, TX2_C, SEL_SCIF2_2),
 	PINMUX_IPSR_MSEL(IP7_11_9, RMII0_RX_ER_B, SEL_RMII_1),
 	PINMUX_IPSR_MSEL(IP7_11_9, TIOC3B_A, SEL_MTU2_CH3_0),
-	PINMUX_IPSR_DATA(IP7_11_9, HIFD13),
+	PINMUX_IPSR_GPSR(IP7_11_9, HIFD13),
 
-	PINMUX_IPSR_DATA(IP7_14_12, DU0_DG6),
+	PINMUX_IPSR_GPSR(IP7_14_12, DU0_DG6),
 	PINMUX_IPSR_MSEL(IP7_14_12, RX3_C, SEL_SCIF3_2),
 	PINMUX_IPSR_MSEL(IP7_14_12, RMII0_RXD0_B, SEL_RMII_1),
 	PINMUX_IPSR_MSEL(IP7_14_12, TIOC3C_A, SEL_MTU2_CH3_0),
-	PINMUX_IPSR_DATA(IP7_14_12, HIFD14),
+	PINMUX_IPSR_GPSR(IP7_14_12, HIFD14),
 
-	PINMUX_IPSR_DATA(IP7_17_15, DU0_DG7),
+	PINMUX_IPSR_GPSR(IP7_17_15, DU0_DG7),
 	PINMUX_IPSR_MSEL(IP7_17_15, TX3_C, SEL_SCIF3_2),
 	PINMUX_IPSR_MSEL(IP7_17_15, RMII0_RXD1_B, SEL_RMII_1),
 	PINMUX_IPSR_MSEL(IP7_17_15, TIOC3D_A, SEL_MTU2_CH3_0),
-	PINMUX_IPSR_DATA(IP7_17_15, HIFD15),
+	PINMUX_IPSR_GPSR(IP7_17_15, HIFD15),
 
-	PINMUX_IPSR_DATA(IP7_20_18, DU0_DB0),
+	PINMUX_IPSR_GPSR(IP7_20_18, DU0_DB0),
 	PINMUX_IPSR_MSEL(IP7_20_18, RX4_C, SEL_SCIF4_2),
 	PINMUX_IPSR_MSEL(IP7_20_18, RMII0_TXD_EN_B, SEL_RMII_1),
 	PINMUX_IPSR_MSEL(IP7_20_18, TIOC4A_A, SEL_MTU2_CH4_0),
-	PINMUX_IPSR_DATA(IP7_20_18, HIFCS),
+	PINMUX_IPSR_GPSR(IP7_20_18, HIFCS),
 
-	PINMUX_IPSR_DATA(IP7_23_21, DU0_DB1),
+	PINMUX_IPSR_GPSR(IP7_23_21, DU0_DB1),
 	PINMUX_IPSR_MSEL(IP7_23_21, TX4_C, SEL_SCIF4_2),
 	PINMUX_IPSR_MSEL(IP7_23_21, RMII0_TXD0_B, SEL_RMII_1),
 	PINMUX_IPSR_MSEL(IP7_23_21, TIOC4B_A, SEL_MTU2_CH4_0),
-	PINMUX_IPSR_DATA(IP7_23_21, HIFWR),
+	PINMUX_IPSR_GPSR(IP7_23_21, HIFWR),
 
-	PINMUX_IPSR_DATA(IP7_26_24, DU0_DB2),
+	PINMUX_IPSR_GPSR(IP7_26_24, DU0_DB2),
 	PINMUX_IPSR_MSEL(IP7_26_24, RX5_B, SEL_SCIF5_1),
 	PINMUX_IPSR_MSEL(IP7_26_24, RMII0_TXD1_B, SEL_RMII_1),
 	PINMUX_IPSR_MSEL(IP7_26_24, TIOC4C_A, SEL_MTU2_CH4_0),
 
-	PINMUX_IPSR_DATA(IP7_28_27, DU0_DB3),
+	PINMUX_IPSR_GPSR(IP7_28_27, DU0_DB3),
 	PINMUX_IPSR_MSEL(IP7_28_27, TX5_B, SEL_SCIF5_1),
 	PINMUX_IPSR_MSEL(IP7_28_27, TIOC4D_A, SEL_MTU2_CH4_0),
-	PINMUX_IPSR_DATA(IP7_28_27, HIFRD),
+	PINMUX_IPSR_GPSR(IP7_28_27, HIFRD),
 
-	PINMUX_IPSR_DATA(IP7_30_29, DU0_DB4),
-	PINMUX_IPSR_DATA(IP7_30_29, HIFINT),
+	PINMUX_IPSR_GPSR(IP7_30_29, DU0_DB4),
+	PINMUX_IPSR_GPSR(IP7_30_29, HIFINT),
 
 	/* IPSR8 */
-	PINMUX_IPSR_DATA(IP8_1_0, DU0_DB5),
-	PINMUX_IPSR_DATA(IP8_1_0, HIFDREQ),
+	PINMUX_IPSR_GPSR(IP8_1_0, DU0_DB5),
+	PINMUX_IPSR_GPSR(IP8_1_0, HIFDREQ),
 
-	PINMUX_IPSR_DATA(IP8_3_2, DU0_DB6),
-	PINMUX_IPSR_DATA(IP8_3_2, HIFRDY),
+	PINMUX_IPSR_GPSR(IP8_3_2, DU0_DB6),
+	PINMUX_IPSR_GPSR(IP8_3_2, HIFRDY),
 
-	PINMUX_IPSR_DATA(IP8_5_4, DU0_DB7),
+	PINMUX_IPSR_GPSR(IP8_5_4, DU0_DB7),
 	PINMUX_IPSR_MSEL(IP8_5_4, SSI_SCK0_B, SEL_SSI0_1),
 	PINMUX_IPSR_MSEL(IP8_5_4, HIFEBL_B, SEL_HIF_1),
 
-	PINMUX_IPSR_DATA(IP8_7_6, DU0_DOTCLKIN),
+	PINMUX_IPSR_GPSR(IP8_7_6, DU0_DOTCLKIN),
 	PINMUX_IPSR_MSEL(IP8_7_6, HSPI_CS0_C, SEL_HSPI_2),
 	PINMUX_IPSR_MSEL(IP8_7_6, SSI_WS0_B, SEL_SSI0_1),
 
-	PINMUX_IPSR_DATA(IP8_9_8, DU0_DOTCLKOUT),
+	PINMUX_IPSR_GPSR(IP8_9_8, DU0_DOTCLKOUT),
 	PINMUX_IPSR_MSEL(IP8_9_8, HSPI_CLK0_C, SEL_HSPI_2),
 	PINMUX_IPSR_MSEL(IP8_9_8, SSI_SDATA0_B, SEL_SSI0_1),
 
-	PINMUX_IPSR_DATA(IP8_11_10, DU0_EXHSYNC_DU0_HSYNC),
+	PINMUX_IPSR_GPSR(IP8_11_10, DU0_EXHSYNC_DU0_HSYNC),
 	PINMUX_IPSR_MSEL(IP8_11_10, HSPI_TX0_C, SEL_HSPI_2),
 	PINMUX_IPSR_MSEL(IP8_11_10, SSI_SCK1_B, SEL_SSI1_1),
 
-	PINMUX_IPSR_DATA(IP8_13_12, DU0_EXVSYNC_DU0_VSYNC),
+	PINMUX_IPSR_GPSR(IP8_13_12, DU0_EXVSYNC_DU0_VSYNC),
 	PINMUX_IPSR_MSEL(IP8_13_12, HSPI_RX0_C, SEL_HSPI_2),
 	PINMUX_IPSR_MSEL(IP8_13_12, SSI_WS1_B, SEL_SSI1_1),
 
-	PINMUX_IPSR_DATA(IP8_15_14, DU0_EXODDF_DU0_ODDF),
+	PINMUX_IPSR_GPSR(IP8_15_14, DU0_EXODDF_DU0_ODDF),
 	PINMUX_IPSR_MSEL(IP8_15_14, CAN0_RX_B, SEL_RCAN0_1),
 	PINMUX_IPSR_MSEL(IP8_15_14, HSCK0_B, SEL_HSCIF_1),
 	PINMUX_IPSR_MSEL(IP8_15_14, SSI_SDATA1_B, SEL_SSI1_1),
 
-	PINMUX_IPSR_DATA(IP8_17_16, DU0_DISP),
+	PINMUX_IPSR_GPSR(IP8_17_16, DU0_DISP),
 	PINMUX_IPSR_MSEL(IP8_17_16, CAN0_TX_B, SEL_RCAN0_1),
 	PINMUX_IPSR_MSEL(IP8_17_16, HRX0_B, SEL_HSCIF_1),
 	PINMUX_IPSR_MSEL(IP8_17_16, AUDIO_CLKA_B, SEL_AUDIO_CLKA_1),
 
-	PINMUX_IPSR_DATA(IP8_19_18, DU0_CDE),
+	PINMUX_IPSR_GPSR(IP8_19_18, DU0_CDE),
 	PINMUX_IPSR_MSEL(IP8_19_18, HTX0_B, SEL_HSCIF_1),
 	PINMUX_IPSR_MSEL(IP8_19_18, AUDIO_CLKB_B, SEL_AUDIO_CLKB_1),
 	PINMUX_IPSR_MSEL(IP8_19_18, LCD_VCPWC_B, SEL_LCDC_1),
@@ -1139,12 +1139,12 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP8_22_20, IRQ0_A, SEL_INTC_0),
 	PINMUX_IPSR_MSEL(IP8_22_20, HSPI_TX_B, SEL_HSPI_1),
 	PINMUX_IPSR_MSEL(IP8_22_20, RX3_E, SEL_SCIF3_4),
-	PINMUX_IPSR_DATA(IP8_22_20, ET0_ERXD0),
+	PINMUX_IPSR_GPSR(IP8_22_20, ET0_ERXD0),
 
 	PINMUX_IPSR_MSEL(IP8_25_23, IRQ1_A, SEL_INTC_0),
 	PINMUX_IPSR_MSEL(IP8_25_23, HSPI_RX_B, SEL_HSPI_1),
 	PINMUX_IPSR_MSEL(IP8_25_23, TX3_E, SEL_SCIF3_4),
-	PINMUX_IPSR_DATA(IP8_25_23, ET0_ERXD1),
+	PINMUX_IPSR_GPSR(IP8_25_23, ET0_ERXD1),
 
 	PINMUX_IPSR_MSEL(IP8_27_26, IRQ2_A, SEL_INTC_0),
 	PINMUX_IPSR_MSEL(IP8_27_26, CTS0_A, SEL_SCIF0_0),
@@ -1220,26 +1220,26 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP9_29_28, LCD_DATA14_B, SEL_LCDC_1),
 
 	/* IPSE10 */
-	PINMUX_IPSR_DATA(IP10_2_0, SSI_SCK23),
+	PINMUX_IPSR_GPSR(IP10_2_0, SSI_SCK23),
 	PINMUX_IPSR_MSEL(IP10_2_0, VI1_4_B, SEL_VIN1_1),
 	PINMUX_IPSR_MSEL(IP10_2_0, RX1_D, SEL_SCIF1_3),
 	PINMUX_IPSR_MSEL(IP10_2_0, FCLE_B, SEL_FLCTL_1),
 	PINMUX_IPSR_MSEL(IP10_2_0, LCD_DATA15_B, SEL_LCDC_1),
 
-	PINMUX_IPSR_DATA(IP10_5_3, SSI_WS23),
+	PINMUX_IPSR_GPSR(IP10_5_3, SSI_WS23),
 	PINMUX_IPSR_MSEL(IP10_5_3, VI1_5_B, SEL_VIN1_1),
 	PINMUX_IPSR_MSEL(IP10_5_3, TX1_D, SEL_SCIF1_3),
 	PINMUX_IPSR_MSEL(IP10_5_3, HSCK0_C, SEL_HSCIF_2),
 	PINMUX_IPSR_MSEL(IP10_5_3, FALE_B, SEL_FLCTL_1),
 	PINMUX_IPSR_MSEL(IP10_5_3, LCD_DON_B, SEL_LCDC_1),
 
-	PINMUX_IPSR_DATA(IP10_8_6, SSI_SDATA2),
+	PINMUX_IPSR_GPSR(IP10_8_6, SSI_SDATA2),
 	PINMUX_IPSR_MSEL(IP10_8_6, VI1_6_B, SEL_VIN1_1),
 	PINMUX_IPSR_MSEL(IP10_8_6, HRX0_C, SEL_HSCIF_2),
 	PINMUX_IPSR_MSEL(IP10_8_6, FRE_B, SEL_FLCTL_1),
 	PINMUX_IPSR_MSEL(IP10_8_6, LCD_CL1_B, SEL_LCDC_1),
 
-	PINMUX_IPSR_DATA(IP10_11_9, SSI_SDATA3),
+	PINMUX_IPSR_GPSR(IP10_11_9, SSI_SDATA3),
 	PINMUX_IPSR_MSEL(IP10_11_9, VI1_7_B, SEL_VIN1_1),
 	PINMUX_IPSR_MSEL(IP10_11_9, HTX0_C, SEL_HSCIF_2),
 	PINMUX_IPSR_MSEL(IP10_11_9, FWE_B, SEL_FLCTL_1),
@@ -1254,13 +1254,13 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_MSEL(IP10_15, AUDIO_CLKB_A, SEL_AUDIO_CLKB_0),
 	PINMUX_IPSR_MSEL(IP10_15, LCD_CLK_B, SEL_LCDC_1),
 
-	PINMUX_IPSR_DATA(IP10_18_16, AUDIO_CLKC),
+	PINMUX_IPSR_GPSR(IP10_18_16, AUDIO_CLKC),
 	PINMUX_IPSR_MSEL(IP10_18_16, SCK1_E, SEL_SCIF1_4),
 	PINMUX_IPSR_MSEL(IP10_18_16, HCTS0_C, SEL_HSCIF_2),
 	PINMUX_IPSR_MSEL(IP10_18_16, FRB_B, SEL_FLCTL_1),
 	PINMUX_IPSR_MSEL(IP10_18_16, LCD_VEPWC_B, SEL_LCDC_1),
 
-	PINMUX_IPSR_DATA(IP10_21_19, AUDIO_CLKOUT),
+	PINMUX_IPSR_GPSR(IP10_21_19, AUDIO_CLKOUT),
 	PINMUX_IPSR_MSEL(IP10_21_19, TX1_E, SEL_SCIF1_4),
 	PINMUX_IPSR_MSEL(IP10_21_19, HRTS0_C, SEL_HSCIF_2),
 	PINMUX_IPSR_MSEL(IP10_21_19, FSE_B, SEL_FLCTL_1),
@@ -1271,85 +1271,85 @@ static const u16 pinmux_data[] = {
 
 	PINMUX_IPSR_MSEL(IP10_24_23, CAN0_TX_A, SEL_RCAN0_0),
 	PINMUX_IPSR_MSEL(IP10_24_23, TX4_D, SEL_SCIF4_3),
-	PINMUX_IPSR_DATA(IP10_24_23, MLB_CLK),
+	PINMUX_IPSR_GPSR(IP10_24_23, MLB_CLK),
 
 	PINMUX_IPSR_MSEL(IP10_25, CAN1_RX_A, SEL_RCAN1_0),
 	PINMUX_IPSR_MSEL(IP10_25, IRQ1_B, SEL_INTC_1),
 
 	PINMUX_IPSR_MSEL(IP10_27_26, CAN0_RX_A, SEL_RCAN0_0),
 	PINMUX_IPSR_MSEL(IP10_27_26, IRQ0_B, SEL_INTC_1),
-	PINMUX_IPSR_DATA(IP10_27_26, MLB_SIG),
+	PINMUX_IPSR_GPSR(IP10_27_26, MLB_SIG),
 
 	PINMUX_IPSR_MSEL(IP10_29_28, CAN1_TX_A, SEL_RCAN1_0),
 	PINMUX_IPSR_MSEL(IP10_29_28, TX5_C, SEL_SCIF1_2),
-	PINMUX_IPSR_DATA(IP10_29_28, MLB_DAT),
+	PINMUX_IPSR_GPSR(IP10_29_28, MLB_DAT),
 
 	/* IPSR11 */
-	PINMUX_IPSR_DATA(IP11_0, SCL1),
+	PINMUX_IPSR_GPSR(IP11_0, SCL1),
 	PINMUX_IPSR_MSEL(IP11_0, SCIF_CLK_C, SEL_SCIF_CLK_2),
 
-	PINMUX_IPSR_DATA(IP11_1, SDA1),
+	PINMUX_IPSR_GPSR(IP11_1, SDA1),
 	PINMUX_IPSR_MSEL(IP11_0, RX1_E, SEL_SCIF1_4),
 
-	PINMUX_IPSR_DATA(IP11_2, SDA0),
+	PINMUX_IPSR_GPSR(IP11_2, SDA0),
 	PINMUX_IPSR_MSEL(IP11_2, HIFEBL_A, SEL_HIF_0),
 
-	PINMUX_IPSR_DATA(IP11_3, SDSELF),
+	PINMUX_IPSR_GPSR(IP11_3, SDSELF),
 	PINMUX_IPSR_MSEL(IP11_3, RTS1_E, SEL_SCIF1_3),
 
 	PINMUX_IPSR_MSEL(IP11_6_4, SCIF_CLK_A, SEL_SCIF_CLK_0),
 	PINMUX_IPSR_MSEL(IP11_6_4, HSPI_CLK_A, SEL_HSPI_0),
-	PINMUX_IPSR_DATA(IP11_6_4, VI0_CLK),
+	PINMUX_IPSR_GPSR(IP11_6_4, VI0_CLK),
 	PINMUX_IPSR_MSEL(IP11_6_4, RMII0_TXD0_A, SEL_RMII_0),
-	PINMUX_IPSR_DATA(IP11_6_4, ET0_ERXD4),
+	PINMUX_IPSR_GPSR(IP11_6_4, ET0_ERXD4),
 
 	PINMUX_IPSR_MSEL(IP11_9_7, SCK0_A, SEL_SCIF0_0),
 	PINMUX_IPSR_MSEL(IP11_9_7, HSPI_CS_A, SEL_HSPI_0),
-	PINMUX_IPSR_DATA(IP11_9_7, VI0_CLKENB),
+	PINMUX_IPSR_GPSR(IP11_9_7, VI0_CLKENB),
 	PINMUX_IPSR_MSEL(IP11_9_7, RMII0_TXD1_A, SEL_RMII_0),
-	PINMUX_IPSR_DATA(IP11_9_7, ET0_ERXD5),
+	PINMUX_IPSR_GPSR(IP11_9_7, ET0_ERXD5),
 
 	PINMUX_IPSR_MSEL(IP11_11_10, RX0_A, SEL_SCIF0_0),
 	PINMUX_IPSR_MSEL(IP11_11_10, HSPI_RX_A, SEL_HSPI_0),
 	PINMUX_IPSR_MSEL(IP11_11_10, RMII0_RXD0_A, SEL_RMII_0),
-	PINMUX_IPSR_DATA(IP11_11_10, ET0_ERXD6),
+	PINMUX_IPSR_GPSR(IP11_11_10, ET0_ERXD6),
 
 	PINMUX_IPSR_MSEL(IP11_12, TX0_A, SEL_SCIF0_0),
 	PINMUX_IPSR_MSEL(IP11_12, HSPI_TX_A, SEL_HSPI_0),
 
-	PINMUX_IPSR_DATA(IP11_15_13, PENC1),
+	PINMUX_IPSR_GPSR(IP11_15_13, PENC1),
 	PINMUX_IPSR_MSEL(IP11_15_13, TX3_D, SEL_SCIF3_3),
 	PINMUX_IPSR_MSEL(IP11_15_13, CAN1_TX_B,  SEL_RCAN1_1),
 	PINMUX_IPSR_MSEL(IP11_15_13, TX5_D, SEL_SCIF5_3),
 	PINMUX_IPSR_MSEL(IP11_15_13, IETX_B, SEL_IEBUS_1),
 
-	PINMUX_IPSR_DATA(IP11_18_16, USB_OVC1),
+	PINMUX_IPSR_GPSR(IP11_18_16, USB_OVC1),
 	PINMUX_IPSR_MSEL(IP11_18_16, RX3_D, SEL_SCIF3_3),
 	PINMUX_IPSR_MSEL(IP11_18_16, CAN1_RX_B, SEL_RCAN1_1),
 	PINMUX_IPSR_MSEL(IP11_18_16, RX5_D, SEL_SCIF5_3),
 	PINMUX_IPSR_MSEL(IP11_18_16, IERX_B, SEL_IEBUS_1),
 
-	PINMUX_IPSR_DATA(IP11_20_19, DREQ0),
+	PINMUX_IPSR_GPSR(IP11_20_19, DREQ0),
 	PINMUX_IPSR_MSEL(IP11_20_19, SD1_CLK_A, SEL_SDHI1_0),
-	PINMUX_IPSR_DATA(IP11_20_19, ET0_TX_EN),
+	PINMUX_IPSR_GPSR(IP11_20_19, ET0_TX_EN),
 
-	PINMUX_IPSR_DATA(IP11_22_21, DACK0),
+	PINMUX_IPSR_GPSR(IP11_22_21, DACK0),
 	PINMUX_IPSR_MSEL(IP11_22_21, SD1_DAT3_A, SEL_SDHI1_0),
-	PINMUX_IPSR_DATA(IP11_22_21, ET0_TX_ER),
+	PINMUX_IPSR_GPSR(IP11_22_21, ET0_TX_ER),
 
-	PINMUX_IPSR_DATA(IP11_25_23, DREQ1),
+	PINMUX_IPSR_GPSR(IP11_25_23, DREQ1),
 	PINMUX_IPSR_MSEL(IP11_25_23, HSPI_CLK_B, SEL_HSPI_1),
 	PINMUX_IPSR_MSEL(IP11_25_23, RX4_B, SEL_SCIF4_1),
 	PINMUX_IPSR_MSEL(IP11_25_23, ET0_PHY_INT_C, SEL_ET0_CTL_0),
 	PINMUX_IPSR_MSEL(IP11_25_23, ET0_TX_CLK_A, SEL_ET0_0),
 
-	PINMUX_IPSR_DATA(IP11_27_26, DACK1),
+	PINMUX_IPSR_GPSR(IP11_27_26, DACK1),
 	PINMUX_IPSR_MSEL(IP11_27_26, HSPI_CS_B, SEL_HSPI_1),
 	PINMUX_IPSR_MSEL(IP11_27_26, TX4_B, SEL_SCIF3_1),
 	PINMUX_IPSR_MSEL(IP11_27_26, ET0_RX_CLK_A, SEL_ET0_0),
 
-	PINMUX_IPSR_DATA(IP11_28, PRESETOUT),
-	PINMUX_IPSR_DATA(IP11_28, ST_CLKOUT),
+	PINMUX_IPSR_GPSR(IP11_28, PRESETOUT),
+	PINMUX_IPSR_GPSR(IP11_28, ST_CLKOUT),
 };
 
 static const struct sh_pfc_pin pinmux_pins[] = {
diff --git a/drivers/pinctrl/sh-pfc/sh_pfc.h b/drivers/pinctrl/sh-pfc/sh_pfc.h
index 2123ab49d6a5..a490834e2089 100644
--- a/drivers/pinctrl/sh-pfc/sh_pfc.h
+++ b/drivers/pinctrl/sh-pfc/sh_pfc.h
@@ -100,10 +100,31 @@ struct pinmux_cfg_reg {
 	const u8 *var_field_width;
 };
 
+/*
+ * Describe a config register consisting of several fields of the same width
+ *   - name: Register name (unused, for documentation purposes only)
+ *   - r: Physical register address
+ *   - r_width: Width of the register (in bits)
+ *   - f_width: Width of the fixed-width register fields (in bits)
+ * This macro must be followed by initialization data: For each register field
+ * (from left to right, i.e. MSB to LSB), 2^f_width enum IDs must be specified,
+ * one for each possible combination of the register field bit values.
+ */
 #define PINMUX_CFG_REG(name, r, r_width, f_width) \
 	.reg = r, .reg_width = r_width, .field_width = f_width,		\
 	.enum_ids = (const u16 [(r_width / f_width) * (1 << f_width)])
 
+/*
+ * Describe a config register consisting of several fields of different widths
+ *   - name: Register name (unused, for documentation purposes only)
+ *   - r: Physical register address
+ *   - r_width: Width of the register (in bits)
+ *   - var_fw0, var_fwn...: List of widths of the register fields (in bits),
+ *                          From left to right (i.e. MSB to LSB)
+ * This macro must be followed by initialization data: For each register field
+ * (from left to right, i.e. MSB to LSB), 2^var_fwi enum IDs must be specified,
+ * one for each possible combination of the register field bit values.
+ */
 #define PINMUX_CFG_REG_VAR(name, r, r_width, var_fw0, var_fwn...) \
 	.reg = r, .reg_width = r_width,	\
 	.var_field_width = (const u8 [r_width]) \
@@ -116,6 +137,14 @@ struct pinmux_data_reg {
 	const u16 *enum_ids;
 };
 
+/*
+ * Describe a data register
+ *   - name: Register name (unused, for documentation purposes only)
+ *   - r: Physical register address
+ *   - r_width: Width of the register (in bits)
+ * This macro must be followed by initialization data: For each register bit
+ * (from left to right, i.e. MSB to LSB), one enum ID must be specified.
+ */
 #define PINMUX_DATA_REG(name, r, r_width) \
 	.reg = r, .reg_width = r_width,	\
 	.enum_ids = (const u16 [r_width]) \
@@ -124,6 +153,10 @@ struct pinmux_irq {
 	const short *gpios;
 };
 
+/*
+ * Describe the mapping from GPIOs to a single IRQ
+ *   - ids...: List of GPIOs that are mapped to the same IRQ
+ */
 #define PINMUX_IRQ(ids...)			   \
 	{ .gpios = (const short []) { ids, -1 } }
 
@@ -185,18 +218,65 @@ struct sh_pfc_soc_info {
  * sh_pfc_soc_info pinmux_data array macros
  */
 
+/*
+ * Describe generic pinmux data
+ *   - data_or_mark: *_DATA or *_MARK enum ID
+ *   - ids...: List of enum IDs to associate with data_or_mark
+ */
 #define PINMUX_DATA(data_or_mark, ids...)	data_or_mark, ids, 0
 
-#define PINMUX_IPSR_NOGP(ispr, fn)					\
+/*
+ * Describe a pinmux configuration without GPIO function that needs
+ * configuration in a Peripheral Function Select Register (IPSR)
+ *   - ipsr: IPSR field (unused, for documentation purposes only)
+ *   - fn: Function name, referring to a field in the IPSR
+ */
+#define PINMUX_IPSR_NOGP(ipsr, fn)					\
 	PINMUX_DATA(fn##_MARK, FN_##fn)
-#define PINMUX_IPSR_DATA(ipsr, fn)					\
+
+/*
+ * Describe a pinmux configuration with GPIO function that needs configuration
+ * in both a Peripheral Function Select Register (IPSR) and in a
+ * GPIO/Peripheral Function Select Register (GPSR)
+ *   - ipsr: IPSR field
+ *   - fn: Function name, also referring to the IPSR field
+ */
+#define PINMUX_IPSR_GPSR(ipsr, fn)					\
 	PINMUX_DATA(fn##_MARK, FN_##fn, FN_##ipsr)
-#define PINMUX_IPSR_NOGM(ispr, fn, ms)					\
-	PINMUX_DATA(fn##_MARK, FN_##fn, FN_##ms)
-#define PINMUX_IPSR_NOFN(ipsr, fn, ms)					\
-	PINMUX_DATA(fn##_MARK, FN_##ipsr, FN_##ms)
-#define PINMUX_IPSR_MSEL(ipsr, fn, ms)					\
-	PINMUX_DATA(fn##_MARK, FN_##ms, FN_##ipsr, FN_##fn)
+
+/*
+ * Describe a pinmux configuration without GPIO function that needs
+ * configuration in a Peripheral Function Select Register (IPSR), and where the
+ * pinmux function has a representation in a Module Select Register (MOD_SEL).
+ *   - ipsr: IPSR field (unused, for documentation purposes only)
+ *   - fn: Function name, also referring to the IPSR field
+ *   - msel: Module selector
+ */
+#define PINMUX_IPSR_NOGM(ipsr, fn, msel)				\
+	PINMUX_DATA(fn##_MARK, FN_##fn, FN_##msel)
+
+/*
+ * Describe a pinmux configuration with GPIO function where the pinmux function
+ * has no representation in a Peripheral Function Select Register (IPSR), but
+ * instead solely depends on a group selection.
+ *   - gpsr: GPSR field
+ *   - fn: Function name, also referring to the GPSR field
+ *   - gsel: Group selector
+ */
+#define PINMUX_IPSR_NOFN(gpsr, fn, gsel)				\
+	PINMUX_DATA(fn##_MARK, FN_##gpsr, FN_##gsel)
+
+/*
+ * Describe a pinmux configuration with GPIO function that needs configuration
+ * in both a Peripheral Function Select Register (IPSR) and a GPIO/Peripheral
+ * Function Select Register (GPSR), and where the pinmux function has a
+ * representation in a Module Select Register (MOD_SEL).
+ *   - ipsr: IPSR field
+ *   - fn: Function name, also referring to the IPSR field
+ *   - msel: Module selector
+ */
+#define PINMUX_IPSR_MSEL(ipsr, fn, msel)				\
+	PINMUX_DATA(fn##_MARK, FN_##msel, FN_##ipsr, FN_##fn)
 
 /*
  * Describe a pinmux configuration for a single-function pin with GPIO
@@ -381,7 +461,7 @@ struct sh_pfc_soc_info {
 	PINMUX_GPIO_FN(GPIO_FN_##str, PINMUX_FN_BASE, str##_MARK)
 
 /*
- * PORTnCR macro
+ * PORTnCR helper macro for SH-Mobile/R-Mobile
  */
 #define PORTCR(nr, reg)							\
 	{								\
diff --git a/drivers/pinctrl/stm32/Kconfig b/drivers/pinctrl/stm32/Kconfig
new file mode 100644
index 000000000000..0f28841b2332
--- /dev/null
+++ b/drivers/pinctrl/stm32/Kconfig
@@ -0,0 +1,16 @@
+if ARCH_STM32 || COMPILE_TEST
+
+config PINCTRL_STM32
+	bool
+	depends on OF
+	select PINMUX
+	select GENERIC_PINCONF
+	select GPIOLIB
+
+config PINCTRL_STM32F429
+	bool "STMicroelectronics STM32F429 pin control" if COMPILE_TEST && !MACH_STM32F429
+	depends on OF
+	default MACH_STM32F429
+	select PINCTRL_STM32
+
+endif
diff --git a/drivers/pinctrl/stm32/Makefile b/drivers/pinctrl/stm32/Makefile
new file mode 100644
index 000000000000..fc17d4238845
--- /dev/null
+++ b/drivers/pinctrl/stm32/Makefile
@@ -0,0 +1,5 @@
+# Core
+obj-$(CONFIG_PINCTRL_STM32) += pinctrl-stm32.o
+
+# SoC Drivers
+obj-$(CONFIG_PINCTRL_STM32F429)	+= pinctrl-stm32f429.o
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
new file mode 100644
index 000000000000..8deb566ed4cd
--- /dev/null
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -0,0 +1,829 @@
+/*
+ * Copyright (C) Maxime Coquelin 2015
+ * Author:  Maxime Coquelin <mcoquelin.stm32@gmail.com>
+ * License terms:  GNU General Public License (GPL), version 2
+ *
+ * Heavily based on Mediatek's pinctrl driver
+ */
+#include <linux/clk.h>
+#include <linux/gpio/driver.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/pinctrl/machine.h>
+#include <linux/pinctrl/pinconf.h>
+#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinmux.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+#include <linux/slab.h>
+
+#include "../core.h"
+#include "../pinconf.h"
+#include "../pinctrl-utils.h"
+#include "pinctrl-stm32.h"
+
+#define STM32_GPIO_MODER	0x00
+#define STM32_GPIO_TYPER	0x04
+#define STM32_GPIO_SPEEDR	0x08
+#define STM32_GPIO_PUPDR	0x0c
+#define STM32_GPIO_IDR		0x10
+#define STM32_GPIO_ODR		0x14
+#define STM32_GPIO_BSRR		0x18
+#define STM32_GPIO_LCKR		0x1c
+#define STM32_GPIO_AFRL		0x20
+#define STM32_GPIO_AFRH		0x24
+
+#define STM32_GPIO_PINS_PER_BANK 16
+
+#define gpio_range_to_bank(chip) \
+		container_of(chip, struct stm32_gpio_bank, range)
+
+static const char * const stm32_gpio_functions[] = {
+	"gpio", "af0", "af1",
+	"af2", "af3", "af4",
+	"af5", "af6", "af7",
+	"af8", "af9", "af10",
+	"af11", "af12", "af13",
+	"af14", "af15", "analog",
+};
+
+struct stm32_pinctrl_group {
+	const char *name;
+	unsigned long config;
+	unsigned pin;
+};
+
+struct stm32_gpio_bank {
+	void __iomem *base;
+	struct clk *clk;
+	spinlock_t lock;
+	struct gpio_chip gpio_chip;
+	struct pinctrl_gpio_range range;
+};
+
+struct stm32_pinctrl {
+	struct device *dev;
+	struct pinctrl_dev *pctl_dev;
+	struct pinctrl_desc pctl_desc;
+	struct stm32_pinctrl_group *groups;
+	unsigned ngroups;
+	const char **grp_names;
+	struct stm32_gpio_bank *banks;
+	unsigned nbanks;
+	const struct stm32_pinctrl_match_data *match_data;
+};
+
+static inline int stm32_gpio_pin(int gpio)
+{
+	return gpio % STM32_GPIO_PINS_PER_BANK;
+}
+
+static inline u32 stm32_gpio_get_mode(u32 function)
+{
+	switch (function) {
+	case STM32_PIN_GPIO:
+		return 0;
+	case STM32_PIN_AF(0) ... STM32_PIN_AF(15):
+		return 2;
+	case STM32_PIN_ANALOG:
+		return 3;
+	}
+
+	return 0;
+}
+
+static inline u32 stm32_gpio_get_alt(u32 function)
+{
+	switch (function) {
+	case STM32_PIN_GPIO:
+		return 0;
+	case STM32_PIN_AF(0) ... STM32_PIN_AF(15):
+		return function - 1;
+	case STM32_PIN_ANALOG:
+		return 0;
+	}
+
+	return 0;
+}
+
+/* GPIO functions */
+
+static inline void __stm32_gpio_set(struct stm32_gpio_bank *bank,
+	unsigned offset, int value)
+{
+	if (!value)
+		offset += STM32_GPIO_PINS_PER_BANK;
+
+	clk_enable(bank->clk);
+
+	writel_relaxed(BIT(offset), bank->base + STM32_GPIO_BSRR);
+
+	clk_disable(bank->clk);
+}
+
+static int stm32_gpio_request(struct gpio_chip *chip, unsigned offset)
+{
+	return pinctrl_request_gpio(chip->base + offset);
+}
+
+static void stm32_gpio_free(struct gpio_chip *chip, unsigned offset)
+{
+	pinctrl_free_gpio(chip->base + offset);
+}
+
+static int stm32_gpio_get(struct gpio_chip *chip, unsigned offset)
+{
+	struct stm32_gpio_bank *bank = gpiochip_get_data(chip);
+	int ret;
+
+	clk_enable(bank->clk);
+
+	ret = !!(readl_relaxed(bank->base + STM32_GPIO_IDR) & BIT(offset));
+
+	clk_disable(bank->clk);
+
+	return ret;
+}
+
+static void stm32_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
+{
+	struct stm32_gpio_bank *bank = gpiochip_get_data(chip);
+
+	__stm32_gpio_set(bank, offset, value);
+}
+
+static int stm32_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
+{
+	return pinctrl_gpio_direction_input(chip->base + offset);
+}
+
+static int stm32_gpio_direction_output(struct gpio_chip *chip,
+	unsigned offset, int value)
+{
+	struct stm32_gpio_bank *bank = gpiochip_get_data(chip);
+
+	__stm32_gpio_set(bank, offset, value);
+	pinctrl_gpio_direction_output(chip->base + offset);
+
+	return 0;
+}
+
+static struct gpio_chip stm32_gpio_template = {
+	.request		= stm32_gpio_request,
+	.free			= stm32_gpio_free,
+	.get			= stm32_gpio_get,
+	.set			= stm32_gpio_set,
+	.direction_input	= stm32_gpio_direction_input,
+	.direction_output	= stm32_gpio_direction_output,
+};
+
+/* Pinctrl functions */
+
+static struct stm32_pinctrl_group *
+stm32_pctrl_find_group_by_pin(struct stm32_pinctrl *pctl, u32 pin)
+{
+	int i;
+
+	for (i = 0; i < pctl->ngroups; i++) {
+		struct stm32_pinctrl_group *grp = pctl->groups + i;
+
+		if (grp->pin == pin)
+			return grp;
+	}
+
+	return NULL;
+}
+
+static bool stm32_pctrl_is_function_valid(struct stm32_pinctrl *pctl,
+		u32 pin_num, u32 fnum)
+{
+	int i;
+
+	for (i = 0; i < pctl->match_data->npins; i++) {
+		const struct stm32_desc_pin *pin = pctl->match_data->pins + i;
+		const struct stm32_desc_function *func = pin->functions;
+
+		if (pin->pin.number != pin_num)
+			continue;
+
+		while (func && func->name) {
+			if (func->num == fnum)
+				return true;
+			func++;
+		}
+
+		break;
+	}
+
+	return false;
+}
+
+static int stm32_pctrl_dt_node_to_map_func(struct stm32_pinctrl *pctl,
+		u32 pin, u32 fnum, struct stm32_pinctrl_group *grp,
+		struct pinctrl_map **map, unsigned *reserved_maps,
+		unsigned *num_maps)
+{
+	if (*num_maps == *reserved_maps)
+		return -ENOSPC;
+
+	(*map)[*num_maps].type = PIN_MAP_TYPE_MUX_GROUP;
+	(*map)[*num_maps].data.mux.group = grp->name;
+
+	if (!stm32_pctrl_is_function_valid(pctl, pin, fnum)) {
+		dev_err(pctl->dev, "invalid function %d on pin %d .\n",
+				fnum, pin);
+		return -EINVAL;
+	}
+
+	(*map)[*num_maps].data.mux.function = stm32_gpio_functions[fnum];
+	(*num_maps)++;
+
+	return 0;
+}
+
+static int stm32_pctrl_dt_subnode_to_map(struct pinctrl_dev *pctldev,
+				      struct device_node *node,
+				      struct pinctrl_map **map,
+				      unsigned *reserved_maps,
+				      unsigned *num_maps)
+{
+	struct stm32_pinctrl *pctl;
+	struct stm32_pinctrl_group *grp;
+	struct property *pins;
+	u32 pinfunc, pin, func;
+	unsigned long *configs;
+	unsigned int num_configs;
+	bool has_config = 0;
+	unsigned reserve = 0;
+	int num_pins, num_funcs, maps_per_pin, i, err;
+
+	pctl = pinctrl_dev_get_drvdata(pctldev);
+
+	pins = of_find_property(node, "pinmux", NULL);
+	if (!pins) {
+		dev_err(pctl->dev, "missing pins property in node %s .\n",
+				node->name);
+		return -EINVAL;
+	}
+
+	err = pinconf_generic_parse_dt_config(node, pctldev, &configs,
+		&num_configs);
+	if (err)
+		return err;
+
+	if (num_configs)
+		has_config = 1;
+
+	num_pins = pins->length / sizeof(u32);
+	num_funcs = num_pins;
+	maps_per_pin = 0;
+	if (num_funcs)
+		maps_per_pin++;
+	if (has_config && num_pins >= 1)
+		maps_per_pin++;
+
+	if (!num_pins || !maps_per_pin)
+		return -EINVAL;
+
+	reserve = num_pins * maps_per_pin;
+
+	err = pinctrl_utils_reserve_map(pctldev, map,
+			reserved_maps, num_maps, reserve);
+	if (err)
+		return err;
+
+	for (i = 0; i < num_pins; i++) {
+		err = of_property_read_u32_index(node, "pinmux",
+				i, &pinfunc);
+		if (err)
+			return err;
+
+		pin = STM32_GET_PIN_NO(pinfunc);
+		func = STM32_GET_PIN_FUNC(pinfunc);
+
+		if (pin >= pctl->match_data->npins) {
+			dev_err(pctl->dev, "invalid pin number.\n");
+			return -EINVAL;
+		}
+
+		if (!stm32_pctrl_is_function_valid(pctl, pin, func)) {
+			dev_err(pctl->dev, "invalid function.\n");
+			return -EINVAL;
+		}
+
+		grp = stm32_pctrl_find_group_by_pin(pctl, pin);
+		if (!grp) {
+			dev_err(pctl->dev, "unable to match pin %d to group\n",
+					pin);
+			return -EINVAL;
+		}
+
+		err = stm32_pctrl_dt_node_to_map_func(pctl, pin, func, grp, map,
+				reserved_maps, num_maps);
+		if (err)
+			return err;
+
+		if (has_config) {
+			err = pinctrl_utils_add_map_configs(pctldev, map,
+					reserved_maps, num_maps, grp->name,
+					configs, num_configs,
+					PIN_MAP_TYPE_CONFIGS_GROUP);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+static int stm32_pctrl_dt_node_to_map(struct pinctrl_dev *pctldev,
+				 struct device_node *np_config,
+				 struct pinctrl_map **map, unsigned *num_maps)
+{
+	struct device_node *np;
+	unsigned reserved_maps;
+	int ret;
+
+	*map = NULL;
+	*num_maps = 0;
+	reserved_maps = 0;
+
+	for_each_child_of_node(np_config, np) {
+		ret = stm32_pctrl_dt_subnode_to_map(pctldev, np, map,
+				&reserved_maps, num_maps);
+		if (ret < 0) {
+			pinctrl_utils_dt_free_map(pctldev, *map, *num_maps);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int stm32_pctrl_get_groups_count(struct pinctrl_dev *pctldev)
+{
+	struct stm32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+
+	return pctl->ngroups;
+}
+
+static const char *stm32_pctrl_get_group_name(struct pinctrl_dev *pctldev,
+					      unsigned group)
+{
+	struct stm32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+
+	return pctl->groups[group].name;
+}
+
+static int stm32_pctrl_get_group_pins(struct pinctrl_dev *pctldev,
+				      unsigned group,
+				      const unsigned **pins,
+				      unsigned *num_pins)
+{
+	struct stm32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+
+	*pins = (unsigned *)&pctl->groups[group].pin;
+	*num_pins = 1;
+
+	return 0;
+}
+
+static const struct pinctrl_ops stm32_pctrl_ops = {
+	.dt_node_to_map		= stm32_pctrl_dt_node_to_map,
+	.dt_free_map		= pinctrl_utils_dt_free_map,
+	.get_groups_count	= stm32_pctrl_get_groups_count,
+	.get_group_name		= stm32_pctrl_get_group_name,
+	.get_group_pins		= stm32_pctrl_get_group_pins,
+};
+
+
+/* Pinmux functions */
+
+static int stm32_pmx_get_funcs_cnt(struct pinctrl_dev *pctldev)
+{
+	return ARRAY_SIZE(stm32_gpio_functions);
+}
+
+static const char *stm32_pmx_get_func_name(struct pinctrl_dev *pctldev,
+					   unsigned selector)
+{
+	return stm32_gpio_functions[selector];
+}
+
+static int stm32_pmx_get_func_groups(struct pinctrl_dev *pctldev,
+				     unsigned function,
+				     const char * const **groups,
+				     unsigned * const num_groups)
+{
+	struct stm32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+
+	*groups = pctl->grp_names;
+	*num_groups = pctl->ngroups;
+
+	return 0;
+}
+
+static void stm32_pmx_set_mode(struct stm32_gpio_bank *bank,
+		int pin, u32 mode, u32 alt)
+{
+	u32 val;
+	int alt_shift = (pin % 8) * 4;
+	int alt_offset = STM32_GPIO_AFRL + (pin / 8) * 4;
+	unsigned long flags;
+
+	clk_enable(bank->clk);
+	spin_lock_irqsave(&bank->lock, flags);
+
+	val = readl_relaxed(bank->base + alt_offset);
+	val &= ~GENMASK(alt_shift + 3, alt_shift);
+	val |= (alt << alt_shift);
+	writel_relaxed(val, bank->base + alt_offset);
+
+	val = readl_relaxed(bank->base + STM32_GPIO_MODER);
+	val &= ~GENMASK(pin * 2 + 1, pin * 2);
+	val |= mode << (pin * 2);
+	writel_relaxed(val, bank->base + STM32_GPIO_MODER);
+
+	spin_unlock_irqrestore(&bank->lock, flags);
+	clk_disable(bank->clk);
+}
+
+static int stm32_pmx_set_mux(struct pinctrl_dev *pctldev,
+			    unsigned function,
+			    unsigned group)
+{
+	bool ret;
+	struct stm32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+	struct stm32_pinctrl_group *g = pctl->groups + group;
+	struct pinctrl_gpio_range *range;
+	struct stm32_gpio_bank *bank;
+	u32 mode, alt;
+	int pin;
+
+	ret = stm32_pctrl_is_function_valid(pctl, g->pin, function);
+	if (!ret) {
+		dev_err(pctl->dev, "invalid function %d on group %d .\n",
+				function, group);
+		return -EINVAL;
+	}
+
+	range = pinctrl_find_gpio_range_from_pin(pctldev, g->pin);
+	bank = gpio_range_to_bank(range);
+	pin = stm32_gpio_pin(g->pin);
+
+	mode = stm32_gpio_get_mode(function);
+	alt = stm32_gpio_get_alt(function);
+
+	stm32_pmx_set_mode(bank, pin, mode, alt);
+
+	return 0;
+}
+
+static int stm32_pmx_gpio_set_direction(struct pinctrl_dev *pctldev,
+			struct pinctrl_gpio_range *range, unsigned gpio,
+			bool input)
+{
+	struct stm32_gpio_bank *bank = gpio_range_to_bank(range);
+	int pin = stm32_gpio_pin(gpio);
+
+	stm32_pmx_set_mode(bank, pin, !input, 0);
+
+	return 0;
+}
+
+static const struct pinmux_ops stm32_pmx_ops = {
+	.get_functions_count	= stm32_pmx_get_funcs_cnt,
+	.get_function_name	= stm32_pmx_get_func_name,
+	.get_function_groups	= stm32_pmx_get_func_groups,
+	.set_mux		= stm32_pmx_set_mux,
+	.gpio_set_direction	= stm32_pmx_gpio_set_direction,
+};
+
+/* Pinconf functions */
+
+static void stm32_pconf_set_driving(struct stm32_gpio_bank *bank,
+	unsigned offset, u32 drive)
+{
+	unsigned long flags;
+	u32 val;
+
+	clk_enable(bank->clk);
+	spin_lock_irqsave(&bank->lock, flags);
+
+	val = readl_relaxed(bank->base + STM32_GPIO_TYPER);
+	val &= ~BIT(offset);
+	val |= drive << offset;
+	writel_relaxed(val, bank->base + STM32_GPIO_TYPER);
+
+	spin_unlock_irqrestore(&bank->lock, flags);
+	clk_disable(bank->clk);
+}
+
+static void stm32_pconf_set_speed(struct stm32_gpio_bank *bank,
+	unsigned offset, u32 speed)
+{
+	unsigned long flags;
+	u32 val;
+
+	clk_enable(bank->clk);
+	spin_lock_irqsave(&bank->lock, flags);
+
+	val = readl_relaxed(bank->base + STM32_GPIO_SPEEDR);
+	val &= ~GENMASK(offset * 2 + 1, offset * 2);
+	val |= speed << (offset * 2);
+	writel_relaxed(val, bank->base + STM32_GPIO_SPEEDR);
+
+	spin_unlock_irqrestore(&bank->lock, flags);
+	clk_disable(bank->clk);
+}
+
+static void stm32_pconf_set_bias(struct stm32_gpio_bank *bank,
+	unsigned offset, u32 bias)
+{
+	unsigned long flags;
+	u32 val;
+
+	clk_enable(bank->clk);
+	spin_lock_irqsave(&bank->lock, flags);
+
+	val = readl_relaxed(bank->base + STM32_GPIO_PUPDR);
+	val &= ~GENMASK(offset * 2 + 1, offset * 2);
+	val |= bias << (offset * 2);
+	writel_relaxed(val, bank->base + STM32_GPIO_PUPDR);
+
+	spin_unlock_irqrestore(&bank->lock, flags);
+	clk_disable(bank->clk);
+}
+
+static int stm32_pconf_parse_conf(struct pinctrl_dev *pctldev,
+		unsigned int pin, enum pin_config_param param,
+		enum pin_config_param arg)
+{
+	struct pinctrl_gpio_range *range;
+	struct stm32_gpio_bank *bank;
+	int offset, ret = 0;
+
+	range = pinctrl_find_gpio_range_from_pin(pctldev, pin);
+	bank = gpio_range_to_bank(range);
+	offset = stm32_gpio_pin(pin);
+
+	switch (param) {
+	case PIN_CONFIG_DRIVE_PUSH_PULL:
+		stm32_pconf_set_driving(bank, offset, 0);
+		break;
+	case PIN_CONFIG_DRIVE_OPEN_DRAIN:
+		stm32_pconf_set_driving(bank, offset, 1);
+		break;
+	case PIN_CONFIG_SLEW_RATE:
+		stm32_pconf_set_speed(bank, offset, arg);
+		break;
+	case PIN_CONFIG_BIAS_DISABLE:
+		stm32_pconf_set_bias(bank, offset, 0);
+		break;
+	case PIN_CONFIG_BIAS_PULL_UP:
+		stm32_pconf_set_bias(bank, offset, 1);
+		break;
+	case PIN_CONFIG_BIAS_PULL_DOWN:
+		stm32_pconf_set_bias(bank, offset, 2);
+		break;
+	case PIN_CONFIG_OUTPUT:
+		__stm32_gpio_set(bank, offset, arg);
+		ret = stm32_pmx_gpio_set_direction(pctldev, NULL, pin, false);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static int stm32_pconf_group_get(struct pinctrl_dev *pctldev,
+				 unsigned group,
+				 unsigned long *config)
+{
+	struct stm32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+
+	*config = pctl->groups[group].config;
+
+	return 0;
+}
+
+static int stm32_pconf_group_set(struct pinctrl_dev *pctldev, unsigned group,
+				 unsigned long *configs, unsigned num_configs)
+{
+	struct stm32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
+	struct stm32_pinctrl_group *g = &pctl->groups[group];
+	int i, ret;
+
+	for (i = 0; i < num_configs; i++) {
+		ret = stm32_pconf_parse_conf(pctldev, g->pin,
+			pinconf_to_config_param(configs[i]),
+			pinconf_to_config_argument(configs[i]));
+		if (ret < 0)
+			return ret;
+
+		g->config = configs[i];
+	}
+
+	return 0;
+}
+
+static const struct pinconf_ops stm32_pconf_ops = {
+	.pin_config_group_get	= stm32_pconf_group_get,
+	.pin_config_group_set	= stm32_pconf_group_set,
+};
+
+static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl,
+	struct device_node *np)
+{
+	int bank_nr = pctl->nbanks;
+	struct stm32_gpio_bank *bank = &pctl->banks[bank_nr];
+	struct pinctrl_gpio_range *range = &bank->range;
+	struct device *dev = pctl->dev;
+	struct resource res;
+	struct reset_control *rstc;
+	int err, npins;
+
+	rstc = of_reset_control_get(np, NULL);
+	if (!IS_ERR(rstc))
+		reset_control_deassert(rstc);
+
+	if (of_address_to_resource(np, 0, &res))
+		return -ENODEV;
+
+	bank->base = devm_ioremap_resource(dev, &res);
+	if (IS_ERR(bank->base))
+		return PTR_ERR(bank->base);
+
+	bank->clk = of_clk_get_by_name(np, NULL);
+	if (IS_ERR(bank->clk)) {
+		dev_err(dev, "failed to get clk (%ld)\n", PTR_ERR(bank->clk));
+		return PTR_ERR(bank->clk);
+	}
+
+	err = clk_prepare(bank->clk);
+	if (err) {
+		dev_err(dev, "failed to prepare clk (%d)\n", err);
+		return err;
+	}
+
+	npins = pctl->match_data->npins;
+	npins -= bank_nr * STM32_GPIO_PINS_PER_BANK;
+	if (npins < 0)
+		return -EINVAL;
+	else if (npins > STM32_GPIO_PINS_PER_BANK)
+		npins = STM32_GPIO_PINS_PER_BANK;
+
+	bank->gpio_chip = stm32_gpio_template;
+	bank->gpio_chip.base = bank_nr * STM32_GPIO_PINS_PER_BANK;
+	bank->gpio_chip.ngpio = npins;
+	bank->gpio_chip.of_node = np;
+	bank->gpio_chip.parent = dev;
+	spin_lock_init(&bank->lock);
+
+	of_property_read_string(np, "st,bank-name", &range->name);
+	bank->gpio_chip.label = range->name;
+
+	range->id = bank_nr;
+	range->pin_base = range->base = range->id * STM32_GPIO_PINS_PER_BANK;
+	range->npins = bank->gpio_chip.ngpio;
+	range->gc = &bank->gpio_chip;
+	err = gpiochip_add_data(&bank->gpio_chip, bank);
+	if (err) {
+		dev_err(dev, "Failed to add gpiochip(%d)!\n", bank_nr);
+		return err;
+	}
+
+	dev_info(dev, "%s bank added\n", range->name);
+	return 0;
+}
+
+static int stm32_pctrl_build_state(struct platform_device *pdev)
+{
+	struct stm32_pinctrl *pctl = platform_get_drvdata(pdev);
+	int i;
+
+	pctl->ngroups = pctl->match_data->npins;
+
+	/* Allocate groups */
+	pctl->groups = devm_kcalloc(&pdev->dev, pctl->ngroups,
+				    sizeof(*pctl->groups), GFP_KERNEL);
+	if (!pctl->groups)
+		return -ENOMEM;
+
+	/* We assume that one pin is one group, use pin name as group name. */
+	pctl->grp_names = devm_kcalloc(&pdev->dev, pctl->ngroups,
+				       sizeof(*pctl->grp_names), GFP_KERNEL);
+	if (!pctl->grp_names)
+		return -ENOMEM;
+
+	for (i = 0; i < pctl->match_data->npins; i++) {
+		const struct stm32_desc_pin *pin = pctl->match_data->pins + i;
+		struct stm32_pinctrl_group *group = pctl->groups + i;
+
+		group->name = pin->pin.name;
+		group->pin = pin->pin.number;
+
+		pctl->grp_names[i] = pin->pin.name;
+	}
+
+	return 0;
+}
+
+int stm32_pctl_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct device_node *child;
+	const struct of_device_id *match;
+	struct device *dev = &pdev->dev;
+	struct stm32_pinctrl *pctl;
+	struct pinctrl_pin_desc *pins;
+	int i, ret, banks = 0;
+
+	if (!np)
+		return -EINVAL;
+
+	match = of_match_device(dev->driver->of_match_table, dev);
+	if (!match || !match->data)
+		return -EINVAL;
+
+	if (!of_find_property(np, "pins-are-numbered", NULL)) {
+		dev_err(dev, "only support pins-are-numbered format\n");
+		return -EINVAL;
+	}
+
+	pctl = devm_kzalloc(dev, sizeof(*pctl), GFP_KERNEL);
+	if (!pctl)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, pctl);
+
+	pctl->dev = dev;
+	pctl->match_data = match->data;
+	ret = stm32_pctrl_build_state(pdev);
+	if (ret) {
+		dev_err(dev, "build state failed: %d\n", ret);
+		return -EINVAL;
+	}
+
+	for_each_child_of_node(np, child)
+		if (of_property_read_bool(child, "gpio-controller"))
+			banks++;
+
+	if (!banks) {
+		dev_err(dev, "at least one GPIO bank is required\n");
+		return -EINVAL;
+	}
+
+	pctl->banks = devm_kcalloc(dev, banks, sizeof(*pctl->banks),
+			GFP_KERNEL);
+	if (!pctl->banks)
+		return -ENOMEM;
+
+	for_each_child_of_node(np, child) {
+		if (of_property_read_bool(child, "gpio-controller")) {
+			ret = stm32_gpiolib_register_bank(pctl, child);
+			if (ret)
+				return ret;
+
+			pctl->nbanks++;
+		}
+	}
+
+	pins = devm_kcalloc(&pdev->dev, pctl->match_data->npins, sizeof(*pins),
+			    GFP_KERNEL);
+	if (!pins)
+		return -ENOMEM;
+
+	for (i = 0; i < pctl->match_data->npins; i++)
+		pins[i] = pctl->match_data->pins[i].pin;
+
+	pctl->pctl_desc.name = dev_name(&pdev->dev);
+	pctl->pctl_desc.owner = THIS_MODULE;
+	pctl->pctl_desc.pins = pins;
+	pctl->pctl_desc.npins = pctl->match_data->npins;
+	pctl->pctl_desc.confops = &stm32_pconf_ops;
+	pctl->pctl_desc.pctlops = &stm32_pctrl_ops;
+	pctl->pctl_desc.pmxops = &stm32_pmx_ops;
+	pctl->dev = &pdev->dev;
+
+	pctl->pctl_dev = pinctrl_register(&pctl->pctl_desc, &pdev->dev, pctl);
+	if (!pctl->pctl_dev) {
+		dev_err(&pdev->dev, "Failed pinctrl registration\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < pctl->nbanks; i++)
+		pinctrl_add_gpio_range(pctl->pctl_dev, &pctl->banks[i].range);
+
+	dev_info(dev, "Pinctrl STM32 initialized\n");
+
+	return 0;
+}
+
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.h b/drivers/pinctrl/stm32/pinctrl-stm32.h
new file mode 100644
index 000000000000..35ebc94c01e4
--- /dev/null
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.h
@@ -0,0 +1,51 @@
+/*
+ * Copyright (C) Maxime Coquelin 2015
+ * Author:  Maxime Coquelin <mcoquelin.stm32@gmail.com>
+ * License terms:  GNU General Public License (GPL), version 2
+ */
+#ifndef __PINCTRL_STM32_H
+#define __PINCTRL_STM32_H
+
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinconf-generic.h>
+
+#define STM32_PIN_NO(x) ((x) << 8)
+#define STM32_GET_PIN_NO(x) ((x) >> 8)
+#define STM32_GET_PIN_FUNC(x) ((x) & 0xff)
+
+#define STM32_PIN_GPIO		0
+#define STM32_PIN_AF(x)		((x) + 1)
+#define STM32_PIN_ANALOG	(STM32_PIN_AF(15) + 1)
+
+struct stm32_desc_function {
+	const char *name;
+	const unsigned char num;
+};
+
+struct stm32_desc_pin {
+	struct pinctrl_pin_desc pin;
+	const struct stm32_desc_function *functions;
+};
+
+#define STM32_PIN(_pin, ...)					\
+	{							\
+		.pin = _pin,					\
+		.functions = (struct stm32_desc_function[]){	\
+			__VA_ARGS__, { } },			\
+	}
+
+#define STM32_FUNCTION(_num, _name)		\
+	{							\
+		.num = _num,					\
+		.name = _name,					\
+	}
+
+struct stm32_pinctrl_match_data {
+	const struct stm32_desc_pin *pins;
+	const unsigned int npins;
+};
+
+int stm32_pctl_probe(struct platform_device *pdev);
+
+#endif /* __PINCTRL_STM32_H */
+
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32f429.c b/drivers/pinctrl/stm32/pinctrl-stm32f429.c
new file mode 100644
index 000000000000..e9b15dc0654b
--- /dev/null
+++ b/drivers/pinctrl/stm32/pinctrl-stm32f429.c
@@ -0,0 +1,1591 @@
+/*
+ * Copyright (C) Maxime Coquelin 2015
+ * Author:  Maxime Coquelin <mcoquelin.stm32@gmail.com>
+ * License terms:  GNU General Public License (GPL), version 2
+ */
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include "pinctrl-stm32.h"
+
+static const struct stm32_desc_pin stm32f429_pins[] = {
+	STM32_PIN(
+		PINCTRL_PIN(0, "PA0"),
+		STM32_FUNCTION(0, "GPIOA0"),
+		STM32_FUNCTION(2, "TIM2_CH1 TIM2_ETR"),
+		STM32_FUNCTION(3, "TIM5_CH1"),
+		STM32_FUNCTION(4, "TIM8_ETR"),
+		STM32_FUNCTION(8, "USART2_CTS"),
+		STM32_FUNCTION(9, "UART4_TX"),
+		STM32_FUNCTION(12, "ETH_MII_CRS"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(1, "PA1"),
+		STM32_FUNCTION(0, "GPIOA1"),
+		STM32_FUNCTION(2, "TIM2_CH2"),
+		STM32_FUNCTION(3, "TIM5_CH2"),
+		STM32_FUNCTION(8, "USART2_RTS"),
+		STM32_FUNCTION(9, "UART4_RX"),
+		STM32_FUNCTION(12, "ETH_MII_RX_CLK ETH_RMII_REF_CLK"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(2, "PA2"),
+		STM32_FUNCTION(0, "GPIOA2"),
+		STM32_FUNCTION(2, "TIM2_CH3"),
+		STM32_FUNCTION(3, "TIM5_CH3"),
+		STM32_FUNCTION(4, "TIM9_CH1"),
+		STM32_FUNCTION(8, "USART2_TX"),
+		STM32_FUNCTION(12, "ETH_MDIO"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(3, "PA3"),
+		STM32_FUNCTION(0, "GPIOA3"),
+		STM32_FUNCTION(2, "TIM2_CH4"),
+		STM32_FUNCTION(3, "TIM5_CH4"),
+		STM32_FUNCTION(4, "TIM9_CH2"),
+		STM32_FUNCTION(8, "USART2_RX"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_D0"),
+		STM32_FUNCTION(12, "ETH_MII_COL"),
+		STM32_FUNCTION(15, "LCD_B5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(4, "PA4"),
+		STM32_FUNCTION(0, "GPIOA4"),
+		STM32_FUNCTION(6, "SPI1_NSS"),
+		STM32_FUNCTION(7, "SPI3_NSS I2S3_WS"),
+		STM32_FUNCTION(8, "USART2_CK"),
+		STM32_FUNCTION(13, "OTG_HS_SOF"),
+		STM32_FUNCTION(14, "DCMI_HSYNC"),
+		STM32_FUNCTION(15, "LCD_VSYNC"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(5, "PA5"),
+		STM32_FUNCTION(0, "GPIOA5"),
+		STM32_FUNCTION(2, "TIM2_CH1 TIM2_ETR"),
+		STM32_FUNCTION(4, "TIM8_CH1N"),
+		STM32_FUNCTION(6, "SPI1_SCK"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_CK"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(6, "PA6"),
+		STM32_FUNCTION(0, "GPIOA6"),
+		STM32_FUNCTION(2, "TIM1_BKIN"),
+		STM32_FUNCTION(3, "TIM3_CH1"),
+		STM32_FUNCTION(4, "TIM8_BKIN"),
+		STM32_FUNCTION(6, "SPI1_MISO"),
+		STM32_FUNCTION(10, "TIM13_CH1"),
+		STM32_FUNCTION(14, "DCMI_PIXCLK"),
+		STM32_FUNCTION(15, "LCD_G2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(7, "PA7"),
+		STM32_FUNCTION(0, "GPIOA7"),
+		STM32_FUNCTION(2, "TIM1_CH1N"),
+		STM32_FUNCTION(3, "TIM3_CH2"),
+		STM32_FUNCTION(4, "TIM8_CH1N"),
+		STM32_FUNCTION(6, "SPI1_MOSI"),
+		STM32_FUNCTION(10, "TIM14_CH1"),
+		STM32_FUNCTION(12, "ETH_MII_RX_DV ETH_RMII_CRS_DV"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(8, "PA8"),
+		STM32_FUNCTION(0, "GPIOA8"),
+		STM32_FUNCTION(1, "MCO1"),
+		STM32_FUNCTION(2, "TIM1_CH1"),
+		STM32_FUNCTION(5, "I2C3_SCL"),
+		STM32_FUNCTION(8, "USART1_CK"),
+		STM32_FUNCTION(11, "OTG_FS_SOF"),
+		STM32_FUNCTION(15, "LCD_R6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(9, "PA9"),
+		STM32_FUNCTION(0, "GPIOA9"),
+		STM32_FUNCTION(2, "TIM1_CH2"),
+		STM32_FUNCTION(5, "I2C3_SMBA"),
+		STM32_FUNCTION(8, "USART1_TX"),
+		STM32_FUNCTION(14, "DCMI_D0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(10, "PA10"),
+		STM32_FUNCTION(0, "GPIOA10"),
+		STM32_FUNCTION(2, "TIM1_CH3"),
+		STM32_FUNCTION(8, "USART1_RX"),
+		STM32_FUNCTION(11, "OTG_FS_ID"),
+		STM32_FUNCTION(14, "DCMI_D1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(11, "PA11"),
+		STM32_FUNCTION(0, "GPIOA11"),
+		STM32_FUNCTION(2, "TIM1_CH4"),
+		STM32_FUNCTION(8, "USART1_CTS"),
+		STM32_FUNCTION(10, "CAN1_RX"),
+		STM32_FUNCTION(11, "OTG_FS_DM"),
+		STM32_FUNCTION(15, "LCD_R4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(12, "PA12"),
+		STM32_FUNCTION(0, "GPIOA12"),
+		STM32_FUNCTION(2, "TIM1_ETR"),
+		STM32_FUNCTION(8, "USART1_RTS"),
+		STM32_FUNCTION(10, "CAN1_TX"),
+		STM32_FUNCTION(11, "OTG_FS_DP"),
+		STM32_FUNCTION(15, "LCD_R5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(13, "PA13"),
+		STM32_FUNCTION(0, "GPIOA13"),
+		STM32_FUNCTION(1, "JTMS SWDIO"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(14, "PA14"),
+		STM32_FUNCTION(0, "GPIOA14"),
+		STM32_FUNCTION(1, "JTCK SWCLK"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(15, "PA15"),
+		STM32_FUNCTION(0, "GPIOA15"),
+		STM32_FUNCTION(1, "JTDI"),
+		STM32_FUNCTION(2, "TIM2_CH1 TIM2_ETR"),
+		STM32_FUNCTION(6, "SPI1_NSS"),
+		STM32_FUNCTION(7, "SPI3_NSS I2S3_WS"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(16, "PB0"),
+		STM32_FUNCTION(0, "GPIOB0"),
+		STM32_FUNCTION(2, "TIM1_CH2N"),
+		STM32_FUNCTION(3, "TIM3_CH3"),
+		STM32_FUNCTION(4, "TIM8_CH2N"),
+		STM32_FUNCTION(10, "LCD_R3"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_D1"),
+		STM32_FUNCTION(12, "ETH_MII_RXD2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(17, "PB1"),
+		STM32_FUNCTION(0, "GPIOB1"),
+		STM32_FUNCTION(2, "TIM1_CH3N"),
+		STM32_FUNCTION(3, "TIM3_CH4"),
+		STM32_FUNCTION(4, "TIM8_CH3N"),
+		STM32_FUNCTION(10, "LCD_R6"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_D2"),
+		STM32_FUNCTION(12, "ETH_MII_RXD3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(18, "PB2"),
+		STM32_FUNCTION(0, "GPIOB2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(19, "PB3"),
+		STM32_FUNCTION(0, "GPIOB3"),
+		STM32_FUNCTION(1, "JTDO TRACESWO"),
+		STM32_FUNCTION(2, "TIM2_CH2"),
+		STM32_FUNCTION(6, "SPI1_SCK"),
+		STM32_FUNCTION(7, "SPI3_SCK I2S3_CK"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(20, "PB4"),
+		STM32_FUNCTION(0, "GPIOB4"),
+		STM32_FUNCTION(1, "NJTRST"),
+		STM32_FUNCTION(3, "TIM3_CH1"),
+		STM32_FUNCTION(6, "SPI1_MISO"),
+		STM32_FUNCTION(7, "SPI3_MISO"),
+		STM32_FUNCTION(8, "I2S3EXT_SD"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(21, "PB5"),
+		STM32_FUNCTION(0, "GPIOB5"),
+		STM32_FUNCTION(3, "TIM3_CH2"),
+		STM32_FUNCTION(5, "I2C1_SMBA"),
+		STM32_FUNCTION(6, "SPI1_MOSI"),
+		STM32_FUNCTION(7, "SPI3_MOSI I2S3_SD"),
+		STM32_FUNCTION(10, "CAN2_RX"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_D7"),
+		STM32_FUNCTION(12, "ETH_PPS_OUT"),
+		STM32_FUNCTION(13, "FMC_SDCKE1"),
+		STM32_FUNCTION(14, "DCMI_D10"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(22, "PB6"),
+		STM32_FUNCTION(0, "GPIOB6"),
+		STM32_FUNCTION(3, "TIM4_CH1"),
+		STM32_FUNCTION(5, "I2C1_SCL"),
+		STM32_FUNCTION(8, "USART1_TX"),
+		STM32_FUNCTION(10, "CAN2_TX"),
+		STM32_FUNCTION(13, "FMC_SDNE1"),
+		STM32_FUNCTION(14, "DCMI_D5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(23, "PB7"),
+		STM32_FUNCTION(0, "GPIOB7"),
+		STM32_FUNCTION(3, "TIM4_CH2"),
+		STM32_FUNCTION(5, "I2C1_SDA"),
+		STM32_FUNCTION(8, "USART1_RX"),
+		STM32_FUNCTION(13, "FMC_NL"),
+		STM32_FUNCTION(14, "DCMI_VSYNC"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(24, "PB8"),
+		STM32_FUNCTION(0, "GPIOB8"),
+		STM32_FUNCTION(3, "TIM4_CH3"),
+		STM32_FUNCTION(4, "TIM10_CH1"),
+		STM32_FUNCTION(5, "I2C1_SCL"),
+		STM32_FUNCTION(10, "CAN1_RX"),
+		STM32_FUNCTION(12, "ETH_MII_TXD3"),
+		STM32_FUNCTION(13, "SDIO_D4"),
+		STM32_FUNCTION(14, "DCMI_D6"),
+		STM32_FUNCTION(15, "LCD_B6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(25, "PB9"),
+		STM32_FUNCTION(0, "GPIOB9"),
+		STM32_FUNCTION(3, "TIM4_CH4"),
+		STM32_FUNCTION(4, "TIM11_CH1"),
+		STM32_FUNCTION(5, "I2C1_SDA"),
+		STM32_FUNCTION(6, "SPI2_NSS I2S2_WS"),
+		STM32_FUNCTION(10, "CAN1_TX"),
+		STM32_FUNCTION(13, "SDIO_D5"),
+		STM32_FUNCTION(14, "DCMI_D7"),
+		STM32_FUNCTION(15, "LCD_B7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(26, "PB10"),
+		STM32_FUNCTION(0, "GPIOB10"),
+		STM32_FUNCTION(2, "TIM2_CH3"),
+		STM32_FUNCTION(5, "I2C2_SCL"),
+		STM32_FUNCTION(6, "SPI2_SCK I2S2_CK"),
+		STM32_FUNCTION(8, "USART3_TX"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_D3"),
+		STM32_FUNCTION(12, "ETH_MII_RX_ER"),
+		STM32_FUNCTION(15, "LCD_G4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(27, "PB11"),
+		STM32_FUNCTION(0, "GPIOB11"),
+		STM32_FUNCTION(2, "TIM2_CH4"),
+		STM32_FUNCTION(5, "I2C2_SDA"),
+		STM32_FUNCTION(8, "USART3_RX"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_D4"),
+		STM32_FUNCTION(12, "ETH_MII_TX_EN ETH_RMII_TX_EN"),
+		STM32_FUNCTION(15, "LCD_G5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(28, "PB12"),
+		STM32_FUNCTION(0, "GPIOB12"),
+		STM32_FUNCTION(2, "TIM1_BKIN"),
+		STM32_FUNCTION(5, "I2C2_SMBA"),
+		STM32_FUNCTION(6, "SPI2_NSS I2S2_WS"),
+		STM32_FUNCTION(8, "USART3_CK"),
+		STM32_FUNCTION(10, "CAN2_RX"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_D5"),
+		STM32_FUNCTION(12, "ETH_MII_TXD0 ETH_RMII_TXD0"),
+		STM32_FUNCTION(13, "OTG_HS_ID"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(29, "PB13"),
+		STM32_FUNCTION(0, "GPIOB13"),
+		STM32_FUNCTION(2, "TIM1_CH1N"),
+		STM32_FUNCTION(6, "SPI2_SCK I2S2_CK"),
+		STM32_FUNCTION(8, "USART3_CTS"),
+		STM32_FUNCTION(10, "CAN2_TX"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_D6"),
+		STM32_FUNCTION(12, "ETH_MII_TXD1 ETH_RMII_TXD1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(30, "PB14"),
+		STM32_FUNCTION(0, "GPIOB14"),
+		STM32_FUNCTION(2, "TIM1_CH2N"),
+		STM32_FUNCTION(4, "TIM8_CH2N"),
+		STM32_FUNCTION(6, "SPI2_MISO"),
+		STM32_FUNCTION(7, "I2S2EXT_SD"),
+		STM32_FUNCTION(8, "USART3_RTS"),
+		STM32_FUNCTION(10, "TIM12_CH1"),
+		STM32_FUNCTION(13, "OTG_HS_DM"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(31, "PB15"),
+		STM32_FUNCTION(0, "GPIOB15"),
+		STM32_FUNCTION(1, "RTC_REFIN"),
+		STM32_FUNCTION(2, "TIM1_CH3N"),
+		STM32_FUNCTION(4, "TIM8_CH3N"),
+		STM32_FUNCTION(6, "SPI2_MOSI I2S2_SD"),
+		STM32_FUNCTION(10, "TIM12_CH2"),
+		STM32_FUNCTION(13, "OTG_HS_DP"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(32, "PC0"),
+		STM32_FUNCTION(0, "GPIOC0"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_STP"),
+		STM32_FUNCTION(13, "FMC_SDNWE"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(33, "PC1"),
+		STM32_FUNCTION(0, "GPIOC1"),
+		STM32_FUNCTION(12, "ETH_MDC"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(34, "PC2"),
+		STM32_FUNCTION(0, "GPIOC2"),
+		STM32_FUNCTION(6, "SPI2_MISO"),
+		STM32_FUNCTION(7, "I2S2EXT_SD"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_DIR"),
+		STM32_FUNCTION(12, "ETH_MII_TXD2"),
+		STM32_FUNCTION(13, "FMC_SDNE0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(35, "PC3"),
+		STM32_FUNCTION(0, "GPIOC3"),
+		STM32_FUNCTION(6, "SPI2_MOSI I2S2_SD"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_NXT"),
+		STM32_FUNCTION(12, "ETH_MII_TX_CLK"),
+		STM32_FUNCTION(13, "FMC_SDCKE0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(36, "PC4"),
+		STM32_FUNCTION(0, "GPIOC4"),
+		STM32_FUNCTION(12, "ETH_MII_RXD0 ETH_RMII_RXD0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(37, "PC5"),
+		STM32_FUNCTION(0, "GPIOC5"),
+		STM32_FUNCTION(12, "ETH_MII_RXD1 ETH_RMII_RXD1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(38, "PC6"),
+		STM32_FUNCTION(0, "GPIOC6"),
+		STM32_FUNCTION(3, "TIM3_CH1"),
+		STM32_FUNCTION(4, "TIM8_CH1"),
+		STM32_FUNCTION(6, "I2S2_MCK"),
+		STM32_FUNCTION(9, "USART6_TX"),
+		STM32_FUNCTION(13, "SDIO_D6"),
+		STM32_FUNCTION(14, "DCMI_D0"),
+		STM32_FUNCTION(15, "LCD_HSYNC"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(39, "PC7"),
+		STM32_FUNCTION(0, "GPIOC7"),
+		STM32_FUNCTION(3, "TIM3_CH2"),
+		STM32_FUNCTION(4, "TIM8_CH2"),
+		STM32_FUNCTION(7, "I2S3_MCK"),
+		STM32_FUNCTION(9, "USART6_RX"),
+		STM32_FUNCTION(13, "SDIO_D7"),
+		STM32_FUNCTION(14, "DCMI_D1"),
+		STM32_FUNCTION(15, "LCD_G6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(40, "PC8"),
+		STM32_FUNCTION(0, "GPIOC8"),
+		STM32_FUNCTION(3, "TIM3_CH3"),
+		STM32_FUNCTION(4, "TIM8_CH3"),
+		STM32_FUNCTION(9, "USART6_CK"),
+		STM32_FUNCTION(13, "SDIO_D0"),
+		STM32_FUNCTION(14, "DCMI_D2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(41, "PC9"),
+		STM32_FUNCTION(0, "GPIOC9"),
+		STM32_FUNCTION(1, "MCO2"),
+		STM32_FUNCTION(3, "TIM3_CH4"),
+		STM32_FUNCTION(4, "TIM8_CH4"),
+		STM32_FUNCTION(5, "I2C3_SDA"),
+		STM32_FUNCTION(6, "I2S_CKIN"),
+		STM32_FUNCTION(13, "SDIO_D1"),
+		STM32_FUNCTION(14, "DCMI_D3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(42, "PC10"),
+		STM32_FUNCTION(0, "GPIOC10"),
+		STM32_FUNCTION(7, "SPI3_SCK I2S3_CK"),
+		STM32_FUNCTION(8, "USART3_TX"),
+		STM32_FUNCTION(9, "UART4_TX"),
+		STM32_FUNCTION(13, "SDIO_D2"),
+		STM32_FUNCTION(14, "DCMI_D8"),
+		STM32_FUNCTION(15, "LCD_R2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(43, "PC11"),
+		STM32_FUNCTION(0, "GPIOC11"),
+		STM32_FUNCTION(6, "I2S3EXT_SD"),
+		STM32_FUNCTION(7, "SPI3_MISO"),
+		STM32_FUNCTION(8, "USART3_RX"),
+		STM32_FUNCTION(9, "UART4_RX"),
+		STM32_FUNCTION(13, "SDIO_D3"),
+		STM32_FUNCTION(14, "DCMI_D4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(44, "PC12"),
+		STM32_FUNCTION(0, "GPIOC12"),
+		STM32_FUNCTION(7, "SPI3_MOSI I2S3_SD"),
+		STM32_FUNCTION(8, "USART3_CK"),
+		STM32_FUNCTION(9, "UART5_TX"),
+		STM32_FUNCTION(13, "SDIO_CK"),
+		STM32_FUNCTION(14, "DCMI_D9"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(45, "PC13"),
+		STM32_FUNCTION(0, "GPIOC13"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(46, "PC14"),
+		STM32_FUNCTION(0, "GPIOC14"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(47, "PC15"),
+		STM32_FUNCTION(0, "GPIOC15"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(48, "PD0"),
+		STM32_FUNCTION(0, "GPIOD0"),
+		STM32_FUNCTION(10, "CAN1_RX"),
+		STM32_FUNCTION(13, "FMC_D2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(49, "PD1"),
+		STM32_FUNCTION(0, "GPIOD1"),
+		STM32_FUNCTION(10, "CAN1_TX"),
+		STM32_FUNCTION(13, "FMC_D3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(50, "PD2"),
+		STM32_FUNCTION(0, "GPIOD2"),
+		STM32_FUNCTION(3, "TIM3_ETR"),
+		STM32_FUNCTION(9, "UART5_RX"),
+		STM32_FUNCTION(13, "SDIO_CMD"),
+		STM32_FUNCTION(14, "DCMI_D11"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(51, "PD3"),
+		STM32_FUNCTION(0, "GPIOD3"),
+		STM32_FUNCTION(6, "SPI2_SCK I2S2_CK"),
+		STM32_FUNCTION(8, "USART2_CTS"),
+		STM32_FUNCTION(13, "FMC_CLK"),
+		STM32_FUNCTION(14, "DCMI_D5"),
+		STM32_FUNCTION(15, "LCD_G7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(52, "PD4"),
+		STM32_FUNCTION(0, "GPIOD4"),
+		STM32_FUNCTION(8, "USART2_RTS"),
+		STM32_FUNCTION(13, "FMC_NOE"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(53, "PD5"),
+		STM32_FUNCTION(0, "GPIOD5"),
+		STM32_FUNCTION(8, "USART2_TX"),
+		STM32_FUNCTION(13, "FMC_NWE"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(54, "PD6"),
+		STM32_FUNCTION(0, "GPIOD6"),
+		STM32_FUNCTION(6, "SPI3_MOSI I2S3_SD"),
+		STM32_FUNCTION(7, "SAI1_SD_A"),
+		STM32_FUNCTION(8, "USART2_RX"),
+		STM32_FUNCTION(13, "FMC_NWAIT"),
+		STM32_FUNCTION(14, "DCMI_D10"),
+		STM32_FUNCTION(15, "LCD_B2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(55, "PD7"),
+		STM32_FUNCTION(0, "GPIOD7"),
+		STM32_FUNCTION(8, "USART2_CK"),
+		STM32_FUNCTION(13, "FMC_NE1 FMC_NCE2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(56, "PD8"),
+		STM32_FUNCTION(0, "GPIOD8"),
+		STM32_FUNCTION(8, "USART3_TX"),
+		STM32_FUNCTION(13, "FMC_D13"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(57, "PD9"),
+		STM32_FUNCTION(0, "GPIOD9"),
+		STM32_FUNCTION(8, "USART3_RX"),
+		STM32_FUNCTION(13, "FMC_D14"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(58, "PD10"),
+		STM32_FUNCTION(0, "GPIOD10"),
+		STM32_FUNCTION(8, "USART3_CK"),
+		STM32_FUNCTION(13, "FMC_D15"),
+		STM32_FUNCTION(15, "LCD_B3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(59, "PD11"),
+		STM32_FUNCTION(0, "GPIOD11"),
+		STM32_FUNCTION(8, "USART3_CTS"),
+		STM32_FUNCTION(13, "FMC_A16"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(60, "PD12"),
+		STM32_FUNCTION(0, "GPIOD12"),
+		STM32_FUNCTION(3, "TIM4_CH1"),
+		STM32_FUNCTION(8, "USART3_RTS"),
+		STM32_FUNCTION(13, "FMC_A17"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(61, "PD13"),
+		STM32_FUNCTION(0, "GPIOD13"),
+		STM32_FUNCTION(3, "TIM4_CH2"),
+		STM32_FUNCTION(13, "FMC_A18"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(62, "PD14"),
+		STM32_FUNCTION(0, "GPIOD14"),
+		STM32_FUNCTION(3, "TIM4_CH3"),
+		STM32_FUNCTION(13, "FMC_D0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(63, "PD15"),
+		STM32_FUNCTION(0, "GPIOD15"),
+		STM32_FUNCTION(3, "TIM4_CH4"),
+		STM32_FUNCTION(13, "FMC_D1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(64, "PE0"),
+		STM32_FUNCTION(0, "GPIOE0"),
+		STM32_FUNCTION(3, "TIM4_ETR"),
+		STM32_FUNCTION(9, "UART8_RX"),
+		STM32_FUNCTION(13, "FMC_NBL0"),
+		STM32_FUNCTION(14, "DCMI_D2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(65, "PE1"),
+		STM32_FUNCTION(0, "GPIOE1"),
+		STM32_FUNCTION(9, "UART8_TX"),
+		STM32_FUNCTION(13, "FMC_NBL1"),
+		STM32_FUNCTION(14, "DCMI_D3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(66, "PE2"),
+		STM32_FUNCTION(0, "GPIOE2"),
+		STM32_FUNCTION(1, "TRACECLK"),
+		STM32_FUNCTION(6, "SPI4_SCK"),
+		STM32_FUNCTION(7, "SAI1_MCLK_A"),
+		STM32_FUNCTION(12, "ETH_MII_TXD3"),
+		STM32_FUNCTION(13, "FMC_A23"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(67, "PE3"),
+		STM32_FUNCTION(0, "GPIOE3"),
+		STM32_FUNCTION(1, "TRACED0"),
+		STM32_FUNCTION(7, "SAI1_SD_B"),
+		STM32_FUNCTION(13, "FMC_A19"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(68, "PE4"),
+		STM32_FUNCTION(0, "GPIOE4"),
+		STM32_FUNCTION(1, "TRACED1"),
+		STM32_FUNCTION(6, "SPI4_NSS"),
+		STM32_FUNCTION(7, "SAI1_FS_A"),
+		STM32_FUNCTION(13, "FMC_A20"),
+		STM32_FUNCTION(14, "DCMI_D4"),
+		STM32_FUNCTION(15, "LCD_B0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(69, "PE5"),
+		STM32_FUNCTION(0, "GPIOE5"),
+		STM32_FUNCTION(1, "TRACED2"),
+		STM32_FUNCTION(4, "TIM9_CH1"),
+		STM32_FUNCTION(6, "SPI4_MISO"),
+		STM32_FUNCTION(7, "SAI1_SCK_A"),
+		STM32_FUNCTION(13, "FMC_A21"),
+		STM32_FUNCTION(14, "DCMI_D6"),
+		STM32_FUNCTION(15, "LCD_G0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(70, "PE6"),
+		STM32_FUNCTION(0, "GPIOE6"),
+		STM32_FUNCTION(1, "TRACED3"),
+		STM32_FUNCTION(4, "TIM9_CH2"),
+		STM32_FUNCTION(6, "SPI4_MOSI"),
+		STM32_FUNCTION(7, "SAI1_SD_A"),
+		STM32_FUNCTION(13, "FMC_A22"),
+		STM32_FUNCTION(14, "DCMI_D7"),
+		STM32_FUNCTION(15, "LCD_G1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(71, "PE7"),
+		STM32_FUNCTION(0, "GPIOE7"),
+		STM32_FUNCTION(2, "TIM1_ETR"),
+		STM32_FUNCTION(9, "UART7_RX"),
+		STM32_FUNCTION(13, "FMC_D4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(72, "PE8"),
+		STM32_FUNCTION(0, "GPIOE8"),
+		STM32_FUNCTION(2, "TIM1_CH1N"),
+		STM32_FUNCTION(9, "UART7_TX"),
+		STM32_FUNCTION(13, "FMC_D5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(73, "PE9"),
+		STM32_FUNCTION(0, "GPIOE9"),
+		STM32_FUNCTION(2, "TIM1_CH1"),
+		STM32_FUNCTION(13, "FMC_D6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(74, "PE10"),
+		STM32_FUNCTION(0, "GPIOE10"),
+		STM32_FUNCTION(2, "TIM1_CH2N"),
+		STM32_FUNCTION(13, "FMC_D7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(75, "PE11"),
+		STM32_FUNCTION(0, "GPIOE11"),
+		STM32_FUNCTION(2, "TIM1_CH2"),
+		STM32_FUNCTION(6, "SPI4_NSS"),
+		STM32_FUNCTION(13, "FMC_D8"),
+		STM32_FUNCTION(15, "LCD_G3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(76, "PE12"),
+		STM32_FUNCTION(0, "GPIOE12"),
+		STM32_FUNCTION(2, "TIM1_CH3N"),
+		STM32_FUNCTION(6, "SPI4_SCK"),
+		STM32_FUNCTION(13, "FMC_D9"),
+		STM32_FUNCTION(15, "LCD_B4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(77, "PE13"),
+		STM32_FUNCTION(0, "GPIOE13"),
+		STM32_FUNCTION(2, "TIM1_CH3"),
+		STM32_FUNCTION(6, "SPI4_MISO"),
+		STM32_FUNCTION(13, "FMC_D10"),
+		STM32_FUNCTION(15, "LCD_DE"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(78, "PE14"),
+		STM32_FUNCTION(0, "GPIOE14"),
+		STM32_FUNCTION(2, "TIM1_CH4"),
+		STM32_FUNCTION(6, "SPI4_MOSI"),
+		STM32_FUNCTION(13, "FMC_D11"),
+		STM32_FUNCTION(15, "LCD_CLK"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(79, "PE15"),
+		STM32_FUNCTION(0, "GPIOE15"),
+		STM32_FUNCTION(2, "TIM1_BKIN"),
+		STM32_FUNCTION(13, "FMC_D12"),
+		STM32_FUNCTION(15, "LCD_R7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(80, "PF0"),
+		STM32_FUNCTION(0, "GPIOF0"),
+		STM32_FUNCTION(5, "I2C2_SDA"),
+		STM32_FUNCTION(13, "FMC_A0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(81, "PF1"),
+		STM32_FUNCTION(0, "GPIOF1"),
+		STM32_FUNCTION(5, "I2C2_SCL"),
+		STM32_FUNCTION(13, "FMC_A1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(82, "PF2"),
+		STM32_FUNCTION(0, "GPIOF2"),
+		STM32_FUNCTION(5, "I2C2_SMBA"),
+		STM32_FUNCTION(13, "FMC_A2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(83, "PF3"),
+		STM32_FUNCTION(0, "GPIOF3"),
+		STM32_FUNCTION(13, "FMC_A3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(84, "PF4"),
+		STM32_FUNCTION(0, "GPIOF4"),
+		STM32_FUNCTION(13, "FMC_A4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(85, "PF5"),
+		STM32_FUNCTION(0, "GPIOF5"),
+		STM32_FUNCTION(13, "FMC_A5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(86, "PF6"),
+		STM32_FUNCTION(0, "GPIOF6"),
+		STM32_FUNCTION(4, "TIM10_CH1"),
+		STM32_FUNCTION(6, "SPI5_NSS"),
+		STM32_FUNCTION(7, "SAI1_SD_B"),
+		STM32_FUNCTION(9, "UART7_RX"),
+		STM32_FUNCTION(13, "FMC_NIORD"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(87, "PF7"),
+		STM32_FUNCTION(0, "GPIOF7"),
+		STM32_FUNCTION(4, "TIM11_CH1"),
+		STM32_FUNCTION(6, "SPI5_SCK"),
+		STM32_FUNCTION(7, "SAI1_MCLK_B"),
+		STM32_FUNCTION(9, "UART7_TX"),
+		STM32_FUNCTION(13, "FMC_NREG"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(88, "PF8"),
+		STM32_FUNCTION(0, "GPIOF8"),
+		STM32_FUNCTION(6, "SPI5_MISO"),
+		STM32_FUNCTION(7, "SAI1_SCK_B"),
+		STM32_FUNCTION(10, "TIM13_CH1"),
+		STM32_FUNCTION(13, "FMC_NIOWR"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(89, "PF9"),
+		STM32_FUNCTION(0, "GPIOF9"),
+		STM32_FUNCTION(6, "SPI5_MOSI"),
+		STM32_FUNCTION(7, "SAI1_FS_B"),
+		STM32_FUNCTION(10, "TIM14_CH1"),
+		STM32_FUNCTION(13, "FMC_CD"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(90, "PF10"),
+		STM32_FUNCTION(0, "GPIOF10"),
+		STM32_FUNCTION(13, "FMC_INTR"),
+		STM32_FUNCTION(14, "DCMI_D11"),
+		STM32_FUNCTION(15, "LCD_DE"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(91, "PF11"),
+		STM32_FUNCTION(0, "GPIOF11"),
+		STM32_FUNCTION(6, "SPI5_MOSI"),
+		STM32_FUNCTION(13, "FMC_SDNRAS"),
+		STM32_FUNCTION(14, "DCMI_D12"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(92, "PF12"),
+		STM32_FUNCTION(0, "GPIOF12"),
+		STM32_FUNCTION(13, "FMC_A6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(93, "PF13"),
+		STM32_FUNCTION(0, "GPIOF13"),
+		STM32_FUNCTION(13, "FMC_A7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(94, "PF14"),
+		STM32_FUNCTION(0, "GPIOF14"),
+		STM32_FUNCTION(13, "FMC_A8"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(95, "PF15"),
+		STM32_FUNCTION(0, "GPIOF15"),
+		STM32_FUNCTION(13, "FMC_A9"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(96, "PG0"),
+		STM32_FUNCTION(0, "GPIOG0"),
+		STM32_FUNCTION(13, "FMC_A10"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(97, "PG1"),
+		STM32_FUNCTION(0, "GPIOG1"),
+		STM32_FUNCTION(13, "FMC_A11"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(98, "PG2"),
+		STM32_FUNCTION(0, "GPIOG2"),
+		STM32_FUNCTION(13, "FMC_A12"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(99, "PG3"),
+		STM32_FUNCTION(0, "GPIOG3"),
+		STM32_FUNCTION(13, "FMC_A13"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(100, "PG4"),
+		STM32_FUNCTION(0, "GPIOG4"),
+		STM32_FUNCTION(13, "FMC_A14 FMC_BA0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(101, "PG5"),
+		STM32_FUNCTION(0, "GPIOG5"),
+		STM32_FUNCTION(13, "FMC_A15 FMC_BA1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(102, "PG6"),
+		STM32_FUNCTION(0, "GPIOG6"),
+		STM32_FUNCTION(13, "FMC_INT2"),
+		STM32_FUNCTION(14, "DCMI_D12"),
+		STM32_FUNCTION(15, "LCD_R7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(103, "PG7"),
+		STM32_FUNCTION(0, "GPIOG7"),
+		STM32_FUNCTION(9, "USART6_CK"),
+		STM32_FUNCTION(13, "FMC_INT3"),
+		STM32_FUNCTION(14, "DCMI_D13"),
+		STM32_FUNCTION(15, "LCD_CLK"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(104, "PG8"),
+		STM32_FUNCTION(0, "GPIOG8"),
+		STM32_FUNCTION(6, "SPI6_NSS"),
+		STM32_FUNCTION(9, "USART6_RTS"),
+		STM32_FUNCTION(12, "ETH_PPS_OUT"),
+		STM32_FUNCTION(13, "FMC_SDCLK"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(105, "PG9"),
+		STM32_FUNCTION(0, "GPIOG9"),
+		STM32_FUNCTION(9, "USART6_RX"),
+		STM32_FUNCTION(13, "FMC_NE2 FMC_NCE3"),
+		STM32_FUNCTION(14, "DCMI_VSYNC"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(106, "PG10"),
+		STM32_FUNCTION(0, "GPIOG10"),
+		STM32_FUNCTION(10, "LCD_G3"),
+		STM32_FUNCTION(13, "FMC_NCE4_1 FMC_NE3"),
+		STM32_FUNCTION(14, "DCMI_D2"),
+		STM32_FUNCTION(15, "LCD_B2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(107, "PG11"),
+		STM32_FUNCTION(0, "GPIOG11"),
+		STM32_FUNCTION(12, "ETH_MII_TX_EN ETH_RMII_TX_EN"),
+		STM32_FUNCTION(13, "FMC_NCE4_2"),
+		STM32_FUNCTION(14, "DCMI_D3"),
+		STM32_FUNCTION(15, "LCD_B3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(108, "PG12"),
+		STM32_FUNCTION(0, "GPIOG12"),
+		STM32_FUNCTION(6, "SPI6_MISO"),
+		STM32_FUNCTION(9, "USART6_RTS"),
+		STM32_FUNCTION(10, "LCD_B4"),
+		STM32_FUNCTION(13, "FMC_NE4"),
+		STM32_FUNCTION(15, "LCD_B1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(109, "PG13"),
+		STM32_FUNCTION(0, "GPIOG13"),
+		STM32_FUNCTION(6, "SPI6_SCK"),
+		STM32_FUNCTION(9, "USART6_CTS"),
+		STM32_FUNCTION(12, "ETH_MII_TXD0 ETH_RMII_TXD0"),
+		STM32_FUNCTION(13, "FMC_A24"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(110, "PG14"),
+		STM32_FUNCTION(0, "GPIOG14"),
+		STM32_FUNCTION(6, "SPI6_MOSI"),
+		STM32_FUNCTION(9, "USART6_TX"),
+		STM32_FUNCTION(12, "ETH_MII_TXD1 ETH_RMII_TXD1"),
+		STM32_FUNCTION(13, "FMC_A25"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(111, "PG15"),
+		STM32_FUNCTION(0, "GPIOG15"),
+		STM32_FUNCTION(9, "USART6_CTS"),
+		STM32_FUNCTION(13, "FMC_SDNCAS"),
+		STM32_FUNCTION(14, "DCMI_D13"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(112, "PH0"),
+		STM32_FUNCTION(0, "GPIOH0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(113, "PH1"),
+		STM32_FUNCTION(0, "GPIOH1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(114, "PH2"),
+		STM32_FUNCTION(0, "GPIOH2"),
+		STM32_FUNCTION(12, "ETH_MII_CRS"),
+		STM32_FUNCTION(13, "FMC_SDCKE0"),
+		STM32_FUNCTION(15, "LCD_R0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(115, "PH3"),
+		STM32_FUNCTION(0, "GPIOH3"),
+		STM32_FUNCTION(12, "ETH_MII_COL"),
+		STM32_FUNCTION(13, "FMC_SDNE0"),
+		STM32_FUNCTION(15, "LCD_R1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(116, "PH4"),
+		STM32_FUNCTION(0, "GPIOH4"),
+		STM32_FUNCTION(5, "I2C2_SCL"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_NXT"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(117, "PH5"),
+		STM32_FUNCTION(0, "GPIOH5"),
+		STM32_FUNCTION(5, "I2C2_SDA"),
+		STM32_FUNCTION(6, "SPI5_NSS"),
+		STM32_FUNCTION(13, "FMC_SDNWE"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(118, "PH6"),
+		STM32_FUNCTION(0, "GPIOH6"),
+		STM32_FUNCTION(5, "I2C2_SMBA"),
+		STM32_FUNCTION(6, "SPI5_SCK"),
+		STM32_FUNCTION(10, "TIM12_CH1"),
+		STM32_FUNCTION(12, "ETH_MII_RXD2"),
+		STM32_FUNCTION(13, "FMC_SDNE1"),
+		STM32_FUNCTION(14, "DCMI_D8"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(119, "PH7"),
+		STM32_FUNCTION(0, "GPIOH7"),
+		STM32_FUNCTION(5, "I2C3_SCL"),
+		STM32_FUNCTION(6, "SPI5_MISO"),
+		STM32_FUNCTION(12, "ETH_MII_RXD3"),
+		STM32_FUNCTION(13, "FMC_SDCKE1"),
+		STM32_FUNCTION(14, "DCMI_D9"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(120, "PH8"),
+		STM32_FUNCTION(0, "GPIOH8"),
+		STM32_FUNCTION(5, "I2C3_SDA"),
+		STM32_FUNCTION(13, "FMC_D16"),
+		STM32_FUNCTION(14, "DCMI_HSYNC"),
+		STM32_FUNCTION(15, "LCD_R2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(121, "PH9"),
+		STM32_FUNCTION(0, "GPIOH9"),
+		STM32_FUNCTION(5, "I2C3_SMBA"),
+		STM32_FUNCTION(10, "TIM12_CH2"),
+		STM32_FUNCTION(13, "FMC_D17"),
+		STM32_FUNCTION(14, "DCMI_D0"),
+		STM32_FUNCTION(15, "LCD_R3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(122, "PH10"),
+		STM32_FUNCTION(0, "GPIOH10"),
+		STM32_FUNCTION(3, "TIM5_CH1"),
+		STM32_FUNCTION(13, "FMC_D18"),
+		STM32_FUNCTION(14, "DCMI_D1"),
+		STM32_FUNCTION(15, "LCD_R4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(123, "PH11"),
+		STM32_FUNCTION(0, "GPIOH11"),
+		STM32_FUNCTION(3, "TIM5_CH2"),
+		STM32_FUNCTION(13, "FMC_D19"),
+		STM32_FUNCTION(14, "DCMI_D2"),
+		STM32_FUNCTION(15, "LCD_R5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(124, "PH12"),
+		STM32_FUNCTION(0, "GPIOH12"),
+		STM32_FUNCTION(3, "TIM5_CH3"),
+		STM32_FUNCTION(13, "FMC_D20"),
+		STM32_FUNCTION(14, "DCMI_D3"),
+		STM32_FUNCTION(15, "LCD_R6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(125, "PH13"),
+		STM32_FUNCTION(0, "GPIOH13"),
+		STM32_FUNCTION(4, "TIM8_CH1N"),
+		STM32_FUNCTION(10, "CAN1_TX"),
+		STM32_FUNCTION(13, "FMC_D21"),
+		STM32_FUNCTION(15, "LCD_G2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(126, "PH14"),
+		STM32_FUNCTION(0, "GPIOH14"),
+		STM32_FUNCTION(4, "TIM8_CH2N"),
+		STM32_FUNCTION(13, "FMC_D22"),
+		STM32_FUNCTION(14, "DCMI_D4"),
+		STM32_FUNCTION(15, "LCD_G3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(127, "PH15"),
+		STM32_FUNCTION(0, "GPIOH15"),
+		STM32_FUNCTION(4, "TIM8_CH3N"),
+		STM32_FUNCTION(13, "FMC_D23"),
+		STM32_FUNCTION(14, "DCMI_D11"),
+		STM32_FUNCTION(15, "LCD_G4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(128, "PI0"),
+		STM32_FUNCTION(0, "GPIOI0"),
+		STM32_FUNCTION(3, "TIM5_CH4"),
+		STM32_FUNCTION(6, "SPI2_NSS I2S2_WS"),
+		STM32_FUNCTION(13, "FMC_D24"),
+		STM32_FUNCTION(14, "DCMI_D13"),
+		STM32_FUNCTION(15, "LCD_G5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(129, "PI1"),
+		STM32_FUNCTION(0, "GPIOI1"),
+		STM32_FUNCTION(6, "SPI2_SCK I2S2_CK"),
+		STM32_FUNCTION(13, "FMC_D25"),
+		STM32_FUNCTION(14, "DCMI_D8"),
+		STM32_FUNCTION(15, "LCD_G6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(130, "PI2"),
+		STM32_FUNCTION(0, "GPIOI2"),
+		STM32_FUNCTION(4, "TIM8_CH4"),
+		STM32_FUNCTION(6, "SPI2_MISO"),
+		STM32_FUNCTION(7, "I2S2EXT_SD"),
+		STM32_FUNCTION(13, "FMC_D26"),
+		STM32_FUNCTION(14, "DCMI_D9"),
+		STM32_FUNCTION(15, "LCD_G7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(131, "PI3"),
+		STM32_FUNCTION(0, "GPIOI3"),
+		STM32_FUNCTION(4, "TIM8_ETR"),
+		STM32_FUNCTION(6, "SPI2_MOSI I2S2_SD"),
+		STM32_FUNCTION(13, "FMC_D27"),
+		STM32_FUNCTION(14, "DCMI_D10"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(132, "PI4"),
+		STM32_FUNCTION(0, "GPIOI4"),
+		STM32_FUNCTION(4, "TIM8_BKIN"),
+		STM32_FUNCTION(13, "FMC_NBL2"),
+		STM32_FUNCTION(14, "DCMI_D5"),
+		STM32_FUNCTION(15, "LCD_B4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(133, "PI5"),
+		STM32_FUNCTION(0, "GPIOI5"),
+		STM32_FUNCTION(4, "TIM8_CH1"),
+		STM32_FUNCTION(13, "FMC_NBL3"),
+		STM32_FUNCTION(14, "DCMI_VSYNC"),
+		STM32_FUNCTION(15, "LCD_B5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(134, "PI6"),
+		STM32_FUNCTION(0, "GPIOI6"),
+		STM32_FUNCTION(4, "TIM8_CH2"),
+		STM32_FUNCTION(13, "FMC_D28"),
+		STM32_FUNCTION(14, "DCMI_D6"),
+		STM32_FUNCTION(15, "LCD_B6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(135, "PI7"),
+		STM32_FUNCTION(0, "GPIOI7"),
+		STM32_FUNCTION(4, "TIM8_CH3"),
+		STM32_FUNCTION(13, "FMC_D29"),
+		STM32_FUNCTION(14, "DCMI_D7"),
+		STM32_FUNCTION(15, "LCD_B7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(136, "PI8"),
+		STM32_FUNCTION(0, "GPIOI8"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(137, "PI9"),
+		STM32_FUNCTION(0, "GPIOI9"),
+		STM32_FUNCTION(10, "CAN1_RX"),
+		STM32_FUNCTION(13, "FMC_D30"),
+		STM32_FUNCTION(15, "LCD_VSYNC"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(138, "PI10"),
+		STM32_FUNCTION(0, "GPIOI10"),
+		STM32_FUNCTION(12, "ETH_MII_RX_ER"),
+		STM32_FUNCTION(13, "FMC_D31"),
+		STM32_FUNCTION(15, "LCD_HSYNC"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(139, "PI11"),
+		STM32_FUNCTION(0, "GPIOI11"),
+		STM32_FUNCTION(11, "OTG_HS_ULPI_DIR"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(140, "PI12"),
+		STM32_FUNCTION(0, "GPIOI12"),
+		STM32_FUNCTION(15, "LCD_HSYNC"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(141, "PI13"),
+		STM32_FUNCTION(0, "GPIOI13"),
+		STM32_FUNCTION(15, "LCD_VSYNC"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(142, "PI14"),
+		STM32_FUNCTION(0, "GPIOI14"),
+		STM32_FUNCTION(15, "LCD_CLK"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(143, "PI15"),
+		STM32_FUNCTION(0, "GPIOI15"),
+		STM32_FUNCTION(15, "LCD_R0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(144, "PJ0"),
+		STM32_FUNCTION(0, "GPIOJ0"),
+		STM32_FUNCTION(15, "LCD_R1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(145, "PJ1"),
+		STM32_FUNCTION(0, "GPIOJ1"),
+		STM32_FUNCTION(15, "LCD_R2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(146, "PJ2"),
+		STM32_FUNCTION(0, "GPIOJ2"),
+		STM32_FUNCTION(15, "LCD_R3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(147, "PJ3"),
+		STM32_FUNCTION(0, "GPIOJ3"),
+		STM32_FUNCTION(15, "LCD_R4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(148, "PJ4"),
+		STM32_FUNCTION(0, "GPIOJ4"),
+		STM32_FUNCTION(15, "LCD_R5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(149, "PJ5"),
+		STM32_FUNCTION(0, "GPIOJ5"),
+		STM32_FUNCTION(15, "LCD_R6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(150, "PJ6"),
+		STM32_FUNCTION(0, "GPIOJ6"),
+		STM32_FUNCTION(15, "LCD_R7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(151, "PJ7"),
+		STM32_FUNCTION(0, "GPIOJ7"),
+		STM32_FUNCTION(15, "LCD_G0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(152, "PJ8"),
+		STM32_FUNCTION(0, "GPIOJ8"),
+		STM32_FUNCTION(15, "LCD_G1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(153, "PJ9"),
+		STM32_FUNCTION(0, "GPIOJ9"),
+		STM32_FUNCTION(15, "LCD_G2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(154, "PJ10"),
+		STM32_FUNCTION(0, "GPIOJ10"),
+		STM32_FUNCTION(15, "LCD_G3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(155, "PJ11"),
+		STM32_FUNCTION(0, "GPIOJ11"),
+		STM32_FUNCTION(15, "LCD_G4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(156, "PJ12"),
+		STM32_FUNCTION(0, "GPIOJ12"),
+		STM32_FUNCTION(15, "LCD_B0"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(157, "PJ13"),
+		STM32_FUNCTION(0, "GPIOJ13"),
+		STM32_FUNCTION(15, "LCD_B1"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(158, "PJ14"),
+		STM32_FUNCTION(0, "GPIOJ14"),
+		STM32_FUNCTION(15, "LCD_B2"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(159, "PJ15"),
+		STM32_FUNCTION(0, "GPIOJ15"),
+		STM32_FUNCTION(15, "LCD_B3"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(160, "PK0"),
+		STM32_FUNCTION(0, "GPIOK0"),
+		STM32_FUNCTION(15, "LCD_G5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(161, "PK1"),
+		STM32_FUNCTION(0, "GPIOK1"),
+		STM32_FUNCTION(15, "LCD_G6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(162, "PK2"),
+		STM32_FUNCTION(0, "GPIOK2"),
+		STM32_FUNCTION(15, "LCD_G7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(163, "PK3"),
+		STM32_FUNCTION(0, "GPIOK3"),
+		STM32_FUNCTION(15, "LCD_B4"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(164, "PK4"),
+		STM32_FUNCTION(0, "GPIOK4"),
+		STM32_FUNCTION(15, "LCD_B5"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(165, "PK5"),
+		STM32_FUNCTION(0, "GPIOK5"),
+		STM32_FUNCTION(15, "LCD_B6"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(166, "PK6"),
+		STM32_FUNCTION(0, "GPIOK6"),
+		STM32_FUNCTION(15, "LCD_B7"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+	STM32_PIN(
+		PINCTRL_PIN(167, "PK7"),
+		STM32_FUNCTION(0, "GPIOK7"),
+		STM32_FUNCTION(15, "LCD_DE"),
+		STM32_FUNCTION(16, "EVENTOUT"),
+		STM32_FUNCTION(17, "ANALOG")
+	),
+};
+
+static struct stm32_pinctrl_match_data stm32f429_match_data = {
+	.pins = stm32f429_pins,
+	.npins = ARRAY_SIZE(stm32f429_pins),
+};
+
+static const struct of_device_id stm32f429_pctrl_match[] = {
+	{
+		.compatible = "st,stm32f429-pinctrl",
+		.data = &stm32f429_match_data,
+	},
+	{ }
+};
+
+static struct platform_driver stm32f429_pinctrl_driver = {
+	.probe = stm32_pctl_probe,
+	.driver = {
+		.name = "stm32f429-pinctrl",
+		.of_match_table = stm32f429_pctrl_match,
+	},
+};
+
+static int __init stm32f429_pinctrl_init(void)
+{
+	return platform_driver_register(&stm32f429_pinctrl_driver);
+}
+device_initcall(stm32f429_pinctrl_init);
diff --git a/drivers/pinctrl/sunxi/Kconfig b/drivers/pinctrl/sunxi/Kconfig
index f8dbc8bec0e1..aaf075b972f5 100644
--- a/drivers/pinctrl/sunxi/Kconfig
+++ b/drivers/pinctrl/sunxi/Kconfig
@@ -1,67 +1,75 @@
 if ARCH_SUNXI
 
-config PINCTRL_SUNXI_COMMON
+config PINCTRL_SUNXI
 	bool
 	select PINMUX
 	select GENERIC_PINCONF
 
 config PINCTRL_SUN4I_A10
 	def_bool MACH_SUN4I
-	select PINCTRL_SUNXI_COMMON
+	select PINCTRL_SUNXI
 
 config PINCTRL_SUN5I_A10S
 	def_bool MACH_SUN5I
-	select PINCTRL_SUNXI_COMMON
+	select PINCTRL_SUNXI
 
 config PINCTRL_SUN5I_A13
 	def_bool MACH_SUN5I
-	select PINCTRL_SUNXI_COMMON
+	select PINCTRL_SUNXI
 
 config PINCTRL_SUN6I_A31
 	def_bool MACH_SUN6I
-	select PINCTRL_SUNXI_COMMON
+	select PINCTRL_SUNXI
 
 config PINCTRL_SUN6I_A31S
 	def_bool MACH_SUN6I
-	select PINCTRL_SUNXI_COMMON
+	select PINCTRL_SUNXI
 
 config PINCTRL_SUN6I_A31_R
 	def_bool MACH_SUN6I
 	depends on RESET_CONTROLLER
-	select PINCTRL_SUNXI_COMMON
+	select PINCTRL_SUNXI
 
 config PINCTRL_SUN7I_A20
 	def_bool MACH_SUN7I
-	select PINCTRL_SUNXI_COMMON
+	select PINCTRL_SUNXI
 
 config PINCTRL_SUN8I_A23
 	def_bool MACH_SUN8I
-	select PINCTRL_SUNXI_COMMON
+	select PINCTRL_SUNXI
 
 config PINCTRL_SUN8I_A33
 	def_bool MACH_SUN8I
-	select PINCTRL_SUNXI_COMMON
+	select PINCTRL_SUNXI
 
 config PINCTRL_SUN8I_A83T
 	def_bool MACH_SUN8I
-	select PINCTRL_SUNXI_COMMON
+	select PINCTRL_SUNXI
 
 config PINCTRL_SUN8I_A23_R
 	def_bool MACH_SUN8I
 	depends on RESET_CONTROLLER
-	select PINCTRL_SUNXI_COMMON
+	select PINCTRL_SUNXI
 
 config PINCTRL_SUN8I_H3
 	def_bool MACH_SUN8I
+	select PINCTRL_SUNXI
+
+config PINCTRL_SUN8I_H3_R
+	def_bool MACH_SUN8I
 	select PINCTRL_SUNXI_COMMON
 
 config PINCTRL_SUN9I_A80
 	def_bool MACH_SUN9I
-	select PINCTRL_SUNXI_COMMON
+	select PINCTRL_SUNXI
 
 config PINCTRL_SUN9I_A80_R
 	def_bool MACH_SUN9I
 	depends on RESET_CONTROLLER
-	select PINCTRL_SUNXI_COMMON
+	select PINCTRL_SUNXI
+
+config PINCTRL_SUN50I_A64
+	bool
+	select PINCTRL_SUNXI
 
 endif
diff --git a/drivers/pinctrl/sunxi/Makefile b/drivers/pinctrl/sunxi/Makefile
index ef82f22bb9ef..2d8b64e222e0 100644
--- a/drivers/pinctrl/sunxi/Makefile
+++ b/drivers/pinctrl/sunxi/Makefile
@@ -1,5 +1,5 @@
 # Core
-obj-$(CONFIG_PINCTRL_SUNXI_COMMON)	+= pinctrl-sunxi.o
+obj-y					+= pinctrl-sunxi.o
 
 # SoC Drivers
 obj-$(CONFIG_PINCTRL_SUN4I_A10)		+= pinctrl-sun4i-a10.o
@@ -12,7 +12,9 @@ obj-$(CONFIG_PINCTRL_SUN7I_A20)		+= pinctrl-sun7i-a20.o
 obj-$(CONFIG_PINCTRL_SUN8I_A23)		+= pinctrl-sun8i-a23.o
 obj-$(CONFIG_PINCTRL_SUN8I_A23_R)	+= pinctrl-sun8i-a23-r.o
 obj-$(CONFIG_PINCTRL_SUN8I_A33)		+= pinctrl-sun8i-a33.o
+obj-$(CONFIG_PINCTRL_SUN50I_A64)	+= pinctrl-sun50i-a64.o
 obj-$(CONFIG_PINCTRL_SUN8I_A83T)	+= pinctrl-sun8i-a83t.o
 obj-$(CONFIG_PINCTRL_SUN8I_H3)		+= pinctrl-sun8i-h3.o
+obj-$(CONFIG_PINCTRL_SUN8I_H3_R)	+= pinctrl-sun8i-h3-r.o
 obj-$(CONFIG_PINCTRL_SUN9I_A80)		+= pinctrl-sun9i-a80.o
 obj-$(CONFIG_PINCTRL_SUN9I_A80_R)	+= pinctrl-sun9i-a80-r.o
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun50i-a64.c b/drivers/pinctrl/sunxi/pinctrl-sun50i-a64.c
new file mode 100644
index 000000000000..4f2a726bbaeb
--- /dev/null
+++ b/drivers/pinctrl/sunxi/pinctrl-sun50i-a64.c
@@ -0,0 +1,601 @@
+/*
+ * Allwinner A64 SoCs pinctrl driver.
+ *
+ * Copyright (C) 2016 - ARM Ltd.
+ * Author: Andre Przywara <andre.przywara@arm.com>
+ *
+ * Based on pinctrl-sun7i-a20.c, which is:
+ * Copyright (C) 2014 Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pinctrl/pinctrl.h>
+
+#include "pinctrl-sunxi.h"
+
+static const struct sunxi_desc_pin a64_pins[] = {
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(B, 0),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart2"),		/* TX */
+		  SUNXI_FUNCTION(0x4, "jtag"),		/* MS0 */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 0)),	/* EINT0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(B, 1),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart2"),		/* RX */
+		  SUNXI_FUNCTION(0x4, "jtag"),		/* CK0 */
+		  SUNXI_FUNCTION(0x5, "sim"),		/* VCCEN */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 1)),		/* EINT1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(B, 2),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart2"),		/* RTS */
+		  SUNXI_FUNCTION(0x4, "jtag"),		/* DO0 */
+		  SUNXI_FUNCTION(0x5, "sim"),		/* VPPEN */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 2)),		/* EINT2 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(B, 3),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart2"),		/* CTS */
+		  SUNXI_FUNCTION(0x3, "i2s0"),		/* MCLK */
+		  SUNXI_FUNCTION(0x4, "jtag"),		/* DI0 */
+		  SUNXI_FUNCTION(0x5, "sim"),		/* VPPPP */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 3)),		/* EINT3 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(B, 4),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "aif2"),		/* SYNC */
+		  SUNXI_FUNCTION(0x3, "i2s0"),		/* SYNC */
+		  SUNXI_FUNCTION(0x5, "sim"),		/* CLK */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 4)),		/* EINT4 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(B, 5),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "aif2"),		/* BCLK */
+		  SUNXI_FUNCTION(0x3, "i2s0"),		/* BCLK */
+		  SUNXI_FUNCTION(0x5, "sim"),		/* DATA */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 5)),		/* EINT5 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(B, 6),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "aif2"),		/* DOUT */
+		  SUNXI_FUNCTION(0x3, "i2s0"),		/* DOUT */
+		  SUNXI_FUNCTION(0x5, "sim"),		/* RST */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 6)),		/* EINT6 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(B, 7),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "aif2"),		/* DIN */
+		  SUNXI_FUNCTION(0x3, "i2s0"),		/* DIN */
+		  SUNXI_FUNCTION(0x5, "sim"),		/* DET */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 7)),		/* EINT7 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(B, 8),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x4, "uart0"),		/* TX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 8)),		/* EINT8 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(B, 9),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x4, "uart0"),		/* RX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 9)),		/* EINT9 */
+	/* Hole */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 0),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* NWE */
+		  SUNXI_FUNCTION(0x4, "spi0")),		/* MOSI */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 1),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* NALE */
+		  SUNXI_FUNCTION(0x3, "mmc2"),		/* DS */
+		  SUNXI_FUNCTION(0x4, "spi0")),		/* MISO */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 2),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* NCLE */
+		  SUNXI_FUNCTION(0x4, "spi0")),		/* SCK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 3),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* NCE1 */
+		  SUNXI_FUNCTION(0x4, "spi0")),		/* CS */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 4),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0")),	/* NCE0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 5),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* NRE# */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* CLK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 6),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* NRB0 */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* CMD */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 7),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0")),	/* NRB1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 8),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* NDQ0 */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* D0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 9),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* NDQ1 */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* D1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 10),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* NDQ2 */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* D2 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 11),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* NDQ3 */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* D3 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 12),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* NDQ4 */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* D4 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 13),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* NDQ5 */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* D5 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 14),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* NDQ6 */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* D6 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 15),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* NDQ7 */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* D7 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 16),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "nand0"),		/* NDQS */
+		  SUNXI_FUNCTION(0x3, "mmc2")),		/* RST */
+	/* Hole */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 0),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* D2 */
+		  SUNXI_FUNCTION(0x3, "uart3"),		/* TX */
+		  SUNXI_FUNCTION(0x4, "spi1"),		/* CS */
+		  SUNXI_FUNCTION(0x5, "ccir")),		/* CLK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 1),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* D3 */
+		  SUNXI_FUNCTION(0x3, "uart3"),		/* RX */
+		  SUNXI_FUNCTION(0x4, "spi1"),		/* CLK */
+		  SUNXI_FUNCTION(0x5, "ccir")),		/* DE */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 2),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* D4 */
+		  SUNXI_FUNCTION(0x3, "uart4"),		/* TX */
+		  SUNXI_FUNCTION(0x4, "spi1"),		/* MOSI */
+		  SUNXI_FUNCTION(0x5, "ccir")),		/* HSYNC */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 3),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* D5 */
+		  SUNXI_FUNCTION(0x3, "uart4"),		/* RX */
+		  SUNXI_FUNCTION(0x4, "spi1"),		/* MISO */
+		  SUNXI_FUNCTION(0x5, "ccir")),		/* VSYNC */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 4),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* D6 */
+		  SUNXI_FUNCTION(0x3, "uart4"),		/* RTS */
+		  SUNXI_FUNCTION(0x5, "ccir")),		/* D0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 5),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* D7 */
+		  SUNXI_FUNCTION(0x3, "uart4"),		/* CTS */
+		  SUNXI_FUNCTION(0x5, "ccir")),		/* D1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 6),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* D10 */
+		  SUNXI_FUNCTION(0x5, "ccir")),		/* D2 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 7),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* D11 */
+		  SUNXI_FUNCTION(0x5, "ccir")),		/* D3 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 8),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* D12 */
+		  SUNXI_FUNCTION(0x4, "emac"),		/* ERXD3 */
+		  SUNXI_FUNCTION(0x5, "ccir")),		/* D4 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 9),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* D13 */
+		  SUNXI_FUNCTION(0x4, "emac"),		/* ERXD2 */
+		  SUNXI_FUNCTION(0x5, "ccir")),		/* D5 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 10),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* D14 */
+		  SUNXI_FUNCTION(0x4, "emac")),		/* ERXD1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 11),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* D15 */
+		  SUNXI_FUNCTION(0x4, "emac")),		/* ERXD0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 12),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* D18 */
+		  SUNXI_FUNCTION(0x3, "lvds0"),		/* VP0 */
+		  SUNXI_FUNCTION(0x4, "emac")),		/* ERXCK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 13),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* D19 */
+		  SUNXI_FUNCTION(0x3, "lvds0"),		/* VN0 */
+		  SUNXI_FUNCTION(0x4, "emac")),		/* ERXCTL */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 14),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* D20 */
+		  SUNXI_FUNCTION(0x3, "lvds0"),		/* VP1 */
+		  SUNXI_FUNCTION(0x4, "emac")),		/* ENULL */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 15),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* D21 */
+		  SUNXI_FUNCTION(0x3, "lvds0"),		/* VN1 */
+		  SUNXI_FUNCTION(0x4, "emac"),		/* ETXD3 */
+		  SUNXI_FUNCTION(0x5, "ccir")),		/* D6 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 16),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* D22 */
+		  SUNXI_FUNCTION(0x3, "lvds0"),		/* VP2 */
+		  SUNXI_FUNCTION(0x4, "emac"),		/* ETXD2 */
+		  SUNXI_FUNCTION(0x5, "ccir")),		/* D7 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 17),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* D23 */
+		  SUNXI_FUNCTION(0x3, "lvds0"),		/* VN2 */
+		  SUNXI_FUNCTION(0x4, "emac")),		/* ETXD1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 18),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* CLK */
+		  SUNXI_FUNCTION(0x3, "lvds0"),		/* VPC */
+		  SUNXI_FUNCTION(0x4, "emac")),		/* ETXD0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 19),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* DE */
+		  SUNXI_FUNCTION(0x3, "lvds0"),		/* VNC */
+		  SUNXI_FUNCTION(0x4, "emac")),		/* ETXCK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 20),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* HSYNC */
+		  SUNXI_FUNCTION(0x3, "lvds0"),		/* VP3 */
+		  SUNXI_FUNCTION(0x4, "emac")),		/* ETXCTL */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 21),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "lcd0"),		/* VSYNC */
+		  SUNXI_FUNCTION(0x3, "lvds0"),		/* VN3 */
+		  SUNXI_FUNCTION(0x4, "emac")),		/* ECLKIN */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 22),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "pwm"),		/* PWM0 */
+		  SUNXI_FUNCTION(0x4, "emac")),		/* EMDC */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 23),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x4, "emac")),		/* EMDIO */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(D, 24),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out")),
+	/* Hole */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 0),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi0"),		/* PCK */
+		  SUNXI_FUNCTION(0x4, "ts0")),		/* CLK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 1),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi0"),		/* CK */
+		  SUNXI_FUNCTION(0x4, "ts0")),		/* ERR */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 2),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi0"),		/* HSYNC */
+		  SUNXI_FUNCTION(0x4, "ts0")),		/* SYNC */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 3),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi0"),		/* VSYNC */
+		  SUNXI_FUNCTION(0x4, "ts0")),		/* DVLD */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 4),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi0"),		/* D0 */
+		  SUNXI_FUNCTION(0x4, "ts0")),		/* D0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 5),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi0"),		/* D1 */
+		  SUNXI_FUNCTION(0x4, "ts0")),		/* D1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 6),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi0"),		/* D2 */
+		  SUNXI_FUNCTION(0x4, "ts0")),		/* D2 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 7),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi0"),		/* D3 */
+		  SUNXI_FUNCTION(0x4, "ts0")),		/* D3 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 8),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi0"),		/* D4 */
+		  SUNXI_FUNCTION(0x4, "ts0")),		/* D4 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 9),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi0"),		/* D5 */
+		  SUNXI_FUNCTION(0x4, "ts0")),		/* D5 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 10),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi0"),		/* D6 */
+		  SUNXI_FUNCTION(0x4, "ts0")),		/* D6 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 11),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi0"),		/* D7 */
+		  SUNXI_FUNCTION(0x4, "ts0")),		/* D7 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 12),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi0")),		/* SCK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 13),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "csi0")),		/* SDA */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 14),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "pll"),		/* LOCK_DBG */
+		  SUNXI_FUNCTION(0x3, "i2c2")),		/* SCK */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 15),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x3, "i2c2")),		/* SDA */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 16),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out")),
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(E, 17),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out")),
+	/* Hole */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(F, 0),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc0"),		/* D1 */
+		  SUNXI_FUNCTION(0x3, "jtag")),		/* MSI */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(F, 1),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc0"),		/* D0 */
+		  SUNXI_FUNCTION(0x3, "jtag")),		/* DI1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(F, 2),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc0"),		/* CLK */
+		  SUNXI_FUNCTION(0x3, "uart0")),	/* TX */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(F, 3),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc0"),		/* CMD */
+		  SUNXI_FUNCTION(0x3, "jtag")),		/* DO1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(F, 4),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc0"),		/* D3 */
+		  SUNXI_FUNCTION(0x4, "uart0")),	/* RX */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(F, 5),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc0"),		/* D2 */
+		  SUNXI_FUNCTION(0x3, "jtag")),		/* CK1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(F, 6),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out")),
+	/* Hole */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 0),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc1"),		/* CLK */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 0)),	/* EINT0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 1),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc1"),		/* CMD */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 1)),	/* EINT1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 2),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc1"),		/* D0 */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 2)),	/* EINT2 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 3),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc1"),		/* D1 */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 3)),	/* EINT3 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 4),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc1"),		/* D2 */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 4)),	/* EINT4 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 5),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mmc1"),		/* D3 */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 5)),	/* EINT5 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 6),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart1"),		/* TX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 6)),	/* EINT6 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 7),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart1"),		/* RX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 7)),	/* EINT7 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 8),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart1"),		/* RTS */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 8)),	/* EINT8 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 9),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart1"),		/* CTS */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 9)),	/* EINT9 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 10),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "aif3"),		/* SYNC */
+		  SUNXI_FUNCTION(0x3, "i2s1"),		/* SYNC */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 10)),	/* EINT10 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 11),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "aif3"),		/* BCLK */
+		  SUNXI_FUNCTION(0x3, "i2s1"),		/* BCLK */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 11)),	/* EINT11 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 12),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "aif3"),		/* DOUT */
+		  SUNXI_FUNCTION(0x3, "i2s1"),		/* DOUT */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 12)),	/* EINT12 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 13),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "aif3"),		/* DIN */
+		  SUNXI_FUNCTION(0x3, "i2s1"),		/* DIN */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 1, 13)),	/* EINT13 */
+	/* Hole */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 0),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "i2c0"),		/* SCK */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 0)),	/* EINT0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 1),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "i2c0"),		/* SDA */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 1)),	/* EINT1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 2),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "i2c1"),		/* SCK */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 2)),	/* EINT2 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 3),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "i2c1"),		/* SDA */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 3)),	/* EINT3 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 4),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart3"),		/* TX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 4)),	/* EINT4 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 5),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart3"),		/* RX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 5)),	/* EINT5 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 6),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart3"),		/* RTS */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 6)),	/* EINT6 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 7),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "uart3"),		/* CTS */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 7)),	/* EINT7 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 8),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "spdif"),		/* OUT */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 8)),	/* EINT8 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 9),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 9)),	/* EINT9 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 10),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mic"),		/* CLK */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 10)),	/* EINT10 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 11),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "mic"),		/* DATA */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 11)),	/* EINT11 */
+};
+
+static const struct sunxi_pinctrl_desc a64_pinctrl_data = {
+	.pins = a64_pins,
+	.npins = ARRAY_SIZE(a64_pins),
+	.irq_banks = 3,
+};
+
+static int a64_pinctrl_probe(struct platform_device *pdev)
+{
+	return sunxi_pinctrl_init(pdev,
+				  &a64_pinctrl_data);
+}
+
+static const struct of_device_id a64_pinctrl_match[] = {
+	{ .compatible = "allwinner,sun50i-a64-pinctrl", },
+	{}
+};
+
+static struct platform_driver a64_pinctrl_driver = {
+	.probe	= a64_pinctrl_probe,
+	.driver	= {
+		.name		= "sun50i-a64-pinctrl",
+		.of_match_table	= a64_pinctrl_match,
+	},
+};
+builtin_platform_driver(a64_pinctrl_driver);
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun7i-a20.c b/drivers/pinctrl/sunxi/pinctrl-sun7i-a20.c
index cf1ce0c02600..435ad30f45db 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sun7i-a20.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sun7i-a20.c
@@ -343,26 +343,22 @@ static const struct sunxi_desc_pin sun7i_a20_pins[] = {
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
 		  SUNXI_FUNCTION(0x2, "nand0"),		/* NCE4 */
-		  SUNXI_FUNCTION(0x3, "spi2"),		/* CS0 */
-		  SUNXI_FUNCTION_IRQ(0x6, 12)),		/* EINT12 */
+		  SUNXI_FUNCTION(0x3, "spi2")),		/* CS0 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 20),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
 		  SUNXI_FUNCTION(0x2, "nand0"),		/* NCE5 */
-		  SUNXI_FUNCTION(0x3, "spi2"),		/* CLK */
-		  SUNXI_FUNCTION_IRQ(0x6, 13)),		/* EINT13 */
+		  SUNXI_FUNCTION(0x3, "spi2")),		/* CLK */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 21),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
 		  SUNXI_FUNCTION(0x2, "nand0"),		/* NCE6 */
-		  SUNXI_FUNCTION(0x3, "spi2"),		/* MOSI */
-		  SUNXI_FUNCTION_IRQ(0x6, 14)),		/* EINT14 */
+		  SUNXI_FUNCTION(0x3, "spi2")),		/* MOSI */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 22),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
 		  SUNXI_FUNCTION(0x2, "nand0"),		/* NCE7 */
-		  SUNXI_FUNCTION(0x3, "spi2"),		/* MISO */
-		  SUNXI_FUNCTION_IRQ(0x6, 15)),		/* EINT15 */
+		  SUNXI_FUNCTION(0x3, "spi2")),		/* MISO */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(C, 23),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
@@ -960,65 +956,65 @@ static const struct sunxi_desc_pin sun7i_a20_pins[] = {
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
 		  SUNXI_FUNCTION(0x2, "spi0"),		/* CS0 */
 		  SUNXI_FUNCTION(0x3, "uart5"),		/* TX */
-		  SUNXI_FUNCTION_IRQ(0x5, 22)),		/* EINT22 */
+		  SUNXI_FUNCTION_IRQ(0x6, 22)),		/* EINT22 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(I, 11),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
 		  SUNXI_FUNCTION(0x2, "spi0"),		/* CLK */
 		  SUNXI_FUNCTION(0x3, "uart5"),		/* RX */
-		  SUNXI_FUNCTION_IRQ(0x5, 23)),		/* EINT23 */
+		  SUNXI_FUNCTION_IRQ(0x6, 23)),		/* EINT23 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(I, 12),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
 		  SUNXI_FUNCTION(0x2, "spi0"),		/* MOSI */
 		  SUNXI_FUNCTION(0x3, "uart6"),		/* TX */
 		  SUNXI_FUNCTION(0x4, "clk_out_a"),	/* CLK_OUT_A */
-		  SUNXI_FUNCTION_IRQ(0x5, 24)),		/* EINT24 */
+		  SUNXI_FUNCTION_IRQ(0x6, 24)),		/* EINT24 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(I, 13),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
 		  SUNXI_FUNCTION(0x2, "spi0"),		/* MISO */
 		  SUNXI_FUNCTION(0x3, "uart6"),		/* RX */
 		  SUNXI_FUNCTION(0x4, "clk_out_b"),	/* CLK_OUT_B */
-		  SUNXI_FUNCTION_IRQ(0x5, 25)),		/* EINT25 */
+		  SUNXI_FUNCTION_IRQ(0x6, 25)),		/* EINT25 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(I, 14),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
 		  SUNXI_FUNCTION(0x2, "spi0"),		/* CS1 */
 		  SUNXI_FUNCTION(0x3, "ps2"),		/* SCK1 */
 		  SUNXI_FUNCTION(0x4, "timer4"),	/* TCLKIN0 */
-		  SUNXI_FUNCTION_IRQ(0x5, 26)),		/* EINT26 */
+		  SUNXI_FUNCTION_IRQ(0x6, 26)),		/* EINT26 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(I, 15),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
 		  SUNXI_FUNCTION(0x2, "spi1"),		/* CS1 */
 		  SUNXI_FUNCTION(0x3, "ps2"),		/* SDA1 */
 		  SUNXI_FUNCTION(0x4, "timer5"),	/* TCLKIN1 */
-		  SUNXI_FUNCTION_IRQ(0x5, 27)),		/* EINT27 */
+		  SUNXI_FUNCTION_IRQ(0x6, 27)),		/* EINT27 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(I, 16),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
 		  SUNXI_FUNCTION(0x2, "spi1"),		/* CS0 */
 		  SUNXI_FUNCTION(0x3, "uart2"),		/* RTS */
-		  SUNXI_FUNCTION_IRQ(0x5, 28)),		/* EINT28 */
+		  SUNXI_FUNCTION_IRQ(0x6, 28)),		/* EINT28 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(I, 17),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
 		  SUNXI_FUNCTION(0x2, "spi1"),		/* CLK */
 		  SUNXI_FUNCTION(0x3, "uart2"),		/* CTS */
-		  SUNXI_FUNCTION_IRQ(0x5, 29)),		/* EINT29 */
+		  SUNXI_FUNCTION_IRQ(0x6, 29)),		/* EINT29 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(I, 18),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
 		  SUNXI_FUNCTION(0x2, "spi1"),		/* MOSI */
 		  SUNXI_FUNCTION(0x3, "uart2"),		/* TX */
-		  SUNXI_FUNCTION_IRQ(0x5, 30)),		/* EINT30 */
+		  SUNXI_FUNCTION_IRQ(0x6, 30)),		/* EINT30 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(I, 19),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
 		  SUNXI_FUNCTION(0x2, "spi1"),		/* MISO */
 		  SUNXI_FUNCTION(0x3, "uart2"),		/* RX */
-		  SUNXI_FUNCTION_IRQ(0x5, 31)),		/* EINT31 */
+		  SUNXI_FUNCTION_IRQ(0x6, 31)),		/* EINT31 */
 	SUNXI_PIN(SUNXI_PINCTRL_PIN(I, 20),
 		  SUNXI_FUNCTION(0x0, "gpio_in"),
 		  SUNXI_FUNCTION(0x1, "gpio_out"),
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun8i-h3-r.c b/drivers/pinctrl/sunxi/pinctrl-sun8i-h3-r.c
new file mode 100644
index 000000000000..686ec212120b
--- /dev/null
+++ b/drivers/pinctrl/sunxi/pinctrl-sun8i-h3-r.c
@@ -0,0 +1,106 @@
+/*
+ * Allwinner H3 SoCs pinctrl driver.
+ *
+ * Copyright (C) 2016 Krzysztof Adamski <k@japko.eu>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pinctrl/pinctrl.h>
+
+#include "pinctrl-sunxi.h"
+
+static const struct sunxi_desc_pin sun8i_h3_r_pins[] = {
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 0),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_twi"),         /* SCK */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 0)),	/* PL_EINT0 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 1),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_twi"),         /* SDA */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 1)),	/* PL_EINT1 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 2),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_uart"),        /* TX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 2)),	/* PL_EINT2 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 3),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_uart"),        /* RX */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 3)),	/* PL_EINT3 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 4),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_jtag"),        /* MS */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 4)),	/* PL_EINT4 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 5),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_jtag"),        /* CK */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 5)),	/* PL_EINT5 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 6),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_jtag"),        /* DO */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 6)),	/* PL_EINT6 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 7),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_jtag"),        /* DI */
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 7)),	/* PL_EINT7 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 8),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 8)),	/* PL_EINT8 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 9),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 9)),	/* PL_EINT9 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 10),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_pwm"),
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 10)),	/* PL_EINT10 */
+	SUNXI_PIN(SUNXI_PINCTRL_PIN(L, 11),
+		  SUNXI_FUNCTION(0x0, "gpio_in"),
+		  SUNXI_FUNCTION(0x1, "gpio_out"),
+		  SUNXI_FUNCTION(0x2, "s_cir_rx"),
+		  SUNXI_FUNCTION_IRQ_BANK(0x6, 0, 11)),	/* PL_EINT11 */
+};
+
+static const struct sunxi_pinctrl_desc sun8i_h3_r_pinctrl_data = {
+	.pins = sun8i_h3_r_pins,
+	.npins = ARRAY_SIZE(sun8i_h3_r_pins),
+	.irq_banks = 1,
+	.pin_base = PL_BASE,
+	.irq_read_needs_mux = true
+};
+
+static int sun8i_h3_r_pinctrl_probe(struct platform_device *pdev)
+{
+	return sunxi_pinctrl_init(pdev,
+				  &sun8i_h3_r_pinctrl_data);
+}
+
+static const struct of_device_id sun8i_h3_r_pinctrl_match[] = {
+	{ .compatible = "allwinner,sun8i-h3-r-pinctrl", },
+	{}
+};
+
+static struct platform_driver sun8i_h3_r_pinctrl_driver = {
+	.probe	= sun8i_h3_r_pinctrl_probe,
+	.driver	= {
+		.name		= "sun8i-h3-r-pinctrl",
+		.of_match_table	= sun8i_h3_r_pinctrl_match,
+	},
+};
+builtin_platform_driver(sun8i_h3_r_pinctrl_driver);
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun8i-h3.c b/drivers/pinctrl/sunxi/pinctrl-sun8i-h3.c
index 77d4cf047cee..11760bbe9d51 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sun8i-h3.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sun8i-h3.c
@@ -492,6 +492,7 @@ static const struct sunxi_pinctrl_desc sun8i_h3_pinctrl_data = {
 	.pins = sun8i_h3_pins,
 	.npins = ARRAY_SIZE(sun8i_h3_pins),
 	.irq_banks = 2,
+	.irq_read_needs_mux = true
 };
 
 static int sun8i_h3_pinctrl_probe(struct platform_device *pdev)
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun9i-a80-r.c b/drivers/pinctrl/sunxi/pinctrl-sun9i-a80-r.c
index 42547ffa20a8..92a873f73697 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sun9i-a80-r.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sun9i-a80-r.c
@@ -9,7 +9,7 @@
  * warranty of any kind, whether express or implied.
  */
 
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
@@ -164,7 +164,6 @@ static const struct of_device_id sun9i_a80_r_pinctrl_match[] = {
 	{ .compatible = "allwinner,sun9i-a80-r-pinctrl", },
 	{}
 };
-MODULE_DEVICE_TABLE(of, sun9i_a80_r_pinctrl_match);
 
 static struct platform_driver sun9i_a80_r_pinctrl_driver = {
 	.probe	= sun9i_a80_r_pinctrl_probe,
@@ -174,8 +173,4 @@ static struct platform_driver sun9i_a80_r_pinctrl_driver = {
 		.of_match_table	= sun9i_a80_r_pinctrl_match,
 	},
 };
-module_platform_driver(sun9i_a80_r_pinctrl_driver);
-
-MODULE_AUTHOR("Maxime Ripard <maxime.ripard@free-electrons.com");
-MODULE_DESCRIPTION("Allwinner A80 R_PIO pinctrl driver");
-MODULE_LICENSE("GPL");
+builtin_platform_driver(sun9i_a80_r_pinctrl_driver);
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index 7a2465f5e71e..3a2f5619f87c 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -15,7 +15,7 @@
 #include <linux/gpio/driver.h>
 #include <linux/irqdomain.h>
 #include <linux/irqchip/chained_irq.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
@@ -459,15 +459,16 @@ static int sunxi_pinctrl_gpio_get(struct gpio_chip *chip, unsigned offset)
 	u8 index = sunxi_data_offset(offset);
 	u32 set_mux = pctl->desc->irq_read_needs_mux &&
 			test_bit(FLAG_USED_AS_IRQ, &chip->desc[offset].flags);
+	u32 pin = offset + chip->base;
 	u32 val;
 
 	if (set_mux)
-		sunxi_pmx_set(pctl->pctl_dev, offset, SUN4I_FUNC_INPUT);
+		sunxi_pmx_set(pctl->pctl_dev, pin, SUN4I_FUNC_INPUT);
 
 	val = (readl(pctl->membase + reg) >> index) & DATA_PINS_MASK;
 
 	if (set_mux)
-		sunxi_pmx_set(pctl->pctl_dev, offset, SUN4I_FUNC_IRQ);
+		sunxi_pmx_set(pctl->pctl_dev, pin, SUN4I_FUNC_IRQ);
 
 	return !!val;
 }
diff --git a/drivers/pinctrl/tegra/Kconfig b/drivers/pinctrl/tegra/Kconfig
new file mode 100644
index 000000000000..24e20cc08d5b
--- /dev/null
+++ b/drivers/pinctrl/tegra/Kconfig
@@ -0,0 +1,30 @@
+config PINCTRL_TEGRA
+	bool
+	select PINMUX
+	select PINCONF
+
+config PINCTRL_TEGRA20
+	bool
+	select PINCTRL_TEGRA
+
+config PINCTRL_TEGRA30
+	bool
+	select PINCTRL_TEGRA
+
+config PINCTRL_TEGRA114
+	bool
+	select PINCTRL_TEGRA
+
+config PINCTRL_TEGRA124
+	bool
+	select PINCTRL_TEGRA
+
+config PINCTRL_TEGRA210
+	bool
+	select PINCTRL_TEGRA
+
+config PINCTRL_TEGRA_XUSB
+	def_bool y if ARCH_TEGRA
+	select GENERIC_PHY
+	select PINCONF
+	select PINMUX
diff --git a/drivers/pinctrl/tegra/Makefile b/drivers/pinctrl/tegra/Makefile
new file mode 100644
index 000000000000..a927379b6794
--- /dev/null
+++ b/drivers/pinctrl/tegra/Makefile
@@ -0,0 +1,7 @@
+obj-y					+= pinctrl-tegra.o
+obj-$(CONFIG_PINCTRL_TEGRA20)		+= pinctrl-tegra20.o
+obj-$(CONFIG_PINCTRL_TEGRA30)		+= pinctrl-tegra30.o
+obj-$(CONFIG_PINCTRL_TEGRA114)		+= pinctrl-tegra114.o
+obj-$(CONFIG_PINCTRL_TEGRA124)		+= pinctrl-tegra124.o
+obj-$(CONFIG_PINCTRL_TEGRA210)		+= pinctrl-tegra210.o
+obj-$(CONFIG_PINCTRL_TEGRA_XUSB)	+= pinctrl-tegra-xusb.o
diff --git a/drivers/pinctrl/pinctrl-tegra-xusb.c b/drivers/pinctrl/tegra/pinctrl-tegra-xusb.c
index bd3aa5a4fd6d..2f06029c9405 100644
--- a/drivers/pinctrl/pinctrl-tegra-xusb.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra-xusb.c
@@ -24,8 +24,8 @@
 
 #include <dt-bindings/pinctrl/pinctrl-tegra-xusb.h>
 
-#include "core.h"
-#include "pinctrl-utils.h"
+#include "../core.h"
+#include "../pinctrl-utils.h"
 
 #define XUSB_PADCTL_ELPG_PROGRAM 0x01c
 #define XUSB_PADCTL_ELPG_PROGRAM_AUX_MUX_LP0_VCORE_DOWN (1 << 26)
diff --git a/drivers/pinctrl/pinctrl-tegra.c b/drivers/pinctrl/tegra/pinctrl-tegra.c
index 9da4da219a07..49388822c0e9 100644
--- a/drivers/pinctrl/pinctrl-tegra.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra.c
@@ -30,9 +30,9 @@
 #include <linux/pinctrl/pinconf.h>
 #include <linux/slab.h>
 
-#include "core.h"
+#include "../core.h"
+#include "../pinctrl-utils.h"
 #include "pinctrl-tegra.h"
-#include "pinctrl-utils.h"
 
 struct tegra_pmx {
 	struct device *dev;
diff --git a/drivers/pinctrl/pinctrl-tegra.h b/drivers/pinctrl/tegra/pinctrl-tegra.h
index 1615db7e3a4b..1615db7e3a4b 100644
--- a/drivers/pinctrl/pinctrl-tegra.h
+++ b/drivers/pinctrl/tegra/pinctrl-tegra.h
diff --git a/drivers/pinctrl/pinctrl-tegra114.c b/drivers/pinctrl/tegra/pinctrl-tegra114.c
index 05e49d5137ab..05e49d5137ab 100644
--- a/drivers/pinctrl/pinctrl-tegra114.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra114.c
diff --git a/drivers/pinctrl/pinctrl-tegra124.c b/drivers/pinctrl/tegra/pinctrl-tegra124.c
index 7cd44c7c296d..7cd44c7c296d 100644
--- a/drivers/pinctrl/pinctrl-tegra124.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra124.c
diff --git a/drivers/pinctrl/pinctrl-tegra20.c b/drivers/pinctrl/tegra/pinctrl-tegra20.c
index 4833db4433d9..4833db4433d9 100644
--- a/drivers/pinctrl/pinctrl-tegra20.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra20.c
diff --git a/drivers/pinctrl/pinctrl-tegra210.c b/drivers/pinctrl/tegra/pinctrl-tegra210.c
index 252b464901c0..252b464901c0 100644
--- a/drivers/pinctrl/pinctrl-tegra210.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra210.c
diff --git a/drivers/pinctrl/pinctrl-tegra30.c b/drivers/pinctrl/tegra/pinctrl-tegra30.c
index 47b2fd8bb2e9..47b2fd8bb2e9 100644
--- a/drivers/pinctrl/pinctrl-tegra30.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra30.c
diff --git a/drivers/pinctrl/uniphier/Kconfig b/drivers/pinctrl/uniphier/Kconfig
index 7abd614dc383..0b40ded5738f 100644
--- a/drivers/pinctrl/uniphier/Kconfig
+++ b/drivers/pinctrl/uniphier/Kconfig
@@ -1,6 +1,6 @@
 menuconfig PINCTRL_UNIPHIER
 	bool "UniPhier SoC pinctrl drivers"
-	depends on ARCH_UNIPHIER
+	depends on ARCH_UNIPHIER || COMPILE_TEST
 	depends on OF && MFD_SYSCON
 	default y
 	select PINMUX
@@ -8,27 +8,27 @@ menuconfig PINCTRL_UNIPHIER
 
 if PINCTRL_UNIPHIER
 
-config PINCTRL_UNIPHIER_PH1_LD4
+config PINCTRL_UNIPHIER_LD4
 	tristate "UniPhier PH1-LD4 SoC pinctrl driver"
 	default y
 
-config PINCTRL_UNIPHIER_PH1_PRO4
+config PINCTRL_UNIPHIER_PRO4
 	tristate "UniPhier PH1-Pro4 SoC pinctrl driver"
 	default y
 
-config PINCTRL_UNIPHIER_PH1_SLD8
+config PINCTRL_UNIPHIER_SLD8
 	tristate "UniPhier PH1-sLD8 SoC pinctrl driver"
 	default y
 
-config PINCTRL_UNIPHIER_PH1_PRO5
+config PINCTRL_UNIPHIER_PRO5
 	tristate "UniPhier PH1-Pro5 SoC pinctrl driver"
 	default y
 
-config PINCTRL_UNIPHIER_PROXSTREAM2
+config PINCTRL_UNIPHIER_PXS2
 	tristate "UniPhier ProXstream2 SoC pinctrl driver"
 	default y
 
-config PINCTRL_UNIPHIER_PH1_LD6B
+config PINCTRL_UNIPHIER_LD6B
 	tristate "UniPhier PH1-LD6b SoC pinctrl driver"
 	default y
 
diff --git a/drivers/pinctrl/uniphier/Makefile b/drivers/pinctrl/uniphier/Makefile
index e7ce9670306c..3b8f9ee0bb6f 100644
--- a/drivers/pinctrl/uniphier/Makefile
+++ b/drivers/pinctrl/uniphier/Makefile
@@ -1,8 +1,8 @@
-obj-y						+= pinctrl-uniphier-core.o
+obj-y					+= pinctrl-uniphier-core.o
 
-obj-$(CONFIG_PINCTRL_UNIPHIER_PH1_LD4)		+= pinctrl-ph1-ld4.o
-obj-$(CONFIG_PINCTRL_UNIPHIER_PH1_PRO4)		+= pinctrl-ph1-pro4.o
-obj-$(CONFIG_PINCTRL_UNIPHIER_PH1_SLD8)		+= pinctrl-ph1-sld8.o
-obj-$(CONFIG_PINCTRL_UNIPHIER_PH1_PRO5)		+= pinctrl-ph1-pro5.o
-obj-$(CONFIG_PINCTRL_UNIPHIER_PROXSTREAM2)	+= pinctrl-proxstream2.o
-obj-$(CONFIG_PINCTRL_UNIPHIER_PH1_LD6B)		+= pinctrl-ph1-ld6b.o
+obj-$(CONFIG_PINCTRL_UNIPHIER_LD4)	+= pinctrl-uniphier-ld4.o
+obj-$(CONFIG_PINCTRL_UNIPHIER_PRO4)	+= pinctrl-uniphier-pro4.o
+obj-$(CONFIG_PINCTRL_UNIPHIER_SLD8)	+= pinctrl-uniphier-sld8.o
+obj-$(CONFIG_PINCTRL_UNIPHIER_PRO5)	+= pinctrl-uniphier-pro5.o
+obj-$(CONFIG_PINCTRL_UNIPHIER_PXS2)	+= pinctrl-uniphier-pxs2.o
+obj-$(CONFIG_PINCTRL_UNIPHIER_LD6B)	+= pinctrl-uniphier-ld6b.o
diff --git a/drivers/pinctrl/uniphier/pinctrl-ph1-ld4.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c
index a7056dccfa53..a7056dccfa53 100644
--- a/drivers/pinctrl/uniphier/pinctrl-ph1-ld4.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c
diff --git a/drivers/pinctrl/uniphier/pinctrl-ph1-ld6b.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c
index 1824831bb4da..1824831bb4da 100644
--- a/drivers/pinctrl/uniphier/pinctrl-ph1-ld6b.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c
diff --git a/drivers/pinctrl/uniphier/pinctrl-ph1-pro4.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c
index ec8e92dfaf8c..ec8e92dfaf8c 100644
--- a/drivers/pinctrl/uniphier/pinctrl-ph1-pro4.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c
diff --git a/drivers/pinctrl/uniphier/pinctrl-ph1-pro5.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c
index e3d648eae85a..e3d648eae85a 100644
--- a/drivers/pinctrl/uniphier/pinctrl-ph1-pro5.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c
diff --git a/drivers/pinctrl/uniphier/pinctrl-proxstream2.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c
index bc00d7591c59..bc00d7591c59 100644
--- a/drivers/pinctrl/uniphier/pinctrl-proxstream2.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c
diff --git a/drivers/pinctrl/uniphier/pinctrl-ph1-sld8.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c
index c3700a33a5da..c3700a33a5da 100644
--- a/drivers/pinctrl/uniphier/pinctrl-ph1-sld8.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c
diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c
index 20f0ad9bb9f3..e20f23e04c24 100644
--- a/drivers/platform/x86/intel-hid.c
+++ b/drivers/platform/x86/intel-hid.c
@@ -41,8 +41,7 @@ static const struct key_entry intel_hid_keymap[] = {
 	{ KE_KEY, 4, { KEY_HOME } },
 	{ KE_KEY, 5, { KEY_END } },
 	{ KE_KEY, 6, { KEY_PAGEUP } },
-	{ KE_KEY, 4, { KEY_PAGEDOWN } },
-	{ KE_KEY, 4, { KEY_HOME } },
+	{ KE_KEY, 7, { KEY_PAGEDOWN } },
 	{ KE_KEY, 8, { KEY_RFKILL } },
 	{ KE_KEY, 9, { KEY_POWER } },
 	{ KE_KEY, 11, { KEY_SLEEP } },
diff --git a/drivers/platform/x86/intel_scu_ipcutil.c b/drivers/platform/x86/intel_scu_ipcutil.c
index 02bc5a6343c3..aa454241489c 100644
--- a/drivers/platform/x86/intel_scu_ipcutil.c
+++ b/drivers/platform/x86/intel_scu_ipcutil.c
@@ -49,7 +49,7 @@ struct scu_ipc_data {
 
 static int scu_reg_access(u32 cmd, struct scu_ipc_data  *data)
 {
-	int count = data->count;
+	unsigned int count = data->count;
 
 	if (count == 0 || count == 3 || count > 4)
 		return -EINVAL;
diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c
index 05796495be0e..4b717c699313 100644
--- a/drivers/pnp/pnpacpi/rsparser.c
+++ b/drivers/pnp/pnpacpi/rsparser.c
@@ -252,6 +252,10 @@ static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res,
 	case ACPI_RESOURCE_TYPE_GENERIC_REGISTER:
 		break;
 
+	case ACPI_RESOURCE_TYPE_SERIAL_BUS:
+		/* serial bus connections (I2C/SPI/UART) are not pnp */
+		break;
+
 	default:
 		dev_warn(&dev->dev, "unknown resource type %d in _CRS\n",
 			 res->type);
diff --git a/drivers/power/bq27xxx_battery_i2c.c b/drivers/power/bq27xxx_battery_i2c.c
index 9429e66be096..8eafc6f0df88 100644
--- a/drivers/power/bq27xxx_battery_i2c.c
+++ b/drivers/power/bq27xxx_battery_i2c.c
@@ -21,6 +21,9 @@
 
 #include <linux/power/bq27xxx_battery.h>
 
+static DEFINE_IDR(battery_id);
+static DEFINE_MUTEX(battery_mutex);
+
 static irqreturn_t bq27xxx_battery_irq_handler_thread(int irq, void *data)
 {
 	struct bq27xxx_device_info *di = data;
@@ -70,19 +73,33 @@ static int bq27xxx_battery_i2c_probe(struct i2c_client *client,
 {
 	struct bq27xxx_device_info *di;
 	int ret;
+	char *name;
+	int num;
+
+	/* Get new ID for the new battery device */
+	mutex_lock(&battery_mutex);
+	num = idr_alloc(&battery_id, client, 0, 0, GFP_KERNEL);
+	mutex_unlock(&battery_mutex);
+	if (num < 0)
+		return num;
+
+	name = devm_kasprintf(&client->dev, GFP_KERNEL, "%s-%d", id->name, num);
+	if (!name)
+		goto err_mem;
 
 	di = devm_kzalloc(&client->dev, sizeof(*di), GFP_KERNEL);
 	if (!di)
-		return -ENOMEM;
+		goto err_mem;
 
+	di->id = num;
 	di->dev = &client->dev;
 	di->chip = id->driver_data;
-	di->name = id->name;
+	di->name = name;
 	di->bus.read = bq27xxx_battery_i2c_read;
 
 	ret = bq27xxx_battery_setup(di);
 	if (ret)
-		return ret;
+		goto err_failed;
 
 	/* Schedule a polling after about 1 min */
 	schedule_delayed_work(&di->work, 60 * HZ);
@@ -103,6 +120,16 @@ static int bq27xxx_battery_i2c_probe(struct i2c_client *client,
 	}
 
 	return 0;
+
+err_mem:
+	ret = -ENOMEM;
+
+err_failed:
+	mutex_lock(&battery_mutex);
+	idr_remove(&battery_id, num);
+	mutex_unlock(&battery_mutex);
+
+	return ret;
 }
 
 static int bq27xxx_battery_i2c_remove(struct i2c_client *client)
@@ -111,6 +138,10 @@ static int bq27xxx_battery_i2c_remove(struct i2c_client *client)
 
 	bq27xxx_battery_teardown(di);
 
+	mutex_lock(&battery_mutex);
+	idr_remove(&battery_id, di->id);
+	mutex_unlock(&battery_mutex);
+
 	return 0;
 }
 
diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c
index 6c592dc71aee..cdfd01f0adb8 100644
--- a/drivers/powercap/intel_rapl.c
+++ b/drivers/powercap/intel_rapl.c
@@ -133,6 +133,12 @@ struct rapl_domain_data {
 	unsigned long timestamp;
 };
 
+struct msrl_action {
+	u32 msr_no;
+	u64 clear_mask;
+	u64 set_mask;
+	int err;
+};
 
 #define	DOMAIN_STATE_INACTIVE           BIT(0)
 #define	DOMAIN_STATE_POWER_LIMIT_SET    BIT(1)
@@ -149,6 +155,7 @@ struct rapl_power_limit {
 static const char pl1_name[] = "long_term";
 static const char pl2_name[] = "short_term";
 
+struct rapl_package;
 struct rapl_domain {
 	const char *name;
 	enum rapl_domain_type id;
@@ -159,7 +166,7 @@ struct rapl_domain {
 	u64 attr_map; /* track capabilities */
 	unsigned int state;
 	unsigned int domain_energy_unit;
-	int package_id;
+	struct rapl_package *rp;
 };
 #define power_zone_to_rapl_domain(_zone) \
 	container_of(_zone, struct rapl_domain, power_zone)
@@ -184,6 +191,7 @@ struct rapl_package {
 					* notify interrupt enable status.
 					*/
 	struct list_head plist;
+	int lead_cpu; /* one active cpu per package for access */
 };
 
 struct rapl_defaults {
@@ -231,10 +239,10 @@ static int rapl_read_data_raw(struct rapl_domain *rd,
 static int rapl_write_data_raw(struct rapl_domain *rd,
 			enum rapl_primitives prim,
 			unsigned long long value);
-static u64 rapl_unit_xlate(struct rapl_domain *rd, int package,
+static u64 rapl_unit_xlate(struct rapl_domain *rd,
 			enum unit_type type, u64 value,
 			int to_raw);
-static void package_power_limit_irq_save(int package_id);
+static void package_power_limit_irq_save(struct rapl_package *rp);
 
 static LIST_HEAD(rapl_packages); /* guarded by CPU hotplug lock */
 
@@ -260,20 +268,6 @@ static struct rapl_package *find_package_by_id(int id)
 	return NULL;
 }
 
-/* caller to ensure CPU hotplug lock is held */
-static int find_active_cpu_on_package(int package_id)
-{
-	int i;
-
-	for_each_online_cpu(i) {
-		if (topology_physical_package_id(i) == package_id)
-			return i;
-	}
-	/* all CPUs on this package are offline */
-
-	return -ENODEV;
-}
-
 /* caller must hold cpu hotplug lock */
 static void rapl_cleanup_data(void)
 {
@@ -312,25 +306,19 @@ static int get_max_energy_counter(struct powercap_zone *pcd_dev, u64 *energy)
 {
 	struct rapl_domain *rd = power_zone_to_rapl_domain(pcd_dev);
 
-	*energy = rapl_unit_xlate(rd, 0, ENERGY_UNIT, ENERGY_STATUS_MASK, 0);
+	*energy = rapl_unit_xlate(rd, ENERGY_UNIT, ENERGY_STATUS_MASK, 0);
 	return 0;
 }
 
 static int release_zone(struct powercap_zone *power_zone)
 {
 	struct rapl_domain *rd = power_zone_to_rapl_domain(power_zone);
-	struct rapl_package *rp;
+	struct rapl_package *rp = rd->rp;
 
 	/* package zone is the last zone of a package, we can free
 	 * memory here since all children has been unregistered.
 	 */
 	if (rd->id == RAPL_DOMAIN_PACKAGE) {
-		rp = find_package_by_id(rd->package_id);
-		if (!rp) {
-			dev_warn(&power_zone->dev, "no package id %s\n",
-				rd->name);
-			return -ENODEV;
-		}
 		kfree(rd);
 		rp->domains = NULL;
 	}
@@ -432,11 +420,7 @@ static int set_power_limit(struct powercap_zone *power_zone, int id,
 
 	get_online_cpus();
 	rd = power_zone_to_rapl_domain(power_zone);
-	rp = find_package_by_id(rd->package_id);
-	if (!rp) {
-		ret = -ENODEV;
-		goto set_exit;
-	}
+	rp = rd->rp;
 
 	if (rd->state & DOMAIN_STATE_BIOS_LOCKED) {
 		dev_warn(&power_zone->dev, "%s locked by BIOS, monitoring only\n",
@@ -456,7 +440,7 @@ static int set_power_limit(struct powercap_zone *power_zone, int id,
 		ret = -EINVAL;
 	}
 	if (!ret)
-		package_power_limit_irq_save(rd->package_id);
+		package_power_limit_irq_save(rp);
 set_exit:
 	put_online_cpus();
 	return ret;
@@ -655,24 +639,19 @@ static void rapl_init_domains(struct rapl_package *rp)
 			break;
 		}
 		if (mask) {
-			rd->package_id = rp->id;
+			rd->rp = rp;
 			rd++;
 		}
 	}
 }
 
-static u64 rapl_unit_xlate(struct rapl_domain *rd, int package,
-			enum unit_type type, u64 value,
-			int to_raw)
+static u64 rapl_unit_xlate(struct rapl_domain *rd, enum unit_type type,
+			u64 value, int to_raw)
 {
 	u64 units = 1;
-	struct rapl_package *rp;
+	struct rapl_package *rp = rd->rp;
 	u64 scale = 1;
 
-	rp = find_package_by_id(package);
-	if (!rp)
-		return value;
-
 	switch (type) {
 	case POWER_UNIT:
 		units = rp->power_unit;
@@ -769,10 +748,8 @@ static int rapl_read_data_raw(struct rapl_domain *rd,
 	msr = rd->msrs[rp->id];
 	if (!msr)
 		return -EINVAL;
-	/* use physical package id to look up active cpus */
-	cpu = find_active_cpu_on_package(rd->package_id);
-	if (cpu < 0)
-		return cpu;
+
+	cpu = rd->rp->lead_cpu;
 
 	/* special-case package domain, which uses a different bit*/
 	if (prim == FW_LOCK && rd->id == RAPL_DOMAIN_PACKAGE) {
@@ -793,42 +770,66 @@ static int rapl_read_data_raw(struct rapl_domain *rd,
 	final = value & rp->mask;
 	final = final >> rp->shift;
 	if (xlate)
-		*data = rapl_unit_xlate(rd, rd->package_id, rp->unit, final, 0);
+		*data = rapl_unit_xlate(rd, rp->unit, final, 0);
 	else
 		*data = final;
 
 	return 0;
 }
 
+
+static int msrl_update_safe(u32 msr_no, u64 clear_mask, u64 set_mask)
+{
+	int err;
+	u64 val;
+
+	err = rdmsrl_safe(msr_no, &val);
+	if (err)
+		goto out;
+
+	val &= ~clear_mask;
+	val |= set_mask;
+
+	err = wrmsrl_safe(msr_no, val);
+
+out:
+	return err;
+}
+
+static void msrl_update_func(void *info)
+{
+	struct msrl_action *ma = info;
+
+	ma->err = msrl_update_safe(ma->msr_no, ma->clear_mask, ma->set_mask);
+}
+
 /* Similar use of primitive info in the read counterpart */
 static int rapl_write_data_raw(struct rapl_domain *rd,
 			enum rapl_primitives prim,
 			unsigned long long value)
 {
-	u64 msr_val;
-	u32 msr;
 	struct rapl_primitive_info *rp = &rpi[prim];
 	int cpu;
+	u64 bits;
+	struct msrl_action ma;
+	int ret;
 
-	cpu = find_active_cpu_on_package(rd->package_id);
-	if (cpu < 0)
-		return cpu;
-	msr = rd->msrs[rp->id];
-	if (rdmsrl_safe_on_cpu(cpu, msr, &msr_val)) {
-		dev_dbg(&rd->power_zone.dev,
-			"failed to read msr 0x%x on cpu %d\n", msr, cpu);
-		return -EIO;
-	}
-	value = rapl_unit_xlate(rd, rd->package_id, rp->unit, value, 1);
-	msr_val &= ~rp->mask;
-	msr_val |= value << rp->shift;
-	if (wrmsrl_safe_on_cpu(cpu, msr, msr_val)) {
-		dev_dbg(&rd->power_zone.dev,
-			"failed to write msr 0x%x on cpu %d\n", msr, cpu);
-		return -EIO;
-	}
+	cpu = rd->rp->lead_cpu;
+	bits = rapl_unit_xlate(rd, rp->unit, value, 1);
+	bits |= bits << rp->shift;
+	memset(&ma, 0, sizeof(ma));
 
-	return 0;
+	ma.msr_no = rd->msrs[rp->id];
+	ma.clear_mask = rp->mask;
+	ma.set_mask = bits;
+
+	ret = smp_call_function_single(cpu, msrl_update_func, &ma, 1);
+	if (ret)
+		WARN_ON_ONCE(ret);
+	else
+		ret = ma.err;
+
+	return ret;
 }
 
 /*
@@ -893,6 +894,21 @@ static int rapl_check_unit_atom(struct rapl_package *rp, int cpu)
 	return 0;
 }
 
+static void power_limit_irq_save_cpu(void *info)
+{
+	u32 l, h = 0;
+	struct rapl_package *rp = (struct rapl_package *)info;
+
+	/* save the state of PLN irq mask bit before disabling it */
+	rdmsr_safe(MSR_IA32_PACKAGE_THERM_INTERRUPT, &l, &h);
+	if (!(rp->power_limit_irq & PACKAGE_PLN_INT_SAVED)) {
+		rp->power_limit_irq = l & PACKAGE_THERM_INT_PLN_ENABLE;
+		rp->power_limit_irq |= PACKAGE_PLN_INT_SAVED;
+	}
+	l &= ~PACKAGE_THERM_INT_PLN_ENABLE;
+	wrmsr_safe(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h);
+}
+
 
 /* REVISIT:
  * When package power limit is set artificially low by RAPL, LVT
@@ -904,61 +920,40 @@ static int rapl_check_unit_atom(struct rapl_package *rp, int cpu)
  * to do by adding an atomic notifier.
  */
 
-static void package_power_limit_irq_save(int package_id)
+static void package_power_limit_irq_save(struct rapl_package *rp)
 {
-	u32 l, h = 0;
-	int cpu;
-	struct rapl_package *rp;
-
-	rp = find_package_by_id(package_id);
-	if (!rp)
-		return;
-
 	if (!boot_cpu_has(X86_FEATURE_PTS) || !boot_cpu_has(X86_FEATURE_PLN))
 		return;
 
-	cpu = find_active_cpu_on_package(package_id);
-	if (cpu < 0)
-		return;
-	/* save the state of PLN irq mask bit before disabling it */
-	rdmsr_safe_on_cpu(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &l, &h);
-	if (!(rp->power_limit_irq & PACKAGE_PLN_INT_SAVED)) {
-		rp->power_limit_irq = l & PACKAGE_THERM_INT_PLN_ENABLE;
-		rp->power_limit_irq |= PACKAGE_PLN_INT_SAVED;
-	}
-	l &= ~PACKAGE_THERM_INT_PLN_ENABLE;
-	wrmsr_on_cpu(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h);
+	smp_call_function_single(rp->lead_cpu, power_limit_irq_save_cpu, rp, 1);
 }
 
-/* restore per package power limit interrupt enable state */
-static void package_power_limit_irq_restore(int package_id)
+static void power_limit_irq_restore_cpu(void *info)
 {
-	u32 l, h;
-	int cpu;
-	struct rapl_package *rp;
+	u32 l, h = 0;
+	struct rapl_package *rp = (struct rapl_package *)info;
 
-	rp = find_package_by_id(package_id);
-	if (!rp)
-		return;
+	rdmsr_safe(MSR_IA32_PACKAGE_THERM_INTERRUPT, &l, &h);
 
-	if (!boot_cpu_has(X86_FEATURE_PTS) || !boot_cpu_has(X86_FEATURE_PLN))
-		return;
+	if (rp->power_limit_irq & PACKAGE_THERM_INT_PLN_ENABLE)
+		l |= PACKAGE_THERM_INT_PLN_ENABLE;
+	else
+		l &= ~PACKAGE_THERM_INT_PLN_ENABLE;
+
+	wrmsr_safe(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h);
+}
 
-	cpu = find_active_cpu_on_package(package_id);
-	if (cpu < 0)
+/* restore per package power limit interrupt enable state */
+static void package_power_limit_irq_restore(struct rapl_package *rp)
+{
+	if (!boot_cpu_has(X86_FEATURE_PTS) || !boot_cpu_has(X86_FEATURE_PLN))
 		return;
 
 	/* irq enable state not saved, nothing to restore */
 	if (!(rp->power_limit_irq & PACKAGE_PLN_INT_SAVED))
 		return;
-	rdmsr_safe_on_cpu(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &l, &h);
-
-	if (rp->power_limit_irq & PACKAGE_THERM_INT_PLN_ENABLE)
-		l |= PACKAGE_THERM_INT_PLN_ENABLE;
-	else
-		l &= ~PACKAGE_THERM_INT_PLN_ENABLE;
 
-	wrmsr_on_cpu(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h);
+	smp_call_function_single(rp->lead_cpu, power_limit_irq_restore_cpu, rp, 1);
 }
 
 static void set_floor_freq_default(struct rapl_domain *rd, bool mode)
@@ -1141,7 +1136,7 @@ static int rapl_unregister_powercap(void)
 	 * hotplug lock held
 	 */
 	list_for_each_entry(rp, &rapl_packages, plist) {
-		package_power_limit_irq_restore(rp->id);
+		package_power_limit_irq_restore(rp);
 
 		for (rd = rp->domains; rd < rp->domains + rp->nr_domains;
 		     rd++) {
@@ -1392,7 +1387,8 @@ static int rapl_detect_topology(void)
 			/* add the new package to the list */
 			new_package->id = phy_package_id;
 			new_package->nr_cpus = 1;
-
+			/* use the first active cpu of the package to access */
+			new_package->lead_cpu = i;
 			/* check if the package contains valid domains */
 			if (rapl_detect_domains(new_package, i) ||
 				rapl_defaults->check_unit(new_package, i)) {
@@ -1448,6 +1444,8 @@ static int rapl_add_package(int cpu)
 	/* add the new package to the list */
 	rp->id = phy_package_id;
 	rp->nr_cpus = 1;
+	rp->lead_cpu = cpu;
+
 	/* check if the package contains valid domains */
 	if (rapl_detect_domains(rp, cpu) ||
 		rapl_defaults->check_unit(rp, cpu)) {
@@ -1480,6 +1478,7 @@ static int rapl_cpu_callback(struct notifier_block *nfb,
 	unsigned long cpu = (unsigned long)hcpu;
 	int phy_package_id;
 	struct rapl_package *rp;
+	int lead_cpu;
 
 	phy_package_id = topology_physical_package_id(cpu);
 	switch (action) {
@@ -1500,6 +1499,15 @@ static int rapl_cpu_callback(struct notifier_block *nfb,
 			break;
 		if (--rp->nr_cpus == 0)
 			rapl_remove_package(rp);
+		else if (cpu == rp->lead_cpu) {
+			/* choose another active cpu in the package */
+			lead_cpu = cpumask_any_but(topology_core_cpumask(cpu), cpu);
+			if (lead_cpu < nr_cpu_ids)
+				rp->lead_cpu = lead_cpu;
+			else /* should never go here */
+				pr_err("no active cpu available for package %d\n",
+					phy_package_id);
+		}
 	}
 
 	return NOTIFY_OK;
diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index da7bae991552..579fd65299a0 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -22,6 +22,7 @@
 #include <linux/poll.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/timekeeping.h>
 
 #include "ptp_private.h"
 
@@ -120,11 +121,13 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 	struct ptp_clock_caps caps;
 	struct ptp_clock_request req;
 	struct ptp_sys_offset *sysoff = NULL;
+	struct ptp_sys_offset_precise precise_offset;
 	struct ptp_pin_desc pd;
 	struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
 	struct ptp_clock_info *ops = ptp->info;
 	struct ptp_clock_time *pct;
 	struct timespec64 ts;
+	struct system_device_crosststamp xtstamp;
 	int enable, err = 0;
 	unsigned int i, pin_index;
 
@@ -138,6 +141,7 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 		caps.n_per_out = ptp->info->n_per_out;
 		caps.pps = ptp->info->pps;
 		caps.n_pins = ptp->info->n_pins;
+		caps.cross_timestamping = ptp->info->getcrosststamp != NULL;
 		if (copy_to_user((void __user *)arg, &caps, sizeof(caps)))
 			err = -EFAULT;
 		break;
@@ -180,6 +184,29 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 		err = ops->enable(ops, &req, enable);
 		break;
 
+	case PTP_SYS_OFFSET_PRECISE:
+		if (!ptp->info->getcrosststamp) {
+			err = -EOPNOTSUPP;
+			break;
+		}
+		err = ptp->info->getcrosststamp(ptp->info, &xtstamp);
+		if (err)
+			break;
+
+		ts = ktime_to_timespec64(xtstamp.device);
+		precise_offset.device.sec = ts.tv_sec;
+		precise_offset.device.nsec = ts.tv_nsec;
+		ts = ktime_to_timespec64(xtstamp.sys_realtime);
+		precise_offset.sys_realtime.sec = ts.tv_sec;
+		precise_offset.sys_realtime.nsec = ts.tv_nsec;
+		ts = ktime_to_timespec64(xtstamp.sys_monoraw);
+		precise_offset.sys_monoraw.sec = ts.tv_sec;
+		precise_offset.sys_monoraw.nsec = ts.tv_nsec;
+		if (copy_to_user((void __user *)arg, &precise_offset,
+				 sizeof(precise_offset)))
+			err = -EFAULT;
+		break;
+
 	case PTP_SYS_OFFSET:
 		sysoff = kmalloc(sizeof(*sysoff), GFP_KERNEL);
 		if (!sysoff) {
diff --git a/drivers/rapidio/rio.c b/drivers/rapidio/rio.c
index d7b87c64b7cd..e220edc85c68 100644
--- a/drivers/rapidio/rio.c
+++ b/drivers/rapidio/rio.c
@@ -117,7 +117,7 @@ int rio_request_inb_mbox(struct rio_mport *mport,
 	if (mport->ops->open_inb_mbox == NULL)
 		goto out;
 
-	res = kmalloc(sizeof(struct resource), GFP_KERNEL);
+	res = kzalloc(sizeof(struct resource), GFP_KERNEL);
 
 	if (res) {
 		rio_init_mbox_res(res, mbox, mbox);
@@ -185,7 +185,7 @@ int rio_request_outb_mbox(struct rio_mport *mport,
 	if (mport->ops->open_outb_mbox == NULL)
 		goto out;
 
-	res = kmalloc(sizeof(struct resource), GFP_KERNEL);
+	res = kzalloc(sizeof(struct resource), GFP_KERNEL);
 
 	if (res) {
 		rio_init_mbox_res(res, mbox, mbox);
@@ -285,7 +285,7 @@ int rio_request_inb_dbell(struct rio_mport *mport,
 {
 	int rc = 0;
 
-	struct resource *res = kmalloc(sizeof(struct resource), GFP_KERNEL);
+	struct resource *res = kzalloc(sizeof(struct resource), GFP_KERNEL);
 
 	if (res) {
 		rio_init_dbell_res(res, start, end);
@@ -360,7 +360,7 @@ int rio_release_inb_dbell(struct rio_mport *mport, u16 start, u16 end)
 struct resource *rio_request_outb_dbell(struct rio_dev *rdev, u16 start,
 					u16 end)
 {
-	struct resource *res = kmalloc(sizeof(struct resource), GFP_KERNEL);
+	struct resource *res = kzalloc(sizeof(struct resource), GFP_KERNEL);
 
 	if (res) {
 		rio_init_dbell_res(res, start, end);
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 8155e80dd3f8..91040ec8e242 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -78,6 +78,15 @@ config REGULATOR_ACT8865
 	  This driver controls a active-semi act8865 voltage output
 	  regulator via I2C bus.
 
+config REGULATOR_ACT8945A
+	tristate "Active-semi ACT8945A voltage regulator"
+	depends on MFD_ACT8945A
+	help
+	  This driver controls a active-semi ACT8945A voltage regulator
+	  via I2C bus. The ACT8945A features three step-down DC/DC converters
+	  and four low-dropout linear regulators, along with a ActivePath
+	  battery charger.
+
 config REGULATOR_AD5398
 	tristate "Analog Devices AD5398/AD5821 regulators"
 	depends on I2C
@@ -261,6 +270,14 @@ config REGULATOR_HI6421
 	  21 general purpose LDOs, 3 dedicated LDOs, and 5 BUCKs. All
 	  of them come with support to either ECO (idle) or sleep mode.
 
+config REGULATOR_HI655X
+	tristate "Hisilicon HI655X PMIC regulators support"
+	depends on ARCH_HISI || COMPILE_TEST
+	depends on MFD_HI655X_PMIC && OF
+	help
+	  This driver provides support for the voltage regulators of the
+	  Hisilicon Hi655x PMIC device.
+
 config REGULATOR_ISL9305
 	tristate "Intersil ISL9305 regulator"
 	depends on I2C
@@ -343,6 +360,15 @@ config REGULATOR_MAX1586
 	  regulator via I2C bus. The provided regulator is suitable
 	  for PXA27x chips to control VCC_CORE and VCC_USIM voltages.
 
+config REGULATOR_MAX77620
+	tristate "Maxim 77620/MAX20024 voltage regulator"
+	depends on MFD_MAX77620
+	help
+	  This driver controls Maxim MAX77620 voltage output regulator
+	  via I2C bus. The provided regulator is suitable for Tegra
+	  chip to control Step-Down DC-DC and LDOs. Say Y here to
+	  enable the regulator driver.
+
 config REGULATOR_MAX8649
 	tristate "Maxim 8649 voltage regulator"
 	depends on I2C
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index 980b1943fa81..61bfbb9d4a0c 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -15,6 +15,7 @@ obj-$(CONFIG_REGULATOR_AAT2870) += aat2870-regulator.o
 obj-$(CONFIG_REGULATOR_AB3100) += ab3100.o
 obj-$(CONFIG_REGULATOR_AB8500)	+= ab8500-ext.o ab8500.o
 obj-$(CONFIG_REGULATOR_ACT8865) += act8865-regulator.o
+obj-$(CONFIG_REGULATOR_ACT8945A) += act8945a-regulator.o
 obj-$(CONFIG_REGULATOR_AD5398) += ad5398.o
 obj-$(CONFIG_REGULATOR_ANATOP) += anatop-regulator.o
 obj-$(CONFIG_REGULATOR_ARIZONA) += arizona-micsupp.o arizona-ldo1.o
@@ -34,6 +35,7 @@ obj-$(CONFIG_REGULATOR_DB8500_PRCMU) += db8500-prcmu.o
 obj-$(CONFIG_REGULATOR_FAN53555) += fan53555.o
 obj-$(CONFIG_REGULATOR_GPIO) += gpio-regulator.o
 obj-$(CONFIG_REGULATOR_HI6421) += hi6421-regulator.o
+obj-$(CONFIG_REGULATOR_HI655X) += hi655x-regulator.o
 obj-$(CONFIG_REGULATOR_ISL6271A) += isl6271a-regulator.o
 obj-$(CONFIG_REGULATOR_ISL9305) += isl9305.o
 obj-$(CONFIG_REGULATOR_LM363X) += lm363x-regulator.o
@@ -46,6 +48,7 @@ obj-$(CONFIG_REGULATOR_LP8755) += lp8755.o
 obj-$(CONFIG_REGULATOR_LTC3589) += ltc3589.o
 obj-$(CONFIG_REGULATOR_MAX14577) += max14577.o
 obj-$(CONFIG_REGULATOR_MAX1586) += max1586.o
+obj-$(CONFIG_REGULATOR_MAX77620) += max77620-regulator.o
 obj-$(CONFIG_REGULATOR_MAX8649)	+= max8649.o
 obj-$(CONFIG_REGULATOR_MAX8660) += max8660.o
 obj-$(CONFIG_REGULATOR_MAX8907) += max8907-regulator.o
@@ -54,9 +57,9 @@ obj-$(CONFIG_REGULATOR_MAX8952) += max8952.o
 obj-$(CONFIG_REGULATOR_MAX8973) += max8973-regulator.o
 obj-$(CONFIG_REGULATOR_MAX8997) += max8997.o
 obj-$(CONFIG_REGULATOR_MAX8998) += max8998.o
-obj-$(CONFIG_REGULATOR_MAX77686) += max77686.o
+obj-$(CONFIG_REGULATOR_MAX77686) += max77686-regulator.o
 obj-$(CONFIG_REGULATOR_MAX77693) += max77693.o
-obj-$(CONFIG_REGULATOR_MAX77802) += max77802.o
+obj-$(CONFIG_REGULATOR_MAX77802) += max77802-regulator.o
 obj-$(CONFIG_REGULATOR_MC13783) += mc13783-regulator.o
 obj-$(CONFIG_REGULATOR_MC13892) += mc13892-regulator.o
 obj-$(CONFIG_REGULATOR_MC13XXX_CORE) +=  mc13xxx-regulator-core.o
@@ -98,7 +101,7 @@ obj-$(CONFIG_REGULATOR_TPS65910) += tps65910-regulator.o
 obj-$(CONFIG_REGULATOR_TPS65912) += tps65912-regulator.o
 obj-$(CONFIG_REGULATOR_TPS80031) += tps80031-regulator.o
 obj-$(CONFIG_REGULATOR_TWL4030) += twl-regulator.o
-obj-$(CONFIG_REGULATOR_VEXPRESS) += vexpress.o
+obj-$(CONFIG_REGULATOR_VEXPRESS) += vexpress-regulator.o
 obj-$(CONFIG_REGULATOR_WM831X) += wm831x-dcdc.o
 obj-$(CONFIG_REGULATOR_WM831X) += wm831x-isink.o
 obj-$(CONFIG_REGULATOR_WM831X) += wm831x-ldo.o
diff --git a/drivers/regulator/act8865-regulator.c b/drivers/regulator/act8865-regulator.c
index f8d4cd3d1397..000d566e32a4 100644
--- a/drivers/regulator/act8865-regulator.c
+++ b/drivers/regulator/act8865-regulator.c
@@ -218,7 +218,7 @@ static const struct regulator_desc act8600_regulators[] = {
 		.ops = &act8865_ldo_ops,
 		.type = REGULATOR_VOLTAGE,
 		.n_voltages = 1,
-		.fixed_uV = 1800000,
+		.fixed_uV = 3300000,
 		.enable_reg = ACT8600_LDO910_CTRL,
 		.enable_mask = ACT8865_ENA,
 		.owner = THIS_MODULE,
@@ -369,7 +369,7 @@ static int act8865_pdata_from_dt(struct device *dev,
 	for (i = 0; i < num_matches; i++) {
 		regulator->id = i;
 		regulator->name = matches[i].name;
-		regulator->platform_data = matches[i].init_data;
+		regulator->init_data = matches[i].init_data;
 		of_node[i] = matches[i].of_node;
 		regulator++;
 	}
@@ -396,7 +396,7 @@ static struct regulator_init_data
 
 	for (i = 0; i < pdata->num_regulators; i++) {
 		if (pdata->regulators[i].id == id)
-			return pdata->regulators[i].platform_data;
+			return pdata->regulators[i].init_data;
 	}
 
 	return NULL;
@@ -415,7 +415,7 @@ static void act8865_power_off(void)
 static int act8865_pmic_probe(struct i2c_client *client,
 			      const struct i2c_device_id *i2c_id)
 {
-	static const struct regulator_desc *regulators;
+	const struct regulator_desc *regulators;
 	struct act8865_platform_data pdata_of, *pdata;
 	struct device *dev = &client->dev;
 	struct device_node **of_node;
diff --git a/drivers/regulator/act8945a-regulator.c b/drivers/regulator/act8945a-regulator.c
new file mode 100644
index 000000000000..441864b9fece
--- /dev/null
+++ b/drivers/regulator/act8945a-regulator.c
@@ -0,0 +1,165 @@
+/*
+ * Voltage regulation driver for active-semi ACT8945A PMIC
+ *
+ * Copyright (C) 2015 Atmel Corporation
+ *
+ * Author: Wenyou Yang <wenyou.yang@atmel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+
+/**
+ * ACT8945A Global Register Map.
+ */
+#define ACT8945A_SYS_MODE	0x00
+#define ACT8945A_SYS_CTRL	0x01
+#define ACT8945A_DCDC1_VSET1	0x20
+#define ACT8945A_DCDC1_VSET2	0x21
+#define ACT8945A_DCDC1_CTRL	0x22
+#define ACT8945A_DCDC2_VSET1	0x30
+#define ACT8945A_DCDC2_VSET2	0x31
+#define ACT8945A_DCDC2_CTRL	0x32
+#define ACT8945A_DCDC3_VSET1	0x40
+#define ACT8945A_DCDC3_VSET2	0x41
+#define ACT8945A_DCDC3_CTRL	0x42
+#define ACT8945A_LDO1_VSET	0x50
+#define ACT8945A_LDO1_CTRL	0x51
+#define ACT8945A_LDO2_VSET	0x54
+#define ACT8945A_LDO2_CTRL	0x55
+#define ACT8945A_LDO3_VSET	0x60
+#define ACT8945A_LDO3_CTRL	0x61
+#define ACT8945A_LDO4_VSET	0x64
+#define ACT8945A_LDO4_CTRL	0x65
+
+/**
+ * Field Definitions.
+ */
+#define ACT8945A_ENA		0x80	/* ON - [7] */
+#define ACT8945A_VSEL_MASK	0x3F	/* VSET - [5:0] */
+
+/**
+ * ACT8945A Voltage Number
+ */
+#define ACT8945A_VOLTAGE_NUM	64
+
+enum {
+	ACT8945A_ID_DCDC1,
+	ACT8945A_ID_DCDC2,
+	ACT8945A_ID_DCDC3,
+	ACT8945A_ID_LDO1,
+	ACT8945A_ID_LDO2,
+	ACT8945A_ID_LDO3,
+	ACT8945A_ID_LDO4,
+	ACT8945A_REG_NUM,
+};
+
+static const struct regulator_linear_range act8945a_voltage_ranges[] = {
+	REGULATOR_LINEAR_RANGE(600000, 0, 23, 25000),
+	REGULATOR_LINEAR_RANGE(1200000, 24, 47, 50000),
+	REGULATOR_LINEAR_RANGE(2400000, 48, 63, 100000),
+};
+
+static struct regulator_ops act8945a_ops = {
+	.list_voltage		= regulator_list_voltage_linear_range,
+	.map_voltage		= regulator_map_voltage_linear_range,
+	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
+	.set_voltage_sel	= regulator_set_voltage_sel_regmap,
+	.enable			= regulator_enable_regmap,
+	.disable		= regulator_disable_regmap,
+	.is_enabled		= regulator_is_enabled_regmap,
+};
+
+#define ACT89xx_REG(_name, _family, _id, _vsel_reg, _supply)		\
+	[_family##_ID_##_id] = {					\
+		.name			= _name,			\
+		.supply_name		= _supply,			\
+		.of_match		= of_match_ptr("REG_"#_id),	\
+		.regulators_node	= of_match_ptr("regulators"),	\
+		.id			= _family##_ID_##_id,		\
+		.type			= REGULATOR_VOLTAGE,		\
+		.ops			= &act8945a_ops,		\
+		.n_voltages		= ACT8945A_VOLTAGE_NUM,		\
+		.linear_ranges		= act8945a_voltage_ranges,	\
+		.n_linear_ranges	= ARRAY_SIZE(act8945a_voltage_ranges), \
+		.vsel_reg		= _family##_##_id##_##_vsel_reg, \
+		.vsel_mask		= ACT8945A_VSEL_MASK,		\
+		.enable_reg		= _family##_##_id##_CTRL,	\
+		.enable_mask		= ACT8945A_ENA,			\
+		.owner			= THIS_MODULE,			\
+	}
+
+static const struct regulator_desc act8945a_regulators[] = {
+	ACT89xx_REG("DCDC_REG1", ACT8945A, DCDC1, VSET1, "vp1"),
+	ACT89xx_REG("DCDC_REG2", ACT8945A, DCDC2, VSET1, "vp2"),
+	ACT89xx_REG("DCDC_REG3", ACT8945A, DCDC3, VSET1, "vp3"),
+	ACT89xx_REG("LDO_REG1", ACT8945A, LDO1, VSET, "inl45"),
+	ACT89xx_REG("LDO_REG2", ACT8945A, LDO2, VSET, "inl45"),
+	ACT89xx_REG("LDO_REG3", ACT8945A, LDO3, VSET, "inl67"),
+	ACT89xx_REG("LDO_REG4", ACT8945A, LDO4, VSET, "inl67"),
+};
+
+static const struct regulator_desc act8945a_alt_regulators[] = {
+	ACT89xx_REG("DCDC_REG1", ACT8945A, DCDC1, VSET2, "vp1"),
+	ACT89xx_REG("DCDC_REG2", ACT8945A, DCDC2, VSET2, "vp2"),
+	ACT89xx_REG("DCDC_REG3", ACT8945A, DCDC3, VSET2, "vp3"),
+	ACT89xx_REG("LDO_REG1", ACT8945A, LDO1, VSET, "inl45"),
+	ACT89xx_REG("LDO_REG2", ACT8945A, LDO2, VSET, "inl45"),
+	ACT89xx_REG("LDO_REG3", ACT8945A, LDO3, VSET, "inl67"),
+	ACT89xx_REG("LDO_REG4", ACT8945A, LDO4, VSET, "inl67"),
+};
+
+static int act8945a_pmic_probe(struct platform_device *pdev)
+{
+	struct regulator_config config = { };
+	const struct regulator_desc *regulators;
+	struct regulator_dev *rdev;
+	int i, num_regulators;
+	bool voltage_select;
+
+	voltage_select = of_property_read_bool(pdev->dev.parent->of_node,
+					       "active-semi,vsel-high");
+
+	if (voltage_select) {
+		regulators = act8945a_alt_regulators;
+		num_regulators = ARRAY_SIZE(act8945a_alt_regulators);
+	} else {
+		regulators = act8945a_regulators;
+		num_regulators = ARRAY_SIZE(act8945a_regulators);
+	}
+
+	config.dev = &pdev->dev;
+	config.dev->of_node = pdev->dev.parent->of_node;
+	for (i = 0; i < num_regulators; i++) {
+		rdev = devm_regulator_register(&pdev->dev, &regulators[i], &config);
+		if (IS_ERR(rdev)) {
+			dev_err(&pdev->dev,
+				"failed to register %s regulator\n",
+				regulators[i].name);
+			return PTR_ERR(rdev);
+		}
+	}
+
+	return 0;
+}
+
+static struct platform_driver act8945a_pmic_driver = {
+	.driver = {
+		.name = "act8945a-regulator",
+	},
+	.probe = act8945a_pmic_probe,
+};
+module_platform_driver(act8945a_pmic_driver);
+
+MODULE_DESCRIPTION("Active-semi ACT8945A voltage regulator driver");
+MODULE_AUTHOR("Wenyou Yang <wenyou.yang@atmel.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/regulator/ad5398.c b/drivers/regulator/ad5398.c
index ea50a886ba63..8b0f788a9bbb 100644
--- a/drivers/regulator/ad5398.c
+++ b/drivers/regulator/ad5398.c
@@ -58,10 +58,12 @@ static int ad5398_write_reg(struct i2c_client *client, const unsigned short data
 
 	val = cpu_to_be16(data);
 	ret = i2c_master_send(client, (char *)&val, 2);
-	if (ret < 0)
+	if (ret != 2) {
 		dev_err(&client->dev, "I2C write error\n");
+		return ret < 0 ? ret : -EIO;
+	}
 
-	return ret;
+	return 0;
 }
 
 static int ad5398_get_current_limit(struct regulator_dev *rdev)
diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c
index f2e1a39ce0f3..214e815e98eb 100644
--- a/drivers/regulator/axp20x-regulator.c
+++ b/drivers/regulator/axp20x-regulator.c
@@ -39,7 +39,7 @@
 #define AXP_DESC_IO(_family, _id, _match, _supply, _min, _max, _step, _vreg,	\
 		    _vmask, _ereg, _emask, _enable_val, _disable_val)		\
 	[_family##_##_id] = {							\
-		.name		= #_id,						\
+		.name		= (_match),					\
 		.supply_name	= (_supply),					\
 		.of_match	= of_match_ptr(_match),				\
 		.regulators_node = of_match_ptr("regulators"),			\
@@ -61,7 +61,7 @@
 #define AXP_DESC(_family, _id, _match, _supply, _min, _max, _step, _vreg,	\
 		 _vmask, _ereg, _emask) 					\
 	[_family##_##_id] = {							\
-		.name		= #_id,						\
+		.name		= (_match),					\
 		.supply_name	= (_supply),					\
 		.of_match	= of_match_ptr(_match),				\
 		.regulators_node = of_match_ptr("regulators"),			\
@@ -78,21 +78,15 @@
 		.ops		= &axp20x_ops,					\
 	}
 
-#define AXP_DESC_SW(_family, _id, _match, _supply, _min, _max, _step, _vreg,	\
-		    _vmask, _ereg, _emask) 					\
+#define AXP_DESC_SW(_family, _id, _match, _supply, _ereg, _emask)		\
 	[_family##_##_id] = {							\
-		.name		= #_id,						\
+		.name		= (_match),					\
 		.supply_name	= (_supply),					\
 		.of_match	= of_match_ptr(_match),				\
 		.regulators_node = of_match_ptr("regulators"),			\
 		.type		= REGULATOR_VOLTAGE,				\
 		.id		= _family##_##_id,				\
-		.n_voltages	= (((_max) - (_min)) / (_step) + 1),		\
 		.owner		= THIS_MODULE,					\
-		.min_uV		= (_min) * 1000,				\
-		.uV_step	= (_step) * 1000,				\
-		.vsel_reg	= (_vreg),					\
-		.vsel_mask	= (_vmask),					\
 		.enable_reg	= (_ereg),					\
 		.enable_mask	= (_emask),					\
 		.ops		= &axp20x_ops_sw,				\
@@ -100,7 +94,7 @@
 
 #define AXP_DESC_FIXED(_family, _id, _match, _supply, _volt)			\
 	[_family##_##_id] = {							\
-		.name		= #_id,						\
+		.name		= (_match),					\
 		.supply_name	= (_supply),					\
 		.of_match	= of_match_ptr(_match),				\
 		.regulators_node = of_match_ptr("regulators"),			\
@@ -112,39 +106,34 @@
 		.ops		= &axp20x_ops_fixed				\
 	}
 
-#define AXP_DESC_TABLE(_family, _id, _match, _supply, _table, _vreg, _vmask,	\
-		       _ereg, _emask)						\
+#define AXP_DESC_RANGES(_family, _id, _match, _supply, _ranges, _n_voltages,	\
+			_vreg, _vmask, _ereg, _emask)				\
 	[_family##_##_id] = {							\
-		.name		= #_id,						\
+		.name		= (_match),					\
 		.supply_name	= (_supply),					\
 		.of_match	= of_match_ptr(_match),				\
 		.regulators_node = of_match_ptr("regulators"),			\
 		.type		= REGULATOR_VOLTAGE,				\
 		.id		= _family##_##_id,				\
-		.n_voltages	= ARRAY_SIZE(_table),				\
+		.n_voltages	= (_n_voltages),				\
 		.owner		= THIS_MODULE,					\
 		.vsel_reg	= (_vreg),					\
 		.vsel_mask	= (_vmask),					\
 		.enable_reg	= (_ereg),					\
 		.enable_mask	= (_emask),					\
-		.volt_table	= (_table),					\
-		.ops		= &axp20x_ops_table,				\
+		.linear_ranges	= (_ranges),					\
+		.n_linear_ranges = ARRAY_SIZE(_ranges),				\
+		.ops		= &axp20x_ops_range,				\
 	}
 
-static const int axp20x_ldo4_data[] = { 1250000, 1300000, 1400000, 1500000, 1600000,
-					1700000, 1800000, 1900000, 2000000, 2500000,
-					2700000, 2800000, 3000000, 3100000, 3200000,
-					3300000 };
-
 static struct regulator_ops axp20x_ops_fixed = {
 	.list_voltage		= regulator_list_voltage_linear,
 };
 
-static struct regulator_ops axp20x_ops_table = {
+static struct regulator_ops axp20x_ops_range = {
 	.set_voltage_sel	= regulator_set_voltage_sel_regmap,
 	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
-	.list_voltage		= regulator_list_voltage_table,
-	.map_voltage		= regulator_map_voltage_ascend,
+	.list_voltage		= regulator_list_voltage_linear_range,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
 	.is_enabled		= regulator_is_enabled_regmap,
@@ -160,13 +149,17 @@ static struct regulator_ops axp20x_ops = {
 };
 
 static struct regulator_ops axp20x_ops_sw = {
-	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
-	.list_voltage		= regulator_list_voltage_linear,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
 	.is_enabled		= regulator_is_enabled_regmap,
 };
 
+static const struct regulator_linear_range axp20x_ldo4_ranges[] = {
+	REGULATOR_LINEAR_RANGE(1250000, 0x0, 0x0, 0),
+	REGULATOR_LINEAR_RANGE(1300000, 0x1, 0x8, 100000),
+	REGULATOR_LINEAR_RANGE(2500000, 0x9, 0xf, 100000),
+};
+
 static const struct regulator_desc axp20x_regulators[] = {
 	AXP_DESC(AXP20X, DCDC2, "dcdc2", "vin2", 700, 2275, 25,
 		 AXP20X_DCDC2_V_OUT, 0x3f, AXP20X_PWR_OUT_CTRL, 0x10),
@@ -177,8 +170,9 @@ static const struct regulator_desc axp20x_regulators[] = {
 		 AXP20X_LDO24_V_OUT, 0xf0, AXP20X_PWR_OUT_CTRL, 0x04),
 	AXP_DESC(AXP20X, LDO3, "ldo3", "ldo3in", 700, 3500, 25,
 		 AXP20X_LDO3_V_OUT, 0x7f, AXP20X_PWR_OUT_CTRL, 0x40),
-	AXP_DESC_TABLE(AXP20X, LDO4, "ldo4", "ldo24in", axp20x_ldo4_data,
-		       AXP20X_LDO24_V_OUT, 0x0f, AXP20X_PWR_OUT_CTRL, 0x08),
+	AXP_DESC_RANGES(AXP20X, LDO4, "ldo4", "ldo24in", axp20x_ldo4_ranges,
+			16, AXP20X_LDO24_V_OUT, 0x0f, AXP20X_PWR_OUT_CTRL,
+			0x08),
 	AXP_DESC_IO(AXP20X, LDO5, "ldo5", "ldo5in", 1800, 3300, 100,
 		    AXP20X_LDO5_V_OUT, 0xf0, AXP20X_GPIO0_CTRL, 0x07,
 		    AXP20X_IO_ENABLED, AXP20X_IO_DISABLED),
@@ -196,8 +190,8 @@ static const struct regulator_desc axp22x_regulators[] = {
 	AXP_DESC(AXP22X, DCDC5, "dcdc5", "vin5", 1000, 2550, 50,
 		 AXP22X_DCDC5_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL1, BIT(5)),
 	/* secondary switchable output of DCDC1 */
-	AXP_DESC_SW(AXP22X, DC1SW, "dc1sw", NULL, 1600, 3400, 100,
-		    AXP22X_DCDC1_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, BIT(7)),
+	AXP_DESC_SW(AXP22X, DC1SW, "dc1sw", NULL, AXP22X_PWR_OUT_CTRL2,
+		    BIT(7)),
 	/* LDO regulator internally chained to DCDC5 */
 	AXP_DESC(AXP22X, DC5LDO, "dc5ldo", NULL, 700, 1400, 100,
 		 AXP22X_DC5LDO_V_OUT, 0x7, AXP22X_PWR_OUT_CTRL1, BIT(0)),
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 744c9889f88d..e0b764284773 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1057,18 +1057,18 @@ static int set_machine_constraints(struct regulator_dev *rdev,
 
 	ret = machine_constraints_voltage(rdev, rdev->constraints);
 	if (ret != 0)
-		goto out;
+		return ret;
 
 	ret = machine_constraints_current(rdev, rdev->constraints);
 	if (ret != 0)
-		goto out;
+		return ret;
 
 	if (rdev->constraints->ilim_uA && ops->set_input_current_limit) {
 		ret = ops->set_input_current_limit(rdev,
 						   rdev->constraints->ilim_uA);
 		if (ret < 0) {
 			rdev_err(rdev, "failed to set input limit\n");
-			goto out;
+			return ret;
 		}
 	}
 
@@ -1077,21 +1077,20 @@ static int set_machine_constraints(struct regulator_dev *rdev,
 		ret = suspend_prepare(rdev, rdev->constraints->initial_state);
 		if (ret < 0) {
 			rdev_err(rdev, "failed to set suspend state\n");
-			goto out;
+			return ret;
 		}
 	}
 
 	if (rdev->constraints->initial_mode) {
 		if (!ops->set_mode) {
 			rdev_err(rdev, "no set_mode operation\n");
-			ret = -EINVAL;
-			goto out;
+			return -EINVAL;
 		}
 
 		ret = ops->set_mode(rdev, rdev->constraints->initial_mode);
 		if (ret < 0) {
 			rdev_err(rdev, "failed to set initial mode: %d\n", ret);
-			goto out;
+			return ret;
 		}
 	}
 
@@ -1102,7 +1101,7 @@ static int set_machine_constraints(struct regulator_dev *rdev,
 		ret = _regulator_do_enable(rdev);
 		if (ret < 0 && ret != -EINVAL) {
 			rdev_err(rdev, "failed to enable\n");
-			goto out;
+			return ret;
 		}
 	}
 
@@ -1111,7 +1110,7 @@ static int set_machine_constraints(struct regulator_dev *rdev,
 		ret = ops->set_ramp_delay(rdev, rdev->constraints->ramp_delay);
 		if (ret < 0) {
 			rdev_err(rdev, "failed to set ramp_delay\n");
-			goto out;
+			return ret;
 		}
 	}
 
@@ -1119,7 +1118,7 @@ static int set_machine_constraints(struct regulator_dev *rdev,
 		ret = ops->set_pull_down(rdev);
 		if (ret < 0) {
 			rdev_err(rdev, "failed to set pull down\n");
-			goto out;
+			return ret;
 		}
 	}
 
@@ -1127,7 +1126,7 @@ static int set_machine_constraints(struct regulator_dev *rdev,
 		ret = ops->set_soft_start(rdev);
 		if (ret < 0) {
 			rdev_err(rdev, "failed to set soft start\n");
-			goto out;
+			return ret;
 		}
 	}
 
@@ -1136,16 +1135,34 @@ static int set_machine_constraints(struct regulator_dev *rdev,
 		ret = ops->set_over_current_protection(rdev);
 		if (ret < 0) {
 			rdev_err(rdev, "failed to set over current protection\n");
-			goto out;
+			return ret;
+		}
+	}
+
+	if (rdev->constraints->active_discharge && ops->set_active_discharge) {
+		bool ad_state = (rdev->constraints->active_discharge ==
+			      REGULATOR_ACTIVE_DISCHARGE_ENABLE) ? true : false;
+
+		ret = ops->set_active_discharge(rdev, ad_state);
+		if (ret < 0) {
+			rdev_err(rdev, "failed to set active discharge\n");
+			return ret;
+		}
+	}
+
+	if (rdev->constraints->active_discharge && ops->set_active_discharge) {
+		bool ad_state = (rdev->constraints->active_discharge ==
+			      REGULATOR_ACTIVE_DISCHARGE_ENABLE) ? true : false;
+
+		ret = ops->set_active_discharge(rdev, ad_state);
+		if (ret < 0) {
+			rdev_err(rdev, "failed to set active discharge\n");
+			return ret;
 		}
 	}
 
 	print_constraints(rdev);
 	return 0;
-out:
-	kfree(rdev->constraints);
-	rdev->constraints = NULL;
-	return ret;
 }
 
 /**
@@ -3918,6 +3935,16 @@ regulator_register(const struct regulator_desc *regulator_desc,
 			goto clean;
 	}
 
+	if ((config->ena_gpio || config->ena_gpio_initialized) &&
+	    gpio_is_valid(config->ena_gpio)) {
+		ret = regulator_ena_gpio_request(rdev, config);
+		if (ret != 0) {
+			rdev_err(rdev, "Failed to request enable GPIO%d: %d\n",
+				 config->ena_gpio, ret);
+			goto clean;
+		}
+	}
+
 	/* register with sysfs */
 	rdev->dev.class = &regulator_class;
 	rdev->dev.parent = dev;
@@ -3926,21 +3953,11 @@ regulator_register(const struct regulator_desc *regulator_desc,
 	ret = device_register(&rdev->dev);
 	if (ret != 0) {
 		put_device(&rdev->dev);
-		goto clean;
+		goto wash;
 	}
 
 	dev_set_drvdata(&rdev->dev, rdev);
 
-	if ((config->ena_gpio || config->ena_gpio_initialized) &&
-	    gpio_is_valid(config->ena_gpio)) {
-		ret = regulator_ena_gpio_request(rdev, config);
-		if (ret != 0) {
-			rdev_err(rdev, "Failed to request enable GPIO%d: %d\n",
-				 config->ena_gpio, ret);
-			goto wash;
-		}
-	}
-
 	/* set regulator constraints */
 	if (init_data)
 		constraints = &init_data->constraints;
@@ -3979,13 +3996,13 @@ unset_supplies:
 
 scrub:
 	regulator_ena_gpio_free(rdev);
-	kfree(rdev->constraints);
-wash:
 	device_unregister(&rdev->dev);
 	/* device core frees rdev */
 	rdev = ERR_PTR(ret);
 	goto out;
 
+wash:
+	regulator_ena_gpio_free(rdev);
 clean:
 	kfree(rdev);
 	rdev = ERR_PTR(ret);
diff --git a/drivers/regulator/da9210-regulator.c b/drivers/regulator/da9210-regulator.c
index 8b3cc9f0cd64..01c0e3709b66 100644
--- a/drivers/regulator/da9210-regulator.c
+++ b/drivers/regulator/da9210-regulator.c
@@ -132,6 +132,8 @@ static irqreturn_t da9210_irq_handler(int irq, void *data)
 	if (error < 0)
 		goto error_i2c;
 
+	mutex_lock(&chip->rdev->mutex);
+
 	if (val & DA9210_E_OVCURR) {
 		regulator_notifier_call_chain(chip->rdev,
 					      REGULATOR_EVENT_OVER_CURRENT,
@@ -155,6 +157,9 @@ static irqreturn_t da9210_irq_handler(int irq, void *data)
 					      NULL);
 		handled |= DA9210_E_VMAX;
 	}
+
+	mutex_unlock(&chip->rdev->mutex);
+
 	if (handled) {
 		/* Clear handled events */
 		error = regmap_write(chip->regmap, DA9210_REG_EVENT_B, handled);
diff --git a/drivers/regulator/fan53555.c b/drivers/regulator/fan53555.c
index 4940e8287df6..2cb5cc311610 100644
--- a/drivers/regulator/fan53555.c
+++ b/drivers/regulator/fan53555.c
@@ -114,6 +114,22 @@ static int fan53555_set_suspend_voltage(struct regulator_dev *rdev, int uV)
 	return 0;
 }
 
+static int fan53555_set_suspend_enable(struct regulator_dev *rdev)
+{
+	struct fan53555_device_info *di = rdev_get_drvdata(rdev);
+
+	return regmap_update_bits(di->regmap, di->sleep_reg,
+				  VSEL_BUCK_EN, VSEL_BUCK_EN);
+}
+
+static int fan53555_set_suspend_disable(struct regulator_dev *rdev)
+{
+	struct fan53555_device_info *di = rdev_get_drvdata(rdev);
+
+	return regmap_update_bits(di->regmap, di->sleep_reg,
+				  VSEL_BUCK_EN, 0);
+}
+
 static int fan53555_set_mode(struct regulator_dev *rdev, unsigned int mode)
 {
 	struct fan53555_device_info *di = rdev_get_drvdata(rdev);
@@ -192,6 +208,8 @@ static struct regulator_ops fan53555_regulator_ops = {
 	.set_mode = fan53555_set_mode,
 	.get_mode = fan53555_get_mode,
 	.set_ramp_delay = fan53555_set_ramp,
+	.set_suspend_enable = fan53555_set_suspend_enable,
+	.set_suspend_disable = fan53555_set_suspend_disable,
 };
 
 static int fan53555_voltages_setup_fairchild(struct fan53555_device_info *di)
diff --git a/drivers/regulator/gpio-regulator.c b/drivers/regulator/gpio-regulator.c
index 7bba8b747f30..a8718e98674a 100644
--- a/drivers/regulator/gpio-regulator.c
+++ b/drivers/regulator/gpio-regulator.c
@@ -283,8 +283,10 @@ static int gpio_regulator_probe(struct platform_device *pdev)
 		drvdata->nr_gpios = config->nr_gpios;
 		ret = gpio_request_array(drvdata->gpios, drvdata->nr_gpios);
 		if (ret) {
-			dev_err(&pdev->dev,
-			"Could not obtain regulator setting GPIOs: %d\n", ret);
+			if (ret != -EPROBE_DEFER)
+				dev_err(&pdev->dev,
+					"Could not obtain regulator setting GPIOs: %d\n",
+					ret);
 			goto err_memstate;
 		}
 	}
diff --git a/drivers/regulator/helpers.c b/drivers/regulator/helpers.c
index 3bbb32680a94..b1e32e7482e9 100644
--- a/drivers/regulator/helpers.c
+++ b/drivers/regulator/helpers.c
@@ -465,3 +465,26 @@ int regulator_get_bypass_regmap(struct regulator_dev *rdev, bool *enable)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(regulator_get_bypass_regmap);
+
+/**
+ * regulator_set_active_discharge_regmap - Default set_active_discharge()
+ *					   using regmap
+ *
+ * @rdev: device to operate on.
+ * @enable: state to set, 0 to disable and 1 to enable.
+ */
+int regulator_set_active_discharge_regmap(struct regulator_dev *rdev,
+					  bool enable)
+{
+	unsigned int val;
+
+	if (enable)
+		val = rdev->desc->active_discharge_on;
+	else
+		val = rdev->desc->active_discharge_off;
+
+	return regmap_update_bits(rdev->regmap,
+				  rdev->desc->active_discharge_reg,
+				  rdev->desc->active_discharge_mask, val);
+}
+EXPORT_SYMBOL_GPL(regulator_set_active_discharge_regmap);
diff --git a/drivers/regulator/hi655x-regulator.c b/drivers/regulator/hi655x-regulator.c
new file mode 100644
index 000000000000..aca18466f522
--- /dev/null
+++ b/drivers/regulator/hi655x-regulator.c
@@ -0,0 +1,227 @@
+/*
+ * Device driver for regulators in Hi655x IC
+ *
+ * Copyright (c) 2016 Hisilicon.
+ *
+ * Authors:
+ * Chen Feng <puck.chen@hisilicon.com>
+ * Fei  Wang <w.f@huawei.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/of_regulator.h>
+#include <linux/mfd/hi655x-pmic.h>
+
+struct hi655x_regulator {
+	unsigned int disable_reg;
+	unsigned int status_reg;
+	unsigned int ctrl_regs;
+	unsigned int ctrl_mask;
+	struct regulator_desc rdesc;
+};
+
+/* LDO7 & LDO10 */
+static const unsigned int ldo7_voltages[] = {
+	1800000, 1850000, 2850000, 2900000,
+	3000000, 3100000, 3200000, 3300000,
+};
+
+static const unsigned int ldo19_voltages[] = {
+	1800000, 1850000, 1900000, 1750000,
+	2800000, 2850000, 2900000, 3000000,
+};
+
+static const unsigned int ldo22_voltages[] = {
+	 900000, 1000000, 1050000, 1100000,
+	1150000, 1175000, 1185000, 1200000,
+};
+
+enum hi655x_regulator_id {
+	HI655X_LDO0,
+	HI655X_LDO1,
+	HI655X_LDO2,
+	HI655X_LDO3,
+	HI655X_LDO4,
+	HI655X_LDO5,
+	HI655X_LDO6,
+	HI655X_LDO7,
+	HI655X_LDO8,
+	HI655X_LDO9,
+	HI655X_LDO10,
+	HI655X_LDO11,
+	HI655X_LDO12,
+	HI655X_LDO13,
+	HI655X_LDO14,
+	HI655X_LDO15,
+	HI655X_LDO16,
+	HI655X_LDO17,
+	HI655X_LDO18,
+	HI655X_LDO19,
+	HI655X_LDO20,
+	HI655X_LDO21,
+	HI655X_LDO22,
+};
+
+static int hi655x_is_enabled(struct regulator_dev *rdev)
+{
+	unsigned int value = 0;
+
+	struct hi655x_regulator *regulator = rdev_get_drvdata(rdev);
+
+	regmap_read(rdev->regmap, regulator->status_reg, &value);
+	return (value & BIT(regulator->ctrl_mask));
+}
+
+static int hi655x_disable(struct regulator_dev *rdev)
+{
+	int ret = 0;
+
+	struct hi655x_regulator *regulator = rdev_get_drvdata(rdev);
+
+	ret = regmap_write(rdev->regmap, regulator->disable_reg,
+			   BIT(regulator->ctrl_mask));
+	return ret;
+}
+
+static struct regulator_ops hi655x_regulator_ops = {
+	.enable = regulator_enable_regmap,
+	.disable = hi655x_disable,
+	.is_enabled = hi655x_is_enabled,
+	.list_voltage = regulator_list_voltage_table,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+};
+
+static struct regulator_ops hi655x_ldo_linear_ops = {
+	.enable = regulator_enable_regmap,
+	.disable = hi655x_disable,
+	.is_enabled = hi655x_is_enabled,
+	.list_voltage = regulator_list_voltage_linear,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+};
+
+#define HI655X_LDO(_ID, vreg, vmask, ereg, dreg,                 \
+		   sreg, cmask, vtable) {                        \
+	.rdesc = {                                               \
+		.name            = #_ID,                         \
+		.of_match        = of_match_ptr(#_ID),           \
+		.ops             = &hi655x_regulator_ops,        \
+		.regulators_node = of_match_ptr("regulators"),   \
+		.type            = REGULATOR_VOLTAGE,            \
+		.id              = HI655X_##_ID,                 \
+		.owner           = THIS_MODULE,                  \
+		.n_voltages      = ARRAY_SIZE(vtable),           \
+		.volt_table      = vtable,                       \
+		.vsel_reg        = HI655X_BUS_ADDR(vreg),        \
+		.vsel_mask       = vmask,                        \
+		.enable_reg      = HI655X_BUS_ADDR(ereg),        \
+		.enable_mask     = BIT(cmask),                   \
+	},                                                       \
+	.disable_reg = HI655X_BUS_ADDR(dreg),                    \
+	.status_reg = HI655X_BUS_ADDR(sreg),                     \
+	.ctrl_mask = cmask,                                      \
+}
+
+#define HI655X_LDO_LINEAR(_ID, vreg, vmask, ereg, dreg,          \
+			  sreg, cmask, minv, nvolt, vstep) {     \
+	.rdesc = {                                               \
+		.name            = #_ID,                         \
+		.of_match        = of_match_ptr(#_ID),           \
+		.ops             = &hi655x_ldo_linear_ops,       \
+		.regulators_node = of_match_ptr("regulators"),   \
+		.type            = REGULATOR_VOLTAGE,            \
+		.id              = HI655X_##_ID,                 \
+		.owner           = THIS_MODULE,                  \
+		.min_uV          = minv,                         \
+		.n_voltages      = nvolt,                        \
+		.uV_step         = vstep,                        \
+		.vsel_reg        = HI655X_BUS_ADDR(vreg),        \
+		.vsel_mask       = vmask,                        \
+		.enable_reg      = HI655X_BUS_ADDR(ereg),        \
+		.enable_mask     = BIT(cmask),                   \
+	},                                                       \
+	.disable_reg = HI655X_BUS_ADDR(dreg),                    \
+	.status_reg = HI655X_BUS_ADDR(sreg),                     \
+	.ctrl_mask = cmask,                                      \
+}
+
+static struct hi655x_regulator regulators[] = {
+	HI655X_LDO_LINEAR(LDO2, 0x72, 0x07, 0x29, 0x2a, 0x2b, 0x01,
+			  2500000, 8, 100000),
+	HI655X_LDO(LDO7, 0x78, 0x07, 0x29, 0x2a, 0x2b, 0x06, ldo7_voltages),
+	HI655X_LDO(LDO10, 0x78, 0x07, 0x29, 0x2a, 0x2b, 0x01, ldo7_voltages),
+	HI655X_LDO_LINEAR(LDO13, 0x7e, 0x07, 0x2c, 0x2d, 0x2e, 0x04,
+			  1600000, 8, 50000),
+	HI655X_LDO_LINEAR(LDO14, 0x7f, 0x07, 0x2c, 0x2d, 0x2e, 0x05,
+			  2500000, 8, 100000),
+	HI655X_LDO_LINEAR(LDO15, 0x80, 0x07, 0x2c, 0x2d, 0x2e, 0x06,
+			  1600000, 8, 50000),
+	HI655X_LDO_LINEAR(LDO17, 0x82, 0x07, 0x2f, 0x30, 0x31, 0x00,
+			  2500000, 8, 100000),
+	HI655X_LDO(LDO19, 0x84, 0x07, 0x2f, 0x30, 0x31, 0x02, ldo19_voltages),
+	HI655X_LDO_LINEAR(LDO21, 0x86, 0x07, 0x2f, 0x30, 0x31, 0x04,
+			  1650000, 8, 50000),
+	HI655X_LDO(LDO22, 0x87, 0x07, 0x2f, 0x30, 0x31, 0x05, ldo22_voltages),
+};
+
+static int hi655x_regulator_probe(struct platform_device *pdev)
+{
+	unsigned int i;
+	struct hi655x_regulator *regulator;
+	struct hi655x_pmic *pmic;
+	struct regulator_config config = { };
+	struct regulator_dev *rdev;
+
+	pmic = dev_get_drvdata(pdev->dev.parent);
+	if (!pmic) {
+		dev_err(&pdev->dev, "no pmic in the regulator parent node\n");
+		return -ENODEV;
+	}
+
+	regulator = devm_kzalloc(&pdev->dev, sizeof(*regulator), GFP_KERNEL);
+	if (!regulator)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, regulator);
+
+	config.dev = pdev->dev.parent;
+	config.regmap = pmic->regmap;
+	config.driver_data = regulator;
+	for (i = 0; i < ARRAY_SIZE(regulators); i++) {
+		rdev = devm_regulator_register(&pdev->dev,
+					       &regulators[i].rdesc,
+					       &config);
+		if (IS_ERR(rdev)) {
+			dev_err(&pdev->dev, "failed to register regulator %s\n",
+				regulator->rdesc.name);
+			return PTR_ERR(rdev);
+		}
+	}
+	return 0;
+}
+
+static struct platform_driver hi655x_regulator_driver = {
+	.driver = {
+		.name	= "hi655x-regulator",
+	},
+	.probe	= hi655x_regulator_probe,
+};
+module_platform_driver(hi655x_regulator_driver);
+
+MODULE_AUTHOR("Chen Feng <puck.chen@hisilicon.com>");
+MODULE_DESCRIPTION("Hisilicon Hi655x regulator driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/regulator/lp872x.c b/drivers/regulator/lp872x.c
index 19d758486553..38992112fd6e 100644
--- a/drivers/regulator/lp872x.c
+++ b/drivers/regulator/lp872x.c
@@ -15,6 +15,7 @@
 #include <linux/regmap.h>
 #include <linux/err.h>
 #include <linux/gpio.h>
+#include <linux/delay.h>
 #include <linux/regulator/lp872x.h>
 #include <linux/regulator/driver.h>
 #include <linux/platform_device.h>
@@ -738,10 +739,8 @@ static int lp872x_init_dvs(struct lp872x *lp)
 		goto set_default_dvs_mode;
 
 	gpio = dvs->gpio;
-	if (!gpio_is_valid(gpio)) {
-		dev_warn(lp->dev, "invalid gpio: %d\n", gpio);
+	if (!gpio_is_valid(gpio))
 		goto set_default_dvs_mode;
-	}
 
 	pinstate = dvs->init_state;
 	ret = devm_gpio_request_one(lp->dev, gpio, pinstate, "LP872X DVS");
@@ -759,6 +758,33 @@ set_default_dvs_mode:
 				default_dvs_mode[lp->chipid]);
 }
 
+static int lp872x_hw_enable(struct lp872x *lp)
+{
+	int ret, gpio;
+
+	if (!lp->pdata)
+		return -EINVAL;
+
+	gpio = lp->pdata->enable_gpio;
+	if (!gpio_is_valid(gpio))
+		return 0;
+
+	/* Always set enable GPIO high. */
+	ret = devm_gpio_request_one(lp->dev, gpio, GPIOF_OUT_INIT_HIGH, "LP872X EN");
+	if (ret) {
+		dev_err(lp->dev, "gpio request err: %d\n", ret);
+		return ret;
+	}
+
+	/* Each chip has a different enable delay. */
+	if (lp->chipid == LP8720)
+		usleep_range(LP8720_ENABLE_DELAY, 1.5 * LP8720_ENABLE_DELAY);
+	else
+		usleep_range(LP8725_ENABLE_DELAY, 1.5 * LP8725_ENABLE_DELAY);
+
+	return 0;
+}
+
 static int lp872x_config(struct lp872x *lp)
 {
 	struct lp872x_platform_data *pdata = lp->pdata;
@@ -877,6 +903,8 @@ static struct lp872x_platform_data
 	of_property_read_u8(np, "ti,dvs-state", &dvs_state);
 	pdata->dvs->init_state = dvs_state ? DVS_HIGH : DVS_LOW;
 
+	pdata->enable_gpio = of_get_named_gpio(np, "enable-gpios", 0);
+
 	if (of_get_child_count(np) == 0)
 		goto out;
 
@@ -950,6 +978,10 @@ static int lp872x_probe(struct i2c_client *cl, const struct i2c_device_id *id)
 	lp->chipid = id->driver_data;
 	i2c_set_clientdata(cl, lp);
 
+	ret = lp872x_hw_enable(lp);
+	if (ret)
+		return ret;
+
 	ret = lp872x_config(lp);
 	if (ret)
 		return ret;
diff --git a/drivers/regulator/ltc3589.c b/drivers/regulator/ltc3589.c
index 972c386b2690..47bef328fb58 100644
--- a/drivers/regulator/ltc3589.c
+++ b/drivers/regulator/ltc3589.c
@@ -520,12 +520,15 @@ static int ltc3589_probe(struct i2c_client *client,
 		}
 	}
 
-	ret = devm_request_threaded_irq(dev, client->irq, NULL, ltc3589_isr,
-					IRQF_TRIGGER_LOW | IRQF_ONESHOT,
-					client->name, ltc3589);
-	if (ret) {
-		dev_err(dev, "Failed to request IRQ: %d\n", ret);
-		return ret;
+	if (client->irq) {
+		ret = devm_request_threaded_irq(dev, client->irq, NULL,
+						ltc3589_isr,
+						IRQF_TRIGGER_LOW | IRQF_ONESHOT,
+						client->name, ltc3589);
+		if (ret) {
+			dev_err(dev, "Failed to request IRQ: %d\n", ret);
+			return ret;
+		}
 	}
 
 	return 0;
diff --git a/drivers/regulator/max77620-regulator.c b/drivers/regulator/max77620-regulator.c
new file mode 100644
index 000000000000..73a3356a5c19
--- /dev/null
+++ b/drivers/regulator/max77620-regulator.c
@@ -0,0 +1,813 @@
+/*
+ * Maxim MAX77620 Regulator driver
+ *
+ * Copyright (c) 2016, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * Author: Mallikarjun Kasoju <mkasoju@nvidia.com>
+ *	Laxman Dewangan <ldewangan@nvidia.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/mfd/max77620.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/of_regulator.h>
+
+#define max77620_rails(_name)	"max77620-"#_name
+
+/* Power Mode */
+#define MAX77620_POWER_MODE_NORMAL		3
+#define MAX77620_POWER_MODE_LPM			2
+#define MAX77620_POWER_MODE_GLPM		1
+#define MAX77620_POWER_MODE_DISABLE		0
+
+/* SD Slew Rate */
+#define MAX77620_SD_SR_13_75			0
+#define MAX77620_SD_SR_27_5			1
+#define MAX77620_SD_SR_55			2
+#define MAX77620_SD_SR_100			3
+
+enum max77620_regulators {
+	MAX77620_REGULATOR_ID_SD0,
+	MAX77620_REGULATOR_ID_SD1,
+	MAX77620_REGULATOR_ID_SD2,
+	MAX77620_REGULATOR_ID_SD3,
+	MAX77620_REGULATOR_ID_SD4,
+	MAX77620_REGULATOR_ID_LDO0,
+	MAX77620_REGULATOR_ID_LDO1,
+	MAX77620_REGULATOR_ID_LDO2,
+	MAX77620_REGULATOR_ID_LDO3,
+	MAX77620_REGULATOR_ID_LDO4,
+	MAX77620_REGULATOR_ID_LDO5,
+	MAX77620_REGULATOR_ID_LDO6,
+	MAX77620_REGULATOR_ID_LDO7,
+	MAX77620_REGULATOR_ID_LDO8,
+	MAX77620_NUM_REGS,
+};
+
+/* Regulator types */
+enum max77620_regulator_type {
+	MAX77620_REGULATOR_TYPE_SD,
+	MAX77620_REGULATOR_TYPE_LDO_N,
+	MAX77620_REGULATOR_TYPE_LDO_P,
+};
+
+struct max77620_regulator_info {
+	u8 type;
+	u8 fps_addr;
+	u8 volt_addr;
+	u8 cfg_addr;
+	u8 power_mode_mask;
+	u8 power_mode_shift;
+	u8 remote_sense_addr;
+	u8 remote_sense_mask;
+	struct regulator_desc desc;
+};
+
+struct max77620_regulator_pdata {
+	struct regulator_init_data *reg_idata;
+	int active_fps_src;
+	int active_fps_pd_slot;
+	int active_fps_pu_slot;
+	int suspend_fps_src;
+	int suspend_fps_pd_slot;
+	int suspend_fps_pu_slot;
+	int current_mode;
+};
+
+struct max77620_regulator {
+	struct device *dev;
+	struct regmap *rmap;
+	struct max77620_regulator_info *rinfo[MAX77620_NUM_REGS];
+	struct max77620_regulator_pdata reg_pdata[MAX77620_NUM_REGS];
+	int enable_power_mode[MAX77620_NUM_REGS];
+	int current_power_mode[MAX77620_NUM_REGS];
+	int active_fps_src[MAX77620_NUM_REGS];
+};
+
+#define fps_src_name(fps_src)	\
+	(fps_src == MAX77620_FPS_SRC_0 ? "FPS_SRC_0" :	\
+	fps_src == MAX77620_FPS_SRC_1 ? "FPS_SRC_1" :	\
+	fps_src == MAX77620_FPS_SRC_2 ? "FPS_SRC_2" : "FPS_SRC_NONE")
+
+static int max77620_regulator_get_fps_src(struct max77620_regulator *pmic,
+					  int id)
+{
+	struct max77620_regulator_info *rinfo = pmic->rinfo[id];
+	unsigned int val;
+	int ret;
+
+	ret = regmap_read(pmic->rmap, rinfo->fps_addr, &val);
+	if (ret < 0) {
+		dev_err(pmic->dev, "Reg 0x%02x read failed %d\n",
+			rinfo->fps_addr, ret);
+		return ret;
+	}
+
+	return (val & MAX77620_FPS_SRC_MASK) >> MAX77620_FPS_SRC_SHIFT;
+}
+
+static int max77620_regulator_set_fps_src(struct max77620_regulator *pmic,
+					  int fps_src, int id)
+{
+	struct max77620_regulator_info *rinfo = pmic->rinfo[id];
+	unsigned int val;
+	int ret;
+
+	switch (fps_src) {
+	case MAX77620_FPS_SRC_0:
+	case MAX77620_FPS_SRC_1:
+	case MAX77620_FPS_SRC_2:
+	case MAX77620_FPS_SRC_NONE:
+		break;
+
+	case MAX77620_FPS_SRC_DEF:
+		ret = regmap_read(pmic->rmap, rinfo->fps_addr, &val);
+		if (ret < 0) {
+			dev_err(pmic->dev, "Reg 0x%02x read failed %d\n",
+				rinfo->fps_addr, ret);
+			return ret;
+		}
+		ret = (val & MAX77620_FPS_SRC_MASK) >> MAX77620_FPS_SRC_SHIFT;
+		pmic->active_fps_src[id] = ret;
+		return 0;
+
+	default:
+		dev_err(pmic->dev, "Invalid FPS %d for regulator %d\n",
+			fps_src, id);
+		return -EINVAL;
+	}
+
+	ret = regmap_update_bits(pmic->rmap, rinfo->fps_addr,
+				 MAX77620_FPS_SRC_MASK,
+				 fps_src << MAX77620_FPS_SRC_SHIFT);
+	if (ret < 0) {
+		dev_err(pmic->dev, "Reg 0x%02x update failed %d\n",
+			rinfo->fps_addr, ret);
+		return ret;
+	}
+	pmic->active_fps_src[id] = fps_src;
+
+	return 0;
+}
+
+static int max77620_regulator_set_fps_slots(struct max77620_regulator *pmic,
+					    int id, bool is_suspend)
+{
+	struct max77620_regulator_pdata *rpdata = &pmic->reg_pdata[id];
+	struct max77620_regulator_info *rinfo = pmic->rinfo[id];
+	unsigned int val = 0;
+	unsigned int mask = 0;
+	int pu = rpdata->active_fps_pu_slot;
+	int pd = rpdata->active_fps_pd_slot;
+	int ret = 0;
+
+	if (is_suspend) {
+		pu = rpdata->suspend_fps_pu_slot;
+		pd = rpdata->suspend_fps_pd_slot;
+	}
+
+	/* FPS power up period setting */
+	if (pu >= 0) {
+		val |= (pu << MAX77620_FPS_PU_PERIOD_SHIFT);
+		mask |= MAX77620_FPS_PU_PERIOD_MASK;
+	}
+
+	/* FPS power down period setting */
+	if (pd >= 0) {
+		val |= (pd << MAX77620_FPS_PD_PERIOD_SHIFT);
+		mask |= MAX77620_FPS_PD_PERIOD_MASK;
+	}
+
+	if (mask) {
+		ret = regmap_update_bits(pmic->rmap, rinfo->fps_addr,
+					 mask, val);
+		if (ret < 0) {
+			dev_err(pmic->dev, "Reg 0x%02x update failed: %d\n",
+				rinfo->fps_addr, ret);
+			return ret;
+		}
+	}
+
+	return ret;
+}
+
+static int max77620_regulator_set_power_mode(struct max77620_regulator *pmic,
+					     int power_mode, int id)
+{
+	struct max77620_regulator_info *rinfo = pmic->rinfo[id];
+	u8 mask = rinfo->power_mode_mask;
+	u8 shift = rinfo->power_mode_shift;
+	u8 addr;
+	int ret;
+
+	switch (rinfo->type) {
+	case MAX77620_REGULATOR_TYPE_SD:
+		addr = rinfo->cfg_addr;
+		break;
+	default:
+		addr = rinfo->volt_addr;
+		break;
+	}
+
+	ret = regmap_update_bits(pmic->rmap, addr, mask, power_mode << shift);
+	if (ret < 0) {
+		dev_err(pmic->dev, "Regulator %d mode set failed: %d\n",
+			id, ret);
+		return ret;
+	}
+	pmic->current_power_mode[id] = power_mode;
+
+	return ret;
+}
+
+static int max77620_regulator_get_power_mode(struct max77620_regulator *pmic,
+					     int id)
+{
+	struct max77620_regulator_info *rinfo = pmic->rinfo[id];
+	unsigned int val, addr;
+	u8 mask = rinfo->power_mode_mask;
+	u8 shift = rinfo->power_mode_shift;
+	int ret;
+
+	switch (rinfo->type) {
+	case MAX77620_REGULATOR_TYPE_SD:
+		addr = rinfo->cfg_addr;
+		break;
+	default:
+		addr = rinfo->volt_addr;
+		break;
+	}
+
+	ret = regmap_read(pmic->rmap, addr, &val);
+	if (ret < 0) {
+		dev_err(pmic->dev, "Regulator %d: Reg 0x%02x read failed: %d\n",
+			id, addr, ret);
+		return ret;
+	}
+
+	return (val & mask) >> shift;
+}
+
+static int max77620_read_slew_rate(struct max77620_regulator *pmic, int id)
+{
+	struct max77620_regulator_info *rinfo = pmic->rinfo[id];
+	unsigned int rval;
+	int slew_rate;
+	int ret;
+
+	ret = regmap_read(pmic->rmap, rinfo->cfg_addr, &rval);
+	if (ret < 0) {
+		dev_err(pmic->dev, "Register 0x%02x read failed: %d\n",
+			rinfo->cfg_addr, ret);
+		return ret;
+	}
+
+	switch (rinfo->type) {
+	case MAX77620_REGULATOR_TYPE_SD:
+		slew_rate = (rval >> MAX77620_SD_SR_SHIFT) & 0x3;
+		switch (slew_rate) {
+		case 0:
+			slew_rate = 13750;
+			break;
+		case 1:
+			slew_rate = 27500;
+			break;
+		case 2:
+			slew_rate = 55000;
+			break;
+		case 3:
+			slew_rate = 100000;
+			break;
+		}
+		rinfo->desc.ramp_delay = slew_rate;
+		break;
+	default:
+		slew_rate = rval & 0x1;
+		switch (slew_rate) {
+		case 0:
+			slew_rate = 100000;
+			break;
+		case 1:
+			slew_rate = 5000;
+			break;
+		}
+		rinfo->desc.ramp_delay = slew_rate;
+		break;
+	}
+
+	return 0;
+}
+
+static int max77620_init_pmic(struct max77620_regulator *pmic, int id)
+{
+	struct max77620_regulator_pdata *rpdata = &pmic->reg_pdata[id];
+	int ret;
+
+	/* Update power mode */
+	ret = max77620_regulator_get_power_mode(pmic, id);
+	if (ret < 0)
+		return ret;
+
+	pmic->current_power_mode[id] = ret;
+	pmic->enable_power_mode[id] = MAX77620_POWER_MODE_NORMAL;
+
+	if (rpdata->active_fps_src == MAX77620_FPS_SRC_DEF) {
+		ret = max77620_regulator_get_fps_src(pmic, id);
+		if (ret < 0)
+			return ret;
+		rpdata->active_fps_src = ret;
+	}
+
+	 /* If rails are externally control of FPS then enable it always. */
+	if (rpdata->active_fps_src == MAX77620_FPS_SRC_NONE) {
+		ret = max77620_regulator_set_power_mode(pmic,
+					pmic->enable_power_mode[id], id);
+		if (ret < 0)
+			return ret;
+	} else {
+		if (pmic->current_power_mode[id] !=
+		     pmic->enable_power_mode[id]) {
+			ret = max77620_regulator_set_power_mode(pmic,
+					pmic->enable_power_mode[id], id);
+			if (ret < 0)
+				return ret;
+		}
+	}
+
+	ret = max77620_regulator_set_fps_src(pmic, rpdata->active_fps_src, id);
+	if (ret < 0)
+		return ret;
+
+	ret = max77620_regulator_set_fps_slots(pmic, id, false);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int max77620_regulator_enable(struct regulator_dev *rdev)
+{
+	struct max77620_regulator *pmic = rdev_get_drvdata(rdev);
+	int id = rdev_get_id(rdev);
+
+	if (pmic->active_fps_src[id] != MAX77620_FPS_SRC_NONE)
+		return 0;
+
+	return max77620_regulator_set_power_mode(pmic,
+			pmic->enable_power_mode[id], id);
+}
+
+static int max77620_regulator_disable(struct regulator_dev *rdev)
+{
+	struct max77620_regulator *pmic = rdev_get_drvdata(rdev);
+	int id = rdev_get_id(rdev);
+
+	if (pmic->active_fps_src[id] != MAX77620_FPS_SRC_NONE)
+		return 0;
+
+	return max77620_regulator_set_power_mode(pmic,
+			MAX77620_POWER_MODE_DISABLE, id);
+}
+
+static int max77620_regulator_is_enabled(struct regulator_dev *rdev)
+{
+	struct max77620_regulator *pmic = rdev_get_drvdata(rdev);
+	int id = rdev_get_id(rdev);
+	int ret = 1;
+
+	if (pmic->active_fps_src[id] != MAX77620_FPS_SRC_NONE)
+		return 1;
+
+	ret = max77620_regulator_get_power_mode(pmic, id);
+	if (ret < 0)
+		return ret;
+
+	if (ret != MAX77620_POWER_MODE_DISABLE)
+		return 1;
+
+	return 0;
+}
+
+static int max77620_regulator_set_mode(struct regulator_dev *rdev,
+				       unsigned int mode)
+{
+	struct max77620_regulator *pmic = rdev_get_drvdata(rdev);
+	int id = rdev_get_id(rdev);
+	struct max77620_regulator_info *rinfo = pmic->rinfo[id];
+	struct max77620_regulator_pdata *rpdata = &pmic->reg_pdata[id];
+	bool fpwm = false;
+	int power_mode;
+	int ret;
+	u8 val;
+
+	switch (mode) {
+	case REGULATOR_MODE_FAST:
+		fpwm = true;
+		power_mode = MAX77620_POWER_MODE_NORMAL;
+		break;
+
+	case REGULATOR_MODE_NORMAL:
+		power_mode = MAX77620_POWER_MODE_NORMAL;
+		break;
+
+	case REGULATOR_MODE_IDLE:
+		power_mode = MAX77620_POWER_MODE_LPM;
+		break;
+
+	default:
+		dev_err(pmic->dev, "Regulator %d mode %d is invalid\n",
+			id, mode);
+		return -EINVAL;
+	}
+
+	if (rinfo->type != MAX77620_REGULATOR_TYPE_SD)
+		goto skip_fpwm;
+
+	val = (fpwm) ? MAX77620_SD_FPWM_MASK : 0;
+	ret = regmap_update_bits(pmic->rmap, rinfo->cfg_addr,
+				 MAX77620_SD_FPWM_MASK, val);
+	if (ret < 0) {
+		dev_err(pmic->dev, "Reg 0x%02x update failed: %d\n",
+			rinfo->cfg_addr, ret);
+		return ret;
+	}
+	rpdata->current_mode = mode;
+
+skip_fpwm:
+	ret = max77620_regulator_set_power_mode(pmic, power_mode, id);
+	if (ret < 0)
+		return ret;
+
+	pmic->enable_power_mode[id] = power_mode;
+
+	return 0;
+}
+
+static unsigned int max77620_regulator_get_mode(struct regulator_dev *rdev)
+{
+	struct max77620_regulator *pmic = rdev_get_drvdata(rdev);
+	int id = rdev_get_id(rdev);
+	struct max77620_regulator_info *rinfo = pmic->rinfo[id];
+	int fpwm = 0;
+	int ret;
+	int pm_mode, reg_mode;
+	unsigned int val;
+
+	ret = max77620_regulator_get_power_mode(pmic, id);
+	if (ret < 0)
+		return 0;
+
+	pm_mode = ret;
+
+	if (rinfo->type == MAX77620_REGULATOR_TYPE_SD) {
+		ret = regmap_read(pmic->rmap, rinfo->cfg_addr, &val);
+		if (ret < 0) {
+			dev_err(pmic->dev, "Reg 0x%02x read failed: %d\n",
+				rinfo->cfg_addr, ret);
+			return ret;
+		}
+		fpwm = !!(val & MAX77620_SD_FPWM_MASK);
+	}
+
+	switch (pm_mode) {
+	case MAX77620_POWER_MODE_NORMAL:
+	case MAX77620_POWER_MODE_DISABLE:
+		if (fpwm)
+			reg_mode = REGULATOR_MODE_FAST;
+		else
+			reg_mode = REGULATOR_MODE_NORMAL;
+		break;
+	case MAX77620_POWER_MODE_LPM:
+	case MAX77620_POWER_MODE_GLPM:
+		reg_mode = REGULATOR_MODE_IDLE;
+		break;
+	default:
+		return 0;
+	}
+
+	return reg_mode;
+}
+
+static int max77620_regulator_set_ramp_delay(struct regulator_dev *rdev,
+					     int ramp_delay)
+{
+	struct max77620_regulator *pmic = rdev_get_drvdata(rdev);
+	int id = rdev_get_id(rdev);
+	struct max77620_regulator_info *rinfo = pmic->rinfo[id];
+	int ret, val;
+	u8 mask;
+
+	if (rinfo->type == MAX77620_REGULATOR_TYPE_SD) {
+		if (ramp_delay <= 13750)
+			val = 0;
+		else if (ramp_delay <= 27500)
+			val = 1;
+		else if (ramp_delay <= 55000)
+			val = 2;
+		else
+			val = 3;
+		val <<= MAX77620_SD_SR_SHIFT;
+		mask = MAX77620_SD_SR_MASK;
+	} else {
+		if (ramp_delay <= 5000)
+			val = 1;
+		else
+			val = 0;
+		mask = MAX77620_LDO_SLEW_RATE_MASK;
+	}
+
+	ret = regmap_update_bits(pmic->rmap, rinfo->cfg_addr, mask, val);
+	if (ret < 0)
+		dev_err(pmic->dev, "Reg 0x%02x update failed: %d\n",
+			rinfo->cfg_addr, ret);
+
+	return ret;
+}
+
+static int max77620_of_parse_cb(struct device_node *np,
+				const struct regulator_desc *desc,
+				struct regulator_config *config)
+{
+	struct max77620_regulator *pmic = config->driver_data;
+	struct max77620_regulator_pdata *rpdata = &pmic->reg_pdata[desc->id];
+	u32 pval;
+	int ret;
+
+	ret = of_property_read_u32(np, "maxim,active-fps-source", &pval);
+	rpdata->active_fps_src = (!ret) ? pval : MAX77620_FPS_SRC_DEF;
+
+	ret = of_property_read_u32(np, "maxim,active-fps-power-up-slot", &pval);
+	rpdata->active_fps_pu_slot = (!ret) ? pval : -1;
+
+	ret = of_property_read_u32(
+			np, "maxim,active-fps-power-down-slot", &pval);
+	rpdata->active_fps_pd_slot = (!ret) ? pval : -1;
+
+	ret = of_property_read_u32(np, "maxim,suspend-fps-source", &pval);
+	rpdata->suspend_fps_src = (!ret) ? pval : -1;
+
+	ret = of_property_read_u32(
+			np, "maxim,suspend-fps-power-up-slot", &pval);
+	rpdata->suspend_fps_pu_slot = (!ret) ? pval : -1;
+
+	ret = of_property_read_u32(
+			np, "maxim,suspend-fps-power-down-slot", &pval);
+	rpdata->suspend_fps_pd_slot = (!ret) ? pval : -1;
+
+	return max77620_init_pmic(pmic, desc->id);
+}
+
+static struct regulator_ops max77620_regulator_ops = {
+	.is_enabled = max77620_regulator_is_enabled,
+	.enable = max77620_regulator_enable,
+	.disable = max77620_regulator_disable,
+	.list_voltage = regulator_list_voltage_linear,
+	.map_voltage = regulator_map_voltage_linear,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+	.set_mode = max77620_regulator_set_mode,
+	.get_mode = max77620_regulator_get_mode,
+	.set_ramp_delay = max77620_regulator_set_ramp_delay,
+	.set_voltage_time_sel = regulator_set_voltage_time_sel,
+	.set_active_discharge = regulator_set_active_discharge_regmap,
+};
+
+#define MAX77620_SD_CNF2_ROVS_EN_NONE	0
+#define RAIL_SD(_id, _name, _sname, _volt_mask, _min_uV, _max_uV,	\
+		_step_uV, _rs_add, _rs_mask)				\
+	[MAX77620_REGULATOR_ID_##_id] = {				\
+		.type = MAX77620_REGULATOR_TYPE_SD,			\
+		.volt_addr = MAX77620_REG_##_id,			\
+		.cfg_addr = MAX77620_REG_##_id##_CFG,			\
+		.fps_addr = MAX77620_REG_FPS_##_id,			\
+		.remote_sense_addr = _rs_add,				\
+		.remote_sense_mask = MAX77620_SD_CNF2_ROVS_EN_##_rs_mask, \
+		.power_mode_mask = MAX77620_SD_POWER_MODE_MASK,		\
+		.power_mode_shift = MAX77620_SD_POWER_MODE_SHIFT,	\
+		.desc = {						\
+			.name = max77620_rails(_name),			\
+			.of_match = of_match_ptr(#_name),		\
+			.regulators_node = of_match_ptr("regulators"),	\
+			.of_parse_cb = max77620_of_parse_cb,		\
+			.supply_name = _sname,				\
+			.id = MAX77620_REGULATOR_ID_##_id,		\
+			.ops = &max77620_regulator_ops,			\
+			.n_voltages = ((_max_uV - _min_uV) / _step_uV) + 1, \
+			.min_uV = _min_uV,				\
+			.uV_step = _step_uV,				\
+			.enable_time = 500,				\
+			.vsel_mask = MAX77620_##_volt_mask##_VOLT_MASK,	\
+			.vsel_reg = MAX77620_REG_##_id,			\
+			.active_discharge_off = 0,			\
+			.active_discharge_on = MAX77620_SD_CFG1_ADE_ENABLE, \
+			.active_discharge_mask = MAX77620_SD_CFG1_ADE_MASK, \
+			.active_discharge_reg = MAX77620_REG_##_id##_CFG, \
+			.type = REGULATOR_VOLTAGE,			\
+		},							\
+	}
+
+#define RAIL_LDO(_id, _name, _sname, _type, _min_uV, _max_uV, _step_uV) \
+	[MAX77620_REGULATOR_ID_##_id] = {				\
+		.type = MAX77620_REGULATOR_TYPE_LDO_##_type,		\
+		.volt_addr = MAX77620_REG_##_id##_CFG,			\
+		.cfg_addr = MAX77620_REG_##_id##_CFG2,			\
+		.fps_addr = MAX77620_REG_FPS_##_id,			\
+		.remote_sense_addr = 0xFF,				\
+		.power_mode_mask = MAX77620_LDO_POWER_MODE_MASK,	\
+		.power_mode_shift = MAX77620_LDO_POWER_MODE_SHIFT,	\
+		.desc = {						\
+			.name = max77620_rails(_name),			\
+			.of_match = of_match_ptr(#_name),		\
+			.regulators_node = of_match_ptr("regulators"),	\
+			.of_parse_cb = max77620_of_parse_cb,		\
+			.supply_name = _sname,				\
+			.id = MAX77620_REGULATOR_ID_##_id,		\
+			.ops = &max77620_regulator_ops,			\
+			.n_voltages = ((_max_uV - _min_uV) / _step_uV) + 1, \
+			.min_uV = _min_uV,				\
+			.uV_step = _step_uV,				\
+			.enable_time = 500,				\
+			.vsel_mask = MAX77620_LDO_VOLT_MASK,		\
+			.vsel_reg = MAX77620_REG_##_id##_CFG,		\
+			.active_discharge_off = 0,			\
+			.active_discharge_on = MAX77620_LDO_CFG2_ADE_ENABLE, \
+			.active_discharge_mask = MAX77620_LDO_CFG2_ADE_MASK, \
+			.active_discharge_reg = MAX77620_REG_##_id##_CFG2, \
+			.type = REGULATOR_VOLTAGE,			\
+		},							\
+	}
+
+static struct max77620_regulator_info max77620_regs_info[MAX77620_NUM_REGS] = {
+	RAIL_SD(SD0, sd0, "in-sd0", SD0, 600000, 1400000, 12500, 0x22, SD0),
+	RAIL_SD(SD1, sd1, "in-sd1", SD1, 600000, 1550000, 12500, 0x22, SD1),
+	RAIL_SD(SD2, sd2, "in-sd2", SDX, 600000, 3787500, 12500, 0xFF, NONE),
+	RAIL_SD(SD3, sd3, "in-sd3", SDX, 600000, 3787500, 12500, 0xFF, NONE),
+	RAIL_SD(SD4, sd4, "in-sd4", SDX, 600000, 3787500, 12500, 0xFF, NONE),
+
+	RAIL_LDO(LDO0, ldo0, "in-ldo0-1", N, 800000, 2375000, 25000),
+	RAIL_LDO(LDO1, ldo1, "in-ldo0-1", N, 800000, 2375000, 25000),
+	RAIL_LDO(LDO2, ldo2, "in-ldo2",   P, 800000, 3950000, 50000),
+	RAIL_LDO(LDO3, ldo3, "in-ldo3-5", P, 800000, 3950000, 50000),
+	RAIL_LDO(LDO4, ldo4, "in-ldo4-6", P, 800000, 1587500, 12500),
+	RAIL_LDO(LDO5, ldo5, "in-ldo3-5", P, 800000, 3950000, 50000),
+	RAIL_LDO(LDO6, ldo6, "in-ldo4-6", P, 800000, 3950000, 50000),
+	RAIL_LDO(LDO7, ldo7, "in-ldo7-8", N, 800000, 3950000, 50000),
+	RAIL_LDO(LDO8, ldo8, "in-ldo7-8", N, 800000, 3950000, 50000),
+};
+
+static struct max77620_regulator_info max20024_regs_info[MAX77620_NUM_REGS] = {
+	RAIL_SD(SD0, sd0, "in-sd0", SD0, 800000, 1587500, 12500, 0x22, SD0),
+	RAIL_SD(SD1, sd1, "in-sd1", SD1, 600000, 3387500, 12500, 0x22, SD1),
+	RAIL_SD(SD2, sd2, "in-sd2", SDX, 600000, 3787500, 12500, 0xFF, NONE),
+	RAIL_SD(SD3, sd3, "in-sd3", SDX, 600000, 3787500, 12500, 0xFF, NONE),
+	RAIL_SD(SD4, sd4, "in-sd4", SDX, 600000, 3787500, 12500, 0xFF, NONE),
+
+	RAIL_LDO(LDO0, ldo0, "in-ldo0-1", N, 800000, 2375000, 25000),
+	RAIL_LDO(LDO1, ldo1, "in-ldo0-1", N, 800000, 2375000, 25000),
+	RAIL_LDO(LDO2, ldo2, "in-ldo2",   P, 800000, 3950000, 50000),
+	RAIL_LDO(LDO3, ldo3, "in-ldo3-5", P, 800000, 3950000, 50000),
+	RAIL_LDO(LDO4, ldo4, "in-ldo4-6", P, 800000, 1587500, 12500),
+	RAIL_LDO(LDO5, ldo5, "in-ldo3-5", P, 800000, 3950000, 50000),
+	RAIL_LDO(LDO6, ldo6, "in-ldo4-6", P, 800000, 3950000, 50000),
+	RAIL_LDO(LDO7, ldo7, "in-ldo7-8", N, 800000, 3950000, 50000),
+	RAIL_LDO(LDO8, ldo8, "in-ldo7-8", N, 800000, 3950000, 50000),
+};
+
+static int max77620_regulator_probe(struct platform_device *pdev)
+{
+	struct max77620_chip *max77620_chip = dev_get_drvdata(pdev->dev.parent);
+	struct max77620_regulator_info *rinfo;
+	struct device *dev = &pdev->dev;
+	struct regulator_config config = { };
+	struct max77620_regulator *pmic;
+	int ret = 0;
+	int id;
+
+	pmic = devm_kzalloc(dev, sizeof(*pmic), GFP_KERNEL);
+	if (!pmic)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, pmic);
+	pmic->dev = dev;
+	pmic->rmap = max77620_chip->rmap;
+	if (!dev->of_node)
+		dev->of_node = pdev->dev.parent->of_node;
+
+	switch (max77620_chip->chip_id) {
+	case MAX77620:
+		rinfo = max77620_regs_info;
+		break;
+	default:
+		rinfo = max20024_regs_info;
+		break;
+	}
+
+	config.regmap = pmic->rmap;
+	config.dev = dev;
+	config.driver_data = pmic;
+
+	for (id = 0; id < MAX77620_NUM_REGS; id++) {
+		struct regulator_dev *rdev;
+		struct regulator_desc *rdesc;
+
+		if ((max77620_chip->chip_id == MAX77620) &&
+		    (id == MAX77620_REGULATOR_ID_SD4))
+			continue;
+
+		rdesc = &rinfo[id].desc;
+		pmic->rinfo[id] = &max77620_regs_info[id];
+		pmic->enable_power_mode[id] = MAX77620_POWER_MODE_NORMAL;
+
+		ret = max77620_read_slew_rate(pmic, id);
+		if (ret < 0)
+			return ret;
+
+		rdev = devm_regulator_register(dev, rdesc, &config);
+		if (IS_ERR(rdev)) {
+			ret = PTR_ERR(rdev);
+			dev_err(dev, "Regulator registration %s failed: %d\n",
+				rdesc->name, ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int max77620_regulator_suspend(struct device *dev)
+{
+	struct max77620_regulator *pmic = dev_get_drvdata(dev);
+	struct max77620_regulator_pdata *reg_pdata;
+	int id;
+
+	for (id = 0; id < MAX77620_NUM_REGS; id++) {
+		reg_pdata = &pmic->reg_pdata[id];
+
+		max77620_regulator_set_fps_slots(pmic, id, true);
+		if (reg_pdata->suspend_fps_src < 0)
+			continue;
+
+		max77620_regulator_set_fps_src(pmic, reg_pdata->suspend_fps_src,
+					       id);
+	}
+
+	return 0;
+}
+
+static int max77620_regulator_resume(struct device *dev)
+{
+	struct max77620_regulator *pmic = dev_get_drvdata(dev);
+	struct max77620_regulator_pdata *reg_pdata;
+	int id;
+
+	for (id = 0; id < MAX77620_NUM_REGS; id++) {
+		reg_pdata = &pmic->reg_pdata[id];
+
+		max77620_regulator_set_fps_slots(pmic, id, false);
+		if (reg_pdata->active_fps_src < 0)
+			continue;
+		max77620_regulator_set_fps_src(pmic, reg_pdata->active_fps_src,
+					       id);
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops max77620_regulator_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(max77620_regulator_suspend,
+				max77620_regulator_resume)
+};
+
+static const struct platform_device_id max77620_regulator_devtype[] = {
+	{ .name = "max77620-pmic", },
+	{ .name = "max20024-pmic", },
+	{},
+};
+MODULE_DEVICE_TABLE(platform, max77620_regulator_devtype);
+
+static struct platform_driver max77620_regulator_driver = {
+	.probe = max77620_regulator_probe,
+	.id_table = max77620_regulator_devtype,
+	.driver = {
+		.name = "max77620-pmic",
+		.pm = &max77620_regulator_pm_ops,
+	},
+};
+
+module_platform_driver(max77620_regulator_driver);
+
+MODULE_DESCRIPTION("MAX77620/MAX20024 regulator driver");
+MODULE_AUTHOR("Mallikarjun Kasoju <mkasoju@nvidia.com>");
+MODULE_AUTHOR("Laxman Dewangan <ldewangan@nvidia.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/regulator/max77686.c b/drivers/regulator/max77686-regulator.c
index 17ccf365a9c0..17ccf365a9c0 100644
--- a/drivers/regulator/max77686.c
+++ b/drivers/regulator/max77686-regulator.c
diff --git a/drivers/regulator/max77802.c b/drivers/regulator/max77802-regulator.c
index c07ee13bd470..c07ee13bd470 100644
--- a/drivers/regulator/max77802.c
+++ b/drivers/regulator/max77802-regulator.c
diff --git a/drivers/regulator/mt6397-regulator.c b/drivers/regulator/mt6397-regulator.c
index a5b2f4762677..17a5b6c2d6a9 100644
--- a/drivers/regulator/mt6397-regulator.c
+++ b/drivers/regulator/mt6397-regulator.c
@@ -317,11 +317,25 @@ static int mt6397_regulator_probe(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct platform_device_id mt6397_platform_ids[] = {
+	{"mt6397-regulator", 0},
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(platform, mt6397_platform_ids);
+
+static const struct of_device_id mt6397_of_match[] = {
+	{ .compatible = "mediatek,mt6397-regulator", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, mt6397_of_match);
+
 static struct platform_driver mt6397_regulator_driver = {
 	.driver = {
 		.name = "mt6397-regulator",
+		.of_match_table = of_match_ptr(mt6397_of_match),
 	},
 	.probe = mt6397_regulator_probe,
+	.id_table = mt6397_platform_ids,
 };
 
 module_platform_driver(mt6397_regulator_driver);
@@ -329,4 +343,3 @@ module_platform_driver(mt6397_regulator_driver);
 MODULE_AUTHOR("Flora Fu <flora.fu@mediatek.com>");
 MODULE_DESCRIPTION("Regulator Driver for MediaTek MT6397 PMIC");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:mt6397-regulator");
diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index 499e437c7e91..6b0aa80b22fd 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -28,7 +28,6 @@ static void of_get_regulation_constraints(struct device_node *np,
 					struct regulator_init_data **init_data,
 					const struct regulator_desc *desc)
 {
-	const __be32 *min_uV, *max_uV;
 	struct regulation_constraints *constraints = &(*init_data)->constraints;
 	struct regulator_state *suspend_state;
 	struct device_node *suspend_np;
@@ -37,18 +36,18 @@ static void of_get_regulation_constraints(struct device_node *np,
 
 	constraints->name = of_get_property(np, "regulator-name", NULL);
 
-	min_uV = of_get_property(np, "regulator-min-microvolt", NULL);
-	if (min_uV)
-		constraints->min_uV = be32_to_cpu(*min_uV);
-	max_uV = of_get_property(np, "regulator-max-microvolt", NULL);
-	if (max_uV)
-		constraints->max_uV = be32_to_cpu(*max_uV);
+	if (!of_property_read_u32(np, "regulator-min-microvolt", &pval))
+		constraints->min_uV = pval;
+
+	if (!of_property_read_u32(np, "regulator-max-microvolt", &pval))
+		constraints->max_uV = pval;
 
 	/* Voltage change possible? */
 	if (constraints->min_uV != constraints->max_uV)
 		constraints->valid_ops_mask |= REGULATOR_CHANGE_VOLTAGE;
 	/* Only one voltage?  Then make sure it's set. */
-	if (min_uV && max_uV && constraints->min_uV == constraints->max_uV)
+	if (constraints->min_uV && constraints->max_uV &&
+	    constraints->min_uV == constraints->max_uV)
 		constraints->apply_uV = true;
 
 	if (!of_property_read_u32(np, "regulator-microvolt-offset", &pval))
@@ -93,6 +92,12 @@ static void of_get_regulation_constraints(struct device_node *np,
 
 	constraints->soft_start = of_property_read_bool(np,
 					"regulator-soft-start");
+	ret = of_property_read_u32(np, "regulator-active-discharge", &pval);
+	if (!ret) {
+		constraints->active_discharge =
+				(pval) ? REGULATOR_ACTIVE_DISCHARGE_ENABLE :
+					REGULATOR_ACTIVE_DISCHARGE_DISABLE;
+	}
 
 	if (!of_property_read_u32(np, "regulator-initial-mode", &pval)) {
 		if (desc && desc->of_map_mode) {
diff --git a/drivers/regulator/pv88060-regulator.c b/drivers/regulator/pv88060-regulator.c
index 094376c8de4b..c448b727f5f8 100644
--- a/drivers/regulator/pv88060-regulator.c
+++ b/drivers/regulator/pv88060-regulator.c
@@ -285,8 +285,8 @@ static irqreturn_t pv88060_irq_handler(int irq, void *data)
 			}
 		}
 
-		err = regmap_update_bits(chip->regmap, PV88060_REG_EVENT_A,
-			PV88060_E_VDD_FLT, PV88060_E_VDD_FLT);
+		err = regmap_write(chip->regmap, PV88060_REG_EVENT_A,
+			PV88060_E_VDD_FLT);
 		if (err < 0)
 			goto error_i2c;
 
@@ -302,8 +302,8 @@ static irqreturn_t pv88060_irq_handler(int irq, void *data)
 			}
 		}
 
-		err = regmap_update_bits(chip->regmap, PV88060_REG_EVENT_A,
-			PV88060_E_OVER_TEMP, PV88060_E_OVER_TEMP);
+		err = regmap_write(chip->regmap, PV88060_REG_EVENT_A,
+			PV88060_E_OVER_TEMP);
 		if (err < 0)
 			goto error_i2c;
 
diff --git a/drivers/regulator/pv88090-regulator.c b/drivers/regulator/pv88090-regulator.c
index ac15f31b5fe0..0057c6740d6f 100644
--- a/drivers/regulator/pv88090-regulator.c
+++ b/drivers/regulator/pv88090-regulator.c
@@ -283,8 +283,8 @@ static irqreturn_t pv88090_irq_handler(int irq, void *data)
 			}
 		}
 
-		err = regmap_update_bits(chip->regmap, PV88090_REG_EVENT_A,
-			PV88090_E_VDD_FLT, PV88090_E_VDD_FLT);
+		err = regmap_write(chip->regmap, PV88090_REG_EVENT_A,
+			PV88090_E_VDD_FLT);
 		if (err < 0)
 			goto error_i2c;
 
@@ -300,8 +300,8 @@ static irqreturn_t pv88090_irq_handler(int irq, void *data)
 			}
 		}
 
-		err = regmap_update_bits(chip->regmap, PV88090_REG_EVENT_A,
-			PV88090_E_OVER_TEMP, PV88090_E_OVER_TEMP);
+		err = regmap_write(chip->regmap, PV88090_REG_EVENT_A,
+			PV88090_E_OVER_TEMP);
 		if (err < 0)
 			goto error_i2c;
 
diff --git a/drivers/regulator/pwm-regulator.c b/drivers/regulator/pwm-regulator.c
index 3aca067b9901..4689d62f4841 100644
--- a/drivers/regulator/pwm-regulator.c
+++ b/drivers/regulator/pwm-regulator.c
@@ -27,6 +27,13 @@ struct pwm_regulator_data {
 
 	/* Voltage table */
 	struct pwm_voltages *duty_cycle_table;
+
+	/* regulator descriptor */
+	struct regulator_desc desc;
+
+	/* Regulator ops */
+	struct regulator_ops ops;
+
 	int state;
 
 	/* Continuous voltage */
@@ -115,7 +122,7 @@ static int pwm_voltage_to_duty_cycle_percentage(struct regulator_dev *rdev, int
 	int max_uV = rdev->constraints->max_uV;
 	int diff = max_uV - min_uV;
 
-	return 100 - (((req_uV * 100) - (min_uV * 100)) / diff);
+	return ((req_uV * 100) - (min_uV * 100)) / diff;
 }
 
 static int pwm_regulator_get_voltage(struct regulator_dev *rdev)
@@ -212,8 +219,10 @@ static int pwm_regulator_init_table(struct platform_device *pdev,
 	}
 
 	drvdata->duty_cycle_table	= duty_cycle_table;
-	pwm_regulator_desc.ops		= &pwm_regulator_voltage_table_ops;
-	pwm_regulator_desc.n_voltages	= length / sizeof(*duty_cycle_table);
+	memcpy(&drvdata->ops, &pwm_regulator_voltage_table_ops,
+	       sizeof(drvdata->ops));
+	drvdata->desc.ops = &drvdata->ops;
+	drvdata->desc.n_voltages	= length / sizeof(*duty_cycle_table);
 
 	return 0;
 }
@@ -221,8 +230,10 @@ static int pwm_regulator_init_table(struct platform_device *pdev,
 static int pwm_regulator_init_continuous(struct platform_device *pdev,
 					 struct pwm_regulator_data *drvdata)
 {
-	pwm_regulator_desc.ops = &pwm_regulator_voltage_continuous_ops;
-	pwm_regulator_desc.continuous_voltage_range = true;
+	memcpy(&drvdata->ops, &pwm_regulator_voltage_continuous_ops,
+	       sizeof(drvdata->ops));
+	drvdata->desc.ops = &drvdata->ops;
+	drvdata->desc.continuous_voltage_range = true;
 
 	return 0;
 }
@@ -245,6 +256,8 @@ static int pwm_regulator_probe(struct platform_device *pdev)
 	if (!drvdata)
 		return -ENOMEM;
 
+	memcpy(&drvdata->desc, &pwm_regulator_desc, sizeof(drvdata->desc));
+
 	if (of_find_property(np, "voltage-table", NULL))
 		ret = pwm_regulator_init_table(pdev, drvdata);
 	else
@@ -253,7 +266,7 @@ static int pwm_regulator_probe(struct platform_device *pdev)
 		return ret;
 
 	init_data = of_get_regulator_init_data(&pdev->dev, np,
-					       &pwm_regulator_desc);
+					       &drvdata->desc);
 	if (!init_data)
 		return -ENOMEM;
 
@@ -269,10 +282,10 @@ static int pwm_regulator_probe(struct platform_device *pdev)
 	}
 
 	regulator = devm_regulator_register(&pdev->dev,
-					    &pwm_regulator_desc, &config);
+					    &drvdata->desc, &config);
 	if (IS_ERR(regulator)) {
 		dev_err(&pdev->dev, "Failed to register regulator %s\n",
-			pwm_regulator_desc.name);
+			drvdata->desc.name);
 		return PTR_ERR(regulator);
 	}
 
diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c
index 3242ffc0cb25..d24e2c783dc5 100644
--- a/drivers/regulator/s2mps11.c
+++ b/drivers/regulator/s2mps11.c
@@ -38,7 +38,6 @@
 /* The highest number of possible regulators for supported devices. */
 #define S2MPS_REGULATOR_MAX		S2MPS13_REGULATOR_MAX
 struct s2mps11_info {
-	unsigned int rdev_num;
 	int ramp_delay2;
 	int ramp_delay34;
 	int ramp_delay5;
@@ -54,7 +53,10 @@ struct s2mps11_info {
 	 */
 	DECLARE_BITMAP(suspend_state, S2MPS_REGULATOR_MAX);
 
-	/* Array of size rdev_num with GPIO-s for external sleep control */
+	/*
+	 * Array (size: number of regulators) with GPIO-s for external
+	 * sleep control.
+	 */
 	int *ext_control_gpio;
 };
 
@@ -819,7 +821,8 @@ static void s2mps14_pmic_dt_parse_ext_control_gpio(struct platform_device *pdev,
 }
 
 static int s2mps11_pmic_dt_parse(struct platform_device *pdev,
-		struct of_regulator_match *rdata, struct s2mps11_info *s2mps11)
+		struct of_regulator_match *rdata, struct s2mps11_info *s2mps11,
+		unsigned int rdev_num)
 {
 	struct device_node *reg_np;
 
@@ -829,7 +832,7 @@ static int s2mps11_pmic_dt_parse(struct platform_device *pdev,
 		return -EINVAL;
 	}
 
-	of_regulator_match(&pdev->dev, reg_np, rdata, s2mps11->rdev_num);
+	of_regulator_match(&pdev->dev, reg_np, rdata, rdev_num);
 	if (s2mps11->dev_type == S2MPS14X)
 		s2mps14_pmic_dt_parse_ext_control_gpio(pdev, rdata, s2mps11);
 
@@ -1077,6 +1080,7 @@ static int s2mps11_pmic_probe(struct platform_device *pdev)
 	struct of_regulator_match *rdata = NULL;
 	struct regulator_config config = { };
 	struct s2mps11_info *s2mps11;
+	unsigned int rdev_num = 0;
 	int i, ret = 0;
 	const struct regulator_desc *regulators;
 
@@ -1088,28 +1092,29 @@ static int s2mps11_pmic_probe(struct platform_device *pdev)
 	s2mps11->dev_type = platform_get_device_id(pdev)->driver_data;
 	switch (s2mps11->dev_type) {
 	case S2MPS11X:
-		s2mps11->rdev_num = ARRAY_SIZE(s2mps11_regulators);
+		rdev_num = ARRAY_SIZE(s2mps11_regulators);
 		regulators = s2mps11_regulators;
-		BUILD_BUG_ON(S2MPS_REGULATOR_MAX < s2mps11->rdev_num);
+		BUILD_BUG_ON(S2MPS_REGULATOR_MAX < ARRAY_SIZE(s2mps11_regulators));
 		break;
 	case S2MPS13X:
-		s2mps11->rdev_num = ARRAY_SIZE(s2mps13_regulators);
+		rdev_num = ARRAY_SIZE(s2mps13_regulators);
 		regulators = s2mps13_regulators;
-		BUILD_BUG_ON(S2MPS_REGULATOR_MAX < s2mps11->rdev_num);
+		BUILD_BUG_ON(S2MPS_REGULATOR_MAX < ARRAY_SIZE(s2mps13_regulators));
 		break;
 	case S2MPS14X:
-		s2mps11->rdev_num = ARRAY_SIZE(s2mps14_regulators);
+		rdev_num = ARRAY_SIZE(s2mps14_regulators);
 		regulators = s2mps14_regulators;
-		BUILD_BUG_ON(S2MPS_REGULATOR_MAX < s2mps11->rdev_num);
+		BUILD_BUG_ON(S2MPS_REGULATOR_MAX < ARRAY_SIZE(s2mps14_regulators));
 		break;
 	case S2MPS15X:
-		s2mps11->rdev_num = ARRAY_SIZE(s2mps15_regulators);
+		rdev_num = ARRAY_SIZE(s2mps15_regulators);
 		regulators = s2mps15_regulators;
+		BUILD_BUG_ON(S2MPS_REGULATOR_MAX < ARRAY_SIZE(s2mps15_regulators));
 		break;
 	case S2MPU02:
-		s2mps11->rdev_num = ARRAY_SIZE(s2mpu02_regulators);
+		rdev_num = ARRAY_SIZE(s2mpu02_regulators);
 		regulators = s2mpu02_regulators;
-		BUILD_BUG_ON(S2MPS_REGULATOR_MAX < s2mps11->rdev_num);
+		BUILD_BUG_ON(S2MPS_REGULATOR_MAX < ARRAY_SIZE(s2mpu02_regulators));
 		break;
 	default:
 		dev_err(&pdev->dev, "Invalid device type: %u\n",
@@ -1118,7 +1123,7 @@ static int s2mps11_pmic_probe(struct platform_device *pdev)
 	}
 
 	s2mps11->ext_control_gpio = devm_kmalloc(&pdev->dev,
-			sizeof(*s2mps11->ext_control_gpio) * s2mps11->rdev_num,
+			sizeof(*s2mps11->ext_control_gpio) * rdev_num,
 			GFP_KERNEL);
 	if (!s2mps11->ext_control_gpio)
 		return -ENOMEM;
@@ -1126,7 +1131,7 @@ static int s2mps11_pmic_probe(struct platform_device *pdev)
 	 * 0 is a valid GPIO so initialize all GPIO-s to negative value
 	 * to indicate that external control won't be used for this regulator.
 	 */
-	for (i = 0; i < s2mps11->rdev_num; i++)
+	for (i = 0; i < rdev_num; i++)
 		s2mps11->ext_control_gpio[i] = -EINVAL;
 
 	if (!iodev->dev->of_node) {
@@ -1140,14 +1145,14 @@ static int s2mps11_pmic_probe(struct platform_device *pdev)
 		}
 	}
 
-	rdata = kzalloc(sizeof(*rdata) * s2mps11->rdev_num, GFP_KERNEL);
+	rdata = kzalloc(sizeof(*rdata) * rdev_num, GFP_KERNEL);
 	if (!rdata)
 		return -ENOMEM;
 
-	for (i = 0; i < s2mps11->rdev_num; i++)
+	for (i = 0; i < rdev_num; i++)
 		rdata[i].name = regulators[i].name;
 
-	ret = s2mps11_pmic_dt_parse(pdev, rdata, s2mps11);
+	ret = s2mps11_pmic_dt_parse(pdev, rdata, s2mps11, rdev_num);
 	if (ret)
 		goto out;
 
@@ -1159,7 +1164,7 @@ common_reg:
 	config.driver_data = s2mps11;
 	config.ena_gpio_flags = GPIOF_OUT_INIT_HIGH;
 	config.ena_gpio_initialized = true;
-	for (i = 0; i < s2mps11->rdev_num; i++) {
+	for (i = 0; i < rdev_num; i++) {
 		struct regulator_dev *regulator;
 
 		if (pdata) {
diff --git a/drivers/regulator/s5m8767.c b/drivers/regulator/s5m8767.c
index 58f5d3b8e981..27343e1c43ef 100644
--- a/drivers/regulator/s5m8767.c
+++ b/drivers/regulator/s5m8767.c
@@ -202,9 +202,10 @@ static int s5m8767_get_register(struct s5m8767_info *s5m8767, int reg_id,
 		}
 	}
 
-	if (i < s5m8767->num_regulators)
-		*enable_ctrl =
-		s5m8767_opmode_reg[reg_id][mode] << S5M8767_ENCTRL_SHIFT;
+	if (i >= s5m8767->num_regulators)
+		return -EINVAL;
+
+	*enable_ctrl = s5m8767_opmode_reg[reg_id][mode] << S5M8767_ENCTRL_SHIFT;
 
 	return 0;
 }
@@ -937,8 +938,12 @@ static int s5m8767_pmic_probe(struct platform_device *pdev)
 			else
 				regulators[id].vsel_mask = 0xff;
 
-			s5m8767_get_register(s5m8767, id, &enable_reg,
+			ret = s5m8767_get_register(s5m8767, id, &enable_reg,
 					     &enable_val);
+			if (ret) {
+				dev_err(s5m8767->dev, "error reading registers\n");
+				return ret;
+			}
 			regulators[id].enable_reg = enable_reg;
 			regulators[id].enable_mask = S5M8767_ENCTRL_MASK;
 			regulators[id].enable_val = enable_val;
diff --git a/drivers/regulator/vexpress.c b/drivers/regulator/vexpress-regulator.c
index c810cbbd463f..c810cbbd463f 100644
--- a/drivers/regulator/vexpress.c
+++ b/drivers/regulator/vexpress-regulator.c
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 376322f71fd5..544bd3493852 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -140,7 +140,6 @@ config RTC_DRV_TEST
 	  will be called rtc-test.
 
 comment "I2C RTC drivers"
-	depends on I2C
 
 if I2C
 
@@ -212,6 +211,15 @@ config RTC_DRV_DS1307
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-ds1307.
 
+config RTC_DRV_DS1307_HWMON
+	bool "HWMON support for rtc-ds1307"
+	depends on RTC_DRV_DS1307 && HWMON
+	depends on !(RTC_DRV_DS1307=y && HWMON=m)
+	default y
+	help
+	  Say Y here if you want to expose temperature sensor data on
+	  rtc-ds1307 (only DS3231)
+
 config RTC_DRV_DS1374
 	tristate "Dallas/Maxim DS1374"
 	help
@@ -239,16 +247,6 @@ config RTC_DRV_DS1672
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-ds1672.
 
-config RTC_DRV_DS3232
-	tristate "Dallas/Maxim DS3232"
-	help
-	  If you say yes here you get support for Dallas Semiconductor
-	  DS3232 real-time clock chips. If an interrupt is associated
-	  with the device, the alarm functionality is supported.
-
-	  This driver can also be built as a module.  If so, the module
-	  will be called rtc-ds3232.
-
 config RTC_DRV_HYM8563
 	tristate "Haoyu Microelectronics HYM8563"
 	depends on OF
@@ -317,10 +315,10 @@ config RTC_DRV_MAX8997
 
 config RTC_DRV_MAX77686
 	tristate "Maxim MAX77686"
-	depends on MFD_MAX77686
+	depends on MFD_MAX77686 || MFD_MAX77620
 	help
 	  If you say yes here you will get support for the
-	  RTC of Maxim MAX77686 PMIC.
+	  RTC of Maxim MAX77686/MAX77620/MAX77802 PMIC.
 
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-max77686.
@@ -335,16 +333,6 @@ config RTC_DRV_RK808
 	  This driver can also be built as a module. If so, the module
 	  will be called rk808-rtc.
 
-config RTC_DRV_MAX77802
-	tristate "Maxim 77802 RTC"
-	depends on MFD_MAX77686
-	help
-	  If you say yes here you will get support for the
-	  RTC of Maxim MAX77802 PMIC.
-
-	  This driver can also be built as a module. If so, the module
-	  will be called rtc-max77802.
-
 config RTC_DRV_RS5C372
 	tristate "Ricoh R2025S/D, RS5C372A/B, RV5C386, RV5C387A"
 	help
@@ -391,25 +379,6 @@ config RTC_DRV_X1205
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-x1205.
 
-config RTC_DRV_PALMAS
-	tristate "TI Palmas RTC driver"
-	depends on MFD_PALMAS
-	help
-	  If you say yes here you get support for the RTC of TI PALMA series PMIC
-	  chips.
-
-	  This driver can also be built as a module. If so, the module
-	  will be called rtc-palma.
-
-config RTC_DRV_PCF2127
-	tristate "NXP PCF2127"
-	help
-	  If you say yes here you get support for the NXP PCF2127/29 RTC
-	  chips.
-
-	  This driver can also be built as a module. If so, the module
-	  will be called rtc-pcf2127.
-
 config RTC_DRV_PCF8523
 	tristate "NXP PCF8523"
 	help
@@ -419,6 +388,14 @@ config RTC_DRV_PCF8523
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-pcf8523.
 
+config RTC_DRV_PCF85063
+	tristate "NXP PCF85063"
+	help
+	  If you say yes here you get support for the PCF85063 RTC chip
+
+	  This driver can also be built as a module. If so, the module
+	  will be called rtc-pcf85063.
+
 config RTC_DRV_PCF8563
 	tristate "Philips PCF8563/Epson RTC8564"
 	help
@@ -429,14 +406,6 @@ config RTC_DRV_PCF8563
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-pcf8563.
 
-config RTC_DRV_PCF85063
-	tristate "nxp PCF85063"
-	help
-	  If you say yes here you get support for the PCF85063 RTC chip
-
-	  This driver can also be built as a module. If so, the module
-	  will be called rtc-pcf85063.
-
 config RTC_DRV_PCF8583
 	tristate "Philips PCF8583"
 	help
@@ -501,6 +470,16 @@ config RTC_DRV_TWL4030
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-twl.
 
+config RTC_DRV_PALMAS
+	tristate "TI Palmas RTC driver"
+	depends on MFD_PALMAS
+	help
+	  If you say yes here you get support for the RTC of TI PALMA series PMIC
+	  chips.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called rtc-palma.
+
 config RTC_DRV_TPS6586X
 	tristate "TI TPS6586X RTC driver"
 	depends on MFD_TPS6586X
@@ -595,14 +574,23 @@ config RTC_DRV_EM3027
 	  will be called rtc-em3027.
 
 config RTC_DRV_RV3029C2
-	tristate "Micro Crystal RTC"
+	tristate "Micro Crystal RV3029"
 	help
 	  If you say yes here you get support for the Micro Crystal
-	  RV3029-C2 RTC chips.
+	  RV3029 RTC chips.
 
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-rv3029c2.
 
+config RTC_DRV_RV3029_HWMON
+	bool "HWMON support for RV3029"
+	depends on RTC_DRV_RV3029C2 && HWMON
+	depends on !(RTC_DRV_RV3029C2=y && HWMON=m)
+	default y
+	help
+	  Say Y here if you want to expose temperature sensor data on
+	  rtc-rv3029c2.
+
 config RTC_DRV_RV8803
 	tristate "Micro Crystal RV8803"
 	help
@@ -691,15 +679,6 @@ config RTC_DRV_DS1390
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-ds1390.
 
-config RTC_DRV_MAX6902
-	tristate "Maxim MAX6902"
-	help
-	  If you say yes here you will get support for the
-	  Maxim MAX6902 SPI RTC chip.
-
-	  This driver can also be built as a module. If so, the module
-	  will be called rtc-max6902.
-
 config RTC_DRV_R9701
 	tristate "Epson RTC-9701JE"
 	help
@@ -709,6 +688,23 @@ config RTC_DRV_R9701
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-r9701.
 
+config RTC_DRV_RX4581
+	tristate "Epson RX-4581"
+	help
+	  If you say yes here you will get support for the Epson RX-4581.
+
+	  This driver can also be built as a module. If so the module
+	  will be called rtc-rx4581.
+
+config RTC_DRV_RX6110
+	tristate "Epson RX-6110"
+	select REGMAP_SPI
+	help
+	  If you say yes here you will get support for the Epson RX-6610.
+
+	  This driver can also be built as a module. If so the module
+	  will be called rtc-rx6110.
+
 config RTC_DRV_RS5C348
 	tristate "Ricoh RS5C348A/B"
 	help
@@ -718,14 +714,14 @@ config RTC_DRV_RS5C348
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-rs5c348.
 
-config RTC_DRV_DS3234
-	tristate "Maxim/Dallas DS3234"
+config RTC_DRV_MAX6902
+	tristate "Maxim MAX6902"
 	help
-	  If you say yes here you get support for the
-	  Maxim/Dallas DS3234 SPI RTC chip.
+	  If you say yes here you will get support for the
+	  Maxim MAX6902 SPI RTC chip.
 
 	  This driver can also be built as a module. If so, the module
-	  will be called rtc-ds3234.
+	  will be called rtc-max6902.
 
 config RTC_DRV_PCF2123
 	tristate "NXP PCF2123"
@@ -736,14 +732,6 @@ config RTC_DRV_PCF2123
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-pcf2123.
 
-config RTC_DRV_RX4581
-	tristate "Epson RX-4581"
-	help
-	  If you say yes here you will get support for the Epson RX-4581.
-
-	  This driver can also be built as a module. If so the module
-	  will be called rtc-rx4581.
-
 config RTC_DRV_MCP795
 	tristate "Microchip MCP795"
 	help
@@ -754,6 +742,41 @@ config RTC_DRV_MCP795
 
 endif # SPI_MASTER
 
+#
+# Helper to resolve issues with configs that have SPI enabled but I2C
+# modular.  See SND_SOC_I2C_AND_SPI for more information
+#
+config RTC_I2C_AND_SPI
+	tristate
+	default m if I2C=m
+	default y if I2C=y
+	default y if SPI_MASTER=y
+	select REGMAP_I2C if I2C
+	select REGMAP_SPI if SPI_MASTER
+
+comment "SPI and I2C RTC drivers"
+
+config RTC_DRV_DS3232
+	tristate "Dallas/Maxim DS3232/DS3234"
+	depends on RTC_I2C_AND_SPI
+	help
+	  If you say yes here you get support for Dallas Semiconductor
+	  DS3232 and DS3234 real-time clock chips. If an interrupt is associated
+	  with the device, the alarm functionality is supported.
+
+	  This driver can also be built as a module.  If so, the module
+	  will be called rtc-ds3232.
+
+config RTC_DRV_PCF2127
+	tristate "NXP PCF2127"
+	depends on RTC_I2C_AND_SPI
+	help
+	  If you say yes here you get support for the NXP PCF2127/29 RTC
+	  chips.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called rtc-pcf2127.
+
 comment "Platform RTC drivers"
 
 # this 'CMOS' RTC driver is arch dependent because <asm-generic/rtc.h>
@@ -1087,7 +1110,7 @@ config RTC_DRV_WM8350
 
 config RTC_DRV_SPEAR
 	tristate "SPEAR ST RTC"
-	depends on PLAT_SPEAR
+	depends on PLAT_SPEAR || COMPILE_TEST
 	default y
 	help
 	 If you say Y here you will get support for the RTC found on
@@ -1119,7 +1142,7 @@ config RTC_DRV_AB8500
 
 config RTC_DRV_NUC900
 	tristate "NUC910/NUC920 RTC driver"
-	depends on ARCH_W90X900
+	depends on ARCH_W90X900 || COMPILE_TEST
 	help
 	  If you say yes here you get support for the RTC subsystem of the
 	  NUC910/NUC920 used in embedded systems.
@@ -1144,9 +1167,19 @@ config RTC_DRV_ZYNQMP
 
 comment "on-CPU RTC drivers"
 
+config RTC_DRV_ASM9260
+	tristate "Alphascale asm9260 RTC"
+	depends on MACH_ASM9260
+	help
+	  If you say yes here you get support for the RTC on the
+	  Alphascale asm9260 SoC.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called rtc-asm9260.
+
 config RTC_DRV_DAVINCI
 	tristate "TI DaVinci RTC"
-	depends on ARCH_DAVINCI_DM365
+	depends on ARCH_DAVINCI_DM365 || COMPILE_TEST
 	help
 	  If you say yes here you get support for the RTC on the
 	  DaVinci platforms (DM365).
@@ -1156,7 +1189,7 @@ config RTC_DRV_DAVINCI
 
 config RTC_DRV_DIGICOLOR
 	tristate "Conexant Digicolor RTC"
-	depends on ARCH_DIGICOLOR
+	depends on ARCH_DIGICOLOR || COMPILE_TEST
 	help
 	  If you say yes here you get support for the RTC on Conexant
 	  Digicolor platforms. This currently includes the CX92755 SoC.
@@ -1175,7 +1208,7 @@ config RTC_DRV_IMXDI
 
 config RTC_DRV_OMAP
 	tristate "TI OMAP Real Time Clock"
-	depends on ARCH_OMAP || ARCH_DAVINCI
+	depends on ARCH_OMAP || ARCH_DAVINCI || COMPILE_TEST
 	help
 	  Say "yes" here to support the on chip real time clock
 	  present on TI OMAP1, AM33xx, DA8xx/OMAP-L13x, AM43xx and DRA7xx.
@@ -1192,7 +1225,7 @@ config HAVE_S3C_RTC
 
 config RTC_DRV_S3C
 	tristate "Samsung S3C series SoC RTC"
-	depends on ARCH_S3C64XX || HAVE_S3C_RTC
+	depends on ARCH_S3C64XX || HAVE_S3C_RTC || COMPILE_TEST
 	help
 	  RTC (Realtime Clock) driver for the clock inbuilt into the
 	  Samsung S3C24XX series of SoCs. This can provide periodic
@@ -1208,7 +1241,7 @@ config RTC_DRV_S3C
 
 config RTC_DRV_EP93XX
 	tristate "Cirrus Logic EP93XX"
-	depends on ARCH_EP93XX
+	depends on ARCH_EP93XX || COMPILE_TEST
 	help
 	  If you say yes here you get support for the
 	  RTC embedded in the Cirrus Logic EP93XX processors.
@@ -1238,7 +1271,7 @@ config RTC_DRV_SH
 
 config RTC_DRV_VR41XX
 	tristate "NEC VR41XX"
-	depends on CPU_VR41XX
+	depends on CPU_VR41XX || COMPILE_TEST
 	help
 	  If you say Y here you will get access to the real time clock
 	  built into your NEC VR41XX CPU.
@@ -1268,14 +1301,14 @@ config RTC_DRV_PL031
 
 config RTC_DRV_AT32AP700X
 	tristate "AT32AP700X series RTC"
-	depends on PLATFORM_AT32AP
+	depends on PLATFORM_AT32AP || COMPILE_TEST
 	help
 	  Driver for the internal RTC (Realtime Clock) on Atmel AVR32
 	  AT32AP700x family processors.
 
 config RTC_DRV_AT91RM9200
 	tristate "AT91RM9200 or some AT91SAM9 RTC"
-	depends on ARCH_AT91
+	depends on ARCH_AT91 || COMPILE_TEST
 	help
 	  Driver for the internal RTC (Realtime Clock) module found on
 	  Atmel AT91RM9200's and some  AT91SAM9 chips. On AT91SAM9 chips
@@ -1283,7 +1316,7 @@ config RTC_DRV_AT91RM9200
 
 config RTC_DRV_AT91SAM9
 	tristate "AT91SAM9 RTT as RTC"
-	depends on ARCH_AT91
+	depends on ARCH_AT91 || COMPILE_TEST
 	select MFD_SYSCON
 	help
 	  Some AT91SAM9 SoCs provide an RTT (Real Time Timer) block which
@@ -1325,17 +1358,17 @@ config RTC_DRV_GENERIC
 	tristate "Generic RTC support"
 	# Please consider writing a new RTC driver instead of using the generic
 	# RTC abstraction
-	depends on PARISC || M68K || PPC || SUPERH32
+	depends on PARISC || M68K || PPC || SUPERH32 || COMPILE_TEST
 	help
 	  Say Y or M here to enable RTC support on systems using the generic
 	  RTC abstraction. If you do not know what you are doing, you should
 	  just say Y.
 
 config RTC_DRV_PXA
-       tristate "PXA27x/PXA3xx"
-       depends on ARCH_PXA
-       select RTC_DRV_SA1100
-       help
+	tristate "PXA27x/PXA3xx"
+	depends on ARCH_PXA
+	select RTC_DRV_SA1100
+	help
          If you say Y here you will get access to the real time clock
          built into your PXA27x or PXA3xx CPU. This RTC is actually 2 RTCs
          consisting of an SA1100 compatible RTC and the extended PXA RTC.
@@ -1345,7 +1378,7 @@ config RTC_DRV_PXA
 
 config RTC_DRV_VT8500
 	tristate "VIA/WonderMedia 85xx SoC RTC"
-	depends on ARCH_VT8500
+	depends on ARCH_VT8500 || COMPILE_TEST
 	help
 	  If you say Y here you will get access to the real time clock
 	  built into your VIA VT8500 SoC or its relatives.
@@ -1360,14 +1393,15 @@ config RTC_DRV_SUN4V
 
 config RTC_DRV_SUN6I
 	tristate "Allwinner A31 RTC"
-	depends on MACH_SUN6I || MACH_SUN8I
+	default MACH_SUN6I || MACH_SUN8I || COMPILE_TEST
+	depends on ARCH_SUNXI
 	help
-	  If you say Y here you will get support for the RTC found on
-	  Allwinner A31.
+	  If you say Y here you will get support for the RTC found in
+	  some Allwinner SoCs like the A31 or the A64.
 
 config RTC_DRV_SUNXI
 	tristate "Allwinner sun4i/sun7i RTC"
-	depends on MACH_SUN4I || MACH_SUN7I
+	depends on MACH_SUN4I || MACH_SUN7I || COMPILE_TEST
 	help
 	  If you say Y here you will get support for the RTC found on
 	  Allwinner A10/A20.
@@ -1388,7 +1422,7 @@ config RTC_DRV_TX4939
 
 config RTC_DRV_MV
 	tristate "Marvell SoC RTC"
-	depends on ARCH_DOVE || ARCH_MVEBU
+	depends on ARCH_DOVE || ARCH_MVEBU || COMPILE_TEST
 	help
 	  If you say yes here you will get support for the in-chip RTC
 	  that can be found in some of Marvell's SoC devices, such as
@@ -1399,7 +1433,7 @@ config RTC_DRV_MV
 
 config RTC_DRV_ARMADA38X
 	tristate "Armada 38x Marvell SoC RTC"
-	depends on ARCH_MVEBU
+	depends on ARCH_MVEBU || COMPILE_TEST
 	help
 	  If you say yes here you will get support for the in-chip RTC
 	  that can be found in the Armada 38x Marvell's SoC device
@@ -1429,7 +1463,7 @@ config RTC_DRV_PS3
 
 config RTC_DRV_COH901331
 	tristate "ST-Ericsson COH 901 331 RTC"
-	depends on ARCH_U300
+	depends on ARCH_U300 || COMPILE_TEST
 	help
 	  If you say Y here you will get access to ST-Ericsson
 	  COH 901 331 RTC clock found in some ST-Ericsson Mobile
@@ -1441,7 +1475,7 @@ config RTC_DRV_COH901331
 
 config RTC_DRV_STMP
 	tristate "Freescale STMP3xxx/i.MX23/i.MX28 RTC"
-	depends on ARCH_MXS
+	depends on ARCH_MXS || COMPILE_TEST
 	select STMP_DEVICE
 	help
 	  If you say yes here you will get support for the onboard
@@ -1476,7 +1510,7 @@ config RTC_DRV_MPC5121
 
 config RTC_DRV_JZ4740
 	tristate "Ingenic JZ4740 SoC"
-	depends on MACH_JZ4740
+	depends on MACH_JZ4740 || COMPILE_TEST
 	help
 	  If you say yes here you get support for the Ingenic JZ4740 SoC RTC
 	  controller.
@@ -1497,7 +1531,7 @@ config RTC_DRV_LPC24XX
 	  so, the module will be called rtc-lpc24xx.
 
 config RTC_DRV_LPC32XX
-	depends on ARCH_LPC32XX
+	depends on ARCH_LPC32XX || COMPILE_TEST
 	tristate "NXP LPC32XX RTC"
 	help
 	  This enables support for the NXP RTC in the LPC32XX
@@ -1507,7 +1541,7 @@ config RTC_DRV_LPC32XX
 
 config RTC_DRV_PM8XXX
 	tristate "Qualcomm PMIC8XXX RTC"
-	depends on MFD_PM8XXX || MFD_SPMI_PMIC
+	depends on MFD_PM8XXX || MFD_SPMI_PMIC || COMPILE_TEST
 	help
 	  If you say yes here you get support for the
 	  Qualcomm PMIC8XXX RTC.
@@ -1517,7 +1551,7 @@ config RTC_DRV_PM8XXX
 
 config RTC_DRV_TEGRA
 	tristate "NVIDIA Tegra Internal RTC driver"
-	depends on ARCH_TEGRA
+	depends on ARCH_TEGRA || COMPILE_TEST
 	help
 	  If you say yes here you get support for the
 	  Tegra 200 series internal RTC module.
@@ -1603,7 +1637,7 @@ config RTC_DRV_MOXART
 
 config RTC_DRV_MT6397
 	tristate "Mediatek Real Time Clock driver"
-	depends on MFD_MT6397 || COMPILE_TEST
+	depends on MFD_MT6397 || (COMPILE_TEST && IRQ_DOMAIN)
 	help
 	  This selects the Mediatek(R) RTC driver. RTC is part of Mediatek
 	  MT6397 PMIC. You should enable MT6397 PMIC MFD before select
@@ -1622,6 +1656,16 @@ config RTC_DRV_XGENE
 	  This driver can also be built as a module, if so, the module
 	  will be called "rtc-xgene".
 
+config RTC_DRV_PIC32
+	tristate "Microchip PIC32 RTC"
+	depends on MACH_PIC32
+	default y
+	help
+	   If you say yes here you get support for the PIC32 RTC module.
+
+	   This driver can also be built as a module. If so, the module
+	   will be called rtc-pic32
+
 comment "HID Sensor RTC drivers"
 
 config RTC_DRV_HID_SENSOR_TIME
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index 62d61b26ca7e..ea2833723fa9 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_RTC_DRV_ABB5ZES3)	+= rtc-ab-b5ze-s3.o
 obj-$(CONFIG_RTC_DRV_ABX80X)	+= rtc-abx80x.o
 obj-$(CONFIG_RTC_DRV_ARMADA38X)	+= rtc-armada38x.o
 obj-$(CONFIG_RTC_DRV_AS3722)	+= rtc-as3722.o
+obj-$(CONFIG_RTC_DRV_ASM9260)	+= rtc-asm9260.o
 obj-$(CONFIG_RTC_DRV_AT32AP700X)+= rtc-at32ap700x.o
 obj-$(CONFIG_RTC_DRV_AT91RM9200)+= rtc-at91rm9200.o
 obj-$(CONFIG_RTC_DRV_AT91SAM9)	+= rtc-at91sam9.o
@@ -59,7 +60,6 @@ obj-$(CONFIG_RTC_DRV_DS1685_FAMILY)	+= rtc-ds1685.o
 obj-$(CONFIG_RTC_DRV_DS1742)	+= rtc-ds1742.o
 obj-$(CONFIG_RTC_DRV_DS2404)	+= rtc-ds2404.o
 obj-$(CONFIG_RTC_DRV_DS3232)	+= rtc-ds3232.o
-obj-$(CONFIG_RTC_DRV_DS3234)	+= rtc-ds3234.o
 obj-$(CONFIG_RTC_DRV_EFI)	+= rtc-efi.o
 obj-$(CONFIG_RTC_DRV_EM3027)	+= rtc-em3027.o
 obj-$(CONFIG_RTC_DRV_EP93XX)	+= rtc-ep93xx.o
@@ -86,7 +86,6 @@ obj-$(CONFIG_RTC_DRV_M48T86)	+= rtc-m48t86.o
 obj-$(CONFIG_RTC_DRV_MAX6900)	+= rtc-max6900.o
 obj-$(CONFIG_RTC_DRV_MAX6902)	+= rtc-max6902.o
 obj-$(CONFIG_RTC_DRV_MAX77686)	+= rtc-max77686.o
-obj-$(CONFIG_RTC_DRV_MAX77802)	+= rtc-max77802.o
 obj-$(CONFIG_RTC_DRV_MAX8907)	+= rtc-max8907.o
 obj-$(CONFIG_RTC_DRV_MAX8925)	+= rtc-max8925.o
 obj-$(CONFIG_RTC_DRV_MAX8997)	+= rtc-max8997.o
@@ -112,6 +111,7 @@ obj-$(CONFIG_RTC_DRV_PCF85063)	+= rtc-pcf85063.o
 obj-$(CONFIG_RTC_DRV_PCF8523)	+= rtc-pcf8523.o
 obj-$(CONFIG_RTC_DRV_PCF8563)	+= rtc-pcf8563.o
 obj-$(CONFIG_RTC_DRV_PCF8583)	+= rtc-pcf8583.o
+obj-$(CONFIG_RTC_DRV_PIC32)	+= rtc-pic32.o
 obj-$(CONFIG_RTC_DRV_PL030)	+= rtc-pl030.o
 obj-$(CONFIG_RTC_DRV_PL031)	+= rtc-pl031.o
 obj-$(CONFIG_RTC_DRV_PM8XXX)	+= rtc-pm8xxx.o
@@ -128,6 +128,7 @@ obj-$(CONFIG_RTC_DRV_RS5C372)	+= rtc-rs5c372.o
 obj-$(CONFIG_RTC_DRV_RV3029C2)	+= rtc-rv3029c2.o
 obj-$(CONFIG_RTC_DRV_RV8803)	+= rtc-rv8803.o
 obj-$(CONFIG_RTC_DRV_RX4581)	+= rtc-rx4581.o
+obj-$(CONFIG_RTC_DRV_RX6110)	+= rtc-rx6110.o
 obj-$(CONFIG_RTC_DRV_RX8010)	+= rtc-rx8010.o
 obj-$(CONFIG_RTC_DRV_RX8025)	+= rtc-rx8025.o
 obj-$(CONFIG_RTC_DRV_RX8581)	+= rtc-rx8581.o
diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index de86578bcd6d..74fd9746aeca 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -361,17 +361,4 @@ static int __init rtc_init(void)
 	rtc_dev_init();
 	return 0;
 }
-
-static void __exit rtc_exit(void)
-{
-	rtc_dev_exit();
-	class_destroy(rtc_class);
-	ida_destroy(&rtc_ida);
-}
-
 subsys_initcall(rtc_init);
-module_exit(rtc_exit);
-
-MODULE_AUTHOR("Alessandro Zummo <a.zummo@towertech.it>");
-MODULE_DESCRIPTION("RTC class support");
-MODULE_LICENSE("GPL");
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index 5836751b8203..9ef5f6f89f98 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -939,4 +939,58 @@ void rtc_timer_cancel(struct rtc_device *rtc, struct rtc_timer *timer)
 	mutex_unlock(&rtc->ops_lock);
 }
 
+/**
+ * rtc_read_offset - Read the amount of rtc offset in parts per billion
+ * @ rtc: rtc device to be used
+ * @ offset: the offset in parts per billion
+ *
+ * see below for details.
+ *
+ * Kernel interface to read rtc clock offset
+ * Returns 0 on success, or a negative number on error.
+ * If read_offset() is not implemented for the rtc, return -EINVAL
+ */
+int rtc_read_offset(struct rtc_device *rtc, long *offset)
+{
+	int ret;
+
+	if (!rtc->ops)
+		return -ENODEV;
+
+	if (!rtc->ops->read_offset)
+		return -EINVAL;
+
+	mutex_lock(&rtc->ops_lock);
+	ret = rtc->ops->read_offset(rtc->dev.parent, offset);
+	mutex_unlock(&rtc->ops_lock);
+	return ret;
+}
 
+/**
+ * rtc_set_offset - Adjusts the duration of the average second
+ * @ rtc: rtc device to be used
+ * @ offset: the offset in parts per billion
+ *
+ * Some rtc's allow an adjustment to the average duration of a second
+ * to compensate for differences in the actual clock rate due to temperature,
+ * the crystal, capacitor, etc.
+ *
+ * Kernel interface to adjust an rtc clock offset.
+ * Return 0 on success, or a negative number on error.
+ * If the rtc offset is not setable (or not implemented), return -EINVAL
+ */
+int rtc_set_offset(struct rtc_device *rtc, long offset)
+{
+	int ret;
+
+	if (!rtc->ops)
+		return -ENODEV;
+
+	if (!rtc->ops->set_offset)
+		return -EINVAL;
+
+	mutex_lock(&rtc->ops_lock);
+	ret = rtc->ops->set_offset(rtc->dev.parent, offset);
+	mutex_unlock(&rtc->ops_lock);
+	return ret;
+}
diff --git a/drivers/rtc/rtc-as3722.c b/drivers/rtc/rtc-as3722.c
index 56cc5821118b..6ef0c887e6ca 100644
--- a/drivers/rtc/rtc-as3722.c
+++ b/drivers/rtc/rtc-as3722.c
@@ -210,7 +210,7 @@ static int as3722_rtc_probe(struct platform_device *pdev)
 	dev_info(&pdev->dev, "RTC interrupt %d\n", as3722_rtc->alarm_irq);
 
 	ret = devm_request_threaded_irq(&pdev->dev, as3722_rtc->alarm_irq, NULL,
-			as3722_alarm_irq, IRQF_ONESHOT | IRQF_EARLY_RESUME,
+			as3722_alarm_irq, IRQF_ONESHOT,
 			"rtc-alarm", as3722_rtc);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Failed to request alarm IRQ %d: %d\n",
diff --git a/drivers/rtc/rtc-asm9260.c b/drivers/rtc/rtc-asm9260.c
new file mode 100644
index 000000000000..14e08c4c1a01
--- /dev/null
+++ b/drivers/rtc/rtc-asm9260.c
@@ -0,0 +1,355 @@
+/*
+ * Copyright (C) 2016 Oleksij Rempel <linux@rempel-privat.de>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License,
+ * or (at your option) any later version.
+ */
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/rtc.h>
+
+/* Miscellaneous registers */
+/* Interrupt Location Register */
+#define HW_ILR			0x00
+#define BM_RTCALF		BIT(1)
+#define BM_RTCCIF		BIT(0)
+
+/* Clock Control Register */
+#define HW_CCR			0x08
+/* Calibration counter disable */
+#define BM_CCALOFF		BIT(4)
+/* Reset internal oscillator divider */
+#define BM_CTCRST		BIT(1)
+/* Clock Enable */
+#define BM_CLKEN		BIT(0)
+
+/* Counter Increment Interrupt Register */
+#define HW_CIIR			0x0C
+#define BM_CIIR_IMYEAR		BIT(7)
+#define BM_CIIR_IMMON		BIT(6)
+#define BM_CIIR_IMDOY		BIT(5)
+#define BM_CIIR_IMDOW		BIT(4)
+#define BM_CIIR_IMDOM		BIT(3)
+#define BM_CIIR_IMHOUR		BIT(2)
+#define BM_CIIR_IMMIN		BIT(1)
+#define BM_CIIR_IMSEC		BIT(0)
+
+/* Alarm Mask Register */
+#define HW_AMR			0x10
+#define BM_AMR_IMYEAR		BIT(7)
+#define BM_AMR_IMMON		BIT(6)
+#define BM_AMR_IMDOY		BIT(5)
+#define BM_AMR_IMDOW		BIT(4)
+#define BM_AMR_IMDOM		BIT(3)
+#define BM_AMR_IMHOUR		BIT(2)
+#define BM_AMR_IMMIN		BIT(1)
+#define BM_AMR_IMSEC		BIT(0)
+#define BM_AMR_OFF		0xff
+
+/* Consolidated time registers */
+#define HW_CTIME0		0x14
+#define BM_CTIME0_DOW_S		24
+#define BM_CTIME0_DOW_M		0x7
+#define BM_CTIME0_HOUR_S	16
+#define BM_CTIME0_HOUR_M	0x1f
+#define BM_CTIME0_MIN_S		8
+#define BM_CTIME0_MIN_M		0x3f
+#define BM_CTIME0_SEC_S		0
+#define BM_CTIME0_SEC_M		0x3f
+
+#define HW_CTIME1		0x18
+#define BM_CTIME1_YEAR_S	16
+#define BM_CTIME1_YEAR_M	0xfff
+#define BM_CTIME1_MON_S		8
+#define BM_CTIME1_MON_M		0xf
+#define BM_CTIME1_DOM_S		0
+#define BM_CTIME1_DOM_M		0x1f
+
+#define HW_CTIME2		0x1C
+#define BM_CTIME2_DOY_S		0
+#define BM_CTIME2_DOY_M		0xfff
+
+/* Time counter registers */
+#define HW_SEC			0x20
+#define HW_MIN			0x24
+#define HW_HOUR			0x28
+#define HW_DOM			0x2C
+#define HW_DOW			0x30
+#define HW_DOY			0x34
+#define HW_MONTH		0x38
+#define HW_YEAR			0x3C
+
+#define HW_CALIBRATION		0x40
+#define BM_CALDIR_BACK		BIT(17)
+#define BM_CALVAL_M		0x1ffff
+
+/* General purpose registers */
+#define HW_GPREG0		0x44
+#define HW_GPREG1		0x48
+#define HW_GPREG2		0x4C
+#define HW_GPREG3		0x50
+#define HW_GPREG4		0x54
+
+/* Alarm register group */
+#define HW_ALSEC		0x60
+#define HW_ALMIN		0x64
+#define HW_ALHOUR		0x68
+#define HW_ALDOM		0x6C
+#define HW_ALDOW		0x70
+#define HW_ALDOY		0x74
+#define HW_ALMON		0x78
+#define HW_ALYEAR		0x7C
+
+struct asm9260_rtc_priv {
+	struct device		*dev;
+	void __iomem		*iobase;
+	struct rtc_device	*rtc;
+	struct clk		*clk;
+	/* io lock */
+	spinlock_t		lock;
+};
+
+static irqreturn_t asm9260_rtc_irq(int irq, void *dev_id)
+{
+	struct asm9260_rtc_priv *priv = dev_id;
+	u32 isr;
+	unsigned long events = 0;
+
+	isr = ioread32(priv->iobase + HW_CIIR);
+	if (!isr)
+		return IRQ_NONE;
+
+	iowrite32(0, priv->iobase + HW_CIIR);
+
+	events |= RTC_AF | RTC_IRQF;
+
+	rtc_update_irq(priv->rtc, 1, events);
+
+	return IRQ_HANDLED;
+}
+
+static int asm9260_rtc_read_time(struct device *dev, struct rtc_time *tm)
+{
+	struct asm9260_rtc_priv *priv = dev_get_drvdata(dev);
+	u32 ctime0, ctime1, ctime2;
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(&priv->lock, irq_flags);
+	ctime0 = ioread32(priv->iobase + HW_CTIME0);
+	ctime1 = ioread32(priv->iobase + HW_CTIME1);
+	ctime2 = ioread32(priv->iobase + HW_CTIME2);
+
+	if (ctime1 != ioread32(priv->iobase + HW_CTIME1)) {
+		/*
+		 * woops, counter flipped right now. Now we are safe
+		 * to reread.
+		 */
+		ctime0 = ioread32(priv->iobase + HW_CTIME0);
+		ctime1 = ioread32(priv->iobase + HW_CTIME1);
+		ctime2 = ioread32(priv->iobase + HW_CTIME2);
+	}
+	spin_unlock_irqrestore(&priv->lock, irq_flags);
+
+	tm->tm_sec  = (ctime0 >> BM_CTIME0_SEC_S)  & BM_CTIME0_SEC_M;
+	tm->tm_min  = (ctime0 >> BM_CTIME0_MIN_S)  & BM_CTIME0_MIN_M;
+	tm->tm_hour = (ctime0 >> BM_CTIME0_HOUR_S) & BM_CTIME0_HOUR_M;
+	tm->tm_wday = (ctime0 >> BM_CTIME0_DOW_S)  & BM_CTIME0_DOW_M;
+
+	tm->tm_mday = (ctime1 >> BM_CTIME1_DOM_S)  & BM_CTIME1_DOM_M;
+	tm->tm_mon  = (ctime1 >> BM_CTIME1_MON_S)  & BM_CTIME1_MON_M;
+	tm->tm_year = (ctime1 >> BM_CTIME1_YEAR_S) & BM_CTIME1_YEAR_M;
+
+	tm->tm_yday = (ctime2 >> BM_CTIME2_DOY_S)  & BM_CTIME2_DOY_M;
+
+	return 0;
+}
+
+static int asm9260_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+	struct asm9260_rtc_priv *priv = dev_get_drvdata(dev);
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(&priv->lock, irq_flags);
+	/*
+	 * make sure SEC counter will not flip other counter on write time,
+	 * real value will be written at the enf of sequence.
+	 */
+	iowrite32(0, priv->iobase + HW_SEC);
+
+	iowrite32(tm->tm_year, priv->iobase + HW_YEAR);
+	iowrite32(tm->tm_mon,  priv->iobase + HW_MONTH);
+	iowrite32(tm->tm_mday, priv->iobase + HW_DOM);
+	iowrite32(tm->tm_wday, priv->iobase + HW_DOW);
+	iowrite32(tm->tm_yday, priv->iobase + HW_DOY);
+	iowrite32(tm->tm_hour, priv->iobase + HW_HOUR);
+	iowrite32(tm->tm_min,  priv->iobase + HW_MIN);
+	iowrite32(tm->tm_sec,  priv->iobase + HW_SEC);
+	spin_unlock_irqrestore(&priv->lock, irq_flags);
+
+	return 0;
+}
+
+static int asm9260_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct asm9260_rtc_priv *priv = dev_get_drvdata(dev);
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(&priv->lock, irq_flags);
+	alrm->time.tm_year = ioread32(priv->iobase + HW_ALYEAR);
+	alrm->time.tm_mon  = ioread32(priv->iobase + HW_ALMON);
+	alrm->time.tm_mday = ioread32(priv->iobase + HW_ALDOM);
+	alrm->time.tm_wday = ioread32(priv->iobase + HW_ALDOW);
+	alrm->time.tm_yday = ioread32(priv->iobase + HW_ALDOY);
+	alrm->time.tm_hour = ioread32(priv->iobase + HW_ALHOUR);
+	alrm->time.tm_min  = ioread32(priv->iobase + HW_ALMIN);
+	alrm->time.tm_sec  = ioread32(priv->iobase + HW_ALSEC);
+
+	alrm->enabled = ioread32(priv->iobase + HW_AMR) ? 1 : 0;
+	alrm->pending = ioread32(priv->iobase + HW_CIIR) ? 1 : 0;
+	spin_unlock_irqrestore(&priv->lock, irq_flags);
+
+	return rtc_valid_tm(&alrm->time);
+}
+
+static int asm9260_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct asm9260_rtc_priv *priv = dev_get_drvdata(dev);
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(&priv->lock, irq_flags);
+	iowrite32(alrm->time.tm_year, priv->iobase + HW_ALYEAR);
+	iowrite32(alrm->time.tm_mon,  priv->iobase + HW_ALMON);
+	iowrite32(alrm->time.tm_mday, priv->iobase + HW_ALDOM);
+	iowrite32(alrm->time.tm_wday, priv->iobase + HW_ALDOW);
+	iowrite32(alrm->time.tm_yday, priv->iobase + HW_ALDOY);
+	iowrite32(alrm->time.tm_hour, priv->iobase + HW_ALHOUR);
+	iowrite32(alrm->time.tm_min,  priv->iobase + HW_ALMIN);
+	iowrite32(alrm->time.tm_sec,  priv->iobase + HW_ALSEC);
+
+	iowrite32(alrm->enabled ? 0 : BM_AMR_OFF, priv->iobase + HW_AMR);
+	spin_unlock_irqrestore(&priv->lock, irq_flags);
+
+	return 0;
+}
+
+static int asm9260_alarm_irq_enable(struct device *dev, unsigned int enabled)
+{
+	struct asm9260_rtc_priv *priv = dev_get_drvdata(dev);
+
+	iowrite32(enabled ? 0 : BM_AMR_OFF, priv->iobase + HW_AMR);
+	return 0;
+}
+
+static const struct rtc_class_ops asm9260_rtc_ops = {
+	.read_time		= asm9260_rtc_read_time,
+	.set_time		= asm9260_rtc_set_time,
+	.read_alarm		= asm9260_rtc_read_alarm,
+	.set_alarm		= asm9260_rtc_set_alarm,
+	.alarm_irq_enable	= asm9260_alarm_irq_enable,
+};
+
+static int __init asm9260_rtc_probe(struct platform_device *pdev)
+{
+	struct asm9260_rtc_priv *priv;
+	struct device *dev = &pdev->dev;
+	struct resource	*res;
+	int irq_alarm, ret;
+	u32 ccr;
+
+	priv = devm_kzalloc(dev, sizeof(struct asm9260_rtc_priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->dev = &pdev->dev;
+	platform_set_drvdata(pdev, priv);
+
+	irq_alarm = platform_get_irq(pdev, 0);
+	if (irq_alarm < 0) {
+		dev_err(dev, "No alarm IRQ resource defined\n");
+		return irq_alarm;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->iobase = devm_ioremap_resource(dev, res);
+	if (IS_ERR(priv->iobase))
+		return PTR_ERR(priv->iobase);
+
+	priv->clk = devm_clk_get(dev, "ahb");
+	ret = clk_prepare_enable(priv->clk);
+	if (ret) {
+		dev_err(dev, "Failed to enable clk!\n");
+		return ret;
+	}
+
+	ccr = ioread32(priv->iobase + HW_CCR);
+	/* if dev is not enabled, reset it */
+	if ((ccr & (BM_CLKEN | BM_CTCRST)) != BM_CLKEN) {
+		iowrite32(BM_CTCRST, priv->iobase + HW_CCR);
+		ccr = 0;
+	}
+
+	iowrite32(BM_CLKEN | ccr, priv->iobase + HW_CCR);
+	iowrite32(0, priv->iobase + HW_CIIR);
+	iowrite32(BM_AMR_OFF, priv->iobase + HW_AMR);
+
+	priv->rtc = devm_rtc_device_register(dev, dev_name(dev),
+					     &asm9260_rtc_ops, THIS_MODULE);
+	if (IS_ERR(priv->rtc)) {
+		ret = PTR_ERR(priv->rtc);
+		dev_err(dev, "Failed to register RTC device: %d\n", ret);
+		goto err_return;
+	}
+
+	ret = devm_request_threaded_irq(dev, irq_alarm, NULL,
+					asm9260_rtc_irq, IRQF_ONESHOT,
+					dev_name(dev), priv);
+	if (ret < 0) {
+		dev_err(dev, "can't get irq %i, err %d\n",
+			irq_alarm, ret);
+		goto err_return;
+	}
+
+	return 0;
+
+err_return:
+	clk_disable_unprepare(priv->clk);
+	return ret;
+}
+
+static int __exit asm9260_rtc_remove(struct platform_device *pdev)
+{
+	struct asm9260_rtc_priv *priv = platform_get_drvdata(pdev);
+
+	/* Disable alarm matching */
+	iowrite32(BM_AMR_OFF, priv->iobase + HW_AMR);
+	clk_disable_unprepare(priv->clk);
+	return 0;
+}
+
+static const struct of_device_id asm9260_dt_ids[] = {
+	{ .compatible = "alphascale,asm9260-rtc", },
+	{}
+};
+
+static struct platform_driver asm9260_rtc_driver = {
+	.probe		= asm9260_rtc_probe,
+	.remove		= asm9260_rtc_remove,
+	.driver		= {
+		.name	= "asm9260-rtc",
+		.owner	= THIS_MODULE,
+		.of_match_table = asm9260_dt_ids,
+	},
+};
+
+module_platform_driver(asm9260_rtc_driver);
+
+MODULE_AUTHOR("Oleksij Rempel <linux@rempel-privat.de>");
+MODULE_DESCRIPTION("Alphascale asm9260 SoC Realtime Clock Driver (RTC)");
+MODULE_LICENSE("GPL");
diff --git a/drivers/rtc/rtc-ds1305.c b/drivers/rtc/rtc-ds1305.c
index f39691eea736..8e41c4613e51 100644
--- a/drivers/rtc/rtc-ds1305.c
+++ b/drivers/rtc/rtc-ds1305.c
@@ -532,7 +532,7 @@ ds1305_nvram_read(struct file *filp, struct kobject *kobj,
 	struct spi_transfer	x[2];
 	int			status;
 
-	spi = container_of(kobj, struct spi_device, dev.kobj);
+	spi = to_spi_device(kobj_to_dev(kobj));
 
 	addr = DS1305_NVRAM + off;
 	msg_init(&m, x, &addr, count, NULL, buf);
@@ -554,7 +554,7 @@ ds1305_nvram_write(struct file *filp, struct kobject *kobj,
 	struct spi_transfer	x[2];
 	int			status;
 
-	spi = container_of(kobj, struct spi_device, dev.kobj);
+	spi = to_spi_device(kobj_to_dev(kobj));
 
 	addr = (DS1305_WRITE | DS1305_NVRAM) + off;
 	msg_init(&m, x, &addr, count, buf, NULL);
diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c
index cf685f67b391..b2156ee5bae1 100644
--- a/drivers/rtc/rtc-ds1307.c
+++ b/drivers/rtc/rtc-ds1307.c
@@ -19,6 +19,9 @@
 #include <linux/rtc.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/clk-provider.h>
 
 /*
  * We can't determine type by probing, but if we expect pre-Linux code
@@ -89,6 +92,7 @@ enum ds_type {
 #	define DS1340_BIT_OSF		0x80
 #define DS1337_REG_STATUS	0x0f
 #	define DS1337_BIT_OSF		0x80
+#	define DS3231_BIT_EN32KHZ	0x08
 #	define DS1337_BIT_A2I		0x02
 #	define DS1337_BIT_A1I		0x01
 #define DS1339_REG_ALARM1_SECS	0x07
@@ -118,6 +122,9 @@ struct ds1307 {
 			       u8 length, u8 *values);
 	s32 (*write_block_data)(const struct i2c_client *client, u8 command,
 				u8 length, const u8 *values);
+#ifdef CONFIG_COMMON_CLK
+	struct clk_hw		clks[2];
+#endif
 };
 
 struct chip_desc {
@@ -842,6 +849,378 @@ out:
 	return;
 }
 
+/*----------------------------------------------------------------------*/
+
+#ifdef CONFIG_RTC_DRV_DS1307_HWMON
+
+/*
+ * Temperature sensor support for ds3231 devices.
+ */
+
+#define DS3231_REG_TEMPERATURE	0x11
+
+/*
+ * A user-initiated temperature conversion is not started by this function,
+ * so the temperature is updated once every 64 seconds.
+ */
+static int ds3231_hwmon_read_temp(struct device *dev, s16 *mC)
+{
+	struct ds1307 *ds1307 = dev_get_drvdata(dev);
+	u8 temp_buf[2];
+	s16 temp;
+	int ret;
+
+	ret = ds1307->read_block_data(ds1307->client, DS3231_REG_TEMPERATURE,
+					sizeof(temp_buf), temp_buf);
+	if (ret < 0)
+		return ret;
+	if (ret != sizeof(temp_buf))
+		return -EIO;
+
+	/*
+	 * Temperature is represented as a 10-bit code with a resolution of
+	 * 0.25 degree celsius and encoded in two's complement format.
+	 */
+	temp = (temp_buf[0] << 8) | temp_buf[1];
+	temp >>= 6;
+	*mC = temp * 250;
+
+	return 0;
+}
+
+static ssize_t ds3231_hwmon_show_temp(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	int ret;
+	s16 temp;
+
+	ret = ds3231_hwmon_read_temp(dev, &temp);
+	if (ret)
+		return ret;
+
+	return sprintf(buf, "%d\n", temp);
+}
+static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, ds3231_hwmon_show_temp,
+			NULL, 0);
+
+static struct attribute *ds3231_hwmon_attrs[] = {
+	&sensor_dev_attr_temp1_input.dev_attr.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(ds3231_hwmon);
+
+static void ds1307_hwmon_register(struct ds1307 *ds1307)
+{
+	struct device *dev;
+
+	if (ds1307->type != ds_3231)
+		return;
+
+	dev = devm_hwmon_device_register_with_groups(&ds1307->client->dev,
+						ds1307->client->name,
+						ds1307, ds3231_hwmon_groups);
+	if (IS_ERR(dev)) {
+		dev_warn(&ds1307->client->dev,
+			"unable to register hwmon device %ld\n", PTR_ERR(dev));
+	}
+}
+
+#else
+
+static void ds1307_hwmon_register(struct ds1307 *ds1307)
+{
+}
+
+#endif /* CONFIG_RTC_DRV_DS1307_HWMON */
+
+/*----------------------------------------------------------------------*/
+
+/*
+ * Square-wave output support for DS3231
+ * Datasheet: https://datasheets.maximintegrated.com/en/ds/DS3231.pdf
+ */
+#ifdef CONFIG_COMMON_CLK
+
+enum {
+	DS3231_CLK_SQW = 0,
+	DS3231_CLK_32KHZ,
+};
+
+#define clk_sqw_to_ds1307(clk)	\
+	container_of(clk, struct ds1307, clks[DS3231_CLK_SQW])
+#define clk_32khz_to_ds1307(clk)	\
+	container_of(clk, struct ds1307, clks[DS3231_CLK_32KHZ])
+
+static int ds3231_clk_sqw_rates[] = {
+	1,
+	1024,
+	4096,
+	8192,
+};
+
+static int ds1337_write_control(struct ds1307 *ds1307, u8 mask, u8 value)
+{
+	struct i2c_client *client = ds1307->client;
+	struct mutex *lock = &ds1307->rtc->ops_lock;
+	int control;
+	int ret;
+
+	mutex_lock(lock);
+
+	control = i2c_smbus_read_byte_data(client, DS1337_REG_CONTROL);
+	if (control < 0) {
+		ret = control;
+		goto out;
+	}
+
+	control &= ~mask;
+	control |= value;
+
+	ret = i2c_smbus_write_byte_data(client, DS1337_REG_CONTROL, control);
+out:
+	mutex_unlock(lock);
+
+	return ret;
+}
+
+static unsigned long ds3231_clk_sqw_recalc_rate(struct clk_hw *hw,
+						unsigned long parent_rate)
+{
+	struct ds1307 *ds1307 = clk_sqw_to_ds1307(hw);
+	int control;
+	int rate_sel = 0;
+
+	control = i2c_smbus_read_byte_data(ds1307->client, DS1337_REG_CONTROL);
+	if (control < 0)
+		return control;
+	if (control & DS1337_BIT_RS1)
+		rate_sel += 1;
+	if (control & DS1337_BIT_RS2)
+		rate_sel += 2;
+
+	return ds3231_clk_sqw_rates[rate_sel];
+}
+
+static long ds3231_clk_sqw_round_rate(struct clk_hw *hw, unsigned long rate,
+					unsigned long *prate)
+{
+	int i;
+
+	for (i = ARRAY_SIZE(ds3231_clk_sqw_rates) - 1; i >= 0; i--) {
+		if (ds3231_clk_sqw_rates[i] <= rate)
+			return ds3231_clk_sqw_rates[i];
+	}
+
+	return 0;
+}
+
+static int ds3231_clk_sqw_set_rate(struct clk_hw *hw, unsigned long rate,
+					unsigned long parent_rate)
+{
+	struct ds1307 *ds1307 = clk_sqw_to_ds1307(hw);
+	int control = 0;
+	int rate_sel;
+
+	for (rate_sel = 0; rate_sel < ARRAY_SIZE(ds3231_clk_sqw_rates);
+			rate_sel++) {
+		if (ds3231_clk_sqw_rates[rate_sel] == rate)
+			break;
+	}
+
+	if (rate_sel == ARRAY_SIZE(ds3231_clk_sqw_rates))
+		return -EINVAL;
+
+	if (rate_sel & 1)
+		control |= DS1337_BIT_RS1;
+	if (rate_sel & 2)
+		control |= DS1337_BIT_RS2;
+
+	return ds1337_write_control(ds1307, DS1337_BIT_RS1 | DS1337_BIT_RS2,
+				control);
+}
+
+static int ds3231_clk_sqw_prepare(struct clk_hw *hw)
+{
+	struct ds1307 *ds1307 = clk_sqw_to_ds1307(hw);
+
+	return ds1337_write_control(ds1307, DS1337_BIT_INTCN, 0);
+}
+
+static void ds3231_clk_sqw_unprepare(struct clk_hw *hw)
+{
+	struct ds1307 *ds1307 = clk_sqw_to_ds1307(hw);
+
+	ds1337_write_control(ds1307, DS1337_BIT_INTCN, DS1337_BIT_INTCN);
+}
+
+static int ds3231_clk_sqw_is_prepared(struct clk_hw *hw)
+{
+	struct ds1307 *ds1307 = clk_sqw_to_ds1307(hw);
+	int control;
+
+	control = i2c_smbus_read_byte_data(ds1307->client, DS1337_REG_CONTROL);
+	if (control < 0)
+		return control;
+
+	return !(control & DS1337_BIT_INTCN);
+}
+
+static const struct clk_ops ds3231_clk_sqw_ops = {
+	.prepare = ds3231_clk_sqw_prepare,
+	.unprepare = ds3231_clk_sqw_unprepare,
+	.is_prepared = ds3231_clk_sqw_is_prepared,
+	.recalc_rate = ds3231_clk_sqw_recalc_rate,
+	.round_rate = ds3231_clk_sqw_round_rate,
+	.set_rate = ds3231_clk_sqw_set_rate,
+};
+
+static unsigned long ds3231_clk_32khz_recalc_rate(struct clk_hw *hw,
+						unsigned long parent_rate)
+{
+	return 32768;
+}
+
+static int ds3231_clk_32khz_control(struct ds1307 *ds1307, bool enable)
+{
+	struct i2c_client *client = ds1307->client;
+	struct mutex *lock = &ds1307->rtc->ops_lock;
+	int status;
+	int ret;
+
+	mutex_lock(lock);
+
+	status = i2c_smbus_read_byte_data(client, DS1337_REG_STATUS);
+	if (status < 0) {
+		ret = status;
+		goto out;
+	}
+
+	if (enable)
+		status |= DS3231_BIT_EN32KHZ;
+	else
+		status &= ~DS3231_BIT_EN32KHZ;
+
+	ret = i2c_smbus_write_byte_data(client, DS1337_REG_STATUS, status);
+out:
+	mutex_unlock(lock);
+
+	return ret;
+}
+
+static int ds3231_clk_32khz_prepare(struct clk_hw *hw)
+{
+	struct ds1307 *ds1307 = clk_32khz_to_ds1307(hw);
+
+	return ds3231_clk_32khz_control(ds1307, true);
+}
+
+static void ds3231_clk_32khz_unprepare(struct clk_hw *hw)
+{
+	struct ds1307 *ds1307 = clk_32khz_to_ds1307(hw);
+
+	ds3231_clk_32khz_control(ds1307, false);
+}
+
+static int ds3231_clk_32khz_is_prepared(struct clk_hw *hw)
+{
+	struct ds1307 *ds1307 = clk_32khz_to_ds1307(hw);
+	int status;
+
+	status = i2c_smbus_read_byte_data(ds1307->client, DS1337_REG_STATUS);
+	if (status < 0)
+		return status;
+
+	return !!(status & DS3231_BIT_EN32KHZ);
+}
+
+static const struct clk_ops ds3231_clk_32khz_ops = {
+	.prepare = ds3231_clk_32khz_prepare,
+	.unprepare = ds3231_clk_32khz_unprepare,
+	.is_prepared = ds3231_clk_32khz_is_prepared,
+	.recalc_rate = ds3231_clk_32khz_recalc_rate,
+};
+
+static struct clk_init_data ds3231_clks_init[] = {
+	[DS3231_CLK_SQW] = {
+		.name = "ds3231_clk_sqw",
+		.ops = &ds3231_clk_sqw_ops,
+		.flags = CLK_IS_ROOT,
+	},
+	[DS3231_CLK_32KHZ] = {
+		.name = "ds3231_clk_32khz",
+		.ops = &ds3231_clk_32khz_ops,
+		.flags = CLK_IS_ROOT,
+	},
+};
+
+static int ds3231_clks_register(struct ds1307 *ds1307)
+{
+	struct i2c_client *client = ds1307->client;
+	struct device_node *node = client->dev.of_node;
+	struct clk_onecell_data	*onecell;
+	int i;
+
+	onecell = devm_kzalloc(&client->dev, sizeof(*onecell), GFP_KERNEL);
+	if (!onecell)
+		return -ENOMEM;
+
+	onecell->clk_num = ARRAY_SIZE(ds3231_clks_init);
+	onecell->clks = devm_kcalloc(&client->dev, onecell->clk_num,
+					sizeof(onecell->clks[0]), GFP_KERNEL);
+	if (!onecell->clks)
+		return -ENOMEM;
+
+	for (i = 0; i < ARRAY_SIZE(ds3231_clks_init); i++) {
+		struct clk_init_data init = ds3231_clks_init[i];
+
+		/*
+		 * Interrupt signal due to alarm conditions and square-wave
+		 * output share same pin, so don't initialize both.
+		 */
+		if (i == DS3231_CLK_SQW && test_bit(HAS_ALARM, &ds1307->flags))
+			continue;
+
+		/* optional override of the clockname */
+		of_property_read_string_index(node, "clock-output-names", i,
+						&init.name);
+		ds1307->clks[i].init = &init;
+
+		onecell->clks[i] = devm_clk_register(&client->dev,
+							&ds1307->clks[i]);
+		if (IS_ERR(onecell->clks[i]))
+			return PTR_ERR(onecell->clks[i]);
+	}
+
+	if (!node)
+		return 0;
+
+	of_clk_add_provider(node, of_clk_src_onecell_get, onecell);
+
+	return 0;
+}
+
+static void ds1307_clks_register(struct ds1307 *ds1307)
+{
+	int ret;
+
+	if (ds1307->type != ds_3231)
+		return;
+
+	ret = ds3231_clks_register(ds1307);
+	if (ret) {
+		dev_warn(&ds1307->client->dev,
+			"unable to register clock device %d\n", ret);
+	}
+}
+
+#else
+
+static void ds1307_clks_register(struct ds1307 *ds1307)
+{
+}
+
+#endif /* CONFIG_COMMON_CLK */
+
 static int ds1307_probe(struct i2c_client *client,
 			const struct i2c_device_id *id)
 {
@@ -851,6 +1230,7 @@ static int ds1307_probe(struct i2c_client *client,
 	struct chip_desc	*chip = &chips[id->driver_data];
 	struct i2c_adapter	*adapter = to_i2c_adapter(client->dev.parent);
 	bool			want_irq = false;
+	bool			ds1307_can_wakeup_device = false;
 	unsigned char		*buf;
 	struct ds1307_platform_data *pdata = dev_get_platdata(&client->dev);
 	irq_handler_t	irq_handler = ds1307_irq;
@@ -898,6 +1278,20 @@ static int ds1307_probe(struct i2c_client *client,
 		ds1307->write_block_data = ds1307_write_block_data;
 	}
 
+#ifdef CONFIG_OF
+/*
+ * For devices with no IRQ directly connected to the SoC, the RTC chip
+ * can be forced as a wakeup source by stating that explicitly in
+ * the device's .dts file using the "wakeup-source" boolean property.
+ * If the "wakeup-source" property is set, don't request an IRQ.
+ * This will guarantee the 'wakealarm' sysfs entry is available on the device,
+ * if supported by the RTC.
+ */
+	if (of_property_read_bool(client->dev.of_node, "wakeup-source")) {
+		ds1307_can_wakeup_device = true;
+	}
+#endif
+
 	switch (ds1307->type) {
 	case ds_1337:
 	case ds_1339:
@@ -916,11 +1310,13 @@ static int ds1307_probe(struct i2c_client *client,
 			ds1307->regs[0] &= ~DS1337_BIT_nEOSC;
 
 		/*
-		 * Using IRQ?  Disable the square wave and both alarms.
+		 * Using IRQ or defined as wakeup-source?
+		 * Disable the square wave and both alarms.
 		 * For some variants, be sure alarms can trigger when we're
 		 * running on Vbackup (BBSQI/BBSQW)
 		 */
-		if (ds1307->client->irq > 0 && chip->alarm) {
+		if (chip->alarm && (ds1307->client->irq > 0 ||
+						ds1307_can_wakeup_device)) {
 			ds1307->regs[0] |= DS1337_BIT_INTCN
 					| bbsqi_bitpos[ds1307->type];
 			ds1307->regs[0] &= ~(DS1337_BIT_A2IE | DS1337_BIT_A1IE);
@@ -1135,6 +1531,14 @@ read_rtc:
 		return PTR_ERR(ds1307->rtc);
 	}
 
+	if (ds1307_can_wakeup_device) {
+		/* Disable request for an IRQ */
+		want_irq = false;
+		dev_info(&client->dev, "'wakeup-source' is set, request for an IRQ is disabled!\n");
+		/* We cannot support UIE mode if we do not have an IRQ line */
+		ds1307->rtc->uie_unsupported = 1;
+	}
+
 	if (want_irq) {
 		err = devm_request_threaded_irq(&client->dev,
 						client->irq, NULL, irq_handler,
@@ -1182,6 +1586,9 @@ read_rtc:
 		}
 	}
 
+	ds1307_hwmon_register(ds1307);
+	ds1307_clks_register(ds1307);
+
 	return 0;
 
 exit:
diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c
index 535050fc5e9f..1e6cfc84b1f6 100644
--- a/drivers/rtc/rtc-ds1685.c
+++ b/drivers/rtc/rtc-ds1685.c
@@ -187,9 +187,9 @@ ds1685_rtc_end_data_access(struct ds1685_priv *rtc)
  * Only use this where you are certain another lock will not be held.
  */
 static inline void
-ds1685_rtc_begin_ctrl_access(struct ds1685_priv *rtc, unsigned long flags)
+ds1685_rtc_begin_ctrl_access(struct ds1685_priv *rtc, unsigned long *flags)
 {
-	spin_lock_irqsave(&rtc->lock, flags);
+	spin_lock_irqsave(&rtc->lock, *flags);
 	ds1685_rtc_switch_to_bank1(rtc);
 }
 
@@ -1300,7 +1300,7 @@ ds1685_rtc_sysfs_ctrl_regs_store(struct device *dev,
 {
 	struct ds1685_priv *rtc = dev_get_drvdata(dev);
 	u8 reg = 0, bit = 0, tmp;
-	unsigned long flags = 0;
+	unsigned long flags;
 	long int val = 0;
 	const struct ds1685_rtc_ctrl_regs *reg_info =
 		ds1685_rtc_sysfs_ctrl_regs_lookup(attr->attr.name);
@@ -1321,7 +1321,7 @@ ds1685_rtc_sysfs_ctrl_regs_store(struct device *dev,
 	bit = reg_info->bit;
 
 	/* Safe to spinlock during a write. */
-	ds1685_rtc_begin_ctrl_access(rtc, flags);
+	ds1685_rtc_begin_ctrl_access(rtc, &flags);
 	tmp = rtc->read(rtc, reg);
 	rtc->write(rtc, reg, (val ? (tmp | bit) : (tmp & ~(bit))));
 	ds1685_rtc_end_ctrl_access(rtc, flags);
@@ -2161,6 +2161,7 @@ ds1685_rtc_poweroff(struct platform_device *pdev)
 	/* Check for valid RTC data, else, spin forever. */
 	if (unlikely(!pdev)) {
 		pr_emerg("platform device data not available, spinning forever ...\n");
+		while(1);
 		unreachable();
 	} else {
 		/* Get the rtc data. */
diff --git a/drivers/rtc/rtc-ds3232.c b/drivers/rtc/rtc-ds3232.c
index 4e99ace66f74..7edc889729c5 100644
--- a/drivers/rtc/rtc-ds3232.c
+++ b/drivers/rtc/rtc-ds3232.c
@@ -1,19 +1,15 @@
 /*
- * RTC client/driver for the Maxim/Dallas DS3232 Real-Time Clock over I2C
+ * RTC client/driver for the Maxim/Dallas DS3232/DS3234 Real-Time Clock
  *
  * Copyright (C) 2009-2011 Freescale Semiconductor.
  * Author: Jack Lan <jack.lan@freescale.com>
+ * Copyright (C) 2008 MIMOMax Wireless Ltd.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
  * Free Software Foundation;  either version 2 of the  License, or (at your
  * option) any later version.
  */
-/*
- * It would be more efficient to use i2c msgs/i2c_transfer directly but, as
- * recommened in .../Documentation/i2c/writing-clients section
- * "Sending and receiving", using SMBus level communication is preferred.
- */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
@@ -21,10 +17,11 @@
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/i2c.h>
+#include <linux/spi/spi.h>
 #include <linux/rtc.h>
 #include <linux/bcd.h>
-#include <linux/workqueue.h>
 #include <linux/slab.h>
+#include <linux/regmap.h>
 
 #define DS3232_REG_SECONDS	0x00
 #define DS3232_REG_MINUTES	0x01
@@ -50,39 +47,33 @@
 #       define DS3232_REG_SR_A1F   0x01
 
 struct ds3232 {
-	struct i2c_client *client;
+	struct device *dev;
+	struct regmap *regmap;
+	int irq;
 	struct rtc_device *rtc;
-	struct work_struct work;
 
-	/* The mutex protects alarm operations, and prevents a race
-	 * between the enable_irq() in the workqueue and the free_irq()
-	 * in the remove function.
-	 */
-	struct mutex mutex;
 	bool suspended;
-	int exiting;
 };
 
-static struct i2c_driver ds3232_driver;
-
-static int ds3232_check_rtc_status(struct i2c_client *client)
+static int ds3232_check_rtc_status(struct device *dev)
 {
+	struct ds3232 *ds3232 = dev_get_drvdata(dev);
 	int ret = 0;
 	int control, stat;
 
-	stat = i2c_smbus_read_byte_data(client, DS3232_REG_SR);
-	if (stat < 0)
-		return stat;
+	ret = regmap_read(ds3232->regmap, DS3232_REG_SR, &stat);
+	if (ret)
+		return ret;
 
 	if (stat & DS3232_REG_SR_OSF)
-		dev_warn(&client->dev,
+		dev_warn(dev,
 				"oscillator discontinuity flagged, "
 				"time unreliable\n");
 
 	stat &= ~(DS3232_REG_SR_OSF | DS3232_REG_SR_A1F | DS3232_REG_SR_A2F);
 
-	ret = i2c_smbus_write_byte_data(client, DS3232_REG_SR, stat);
-	if (ret < 0)
+	ret = regmap_write(ds3232->regmap, DS3232_REG_SR, stat);
+	if (ret)
 		return ret;
 
 	/* If the alarm is pending, clear it before requesting
@@ -90,31 +81,28 @@ static int ds3232_check_rtc_status(struct i2c_client *client)
 	 * before everything is initialized.
 	 */
 
-	control = i2c_smbus_read_byte_data(client, DS3232_REG_CR);
-	if (control < 0)
-		return control;
+	ret = regmap_read(ds3232->regmap, DS3232_REG_CR, &control);
+	if (ret)
+		return ret;
 
 	control &= ~(DS3232_REG_CR_A1IE | DS3232_REG_CR_A2IE);
 	control |= DS3232_REG_CR_INTCN;
 
-	return i2c_smbus_write_byte_data(client, DS3232_REG_CR, control);
+	return regmap_write(ds3232->regmap, DS3232_REG_CR, control);
 }
 
 static int ds3232_read_time(struct device *dev, struct rtc_time *time)
 {
-	struct i2c_client *client = to_i2c_client(dev);
+	struct ds3232 *ds3232 = dev_get_drvdata(dev);
 	int ret;
 	u8 buf[7];
 	unsigned int year, month, day, hour, minute, second;
 	unsigned int week, twelve_hr, am_pm;
 	unsigned int century, add_century = 0;
 
-	ret = i2c_smbus_read_i2c_block_data(client, DS3232_REG_SECONDS, 7, buf);
-
-	if (ret < 0)
+	ret = regmap_bulk_read(ds3232->regmap, DS3232_REG_SECONDS, buf, 7);
+	if (ret)
 		return ret;
-	if (ret < 7)
-		return -EIO;
 
 	second = buf[0];
 	minute = buf[1];
@@ -159,7 +147,7 @@ static int ds3232_read_time(struct device *dev, struct rtc_time *time)
 
 static int ds3232_set_time(struct device *dev, struct rtc_time *time)
 {
-	struct i2c_client *client = to_i2c_client(dev);
+	struct ds3232 *ds3232 = dev_get_drvdata(dev);
 	u8 buf[7];
 
 	/* Extract time from rtc_time and load into ds3232*/
@@ -179,8 +167,7 @@ static int ds3232_set_time(struct device *dev, struct rtc_time *time)
 		buf[6] = bin2bcd(time->tm_year);
 	}
 
-	return i2c_smbus_write_i2c_block_data(client,
-					      DS3232_REG_SECONDS, 7, buf);
+	return regmap_bulk_write(ds3232->regmap, DS3232_REG_SECONDS, buf, 7);
 }
 
 /*
@@ -190,24 +177,19 @@ static int ds3232_set_time(struct device *dev, struct rtc_time *time)
  */
 static int ds3232_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 {
-	struct i2c_client *client = to_i2c_client(dev);
-	struct ds3232 *ds3232 = i2c_get_clientdata(client);
+	struct ds3232 *ds3232 = dev_get_drvdata(dev);
 	int control, stat;
 	int ret;
 	u8 buf[4];
 
-	mutex_lock(&ds3232->mutex);
-
-	ret = i2c_smbus_read_byte_data(client, DS3232_REG_SR);
-	if (ret < 0)
+	ret = regmap_read(ds3232->regmap, DS3232_REG_SR, &stat);
+	if (ret)
 		goto out;
-	stat = ret;
-	ret = i2c_smbus_read_byte_data(client, DS3232_REG_CR);
-	if (ret < 0)
+	ret = regmap_read(ds3232->regmap, DS3232_REG_CR, &control);
+	if (ret)
 		goto out;
-	control = ret;
-	ret = i2c_smbus_read_i2c_block_data(client, DS3232_REG_ALARM1, 4, buf);
-	if (ret < 0)
+	ret = regmap_bulk_read(ds3232->regmap, DS3232_REG_ALARM1, buf, 4);
+	if (ret)
 		goto out;
 
 	alarm->time.tm_sec = bcd2bin(buf[0] & 0x7F);
@@ -226,7 +208,6 @@ static int ds3232_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 
 	ret = 0;
 out:
-	mutex_unlock(&ds3232->mutex);
 	return ret;
 }
 
@@ -236,166 +217,129 @@ out:
  */
 static int ds3232_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 {
-	struct i2c_client *client = to_i2c_client(dev);
-	struct ds3232 *ds3232 = i2c_get_clientdata(client);
+	struct ds3232 *ds3232 = dev_get_drvdata(dev);
 	int control, stat;
 	int ret;
 	u8 buf[4];
 
-	if (client->irq <= 0)
+	if (ds3232->irq <= 0)
 		return -EINVAL;
 
-	mutex_lock(&ds3232->mutex);
-
 	buf[0] = bin2bcd(alarm->time.tm_sec);
 	buf[1] = bin2bcd(alarm->time.tm_min);
 	buf[2] = bin2bcd(alarm->time.tm_hour);
 	buf[3] = bin2bcd(alarm->time.tm_mday);
 
 	/* clear alarm interrupt enable bit */
-	ret = i2c_smbus_read_byte_data(client, DS3232_REG_CR);
-	if (ret < 0)
+	ret = regmap_read(ds3232->regmap, DS3232_REG_CR, &control);
+	if (ret)
 		goto out;
-	control = ret;
 	control &= ~(DS3232_REG_CR_A1IE | DS3232_REG_CR_A2IE);
-	ret = i2c_smbus_write_byte_data(client, DS3232_REG_CR, control);
-	if (ret < 0)
+	ret = regmap_write(ds3232->regmap, DS3232_REG_CR, control);
+	if (ret)
 		goto out;
 
 	/* clear any pending alarm flag */
-	ret = i2c_smbus_read_byte_data(client, DS3232_REG_SR);
-	if (ret < 0)
+	ret = regmap_read(ds3232->regmap, DS3232_REG_SR, &stat);
+	if (ret)
 		goto out;
-	stat = ret;
 	stat &= ~(DS3232_REG_SR_A1F | DS3232_REG_SR_A2F);
-	ret = i2c_smbus_write_byte_data(client, DS3232_REG_SR, stat);
-	if (ret < 0)
+	ret = regmap_write(ds3232->regmap, DS3232_REG_SR, stat);
+	if (ret)
 		goto out;
 
-	ret = i2c_smbus_write_i2c_block_data(client, DS3232_REG_ALARM1, 4, buf);
+	ret = regmap_bulk_write(ds3232->regmap, DS3232_REG_ALARM1, buf, 4);
+	if (ret)
+		goto out;
 
 	if (alarm->enabled) {
 		control |= DS3232_REG_CR_A1IE;
-		ret = i2c_smbus_write_byte_data(client, DS3232_REG_CR, control);
+		ret = regmap_write(ds3232->regmap, DS3232_REG_CR, control);
 	}
 out:
-	mutex_unlock(&ds3232->mutex);
 	return ret;
 }
 
-static void ds3232_update_alarm(struct i2c_client *client)
+static int ds3232_update_alarm(struct device *dev, unsigned int enabled)
 {
-	struct ds3232 *ds3232 = i2c_get_clientdata(client);
+	struct ds3232 *ds3232 = dev_get_drvdata(dev);
 	int control;
 	int ret;
-	u8 buf[4];
-
-	mutex_lock(&ds3232->mutex);
-
-	ret = i2c_smbus_read_i2c_block_data(client, DS3232_REG_ALARM1, 4, buf);
-	if (ret < 0)
-		goto unlock;
-
-	buf[0] = bcd2bin(buf[0]) < 0 || (ds3232->rtc->irq_data & RTC_UF) ?
-								0x80 : buf[0];
-	buf[1] = bcd2bin(buf[1]) < 0 || (ds3232->rtc->irq_data & RTC_UF) ?
-								0x80 : buf[1];
-	buf[2] = bcd2bin(buf[2]) < 0 || (ds3232->rtc->irq_data & RTC_UF) ?
-								0x80 : buf[2];
-	buf[3] = bcd2bin(buf[3]) < 0 || (ds3232->rtc->irq_data & RTC_UF) ?
-								0x80 : buf[3];
-
-	ret = i2c_smbus_write_i2c_block_data(client, DS3232_REG_ALARM1, 4, buf);
-	if (ret < 0)
-		goto unlock;
 
-	control = i2c_smbus_read_byte_data(client, DS3232_REG_CR);
-	if (control < 0)
-		goto unlock;
+	ret = regmap_read(ds3232->regmap, DS3232_REG_CR, &control);
+	if (ret)
+		return ret;
 
-	if (ds3232->rtc->irq_data & (RTC_AF | RTC_UF))
+	if (enabled)
 		/* enable alarm1 interrupt */
 		control |= DS3232_REG_CR_A1IE;
 	else
 		/* disable alarm1 interrupt */
 		control &= ~(DS3232_REG_CR_A1IE);
-	i2c_smbus_write_byte_data(client, DS3232_REG_CR, control);
+	ret = regmap_write(ds3232->regmap, DS3232_REG_CR, control);
 
-unlock:
-	mutex_unlock(&ds3232->mutex);
+	return ret;
 }
 
 static int ds3232_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
-	struct i2c_client *client = to_i2c_client(dev);
-	struct ds3232 *ds3232 = i2c_get_clientdata(client);
+	struct ds3232 *ds3232 = dev_get_drvdata(dev);
 
-	if (client->irq <= 0)
+	if (ds3232->irq <= 0)
 		return -EINVAL;
 
-	if (enabled)
-		ds3232->rtc->irq_data |= RTC_AF;
-	else
-		ds3232->rtc->irq_data &= ~RTC_AF;
-
-	ds3232_update_alarm(client);
-	return 0;
+	return ds3232_update_alarm(dev, enabled);
 }
 
 static irqreturn_t ds3232_irq(int irq, void *dev_id)
 {
-	struct i2c_client *client = dev_id;
-	struct ds3232 *ds3232 = i2c_get_clientdata(client);
-
-	disable_irq_nosync(irq);
-
-	/*
-	 * If rtc as a wakeup source, can't schedule the work
-	 * at system resume flow, because at this time the i2c bus
-	 * has not been resumed.
-	 */
-	if (!ds3232->suspended)
-		schedule_work(&ds3232->work);
-
-	return IRQ_HANDLED;
-}
-
-static void ds3232_work(struct work_struct *work)
-{
-	struct ds3232 *ds3232 = container_of(work, struct ds3232, work);
-	struct i2c_client *client = ds3232->client;
+	struct device *dev = dev_id;
+	struct ds3232 *ds3232 = dev_get_drvdata(dev);
+	struct mutex *lock = &ds3232->rtc->ops_lock;
+	int ret;
 	int stat, control;
 
-	mutex_lock(&ds3232->mutex);
+	mutex_lock(lock);
 
-	stat = i2c_smbus_read_byte_data(client, DS3232_REG_SR);
-	if (stat < 0)
+	ret = regmap_read(ds3232->regmap, DS3232_REG_SR, &stat);
+	if (ret)
 		goto unlock;
 
 	if (stat & DS3232_REG_SR_A1F) {
-		control = i2c_smbus_read_byte_data(client, DS3232_REG_CR);
-		if (control < 0) {
-			pr_warn("Read Control Register error - Disable IRQ%d\n",
-				client->irq);
+		ret = regmap_read(ds3232->regmap, DS3232_REG_CR, &control);
+		if (ret) {
+			dev_warn(ds3232->dev,
+				 "Read Control Register error %d\n", ret);
 		} else {
 			/* disable alarm1 interrupt */
 			control &= ~(DS3232_REG_CR_A1IE);
-			i2c_smbus_write_byte_data(client, DS3232_REG_CR,
-						control);
+			ret = regmap_write(ds3232->regmap, DS3232_REG_CR,
+					   control);
+			if (ret) {
+				dev_warn(ds3232->dev,
+					 "Write Control Register error %d\n",
+					 ret);
+				goto unlock;
+			}
 
 			/* clear the alarm pend flag */
 			stat &= ~DS3232_REG_SR_A1F;
-			i2c_smbus_write_byte_data(client, DS3232_REG_SR, stat);
+			ret = regmap_write(ds3232->regmap, DS3232_REG_SR, stat);
+			if (ret) {
+				dev_warn(ds3232->dev,
+					 "Write Status Register error %d\n",
+					 ret);
+				goto unlock;
+			}
 
 			rtc_update_irq(ds3232->rtc, 1, RTC_AF | RTC_IRQF);
-
-			if (!ds3232->exiting)
-				enable_irq(client->irq);
 		}
 	}
 
 unlock:
-	mutex_unlock(&ds3232->mutex);
+	mutex_unlock(lock);
+
+	return IRQ_HANDLED;
 }
 
 static const struct rtc_class_ops ds3232_rtc_ops = {
@@ -406,67 +350,50 @@ static const struct rtc_class_ops ds3232_rtc_ops = {
 	.alarm_irq_enable = ds3232_alarm_irq_enable,
 };
 
-static int ds3232_probe(struct i2c_client *client,
-			const struct i2c_device_id *id)
+static int ds3232_probe(struct device *dev, struct regmap *regmap, int irq,
+			const char *name)
 {
 	struct ds3232 *ds3232;
 	int ret;
 
-	ds3232 = devm_kzalloc(&client->dev, sizeof(struct ds3232), GFP_KERNEL);
+	ds3232 = devm_kzalloc(dev, sizeof(*ds3232), GFP_KERNEL);
 	if (!ds3232)
 		return -ENOMEM;
 
-	ds3232->client = client;
-	i2c_set_clientdata(client, ds3232);
-
-	INIT_WORK(&ds3232->work, ds3232_work);
-	mutex_init(&ds3232->mutex);
+	ds3232->regmap = regmap;
+	ds3232->irq = irq;
+	ds3232->dev = dev;
+	dev_set_drvdata(dev, ds3232);
 
-	ret = ds3232_check_rtc_status(client);
+	ret = ds3232_check_rtc_status(dev);
 	if (ret)
 		return ret;
 
-	if (client->irq > 0) {
-		ret = devm_request_irq(&client->dev, client->irq, ds3232_irq,
-				       IRQF_SHARED, "ds3232", client);
+	if (ds3232->irq > 0) {
+		ret = devm_request_threaded_irq(dev, ds3232->irq, NULL,
+						ds3232_irq,
+						IRQF_SHARED | IRQF_ONESHOT,
+						name, dev);
 		if (ret) {
-			dev_err(&client->dev, "unable to request IRQ\n");
-		}
-		device_init_wakeup(&client->dev, 1);
-	}
-	ds3232->rtc = devm_rtc_device_register(&client->dev, client->name,
-					  &ds3232_rtc_ops, THIS_MODULE);
-	return PTR_ERR_OR_ZERO(ds3232->rtc);
-}
-
-static int ds3232_remove(struct i2c_client *client)
-{
-	struct ds3232 *ds3232 = i2c_get_clientdata(client);
-
-	if (client->irq > 0) {
-		mutex_lock(&ds3232->mutex);
-		ds3232->exiting = 1;
-		mutex_unlock(&ds3232->mutex);
-
-		devm_free_irq(&client->dev, client->irq, client);
-		cancel_work_sync(&ds3232->work);
+			ds3232->irq = 0;
+			dev_err(dev, "unable to request IRQ\n");
+		} else
+			device_init_wakeup(dev, 1);
 	}
+	ds3232->rtc = devm_rtc_device_register(dev, name, &ds3232_rtc_ops,
+						THIS_MODULE);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(ds3232->rtc);
 }
 
 #ifdef CONFIG_PM_SLEEP
 static int ds3232_suspend(struct device *dev)
 {
 	struct ds3232 *ds3232 = dev_get_drvdata(dev);
-	struct i2c_client *client = to_i2c_client(dev);
 
-	if (device_can_wakeup(dev)) {
-		ds3232->suspended = true;
-		if (irq_set_irq_wake(client->irq, 1)) {
+	if (device_may_wakeup(dev)) {
+		if (enable_irq_wake(ds3232->irq))
 			dev_warn_once(dev, "Cannot set wakeup source\n");
-			ds3232->suspended = false;
-		}
 	}
 
 	return 0;
@@ -475,16 +402,9 @@ static int ds3232_suspend(struct device *dev)
 static int ds3232_resume(struct device *dev)
 {
 	struct ds3232 *ds3232 = dev_get_drvdata(dev);
-	struct i2c_client *client = to_i2c_client(dev);
 
-	if (ds3232->suspended) {
-		ds3232->suspended = false;
-
-		/* Clear the hardware alarm pend flag */
-		schedule_work(&ds3232->work);
-
-		irq_set_irq_wake(client->irq, 0);
-	}
+	if (device_may_wakeup(dev))
+		disable_irq_wake(ds3232->irq);
 
 	return 0;
 }
@@ -494,6 +414,27 @@ static const struct dev_pm_ops ds3232_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(ds3232_suspend, ds3232_resume)
 };
 
+#if IS_ENABLED(CONFIG_I2C)
+
+static int ds3232_i2c_probe(struct i2c_client *client,
+			    const struct i2c_device_id *id)
+{
+	struct regmap *regmap;
+	static const struct regmap_config config = {
+		.reg_bits = 8,
+		.val_bits = 8,
+	};
+
+	regmap = devm_regmap_init_i2c(client, &config);
+	if (IS_ERR(regmap)) {
+		dev_err(&client->dev, "%s: regmap allocation failed: %ld\n",
+			__func__, PTR_ERR(regmap));
+		return PTR_ERR(regmap);
+	}
+
+	return ds3232_probe(&client->dev, regmap, client->irq, client->name);
+}
+
 static const struct i2c_device_id ds3232_id[] = {
 	{ "ds3232", 0 },
 	{ }
@@ -505,13 +446,162 @@ static struct i2c_driver ds3232_driver = {
 		.name = "rtc-ds3232",
 		.pm	= &ds3232_pm_ops,
 	},
-	.probe = ds3232_probe,
-	.remove = ds3232_remove,
+	.probe = ds3232_i2c_probe,
 	.id_table = ds3232_id,
 };
 
-module_i2c_driver(ds3232_driver);
+static int ds3232_register_driver(void)
+{
+	return i2c_add_driver(&ds3232_driver);
+}
+
+static void ds3232_unregister_driver(void)
+{
+	i2c_del_driver(&ds3232_driver);
+}
+
+#else
+
+static int ds3232_register_driver(void)
+{
+	return 0;
+}
+
+static void ds3232_unregister_driver(void)
+{
+}
+
+#endif
+
+#if IS_ENABLED(CONFIG_SPI_MASTER)
+
+static int ds3234_probe(struct spi_device *spi)
+{
+	int res;
+	unsigned int tmp;
+	static const struct regmap_config config = {
+		.reg_bits = 8,
+		.val_bits = 8,
+		.write_flag_mask = 0x80,
+	};
+	struct regmap *regmap;
+
+	regmap = devm_regmap_init_spi(spi, &config);
+	if (IS_ERR(regmap)) {
+		dev_err(&spi->dev, "%s: regmap allocation failed: %ld\n",
+			__func__, PTR_ERR(regmap));
+		return PTR_ERR(regmap);
+	}
+
+	spi->mode = SPI_MODE_3;
+	spi->bits_per_word = 8;
+	spi_setup(spi);
+
+	res = regmap_read(regmap, DS3232_REG_SECONDS, &tmp);
+	if (res)
+		return res;
+
+	/* Control settings
+	 *
+	 * CONTROL_REG
+	 * BIT 7	6	5	4	3	2	1	0
+	 *     EOSC	BBSQW	CONV	RS2	RS1	INTCN	A2IE	A1IE
+	 *
+	 *     0	0	0	1	1	1	0	0
+	 *
+	 * CONTROL_STAT_REG
+	 * BIT 7	6	5	4	3	2	1	0
+	 *     OSF	BB32kHz	CRATE1	CRATE0	EN32kHz	BSY	A2F	A1F
+	 *
+	 *     1	0	0	0	1	0	0	0
+	 */
+	res = regmap_read(regmap, DS3232_REG_CR, &tmp);
+	if (res)
+		return res;
+	res = regmap_write(regmap, DS3232_REG_CR, tmp & 0x1c);
+	if (res)
+		return res;
+
+	res = regmap_read(regmap, DS3232_REG_SR, &tmp);
+	if (res)
+		return res;
+	res = regmap_write(regmap, DS3232_REG_SR, tmp & 0x88);
+	if (res)
+		return res;
+
+	/* Print our settings */
+	res = regmap_read(regmap, DS3232_REG_CR, &tmp);
+	if (res)
+		return res;
+	dev_info(&spi->dev, "Control Reg: 0x%02x\n", tmp);
+
+	res = regmap_read(regmap, DS3232_REG_SR, &tmp);
+	if (res)
+		return res;
+	dev_info(&spi->dev, "Ctrl/Stat Reg: 0x%02x\n", tmp);
+
+	return ds3232_probe(&spi->dev, regmap, spi->irq, "ds3234");
+}
+
+static struct spi_driver ds3234_driver = {
+	.driver = {
+		.name	 = "ds3234",
+	},
+	.probe	 = ds3234_probe,
+};
+
+static int ds3234_register_driver(void)
+{
+	return spi_register_driver(&ds3234_driver);
+}
+
+static void ds3234_unregister_driver(void)
+{
+	spi_unregister_driver(&ds3234_driver);
+}
+
+#else
+
+static int ds3234_register_driver(void)
+{
+	return 0;
+}
+
+static void ds3234_unregister_driver(void)
+{
+}
+
+#endif
+
+static int __init ds323x_init(void)
+{
+	int ret;
+
+	ret = ds3232_register_driver();
+	if (ret) {
+		pr_err("Failed to register ds3232 driver: %d\n", ret);
+		return ret;
+	}
+
+	ret = ds3234_register_driver();
+	if (ret) {
+		pr_err("Failed to register ds3234 driver: %d\n", ret);
+		ds3232_unregister_driver();
+	}
+
+	return ret;
+}
+module_init(ds323x_init)
+
+static void __exit ds323x_exit(void)
+{
+	ds3234_unregister_driver();
+	ds3232_unregister_driver();
+}
+module_exit(ds323x_exit)
 
 MODULE_AUTHOR("Srikanth Srinivasan <srikanth.srinivasan@freescale.com>");
-MODULE_DESCRIPTION("Maxim/Dallas DS3232 RTC Driver");
+MODULE_AUTHOR("Dennis Aberilla <denzzzhome@yahoo.com>");
+MODULE_DESCRIPTION("Maxim/Dallas DS3232/DS3234 RTC Driver");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("spi:ds3234");
diff --git a/drivers/rtc/rtc-ds3234.c b/drivers/rtc/rtc-ds3234.c
deleted file mode 100644
index 570ab28fc354..000000000000
--- a/drivers/rtc/rtc-ds3234.c
+++ /dev/null
@@ -1,171 +0,0 @@
-/* rtc-ds3234.c
- *
- * Driver for Dallas Semiconductor (DS3234) SPI RTC with Integrated Crystal
- * and SRAM.
- *
- * Copyright (C) 2008 MIMOMax Wireless Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/rtc.h>
-#include <linux/spi/spi.h>
-#include <linux/bcd.h>
-
-#define DS3234_REG_SECONDS	0x00
-#define DS3234_REG_MINUTES	0x01
-#define DS3234_REG_HOURS	0x02
-#define DS3234_REG_DAY		0x03
-#define DS3234_REG_DATE		0x04
-#define DS3234_REG_MONTH	0x05
-#define DS3234_REG_YEAR		0x06
-#define DS3234_REG_CENTURY	(1 << 7) /* Bit 7 of the Month register */
-
-#define DS3234_REG_CONTROL	0x0E
-#define DS3234_REG_CONT_STAT	0x0F
-
-static int ds3234_set_reg(struct device *dev, unsigned char address,
-				unsigned char data)
-{
-	struct spi_device *spi = to_spi_device(dev);
-	unsigned char buf[2];
-
-	/* MSB must be '1' to indicate write */
-	buf[0] = address | 0x80;
-	buf[1] = data;
-
-	return spi_write_then_read(spi, buf, 2, NULL, 0);
-}
-
-static int ds3234_get_reg(struct device *dev, unsigned char address,
-				unsigned char *data)
-{
-	struct spi_device *spi = to_spi_device(dev);
-
-	*data = address & 0x7f;
-
-	return spi_write_then_read(spi, data, 1, data, 1);
-}
-
-static int ds3234_read_time(struct device *dev, struct rtc_time *dt)
-{
-	int err;
-	unsigned char buf[8];
-	struct spi_device *spi = to_spi_device(dev);
-
-	buf[0] = 0x00; /* Start address */
-
-	err = spi_write_then_read(spi, buf, 1, buf, 8);
-	if (err != 0)
-		return err;
-
-	/* Seconds, Minutes, Hours, Day, Date, Month, Year */
-	dt->tm_sec	= bcd2bin(buf[0]);
-	dt->tm_min	= bcd2bin(buf[1]);
-	dt->tm_hour	= bcd2bin(buf[2] & 0x3f);
-	dt->tm_wday	= bcd2bin(buf[3]) - 1; /* 0 = Sun */
-	dt->tm_mday	= bcd2bin(buf[4]);
-	dt->tm_mon	= bcd2bin(buf[5] & 0x1f) - 1; /* 0 = Jan */
-	dt->tm_year	= bcd2bin(buf[6] & 0xff) + 100; /* Assume 20YY */
-
-	return rtc_valid_tm(dt);
-}
-
-static int ds3234_set_time(struct device *dev, struct rtc_time *dt)
-{
-	ds3234_set_reg(dev, DS3234_REG_SECONDS, bin2bcd(dt->tm_sec));
-	ds3234_set_reg(dev, DS3234_REG_MINUTES, bin2bcd(dt->tm_min));
-	ds3234_set_reg(dev, DS3234_REG_HOURS, bin2bcd(dt->tm_hour) & 0x3f);
-
-	/* 0 = Sun */
-	ds3234_set_reg(dev, DS3234_REG_DAY, bin2bcd(dt->tm_wday + 1));
-	ds3234_set_reg(dev, DS3234_REG_DATE, bin2bcd(dt->tm_mday));
-
-	/* 0 = Jan */
-	ds3234_set_reg(dev, DS3234_REG_MONTH, bin2bcd(dt->tm_mon + 1));
-
-	/* Assume 20YY although we just want to make sure not to go negative. */
-	if (dt->tm_year > 100)
-		dt->tm_year -= 100;
-
-	ds3234_set_reg(dev, DS3234_REG_YEAR, bin2bcd(dt->tm_year));
-
-	return 0;
-}
-
-static const struct rtc_class_ops ds3234_rtc_ops = {
-	.read_time	= ds3234_read_time,
-	.set_time	= ds3234_set_time,
-};
-
-static int ds3234_probe(struct spi_device *spi)
-{
-	struct rtc_device *rtc;
-	unsigned char tmp;
-	int res;
-
-	spi->mode = SPI_MODE_3;
-	spi->bits_per_word = 8;
-	spi_setup(spi);
-
-	res = ds3234_get_reg(&spi->dev, DS3234_REG_SECONDS, &tmp);
-	if (res != 0)
-		return res;
-
-	/* Control settings
-	 *
-	 * CONTROL_REG
-	 * BIT 7	6	5	4	3	2	1	0
-	 *     EOSC	BBSQW	CONV	RS2	RS1	INTCN	A2IE	A1IE
-	 *
-	 *     0	0	0	1	1	1	0	0
-	 *
-	 * CONTROL_STAT_REG
-	 * BIT 7	6	5	4	3	2	1	0
-	 *     OSF	BB32kHz	CRATE1	CRATE0	EN32kHz	BSY	A2F	A1F
-	 *
-	 *     1	0	0	0	1	0	0	0
-	 */
-	ds3234_get_reg(&spi->dev, DS3234_REG_CONTROL, &tmp);
-	ds3234_set_reg(&spi->dev, DS3234_REG_CONTROL, tmp & 0x1c);
-
-	ds3234_get_reg(&spi->dev, DS3234_REG_CONT_STAT, &tmp);
-	ds3234_set_reg(&spi->dev, DS3234_REG_CONT_STAT, tmp & 0x88);
-
-	/* Print our settings */
-	ds3234_get_reg(&spi->dev, DS3234_REG_CONTROL, &tmp);
-	dev_info(&spi->dev, "Control Reg: 0x%02x\n", tmp);
-
-	ds3234_get_reg(&spi->dev, DS3234_REG_CONT_STAT, &tmp);
-	dev_info(&spi->dev, "Ctrl/Stat Reg: 0x%02x\n", tmp);
-
-	rtc = devm_rtc_device_register(&spi->dev, "ds3234",
-				&ds3234_rtc_ops, THIS_MODULE);
-	if (IS_ERR(rtc))
-		return PTR_ERR(rtc);
-
-	spi_set_drvdata(spi, rtc);
-
-	return 0;
-}
-
-static struct spi_driver ds3234_driver = {
-	.driver = {
-		.name	 = "ds3234",
-	},
-	.probe	 = ds3234_probe,
-};
-
-module_spi_driver(ds3234_driver);
-
-MODULE_DESCRIPTION("DS3234 SPI RTC driver");
-MODULE_AUTHOR("Dennis Aberilla <denzzzhome@yahoo.com>");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("spi:ds3234");
diff --git a/drivers/rtc/rtc-generic.c b/drivers/rtc/rtc-generic.c
index e782ebd719b2..d726c6aa96a8 100644
--- a/drivers/rtc/rtc-generic.c
+++ b/drivers/rtc/rtc-generic.c
@@ -9,6 +9,8 @@
 #include <linux/platform_device.h>
 #include <linux/rtc.h>
 
+#if defined(CONFIG_M68K) || defined(CONFIG_PARISC) || \
+    defined(CONFIG_PPC) || defined(CONFIG_SUPERH32)
 #include <asm/rtc.h>
 
 static int generic_get_time(struct device *dev, struct rtc_time *tm)
@@ -33,13 +35,21 @@ static const struct rtc_class_ops generic_rtc_ops = {
 	.read_time = generic_get_time,
 	.set_time = generic_set_time,
 };
+#else
+#define generic_rtc_ops *(struct rtc_class_ops*)NULL
+#endif
 
 static int __init generic_rtc_probe(struct platform_device *dev)
 {
 	struct rtc_device *rtc;
+	const struct rtc_class_ops *ops;
+
+	ops = dev_get_platdata(&dev->dev);
+	if (!ops)
+		ops = &generic_rtc_ops;
 
 	rtc = devm_rtc_device_register(&dev->dev, "rtc-generic",
-					&generic_rtc_ops, THIS_MODULE);
+					ops, THIS_MODULE);
 	if (IS_ERR(rtc))
 		return PTR_ERR(rtc);
 
diff --git a/drivers/rtc/rtc-hym8563.c b/drivers/rtc/rtc-hym8563.c
index 097325d96db5..b1b4746a0eab 100644
--- a/drivers/rtc/rtc-hym8563.c
+++ b/drivers/rtc/rtc-hym8563.c
@@ -144,7 +144,7 @@ static int hym8563_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	 * it does not seem to carry it over a subsequent write/read.
 	 * So we'll limit ourself to 100 years, starting at 2000 for now.
 	 */
-	buf[6] = tm->tm_year - 100;
+	buf[6] = bin2bcd(tm->tm_year - 100);
 
 	/*
 	 * CTL1 only contains TEST-mode bits apart from stop,
diff --git a/drivers/rtc/rtc-max77686.c b/drivers/rtc/rtc-max77686.c
index 7184a0eda793..182fdd00e290 100644
--- a/drivers/rtc/rtc-max77686.c
+++ b/drivers/rtc/rtc-max77686.c
@@ -1,5 +1,5 @@
 /*
- * RTC driver for Maxim MAX77686
+ * RTC driver for Maxim MAX77686 and MAX77802
  *
  * Copyright (C) 2012 Samsung Electronics Co.Ltd
  *
@@ -12,8 +12,7 @@
  *
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
+#include <linux/i2c.h>
 #include <linux/slab.h>
 #include <linux/rtc.h>
 #include <linux/delay.h>
@@ -24,24 +23,38 @@
 #include <linux/irqdomain.h>
 #include <linux/regmap.h>
 
+#define MAX77686_I2C_ADDR_RTC		(0x0C >> 1)
+#define MAX77620_I2C_ADDR_RTC		0x68
+#define MAX77686_INVALID_I2C_ADDR	(-1)
+
+/* Define non existing register */
+#define MAX77686_INVALID_REG		(-1)
+
 /* RTC Control Register */
 #define BCD_EN_SHIFT			0
-#define BCD_EN_MASK			(1 << BCD_EN_SHIFT)
+#define BCD_EN_MASK			BIT(BCD_EN_SHIFT)
 #define MODEL24_SHIFT			1
-#define MODEL24_MASK			(1 << MODEL24_SHIFT)
+#define MODEL24_MASK			BIT(MODEL24_SHIFT)
 /* RTC Update Register1 */
 #define RTC_UDR_SHIFT			0
-#define RTC_UDR_MASK			(1 << RTC_UDR_SHIFT)
+#define RTC_UDR_MASK			BIT(RTC_UDR_SHIFT)
 #define RTC_RBUDR_SHIFT			4
-#define RTC_RBUDR_MASK			(1 << RTC_RBUDR_SHIFT)
+#define RTC_RBUDR_MASK			BIT(RTC_RBUDR_SHIFT)
 /* RTC Hour register */
 #define HOUR_PM_SHIFT			6
-#define HOUR_PM_MASK			(1 << HOUR_PM_SHIFT)
+#define HOUR_PM_MASK			BIT(HOUR_PM_SHIFT)
 /* RTC Alarm Enable */
 #define ALARM_ENABLE_SHIFT		7
-#define ALARM_ENABLE_MASK		(1 << ALARM_ENABLE_SHIFT)
+#define ALARM_ENABLE_MASK		BIT(ALARM_ENABLE_SHIFT)
 
-#define MAX77686_RTC_UPDATE_DELAY	16
+#define REG_RTC_NONE			0xdeadbeef
+
+/*
+ * MAX77802 has separate register (RTCAE1) for alarm enable instead
+ * using 1 bit from registers RTC{SEC,MIN,HOUR,DAY,MONTH,YEAR,DATE}
+ * as in done in MAX77686.
+ */
+#define MAX77802_ALARM_ENABLE_VALUE	0x77
 
 enum {
 	RTC_SEC = 0,
@@ -54,15 +67,38 @@ enum {
 	RTC_NR_TIME
 };
 
+struct max77686_rtc_driver_data {
+	/* Minimum usecs needed for a RTC update */
+	unsigned long		delay;
+	/* Mask used to read RTC registers value */
+	u8			mask;
+	/* Registers offset to I2C addresses map */
+	const unsigned int	*map;
+	/* Has a separate alarm enable register? */
+	bool			alarm_enable_reg;
+	/* I2C address for RTC block */
+	int			rtc_i2c_addr;
+	/* RTC interrupt via platform resource */
+	bool			rtc_irq_from_platform;
+	/* Pending alarm status register */
+	int			alarm_pending_status_reg;
+	/* RTC IRQ CHIP for regmap */
+	const struct regmap_irq_chip *rtc_irq_chip;
+};
+
 struct max77686_rtc_info {
 	struct device		*dev;
-	struct max77686_dev	*max77686;
 	struct i2c_client	*rtc;
 	struct rtc_device	*rtc_dev;
 	struct mutex		lock;
 
 	struct regmap		*regmap;
+	struct regmap		*rtc_regmap;
+
+	const struct max77686_rtc_driver_data *drv_data;
+	struct regmap_irq_chip_data *rtc_irq_data;
 
+	int rtc_irq;
 	int virq;
 	int rtc_24hr_mode;
 };
@@ -72,29 +108,190 @@ enum MAX77686_RTC_OP {
 	MAX77686_RTC_READ,
 };
 
+/* These are not registers but just offsets that are mapped to addresses */
+enum max77686_rtc_reg_offset {
+	REG_RTC_CONTROLM = 0,
+	REG_RTC_CONTROL,
+	REG_RTC_UPDATE0,
+	REG_WTSR_SMPL_CNTL,
+	REG_RTC_SEC,
+	REG_RTC_MIN,
+	REG_RTC_HOUR,
+	REG_RTC_WEEKDAY,
+	REG_RTC_MONTH,
+	REG_RTC_YEAR,
+	REG_RTC_DATE,
+	REG_ALARM1_SEC,
+	REG_ALARM1_MIN,
+	REG_ALARM1_HOUR,
+	REG_ALARM1_WEEKDAY,
+	REG_ALARM1_MONTH,
+	REG_ALARM1_YEAR,
+	REG_ALARM1_DATE,
+	REG_ALARM2_SEC,
+	REG_ALARM2_MIN,
+	REG_ALARM2_HOUR,
+	REG_ALARM2_WEEKDAY,
+	REG_ALARM2_MONTH,
+	REG_ALARM2_YEAR,
+	REG_ALARM2_DATE,
+	REG_RTC_AE1,
+	REG_RTC_END,
+};
+
+/* Maps RTC registers offset to the MAX77686 register addresses */
+static const unsigned int max77686_map[REG_RTC_END] = {
+	[REG_RTC_CONTROLM]   = MAX77686_RTC_CONTROLM,
+	[REG_RTC_CONTROL]    = MAX77686_RTC_CONTROL,
+	[REG_RTC_UPDATE0]    = MAX77686_RTC_UPDATE0,
+	[REG_WTSR_SMPL_CNTL] = MAX77686_WTSR_SMPL_CNTL,
+	[REG_RTC_SEC]        = MAX77686_RTC_SEC,
+	[REG_RTC_MIN]        = MAX77686_RTC_MIN,
+	[REG_RTC_HOUR]       = MAX77686_RTC_HOUR,
+	[REG_RTC_WEEKDAY]    = MAX77686_RTC_WEEKDAY,
+	[REG_RTC_MONTH]      = MAX77686_RTC_MONTH,
+	[REG_RTC_YEAR]       = MAX77686_RTC_YEAR,
+	[REG_RTC_DATE]       = MAX77686_RTC_DATE,
+	[REG_ALARM1_SEC]     = MAX77686_ALARM1_SEC,
+	[REG_ALARM1_MIN]     = MAX77686_ALARM1_MIN,
+	[REG_ALARM1_HOUR]    = MAX77686_ALARM1_HOUR,
+	[REG_ALARM1_WEEKDAY] = MAX77686_ALARM1_WEEKDAY,
+	[REG_ALARM1_MONTH]   = MAX77686_ALARM1_MONTH,
+	[REG_ALARM1_YEAR]    = MAX77686_ALARM1_YEAR,
+	[REG_ALARM1_DATE]    = MAX77686_ALARM1_DATE,
+	[REG_ALARM2_SEC]     = MAX77686_ALARM2_SEC,
+	[REG_ALARM2_MIN]     = MAX77686_ALARM2_MIN,
+	[REG_ALARM2_HOUR]    = MAX77686_ALARM2_HOUR,
+	[REG_ALARM2_WEEKDAY] = MAX77686_ALARM2_WEEKDAY,
+	[REG_ALARM2_MONTH]   = MAX77686_ALARM2_MONTH,
+	[REG_ALARM2_YEAR]    = MAX77686_ALARM2_YEAR,
+	[REG_ALARM2_DATE]    = MAX77686_ALARM2_DATE,
+	[REG_RTC_AE1]	     = REG_RTC_NONE,
+};
+
+static const struct regmap_irq max77686_rtc_irqs[] = {
+	/* RTC interrupts */
+	REGMAP_IRQ_REG(0, 0, MAX77686_RTCINT_RTC60S_MSK),
+	REGMAP_IRQ_REG(1, 0, MAX77686_RTCINT_RTCA1_MSK),
+	REGMAP_IRQ_REG(2, 0, MAX77686_RTCINT_RTCA2_MSK),
+	REGMAP_IRQ_REG(3, 0, MAX77686_RTCINT_SMPL_MSK),
+	REGMAP_IRQ_REG(4, 0, MAX77686_RTCINT_RTC1S_MSK),
+	REGMAP_IRQ_REG(5, 0, MAX77686_RTCINT_WTSR_MSK),
+};
+
+static const struct regmap_irq_chip max77686_rtc_irq_chip = {
+	.name		= "max77686-rtc",
+	.status_base	= MAX77686_RTC_INT,
+	.mask_base	= MAX77686_RTC_INTM,
+	.num_regs	= 1,
+	.irqs		= max77686_rtc_irqs,
+	.num_irqs	= ARRAY_SIZE(max77686_rtc_irqs),
+};
+
+static const struct max77686_rtc_driver_data max77686_drv_data = {
+	.delay = 16000,
+	.mask  = 0x7f,
+	.map   = max77686_map,
+	.alarm_enable_reg  = false,
+	.rtc_irq_from_platform = false,
+	.alarm_pending_status_reg = MAX77686_REG_STATUS2,
+	.rtc_i2c_addr = MAX77686_I2C_ADDR_RTC,
+	.rtc_irq_chip = &max77686_rtc_irq_chip,
+};
+
+static const struct max77686_rtc_driver_data max77620_drv_data = {
+	.delay = 16000,
+	.mask  = 0x7f,
+	.map   = max77686_map,
+	.alarm_enable_reg  = false,
+	.rtc_irq_from_platform = true,
+	.alarm_pending_status_reg = MAX77686_INVALID_REG,
+	.rtc_i2c_addr = MAX77620_I2C_ADDR_RTC,
+	.rtc_irq_chip = &max77686_rtc_irq_chip,
+};
+
+static const unsigned int max77802_map[REG_RTC_END] = {
+	[REG_RTC_CONTROLM]   = MAX77802_RTC_CONTROLM,
+	[REG_RTC_CONTROL]    = MAX77802_RTC_CONTROL,
+	[REG_RTC_UPDATE0]    = MAX77802_RTC_UPDATE0,
+	[REG_WTSR_SMPL_CNTL] = MAX77802_WTSR_SMPL_CNTL,
+	[REG_RTC_SEC]        = MAX77802_RTC_SEC,
+	[REG_RTC_MIN]        = MAX77802_RTC_MIN,
+	[REG_RTC_HOUR]       = MAX77802_RTC_HOUR,
+	[REG_RTC_WEEKDAY]    = MAX77802_RTC_WEEKDAY,
+	[REG_RTC_MONTH]      = MAX77802_RTC_MONTH,
+	[REG_RTC_YEAR]       = MAX77802_RTC_YEAR,
+	[REG_RTC_DATE]       = MAX77802_RTC_DATE,
+	[REG_ALARM1_SEC]     = MAX77802_ALARM1_SEC,
+	[REG_ALARM1_MIN]     = MAX77802_ALARM1_MIN,
+	[REG_ALARM1_HOUR]    = MAX77802_ALARM1_HOUR,
+	[REG_ALARM1_WEEKDAY] = MAX77802_ALARM1_WEEKDAY,
+	[REG_ALARM1_MONTH]   = MAX77802_ALARM1_MONTH,
+	[REG_ALARM1_YEAR]    = MAX77802_ALARM1_YEAR,
+	[REG_ALARM1_DATE]    = MAX77802_ALARM1_DATE,
+	[REG_ALARM2_SEC]     = MAX77802_ALARM2_SEC,
+	[REG_ALARM2_MIN]     = MAX77802_ALARM2_MIN,
+	[REG_ALARM2_HOUR]    = MAX77802_ALARM2_HOUR,
+	[REG_ALARM2_WEEKDAY] = MAX77802_ALARM2_WEEKDAY,
+	[REG_ALARM2_MONTH]   = MAX77802_ALARM2_MONTH,
+	[REG_ALARM2_YEAR]    = MAX77802_ALARM2_YEAR,
+	[REG_ALARM2_DATE]    = MAX77802_ALARM2_DATE,
+	[REG_RTC_AE1]	     = MAX77802_RTC_AE1,
+};
+
+static const struct regmap_irq_chip max77802_rtc_irq_chip = {
+	.name		= "max77802-rtc",
+	.status_base	= MAX77802_RTC_INT,
+	.mask_base	= MAX77802_RTC_INTM,
+	.num_regs	= 1,
+	.irqs		= max77686_rtc_irqs, /* same masks as 77686 */
+	.num_irqs	= ARRAY_SIZE(max77686_rtc_irqs),
+};
+
+static const struct max77686_rtc_driver_data max77802_drv_data = {
+	.delay = 200,
+	.mask  = 0xff,
+	.map   = max77802_map,
+	.alarm_enable_reg  = true,
+	.rtc_irq_from_platform = false,
+	.alarm_pending_status_reg = MAX77686_REG_STATUS2,
+	.rtc_i2c_addr = MAX77686_INVALID_I2C_ADDR,
+	.rtc_irq_chip = &max77802_rtc_irq_chip,
+};
+
 static void max77686_rtc_data_to_tm(u8 *data, struct rtc_time *tm,
-				   int rtc_24hr_mode)
+				    struct max77686_rtc_info *info)
 {
-	tm->tm_sec = data[RTC_SEC] & 0x7f;
-	tm->tm_min = data[RTC_MIN] & 0x7f;
-	if (rtc_24hr_mode)
+	u8 mask = info->drv_data->mask;
+
+	tm->tm_sec = data[RTC_SEC] & mask;
+	tm->tm_min = data[RTC_MIN] & mask;
+	if (info->rtc_24hr_mode) {
 		tm->tm_hour = data[RTC_HOUR] & 0x1f;
-	else {
+	} else {
 		tm->tm_hour = data[RTC_HOUR] & 0x0f;
 		if (data[RTC_HOUR] & HOUR_PM_MASK)
 			tm->tm_hour += 12;
 	}
 
 	/* Only a single bit is set in data[], so fls() would be equivalent */
-	tm->tm_wday = ffs(data[RTC_WEEKDAY] & 0x7f) - 1;
+	tm->tm_wday = ffs(data[RTC_WEEKDAY] & mask) - 1;
 	tm->tm_mday = data[RTC_DATE] & 0x1f;
 	tm->tm_mon = (data[RTC_MONTH] & 0x0f) - 1;
-	tm->tm_year = (data[RTC_YEAR] & 0x7f) + 100;
+	tm->tm_year = data[RTC_YEAR] & mask;
 	tm->tm_yday = 0;
 	tm->tm_isdst = 0;
+
+	/*
+	 * MAX77686 uses 1 bit from sec/min/hour/etc RTC registers and the
+	 * year values are just 0..99 so add 100 to support up to 2099.
+	 */
+	if (!info->drv_data->alarm_enable_reg)
+		tm->tm_year += 100;
 }
 
-static int max77686_rtc_tm_to_data(struct rtc_time *tm, u8 *data)
+static int max77686_rtc_tm_to_data(struct rtc_time *tm, u8 *data,
+				   struct max77686_rtc_info *info)
 {
 	data[RTC_SEC] = tm->tm_sec;
 	data[RTC_MIN] = tm->tm_min;
@@ -102,35 +299,44 @@ static int max77686_rtc_tm_to_data(struct rtc_time *tm, u8 *data)
 	data[RTC_WEEKDAY] = 1 << tm->tm_wday;
 	data[RTC_DATE] = tm->tm_mday;
 	data[RTC_MONTH] = tm->tm_mon + 1;
+
+	if (info->drv_data->alarm_enable_reg) {
+		data[RTC_YEAR] = tm->tm_year;
+		return 0;
+	}
+
 	data[RTC_YEAR] = tm->tm_year > 100 ? (tm->tm_year - 100) : 0;
 
 	if (tm->tm_year < 100) {
-		pr_warn("RTC cannot handle the year %d.  Assume it's 2000.\n",
+		dev_err(info->dev, "RTC cannot handle the year %d.\n",
 			1900 + tm->tm_year);
 		return -EINVAL;
 	}
+
 	return 0;
 }
 
 static int max77686_rtc_update(struct max77686_rtc_info *info,
-	enum MAX77686_RTC_OP op)
+			       enum MAX77686_RTC_OP op)
 {
 	int ret;
 	unsigned int data;
+	unsigned long delay = info->drv_data->delay;
 
 	if (op == MAX77686_RTC_WRITE)
 		data = 1 << RTC_UDR_SHIFT;
 	else
 		data = 1 << RTC_RBUDR_SHIFT;
 
-	ret = regmap_update_bits(info->max77686->rtc_regmap,
-				 MAX77686_RTC_UPDATE0, data, data);
+	ret = regmap_update_bits(info->rtc_regmap,
+				 info->drv_data->map[REG_RTC_UPDATE0],
+				 data, data);
 	if (ret < 0)
-		dev_err(info->dev, "%s: fail to write update reg(ret=%d, data=0x%x)\n",
-				__func__, ret, data);
+		dev_err(info->dev, "Fail to write update reg(ret=%d, data=0x%x)\n",
+			ret, data);
 	else {
-		/* Minimum 16ms delay required before RTC update. */
-		msleep(MAX77686_RTC_UPDATE_DELAY);
+		/* Minimum delay required before RTC update. */
+		usleep_range(delay, delay * 2);
 	}
 
 	return ret;
@@ -148,14 +354,15 @@ static int max77686_rtc_read_time(struct device *dev, struct rtc_time *tm)
 	if (ret < 0)
 		goto out;
 
-	ret = regmap_bulk_read(info->max77686->rtc_regmap,
-				MAX77686_RTC_SEC, data, RTC_NR_TIME);
+	ret = regmap_bulk_read(info->rtc_regmap,
+			       info->drv_data->map[REG_RTC_SEC],
+			       data, ARRAY_SIZE(data));
 	if (ret < 0) {
-		dev_err(info->dev, "%s: fail to read time reg(%d)\n", __func__,	ret);
+		dev_err(info->dev, "Fail to read time reg(%d)\n", ret);
 		goto out;
 	}
 
-	max77686_rtc_data_to_tm(data, tm, info->rtc_24hr_mode);
+	max77686_rtc_data_to_tm(data, tm, info);
 
 	ret = rtc_valid_tm(tm);
 
@@ -170,17 +377,17 @@ static int max77686_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	u8 data[RTC_NR_TIME];
 	int ret;
 
-	ret = max77686_rtc_tm_to_data(tm, data);
+	ret = max77686_rtc_tm_to_data(tm, data, info);
 	if (ret < 0)
 		return ret;
 
 	mutex_lock(&info->lock);
 
-	ret = regmap_bulk_write(info->max77686->rtc_regmap,
-				 MAX77686_RTC_SEC, data, RTC_NR_TIME);
+	ret = regmap_bulk_write(info->rtc_regmap,
+				info->drv_data->map[REG_RTC_SEC],
+				data, ARRAY_SIZE(data));
 	if (ret < 0) {
-		dev_err(info->dev, "%s: fail to write time reg(%d)\n", __func__,
-				ret);
+		dev_err(info->dev, "Fail to write time reg(%d)\n", ret);
 		goto out;
 	}
 
@@ -196,6 +403,7 @@ static int max77686_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	struct max77686_rtc_info *info = dev_get_drvdata(dev);
 	u8 data[RTC_NR_TIME];
 	unsigned int val;
+	const unsigned int *map = info->drv_data->map;
 	int i, ret;
 
 	mutex_lock(&info->lock);
@@ -204,29 +412,53 @@ static int max77686_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	if (ret < 0)
 		goto out;
 
-	ret = regmap_bulk_read(info->max77686->rtc_regmap,
-				 MAX77686_ALARM1_SEC, data, RTC_NR_TIME);
+	ret = regmap_bulk_read(info->rtc_regmap, map[REG_ALARM1_SEC],
+			       data, ARRAY_SIZE(data));
 	if (ret < 0) {
-		dev_err(info->dev, "%s:%d fail to read alarm reg(%d)\n",
-				__func__, __LINE__, ret);
+		dev_err(info->dev, "Fail to read alarm reg(%d)\n", ret);
 		goto out;
 	}
 
-	max77686_rtc_data_to_tm(data, &alrm->time, info->rtc_24hr_mode);
+	max77686_rtc_data_to_tm(data, &alrm->time, info);
 
 	alrm->enabled = 0;
-	for (i = 0; i < RTC_NR_TIME; i++) {
-		if (data[i] & ALARM_ENABLE_MASK) {
+
+	if (info->drv_data->alarm_enable_reg) {
+		if (map[REG_RTC_AE1] == REG_RTC_NONE) {
+			ret = -EINVAL;
+			dev_err(info->dev,
+				"alarm enable register not set(%d)\n", ret);
+			goto out;
+		}
+
+		ret = regmap_read(info->rtc_regmap, map[REG_RTC_AE1], &val);
+		if (ret < 0) {
+			dev_err(info->dev,
+				"fail to read alarm enable(%d)\n", ret);
+			goto out;
+		}
+
+		if (val)
 			alrm->enabled = 1;
-			break;
+	} else {
+		for (i = 0; i < ARRAY_SIZE(data); i++) {
+			if (data[i] & ALARM_ENABLE_MASK) {
+				alrm->enabled = 1;
+				break;
+			}
 		}
 	}
 
 	alrm->pending = 0;
-	ret = regmap_read(info->max77686->regmap, MAX77686_REG_STATUS2, &val);
+
+	if (info->drv_data->alarm_pending_status_reg == MAX77686_INVALID_REG)
+		goto out;
+
+	ret = regmap_read(info->regmap,
+			  info->drv_data->alarm_pending_status_reg, &val);
 	if (ret < 0) {
-		dev_err(info->dev, "%s:%d fail to read status2 reg(%d)\n",
-				__func__, __LINE__, ret);
+		dev_err(info->dev,
+			"Fail to read alarm pending status reg(%d)\n", ret);
 		goto out;
 	}
 
@@ -235,7 +467,7 @@ static int max77686_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 
 out:
 	mutex_unlock(&info->lock);
-	return 0;
+	return ret;
 }
 
 static int max77686_rtc_stop_alarm(struct max77686_rtc_info *info)
@@ -243,6 +475,7 @@ static int max77686_rtc_stop_alarm(struct max77686_rtc_info *info)
 	u8 data[RTC_NR_TIME];
 	int ret, i;
 	struct rtc_time tm;
+	const unsigned int *map = info->drv_data->map;
 
 	if (!mutex_is_locked(&info->lock))
 		dev_warn(info->dev, "%s: should have mutex locked\n", __func__);
@@ -251,24 +484,34 @@ static int max77686_rtc_stop_alarm(struct max77686_rtc_info *info)
 	if (ret < 0)
 		goto out;
 
-	ret = regmap_bulk_read(info->max77686->rtc_regmap,
-				 MAX77686_ALARM1_SEC, data, RTC_NR_TIME);
-	if (ret < 0) {
-		dev_err(info->dev, "%s: fail to read alarm reg(%d)\n",
-				__func__, ret);
-		goto out;
-	}
+	if (info->drv_data->alarm_enable_reg) {
+		if (map[REG_RTC_AE1] == REG_RTC_NONE) {
+			ret = -EINVAL;
+			dev_err(info->dev,
+				"alarm enable register not set(%d)\n", ret);
+			goto out;
+		}
+
+		ret = regmap_write(info->rtc_regmap, map[REG_RTC_AE1], 0);
+	} else {
+		ret = regmap_bulk_read(info->rtc_regmap, map[REG_ALARM1_SEC],
+				       data, ARRAY_SIZE(data));
+		if (ret < 0) {
+			dev_err(info->dev, "Fail to read alarm reg(%d)\n", ret);
+			goto out;
+		}
 
-	max77686_rtc_data_to_tm(data, &tm, info->rtc_24hr_mode);
+		max77686_rtc_data_to_tm(data, &tm, info);
 
-	for (i = 0; i < RTC_NR_TIME; i++)
-		data[i] &= ~ALARM_ENABLE_MASK;
+		for (i = 0; i < ARRAY_SIZE(data); i++)
+			data[i] &= ~ALARM_ENABLE_MASK;
+
+		ret = regmap_bulk_write(info->rtc_regmap, map[REG_ALARM1_SEC],
+					data, ARRAY_SIZE(data));
+	}
 
-	ret = regmap_bulk_write(info->max77686->rtc_regmap,
-				 MAX77686_ALARM1_SEC, data, RTC_NR_TIME);
 	if (ret < 0) {
-		dev_err(info->dev, "%s: fail to write alarm reg(%d)\n",
-				__func__, ret);
+		dev_err(info->dev, "Fail to write alarm reg(%d)\n", ret);
 		goto out;
 	}
 
@@ -282,6 +525,7 @@ static int max77686_rtc_start_alarm(struct max77686_rtc_info *info)
 	u8 data[RTC_NR_TIME];
 	int ret;
 	struct rtc_time tm;
+	const unsigned int *map = info->drv_data->map;
 
 	if (!mutex_is_locked(&info->lock))
 		dev_warn(info->dev, "%s: should have mutex locked\n", __func__);
@@ -290,32 +534,36 @@ static int max77686_rtc_start_alarm(struct max77686_rtc_info *info)
 	if (ret < 0)
 		goto out;
 
-	ret = regmap_bulk_read(info->max77686->rtc_regmap,
-				 MAX77686_ALARM1_SEC, data, RTC_NR_TIME);
-	if (ret < 0) {
-		dev_err(info->dev, "%s: fail to read alarm reg(%d)\n",
-				__func__, ret);
-		goto out;
+	if (info->drv_data->alarm_enable_reg) {
+		ret = regmap_write(info->rtc_regmap, map[REG_RTC_AE1],
+				   MAX77802_ALARM_ENABLE_VALUE);
+	} else {
+		ret = regmap_bulk_read(info->rtc_regmap, map[REG_ALARM1_SEC],
+				       data, ARRAY_SIZE(data));
+		if (ret < 0) {
+			dev_err(info->dev, "Fail to read alarm reg(%d)\n", ret);
+			goto out;
+		}
+
+		max77686_rtc_data_to_tm(data, &tm, info);
+
+		data[RTC_SEC] |= (1 << ALARM_ENABLE_SHIFT);
+		data[RTC_MIN] |= (1 << ALARM_ENABLE_SHIFT);
+		data[RTC_HOUR] |= (1 << ALARM_ENABLE_SHIFT);
+		data[RTC_WEEKDAY] &= ~ALARM_ENABLE_MASK;
+		if (data[RTC_MONTH] & 0xf)
+			data[RTC_MONTH] |= (1 << ALARM_ENABLE_SHIFT);
+		if (data[RTC_YEAR] & info->drv_data->mask)
+			data[RTC_YEAR] |= (1 << ALARM_ENABLE_SHIFT);
+		if (data[RTC_DATE] & 0x1f)
+			data[RTC_DATE] |= (1 << ALARM_ENABLE_SHIFT);
+
+		ret = regmap_bulk_write(info->rtc_regmap, map[REG_ALARM1_SEC],
+					data, ARRAY_SIZE(data));
 	}
 
-	max77686_rtc_data_to_tm(data, &tm, info->rtc_24hr_mode);
-
-	data[RTC_SEC] |= (1 << ALARM_ENABLE_SHIFT);
-	data[RTC_MIN] |= (1 << ALARM_ENABLE_SHIFT);
-	data[RTC_HOUR] |= (1 << ALARM_ENABLE_SHIFT);
-	data[RTC_WEEKDAY] &= ~ALARM_ENABLE_MASK;
-	if (data[RTC_MONTH] & 0xf)
-		data[RTC_MONTH] |= (1 << ALARM_ENABLE_SHIFT);
-	if (data[RTC_YEAR] & 0x7f)
-		data[RTC_YEAR] |= (1 << ALARM_ENABLE_SHIFT);
-	if (data[RTC_DATE] & 0x1f)
-		data[RTC_DATE] |= (1 << ALARM_ENABLE_SHIFT);
-
-	ret = regmap_bulk_write(info->max77686->rtc_regmap,
-				 MAX77686_ALARM1_SEC, data, RTC_NR_TIME);
 	if (ret < 0) {
-		dev_err(info->dev, "%s: fail to write alarm reg(%d)\n",
-				__func__, ret);
+		dev_err(info->dev, "Fail to write alarm reg(%d)\n", ret);
 		goto out;
 	}
 
@@ -330,7 +578,7 @@ static int max77686_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	u8 data[RTC_NR_TIME];
 	int ret;
 
-	ret = max77686_rtc_tm_to_data(&alrm->time, data);
+	ret = max77686_rtc_tm_to_data(&alrm->time, data, info);
 	if (ret < 0)
 		return ret;
 
@@ -340,12 +588,12 @@ static int max77686_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	if (ret < 0)
 		goto out;
 
-	ret = regmap_bulk_write(info->max77686->rtc_regmap,
-				 MAX77686_ALARM1_SEC, data, RTC_NR_TIME);
+	ret = regmap_bulk_write(info->rtc_regmap,
+				info->drv_data->map[REG_ALARM1_SEC],
+				data, ARRAY_SIZE(data));
 
 	if (ret < 0) {
-		dev_err(info->dev, "%s: fail to write alarm reg(%d)\n",
-				__func__, ret);
+		dev_err(info->dev, "Fail to write alarm reg(%d)\n", ret);
 		goto out;
 	}
 
@@ -361,7 +609,7 @@ out:
 }
 
 static int max77686_rtc_alarm_irq_enable(struct device *dev,
-					unsigned int enabled)
+					 unsigned int enabled)
 {
 	struct max77686_rtc_info *info = dev_get_drvdata(dev);
 	int ret;
@@ -380,7 +628,7 @@ static irqreturn_t max77686_rtc_alarm_irq(int irq, void *data)
 {
 	struct max77686_rtc_info *info = data;
 
-	dev_info(info->dev, "%s:irq(%d)\n", __func__, irq);
+	dev_dbg(info->dev, "RTC alarm IRQ: %d\n", irq);
 
 	rtc_update_irq(info->rtc_dev, 1, RTC_IRQF | RTC_AF);
 
@@ -406,10 +654,11 @@ static int max77686_rtc_init_reg(struct max77686_rtc_info *info)
 
 	info->rtc_24hr_mode = 1;
 
-	ret = regmap_bulk_write(info->max77686->rtc_regmap, MAX77686_RTC_CONTROLM, data, 2);
+	ret = regmap_bulk_write(info->rtc_regmap,
+				info->drv_data->map[REG_RTC_CONTROLM],
+				data, ARRAY_SIZE(data));
 	if (ret < 0) {
-		dev_err(info->dev, "%s: fail to write controlm reg(%d)\n",
-				__func__, ret);
+		dev_err(info->dev, "Fail to write controlm reg(%d)\n", ret);
 		return ret;
 	}
 
@@ -417,28 +666,97 @@ static int max77686_rtc_init_reg(struct max77686_rtc_info *info)
 	return ret;
 }
 
+static const struct regmap_config max77686_rtc_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+};
+
+static int max77686_init_rtc_regmap(struct max77686_rtc_info *info)
+{
+	struct device *parent = info->dev->parent;
+	struct i2c_client *parent_i2c = to_i2c_client(parent);
+	int ret;
+
+	if (info->drv_data->rtc_irq_from_platform) {
+		struct platform_device *pdev = to_platform_device(info->dev);
+
+		info->rtc_irq = platform_get_irq(pdev, 0);
+		if (info->rtc_irq < 0) {
+			dev_err(info->dev, "Failed to get rtc interrupts: %d\n",
+				info->rtc_irq);
+			return info->rtc_irq;
+		}
+	} else {
+		info->rtc_irq =  parent_i2c->irq;
+	}
+
+	info->regmap = dev_get_regmap(parent, NULL);
+	if (!info->regmap) {
+		dev_err(info->dev, "Failed to get rtc regmap\n");
+		return -ENODEV;
+	}
+
+	if (info->drv_data->rtc_i2c_addr == MAX77686_INVALID_I2C_ADDR) {
+		info->rtc_regmap = info->regmap;
+		goto add_rtc_irq;
+	}
+
+	info->rtc = i2c_new_dummy(parent_i2c->adapter,
+				  info->drv_data->rtc_i2c_addr);
+	if (!info->rtc) {
+		dev_err(info->dev, "Failed to allocate I2C device for RTC\n");
+		return -ENODEV;
+	}
+
+	info->rtc_regmap = devm_regmap_init_i2c(info->rtc,
+						&max77686_rtc_regmap_config);
+	if (IS_ERR(info->rtc_regmap)) {
+		ret = PTR_ERR(info->rtc_regmap);
+		dev_err(info->dev, "Failed to allocate RTC regmap: %d\n", ret);
+		goto err_unregister_i2c;
+	}
+
+add_rtc_irq:
+	ret = regmap_add_irq_chip(info->rtc_regmap, info->rtc_irq,
+				  IRQF_TRIGGER_FALLING | IRQF_ONESHOT |
+				  IRQF_SHARED, 0, info->drv_data->rtc_irq_chip,
+				  &info->rtc_irq_data);
+	if (ret < 0) {
+		dev_err(info->dev, "Failed to add RTC irq chip: %d\n", ret);
+		goto err_unregister_i2c;
+	}
+
+	return 0;
+
+err_unregister_i2c:
+	if (info->rtc)
+		i2c_unregister_device(info->rtc);
+	return ret;
+}
+
 static int max77686_rtc_probe(struct platform_device *pdev)
 {
-	struct max77686_dev *max77686 = dev_get_drvdata(pdev->dev.parent);
 	struct max77686_rtc_info *info;
+	const struct platform_device_id *id = platform_get_device_id(pdev);
 	int ret;
 
-	dev_info(&pdev->dev, "%s\n", __func__);
-
 	info = devm_kzalloc(&pdev->dev, sizeof(struct max77686_rtc_info),
-				GFP_KERNEL);
+			    GFP_KERNEL);
 	if (!info)
 		return -ENOMEM;
 
 	mutex_init(&info->lock);
 	info->dev = &pdev->dev;
-	info->max77686 = max77686;
-	info->rtc = max77686->rtc;
+	info->drv_data = (const struct max77686_rtc_driver_data *)
+		id->driver_data;
+
+	ret = max77686_init_rtc_regmap(info);
+	if (ret < 0)
+		return ret;
 
 	platform_set_drvdata(pdev, info);
 
 	ret = max77686_rtc_init_reg(info);
-
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Failed to initialize RTC reg:%d\n", ret);
 		goto err_rtc;
@@ -446,7 +764,7 @@ static int max77686_rtc_probe(struct platform_device *pdev)
 
 	device_init_wakeup(&pdev->dev, 1);
 
-	info->rtc_dev = devm_rtc_device_register(&pdev->dev, "max77686-rtc",
+	info->rtc_dev = devm_rtc_device_register(&pdev->dev, id->name,
 					&max77686_rtc_ops, THIS_MODULE);
 
 	if (IS_ERR(info->rtc_dev)) {
@@ -457,29 +775,43 @@ static int max77686_rtc_probe(struct platform_device *pdev)
 		goto err_rtc;
 	}
 
-	if (!max77686->rtc_irq_data) {
-		ret = -EINVAL;
-		dev_err(&pdev->dev, "%s: no RTC regmap IRQ chip\n", __func__);
-		goto err_rtc;
-	}
-
-	info->virq = regmap_irq_get_virq(max77686->rtc_irq_data,
+	info->virq = regmap_irq_get_virq(info->rtc_irq_data,
 					 MAX77686_RTCIRQ_RTCA1);
-	if (!info->virq) {
+	if (info->virq <= 0) {
 		ret = -ENXIO;
 		goto err_rtc;
 	}
 
-	ret = devm_request_threaded_irq(&pdev->dev, info->virq, NULL,
-				max77686_rtc_alarm_irq, 0, "rtc-alarm1", info);
-	if (ret < 0)
+	ret = request_threaded_irq(info->virq, NULL, max77686_rtc_alarm_irq, 0,
+				   "rtc-alarm1", info);
+	if (ret < 0) {
 		dev_err(&pdev->dev, "Failed to request alarm IRQ: %d: %d\n",
 			info->virq, ret);
+		goto err_rtc;
+	}
+
+	return 0;
 
 err_rtc:
+	regmap_del_irq_chip(info->rtc_irq, info->rtc_irq_data);
+	if (info->rtc)
+		i2c_unregister_device(info->rtc);
+
 	return ret;
 }
 
+static int max77686_rtc_remove(struct platform_device *pdev)
+{
+	struct max77686_rtc_info *info = platform_get_drvdata(pdev);
+
+	free_irq(info->virq, info);
+	regmap_del_irq_chip(info->rtc_irq, info->rtc_irq_data);
+	if (info->rtc)
+		i2c_unregister_device(info->rtc);
+
+	return 0;
+}
+
 #ifdef CONFIG_PM_SLEEP
 static int max77686_rtc_suspend(struct device *dev)
 {
@@ -508,7 +840,9 @@ static SIMPLE_DEV_PM_OPS(max77686_rtc_pm_ops,
 			 max77686_rtc_suspend, max77686_rtc_resume);
 
 static const struct platform_device_id rtc_id[] = {
-	{ "max77686-rtc", 0 },
+	{ "max77686-rtc", .driver_data = (kernel_ulong_t)&max77686_drv_data, },
+	{ "max77802-rtc", .driver_data = (kernel_ulong_t)&max77802_drv_data, },
+	{ "max77620-rtc", .driver_data = (kernel_ulong_t)&max77620_drv_data, },
 	{},
 };
 MODULE_DEVICE_TABLE(platform, rtc_id);
@@ -519,6 +853,7 @@ static struct platform_driver max77686_rtc_driver = {
 		.pm	= &max77686_rtc_pm_ops,
 	},
 	.probe		= max77686_rtc_probe,
+	.remove		= max77686_rtc_remove,
 	.id_table	= rtc_id,
 };
 
diff --git a/drivers/rtc/rtc-max77802.c b/drivers/rtc/rtc-max77802.c
deleted file mode 100644
index 82ffcc5a5345..000000000000
--- a/drivers/rtc/rtc-max77802.c
+++ /dev/null
@@ -1,502 +0,0 @@
-/*
- * RTC driver for Maxim MAX77802
- *
- * Copyright (C) 2013 Google, Inc
- *
- * Copyright (C) 2012 Samsung Electronics Co.Ltd
- *
- *  based on rtc-max8997.c
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- */
-
-#include <linux/slab.h>
-#include <linux/rtc.h>
-#include <linux/delay.h>
-#include <linux/mutex.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/mfd/max77686-private.h>
-#include <linux/irqdomain.h>
-#include <linux/regmap.h>
-
-/* RTC Control Register */
-#define BCD_EN_SHIFT			0
-#define BCD_EN_MASK			(1 << BCD_EN_SHIFT)
-#define MODEL24_SHIFT			1
-#define MODEL24_MASK			(1 << MODEL24_SHIFT)
-/* RTC Update Register1 */
-#define RTC_UDR_SHIFT			0
-#define RTC_UDR_MASK			(1 << RTC_UDR_SHIFT)
-#define RTC_RBUDR_SHIFT			4
-#define RTC_RBUDR_MASK			(1 << RTC_RBUDR_SHIFT)
-/* RTC Hour register */
-#define HOUR_PM_SHIFT			6
-#define HOUR_PM_MASK			(1 << HOUR_PM_SHIFT)
-/* RTC Alarm Enable */
-#define ALARM_ENABLE_SHIFT		7
-#define ALARM_ENABLE_MASK		(1 << ALARM_ENABLE_SHIFT)
-
-/* For the RTCAE1 register, we write this value to enable the alarm */
-#define ALARM_ENABLE_VALUE		0x77
-
-#define MAX77802_RTC_UPDATE_DELAY_US	200
-
-enum {
-	RTC_SEC = 0,
-	RTC_MIN,
-	RTC_HOUR,
-	RTC_WEEKDAY,
-	RTC_MONTH,
-	RTC_YEAR,
-	RTC_DATE,
-	RTC_NR_TIME
-};
-
-struct max77802_rtc_info {
-	struct device		*dev;
-	struct max77686_dev	*max77802;
-	struct i2c_client	*rtc;
-	struct rtc_device	*rtc_dev;
-	struct mutex		lock;
-
-	struct regmap		*regmap;
-
-	int virq;
-	int rtc_24hr_mode;
-};
-
-enum MAX77802_RTC_OP {
-	MAX77802_RTC_WRITE,
-	MAX77802_RTC_READ,
-};
-
-static void max77802_rtc_data_to_tm(u8 *data, struct rtc_time *tm,
-				   int rtc_24hr_mode)
-{
-	tm->tm_sec = data[RTC_SEC] & 0xff;
-	tm->tm_min = data[RTC_MIN] & 0xff;
-	if (rtc_24hr_mode)
-		tm->tm_hour = data[RTC_HOUR] & 0x1f;
-	else {
-		tm->tm_hour = data[RTC_HOUR] & 0x0f;
-		if (data[RTC_HOUR] & HOUR_PM_MASK)
-			tm->tm_hour += 12;
-	}
-
-	/* Only a single bit is set in data[], so fls() would be equivalent */
-	tm->tm_wday = ffs(data[RTC_WEEKDAY] & 0xff) - 1;
-	tm->tm_mday = data[RTC_DATE] & 0x1f;
-	tm->tm_mon = (data[RTC_MONTH] & 0x0f) - 1;
-
-	tm->tm_year = data[RTC_YEAR] & 0xff;
-	tm->tm_yday = 0;
-	tm->tm_isdst = 0;
-}
-
-static int max77802_rtc_tm_to_data(struct rtc_time *tm, u8 *data)
-{
-	data[RTC_SEC] = tm->tm_sec;
-	data[RTC_MIN] = tm->tm_min;
-	data[RTC_HOUR] = tm->tm_hour;
-	data[RTC_WEEKDAY] = 1 << tm->tm_wday;
-	data[RTC_DATE] = tm->tm_mday;
-	data[RTC_MONTH] = tm->tm_mon + 1;
-	data[RTC_YEAR] = tm->tm_year;
-
-	return 0;
-}
-
-static int max77802_rtc_update(struct max77802_rtc_info *info,
-	enum MAX77802_RTC_OP op)
-{
-	int ret;
-	unsigned int data;
-
-	if (op == MAX77802_RTC_WRITE)
-		data = 1 << RTC_UDR_SHIFT;
-	else
-		data = 1 << RTC_RBUDR_SHIFT;
-
-	ret = regmap_update_bits(info->max77802->regmap,
-				 MAX77802_RTC_UPDATE0, data, data);
-	if (ret < 0)
-		dev_err(info->dev, "%s: fail to write update reg(ret=%d, data=0x%x)\n",
-				__func__, ret, data);
-	else {
-		/* Minimum delay required before RTC update. */
-		usleep_range(MAX77802_RTC_UPDATE_DELAY_US,
-			     MAX77802_RTC_UPDATE_DELAY_US * 2);
-	}
-
-	return ret;
-}
-
-static int max77802_rtc_read_time(struct device *dev, struct rtc_time *tm)
-{
-	struct max77802_rtc_info *info = dev_get_drvdata(dev);
-	u8 data[RTC_NR_TIME];
-	int ret;
-
-	mutex_lock(&info->lock);
-
-	ret = max77802_rtc_update(info, MAX77802_RTC_READ);
-	if (ret < 0)
-		goto out;
-
-	ret = regmap_bulk_read(info->max77802->regmap,
-				MAX77802_RTC_SEC, data, RTC_NR_TIME);
-	if (ret < 0) {
-		dev_err(info->dev, "%s: fail to read time reg(%d)\n", __func__,
-			ret);
-		goto out;
-	}
-
-	max77802_rtc_data_to_tm(data, tm, info->rtc_24hr_mode);
-
-	ret = rtc_valid_tm(tm);
-
-out:
-	mutex_unlock(&info->lock);
-	return ret;
-}
-
-static int max77802_rtc_set_time(struct device *dev, struct rtc_time *tm)
-{
-	struct max77802_rtc_info *info = dev_get_drvdata(dev);
-	u8 data[RTC_NR_TIME];
-	int ret;
-
-	ret = max77802_rtc_tm_to_data(tm, data);
-	if (ret < 0)
-		return ret;
-
-	mutex_lock(&info->lock);
-
-	ret = regmap_bulk_write(info->max77802->regmap,
-				 MAX77802_RTC_SEC, data, RTC_NR_TIME);
-	if (ret < 0) {
-		dev_err(info->dev, "%s: fail to write time reg(%d)\n", __func__,
-			ret);
-		goto out;
-	}
-
-	ret = max77802_rtc_update(info, MAX77802_RTC_WRITE);
-
-out:
-	mutex_unlock(&info->lock);
-	return ret;
-}
-
-static int max77802_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
-{
-	struct max77802_rtc_info *info = dev_get_drvdata(dev);
-	u8 data[RTC_NR_TIME];
-	unsigned int val;
-	int ret;
-
-	mutex_lock(&info->lock);
-
-	ret = max77802_rtc_update(info, MAX77802_RTC_READ);
-	if (ret < 0)
-		goto out;
-
-	ret = regmap_bulk_read(info->max77802->regmap,
-				 MAX77802_ALARM1_SEC, data, RTC_NR_TIME);
-	if (ret < 0) {
-		dev_err(info->dev, "%s:%d fail to read alarm reg(%d)\n",
-				__func__, __LINE__, ret);
-		goto out;
-	}
-
-	max77802_rtc_data_to_tm(data, &alrm->time, info->rtc_24hr_mode);
-
-	alrm->enabled = 0;
-	ret = regmap_read(info->max77802->regmap,
-			  MAX77802_RTC_AE1, &val);
-	if (ret < 0) {
-		dev_err(info->dev, "%s:%d fail to read alarm enable(%d)\n",
-			__func__, __LINE__, ret);
-		goto out;
-	}
-	if (val)
-		alrm->enabled = 1;
-
-	alrm->pending = 0;
-	ret = regmap_read(info->max77802->regmap, MAX77802_REG_STATUS2, &val);
-	if (ret < 0) {
-		dev_err(info->dev, "%s:%d fail to read status2 reg(%d)\n",
-				__func__, __LINE__, ret);
-		goto out;
-	}
-
-	if (val & (1 << 2)) /* RTCA1 */
-		alrm->pending = 1;
-
-out:
-	mutex_unlock(&info->lock);
-	return 0;
-}
-
-static int max77802_rtc_stop_alarm(struct max77802_rtc_info *info)
-{
-	int ret;
-
-	if (!mutex_is_locked(&info->lock))
-		dev_warn(info->dev, "%s: should have mutex locked\n", __func__);
-
-	ret = max77802_rtc_update(info, MAX77802_RTC_READ);
-	if (ret < 0)
-		goto out;
-
-	ret = regmap_write(info->max77802->regmap,
-			   MAX77802_RTC_AE1, 0);
-	if (ret < 0) {
-		dev_err(info->dev, "%s: fail to write alarm reg(%d)\n",
-			__func__, ret);
-		goto out;
-	}
-
-	ret = max77802_rtc_update(info, MAX77802_RTC_WRITE);
-out:
-	return ret;
-}
-
-static int max77802_rtc_start_alarm(struct max77802_rtc_info *info)
-{
-	int ret;
-
-	if (!mutex_is_locked(&info->lock))
-		dev_warn(info->dev, "%s: should have mutex locked\n",
-			 __func__);
-
-	ret = max77802_rtc_update(info, MAX77802_RTC_READ);
-	if (ret < 0)
-		goto out;
-
-	ret = regmap_write(info->max77802->regmap,
-				   MAX77802_RTC_AE1,
-				   ALARM_ENABLE_VALUE);
-
-	if (ret < 0) {
-		dev_err(info->dev, "%s: fail to read alarm reg(%d)\n",
-				__func__, ret);
-		goto out;
-	}
-
-	ret = max77802_rtc_update(info, MAX77802_RTC_WRITE);
-out:
-	return ret;
-}
-
-static int max77802_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
-{
-	struct max77802_rtc_info *info = dev_get_drvdata(dev);
-	u8 data[RTC_NR_TIME];
-	int ret;
-
-	ret = max77802_rtc_tm_to_data(&alrm->time, data);
-	if (ret < 0)
-		return ret;
-
-	mutex_lock(&info->lock);
-
-	ret = max77802_rtc_stop_alarm(info);
-	if (ret < 0)
-		goto out;
-
-	ret = regmap_bulk_write(info->max77802->regmap,
-				 MAX77802_ALARM1_SEC, data, RTC_NR_TIME);
-
-	if (ret < 0) {
-		dev_err(info->dev, "%s: fail to write alarm reg(%d)\n",
-				__func__, ret);
-		goto out;
-	}
-
-	ret = max77802_rtc_update(info, MAX77802_RTC_WRITE);
-	if (ret < 0)
-		goto out;
-
-	if (alrm->enabled)
-		ret = max77802_rtc_start_alarm(info);
-out:
-	mutex_unlock(&info->lock);
-	return ret;
-}
-
-static int max77802_rtc_alarm_irq_enable(struct device *dev,
-					 unsigned int enabled)
-{
-	struct max77802_rtc_info *info = dev_get_drvdata(dev);
-	int ret;
-
-	mutex_lock(&info->lock);
-	if (enabled)
-		ret = max77802_rtc_start_alarm(info);
-	else
-		ret = max77802_rtc_stop_alarm(info);
-	mutex_unlock(&info->lock);
-
-	return ret;
-}
-
-static irqreturn_t max77802_rtc_alarm_irq(int irq, void *data)
-{
-	struct max77802_rtc_info *info = data;
-
-	dev_dbg(info->dev, "%s:irq(%d)\n", __func__, irq);
-
-	rtc_update_irq(info->rtc_dev, 1, RTC_IRQF | RTC_AF);
-
-	return IRQ_HANDLED;
-}
-
-static const struct rtc_class_ops max77802_rtc_ops = {
-	.read_time = max77802_rtc_read_time,
-	.set_time = max77802_rtc_set_time,
-	.read_alarm = max77802_rtc_read_alarm,
-	.set_alarm = max77802_rtc_set_alarm,
-	.alarm_irq_enable = max77802_rtc_alarm_irq_enable,
-};
-
-static int max77802_rtc_init_reg(struct max77802_rtc_info *info)
-{
-	u8 data[2];
-	int ret;
-
-	max77802_rtc_update(info, MAX77802_RTC_READ);
-
-	/* Set RTC control register : Binary mode, 24hour mdoe */
-	data[0] = (1 << BCD_EN_SHIFT) | (1 << MODEL24_SHIFT);
-	data[1] = (0 << BCD_EN_SHIFT) | (1 << MODEL24_SHIFT);
-
-	info->rtc_24hr_mode = 1;
-
-	ret = regmap_bulk_write(info->max77802->regmap,
-				MAX77802_RTC_CONTROLM, data, ARRAY_SIZE(data));
-	if (ret < 0) {
-		dev_err(info->dev, "%s: fail to write controlm reg(%d)\n",
-				__func__, ret);
-		return ret;
-	}
-
-	ret = max77802_rtc_update(info, MAX77802_RTC_WRITE);
-	return ret;
-}
-
-static int max77802_rtc_probe(struct platform_device *pdev)
-{
-	struct max77686_dev *max77802 = dev_get_drvdata(pdev->dev.parent);
-	struct max77802_rtc_info *info;
-	int ret;
-
-	dev_dbg(&pdev->dev, "%s\n", __func__);
-
-	info = devm_kzalloc(&pdev->dev, sizeof(struct max77802_rtc_info),
-			    GFP_KERNEL);
-	if (!info)
-		return -ENOMEM;
-
-	mutex_init(&info->lock);
-	info->dev = &pdev->dev;
-	info->max77802 = max77802;
-	info->rtc = max77802->i2c;
-
-	platform_set_drvdata(pdev, info);
-
-	ret = max77802_rtc_init_reg(info);
-
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to initialize RTC reg:%d\n", ret);
-		return ret;
-	}
-
-	device_init_wakeup(&pdev->dev, 1);
-
-	info->rtc_dev = devm_rtc_device_register(&pdev->dev, "max77802-rtc",
-						 &max77802_rtc_ops, THIS_MODULE);
-
-	if (IS_ERR(info->rtc_dev)) {
-		ret = PTR_ERR(info->rtc_dev);
-		dev_err(&pdev->dev, "Failed to register RTC device: %d\n", ret);
-		if (ret == 0)
-			ret = -EINVAL;
-		return ret;
-	}
-
-	if (!max77802->rtc_irq_data) {
-		dev_err(&pdev->dev, "No RTC regmap IRQ chip\n");
-		return -EINVAL;
-	}
-
-	info->virq = regmap_irq_get_virq(max77802->rtc_irq_data,
-					 MAX77686_RTCIRQ_RTCA1);
-
-	if (info->virq <= 0) {
-		dev_err(&pdev->dev, "Failed to get virtual IRQ %d\n",
-			MAX77686_RTCIRQ_RTCA1);
-		return -EINVAL;
-	}
-
-	ret = devm_request_threaded_irq(&pdev->dev, info->virq, NULL,
-					max77802_rtc_alarm_irq, 0, "rtc-alarm1",
-					info);
-	if (ret < 0)
-		dev_err(&pdev->dev, "Failed to request alarm IRQ: %d: %d\n",
-			info->virq, ret);
-
-	return ret;
-}
-
-#ifdef CONFIG_PM_SLEEP
-static int max77802_rtc_suspend(struct device *dev)
-{
-	if (device_may_wakeup(dev)) {
-		struct max77802_rtc_info *info = dev_get_drvdata(dev);
-
-		return enable_irq_wake(info->virq);
-	}
-
-	return 0;
-}
-
-static int max77802_rtc_resume(struct device *dev)
-{
-	if (device_may_wakeup(dev)) {
-		struct max77802_rtc_info *info = dev_get_drvdata(dev);
-
-		return disable_irq_wake(info->virq);
-	}
-
-	return 0;
-}
-#endif
-
-static SIMPLE_DEV_PM_OPS(max77802_rtc_pm_ops,
-			 max77802_rtc_suspend, max77802_rtc_resume);
-
-static const struct platform_device_id rtc_id[] = {
-	{ "max77802-rtc", 0 },
-	{},
-};
-MODULE_DEVICE_TABLE(platform, rtc_id);
-
-static struct platform_driver max77802_rtc_driver = {
-	.driver		= {
-		.name	= "max77802-rtc",
-		.pm	= &max77802_rtc_pm_ops,
-	},
-	.probe		= max77802_rtc_probe,
-	.id_table	= rtc_id,
-};
-
-module_platform_driver(max77802_rtc_driver);
-
-MODULE_DESCRIPTION("Maxim MAX77802 RTC driver");
-MODULE_AUTHOR("Simon Glass <sjg@chromium.org>");
-MODULE_LICENSE("GPL");
diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c
index 06a5c52b292f..44f622c3e048 100644
--- a/drivers/rtc/rtc-mt6397.c
+++ b/drivers/rtc/rtc-mt6397.c
@@ -419,4 +419,3 @@ module_platform_driver(mtk_rtc_driver);
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Tianping Fang <tianping.fang@mediatek.com>");
 MODULE_DESCRIPTION("RTC Driver for MediaTek MT6397 PMIC");
-MODULE_ALIAS("platform:mt6397-rtc");
diff --git a/drivers/rtc/rtc-palmas.c b/drivers/rtc/rtc-palmas.c
index 7ea2c471feca..6080e0edef63 100644
--- a/drivers/rtc/rtc-palmas.c
+++ b/drivers/rtc/rtc-palmas.c
@@ -311,8 +311,7 @@ static int palmas_rtc_probe(struct platform_device *pdev)
 
 	ret = devm_request_threaded_irq(&pdev->dev, palmas_rtc->irq, NULL,
 			palmas_rtc_interrupt,
-			IRQF_TRIGGER_LOW | IRQF_ONESHOT |
-			IRQF_EARLY_RESUME,
+			IRQF_TRIGGER_LOW | IRQF_ONESHOT,
 			dev_name(&pdev->dev), palmas_rtc);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "IRQ request failed, err = %d\n", ret);
diff --git a/drivers/rtc/rtc-pcf2123.c b/drivers/rtc/rtc-pcf2123.c
index ea8a31c91641..da27738b1242 100644
--- a/drivers/rtc/rtc-pcf2123.c
+++ b/drivers/rtc/rtc-pcf2123.c
@@ -48,6 +48,7 @@
 
 #define DRV_VERSION "0.6"
 
+/* REGISTERS */
 #define PCF2123_REG_CTRL1	(0x00)	/* Control Register 1 */
 #define PCF2123_REG_CTRL2	(0x01)	/* Control Register 2 */
 #define PCF2123_REG_SC		(0x02)	/* datetime */
@@ -57,10 +58,54 @@
 #define PCF2123_REG_DW		(0x06)
 #define PCF2123_REG_MO		(0x07)
 #define PCF2123_REG_YR		(0x08)
+#define PCF2123_REG_ALRM_MN	(0x09)	/* Alarm Registers */
+#define PCF2123_REG_ALRM_HR	(0x0a)
+#define PCF2123_REG_ALRM_DM	(0x0b)
+#define PCF2123_REG_ALRM_DW	(0x0c)
+#define PCF2123_REG_OFFSET	(0x0d)	/* Clock Rate Offset Register */
+#define PCF2123_REG_TMR_CLKOUT	(0x0e)	/* Timer Registers */
+#define PCF2123_REG_CTDWN_TMR	(0x0f)
+
+/* PCF2123_REG_CTRL1 BITS */
+#define CTRL1_CLEAR		(0)	/* Clear */
+#define CTRL1_CORR_INT		BIT(1)	/* Correction irq enable */
+#define CTRL1_12_HOUR		BIT(2)	/* 12 hour time */
+#define CTRL1_SW_RESET	(BIT(3) | BIT(4) | BIT(6))	/* Software reset */
+#define CTRL1_STOP		BIT(5)	/* Stop the clock */
+#define CTRL1_EXT_TEST		BIT(7)	/* External clock test mode */
+
+/* PCF2123_REG_CTRL2 BITS */
+#define CTRL2_TIE		BIT(0)	/* Countdown timer irq enable */
+#define CTRL2_AIE		BIT(1)	/* Alarm irq enable */
+#define CTRL2_TF		BIT(2)	/* Countdown timer flag */
+#define CTRL2_AF		BIT(3)	/* Alarm flag */
+#define CTRL2_TI_TP		BIT(4)	/* Irq pin generates pulse */
+#define CTRL2_MSF		BIT(5)	/* Minute or second irq flag */
+#define CTRL2_SI		BIT(6)	/* Second irq enable */
+#define CTRL2_MI		BIT(7)	/* Minute irq enable */
+
+/* PCF2123_REG_SC BITS */
+#define OSC_HAS_STOPPED		BIT(7)	/* Clock has been stopped */
+
+/* PCF2123_REG_ALRM_XX BITS */
+#define ALRM_ENABLE		BIT(7)	/* MN, HR, DM, or DW alarm enable */
+
+/* PCF2123_REG_TMR_CLKOUT BITS */
+#define CD_TMR_4096KHZ		(0)	/* 4096 KHz countdown timer */
+#define CD_TMR_64HZ		(1)	/* 64 Hz countdown timer */
+#define CD_TMR_1HZ		(2)	/* 1 Hz countdown timer */
+#define CD_TMR_60th_HZ		(3)	/* 60th Hz countdown timer */
+#define CD_TMR_TE		BIT(3)	/* Countdown timer enable */
+
+/* PCF2123_REG_OFFSET BITS */
+#define OFFSET_SIGN_BIT		BIT(6)	/* 2's complement sign bit */
+#define OFFSET_COARSE		BIT(7)	/* Coarse mode offset */
+#define OFFSET_STEP		(2170)	/* Offset step in parts per billion */
+
+/* READ/WRITE ADDRESS BITS */
+#define PCF2123_WRITE		BIT(4)
+#define PCF2123_READ		(BIT(4) | BIT(7))
 
-#define PCF2123_SUBADDR		(1 << 4)
-#define PCF2123_WRITE		((0 << 7) | PCF2123_SUBADDR)
-#define PCF2123_READ		((1 << 7) | PCF2123_SUBADDR)
 
 static struct spi_driver pcf2123_driver;
 
@@ -84,12 +129,44 @@ static inline void pcf2123_delay_trec(void)
 	ndelay(30);
 }
 
+static int pcf2123_read(struct device *dev, u8 reg, u8 *rxbuf, size_t size)
+{
+	struct spi_device *spi = to_spi_device(dev);
+	int ret;
+
+	reg |= PCF2123_READ;
+	ret = spi_write_then_read(spi, &reg, 1, rxbuf, size);
+	pcf2123_delay_trec();
+
+	return ret;
+}
+
+static int pcf2123_write(struct device *dev, u8 *txbuf, size_t size)
+{
+	struct spi_device *spi = to_spi_device(dev);
+	int ret;
+
+	txbuf[0] |= PCF2123_WRITE;
+	ret = spi_write(spi, txbuf, size);
+	pcf2123_delay_trec();
+
+	return ret;
+}
+
+static int pcf2123_write_reg(struct device *dev, u8 reg, u8 val)
+{
+	u8 txbuf[2];
+
+	txbuf[0] = reg;
+	txbuf[1] = val;
+	return pcf2123_write(dev, txbuf, sizeof(txbuf));
+}
+
 static ssize_t pcf2123_show(struct device *dev, struct device_attribute *attr,
 			    char *buffer)
 {
-	struct spi_device *spi = to_spi_device(dev);
 	struct pcf2123_sysfs_reg *r;
-	u8 txbuf[1], rxbuf[1];
+	u8 rxbuf[1];
 	unsigned long reg;
 	int ret;
 
@@ -99,19 +176,16 @@ static ssize_t pcf2123_show(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
-	txbuf[0] = PCF2123_READ | reg;
-	ret = spi_write_then_read(spi, txbuf, 1, rxbuf, 1);
+	ret = pcf2123_read(dev, reg, rxbuf, 1);
 	if (ret < 0)
 		return -EIO;
-	pcf2123_delay_trec();
+
 	return sprintf(buffer, "0x%x\n", rxbuf[0]);
 }
 
 static ssize_t pcf2123_store(struct device *dev, struct device_attribute *attr,
 			     const char *buffer, size_t count) {
-	struct spi_device *spi = to_spi_device(dev);
 	struct pcf2123_sysfs_reg *r;
-	u8 txbuf[2];
 	unsigned long reg;
 	unsigned long val;
 
@@ -127,27 +201,78 @@ static ssize_t pcf2123_store(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
-	txbuf[0] = PCF2123_WRITE | reg;
-	txbuf[1] = val;
-	ret = spi_write(spi, txbuf, sizeof(txbuf));
+	pcf2123_write_reg(dev, reg, val);
 	if (ret < 0)
 		return -EIO;
-	pcf2123_delay_trec();
 	return count;
 }
 
+static int pcf2123_read_offset(struct device *dev, long *offset)
+{
+	int ret;
+	s8 reg;
+
+	ret = pcf2123_read(dev, PCF2123_REG_OFFSET, &reg, 1);
+	if (ret < 0)
+		return ret;
+
+	if (reg & OFFSET_COARSE)
+		reg <<= 1; /* multiply by 2 and sign extend */
+	else
+		reg |= (reg & OFFSET_SIGN_BIT) << 1; /* sign extend only */
+
+	*offset = ((long)reg) * OFFSET_STEP;
+
+	return 0;
+}
+
+/*
+ * The offset register is a 7 bit signed value with a coarse bit in bit 7.
+ * The main difference between the two is normal offset adjusts the first
+ * second of n minutes every other hour, with 61, 62 and 63 being shoved
+ * into the 60th minute.
+ * The coarse adjustment does the same, but every hour.
+ * the two overlap, with every even normal offset value corresponding
+ * to a coarse offset. Based on this algorithm, it seems that despite the
+ * name, coarse offset is a better fit for overlapping values.
+ */
+static int pcf2123_set_offset(struct device *dev, long offset)
+{
+	s8 reg;
+
+	if (offset > OFFSET_STEP * 127)
+		reg = 127;
+	else if (offset < OFFSET_STEP * -128)
+		reg = -128;
+	else
+		reg = (s8)((offset + (OFFSET_STEP >> 1)) / OFFSET_STEP);
+
+	/* choose fine offset only for odd values in the normal range */
+	if (reg & 1 && reg <= 63 && reg >= -64) {
+		/* Normal offset. Clear the coarse bit */
+		reg &= ~OFFSET_COARSE;
+	} else {
+		/* Coarse offset. Divide by 2 and set the coarse bit */
+		reg >>= 1;
+		reg |= OFFSET_COARSE;
+	}
+
+	return pcf2123_write_reg(dev, PCF2123_REG_OFFSET, reg);
+}
+
 static int pcf2123_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
-	struct spi_device *spi = to_spi_device(dev);
-	u8 txbuf[1], rxbuf[7];
+	u8 rxbuf[7];
 	int ret;
 
-	txbuf[0] = PCF2123_READ | PCF2123_REG_SC;
-	ret = spi_write_then_read(spi, txbuf, sizeof(txbuf),
-			rxbuf, sizeof(rxbuf));
+	ret = pcf2123_read(dev, PCF2123_REG_SC, rxbuf, sizeof(rxbuf));
 	if (ret < 0)
 		return ret;
-	pcf2123_delay_trec();
+
+	if (rxbuf[0] & OSC_HAS_STOPPED) {
+		dev_info(dev, "clock was stopped. Time is not valid\n");
+		return -EINVAL;
+	}
 
 	tm->tm_sec = bcd2bin(rxbuf[0] & 0x7F);
 	tm->tm_min = bcd2bin(rxbuf[1] & 0x7F);
@@ -170,7 +295,6 @@ static int pcf2123_rtc_read_time(struct device *dev, struct rtc_time *tm)
 
 static int pcf2123_rtc_set_time(struct device *dev, struct rtc_time *tm)
 {
-	struct spi_device *spi = to_spi_device(dev);
 	u8 txbuf[8];
 	int ret;
 
@@ -181,15 +305,12 @@ static int pcf2123_rtc_set_time(struct device *dev, struct rtc_time *tm)
 			tm->tm_mday, tm->tm_mon, tm->tm_year, tm->tm_wday);
 
 	/* Stop the counter first */
-	txbuf[0] = PCF2123_WRITE | PCF2123_REG_CTRL1;
-	txbuf[1] = 0x20;
-	ret = spi_write(spi, txbuf, 2);
+	ret = pcf2123_write_reg(dev, PCF2123_REG_CTRL1, CTRL1_STOP);
 	if (ret < 0)
 		return ret;
-	pcf2123_delay_trec();
 
 	/* Set the new time */
-	txbuf[0] = PCF2123_WRITE | PCF2123_REG_SC;
+	txbuf[0] = PCF2123_REG_SC;
 	txbuf[1] = bin2bcd(tm->tm_sec & 0x7F);
 	txbuf[2] = bin2bcd(tm->tm_min & 0x7F);
 	txbuf[3] = bin2bcd(tm->tm_hour & 0x3F);
@@ -198,18 +319,48 @@ static int pcf2123_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	txbuf[6] = bin2bcd((tm->tm_mon + 1) & 0x1F); /* rtc mn 1-12 */
 	txbuf[7] = bin2bcd(tm->tm_year < 100 ? tm->tm_year : tm->tm_year - 100);
 
-	ret = spi_write(spi, txbuf, sizeof(txbuf));
+	ret = pcf2123_write(dev, txbuf, sizeof(txbuf));
 	if (ret < 0)
 		return ret;
-	pcf2123_delay_trec();
 
 	/* Start the counter */
-	txbuf[0] = PCF2123_WRITE | PCF2123_REG_CTRL1;
-	txbuf[1] = 0x00;
-	ret = spi_write(spi, txbuf, 2);
+	ret = pcf2123_write_reg(dev, PCF2123_REG_CTRL1, CTRL1_CLEAR);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int pcf2123_reset(struct device *dev)
+{
+	int ret;
+	u8  rxbuf[2];
+
+	ret = pcf2123_write_reg(dev, PCF2123_REG_CTRL1, CTRL1_SW_RESET);
+	if (ret < 0)
+		return ret;
+
+	/* Stop the counter */
+	dev_dbg(dev, "stopping RTC\n");
+	ret = pcf2123_write_reg(dev, PCF2123_REG_CTRL1, CTRL1_STOP);
+	if (ret < 0)
+		return ret;
+
+	/* See if the counter was actually stopped */
+	dev_dbg(dev, "checking for presence of RTC\n");
+	ret = pcf2123_read(dev, PCF2123_REG_CTRL1, rxbuf, sizeof(rxbuf));
+	if (ret < 0)
+		return ret;
+
+	dev_dbg(dev, "received data from RTC (0x%02X 0x%02X)\n",
+		rxbuf[0], rxbuf[1]);
+	if (!(rxbuf[0] & CTRL1_STOP))
+		return -ENODEV;
+
+	/* Start the counter */
+	ret = pcf2123_write_reg(dev, PCF2123_REG_CTRL1, CTRL1_CLEAR);
 	if (ret < 0)
 		return ret;
-	pcf2123_delay_trec();
 
 	return 0;
 }
@@ -217,13 +368,16 @@ static int pcf2123_rtc_set_time(struct device *dev, struct rtc_time *tm)
 static const struct rtc_class_ops pcf2123_rtc_ops = {
 	.read_time	= pcf2123_rtc_read_time,
 	.set_time	= pcf2123_rtc_set_time,
+	.read_offset	= pcf2123_read_offset,
+	.set_offset	= pcf2123_set_offset,
+
 };
 
 static int pcf2123_probe(struct spi_device *spi)
 {
 	struct rtc_device *rtc;
+	struct rtc_time tm;
 	struct pcf2123_plat_data *pdata;
-	u8 txbuf[2], rxbuf[2];
 	int ret, i;
 
 	pdata = devm_kzalloc(&spi->dev, sizeof(struct pcf2123_plat_data),
@@ -232,56 +386,19 @@ static int pcf2123_probe(struct spi_device *spi)
 		return -ENOMEM;
 	spi->dev.platform_data = pdata;
 
-	/* Send a software reset command */
-	txbuf[0] = PCF2123_WRITE | PCF2123_REG_CTRL1;
-	txbuf[1] = 0x58;
-	dev_dbg(&spi->dev, "resetting RTC (0x%02X 0x%02X)\n",
-			txbuf[0], txbuf[1]);
-	ret = spi_write(spi, txbuf, 2 * sizeof(u8));
-	if (ret < 0)
-		goto kfree_exit;
-	pcf2123_delay_trec();
-
-	/* Stop the counter */
-	txbuf[0] = PCF2123_WRITE | PCF2123_REG_CTRL1;
-	txbuf[1] = 0x20;
-	dev_dbg(&spi->dev, "stopping RTC (0x%02X 0x%02X)\n",
-			txbuf[0], txbuf[1]);
-	ret = spi_write(spi, txbuf, 2 * sizeof(u8));
-	if (ret < 0)
-		goto kfree_exit;
-	pcf2123_delay_trec();
-
-	/* See if the counter was actually stopped */
-	txbuf[0] = PCF2123_READ | PCF2123_REG_CTRL1;
-	dev_dbg(&spi->dev, "checking for presence of RTC (0x%02X)\n",
-			txbuf[0]);
-	ret = spi_write_then_read(spi, txbuf, 1 * sizeof(u8),
-					rxbuf, 2 * sizeof(u8));
-	dev_dbg(&spi->dev, "received data from RTC (0x%02X 0x%02X)\n",
-			rxbuf[0], rxbuf[1]);
-	if (ret < 0)
-		goto kfree_exit;
-	pcf2123_delay_trec();
-
-	if (!(rxbuf[0] & 0x20)) {
-		dev_err(&spi->dev, "chip not found\n");
-		ret = -ENODEV;
-		goto kfree_exit;
+	ret = pcf2123_rtc_read_time(&spi->dev, &tm);
+	if (ret < 0) {
+		ret = pcf2123_reset(&spi->dev);
+		if (ret < 0) {
+			dev_err(&spi->dev, "chip not found\n");
+			goto kfree_exit;
+		}
 	}
 
 	dev_info(&spi->dev, "chip found, driver version " DRV_VERSION "\n");
 	dev_info(&spi->dev, "spiclk %u KHz.\n",
 			(spi->max_speed_hz + 500) / 1000);
 
-	/* Start the counter */
-	txbuf[0] = PCF2123_WRITE | PCF2123_REG_CTRL1;
-	txbuf[1] = 0x00;
-	ret = spi_write(spi, txbuf, sizeof(txbuf));
-	if (ret < 0)
-		goto kfree_exit;
-	pcf2123_delay_trec();
-
 	/* Finalize the initialization */
 	rtc = devm_rtc_device_register(&spi->dev, pcf2123_driver.driver.name,
 			&pcf2123_rtc_ops, THIS_MODULE);
diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 629bfdf8c745..2bfdf638b673 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -1,12 +1,12 @@
 /*
- * An I2C driver for the NXP PCF2127 RTC
+ * An I2C and SPI driver for the NXP PCF2127/29 RTC
  * Copyright 2013 Til-Technologies
  *
  * Author: Renaud Cerrato <r.cerrato@til-technologies.fr>
  *
  * based on the other drivers in this same directory.
  *
- * http://www.nxp.com/documents/data_sheet/PCF2127AT.pdf
+ * Datasheet: http://cache.nxp.com/documents/data_sheet/PCF2127.pdf
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -14,11 +14,13 @@
  */
 
 #include <linux/i2c.h>
+#include <linux/spi/spi.h>
 #include <linux/bcd.h>
 #include <linux/rtc.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/regmap.h>
 
 #define PCF2127_REG_CTRL1       (0x00)  /* Control Register 1 */
 #define PCF2127_REG_CTRL2       (0x01)  /* Control Register 2 */
@@ -36,29 +38,30 @@
 
 #define PCF2127_OSF             BIT(7)  /* Oscillator Fail flag */
 
-static struct i2c_driver pcf2127_driver;
-
 struct pcf2127 {
 	struct rtc_device *rtc;
+	struct regmap *regmap;
 };
 
 /*
  * In the routines that deal directly with the pcf2127 hardware, we use
  * rtc_time -- month 0-11, hour 0-23, yr = calendar year-epoch.
  */
-static int pcf2127_get_datetime(struct i2c_client *client, struct rtc_time *tm)
+static int pcf2127_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
-	unsigned char buf[10] = { PCF2127_REG_CTRL1 };
+	struct pcf2127 *pcf2127 = dev_get_drvdata(dev);
+	unsigned char buf[10];
+	int ret;
 
-	/* read registers */
-	if (i2c_master_send(client, buf, 1) != 1 ||
-		i2c_master_recv(client, buf, sizeof(buf)) != sizeof(buf)) {
-		dev_err(&client->dev, "%s: read error\n", __func__);
-		return -EIO;
+	ret = regmap_bulk_read(pcf2127->regmap, PCF2127_REG_CTRL1, buf,
+				sizeof(buf));
+	if (ret) {
+		dev_err(dev, "%s: read error\n", __func__);
+		return ret;
 	}
 
 	if (buf[PCF2127_REG_CTRL3] & PCF2127_REG_CTRL3_BLF)
-		dev_info(&client->dev,
+		dev_info(dev,
 			"low voltage detected, check/replace RTC battery.\n");
 
 	if (buf[PCF2127_REG_SC] & PCF2127_OSF) {
@@ -66,12 +69,12 @@ static int pcf2127_get_datetime(struct i2c_client *client, struct rtc_time *tm)
 		 * no need clear the flag here,
 		 * it will be cleared once the new date is saved
 		 */
-		dev_warn(&client->dev,
+		dev_warn(dev,
 			 "oscillator stop detected, date/time is not reliable\n");
 		return -EINVAL;
 	}
 
-	dev_dbg(&client->dev,
+	dev_dbg(dev,
 		"%s: raw data is cr1=%02x, cr2=%02x, cr3=%02x, "
 		"sec=%02x, min=%02x, hr=%02x, "
 		"mday=%02x, wday=%02x, mon=%02x, year=%02x\n",
@@ -91,7 +94,7 @@ static int pcf2127_get_datetime(struct i2c_client *client, struct rtc_time *tm)
 	if (tm->tm_year < 70)
 		tm->tm_year += 100;	/* assume we are in 1970...2069 */
 
-	dev_dbg(&client->dev, "%s: tm is secs=%d, mins=%d, hours=%d, "
+	dev_dbg(dev, "%s: tm is secs=%d, mins=%d, hours=%d, "
 		"mday=%d, mon=%d, year=%d, wday=%d\n",
 		__func__,
 		tm->tm_sec, tm->tm_min, tm->tm_hour,
@@ -100,20 +103,18 @@ static int pcf2127_get_datetime(struct i2c_client *client, struct rtc_time *tm)
 	return rtc_valid_tm(tm);
 }
 
-static int pcf2127_set_datetime(struct i2c_client *client, struct rtc_time *tm)
+static int pcf2127_rtc_set_time(struct device *dev, struct rtc_time *tm)
 {
-	unsigned char buf[8];
+	struct pcf2127 *pcf2127 = dev_get_drvdata(dev);
+	unsigned char buf[7];
 	int i = 0, err;
 
-	dev_dbg(&client->dev, "%s: secs=%d, mins=%d, hours=%d, "
+	dev_dbg(dev, "%s: secs=%d, mins=%d, hours=%d, "
 		"mday=%d, mon=%d, year=%d, wday=%d\n",
 		__func__,
 		tm->tm_sec, tm->tm_min, tm->tm_hour,
 		tm->tm_mday, tm->tm_mon, tm->tm_year, tm->tm_wday);
 
-	/* start register address */
-	buf[i++] = PCF2127_REG_SC;
-
 	/* hours, minutes and seconds */
 	buf[i++] = bin2bcd(tm->tm_sec);	/* this will also clear OSF flag */
 	buf[i++] = bin2bcd(tm->tm_min);
@@ -128,11 +129,11 @@ static int pcf2127_set_datetime(struct i2c_client *client, struct rtc_time *tm)
 	buf[i++] = bin2bcd(tm->tm_year % 100);
 
 	/* write register's data */
-	err = i2c_master_send(client, buf, i);
-	if (err != i) {
-		dev_err(&client->dev,
+	err = regmap_bulk_write(pcf2127->regmap, PCF2127_REG_SC, buf, i);
+	if (err) {
+		dev_err(dev,
 			"%s: err=%d", __func__, err);
-		return -EIO;
+		return err;
 	}
 
 	return 0;
@@ -142,26 +143,17 @@ static int pcf2127_set_datetime(struct i2c_client *client, struct rtc_time *tm)
 static int pcf2127_rtc_ioctl(struct device *dev,
 				unsigned int cmd, unsigned long arg)
 {
-	struct i2c_client *client = to_i2c_client(dev);
-	unsigned char buf = PCF2127_REG_CTRL3;
+	struct pcf2127 *pcf2127 = dev_get_drvdata(dev);
 	int touser;
 	int ret;
 
 	switch (cmd) {
 	case RTC_VL_READ:
-		ret = i2c_master_send(client, &buf, 1);
-		if (!ret)
-			ret = -EIO;
-		if (ret < 0)
-			return ret;
-
-		ret = i2c_master_recv(client, &buf, 1);
-		if (!ret)
-			ret = -EIO;
-		if (ret < 0)
+		ret = regmap_read(pcf2127->regmap, PCF2127_REG_CTRL3, &touser);
+		if (ret)
 			return ret;
 
-		touser = buf & PCF2127_REG_CTRL3_BLF ? 1 : 0;
+		touser = touser & PCF2127_REG_CTRL3_BLF ? 1 : 0;
 
 		if (copy_to_user((void __user *)arg, &touser, sizeof(int)))
 			return -EFAULT;
@@ -174,71 +166,270 @@ static int pcf2127_rtc_ioctl(struct device *dev,
 #define pcf2127_rtc_ioctl NULL
 #endif
 
-static int pcf2127_rtc_read_time(struct device *dev, struct rtc_time *tm)
-{
-	return pcf2127_get_datetime(to_i2c_client(dev), tm);
-}
-
-static int pcf2127_rtc_set_time(struct device *dev, struct rtc_time *tm)
-{
-	return pcf2127_set_datetime(to_i2c_client(dev), tm);
-}
-
 static const struct rtc_class_ops pcf2127_rtc_ops = {
 	.ioctl		= pcf2127_rtc_ioctl,
 	.read_time	= pcf2127_rtc_read_time,
 	.set_time	= pcf2127_rtc_set_time,
 };
 
-static int pcf2127_probe(struct i2c_client *client,
-				const struct i2c_device_id *id)
+static int pcf2127_probe(struct device *dev, struct regmap *regmap,
+			const char *name)
 {
 	struct pcf2127 *pcf2127;
 
-	dev_dbg(&client->dev, "%s\n", __func__);
+	dev_dbg(dev, "%s\n", __func__);
 
-	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
-		return -ENODEV;
-
-	pcf2127 = devm_kzalloc(&client->dev, sizeof(struct pcf2127),
-				GFP_KERNEL);
+	pcf2127 = devm_kzalloc(dev, sizeof(*pcf2127), GFP_KERNEL);
 	if (!pcf2127)
 		return -ENOMEM;
 
-	i2c_set_clientdata(client, pcf2127);
+	pcf2127->regmap = regmap;
+
+	dev_set_drvdata(dev, pcf2127);
 
-	pcf2127->rtc = devm_rtc_device_register(&client->dev,
-				pcf2127_driver.driver.name,
-				&pcf2127_rtc_ops, THIS_MODULE);
+	pcf2127->rtc = devm_rtc_device_register(dev, name, &pcf2127_rtc_ops,
+						THIS_MODULE);
 
 	return PTR_ERR_OR_ZERO(pcf2127->rtc);
 }
 
-static const struct i2c_device_id pcf2127_id[] = {
-	{ "pcf2127", 0 },
-	{ }
-};
-MODULE_DEVICE_TABLE(i2c, pcf2127_id);
-
 #ifdef CONFIG_OF
 static const struct of_device_id pcf2127_of_match[] = {
 	{ .compatible = "nxp,pcf2127" },
+	{ .compatible = "nxp,pcf2129" },
 	{}
 };
 MODULE_DEVICE_TABLE(of, pcf2127_of_match);
 #endif
 
-static struct i2c_driver pcf2127_driver = {
+#if IS_ENABLED(CONFIG_I2C)
+
+static int pcf2127_i2c_write(void *context, const void *data, size_t count)
+{
+	struct device *dev = context;
+	struct i2c_client *client = to_i2c_client(dev);
+	int ret;
+
+	ret = i2c_master_send(client, data, count);
+	if (ret != count)
+		return ret < 0 ? ret : -EIO;
+
+	return 0;
+}
+
+static int pcf2127_i2c_gather_write(void *context,
+				const void *reg, size_t reg_size,
+				const void *val, size_t val_size)
+{
+	struct device *dev = context;
+	struct i2c_client *client = to_i2c_client(dev);
+	int ret;
+	void *buf;
+
+	if (WARN_ON(reg_size != 1))
+		return -EINVAL;
+
+	buf = kmalloc(val_size + 1, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	memcpy(buf, reg, 1);
+	memcpy(buf + 1, val, val_size);
+
+	ret = i2c_master_send(client, buf, val_size + 1);
+	if (ret != val_size + 1)
+		return ret < 0 ? ret : -EIO;
+
+	return 0;
+}
+
+static int pcf2127_i2c_read(void *context, const void *reg, size_t reg_size,
+				void *val, size_t val_size)
+{
+	struct device *dev = context;
+	struct i2c_client *client = to_i2c_client(dev);
+	int ret;
+
+	if (WARN_ON(reg_size != 1))
+		return -EINVAL;
+
+	ret = i2c_master_send(client, reg, 1);
+	if (ret != 1)
+		return ret < 0 ? ret : -EIO;
+
+	ret = i2c_master_recv(client, val, val_size);
+	if (ret != val_size)
+		return ret < 0 ? ret : -EIO;
+
+	return 0;
+}
+
+/*
+ * The reason we need this custom regmap_bus instead of using regmap_init_i2c()
+ * is that the STOP condition is required between set register address and
+ * read register data when reading from registers.
+ */
+static const struct regmap_bus pcf2127_i2c_regmap = {
+	.write = pcf2127_i2c_write,
+	.gather_write = pcf2127_i2c_gather_write,
+	.read = pcf2127_i2c_read,
+};
+
+static struct i2c_driver pcf2127_i2c_driver;
+
+static int pcf2127_i2c_probe(struct i2c_client *client,
+				const struct i2c_device_id *id)
+{
+	struct regmap *regmap;
+	static const struct regmap_config config = {
+		.reg_bits = 8,
+		.val_bits = 8,
+	};
+
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
+		return -ENODEV;
+
+	regmap = devm_regmap_init(&client->dev, &pcf2127_i2c_regmap,
+					&client->dev, &config);
+	if (IS_ERR(regmap)) {
+		dev_err(&client->dev, "%s: regmap allocation failed: %ld\n",
+			__func__, PTR_ERR(regmap));
+		return PTR_ERR(regmap);
+	}
+
+	return pcf2127_probe(&client->dev, regmap,
+				pcf2127_i2c_driver.driver.name);
+}
+
+static const struct i2c_device_id pcf2127_i2c_id[] = {
+	{ "pcf2127", 0 },
+	{ "pcf2129", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, pcf2127_i2c_id);
+
+static struct i2c_driver pcf2127_i2c_driver = {
+	.driver		= {
+		.name	= "rtc-pcf2127-i2c",
+		.of_match_table = of_match_ptr(pcf2127_of_match),
+	},
+	.probe		= pcf2127_i2c_probe,
+	.id_table	= pcf2127_i2c_id,
+};
+
+static int pcf2127_i2c_register_driver(void)
+{
+	return i2c_add_driver(&pcf2127_i2c_driver);
+}
+
+static void pcf2127_i2c_unregister_driver(void)
+{
+	i2c_del_driver(&pcf2127_i2c_driver);
+}
+
+#else
+
+static int pcf2127_i2c_register_driver(void)
+{
+	return 0;
+}
+
+static void pcf2127_i2c_unregister_driver(void)
+{
+}
+
+#endif
+
+#if IS_ENABLED(CONFIG_SPI_MASTER)
+
+static struct spi_driver pcf2127_spi_driver;
+
+static int pcf2127_spi_probe(struct spi_device *spi)
+{
+	static const struct regmap_config config = {
+		.reg_bits = 8,
+		.val_bits = 8,
+		.read_flag_mask = 0xa0,
+		.write_flag_mask = 0x20,
+	};
+	struct regmap *regmap;
+
+	regmap = devm_regmap_init_spi(spi, &config);
+	if (IS_ERR(regmap)) {
+		dev_err(&spi->dev, "%s: regmap allocation failed: %ld\n",
+			__func__, PTR_ERR(regmap));
+		return PTR_ERR(regmap);
+	}
+
+	return pcf2127_probe(&spi->dev, regmap, pcf2127_spi_driver.driver.name);
+}
+
+static const struct spi_device_id pcf2127_spi_id[] = {
+	{ "pcf2127", 0 },
+	{ "pcf2129", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, pcf2127_spi_id);
+
+static struct spi_driver pcf2127_spi_driver = {
 	.driver		= {
-		.name	= "rtc-pcf2127",
+		.name	= "rtc-pcf2127-spi",
 		.of_match_table = of_match_ptr(pcf2127_of_match),
 	},
-	.probe		= pcf2127_probe,
-	.id_table	= pcf2127_id,
+	.probe		= pcf2127_spi_probe,
+	.id_table	= pcf2127_spi_id,
 };
 
-module_i2c_driver(pcf2127_driver);
+static int pcf2127_spi_register_driver(void)
+{
+	return spi_register_driver(&pcf2127_spi_driver);
+}
+
+static void pcf2127_spi_unregister_driver(void)
+{
+	spi_unregister_driver(&pcf2127_spi_driver);
+}
+
+#else
+
+static int pcf2127_spi_register_driver(void)
+{
+	return 0;
+}
+
+static void pcf2127_spi_unregister_driver(void)
+{
+}
+
+#endif
+
+static int __init pcf2127_init(void)
+{
+	int ret;
+
+	ret = pcf2127_i2c_register_driver();
+	if (ret) {
+		pr_err("Failed to register pcf2127 i2c driver: %d\n", ret);
+		return ret;
+	}
+
+	ret = pcf2127_spi_register_driver();
+	if (ret) {
+		pr_err("Failed to register pcf2127 spi driver: %d\n", ret);
+		pcf2127_i2c_unregister_driver();
+	}
+
+	return ret;
+}
+module_init(pcf2127_init)
+
+static void __exit pcf2127_exit(void)
+{
+	pcf2127_spi_unregister_driver();
+	pcf2127_i2c_unregister_driver();
+}
+module_exit(pcf2127_exit)
 
 MODULE_AUTHOR("Renaud Cerrato <r.cerrato@til-technologies.fr>");
-MODULE_DESCRIPTION("NXP PCF2127 RTC driver");
+MODULE_DESCRIPTION("NXP PCF2127/29 RTC driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c
index 63334cbeca41..e8ddbb359d11 100644
--- a/drivers/rtc/rtc-pcf85063.c
+++ b/drivers/rtc/rtc-pcf85063.c
@@ -16,12 +16,12 @@
 #include <linux/rtc.h>
 #include <linux/module.h>
 
-#define DRV_VERSION "0.0.1"
-
 #define PCF85063_REG_CTRL1		0x00 /* status */
+#define PCF85063_REG_CTRL1_STOP		BIT(5)
 #define PCF85063_REG_CTRL2		0x01
 
 #define PCF85063_REG_SC			0x04 /* datetime */
+#define PCF85063_REG_SC_OS		0x80
 #define PCF85063_REG_MN			0x05
 #define PCF85063_REG_HR			0x06
 #define PCF85063_REG_DM			0x07
@@ -29,15 +29,31 @@
 #define PCF85063_REG_MO			0x09
 #define PCF85063_REG_YR			0x0A
 
-#define PCF85063_MO_C			0x80 /* century */
-
 static struct i2c_driver pcf85063_driver;
 
-struct pcf85063 {
-	struct rtc_device *rtc;
-	int c_polarity;	/* 0: MO_C=1 means 19xx, otherwise MO_C=1 means 20xx */
-	int voltage_low; /* indicates if a low_voltage was detected */
-};
+static int pcf85063_stop_clock(struct i2c_client *client, u8 *ctrl1)
+{
+	s32 ret;
+
+	ret = i2c_smbus_read_byte_data(client, PCF85063_REG_CTRL1);
+	if (ret < 0) {
+		dev_err(&client->dev, "Failing to stop the clock\n");
+		return -EIO;
+	}
+
+	/* stop the clock */
+	ret |= PCF85063_REG_CTRL1_STOP;
+
+	ret = i2c_smbus_write_byte_data(client, PCF85063_REG_CTRL1, ret);
+	if (ret < 0) {
+		dev_err(&client->dev, "Failing to stop the clock\n");
+		return -EIO;
+	}
+
+	*ctrl1 = ret;
+
+	return 0;
+}
 
 /*
  * In the routines that deal directly with the pcf85063 hardware, we use
@@ -45,81 +61,85 @@ struct pcf85063 {
  */
 static int pcf85063_get_datetime(struct i2c_client *client, struct rtc_time *tm)
 {
-	struct pcf85063 *pcf85063 = i2c_get_clientdata(client);
-	unsigned char buf[13] = { PCF85063_REG_CTRL1 };
-	struct i2c_msg msgs[] = {
-		{/* setup read ptr */
-			.addr = client->addr,
-			.len = 1,
-			.buf = buf
-		},
-		{/* read status + date */
-			.addr = client->addr,
-			.flags = I2C_M_RD,
-			.len = 13,
-			.buf = buf
-		},
-	};
-
-	/* read registers */
-	if ((i2c_transfer(client->adapter, msgs, 2)) != 2) {
-		dev_err(&client->dev, "%s: read error\n", __func__);
+	int rc;
+	u8 regs[7];
+
+	/*
+	 * while reading, the time/date registers are blocked and not updated
+	 * anymore until the access is finished. To not lose a second
+	 * event, the access must be finished within one second. So, read all
+	 * time/date registers in one turn.
+	 */
+	rc = i2c_smbus_read_i2c_block_data(client, PCF85063_REG_SC,
+					   sizeof(regs), regs);
+	if (rc != sizeof(regs)) {
+		dev_err(&client->dev, "date/time register read error\n");
 		return -EIO;
 	}
 
-	tm->tm_sec = bcd2bin(buf[PCF85063_REG_SC] & 0x7F);
-	tm->tm_min = bcd2bin(buf[PCF85063_REG_MN] & 0x7F);
-	tm->tm_hour = bcd2bin(buf[PCF85063_REG_HR] & 0x3F); /* rtc hr 0-23 */
-	tm->tm_mday = bcd2bin(buf[PCF85063_REG_DM] & 0x3F);
-	tm->tm_wday = buf[PCF85063_REG_DW] & 0x07;
-	tm->tm_mon = bcd2bin(buf[PCF85063_REG_MO] & 0x1F) - 1; /* rtc mn 1-12 */
-	tm->tm_year = bcd2bin(buf[PCF85063_REG_YR]);
+	/* if the clock has lost its power it makes no sense to use its time */
+	if (regs[0] & PCF85063_REG_SC_OS) {
+		dev_warn(&client->dev, "Power loss detected, invalid time\n");
+		return -EINVAL;
+	}
+
+	tm->tm_sec = bcd2bin(regs[0] & 0x7F);
+	tm->tm_min = bcd2bin(regs[1] & 0x7F);
+	tm->tm_hour = bcd2bin(regs[2] & 0x3F); /* rtc hr 0-23 */
+	tm->tm_mday = bcd2bin(regs[3] & 0x3F);
+	tm->tm_wday = regs[4] & 0x07;
+	tm->tm_mon = bcd2bin(regs[5] & 0x1F) - 1; /* rtc mn 1-12 */
+	tm->tm_year = bcd2bin(regs[6]);
 	if (tm->tm_year < 70)
 		tm->tm_year += 100;	/* assume we are in 1970...2069 */
-	/* detect the polarity heuristically. see note above. */
-	pcf85063->c_polarity = (buf[PCF85063_REG_MO] & PCF85063_MO_C) ?
-		(tm->tm_year >= 100) : (tm->tm_year < 100);
 
 	return rtc_valid_tm(tm);
 }
 
 static int pcf85063_set_datetime(struct i2c_client *client, struct rtc_time *tm)
 {
-	int i = 0, err = 0;
-	unsigned char buf[11];
+	int rc;
+	u8 regs[8];
 
-	/* Control & status */
-	buf[PCF85063_REG_CTRL1] = 0;
-	buf[PCF85063_REG_CTRL2] = 5;
+	/*
+	 * to accurately set the time, reset the divider chain and keep it in
+	 * reset state until all time/date registers are written
+	 */
+	rc = pcf85063_stop_clock(client, &regs[7]);
+	if (rc != 0)
+		return rc;
 
 	/* hours, minutes and seconds */
-	buf[PCF85063_REG_SC] = bin2bcd(tm->tm_sec) & 0x7F;
+	regs[0] = bin2bcd(tm->tm_sec) & 0x7F; /* clear OS flag */
 
-	buf[PCF85063_REG_MN] = bin2bcd(tm->tm_min);
-	buf[PCF85063_REG_HR] = bin2bcd(tm->tm_hour);
+	regs[1] = bin2bcd(tm->tm_min);
+	regs[2] = bin2bcd(tm->tm_hour);
 
 	/* Day of month, 1 - 31 */
-	buf[PCF85063_REG_DM] = bin2bcd(tm->tm_mday);
+	regs[3] = bin2bcd(tm->tm_mday);
 
 	/* Day, 0 - 6 */
-	buf[PCF85063_REG_DW] = tm->tm_wday & 0x07;
+	regs[4] = tm->tm_wday & 0x07;
 
 	/* month, 1 - 12 */
-	buf[PCF85063_REG_MO] = bin2bcd(tm->tm_mon + 1);
+	regs[5] = bin2bcd(tm->tm_mon + 1);
 
 	/* year and century */
-	buf[PCF85063_REG_YR] = bin2bcd(tm->tm_year % 100);
-
-	/* write register's data */
-	for (i = 0; i < sizeof(buf); i++) {
-		unsigned char data[2] = { i, buf[i] };
-
-		err = i2c_master_send(client, data, sizeof(data));
-		if (err != sizeof(data)) {
-			dev_err(&client->dev, "%s: err=%d addr=%02x, data=%02x\n",
-					__func__, err, data[0], data[1]);
-			return -EIO;
-		}
+	regs[6] = bin2bcd(tm->tm_year % 100);
+
+	/*
+	 * after all time/date registers are written, let the 'address auto
+	 * increment' feature wrap around and write register CTRL1 to re-enable
+	 * the clock divider chain again
+	 */
+	regs[7] &= ~PCF85063_REG_CTRL1_STOP;
+
+	/* write all registers at once */
+	rc = i2c_smbus_write_i2c_block_data(client, PCF85063_REG_SC,
+					    sizeof(regs), regs);
+	if (rc < 0) {
+		dev_err(&client->dev, "date/time register write error\n");
+		return rc;
 	}
 
 	return 0;
@@ -143,27 +163,18 @@ static const struct rtc_class_ops pcf85063_rtc_ops = {
 static int pcf85063_probe(struct i2c_client *client,
 				const struct i2c_device_id *id)
 {
-	struct pcf85063 *pcf85063;
+	struct rtc_device *rtc;
 
 	dev_dbg(&client->dev, "%s\n", __func__);
 
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
 		return -ENODEV;
 
-	pcf85063 = devm_kzalloc(&client->dev, sizeof(struct pcf85063),
-				GFP_KERNEL);
-	if (!pcf85063)
-		return -ENOMEM;
-
-	dev_info(&client->dev, "chip found, driver version " DRV_VERSION "\n");
-
-	i2c_set_clientdata(client, pcf85063);
-
-	pcf85063->rtc = devm_rtc_device_register(&client->dev,
-				pcf85063_driver.driver.name,
-				&pcf85063_rtc_ops, THIS_MODULE);
+	rtc = devm_rtc_device_register(&client->dev,
+				       pcf85063_driver.driver.name,
+				       &pcf85063_rtc_ops, THIS_MODULE);
 
-	return PTR_ERR_OR_ZERO(pcf85063->rtc);
+	return PTR_ERR_OR_ZERO(rtc);
 }
 
 static const struct i2c_device_id pcf85063_id[] = {
@@ -194,4 +205,3 @@ module_i2c_driver(pcf85063_driver);
 MODULE_AUTHOR("Søren Andersen <san@rosetechnology.dk>");
 MODULE_DESCRIPTION("PCF85063 RTC driver");
 MODULE_LICENSE("GPL");
-MODULE_VERSION(DRV_VERSION);
diff --git a/drivers/rtc/rtc-pcf8523.c b/drivers/rtc/rtc-pcf8523.c
index 988566caaaa6..28c48b3c1946 100644
--- a/drivers/rtc/rtc-pcf8523.c
+++ b/drivers/rtc/rtc-pcf8523.c
@@ -178,28 +178,8 @@ static int pcf8523_rtc_read_time(struct device *dev, struct rtc_time *tm)
 	if (err < 0)
 		return err;
 
-	if (regs[0] & REG_SECONDS_OS) {
-		/*
-		 * If the oscillator was stopped, try to clear the flag. Upon
-		 * power-up the flag is always set, but if we cannot clear it
-		 * the oscillator isn't running properly for some reason. The
-		 * sensible thing therefore is to return an error, signalling
-		 * that the clock cannot be assumed to be correct.
-		 */
-
-		regs[0] &= ~REG_SECONDS_OS;
-
-		err = pcf8523_write(client, REG_SECONDS, regs[0]);
-		if (err < 0)
-			return err;
-
-		err = pcf8523_read(client, REG_SECONDS, &regs[0]);
-		if (err < 0)
-			return err;
-
-		if (regs[0] & REG_SECONDS_OS)
-			return -EAGAIN;
-	}
+	if (regs[0] & REG_SECONDS_OS)
+		return -EINVAL;
 
 	tm->tm_sec = bcd2bin(regs[0] & 0x7f);
 	tm->tm_min = bcd2bin(regs[1] & 0x7f);
@@ -235,6 +215,7 @@ static int pcf8523_rtc_set_time(struct device *dev, struct rtc_time *tm)
 		return err;
 
 	regs[0] = REG_SECONDS;
+	/* This will purposely overwrite REG_SECONDS_OS */
 	regs[1] = bin2bcd(tm->tm_sec);
 	regs[2] = bin2bcd(tm->tm_min);
 	regs[3] = bin2bcd(tm->tm_hour);
diff --git a/drivers/rtc/rtc-pic32.c b/drivers/rtc/rtc-pic32.c
new file mode 100644
index 000000000000..64e1e4578492
--- /dev/null
+++ b/drivers/rtc/rtc-pic32.c
@@ -0,0 +1,411 @@
+/*
+ * PIC32 RTC driver
+ *
+ * Joshua Henderson <joshua.henderson@microchip.com>
+ * Copyright (C) 2016 Microchip Technology Inc.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/rtc.h>
+#include <linux/bcd.h>
+
+#include <asm/mach-pic32/pic32.h>
+
+#define PIC32_RTCCON		0x00
+#define PIC32_RTCCON_ON		BIT(15)
+#define PIC32_RTCCON_SIDL	BIT(13)
+#define PIC32_RTCCON_RTCCLKSEL	(3 << 9)
+#define PIC32_RTCCON_RTCCLKON	BIT(6)
+#define PIC32_RTCCON_RTCWREN	BIT(3)
+#define PIC32_RTCCON_RTCSYNC	BIT(2)
+#define PIC32_RTCCON_HALFSEC	BIT(1)
+#define PIC32_RTCCON_RTCOE	BIT(0)
+
+#define PIC32_RTCALRM		0x10
+#define PIC32_RTCALRM_ALRMEN	BIT(15)
+#define PIC32_RTCALRM_CHIME	BIT(14)
+#define PIC32_RTCALRM_PIV	BIT(13)
+#define PIC32_RTCALRM_ALARMSYNC	BIT(12)
+#define PIC32_RTCALRM_AMASK	0x0F00
+#define PIC32_RTCALRM_ARPT	0xFF
+
+#define PIC32_RTCHOUR		0x23
+#define PIC32_RTCMIN		0x22
+#define PIC32_RTCSEC		0x21
+#define PIC32_RTCYEAR		0x33
+#define PIC32_RTCMON		0x32
+#define PIC32_RTCDAY		0x31
+
+#define PIC32_ALRMTIME		0x40
+#define PIC32_ALRMDATE		0x50
+
+#define PIC32_ALRMHOUR		0x43
+#define PIC32_ALRMMIN		0x42
+#define PIC32_ALRMSEC		0x41
+#define PIC32_ALRMYEAR		0x53
+#define PIC32_ALRMMON		0x52
+#define PIC32_ALRMDAY		0x51
+
+struct pic32_rtc_dev {
+	struct rtc_device	*rtc;
+	void __iomem		*reg_base;
+	struct clk		*clk;
+	spinlock_t		alarm_lock;
+	int			alarm_irq;
+	bool			alarm_clk_enabled;
+};
+
+static void pic32_rtc_alarm_clk_enable(struct pic32_rtc_dev *pdata,
+				       bool enable)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&pdata->alarm_lock, flags);
+	if (enable) {
+		if (!pdata->alarm_clk_enabled) {
+			clk_enable(pdata->clk);
+			pdata->alarm_clk_enabled = true;
+		}
+	} else {
+		if (pdata->alarm_clk_enabled) {
+			clk_disable(pdata->clk);
+			pdata->alarm_clk_enabled = false;
+		}
+	}
+	spin_unlock_irqrestore(&pdata->alarm_lock, flags);
+}
+
+static irqreturn_t pic32_rtc_alarmirq(int irq, void *id)
+{
+	struct pic32_rtc_dev *pdata = (struct pic32_rtc_dev *)id;
+
+	clk_enable(pdata->clk);
+	rtc_update_irq(pdata->rtc, 1, RTC_AF | RTC_IRQF);
+	clk_disable(pdata->clk);
+
+	pic32_rtc_alarm_clk_enable(pdata, false);
+
+	return IRQ_HANDLED;
+}
+
+static int pic32_rtc_setaie(struct device *dev, unsigned int enabled)
+{
+	struct pic32_rtc_dev *pdata = dev_get_drvdata(dev);
+	void __iomem *base = pdata->reg_base;
+
+	clk_enable(pdata->clk);
+
+	writel(PIC32_RTCALRM_ALRMEN,
+	       base + (enabled ? PIC32_SET(PIC32_RTCALRM) :
+		       PIC32_CLR(PIC32_RTCALRM)));
+
+	clk_disable(pdata->clk);
+
+	pic32_rtc_alarm_clk_enable(pdata, enabled);
+
+	return 0;
+}
+
+static int pic32_rtc_setfreq(struct device *dev, int freq)
+{
+	struct pic32_rtc_dev *pdata = dev_get_drvdata(dev);
+	void __iomem *base = pdata->reg_base;
+
+	clk_enable(pdata->clk);
+
+	writel(PIC32_RTCALRM_AMASK, base + PIC32_CLR(PIC32_RTCALRM));
+	writel(freq << 8, base + PIC32_SET(PIC32_RTCALRM));
+	writel(PIC32_RTCALRM_CHIME, base + PIC32_SET(PIC32_RTCALRM));
+
+	clk_disable(pdata->clk);
+
+	return 0;
+}
+
+static int pic32_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm)
+{
+	struct pic32_rtc_dev *pdata = dev_get_drvdata(dev);
+	void __iomem *base = pdata->reg_base;
+	unsigned int tries = 0;
+
+	clk_enable(pdata->clk);
+
+	do {
+		rtc_tm->tm_hour = readb(base + PIC32_RTCHOUR);
+		rtc_tm->tm_min = readb(base + PIC32_RTCMIN);
+		rtc_tm->tm_mon  = readb(base + PIC32_RTCMON);
+		rtc_tm->tm_mday = readb(base + PIC32_RTCDAY);
+		rtc_tm->tm_year = readb(base + PIC32_RTCYEAR);
+		rtc_tm->tm_sec  = readb(base + PIC32_RTCSEC);
+
+		/*
+		 * The only way to work out whether the system was mid-update
+		 * when we read it is to check the second counter, and if it
+		 * is zero, then we re-try the entire read.
+		 */
+		tries += 1;
+	} while (rtc_tm->tm_sec == 0 && tries < 2);
+
+	rtc_tm->tm_sec = bcd2bin(rtc_tm->tm_sec);
+	rtc_tm->tm_min = bcd2bin(rtc_tm->tm_min);
+	rtc_tm->tm_hour = bcd2bin(rtc_tm->tm_hour);
+	rtc_tm->tm_mday = bcd2bin(rtc_tm->tm_mday);
+	rtc_tm->tm_mon = bcd2bin(rtc_tm->tm_mon) - 1;
+	rtc_tm->tm_year = bcd2bin(rtc_tm->tm_year);
+
+	rtc_tm->tm_year += 100;
+
+	dev_dbg(dev, "read time %04d.%02d.%02d %02d:%02d:%02d\n",
+		1900 + rtc_tm->tm_year, rtc_tm->tm_mon, rtc_tm->tm_mday,
+		rtc_tm->tm_hour, rtc_tm->tm_min, rtc_tm->tm_sec);
+
+	clk_disable(pdata->clk);
+	return rtc_valid_tm(rtc_tm);
+}
+
+static int pic32_rtc_settime(struct device *dev, struct rtc_time *tm)
+{
+	struct pic32_rtc_dev *pdata = dev_get_drvdata(dev);
+	void __iomem *base = pdata->reg_base;
+	int year = tm->tm_year - 100;
+
+	dev_dbg(dev, "set time %04d.%02d.%02d %02d:%02d:%02d\n",
+		1900 + tm->tm_year, tm->tm_mon, tm->tm_mday,
+		tm->tm_hour, tm->tm_min, tm->tm_sec);
+
+	if (year < 0 || year >= 100) {
+		dev_err(dev, "rtc only supports 100 years\n");
+		return -EINVAL;
+	}
+
+	clk_enable(pdata->clk);
+	writeb(bin2bcd(tm->tm_sec),  base + PIC32_RTCSEC);
+	writeb(bin2bcd(tm->tm_min),  base + PIC32_RTCMIN);
+	writeb(bin2bcd(tm->tm_hour), base + PIC32_RTCHOUR);
+	writeb(bin2bcd(tm->tm_mday), base + PIC32_RTCDAY);
+	writeb(bin2bcd(tm->tm_mon + 1), base + PIC32_RTCMON);
+	writeb(bin2bcd(year), base + PIC32_RTCYEAR);
+	clk_disable(pdata->clk);
+
+	return 0;
+}
+
+static int pic32_rtc_getalarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct pic32_rtc_dev *pdata = dev_get_drvdata(dev);
+	struct rtc_time *alm_tm = &alrm->time;
+	void __iomem *base = pdata->reg_base;
+	unsigned int alm_en;
+
+	clk_enable(pdata->clk);
+	alm_tm->tm_sec  = readb(base + PIC32_ALRMSEC);
+	alm_tm->tm_min  = readb(base + PIC32_ALRMMIN);
+	alm_tm->tm_hour = readb(base + PIC32_ALRMHOUR);
+	alm_tm->tm_mon  = readb(base + PIC32_ALRMMON);
+	alm_tm->tm_mday = readb(base + PIC32_ALRMDAY);
+	alm_tm->tm_year = readb(base + PIC32_ALRMYEAR);
+
+	alm_en = readb(base + PIC32_RTCALRM);
+
+	alrm->enabled = (alm_en & PIC32_RTCALRM_ALRMEN) ? 1 : 0;
+
+	dev_dbg(dev, "getalarm: %d, %04d.%02d.%02d %02d:%02d:%02d\n",
+		alm_en,
+		1900 + alm_tm->tm_year, alm_tm->tm_mon, alm_tm->tm_mday,
+		alm_tm->tm_hour, alm_tm->tm_min, alm_tm->tm_sec);
+
+	alm_tm->tm_sec = bcd2bin(alm_tm->tm_sec);
+	alm_tm->tm_min = bcd2bin(alm_tm->tm_min);
+	alm_tm->tm_hour = bcd2bin(alm_tm->tm_hour);
+	alm_tm->tm_mday = bcd2bin(alm_tm->tm_mday);
+	alm_tm->tm_mon = bcd2bin(alm_tm->tm_mon) - 1;
+	alm_tm->tm_year = bcd2bin(alm_tm->tm_year);
+
+	clk_disable(pdata->clk);
+	return 0;
+}
+
+static int pic32_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct pic32_rtc_dev *pdata = dev_get_drvdata(dev);
+	struct rtc_time *tm = &alrm->time;
+	void __iomem *base = pdata->reg_base;
+
+	clk_enable(pdata->clk);
+	dev_dbg(dev, "setalarm: %d, %04d.%02d.%02d %02d:%02d:%02d\n",
+		alrm->enabled,
+		1900 + tm->tm_year, tm->tm_mon + 1, tm->tm_mday,
+		tm->tm_hour, tm->tm_min, tm->tm_sec);
+
+	writel(0x00, base + PIC32_ALRMTIME);
+	writel(0x00, base + PIC32_ALRMDATE);
+
+	pic32_rtc_setaie(dev, alrm->enabled);
+
+	clk_disable(pdata->clk);
+	return 0;
+}
+
+static int pic32_rtc_proc(struct device *dev, struct seq_file *seq)
+{
+	struct pic32_rtc_dev *pdata = dev_get_drvdata(dev);
+	void __iomem *base = pdata->reg_base;
+	unsigned int repeat;
+
+	clk_enable(pdata->clk);
+
+	repeat = readw(base + PIC32_RTCALRM);
+	repeat &= PIC32_RTCALRM_ARPT;
+	seq_printf(seq, "periodic_IRQ\t: %s\n", repeat  ? "yes" : "no");
+
+	clk_disable(pdata->clk);
+	return 0;
+}
+
+static const struct rtc_class_ops pic32_rtcops = {
+	.read_time	  = pic32_rtc_gettime,
+	.set_time	  = pic32_rtc_settime,
+	.read_alarm	  = pic32_rtc_getalarm,
+	.set_alarm	  = pic32_rtc_setalarm,
+	.proc		  = pic32_rtc_proc,
+	.alarm_irq_enable = pic32_rtc_setaie,
+};
+
+static void pic32_rtc_enable(struct pic32_rtc_dev *pdata, int en)
+{
+	void __iomem *base = pdata->reg_base;
+
+	if (!base)
+		return;
+
+	clk_enable(pdata->clk);
+	if (!en) {
+		writel(PIC32_RTCCON_ON, base + PIC32_CLR(PIC32_RTCCON));
+	} else {
+		pic32_syskey_unlock();
+
+		writel(PIC32_RTCCON_RTCWREN, base + PIC32_SET(PIC32_RTCCON));
+		writel(3 << 9, base + PIC32_CLR(PIC32_RTCCON));
+
+		if (!(readl(base + PIC32_RTCCON) & PIC32_RTCCON_ON))
+			writel(PIC32_RTCCON_ON, base + PIC32_SET(PIC32_RTCCON));
+	}
+	clk_disable(pdata->clk);
+}
+
+static int pic32_rtc_remove(struct platform_device *pdev)
+{
+	struct pic32_rtc_dev *pdata = platform_get_drvdata(pdev);
+
+	pic32_rtc_setaie(&pdev->dev, 0);
+	clk_unprepare(pdata->clk);
+	pdata->clk = NULL;
+
+	return 0;
+}
+
+static int pic32_rtc_probe(struct platform_device *pdev)
+{
+	struct pic32_rtc_dev *pdata;
+	struct resource *res;
+	int ret;
+
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, pdata);
+
+	pdata->alarm_irq = platform_get_irq(pdev, 0);
+	if (pdata->alarm_irq < 0) {
+		dev_err(&pdev->dev, "no irq for alarm\n");
+		return pdata->alarm_irq;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	pdata->reg_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(pdata->reg_base))
+		return PTR_ERR(pdata->reg_base);
+
+	pdata->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(pdata->clk)) {
+		dev_err(&pdev->dev, "failed to find rtc clock source\n");
+		ret = PTR_ERR(pdata->clk);
+		pdata->clk = NULL;
+		return ret;
+	}
+
+	spin_lock_init(&pdata->alarm_lock);
+
+	clk_prepare_enable(pdata->clk);
+
+	pic32_rtc_enable(pdata, 1);
+
+	device_init_wakeup(&pdev->dev, 1);
+
+	pdata->rtc = devm_rtc_device_register(&pdev->dev, pdev->name,
+						 &pic32_rtcops,
+						 THIS_MODULE);
+	if (IS_ERR(pdata->rtc)) {
+		ret = PTR_ERR(pdata->rtc);
+		goto err_nortc;
+	}
+
+	pdata->rtc->max_user_freq = 128;
+
+	pic32_rtc_setfreq(&pdev->dev, 1);
+	ret = devm_request_irq(&pdev->dev, pdata->alarm_irq,
+			       pic32_rtc_alarmirq, 0,
+			       dev_name(&pdev->dev), pdata);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"IRQ %d error %d\n", pdata->alarm_irq, ret);
+		goto err_nortc;
+	}
+
+	clk_disable(pdata->clk);
+
+	return 0;
+
+err_nortc:
+	pic32_rtc_enable(pdata, 0);
+	clk_disable_unprepare(pdata->clk);
+
+	return ret;
+}
+
+static const struct of_device_id pic32_rtc_dt_ids[] = {
+	{ .compatible = "microchip,pic32mzda-rtc" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, pic32_rtc_dt_ids);
+
+static struct platform_driver pic32_rtc_driver = {
+	.probe		= pic32_rtc_probe,
+	.remove		= pic32_rtc_remove,
+	.driver		= {
+		.name	= "pic32-rtc",
+		.owner	= THIS_MODULE,
+		.of_match_table	= of_match_ptr(pic32_rtc_dt_ids),
+	},
+};
+module_platform_driver(pic32_rtc_driver);
+
+MODULE_DESCRIPTION("Microchip PIC32 RTC Driver");
+MODULE_AUTHOR("Joshua Henderson <joshua.henderson@microchip.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/rtc/rtc-rv3029c2.c b/drivers/rtc/rtc-rv3029c2.c
index e9ac5a43be1a..d0cbf08040cd 100644
--- a/drivers/rtc/rtc-rv3029c2.c
+++ b/drivers/rtc/rtc-rv3029c2.c
@@ -1,7 +1,8 @@
 /*
- * Micro Crystal RV-3029C2 rtc class driver
+ * Micro Crystal RV-3029 rtc class driver
  *
  * Author: Gregory Hermant <gregory.hermant@calao-systems.com>
+ *         Michael Buesch <m@bues.ch>
  *
  * based on previously existing rtc class drivers
  *
@@ -9,89 +10,120 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  *
- * NOTE: Currently this driver only supports the bare minimum for read
- * and write the RTC and alarms. The extra features provided by this chip
- * (trickle charger, eeprom, T° compensation) are unavailable.
  */
 
 #include <linux/module.h>
 #include <linux/i2c.h>
 #include <linux/bcd.h>
 #include <linux/rtc.h>
+#include <linux/delay.h>
+#include <linux/of.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+
 
 /* Register map */
 /* control section */
-#define RV3029C2_ONOFF_CTRL		0x00
-#define RV3029C2_IRQ_CTRL		0x01
-#define RV3029C2_IRQ_CTRL_AIE		(1 << 0)
-#define RV3029C2_IRQ_FLAGS		0x02
-#define RV3029C2_IRQ_FLAGS_AF		(1 << 0)
-#define RV3029C2_STATUS			0x03
-#define RV3029C2_STATUS_VLOW1		(1 << 2)
-#define RV3029C2_STATUS_VLOW2		(1 << 3)
-#define RV3029C2_STATUS_SR		(1 << 4)
-#define RV3029C2_STATUS_PON		(1 << 5)
-#define RV3029C2_STATUS_EEBUSY		(1 << 7)
-#define RV3029C2_RST_CTRL		0x04
-#define RV3029C2_CONTROL_SECTION_LEN	0x05
+#define RV3029_ONOFF_CTRL		0x00
+#define RV3029_ONOFF_CTRL_WE		BIT(0)
+#define RV3029_ONOFF_CTRL_TE		BIT(1)
+#define RV3029_ONOFF_CTRL_TAR		BIT(2)
+#define RV3029_ONOFF_CTRL_EERE		BIT(3)
+#define RV3029_ONOFF_CTRL_SRON		BIT(4)
+#define RV3029_ONOFF_CTRL_TD0		BIT(5)
+#define RV3029_ONOFF_CTRL_TD1		BIT(6)
+#define RV3029_ONOFF_CTRL_CLKINT	BIT(7)
+#define RV3029_IRQ_CTRL			0x01
+#define RV3029_IRQ_CTRL_AIE		BIT(0)
+#define RV3029_IRQ_CTRL_TIE		BIT(1)
+#define RV3029_IRQ_CTRL_V1IE		BIT(2)
+#define RV3029_IRQ_CTRL_V2IE		BIT(3)
+#define RV3029_IRQ_CTRL_SRIE		BIT(4)
+#define RV3029_IRQ_FLAGS		0x02
+#define RV3029_IRQ_FLAGS_AF		BIT(0)
+#define RV3029_IRQ_FLAGS_TF		BIT(1)
+#define RV3029_IRQ_FLAGS_V1IF		BIT(2)
+#define RV3029_IRQ_FLAGS_V2IF		BIT(3)
+#define RV3029_IRQ_FLAGS_SRF		BIT(4)
+#define RV3029_STATUS			0x03
+#define RV3029_STATUS_VLOW1		BIT(2)
+#define RV3029_STATUS_VLOW2		BIT(3)
+#define RV3029_STATUS_SR		BIT(4)
+#define RV3029_STATUS_PON		BIT(5)
+#define RV3029_STATUS_EEBUSY		BIT(7)
+#define RV3029_RST_CTRL			0x04
+#define RV3029_RST_CTRL_SYSR		BIT(4)
+#define RV3029_CONTROL_SECTION_LEN	0x05
 
 /* watch section */
-#define RV3029C2_W_SEC			0x08
-#define RV3029C2_W_MINUTES		0x09
-#define RV3029C2_W_HOURS		0x0A
-#define RV3029C2_REG_HR_12_24		(1<<6)  /* 24h/12h mode */
-#define RV3029C2_REG_HR_PM		(1<<5)  /* PM/AM bit in 12h mode */
-#define RV3029C2_W_DATE			0x0B
-#define RV3029C2_W_DAYS			0x0C
-#define RV3029C2_W_MONTHS		0x0D
-#define RV3029C2_W_YEARS		0x0E
-#define RV3029C2_WATCH_SECTION_LEN	0x07
+#define RV3029_W_SEC			0x08
+#define RV3029_W_MINUTES		0x09
+#define RV3029_W_HOURS			0x0A
+#define RV3029_REG_HR_12_24		BIT(6) /* 24h/12h mode */
+#define RV3029_REG_HR_PM		BIT(5) /* PM/AM bit in 12h mode */
+#define RV3029_W_DATE			0x0B
+#define RV3029_W_DAYS			0x0C
+#define RV3029_W_MONTHS			0x0D
+#define RV3029_W_YEARS			0x0E
+#define RV3029_WATCH_SECTION_LEN	0x07
 
 /* alarm section */
-#define RV3029C2_A_SC			0x10
-#define RV3029C2_A_MN			0x11
-#define RV3029C2_A_HR			0x12
-#define RV3029C2_A_DT			0x13
-#define RV3029C2_A_DW			0x14
-#define RV3029C2_A_MO			0x15
-#define RV3029C2_A_YR			0x16
-#define RV3029C2_ALARM_SECTION_LEN	0x07
+#define RV3029_A_SC			0x10
+#define RV3029_A_MN			0x11
+#define RV3029_A_HR			0x12
+#define RV3029_A_DT			0x13
+#define RV3029_A_DW			0x14
+#define RV3029_A_MO			0x15
+#define RV3029_A_YR			0x16
+#define RV3029_ALARM_SECTION_LEN	0x07
 
 /* timer section */
-#define RV3029C2_TIMER_LOW		0x18
-#define RV3029C2_TIMER_HIGH		0x19
+#define RV3029_TIMER_LOW		0x18
+#define RV3029_TIMER_HIGH		0x19
 
 /* temperature section */
-#define RV3029C2_TEMP_PAGE		0x20
+#define RV3029_TEMP_PAGE		0x20
 
 /* eeprom data section */
-#define RV3029C2_E2P_EEDATA1		0x28
-#define RV3029C2_E2P_EEDATA2		0x29
+#define RV3029_E2P_EEDATA1		0x28
+#define RV3029_E2P_EEDATA2		0x29
+#define RV3029_E2PDATA_SECTION_LEN	0x02
 
 /* eeprom control section */
-#define RV3029C2_CONTROL_E2P_EECTRL	0x30
-#define RV3029C2_TRICKLE_1K		(1<<0)  /*  1K resistance */
-#define RV3029C2_TRICKLE_5K		(1<<1)  /*  5K resistance */
-#define RV3029C2_TRICKLE_20K		(1<<2)  /* 20K resistance */
-#define RV3029C2_TRICKLE_80K		(1<<3)  /* 80K resistance */
-#define RV3029C2_CONTROL_E2P_XTALOFFSET	0x31
-#define RV3029C2_CONTROL_E2P_QCOEF	0x32
-#define RV3029C2_CONTROL_E2P_TURNOVER	0x33
+#define RV3029_CONTROL_E2P_EECTRL	0x30
+#define RV3029_EECTRL_THP		BIT(0) /* temp scan interval */
+#define RV3029_EECTRL_THE		BIT(1) /* thermometer enable */
+#define RV3029_EECTRL_FD0		BIT(2) /* CLKOUT */
+#define RV3029_EECTRL_FD1		BIT(3) /* CLKOUT */
+#define RV3029_TRICKLE_1K		BIT(4) /* 1.5K resistance */
+#define RV3029_TRICKLE_5K		BIT(5) /* 5K   resistance */
+#define RV3029_TRICKLE_20K		BIT(6) /* 20K  resistance */
+#define RV3029_TRICKLE_80K		BIT(7) /* 80K  resistance */
+#define RV3029_TRICKLE_MASK		(RV3029_TRICKLE_1K |\
+					 RV3029_TRICKLE_5K |\
+					 RV3029_TRICKLE_20K |\
+					 RV3029_TRICKLE_80K)
+#define RV3029_TRICKLE_SHIFT		4
+#define RV3029_CONTROL_E2P_XOFFS	0x31 /* XTAL offset */
+#define RV3029_CONTROL_E2P_XOFFS_SIGN	BIT(7) /* Sign: 1->pos, 0->neg */
+#define RV3029_CONTROL_E2P_QCOEF	0x32 /* XTAL temp drift coef */
+#define RV3029_CONTROL_E2P_TURNOVER	0x33 /* XTAL turnover temp (in *C) */
+#define RV3029_CONTROL_E2P_TOV_MASK	0x3F /* XTAL turnover temp mask */
 
 /* user ram section */
-#define RV3029C2_USR1_RAM_PAGE		0x38
-#define RV3029C2_USR1_SECTION_LEN	0x04
-#define RV3029C2_USR2_RAM_PAGE		0x3C
-#define RV3029C2_USR2_SECTION_LEN	0x04
+#define RV3029_USR1_RAM_PAGE		0x38
+#define RV3029_USR1_SECTION_LEN		0x04
+#define RV3029_USR2_RAM_PAGE		0x3C
+#define RV3029_USR2_SECTION_LEN		0x04
 
 static int
-rv3029c2_i2c_read_regs(struct i2c_client *client, u8 reg, u8 *buf,
-	unsigned len)
+rv3029_i2c_read_regs(struct i2c_client *client, u8 reg, u8 *buf,
+		     unsigned len)
 {
 	int ret;
 
-	if ((reg > RV3029C2_USR1_RAM_PAGE + 7) ||
-		(reg + len > RV3029C2_USR1_RAM_PAGE + 8))
+	if ((reg > RV3029_USR1_RAM_PAGE + 7) ||
+		(reg + len > RV3029_USR1_RAM_PAGE + 8))
 		return -EINVAL;
 
 	ret = i2c_smbus_read_i2c_block_data(client, reg, len, buf);
@@ -103,20 +135,38 @@ rv3029c2_i2c_read_regs(struct i2c_client *client, u8 reg, u8 *buf,
 }
 
 static int
-rv3029c2_i2c_write_regs(struct i2c_client *client, u8 reg, u8 const buf[],
-			unsigned len)
+rv3029_i2c_write_regs(struct i2c_client *client, u8 reg, u8 const buf[],
+		      unsigned len)
 {
-	if ((reg > RV3029C2_USR1_RAM_PAGE + 7) ||
-		(reg + len > RV3029C2_USR1_RAM_PAGE + 8))
+	if ((reg > RV3029_USR1_RAM_PAGE + 7) ||
+		(reg + len > RV3029_USR1_RAM_PAGE + 8))
 		return -EINVAL;
 
 	return i2c_smbus_write_i2c_block_data(client, reg, len, buf);
 }
 
 static int
-rv3029c2_i2c_get_sr(struct i2c_client *client, u8 *buf)
+rv3029_i2c_update_bits(struct i2c_client *client, u8 reg, u8 mask, u8 set)
+{
+	u8 buf;
+	int ret;
+
+	ret = rv3029_i2c_read_regs(client, reg, &buf, 1);
+	if (ret < 0)
+		return ret;
+	buf &= ~mask;
+	buf |= set & mask;
+	ret = rv3029_i2c_write_regs(client, reg, &buf, 1);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int
+rv3029_i2c_get_sr(struct i2c_client *client, u8 *buf)
 {
-	int ret = rv3029c2_i2c_read_regs(client, RV3029C2_STATUS, buf, 1);
+	int ret = rv3029_i2c_read_regs(client, RV3029_STATUS, buf, 1);
 
 	if (ret < 0)
 		return -EIO;
@@ -125,83 +175,224 @@ rv3029c2_i2c_get_sr(struct i2c_client *client, u8 *buf)
 }
 
 static int
-rv3029c2_i2c_set_sr(struct i2c_client *client, u8 val)
+rv3029_i2c_set_sr(struct i2c_client *client, u8 val)
 {
 	u8 buf[1];
 	int sr;
 
 	buf[0] = val;
-	sr = rv3029c2_i2c_write_regs(client, RV3029C2_STATUS, buf, 1);
+	sr = rv3029_i2c_write_regs(client, RV3029_STATUS, buf, 1);
 	dev_dbg(&client->dev, "status = 0x%.2x (%d)\n", buf[0], buf[0]);
 	if (sr < 0)
 		return -EIO;
 	return 0;
 }
 
+static int rv3029_eeprom_busywait(struct i2c_client *client)
+{
+	int i, ret;
+	u8 sr;
+
+	for (i = 100; i > 0; i--) {
+		ret = rv3029_i2c_get_sr(client, &sr);
+		if (ret < 0)
+			break;
+		if (!(sr & RV3029_STATUS_EEBUSY))
+			break;
+		usleep_range(1000, 10000);
+	}
+	if (i <= 0) {
+		dev_err(&client->dev, "EEPROM busy wait timeout.\n");
+		return -ETIMEDOUT;
+	}
+
+	return ret;
+}
+
+static int rv3029_eeprom_exit(struct i2c_client *client)
+{
+	/* Re-enable eeprom refresh */
+	return rv3029_i2c_update_bits(client, RV3029_ONOFF_CTRL,
+				      RV3029_ONOFF_CTRL_EERE,
+				      RV3029_ONOFF_CTRL_EERE);
+}
+
+static int rv3029_eeprom_enter(struct i2c_client *client)
+{
+	int ret;
+	u8 sr;
+
+	/* Check whether we are in the allowed voltage range. */
+	ret = rv3029_i2c_get_sr(client, &sr);
+	if (ret < 0)
+		return ret;
+	if (sr & (RV3029_STATUS_VLOW1 | RV3029_STATUS_VLOW2)) {
+		/* We clear the bits and retry once just in case
+		 * we had a brown out in early startup.
+		 */
+		sr &= ~RV3029_STATUS_VLOW1;
+		sr &= ~RV3029_STATUS_VLOW2;
+		ret = rv3029_i2c_set_sr(client, sr);
+		if (ret < 0)
+			return ret;
+		usleep_range(1000, 10000);
+		ret = rv3029_i2c_get_sr(client, &sr);
+		if (ret < 0)
+			return ret;
+		if (sr & (RV3029_STATUS_VLOW1 | RV3029_STATUS_VLOW2)) {
+			dev_err(&client->dev,
+				"Supply voltage is too low to safely access the EEPROM.\n");
+			return -ENODEV;
+		}
+	}
+
+	/* Disable eeprom refresh. */
+	ret = rv3029_i2c_update_bits(client, RV3029_ONOFF_CTRL,
+				     RV3029_ONOFF_CTRL_EERE, 0);
+	if (ret < 0)
+		return ret;
+
+	/* Wait for any previous eeprom accesses to finish. */
+	ret = rv3029_eeprom_busywait(client);
+	if (ret < 0)
+		rv3029_eeprom_exit(client);
+
+	return ret;
+}
+
+static int rv3029_eeprom_read(struct i2c_client *client, u8 reg,
+			      u8 buf[], size_t len)
+{
+	int ret, err;
+
+	err = rv3029_eeprom_enter(client);
+	if (err < 0)
+		return err;
+
+	ret = rv3029_i2c_read_regs(client, reg, buf, len);
+
+	err = rv3029_eeprom_exit(client);
+	if (err < 0)
+		return err;
+
+	return ret;
+}
+
+static int rv3029_eeprom_write(struct i2c_client *client, u8 reg,
+			       u8 const buf[], size_t len)
+{
+	int ret, err;
+	size_t i;
+	u8 tmp;
+
+	err = rv3029_eeprom_enter(client);
+	if (err < 0)
+		return err;
+
+	for (i = 0; i < len; i++, reg++) {
+		ret = rv3029_i2c_read_regs(client, reg, &tmp, 1);
+		if (ret < 0)
+			break;
+		if (tmp != buf[i]) {
+			ret = rv3029_i2c_write_regs(client, reg, &buf[i], 1);
+			if (ret < 0)
+				break;
+		}
+		ret = rv3029_eeprom_busywait(client);
+		if (ret < 0)
+			break;
+	}
+
+	err = rv3029_eeprom_exit(client);
+	if (err < 0)
+		return err;
+
+	return ret;
+}
+
+static int rv3029_eeprom_update_bits(struct i2c_client *client,
+				     u8 reg, u8 mask, u8 set)
+{
+	u8 buf;
+	int ret;
+
+	ret = rv3029_eeprom_read(client, reg, &buf, 1);
+	if (ret < 0)
+		return ret;
+	buf &= ~mask;
+	buf |= set & mask;
+	ret = rv3029_eeprom_write(client, reg, &buf, 1);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
 static int
-rv3029c2_i2c_read_time(struct i2c_client *client, struct rtc_time *tm)
+rv3029_i2c_read_time(struct i2c_client *client, struct rtc_time *tm)
 {
 	u8 buf[1];
 	int ret;
-	u8 regs[RV3029C2_WATCH_SECTION_LEN] = { 0, };
+	u8 regs[RV3029_WATCH_SECTION_LEN] = { 0, };
 
-	ret = rv3029c2_i2c_get_sr(client, buf);
+	ret = rv3029_i2c_get_sr(client, buf);
 	if (ret < 0) {
 		dev_err(&client->dev, "%s: reading SR failed\n", __func__);
 		return -EIO;
 	}
 
-	ret = rv3029c2_i2c_read_regs(client, RV3029C2_W_SEC , regs,
-					RV3029C2_WATCH_SECTION_LEN);
+	ret = rv3029_i2c_read_regs(client, RV3029_W_SEC, regs,
+				   RV3029_WATCH_SECTION_LEN);
 	if (ret < 0) {
 		dev_err(&client->dev, "%s: reading RTC section failed\n",
 			__func__);
 		return ret;
 	}
 
-	tm->tm_sec = bcd2bin(regs[RV3029C2_W_SEC-RV3029C2_W_SEC]);
-	tm->tm_min = bcd2bin(regs[RV3029C2_W_MINUTES-RV3029C2_W_SEC]);
+	tm->tm_sec = bcd2bin(regs[RV3029_W_SEC-RV3029_W_SEC]);
+	tm->tm_min = bcd2bin(regs[RV3029_W_MINUTES-RV3029_W_SEC]);
 
 	/* HR field has a more complex interpretation */
 	{
-		const u8 _hr = regs[RV3029C2_W_HOURS-RV3029C2_W_SEC];
-		if (_hr & RV3029C2_REG_HR_12_24) {
+		const u8 _hr = regs[RV3029_W_HOURS-RV3029_W_SEC];
+
+		if (_hr & RV3029_REG_HR_12_24) {
 			/* 12h format */
 			tm->tm_hour = bcd2bin(_hr & 0x1f);
-			if (_hr & RV3029C2_REG_HR_PM)	/* PM flag set */
+			if (_hr & RV3029_REG_HR_PM)	/* PM flag set */
 				tm->tm_hour += 12;
 		} else /* 24h format */
 			tm->tm_hour = bcd2bin(_hr & 0x3f);
 	}
 
-	tm->tm_mday = bcd2bin(regs[RV3029C2_W_DATE-RV3029C2_W_SEC]);
-	tm->tm_mon = bcd2bin(regs[RV3029C2_W_MONTHS-RV3029C2_W_SEC]) - 1;
-	tm->tm_year = bcd2bin(regs[RV3029C2_W_YEARS-RV3029C2_W_SEC]) + 100;
-	tm->tm_wday = bcd2bin(regs[RV3029C2_W_DAYS-RV3029C2_W_SEC]) - 1;
+	tm->tm_mday = bcd2bin(regs[RV3029_W_DATE-RV3029_W_SEC]);
+	tm->tm_mon = bcd2bin(regs[RV3029_W_MONTHS-RV3029_W_SEC]) - 1;
+	tm->tm_year = bcd2bin(regs[RV3029_W_YEARS-RV3029_W_SEC]) + 100;
+	tm->tm_wday = bcd2bin(regs[RV3029_W_DAYS-RV3029_W_SEC]) - 1;
 
 	return 0;
 }
 
-static int rv3029c2_rtc_read_time(struct device *dev, struct rtc_time *tm)
+static int rv3029_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
-	return rv3029c2_i2c_read_time(to_i2c_client(dev), tm);
+	return rv3029_i2c_read_time(to_i2c_client(dev), tm);
 }
 
 static int
-rv3029c2_i2c_read_alarm(struct i2c_client *client, struct rtc_wkalrm *alarm)
+rv3029_i2c_read_alarm(struct i2c_client *client, struct rtc_wkalrm *alarm)
 {
 	struct rtc_time *const tm = &alarm->time;
 	int ret;
 	u8 regs[8];
 
-	ret = rv3029c2_i2c_get_sr(client, regs);
+	ret = rv3029_i2c_get_sr(client, regs);
 	if (ret < 0) {
 		dev_err(&client->dev, "%s: reading SR failed\n", __func__);
 		return -EIO;
 	}
 
-	ret = rv3029c2_i2c_read_regs(client, RV3029C2_A_SC, regs,
-					RV3029C2_ALARM_SECTION_LEN);
+	ret = rv3029_i2c_read_regs(client, RV3029_A_SC, regs,
+				   RV3029_ALARM_SECTION_LEN);
 
 	if (ret < 0) {
 		dev_err(&client->dev, "%s: reading alarm section failed\n",
@@ -209,51 +400,42 @@ rv3029c2_i2c_read_alarm(struct i2c_client *client, struct rtc_wkalrm *alarm)
 		return ret;
 	}
 
-	tm->tm_sec = bcd2bin(regs[RV3029C2_A_SC-RV3029C2_A_SC] & 0x7f);
-	tm->tm_min = bcd2bin(regs[RV3029C2_A_MN-RV3029C2_A_SC] & 0x7f);
-	tm->tm_hour = bcd2bin(regs[RV3029C2_A_HR-RV3029C2_A_SC] & 0x3f);
-	tm->tm_mday = bcd2bin(regs[RV3029C2_A_DT-RV3029C2_A_SC] & 0x3f);
-	tm->tm_mon = bcd2bin(regs[RV3029C2_A_MO-RV3029C2_A_SC] & 0x1f) - 1;
-	tm->tm_year = bcd2bin(regs[RV3029C2_A_YR-RV3029C2_A_SC] & 0x7f) + 100;
-	tm->tm_wday = bcd2bin(regs[RV3029C2_A_DW-RV3029C2_A_SC] & 0x07) - 1;
+	tm->tm_sec = bcd2bin(regs[RV3029_A_SC-RV3029_A_SC] & 0x7f);
+	tm->tm_min = bcd2bin(regs[RV3029_A_MN-RV3029_A_SC] & 0x7f);
+	tm->tm_hour = bcd2bin(regs[RV3029_A_HR-RV3029_A_SC] & 0x3f);
+	tm->tm_mday = bcd2bin(regs[RV3029_A_DT-RV3029_A_SC] & 0x3f);
+	tm->tm_mon = bcd2bin(regs[RV3029_A_MO-RV3029_A_SC] & 0x1f) - 1;
+	tm->tm_year = bcd2bin(regs[RV3029_A_YR-RV3029_A_SC] & 0x7f) + 100;
+	tm->tm_wday = bcd2bin(regs[RV3029_A_DW-RV3029_A_SC] & 0x07) - 1;
 
 	return 0;
 }
 
 static int
-rv3029c2_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
+rv3029_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 {
-	return rv3029c2_i2c_read_alarm(to_i2c_client(dev), alarm);
+	return rv3029_i2c_read_alarm(to_i2c_client(dev), alarm);
 }
 
-static int rv3029c2_rtc_i2c_alarm_set_irq(struct i2c_client *client,
+static int rv3029_rtc_i2c_alarm_set_irq(struct i2c_client *client,
 					int enable)
 {
 	int ret;
-	u8 buf[1];
-
-	/* enable AIE irq */
-	ret = rv3029c2_i2c_read_regs(client, RV3029C2_IRQ_CTRL,	buf, 1);
-	if (ret < 0) {
-		dev_err(&client->dev, "can't read INT reg\n");
-		return ret;
-	}
-	if (enable)
-		buf[0] |= RV3029C2_IRQ_CTRL_AIE;
-	else
-		buf[0] &= ~RV3029C2_IRQ_CTRL_AIE;
 
-	ret = rv3029c2_i2c_write_regs(client, RV3029C2_IRQ_CTRL, buf, 1);
+	/* enable/disable AIE irq */
+	ret = rv3029_i2c_update_bits(client, RV3029_IRQ_CTRL,
+				     RV3029_IRQ_CTRL_AIE,
+				     (enable ? RV3029_IRQ_CTRL_AIE : 0));
 	if (ret < 0) {
-		dev_err(&client->dev, "can't set INT reg\n");
+		dev_err(&client->dev, "can't update INT reg\n");
 		return ret;
 	}
 
 	return 0;
 }
 
-static int rv3029c2_rtc_i2c_set_alarm(struct i2c_client *client,
-					struct rtc_wkalrm *alarm)
+static int rv3029_rtc_i2c_set_alarm(struct i2c_client *client,
+				    struct rtc_wkalrm *alarm)
 {
 	struct rtc_time *const tm = &alarm->time;
 	int ret;
@@ -267,50 +449,41 @@ static int rv3029c2_rtc_i2c_set_alarm(struct i2c_client *client,
 	if (tm->tm_year < 100)
 		return -EINVAL;
 
-	ret = rv3029c2_i2c_get_sr(client, regs);
+	ret = rv3029_i2c_get_sr(client, regs);
 	if (ret < 0) {
 		dev_err(&client->dev, "%s: reading SR failed\n", __func__);
 		return -EIO;
 	}
-	regs[RV3029C2_A_SC-RV3029C2_A_SC] = bin2bcd(tm->tm_sec & 0x7f);
-	regs[RV3029C2_A_MN-RV3029C2_A_SC] = bin2bcd(tm->tm_min & 0x7f);
-	regs[RV3029C2_A_HR-RV3029C2_A_SC] = bin2bcd(tm->tm_hour & 0x3f);
-	regs[RV3029C2_A_DT-RV3029C2_A_SC] = bin2bcd(tm->tm_mday & 0x3f);
-	regs[RV3029C2_A_MO-RV3029C2_A_SC] = bin2bcd((tm->tm_mon & 0x1f) - 1);
-	regs[RV3029C2_A_DW-RV3029C2_A_SC] = bin2bcd((tm->tm_wday & 7) - 1);
-	regs[RV3029C2_A_YR-RV3029C2_A_SC] = bin2bcd((tm->tm_year & 0x7f) - 100);
-
-	ret = rv3029c2_i2c_write_regs(client, RV3029C2_A_SC, regs,
-					RV3029C2_ALARM_SECTION_LEN);
+	regs[RV3029_A_SC-RV3029_A_SC] = bin2bcd(tm->tm_sec & 0x7f);
+	regs[RV3029_A_MN-RV3029_A_SC] = bin2bcd(tm->tm_min & 0x7f);
+	regs[RV3029_A_HR-RV3029_A_SC] = bin2bcd(tm->tm_hour & 0x3f);
+	regs[RV3029_A_DT-RV3029_A_SC] = bin2bcd(tm->tm_mday & 0x3f);
+	regs[RV3029_A_MO-RV3029_A_SC] = bin2bcd((tm->tm_mon & 0x1f) - 1);
+	regs[RV3029_A_DW-RV3029_A_SC] = bin2bcd((tm->tm_wday & 7) - 1);
+	regs[RV3029_A_YR-RV3029_A_SC] = bin2bcd((tm->tm_year & 0x7f) - 100);
+
+	ret = rv3029_i2c_write_regs(client, RV3029_A_SC, regs,
+				    RV3029_ALARM_SECTION_LEN);
 	if (ret < 0)
 		return ret;
 
 	if (alarm->enabled) {
-		u8 buf[1];
-
 		/* clear AF flag */
-		ret = rv3029c2_i2c_read_regs(client, RV3029C2_IRQ_FLAGS,
-						buf, 1);
-		if (ret < 0) {
-			dev_err(&client->dev, "can't read alarm flag\n");
-			return ret;
-		}
-		buf[0] &= ~RV3029C2_IRQ_FLAGS_AF;
-		ret = rv3029c2_i2c_write_regs(client, RV3029C2_IRQ_FLAGS,
-						buf, 1);
+		ret = rv3029_i2c_update_bits(client, RV3029_IRQ_FLAGS,
+					     RV3029_IRQ_FLAGS_AF, 0);
 		if (ret < 0) {
-			dev_err(&client->dev, "can't set alarm flag\n");
+			dev_err(&client->dev, "can't clear alarm flag\n");
 			return ret;
 		}
 		/* enable AIE irq */
-		ret = rv3029c2_rtc_i2c_alarm_set_irq(client, 1);
+		ret = rv3029_rtc_i2c_alarm_set_irq(client, 1);
 		if (ret)
 			return ret;
 
 		dev_dbg(&client->dev, "alarm IRQ armed\n");
 	} else {
 		/* disable AIE irq */
-		ret = rv3029c2_rtc_i2c_alarm_set_irq(client, 0);
+		ret = rv3029_rtc_i2c_alarm_set_irq(client, 0);
 		if (ret)
 			return ret;
 
@@ -320,13 +493,13 @@ static int rv3029c2_rtc_i2c_set_alarm(struct i2c_client *client,
 	return 0;
 }
 
-static int rv3029c2_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
+static int rv3029_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 {
-	return rv3029c2_rtc_i2c_set_alarm(to_i2c_client(dev), alarm);
+	return rv3029_rtc_i2c_set_alarm(to_i2c_client(dev), alarm);
 }
 
 static int
-rv3029c2_i2c_set_time(struct i2c_client *client, struct rtc_time const *tm)
+rv3029_i2c_set_time(struct i2c_client *client, struct rtc_time const *tm)
 {
 	u8 regs[8];
 	int ret;
@@ -339,26 +512,26 @@ rv3029c2_i2c_set_time(struct i2c_client *client, struct rtc_time const *tm)
 	if (tm->tm_year < 100)
 		return -EINVAL;
 
-	regs[RV3029C2_W_SEC-RV3029C2_W_SEC] = bin2bcd(tm->tm_sec);
-	regs[RV3029C2_W_MINUTES-RV3029C2_W_SEC] = bin2bcd(tm->tm_min);
-	regs[RV3029C2_W_HOURS-RV3029C2_W_SEC] = bin2bcd(tm->tm_hour);
-	regs[RV3029C2_W_DATE-RV3029C2_W_SEC] = bin2bcd(tm->tm_mday);
-	regs[RV3029C2_W_MONTHS-RV3029C2_W_SEC] = bin2bcd(tm->tm_mon+1);
-	regs[RV3029C2_W_DAYS-RV3029C2_W_SEC] = bin2bcd((tm->tm_wday & 7)+1);
-	regs[RV3029C2_W_YEARS-RV3029C2_W_SEC] = bin2bcd(tm->tm_year - 100);
+	regs[RV3029_W_SEC-RV3029_W_SEC] = bin2bcd(tm->tm_sec);
+	regs[RV3029_W_MINUTES-RV3029_W_SEC] = bin2bcd(tm->tm_min);
+	regs[RV3029_W_HOURS-RV3029_W_SEC] = bin2bcd(tm->tm_hour);
+	regs[RV3029_W_DATE-RV3029_W_SEC] = bin2bcd(tm->tm_mday);
+	regs[RV3029_W_MONTHS-RV3029_W_SEC] = bin2bcd(tm->tm_mon+1);
+	regs[RV3029_W_DAYS-RV3029_W_SEC] = bin2bcd((tm->tm_wday & 7)+1);
+	regs[RV3029_W_YEARS-RV3029_W_SEC] = bin2bcd(tm->tm_year - 100);
 
-	ret = rv3029c2_i2c_write_regs(client, RV3029C2_W_SEC, regs,
-					RV3029C2_WATCH_SECTION_LEN);
+	ret = rv3029_i2c_write_regs(client, RV3029_W_SEC, regs,
+				    RV3029_WATCH_SECTION_LEN);
 	if (ret < 0)
 		return ret;
 
-	ret = rv3029c2_i2c_get_sr(client, regs);
+	ret = rv3029_i2c_get_sr(client, regs);
 	if (ret < 0) {
 		dev_err(&client->dev, "%s: reading SR failed\n", __func__);
 		return ret;
 	}
 	/* clear PON bit */
-	ret = rv3029c2_i2c_set_sr(client, (regs[0] & ~RV3029C2_STATUS_PON));
+	ret = rv3029_i2c_set_sr(client, (regs[0] & ~RV3029_STATUS_PON));
 	if (ret < 0) {
 		dev_err(&client->dev, "%s: reading SR failed\n", __func__);
 		return ret;
@@ -367,26 +540,238 @@ rv3029c2_i2c_set_time(struct i2c_client *client, struct rtc_time const *tm)
 	return 0;
 }
 
-static int rv3029c2_rtc_set_time(struct device *dev, struct rtc_time *tm)
+static int rv3029_rtc_set_time(struct device *dev, struct rtc_time *tm)
 {
-	return rv3029c2_i2c_set_time(to_i2c_client(dev), tm);
+	return rv3029_i2c_set_time(to_i2c_client(dev), tm);
 }
 
-static const struct rtc_class_ops rv3029c2_rtc_ops = {
-	.read_time	= rv3029c2_rtc_read_time,
-	.set_time	= rv3029c2_rtc_set_time,
-	.read_alarm	= rv3029c2_rtc_read_alarm,
-	.set_alarm	= rv3029c2_rtc_set_alarm,
+static const struct rv3029_trickle_tab_elem {
+	u32 r;		/* resistance in ohms */
+	u8 conf;	/* trickle config bits */
+} rv3029_trickle_tab[] = {
+	{
+		.r	= 1076,
+		.conf	= RV3029_TRICKLE_1K | RV3029_TRICKLE_5K |
+			  RV3029_TRICKLE_20K | RV3029_TRICKLE_80K,
+	}, {
+		.r	= 1091,
+		.conf	= RV3029_TRICKLE_1K | RV3029_TRICKLE_5K |
+			  RV3029_TRICKLE_20K,
+	}, {
+		.r	= 1137,
+		.conf	= RV3029_TRICKLE_1K | RV3029_TRICKLE_5K |
+			  RV3029_TRICKLE_80K,
+	}, {
+		.r	= 1154,
+		.conf	= RV3029_TRICKLE_1K | RV3029_TRICKLE_5K,
+	}, {
+		.r	= 1371,
+		.conf	= RV3029_TRICKLE_1K | RV3029_TRICKLE_20K |
+			  RV3029_TRICKLE_80K,
+	}, {
+		.r	= 1395,
+		.conf	= RV3029_TRICKLE_1K | RV3029_TRICKLE_20K,
+	}, {
+		.r	= 1472,
+		.conf	= RV3029_TRICKLE_1K | RV3029_TRICKLE_80K,
+	}, {
+		.r	= 1500,
+		.conf	= RV3029_TRICKLE_1K,
+	}, {
+		.r	= 3810,
+		.conf	= RV3029_TRICKLE_5K | RV3029_TRICKLE_20K |
+			  RV3029_TRICKLE_80K,
+	}, {
+		.r	= 4000,
+		.conf	= RV3029_TRICKLE_5K | RV3029_TRICKLE_20K,
+	}, {
+		.r	= 4706,
+		.conf	= RV3029_TRICKLE_5K | RV3029_TRICKLE_80K,
+	}, {
+		.r	= 5000,
+		.conf	= RV3029_TRICKLE_5K,
+	}, {
+		.r	= 16000,
+		.conf	= RV3029_TRICKLE_20K | RV3029_TRICKLE_80K,
+	}, {
+		.r	= 20000,
+		.conf	= RV3029_TRICKLE_20K,
+	}, {
+		.r	= 80000,
+		.conf	= RV3029_TRICKLE_80K,
+	},
 };
 
-static struct i2c_device_id rv3029c2_id[] = {
+static void rv3029_trickle_config(struct i2c_client *client)
+{
+	struct device_node *of_node = client->dev.of_node;
+	const struct rv3029_trickle_tab_elem *elem;
+	int i, err;
+	u32 ohms;
+	u8 trickle_set_bits;
+
+	if (!of_node)
+		return;
+
+	/* Configure the trickle charger. */
+	err = of_property_read_u32(of_node, "trickle-resistor-ohms", &ohms);
+	if (err) {
+		/* Disable trickle charger. */
+		trickle_set_bits = 0;
+	} else {
+		/* Enable trickle charger. */
+		for (i = 0; i < ARRAY_SIZE(rv3029_trickle_tab); i++) {
+			elem = &rv3029_trickle_tab[i];
+			if (elem->r >= ohms)
+				break;
+		}
+		trickle_set_bits = elem->conf;
+		dev_info(&client->dev,
+			 "Trickle charger enabled at %d ohms resistance.\n",
+			 elem->r);
+	}
+	err = rv3029_eeprom_update_bits(client, RV3029_CONTROL_E2P_EECTRL,
+					RV3029_TRICKLE_MASK,
+					trickle_set_bits);
+	if (err < 0) {
+		dev_err(&client->dev,
+			"Failed to update trickle charger config\n");
+	}
+}
+
+#ifdef CONFIG_RTC_DRV_RV3029_HWMON
+
+static int rv3029_read_temp(struct i2c_client *client, int *temp_mC)
+{
+	int ret;
+	u8 temp;
+
+	ret = rv3029_i2c_read_regs(client, RV3029_TEMP_PAGE, &temp, 1);
+	if (ret < 0)
+		return ret;
+
+	*temp_mC = ((int)temp - 60) * 1000;
+
+	return 0;
+}
+
+static ssize_t rv3029_hwmon_show_temp(struct device *dev,
+				      struct device_attribute *attr,
+				      char *buf)
+{
+	struct i2c_client *client = dev_get_drvdata(dev);
+	int ret, temp_mC;
+
+	ret = rv3029_read_temp(client, &temp_mC);
+	if (ret < 0)
+		return ret;
+
+	return sprintf(buf, "%d\n", temp_mC);
+}
+
+static ssize_t rv3029_hwmon_set_update_interval(struct device *dev,
+						struct device_attribute *attr,
+						const char *buf,
+						size_t count)
+{
+	struct i2c_client *client = dev_get_drvdata(dev);
+	unsigned long interval_ms;
+	int ret;
+	u8 th_set_bits = 0;
+
+	ret = kstrtoul(buf, 10, &interval_ms);
+	if (ret < 0)
+		return ret;
+
+	if (interval_ms != 0) {
+		th_set_bits |= RV3029_EECTRL_THE;
+		if (interval_ms >= 16000)
+			th_set_bits |= RV3029_EECTRL_THP;
+	}
+	ret = rv3029_eeprom_update_bits(client, RV3029_CONTROL_E2P_EECTRL,
+					RV3029_EECTRL_THE | RV3029_EECTRL_THP,
+					th_set_bits);
+	if (ret < 0)
+		return ret;
+
+	return count;
+}
+
+static ssize_t rv3029_hwmon_show_update_interval(struct device *dev,
+						 struct device_attribute *attr,
+						 char *buf)
+{
+	struct i2c_client *client = dev_get_drvdata(dev);
+	int ret, interval_ms;
+	u8 eectrl;
+
+	ret = rv3029_eeprom_read(client, RV3029_CONTROL_E2P_EECTRL,
+				 &eectrl, 1);
+	if (ret < 0)
+		return ret;
+
+	if (eectrl & RV3029_EECTRL_THE) {
+		if (eectrl & RV3029_EECTRL_THP)
+			interval_ms = 16000;
+		else
+			interval_ms = 1000;
+	} else {
+		interval_ms = 0;
+	}
+
+	return sprintf(buf, "%d\n", interval_ms);
+}
+
+static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, rv3029_hwmon_show_temp,
+			  NULL, 0);
+static SENSOR_DEVICE_ATTR(update_interval, S_IWUSR | S_IRUGO,
+			  rv3029_hwmon_show_update_interval,
+			  rv3029_hwmon_set_update_interval, 0);
+
+static struct attribute *rv3029_hwmon_attrs[] = {
+	&sensor_dev_attr_temp1_input.dev_attr.attr,
+	&sensor_dev_attr_update_interval.dev_attr.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(rv3029_hwmon);
+
+static void rv3029_hwmon_register(struct i2c_client *client)
+{
+	struct device *hwmon_dev;
+
+	hwmon_dev = devm_hwmon_device_register_with_groups(
+		&client->dev, client->name, client, rv3029_hwmon_groups);
+	if (IS_ERR(hwmon_dev)) {
+		dev_warn(&client->dev,
+			"unable to register hwmon device %ld\n",
+			PTR_ERR(hwmon_dev));
+	}
+}
+
+#else /* CONFIG_RTC_DRV_RV3029_HWMON */
+
+static void rv3029_hwmon_register(struct i2c_client *client)
+{
+}
+
+#endif /* CONFIG_RTC_DRV_RV3029_HWMON */
+
+static const struct rtc_class_ops rv3029_rtc_ops = {
+	.read_time	= rv3029_rtc_read_time,
+	.set_time	= rv3029_rtc_set_time,
+	.read_alarm	= rv3029_rtc_read_alarm,
+	.set_alarm	= rv3029_rtc_set_alarm,
+};
+
+static struct i2c_device_id rv3029_id[] = {
+	{ "rv3029", 0 },
 	{ "rv3029c2", 0 },
 	{ }
 };
-MODULE_DEVICE_TABLE(i2c, rv3029c2_id);
+MODULE_DEVICE_TABLE(i2c, rv3029_id);
 
-static int rv3029c2_probe(struct i2c_client *client,
-			  const struct i2c_device_id *id)
+static int rv3029_probe(struct i2c_client *client,
+			const struct i2c_device_id *id)
 {
 	struct rtc_device *rtc;
 	int rc = 0;
@@ -395,14 +780,17 @@ static int rv3029c2_probe(struct i2c_client *client,
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_EMUL))
 		return -ENODEV;
 
-	rc = rv3029c2_i2c_get_sr(client, buf);
+	rc = rv3029_i2c_get_sr(client, buf);
 	if (rc < 0) {
 		dev_err(&client->dev, "reading status failed\n");
 		return rc;
 	}
 
+	rv3029_trickle_config(client);
+	rv3029_hwmon_register(client);
+
 	rtc = devm_rtc_device_register(&client->dev, client->name,
-					&rv3029c2_rtc_ops, THIS_MODULE);
+				       &rv3029_rtc_ops, THIS_MODULE);
 
 	if (IS_ERR(rtc))
 		return PTR_ERR(rtc);
@@ -412,16 +800,17 @@ static int rv3029c2_probe(struct i2c_client *client,
 	return 0;
 }
 
-static struct i2c_driver rv3029c2_driver = {
+static struct i2c_driver rv3029_driver = {
 	.driver = {
 		.name = "rtc-rv3029c2",
 	},
-	.probe = rv3029c2_probe,
-	.id_table = rv3029c2_id,
+	.probe		= rv3029_probe,
+	.id_table	= rv3029_id,
 };
 
-module_i2c_driver(rv3029c2_driver);
+module_i2c_driver(rv3029_driver);
 
 MODULE_AUTHOR("Gregory Hermant <gregory.hermant@calao-systems.com>");
-MODULE_DESCRIPTION("Micro Crystal RV3029C2 RTC driver");
+MODULE_AUTHOR("Michael Buesch <m@bues.ch>");
+MODULE_DESCRIPTION("Micro Crystal RV3029 RTC driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c
index 7155c0816aa6..8d9f35ceb808 100644
--- a/drivers/rtc/rtc-rv8803.c
+++ b/drivers/rtc/rtc-rv8803.c
@@ -52,7 +52,7 @@
 struct rv8803_data {
 	struct i2c_client *client;
 	struct rtc_device *rtc;
-	spinlock_t flags_lock;
+	struct mutex flags_lock;
 	u8 ctrl;
 };
 
@@ -63,11 +63,11 @@ static irqreturn_t rv8803_handle_irq(int irq, void *dev_id)
 	unsigned long events = 0;
 	int flags;
 
-	spin_lock(&rv8803->flags_lock);
+	mutex_lock(&rv8803->flags_lock);
 
 	flags = i2c_smbus_read_byte_data(client, RV8803_FLAG);
 	if (flags <= 0) {
-		spin_unlock(&rv8803->flags_lock);
+		mutex_unlock(&rv8803->flags_lock);
 		return IRQ_NONE;
 	}
 
@@ -102,7 +102,7 @@ static irqreturn_t rv8803_handle_irq(int irq, void *dev_id)
 					  rv8803->ctrl);
 	}
 
-	spin_unlock(&rv8803->flags_lock);
+	mutex_unlock(&rv8803->flags_lock);
 
 	return IRQ_HANDLED;
 }
@@ -155,7 +155,6 @@ static int rv8803_set_time(struct device *dev, struct rtc_time *tm)
 	struct rv8803_data *rv8803 = dev_get_drvdata(dev);
 	u8 date[7];
 	int flags, ret;
-	unsigned long irqflags;
 
 	if ((tm->tm_year < 100) || (tm->tm_year > 199))
 		return -EINVAL;
@@ -173,18 +172,18 @@ static int rv8803_set_time(struct device *dev, struct rtc_time *tm)
 	if (ret < 0)
 		return ret;
 
-	spin_lock_irqsave(&rv8803->flags_lock, irqflags);
+	mutex_lock(&rv8803->flags_lock);
 
 	flags = i2c_smbus_read_byte_data(rv8803->client, RV8803_FLAG);
 	if (flags < 0) {
-		spin_unlock_irqrestore(&rv8803->flags_lock, irqflags);
+		mutex_unlock(&rv8803->flags_lock);
 		return flags;
 	}
 
 	ret = i2c_smbus_write_byte_data(rv8803->client, RV8803_FLAG,
 					flags & ~RV8803_FLAG_V2F);
 
-	spin_unlock_irqrestore(&rv8803->flags_lock, irqflags);
+	mutex_unlock(&rv8803->flags_lock);
 
 	return ret;
 }
@@ -226,7 +225,6 @@ static int rv8803_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	u8 alarmvals[3];
 	u8 ctrl[2];
 	int ret, err;
-	unsigned long irqflags;
 
 	/* The alarm has no seconds, round up to nearest minute */
 	if (alrm->time.tm_sec) {
@@ -236,11 +234,11 @@ static int rv8803_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 		rtc_time64_to_tm(alarm_time, &alrm->time);
 	}
 
-	spin_lock_irqsave(&rv8803->flags_lock, irqflags);
+	mutex_lock(&rv8803->flags_lock);
 
 	ret = i2c_smbus_read_i2c_block_data(client, RV8803_FLAG, 2, ctrl);
 	if (ret != 2) {
-		spin_unlock_irqrestore(&rv8803->flags_lock, irqflags);
+		mutex_unlock(&rv8803->flags_lock);
 		return ret < 0 ? ret : -EIO;
 	}
 
@@ -253,14 +251,14 @@ static int rv8803_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 		err = i2c_smbus_write_byte_data(rv8803->client, RV8803_CTRL,
 						rv8803->ctrl);
 		if (err) {
-			spin_unlock_irqrestore(&rv8803->flags_lock, irqflags);
+			mutex_unlock(&rv8803->flags_lock);
 			return err;
 		}
 	}
 
 	ctrl[1] &= ~RV8803_FLAG_AF;
 	err = i2c_smbus_write_byte_data(rv8803->client, RV8803_FLAG, ctrl[1]);
-	spin_unlock_irqrestore(&rv8803->flags_lock, irqflags);
+	mutex_unlock(&rv8803->flags_lock);
 	if (err)
 		return err;
 
@@ -289,7 +287,6 @@ static int rv8803_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	struct i2c_client *client = to_i2c_client(dev);
 	struct rv8803_data *rv8803 = dev_get_drvdata(dev);
 	int ctrl, flags, err;
-	unsigned long irqflags;
 
 	ctrl = rv8803->ctrl;
 
@@ -305,15 +302,15 @@ static int rv8803_alarm_irq_enable(struct device *dev, unsigned int enabled)
 			ctrl &= ~RV8803_CTRL_AIE;
 	}
 
-	spin_lock_irqsave(&rv8803->flags_lock, irqflags);
+	mutex_lock(&rv8803->flags_lock);
 	flags = i2c_smbus_read_byte_data(client, RV8803_FLAG);
 	if (flags < 0) {
-		spin_unlock_irqrestore(&rv8803->flags_lock, irqflags);
+		mutex_unlock(&rv8803->flags_lock);
 		return flags;
 	}
 	flags &= ~(RV8803_FLAG_AF | RV8803_FLAG_UF);
 	err = i2c_smbus_write_byte_data(client, RV8803_FLAG, flags);
-	spin_unlock_irqrestore(&rv8803->flags_lock, irqflags);
+	mutex_unlock(&rv8803->flags_lock);
 	if (err)
 		return err;
 
@@ -333,7 +330,6 @@ static int rv8803_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
 	struct i2c_client *client = to_i2c_client(dev);
 	struct rv8803_data *rv8803 = dev_get_drvdata(dev);
 	int flags, ret = 0;
-	unsigned long irqflags;
 
 	switch (cmd) {
 	case RTC_VL_READ:
@@ -355,16 +351,16 @@ static int rv8803_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
 		return 0;
 
 	case RTC_VL_CLR:
-		spin_lock_irqsave(&rv8803->flags_lock, irqflags);
+		mutex_lock(&rv8803->flags_lock);
 		flags = i2c_smbus_read_byte_data(client, RV8803_FLAG);
 		if (flags < 0) {
-			spin_unlock_irqrestore(&rv8803->flags_lock, irqflags);
+			mutex_unlock(&rv8803->flags_lock);
 			return flags;
 		}
 
 		flags &= ~(RV8803_FLAG_V1F | RV8803_FLAG_V2F);
 		ret = i2c_smbus_write_byte_data(client, RV8803_FLAG, flags);
-		spin_unlock_irqrestore(&rv8803->flags_lock, irqflags);
+		mutex_unlock(&rv8803->flags_lock);
 		if (ret < 0)
 			return ret;
 
@@ -441,6 +437,7 @@ static int rv8803_probe(struct i2c_client *client,
 	if (!rv8803)
 		return -ENOMEM;
 
+	mutex_init(&rv8803->flags_lock);
 	rv8803->client = client;
 	i2c_set_clientdata(client, rv8803);
 
diff --git a/drivers/rtc/rtc-rx6110.c b/drivers/rtc/rtc-rx6110.c
new file mode 100644
index 000000000000..bbad00b233bc
--- /dev/null
+++ b/drivers/rtc/rtc-rx6110.c
@@ -0,0 +1,402 @@
+/*
+ * Driver for the Epson RTC module RX-6110 SA
+ *
+ * Copyright(C) 2015 Pengutronix, Steffen Trumtrar <kernel@pengutronix.de>
+ * Copyright(C) SEIKO EPSON CORPORATION 2013. All rights reserved.
+ *
+ * This driver software is distributed as is, without any warranty of any kind,
+ * either express or implied as further specified in the GNU Public License.
+ * This software may be used and distributed according to the terms of the GNU
+ * Public License, version 2 as published by the Free Software Foundation.
+ * See the file COPYING in the main directory of this archive for more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/bcd.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_gpio.h>
+#include <linux/regmap.h>
+#include <linux/rtc.h>
+#include <linux/spi/spi.h>
+
+/* RX-6110 Register definitions */
+#define RX6110_REG_SEC		0x10
+#define RX6110_REG_MIN		0x11
+#define RX6110_REG_HOUR		0x12
+#define RX6110_REG_WDAY		0x13
+#define RX6110_REG_MDAY		0x14
+#define RX6110_REG_MONTH	0x15
+#define RX6110_REG_YEAR		0x16
+#define RX6110_REG_RES1		0x17
+#define RX6110_REG_ALMIN	0x18
+#define RX6110_REG_ALHOUR	0x19
+#define RX6110_REG_ALWDAY	0x1A
+#define RX6110_REG_TCOUNT0	0x1B
+#define RX6110_REG_TCOUNT1	0x1C
+#define RX6110_REG_EXT		0x1D
+#define RX6110_REG_FLAG		0x1E
+#define RX6110_REG_CTRL		0x1F
+#define RX6110_REG_USER0	0x20
+#define RX6110_REG_USER1	0x21
+#define RX6110_REG_USER2	0x22
+#define RX6110_REG_USER3	0x23
+#define RX6110_REG_USER4	0x24
+#define RX6110_REG_USER5	0x25
+#define RX6110_REG_USER6	0x26
+#define RX6110_REG_USER7	0x27
+#define RX6110_REG_USER8	0x28
+#define RX6110_REG_USER9	0x29
+#define RX6110_REG_USERA	0x2A
+#define RX6110_REG_USERB	0x2B
+#define RX6110_REG_USERC	0x2C
+#define RX6110_REG_USERD	0x2D
+#define RX6110_REG_USERE	0x2E
+#define RX6110_REG_USERF	0x2F
+#define RX6110_REG_RES2		0x30
+#define RX6110_REG_RES3		0x31
+#define RX6110_REG_IRQ		0x32
+
+#define RX6110_BIT_ALARM_EN		BIT(7)
+
+/* Extension Register (1Dh) bit positions */
+#define RX6110_BIT_EXT_TSEL0		BIT(0)
+#define RX6110_BIT_EXT_TSEL1		BIT(1)
+#define RX6110_BIT_EXT_TSEL2		BIT(2)
+#define RX6110_BIT_EXT_WADA		BIT(3)
+#define RX6110_BIT_EXT_TE		BIT(4)
+#define RX6110_BIT_EXT_USEL		BIT(5)
+#define RX6110_BIT_EXT_FSEL0		BIT(6)
+#define RX6110_BIT_EXT_FSEL1		BIT(7)
+
+/* Flag Register (1Eh) bit positions */
+#define RX6110_BIT_FLAG_VLF		BIT(1)
+#define RX6110_BIT_FLAG_AF		BIT(3)
+#define RX6110_BIT_FLAG_TF		BIT(4)
+#define RX6110_BIT_FLAG_UF		BIT(5)
+
+/* Control Register (1Fh) bit positions */
+#define RX6110_BIT_CTRL_TBKE		BIT(0)
+#define RX6110_BIT_CTRL_TBKON		BIT(1)
+#define RX6110_BIT_CTRL_TSTP		BIT(2)
+#define RX6110_BIT_CTRL_AIE		BIT(3)
+#define RX6110_BIT_CTRL_TIE		BIT(4)
+#define RX6110_BIT_CTRL_UIE		BIT(5)
+#define RX6110_BIT_CTRL_STOP		BIT(6)
+#define RX6110_BIT_CTRL_TEST		BIT(7)
+
+enum {
+	RTC_SEC = 0,
+	RTC_MIN,
+	RTC_HOUR,
+	RTC_WDAY,
+	RTC_MDAY,
+	RTC_MONTH,
+	RTC_YEAR,
+	RTC_NR_TIME
+};
+
+#define RX6110_DRIVER_NAME		"rx6110"
+
+struct rx6110_data {
+	struct rtc_device *rtc;
+	struct regmap *regmap;
+};
+
+/**
+ * rx6110_rtc_tm_to_data - convert rtc_time to native time encoding
+ *
+ * @tm: holds date and time
+ * @data: holds the encoding in rx6110 native form
+ */
+static int rx6110_rtc_tm_to_data(struct rtc_time *tm, u8 *data)
+{
+	pr_debug("%s: date %ds %dm %dh %dmd %dm %dy\n", __func__,
+		 tm->tm_sec, tm->tm_min, tm->tm_hour,
+		 tm->tm_mday, tm->tm_mon, tm->tm_year);
+
+	/*
+	 * The year in the RTC is a value between 0 and 99.
+	 * Assume that this represents the current century
+	 * and disregard all other values.
+	 */
+	if (tm->tm_year < 100 || tm->tm_year >= 200)
+		return -EINVAL;
+
+	data[RTC_SEC] = bin2bcd(tm->tm_sec);
+	data[RTC_MIN] = bin2bcd(tm->tm_min);
+	data[RTC_HOUR] = bin2bcd(tm->tm_hour);
+	data[RTC_WDAY] = BIT(bin2bcd(tm->tm_wday));
+	data[RTC_MDAY] = bin2bcd(tm->tm_mday);
+	data[RTC_MONTH] = bin2bcd(tm->tm_mon + 1);
+	data[RTC_YEAR] = bin2bcd(tm->tm_year % 100);
+
+	return 0;
+}
+
+/**
+ * rx6110_data_to_rtc_tm - convert native time encoding to rtc_time
+ *
+ * @data: holds the encoding in rx6110 native form
+ * @tm: holds date and time
+ */
+static int rx6110_data_to_rtc_tm(u8 *data, struct rtc_time *tm)
+{
+	tm->tm_sec = bcd2bin(data[RTC_SEC] & 0x7f);
+	tm->tm_min = bcd2bin(data[RTC_MIN] & 0x7f);
+	/* only 24-hour clock */
+	tm->tm_hour = bcd2bin(data[RTC_HOUR] & 0x3f);
+	tm->tm_wday = ffs(data[RTC_WDAY] & 0x7f);
+	tm->tm_mday = bcd2bin(data[RTC_MDAY] & 0x3f);
+	tm->tm_mon = bcd2bin(data[RTC_MONTH] & 0x1f) - 1;
+	tm->tm_year = bcd2bin(data[RTC_YEAR]) + 100;
+
+	pr_debug("%s: date %ds %dm %dh %dmd %dm %dy\n", __func__,
+		 tm->tm_sec, tm->tm_min, tm->tm_hour,
+		 tm->tm_mday, tm->tm_mon, tm->tm_year);
+
+	/*
+	 * The year in the RTC is a value between 0 and 99.
+	 * Assume that this represents the current century
+	 * and disregard all other values.
+	 */
+	if (tm->tm_year < 100 || tm->tm_year >= 200)
+		return -EINVAL;
+
+	return 0;
+}
+
+/**
+ * rx6110_set_time - set the current time in the rx6110 registers
+ *
+ * @dev: the rtc device in use
+ * @tm: holds date and time
+ *
+ * BUG: The HW assumes every year that is a multiple of 4 to be a leap
+ * year. Next time this is wrong is 2100, which will not be a leap year
+ *
+ * Note: If STOP is not set/cleared, the clock will start when the seconds
+ *       register is written
+ *
+ */
+static int rx6110_set_time(struct device *dev, struct rtc_time *tm)
+{
+	struct rx6110_data *rx6110 = dev_get_drvdata(dev);
+	u8 data[RTC_NR_TIME];
+	int ret;
+
+	ret = rx6110_rtc_tm_to_data(tm, data);
+	if (ret < 0)
+		return ret;
+
+	/* set STOP bit before changing clock/calendar */
+	ret = regmap_update_bits(rx6110->regmap, RX6110_REG_CTRL,
+				 RX6110_BIT_CTRL_STOP, RX6110_BIT_CTRL_STOP);
+	if (ret)
+		return ret;
+
+	ret = regmap_bulk_write(rx6110->regmap, RX6110_REG_SEC, data,
+				RTC_NR_TIME);
+	if (ret)
+		return ret;
+
+	/* The time in the RTC is valid. Be sure to have VLF cleared. */
+	ret = regmap_update_bits(rx6110->regmap, RX6110_REG_FLAG,
+				 RX6110_BIT_FLAG_VLF, 0);
+	if (ret)
+		return ret;
+
+	/* clear STOP bit after changing clock/calendar */
+	ret = regmap_update_bits(rx6110->regmap, RX6110_REG_CTRL,
+				 RX6110_BIT_CTRL_STOP, 0);
+
+	return ret;
+}
+
+/**
+ * rx6110_get_time - get the current time from the rx6110 registers
+ * @dev: the rtc device in use
+ * @tm: holds date and time
+ */
+static int rx6110_get_time(struct device *dev, struct rtc_time *tm)
+{
+	struct rx6110_data *rx6110 = dev_get_drvdata(dev);
+	u8 data[RTC_NR_TIME];
+	int flags;
+	int ret;
+
+	ret = regmap_read(rx6110->regmap, RX6110_REG_FLAG, &flags);
+	if (ret)
+		return -EINVAL;
+
+	/* check for VLF Flag (set at power-on) */
+	if ((flags & RX6110_BIT_FLAG_VLF)) {
+		dev_warn(dev, "Voltage low, data is invalid.\n");
+		return -EINVAL;
+	}
+
+	/* read registers to date */
+	ret = regmap_bulk_read(rx6110->regmap, RX6110_REG_SEC, data,
+			       RTC_NR_TIME);
+	if (ret)
+		return ret;
+
+	ret = rx6110_data_to_rtc_tm(data, tm);
+	if (ret)
+		return ret;
+
+	dev_dbg(dev, "%s: date %ds %dm %dh %dmd %dm %dy\n", __func__,
+		tm->tm_sec, tm->tm_min, tm->tm_hour,
+		tm->tm_mday, tm->tm_mon, tm->tm_year);
+
+	return rtc_valid_tm(tm);
+}
+
+static const struct reg_sequence rx6110_default_regs[] = {
+	{ RX6110_REG_RES1,   0xB8 },
+	{ RX6110_REG_RES2,   0x00 },
+	{ RX6110_REG_RES3,   0x10 },
+	{ RX6110_REG_IRQ,    0x00 },
+	{ RX6110_REG_ALMIN,  0x00 },
+	{ RX6110_REG_ALHOUR, 0x00 },
+	{ RX6110_REG_ALWDAY, 0x00 },
+};
+
+/**
+ * rx6110_init - initialize the rx6110 registers
+ *
+ * @rx6110: pointer to the rx6110 struct in use
+ *
+ */
+static int rx6110_init(struct rx6110_data *rx6110)
+{
+	struct rtc_device *rtc = rx6110->rtc;
+	int flags;
+	int ret;
+
+	ret = regmap_update_bits(rx6110->regmap, RX6110_REG_EXT,
+				 RX6110_BIT_EXT_TE, 0);
+	if (ret)
+		return ret;
+
+	ret = regmap_register_patch(rx6110->regmap, rx6110_default_regs,
+				    ARRAY_SIZE(rx6110_default_regs));
+	if (ret)
+		return ret;
+
+	ret = regmap_read(rx6110->regmap, RX6110_REG_FLAG, &flags);
+	if (ret)
+		return ret;
+
+	/* check for VLF Flag (set at power-on) */
+	if ((flags & RX6110_BIT_FLAG_VLF))
+		dev_warn(&rtc->dev, "Voltage low, data loss detected.\n");
+
+	/* check for Alarm Flag */
+	if (flags & RX6110_BIT_FLAG_AF)
+		dev_warn(&rtc->dev, "An alarm may have been missed.\n");
+
+	/* check for Periodic Timer Flag */
+	if (flags & RX6110_BIT_FLAG_TF)
+		dev_warn(&rtc->dev, "Periodic timer was detected\n");
+
+	/* check for Update Timer Flag */
+	if (flags & RX6110_BIT_FLAG_UF)
+		dev_warn(&rtc->dev, "Update timer was detected\n");
+
+	/* clear all flags BUT VLF */
+	ret = regmap_update_bits(rx6110->regmap, RX6110_REG_FLAG,
+				 RX6110_BIT_FLAG_AF |
+				 RX6110_BIT_FLAG_UF |
+				 RX6110_BIT_FLAG_TF,
+				 0);
+
+	return ret;
+}
+
+static struct rtc_class_ops rx6110_rtc_ops = {
+	.read_time = rx6110_get_time,
+	.set_time = rx6110_set_time,
+};
+
+static struct regmap_config regmap_spi_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = RX6110_REG_IRQ,
+	.read_flag_mask = 0x80,
+};
+
+/**
+ * rx6110_probe - initialize rtc driver
+ * @spi: pointer to spi device
+ */
+static int rx6110_probe(struct spi_device *spi)
+{
+	struct rx6110_data *rx6110;
+	int err;
+
+	if ((spi->bits_per_word && spi->bits_per_word != 8) ||
+	    (spi->max_speed_hz > 2000000) ||
+	    (spi->mode != (SPI_CS_HIGH | SPI_CPOL | SPI_CPHA))) {
+		dev_warn(&spi->dev, "SPI settings: bits_per_word: %d, max_speed_hz: %d, mode: %xh\n",
+			 spi->bits_per_word, spi->max_speed_hz, spi->mode);
+		dev_warn(&spi->dev, "driving device in an unsupported mode");
+	}
+
+	rx6110 = devm_kzalloc(&spi->dev, sizeof(*rx6110), GFP_KERNEL);
+	if (!rx6110)
+		return -ENOMEM;
+
+	rx6110->regmap = devm_regmap_init_spi(spi, &regmap_spi_config);
+	if (IS_ERR(rx6110->regmap)) {
+		dev_err(&spi->dev, "regmap init failed for rtc rx6110\n");
+		return PTR_ERR(rx6110->regmap);
+	}
+
+	spi_set_drvdata(spi, rx6110);
+
+	rx6110->rtc = devm_rtc_device_register(&spi->dev,
+					       RX6110_DRIVER_NAME,
+					       &rx6110_rtc_ops, THIS_MODULE);
+
+	if (IS_ERR(rx6110->rtc))
+		return PTR_ERR(rx6110->rtc);
+
+	err = rx6110_init(rx6110);
+	if (err)
+		return err;
+
+	rx6110->rtc->max_user_freq = 1;
+
+	return 0;
+}
+
+static int rx6110_remove(struct spi_device *spi)
+{
+	return 0;
+}
+
+static const struct spi_device_id rx6110_id[] = {
+	{ "rx6110", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, rx6110_id);
+
+static struct spi_driver rx6110_driver = {
+	.driver = {
+		.name = RX6110_DRIVER_NAME,
+		.owner = THIS_MODULE,
+	},
+	.probe		= rx6110_probe,
+	.remove		= rx6110_remove,
+	.id_table	= rx6110_id,
+};
+
+module_spi_driver(rx6110_driver);
+
+MODULE_AUTHOR("Val Krutov <val.krutov@erd.epson.com>");
+MODULE_DESCRIPTION("RX-6110 SA RTC driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/rtc/rtc-rx8025.c b/drivers/rtc/rtc-rx8025.c
index bd911bafb809..b69647e0be23 100644
--- a/drivers/rtc/rtc-rx8025.c
+++ b/drivers/rtc/rtc-rx8025.c
@@ -65,7 +65,6 @@
 
 static const struct i2c_device_id rx8025_id[] = {
 	{ "rx8025", 0 },
-	{ "rv8803", 1 },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, rx8025_id);
@@ -147,8 +146,10 @@ static irqreturn_t rx8025_handle_irq(int irq, void *dev_id)
 {
 	struct i2c_client *client = dev_id;
 	struct rx8025_data *rx8025 = i2c_get_clientdata(client);
+	struct mutex *lock = &rx8025->rtc->ops_lock;
 	int status;
 
+	mutex_lock(lock);
 	status = rx8025_read_reg(client, RX8025_REG_CTRL2);
 	if (status < 0)
 		goto out;
@@ -173,6 +174,8 @@ static irqreturn_t rx8025_handle_irq(int irq, void *dev_id)
 	}
 
 out:
+	mutex_unlock(lock);
+
 	return IRQ_HANDLED;
 }
 
@@ -341,7 +344,17 @@ static int rx8025_set_alarm(struct device *dev, struct rtc_wkalrm *t)
 	if (client->irq <= 0)
 		return -EINVAL;
 
-	/* Hardware alarm precision is 1 minute! */
+	/*
+	 * Hardware alarm precision is 1 minute!
+	 * round up to nearest minute
+	 */
+	if (t->time.tm_sec) {
+		time64_t alarm_time = rtc_tm_to_time64(&t->time);
+
+		alarm_time += 60 - t->time.tm_sec;
+		rtc_time64_to_tm(alarm_time, &t->time);
+	}
+
 	ald[0] = bin2bcd(t->time.tm_min);
 	if (rx8025->ctrl1 & RX8025_BIT_CTRL1_1224)
 		ald[1] = bin2bcd(t->time.tm_hour);
@@ -539,8 +552,9 @@ static int rx8025_probe(struct i2c_client *client,
 	if (client->irq > 0) {
 		dev_info(&client->dev, "IRQ %d supplied\n", client->irq);
 		err = devm_request_threaded_irq(&client->dev, client->irq, NULL,
-						rx8025_handle_irq, 0, "rx8025",
-						client);
+						rx8025_handle_irq,
+						IRQF_ONESHOT,
+						"rx8025", client);
 		if (err) {
 			dev_err(&client->dev, "unable to request IRQ, alarms disabled\n");
 			client->irq = 0;
@@ -549,6 +563,9 @@ static int rx8025_probe(struct i2c_client *client,
 
 	rx8025->rtc->max_user_freq = 1;
 
+	/* the rx8025 alarm only supports a minute accuracy */
+	rx8025->rtc->uie_unsupported = 1;
+
 	err = rx8025_sysfs_register(&client->dev);
 	return err;
 }
diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c
index 7407d7394bb4..0477678d968f 100644
--- a/drivers/rtc/rtc-s5m.c
+++ b/drivers/rtc/rtc-s5m.c
@@ -216,7 +216,7 @@ static int s5m8767_tm_to_data(struct rtc_time *tm, u8 *data)
  * Read RTC_UDR_CON register and wait till UDR field is cleared.
  * This indicates that time/alarm update ended.
  */
-static inline int s5m8767_wait_for_udr_update(struct s5m_rtc_info *info)
+static int s5m8767_wait_for_udr_update(struct s5m_rtc_info *info)
 {
 	int ret, retry = UDR_READ_RETRY_CNT;
 	unsigned int data;
@@ -231,7 +231,7 @@ static inline int s5m8767_wait_for_udr_update(struct s5m_rtc_info *info)
 	return ret;
 }
 
-static inline int s5m_check_peding_alarm_interrupt(struct s5m_rtc_info *info,
+static int s5m_check_peding_alarm_interrupt(struct s5m_rtc_info *info,
 		struct rtc_wkalrm *alarm)
 {
 	int ret;
@@ -264,7 +264,7 @@ static inline int s5m_check_peding_alarm_interrupt(struct s5m_rtc_info *info,
 	return 0;
 }
 
-static inline int s5m8767_rtc_set_time_reg(struct s5m_rtc_info *info)
+static int s5m8767_rtc_set_time_reg(struct s5m_rtc_info *info)
 {
 	int ret;
 	unsigned int data;
@@ -288,7 +288,7 @@ static inline int s5m8767_rtc_set_time_reg(struct s5m_rtc_info *info)
 	return ret;
 }
 
-static inline int s5m8767_rtc_set_alarm_reg(struct s5m_rtc_info *info)
+static int s5m8767_rtc_set_alarm_reg(struct s5m_rtc_info *info)
 {
 	int ret;
 	unsigned int data;
diff --git a/drivers/rtc/rtc-sysfs.c b/drivers/rtc/rtc-sysfs.c
index 463e286064ab..63b9fb1318c2 100644
--- a/drivers/rtc/rtc-sysfs.c
+++ b/drivers/rtc/rtc-sysfs.c
@@ -218,6 +218,34 @@ wakealarm_store(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RW(wakealarm);
 
+static ssize_t
+offset_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	ssize_t retval;
+	long offset;
+
+	retval = rtc_read_offset(to_rtc_device(dev), &offset);
+	if (retval == 0)
+		retval = sprintf(buf, "%ld\n", offset);
+
+	return retval;
+}
+
+static ssize_t
+offset_store(struct device *dev, struct device_attribute *attr,
+	     const char *buf, size_t n)
+{
+	ssize_t retval;
+	long offset;
+
+	retval = kstrtol(buf, 10, &offset);
+	if (retval == 0)
+		retval = rtc_set_offset(to_rtc_device(dev), offset);
+
+	return (retval < 0) ? retval : n;
+}
+static DEVICE_ATTR_RW(offset);
+
 static struct attribute *rtc_attrs[] = {
 	&dev_attr_name.attr,
 	&dev_attr_date.attr,
@@ -226,6 +254,7 @@ static struct attribute *rtc_attrs[] = {
 	&dev_attr_max_user_freq.attr,
 	&dev_attr_hctosys.attr,
 	&dev_attr_wakealarm.attr,
+	&dev_attr_offset.attr,
 	NULL,
 };
 
@@ -249,9 +278,13 @@ static umode_t rtc_attr_is_visible(struct kobject *kobj,
 	struct rtc_device *rtc = to_rtc_device(dev);
 	umode_t mode = attr->mode;
 
-	if (attr == &dev_attr_wakealarm.attr)
+	if (attr == &dev_attr_wakealarm.attr) {
 		if (!rtc_does_wakealarm(rtc))
 			mode = 0;
+	} else if (attr == &dev_attr_offset.attr) {
+		if (!rtc->ops->set_offset)
+			mode = 0;
+	}
 
 	return mode;
 }
diff --git a/drivers/rtc/rtc-tps6586x.c b/drivers/rtc/rtc-tps6586x.c
index 3b6ce80a769c..e404faac6851 100644
--- a/drivers/rtc/rtc-tps6586x.c
+++ b/drivers/rtc/rtc-tps6586x.c
@@ -286,7 +286,7 @@ static int tps6586x_rtc_probe(struct platform_device *pdev)
 
 	ret = devm_request_threaded_irq(&pdev->dev, rtc->irq, NULL,
 				tps6586x_rtc_irq,
-				IRQF_ONESHOT | IRQF_EARLY_RESUME,
+				IRQF_ONESHOT,
 				dev_name(&pdev->dev), rtc);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "request IRQ(%d) failed with ret %d\n",
diff --git a/drivers/rtc/rtc-tps65910.c b/drivers/rtc/rtc-tps65910.c
index f42aa2b2dcba..5a3d53caa485 100644
--- a/drivers/rtc/rtc-tps65910.c
+++ b/drivers/rtc/rtc-tps65910.c
@@ -268,7 +268,7 @@ static int tps65910_rtc_probe(struct platform_device *pdev)
 	}
 
 	ret = devm_request_threaded_irq(&pdev->dev, irq, NULL,
-		tps65910_rtc_interrupt, IRQF_TRIGGER_LOW | IRQF_EARLY_RESUME,
+		tps65910_rtc_interrupt, IRQF_TRIGGER_LOW,
 		dev_name(&pdev->dev), &pdev->dev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "IRQ is not free.\n");
diff --git a/drivers/rtc/rtc-tps80031.c b/drivers/rtc/rtc-tps80031.c
index 27e254cde715..737f26eb284a 100644
--- a/drivers/rtc/rtc-tps80031.c
+++ b/drivers/rtc/rtc-tps80031.c
@@ -287,7 +287,7 @@ static int tps80031_rtc_probe(struct platform_device *pdev)
 
 	ret = devm_request_threaded_irq(&pdev->dev, rtc->irq, NULL,
 			tps80031_rtc_irq,
-			IRQF_ONESHOT | IRQF_EARLY_RESUME,
+			IRQF_ONESHOT,
 			dev_name(&pdev->dev), rtc);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "request IRQ:%d failed, err = %d\n",
diff --git a/drivers/rtc/rtc-vr41xx.c b/drivers/rtc/rtc-vr41xx.c
index f64c282275b3..e1b86bb01062 100644
--- a/drivers/rtc/rtc-vr41xx.c
+++ b/drivers/rtc/rtc-vr41xx.c
@@ -272,12 +272,13 @@ static irqreturn_t rtclong1_interrupt(int irq, void *dev_id)
 }
 
 static const struct rtc_class_ops vr41xx_rtc_ops = {
-	.release	= vr41xx_rtc_release,
-	.ioctl		= vr41xx_rtc_ioctl,
-	.read_time	= vr41xx_rtc_read_time,
-	.set_time	= vr41xx_rtc_set_time,
-	.read_alarm	= vr41xx_rtc_read_alarm,
-	.set_alarm	= vr41xx_rtc_set_alarm,
+	.release		= vr41xx_rtc_release,
+	.ioctl			= vr41xx_rtc_ioctl,
+	.read_time		= vr41xx_rtc_read_time,
+	.set_time		= vr41xx_rtc_set_time,
+	.read_alarm		= vr41xx_rtc_read_alarm,
+	.set_alarm		= vr41xx_rtc_set_alarm,
+	.alarm_irq_enable	= vr41xx_rtc_alarm_irq_enable,
 };
 
 static int rtc_probe(struct platform_device *pdev)
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 41605dac8309..c78db05e75b1 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -3035,6 +3035,7 @@ static void dasd_setup_queue(struct dasd_block *block)
 		max = block->base->discipline->max_blocks << block->s2b_shift;
 	}
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, block->request_queue);
+	block->request_queue->limits.max_dev_sectors = max;
 	blk_queue_logical_block_size(block->request_queue,
 				     block->bp_block);
 	blk_queue_max_hw_sectors(block->request_queue, max);
diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c
index 184b1dbeb554..17ad5749e91d 100644
--- a/drivers/s390/block/dasd_alias.c
+++ b/drivers/s390/block/dasd_alias.c
@@ -185,14 +185,12 @@ static void _free_lcu(struct alias_lcu *lcu)
  */
 int dasd_alias_make_device_known_to_lcu(struct dasd_device *device)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	unsigned long flags;
 	struct alias_server *server, *newserver;
 	struct alias_lcu *lcu, *newlcu;
 	struct dasd_uid uid;
 
-	private = (struct dasd_eckd_private *) device->private;
-
 	device->discipline->get_uid(device, &uid);
 	spin_lock_irqsave(&aliastree.lock, flags);
 	server = _find_server(&uid);
@@ -244,14 +242,13 @@ int dasd_alias_make_device_known_to_lcu(struct dasd_device *device)
  */
 void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	unsigned long flags;
 	struct alias_lcu *lcu;
 	struct alias_server *server;
 	int was_pending;
 	struct dasd_uid uid;
 
-	private = (struct dasd_eckd_private *) device->private;
 	lcu = private->lcu;
 	/* nothing to do if already disconnected */
 	if (!lcu)
@@ -264,8 +261,10 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device)
 		spin_unlock_irqrestore(&lcu->lock, flags);
 		cancel_work_sync(&lcu->suc_data.worker);
 		spin_lock_irqsave(&lcu->lock, flags);
-		if (device == lcu->suc_data.device)
+		if (device == lcu->suc_data.device) {
+			dasd_put_device(device);
 			lcu->suc_data.device = NULL;
+		}
 	}
 	was_pending = 0;
 	if (device == lcu->ruac_data.device) {
@@ -273,8 +272,10 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device)
 		was_pending = 1;
 		cancel_delayed_work_sync(&lcu->ruac_data.dwork);
 		spin_lock_irqsave(&lcu->lock, flags);
-		if (device == lcu->ruac_data.device)
+		if (device == lcu->ruac_data.device) {
+			dasd_put_device(device);
 			lcu->ruac_data.device = NULL;
+		}
 	}
 	private->lcu = NULL;
 	spin_unlock_irqrestore(&lcu->lock, flags);
@@ -312,25 +313,15 @@ static int _add_device_to_lcu(struct alias_lcu *lcu,
 			      struct dasd_device *pos)
 {
 
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	struct alias_pav_group *group;
 	struct dasd_uid uid;
-	unsigned long flags;
-
-	private = (struct dasd_eckd_private *) device->private;
 
-	/* only lock if not already locked */
-	if (device != pos)
-		spin_lock_irqsave_nested(get_ccwdev_lock(device->cdev), flags,
-					 CDEV_NESTED_SECOND);
 	private->uid.type = lcu->uac->unit[private->uid.real_unit_addr].ua_type;
 	private->uid.base_unit_addr =
 		lcu->uac->unit[private->uid.real_unit_addr].base_ua;
 	uid = private->uid;
 
-	if (device != pos)
-		spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
-
 	/* if we have no PAV anyway, we don't need to bother with PAV groups */
 	if (lcu->pav == NO_PAV) {
 		list_move(&device->alias_list, &lcu->active_devices);
@@ -366,10 +357,9 @@ static int _add_device_to_lcu(struct alias_lcu *lcu,
 static void _remove_device_from_lcu(struct alias_lcu *lcu,
 				    struct dasd_device *device)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	struct alias_pav_group *group;
 
-	private = (struct dasd_eckd_private *) device->private;
 	list_move(&device->alias_list, &lcu->inactive_devices);
 	group = private->pavgroup;
 	if (!group)
@@ -407,6 +397,130 @@ suborder_not_supported(struct dasd_ccw_req *cqr)
 	return 0;
 }
 
+/*
+ * This function tries to lock all devices on an lcu via trylock
+ * return NULL on success otherwise return first failed device
+ */
+static struct dasd_device *_trylock_all_devices_on_lcu(struct alias_lcu *lcu,
+						      struct dasd_device *pos)
+
+{
+	struct alias_pav_group *pavgroup;
+	struct dasd_device *device;
+
+	list_for_each_entry(device, &lcu->active_devices, alias_list) {
+		if (device == pos)
+			continue;
+		if (!spin_trylock(get_ccwdev_lock(device->cdev)))
+			return device;
+	}
+	list_for_each_entry(device, &lcu->inactive_devices, alias_list) {
+		if (device == pos)
+			continue;
+		if (!spin_trylock(get_ccwdev_lock(device->cdev)))
+			return device;
+	}
+	list_for_each_entry(pavgroup, &lcu->grouplist, group) {
+		list_for_each_entry(device, &pavgroup->baselist, alias_list) {
+			if (device == pos)
+				continue;
+			if (!spin_trylock(get_ccwdev_lock(device->cdev)))
+				return device;
+		}
+		list_for_each_entry(device, &pavgroup->aliaslist, alias_list) {
+			if (device == pos)
+				continue;
+			if (!spin_trylock(get_ccwdev_lock(device->cdev)))
+				return device;
+		}
+	}
+	return NULL;
+}
+
+/*
+ * unlock all devices except the one that is specified as pos
+ * stop if enddev is specified and reached
+ */
+static void _unlock_all_devices_on_lcu(struct alias_lcu *lcu,
+				       struct dasd_device *pos,
+				       struct dasd_device *enddev)
+
+{
+	struct alias_pav_group *pavgroup;
+	struct dasd_device *device;
+
+	list_for_each_entry(device, &lcu->active_devices, alias_list) {
+		if (device == pos)
+			continue;
+		if (device == enddev)
+			return;
+		spin_unlock(get_ccwdev_lock(device->cdev));
+	}
+	list_for_each_entry(device, &lcu->inactive_devices, alias_list) {
+		if (device == pos)
+			continue;
+		if (device == enddev)
+			return;
+		spin_unlock(get_ccwdev_lock(device->cdev));
+	}
+	list_for_each_entry(pavgroup, &lcu->grouplist, group) {
+		list_for_each_entry(device, &pavgroup->baselist, alias_list) {
+			if (device == pos)
+				continue;
+			if (device == enddev)
+				return;
+			spin_unlock(get_ccwdev_lock(device->cdev));
+		}
+		list_for_each_entry(device, &pavgroup->aliaslist, alias_list) {
+			if (device == pos)
+				continue;
+			if (device == enddev)
+				return;
+			spin_unlock(get_ccwdev_lock(device->cdev));
+		}
+	}
+}
+
+/*
+ *  this function is needed because the locking order
+ *  device lock -> lcu lock
+ *  needs to be assured when iterating over devices in an LCU
+ *
+ *  if a device is specified in pos then the device lock is already hold
+ */
+static void _trylock_and_lock_lcu_irqsave(struct alias_lcu *lcu,
+					  struct dasd_device *pos,
+					  unsigned long *flags)
+{
+	struct dasd_device *failed;
+
+	do {
+		spin_lock_irqsave(&lcu->lock, *flags);
+		failed = _trylock_all_devices_on_lcu(lcu, pos);
+		if (failed) {
+			_unlock_all_devices_on_lcu(lcu, pos, failed);
+			spin_unlock_irqrestore(&lcu->lock, *flags);
+			cpu_relax();
+		}
+	} while (failed);
+}
+
+static void _trylock_and_lock_lcu(struct alias_lcu *lcu,
+				  struct dasd_device *pos)
+{
+	struct dasd_device *failed;
+
+	do {
+		spin_lock(&lcu->lock);
+		failed = _trylock_all_devices_on_lcu(lcu, pos);
+		if (failed) {
+			_unlock_all_devices_on_lcu(lcu, pos, failed);
+			spin_unlock(&lcu->lock);
+			cpu_relax();
+		}
+	} while (failed);
+}
+
 static int read_unit_address_configuration(struct dasd_device *device,
 					   struct alias_lcu *lcu)
 {
@@ -483,13 +597,13 @@ static int _lcu_update(struct dasd_device *refdev, struct alias_lcu *lcu)
 		list_for_each_entry_safe(device, tempdev, &pavgroup->baselist,
 					 alias_list) {
 			list_move(&device->alias_list, &lcu->active_devices);
-			private = (struct dasd_eckd_private *) device->private;
+			private = device->private;
 			private->pavgroup = NULL;
 		}
 		list_for_each_entry_safe(device, tempdev, &pavgroup->aliaslist,
 					 alias_list) {
 			list_move(&device->alias_list, &lcu->active_devices);
-			private = (struct dasd_eckd_private *) device->private;
+			private = device->private;
 			private->pavgroup = NULL;
 		}
 		list_del(&pavgroup->group);
@@ -501,10 +615,7 @@ static int _lcu_update(struct dasd_device *refdev, struct alias_lcu *lcu)
 	if (rc)
 		return rc;
 
-	/* need to take cdev lock before lcu lock */
-	spin_lock_irqsave_nested(get_ccwdev_lock(refdev->cdev), flags,
-				 CDEV_NESTED_FIRST);
-	spin_lock(&lcu->lock);
+	_trylock_and_lock_lcu_irqsave(lcu, NULL, &flags);
 	lcu->pav = NO_PAV;
 	for (i = 0; i < MAX_DEVICES_PER_LCU; ++i) {
 		switch (lcu->uac->unit[i].ua_type) {
@@ -523,8 +634,8 @@ static int _lcu_update(struct dasd_device *refdev, struct alias_lcu *lcu)
 				 alias_list) {
 		_add_device_to_lcu(lcu, device, refdev);
 	}
-	spin_unlock(&lcu->lock);
-	spin_unlock_irqrestore(get_ccwdev_lock(refdev->cdev), flags);
+	_unlock_all_devices_on_lcu(lcu, NULL, NULL);
+	spin_unlock_irqrestore(&lcu->lock, flags);
 	return 0;
 }
 
@@ -549,8 +660,10 @@ static void lcu_update_work(struct work_struct *work)
 	if ((rc && (rc != -EOPNOTSUPP)) || (lcu->flags & NEED_UAC_UPDATE)) {
 		DBF_DEV_EVENT(DBF_WARNING, device, "could not update"
 			    " alias data in lcu (rc = %d), retry later", rc);
-		schedule_delayed_work(&lcu->ruac_data.dwork, 30*HZ);
+		if (!schedule_delayed_work(&lcu->ruac_data.dwork, 30*HZ))
+			dasd_put_device(device);
 	} else {
+		dasd_put_device(device);
 		lcu->ruac_data.device = NULL;
 		lcu->flags &= ~UPDATE_PENDING;
 	}
@@ -593,23 +706,22 @@ static int _schedule_lcu_update(struct alias_lcu *lcu,
 	 */
 	if (!usedev)
 		return -EINVAL;
+	dasd_get_device(usedev);
 	lcu->ruac_data.device = usedev;
-	schedule_delayed_work(&lcu->ruac_data.dwork, 0);
+	if (!schedule_delayed_work(&lcu->ruac_data.dwork, 0))
+		dasd_put_device(usedev);
 	return 0;
 }
 
 int dasd_alias_add_device(struct dasd_device *device)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	struct alias_lcu *lcu;
 	unsigned long flags;
 	int rc;
 
-	private = (struct dasd_eckd_private *) device->private;
 	lcu = private->lcu;
 	rc = 0;
-
-	/* need to take cdev lock before lcu lock */
 	spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
 	spin_lock(&lcu->lock);
 	if (!(lcu->flags & UPDATE_PENDING)) {
@@ -628,20 +740,18 @@ int dasd_alias_add_device(struct dasd_device *device)
 
 int dasd_alias_update_add_device(struct dasd_device *device)
 {
-	struct dasd_eckd_private *private;
-	private = (struct dasd_eckd_private *) device->private;
+	struct dasd_eckd_private *private = device->private;
+
 	private->lcu->flags |= UPDATE_PENDING;
 	return dasd_alias_add_device(device);
 }
 
 int dasd_alias_remove_device(struct dasd_device *device)
 {
-	struct dasd_eckd_private *private;
-	struct alias_lcu *lcu;
+	struct dasd_eckd_private *private = device->private;
+	struct alias_lcu *lcu = private->lcu;
 	unsigned long flags;
 
-	private = (struct dasd_eckd_private *) device->private;
-	lcu = private->lcu;
 	/* nothing to do if already removed */
 	if (!lcu)
 		return 0;
@@ -653,16 +763,12 @@ int dasd_alias_remove_device(struct dasd_device *device)
 
 struct dasd_device *dasd_alias_get_start_dev(struct dasd_device *base_device)
 {
-
+	struct dasd_eckd_private *alias_priv, *private = base_device->private;
+	struct alias_pav_group *group = private->pavgroup;
+	struct alias_lcu *lcu = private->lcu;
 	struct dasd_device *alias_device;
-	struct alias_pav_group *group;
-	struct alias_lcu *lcu;
-	struct dasd_eckd_private *private, *alias_priv;
 	unsigned long flags;
 
-	private = (struct dasd_eckd_private *) base_device->private;
-	group = private->pavgroup;
-	lcu = private->lcu;
 	if (!group || !lcu)
 		return NULL;
 	if (lcu->pav == NO_PAV ||
@@ -698,7 +804,7 @@ struct dasd_device *dasd_alias_get_start_dev(struct dasd_device *base_device)
 		group->next = list_first_entry(&alias_device->alias_list,
 					       struct dasd_device, alias_list);
 	spin_unlock_irqrestore(&lcu->lock, flags);
-	alias_priv = (struct dasd_eckd_private *) alias_device->private;
+	alias_priv = alias_device->private;
 	if ((alias_priv->count < private->count) && !alias_device->stopped &&
 	    !test_bit(DASD_FLAG_OFFLINE, &alias_device->flags))
 		return alias_device;
@@ -723,7 +829,7 @@ static int reset_summary_unit_check(struct alias_lcu *lcu,
 	ASCEBC((char *) &cqr->magic, 4);
 	ccw = cqr->cpaddr;
 	ccw->cmd_code = DASD_ECKD_CCW_RSCK;
-	ccw->flags = 0 ;
+	ccw->flags = CCW_FLAG_SLI;
 	ccw->count = 16;
 	ccw->cda = (__u32)(addr_t) cqr->data;
 	((char *)cqr->data)[0] = reason;
@@ -746,30 +852,19 @@ static void _restart_all_base_devices_on_lcu(struct alias_lcu *lcu)
 	struct alias_pav_group *pavgroup;
 	struct dasd_device *device;
 	struct dasd_eckd_private *private;
-	unsigned long flags;
 
 	/* active and inactive list can contain alias as well as base devices */
 	list_for_each_entry(device, &lcu->active_devices, alias_list) {
-		private = (struct dasd_eckd_private *) device->private;
-		spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
-		if (private->uid.type != UA_BASE_DEVICE) {
-			spin_unlock_irqrestore(get_ccwdev_lock(device->cdev),
-					       flags);
+		private = device->private;
+		if (private->uid.type != UA_BASE_DEVICE)
 			continue;
-		}
-		spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
 		dasd_schedule_block_bh(device->block);
 		dasd_schedule_device_bh(device);
 	}
 	list_for_each_entry(device, &lcu->inactive_devices, alias_list) {
-		private = (struct dasd_eckd_private *) device->private;
-		spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
-		if (private->uid.type != UA_BASE_DEVICE) {
-			spin_unlock_irqrestore(get_ccwdev_lock(device->cdev),
-					       flags);
+		private = device->private;
+		if (private->uid.type != UA_BASE_DEVICE)
 			continue;
-		}
-		spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
 		dasd_schedule_block_bh(device->block);
 		dasd_schedule_device_bh(device);
 	}
@@ -804,7 +899,7 @@ static void flush_all_alias_devices_on_lcu(struct alias_lcu *lcu)
 	spin_lock_irqsave(&lcu->lock, flags);
 	list_for_each_entry_safe(device, temp, &lcu->active_devices,
 				 alias_list) {
-		private = (struct dasd_eckd_private *) device->private;
+		private = device->private;
 		if (private->uid.type == UA_BASE_DEVICE)
 			continue;
 		list_move(&device->alias_list, &active);
@@ -826,45 +921,27 @@ static void flush_all_alias_devices_on_lcu(struct alias_lcu *lcu)
 		if (device == list_first_entry(&active,
 					       struct dasd_device, alias_list)) {
 			list_move(&device->alias_list, &lcu->active_devices);
-			private = (struct dasd_eckd_private *) device->private;
+			private = device->private;
 			private->pavgroup = NULL;
 		}
 	}
 	spin_unlock_irqrestore(&lcu->lock, flags);
 }
 
-static void __stop_device_on_lcu(struct dasd_device *device,
-				 struct dasd_device *pos)
-{
-	/* If pos == device then device is already locked! */
-	if (pos == device) {
-		dasd_device_set_stop_bits(pos, DASD_STOPPED_SU);
-		return;
-	}
-	spin_lock(get_ccwdev_lock(pos->cdev));
-	dasd_device_set_stop_bits(pos, DASD_STOPPED_SU);
-	spin_unlock(get_ccwdev_lock(pos->cdev));
-}
-
-/*
- * This function is called in interrupt context, so the
- * cdev lock for device is already locked!
- */
-static void _stop_all_devices_on_lcu(struct alias_lcu *lcu,
-				     struct dasd_device *device)
+static void _stop_all_devices_on_lcu(struct alias_lcu *lcu)
 {
 	struct alias_pav_group *pavgroup;
-	struct dasd_device *pos;
+	struct dasd_device *device;
 
-	list_for_each_entry(pos, &lcu->active_devices, alias_list)
-		__stop_device_on_lcu(device, pos);
-	list_for_each_entry(pos, &lcu->inactive_devices, alias_list)
-		__stop_device_on_lcu(device, pos);
+	list_for_each_entry(device, &lcu->active_devices, alias_list)
+		dasd_device_set_stop_bits(device, DASD_STOPPED_SU);
+	list_for_each_entry(device, &lcu->inactive_devices, alias_list)
+		dasd_device_set_stop_bits(device, DASD_STOPPED_SU);
 	list_for_each_entry(pavgroup, &lcu->grouplist, group) {
-		list_for_each_entry(pos, &pavgroup->baselist, alias_list)
-			__stop_device_on_lcu(device, pos);
-		list_for_each_entry(pos, &pavgroup->aliaslist, alias_list)
-			__stop_device_on_lcu(device, pos);
+		list_for_each_entry(device, &pavgroup->baselist, alias_list)
+			dasd_device_set_stop_bits(device, DASD_STOPPED_SU);
+		list_for_each_entry(device, &pavgroup->aliaslist, alias_list)
+			dasd_device_set_stop_bits(device, DASD_STOPPED_SU);
 	}
 }
 
@@ -872,33 +949,16 @@ static void _unstop_all_devices_on_lcu(struct alias_lcu *lcu)
 {
 	struct alias_pav_group *pavgroup;
 	struct dasd_device *device;
-	unsigned long flags;
 
-	list_for_each_entry(device, &lcu->active_devices, alias_list) {
-		spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
+	list_for_each_entry(device, &lcu->active_devices, alias_list)
 		dasd_device_remove_stop_bits(device, DASD_STOPPED_SU);
-		spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
-	}
-
-	list_for_each_entry(device, &lcu->inactive_devices, alias_list) {
-		spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
+	list_for_each_entry(device, &lcu->inactive_devices, alias_list)
 		dasd_device_remove_stop_bits(device, DASD_STOPPED_SU);
-		spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
-	}
-
 	list_for_each_entry(pavgroup, &lcu->grouplist, group) {
-		list_for_each_entry(device, &pavgroup->baselist, alias_list) {
-			spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
+		list_for_each_entry(device, &pavgroup->baselist, alias_list)
 			dasd_device_remove_stop_bits(device, DASD_STOPPED_SU);
-			spin_unlock_irqrestore(get_ccwdev_lock(device->cdev),
-					       flags);
-		}
-		list_for_each_entry(device, &pavgroup->aliaslist, alias_list) {
-			spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
+		list_for_each_entry(device, &pavgroup->aliaslist, alias_list)
 			dasd_device_remove_stop_bits(device, DASD_STOPPED_SU);
-			spin_unlock_irqrestore(get_ccwdev_lock(device->cdev),
-					       flags);
-		}
 	}
 }
 
@@ -924,12 +984,14 @@ static void summary_unit_check_handling_work(struct work_struct *work)
 	spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
 	reset_summary_unit_check(lcu, device, suc_data->reason);
 
-	spin_lock_irqsave(&lcu->lock, flags);
+	_trylock_and_lock_lcu_irqsave(lcu, NULL, &flags);
 	_unstop_all_devices_on_lcu(lcu);
 	_restart_all_base_devices_on_lcu(lcu);
 	/* 3. read new alias configuration */
 	_schedule_lcu_update(lcu, device);
 	lcu->suc_data.device = NULL;
+	dasd_put_device(device);
+	_unlock_all_devices_on_lcu(lcu, NULL, NULL);
 	spin_unlock_irqrestore(&lcu->lock, flags);
 }
 
@@ -939,13 +1001,11 @@ static void summary_unit_check_handling_work(struct work_struct *work)
 void dasd_alias_handle_summary_unit_check(struct dasd_device *device,
 					  struct irb *irb)
 {
+	struct dasd_eckd_private *private = device->private;
 	struct alias_lcu *lcu;
 	char reason;
-	struct dasd_eckd_private *private;
 	char *sense;
 
-	private = (struct dasd_eckd_private *) device->private;
-
 	sense = dasd_get_sense(irb);
 	if (sense) {
 		reason = sense[8];
@@ -965,10 +1025,7 @@ void dasd_alias_handle_summary_unit_check(struct dasd_device *device,
 			    " unit check (no lcu structure)");
 		return;
 	}
-	spin_lock(&lcu->lock);
-	_stop_all_devices_on_lcu(lcu, device);
-	/* prepare for lcu_update */
-	private->lcu->flags |= NEED_UAC_UPDATE | UPDATE_PENDING;
+	_trylock_and_lock_lcu(lcu, device);
 	/* If this device is about to be removed just return and wait for
 	 * the next interrupt on a different device
 	 */
@@ -976,6 +1033,7 @@ void dasd_alias_handle_summary_unit_check(struct dasd_device *device,
 		DBF_DEV_EVENT(DBF_WARNING, device, "%s",
 			    "device is in offline processing,"
 			    " don't do summary unit check handling");
+		_unlock_all_devices_on_lcu(lcu, device, NULL);
 		spin_unlock(&lcu->lock);
 		return;
 	}
@@ -984,11 +1042,18 @@ void dasd_alias_handle_summary_unit_check(struct dasd_device *device,
 		DBF_DEV_EVENT(DBF_WARNING, device, "%s",
 			    "previous instance of summary unit check worker"
 			    " still pending");
+		_unlock_all_devices_on_lcu(lcu, device, NULL);
 		spin_unlock(&lcu->lock);
 		return ;
 	}
+	_stop_all_devices_on_lcu(lcu);
+	/* prepare for lcu_update */
+	private->lcu->flags |= NEED_UAC_UPDATE | UPDATE_PENDING;
 	lcu->suc_data.reason = reason;
 	lcu->suc_data.device = device;
+	dasd_get_device(device);
+	_unlock_all_devices_on_lcu(lcu, device, NULL);
 	spin_unlock(&lcu->lock);
-	schedule_work(&lcu->suc_data.worker);
+	if (!schedule_work(&lcu->suc_data.worker))
+		dasd_put_device(device);
 };
diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index 8286f742436b..2f18f61092b5 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -214,8 +214,8 @@ dasd_feature_list(char *str, char **endp)
 		else if (len == 8 && !strncmp(str, "failfast", 8))
 			features |= DASD_FEATURE_FAILFAST;
 		else {
-			pr_warning("%*s is not a supported device option\n",
-				   len, str);
+			pr_warn("%*s is not a supported device option\n",
+				len, str);
 			rc = -EINVAL;
 		}
 		str += len;
@@ -224,8 +224,7 @@ dasd_feature_list(char *str, char **endp)
 		str++;
 	}
 	if (*str != ')') {
-		pr_warning("A closing parenthesis ')' is missing in the "
-			   "dasd= parameter\n");
+		pr_warn("A closing parenthesis ')' is missing in the dasd= parameter\n");
 		rc = -EINVAL;
 	} else
 		str++;
@@ -348,8 +347,7 @@ dasd_parse_range( char *parsestring ) {
 		return str + 1;
 	if (*str == '\0')
 		return str;
-	pr_warning("The dasd= parameter value %s has an invalid ending\n",
-		   str);
+	pr_warn("The dasd= parameter value %s has an invalid ending\n", str);
 	return ERR_PTR(-EINVAL);
 }
 
diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c
index cb61f300f8b5..5667146c6a0a 100644
--- a/drivers/s390/block/dasd_diag.c
+++ b/drivers/s390/block/dasd_diag.c
@@ -67,7 +67,7 @@ static const u8 DASD_DIAG_CMS1[] = { 0xc3, 0xd4, 0xe2, 0xf1 };/* EBCDIC CMS1 */
  * and function code cmd.
  * In case of an exception return 3. Otherwise return result of bitwise OR of
  * resulting condition code and DIAG return code. */
-static inline int dia250(void *iob, int cmd)
+static inline int __dia250(void *iob, int cmd)
 {
 	register unsigned long reg2 asm ("2") = (unsigned long) iob;
 	typedef union {
@@ -77,7 +77,6 @@ static inline int dia250(void *iob, int cmd)
 	int rc;
 
 	rc = 3;
-	diag_stat_inc(DIAG_STAT_X250);
 	asm volatile(
 		"	diag	2,%2,0x250\n"
 		"0:	ipm	%0\n"
@@ -91,6 +90,12 @@ static inline int dia250(void *iob, int cmd)
 	return rc;
 }
 
+static inline int dia250(void *iob, int cmd)
+{
+	diag_stat_inc(DIAG_STAT_X250);
+	return __dia250(iob, cmd);
+}
+
 /* Initialize block I/O to DIAG device using the specified blocksize and
  * block offset. On success, return zero and set end_block to contain the
  * number of blocks on the device minus the specified offset. Return non-zero
@@ -99,12 +104,10 @@ static inline int
 mdsk_init_io(struct dasd_device *device, unsigned int blocksize,
 	     blocknum_t offset, blocknum_t *end_block)
 {
-	struct dasd_diag_private *private;
-	struct dasd_diag_init_io *iib;
+	struct dasd_diag_private *private = device->private;
+	struct dasd_diag_init_io *iib = &private->iib;
 	int rc;
 
-	private = (struct dasd_diag_private *) device->private;
-	iib = &private->iib;
 	memset(iib, 0, sizeof (struct dasd_diag_init_io));
 
 	iib->dev_nr = private->dev_id.devno;
@@ -125,12 +128,10 @@ mdsk_init_io(struct dasd_device *device, unsigned int blocksize,
 static inline int
 mdsk_term_io(struct dasd_device * device)
 {
-	struct dasd_diag_private *private;
-	struct dasd_diag_init_io *iib;
+	struct dasd_diag_private *private = device->private;
+	struct dasd_diag_init_io *iib = &private->iib;
 	int rc;
 
-	private = (struct dasd_diag_private *) device->private;
-	iib = &private->iib;
 	memset(iib, 0, sizeof (struct dasd_diag_init_io));
 	iib->dev_nr = private->dev_id.devno;
 	rc = dia250(iib, TERM_BIO);
@@ -148,14 +149,13 @@ dasd_diag_erp(struct dasd_device *device)
 	rc = mdsk_init_io(device, device->block->bp_block, 0, NULL);
 	if (rc == 4) {
 		if (!(test_and_set_bit(DASD_FLAG_DEVICE_RO, &device->flags)))
-			pr_warning("%s: The access mode of a DIAG device "
-				   "changed to read-only\n",
-				   dev_name(&device->cdev->dev));
+			pr_warn("%s: The access mode of a DIAG device changed to read-only\n",
+				dev_name(&device->cdev->dev));
 		rc = 0;
 	}
 	if (rc)
-		pr_warning("%s: DIAG ERP failed with "
-			    "rc=%d\n", dev_name(&device->cdev->dev), rc);
+		pr_warn("%s: DIAG ERP failed with rc=%d\n",
+			dev_name(&device->cdev->dev), rc);
 }
 
 /* Start a given request at the device. Return zero on success, non-zero
@@ -175,8 +175,8 @@ dasd_start_diag(struct dasd_ccw_req * cqr)
 		cqr->status = DASD_CQR_ERROR;
 		return -EIO;
 	}
-	private = (struct dasd_diag_private *) device->private;
-	dreq = (struct dasd_diag_req *) cqr->data;
+	private = device->private;
+	dreq = cqr->data;
 
 	private->iob.dev_nr = private->dev_id.devno;
 	private->iob.key = 0;
@@ -315,18 +315,17 @@ static void dasd_ext_handler(struct ext_code ext_code,
 static int
 dasd_diag_check_device(struct dasd_device *device)
 {
-	struct dasd_block *block;
-	struct dasd_diag_private *private;
+	struct dasd_diag_private *private = device->private;
 	struct dasd_diag_characteristics *rdc_data;
-	struct dasd_diag_bio bio;
 	struct vtoc_cms_label *label;
-	blocknum_t end_block;
+	struct dasd_block *block;
+	struct dasd_diag_bio bio;
 	unsigned int sb, bsize;
+	blocknum_t end_block;
 	int rc;
 
-	private = (struct dasd_diag_private *) device->private;
 	if (private == NULL) {
-		private = kzalloc(sizeof(struct dasd_diag_private),GFP_KERNEL);
+		private = kzalloc(sizeof(*private), GFP_KERNEL);
 		if (private == NULL) {
 			DBF_DEV_EVENT(DBF_WARNING, device, "%s",
 				"Allocating memory for private DASD data "
@@ -334,7 +333,7 @@ dasd_diag_check_device(struct dasd_device *device)
 			return -ENOMEM;
 		}
 		ccw_device_get_id(device->cdev, &private->dev_id);
-		device->private = (void *) private;
+		device->private = private;
 	}
 	block = dasd_alloc_block();
 	if (IS_ERR(block)) {
@@ -348,7 +347,7 @@ dasd_diag_check_device(struct dasd_device *device)
 	block->base = device;
 
 	/* Read Device Characteristics */
-	rdc_data = (void *) &(private->rdc_data);
+	rdc_data = &private->rdc_data;
 	rdc_data->dev_nr = private->dev_id.devno;
 	rdc_data->rdc_len = sizeof (struct dasd_diag_characteristics);
 
@@ -372,9 +371,9 @@ dasd_diag_check_device(struct dasd_device *device)
 		private->pt_block = 2;
 		break;
 	default:
-		pr_warning("%s: Device type %d is not supported "
-			   "in DIAG mode\n", dev_name(&device->cdev->dev),
-			   private->rdc_data.vdev_class);
+		pr_warn("%s: Device type %d is not supported in DIAG mode\n",
+			dev_name(&device->cdev->dev),
+			private->rdc_data.vdev_class);
 		rc = -EOPNOTSUPP;
 		goto out;
 	}
@@ -415,8 +414,8 @@ dasd_diag_check_device(struct dasd_device *device)
 		private->iob.flaga = DASD_DIAG_FLAGA_DEFAULT;
 		rc = dia250(&private->iob, RW_BIO);
 		if (rc == 3) {
-			pr_warning("%s: A 64-bit DIAG call failed\n",
-				   dev_name(&device->cdev->dev));
+			pr_warn("%s: A 64-bit DIAG call failed\n",
+				dev_name(&device->cdev->dev));
 			rc = -EOPNOTSUPP;
 			goto out_label;
 		}
@@ -425,9 +424,8 @@ dasd_diag_check_device(struct dasd_device *device)
 			break;
 	}
 	if (bsize > PAGE_SIZE) {
-		pr_warning("%s: Accessing the DASD failed because of an "
-			   "incorrect format (rc=%d)\n",
-			   dev_name(&device->cdev->dev), rc);
+		pr_warn("%s: Accessing the DASD failed because of an incorrect format (rc=%d)\n",
+			dev_name(&device->cdev->dev), rc);
 		rc = -EIO;
 		goto out_label;
 	}
@@ -445,8 +443,8 @@ dasd_diag_check_device(struct dasd_device *device)
 		block->s2b_shift++;
 	rc = mdsk_init_io(device, block->bp_block, 0, NULL);
 	if (rc && (rc != 4)) {
-		pr_warning("%s: DIAG initialization failed with rc=%d\n",
-			   dev_name(&device->cdev->dev), rc);
+		pr_warn("%s: DIAG initialization failed with rc=%d\n",
+			dev_name(&device->cdev->dev), rc);
 		rc = -EIO;
 	} else {
 		if (rc == 4)
@@ -596,16 +594,14 @@ static int
 dasd_diag_fill_info(struct dasd_device * device,
 		    struct dasd_information2_t * info)
 {
-	struct dasd_diag_private *private;
+	struct dasd_diag_private *private = device->private;
 
-	private = (struct dasd_diag_private *) device->private;
 	info->label_block = (unsigned int) private->pt_block;
 	info->FBA_layout = 1;
 	info->format = DASD_FORMAT_LDL;
-	info->characteristics_size = sizeof (struct dasd_diag_characteristics);
-	memcpy(info->characteristics,
-	       &((struct dasd_diag_private *) device->private)->rdc_data,
-	       sizeof (struct dasd_diag_characteristics));
+	info->characteristics_size = sizeof(private->rdc_data);
+	memcpy(info->characteristics, &private->rdc_data,
+	       sizeof(private->rdc_data));
 	info->confdata_size = 0;
 	return 0;
 }
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 9083247f55a8..75c032dcf173 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -212,10 +212,9 @@ check_XRC (struct ccw1         *de_ccw,
            struct DE_eckd_data *data,
            struct dasd_device  *device)
 {
-        struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	int rc;
 
-        private = (struct dasd_eckd_private *) device->private;
 	if (!private->rdc_data.facilities.XRC_supported)
 		return 0;
 
@@ -237,13 +236,11 @@ static int
 define_extent(struct ccw1 *ccw, struct DE_eckd_data *data, unsigned int trk,
 	      unsigned int totrk, int cmd, struct dasd_device *device)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	u32 begcyl, endcyl;
 	u16 heads, beghead, endhead;
 	int rc = 0;
 
-	private = (struct dasd_eckd_private *) device->private;
-
 	ccw->cmd_code = DASD_ECKD_CCW_DEFINE_EXTENT;
 	ccw->flags = 0;
 	ccw->count = 16;
@@ -322,10 +319,9 @@ define_extent(struct ccw1 *ccw, struct DE_eckd_data *data, unsigned int trk,
 static int check_XRC_on_prefix(struct PFX_eckd_data *pfxdata,
 			       struct dasd_device  *device)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	int rc;
 
-	private = (struct dasd_eckd_private *) device->private;
 	if (!private->rdc_data.facilities.XRC_supported)
 		return 0;
 
@@ -346,12 +342,10 @@ static void fill_LRE_data(struct LRE_eckd_data *data, unsigned int trk,
 			  struct dasd_device *device, unsigned int reclen,
 			  unsigned int tlf)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	int sector;
 	int dn, d;
 
-	private = (struct dasd_eckd_private *) device->private;
-
 	memset(data, 0, sizeof(*data));
 	sector = 0;
 	if (rec_on_trk) {
@@ -488,8 +482,8 @@ static int prefix_LRE(struct ccw1 *ccw, struct PFX_eckd_data *pfxdata,
 	u16 heads, beghead, endhead;
 	int rc = 0;
 
-	basepriv = (struct dasd_eckd_private *) basedev->private;
-	startpriv = (struct dasd_eckd_private *) startdev->private;
+	basepriv = basedev->private;
+	startpriv = startdev->private;
 	dedata = &pfxdata->define_extent;
 	lredata = &pfxdata->locate_record;
 
@@ -631,12 +625,10 @@ locate_record(struct ccw1 *ccw, struct LO_eckd_data *data, unsigned int trk,
 	      unsigned int rec_on_trk, int no_rec, int cmd,
 	      struct dasd_device * device, int reclen)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	int sector;
 	int dn, d;
 
-	private = (struct dasd_eckd_private *) device->private;
-
 	DBF_DEV_EVENT(DBF_INFO, device,
 		  "Locate: trk %d, rec %d, no_rec %d, cmd %d, reclen %d",
 		  trk, rec_on_trk, no_rec, cmd, reclen);
@@ -800,10 +792,9 @@ static void create_uid(struct dasd_eckd_private *private)
  */
 static int dasd_eckd_generate_uid(struct dasd_device *device)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	unsigned long flags;
 
-	private = (struct dasd_eckd_private *) device->private;
 	if (!private)
 		return -ENODEV;
 	if (!private->ned || !private->gneq)
@@ -816,11 +807,10 @@ static int dasd_eckd_generate_uid(struct dasd_device *device)
 
 static int dasd_eckd_get_uid(struct dasd_device *device, struct dasd_uid *uid)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	unsigned long flags;
 
-	if (device->private) {
-		private = (struct dasd_eckd_private *)device->private;
+	if (private) {
 		spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
 		*uid = private->uid;
 		spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
@@ -1034,10 +1024,9 @@ static unsigned char dasd_eckd_path_access(void *conf_data, int conf_len)
 
 static void dasd_eckd_clear_conf_data(struct dasd_device *device)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	int i;
 
-	private = (struct dasd_eckd_private *) device->private;
 	private->conf_data = NULL;
 	private->conf_len = 0;
 	for (i = 0; i < 8; i++) {
@@ -1058,7 +1047,7 @@ static int dasd_eckd_read_conf(struct dasd_device *device)
 	struct dasd_uid *uid;
 	char print_path_uid[60], print_device_uid[60];
 
-	private = (struct dasd_eckd_private *) device->private;
+	private = device->private;
 	path_data = &device->path_data;
 	opm = ccw_device_get_path_mask(device->cdev);
 	conf_data_saved = 0;
@@ -1191,11 +1180,10 @@ static int dasd_eckd_read_conf(struct dasd_device *device)
 
 static int verify_fcx_max_data(struct dasd_device *device, __u8 lpm)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	int mdc;
 	u32 fcx_max_data;
 
-	private = (struct dasd_eckd_private *) device->private;
 	if (private->fcx_max_data) {
 		mdc = ccw_device_get_mdc(device->cdev, lpm);
 		if ((mdc < 0)) {
@@ -1221,15 +1209,10 @@ static int verify_fcx_max_data(struct dasd_device *device, __u8 lpm)
 static int rebuild_device_uid(struct dasd_device *device,
 			      struct path_verification_work_data *data)
 {
-	struct dasd_eckd_private *private;
-	struct dasd_path *path_data;
-	__u8 lpm, opm;
-	int rc;
-
-	rc = -ENODEV;
-	private = (struct dasd_eckd_private *) device->private;
-	path_data = &device->path_data;
-	opm = device->path_data.opm;
+	struct dasd_eckd_private *private = device->private;
+	struct dasd_path *path_data = &device->path_data;
+	__u8 lpm, opm = path_data->opm;
+	int rc = -ENODEV;
 
 	for (lpm = 0x80; lpm; lpm >>= 1) {
 		if (!(lpm & opm))
@@ -1463,14 +1446,13 @@ static int dasd_eckd_verify_path(struct dasd_device *device, __u8 lpm)
 
 static int dasd_eckd_read_features(struct dasd_device *device)
 {
+	struct dasd_eckd_private *private = device->private;
 	struct dasd_psf_prssd_data *prssdp;
 	struct dasd_rssd_features *features;
 	struct dasd_ccw_req *cqr;
 	struct ccw1 *ccw;
 	int rc;
-	struct dasd_eckd_private *private;
 
-	private = (struct dasd_eckd_private *) device->private;
 	memset(&private->features, 0, sizeof(struct dasd_rssd_features));
 	cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */	+ 1 /* RSSD */,
 				   (sizeof(struct dasd_psf_prssd_data) +
@@ -1605,11 +1587,9 @@ dasd_eckd_psf_ssc(struct dasd_device *device, int enable_pav,
 static int dasd_eckd_validate_server(struct dasd_device *device,
 				     unsigned long flags)
 {
-	int rc;
-	struct dasd_eckd_private *private;
-	int enable_pav;
+	struct dasd_eckd_private *private = device->private;
+	int enable_pav, rc;
 
-	private = (struct dasd_eckd_private *) device->private;
 	if (private->uid.type == UA_BASE_PAV_ALIAS ||
 	    private->uid.type == UA_HYPER_PAV_ALIAS)
 		return 0;
@@ -1662,14 +1642,13 @@ static void dasd_eckd_kick_validate_server(struct dasd_device *device)
 
 static u32 get_fcx_max_data(struct dasd_device *device)
 {
-	int tpm, mdc;
+	struct dasd_eckd_private *private = device->private;
 	int fcx_in_css, fcx_in_gneq, fcx_in_features;
-	struct dasd_eckd_private *private;
+	int tpm, mdc;
 
 	if (dasd_nofcx)
 		return 0;
 	/* is transport mode supported? */
-	private = (struct dasd_eckd_private *) device->private;
 	fcx_in_css = css_general_characteristics.fcx;
 	fcx_in_gneq = private->gneq->reserved2[7] & 0x04;
 	fcx_in_features = private->features.feature[40] & 0x80;
@@ -1694,7 +1673,7 @@ static u32 get_fcx_max_data(struct dasd_device *device)
 static int
 dasd_eckd_check_characteristics(struct dasd_device *device)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	struct dasd_block *block;
 	struct dasd_uid temp_uid;
 	int rc, i;
@@ -1713,7 +1692,6 @@ dasd_eckd_check_characteristics(struct dasd_device *device)
 		dev_info(&device->cdev->dev,
 			 "The DASD is not operating in multipath mode\n");
 	}
-	private = (struct dasd_eckd_private *) device->private;
 	if (!private) {
 		private = kzalloc(sizeof(*private), GFP_KERNEL | GFP_DMA);
 		if (!private) {
@@ -1722,7 +1700,7 @@ dasd_eckd_check_characteristics(struct dasd_device *device)
 				 "failed\n");
 			return -ENOMEM;
 		}
-		device->private = (void *) private;
+		device->private = private;
 	} else {
 		memset(private, 0, sizeof(*private));
 	}
@@ -1837,10 +1815,9 @@ out_err1:
 
 static void dasd_eckd_uncheck_device(struct dasd_device *device)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	int i;
 
-	private = (struct dasd_eckd_private *) device->private;
 	dasd_alias_disconnect_device_from_lcu(device);
 	private->ned = NULL;
 	private->sneq = NULL;
@@ -1863,7 +1840,7 @@ static void dasd_eckd_uncheck_device(struct dasd_device *device)
 static struct dasd_ccw_req *
 dasd_eckd_analysis_ccw(struct dasd_device *device)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	struct eckd_count *count_data;
 	struct LO_eckd_data *LO_data;
 	struct dasd_ccw_req *cqr;
@@ -1871,8 +1848,6 @@ dasd_eckd_analysis_ccw(struct dasd_device *device)
 	int cplength, datasize;
 	int i;
 
-	private = (struct dasd_eckd_private *) device->private;
-
 	cplength = 8;
 	datasize = sizeof(struct DE_eckd_data) + 2*sizeof(struct LO_eckd_data);
 	cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, cplength, datasize, device);
@@ -1946,11 +1921,9 @@ static int dasd_eckd_analysis_evaluation(struct dasd_ccw_req *init_cqr)
 static void dasd_eckd_analysis_callback(struct dasd_ccw_req *init_cqr,
 					void *data)
 {
-	struct dasd_eckd_private *private;
-	struct dasd_device *device;
+	struct dasd_device *device = init_cqr->startdev;
+	struct dasd_eckd_private *private = device->private;
 
-	device = init_cqr->startdev;
-	private = (struct dasd_eckd_private *) device->private;
 	private->init_cqr_status = dasd_eckd_analysis_evaluation(init_cqr);
 	dasd_sfree_request(init_cqr, device);
 	dasd_kick_device(device);
@@ -1977,15 +1950,13 @@ static int dasd_eckd_start_analysis(struct dasd_block *block)
 
 static int dasd_eckd_end_analysis(struct dasd_block *block)
 {
-	struct dasd_device *device;
-	struct dasd_eckd_private *private;
+	struct dasd_device *device = block->base;
+	struct dasd_eckd_private *private = device->private;
 	struct eckd_count *count_area;
 	unsigned int sb, blk_per_trk;
 	int status, i;
 	struct dasd_ccw_req *init_cqr;
 
-	device = block->base;
-	private = (struct dasd_eckd_private *) device->private;
 	status = private->init_cqr_status;
 	private->init_cqr_status = -1;
 	if (status == INIT_CQR_ERROR) {
@@ -2083,9 +2054,8 @@ raw:
 
 static int dasd_eckd_do_analysis(struct dasd_block *block)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = block->base->private;
 
-	private = (struct dasd_eckd_private *) block->base->private;
 	if (private->init_cqr_status < 0)
 		return dasd_eckd_start_analysis(block);
 	else
@@ -2112,9 +2082,8 @@ static int dasd_eckd_basic_to_known(struct dasd_device *device)
 static int
 dasd_eckd_fill_geometry(struct dasd_block *block, struct hd_geometry *geo)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = block->base->private;
 
-	private = (struct dasd_eckd_private *) block->base->private;
 	if (dasd_check_blocksize(block->bp_block) == 0) {
 		geo->sectors = recs_per_track(&private->rdc_data,
 					      0, block->bp_block);
@@ -2151,8 +2120,8 @@ dasd_eckd_build_format(struct dasd_device *base,
 	if (!startdev)
 		startdev = base;
 
-	start_priv = (struct dasd_eckd_private *) startdev->private;
-	base_priv = (struct dasd_eckd_private *) base->private;
+	start_priv = startdev->private;
+	base_priv = base->private;
 
 	rpt = recs_per_track(&base_priv->rdc_data, 0, fdata->blksize);
 
@@ -2349,14 +2318,14 @@ dasd_eckd_build_format(struct dasd_device *base,
 				 * when formatting CDL
 				 */
 				if ((intensity & 0x08) &&
-				    fdata->start_unit == 0) {
+				    address.cyl == 0 && address.head == 0) {
 					if (i < 3) {
 						ect->kl = 4;
 						ect->dl = sizes_trk0[i] - 4;
 					}
 				}
 				if ((intensity & 0x08) &&
-				    fdata->start_unit == 1) {
+				    address.cyl == 0 && address.head == 1) {
 					ect->kl = 44;
 					ect->dl = LABEL_SIZE - 44;
 				}
@@ -2386,23 +2355,24 @@ dasd_eckd_build_format(struct dasd_device *base,
 	return fcp;
 }
 
-static int
-dasd_eckd_format_device(struct dasd_device *base,
-			struct format_data_t *fdata,
-			int enable_pav)
+/*
+ * Wrapper function to build a CCW request depending on input data
+ */
+static struct dasd_ccw_req *
+dasd_eckd_format_build_ccw_req(struct dasd_device *base,
+			       struct format_data_t *fdata, int enable_pav)
 {
-	struct dasd_ccw_req *cqr, *n;
-	struct dasd_block *block;
-	struct dasd_eckd_private *private;
-	struct list_head format_queue;
-	struct dasd_device *device;
-	int old_stop, format_step;
-	int step, rc = 0, sleep_rc;
+	return dasd_eckd_build_format(base, fdata, enable_pav);
+}
 
-	block = base->block;
-	private = (struct dasd_eckd_private *) base->private;
+/*
+ * Sanity checks on format_data
+ */
+static int dasd_eckd_format_sanity_checks(struct dasd_device *base,
+					  struct format_data_t *fdata)
+{
+	struct dasd_eckd_private *private = base->private;
 
-	/* Sanity checks. */
 	if (fdata->start_unit >=
 	    (private->real_cyl * private->rdc_data.trk_per_cyl)) {
 		dev_warn(&base->cdev->dev,
@@ -2429,75 +2399,98 @@ dasd_eckd_format_device(struct dasd_device *base,
 			 fdata->blksize);
 		return -EINVAL;
 	}
+	return 0;
+}
+
+/*
+ * This function will process format_data originally coming from an IOCTL
+ */
+static int dasd_eckd_format_process_data(struct dasd_device *base,
+					 struct format_data_t *fdata,
+					 int enable_pav)
+{
+	struct dasd_eckd_private *private = base->private;
+	struct dasd_ccw_req *cqr, *n;
+	struct list_head format_queue;
+	struct dasd_device *device;
+	int old_start, old_stop, format_step;
+	int step, retry;
+	int rc;
+
+	rc = dasd_eckd_format_sanity_checks(base, fdata);
+	if (rc)
+		return rc;
 
 	INIT_LIST_HEAD(&format_queue);
 
+	old_start = fdata->start_unit;
 	old_stop = fdata->stop_unit;
-	while (fdata->start_unit <= 1) {
-		fdata->stop_unit = fdata->start_unit;
-		cqr = dasd_eckd_build_format(base, fdata, enable_pav);
-		list_add(&cqr->blocklist, &format_queue);
-
-		fdata->stop_unit = old_stop;
-		fdata->start_unit++;
 
-		if (fdata->start_unit > fdata->stop_unit)
-			goto sleep;
-	}
+	format_step = DASD_CQR_MAX_CCW / recs_per_track(&private->rdc_data, 0,
+							fdata->blksize);
+	do {
+		retry = 0;
+		while (fdata->start_unit <= old_stop) {
+			step = fdata->stop_unit - fdata->start_unit + 1;
+			if (step > format_step) {
+				fdata->stop_unit =
+					fdata->start_unit + format_step - 1;
+			}
 
-retry:
-	format_step = 255 / recs_per_track(&private->rdc_data, 0,
-					   fdata->blksize);
-	while (fdata->start_unit <= old_stop) {
-		step = fdata->stop_unit - fdata->start_unit + 1;
-		if (step > format_step)
-			fdata->stop_unit = fdata->start_unit + format_step - 1;
+			cqr = dasd_eckd_format_build_ccw_req(base, fdata,
+							     enable_pav);
+			if (IS_ERR(cqr)) {
+				rc = PTR_ERR(cqr);
+				if (rc == -ENOMEM) {
+					if (list_empty(&format_queue))
+						goto out;
+					/*
+					 * not enough memory available, start
+					 * requests retry after first requests
+					 * were finished
+					 */
+					retry = 1;
+					break;
+				}
+				goto out_err;
+			}
+			list_add_tail(&cqr->blocklist, &format_queue);
 
-		cqr = dasd_eckd_build_format(base, fdata, enable_pav);
-		if (IS_ERR(cqr)) {
-			if (PTR_ERR(cqr) == -ENOMEM) {
-				/*
-				 * not enough memory available
-				 * go to out and start requests
-				 * retry after first requests were finished
-				 */
-				fdata->stop_unit = old_stop;
-				goto sleep;
-			} else
-				return PTR_ERR(cqr);
+			fdata->start_unit = fdata->stop_unit + 1;
+			fdata->stop_unit = old_stop;
 		}
-		list_add(&cqr->blocklist, &format_queue);
 
-		fdata->start_unit = fdata->stop_unit + 1;
-		fdata->stop_unit = old_stop;
-	}
+		rc = dasd_sleep_on_queue(&format_queue);
 
-sleep:
-	sleep_rc = dasd_sleep_on_queue(&format_queue);
+out_err:
+		list_for_each_entry_safe(cqr, n, &format_queue, blocklist) {
+			device = cqr->startdev;
+			private = device->private;
+			if (cqr->status == DASD_CQR_FAILED)
+				rc = -EIO;
+			list_del_init(&cqr->blocklist);
+			dasd_sfree_request(cqr, device);
+			private->count--;
+		}
 
-	list_for_each_entry_safe(cqr, n, &format_queue, blocklist) {
-		device = cqr->startdev;
-		private = (struct dasd_eckd_private *) device->private;
-		if (cqr->status == DASD_CQR_FAILED)
-			rc = -EIO;
-		list_del_init(&cqr->blocklist);
-		dasd_sfree_request(cqr, device);
-		private->count--;
-	}
+		if (rc)
+			goto out;
 
-	if (sleep_rc)
-		return sleep_rc;
+	} while (retry);
 
-	/*
-	 * in case of ENOMEM we need to retry after
-	 * first requests are finished
-	 */
-	if (fdata->start_unit <= fdata->stop_unit)
-		goto retry;
+out:
+	fdata->start_unit = old_start;
+	fdata->stop_unit = old_stop;
 
 	return rc;
 }
 
+static int dasd_eckd_format_device(struct dasd_device *base,
+				   struct format_data_t *fdata, int enable_pav)
+{
+	return dasd_eckd_format_process_data(base, fdata, enable_pav);
+}
+
 static void dasd_eckd_handle_terminated_request(struct dasd_ccw_req *cqr)
 {
 	if (cqr->retries < 0) {
@@ -2543,9 +2536,8 @@ static void dasd_eckd_check_for_device_change(struct dasd_device *device,
 {
 	char mask;
 	char *sense = NULL;
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 
-	private = (struct dasd_eckd_private *) device->private;
 	/* first of all check for state change pending interrupt */
 	mask = DEV_STAT_ATTENTION | DEV_STAT_DEV_END | DEV_STAT_UNIT_EXCEP;
 	if ((scsw_dstat(&irb->scsw) & mask) == mask) {
@@ -2634,7 +2626,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_single(
 	struct dasd_device *basedev;
 
 	basedev = block->base;
-	private = (struct dasd_eckd_private *) basedev->private;
+	private = basedev->private;
 	if (rq_data_dir(req) == READ)
 		cmd = DASD_ECKD_CCW_READ_MT;
 	else if (rq_data_dir(req) == WRITE)
@@ -2990,8 +2982,8 @@ static int prepare_itcw(struct itcw *itcw,
 
 
 	/* setup prefix data */
-	basepriv = (struct dasd_eckd_private *) basedev->private;
-	startpriv = (struct dasd_eckd_private *) startdev->private;
+	basepriv = basedev->private;
+	startpriv = startdev->private;
 	dedata = &pfxdata.define_extent;
 	lredata = &pfxdata.locate_record;
 
@@ -3278,7 +3270,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp(struct dasd_device *startdev,
 	struct dasd_ccw_req *cqr;
 
 	basedev = block->base;
-	private = (struct dasd_eckd_private *) basedev->private;
+	private = basedev->private;
 
 	/* Calculate number of blocks/records per track. */
 	blksize = block->bp_block;
@@ -3503,7 +3495,7 @@ dasd_eckd_free_cp(struct dasd_ccw_req *cqr, struct request *req)
 
 	if (!dasd_page_cache)
 		goto out;
-	private = (struct dasd_eckd_private *) cqr->block->base->private;
+	private = cqr->block->base->private;
 	blksize = cqr->block->bp_block;
 	blk_per_trk = recs_per_track(&private->rdc_data, 0, blksize);
 	recid = blk_rq_pos(req) >> cqr->block->s2b_shift;
@@ -3587,7 +3579,7 @@ static struct dasd_ccw_req *dasd_eckd_build_alias_cp(struct dasd_device *base,
 	startdev = dasd_alias_get_start_dev(base);
 	if (!startdev)
 		startdev = base;
-	private = (struct dasd_eckd_private *) startdev->private;
+	private = startdev->private;
 	if (private->count >= DASD_ECKD_CHANQ_MAX_SIZE)
 		return ERR_PTR(-EBUSY);
 
@@ -3610,7 +3602,7 @@ static int dasd_eckd_free_alias_cp(struct dasd_ccw_req *cqr,
 	unsigned long flags;
 
 	spin_lock_irqsave(get_ccwdev_lock(cqr->memdev->cdev), flags);
-	private = (struct dasd_eckd_private *) cqr->memdev->private;
+	private = cqr->memdev->private;
 	private->count--;
 	spin_unlock_irqrestore(get_ccwdev_lock(cqr->memdev->cdev), flags);
 	return dasd_eckd_free_cp(cqr, req);
@@ -3620,15 +3612,14 @@ static int
 dasd_eckd_fill_info(struct dasd_device * device,
 		    struct dasd_information2_t * info)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 
-	private = (struct dasd_eckd_private *) device->private;
 	info->label_block = 2;
 	info->FBA_layout = private->uses_cdl ? 0 : 1;
 	info->format = private->uses_cdl ? DASD_FORMAT_CDL : DASD_FORMAT_LDL;
-	info->characteristics_size = sizeof(struct dasd_eckd_characteristics);
+	info->characteristics_size = sizeof(private->rdc_data);
 	memcpy(info->characteristics, &private->rdc_data,
-	       sizeof(struct dasd_eckd_characteristics));
+	       sizeof(private->rdc_data));
 	info->confdata_size = min((unsigned long)private->conf_len,
 				  sizeof(info->configuration_data));
 	memcpy(info->configuration_data, private->conf_data,
@@ -3941,8 +3932,7 @@ dasd_eckd_performance(struct dasd_device *device, void __user *argp)
 static int
 dasd_eckd_get_attrib(struct dasd_device *device, void __user *argp)
 {
-	struct dasd_eckd_private *private =
-		(struct dasd_eckd_private *)device->private;
+	struct dasd_eckd_private *private = device->private;
 	struct attrib_data_t attrib = private->attrib;
 	int rc;
 
@@ -3966,8 +3956,7 @@ dasd_eckd_get_attrib(struct dasd_device *device, void __user *argp)
 static int
 dasd_eckd_set_attrib(struct dasd_device *device, void __user *argp)
 {
-	struct dasd_eckd_private *private =
-		(struct dasd_eckd_private *)device->private;
+	struct dasd_eckd_private *private = device->private;
 	struct attrib_data_t attrib;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -4430,15 +4419,13 @@ static int dasd_eckd_pm_freeze(struct dasd_device *device)
 
 static int dasd_eckd_restore_device(struct dasd_device *device)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	struct dasd_eckd_characteristics temp_rdc_data;
 	int rc;
 	struct dasd_uid temp_uid;
 	unsigned long flags;
 	unsigned long cqr_flags = 0;
 
-	private = (struct dasd_eckd_private *) device->private;
-
 	/* Read Configuration Data */
 	rc = dasd_eckd_read_conf(device);
 	if (rc) {
@@ -4502,14 +4489,12 @@ out_err:
 
 static int dasd_eckd_reload_device(struct dasd_device *device)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	int rc, old_base;
 	char print_uid[60];
 	struct dasd_uid uid;
 	unsigned long flags;
 
-	private = (struct dasd_eckd_private *) device->private;
-
 	spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
 	old_base = private->uid.base_unit_addr;
 	spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
@@ -4556,12 +4541,10 @@ static int dasd_eckd_read_message_buffer(struct dasd_device *device,
 {
 	struct dasd_rssd_messages *message_buf;
 	struct dasd_psf_prssd_data *prssdp;
-	struct dasd_eckd_private *private;
 	struct dasd_ccw_req *cqr;
 	struct ccw1 *ccw;
 	int rc;
 
-	private = (struct dasd_eckd_private *) device->private;
 	cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */	+ 1 /* RSSD */,
 				   (sizeof(struct dasd_psf_prssd_data) +
 				    sizeof(struct dasd_rssd_messages)),
@@ -4686,11 +4669,10 @@ static struct dasd_conf_data *dasd_eckd_get_ref_conf(struct dasd_device *device,
 						     __u8 lpum,
 						     struct dasd_cuir_message *cuir)
 {
-	struct dasd_eckd_private *private;
+	struct dasd_eckd_private *private = device->private;
 	struct dasd_conf_data *conf_data;
 	int path, pos;
 
-	private = (struct dasd_eckd_private *) device->private;
 	if (cuir->record_selector == 0)
 		goto out;
 	for (path = 0x80, pos = 0; path; path >>= 1, pos++) {
@@ -4715,9 +4697,9 @@ out:
 static int dasd_eckd_cuir_scope(struct dasd_device *device, __u8 lpum,
 				struct dasd_cuir_message *cuir)
 {
+	struct dasd_eckd_private *private = device->private;
 	struct dasd_conf_data *ref_conf_data;
 	unsigned long bitmask = 0, mask = 0;
-	struct dasd_eckd_private *private;
 	struct dasd_conf_data *conf_data;
 	unsigned int pos, path;
 	char *ref_gneq, *gneq;
@@ -4730,7 +4712,6 @@ static int dasd_eckd_cuir_scope(struct dasd_device *device, __u8 lpum,
 	    !(cuir->neq_map[0] | cuir->neq_map[1] | cuir->neq_map[2]))
 		return lpum;
 
-	private = (struct dasd_eckd_private *) device->private;
 	/* get reference conf data */
 	ref_conf_data = dasd_eckd_get_ref_conf(device, lpum, cuir);
 	/* reference ned is determined by ned_map field */
@@ -4829,14 +4810,13 @@ static int dasd_eckd_cuir_quiesce(struct dasd_device *device, __u8 lpum,
 				  struct subchannel_id sch_id,
 				  struct dasd_cuir_message *cuir)
 {
+	struct dasd_eckd_private *private = device->private;
 	struct alias_pav_group *pavgroup, *tempgroup;
-	struct dasd_eckd_private *private;
 	struct dasd_device *dev, *n;
 	unsigned long paths = 0;
 	unsigned long flags;
 	int tbcpm;
 
-	private = (struct dasd_eckd_private *) device->private;
 	/* active devices */
 	list_for_each_entry_safe(dev, n, &private->lcu->active_devices,
 				 alias_list) {
@@ -4892,13 +4872,12 @@ static int dasd_eckd_cuir_resume(struct dasd_device *device, __u8 lpum,
 				 struct subchannel_id sch_id,
 				 struct dasd_cuir_message *cuir)
 {
+	struct dasd_eckd_private *private = device->private;
 	struct alias_pav_group *pavgroup, *tempgroup;
-	struct dasd_eckd_private *private;
 	struct dasd_device *dev, *n;
 	unsigned long paths = 0;
 	int tbcpm;
 
-	private = (struct dasd_eckd_private *) device->private;
 	/*
 	 * the path may have been added through a generic path event before
 	 * only trigger path verification if the path is not already in use
diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c
index c9262e78938b..d7b5b550364b 100644
--- a/drivers/s390/block/dasd_fba.c
+++ b/drivers/s390/block/dasd_fba.c
@@ -125,13 +125,11 @@ locate_record(struct ccw1 * ccw, struct LO_fba_data *data, int rw,
 static int
 dasd_fba_check_characteristics(struct dasd_device *device)
 {
-	struct dasd_block *block;
-	struct dasd_fba_private *private;
+	struct dasd_fba_private *private = device->private;
 	struct ccw_device *cdev = device->cdev;
-	int rc;
-	int readonly;
+	struct dasd_block *block;
+	int readonly, rc;
 
-	private = (struct dasd_fba_private *) device->private;
 	if (!private) {
 		private = kzalloc(sizeof(*private), GFP_KERNEL | GFP_DMA);
 		if (!private) {
@@ -140,7 +138,7 @@ dasd_fba_check_characteristics(struct dasd_device *device)
 				 "data failed\n");
 			return -ENOMEM;
 		}
-		device->private = (void *) private;
+		device->private = private;
 	} else {
 		memset(private, 0, sizeof(*private));
 	}
@@ -192,10 +190,9 @@ dasd_fba_check_characteristics(struct dasd_device *device)
 
 static int dasd_fba_do_analysis(struct dasd_block *block)
 {
-	struct dasd_fba_private *private;
+	struct dasd_fba_private *private = block->base->private;
 	int sb, rc;
 
-	private = (struct dasd_fba_private *) block->base->private;
 	rc = dasd_check_blocksize(private->rdc_data.blk_size);
 	if (rc) {
 		DBF_DEV_EVENT(DBF_WARNING, block->base, "unknown blocksize %d",
@@ -254,7 +251,7 @@ static struct dasd_ccw_req *dasd_fba_build_cp(struct dasd_device * memdev,
 					      struct dasd_block *block,
 					      struct request *req)
 {
-	struct dasd_fba_private *private;
+	struct dasd_fba_private *private = block->base->private;
 	unsigned long *idaws;
 	struct LO_fba_data *LO_data;
 	struct dasd_ccw_req *cqr;
@@ -267,7 +264,6 @@ static struct dasd_ccw_req *dasd_fba_build_cp(struct dasd_device * memdev,
 	unsigned int blksize, off;
 	unsigned char cmd;
 
-	private = (struct dasd_fba_private *) block->base->private;
 	if (rq_data_dir(req) == READ) {
 		cmd = DASD_FBA_CCW_READ;
 	} else if (rq_data_dir(req) == WRITE) {
@@ -379,7 +375,7 @@ static struct dasd_ccw_req *dasd_fba_build_cp(struct dasd_device * memdev,
 static int
 dasd_fba_free_cp(struct dasd_ccw_req *cqr, struct request *req)
 {
-	struct dasd_fba_private *private;
+	struct dasd_fba_private *private = cqr->block->base->private;
 	struct ccw1 *ccw;
 	struct req_iterator iter;
 	struct bio_vec bv;
@@ -389,7 +385,6 @@ dasd_fba_free_cp(struct dasd_ccw_req *cqr, struct request *req)
 
 	if (!dasd_page_cache)
 		goto out;
-	private = (struct dasd_fba_private *) cqr->block->base->private;
 	blksize = cqr->block->bp_block;
 	ccw = cqr->cpaddr;
 	/* Skip over define extent & locate record. */
@@ -436,13 +431,14 @@ static int
 dasd_fba_fill_info(struct dasd_device * device,
 		   struct dasd_information2_t * info)
 {
+	struct dasd_fba_private *private = device->private;
+
 	info->label_block = 1;
 	info->FBA_layout = 1;
 	info->format = DASD_FORMAT_LDL;
-	info->characteristics_size = sizeof(struct dasd_fba_characteristics);
-	memcpy(info->characteristics,
-	       &((struct dasd_fba_private *) device->private)->rdc_data,
-	       sizeof (struct dasd_fba_characteristics));
+	info->characteristics_size = sizeof(private->rdc_data);
+	memcpy(info->characteristics, &private->rdc_data,
+	       sizeof(private->rdc_data));
 	info->confdata_size = 0;
 	return 0;
 }
diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c
index ef1d9fb06cab..31d544a87ba9 100644
--- a/drivers/s390/block/dasd_genhd.c
+++ b/drivers/s390/block/dasd_genhd.c
@@ -178,8 +178,8 @@ int dasd_gendisk_init(void)
 	/* Register to static dasd major 94 */
 	rc = register_blkdev(DASD_MAJOR, "dasd");
 	if (rc != 0) {
-		pr_warning("Registering the device driver with major number "
-			   "%d failed\n", DASD_MAJOR);
+		pr_warn("Registering the device driver with major number %d failed\n",
+			DASD_MAJOR);
 		return rc;
 	}
 	return 0;
diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
index 4aed5ed70836..8de29be32a56 100644
--- a/drivers/s390/block/dasd_int.h
+++ b/drivers/s390/block/dasd_int.h
@@ -241,6 +241,13 @@ struct dasd_ccw_req {
 typedef struct dasd_ccw_req *(*dasd_erp_fn_t) (struct dasd_ccw_req *);
 
 /*
+ * A single CQR can only contain a maximum of 255 CCWs. It is limited by
+ * the locate record and locate record extended count value which can only hold
+ * 1 Byte max.
+ */
+#define DASD_CQR_MAX_CCW 255
+
+/*
  * Unique identifier for dasd device.
  */
 #define UA_NOT_CONFIGURED  0x00
@@ -438,7 +445,7 @@ struct dasd_device {
 	/* Device discipline stuff. */
 	struct dasd_discipline *discipline;
 	struct dasd_discipline *base_discipline;
-	char *private;
+	void *private;
 	struct dasd_path path_data;
 
 	/* Device state and target state. */
diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
index 02837d0ad942..90f30cc31561 100644
--- a/drivers/s390/block/dasd_ioctl.c
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -203,9 +203,7 @@ static int
 dasd_format(struct dasd_block *block, struct format_data_t *fdata)
 {
 	struct dasd_device *base;
-	int enable_pav = 1;
-	int rc, retries;
-	int start, stop;
+	int rc;
 
 	base = block->base;
 	if (base->discipline->format_device == NULL)
@@ -233,30 +231,11 @@ dasd_format(struct dasd_block *block, struct format_data_t *fdata)
 		bdput(bdev);
 	}
 
-	retries = 255;
-	/* backup start- and endtrack for retries */
-	start = fdata->start_unit;
-	stop = fdata->stop_unit;
-	do {
-		rc = base->discipline->format_device(base, fdata, enable_pav);
-		if (rc) {
-			if (rc == -EAGAIN) {
-				retries--;
-				/* disable PAV in case of errors */
-				enable_pav = 0;
-				fdata->start_unit = start;
-				fdata->stop_unit = stop;
-			} else
-				return rc;
-		} else
-			/* success */
-			break;
-	} while (retries);
-
-	if (!retries)
-		return -EIO;
-	else
-		return 0;
+	rc = base->discipline->format_device(base, fdata, 1);
+	if (rc == -EAGAIN)
+		rc = base->discipline->format_device(base, fdata, 0);
+
+	return rc;
 }
 
 /*
@@ -286,9 +265,8 @@ dasd_ioctl_format(struct block_device *bdev, void __user *argp)
 		return -EFAULT;
 	}
 	if (bdev != bdev->bd_contains) {
-		pr_warning("%s: The specified DASD is a partition and cannot "
-			   "be formatted\n",
-			   dev_name(&base->cdev->dev));
+		pr_warn("%s: The specified DASD is a partition and cannot be formatted\n",
+			dev_name(&base->cdev->dev));
 		dasd_put_device(base);
 		return -EINVAL;
 	}
diff --git a/drivers/s390/block/dasd_proc.c b/drivers/s390/block/dasd_proc.c
index aa7bb2d1da81..bad7a196bf84 100644
--- a/drivers/s390/block/dasd_proc.c
+++ b/drivers/s390/block/dasd_proc.c
@@ -322,13 +322,12 @@ static ssize_t dasd_stats_proc_write(struct file *file,
 	return user_len;
 out_parse_error:
 	rc = -EINVAL;
-	pr_warning("%s is not a supported value for /proc/dasd/statistics\n",
-		str);
+	pr_warn("%s is not a supported value for /proc/dasd/statistics\n", str);
 out_error:
 	vfree(buffer);
 	return rc;
 #else
-	pr_warning("/proc/dasd/statistics: is not activated in this kernel\n");
+	pr_warn("/proc/dasd/statistics: is not activated in this kernel\n");
 	return user_len;
 #endif				/* CONFIG_DASD_PROFILE */
 }
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index ce7b70181740..1bce9cf51b1e 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -738,15 +738,15 @@ dcssblk_remove_store(struct device *dev, struct device_attribute *attr, const ch
 	dev_info = dcssblk_get_device_by_name(local_buf);
 	if (dev_info == NULL) {
 		up_write(&dcssblk_devices_sem);
-		pr_warning("Device %s cannot be removed because it is not a "
-			   "known device\n", local_buf);
+		pr_warn("Device %s cannot be removed because it is not a known device\n",
+			local_buf);
 		rc = -ENODEV;
 		goto out_buf;
 	}
 	if (atomic_read(&dev_info->use_count) != 0) {
 		up_write(&dcssblk_devices_sem);
-		pr_warning("Device %s cannot be removed while it is in "
-			   "use\n", local_buf);
+		pr_warn("Device %s cannot be removed while it is in use\n",
+			local_buf);
 		rc = -EBUSY;
 		goto out_buf;
 	}
@@ -850,9 +850,8 @@ dcssblk_make_request(struct request_queue *q, struct bio *bio)
 		case SEG_TYPE_SC:
 			/* cannot write to these segments */
 			if (bio_data_dir(bio) == WRITE) {
-				pr_warning("Writing to %s failed because it "
-					   "is a read-only device\n",
-					   dev_name(&dev_info->dev));
+				pr_warn("Writing to %s failed because it is a read-only device\n",
+					dev_name(&dev_info->dev));
 				goto fail;
 			}
 		}
diff --git a/drivers/s390/char/monreader.c b/drivers/s390/char/monreader.c
index fc94bfdceb95..ebdeaa53182d 100644
--- a/drivers/s390/char/monreader.c
+++ b/drivers/s390/char/monreader.c
@@ -257,7 +257,7 @@ static void mon_iucv_message_pending(struct iucv_path *path,
 	memcpy(&monpriv->msg_array[monpriv->write_index]->msg,
 	       msg, sizeof(*msg));
 	if (atomic_inc_return(&monpriv->msglim_count) == MON_MSGLIM) {
-		pr_warning("The read queue for monitor data is full\n");
+		pr_warn("The read queue for monitor data is full\n");
 		monpriv->msg_array[monpriv->write_index]->msglim_reached = 1;
 	}
 	monpriv->write_index = (monpriv->write_index + 1) % MON_MSGLIM;
@@ -342,8 +342,8 @@ static int mon_close(struct inode *inode, struct file *filp)
 	if (monpriv->path) {
 		rc = iucv_path_sever(monpriv->path, user_data_sever);
 		if (rc)
-			pr_warning("Disconnecting the z/VM *MONITOR system "
-				   "service failed with rc=%i\n", rc);
+			pr_warn("Disconnecting the z/VM *MONITOR system service failed with rc=%i\n",
+				rc);
 		iucv_path_free(monpriv->path);
 	}
 
@@ -469,8 +469,8 @@ static int monreader_freeze(struct device *dev)
 	if (monpriv->path) {
 		rc = iucv_path_sever(monpriv->path, user_data_sever);
 		if (rc)
-			pr_warning("Disconnecting the z/VM *MONITOR system "
-				   "service failed with rc=%i\n", rc);
+			pr_warn("Disconnecting the z/VM *MONITOR system service failed with rc=%i\n",
+				rc);
 		iucv_path_free(monpriv->path);
 	}
 	atomic_set(&monpriv->iucv_severed, 0);
diff --git a/drivers/s390/char/sclp_cmd.c b/drivers/s390/char/sclp_cmd.c
index 806239c2cf2f..d3947ea3e351 100644
--- a/drivers/s390/char/sclp_cmd.c
+++ b/drivers/s390/char/sclp_cmd.c
@@ -67,8 +67,8 @@ int sclp_sync_request_timeout(sclp_cmdw_t cmd, void *sccb, int timeout)
 
 	/* Check response. */
 	if (request->status != SCLP_REQ_DONE) {
-		pr_warning("sync request failed (cmd=0x%08x, "
-			   "status=0x%02x)\n", cmd, request->status);
+		pr_warn("sync request failed (cmd=0x%08x, status=0x%02x)\n",
+			cmd, request->status);
 		rc = -EIO;
 	}
 out:
@@ -122,8 +122,8 @@ int sclp_get_core_info(struct sclp_core_info *info)
 	if (rc)
 		goto out;
 	if (sccb->header.response_code != 0x0010) {
-		pr_warning("readcpuinfo failed (response=0x%04x)\n",
-			   sccb->header.response_code);
+		pr_warn("readcpuinfo failed (response=0x%04x)\n",
+			sccb->header.response_code);
 		rc = -EIO;
 		goto out;
 	}
@@ -160,9 +160,8 @@ static int do_core_configure(sclp_cmdw_t cmd)
 	case 0x0120:
 		break;
 	default:
-		pr_warning("configure cpu failed (cmd=0x%08x, "
-			   "response=0x%04x)\n", cmd,
-			   sccb->header.response_code);
+		pr_warn("configure cpu failed (cmd=0x%08x, response=0x%04x)\n",
+			cmd, sccb->header.response_code);
 		rc = -EIO;
 		break;
 	}
@@ -230,9 +229,8 @@ static int do_assign_storage(sclp_cmdw_t cmd, u16 rn)
 	case 0x0120:
 		break;
 	default:
-		pr_warning("assign storage failed (cmd=0x%08x, "
-			   "response=0x%04x, rn=0x%04x)\n", cmd,
-			   sccb->header.response_code, rn);
+		pr_warn("assign storage failed (cmd=0x%08x, response=0x%04x, rn=0x%04x)\n",
+			cmd, sccb->header.response_code, rn);
 		rc = -EIO;
 		break;
 	}
@@ -675,9 +673,8 @@ static int do_chp_configure(sclp_cmdw_t cmd)
 	case 0x0450:
 		break;
 	default:
-		pr_warning("configure channel-path failed "
-			   "(cmd=0x%08x, response=0x%04x)\n", cmd,
-			   sccb->header.response_code);
+		pr_warn("configure channel-path failed (cmd=0x%08x, response=0x%04x)\n",
+			cmd, sccb->header.response_code);
 		rc = -EIO;
 		break;
 	}
@@ -744,8 +741,8 @@ int sclp_chp_read_info(struct sclp_chp_info *info)
 	if (rc)
 		goto out;
 	if (sccb->header.response_code != 0x0010) {
-		pr_warning("read channel-path info failed "
-			   "(response=0x%04x)\n", sccb->header.response_code);
+		pr_warn("read channel-path info failed (response=0x%04x)\n",
+			sccb->header.response_code);
 		rc = -EIO;
 		goto out;
 	}
diff --git a/drivers/s390/char/sclp_cpi_sys.c b/drivers/s390/char/sclp_cpi_sys.c
index 2acea809e2ac..f344e5bd2d9f 100644
--- a/drivers/s390/char/sclp_cpi_sys.c
+++ b/drivers/s390/char/sclp_cpi_sys.c
@@ -154,16 +154,14 @@ static int cpi_req(void)
 	wait_for_completion(&completion);
 
 	if (req->status != SCLP_REQ_DONE) {
-		pr_warning("request failed (status=0x%02x)\n",
-			   req->status);
+		pr_warn("request failed (status=0x%02x)\n", req->status);
 		rc = -EIO;
 		goto out_free_req;
 	}
 
 	response = ((struct cpi_sccb *) req->sccb)->header.response_code;
 	if (response != 0x0020) {
-		pr_warning("request failed with response code 0x%x\n",
-			   response);
+		pr_warn("request failed with response code 0x%x\n", response);
 		rc = -EIO;
 	}
 
diff --git a/drivers/s390/char/tape_core.c b/drivers/s390/char/tape_core.c
index f3b5123faf08..3c379da2eef8 100644
--- a/drivers/s390/char/tape_core.c
+++ b/drivers/s390/char/tape_core.c
@@ -699,8 +699,8 @@ tape_generic_remove(struct ccw_device *cdev)
 			 */
 			DBF_EVENT(3, "(%08x): Drive in use vanished!\n",
 				device->cdev_id);
-			pr_warning("%s: A tape unit was detached while in "
-				   "use\n", dev_name(&device->cdev->dev));
+			pr_warn("%s: A tape unit was detached while in use\n",
+				dev_name(&device->cdev->dev));
 			tape_state_set(device, TS_NOT_OPER);
 			__tape_discard_requests(device);
 			spin_unlock_irq(get_ccwdev_lock(device->cdev));
diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c
index 799c1524c779..e883063c7258 100644
--- a/drivers/s390/char/vmlogrdr.c
+++ b/drivers/s390/char/vmlogrdr.c
@@ -343,8 +343,7 @@ static int vmlogrdr_open (struct inode *inode, struct file *filp)
 	if (logptr->autorecording) {
 		ret = vmlogrdr_recording(logptr,1,logptr->autopurge);
 		if (ret)
-			pr_warning("vmlogrdr: failed to start "
-				   "recording automatically\n");
+			pr_warn("vmlogrdr: failed to start recording automatically\n");
 	}
 
 	/* create connection to the system service */
@@ -396,8 +395,7 @@ static int vmlogrdr_release (struct inode *inode, struct file *filp)
 	if (logptr->autorecording) {
 		ret = vmlogrdr_recording(logptr,0,logptr->autopurge);
 		if (ret)
-			pr_warning("vmlogrdr: failed to stop "
-				   "recording automatically\n");
+			pr_warn("vmlogrdr: failed to stop recording automatically\n");
 	}
 	logptr->dev_in_use = 0;
 
diff --git a/drivers/s390/cio/blacklist.c b/drivers/s390/cio/blacklist.c
index 20314aad7ab7..9082476b51db 100644
--- a/drivers/s390/cio/blacklist.c
+++ b/drivers/s390/cio/blacklist.c
@@ -51,9 +51,8 @@ static int blacklist_range(range_action action, unsigned int from_ssid,
 {
 	if ((from_ssid > to_ssid) || ((from_ssid == to_ssid) && (from > to))) {
 		if (msgtrigger)
-			pr_warning("0.%x.%04x to 0.%x.%04x is not a valid "
-				   "range for cio_ignore\n", from_ssid, from,
-				   to_ssid, to);
+			pr_warn("0.%x.%04x to 0.%x.%04x is not a valid range for cio_ignore\n",
+				from_ssid, from, to_ssid, to);
 
 		return 1;
 	}
@@ -140,8 +139,8 @@ static int parse_busid(char *str, unsigned int *cssid, unsigned int *ssid,
 	rc = 0;
 out:
 	if (rc && msgtrigger)
-		pr_warning("%s is not a valid device for the cio_ignore "
-			   "kernel parameter\n", str);
+		pr_warn("%s is not a valid device for the cio_ignore kernel parameter\n",
+			str);
 
 	return rc;
 }
diff --git a/drivers/s390/cio/ccwreq.c b/drivers/s390/cio/ccwreq.c
index 79f59915f71b..2782100b2c07 100644
--- a/drivers/s390/cio/ccwreq.c
+++ b/drivers/s390/cio/ccwreq.c
@@ -333,13 +333,12 @@ void ccw_request_timeout(struct ccw_device *cdev)
 
 	for (chp = 0; chp < 8; chp++) {
 		if ((0x80 >> chp) & sch->schib.pmcw.lpum)
-			pr_warning("%s: No interrupt was received within %lus "
-				   "(CS=%02x, DS=%02x, CHPID=%x.%02x)\n",
-				   dev_name(&cdev->dev), req->timeout / HZ,
-				   scsw_cstat(&sch->schib.scsw),
-				   scsw_dstat(&sch->schib.scsw),
-				   sch->schid.cssid,
-				   sch->schib.pmcw.chpid[chp]);
+			pr_warn("%s: No interrupt was received within %lus (CS=%02x, DS=%02x, CHPID=%x.%02x)\n",
+				dev_name(&cdev->dev), req->timeout / HZ,
+				scsw_cstat(&sch->schib.scsw),
+				scsw_dstat(&sch->schib.scsw),
+				sch->schid.cssid,
+				sch->schib.pmcw.chpid[chp]);
 	}
 
 	if (!ccwreq_next_path(cdev)) {
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index 39a8ae54e9c1..de6fccc13124 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -656,7 +656,7 @@ struct subchannel *cio_probe_console(void)
 
 	sch_no = cio_get_console_sch_no();
 	if (sch_no == -1) {
-		pr_warning("No CCW console was found\n");
+		pr_warn("No CCW console was found\n");
 		return ERR_PTR(-ENODEV);
 	}
 	init_subchannel_id(&schid);
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index 6aae68412802..7ada078ffdd0 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -364,11 +364,11 @@ int ccw_device_set_offline(struct ccw_device *cdev)
 		   cdev->private->state == DEV_STATE_DISCONNECTED));
 	/* Inform the user if set offline failed. */
 	if (cdev->private->state == DEV_STATE_BOXED) {
-		pr_warning("%s: The device entered boxed state while "
-			   "being set offline\n", dev_name(&cdev->dev));
+		pr_warn("%s: The device entered boxed state while being set offline\n",
+			dev_name(&cdev->dev));
 	} else if (cdev->private->state == DEV_STATE_NOT_OPER) {
-		pr_warning("%s: The device stopped operating while "
-			   "being set offline\n", dev_name(&cdev->dev));
+		pr_warn("%s: The device stopped operating while being set offline\n",
+			dev_name(&cdev->dev));
 	}
 	/* Give up reference from ccw_device_set_online(). */
 	put_device(&cdev->dev);
@@ -429,13 +429,11 @@ int ccw_device_set_online(struct ccw_device *cdev)
 		spin_unlock_irq(cdev->ccwlock);
 		/* Inform the user that set online failed. */
 		if (cdev->private->state == DEV_STATE_BOXED) {
-			pr_warning("%s: Setting the device online failed "
-				   "because it is boxed\n",
-				   dev_name(&cdev->dev));
+			pr_warn("%s: Setting the device online failed because it is boxed\n",
+				dev_name(&cdev->dev));
 		} else if (cdev->private->state == DEV_STATE_NOT_OPER) {
-			pr_warning("%s: Setting the device online failed "
-				   "because it is not operational\n",
-				   dev_name(&cdev->dev));
+			pr_warn("%s: Setting the device online failed because it is not operational\n",
+				dev_name(&cdev->dev));
 		}
 		/* Give up online reference since onlining failed. */
 		put_device(&cdev->dev);
@@ -619,9 +617,8 @@ initiate_logging(struct device *dev, struct device_attribute *attr,
 
 	rc = chsc_siosl(sch->schid);
 	if (rc < 0) {
-		pr_warning("Logging for subchannel 0.%x.%04x failed with "
-			   "errno=%d\n",
-			   sch->schid.ssid, sch->schid.sch_no, rc);
+		pr_warn("Logging for subchannel 0.%x.%04x failed with errno=%d\n",
+			sch->schid.ssid, sch->schid.sch_no, rc);
 		return rc;
 	}
 	pr_notice("Logging for subchannel 0.%x.%04x was triggered\n",
diff --git a/drivers/s390/net/lcs.c b/drivers/s390/net/lcs.c
index 2f5b518b0e78..251db0a02e73 100644
--- a/drivers/s390/net/lcs.c
+++ b/drivers/s390/net/lcs.c
@@ -1761,8 +1761,8 @@ lcs_get_control(struct lcs_card *card, struct lcs_cmd *cmd)
 			lcs_schedule_recovery(card);
 			break;
 		case LCS_CMD_STOPLAN:
-			pr_warning("Stoplan for %s initiated by LGW.\n",
-				   card->dev->name);
+			pr_warn("Stoplan for %s initiated by LGW\n",
+				card->dev->name);
 			if (card->dev)
 				netif_carrier_off(card->dev);
 			break;
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 7c8c68c26540..ac544330daeb 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3624,7 +3624,7 @@ static int qeth_l3_register_notifiers(void)
 		return rc;
 	}
 #else
-	pr_warning("There is no IPv6 support for the layer 3 discipline\n");
+	pr_warn("There is no IPv6 support for the layer 3 discipline\n");
 #endif
 	return 0;
 }
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index e2f31c93717d..e80768f8e579 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -596,6 +596,7 @@ config XEN_SCSI_FRONTEND
 config HYPERV_STORAGE
 	tristate "Microsoft Hyper-V virtual storage driver"
 	depends on SCSI && HYPERV
+	depends on m || SCSI_FC_ATTRS != m
 	default HYPERV
 	help
 	  Select this option to enable the Hyper-V virtual storage driver.
diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c
index d72867257346..3eff2a69fe08 100644
--- a/drivers/scsi/NCR5380.c
+++ b/drivers/scsi/NCR5380.c
@@ -760,7 +760,7 @@ static struct scsi_cmnd *dequeue_next_cmd(struct Scsi_Host *instance)
 	struct NCR5380_cmd *ncmd;
 	struct scsi_cmnd *cmd;
 
-	if (list_empty(&hostdata->autosense)) {
+	if (hostdata->sensing || list_empty(&hostdata->autosense)) {
 		list_for_each_entry(ncmd, &hostdata->unissued, list) {
 			cmd = NCR5380_to_scmd(ncmd);
 			dsprintk(NDEBUG_QUEUES, instance, "dequeue: cmd=%p target=%d busy=0x%02x lun=%llu\n",
@@ -793,7 +793,7 @@ static void requeue_cmd(struct Scsi_Host *instance, struct scsi_cmnd *cmd)
 	struct NCR5380_hostdata *hostdata = shost_priv(instance);
 	struct NCR5380_cmd *ncmd = scsi_cmd_priv(cmd);
 
-	if (hostdata->sensing) {
+	if (hostdata->sensing == cmd) {
 		scsi_eh_restore_cmnd(cmd, &hostdata->ses);
 		list_add(&ncmd->list, &hostdata->autosense);
 		hostdata->sensing = NULL;
@@ -815,15 +815,17 @@ static void NCR5380_main(struct work_struct *work)
 	struct NCR5380_hostdata *hostdata =
 		container_of(work, struct NCR5380_hostdata, main_task);
 	struct Scsi_Host *instance = hostdata->host;
-	struct scsi_cmnd *cmd;
 	int done;
 
 	do {
 		done = 1;
 
 		spin_lock_irq(&hostdata->lock);
-		while (!hostdata->connected &&
-		       (cmd = dequeue_next_cmd(instance))) {
+		while (!hostdata->connected && !hostdata->selecting) {
+			struct scsi_cmnd *cmd = dequeue_next_cmd(instance);
+
+			if (!cmd)
+				break;
 
 			dsprintk(NDEBUG_MAIN, instance, "main: dequeued %p\n", cmd);
 
@@ -840,8 +842,7 @@ static void NCR5380_main(struct work_struct *work)
 			 * entire unit.
 			 */
 
-			cmd = NCR5380_select(instance, cmd);
-			if (!cmd) {
+			if (!NCR5380_select(instance, cmd)) {
 				dsprintk(NDEBUG_MAIN, instance, "main: select complete\n");
 			} else {
 				dsprintk(NDEBUG_MAIN | NDEBUG_QUEUES, instance,
@@ -1056,6 +1057,11 @@ static struct scsi_cmnd *NCR5380_select(struct Scsi_Host *instance,
 		/* Reselection interrupt */
 		goto out;
 	}
+	if (!hostdata->selecting) {
+		/* Command was aborted */
+		NCR5380_write(MODE_REG, MR_BASE);
+		goto out;
+	}
 	if (err < 0) {
 		NCR5380_write(MODE_REG, MR_BASE);
 		shost_printk(KERN_ERR, instance,
@@ -1759,9 +1765,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 	unsigned char msgout = NOP;
 	int sink = 0;
 	int len;
-#if defined(PSEUDO_DMA) || defined(REAL_DMA_POLL)
 	int transfersize;
-#endif
 	unsigned char *data;
 	unsigned char phase, tmp, extended_msg[10], old_phase = 0xff;
 	struct scsi_cmnd *cmd;
@@ -1798,6 +1802,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 				do_abort(instance);
 				cmd->result = DID_ERROR << 16;
 				complete_cmd(instance, cmd);
+				hostdata->connected = NULL;
 				return;
 #endif
 			case PHASE_DATAIN:
@@ -1847,20 +1852,23 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 						sink = 1;
 						do_abort(instance);
 						cmd->result = DID_ERROR << 16;
-						complete_cmd(instance, cmd);
 						/* XXX - need to source or sink data here, as appropriate */
 					} else
 						cmd->SCp.this_residual -= transfersize - len;
 				} else
 #endif				/* defined(PSEUDO_DMA) || defined(REAL_DMA_POLL) */
 				{
-					spin_unlock_irq(&hostdata->lock);
-					NCR5380_transfer_pio(instance, &phase,
-					                     (int *)&cmd->SCp.this_residual,
+					/* Break up transfer into 3 ms chunks,
+					 * presuming 6 accesses per handshake.
+					 */
+					transfersize = min((unsigned long)cmd->SCp.this_residual,
+					                   hostdata->accesses_per_ms / 2);
+					len = transfersize;
+					NCR5380_transfer_pio(instance, &phase, &len,
 					                     (unsigned char **)&cmd->SCp.ptr);
-					spin_lock_irq(&hostdata->lock);
+					cmd->SCp.this_residual -= transfersize - len;
 				}
-				break;
+				return;
 			case PHASE_MSGIN:
 				len = 1;
 				data = &tmp;
@@ -2292,14 +2300,17 @@ static bool list_del_cmd(struct list_head *haystack,
  * [disconnected -> connected ->]...
  * [autosense -> connected ->] done
  *
- * If cmd is unissued then just remove it.
- * If cmd is disconnected, try to select the target.
- * If cmd is connected, try to send an abort message.
- * If cmd is waiting for autosense, give it a chance to complete but check
- * that it isn't left connected.
  * If cmd was not found at all then presumably it has already been completed,
  * in which case return SUCCESS to try to avoid further EH measures.
+ *
  * If the command has not completed yet, we must not fail to find it.
+ * We have no option but to forget the aborted command (even if it still
+ * lacks sense data). The mid-layer may re-issue a command that is in error
+ * recovery (see scsi_send_eh_cmnd), but the logic and data structures in
+ * this driver are such that a command can appear on one queue only.
+ *
+ * The lock protects driver data structures, but EH handlers also use it
+ * to serialize their own execution and prevent their own re-entry.
  */
 
 static int NCR5380_abort(struct scsi_cmnd *cmd)
@@ -2322,6 +2333,7 @@ static int NCR5380_abort(struct scsi_cmnd *cmd)
 		         "abort: removed %p from issue queue\n", cmd);
 		cmd->result = DID_ABORT << 16;
 		cmd->scsi_done(cmd); /* No tag or busy flag to worry about */
+		goto out;
 	}
 
 	if (hostdata->selecting == cmd) {
@@ -2336,58 +2348,21 @@ static int NCR5380_abort(struct scsi_cmnd *cmd)
 	if (list_del_cmd(&hostdata->disconnected, cmd)) {
 		dsprintk(NDEBUG_ABORT, instance,
 		         "abort: removed %p from disconnected list\n", cmd);
-		cmd->result = DID_ERROR << 16;
-		if (!hostdata->connected)
-			NCR5380_select(instance, cmd);
-		if (hostdata->connected != cmd) {
-			complete_cmd(instance, cmd);
-			result = FAILED;
-			goto out;
-		}
+		/* Can't call NCR5380_select() and send ABORT because that
+		 * means releasing the lock. Need a bus reset.
+		 */
+		set_host_byte(cmd, DID_ERROR);
+		complete_cmd(instance, cmd);
+		result = FAILED;
+		goto out;
 	}
 
 	if (hostdata->connected == cmd) {
 		dsprintk(NDEBUG_ABORT, instance, "abort: cmd %p is connected\n", cmd);
 		hostdata->connected = NULL;
-		if (do_abort(instance)) {
-			set_host_byte(cmd, DID_ERROR);
-			complete_cmd(instance, cmd);
-			result = FAILED;
-			goto out;
-		}
-		set_host_byte(cmd, DID_ABORT);
 #ifdef REAL_DMA
 		hostdata->dma_len = 0;
 #endif
-		if (cmd->cmnd[0] == REQUEST_SENSE)
-			complete_cmd(instance, cmd);
-		else {
-			struct NCR5380_cmd *ncmd = scsi_cmd_priv(cmd);
-
-			/* Perform autosense for this command */
-			list_add(&ncmd->list, &hostdata->autosense);
-		}
-	}
-
-	if (list_find_cmd(&hostdata->autosense, cmd)) {
-		dsprintk(NDEBUG_ABORT, instance,
-		         "abort: found %p on sense queue\n", cmd);
-		spin_unlock_irqrestore(&hostdata->lock, flags);
-		queue_work(hostdata->work_q, &hostdata->main_task);
-		msleep(1000);
-		spin_lock_irqsave(&hostdata->lock, flags);
-		if (list_del_cmd(&hostdata->autosense, cmd)) {
-			dsprintk(NDEBUG_ABORT, instance,
-			         "abort: removed %p from sense queue\n", cmd);
-			set_host_byte(cmd, DID_ABORT);
-			complete_cmd(instance, cmd);
-			goto out;
-		}
-	}
-
-	if (hostdata->connected == cmd) {
-		dsprintk(NDEBUG_ABORT, instance, "abort: cmd %p is connected\n", cmd);
-		hostdata->connected = NULL;
 		if (do_abort(instance)) {
 			set_host_byte(cmd, DID_ERROR);
 			complete_cmd(instance, cmd);
@@ -2395,9 +2370,14 @@ static int NCR5380_abort(struct scsi_cmnd *cmd)
 			goto out;
 		}
 		set_host_byte(cmd, DID_ABORT);
-#ifdef REAL_DMA
-		hostdata->dma_len = 0;
-#endif
+		complete_cmd(instance, cmd);
+		goto out;
+	}
+
+	if (list_del_cmd(&hostdata->autosense, cmd)) {
+		dsprintk(NDEBUG_ABORT, instance,
+		         "abort: removed %p from sense queue\n", cmd);
+		set_host_byte(cmd, DID_ERROR);
 		complete_cmd(instance, cmd);
 	}
 
@@ -2450,7 +2430,16 @@ static int NCR5380_bus_reset(struct scsi_cmnd *cmd)
 	 * commands!
 	 */
 
-	hostdata->selecting = NULL;
+	if (list_del_cmd(&hostdata->unissued, cmd)) {
+		cmd->result = DID_RESET << 16;
+		cmd->scsi_done(cmd);
+	}
+
+	if (hostdata->selecting) {
+		hostdata->selecting->result = DID_RESET << 16;
+		complete_cmd(instance, hostdata->selecting);
+		hostdata->selecting = NULL;
+	}
 
 	list_for_each_entry(ncmd, &hostdata->disconnected, list) {
 		struct scsi_cmnd *cmd = NCR5380_to_scmd(ncmd);
@@ -2458,6 +2447,7 @@ static int NCR5380_bus_reset(struct scsi_cmnd *cmd)
 		set_host_byte(cmd, DID_RESET);
 		cmd->scsi_done(cmd);
 	}
+	INIT_LIST_HEAD(&hostdata->disconnected);
 
 	list_for_each_entry(ncmd, &hostdata->autosense, list) {
 		struct scsi_cmnd *cmd = NCR5380_to_scmd(ncmd);
@@ -2465,6 +2455,7 @@ static int NCR5380_bus_reset(struct scsi_cmnd *cmd)
 		set_host_byte(cmd, DID_RESET);
 		cmd->scsi_done(cmd);
 	}
+	INIT_LIST_HEAD(&hostdata->autosense);
 
 	if (hostdata->connected) {
 		set_host_byte(hostdata->connected, DID_RESET);
@@ -2472,12 +2463,6 @@ static int NCR5380_bus_reset(struct scsi_cmnd *cmd)
 		hostdata->connected = NULL;
 	}
 
-	if (hostdata->sensing) {
-		set_host_byte(hostdata->connected, DID_RESET);
-		complete_cmd(instance, hostdata->sensing);
-		hostdata->sensing = NULL;
-	}
-
 	for (i = 0; i < 8; ++i)
 		hostdata->busy[i] = 0;
 #ifdef REAL_DMA
diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index e4c243748a97..7dfd0fa27255 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -323,7 +323,6 @@ static inline int aac_valid_context(struct scsi_cmnd *scsicmd,
 	if (unlikely(!scsicmd || !scsicmd->scsi_done)) {
 		dprintk((KERN_WARNING "aac_valid_context: scsi command corrupt\n"));
 		aac_fib_complete(fibptr);
-		aac_fib_free(fibptr);
 		return 0;
 	}
 	scsicmd->SCp.phase = AAC_OWNER_MIDLEVEL;
@@ -331,7 +330,6 @@ static inline int aac_valid_context(struct scsi_cmnd *scsicmd,
 	if (unlikely(!device || !scsi_device_online(device))) {
 		dprintk((KERN_WARNING "aac_valid_context: scsi device corrupt\n"));
 		aac_fib_complete(fibptr);
-		aac_fib_free(fibptr);
 		return 0;
 	}
 	return 1;
@@ -541,7 +539,6 @@ static void get_container_name_callback(void *context, struct fib * fibptr)
 	scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 | SAM_STAT_GOOD;
 
 	aac_fib_complete(fibptr);
-	aac_fib_free(fibptr);
 	scsicmd->scsi_done(scsicmd);
 }
 
@@ -557,7 +554,8 @@ static int aac_get_container_name(struct scsi_cmnd * scsicmd)
 
 	dev = (struct aac_dev *)scsicmd->device->host->hostdata;
 
-	if (!(cmd_fibcontext = aac_fib_alloc(dev)))
+	cmd_fibcontext = aac_fib_alloc_tag(dev, scsicmd);
+	if (!cmd_fibcontext)
 		return -ENOMEM;
 
 	aac_fib_init(cmd_fibcontext);
@@ -586,7 +584,6 @@ static int aac_get_container_name(struct scsi_cmnd * scsicmd)
 
 	printk(KERN_WARNING "aac_get_container_name: aac_fib_send failed with status: %d.\n", status);
 	aac_fib_complete(cmd_fibcontext);
-	aac_fib_free(cmd_fibcontext);
 	return -1;
 }
 
@@ -1024,7 +1021,6 @@ static void get_container_serial_callback(void *context, struct fib * fibptr)
 	scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 | SAM_STAT_GOOD;
 
 	aac_fib_complete(fibptr);
-	aac_fib_free(fibptr);
 	scsicmd->scsi_done(scsicmd);
 }
 
@@ -1040,7 +1036,8 @@ static int aac_get_container_serial(struct scsi_cmnd * scsicmd)
 
 	dev = (struct aac_dev *)scsicmd->device->host->hostdata;
 
-	if (!(cmd_fibcontext = aac_fib_alloc(dev)))
+	cmd_fibcontext = aac_fib_alloc_tag(dev, scsicmd);
+	if (!cmd_fibcontext)
 		return -ENOMEM;
 
 	aac_fib_init(cmd_fibcontext);
@@ -1068,7 +1065,6 @@ static int aac_get_container_serial(struct scsi_cmnd * scsicmd)
 
 	printk(KERN_WARNING "aac_get_container_serial: aac_fib_send failed with status: %d.\n", status);
 	aac_fib_complete(cmd_fibcontext);
-	aac_fib_free(cmd_fibcontext);
 	return -1;
 }
 
@@ -1869,7 +1865,6 @@ static void io_callback(void *context, struct fib * fibptr)
 		break;
 	}
 	aac_fib_complete(fibptr);
-	aac_fib_free(fibptr);
 
 	scsicmd->scsi_done(scsicmd);
 }
@@ -1954,7 +1949,8 @@ static int aac_read(struct scsi_cmnd * scsicmd)
 	/*
 	 *	Alocate and initialize a Fib
 	 */
-	if (!(cmd_fibcontext = aac_fib_alloc(dev))) {
+	cmd_fibcontext = aac_fib_alloc_tag(dev, scsicmd);
+	if (!cmd_fibcontext) {
 		printk(KERN_WARNING "aac_read: fib allocation failed\n");
 		return -1;
 	}
@@ -2051,7 +2047,8 @@ static int aac_write(struct scsi_cmnd * scsicmd)
 	/*
 	 *	Allocate and initialize a Fib then setup a BlockWrite command
 	 */
-	if (!(cmd_fibcontext = aac_fib_alloc(dev))) {
+	cmd_fibcontext = aac_fib_alloc_tag(dev, scsicmd);
+	if (!cmd_fibcontext) {
 		/* FIB temporarily unavailable,not catastrophic failure */
 
 		/* scsicmd->result = DID_ERROR << 16;
@@ -2285,7 +2282,7 @@ static int aac_start_stop(struct scsi_cmnd *scsicmd)
 	/*
 	 *	Allocate and initialize a Fib
 	 */
-	cmd_fibcontext = aac_fib_alloc(aac);
+	cmd_fibcontext = aac_fib_alloc_tag(aac, scsicmd);
 	if (!cmd_fibcontext)
 		return SCSI_MLQUEUE_HOST_BUSY;
 
@@ -3157,7 +3154,6 @@ static void aac_srb_callback(void *context, struct fib * fibptr)
 	scsicmd->result |= le32_to_cpu(srbreply->scsi_status);
 
 	aac_fib_complete(fibptr);
-	aac_fib_free(fibptr);
 	scsicmd->scsi_done(scsicmd);
 }
 
@@ -3187,9 +3183,10 @@ static int aac_send_srb_fib(struct scsi_cmnd* scsicmd)
 	/*
 	 *	Allocate and initialize a Fib then setup a BlockWrite command
 	 */
-	if (!(cmd_fibcontext = aac_fib_alloc(dev))) {
+	cmd_fibcontext = aac_fib_alloc_tag(dev, scsicmd);
+	if (!cmd_fibcontext)
 		return -1;
-	}
+
 	status = aac_adapter_scsi(cmd_fibcontext, scsicmd);
 
 	/*
diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h
index 074878b55a0b..efa493cf1bc6 100644
--- a/drivers/scsi/aacraid/aacraid.h
+++ b/drivers/scsi/aacraid/aacraid.h
@@ -62,7 +62,7 @@ enum {
 #define	PMC_GLOBAL_INT_BIT0		0x00000001
 
 #ifndef AAC_DRIVER_BUILD
-# define AAC_DRIVER_BUILD 41010
+# define AAC_DRIVER_BUILD 41052
 # define AAC_DRIVER_BRANCH "-ms"
 #endif
 #define MAXIMUM_NUM_CONTAINERS	32
@@ -94,6 +94,13 @@ enum {
 #define aac_phys_to_logical(x)  ((x)+1)
 #define aac_logical_to_phys(x)  ((x)?(x)-1:0)
 
+/*
+ * These macros are for keeping track of
+ * character device state.
+ */
+#define AAC_CHARDEV_UNREGISTERED	(-1)
+#define AAC_CHARDEV_NEEDS_REINIT	(-2)
+
 /* #define AAC_DETAILED_STATUS_INFO */
 
 struct diskparm
@@ -944,6 +951,7 @@ struct fib {
 	 */
 	struct list_head	fiblink;
 	void			*data;
+	u32			vector_no;
 	struct hw_fib		*hw_fib_va;		/* Actual shared object */
 	dma_addr_t		hw_fib_pa;		/* physical address of hw_fib*/
 };
@@ -1123,6 +1131,7 @@ struct aac_dev
 	struct fib		*free_fib;
 	spinlock_t		fib_lock;
 
+	struct mutex		ioctl_mutex;
 	struct aac_queue_block *queues;
 	/*
 	 *	The user API will use an IOCTL to register itself to receive
@@ -1234,6 +1243,7 @@ struct aac_dev
 	struct msix_entry	msixentry[AAC_MAX_MSIX];
 	struct aac_msix_ctx	aac_msix[AAC_MAX_MSIX]; /* context */
 	u8			adapter_shutdown;
+	u32			handle_pci_error;
 };
 
 #define aac_adapter_interrupt(dev) \
@@ -2113,7 +2123,9 @@ static inline unsigned int cap_to_cyls(sector_t capacity, unsigned divisor)
 int aac_acquire_irq(struct aac_dev *dev);
 void aac_free_irq(struct aac_dev *dev);
 const char *aac_driverinfo(struct Scsi_Host *);
+void aac_fib_vector_assign(struct aac_dev *dev);
 struct fib *aac_fib_alloc(struct aac_dev *dev);
+struct fib *aac_fib_alloc_tag(struct aac_dev *dev, struct scsi_cmnd *scmd);
 int aac_fib_setup(struct aac_dev *dev);
 void aac_fib_map_free(struct aac_dev *dev);
 void aac_fib_free(struct fib * context);
diff --git a/drivers/scsi/aacraid/commctrl.c b/drivers/scsi/aacraid/commctrl.c
index 54195a117f72..4b3bb52b5108 100644
--- a/drivers/scsi/aacraid/commctrl.c
+++ b/drivers/scsi/aacraid/commctrl.c
@@ -855,13 +855,20 @@ int aac_do_ioctl(struct aac_dev * dev, int cmd, void __user *arg)
 {
 	int status;
 
+	mutex_lock(&dev->ioctl_mutex);
+
+	if (dev->adapter_shutdown) {
+		status = -EACCES;
+		goto cleanup;
+	}
+
 	/*
 	 *	HBA gets first crack
 	 */
 
 	status = aac_dev_ioctl(dev, cmd, arg);
 	if (status != -ENOTTY)
-		return status;
+		goto cleanup;
 
 	switch (cmd) {
 	case FSACTL_MINIPORT_REV_CHECK:
@@ -890,6 +897,10 @@ int aac_do_ioctl(struct aac_dev * dev, int cmd, void __user *arg)
 		status = -ENOTTY;
 		break;
 	}
+
+cleanup:
+	mutex_unlock(&dev->ioctl_mutex);
+
 	return status;
 }
 
diff --git a/drivers/scsi/aacraid/comminit.c b/drivers/scsi/aacraid/comminit.c
index 0e954e37f0b5..2b4e75380ae6 100644
--- a/drivers/scsi/aacraid/comminit.c
+++ b/drivers/scsi/aacraid/comminit.c
@@ -212,8 +212,11 @@ int aac_send_shutdown(struct aac_dev * dev)
 		return -ENOMEM;
 	aac_fib_init(fibctx);
 
-	cmd = (struct aac_close *) fib_data(fibctx);
+	mutex_lock(&dev->ioctl_mutex);
+	dev->adapter_shutdown = 1;
+	mutex_unlock(&dev->ioctl_mutex);
 
+	cmd = (struct aac_close *) fib_data(fibctx);
 	cmd->command = cpu_to_le32(VM_CloseAll);
 	cmd->cid = cpu_to_le32(0xfffffffe);
 
@@ -229,7 +232,6 @@ int aac_send_shutdown(struct aac_dev * dev)
 	/* FIB should be freed only after getting the response from the F/W */
 	if (status != -ERESTARTSYS)
 		aac_fib_free(fibctx);
-	dev->adapter_shutdown = 1;
 	if ((dev->pdev->device == PMC_DEVICE_S7 ||
 	     dev->pdev->device == PMC_DEVICE_S8 ||
 	     dev->pdev->device == PMC_DEVICE_S9) &&
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index a1f90fe849c9..511bbc575062 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -83,13 +83,38 @@ static int fib_map_alloc(struct aac_dev *dev)
 
 void aac_fib_map_free(struct aac_dev *dev)
 {
-	pci_free_consistent(dev->pdev,
-	  dev->max_fib_size * (dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB),
-	  dev->hw_fib_va, dev->hw_fib_pa);
+	if (dev->hw_fib_va && dev->max_fib_size) {
+		pci_free_consistent(dev->pdev,
+		(dev->max_fib_size *
+		(dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB)),
+		dev->hw_fib_va, dev->hw_fib_pa);
+	}
 	dev->hw_fib_va = NULL;
 	dev->hw_fib_pa = 0;
 }
 
+void aac_fib_vector_assign(struct aac_dev *dev)
+{
+	u32 i = 0;
+	u32 vector = 1;
+	struct fib *fibptr = NULL;
+
+	for (i = 0, fibptr = &dev->fibs[i];
+		i < (dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB);
+		i++, fibptr++) {
+		if ((dev->max_msix == 1) ||
+		  (i > ((dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB - 1)
+			- dev->vector_cap))) {
+			fibptr->vector_no = 0;
+		} else {
+			fibptr->vector_no = vector;
+			vector++;
+			if (vector == dev->max_msix)
+				vector = 1;
+		}
+	}
+}
+
 /**
  *	aac_fib_setup	-	setup the fibs
  *	@dev: Adapter to set up
@@ -137,6 +162,7 @@ int aac_fib_setup(struct aac_dev * dev)
 		i++, fibptr++)
 	{
 		fibptr->flags = 0;
+		fibptr->size = sizeof(struct fib);
 		fibptr->dev = dev;
 		fibptr->hw_fib_va = hw_fib;
 		fibptr->data = (void *) fibptr->hw_fib_va->data;
@@ -151,18 +177,49 @@ int aac_fib_setup(struct aac_dev * dev)
 		hw_fib_pa = hw_fib_pa +
 			dev->max_fib_size + sizeof(struct aac_fib_xporthdr);
 	}
+
+	/*
+	 *Assign vector numbers to fibs
+	 */
+	aac_fib_vector_assign(dev);
+
 	/*
 	 *	Add the fib chain to the free list
 	 */
 	dev->fibs[dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB - 1].next = NULL;
 	/*
-	 *	Enable this to debug out of queue space
-	 */
-	dev->free_fib = &dev->fibs[0];
+	*	Set 8 fibs aside for management tools
+	*/
+	dev->free_fib = &dev->fibs[dev->scsi_host_ptr->can_queue];
 	return 0;
 }
 
 /**
+ *	aac_fib_alloc_tag-allocate a fib using tags
+ *	@dev: Adapter to allocate the fib for
+ *
+ *	Allocate a fib from the adapter fib pool using tags
+ *	from the blk layer.
+ */
+
+struct fib *aac_fib_alloc_tag(struct aac_dev *dev, struct scsi_cmnd *scmd)
+{
+	struct fib *fibptr;
+
+	fibptr = &dev->fibs[scmd->request->tag];
+	/*
+	 *	Null out fields that depend on being zero at the start of
+	 *	each I/O
+	 */
+	fibptr->hw_fib_va->header.XferState = 0;
+	fibptr->type = FSAFS_NTC_FIB_CONTEXT;
+	fibptr->callback_data = NULL;
+	fibptr->callback = NULL;
+
+	return fibptr;
+}
+
+/**
  *	aac_fib_alloc	-	allocate a fib
  *	@dev: Adapter to allocate the fib for
  *
diff --git a/drivers/scsi/aacraid/dpcsup.c b/drivers/scsi/aacraid/dpcsup.c
index da9d9936e995..d677b52860ae 100644
--- a/drivers/scsi/aacraid/dpcsup.c
+++ b/drivers/scsi/aacraid/dpcsup.c
@@ -394,7 +394,6 @@ unsigned int aac_intr_normal(struct aac_dev *dev, u32 index,
 				fib->callback(fib->callback_data, fib);
 			} else {
 				aac_fib_complete(fib);
-				aac_fib_free(fib);
 			}
 		} else {
 			unsigned long flagv;
@@ -416,7 +415,6 @@ unsigned int aac_intr_normal(struct aac_dev *dev, u32 index,
 				fib->done = 0;
 				spin_unlock_irqrestore(&fib->event_lock, flagv);
 				aac_fib_complete(fib);
-				aac_fib_free(fib);
 			}
 
 		}
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 76eaa38ffd6e..21a67ed047e8 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -38,6 +38,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/pci.h>
+#include <linux/aer.h>
 #include <linux/pci-aspm.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
@@ -79,7 +80,7 @@ MODULE_VERSION(AAC_DRIVER_FULL_VERSION);
 
 static DEFINE_MUTEX(aac_mutex);
 static LIST_HEAD(aac_devices);
-static int aac_cfg_major = -1;
+static int aac_cfg_major = AAC_CHARDEV_UNREGISTERED;
 char aac_driver_version[] = AAC_DRIVER_FULL_VERSION;
 
 /*
@@ -454,6 +455,8 @@ static int aac_slave_configure(struct scsi_device *sdev)
 	} else
 		scsi_change_queue_depth(sdev, 1);
 
+		sdev->tagged_supported = 1;
+
 	return 0;
 }
 
@@ -700,23 +703,18 @@ static int aac_cfg_open(struct inode *inode, struct file *file)
 static long aac_cfg_ioctl(struct file *file,
 		unsigned int cmd, unsigned long arg)
 {
-	int ret;
-	struct aac_dev *aac;
-	aac = (struct aac_dev *)file->private_data;
-	if (!capable(CAP_SYS_RAWIO) || aac->adapter_shutdown)
+	struct aac_dev *aac = (struct aac_dev *)file->private_data;
+
+	if (!capable(CAP_SYS_RAWIO))
 		return -EPERM;
-	mutex_lock(&aac_mutex);
-	ret = aac_do_ioctl(file->private_data, cmd, (void __user *)arg);
-	mutex_unlock(&aac_mutex);
 
-	return ret;
+	return aac_do_ioctl(aac, cmd, (void __user *)arg);
 }
 
 #ifdef CONFIG_COMPAT
 static long aac_compat_do_ioctl(struct aac_dev *dev, unsigned cmd, unsigned long arg)
 {
 	long ret;
-	mutex_lock(&aac_mutex);
 	switch (cmd) {
 	case FSACTL_MINIPORT_REV_CHECK:
 	case FSACTL_SENDFIB:
@@ -750,7 +748,6 @@ static long aac_compat_do_ioctl(struct aac_dev *dev, unsigned cmd, unsigned long
 		ret = -ENOIOCTLCMD;
 		break;
 	}
-	mutex_unlock(&aac_mutex);
 	return ret;
 }
 
@@ -1075,6 +1072,8 @@ static void __aac_shutdown(struct aac_dev * aac)
 	int i;
 	int cpu;
 
+	aac_send_shutdown(aac);
+
 	if (aac->aif_thread) {
 		int i;
 		/* Clear out events first */
@@ -1086,7 +1085,6 @@ static void __aac_shutdown(struct aac_dev * aac)
 		}
 		kthread_stop(aac->thread);
 	}
-	aac_send_shutdown(aac);
 	aac_adapter_disable_int(aac);
 	cpu = cpumask_first(cpu_online_mask);
 	if (aac->pdev->device == PMC_DEVICE_S6 ||
@@ -1120,6 +1118,13 @@ static void __aac_shutdown(struct aac_dev * aac)
 	else if (aac->max_msix > 1)
 		pci_disable_msix(aac->pdev);
 }
+static void aac_init_char(void)
+{
+	aac_cfg_major = register_chrdev(0, "aac", &aac_cfg_fops);
+	if (aac_cfg_major < 0) {
+		pr_err("aacraid: unable to register \"aac\" device.\n");
+	}
+}
 
 static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 {
@@ -1132,6 +1137,12 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	u64 dmamask;
 	extern int aac_sync_mode;
 
+	/*
+	 * Only series 7 needs freset.
+	 */
+	 if (pdev->device == PMC_DEVICE_S7)
+		pdev->needs_freset = 1;
+
 	list_for_each_entry(aac, &aac_devices, entry) {
 		if (aac->id > unique_id)
 			break;
@@ -1171,6 +1182,9 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	shost->max_cmd_len = 16;
 	shost->use_cmd_list = 1;
 
+	if (aac_cfg_major == AAC_CHARDEV_NEEDS_REINIT)
+		aac_init_char();
+
 	aac = (struct aac_dev *)shost->hostdata;
 	aac->base_start = pci_resource_start(pdev, 0);
 	aac->scsi_host_ptr = shost;
@@ -1185,6 +1199,7 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto out_free_host;
 	spin_lock_init(&aac->fib_lock);
 
+	mutex_init(&aac->ioctl_mutex);
 	/*
 	 *	Map in the registers from the adapter.
 	 */
@@ -1296,6 +1311,9 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto out_deinit;
 	scsi_scan_host(shost);
 
+	pci_enable_pcie_error_reporting(pdev);
+	pci_save_state(pdev);
+
 	return 0;
 
  out_deinit:
@@ -1317,7 +1335,6 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	return error;
 }
 
-#if (defined(CONFIG_PM))
 static void aac_release_resources(struct aac_dev *aac)
 {
 	int i;
@@ -1404,14 +1421,26 @@ static int aac_acquire_resources(struct aac_dev *dev)
 
 	aac_adapter_enable_int(dev);
 
-	if (!dev->sync_mode)
+	/*max msix may change  after EEH
+	 * Re-assign vectors to fibs
+	 */
+	aac_fib_vector_assign(dev);
+
+	if (!dev->sync_mode) {
+		/* After EEH recovery or suspend resume, max_msix count
+		 * may change, therfore updating in init as well.
+		 */
 		aac_adapter_start(dev);
+		dev->init->Sa_MSIXVectors = cpu_to_le32(dev->max_msix);
+	}
 	return 0;
 
 error_iounmap:
 	return -1;
 
 }
+
+#if (defined(CONFIG_PM))
 static int aac_suspend(struct pci_dev *pdev, pm_message_t state)
 {
 
@@ -1495,10 +1524,142 @@ static void aac_remove_one(struct pci_dev *pdev)
 	pci_disable_device(pdev);
 	if (list_empty(&aac_devices)) {
 		unregister_chrdev(aac_cfg_major, "aac");
-		aac_cfg_major = -1;
+		aac_cfg_major = AAC_CHARDEV_NEEDS_REINIT;
+	}
+}
+
+static void aac_flush_ios(struct aac_dev *aac)
+{
+	int i;
+	struct scsi_cmnd *cmd;
+
+	for (i = 0; i < aac->scsi_host_ptr->can_queue; i++) {
+		cmd = (struct scsi_cmnd *)aac->fibs[i].callback_data;
+		if (cmd && (cmd->SCp.phase == AAC_OWNER_FIRMWARE)) {
+			scsi_dma_unmap(cmd);
+
+			if (aac->handle_pci_error)
+				cmd->result = DID_NO_CONNECT << 16;
+			else
+				cmd->result = DID_RESET << 16;
+
+			cmd->scsi_done(cmd);
+		}
+	}
+}
+
+static pci_ers_result_t aac_pci_error_detected(struct pci_dev *pdev,
+					enum pci_channel_state error)
+{
+	struct Scsi_Host *shost = pci_get_drvdata(pdev);
+	struct aac_dev *aac = shost_priv(shost);
+
+	dev_err(&pdev->dev, "aacraid: PCI error detected %x\n", error);
+
+	switch (error) {
+	case pci_channel_io_normal:
+		return PCI_ERS_RESULT_CAN_RECOVER;
+	case pci_channel_io_frozen:
+		aac->handle_pci_error = 1;
+
+		scsi_block_requests(aac->scsi_host_ptr);
+		aac_flush_ios(aac);
+		aac_release_resources(aac);
+
+		pci_disable_pcie_error_reporting(pdev);
+		aac_adapter_ioremap(aac, 0);
+
+		return PCI_ERS_RESULT_NEED_RESET;
+	case pci_channel_io_perm_failure:
+		aac->handle_pci_error = 1;
+
+		aac_flush_ios(aac);
+		return PCI_ERS_RESULT_DISCONNECT;
 	}
+
+	return PCI_ERS_RESULT_NEED_RESET;
+}
+
+static pci_ers_result_t aac_pci_mmio_enabled(struct pci_dev *pdev)
+{
+	dev_err(&pdev->dev, "aacraid: PCI error - mmio enabled\n");
+	return PCI_ERS_RESULT_NEED_RESET;
 }
 
+static pci_ers_result_t aac_pci_slot_reset(struct pci_dev *pdev)
+{
+	dev_err(&pdev->dev, "aacraid: PCI error - slot reset\n");
+	pci_restore_state(pdev);
+	if (pci_enable_device(pdev)) {
+		dev_warn(&pdev->dev,
+			"aacraid: failed to enable slave\n");
+		goto fail_device;
+	}
+
+	pci_set_master(pdev);
+
+	if (pci_enable_device_mem(pdev)) {
+		dev_err(&pdev->dev, "pci_enable_device_mem failed\n");
+		goto fail_device;
+	}
+
+	return PCI_ERS_RESULT_RECOVERED;
+
+fail_device:
+	dev_err(&pdev->dev, "aacraid: PCI error - slot reset failed\n");
+	return PCI_ERS_RESULT_DISCONNECT;
+}
+
+
+static void aac_pci_resume(struct pci_dev *pdev)
+{
+	struct Scsi_Host *shost = pci_get_drvdata(pdev);
+	struct scsi_device *sdev = NULL;
+	struct aac_dev *aac = (struct aac_dev *)shost_priv(shost);
+
+	pci_cleanup_aer_uncorrect_error_status(pdev);
+
+	if (aac_adapter_ioremap(aac, aac->base_size)) {
+
+		dev_err(&pdev->dev, "aacraid: ioremap failed\n");
+		/* remap failed, go back ... */
+		aac->comm_interface = AAC_COMM_PRODUCER;
+		if (aac_adapter_ioremap(aac, AAC_MIN_FOOTPRINT_SIZE)) {
+			dev_warn(&pdev->dev,
+				"aacraid: unable to map adapter.\n");
+
+			return;
+		}
+	}
+
+	msleep(10000);
+
+	aac_acquire_resources(aac);
+
+	/*
+	 * reset this flag to unblock ioctl() as it was set
+	 * at aac_send_shutdown() to block ioctls from upperlayer
+	 */
+	aac->adapter_shutdown = 0;
+	aac->handle_pci_error = 0;
+
+	shost_for_each_device(sdev, shost)
+		if (sdev->sdev_state == SDEV_OFFLINE)
+			sdev->sdev_state = SDEV_RUNNING;
+	scsi_unblock_requests(aac->scsi_host_ptr);
+	scsi_scan_host(aac->scsi_host_ptr);
+	pci_save_state(pdev);
+
+	dev_err(&pdev->dev, "aacraid: PCI error - resume\n");
+}
+
+static struct pci_error_handlers aac_pci_err_handler = {
+	.error_detected		= aac_pci_error_detected,
+	.mmio_enabled		= aac_pci_mmio_enabled,
+	.slot_reset		= aac_pci_slot_reset,
+	.resume			= aac_pci_resume,
+};
+
 static struct pci_driver aac_pci_driver = {
 	.name		= AAC_DRIVERNAME,
 	.id_table	= aac_pci_tbl,
@@ -1509,6 +1670,7 @@ static struct pci_driver aac_pci_driver = {
 	.resume		= aac_resume,
 #endif
 	.shutdown	= aac_shutdown,
+	.err_handler    = &aac_pci_err_handler,
 };
 
 static int __init aac_init(void)
@@ -1522,11 +1684,8 @@ static int __init aac_init(void)
 	if (error < 0)
 		return error;
 
-	aac_cfg_major = register_chrdev( 0, "aac", &aac_cfg_fops);
-	if (aac_cfg_major < 0) {
-		printk(KERN_WARNING
-			"aacraid: unable to register \"aac\" device.\n");
-	}
+	aac_init_char();
+
 
 	return 0;
 }
diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c
index 2aa34ea8ceb1..bc0203f3d243 100644
--- a/drivers/scsi/aacraid/src.c
+++ b/drivers/scsi/aacraid/src.c
@@ -156,8 +156,8 @@ static irqreturn_t aac_src_intr_message(int irq, void *dev_id)
 				break;
 			if (dev->msi_enabled && dev->max_msix > 1)
 				atomic_dec(&dev->rrq_outstanding[vector_no]);
-			aac_intr_normal(dev, handle-1, 0, isFastResponse, NULL);
 			dev->host_rrq[index++] = 0;
+			aac_intr_normal(dev, handle-1, 0, isFastResponse, NULL);
 			if (index == (vector_no + 1) * dev->vector_cap)
 				index = vector_no * dev->vector_cap;
 			dev->host_rrq_idx[vector_no] = index;
@@ -452,36 +452,20 @@ static int aac_src_deliver_message(struct fib *fib)
 #endif
 
 	u16 hdr_size = le16_to_cpu(fib->hw_fib_va->header.Size);
+	u16 vector_no;
 
 	atomic_inc(&q->numpending);
 
 	if (dev->msi_enabled && fib->hw_fib_va->header.Command != AifRequest &&
 	    dev->max_msix > 1) {
-		u_int16_t vector_no, first_choice = 0xffff;
-
-		vector_no = dev->fibs_pushed_no % dev->max_msix;
-		do {
-			vector_no += 1;
-			if (vector_no == dev->max_msix)
-				vector_no = 1;
-			if (atomic_read(&dev->rrq_outstanding[vector_no]) <
-			    dev->vector_cap)
-				break;
-			if (0xffff == first_choice)
-				first_choice = vector_no;
-			else if (vector_no == first_choice)
-				break;
-		} while (1);
-		if (vector_no == first_choice)
-			vector_no = 0;
-		atomic_inc(&dev->rrq_outstanding[vector_no]);
-		if (dev->fibs_pushed_no == 0xffffffff)
-			dev->fibs_pushed_no = 0;
-		else
-			dev->fibs_pushed_no++;
+		vector_no = fib->vector_no;
 		fib->hw_fib_va->header.Handle += (vector_no << 16);
+	} else {
+		vector_no = 0;
 	}
 
+	atomic_inc(&dev->rrq_outstanding[vector_no]);
+
 	if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE2) {
 		/* Calculate the amount to the fibsize bits */
 		fibsize = (hdr_size + 127) / 128 - 1;
diff --git a/drivers/scsi/aha1542.c b/drivers/scsi/aha1542.c
index 5b8b2937a3fe..7db448ec8beb 100644
--- a/drivers/scsi/aha1542.c
+++ b/drivers/scsi/aha1542.c
@@ -403,6 +403,9 @@ static int aha1542_queuecommand(struct Scsi_Host *sh, struct scsi_cmnd *cmd)
 		cptr = kmalloc(sizeof(*cptr) * sg_count, GFP_KERNEL | GFP_DMA);
 		if (!cptr)
 			return SCSI_MLQUEUE_HOST_BUSY;
+	} else {
+		sg_count = 0;
+		cptr = NULL;
 	}
 
 	/* Use the outgoing mailboxes in a round-robin fashion, because this
diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c
index b846a4683562..fc6a83188c1e 100644
--- a/drivers/scsi/aic7xxx/aic7xxx_osm.c
+++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c
@@ -1336,6 +1336,7 @@ ahc_platform_set_tags(struct ahc_softc *ahc, struct scsi_device *sdev,
 	case AHC_DEV_Q_TAGGED:
 		scsi_change_queue_depth(sdev,
 				dev->openings + dev->active);
+		break;
 	default:
 		/*
 		 * We allow the OS to queue 2 untagged transactions to
diff --git a/drivers/scsi/arm/acornscsi.c b/drivers/scsi/arm/acornscsi.c
index deaaf84989cd..12b88294d667 100644
--- a/drivers/scsi/arm/acornscsi.c
+++ b/drivers/scsi/arm/acornscsi.c
@@ -677,7 +677,8 @@ int round_period(unsigned int period)
  * Copyright: Copyright (c) 1996 John Shifflett, GeoLog Consulting
  */
 static
-unsigned char calc_sync_xfer(unsigned int period, unsigned int offset)
+unsigned char __maybe_unused calc_sync_xfer(unsigned int period,
+					    unsigned int offset)
 {
     return sync_xfer_table[round_period(period)].reg_value |
 		((offset < SDTR_SIZE) ? offset : SDTR_SIZE);
diff --git a/drivers/scsi/arm/fas216.c b/drivers/scsi/arm/fas216.c
index decdc71b6b86..24388795ee9a 100644
--- a/drivers/scsi/arm/fas216.c
+++ b/drivers/scsi/arm/fas216.c
@@ -98,6 +98,7 @@ static int level_mask = LOG_ERROR;
 
 module_param(level_mask, int, 0644);
 
+#ifndef MODULE
 static int __init fas216_log_setup(char *str)
 {
 	char *s;
@@ -138,6 +139,7 @@ static int __init fas216_log_setup(char *str)
 }
 
 __setup("fas216_logging=", fas216_log_setup);
+#endif
 
 static inline unsigned char fas216_readb(FAS216_Info *info, unsigned int reg)
 {
diff --git a/drivers/scsi/atari_NCR5380.c b/drivers/scsi/atari_NCR5380.c
index e65478651ca9..389825ba5d96 100644
--- a/drivers/scsi/atari_NCR5380.c
+++ b/drivers/scsi/atari_NCR5380.c
@@ -862,7 +862,7 @@ static struct scsi_cmnd *dequeue_next_cmd(struct Scsi_Host *instance)
 	struct NCR5380_cmd *ncmd;
 	struct scsi_cmnd *cmd;
 
-	if (list_empty(&hostdata->autosense)) {
+	if (hostdata->sensing || list_empty(&hostdata->autosense)) {
 		list_for_each_entry(ncmd, &hostdata->unissued, list) {
 			cmd = NCR5380_to_scmd(ncmd);
 			dsprintk(NDEBUG_QUEUES, instance, "dequeue: cmd=%p target=%d busy=0x%02x lun=%llu\n",
@@ -901,7 +901,7 @@ static void requeue_cmd(struct Scsi_Host *instance, struct scsi_cmnd *cmd)
 	struct NCR5380_hostdata *hostdata = shost_priv(instance);
 	struct NCR5380_cmd *ncmd = scsi_cmd_priv(cmd);
 
-	if (hostdata->sensing) {
+	if (hostdata->sensing == cmd) {
 		scsi_eh_restore_cmnd(cmd, &hostdata->ses);
 		list_add(&ncmd->list, &hostdata->autosense);
 		hostdata->sensing = NULL;
@@ -923,7 +923,6 @@ static void NCR5380_main(struct work_struct *work)
 	struct NCR5380_hostdata *hostdata =
 		container_of(work, struct NCR5380_hostdata, main_task);
 	struct Scsi_Host *instance = hostdata->host;
-	struct scsi_cmnd *cmd;
 	int done;
 
 	/*
@@ -936,8 +935,11 @@ static void NCR5380_main(struct work_struct *work)
 		done = 1;
 
 		spin_lock_irq(&hostdata->lock);
-		while (!hostdata->connected &&
-		       (cmd = dequeue_next_cmd(instance))) {
+		while (!hostdata->connected && !hostdata->selecting) {
+			struct scsi_cmnd *cmd = dequeue_next_cmd(instance);
+
+			if (!cmd)
+				break;
 
 			dsprintk(NDEBUG_MAIN, instance, "main: dequeued %p\n", cmd);
 
@@ -960,8 +962,7 @@ static void NCR5380_main(struct work_struct *work)
 #ifdef SUPPORT_TAGS
 			cmd_get_tag(cmd, cmd->cmnd[0] != REQUEST_SENSE);
 #endif
-			cmd = NCR5380_select(instance, cmd);
-			if (!cmd) {
+			if (!NCR5380_select(instance, cmd)) {
 				dsprintk(NDEBUG_MAIN, instance, "main: select complete\n");
 				maybe_release_dma_irq(instance);
 			} else {
@@ -1257,6 +1258,11 @@ static struct scsi_cmnd *NCR5380_select(struct Scsi_Host *instance,
 		/* Reselection interrupt */
 		goto out;
 	}
+	if (!hostdata->selecting) {
+		/* Command was aborted */
+		NCR5380_write(MODE_REG, MR_BASE);
+		goto out;
+	}
 	if (err < 0) {
 		NCR5380_write(MODE_REG, MR_BASE);
 		shost_printk(KERN_ERR, instance,
@@ -1838,9 +1844,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 	unsigned char msgout = NOP;
 	int sink = 0;
 	int len;
-#if defined(REAL_DMA)
 	int transfersize;
-#endif
 	unsigned char *data;
 	unsigned char phase, tmp, extended_msg[10], old_phase = 0xff;
 	struct scsi_cmnd *cmd;
@@ -1909,6 +1913,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 				do_abort(instance);
 				cmd->result = DID_ERROR << 16;
 				complete_cmd(instance, cmd);
+				hostdata->connected = NULL;
 				return;
 #endif
 			case PHASE_DATAIN:
@@ -1966,7 +1971,6 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 						sink = 1;
 						do_abort(instance);
 						cmd->result = DID_ERROR << 16;
-						complete_cmd(instance, cmd);
 						/* XXX - need to source or sink data here, as appropriate */
 					} else {
 #ifdef REAL_DMA
@@ -1983,18 +1987,22 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 				} else
 #endif /* defined(REAL_DMA) */
 				{
-					spin_unlock_irq(&hostdata->lock);
-					NCR5380_transfer_pio(instance, &phase,
-					                     (int *)&cmd->SCp.this_residual,
+					/* Break up transfer into 3 ms chunks,
+					 * presuming 6 accesses per handshake.
+					 */
+					transfersize = min((unsigned long)cmd->SCp.this_residual,
+					                   hostdata->accesses_per_ms / 2);
+					len = transfersize;
+					NCR5380_transfer_pio(instance, &phase, &len,
 					                     (unsigned char **)&cmd->SCp.ptr);
-					spin_lock_irq(&hostdata->lock);
+					cmd->SCp.this_residual -= transfersize - len;
 				}
 #if defined(CONFIG_SUN3) && defined(REAL_DMA)
 				/* if we had intended to dma that command clear it */
 				if (sun3_dma_setup_done == cmd)
 					sun3_dma_setup_done = NULL;
 #endif
-				break;
+				return;
 			case PHASE_MSGIN:
 				len = 1;
 				data = &tmp;
@@ -2487,14 +2495,17 @@ static bool list_del_cmd(struct list_head *haystack,
  * [disconnected -> connected ->]...
  * [autosense -> connected ->] done
  *
- * If cmd is unissued then just remove it.
- * If cmd is disconnected, try to select the target.
- * If cmd is connected, try to send an abort message.
- * If cmd is waiting for autosense, give it a chance to complete but check
- * that it isn't left connected.
  * If cmd was not found at all then presumably it has already been completed,
  * in which case return SUCCESS to try to avoid further EH measures.
+ *
  * If the command has not completed yet, we must not fail to find it.
+ * We have no option but to forget the aborted command (even if it still
+ * lacks sense data). The mid-layer may re-issue a command that is in error
+ * recovery (see scsi_send_eh_cmnd), but the logic and data structures in
+ * this driver are such that a command can appear on one queue only.
+ *
+ * The lock protects driver data structures, but EH handlers also use it
+ * to serialize their own execution and prevent their own re-entry.
  */
 
 static int NCR5380_abort(struct scsi_cmnd *cmd)
@@ -2517,6 +2528,7 @@ static int NCR5380_abort(struct scsi_cmnd *cmd)
 		         "abort: removed %p from issue queue\n", cmd);
 		cmd->result = DID_ABORT << 16;
 		cmd->scsi_done(cmd); /* No tag or busy flag to worry about */
+		goto out;
 	}
 
 	if (hostdata->selecting == cmd) {
@@ -2531,58 +2543,21 @@ static int NCR5380_abort(struct scsi_cmnd *cmd)
 	if (list_del_cmd(&hostdata->disconnected, cmd)) {
 		dsprintk(NDEBUG_ABORT, instance,
 		         "abort: removed %p from disconnected list\n", cmd);
-		cmd->result = DID_ERROR << 16;
-		if (!hostdata->connected)
-			NCR5380_select(instance, cmd);
-		if (hostdata->connected != cmd) {
-			complete_cmd(instance, cmd);
-			result = FAILED;
-			goto out;
-		}
+		/* Can't call NCR5380_select() and send ABORT because that
+		 * means releasing the lock. Need a bus reset.
+		 */
+		set_host_byte(cmd, DID_ERROR);
+		complete_cmd(instance, cmd);
+		result = FAILED;
+		goto out;
 	}
 
 	if (hostdata->connected == cmd) {
 		dsprintk(NDEBUG_ABORT, instance, "abort: cmd %p is connected\n", cmd);
 		hostdata->connected = NULL;
-		if (do_abort(instance)) {
-			set_host_byte(cmd, DID_ERROR);
-			complete_cmd(instance, cmd);
-			result = FAILED;
-			goto out;
-		}
-		set_host_byte(cmd, DID_ABORT);
 #ifdef REAL_DMA
 		hostdata->dma_len = 0;
 #endif
-		if (cmd->cmnd[0] == REQUEST_SENSE)
-			complete_cmd(instance, cmd);
-		else {
-			struct NCR5380_cmd *ncmd = scsi_cmd_priv(cmd);
-
-			/* Perform autosense for this command */
-			list_add(&ncmd->list, &hostdata->autosense);
-		}
-	}
-
-	if (list_find_cmd(&hostdata->autosense, cmd)) {
-		dsprintk(NDEBUG_ABORT, instance,
-		         "abort: found %p on sense queue\n", cmd);
-		spin_unlock_irqrestore(&hostdata->lock, flags);
-		queue_work(hostdata->work_q, &hostdata->main_task);
-		msleep(1000);
-		spin_lock_irqsave(&hostdata->lock, flags);
-		if (list_del_cmd(&hostdata->autosense, cmd)) {
-			dsprintk(NDEBUG_ABORT, instance,
-			         "abort: removed %p from sense queue\n", cmd);
-			set_host_byte(cmd, DID_ABORT);
-			complete_cmd(instance, cmd);
-			goto out;
-		}
-	}
-
-	if (hostdata->connected == cmd) {
-		dsprintk(NDEBUG_ABORT, instance, "abort: cmd %p is connected\n", cmd);
-		hostdata->connected = NULL;
 		if (do_abort(instance)) {
 			set_host_byte(cmd, DID_ERROR);
 			complete_cmd(instance, cmd);
@@ -2590,9 +2565,14 @@ static int NCR5380_abort(struct scsi_cmnd *cmd)
 			goto out;
 		}
 		set_host_byte(cmd, DID_ABORT);
-#ifdef REAL_DMA
-		hostdata->dma_len = 0;
-#endif
+		complete_cmd(instance, cmd);
+		goto out;
+	}
+
+	if (list_del_cmd(&hostdata->autosense, cmd)) {
+		dsprintk(NDEBUG_ABORT, instance,
+		         "abort: removed %p from sense queue\n", cmd);
+		set_host_byte(cmd, DID_ERROR);
 		complete_cmd(instance, cmd);
 	}
 
@@ -2646,7 +2626,16 @@ static int NCR5380_bus_reset(struct scsi_cmnd *cmd)
 	 * commands!
 	 */
 
-	hostdata->selecting = NULL;
+	if (list_del_cmd(&hostdata->unissued, cmd)) {
+		cmd->result = DID_RESET << 16;
+		cmd->scsi_done(cmd);
+	}
+
+	if (hostdata->selecting) {
+		hostdata->selecting->result = DID_RESET << 16;
+		complete_cmd(instance, hostdata->selecting);
+		hostdata->selecting = NULL;
+	}
 
 	list_for_each_entry(ncmd, &hostdata->disconnected, list) {
 		struct scsi_cmnd *cmd = NCR5380_to_scmd(ncmd);
@@ -2654,6 +2643,7 @@ static int NCR5380_bus_reset(struct scsi_cmnd *cmd)
 		set_host_byte(cmd, DID_RESET);
 		cmd->scsi_done(cmd);
 	}
+	INIT_LIST_HEAD(&hostdata->disconnected);
 
 	list_for_each_entry(ncmd, &hostdata->autosense, list) {
 		struct scsi_cmnd *cmd = NCR5380_to_scmd(ncmd);
@@ -2661,6 +2651,7 @@ static int NCR5380_bus_reset(struct scsi_cmnd *cmd)
 		set_host_byte(cmd, DID_RESET);
 		cmd->scsi_done(cmd);
 	}
+	INIT_LIST_HEAD(&hostdata->autosense);
 
 	if (hostdata->connected) {
 		set_host_byte(hostdata->connected, DID_RESET);
@@ -2668,12 +2659,6 @@ static int NCR5380_bus_reset(struct scsi_cmnd *cmd)
 		hostdata->connected = NULL;
 	}
 
-	if (hostdata->sensing) {
-		set_host_byte(hostdata->connected, DID_RESET);
-		complete_cmd(instance, hostdata->sensing);
-		hostdata->sensing = NULL;
-	}
-
 #ifdef SUPPORT_TAGS
 	free_all_tags(hostdata);
 #endif
diff --git a/drivers/scsi/be2iscsi/be.h b/drivers/scsi/be2iscsi/be.h
index a41c6432f444..ee5ace873535 100644
--- a/drivers/scsi/be2iscsi/be.h
+++ b/drivers/scsi/be2iscsi/be.h
@@ -42,7 +42,7 @@ struct be_queue_info {
 	u16 id;
 	u16 tail, head;
 	bool created;
-	atomic_t used;		/* Number of valid elements in the queue */
+	u16 used;		/* Number of valid elements in the queue */
 };
 
 static inline u32 MODULO(u16 val, u16 limit)
@@ -110,10 +110,9 @@ struct be_mcc_obj {
 };
 
 struct beiscsi_mcc_tag_state {
-#define MCC_TAG_STATE_COMPLETED 0x00
-#define MCC_TAG_STATE_RUNNING   0x01
-#define MCC_TAG_STATE_TIMEOUT   0x02
-	uint8_t tag_state;
+	unsigned long tag_state;
+#define MCC_TAG_STATE_RUNNING	1
+#define MCC_TAG_STATE_TIMEOUT	2
 	struct be_dma_mem tag_mem_state;
 };
 
@@ -124,7 +123,7 @@ struct be_ctrl_info {
 	struct pci_dev *pdev;
 
 	/* Mbox used for cmd request/response */
-	spinlock_t mbox_lock;	/* For serializing mbox cmds to BE card */
+	struct mutex mbox_lock;	/* For serializing mbox cmds to BE card */
 	struct be_dma_mem mbox_mem;
 	/* Mbox mem is adjusted to align to 16 bytes. The allocated addr
 	 * is stored for freeing purpose */
@@ -133,11 +132,10 @@ struct be_ctrl_info {
 	/* MCC Rings */
 	struct be_mcc_obj mcc_obj;
 	spinlock_t mcc_lock;	/* For serializing mcc cmds to BE card */
-	spinlock_t mcc_cq_lock;
 
 	wait_queue_head_t mcc_wait[MAX_MCC_CMD + 1];
 	unsigned int mcc_tag[MAX_MCC_CMD];
-	unsigned int mcc_numtag[MAX_MCC_CMD + 1];
+	unsigned int mcc_tag_status[MAX_MCC_CMD + 1];
 	unsigned short mcc_alloc_index;
 	unsigned short mcc_free_index;
 	unsigned int mcc_tag_available;
@@ -147,6 +145,12 @@ struct be_ctrl_info {
 
 #include "be_cmds.h"
 
+/* WRB index mask for MCC_Q_LEN queue entries */
+#define MCC_Q_WRB_IDX_MASK	CQE_STATUS_WRB_MASK
+#define MCC_Q_WRB_IDX_SHIFT	CQE_STATUS_WRB_SHIFT
+/* TAG is from 1...MAX_MCC_CMD, MASK includes MAX_MCC_CMD */
+#define MCC_Q_CMD_TAG_MASK	((MAX_MCC_CMD << 1) - 1)
+
 #define PAGE_SHIFT_4K 12
 #define PAGE_SIZE_4K (1 << PAGE_SHIFT_4K)
 #define mcc_timeout		120000 /* 12s timeout */
diff --git a/drivers/scsi/be2iscsi/be_cmds.c b/drivers/scsi/be2iscsi/be_cmds.c
index 2778089b01a5..a55eaeea37e7 100644
--- a/drivers/scsi/be2iscsi/be_cmds.c
+++ b/drivers/scsi/be2iscsi/be_cmds.c
@@ -104,24 +104,16 @@ int be_chk_reset_complete(struct beiscsi_hba *phba)
 	return 0;
 }
 
-void be_mcc_notify(struct beiscsi_hba *phba)
-{
-	struct be_queue_info *mccq = &phba->ctrl.mcc_obj.q;
-	u32 val = 0;
-
-	val |= mccq->id & DB_MCCQ_RING_ID_MASK;
-	val |= 1 << DB_MCCQ_NUM_POSTED_SHIFT;
-	iowrite32(val, phba->db_va + DB_MCCQ_OFFSET);
-}
-
 unsigned int alloc_mcc_tag(struct beiscsi_hba *phba)
 {
 	unsigned int tag = 0;
 
+	spin_lock(&phba->ctrl.mcc_lock);
 	if (phba->ctrl.mcc_tag_available) {
 		tag = phba->ctrl.mcc_tag[phba->ctrl.mcc_alloc_index];
 		phba->ctrl.mcc_tag[phba->ctrl.mcc_alloc_index] = 0;
-		phba->ctrl.mcc_numtag[tag] = 0;
+		phba->ctrl.mcc_tag_status[tag] = 0;
+		phba->ctrl.ptag_state[tag].tag_state = 0;
 	}
 	if (tag) {
 		phba->ctrl.mcc_tag_available--;
@@ -130,11 +122,89 @@ unsigned int alloc_mcc_tag(struct beiscsi_hba *phba)
 		else
 			phba->ctrl.mcc_alloc_index++;
 	}
+	spin_unlock(&phba->ctrl.mcc_lock);
 	return tag;
 }
 
+struct be_mcc_wrb *alloc_mcc_wrb(struct beiscsi_hba *phba,
+				 unsigned int *ref_tag)
+{
+	struct be_queue_info *mccq = &phba->ctrl.mcc_obj.q;
+	struct be_mcc_wrb *wrb = NULL;
+	unsigned int tag;
+
+	spin_lock_bh(&phba->ctrl.mcc_lock);
+	if (mccq->used == mccq->len) {
+		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT |
+			    BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
+			    "BC_%d : MCC queue full: WRB used %u tag avail %u\n",
+			    mccq->used, phba->ctrl.mcc_tag_available);
+		goto alloc_failed;
+	}
+
+	if (!phba->ctrl.mcc_tag_available)
+		goto alloc_failed;
+
+	tag = phba->ctrl.mcc_tag[phba->ctrl.mcc_alloc_index];
+	if (!tag) {
+		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT |
+			    BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
+			    "BC_%d : MCC tag 0 allocated: tag avail %u alloc index %u\n",
+			    phba->ctrl.mcc_tag_available,
+			    phba->ctrl.mcc_alloc_index);
+		goto alloc_failed;
+	}
+
+	/* return this tag for further reference */
+	*ref_tag = tag;
+	phba->ctrl.mcc_tag[phba->ctrl.mcc_alloc_index] = 0;
+	phba->ctrl.mcc_tag_status[tag] = 0;
+	phba->ctrl.ptag_state[tag].tag_state = 0;
+	phba->ctrl.mcc_tag_available--;
+	if (phba->ctrl.mcc_alloc_index == (MAX_MCC_CMD - 1))
+		phba->ctrl.mcc_alloc_index = 0;
+	else
+		phba->ctrl.mcc_alloc_index++;
+
+	wrb = queue_head_node(mccq);
+	memset(wrb, 0, sizeof(*wrb));
+	wrb->tag0 = tag;
+	wrb->tag0 |= (mccq->head << MCC_Q_WRB_IDX_SHIFT) & MCC_Q_WRB_IDX_MASK;
+	queue_head_inc(mccq);
+	mccq->used++;
+
+alloc_failed:
+	spin_unlock_bh(&phba->ctrl.mcc_lock);
+	return wrb;
+}
+
+void free_mcc_wrb(struct be_ctrl_info *ctrl, unsigned int tag)
+{
+	struct be_queue_info *mccq = &ctrl->mcc_obj.q;
+
+	spin_lock_bh(&ctrl->mcc_lock);
+	tag = tag & MCC_Q_CMD_TAG_MASK;
+	ctrl->mcc_tag[ctrl->mcc_free_index] = tag;
+	if (ctrl->mcc_free_index == (MAX_MCC_CMD - 1))
+		ctrl->mcc_free_index = 0;
+	else
+		ctrl->mcc_free_index++;
+	ctrl->mcc_tag_available++;
+	mccq->used--;
+	spin_unlock_bh(&ctrl->mcc_lock);
+}
+
+/**
+ * beiscsi_fail_session(): Closing session with appropriate error
+ * @cls_session: ptr to session
+ **/
+void beiscsi_fail_session(struct iscsi_cls_session *cls_session)
+{
+	iscsi_session_failure(cls_session->dd_data, ISCSI_ERR_CONN_FAILED);
+}
+
 /*
- * beiscsi_mccq_compl()- Wait for completion of MBX
+ * beiscsi_mccq_compl_wait()- Process completion in MCC CQ
  * @phba: Driver private structure
  * @tag: Tag for the MBX Command
  * @wrb: the WRB used for the MBX Command
@@ -146,43 +216,40 @@ unsigned int alloc_mcc_tag(struct beiscsi_hba *phba)
  * Success: 0
  * Failure: Non-Zero
  **/
-int beiscsi_mccq_compl(struct beiscsi_hba *phba,
-		uint32_t tag, struct be_mcc_wrb **wrb,
-		struct be_dma_mem *mbx_cmd_mem)
+int beiscsi_mccq_compl_wait(struct beiscsi_hba *phba,
+			    uint32_t tag, struct be_mcc_wrb **wrb,
+			    struct be_dma_mem *mbx_cmd_mem)
 {
 	int rc = 0;
-	uint32_t mcc_tag_response;
+	uint32_t mcc_tag_status;
 	uint16_t status = 0, addl_status = 0, wrb_num = 0;
 	struct be_mcc_wrb *temp_wrb;
 	struct be_cmd_req_hdr *mbx_hdr;
 	struct be_cmd_resp_hdr *mbx_resp_hdr;
 	struct be_queue_info *mccq = &phba->ctrl.mcc_obj.q;
 
-	if (beiscsi_error(phba)) {
-		free_mcc_tag(&phba->ctrl, tag);
+	if (beiscsi_error(phba))
 		return -EPERM;
-	}
-
-	/* Set MBX Tag state to Active */
-	spin_lock(&phba->ctrl.mbox_lock);
-	phba->ctrl.ptag_state[tag].tag_state = MCC_TAG_STATE_RUNNING;
-	spin_unlock(&phba->ctrl.mbox_lock);
 
 	/* wait for the mccq completion */
 	rc = wait_event_interruptible_timeout(
 				phba->ctrl.mcc_wait[tag],
-				phba->ctrl.mcc_numtag[tag],
+				phba->ctrl.mcc_tag_status[tag],
 				msecs_to_jiffies(
 				BEISCSI_HOST_MBX_TIMEOUT));
-
+	/**
+	 * If MBOX cmd timeout expired, tag and resource allocated
+	 * for cmd is not freed until FW returns completion.
+	 */
 	if (rc <= 0) {
 		struct be_dma_mem *tag_mem;
-		/* Set MBX Tag state to timeout */
-		spin_lock(&phba->ctrl.mbox_lock);
-		phba->ctrl.ptag_state[tag].tag_state = MCC_TAG_STATE_TIMEOUT;
-		spin_unlock(&phba->ctrl.mbox_lock);
 
-		/* Store resource addr to be freed later */
+		/**
+		 * PCI/DMA memory allocated and posted in non-embedded mode
+		 * will have mbx_cmd_mem != NULL.
+		 * Save virtual and bus addresses for the command so that it
+		 * can be freed later.
+		 **/
 		tag_mem = &phba->ctrl.ptag_state[tag].tag_mem_state;
 		if (mbx_cmd_mem) {
 			tag_mem->size = mbx_cmd_mem->size;
@@ -191,28 +258,28 @@ int beiscsi_mccq_compl(struct beiscsi_hba *phba,
 		} else
 			tag_mem->size = 0;
 
+		/* first make tag_mem_state visible to all */
+		wmb();
+		set_bit(MCC_TAG_STATE_TIMEOUT,
+				&phba->ctrl.ptag_state[tag].tag_state);
+
 		beiscsi_log(phba, KERN_ERR,
 			    BEISCSI_LOG_INIT | BEISCSI_LOG_EH |
 			    BEISCSI_LOG_CONFIG,
 			    "BC_%d : MBX Cmd Completion timed out\n");
 		return -EBUSY;
-	} else {
-		rc = 0;
-		/* Set MBX Tag state to completed */
-		spin_lock(&phba->ctrl.mbox_lock);
-		phba->ctrl.ptag_state[tag].tag_state = MCC_TAG_STATE_COMPLETED;
-		spin_unlock(&phba->ctrl.mbox_lock);
 	}
 
-	mcc_tag_response = phba->ctrl.mcc_numtag[tag];
-	status = (mcc_tag_response & CQE_STATUS_MASK);
-	addl_status = ((mcc_tag_response & CQE_STATUS_ADDL_MASK) >>
+	rc = 0;
+	mcc_tag_status = phba->ctrl.mcc_tag_status[tag];
+	status = (mcc_tag_status & CQE_STATUS_MASK);
+	addl_status = ((mcc_tag_status & CQE_STATUS_ADDL_MASK) >>
 			CQE_STATUS_ADDL_SHIFT);
 
 	if (mbx_cmd_mem) {
 		mbx_hdr = (struct be_cmd_req_hdr *)mbx_cmd_mem->va;
 	} else {
-		wrb_num = (mcc_tag_response & CQE_STATUS_WRB_MASK) >>
+		wrb_num = (mcc_tag_status & CQE_STATUS_WRB_MASK) >>
 			   CQE_STATUS_WRB_SHIFT;
 		temp_wrb = (struct be_mcc_wrb *)queue_get_wrb(mccq, wrb_num);
 		mbx_hdr = embedded_payload(temp_wrb);
@@ -231,7 +298,7 @@ int beiscsi_mccq_compl(struct beiscsi_hba *phba,
 			    mbx_hdr->subsystem,
 			    mbx_hdr->opcode,
 			    status, addl_status);
-
+		rc = -EIO;
 		if (status == MCC_STATUS_INSUFFICIENT_BUFFER) {
 			mbx_resp_hdr = (struct be_cmd_resp_hdr *) mbx_hdr;
 			beiscsi_log(phba, KERN_WARNING,
@@ -241,70 +308,16 @@ int beiscsi_mccq_compl(struct beiscsi_hba *phba,
 				    "Resp_Len : %d Actual_Resp_Len : %d\n",
 				    mbx_resp_hdr->response_length,
 				    mbx_resp_hdr->actual_resp_len);
-
 			rc = -EAGAIN;
-			goto release_mcc_tag;
 		}
-		rc = -EIO;
 	}
 
-release_mcc_tag:
-	/* Release the MCC entry */
-	free_mcc_tag(&phba->ctrl, tag);
-
+	free_mcc_wrb(&phba->ctrl, tag);
 	return rc;
 }
 
-void free_mcc_tag(struct be_ctrl_info *ctrl, unsigned int tag)
-{
-	spin_lock(&ctrl->mbox_lock);
-	tag = tag & 0x000000FF;
-	ctrl->mcc_tag[ctrl->mcc_free_index] = tag;
-	if (ctrl->mcc_free_index == (MAX_MCC_CMD - 1))
-		ctrl->mcc_free_index = 0;
-	else
-		ctrl->mcc_free_index++;
-	ctrl->mcc_tag_available++;
-	spin_unlock(&ctrl->mbox_lock);
-}
-
-bool is_link_state_evt(u32 trailer)
-{
-	return (((trailer >> ASYNC_TRAILER_EVENT_CODE_SHIFT) &
-		  ASYNC_TRAILER_EVENT_CODE_MASK) ==
-		  ASYNC_EVENT_CODE_LINK_STATE);
-}
-
-static bool is_iscsi_evt(u32 trailer)
-{
-	return ((trailer >> ASYNC_TRAILER_EVENT_CODE_SHIFT) &
-		  ASYNC_TRAILER_EVENT_CODE_MASK) ==
-		  ASYNC_EVENT_CODE_ISCSI;
-}
-
-static int iscsi_evt_type(u32 trailer)
-{
-	return (trailer >> ASYNC_TRAILER_EVENT_TYPE_SHIFT) &
-		 ASYNC_TRAILER_EVENT_TYPE_MASK;
-}
-
-static inline bool be_mcc_compl_is_new(struct be_mcc_compl *compl)
-{
-	if (compl->flags != 0) {
-		compl->flags = le32_to_cpu(compl->flags);
-		WARN_ON((compl->flags & CQE_FLAGS_VALID_MASK) == 0);
-		return true;
-	} else
-		return false;
-}
-
-static inline void be_mcc_compl_use(struct be_mcc_compl *compl)
-{
-	compl->flags = 0;
-}
-
 /*
- * be_mcc_compl_process()- Check the MBX comapletion status
+ * beiscsi_process_mbox_compl()- Check the MBX completion status
  * @ctrl: Function specific MBX data structure
  * @compl: Completion status of MBX Command
  *
@@ -314,8 +327,8 @@ static inline void be_mcc_compl_use(struct be_mcc_compl *compl)
  * Success: Zero
  * Failure: Non-Zero
  **/
-static int be_mcc_compl_process(struct be_ctrl_info *ctrl,
-				struct be_mcc_compl *compl)
+static int beiscsi_process_mbox_compl(struct be_ctrl_info *ctrl,
+				      struct be_mcc_compl *compl)
 {
 	u16 compl_status, extd_status;
 	struct be_mcc_wrb *wrb = wrb_from_mbox(&ctrl->mbox_mem);
@@ -323,206 +336,228 @@ static int be_mcc_compl_process(struct be_ctrl_info *ctrl,
 	struct be_cmd_req_hdr *hdr = embedded_payload(wrb);
 	struct be_cmd_resp_hdr *resp_hdr;
 
-	be_dws_le_to_cpu(compl, 4);
-
-	compl_status = (compl->status >> CQE_STATUS_COMPL_SHIFT) &
-					CQE_STATUS_COMPL_MASK;
-	if (compl_status != MCC_STATUS_SUCCESS) {
-		extd_status = (compl->status >> CQE_STATUS_EXTD_SHIFT) &
-						CQE_STATUS_EXTD_MASK;
-
+	/**
+	 * To check if valid bit is set, check the entire word as we don't know
+	 * the endianness of the data (old entry is host endian while a new
+	 * entry is little endian)
+	 */
+	if (!compl->flags) {
 		beiscsi_log(phba, KERN_ERR,
-			    BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
-			    "BC_%d : error in cmd completion: "
-			    "Subsystem : %d Opcode : %d "
-			    "status(compl/extd)=%d/%d\n",
-			    hdr->subsystem, hdr->opcode,
-			    compl_status, extd_status);
-
-		if (compl_status == MCC_STATUS_INSUFFICIENT_BUFFER) {
-			resp_hdr = (struct be_cmd_resp_hdr *) hdr;
-			if (resp_hdr->response_length)
-				return 0;
-		}
+				BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
+				"BC_%d : BMBX busy, no completion\n");
 		return -EBUSY;
 	}
-	return 0;
-}
-
-int be_mcc_compl_process_isr(struct be_ctrl_info *ctrl,
-				    struct be_mcc_compl *compl)
-{
-	struct beiscsi_hba *phba = pci_get_drvdata(ctrl->pdev);
-	u16 compl_status, extd_status;
-	unsigned short tag;
+	compl->flags = le32_to_cpu(compl->flags);
+	WARN_ON((compl->flags & CQE_FLAGS_VALID_MASK) == 0);
 
+	/**
+	 * Just swap the status to host endian;
+	 * mcc tag is opaquely copied from mcc_wrb.
+	 */
 	be_dws_le_to_cpu(compl, 4);
-
 	compl_status = (compl->status >> CQE_STATUS_COMPL_SHIFT) &
-					CQE_STATUS_COMPL_MASK;
-	/* The ctrl.mcc_numtag[tag] is filled with
-	 * [31] = valid, [30:24] = Rsvd, [23:16] = wrb, [15:8] = extd_status,
-	 * [7:0] = compl_status
-	 */
-	tag = (compl->tag0 & 0x000000FF);
+		CQE_STATUS_COMPL_MASK;
 	extd_status = (compl->status >> CQE_STATUS_EXTD_SHIFT) &
-					CQE_STATUS_EXTD_MASK;
+		CQE_STATUS_EXTD_MASK;
+	/* Need to reset the entire word that houses the valid bit */
+	compl->flags = 0;
 
-	ctrl->mcc_numtag[tag]  = 0x80000000;
-	ctrl->mcc_numtag[tag] |= (compl->tag0 & 0x00FF0000);
-	ctrl->mcc_numtag[tag] |= (extd_status & 0x000000FF) << 8;
-	ctrl->mcc_numtag[tag] |= (compl_status & 0x000000FF);
+	if (compl_status == MCC_STATUS_SUCCESS)
+		return 0;
 
-	if (ctrl->ptag_state[tag].tag_state == MCC_TAG_STATE_RUNNING) {
-		wake_up_interruptible(&ctrl->mcc_wait[tag]);
-	} else if (ctrl->ptag_state[tag].tag_state == MCC_TAG_STATE_TIMEOUT) {
-		struct be_dma_mem *tag_mem;
-		tag_mem = &ctrl->ptag_state[tag].tag_mem_state;
+	beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
+		    "BC_%d : error in cmd completion: Subsystem : %d Opcode : %d status(compl/extd)=%d/%d\n",
+		    hdr->subsystem, hdr->opcode, compl_status, extd_status);
 
-		beiscsi_log(phba, KERN_WARNING,
-			    BEISCSI_LOG_MBOX | BEISCSI_LOG_INIT |
-			    BEISCSI_LOG_CONFIG,
-			    "BC_%d : MBX Completion for timeout Command "
-			    "from FW\n");
-		/* Check if memory needs to be freed */
-		if (tag_mem->size)
-			pci_free_consistent(ctrl->pdev, tag_mem->size,
-					    tag_mem->va, tag_mem->dma);
-
-		/* Change tag state */
-		spin_lock(&phba->ctrl.mbox_lock);
-		ctrl->ptag_state[tag].tag_state = MCC_TAG_STATE_COMPLETED;
-		spin_unlock(&phba->ctrl.mbox_lock);
-
-		/* Free MCC Tag */
-		free_mcc_tag(ctrl, tag);
+	if (compl_status == MCC_STATUS_INSUFFICIENT_BUFFER) {
+		/* if status is insufficient buffer, check the length */
+		resp_hdr = (struct be_cmd_resp_hdr *) hdr;
+		if (resp_hdr->response_length)
+			return 0;
 	}
-
-	return 0;
+	return -EINVAL;
 }
 
-static struct be_mcc_compl *be_mcc_compl_get(struct beiscsi_hba *phba)
+static void beiscsi_process_async_link(struct beiscsi_hba *phba,
+				       struct be_mcc_compl *compl)
 {
-	struct be_queue_info *mcc_cq = &phba->ctrl.mcc_obj.cq;
-	struct be_mcc_compl *compl = queue_tail_node(mcc_cq);
+	struct be_async_event_link_state *evt;
+
+	evt = (struct be_async_event_link_state *)compl;
 
-	if (be_mcc_compl_is_new(compl)) {
-		queue_tail_inc(mcc_cq);
-		return compl;
+	phba->port_speed = evt->port_speed;
+	/**
+	 * Check logical link status in ASYNC event.
+	 * This has been newly introduced in SKH-R Firmware 10.0.338.45.
+	 **/
+	if (evt->port_link_status & BE_ASYNC_LINK_UP_MASK) {
+		phba->state = BE_ADAPTER_LINK_UP | BE_ADAPTER_CHECK_BOOT;
+		phba->get_boot = BE_GET_BOOT_RETRIES;
+		__beiscsi_log(phba, KERN_ERR,
+			      "BC_%d : Link Up on Port %d tag 0x%x\n",
+			      evt->physical_port, evt->event_tag);
+	} else {
+		phba->state = BE_ADAPTER_LINK_DOWN;
+		__beiscsi_log(phba, KERN_ERR,
+			      "BC_%d : Link Down on Port %d tag 0x%x\n",
+			      evt->physical_port, evt->event_tag);
+		iscsi_host_for_each_session(phba->shost,
+					    beiscsi_fail_session);
 	}
-	return NULL;
 }
 
-/**
- * be2iscsi_fail_session(): Closing session with appropriate error
- * @cls_session: ptr to session
- *
- * Depending on adapter state appropriate error flag is passed.
- **/
-void be2iscsi_fail_session(struct iscsi_cls_session *cls_session)
+static char *beiscsi_port_misconf_event_msg[] = {
+	"Physical Link is functional.",
+	"Optics faulted/incorrectly installed/not installed - Reseat optics, if issue not resolved, replace.",
+	"Optics of two types installed - Remove one optic or install matching pair of optics.",
+	"Incompatible optics - Replace with compatible optics for card to function.",
+	"Unqualified optics - Replace with Avago optics for Warranty and Technical Support.",
+	"Uncertified optics - Replace with Avago Certified optics to enable link operation."
+};
+
+static void beiscsi_process_async_sli(struct beiscsi_hba *phba,
+				      struct be_mcc_compl *compl)
 {
-	struct Scsi_Host *shost = iscsi_session_to_shost(cls_session);
-	struct beiscsi_hba *phba = iscsi_host_priv(shost);
-	uint32_t iscsi_err_flag;
+	struct be_async_event_sli *async_sli;
+	u8 evt_type, state, old_state, le;
+	char *sev = KERN_WARNING;
+	char *msg = NULL;
+
+	evt_type = compl->flags >> ASYNC_TRAILER_EVENT_TYPE_SHIFT;
+	evt_type &= ASYNC_TRAILER_EVENT_TYPE_MASK;
+
+	/* processing only MISCONFIGURED physical port event */
+	if (evt_type != ASYNC_SLI_EVENT_TYPE_MISCONFIGURED)
+		return;
+
+	async_sli = (struct be_async_event_sli *)compl;
+	state = async_sli->event_data1 >>
+		 (phba->fw_config.phys_port * 8) & 0xff;
+	le = async_sli->event_data2 >>
+		 (phba->fw_config.phys_port * 8) & 0xff;
+
+	old_state = phba->optic_state;
+	phba->optic_state = state;
+
+	if (state >= ARRAY_SIZE(beiscsi_port_misconf_event_msg)) {
+		/* fw is reporting a state we don't know, log and return */
+		__beiscsi_log(phba, KERN_ERR,
+			    "BC_%d : Port %c: Unrecognized optic state 0x%x\n",
+			    phba->port_name, async_sli->event_data1);
+		return;
+	}
 
-	if (phba->state & BE_ADAPTER_STATE_SHUTDOWN)
-		iscsi_err_flag = ISCSI_ERR_INVALID_HOST;
-	else
-		iscsi_err_flag = ISCSI_ERR_CONN_FAILED;
+	if (ASYNC_SLI_LINK_EFFECT_VALID(le)) {
+		/* log link effect for unqualified-4, uncertified-5 optics */
+		if (state > 3)
+			msg = (ASYNC_SLI_LINK_EFFECT_STATE(le)) ?
+				" Link is non-operational." :
+				" Link is operational.";
+		/* 1 - info */
+		if (ASYNC_SLI_LINK_EFFECT_SEV(le) == 1)
+			sev = KERN_INFO;
+		/* 2 - error */
+		if (ASYNC_SLI_LINK_EFFECT_SEV(le) == 2)
+			sev = KERN_ERR;
+	}
 
-	iscsi_session_failure(cls_session->dd_data, ISCSI_ERR_CONN_FAILED);
+	if (old_state != phba->optic_state)
+		__beiscsi_log(phba, sev, "BC_%d : Port %c: %s%s\n",
+			      phba->port_name,
+			      beiscsi_port_misconf_event_msg[state],
+			      !msg ? "" : msg);
 }
 
-void beiscsi_async_link_state_process(struct beiscsi_hba *phba,
-		struct be_async_event_link_state *evt)
+void beiscsi_process_async_event(struct beiscsi_hba *phba,
+				struct be_mcc_compl *compl)
 {
-	if ((evt->port_link_status == ASYNC_EVENT_LINK_DOWN) ||
-	    ((evt->port_link_status & ASYNC_EVENT_LOGICAL) &&
-	     (evt->port_fault != BEISCSI_PHY_LINK_FAULT_NONE))) {
-		phba->state = BE_ADAPTER_LINK_DOWN;
-
-		beiscsi_log(phba, KERN_ERR,
-			    BEISCSI_LOG_CONFIG | BEISCSI_LOG_INIT,
-			    "BC_%d : Link Down on Port %d\n",
-			    evt->physical_port);
-
-		iscsi_host_for_each_session(phba->shost,
-					    be2iscsi_fail_session);
-	} else if ((evt->port_link_status & ASYNC_EVENT_LINK_UP) ||
-		    ((evt->port_link_status & ASYNC_EVENT_LOGICAL) &&
-		     (evt->port_fault == BEISCSI_PHY_LINK_FAULT_NONE))) {
-		phba->state = BE_ADAPTER_LINK_UP | BE_ADAPTER_CHECK_BOOT;
+	char *sev = KERN_INFO;
+	u8 evt_code;
+
+	/* interpret flags as an async trailer */
+	evt_code = compl->flags >> ASYNC_TRAILER_EVENT_CODE_SHIFT;
+	evt_code &= ASYNC_TRAILER_EVENT_CODE_MASK;
+	switch (evt_code) {
+	case ASYNC_EVENT_CODE_LINK_STATE:
+		beiscsi_process_async_link(phba, compl);
+		break;
+	case ASYNC_EVENT_CODE_ISCSI:
+		phba->state |= BE_ADAPTER_CHECK_BOOT;
 		phba->get_boot = BE_GET_BOOT_RETRIES;
-
-		beiscsi_log(phba, KERN_ERR,
-			    BEISCSI_LOG_CONFIG | BEISCSI_LOG_INIT,
-			    "BC_%d : Link UP on Port %d\n",
-			    evt->physical_port);
+		sev = KERN_ERR;
+		break;
+	case ASYNC_EVENT_CODE_SLI:
+		beiscsi_process_async_sli(phba, compl);
+		break;
+	default:
+		/* event not registered */
+		sev = KERN_ERR;
 	}
+
+	beiscsi_log(phba, sev, BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
+		    "BC_%d : ASYNC Event %x: status 0x%08x flags 0x%08x\n",
+		    evt_code, compl->status, compl->flags);
 }
 
-int beiscsi_process_mcc(struct beiscsi_hba *phba)
+int beiscsi_process_mcc_compl(struct be_ctrl_info *ctrl,
+			      struct be_mcc_compl *compl)
 {
-	struct be_mcc_compl *compl;
-	int num = 0, status = 0;
-	struct be_ctrl_info *ctrl = &phba->ctrl;
+	struct beiscsi_hba *phba = pci_get_drvdata(ctrl->pdev);
+	u16 compl_status, extd_status;
+	struct be_dma_mem *tag_mem;
+	unsigned int tag, wrb_idx;
 
-	spin_lock_bh(&phba->ctrl.mcc_cq_lock);
-	while ((compl = be_mcc_compl_get(phba))) {
-		if (compl->flags & CQE_FLAGS_ASYNC_MASK) {
-			/* Interpret flags as an async trailer */
-			if (is_link_state_evt(compl->flags))
-				/* Interpret compl as a async link evt */
-				beiscsi_async_link_state_process(phba,
-				   (struct be_async_event_link_state *) compl);
-			else if (is_iscsi_evt(compl->flags)) {
-				switch (iscsi_evt_type(compl->flags)) {
-				case ASYNC_EVENT_NEW_ISCSI_TGT_DISC:
-				case ASYNC_EVENT_NEW_ISCSI_CONN:
-				case ASYNC_EVENT_NEW_TCP_CONN:
-					phba->state |= BE_ADAPTER_CHECK_BOOT;
-					phba->get_boot = BE_GET_BOOT_RETRIES;
-					beiscsi_log(phba, KERN_ERR,
-						    BEISCSI_LOG_CONFIG |
-						    BEISCSI_LOG_MBOX,
-						    "BC_%d : Async iscsi Event,"
-						    " flags handled = 0x%08x\n",
-						    compl->flags);
-					break;
-				default:
-					phba->state |= BE_ADAPTER_CHECK_BOOT;
-					phba->get_boot = BE_GET_BOOT_RETRIES;
-					beiscsi_log(phba, KERN_ERR,
-						    BEISCSI_LOG_CONFIG |
-						    BEISCSI_LOG_MBOX,
-						    "BC_%d : Unsupported Async"
-						    " Event, flags = 0x%08x\n",
-						    compl->flags);
-				}
-			} else
-				beiscsi_log(phba, KERN_ERR,
-					    BEISCSI_LOG_CONFIG |
-					    BEISCSI_LOG_MBOX,
-					    "BC_%d : Unsupported Async Event, flags"
-					    " = 0x%08x\n", compl->flags);
-
-		} else if (compl->flags & CQE_FLAGS_COMPLETED_MASK) {
-				status = be_mcc_compl_process(ctrl, compl);
-				atomic_dec(&phba->ctrl.mcc_obj.q.used);
-		}
-		be_mcc_compl_use(compl);
-		num++;
+	be_dws_le_to_cpu(compl, 4);
+	tag = (compl->tag0 & MCC_Q_CMD_TAG_MASK);
+	wrb_idx = (compl->tag0 & CQE_STATUS_WRB_MASK) >> CQE_STATUS_WRB_SHIFT;
+
+	if (!test_bit(MCC_TAG_STATE_RUNNING,
+		      &ctrl->ptag_state[tag].tag_state)) {
+		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_MBOX |
+			    BEISCSI_LOG_INIT | BEISCSI_LOG_CONFIG,
+			    "BC_%d : MBX cmd completed but not posted\n");
+		return 0;
 	}
 
-	if (num)
-		hwi_ring_cq_db(phba, phba->ctrl.mcc_obj.cq.id, num, 1, 0);
+	if (test_bit(MCC_TAG_STATE_TIMEOUT, &ctrl->ptag_state[tag].tag_state)) {
+		beiscsi_log(phba, KERN_WARNING,
+			    BEISCSI_LOG_MBOX | BEISCSI_LOG_INIT |
+			    BEISCSI_LOG_CONFIG,
+			    "BC_%d : MBX Completion for timeout Command from FW\n");
+		/**
+		 * Check for the size before freeing resource.
+		 * Only for non-embedded cmd, PCI resource is allocated.
+		 **/
+		tag_mem = &ctrl->ptag_state[tag].tag_mem_state;
+		if (tag_mem->size)
+			pci_free_consistent(ctrl->pdev, tag_mem->size,
+					tag_mem->va, tag_mem->dma);
+		free_mcc_wrb(ctrl, tag);
+		return 0;
+	}
 
-	spin_unlock_bh(&phba->ctrl.mcc_cq_lock);
-	return status;
+	compl_status = (compl->status >> CQE_STATUS_COMPL_SHIFT) &
+		       CQE_STATUS_COMPL_MASK;
+	extd_status = (compl->status >> CQE_STATUS_EXTD_SHIFT) &
+		      CQE_STATUS_EXTD_MASK;
+	/* The ctrl.mcc_tag_status[tag] is filled with
+	 * [31] = valid, [30:24] = Rsvd, [23:16] = wrb, [15:8] = extd_status,
+	 * [7:0] = compl_status
+	 */
+	ctrl->mcc_tag_status[tag] = CQE_VALID_MASK;
+	ctrl->mcc_tag_status[tag] |= (wrb_idx << CQE_STATUS_WRB_SHIFT);
+	ctrl->mcc_tag_status[tag] |= (extd_status << CQE_STATUS_ADDL_SHIFT) &
+				     CQE_STATUS_ADDL_MASK;
+	ctrl->mcc_tag_status[tag] |= (compl_status & CQE_STATUS_MASK);
+
+	/* write ordering forced in wake_up_interruptible */
+	clear_bit(MCC_TAG_STATE_RUNNING, &ctrl->ptag_state[tag].tag_state);
+	wake_up_interruptible(&ctrl->mcc_wait[tag]);
+	return 0;
 }
 
 /*
- * be_mcc_wait_compl()- Wait for MBX completion
+ * be_mcc_compl_poll()- Wait for MBX completion
  * @phba: driver private structure
  *
  * Wait till no more pending mcc requests are present
@@ -532,50 +567,57 @@ int beiscsi_process_mcc(struct beiscsi_hba *phba)
  * Failure: Non-Zero
  *
  **/
-static int be_mcc_wait_compl(struct beiscsi_hba *phba)
+int be_mcc_compl_poll(struct beiscsi_hba *phba, unsigned int tag)
 {
-	int i, status;
+	struct be_ctrl_info *ctrl = &phba->ctrl;
+	int i;
+
+	if (!test_bit(MCC_TAG_STATE_RUNNING,
+		      &ctrl->ptag_state[tag].tag_state)) {
+		beiscsi_log(phba, KERN_ERR,
+			    BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
+			    "BC_%d: tag %u state not running\n", tag);
+		return 0;
+	}
 	for (i = 0; i < mcc_timeout; i++) {
 		if (beiscsi_error(phba))
 			return -EIO;
 
-		status = beiscsi_process_mcc(phba);
-		if (status)
-			return status;
-
-		if (atomic_read(&phba->ctrl.mcc_obj.q.used) == 0)
+		beiscsi_process_mcc_cq(phba);
+		/* after polling, wrb and tag need to be released */
+		if (!test_bit(MCC_TAG_STATE_RUNNING,
+			      &ctrl->ptag_state[tag].tag_state)) {
+			free_mcc_wrb(ctrl, tag);
 			break;
+		}
 		udelay(100);
 	}
-	if (i == mcc_timeout) {
-		beiscsi_log(phba, KERN_ERR,
-			    BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
-			    "BC_%d : FW Timed Out\n");
-		phba->fw_timeout = true;
-		beiscsi_ue_detect(phba);
-		return -EBUSY;
-	}
-	return 0;
+
+	if (i < mcc_timeout)
+		return 0;
+
+	beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
+		    "BC_%d : FW Timed Out\n");
+	phba->fw_timeout = true;
+	beiscsi_ue_detect(phba);
+	return -EBUSY;
 }
 
-/*
- * be_mcc_notify_wait()- Notify and wait for Compl
- * @phba: driver private structure
- *
- * Notify MCC requests and wait for completion
- *
- * return
- * Success: 0
- * Failure: Non-Zero
- **/
-int be_mcc_notify_wait(struct beiscsi_hba *phba)
+void be_mcc_notify(struct beiscsi_hba *phba, unsigned int tag)
 {
-	be_mcc_notify(phba);
-	return be_mcc_wait_compl(phba);
+	struct be_queue_info *mccq = &phba->ctrl.mcc_obj.q;
+	u32 val = 0;
+
+	set_bit(MCC_TAG_STATE_RUNNING, &phba->ctrl.ptag_state[tag].tag_state);
+	val |= mccq->id & DB_MCCQ_RING_ID_MASK;
+	val |= 1 << DB_MCCQ_NUM_POSTED_SHIFT;
+	/* make request available for DMA */
+	wmb();
+	iowrite32(val, phba->db_va + DB_MCCQ_OFFSET);
 }
 
 /*
- * be_mbox_db_ready_wait()- Check ready status
+ * be_mbox_db_ready_poll()- Check ready status
  * @ctrl: Function specific MBX data structure
  *
  * Check for the ready status of FW to send BMBX
@@ -585,49 +627,45 @@ int be_mcc_notify_wait(struct beiscsi_hba *phba)
  * Success: 0
  * Failure: Non-Zero
  **/
-static int be_mbox_db_ready_wait(struct be_ctrl_info *ctrl)
+static int be_mbox_db_ready_poll(struct be_ctrl_info *ctrl)
 {
-#define BEISCSI_MBX_RDY_BIT_TIMEOUT	4000	/* 4sec */
+	/* wait 30s for generic non-flash MBOX operation */
+#define BEISCSI_MBX_RDY_BIT_TIMEOUT	30000
 	void __iomem *db = ctrl->db + MPU_MAILBOX_DB_OFFSET;
 	struct beiscsi_hba *phba = pci_get_drvdata(ctrl->pdev);
 	unsigned long timeout;
-	bool read_flag = false;
-	int ret = 0, i;
 	u32 ready;
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(rdybit_check_q);
 
-	if (beiscsi_error(phba))
-		return -EIO;
+	/*
+	 * This BMBX busy wait path is used during init only.
+	 * For the commands executed during init, 5s should suffice.
+	 */
+	timeout = jiffies + msecs_to_jiffies(BEISCSI_MBX_RDY_BIT_TIMEOUT);
+	do {
+		if (beiscsi_error(phba))
+			return -EIO;
 
-	timeout = jiffies + (HZ * 110);
+		ready = ioread32(db);
+		if (ready == 0xffffffff)
+			return -EIO;
 
-	do {
-		for (i = 0; i < BEISCSI_MBX_RDY_BIT_TIMEOUT; i++) {
-			ready = ioread32(db) & MPU_MAILBOX_DB_RDY_MASK;
-			if (ready) {
-				read_flag = true;
-				break;
-			}
-			mdelay(1);
-		}
+		ready &= MPU_MAILBOX_DB_RDY_MASK;
+		if (ready)
+			return 0;
 
-		if (!read_flag) {
-			wait_event_timeout(rdybit_check_q,
-					  (read_flag != true),
-					   HZ * 5);
-		}
-	} while ((time_before(jiffies, timeout)) && !read_flag);
+		if (time_after(jiffies, timeout))
+			break;
+		msleep(20);
+	} while (!ready);
 
-	if (!read_flag) {
-		beiscsi_log(phba, KERN_ERR,
-			    BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
-			    "BC_%d : FW Timed Out\n");
-			phba->fw_timeout = true;
-			beiscsi_ue_detect(phba);
-			ret = -EBUSY;
-	}
+	beiscsi_log(phba, KERN_ERR,
+			BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
+			"BC_%d : FW Timed Out\n");
+
+	phba->fw_timeout = true;
+	beiscsi_ue_detect(phba);
 
-	return ret;
+	return -EBUSY;
 }
 
 /*
@@ -648,10 +686,8 @@ int be_mbox_notify(struct be_ctrl_info *ctrl)
 	void __iomem *db = ctrl->db + MPU_MAILBOX_DB_OFFSET;
 	struct be_dma_mem *mbox_mem = &ctrl->mbox_mem;
 	struct be_mcc_mailbox *mbox = mbox_mem->va;
-	struct be_mcc_compl *compl = &mbox->compl;
-	struct beiscsi_hba *phba = pci_get_drvdata(ctrl->pdev);
 
-	status = be_mbox_db_ready_wait(ctrl);
+	status = be_mbox_db_ready_poll(ctrl);
 	if (status)
 		return status;
 
@@ -660,7 +696,7 @@ int be_mbox_notify(struct be_ctrl_info *ctrl)
 	val |= (upper_32_bits(mbox_mem->dma) >> 2) << 2;
 	iowrite32(val, db);
 
-	status = be_mbox_db_ready_wait(ctrl);
+	status = be_mbox_db_ready_poll(ctrl);
 	if (status)
 		return status;
 
@@ -670,81 +706,15 @@ int be_mbox_notify(struct be_ctrl_info *ctrl)
 	val |= (u32) (mbox_mem->dma >> 4) << 2;
 	iowrite32(val, db);
 
-	status = be_mbox_db_ready_wait(ctrl);
+	status = be_mbox_db_ready_poll(ctrl);
 	if (status)
 		return status;
 
-	if (be_mcc_compl_is_new(compl)) {
-		status = be_mcc_compl_process(ctrl, &mbox->compl);
-		be_mcc_compl_use(compl);
-		if (status) {
-			beiscsi_log(phba, KERN_ERR,
-				    BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
-				    "BC_%d : After be_mcc_compl_process\n");
-
-			return status;
-		}
-	} else {
-		beiscsi_log(phba, KERN_ERR,
-			    BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
-			    "BC_%d : Invalid Mailbox Completion\n");
-
-		return -EBUSY;
-	}
-	return 0;
-}
-
-/*
- * Insert the mailbox address into the doorbell in two steps
- * Polls on the mbox doorbell till a command completion (or a timeout) occurs
- */
-static int be_mbox_notify_wait(struct beiscsi_hba *phba)
-{
-	int status;
-	u32 val = 0;
-	void __iomem *db = phba->ctrl.db + MPU_MAILBOX_DB_OFFSET;
-	struct be_dma_mem *mbox_mem = &phba->ctrl.mbox_mem;
-	struct be_mcc_mailbox *mbox = mbox_mem->va;
-	struct be_mcc_compl *compl = &mbox->compl;
-	struct be_ctrl_info *ctrl = &phba->ctrl;
-
-	status = be_mbox_db_ready_wait(ctrl);
-	if (status)
-		return status;
-
-	val |= MPU_MAILBOX_DB_HI_MASK;
-	/* at bits 2 - 31 place mbox dma addr msb bits 34 - 63 */
-	val |= (upper_32_bits(mbox_mem->dma) >> 2) << 2;
-	iowrite32(val, db);
-
-	/* wait for ready to be set */
-	status = be_mbox_db_ready_wait(ctrl);
-	if (status != 0)
-		return status;
-
-	val = 0;
-	/* at bits 2 - 31 place mbox dma addr lsb bits 4 - 33 */
-	val |= (u32)(mbox_mem->dma >> 4) << 2;
-	iowrite32(val, db);
+	/* RDY is set; small delay before CQE read. */
+	udelay(1);
 
-	status = be_mbox_db_ready_wait(ctrl);
-	if (status != 0)
-		return status;
-
-	/* A cq entry has been made now */
-	if (be_mcc_compl_is_new(compl)) {
-		status = be_mcc_compl_process(ctrl, &mbox->compl);
-		be_mcc_compl_use(compl);
-		if (status)
-			return status;
-	} else {
-		beiscsi_log(phba, KERN_ERR,
-			    BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
-			    "BC_%d : invalid mailbox completion\n");
-
-		return -EBUSY;
-	}
-	return 0;
+	status = beiscsi_process_mbox_compl(ctrl, &mbox->compl);
+	return status;
 }
 
 void be_wrb_hdr_prepare(struct be_mcc_wrb *wrb, int payload_len,
@@ -809,21 +779,6 @@ struct be_mcc_wrb *wrb_from_mbox(struct be_dma_mem *mbox_mem)
 	return &((struct be_mcc_mailbox *)(mbox_mem->va))->wrb;
 }
 
-struct be_mcc_wrb *wrb_from_mccq(struct beiscsi_hba *phba)
-{
-	struct be_queue_info *mccq = &phba->ctrl.mcc_obj.q;
-	struct be_mcc_wrb *wrb;
-
-	WARN_ON(atomic_read(&mccq->used) >= mccq->len);
-	wrb = queue_head_node(mccq);
-	memset(wrb, 0, sizeof(*wrb));
-	wrb->tag0 = (mccq->head & 0x000000FF) << 16;
-	queue_head_inc(mccq);
-	atomic_inc(&mccq->used);
-	return wrb;
-}
-
-
 int beiscsi_cmd_eq_create(struct be_ctrl_info *ctrl,
 			  struct be_queue_info *eq, int eq_delay)
 {
@@ -833,7 +788,7 @@ int beiscsi_cmd_eq_create(struct be_ctrl_info *ctrl,
 	struct be_dma_mem *q_mem = &eq->dma_mem;
 	int status;
 
-	spin_lock(&ctrl->mbox_lock);
+	mutex_lock(&ctrl->mbox_lock);
 	memset(wrb, 0, sizeof(*wrb));
 
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
@@ -860,7 +815,7 @@ int beiscsi_cmd_eq_create(struct be_ctrl_info *ctrl,
 		eq->id = le16_to_cpu(resp->eq_id);
 		eq->created = true;
 	}
-	spin_unlock(&ctrl->mbox_lock);
+	mutex_unlock(&ctrl->mbox_lock);
 	return status;
 }
 
@@ -881,7 +836,7 @@ int be_cmd_fw_initialize(struct be_ctrl_info *ctrl)
 	int status;
 	u8 *endian_check;
 
-	spin_lock(&ctrl->mbox_lock);
+	mutex_lock(&ctrl->mbox_lock);
 	memset(wrb, 0, sizeof(*wrb));
 
 	endian_check = (u8 *) wrb;
@@ -900,7 +855,7 @@ int be_cmd_fw_initialize(struct be_ctrl_info *ctrl)
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
 			    "BC_%d : be_cmd_fw_initialize Failed\n");
 
-	spin_unlock(&ctrl->mbox_lock);
+	mutex_unlock(&ctrl->mbox_lock);
 	return status;
 }
 
@@ -921,7 +876,7 @@ int be_cmd_fw_uninit(struct be_ctrl_info *ctrl)
 	int status;
 	u8 *endian_check;
 
-	spin_lock(&ctrl->mbox_lock);
+	mutex_lock(&ctrl->mbox_lock);
 	memset(wrb, 0, sizeof(*wrb));
 
 	endian_check = (u8 *) wrb;
@@ -941,7 +896,7 @@ int be_cmd_fw_uninit(struct be_ctrl_info *ctrl)
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
 			    "BC_%d : be_cmd_fw_uninit Failed\n");
 
-	spin_unlock(&ctrl->mbox_lock);
+	mutex_unlock(&ctrl->mbox_lock);
 	return status;
 }
 
@@ -957,7 +912,7 @@ int beiscsi_cmd_cq_create(struct be_ctrl_info *ctrl,
 	void *ctxt = &req->context;
 	int status;
 
-	spin_lock(&ctrl->mbox_lock);
+	mutex_lock(&ctrl->mbox_lock);
 	memset(wrb, 0, sizeof(*wrb));
 
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
@@ -1007,7 +962,7 @@ int beiscsi_cmd_cq_create(struct be_ctrl_info *ctrl,
 			    "BC_%d : In be_cmd_cq_create, status=ox%08x\n",
 			    status);
 
-	spin_unlock(&ctrl->mbox_lock);
+	mutex_unlock(&ctrl->mbox_lock);
 
 	return status;
 }
@@ -1025,13 +980,13 @@ int beiscsi_cmd_mccq_create(struct beiscsi_hba *phba,
 			struct be_queue_info *cq)
 {
 	struct be_mcc_wrb *wrb;
-	struct be_cmd_req_mcc_create *req;
+	struct be_cmd_req_mcc_create_ext *req;
 	struct be_dma_mem *q_mem = &mccq->dma_mem;
 	struct be_ctrl_info *ctrl;
 	void *ctxt;
 	int status;
 
-	spin_lock(&phba->ctrl.mbox_lock);
+	mutex_lock(&phba->ctrl.mbox_lock);
 	ctrl = &phba->ctrl;
 	wrb = wrb_from_mbox(&ctrl->mbox_mem);
 	memset(wrb, 0, sizeof(*wrb));
@@ -1041,9 +996,12 @@ int beiscsi_cmd_mccq_create(struct beiscsi_hba *phba,
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
 
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-			OPCODE_COMMON_MCC_CREATE, sizeof(*req));
+			OPCODE_COMMON_MCC_CREATE_EXT, sizeof(*req));
 
 	req->num_pages = PAGES_4K_SPANNED(q_mem->va, q_mem->size);
+	req->async_evt_bitmap = 1 << ASYNC_EVENT_CODE_LINK_STATE;
+	req->async_evt_bitmap |= 1 << ASYNC_EVENT_CODE_ISCSI;
+	req->async_evt_bitmap |= 1 << ASYNC_EVENT_CODE_SLI;
 
 	AMAP_SET_BITS(struct amap_mcc_context, fid, ctxt,
 		      PCI_FUNC(phba->pcidev->devfn));
@@ -1056,13 +1014,13 @@ int beiscsi_cmd_mccq_create(struct beiscsi_hba *phba,
 
 	be_cmd_page_addrs_prepare(req->pages, ARRAY_SIZE(req->pages), q_mem);
 
-	status = be_mbox_notify_wait(phba);
+	status = be_mbox_notify(ctrl);
 	if (!status) {
 		struct be_cmd_resp_mcc_create *resp = embedded_payload(wrb);
 		mccq->id = le16_to_cpu(resp->id);
 		mccq->created = true;
 	}
-	spin_unlock(&phba->ctrl.mbox_lock);
+	mutex_unlock(&phba->ctrl.mbox_lock);
 
 	return status;
 }
@@ -1080,7 +1038,7 @@ int beiscsi_cmd_q_destroy(struct be_ctrl_info *ctrl, struct be_queue_info *q,
 		    "BC_%d : In beiscsi_cmd_q_destroy "
 		    "queue_type : %d\n", queue_type);
 
-	spin_lock(&ctrl->mbox_lock);
+	mutex_lock(&ctrl->mbox_lock);
 	memset(wrb, 0, sizeof(*wrb));
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
 
@@ -1110,7 +1068,7 @@ int beiscsi_cmd_q_destroy(struct be_ctrl_info *ctrl, struct be_queue_info *q,
 		opcode = OPCODE_COMMON_ISCSI_CFG_REMOVE_SGL_PAGES;
 		break;
 	default:
-		spin_unlock(&ctrl->mbox_lock);
+		mutex_unlock(&ctrl->mbox_lock);
 		BUG();
 		return -ENXIO;
 	}
@@ -1120,7 +1078,7 @@ int beiscsi_cmd_q_destroy(struct be_ctrl_info *ctrl, struct be_queue_info *q,
 
 	status = be_mbox_notify(ctrl);
 
-	spin_unlock(&ctrl->mbox_lock);
+	mutex_unlock(&ctrl->mbox_lock);
 	return status;
 }
 
@@ -1155,7 +1113,7 @@ int be_cmd_create_default_pdu_queue(struct be_ctrl_info *ctrl,
 	void *ctxt = &req->context;
 	int status;
 
-	spin_lock(&ctrl->mbox_lock);
+	mutex_lock(&ctrl->mbox_lock);
 	memset(wrb, 0, sizeof(*wrb));
 
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
@@ -1227,7 +1185,7 @@ int be_cmd_create_default_pdu_queue(struct be_ctrl_info *ctrl,
 			defq_ring->doorbell_offset = resp->doorbell_offset;
 		}
 	}
-	spin_unlock(&ctrl->mbox_lock);
+	mutex_unlock(&ctrl->mbox_lock);
 
 	return status;
 }
@@ -1255,7 +1213,7 @@ int be_cmd_wrbq_create(struct be_ctrl_info *ctrl,
 	struct beiscsi_hba *phba = pci_get_drvdata(ctrl->pdev);
 	int status;
 
-	spin_lock(&ctrl->mbox_lock);
+	mutex_lock(&ctrl->mbox_lock);
 	memset(wrb, 0, sizeof(*wrb));
 
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
@@ -1286,7 +1244,7 @@ int be_cmd_wrbq_create(struct be_ctrl_info *ctrl,
 			pwrb_context->doorbell_offset = resp->doorbell_offset;
 		}
 	}
-	spin_unlock(&ctrl->mbox_lock);
+	mutex_unlock(&ctrl->mbox_lock);
 	return status;
 }
 
@@ -1297,7 +1255,7 @@ int be_cmd_iscsi_post_template_hdr(struct be_ctrl_info *ctrl,
 	struct be_post_template_pages_req *req = embedded_payload(wrb);
 	int status;
 
-	spin_lock(&ctrl->mbox_lock);
+	mutex_lock(&ctrl->mbox_lock);
 
 	memset(wrb, 0, sizeof(*wrb));
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
@@ -1310,7 +1268,7 @@ int be_cmd_iscsi_post_template_hdr(struct be_ctrl_info *ctrl,
 	be_cmd_page_addrs_prepare(req->pages, ARRAY_SIZE(req->pages), q_mem);
 
 	status = be_mbox_notify(ctrl);
-	spin_unlock(&ctrl->mbox_lock);
+	mutex_unlock(&ctrl->mbox_lock);
 	return status;
 }
 
@@ -1320,7 +1278,7 @@ int be_cmd_iscsi_remove_template_hdr(struct be_ctrl_info *ctrl)
 	struct be_remove_template_pages_req *req = embedded_payload(wrb);
 	int status;
 
-	spin_lock(&ctrl->mbox_lock);
+	mutex_lock(&ctrl->mbox_lock);
 
 	memset(wrb, 0, sizeof(*wrb));
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
@@ -1331,7 +1289,7 @@ int be_cmd_iscsi_remove_template_hdr(struct be_ctrl_info *ctrl)
 	req->type = BEISCSI_TEMPLATE_HDR_TYPE_ISCSI;
 
 	status = be_mbox_notify(ctrl);
-	spin_unlock(&ctrl->mbox_lock);
+	mutex_unlock(&ctrl->mbox_lock);
 	return status;
 }
 
@@ -1350,7 +1308,7 @@ int be_cmd_iscsi_post_sgl_pages(struct be_ctrl_info *ctrl,
 	if (num_pages == 0xff)
 		num_pages = 1;
 
-	spin_lock(&ctrl->mbox_lock);
+	mutex_lock(&ctrl->mbox_lock);
 	do {
 		memset(wrb, 0, sizeof(*wrb));
 		be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
@@ -1379,7 +1337,7 @@ int be_cmd_iscsi_post_sgl_pages(struct be_ctrl_info *ctrl,
 		}
 	} while (num_pages > 0);
 error:
-	spin_unlock(&ctrl->mbox_lock);
+	mutex_unlock(&ctrl->mbox_lock);
 	if (status != 0)
 		beiscsi_cmd_q_destroy(ctrl, NULL, QTYPE_SGL);
 	return status;
@@ -1392,15 +1350,15 @@ int beiscsi_cmd_reset_function(struct beiscsi_hba  *phba)
 	struct be_post_sgl_pages_req *req = embedded_payload(wrb);
 	int status;
 
-	spin_lock(&ctrl->mbox_lock);
+	mutex_lock(&ctrl->mbox_lock);
 
 	req = embedded_payload(wrb);
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
 			   OPCODE_COMMON_FUNCTION_RESET, sizeof(*req));
-	status = be_mbox_notify_wait(phba);
+	status = be_mbox_notify(ctrl);
 
-	spin_unlock(&ctrl->mbox_lock);
+	mutex_unlock(&ctrl->mbox_lock);
 	return status;
 }
 
@@ -1417,21 +1375,20 @@ int beiscsi_cmd_reset_function(struct beiscsi_hba  *phba)
 int be_cmd_set_vlan(struct beiscsi_hba *phba,
 		     uint16_t vlan_tag)
 {
-	unsigned int tag = 0;
+	unsigned int tag;
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_set_vlan_req *req;
 	struct be_ctrl_info *ctrl = &phba->ctrl;
 
-	spin_lock(&ctrl->mbox_lock);
-	tag = alloc_mcc_tag(phba);
-	if (!tag) {
-		spin_unlock(&ctrl->mbox_lock);
-		return tag;
+	if (mutex_lock_interruptible(&ctrl->mbox_lock))
+		return 0;
+	wrb = alloc_mcc_wrb(phba, &tag);
+	if (!wrb) {
+		mutex_unlock(&ctrl->mbox_lock);
+		return 0;
 	}
 
-	wrb = wrb_from_mccq(phba);
 	req = embedded_payload(wrb);
-	wrb->tag0 |= tag;
 	be_wrb_hdr_prepare(wrb, sizeof(*wrb), true, 0);
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI,
 			   OPCODE_COMMON_ISCSI_NTWK_SET_VLAN,
@@ -1440,8 +1397,8 @@ int be_cmd_set_vlan(struct beiscsi_hba *phba,
 	req->interface_hndl = phba->interface_handle;
 	req->vlan_priority = vlan_tag;
 
-	be_mcc_notify(phba);
-	spin_unlock(&ctrl->mbox_lock);
+	be_mcc_notify(phba, tag);
+	mutex_unlock(&ctrl->mbox_lock);
 
 	return tag;
 }
diff --git a/drivers/scsi/be2iscsi/be_cmds.h b/drivers/scsi/be2iscsi/be_cmds.h
index 4bfca355fbe4..deeb951e6874 100644
--- a/drivers/scsi/be2iscsi/be_cmds.h
+++ b/drivers/scsi/be2iscsi/be_cmds.h
@@ -58,15 +58,16 @@ struct be_mcc_wrb {
 #define MCC_STATUS_ILLEGAL_FIELD 0x3
 #define MCC_STATUS_INSUFFICIENT_BUFFER 0x4
 
-#define CQE_STATUS_COMPL_MASK 0xFFFF
-#define CQE_STATUS_COMPL_SHIFT 0	/* bits 0 - 15 */
-#define CQE_STATUS_EXTD_MASK 0xFFFF
-#define CQE_STATUS_EXTD_SHIFT 16		/* bits 0 - 15 */
+#define CQE_STATUS_COMPL_MASK	0xFFFF
+#define CQE_STATUS_COMPL_SHIFT	0		/* bits 0 - 15 */
+#define CQE_STATUS_EXTD_MASK	0xFFFF
+#define CQE_STATUS_EXTD_SHIFT	16		/* bits 31 - 16 */
 #define CQE_STATUS_ADDL_MASK	0xFF00
-#define CQE_STATUS_MASK	0xFF
-#define CQE_STATUS_ADDL_SHIFT	0x08
+#define CQE_STATUS_ADDL_SHIFT	8
+#define CQE_STATUS_MASK		0xFF
 #define CQE_STATUS_WRB_MASK	0xFF0000
 #define CQE_STATUS_WRB_SHIFT	16
+
 #define BEISCSI_HOST_MBX_TIMEOUT (110 * 1000)
 #define BEISCSI_FW_MBX_TIMEOUT	100
 
@@ -119,13 +120,22 @@ struct be_mcc_compl {
 #define ASYNC_TRAILER_EVENT_CODE_MASK	0xFF
 #define ASYNC_EVENT_CODE_LINK_STATE	0x1
 #define ASYNC_EVENT_CODE_ISCSI		0x4
+#define ASYNC_EVENT_CODE_SLI		0x11
 
 #define ASYNC_TRAILER_EVENT_TYPE_SHIFT	16	/* bits 16 - 23 */
-#define ASYNC_TRAILER_EVENT_TYPE_MASK	0xF
+#define ASYNC_TRAILER_EVENT_TYPE_MASK	0xFF
+
+/* iSCSI events */
 #define ASYNC_EVENT_NEW_ISCSI_TGT_DISC	0x4
 #define ASYNC_EVENT_NEW_ISCSI_CONN	0x5
 #define ASYNC_EVENT_NEW_TCP_CONN	0x7
 
+/* SLI events */
+#define ASYNC_SLI_EVENT_TYPE_MISCONFIGURED	0x9
+#define ASYNC_SLI_LINK_EFFECT_VALID(le)		(le & 0x80)
+#define ASYNC_SLI_LINK_EFFECT_SEV(le)		((le >> 1)  & 0x03)
+#define ASYNC_SLI_LINK_EFFECT_STATE(le)		(le & 0x01)
+
 struct be_async_event_trailer {
 	u32 code;
 };
@@ -133,7 +143,6 @@ struct be_async_event_trailer {
 enum {
 	ASYNC_EVENT_LINK_DOWN = 0x0,
 	ASYNC_EVENT_LINK_UP = 0x1,
-	ASYNC_EVENT_LOGICAL = 0x2
 };
 
 /**
@@ -143,16 +152,39 @@ enum {
 struct be_async_event_link_state {
 	u8 physical_port;
 	u8 port_link_status;
+/**
+ * ASYNC_EVENT_LINK_DOWN		0x0
+ * ASYNC_EVENT_LINK_UP			0x1
+ * ASYNC_EVENT_LINK_LOGICAL_DOWN	0x2
+ * ASYNC_EVENT_LINK_LOGICAL_UP		0x3
+ */
+#define BE_ASYNC_LINK_UP_MASK		0x01
 	u8 port_duplex;
 	u8 port_speed;
-#define BEISCSI_PHY_LINK_FAULT_NONE	0x00
-#define BEISCSI_PHY_LINK_FAULT_LOCAL	0x01
-#define BEISCSI_PHY_LINK_FAULT_REMOTE	0x02
+/* BE2ISCSI_LINK_SPEED_ZERO	0x00 - no link */
+#define BE2ISCSI_LINK_SPEED_10MBPS	0x01
+#define BE2ISCSI_LINK_SPEED_100MBPS	0x02
+#define BE2ISCSI_LINK_SPEED_1GBPS	0x03
+#define BE2ISCSI_LINK_SPEED_10GBPS	0x04
+#define BE2ISCSI_LINK_SPEED_25GBPS	0x06
+#define BE2ISCSI_LINK_SPEED_40GBPS	0x07
 	u8 port_fault;
-	u8 rsvd0[7];
+	u8 event_reason;
+	u16 qos_link_speed;
+	u32 event_tag;
 	struct be_async_event_trailer trailer;
 } __packed;
 
+/**
+ * When async-trailer is SLI event, mcc_compl is interpreted as
+ */
+struct be_async_event_sli {
+	u32 event_data1;
+	u32 event_data2;
+	u32 reserved;
+	u32 trailer;
+} __packed;
+
 struct be_mcc_mailbox {
 	struct be_mcc_wrb wrb;
 	struct be_mcc_compl compl;
@@ -172,6 +204,7 @@ struct be_mcc_mailbox {
 #define OPCODE_COMMON_CQ_CREATE				12
 #define OPCODE_COMMON_EQ_CREATE				13
 #define OPCODE_COMMON_MCC_CREATE			21
+#define OPCODE_COMMON_MCC_CREATE_EXT			90
 #define OPCODE_COMMON_ADD_TEMPLATE_HEADER_BUFFERS	24
 #define OPCODE_COMMON_REMOVE_TEMPLATE_HEADER_BUFFERS	25
 #define OPCODE_COMMON_GET_CNTL_ATTRIBUTES		32
@@ -183,6 +216,7 @@ struct be_mcc_mailbox {
 #define OPCODE_COMMON_EQ_DESTROY			55
 #define OPCODE_COMMON_QUERY_FIRMWARE_CONFIG		58
 #define OPCODE_COMMON_FUNCTION_RESET			61
+#define OPCODE_COMMON_GET_PORT_NAME			77
 
 /**
  * LIST of opcodes that are common between Initiator and Target
@@ -587,10 +621,11 @@ struct amap_mcc_context {
 	u8 rsvd2[32];
 } __packed;
 
-struct be_cmd_req_mcc_create {
+struct be_cmd_req_mcc_create_ext {
 	struct be_cmd_req_hdr hdr;
 	u16 num_pages;
 	u16 rsvd0;
+	u32 async_evt_bitmap;
 	u8 context[sizeof(struct amap_mcc_context) / 8];
 	struct phys_addr pages[8];
 } __packed;
@@ -653,20 +688,6 @@ struct be_cmd_req_modify_eq_delay {
 
 /******************** Get MAC ADDR *******************/
 
-#define ETH_ALEN	6
-
-struct be_cmd_get_nic_conf_req {
-	struct be_cmd_req_hdr hdr;
-	u32 nic_port_count;
-	u32 speed;
-	u32 max_speed;
-	u32 link_state;
-	u32 max_frame_size;
-	u16 size_of_structure;
-	u8 mac_address[ETH_ALEN];
-	u32 rsvd[23];
-};
-
 struct be_cmd_get_nic_conf_resp {
 	struct be_cmd_resp_hdr hdr;
 	u32 nic_port_count;
@@ -675,9 +696,8 @@ struct be_cmd_get_nic_conf_resp {
 	u32 link_state;
 	u32 max_frame_size;
 	u16 size_of_structure;
-	u8 mac_address[6];
-	u32 rsvd[23];
-};
+	u8 mac_address[ETH_ALEN];
+} __packed;
 
 #define BEISCSI_ALIAS_LEN 32
 
@@ -689,29 +709,6 @@ struct be_cmd_hba_name {
 	u8 initiator_alias[BEISCSI_ALIAS_LEN];
 } __packed;
 
-struct be_cmd_ntwk_link_status_req {
-	struct be_cmd_req_hdr hdr;
-	u32 rsvd0;
-} __packed;
-
-/*** Port Speed Values ***/
-#define BE2ISCSI_LINK_SPEED_ZERO	0x00
-#define BE2ISCSI_LINK_SPEED_10MBPS	0x01
-#define BE2ISCSI_LINK_SPEED_100MBPS	0x02
-#define BE2ISCSI_LINK_SPEED_1GBPS	0x03
-#define BE2ISCSI_LINK_SPEED_10GBPS	0x04
-struct be_cmd_ntwk_link_status_resp {
-	struct be_cmd_resp_hdr hdr;
-	u8 phys_port;
-	u8 mac_duplex;
-	u8 mac_speed;
-	u8 mac_fault;
-	u8 mgmt_mac_duplex;
-	u8 mgmt_mac_speed;
-	u16 qos_link_speed;
-	u32 logical_link_speed;
-} __packed;
-
 int beiscsi_cmd_eq_create(struct be_ctrl_info *ctrl,
 			  struct be_queue_info *eq, int eq_delay);
 
@@ -730,28 +727,28 @@ int be_poll_mcc(struct be_ctrl_info *ctrl);
 int mgmt_check_supported_fw(struct be_ctrl_info *ctrl,
 				      struct beiscsi_hba *phba);
 unsigned int be_cmd_get_initname(struct beiscsi_hba *phba);
-unsigned int be_cmd_get_port_speed(struct beiscsi_hba *phba);
 
-void free_mcc_tag(struct be_ctrl_info *ctrl, unsigned int tag);
+void free_mcc_wrb(struct be_ctrl_info *ctrl, unsigned int tag);
 
 int be_cmd_modify_eq_delay(struct beiscsi_hba *phba, struct be_set_eqd *,
 			    int num);
-int beiscsi_mccq_compl(struct beiscsi_hba *phba,
-			uint32_t tag, struct be_mcc_wrb **wrb,
-			struct be_dma_mem *mbx_cmd_mem);
+int beiscsi_mccq_compl_wait(struct beiscsi_hba *phba,
+			    uint32_t tag, struct be_mcc_wrb **wrb,
+			    struct be_dma_mem *mbx_cmd_mem);
 /*ISCSI Functuions */
 int be_cmd_fw_initialize(struct be_ctrl_info *ctrl);
 int be_cmd_fw_uninit(struct be_ctrl_info *ctrl);
 
 struct be_mcc_wrb *wrb_from_mbox(struct be_dma_mem *mbox_mem);
-struct be_mcc_wrb *wrb_from_mccq(struct beiscsi_hba *phba);
-int be_mcc_notify_wait(struct beiscsi_hba *phba);
-void be_mcc_notify(struct beiscsi_hba *phba);
-unsigned int alloc_mcc_tag(struct beiscsi_hba *phba);
-void beiscsi_async_link_state_process(struct beiscsi_hba *phba,
-		struct be_async_event_link_state *evt);
-int be_mcc_compl_process_isr(struct be_ctrl_info *ctrl,
-				    struct be_mcc_compl *compl);
+int be_mcc_compl_poll(struct beiscsi_hba *phba, unsigned int tag);
+void be_mcc_notify(struct beiscsi_hba *phba, unsigned int tag);
+struct be_mcc_wrb *alloc_mcc_wrb(struct beiscsi_hba *phba,
+				 unsigned int *ref_tag);
+void beiscsi_process_async_event(struct beiscsi_hba *phba,
+				struct be_mcc_compl *compl);
+int beiscsi_process_mcc_compl(struct be_ctrl_info *ctrl,
+			      struct be_mcc_compl *compl);
+
 
 int be_mbox_notify(struct be_ctrl_info *ctrl);
 
@@ -777,8 +774,6 @@ int be_cmd_wrbq_create(struct be_ctrl_info *ctrl, struct be_dma_mem *q_mem,
 		       struct hwi_wrb_context *pwrb_context,
 		       uint8_t ulp_num);
 
-bool is_link_state_evt(u32 trailer);
-
 /* Configuration Functions */
 int be_cmd_set_vlan(struct beiscsi_hba *phba, uint16_t vlan_tag);
 
@@ -1137,6 +1132,21 @@ struct be_cmd_get_all_if_id_req {
 	u32 if_hndl_list[1];
 } __packed;
 
+struct be_cmd_get_port_name {
+	union {
+		struct be_cmd_req_hdr req_hdr;
+		struct be_cmd_resp_hdr resp_hdr;
+	} h;
+	union {
+		struct {
+			u32 reserved;
+		} req;
+		struct {
+			u32 port_names;
+		} resp;
+	} p;
+} __packed;
+
 #define ISCSI_OPCODE_SCSI_DATA_OUT		5
 #define OPCODE_COMMON_NTWK_LINK_STATUS_QUERY 5
 #define OPCODE_COMMON_MODIFY_EQ_DELAY		41
@@ -1367,5 +1377,5 @@ void be_wrb_hdr_prepare(struct be_mcc_wrb *wrb, int payload_len,
 void be_cmd_hdr_prepare(struct be_cmd_req_hdr *req_hdr,
 			u8 subsystem, u8 opcode, int cmd_len);
 
-void be2iscsi_fail_session(struct iscsi_cls_session *cls_session);
+void beiscsi_fail_session(struct iscsi_cls_session *cls_session);
 #endif /* !BEISCSI_CMDS_H */
diff --git a/drivers/scsi/be2iscsi/be_iscsi.c b/drivers/scsi/be2iscsi/be_iscsi.c
index 022e87b62e40..09f89a3eaa87 100644
--- a/drivers/scsi/be2iscsi/be_iscsi.c
+++ b/drivers/scsi/be2iscsi/be_iscsi.c
@@ -367,13 +367,14 @@ beiscsi_set_vlan_tag(struct Scsi_Host *shost,
 		      struct iscsi_iface_param_info *iface_param)
 {
 	struct beiscsi_hba *phba = iscsi_host_priv(shost);
-	int ret = 0;
+	int ret;
 
 	/* Get the Interface Handle */
-	if (mgmt_get_all_if_id(phba)) {
+	ret = mgmt_get_all_if_id(phba);
+	if (ret) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_CONFIG,
 			    "BS_%d : Getting Interface Handle Failed\n");
-		return -EIO;
+		return ret;
 	}
 
 	switch (iface_param->param) {
@@ -465,6 +466,10 @@ beiscsi_set_ipv6(struct Scsi_Host *shost,
 		ret = mgmt_set_ip(phba, iface_param, NULL,
 				  ISCSI_BOOTPROTO_STATIC);
 		break;
+	case ISCSI_NET_PARAM_VLAN_ENABLED:
+	case ISCSI_NET_PARAM_VLAN_TAG:
+		ret = beiscsi_set_vlan_tag(shost, iface_param);
+		break;
 	default:
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_CONFIG,
 			    "BS_%d : Param %d not supported\n",
@@ -730,7 +735,7 @@ static int beiscsi_get_initname(char *buf, struct beiscsi_hba *phba)
 		return -EBUSY;
 	}
 
-	rc = beiscsi_mccq_compl(phba, tag, &wrb, NULL);
+	rc = beiscsi_mccq_compl_wait(phba, tag, &wrb, NULL);
 	if (rc) {
 		beiscsi_log(phba, KERN_ERR,
 			    BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
@@ -753,7 +758,7 @@ static void beiscsi_get_port_state(struct Scsi_Host *shost)
 	struct beiscsi_hba *phba = iscsi_host_priv(shost);
 	struct iscsi_cls_host *ihost = shost->shost_data;
 
-	ihost->port_state = (phba->state == BE_ADAPTER_LINK_UP) ?
+	ihost->port_state = (phba->state & BE_ADAPTER_LINK_UP) ?
 		ISCSI_PORT_STATE_UP : ISCSI_PORT_STATE_DOWN;
 }
 
@@ -761,34 +766,13 @@ static void beiscsi_get_port_state(struct Scsi_Host *shost)
  * beiscsi_get_port_speed  - Get the Port Speed from Adapter
  * @shost : pointer to scsi_host structure
  *
- * returns Success/Failure
  */
-static int beiscsi_get_port_speed(struct Scsi_Host *shost)
+static void beiscsi_get_port_speed(struct Scsi_Host *shost)
 {
-	int rc;
-	unsigned int tag;
-	struct be_mcc_wrb *wrb;
-	struct be_cmd_ntwk_link_status_resp *resp;
 	struct beiscsi_hba *phba = iscsi_host_priv(shost);
 	struct iscsi_cls_host *ihost = shost->shost_data;
 
-	tag = be_cmd_get_port_speed(phba);
-	if (!tag) {
-		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_CONFIG,
-			    "BS_%d : Getting Port Speed Failed\n");
-
-		 return -EBUSY;
-	}
-	rc = beiscsi_mccq_compl(phba, tag, &wrb, NULL);
-	if (rc) {
-		beiscsi_log(phba, KERN_ERR,
-			    BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
-			    "BS_%d : Port Speed MBX Failed\n");
-		return rc;
-	}
-	resp = embedded_payload(wrb);
-
-	switch (resp->mac_speed) {
+	switch (phba->port_speed) {
 	case BE2ISCSI_LINK_SPEED_10MBPS:
 		ihost->port_speed = ISCSI_PORT_SPEED_10MBPS;
 		break;
@@ -801,10 +785,15 @@ static int beiscsi_get_port_speed(struct Scsi_Host *shost)
 	case BE2ISCSI_LINK_SPEED_10GBPS:
 		ihost->port_speed = ISCSI_PORT_SPEED_10GBPS;
 		break;
+	case BE2ISCSI_LINK_SPEED_25GBPS:
+		ihost->port_speed = ISCSI_PORT_SPEED_25GBPS;
+		break;
+	case BE2ISCSI_LINK_SPEED_40GBPS:
+		ihost->port_speed = ISCSI_PORT_SPEED_40GBPS;
+		break;
 	default:
 		ihost->port_speed = ISCSI_PORT_SPEED_UNKNOWN;
 	}
-	return 0;
 }
 
 /**
@@ -854,12 +843,7 @@ int beiscsi_get_host_param(struct Scsi_Host *shost,
 		status = sprintf(buf, "%s\n", iscsi_get_port_state_name(shost));
 		break;
 	case ISCSI_HOST_PARAM_PORT_SPEED:
-		status = beiscsi_get_port_speed(shost);
-		if (status) {
-			beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_CONFIG,
-				    "BS_%d : Retreiving Port Speed Failed\n");
-			return status;
-		}
+		beiscsi_get_port_speed(shost);
 		status = sprintf(buf, "%s\n", iscsi_get_port_speed_name(shost));
 		break;
 	default:
@@ -1159,7 +1143,7 @@ static int beiscsi_open_conn(struct iscsi_endpoint *ep,
 		return -EAGAIN;
 	}
 
-	ret = beiscsi_mccq_compl(phba, tag, NULL, &nonemb_cmd);
+	ret = beiscsi_mccq_compl_wait(phba, tag, NULL, &nonemb_cmd);
 	if (ret) {
 		beiscsi_log(phba, KERN_ERR,
 			    BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
@@ -1293,7 +1277,7 @@ static void beiscsi_flush_cq(struct beiscsi_hba *phba)
 	for (i = 0; i < phba->num_cpus; i++) {
 		pbe_eq = &phwi_context->be_eq[i];
 		irq_poll_disable(&pbe_eq->iopoll);
-		beiscsi_process_cq(pbe_eq);
+		beiscsi_process_cq(pbe_eq, BE2_MAX_NUM_CQ_PROC);
 		irq_poll_enable(&pbe_eq->iopoll);
 	}
 }
@@ -1318,7 +1302,7 @@ static int beiscsi_close_conn(struct  beiscsi_endpoint *beiscsi_ep, int flag)
 		ret = -EAGAIN;
 	}
 
-	ret = beiscsi_mccq_compl(phba, tag, NULL, NULL);
+	ret = beiscsi_mccq_compl_wait(phba, tag, NULL, NULL);
 
 	/* Flush the CQ entries */
 	beiscsi_flush_cq(phba);
@@ -1393,7 +1377,7 @@ void beiscsi_ep_disconnect(struct iscsi_endpoint *ep)
 			    beiscsi_ep->ep_cid);
 	}
 
-	beiscsi_mccq_compl(phba, tag, NULL, NULL);
+	beiscsi_mccq_compl_wait(phba, tag, NULL, NULL);
 	beiscsi_close_conn(beiscsi_ep, tcp_upload_flag);
 free_ep:
 	msleep(BEISCSI_LOGOUT_SYNC_DELAY);
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index cb9072a841be..f05e7737107d 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -29,6 +29,7 @@
 #include <linux/iscsi_boot_sysfs.h>
 #include <linux/module.h>
 #include <linux/bsg-lib.h>
+#include <linux/irq_poll.h>
 
 #include <scsi/libiscsi.h>
 #include <scsi/scsi_bsg_iscsi.h>
@@ -285,7 +286,7 @@ static int beiscsi_eh_abort(struct scsi_cmnd *sc)
 		return FAILED;
 	}
 
-	rc = beiscsi_mccq_compl(phba, tag, NULL, &nonemb_cmd);
+	rc = beiscsi_mccq_compl_wait(phba, tag, NULL, &nonemb_cmd);
 	if (rc != -EBUSY)
 		pci_free_consistent(phba->ctrl.pdev, nonemb_cmd.size,
 				    nonemb_cmd.va, nonemb_cmd.dma);
@@ -366,7 +367,7 @@ static int beiscsi_eh_device_reset(struct scsi_cmnd *sc)
 		return FAILED;
 	}
 
-	rc = beiscsi_mccq_compl(phba, tag, NULL, &nonemb_cmd);
+	rc = beiscsi_mccq_compl_wait(phba, tag, NULL, &nonemb_cmd);
 	if (rc != -EBUSY)
 		pci_free_consistent(phba->ctrl.pdev, nonemb_cmd.size,
 				    nonemb_cmd.va, nonemb_cmd.dma);
@@ -727,9 +728,8 @@ static int be_ctrl_init(struct beiscsi_hba *phba, struct pci_dev *pdev)
 	mbox_mem_align->va = PTR_ALIGN(mbox_mem_alloc->va, 16);
 	mbox_mem_align->dma = PTR_ALIGN(mbox_mem_alloc->dma, 16);
 	memset(mbox_mem_align->va, 0, sizeof(struct be_mcc_mailbox));
-	spin_lock_init(&ctrl->mbox_lock);
+	mutex_init(&ctrl->mbox_lock);
 	spin_lock_init(&phba->ctrl.mcc_lock);
-	spin_lock_init(&phba->ctrl.mcc_cq_lock);
 
 	return status;
 }
@@ -895,31 +895,17 @@ static irqreturn_t be_isr_mcc(int irq, void *dev_id)
 static irqreturn_t be_isr_msix(int irq, void *dev_id)
 {
 	struct beiscsi_hba *phba;
-	struct be_eq_entry *eqe = NULL;
 	struct be_queue_info *eq;
-	struct be_queue_info *cq;
-	unsigned int num_eq_processed;
 	struct be_eq_obj *pbe_eq;
 
 	pbe_eq = dev_id;
 	eq = &pbe_eq->q;
-	cq = pbe_eq->cq;
-	eqe = queue_tail_node(eq);
 
 	phba = pbe_eq->phba;
-	num_eq_processed = 0;
-	while (eqe->dw[offsetof(struct amap_eq_entry, valid) / 32]
-				& EQE_VALID_MASK) {
-		irq_poll_sched(&pbe_eq->iopoll);
 
-		AMAP_SET_BITS(struct amap_eq_entry, valid, eqe, 0);
-		queue_tail_inc(eq);
-		eqe = queue_tail_node(eq);
-		num_eq_processed++;
-	}
-
-	if (num_eq_processed)
-		hwi_ring_eq_db(phba, eq->id, 1,	num_eq_processed, 0, 1);
+	/* disable interrupt till iopoll completes */
+	hwi_ring_eq_db(phba, eq->id, 1,	0, 0, 1);
+	irq_poll_sched(&pbe_eq->iopoll);
 
 	return IRQ_HANDLED;
 }
@@ -996,6 +982,7 @@ static irqreturn_t be_isr(int irq, void *dev_id)
 		return IRQ_NONE;
 }
 
+
 static int beiscsi_init_irqs(struct beiscsi_hba *phba)
 {
 	struct pci_dev *pcidev = phba->pcidev;
@@ -1070,7 +1057,7 @@ free_msix_irqs:
 
 void hwi_ring_cq_db(struct beiscsi_hba *phba,
 			   unsigned int id, unsigned int num_processed,
-			   unsigned char rearm, unsigned char event)
+			   unsigned char rearm)
 {
 	u32 val = 0;
 
@@ -1145,6 +1132,7 @@ static struct sgl_handle *alloc_io_sgl_handle(struct beiscsi_hba *phba)
 {
 	struct sgl_handle *psgl_handle;
 
+	spin_lock_bh(&phba->io_sgl_lock);
 	if (phba->io_sgl_hndl_avbl) {
 		beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_IO,
 			    "BM_%d : In alloc_io_sgl_handle,"
@@ -1162,12 +1150,14 @@ static struct sgl_handle *alloc_io_sgl_handle(struct beiscsi_hba *phba)
 			phba->io_sgl_alloc_index++;
 	} else
 		psgl_handle = NULL;
+	spin_unlock_bh(&phba->io_sgl_lock);
 	return psgl_handle;
 }
 
 static void
 free_io_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
 {
+	spin_lock_bh(&phba->io_sgl_lock);
 	beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_IO,
 		    "BM_%d : In free_,io_sgl_free_index=%d\n",
 		    phba->io_sgl_free_index);
@@ -1182,6 +1172,7 @@ free_io_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
 			     "value there=%p\n", phba->io_sgl_free_index,
 			     phba->io_sgl_hndl_base
 			     [phba->io_sgl_free_index]);
+		 spin_unlock_bh(&phba->io_sgl_lock);
 		return;
 	}
 	phba->io_sgl_hndl_base[phba->io_sgl_free_index] = psgl_handle;
@@ -1190,6 +1181,25 @@ free_io_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
 		phba->io_sgl_free_index = 0;
 	else
 		phba->io_sgl_free_index++;
+	spin_unlock_bh(&phba->io_sgl_lock);
+}
+
+static inline struct wrb_handle *
+beiscsi_get_wrb_handle(struct hwi_wrb_context *pwrb_context,
+		       unsigned int wrbs_per_cxn)
+{
+	struct wrb_handle *pwrb_handle;
+
+	spin_lock_bh(&pwrb_context->wrb_lock);
+	pwrb_handle = pwrb_context->pwrb_handle_base[pwrb_context->alloc_index];
+	pwrb_context->wrb_handles_available--;
+	if (pwrb_context->alloc_index == (wrbs_per_cxn - 1))
+		pwrb_context->alloc_index = 0;
+	else
+		pwrb_context->alloc_index++;
+	spin_unlock_bh(&pwrb_context->wrb_lock);
+
+	return pwrb_handle;
 }
 
 /**
@@ -1201,30 +1211,32 @@ free_io_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
  * This happens under session_lock until submission to chip
  */
 struct wrb_handle *alloc_wrb_handle(struct beiscsi_hba *phba, unsigned int cid,
-				     struct hwi_wrb_context **pcontext)
+				    struct hwi_wrb_context **pcontext)
 {
 	struct hwi_wrb_context *pwrb_context;
 	struct hwi_controller *phwi_ctrlr;
-	struct wrb_handle *pwrb_handle;
 	uint16_t cri_index = BE_GET_CRI_FROM_CID(cid);
 
 	phwi_ctrlr = phba->phwi_ctrlr;
 	pwrb_context = &phwi_ctrlr->wrb_context[cri_index];
-	if (pwrb_context->wrb_handles_available >= 2) {
-		pwrb_handle = pwrb_context->pwrb_handle_base[
-					    pwrb_context->alloc_index];
-		pwrb_context->wrb_handles_available--;
-		if (pwrb_context->alloc_index ==
-						(phba->params.wrbs_per_cxn - 1))
-			pwrb_context->alloc_index = 0;
-		else
-			pwrb_context->alloc_index++;
+	/* return the context address */
+	*pcontext = pwrb_context;
+	return beiscsi_get_wrb_handle(pwrb_context, phba->params.wrbs_per_cxn);
+}
 
-		/* Return the context address */
-		*pcontext = pwrb_context;
-	} else
-		pwrb_handle = NULL;
-	return pwrb_handle;
+static inline void
+beiscsi_put_wrb_handle(struct hwi_wrb_context *pwrb_context,
+		       struct wrb_handle *pwrb_handle,
+		       unsigned int wrbs_per_cxn)
+{
+	spin_lock_bh(&pwrb_context->wrb_lock);
+	pwrb_context->pwrb_handle_base[pwrb_context->free_index] = pwrb_handle;
+	pwrb_context->wrb_handles_available++;
+	if (pwrb_context->free_index == (wrbs_per_cxn - 1))
+		pwrb_context->free_index = 0;
+	else
+		pwrb_context->free_index++;
+	spin_unlock_bh(&pwrb_context->wrb_lock);
 }
 
 /**
@@ -1239,13 +1251,9 @@ static void
 free_wrb_handle(struct beiscsi_hba *phba, struct hwi_wrb_context *pwrb_context,
 		struct wrb_handle *pwrb_handle)
 {
-	pwrb_context->pwrb_handle_base[pwrb_context->free_index] = pwrb_handle;
-	pwrb_context->wrb_handles_available++;
-	if (pwrb_context->free_index == (phba->params.wrbs_per_cxn - 1))
-		pwrb_context->free_index = 0;
-	else
-		pwrb_context->free_index++;
-
+	beiscsi_put_wrb_handle(pwrb_context,
+			       pwrb_handle,
+			       phba->params.wrbs_per_cxn);
 	beiscsi_log(phba, KERN_INFO,
 		    BEISCSI_LOG_IO | BEISCSI_LOG_CONFIG,
 		    "BM_%d : FREE WRB: pwrb_handle=%p free_index=0x%x"
@@ -1258,6 +1266,7 @@ static struct sgl_handle *alloc_mgmt_sgl_handle(struct beiscsi_hba *phba)
 {
 	struct sgl_handle *psgl_handle;
 
+	spin_lock_bh(&phba->mgmt_sgl_lock);
 	if (phba->eh_sgl_hndl_avbl) {
 		psgl_handle = phba->eh_sgl_hndl_base[phba->eh_sgl_alloc_index];
 		phba->eh_sgl_hndl_base[phba->eh_sgl_alloc_index] = NULL;
@@ -1275,13 +1284,14 @@ static struct sgl_handle *alloc_mgmt_sgl_handle(struct beiscsi_hba *phba)
 			phba->eh_sgl_alloc_index++;
 	} else
 		psgl_handle = NULL;
+	spin_unlock_bh(&phba->mgmt_sgl_lock);
 	return psgl_handle;
 }
 
 void
 free_mgmt_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
 {
-
+	spin_lock_bh(&phba->mgmt_sgl_lock);
 	beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_CONFIG,
 		    "BM_%d : In  free_mgmt_sgl_handle,"
 		    "eh_sgl_free_index=%d\n",
@@ -1296,6 +1306,7 @@ free_mgmt_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
 			    "BM_%d : Double Free in eh SGL ,"
 			    "eh_sgl_free_index=%d\n",
 			    phba->eh_sgl_free_index);
+		spin_unlock_bh(&phba->mgmt_sgl_lock);
 		return;
 	}
 	phba->eh_sgl_hndl_base[phba->eh_sgl_free_index] = psgl_handle;
@@ -1305,6 +1316,7 @@ free_mgmt_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
 		phba->eh_sgl_free_index = 0;
 	else
 		phba->eh_sgl_free_index++;
+	spin_unlock_bh(&phba->mgmt_sgl_lock);
 }
 
 static void
@@ -2029,7 +2041,7 @@ static void hwi_process_default_pdu_ring(struct beiscsi_conn *beiscsi_conn,
 			       phwi_ctrlr, cri_index));
 }
 
-static void  beiscsi_process_mcc_isr(struct beiscsi_hba *phba)
+void beiscsi_process_mcc_cq(struct beiscsi_hba *phba)
 {
 	struct be_queue_info *mcc_cq;
 	struct  be_mcc_compl *mcc_compl;
@@ -2039,31 +2051,15 @@ static void  beiscsi_process_mcc_isr(struct beiscsi_hba *phba)
 	mcc_compl = queue_tail_node(mcc_cq);
 	mcc_compl->flags = le32_to_cpu(mcc_compl->flags);
 	while (mcc_compl->flags & CQE_FLAGS_VALID_MASK) {
-
 		if (num_processed >= 32) {
 			hwi_ring_cq_db(phba, mcc_cq->id,
-					num_processed, 0, 0);
+					num_processed, 0);
 			num_processed = 0;
 		}
 		if (mcc_compl->flags & CQE_FLAGS_ASYNC_MASK) {
-			/* Interpret flags as an async trailer */
-			if (is_link_state_evt(mcc_compl->flags))
-				/* Interpret compl as a async link evt */
-				beiscsi_async_link_state_process(phba,
-				(struct be_async_event_link_state *) mcc_compl);
-			else {
-				beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_MBOX,
-					    "BM_%d :  Unsupported Async Event, flags"
-					    " = 0x%08x\n",
-					    mcc_compl->flags);
-				if (phba->state & BE_ADAPTER_LINK_UP) {
-					phba->state |= BE_ADAPTER_CHECK_BOOT;
-					phba->get_boot = BE_GET_BOOT_RETRIES;
-				}
-			}
+			beiscsi_process_async_event(phba, mcc_compl);
 		} else if (mcc_compl->flags & CQE_FLAGS_COMPLETED_MASK) {
-			be_mcc_compl_process_isr(&phba->ctrl, mcc_compl);
-			atomic_dec(&phba->ctrl.mcc_obj.q.used);
+			beiscsi_process_mcc_compl(&phba->ctrl, mcc_compl);
 		}
 
 		mcc_compl->flags = 0;
@@ -2074,24 +2070,24 @@ static void  beiscsi_process_mcc_isr(struct beiscsi_hba *phba)
 	}
 
 	if (num_processed > 0)
-		hwi_ring_cq_db(phba, mcc_cq->id, num_processed, 1, 0);
-
+		hwi_ring_cq_db(phba, mcc_cq->id, num_processed, 1);
 }
 
 /**
  * beiscsi_process_cq()- Process the Completion Queue
  * @pbe_eq: Event Q on which the Completion has come
+ * @budget: Max number of events to processed
  *
  * return
  *     Number of Completion Entries processed.
  **/
-unsigned int beiscsi_process_cq(struct be_eq_obj *pbe_eq)
+unsigned int beiscsi_process_cq(struct be_eq_obj *pbe_eq, int budget)
 {
 	struct be_queue_info *cq;
 	struct sol_cqe *sol;
 	struct dmsg_cqe *dmsg;
+	unsigned int total = 0;
 	unsigned int num_processed = 0;
-	unsigned int tot_nump = 0;
 	unsigned short code = 0, cid = 0;
 	uint16_t cri_index = 0;
 	struct beiscsi_conn *beiscsi_conn;
@@ -2142,12 +2138,12 @@ unsigned int beiscsi_process_cq(struct be_eq_obj *pbe_eq)
 		beiscsi_ep = ep->dd_data;
 		beiscsi_conn = beiscsi_ep->conn;
 
-		if (num_processed >= 32) {
-			hwi_ring_cq_db(phba, cq->id,
-					num_processed, 0, 0);
-			tot_nump += num_processed;
+		/* replenish cq */
+		if (num_processed == 32) {
+			hwi_ring_cq_db(phba, cq->id, 32, 0);
 			num_processed = 0;
 		}
+		total++;
 
 		switch (code) {
 		case SOL_CMD_COMPLETE:
@@ -2192,7 +2188,13 @@ unsigned int beiscsi_process_cq(struct be_eq_obj *pbe_eq)
 				    "BM_%d : Ignoring %s[%d] on CID : %d\n",
 				    cqe_desc[code], code, cid);
 			break;
+		case CXN_KILLED_HDR_DIGEST_ERR:
 		case SOL_CMD_KILLED_DATA_DIGEST_ERR:
+			beiscsi_log(phba, KERN_ERR,
+				    BEISCSI_LOG_CONFIG | BEISCSI_LOG_IO,
+				    "BM_%d : Cmd Notification %s[%d] on CID : %d\n",
+				    cqe_desc[code], code,  cid);
+			break;
 		case CMD_KILLED_INVALID_STATSN_RCVD:
 		case CMD_KILLED_INVALID_R2T_RCVD:
 		case CMD_CXN_KILLED_LUN_INVALID:
@@ -2218,7 +2220,6 @@ unsigned int beiscsi_process_cq(struct be_eq_obj *pbe_eq)
 		case CXN_KILLED_PDU_SIZE_EXCEEDS_DSL:
 		case CXN_KILLED_BURST_LEN_MISMATCH:
 		case CXN_KILLED_AHS_RCVD:
-		case CXN_KILLED_HDR_DIGEST_ERR:
 		case CXN_KILLED_UNKNOWN_HDR:
 		case CXN_KILLED_STALE_ITT_TTT_RCVD:
 		case CXN_KILLED_INVALID_ITT_TTT_RCVD:
@@ -2253,13 +2254,12 @@ proc_next_cqe:
 		queue_tail_inc(cq);
 		sol = queue_tail_node(cq);
 		num_processed++;
+		if (total == budget)
+			break;
 	}
 
-	if (num_processed > 0) {
-		tot_nump += num_processed;
-		hwi_ring_cq_db(phba, cq->id, num_processed, 1, 0);
-	}
-	return tot_nump;
+	hwi_ring_cq_db(phba, cq->id, num_processed, 1);
+	return total;
 }
 
 void beiscsi_process_all_cqs(struct work_struct *work)
@@ -2279,14 +2279,14 @@ void beiscsi_process_all_cqs(struct work_struct *work)
 		spin_lock_irqsave(&phba->isr_lock, flags);
 		pbe_eq->todo_mcc_cq = false;
 		spin_unlock_irqrestore(&phba->isr_lock, flags);
-		beiscsi_process_mcc_isr(phba);
+		beiscsi_process_mcc_cq(phba);
 	}
 
 	if (pbe_eq->todo_cq) {
 		spin_lock_irqsave(&phba->isr_lock, flags);
 		pbe_eq->todo_cq = false;
 		spin_unlock_irqrestore(&phba->isr_lock, flags);
-		beiscsi_process_cq(pbe_eq);
+		beiscsi_process_cq(pbe_eq, BE2_MAX_NUM_CQ_PROC);
 	}
 
 	/* rearm EQ for further interrupts */
@@ -2295,20 +2295,36 @@ void beiscsi_process_all_cqs(struct work_struct *work)
 
 static int be_iopoll(struct irq_poll *iop, int budget)
 {
-	unsigned int ret;
+	unsigned int ret, num_eq_processed;
 	struct beiscsi_hba *phba;
 	struct be_eq_obj *pbe_eq;
+	struct be_eq_entry *eqe = NULL;
+	struct be_queue_info *eq;
 
+	num_eq_processed = 0;
 	pbe_eq = container_of(iop, struct be_eq_obj, iopoll);
-	ret = beiscsi_process_cq(pbe_eq);
+	phba = pbe_eq->phba;
+	eq = &pbe_eq->q;
+	eqe = queue_tail_node(eq);
+
+	while (eqe->dw[offsetof(struct amap_eq_entry, valid) / 32] &
+			EQE_VALID_MASK) {
+		AMAP_SET_BITS(struct amap_eq_entry, valid, eqe, 0);
+		queue_tail_inc(eq);
+		eqe = queue_tail_node(eq);
+		num_eq_processed++;
+	}
+
+	hwi_ring_eq_db(phba, eq->id, 1, num_eq_processed, 0, 1);
+
+	ret = beiscsi_process_cq(pbe_eq, budget);
 	pbe_eq->cq_count += ret;
 	if (ret < budget) {
-		phba = pbe_eq->phba;
 		irq_poll_complete(iop);
 		beiscsi_log(phba, KERN_INFO,
 			    BEISCSI_LOG_CONFIG | BEISCSI_LOG_IO,
-			    "BM_%d : rearm pbe_eq->q.id =%d\n",
-			    pbe_eq->q.id);
+			    "BM_%d : rearm pbe_eq->q.id =%d ret %d\n",
+			    pbe_eq->q.id, ret);
 		hwi_ring_eq_db(phba, pbe_eq->q.id, 0, 0, 1, 1);
 	}
 	return ret;
@@ -2502,7 +2518,7 @@ hwi_write_sgl(struct iscsi_wrb *pwrb, struct scatterlist *sg,
  * @pwrb: ptr to the WRB entry
  * @task: iscsi task which is to be executed
  **/
-static void hwi_write_buffer(struct iscsi_wrb *pwrb, struct iscsi_task *task)
+static int hwi_write_buffer(struct iscsi_wrb *pwrb, struct iscsi_task *task)
 {
 	struct iscsi_sge *psgl;
 	struct beiscsi_io_task *io_task = task->dd_data;
@@ -2534,6 +2550,9 @@ static void hwi_write_buffer(struct iscsi_wrb *pwrb, struct iscsi_task *task)
 							     task->data,
 							     task->data_count,
 							     PCI_DMA_TODEVICE);
+			if (pci_dma_mapping_error(phba->pcidev,
+						  io_task->mtask_addr))
+				return -ENOMEM;
 			io_task->mtask_data_count = task->data_count;
 		} else
 			io_task->mtask_addr = 0;
@@ -2578,6 +2597,7 @@ static void hwi_write_buffer(struct iscsi_wrb *pwrb, struct iscsi_task *task)
 		AMAP_SET_BITS(struct amap_iscsi_sge, len, psgl, 0x106);
 	}
 	AMAP_SET_BITS(struct amap_iscsi_sge, last_sge, psgl, 1);
+	return 0;
 }
 
 /**
@@ -2706,8 +2726,10 @@ static int beiscsi_alloc_mem(struct beiscsi_hba *phba)
 	phwi_ctrlr->wrb_context = kzalloc(sizeof(struct hwi_wrb_context) *
 					  phba->params.cxns_per_ctrl,
 					  GFP_KERNEL);
-	if (!phwi_ctrlr->wrb_context)
+	if (!phwi_ctrlr->wrb_context) {
+		kfree(phba->phwi_ctrlr);
 		return -ENOMEM;
+	}
 
 	phba->init_mem = kcalloc(SE_MEM_MAX, sizeof(*mem_descr),
 				 GFP_KERNEL);
@@ -2904,6 +2926,7 @@ static int beiscsi_init_wrb_handle(struct beiscsi_hba *phba)
 			}
 			num_cxn_wrbh--;
 		}
+		spin_lock_init(&pwrb_context->wrb_lock);
 	}
 	idx = 0;
 	for (index = 0; index < phba->params.cxns_per_ctrl; index++) {
@@ -3866,6 +3889,8 @@ static int hwi_init_port(struct beiscsi_hba *phba)
 	phwi_context->min_eqd = 0;
 	phwi_context->cur_eqd = 0;
 	be_cmd_fw_initialize(&phba->ctrl);
+	/* set optic state to unknown */
+	phba->optic_state = 0xff;
 
 	status = beiscsi_create_eqs(phba, phwi_context);
 	if (status != 0) {
@@ -4384,7 +4409,7 @@ static int beiscsi_get_boot_info(struct beiscsi_hba *phba)
 		goto boot_freemem;
 	}
 
-	ret = beiscsi_mccq_compl(phba, tag, NULL, &nonemb_cmd);
+	ret = beiscsi_mccq_compl_wait(phba, tag, NULL, &nonemb_cmd);
 	if (ret) {
 		beiscsi_log(phba, KERN_ERR,
 			    BEISCSI_LOG_INIT | BEISCSI_LOG_CONFIG,
@@ -4468,6 +4493,7 @@ put_shost:
 	scsi_host_put(phba->shost);
 free_kset:
 	iscsi_boot_destroy_kset(phba->boot_kset);
+	phba->boot_kset = NULL;
 	return -ENOMEM;
 }
 
@@ -4607,11 +4633,9 @@ beiscsi_free_mgmt_task_handles(struct beiscsi_conn *beiscsi_conn,
 	}
 
 	if (io_task->psgl_handle) {
-		spin_lock_bh(&phba->mgmt_sgl_lock);
 		free_mgmt_sgl_handle(phba,
 				     io_task->psgl_handle);
 		io_task->psgl_handle = NULL;
-		spin_unlock_bh(&phba->mgmt_sgl_lock);
 	}
 
 	if (io_task->mtask_addr) {
@@ -4657,9 +4681,7 @@ static void beiscsi_cleanup_task(struct iscsi_task *task)
 		}
 
 		if (io_task->psgl_handle) {
-			spin_lock(&phba->io_sgl_lock);
 			free_io_sgl_handle(phba, io_task->psgl_handle);
-			spin_unlock(&phba->io_sgl_lock);
 			io_task->psgl_handle = NULL;
 		}
 
@@ -4714,6 +4736,20 @@ beiscsi_offload_connection(struct beiscsi_conn *beiscsi_conn,
 	doorbell |= 1 << DB_DEF_PDU_NUM_POSTED_SHIFT;
 	iowrite32(doorbell, phba->db_va +
 		  beiscsi_conn->doorbell_offset);
+
+	/*
+	 * There is no completion for CONTEXT_UPDATE. The completion of next
+	 * WRB posted guarantees FW's processing and DMA'ing of it.
+	 * Use beiscsi_put_wrb_handle to put it back in the pool which makes
+	 * sure zero'ing or reuse of the WRB only after wrbs_per_cxn.
+	 */
+	beiscsi_put_wrb_handle(pwrb_context, pwrb_handle,
+			       phba->params.wrbs_per_cxn);
+	beiscsi_log(phba, KERN_INFO,
+		    BEISCSI_LOG_IO | BEISCSI_LOG_CONFIG,
+		    "BM_%d : put CONTEXT_UPDATE pwrb_handle=%p free_index=0x%x wrb_handles_available=%d\n",
+		    pwrb_handle, pwrb_context->free_index,
+		    pwrb_context->wrb_handles_available);
 }
 
 static void beiscsi_parse_pdu(struct iscsi_conn *conn, itt_t itt,
@@ -4761,9 +4797,7 @@ static int beiscsi_alloc_pdu(struct iscsi_task *task, uint8_t opcode)
 	io_task->pwrb_handle = NULL;
 
 	if (task->sc) {
-		spin_lock(&phba->io_sgl_lock);
 		io_task->psgl_handle = alloc_io_sgl_handle(phba);
-		spin_unlock(&phba->io_sgl_lock);
 		if (!io_task->psgl_handle) {
 			beiscsi_log(phba, KERN_ERR,
 				    BEISCSI_LOG_IO | BEISCSI_LOG_CONFIG,
@@ -4788,10 +4822,8 @@ static int beiscsi_alloc_pdu(struct iscsi_task *task, uint8_t opcode)
 		if ((opcode & ISCSI_OPCODE_MASK) == ISCSI_OP_LOGIN) {
 			beiscsi_conn->task = task;
 			if (!beiscsi_conn->login_in_progress) {
-				spin_lock(&phba->mgmt_sgl_lock);
 				io_task->psgl_handle = (struct sgl_handle *)
 						alloc_mgmt_sgl_handle(phba);
-				spin_unlock(&phba->mgmt_sgl_lock);
 				if (!io_task->psgl_handle) {
 					beiscsi_log(phba, KERN_ERR,
 						    BEISCSI_LOG_IO |
@@ -4830,9 +4862,7 @@ static int beiscsi_alloc_pdu(struct iscsi_task *task, uint8_t opcode)
 						beiscsi_conn->plogin_wrb_handle;
 			}
 		} else {
-			spin_lock(&phba->mgmt_sgl_lock);
 			io_task->psgl_handle = alloc_mgmt_sgl_handle(phba);
-			spin_unlock(&phba->mgmt_sgl_lock);
 			if (!io_task->psgl_handle) {
 				beiscsi_log(phba, KERN_ERR,
 					    BEISCSI_LOG_IO |
@@ -4867,15 +4897,11 @@ static int beiscsi_alloc_pdu(struct iscsi_task *task, uint8_t opcode)
 	return 0;
 
 free_io_hndls:
-	spin_lock(&phba->io_sgl_lock);
 	free_io_sgl_handle(phba, io_task->psgl_handle);
-	spin_unlock(&phba->io_sgl_lock);
 	goto free_hndls;
 free_mgmt_hndls:
-	spin_lock(&phba->mgmt_sgl_lock);
 	free_mgmt_sgl_handle(phba, io_task->psgl_handle);
 	io_task->psgl_handle = NULL;
-	spin_unlock(&phba->mgmt_sgl_lock);
 free_hndls:
 	phwi_ctrlr = phba->phwi_ctrlr;
 	cri_index = BE_GET_CRI_FROM_CID(
@@ -4903,7 +4929,6 @@ int beiscsi_iotask_v2(struct iscsi_task *task, struct scatterlist *sg,
 
 	pwrb = io_task->pwrb_handle->pwrb;
 
-	io_task->cmd_bhs->iscsi_hdr.exp_statsn = 0;
 	io_task->bhs_len = sizeof(struct be_cmd_bhs);
 
 	if (writedir) {
@@ -4964,7 +4989,6 @@ static int beiscsi_iotask(struct iscsi_task *task, struct scatterlist *sg,
 	unsigned int doorbell = 0;
 
 	pwrb = io_task->pwrb_handle->pwrb;
-	io_task->cmd_bhs->iscsi_hdr.exp_statsn = 0;
 	io_task->bhs_len = sizeof(struct be_cmd_bhs);
 
 	if (writedir) {
@@ -5023,6 +5047,7 @@ static int beiscsi_mtask(struct iscsi_task *task)
 	unsigned int doorbell = 0;
 	unsigned int cid;
 	unsigned int pwrb_typeoffset = 0;
+	int ret = 0;
 
 	cid = beiscsi_conn->beiscsi_conn_cid;
 	pwrb = io_task->pwrb_handle->pwrb;
@@ -5071,7 +5096,7 @@ static int beiscsi_mtask(struct iscsi_task *task)
 	case ISCSI_OP_LOGIN:
 		AMAP_SET_BITS(struct amap_iscsi_wrb, cmdsn_itt, pwrb, 1);
 		ADAPTER_SET_WRB_TYPE(pwrb, TGT_DM_CMD, pwrb_typeoffset);
-		hwi_write_buffer(pwrb, task);
+		ret = hwi_write_buffer(pwrb, task);
 		break;
 	case ISCSI_OP_NOOP_OUT:
 		if (task->hdr->ttt != ISCSI_RESERVED_TAG) {
@@ -5091,19 +5116,19 @@ static int beiscsi_mtask(struct iscsi_task *task)
 				AMAP_SET_BITS(struct amap_iscsi_wrb_v2,
 					      dmsg, pwrb, 0);
 		}
-		hwi_write_buffer(pwrb, task);
+		ret = hwi_write_buffer(pwrb, task);
 		break;
 	case ISCSI_OP_TEXT:
 		ADAPTER_SET_WRB_TYPE(pwrb, TGT_DM_CMD, pwrb_typeoffset);
-		hwi_write_buffer(pwrb, task);
+		ret = hwi_write_buffer(pwrb, task);
 		break;
 	case ISCSI_OP_SCSI_TMFUNC:
 		ADAPTER_SET_WRB_TYPE(pwrb, INI_TMF_CMD, pwrb_typeoffset);
-		hwi_write_buffer(pwrb, task);
+		ret = hwi_write_buffer(pwrb, task);
 		break;
 	case ISCSI_OP_LOGOUT:
 		ADAPTER_SET_WRB_TYPE(pwrb, HWH_TYPE_LOGOUT, pwrb_typeoffset);
-		hwi_write_buffer(pwrb, task);
+		ret = hwi_write_buffer(pwrb, task);
 		break;
 
 	default:
@@ -5114,6 +5139,9 @@ static int beiscsi_mtask(struct iscsi_task *task)
 		return -EINVAL;
 	}
 
+	if (ret)
+		return ret;
+
 	/* Set the task type */
 	io_task->wrb_type = (is_chip_be2_be3r(phba)) ?
 		AMAP_GET_BITS(struct amap_iscsi_wrb, type, pwrb) :
@@ -5132,23 +5160,21 @@ static int beiscsi_task_xmit(struct iscsi_task *task)
 {
 	struct beiscsi_io_task *io_task = task->dd_data;
 	struct scsi_cmnd *sc = task->sc;
-	struct beiscsi_hba *phba = NULL;
+	struct beiscsi_hba *phba;
 	struct scatterlist *sg;
 	int num_sg;
 	unsigned int  writedir = 0, xferlen = 0;
 
-	phba = ((struct beiscsi_conn *)task->conn->dd_data)->phba;
+	if (!io_task->conn->login_in_progress)
+		task->hdr->exp_statsn = 0;
 
 	if (!sc)
 		return beiscsi_mtask(task);
 
 	io_task->scsi_cmnd = sc;
 	num_sg = scsi_dma_map(sc);
+	phba = io_task->conn->phba;
 	if (num_sg < 0) {
-		struct iscsi_conn *conn = task->conn;
-		struct beiscsi_hba *phba = NULL;
-
-		phba = ((struct beiscsi_conn *)conn->dd_data)->phba;
 		beiscsi_log(phba, KERN_ERR,
 			    BEISCSI_LOG_IO | BEISCSI_LOG_ISCSI,
 			    "BM_%d : scsi_dma_map Failed "
@@ -5211,12 +5237,13 @@ static int beiscsi_bsg_request(struct bsg_job *job)
 
 		rc = wait_event_interruptible_timeout(
 					phba->ctrl.mcc_wait[tag],
-					phba->ctrl.mcc_numtag[tag],
+					phba->ctrl.mcc_tag_status[tag],
 					msecs_to_jiffies(
 					BEISCSI_HOST_MBX_TIMEOUT));
-		extd_status = (phba->ctrl.mcc_numtag[tag] & 0x0000FF00) >> 8;
-		status = phba->ctrl.mcc_numtag[tag] & 0x000000FF;
-		free_mcc_tag(&phba->ctrl, tag);
+		extd_status = (phba->ctrl.mcc_tag_status[tag] &
+			       CQE_STATUS_ADDL_MASK) >> CQE_STATUS_ADDL_SHIFT;
+		status = phba->ctrl.mcc_tag_status[tag] & CQE_STATUS_MASK;
+		free_mcc_wrb(&phba->ctrl, tag);
 		resp = (struct be_cmd_resp_hdr *)nonemb_cmd.va;
 		sg_copy_from_buffer(job->reply_payload.sg_list,
 				    job->reply_payload.sg_cnt,
@@ -5277,15 +5304,12 @@ static void beiscsi_quiesce(struct beiscsi_hba *phba,
 	if (phba->msix_enabled) {
 		for (i = 0; i <= phba->num_cpus; i++) {
 			msix_vec = phba->msix_entries[i].vector;
-			synchronize_irq(msix_vec);
 			free_irq(msix_vec, &phwi_context->be_eq[i]);
 			kfree(phba->msi_name[i]);
 		}
 	} else
-		if (phba->pcidev->irq) {
-			synchronize_irq(phba->pcidev->irq);
+		if (phba->pcidev->irq)
 			free_irq(phba->pcidev->irq, phba);
-		}
 	pci_disable_msix(phba->pcidev);
 	cancel_delayed_work_sync(&phba->beiscsi_hw_check_task);
 
@@ -5313,7 +5337,6 @@ static void beiscsi_quiesce(struct beiscsi_hba *phba,
 
 static void beiscsi_remove(struct pci_dev *pcidev)
 {
-
 	struct beiscsi_hba *phba = NULL;
 
 	phba = pci_get_drvdata(pcidev);
@@ -5323,9 +5346,9 @@ static void beiscsi_remove(struct pci_dev *pcidev)
 	}
 
 	beiscsi_destroy_def_ifaces(phba);
-	beiscsi_quiesce(phba, BEISCSI_CLEAN_UNLOAD);
 	iscsi_boot_destroy_kset(phba->boot_kset);
 	iscsi_host_remove(phba->shost);
+	beiscsi_quiesce(phba, BEISCSI_CLEAN_UNLOAD);
 	pci_dev_put(phba->pcidev);
 	iscsi_host_free(phba->shost);
 	pci_disable_pcie_error_reporting(pcidev);
@@ -5334,23 +5357,6 @@ static void beiscsi_remove(struct pci_dev *pcidev)
 	pci_disable_device(pcidev);
 }
 
-static void beiscsi_shutdown(struct pci_dev *pcidev)
-{
-
-	struct beiscsi_hba *phba = NULL;
-
-	phba = (struct beiscsi_hba *)pci_get_drvdata(pcidev);
-	if (!phba) {
-		dev_err(&pcidev->dev, "beiscsi_shutdown called with no phba\n");
-		return;
-	}
-
-	phba->state = BE_ADAPTER_STATE_SHUTDOWN;
-	iscsi_host_for_each_session(phba->shost, be2iscsi_fail_session);
-	beiscsi_quiesce(phba, BEISCSI_CLEAN_UNLOAD);
-	pci_disable_device(pcidev);
-}
-
 static void beiscsi_msix_enable(struct beiscsi_hba *phba)
 {
 	int i, status;
@@ -5413,7 +5419,7 @@ static void be_eqd_update(struct beiscsi_hba *phba)
 	if (num) {
 		tag = be_cmd_modify_eq_delay(phba, set_eqd, num);
 		if (tag)
-			beiscsi_mccq_compl(phba, tag, NULL, NULL);
+			beiscsi_mccq_compl_wait(phba, tag, NULL, NULL);
 	}
 }
 
@@ -5564,11 +5570,17 @@ static void beiscsi_eeh_resume(struct pci_dev *pdev)
 	phba->shost->max_id = phba->params.cxns_per_ctrl;
 	phba->shost->can_queue = phba->params.ios_per_ctrl;
 	ret = hwi_init_controller(phba);
+	if (ret) {
+		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
+			    "BM_%d : beiscsi_eeh_resume -"
+			     "Failed to initialize beiscsi_hba.\n");
+		goto ret_err;
+	}
 
 	for (i = 0; i < MAX_MCC_CMD; i++) {
 		init_waitqueue_head(&phba->ctrl.mcc_wait[i + 1]);
 		phba->ctrl.mcc_tag[i] = i + 1;
-		phba->ctrl.mcc_numtag[i + 1] = 0;
+		phba->ctrl.mcc_tag_status[i + 1] = 0;
 		phba->ctrl.mcc_tag_available++;
 	}
 
@@ -5670,6 +5682,9 @@ static int beiscsi_dev_probe(struct pci_dev *pcidev,
 		goto hba_free;
 	}
 
+	/*
+	 * FUNCTION_RESET should clean up any stale info in FW for this fn
+	 */
 	ret = beiscsi_cmd_reset_function(phba);
 	if (ret) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
@@ -5693,6 +5708,8 @@ static int beiscsi_dev_probe(struct pci_dev *pcidev,
 			    "BM_%d : Error getting fw config\n");
 		goto free_port;
 	}
+	mgmt_get_port_name(&phba->ctrl, phba);
+	beiscsi_get_params(phba);
 
 	if (enable_msix)
 		find_num_cpus(phba);
@@ -5710,7 +5727,6 @@ static int beiscsi_dev_probe(struct pci_dev *pcidev,
 	}
 
 	phba->shost->max_id = phba->params.cxns_per_ctrl;
-	beiscsi_get_params(phba);
 	phba->shost->can_queue = phba->params.ios_per_ctrl;
 	ret = beiscsi_init_port(phba);
 	if (ret < 0) {
@@ -5723,7 +5739,7 @@ static int beiscsi_dev_probe(struct pci_dev *pcidev,
 	for (i = 0; i < MAX_MCC_CMD; i++) {
 		init_waitqueue_head(&phba->ctrl.mcc_wait[i + 1]);
 		phba->ctrl.mcc_tag[i] = i + 1;
-		phba->ctrl.mcc_numtag[i + 1] = 0;
+		phba->ctrl.mcc_tag_status[i + 1] = 0;
 		phba->ctrl.mcc_tag_available++;
 		memset(&phba->ctrl.ptag_state[i].tag_mem_state, 0,
 		       sizeof(struct be_dma_mem));
@@ -5857,7 +5873,6 @@ static struct pci_driver beiscsi_pci_driver = {
 	.name = DRV_NAME,
 	.probe = beiscsi_dev_probe,
 	.remove = beiscsi_remove,
-	.shutdown = beiscsi_shutdown,
 	.id_table = beiscsi_pci_id_table,
 	.err_handler = &beiscsi_eeh_handlers
 };
diff --git a/drivers/scsi/be2iscsi/be_main.h b/drivers/scsi/be2iscsi/be_main.h
index 5c67c0732241..30a4606d9a3b 100644
--- a/drivers/scsi/be2iscsi/be_main.h
+++ b/drivers/scsi/be2iscsi/be_main.h
@@ -36,7 +36,7 @@
 #include <scsi/scsi_transport_iscsi.h>
 
 #define DRV_NAME		"be2iscsi"
-#define BUILD_STR		"10.6.0.1"
+#define BUILD_STR		"11.0.0.0"
 #define BE_NAME			"Emulex OneConnect" \
 				"Open-iSCSI Driver version" BUILD_STR
 #define DRV_DESC		BE_NAME " " "Driver"
@@ -63,6 +63,7 @@
 #define BE2_SGE			32
 #define BE2_DEFPDU_HDR_SZ	64
 #define BE2_DEFPDU_DATA_SZ	8192
+#define BE2_MAX_NUM_CQ_PROC	512
 
 #define MAX_CPUS		64
 #define BEISCSI_MAX_NUM_CPUS	7
@@ -103,8 +104,7 @@
 #define BE_ADAPTER_LINK_UP	0x001
 #define BE_ADAPTER_LINK_DOWN	0x002
 #define BE_ADAPTER_PCI_ERR	0x004
-#define BE_ADAPTER_STATE_SHUTDOWN	0x008
-#define BE_ADAPTER_CHECK_BOOT	0x010
+#define BE_ADAPTER_CHECK_BOOT	0x008
 
 
 #define BEISCSI_CLEAN_UNLOAD	0x01
@@ -304,6 +304,7 @@ struct invalidate_command_table {
 #define BEISCSI_GET_ULP_FROM_CRI(phwi_ctrlr, cri) \
 	(phwi_ctrlr->wrb_context[cri].ulp_num)
 struct hwi_wrb_context {
+	spinlock_t wrb_lock;
 	struct list_head wrb_handle_list;
 	struct list_head wrb_handle_drvr_list;
 	struct wrb_handle **pwrb_handle_base;
@@ -398,7 +399,9 @@ struct beiscsi_hba {
 		 * group together since they are used most frequently
 		 * for cid to cri conversion
 		 */
+#define BEISCSI_PHYS_PORT_MAX	4
 		unsigned int phys_port;
+		/* valid values of phys_port id are 0, 1, 2, 3 */
 		unsigned int eqid_count;
 		unsigned int cqid_count;
 		unsigned int iscsi_cid_start[BEISCSI_ULP_COUNT];
@@ -416,6 +419,7 @@ struct beiscsi_hba {
 	} fw_config;
 
 	unsigned int state;
+	u8 optic_state;
 	int get_boot;
 	bool fw_timeout;
 	bool ue_detected;
@@ -423,6 +427,8 @@ struct beiscsi_hba {
 
 	bool mac_addr_set;
 	u8 mac_address[ETH_ALEN];
+	u8 port_name;
+	u8 port_speed;
 	char fw_ver_str[BEISCSI_VER_STRLEN];
 	char wq_name[20];
 	struct workqueue_struct *wq;	/* The actuak work queue */
@@ -845,9 +851,10 @@ void beiscsi_free_mgmt_task_handles(struct beiscsi_conn *beiscsi_conn,
 
 void hwi_ring_cq_db(struct beiscsi_hba *phba,
 		     unsigned int id, unsigned int num_processed,
-		     unsigned char rearm, unsigned char event);
+		     unsigned char rearm);
 
-unsigned int beiscsi_process_cq(struct be_eq_obj *pbe_eq);
+unsigned int beiscsi_process_cq(struct be_eq_obj *pbe_eq, int budget);
+void beiscsi_process_mcc_cq(struct beiscsi_hba *phba);
 
 static inline bool beiscsi_error(struct beiscsi_hba *phba)
 {
@@ -1074,12 +1081,14 @@ struct hwi_context_memory {
 #define BEISCSI_LOG_CONFIG	0x0020	/* CONFIG Code Path */
 #define BEISCSI_LOG_ISCSI	0x0040	/* SCSI/iSCSI Protocol related Logs */
 
+#define __beiscsi_log(phba, level, fmt, arg...) \
+	shost_printk(level, phba->shost, fmt, __LINE__, ##arg)
+
 #define beiscsi_log(phba, level, mask, fmt, arg...) \
 do { \
 	uint32_t log_value = phba->attr_log_enable; \
 		if (((mask) & log_value) || (level[1] <= '3')) \
-			shost_printk(level, phba->shost, \
-				     fmt, __LINE__, ##arg); \
-} while (0)
+			__beiscsi_log(phba, level, fmt, ##arg); \
+} while (0);
 
 #endif
diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c
index aea3e6b9477d..83926e221f1e 100644
--- a/drivers/scsi/be2iscsi/be_mgmt.c
+++ b/drivers/scsi/be2iscsi/be_mgmt.c
@@ -161,20 +161,17 @@ int be_cmd_modify_eq_delay(struct beiscsi_hba *phba,
 	struct be_ctrl_info *ctrl = &phba->ctrl;
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_modify_eq_delay *req;
-	unsigned int tag = 0;
+	unsigned int tag;
 	int i;
 
-	spin_lock(&ctrl->mbox_lock);
-	tag = alloc_mcc_tag(phba);
-	if (!tag) {
-		spin_unlock(&ctrl->mbox_lock);
-		return tag;
+	mutex_lock(&ctrl->mbox_lock);
+	wrb = alloc_mcc_wrb(phba, &tag);
+	if (!wrb) {
+		mutex_unlock(&ctrl->mbox_lock);
+		return 0;
 	}
 
-	wrb = wrb_from_mccq(phba);
 	req = embedded_payload(wrb);
-
-	wrb->tag0 |= tag;
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
 		OPCODE_COMMON_MODIFY_EQ_DELAY, sizeof(*req));
@@ -187,8 +184,8 @@ int be_cmd_modify_eq_delay(struct beiscsi_hba *phba,
 				cpu_to_le32(set_eqd[i].delay_multiplier);
 	}
 
-	be_mcc_notify(phba);
-	spin_unlock(&ctrl->mbox_lock);
+	be_mcc_notify(phba, tag);
+	mutex_unlock(&ctrl->mbox_lock);
 	return tag;
 }
 
@@ -209,22 +206,20 @@ unsigned int mgmt_reopen_session(struct beiscsi_hba *phba,
 	struct be_ctrl_info *ctrl = &phba->ctrl;
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_reopen_session_req *req;
-	unsigned int tag = 0;
+	unsigned int tag;
 
 	beiscsi_log(phba, KERN_INFO,
 		    BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
 		    "BG_%d : In bescsi_get_boot_target\n");
 
-	spin_lock(&ctrl->mbox_lock);
-	tag = alloc_mcc_tag(phba);
-	if (!tag) {
-		spin_unlock(&ctrl->mbox_lock);
-		return tag;
+	mutex_lock(&ctrl->mbox_lock);
+	wrb = alloc_mcc_wrb(phba, &tag);
+	if (!wrb) {
+		mutex_unlock(&ctrl->mbox_lock);
+		return 0;
 	}
 
-	wrb = wrb_from_mccq(phba);
 	req = embedded_payload(wrb);
-	wrb->tag0 |= tag;
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI_INI,
 			   OPCODE_ISCSI_INI_DRIVER_REOPEN_ALL_SESSIONS,
@@ -234,8 +229,8 @@ unsigned int mgmt_reopen_session(struct beiscsi_hba *phba,
 	req->reopen_type = reopen_type;
 	req->session_handle = sess_handle;
 
-	be_mcc_notify(phba);
-	spin_unlock(&ctrl->mbox_lock);
+	be_mcc_notify(phba, tag);
+	mutex_unlock(&ctrl->mbox_lock);
 	return tag;
 }
 
@@ -244,29 +239,27 @@ unsigned int mgmt_get_boot_target(struct beiscsi_hba *phba)
 	struct be_ctrl_info *ctrl = &phba->ctrl;
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_get_boot_target_req *req;
-	unsigned int tag = 0;
+	unsigned int tag;
 
 	beiscsi_log(phba, KERN_INFO,
 		    BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
 		    "BG_%d : In bescsi_get_boot_target\n");
 
-	spin_lock(&ctrl->mbox_lock);
-	tag = alloc_mcc_tag(phba);
-	if (!tag) {
-		spin_unlock(&ctrl->mbox_lock);
-		return tag;
+	mutex_lock(&ctrl->mbox_lock);
+	wrb = alloc_mcc_wrb(phba, &tag);
+	if (!wrb) {
+		mutex_unlock(&ctrl->mbox_lock);
+		return 0;
 	}
 
-	wrb = wrb_from_mccq(phba);
 	req = embedded_payload(wrb);
-	wrb->tag0 |= tag;
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI_INI,
 			   OPCODE_ISCSI_INI_BOOT_GET_BOOT_TARGET,
 			   sizeof(struct be_cmd_get_boot_target_resp));
 
-	be_mcc_notify(phba);
-	spin_unlock(&ctrl->mbox_lock);
+	be_mcc_notify(phba, tag);
+	mutex_unlock(&ctrl->mbox_lock);
 	return tag;
 }
 
@@ -276,7 +269,7 @@ unsigned int mgmt_get_session_info(struct beiscsi_hba *phba,
 {
 	struct be_ctrl_info *ctrl = &phba->ctrl;
 	struct be_mcc_wrb *wrb;
-	unsigned int tag = 0;
+	unsigned int tag;
 	struct  be_cmd_get_session_req *req;
 	struct be_cmd_get_session_resp *resp;
 	struct be_sge *sge;
@@ -285,22 +278,17 @@ unsigned int mgmt_get_session_info(struct beiscsi_hba *phba,
 		    BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
 		    "BG_%d : In beiscsi_get_session_info\n");
 
-	spin_lock(&ctrl->mbox_lock);
-	tag = alloc_mcc_tag(phba);
-	if (!tag) {
-		spin_unlock(&ctrl->mbox_lock);
-		return tag;
+	mutex_lock(&ctrl->mbox_lock);
+	wrb = alloc_mcc_wrb(phba, &tag);
+	if (!wrb) {
+		mutex_unlock(&ctrl->mbox_lock);
+		return 0;
 	}
 
 	nonemb_cmd->size = sizeof(*resp);
 	req = nonemb_cmd->va;
 	memset(req, 0, sizeof(*req));
-	wrb = wrb_from_mccq(phba);
 	sge = nonembedded_sgl(wrb);
-	wrb->tag0 |= tag;
-
-
-	wrb->tag0 |= tag;
 	be_wrb_hdr_prepare(wrb, sizeof(*req), false, 1);
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI_INI,
 			   OPCODE_ISCSI_INI_SESSION_GET_A_SESSION,
@@ -310,12 +298,54 @@ unsigned int mgmt_get_session_info(struct beiscsi_hba *phba,
 	sge->pa_lo = cpu_to_le32(nonemb_cmd->dma & 0xFFFFFFFF);
 	sge->len = cpu_to_le32(nonemb_cmd->size);
 
-	be_mcc_notify(phba);
-	spin_unlock(&ctrl->mbox_lock);
+	be_mcc_notify(phba, tag);
+	mutex_unlock(&ctrl->mbox_lock);
 	return tag;
 }
 
 /**
+ * mgmt_get_port_name()- Get port name for the function
+ * @ctrl: ptr to Ctrl Info
+ * @phba: ptr to the dev priv structure
+ *
+ * Get the alphanumeric character for port
+ *
+ **/
+int mgmt_get_port_name(struct be_ctrl_info *ctrl,
+		       struct beiscsi_hba *phba)
+{
+	int ret = 0;
+	struct be_mcc_wrb *wrb;
+	struct be_cmd_get_port_name *ioctl;
+
+	mutex_lock(&ctrl->mbox_lock);
+	wrb = wrb_from_mbox(&ctrl->mbox_mem);
+	memset(wrb, 0, sizeof(*wrb));
+	ioctl = embedded_payload(wrb);
+
+	be_wrb_hdr_prepare(wrb, sizeof(*ioctl), true, 0);
+	be_cmd_hdr_prepare(&ioctl->h.req_hdr, CMD_SUBSYSTEM_COMMON,
+			   OPCODE_COMMON_GET_PORT_NAME,
+			   EMBED_MBX_MAX_PAYLOAD_SIZE);
+	ret = be_mbox_notify(ctrl);
+	phba->port_name = 0;
+	if (!ret) {
+		phba->port_name = ioctl->p.resp.port_names >>
+				  (phba->fw_config.phys_port * 8) & 0xff;
+	} else {
+		beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_INIT,
+			    "BG_%d : GET_PORT_NAME ret 0x%x status 0x%x\n",
+			    ret, ioctl->h.resp_hdr.status);
+	}
+
+	if (phba->port_name == 0)
+		phba->port_name = '?';
+
+	mutex_unlock(&ctrl->mbox_lock);
+	return ret;
+}
+
+/**
  * mgmt_get_fw_config()- Get the FW config for the function
  * @ctrl: ptr to Ctrl Info
  * @phba: ptr to the dev priv structure
@@ -331,91 +361,147 @@ int mgmt_get_fw_config(struct be_ctrl_info *ctrl,
 				struct beiscsi_hba *phba)
 {
 	struct be_mcc_wrb *wrb = wrb_from_mbox(&ctrl->mbox_mem);
-	struct be_fw_cfg *req = embedded_payload(wrb);
-	int status = 0;
+	struct be_fw_cfg *pfw_cfg = embedded_payload(wrb);
+	uint32_t cid_count, icd_count;
+	int status = -EINVAL;
+	uint8_t ulp_num = 0;
 
-	spin_lock(&ctrl->mbox_lock);
+	mutex_lock(&ctrl->mbox_lock);
 	memset(wrb, 0, sizeof(*wrb));
+	be_wrb_hdr_prepare(wrb, sizeof(*pfw_cfg), true, 0);
 
-	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
-
-	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
+	be_cmd_hdr_prepare(&pfw_cfg->hdr, CMD_SUBSYSTEM_COMMON,
 			   OPCODE_COMMON_QUERY_FIRMWARE_CONFIG,
 			   EMBED_MBX_MAX_PAYLOAD_SIZE);
-	status = be_mbox_notify(ctrl);
-	if (!status) {
-		uint8_t ulp_num = 0;
-		struct be_fw_cfg *pfw_cfg;
-		pfw_cfg = req;
 
-		if (!is_chip_be2_be3r(phba)) {
-			phba->fw_config.eqid_count = pfw_cfg->eqid_count;
-			phba->fw_config.cqid_count = pfw_cfg->cqid_count;
+	if (be_mbox_notify(ctrl)) {
+		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
+			    "BG_%d : Failed in mgmt_get_fw_config\n");
+		goto fail_init;
+	}
 
-			beiscsi_log(phba, KERN_INFO,
-				    BEISCSI_LOG_INIT,
-				    "BG_%d : EQ_Count : %d CQ_Count : %d\n",
-				    phba->fw_config.eqid_count,
+	/* FW response formats depend on port id */
+	phba->fw_config.phys_port = pfw_cfg->phys_port;
+	if (phba->fw_config.phys_port >= BEISCSI_PHYS_PORT_MAX) {
+		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
+			    "BG_%d : invalid physical port id %d\n",
+			    phba->fw_config.phys_port);
+		goto fail_init;
+	}
+
+	/* populate and check FW config against min and max values */
+	if (!is_chip_be2_be3r(phba)) {
+		phba->fw_config.eqid_count = pfw_cfg->eqid_count;
+		phba->fw_config.cqid_count = pfw_cfg->cqid_count;
+		if (phba->fw_config.eqid_count == 0 ||
+		    phba->fw_config.eqid_count > 2048) {
+			beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
+				    "BG_%d : invalid EQ count %d\n",
+				    phba->fw_config.eqid_count);
+			goto fail_init;
+		}
+		if (phba->fw_config.cqid_count == 0 ||
+		    phba->fw_config.cqid_count > 4096) {
+			beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
+				    "BG_%d : invalid CQ count %d\n",
 				    phba->fw_config.cqid_count);
+			goto fail_init;
 		}
+		beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_INIT,
+			    "BG_%d : EQ_Count : %d CQ_Count : %d\n",
+			    phba->fw_config.eqid_count,
+			    phba->fw_config.cqid_count);
+	}
 
-		for (ulp_num = 0; ulp_num < BEISCSI_ULP_COUNT; ulp_num++)
-			if (pfw_cfg->ulp[ulp_num].ulp_mode &
-			    BEISCSI_ULP_ISCSI_INI_MODE)
-				set_bit(ulp_num,
-				&phba->fw_config.ulp_supported);
-
-		phba->fw_config.phys_port = pfw_cfg->phys_port;
-		for (ulp_num = 0; ulp_num < BEISCSI_ULP_COUNT; ulp_num++) {
-			if (test_bit(ulp_num, &phba->fw_config.ulp_supported)) {
-
-				phba->fw_config.iscsi_cid_start[ulp_num] =
-					pfw_cfg->ulp[ulp_num].sq_base;
-				phba->fw_config.iscsi_cid_count[ulp_num] =
-					pfw_cfg->ulp[ulp_num].sq_count;
-
-				phba->fw_config.iscsi_icd_start[ulp_num] =
-					pfw_cfg->ulp[ulp_num].icd_base;
-				phba->fw_config.iscsi_icd_count[ulp_num] =
-					pfw_cfg->ulp[ulp_num].icd_count;
-
-				phba->fw_config.iscsi_chain_start[ulp_num] =
-					pfw_cfg->chain_icd[ulp_num].chain_base;
-				phba->fw_config.iscsi_chain_count[ulp_num] =
-					pfw_cfg->chain_icd[ulp_num].chain_count;
-
-				beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_INIT,
-					    "BG_%d : Function loaded on ULP : %d\n"
-					    "\tiscsi_cid_count : %d\n"
-					    "\tiscsi_cid_start : %d\n"
-					    "\t iscsi_icd_count : %d\n"
-					    "\t iscsi_icd_start : %d\n",
-					    ulp_num,
-					    phba->fw_config.
-					    iscsi_cid_count[ulp_num],
-					    phba->fw_config.
-					    iscsi_cid_start[ulp_num],
-					    phba->fw_config.
-					    iscsi_icd_count[ulp_num],
-					    phba->fw_config.
-					    iscsi_icd_start[ulp_num]);
-			}
+	/**
+	 * Check on which all ULP iSCSI Protocol is loaded.
+	 * Set the Bit for those ULP. This set flag is used
+	 * at all places in the code to check on which ULP
+	 * iSCSi Protocol is loaded
+	 **/
+	for (ulp_num = 0; ulp_num < BEISCSI_ULP_COUNT; ulp_num++) {
+		if (pfw_cfg->ulp[ulp_num].ulp_mode &
+		    BEISCSI_ULP_ISCSI_INI_MODE) {
+			set_bit(ulp_num, &phba->fw_config.ulp_supported);
+
+			/* Get the CID, ICD and Chain count for each ULP */
+			phba->fw_config.iscsi_cid_start[ulp_num] =
+				pfw_cfg->ulp[ulp_num].sq_base;
+			phba->fw_config.iscsi_cid_count[ulp_num] =
+				pfw_cfg->ulp[ulp_num].sq_count;
+
+			phba->fw_config.iscsi_icd_start[ulp_num] =
+				pfw_cfg->ulp[ulp_num].icd_base;
+			phba->fw_config.iscsi_icd_count[ulp_num] =
+				pfw_cfg->ulp[ulp_num].icd_count;
+
+			phba->fw_config.iscsi_chain_start[ulp_num] =
+				pfw_cfg->chain_icd[ulp_num].chain_base;
+			phba->fw_config.iscsi_chain_count[ulp_num] =
+				pfw_cfg->chain_icd[ulp_num].chain_count;
+
+			beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_INIT,
+				    "BG_%d : Function loaded on ULP : %d\n"
+				    "\tiscsi_cid_count : %d\n"
+				    "\tiscsi_cid_start : %d\n"
+				    "\t iscsi_icd_count : %d\n"
+				    "\t iscsi_icd_start : %d\n",
+				    ulp_num,
+				    phba->fw_config.
+				    iscsi_cid_count[ulp_num],
+				    phba->fw_config.
+				    iscsi_cid_start[ulp_num],
+				    phba->fw_config.
+				    iscsi_icd_count[ulp_num],
+				    phba->fw_config.
+				    iscsi_icd_start[ulp_num]);
 		}
+	}
 
-		phba->fw_config.dual_ulp_aware = (pfw_cfg->function_mode &
-						  BEISCSI_FUNC_DUA_MODE);
+	if (phba->fw_config.ulp_supported == 0) {
+		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
+			    "BG_%d : iSCSI initiator mode not set: ULP0 %x ULP1 %x\n",
+			    pfw_cfg->ulp[BEISCSI_ULP0].ulp_mode,
+			    pfw_cfg->ulp[BEISCSI_ULP1].ulp_mode);
+		goto fail_init;
+	}
 
-		beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_INIT,
-			    "BG_%d : DUA Mode : 0x%x\n",
-			    phba->fw_config.dual_ulp_aware);
+	/**
+	 * ICD is shared among ULPs. Use icd_count of any one loaded ULP
+	 **/
+	for (ulp_num = 0; ulp_num < BEISCSI_ULP_COUNT; ulp_num++)
+		if (test_bit(ulp_num, &phba->fw_config.ulp_supported))
+			break;
+	icd_count = phba->fw_config.iscsi_icd_count[ulp_num];
+	if (icd_count == 0 || icd_count > 65536) {
+		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
+			    "BG_%d: invalid ICD count %d\n", icd_count);
+		goto fail_init;
+	}
 
-	} else {
+	cid_count = BEISCSI_GET_CID_COUNT(phba, BEISCSI_ULP0) +
+		    BEISCSI_GET_CID_COUNT(phba, BEISCSI_ULP1);
+	if (cid_count == 0 || cid_count > 4096) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
-			    "BG_%d : Failed in mgmt_get_fw_config\n");
-		status = -EINVAL;
+			    "BG_%d: invalid CID count %d\n", cid_count);
+		goto fail_init;
 	}
 
-	spin_unlock(&ctrl->mbox_lock);
+	/**
+	 * Check FW is dual ULP aware i.e. can handle either
+	 * of the protocols.
+	 */
+	phba->fw_config.dual_ulp_aware = (pfw_cfg->function_mode &
+					  BEISCSI_FUNC_DUA_MODE);
+
+	beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_INIT,
+		    "BG_%d : DUA Mode : 0x%x\n",
+		    phba->fw_config.dual_ulp_aware);
+
+	/* all set, continue using this FW config */
+	status = 0;
+fail_init:
+	mutex_unlock(&ctrl->mbox_lock);
 	return status;
 }
 
@@ -440,7 +526,7 @@ int mgmt_check_supported_fw(struct be_ctrl_info *ctrl,
 	nonemb_cmd.size = sizeof(struct be_mgmt_controller_attributes);
 	req = nonemb_cmd.va;
 	memset(req, 0, sizeof(*req));
-	spin_lock(&ctrl->mbox_lock);
+	mutex_lock(&ctrl->mbox_lock);
 	memset(wrb, 0, sizeof(*wrb));
 	be_wrb_hdr_prepare(wrb, sizeof(*req), false, 1);
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
@@ -470,7 +556,7 @@ int mgmt_check_supported_fw(struct be_ctrl_info *ctrl,
 	} else
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
 			    "BG_%d :  Failed in mgmt_check_supported_fw\n");
-	spin_unlock(&ctrl->mbox_lock);
+	mutex_unlock(&ctrl->mbox_lock);
 	if (nonemb_cmd.va)
 		pci_free_consistent(ctrl->pdev, nonemb_cmd.size,
 				    nonemb_cmd.va, nonemb_cmd.dma);
@@ -501,8 +587,9 @@ unsigned int mgmt_vendor_specific_fw_cmd(struct be_ctrl_info *ctrl,
 	req->region = region;
 	req->sector = sector;
 	req->offset = offset;
-	spin_lock(&ctrl->mbox_lock);
 
+	if (mutex_lock_interruptible(&ctrl->mbox_lock))
+		return 0;
 	switch (bsg_req->rqst_data.h_vendor.vendor_cmd[0]) {
 	case BEISCSI_WRITE_FLASH:
 		offset = sector * sector_size + offset;
@@ -521,28 +608,26 @@ unsigned int mgmt_vendor_specific_fw_cmd(struct be_ctrl_info *ctrl,
 			    "BG_%d : Unsupported cmd = 0x%x\n\n",
 			    bsg_req->rqst_data.h_vendor.vendor_cmd[0]);
 
-		spin_unlock(&ctrl->mbox_lock);
+		mutex_unlock(&ctrl->mbox_lock);
 		return -ENOSYS;
 	}
 
-	tag = alloc_mcc_tag(phba);
-	if (!tag) {
-		spin_unlock(&ctrl->mbox_lock);
-		return tag;
+	wrb = alloc_mcc_wrb(phba, &tag);
+	if (!wrb) {
+		mutex_unlock(&ctrl->mbox_lock);
+		return 0;
 	}
 
-	wrb = wrb_from_mccq(phba);
 	mcc_sge = nonembedded_sgl(wrb);
 	be_wrb_hdr_prepare(wrb, nonemb_cmd->size, false,
 			   job->request_payload.sg_cnt);
 	mcc_sge->pa_hi = cpu_to_le32(upper_32_bits(nonemb_cmd->dma));
 	mcc_sge->pa_lo = cpu_to_le32(nonemb_cmd->dma & 0xFFFFFFFF);
 	mcc_sge->len = cpu_to_le32(nonemb_cmd->size);
-	wrb->tag0 |= tag;
 
-	be_mcc_notify(phba);
+	be_mcc_notify(phba, tag);
 
-	spin_unlock(&ctrl->mbox_lock);
+	mutex_unlock(&ctrl->mbox_lock);
 	return tag;
 }
 
@@ -558,12 +643,19 @@ unsigned int mgmt_vendor_specific_fw_cmd(struct be_ctrl_info *ctrl,
 int mgmt_epfw_cleanup(struct beiscsi_hba *phba, unsigned short ulp_num)
 {
 	struct be_ctrl_info *ctrl = &phba->ctrl;
-	struct be_mcc_wrb *wrb = wrb_from_mccq(phba);
-	struct iscsi_cleanup_req *req = embedded_payload(wrb);
-	int status = 0;
+	struct be_mcc_wrb *wrb;
+	struct iscsi_cleanup_req *req;
+	unsigned int tag;
+	int status;
 
-	spin_lock(&ctrl->mbox_lock);
+	mutex_lock(&ctrl->mbox_lock);
+	wrb = alloc_mcc_wrb(phba, &tag);
+	if (!wrb) {
+		mutex_unlock(&ctrl->mbox_lock);
+		return -EBUSY;
+	}
 
+	req = embedded_payload(wrb);
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI,
 			   OPCODE_COMMON_ISCSI_CLEANUP, sizeof(*req));
@@ -572,11 +664,12 @@ int mgmt_epfw_cleanup(struct beiscsi_hba *phba, unsigned short ulp_num)
 	req->hdr_ring_id = cpu_to_le16(HWI_GET_DEF_HDRQ_ID(phba, ulp_num));
 	req->data_ring_id = cpu_to_le16(HWI_GET_DEF_BUFQ_ID(phba, ulp_num));
 
-	status =  be_mcc_notify_wait(phba);
+	be_mcc_notify(phba, tag);
+	status = be_mcc_compl_poll(phba, tag);
 	if (status)
 		beiscsi_log(phba, KERN_WARNING, BEISCSI_LOG_INIT,
 			    "BG_%d : mgmt_epfw_cleanup , FAILED\n");
-	spin_unlock(&ctrl->mbox_lock);
+	mutex_unlock(&ctrl->mbox_lock);
 	return status;
 }
 
@@ -590,20 +683,18 @@ unsigned int  mgmt_invalidate_icds(struct beiscsi_hba *phba,
 	struct be_mcc_wrb *wrb;
 	struct be_sge *sge;
 	struct invalidate_commands_params_in *req;
-	unsigned int i, tag = 0;
+	unsigned int i, tag;
 
-	spin_lock(&ctrl->mbox_lock);
-	tag = alloc_mcc_tag(phba);
-	if (!tag) {
-		spin_unlock(&ctrl->mbox_lock);
-		return tag;
+	mutex_lock(&ctrl->mbox_lock);
+	wrb = alloc_mcc_wrb(phba, &tag);
+	if (!wrb) {
+		mutex_unlock(&ctrl->mbox_lock);
+		return 0;
 	}
 
 	req = nonemb_cmd->va;
 	memset(req, 0, sizeof(*req));
-	wrb = wrb_from_mccq(phba);
 	sge = nonembedded_sgl(wrb);
-	wrb->tag0 |= tag;
 
 	be_wrb_hdr_prepare(wrb, sizeof(*req), false, 1);
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI,
@@ -621,8 +712,8 @@ unsigned int  mgmt_invalidate_icds(struct beiscsi_hba *phba,
 	sge->pa_lo = cpu_to_le32(nonemb_cmd->dma & 0xFFFFFFFF);
 	sge->len = cpu_to_le32(nonemb_cmd->size);
 
-	be_mcc_notify(phba);
-	spin_unlock(&ctrl->mbox_lock);
+	be_mcc_notify(phba, tag);
+	mutex_unlock(&ctrl->mbox_lock);
 	return tag;
 }
 
@@ -637,16 +728,14 @@ unsigned int mgmt_invalidate_connection(struct beiscsi_hba *phba,
 	struct iscsi_invalidate_connection_params_in *req;
 	unsigned int tag = 0;
 
-	spin_lock(&ctrl->mbox_lock);
-	tag = alloc_mcc_tag(phba);
-	if (!tag) {
-		spin_unlock(&ctrl->mbox_lock);
-		return tag;
+	mutex_lock(&ctrl->mbox_lock);
+	wrb = alloc_mcc_wrb(phba, &tag);
+	if (!wrb) {
+		mutex_unlock(&ctrl->mbox_lock);
+		return 0;
 	}
-	wrb = wrb_from_mccq(phba);
-	wrb->tag0 |= tag;
-	req = embedded_payload(wrb);
 
+	req = embedded_payload(wrb);
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI_INI,
 			   OPCODE_ISCSI_INI_DRIVER_INVALIDATE_CONNECTION,
@@ -658,8 +747,8 @@ unsigned int mgmt_invalidate_connection(struct beiscsi_hba *phba,
 	else
 		req->cleanup_type = CMD_ISCSI_CONNECTION_INVALIDATE;
 	req->save_cfg = savecfg_flag;
-	be_mcc_notify(phba);
-	spin_unlock(&ctrl->mbox_lock);
+	be_mcc_notify(phba, tag);
+	mutex_unlock(&ctrl->mbox_lock);
 	return tag;
 }
 
@@ -669,25 +758,23 @@ unsigned int mgmt_upload_connection(struct beiscsi_hba *phba,
 	struct be_ctrl_info *ctrl = &phba->ctrl;
 	struct be_mcc_wrb *wrb;
 	struct tcp_upload_params_in *req;
-	unsigned int tag = 0;
+	unsigned int tag;
 
-	spin_lock(&ctrl->mbox_lock);
-	tag = alloc_mcc_tag(phba);
-	if (!tag) {
-		spin_unlock(&ctrl->mbox_lock);
-		return tag;
+	mutex_lock(&ctrl->mbox_lock);
+	wrb = alloc_mcc_wrb(phba, &tag);
+	if (!wrb) {
+		mutex_unlock(&ctrl->mbox_lock);
+		return 0;
 	}
-	wrb = wrb_from_mccq(phba);
-	req = embedded_payload(wrb);
-	wrb->tag0 |= tag;
 
+	req = embedded_payload(wrb);
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
 	be_cmd_hdr_prepare(&req->hdr, CMD_COMMON_TCP_UPLOAD,
 			   OPCODE_COMMON_TCP_UPLOAD, sizeof(*req));
 	req->id = (unsigned short)cid;
 	req->upload_type = (unsigned char)upload_flag;
-	be_mcc_notify(phba);
-	spin_unlock(&ctrl->mbox_lock);
+	be_mcc_notify(phba, tag);
+	mutex_unlock(&ctrl->mbox_lock);
 	return tag;
 }
 
@@ -722,6 +809,13 @@ int mgmt_open_connection(struct beiscsi_hba *phba,
 	unsigned short cid = beiscsi_ep->ep_cid;
 	struct be_sge *sge;
 
+	if (dst_addr->sa_family != PF_INET && dst_addr->sa_family != PF_INET6) {
+		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_CONFIG,
+			    "BG_%d : unknown addr family %d\n",
+			    dst_addr->sa_family);
+		return -EINVAL;
+	}
+
 	phwi_ctrlr = phba->phwi_ctrlr;
 	phwi_context = phwi_ctrlr->phwi_ctxt;
 
@@ -732,18 +826,17 @@ int mgmt_open_connection(struct beiscsi_hba *phba,
 
 	ptemplate_address = &template_address;
 	ISCSI_GET_PDU_TEMPLATE_ADDRESS(phba, ptemplate_address);
-	spin_lock(&ctrl->mbox_lock);
-	tag = alloc_mcc_tag(phba);
-	if (!tag) {
-		spin_unlock(&ctrl->mbox_lock);
-		return tag;
+	if (mutex_lock_interruptible(&ctrl->mbox_lock))
+		return 0;
+	wrb = alloc_mcc_wrb(phba, &tag);
+	if (!wrb) {
+		mutex_unlock(&ctrl->mbox_lock);
+		return 0;
 	}
-	wrb = wrb_from_mccq(phba);
-	sge = nonembedded_sgl(wrb);
 
+	sge = nonembedded_sgl(wrb);
 	req = nonemb_cmd->va;
 	memset(req, 0, sizeof(*req));
-	wrb->tag0 |= tag;
 
 	be_wrb_hdr_prepare(wrb, nonemb_cmd->size, false, 1);
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI,
@@ -760,7 +853,8 @@ int mgmt_open_connection(struct beiscsi_hba *phba,
 		beiscsi_ep->dst_addr = daddr_in->sin_addr.s_addr;
 		beiscsi_ep->dst_tcpport = ntohs(daddr_in->sin_port);
 		beiscsi_ep->ip_type = BE2_IPV4;
-	} else if (dst_addr->sa_family == PF_INET6) {
+	} else {
+		/* else its PF_INET6 family */
 		req->ip_address.ip_type = BE2_IPV6;
 		memcpy(&req->ip_address.addr,
 		       &daddr_in6->sin6_addr.in6_u.u6_addr8, 16);
@@ -769,14 +863,6 @@ int mgmt_open_connection(struct beiscsi_hba *phba,
 		memcpy(&beiscsi_ep->dst6_addr,
 		       &daddr_in6->sin6_addr.in6_u.u6_addr8, 16);
 		beiscsi_ep->ip_type = BE2_IPV6;
-	} else{
-		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_CONFIG,
-			    "BG_%d : unknown addr family %d\n",
-			    dst_addr->sa_family);
-		spin_unlock(&ctrl->mbox_lock);
-		free_mcc_tag(&phba->ctrl, tag);
-		return -EINVAL;
-
 	}
 	req->cid = cid;
 	i = phba->nxt_cqid++;
@@ -801,35 +887,45 @@ int mgmt_open_connection(struct beiscsi_hba *phba,
 		req->tcp_window_scale_count = 2;
 	}
 
-	be_mcc_notify(phba);
-	spin_unlock(&ctrl->mbox_lock);
+	be_mcc_notify(phba, tag);
+	mutex_unlock(&ctrl->mbox_lock);
 	return tag;
 }
 
 unsigned int mgmt_get_all_if_id(struct beiscsi_hba *phba)
 {
 	struct be_ctrl_info *ctrl = &phba->ctrl;
-	struct be_mcc_wrb *wrb = wrb_from_mbox(&ctrl->mbox_mem);
-	struct be_cmd_get_all_if_id_req *req = embedded_payload(wrb);
-	struct be_cmd_get_all_if_id_req *pbe_allid = req;
+	struct be_mcc_wrb *wrb;
+	struct be_cmd_get_all_if_id_req *req;
+	struct be_cmd_get_all_if_id_req *pbe_allid;
+	unsigned int tag;
 	int status = 0;
 
-	memset(wrb, 0, sizeof(*wrb));
-
-	spin_lock(&ctrl->mbox_lock);
+	if (mutex_lock_interruptible(&ctrl->mbox_lock))
+		return -EINTR;
+	wrb = alloc_mcc_wrb(phba, &tag);
+	if (!wrb) {
+		mutex_unlock(&ctrl->mbox_lock);
+		return -ENOMEM;
+	}
 
+	req = embedded_payload(wrb);
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI,
 			   OPCODE_COMMON_ISCSI_NTWK_GET_ALL_IF_ID,
 			   sizeof(*req));
-	status = be_mbox_notify(ctrl);
-	if (!status)
-		phba->interface_handle = pbe_allid->if_hndl_list[0];
-	else {
+	be_mcc_notify(phba, tag);
+	mutex_unlock(&ctrl->mbox_lock);
+
+	status = beiscsi_mccq_compl_wait(phba, tag, &wrb, NULL);
+	if (status) {
 		beiscsi_log(phba, KERN_WARNING, BEISCSI_LOG_CONFIG,
 			    "BG_%d : Failed in mgmt_get_all_if_id\n");
+		return -EBUSY;
 	}
-	spin_unlock(&ctrl->mbox_lock);
+
+	pbe_allid = embedded_payload(wrb);
+	phba->interface_handle = pbe_allid->if_hndl_list[0];
 
 	return status;
 }
@@ -852,27 +948,24 @@ static int mgmt_exec_nonemb_cmd(struct beiscsi_hba *phba,
 	unsigned int tag;
 	int rc = 0;
 
-	spin_lock(&ctrl->mbox_lock);
-	tag = alloc_mcc_tag(phba);
-	if (!tag) {
-		spin_unlock(&ctrl->mbox_lock);
+	mutex_lock(&ctrl->mbox_lock);
+	wrb = alloc_mcc_wrb(phba, &tag);
+	if (!wrb) {
+		mutex_unlock(&ctrl->mbox_lock);
 		rc = -ENOMEM;
 		goto free_cmd;
 	}
 
-	wrb = wrb_from_mccq(phba);
-	wrb->tag0 |= tag;
 	sge = nonembedded_sgl(wrb);
-
 	be_wrb_hdr_prepare(wrb, nonemb_cmd->size, false, 1);
 	sge->pa_hi = cpu_to_le32(upper_32_bits(nonemb_cmd->dma));
 	sge->pa_lo = cpu_to_le32(lower_32_bits(nonemb_cmd->dma));
 	sge->len = cpu_to_le32(nonemb_cmd->size);
 
-	be_mcc_notify(phba);
-	spin_unlock(&ctrl->mbox_lock);
+	be_mcc_notify(phba, tag);
+	mutex_unlock(&ctrl->mbox_lock);
 
-	rc = beiscsi_mccq_compl(phba, tag, NULL, nonemb_cmd);
+	rc = beiscsi_mccq_compl_wait(phba, tag, NULL, nonemb_cmd);
 
 	if (resp_buf)
 		memcpy(resp_buf, nonemb_cmd->va, resp_buf_len);
@@ -1003,8 +1096,9 @@ int mgmt_set_ip(struct beiscsi_hba *phba,
 	uint32_t ip_type;
 	int rc;
 
-	if (mgmt_get_all_if_id(phba))
-		return -EIO;
+	rc = mgmt_get_all_if_id(phba);
+	if (rc)
+		return rc;
 
 	ip_type = (ip_param->param == ISCSI_NET_PARAM_IPV6_ADDR) ?
 		BE2_IPV6 : BE2_IPV4 ;
@@ -1173,8 +1267,9 @@ int mgmt_get_if_info(struct beiscsi_hba *phba, int ip_type,
 	uint32_t ioctl_size = sizeof(struct be_cmd_get_if_info_resp);
 	int rc;
 
-	if (mgmt_get_all_if_id(phba))
-		return -EIO;
+	rc = mgmt_get_all_if_id(phba);
+	if (rc)
+		return rc;
 
 	do {
 		rc = mgmt_alloc_cmd_data(phba, &nonemb_cmd,
@@ -1245,55 +1340,27 @@ int mgmt_get_nic_conf(struct beiscsi_hba *phba,
 
 unsigned int be_cmd_get_initname(struct beiscsi_hba *phba)
 {
-	unsigned int tag = 0;
+	unsigned int tag;
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_hba_name *req;
 	struct be_ctrl_info *ctrl = &phba->ctrl;
 
-	spin_lock(&ctrl->mbox_lock);
-	tag = alloc_mcc_tag(phba);
-	if (!tag) {
-		spin_unlock(&ctrl->mbox_lock);
-		return tag;
+	if (mutex_lock_interruptible(&ctrl->mbox_lock))
+		return 0;
+	wrb = alloc_mcc_wrb(phba, &tag);
+	if (!wrb) {
+		mutex_unlock(&ctrl->mbox_lock);
+		return 0;
 	}
 
-	wrb = wrb_from_mccq(phba);
 	req = embedded_payload(wrb);
-	wrb->tag0 |= tag;
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI_INI,
 			OPCODE_ISCSI_INI_CFG_GET_HBA_NAME,
 			sizeof(*req));
 
-	be_mcc_notify(phba);
-	spin_unlock(&ctrl->mbox_lock);
-	return tag;
-}
-
-unsigned int be_cmd_get_port_speed(struct beiscsi_hba *phba)
-{
-	unsigned int tag = 0;
-	struct be_mcc_wrb *wrb;
-	struct be_cmd_ntwk_link_status_req *req;
-	struct be_ctrl_info *ctrl = &phba->ctrl;
-
-	spin_lock(&ctrl->mbox_lock);
-	tag = alloc_mcc_tag(phba);
-	if (!tag) {
-		spin_unlock(&ctrl->mbox_lock);
-		return tag;
-	}
-
-	wrb = wrb_from_mccq(phba);
-	req = embedded_payload(wrb);
-	wrb->tag0 |= tag;
-	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
-	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-			OPCODE_COMMON_NTWK_LINK_STATUS_QUERY,
-			sizeof(*req));
-
-	be_mcc_notify(phba);
-	spin_unlock(&ctrl->mbox_lock);
+	be_mcc_notify(phba, tag);
+	mutex_unlock(&ctrl->mbox_lock);
 	return tag;
 }
 
@@ -1330,7 +1397,7 @@ int be_mgmt_get_boot_shandle(struct beiscsi_hba *phba,
 			return -EAGAIN;
 		}
 
-		rc = beiscsi_mccq_compl(phba, tag, &wrb, NULL);
+		rc = beiscsi_mccq_compl_wait(phba, tag, &wrb, NULL);
 		if (rc) {
 			beiscsi_log(phba, KERN_ERR,
 				    BEISCSI_LOG_INIT | BEISCSI_LOG_CONFIG,
@@ -1364,7 +1431,7 @@ int be_mgmt_get_boot_shandle(struct beiscsi_hba *phba,
 			return -EAGAIN;
 		}
 
-		rc = beiscsi_mccq_compl(phba, tag, NULL, NULL);
+		rc = beiscsi_mccq_compl_wait(phba, tag, NULL, NULL);
 		if (rc) {
 			beiscsi_log(phba, KERN_ERR,
 				    BEISCSI_LOG_INIT | BEISCSI_LOG_CONFIG,
@@ -1406,7 +1473,7 @@ int mgmt_set_vlan(struct beiscsi_hba *phba,
 		return -EBUSY;
 	}
 
-	rc = beiscsi_mccq_compl(phba, tag, NULL, NULL);
+	rc = beiscsi_mccq_compl_wait(phba, tag, NULL, NULL);
 	if (rc) {
 		beiscsi_log(phba, KERN_ERR,
 			    (BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX),
@@ -1749,19 +1816,17 @@ int beiscsi_logout_fw_sess(struct beiscsi_hba *phba,
 		    BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
 		    "BG_%d : In bescsi_logout_fwboot_sess\n");
 
-	spin_lock(&ctrl->mbox_lock);
-	tag = alloc_mcc_tag(phba);
-	if (!tag) {
-		spin_unlock(&ctrl->mbox_lock);
+	mutex_lock(&ctrl->mbox_lock);
+	wrb = alloc_mcc_wrb(phba, &tag);
+	if (!wrb) {
+		mutex_unlock(&ctrl->mbox_lock);
 		beiscsi_log(phba, KERN_INFO,
 			    BEISCSI_LOG_CONFIG | BEISCSI_LOG_MBOX,
 			    "BG_%d : MBX Tag Failure\n");
 		return -EINVAL;
 	}
 
-	wrb = wrb_from_mccq(phba);
 	req = embedded_payload(wrb);
-	wrb->tag0 |= tag;
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI_INI,
 			   OPCODE_ISCSI_INI_SESSION_LOGOUT_TARGET,
@@ -1769,10 +1834,10 @@ int beiscsi_logout_fw_sess(struct beiscsi_hba *phba,
 
 	/* Set the session handle */
 	req->session_handle = fw_sess_handle;
-	be_mcc_notify(phba);
-	spin_unlock(&ctrl->mbox_lock);
+	be_mcc_notify(phba, tag);
+	mutex_unlock(&ctrl->mbox_lock);
 
-	rc = beiscsi_mccq_compl(phba, tag, &wrb, NULL);
+	rc = beiscsi_mccq_compl_wait(phba, tag, &wrb, NULL);
 	if (rc) {
 		beiscsi_log(phba, KERN_ERR,
 			    BEISCSI_LOG_INIT | BEISCSI_LOG_CONFIG,
diff --git a/drivers/scsi/be2iscsi/be_mgmt.h b/drivers/scsi/be2iscsi/be_mgmt.h
index c1dbb690ee27..f3a48a04b2ca 100644
--- a/drivers/scsi/be2iscsi/be_mgmt.h
+++ b/drivers/scsi/be2iscsi/be_mgmt.h
@@ -268,6 +268,8 @@ struct beiscsi_endpoint {
 
 int mgmt_get_fw_config(struct be_ctrl_info *ctrl,
 				 struct beiscsi_hba *phba);
+int mgmt_get_port_name(struct be_ctrl_info *ctrl,
+		       struct beiscsi_hba *phba);
 
 unsigned int mgmt_invalidate_connection(struct beiscsi_hba *phba,
 					 struct beiscsi_endpoint *beiscsi_ep,
diff --git a/drivers/scsi/bfa/bfa_core.c b/drivers/scsi/bfa/bfa_core.c
index 2ea0db4b62a7..7209afad82f7 100644
--- a/drivers/scsi/bfa/bfa_core.c
+++ b/drivers/scsi/bfa/bfa_core.c
@@ -91,6 +91,25 @@ static bfa_ioc_mbox_mcfunc_t  bfa_mbox_isrs[BFI_MC_MAX] = {
 
 
 
+void
+__bfa_trc(struct bfa_trc_mod_s *trcm, int fileno, int line, u64 data)
+{
+	int		tail = trcm->tail;
+	struct bfa_trc_s	*trc = &trcm->trc[tail];
+
+	if (trcm->stopped)
+		return;
+
+	trc->fileno = (u16) fileno;
+	trc->line = (u16) line;
+	trc->data.u64 = data;
+	trc->timestamp = BFA_TRC_TS(trcm);
+
+	trcm->tail = (trcm->tail + 1) & (BFA_TRC_MAX - 1);
+	if (trcm->tail == trcm->head)
+		trcm->head = (trcm->head + 1) & (BFA_TRC_MAX - 1);
+}
+
 static void
 bfa_com_port_attach(struct bfa_s *bfa)
 {
diff --git a/drivers/scsi/bfa/bfa_cs.h b/drivers/scsi/bfa/bfa_cs.h
index da9cf655be26..df6760ca0911 100644
--- a/drivers/scsi/bfa/bfa_cs.h
+++ b/drivers/scsi/bfa/bfa_cs.h
@@ -108,44 +108,11 @@ bfa_trc_stop(struct bfa_trc_mod_s *trcm)
 	trcm->stopped = 1;
 }
 
-static inline void
-__bfa_trc(struct bfa_trc_mod_s *trcm, int fileno, int line, u64 data)
-{
-	int		tail = trcm->tail;
-	struct bfa_trc_s	*trc = &trcm->trc[tail];
-
-	if (trcm->stopped)
-		return;
-
-	trc->fileno = (u16) fileno;
-	trc->line = (u16) line;
-	trc->data.u64 = data;
-	trc->timestamp = BFA_TRC_TS(trcm);
-
-	trcm->tail = (trcm->tail + 1) & (BFA_TRC_MAX - 1);
-	if (trcm->tail == trcm->head)
-		trcm->head = (trcm->head + 1) & (BFA_TRC_MAX - 1);
-}
-
+void
+__bfa_trc(struct bfa_trc_mod_s *trcm, int fileno, int line, u64 data);
 
-static inline void
-__bfa_trc32(struct bfa_trc_mod_s *trcm, int fileno, int line, u32 data)
-{
-	int		tail = trcm->tail;
-	struct bfa_trc_s *trc = &trcm->trc[tail];
-
-	if (trcm->stopped)
-		return;
-
-	trc->fileno = (u16) fileno;
-	trc->line = (u16) line;
-	trc->data.u32.u32 = data;
-	trc->timestamp = BFA_TRC_TS(trcm);
-
-	trcm->tail = (trcm->tail + 1) & (BFA_TRC_MAX - 1);
-	if (trcm->tail == trcm->head)
-		trcm->head = (trcm->head + 1) & (BFA_TRC_MAX - 1);
-}
+void
+__bfa_trc32(struct bfa_trc_mod_s *trcm, int fileno, int line, u32 data);
 
 #define bfa_sm_fault(__mod, __event)	do {				\
 	bfa_trc(__mod, (((u32)0xDEAD << 16) | __event));		\
diff --git a/drivers/scsi/bfa/bfa_ioc.c b/drivers/scsi/bfa/bfa_ioc.c
index 251e2ff8ff5f..a1ada4a31c97 100644
--- a/drivers/scsi/bfa/bfa_ioc.c
+++ b/drivers/scsi/bfa/bfa_ioc.c
@@ -2803,7 +2803,7 @@ void
 bfa_ioc_get_adapter_manufacturer(struct bfa_ioc_s *ioc, char *manufacturer)
 {
 	memset((void *)manufacturer, 0, BFA_ADAPTER_MFG_NAME_LEN);
-	memcpy(manufacturer, BFA_MFG_NAME, BFA_ADAPTER_MFG_NAME_LEN);
+	strncpy(manufacturer, BFA_MFG_NAME, BFA_ADAPTER_MFG_NAME_LEN);
 }
 
 void
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index 67405c628864..d7029ea5d319 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -97,6 +97,15 @@ static void __exit bnx2fc_mod_exit(void);
 
 unsigned int bnx2fc_debug_level;
 module_param_named(debug_logging, bnx2fc_debug_level, int, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(debug_logging,
+		"Option to enable extended logging,\n"
+		"\t\tDefault is 0 - no logging.\n"
+		"\t\t0x01 - SCSI cmd error, cleanup.\n"
+		"\t\t0x02 - Session setup, cleanup, etc.\n"
+		"\t\t0x04 - lport events, link, mtu, etc.\n"
+		"\t\t0x08 - ELS logs.\n"
+		"\t\t0x10 - fcoe L2 fame related logs.\n"
+		"\t\t0xff - LOG all messages.");
 
 static int bnx2fc_cpu_callback(struct notifier_block *nfb,
 			     unsigned long action, void *hcpu);
diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c
index 0002caf687dd..2230dab67ca5 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_io.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_io.c
@@ -1104,8 +1104,7 @@ int bnx2fc_eh_abort(struct scsi_cmnd *sc_cmd)
 	struct bnx2fc_cmd *io_req;
 	struct fc_lport *lport;
 	struct bnx2fc_rport *tgt;
-	int rc = FAILED;
-
+	int rc;
 
 	rc = fc_block_scsi_eh(sc_cmd);
 	if (rc)
@@ -1114,7 +1113,7 @@ int bnx2fc_eh_abort(struct scsi_cmnd *sc_cmd)
 	lport = shost_priv(sc_cmd->device->host);
 	if ((lport->state != LPORT_ST_READY) || !(lport->link_up)) {
 		printk(KERN_ERR PFX "eh_abort: link not ready\n");
-		return rc;
+		return FAILED;
 	}
 
 	tgt = (struct bnx2fc_rport *)&rp[1];
diff --git a/drivers/scsi/cxlflash/common.h b/drivers/scsi/cxlflash/common.h
index 5ada9268a450..a8ac4c0a1493 100644
--- a/drivers/scsi/cxlflash/common.h
+++ b/drivers/scsi/cxlflash/common.h
@@ -34,7 +34,6 @@ extern const struct file_operations cxlflash_cxl_fops;
 								   sectors
 								*/
 
-#define NUM_RRQ_ENTRY    16     /* for master issued cmds */
 #define MAX_RHT_PER_CONTEXT (PAGE_SIZE / sizeof(struct sisl_rht_entry))
 
 /* AFU command retry limit */
@@ -48,9 +47,12 @@ extern const struct file_operations cxlflash_cxl_fops;
 							   index derivation
 							 */
 
-#define CXLFLASH_MAX_CMDS               16
+#define CXLFLASH_MAX_CMDS               256
 #define CXLFLASH_MAX_CMDS_PER_LUN       CXLFLASH_MAX_CMDS
 
+/* RRQ for master issued cmds */
+#define NUM_RRQ_ENTRY                   CXLFLASH_MAX_CMDS
+
 
 static inline void check_sizes(void)
 {
@@ -149,7 +151,7 @@ struct afu_cmd {
 struct afu {
 	/* Stuff requiring alignment go first. */
 
-	u64 rrq_entry[NUM_RRQ_ENTRY];	/* 128B RRQ */
+	u64 rrq_entry[NUM_RRQ_ENTRY];	/* 2K RRQ */
 	/*
 	 * Command & data for AFU commands.
 	 */
diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c
index f6d90ce8f3b7..3879b46d79e1 100644
--- a/drivers/scsi/cxlflash/main.c
+++ b/drivers/scsi/cxlflash/main.c
@@ -726,11 +726,11 @@ static void term_mc(struct cxlflash_cfg *cfg, enum undo_level level)
  */
 static void term_afu(struct cxlflash_cfg *cfg)
 {
-	term_mc(cfg, UNDO_START);
-
 	if (cfg->afu)
 		stop_afu(cfg);
 
+	term_mc(cfg, UNDO_START);
+
 	pr_debug("%s: returning\n", __func__);
 }
 
@@ -767,7 +767,6 @@ static void cxlflash_remove(struct pci_dev *pdev)
 		cancel_work_sync(&cfg->work_q);
 		term_afu(cfg);
 	case INIT_STATE_PCI:
-		pci_release_regions(cfg->dev);
 		pci_disable_device(pdev);
 	case INIT_STATE_NONE:
 		free_mem(cfg);
@@ -840,15 +839,6 @@ static int init_pci(struct cxlflash_cfg *cfg)
 	struct pci_dev *pdev = cfg->dev;
 	int rc = 0;
 
-	cfg->cxlflash_regs_pci = pci_resource_start(pdev, 0);
-	rc = pci_request_regions(pdev, CXLFLASH_NAME);
-	if (rc < 0) {
-		dev_err(&pdev->dev,
-			"%s: Couldn't register memory range of registers\n",
-			__func__);
-		goto out;
-	}
-
 	rc = pci_enable_device(pdev);
 	if (rc || pci_channel_offline(pdev)) {
 		if (pci_channel_offline(pdev)) {
@@ -860,55 +850,13 @@ static int init_pci(struct cxlflash_cfg *cfg)
 			dev_err(&pdev->dev, "%s: Cannot enable adapter\n",
 				__func__);
 			cxlflash_wait_for_pci_err_recovery(cfg);
-			goto out_release_regions;
-		}
-	}
-
-	rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (rc < 0) {
-		dev_dbg(&pdev->dev, "%s: Failed to set 64 bit PCI DMA mask\n",
-			__func__);
-		rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
-	}
-
-	if (rc < 0) {
-		dev_err(&pdev->dev, "%s: Failed to set PCI DMA mask\n",
-			__func__);
-		goto out_disable;
-	}
-
-	pci_set_master(pdev);
-
-	if (pci_channel_offline(pdev)) {
-		cxlflash_wait_for_pci_err_recovery(cfg);
-		if (pci_channel_offline(pdev)) {
-			rc = -EIO;
-			goto out_msi_disable;
+			goto out;
 		}
 	}
 
-	rc = pci_save_state(pdev);
-
-	if (rc != PCIBIOS_SUCCESSFUL) {
-		dev_err(&pdev->dev, "%s: Failed to save PCI config space\n",
-			__func__);
-		rc = -EIO;
-		goto cleanup_nolog;
-	}
-
 out:
 	pr_debug("%s: returning rc=%d\n", __func__, rc);
 	return rc;
-
-cleanup_nolog:
-out_msi_disable:
-	cxlflash_wait_for_pci_err_recovery(cfg);
-out_disable:
-	pci_disable_device(pdev);
-out_release_regions:
-	pci_release_regions(pdev);
-	goto out;
-
 }
 
 /**
@@ -2149,6 +2097,16 @@ static ssize_t lun_mode_store(struct device *dev,
 	rc = kstrtouint(buf, 10, &lun_mode);
 	if (!rc && (lun_mode < 5) && (lun_mode != afu->internal_lun)) {
 		afu->internal_lun = lun_mode;
+
+		/*
+		 * When configured for internal LUN, there is only one channel,
+		 * channel number 0, else there will be 2 (default).
+		 */
+		if (afu->internal_lun)
+			shost->max_channel = 0;
+		else
+			shost->max_channel = NUM_FC_PORTS - 1;
+
 		afu_reset(cfg);
 		scsi_scan_host(cfg->host);
 	}
@@ -2295,7 +2253,7 @@ static struct scsi_host_template driver_template = {
 	.eh_device_reset_handler = cxlflash_eh_device_reset_handler,
 	.eh_host_reset_handler = cxlflash_eh_host_reset_handler,
 	.change_queue_depth = cxlflash_change_queue_depth,
-	.cmd_per_lun = 16,
+	.cmd_per_lun = CXLFLASH_MAX_CMDS_PER_LUN,
 	.can_queue = CXLFLASH_MAX_CMDS,
 	.this_id = -1,
 	.sg_tablesize = SG_NONE,	/* No scatter gather support */
@@ -2544,8 +2502,8 @@ static pci_ers_result_t cxlflash_pci_error_detected(struct pci_dev *pdev,
 		if (unlikely(rc))
 			dev_err(dev, "%s: Failed to mark user contexts!(%d)\n",
 				__func__, rc);
-		term_mc(cfg, UNDO_START);
 		stop_afu(cfg);
+		term_mc(cfg, UNDO_START);
 		return PCI_ERS_RESULT_NEED_RESET;
 	case pci_channel_io_perm_failure:
 		cfg->state = STATE_FAILTERM;
diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c
index f4020dbb55c3..d8a5cb3cd2bd 100644
--- a/drivers/scsi/cxlflash/superpipe.c
+++ b/drivers/scsi/cxlflash/superpipe.c
@@ -709,27 +709,32 @@ int cxlflash_disk_release(struct scsi_device *sdev,
  * @cfg:	Internal structure associated with the host.
  * @ctxi:	Context to release.
  *
- * Note that the rht_lun member of the context was cut from a single
- * allocation when the context was created and therefore does not need
- * to be explicitly freed. Also note that we conditionally check for the
- * existence of the context control map before clearing the RHT registers
- * and context capabilities because it is possible to destroy a context
- * while the context is in the error state (previous mapping was removed
- * [so we don't have to worry about clearing] and context is waiting for
- * a new mapping).
+ * This routine is safe to be called with a a non-initialized context
+ * and is tolerant of being called with the context's mutex held (it
+ * will be unlocked if necessary before freeing). Also note that the
+ * routine conditionally checks for the existence of the context control
+ * map before clearing the RHT registers and context capabilities because
+ * it is possible to destroy a context while the context is in the error
+ * state (previous mapping was removed [so there is no need to worry about
+ * clearing] and context is waiting for a new mapping).
  */
 static void destroy_context(struct cxlflash_cfg *cfg,
 			    struct ctx_info *ctxi)
 {
 	struct afu *afu = cfg->afu;
 
-	WARN_ON(!list_empty(&ctxi->luns));
+	if (ctxi->initialized) {
+		WARN_ON(!list_empty(&ctxi->luns));
 
-	/* Clear RHT registers and drop all capabilities for this context */
-	if (afu->afu_map && ctxi->ctrl_map) {
-		writeq_be(0, &ctxi->ctrl_map->rht_start);
-		writeq_be(0, &ctxi->ctrl_map->rht_cnt_id);
-		writeq_be(0, &ctxi->ctrl_map->ctx_cap);
+		/* Clear RHT registers and drop all capabilities for context */
+		if (afu->afu_map && ctxi->ctrl_map) {
+			writeq_be(0, &ctxi->ctrl_map->rht_start);
+			writeq_be(0, &ctxi->ctrl_map->rht_cnt_id);
+			writeq_be(0, &ctxi->ctrl_map->ctx_cap);
+		}
+
+		if (mutex_is_locked(&ctxi->mutex))
+			mutex_unlock(&ctxi->mutex);
 	}
 
 	/* Free memory associated with context */
@@ -742,23 +747,12 @@ static void destroy_context(struct cxlflash_cfg *cfg,
 /**
  * create_context() - allocates and initializes a context
  * @cfg:	Internal structure associated with the host.
- * @ctx:	Previously obtained CXL context reference.
- * @ctxid:	Previously obtained process element associated with CXL context.
- * @adap_fd:	Previously obtained adapter fd associated with CXL context.
- * @file:	Previously obtained file associated with CXL context.
- * @perms:	User-specified permissions.
- *
- * The context's mutex is locked when an allocated context is returned.
  *
  * Return: Allocated context on success, NULL on failure
  */
-static struct ctx_info *create_context(struct cxlflash_cfg *cfg,
-				       struct cxl_context *ctx, int ctxid,
-				       int adap_fd, struct file *file,
-				       u32 perms)
+static struct ctx_info *create_context(struct cxlflash_cfg *cfg)
 {
 	struct device *dev = &cfg->dev->dev;
-	struct afu *afu = cfg->afu;
 	struct ctx_info *ctxi = NULL;
 	struct llun_info **lli = NULL;
 	u8 *ws = NULL;
@@ -781,28 +775,49 @@ static struct ctx_info *create_context(struct cxlflash_cfg *cfg,
 	ctxi->rht_lun = lli;
 	ctxi->rht_needs_ws = ws;
 	ctxi->rht_start = rhte;
-	ctxi->rht_perms = perms;
+out:
+	return ctxi;
+
+err:
+	kfree(ws);
+	kfree(lli);
+	kfree(ctxi);
+	ctxi = NULL;
+	goto out;
+}
+
+/**
+ * init_context() - initializes a previously allocated context
+ * @ctxi:	Previously allocated context
+ * @cfg:	Internal structure associated with the host.
+ * @ctx:	Previously obtained CXL context reference.
+ * @ctxid:	Previously obtained process element associated with CXL context.
+ * @adap_fd:	Previously obtained adapter fd associated with CXL context.
+ * @file:	Previously obtained file associated with CXL context.
+ * @perms:	User-specified permissions.
+ *
+ * Upon return, the context is marked as initialized and the context's mutex
+ * is locked.
+ */
+static void init_context(struct ctx_info *ctxi, struct cxlflash_cfg *cfg,
+			 struct cxl_context *ctx, int ctxid, int adap_fd,
+			 struct file *file, u32 perms)
+{
+	struct afu *afu = cfg->afu;
 
+	ctxi->rht_perms = perms;
 	ctxi->ctrl_map = &afu->afu_map->ctrls[ctxid].ctrl;
 	ctxi->ctxid = ENCODE_CTXID(ctxi, ctxid);
 	ctxi->lfd = adap_fd;
 	ctxi->pid = current->tgid; /* tgid = pid */
 	ctxi->ctx = ctx;
 	ctxi->file = file;
+	ctxi->initialized = true;
 	mutex_init(&ctxi->mutex);
 	INIT_LIST_HEAD(&ctxi->luns);
 	INIT_LIST_HEAD(&ctxi->list); /* initialize for list_empty() */
 
 	mutex_lock(&ctxi->mutex);
-out:
-	return ctxi;
-
-err:
-	kfree(ws);
-	kfree(lli);
-	kfree(ctxi);
-	ctxi = NULL;
-	goto out;
 }
 
 /**
@@ -1300,9 +1315,9 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 	u32 perms;
 	int ctxid = -1;
 	u64 rctxid = 0UL;
-	struct file *file;
+	struct file *file = NULL;
 
-	struct cxl_context *ctx;
+	struct cxl_context *ctx = NULL;
 
 	int fd = -1;
 
@@ -1356,7 +1371,7 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 	if (unlikely(!lun_access)) {
 		dev_err(dev, "%s: Unable to allocate lun_access!\n", __func__);
 		rc = -ENOMEM;
-		goto err0;
+		goto err;
 	}
 
 	lun_access->lli = lli;
@@ -1371,53 +1386,56 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 		goto out_attach;
 	}
 
+	ctxi = create_context(cfg);
+	if (unlikely(!ctxi)) {
+		dev_err(dev, "%s: Failed to create context! (%d)\n",
+			__func__, ctxid);
+		goto err;
+	}
+
 	ctx = cxl_dev_context_init(cfg->dev);
 	if (IS_ERR_OR_NULL(ctx)) {
 		dev_err(dev, "%s: Could not initialize context %p\n",
 			__func__, ctx);
 		rc = -ENODEV;
-		goto err1;
+		goto err;
+	}
+
+	work = &ctxi->work;
+	work->num_interrupts = attach->num_interrupts;
+	work->flags = CXL_START_WORK_NUM_IRQS;
+
+	rc = cxl_start_work(ctx, work);
+	if (unlikely(rc)) {
+		dev_dbg(dev, "%s: Could not start context rc=%d\n",
+			__func__, rc);
+		goto err;
 	}
 
 	ctxid = cxl_process_element(ctx);
 	if (unlikely((ctxid >= MAX_CONTEXT) || (ctxid < 0))) {
 		dev_err(dev, "%s: ctxid (%d) invalid!\n", __func__, ctxid);
 		rc = -EPERM;
-		goto err2;
+		goto err;
 	}
 
 	file = cxl_get_fd(ctx, &cfg->cxl_fops, &fd);
 	if (unlikely(fd < 0)) {
 		rc = -ENODEV;
 		dev_err(dev, "%s: Could not get file descriptor\n", __func__);
-		goto err2;
+		goto err;
 	}
 
 	/* Translate read/write O_* flags from fcntl.h to AFU permission bits */
 	perms = SISL_RHT_PERM(attach->hdr.flags + 1);
 
-	ctxi = create_context(cfg, ctx, ctxid, fd, file, perms);
-	if (unlikely(!ctxi)) {
-		dev_err(dev, "%s: Failed to create context! (%d)\n",
-			__func__, ctxid);
-		goto err3;
-	}
-
-	work = &ctxi->work;
-	work->num_interrupts = attach->num_interrupts;
-	work->flags = CXL_START_WORK_NUM_IRQS;
-
-	rc = cxl_start_work(ctx, work);
-	if (unlikely(rc)) {
-		dev_dbg(dev, "%s: Could not start context rc=%d\n",
-			__func__, rc);
-		goto err4;
-	}
+	/* Context mutex is locked upon return */
+	init_context(ctxi, cfg, ctx, ctxid, fd, file, perms);
 
 	rc = afu_attach(cfg, ctxi);
 	if (unlikely(rc)) {
 		dev_err(dev, "%s: Could not attach AFU rc %d\n", __func__, rc);
-		goto err5;
+		goto err;
 	}
 
 	/*
@@ -1453,13 +1471,14 @@ out:
 		__func__, ctxid, fd, attach->block_size, rc, attach->last_lba);
 	return rc;
 
-err5:
-	cxl_stop_context(ctx);
-err4:
-	put_context(ctxi);
-	destroy_context(cfg, ctxi);
-	ctxi = NULL;
-err3:
+err:
+	/* Cleanup CXL context; okay to 'stop' even if it was not started */
+	if (!IS_ERR_OR_NULL(ctx)) {
+		cxl_stop_context(ctx);
+		cxl_release_context(ctx);
+		ctx = NULL;
+	}
+
 	/*
 	 * Here, we're overriding the fops with a dummy all-NULL fops because
 	 * fput() calls the release fop, which will cause us to mistakenly
@@ -1467,15 +1486,21 @@ err3:
 	 * to that routine (cxlflash_cxl_release) we should try to fix the
 	 * issue here.
 	 */
-	file->f_op = &null_fops;
-	fput(file);
-	put_unused_fd(fd);
-	fd = -1;
-err2:
-	cxl_release_context(ctx);
-err1:
+	if (fd > 0) {
+		file->f_op = &null_fops;
+		fput(file);
+		put_unused_fd(fd);
+		fd = -1;
+		file = NULL;
+	}
+
+	/* Cleanup our context; safe to call even with mutex locked */
+	if (ctxi) {
+		destroy_context(cfg, ctxi);
+		ctxi = NULL;
+	}
+
 	kfree(lun_access);
-err0:
 	scsi_device_put(sdev);
 	goto out;
 }
@@ -1507,24 +1532,24 @@ static int recover_context(struct cxlflash_cfg *cfg, struct ctx_info *ctxi)
 		goto out;
 	}
 
+	rc = cxl_start_work(ctx, &ctxi->work);
+	if (unlikely(rc)) {
+		dev_dbg(dev, "%s: Could not start context rc=%d\n",
+			__func__, rc);
+		goto err1;
+	}
+
 	ctxid = cxl_process_element(ctx);
 	if (unlikely((ctxid >= MAX_CONTEXT) || (ctxid < 0))) {
 		dev_err(dev, "%s: ctxid (%d) invalid!\n", __func__, ctxid);
 		rc = -EPERM;
-		goto err1;
+		goto err2;
 	}
 
 	file = cxl_get_fd(ctx, &cfg->cxl_fops, &fd);
 	if (unlikely(fd < 0)) {
 		rc = -ENODEV;
 		dev_err(dev, "%s: Could not get file descriptor\n", __func__);
-		goto err1;
-	}
-
-	rc = cxl_start_work(ctx, &ctxi->work);
-	if (unlikely(rc)) {
-		dev_dbg(dev, "%s: Could not start context rc=%d\n",
-			__func__, rc);
 		goto err2;
 	}
 
@@ -1569,10 +1594,10 @@ out:
 	return rc;
 
 err3:
-	cxl_stop_context(ctx);
-err2:
 	fput(file);
 	put_unused_fd(fd);
+err2:
+	cxl_stop_context(ctx);
 err1:
 	cxl_release_context(ctx);
 	goto out;
diff --git a/drivers/scsi/cxlflash/superpipe.h b/drivers/scsi/cxlflash/superpipe.h
index bede574bcd77..5f9a091fda95 100644
--- a/drivers/scsi/cxlflash/superpipe.h
+++ b/drivers/scsi/cxlflash/superpipe.h
@@ -102,6 +102,7 @@ struct ctx_info {
 	u64 ctxid;
 	int lfd;
 	pid_t pid;
+	bool initialized;
 	bool unavail;
 	bool err_recovery_active;
 	struct mutex mutex; /* Context protection */
diff --git a/drivers/scsi/device_handler/Kconfig b/drivers/scsi/device_handler/Kconfig
index e5647d59224f..0b331c9c0a8f 100644
--- a/drivers/scsi/device_handler/Kconfig
+++ b/drivers/scsi/device_handler/Kconfig
@@ -13,13 +13,13 @@ menuconfig SCSI_DH
 
 config SCSI_DH_RDAC
 	tristate "LSI RDAC Device Handler"
-	depends on SCSI_DH
+	depends on SCSI_DH && SCSI
 	help
 	If you have a LSI RDAC select y. Otherwise, say N.
 
 config SCSI_DH_HP_SW
 	tristate "HP/COMPAQ MSA Device Handler"
-	depends on SCSI_DH
+	depends on SCSI_DH && SCSI
 	help
 	If you have a HP/COMPAQ MSA device that requires START_STOP to
 	be sent to start it and cannot upgrade the firmware then select y.
@@ -27,13 +27,13 @@ config SCSI_DH_HP_SW
 
 config SCSI_DH_EMC
 	tristate "EMC CLARiiON Device Handler"
-	depends on SCSI_DH
+	depends on SCSI_DH && SCSI
 	help
 	If you have a EMC CLARiiON select y. Otherwise, say N.
 
 config SCSI_DH_ALUA
 	tristate "SPC-3 ALUA Device Handler"
-	depends on SCSI_DH
+	depends on SCSI_DH && SCSI
 	help
 	  SCSI Device handler for generic SPC-3 Asymmetric Logical Unit
 	  Access (ALUA).
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index 5a328bf81836..5bcdf8dd6fb0 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -24,20 +24,13 @@
 #include <linux/module.h>
 #include <asm/unaligned.h>
 #include <scsi/scsi.h>
+#include <scsi/scsi_proto.h>
 #include <scsi/scsi_dbg.h>
 #include <scsi/scsi_eh.h>
 #include <scsi/scsi_dh.h>
 
 #define ALUA_DH_NAME "alua"
-#define ALUA_DH_VER "1.3"
-
-#define TPGS_STATE_OPTIMIZED		0x0
-#define TPGS_STATE_NONOPTIMIZED		0x1
-#define TPGS_STATE_STANDBY		0x2
-#define TPGS_STATE_UNAVAILABLE		0x3
-#define TPGS_STATE_LBA_DEPENDENT	0x4
-#define TPGS_STATE_OFFLINE		0xe
-#define TPGS_STATE_TRANSITIONING	0xf
+#define ALUA_DH_VER "2.0"
 
 #define TPGS_SUPPORT_NONE		0x00
 #define TPGS_SUPPORT_OPTIMIZED		0x01
@@ -56,27 +49,62 @@
 #define TPGS_MODE_IMPLICIT		0x1
 #define TPGS_MODE_EXPLICIT		0x2
 
-#define ALUA_INQUIRY_SIZE		36
+#define ALUA_RTPG_SIZE			128
 #define ALUA_FAILOVER_TIMEOUT		60
 #define ALUA_FAILOVER_RETRIES		5
+#define ALUA_RTPG_DELAY_MSECS		5
 
 /* device handler flags */
-#define ALUA_OPTIMIZE_STPG		1
-#define ALUA_RTPG_EXT_HDR_UNSUPP	2
+#define ALUA_OPTIMIZE_STPG		0x01
+#define ALUA_RTPG_EXT_HDR_UNSUPP	0x02
+#define ALUA_SYNC_STPG			0x04
+/* State machine flags */
+#define ALUA_PG_RUN_RTPG		0x10
+#define ALUA_PG_RUN_STPG		0x20
+#define ALUA_PG_RUNNING			0x40
 
-struct alua_dh_data {
+static uint optimize_stpg;
+module_param(optimize_stpg, uint, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(optimize_stpg, "Allow use of a non-optimized path, rather than sending a STPG, when implicit TPGS is supported (0=No,1=Yes). Default is 0.");
+
+static LIST_HEAD(port_group_list);
+static DEFINE_SPINLOCK(port_group_lock);
+static struct workqueue_struct *kaluad_wq;
+static struct workqueue_struct *kaluad_sync_wq;
+
+struct alua_port_group {
+	struct kref		kref;
+	struct rcu_head		rcu;
+	struct list_head	node;
+	struct list_head	dh_list;
+	unsigned char		device_id_str[256];
+	int			device_id_len;
 	int			group_id;
-	int			rel_port;
 	int			tpgs;
 	int			state;
 	int			pref;
 	unsigned		flags; /* used for optimizing STPG */
-	unsigned char		inq[ALUA_INQUIRY_SIZE];
-	unsigned char		*buff;
-	int			bufflen;
 	unsigned char		transition_tmo;
-	unsigned char		sense[SCSI_SENSE_BUFFERSIZE];
+	unsigned long		expiry;
+	unsigned long		interval;
+	struct delayed_work	rtpg_work;
+	spinlock_t		lock;
+	struct list_head	rtpg_list;
+	struct scsi_device	*rtpg_sdev;
+};
+
+struct alua_dh_data {
+	struct list_head	node;
+	struct alua_port_group	*pg;
+	int			group_id;
+	spinlock_t		pg_lock;
 	struct scsi_device	*sdev;
+	int			init_error;
+	struct mutex		init_mutex;
+};
+
+struct alua_queue_data {
+	struct list_head	entry;
 	activate_complete	callback_fn;
 	void			*callback_data;
 };
@@ -84,179 +112,160 @@ struct alua_dh_data {
 #define ALUA_POLICY_SWITCH_CURRENT	0
 #define ALUA_POLICY_SWITCH_ALL		1
 
-static char print_alua_state(int);
+static void alua_rtpg_work(struct work_struct *work);
+static void alua_rtpg_queue(struct alua_port_group *pg,
+			    struct scsi_device *sdev,
+			    struct alua_queue_data *qdata, bool force);
+static void alua_check(struct scsi_device *sdev, bool force);
 
-static int realloc_buffer(struct alua_dh_data *h, unsigned len)
+static void release_port_group(struct kref *kref)
 {
-	if (h->buff && h->buff != h->inq)
-		kfree(h->buff);
-
-	h->buff = kmalloc(len, GFP_NOIO);
-	if (!h->buff) {
-		h->buff = h->inq;
-		h->bufflen = ALUA_INQUIRY_SIZE;
-		return 1;
-	}
-	h->bufflen = len;
-	return 0;
-}
-
-static struct request *get_alua_req(struct scsi_device *sdev,
-				    void *buffer, unsigned buflen, int rw)
-{
-	struct request *rq;
-	struct request_queue *q = sdev->request_queue;
-
-	rq = blk_get_request(q, rw, GFP_NOIO);
-
-	if (IS_ERR(rq)) {
-		sdev_printk(KERN_INFO, sdev,
-			    "%s: blk_get_request failed\n", __func__);
-		return NULL;
-	}
-	blk_rq_set_block_pc(rq);
-
-	if (buflen && blk_rq_map_kern(q, rq, buffer, buflen, GFP_NOIO)) {
-		blk_put_request(rq);
-		sdev_printk(KERN_INFO, sdev,
-			    "%s: blk_rq_map_kern failed\n", __func__);
-		return NULL;
-	}
-
-	rq->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
-			 REQ_FAILFAST_DRIVER;
-	rq->retries = ALUA_FAILOVER_RETRIES;
-	rq->timeout = ALUA_FAILOVER_TIMEOUT * HZ;
-
-	return rq;
+	struct alua_port_group *pg;
+
+	pg = container_of(kref, struct alua_port_group, kref);
+	if (pg->rtpg_sdev)
+		flush_delayed_work(&pg->rtpg_work);
+	spin_lock(&port_group_lock);
+	list_del(&pg->node);
+	spin_unlock(&port_group_lock);
+	kfree_rcu(pg, rcu);
 }
 
 /*
  * submit_rtpg - Issue a REPORT TARGET GROUP STATES command
  * @sdev: sdev the command should be sent to
  */
-static unsigned submit_rtpg(struct scsi_device *sdev, struct alua_dh_data *h)
+static int submit_rtpg(struct scsi_device *sdev, unsigned char *buff,
+		       int bufflen, struct scsi_sense_hdr *sshdr, int flags)
 {
-	struct request *rq;
-	int err = 0;
-
-	rq = get_alua_req(sdev, h->buff, h->bufflen, READ);
-	if (!rq) {
-		err = DRIVER_BUSY << 24;
-		goto done;
-	}
+	u8 cdb[COMMAND_SIZE(MAINTENANCE_IN)];
+	int req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+		REQ_FAILFAST_DRIVER;
 
 	/* Prepare the command. */
-	rq->cmd[0] = MAINTENANCE_IN;
-	if (!(h->flags & ALUA_RTPG_EXT_HDR_UNSUPP))
-		rq->cmd[1] = MI_REPORT_TARGET_PGS | MI_EXT_HDR_PARAM_FMT;
+	memset(cdb, 0x0, COMMAND_SIZE(MAINTENANCE_IN));
+	cdb[0] = MAINTENANCE_IN;
+	if (!(flags & ALUA_RTPG_EXT_HDR_UNSUPP))
+		cdb[1] = MI_REPORT_TARGET_PGS | MI_EXT_HDR_PARAM_FMT;
 	else
-		rq->cmd[1] = MI_REPORT_TARGET_PGS;
-	put_unaligned_be32(h->bufflen, &rq->cmd[6]);
-	rq->cmd_len = COMMAND_SIZE(MAINTENANCE_IN);
-
-	rq->sense = h->sense;
-	memset(rq->sense, 0, SCSI_SENSE_BUFFERSIZE);
-	rq->sense_len = 0;
-
-	blk_execute_rq(rq->q, NULL, rq, 1);
-	if (rq->errors)
-		err = rq->errors;
-	blk_put_request(rq);
-done:
-	return err;
+		cdb[1] = MI_REPORT_TARGET_PGS;
+	put_unaligned_be32(bufflen, &cdb[6]);
+
+	return scsi_execute_req_flags(sdev, cdb, DMA_FROM_DEVICE,
+				      buff, bufflen, sshdr,
+				      ALUA_FAILOVER_TIMEOUT * HZ,
+				      ALUA_FAILOVER_RETRIES, NULL, req_flags);
 }
 
 /*
- * stpg_endio - Evaluate SET TARGET GROUP STATES
- * @sdev: the device to be evaluated
- * @state: the new target group state
+ * submit_stpg - Issue a SET TARGET PORT GROUP command
  *
- * Evaluate a SET TARGET GROUP STATES command response.
+ * Currently we're only setting the current target port group state
+ * to 'active/optimized' and let the array firmware figure out
+ * the states of the remaining groups.
  */
-static void stpg_endio(struct request *req, int error)
+static int submit_stpg(struct scsi_device *sdev, int group_id,
+		       struct scsi_sense_hdr *sshdr)
 {
-	struct alua_dh_data *h = req->end_io_data;
-	struct scsi_sense_hdr sense_hdr;
-	unsigned err = SCSI_DH_OK;
+	u8 cdb[COMMAND_SIZE(MAINTENANCE_OUT)];
+	unsigned char stpg_data[8];
+	int stpg_len = 8;
+	int req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+		REQ_FAILFAST_DRIVER;
 
-	if (host_byte(req->errors) != DID_OK ||
-	    msg_byte(req->errors) != COMMAND_COMPLETE) {
-		err = SCSI_DH_IO;
-		goto done;
+	/* Prepare the data buffer */
+	memset(stpg_data, 0, stpg_len);
+	stpg_data[4] = SCSI_ACCESS_STATE_OPTIMAL;
+	put_unaligned_be16(group_id, &stpg_data[6]);
+
+	/* Prepare the command. */
+	memset(cdb, 0x0, COMMAND_SIZE(MAINTENANCE_OUT));
+	cdb[0] = MAINTENANCE_OUT;
+	cdb[1] = MO_SET_TARGET_PGS;
+	put_unaligned_be32(stpg_len, &cdb[6]);
+
+	return scsi_execute_req_flags(sdev, cdb, DMA_TO_DEVICE,
+				      stpg_data, stpg_len,
+				      sshdr, ALUA_FAILOVER_TIMEOUT * HZ,
+				      ALUA_FAILOVER_RETRIES, NULL, req_flags);
+}
+
+struct alua_port_group *alua_find_get_pg(char *id_str, size_t id_size,
+					 int group_id)
+{
+	struct alua_port_group *pg;
+
+	list_for_each_entry(pg, &port_group_list, node) {
+		if (pg->group_id != group_id)
+			continue;
+		if (pg->device_id_len != id_size)
+			continue;
+		if (strncmp(pg->device_id_str, id_str, id_size))
+			continue;
+		if (!kref_get_unless_zero(&pg->kref))
+			continue;
+		return pg;
 	}
 
-	if (scsi_normalize_sense(h->sense, SCSI_SENSE_BUFFERSIZE,
-				 &sense_hdr)) {
-		if (sense_hdr.sense_key == NOT_READY &&
-		    sense_hdr.asc == 0x04 && sense_hdr.ascq == 0x0a) {
-			/* ALUA state transition already in progress */
-			err = SCSI_DH_OK;
-			goto done;
-		}
-		if (sense_hdr.sense_key == UNIT_ATTENTION) {
-			err = SCSI_DH_RETRY;
-			goto done;
-		}
-		sdev_printk(KERN_INFO, h->sdev, "%s: stpg failed\n",
-			    ALUA_DH_NAME);
-		scsi_print_sense_hdr(h->sdev, ALUA_DH_NAME, &sense_hdr);
-		err = SCSI_DH_IO;
-	} else if (error)
-		err = SCSI_DH_IO;
-
-	if (err == SCSI_DH_OK) {
-		h->state = TPGS_STATE_OPTIMIZED;
-		sdev_printk(KERN_INFO, h->sdev,
-			    "%s: port group %02x switched to state %c\n",
-			    ALUA_DH_NAME, h->group_id,
-			    print_alua_state(h->state));
-	}
-done:
-	req->end_io_data = NULL;
-	__blk_put_request(req->q, req);
-	if (h->callback_fn) {
-		h->callback_fn(h->callback_data, err);
-		h->callback_fn = h->callback_data = NULL;
-	}
-	return;
+	return NULL;
 }
 
 /*
- * submit_stpg - Issue a SET TARGET GROUP STATES command
+ * alua_alloc_pg - Allocate a new port_group structure
+ * @sdev: scsi device
+ * @h: alua device_handler data
+ * @group_id: port group id
  *
- * Currently we're only setting the current target port group state
- * to 'active/optimized' and let the array firmware figure out
- * the states of the remaining groups.
+ * Allocate a new port_group structure for a given
+ * device.
  */
-static unsigned submit_stpg(struct alua_dh_data *h)
+struct alua_port_group *alua_alloc_pg(struct scsi_device *sdev,
+				      int group_id, int tpgs)
 {
-	struct request *rq;
-	int stpg_len = 8;
-	struct scsi_device *sdev = h->sdev;
+	struct alua_port_group *pg, *tmp_pg;
 
-	/* Prepare the data buffer */
-	memset(h->buff, 0, stpg_len);
-	h->buff[4] = TPGS_STATE_OPTIMIZED & 0x0f;
-	put_unaligned_be16(h->group_id, &h->buff[6]);
-
-	rq = get_alua_req(sdev, h->buff, stpg_len, WRITE);
-	if (!rq)
-		return SCSI_DH_RES_TEMP_UNAVAIL;
+	pg = kzalloc(sizeof(struct alua_port_group), GFP_KERNEL);
+	if (!pg)
+		return ERR_PTR(-ENOMEM);
 
-	/* Prepare the command. */
-	rq->cmd[0] = MAINTENANCE_OUT;
-	rq->cmd[1] = MO_SET_TARGET_PGS;
-	put_unaligned_be32(stpg_len, &rq->cmd[6]);
-	rq->cmd_len = COMMAND_SIZE(MAINTENANCE_OUT);
+	pg->device_id_len = scsi_vpd_lun_id(sdev, pg->device_id_str,
+					    sizeof(pg->device_id_str));
+	if (pg->device_id_len <= 0) {
+		/*
+		 * Internal error: TPGS supported but no device
+		 * identifcation found. Disable ALUA support.
+		 */
+		kfree(pg);
+		sdev_printk(KERN_INFO, sdev,
+			    "%s: No device descriptors found\n",
+			    ALUA_DH_NAME);
+		return ERR_PTR(-ENXIO);
+	}
+	pg->group_id = group_id;
+	pg->tpgs = tpgs;
+	pg->state = SCSI_ACCESS_STATE_OPTIMAL;
+	if (optimize_stpg)
+		pg->flags |= ALUA_OPTIMIZE_STPG;
+	kref_init(&pg->kref);
+	INIT_DELAYED_WORK(&pg->rtpg_work, alua_rtpg_work);
+	INIT_LIST_HEAD(&pg->rtpg_list);
+	INIT_LIST_HEAD(&pg->node);
+	INIT_LIST_HEAD(&pg->dh_list);
+	spin_lock_init(&pg->lock);
+
+	spin_lock(&port_group_lock);
+	tmp_pg = alua_find_get_pg(pg->device_id_str, pg->device_id_len,
+				  group_id);
+	if (tmp_pg) {
+		spin_unlock(&port_group_lock);
+		kfree(pg);
+		return tmp_pg;
+	}
 
-	rq->sense = h->sense;
-	memset(rq->sense, 0, SCSI_SENSE_BUFFERSIZE);
-	rq->sense_len = 0;
-	rq->end_io_data = h;
+	list_add(&pg->node, &port_group_list);
+	spin_unlock(&port_group_lock);
 
-	blk_execute_rq_nowait(rq->q, NULL, rq, 1, stpg_endio);
-	return SCSI_DH_OK;
+	return pg;
 }
 
 /*
@@ -318,9 +327,13 @@ static int alua_check_tpgs(struct scsi_device *sdev)
  * Extract the relative target port and the target port group
  * descriptor from the list of identificators.
  */
-static int alua_check_vpd(struct scsi_device *sdev, struct alua_dh_data *h)
+static int alua_check_vpd(struct scsi_device *sdev, struct alua_dh_data *h,
+			  int tpgs)
 {
 	int rel_port = -1, group_id;
+	struct alua_port_group *pg, *old_pg = NULL;
+	bool pg_updated;
+	unsigned long flags;
 
 	group_id = scsi_vpd_tpg_id(sdev, &rel_port);
 	if (group_id < 0) {
@@ -334,32 +347,63 @@ static int alua_check_vpd(struct scsi_device *sdev, struct alua_dh_data *h)
 			    ALUA_DH_NAME);
 		return SCSI_DH_DEV_UNSUPP;
 	}
-	h->state = TPGS_STATE_OPTIMIZED;
-	h->group_id = group_id;
 
+	pg = alua_alloc_pg(sdev, group_id, tpgs);
+	if (IS_ERR(pg)) {
+		if (PTR_ERR(pg) == -ENOMEM)
+			return SCSI_DH_NOMEM;
+		return SCSI_DH_DEV_UNSUPP;
+	}
 	sdev_printk(KERN_INFO, sdev,
-		    "%s: port group %02x rel port %02x\n",
-		    ALUA_DH_NAME, h->group_id, h->rel_port);
+		    "%s: device %s port group %x rel port %x\n",
+		    ALUA_DH_NAME, pg->device_id_str, group_id, rel_port);
+
+	/* Check for existing port group references */
+	spin_lock(&h->pg_lock);
+	old_pg = h->pg;
+	if (old_pg != pg) {
+		/* port group has changed. Update to new port group */
+		if (h->pg) {
+			spin_lock_irqsave(&old_pg->lock, flags);
+			list_del_rcu(&h->node);
+			spin_unlock_irqrestore(&old_pg->lock, flags);
+		}
+		rcu_assign_pointer(h->pg, pg);
+		pg_updated = true;
+	}
 
-	return 0;
+	spin_lock_irqsave(&pg->lock, flags);
+	if (sdev->synchronous_alua)
+		pg->flags |= ALUA_SYNC_STPG;
+	if (pg_updated)
+		list_add_rcu(&h->node, &pg->dh_list);
+	spin_unlock_irqrestore(&pg->lock, flags);
+
+	alua_rtpg_queue(h->pg, sdev, NULL, true);
+	spin_unlock(&h->pg_lock);
+
+	if (old_pg)
+		kref_put(&old_pg->kref, release_port_group);
+
+	return SCSI_DH_OK;
 }
 
-static char print_alua_state(int state)
+static char print_alua_state(unsigned char state)
 {
 	switch (state) {
-	case TPGS_STATE_OPTIMIZED:
+	case SCSI_ACCESS_STATE_OPTIMAL:
 		return 'A';
-	case TPGS_STATE_NONOPTIMIZED:
+	case SCSI_ACCESS_STATE_ACTIVE:
 		return 'N';
-	case TPGS_STATE_STANDBY:
+	case SCSI_ACCESS_STATE_STANDBY:
 		return 'S';
-	case TPGS_STATE_UNAVAILABLE:
+	case SCSI_ACCESS_STATE_UNAVAILABLE:
 		return 'U';
-	case TPGS_STATE_LBA_DEPENDENT:
+	case SCSI_ACCESS_STATE_LBA:
 		return 'L';
-	case TPGS_STATE_OFFLINE:
+	case SCSI_ACCESS_STATE_OFFLINE:
 		return 'O';
-	case TPGS_STATE_TRANSITIONING:
+	case SCSI_ACCESS_STATE_TRANSITIONING:
 		return 'T';
 	default:
 		return 'X';
@@ -371,18 +415,24 @@ static int alua_check_sense(struct scsi_device *sdev,
 {
 	switch (sense_hdr->sense_key) {
 	case NOT_READY:
-		if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x0a)
+		if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x0a) {
 			/*
 			 * LUN Not Accessible - ALUA state transition
 			 */
-			return ADD_TO_MLQUEUE;
+			alua_check(sdev, false);
+			return NEEDS_RETRY;
+		}
 		break;
 	case UNIT_ATTENTION:
-		if (sense_hdr->asc == 0x29 && sense_hdr->ascq == 0x00)
+		if (sense_hdr->asc == 0x29 && sense_hdr->ascq == 0x00) {
 			/*
-			 * Power On, Reset, or Bus Device Reset, just retry.
+			 * Power On, Reset, or Bus Device Reset.
+			 * Might have obscured a state transition,
+			 * so schedule a recheck.
 			 */
+			alua_check(sdev, true);
 			return ADD_TO_MLQUEUE;
+		}
 		if (sense_hdr->asc == 0x29 && sense_hdr->ascq == 0x04)
 			/*
 			 * Device internal reset
@@ -393,16 +443,20 @@ static int alua_check_sense(struct scsi_device *sdev,
 			 * Mode Parameters Changed
 			 */
 			return ADD_TO_MLQUEUE;
-		if (sense_hdr->asc == 0x2a && sense_hdr->ascq == 0x06)
+		if (sense_hdr->asc == 0x2a && sense_hdr->ascq == 0x06) {
 			/*
 			 * ALUA state changed
 			 */
+			alua_check(sdev, true);
 			return ADD_TO_MLQUEUE;
-		if (sense_hdr->asc == 0x2a && sense_hdr->ascq == 0x07)
+		}
+		if (sense_hdr->asc == 0x2a && sense_hdr->ascq == 0x07) {
 			/*
 			 * Implicit ALUA state transition failed
 			 */
+			alua_check(sdev, true);
 			return ADD_TO_MLQUEUE;
+		}
 		if (sense_hdr->asc == 0x3f && sense_hdr->ascq == 0x03)
 			/*
 			 * Inquiry data has changed
@@ -422,38 +476,71 @@ static int alua_check_sense(struct scsi_device *sdev,
 }
 
 /*
+ * alua_tur - Send a TEST UNIT READY
+ * @sdev: device to which the TEST UNIT READY command should be send
+ *
+ * Send a TEST UNIT READY to @sdev to figure out the device state
+ * Returns SCSI_DH_RETRY if the sense code is NOT READY/ALUA TRANSITIONING,
+ * SCSI_DH_OK if no error occurred, and SCSI_DH_IO otherwise.
+ */
+static int alua_tur(struct scsi_device *sdev)
+{
+	struct scsi_sense_hdr sense_hdr;
+	int retval;
+
+	retval = scsi_test_unit_ready(sdev, ALUA_FAILOVER_TIMEOUT * HZ,
+				      ALUA_FAILOVER_RETRIES, &sense_hdr);
+	if (sense_hdr.sense_key == NOT_READY &&
+	    sense_hdr.asc == 0x04 && sense_hdr.ascq == 0x0a)
+		return SCSI_DH_RETRY;
+	else if (retval)
+		return SCSI_DH_IO;
+	else
+		return SCSI_DH_OK;
+}
+
+/*
  * alua_rtpg - Evaluate REPORT TARGET GROUP STATES
  * @sdev: the device to be evaluated.
- * @wait_for_transition: if nonzero, wait ALUA_FAILOVER_TIMEOUT seconds for device to exit transitioning state
  *
  * Evaluate the Target Port Group State.
  * Returns SCSI_DH_DEV_OFFLINED if the path is
  * found to be unusable.
  */
-static int alua_rtpg(struct scsi_device *sdev, struct alua_dh_data *h, int wait_for_transition)
+static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg)
 {
 	struct scsi_sense_hdr sense_hdr;
-	int len, k, off, valid_states = 0;
-	unsigned char *ucp;
+	struct alua_port_group *tmp_pg;
+	int len, k, off, valid_states = 0, bufflen = ALUA_RTPG_SIZE;
+	unsigned char *desc, *buff;
 	unsigned err, retval;
-	unsigned long expiry, interval = 0;
 	unsigned int tpg_desc_tbl_off;
 	unsigned char orig_transition_tmo;
+	unsigned long flags;
 
-	if (!h->transition_tmo)
-		expiry = round_jiffies_up(jiffies + ALUA_FAILOVER_TIMEOUT * HZ);
-	else
-		expiry = round_jiffies_up(jiffies + h->transition_tmo * HZ);
+	if (!pg->expiry) {
+		unsigned long transition_tmo = ALUA_FAILOVER_TIMEOUT * HZ;
+
+		if (pg->transition_tmo)
+			transition_tmo = pg->transition_tmo * HZ;
+
+		pg->expiry = round_jiffies_up(jiffies + transition_tmo);
+	}
+
+	buff = kzalloc(bufflen, GFP_KERNEL);
+	if (!buff)
+		return SCSI_DH_DEV_TEMP_BUSY;
 
  retry:
-	retval = submit_rtpg(sdev, h);
+	retval = submit_rtpg(sdev, buff, bufflen, &sense_hdr, pg->flags);
+
 	if (retval) {
-		if (!scsi_normalize_sense(h->sense, SCSI_SENSE_BUFFERSIZE,
-					  &sense_hdr)) {
+		if (!scsi_sense_valid(&sense_hdr)) {
 			sdev_printk(KERN_INFO, sdev,
 				    "%s: rtpg failed, result %d\n",
 				    ALUA_DH_NAME, retval);
-			if (driver_byte(retval) == DRIVER_BUSY)
+			kfree(buff);
+			if (driver_byte(retval) == DRIVER_ERROR)
 				return SCSI_DH_DEV_TEMP_BUSY;
 			return SCSI_DH_IO;
 		}
@@ -466,10 +553,10 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_dh_data *h, int wait_
 		 * The retry without rtpg_ext_hdr_req set
 		 * handles this.
 		 */
-		if (!(h->flags & ALUA_RTPG_EXT_HDR_UNSUPP) &&
+		if (!(pg->flags & ALUA_RTPG_EXT_HDR_UNSUPP) &&
 		    sense_hdr.sense_key == ILLEGAL_REQUEST &&
 		    sense_hdr.asc == 0x24 && sense_hdr.ascq == 0) {
-			h->flags |= ALUA_RTPG_EXT_HDR_UNSUPP;
+			pg->flags |= ALUA_RTPG_EXT_HDR_UNSUPP;
 			goto retry;
 		}
 		/*
@@ -481,65 +568,96 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_dh_data *h, int wait_
 			err = SCSI_DH_RETRY;
 		else if (sense_hdr.sense_key == UNIT_ATTENTION)
 			err = SCSI_DH_RETRY;
-		if (err == SCSI_DH_RETRY && time_before(jiffies, expiry)) {
+		if (err == SCSI_DH_RETRY &&
+		    pg->expiry != 0 && time_before(jiffies, pg->expiry)) {
 			sdev_printk(KERN_ERR, sdev, "%s: rtpg retry\n",
 				    ALUA_DH_NAME);
 			scsi_print_sense_hdr(sdev, ALUA_DH_NAME, &sense_hdr);
-			goto retry;
+			return err;
 		}
 		sdev_printk(KERN_ERR, sdev, "%s: rtpg failed\n",
 			    ALUA_DH_NAME);
 		scsi_print_sense_hdr(sdev, ALUA_DH_NAME, &sense_hdr);
+		kfree(buff);
+		pg->expiry = 0;
 		return SCSI_DH_IO;
 	}
 
-	len = get_unaligned_be32(&h->buff[0]) + 4;
+	len = get_unaligned_be32(&buff[0]) + 4;
 
-	if (len > h->bufflen) {
+	if (len > bufflen) {
 		/* Resubmit with the correct length */
-		if (realloc_buffer(h, len)) {
+		kfree(buff);
+		bufflen = len;
+		buff = kmalloc(bufflen, GFP_KERNEL);
+		if (!buff) {
 			sdev_printk(KERN_WARNING, sdev,
 				    "%s: kmalloc buffer failed\n",__func__);
 			/* Temporary failure, bypass */
+			pg->expiry = 0;
 			return SCSI_DH_DEV_TEMP_BUSY;
 		}
 		goto retry;
 	}
 
-	orig_transition_tmo = h->transition_tmo;
-	if ((h->buff[4] & RTPG_FMT_MASK) == RTPG_FMT_EXT_HDR && h->buff[5] != 0)
-		h->transition_tmo = h->buff[5];
+	orig_transition_tmo = pg->transition_tmo;
+	if ((buff[4] & RTPG_FMT_MASK) == RTPG_FMT_EXT_HDR && buff[5] != 0)
+		pg->transition_tmo = buff[5];
 	else
-		h->transition_tmo = ALUA_FAILOVER_TIMEOUT;
+		pg->transition_tmo = ALUA_FAILOVER_TIMEOUT;
 
-	if (wait_for_transition && (orig_transition_tmo != h->transition_tmo)) {
+	if (orig_transition_tmo != pg->transition_tmo) {
 		sdev_printk(KERN_INFO, sdev,
 			    "%s: transition timeout set to %d seconds\n",
-			    ALUA_DH_NAME, h->transition_tmo);
-		expiry = jiffies + h->transition_tmo * HZ;
+			    ALUA_DH_NAME, pg->transition_tmo);
+		pg->expiry = jiffies + pg->transition_tmo * HZ;
 	}
 
-	if ((h->buff[4] & RTPG_FMT_MASK) == RTPG_FMT_EXT_HDR)
+	if ((buff[4] & RTPG_FMT_MASK) == RTPG_FMT_EXT_HDR)
 		tpg_desc_tbl_off = 8;
 	else
 		tpg_desc_tbl_off = 4;
 
-	for (k = tpg_desc_tbl_off, ucp = h->buff + tpg_desc_tbl_off;
+	for (k = tpg_desc_tbl_off, desc = buff + tpg_desc_tbl_off;
 	     k < len;
-	     k += off, ucp += off) {
-
-		if (h->group_id == get_unaligned_be16(&ucp[2])) {
-			h->state = ucp[0] & 0x0f;
-			h->pref = ucp[0] >> 7;
-			valid_states = ucp[1];
+	     k += off, desc += off) {
+		u16 group_id = get_unaligned_be16(&desc[2]);
+
+		spin_lock_irqsave(&port_group_lock, flags);
+		tmp_pg = alua_find_get_pg(pg->device_id_str, pg->device_id_len,
+					  group_id);
+		spin_unlock_irqrestore(&port_group_lock, flags);
+		if (tmp_pg) {
+			if (spin_trylock_irqsave(&tmp_pg->lock, flags)) {
+				if ((tmp_pg == pg) ||
+				    !(tmp_pg->flags & ALUA_PG_RUNNING)) {
+					struct alua_dh_data *h;
+
+					tmp_pg->state = desc[0] & 0x0f;
+					tmp_pg->pref = desc[0] >> 7;
+					rcu_read_lock();
+					list_for_each_entry_rcu(h,
+						&tmp_pg->dh_list, node) {
+						/* h->sdev should always be valid */
+						BUG_ON(!h->sdev);
+						h->sdev->access_state = desc[0];
+					}
+					rcu_read_unlock();
+				}
+				if (tmp_pg == pg)
+					valid_states = desc[1];
+				spin_unlock_irqrestore(&tmp_pg->lock, flags);
+			}
+			kref_put(&tmp_pg->kref, release_port_group);
 		}
-		off = 8 + (ucp[7] * 4);
+		off = 8 + (desc[7] * 4);
 	}
 
+	spin_lock_irqsave(&pg->lock, flags);
 	sdev_printk(KERN_INFO, sdev,
 		    "%s: port group %02x state %c %s supports %c%c%c%c%c%c%c\n",
-		    ALUA_DH_NAME, h->group_id, print_alua_state(h->state),
-		    h->pref ? "preferred" : "non-preferred",
+		    ALUA_DH_NAME, pg->group_id, print_alua_state(pg->state),
+		    pg->pref ? "preferred" : "non-preferred",
 		    valid_states&TPGS_SUPPORT_TRANSITION?'T':'t',
 		    valid_states&TPGS_SUPPORT_OFFLINE?'O':'o',
 		    valid_states&TPGS_SUPPORT_LBA_DEPENDENT?'L':'l',
@@ -548,36 +666,236 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_dh_data *h, int wait_
 		    valid_states&TPGS_SUPPORT_NONOPTIMIZED?'N':'n',
 		    valid_states&TPGS_SUPPORT_OPTIMIZED?'A':'a');
 
-	switch (h->state) {
-	case TPGS_STATE_TRANSITIONING:
-		if (wait_for_transition) {
-			if (time_before(jiffies, expiry)) {
-				/* State transition, retry */
-				interval += 2000;
-				msleep(interval);
-				goto retry;
-			}
+	switch (pg->state) {
+	case SCSI_ACCESS_STATE_TRANSITIONING:
+		if (time_before(jiffies, pg->expiry)) {
+			/* State transition, retry */
+			pg->interval = 2;
 			err = SCSI_DH_RETRY;
 		} else {
-			err = SCSI_DH_OK;
-		}
+			struct alua_dh_data *h;
 
-		/* Transitioning time exceeded, set port to standby */
-		h->state = TPGS_STATE_STANDBY;
+			/* Transitioning time exceeded, set port to standby */
+			err = SCSI_DH_IO;
+			pg->state = SCSI_ACCESS_STATE_STANDBY;
+			pg->expiry = 0;
+			rcu_read_lock();
+			list_for_each_entry_rcu(h, &pg->dh_list, node) {
+				BUG_ON(!h->sdev);
+				h->sdev->access_state =
+					(pg->state & SCSI_ACCESS_STATE_MASK);
+				if (pg->pref)
+					h->sdev->access_state |=
+						SCSI_ACCESS_STATE_PREFERRED;
+			}
+			rcu_read_unlock();
+		}
 		break;
-	case TPGS_STATE_OFFLINE:
+	case SCSI_ACCESS_STATE_OFFLINE:
 		/* Path unusable */
 		err = SCSI_DH_DEV_OFFLINED;
+		pg->expiry = 0;
 		break;
 	default:
 		/* Useable path if active */
 		err = SCSI_DH_OK;
+		pg->expiry = 0;
 		break;
 	}
+	spin_unlock_irqrestore(&pg->lock, flags);
+	kfree(buff);
 	return err;
 }
 
 /*
+ * alua_stpg - Issue a SET TARGET PORT GROUP command
+ *
+ * Issue a SET TARGET PORT GROUP command and evaluate the
+ * response. Returns SCSI_DH_RETRY per default to trigger
+ * a re-evaluation of the target group state or SCSI_DH_OK
+ * if no further action needs to be taken.
+ */
+static unsigned alua_stpg(struct scsi_device *sdev, struct alua_port_group *pg)
+{
+	int retval;
+	struct scsi_sense_hdr sense_hdr;
+
+	if (!(pg->tpgs & TPGS_MODE_EXPLICIT)) {
+		/* Only implicit ALUA supported, retry */
+		return SCSI_DH_RETRY;
+	}
+	switch (pg->state) {
+	case SCSI_ACCESS_STATE_OPTIMAL:
+		return SCSI_DH_OK;
+	case SCSI_ACCESS_STATE_ACTIVE:
+		if ((pg->flags & ALUA_OPTIMIZE_STPG) &&
+		    !pg->pref &&
+		    (pg->tpgs & TPGS_MODE_IMPLICIT))
+			return SCSI_DH_OK;
+		break;
+	case SCSI_ACCESS_STATE_STANDBY:
+	case SCSI_ACCESS_STATE_UNAVAILABLE:
+		break;
+	case SCSI_ACCESS_STATE_OFFLINE:
+		return SCSI_DH_IO;
+	case SCSI_ACCESS_STATE_TRANSITIONING:
+		break;
+	default:
+		sdev_printk(KERN_INFO, sdev,
+			    "%s: stpg failed, unhandled TPGS state %d",
+			    ALUA_DH_NAME, pg->state);
+		return SCSI_DH_NOSYS;
+	}
+	retval = submit_stpg(sdev, pg->group_id, &sense_hdr);
+
+	if (retval) {
+		if (!scsi_sense_valid(&sense_hdr)) {
+			sdev_printk(KERN_INFO, sdev,
+				    "%s: stpg failed, result %d",
+				    ALUA_DH_NAME, retval);
+			if (driver_byte(retval) == DRIVER_ERROR)
+				return SCSI_DH_DEV_TEMP_BUSY;
+		} else {
+			sdev_printk(KERN_INFO, sdev, "%s: stpg failed\n",
+				    ALUA_DH_NAME);
+			scsi_print_sense_hdr(sdev, ALUA_DH_NAME, &sense_hdr);
+		}
+	}
+	/* Retry RTPG */
+	return SCSI_DH_RETRY;
+}
+
+static void alua_rtpg_work(struct work_struct *work)
+{
+	struct alua_port_group *pg =
+		container_of(work, struct alua_port_group, rtpg_work.work);
+	struct scsi_device *sdev;
+	LIST_HEAD(qdata_list);
+	int err = SCSI_DH_OK;
+	struct alua_queue_data *qdata, *tmp;
+	unsigned long flags;
+	struct workqueue_struct *alua_wq = kaluad_wq;
+
+	spin_lock_irqsave(&pg->lock, flags);
+	sdev = pg->rtpg_sdev;
+	if (!sdev) {
+		WARN_ON(pg->flags & ALUA_PG_RUN_RTPG);
+		WARN_ON(pg->flags & ALUA_PG_RUN_STPG);
+		spin_unlock_irqrestore(&pg->lock, flags);
+		return;
+	}
+	if (pg->flags & ALUA_SYNC_STPG)
+		alua_wq = kaluad_sync_wq;
+	pg->flags |= ALUA_PG_RUNNING;
+	if (pg->flags & ALUA_PG_RUN_RTPG) {
+		int state = pg->state;
+
+		pg->flags &= ~ALUA_PG_RUN_RTPG;
+		spin_unlock_irqrestore(&pg->lock, flags);
+		if (state == SCSI_ACCESS_STATE_TRANSITIONING) {
+			if (alua_tur(sdev) == SCSI_DH_RETRY) {
+				spin_lock_irqsave(&pg->lock, flags);
+				pg->flags &= ~ALUA_PG_RUNNING;
+				pg->flags |= ALUA_PG_RUN_RTPG;
+				spin_unlock_irqrestore(&pg->lock, flags);
+				queue_delayed_work(alua_wq, &pg->rtpg_work,
+						   pg->interval * HZ);
+				return;
+			}
+			/* Send RTPG on failure or if TUR indicates SUCCESS */
+		}
+		err = alua_rtpg(sdev, pg);
+		spin_lock_irqsave(&pg->lock, flags);
+		if (err == SCSI_DH_RETRY || pg->flags & ALUA_PG_RUN_RTPG) {
+			pg->flags &= ~ALUA_PG_RUNNING;
+			pg->flags |= ALUA_PG_RUN_RTPG;
+			spin_unlock_irqrestore(&pg->lock, flags);
+			queue_delayed_work(alua_wq, &pg->rtpg_work,
+					   pg->interval * HZ);
+			return;
+		}
+		if (err != SCSI_DH_OK)
+			pg->flags &= ~ALUA_PG_RUN_STPG;
+	}
+	if (pg->flags & ALUA_PG_RUN_STPG) {
+		pg->flags &= ~ALUA_PG_RUN_STPG;
+		spin_unlock_irqrestore(&pg->lock, flags);
+		err = alua_stpg(sdev, pg);
+		spin_lock_irqsave(&pg->lock, flags);
+		if (err == SCSI_DH_RETRY || pg->flags & ALUA_PG_RUN_RTPG) {
+			pg->flags |= ALUA_PG_RUN_RTPG;
+			pg->interval = 0;
+			pg->flags &= ~ALUA_PG_RUNNING;
+			spin_unlock_irqrestore(&pg->lock, flags);
+			queue_delayed_work(alua_wq, &pg->rtpg_work,
+					   pg->interval * HZ);
+			return;
+		}
+	}
+
+	list_splice_init(&pg->rtpg_list, &qdata_list);
+	pg->rtpg_sdev = NULL;
+	spin_unlock_irqrestore(&pg->lock, flags);
+
+	list_for_each_entry_safe(qdata, tmp, &qdata_list, entry) {
+		list_del(&qdata->entry);
+		if (qdata->callback_fn)
+			qdata->callback_fn(qdata->callback_data, err);
+		kfree(qdata);
+	}
+	spin_lock_irqsave(&pg->lock, flags);
+	pg->flags &= ~ALUA_PG_RUNNING;
+	spin_unlock_irqrestore(&pg->lock, flags);
+	scsi_device_put(sdev);
+	kref_put(&pg->kref, release_port_group);
+}
+
+static void alua_rtpg_queue(struct alua_port_group *pg,
+			    struct scsi_device *sdev,
+			    struct alua_queue_data *qdata, bool force)
+{
+	int start_queue = 0;
+	unsigned long flags;
+	struct workqueue_struct *alua_wq = kaluad_wq;
+
+	if (!pg)
+		return;
+
+	spin_lock_irqsave(&pg->lock, flags);
+	if (qdata) {
+		list_add_tail(&qdata->entry, &pg->rtpg_list);
+		pg->flags |= ALUA_PG_RUN_STPG;
+		force = true;
+	}
+	if (pg->rtpg_sdev == NULL) {
+		pg->interval = 0;
+		pg->flags |= ALUA_PG_RUN_RTPG;
+		kref_get(&pg->kref);
+		pg->rtpg_sdev = sdev;
+		scsi_device_get(sdev);
+		start_queue = 1;
+	} else if (!(pg->flags & ALUA_PG_RUN_RTPG) && force) {
+		pg->flags |= ALUA_PG_RUN_RTPG;
+		/* Do not queue if the worker is already running */
+		if (!(pg->flags & ALUA_PG_RUNNING)) {
+			kref_get(&pg->kref);
+			start_queue = 1;
+		}
+	}
+
+	if (pg->flags & ALUA_SYNC_STPG)
+		alua_wq = kaluad_sync_wq;
+	spin_unlock_irqrestore(&pg->lock, flags);
+
+	if (start_queue &&
+	    !queue_delayed_work(alua_wq, &pg->rtpg_work,
+				msecs_to_jiffies(ALUA_RTPG_DELAY_MSECS))) {
+		scsi_device_put(sdev);
+		kref_put(&pg->kref, release_port_group);
+	}
+}
+
+/*
  * alua_initialize - Initialize ALUA state
  * @sdev: the device to be initialized
  *
@@ -586,21 +904,14 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_dh_data *h, int wait_
  */
 static int alua_initialize(struct scsi_device *sdev, struct alua_dh_data *h)
 {
-	int err = SCSI_DH_DEV_UNSUPP;
-
-	h->tpgs = alua_check_tpgs(sdev);
-	if (h->tpgs == TPGS_MODE_NONE)
-		goto out;
-
-	err = alua_check_vpd(sdev, h);
-	if (err != SCSI_DH_OK)
-		goto out;
-
-	err = alua_rtpg(sdev, h, 0);
-	if (err != SCSI_DH_OK)
-		goto out;
-
-out:
+	int err = SCSI_DH_DEV_UNSUPP, tpgs;
+
+	mutex_lock(&h->init_mutex);
+	tpgs = alua_check_tpgs(sdev);
+	if (tpgs != TPGS_MODE_NONE)
+		err = alua_check_vpd(sdev, h, tpgs);
+	h->init_error = err;
+	mutex_unlock(&h->init_mutex);
 	return err;
 }
 /*
@@ -615,9 +926,11 @@ out:
 static int alua_set_params(struct scsi_device *sdev, const char *params)
 {
 	struct alua_dh_data *h = sdev->handler_data;
+	struct alua_port_group __rcu *pg = NULL;
 	unsigned int optimize = 0, argc;
 	const char *p = params;
 	int result = SCSI_DH_OK;
+	unsigned long flags;
 
 	if ((sscanf(params, "%u", &argc) != 1) || (argc != 1))
 		return -EINVAL;
@@ -627,18 +940,23 @@ static int alua_set_params(struct scsi_device *sdev, const char *params)
 	if ((sscanf(p, "%u", &optimize) != 1) || (optimize > 1))
 		return -EINVAL;
 
+	rcu_read_lock();
+	pg = rcu_dereference(h->pg);
+	if (!pg) {
+		rcu_read_unlock();
+		return -ENXIO;
+	}
+	spin_lock_irqsave(&pg->lock, flags);
 	if (optimize)
-		h->flags |= ALUA_OPTIMIZE_STPG;
+		pg->flags |= ALUA_OPTIMIZE_STPG;
 	else
-		h->flags &= ~ALUA_OPTIMIZE_STPG;
+		pg->flags &= ~ALUA_OPTIMIZE_STPG;
+	spin_unlock_irqrestore(&pg->lock, flags);
+	rcu_read_unlock();
 
 	return result;
 }
 
-static uint optimize_stpg;
-module_param(optimize_stpg, uint, S_IRUGO|S_IWUSR);
-MODULE_PARM_DESC(optimize_stpg, "Allow use of a non-optimized path, rather than sending a STPG, when implicit TPGS is supported (0=No,1=Yes). Default is 0.");
-
 /*
  * alua_activate - activate a path
  * @sdev: device on the path to be activated
@@ -654,48 +972,33 @@ static int alua_activate(struct scsi_device *sdev,
 {
 	struct alua_dh_data *h = sdev->handler_data;
 	int err = SCSI_DH_OK;
-	int stpg = 0;
+	struct alua_queue_data *qdata;
+	struct alua_port_group __rcu *pg;
 
-	err = alua_rtpg(sdev, h, 1);
-	if (err != SCSI_DH_OK)
+	qdata = kzalloc(sizeof(*qdata), GFP_KERNEL);
+	if (!qdata) {
+		err = SCSI_DH_RES_TEMP_UNAVAIL;
 		goto out;
-
-	if (optimize_stpg)
-		h->flags |= ALUA_OPTIMIZE_STPG;
-
-	if (h->tpgs & TPGS_MODE_EXPLICIT) {
-		switch (h->state) {
-		case TPGS_STATE_NONOPTIMIZED:
-			stpg = 1;
-			if ((h->flags & ALUA_OPTIMIZE_STPG) &&
-			    (!h->pref) &&
-			    (h->tpgs & TPGS_MODE_IMPLICIT))
-				stpg = 0;
-			break;
-		case TPGS_STATE_STANDBY:
-		case TPGS_STATE_UNAVAILABLE:
-			stpg = 1;
-			break;
-		case TPGS_STATE_OFFLINE:
-			err = SCSI_DH_IO;
-			break;
-		case TPGS_STATE_TRANSITIONING:
-			err = SCSI_DH_RETRY;
-			break;
-		default:
-			break;
-		}
 	}
-
-	if (stpg) {
-		h->callback_fn = fn;
-		h->callback_data = data;
-		err = submit_stpg(h);
-		if (err == SCSI_DH_OK)
-			return 0;
-		h->callback_fn = h->callback_data = NULL;
+	qdata->callback_fn = fn;
+	qdata->callback_data = data;
+
+	mutex_lock(&h->init_mutex);
+	rcu_read_lock();
+	pg = rcu_dereference(h->pg);
+	if (!pg || !kref_get_unless_zero(&pg->kref)) {
+		rcu_read_unlock();
+		kfree(qdata);
+		err = h->init_error;
+		mutex_unlock(&h->init_mutex);
+		goto out;
 	}
+	fn = NULL;
+	rcu_read_unlock();
+	mutex_unlock(&h->init_mutex);
 
+	alua_rtpg_queue(pg, sdev, qdata, true);
+	kref_put(&pg->kref, release_port_group);
 out:
 	if (fn)
 		fn(data, err);
@@ -703,6 +1006,29 @@ out:
 }
 
 /*
+ * alua_check - check path status
+ * @sdev: device on the path to be checked
+ *
+ * Check the device status
+ */
+static void alua_check(struct scsi_device *sdev, bool force)
+{
+	struct alua_dh_data *h = sdev->handler_data;
+	struct alua_port_group *pg;
+
+	rcu_read_lock();
+	pg = rcu_dereference(h->pg);
+	if (!pg || !kref_get_unless_zero(&pg->kref)) {
+		rcu_read_unlock();
+		return;
+	}
+	rcu_read_unlock();
+
+	alua_rtpg_queue(pg, sdev, NULL, force);
+	kref_put(&pg->kref, release_port_group);
+}
+
+/*
  * alua_prep_fn - request callback
  *
  * Fail I/O to all paths not in state
@@ -711,13 +1037,20 @@ out:
 static int alua_prep_fn(struct scsi_device *sdev, struct request *req)
 {
 	struct alua_dh_data *h = sdev->handler_data;
+	struct alua_port_group __rcu *pg;
+	unsigned char state = SCSI_ACCESS_STATE_OPTIMAL;
 	int ret = BLKPREP_OK;
 
-	if (h->state == TPGS_STATE_TRANSITIONING)
+	rcu_read_lock();
+	pg = rcu_dereference(h->pg);
+	if (pg)
+		state = pg->state;
+	rcu_read_unlock();
+	if (state == SCSI_ACCESS_STATE_TRANSITIONING)
 		ret = BLKPREP_DEFER;
-	else if (h->state != TPGS_STATE_OPTIMIZED &&
-		 h->state != TPGS_STATE_NONOPTIMIZED &&
-		 h->state != TPGS_STATE_LBA_DEPENDENT) {
+	else if (state != SCSI_ACCESS_STATE_OPTIMAL &&
+		 state != SCSI_ACCESS_STATE_ACTIVE &&
+		 state != SCSI_ACCESS_STATE_LBA) {
 		ret = BLKPREP_KILL;
 		req->cmd_flags |= REQ_QUIET;
 	}
@@ -725,6 +1058,13 @@ static int alua_prep_fn(struct scsi_device *sdev, struct request *req)
 
 }
 
+static void alua_rescan(struct scsi_device *sdev)
+{
+	struct alua_dh_data *h = sdev->handler_data;
+
+	alua_initialize(sdev, h);
+}
+
 /*
  * alua_bus_attach - Attach device handler
  * @sdev: device to be attached to
@@ -732,20 +1072,21 @@ static int alua_prep_fn(struct scsi_device *sdev, struct request *req)
 static int alua_bus_attach(struct scsi_device *sdev)
 {
 	struct alua_dh_data *h;
-	int err;
+	int err, ret = -EINVAL;
 
 	h = kzalloc(sizeof(*h) , GFP_KERNEL);
 	if (!h)
 		return -ENOMEM;
-	h->tpgs = TPGS_MODE_UNINITIALIZED;
-	h->state = TPGS_STATE_OPTIMIZED;
-	h->group_id = -1;
-	h->rel_port = -1;
-	h->buff = h->inq;
-	h->bufflen = ALUA_INQUIRY_SIZE;
+	spin_lock_init(&h->pg_lock);
+	rcu_assign_pointer(h->pg, NULL);
+	h->init_error = SCSI_DH_OK;
 	h->sdev = sdev;
+	INIT_LIST_HEAD(&h->node);
 
+	mutex_init(&h->init_mutex);
 	err = alua_initialize(sdev, h);
+	if (err == SCSI_DH_NOMEM)
+		ret = -ENOMEM;
 	if (err != SCSI_DH_OK && err != SCSI_DH_DEV_OFFLINED)
 		goto failed;
 
@@ -753,7 +1094,7 @@ static int alua_bus_attach(struct scsi_device *sdev)
 	return 0;
 failed:
 	kfree(h);
-	return -EINVAL;
+	return ret;
 }
 
 /*
@@ -763,9 +1104,19 @@ failed:
 static void alua_bus_detach(struct scsi_device *sdev)
 {
 	struct alua_dh_data *h = sdev->handler_data;
-
-	if (h->buff && h->inq != h->buff)
-		kfree(h->buff);
+	struct alua_port_group *pg;
+
+	spin_lock(&h->pg_lock);
+	pg = h->pg;
+	rcu_assign_pointer(h->pg, NULL);
+	h->sdev = NULL;
+	spin_unlock(&h->pg_lock);
+	if (pg) {
+		spin_lock(&pg->lock);
+		list_del_rcu(&h->node);
+		spin_unlock(&pg->lock);
+		kref_put(&pg->kref, release_port_group);
+	}
 	sdev->handler_data = NULL;
 	kfree(h);
 }
@@ -778,6 +1129,7 @@ static struct scsi_device_handler alua_dh = {
 	.prep_fn = alua_prep_fn,
 	.check_sense = alua_check_sense,
 	.activate = alua_activate,
+	.rescan = alua_rescan,
 	.set_params = alua_set_params,
 };
 
@@ -785,16 +1137,31 @@ static int __init alua_init(void)
 {
 	int r;
 
+	kaluad_wq = alloc_workqueue("kaluad", WQ_MEM_RECLAIM, 0);
+	if (!kaluad_wq) {
+		/* Temporary failure, bypass */
+		return SCSI_DH_DEV_TEMP_BUSY;
+	}
+	kaluad_sync_wq = create_workqueue("kaluad_sync");
+	if (!kaluad_sync_wq) {
+		destroy_workqueue(kaluad_wq);
+		return SCSI_DH_DEV_TEMP_BUSY;
+	}
 	r = scsi_register_device_handler(&alua_dh);
-	if (r != 0)
+	if (r != 0) {
 		printk(KERN_ERR "%s: Failed to register scsi device handler",
 			ALUA_DH_NAME);
+		destroy_workqueue(kaluad_sync_wq);
+		destroy_workqueue(kaluad_wq);
+	}
 	return r;
 }
 
 static void __exit alua_exit(void)
 {
 	scsi_unregister_device_handler(&alua_dh);
+	destroy_workqueue(kaluad_sync_wq);
+	destroy_workqueue(kaluad_wq);
 }
 
 module_init(alua_init);
diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c
index e6fb97cb12f4..375d81850f15 100644
--- a/drivers/scsi/device_handler/scsi_dh_emc.c
+++ b/drivers/scsi/device_handler/scsi_dh_emc.c
@@ -199,7 +199,12 @@ static int parse_sp_info_reply(struct scsi_device *sdev,
 	csdev->lun_state = csdev->buffer[4];
 	csdev->current_sp = csdev->buffer[8];
 	csdev->port = csdev->buffer[7];
-
+	if (csdev->lun_state == CLARIION_LUN_OWNED)
+		sdev->access_state = SCSI_ACCESS_STATE_OPTIMAL;
+	else
+		sdev->access_state = SCSI_ACCESS_STATE_STANDBY;
+	if (csdev->default_sp == csdev->current_sp)
+		sdev->access_state |= SCSI_ACCESS_STATE_PREFERRED;
 out:
 	return err;
 }
diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c
index 361358134315..06fbd0b0c68a 100644
--- a/drivers/scsi/device_handler/scsi_dh_rdac.c
+++ b/drivers/scsi/device_handler/scsi_dh_rdac.c
@@ -165,6 +165,7 @@ struct rdac_controller {
 	struct work_struct	ms_work;
 	struct scsi_device	*ms_sdev;
 	struct list_head	ms_head;
+	struct list_head	dh_list;
 };
 
 struct c2_inquiry {
@@ -181,7 +182,9 @@ struct c2_inquiry {
 };
 
 struct rdac_dh_data {
+	struct list_head	node;
 	struct rdac_controller	*ctlr;
+	struct scsi_device	*sdev;
 #define UNINITIALIZED_LUN	(1 << 8)
 	unsigned		lun;
 
@@ -392,6 +395,7 @@ static struct rdac_controller *get_controller(int index, char *array_name,
 	INIT_WORK(&ctlr->ms_work, send_mode_select);
 	INIT_LIST_HEAD(&ctlr->ms_head);
 	list_add(&ctlr->node, &ctlr_list);
+	INIT_LIST_HEAD(&ctlr->dh_list);
 
 	return ctlr;
 }
@@ -455,7 +459,8 @@ static int get_lun_info(struct scsi_device *sdev, struct rdac_dh_data *h,
 
 static int check_ownership(struct scsi_device *sdev, struct rdac_dh_data *h)
 {
-	int err;
+	int err, access_state;
+	struct rdac_dh_data *tmp;
 	struct c9_inquiry *inqp;
 
 	h->state = RDAC_STATE_ACTIVE;
@@ -471,19 +476,31 @@ static int check_ownership(struct scsi_device *sdev, struct rdac_dh_data *h)
 			h->mode = RDAC_MODE; /* LUN in RDAC mode */
 
 		/* Update ownership */
-		if (inqp->avte_cvp & 0x1)
+		if (inqp->avte_cvp & 0x1) {
 			h->lun_state = RDAC_LUN_OWNED;
-		else {
+			access_state = SCSI_ACCESS_STATE_OPTIMAL;
+		} else {
 			h->lun_state = RDAC_LUN_UNOWNED;
-			if (h->mode == RDAC_MODE)
+			if (h->mode == RDAC_MODE) {
 				h->state = RDAC_STATE_PASSIVE;
+				access_state = SCSI_ACCESS_STATE_STANDBY;
+			} else
+				access_state = SCSI_ACCESS_STATE_ACTIVE;
 		}
 
 		/* Update path prio*/
-		if (inqp->path_prio & 0x1)
+		if (inqp->path_prio & 0x1) {
 			h->preferred = RDAC_PREFERRED;
-		else
+			access_state |= SCSI_ACCESS_STATE_PREFERRED;
+		} else
 			h->preferred = RDAC_NON_PREFERRED;
+		rcu_read_lock();
+		list_for_each_entry_rcu(tmp, &h->ctlr->dh_list, node) {
+			/* h->sdev should always be valid */
+			BUG_ON(!tmp->sdev);
+			tmp->sdev->access_state = access_state;
+		}
+		rcu_read_unlock();
 	}
 
 	return err;
@@ -508,6 +525,10 @@ static int initialize_controller(struct scsi_device *sdev,
 		h->ctlr = get_controller(index, array_name, array_id, sdev);
 		if (!h->ctlr)
 			err = SCSI_DH_RES_TEMP_UNAVAIL;
+		else {
+			list_add_rcu(&h->node, &h->ctlr->dh_list);
+			h->sdev = sdev;
+		}
 		spin_unlock(&list_lock);
 	}
 	return err;
@@ -562,7 +583,7 @@ static int mode_select_handle_sense(struct scsi_device *sdev,
 			/*
 			 * Command Lock contention
 			 */
-			err = SCSI_DH_RETRY;
+			err = SCSI_DH_IMM_RETRY;
 		break;
 	default:
 		break;
@@ -612,6 +633,8 @@ retry:
 		err = mode_select_handle_sense(sdev, h->sense);
 		if (err == SCSI_DH_RETRY && retry_cnt--)
 			goto retry;
+		if (err == SCSI_DH_IMM_RETRY)
+			goto retry;
 	}
 	if (err == SCSI_DH_OK) {
 		h->state = RDAC_STATE_ACTIVE;
@@ -827,8 +850,11 @@ static void rdac_bus_detach( struct scsi_device *sdev )
 		flush_workqueue(kmpath_rdacd);
 
 	spin_lock(&list_lock);
-	if (h->ctlr)
+	if (h->ctlr) {
+		list_del_rcu(&h->node);
+		h->sdev = NULL;
 		kref_put(&h->ctlr->kref, release_controller);
+	}
 	spin_unlock(&list_lock);
 	sdev->handler_data = NULL;
 	kfree(h);
diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c
index d4cda5e9600e..21c8d210c456 100644
--- a/drivers/scsi/dpt_i2o.c
+++ b/drivers/scsi/dpt_i2o.c
@@ -180,11 +180,14 @@ static u8 adpt_read_blink_led(adpt_hba* host)
  *============================================================================
  */
 
+#ifdef MODULE
 static struct pci_device_id dptids[] = {
 	{ PCI_DPT_VENDOR_ID, PCI_DPT_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,},
 	{ PCI_DPT_VENDOR_ID, PCI_DPT_RAPTOR_DEVICE_ID, PCI_ANY_ID, PCI_ANY_ID,},
 	{ 0, }
 };
+#endif
+
 MODULE_DEVICE_TABLE(pci,dptids);
 
 static int adpt_detect(struct scsi_host_template* sht)
diff --git a/drivers/scsi/esas2r/esas2r_ioctl.c b/drivers/scsi/esas2r/esas2r_ioctl.c
index baf913047b48..3e8483410f61 100644
--- a/drivers/scsi/esas2r/esas2r_ioctl.c
+++ b/drivers/scsi/esas2r/esas2r_ioctl.c
@@ -1360,14 +1360,15 @@ int esas2r_ioctl_handler(void *hostdata, int cmd, void __user *arg)
 	if (ioctl->header.channel == 0xFF) {
 		a = (struct esas2r_adapter *)hostdata;
 	} else {
-		a = esas2r_adapters[ioctl->header.channel];
-		if (ioctl->header.channel >= MAX_ADAPTERS || (a == NULL)) {
+		if (ioctl->header.channel >= MAX_ADAPTERS ||
+			esas2r_adapters[ioctl->header.channel] == NULL) {
 			ioctl->header.return_code = IOCTL_BAD_CHANNEL;
 			esas2r_log(ESAS2R_LOG_WARN, "bad channel value");
 			kfree(ioctl);
 
 			return -ENOTSUPP;
 		}
+		a = esas2r_adapters[ioctl->header.channel];
 	}
 
 	switch (cmd) {
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index 34a1b1f333b4..3e83d485f743 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -1118,7 +1118,8 @@ static void fcoe_ctlr_recv_adv(struct fcoe_ctlr *fip, struct sk_buff *skb)
 	 * If this is the first validated FCF, note the time and
 	 * set a timer to trigger selection.
 	 */
-	if (mtu_valid && !fip->sel_fcf && fcoe_ctlr_fcf_usable(fcf)) {
+	if (mtu_valid && !fip->sel_fcf && !fip->sel_time &&
+	    fcoe_ctlr_fcf_usable(fcf)) {
 		fip->sel_time = jiffies +
 			msecs_to_jiffies(FCOE_CTLR_START_DELAY);
 		if (!timer_pending(&fip->timer) ||
diff --git a/drivers/scsi/fdomain.c b/drivers/scsi/fdomain.c
index eefe14d453db..b87ab38a4530 100644
--- a/drivers/scsi/fdomain.c
+++ b/drivers/scsi/fdomain.c
@@ -1768,7 +1768,7 @@ struct scsi_host_template fdomain_driver_template = {
 };
 
 #ifndef PCMCIA
-#ifdef CONFIG_PCI
+#if defined(CONFIG_PCI) && defined(MODULE)
 
 static struct pci_device_id fdomain_pci_tbl[] = {
 	{ PCI_VENDOR_ID_FD, PCI_DEVICE_ID_FD_36C70,
diff --git a/drivers/scsi/gdth.c b/drivers/scsi/gdth.c
index 71e138044379..0a767740bf02 100644
--- a/drivers/scsi/gdth.c
+++ b/drivers/scsi/gdth.c
@@ -2838,7 +2838,6 @@ static gdth_evt_str *gdth_store_event(gdth_ha_str *ha, u16 source,
                                       u16 idx, gdth_evt_data *evt)
 {
     gdth_evt_str *e;
-    struct timeval tv;
 
     /* no GDTH_LOCK_HA() ! */
     TRACE2(("gdth_store_event() source %d idx %d\n", source, idx));
@@ -2854,8 +2853,7 @@ static gdth_evt_str *gdth_store_event(gdth_ha_str *ha, u16 source,
             !strcmp((char *)&ebuffer[elastidx].event_data.event_string,
             (char *)&evt->event_string)))) { 
         e = &ebuffer[elastidx];
-        do_gettimeofday(&tv);
-        e->last_stamp = tv.tv_sec;
+	e->last_stamp = (u32)ktime_get_real_seconds();
         ++e->same_count;
     } else {
         if (ebuffer[elastidx].event_source != 0) {  /* entry not free ? */
@@ -2871,8 +2869,7 @@ static gdth_evt_str *gdth_store_event(gdth_ha_str *ha, u16 source,
         e = &ebuffer[elastidx];
         e->event_source = source;
         e->event_idx = idx;
-        do_gettimeofday(&tv);
-        e->first_stamp = e->last_stamp = tv.tv_sec;
+	e->first_stamp = e->last_stamp = (u32)ktime_get_real_seconds();
         e->same_count = 1;
         e->event_data = *evt;
         e->application = 0;
diff --git a/drivers/scsi/gdth_proc.c b/drivers/scsi/gdth_proc.c
index e66e997992e3..be609db66807 100644
--- a/drivers/scsi/gdth_proc.c
+++ b/drivers/scsi/gdth_proc.c
@@ -148,7 +148,6 @@ int gdth_show_info(struct seq_file *m, struct Scsi_Host *host)
     gdth_cmd_str *gdtcmd;
     gdth_evt_str *estr;
     char hrec[161];
-    struct timeval tv;
 
     char *buf;
     gdth_dskstat_str *pds;
@@ -540,8 +539,14 @@ int gdth_show_info(struct seq_file *m, struct Scsi_Host *host)
         if (estr->event_data.eu.driver.ionode == ha->hanum &&
             estr->event_source == ES_ASYNC) { 
             gdth_log_event(&estr->event_data, hrec);
-            do_gettimeofday(&tv);
-            sec = (int)(tv.tv_sec - estr->first_stamp);
+
+	    /*
+	     * Elapsed seconds subtraction with unsigned operands is
+	     * safe from wrap around in year 2106.  Executes as:
+	     * operand a + (2's complement operand b) + 1
+	     */
+
+	    sec = (int)((u32)ktime_get_real_seconds() - estr->first_stamp);
             if (sec < 0) sec = 0;
             seq_printf(m," date- %02d:%02d:%02d\t%s\n",
                            sec/3600, sec%3600/60, sec%60, hrec);
diff --git a/drivers/scsi/hisi_sas/Kconfig b/drivers/scsi/hisi_sas/Kconfig
index b67661836c9f..d1dd1616f983 100644
--- a/drivers/scsi/hisi_sas/Kconfig
+++ b/drivers/scsi/hisi_sas/Kconfig
@@ -1,6 +1,6 @@
 config SCSI_HISI_SAS
 	tristate "HiSilicon SAS"
-	depends on HAS_DMA
+	depends on HAS_DMA && HAS_IOMEM
 	depends on ARM64 || COMPILE_TEST
 	select SCSI_SAS_LIBSAS
 	select BLK_DEV_INTEGRITY
diff --git a/drivers/scsi/hisi_sas/Makefile b/drivers/scsi/hisi_sas/Makefile
index 3e70eae81343..c6d3a1b5fcb9 100644
--- a/drivers/scsi/hisi_sas/Makefile
+++ b/drivers/scsi/hisi_sas/Makefile
@@ -1,2 +1,2 @@
 obj-$(CONFIG_SCSI_HISI_SAS)		+= hisi_sas_main.o
-obj-$(CONFIG_SCSI_HISI_SAS)		+= hisi_sas_v1_hw.o
+obj-$(CONFIG_SCSI_HISI_SAS)		+= hisi_sas_v1_hw.o hisi_sas_v2_hw.o
diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index 5af2e4187f01..29e89f340b64 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -12,22 +12,24 @@
 #ifndef _HISI_SAS_H_
 #define _HISI_SAS_H_
 
+#include <linux/acpi.h>
 #include <linux/dmapool.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/regmap.h>
+#include <scsi/sas_ata.h>
 #include <scsi/libsas.h>
 
-#define DRV_VERSION "v1.0"
+#define DRV_VERSION "v1.3"
 
 #define HISI_SAS_MAX_PHYS	9
 #define HISI_SAS_MAX_QUEUES	32
 #define HISI_SAS_QUEUE_SLOTS 512
-#define HISI_SAS_MAX_ITCT_ENTRIES 4096
+#define HISI_SAS_MAX_ITCT_ENTRIES 2048
 #define HISI_SAS_MAX_DEVICES HISI_SAS_MAX_ITCT_ENTRIES
-#define HISI_SAS_COMMAND_ENTRIES 8192
 
 #define HISI_SAS_STATUS_BUF_SZ \
 		(sizeof(struct hisi_sas_err_record) + 1024)
@@ -36,6 +38,11 @@
 
 #define HISI_SAS_MAX_SSP_RESP_SZ (sizeof(struct ssp_frame_hdr) + 1024)
 #define HISI_SAS_MAX_SMP_RESP_SZ 1028
+#define HISI_SAS_MAX_STP_RESP_SZ 28
+
+#define DEV_IS_EXPANDER(type) \
+	((type == SAS_EDGE_EXPANDER_DEVICE) || \
+	(type == SAS_FANOUT_EXPANDER_DEVICE))
 
 struct hisi_hba;
 
@@ -105,6 +112,7 @@ struct hisi_sas_slot {
 	int	cmplt_queue;
 	int	cmplt_queue_slot;
 	int	idx;
+	int	abort;
 	void	*cmd_hdr;
 	dma_addr_t cmd_hdr_dma;
 	void	*status_buffer;
@@ -113,6 +121,7 @@ struct hisi_sas_slot {
 	dma_addr_t command_table_dma;
 	struct hisi_sas_sge_page *sge_page;
 	dma_addr_t sge_page_dma;
+	struct work_struct abort_slot;
 };
 
 struct hisi_sas_tmf_task {
@@ -132,6 +141,8 @@ struct hisi_sas_hw {
 			struct hisi_sas_tmf_task *tmf);
 	int (*prep_smp)(struct hisi_hba *hisi_hba,
 			struct hisi_sas_slot *slot);
+	int (*prep_stp)(struct hisi_hba *hisi_hba,
+			struct hisi_sas_slot *slot);
 	int (*slot_complete)(struct hisi_hba *hisi_hba,
 			     struct hisi_sas_slot *slot, int abort);
 	void (*phy_enable)(struct hisi_hba *hisi_hba, int phy_no);
@@ -140,6 +151,7 @@ struct hisi_sas_hw {
 	void (*free_device)(struct hisi_hba *hisi_hba,
 			    struct hisi_sas_device *dev);
 	int (*get_wideport_bitmap)(struct hisi_hba *hisi_hba, int port_id);
+	int max_command_entries;
 	int complete_hdr_size;
 };
 
@@ -244,18 +256,7 @@ struct hisi_sas_itct {
 	__le64 sas_addr;
 	__le64 qw2;
 	__le64 qw3;
-	__le64 qw4;
-	__le64 qw_sata_ncq0_3;
-	__le64 qw_sata_ncq7_4;
-	__le64 qw_sata_ncq11_8;
-	__le64 qw_sata_ncq15_12;
-	__le64 qw_sata_ncq19_16;
-	__le64 qw_sata_ncq23_20;
-	__le64 qw_sata_ncq27_24;
-	__le64 qw_sata_ncq31_28;
-	__le64 qw_non_ncq_iptt;
-	__le64 qw_rsvd0;
-	__le64 qw_rsvd1;
+	__le64 qw4_15[12];
 };
 
 struct hisi_sas_iost {
@@ -266,17 +267,7 @@ struct hisi_sas_iost {
 };
 
 struct hisi_sas_err_record {
-	/* dw0 */
-	__le32 dma_err_type;
-
-	/* dw1 */
-	__le32 trans_tx_fail_type;
-
-	/* dw2 */
-	__le32 trans_rx_fail_type;
-
-	/* dw3 */
-	u32 rsvd;
+	u32	data[4];
 };
 
 struct hisi_sas_initial_fis {
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 99b1950d751c..097ab4f27a6b 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -12,13 +12,12 @@
 #include "hisi_sas.h"
 #define DRV_NAME "hisi_sas"
 
-#define DEV_IS_EXPANDER(type) \
-	((type == SAS_EDGE_EXPANDER_DEVICE) || \
-	(type == SAS_FANOUT_EXPANDER_DEVICE))
-
 #define DEV_IS_GONE(dev) \
 	((!dev) || (dev->dev_type == SAS_PHY_UNUSED))
 
+static int hisi_sas_debug_issue_ssp_tmf(struct domain_device *device,
+				u8 *lun, struct hisi_sas_tmf_task *tmf);
+
 static struct hisi_hba *dev_to_hisi_hba(struct domain_device *device)
 {
 	return device->port->ha->lldd_ha;
@@ -111,6 +110,50 @@ static int hisi_sas_task_prep_ssp(struct hisi_hba *hisi_hba,
 	return hisi_hba->hw->prep_ssp(hisi_hba, slot, is_tmf, tmf);
 }
 
+static int hisi_sas_task_prep_ata(struct hisi_hba *hisi_hba,
+				  struct hisi_sas_slot *slot)
+{
+	return hisi_hba->hw->prep_stp(hisi_hba, slot);
+}
+
+/*
+ * This function will issue an abort TMF regardless of whether the
+ * task is in the sdev or not. Then it will do the task complete
+ * cleanup and callbacks.
+ */
+static void hisi_sas_slot_abort(struct work_struct *work)
+{
+	struct hisi_sas_slot *abort_slot =
+		container_of(work, struct hisi_sas_slot, abort_slot);
+	struct sas_task *task = abort_slot->task;
+	struct hisi_hba *hisi_hba = dev_to_hisi_hba(task->dev);
+	struct scsi_cmnd *cmnd = task->uldd_task;
+	struct hisi_sas_tmf_task tmf_task;
+	struct domain_device *device = task->dev;
+	struct hisi_sas_device *sas_dev = device->lldd_dev;
+	struct scsi_lun lun;
+	struct device *dev = &hisi_hba->pdev->dev;
+	int tag = abort_slot->idx;
+
+	if (!(task->task_proto & SAS_PROTOCOL_SSP)) {
+		dev_err(dev, "cannot abort slot for non-ssp task\n");
+		goto out;
+	}
+
+	int_to_scsilun(cmnd->device->lun, &lun);
+	tmf_task.tmf = TMF_ABORT_TASK;
+	tmf_task.tag_of_task_to_be_managed = cpu_to_le16(tag);
+
+	hisi_sas_debug_issue_ssp_tmf(task->dev, lun.scsi_lun, &tmf_task);
+out:
+	/* Do cleanup for this task */
+	hisi_sas_slot_task_free(hisi_hba, task, abort_slot);
+	if (task->task_done)
+		task->task_done(task);
+	if (sas_dev && sas_dev->running_req)
+		sas_dev->running_req--;
+}
+
 static int hisi_sas_task_prep(struct sas_task *task, struct hisi_hba *hisi_hba,
 			      int is_tmf, struct hisi_sas_tmf_task *tmf,
 			      int *pass)
@@ -204,6 +247,7 @@ static int hisi_sas_task_prep(struct sas_task *task, struct hisi_hba *hisi_hba,
 	slot->task = task;
 	slot->port = port;
 	task->lldd_task = slot;
+	INIT_WORK(&slot->abort_slot, hisi_sas_slot_abort);
 
 	slot->status_buffer = dma_pool_alloc(hisi_hba->status_buffer_pool,
 					     GFP_ATOMIC,
@@ -234,6 +278,8 @@ static int hisi_sas_task_prep(struct sas_task *task, struct hisi_hba *hisi_hba,
 	case SAS_PROTOCOL_SATA:
 	case SAS_PROTOCOL_STP:
 	case SAS_PROTOCOL_SATA | SAS_PROTOCOL_STP:
+		rc = hisi_sas_task_prep_ata(hisi_hba, slot);
+		break;
 	default:
 		dev_err(dev, "task prep: unknown/unsupported proto (0x%x)\n",
 			task->task_proto);
@@ -407,6 +453,19 @@ static int hisi_sas_dev_found(struct domain_device *device)
 	return 0;
 }
 
+static int hisi_sas_slave_configure(struct scsi_device *sdev)
+{
+	struct domain_device *dev = sdev_to_domain_dev(sdev);
+	int ret = sas_slave_configure(sdev);
+
+	if (ret)
+		return ret;
+	if (!dev_is_sata(dev))
+		sas_change_queue_depth(sdev, 64);
+
+	return 0;
+}
+
 static void hisi_sas_scan_start(struct Scsi_Host *shost)
 {
 	struct hisi_hba *hisi_hba = shost_priv(shost);
@@ -657,7 +716,7 @@ static int hisi_sas_exec_internal_tmf_task(struct domain_device *device,
 		}
 
 		if (task->task_status.resp == SAS_TASK_COMPLETE &&
-		    task->task_status.stat == SAM_STAT_GOOD) {
+		     task->task_status.stat == TMF_RESP_FUNC_COMPLETE) {
 			res = TMF_RESP_FUNC_COMPLETE;
 			break;
 		}
@@ -944,7 +1003,7 @@ static struct scsi_host_template hisi_sas_sht = {
 	.name			= DRV_NAME,
 	.queuecommand		= sas_queuecommand,
 	.target_alloc		= sas_target_alloc,
-	.slave_configure	= sas_slave_configure,
+	.slave_configure	= hisi_sas_slave_configure,
 	.scan_finished		= hisi_sas_scan_finished,
 	.scan_start		= hisi_sas_scan_start,
 	.change_queue_depth	= sas_change_queue_depth,
@@ -977,9 +1036,9 @@ static struct sas_domain_function_template hisi_sas_transport_ops = {
 
 static int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 {
-	int i, s;
 	struct platform_device *pdev = hisi_hba->pdev;
 	struct device *dev = &pdev->dev;
+	int i, s, max_command_entries = hisi_hba->hw->max_command_entries;
 
 	spin_lock_init(&hisi_hba->lock);
 	for (i = 0; i < hisi_hba->n_phy; i++) {
@@ -1039,13 +1098,13 @@ static int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 
 	memset(hisi_hba->itct, 0, s);
 
-	hisi_hba->slot_info = devm_kcalloc(dev, HISI_SAS_COMMAND_ENTRIES,
+	hisi_hba->slot_info = devm_kcalloc(dev, max_command_entries,
 					   sizeof(struct hisi_sas_slot),
 					   GFP_KERNEL);
 	if (!hisi_hba->slot_info)
 		goto err_out;
 
-	s = HISI_SAS_COMMAND_ENTRIES * sizeof(struct hisi_sas_iost);
+	s = max_command_entries * sizeof(struct hisi_sas_iost);
 	hisi_hba->iost = dma_alloc_coherent(dev, s, &hisi_hba->iost_dma,
 					    GFP_KERNEL);
 	if (!hisi_hba->iost)
@@ -1053,7 +1112,7 @@ static int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 
 	memset(hisi_hba->iost, 0, s);
 
-	s = HISI_SAS_COMMAND_ENTRIES * sizeof(struct hisi_sas_breakpoint);
+	s = max_command_entries * sizeof(struct hisi_sas_breakpoint);
 	hisi_hba->breakpoint = dma_alloc_coherent(dev, s,
 				&hisi_hba->breakpoint_dma, GFP_KERNEL);
 	if (!hisi_hba->breakpoint)
@@ -1061,7 +1120,7 @@ static int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 
 	memset(hisi_hba->breakpoint, 0, s);
 
-	hisi_hba->slot_index_count = HISI_SAS_COMMAND_ENTRIES;
+	hisi_hba->slot_index_count = max_command_entries;
 	s = hisi_hba->slot_index_count / sizeof(unsigned long);
 	hisi_hba->slot_index_tags = devm_kzalloc(dev, s, GFP_KERNEL);
 	if (!hisi_hba->slot_index_tags)
@@ -1079,7 +1138,7 @@ static int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 		goto err_out;
 	memset(hisi_hba->initial_fis, 0, s);
 
-	s = HISI_SAS_COMMAND_ENTRIES * sizeof(struct hisi_sas_breakpoint) * 2;
+	s = max_command_entries * sizeof(struct hisi_sas_breakpoint) * 2;
 	hisi_hba->sata_breakpoint = dma_alloc_coherent(dev, s,
 				&hisi_hba->sata_breakpoint_dma, GFP_KERNEL);
 	if (!hisi_hba->sata_breakpoint)
@@ -1102,7 +1161,7 @@ err_out:
 static void hisi_sas_free(struct hisi_hba *hisi_hba)
 {
 	struct device *dev = &hisi_hba->pdev->dev;
-	int i, s;
+	int i, s, max_command_entries = hisi_hba->hw->max_command_entries;
 
 	for (i = 0; i < hisi_hba->queue_count; i++) {
 		s = sizeof(struct hisi_sas_cmd_hdr) * HISI_SAS_QUEUE_SLOTS;
@@ -1127,12 +1186,12 @@ static void hisi_sas_free(struct hisi_hba *hisi_hba)
 		dma_free_coherent(dev, s,
 				  hisi_hba->itct, hisi_hba->itct_dma);
 
-	s = HISI_SAS_COMMAND_ENTRIES * sizeof(struct hisi_sas_iost);
+	s = max_command_entries * sizeof(struct hisi_sas_iost);
 	if (hisi_hba->iost)
 		dma_free_coherent(dev, s,
 				  hisi_hba->iost, hisi_hba->iost_dma);
 
-	s = HISI_SAS_COMMAND_ENTRIES * sizeof(struct hisi_sas_breakpoint);
+	s = max_command_entries * sizeof(struct hisi_sas_breakpoint);
 	if (hisi_hba->breakpoint)
 		dma_free_coherent(dev, s,
 				  hisi_hba->breakpoint,
@@ -1145,7 +1204,7 @@ static void hisi_sas_free(struct hisi_hba *hisi_hba)
 				  hisi_hba->initial_fis,
 				  hisi_hba->initial_fis_dma);
 
-	s = HISI_SAS_COMMAND_ENTRIES * sizeof(struct hisi_sas_breakpoint) * 2;
+	s = max_command_entries * sizeof(struct hisi_sas_breakpoint) * 2;
 	if (hisi_hba->sata_breakpoint)
 		dma_free_coherent(dev, s,
 				  hisi_hba->sata_breakpoint,
@@ -1163,7 +1222,6 @@ static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
 	struct hisi_hba *hisi_hba;
 	struct device *dev = &pdev->dev;
 	struct device_node *np = pdev->dev.of_node;
-	struct property *sas_addr_prop;
 
 	shost = scsi_host_alloc(&hisi_sas_sht, sizeof(*hisi_hba));
 	if (!shost)
@@ -1177,27 +1235,34 @@ static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
 
 	init_timer(&hisi_hba->timer);
 
-	sas_addr_prop = of_find_property(np, "sas-addr", NULL);
-	if (!sas_addr_prop || (sas_addr_prop->length != SAS_ADDR_SIZE))
+	if (device_property_read_u8_array(dev, "sas-addr", hisi_hba->sas_addr,
+					  SAS_ADDR_SIZE))
 		goto err_out;
-	memcpy(hisi_hba->sas_addr, sas_addr_prop->value, SAS_ADDR_SIZE);
 
-	if (of_property_read_u32(np, "ctrl-reset-reg",
-				 &hisi_hba->ctrl_reset_reg))
-		goto err_out;
+	if (np) {
+		hisi_hba->ctrl = syscon_regmap_lookup_by_phandle(np,
+					"hisilicon,sas-syscon");
+		if (IS_ERR(hisi_hba->ctrl))
+			goto err_out;
 
-	if (of_property_read_u32(np, "ctrl-reset-sts-reg",
-				 &hisi_hba->ctrl_reset_sts_reg))
-		goto err_out;
+		if (device_property_read_u32(dev, "ctrl-reset-reg",
+					     &hisi_hba->ctrl_reset_reg))
+			goto err_out;
 
-	if (of_property_read_u32(np, "ctrl-clock-ena-reg",
-				 &hisi_hba->ctrl_clock_ena_reg))
-		goto err_out;
+		if (device_property_read_u32(dev, "ctrl-reset-sts-reg",
+					     &hisi_hba->ctrl_reset_sts_reg))
+			goto err_out;
 
-	if (of_property_read_u32(np, "phy-count", &hisi_hba->n_phy))
+		if (device_property_read_u32(dev, "ctrl-clock-ena-reg",
+					     &hisi_hba->ctrl_clock_ena_reg))
+			goto err_out;
+	}
+
+	if (device_property_read_u32(dev, "phy-count", &hisi_hba->n_phy))
 		goto err_out;
 
-	if (of_property_read_u32(np, "queue-count", &hisi_hba->queue_count))
+	if (device_property_read_u32(dev, "queue-count",
+				     &hisi_hba->queue_count))
 		goto err_out;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -1205,11 +1270,6 @@ static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
 	if (IS_ERR(hisi_hba->regs))
 		goto err_out;
 
-	hisi_hba->ctrl = syscon_regmap_lookup_by_phandle(
-				np, "hisilicon,sas-syscon");
-	if (IS_ERR(hisi_hba->ctrl))
-		goto err_out;
-
 	if (hisi_sas_alloc(hisi_hba, shost)) {
 		hisi_sas_free(hisi_hba);
 		goto err_out;
@@ -1277,8 +1337,8 @@ int hisi_sas_probe(struct platform_device *pdev,
 	shost->max_channel = 1;
 	shost->max_cmd_len = 16;
 	shost->sg_tablesize = min_t(u16, SG_ALL, HISI_SAS_SGE_PAGE_CNT);
-	shost->can_queue = HISI_SAS_COMMAND_ENTRIES;
-	shost->cmd_per_lun = HISI_SAS_COMMAND_ENTRIES;
+	shost->can_queue = hisi_hba->hw->max_command_entries;
+	shost->cmd_per_lun = hisi_hba->hw->max_command_entries;
 
 	sha->sas_ha_name = DRV_NAME;
 	sha->dev = &hisi_hba->pdev->dev;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
index 057fdeb720ac..1abbc2e162df 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -288,6 +288,20 @@ struct hisi_sas_complete_v1_hdr {
 	__le32 data;
 };
 
+struct hisi_sas_err_record_v1 {
+	/* dw0 */
+	__le32 dma_err_type;
+
+	/* dw1 */
+	__le32 trans_tx_fail_type;
+
+	/* dw2 */
+	__le32 trans_rx_fail_type;
+
+	/* dw3 */
+	u32 rsvd;
+};
+
 enum {
 	HISI_SAS_PHY_BCAST_ACK = 0,
 	HISI_SAS_PHY_SL_PHY_ENABLED,
@@ -392,6 +406,8 @@ enum {
 	TRANS_RX_SMP_RESP_TIMEOUT_ERR, /* 0x31a */
 };
 
+#define HISI_SAS_COMMAND_ENTRIES_V1_HW 8192
+
 #define HISI_SAS_PHY_MAX_INT_NR (HISI_SAS_PHY_INT_NR * HISI_SAS_MAX_PHYS)
 #define HISI_SAS_CQ_MAX_INT_NR (HISI_SAS_MAX_QUEUES)
 #define HISI_SAS_FATAL_INT_NR (2)
@@ -607,31 +623,42 @@ static int reset_hw_v1_hw(struct hisi_hba *hisi_hba)
 			return -EIO;
 	}
 
-	/* Apply reset and disable clock */
-	/* clk disable reg is offset by +4 bytes from clk enable reg */
-	regmap_write(hisi_hba->ctrl, hisi_hba->ctrl_reset_reg,
-		     RESET_VALUE);
-	regmap_write(hisi_hba->ctrl, hisi_hba->ctrl_clock_ena_reg + 4,
-		     RESET_VALUE);
-	msleep(1);
-	regmap_read(hisi_hba->ctrl, hisi_hba->ctrl_reset_sts_reg, &val);
-	if (RESET_VALUE != (val & RESET_VALUE)) {
-		dev_err(dev, "Reset failed\n");
-		return -EIO;
-	}
+	if (ACPI_HANDLE(dev)) {
+		acpi_status s;
 
-	/* De-reset and enable clock */
-	/* deassert rst reg is offset by +4 bytes from assert reg */
-	regmap_write(hisi_hba->ctrl, hisi_hba->ctrl_reset_reg + 4,
-		     RESET_VALUE);
-	regmap_write(hisi_hba->ctrl, hisi_hba->ctrl_clock_ena_reg,
-		     RESET_VALUE);
-	msleep(1);
-	regmap_read(hisi_hba->ctrl, hisi_hba->ctrl_reset_sts_reg, &val);
-	if (val & RESET_VALUE) {
-		dev_err(dev, "De-reset failed\n");
-		return -EIO;
-	}
+		s = acpi_evaluate_object(ACPI_HANDLE(dev), "_RST", NULL, NULL);
+		if (ACPI_FAILURE(s)) {
+			dev_err(dev, "Reset failed\n");
+			return -EIO;
+		}
+	} else if (hisi_hba->ctrl) {
+		/* Apply reset and disable clock */
+		/* clk disable reg is offset by +4 bytes from clk enable reg */
+		regmap_write(hisi_hba->ctrl, hisi_hba->ctrl_reset_reg,
+			     RESET_VALUE);
+		regmap_write(hisi_hba->ctrl, hisi_hba->ctrl_clock_ena_reg + 4,
+			     RESET_VALUE);
+		msleep(1);
+		regmap_read(hisi_hba->ctrl, hisi_hba->ctrl_reset_sts_reg, &val);
+		if (RESET_VALUE != (val & RESET_VALUE)) {
+			dev_err(dev, "Reset failed\n");
+			return -EIO;
+		}
+
+		/* De-reset and enable clock */
+		/* deassert rst reg is offset by +4 bytes from assert reg */
+		regmap_write(hisi_hba->ctrl, hisi_hba->ctrl_reset_reg + 4,
+			     RESET_VALUE);
+		regmap_write(hisi_hba->ctrl, hisi_hba->ctrl_clock_ena_reg,
+			     RESET_VALUE);
+		msleep(1);
+		regmap_read(hisi_hba->ctrl, hisi_hba->ctrl_reset_sts_reg, &val);
+		if (val & RESET_VALUE) {
+			dev_err(dev, "De-reset failed\n");
+			return -EIO;
+		}
+	} else
+		dev_warn(dev, "no reset method\n");
 
 	return 0;
 }
@@ -1096,7 +1123,7 @@ static void slot_err_v1_hw(struct hisi_hba *hisi_hba,
 			   struct hisi_sas_slot *slot)
 {
 	struct task_status_struct *ts = &task->task_status;
-	struct hisi_sas_err_record *err_record = slot->status_buffer;
+	struct hisi_sas_err_record_v1 *err_record = slot->status_buffer;
 	struct device *dev = &hisi_hba->pdev->dev;
 
 	switch (task->task_proto) {
@@ -1185,6 +1212,14 @@ static void slot_err_v1_hw(struct hisi_hba *hisi_hba,
 			ts->stat = SAS_NAK_R_ERR;
 			break;
 		}
+		case TRANS_TX_CREDIT_TIMEOUT_ERR:
+		case TRANS_TX_CLOSE_NORMAL_ERR:
+		{
+			/* This will request a retry */
+			ts->stat = SAS_QUEUE_FULL;
+			slot->abort = 1;
+			break;
+		}
 		default:
 		{
 			ts->stat = SAM_STAT_CHECK_CONDITION;
@@ -1220,7 +1255,6 @@ static int slot_complete_v1_hw(struct hisi_hba *hisi_hba,
 	struct domain_device *device;
 	enum exec_status sts;
 	struct hisi_sas_complete_v1_hdr *complete_queue =
-			(struct hisi_sas_complete_v1_hdr *)
 			hisi_hba->complete_hdr[slot->cmplt_queue];
 	struct hisi_sas_complete_v1_hdr *complete_hdr;
 	u32 cmplt_hdr_data;
@@ -1289,13 +1323,15 @@ static int slot_complete_v1_hw(struct hisi_hba *hisi_hba,
 		goto out;
 	}
 
-	if (cmplt_hdr_data & CMPLT_HDR_ERR_RCRD_XFRD_MSK) {
-		if (!(cmplt_hdr_data & CMPLT_HDR_CMD_CMPLT_MSK) ||
-		    !(cmplt_hdr_data & CMPLT_HDR_RSPNS_XFRD_MSK))
-			ts->stat = SAS_DATA_OVERRUN;
-		else
-			slot_err_v1_hw(hisi_hba, task, slot);
+	if (cmplt_hdr_data & CMPLT_HDR_ERR_RCRD_XFRD_MSK &&
+		!(cmplt_hdr_data & CMPLT_HDR_RSPNS_XFRD_MSK)) {
 
+		slot_err_v1_hw(hisi_hba, task, slot);
+		if (unlikely(slot->abort)) {
+			queue_work(hisi_hba->wq, &slot->abort_slot);
+			/* immediately return and do not complete */
+			return ts->stat;
+		}
 		goto out;
 	}
 
@@ -1799,6 +1835,7 @@ static const struct hisi_sas_hw hisi_sas_v1_hw = {
 	.phy_disable = disable_phy_v1_hw,
 	.phy_hard_reset = phy_hard_reset_v1_hw,
 	.get_wideport_bitmap = get_wideport_bitmap_v1_hw,
+	.max_command_entries = HISI_SAS_COMMAND_ENTRIES_V1_HW,
 	.complete_hdr_size = sizeof(struct hisi_sas_complete_v1_hdr),
 };
 
@@ -1818,12 +1855,20 @@ static const struct of_device_id sas_v1_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, sas_v1_of_match);
 
+static const struct acpi_device_id sas_v1_acpi_match[] = {
+	{ "HISI0161", 0 },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(acpi, sas_v1_acpi_match);
+
 static struct platform_driver hisi_sas_v1_driver = {
 	.probe = hisi_sas_v1_probe,
 	.remove = hisi_sas_v1_remove,
 	.driver = {
 		.name = DRV_NAME,
 		.of_match_table = sas_v1_of_match,
+		.acpi_match_table = ACPI_PTR(sas_v1_acpi_match),
 	},
 };
 
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
new file mode 100644
index 000000000000..b7337476454b
--- /dev/null
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -0,0 +1,2214 @@
+/*
+ * Copyright (c) 2016 Linaro Ltd.
+ * Copyright (c) 2016 Hisilicon Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#include "hisi_sas.h"
+#define DRV_NAME "hisi_sas_v2_hw"
+
+/* global registers need init*/
+#define DLVRY_QUEUE_ENABLE		0x0
+#define IOST_BASE_ADDR_LO		0x8
+#define IOST_BASE_ADDR_HI		0xc
+#define ITCT_BASE_ADDR_LO		0x10
+#define ITCT_BASE_ADDR_HI		0x14
+#define IO_BROKEN_MSG_ADDR_LO		0x18
+#define IO_BROKEN_MSG_ADDR_HI		0x1c
+#define PHY_CONTEXT			0x20
+#define PHY_STATE			0x24
+#define PHY_PORT_NUM_MA			0x28
+#define PORT_STATE			0x2c
+#define PORT_STATE_PHY8_PORT_NUM_OFF	16
+#define PORT_STATE_PHY8_PORT_NUM_MSK	(0xf << PORT_STATE_PHY8_PORT_NUM_OFF)
+#define PORT_STATE_PHY8_CONN_RATE_OFF	20
+#define PORT_STATE_PHY8_CONN_RATE_MSK	(0xf << PORT_STATE_PHY8_CONN_RATE_OFF)
+#define PHY_CONN_RATE			0x30
+#define HGC_TRANS_TASK_CNT_LIMIT	0x38
+#define AXI_AHB_CLK_CFG			0x3c
+#define ITCT_CLR			0x44
+#define ITCT_CLR_EN_OFF			16
+#define ITCT_CLR_EN_MSK			(0x1 << ITCT_CLR_EN_OFF)
+#define ITCT_DEV_OFF			0
+#define ITCT_DEV_MSK			(0x7ff << ITCT_DEV_OFF)
+#define AXI_USER1			0x48
+#define AXI_USER2			0x4c
+#define IO_SATA_BROKEN_MSG_ADDR_LO	0x58
+#define IO_SATA_BROKEN_MSG_ADDR_HI	0x5c
+#define SATA_INITI_D2H_STORE_ADDR_LO	0x60
+#define SATA_INITI_D2H_STORE_ADDR_HI	0x64
+#define HGC_SAS_TX_OPEN_FAIL_RETRY_CTRL	0x84
+#define HGC_SAS_TXFAIL_RETRY_CTRL	0x88
+#define HGC_GET_ITV_TIME		0x90
+#define DEVICE_MSG_WORK_MODE		0x94
+#define OPENA_WT_CONTI_TIME		0x9c
+#define I_T_NEXUS_LOSS_TIME		0xa0
+#define MAX_CON_TIME_LIMIT_TIME		0xa4
+#define BUS_INACTIVE_LIMIT_TIME		0xa8
+#define REJECT_TO_OPEN_LIMIT_TIME	0xac
+#define CFG_AGING_TIME			0xbc
+#define HGC_DFX_CFG2			0xc0
+#define HGC_IOMB_PROC1_STATUS	0x104
+#define CFG_1US_TIMER_TRSH		0xcc
+#define HGC_INVLD_DQE_INFO		0x148
+#define HGC_INVLD_DQE_INFO_FB_CH0_OFF	9
+#define HGC_INVLD_DQE_INFO_FB_CH0_MSK	(0x1 << HGC_INVLD_DQE_INFO_FB_CH0_OFF)
+#define HGC_INVLD_DQE_INFO_FB_CH3_OFF	18
+#define INT_COAL_EN			0x19c
+#define OQ_INT_COAL_TIME		0x1a0
+#define OQ_INT_COAL_CNT			0x1a4
+#define ENT_INT_COAL_TIME		0x1a8
+#define ENT_INT_COAL_CNT		0x1ac
+#define OQ_INT_SRC			0x1b0
+#define OQ_INT_SRC_MSK			0x1b4
+#define ENT_INT_SRC1			0x1b8
+#define ENT_INT_SRC1_D2H_FIS_CH0_OFF	0
+#define ENT_INT_SRC1_D2H_FIS_CH0_MSK	(0x1 << ENT_INT_SRC1_D2H_FIS_CH0_OFF)
+#define ENT_INT_SRC1_D2H_FIS_CH1_OFF	8
+#define ENT_INT_SRC1_D2H_FIS_CH1_MSK	(0x1 << ENT_INT_SRC1_D2H_FIS_CH1_OFF)
+#define ENT_INT_SRC2			0x1bc
+#define ENT_INT_SRC3			0x1c0
+#define ENT_INT_SRC3_ITC_INT_OFF	15
+#define ENT_INT_SRC3_ITC_INT_MSK	(0x1 << ENT_INT_SRC3_ITC_INT_OFF)
+#define ENT_INT_SRC_MSK1		0x1c4
+#define ENT_INT_SRC_MSK2		0x1c8
+#define ENT_INT_SRC_MSK3		0x1cc
+#define ENT_INT_SRC_MSK3_ENT95_MSK_OFF	31
+#define ENT_INT_SRC_MSK3_ENT95_MSK_MSK	(0x1 << ENT_INT_SRC_MSK3_ENT95_MSK_OFF)
+#define SAS_ECC_INTR_MSK		0x1ec
+#define HGC_ERR_STAT_EN			0x238
+#define DLVRY_Q_0_BASE_ADDR_LO		0x260
+#define DLVRY_Q_0_BASE_ADDR_HI		0x264
+#define DLVRY_Q_0_DEPTH			0x268
+#define DLVRY_Q_0_WR_PTR		0x26c
+#define DLVRY_Q_0_RD_PTR		0x270
+#define HYPER_STREAM_ID_EN_CFG		0xc80
+#define OQ0_INT_SRC_MSK			0xc90
+#define COMPL_Q_0_BASE_ADDR_LO		0x4e0
+#define COMPL_Q_0_BASE_ADDR_HI		0x4e4
+#define COMPL_Q_0_DEPTH			0x4e8
+#define COMPL_Q_0_WR_PTR		0x4ec
+#define COMPL_Q_0_RD_PTR		0x4f0
+
+/* phy registers need init */
+#define PORT_BASE			(0x2000)
+
+#define PHY_CFG				(PORT_BASE + 0x0)
+#define HARD_PHY_LINKRATE		(PORT_BASE + 0x4)
+#define PHY_CFG_ENA_OFF			0
+#define PHY_CFG_ENA_MSK			(0x1 << PHY_CFG_ENA_OFF)
+#define PHY_CFG_DC_OPT_OFF		2
+#define PHY_CFG_DC_OPT_MSK		(0x1 << PHY_CFG_DC_OPT_OFF)
+#define PROG_PHY_LINK_RATE		(PORT_BASE + 0x8)
+#define PROG_PHY_LINK_RATE_MAX_OFF	0
+#define PROG_PHY_LINK_RATE_MAX_MSK	(0xff << PROG_PHY_LINK_RATE_MAX_OFF)
+#define PHY_CTRL			(PORT_BASE + 0x14)
+#define PHY_CTRL_RESET_OFF		0
+#define PHY_CTRL_RESET_MSK		(0x1 << PHY_CTRL_RESET_OFF)
+#define SAS_PHY_CTRL			(PORT_BASE + 0x20)
+#define SL_CFG				(PORT_BASE + 0x84)
+#define PHY_PCN				(PORT_BASE + 0x44)
+#define SL_TOUT_CFG			(PORT_BASE + 0x8c)
+#define SL_CONTROL			(PORT_BASE + 0x94)
+#define SL_CONTROL_NOTIFY_EN_OFF	0
+#define SL_CONTROL_NOTIFY_EN_MSK	(0x1 << SL_CONTROL_NOTIFY_EN_OFF)
+#define TX_ID_DWORD0			(PORT_BASE + 0x9c)
+#define TX_ID_DWORD1			(PORT_BASE + 0xa0)
+#define TX_ID_DWORD2			(PORT_BASE + 0xa4)
+#define TX_ID_DWORD3			(PORT_BASE + 0xa8)
+#define TX_ID_DWORD4			(PORT_BASE + 0xaC)
+#define TX_ID_DWORD5			(PORT_BASE + 0xb0)
+#define TX_ID_DWORD6			(PORT_BASE + 0xb4)
+#define RX_IDAF_DWORD0			(PORT_BASE + 0xc4)
+#define RX_IDAF_DWORD1			(PORT_BASE + 0xc8)
+#define RX_IDAF_DWORD2			(PORT_BASE + 0xcc)
+#define RX_IDAF_DWORD3			(PORT_BASE + 0xd0)
+#define RX_IDAF_DWORD4			(PORT_BASE + 0xd4)
+#define RX_IDAF_DWORD5			(PORT_BASE + 0xd8)
+#define RX_IDAF_DWORD6			(PORT_BASE + 0xdc)
+#define RXOP_CHECK_CFG_H		(PORT_BASE + 0xfc)
+#define DONE_RECEIVED_TIME		(PORT_BASE + 0x11c)
+#define CHL_INT0			(PORT_BASE + 0x1b4)
+#define CHL_INT0_HOTPLUG_TOUT_OFF	0
+#define CHL_INT0_HOTPLUG_TOUT_MSK	(0x1 << CHL_INT0_HOTPLUG_TOUT_OFF)
+#define CHL_INT0_SL_RX_BCST_ACK_OFF	1
+#define CHL_INT0_SL_RX_BCST_ACK_MSK	(0x1 << CHL_INT0_SL_RX_BCST_ACK_OFF)
+#define CHL_INT0_SL_PHY_ENABLE_OFF	2
+#define CHL_INT0_SL_PHY_ENABLE_MSK	(0x1 << CHL_INT0_SL_PHY_ENABLE_OFF)
+#define CHL_INT0_NOT_RDY_OFF		4
+#define CHL_INT0_NOT_RDY_MSK		(0x1 << CHL_INT0_NOT_RDY_OFF)
+#define CHL_INT0_PHY_RDY_OFF		5
+#define CHL_INT0_PHY_RDY_MSK		(0x1 << CHL_INT0_PHY_RDY_OFF)
+#define CHL_INT1			(PORT_BASE + 0x1b8)
+#define CHL_INT1_DMAC_TX_ECC_ERR_OFF	15
+#define CHL_INT1_DMAC_TX_ECC_ERR_MSK	(0x1 << CHL_INT1_DMAC_TX_ECC_ERR_OFF)
+#define CHL_INT1_DMAC_RX_ECC_ERR_OFF	17
+#define CHL_INT1_DMAC_RX_ECC_ERR_MSK	(0x1 << CHL_INT1_DMAC_RX_ECC_ERR_OFF)
+#define CHL_INT2			(PORT_BASE + 0x1bc)
+#define CHL_INT0_MSK			(PORT_BASE + 0x1c0)
+#define CHL_INT1_MSK			(PORT_BASE + 0x1c4)
+#define CHL_INT2_MSK			(PORT_BASE + 0x1c8)
+#define CHL_INT_COAL_EN			(PORT_BASE + 0x1d0)
+#define PHY_CTRL_RDY_MSK		(PORT_BASE + 0x2b0)
+#define PHYCTRL_NOT_RDY_MSK		(PORT_BASE + 0x2b4)
+#define PHYCTRL_DWS_RESET_MSK		(PORT_BASE + 0x2b8)
+#define PHYCTRL_PHY_ENA_MSK		(PORT_BASE + 0x2bc)
+#define SL_RX_BCAST_CHK_MSK		(PORT_BASE + 0x2c0)
+#define PHYCTRL_OOB_RESTART_MSK		(PORT_BASE + 0x2c4)
+#define DMA_TX_STATUS			(PORT_BASE + 0x2d0)
+#define DMA_TX_STATUS_BUSY_OFF		0
+#define DMA_TX_STATUS_BUSY_MSK		(0x1 << DMA_TX_STATUS_BUSY_OFF)
+#define DMA_RX_STATUS			(PORT_BASE + 0x2e8)
+#define DMA_RX_STATUS_BUSY_OFF		0
+#define DMA_RX_STATUS_BUSY_MSK		(0x1 << DMA_RX_STATUS_BUSY_OFF)
+
+#define AXI_CFG				(0x5100)
+#define AM_CFG_MAX_TRANS		(0x5010)
+#define AM_CFG_SINGLE_PORT_MAX_TRANS	(0x5014)
+
+/* HW dma structures */
+/* Delivery queue header */
+/* dw0 */
+#define CMD_HDR_RESP_REPORT_OFF		5
+#define CMD_HDR_RESP_REPORT_MSK		(0x1 << CMD_HDR_RESP_REPORT_OFF)
+#define CMD_HDR_TLR_CTRL_OFF		6
+#define CMD_HDR_TLR_CTRL_MSK		(0x3 << CMD_HDR_TLR_CTRL_OFF)
+#define CMD_HDR_PORT_OFF		18
+#define CMD_HDR_PORT_MSK		(0xf << CMD_HDR_PORT_OFF)
+#define CMD_HDR_PRIORITY_OFF		27
+#define CMD_HDR_PRIORITY_MSK		(0x1 << CMD_HDR_PRIORITY_OFF)
+#define CMD_HDR_CMD_OFF			29
+#define CMD_HDR_CMD_MSK			(0x7 << CMD_HDR_CMD_OFF)
+/* dw1 */
+#define CMD_HDR_DIR_OFF			5
+#define CMD_HDR_DIR_MSK			(0x3 << CMD_HDR_DIR_OFF)
+#define CMD_HDR_RESET_OFF		7
+#define CMD_HDR_RESET_MSK		(0x1 << CMD_HDR_RESET_OFF)
+#define CMD_HDR_VDTL_OFF		10
+#define CMD_HDR_VDTL_MSK		(0x1 << CMD_HDR_VDTL_OFF)
+#define CMD_HDR_FRAME_TYPE_OFF		11
+#define CMD_HDR_FRAME_TYPE_MSK		(0x1f << CMD_HDR_FRAME_TYPE_OFF)
+#define CMD_HDR_DEV_ID_OFF		16
+#define CMD_HDR_DEV_ID_MSK		(0xffff << CMD_HDR_DEV_ID_OFF)
+/* dw2 */
+#define CMD_HDR_CFL_OFF			0
+#define CMD_HDR_CFL_MSK			(0x1ff << CMD_HDR_CFL_OFF)
+#define CMD_HDR_NCQ_TAG_OFF		10
+#define CMD_HDR_NCQ_TAG_MSK		(0x1f << CMD_HDR_NCQ_TAG_OFF)
+#define CMD_HDR_MRFL_OFF		15
+#define CMD_HDR_MRFL_MSK		(0x1ff << CMD_HDR_MRFL_OFF)
+#define CMD_HDR_SG_MOD_OFF		24
+#define CMD_HDR_SG_MOD_MSK		(0x3 << CMD_HDR_SG_MOD_OFF)
+#define CMD_HDR_FIRST_BURST_OFF		26
+#define CMD_HDR_FIRST_BURST_MSK		(0x1 << CMD_HDR_SG_MOD_OFF)
+/* dw3 */
+#define CMD_HDR_IPTT_OFF		0
+#define CMD_HDR_IPTT_MSK		(0xffff << CMD_HDR_IPTT_OFF)
+/* dw6 */
+#define CMD_HDR_DIF_SGL_LEN_OFF		0
+#define CMD_HDR_DIF_SGL_LEN_MSK		(0xffff << CMD_HDR_DIF_SGL_LEN_OFF)
+#define CMD_HDR_DATA_SGL_LEN_OFF	16
+#define CMD_HDR_DATA_SGL_LEN_MSK	(0xffff << CMD_HDR_DATA_SGL_LEN_OFF)
+
+/* Completion header */
+/* dw0 */
+#define CMPLT_HDR_RSPNS_XFRD_OFF	10
+#define CMPLT_HDR_RSPNS_XFRD_MSK	(0x1 << CMPLT_HDR_RSPNS_XFRD_OFF)
+#define CMPLT_HDR_ERX_OFF		12
+#define CMPLT_HDR_ERX_MSK		(0x1 << CMPLT_HDR_ERX_OFF)
+/* dw1 */
+#define CMPLT_HDR_IPTT_OFF		0
+#define CMPLT_HDR_IPTT_MSK		(0xffff << CMPLT_HDR_IPTT_OFF)
+#define CMPLT_HDR_DEV_ID_OFF		16
+#define CMPLT_HDR_DEV_ID_MSK		(0xffff << CMPLT_HDR_DEV_ID_OFF)
+
+/* ITCT header */
+/* qw0 */
+#define ITCT_HDR_DEV_TYPE_OFF		0
+#define ITCT_HDR_DEV_TYPE_MSK		(0x3 << ITCT_HDR_DEV_TYPE_OFF)
+#define ITCT_HDR_VALID_OFF		2
+#define ITCT_HDR_VALID_MSK		(0x1 << ITCT_HDR_VALID_OFF)
+#define ITCT_HDR_MCR_OFF		5
+#define ITCT_HDR_MCR_MSK		(0xf << ITCT_HDR_MCR_OFF)
+#define ITCT_HDR_VLN_OFF		9
+#define ITCT_HDR_VLN_MSK		(0xf << ITCT_HDR_VLN_OFF)
+#define ITCT_HDR_PORT_ID_OFF		28
+#define ITCT_HDR_PORT_ID_MSK		(0xf << ITCT_HDR_PORT_ID_OFF)
+/* qw2 */
+#define ITCT_HDR_INLT_OFF		0
+#define ITCT_HDR_INLT_MSK		(0xffffULL << ITCT_HDR_INLT_OFF)
+#define ITCT_HDR_BITLT_OFF		16
+#define ITCT_HDR_BITLT_MSK		(0xffffULL << ITCT_HDR_BITLT_OFF)
+#define ITCT_HDR_MCTLT_OFF		32
+#define ITCT_HDR_MCTLT_MSK		(0xffffULL << ITCT_HDR_MCTLT_OFF)
+#define ITCT_HDR_RTOLT_OFF		48
+#define ITCT_HDR_RTOLT_MSK		(0xffffULL << ITCT_HDR_RTOLT_OFF)
+
+struct hisi_sas_complete_v2_hdr {
+	__le32 dw0;
+	__le32 dw1;
+	__le32 act;
+	__le32 dw3;
+};
+
+struct hisi_sas_err_record_v2 {
+	/* dw0 */
+	__le32 trans_tx_fail_type;
+
+	/* dw1 */
+	__le32 trans_rx_fail_type;
+
+	/* dw2 */
+	__le16 dma_tx_err_type;
+	__le16 sipc_rx_err_type;
+
+	/* dw3 */
+	__le32 dma_rx_err_type;
+};
+
+enum {
+	HISI_SAS_PHY_PHY_UPDOWN,
+	HISI_SAS_PHY_CHNL_INT,
+	HISI_SAS_PHY_INT_NR
+};
+
+enum {
+	TRANS_TX_FAIL_BASE = 0x0, /* dw0 */
+	TRANS_RX_FAIL_BASE = 0x100, /* dw1 */
+	DMA_TX_ERR_BASE = 0x200, /* dw2 bit 15-0 */
+	SIPC_RX_ERR_BASE = 0x300, /* dw2 bit 31-16*/
+	DMA_RX_ERR_BASE = 0x400, /* dw3 */
+
+	/* trans tx*/
+	TRANS_TX_OPEN_FAIL_WITH_IT_NEXUS_LOSS = TRANS_TX_FAIL_BASE, /* 0x0 */
+	TRANS_TX_ERR_PHY_NOT_ENABLE, /* 0x1 */
+	TRANS_TX_OPEN_CNX_ERR_WRONG_DESTINATION, /* 0x2 */
+	TRANS_TX_OPEN_CNX_ERR_ZONE_VIOLATION, /* 0x3 */
+	TRANS_TX_OPEN_CNX_ERR_BY_OTHER, /* 0x4 */
+	RESERVED0, /* 0x5 */
+	TRANS_TX_OPEN_CNX_ERR_AIP_TIMEOUT, /* 0x6 */
+	TRANS_TX_OPEN_CNX_ERR_STP_RESOURCES_BUSY, /* 0x7 */
+	TRANS_TX_OPEN_CNX_ERR_PROTOCOL_NOT_SUPPORTED, /* 0x8 */
+	TRANS_TX_OPEN_CNX_ERR_CONNECTION_RATE_NOT_SUPPORTED, /* 0x9 */
+	TRANS_TX_OPEN_CNX_ERR_BAD_DESTINATION, /* 0xa */
+	TRANS_TX_OPEN_CNX_ERR_BREAK_RCVD, /* 0xb */
+	TRANS_TX_OPEN_CNX_ERR_LOW_PHY_POWER, /* 0xc */
+	TRANS_TX_OPEN_CNX_ERR_PATHWAY_BLOCKED, /* 0xd */
+	TRANS_TX_OPEN_CNX_ERR_OPEN_TIMEOUT, /* 0xe */
+	TRANS_TX_OPEN_CNX_ERR_NO_DESTINATION, /* 0xf */
+	TRANS_TX_OPEN_RETRY_ERR_THRESHOLD_REACHED, /* 0x10 */
+	TRANS_TX_ERR_FRAME_TXED, /* 0x11 */
+	TRANS_TX_ERR_WITH_BREAK_TIMEOUT, /* 0x12 */
+	TRANS_TX_ERR_WITH_BREAK_REQUEST, /* 0x13 */
+	TRANS_TX_ERR_WITH_BREAK_RECEVIED, /* 0x14 */
+	TRANS_TX_ERR_WITH_CLOSE_TIMEOUT, /* 0x15 */
+	TRANS_TX_ERR_WITH_CLOSE_NORMAL, /* 0x16 for ssp*/
+	TRANS_TX_ERR_WITH_CLOSE_PHYDISALE, /* 0x17 */
+	TRANS_TX_ERR_WITH_CLOSE_DWS_TIMEOUT, /* 0x18 */
+	TRANS_TX_ERR_WITH_CLOSE_COMINIT, /* 0x19 */
+	TRANS_TX_ERR_WITH_NAK_RECEVIED, /* 0x1a for ssp*/
+	TRANS_TX_ERR_WITH_ACK_NAK_TIMEOUT, /* 0x1b for ssp*/
+	/*IO_TX_ERR_WITH_R_ERR_RECEVIED, [> 0x1b for sata/stp<] */
+	TRANS_TX_ERR_WITH_CREDIT_TIMEOUT, /* 0x1c for ssp */
+	/*IO_RX_ERR_WITH_SATA_DEVICE_LOST 0x1c for sata/stp */
+	TRANS_TX_ERR_WITH_IPTT_CONFLICT, /* 0x1d for ssp/smp */
+	TRANS_TX_ERR_WITH_OPEN_BY_DES_OR_OTHERS, /* 0x1e */
+	/*IO_TX_ERR_WITH_SYNC_RXD, [> 0x1e <] for sata/stp */
+	TRANS_TX_ERR_WITH_WAIT_RECV_TIMEOUT, /* 0x1f for sata/stp */
+
+	/* trans rx */
+	TRANS_RX_ERR_WITH_RXFRAME_CRC_ERR = TRANS_RX_FAIL_BASE, /* 0x100 */
+	TRANS_RX_ERR_WITH_RXFIS_8B10B_DISP_ERR, /* 0x101 for sata/stp */
+	TRANS_RX_ERR_WITH_RXFRAME_HAVE_ERRPRM, /* 0x102 for ssp/smp */
+	/*IO_ERR_WITH_RXFIS_8B10B_CODE_ERR, [> 0x102 <] for sata/stp */
+	TRANS_RX_ERR_WITH_RXFIS_DECODE_ERROR, /* 0x103 for sata/stp */
+	TRANS_RX_ERR_WITH_RXFIS_CRC_ERR, /* 0x104 for sata/stp */
+	TRANS_RX_ERR_WITH_RXFRAME_LENGTH_OVERRUN, /* 0x105 for smp */
+	/*IO_ERR_WITH_RXFIS_TX SYNCP, [> 0x105 <] for sata/stp */
+	TRANS_RX_ERR_WITH_RXFIS_RX_SYNCP, /* 0x106 for sata/stp*/
+	TRANS_RX_ERR_WITH_LINK_BUF_OVERRUN, /* 0x107 */
+	TRANS_RX_ERR_WITH_BREAK_TIMEOUT, /* 0x108 */
+	TRANS_RX_ERR_WITH_BREAK_REQUEST, /* 0x109 */
+	TRANS_RX_ERR_WITH_BREAK_RECEVIED, /* 0x10a */
+	RESERVED1, /* 0x10b */
+	TRANS_RX_ERR_WITH_CLOSE_NORMAL, /* 0x10c */
+	TRANS_RX_ERR_WITH_CLOSE_PHY_DISABLE, /* 0x10d */
+	TRANS_RX_ERR_WITH_CLOSE_DWS_TIMEOUT, /* 0x10e */
+	TRANS_RX_ERR_WITH_CLOSE_COMINIT, /* 0x10f */
+	TRANS_RX_ERR_WITH_DATA_LEN0, /* 0x110 for ssp/smp */
+	TRANS_RX_ERR_WITH_BAD_HASH, /* 0x111 for ssp */
+	/*IO_RX_ERR_WITH_FIS_TOO_SHORT, [> 0x111 <] for sata/stp */
+	TRANS_RX_XRDY_WLEN_ZERO_ERR, /* 0x112 for ssp*/
+	/*IO_RX_ERR_WITH_FIS_TOO_LONG, [> 0x112 <] for sata/stp */
+	TRANS_RX_SSP_FRM_LEN_ERR, /* 0x113 for ssp */
+	/*IO_RX_ERR_WITH_SATA_DEVICE_LOST, [> 0x113 <] for sata */
+	RESERVED2, /* 0x114 */
+	RESERVED3, /* 0x115 */
+	RESERVED4, /* 0x116 */
+	RESERVED5, /* 0x117 */
+	TRANS_RX_ERR_WITH_BAD_FRM_TYPE, /* 0x118 */
+	TRANS_RX_SMP_FRM_LEN_ERR, /* 0x119 */
+	TRANS_RX_SMP_RESP_TIMEOUT_ERR, /* 0x11a */
+	RESERVED6, /* 0x11b */
+	RESERVED7, /* 0x11c */
+	RESERVED8, /* 0x11d */
+	RESERVED9, /* 0x11e */
+	TRANS_RX_R_ERR, /* 0x11f */
+
+	/* dma tx */
+	DMA_TX_DIF_CRC_ERR = DMA_TX_ERR_BASE, /* 0x200 */
+	DMA_TX_DIF_APP_ERR, /* 0x201 */
+	DMA_TX_DIF_RPP_ERR, /* 0x202 */
+	DMA_TX_DATA_SGL_OVERFLOW, /* 0x203 */
+	DMA_TX_DIF_SGL_OVERFLOW, /* 0x204 */
+	DMA_TX_UNEXP_XFER_ERR, /* 0x205 */
+	DMA_TX_UNEXP_RETRANS_ERR, /* 0x206 */
+	DMA_TX_XFER_LEN_OVERFLOW, /* 0x207 */
+	DMA_TX_XFER_OFFSET_ERR, /* 0x208 */
+	DMA_TX_RAM_ECC_ERR, /* 0x209 */
+	DMA_TX_DIF_LEN_ALIGN_ERR, /* 0x20a */
+
+	/* sipc rx */
+	SIPC_RX_FIS_STATUS_ERR_BIT_VLD = SIPC_RX_ERR_BASE, /* 0x300 */
+	SIPC_RX_PIO_WRSETUP_STATUS_DRQ_ERR, /* 0x301 */
+	SIPC_RX_FIS_STATUS_BSY_BIT_ERR, /* 0x302 */
+	SIPC_RX_WRSETUP_LEN_ODD_ERR, /* 0x303 */
+	SIPC_RX_WRSETUP_LEN_ZERO_ERR, /* 0x304 */
+	SIPC_RX_WRDATA_LEN_NOT_MATCH_ERR, /* 0x305 */
+	SIPC_RX_NCQ_WRSETUP_OFFSET_ERR, /* 0x306 */
+	SIPC_RX_NCQ_WRSETUP_AUTO_ACTIVE_ERR, /* 0x307 */
+	SIPC_RX_SATA_UNEXP_FIS_ERR, /* 0x308 */
+	SIPC_RX_WRSETUP_ESTATUS_ERR, /* 0x309 */
+	SIPC_RX_DATA_UNDERFLOW_ERR, /* 0x30a */
+
+	/* dma rx */
+	DMA_RX_DIF_CRC_ERR = DMA_RX_ERR_BASE, /* 0x400 */
+	DMA_RX_DIF_APP_ERR, /* 0x401 */
+	DMA_RX_DIF_RPP_ERR, /* 0x402 */
+	DMA_RX_DATA_SGL_OVERFLOW, /* 0x403 */
+	DMA_RX_DIF_SGL_OVERFLOW, /* 0x404 */
+	DMA_RX_DATA_LEN_OVERFLOW, /* 0x405 */
+	DMA_RX_DATA_LEN_UNDERFLOW, /* 0x406 */
+	DMA_RX_DATA_OFFSET_ERR, /* 0x407 */
+	RESERVED10, /* 0x408 */
+	DMA_RX_SATA_FRAME_TYPE_ERR, /* 0x409 */
+	DMA_RX_RESP_BUF_OVERFLOW, /* 0x40a */
+	DMA_RX_UNEXP_RETRANS_RESP_ERR, /* 0x40b */
+	DMA_RX_UNEXP_NORM_RESP_ERR, /* 0x40c */
+	DMA_RX_UNEXP_RDFRAME_ERR, /* 0x40d */
+	DMA_RX_PIO_DATA_LEN_ERR, /* 0x40e */
+	DMA_RX_RDSETUP_STATUS_ERR, /* 0x40f */
+	DMA_RX_RDSETUP_STATUS_DRQ_ERR, /* 0x410 */
+	DMA_RX_RDSETUP_STATUS_BSY_ERR, /* 0x411 */
+	DMA_RX_RDSETUP_LEN_ODD_ERR, /* 0x412 */
+	DMA_RX_RDSETUP_LEN_ZERO_ERR, /* 0x413 */
+	DMA_RX_RDSETUP_LEN_OVER_ERR, /* 0x414 */
+	DMA_RX_RDSETUP_OFFSET_ERR, /* 0x415 */
+	DMA_RX_RDSETUP_ACTIVE_ERR, /* 0x416 */
+	DMA_RX_RDSETUP_ESTATUS_ERR, /* 0x417 */
+	DMA_RX_RAM_ECC_ERR, /* 0x418 */
+	DMA_RX_UNKNOWN_FRM_ERR, /* 0x419 */
+};
+
+#define HISI_SAS_COMMAND_ENTRIES_V2_HW 4096
+
+#define DIR_NO_DATA 0
+#define DIR_TO_INI 1
+#define DIR_TO_DEVICE 2
+#define DIR_RESERVED 3
+
+#define SATA_PROTOCOL_NONDATA		0x1
+#define SATA_PROTOCOL_PIO		0x2
+#define SATA_PROTOCOL_DMA		0x4
+#define SATA_PROTOCOL_FPDMA		0x8
+#define SATA_PROTOCOL_ATAPI		0x10
+
+static u32 hisi_sas_read32(struct hisi_hba *hisi_hba, u32 off)
+{
+	void __iomem *regs = hisi_hba->regs + off;
+
+	return readl(regs);
+}
+
+static u32 hisi_sas_read32_relaxed(struct hisi_hba *hisi_hba, u32 off)
+{
+	void __iomem *regs = hisi_hba->regs + off;
+
+	return readl_relaxed(regs);
+}
+
+static void hisi_sas_write32(struct hisi_hba *hisi_hba, u32 off, u32 val)
+{
+	void __iomem *regs = hisi_hba->regs + off;
+
+	writel(val, regs);
+}
+
+static void hisi_sas_phy_write32(struct hisi_hba *hisi_hba, int phy_no,
+				 u32 off, u32 val)
+{
+	void __iomem *regs = hisi_hba->regs + (0x400 * phy_no) + off;
+
+	writel(val, regs);
+}
+
+static u32 hisi_sas_phy_read32(struct hisi_hba *hisi_hba,
+				      int phy_no, u32 off)
+{
+	void __iomem *regs = hisi_hba->regs + (0x400 * phy_no) + off;
+
+	return readl(regs);
+}
+
+static void config_phy_opt_mode_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	u32 cfg = hisi_sas_phy_read32(hisi_hba, phy_no, PHY_CFG);
+
+	cfg &= ~PHY_CFG_DC_OPT_MSK;
+	cfg |= 1 << PHY_CFG_DC_OPT_OFF;
+	hisi_sas_phy_write32(hisi_hba, phy_no, PHY_CFG, cfg);
+}
+
+static void config_id_frame_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	struct sas_identify_frame identify_frame;
+	u32 *identify_buffer;
+
+	memset(&identify_frame, 0, sizeof(identify_frame));
+	identify_frame.dev_type = SAS_END_DEVICE;
+	identify_frame.frame_type = 0;
+	identify_frame._un1 = 1;
+	identify_frame.initiator_bits = SAS_PROTOCOL_ALL;
+	identify_frame.target_bits = SAS_PROTOCOL_NONE;
+	memcpy(&identify_frame._un4_11[0], hisi_hba->sas_addr, SAS_ADDR_SIZE);
+	memcpy(&identify_frame.sas_addr[0], hisi_hba->sas_addr,	SAS_ADDR_SIZE);
+	identify_frame.phy_id = phy_no;
+	identify_buffer = (u32 *)(&identify_frame);
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, TX_ID_DWORD0,
+			__swab32(identify_buffer[0]));
+	hisi_sas_phy_write32(hisi_hba, phy_no, TX_ID_DWORD1,
+			identify_buffer[2]);
+	hisi_sas_phy_write32(hisi_hba, phy_no, TX_ID_DWORD2,
+			identify_buffer[1]);
+	hisi_sas_phy_write32(hisi_hba, phy_no, TX_ID_DWORD3,
+			identify_buffer[4]);
+	hisi_sas_phy_write32(hisi_hba, phy_no, TX_ID_DWORD4,
+			identify_buffer[3]);
+	hisi_sas_phy_write32(hisi_hba, phy_no, TX_ID_DWORD5,
+			__swab32(identify_buffer[5]));
+}
+
+static void init_id_frame_v2_hw(struct hisi_hba *hisi_hba)
+{
+	int i;
+
+	for (i = 0; i < hisi_hba->n_phy; i++)
+		config_id_frame_v2_hw(hisi_hba, i);
+}
+
+static void setup_itct_v2_hw(struct hisi_hba *hisi_hba,
+			     struct hisi_sas_device *sas_dev)
+{
+	struct domain_device *device = sas_dev->sas_device;
+	struct device *dev = &hisi_hba->pdev->dev;
+	u64 qw0, device_id = sas_dev->device_id;
+	struct hisi_sas_itct *itct = &hisi_hba->itct[device_id];
+	struct domain_device *parent_dev = device->parent;
+	struct hisi_sas_port *port = device->port->lldd_port;
+
+	memset(itct, 0, sizeof(*itct));
+
+	/* qw0 */
+	qw0 = 0;
+	switch (sas_dev->dev_type) {
+	case SAS_END_DEVICE:
+	case SAS_EDGE_EXPANDER_DEVICE:
+	case SAS_FANOUT_EXPANDER_DEVICE:
+		qw0 = HISI_SAS_DEV_TYPE_SSP << ITCT_HDR_DEV_TYPE_OFF;
+		break;
+	case SAS_SATA_DEV:
+		if (parent_dev && DEV_IS_EXPANDER(parent_dev->dev_type))
+			qw0 = HISI_SAS_DEV_TYPE_STP << ITCT_HDR_DEV_TYPE_OFF;
+		else
+			qw0 = HISI_SAS_DEV_TYPE_SATA << ITCT_HDR_DEV_TYPE_OFF;
+		break;
+	default:
+		dev_warn(dev, "setup itct: unsupported dev type (%d)\n",
+			 sas_dev->dev_type);
+	}
+
+	qw0 |= ((1 << ITCT_HDR_VALID_OFF) |
+		(device->max_linkrate << ITCT_HDR_MCR_OFF) |
+		(1 << ITCT_HDR_VLN_OFF) |
+		(port->id << ITCT_HDR_PORT_ID_OFF));
+	itct->qw0 = cpu_to_le64(qw0);
+
+	/* qw1 */
+	memcpy(&itct->sas_addr, device->sas_addr, SAS_ADDR_SIZE);
+	itct->sas_addr = __swab64(itct->sas_addr);
+
+	/* qw2 */
+	itct->qw2 = cpu_to_le64((500ULL << ITCT_HDR_INLT_OFF) |
+				(0xff00ULL << ITCT_HDR_BITLT_OFF) |
+				(0xff00ULL << ITCT_HDR_MCTLT_OFF) |
+				(0xff00ULL << ITCT_HDR_RTOLT_OFF));
+}
+
+static void free_device_v2_hw(struct hisi_hba *hisi_hba,
+			      struct hisi_sas_device *sas_dev)
+{
+	u64 qw0, dev_id = sas_dev->device_id;
+	struct device *dev = &hisi_hba->pdev->dev;
+	struct hisi_sas_itct *itct = &hisi_hba->itct[dev_id];
+	u32 reg_val = hisi_sas_read32(hisi_hba, ENT_INT_SRC3);
+	int i;
+
+	/* clear the itct interrupt state */
+	if (ENT_INT_SRC3_ITC_INT_MSK & reg_val)
+		hisi_sas_write32(hisi_hba, ENT_INT_SRC3,
+				 ENT_INT_SRC3_ITC_INT_MSK);
+
+	/* clear the itct int*/
+	for (i = 0; i < 2; i++) {
+		/* clear the itct table*/
+		reg_val = hisi_sas_read32(hisi_hba, ITCT_CLR);
+		reg_val |= ITCT_CLR_EN_MSK | (dev_id & ITCT_DEV_MSK);
+		hisi_sas_write32(hisi_hba, ITCT_CLR, reg_val);
+
+		udelay(10);
+		reg_val = hisi_sas_read32(hisi_hba, ENT_INT_SRC3);
+		if (ENT_INT_SRC3_ITC_INT_MSK & reg_val) {
+			dev_dbg(dev, "got clear ITCT done interrupt\n");
+
+			/* invalid the itct state*/
+			qw0 = cpu_to_le64(itct->qw0);
+			qw0 &= ~(1 << ITCT_HDR_VALID_OFF);
+			hisi_sas_write32(hisi_hba, ENT_INT_SRC3,
+					 ENT_INT_SRC3_ITC_INT_MSK);
+			hisi_hba->devices[dev_id].dev_type = SAS_PHY_UNUSED;
+			hisi_hba->devices[dev_id].dev_status = HISI_SAS_DEV_NORMAL;
+
+			/* clear the itct */
+			hisi_sas_write32(hisi_hba, ITCT_CLR, 0);
+			dev_dbg(dev, "clear ITCT ok\n");
+			break;
+		}
+	}
+}
+
+static int reset_hw_v2_hw(struct hisi_hba *hisi_hba)
+{
+	int i, reset_val;
+	u32 val;
+	unsigned long end_time;
+	struct device *dev = &hisi_hba->pdev->dev;
+
+	/* The mask needs to be set depending on the number of phys */
+	if (hisi_hba->n_phy == 9)
+		reset_val = 0x1fffff;
+	else
+		reset_val = 0x7ffff;
+
+	/* Disable all of the DQ */
+	for (i = 0; i < HISI_SAS_MAX_QUEUES; i++)
+		hisi_sas_write32(hisi_hba, DLVRY_QUEUE_ENABLE, 0);
+
+	/* Disable all of the PHYs */
+	for (i = 0; i < hisi_hba->n_phy; i++) {
+		u32 phy_cfg = hisi_sas_phy_read32(hisi_hba, i, PHY_CFG);
+
+		phy_cfg &= ~PHY_CTRL_RESET_MSK;
+		hisi_sas_phy_write32(hisi_hba, i, PHY_CFG, phy_cfg);
+	}
+	udelay(50);
+
+	/* Ensure DMA tx & rx idle */
+	for (i = 0; i < hisi_hba->n_phy; i++) {
+		u32 dma_tx_status, dma_rx_status;
+
+		end_time = jiffies + msecs_to_jiffies(1000);
+
+		while (1) {
+			dma_tx_status = hisi_sas_phy_read32(hisi_hba, i,
+							    DMA_TX_STATUS);
+			dma_rx_status = hisi_sas_phy_read32(hisi_hba, i,
+							    DMA_RX_STATUS);
+
+			if (!(dma_tx_status & DMA_TX_STATUS_BUSY_MSK) &&
+				!(dma_rx_status & DMA_RX_STATUS_BUSY_MSK))
+				break;
+
+			msleep(20);
+			if (time_after(jiffies, end_time))
+				return -EIO;
+		}
+	}
+
+	/* Ensure axi bus idle */
+	end_time = jiffies + msecs_to_jiffies(1000);
+	while (1) {
+		u32 axi_status =
+			hisi_sas_read32(hisi_hba, AXI_CFG);
+
+		if (axi_status == 0)
+			break;
+
+		msleep(20);
+		if (time_after(jiffies, end_time))
+			return -EIO;
+	}
+
+	/* reset and disable clock*/
+	regmap_write(hisi_hba->ctrl, hisi_hba->ctrl_reset_reg,
+			reset_val);
+	regmap_write(hisi_hba->ctrl, hisi_hba->ctrl_clock_ena_reg + 4,
+			reset_val);
+	msleep(1);
+	regmap_read(hisi_hba->ctrl, hisi_hba->ctrl_reset_sts_reg, &val);
+	if (reset_val != (val & reset_val)) {
+		dev_err(dev, "SAS reset fail.\n");
+		return -EIO;
+	}
+
+	/* De-reset and enable clock*/
+	regmap_write(hisi_hba->ctrl, hisi_hba->ctrl_reset_reg + 4,
+			reset_val);
+	regmap_write(hisi_hba->ctrl, hisi_hba->ctrl_clock_ena_reg,
+			reset_val);
+	msleep(1);
+	regmap_read(hisi_hba->ctrl, hisi_hba->ctrl_reset_sts_reg,
+			&val);
+	if (val & reset_val) {
+		dev_err(dev, "SAS de-reset fail.\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static void init_reg_v2_hw(struct hisi_hba *hisi_hba)
+{
+	struct device *dev = &hisi_hba->pdev->dev;
+	struct device_node *np = dev->of_node;
+	int i;
+
+	/* Global registers init */
+
+	/* Deal with am-max-transmissions quirk */
+	if (of_get_property(np, "hip06-sas-v2-quirk-amt", NULL)) {
+		hisi_sas_write32(hisi_hba, AM_CFG_MAX_TRANS, 0x2020);
+		hisi_sas_write32(hisi_hba, AM_CFG_SINGLE_PORT_MAX_TRANS,
+				 0x2020);
+	} /* Else, use defaults -> do nothing */
+
+	hisi_sas_write32(hisi_hba, DLVRY_QUEUE_ENABLE,
+			 (u32)((1ULL << hisi_hba->queue_count) - 1));
+	hisi_sas_write32(hisi_hba, AXI_USER1, 0xc0000000);
+	hisi_sas_write32(hisi_hba, AXI_USER2, 0x10000);
+	hisi_sas_write32(hisi_hba, HGC_SAS_TXFAIL_RETRY_CTRL, 0x108);
+	hisi_sas_write32(hisi_hba, HGC_SAS_TX_OPEN_FAIL_RETRY_CTRL, 0x7FF);
+	hisi_sas_write32(hisi_hba, OPENA_WT_CONTI_TIME, 0x1);
+	hisi_sas_write32(hisi_hba, I_T_NEXUS_LOSS_TIME, 0x1F4);
+	hisi_sas_write32(hisi_hba, MAX_CON_TIME_LIMIT_TIME, 0x4E20);
+	hisi_sas_write32(hisi_hba, BUS_INACTIVE_LIMIT_TIME, 0x1);
+	hisi_sas_write32(hisi_hba, CFG_AGING_TIME, 0x1);
+	hisi_sas_write32(hisi_hba, HGC_ERR_STAT_EN, 0x1);
+	hisi_sas_write32(hisi_hba, HGC_GET_ITV_TIME, 0x1);
+	hisi_sas_write32(hisi_hba, INT_COAL_EN, 0x1);
+	hisi_sas_write32(hisi_hba, OQ_INT_COAL_TIME, 0x1);
+	hisi_sas_write32(hisi_hba, OQ_INT_COAL_CNT, 0x1);
+	hisi_sas_write32(hisi_hba, ENT_INT_COAL_TIME, 0x1);
+	hisi_sas_write32(hisi_hba, ENT_INT_COAL_CNT, 0x1);
+	hisi_sas_write32(hisi_hba, OQ_INT_SRC, 0x0);
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC1, 0xffffffff);
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC2, 0xffffffff);
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC3, 0xffffffff);
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK1, 0x7efefefe);
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK2, 0x7efefefe);
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK3, 0x7ffffffe);
+	hisi_sas_write32(hisi_hba, SAS_ECC_INTR_MSK, 0xfffff3c0);
+	for (i = 0; i < hisi_hba->queue_count; i++)
+		hisi_sas_write32(hisi_hba, OQ0_INT_SRC_MSK+0x4*i, 0);
+
+	hisi_sas_write32(hisi_hba, AXI_AHB_CLK_CFG, 1);
+	hisi_sas_write32(hisi_hba, HYPER_STREAM_ID_EN_CFG, 1);
+
+	for (i = 0; i < hisi_hba->n_phy; i++) {
+		hisi_sas_phy_write32(hisi_hba, i, PROG_PHY_LINK_RATE, 0x855);
+		hisi_sas_phy_write32(hisi_hba, i, SAS_PHY_CTRL, 0x30b9908);
+		hisi_sas_phy_write32(hisi_hba, i, SL_TOUT_CFG, 0x7d7d7d7d);
+		hisi_sas_phy_write32(hisi_hba, i, DONE_RECEIVED_TIME, 0x10);
+		hisi_sas_phy_write32(hisi_hba, i, CHL_INT0, 0xffffffff);
+		hisi_sas_phy_write32(hisi_hba, i, CHL_INT1, 0xffffffff);
+		hisi_sas_phy_write32(hisi_hba, i, CHL_INT2, 0xffffffff);
+		hisi_sas_phy_write32(hisi_hba, i, RXOP_CHECK_CFG_H, 0x1000);
+		hisi_sas_phy_write32(hisi_hba, i, CHL_INT1_MSK, 0xffffffff);
+		hisi_sas_phy_write32(hisi_hba, i, CHL_INT2_MSK, 0x8ffffbff);
+		hisi_sas_phy_write32(hisi_hba, i, SL_CFG, 0x23f801fc);
+		hisi_sas_phy_write32(hisi_hba, i, PHY_CTRL_RDY_MSK, 0x0);
+		hisi_sas_phy_write32(hisi_hba, i, PHYCTRL_NOT_RDY_MSK, 0x0);
+		hisi_sas_phy_write32(hisi_hba, i, PHYCTRL_DWS_RESET_MSK, 0x0);
+		hisi_sas_phy_write32(hisi_hba, i, PHYCTRL_PHY_ENA_MSK, 0x0);
+		hisi_sas_phy_write32(hisi_hba, i, SL_RX_BCAST_CHK_MSK, 0x0);
+		hisi_sas_phy_write32(hisi_hba, i, CHL_INT_COAL_EN, 0x0);
+		hisi_sas_phy_write32(hisi_hba, i, PHYCTRL_OOB_RESTART_MSK, 0x0);
+		hisi_sas_phy_write32(hisi_hba, i, PHY_CTRL, 0x199B694);
+	}
+
+	for (i = 0; i < hisi_hba->queue_count; i++) {
+		/* Delivery queue */
+		hisi_sas_write32(hisi_hba,
+				 DLVRY_Q_0_BASE_ADDR_HI + (i * 0x14),
+				 upper_32_bits(hisi_hba->cmd_hdr_dma[i]));
+
+		hisi_sas_write32(hisi_hba, DLVRY_Q_0_BASE_ADDR_LO + (i * 0x14),
+				 lower_32_bits(hisi_hba->cmd_hdr_dma[i]));
+
+		hisi_sas_write32(hisi_hba, DLVRY_Q_0_DEPTH + (i * 0x14),
+				 HISI_SAS_QUEUE_SLOTS);
+
+		/* Completion queue */
+		hisi_sas_write32(hisi_hba, COMPL_Q_0_BASE_ADDR_HI + (i * 0x14),
+				 upper_32_bits(hisi_hba->complete_hdr_dma[i]));
+
+		hisi_sas_write32(hisi_hba, COMPL_Q_0_BASE_ADDR_LO + (i * 0x14),
+				 lower_32_bits(hisi_hba->complete_hdr_dma[i]));
+
+		hisi_sas_write32(hisi_hba, COMPL_Q_0_DEPTH + (i * 0x14),
+				 HISI_SAS_QUEUE_SLOTS);
+	}
+
+	/* itct */
+	hisi_sas_write32(hisi_hba, ITCT_BASE_ADDR_LO,
+			 lower_32_bits(hisi_hba->itct_dma));
+
+	hisi_sas_write32(hisi_hba, ITCT_BASE_ADDR_HI,
+			 upper_32_bits(hisi_hba->itct_dma));
+
+	/* iost */
+	hisi_sas_write32(hisi_hba, IOST_BASE_ADDR_LO,
+			 lower_32_bits(hisi_hba->iost_dma));
+
+	hisi_sas_write32(hisi_hba, IOST_BASE_ADDR_HI,
+			 upper_32_bits(hisi_hba->iost_dma));
+
+	/* breakpoint */
+	hisi_sas_write32(hisi_hba, IO_BROKEN_MSG_ADDR_LO,
+			 lower_32_bits(hisi_hba->breakpoint_dma));
+
+	hisi_sas_write32(hisi_hba, IO_BROKEN_MSG_ADDR_HI,
+			 upper_32_bits(hisi_hba->breakpoint_dma));
+
+	/* SATA broken msg */
+	hisi_sas_write32(hisi_hba, IO_SATA_BROKEN_MSG_ADDR_LO,
+			 lower_32_bits(hisi_hba->sata_breakpoint_dma));
+
+	hisi_sas_write32(hisi_hba, IO_SATA_BROKEN_MSG_ADDR_HI,
+			 upper_32_bits(hisi_hba->sata_breakpoint_dma));
+
+	/* SATA initial fis */
+	hisi_sas_write32(hisi_hba, SATA_INITI_D2H_STORE_ADDR_LO,
+			 lower_32_bits(hisi_hba->initial_fis_dma));
+
+	hisi_sas_write32(hisi_hba, SATA_INITI_D2H_STORE_ADDR_HI,
+			 upper_32_bits(hisi_hba->initial_fis_dma));
+}
+
+static int hw_init_v2_hw(struct hisi_hba *hisi_hba)
+{
+	struct device *dev = &hisi_hba->pdev->dev;
+	int rc;
+
+	rc = reset_hw_v2_hw(hisi_hba);
+	if (rc) {
+		dev_err(dev, "hisi_sas_reset_hw failed, rc=%d", rc);
+		return rc;
+	}
+
+	msleep(100);
+	init_reg_v2_hw(hisi_hba);
+
+	init_id_frame_v2_hw(hisi_hba);
+
+	return 0;
+}
+
+static void enable_phy_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	u32 cfg = hisi_sas_phy_read32(hisi_hba, phy_no, PHY_CFG);
+
+	cfg |= PHY_CFG_ENA_MSK;
+	hisi_sas_phy_write32(hisi_hba, phy_no, PHY_CFG, cfg);
+}
+
+static void disable_phy_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	u32 cfg = hisi_sas_phy_read32(hisi_hba, phy_no, PHY_CFG);
+
+	cfg &= ~PHY_CFG_ENA_MSK;
+	hisi_sas_phy_write32(hisi_hba, phy_no, PHY_CFG, cfg);
+}
+
+static void start_phy_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	config_id_frame_v2_hw(hisi_hba, phy_no);
+	config_phy_opt_mode_v2_hw(hisi_hba, phy_no);
+	enable_phy_v2_hw(hisi_hba, phy_no);
+}
+
+static void stop_phy_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	disable_phy_v2_hw(hisi_hba, phy_no);
+}
+
+static void phy_hard_reset_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	stop_phy_v2_hw(hisi_hba, phy_no);
+	msleep(100);
+	start_phy_v2_hw(hisi_hba, phy_no);
+}
+
+static void start_phys_v2_hw(unsigned long data)
+{
+	struct hisi_hba *hisi_hba = (struct hisi_hba *)data;
+	int i;
+
+	for (i = 0; i < hisi_hba->n_phy; i++)
+		start_phy_v2_hw(hisi_hba, i);
+}
+
+static void phys_init_v2_hw(struct hisi_hba *hisi_hba)
+{
+	int i;
+	struct timer_list *timer = &hisi_hba->timer;
+
+	for (i = 0; i < hisi_hba->n_phy; i++) {
+		hisi_sas_phy_write32(hisi_hba, i, CHL_INT2_MSK, 0x6a);
+		hisi_sas_phy_read32(hisi_hba, i, CHL_INT2_MSK);
+	}
+
+	setup_timer(timer, start_phys_v2_hw, (unsigned long)hisi_hba);
+	mod_timer(timer, jiffies + HZ);
+}
+
+static void sl_notify_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	u32 sl_control;
+
+	sl_control = hisi_sas_phy_read32(hisi_hba, phy_no, SL_CONTROL);
+	sl_control |= SL_CONTROL_NOTIFY_EN_MSK;
+	hisi_sas_phy_write32(hisi_hba, phy_no, SL_CONTROL, sl_control);
+	msleep(1);
+	sl_control = hisi_sas_phy_read32(hisi_hba, phy_no, SL_CONTROL);
+	sl_control &= ~SL_CONTROL_NOTIFY_EN_MSK;
+	hisi_sas_phy_write32(hisi_hba, phy_no, SL_CONTROL, sl_control);
+}
+
+static int get_wideport_bitmap_v2_hw(struct hisi_hba *hisi_hba, int port_id)
+{
+	int i, bitmap = 0;
+	u32 phy_port_num_ma = hisi_sas_read32(hisi_hba, PHY_PORT_NUM_MA);
+	u32 phy_state = hisi_sas_read32(hisi_hba, PHY_STATE);
+
+	for (i = 0; i < (hisi_hba->n_phy < 9 ? hisi_hba->n_phy : 8); i++)
+		if (phy_state & 1 << i)
+			if (((phy_port_num_ma >> (i * 4)) & 0xf) == port_id)
+				bitmap |= 1 << i;
+
+	if (hisi_hba->n_phy == 9) {
+		u32 port_state = hisi_sas_read32(hisi_hba, PORT_STATE);
+
+		if (phy_state & 1 << 8)
+			if (((port_state & PORT_STATE_PHY8_PORT_NUM_MSK) >>
+			     PORT_STATE_PHY8_PORT_NUM_OFF) == port_id)
+				bitmap |= 1 << 9;
+	}
+
+	return bitmap;
+}
+
+/**
+ * This function allocates across all queues to load balance.
+ * Slots are allocated from queues in a round-robin fashion.
+ *
+ * The callpath to this function and upto writing the write
+ * queue pointer should be safe from interruption.
+ */
+static int get_free_slot_v2_hw(struct hisi_hba *hisi_hba, int *q, int *s)
+{
+	struct device *dev = &hisi_hba->pdev->dev;
+	u32 r, w;
+	int queue = hisi_hba->queue;
+
+	while (1) {
+		w = hisi_sas_read32_relaxed(hisi_hba,
+					    DLVRY_Q_0_WR_PTR + (queue * 0x14));
+		r = hisi_sas_read32_relaxed(hisi_hba,
+					    DLVRY_Q_0_RD_PTR + (queue * 0x14));
+		if (r == (w+1) % HISI_SAS_QUEUE_SLOTS) {
+			queue = (queue + 1) % hisi_hba->queue_count;
+			if (queue == hisi_hba->queue) {
+				dev_warn(dev, "could not find free slot\n");
+				return -EAGAIN;
+			}
+			continue;
+		}
+		break;
+	}
+	hisi_hba->queue = (queue + 1) % hisi_hba->queue_count;
+	*q = queue;
+	*s = w;
+	return 0;
+}
+
+static void start_delivery_v2_hw(struct hisi_hba *hisi_hba)
+{
+	int dlvry_queue = hisi_hba->slot_prep->dlvry_queue;
+	int dlvry_queue_slot = hisi_hba->slot_prep->dlvry_queue_slot;
+
+	hisi_sas_write32(hisi_hba, DLVRY_Q_0_WR_PTR + (dlvry_queue * 0x14),
+			 ++dlvry_queue_slot % HISI_SAS_QUEUE_SLOTS);
+}
+
+static int prep_prd_sge_v2_hw(struct hisi_hba *hisi_hba,
+			      struct hisi_sas_slot *slot,
+			      struct hisi_sas_cmd_hdr *hdr,
+			      struct scatterlist *scatter,
+			      int n_elem)
+{
+	struct device *dev = &hisi_hba->pdev->dev;
+	struct scatterlist *sg;
+	int i;
+
+	if (n_elem > HISI_SAS_SGE_PAGE_CNT) {
+		dev_err(dev, "prd err: n_elem(%d) > HISI_SAS_SGE_PAGE_CNT",
+			n_elem);
+		return -EINVAL;
+	}
+
+	slot->sge_page = dma_pool_alloc(hisi_hba->sge_page_pool, GFP_ATOMIC,
+					&slot->sge_page_dma);
+	if (!slot->sge_page)
+		return -ENOMEM;
+
+	for_each_sg(scatter, sg, n_elem, i) {
+		struct hisi_sas_sge *entry = &slot->sge_page->sge[i];
+
+		entry->addr = cpu_to_le64(sg_dma_address(sg));
+		entry->page_ctrl_0 = entry->page_ctrl_1 = 0;
+		entry->data_len = cpu_to_le32(sg_dma_len(sg));
+		entry->data_off = 0;
+	}
+
+	hdr->prd_table_addr = cpu_to_le64(slot->sge_page_dma);
+
+	hdr->sg_len = cpu_to_le32(n_elem << CMD_HDR_DATA_SGL_LEN_OFF);
+
+	return 0;
+}
+
+static int prep_smp_v2_hw(struct hisi_hba *hisi_hba,
+			  struct hisi_sas_slot *slot)
+{
+	struct sas_task *task = slot->task;
+	struct hisi_sas_cmd_hdr *hdr = slot->cmd_hdr;
+	struct domain_device *device = task->dev;
+	struct device *dev = &hisi_hba->pdev->dev;
+	struct hisi_sas_port *port = slot->port;
+	struct scatterlist *sg_req, *sg_resp;
+	struct hisi_sas_device *sas_dev = device->lldd_dev;
+	dma_addr_t req_dma_addr;
+	unsigned int req_len, resp_len;
+	int elem, rc;
+
+	/*
+	* DMA-map SMP request, response buffers
+	*/
+	/* req */
+	sg_req = &task->smp_task.smp_req;
+	elem = dma_map_sg(dev, sg_req, 1, DMA_TO_DEVICE);
+	if (!elem)
+		return -ENOMEM;
+	req_len = sg_dma_len(sg_req);
+	req_dma_addr = sg_dma_address(sg_req);
+
+	/* resp */
+	sg_resp = &task->smp_task.smp_resp;
+	elem = dma_map_sg(dev, sg_resp, 1, DMA_FROM_DEVICE);
+	if (!elem) {
+		rc = -ENOMEM;
+		goto err_out_req;
+	}
+	resp_len = sg_dma_len(sg_resp);
+	if ((req_len & 0x3) || (resp_len & 0x3)) {
+		rc = -EINVAL;
+		goto err_out_resp;
+	}
+
+	/* create header */
+	/* dw0 */
+	hdr->dw0 = cpu_to_le32((port->id << CMD_HDR_PORT_OFF) |
+			       (1 << CMD_HDR_PRIORITY_OFF) | /* high pri */
+			       (2 << CMD_HDR_CMD_OFF)); /* smp */
+
+	/* map itct entry */
+	hdr->dw1 = cpu_to_le32((sas_dev->device_id << CMD_HDR_DEV_ID_OFF) |
+			       (1 << CMD_HDR_FRAME_TYPE_OFF) |
+			       (DIR_NO_DATA << CMD_HDR_DIR_OFF));
+
+	/* dw2 */
+	hdr->dw2 = cpu_to_le32((((req_len - 4) / 4) << CMD_HDR_CFL_OFF) |
+			       (HISI_SAS_MAX_SMP_RESP_SZ / 4 <<
+			       CMD_HDR_MRFL_OFF));
+
+	hdr->transfer_tags = cpu_to_le32(slot->idx << CMD_HDR_IPTT_OFF);
+
+	hdr->cmd_table_addr = cpu_to_le64(req_dma_addr);
+	hdr->sts_buffer_addr = cpu_to_le64(slot->status_buffer_dma);
+
+	return 0;
+
+err_out_resp:
+	dma_unmap_sg(dev, &slot->task->smp_task.smp_resp, 1,
+		     DMA_FROM_DEVICE);
+err_out_req:
+	dma_unmap_sg(dev, &slot->task->smp_task.smp_req, 1,
+		     DMA_TO_DEVICE);
+	return rc;
+}
+
+static int prep_ssp_v2_hw(struct hisi_hba *hisi_hba,
+			  struct hisi_sas_slot *slot, int is_tmf,
+			  struct hisi_sas_tmf_task *tmf)
+{
+	struct sas_task *task = slot->task;
+	struct hisi_sas_cmd_hdr *hdr = slot->cmd_hdr;
+	struct domain_device *device = task->dev;
+	struct hisi_sas_device *sas_dev = device->lldd_dev;
+	struct hisi_sas_port *port = slot->port;
+	struct sas_ssp_task *ssp_task = &task->ssp_task;
+	struct scsi_cmnd *scsi_cmnd = ssp_task->cmd;
+	int has_data = 0, rc, priority = is_tmf;
+	u8 *buf_cmd;
+	u32 dw1 = 0, dw2 = 0;
+
+	hdr->dw0 = cpu_to_le32((1 << CMD_HDR_RESP_REPORT_OFF) |
+			       (2 << CMD_HDR_TLR_CTRL_OFF) |
+			       (port->id << CMD_HDR_PORT_OFF) |
+			       (priority << CMD_HDR_PRIORITY_OFF) |
+			       (1 << CMD_HDR_CMD_OFF)); /* ssp */
+
+	dw1 = 1 << CMD_HDR_VDTL_OFF;
+	if (is_tmf) {
+		dw1 |= 2 << CMD_HDR_FRAME_TYPE_OFF;
+		dw1 |= DIR_NO_DATA << CMD_HDR_DIR_OFF;
+	} else {
+		dw1 |= 1 << CMD_HDR_FRAME_TYPE_OFF;
+		switch (scsi_cmnd->sc_data_direction) {
+		case DMA_TO_DEVICE:
+			has_data = 1;
+			dw1 |= DIR_TO_DEVICE << CMD_HDR_DIR_OFF;
+			break;
+		case DMA_FROM_DEVICE:
+			has_data = 1;
+			dw1 |= DIR_TO_INI << CMD_HDR_DIR_OFF;
+			break;
+		default:
+			dw1 &= ~CMD_HDR_DIR_MSK;
+		}
+	}
+
+	/* map itct entry */
+	dw1 |= sas_dev->device_id << CMD_HDR_DEV_ID_OFF;
+	hdr->dw1 = cpu_to_le32(dw1);
+
+	dw2 = (((sizeof(struct ssp_command_iu) + sizeof(struct ssp_frame_hdr)
+	      + 3) / 4) << CMD_HDR_CFL_OFF) |
+	      ((HISI_SAS_MAX_SSP_RESP_SZ / 4) << CMD_HDR_MRFL_OFF) |
+	      (2 << CMD_HDR_SG_MOD_OFF);
+	hdr->dw2 = cpu_to_le32(dw2);
+
+	hdr->transfer_tags = cpu_to_le32(slot->idx);
+
+	if (has_data) {
+		rc = prep_prd_sge_v2_hw(hisi_hba, slot, hdr, task->scatter,
+					slot->n_elem);
+		if (rc)
+			return rc;
+	}
+
+	hdr->data_transfer_len = cpu_to_le32(task->total_xfer_len);
+	hdr->cmd_table_addr = cpu_to_le64(slot->command_table_dma);
+	hdr->sts_buffer_addr = cpu_to_le64(slot->status_buffer_dma);
+
+	buf_cmd = slot->command_table + sizeof(struct ssp_frame_hdr);
+
+	memcpy(buf_cmd, &task->ssp_task.LUN, 8);
+	if (!is_tmf) {
+		buf_cmd[9] = task->ssp_task.task_attr |
+				(task->ssp_task.task_prio << 3);
+		memcpy(buf_cmd + 12, task->ssp_task.cmd->cmnd,
+				task->ssp_task.cmd->cmd_len);
+	} else {
+		buf_cmd[10] = tmf->tmf;
+		switch (tmf->tmf) {
+		case TMF_ABORT_TASK:
+		case TMF_QUERY_TASK:
+			buf_cmd[12] =
+				(tmf->tag_of_task_to_be_managed >> 8) & 0xff;
+			buf_cmd[13] =
+				tmf->tag_of_task_to_be_managed & 0xff;
+			break;
+		default:
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static void sata_done_v2_hw(struct hisi_hba *hisi_hba, struct sas_task *task,
+			    struct hisi_sas_slot *slot)
+{
+	struct task_status_struct *ts = &task->task_status;
+	struct ata_task_resp *resp = (struct ata_task_resp *)ts->buf;
+	struct dev_to_host_fis *d2h = slot->status_buffer +
+				      sizeof(struct hisi_sas_err_record);
+
+	resp->frame_len = sizeof(struct dev_to_host_fis);
+	memcpy(&resp->ending_fis[0], d2h, sizeof(struct dev_to_host_fis));
+
+	ts->buf_valid_size = sizeof(*resp);
+}
+
+/* by default, task resp is complete */
+static void slot_err_v2_hw(struct hisi_hba *hisi_hba,
+			   struct sas_task *task,
+			   struct hisi_sas_slot *slot)
+{
+	struct task_status_struct *ts = &task->task_status;
+	struct hisi_sas_err_record_v2 *err_record = slot->status_buffer;
+	u32 trans_tx_fail_type = cpu_to_le32(err_record->trans_tx_fail_type);
+	u32 trans_rx_fail_type = cpu_to_le32(err_record->trans_rx_fail_type);
+	u16 dma_tx_err_type = cpu_to_le16(err_record->dma_tx_err_type);
+	u16 sipc_rx_err_type = cpu_to_le16(err_record->sipc_rx_err_type);
+	u32 dma_rx_err_type = cpu_to_le32(err_record->dma_rx_err_type);
+	int error = -1;
+
+	if (dma_rx_err_type) {
+		error = ffs(dma_rx_err_type)
+			- 1 + DMA_RX_ERR_BASE;
+	} else if (sipc_rx_err_type) {
+		error = ffs(sipc_rx_err_type)
+			- 1 + SIPC_RX_ERR_BASE;
+	}  else if (dma_tx_err_type) {
+		error = ffs(dma_tx_err_type)
+			- 1 + DMA_TX_ERR_BASE;
+	} else if (trans_rx_fail_type) {
+		error = ffs(trans_rx_fail_type)
+			- 1 + TRANS_RX_FAIL_BASE;
+	} else if (trans_tx_fail_type) {
+		error = ffs(trans_tx_fail_type)
+			- 1 + TRANS_TX_FAIL_BASE;
+	}
+
+	switch (task->task_proto) {
+	case SAS_PROTOCOL_SSP:
+	{
+		switch (error) {
+		case TRANS_TX_OPEN_CNX_ERR_NO_DESTINATION:
+		{
+			ts->stat = SAS_OPEN_REJECT;
+			ts->open_rej_reason = SAS_OREJ_NO_DEST;
+			break;
+		}
+		case TRANS_TX_OPEN_CNX_ERR_PATHWAY_BLOCKED:
+		{
+			ts->stat = SAS_OPEN_REJECT;
+			ts->open_rej_reason = SAS_OREJ_PATH_BLOCKED;
+			break;
+		}
+		case TRANS_TX_OPEN_CNX_ERR_PROTOCOL_NOT_SUPPORTED:
+		{
+			ts->stat = SAS_OPEN_REJECT;
+			ts->open_rej_reason = SAS_OREJ_EPROTO;
+			break;
+		}
+		case TRANS_TX_OPEN_CNX_ERR_CONNECTION_RATE_NOT_SUPPORTED:
+		{
+			ts->stat = SAS_OPEN_REJECT;
+			ts->open_rej_reason = SAS_OREJ_CONN_RATE;
+			break;
+		}
+		case TRANS_TX_OPEN_CNX_ERR_BAD_DESTINATION:
+		{
+			ts->stat = SAS_OPEN_REJECT;
+			ts->open_rej_reason = SAS_OREJ_BAD_DEST;
+			break;
+		}
+		case TRANS_TX_OPEN_CNX_ERR_BREAK_RCVD:
+		{
+			ts->stat = SAS_OPEN_REJECT;
+			ts->open_rej_reason = SAS_OREJ_RSVD_RETRY;
+			break;
+		}
+		case TRANS_TX_OPEN_CNX_ERR_WRONG_DESTINATION:
+		{
+			ts->stat = SAS_OPEN_REJECT;
+			ts->open_rej_reason = SAS_OREJ_WRONG_DEST;
+			break;
+		}
+		case TRANS_TX_OPEN_CNX_ERR_ZONE_VIOLATION:
+		{
+			ts->stat = SAS_OPEN_REJECT;
+			ts->open_rej_reason = SAS_OREJ_UNKNOWN;
+			break;
+		}
+		case TRANS_TX_OPEN_CNX_ERR_LOW_PHY_POWER:
+		{
+			/* not sure */
+			ts->stat = SAS_DEV_NO_RESPONSE;
+			break;
+		}
+		case TRANS_RX_ERR_WITH_CLOSE_PHY_DISABLE:
+		{
+			ts->stat = SAS_PHY_DOWN;
+			break;
+		}
+		case TRANS_TX_OPEN_CNX_ERR_OPEN_TIMEOUT:
+		{
+			ts->stat = SAS_OPEN_TO;
+			break;
+		}
+		case DMA_RX_DATA_LEN_OVERFLOW:
+		{
+			ts->stat = SAS_DATA_OVERRUN;
+			ts->residual = 0;
+			break;
+		}
+		case DMA_RX_DATA_LEN_UNDERFLOW:
+		case SIPC_RX_DATA_UNDERFLOW_ERR:
+		{
+			ts->residual = trans_tx_fail_type;
+			ts->stat = SAS_DATA_UNDERRUN;
+			break;
+		}
+		case TRANS_TX_ERR_FRAME_TXED:
+		{
+			/* This will request a retry */
+			ts->stat = SAS_QUEUE_FULL;
+			slot->abort = 1;
+			break;
+		}
+		case TRANS_TX_OPEN_FAIL_WITH_IT_NEXUS_LOSS:
+		case TRANS_TX_ERR_PHY_NOT_ENABLE:
+		case TRANS_TX_OPEN_CNX_ERR_BY_OTHER:
+		case TRANS_TX_OPEN_CNX_ERR_AIP_TIMEOUT:
+		case TRANS_TX_OPEN_RETRY_ERR_THRESHOLD_REACHED:
+		case TRANS_TX_ERR_WITH_BREAK_TIMEOUT:
+		case TRANS_TX_ERR_WITH_BREAK_REQUEST:
+		case TRANS_TX_ERR_WITH_BREAK_RECEVIED:
+		case TRANS_TX_ERR_WITH_CLOSE_TIMEOUT:
+		case TRANS_TX_ERR_WITH_CLOSE_NORMAL:
+		case TRANS_TX_ERR_WITH_CLOSE_DWS_TIMEOUT:
+		case TRANS_TX_ERR_WITH_CLOSE_COMINIT:
+		case TRANS_TX_ERR_WITH_NAK_RECEVIED:
+		case TRANS_TX_ERR_WITH_ACK_NAK_TIMEOUT:
+		case TRANS_TX_ERR_WITH_IPTT_CONFLICT:
+		case TRANS_TX_ERR_WITH_CREDIT_TIMEOUT:
+		case TRANS_RX_ERR_WITH_RXFRAME_CRC_ERR:
+		case TRANS_RX_ERR_WITH_RXFIS_8B10B_DISP_ERR:
+		case TRANS_RX_ERR_WITH_RXFRAME_HAVE_ERRPRM:
+		case TRANS_RX_ERR_WITH_BREAK_TIMEOUT:
+		case TRANS_RX_ERR_WITH_BREAK_REQUEST:
+		case TRANS_RX_ERR_WITH_BREAK_RECEVIED:
+		case TRANS_RX_ERR_WITH_CLOSE_NORMAL:
+		case TRANS_RX_ERR_WITH_CLOSE_DWS_TIMEOUT:
+		case TRANS_RX_ERR_WITH_CLOSE_COMINIT:
+		case TRANS_RX_ERR_WITH_DATA_LEN0:
+		case TRANS_RX_ERR_WITH_BAD_HASH:
+		case TRANS_RX_XRDY_WLEN_ZERO_ERR:
+		case TRANS_RX_SSP_FRM_LEN_ERR:
+		case TRANS_RX_ERR_WITH_BAD_FRM_TYPE:
+		case DMA_TX_UNEXP_XFER_ERR:
+		case DMA_TX_UNEXP_RETRANS_ERR:
+		case DMA_TX_XFER_LEN_OVERFLOW:
+		case DMA_TX_XFER_OFFSET_ERR:
+		case DMA_RX_DATA_OFFSET_ERR:
+		case DMA_RX_UNEXP_NORM_RESP_ERR:
+		case DMA_RX_UNEXP_RDFRAME_ERR:
+		case DMA_RX_UNKNOWN_FRM_ERR:
+		{
+			ts->stat = SAS_OPEN_REJECT;
+			ts->open_rej_reason = SAS_OREJ_UNKNOWN;
+			break;
+		}
+		default:
+			break;
+		}
+	}
+		break;
+	case SAS_PROTOCOL_SMP:
+		ts->stat = SAM_STAT_CHECK_CONDITION;
+		break;
+
+	case SAS_PROTOCOL_SATA:
+	case SAS_PROTOCOL_STP:
+	case SAS_PROTOCOL_SATA | SAS_PROTOCOL_STP:
+	{
+		switch (error) {
+		case TRANS_TX_OPEN_CNX_ERR_LOW_PHY_POWER:
+		case TRANS_TX_OPEN_CNX_ERR_PATHWAY_BLOCKED:
+		case TRANS_TX_OPEN_CNX_ERR_NO_DESTINATION:
+		{
+			ts->resp = SAS_TASK_UNDELIVERED;
+			ts->stat = SAS_DEV_NO_RESPONSE;
+			break;
+		}
+		case TRANS_TX_OPEN_CNX_ERR_PROTOCOL_NOT_SUPPORTED:
+		case TRANS_TX_OPEN_CNX_ERR_CONNECTION_RATE_NOT_SUPPORTED:
+		case TRANS_TX_OPEN_CNX_ERR_BAD_DESTINATION:
+		case TRANS_TX_OPEN_CNX_ERR_BREAK_RCVD:
+		case TRANS_TX_OPEN_CNX_ERR_WRONG_DESTINATION:
+		case TRANS_TX_OPEN_CNX_ERR_ZONE_VIOLATION:
+		case TRANS_TX_OPEN_CNX_ERR_STP_RESOURCES_BUSY:
+		{
+			ts->stat = SAS_OPEN_REJECT;
+			break;
+		}
+		case TRANS_TX_OPEN_CNX_ERR_OPEN_TIMEOUT:
+		{
+			ts->stat = SAS_OPEN_TO;
+			break;
+		}
+		case DMA_RX_DATA_LEN_OVERFLOW:
+		{
+			ts->stat = SAS_DATA_OVERRUN;
+			break;
+		}
+		case TRANS_TX_OPEN_FAIL_WITH_IT_NEXUS_LOSS:
+		case TRANS_TX_ERR_PHY_NOT_ENABLE:
+		case TRANS_TX_OPEN_CNX_ERR_BY_OTHER:
+		case TRANS_TX_OPEN_CNX_ERR_AIP_TIMEOUT:
+		case TRANS_TX_OPEN_RETRY_ERR_THRESHOLD_REACHED:
+		case TRANS_TX_ERR_WITH_BREAK_TIMEOUT:
+		case TRANS_TX_ERR_WITH_BREAK_REQUEST:
+		case TRANS_TX_ERR_WITH_BREAK_RECEVIED:
+		case TRANS_TX_ERR_WITH_CLOSE_TIMEOUT:
+		case TRANS_TX_ERR_WITH_CLOSE_NORMAL:
+		case TRANS_TX_ERR_WITH_CLOSE_DWS_TIMEOUT:
+		case TRANS_TX_ERR_WITH_CLOSE_COMINIT:
+		case TRANS_TX_ERR_WITH_NAK_RECEVIED:
+		case TRANS_TX_ERR_WITH_ACK_NAK_TIMEOUT:
+		case TRANS_TX_ERR_WITH_CREDIT_TIMEOUT:
+		case TRANS_TX_ERR_WITH_WAIT_RECV_TIMEOUT:
+		case TRANS_RX_ERR_WITH_RXFIS_8B10B_DISP_ERR:
+		case TRANS_RX_ERR_WITH_RXFRAME_HAVE_ERRPRM:
+		case TRANS_RX_ERR_WITH_RXFIS_DECODE_ERROR:
+		case TRANS_RX_ERR_WITH_RXFIS_CRC_ERR:
+		case TRANS_RX_ERR_WITH_RXFRAME_LENGTH_OVERRUN:
+		case TRANS_RX_ERR_WITH_RXFIS_RX_SYNCP:
+		case TRANS_RX_ERR_WITH_CLOSE_NORMAL:
+		case TRANS_RX_ERR_WITH_CLOSE_PHY_DISABLE:
+		case TRANS_RX_ERR_WITH_CLOSE_DWS_TIMEOUT:
+		case TRANS_RX_ERR_WITH_CLOSE_COMINIT:
+		case TRANS_RX_ERR_WITH_DATA_LEN0:
+		case TRANS_RX_ERR_WITH_BAD_HASH:
+		case TRANS_RX_XRDY_WLEN_ZERO_ERR:
+		case TRANS_RX_SSP_FRM_LEN_ERR:
+		case SIPC_RX_FIS_STATUS_ERR_BIT_VLD:
+		case SIPC_RX_PIO_WRSETUP_STATUS_DRQ_ERR:
+		case SIPC_RX_FIS_STATUS_BSY_BIT_ERR:
+		case SIPC_RX_WRSETUP_LEN_ODD_ERR:
+		case SIPC_RX_WRSETUP_LEN_ZERO_ERR:
+		case SIPC_RX_WRDATA_LEN_NOT_MATCH_ERR:
+		case SIPC_RX_SATA_UNEXP_FIS_ERR:
+		case DMA_RX_SATA_FRAME_TYPE_ERR:
+		case DMA_RX_UNEXP_RDFRAME_ERR:
+		case DMA_RX_PIO_DATA_LEN_ERR:
+		case DMA_RX_RDSETUP_STATUS_ERR:
+		case DMA_RX_RDSETUP_STATUS_DRQ_ERR:
+		case DMA_RX_RDSETUP_STATUS_BSY_ERR:
+		case DMA_RX_RDSETUP_LEN_ODD_ERR:
+		case DMA_RX_RDSETUP_LEN_ZERO_ERR:
+		case DMA_RX_RDSETUP_LEN_OVER_ERR:
+		case DMA_RX_RDSETUP_OFFSET_ERR:
+		case DMA_RX_RDSETUP_ACTIVE_ERR:
+		case DMA_RX_RDSETUP_ESTATUS_ERR:
+		case DMA_RX_UNKNOWN_FRM_ERR:
+		{
+			ts->stat = SAS_OPEN_REJECT;
+			break;
+		}
+		default:
+		{
+			ts->stat = SAS_PROTO_RESPONSE;
+			break;
+		}
+		}
+		sata_done_v2_hw(hisi_hba, task, slot);
+	}
+		break;
+	default:
+		break;
+	}
+}
+
+static int
+slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot,
+		    int abort)
+{
+	struct sas_task *task = slot->task;
+	struct hisi_sas_device *sas_dev;
+	struct device *dev = &hisi_hba->pdev->dev;
+	struct task_status_struct *ts;
+	struct domain_device *device;
+	enum exec_status sts;
+	struct hisi_sas_complete_v2_hdr *complete_queue =
+			hisi_hba->complete_hdr[slot->cmplt_queue];
+	struct hisi_sas_complete_v2_hdr *complete_hdr =
+			&complete_queue[slot->cmplt_queue_slot];
+
+	if (unlikely(!task || !task->lldd_task || !task->dev))
+		return -EINVAL;
+
+	ts = &task->task_status;
+	device = task->dev;
+	sas_dev = device->lldd_dev;
+
+	task->task_state_flags &=
+		~(SAS_TASK_STATE_PENDING | SAS_TASK_AT_INITIATOR);
+	task->task_state_flags |= SAS_TASK_STATE_DONE;
+
+	memset(ts, 0, sizeof(*ts));
+	ts->resp = SAS_TASK_COMPLETE;
+
+	if (unlikely(!sas_dev || abort)) {
+		if (!sas_dev)
+			dev_dbg(dev, "slot complete: port has not device\n");
+		ts->stat = SAS_PHY_DOWN;
+		goto out;
+	}
+
+	if ((complete_hdr->dw0 & CMPLT_HDR_ERX_MSK) &&
+		(!(complete_hdr->dw0 & CMPLT_HDR_RSPNS_XFRD_MSK))) {
+
+		slot_err_v2_hw(hisi_hba, task, slot);
+		if (unlikely(slot->abort)) {
+			queue_work(hisi_hba->wq, &slot->abort_slot);
+			/* immediately return and do not complete */
+			return ts->stat;
+		}
+		goto out;
+	}
+
+	switch (task->task_proto) {
+	case SAS_PROTOCOL_SSP:
+	{
+		struct ssp_response_iu *iu = slot->status_buffer +
+			sizeof(struct hisi_sas_err_record);
+
+		sas_ssp_task_response(dev, task, iu);
+		break;
+	}
+	case SAS_PROTOCOL_SMP:
+	{
+		struct scatterlist *sg_resp = &task->smp_task.smp_resp;
+		void *to;
+
+		ts->stat = SAM_STAT_GOOD;
+		to = kmap_atomic(sg_page(sg_resp));
+
+		dma_unmap_sg(dev, &task->smp_task.smp_resp, 1,
+			     DMA_FROM_DEVICE);
+		dma_unmap_sg(dev, &task->smp_task.smp_req, 1,
+			     DMA_TO_DEVICE);
+		memcpy(to + sg_resp->offset,
+		       slot->status_buffer +
+		       sizeof(struct hisi_sas_err_record),
+		       sg_dma_len(sg_resp));
+		kunmap_atomic(to);
+		break;
+	}
+	case SAS_PROTOCOL_SATA:
+	case SAS_PROTOCOL_STP:
+	case SAS_PROTOCOL_SATA | SAS_PROTOCOL_STP:
+	{
+		ts->stat = SAM_STAT_GOOD;
+		sata_done_v2_hw(hisi_hba, task, slot);
+		break;
+	}
+	default:
+		ts->stat = SAM_STAT_CHECK_CONDITION;
+		break;
+	}
+
+	if (!slot->port->port_attached) {
+		dev_err(dev, "slot complete: port %d has removed\n",
+			slot->port->sas_port.id);
+		ts->stat = SAS_PHY_DOWN;
+	}
+
+out:
+	if (sas_dev && sas_dev->running_req)
+		sas_dev->running_req--;
+
+	hisi_sas_slot_task_free(hisi_hba, task, slot);
+	sts = ts->stat;
+
+	if (task->task_done)
+		task->task_done(task);
+
+	return sts;
+}
+
+static u8 get_ata_protocol(u8 cmd, int direction)
+{
+	switch (cmd) {
+	case ATA_CMD_FPDMA_WRITE:
+	case ATA_CMD_FPDMA_READ:
+	return SATA_PROTOCOL_FPDMA;
+
+	case ATA_CMD_ID_ATA:
+	case ATA_CMD_PMP_READ:
+	case ATA_CMD_READ_LOG_EXT:
+	case ATA_CMD_PIO_READ:
+	case ATA_CMD_PIO_READ_EXT:
+	case ATA_CMD_PMP_WRITE:
+	case ATA_CMD_WRITE_LOG_EXT:
+	case ATA_CMD_PIO_WRITE:
+	case ATA_CMD_PIO_WRITE_EXT:
+	return SATA_PROTOCOL_PIO;
+
+	case ATA_CMD_READ:
+	case ATA_CMD_READ_EXT:
+	case ATA_CMD_READ_LOG_DMA_EXT:
+	case ATA_CMD_WRITE:
+	case ATA_CMD_WRITE_EXT:
+	case ATA_CMD_WRITE_QUEUED:
+	case ATA_CMD_WRITE_LOG_DMA_EXT:
+	return SATA_PROTOCOL_DMA;
+
+	case ATA_CMD_DOWNLOAD_MICRO:
+	case ATA_CMD_DEV_RESET:
+	case ATA_CMD_CHK_POWER:
+	case ATA_CMD_FLUSH:
+	case ATA_CMD_FLUSH_EXT:
+	case ATA_CMD_VERIFY:
+	case ATA_CMD_VERIFY_EXT:
+	case ATA_CMD_SET_FEATURES:
+	case ATA_CMD_STANDBY:
+	case ATA_CMD_STANDBYNOW1:
+	return SATA_PROTOCOL_NONDATA;
+	default:
+		if (direction == DMA_NONE)
+			return SATA_PROTOCOL_NONDATA;
+		return SATA_PROTOCOL_PIO;
+	}
+}
+
+static int get_ncq_tag_v2_hw(struct sas_task *task, u32 *tag)
+{
+	struct ata_queued_cmd *qc = task->uldd_task;
+
+	if (qc) {
+		if (qc->tf.command == ATA_CMD_FPDMA_WRITE ||
+			qc->tf.command == ATA_CMD_FPDMA_READ) {
+			*tag = qc->tag;
+			return 1;
+		}
+	}
+	return 0;
+}
+
+static int prep_ata_v2_hw(struct hisi_hba *hisi_hba,
+			  struct hisi_sas_slot *slot)
+{
+	struct sas_task *task = slot->task;
+	struct domain_device *device = task->dev;
+	struct domain_device *parent_dev = device->parent;
+	struct hisi_sas_device *sas_dev = device->lldd_dev;
+	struct hisi_sas_cmd_hdr *hdr = slot->cmd_hdr;
+	struct hisi_sas_port *port = device->port->lldd_port;
+	u8 *buf_cmd;
+	int has_data = 0, rc = 0, hdr_tag = 0;
+	u32 dw1 = 0, dw2 = 0;
+
+	/* create header */
+	/* dw0 */
+	hdr->dw0 = cpu_to_le32(port->id << CMD_HDR_PORT_OFF);
+	if (parent_dev && DEV_IS_EXPANDER(parent_dev->dev_type))
+		hdr->dw0 |= cpu_to_le32(3 << CMD_HDR_CMD_OFF);
+	else
+		hdr->dw0 |= cpu_to_le32(4 << CMD_HDR_CMD_OFF);
+
+	/* dw1 */
+	switch (task->data_dir) {
+	case DMA_TO_DEVICE:
+		has_data = 1;
+		dw1 |= DIR_TO_DEVICE << CMD_HDR_DIR_OFF;
+		break;
+	case DMA_FROM_DEVICE:
+		has_data = 1;
+		dw1 |= DIR_TO_INI << CMD_HDR_DIR_OFF;
+		break;
+	default:
+		dw1 &= ~CMD_HDR_DIR_MSK;
+	}
+
+	if (0 == task->ata_task.fis.command)
+		dw1 |= 1 << CMD_HDR_RESET_OFF;
+
+	dw1 |= (get_ata_protocol(task->ata_task.fis.command, task->data_dir))
+		<< CMD_HDR_FRAME_TYPE_OFF;
+	dw1 |= sas_dev->device_id << CMD_HDR_DEV_ID_OFF;
+	hdr->dw1 = cpu_to_le32(dw1);
+
+	/* dw2 */
+	if (task->ata_task.use_ncq && get_ncq_tag_v2_hw(task, &hdr_tag)) {
+		task->ata_task.fis.sector_count |= (u8) (hdr_tag << 3);
+		dw2 |= hdr_tag << CMD_HDR_NCQ_TAG_OFF;
+	}
+
+	dw2 |= (HISI_SAS_MAX_STP_RESP_SZ / 4) << CMD_HDR_CFL_OFF |
+			2 << CMD_HDR_SG_MOD_OFF;
+	hdr->dw2 = cpu_to_le32(dw2);
+
+	/* dw3 */
+	hdr->transfer_tags = cpu_to_le32(slot->idx);
+
+	if (has_data) {
+		rc = prep_prd_sge_v2_hw(hisi_hba, slot, hdr, task->scatter,
+					slot->n_elem);
+		if (rc)
+			return rc;
+	}
+
+
+	hdr->data_transfer_len = cpu_to_le32(task->total_xfer_len);
+	hdr->cmd_table_addr = cpu_to_le64(slot->command_table_dma);
+	hdr->sts_buffer_addr = cpu_to_le64(slot->status_buffer_dma);
+
+	buf_cmd = slot->command_table;
+
+	if (likely(!task->ata_task.device_control_reg_update))
+		task->ata_task.fis.flags |= 0x80; /* C=1: update ATA cmd reg */
+	/* fill in command FIS */
+	memcpy(buf_cmd, &task->ata_task.fis, sizeof(struct host_to_dev_fis));
+
+	return 0;
+}
+
+static int phy_up_v2_hw(int phy_no, struct hisi_hba *hisi_hba)
+{
+	int i, res = 0;
+	u32 context, port_id, link_rate, hard_phy_linkrate;
+	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
+	struct asd_sas_phy *sas_phy = &phy->sas_phy;
+	struct device *dev = &hisi_hba->pdev->dev;
+	u32 *frame_rcvd = (u32 *)sas_phy->frame_rcvd;
+	struct sas_identify_frame *id = (struct sas_identify_frame *)frame_rcvd;
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, PHYCTRL_PHY_ENA_MSK, 1);
+
+	/* Check for SATA dev */
+	context = hisi_sas_read32(hisi_hba, PHY_CONTEXT);
+	if (context & (1 << phy_no))
+		goto end;
+
+	if (phy_no == 8) {
+		u32 port_state = hisi_sas_read32(hisi_hba, PORT_STATE);
+
+		port_id = (port_state & PORT_STATE_PHY8_PORT_NUM_MSK) >>
+			  PORT_STATE_PHY8_PORT_NUM_OFF;
+		link_rate = (port_state & PORT_STATE_PHY8_CONN_RATE_MSK) >>
+			    PORT_STATE_PHY8_CONN_RATE_OFF;
+	} else {
+		port_id = hisi_sas_read32(hisi_hba, PHY_PORT_NUM_MA);
+		port_id = (port_id >> (4 * phy_no)) & 0xf;
+		link_rate = hisi_sas_read32(hisi_hba, PHY_CONN_RATE);
+		link_rate = (link_rate >> (phy_no * 4)) & 0xf;
+	}
+
+	if (port_id == 0xf) {
+		dev_err(dev, "phyup: phy%d invalid portid\n", phy_no);
+		res = IRQ_NONE;
+		goto end;
+	}
+
+	for (i = 0; i < 6; i++) {
+		u32 idaf = hisi_sas_phy_read32(hisi_hba, phy_no,
+					       RX_IDAF_DWORD0 + (i * 4));
+		frame_rcvd[i] = __swab32(idaf);
+	}
+
+	/* Get the linkrates */
+	link_rate = hisi_sas_read32(hisi_hba, PHY_CONN_RATE);
+	link_rate = (link_rate >> (phy_no * 4)) & 0xf;
+	sas_phy->linkrate = link_rate;
+	hard_phy_linkrate = hisi_sas_phy_read32(hisi_hba, phy_no,
+						HARD_PHY_LINKRATE);
+	phy->maximum_linkrate = hard_phy_linkrate & 0xf;
+	phy->minimum_linkrate = (hard_phy_linkrate >> 4) & 0xf;
+
+	sas_phy->oob_mode = SAS_OOB_MODE;
+	memcpy(sas_phy->attached_sas_addr, &id->sas_addr, SAS_ADDR_SIZE);
+	dev_info(dev, "phyup: phy%d link_rate=%d\n", phy_no, link_rate);
+	phy->port_id = port_id;
+	phy->phy_type &= ~(PORT_TYPE_SAS | PORT_TYPE_SATA);
+	phy->phy_type |= PORT_TYPE_SAS;
+	phy->phy_attached = 1;
+	phy->identify.device_type = id->dev_type;
+	phy->frame_rcvd_size =	sizeof(struct sas_identify_frame);
+	if (phy->identify.device_type == SAS_END_DEVICE)
+		phy->identify.target_port_protocols =
+			SAS_PROTOCOL_SSP;
+	else if (phy->identify.device_type != SAS_PHY_UNUSED)
+		phy->identify.target_port_protocols =
+			SAS_PROTOCOL_SMP;
+	queue_work(hisi_hba->wq, &phy->phyup_ws);
+
+end:
+	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0,
+			     CHL_INT0_SL_PHY_ENABLE_MSK);
+	hisi_sas_phy_write32(hisi_hba, phy_no, PHYCTRL_PHY_ENA_MSK, 0);
+
+	return res;
+}
+
+static int phy_down_v2_hw(int phy_no, struct hisi_hba *hisi_hba)
+{
+	int res = 0;
+	u32 phy_cfg, phy_state;
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, PHYCTRL_NOT_RDY_MSK, 1);
+
+	phy_cfg = hisi_sas_phy_read32(hisi_hba, phy_no, PHY_CFG);
+
+	phy_state = hisi_sas_read32(hisi_hba, PHY_STATE);
+
+	hisi_sas_phy_down(hisi_hba, phy_no, (phy_state & 1 << phy_no) ? 1 : 0);
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0, CHL_INT0_NOT_RDY_MSK);
+	hisi_sas_phy_write32(hisi_hba, phy_no, PHYCTRL_NOT_RDY_MSK, 0);
+
+	return res;
+}
+
+static irqreturn_t int_phy_updown_v2_hw(int irq_no, void *p)
+{
+	struct hisi_hba *hisi_hba = p;
+	u32 irq_msk;
+	int phy_no = 0;
+	irqreturn_t res = IRQ_HANDLED;
+
+	irq_msk = (hisi_sas_read32(hisi_hba, HGC_INVLD_DQE_INFO)
+		   >> HGC_INVLD_DQE_INFO_FB_CH0_OFF) & 0x1ff;
+	while (irq_msk) {
+		if (irq_msk  & 1) {
+			u32 irq_value = hisi_sas_phy_read32(hisi_hba, phy_no,
+							    CHL_INT0);
+
+			if (irq_value & CHL_INT0_SL_PHY_ENABLE_MSK)
+				/* phy up */
+				if (phy_up_v2_hw(phy_no, hisi_hba)) {
+					res = IRQ_NONE;
+					goto end;
+				}
+
+			if (irq_value & CHL_INT0_NOT_RDY_MSK)
+				/* phy down */
+				if (phy_down_v2_hw(phy_no, hisi_hba)) {
+					res = IRQ_NONE;
+					goto end;
+				}
+		}
+		irq_msk >>= 1;
+		phy_no++;
+	}
+
+end:
+	return res;
+}
+
+static void phy_bcast_v2_hw(int phy_no, struct hisi_hba *hisi_hba)
+{
+	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
+	struct asd_sas_phy *sas_phy = &phy->sas_phy;
+	struct sas_ha_struct *sas_ha = &hisi_hba->sha;
+	unsigned long flags;
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 1);
+
+	spin_lock_irqsave(&hisi_hba->lock, flags);
+	sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
+	spin_unlock_irqrestore(&hisi_hba->lock, flags);
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0,
+			     CHL_INT0_SL_RX_BCST_ACK_MSK);
+	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 0);
+}
+
+static irqreturn_t int_chnl_int_v2_hw(int irq_no, void *p)
+{
+	struct hisi_hba *hisi_hba = p;
+	struct device *dev = &hisi_hba->pdev->dev;
+	u32 ent_msk, ent_tmp, irq_msk;
+	int phy_no = 0;
+
+	ent_msk = hisi_sas_read32(hisi_hba, ENT_INT_SRC_MSK3);
+	ent_tmp = ent_msk;
+	ent_msk |= ENT_INT_SRC_MSK3_ENT95_MSK_MSK;
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK3, ent_msk);
+
+	irq_msk = (hisi_sas_read32(hisi_hba, HGC_INVLD_DQE_INFO) >>
+			HGC_INVLD_DQE_INFO_FB_CH3_OFF) & 0x1ff;
+
+	while (irq_msk) {
+		if (irq_msk & (1 << phy_no)) {
+			u32 irq_value0 = hisi_sas_phy_read32(hisi_hba, phy_no,
+							     CHL_INT0);
+			u32 irq_value1 = hisi_sas_phy_read32(hisi_hba, phy_no,
+							     CHL_INT1);
+			u32 irq_value2 = hisi_sas_phy_read32(hisi_hba, phy_no,
+							     CHL_INT2);
+
+			if (irq_value1) {
+				if (irq_value1 & (CHL_INT1_DMAC_RX_ECC_ERR_MSK |
+						  CHL_INT1_DMAC_TX_ECC_ERR_MSK))
+					panic("%s: DMAC RX/TX ecc bad error! (0x%x)",
+						dev_name(dev), irq_value1);
+
+				hisi_sas_phy_write32(hisi_hba, phy_no,
+						     CHL_INT1, irq_value1);
+			}
+
+			if (irq_value2)
+				hisi_sas_phy_write32(hisi_hba, phy_no,
+						     CHL_INT2, irq_value2);
+
+
+			if (irq_value0) {
+				if (irq_value0 & CHL_INT0_SL_RX_BCST_ACK_MSK)
+					phy_bcast_v2_hw(phy_no, hisi_hba);
+
+				hisi_sas_phy_write32(hisi_hba, phy_no,
+						CHL_INT0, irq_value0
+						& (~CHL_INT0_HOTPLUG_TOUT_MSK)
+						& (~CHL_INT0_SL_PHY_ENABLE_MSK)
+						& (~CHL_INT0_NOT_RDY_MSK));
+			}
+		}
+		irq_msk &= ~(1 << phy_no);
+		phy_no++;
+	}
+
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK3, ent_tmp);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t cq_interrupt_v2_hw(int irq_no, void *p)
+{
+	struct hisi_sas_cq *cq = p;
+	struct hisi_hba *hisi_hba = cq->hisi_hba;
+	struct hisi_sas_slot *slot;
+	struct hisi_sas_itct *itct;
+	struct hisi_sas_complete_v2_hdr *complete_queue;
+	u32 irq_value, rd_point, wr_point, dev_id;
+	int queue = cq->id;
+
+	complete_queue = hisi_hba->complete_hdr[queue];
+	irq_value = hisi_sas_read32(hisi_hba, OQ_INT_SRC);
+
+	hisi_sas_write32(hisi_hba, OQ_INT_SRC, 1 << queue);
+
+	rd_point = hisi_sas_read32(hisi_hba, COMPL_Q_0_RD_PTR +
+				   (0x14 * queue));
+	wr_point = hisi_sas_read32(hisi_hba, COMPL_Q_0_WR_PTR +
+				   (0x14 * queue));
+
+	while (rd_point != wr_point) {
+		struct hisi_sas_complete_v2_hdr *complete_hdr;
+		int iptt;
+
+		complete_hdr = &complete_queue[rd_point];
+
+		/* Check for NCQ completion */
+		if (complete_hdr->act) {
+			u32 act_tmp = complete_hdr->act;
+			int ncq_tag_count = ffs(act_tmp);
+
+			dev_id = (complete_hdr->dw1 & CMPLT_HDR_DEV_ID_MSK) >>
+				 CMPLT_HDR_DEV_ID_OFF;
+			itct = &hisi_hba->itct[dev_id];
+
+			/* The NCQ tags are held in the itct header */
+			while (ncq_tag_count) {
+				__le64 *ncq_tag = &itct->qw4_15[0];
+
+				ncq_tag_count -= 1;
+				iptt = (ncq_tag[ncq_tag_count / 5]
+					>> (ncq_tag_count % 5) * 12) & 0xfff;
+
+				slot = &hisi_hba->slot_info[iptt];
+				slot->cmplt_queue_slot = rd_point;
+				slot->cmplt_queue = queue;
+				slot_complete_v2_hw(hisi_hba, slot, 0);
+
+				act_tmp &= ~(1 << ncq_tag_count);
+				ncq_tag_count = ffs(act_tmp);
+			}
+		} else {
+			iptt = (complete_hdr->dw1) & CMPLT_HDR_IPTT_MSK;
+			slot = &hisi_hba->slot_info[iptt];
+			slot->cmplt_queue_slot = rd_point;
+			slot->cmplt_queue = queue;
+			slot_complete_v2_hw(hisi_hba, slot, 0);
+		}
+
+		if (++rd_point >= HISI_SAS_QUEUE_SLOTS)
+			rd_point = 0;
+	}
+
+	/* update rd_point */
+	hisi_sas_write32(hisi_hba, COMPL_Q_0_RD_PTR + (0x14 * queue), rd_point);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t sata_int_v2_hw(int irq_no, void *p)
+{
+	struct hisi_sas_phy *phy = p;
+	struct hisi_hba *hisi_hba = phy->hisi_hba;
+	struct asd_sas_phy *sas_phy = &phy->sas_phy;
+	struct device *dev = &hisi_hba->pdev->dev;
+	struct	hisi_sas_initial_fis *initial_fis;
+	struct dev_to_host_fis *fis;
+	u32 ent_tmp, ent_msk, ent_int, port_id, link_rate, hard_phy_linkrate;
+	irqreturn_t res = IRQ_HANDLED;
+	u8 attached_sas_addr[SAS_ADDR_SIZE] = {0};
+	int phy_no;
+
+	phy_no = sas_phy->id;
+	initial_fis = &hisi_hba->initial_fis[phy_no];
+	fis = &initial_fis->fis;
+
+	ent_msk = hisi_sas_read32(hisi_hba, ENT_INT_SRC_MSK1);
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK1, ent_msk | 1 << phy_no);
+
+	ent_int = hisi_sas_read32(hisi_hba, ENT_INT_SRC1);
+	ent_tmp = ent_int;
+	ent_int >>= ENT_INT_SRC1_D2H_FIS_CH1_OFF * (phy_no % 4);
+	if ((ent_int & ENT_INT_SRC1_D2H_FIS_CH0_MSK) == 0) {
+		dev_warn(dev, "sata int: phy%d did not receive FIS\n", phy_no);
+		hisi_sas_write32(hisi_hba, ENT_INT_SRC1, ent_tmp);
+		hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK1, ent_msk);
+		res = IRQ_NONE;
+		goto end;
+	}
+
+	if (unlikely(phy_no == 8)) {
+		u32 port_state = hisi_sas_read32(hisi_hba, PORT_STATE);
+
+		port_id = (port_state & PORT_STATE_PHY8_PORT_NUM_MSK) >>
+			  PORT_STATE_PHY8_PORT_NUM_OFF;
+		link_rate = (port_state & PORT_STATE_PHY8_CONN_RATE_MSK) >>
+			    PORT_STATE_PHY8_CONN_RATE_OFF;
+	} else {
+		port_id = hisi_sas_read32(hisi_hba, PHY_PORT_NUM_MA);
+		port_id = (port_id >> (4 * phy_no)) & 0xf;
+		link_rate = hisi_sas_read32(hisi_hba, PHY_CONN_RATE);
+		link_rate = (link_rate >> (phy_no * 4)) & 0xf;
+	}
+
+	if (port_id == 0xf) {
+		dev_err(dev, "sata int: phy%d invalid portid\n", phy_no);
+		res = IRQ_NONE;
+		goto end;
+	}
+
+	sas_phy->linkrate = link_rate;
+	hard_phy_linkrate = hisi_sas_phy_read32(hisi_hba, phy_no,
+						HARD_PHY_LINKRATE);
+	phy->maximum_linkrate = hard_phy_linkrate & 0xf;
+	phy->minimum_linkrate = (hard_phy_linkrate >> 4) & 0xf;
+
+	sas_phy->oob_mode = SATA_OOB_MODE;
+	/* Make up some unique SAS address */
+	attached_sas_addr[0] = 0x50;
+	attached_sas_addr[7] = phy_no;
+	memcpy(sas_phy->attached_sas_addr, attached_sas_addr, SAS_ADDR_SIZE);
+	memcpy(sas_phy->frame_rcvd, fis, sizeof(struct dev_to_host_fis));
+	dev_info(dev, "sata int phyup: phy%d link_rate=%d\n", phy_no, link_rate);
+	phy->phy_type &= ~(PORT_TYPE_SAS | PORT_TYPE_SATA);
+	phy->port_id = port_id;
+	phy->phy_type |= PORT_TYPE_SATA;
+	phy->phy_attached = 1;
+	phy->identify.device_type = SAS_SATA_DEV;
+	phy->frame_rcvd_size = sizeof(struct dev_to_host_fis);
+	phy->identify.target_port_protocols = SAS_PROTOCOL_SATA;
+	queue_work(hisi_hba->wq, &phy->phyup_ws);
+
+end:
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC1, ent_tmp);
+	hisi_sas_write32(hisi_hba, ENT_INT_SRC_MSK1, ent_msk);
+
+	return res;
+}
+
+static irq_handler_t phy_interrupts[HISI_SAS_PHY_INT_NR] = {
+	int_phy_updown_v2_hw,
+	int_chnl_int_v2_hw,
+};
+
+/**
+ * There is a limitation in the hip06 chipset that we need
+ * to map in all mbigen interrupts, even if they are not used.
+ */
+static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
+{
+	struct platform_device *pdev = hisi_hba->pdev;
+	struct device *dev = &pdev->dev;
+	int i, irq, rc, irq_map[128];
+
+
+	for (i = 0; i < 128; i++)
+		irq_map[i] = platform_get_irq(pdev, i);
+
+	for (i = 0; i < HISI_SAS_PHY_INT_NR; i++) {
+		int idx = i;
+
+		irq = irq_map[idx + 1]; /* Phy up/down is irq1 */
+		if (!irq) {
+			dev_err(dev, "irq init: fail map phy interrupt %d\n",
+				idx);
+			return -ENOENT;
+		}
+
+		rc = devm_request_irq(dev, irq, phy_interrupts[i], 0,
+				      DRV_NAME " phy", hisi_hba);
+		if (rc) {
+			dev_err(dev, "irq init: could not request "
+				"phy interrupt %d, rc=%d\n",
+				irq, rc);
+			return -ENOENT;
+		}
+	}
+
+	for (i = 0; i < hisi_hba->n_phy; i++) {
+		struct hisi_sas_phy *phy = &hisi_hba->phy[i];
+		int idx = i + 72; /* First SATA interrupt is irq72 */
+
+		irq = irq_map[idx];
+		if (!irq) {
+			dev_err(dev, "irq init: fail map phy interrupt %d\n",
+				idx);
+			return -ENOENT;
+		}
+
+		rc = devm_request_irq(dev, irq, sata_int_v2_hw, 0,
+				      DRV_NAME " sata", phy);
+		if (rc) {
+			dev_err(dev, "irq init: could not request "
+				"sata interrupt %d, rc=%d\n",
+				irq, rc);
+			return -ENOENT;
+		}
+	}
+
+	for (i = 0; i < hisi_hba->queue_count; i++) {
+		int idx = i + 96; /* First cq interrupt is irq96 */
+
+		irq = irq_map[idx];
+		if (!irq) {
+			dev_err(dev,
+				"irq init: could not map cq interrupt %d\n",
+				idx);
+			return -ENOENT;
+		}
+		rc = devm_request_irq(dev, irq, cq_interrupt_v2_hw, 0,
+				      DRV_NAME " cq", &hisi_hba->cq[i]);
+		if (rc) {
+			dev_err(dev,
+				"irq init: could not request cq interrupt %d, rc=%d\n",
+				irq, rc);
+			return -ENOENT;
+		}
+	}
+
+	return 0;
+}
+
+static int hisi_sas_v2_init(struct hisi_hba *hisi_hba)
+{
+	int rc;
+
+	rc = hw_init_v2_hw(hisi_hba);
+	if (rc)
+		return rc;
+
+	rc = interrupt_init_v2_hw(hisi_hba);
+	if (rc)
+		return rc;
+
+	phys_init_v2_hw(hisi_hba);
+
+	return 0;
+}
+
+static const struct hisi_sas_hw hisi_sas_v2_hw = {
+	.hw_init = hisi_sas_v2_init,
+	.setup_itct = setup_itct_v2_hw,
+	.sl_notify = sl_notify_v2_hw,
+	.get_wideport_bitmap = get_wideport_bitmap_v2_hw,
+	.free_device = free_device_v2_hw,
+	.prep_smp = prep_smp_v2_hw,
+	.prep_ssp = prep_ssp_v2_hw,
+	.prep_stp = prep_ata_v2_hw,
+	.get_free_slot = get_free_slot_v2_hw,
+	.start_delivery = start_delivery_v2_hw,
+	.slot_complete = slot_complete_v2_hw,
+	.phy_enable = enable_phy_v2_hw,
+	.phy_disable = disable_phy_v2_hw,
+	.phy_hard_reset = phy_hard_reset_v2_hw,
+	.max_command_entries = HISI_SAS_COMMAND_ENTRIES_V2_HW,
+	.complete_hdr_size = sizeof(struct hisi_sas_complete_v2_hdr),
+};
+
+static int hisi_sas_v2_probe(struct platform_device *pdev)
+{
+	return hisi_sas_probe(pdev, &hisi_sas_v2_hw);
+}
+
+static int hisi_sas_v2_remove(struct platform_device *pdev)
+{
+	return hisi_sas_remove(pdev);
+}
+
+static const struct of_device_id sas_v2_of_match[] = {
+	{ .compatible = "hisilicon,hip06-sas-v2",},
+	{},
+};
+MODULE_DEVICE_TABLE(of, sas_v2_of_match);
+
+static struct platform_driver hisi_sas_v2_driver = {
+	.probe = hisi_sas_v2_probe,
+	.remove = hisi_sas_v2_remove,
+	.driver = {
+		.name = DRV_NAME,
+		.of_match_table = sas_v2_of_match,
+	},
+};
+
+module_platform_driver(hisi_sas_v2_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("John Garry <john.garry@huawei.com>");
+MODULE_DESCRIPTION("HISILICON SAS controller v2 hw driver");
+MODULE_ALIAS("platform:" DRV_NAME);
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 82ac1cd818ac..94025c5cf797 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -33,7 +33,7 @@
 #include <linux/transport_class.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
-
+#include <linux/idr.h>
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_transport.h>
@@ -42,7 +42,7 @@
 #include "scsi_logging.h"
 
 
-static atomic_t scsi_host_next_hn = ATOMIC_INIT(0);	/* host_no for next new host */
+static DEFINE_IDA(host_index_ida);
 
 
 static void scsi_host_cls_release(struct device *dev)
@@ -355,6 +355,8 @@ static void scsi_host_dev_release(struct device *dev)
 
 	kfree(shost->shost_data);
 
+	ida_simple_remove(&host_index_ida, shost->host_no);
+
 	if (parent)
 		put_device(parent);
 	kfree(shost);
@@ -388,6 +390,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 {
 	struct Scsi_Host *shost;
 	gfp_t gfp_mask = GFP_KERNEL;
+	int index;
 
 	if (sht->unchecked_isa_dma && privsize)
 		gfp_mask |= __GFP_DMA;
@@ -406,11 +409,11 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 	init_waitqueue_head(&shost->host_wait);
 	mutex_init(&shost->scan_mutex);
 
-	/*
-	 * subtract one because we increment first then return, but we need to
-	 * know what the next host number was before increment
-	 */
-	shost->host_no = atomic_inc_return(&scsi_host_next_hn) - 1;
+	index = ida_simple_get(&host_index_ida, 0, 0, GFP_KERNEL);
+	if (index < 0)
+		goto fail_kfree;
+	shost->host_no = index;
+
 	shost->dma_channel = 0xff;
 
 	/* These three are default values which can be overridden */
@@ -495,7 +498,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 		shost_printk(KERN_WARNING, shost,
 			"error handler thread failed to spawn, error = %ld\n",
 			PTR_ERR(shost->ehandler));
-		goto fail_kfree;
+		goto fail_index_remove;
 	}
 
 	shost->tmf_work_q = alloc_workqueue("scsi_tmf_%d",
@@ -511,6 +514,8 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 
  fail_kthread:
 	kthread_stop(shost->ehandler);
+ fail_index_remove:
+	ida_simple_remove(&host_index_ida, shost->host_no);
  fail_kfree:
 	kfree(shost);
 	return NULL;
@@ -606,6 +611,7 @@ int scsi_init_hosts(void)
 void scsi_exit_hosts(void)
 {
 	class_unregister(&shost_class);
+	ida_destroy(&host_index_ida);
 }
 
 int scsi_is_host_device(const struct device *dev)
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 38ce0e308fbe..5be944c8b71c 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -1,5 +1,6 @@
 /*
  *    Disk Array driver for HP Smart Array SAS controllers
+ *    Copyright 2016 Microsemi Corporation
  *    Copyright 2014-2015 PMC-Sierra, Inc.
  *    Copyright 2000,2009-2015 Hewlett-Packard Development Company, L.P.
  *
@@ -12,7 +13,7 @@
  *    MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
  *    NON INFRINGEMENT.  See the GNU General Public License for more details.
  *
- *    Questions/Comments/Bugfixes to storagedev@pmcs.com
+ *    Questions/Comments/Bugfixes to esc.storagedev@microsemi.com
  *
  */
 
@@ -809,7 +810,8 @@ static ssize_t path_info_show(struct device *dev,
 				PAGE_SIZE - output_len,
 				"PORT: %.2s ",
 				phys_connector);
-		if (hdev->devtype == TYPE_DISK && hdev->expose_device) {
+		if ((hdev->devtype == TYPE_DISK || hdev->devtype == TYPE_ZBC) &&
+			hdev->expose_device) {
 			if (box == 0 || box == 0xFF) {
 				output_len += scnprintf(buf + output_len,
 					PAGE_SIZE - output_len,
@@ -1166,6 +1168,7 @@ static void hpsa_show_dev_msg(const char *level, struct ctlr_info *h,
 		snprintf(label, LABEL_SIZE, "enclosure");
 		break;
 	case TYPE_DISK:
+	case TYPE_ZBC:
 		if (dev->external)
 			snprintf(label, LABEL_SIZE, "external");
 		else if (!is_logical_dev_addr_mode(dev->scsi3addr))
@@ -1636,6 +1639,8 @@ static void hpsa_figure_phys_disk_ptrs(struct ctlr_info *h,
 				continue;
 			if (dev[j]->devtype != TYPE_DISK)
 				continue;
+			if (dev[j]->devtype != TYPE_ZBC)
+				continue;
 			if (is_logical_device(dev[j]))
 				continue;
 			if (dev[j]->ioaccel_handle != dd[i].ioaccel_handle)
@@ -1681,6 +1686,8 @@ static void hpsa_update_log_drive_phys_drive_ptrs(struct ctlr_info *h,
 			continue;
 		if (dev[i]->devtype != TYPE_DISK)
 			continue;
+		if (dev[i]->devtype != TYPE_ZBC)
+			continue;
 		if (!is_logical_device(dev[i]))
 			continue;
 
@@ -3208,8 +3215,10 @@ static void hpsa_get_enclosure_info(struct ctlr_info *h,
 
 	bmic_device_index = GET_BMIC_DRIVE_NUMBER(&rle->lunid[0]);
 
-	if (bmic_device_index == 0xFF00)
+	if (bmic_device_index == 0xFF00 || MASKED_DEVICE(&rle->lunid[0])) {
+		rc = IO_OK;
 		goto out;
+	}
 
 	bssbp = kzalloc(sizeof(*bssbp), GFP_KERNEL);
 	if (!bssbp)
@@ -3657,18 +3666,6 @@ static int hpsa_device_supports_aborts(struct ctlr_info *h,
 	return rc;
 }
 
-static void sanitize_inquiry_string(unsigned char *s, int len)
-{
-	bool terminated = false;
-
-	for (; len > 0; (--len, ++s)) {
-		if (*s == 0)
-			terminated = true;
-		if (terminated || *s < 0x20 || *s > 0x7e)
-			*s = ' ';
-	}
-}
-
 static int hpsa_update_device_info(struct ctlr_info *h,
 	unsigned char scsi3addr[], struct hpsa_scsi_dev_t *this_device,
 	unsigned char *is_OBDR_device)
@@ -3699,8 +3696,8 @@ static int hpsa_update_device_info(struct ctlr_info *h,
 		goto bail_out;
 	}
 
-	sanitize_inquiry_string(&inq_buff[8], 8);
-	sanitize_inquiry_string(&inq_buff[16], 16);
+	scsi_sanitize_inquiry_string(&inq_buff[8], 8);
+	scsi_sanitize_inquiry_string(&inq_buff[16], 16);
 
 	this_device->devtype = (inq_buff[0] & 0x1f);
 	memcpy(this_device->scsi3addr, scsi3addr, 8);
@@ -3713,7 +3710,8 @@ static int hpsa_update_device_info(struct ctlr_info *h,
 	hpsa_get_device_id(h, scsi3addr, this_device->device_id, 8,
 		sizeof(this_device->device_id));
 
-	if (this_device->devtype == TYPE_DISK &&
+	if ((this_device->devtype == TYPE_DISK ||
+		this_device->devtype == TYPE_ZBC) &&
 		is_logical_dev_addr_mode(scsi3addr)) {
 		int volume_offline;
 
@@ -4181,6 +4179,7 @@ static void hpsa_update_scsi_devices(struct ctlr_info *h)
 				ncurrent++;
 			break;
 		case TYPE_DISK:
+		case TYPE_ZBC:
 			if (this_device->physical_device) {
 				/* The disk is in HBA mode. */
 				/* Never use RAID mapper in HBA mode. */
@@ -4197,7 +4196,8 @@ static void hpsa_update_scsi_devices(struct ctlr_info *h)
 			ncurrent++;
 			break;
 		case TYPE_ENCLOSURE:
-			hpsa_get_enclosure_info(h, lunaddrbytes,
+			if (!this_device->external)
+				hpsa_get_enclosure_info(h, lunaddrbytes,
 						physdev_list, phys_dev_index,
 						this_device);
 			ncurrent++;
@@ -4970,6 +4970,8 @@ static int hpsa_scsi_ioaccel_raid_map(struct ctlr_info *h,
 		return IO_ACCEL_INELIGIBLE;
 
 	c->phys_disk = dev->phys_disk[map_index];
+	if (!c->phys_disk)
+		return IO_ACCEL_INELIGIBLE;
 
 	disk_handle = dd[map_index].ioaccel_handle;
 	disk_block = le64_to_cpu(map->disk_starting_blk) +
@@ -5835,7 +5837,7 @@ static int hpsa_send_abort_ioaccel2(struct ctlr_info *h,
 }
 
 static int hpsa_send_abort_both_ways(struct ctlr_info *h,
-	unsigned char *scsi3addr, struct CommandList *abort, int reply_queue)
+	struct hpsa_scsi_dev_t *dev, struct CommandList *abort, int reply_queue)
 {
 	/*
 	 * ioccelerator mode 2 commands should be aborted via the
@@ -5844,14 +5846,16 @@ static int hpsa_send_abort_both_ways(struct ctlr_info *h,
 	 * Change abort to physical device reset when abort TMF is unsupported.
 	 */
 	if (abort->cmd_type == CMD_IOACCEL2) {
-		if (HPSATMF_IOACCEL_ENABLED & h->TMFSupportFlags)
+		if ((HPSATMF_IOACCEL_ENABLED & h->TMFSupportFlags) ||
+			dev->physical_device)
 			return hpsa_send_abort_ioaccel2(h, abort,
 						reply_queue);
 		else
-			return hpsa_send_reset_as_abort_ioaccel2(h, scsi3addr,
+			return hpsa_send_reset_as_abort_ioaccel2(h,
+							dev->scsi3addr,
 							abort, reply_queue);
 	}
-	return hpsa_send_abort(h, scsi3addr, abort, reply_queue);
+	return hpsa_send_abort(h, dev->scsi3addr, abort, reply_queue);
 }
 
 /* Find out which reply queue a command was meant to return on */
@@ -5989,7 +5993,7 @@ static int hpsa_eh_abort_handler(struct scsi_cmnd *sc)
 		cmd_free(h, abort);
 		return FAILED;
 	}
-	rc = hpsa_send_abort_both_ways(h, dev->scsi3addr, abort, reply_queue);
+	rc = hpsa_send_abort_both_ways(h, dev, abort, reply_queue);
 	atomic_inc(&h->abort_cmds_available);
 	wake_up_all(&h->abort_cmd_wait_queue);
 	if (rc != 0) {
diff --git a/drivers/scsi/hpsa.h b/drivers/scsi/hpsa.h
index fdd39fc0b199..d06bb7417e36 100644
--- a/drivers/scsi/hpsa.h
+++ b/drivers/scsi/hpsa.h
@@ -1,5 +1,6 @@
 /*
  *    Disk Array driver for HP Smart Array SAS controllers
+ *    Copyright 2016 Microsemi Corporation
  *    Copyright 2014-2015 PMC-Sierra, Inc.
  *    Copyright 2000,2009-2015 Hewlett-Packard Development Company, L.P.
  *
@@ -12,7 +13,7 @@
  *    MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
  *    NON INFRINGEMENT.  See the GNU General Public License for more details.
  *
- *    Questions/Comments/Bugfixes to storagedev@pmcs.com
+ *    Questions/Comments/Bugfixes to esc.storagedev@microsemi.com
  *
  */
 #ifndef HPSA_H
diff --git a/drivers/scsi/hpsa_cmd.h b/drivers/scsi/hpsa_cmd.h
index 6a919ada96b3..a5be153d92d4 100644
--- a/drivers/scsi/hpsa_cmd.h
+++ b/drivers/scsi/hpsa_cmd.h
@@ -1,5 +1,6 @@
 /*
  *    Disk Array driver for HP Smart Array SAS controllers
+ *    Copyright 2016 Microsemi Corporation
  *    Copyright 2014-2015 PMC-Sierra, Inc.
  *    Copyright 2000,2009-2015 Hewlett-Packard Development Company, L.P.
  *
@@ -12,7 +13,7 @@
  *    MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
  *    NON INFRINGEMENT.  See the GNU General Public License for more details.
  *
- *    Questions/Comments/Bugfixes to storagedev@pmcs.com
+ *    Questions/Comments/Bugfixes to esc.storagedev@microsemi.com
  *
  */
 #ifndef HPSA_CMD_H
@@ -289,7 +290,7 @@ struct SenseSubsystem_info {
 #define BMIC_IDENTIFY_CONTROLLER 0x11
 #define BMIC_SET_DIAG_OPTIONS 0xF4
 #define BMIC_SENSE_DIAG_OPTIONS 0xF5
-#define HPSA_DIAG_OPTS_DISABLE_RLD_CACHING 0x40000000
+#define HPSA_DIAG_OPTS_DISABLE_RLD_CACHING 0x80000000
 #define BMIC_SENSE_SUBSYSTEM_INFORMATION 0x66
 #define BMIC_SENSE_STORAGE_BOX_PARAMS 0x65
 
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 6aa317c303e2..fc523c3e5019 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -2636,7 +2636,8 @@ static void ibmvfc_handle_async(struct ibmvfc_async_crq *crq,
 	struct ibmvfc_target *tgt;
 
 	ibmvfc_log(vhost, desc->log_level, "%s event received. scsi_id: %llx, wwpn: %llx,"
-		   " node_name: %llx%s\n", desc->desc, crq->scsi_id, crq->wwpn, crq->node_name,
+		   " node_name: %llx%s\n", desc->desc, be64_to_cpu(crq->scsi_id),
+		   be64_to_cpu(crq->wwpn), be64_to_cpu(crq->node_name),
 		   ibmvfc_get_link_state(crq->link_state));
 
 	switch (be64_to_cpu(crq->event)) {
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index adfef9db6f1e..d9534ee6ef52 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -182,7 +182,7 @@ static struct viosrp_crq *crq_queue_next_crq(struct crq_queue *queue)
 
 	spin_lock_irqsave(&queue->lock, flags);
 	crq = &queue->msgs[queue->cur];
-	if (crq->valid & 0x80) {
+	if (crq->valid != VIOSRP_CRQ_FREE) {
 		if (++queue->cur == queue->size)
 			queue->cur = 0;
 
@@ -231,7 +231,7 @@ static void ibmvscsi_task(void *data)
 		/* Pull all the valid messages off the CRQ */
 		while ((crq = crq_queue_next_crq(&hostdata->queue)) != NULL) {
 			ibmvscsi_handle_crq(crq, hostdata);
-			crq->valid = 0x00;
+			crq->valid = VIOSRP_CRQ_FREE;
 		}
 
 		vio_enable_interrupts(vdev);
@@ -239,7 +239,7 @@ static void ibmvscsi_task(void *data)
 		if (crq != NULL) {
 			vio_disable_interrupts(vdev);
 			ibmvscsi_handle_crq(crq, hostdata);
-			crq->valid = 0x00;
+			crq->valid = VIOSRP_CRQ_FREE;
 		} else {
 			done = 1;
 		}
@@ -248,25 +248,23 @@ static void ibmvscsi_task(void *data)
 
 static void gather_partition_info(void)
 {
-	struct device_node *rootdn;
-
 	const char *ppartition_name;
 	const __be32 *p_number_ptr;
 
 	/* Retrieve information about this partition */
-	rootdn = of_find_node_by_path("/");
-	if (!rootdn) {
+	if (!of_root)
 		return;
-	}
 
-	ppartition_name = of_get_property(rootdn, "ibm,partition-name", NULL);
+	of_node_get(of_root);
+
+	ppartition_name = of_get_property(of_root, "ibm,partition-name", NULL);
 	if (ppartition_name)
 		strncpy(partition_name, ppartition_name,
 				sizeof(partition_name));
-	p_number_ptr = of_get_property(rootdn, "ibm,partition-no", NULL);
+	p_number_ptr = of_get_property(of_root, "ibm,partition-no", NULL);
 	if (p_number_ptr)
 		partition_number = of_read_number(p_number_ptr, 1);
-	of_node_put(rootdn);
+	of_node_put(of_root);
 }
 
 static void set_adapter_info(struct ibmvscsi_host_data *hostdata)
@@ -283,8 +281,8 @@ static void set_adapter_info(struct ibmvscsi_host_data *hostdata)
 	hostdata->madapter_info.partition_number =
 					cpu_to_be32(partition_number);
 
-	hostdata->madapter_info.mad_version = cpu_to_be32(1);
-	hostdata->madapter_info.os_type = cpu_to_be32(2);
+	hostdata->madapter_info.mad_version = cpu_to_be32(SRP_MAD_VERSION_1);
+	hostdata->madapter_info.os_type = cpu_to_be32(SRP_MAD_OS_LINUX);
 }
 
 /**
@@ -316,7 +314,7 @@ static int ibmvscsi_reset_crq_queue(struct crq_queue *queue,
 	rc = plpar_hcall_norets(H_REG_CRQ,
 				vdev->unit_address,
 				queue->msg_token, PAGE_SIZE);
-	if (rc == 2) {
+	if (rc == H_CLOSED) {
 		/* Adapter is good, but other end is not ready */
 		dev_warn(hostdata->dev, "Partner adapter not ready\n");
 	} else if (rc != 0) {
@@ -366,7 +364,7 @@ static int ibmvscsi_init_crq_queue(struct crq_queue *queue,
 		rc = ibmvscsi_reset_crq_queue(queue,
 					      hostdata);
 
-	if (rc == 2) {
+	if (rc == H_CLOSED) {
 		/* Adapter is good, but other end is not ready */
 		dev_warn(hostdata->dev, "Partner adapter not ready\n");
 		retrc = 0;
@@ -474,7 +472,7 @@ static int initialize_event_pool(struct event_pool *pool,
 		struct srp_event_struct *evt = &pool->events[i];
 		memset(&evt->crq, 0x00, sizeof(evt->crq));
 		atomic_set(&evt->free, 1);
-		evt->crq.valid = 0x80;
+		evt->crq.valid = VIOSRP_CRQ_CMD_RSP;
 		evt->crq.IU_length = cpu_to_be16(sizeof(*evt->xfer_iu));
 		evt->crq.IU_data_ptr = cpu_to_be64(pool->iu_token +
 			sizeof(*evt->xfer_iu) * i);
@@ -1398,7 +1396,7 @@ static void adapter_info_rsp(struct srp_event_struct *evt_struct)
 			hostdata->host->max_sectors = 
 				be32_to_cpu(hostdata->madapter_info.port_max_txu[0]) >> 9;
 		
-		if (be32_to_cpu(hostdata->madapter_info.os_type) == 3 &&
+		if (be32_to_cpu(hostdata->madapter_info.os_type) == SRP_MAD_OS_AIX &&
 		    strcmp(hostdata->madapter_info.srp_version, "1.6a") <= 0) {
 			dev_err(hostdata->dev, "host (Ver. %s) doesn't support large transfers\n",
 				hostdata->madapter_info.srp_version);
@@ -1407,7 +1405,7 @@ static void adapter_info_rsp(struct srp_event_struct *evt_struct)
 			hostdata->host->sg_tablesize = MAX_INDIRECT_BUFS;
 		}
 
-		if (be32_to_cpu(hostdata->madapter_info.os_type) == 3) {
+		if (be32_to_cpu(hostdata->madapter_info.os_type) == SRP_MAD_OS_AIX) {
 			enable_fast_fail(hostdata);
 			return;
 		}
@@ -1767,9 +1765,9 @@ static void ibmvscsi_handle_crq(struct viosrp_crq *crq,
 	struct srp_event_struct *evt_struct =
 			(__force struct srp_event_struct *)crq->IU_data_ptr;
 	switch (crq->valid) {
-	case 0xC0:		/* initialization */
+	case VIOSRP_CRQ_INIT_RSP:		/* initialization */
 		switch (crq->format) {
-		case 0x01:	/* Initialization message */
+		case VIOSRP_CRQ_INIT:	/* Initialization message */
 			dev_info(hostdata->dev, "partner initialized\n");
 			/* Send back a response */
 			rc = ibmvscsi_send_crq(hostdata, 0xC002000000000000LL, 0);
@@ -1781,7 +1779,7 @@ static void ibmvscsi_handle_crq(struct viosrp_crq *crq,
 			}
 
 			break;
-		case 0x02:	/* Initialization response */
+		case VIOSRP_CRQ_INIT_COMPLETE:	/* Initialization response */
 			dev_info(hostdata->dev, "partner initialization complete\n");
 
 			/* Now login */
@@ -1791,7 +1789,7 @@ static void ibmvscsi_handle_crq(struct viosrp_crq *crq,
 			dev_err(hostdata->dev, "unknown crq message type: %d\n", crq->format);
 		}
 		return;
-	case 0xFF:	/* Hypervisor telling us the connection is closed */
+	case VIOSRP_CRQ_XPORT_EVENT:	/* Hypervisor telling us the connection is closed */
 		scsi_block_requests(hostdata->host);
 		atomic_set(&hostdata->request_limit, 0);
 		if (crq->format == 0x06) {
@@ -1807,7 +1805,7 @@ static void ibmvscsi_handle_crq(struct viosrp_crq *crq,
 			ibmvscsi_reset_host(hostdata);
 		}
 		return;
-	case 0x80:		/* real payload */
+	case VIOSRP_CRQ_CMD_RSP:		/* real payload */
 		break;
 	default:
 		dev_err(hostdata->dev, "got an invalid message type 0x%02x\n",
@@ -1855,62 +1853,6 @@ static void ibmvscsi_handle_crq(struct viosrp_crq *crq,
 }
 
 /**
- * ibmvscsi_get_host_config: Send the command to the server to get host
- * configuration data.  The data is opaque to us.
- */
-static int ibmvscsi_do_host_config(struct ibmvscsi_host_data *hostdata,
-				   unsigned char *buffer, int length)
-{
-	struct viosrp_host_config *host_config;
-	struct srp_event_struct *evt_struct;
-	unsigned long flags;
-	dma_addr_t addr;
-	int rc;
-
-	evt_struct = get_event_struct(&hostdata->pool);
-	if (!evt_struct) {
-		dev_err(hostdata->dev, "couldn't allocate event for HOST_CONFIG!\n");
-		return -1;
-	}
-
-	init_event_struct(evt_struct,
-			  sync_completion,
-			  VIOSRP_MAD_FORMAT,
-			  info_timeout);
-
-	host_config = &evt_struct->iu.mad.host_config;
-
-	/* The transport length field is only 16-bit */
-	length = min(0xffff, length);
-
-	/* Set up a lun reset SRP command */
-	memset(host_config, 0x00, sizeof(*host_config));
-	host_config->common.type = cpu_to_be32(VIOSRP_HOST_CONFIG_TYPE);
-	host_config->common.length = cpu_to_be16(length);
-	addr = dma_map_single(hostdata->dev, buffer, length, DMA_BIDIRECTIONAL);
-
-	if (dma_mapping_error(hostdata->dev, addr)) {
-		if (!firmware_has_feature(FW_FEATURE_CMO))
-			dev_err(hostdata->dev,
-			        "dma_mapping error getting host config\n");
-		free_event_struct(&hostdata->pool, evt_struct);
-		return -1;
-	}
-
-	host_config->buffer = cpu_to_be64(addr);
-
-	init_completion(&evt_struct->comp);
-	spin_lock_irqsave(hostdata->host->host_lock, flags);
-	rc = ibmvscsi_send_srp_event(evt_struct, hostdata, info_timeout * 2);
-	spin_unlock_irqrestore(hostdata->host->host_lock, flags);
-	if (rc == 0)
-		wait_for_completion(&evt_struct->comp);
-	dma_unmap_single(hostdata->dev, addr, length, DMA_BIDIRECTIONAL);
-
-	return rc;
-}
-
-/**
  * ibmvscsi_slave_configure: Set the "allow_restart" flag for each disk.
  * @sdev:	struct scsi_device device to configure
  *
@@ -2041,7 +1983,7 @@ static ssize_t show_host_partition_number(struct device *dev,
 	int len;
 
 	len = snprintf(buf, PAGE_SIZE, "%d\n",
-		       hostdata->madapter_info.partition_number);
+		       be32_to_cpu(hostdata->madapter_info.partition_number));
 	return len;
 }
 
@@ -2061,7 +2003,7 @@ static ssize_t show_host_mad_version(struct device *dev,
 	int len;
 
 	len = snprintf(buf, PAGE_SIZE, "%d\n",
-		       hostdata->madapter_info.mad_version);
+		       be32_to_cpu(hostdata->madapter_info.mad_version));
 	return len;
 }
 
@@ -2080,7 +2022,8 @@ static ssize_t show_host_os_type(struct device *dev,
 	struct ibmvscsi_host_data *hostdata = shost_priv(shost);
 	int len;
 
-	len = snprintf(buf, PAGE_SIZE, "%d\n", hostdata->madapter_info.os_type);
+	len = snprintf(buf, PAGE_SIZE, "%d\n",
+		       be32_to_cpu(hostdata->madapter_info.os_type));
 	return len;
 }
 
@@ -2095,21 +2038,14 @@ static struct device_attribute ibmvscsi_host_os_type = {
 static ssize_t show_host_config(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	struct Scsi_Host *shost = class_to_shost(dev);
-	struct ibmvscsi_host_data *hostdata = shost_priv(shost);
-
-	/* returns null-terminated host config data */
-	if (ibmvscsi_do_host_config(hostdata, buf, PAGE_SIZE) == 0)
-		return strlen(buf);
-	else
-		return 0;
+	return 0;
 }
 
 static struct device_attribute ibmvscsi_host_config = {
 	.attr = {
-		 .name = "config",
-		 .mode = S_IRUGO,
-		 },
+		.name = "config",
+		.mode = S_IRUGO,
+		},
 	.show = show_host_config,
 };
 
diff --git a/drivers/scsi/ibmvscsi/viosrp.h b/drivers/scsi/ibmvscsi/viosrp.h
index 116243087622..c1ab8a4c3161 100644
--- a/drivers/scsi/ibmvscsi/viosrp.h
+++ b/drivers/scsi/ibmvscsi/viosrp.h
@@ -51,13 +51,25 @@ union srp_iu {
 	u8 reserved[SRP_MAX_IU_LEN];
 };
 
+enum viosrp_crq_headers {
+	VIOSRP_CRQ_FREE = 0x00,
+	VIOSRP_CRQ_CMD_RSP = 0x80,
+	VIOSRP_CRQ_INIT_RSP = 0xC0,
+	VIOSRP_CRQ_XPORT_EVENT = 0xFF
+};
+
+enum viosrp_crq_init_formats {
+	VIOSRP_CRQ_INIT = 0x01,
+	VIOSRP_CRQ_INIT_COMPLETE = 0x02
+};
+
 enum viosrp_crq_formats {
 	VIOSRP_SRP_FORMAT = 0x01,
 	VIOSRP_MAD_FORMAT = 0x02,
 	VIOSRP_OS400_FORMAT = 0x03,
 	VIOSRP_AIX_FORMAT = 0x04,
-	VIOSRP_LINUX_FORMAT = 0x06,
-	VIOSRP_INLINE_FORMAT = 0x07
+	VIOSRP_LINUX_FORMAT = 0x05,
+	VIOSRP_INLINE_FORMAT = 0x06
 };
 
 enum viosrp_crq_status {
@@ -87,7 +99,6 @@ enum viosrp_mad_types {
 	VIOSRP_EMPTY_IU_TYPE = 0x01,
 	VIOSRP_ERROR_LOG_TYPE = 0x02,
 	VIOSRP_ADAPTER_INFO_TYPE = 0x03,
-	VIOSRP_HOST_CONFIG_TYPE = 0x04,
 	VIOSRP_CAPABILITIES_TYPE = 0x05,
 	VIOSRP_ENABLE_FAST_FAIL = 0x08,
 };
@@ -153,11 +164,6 @@ struct viosrp_adapter_info {
 	__be64 buffer;
 };
 
-struct viosrp_host_config {
-	struct mad_common common;
-	__be64 buffer;
-};
-
 struct viosrp_fast_fail {
 	struct mad_common common;
 };
@@ -195,7 +201,6 @@ union mad_iu {
 	struct viosrp_empty_iu empty_iu;
 	struct viosrp_error_log error_log;
 	struct viosrp_adapter_info adapter_info;
-	struct viosrp_host_config host_config;
 	struct viosrp_fast_fail fast_fail;
 	struct viosrp_capabilities capabilities;
 };
@@ -209,7 +214,10 @@ struct mad_adapter_info_data {
 	char srp_version[8];
 	char partition_name[96];
 	__be32 partition_number;
+#define SRP_MAD_VERSION_1 1
 	__be32 mad_version;
+#define SRP_MAD_OS_LINUX 2
+#define SRP_MAD_OS_AIX 3
 	__be32 os_type;
 	__be32 port_max_txu[8];	/* per-port maximum transfer */
 };
diff --git a/drivers/scsi/imm.c b/drivers/scsi/imm.c
index f8b88fa78e62..9164ce1249c1 100644
--- a/drivers/scsi/imm.c
+++ b/drivers/scsi/imm.c
@@ -77,9 +77,10 @@ static void imm_wakeup(void *ref)
 
 	spin_lock_irqsave(&arbitration_lock, flags);
 	if (dev->wanted) {
-		parport_claim(dev->dev);
-		got_it(dev);
-		dev->wanted = 0;
+		if (parport_claim(dev->dev) == 0) {
+			got_it(dev);
+			dev->wanted = 0;
+		}
 	}
 	spin_unlock_irqrestore(&arbitration_lock, flags);
 }
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 3b3e0998fa6e..d6a691e27d33 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -4002,6 +4002,7 @@ static ssize_t ipr_store_update_fw(struct device *dev,
 	struct ipr_sglist *sglist;
 	char fname[100];
 	char *src;
+	char *endline;
 	int result, dnld_size;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -4009,6 +4010,10 @@ static ssize_t ipr_store_update_fw(struct device *dev,
 
 	snprintf(fname, sizeof(fname), "%s", buf);
 
+	endline = strchr(fname, '\n');
+	if (endline)
+		*endline = '\0';
+
 	if (request_firmware(&fw_entry, fname, &ioa_cfg->pdev->dev)) {
 		dev_err(&ioa_cfg->pdev->dev, "Firmware file %s not found\n", fname);
 		return -EIO;
diff --git a/drivers/scsi/iscsi_boot_sysfs.c b/drivers/scsi/iscsi_boot_sysfs.c
index 680bf6f0ce76..8f0ea97cf31f 100644
--- a/drivers/scsi/iscsi_boot_sysfs.c
+++ b/drivers/scsi/iscsi_boot_sysfs.c
@@ -166,6 +166,7 @@ static struct attribute_group iscsi_boot_target_attr_group = {
 iscsi_boot_rd_attr(eth_index, index, ISCSI_BOOT_ETH_INDEX);
 iscsi_boot_rd_attr(eth_flags, flags, ISCSI_BOOT_ETH_FLAGS);
 iscsi_boot_rd_attr(eth_ip, ip-addr, ISCSI_BOOT_ETH_IP_ADDR);
+iscsi_boot_rd_attr(eth_prefix, prefix-len, ISCSI_BOOT_ETH_PREFIX_LEN);
 iscsi_boot_rd_attr(eth_subnet, subnet-mask, ISCSI_BOOT_ETH_SUBNET_MASK);
 iscsi_boot_rd_attr(eth_origin, origin, ISCSI_BOOT_ETH_ORIGIN);
 iscsi_boot_rd_attr(eth_gateway, gateway, ISCSI_BOOT_ETH_GATEWAY);
@@ -181,6 +182,7 @@ static struct attribute *ethernet_attrs[] = {
 	&iscsi_boot_attr_eth_index.attr,
 	&iscsi_boot_attr_eth_flags.attr,
 	&iscsi_boot_attr_eth_ip.attr,
+	&iscsi_boot_attr_eth_prefix.attr,
 	&iscsi_boot_attr_eth_subnet.attr,
 	&iscsi_boot_attr_eth_origin.attr,
 	&iscsi_boot_attr_eth_gateway.attr,
@@ -208,6 +210,9 @@ static umode_t iscsi_boot_eth_attr_is_visible(struct kobject *kobj,
 	else if (attr ==  &iscsi_boot_attr_eth_ip.attr)
 		return boot_kobj->is_visible(boot_kobj->data,
 					     ISCSI_BOOT_ETH_IP_ADDR);
+	else if (attr ==  &iscsi_boot_attr_eth_prefix.attr)
+		return boot_kobj->is_visible(boot_kobj->data,
+					     ISCSI_BOOT_ETH_PREFIX_LEN);
 	else if (attr ==  &iscsi_boot_attr_eth_subnet.attr)
 		return boot_kobj->is_visible(boot_kobj->data,
 					     ISCSI_BOOT_ETH_SUBNET_MASK);
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 0b8af186e707..2e4c82f8329c 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -26,12 +26,12 @@
  *	Zhenyu Wang
  */
 
+#include <crypto/hash.h>
 #include <linux/types.h>
 #include <linux/inet.h>
 #include <linux/slab.h>
 #include <linux/file.h>
 #include <linux/blkdev.h>
-#include <linux/crypto.h>
 #include <linux/delay.h>
 #include <linux/kfifo.h>
 #include <linux/scatterlist.h>
@@ -428,7 +428,7 @@ static void iscsi_sw_tcp_send_hdr_prep(struct iscsi_conn *conn, void *hdr,
 	 * sufficient room.
 	 */
 	if (conn->hdrdgst_en) {
-		iscsi_tcp_dgst_header(&tcp_sw_conn->tx_hash, hdr, hdrlen,
+		iscsi_tcp_dgst_header(tcp_sw_conn->tx_hash, hdr, hdrlen,
 				      hdr + hdrlen);
 		hdrlen += ISCSI_DIGEST_SIZE;
 	}
@@ -454,7 +454,7 @@ iscsi_sw_tcp_send_data_prep(struct iscsi_conn *conn, struct scatterlist *sg,
 {
 	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
 	struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
-	struct hash_desc *tx_hash = NULL;
+	struct ahash_request *tx_hash = NULL;
 	unsigned int hdr_spec_len;
 
 	ISCSI_SW_TCP_DBG(conn, "offset=%d, datalen=%d %s\n", offset, len,
@@ -467,7 +467,7 @@ iscsi_sw_tcp_send_data_prep(struct iscsi_conn *conn, struct scatterlist *sg,
 	WARN_ON(iscsi_padded(len) != iscsi_padded(hdr_spec_len));
 
 	if (conn->datadgst_en)
-		tx_hash = &tcp_sw_conn->tx_hash;
+		tx_hash = tcp_sw_conn->tx_hash;
 
 	return iscsi_segment_seek_sg(&tcp_sw_conn->out.data_segment,
 				     sg, count, offset, len,
@@ -480,7 +480,7 @@ iscsi_sw_tcp_send_linear_data_prep(struct iscsi_conn *conn, void *data,
 {
 	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
 	struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
-	struct hash_desc *tx_hash = NULL;
+	struct ahash_request *tx_hash = NULL;
 	unsigned int hdr_spec_len;
 
 	ISCSI_SW_TCP_DBG(conn, "datalen=%zd %s\n", len, conn->datadgst_en ?
@@ -492,7 +492,7 @@ iscsi_sw_tcp_send_linear_data_prep(struct iscsi_conn *conn, void *data,
 	WARN_ON(iscsi_padded(len) != iscsi_padded(hdr_spec_len));
 
 	if (conn->datadgst_en)
-		tx_hash = &tcp_sw_conn->tx_hash;
+		tx_hash = tcp_sw_conn->tx_hash;
 
 	iscsi_segment_init_linear(&tcp_sw_conn->out.data_segment,
 				data, len, NULL, tx_hash);
@@ -543,6 +543,7 @@ iscsi_sw_tcp_conn_create(struct iscsi_cls_session *cls_session,
 	struct iscsi_cls_conn *cls_conn;
 	struct iscsi_tcp_conn *tcp_conn;
 	struct iscsi_sw_tcp_conn *tcp_sw_conn;
+	struct crypto_ahash *tfm;
 
 	cls_conn = iscsi_tcp_conn_setup(cls_session, sizeof(*tcp_sw_conn),
 					conn_idx);
@@ -552,23 +553,28 @@ iscsi_sw_tcp_conn_create(struct iscsi_cls_session *cls_session,
 	tcp_conn = conn->dd_data;
 	tcp_sw_conn = tcp_conn->dd_data;
 
-	tcp_sw_conn->tx_hash.tfm = crypto_alloc_hash("crc32c", 0,
-						     CRYPTO_ALG_ASYNC);
-	tcp_sw_conn->tx_hash.flags = 0;
-	if (IS_ERR(tcp_sw_conn->tx_hash.tfm))
+	tfm = crypto_alloc_ahash("crc32c", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm))
 		goto free_conn;
 
-	tcp_sw_conn->rx_hash.tfm = crypto_alloc_hash("crc32c", 0,
-						     CRYPTO_ALG_ASYNC);
-	tcp_sw_conn->rx_hash.flags = 0;
-	if (IS_ERR(tcp_sw_conn->rx_hash.tfm))
-		goto free_tx_tfm;
-	tcp_conn->rx_hash = &tcp_sw_conn->rx_hash;
+	tcp_sw_conn->tx_hash = ahash_request_alloc(tfm, GFP_KERNEL);
+	if (!tcp_sw_conn->tx_hash)
+		goto free_tfm;
+	ahash_request_set_callback(tcp_sw_conn->tx_hash, 0, NULL, NULL);
+
+	tcp_sw_conn->rx_hash = ahash_request_alloc(tfm, GFP_KERNEL);
+	if (!tcp_sw_conn->rx_hash)
+		goto free_tx_hash;
+	ahash_request_set_callback(tcp_sw_conn->rx_hash, 0, NULL, NULL);
+
+	tcp_conn->rx_hash = tcp_sw_conn->rx_hash;
 
 	return cls_conn;
 
-free_tx_tfm:
-	crypto_free_hash(tcp_sw_conn->tx_hash.tfm);
+free_tx_hash:
+	ahash_request_free(tcp_sw_conn->tx_hash);
+free_tfm:
+	crypto_free_ahash(tfm);
 free_conn:
 	iscsi_conn_printk(KERN_ERR, conn,
 			  "Could not create connection due to crc32c "
@@ -607,10 +613,14 @@ static void iscsi_sw_tcp_conn_destroy(struct iscsi_cls_conn *cls_conn)
 
 	iscsi_sw_tcp_release_conn(conn);
 
-	if (tcp_sw_conn->tx_hash.tfm)
-		crypto_free_hash(tcp_sw_conn->tx_hash.tfm);
-	if (tcp_sw_conn->rx_hash.tfm)
-		crypto_free_hash(tcp_sw_conn->rx_hash.tfm);
+	ahash_request_free(tcp_sw_conn->rx_hash);
+	if (tcp_sw_conn->tx_hash) {
+		struct crypto_ahash *tfm;
+
+		tfm = crypto_ahash_reqtfm(tcp_sw_conn->tx_hash);
+		ahash_request_free(tcp_sw_conn->tx_hash);
+		crypto_free_ahash(tfm);
+	}
 
 	iscsi_tcp_conn_teardown(cls_conn);
 }
diff --git a/drivers/scsi/iscsi_tcp.h b/drivers/scsi/iscsi_tcp.h
index f42ecb238af5..06d42d00a323 100644
--- a/drivers/scsi/iscsi_tcp.h
+++ b/drivers/scsi/iscsi_tcp.h
@@ -45,8 +45,8 @@ struct iscsi_sw_tcp_conn {
 	void			(*old_write_space)(struct sock *);
 
 	/* data and header digests */
-	struct hash_desc	tx_hash;	/* CRC32C (Tx) */
-	struct hash_desc	rx_hash;	/* CRC32C (Rx) */
+	struct ahash_request	*tx_hash;	/* CRC32C (Tx) */
+	struct ahash_request	*rx_hash;	/* CRC32C (Rx) */
 
 	/* MIB custom statistics */
 	uint32_t		sendpage_failures_cnt;
diff --git a/drivers/scsi/libiscsi_tcp.c b/drivers/scsi/libiscsi_tcp.c
index 60cb6dc3c6f0..63a1d69ff515 100644
--- a/drivers/scsi/libiscsi_tcp.c
+++ b/drivers/scsi/libiscsi_tcp.c
@@ -26,13 +26,13 @@
  *	Zhenyu Wang
  */
 
+#include <crypto/hash.h>
 #include <linux/types.h>
 #include <linux/list.h>
 #include <linux/inet.h>
 #include <linux/slab.h>
 #include <linux/file.h>
 #include <linux/blkdev.h>
-#include <linux/crypto.h>
 #include <linux/delay.h>
 #include <linux/kfifo.h>
 #include <linux/scatterlist.h>
@@ -214,7 +214,8 @@ int iscsi_tcp_segment_done(struct iscsi_tcp_conn *tcp_conn,
 		} else
 			sg_init_one(&sg, segment->data + segment->copied,
 				    copied);
-		crypto_hash_update(segment->hash, &sg, copied);
+		ahash_request_set_crypt(segment->hash, &sg, NULL, copied);
+		crypto_ahash_update(segment->hash);
 	}
 
 	segment->copied += copied;
@@ -260,7 +261,9 @@ int iscsi_tcp_segment_done(struct iscsi_tcp_conn *tcp_conn,
 	 * is completely handled in hdr done function.
 	 */
 	if (segment->hash) {
-		crypto_hash_final(segment->hash, segment->digest);
+		ahash_request_set_crypt(segment->hash, NULL,
+					segment->digest, 0);
+		crypto_ahash_final(segment->hash);
 		iscsi_tcp_segment_splice_digest(segment,
 				 recv ? segment->recv_digest : segment->digest);
 		return 0;
@@ -310,13 +313,14 @@ iscsi_tcp_segment_recv(struct iscsi_tcp_conn *tcp_conn,
 }
 
 inline void
-iscsi_tcp_dgst_header(struct hash_desc *hash, const void *hdr, size_t hdrlen,
-		      unsigned char digest[ISCSI_DIGEST_SIZE])
+iscsi_tcp_dgst_header(struct ahash_request *hash, const void *hdr,
+		      size_t hdrlen, unsigned char digest[ISCSI_DIGEST_SIZE])
 {
 	struct scatterlist sg;
 
 	sg_init_one(&sg, hdr, hdrlen);
-	crypto_hash_digest(hash, &sg, hdrlen, digest);
+	ahash_request_set_crypt(hash, &sg, digest, hdrlen);
+	crypto_ahash_digest(hash);
 }
 EXPORT_SYMBOL_GPL(iscsi_tcp_dgst_header);
 
@@ -341,7 +345,7 @@ iscsi_tcp_dgst_verify(struct iscsi_tcp_conn *tcp_conn,
  */
 static inline void
 __iscsi_segment_init(struct iscsi_segment *segment, size_t size,
-		     iscsi_segment_done_fn_t *done, struct hash_desc *hash)
+		     iscsi_segment_done_fn_t *done, struct ahash_request *hash)
 {
 	memset(segment, 0, sizeof(*segment));
 	segment->total_size = size;
@@ -349,14 +353,14 @@ __iscsi_segment_init(struct iscsi_segment *segment, size_t size,
 
 	if (hash) {
 		segment->hash = hash;
-		crypto_hash_init(hash);
+		crypto_ahash_init(hash);
 	}
 }
 
 inline void
 iscsi_segment_init_linear(struct iscsi_segment *segment, void *data,
 			  size_t size, iscsi_segment_done_fn_t *done,
-			  struct hash_desc *hash)
+			  struct ahash_request *hash)
 {
 	__iscsi_segment_init(segment, size, done, hash);
 	segment->data = data;
@@ -368,7 +372,8 @@ inline int
 iscsi_segment_seek_sg(struct iscsi_segment *segment,
 		      struct scatterlist *sg_list, unsigned int sg_count,
 		      unsigned int offset, size_t size,
-		      iscsi_segment_done_fn_t *done, struct hash_desc *hash)
+		      iscsi_segment_done_fn_t *done,
+		      struct ahash_request *hash)
 {
 	struct scatterlist *sg;
 	unsigned int i;
@@ -431,7 +436,7 @@ static void
 iscsi_tcp_data_recv_prep(struct iscsi_tcp_conn *tcp_conn)
 {
 	struct iscsi_conn *conn = tcp_conn->iscsi_conn;
-	struct hash_desc *rx_hash = NULL;
+	struct ahash_request *rx_hash = NULL;
 
 	if (conn->datadgst_en &&
 	    !(conn->session->tt->caps & CAP_DIGEST_OFFLOAD))
@@ -686,7 +691,7 @@ iscsi_tcp_hdr_dissect(struct iscsi_conn *conn, struct iscsi_hdr *hdr)
 
 		if (tcp_conn->in.datalen) {
 			struct iscsi_tcp_task *tcp_task = task->dd_data;
-			struct hash_desc *rx_hash = NULL;
+			struct ahash_request *rx_hash = NULL;
 			struct scsi_data_buffer *sdb = scsi_in(task->sc);
 
 			/*
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index 25aa9b98d53a..a63542bac153 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -1054,11 +1054,11 @@ lpfc_debugfs_dif_err_write(struct file *file, const char __user *buf,
 {
 	struct dentry *dent = file->f_path.dentry;
 	struct lpfc_hba *phba = file->private_data;
-	char dstbuf[32];
+	char dstbuf[33];
 	uint64_t tmp = 0;
 	int size;
 
-	memset(dstbuf, 0, 32);
+	memset(dstbuf, 0, 33);
 	size = (nbytes < 32) ? nbytes : 32;
 	if (copy_from_user(dstbuf, buf, size))
 		return 0;
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index c37d72effbff..25b5dcd1a5c8 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -25,6 +25,7 @@
 #include <linux/pci.h>
 #include <linux/kthread.h>
 #include <linux/interrupt.h>
+#include <linux/lockdep.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_device.h>
@@ -1314,6 +1315,8 @@ __lpfc_update_fcf_record_pri(struct lpfc_hba *phba, uint16_t fcf_index,
 {
 	struct lpfc_fcf_pri *fcf_pri;
 
+	lockdep_assert_held(&phba->hbalock);
+
 	fcf_pri = &phba->fcf.fcf_pri[fcf_index];
 	fcf_pri->fcf_rec.fcf_index = fcf_index;
 	/* FCF record priority */
@@ -1398,6 +1401,8 @@ __lpfc_update_fcf_record(struct lpfc_hba *phba, struct lpfc_fcf_rec *fcf_rec,
 		       struct fcf_record *new_fcf_record, uint32_t addr_mode,
 		       uint16_t vlan_id, uint32_t flag)
 {
+	lockdep_assert_held(&phba->hbalock);
+
 	/* Copy the fields from the HBA's FCF record */
 	lpfc_copy_fcf_record(fcf_rec, new_fcf_record);
 	/* Update other fields of driver FCF record */
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 152b3c8a5428..3bd0be6277b3 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -4139,23 +4139,6 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 	/* The sdev is not guaranteed to be valid post scsi_done upcall. */
 	cmd->scsi_done(cmd);
 
-	if (phba->cfg_poll & ENABLE_FCP_RING_POLLING) {
-		spin_lock_irqsave(&phba->hbalock, flags);
-		lpfc_cmd->pCmd = NULL;
-		spin_unlock_irqrestore(&phba->hbalock, flags);
-
-		/*
-		 * If there is a thread waiting for command completion
-		 * wake up the thread.
-		 */
-		spin_lock_irqsave(shost->host_lock, flags);
-		if (lpfc_cmd->waitq)
-			wake_up(lpfc_cmd->waitq);
-		spin_unlock_irqrestore(shost->host_lock, flags);
-		lpfc_release_scsi_buf(phba, lpfc_cmd);
-		return;
-	}
-
 	spin_lock_irqsave(&phba->hbalock, flags);
 	lpfc_cmd->pCmd = NULL;
 	spin_unlock_irqrestore(&phba->hbalock, flags);
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 92dfd6a5178c..2207726b88ee 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -24,6 +24,7 @@
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
+#include <linux/lockdep.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
@@ -576,6 +577,8 @@ __lpfc_sli_get_iocbq(struct lpfc_hba *phba)
 	struct list_head *lpfc_iocb_list = &phba->lpfc_iocb_list;
 	struct lpfc_iocbq * iocbq = NULL;
 
+	lockdep_assert_held(&phba->hbalock);
+
 	list_remove_head(lpfc_iocb_list, iocbq, struct lpfc_iocbq, list);
 	if (iocbq)
 		phba->iocb_cnt++;
@@ -797,6 +800,7 @@ int
 lpfc_test_rrq_active(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp,
 			uint16_t  xritag)
 {
+	lockdep_assert_held(&phba->hbalock);
 	if (!ndlp)
 		return 0;
 	if (!ndlp->active_rrqs_xri_bitmap)
@@ -914,6 +918,8 @@ __lpfc_sli_get_sglq(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq)
 	struct lpfc_nodelist *ndlp;
 	int found = 0;
 
+	lockdep_assert_held(&phba->hbalock);
+
 	if (piocbq->iocb_flag &  LPFC_IO_FCP) {
 		lpfc_cmd = (struct lpfc_scsi_buf *) piocbq->context1;
 		ndlp = lpfc_cmd->rdata->pnode;
@@ -1003,6 +1009,8 @@ __lpfc_sli_release_iocbq_s4(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
 	unsigned long iflag = 0;
 	struct lpfc_sli_ring *pring = &phba->sli.ring[LPFC_ELS_RING];
 
+	lockdep_assert_held(&phba->hbalock);
+
 	if (iocbq->sli4_xritag == NO_XRI)
 		sglq = NULL;
 	else
@@ -1058,6 +1066,7 @@ __lpfc_sli_release_iocbq_s3(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
 {
 	size_t start_clean = offsetof(struct lpfc_iocbq, iocb);
 
+	lockdep_assert_held(&phba->hbalock);
 
 	/*
 	 * Clean all volatile data fields, preserve iotag and node struct.
@@ -1080,6 +1089,8 @@ __lpfc_sli_release_iocbq_s3(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
 static void
 __lpfc_sli_release_iocbq(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq)
 {
+	lockdep_assert_held(&phba->hbalock);
+
 	phba->__lpfc_sli_release_iocbq(phba, iocbq);
 	phba->iocb_cnt--;
 }
@@ -1310,6 +1321,8 @@ static int
 lpfc_sli_ringtxcmpl_put(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 			struct lpfc_iocbq *piocb)
 {
+	lockdep_assert_held(&phba->hbalock);
+
 	list_add_tail(&piocb->list, &pring->txcmplq);
 	piocb->iocb_flag |= LPFC_IO_ON_TXCMPLQ;
 
@@ -1344,6 +1357,8 @@ lpfc_sli_ringtx_get(struct lpfc_hba *phba, struct lpfc_sli_ring *pring)
 {
 	struct lpfc_iocbq *cmd_iocb;
 
+	lockdep_assert_held(&phba->hbalock);
+
 	list_remove_head((&pring->txq), cmd_iocb, struct lpfc_iocbq, list);
 	return cmd_iocb;
 }
@@ -1367,6 +1382,9 @@ lpfc_sli_next_iocb_slot (struct lpfc_hba *phba, struct lpfc_sli_ring *pring)
 {
 	struct lpfc_pgp *pgp = &phba->port_gp[pring->ringno];
 	uint32_t  max_cmd_idx = pring->sli.sli3.numCiocb;
+
+	lockdep_assert_held(&phba->hbalock);
+
 	if ((pring->sli.sli3.next_cmdidx == pring->sli.sli3.cmdidx) &&
 	   (++pring->sli.sli3.next_cmdidx >= max_cmd_idx))
 		pring->sli.sli3.next_cmdidx = 0;
@@ -1497,6 +1515,7 @@ static void
 lpfc_sli_submit_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		IOCB_t *iocb, struct lpfc_iocbq *nextiocb)
 {
+	lockdep_assert_held(&phba->hbalock);
 	/*
 	 * Set up an iotag
 	 */
@@ -1606,6 +1625,8 @@ lpfc_sli_resume_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring)
 	IOCB_t *iocb;
 	struct lpfc_iocbq *nextiocb;
 
+	lockdep_assert_held(&phba->hbalock);
+
 	/*
 	 * Check to see if:
 	 *  (a) there is anything on the txq to send
@@ -1647,6 +1668,8 @@ lpfc_sli_next_hbq_slot(struct lpfc_hba *phba, uint32_t hbqno)
 {
 	struct hbq_s *hbqp = &phba->hbqs[hbqno];
 
+	lockdep_assert_held(&phba->hbalock);
+
 	if (hbqp->next_hbqPutIdx == hbqp->hbqPutIdx &&
 	    ++hbqp->next_hbqPutIdx >= hbqp->entry_count)
 		hbqp->next_hbqPutIdx = 0;
@@ -1747,6 +1770,7 @@ static int
 lpfc_sli_hbq_to_firmware(struct lpfc_hba *phba, uint32_t hbqno,
 			 struct hbq_dmabuf *hbq_buf)
 {
+	lockdep_assert_held(&phba->hbalock);
 	return phba->lpfc_sli_hbq_to_firmware(phba, hbqno, hbq_buf);
 }
 
@@ -1768,6 +1792,7 @@ lpfc_sli_hbq_to_firmware_s3(struct lpfc_hba *phba, uint32_t hbqno,
 	struct lpfc_hbq_entry *hbqe;
 	dma_addr_t physaddr = hbq_buf->dbuf.phys;
 
+	lockdep_assert_held(&phba->hbalock);
 	/* Get next HBQ entry slot to use */
 	hbqe = lpfc_sli_next_hbq_slot(phba, hbqno);
 	if (hbqe) {
@@ -1808,6 +1833,7 @@ lpfc_sli_hbq_to_firmware_s4(struct lpfc_hba *phba, uint32_t hbqno,
 	struct lpfc_rqe hrqe;
 	struct lpfc_rqe drqe;
 
+	lockdep_assert_held(&phba->hbalock);
 	hrqe.address_lo = putPaddrLow(hbq_buf->hbuf.phys);
 	hrqe.address_hi = putPaddrHigh(hbq_buf->hbuf.phys);
 	drqe.address_lo = putPaddrLow(hbq_buf->dbuf.phys);
@@ -1986,6 +2012,8 @@ lpfc_sli_hbqbuf_find(struct lpfc_hba *phba, uint32_t tag)
 	struct hbq_dmabuf *hbq_buf;
 	uint32_t hbqno;
 
+	lockdep_assert_held(&phba->hbalock);
+
 	hbqno = tag >> 16;
 	if (hbqno >= LPFC_MAX_HBQS)
 		return NULL;
@@ -2647,6 +2675,7 @@ lpfc_sli_iocbq_lookup(struct lpfc_hba *phba,
 {
 	struct lpfc_iocbq *cmd_iocb = NULL;
 	uint16_t iotag;
+	lockdep_assert_held(&phba->hbalock);
 
 	iotag = prspiocb->iocb.ulpIoTag;
 
@@ -2685,6 +2714,7 @@ lpfc_sli_iocbq_lookup_by_tag(struct lpfc_hba *phba,
 {
 	struct lpfc_iocbq *cmd_iocb;
 
+	lockdep_assert_held(&phba->hbalock);
 	if (iotag != 0 && iotag <= phba->sli.last_iotag) {
 		cmd_iocb = phba->sli.iocbq_lookup[iotag];
 		if (cmd_iocb->iocb_flag & LPFC_IO_ON_TXCMPLQ) {
@@ -3799,6 +3829,8 @@ void lpfc_reset_barrier(struct lpfc_hba *phba)
 	int  i;
 	uint8_t hdrtype;
 
+	lockdep_assert_held(&phba->hbalock);
+
 	pci_read_config_byte(phba->pcidev, PCI_HEADER_TYPE, &hdrtype);
 	if (hdrtype != 0x80 ||
 	    (FC_JEDEC_ID(phba->vpd.rev.biuRev) != HELIOS_JEDEC_ID &&
@@ -7861,6 +7893,7 @@ void
 __lpfc_sli_ringtx_put(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		    struct lpfc_iocbq *piocb)
 {
+	lockdep_assert_held(&phba->hbalock);
 	/* Insert the caller's iocb in the txq tail for later processing. */
 	list_add_tail(&piocb->list, &pring->txq);
 }
@@ -7888,6 +7921,8 @@ lpfc_sli_next_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 {
 	struct lpfc_iocbq * nextiocb;
 
+	lockdep_assert_held(&phba->hbalock);
+
 	nextiocb = lpfc_sli_ringtx_get(phba, pring);
 	if (!nextiocb) {
 		nextiocb = *piocb;
@@ -7927,6 +7962,8 @@ __lpfc_sli_issue_iocb_s3(struct lpfc_hba *phba, uint32_t ring_number,
 	IOCB_t *iocb;
 	struct lpfc_sli_ring *pring = &phba->sli.ring[ring_number];
 
+	lockdep_assert_held(&phba->hbalock);
+
 	if (piocb->iocb_cmpl && (!piocb->vport) &&
 	   (piocb->iocb.ulpCommand != CMD_ABORT_XRI_CN) &&
 	   (piocb->iocb.ulpCommand != CMD_CLOSE_XRI_CN)) {
@@ -8642,6 +8679,8 @@ __lpfc_sli_issue_iocb_s4(struct lpfc_hba *phba, uint32_t ring_number,
 	struct lpfc_queue *wq;
 	struct lpfc_sli_ring *pring = &phba->sli.ring[ring_number];
 
+	lockdep_assert_held(&phba->hbalock);
+
 	if (piocb->sli4_xritag == NO_XRI) {
 		if (piocb->iocb.ulpCommand == CMD_ABORT_XRI_CN ||
 		    piocb->iocb.ulpCommand == CMD_CLOSE_XRI_CN)
@@ -9752,6 +9791,8 @@ lpfc_sli_abort_iotag_issue(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	int retval;
 	unsigned long iflags;
 
+	lockdep_assert_held(&phba->hbalock);
+
 	/*
 	 * There are certain command types we don't want to abort.  And we
 	 * don't want to abort commands that are already in the process of
@@ -9854,6 +9895,8 @@ lpfc_sli_issue_abort_iotag(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	int retval = IOCB_ERROR;
 	IOCB_t *icmd = NULL;
 
+	lockdep_assert_held(&phba->hbalock);
+
 	/*
 	 * There are certain command types we don't want to abort.  And we
 	 * don't want to abort commands that are already in the process of
diff --git a/drivers/scsi/mac53c94.c b/drivers/scsi/mac53c94.c
index 141226631429..a6682c508c4c 100644
--- a/drivers/scsi/mac53c94.c
+++ b/drivers/scsi/mac53c94.c
@@ -18,11 +18,11 @@
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/pci.h>
 #include <asm/dbdma.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
 #include <asm/prom.h>
-#include <asm/pci-bridge.h>
 #include <asm/macio.h>
 
 #include <scsi/scsi.h>
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index c0f7c8ce54aa..4484e63033a5 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -35,8 +35,8 @@
 /*
  * MegaRAID SAS Driver meta data
  */
-#define MEGASAS_VERSION				"06.808.16.00-rc1"
-#define MEGASAS_RELDATE				"Oct. 8, 2015"
+#define MEGASAS_VERSION				"06.810.09.00-rc1"
+#define MEGASAS_RELDATE				"Jan. 28, 2016"
 
 /*
  * Device IDs
@@ -152,6 +152,7 @@
 #define MFI_RESET_FLAGS				MFI_INIT_READY| \
 						MFI_INIT_MFIMODE| \
 						MFI_INIT_ABORT
+#define MPI2_IOCINIT_MSGFLAG_RDPQ_ARRAY_MODE    (0x01)
 
 /*
  * MFI frame flags
@@ -170,6 +171,7 @@
 
 /* Driver internal */
 #define DRV_DCMD_POLLED_MODE		0x1
+#define DRV_DCMD_SKIP_REFIRE		0x2
 
 /*
  * Definition for cmd_status
@@ -214,6 +216,7 @@
 
 #define MR_DCMD_CTRL_SET_CRASH_DUMP_PARAMS	0x01190100
 #define MR_DRIVER_SET_APP_CRASHDUMP_MODE	(0xF0010000 | 0x0600)
+#define MR_DCMD_PD_GET_INFO			0x02020000
 
 /*
  * Global functions
@@ -390,6 +393,7 @@ enum MR_EVT_ARGS {
 
 
 #define SGE_BUFFER_SIZE	4096
+#define MEGASAS_CLUSTER_ID_SIZE	16
 /*
  * define constants for device list query options
  */
@@ -434,6 +438,257 @@ enum MR_PD_STATE {
 	MR_PD_STATE_SYSTEM              = 0x40,
  };
 
+union MR_PD_REF {
+	struct {
+		u16	 deviceId;
+		u16	 seqNum;
+	} mrPdRef;
+	u32	 ref;
+};
+
+/*
+ * define the DDF Type bit structure
+ */
+union MR_PD_DDF_TYPE {
+	 struct {
+		union {
+			struct {
+#ifndef __BIG_ENDIAN_BITFIELD
+				 u16	 forcedPDGUID:1;
+				 u16	 inVD:1;
+				 u16	 isGlobalSpare:1;
+				 u16	 isSpare:1;
+				 u16	 isForeign:1;
+				 u16	 reserved:7;
+				 u16	 intf:4;
+#else
+				 u16	 intf:4;
+				 u16	 reserved:7;
+				 u16	 isForeign:1;
+				 u16	 isSpare:1;
+				 u16	 isGlobalSpare:1;
+				 u16	 inVD:1;
+				 u16	 forcedPDGUID:1;
+#endif
+			 } pdType;
+			 u16	 type;
+		 };
+		 u16	 reserved;
+	 } ddf;
+	 struct {
+		 u32	reserved;
+	 } nonDisk;
+	 u32	 type;
+} __packed;
+
+/*
+ * defines the progress structure
+ */
+union MR_PROGRESS {
+	struct  {
+		u16 progress;
+		union {
+			u16 elapsedSecs;
+			u16 elapsedSecsForLastPercent;
+		};
+	} mrProgress;
+	u32 w;
+} __packed;
+
+/*
+ * defines the physical drive progress structure
+ */
+struct MR_PD_PROGRESS {
+	struct {
+#ifndef MFI_BIG_ENDIAN
+		u32     rbld:1;
+		u32     patrol:1;
+		u32     clear:1;
+		u32     copyBack:1;
+		u32     erase:1;
+		u32     locate:1;
+		u32     reserved:26;
+#else
+		u32     reserved:26;
+		u32     locate:1;
+		u32     erase:1;
+		u32     copyBack:1;
+		u32     clear:1;
+		u32     patrol:1;
+		u32     rbld:1;
+#endif
+	} active;
+	union MR_PROGRESS     rbld;
+	union MR_PROGRESS     patrol;
+	union {
+		union MR_PROGRESS     clear;
+		union MR_PROGRESS     erase;
+	};
+
+	struct {
+#ifndef MFI_BIG_ENDIAN
+		u32     rbld:1;
+		u32     patrol:1;
+		u32     clear:1;
+		u32     copyBack:1;
+		u32     erase:1;
+		u32     reserved:27;
+#else
+		u32     reserved:27;
+		u32     erase:1;
+		u32     copyBack:1;
+		u32     clear:1;
+		u32     patrol:1;
+		u32     rbld:1;
+#endif
+	} pause;
+
+	union MR_PROGRESS     reserved[3];
+} __packed;
+
+struct  MR_PD_INFO {
+	union MR_PD_REF	ref;
+	u8 inquiryData[96];
+	u8 vpdPage83[64];
+	u8 notSupported;
+	u8 scsiDevType;
+
+	union {
+		u8 connectedPortBitmap;
+		u8 connectedPortNumbers;
+	};
+
+	u8 deviceSpeed;
+	u32 mediaErrCount;
+	u32 otherErrCount;
+	u32 predFailCount;
+	u32 lastPredFailEventSeqNum;
+
+	u16 fwState;
+	u8 disabledForRemoval;
+	u8 linkSpeed;
+	union MR_PD_DDF_TYPE state;
+
+	struct {
+		u8 count;
+#ifndef __BIG_ENDIAN_BITFIELD
+		u8 isPathBroken:4;
+		u8 reserved3:3;
+		u8 widePortCapable:1;
+#else
+		u8 widePortCapable:1;
+		u8 reserved3:3;
+		u8 isPathBroken:4;
+#endif
+
+		u8 connectorIndex[2];
+		u8 reserved[4];
+		u64 sasAddr[2];
+		u8 reserved2[16];
+	} pathInfo;
+
+	u64 rawSize;
+	u64 nonCoercedSize;
+	u64 coercedSize;
+	u16 enclDeviceId;
+	u8 enclIndex;
+
+	union {
+		u8 slotNumber;
+		u8 enclConnectorIndex;
+	};
+
+	struct MR_PD_PROGRESS progInfo;
+	u8 badBlockTableFull;
+	u8 unusableInCurrentConfig;
+	u8 vpdPage83Ext[64];
+	u8 powerState;
+	u8 enclPosition;
+	u32 allowedOps;
+	u16 copyBackPartnerId;
+	u16 enclPartnerDeviceId;
+	struct {
+#ifndef __BIG_ENDIAN_BITFIELD
+		u16 fdeCapable:1;
+		u16 fdeEnabled:1;
+		u16 secured:1;
+		u16 locked:1;
+		u16 foreign:1;
+		u16 needsEKM:1;
+		u16 reserved:10;
+#else
+		u16 reserved:10;
+		u16 needsEKM:1;
+		u16 foreign:1;
+		u16 locked:1;
+		u16 secured:1;
+		u16 fdeEnabled:1;
+		u16 fdeCapable:1;
+#endif
+	} security;
+	u8 mediaType;
+	u8 notCertified;
+	u8 bridgeVendor[8];
+	u8 bridgeProductIdentification[16];
+	u8 bridgeProductRevisionLevel[4];
+	u8 satBridgeExists;
+
+	u8 interfaceType;
+	u8 temperature;
+	u8 emulatedBlockSize;
+	u16 userDataBlockSize;
+	u16 reserved2;
+
+	struct {
+#ifndef __BIG_ENDIAN_BITFIELD
+		u32 piType:3;
+		u32 piFormatted:1;
+		u32 piEligible:1;
+		u32 NCQ:1;
+		u32 WCE:1;
+		u32 commissionedSpare:1;
+		u32 emergencySpare:1;
+		u32 ineligibleForSSCD:1;
+		u32 ineligibleForLd:1;
+		u32 useSSEraseType:1;
+		u32 wceUnchanged:1;
+		u32 supportScsiUnmap:1;
+		u32 reserved:18;
+#else
+		u32 reserved:18;
+		u32 supportScsiUnmap:1;
+		u32 wceUnchanged:1;
+		u32 useSSEraseType:1;
+		u32 ineligibleForLd:1;
+		u32 ineligibleForSSCD:1;
+		u32 emergencySpare:1;
+		u32 commissionedSpare:1;
+		u32 WCE:1;
+		u32 NCQ:1;
+		u32 piEligible:1;
+		u32 piFormatted:1;
+		u32 piType:3;
+#endif
+	} properties;
+
+	u64 shieldDiagCompletionTime;
+	u8 shieldCounter;
+
+	u8 linkSpeedOther;
+	u8 reserved4[2];
+
+	struct {
+#ifndef __BIG_ENDIAN_BITFIELD
+		u32 bbmErrCountSupported:1;
+		u32 bbmErrCount:31;
+#else
+		u32 bbmErrCount:31;
+		u32 bbmErrCountSupported:1;
+#endif
+	} bbmErr;
+
+	u8 reserved1[512-428];
+} __packed;
 
  /*
  * defines the physical drive address structure
@@ -473,6 +728,7 @@ struct megasas_pd_list {
 	u16             tid;
 	u8             driveType;
 	u8             driveState;
+	u8             interface;
 } __packed;
 
  /*
@@ -972,7 +1228,8 @@ struct megasas_ctrl_info {
 	*/
 	struct {
 #if defined(__BIG_ENDIAN_BITFIELD)
-		u32     reserved:26;
+		u32     reserved:25;
+		u32     passive:1;
 		u32     premiumFeatureMismatch:1;
 		u32     ctrlPropIncompatible:1;
 		u32     fwVersionMismatch:1;
@@ -986,11 +1243,12 @@ struct megasas_ctrl_info {
 		u32     fwVersionMismatch:1;
 		u32     ctrlPropIncompatible:1;
 		u32     premiumFeatureMismatch:1;
-		u32     reserved:26;
+		u32     passive:1;
+		u32     reserved:25;
 #endif
 	} cluster;
 
-	char clusterId[16];                     /*7D4h */
+	char clusterId[MEGASAS_CLUSTER_ID_SIZE]; /*0x7D4 */
 	struct {
 		u8  maxVFsSupported;            /*0x7E4*/
 		u8  numVFsEnabled;              /*0x7E5*/
@@ -1083,6 +1341,8 @@ struct megasas_ctrl_info {
 
 #define VD_EXT_DEBUG 0
 
+#define SCAN_PD_CHANNEL	0x1
+#define SCAN_VD_CHANNEL	0x2
 
 enum MR_SCSI_CMD_TYPE {
 	READ_WRITE_LDIO = 0,
@@ -1091,6 +1351,17 @@ enum MR_SCSI_CMD_TYPE {
 	NON_READ_WRITE_SYSPDIO = 3,
 };
 
+enum DCMD_TIMEOUT_ACTION {
+	INITIATE_OCR = 0,
+	KILL_ADAPTER = 1,
+	IGNORE_TIMEOUT = 2,
+};
+
+enum FW_BOOT_CONTEXT {
+	PROBE_CONTEXT = 0,
+	OCR_CONTEXT = 1,
+};
+
 /* Frame Type */
 #define IO_FRAME				0
 #define PTHRU_FRAME				1
@@ -1137,6 +1408,7 @@ enum MR_SCSI_CMD_TYPE {
 
 #define MFI_OB_INTR_STATUS_MASK			0x00000002
 #define MFI_POLL_TIMEOUT_SECS			60
+#define MFI_IO_TIMEOUT_SECS			180
 #define MEGASAS_SRIOV_HEARTBEAT_INTERVAL_VF	(5 * HZ)
 #define MEGASAS_OCR_SETTLE_TIME_VF		(1000 * 30)
 #define MEGASAS_ROUTINE_WAIT_TIME_VF		300
@@ -1154,6 +1426,7 @@ enum MR_SCSI_CMD_TYPE {
 #define MR_MAX_REPLY_QUEUES_EXT_OFFSET          0X003FC000
 #define MR_MAX_REPLY_QUEUES_EXT_OFFSET_SHIFT    14
 #define MR_MAX_MSIX_REG_ARRAY                   16
+#define MR_RDPQ_MODE_OFFSET			0X00800000
 /*
 * register set for both 1068 and 1078 controllers
 * structure extended for 1078 registers
@@ -1193,8 +1466,9 @@ struct megasas_register_set {
 
 	u32 	outbound_scratch_pad ;		/*00B0h*/
 	u32	outbound_scratch_pad_2;         /*00B4h*/
+	u32	outbound_scratch_pad_3;         /*00B8h*/
 
-	u32	reserved_4[2];			/*00B8h*/
+	u32	reserved_4;			/*00BCh*/
 
 	u32 	inbound_low_queue_port ;	/*00C0h*/
 
@@ -1266,7 +1540,10 @@ union megasas_sgl_frame {
 typedef union _MFI_CAPABILITIES {
 	struct {
 #if   defined(__BIG_ENDIAN_BITFIELD)
-		u32     reserved:23;
+		u32     reserved:20;
+		u32     support_qd_throttling:1;
+		u32     support_fp_rlbypass:1;
+		u32     support_vfid_in_ioframe:1;
 		u32     support_ext_io_size:1;
 		u32	support_ext_queue_depth:1;
 		u32     security_protocol_cmds_fw:1;
@@ -1286,7 +1563,10 @@ typedef union _MFI_CAPABILITIES {
 		u32     security_protocol_cmds_fw:1;
 		u32	support_ext_queue_depth:1;
 		u32     support_ext_io_size:1;
-		u32     reserved:23;
+		u32     support_vfid_in_ioframe:1;
+		u32     support_fp_rlbypass:1;
+		u32     support_qd_throttling:1;
+		u32     reserved:20;
 #endif
 	} mfi_capabilities;
 	__le32		reg;
@@ -1511,6 +1791,15 @@ union megasas_frame {
 	u8 raw_bytes[64];
 };
 
+/**
+ * struct MR_PRIV_DEVICE - sdev private hostdata
+ * @is_tm_capable: firmware managed tm_capable flag
+ * @tm_busy: TM request is in progress
+ */
+struct MR_PRIV_DEVICE {
+	bool is_tm_capable;
+	bool tm_busy;
+};
 struct megasas_cmd;
 
 union megasas_evt_class_locale {
@@ -1700,6 +1989,19 @@ struct MR_DRV_SYSTEM_INFO {
 	u8	reserved[1980];
 };
 
+enum MR_PD_TYPE {
+		 UNKNOWN_DRIVE = 0,
+		 PARALLEL_SCSI = 1,
+		 SAS_PD = 2,
+		 SATA_PD = 3,
+		 FC_PD = 4,
+};
+
+/* JBOD Queue depth definitions */
+#define MEGASAS_SATA_QD	32
+#define MEGASAS_SAS_QD	64
+#define MEGASAS_DEFAULT_PD_QD	64
+
 struct megasas_instance {
 
 	__le32 *producer;
@@ -1714,6 +2016,8 @@ struct megasas_instance {
 	dma_addr_t vf_affiliation_111_h;
 	struct MR_CTRL_HB_HOST_MEM *hb_host_mem;
 	dma_addr_t hb_host_mem_h;
+	struct MR_PD_INFO *pd_info;
+	dma_addr_t pd_info_h;
 
 	__le32 *reply_queue;
 	dma_addr_t reply_queue_h;
@@ -1745,6 +2049,8 @@ struct megasas_instance {
 	u16 max_fw_cmds;
 	u16 max_mfi_cmds;
 	u16 max_scsi_cmds;
+	u16 ldio_threshold;
+	u16 cur_can_queue;
 	u32 max_sectors_per_req;
 	struct megasas_aen_event *ev;
 
@@ -1762,7 +2068,7 @@ struct megasas_instance {
 	struct megasas_evt_detail *evt_detail;
 	dma_addr_t evt_detail_h;
 	struct megasas_cmd *aen_cmd;
-	struct mutex aen_mutex;
+	struct mutex hba_mutex;
 	struct semaphore ioctl_sem;
 
 	struct Scsi_Host *host;
@@ -1775,6 +2081,7 @@ struct megasas_instance {
 	u32 fw_support_ieee;
 
 	atomic_t fw_outstanding;
+	atomic_t ldio_outstanding;
 	atomic_t fw_reset_no_pci_access;
 
 	struct megasas_instance_template *instancet;
@@ -1797,7 +2104,7 @@ struct megasas_instance {
 	u16 drv_supported_vd_count;
 	u16 drv_supported_pd_count;
 
-	u8 adprecovery;
+	atomic_t adprecovery;
 	unsigned long last_time;
 	u32 mfiStatus;
 	u32 last_seq_num;
@@ -1822,11 +2129,14 @@ struct megasas_instance {
 	char skip_heartbeat_timer_del;
 	u8 requestorId;
 	char PlasmaFW111;
-	char mpio;
+	char clusterId[MEGASAS_CLUSTER_ID_SIZE];
+	u8 peerIsPresent;
+	u8 passive;
 	u16 throttlequeuedepth;
 	u8 mask_interrupts;
 	u16 max_chain_frame_sz;
 	u8 is_imr;
+	u8 is_rdpq;
 	bool dev_handle;
 };
 struct MR_LD_VF_MAP {
@@ -1916,7 +2226,7 @@ struct megasas_instance_template {
 	u32 (*init_adapter)(struct megasas_instance *);
 	u32 (*build_and_issue_cmd) (struct megasas_instance *,
 				    struct scsi_cmnd *);
-	void (*issue_dcmd) (struct megasas_instance *instance,
+	int (*issue_dcmd)(struct megasas_instance *instance,
 			    struct megasas_cmd *cmd);
 };
 
@@ -2014,6 +2324,19 @@ struct megasas_mgmt_info {
 	int max_index;
 };
 
+enum MEGASAS_OCR_CAUSE {
+	FW_FAULT_OCR			= 0,
+	SCSIIO_TIMEOUT_OCR		= 1,
+	MFI_IO_TIMEOUT_OCR		= 2,
+};
+
+enum DCMD_RETURN_STATUS {
+	DCMD_SUCCESS		= 0,
+	DCMD_TIMEOUT		= 1,
+	DCMD_FAILED		= 2,
+	DCMD_NOT_FIRED		= 3,
+};
+
 u8
 MR_BuildRaidContext(struct megasas_instance *instance,
 		    struct IO_REQUEST_INFO *io_info,
@@ -2051,4 +2374,8 @@ void megasas_return_mfi_mpt_pthr(struct megasas_instance *instance,
 int megasas_cmd_type(struct scsi_cmnd *cmd);
 void megasas_setup_jbod_map(struct megasas_instance *instance);
 
+void megasas_update_sdev_properties(struct scsi_device *sdev);
+int megasas_reset_fusion(struct Scsi_Host *shost, int reason);
+int megasas_task_abort_fusion(struct scsi_cmnd *scmd);
+int megasas_reset_target_fusion(struct scsi_cmnd *scmd);
 #endif				/*LSI_MEGARAID_SAS_H */
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 97a1c1c33b05..5c08568ccfbf 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -83,7 +83,7 @@ module_param(throttlequeuedepth, int, S_IRUGO);
 MODULE_PARM_DESC(throttlequeuedepth,
 	"Adapter queue depth when throttled due to I/O timeout. Default: 16");
 
-int resetwaittime = MEGASAS_RESET_WAIT_TIME;
+unsigned int resetwaittime = MEGASAS_RESET_WAIT_TIME;
 module_param(resetwaittime, int, S_IRUGO);
 MODULE_PARM_DESC(resetwaittime, "Wait time in seconds after I/O timeout "
 		 "before resetting adapter. Default: 180");
@@ -92,6 +92,18 @@ int smp_affinity_enable = 1;
 module_param(smp_affinity_enable, int, S_IRUGO);
 MODULE_PARM_DESC(smp_affinity_enable, "SMP affinity feature enable/disbale Default: enable(1)");
 
+int rdpq_enable = 1;
+module_param(rdpq_enable, int, S_IRUGO);
+MODULE_PARM_DESC(rdpq_enable, " Allocate reply queue in chunks for large queue depth enable/disable Default: disable(0)");
+
+unsigned int dual_qdepth_disable;
+module_param(dual_qdepth_disable, int, S_IRUGO);
+MODULE_PARM_DESC(dual_qdepth_disable, "Disable dual queue depth feature. Default: 0");
+
+unsigned int scmd_timeout = MEGASAS_DEFAULT_CMD_TIMEOUT;
+module_param(scmd_timeout, int, S_IRUGO);
+MODULE_PARM_DESC(scmd_timeout, "scsi command timeout (10-90s), default 90s. See megasas_reset_timer.");
+
 MODULE_LICENSE("GPL");
 MODULE_VERSION(MEGASAS_VERSION);
 MODULE_AUTHOR("megaraidlinux.pdl@avagotech.com");
@@ -104,6 +116,8 @@ static int megasas_ld_list_query(struct megasas_instance *instance,
 static int megasas_issue_init_mfi(struct megasas_instance *instance);
 static int megasas_register_aen(struct megasas_instance *instance,
 				u32 seq_num, u32 class_locale_word);
+static int
+megasas_get_pd_info(struct megasas_instance *instance, u16 device_id);
 /*
  * PCI ID table for all supported controllers
  */
@@ -189,18 +203,18 @@ int
 wait_and_poll(struct megasas_instance *instance, struct megasas_cmd *cmd,
 	int seconds);
 void megasas_reset_reply_desc(struct megasas_instance *instance);
-int megasas_reset_fusion(struct Scsi_Host *shost, int iotimeout);
 void megasas_fusion_ocr_wq(struct work_struct *work);
 static int megasas_get_ld_vf_affiliation(struct megasas_instance *instance,
 					 int initial);
 int megasas_check_mpio_paths(struct megasas_instance *instance,
 			     struct scsi_cmnd *scmd);
 
-void
+int
 megasas_issue_dcmd(struct megasas_instance *instance, struct megasas_cmd *cmd)
 {
 	instance->instancet->fire_cmd(instance,
 		cmd->frame_phys_addr, 0, instance->reg_set);
+	return 0;
 }
 
 /**
@@ -473,7 +487,7 @@ static int
 megasas_check_reset_xscale(struct megasas_instance *instance,
 		struct megasas_register_set __iomem *regs)
 {
-	if ((instance->adprecovery != MEGASAS_HBA_OPERATIONAL) &&
+	if ((atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL) &&
 	    (le32_to_cpu(*instance->consumer) ==
 		MEGASAS_ADPRESET_INPROG_SIGN))
 		return 1;
@@ -609,7 +623,7 @@ static int
 megasas_check_reset_ppc(struct megasas_instance *instance,
 			struct megasas_register_set __iomem *regs)
 {
-	if (instance->adprecovery != MEGASAS_HBA_OPERATIONAL)
+	if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL)
 		return 1;
 
 	return 0;
@@ -735,6 +749,7 @@ megasas_fire_cmd_skinny(struct megasas_instance *instance,
 	       &(regs)->inbound_high_queue_port);
 	writel((lower_32_bits(frame_phys_addr) | (frame_count<<1))|1,
 	       &(regs)->inbound_low_queue_port);
+	mmiowb();
 	spin_unlock_irqrestore(&instance->hba_lock, flags);
 }
 
@@ -746,7 +761,7 @@ static int
 megasas_check_reset_skinny(struct megasas_instance *instance,
 				struct megasas_register_set __iomem *regs)
 {
-	if (instance->adprecovery != MEGASAS_HBA_OPERATIONAL)
+	if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL)
 		return 1;
 
 	return 0;
@@ -940,9 +955,8 @@ static int
 megasas_check_reset_gen2(struct megasas_instance *instance,
 		struct megasas_register_set __iomem *regs)
 {
-	if (instance->adprecovery != MEGASAS_HBA_OPERATIONAL) {
+	if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL)
 		return 1;
-	}
 
 	return 0;
 }
@@ -983,25 +997,20 @@ extern struct megasas_instance_template megasas_instance_template_fusion;
 int
 megasas_issue_polled(struct megasas_instance *instance, struct megasas_cmd *cmd)
 {
-	int seconds;
 	struct megasas_header *frame_hdr = &cmd->frame->hdr;
 
-	frame_hdr->cmd_status = MFI_CMD_STATUS_POLL_MODE;
+	frame_hdr->cmd_status = MFI_STAT_INVALID_STATUS;
 	frame_hdr->flags |= cpu_to_le16(MFI_FRAME_DONT_POST_IN_REPLY_QUEUE);
 
-	/*
-	 * Issue the frame using inbound queue port
-	 */
-	instance->instancet->issue_dcmd(instance, cmd);
+	if ((atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) ||
+		(instance->instancet->issue_dcmd(instance, cmd))) {
+		dev_err(&instance->pdev->dev, "Failed from %s %d\n",
+			__func__, __LINE__);
+		return DCMD_NOT_FIRED;
+	}
 
-	/*
-	 * Wait for cmd_status to change
-	 */
-	if (instance->requestorId)
-		seconds = MEGASAS_ROUTINE_WAIT_TIME_VF;
-	else
-		seconds = MFI_POLL_TIMEOUT_SECS;
-	return wait_and_poll(instance, cmd, seconds);
+	return wait_and_poll(instance, cmd, instance->requestorId ?
+			MEGASAS_ROUTINE_WAIT_TIME_VF : MFI_IO_TIMEOUT_SECS);
 }
 
 /**
@@ -1019,21 +1028,29 @@ megasas_issue_blocked_cmd(struct megasas_instance *instance,
 			  struct megasas_cmd *cmd, int timeout)
 {
 	int ret = 0;
-
 	cmd->cmd_status_drv = MFI_STAT_INVALID_STATUS;
 
-	instance->instancet->issue_dcmd(instance, cmd);
+	if ((atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) ||
+		(instance->instancet->issue_dcmd(instance, cmd))) {
+		dev_err(&instance->pdev->dev, "Failed from %s %d\n",
+			__func__, __LINE__);
+		return DCMD_NOT_FIRED;
+	}
+
 	if (timeout) {
 		ret = wait_event_timeout(instance->int_cmd_wait_q,
 				cmd->cmd_status_drv != MFI_STAT_INVALID_STATUS, timeout * HZ);
-		if (!ret)
-			return 1;
+		if (!ret) {
+			dev_err(&instance->pdev->dev, "Failed from %s %d DCMD Timed out\n",
+				__func__, __LINE__);
+			return DCMD_TIMEOUT;
+		}
 	} else
 		wait_event(instance->int_cmd_wait_q,
 				cmd->cmd_status_drv != MFI_STAT_INVALID_STATUS);
 
 	return (cmd->cmd_status_drv == MFI_STAT_OK) ?
-		0 : 1;
+		DCMD_SUCCESS : DCMD_FAILED;
 }
 
 /**
@@ -1077,15 +1094,20 @@ megasas_issue_blocked_abort_cmd(struct megasas_instance *instance,
 	cmd->sync_cmd = 1;
 	cmd->cmd_status_drv = MFI_STAT_INVALID_STATUS;
 
-	instance->instancet->issue_dcmd(instance, cmd);
+	if ((atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) ||
+		(instance->instancet->issue_dcmd(instance, cmd))) {
+		dev_err(&instance->pdev->dev, "Failed from %s %d\n",
+			__func__, __LINE__);
+		return DCMD_NOT_FIRED;
+	}
 
 	if (timeout) {
 		ret = wait_event_timeout(instance->abort_cmd_wait_q,
 				cmd->cmd_status_drv != MFI_STAT_INVALID_STATUS, timeout * HZ);
 		if (!ret) {
-			dev_err(&instance->pdev->dev, "Command timedout"
-				"from %s\n", __func__);
-			return 1;
+			dev_err(&instance->pdev->dev, "Failed from %s %d Abort Timed out\n",
+				__func__, __LINE__);
+			return DCMD_TIMEOUT;
 		}
 	} else
 		wait_event(instance->abort_cmd_wait_q,
@@ -1094,7 +1116,8 @@ megasas_issue_blocked_abort_cmd(struct megasas_instance *instance,
 	cmd->sync_cmd = 0;
 
 	megasas_return_cmd(instance, cmd);
-	return 0;
+	return (cmd->cmd_status_drv == MFI_STAT_OK) ?
+		DCMD_SUCCESS : DCMD_FAILED;
 }
 
 /**
@@ -1621,7 +1644,7 @@ megasas_build_and_issue_cmd(struct megasas_instance *instance,
 	return 0;
 out_return_cmd:
 	megasas_return_cmd(instance, cmd);
-	return 1;
+	return SCSI_MLQUEUE_HOST_BUSY;
 }
 
 
@@ -1634,7 +1657,7 @@ static int
 megasas_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 {
 	struct megasas_instance *instance;
-	unsigned long flags;
+	struct MR_PRIV_DEVICE *mr_device_priv_data;
 
 	instance = (struct megasas_instance *)
 	    scmd->device->host->hostdata;
@@ -1648,35 +1671,38 @@ megasas_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 	if (instance->issuepend_done == 0)
 		return SCSI_MLQUEUE_HOST_BUSY;
 
-	spin_lock_irqsave(&instance->hba_lock, flags);
 
 	/* Check for an mpio path and adjust behavior */
-	if (instance->adprecovery == MEGASAS_ADPRESET_SM_INFAULT) {
+	if (atomic_read(&instance->adprecovery) == MEGASAS_ADPRESET_SM_INFAULT) {
 		if (megasas_check_mpio_paths(instance, scmd) ==
 		    (DID_RESET << 16)) {
-			spin_unlock_irqrestore(&instance->hba_lock, flags);
 			return SCSI_MLQUEUE_HOST_BUSY;
 		} else {
-			spin_unlock_irqrestore(&instance->hba_lock, flags);
 			scmd->result = DID_NO_CONNECT << 16;
 			scmd->scsi_done(scmd);
 			return 0;
 		}
 	}
 
-	if (instance->adprecovery == MEGASAS_HW_CRITICAL_ERROR) {
-		spin_unlock_irqrestore(&instance->hba_lock, flags);
+	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
 		scmd->result = DID_NO_CONNECT << 16;
 		scmd->scsi_done(scmd);
 		return 0;
 	}
 
-	if (instance->adprecovery != MEGASAS_HBA_OPERATIONAL) {
-		spin_unlock_irqrestore(&instance->hba_lock, flags);
-		return SCSI_MLQUEUE_HOST_BUSY;
+	mr_device_priv_data = scmd->device->hostdata;
+	if (!mr_device_priv_data) {
+		scmd->result = DID_NO_CONNECT << 16;
+		scmd->scsi_done(scmd);
+		return 0;
 	}
 
-	spin_unlock_irqrestore(&instance->hba_lock, flags);
+	if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL)
+		return SCSI_MLQUEUE_HOST_BUSY;
+
+	if (mr_device_priv_data->tm_busy)
+		return SCSI_MLQUEUE_DEVICE_BUSY;
+
 
 	scmd->result = 0;
 
@@ -1699,12 +1725,7 @@ megasas_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 		break;
 	}
 
-	if (instance->instancet->build_and_issue_cmd(instance, scmd)) {
-		dev_err(&instance->pdev->dev, "Err returned from build_and_issue_cmd\n");
-		return SCSI_MLQUEUE_HOST_BUSY;
-	}
-
-	return 0;
+	return instance->instancet->build_and_issue_cmd(instance, scmd);
 
  out_done:
 	scmd->scsi_done(scmd);
@@ -1726,27 +1747,39 @@ static struct megasas_instance *megasas_lookup_instance(u16 host_no)
 }
 
 /*
-* megasas_set_dma_alignment - Set DMA alignment for PI enabled VD
+* megasas_update_sdev_properties - Update sdev structure based on controller's FW capabilities
 *
 * @sdev: OS provided scsi device
 *
 * Returns void
 */
-static void megasas_set_dma_alignment(struct scsi_device *sdev)
+void megasas_update_sdev_properties(struct scsi_device *sdev)
 {
+	u16 pd_index = 0;
 	u32 device_id, ld;
 	struct megasas_instance *instance;
 	struct fusion_context *fusion;
+	struct MR_PRIV_DEVICE *mr_device_priv_data;
+	struct MR_PD_CFG_SEQ_NUM_SYNC *pd_sync;
 	struct MR_LD_RAID *raid;
 	struct MR_DRV_RAID_MAP_ALL *local_map_ptr;
 
 	instance = megasas_lookup_instance(sdev->host->host_no);
 	fusion = instance->ctrl_context;
+	mr_device_priv_data = sdev->hostdata;
 
 	if (!fusion)
 		return;
 
-	if (sdev->channel >= MEGASAS_MAX_PD_CHANNELS) {
+	if (sdev->channel < MEGASAS_MAX_PD_CHANNELS &&
+		instance->use_seqnum_jbod_fp) {
+		pd_index = (sdev->channel * MEGASAS_MAX_DEV_PER_CHANNEL) +
+			sdev->id;
+		pd_sync = (void *)fusion->pd_seq_sync
+				[(instance->pd_seq_map_id - 1) & 1];
+		mr_device_priv_data->is_tm_capable =
+			pd_sync->seq[pd_index].capability.tmCapable;
+	} else {
 		device_id = ((sdev->channel % 2) * MEGASAS_MAX_DEV_PER_CHANNEL)
 					+ sdev->id;
 		local_map_ptr = fusion->ld_drv_map[(instance->map_id & 1)];
@@ -1754,10 +1787,51 @@ static void megasas_set_dma_alignment(struct scsi_device *sdev)
 		raid = MR_LdRaidGet(ld, local_map_ptr);
 
 		if (raid->capability.ldPiMode == MR_PROT_INFO_TYPE_CONTROLLER)
-			blk_queue_update_dma_alignment(sdev->request_queue, 0x7);
+		blk_queue_update_dma_alignment(sdev->request_queue, 0x7);
+		mr_device_priv_data->is_tm_capable =
+			raid->capability.tmCapable;
+	}
+}
+
+static void megasas_set_device_queue_depth(struct scsi_device *sdev)
+{
+	u16				pd_index = 0;
+	int		ret = DCMD_FAILED;
+	struct megasas_instance *instance;
+
+	instance = megasas_lookup_instance(sdev->host->host_no);
+
+	if (sdev->channel < MEGASAS_MAX_PD_CHANNELS) {
+		pd_index = (sdev->channel * MEGASAS_MAX_DEV_PER_CHANNEL) + sdev->id;
+
+		if (instance->pd_info) {
+			mutex_lock(&instance->hba_mutex);
+			ret = megasas_get_pd_info(instance, pd_index);
+			mutex_unlock(&instance->hba_mutex);
+		}
+
+		if (ret != DCMD_SUCCESS)
+			return;
+
+		if (instance->pd_list[pd_index].driveState == MR_PD_STATE_SYSTEM) {
+
+			switch (instance->pd_list[pd_index].interface) {
+			case SAS_PD:
+				scsi_change_queue_depth(sdev, MEGASAS_SAS_QD);
+				break;
+
+			case SATA_PD:
+				scsi_change_queue_depth(sdev, MEGASAS_SATA_QD);
+				break;
+
+			default:
+				scsi_change_queue_depth(sdev, MEGASAS_DEFAULT_PD_QD);
+			}
+		}
 	}
 }
 
+
 static int megasas_slave_configure(struct scsi_device *sdev)
 {
 	u16 pd_index = 0;
@@ -1774,12 +1848,14 @@ static int megasas_slave_configure(struct scsi_device *sdev)
 				return -ENXIO;
 		}
 	}
-	megasas_set_dma_alignment(sdev);
+	megasas_set_device_queue_depth(sdev);
+	megasas_update_sdev_properties(sdev);
+
 	/*
 	 * The RAID firmware may require extended timeouts.
 	 */
 	blk_queue_rq_timeout(sdev->request_queue,
-		MEGASAS_DEFAULT_CMD_TIMEOUT * HZ);
+		scmd_timeout * HZ);
 
 	return 0;
 }
@@ -1788,6 +1864,7 @@ static int megasas_slave_alloc(struct scsi_device *sdev)
 {
 	u16 pd_index = 0;
 	struct megasas_instance *instance ;
+	struct MR_PRIV_DEVICE *mr_device_priv_data;
 
 	instance = megasas_lookup_instance(sdev->host->host_no);
 	if (sdev->channel < MEGASAS_MAX_PD_CHANNELS) {
@@ -1799,13 +1876,26 @@ static int megasas_slave_alloc(struct scsi_device *sdev)
 			sdev->id;
 		if ((instance->allow_fw_scan || instance->pd_list[pd_index].driveState ==
 			MR_PD_STATE_SYSTEM)) {
-			return 0;
+			goto scan_target;
 		}
 		return -ENXIO;
 	}
+
+scan_target:
+	mr_device_priv_data = kzalloc(sizeof(*mr_device_priv_data),
+					GFP_KERNEL);
+	if (!mr_device_priv_data)
+		return -ENOMEM;
+	sdev->hostdata = mr_device_priv_data;
 	return 0;
 }
 
+static void megasas_slave_destroy(struct scsi_device *sdev)
+{
+	kfree(sdev->hostdata);
+	sdev->hostdata = NULL;
+}
+
 /*
 * megasas_complete_outstanding_ioctls - Complete outstanding ioctls after a
 *                                       kill adapter
@@ -1845,7 +1935,7 @@ static void megasas_complete_outstanding_ioctls(struct megasas_instance *instanc
 void megaraid_sas_kill_hba(struct megasas_instance *instance)
 {
 	/* Set critical error to block I/O & ioctls in case caller didn't */
-	instance->adprecovery = MEGASAS_HW_CRITICAL_ERROR;
+	atomic_set(&instance->adprecovery, MEGASAS_HW_CRITICAL_ERROR);
 	/* Wait 1 second to ensure IO or ioctls in build have posted */
 	msleep(1000);
 	if ((instance->pdev->device == PCI_DEVICE_ID_LSI_SAS0073SKINNY) ||
@@ -1854,7 +1944,7 @@ void megaraid_sas_kill_hba(struct megasas_instance *instance)
 		writel(MFI_STOP_ADP, &instance->reg_set->doorbell);
 		/* Flush */
 		readl(&instance->reg_set->doorbell);
-		if (instance->mpio && instance->requestorId)
+		if (instance->requestorId && instance->peerIsPresent)
 			memset(instance->ld_ids, 0xff, MEGASAS_MAX_LD_IDS);
 	} else {
 		writel(MFI_STOP_ADP,
@@ -1883,7 +1973,7 @@ megasas_check_and_restore_queue_depth(struct megasas_instance *instance)
 		spin_lock_irqsave(instance->host->host_lock, flags);
 		instance->flag &= ~MEGASAS_FW_BUSY;
 
-		instance->host->can_queue = instance->max_scsi_cmds;
+		instance->host->can_queue = instance->cur_can_queue;
 		spin_unlock_irqrestore(instance->host->host_lock, flags);
 	}
 }
@@ -1905,7 +1995,7 @@ static void megasas_complete_cmd_dpc(unsigned long instance_addr)
 	unsigned long flags;
 
 	/* If we have already declared adapter dead, donot complete cmds */
-	if (instance->adprecovery == MEGASAS_HW_CRITICAL_ERROR)
+	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR)
 		return;
 
 	spin_lock_irqsave(&instance->completion_lock, flags);
@@ -1974,7 +2064,7 @@ void megasas_do_ocr(struct megasas_instance *instance)
 		*instance->consumer = cpu_to_le32(MEGASAS_ADPRESET_INPROG_SIGN);
 	}
 	instance->instancet->disable_intr(instance);
-	instance->adprecovery   = MEGASAS_ADPRESET_SM_INFAULT;
+	atomic_set(&instance->adprecovery, MEGASAS_ADPRESET_SM_INFAULT);
 	instance->issuepend_done = 0;
 
 	atomic_set(&instance->fw_outstanding, 0);
@@ -2054,9 +2144,7 @@ static int megasas_get_ld_vf_affiliation_111(struct megasas_instance *instance,
 	dev_warn(&instance->pdev->dev, "SR-IOV: Getting LD/VF affiliation for "
 	       "scsi%d\n", instance->host->host_no);
 
-	megasas_issue_blocked_cmd(instance, cmd, 0);
-
-	if (dcmd->cmd_status) {
+	if (megasas_issue_blocked_cmd(instance, cmd, 0) != DCMD_SUCCESS) {
 		dev_warn(&instance->pdev->dev, "SR-IOV: LD/VF affiliation DCMD"
 		       " failed with status 0x%x for scsi%d\n",
 		       dcmd->cmd_status, instance->host->host_no);
@@ -2166,9 +2254,8 @@ static int megasas_get_ld_vf_affiliation_12(struct megasas_instance *instance,
 	dev_warn(&instance->pdev->dev, "SR-IOV: Getting LD/VF affiliation for "
 	       "scsi%d\n", instance->host->host_no);
 
-	megasas_issue_blocked_cmd(instance, cmd, 0);
 
-	if (dcmd->cmd_status) {
+	if (megasas_issue_blocked_cmd(instance, cmd, 0) != DCMD_SUCCESS) {
 		dev_warn(&instance->pdev->dev, "SR-IOV: LD/VF affiliation DCMD"
 		       " failed with status 0x%x for scsi%d\n",
 		       dcmd->cmd_status, instance->host->host_no);
@@ -2373,21 +2460,21 @@ void megasas_sriov_heartbeat_handler(unsigned long instance_addr)
  */
 static int megasas_wait_for_outstanding(struct megasas_instance *instance)
 {
-	int i;
+	int i, sl, outstanding;
 	u32 reset_index;
 	u32 wait_time = MEGASAS_RESET_WAIT_TIME;
-	u8 adprecovery;
 	unsigned long flags;
 	struct list_head clist_local;
 	struct megasas_cmd *reset_cmd;
 	u32 fw_state;
-	u8 kill_adapter_flag;
 
-	spin_lock_irqsave(&instance->hba_lock, flags);
-	adprecovery = instance->adprecovery;
-	spin_unlock_irqrestore(&instance->hba_lock, flags);
+	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
+		dev_info(&instance->pdev->dev, "%s:%d HBA is killed.\n",
+		__func__, __LINE__);
+		return FAILED;
+	}
 
-	if (adprecovery != MEGASAS_HBA_OPERATIONAL) {
+	if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL) {
 
 		INIT_LIST_HEAD(&clist_local);
 		spin_lock_irqsave(&instance->hba_lock, flags);
@@ -2398,18 +2485,13 @@ static int megasas_wait_for_outstanding(struct megasas_instance *instance)
 		dev_notice(&instance->pdev->dev, "HBA reset wait ...\n");
 		for (i = 0; i < wait_time; i++) {
 			msleep(1000);
-			spin_lock_irqsave(&instance->hba_lock, flags);
-			adprecovery = instance->adprecovery;
-			spin_unlock_irqrestore(&instance->hba_lock, flags);
-			if (adprecovery == MEGASAS_HBA_OPERATIONAL)
+			if (atomic_read(&instance->adprecovery) == MEGASAS_HBA_OPERATIONAL)
 				break;
 		}
 
-		if (adprecovery != MEGASAS_HBA_OPERATIONAL) {
+		if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL) {
 			dev_notice(&instance->pdev->dev, "reset: Stopping HBA.\n");
-			spin_lock_irqsave(&instance->hba_lock, flags);
-			instance->adprecovery = MEGASAS_HW_CRITICAL_ERROR;
-			spin_unlock_irqrestore(&instance->hba_lock, flags);
+			atomic_set(&instance->adprecovery, MEGASAS_HW_CRITICAL_ERROR);
 			return FAILED;
 		}
 
@@ -2447,7 +2529,7 @@ static int megasas_wait_for_outstanding(struct megasas_instance *instance)
 	}
 
 	for (i = 0; i < resetwaittime; i++) {
-		int outstanding = atomic_read(&instance->fw_outstanding);
+		outstanding = atomic_read(&instance->fw_outstanding);
 
 		if (!outstanding)
 			break;
@@ -2466,67 +2548,60 @@ static int megasas_wait_for_outstanding(struct megasas_instance *instance)
 	}
 
 	i = 0;
-	kill_adapter_flag = 0;
+	outstanding = atomic_read(&instance->fw_outstanding);
+	fw_state = instance->instancet->read_fw_status_reg(instance->reg_set) & MFI_STATE_MASK;
+
+	if ((!outstanding && (fw_state == MFI_STATE_OPERATIONAL)))
+		goto no_outstanding;
+
+	if (instance->disableOnlineCtrlReset)
+		goto kill_hba_and_failed;
 	do {
-		fw_state = instance->instancet->read_fw_status_reg(
-					instance->reg_set) & MFI_STATE_MASK;
-		if ((fw_state == MFI_STATE_FAULT) &&
-			(instance->disableOnlineCtrlReset == 0)) {
-			if (i == 3) {
-				kill_adapter_flag = 2;
-				break;
-			}
+		if ((fw_state == MFI_STATE_FAULT) || atomic_read(&instance->fw_outstanding)) {
+			dev_info(&instance->pdev->dev,
+				"%s:%d waiting_for_outstanding: before issue OCR. FW state = 0x%x, oustanding 0x%x\n",
+				__func__, __LINE__, fw_state, atomic_read(&instance->fw_outstanding));
+			if (i == 3)
+				goto kill_hba_and_failed;
 			megasas_do_ocr(instance);
-			kill_adapter_flag = 1;
 
-			/* wait for 1 secs to let FW finish the pending cmds */
-			msleep(1000);
+			if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
+				dev_info(&instance->pdev->dev, "%s:%d OCR failed and HBA is killed.\n",
+				__func__, __LINE__);
+				return FAILED;
+			}
+			dev_info(&instance->pdev->dev, "%s:%d waiting_for_outstanding: after issue OCR.\n",
+				__func__, __LINE__);
+
+			for (sl = 0; sl < 10; sl++)
+				msleep(500);
+
+			outstanding = atomic_read(&instance->fw_outstanding);
+
+			fw_state = instance->instancet->read_fw_status_reg(instance->reg_set) & MFI_STATE_MASK;
+			if ((!outstanding && (fw_state == MFI_STATE_OPERATIONAL)))
+				goto no_outstanding;
 		}
 		i++;
 	} while (i <= 3);
 
-	if (atomic_read(&instance->fw_outstanding) && !kill_adapter_flag) {
-		if (instance->disableOnlineCtrlReset == 0) {
-			megasas_do_ocr(instance);
+no_outstanding:
 
-			/* wait for 5 secs to let FW finish the pending cmds */
-			for (i = 0; i < wait_time; i++) {
-				int outstanding =
-					atomic_read(&instance->fw_outstanding);
-				if (!outstanding)
-					return SUCCESS;
-				msleep(1000);
-			}
-		}
-	}
+	dev_info(&instance->pdev->dev, "%s:%d no more pending commands remain after reset handling.\n",
+		__func__, __LINE__);
+	return SUCCESS;
 
-	if (atomic_read(&instance->fw_outstanding) ||
-					(kill_adapter_flag == 2)) {
-		dev_notice(&instance->pdev->dev, "pending cmds after reset\n");
-		/*
-		 * Send signal to FW to stop processing any pending cmds.
-		 * The controller will be taken offline by the OS now.
-		 */
-		if ((instance->pdev->device ==
-			PCI_DEVICE_ID_LSI_SAS0073SKINNY) ||
-			(instance->pdev->device ==
-			PCI_DEVICE_ID_LSI_SAS0071SKINNY)) {
-			writel(MFI_STOP_ADP,
-				&instance->reg_set->doorbell);
-		} else {
-			writel(MFI_STOP_ADP,
-				&instance->reg_set->inbound_doorbell);
-		}
-		megasas_dump_pending_frames(instance);
-		spin_lock_irqsave(&instance->hba_lock, flags);
-		instance->adprecovery = MEGASAS_HW_CRITICAL_ERROR;
-		spin_unlock_irqrestore(&instance->hba_lock, flags);
-		return FAILED;
-	}
+kill_hba_and_failed:
 
-	dev_notice(&instance->pdev->dev, "no pending cmds after reset\n");
+	/* Reset not supported, kill adapter */
+	dev_info(&instance->pdev->dev, "%s:%d killing adapter scsi%d"
+		" disableOnlineCtrlReset %d fw_outstanding %d \n",
+		__func__, __LINE__, instance->host->host_no, instance->disableOnlineCtrlReset,
+		atomic_read(&instance->fw_outstanding));
+	megasas_dump_pending_frames(instance);
+	megaraid_sas_kill_hba(instance);
 
-	return SUCCESS;
+	return FAILED;
 }
 
 /**
@@ -2547,7 +2622,7 @@ static int megasas_generic_reset(struct scsi_cmnd *scmd)
 	scmd_printk(KERN_NOTICE, scmd, "megasas: RESET cmd=%x retries=%x\n",
 		 scmd->cmnd[0], scmd->retries);
 
-	if (instance->adprecovery == MEGASAS_HW_CRITICAL_ERROR) {
+	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
 		dev_err(&instance->pdev->dev, "cannot recover from previous reset failures\n");
 		return FAILED;
 	}
@@ -2575,7 +2650,7 @@ blk_eh_timer_return megasas_reset_timer(struct scsi_cmnd *scmd)
 	unsigned long flags;
 
 	if (time_after(jiffies, scmd->jiffies_at_alloc +
-				(MEGASAS_DEFAULT_CMD_TIMEOUT * 2) * HZ)) {
+				(scmd_timeout * 2) * HZ)) {
 		return BLK_EH_NOT_HANDLED;
 	}
 
@@ -2851,6 +2926,16 @@ megasas_page_size_show(struct device *cdev,
 	return snprintf(buf, PAGE_SIZE, "%ld\n", (unsigned long)PAGE_SIZE - 1);
 }
 
+static ssize_t
+megasas_ldio_outstanding_show(struct device *cdev, struct device_attribute *attr,
+	char *buf)
+{
+	struct Scsi_Host *shost = class_to_shost(cdev);
+	struct megasas_instance *instance = (struct megasas_instance *)shost->hostdata;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&instance->ldio_outstanding));
+}
+
 static DEVICE_ATTR(fw_crash_buffer, S_IRUGO | S_IWUSR,
 	megasas_fw_crash_buffer_show, megasas_fw_crash_buffer_store);
 static DEVICE_ATTR(fw_crash_buffer_size, S_IRUGO,
@@ -2859,12 +2944,15 @@ static DEVICE_ATTR(fw_crash_state, S_IRUGO | S_IWUSR,
 	megasas_fw_crash_state_show, megasas_fw_crash_state_store);
 static DEVICE_ATTR(page_size, S_IRUGO,
 	megasas_page_size_show, NULL);
+static DEVICE_ATTR(ldio_outstanding, S_IRUGO,
+	megasas_ldio_outstanding_show, NULL);
 
 struct device_attribute *megaraid_host_attrs[] = {
 	&dev_attr_fw_crash_buffer_size,
 	&dev_attr_fw_crash_buffer,
 	&dev_attr_fw_crash_state,
 	&dev_attr_page_size,
+	&dev_attr_ldio_outstanding,
 	NULL,
 };
 
@@ -2878,6 +2966,7 @@ static struct scsi_host_template megasas_template = {
 	.proc_name = "megaraid_sas",
 	.slave_configure = megasas_slave_configure,
 	.slave_alloc = megasas_slave_alloc,
+	.slave_destroy = megasas_slave_destroy,
 	.queuecommand = megasas_queue_command,
 	.eh_device_reset_handler = megasas_reset_device,
 	.eh_bus_reset_handler = megasas_reset_bus_host,
@@ -3277,13 +3366,13 @@ process_fw_state_change_wq(struct work_struct *work)
 	u32 wait;
 	unsigned long flags;
 
-	if (instance->adprecovery != MEGASAS_ADPRESET_SM_INFAULT) {
+    if (atomic_read(&instance->adprecovery) != MEGASAS_ADPRESET_SM_INFAULT) {
 		dev_notice(&instance->pdev->dev, "error, recovery st %x\n",
-				instance->adprecovery);
+				atomic_read(&instance->adprecovery));
 		return ;
 	}
 
-	if (instance->adprecovery == MEGASAS_ADPRESET_SM_INFAULT) {
+	if (atomic_read(&instance->adprecovery) == MEGASAS_ADPRESET_SM_INFAULT) {
 		dev_notice(&instance->pdev->dev, "FW detected to be in fault"
 					"state, restarting it...\n");
 
@@ -3326,7 +3415,7 @@ process_fw_state_change_wq(struct work_struct *work)
 		megasas_issue_init_mfi(instance);
 
 		spin_lock_irqsave(&instance->hba_lock, flags);
-		instance->adprecovery	= MEGASAS_HBA_OPERATIONAL;
+		atomic_set(&instance->adprecovery, MEGASAS_HBA_OPERATIONAL);
 		spin_unlock_irqrestore(&instance->hba_lock, flags);
 		instance->instancet->enable_intr(instance);
 
@@ -3391,14 +3480,14 @@ megasas_deplete_reply_queue(struct megasas_instance *instance,
 
 
 			instance->instancet->disable_intr(instance);
-			instance->adprecovery	= MEGASAS_ADPRESET_SM_INFAULT;
+			atomic_set(&instance->adprecovery, MEGASAS_ADPRESET_SM_INFAULT);
 			instance->issuepend_done = 0;
 
 			atomic_set(&instance->fw_outstanding, 0);
 			megasas_internal_reset_defer_cmds(instance);
 
 			dev_notice(&instance->pdev->dev, "fwState=%x, stage:%d\n",
-					fw_state, instance->adprecovery);
+					fw_state, atomic_read(&instance->adprecovery));
 
 			schedule_work(&instance->work_init);
 			return IRQ_HANDLED;
@@ -3852,6 +3941,92 @@ int megasas_alloc_cmds(struct megasas_instance *instance)
 }
 
 /*
+ * dcmd_timeout_ocr_possible -	Check if OCR is possible based on Driver/FW state.
+ * @instance:				Adapter soft state
+ *
+ * Return 0 for only Fusion adapter, if driver load/unload is not in progress
+ * or FW is not under OCR.
+ */
+inline int
+dcmd_timeout_ocr_possible(struct megasas_instance *instance) {
+
+	if (!instance->ctrl_context)
+		return KILL_ADAPTER;
+	else if (instance->unload ||
+			test_bit(MEGASAS_FUSION_IN_RESET, &instance->reset_flags))
+		return IGNORE_TIMEOUT;
+	else
+		return INITIATE_OCR;
+}
+
+static int
+megasas_get_pd_info(struct megasas_instance *instance, u16 device_id)
+{
+	int ret;
+	struct megasas_cmd *cmd;
+	struct megasas_dcmd_frame *dcmd;
+
+	cmd = megasas_get_cmd(instance);
+
+	if (!cmd) {
+		dev_err(&instance->pdev->dev, "Failed to get cmd %s\n", __func__);
+		return -ENOMEM;
+	}
+
+	dcmd = &cmd->frame->dcmd;
+
+	memset(instance->pd_info, 0, sizeof(*instance->pd_info));
+	memset(dcmd->mbox.b, 0, MFI_MBOX_SIZE);
+
+	dcmd->mbox.s[0] = cpu_to_le16(device_id);
+	dcmd->cmd = MFI_CMD_DCMD;
+	dcmd->cmd_status = 0xFF;
+	dcmd->sge_count = 1;
+	dcmd->flags = cpu_to_le16(MFI_FRAME_DIR_READ);
+	dcmd->timeout = 0;
+	dcmd->pad_0 = 0;
+	dcmd->data_xfer_len = cpu_to_le32(sizeof(struct MR_PD_INFO));
+	dcmd->opcode = cpu_to_le32(MR_DCMD_PD_GET_INFO);
+	dcmd->sgl.sge32[0].phys_addr = cpu_to_le32(instance->pd_info_h);
+	dcmd->sgl.sge32[0].length = cpu_to_le32(sizeof(struct MR_PD_INFO));
+
+	if (instance->ctrl_context && !instance->mask_interrupts)
+		ret = megasas_issue_blocked_cmd(instance, cmd, MFI_IO_TIMEOUT_SECS);
+	else
+		ret = megasas_issue_polled(instance, cmd);
+
+	switch (ret) {
+	case DCMD_SUCCESS:
+		instance->pd_list[device_id].interface =
+				instance->pd_info->state.ddf.pdType.intf;
+		break;
+
+	case DCMD_TIMEOUT:
+
+		switch (dcmd_timeout_ocr_possible(instance)) {
+		case INITIATE_OCR:
+			cmd->flags |= DRV_DCMD_SKIP_REFIRE;
+			megasas_reset_fusion(instance->host,
+				MFI_IO_TIMEOUT_OCR);
+			break;
+		case KILL_ADAPTER:
+			megaraid_sas_kill_hba(instance);
+			break;
+		case IGNORE_TIMEOUT:
+			dev_info(&instance->pdev->dev, "Ignore DCMD timeout: %s %d\n",
+				__func__, __LINE__);
+			break;
+		}
+
+		break;
+	}
+
+	if (ret != DCMD_TIMEOUT)
+		megasas_return_cmd(instance, cmd);
+
+	return ret;
+}
+/*
  * megasas_get_pd_list_info -	Returns FW's pd_list structure
  * @instance:				Adapter soft state
  * @pd_list:				pd_list structure
@@ -3906,42 +4081,72 @@ megasas_get_pd_list(struct megasas_instance *instance)
 
 	if (instance->ctrl_context && !instance->mask_interrupts)
 		ret = megasas_issue_blocked_cmd(instance, cmd,
-			MEGASAS_BLOCKED_CMD_TIMEOUT);
+			MFI_IO_TIMEOUT_SECS);
 	else
 		ret = megasas_issue_polled(instance, cmd);
 
-	/*
-	 * the following function will get the instance PD LIST.
-	 */
+	switch (ret) {
+	case DCMD_FAILED:
+		megaraid_sas_kill_hba(instance);
+		break;
+	case DCMD_TIMEOUT:
+
+		switch (dcmd_timeout_ocr_possible(instance)) {
+		case INITIATE_OCR:
+			cmd->flags |= DRV_DCMD_SKIP_REFIRE;
+			/*
+			 * DCMD failed from AEN path.
+			 * AEN path already hold reset_mutex to avoid PCI access
+			 * while OCR is in progress.
+			 */
+			mutex_unlock(&instance->reset_mutex);
+			megasas_reset_fusion(instance->host,
+						MFI_IO_TIMEOUT_OCR);
+			mutex_lock(&instance->reset_mutex);
+			break;
+		case KILL_ADAPTER:
+			megaraid_sas_kill_hba(instance);
+			break;
+		case IGNORE_TIMEOUT:
+			dev_info(&instance->pdev->dev, "Ignore DCMD timeout: %s %d \n",
+				__func__, __LINE__);
+			break;
+		}
 
-	pd_addr = ci->addr;
+		break;
+
+	case DCMD_SUCCESS:
+		pd_addr = ci->addr;
 
-	if (ret == 0 &&
-	     (le32_to_cpu(ci->count) <
-		  (MEGASAS_MAX_PD_CHANNELS * MEGASAS_MAX_DEV_PER_CHANNEL))) {
+		if ((le32_to_cpu(ci->count) >
+			(MEGASAS_MAX_PD_CHANNELS * MEGASAS_MAX_DEV_PER_CHANNEL)))
+			break;
 
 		memset(instance->local_pd_list, 0,
-			MEGASAS_MAX_PD * sizeof(struct megasas_pd_list));
+				MEGASAS_MAX_PD * sizeof(struct megasas_pd_list));
 
 		for (pd_index = 0; pd_index < le32_to_cpu(ci->count); pd_index++) {
-
 			instance->local_pd_list[le16_to_cpu(pd_addr->deviceId)].tid	=
-				le16_to_cpu(pd_addr->deviceId);
+					le16_to_cpu(pd_addr->deviceId);
 			instance->local_pd_list[le16_to_cpu(pd_addr->deviceId)].driveType	=
-							pd_addr->scsiDevType;
+					pd_addr->scsiDevType;
 			instance->local_pd_list[le16_to_cpu(pd_addr->deviceId)].driveState	=
-							MR_PD_STATE_SYSTEM;
+					MR_PD_STATE_SYSTEM;
 			pd_addr++;
 		}
+
 		memcpy(instance->pd_list, instance->local_pd_list,
 			sizeof(instance->pd_list));
+		break;
+
 	}
 
 	pci_free_consistent(instance->pdev,
 				MEGASAS_MAX_PD * sizeof(struct MR_PD_LIST),
 				ci, ci_h);
 
-	megasas_return_cmd(instance, cmd);
+	if (ret != DCMD_TIMEOUT)
+		megasas_return_cmd(instance, cmd);
 
 	return ret;
 }
@@ -4002,33 +4207,63 @@ megasas_get_ld_list(struct megasas_instance *instance)
 
 	if (instance->ctrl_context && !instance->mask_interrupts)
 		ret = megasas_issue_blocked_cmd(instance, cmd,
-			MEGASAS_BLOCKED_CMD_TIMEOUT);
+			MFI_IO_TIMEOUT_SECS);
 	else
 		ret = megasas_issue_polled(instance, cmd);
 
-
 	ld_count = le32_to_cpu(ci->ldCount);
 
-	/* the following function will get the instance PD LIST */
+	switch (ret) {
+	case DCMD_FAILED:
+		megaraid_sas_kill_hba(instance);
+		break;
+	case DCMD_TIMEOUT:
+
+		switch (dcmd_timeout_ocr_possible(instance)) {
+		case INITIATE_OCR:
+			cmd->flags |= DRV_DCMD_SKIP_REFIRE;
+			/*
+			 * DCMD failed from AEN path.
+			 * AEN path already hold reset_mutex to avoid PCI access
+			 * while OCR is in progress.
+			 */
+			mutex_unlock(&instance->reset_mutex);
+			megasas_reset_fusion(instance->host,
+						MFI_IO_TIMEOUT_OCR);
+			mutex_lock(&instance->reset_mutex);
+			break;
+		case KILL_ADAPTER:
+			megaraid_sas_kill_hba(instance);
+			break;
+		case IGNORE_TIMEOUT:
+			dev_info(&instance->pdev->dev, "Ignore DCMD timeout: %s %d\n",
+				__func__, __LINE__);
+			break;
+		}
+
+		break;
+
+	case DCMD_SUCCESS:
+		if (ld_count > instance->fw_supported_vd_count)
+			break;
 
-	if ((ret == 0) && (ld_count <= instance->fw_supported_vd_count)) {
 		memset(instance->ld_ids, 0xff, MAX_LOGICAL_DRIVES_EXT);
 
 		for (ld_index = 0; ld_index < ld_count; ld_index++) {
 			if (ci->ldList[ld_index].state != 0) {
 				ids = ci->ldList[ld_index].ref.targetId;
-				instance->ld_ids[ids] =
-					ci->ldList[ld_index].ref.targetId;
+				instance->ld_ids[ids] = ci->ldList[ld_index].ref.targetId;
 			}
 		}
+
+		break;
 	}
 
-	pci_free_consistent(instance->pdev,
-				sizeof(struct MR_LD_LIST),
-				ci,
-				ci_h);
+	pci_free_consistent(instance->pdev, sizeof(struct MR_LD_LIST), ci, ci_h);
+
+	if (ret != DCMD_TIMEOUT)
+		megasas_return_cmd(instance, cmd);
 
-	megasas_return_cmd(instance, cmd);
 	return ret;
 }
 
@@ -4090,26 +4325,61 @@ megasas_ld_list_query(struct megasas_instance *instance, u8 query_type)
 	dcmd->pad_0  = 0;
 
 	if (instance->ctrl_context && !instance->mask_interrupts)
-		ret = megasas_issue_blocked_cmd(instance, cmd,
-			MEGASAS_BLOCKED_CMD_TIMEOUT);
+		ret = megasas_issue_blocked_cmd(instance, cmd, MFI_IO_TIMEOUT_SECS);
 	else
 		ret = megasas_issue_polled(instance, cmd);
 
-	tgtid_count = le32_to_cpu(ci->count);
+	switch (ret) {
+	case DCMD_FAILED:
+		dev_info(&instance->pdev->dev,
+			"DCMD not supported by firmware - %s %d\n",
+				__func__, __LINE__);
+		ret = megasas_get_ld_list(instance);
+		break;
+	case DCMD_TIMEOUT:
+		switch (dcmd_timeout_ocr_possible(instance)) {
+		case INITIATE_OCR:
+			cmd->flags |= DRV_DCMD_SKIP_REFIRE;
+			/*
+			 * DCMD failed from AEN path.
+			 * AEN path already hold reset_mutex to avoid PCI access
+			 * while OCR is in progress.
+			 */
+			mutex_unlock(&instance->reset_mutex);
+			megasas_reset_fusion(instance->host,
+						MFI_IO_TIMEOUT_OCR);
+			mutex_lock(&instance->reset_mutex);
+			break;
+		case KILL_ADAPTER:
+			megaraid_sas_kill_hba(instance);
+			break;
+		case IGNORE_TIMEOUT:
+			dev_info(&instance->pdev->dev, "Ignore DCMD timeout: %s %d\n",
+				__func__, __LINE__);
+			break;
+		}
+
+		break;
+	case DCMD_SUCCESS:
+		tgtid_count = le32_to_cpu(ci->count);
+
+		if ((tgtid_count > (instance->fw_supported_vd_count)))
+			break;
 
-	if ((ret == 0) && (tgtid_count <= (instance->fw_supported_vd_count))) {
 		memset(instance->ld_ids, 0xff, MEGASAS_MAX_LD_IDS);
 		for (ld_index = 0; ld_index < tgtid_count; ld_index++) {
 			ids = ci->targetId[ld_index];
 			instance->ld_ids[ids] = ci->targetId[ld_index];
 		}
 
+		break;
 	}
 
 	pci_free_consistent(instance->pdev, sizeof(struct MR_LD_TARGETID_LIST),
-			    ci, ci_h);
+		    ci, ci_h);
 
-	megasas_return_cmd(instance, cmd);
+	if (ret != DCMD_TIMEOUT)
+		megasas_return_cmd(instance, cmd);
 
 	return ret;
 }
@@ -4223,38 +4493,73 @@ megasas_get_ctrl_info(struct megasas_instance *instance)
 	dcmd->mbox.b[0] = 1;
 
 	if (instance->ctrl_context && !instance->mask_interrupts)
-		ret = megasas_issue_blocked_cmd(instance, cmd,
-			MEGASAS_BLOCKED_CMD_TIMEOUT);
+		ret = megasas_issue_blocked_cmd(instance, cmd, MFI_IO_TIMEOUT_SECS);
 	else
 		ret = megasas_issue_polled(instance, cmd);
 
-	if (!ret) {
+	switch (ret) {
+	case DCMD_SUCCESS:
 		memcpy(ctrl_info, ci, sizeof(struct megasas_ctrl_info));
+		/* Save required controller information in
+		 * CPU endianness format.
+		 */
 		le32_to_cpus((u32 *)&ctrl_info->properties.OnOffProperties);
 		le32_to_cpus((u32 *)&ctrl_info->adapterOperations2);
 		le32_to_cpus((u32 *)&ctrl_info->adapterOperations3);
+
+		/* Update the latest Ext VD info.
+		 * From Init path, store current firmware details.
+		 * From OCR path, detect any firmware properties changes.
+		 * in case of Firmware upgrade without system reboot.
+		 */
 		megasas_update_ext_vd_details(instance);
 		instance->use_seqnum_jbod_fp =
 			ctrl_info->adapterOperations3.useSeqNumJbodFP;
+
+		/*Check whether controller is iMR or MR */
 		instance->is_imr = (ctrl_info->memory_size ? 0 : 1);
 		dev_info(&instance->pdev->dev,
-				"controller type\t: %s(%dMB)\n",
-				instance->is_imr ? "iMR" : "MR",
-				le16_to_cpu(ctrl_info->memory_size));
+			"controller type\t: %s(%dMB)\n",
+			instance->is_imr ? "iMR" : "MR",
+			le16_to_cpu(ctrl_info->memory_size));
+
 		instance->disableOnlineCtrlReset =
 			ctrl_info->properties.OnOffProperties.disableOnlineCtrlReset;
-		dev_info(&instance->pdev->dev, "Online Controller Reset(OCR)\t: %s\n",
-			instance->disableOnlineCtrlReset ? "Disabled" : "Enabled");
 		instance->secure_jbod_support =
 			ctrl_info->adapterOperations3.supportSecurityonJBOD;
+		dev_info(&instance->pdev->dev, "Online Controller Reset(OCR)\t: %s\n",
+			instance->disableOnlineCtrlReset ? "Disabled" : "Enabled");
 		dev_info(&instance->pdev->dev, "Secure JBOD support\t: %s\n",
 			instance->secure_jbod_support ? "Yes" : "No");
+		break;
+
+	case DCMD_TIMEOUT:
+		switch (dcmd_timeout_ocr_possible(instance)) {
+		case INITIATE_OCR:
+			cmd->flags |= DRV_DCMD_SKIP_REFIRE;
+			megasas_reset_fusion(instance->host,
+				MFI_IO_TIMEOUT_OCR);
+			break;
+		case KILL_ADAPTER:
+			megaraid_sas_kill_hba(instance);
+			break;
+		case IGNORE_TIMEOUT:
+			dev_info(&instance->pdev->dev, "Ignore DCMD timeout: %s %d\n",
+				__func__, __LINE__);
+			break;
+		}
+	case DCMD_FAILED:
+		megaraid_sas_kill_hba(instance);
+		break;
+
 	}
 
 	pci_free_consistent(instance->pdev, sizeof(struct megasas_ctrl_info),
 			    ci, ci_h);
 
 	megasas_return_cmd(instance, cmd);
+
+
 	return ret;
 }
 
@@ -4304,12 +4609,28 @@ int megasas_set_crash_dump_params(struct megasas_instance *instance,
 	dcmd->sgl.sge32[0].length = cpu_to_le32(CRASH_DMA_BUF_SIZE);
 
 	if (instance->ctrl_context && !instance->mask_interrupts)
-		ret = megasas_issue_blocked_cmd(instance, cmd,
-			MEGASAS_BLOCKED_CMD_TIMEOUT);
+		ret = megasas_issue_blocked_cmd(instance, cmd, MFI_IO_TIMEOUT_SECS);
 	else
 		ret = megasas_issue_polled(instance, cmd);
 
-	megasas_return_cmd(instance, cmd);
+	if (ret == DCMD_TIMEOUT) {
+		switch (dcmd_timeout_ocr_possible(instance)) {
+		case INITIATE_OCR:
+			cmd->flags |= DRV_DCMD_SKIP_REFIRE;
+			megasas_reset_fusion(instance->host,
+					MFI_IO_TIMEOUT_OCR);
+			break;
+		case KILL_ADAPTER:
+			megaraid_sas_kill_hba(instance);
+			break;
+		case IGNORE_TIMEOUT:
+			dev_info(&instance->pdev->dev, "Ignore DCMD timeout: %s %d\n",
+				__func__, __LINE__);
+			break;
+		}
+	} else
+		megasas_return_cmd(instance, cmd);
+
 	return ret;
 }
 
@@ -4426,6 +4747,7 @@ megasas_init_adapter_mfi(struct megasas_instance *instance)
 		sema_init(&instance->ioctl_sem, (MEGASAS_MFI_IOCTL_CMDS));
 	}
 
+	instance->cur_can_queue = instance->max_scsi_cmds;
 	/*
 	 * Create a pool of commands
 	 */
@@ -4756,6 +5078,9 @@ static int megasas_init_fw(struct megasas_instance *instance)
 				instance->msix_vectors = ((scratch_pad_2
 					& MR_MAX_REPLY_QUEUES_EXT_OFFSET)
 					>> MR_MAX_REPLY_QUEUES_EXT_OFFSET_SHIFT) + 1;
+				if (rdpq_enable)
+					instance->is_rdpq = (scratch_pad_2 & MR_RDPQ_MODE_OFFSET) ?
+								1 : 0;
 				fw_msix_count = instance->msix_vectors;
 				/* Save 1-15 reply post index address to local memory
 				 * Index 0 is already saved from reg offset
@@ -4792,6 +5117,8 @@ static int megasas_init_fw(struct megasas_instance *instance)
 	dev_info(&instance->pdev->dev,
 		"current msix/online cpus\t: (%d/%d)\n",
 		instance->msix_vectors, (unsigned int)num_online_cpus());
+	dev_info(&instance->pdev->dev,
+		"RDPQ mode\t: (%s)\n", instance->is_rdpq ? "enabled" : "disabled");
 
 	tasklet_init(&instance->isr_tasklet, instance->instancet->tasklet,
 		(unsigned long)instance);
@@ -4856,7 +5183,9 @@ static int megasas_init_fw(struct megasas_instance *instance)
 
 	tmp_sectors = min_t(u32, max_sectors_1, max_sectors_2);
 
-	instance->mpio = ctrl_info->adapterOperations2.mpio;
+	instance->peerIsPresent = ctrl_info->cluster.peerIsPresent;
+	instance->passive = ctrl_info->cluster.passive;
+	memcpy(instance->clusterId, ctrl_info->clusterId, sizeof(instance->clusterId));
 	instance->UnevenSpanSupport =
 		ctrl_info->adapterOperations2.supportUnevenSpans;
 	if (instance->UnevenSpanSupport) {
@@ -4932,6 +5261,11 @@ static int megasas_init_fw(struct megasas_instance *instance)
 		instance->throttlequeuedepth =
 				MEGASAS_THROTTLE_QUEUE_DEPTH;
 
+	if (resetwaittime > MEGASAS_RESET_WAIT_TIME)
+		resetwaittime = MEGASAS_RESET_WAIT_TIME;
+
+	if ((scmd_timeout < 10) || (scmd_timeout > MEGASAS_DEFAULT_CMD_TIMEOUT))
+		scmd_timeout = MEGASAS_DEFAULT_CMD_TIMEOUT;
 
 	/* Launch SR-IOV heartbeat timer */
 	if (instance->requestorId) {
@@ -5035,10 +5369,8 @@ megasas_get_seq_num(struct megasas_instance *instance,
 	dcmd->sgl.sge32[0].phys_addr = cpu_to_le32(el_info_h);
 	dcmd->sgl.sge32[0].length = cpu_to_le32(sizeof(struct megasas_evt_log_info));
 
-	if (megasas_issue_blocked_cmd(instance, cmd, 30))
-		dev_err(&instance->pdev->dev, "Command timedout"
-			"from %s\n", __func__);
-	else {
+	if (megasas_issue_blocked_cmd(instance, cmd, MFI_IO_TIMEOUT_SECS) ==
+		DCMD_SUCCESS) {
 		/*
 		 * Copy the data back into callers buffer
 		 */
@@ -5047,7 +5379,9 @@ megasas_get_seq_num(struct megasas_instance *instance,
 		eli->clear_seq_num = el_info->clear_seq_num;
 		eli->shutdown_seq_num = el_info->shutdown_seq_num;
 		eli->boot_seq_num = el_info->boot_seq_num;
-	}
+	} else
+		dev_err(&instance->pdev->dev, "DCMD failed "
+			"from %s\n", __func__);
 
 	pci_free_consistent(instance->pdev, sizeof(struct megasas_evt_log_info),
 			    el_info, el_info_h);
@@ -5262,6 +5596,8 @@ static int megasas_io_attach(struct megasas_instance *instance)
 	if (instance->ctrl_context) {
 		host->hostt->eh_device_reset_handler = NULL;
 		host->hostt->eh_bus_reset_handler = NULL;
+		host->hostt->eh_target_reset_handler = megasas_reset_target_fusion;
+		host->hostt->eh_abort_handler = megasas_task_abort_fusion;
 	}
 
 	/*
@@ -5447,7 +5783,7 @@ static int megasas_probe_one(struct pci_dev *pdev,
 	instance->flag_ieee = 0;
 	instance->ev = NULL;
 	instance->issuepend_done = 1;
-	instance->adprecovery = MEGASAS_HBA_OPERATIONAL;
+	atomic_set(&instance->adprecovery, MEGASAS_HBA_OPERATIONAL);
 	instance->is_imr = 0;
 
 	instance->evt_detail = pci_alloc_consistent(pdev,
@@ -5461,6 +5797,12 @@ static int megasas_probe_one(struct pci_dev *pdev,
 		goto fail_alloc_dma_buf;
 	}
 
+	instance->pd_info = pci_alloc_consistent(pdev,
+		sizeof(struct MR_PD_INFO), &instance->pd_info_h);
+
+	if (!instance->pd_info)
+		dev_err(&instance->pdev->dev, "Failed to alloc mem for pd_info\n");
+
 	/*
 	 * Initialize locks and queues
 	 */
@@ -5476,8 +5818,8 @@ static int megasas_probe_one(struct pci_dev *pdev,
 	spin_lock_init(&instance->hba_lock);
 	spin_lock_init(&instance->completion_lock);
 
-	mutex_init(&instance->aen_mutex);
 	mutex_init(&instance->reset_mutex);
+	mutex_init(&instance->hba_mutex);
 
 	/*
 	 * Initialize PCI related and misc parameters
@@ -5592,6 +5934,10 @@ fail_alloc_dma_buf:
 				    instance->evt_detail,
 				    instance->evt_detail_h);
 
+	if (instance->pd_info)
+		pci_free_consistent(pdev, sizeof(struct MR_PD_INFO),
+					instance->pd_info,
+					instance->pd_info_h);
 	if (instance->producer)
 		pci_free_consistent(pdev, sizeof(u32), instance->producer,
 				    instance->producer_h);
@@ -5616,7 +5962,7 @@ static void megasas_flush_cache(struct megasas_instance *instance)
 	struct megasas_cmd *cmd;
 	struct megasas_dcmd_frame *dcmd;
 
-	if (instance->adprecovery == MEGASAS_HW_CRITICAL_ERROR)
+	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR)
 		return;
 
 	cmd = megasas_get_cmd(instance);
@@ -5638,9 +5984,12 @@ static void megasas_flush_cache(struct megasas_instance *instance)
 	dcmd->opcode = cpu_to_le32(MR_DCMD_CTRL_CACHE_FLUSH);
 	dcmd->mbox.b[0] = MR_FLUSH_CTRL_CACHE | MR_FLUSH_DISK_CACHE;
 
-	if (megasas_issue_blocked_cmd(instance, cmd, 30))
-		dev_err(&instance->pdev->dev, "Command timedout"
-			" from %s\n", __func__);
+	if (megasas_issue_blocked_cmd(instance, cmd, MFI_IO_TIMEOUT_SECS)
+			!= DCMD_SUCCESS) {
+		dev_err(&instance->pdev->dev,
+			"return from %s %d\n", __func__, __LINE__);
+		return;
+	}
 
 	megasas_return_cmd(instance, cmd);
 }
@@ -5656,7 +6005,7 @@ static void megasas_shutdown_controller(struct megasas_instance *instance,
 	struct megasas_cmd *cmd;
 	struct megasas_dcmd_frame *dcmd;
 
-	if (instance->adprecovery == MEGASAS_HW_CRITICAL_ERROR)
+	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR)
 		return;
 
 	cmd = megasas_get_cmd(instance);
@@ -5666,13 +6015,13 @@ static void megasas_shutdown_controller(struct megasas_instance *instance,
 
 	if (instance->aen_cmd)
 		megasas_issue_blocked_abort_cmd(instance,
-			instance->aen_cmd, MEGASAS_BLOCKED_CMD_TIMEOUT);
+			instance->aen_cmd, MFI_IO_TIMEOUT_SECS);
 	if (instance->map_update_cmd)
 		megasas_issue_blocked_abort_cmd(instance,
-			instance->map_update_cmd, MEGASAS_BLOCKED_CMD_TIMEOUT);
+			instance->map_update_cmd, MFI_IO_TIMEOUT_SECS);
 	if (instance->jbod_seq_cmd)
 		megasas_issue_blocked_abort_cmd(instance,
-			instance->jbod_seq_cmd, MEGASAS_BLOCKED_CMD_TIMEOUT);
+			instance->jbod_seq_cmd, MFI_IO_TIMEOUT_SECS);
 
 	dcmd = &cmd->frame->dcmd;
 
@@ -5687,9 +6036,12 @@ static void megasas_shutdown_controller(struct megasas_instance *instance,
 	dcmd->data_xfer_len = 0;
 	dcmd->opcode = cpu_to_le32(opcode);
 
-	if (megasas_issue_blocked_cmd(instance, cmd, 30))
-		dev_err(&instance->pdev->dev, "Command timedout"
-			"from %s\n", __func__);
+	if (megasas_issue_blocked_cmd(instance, cmd, MFI_IO_TIMEOUT_SECS)
+			!= DCMD_SUCCESS) {
+		dev_err(&instance->pdev->dev,
+			"return from %s %d\n", __func__, __LINE__);
+		return;
+	}
 
 	megasas_return_cmd(instance, cmd);
 }
@@ -5847,6 +6199,10 @@ fail_init_mfi:
 				instance->evt_detail,
 				instance->evt_detail_h);
 
+	if (instance->pd_info)
+		pci_free_consistent(pdev, sizeof(struct MR_PD_INFO),
+					instance->pd_info,
+					instance->pd_info_h);
 	if (instance->producer)
 		pci_free_consistent(pdev, sizeof(u32), instance->producer,
 				instance->producer_h);
@@ -5941,11 +6297,11 @@ static void megasas_detach_one(struct pci_dev *pdev)
 			if (fusion->ld_drv_map[i])
 				free_pages((ulong)fusion->ld_drv_map[i],
 					fusion->drv_map_pages);
-				if (fusion->pd_seq_sync)
-					dma_free_coherent(&instance->pdev->dev,
-						pd_seq_map_sz,
-						fusion->pd_seq_sync[i],
-						fusion->pd_seq_phys[i]);
+			if (fusion->pd_seq_sync[i])
+				dma_free_coherent(&instance->pdev->dev,
+					pd_seq_map_sz,
+					fusion->pd_seq_sync[i],
+					fusion->pd_seq_phys[i]);
 		}
 		free_pages((ulong)instance->ctrl_context,
 			instance->ctrl_context_pages);
@@ -5965,6 +6321,10 @@ static void megasas_detach_one(struct pci_dev *pdev)
 		pci_free_consistent(pdev, sizeof(struct megasas_evt_detail),
 				instance->evt_detail, instance->evt_detail_h);
 
+	if (instance->pd_info)
+		pci_free_consistent(pdev, sizeof(struct MR_PD_INFO),
+					instance->pd_info,
+					instance->pd_info_h);
 	if (instance->vf_affiliation)
 		pci_free_consistent(pdev, (MAX_LOGICAL_DRIVES + 1) *
 				    sizeof(struct MR_LD_VF_AFFILIATION),
@@ -6090,7 +6450,7 @@ static int megasas_set_crash_dump_params_ioctl(struct megasas_cmd *cmd)
 	for (i = 0; i < megasas_mgmt_info.max_index; i++) {
 		local_instance = megasas_mgmt_info.instance[i];
 		if (local_instance && local_instance->crash_dump_drv_support) {
-			if ((local_instance->adprecovery ==
+			if ((atomic_read(&local_instance->adprecovery) ==
 				MEGASAS_HBA_OPERATIONAL) &&
 				!megasas_set_crash_dump_params(local_instance,
 					crash_support)) {
@@ -6227,7 +6587,15 @@ megasas_mgmt_fw_ioctl(struct megasas_instance *instance,
 	 * cmd to the SCSI mid-layer
 	 */
 	cmd->sync_cmd = 1;
-	megasas_issue_blocked_cmd(instance, cmd, 0);
+	if (megasas_issue_blocked_cmd(instance, cmd, 0) == DCMD_NOT_FIRED) {
+		cmd->sync_cmd = 0;
+		dev_err(&instance->pdev->dev,
+			"return -EBUSY from %s %d opcode 0x%x cmd->cmd_status_drv 0x%x\n",
+			__func__, __LINE__, cmd->frame->dcmd.opcode,
+			cmd->cmd_status_drv);
+		return -EBUSY;
+	}
+
 	cmd->sync_cmd = 0;
 
 	if (instance->unload == 1) {
@@ -6330,7 +6698,7 @@ static int megasas_mgmt_ioctl_fw(struct file *file, unsigned long arg)
 		goto out_kfree_ioc;
 	}
 
-	if (instance->adprecovery == MEGASAS_HW_CRITICAL_ERROR) {
+	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
 		dev_err(&instance->pdev->dev, "Controller in crit error\n");
 		error = -ENODEV;
 		goto out_kfree_ioc;
@@ -6349,7 +6717,7 @@ static int megasas_mgmt_ioctl_fw(struct file *file, unsigned long arg)
 	for (i = 0; i < wait_time; i++) {
 
 		spin_lock_irqsave(&instance->hba_lock, flags);
-		if (instance->adprecovery == MEGASAS_HBA_OPERATIONAL) {
+		if (atomic_read(&instance->adprecovery) == MEGASAS_HBA_OPERATIONAL) {
 			spin_unlock_irqrestore(&instance->hba_lock, flags);
 			break;
 		}
@@ -6364,7 +6732,7 @@ static int megasas_mgmt_ioctl_fw(struct file *file, unsigned long arg)
 	}
 
 	spin_lock_irqsave(&instance->hba_lock, flags);
-	if (instance->adprecovery != MEGASAS_HBA_OPERATIONAL) {
+	if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL) {
 		spin_unlock_irqrestore(&instance->hba_lock, flags);
 
 		dev_err(&instance->pdev->dev, "timed out while"
@@ -6406,7 +6774,7 @@ static int megasas_mgmt_ioctl_aen(struct file *file, unsigned long arg)
 	if (!instance)
 		return -ENODEV;
 
-	if (instance->adprecovery == MEGASAS_HW_CRITICAL_ERROR) {
+	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
 		return -ENODEV;
 	}
 
@@ -6417,7 +6785,7 @@ static int megasas_mgmt_ioctl_aen(struct file *file, unsigned long arg)
 	for (i = 0; i < wait_time; i++) {
 
 		spin_lock_irqsave(&instance->hba_lock, flags);
-		if (instance->adprecovery == MEGASAS_HBA_OPERATIONAL) {
+		if (atomic_read(&instance->adprecovery) == MEGASAS_HBA_OPERATIONAL) {
 			spin_unlock_irqrestore(&instance->hba_lock,
 						flags);
 			break;
@@ -6434,7 +6802,7 @@ static int megasas_mgmt_ioctl_aen(struct file *file, unsigned long arg)
 	}
 
 	spin_lock_irqsave(&instance->hba_lock, flags);
-	if (instance->adprecovery != MEGASAS_HBA_OPERATIONAL) {
+	if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL) {
 		spin_unlock_irqrestore(&instance->hba_lock, flags);
 		dev_err(&instance->pdev->dev, "timed out while waiting"
 				"for HBA to recover\n");
@@ -6442,10 +6810,10 @@ static int megasas_mgmt_ioctl_aen(struct file *file, unsigned long arg)
 	}
 	spin_unlock_irqrestore(&instance->hba_lock, flags);
 
-	mutex_lock(&instance->aen_mutex);
+	mutex_lock(&instance->reset_mutex);
 	error = megasas_register_aen(instance, aen.seq_num,
 				     aen.class_locale_word);
-	mutex_unlock(&instance->aen_mutex);
+	mutex_unlock(&instance->reset_mutex);
 	return error;
 }
 
@@ -6476,9 +6844,9 @@ static int megasas_mgmt_compat_ioctl_fw(struct file *file, unsigned long arg)
 	int i;
 	int error = 0;
 	compat_uptr_t ptr;
-	unsigned long local_raw_ptr;
 	u32 local_sense_off;
 	u32 local_sense_len;
+	u32 user_sense_off;
 
 	if (clear_user(ioc, sizeof(*ioc)))
 		return -EFAULT;
@@ -6496,17 +6864,16 @@ static int megasas_mgmt_compat_ioctl_fw(struct file *file, unsigned long arg)
 	 * sense_len is not null, so prepare the 64bit value under
 	 * the same condition.
 	 */
-	if (get_user(local_raw_ptr, ioc->frame.raw) ||
-		get_user(local_sense_off, &ioc->sense_off) ||
-		get_user(local_sense_len, &ioc->sense_len))
+	if (get_user(local_sense_off, &ioc->sense_off) ||
+		get_user(local_sense_len, &ioc->sense_len) ||
+		get_user(user_sense_off, &cioc->sense_off))
 		return -EFAULT;
 
-
 	if (local_sense_len) {
 		void __user **sense_ioc_ptr =
-			(void __user **)((u8*)local_raw_ptr + local_sense_off);
+			(void __user **)((u8 *)((unsigned long)&ioc->frame.raw) + local_sense_off);
 		compat_uptr_t *sense_cioc_ptr =
-			(compat_uptr_t *)(cioc->frame.raw + cioc->sense_off);
+			(compat_uptr_t *)(((unsigned long)&cioc->frame.raw) + user_sense_off);
 		if (get_user(ptr, sense_cioc_ptr) ||
 		    put_user(compat_ptr(ptr), sense_ioc_ptr))
 			return -EFAULT;
@@ -6647,6 +7014,7 @@ megasas_aen_polling(struct work_struct *work)
 	int     i, j, doscan = 0;
 	u32 seq_num, wait_time = MEGASAS_RESET_WAIT_TIME;
 	int error;
+	u8  dcmd_ret = DCMD_SUCCESS;
 
 	if (!instance) {
 		printk(KERN_ERR "invalid instance!\n");
@@ -6659,16 +7027,7 @@ megasas_aen_polling(struct work_struct *work)
 		wait_time = MEGASAS_ROUTINE_WAIT_TIME_VF;
 
 	/* Don't run the event workqueue thread if OCR is running */
-	for (i = 0; i < wait_time; i++) {
-		if (instance->adprecovery == MEGASAS_HBA_OPERATIONAL)
-			break;
-		if (!(i % MEGASAS_RESET_NOTICE_INTERVAL)) {
-			dev_notice(&instance->pdev->dev, "%s waiting for "
-			       "controller reset to finish for scsi%d\n",
-			       __func__, instance->host->host_no);
-		}
-		msleep(1000);
-	}
+	mutex_lock(&instance->reset_mutex);
 
 	instance->ev = NULL;
 	host = instance->host;
@@ -6676,212 +7035,127 @@ megasas_aen_polling(struct work_struct *work)
 		megasas_decode_evt(instance);
 
 		switch (le32_to_cpu(instance->evt_detail->code)) {
-		case MR_EVT_PD_INSERTED:
-			if (megasas_get_pd_list(instance) == 0) {
-			for (i = 0; i < MEGASAS_MAX_PD_CHANNELS; i++) {
-				for (j = 0;
-				j < MEGASAS_MAX_DEV_PER_CHANNEL;
-				j++) {
-
-				pd_index =
-				(i * MEGASAS_MAX_DEV_PER_CHANNEL) + j;
-
-				sdev1 = scsi_device_lookup(host, i, j, 0);
-
-				if (instance->pd_list[pd_index].driveState
-						== MR_PD_STATE_SYSTEM) {
-					if (!sdev1)
-						scsi_add_device(host, i, j, 0);
-
-					if (sdev1)
-						scsi_device_put(sdev1);
-					}
-				}
-			}
-			}
-			doscan = 0;
-			break;
 
+		case MR_EVT_PD_INSERTED:
 		case MR_EVT_PD_REMOVED:
-			if (megasas_get_pd_list(instance) == 0) {
-			for (i = 0; i < MEGASAS_MAX_PD_CHANNELS; i++) {
-				for (j = 0;
-				j < MEGASAS_MAX_DEV_PER_CHANNEL;
-				j++) {
-
-				pd_index =
-				(i * MEGASAS_MAX_DEV_PER_CHANNEL) + j;
-
-				sdev1 = scsi_device_lookup(host, i, j, 0);
-
-				if (instance->pd_list[pd_index].driveState
-					== MR_PD_STATE_SYSTEM) {
-					if (sdev1)
-						scsi_device_put(sdev1);
-				} else {
-					if (sdev1) {
-						scsi_remove_device(sdev1);
-						scsi_device_put(sdev1);
-					}
-				}
-				}
-			}
-			}
-			doscan = 0;
+			dcmd_ret = megasas_get_pd_list(instance);
+			if (dcmd_ret == DCMD_SUCCESS)
+				doscan = SCAN_PD_CHANNEL;
 			break;
 
 		case MR_EVT_LD_OFFLINE:
 		case MR_EVT_CFG_CLEARED:
 		case MR_EVT_LD_DELETED:
-			if (!instance->requestorId ||
-			    megasas_get_ld_vf_affiliation(instance, 0)) {
-				if (megasas_ld_list_query(instance,
-							  MR_LD_QUERY_TYPE_EXPOSED_TO_HOST))
-					megasas_get_ld_list(instance);
-				for (i = 0; i < MEGASAS_MAX_LD_CHANNELS; i++) {
-					for (j = 0;
-					     j < MEGASAS_MAX_DEV_PER_CHANNEL;
-					     j++) {
-
-						ld_index =
-							(i * MEGASAS_MAX_DEV_PER_CHANNEL) + j;
-
-						sdev1 = scsi_device_lookup(host, MEGASAS_MAX_PD_CHANNELS + i, j, 0);
-
-						if (instance->ld_ids[ld_index]
-						    != 0xff) {
-							if (sdev1)
-								scsi_device_put(sdev1);
-						} else {
-							if (sdev1) {
-								scsi_remove_device(sdev1);
-								scsi_device_put(sdev1);
-							}
-						}
-					}
-				}
-				doscan = 0;
-			}
-			break;
 		case MR_EVT_LD_CREATED:
 			if (!instance->requestorId ||
-			    megasas_get_ld_vf_affiliation(instance, 0)) {
-				if (megasas_ld_list_query(instance,
-							  MR_LD_QUERY_TYPE_EXPOSED_TO_HOST))
-					megasas_get_ld_list(instance);
-				for (i = 0; i < MEGASAS_MAX_LD_CHANNELS; i++) {
-					for (j = 0;
-					     j < MEGASAS_MAX_DEV_PER_CHANNEL;
-					     j++) {
-						ld_index =
-							(i * MEGASAS_MAX_DEV_PER_CHANNEL) + j;
-
-						sdev1 = scsi_device_lookup(host, MEGASAS_MAX_PD_CHANNELS + i, j, 0);
-
-						if (instance->ld_ids[ld_index]
-						    != 0xff) {
-							if (!sdev1)
-								scsi_add_device(host, MEGASAS_MAX_PD_CHANNELS + i, j, 0);
-						}
-						if (sdev1)
-							scsi_device_put(sdev1);
-					}
-				}
-				doscan = 0;
-			}
+				(instance->requestorId && megasas_get_ld_vf_affiliation(instance, 0)))
+				dcmd_ret = megasas_ld_list_query(instance, MR_LD_QUERY_TYPE_EXPOSED_TO_HOST);
+
+			if (dcmd_ret == DCMD_SUCCESS)
+				doscan = SCAN_VD_CHANNEL;
+
 			break;
+
 		case MR_EVT_CTRL_HOST_BUS_SCAN_REQUESTED:
 		case MR_EVT_FOREIGN_CFG_IMPORTED:
 		case MR_EVT_LD_STATE_CHANGE:
-			doscan = 1;
+			dcmd_ret = megasas_get_pd_list(instance);
+
+			if (dcmd_ret != DCMD_SUCCESS)
+				break;
+
+			if (!instance->requestorId ||
+				(instance->requestorId && megasas_get_ld_vf_affiliation(instance, 0)))
+				dcmd_ret = megasas_ld_list_query(instance, MR_LD_QUERY_TYPE_EXPOSED_TO_HOST);
+
+			if (dcmd_ret != DCMD_SUCCESS)
+				break;
+
+			doscan = SCAN_VD_CHANNEL | SCAN_PD_CHANNEL;
+			dev_info(&instance->pdev->dev, "scanning for scsi%d...\n",
+				instance->host->host_no);
 			break;
+
 		case MR_EVT_CTRL_PROP_CHANGED:
-			megasas_get_ctrl_info(instance);
-			break;
+				dcmd_ret = megasas_get_ctrl_info(instance);
+				break;
 		default:
 			doscan = 0;
 			break;
 		}
 	} else {
 		dev_err(&instance->pdev->dev, "invalid evt_detail!\n");
+		mutex_unlock(&instance->reset_mutex);
 		kfree(ev);
 		return;
 	}
 
-	if (doscan) {
-		dev_info(&instance->pdev->dev, "scanning for scsi%d...\n",
-		       instance->host->host_no);
-		if (megasas_get_pd_list(instance) == 0) {
-			for (i = 0; i < MEGASAS_MAX_PD_CHANNELS; i++) {
-				for (j = 0; j < MEGASAS_MAX_DEV_PER_CHANNEL; j++) {
-					pd_index = i*MEGASAS_MAX_DEV_PER_CHANNEL + j;
-					sdev1 = scsi_device_lookup(host, i, j, 0);
-					if (instance->pd_list[pd_index].driveState ==
-					    MR_PD_STATE_SYSTEM) {
-						if (!sdev1) {
-							scsi_add_device(host, i, j, 0);
-						}
-						if (sdev1)
-							scsi_device_put(sdev1);
-					} else {
-						if (sdev1) {
-							scsi_remove_device(sdev1);
-							scsi_device_put(sdev1);
-						}
+	mutex_unlock(&instance->reset_mutex);
+
+	if (doscan & SCAN_PD_CHANNEL) {
+		for (i = 0; i < MEGASAS_MAX_PD_CHANNELS; i++) {
+			for (j = 0; j < MEGASAS_MAX_DEV_PER_CHANNEL; j++) {
+				pd_index = i*MEGASAS_MAX_DEV_PER_CHANNEL + j;
+				sdev1 = scsi_device_lookup(host, i, j, 0);
+				if (instance->pd_list[pd_index].driveState ==
+							MR_PD_STATE_SYSTEM) {
+					if (!sdev1)
+						scsi_add_device(host, i, j, 0);
+					else
+						scsi_device_put(sdev1);
+				} else {
+					if (sdev1) {
+						scsi_remove_device(sdev1);
+						scsi_device_put(sdev1);
 					}
 				}
 			}
 		}
+	}
 
-		if (!instance->requestorId ||
-		    megasas_get_ld_vf_affiliation(instance, 0)) {
-			if (megasas_ld_list_query(instance,
-						  MR_LD_QUERY_TYPE_EXPOSED_TO_HOST))
-				megasas_get_ld_list(instance);
-			for (i = 0; i < MEGASAS_MAX_LD_CHANNELS; i++) {
-				for (j = 0; j < MEGASAS_MAX_DEV_PER_CHANNEL;
-				     j++) {
-					ld_index =
-						(i * MEGASAS_MAX_DEV_PER_CHANNEL) + j;
-
-					sdev1 = scsi_device_lookup(host,
-								   MEGASAS_MAX_PD_CHANNELS + i, j, 0);
-					if (instance->ld_ids[ld_index]
-					    != 0xff) {
-						if (!sdev1)
-							scsi_add_device(host, MEGASAS_MAX_PD_CHANNELS + i, j, 0);
-						else
-							scsi_device_put(sdev1);
-					} else {
-						if (sdev1) {
-							scsi_remove_device(sdev1);
-							scsi_device_put(sdev1);
-						}
+	if (doscan & SCAN_VD_CHANNEL) {
+		for (i = 0; i < MEGASAS_MAX_LD_CHANNELS; i++) {
+			for (j = 0; j < MEGASAS_MAX_DEV_PER_CHANNEL; j++) {
+				ld_index = (i * MEGASAS_MAX_DEV_PER_CHANNEL) + j;
+				sdev1 = scsi_device_lookup(host, MEGASAS_MAX_PD_CHANNELS + i, j, 0);
+				if (instance->ld_ids[ld_index] != 0xff) {
+					if (!sdev1)
+						scsi_add_device(host, MEGASAS_MAX_PD_CHANNELS + i, j, 0);
+					else
+						scsi_device_put(sdev1);
+				} else {
+					if (sdev1) {
+						scsi_remove_device(sdev1);
+						scsi_device_put(sdev1);
 					}
 				}
 			}
 		}
 	}
 
-	if (instance->aen_cmd != NULL) {
-		kfree(ev);
-		return ;
-	}
-
-	seq_num = le32_to_cpu(instance->evt_detail->seq_num) + 1;
+	if (dcmd_ret == DCMD_SUCCESS)
+		seq_num = le32_to_cpu(instance->evt_detail->seq_num) + 1;
+	else
+		seq_num = instance->last_seq_num;
 
 	/* Register AEN with FW for latest sequence number plus 1 */
 	class_locale.members.reserved = 0;
 	class_locale.members.locale = MR_EVT_LOCALE_ALL;
 	class_locale.members.class = MR_EVT_CLASS_DEBUG;
-	mutex_lock(&instance->aen_mutex);
+
+	if (instance->aen_cmd != NULL) {
+		kfree(ev);
+		return;
+	}
+
+	mutex_lock(&instance->reset_mutex);
 	error = megasas_register_aen(instance, seq_num,
 					class_locale.word);
-	mutex_unlock(&instance->aen_mutex);
-
 	if (error)
-		dev_err(&instance->pdev->dev, "register aen failed error %x\n", error);
+		dev_err(&instance->pdev->dev,
+			"register aen failed error %x\n", error);
 
+	mutex_unlock(&instance->reset_mutex);
 	kfree(ev);
 }
 
diff --git a/drivers/scsi/megaraid/megaraid_sas_fp.c b/drivers/scsi/megaraid/megaraid_sas_fp.c
index 741509b35617..e413113c86ac 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fp.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fp.c
@@ -1020,6 +1020,8 @@ MR_BuildRaidContext(struct megasas_instance *instance,
 	/* assume this IO needs the full row - we'll adjust if not true */
 	regSize             = stripSize;
 
+	io_info->do_fp_rlbypass = raid->capability.fpBypassRegionLock;
+
 	/* Check if we can send this I/O via FastPath */
 	if (raid->capability.fpCapable) {
 		if (isRead)
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 8d630a552b07..98a848bdfdc2 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -91,7 +91,10 @@ void megasas_start_timer(struct megasas_instance *instance,
 			struct timer_list *timer,
 			 void *fn, unsigned long interval);
 extern struct megasas_mgmt_info megasas_mgmt_info;
-extern int resetwaittime;
+extern unsigned int resetwaittime;
+extern unsigned int dual_qdepth_disable;
+static void megasas_free_rdpq_fusion(struct megasas_instance *instance);
+static void megasas_free_reply_fusion(struct megasas_instance *instance);
 
 
 
@@ -201,58 +204,72 @@ megasas_fire_cmd_fusion(struct megasas_instance *instance,
 		&instance->reg_set->inbound_low_queue_port);
 	writel(le32_to_cpu(req_desc->u.high),
 		&instance->reg_set->inbound_high_queue_port);
+	mmiowb();
 	spin_unlock_irqrestore(&instance->hba_lock, flags);
 #endif
 }
 
-
 /**
- * megasas_teardown_frame_pool_fusion -	Destroy the cmd frame DMA pool
- * @instance:				Adapter soft state
+ * megasas_fusion_update_can_queue -	Do all Adapter Queue depth related calculations here
+ * @instance:							Adapter soft state
+ * fw_boot_context:						Whether this function called during probe or after OCR
+ *
+ * This function is only for fusion controllers.
+ * Update host can queue, if firmware downgrade max supported firmware commands.
+ * Firmware upgrade case will be skiped because underlying firmware has
+ * more resource than exposed to the OS.
+ *
  */
-static void megasas_teardown_frame_pool_fusion(
-	struct megasas_instance *instance)
+static void
+megasas_fusion_update_can_queue(struct megasas_instance *instance, int fw_boot_context)
 {
-	int i;
-	struct fusion_context *fusion = instance->ctrl_context;
-
-	u16 max_cmd = instance->max_fw_cmds;
+	u16 cur_max_fw_cmds = 0;
+	u16 ldio_threshold = 0;
+	struct megasas_register_set __iomem *reg_set;
 
-	struct megasas_cmd_fusion *cmd;
+	reg_set = instance->reg_set;
 
-	if (!fusion->sg_dma_pool || !fusion->sense_dma_pool) {
-		dev_err(&instance->pdev->dev, "dma pool is null. SG Pool %p, "
-		       "sense pool : %p\n", fusion->sg_dma_pool,
-		       fusion->sense_dma_pool);
-		return;
-	}
+	cur_max_fw_cmds = readl(&instance->reg_set->outbound_scratch_pad_3) & 0x00FFFF;
 
-	/*
-	 * Return all frames to pool
-	 */
-	for (i = 0; i < max_cmd; i++) {
+	if (dual_qdepth_disable || !cur_max_fw_cmds)
+		cur_max_fw_cmds = instance->instancet->read_fw_status_reg(reg_set) & 0x00FFFF;
+	else
+		ldio_threshold =
+			(instance->instancet->read_fw_status_reg(reg_set) & 0x00FFFF) - MEGASAS_FUSION_IOCTL_CMDS;
+
+	dev_info(&instance->pdev->dev,
+			"Current firmware maximum commands: %d\t LDIO threshold: %d\n",
+			cur_max_fw_cmds, ldio_threshold);
+
+	if (fw_boot_context == OCR_CONTEXT) {
+		cur_max_fw_cmds = cur_max_fw_cmds - 1;
+		if (cur_max_fw_cmds <= instance->max_fw_cmds) {
+			instance->cur_can_queue =
+				cur_max_fw_cmds - (MEGASAS_FUSION_INTERNAL_CMDS +
+						MEGASAS_FUSION_IOCTL_CMDS);
+			instance->host->can_queue = instance->cur_can_queue;
+			instance->ldio_threshold = ldio_threshold;
+		}
+	} else {
+		instance->max_fw_cmds = cur_max_fw_cmds;
+		instance->ldio_threshold = ldio_threshold;
 
-		cmd = fusion->cmd_list[i];
+		if (!instance->is_rdpq)
+			instance->max_fw_cmds = min_t(u16, instance->max_fw_cmds, 1024);
 
-		if (cmd->sg_frame)
-			pci_pool_free(fusion->sg_dma_pool, cmd->sg_frame,
-				      cmd->sg_frame_phys_addr);
+		/*
+		* Reduce the max supported cmds by 1. This is to ensure that the
+		* reply_q_sz (1 more than the max cmd that driver may send)
+		* does not exceed max cmds that the FW can support
+		*/
+		instance->max_fw_cmds = instance->max_fw_cmds-1;
 
-		if (cmd->sense)
-			pci_pool_free(fusion->sense_dma_pool, cmd->sense,
-				      cmd->sense_phys_addr);
+		instance->max_scsi_cmds = instance->max_fw_cmds -
+				(MEGASAS_FUSION_INTERNAL_CMDS +
+				MEGASAS_FUSION_IOCTL_CMDS);
+		instance->cur_can_queue = instance->max_scsi_cmds;
 	}
-
-	/*
-	 * Now destroy the pool itself
-	 */
-	pci_pool_destroy(fusion->sg_dma_pool);
-	pci_pool_destroy(fusion->sense_dma_pool);
-
-	fusion->sg_dma_pool = NULL;
-	fusion->sense_dma_pool = NULL;
 }
-
 /**
  * megasas_free_cmds_fusion -	Free all the cmds in the free cmd pool
  * @instance:		Adapter soft state
@@ -262,55 +279,65 @@ megasas_free_cmds_fusion(struct megasas_instance *instance)
 {
 	int i;
 	struct fusion_context *fusion = instance->ctrl_context;
+	struct megasas_cmd_fusion *cmd;
 
-	u32 max_cmds, req_sz, reply_sz, io_frames_sz;
+	/* SG, Sense */
+	for (i = 0; i < instance->max_fw_cmds; i++) {
+		cmd = fusion->cmd_list[i];
+		if (cmd) {
+			if (cmd->sg_frame)
+				pci_pool_free(fusion->sg_dma_pool, cmd->sg_frame,
+				      cmd->sg_frame_phys_addr);
+			if (cmd->sense)
+				pci_pool_free(fusion->sense_dma_pool, cmd->sense,
+				      cmd->sense_phys_addr);
+		}
+	}
 
+	if (fusion->sg_dma_pool) {
+		pci_pool_destroy(fusion->sg_dma_pool);
+		fusion->sg_dma_pool = NULL;
+	}
+	if (fusion->sense_dma_pool) {
+		pci_pool_destroy(fusion->sense_dma_pool);
+		fusion->sense_dma_pool = NULL;
+	}
 
-	req_sz = fusion->request_alloc_sz;
-	reply_sz = fusion->reply_alloc_sz;
-	io_frames_sz = fusion->io_frames_alloc_sz;
 
-	max_cmds = instance->max_fw_cmds;
+	/* Reply Frame, Desc*/
+	if (instance->is_rdpq)
+		megasas_free_rdpq_fusion(instance);
+	else
+		megasas_free_reply_fusion(instance);
 
-	/* Free descriptors and request Frames memory */
+	/* Request Frame, Desc*/
 	if (fusion->req_frames_desc)
-		dma_free_coherent(&instance->pdev->dev, req_sz,
-				  fusion->req_frames_desc,
-				  fusion->req_frames_desc_phys);
-
-	if (fusion->reply_frames_desc) {
-		pci_pool_free(fusion->reply_frames_desc_pool,
-			      fusion->reply_frames_desc,
-			      fusion->reply_frames_desc_phys);
-		pci_pool_destroy(fusion->reply_frames_desc_pool);
-	}
-
-	if (fusion->io_request_frames) {
+		dma_free_coherent(&instance->pdev->dev,
+			fusion->request_alloc_sz, fusion->req_frames_desc,
+			fusion->req_frames_desc_phys);
+	if (fusion->io_request_frames)
 		pci_pool_free(fusion->io_request_frames_pool,
-			      fusion->io_request_frames,
-			      fusion->io_request_frames_phys);
+			fusion->io_request_frames,
+			fusion->io_request_frames_phys);
+	if (fusion->io_request_frames_pool) {
 		pci_pool_destroy(fusion->io_request_frames_pool);
+		fusion->io_request_frames_pool = NULL;
 	}
 
-	/* Free the Fusion frame pool */
-	megasas_teardown_frame_pool_fusion(instance);
 
-	/* Free all the commands in the cmd_list */
-	for (i = 0; i < max_cmds; i++)
+	/* cmd_list */
+	for (i = 0; i < instance->max_fw_cmds; i++)
 		kfree(fusion->cmd_list[i]);
 
-	/* Free the cmd_list buffer itself */
 	kfree(fusion->cmd_list);
-	fusion->cmd_list = NULL;
-
 }
 
 /**
- * megasas_create_frame_pool_fusion -	Creates DMA pool for cmd frames
+ * megasas_create_sg_sense_fusion -	Creates DMA pool for cmd frames
  * @instance:			Adapter soft state
  *
  */
-static int megasas_create_frame_pool_fusion(struct megasas_instance *instance)
+static int megasas_create_sg_sense_fusion(struct megasas_instance *instance)
 {
 	int i;
 	u32 max_cmd;
@@ -321,25 +348,17 @@ static int megasas_create_frame_pool_fusion(struct megasas_instance *instance)
 	max_cmd = instance->max_fw_cmds;
 
 
-	/*
-	 * Use DMA pool facility provided by PCI layer
-	 */
-
-	fusion->sg_dma_pool = pci_pool_create("sg_pool_fusion", instance->pdev,
-						instance->max_chain_frame_sz,
-						4, 0);
-	if (!fusion->sg_dma_pool) {
-		dev_printk(KERN_DEBUG, &instance->pdev->dev, "failed to setup request pool fusion\n");
-		return -ENOMEM;
-	}
-	fusion->sense_dma_pool = pci_pool_create("sense pool fusion",
-						 instance->pdev,
-						 SCSI_SENSE_BUFFERSIZE, 64, 0);
+	fusion->sg_dma_pool =
+			pci_pool_create("mr_sg", instance->pdev,
+				instance->max_chain_frame_sz, 4, 0);
+	/* SCSI_SENSE_BUFFERSIZE  = 96 bytes */
+	fusion->sense_dma_pool =
+			pci_pool_create("mr_sense", instance->pdev,
+				SCSI_SENSE_BUFFERSIZE, 64, 0);
 
-	if (!fusion->sense_dma_pool) {
-		dev_printk(KERN_DEBUG, &instance->pdev->dev, "failed to setup sense pool fusion\n");
-		pci_pool_destroy(fusion->sg_dma_pool);
-		fusion->sg_dma_pool = NULL;
+	if (!fusion->sense_dma_pool || !fusion->sg_dma_pool) {
+		dev_err(&instance->pdev->dev,
+			"Failed from %s %d\n",  __func__, __LINE__);
 		return -ENOMEM;
 	}
 
@@ -347,160 +366,280 @@ static int megasas_create_frame_pool_fusion(struct megasas_instance *instance)
 	 * Allocate and attach a frame to each of the commands in cmd_list
 	 */
 	for (i = 0; i < max_cmd; i++) {
-
 		cmd = fusion->cmd_list[i];
-
 		cmd->sg_frame = pci_pool_alloc(fusion->sg_dma_pool,
-					       GFP_KERNEL,
-					       &cmd->sg_frame_phys_addr);
+					GFP_KERNEL, &cmd->sg_frame_phys_addr);
 
 		cmd->sense = pci_pool_alloc(fusion->sense_dma_pool,
-					    GFP_KERNEL, &cmd->sense_phys_addr);
-		/*
-		 * megasas_teardown_frame_pool_fusion() takes care of freeing
-		 * whatever has been allocated
-		 */
+					GFP_KERNEL, &cmd->sense_phys_addr);
 		if (!cmd->sg_frame || !cmd->sense) {
-			dev_printk(KERN_DEBUG, &instance->pdev->dev, "pci_pool_alloc failed\n");
-			megasas_teardown_frame_pool_fusion(instance);
+			dev_err(&instance->pdev->dev,
+				"Failed from %s %d\n",  __func__, __LINE__);
 			return -ENOMEM;
 		}
 	}
 	return 0;
 }
 
-/**
- * megasas_alloc_cmds_fusion -	Allocates the command packets
- * @instance:		Adapter soft state
- *
- *
- * Each frame has a 32-bit field called context. This context is used to get
- * back the megasas_cmd_fusion from the frame when a frame gets completed
- * In this driver, the 32 bit values are the indices into an array cmd_list.
- * This array is used only to look up the megasas_cmd_fusion given the context.
- * The free commands themselves are maintained in a linked list called cmd_pool.
- *
- * cmds are formed in the io_request and sg_frame members of the
- * megasas_cmd_fusion. The context field is used to get a request descriptor
- * and is used as SMID of the cmd.
- * SMID value range is from 1 to max_fw_cmds.
- */
 int
-megasas_alloc_cmds_fusion(struct megasas_instance *instance)
+megasas_alloc_cmdlist_fusion(struct megasas_instance *instance)
 {
-	int i, j, count;
-	u32 max_cmd, io_frames_sz;
+	u32 max_cmd, i;
 	struct fusion_context *fusion;
-	struct megasas_cmd_fusion *cmd;
-	union MPI2_REPLY_DESCRIPTORS_UNION *reply_desc;
-	u32 offset;
-	dma_addr_t io_req_base_phys;
-	u8 *io_req_base;
 
 	fusion = instance->ctrl_context;
 
 	max_cmd = instance->max_fw_cmds;
 
+	/*
+	 * fusion->cmd_list is an array of struct megasas_cmd_fusion pointers.
+	 * Allocate the dynamic array first and then allocate individual
+	 * commands.
+	 */
+	fusion->cmd_list = kzalloc(sizeof(struct megasas_cmd_fusion *) * max_cmd,
+						GFP_KERNEL);
+	if (!fusion->cmd_list) {
+		dev_err(&instance->pdev->dev,
+			"Failed from %s %d\n",  __func__, __LINE__);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < max_cmd; i++) {
+		fusion->cmd_list[i] = kzalloc(sizeof(struct megasas_cmd_fusion),
+					      GFP_KERNEL);
+		if (!fusion->cmd_list[i]) {
+			dev_err(&instance->pdev->dev,
+				"Failed from %s %d\n",  __func__, __LINE__);
+			return -ENOMEM;
+		}
+	}
+	return 0;
+}
+int
+megasas_alloc_request_fusion(struct megasas_instance *instance)
+{
+	struct fusion_context *fusion;
+
+	fusion = instance->ctrl_context;
+
 	fusion->req_frames_desc =
 		dma_alloc_coherent(&instance->pdev->dev,
-				   fusion->request_alloc_sz,
-				   &fusion->req_frames_desc_phys, GFP_KERNEL);
-
+			fusion->request_alloc_sz,
+			&fusion->req_frames_desc_phys, GFP_KERNEL);
 	if (!fusion->req_frames_desc) {
-		dev_err(&instance->pdev->dev, "Could not allocate memory for "
-		       "request_frames\n");
-		goto fail_req_desc;
+		dev_err(&instance->pdev->dev,
+			"Failed from %s %d\n",  __func__, __LINE__);
+		return -ENOMEM;
 	}
 
+	fusion->io_request_frames_pool =
+			pci_pool_create("mr_ioreq", instance->pdev,
+				fusion->io_frames_alloc_sz, 16, 0);
+
+	if (!fusion->io_request_frames_pool) {
+		dev_err(&instance->pdev->dev,
+			"Failed from %s %d\n",  __func__, __LINE__);
+		return -ENOMEM;
+	}
+
+	fusion->io_request_frames =
+			pci_pool_alloc(fusion->io_request_frames_pool,
+				GFP_KERNEL, &fusion->io_request_frames_phys);
+	if (!fusion->io_request_frames) {
+		dev_err(&instance->pdev->dev,
+			"Failed from %s %d\n",  __func__, __LINE__);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+int
+megasas_alloc_reply_fusion(struct megasas_instance *instance)
+{
+	int i, count;
+	struct fusion_context *fusion;
+	union MPI2_REPLY_DESCRIPTORS_UNION *reply_desc;
+	fusion = instance->ctrl_context;
+
 	count = instance->msix_vectors > 0 ? instance->msix_vectors : 1;
 	fusion->reply_frames_desc_pool =
-		pci_pool_create("reply_frames pool", instance->pdev,
+			pci_pool_create("mr_reply", instance->pdev,
 				fusion->reply_alloc_sz * count, 16, 0);
 
 	if (!fusion->reply_frames_desc_pool) {
-		dev_err(&instance->pdev->dev, "Could not allocate memory for "
-		       "reply_frame pool\n");
-		goto fail_reply_desc;
+		dev_err(&instance->pdev->dev,
+			"Failed from %s %d\n",  __func__, __LINE__);
+		return -ENOMEM;
 	}
 
-	fusion->reply_frames_desc =
-		pci_pool_alloc(fusion->reply_frames_desc_pool, GFP_KERNEL,
-			       &fusion->reply_frames_desc_phys);
-	if (!fusion->reply_frames_desc) {
-		dev_err(&instance->pdev->dev, "Could not allocate memory for "
-		       "reply_frame pool\n");
-		pci_pool_destroy(fusion->reply_frames_desc_pool);
-		goto fail_reply_desc;
+	fusion->reply_frames_desc[0] =
+		pci_pool_alloc(fusion->reply_frames_desc_pool,
+			GFP_KERNEL, &fusion->reply_frames_desc_phys[0]);
+	if (!fusion->reply_frames_desc[0]) {
+		dev_err(&instance->pdev->dev,
+			"Failed from %s %d\n",  __func__, __LINE__);
+		return -ENOMEM;
 	}
-
-	reply_desc = fusion->reply_frames_desc;
+	reply_desc = fusion->reply_frames_desc[0];
 	for (i = 0; i < fusion->reply_q_depth * count; i++, reply_desc++)
 		reply_desc->Words = cpu_to_le64(ULLONG_MAX);
 
-	io_frames_sz = fusion->io_frames_alloc_sz;
+	/* This is not a rdpq mode, but driver still populate
+	 * reply_frame_desc array to use same msix index in ISR path.
+	 */
+	for (i = 0; i < (count - 1); i++)
+		fusion->reply_frames_desc[i + 1] =
+			fusion->reply_frames_desc[i] +
+			(fusion->reply_alloc_sz)/sizeof(union MPI2_REPLY_DESCRIPTORS_UNION);
+
+	return 0;
+}
 
-	fusion->io_request_frames_pool =
-		pci_pool_create("io_request_frames pool", instance->pdev,
-				fusion->io_frames_alloc_sz, 16, 0);
+int
+megasas_alloc_rdpq_fusion(struct megasas_instance *instance)
+{
+	int i, j, count;
+	struct fusion_context *fusion;
+	union MPI2_REPLY_DESCRIPTORS_UNION *reply_desc;
 
-	if (!fusion->io_request_frames_pool) {
-		dev_err(&instance->pdev->dev, "Could not allocate memory for "
-		       "io_request_frame pool\n");
-		goto fail_io_frames;
+	fusion = instance->ctrl_context;
+
+	fusion->rdpq_virt = pci_alloc_consistent(instance->pdev,
+				sizeof(struct MPI2_IOC_INIT_RDPQ_ARRAY_ENTRY) * MAX_MSIX_QUEUES_FUSION,
+				&fusion->rdpq_phys);
+	if (!fusion->rdpq_virt) {
+		dev_err(&instance->pdev->dev,
+			"Failed from %s %d\n",  __func__, __LINE__);
+		return -ENOMEM;
 	}
 
-	fusion->io_request_frames =
-		pci_pool_alloc(fusion->io_request_frames_pool, GFP_KERNEL,
-			       &fusion->io_request_frames_phys);
-	if (!fusion->io_request_frames) {
-		dev_err(&instance->pdev->dev, "Could not allocate memory for "
-		       "io_request_frames frames\n");
-		pci_pool_destroy(fusion->io_request_frames_pool);
-		goto fail_io_frames;
+	memset(fusion->rdpq_virt, 0,
+			sizeof(struct MPI2_IOC_INIT_RDPQ_ARRAY_ENTRY) * MAX_MSIX_QUEUES_FUSION);
+	count = instance->msix_vectors > 0 ? instance->msix_vectors : 1;
+	fusion->reply_frames_desc_pool = pci_pool_create("mr_rdpq",
+							 instance->pdev, fusion->reply_alloc_sz, 16, 0);
+
+	if (!fusion->reply_frames_desc_pool) {
+		dev_err(&instance->pdev->dev,
+			"Failed from %s %d\n",  __func__, __LINE__);
+		return -ENOMEM;
 	}
 
-	/*
-	 * fusion->cmd_list is an array of struct megasas_cmd_fusion pointers.
-	 * Allocate the dynamic array first and then allocate individual
-	 * commands.
-	 */
-	fusion->cmd_list = kzalloc(sizeof(struct megasas_cmd_fusion *)
-				   * max_cmd, GFP_KERNEL);
+	for (i = 0; i < count; i++) {
+		fusion->reply_frames_desc[i] =
+				pci_pool_alloc(fusion->reply_frames_desc_pool,
+					GFP_KERNEL, &fusion->reply_frames_desc_phys[i]);
+		if (!fusion->reply_frames_desc[i]) {
+			dev_err(&instance->pdev->dev,
+				"Failed from %s %d\n",  __func__, __LINE__);
+			return -ENOMEM;
+		}
 
-	if (!fusion->cmd_list) {
-		dev_printk(KERN_DEBUG, &instance->pdev->dev, "out of memory. Could not alloc "
-		       "memory for cmd_list_fusion\n");
-		goto fail_cmd_list;
+		fusion->rdpq_virt[i].RDPQBaseAddress =
+			fusion->reply_frames_desc_phys[i];
+
+		reply_desc = fusion->reply_frames_desc[i];
+		for (j = 0; j < fusion->reply_q_depth; j++, reply_desc++)
+			reply_desc->Words = cpu_to_le64(ULLONG_MAX);
 	}
+	return 0;
+}
 
-	max_cmd = instance->max_fw_cmds;
-	for (i = 0; i < max_cmd; i++) {
-		fusion->cmd_list[i] = kmalloc(sizeof(struct megasas_cmd_fusion),
-					      GFP_KERNEL);
-		if (!fusion->cmd_list[i]) {
-			dev_err(&instance->pdev->dev, "Could not alloc cmd list fusion\n");
+static void
+megasas_free_rdpq_fusion(struct megasas_instance *instance) {
 
-			for (j = 0; j < i; j++)
-				kfree(fusion->cmd_list[j]);
+	int i;
+	struct fusion_context *fusion;
 
-			kfree(fusion->cmd_list);
-			fusion->cmd_list = NULL;
-			goto fail_cmd_list;
-		}
+	fusion = instance->ctrl_context;
+
+	for (i = 0; i < MAX_MSIX_QUEUES_FUSION; i++) {
+		if (fusion->reply_frames_desc[i])
+			pci_pool_free(fusion->reply_frames_desc_pool,
+				fusion->reply_frames_desc[i],
+				fusion->reply_frames_desc_phys[i]);
 	}
 
-	/* The first 256 bytes (SMID 0) is not used. Don't add to cmd list */
-	io_req_base = fusion->io_request_frames +
-		MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE;
-	io_req_base_phys = fusion->io_request_frames_phys +
-		MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE;
+	if (fusion->reply_frames_desc_pool)
+		pci_pool_destroy(fusion->reply_frames_desc_pool);
+
+	if (fusion->rdpq_virt)
+		pci_free_consistent(instance->pdev,
+			sizeof(struct MPI2_IOC_INIT_RDPQ_ARRAY_ENTRY) * MAX_MSIX_QUEUES_FUSION,
+			fusion->rdpq_virt, fusion->rdpq_phys);
+}
+
+static void
+megasas_free_reply_fusion(struct megasas_instance *instance) {
+
+	struct fusion_context *fusion;
+
+	fusion = instance->ctrl_context;
+
+	if (fusion->reply_frames_desc[0])
+		pci_pool_free(fusion->reply_frames_desc_pool,
+			fusion->reply_frames_desc[0],
+			fusion->reply_frames_desc_phys[0]);
+
+	if (fusion->reply_frames_desc_pool)
+		pci_pool_destroy(fusion->reply_frames_desc_pool);
+
+}
+
+
+/**
+ * megasas_alloc_cmds_fusion -	Allocates the command packets
+ * @instance:		Adapter soft state
+ *
+ *
+ * Each frame has a 32-bit field called context. This context is used to get
+ * back the megasas_cmd_fusion from the frame when a frame gets completed
+ * In this driver, the 32 bit values are the indices into an array cmd_list.
+ * This array is used only to look up the megasas_cmd_fusion given the context.
+ * The free commands themselves are maintained in a linked list called cmd_pool.
+ *
+ * cmds are formed in the io_request and sg_frame members of the
+ * megasas_cmd_fusion. The context field is used to get a request descriptor
+ * and is used as SMID of the cmd.
+ * SMID value range is from 1 to max_fw_cmds.
+ */
+int
+megasas_alloc_cmds_fusion(struct megasas_instance *instance)
+{
+	int i;
+	struct fusion_context *fusion;
+	struct megasas_cmd_fusion *cmd;
+	u32 offset;
+	dma_addr_t io_req_base_phys;
+	u8 *io_req_base;
+
+
+	fusion = instance->ctrl_context;
+
+	if (megasas_alloc_cmdlist_fusion(instance))
+		goto fail_exit;
+
+	if (megasas_alloc_request_fusion(instance))
+		goto fail_exit;
+
+	if (instance->is_rdpq) {
+		if (megasas_alloc_rdpq_fusion(instance))
+			goto fail_exit;
+	} else
+		if (megasas_alloc_reply_fusion(instance))
+			goto fail_exit;
+
+
+	/* The first 256 bytes (SMID 0) is not used. Don't add to the cmd list */
+	io_req_base = fusion->io_request_frames + MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE;
+	io_req_base_phys = fusion->io_request_frames_phys + MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE;
 
 	/*
 	 * Add all the commands to command pool (fusion->cmd_pool)
 	 */
 
 	/* SMID 0 is reserved. Set SMID/index from 1 */
-	for (i = 0; i < max_cmd; i++) {
+	for (i = 0; i < instance->max_fw_cmds; i++) {
 		cmd = fusion->cmd_list[i];
 		offset = MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE * i;
 		memset(cmd, 0, sizeof(struct megasas_cmd_fusion));
@@ -518,35 +657,13 @@ megasas_alloc_cmds_fusion(struct megasas_instance *instance)
 		cmd->io_request_phys_addr = io_req_base_phys + offset;
 	}
 
-	/*
-	 * Create a frame pool and assign one frame to each cmd
-	 */
-	if (megasas_create_frame_pool_fusion(instance)) {
-		dev_printk(KERN_DEBUG, &instance->pdev->dev, "Error creating frame DMA pool\n");
-		megasas_free_cmds_fusion(instance);
-		goto fail_req_desc;
-	}
+	if (megasas_create_sg_sense_fusion(instance))
+		goto fail_exit;
 
 	return 0;
 
-fail_cmd_list:
-	pci_pool_free(fusion->io_request_frames_pool, fusion->io_request_frames,
-		      fusion->io_request_frames_phys);
-	pci_pool_destroy(fusion->io_request_frames_pool);
-fail_io_frames:
-	dma_free_coherent(&instance->pdev->dev, fusion->request_alloc_sz,
-			  fusion->reply_frames_desc,
-			  fusion->reply_frames_desc_phys);
-	pci_pool_free(fusion->reply_frames_desc_pool,
-		      fusion->reply_frames_desc,
-		      fusion->reply_frames_desc_phys);
-	pci_pool_destroy(fusion->reply_frames_desc_pool);
-
-fail_reply_desc:
-	dma_free_coherent(&instance->pdev->dev, fusion->request_alloc_sz,
-			  fusion->req_frames_desc,
-			  fusion->req_frames_desc_phys);
-fail_req_desc:
+fail_exit:
+	megasas_free_cmds_fusion(instance);
 	return -ENOMEM;
 }
 
@@ -576,11 +693,12 @@ wait_and_poll(struct megasas_instance *instance, struct megasas_cmd *cmd,
 		msleep(20);
 	}
 
-	if (frame_hdr->cmd_status == 0xff)
-		return -ETIME;
-
-	return (frame_hdr->cmd_status == MFI_STAT_OK) ?
-		0 : 1;
+	if (frame_hdr->cmd_status == MFI_STAT_INVALID_STATUS)
+		return DCMD_TIMEOUT;
+	else if (frame_hdr->cmd_status == MFI_STAT_OK)
+		return DCMD_SUCCESS;
+	else
+		return DCMD_FAILED;
 }
 
 /**
@@ -593,16 +711,17 @@ int
 megasas_ioc_init_fusion(struct megasas_instance *instance)
 {
 	struct megasas_init_frame *init_frame;
-	struct MPI2_IOC_INIT_REQUEST *IOCInitMessage;
+	struct MPI2_IOC_INIT_REQUEST *IOCInitMessage = NULL;
 	dma_addr_t	ioc_init_handle;
 	struct megasas_cmd *cmd;
-	u8 ret;
+	u8 ret, cur_rdpq_mode;
 	struct fusion_context *fusion;
 	union MEGASAS_REQUEST_DESCRIPTOR_UNION req_desc;
 	int i;
 	struct megasas_header *frame_hdr;
 	const char *sys_info;
 	MFI_CAPABILITIES *drv_ops;
+	u32 scratch_pad_2;
 
 	fusion = instance->ctrl_context;
 
@@ -614,6 +733,18 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 		goto fail_get_cmd;
 	}
 
+	scratch_pad_2 = readl
+		(&instance->reg_set->outbound_scratch_pad_2);
+
+	cur_rdpq_mode = (scratch_pad_2 & MR_RDPQ_MODE_OFFSET) ? 1 : 0;
+
+	if (instance->is_rdpq && !cur_rdpq_mode) {
+		dev_err(&instance->pdev->dev, "Firmware downgrade *NOT SUPPORTED*"
+			" from RDPQ mode to non RDPQ mode\n");
+		ret = 1;
+		goto fail_fw_init;
+	}
+
 	IOCInitMessage =
 	  dma_alloc_coherent(&instance->pdev->dev,
 			     sizeof(struct MPI2_IOC_INIT_REQUEST),
@@ -635,7 +766,11 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 	IOCInitMessage->SystemRequestFrameSize = cpu_to_le16(MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE / 4);
 
 	IOCInitMessage->ReplyDescriptorPostQueueDepth = cpu_to_le16(fusion->reply_q_depth);
-	IOCInitMessage->ReplyDescriptorPostQueueAddress	= cpu_to_le64(fusion->reply_frames_desc_phys);
+	IOCInitMessage->ReplyDescriptorPostQueueAddress = instance->is_rdpq ?
+			cpu_to_le64(fusion->rdpq_phys) :
+			cpu_to_le64(fusion->reply_frames_desc_phys[0]);
+	IOCInitMessage->MsgFlags = instance->is_rdpq ?
+			MPI2_IOCINIT_MSGFLAG_RDPQ_ARRAY_MODE : 0;
 	IOCInitMessage->SystemRequestFrameBaseAddress = cpu_to_le64(fusion->io_request_frames_phys);
 	IOCInitMessage->HostMSIxVectors = instance->msix_vectors;
 	init_frame = (struct megasas_init_frame *)cmd->frame;
@@ -665,6 +800,11 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 	if (instance->max_chain_frame_sz > MEGASAS_CHAIN_FRAME_SZ_MIN)
 		drv_ops->mfi_capabilities.support_ext_io_size = 1;
 
+	drv_ops->mfi_capabilities.support_fp_rlbypass = 1;
+	if (!dual_qdepth_disable)
+		drv_ops->mfi_capabilities.support_ext_queue_depth = 1;
+
+	drv_ops->mfi_capabilities.support_qd_throttling = 1;
 	/* Convert capability to LE32 */
 	cpu_to_le32s((u32 *)&init_frame->driver_operations.mfi_capabilities);
 
@@ -784,7 +924,8 @@ megasas_sync_pd_seq_num(struct megasas_instance *instance, bool pend) {
 
 	/* Below code is only for non pended DCMD */
 	if (instance->ctrl_context && !instance->mask_interrupts)
-		ret = megasas_issue_blocked_cmd(instance, cmd, 60);
+		ret = megasas_issue_blocked_cmd(instance, cmd,
+			MFI_IO_TIMEOUT_SECS);
 	else
 		ret = megasas_issue_polled(instance, cmd);
 
@@ -795,7 +936,10 @@ megasas_sync_pd_seq_num(struct megasas_instance *instance, bool pend) {
 		ret = -EINVAL;
 	}
 
-	if (!ret)
+	if (ret == DCMD_TIMEOUT && instance->ctrl_context)
+		megaraid_sas_kill_hba(instance);
+
+	if (ret == DCMD_SUCCESS)
 		instance->pd_seq_map_id++;
 
 	megasas_return_cmd(instance, cmd);
@@ -875,10 +1019,13 @@ megasas_get_ld_map_info(struct megasas_instance *instance)
 
 	if (instance->ctrl_context && !instance->mask_interrupts)
 		ret = megasas_issue_blocked_cmd(instance, cmd,
-			MEGASAS_BLOCKED_CMD_TIMEOUT);
+			MFI_IO_TIMEOUT_SECS);
 	else
 		ret = megasas_issue_polled(instance, cmd);
 
+	if (ret == DCMD_TIMEOUT && instance->ctrl_context)
+		megaraid_sas_kill_hba(instance);
+
 	megasas_return_cmd(instance, cmd);
 
 	return ret;
@@ -1072,12 +1219,7 @@ megasas_init_adapter_fusion(struct megasas_instance *instance)
 
 	reg_set = instance->reg_set;
 
-	/*
-	 * Get various operational parameters from status register
-	 */
-	instance->max_fw_cmds =
-		instance->instancet->read_fw_status_reg(reg_set) & 0x00FFFF;
-	instance->max_fw_cmds = min(instance->max_fw_cmds, (u16)1008);
+	megasas_fusion_update_can_queue(instance, PROBE_CONTEXT);
 
 	/*
 	 * Reduce the max supported cmds by 1. This is to ensure that the
@@ -1658,7 +1800,7 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
 				   local_map_ptr, start_lba_lo);
 		io_request->Function = MPI2_FUNCTION_SCSI_IO_REQUEST;
 		cmd->request_desc->SCSIIO.RequestFlags =
-			(MPI2_REQ_DESCRIPT_FLAGS_HIGH_PRIORITY
+			(MPI2_REQ_DESCRIPT_FLAGS_FP_IO
 			 << MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
 		if (fusion->adapter_type == INVADER_SERIES) {
 			if (io_request->RaidContext.regLockFlags ==
@@ -1702,8 +1844,8 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
 			(MEGASAS_REQ_DESCRIPT_FLAGS_LD_IO
 			 << MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
 		if (fusion->adapter_type == INVADER_SERIES) {
-			if (io_request->RaidContext.regLockFlags ==
-			    REGION_TYPE_UNUSED)
+			if (io_info.do_fp_rlbypass ||
+				(io_request->RaidContext.regLockFlags == REGION_TYPE_UNUSED))
 				cmd->request_desc->SCSIIO.RequestFlags =
 					(MEGASAS_REQ_DESCRIPT_FLAGS_NO_LOCK <<
 					MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
@@ -1791,7 +1933,7 @@ static void megasas_build_ld_nonrw_fusion(struct megasas_instance *instance,
 
 		/* build request descriptor */
 		cmd->request_desc->SCSIIO.RequestFlags =
-			(MPI2_REQ_DESCRIPT_FLAGS_HIGH_PRIORITY <<
+			(MPI2_REQ_DESCRIPT_FLAGS_FP_IO <<
 			MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
 		cmd->request_desc->SCSIIO.DevHandle = devHandle;
 
@@ -1897,7 +2039,7 @@ megasas_build_syspd_fusion(struct megasas_instance *instance,
 				cpu_to_le16(MPI25_SAS_DEVICE0_FLAGS_ENABLED_FAST_PATH);
 		}
 		cmd->request_desc->SCSIIO.RequestFlags =
-			(MPI2_REQ_DESCRIPT_FLAGS_HIGH_PRIORITY <<
+			(MPI2_REQ_DESCRIPT_FLAGS_FP_IO <<
 				MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
 	}
 }
@@ -2035,13 +2177,21 @@ megasas_build_and_issue_cmd_fusion(struct megasas_instance *instance,
 
 	fusion = instance->ctrl_context;
 
+	if ((megasas_cmd_type(scmd) == READ_WRITE_LDIO) &&
+		instance->ldio_threshold &&
+		(atomic_inc_return(&instance->ldio_outstanding) >
+		instance->ldio_threshold)) {
+		atomic_dec(&instance->ldio_outstanding);
+		return SCSI_MLQUEUE_DEVICE_BUSY;
+	}
+
 	cmd = megasas_get_cmd_fusion(instance, scmd->request->tag);
 
 	index = cmd->index;
 
 	req_desc = megasas_get_request_descriptor(instance, index-1);
 	if (!req_desc)
-		return 1;
+		return SCSI_MLQUEUE_HOST_BUSY;
 
 	req_desc->Words = 0;
 	cmd->request_desc = req_desc;
@@ -2050,7 +2200,7 @@ megasas_build_and_issue_cmd_fusion(struct megasas_instance *instance,
 		megasas_return_cmd_fusion(instance, cmd);
 		dev_err(&instance->pdev->dev, "Error building command\n");
 		cmd->request_desc = NULL;
-		return 1;
+		return SCSI_MLQUEUE_HOST_BUSY;
 	}
 
 	req_desc = cmd->request_desc;
@@ -2092,16 +2242,16 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex)
 	struct LD_LOAD_BALANCE_INFO *lbinfo;
 	int threshold_reply_count = 0;
 	struct scsi_cmnd *scmd_local = NULL;
+	struct MR_TASK_MANAGE_REQUEST *mr_tm_req;
+	struct MPI2_SCSI_TASK_MANAGE_REQUEST *mpi_tm_req;
 
 	fusion = instance->ctrl_context;
 
-	if (instance->adprecovery == MEGASAS_HW_CRITICAL_ERROR)
+	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR)
 		return IRQ_HANDLED;
 
-	desc = fusion->reply_frames_desc;
-	desc += ((MSIxIndex * fusion->reply_alloc_sz)/
-		 sizeof(union MPI2_REPLY_DESCRIPTORS_UNION)) +
-		fusion->last_reply_idx[MSIxIndex];
+	desc = fusion->reply_frames_desc[MSIxIndex] +
+				fusion->last_reply_idx[MSIxIndex];
 
 	reply_desc = (struct MPI2_SCSI_IO_SUCCESS_REPLY_DESCRIPTOR *)desc;
 
@@ -2133,6 +2283,16 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex)
 		extStatus = scsi_io_req->RaidContext.exStatus;
 
 		switch (scsi_io_req->Function) {
+		case MPI2_FUNCTION_SCSI_TASK_MGMT:
+			mr_tm_req = (struct MR_TASK_MANAGE_REQUEST *)
+						cmd_fusion->io_request;
+			mpi_tm_req = (struct MPI2_SCSI_TASK_MANAGE_REQUEST *)
+						&mr_tm_req->TmRequest;
+			dev_dbg(&instance->pdev->dev, "TM completion:"
+				"type: 0x%x TaskMID: 0x%x\n",
+				mpi_tm_req->TaskType, mpi_tm_req->TaskMID);
+			complete(&cmd_fusion->done);
+			break;
 		case MPI2_FUNCTION_SCSI_IO_REQUEST:  /*Fast Path IO.*/
 			/* Update load balancing info */
 			device_id = MEGASAS_DEV_INDEX(scmd_local);
@@ -2155,6 +2315,8 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex)
 			map_cmd_status(cmd_fusion, status, extStatus);
 			scsi_io_req->RaidContext.status = 0;
 			scsi_io_req->RaidContext.exStatus = 0;
+			if (megasas_cmd_type(scmd_local) == READ_WRITE_LDIO)
+				atomic_dec(&instance->ldio_outstanding);
 			megasas_return_cmd_fusion(instance, cmd_fusion);
 			scsi_dma_unmap(scmd_local);
 			scmd_local->scsi_done(scmd_local);
@@ -2186,9 +2348,7 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex)
 
 		/* Get the next reply descriptor */
 		if (!fusion->last_reply_idx[MSIxIndex])
-			desc = fusion->reply_frames_desc +
-				((MSIxIndex * fusion->reply_alloc_sz)/
-				 sizeof(union MPI2_REPLY_DESCRIPTORS_UNION));
+			desc = fusion->reply_frames_desc[MSIxIndex];
 		else
 			desc++;
 
@@ -2254,7 +2414,7 @@ megasas_complete_cmd_dpc_fusion(unsigned long instance_addr)
 
 	/* If we have already declared adapter dead, donot complete cmds */
 	spin_lock_irqsave(&instance->hba_lock, flags);
-	if (instance->adprecovery == MEGASAS_HW_CRITICAL_ERROR) {
+	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
 		spin_unlock_irqrestore(&instance->hba_lock, flags);
 		return;
 	}
@@ -2411,7 +2571,7 @@ build_mpt_cmd(struct megasas_instance *instance, struct megasas_cmd *cmd)
  * @cmd:			mfi cmd pointer
  *
  */
-void
+int
 megasas_issue_dcmd_fusion(struct megasas_instance *instance,
 			  struct megasas_cmd *cmd)
 {
@@ -2419,10 +2579,13 @@ megasas_issue_dcmd_fusion(struct megasas_instance *instance,
 
 	req_desc = build_mpt_cmd(instance, cmd);
 	if (!req_desc) {
-		dev_err(&instance->pdev->dev, "Couldn't issue MFI pass thru cmd\n");
-		return;
+		dev_info(&instance->pdev->dev, "Failed from %s %d\n",
+					__func__, __LINE__);
+		return DCMD_NOT_FIRED;
 	}
+
 	megasas_fire_cmd_fusion(instance, req_desc);
+	return DCMD_SUCCESS;
 }
 
 /**
@@ -2583,7 +2746,7 @@ megasas_check_reset_fusion(struct megasas_instance *instance,
 
 /* This function waits for outstanding commands on fusion to complete */
 int megasas_wait_for_outstanding_fusion(struct megasas_instance *instance,
-					int iotimeout, int *convert)
+					int reason, int *convert)
 {
 	int i, outstanding, retval = 0, hb_seconds_missed = 0;
 	u32 fw_state;
@@ -2599,14 +2762,22 @@ int megasas_wait_for_outstanding_fusion(struct megasas_instance *instance,
 			retval = 1;
 			goto out;
 		}
+
+		if (reason == MFI_IO_TIMEOUT_OCR) {
+			dev_info(&instance->pdev->dev,
+				"MFI IO is timed out, initiating OCR\n");
+			retval = 1;
+			goto out;
+		}
+
 		/* If SR-IOV VF mode & heartbeat timeout, don't wait */
-		if (instance->requestorId && !iotimeout) {
+		if (instance->requestorId && !reason) {
 			retval = 1;
 			goto out;
 		}
 
 		/* If SR-IOV VF mode & I/O timeout, check for HB timeout */
-		if (instance->requestorId && iotimeout) {
+		if (instance->requestorId && reason) {
 			if (instance->hb_host_mem->HB.fwCounter !=
 			    instance->hb_host_mem->HB.driverCounter) {
 				instance->hb_host_mem->HB.driverCounter =
@@ -2655,17 +2826,18 @@ out:
 
 void  megasas_reset_reply_desc(struct megasas_instance *instance)
 {
-	int i, count;
+	int i, j, count;
 	struct fusion_context *fusion;
 	union MPI2_REPLY_DESCRIPTORS_UNION *reply_desc;
 
 	fusion = instance->ctrl_context;
 	count = instance->msix_vectors > 0 ? instance->msix_vectors : 1;
-	for (i = 0 ; i < count ; i++)
+	for (i = 0 ; i < count ; i++) {
 		fusion->last_reply_idx[i] = 0;
-	reply_desc = fusion->reply_frames_desc;
-	for (i = 0 ; i < fusion->reply_q_depth * count; i++, reply_desc++)
-		reply_desc->Words = cpu_to_le64(ULLONG_MAX);
+		reply_desc = fusion->reply_frames_desc[i];
+		for (j = 0 ; j < fusion->reply_q_depth; j++, reply_desc++)
+			reply_desc->Words = cpu_to_le64(ULLONG_MAX);
+	}
 }
 
 /*
@@ -2680,6 +2852,7 @@ void megasas_refire_mgmt_cmd(struct megasas_instance *instance)
 	struct megasas_cmd *cmd_mfi;
 	union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc;
 	u16 smid;
+	bool refire_cmd = 0;
 
 	fusion = instance->ctrl_context;
 
@@ -2695,42 +2868,500 @@ void megasas_refire_mgmt_cmd(struct megasas_instance *instance)
 			continue;
 		req_desc = megasas_get_request_descriptor
 					(instance, smid - 1);
-		if (req_desc && ((cmd_mfi->frame->dcmd.opcode !=
+		refire_cmd = req_desc && ((cmd_mfi->frame->dcmd.opcode !=
 				cpu_to_le32(MR_DCMD_LD_MAP_GET_INFO)) &&
 				 (cmd_mfi->frame->dcmd.opcode !=
-				cpu_to_le32(MR_DCMD_SYSTEM_PD_MAP_GET_INFO))))
+				cpu_to_le32(MR_DCMD_SYSTEM_PD_MAP_GET_INFO)))
+				&& !(cmd_mfi->flags & DRV_DCMD_SKIP_REFIRE);
+		if (refire_cmd)
 			megasas_fire_cmd_fusion(instance, req_desc);
 		else
 			megasas_return_cmd(instance, cmd_mfi);
 	}
 }
 
+/*
+ * megasas_track_scsiio : Track SCSI IOs outstanding to a SCSI device
+ * @instance: per adapter struct
+ * @channel: the channel assigned by the OS
+ * @id: the id assigned by the OS
+ *
+ * Returns SUCCESS if no IOs pending to SCSI device, else return FAILED
+ */
+
+static int megasas_track_scsiio(struct megasas_instance *instance,
+		int id, int channel)
+{
+	int i, found = 0;
+	struct megasas_cmd_fusion *cmd_fusion;
+	struct fusion_context *fusion;
+	fusion = instance->ctrl_context;
+
+	for (i = 0 ; i < instance->max_scsi_cmds; i++) {
+		cmd_fusion = fusion->cmd_list[i];
+		if (cmd_fusion->scmd &&
+			(cmd_fusion->scmd->device->id == id &&
+			cmd_fusion->scmd->device->channel == channel)) {
+			dev_info(&instance->pdev->dev,
+				"SCSI commands pending to target"
+				"channel %d id %d \tSMID: 0x%x\n",
+				channel, id, cmd_fusion->index);
+			scsi_print_command(cmd_fusion->scmd);
+			found = 1;
+			break;
+		}
+	}
+
+	return found ? FAILED : SUCCESS;
+}
+
+/**
+ * megasas_tm_response_code - translation of device response code
+ * @ioc: per adapter object
+ * @mpi_reply: MPI reply returned by firmware
+ *
+ * Return nothing.
+ */
+static void
+megasas_tm_response_code(struct megasas_instance *instance,
+		struct MPI2_SCSI_TASK_MANAGE_REPLY *mpi_reply)
+{
+	char *desc;
+
+	switch (mpi_reply->ResponseCode) {
+	case MPI2_SCSITASKMGMT_RSP_TM_COMPLETE:
+		desc = "task management request completed";
+		break;
+	case MPI2_SCSITASKMGMT_RSP_INVALID_FRAME:
+		desc = "invalid frame";
+		break;
+	case MPI2_SCSITASKMGMT_RSP_TM_NOT_SUPPORTED:
+		desc = "task management request not supported";
+		break;
+	case MPI2_SCSITASKMGMT_RSP_TM_FAILED:
+		desc = "task management request failed";
+		break;
+	case MPI2_SCSITASKMGMT_RSP_TM_SUCCEEDED:
+		desc = "task management request succeeded";
+		break;
+	case MPI2_SCSITASKMGMT_RSP_TM_INVALID_LUN:
+		desc = "invalid lun";
+		break;
+	case 0xA:
+		desc = "overlapped tag attempted";
+		break;
+	case MPI2_SCSITASKMGMT_RSP_IO_QUEUED_ON_IOC:
+		desc = "task queued, however not sent to target";
+		break;
+	default:
+		desc = "unknown";
+		break;
+	}
+	dev_dbg(&instance->pdev->dev, "response_code(%01x): %s\n",
+		mpi_reply->ResponseCode, desc);
+	dev_dbg(&instance->pdev->dev,
+		"TerminationCount/DevHandle/Function/TaskType/IOCStat/IOCLoginfo"
+		" 0x%x/0x%x/0x%x/0x%x/0x%x/0x%x\n",
+		mpi_reply->TerminationCount, mpi_reply->DevHandle,
+		mpi_reply->Function, mpi_reply->TaskType,
+		mpi_reply->IOCStatus, mpi_reply->IOCLogInfo);
+}
+
+/**
+ * megasas_issue_tm - main routine for sending tm requests
+ * @instance: per adapter struct
+ * @device_handle: device handle
+ * @channel: the channel assigned by the OS
+ * @id: the id assigned by the OS
+ * @type: MPI2_SCSITASKMGMT_TASKTYPE__XXX (defined in megaraid_sas_fusion.c)
+ * @smid_task: smid assigned to the task
+ * @m_type: TM_MUTEX_ON or TM_MUTEX_OFF
+ * Context: user
+ *
+ * MegaRaid use MPT interface for Task Magement request.
+ * A generic API for sending task management requests to firmware.
+ *
+ * Return SUCCESS or FAILED.
+ */
+static int
+megasas_issue_tm(struct megasas_instance *instance, u16 device_handle,
+	uint channel, uint id, u16 smid_task, u8 type)
+{
+	struct MR_TASK_MANAGE_REQUEST *mr_request;
+	struct MPI2_SCSI_TASK_MANAGE_REQUEST *mpi_request;
+	unsigned long timeleft;
+	struct megasas_cmd_fusion *cmd_fusion;
+	struct megasas_cmd *cmd_mfi;
+	union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc;
+	struct fusion_context *fusion;
+	struct megasas_cmd_fusion *scsi_lookup;
+	int rc;
+	struct MPI2_SCSI_TASK_MANAGE_REPLY *mpi_reply;
+
+	fusion = instance->ctrl_context;
+
+	cmd_mfi = megasas_get_cmd(instance);
+
+	if (!cmd_mfi) {
+		dev_err(&instance->pdev->dev, "Failed from %s %d\n",
+			__func__, __LINE__);
+		return -ENOMEM;
+	}
+
+	cmd_fusion = megasas_get_cmd_fusion(instance,
+			instance->max_scsi_cmds + cmd_mfi->index);
+
+	/*  Save the smid. To be used for returning the cmd */
+	cmd_mfi->context.smid = cmd_fusion->index;
+
+	req_desc = megasas_get_request_descriptor(instance,
+			(cmd_fusion->index - 1));
+	if (!req_desc) {
+		dev_err(&instance->pdev->dev, "Failed from %s %d\n",
+			__func__, __LINE__);
+		megasas_return_cmd(instance, cmd_mfi);
+		return -ENOMEM;
+	}
+
+	cmd_fusion->request_desc = req_desc;
+	req_desc->Words = 0;
+
+	scsi_lookup = fusion->cmd_list[smid_task - 1];
+
+	mr_request = (struct MR_TASK_MANAGE_REQUEST *) cmd_fusion->io_request;
+	memset(mr_request, 0, sizeof(struct MR_TASK_MANAGE_REQUEST));
+	mpi_request = (struct MPI2_SCSI_TASK_MANAGE_REQUEST *) &mr_request->TmRequest;
+	mpi_request->Function = MPI2_FUNCTION_SCSI_TASK_MGMT;
+	mpi_request->DevHandle = cpu_to_le16(device_handle);
+	mpi_request->TaskType = type;
+	mpi_request->TaskMID = cpu_to_le16(smid_task);
+	mpi_request->LUN[1] = 0;
+
+
+	req_desc = cmd_fusion->request_desc;
+	req_desc->HighPriority.SMID = cpu_to_le16(cmd_fusion->index);
+	req_desc->HighPriority.RequestFlags =
+		(MPI2_REQ_DESCRIPT_FLAGS_HIGH_PRIORITY <<
+		MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
+	req_desc->HighPriority.MSIxIndex =  0;
+	req_desc->HighPriority.LMID = 0;
+	req_desc->HighPriority.Reserved1 = 0;
+
+	if (channel < MEGASAS_MAX_PD_CHANNELS)
+		mr_request->tmReqFlags.isTMForPD = 1;
+	else
+		mr_request->tmReqFlags.isTMForLD = 1;
+
+	init_completion(&cmd_fusion->done);
+	megasas_fire_cmd_fusion(instance, req_desc);
+
+	timeleft = wait_for_completion_timeout(&cmd_fusion->done, 50 * HZ);
+
+	if (!timeleft) {
+		dev_err(&instance->pdev->dev,
+			"task mgmt type 0x%x timed out\n", type);
+		cmd_mfi->flags |= DRV_DCMD_SKIP_REFIRE;
+		mutex_unlock(&instance->reset_mutex);
+		rc = megasas_reset_fusion(instance->host, MFI_IO_TIMEOUT_OCR);
+		mutex_lock(&instance->reset_mutex);
+		return rc;
+	}
+
+	mpi_reply = (struct MPI2_SCSI_TASK_MANAGE_REPLY *) &mr_request->TMReply;
+	megasas_tm_response_code(instance, mpi_reply);
+
+	megasas_return_cmd(instance, cmd_mfi);
+	rc = SUCCESS;
+	switch (type) {
+	case MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK:
+		if (scsi_lookup->scmd == NULL)
+			break;
+		else {
+			instance->instancet->disable_intr(instance);
+			msleep(1000);
+			megasas_complete_cmd_dpc_fusion
+					((unsigned long)instance);
+			instance->instancet->enable_intr(instance);
+			if (scsi_lookup->scmd == NULL)
+				break;
+		}
+		rc = FAILED;
+		break;
+
+	case MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET:
+		if ((channel == 0xFFFFFFFF) && (id == 0xFFFFFFFF))
+			break;
+		instance->instancet->disable_intr(instance);
+		msleep(1000);
+		megasas_complete_cmd_dpc_fusion
+				((unsigned long)instance);
+		rc = megasas_track_scsiio(instance, id, channel);
+		instance->instancet->enable_intr(instance);
+
+		break;
+	case MPI2_SCSITASKMGMT_TASKTYPE_ABRT_TASK_SET:
+	case MPI2_SCSITASKMGMT_TASKTYPE_QUERY_TASK:
+		break;
+	default:
+		rc = FAILED;
+		break;
+	}
+
+	return rc;
+
+}
+
+/*
+ * megasas_fusion_smid_lookup : Look for fusion command correpspodning to SCSI
+ * @instance: per adapter struct
+ *
+ * Return Non Zero index, if SMID found in outstanding commands
+ */
+static u16 megasas_fusion_smid_lookup(struct scsi_cmnd *scmd)
+{
+	int i, ret = 0;
+	struct megasas_instance *instance;
+	struct megasas_cmd_fusion *cmd_fusion;
+	struct fusion_context *fusion;
+
+	instance = (struct megasas_instance *)scmd->device->host->hostdata;
+
+	fusion = instance->ctrl_context;
+
+	for (i = 0; i < instance->max_scsi_cmds; i++) {
+		cmd_fusion = fusion->cmd_list[i];
+		if (cmd_fusion->scmd && (cmd_fusion->scmd == scmd)) {
+			scmd_printk(KERN_NOTICE, scmd, "Abort request is for"
+				" SMID: %d\n", cmd_fusion->index);
+			ret = cmd_fusion->index;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+/*
+* megasas_get_tm_devhandle - Get devhandle for TM request
+* @sdev-		     OS provided scsi device
+*
+* Returns-		     devhandle/targetID of SCSI device
+*/
+static u16 megasas_get_tm_devhandle(struct scsi_device *sdev)
+{
+	u16 pd_index = 0;
+	u32 device_id;
+	struct megasas_instance *instance;
+	struct fusion_context *fusion;
+	struct MR_PD_CFG_SEQ_NUM_SYNC *pd_sync;
+	u16 devhandle = (u16)ULONG_MAX;
+
+	instance = (struct megasas_instance *)sdev->host->hostdata;
+	fusion = instance->ctrl_context;
+
+	if (sdev->channel < MEGASAS_MAX_PD_CHANNELS) {
+		if (instance->use_seqnum_jbod_fp) {
+				pd_index = (sdev->channel * MEGASAS_MAX_DEV_PER_CHANNEL) +
+						sdev->id;
+				pd_sync = (void *)fusion->pd_seq_sync
+						[(instance->pd_seq_map_id - 1) & 1];
+				devhandle = pd_sync->seq[pd_index].devHandle;
+		} else
+			sdev_printk(KERN_ERR, sdev, "Firmware expose tmCapable"
+				" without JBOD MAP support from %s %d\n", __func__, __LINE__);
+	} else {
+		device_id = ((sdev->channel % 2) * MEGASAS_MAX_DEV_PER_CHANNEL)
+				+ sdev->id;
+		devhandle = device_id;
+	}
+
+	return devhandle;
+}
+
+/*
+ * megasas_task_abort_fusion : SCSI task abort function for fusion adapters
+ * @scmd : pointer to scsi command object
+ *
+ * Return SUCCESS, if command aborted else FAILED
+ */
+
+int megasas_task_abort_fusion(struct scsi_cmnd *scmd)
+{
+	struct megasas_instance *instance;
+	u16 smid, devhandle;
+	struct fusion_context *fusion;
+	int ret;
+	struct MR_PRIV_DEVICE *mr_device_priv_data;
+	mr_device_priv_data = scmd->device->hostdata;
+
+
+	instance = (struct megasas_instance *)scmd->device->host->hostdata;
+	fusion = instance->ctrl_context;
+
+	if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL) {
+		dev_err(&instance->pdev->dev, "Controller is not OPERATIONAL,"
+		"SCSI host:%d\n", instance->host->host_no);
+		ret = FAILED;
+		return ret;
+	}
+
+	if (!mr_device_priv_data) {
+		sdev_printk(KERN_INFO, scmd->device, "device been deleted! "
+			"scmd(%p)\n", scmd);
+		scmd->result = DID_NO_CONNECT << 16;
+		ret = SUCCESS;
+		goto out;
+	}
+
+
+	if (!mr_device_priv_data->is_tm_capable) {
+		ret = FAILED;
+		goto out;
+	}
+
+	mutex_lock(&instance->reset_mutex);
+
+	smid = megasas_fusion_smid_lookup(scmd);
+
+	if (!smid) {
+		ret = SUCCESS;
+		scmd_printk(KERN_NOTICE, scmd, "Command for which abort is"
+			" issued is not found in oustanding commands\n");
+		mutex_unlock(&instance->reset_mutex);
+		goto out;
+	}
+
+	devhandle = megasas_get_tm_devhandle(scmd->device);
+
+	if (devhandle == (u16)ULONG_MAX) {
+		ret = SUCCESS;
+		sdev_printk(KERN_INFO, scmd->device,
+			"task abort issued for invalid devhandle\n");
+		mutex_unlock(&instance->reset_mutex);
+		goto out;
+	}
+	sdev_printk(KERN_INFO, scmd->device,
+		"attempting task abort! scmd(%p) tm_dev_handle 0x%x\n",
+		scmd, devhandle);
+
+	mr_device_priv_data->tm_busy = 1;
+	ret = megasas_issue_tm(instance, devhandle,
+			scmd->device->channel, scmd->device->id, smid,
+			MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK);
+	mr_device_priv_data->tm_busy = 0;
+
+	mutex_unlock(&instance->reset_mutex);
+out:
+	sdev_printk(KERN_INFO, scmd->device, "task abort: %s scmd(%p)\n",
+			((ret == SUCCESS) ? "SUCCESS" : "FAILED"), scmd);
+
+	return ret;
+}
+
+/*
+ * megasas_reset_target_fusion : target reset function for fusion adapters
+ * scmd: SCSI command pointer
+ *
+ * Returns SUCCESS if all commands associated with target aborted else FAILED
+ */
+
+int megasas_reset_target_fusion(struct scsi_cmnd *scmd)
+{
+
+	struct megasas_instance *instance;
+	int ret = FAILED;
+	u16 devhandle;
+	struct fusion_context *fusion;
+	struct MR_PRIV_DEVICE *mr_device_priv_data;
+	mr_device_priv_data = scmd->device->hostdata;
+
+	instance = (struct megasas_instance *)scmd->device->host->hostdata;
+	fusion = instance->ctrl_context;
+
+	if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL) {
+		dev_err(&instance->pdev->dev, "Controller is not OPERATIONAL,"
+		"SCSI host:%d\n", instance->host->host_no);
+		ret = FAILED;
+		return ret;
+	}
+
+	if (!mr_device_priv_data) {
+		sdev_printk(KERN_INFO, scmd->device, "device been deleted! "
+			"scmd(%p)\n", scmd);
+		scmd->result = DID_NO_CONNECT << 16;
+		ret = SUCCESS;
+		goto out;
+	}
+
+
+	if (!mr_device_priv_data->is_tm_capable) {
+		ret = FAILED;
+		goto out;
+	}
+
+	mutex_lock(&instance->reset_mutex);
+	devhandle = megasas_get_tm_devhandle(scmd->device);
+
+	if (devhandle == (u16)ULONG_MAX) {
+		ret = SUCCESS;
+		sdev_printk(KERN_INFO, scmd->device,
+			"target reset issued for invalid devhandle\n");
+		mutex_unlock(&instance->reset_mutex);
+		goto out;
+	}
+
+	sdev_printk(KERN_INFO, scmd->device,
+		"attempting target reset! scmd(%p) tm_dev_handle 0x%x\n",
+		scmd, devhandle);
+	mr_device_priv_data->tm_busy = 1;
+	ret = megasas_issue_tm(instance, devhandle,
+			scmd->device->channel, scmd->device->id, 0,
+			MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET);
+	mr_device_priv_data->tm_busy = 0;
+	mutex_unlock(&instance->reset_mutex);
+out:
+	scmd_printk(KERN_NOTICE, scmd, "megasas: target reset %s!!\n",
+		(ret == SUCCESS) ? "SUCCESS" : "FAILED");
+
+	return ret;
+}
+
+/*SRIOV get other instance in cluster if any*/
+struct megasas_instance *megasas_get_peer_instance(struct megasas_instance *instance)
+{
+	int i;
+
+	for (i = 0; i < MAX_MGMT_ADAPTERS; i++) {
+		if (megasas_mgmt_info.instance[i] &&
+			(megasas_mgmt_info.instance[i] != instance) &&
+			 megasas_mgmt_info.instance[i]->requestorId &&
+			 megasas_mgmt_info.instance[i]->peerIsPresent &&
+			(memcmp((megasas_mgmt_info.instance[i]->clusterId),
+			instance->clusterId, MEGASAS_CLUSTER_ID_SIZE) == 0))
+			return megasas_mgmt_info.instance[i];
+	}
+	return NULL;
+}
+
 /* Check for a second path that is currently UP */
 int megasas_check_mpio_paths(struct megasas_instance *instance,
 	struct scsi_cmnd *scmd)
 {
-	int i, j, retval = (DID_RESET << 16);
-
-	if (instance->mpio && instance->requestorId) {
-		for (i = 0 ; i < MAX_MGMT_ADAPTERS ; i++)
-			for (j = 0 ; j < MAX_LOGICAL_DRIVES; j++)
-				if (megasas_mgmt_info.instance[i] &&
-				    (megasas_mgmt_info.instance[i] != instance) &&
-				    megasas_mgmt_info.instance[i]->mpio &&
-				    megasas_mgmt_info.instance[i]->requestorId
-				    &&
-				    (megasas_mgmt_info.instance[i]->ld_ids[j]
-				     == scmd->device->id)) {
-					    retval = (DID_NO_CONNECT << 16);
-					    goto out;
-				}
+	struct megasas_instance *peer_instance = NULL;
+	int retval = (DID_RESET << 16);
+
+	if (instance->peerIsPresent) {
+		peer_instance = megasas_get_peer_instance(instance);
+		if ((peer_instance) &&
+			(atomic_read(&peer_instance->adprecovery) ==
+			MEGASAS_HBA_OPERATIONAL))
+			retval = (DID_NO_CONNECT << 16);
 	}
-out:
 	return retval;
 }
 
 /* Core fusion reset function */
-int megasas_reset_fusion(struct Scsi_Host *shost, int iotimeout)
+int megasas_reset_fusion(struct Scsi_Host *shost, int reason)
 {
 	int retval = SUCCESS, i, convert = 0;
 	struct megasas_instance *instance;
@@ -2739,13 +3370,14 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int iotimeout)
 	u32 abs_state, status_reg, reset_adapter;
 	u32 io_timeout_in_crash_mode = 0;
 	struct scsi_cmnd *scmd_local = NULL;
+	struct scsi_device *sdev;
 
 	instance = (struct megasas_instance *)shost->hostdata;
 	fusion = instance->ctrl_context;
 
 	mutex_lock(&instance->reset_mutex);
 
-	if (instance->adprecovery == MEGASAS_HW_CRITICAL_ERROR) {
+	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
 		dev_warn(&instance->pdev->dev, "Hardware critical error, "
 		       "returning FAILED for scsi%d.\n",
 			instance->host->host_no);
@@ -2757,10 +3389,10 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int iotimeout)
 
 	/* IO timeout detected, forcibly put FW in FAULT state */
 	if (abs_state != MFI_STATE_FAULT && instance->crash_dump_buf &&
-		instance->crash_dump_app_support && iotimeout) {
-		dev_info(&instance->pdev->dev, "IO timeout is detected, "
+		instance->crash_dump_app_support && reason) {
+		dev_info(&instance->pdev->dev, "IO/DCMD timeout is detected, "
 			"forcibly FAULT Firmware\n");
-		instance->adprecovery = MEGASAS_ADPRESET_SM_INFAULT;
+		atomic_set(&instance->adprecovery, MEGASAS_ADPRESET_SM_INFAULT);
 		status_reg = readl(&instance->reg_set->doorbell);
 		writel(status_reg | MFI_STATE_FORCE_OCR,
 			&instance->reg_set->doorbell);
@@ -2772,10 +3404,10 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int iotimeout)
 			dev_dbg(&instance->pdev->dev, "waiting for [%d] "
 				"seconds for crash dump collection and OCR "
 				"to be done\n", (io_timeout_in_crash_mode * 3));
-		} while ((instance->adprecovery != MEGASAS_HBA_OPERATIONAL) &&
+		} while ((atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL) &&
 			(io_timeout_in_crash_mode < 80));
 
-		if (instance->adprecovery == MEGASAS_HBA_OPERATIONAL) {
+		if (atomic_read(&instance->adprecovery) == MEGASAS_HBA_OPERATIONAL) {
 			dev_info(&instance->pdev->dev, "OCR done for IO "
 				"timeout case\n");
 			retval = SUCCESS;
@@ -2792,18 +3424,18 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int iotimeout)
 	if (instance->requestorId && !instance->skip_heartbeat_timer_del)
 		del_timer_sync(&instance->sriov_heartbeat_timer);
 	set_bit(MEGASAS_FUSION_IN_RESET, &instance->reset_flags);
-	instance->adprecovery = MEGASAS_ADPRESET_SM_POLLING;
+	atomic_set(&instance->adprecovery, MEGASAS_ADPRESET_SM_POLLING);
 	instance->instancet->disable_intr(instance);
 	msleep(1000);
 
 	/* First try waiting for commands to complete */
-	if (megasas_wait_for_outstanding_fusion(instance, iotimeout,
+	if (megasas_wait_for_outstanding_fusion(instance, reason,
 						&convert)) {
-		instance->adprecovery = MEGASAS_ADPRESET_SM_INFAULT;
+		atomic_set(&instance->adprecovery, MEGASAS_ADPRESET_SM_INFAULT);
 		dev_warn(&instance->pdev->dev, "resetting fusion "
 		       "adapter scsi%d.\n", instance->host->host_no);
 		if (convert)
-			iotimeout = 0;
+			reason = 0;
 
 		/* Now return commands back to the OS */
 		for (i = 0 ; i < instance->max_scsi_cmds; i++) {
@@ -2813,6 +3445,8 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int iotimeout)
 				scmd_local->result =
 					megasas_check_mpio_paths(instance,
 							scmd_local);
+				if (megasas_cmd_type(scmd_local) == READ_WRITE_LDIO)
+					atomic_dec(&instance->ldio_outstanding);
 				megasas_return_cmd_fusion(instance, cmd_fusion);
 				scsi_dma_unmap(scmd_local);
 				scmd_local->scsi_done(scmd_local);
@@ -2837,55 +3471,9 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int iotimeout)
 		}
 
 		/* Let SR-IOV VF & PF sync up if there was a HB failure */
-		if (instance->requestorId && !iotimeout) {
+		if (instance->requestorId && !reason) {
 			msleep(MEGASAS_OCR_SETTLE_TIME_VF);
-			/* Look for a late HB update after VF settle time */
-			if (abs_state == MFI_STATE_OPERATIONAL &&
-			    (instance->hb_host_mem->HB.fwCounter !=
-			     instance->hb_host_mem->HB.driverCounter)) {
-					instance->hb_host_mem->HB.driverCounter =
-						instance->hb_host_mem->HB.fwCounter;
-					dev_warn(&instance->pdev->dev, "SR-IOV:"
-					       "Late FW heartbeat update for "
-					       "scsi%d.\n",
-					       instance->host->host_no);
-			} else {
-				/* In VF mode, first poll for FW ready */
-				for (i = 0;
-				     i < (MEGASAS_RESET_WAIT_TIME * 1000);
-				     i += 20) {
-					status_reg =
-						instance->instancet->
-						read_fw_status_reg(
-							instance->reg_set);
-					abs_state = status_reg &
-						MFI_STATE_MASK;
-					if (abs_state == MFI_STATE_READY) {
-						dev_warn(&instance->pdev->dev,
-						       "SR-IOV: FW was found"
-						       "to be in ready state "
-						       "for scsi%d.\n",
-						       instance->host->host_no);
-						break;
-					}
-					msleep(20);
-				}
-				if (abs_state != MFI_STATE_READY) {
-					dev_warn(&instance->pdev->dev, "SR-IOV: "
-					       "FW not in ready state after %d"
-					       " seconds for scsi%d, status_reg = "
-					       "0x%x.\n",
-					       MEGASAS_RESET_WAIT_TIME,
-					       instance->host->host_no,
-					       status_reg);
-					megaraid_sas_kill_hba(instance);
-					instance->skip_heartbeat_timer_del = 1;
-					instance->adprecovery =
-						MEGASAS_HW_CRITICAL_ERROR;
-					retval = FAILED;
-					goto out;
-				}
-			}
+			goto transition_to_ready;
 		}
 
 		/* Now try to reset the chip */
@@ -2894,23 +3482,28 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int iotimeout)
 			if (instance->instancet->adp_reset
 				(instance, instance->reg_set))
 				continue;
-
+transition_to_ready:
 			/* Wait for FW to become ready */
 			if (megasas_transition_to_ready(instance, 1)) {
-				dev_warn(&instance->pdev->dev, "Failed to "
-				       "transition controller to ready "
-				       "for scsi%d.\n",
-				       instance->host->host_no);
-				continue;
+				dev_warn(&instance->pdev->dev,
+					"Failed to transition controller to ready for "
+					"scsi%d.\n", instance->host->host_no);
+				if (instance->requestorId && !reason)
+					goto fail_kill_adapter;
+				else
+					continue;
 			}
-
 			megasas_reset_reply_desc(instance);
+			megasas_fusion_update_can_queue(instance, OCR_CONTEXT);
+
 			if (megasas_ioc_init_fusion(instance)) {
 				dev_warn(&instance->pdev->dev,
-				       "megasas_ioc_init_fusion() failed!"
-				       " for scsi%d\n",
-				       instance->host->host_no);
-				continue;
+				       "megasas_ioc_init_fusion() failed! for "
+				       "scsi%d\n", instance->host->host_no);
+				if (instance->requestorId && !reason)
+					goto fail_kill_adapter;
+				else
+					continue;
 			}
 
 			megasas_refire_mgmt_cmd(instance);
@@ -2932,10 +3525,13 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int iotimeout)
 
 			megasas_setup_jbod_map(instance);
 
+			shost_for_each_device(sdev, shost)
+				megasas_update_sdev_properties(sdev);
+
 			clear_bit(MEGASAS_FUSION_IN_RESET,
 				  &instance->reset_flags);
 			instance->instancet->enable_intr(instance);
-			instance->adprecovery = MEGASAS_HBA_OPERATIONAL;
+			atomic_set(&instance->adprecovery, MEGASAS_HBA_OPERATIONAL);
 
 			/* Restart SR-IOV heartbeat */
 			if (instance->requestorId) {
@@ -2964,6 +3560,7 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int iotimeout)
 			retval = SUCCESS;
 			goto out;
 		}
+fail_kill_adapter:
 		/* Reset failed, kill the adapter */
 		dev_warn(&instance->pdev->dev, "Reset failed, killing "
 		       "adapter scsi%d.\n", instance->host->host_no);
@@ -2980,7 +3577,7 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int iotimeout)
 		}
 		clear_bit(MEGASAS_FUSION_IN_RESET, &instance->reset_flags);
 		instance->instancet->enable_intr(instance);
-		instance->adprecovery = MEGASAS_HBA_OPERATIONAL;
+		atomic_set(&instance->adprecovery, MEGASAS_HBA_OPERATIONAL);
 	}
 out:
 	clear_bit(MEGASAS_FUSION_IN_RESET, &instance->reset_flags);
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.h b/drivers/scsi/megaraid/megaraid_sas_fusion.h
index 473005c99b44..80eaee22f5bc 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.h
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.h
@@ -176,7 +176,9 @@ enum REGION_TYPE {
 #define MPI2_SCSIIO_EEDPFLAGS_CHECK_GUARD           (0x0100)
 #define MPI2_SCSIIO_EEDPFLAGS_INSERT_OP             (0x0004)
 #define MPI2_FUNCTION_SCSI_IO_REQUEST               (0x00) /* SCSI IO */
-#define MPI2_REQ_DESCRIPT_FLAGS_HIGH_PRIORITY           (0x06)
+#define MPI2_FUNCTION_SCSI_TASK_MGMT                (0x01)
+#define MPI2_REQ_DESCRIPT_FLAGS_HIGH_PRIORITY       (0x03)
+#define MPI2_REQ_DESCRIPT_FLAGS_FP_IO               (0x06)
 #define MPI2_REQ_DESCRIPT_FLAGS_SCSI_IO                 (0x00)
 #define MPI2_SGE_FLAGS_64_BIT_ADDRESSING        (0x02)
 #define MPI2_SCSIIO_CONTROL_WRITE               (0x01000000)
@@ -277,6 +279,100 @@ union MPI2_SCSI_IO_CDB_UNION {
 	struct MPI2_SGE_SIMPLE_UNION SGE;
 };
 
+/****************************************************************************
+*  SCSI Task Management messages
+****************************************************************************/
+
+/*SCSI Task Management Request Message */
+struct MPI2_SCSI_TASK_MANAGE_REQUEST {
+	u16 DevHandle;		/*0x00 */
+	u8 ChainOffset;		/*0x02 */
+	u8 Function;		/*0x03 */
+	u8 Reserved1;		/*0x04 */
+	u8 TaskType;		/*0x05 */
+	u8 Reserved2;		/*0x06 */
+	u8 MsgFlags;		/*0x07 */
+	u8 VP_ID;		/*0x08 */
+	u8 VF_ID;		/*0x09 */
+	u16 Reserved3;		/*0x0A */
+	u8 LUN[8];		/*0x0C */
+	u32 Reserved4[7];	/*0x14 */
+	u16 TaskMID;		/*0x30 */
+	u16 Reserved5;		/*0x32 */
+};
+
+
+/*SCSI Task Management Reply Message */
+struct MPI2_SCSI_TASK_MANAGE_REPLY {
+	u16 DevHandle;		/*0x00 */
+	u8 MsgLength;		/*0x02 */
+	u8 Function;		/*0x03 */
+	u8 ResponseCode;	/*0x04 */
+	u8 TaskType;		/*0x05 */
+	u8 Reserved1;		/*0x06 */
+	u8 MsgFlags;		/*0x07 */
+	u8 VP_ID;		/*0x08 */
+	u8 VF_ID;		/*0x09 */
+	u16 Reserved2;		/*0x0A */
+	u16 Reserved3;		/*0x0C */
+	u16 IOCStatus;		/*0x0E */
+	u32 IOCLogInfo;		/*0x10 */
+	u32 TerminationCount;	/*0x14 */
+	u32 ResponseInfo;	/*0x18 */
+};
+
+struct MR_TM_REQUEST {
+	char request[128];
+};
+
+struct MR_TM_REPLY {
+	char reply[128];
+};
+
+/* SCSI Task Management Request Message */
+struct MR_TASK_MANAGE_REQUEST {
+	/*To be type casted to struct MPI2_SCSI_TASK_MANAGE_REQUEST */
+	struct MR_TM_REQUEST         TmRequest;
+	union {
+		struct {
+#if   defined(__BIG_ENDIAN_BITFIELD)
+			u32 reserved1:30;
+			u32 isTMForPD:1;
+			u32 isTMForLD:1;
+#else
+			u32 isTMForLD:1;
+			u32 isTMForPD:1;
+			u32 reserved1:30;
+#endif
+			u32 reserved2;
+		} tmReqFlags;
+		struct MR_TM_REPLY   TMReply;
+	};
+};
+
+/* TaskType values */
+
+#define MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK           (0x01)
+#define MPI2_SCSITASKMGMT_TASKTYPE_ABRT_TASK_SET        (0x02)
+#define MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET         (0x03)
+#define MPI2_SCSITASKMGMT_TASKTYPE_LOGICAL_UNIT_RESET   (0x05)
+#define MPI2_SCSITASKMGMT_TASKTYPE_CLEAR_TASK_SET       (0x06)
+#define MPI2_SCSITASKMGMT_TASKTYPE_QUERY_TASK           (0x07)
+#define MPI2_SCSITASKMGMT_TASKTYPE_CLR_ACA              (0x08)
+#define MPI2_SCSITASKMGMT_TASKTYPE_QRY_TASK_SET         (0x09)
+#define MPI2_SCSITASKMGMT_TASKTYPE_QRY_ASYNC_EVENT      (0x0A)
+
+/* ResponseCode values */
+
+#define MPI2_SCSITASKMGMT_RSP_TM_COMPLETE               (0x00)
+#define MPI2_SCSITASKMGMT_RSP_INVALID_FRAME             (0x02)
+#define MPI2_SCSITASKMGMT_RSP_TM_NOT_SUPPORTED          (0x04)
+#define MPI2_SCSITASKMGMT_RSP_TM_FAILED                 (0x05)
+#define MPI2_SCSITASKMGMT_RSP_TM_SUCCEEDED              (0x08)
+#define MPI2_SCSITASKMGMT_RSP_TM_INVALID_LUN            (0x09)
+#define MPI2_SCSITASKMGMT_RSP_TM_OVERLAPPED_TAG         (0x0A)
+#define MPI2_SCSITASKMGMT_RSP_IO_QUEUED_ON_IOC          (0x80)
+
 /*
  * RAID SCSI IO Request Message
  * Total SGE count will be one less than  _MPI2_SCSI_IO_REQUEST
@@ -547,7 +643,9 @@ struct MR_SPAN_BLOCK_INFO {
 struct MR_LD_RAID {
 	struct {
 #if   defined(__BIG_ENDIAN_BITFIELD)
-		u32     reserved4:7;
+		u32     reserved4:5;
+		u32     fpBypassRegionLock:1;
+		u32     tmCapable:1;
 		u32	fpNonRWCapable:1;
 		u32     fpReadAcrossStripe:1;
 		u32     fpWriteAcrossStripe:1;
@@ -569,7 +667,9 @@ struct MR_LD_RAID {
 		u32     fpWriteAcrossStripe:1;
 		u32     fpReadAcrossStripe:1;
 		u32	fpNonRWCapable:1;
-		u32     reserved4:7;
+		u32     tmCapable:1;
+		u32     fpBypassRegionLock:1;
+		u32     reserved4:5;
 #endif
 	} capability;
 	__le32     reserved6;
@@ -639,7 +739,7 @@ struct IO_REQUEST_INFO {
 	u8 fpOkForIo;
 	u8 IoforUnevenSpan;
 	u8 start_span;
-	u8 reserved;
+	u8 do_fp_rlbypass;
 	u64 start_row;
 	u8  span_arm;	/* span[7:5], arm[4:0] */
 	u8  pd_after_lb;
@@ -694,6 +794,7 @@ struct megasas_cmd_fusion {
 	u32 sync_cmd_idx;
 	u32 index;
 	u8 pd_r1_lb;
+	struct completion done;
 };
 
 struct LD_LOAD_BALANCE_INFO {
@@ -807,9 +908,18 @@ struct MR_FW_RAID_MAP_EXT {
  *  * define MR_PD_CFG_SEQ structure for system PDs
  *   */
 struct MR_PD_CFG_SEQ {
-	__le16 seqNum;
-	__le16 devHandle;
-	u8  reserved[4];
+	u16 seqNum;
+	u16 devHandle;
+	struct {
+#if   defined(__BIG_ENDIAN_BITFIELD)
+		u8     reserved:7;
+		u8     tmCapable:1;
+#else
+		u8     tmCapable:1;
+		u8     reserved:7;
+#endif
+	} capability;
+	u8  reserved[3];
 } __packed;
 
 struct MR_PD_CFG_SEQ_NUM_SYNC {
@@ -818,6 +928,12 @@ struct MR_PD_CFG_SEQ_NUM_SYNC {
 	struct MR_PD_CFG_SEQ seq[1];
 } __packed;
 
+struct MPI2_IOC_INIT_RDPQ_ARRAY_ENTRY {
+	u64 RDPQBaseAddress;
+	u32 Reserved1;
+	u32 Reserved2;
+};
+
 struct fusion_context {
 	struct megasas_cmd_fusion **cmd_list;
 	dma_addr_t req_frames_desc_phys;
@@ -830,8 +946,8 @@ struct fusion_context {
 	struct dma_pool *sg_dma_pool;
 	struct dma_pool *sense_dma_pool;
 
-	dma_addr_t reply_frames_desc_phys;
-	union MPI2_REPLY_DESCRIPTORS_UNION *reply_frames_desc;
+	dma_addr_t reply_frames_desc_phys[MAX_MSIX_QUEUES_FUSION];
+	union MPI2_REPLY_DESCRIPTORS_UNION *reply_frames_desc[MAX_MSIX_QUEUES_FUSION];
 	struct dma_pool *reply_frames_desc_pool;
 
 	u16 last_reply_idx[MAX_MSIX_QUEUES_FUSION];
@@ -841,6 +957,8 @@ struct fusion_context {
 	u32 reply_alloc_sz;
 	u32 io_frames_alloc_sz;
 
+	struct MPI2_IOC_INIT_RDPQ_ARRAY_ENTRY *rdpq_virt;
+	dma_addr_t rdpq_phys;
 	u16	max_sge_in_main_msg;
 	u16	max_sge_in_chain;
 
diff --git a/drivers/scsi/mesh.c b/drivers/scsi/mesh.c
index 555367f00228..1753e42826dd 100644
--- a/drivers/scsi/mesh.c
+++ b/drivers/scsi/mesh.c
@@ -29,6 +29,7 @@
 #include <linux/interrupt.h>
 #include <linux/reboot.h>
 #include <linux/spinlock.h>
+#include <linux/pci.h>
 #include <asm/dbdma.h>
 #include <asm/io.h>
 #include <asm/pgtable.h>
@@ -38,7 +39,6 @@
 #include <asm/processor.h>
 #include <asm/machdep.h>
 #include <asm/pmac_feature.h>
-#include <asm/pci-bridge.h>
 #include <asm/macio.h>
 
 #include <scsi/scsi.h>
diff --git a/drivers/scsi/mpt3sas/mpi/mpi2.h b/drivers/scsi/mpt3sas/mpi/mpi2.h
index ec27ad2d186f..dfad5b8c1890 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2000-2014 LSI Corporation.
+ * Copyright 2000-2015 Avago Technologies.  All rights reserved.
  *
  *
  *          Name:  mpi2.h
@@ -8,7 +8,7 @@
  *                 scatter/gather formats.
  * Creation Date:  June 21, 2006
  *
- * mpi2.h Version:  02.00.35
+ * mpi2.h Version:  02.00.39
  *
  * NOTE: Names (typedefs, defines, etc.) beginning with an MPI25 or Mpi25
  *       prefix are for use only on MPI v2.5 products, and must not be used
@@ -92,6 +92,14 @@
  * 12-05-13  02.00.33  Bumped MPI2_HEADER_VERSION_UNIT.
  * 01-08-14  02.00.34  Bumped MPI2_HEADER_VERSION_UNIT
  * 06-13-14  02.00.35  Bumped MPI2_HEADER_VERSION_UNIT.
+ * 11-18-14  02.00.36  Updated copyright information.
+ *                     Bumped MPI2_HEADER_VERSION_UNIT.
+ * 03-16-15  02.00.37  Bumped MPI2_HEADER_VERSION_UNIT.
+ *                     Added Scratchpad registers to
+ *                     MPI2_SYSTEM_INTERFACE_REGS.
+ *                     Added MPI2_DIAG_SBR_RELOAD.
+ * 03-19-15  02.00.38  Bumped MPI2_HEADER_VERSION_UNIT.
+ * 05-25-15  02.00.39  Bumped MPI2_HEADER_VERSION_UNIT.
  * --------------------------------------------------------------------------
  */
 
@@ -124,8 +132,14 @@
 					MPI25_VERSION_MINOR)
 #define MPI2_VERSION_02_05                  (0x0205)
 
+/*minor version for MPI v2.6 compatible products */
+#define MPI26_VERSION_MINOR		    (0x06)
+#define MPI26_VERSION ((MPI2_VERSION_MAJOR << MPI2_VERSION_MAJOR_SHIFT) | \
+					MPI26_VERSION_MINOR)
+#define MPI2_VERSION_02_06		    (0x0206)
+
 /*Unit and Dev versioning for this MPI header set */
-#define MPI2_HEADER_VERSION_UNIT            (0x23)
+#define MPI2_HEADER_VERSION_UNIT            (0x27)
 #define MPI2_HEADER_VERSION_DEV             (0x00)
 #define MPI2_HEADER_VERSION_UNIT_MASK       (0xFF00)
 #define MPI2_HEADER_VERSION_UNIT_SHIFT      (8)
@@ -179,10 +193,12 @@ typedef volatile struct _MPI2_SYSTEM_INTERFACE_REGS {
 	U32 HCBSize;		/*0x74 */
 	U32 HCBAddressLow;	/*0x78 */
 	U32 HCBAddressHigh;	/*0x7C */
-	U32 Reserved6[16];	/*0x80 */
+	U32 Reserved6[12];	/*0x80 */
+	U32 Scratchpad[4];	/*0xB0 */
 	U32 RequestDescriptorPostLow;	/*0xC0 */
 	U32 RequestDescriptorPostHigh;	/*0xC4 */
-	U32 Reserved7[14];	/*0xC8 */
+	U32 AtomicRequestDescriptorPost;/*0xC8 */
+	U32 Reserved7[13];	/*0xCC */
 } MPI2_SYSTEM_INTERFACE_REGS,
 	*PTR_MPI2_SYSTEM_INTERFACE_REGS,
 	Mpi2SystemInterfaceRegs_t,
@@ -224,6 +240,8 @@ typedef volatile struct _MPI2_SYSTEM_INTERFACE_REGS {
  */
 #define MPI2_HOST_DIAGNOSTIC_OFFSET             (0x00000008)
 
+#define MPI2_DIAG_SBR_RELOAD                    (0x00002000)
+
 #define MPI2_DIAG_BOOT_DEVICE_SELECT_MASK       (0x00001800)
 #define MPI2_DIAG_BOOT_DEVICE_SELECT_DEFAULT    (0x00000000)
 #define MPI2_DIAG_BOOT_DEVICE_SELECT_HCDW       (0x00000800)
@@ -298,10 +316,19 @@ typedef volatile struct _MPI2_SYSTEM_INTERFACE_REGS {
 #define MPI2_HCB_ADDRESS_HIGH_OFFSET            (0x0000007C)
 
 /*
- *Offsets for the Request Queue
+ *Offsets for the Scratchpad registers
+ */
+#define MPI26_SCRATCHPAD0_OFFSET                (0x000000B0)
+#define MPI26_SCRATCHPAD1_OFFSET                (0x000000B4)
+#define MPI26_SCRATCHPAD2_OFFSET                (0x000000B8)
+#define MPI26_SCRATCHPAD3_OFFSET                (0x000000BC)
+
+/*
+ *Offsets for the Request Descriptor Post Queue
  */
 #define MPI2_REQUEST_DESCRIPTOR_POST_LOW_OFFSET     (0x000000C0)
 #define MPI2_REQUEST_DESCRIPTOR_POST_HIGH_OFFSET    (0x000000C4)
+#define MPI26_ATOMIC_REQUEST_DESCRIPTOR_POST_OFFSET (0x000000C8)
 
 /*Hard Reset delay timings */
 #define MPI2_HARD_RESET_PCIE_FIRST_READ_DELAY_MICRO_SEC     (50000)
@@ -329,7 +356,8 @@ typedef struct _MPI2_DEFAULT_REQUEST_DESCRIPTOR {
 	*pMpi2DefaultRequestDescriptor_t;
 
 /*defines for the RequestFlags field */
-#define MPI2_REQ_DESCRIPT_FLAGS_TYPE_MASK               (0x0E)
+#define MPI2_REQ_DESCRIPT_FLAGS_TYPE_MASK               (0x1E)
+#define MPI2_REQ_DESCRIPT_FLAGS_TYPE_RSHIFT             (1)
 #define MPI2_REQ_DESCRIPT_FLAGS_SCSI_IO                 (0x00)
 #define MPI2_REQ_DESCRIPT_FLAGS_SCSI_TARGET             (0x02)
 #define MPI2_REQ_DESCRIPT_FLAGS_HIGH_PRIORITY           (0x06)
@@ -337,7 +365,7 @@ typedef struct _MPI2_DEFAULT_REQUEST_DESCRIPTOR {
 #define MPI2_REQ_DESCRIPT_FLAGS_RAID_ACCELERATOR        (0x0A)
 #define MPI25_REQ_DESCRIPT_FLAGS_FAST_PATH_SCSI_IO      (0x0C)
 
-#define MPI2_REQ_DESCRIPT_FLAGS_IOC_FIFO_MARKER (0x01)
+#define MPI2_REQ_DESCRIPT_FLAGS_IOC_FIFO_MARKER         (0x01)
 
 /*High Priority Request Descriptor */
 typedef struct _MPI2_HIGH_PRIORITY_REQUEST_DESCRIPTOR {
@@ -408,6 +436,33 @@ typedef union _MPI2_REQUEST_DESCRIPTOR_UNION {
 	Mpi2RequestDescriptorUnion_t,
 	*pMpi2RequestDescriptorUnion_t;
 
+/*Atomic Request Descriptors */
+
+/*
+ * All Atomic Request Descriptors have the same format, so the following
+ * structure is used for all Atomic Request Descriptors:
+ *      Atomic Default Request Descriptor
+ *      Atomic High Priority Request Descriptor
+ *      Atomic SCSI IO Request Descriptor
+ *      Atomic SCSI Target Request Descriptor
+ *      Atomic RAID Accelerator Request Descriptor
+ *      Atomic Fast Path SCSI IO Request Descriptor
+ */
+
+/*Atomic Request Descriptor */
+typedef struct _MPI26_ATOMIC_REQUEST_DESCRIPTOR {
+	U8 RequestFlags;	/* 0x00 */
+	U8 MSIxIndex;		/* 0x01 */
+	U16 SMID;		/* 0x02 */
+} MPI26_ATOMIC_REQUEST_DESCRIPTOR,
+	*PTR_MPI26_ATOMIC_REQUEST_DESCRIPTOR,
+	Mpi26AtomicRequestDescriptor_t,
+	*pMpi26AtomicRequestDescriptor_t;
+
+/*for the RequestFlags field, use the same
+ *defines as MPI2_DEFAULT_REQUEST_DESCRIPTOR
+ */
+
 /*Reply Descriptors */
 
 /*Default Reply Descriptor */
@@ -548,6 +603,7 @@ typedef union _MPI2_REPLY_DESCRIPTORS_UNION {
 #define MPI2_FUNCTION_SCSI_ENCLOSURE_PROCESSOR      (0x18)
 #define MPI2_FUNCTION_SMP_PASSTHROUGH               (0x1A)
 #define MPI2_FUNCTION_SAS_IO_UNIT_CONTROL           (0x1B)
+#define MPI2_FUNCTION_IO_UNIT_CONTROL               (0x1B)
 #define MPI2_FUNCTION_SATA_PASSTHROUGH              (0x1C)
 #define MPI2_FUNCTION_DIAG_BUFFER_POST              (0x1D)
 #define MPI2_FUNCTION_DIAG_RELEASE                  (0x1E)
@@ -587,6 +643,7 @@ typedef union _MPI2_REPLY_DESCRIPTORS_UNION {
 #define MPI2_IOCSTATUS_INVALID_FIELD                (0x0007)
 #define MPI2_IOCSTATUS_INVALID_STATE                (0x0008)
 #define MPI2_IOCSTATUS_OP_STATE_NOT_SUPPORTED       (0x0009)
+#define MPI2_IOCSTATUS_INSUFFICIENT_POWER           (0x000A)
 
 /****************************************************************************
 * Config IOCStatus values
@@ -1045,7 +1102,7 @@ typedef union _MPI2_IEEE_SGE_CHAIN_UNION {
 	Mpi2IeeeSgeChainUnion_t,
 	*pMpi2IeeeSgeChainUnion_t;
 
-/*MPI25_IEEE_SGE_CHAIN64 is for MPI v2.5 products only */
+/*MPI25_IEEE_SGE_CHAIN64 is for MPI v2.5 and later */
 typedef struct _MPI25_IEEE_SGE_CHAIN64 {
 	U64 Address;
 	U32 Length;
@@ -1098,6 +1155,11 @@ typedef union _MPI25_SGE_IO_UNION {
 #define MPI2_IEEE_SGE_FLAGS_SIMPLE_ELEMENT      (0x00)
 #define MPI2_IEEE_SGE_FLAGS_CHAIN_ELEMENT       (0x80)
 
+/*Next Segment Format */
+
+#define MPI26_IEEE_SGE_FLAGS_NSF_MASK           (0x1C)
+#define MPI26_IEEE_SGE_FLAGS_NSF_MPI_IEEE       (0x00)
+
 /*Data Location Address Space */
 
 #define MPI2_IEEE_SGE_FLAGS_ADDR_MASK           (0x03)
@@ -1108,6 +1170,7 @@ typedef union _MPI25_SGE_IO_UNION {
 #define MPI2_IEEE_SGE_FLAGS_SYSTEMPLBPCI_ADDR   (0x03)
 #define MPI2_IEEE_SGE_FLAGS_SYSTEMPLBCPI_ADDR \
 	 (MPI2_IEEE_SGE_FLAGS_SYSTEMPLBPCI_ADDR)
+#define MPI26_IEEE_SGE_FLAGS_IOCCTL_ADDR        (0x02)
 
 /****************************************************************************
 * IEEE SGE operation Macros
@@ -1166,6 +1229,7 @@ typedef union _MPI2_SGE_IO_UNION {
 #define MPI2_SGLFLAGS_SYSTEM_ADDRESS_SPACE          (0x00)
 #define MPI2_SGLFLAGS_IOCDDR_ADDRESS_SPACE          (0x04)
 #define MPI2_SGLFLAGS_IOCPLB_ADDRESS_SPACE          (0x08)
+#define MPI26_SGLFLAGS_IOCPLB_ADDRESS_SPACE         (0x08)
 #define MPI2_SGLFLAGS_IOCPLBNTA_ADDRESS_SPACE       (0x0C)
 /*values for SGL Type subfield */
 #define MPI2_SGLFLAGS_SGL_TYPE_MASK                 (0x03)
diff --git a/drivers/scsi/mpt3sas/mpi/mpi2_cnfg.h b/drivers/scsi/mpt3sas/mpi/mpi2_cnfg.h
index 581fdb375db5..9cf09bf7c4a8 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2_cnfg.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2_cnfg.h
@@ -1,12 +1,12 @@
 /*
- * Copyright (c) 2000-2014 LSI Corporation.
+ * Copyright 2000-2015 Avago Technologies.  All rights reserved.
  *
  *
  *          Name:  mpi2_cnfg.h
  *         Title:  MPI Configuration messages and pages
  * Creation Date:  November 10, 2006
  *
- *   mpi2_cnfg.h Version:  02.00.29
+ *   mpi2_cnfg.h Version:  02.00.33
  *
  * NOTE: Names (typedefs, defines, etc.) beginning with an MPI25 or Mpi25
  *       prefix are for use only on MPI v2.5 products, and must not be used
@@ -178,7 +178,14 @@
  * 01-08-14  02.00.28  Added more defines for the BiosOptions field of
  *		       MPI2_CONFIG_PAGE_BIOS_1.
  * 06-13-14  02.00.29  Added SSUTimeout field to MPI2_CONFIG_PAGE_BIOS_1, and
- *		       more defines for the BiosOptions field..
+ *                     more defines for the BiosOptions field.
+ * 11-18-14  02.00.30  Updated copyright information.
+ *                     Added MPI2_BIOSPAGE1_OPTIONS_ADVANCED_CONFIG.
+ *                     Added AdapterOrderAux fields to BIOS Page 3.
+ * 03-16-15  02.00.31  Updated for MPI v2.6.
+ *                     Added new SAS Phy Event codes
+ * 05-25-15  02.00.33  Added more defines for the BiosOptions field of
+ *                     MPI2_CONFIG_PAGE_BIOS_1.
  * --------------------------------------------------------------------------
  */
 
@@ -355,7 +362,6 @@ typedef union _MPI2_CONFIG_EXT_PAGE_HEADER_UNION {
 #define MPI2_ETHERNET_PGAD_IF_NUMBER_MASK           (0x000000FF)
 
 
-
 /****************************************************************************
 *  Configuration messages
 ****************************************************************************/
@@ -457,8 +463,17 @@ typedef struct _MPI2_CONFIG_REPLY {
 #define MPI25_MFGPAGE_DEVID_SAS3108_5               (0x0094)
 #define MPI25_MFGPAGE_DEVID_SAS3108_6               (0x0095)
 
-
-
+/* MPI v2.6 SAS Products */
+#define MPI26_MFGPAGE_DEVID_SAS3216                 (0x00C9)
+#define MPI26_MFGPAGE_DEVID_SAS3224                 (0x00C4)
+#define MPI26_MFGPAGE_DEVID_SAS3316_1               (0x00C5)
+#define MPI26_MFGPAGE_DEVID_SAS3316_2               (0x00C6)
+#define MPI26_MFGPAGE_DEVID_SAS3316_3               (0x00C7)
+#define MPI26_MFGPAGE_DEVID_SAS3316_4               (0x00C8)
+#define MPI26_MFGPAGE_DEVID_SAS3324_1               (0x00C0)
+#define MPI26_MFGPAGE_DEVID_SAS3324_2               (0x00C1)
+#define MPI26_MFGPAGE_DEVID_SAS3324_3               (0x00C2)
+#define MPI26_MFGPAGE_DEVID_SAS3324_4               (0x00C3)
 
 /*Manufacturing Page 0 */
 
@@ -941,8 +956,8 @@ typedef struct _MPI2_CONFIG_PAGE_IO_UNIT_7 {
 	U8
 		BoardTemperatureUnits;                  /*0x16 */
 	U8                      Reserved3;              /*0x17 */
-	U32			Reserved4;		/* 0x18 */
-	U32			Reserved5;		/* 0x1C */
+	U32			BoardPowerRequirement;	/*0x18 */
+	U32			PCISlotPowerAllocation;	/*0x1C */
 	U32			Reserved6;		/* 0x20 */
 	U32			Reserved7;		/* 0x24 */
 } MPI2_CONFIG_PAGE_IO_UNIT_7,
@@ -1151,6 +1166,62 @@ typedef struct _MPI2_CONFIG_PAGE_IO_UNIT_10 {
 #define MPI2_IOUNITPAGE10_PAGEVERSION                   (0x01)
 
 
+/* IO Unit Page 11 (for MPI v2.6 and later) */
+
+typedef struct _MPI26_IOUNIT11_SPINUP_GROUP {
+	U8          MaxTargetSpinup;            /* 0x00 */
+	U8          SpinupDelay;                /* 0x01 */
+	U8          SpinupFlags;                /* 0x02 */
+	U8          Reserved1;                  /* 0x03 */
+} MPI26_IOUNIT11_SPINUP_GROUP,
+	*PTR_MPI26_IOUNIT11_SPINUP_GROUP,
+	Mpi26IOUnit11SpinupGroup_t,
+	*pMpi26IOUnit11SpinupGroup_t;
+
+/* defines for IO Unit Page 11 SpinupFlags */
+#define MPI26_IOUNITPAGE11_SPINUP_DISABLE_FLAG          (0x01)
+
+
+/*
+ * Host code (drivers, BIOS, utilities, etc.) should leave this define set to
+ * four and check the value returned for NumPhys at runtime.
+ */
+#ifndef MPI26_IOUNITPAGE11_PHY_MAX
+#define MPI26_IOUNITPAGE11_PHY_MAX        (4)
+#endif
+
+typedef struct _MPI26_CONFIG_PAGE_IO_UNIT_11 {
+	MPI2_CONFIG_PAGE_HEADER       Header;			       /*0x00 */
+	U32                           Reserved1;                      /*0x04 */
+	MPI26_IOUNIT11_SPINUP_GROUP   SpinupGroupParameters[4];       /*0x08 */
+	U32                           Reserved2;                      /*0x18 */
+	U32                           Reserved3;                      /*0x1C */
+	U32                           Reserved4;                      /*0x20 */
+	U8                            BootDeviceWaitTime;             /*0x24 */
+	U8                            Reserved5;                      /*0x25 */
+	U16                           Reserved6;                      /*0x26 */
+	U8                            NumPhys;                        /*0x28 */
+	U8                            PEInitialSpinupDelay;           /*0x29 */
+	U8                            PEReplyDelay;                   /*0x2A */
+	U8                            Flags;                          /*0x2B */
+	U8			      PHY[MPI26_IOUNITPAGE11_PHY_MAX];/*0x2C */
+} MPI26_CONFIG_PAGE_IO_UNIT_11,
+	*PTR_MPI26_CONFIG_PAGE_IO_UNIT_11,
+	Mpi26IOUnitPage11_t,
+	*pMpi26IOUnitPage11_t;
+
+#define MPI26_IOUNITPAGE11_PAGEVERSION                  (0x00)
+
+/* defines for Flags field */
+#define MPI26_IOUNITPAGE11_FLAGS_AUTO_PORTENABLE        (0x01)
+
+/* defines for PHY field */
+#define MPI26_IOUNITPAGE11_PHY_SPINUP_GROUP_MASK        (0x03)
+
+
+
+
+
 
 /****************************************************************************
 *  IOC Config Pages
@@ -1343,6 +1414,10 @@ typedef struct _MPI2_CONFIG_PAGE_BIOS_1 {
 #define MPI2_BIOSPAGE1_PAGEVERSION                      (0x07)
 
 /*values for BIOS Page 1 BiosOptions field */
+#define MPI2_BIOSPAGE1_OPTIONS_BOOT_LIST_ADD_ALT_BOOT_DEVICE    (0x00008000)
+#define MPI2_BIOSPAGE1_OPTIONS_ADVANCED_CONFIG                  (0x00004000)
+
+#define MPI2_BIOSPAGE1_OPTIONS_PNS_MASK                         (0x00003800)
 #define MPI2_BIOSPAGE1_OPTIONS_PNS_MASK                         (0x00003800)
 #define MPI2_BIOSPAGE1_OPTIONS_PNS_PBDHL                        (0x00000000)
 #define MPI2_BIOSPAGE1_OPTIONS_PNS_ENCSLOSURE                   (0x00000800)
@@ -1492,6 +1567,8 @@ typedef struct _MPI2_CONFIG_PAGE_BIOS_2 {
 
 /*BIOS Page 3 */
 
+#define MPI2_BIOSPAGE3_NUM_ADAPTER      (4)
+
 typedef struct _MPI2_ADAPTER_INFO {
 	U8      PciBusNumber;                        /*0x00 */
 	U8      PciDeviceAndFunctionNumber;          /*0x01 */
@@ -1502,17 +1579,26 @@ typedef struct _MPI2_ADAPTER_INFO {
 #define MPI2_ADAPTER_INFO_FLAGS_EMBEDDED                (0x0001)
 #define MPI2_ADAPTER_INFO_FLAGS_INIT_STATUS             (0x0002)
 
+typedef struct _MPI2_ADAPTER_ORDER_AUX {
+	U64     WWID;					/* 0x00 */
+	U32     Reserved1;				/* 0x08 */
+	U32     Reserved2;				/* 0x0C */
+} MPI2_ADAPTER_ORDER_AUX, *PTR_MPI2_ADAPTER_ORDER_AUX,
+	Mpi2AdapterOrderAux_t, *pMpi2AdapterOrderAux_t;
+
+
 typedef struct _MPI2_CONFIG_PAGE_BIOS_3 {
 	MPI2_CONFIG_PAGE_HEADER Header;              /*0x00 */
 	U32                     GlobalFlags;         /*0x04 */
 	U32                     BiosVersion;         /*0x08 */
-	MPI2_ADAPTER_INFO       AdapterOrder[4];     /*0x0C */
+	MPI2_ADAPTER_INFO       AdapterOrder[MPI2_BIOSPAGE3_NUM_ADAPTER];
 	U32                     Reserved1;           /*0x1C */
+	MPI2_ADAPTER_ORDER_AUX  AdapterOrderAux[MPI2_BIOSPAGE3_NUM_ADAPTER];
 } MPI2_CONFIG_PAGE_BIOS_3,
 	*PTR_MPI2_CONFIG_PAGE_BIOS_3,
 	Mpi2BiosPage3_t, *pMpi2BiosPage3_t;
 
-#define MPI2_BIOSPAGE3_PAGEVERSION                      (0x00)
+#define MPI2_BIOSPAGE3_PAGEVERSION                      (0x01)
 
 /*values for BIOS Page 3 GlobalFlags */
 #define MPI2_BIOSPAGE3_FLAGS_PAUSE_ON_ERROR             (0x00000002)
@@ -2006,6 +2092,8 @@ typedef struct _MPI2_CONFIG_PAGE_SASIOUNIT_0 {
 #define MPI2_SASIOUNIT0_PORTFLAGS_AUTO_PORT_CONFIG          (0x01)
 
 /*values for SAS IO Unit Page 0 PhyFlags */
+#define MPI2_SASIOUNIT0_PHYFLAGS_INIT_PERSIST_CONNECT       (0x40)
+#define MPI2_SASIOUNIT0_PHYFLAGS_TARG_PERSIST_CONNECT       (0x20)
 #define MPI2_SASIOUNIT0_PHYFLAGS_ZONING_ENABLED             (0x10)
 #define MPI2_SASIOUNIT0_PHYFLAGS_PHY_DISABLED               (0x08)
 
@@ -2108,6 +2196,7 @@ typedef struct _MPI2_CONFIG_PAGE_SASIOUNIT_1 {
 #define MPI2_SASIOUNIT1_CONTROL_CLEAR_AFFILIATION                   (0x0001)
 
 /*values for SAS IO Unit Page 1 AdditionalControlFlags */
+#define MPI2_SASIOUNIT1_ACONTROL_DA_PERSIST_CONNECT                 (0x0100)
 #define MPI2_SASIOUNIT1_ACONTROL_MULTI_PORT_DOMAIN_ILLEGAL          (0x0080)
 #define MPI2_SASIOUNIT1_ACONTROL_SATA_ASYNCHROUNOUS_NOTIFICATION    (0x0040)
 #define MPI2_SASIOUNIT1_ACONTROL_INVALID_TOPOLOGY_CORRECTION        (0x0020)
@@ -2125,6 +2214,8 @@ typedef struct _MPI2_CONFIG_PAGE_SASIOUNIT_1 {
 #define MPI2_SASIOUNIT1_PORT_FLAGS_AUTO_PORT_CONFIG                 (0x01)
 
 /*values for SAS IO Unit Page 1 PhyFlags */
+#define MPI2_SASIOUNIT1_PHYFLAGS_INIT_PERSIST_CONNECT               (0x40)
+#define MPI2_SASIOUNIT1_PHYFLAGS_TARG_PERSIST_CONNECT               (0x20)
 #define MPI2_SASIOUNIT1_PHYFLAGS_ZONING_ENABLE                      (0x10)
 #define MPI2_SASIOUNIT1_PHYFLAGS_PHY_DISABLE                        (0x08)
 
@@ -2144,7 +2235,7 @@ typedef struct _MPI2_CONFIG_PAGE_SASIOUNIT_1 {
  *SAS IO Unit Page 1 ControllerPhyDeviceInfo values */
 
 
-/*SAS IO Unit Page 4 */
+/*SAS IO Unit Page 4 (for MPI v2.5 and earlier) */
 
 typedef struct _MPI2_SAS_IOUNIT4_SPINUP_GROUP {
 	U8          MaxTargetSpinup;            /*0x00 */
@@ -2715,6 +2806,7 @@ typedef struct _MPI2_CONFIG_PAGE_SAS_DEV_0 {
 #define MPI2_SAS_DEVICE0_FLAGS_SATA_NCQ_SUPPORTED           (0x0020)
 #define MPI2_SAS_DEVICE0_FLAGS_SATA_FUA_SUPPORTED           (0x0010)
 #define MPI2_SAS_DEVICE0_FLAGS_PORT_SELECTOR_ATTACH         (0x0008)
+#define MPI2_SAS_DEVICE0_FLAGS_PERSIST_CAPABLE              (0x0004)
 #define MPI2_SAS_DEVICE0_FLAGS_ENCL_LEVEL_VALID             (0x0002)
 #define MPI2_SAS_DEVICE0_FLAGS_DEVICE_PRESENT               (0x0001)
 
@@ -2922,6 +3014,19 @@ typedef struct _MPI2_SASPHY3_PHY_EVENT_CONFIG {
 #define MPI2_SASPHY3_EVENT_CODE_MISALIGNED_MUX_PRIMITIVE    (0xD1)
 #define MPI2_SASPHY3_EVENT_CODE_RX_AIP                      (0xD2)
 
+/*Following codes are product specific and in MPI v2.6 and later */
+#define MPI2_SASPHY3_EVENT_CODE_LCARB_WAIT_TIME		    (0xD3)
+#define MPI2_SASPHY3_EVENT_CODE_RCVD_CONN_RESP_WAIT_TIME    (0xD4)
+#define MPI2_SASPHY3_EVENT_CODE_LCCONN_TIME	            (0xD5)
+#define MPI2_SASPHY3_EVENT_CODE_SSP_TX_START_TRANSMIT	    (0xD6)
+#define MPI2_SASPHY3_EVENT_CODE_SATA_TX_START	            (0xD7)
+#define MPI2_SASPHY3_EVENT_CODE_SMP_TX_START_TRANSMT	    (0xD8)
+#define MPI2_SASPHY3_EVENT_CODE_TX_SMP_BREAK_CONN	    (0xD9)
+#define MPI2_SASPHY3_EVENT_CODE_SSP_RX_START_RECEIVE	    (0xDA)
+#define MPI2_SASPHY3_EVENT_CODE_SATA_RX_START_RECEIVE	    (0xDB)
+#define MPI2_SASPHY3_EVENT_CODE_SMP_RX_START_RECEIVE	    (0xDC)
+
+
 /*values for the CounterType field */
 #define MPI2_SASPHY3_COUNTER_TYPE_WRAPPING                  (0x00)
 #define MPI2_SASPHY3_COUNTER_TYPE_SATURATING                (0x01)
diff --git a/drivers/scsi/mpt3sas/mpi/mpi2_init.h b/drivers/scsi/mpt3sas/mpi/mpi2_init.h
index 068c98efd742..c38f624b859d 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2_init.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2_init.h
@@ -1,12 +1,12 @@
 /*
- * Copyright (c) 2000-2014 LSI Corporation.
+ * Copyright 2000-2015 Avago Technologies.  All rights reserved.
  *
  *
  *          Name:  mpi2_init.h
  *         Title:  MPI SCSI initiator mode messages and structures
  * Creation Date:  June 23, 2006
  *
- * mpi2_init.h Version:  02.00.15
+ * mpi2_init.h Version:  02.00.17
  *
  * NOTE: Names (typedefs, defines, etc.) beginning with an MPI25 or Mpi25
  *       prefix are for use only on MPI v2.5 products, and must not be used
@@ -46,6 +46,11 @@
  * 07-10-12  02.00.14  Added MPI2_SCSIIO_CONTROL_SHIFT_DATADIRECTION.
  * 04-09-13  02.00.15  Added SCSIStatusQualifier field to MPI2_SCSI_IO_REPLY,
  *                     replacing the Reserved4 field.
+ * 11-18-14  02.00.16  Updated copyright information.
+ * 03-16-15  02.00.17  Updated for MPI v2.6.
+ *                     Added MPI26_SCSIIO_IOFLAGS_ESCAPE_PASSTHROUGH.
+ *                     Added MPI2_SEP_REQ_SLOTSTATUS_DEV_OFF and
+ *                     MPI2_SEP_REPLY_SLOTSTATUS_DEV_OFF.
  * --------------------------------------------------------------------------
  */
 
@@ -128,6 +133,7 @@ typedef struct _MPI2_SCSI_IO_REQUEST {
 #define MPI2_SCSIIO_MSGFLAGS_IOCDDR_SENSE_ADDR      (0x04)
 #define MPI2_SCSIIO_MSGFLAGS_IOCPLB_SENSE_ADDR      (0x08)
 #define MPI2_SCSIIO_MSGFLAGS_IOCPLBNTA_SENSE_ADDR   (0x0C)
+#define MPI26_SCSIIO_MSGFLAGS_IOCCTL_SENSE_ADDR     (0x08)
 
 /*SCSI IO SGLFlags bits */
 
@@ -228,7 +234,7 @@ typedef union _MPI25_SCSI_IO_CDB_UNION {
 } MPI25_SCSI_IO_CDB_UNION, *PTR_MPI25_SCSI_IO_CDB_UNION,
 	Mpi25ScsiIoCdb_t, *pMpi25ScsiIoCdb_t;
 
-/*MPI v2.5 SCSI IO Request Message */
+/*MPI v2.5/2.6 SCSI IO Request Message */
 typedef struct _MPI25_SCSI_IO_REQUEST {
 	U16 DevHandle;		/*0x00 */
 	U8 ChainOffset;		/*0x02 */
@@ -302,12 +308,14 @@ typedef struct _MPI25_SCSI_IO_REQUEST {
 #define MPI25_SCSIIO_NUM_SGLOFFSETS                 (4)
 
 /*defines for the IoFlags field */
-#define MPI25_SCSIIO_IOFLAGS_IO_PATH_MASK           (0xC000)
-#define MPI25_SCSIIO_IOFLAGS_NORMAL_PATH            (0x0000)
-#define MPI25_SCSIIO_IOFLAGS_FAST_PATH              (0x4000)
+#define MPI25_SCSIIO_IOFLAGS_IO_PATH_MASK               (0xC000)
+#define MPI25_SCSIIO_IOFLAGS_NORMAL_PATH                (0x0000)
+#define MPI25_SCSIIO_IOFLAGS_FAST_PATH                  (0x4000)
 
+#define MPI26_SCSIIO_IOFLAGS_ESCAPE_PASSTHROUGH         (0x2000)
 #define MPI25_SCSIIO_IOFLAGS_LARGE_CDB                  (0x1000)
 #define MPI25_SCSIIO_IOFLAGS_BIDIRECTIONAL              (0x0800)
+#define MPI26_SCSIIO_IOFLAGS_PORT_REQUEST               (0x0400)
 #define MPI25_SCSIIO_IOFLAGS_CDBLENGTH_MASK             (0x01FF)
 
 /*MPI v2.5 defines for the EEDPFlags bits */
@@ -512,6 +520,7 @@ typedef struct _MPI2_SEP_REQUEST {
 #define MPI2_SEP_REQ_FLAGS_ENCLOSURE_SLOT_ADDRESS       (0x01)
 
 /*SlotStatus defines */
+#define MPI2_SEP_REQ_SLOTSTATUS_DEV_OFF                 (0x00080000)
 #define MPI2_SEP_REQ_SLOTSTATUS_REQUEST_REMOVE          (0x00040000)
 #define MPI2_SEP_REQ_SLOTSTATUS_IDENTIFY_REQUEST        (0x00020000)
 #define MPI2_SEP_REQ_SLOTSTATUS_REBUILD_STOPPED         (0x00000200)
@@ -547,6 +556,7 @@ typedef struct _MPI2_SEP_REPLY {
 	Mpi2SepReply_t, *pMpi2SepReply_t;
 
 /*SlotStatus defines */
+#define MPI2_SEP_REPLY_SLOTSTATUS_DEV_OFF               (0x00080000)
 #define MPI2_SEP_REPLY_SLOTSTATUS_REMOVE_READY          (0x00040000)
 #define MPI2_SEP_REPLY_SLOTSTATUS_IDENTIFY_REQUEST      (0x00020000)
 #define MPI2_SEP_REPLY_SLOTSTATUS_REBUILD_STOPPED       (0x00000200)
diff --git a/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h b/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h
index d7598cc4bb8e..cf510ed91924 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h
@@ -1,12 +1,12 @@
 /*
- * Copyright (c) 2000-2014 LSI Corporation.
+ * Copyright 2000-2015 Avago Technologies.  All rights reserved.
  *
  *
  *          Name:  mpi2_ioc.h
  *         Title:  MPI IOC, Port, Event, FW Download, and FW Upload messages
  * Creation Date:  October 11, 2006
  *
- * mpi2_ioc.h Version:  02.00.24
+ * mpi2_ioc.h Version:  02.00.26
  *
  * NOTE: Names (typedefs, defines, etc.) beginning with an MPI25 or Mpi25
  *       prefix are for use only on MPI v2.5 products, and must not be used
@@ -133,6 +133,10 @@
  *			Added MPI2_FW_DOWNLOAD_ITYPE_PUBLIC_KEY.
  *			Added Encrypted Hash Extended Image.
  * 12-05-13  02.00.24  Added MPI25_HASH_IMAGE_TYPE_BIOS.
+ * 11-18-14  02.00.25  Updated copyright information.
+ * 03-16-15  02.00.26  Added MPI26_FW_HEADER_PID_FAMILY_3324_SAS and
+ *                     MPI26_FW_HEADER_PID_FAMILY_3516_SAS.
+ *                     Added MPI26_CTRL_OP_SHUTDOWN.
  * --------------------------------------------------------------------------
  */
 
@@ -165,7 +169,7 @@ typedef struct _MPI2_IOC_INIT_REQUEST {
 	U16 HeaderVersion;	/*0x0E */
 	U32 Reserved5;		/*0x10 */
 	U16 Reserved6;		/*0x14 */
-	U8 Reserved7;		/*0x16 */
+	U8 HostPageSize;	/*0x16 */
 	U8 HostMSIxVectors;	/*0x17 */
 	U16 Reserved8;		/*0x18 */
 	U16 SystemRequestFrameSize;	/*0x1A */
@@ -289,7 +293,8 @@ typedef struct _MPI2_IOC_FACTS_REPLY {
 	U16 MaxDevHandle;	/*0x38 */
 	U16 MaxPersistentEntries;	/*0x3A */
 	U16 MinDevHandle;	/*0x3C */
-	U16 Reserved4;		/*0x3E */
+	U8 CurrentHostPageSize;	/* 0x3E */
+	U8 Reserved4;		/* 0x3F */
 } MPI2_IOC_FACTS_REPLY, *PTR_MPI2_IOC_FACTS_REPLY,
 	Mpi2IOCFactsReply_t, *pMpi2IOCFactsReply_t;
 
@@ -326,6 +331,7 @@ typedef struct _MPI2_IOC_FACTS_REPLY {
 /*ProductID field uses MPI2_FW_HEADER_PID_ */
 
 /*IOCCapabilities */
+#define MPI26_IOCFACTS_CAPABILITY_ATOMIC_REQ            (0x00080000)
 #define MPI2_IOCFACTS_CAPABILITY_RDPQ_ARRAY_CAPABLE     (0x00040000)
 #define MPI25_IOCFACTS_CAPABILITY_FAST_PATH_CAPABLE     (0x00020000)
 #define MPI2_IOCFACTS_CAPABILITY_HOST_BASED_DISCOVERY   (0x00010000)
@@ -343,8 +349,8 @@ typedef struct _MPI2_IOC_FACTS_REPLY {
 #define MPI2_IOCFACTS_CAPABILITY_TASK_SET_FULL_HANDLING (0x00000004)
 
 /*ProtocolFlags */
-#define MPI2_IOCFACTS_PROTOCOL_SCSI_TARGET              (0x0001)
 #define MPI2_IOCFACTS_PROTOCOL_SCSI_INITIATOR           (0x0002)
+#define MPI2_IOCFACTS_PROTOCOL_SCSI_TARGET              (0x0001)
 
 /****************************************************************************
 * PortFacts message
@@ -1247,6 +1253,7 @@ typedef struct _MPI2_FW_UPLOAD_REQUEST {
 #define MPI2_FW_UPLOAD_ITYPE_MEGARAID           (0x09)
 #define MPI2_FW_UPLOAD_ITYPE_COMPLETE           (0x0A)
 #define MPI2_FW_UPLOAD_ITYPE_COMMON_BOOT_BLOCK  (0x0B)
+#define MPI2_FW_UPLOAD_ITYPE_CBB_BACKUP         (0x0D)
 
 /*MPI v2.0 FWUpload TransactionContext Element */
 typedef struct _MPI2_FW_UPLOAD_TCSGE {
@@ -1328,7 +1335,7 @@ typedef struct _MPI2_FW_IMAGE_HEADER {
 	U32 Reserved54;		/*0x54 */
 	U32 Reserved58;		/*0x58 */
 	U32 Reserved5C;		/*0x5C */
-	U32 Reserved60;		/*0x60 */
+	U32 BootFlags;		/*0x60 */
 	U32 FirmwareVersionNameWhat;	/*0x64 */
 	U8 FirmwareVersionName[32];	/*0x68 */
 	U32 VendorNameWhat;	/*0x88 */
@@ -1354,18 +1361,22 @@ typedef struct _MPI2_FW_IMAGE_HEADER {
 #define MPI2_FW_HEADER_SIGNATURE_OFFSET         (0x00)
 #define MPI2_FW_HEADER_SIGNATURE_MASK           (0xFF000000)
 #define MPI2_FW_HEADER_SIGNATURE                (0xEA000000)
+#define MPI26_FW_HEADER_SIGNATURE               (0xEB000000)
 
 /*Signature0 field */
 #define MPI2_FW_HEADER_SIGNATURE0_OFFSET        (0x04)
 #define MPI2_FW_HEADER_SIGNATURE0               (0x5AFAA55A)
+#define MPI26_FW_HEADER_SIGNATURE0              (0x5AEAA55A)
 
 /*Signature1 field */
 #define MPI2_FW_HEADER_SIGNATURE1_OFFSET        (0x08)
 #define MPI2_FW_HEADER_SIGNATURE1               (0xA55AFAA5)
+#define MPI26_FW_HEADER_SIGNATURE1              (0xA55AEAA5)
 
 /*Signature2 field */
 #define MPI2_FW_HEADER_SIGNATURE2_OFFSET        (0x0C)
 #define MPI2_FW_HEADER_SIGNATURE2               (0x5AA55AFA)
+#define MPI26_FW_HEADER_SIGNATURE2              (0x5AA55AEA)
 
 /*defines for using the ProductID field */
 #define MPI2_FW_HEADER_PID_TYPE_MASK            (0xF000)
@@ -1381,6 +1392,8 @@ typedef struct _MPI2_FW_IMAGE_HEADER {
 #define MPI2_FW_HEADER_PID_FAMILY_2108_SAS      (0x0013)
 #define MPI2_FW_HEADER_PID_FAMILY_2208_SAS      (0x0014)
 #define MPI25_FW_HEADER_PID_FAMILY_3108_SAS     (0x0021)
+#define MPI26_FW_HEADER_PID_FAMILY_3324_SAS     (0x0028)
+#define MPI26_FW_HEADER_PID_FAMILY_3516_SAS     (0x0031)
 
 /*use MPI2_IOCFACTS_PROTOCOL_ defines for ProtocolFlags field */
 
@@ -1388,6 +1401,7 @@ typedef struct _MPI2_FW_IMAGE_HEADER {
 
 #define MPI2_FW_HEADER_IMAGESIZE_OFFSET         (0x2C)
 #define MPI2_FW_HEADER_NEXTIMAGE_OFFSET         (0x30)
+#define MPI26_FW_HEADER_BOOTFLAGS_OFFSET        (0x60)
 #define MPI2_FW_HEADER_VERNMHWAT_OFFSET         (0x64)
 
 #define MPI2_FW_HEADER_WHAT_SIGNATURE           (0x29232840)
@@ -1493,7 +1507,9 @@ typedef struct _MPI2_FLASH_LAYOUT_DATA {
 #define MPI2_FLASH_REGION_CONFIG_1              (0x07)
 #define MPI2_FLASH_REGION_CONFIG_2              (0x08)
 #define MPI2_FLASH_REGION_MEGARAID              (0x09)
-#define MPI2_FLASH_REGION_INIT                  (0x0A)
+#define MPI2_FLASH_REGION_COMMON_BOOT_BLOCK     (0x0A)
+#define MPI2_FLASH_REGION_INIT (MPI2_FLASH_REGION_COMMON_BOOT_BLOCK)
+#define MPI2_FLASH_REGION_CBB_BACKUP            (0x0D)
 
 /*ImageRevision */
 #define MPI2_FLASH_LAYOUT_IMAGE_REVISION        (0x00)
@@ -1619,7 +1635,6 @@ typedef struct _MPI25_ENCRYPTED_HASH_DATA {
 Mpi25EncryptedHashData_t, *pMpi25EncryptedHashData_t;
 
 
-
 /****************************************************************************
 * PowerManagementControl message
 ****************************************************************************/
@@ -1726,4 +1741,90 @@ typedef struct _MPI2_PWR_MGMT_CONTROL_REPLY {
 } MPI2_PWR_MGMT_CONTROL_REPLY, *PTR_MPI2_PWR_MGMT_CONTROL_REPLY,
 	Mpi2PwrMgmtControlReply_t, *pMpi2PwrMgmtControlReply_t;
 
+/****************************************************************************
+*  IO Unit Control messages (MPI v2.6 and later only.)
+****************************************************************************/
+
+/* IO Unit Control Request Message */
+typedef struct _MPI26_IOUNIT_CONTROL_REQUEST {
+	U8                      Operation;          /* 0x00 */
+	U8                      Reserved1;          /* 0x01 */
+	U8                      ChainOffset;        /* 0x02 */
+	U8                      Function;           /* 0x03 */
+	U16                     DevHandle;          /* 0x04 */
+	U8                      IOCParameter;       /* 0x06 */
+	U8                      MsgFlags;           /* 0x07 */
+	U8                      VP_ID;              /* 0x08 */
+	U8                      VF_ID;              /* 0x09 */
+	U16                     Reserved3;          /* 0x0A */
+	U16                     Reserved4;          /* 0x0C */
+	U8                      PhyNum;             /* 0x0E */
+	U8                      PrimFlags;          /* 0x0F */
+	U32                     Primitive;          /* 0x10 */
+	U8                      LookupMethod;       /* 0x14 */
+	U8                      Reserved5;          /* 0x15 */
+	U16                     SlotNumber;         /* 0x16 */
+	U64                     LookupAddress;      /* 0x18 */
+	U32                     IOCParameterValue;  /* 0x20 */
+	U32                     Reserved7;          /* 0x24 */
+	U32                     Reserved8;          /* 0x28 */
+} MPI26_IOUNIT_CONTROL_REQUEST,
+	*PTR_MPI26_IOUNIT_CONTROL_REQUEST,
+	Mpi26IoUnitControlRequest_t,
+	*pMpi26IoUnitControlRequest_t;
+
+/* values for the Operation field */
+#define MPI26_CTRL_OP_CLEAR_ALL_PERSISTENT              (0x02)
+#define MPI26_CTRL_OP_SAS_PHY_LINK_RESET                (0x06)
+#define MPI26_CTRL_OP_SAS_PHY_HARD_RESET                (0x07)
+#define MPI26_CTRL_OP_PHY_CLEAR_ERROR_LOG               (0x08)
+#define MPI26_CTRL_OP_SAS_SEND_PRIMITIVE                (0x0A)
+#define MPI26_CTRL_OP_FORCE_FULL_DISCOVERY              (0x0B)
+#define MPI26_CTRL_OP_REMOVE_DEVICE                     (0x0D)
+#define MPI26_CTRL_OP_LOOKUP_MAPPING                    (0x0E)
+#define MPI26_CTRL_OP_SET_IOC_PARAMETER                 (0x0F)
+#define MPI26_CTRL_OP_ENABLE_FP_DEVICE                  (0x10)
+#define MPI26_CTRL_OP_DISABLE_FP_DEVICE                 (0x11)
+#define MPI26_CTRL_OP_ENABLE_FP_ALL                     (0x12)
+#define MPI26_CTRL_OP_DISABLE_FP_ALL                    (0x13)
+#define MPI26_CTRL_OP_DEV_ENABLE_NCQ                    (0x14)
+#define MPI26_CTRL_OP_DEV_DISABLE_NCQ                   (0x15)
+#define MPI26_CTRL_OP_SHUTDOWN                          (0x16)
+#define MPI26_CTRL_OP_DEV_ENABLE_PERSIST_CONNECTION     (0x17)
+#define MPI26_CTRL_OP_DEV_DISABLE_PERSIST_CONNECTION    (0x18)
+#define MPI26_CTRL_OP_DEV_CLOSE_PERSIST_CONNECTION      (0x19)
+#define MPI26_CTRL_OP_PRODUCT_SPECIFIC_MIN              (0x80)
+
+/* values for the PrimFlags field */
+#define MPI26_CTRL_PRIMFLAGS_SINGLE                     (0x08)
+#define MPI26_CTRL_PRIMFLAGS_TRIPLE                     (0x02)
+#define MPI26_CTRL_PRIMFLAGS_REDUNDANT                  (0x01)
+
+/* values for the LookupMethod field */
+#define MPI26_CTRL_LOOKUP_METHOD_WWID_ADDRESS           (0x01)
+#define MPI26_CTRL_LOOKUP_METHOD_ENCLOSURE_SLOT         (0x02)
+#define MPI26_CTRL_LOOKUP_METHOD_SAS_DEVICE_NAME        (0x03)
+
+
+/* IO Unit Control Reply Message */
+typedef struct _MPI26_IOUNIT_CONTROL_REPLY {
+	U8                      Operation;          /* 0x00 */
+	U8                      Reserved1;          /* 0x01 */
+	U8                      MsgLength;          /* 0x02 */
+	U8                      Function;           /* 0x03 */
+	U16                     DevHandle;          /* 0x04 */
+	U8                      IOCParameter;       /* 0x06 */
+	U8                      MsgFlags;           /* 0x07 */
+	U8                      VP_ID;              /* 0x08 */
+	U8                      VF_ID;              /* 0x09 */
+	U16                     Reserved3;          /* 0x0A */
+	U16                     Reserved4;          /* 0x0C */
+	U16                     IOCStatus;          /* 0x0E */
+	U32                     IOCLogInfo;         /* 0x10 */
+} MPI26_IOUNIT_CONTROL_REPLY,
+	*PTR_MPI26_IOUNIT_CONTROL_REPLY,
+	Mpi26IoUnitControlReply_t,
+	*pMpi26IoUnitControlReply_t;
+
+
 #endif
diff --git a/drivers/scsi/mpt3sas/mpi/mpi2_raid.h b/drivers/scsi/mpt3sas/mpi/mpi2_raid.h
index 13d93ca029d5..1c0eeeeb5eaf 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2_raid.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2_raid.h
@@ -1,12 +1,12 @@
 /*
- * Copyright (c) 2000-2014 LSI Corporation.
+ * Copyright 2000-2014 Avago Technologies.  All rights reserved.
  *
  *
  *          Name:  mpi2_raid.h
  *         Title:  MPI Integrated RAID messages and structures
  * Creation Date:  April 26, 2007
  *
- *   mpi2_raid.h Version:  02.00.10
+ *   mpi2_raid.h Version:  02.00.11
  *
  * Version History
  * ---------------
@@ -31,6 +31,7 @@
  * 07-26-12  02.00.09  Added ElapsedSeconds field to MPI2_RAID_VOL_INDICATOR.
  *                     Added MPI2_RAID_VOL_FLAGS_ELAPSED_SECONDS_VALID define.
  * 04-17-13  02.00.10  Added MPI25_RAID_ACTION_ADATA_ALLOW_PI.
+ * 11-18-14  02.00.11  Updated copyright information.
  * --------------------------------------------------------------------------
  */
 
diff --git a/drivers/scsi/mpt3sas/mpi/mpi2_sas.h b/drivers/scsi/mpt3sas/mpi/mpi2_sas.h
index 156e30543a2f..c10c2c02a945 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2_sas.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2_sas.h
@@ -1,12 +1,12 @@
 /*
- * Copyright (c) 2000-2014 LSI Corporation.
+ * Copyright 2000-2015 Avago Technologies.  All rights reserved.
  *
  *
  *          Name:  mpi2_sas.h
  *         Title:  MPI Serial Attached SCSI structures and definitions
  * Creation Date:  February 9, 2007
  *
- * mpi2_sas.h Version:  02.00.08
+ * mpi2_sas.h Version:  02.00.10
  *
  * NOTE: Names (typedefs, defines, etc.) beginning with an MPI25 or Mpi25
  *       prefix are for use only on MPI v2.5 products, and must not be used
@@ -32,6 +32,9 @@
  *                     Passthrough Request message.
  * 08-19-13  02.00.08  Made MPI2_SAS_OP_TRANSMIT_PORT_SELECT_SIGNAL obsolete
  *			for anything newer than MPI v2.0.
+ * 11-18-14  02.00.09  Updated copyright information.
+ * 03-16-15  02.00.10  Updated for MPI v2.6.
+ *                     Added MPI2_SATA_PT_REQ_PT_FLAGS_FPDMA.
  * --------------------------------------------------------------------------
  */
 
@@ -183,6 +186,7 @@ typedef struct _MPI2_SATA_PASSTHROUGH_REQUEST {
 
 /*values for PassthroughFlags field */
 #define MPI2_SATA_PT_REQ_PT_FLAGS_EXECUTE_DIAG      (0x0100)
+#define MPI2_SATA_PT_REQ_PT_FLAGS_FPDMA             (0x0040)
 #define MPI2_SATA_PT_REQ_PT_FLAGS_DMA               (0x0020)
 #define MPI2_SATA_PT_REQ_PT_FLAGS_PIO               (0x0010)
 #define MPI2_SATA_PT_REQ_PT_FLAGS_UNSPECIFIED_VU    (0x0004)
@@ -216,6 +220,8 @@ typedef struct _MPI2_SATA_PASSTHROUGH_REPLY {
 
 /****************************************************************************
 * SAS IO Unit Control messages
+* (MPI v2.5 and earlier only.
+* Replaced by IO Unit Control messages in MPI v2.6 and later.)
 ****************************************************************************/
 
 /*SAS IO Unit Control Request Message */
diff --git a/drivers/scsi/mpt3sas/mpi/mpi2_tool.h b/drivers/scsi/mpt3sas/mpi/mpi2_tool.h
index 1629e5bce7e1..5f9289a1166f 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2_tool.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2_tool.h
@@ -1,12 +1,12 @@
 /*
- * Copyright (c) 2000-2014 LSI Corporation.
+ * Copyright 2000-2014 Avago Technologies.  All rights reserved.
  *
  *
  *          Name:  mpi2_tool.h
  *         Title:  MPI diagnostic tool structures and definitions
  * Creation Date:  March 26, 2007
  *
- *   mpi2_tool.h Version:  02.00.12
+ *   mpi2_tool.h Version:  02.00.13
  *
  * Version History
  * ---------------
@@ -34,6 +34,7 @@
  *                     it uses MPI Chain SGE as well as MPI Simple SGE.
  * 08-19-13  02.00.11  Added MPI2_TOOLBOX_TEXT_DISPLAY_TOOL and related info.
  * 01-08-14  02.00.12  Added MPI2_TOOLBOX_CLEAN_BIT26_PRODUCT_SPECIFIC.
+ * 11-18-14  02.00.13  Updated copyright information.
  * --------------------------------------------------------------------------
  */
 
diff --git a/drivers/scsi/mpt3sas/mpi/mpi2_type.h b/drivers/scsi/mpt3sas/mpi/mpi2_type.h
index 99ab093602e8..92a81abc2c31 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2_type.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2_type.h
@@ -1,12 +1,12 @@
 /*
- *  Copyright (c) 2000-2014 LSI Corporation.
+ *  Copyright 2000-2014 Avago Technologies.  All rights reserved.
  *
  *
  *           Name:  mpi2_type.h
  *          Title:  MPI basic type definitions
  *  Creation Date:  August 16, 2006
  *
- *    mpi2_type.h Version:  02.00.00
+ *    mpi2_type.h Version:  02.00.01
  *
  *  Version History
  *  ---------------
@@ -14,6 +14,7 @@
  *  Date      Version   Description
  *  --------  --------  ------------------------------------------------------
  *  04-30-07  02.00.00  Corresponds to Fusion-MPT MPI Specification Rev A.
+ *  11-18-14  02.00.01  Updated copyright information.
  *  --------------------------------------------------------------------------
  */
 
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 83658acddd58..e4db5fb3239a 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -83,6 +83,10 @@ static int msix_disable = -1;
 module_param(msix_disable, int, 0);
 MODULE_PARM_DESC(msix_disable, " disable msix routed interrupts (default=0)");
 
+static int smp_affinity_enable = 1;
+module_param(smp_affinity_enable, int, S_IRUGO);
+MODULE_PARM_DESC(smp_affinity_enable, "SMP affinity feature enable/disbale Default: enable(1)");
+
 static int max_msix_vectors = -1;
 module_param(max_msix_vectors, int, 0);
 MODULE_PARM_DESC(max_msix_vectors,
@@ -395,6 +399,9 @@ _base_sas_ioc_info(struct MPT3SAS_ADAPTER *ioc, MPI2DefaultReply_t *mpi_reply,
 	case MPI2_IOCSTATUS_INSUFFICIENT_RESOURCES:
 		desc = "insufficient resources";
 		break;
+	case MPI2_IOCSTATUS_INSUFFICIENT_POWER:
+		desc = "insufficient power";
+		break;
 	case MPI2_IOCSTATUS_INVALID_FIELD:
 		desc = "invalid field";
 		break;
@@ -772,7 +779,7 @@ mpt3sas_base_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
 
 	mpi_reply = mpt3sas_base_get_reply_virt_addr(ioc, reply);
 	if (mpi_reply && mpi_reply->Function == MPI2_FUNCTION_EVENT_ACK)
-		return 1;
+		return mpt3sas_check_for_pending_internal_cmds(ioc, smid);
 
 	if (ioc->base_cmds.status == MPT3_CMD_NOT_USED)
 		return 1;
@@ -803,6 +810,7 @@ _base_async_event(struct MPT3SAS_ADAPTER *ioc, u8 msix_index, u32 reply)
 	Mpi2EventNotificationReply_t *mpi_reply;
 	Mpi2EventAckRequest_t *ack_request;
 	u16 smid;
+	struct _event_ack_list *delayed_event_ack;
 
 	mpi_reply = mpt3sas_base_get_reply_virt_addr(ioc, reply);
 	if (!mpi_reply)
@@ -816,8 +824,18 @@ _base_async_event(struct MPT3SAS_ADAPTER *ioc, u8 msix_index, u32 reply)
 		goto out;
 	smid = mpt3sas_base_get_smid(ioc, ioc->base_cb_idx);
 	if (!smid) {
-		pr_err(MPT3SAS_FMT "%s: failed obtaining a smid\n",
-		    ioc->name, __func__);
+		delayed_event_ack = kzalloc(sizeof(*delayed_event_ack),
+					GFP_ATOMIC);
+		if (!delayed_event_ack)
+			goto out;
+		INIT_LIST_HEAD(&delayed_event_ack->list);
+		delayed_event_ack->Event = mpi_reply->Event;
+		delayed_event_ack->EventContext = mpi_reply->EventContext;
+		list_add_tail(&delayed_event_ack->list,
+				&ioc->delayed_event_ack_list);
+		dewtprintk(ioc, pr_info(MPT3SAS_FMT
+				"DELAYED: EVENT ACK: event (0x%04x)\n",
+				ioc->name, le16_to_cpu(mpi_reply->Event)));
 		goto out;
 	}
 
@@ -1348,6 +1366,7 @@ _base_build_zero_len_sge_ieee(struct MPT3SAS_ADAPTER *ioc, void *paddr)
 	u8 sgl_flags = (MPI2_IEEE_SGE_FLAGS_SIMPLE_ELEMENT |
 		MPI2_IEEE_SGE_FLAGS_SYSTEM_ADDR |
 		MPI25_IEEE_SGE_FLAGS_END_OF_LIST);
+
 	_base_add_sg_single_ieee(paddr, sgl_flags, 0, 0, -1);
 }
 
@@ -1797,9 +1816,10 @@ _base_free_irq(struct MPT3SAS_ADAPTER *ioc)
 
 	list_for_each_entry_safe(reply_q, next, &ioc->reply_queue_list, list) {
 		list_del(&reply_q->list);
-		irq_set_affinity_hint(reply_q->vector, NULL);
-		free_cpumask_var(reply_q->affinity_hint);
-		synchronize_irq(reply_q->vector);
+		if (smp_affinity_enable) {
+			irq_set_affinity_hint(reply_q->vector, NULL);
+			free_cpumask_var(reply_q->affinity_hint);
+		}
 		free_irq(reply_q->vector, reply_q);
 		kfree(reply_q);
 	}
@@ -1829,9 +1849,12 @@ _base_request_irq(struct MPT3SAS_ADAPTER *ioc, u8 index, u32 vector)
 	reply_q->msix_index = index;
 	reply_q->vector = vector;
 
-	if (!alloc_cpumask_var(&reply_q->affinity_hint, GFP_KERNEL))
-		return -ENOMEM;
-	cpumask_clear(reply_q->affinity_hint);
+	if (smp_affinity_enable) {
+		if (!zalloc_cpumask_var(&reply_q->affinity_hint, GFP_KERNEL)) {
+			kfree(reply_q);
+			return -ENOMEM;
+		}
+	}
 
 	atomic_set(&reply_q->busy, 0);
 	if (ioc->msix_enable)
@@ -1845,6 +1868,7 @@ _base_request_irq(struct MPT3SAS_ADAPTER *ioc, u8 index, u32 vector)
 	if (r) {
 		pr_err(MPT3SAS_FMT "unable to allocate interrupt %d!\n",
 		    reply_q->name, vector);
+		free_cpumask_var(reply_q->affinity_hint);
 		kfree(reply_q);
 		return -EBUSY;
 	}
@@ -1894,16 +1918,17 @@ _base_assign_reply_queues(struct MPT3SAS_ADAPTER *ioc)
 
 		for (i = 0 ; i < group ; i++) {
 			ioc->cpu_msix_table[cpu] = index;
-			cpumask_or(reply_q->affinity_hint,
+			if (smp_affinity_enable)
+				cpumask_or(reply_q->affinity_hint,
 				   reply_q->affinity_hint, get_cpu_mask(cpu));
 			cpu = cpumask_next(cpu, cpu_online_mask);
 		}
-
-		if (irq_set_affinity_hint(reply_q->vector,
+		if (smp_affinity_enable)
+			if (irq_set_affinity_hint(reply_q->vector,
 					   reply_q->affinity_hint))
-			dinitprintk(ioc, pr_info(MPT3SAS_FMT
-			    "error setting affinity hint for irq vector %d\n",
-			    ioc->name, reply_q->vector));
+				dinitprintk(ioc, pr_info(MPT3SAS_FMT
+				 "Err setting affinity hint to irq vector %d\n",
+				 ioc->name, reply_q->vector));
 		index++;
 	}
 }
@@ -1961,6 +1986,9 @@ _base_enable_msix(struct MPT3SAS_ADAPTER *ioc)
 	} else if (max_msix_vectors == 0)
 		goto try_ioapic;
 
+	if (ioc->msix_vector_count < ioc->cpu_count)
+		smp_affinity_enable = 0;
+
 	entries = kcalloc(ioc->reply_queue_count, sizeof(struct msix_entry),
 	    GFP_KERNEL);
 	if (!entries) {
@@ -2231,6 +2259,12 @@ mpt3sas_base_get_reply_virt_addr(struct MPT3SAS_ADAPTER *ioc, u32 phys_addr)
 	return ioc->reply + (phys_addr - (u32)ioc->reply_dma);
 }
 
+static inline u8
+_base_get_msix_index(struct MPT3SAS_ADAPTER *ioc)
+{
+	return ioc->cpu_msix_table[raw_smp_processor_id()];
+}
+
 /**
  * mpt3sas_base_get_smid - obtain a free smid from internal queue
  * @ioc: per adapter object
@@ -2291,6 +2325,7 @@ mpt3sas_base_get_smid_scsiio(struct MPT3SAS_ADAPTER *ioc, u8 cb_idx,
 	request->scmd = scmd;
 	request->cb_idx = cb_idx;
 	smid = request->smid;
+	request->msix_io = _base_get_msix_index(ioc);
 	list_del(&request->tracker_list);
 	spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags);
 	return smid;
@@ -2413,12 +2448,6 @@ _base_writeq(__u64 b, volatile void __iomem *addr, spinlock_t *writeq_lock)
 }
 #endif
 
-static inline u8
-_base_get_msix_index(struct MPT3SAS_ADAPTER *ioc)
-{
-	return ioc->cpu_msix_table[raw_smp_processor_id()];
-}
-
 /**
  * mpt3sas_base_put_smid_scsi_io - send SCSI_IO request to firmware
  * @ioc: per adapter object
@@ -2472,18 +2501,19 @@ mpt3sas_base_put_smid_fast_path(struct MPT3SAS_ADAPTER *ioc, u16 smid,
  * mpt3sas_base_put_smid_hi_priority - send Task Managment request to firmware
  * @ioc: per adapter object
  * @smid: system request message index
- *
+ * @msix_task: msix_task will be same as msix of IO incase of task abort else 0.
  * Return nothing.
  */
 void
-mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc, u16 smid)
+mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc, u16 smid,
+	u16 msix_task)
 {
 	Mpi2RequestDescriptorUnion_t descriptor;
 	u64 *request = (u64 *)&descriptor;
 
 	descriptor.HighPriority.RequestFlags =
 	    MPI2_REQ_DESCRIPT_FLAGS_HIGH_PRIORITY;
-	descriptor.HighPriority.MSIxIndex =  0;
+	descriptor.HighPriority.MSIxIndex =  msix_task;
 	descriptor.HighPriority.SMID = cpu_to_le16(smid);
 	descriptor.HighPriority.LMID = 0;
 	descriptor.HighPriority.Reserved1 = 0;
@@ -3185,20 +3215,35 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc,  int sleep_flag)
 	}
 	ioc->shost->sg_tablesize = sg_tablesize;
 
-	ioc->hi_priority_depth = facts->HighPriorityCredit;
-	ioc->internal_depth = ioc->hi_priority_depth + (5);
+	ioc->internal_depth = min_t(int, (facts->HighPriorityCredit + (5)),
+		(facts->RequestCredit / 4));
+	if (ioc->internal_depth < INTERNAL_CMDS_COUNT) {
+		if (facts->RequestCredit <= (INTERNAL_CMDS_COUNT +
+				INTERNAL_SCSIIO_CMDS_COUNT)) {
+			pr_err(MPT3SAS_FMT "IOC doesn't have enough Request \
+			    Credits, it has just %d number of credits\n",
+			    ioc->name, facts->RequestCredit);
+			return -ENOMEM;
+		}
+		ioc->internal_depth = 10;
+	}
+
+	ioc->hi_priority_depth = ioc->internal_depth - (5);
 	/* command line tunables  for max controller queue depth */
 	if (max_queue_depth != -1 && max_queue_depth != 0) {
 		max_request_credit = min_t(u16, max_queue_depth +
-		    ioc->hi_priority_depth + ioc->internal_depth,
-		    facts->RequestCredit);
+			ioc->internal_depth, facts->RequestCredit);
 		if (max_request_credit > MAX_HBA_QUEUE_DEPTH)
 			max_request_credit =  MAX_HBA_QUEUE_DEPTH;
 	} else
 		max_request_credit = min_t(u16, facts->RequestCredit,
 		    MAX_HBA_QUEUE_DEPTH);
 
-	ioc->hba_queue_depth = max_request_credit;
+	/* Firmware maintains additional facts->HighPriorityCredit number of
+	 * credits for HiPriprity Request messages, so hba queue depth will be
+	 * sum of max_request_credit and high priority queue depth.
+	 */
+	ioc->hba_queue_depth = max_request_credit + ioc->hi_priority_depth;
 
 	/* request frame size */
 	ioc->request_sz = facts->IOCRequestFrameSize * 4;
@@ -3206,6 +3251,19 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc,  int sleep_flag)
 	/* reply frame size */
 	ioc->reply_sz = facts->ReplyFrameSize * 4;
 
+	/* chain segment size */
+	if (ioc->hba_mpi_version_belonged != MPI2_VERSION) {
+		if (facts->IOCMaxChainSegmentSize)
+			ioc->chain_segment_sz =
+					facts->IOCMaxChainSegmentSize *
+					MAX_CHAIN_ELEMT_SZ;
+		else
+		/* set to 128 bytes size if IOCMaxChainSegmentSize is zero */
+			ioc->chain_segment_sz = DEFAULT_NUM_FWCHAIN_ELEMTS *
+						    MAX_CHAIN_ELEMT_SZ;
+	} else
+		ioc->chain_segment_sz = ioc->request_sz;
+
 	/* calculate the max scatter element size */
 	sge_size = max_t(u16, ioc->sge_size, ioc->sge_size_ieee);
 
@@ -3217,7 +3275,7 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc,  int sleep_flag)
 	ioc->max_sges_in_main_message = max_sge_elements/sge_size;
 
 	/* now do the same for a chain buffer */
-	max_sge_elements = ioc->request_sz - sge_size;
+	max_sge_elements = ioc->chain_segment_sz - sge_size;
 	ioc->max_sges_in_chain_message = max_sge_elements/sge_size;
 
 	/*
@@ -3245,7 +3303,6 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc,  int sleep_flag)
 		ioc->reply_post_queue_depth += 16 -
 		(ioc->reply_post_queue_depth % 16);
 
-
 	if (ioc->reply_post_queue_depth >
 	    facts->MaxReplyDescriptorPostQueueDepth) {
 		ioc->reply_post_queue_depth =
@@ -3327,7 +3384,7 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc,  int sleep_flag)
 	/* set the scsi host can_queue depth
 	 * with some internal commands that could be outstanding
 	 */
-	ioc->shost->can_queue = ioc->scsiio_depth;
+	ioc->shost->can_queue = ioc->scsiio_depth - INTERNAL_SCSIIO_CMDS_COUNT;
 	dinitprintk(ioc, pr_info(MPT3SAS_FMT
 		"scsi host: can_queue depth (%d)\n",
 		ioc->name, ioc->shost->can_queue));
@@ -3354,8 +3411,9 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc,  int sleep_flag)
 		    ioc->chains_needed_per_io, ioc->request_sz, sz/1024);
 		if (ioc->scsiio_depth < MPT3SAS_SAS_QUEUE_DEPTH)
 			goto out;
-		retry_sz += 64;
-		ioc->hba_queue_depth = max_request_credit - retry_sz;
+		retry_sz = 64;
+		ioc->hba_queue_depth -= retry_sz;
+		_base_release_memory_pools(ioc);
 		goto retry_allocation;
 	}
 
@@ -3410,7 +3468,7 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc,  int sleep_flag)
 		goto out;
 	}
 	ioc->chain_dma_pool = pci_pool_create("chain pool", ioc->pdev,
-	    ioc->request_sz, 16, 0);
+	    ioc->chain_segment_sz, 16, 0);
 	if (!ioc->chain_dma_pool) {
 		pr_err(MPT3SAS_FMT "chain_dma_pool: pci_pool_create failed\n",
 			ioc->name);
@@ -3424,13 +3482,13 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc,  int sleep_flag)
 			ioc->chain_depth = i;
 			goto chain_done;
 		}
-		total_sz += ioc->request_sz;
+		total_sz += ioc->chain_segment_sz;
 	}
  chain_done:
 	dinitprintk(ioc, pr_info(MPT3SAS_FMT
 		"chain pool depth(%d), frame_size(%d), pool_size(%d kB)\n",
-		ioc->name, ioc->chain_depth, ioc->request_sz,
-		((ioc->chain_depth *  ioc->request_sz))/1024));
+		ioc->name, ioc->chain_depth, ioc->chain_segment_sz,
+		((ioc->chain_depth *  ioc->chain_segment_sz))/1024));
 
 	/* initialize hi-priority queue smid's */
 	ioc->hpr_lookup = kcalloc(ioc->hi_priority_depth,
@@ -4291,6 +4349,10 @@ _base_get_ioc_facts(struct MPT3SAS_ADAPTER *ioc, int sleep_flag)
 	facts->FWVersion.Word = le32_to_cpu(mpi_reply.FWVersion.Word);
 	facts->IOCRequestFrameSize =
 	    le16_to_cpu(mpi_reply.IOCRequestFrameSize);
+	if (ioc->hba_mpi_version_belonged != MPI2_VERSION) {
+		facts->IOCMaxChainSegmentSize =
+			le16_to_cpu(mpi_reply.IOCMaxChainSegmentSize);
+	}
 	facts->MaxInitiators = le16_to_cpu(mpi_reply.MaxInitiators);
 	facts->MaxTargets = le16_to_cpu(mpi_reply.MaxTargets);
 	ioc->shost->max_id = -1;
@@ -4973,6 +5035,8 @@ _base_make_ioc_operational(struct MPT3SAS_ADAPTER *ioc, int sleep_flag)
 	u32 reply_address;
 	u16 smid;
 	struct _tr_list *delayed_tr, *delayed_tr_next;
+	struct _sc_list *delayed_sc, *delayed_sc_next;
+	struct _event_ack_list *delayed_event_ack, *delayed_event_ack_next;
 	u8 hide_flag;
 	struct adapter_reply_queue *reply_q;
 	long reply_post_free;
@@ -4995,6 +5059,18 @@ _base_make_ioc_operational(struct MPT3SAS_ADAPTER *ioc, int sleep_flag)
 		kfree(delayed_tr);
 	}
 
+	list_for_each_entry_safe(delayed_sc, delayed_sc_next,
+	    &ioc->delayed_sc_list, list) {
+		list_del(&delayed_sc->list);
+		kfree(delayed_sc);
+	}
+
+	list_for_each_entry_safe(delayed_event_ack, delayed_event_ack_next,
+	    &ioc->delayed_event_ack_list, list) {
+		list_del(&delayed_event_ack->list);
+		kfree(delayed_event_ack);
+	}
+
 	/* initialize the scsi lookup free list */
 	spin_lock_irqsave(&ioc->scsi_lookup_lock, flags);
 	INIT_LIST_HEAD(&ioc->free_list);
@@ -5226,6 +5302,7 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
 		ioc->build_zero_len_sge = &_base_build_zero_len_sge;
 		break;
 	case MPI25_VERSION:
+	case MPI26_VERSION:
 		/*
 		 * In SAS3.0,
 		 * SCSI_IO, SMP_PASSTHRU, SATA_PASSTHRU, Target Assist, and
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 5ad271efbd45..32580b514b18 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -73,9 +73,9 @@
 #define MPT3SAS_DRIVER_NAME		"mpt3sas"
 #define MPT3SAS_AUTHOR "Avago Technologies <MPT-FusionLinux.pdl@avagotech.com>"
 #define MPT3SAS_DESCRIPTION	"LSI MPT Fusion SAS 3.0 Device Driver"
-#define MPT3SAS_DRIVER_VERSION		"09.102.00.00"
-#define MPT3SAS_MAJOR_VERSION		9
-#define MPT3SAS_MINOR_VERSION		102
+#define MPT3SAS_DRIVER_VERSION		"12.100.00.00"
+#define MPT3SAS_MAJOR_VERSION		12
+#define MPT3SAS_MINOR_VERSION		100
 #define MPT3SAS_BUILD_VERSION		0
 #define MPT3SAS_RELEASE_VERSION	00
 
@@ -122,11 +122,16 @@
 #define  NO_SLEEP			0
 
 #define INTERNAL_CMDS_COUNT		10	/* reserved cmds */
+/* reserved for issuing internally framed scsi io cmds */
+#define INTERNAL_SCSIIO_CMDS_COUNT	3
 
 #define MPI3_HIM_MASK			0xFFFFFFFF /* mask every bit*/
 
 #define MPT3SAS_INVALID_DEVICE_HANDLE	0xFFFF
 
+#define MAX_CHAIN_ELEMT_SZ		16
+#define DEFAULT_NUM_FWCHAIN_ELEMTS	8
+
 /*
  * reset phases
  */
@@ -398,6 +403,7 @@ struct MPT3SAS_DEVICE {
 	u8	configured_lun;
 	u8	block;
 	u8	tlr_snoop_check;
+	u8	ignore_delay_remove;
 };
 
 #define MPT3_CMD_NOT_USED	0x8000	/* free */
@@ -643,6 +649,7 @@ struct chain_tracker {
  * @cb_idx: callback index
  * @direct_io: To indicate whether I/O is direct (WARPDRIVE)
  * @tracker_list: list of free request (ioc->free_list)
+ * @msix_io: IO's msix
  */
 struct scsiio_tracker {
 	u16	smid;
@@ -651,6 +658,7 @@ struct scsiio_tracker {
 	u8	direct_io;
 	struct list_head chain_list;
 	struct list_head tracker_list;
+	u16     msix_io;
 };
 
 /**
@@ -676,6 +684,25 @@ struct _tr_list {
 	u16	state;
 };
 
+/**
+ * struct _sc_list - delayed SAS_IO_UNIT_CONTROL message list
+ * @handle: device handle
+ */
+struct _sc_list {
+	struct list_head list;
+	u16     handle;
+};
+
+/**
+ * struct _event_ack_list - delayed event acknowledgment list
+ * @Event: Event ID
+ * @EventContext: used to track the event uniquely
+ */
+struct _event_ack_list {
+	struct list_head list;
+	u16     Event;
+	u32     EventContext;
+};
 
 /**
  * struct adapter_reply_queue - the reply queue struct
@@ -737,7 +764,7 @@ struct mpt3sas_facts {
 	u32			IOCCapabilities;
 	union mpi3_version_union	FWVersion;
 	u16			IOCRequestFrameSize;
-	u16			Reserved3;
+	u16			IOCMaxChainSegmentSize;
 	u16			MaxInitiators;
 	u16			MaxTargets;
 	u16			MaxSasExpanders;
@@ -884,6 +911,8 @@ typedef void (*MPT3SAS_FLUSH_RUNNING_CMDS)(struct MPT3SAS_ADAPTER *ioc);
  * @max_sges_in_chain_message: number sg elements per chain
  * @chains_needed_per_io: max chains per io
  * @chain_depth: total chains allocated
+ * @chain_segment_sz: gives the max number of
+ *			SGEs accommodate on single chain buffer
  * @hi_priority_smid:
  * @hi_priority:
  * @hi_priority_dma:
@@ -921,6 +950,8 @@ typedef void (*MPT3SAS_FLUSH_RUNNING_CMDS)(struct MPT3SAS_ADAPTER *ioc);
  * @replyPostRegisterIndex: index of next position in Reply Desc Post Queue
  * @delayed_tr_list: target reset link list
  * @delayed_tr_volume_list: volume target reset link list
+ * @delayed_sc_list:
+ * @delayed_event_ack_list:
  * @temp_sensors_count: flag to carry the number of temperature sensors
  * @pci_access_mutex: Mutex to synchronize ioctl,sysfs show path and
  *	pci resource handling. PCI resource freeing will lead to free
@@ -1089,6 +1120,7 @@ struct MPT3SAS_ADAPTER {
 	u16		max_sges_in_chain_message;
 	u16		chains_needed_per_io;
 	u32		chain_depth;
+	u16		chain_segment_sz;
 
 	/* hi-priority queue */
 	u16		hi_priority_smid;
@@ -1142,6 +1174,8 @@ struct MPT3SAS_ADAPTER {
 
 	struct list_head delayed_tr_list;
 	struct list_head delayed_tr_volume_list;
+	struct list_head delayed_sc_list;
+	struct list_head delayed_event_ack_list;
 	u8		temp_sensors_count;
 	struct mutex pci_access_mutex;
 
@@ -1213,7 +1247,8 @@ void mpt3sas_base_put_smid_scsi_io(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 	u16 handle);
 void mpt3sas_base_put_smid_fast_path(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 	u16 handle);
-void mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc, u16 smid);
+void mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc,
+	u16 smid, u16 msix_task);
 void mpt3sas_base_put_smid_default(struct MPT3SAS_ADAPTER *ioc, u16 smid);
 void mpt3sas_base_initialize_callback_handler(void);
 u8 mpt3sas_base_register_callback_handler(MPT_CALLBACK cb_func);
@@ -1259,6 +1294,8 @@ void mpt3sas_scsih_clear_tm_flag(struct MPT3SAS_ADAPTER *ioc, u16 handle);
 void mpt3sas_expander_remove(struct MPT3SAS_ADAPTER *ioc, u64 sas_address);
 void mpt3sas_device_remove_by_sas_address(struct MPT3SAS_ADAPTER *ioc,
 	u64 sas_address);
+u8 mpt3sas_check_for_pending_internal_cmds(struct MPT3SAS_ADAPTER *ioc,
+	u16 smid);
 
 struct _sas_node *mpt3sas_scsih_expander_find_by_handle(
 	struct MPT3SAS_ADAPTER *ioc, u16 handle);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index d8366b056b70..7d00f09666b6 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -401,7 +401,8 @@ mpt3sas_ctl_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index,
 	Mpi2EventNotificationReply_t *mpi_reply;
 
 	mpi_reply = mpt3sas_base_get_reply_virt_addr(ioc, reply);
-	mpt3sas_ctl_add_to_event_log(ioc, mpi_reply);
+	if (mpi_reply)
+		mpt3sas_ctl_add_to_event_log(ioc, mpi_reply);
 	return 1;
 }
 
@@ -410,7 +411,7 @@ mpt3sas_ctl_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index,
  * @ioc: per adapter object
  * @iocpp: The ioc pointer is returned in this.
  * @mpi_version: will be MPI2_VERSION for mpt2ctl ioctl device &
- *		MPI25_VERSION for mpt3ctl ioctl device.
+ * MPI25_VERSION | MPI26_VERSION for mpt3ctl ioctl device.
  *
  * Return (-1) means error, else ioc_number.
  */
@@ -419,6 +420,7 @@ _ctl_verify_adapter(int ioc_number, struct MPT3SAS_ADAPTER **iocpp,
 							int mpi_version)
 {
 	struct MPT3SAS_ADAPTER *ioc;
+	int version = 0;
 	/* global ioc lock to protect controller on list operations */
 	spin_lock(&gioc_lock);
 	list_for_each_entry(ioc, &mpt3sas_ioc_list, list) {
@@ -427,8 +429,21 @@ _ctl_verify_adapter(int ioc_number, struct MPT3SAS_ADAPTER **iocpp,
 		/* Check whether this ioctl command is from right
 		 * ioctl device or not, if not continue the search.
 		 */
-		if (ioc->hba_mpi_version_belonged != mpi_version)
-			continue;
+		version = ioc->hba_mpi_version_belonged;
+		/* MPI25_VERSION and MPI26_VERSION uses same ioctl
+		 * device.
+		 */
+		if (mpi_version == (MPI25_VERSION | MPI26_VERSION)) {
+			if ((version == MPI25_VERSION) ||
+				(version == MPI26_VERSION))
+				goto out;
+			else
+				continue;
+		} else {
+			if (version != mpi_version)
+				continue;
+		}
+out:
 		spin_unlock(&gioc_lock);
 		*iocpp = ioc;
 		return ioc_number;
@@ -817,7 +832,7 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 		    tm_request->DevHandle));
 		ioc->build_sg_mpi(ioc, psge, data_out_dma, data_out_sz,
 		    data_in_dma, data_in_sz);
-		mpt3sas_base_put_smid_hi_priority(ioc, smid);
+		mpt3sas_base_put_smid_hi_priority(ioc, smid, 0);
 		break;
 	}
 	case MPI2_FUNCTION_SMP_PASSTHROUGH:
@@ -1053,6 +1068,7 @@ _ctl_getiocinfo(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 		strcat(karg.driver_version, MPT2SAS_DRIVER_VERSION);
 		break;
 	case MPI25_VERSION:
+	case MPI26_VERSION:
 		karg.adapter_type = MPT3_IOCTL_INTERFACE_SAS3;
 		strcat(karg.driver_version, MPT3SAS_DRIVER_VERSION);
 		break;
@@ -2203,7 +2219,7 @@ _ctl_compat_mpt_command(struct MPT3SAS_ADAPTER *ioc, unsigned cmd,
  * @arg - user space data buffer
  * @compat - handles 32 bit applications in 64bit os
  * @mpi_version: will be MPI2_VERSION for mpt2ctl ioctl device &
- *		MPI25_VERSION for mpt3ctl ioctl device.
+ * MPI25_VERSION | MPI26_VERSION for mpt3ctl ioctl device.
  */
 static long
 _ctl_ioctl_main(struct file *file, unsigned int cmd, void __user *arg,
@@ -2341,10 +2357,12 @@ _ctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	long ret;
 
-	/* pass MPI25_VERSION value, to indicate that this ioctl cmd
+	/* pass MPI25_VERSION | MPI26_VERSION value,
+	 * to indicate that this ioctl cmd
 	 * came from mpt3ctl ioctl device.
 	 */
-	ret = _ctl_ioctl_main(file, cmd, (void __user *)arg, 0, MPI25_VERSION);
+	ret = _ctl_ioctl_main(file, cmd, (void __user *)arg, 0,
+		MPI25_VERSION | MPI26_VERSION);
 	return ret;
 }
 
@@ -2379,7 +2397,8 @@ _ctl_ioctl_compat(struct file *file, unsigned cmd, unsigned long arg)
 {
 	long ret;
 
-	ret = _ctl_ioctl_main(file, cmd, (void __user *)arg, 1, MPI25_VERSION);
+	ret = _ctl_ioctl_main(file, cmd, (void __user *)arg, 1,
+		MPI25_VERSION | MPI26_VERSION);
 	return ret;
 }
 
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 9ab77b06434d..e0e4920d0fa6 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -1589,10 +1589,16 @@ scsih_get_resync(struct device *dev)
 		percent_complete = 0;
 
  out:
-	if (ioc->hba_mpi_version_belonged == MPI2_VERSION)
+
+	switch (ioc->hba_mpi_version_belonged) {
+	case MPI2_VERSION:
 		raid_set_resync(mpt2sas_raid_template, dev, percent_complete);
-	if (ioc->hba_mpi_version_belonged == MPI25_VERSION)
+		break;
+	case MPI25_VERSION:
+	case MPI26_VERSION:
 		raid_set_resync(mpt3sas_raid_template, dev, percent_complete);
+		break;
+	}
 }
 
 /**
@@ -1650,10 +1656,15 @@ scsih_get_state(struct device *dev)
 		break;
 	}
  out:
-	if (ioc->hba_mpi_version_belonged == MPI2_VERSION)
+	switch (ioc->hba_mpi_version_belonged) {
+	case MPI2_VERSION:
 		raid_set_state(mpt2sas_raid_template, dev, state);
-	if (ioc->hba_mpi_version_belonged == MPI25_VERSION)
+		break;
+	case MPI25_VERSION:
+	case MPI26_VERSION:
 		raid_set_state(mpt3sas_raid_template, dev, state);
+		break;
+	}
 }
 
 /**
@@ -1682,12 +1693,17 @@ _scsih_set_level(struct MPT3SAS_ADAPTER *ioc,
 		break;
 	}
 
-	if (ioc->hba_mpi_version_belonged == MPI2_VERSION)
+	switch (ioc->hba_mpi_version_belonged) {
+	case MPI2_VERSION:
 		raid_set_level(mpt2sas_raid_template,
-			       &sdev->sdev_gendev, level);
-	if (ioc->hba_mpi_version_belonged == MPI25_VERSION)
+			&sdev->sdev_gendev, level);
+		break;
+	case MPI25_VERSION:
+	case MPI26_VERSION:
 		raid_set_level(mpt3sas_raid_template,
-			       &sdev->sdev_gendev, level);
+			&sdev->sdev_gendev, level);
+		break;
+	}
 }
 
 
@@ -1937,7 +1953,15 @@ scsih_slave_configure(struct scsi_device *sdev)
 	if (sas_device->device_info & MPI2_SAS_DEVICE_INFO_SSP_TARGET) {
 		qdepth = MPT3SAS_SAS_QUEUE_DEPTH;
 		ssp_target = 1;
-		ds = "SSP";
+		if (sas_device->device_info &
+				MPI2_SAS_DEVICE_INFO_SEP) {
+			sdev_printk(KERN_WARNING, sdev,
+			"set ignore_delay_remove for handle(0x%04x)\n",
+			sas_device_priv_data->sas_target->handle);
+			sas_device_priv_data->ignore_delay_remove = 1;
+			ds = "SES";
+		} else
+			ds = "SSP";
 	} else {
 		qdepth = MPT3SAS_SATA_QUEUE_DEPTH;
 		if (sas_device->device_info & MPI2_SAS_DEVICE_INFO_STP_TARGET)
@@ -2193,6 +2217,7 @@ mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, uint channel,
 	unsigned long timeleft;
 	struct scsiio_tracker *scsi_lookup = NULL;
 	int rc;
+	u16 msix_task = 0;
 
 	if (m_type == TM_MUTEX_ON)
 		mutex_lock(&ioc->tm_cmds.mutex);
@@ -2256,7 +2281,12 @@ mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, uint channel,
 	int_to_scsilun(lun, (struct scsi_lun *)mpi_request->LUN);
 	mpt3sas_scsih_set_tm_flag(ioc, handle);
 	init_completion(&ioc->tm_cmds.done);
-	mpt3sas_base_put_smid_hi_priority(ioc, smid);
+	if ((type == MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK) &&
+			(scsi_lookup->msix_io < ioc->reply_queue_count))
+		msix_task = scsi_lookup->msix_io;
+	else
+		msix_task = 0;
+	mpt3sas_base_put_smid_hi_priority(ioc, smid, msix_task);
 	timeleft = wait_for_completion_timeout(&ioc->tm_cmds.done, timeout*HZ);
 	if (!(ioc->tm_cmds.status & MPT3_CMD_COMPLETE)) {
 		pr_err(MPT3SAS_FMT "%s: timeout\n",
@@ -2383,7 +2413,7 @@ _scsih_tm_display_info(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd)
 				 (unsigned long long)
 				 sas_device->enclosure_logical_id,
 				 sas_device->slot);
-			if (sas_device->connector_name)
+			if (sas_device->connector_name[0] != '\0')
 				starget_printk(KERN_INFO, starget,
 				"enclosure level(0x%04x),connector name(%s)\n",
 				 sas_device->enclosure_level,
@@ -2927,6 +2957,12 @@ _scsih_block_io_all_device(struct MPT3SAS_ADAPTER *ioc)
 			continue;
 		if (sas_device_priv_data->block)
 			continue;
+		if (sas_device_priv_data->ignore_delay_remove) {
+			sdev_printk(KERN_INFO, sdev,
+			"%s skip device_block for SES handle(0x%04x)\n",
+			__func__, sas_device_priv_data->sas_target->handle);
+			continue;
+		}
 		_scsih_internal_device_block(sdev, sas_device_priv_data);
 	}
 }
@@ -2959,6 +2995,12 @@ _scsih_block_io_device(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 			continue;
 		if (sas_device->pend_sas_rphy_add)
 			continue;
+		if (sas_device_priv_data->ignore_delay_remove) {
+			sdev_printk(KERN_INFO, sdev,
+			"%s skip device_block for SES handle(0x%04x)\n",
+			__func__, sas_device_priv_data->sas_target->handle);
+			continue;
+		}
 		_scsih_internal_device_block(sdev, sas_device_priv_data);
 	}
 
@@ -3118,7 +3160,7 @@ _scsih_tm_tr_send(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 			 " slot(%d)\n", ioc->name, (unsigned long long)
 			  sas_device->enclosure_logical_id,
 			  sas_device->slot));
-		if (sas_device->connector_name)
+		if (sas_device->connector_name[0] != '\0')
 			dewtprintk(ioc, pr_info(MPT3SAS_FMT
 			 "setting delete flag: enclosure level(0x%04x),"
 			 " connector name( %s)\n", ioc->name,
@@ -3151,7 +3193,7 @@ _scsih_tm_tr_send(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 	mpi_request->Function = MPI2_FUNCTION_SCSI_TASK_MGMT;
 	mpi_request->DevHandle = cpu_to_le16(handle);
 	mpi_request->TaskType = MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET;
-	mpt3sas_base_put_smid_hi_priority(ioc, smid);
+	mpt3sas_base_put_smid_hi_priority(ioc, smid, 0);
 	mpt3sas_trigger_master(ioc, MASTER_TRIGGER_DEVICE_REMOVAL);
 
 out:
@@ -3186,6 +3228,7 @@ _scsih_tm_tr_complete(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
 	Mpi2SasIoUnitControlRequest_t *mpi_request;
 	u16 smid_sas_ctrl;
 	u32 ioc_state;
+	struct _sc_list *delayed_sc;
 
 	if (ioc->remove_host) {
 		dewtprintk(ioc, pr_info(MPT3SAS_FMT
@@ -3228,9 +3271,16 @@ _scsih_tm_tr_complete(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
 
 	smid_sas_ctrl = mpt3sas_base_get_smid(ioc, ioc->tm_sas_control_cb_idx);
 	if (!smid_sas_ctrl) {
-		pr_err(MPT3SAS_FMT "%s: failed obtaining a smid\n",
-		    ioc->name, __func__);
-		return 1;
+		delayed_sc = kzalloc(sizeof(*delayed_sc), GFP_ATOMIC);
+		if (!delayed_sc)
+			return _scsih_check_for_pending_tm(ioc, smid);
+		INIT_LIST_HEAD(&delayed_sc->list);
+		delayed_sc->handle = mpi_request_tm->DevHandle;
+		list_add_tail(&delayed_sc->list, &ioc->delayed_sc_list);
+		dewtprintk(ioc, pr_info(MPT3SAS_FMT
+		    "DELAYED:sc:handle(0x%04x), (open)\n",
+		    ioc->name, handle));
+		return _scsih_check_for_pending_tm(ioc, smid);
 	}
 
 	dewtprintk(ioc, pr_info(MPT3SAS_FMT
@@ -3281,7 +3331,7 @@ _scsih_sas_control_complete(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 		pr_err(MPT3SAS_FMT "mpi_reply not valid at %s:%d/%s()!\n",
 		    ioc->name, __FILE__, __LINE__, __func__);
 	}
-	return 1;
+	return mpt3sas_check_for_pending_internal_cmds(ioc, smid);
 }
 
 /**
@@ -3332,7 +3382,7 @@ _scsih_tm_tr_volume_send(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 	mpi_request->Function = MPI2_FUNCTION_SCSI_TASK_MGMT;
 	mpi_request->DevHandle = cpu_to_le16(handle);
 	mpi_request->TaskType = MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET;
-	mpt3sas_base_put_smid_hi_priority(ioc, smid);
+	mpt3sas_base_put_smid_hi_priority(ioc, smid, 0);
 }
 
 /**
@@ -3388,6 +3438,142 @@ _scsih_tm_volume_tr_complete(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 	return _scsih_check_for_pending_tm(ioc, smid);
 }
 
+/**
+ * _scsih_issue_delayed_event_ack - issue delayed Event ACK messages
+ * @ioc: per adapter object
+ * @smid: system request message index
+ * @event: Event ID
+ * @event_context: used to track events uniquely
+ *
+ * Context - processed in interrupt context.
+ */
+void
+_scsih_issue_delayed_event_ack(struct MPT3SAS_ADAPTER *ioc, u16 smid, u16 event,
+				u32 event_context)
+{
+	Mpi2EventAckRequest_t *ack_request;
+	int i = smid - ioc->internal_smid;
+	unsigned long flags;
+
+	/* Without releasing the smid just update the
+	 * call back index and reuse the same smid for
+	 * processing this delayed request
+	 */
+	spin_lock_irqsave(&ioc->scsi_lookup_lock, flags);
+	ioc->internal_lookup[i].cb_idx = ioc->base_cb_idx;
+	spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags);
+
+	dewtprintk(ioc, pr_info(MPT3SAS_FMT
+		"EVENT ACK: event(0x%04x), smid(%d), cb(%d)\n",
+		ioc->name, le16_to_cpu(event), smid,
+		ioc->base_cb_idx));
+	ack_request = mpt3sas_base_get_msg_frame(ioc, smid);
+	memset(ack_request, 0, sizeof(Mpi2EventAckRequest_t));
+	ack_request->Function = MPI2_FUNCTION_EVENT_ACK;
+	ack_request->Event = event;
+	ack_request->EventContext = event_context;
+	ack_request->VF_ID = 0;  /* TODO */
+	ack_request->VP_ID = 0;
+	mpt3sas_base_put_smid_default(ioc, smid);
+}
+
+/**
+ * _scsih_issue_delayed_sas_io_unit_ctrl - issue delayed
+ *				sas_io_unit_ctrl messages
+ * @ioc: per adapter object
+ * @smid: system request message index
+ * @handle: device handle
+ *
+ * Context - processed in interrupt context.
+ */
+void
+_scsih_issue_delayed_sas_io_unit_ctrl(struct MPT3SAS_ADAPTER *ioc,
+					u16 smid, u16 handle)
+	{
+		Mpi2SasIoUnitControlRequest_t *mpi_request;
+		u32 ioc_state;
+		int i = smid - ioc->internal_smid;
+		unsigned long flags;
+
+		if (ioc->remove_host) {
+			dewtprintk(ioc, pr_info(MPT3SAS_FMT
+			    "%s: host has been removed\n",
+			     __func__, ioc->name));
+			return;
+		} else if (ioc->pci_error_recovery) {
+			dewtprintk(ioc, pr_info(MPT3SAS_FMT
+			    "%s: host in pci error recovery\n",
+			    __func__, ioc->name));
+		return;
+	}
+	ioc_state = mpt3sas_base_get_iocstate(ioc, 1);
+	if (ioc_state != MPI2_IOC_STATE_OPERATIONAL) {
+		dewtprintk(ioc, pr_info(MPT3SAS_FMT
+		    "%s: host is not operational\n",
+		    __func__, ioc->name));
+		return;
+	}
+
+	/* Without releasing the smid just update the
+	 * call back index and reuse the same smid for
+	 * processing this delayed request
+	 */
+	spin_lock_irqsave(&ioc->scsi_lookup_lock, flags);
+	ioc->internal_lookup[i].cb_idx = ioc->tm_sas_control_cb_idx;
+	spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags);
+
+	dewtprintk(ioc, pr_info(MPT3SAS_FMT
+	    "sc_send:handle(0x%04x), (open), smid(%d), cb(%d)\n",
+	    ioc->name, le16_to_cpu(handle), smid,
+	    ioc->tm_sas_control_cb_idx));
+	mpi_request = mpt3sas_base_get_msg_frame(ioc, smid);
+	memset(mpi_request, 0, sizeof(Mpi2SasIoUnitControlRequest_t));
+	mpi_request->Function = MPI2_FUNCTION_SAS_IO_UNIT_CONTROL;
+	mpi_request->Operation = MPI2_SAS_OP_REMOVE_DEVICE;
+	mpi_request->DevHandle = handle;
+	mpt3sas_base_put_smid_default(ioc, smid);
+}
+
+/**
+ * _scsih_check_for_pending_internal_cmds - check for pending internal messages
+ * @ioc: per adapter object
+ * @smid: system request message index
+ *
+ * Context: Executed in interrupt context
+ *
+ * This will check delayed internal messages list, and process the
+ * next request.
+ *
+ * Return 1 meaning mf should be freed from _base_interrupt
+ *        0 means the mf is freed from this function.
+ */
+u8
+mpt3sas_check_for_pending_internal_cmds(struct MPT3SAS_ADAPTER *ioc, u16 smid)
+{
+	struct _sc_list *delayed_sc;
+	struct _event_ack_list *delayed_event_ack;
+
+	if (!list_empty(&ioc->delayed_event_ack_list)) {
+		delayed_event_ack = list_entry(ioc->delayed_event_ack_list.next,
+						struct _event_ack_list, list);
+		_scsih_issue_delayed_event_ack(ioc, smid,
+		  delayed_event_ack->Event, delayed_event_ack->EventContext);
+		list_del(&delayed_event_ack->list);
+		kfree(delayed_event_ack);
+		return 0;
+	}
+
+	if (!list_empty(&ioc->delayed_sc_list)) {
+		delayed_sc = list_entry(ioc->delayed_sc_list.next,
+						struct _sc_list, list);
+		_scsih_issue_delayed_sas_io_unit_ctrl(ioc, smid,
+						 delayed_sc->handle);
+		list_del(&delayed_sc->list);
+		kfree(delayed_sc);
+		return 0;
+	}
+	return 1;
+}
 
 /**
  * _scsih_check_for_pending_tm - check for pending task management
@@ -4084,6 +4270,9 @@ _scsih_scsi_ioc_info(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
 	case MPI2_IOCSTATUS_EEDP_APP_TAG_ERROR:
 		desc_ioc_state = "eedp app tag error";
 		break;
+	case MPI2_IOCSTATUS_INSUFFICIENT_POWER:
+		desc_ioc_state = "insufficient power";
+		break;
 	default:
 		desc_ioc_state = "unknown";
 		break;
@@ -4609,6 +4798,7 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 	case MPI2_IOCSTATUS_INVALID_STATE:
 	case MPI2_IOCSTATUS_SCSI_IO_DATA_ERROR:
 	case MPI2_IOCSTATUS_SCSI_TASK_MGMT_FAILED:
+	case MPI2_IOCSTATUS_INSUFFICIENT_POWER:
 	default:
 		scmd->result = DID_SOFT_ERROR << 16;
 		break;
@@ -8391,7 +8581,8 @@ static struct raid_function_template mpt3sas_raid_functions = {
  * @pdev: PCI device struct
  *
  * return MPI2_VERSION for SAS 2.0 HBA devices,
- *	MPI25_VERSION for SAS 3.0 HBA devices.
+ *	MPI25_VERSION for SAS 3.0 HBA devices, and
+ *	MPI26 VERSION for Cutlass & Invader SAS 3.0 HBA devices
  */
 u16
 _scsih_determine_hba_mpi_version(struct pci_dev *pdev)
@@ -8423,6 +8614,17 @@ _scsih_determine_hba_mpi_version(struct pci_dev *pdev)
 	case MPI25_MFGPAGE_DEVID_SAS3108_5:
 	case MPI25_MFGPAGE_DEVID_SAS3108_6:
 		return MPI25_VERSION;
+	case MPI26_MFGPAGE_DEVID_SAS3216:
+	case MPI26_MFGPAGE_DEVID_SAS3224:
+	case MPI26_MFGPAGE_DEVID_SAS3316_1:
+	case MPI26_MFGPAGE_DEVID_SAS3316_2:
+	case MPI26_MFGPAGE_DEVID_SAS3316_3:
+	case MPI26_MFGPAGE_DEVID_SAS3316_4:
+	case MPI26_MFGPAGE_DEVID_SAS3324_1:
+	case MPI26_MFGPAGE_DEVID_SAS3324_2:
+	case MPI26_MFGPAGE_DEVID_SAS3324_3:
+	case MPI26_MFGPAGE_DEVID_SAS3324_4:
+		return MPI26_VERSION;
 	}
 	return 0;
 }
@@ -8456,7 +8658,8 @@ _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	/* Enumerate only SAS 3.0 HBA's if hbas_to_enumerate is two,
 	 * for other generation HBA's return with -ENODEV
 	 */
-	if ((hbas_to_enumerate == 2) && (hba_mpi_version !=  MPI25_VERSION))
+	if ((hbas_to_enumerate == 2) && (!(hba_mpi_version ==  MPI25_VERSION
+		|| hba_mpi_version ==  MPI26_VERSION)))
 		return -ENODEV;
 
 	switch (hba_mpi_version) {
@@ -8478,6 +8681,7 @@ _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 			ioc->mfg_pg10_hide_flag = MFG_PAGE10_EXPOSE_ALL_DISKS;
 		break;
 	case MPI25_VERSION:
+	case MPI26_VERSION:
 		/* Use mpt3sas driver host template for SAS 3.0 HBA's */
 		shost = scsi_host_alloc(&mpt3sas_driver_template,
 		  sizeof(struct MPT3SAS_ADAPTER));
@@ -8488,7 +8692,9 @@ _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		ioc->hba_mpi_version_belonged = hba_mpi_version;
 		ioc->id = mpt3_ids++;
 		sprintf(ioc->driver_name, "%s", MPT3SAS_DRIVER_NAME);
-		if (pdev->revision >= SAS3_PCI_DEVICE_C0_REVISION)
+		if ((ioc->hba_mpi_version_belonged == MPI25_VERSION &&
+			pdev->revision >= SAS3_PCI_DEVICE_C0_REVISION) ||
+			(ioc->hba_mpi_version_belonged == MPI26_VERSION))
 			ioc->msix96_vector = 1;
 		break;
 	default:
@@ -8533,6 +8739,8 @@ _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	INIT_LIST_HEAD(&ioc->raid_device_list);
 	INIT_LIST_HEAD(&ioc->sas_hba.sas_port_list);
 	INIT_LIST_HEAD(&ioc->delayed_tr_list);
+	INIT_LIST_HEAD(&ioc->delayed_sc_list);
+	INIT_LIST_HEAD(&ioc->delayed_event_ack_list);
 	INIT_LIST_HEAD(&ioc->delayed_tr_volume_list);
 	INIT_LIST_HEAD(&ioc->reply_queue_list);
 
@@ -8866,6 +9074,28 @@ static const struct pci_device_id mpt3sas_pci_table[] = {
 		PCI_ANY_ID, PCI_ANY_ID },
 	{ MPI2_MFGPAGE_VENDORID_LSI, MPI25_MFGPAGE_DEVID_SAS3108_6,
 		PCI_ANY_ID, PCI_ANY_ID },
+	/* Cutlass ~ 3216 and 3224 */
+	{ MPI2_MFGPAGE_VENDORID_LSI, MPI26_MFGPAGE_DEVID_SAS3216,
+		PCI_ANY_ID, PCI_ANY_ID },
+	{ MPI2_MFGPAGE_VENDORID_LSI, MPI26_MFGPAGE_DEVID_SAS3224,
+		PCI_ANY_ID, PCI_ANY_ID },
+	/* Intruder ~ 3316 and 3324 */
+	{ MPI2_MFGPAGE_VENDORID_LSI, MPI26_MFGPAGE_DEVID_SAS3316_1,
+		PCI_ANY_ID, PCI_ANY_ID },
+	{ MPI2_MFGPAGE_VENDORID_LSI, MPI26_MFGPAGE_DEVID_SAS3316_2,
+		PCI_ANY_ID, PCI_ANY_ID },
+	{ MPI2_MFGPAGE_VENDORID_LSI, MPI26_MFGPAGE_DEVID_SAS3316_3,
+		PCI_ANY_ID, PCI_ANY_ID },
+	{ MPI2_MFGPAGE_VENDORID_LSI, MPI26_MFGPAGE_DEVID_SAS3316_4,
+		PCI_ANY_ID, PCI_ANY_ID },
+	{ MPI2_MFGPAGE_VENDORID_LSI, MPI26_MFGPAGE_DEVID_SAS3324_1,
+		PCI_ANY_ID, PCI_ANY_ID },
+	{ MPI2_MFGPAGE_VENDORID_LSI, MPI26_MFGPAGE_DEVID_SAS3324_2,
+		PCI_ANY_ID, PCI_ANY_ID },
+	{ MPI2_MFGPAGE_VENDORID_LSI, MPI26_MFGPAGE_DEVID_SAS3324_3,
+		PCI_ANY_ID, PCI_ANY_ID },
+	{ MPI2_MFGPAGE_VENDORID_LSI, MPI26_MFGPAGE_DEVID_SAS3324_4,
+		PCI_ANY_ID, PCI_ANY_ID },
 	{0}     /* Terminating entry */
 };
 MODULE_DEVICE_TABLE(pci, mpt3sas_pci_table);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_transport.c b/drivers/scsi/mpt3sas/mpt3sas_transport.c
index ca36d7ea0964..6a84b82d71bb 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_transport.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_transport.c
@@ -1418,7 +1418,6 @@ _transport_expander_phy_control(struct MPT3SAS_ADAPTER *ioc,
 	u32 ioc_state;
 	unsigned long timeleft;
 	void *psge;
-	u32 sgl_flags;
 	u8 issue_reset = 0;
 	void *data_out = NULL;
 	dma_addr_t data_out_dma;
@@ -1507,24 +1506,10 @@ _transport_expander_phy_control(struct MPT3SAS_ADAPTER *ioc,
 	    cpu_to_le16(sizeof(struct phy_error_log_request));
 	psge = &mpi_request->SGL;
 
-	/* WRITE sgel first */
-	sgl_flags = (MPI2_SGE_FLAGS_SIMPLE_ELEMENT |
-	    MPI2_SGE_FLAGS_END_OF_BUFFER | MPI2_SGE_FLAGS_HOST_TO_IOC);
-	sgl_flags = sgl_flags << MPI2_SGE_FLAGS_SHIFT;
-	ioc->base_add_sg_single(psge, sgl_flags |
-	    sizeof(struct phy_control_request), data_out_dma);
-
-	/* incr sgel */
-	psge += ioc->sge_size;
-
-	/* READ sgel last */
-	sgl_flags = (MPI2_SGE_FLAGS_SIMPLE_ELEMENT |
-	    MPI2_SGE_FLAGS_LAST_ELEMENT | MPI2_SGE_FLAGS_END_OF_BUFFER |
-	    MPI2_SGE_FLAGS_END_OF_LIST);
-	sgl_flags = sgl_flags << MPI2_SGE_FLAGS_SHIFT;
-	ioc->base_add_sg_single(psge, sgl_flags |
-	    sizeof(struct phy_control_reply), data_out_dma +
-	    sizeof(struct phy_control_request));
+	ioc->build_sg(ioc, psge, data_out_dma,
+			    sizeof(struct phy_control_request),
+	    data_out_dma + sizeof(struct phy_control_request),
+	    sizeof(struct phy_control_reply));
 
 	dtransportprintk(ioc, pr_info(MPT3SAS_FMT
 		"phy_control - send to sas_addr(0x%016llx), phy(%d), opcode(%d)\n",
@@ -1615,7 +1600,7 @@ _transport_phy_reset(struct sas_phy *phy, int hard_reset)
 		    SMP_PHY_CONTROL_LINK_RESET);
 
 	/* handle hba phys */
-	memset(&mpi_request, 0, sizeof(Mpi2SasIoUnitControlReply_t));
+	memset(&mpi_request, 0, sizeof(Mpi2SasIoUnitControlRequest_t));
 	mpi_request.Function = MPI2_FUNCTION_SAS_IO_UNIT_CONTROL;
 	mpi_request.Operation = hard_reset ?
 	    MPI2_SAS_OP_PHY_HARD_RESET : MPI2_SAS_OP_PHY_LINK_RESET;
diff --git a/drivers/scsi/mvumi.c b/drivers/scsi/mvumi.c
index 02360de6b7e0..39285070f3b5 100644
--- a/drivers/scsi/mvumi.c
+++ b/drivers/scsi/mvumi.c
@@ -2629,7 +2629,7 @@ static void mvumi_shutdown(struct pci_dev *pdev)
 	mvumi_flush_cache(mhba);
 }
 
-static int mvumi_suspend(struct pci_dev *pdev, pm_message_t state)
+static int __maybe_unused mvumi_suspend(struct pci_dev *pdev, pm_message_t state)
 {
 	struct mvumi_hba *mhba = NULL;
 
@@ -2648,7 +2648,7 @@ static int mvumi_suspend(struct pci_dev *pdev, pm_message_t state)
 	return 0;
 }
 
-static int mvumi_resume(struct pci_dev *pdev)
+static int __maybe_unused mvumi_resume(struct pci_dev *pdev)
 {
 	int ret;
 	struct mvumi_hba *mhba = NULL;
diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c
index d8a2b5185f56..3b11aad03752 100644
--- a/drivers/scsi/osd/osd_initiator.c
+++ b/drivers/scsi/osd/osd_initiator.c
@@ -2006,9 +2006,8 @@ EXPORT_SYMBOL(osd_sec_init_nosec_doall_caps);
  */
 void osd_set_caps(struct osd_cdb *cdb, const void *caps)
 {
-	bool is_ver1 = true;
 	/* NOTE: They start at same address */
-	memcpy(&cdb->v1.caps, caps, is_ver1 ? OSDv1_CAP_LEN : OSD_CAP_LEN);
+	memcpy(&cdb->v1.caps, caps, OSDv1_CAP_LEN);
 }
 
 bool osd_is_sec_alldata(struct osd_security_parameters *sec_parms __unused)
diff --git a/drivers/scsi/ppa.c b/drivers/scsi/ppa.c
index ee00e27ba396..f6ad579280d4 100644
--- a/drivers/scsi/ppa.c
+++ b/drivers/scsi/ppa.c
@@ -37,6 +37,7 @@ typedef struct {
 	unsigned long recon_tmo;	/* How many usecs to wait for reconnection (6th bit) */
 	unsigned int failed:1;	/* Failure flag                 */
 	unsigned wanted:1;	/* Parport sharing busy flag    */
+	unsigned int dev_no;	/* Device number		*/
 	wait_queue_head_t *waiting;
 	struct Scsi_Host *host;
 	struct list_head list;
@@ -985,15 +986,40 @@ static struct scsi_host_template ppa_template = {
 
 static LIST_HEAD(ppa_hosts);
 
+/*
+ * Finds the first available device number that can be alloted to the
+ * new ppa device and returns the address of the previous node so that
+ * we can add to the tail and have a list in the ascending order.
+ */
+
+static inline ppa_struct *find_parent(void)
+{
+	ppa_struct *dev, *par = NULL;
+	unsigned int cnt = 0;
+
+	if (list_empty(&ppa_hosts))
+		return NULL;
+
+	list_for_each_entry(dev, &ppa_hosts, list) {
+		if (dev->dev_no != cnt)
+			return par;
+		cnt++;
+		par = dev;
+	}
+
+	return par;
+}
+
 static int __ppa_attach(struct parport *pb)
 {
 	struct Scsi_Host *host;
 	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(waiting);
 	DEFINE_WAIT(wait);
-	ppa_struct *dev;
+	ppa_struct *dev, *temp;
 	int ports;
 	int modes, ppb, ppb_hi;
 	int err = -ENOMEM;
+	struct pardev_cb ppa_cb;
 
 	dev = kzalloc(sizeof(ppa_struct), GFP_KERNEL);
 	if (!dev)
@@ -1002,8 +1028,15 @@ static int __ppa_attach(struct parport *pb)
 	dev->mode = PPA_AUTODETECT;
 	dev->recon_tmo = PPA_RECON_TMO;
 	init_waitqueue_head(&waiting);
-	dev->dev = parport_register_device(pb, "ppa", NULL, ppa_wakeup,
-					    NULL, 0, dev);
+	temp = find_parent();
+	if (temp)
+		dev->dev_no = temp->dev_no + 1;
+
+	memset(&ppa_cb, 0, sizeof(ppa_cb));
+	ppa_cb.private = dev;
+	ppa_cb.wakeup = ppa_wakeup;
+
+	dev->dev = parport_register_dev_model(pb, "ppa", &ppa_cb, dev->dev_no);
 
 	if (!dev->dev)
 		goto out;
@@ -1110,9 +1143,10 @@ static void ppa_detach(struct parport *pb)
 }
 
 static struct parport_driver ppa_driver = {
-	.name	= "ppa",
-	.attach	= ppa_attach,
-	.detach	= ppa_detach,
+	.name		= "ppa",
+	.match_port	= ppa_attach,
+	.detach		= ppa_detach,
+	.devmodel	= true,
 };
 
 static int __init ppa_driver_init(void)
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 6992ebc50c87..4dc06a13cab8 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -272,8 +272,8 @@ qla2x00_sysfs_write_nvram(struct file *filp, struct kobject *kobj,
 
 		iter = (uint32_t *)buf;
 		chksum = 0;
-		for (cnt = 0; cnt < ((count >> 2) - 1); cnt++)
-			chksum += le32_to_cpu(*iter++);
+		for (cnt = 0; cnt < ((count >> 2) - 1); cnt++, iter++)
+			chksum += le32_to_cpu(*iter);
 		chksum = ~chksum + 1;
 		*iter = cpu_to_le32(chksum);
 	} else {
@@ -562,6 +562,7 @@ qla2x00_sysfs_read_vpd(struct file *filp, struct kobject *kobj,
 	struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj,
 	    struct device, kobj)));
 	struct qla_hw_data *ha = vha->hw;
+	uint32_t faddr;
 
 	if (unlikely(pci_channel_offline(ha->pdev)))
 		return -EAGAIN;
@@ -569,9 +570,16 @@ qla2x00_sysfs_read_vpd(struct file *filp, struct kobject *kobj,
 	if (!capable(CAP_SYS_ADMIN))
 		return -EINVAL;
 
-	if (IS_NOCACHE_VPD_TYPE(ha))
-		ha->isp_ops->read_optrom(vha, ha->vpd, ha->flt_region_vpd << 2,
+	if (IS_NOCACHE_VPD_TYPE(ha)) {
+		faddr = ha->flt_region_vpd << 2;
+
+		if (IS_QLA27XX(ha) &&
+		    qla27xx_find_valid_image(vha) == QLA27XX_SECONDARY_IMAGE)
+			faddr = ha->flt_region_vpd_sec << 2;
+
+		ha->isp_ops->read_optrom(vha, ha->vpd, faddr,
 		    ha->vpd_size);
+	}
 	return memory_read_from_buffer(buf, count, &off, ha->vpd, ha->vpd_size);
 }
 
@@ -1909,7 +1917,8 @@ qla2x00_get_fc_host_stats(struct Scsi_Host *shost)
 	if (qla2x00_reset_active(vha))
 		goto done;
 
-	stats = dma_pool_alloc(ha->s_dma_pool, GFP_KERNEL, &stats_dma);
+	stats = dma_alloc_coherent(&ha->pdev->dev,
+	    sizeof(struct link_statistics), &stats_dma, GFP_KERNEL);
 	if (stats == NULL) {
 		ql_log(ql_log_warn, vha, 0x707d,
 		    "Failed to allocate memory for stats.\n");
@@ -1957,7 +1966,8 @@ qla2x00_get_fc_host_stats(struct Scsi_Host *shost)
 	do_div(pfc_host_stat->seconds_since_last_reset, HZ);
 
 done_free:
-        dma_pool_free(ha->s_dma_pool, stats, stats_dma);
+	dma_free_coherent(&ha->pdev->dev, sizeof(struct link_statistics),
+	    stats, stats_dma);
 done:
 	return pfc_host_stat;
 }
diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c
index c26acde797f0..392c147d5793 100644
--- a/drivers/scsi/qla2xxx/qla_bsg.c
+++ b/drivers/scsi/qla2xxx/qla_bsg.c
@@ -2107,6 +2107,195 @@ qla8044_serdes_op(struct fc_bsg_job *bsg_job)
 }
 
 static int
+qla27xx_get_flash_upd_cap(struct fc_bsg_job *bsg_job)
+{
+	struct Scsi_Host *host = bsg_job->shost;
+	scsi_qla_host_t *vha = shost_priv(host);
+	struct qla_hw_data *ha = vha->hw;
+	struct qla_flash_update_caps cap;
+
+	if (!(IS_QLA27XX(ha)))
+		return -EPERM;
+
+	memset(&cap, 0, sizeof(cap));
+	cap.capabilities = (uint64_t)ha->fw_attributes_ext[1] << 48 |
+			   (uint64_t)ha->fw_attributes_ext[0] << 32 |
+			   (uint64_t)ha->fw_attributes_h << 16 |
+			   (uint64_t)ha->fw_attributes;
+
+	sg_copy_from_buffer(bsg_job->reply_payload.sg_list,
+	    bsg_job->reply_payload.sg_cnt, &cap, sizeof(cap));
+	bsg_job->reply->reply_payload_rcv_len = sizeof(cap);
+
+	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+	    EXT_STATUS_OK;
+
+	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
+	bsg_job->reply->result = DID_OK << 16;
+	bsg_job->job_done(bsg_job);
+	return 0;
+}
+
+static int
+qla27xx_set_flash_upd_cap(struct fc_bsg_job *bsg_job)
+{
+	struct Scsi_Host *host = bsg_job->shost;
+	scsi_qla_host_t *vha = shost_priv(host);
+	struct qla_hw_data *ha = vha->hw;
+	uint64_t online_fw_attr = 0;
+	struct qla_flash_update_caps cap;
+
+	if (!(IS_QLA27XX(ha)))
+		return -EPERM;
+
+	memset(&cap, 0, sizeof(cap));
+	sg_copy_to_buffer(bsg_job->request_payload.sg_list,
+	    bsg_job->request_payload.sg_cnt, &cap, sizeof(cap));
+
+	online_fw_attr = (uint64_t)ha->fw_attributes_ext[1] << 48 |
+			 (uint64_t)ha->fw_attributes_ext[0] << 32 |
+			 (uint64_t)ha->fw_attributes_h << 16 |
+			 (uint64_t)ha->fw_attributes;
+
+	if (online_fw_attr != cap.capabilities) {
+		bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+		    EXT_STATUS_INVALID_PARAM;
+		return -EINVAL;
+	}
+
+	if (cap.outage_duration < MAX_LOOP_TIMEOUT)  {
+		bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+		    EXT_STATUS_INVALID_PARAM;
+		return -EINVAL;
+	}
+
+	bsg_job->reply->reply_payload_rcv_len = 0;
+
+	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+	    EXT_STATUS_OK;
+
+	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
+	bsg_job->reply->result = DID_OK << 16;
+	bsg_job->job_done(bsg_job);
+	return 0;
+}
+
+static int
+qla27xx_get_bbcr_data(struct fc_bsg_job *bsg_job)
+{
+	struct Scsi_Host *host = bsg_job->shost;
+	scsi_qla_host_t *vha = shost_priv(host);
+	struct qla_hw_data *ha = vha->hw;
+	struct qla_bbcr_data bbcr;
+	uint16_t loop_id, topo, sw_cap;
+	uint8_t domain, area, al_pa, state;
+	int rval;
+
+	if (!(IS_QLA27XX(ha)))
+		return -EPERM;
+
+	memset(&bbcr, 0, sizeof(bbcr));
+
+	if (vha->flags.bbcr_enable)
+		bbcr.status = QLA_BBCR_STATUS_ENABLED;
+	else
+		bbcr.status = QLA_BBCR_STATUS_DISABLED;
+
+	if (bbcr.status == QLA_BBCR_STATUS_ENABLED) {
+		rval = qla2x00_get_adapter_id(vha, &loop_id, &al_pa,
+			&area, &domain, &topo, &sw_cap);
+		if (rval != QLA_SUCCESS) {
+			bbcr.status = QLA_BBCR_STATUS_UNKNOWN;
+			bbcr.state = QLA_BBCR_STATE_OFFLINE;
+			bbcr.mbx1 = loop_id;
+			goto done;
+		}
+
+		state = (vha->bbcr >> 12) & 0x1;
+
+		if (state) {
+			bbcr.state = QLA_BBCR_STATE_OFFLINE;
+			bbcr.offline_reason_code = QLA_BBCR_REASON_LOGIN_REJECT;
+		} else {
+			bbcr.state = QLA_BBCR_STATE_ONLINE;
+			bbcr.negotiated_bbscn = (vha->bbcr >> 8) & 0xf;
+		}
+
+		bbcr.configured_bbscn = vha->bbcr & 0xf;
+	}
+
+done:
+	sg_copy_from_buffer(bsg_job->reply_payload.sg_list,
+		bsg_job->reply_payload.sg_cnt, &bbcr, sizeof(bbcr));
+	bsg_job->reply->reply_payload_rcv_len = sizeof(bbcr);
+
+	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] = EXT_STATUS_OK;
+
+	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
+	bsg_job->reply->result = DID_OK << 16;
+	bsg_job->job_done(bsg_job);
+	return 0;
+}
+
+static int
+qla2x00_get_priv_stats(struct fc_bsg_job *bsg_job)
+{
+	struct Scsi_Host *host = bsg_job->shost;
+	scsi_qla_host_t *vha = shost_priv(host);
+	struct qla_hw_data *ha = vha->hw;
+	struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev);
+	struct link_statistics *stats = NULL;
+	dma_addr_t stats_dma;
+	int rval = QLA_FUNCTION_FAILED;
+
+	if (test_bit(UNLOADING, &vha->dpc_flags))
+		goto done;
+
+	if (unlikely(pci_channel_offline(ha->pdev)))
+		goto done;
+
+	if (qla2x00_reset_active(vha))
+		goto done;
+
+	if (!IS_FWI2_CAPABLE(ha))
+		goto done;
+
+	stats = dma_alloc_coherent(&ha->pdev->dev,
+		sizeof(struct link_statistics), &stats_dma, GFP_KERNEL);
+	if (!stats) {
+		ql_log(ql_log_warn, vha, 0x70e2,
+		"Failed to allocate memory for stats.\n");
+		goto done;
+	}
+
+	memset(stats, 0, sizeof(struct link_statistics));
+
+	rval = qla24xx_get_isp_stats(base_vha, stats, stats_dma);
+
+	if (rval != QLA_SUCCESS)
+		goto done_free;
+
+	ql_dump_buffer(ql_dbg_user + ql_dbg_verbose, vha, 0x70e3,
+	    (uint8_t *)stats, sizeof(struct link_statistics));
+
+	sg_copy_from_buffer(bsg_job->reply_payload.sg_list,
+	bsg_job->reply_payload.sg_cnt, stats, sizeof(struct link_statistics));
+	bsg_job->reply->reply_payload_rcv_len = sizeof(struct link_statistics);
+
+	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] = EXT_STATUS_OK;
+
+	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
+	bsg_job->reply->result = DID_OK << 16;
+	bsg_job->job_done(bsg_job);
+
+done_free:
+	dma_free_coherent(&ha->pdev->dev, sizeof(struct link_statistics),
+		stats, stats_dma);
+done:
+	return rval;
+}
+
+static int
 qla2x00_process_vendor_specific(struct fc_bsg_job *bsg_job)
 {
 	switch (bsg_job->request->rqst_data.h_vendor.vendor_cmd[0]) {
@@ -2161,6 +2350,18 @@ qla2x00_process_vendor_specific(struct fc_bsg_job *bsg_job)
 	case QL_VND_SERDES_OP_EX:
 		return qla8044_serdes_op(bsg_job);
 
+	case QL_VND_GET_FLASH_UPDATE_CAPS:
+		return qla27xx_get_flash_upd_cap(bsg_job);
+
+	case QL_VND_SET_FLASH_UPDATE_CAPS:
+		return qla27xx_set_flash_upd_cap(bsg_job);
+
+	case QL_VND_GET_BBCR_DATA:
+		return qla27xx_get_bbcr_data(bsg_job);
+
+	case QL_VND_GET_PRIV_STATS:
+		return qla2x00_get_priv_stats(bsg_job);
+
 	default:
 		return -ENOSYS;
 	}
diff --git a/drivers/scsi/qla2xxx/qla_bsg.h b/drivers/scsi/qla2xxx/qla_bsg.h
index d38f9efa56fa..c80192d45536 100644
--- a/drivers/scsi/qla2xxx/qla_bsg.h
+++ b/drivers/scsi/qla2xxx/qla_bsg.h
@@ -25,6 +25,10 @@
 #define QL_VND_FX00_MGMT_CMD	0x12
 #define QL_VND_SERDES_OP	0x13
 #define	QL_VND_SERDES_OP_EX	0x14
+#define QL_VND_GET_FLASH_UPDATE_CAPS    0x15
+#define QL_VND_SET_FLASH_UPDATE_CAPS    0x16
+#define QL_VND_GET_BBCR_DATA    0x17
+#define QL_VND_GET_PRIV_STATS	0x18
 
 /* BSG Vendor specific subcode returns */
 #define EXT_STATUS_OK			0
@@ -232,4 +236,34 @@ struct qla_serdes_reg_ex {
 	uint32_t val;
 } __packed;
 
+struct qla_flash_update_caps {
+	uint64_t  capabilities;
+	uint32_t  outage_duration;
+	uint8_t   reserved[20];
+} __packed;
+
+/* BB_CR Status */
+#define QLA_BBCR_STATUS_DISABLED       0
+#define QLA_BBCR_STATUS_ENABLED        1
+#define QLA_BBCR_STATUS_UNKNOWN        2
+
+/* BB_CR State */
+#define QLA_BBCR_STATE_OFFLINE         0
+#define QLA_BBCR_STATE_ONLINE          1
+
+/* BB_CR Offline Reason Code */
+#define QLA_BBCR_REASON_PORT_SPEED     1
+#define QLA_BBCR_REASON_PEER_PORT      2
+#define QLA_BBCR_REASON_SWITCH         3
+#define QLA_BBCR_REASON_LOGIN_REJECT   4
+
+struct  qla_bbcr_data {
+	uint8_t   status;         /* 1 - enabled, 0 - Disabled */
+	uint8_t   state;          /* 1 - online, 0 - offline */
+	uint8_t   configured_bbscn;       /* 0-15 */
+	uint8_t   negotiated_bbscn;       /* 0-15 */
+	uint8_t   offline_reason_code;
+	uint16_t  mbx1;			/* Port state */
+	uint8_t   reserved[9];
+} __packed;
 #endif
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index cd0d94ea7f74..b64c504ff12f 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -11,7 +11,7 @@
  * ----------------------------------------------------------------------
  * |             Level            |   Last Value Used  |     Holes	|
  * ----------------------------------------------------------------------
- * | Module Init and Probe        |       0x017f       | 0x0146         |
+ * | Module Init and Probe        |       0x018f       | 0x0146         |
  * |                              |                    | 0x015b-0x0160	|
  * |                              |                    | 0x016e-0x0170  |
  * | Mailbox commands             |       0x1192       |		|
@@ -27,11 +27,12 @@
  * |                              |                    | 0x303a		|
  * | DPC Thread                   |       0x4023       | 0x4002,0x4013  |
  * | Async Events                 |       0x5089       | 0x502b-0x502f  |
+ * |                              |                    | 0x505e         |
  * |                              |                    | 0x5084,0x5075	|
  * |                              |                    | 0x503d,0x5044  |
  * |                              |                    | 0x507b,0x505f	|
  * | Timer Routines               |       0x6012       |                |
- * | User Space Interactions      |       0x70e65      | 0x7018,0x702e  |
+ * | User Space Interactions      |       0x70e3       | 0x7018,0x702e  |
  * |				  |		       | 0x7020,0x7024  |
  * |                              |                    | 0x7039,0x7045  |
  * |                              |                    | 0x7073-0x7075  |
@@ -293,8 +294,8 @@ qla24xx_read_window(struct device_reg_24xx __iomem *reg, uint32_t iobase,
 
 	WRT_REG_DWORD(&reg->iobase_addr, iobase);
 	dmp_reg = &reg->iobase_window;
-	while (count--)
-		*buf++ = htonl(RD_REG_DWORD(dmp_reg++));
+	for ( ; count--; dmp_reg++)
+		*buf++ = htonl(RD_REG_DWORD(dmp_reg));
 
 	return buf;
 }
@@ -456,8 +457,8 @@ qla2xxx_read_window(struct device_reg_2xxx __iomem *reg, uint32_t count,
 {
 	uint16_t __iomem *dmp_reg = &reg->u.isp2300.fb_cmd;
 
-	while (count--)
-		*buf++ = htons(RD_REG_WORD(dmp_reg++));
+	for ( ; count--; dmp_reg++)
+		*buf++ = htons(RD_REG_WORD(dmp_reg));
 }
 
 static inline void *
@@ -732,16 +733,18 @@ qla2300_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	if (rval == QLA_SUCCESS) {
 		dmp_reg = &reg->flash_address;
-		for (cnt = 0; cnt < sizeof(fw->pbiu_reg) / 2; cnt++)
-			fw->pbiu_reg[cnt] = htons(RD_REG_WORD(dmp_reg++));
+		for (cnt = 0; cnt < sizeof(fw->pbiu_reg) / 2; cnt++, dmp_reg++)
+			fw->pbiu_reg[cnt] = htons(RD_REG_WORD(dmp_reg));
 
 		dmp_reg = &reg->u.isp2300.req_q_in;
-		for (cnt = 0; cnt < sizeof(fw->risc_host_reg) / 2; cnt++)
-			fw->risc_host_reg[cnt] = htons(RD_REG_WORD(dmp_reg++));
+		for (cnt = 0; cnt < sizeof(fw->risc_host_reg) / 2;
+		    cnt++, dmp_reg++)
+			fw->risc_host_reg[cnt] = htons(RD_REG_WORD(dmp_reg));
 
 		dmp_reg = &reg->u.isp2300.mailbox0;
-		for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++)
-			fw->mailbox_reg[cnt] = htons(RD_REG_WORD(dmp_reg++));
+		for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2;
+		    cnt++, dmp_reg++)
+			fw->mailbox_reg[cnt] = htons(RD_REG_WORD(dmp_reg));
 
 		WRT_REG_WORD(&reg->ctrl_status, 0x40);
 		qla2xxx_read_window(reg, 32, fw->resp_dma_reg);
@@ -751,8 +754,9 @@ qla2300_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 		WRT_REG_WORD(&reg->ctrl_status, 0x00);
 		dmp_reg = &reg->risc_hw;
-		for (cnt = 0; cnt < sizeof(fw->risc_hdw_reg) / 2; cnt++)
-			fw->risc_hdw_reg[cnt] = htons(RD_REG_WORD(dmp_reg++));
+		for (cnt = 0; cnt < sizeof(fw->risc_hdw_reg) / 2;
+		    cnt++, dmp_reg++)
+			fw->risc_hdw_reg[cnt] = htons(RD_REG_WORD(dmp_reg));
 
 		WRT_REG_WORD(&reg->pcr, 0x2000);
 		qla2xxx_read_window(reg, 16, fw->risc_gp0_reg);
@@ -895,25 +899,25 @@ qla2100_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 	}
 	if (rval == QLA_SUCCESS) {
 		dmp_reg = &reg->flash_address;
-		for (cnt = 0; cnt < sizeof(fw->pbiu_reg) / 2; cnt++)
-			fw->pbiu_reg[cnt] = htons(RD_REG_WORD(dmp_reg++));
+		for (cnt = 0; cnt < sizeof(fw->pbiu_reg) / 2; cnt++, dmp_reg++)
+			fw->pbiu_reg[cnt] = htons(RD_REG_WORD(dmp_reg));
 
 		dmp_reg = &reg->u.isp2100.mailbox0;
-		for (cnt = 0; cnt < ha->mbx_count; cnt++) {
+		for (cnt = 0; cnt < ha->mbx_count; cnt++, dmp_reg++) {
 			if (cnt == 8)
 				dmp_reg = &reg->u_end.isp2200.mailbox8;
 
-			fw->mailbox_reg[cnt] = htons(RD_REG_WORD(dmp_reg++));
+			fw->mailbox_reg[cnt] = htons(RD_REG_WORD(dmp_reg));
 		}
 
 		dmp_reg = &reg->u.isp2100.unused_2[0];
-		for (cnt = 0; cnt < sizeof(fw->dma_reg) / 2; cnt++)
-			fw->dma_reg[cnt] = htons(RD_REG_WORD(dmp_reg++));
+		for (cnt = 0; cnt < sizeof(fw->dma_reg) / 2; cnt++, dmp_reg++)
+			fw->dma_reg[cnt] = htons(RD_REG_WORD(dmp_reg));
 
 		WRT_REG_WORD(&reg->ctrl_status, 0x00);
 		dmp_reg = &reg->risc_hw;
-		for (cnt = 0; cnt < sizeof(fw->risc_hdw_reg) / 2; cnt++)
-			fw->risc_hdw_reg[cnt] = htons(RD_REG_WORD(dmp_reg++));
+		for (cnt = 0; cnt < sizeof(fw->risc_hdw_reg) / 2; cnt++, dmp_reg++)
+			fw->risc_hdw_reg[cnt] = htons(RD_REG_WORD(dmp_reg));
 
 		WRT_REG_WORD(&reg->pcr, 0x2000);
 		qla2xxx_read_window(reg, 16, fw->risc_gp0_reg);
@@ -1095,8 +1099,8 @@ qla24xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	/* Host interface registers. */
 	dmp_reg = &reg->flash_addr;
-	for (cnt = 0; cnt < sizeof(fw->host_reg) / 4; cnt++)
-		fw->host_reg[cnt] = htonl(RD_REG_DWORD(dmp_reg++));
+	for (cnt = 0; cnt < sizeof(fw->host_reg) / 4; cnt++, dmp_reg++)
+		fw->host_reg[cnt] = htonl(RD_REG_DWORD(dmp_reg));
 
 	/* Disable interrupts. */
 	WRT_REG_DWORD(&reg->ictrl, 0);
@@ -1128,8 +1132,8 @@ qla24xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	/* Mailbox registers. */
 	mbx_reg = &reg->mailbox0;
-	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++)
-		fw->mailbox_reg[cnt] = htons(RD_REG_WORD(mbx_reg++));
+	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, dmp_reg++)
+		fw->mailbox_reg[cnt] = htons(RD_REG_WORD(mbx_reg));
 
 	/* Transfer sequence registers. */
 	iter_reg = fw->xseq_gp_reg;
@@ -1167,20 +1171,20 @@ qla24xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 	iter_reg = fw->req0_dma_reg;
 	iter_reg = qla24xx_read_window(reg, 0x7200, 8, iter_reg);
 	dmp_reg = &reg->iobase_q;
-	for (cnt = 0; cnt < 7; cnt++)
-		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg++));
+	for (cnt = 0; cnt < 7; cnt++, dmp_reg++)
+		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg));
 
 	iter_reg = fw->resp0_dma_reg;
 	iter_reg = qla24xx_read_window(reg, 0x7300, 8, iter_reg);
 	dmp_reg = &reg->iobase_q;
-	for (cnt = 0; cnt < 7; cnt++)
-		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg++));
+	for (cnt = 0; cnt < 7; cnt++, dmp_reg++)
+		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg));
 
 	iter_reg = fw->req1_dma_reg;
 	iter_reg = qla24xx_read_window(reg, 0x7400, 8, iter_reg);
 	dmp_reg = &reg->iobase_q;
-	for (cnt = 0; cnt < 7; cnt++)
-		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg++));
+	for (cnt = 0; cnt < 7; cnt++, dmp_reg++)
+		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg));
 
 	/* Transmit DMA registers. */
 	iter_reg = fw->xmt0_dma_reg;
@@ -1358,8 +1362,10 @@ qla25xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 	RD_REG_DWORD(&reg->iobase_addr);
 	WRT_REG_DWORD(&reg->iobase_window, 0x01);
 	dmp_reg = &reg->iobase_c4;
-	fw->pcie_regs[0] = htonl(RD_REG_DWORD(dmp_reg++));
-	fw->pcie_regs[1] = htonl(RD_REG_DWORD(dmp_reg++));
+	fw->pcie_regs[0] = htonl(RD_REG_DWORD(dmp_reg));
+	dmp_reg++;
+	fw->pcie_regs[1] = htonl(RD_REG_DWORD(dmp_reg));
+	dmp_reg++;
 	fw->pcie_regs[2] = htonl(RD_REG_DWORD(dmp_reg));
 	fw->pcie_regs[3] = htonl(RD_REG_DWORD(&reg->iobase_window));
 
@@ -1368,8 +1374,8 @@ qla25xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	/* Host interface registers. */
 	dmp_reg = &reg->flash_addr;
-	for (cnt = 0; cnt < sizeof(fw->host_reg) / 4; cnt++)
-		fw->host_reg[cnt] = htonl(RD_REG_DWORD(dmp_reg++));
+	for (cnt = 0; cnt < sizeof(fw->host_reg) / 4; cnt++, dmp_reg++)
+		fw->host_reg[cnt] = htonl(RD_REG_DWORD(dmp_reg));
 
 	/* Disable interrupts. */
 	WRT_REG_DWORD(&reg->ictrl, 0);
@@ -1417,8 +1423,8 @@ qla25xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	/* Mailbox registers. */
 	mbx_reg = &reg->mailbox0;
-	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++)
-		fw->mailbox_reg[cnt] = htons(RD_REG_WORD(mbx_reg++));
+	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, mbx_reg++)
+		fw->mailbox_reg[cnt] = htons(RD_REG_WORD(mbx_reg));
 
 	/* Transfer sequence registers. */
 	iter_reg = fw->xseq_gp_reg;
@@ -1481,20 +1487,20 @@ qla25xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 	iter_reg = fw->req0_dma_reg;
 	iter_reg = qla24xx_read_window(reg, 0x7200, 8, iter_reg);
 	dmp_reg = &reg->iobase_q;
-	for (cnt = 0; cnt < 7; cnt++)
-		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg++));
+	for (cnt = 0; cnt < 7; cnt++, dmp_reg++)
+		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg));
 
 	iter_reg = fw->resp0_dma_reg;
 	iter_reg = qla24xx_read_window(reg, 0x7300, 8, iter_reg);
 	dmp_reg = &reg->iobase_q;
-	for (cnt = 0; cnt < 7; cnt++)
-		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg++));
+	for (cnt = 0; cnt < 7; cnt++, dmp_reg++)
+		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg));
 
 	iter_reg = fw->req1_dma_reg;
 	iter_reg = qla24xx_read_window(reg, 0x7400, 8, iter_reg);
 	dmp_reg = &reg->iobase_q;
-	for (cnt = 0; cnt < 7; cnt++)
-		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg++));
+	for (cnt = 0; cnt < 7; cnt++, dmp_reg++)
+		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg));
 
 	/* Transmit DMA registers. */
 	iter_reg = fw->xmt0_dma_reg;
@@ -1679,8 +1685,10 @@ qla81xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 	RD_REG_DWORD(&reg->iobase_addr);
 	WRT_REG_DWORD(&reg->iobase_window, 0x01);
 	dmp_reg = &reg->iobase_c4;
-	fw->pcie_regs[0] = htonl(RD_REG_DWORD(dmp_reg++));
-	fw->pcie_regs[1] = htonl(RD_REG_DWORD(dmp_reg++));
+	fw->pcie_regs[0] = htonl(RD_REG_DWORD(dmp_reg));
+	dmp_reg++;
+	fw->pcie_regs[1] = htonl(RD_REG_DWORD(dmp_reg));
+	dmp_reg++;
 	fw->pcie_regs[2] = htonl(RD_REG_DWORD(dmp_reg));
 	fw->pcie_regs[3] = htonl(RD_REG_DWORD(&reg->iobase_window));
 
@@ -1689,8 +1697,8 @@ qla81xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	/* Host interface registers. */
 	dmp_reg = &reg->flash_addr;
-	for (cnt = 0; cnt < sizeof(fw->host_reg) / 4; cnt++)
-		fw->host_reg[cnt] = htonl(RD_REG_DWORD(dmp_reg++));
+	for (cnt = 0; cnt < sizeof(fw->host_reg) / 4; cnt++, dmp_reg++)
+		fw->host_reg[cnt] = htonl(RD_REG_DWORD(dmp_reg));
 
 	/* Disable interrupts. */
 	WRT_REG_DWORD(&reg->ictrl, 0);
@@ -1738,8 +1746,8 @@ qla81xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	/* Mailbox registers. */
 	mbx_reg = &reg->mailbox0;
-	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++)
-		fw->mailbox_reg[cnt] = htons(RD_REG_WORD(mbx_reg++));
+	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, mbx_reg++)
+		fw->mailbox_reg[cnt] = htons(RD_REG_WORD(mbx_reg));
 
 	/* Transfer sequence registers. */
 	iter_reg = fw->xseq_gp_reg;
@@ -1802,20 +1810,20 @@ qla81xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 	iter_reg = fw->req0_dma_reg;
 	iter_reg = qla24xx_read_window(reg, 0x7200, 8, iter_reg);
 	dmp_reg = &reg->iobase_q;
-	for (cnt = 0; cnt < 7; cnt++)
-		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg++));
+	for (cnt = 0; cnt < 7; cnt++, dmp_reg++)
+		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg));
 
 	iter_reg = fw->resp0_dma_reg;
 	iter_reg = qla24xx_read_window(reg, 0x7300, 8, iter_reg);
 	dmp_reg = &reg->iobase_q;
-	for (cnt = 0; cnt < 7; cnt++)
-		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg++));
+	for (cnt = 0; cnt < 7; cnt++, dmp_reg++)
+		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg));
 
 	iter_reg = fw->req1_dma_reg;
 	iter_reg = qla24xx_read_window(reg, 0x7400, 8, iter_reg);
 	dmp_reg = &reg->iobase_q;
-	for (cnt = 0; cnt < 7; cnt++)
-		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg++));
+	for (cnt = 0; cnt < 7; cnt++, dmp_reg++)
+		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg));
 
 	/* Transmit DMA registers. */
 	iter_reg = fw->xmt0_dma_reg;
@@ -2022,8 +2030,10 @@ qla83xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 	RD_REG_DWORD(&reg->iobase_addr);
 	WRT_REG_DWORD(&reg->iobase_window, 0x01);
 	dmp_reg = &reg->iobase_c4;
-	fw->pcie_regs[0] = htonl(RD_REG_DWORD(dmp_reg++));
-	fw->pcie_regs[1] = htonl(RD_REG_DWORD(dmp_reg++));
+	fw->pcie_regs[0] = htonl(RD_REG_DWORD(dmp_reg));
+	dmp_reg++;
+	fw->pcie_regs[1] = htonl(RD_REG_DWORD(dmp_reg));
+	dmp_reg++;
 	fw->pcie_regs[2] = htonl(RD_REG_DWORD(dmp_reg));
 	fw->pcie_regs[3] = htonl(RD_REG_DWORD(&reg->iobase_window));
 
@@ -2032,8 +2042,8 @@ qla83xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	/* Host interface registers. */
 	dmp_reg = &reg->flash_addr;
-	for (cnt = 0; cnt < sizeof(fw->host_reg) / 4; cnt++)
-		fw->host_reg[cnt] = htonl(RD_REG_DWORD(dmp_reg++));
+	for (cnt = 0; cnt < sizeof(fw->host_reg) / 4; cnt++, dmp_reg++)
+		fw->host_reg[cnt] = htonl(RD_REG_DWORD(dmp_reg));
 
 	/* Disable interrupts. */
 	WRT_REG_DWORD(&reg->ictrl, 0);
@@ -2081,8 +2091,8 @@ qla83xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	/* Mailbox registers. */
 	mbx_reg = &reg->mailbox0;
-	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++)
-		fw->mailbox_reg[cnt] = htons(RD_REG_WORD(mbx_reg++));
+	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, dmp_reg++)
+		fw->mailbox_reg[cnt] = htons(RD_REG_WORD(mbx_reg));
 
 	/* Transfer sequence registers. */
 	iter_reg = fw->xseq_gp_reg;
@@ -2177,20 +2187,20 @@ qla83xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 	iter_reg = fw->req0_dma_reg;
 	iter_reg = qla24xx_read_window(reg, 0x7200, 8, iter_reg);
 	dmp_reg = &reg->iobase_q;
-	for (cnt = 0; cnt < 7; cnt++)
-		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg++));
+	for (cnt = 0; cnt < 7; cnt++, dmp_reg++)
+		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg));
 
 	iter_reg = fw->resp0_dma_reg;
 	iter_reg = qla24xx_read_window(reg, 0x7300, 8, iter_reg);
 	dmp_reg = &reg->iobase_q;
-	for (cnt = 0; cnt < 7; cnt++)
-		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg++));
+	for (cnt = 0; cnt < 7; cnt++, dmp_reg++)
+		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg));
 
 	iter_reg = fw->req1_dma_reg;
 	iter_reg = qla24xx_read_window(reg, 0x7400, 8, iter_reg);
 	dmp_reg = &reg->iobase_q;
-	for (cnt = 0; cnt < 7; cnt++)
-		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg++));
+	for (cnt = 0; cnt < 7; cnt++, dmp_reg++)
+		*iter_reg++ = htonl(RD_REG_DWORD(dmp_reg));
 
 	/* Transmit DMA registers. */
 	iter_reg = fw->xmt0_dma_reg;
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 9872f3429e53..ceb452dd143c 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -1060,6 +1060,12 @@ struct mbx_cmd_32 {
 #define FSTATE_FATAL_ERROR         4
 #define FSTATE_LOOP_BACK_CONN      5
 
+#define QLA27XX_IMG_STATUS_VER_MAJOR   0x01
+#define QLA27XX_IMG_STATUS_VER_MINOR    0x00
+#define QLA27XX_IMG_STATUS_SIGN   0xFACEFADE
+#define QLA27XX_PRIMARY_IMAGE  1
+#define QLA27XX_SECONDARY_IMAGE    2
+
 /*
  * Port Database structure definition
  * Little endian except where noted.
@@ -1248,13 +1254,41 @@ struct link_statistics {
 	uint32_t inval_xmit_word_cnt;
 	uint32_t inval_crc_cnt;
 	uint32_t lip_cnt;
-	uint32_t unused1[0x1a];
+	uint32_t link_up_cnt;
+	uint32_t link_down_loop_init_tmo;
+	uint32_t link_down_los;
+	uint32_t link_down_loss_rcv_clk;
+	uint32_t reserved0[5];
+	uint32_t port_cfg_chg;
+	uint32_t reserved1[11];
+	uint32_t rsp_q_full;
+	uint32_t atio_q_full;
+	uint32_t drop_ae;
+	uint32_t els_proto_err;
+	uint32_t reserved2;
 	uint32_t tx_frames;
 	uint32_t rx_frames;
 	uint32_t discarded_frames;
 	uint32_t dropped_frames;
-	uint32_t unused2[1];
+	uint32_t reserved3;
 	uint32_t nos_rcvd;
+	uint32_t reserved4[4];
+	uint32_t tx_prjt;
+	uint32_t rcv_exfail;
+	uint32_t rcv_abts;
+	uint32_t seq_frm_miss;
+	uint32_t corr_err;
+	uint32_t mb_rqst;
+	uint32_t nport_full;
+	uint32_t eofa;
+	uint32_t reserved5;
+	uint32_t fpm_recv_word_cnt_lo;
+	uint32_t fpm_recv_word_cnt_hi;
+	uint32_t fpm_disc_word_cnt_lo;
+	uint32_t fpm_disc_word_cnt_hi;
+	uint32_t fpm_xmit_word_cnt_lo;
+	uint32_t fpm_xmit_word_cnt_hi;
+	uint32_t reserved6[70];
 };
 
 /*
@@ -3433,14 +3467,20 @@ struct qla_hw_data {
 	uint32_t        flt_region_flt;
 	uint32_t        flt_region_fdt;
 	uint32_t        flt_region_boot;
+	uint32_t        flt_region_boot_sec;
 	uint32_t        flt_region_fw;
+	uint32_t        flt_region_fw_sec;
 	uint32_t        flt_region_vpd_nvram;
 	uint32_t        flt_region_vpd;
+	uint32_t        flt_region_vpd_sec;
 	uint32_t        flt_region_nvram;
 	uint32_t        flt_region_npiv_conf;
 	uint32_t	flt_region_gold_fw;
 	uint32_t	flt_region_fcp_prio;
 	uint32_t	flt_region_bootload;
+	uint32_t	flt_region_img_status_pri;
+	uint32_t	flt_region_img_status_sec;
+	uint8_t         active_image;
 
 	/* Needed for BEACON */
 	uint16_t        beacon_blink_led;
@@ -3571,6 +3611,7 @@ typedef struct scsi_qla_host {
 		uint32_t	delete_progress:1;
 
 		uint32_t	fw_tgt_reported:1;
+		uint32_t	bbcr_enable:1;
 	} flags;
 
 	atomic_t	loop_state;
@@ -3703,8 +3744,19 @@ typedef struct scsi_qla_host {
 	atomic_t	vref_count;
 	struct qla8044_reset_template reset_tmplt;
 	struct qla_tgt_counters tgt_counters;
+	uint16_t	bbcr;
 } scsi_qla_host_t;
 
+struct qla27xx_image_status {
+	uint8_t image_status_mask;
+	uint16_t generation_number;
+	uint8_t reserved[3];
+	uint8_t ver_minor;
+	uint8_t ver_major;
+	uint32_t checksum;
+	uint32_t signature;
+} __packed;
+
 #define SET_VP_IDX	1
 #define SET_AL_PA	2
 #define RESET_VP_IDX	3
diff --git a/drivers/scsi/qla2xxx/qla_fw.h b/drivers/scsi/qla2xxx/qla_fw.h
index 42bb357bf56b..4c0f3a774799 100644
--- a/drivers/scsi/qla2xxx/qla_fw.h
+++ b/drivers/scsi/qla2xxx/qla_fw.h
@@ -1288,7 +1288,9 @@ struct vp_rpt_id_entry_24xx {
 
 	uint8_t vp_idx_map[16];
 
-	uint8_t reserved_4[32];
+	uint8_t reserved_4[28];
+	uint16_t bbcr;
+	uint8_t reserved_5[6];
 };
 
 #define VF_EVFP_IOCB_TYPE       0x26    /* Exchange Virtual Fabric Parameters entry. */
@@ -1393,6 +1395,16 @@ struct qla_flt_header {
 #define FLT_REG_FCOE_NVRAM_0	0xAA
 #define FLT_REG_FCOE_NVRAM_1	0xAC
 
+/* 27xx */
+#define FLT_REG_IMG_PRI_27XX	0x95
+#define FLT_REG_IMG_SEC_27XX	0x96
+#define FLT_REG_FW_SEC_27XX	0x02
+#define FLT_REG_BOOTLOAD_SEC_27XX	0x9
+#define FLT_REG_VPD_SEC_27XX_0	0x50
+#define FLT_REG_VPD_SEC_27XX_1	0x52
+#define FLT_REG_VPD_SEC_27XX_2	0xD8
+#define FLT_REG_VPD_SEC_27XX_3	0xDA
+
 struct qla_flt_region {
 	uint32_t code;
 	uint32_t size;
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index 0103e468e357..fe943772fe7b 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -90,6 +90,7 @@ extern int qla2xxx_mctp_dump(scsi_qla_host_t *);
 extern int
 qla2x00_alloc_outstanding_cmds(struct qla_hw_data *, struct req_que *);
 extern int qla2x00_init_rings(scsi_qla_host_t *);
+extern uint8_t qla27xx_find_valid_image(struct scsi_qla_host *);
 
 /*
  * Global Data in qla_os.c source file.
@@ -121,6 +122,7 @@ extern int ql2xmdcapmask;
 extern int ql2xmdenable;
 extern int ql2xexlogins;
 extern int ql2xexchoffld;
+extern int ql2xfwholdabts;
 
 extern int qla2x00_loop_reset(scsi_qla_host_t *);
 extern void qla2x00_abort_all_cmds(scsi_qla_host_t *, int);
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 52a87657c7dd..c56cdb35f3ed 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -157,8 +157,12 @@ qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport,
 	if (data[1] & QLA_LOGIO_LOGIN_RETRIED)
 		lio->u.logio.flags |= SRB_LOGIN_RETRIED;
 	rval = qla2x00_start_sp(sp);
-	if (rval != QLA_SUCCESS)
+	if (rval != QLA_SUCCESS) {
+		fcport->flags &= ~FCF_ASYNC_SENT;
+		fcport->flags |= FCF_LOGIN_NEEDED;
+		set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
 		goto done_free_sp;
+	}
 
 	ql_dbg(ql_dbg_disc, vha, 0x2072,
 	    "Async-login - hdl=%x, loopid=%x portid=%02x%02x%02x "
@@ -2062,6 +2066,10 @@ qla24xx_update_fw_options(scsi_qla_host_t *vha)
 	if (IS_P3P_TYPE(ha))
 		return;
 
+	/*  Hold status IOCBs until ABTS response received. */
+	if (ql2xfwholdabts)
+		ha->fw_options[3] |= BIT_12;
+
 	/* Update Serial Link options. */
 	if ((le16_to_cpu(ha->fw_seriallink_options24[0]) & BIT_0) == 0)
 		return;
@@ -2204,7 +2212,7 @@ qla2x00_init_rings(scsi_qla_host_t *vha)
 	/* Clear outstanding commands array. */
 	for (que = 0; que < ha->max_req_queues; que++) {
 		req = ha->req_q_map[que];
-		if (!req)
+		if (!req || !test_bit(que, ha->req_qid_map))
 			continue;
 		req->out_ptr = (void *)(req->ring + req->length);
 		*req->out_ptr = 0;
@@ -2221,7 +2229,7 @@ qla2x00_init_rings(scsi_qla_host_t *vha)
 
 	for (que = 0; que < ha->max_rsp_queues; que++) {
 		rsp = ha->rsp_q_map[que];
-		if (!rsp)
+		if (!rsp || !test_bit(que, ha->rsp_qid_map))
 			continue;
 		rsp->in_ptr = (void *)(rsp->ring + rsp->length);
 		*rsp->in_ptr = 0;
@@ -2844,7 +2852,6 @@ qla2x00_nvram_config(scsi_qla_host_t *vha)
 	if (nv->login_timeout < 4)
 		nv->login_timeout = 4;
 	ha->login_timeout = nv->login_timeout;
-	icb->login_timeout = nv->login_timeout;
 
 	/* Set minimum RATOV to 100 tenths of a second. */
 	ha->r_a_tov = 100;
@@ -4981,7 +4988,7 @@ qla25xx_init_queues(struct qla_hw_data *ha)
 
 	for (i = 1; i < ha->max_rsp_queues; i++) {
 		rsp = ha->rsp_q_map[i];
-		if (rsp) {
+		if (rsp && test_bit(i, ha->rsp_qid_map)) {
 			rsp->options &= ~BIT_0;
 			ret = qla25xx_init_rsp_que(base_vha, rsp);
 			if (ret != QLA_SUCCESS)
@@ -4996,8 +5003,8 @@ qla25xx_init_queues(struct qla_hw_data *ha)
 	}
 	for (i = 1; i < ha->max_req_queues; i++) {
 		req = ha->req_q_map[i];
-		if (req) {
-		/* Clear outstanding commands array. */
+		if (req && test_bit(i, ha->req_qid_map)) {
+			/* Clear outstanding commands array. */
 			req->options &= ~BIT_0;
 			ret = qla25xx_init_req_que(base_vha, req);
 			if (ret != QLA_SUCCESS)
@@ -5122,8 +5129,8 @@ qla24xx_nvram_config(scsi_qla_host_t *vha)
 	dptr = (uint32_t *)nv;
 	ha->isp_ops->read_nvram(vha, (uint8_t *)dptr, ha->nvram_base,
 	    ha->nvram_size);
-	for (cnt = 0, chksum = 0; cnt < ha->nvram_size >> 2; cnt++)
-		chksum += le32_to_cpu(*dptr++);
+	for (cnt = 0, chksum = 0; cnt < ha->nvram_size >> 2; cnt++, dptr++)
+		chksum += le32_to_cpu(*dptr);
 
 	ql_dbg(ql_dbg_init + ql_dbg_buffer, vha, 0x006a,
 	    "Contents of NVRAM\n");
@@ -5274,7 +5281,6 @@ qla24xx_nvram_config(scsi_qla_host_t *vha)
 	if (le16_to_cpu(nv->login_timeout) < 4)
 		nv->login_timeout = cpu_to_le16(4);
 	ha->login_timeout = le16_to_cpu(nv->login_timeout);
-	icb->login_timeout = nv->login_timeout;
 
 	/* Set minimum RATOV to 100 tenths of a second. */
 	ha->r_a_tov = 100;
@@ -5346,6 +5352,93 @@ qla24xx_nvram_config(scsi_qla_host_t *vha)
 	return (rval);
 }
 
+uint8_t qla27xx_find_valid_image(struct scsi_qla_host *vha)
+{
+	struct qla27xx_image_status pri_image_status, sec_image_status;
+	uint8_t valid_pri_image, valid_sec_image;
+	uint32_t *wptr;
+	uint32_t cnt, chksum, size;
+	struct qla_hw_data *ha = vha->hw;
+
+	valid_pri_image = valid_sec_image = 1;
+	ha->active_image = 0;
+	size = sizeof(struct qla27xx_image_status) / sizeof(uint32_t);
+
+	if (!ha->flt_region_img_status_pri) {
+		valid_pri_image = 0;
+		goto check_sec_image;
+	}
+
+	qla24xx_read_flash_data(vha, (uint32_t *)(&pri_image_status),
+	    ha->flt_region_img_status_pri, size);
+
+	if (pri_image_status.signature != QLA27XX_IMG_STATUS_SIGN) {
+		ql_dbg(ql_dbg_init, vha, 0x018b,
+		    "Primary image signature (0x%x) not valid\n",
+		    pri_image_status.signature);
+		valid_pri_image = 0;
+		goto check_sec_image;
+	}
+
+	wptr = (uint32_t *)(&pri_image_status);
+	cnt = size;
+
+	for (chksum = 0; cnt--; wptr++)
+		chksum += le32_to_cpu(*wptr);
+	if (chksum) {
+		ql_dbg(ql_dbg_init, vha, 0x018c,
+		    "Checksum validation failed for primary image (0x%x)\n",
+		    chksum);
+		valid_pri_image = 0;
+	}
+
+check_sec_image:
+	if (!ha->flt_region_img_status_sec) {
+		valid_sec_image = 0;
+		goto check_valid_image;
+	}
+
+	qla24xx_read_flash_data(vha, (uint32_t *)(&sec_image_status),
+	    ha->flt_region_img_status_sec, size);
+
+	if (sec_image_status.signature != QLA27XX_IMG_STATUS_SIGN) {
+		ql_dbg(ql_dbg_init, vha, 0x018d,
+		    "Secondary image signature(0x%x) not valid\n",
+		    sec_image_status.signature);
+		valid_sec_image = 0;
+		goto check_valid_image;
+	}
+
+	wptr = (uint32_t *)(&sec_image_status);
+	cnt = size;
+	for (chksum = 0; cnt--; wptr++)
+		chksum += le32_to_cpu(*wptr);
+	if (chksum) {
+		ql_dbg(ql_dbg_init, vha, 0x018e,
+		    "Checksum validation failed for secondary image (0x%x)\n",
+		    chksum);
+		valid_sec_image = 0;
+	}
+
+check_valid_image:
+	if (valid_pri_image && (pri_image_status.image_status_mask & 0x1))
+		ha->active_image = QLA27XX_PRIMARY_IMAGE;
+	if (valid_sec_image && (sec_image_status.image_status_mask & 0x1)) {
+		if (!ha->active_image ||
+		    pri_image_status.generation_number <
+		    sec_image_status.generation_number)
+			ha->active_image = QLA27XX_SECONDARY_IMAGE;
+	}
+
+	ql_dbg(ql_dbg_init, vha, 0x018f, "%s image\n",
+	    ha->active_image == 0 ? "default bootld and fw" :
+	    ha->active_image == 1 ? "primary" :
+	    ha->active_image == 2 ? "secondary" :
+	    "Invalid");
+
+	return ha->active_image;
+}
+
 static int
 qla24xx_load_risc_flash(scsi_qla_host_t *vha, uint32_t *srisc_addr,
     uint32_t faddr)
@@ -5368,6 +5461,10 @@ qla24xx_load_risc_flash(scsi_qla_host_t *vha, uint32_t *srisc_addr,
 	dcode = (uint32_t *)req->ring;
 	*srisc_addr = 0;
 
+	if (IS_QLA27XX(ha) &&
+	    qla27xx_find_valid_image(vha) == QLA27XX_SECONDARY_IMAGE)
+		faddr = ha->flt_region_fw_sec;
+
 	/* Validate firmware image by checking version. */
 	qla24xx_read_flash_data(vha, dcode, faddr + 4, 4);
 	for (i = 0; i < 4; i++)
@@ -6068,8 +6165,8 @@ qla81xx_nvram_config(scsi_qla_host_t *vha)
 	ha->isp_ops->read_optrom(vha, ha->nvram, ha->flt_region_nvram << 2,
 	    ha->nvram_size);
 	dptr = (uint32_t *)nv;
-	for (cnt = 0, chksum = 0; cnt < ha->nvram_size >> 2; cnt++)
-		chksum += le32_to_cpu(*dptr++);
+	for (cnt = 0, chksum = 0; cnt < ha->nvram_size >> 2; cnt++, dptr++)
+		chksum += le32_to_cpu(*dptr);
 
 	ql_dbg(ql_dbg_init + ql_dbg_buffer, vha, 0x0111,
 	    "Contents of NVRAM:\n");
@@ -6231,7 +6328,6 @@ qla81xx_nvram_config(scsi_qla_host_t *vha)
 	if (le16_to_cpu(nv->login_timeout) < 4)
 		nv->login_timeout = cpu_to_le16(4);
 	ha->login_timeout = le16_to_cpu(nv->login_timeout);
-	icb->login_timeout = nv->login_timeout;
 
 	/* Set minimum RATOV to 100 tenths of a second. */
 	ha->r_a_tov = 100;
@@ -6413,12 +6509,17 @@ qla81xx_update_fw_options(scsi_qla_host_t *vha)
 {
 	struct qla_hw_data *ha = vha->hw;
 
+	/*  Hold status IOCBs until ABTS response received. */
+	if (ql2xfwholdabts)
+		ha->fw_options[3] |= BIT_12;
+
 	if (!ql2xetsenable)
-		return;
+		goto out;
 
 	/* Enable ETS Burst. */
 	memset(ha->fw_options, 0, sizeof(ha->fw_options));
 	ha->fw_options[2] |= BIT_9;
+out:
 	qla2x00_set_fw_options(vha, ha->fw_options);
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index a6b7f1588aa4..edc48f3b8230 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -87,8 +87,8 @@ host_to_adap(uint8_t *src, uint8_t *dst, uint32_t bsize)
 	__le32 *odest = (__le32 *) dst;
 	uint32_t iter = bsize >> 2;
 
-	for (; iter ; iter--)
-		*odest++ = cpu_to_le32(*isrc++);
+	for ( ; iter--; isrc++)
+		*odest++ = cpu_to_le32(*isrc);
 }
 
 static inline void
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index d4d65eb0e9b4..5649c200d37c 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -934,10 +934,6 @@ skip_rio:
 			break;
 
 global_port_update:
-			/* Port unavailable. */
-			ql_log(ql_log_warn, vha, 0x505e,
-			    "Link is offline.\n");
-
 			if (atomic_read(&vha->loop_state) != LOOP_DOWN) {
 				atomic_set(&vha->loop_state, LOOP_DOWN);
 				atomic_set(&vha->loop_down_timer,
@@ -3063,9 +3059,9 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 		    "MSI-X: Failed to enable support "
 		    "-- %d/%d\n Retry with %d vectors.\n",
 		    ha->msix_count, ret, ret);
+		ha->msix_count = ret;
+		ha->max_rsp_queues = ha->msix_count - 1;
 	}
-	ha->msix_count = ret;
-	ha->max_rsp_queues = ha->msix_count - 1;
 	ha->msix_entries = kzalloc(sizeof(struct qla_msix_entry) *
 				ha->msix_count, GFP_KERNEL);
 	if (!ha->msix_entries) {
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 87e6758302f6..968b84613096 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -1349,6 +1349,8 @@ qla2x00_get_adapter_id(scsi_qla_host_t *vha, uint16_t *id, uint8_t *al_pa,
 		mcp->in_mb |= MBX_13|MBX_12|MBX_11|MBX_10;
 	if (IS_FWI2_CAPABLE(vha->hw))
 		mcp->in_mb |= MBX_19|MBX_18|MBX_17|MBX_16;
+	if (IS_QLA27XX(vha->hw))
+		mcp->in_mb |= MBX_15;
 	mcp->tov = MBX_TOV_SECONDS;
 	mcp->flags = 0;
 	rval = qla2x00_mailbox_command(vha, mcp);
@@ -1400,6 +1402,9 @@ qla2x00_get_adapter_id(scsi_qla_host_t *vha, uint16_t *id, uint8_t *al_pa,
 				    wwn_to_u64(vha->port_name));
 			}
 		}
+
+		if (IS_QLA27XX(vha->hw))
+			vha->bbcr = mcp->mb[15];
 	}
 
 	return rval;
@@ -2754,7 +2759,7 @@ qla2x00_get_link_status(scsi_qla_host_t *vha, uint16_t loop_id,
 	int rval;
 	mbx_cmd_t mc;
 	mbx_cmd_t *mcp = &mc;
-	uint32_t *siter, *diter, dwords;
+	uint32_t *iter, dwords;
 	struct qla_hw_data *ha = vha->hw;
 
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1084,
@@ -2794,10 +2799,11 @@ qla2x00_get_link_status(scsi_qla_host_t *vha, uint16_t loop_id,
 			/* Copy over data -- firmware data is LE. */
 			ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1086,
 			    "Done %s.\n", __func__);
-			dwords = offsetof(struct link_statistics, unused1) / 4;
-			siter = diter = &stats->link_fail_cnt;
-			while (dwords--)
-				*diter++ = le32_to_cpu(*siter++);
+			dwords = offsetof(struct link_statistics,
+					link_up_cnt) / 4;
+			iter = &stats->link_fail_cnt;
+			for ( ; dwords--; iter++)
+				le32_to_cpus(iter);
 		}
 	} else {
 		/* Failed. */
@@ -2814,7 +2820,7 @@ qla24xx_get_isp_stats(scsi_qla_host_t *vha, struct link_statistics *stats,
 	int rval;
 	mbx_cmd_t mc;
 	mbx_cmd_t *mcp = &mc;
-	uint32_t *siter, *diter, dwords;
+	uint32_t *iter, dwords;
 
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1088,
 	    "Entered %s.\n", __func__);
@@ -2843,9 +2849,9 @@ qla24xx_get_isp_stats(scsi_qla_host_t *vha, struct link_statistics *stats,
 			    "Done %s.\n", __func__);
 			/* Copy over data -- firmware data is LE. */
 			dwords = sizeof(struct link_statistics) / 4;
-			siter = diter = &stats->link_fail_cnt;
-			while (dwords--)
-				*diter++ = le32_to_cpu(*siter++);
+			iter = &stats->link_fail_cnt;
+			for ( ; dwords--; iter++)
+				le32_to_cpus(iter);
 		}
 	} else {
 		/* Failed. */
@@ -3612,6 +3618,9 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 		    rptid_entry->port_id[2], rptid_entry->port_id[1],
 		    rptid_entry->port_id[0]);
 
+		/* buffer to buffer credit flag */
+		vha->flags.bbcr_enable = (rptid_entry->bbcr & 0xf) != 0;
+
 		/* FA-WWN is only for physical port */
 		if (!vp_idx) {
 			void *wwpn = ha->init_cb->port_name;
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index c5dd594f6c31..cf7ba52bae66 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -600,7 +600,7 @@ qla25xx_delete_queues(struct scsi_qla_host *vha)
 	/* Delete request queues */
 	for (cnt = 1; cnt < ha->max_req_queues; cnt++) {
 		req = ha->req_q_map[cnt];
-		if (req) {
+		if (req && test_bit(cnt, ha->req_qid_map)) {
 			ret = qla25xx_delete_req_que(vha, req);
 			if (ret != QLA_SUCCESS) {
 				ql_log(ql_log_warn, vha, 0x00ea,
@@ -614,7 +614,7 @@ qla25xx_delete_queues(struct scsi_qla_host *vha)
 	/* Delete response queues */
 	for (cnt = 1; cnt < ha->max_rsp_queues; cnt++) {
 		rsp = ha->rsp_q_map[cnt];
-		if (rsp) {
+		if (rsp && test_bit(cnt, ha->rsp_qid_map)) {
 			ret = qla25xx_delete_rsp_que(vha, rsp);
 			if (ret != QLA_SUCCESS) {
 				ql_log(ql_log_warn, vha, 0x00eb,
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index f1788db43195..7c0b60ca158f 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -233,6 +233,13 @@ MODULE_PARM_DESC(ql2xexchoffld,
 		 "Number of exchanges to offload. "
 		 "0 (Default)- Disabled.");
 
+int ql2xfwholdabts = 0;
+module_param(ql2xfwholdabts, int, S_IRUGO);
+MODULE_PARM_DESC(ql2xfwholdabts,
+		"Allow FW to hold status IOCB until ABTS rsp received. "
+		"0 (Default) Do not set fw option. "
+		"1 - Set fw option to hold ABTS.");
+
 /*
  * SCSI host template entry points
  */
@@ -409,6 +416,9 @@ static void qla2x00_free_queues(struct qla_hw_data *ha)
 	int cnt;
 
 	for (cnt = 0; cnt < ha->max_req_queues; cnt++) {
+		if (!test_bit(cnt, ha->req_qid_map))
+			continue;
+
 		req = ha->req_q_map[cnt];
 		qla2x00_free_req_que(ha, req);
 	}
@@ -416,6 +426,9 @@ static void qla2x00_free_queues(struct qla_hw_data *ha)
 	ha->req_q_map = NULL;
 
 	for (cnt = 0; cnt < ha->max_rsp_queues; cnt++) {
+		if (!test_bit(cnt, ha->rsp_qid_map))
+			continue;
+
 		rsp = ha->rsp_q_map[cnt];
 		qla2x00_free_rsp_que(ha, rsp);
 	}
@@ -2210,6 +2223,7 @@ qla2x00_set_isp_flags(struct qla_hw_data *ha)
 		ha->device_type |= DT_ZIO_SUPPORTED;
 		ha->device_type |= DT_FWI2;
 		ha->device_type |= DT_IIDMA;
+		ha->device_type |= DT_T10_PI;
 		ha->fw_srisc_address = RISC_START_ADDRESS_2400;
 		break;
 	case PCI_DEVICE_ID_QLOGIC_ISP2271:
@@ -2217,6 +2231,7 @@ qla2x00_set_isp_flags(struct qla_hw_data *ha)
 		ha->device_type |= DT_ZIO_SUPPORTED;
 		ha->device_type |= DT_FWI2;
 		ha->device_type |= DT_IIDMA;
+		ha->device_type |= DT_T10_PI;
 		ha->fw_srisc_address = RISC_START_ADDRESS_2400;
 		break;
 	case PCI_DEVICE_ID_QLOGIC_ISP2261:
@@ -2224,6 +2239,7 @@ qla2x00_set_isp_flags(struct qla_hw_data *ha)
 		ha->device_type |= DT_ZIO_SUPPORTED;
 		ha->device_type |= DT_FWI2;
 		ha->device_type |= DT_IIDMA;
+		ha->device_type |= DT_T10_PI;
 		ha->fw_srisc_address = RISC_START_ADDRESS_2400;
 		break;
 	}
diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c
index 3272ed5bbcc7..5e9392316425 100644
--- a/drivers/scsi/qla2xxx/qla_sup.c
+++ b/drivers/scsi/qla2xxx/qla_sup.c
@@ -610,8 +610,8 @@ qla2xxx_find_flt_start(scsi_qla_host_t *vha, uint32_t *start)
 
 	wptr = (uint16_t *)req->ring;
 	cnt = sizeof(struct qla_flt_location) >> 1;
-	for (chksum = 0; cnt; cnt--)
-		chksum += le16_to_cpu(*wptr++);
+	for (chksum = 0; cnt--; wptr++)
+		chksum += le16_to_cpu(*wptr);
 	if (chksum) {
 		ql_log(ql_log_fatal, vha, 0x0045,
 		    "Inconsistent FLTL detected: checksum=0x%x.\n", chksum);
@@ -702,8 +702,8 @@ qla2xxx_get_flt_info(scsi_qla_host_t *vha, uint32_t flt_addr)
 	}
 
 	cnt = (sizeof(struct qla_flt_header) + le16_to_cpu(flt->length)) >> 1;
-	for (chksum = 0; cnt; cnt--)
-		chksum += le16_to_cpu(*wptr++);
+	for (chksum = 0; cnt--; wptr++)
+		chksum += le16_to_cpu(*wptr);
 	if (chksum) {
 		ql_log(ql_log_fatal, vha, 0x0048,
 		    "Inconsistent FLT detected: version=0x%x length=0x%x checksum=0x%x.\n",
@@ -846,6 +846,38 @@ qla2xxx_get_flt_info(scsi_qla_host_t *vha, uint32_t flt_addr)
 			if (ha->port_no == 1)
 				ha->flt_region_nvram = start;
 			break;
+		case FLT_REG_IMG_PRI_27XX:
+			if (IS_QLA27XX(ha))
+				ha->flt_region_img_status_pri = start;
+			break;
+		case FLT_REG_IMG_SEC_27XX:
+			if (IS_QLA27XX(ha))
+				ha->flt_region_img_status_sec = start;
+			break;
+		case FLT_REG_FW_SEC_27XX:
+			if (IS_QLA27XX(ha))
+				ha->flt_region_fw_sec = start;
+			break;
+		case FLT_REG_BOOTLOAD_SEC_27XX:
+			if (IS_QLA27XX(ha))
+				ha->flt_region_boot_sec = start;
+			break;
+		case FLT_REG_VPD_SEC_27XX_0:
+			if (IS_QLA27XX(ha))
+				ha->flt_region_vpd_sec = start;
+			break;
+		case FLT_REG_VPD_SEC_27XX_1:
+			if (IS_QLA27XX(ha))
+				ha->flt_region_vpd_sec = start;
+			break;
+		case FLT_REG_VPD_SEC_27XX_2:
+			if (IS_QLA27XX(ha))
+				ha->flt_region_vpd_sec = start;
+			break;
+		case FLT_REG_VPD_SEC_27XX_3:
+			if (IS_QLA27XX(ha))
+				ha->flt_region_vpd_sec = start;
+			break;
 		}
 	}
 	goto done;
@@ -898,9 +930,8 @@ qla2xxx_get_fdt_info(scsi_qla_host_t *vha)
 	    fdt->sig[3] != 'D')
 		goto no_flash_data;
 
-	for (cnt = 0, chksum = 0; cnt < sizeof(struct qla_fdt_layout) >> 1;
-	    cnt++)
-		chksum += le16_to_cpu(*wptr++);
+	for (cnt = 0, chksum = 0; cnt < sizeof(*fdt) >> 1; cnt++, wptr++)
+		chksum += le16_to_cpu(*wptr);
 	if (chksum) {
 		ql_dbg(ql_dbg_init, vha, 0x004c,
 		    "Inconsistent FDT detected:"
@@ -995,7 +1026,8 @@ qla2xxx_get_idc_param(scsi_qla_host_t *vha)
 		ha->fcoe_dev_init_timeout = QLA82XX_ROM_DEV_INIT_TIMEOUT;
 		ha->fcoe_reset_timeout = QLA82XX_ROM_DRV_RESET_ACK_TIMEOUT;
 	} else {
-		ha->fcoe_dev_init_timeout = le32_to_cpu(*wptr++);
+		ha->fcoe_dev_init_timeout = le32_to_cpu(*wptr);
+		wptr++;
 		ha->fcoe_reset_timeout = le32_to_cpu(*wptr);
 	}
 	ql_dbg(ql_dbg_init, vha, 0x004e,
@@ -1072,10 +1104,9 @@ qla2xxx_flash_npiv_conf(scsi_qla_host_t *vha)
 	ha->isp_ops->read_optrom(vha, (uint8_t *)data,
 	    ha->flt_region_npiv_conf << 2, NPIV_CONFIG_SIZE);
 
-	cnt = (sizeof(struct qla_npiv_header) + le16_to_cpu(hdr.entries) *
-	    sizeof(struct qla_npiv_entry)) >> 1;
-	for (wptr = data, chksum = 0; cnt; cnt--)
-		chksum += le16_to_cpu(*wptr++);
+	cnt = (sizeof(hdr) + le16_to_cpu(hdr.entries) * sizeof(*entry)) >> 1;
+	for (wptr = data, chksum = 0; cnt--; wptr++)
+		chksum += le16_to_cpu(*wptr);
 	if (chksum) {
 		ql_dbg(ql_dbg_user, vha, 0x7092,
 		    "Inconsistent NPIV-Config "
@@ -2989,6 +3020,9 @@ qla24xx_get_flash_version(scsi_qla_host_t *vha, void *mbuf)
 	uint8_t code_type, last_image;
 	int i;
 	struct qla_hw_data *ha = vha->hw;
+	uint32_t faddr = 0;
+
+	pcihdr = pcids = 0;
 
 	if (IS_P3P_TYPE(ha))
 		return ret;
@@ -3002,9 +3036,11 @@ qla24xx_get_flash_version(scsi_qla_host_t *vha, void *mbuf)
 	memset(ha->fw_revision, 0, sizeof(ha->fw_revision));
 
 	dcode = mbuf;
-
-	/* Begin with first PCI expansion ROM header. */
 	pcihdr = ha->flt_region_boot << 2;
+	if (IS_QLA27XX(ha) &&
+	    qla27xx_find_valid_image(vha) == QLA27XX_SECONDARY_IMAGE)
+		pcihdr = ha->flt_region_boot_sec << 2;
+
 	last_image = 1;
 	do {
 		/* Verify PCI expansion ROM header. */
@@ -3077,8 +3113,12 @@ qla24xx_get_flash_version(scsi_qla_host_t *vha, void *mbuf)
 	/* Read firmware image information. */
 	memset(ha->fw_revision, 0, sizeof(ha->fw_revision));
 	dcode = mbuf;
+	faddr = ha->flt_region_fw;
+	if (IS_QLA27XX(ha) &&
+	    qla27xx_find_valid_image(vha) == QLA27XX_SECONDARY_IMAGE)
+		faddr = ha->flt_region_fw_sec;
 
-	qla24xx_read_flash_data(vha, dcode, ha->flt_region_fw + 4, 4);
+	qla24xx_read_flash_data(vha, dcode, faddr + 4, 4);
 	for (i = 0; i < 4; i++)
 		dcode[i] = be32_to_cpu(dcode[i]);
 
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 8075a4cdb45c..ee967becd257 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -105,7 +105,7 @@ static void qlt_response_pkt(struct scsi_qla_host *ha, response_t *pkt);
 static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun,
 	int fn, void *iocb, int flags);
 static void qlt_send_term_exchange(struct scsi_qla_host *ha, struct qla_tgt_cmd
-	*cmd, struct atio_from_isp *atio, int ha_locked);
+	*cmd, struct atio_from_isp *atio, int ha_locked, int ul_abort);
 static void qlt_reject_free_srr_imm(struct scsi_qla_host *ha,
 	struct qla_tgt_srr_imm *imm, int ha_lock);
 static void qlt_abort_cmd_on_host_reset(struct scsi_qla_host *vha,
@@ -1756,7 +1756,7 @@ void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *mcmd)
 		qlt_send_notify_ack(vha, &mcmd->orig_iocb.imm_ntfy,
 		    0, 0, 0, 0, 0, 0);
 	else {
-		if (mcmd->se_cmd.se_tmr_req->function == TMR_ABORT_TASK)
+		if (mcmd->orig_iocb.atio.u.raw.entry_type == ABTS_RECV_24XX)
 			qlt_24xx_send_abts_resp(vha, &mcmd->orig_iocb.abts,
 			    mcmd->fc_tm_rsp, false);
 		else
@@ -2665,7 +2665,7 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 			/* no need to terminate. FW already freed exchange. */
 			qlt_abort_cmd_on_host_reset(cmd->vha, cmd);
 		else
-			qlt_send_term_exchange(vha, cmd, &cmd->atio, 1);
+			qlt_send_term_exchange(vha, cmd, &cmd->atio, 1, 0);
 		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 		return 0;
 	}
@@ -3173,7 +3173,8 @@ static int __qlt_send_term_exchange(struct scsi_qla_host *vha,
 }
 
 static void qlt_send_term_exchange(struct scsi_qla_host *vha,
-	struct qla_tgt_cmd *cmd, struct atio_from_isp *atio, int ha_locked)
+	struct qla_tgt_cmd *cmd, struct atio_from_isp *atio, int ha_locked,
+	int ul_abort)
 {
 	unsigned long flags = 0;
 	int rc;
@@ -3193,8 +3194,7 @@ static void qlt_send_term_exchange(struct scsi_qla_host *vha,
 		qlt_alloc_qfull_cmd(vha, atio, 0, 0);
 
 done:
-	if (cmd && (!cmd->aborted ||
-	    !cmd->cmd_sent_to_fw)) {
+	if (cmd && !ul_abort && !cmd->aborted) {
 		if (cmd->sg_mapped)
 			qlt_unmap_sg(vha, cmd);
 		vha->hw->tgt.tgt_ops->free_cmd(cmd);
@@ -3253,21 +3253,38 @@ static void qlt_chk_exch_leak_thresh_hold(struct scsi_qla_host *vha)
 
 }
 
-void qlt_abort_cmd(struct qla_tgt_cmd *cmd)
+int qlt_abort_cmd(struct qla_tgt_cmd *cmd)
 {
 	struct qla_tgt *tgt = cmd->tgt;
 	struct scsi_qla_host *vha = tgt->vha;
 	struct se_cmd *se_cmd = &cmd->se_cmd;
+	unsigned long flags;
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf014,
 	    "qla_target(%d): terminating exchange for aborted cmd=%p "
 	    "(se_cmd=%p, tag=%llu)", vha->vp_idx, cmd, &cmd->se_cmd,
 	    se_cmd->tag);
 
+	spin_lock_irqsave(&cmd->cmd_lock, flags);
+	if (cmd->aborted) {
+		spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+		/*
+		 * It's normal to see 2 calls in this path:
+		 *  1) XFER Rdy completion + CMD_T_ABORT
+		 *  2) TCM TMR - drain_state_list
+		 */
+	        ql_dbg(ql_dbg_tgt_mgt, vha, 0xffff,
+			"multiple abort. %p transport_state %x, t_state %x,"
+			" se_cmd_flags %x \n", cmd, cmd->se_cmd.transport_state,
+			cmd->se_cmd.t_state,cmd->se_cmd.se_cmd_flags);
+		return EIO;
+	}
 	cmd->aborted = 1;
 	cmd->cmd_flags |= BIT_6;
+	spin_unlock_irqrestore(&cmd->cmd_lock, flags);
 
-	qlt_send_term_exchange(vha, cmd, &cmd->atio, 0);
+	qlt_send_term_exchange(vha, cmd, &cmd->atio, 0, 1);
+	return 0;
 }
 EXPORT_SYMBOL(qlt_abort_cmd);
 
@@ -3282,6 +3299,9 @@ void qlt_free_cmd(struct qla_tgt_cmd *cmd)
 
 	BUG_ON(cmd->cmd_in_wq);
 
+	if (cmd->sg_mapped)
+		qlt_unmap_sg(cmd->vha, cmd);
+
 	if (!cmd->q_full)
 		qlt_decr_num_pend_cmds(cmd->vha);
 
@@ -3399,7 +3419,7 @@ static int qlt_term_ctio_exchange(struct scsi_qla_host *vha, void *ctio,
 		term = 1;
 
 	if (term)
-		qlt_send_term_exchange(vha, cmd, &cmd->atio, 1);
+		qlt_send_term_exchange(vha, cmd, &cmd->atio, 1, 0);
 
 	return term;
 }
@@ -3580,12 +3600,13 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle,
 		case CTIO_PORT_LOGGED_OUT:
 		case CTIO_PORT_UNAVAILABLE:
 		{
-			int logged_out = (status & 0xFFFF);
+			int logged_out =
+				(status & 0xFFFF) == CTIO_PORT_LOGGED_OUT;
+
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf059,
 			    "qla_target(%d): CTIO with %s status %x "
 			    "received (state %x, se_cmd %p)\n", vha->vp_idx,
-			    (logged_out == CTIO_PORT_LOGGED_OUT) ?
-			    "PORT LOGGED OUT" : "PORT UNAVAILABLE",
+			    logged_out ? "PORT LOGGED OUT" : "PORT UNAVAILABLE",
 			    status, cmd->state, se_cmd);
 
 			if (logged_out && cmd->sess) {
@@ -3754,6 +3775,7 @@ static void __qlt_do_work(struct qla_tgt_cmd *cmd)
 		goto out_term;
 	}
 
+	spin_lock_init(&cmd->cmd_lock);
 	cdb = &atio->u.isp24.fcp_cmnd.cdb[0];
 	cmd->se_cmd.tag = atio->u.isp24.exchange_addr;
 	cmd->unpacked_lun = scsilun_to_int(
@@ -3796,7 +3818,7 @@ out_term:
 	 */
 	cmd->cmd_flags |= BIT_2;
 	spin_lock_irqsave(&ha->hardware_lock, flags);
-	qlt_send_term_exchange(vha, NULL, &cmd->atio, 1);
+	qlt_send_term_exchange(vha, NULL, &cmd->atio, 1, 0);
 
 	qlt_decr_num_pend_cmds(vha);
 	percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
@@ -3918,7 +3940,7 @@ static void qlt_create_sess_from_atio(struct work_struct *work)
 
 out_term:
 	spin_lock_irqsave(&ha->hardware_lock, flags);
-	qlt_send_term_exchange(vha, NULL, &op->atio, 1);
+	qlt_send_term_exchange(vha, NULL, &op->atio, 1, 0);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 	kfree(op);
 
@@ -3982,7 +4004,8 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 
 	cmd->cmd_in_wq = 1;
 	cmd->cmd_flags |= BIT_0;
-	cmd->se_cmd.cpuid = -1;
+	cmd->se_cmd.cpuid = ha->msix_count ?
+		ha->tgt.rspq_vector_cpuid : WORK_CPU_UNBOUND;
 
 	spin_lock(&vha->cmd_list_lock);
 	list_add_tail(&cmd->cmd_list, &vha->qla_cmd_list);
@@ -3990,7 +4013,6 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 
 	INIT_WORK(&cmd->work, qlt_do_work);
 	if (ha->msix_count) {
-		cmd->se_cmd.cpuid = ha->tgt.rspq_vector_cpuid;
 		if (cmd->atio.u.isp24.fcp_cmnd.rddata)
 			queue_work_on(smp_processor_id(), qla_tgt_wq,
 			    &cmd->work);
@@ -4771,7 +4793,7 @@ out_reject:
 		dump_stack();
 	} else {
 		cmd->cmd_flags |= BIT_9;
-		qlt_send_term_exchange(vha, cmd, &cmd->atio, 1);
+		qlt_send_term_exchange(vha, cmd, &cmd->atio, 1, 0);
 	}
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 }
@@ -4950,7 +4972,7 @@ static void qlt_prepare_srr_imm(struct scsi_qla_host *vha,
 				    sctio, sctio->srr_id);
 				list_del(&sctio->srr_list_entry);
 				qlt_send_term_exchange(vha, sctio->cmd,
-				    &sctio->cmd->atio, 1);
+				    &sctio->cmd->atio, 1, 0);
 				kfree(sctio);
 			}
 		}
@@ -5123,7 +5145,7 @@ static int __qlt_send_busy(struct scsi_qla_host *vha,
 	    atio->u.isp24.fcp_hdr.s_id);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 	if (!sess) {
-		qlt_send_term_exchange(vha, NULL, atio, 1);
+		qlt_send_term_exchange(vha, NULL, atio, 1, 0);
 		return 0;
 	}
 	/* Sending marker isn't necessary, since we called from ISR */
@@ -5406,7 +5428,7 @@ static void qlt_24xx_atio_pkt(struct scsi_qla_host *vha,
 #if 1 /* With TERM EXCHANGE some FC cards refuse to boot */
 				qlt_send_busy(vha, atio, SAM_STAT_BUSY);
 #else
-				qlt_send_term_exchange(vha, NULL, atio, 1);
+				qlt_send_term_exchange(vha, NULL, atio, 1, 0);
 #endif
 
 				if (!ha_locked)
@@ -5523,7 +5545,7 @@ static void qlt_response_pkt(struct scsi_qla_host *vha, response_t *pkt)
 #if 1 /* With TERM EXCHANGE some FC cards refuse to boot */
 				qlt_send_busy(vha, atio, 0);
 #else
-				qlt_send_term_exchange(vha, NULL, atio, 1);
+				qlt_send_term_exchange(vha, NULL, atio, 1, 0);
 #endif
 			} else {
 				if (tgt->tgt_stop) {
@@ -5532,7 +5554,7 @@ static void qlt_response_pkt(struct scsi_qla_host *vha, response_t *pkt)
 					    "command to target, sending TERM "
 					    "EXCHANGE for rsp\n");
 					qlt_send_term_exchange(vha, NULL,
-					    atio, 1);
+					    atio, 1, 0);
 				} else {
 					ql_dbg(ql_dbg_tgt, vha, 0xe060,
 					    "qla_target(%d): Unable to send "
@@ -5960,7 +5982,7 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
 	return;
 
 out_term:
-	qlt_send_term_exchange(vha, NULL, &prm->tm_iocb2, 0);
+	qlt_send_term_exchange(vha, NULL, &prm->tm_iocb2, 1, 0);
 	if (sess)
 		ha->tgt.tgt_ops->put_sess(sess);
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 71b2865ba3c8..22a6a767fe07 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -943,6 +943,36 @@ struct qla_tgt_sess {
 	qlt_plogi_ack_t *plogi_link[QLT_PLOGI_LINK_MAX];
 };
 
+typedef enum {
+	/*
+	 * BIT_0 - Atio Arrival / schedule to work
+	 * BIT_1 - qlt_do_work
+	 * BIT_2 - qlt_do work failed
+	 * BIT_3 - xfer rdy/tcm_qla2xxx_write_pending
+	 * BIT_4 - read respond/tcm_qla2xx_queue_data_in
+	 * BIT_5 - status respond / tcm_qla2xx_queue_status
+	 * BIT_6 - tcm request to abort/Term exchange.
+	 *	pre_xmit_response->qlt_send_term_exchange
+	 * BIT_7 - SRR received (qlt_handle_srr->qlt_xmit_response)
+	 * BIT_8 - SRR received (qlt_handle_srr->qlt_rdy_to_xfer)
+	 * BIT_9 - SRR received (qla_handle_srr->qlt_send_term_exchange)
+	 * BIT_10 - Data in - hanlde_data->tcm_qla2xxx_handle_data
+
+	 * BIT_12 - good completion - qlt_ctio_do_completion -->free_cmd
+	 * BIT_13 - Bad completion -
+	 *	qlt_ctio_do_completion --> qlt_term_ctio_exchange
+	 * BIT_14 - Back end data received/sent.
+	 * BIT_15 - SRR prepare ctio
+	 * BIT_16 - complete free
+	 * BIT_17 - flush - qlt_abort_cmd_on_host_reset
+	 * BIT_18 - completion w/abort status
+	 * BIT_19 - completion w/unknown status
+	 * BIT_20 - tcm_qla2xxx_free_cmd
+	 */
+	CMD_FLAG_DATA_WORK = BIT_11,
+	CMD_FLAG_DATA_WORK_FREE = BIT_21,
+} cmd_flags_t;
+
 struct qla_tgt_cmd {
 	struct se_cmd se_cmd;
 	struct qla_tgt_sess *sess;
@@ -952,6 +982,7 @@ struct qla_tgt_cmd {
 	/* Sense buffer that will be mapped into outgoing status */
 	unsigned char sense_buffer[TRANSPORT_SENSE_BUFFER];
 
+	spinlock_t cmd_lock;
 	/* to save extra sess dereferences */
 	unsigned int conf_compl_supported:1;
 	unsigned int sg_mapped:1;
@@ -986,30 +1017,8 @@ struct qla_tgt_cmd {
 
 	uint64_t jiffies_at_alloc;
 	uint64_t jiffies_at_free;
-	/* BIT_0 - Atio Arrival / schedule to work
-	 * BIT_1 - qlt_do_work
-	 * BIT_2 - qlt_do work failed
-	 * BIT_3 - xfer rdy/tcm_qla2xxx_write_pending
-	 * BIT_4 - read respond/tcm_qla2xx_queue_data_in
-	 * BIT_5 - status respond / tcm_qla2xx_queue_status
-	 * BIT_6 - tcm request to abort/Term exchange.
-	 *	pre_xmit_response->qlt_send_term_exchange
-	 * BIT_7 - SRR received (qlt_handle_srr->qlt_xmit_response)
-	 * BIT_8 - SRR received (qlt_handle_srr->qlt_rdy_to_xfer)
-	 * BIT_9 - SRR received (qla_handle_srr->qlt_send_term_exchange)
-	 * BIT_10 - Data in - hanlde_data->tcm_qla2xxx_handle_data
-	 * BIT_11 - Data actually going to TCM : tcm_qla2xx_handle_data_work
-	 * BIT_12 - good completion - qlt_ctio_do_completion -->free_cmd
-	 * BIT_13 - Bad completion -
-	 *	qlt_ctio_do_completion --> qlt_term_ctio_exchange
-	 * BIT_14 - Back end data received/sent.
-	 * BIT_15 - SRR prepare ctio
-	 * BIT_16 - complete free
-	 * BIT_17 - flush - qlt_abort_cmd_on_host_reset
-	 * BIT_18 - completion w/abort status
-	 * BIT_19 - completion w/unknown status
-	 */
-	uint32_t cmd_flags;
+
+	cmd_flags_t cmd_flags;
 };
 
 struct qla_tgt_sess_work_param {
@@ -1148,7 +1157,7 @@ static inline void sid_to_portid(const uint8_t *s_id, port_id_t *p)
 extern void qlt_response_pkt_all_vps(struct scsi_qla_host *, response_t *);
 extern int qlt_rdy_to_xfer(struct qla_tgt_cmd *);
 extern int qlt_xmit_response(struct qla_tgt_cmd *, int, uint8_t);
-extern void qlt_abort_cmd(struct qla_tgt_cmd *);
+extern int qlt_abort_cmd(struct qla_tgt_cmd *);
 extern void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *);
 extern void qlt_free_mcmd(struct qla_tgt_mgmt_cmd *);
 extern void qlt_free_cmd(struct qla_tgt_cmd *cmd);
diff --git a/drivers/scsi/qla2xxx/qla_tmpl.c b/drivers/scsi/qla2xxx/qla_tmpl.c
index ddbe2e7ac14d..c3e622524604 100644
--- a/drivers/scsi/qla2xxx/qla_tmpl.c
+++ b/drivers/scsi/qla2xxx/qla_tmpl.c
@@ -395,6 +395,10 @@ qla27xx_fwdt_entry_t263(struct scsi_qla_host *vha,
 	if (ent->t263.queue_type == T263_QUEUE_TYPE_REQ) {
 		for (i = 0; i < vha->hw->max_req_queues; i++) {
 			struct req_que *req = vha->hw->req_q_map[i];
+
+			if (!test_bit(i, vha->hw->req_qid_map))
+				continue;
+
 			if (req || !buf) {
 				length = req ?
 				    req->length : REQUEST_ENTRY_CNT_24XX;
@@ -408,6 +412,10 @@ qla27xx_fwdt_entry_t263(struct scsi_qla_host *vha,
 	} else if (ent->t263.queue_type == T263_QUEUE_TYPE_RSP) {
 		for (i = 0; i < vha->hw->max_rsp_queues; i++) {
 			struct rsp_que *rsp = vha->hw->rsp_q_map[i];
+
+			if (!test_bit(i, vha->hw->rsp_qid_map))
+				continue;
+
 			if (rsp || !buf) {
 				length = rsp ?
 				    rsp->length : RESPONSE_ENTRY_CNT_MQ;
@@ -634,6 +642,10 @@ qla27xx_fwdt_entry_t274(struct scsi_qla_host *vha,
 	if (ent->t274.queue_type == T274_QUEUE_TYPE_REQ_SHAD) {
 		for (i = 0; i < vha->hw->max_req_queues; i++) {
 			struct req_que *req = vha->hw->req_q_map[i];
+
+			if (!test_bit(i, vha->hw->req_qid_map))
+				continue;
+
 			if (req || !buf) {
 				qla27xx_insert16(i, buf, len);
 				qla27xx_insert16(1, buf, len);
@@ -645,6 +657,10 @@ qla27xx_fwdt_entry_t274(struct scsi_qla_host *vha,
 	} else if (ent->t274.queue_type == T274_QUEUE_TYPE_RSP_SHAD) {
 		for (i = 0; i < vha->hw->max_rsp_queues; i++) {
 			struct rsp_que *rsp = vha->hw->rsp_q_map[i];
+
+			if (!test_bit(i, vha->hw->rsp_qid_map))
+				continue;
+
 			if (rsp || !buf) {
 				qla27xx_insert16(i, buf, len);
 				qla27xx_insert16(1, buf, len);
diff --git a/drivers/scsi/qla2xxx/qla_version.h b/drivers/scsi/qla2xxx/qla_version.h
index 6d31faa8c57b..0bc93fa46dae 100644
--- a/drivers/scsi/qla2xxx/qla_version.h
+++ b/drivers/scsi/qla2xxx/qla_version.h
@@ -7,7 +7,7 @@
 /*
  * Driver version
  */
-#define QLA2XXX_VERSION      "8.07.00.26-k"
+#define QLA2XXX_VERSION      "8.07.00.33-k"
 
 #define QLA_DRIVER_MAJOR_VER	8
 #define QLA_DRIVER_MINOR_VER	7
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index faf0a126627f..1808a01cfb7e 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -298,6 +298,10 @@ static void tcm_qla2xxx_free_cmd(struct qla_tgt_cmd *cmd)
 {
 	cmd->vha->tgt_counters.core_qla_free_cmd++;
 	cmd->cmd_in_wq = 1;
+
+	BUG_ON(cmd->cmd_flags & BIT_20);
+	cmd->cmd_flags |= BIT_20;
+
 	INIT_WORK(&cmd->work, tcm_qla2xxx_complete_free);
 	queue_work_on(smp_processor_id(), tcm_qla2xxx_free_wq, &cmd->work);
 }
@@ -374,6 +378,20 @@ static int tcm_qla2xxx_write_pending(struct se_cmd *se_cmd)
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
+
+	if (cmd->aborted) {
+		/* Cmd can loop during Q-full.  tcm_qla2xxx_aborted_task
+		 * can get ahead of this cmd. tcm_qla2xxx_aborted_task
+		 * already kick start the free.
+		 */
+		pr_debug("write_pending aborted cmd[%p] refcount %d "
+			"transport_state %x, t_state %x, se_cmd_flags %x\n",
+			cmd,cmd->se_cmd.cmd_kref.refcount.counter,
+			cmd->se_cmd.transport_state,
+			cmd->se_cmd.t_state,
+			cmd->se_cmd.se_cmd_flags);
+		return 0;
+	}
 	cmd->cmd_flags |= BIT_3;
 	cmd->bufflen = se_cmd->data_length;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
@@ -405,7 +423,7 @@ static int tcm_qla2xxx_write_pending_status(struct se_cmd *se_cmd)
 	    se_cmd->t_state == TRANSPORT_COMPLETE_QF_WP) {
 		spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
 		wait_for_completion_timeout(&se_cmd->t_transport_stop_comp,
-					    3 * HZ);
+						50);
 		return 0;
 	}
 	spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
@@ -444,6 +462,9 @@ static int tcm_qla2xxx_handle_cmd(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd,
 	if (bidi)
 		flags |= TARGET_SCF_BIDI_OP;
 
+	if (se_cmd->cpuid != WORK_CPU_UNBOUND)
+		flags |= TARGET_SCF_USE_CPUID;
+
 	sess = cmd->sess;
 	if (!sess) {
 		pr_err("Unable to locate struct qla_tgt_sess from qla_tgt_cmd\n");
@@ -465,13 +486,25 @@ static int tcm_qla2xxx_handle_cmd(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd,
 static void tcm_qla2xxx_handle_data_work(struct work_struct *work)
 {
 	struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work);
+	unsigned long flags;
 
 	/*
 	 * Ensure that the complete FCP WRITE payload has been received.
 	 * Otherwise return an exception via CHECK_CONDITION status.
 	 */
 	cmd->cmd_in_wq = 0;
-	cmd->cmd_flags |= BIT_11;
+
+	spin_lock_irqsave(&cmd->cmd_lock, flags);
+	cmd->cmd_flags |= CMD_FLAG_DATA_WORK;
+	if (cmd->aborted) {
+		cmd->cmd_flags |= CMD_FLAG_DATA_WORK_FREE;
+		spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+
+		tcm_qla2xxx_free_cmd(cmd);
+		return;
+	}
+	spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+
 	cmd->vha->tgt_counters.qla_core_ret_ctio++;
 	if (!cmd->write_data_transferred) {
 		/*
@@ -546,6 +579,20 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd)
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
 
+	if (cmd->aborted) {
+		/* Cmd can loop during Q-full.  tcm_qla2xxx_aborted_task
+		 * can get ahead of this cmd. tcm_qla2xxx_aborted_task
+		 * already kick start the free.
+		 */
+		pr_debug("queue_data_in aborted cmd[%p] refcount %d "
+			"transport_state %x, t_state %x, se_cmd_flags %x\n",
+			cmd,cmd->se_cmd.cmd_kref.refcount.counter,
+			cmd->se_cmd.transport_state,
+			cmd->se_cmd.t_state,
+			cmd->se_cmd.se_cmd_flags);
+		return 0;
+	}
+
 	cmd->cmd_flags |= BIT_4;
 	cmd->bufflen = se_cmd->data_length;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
@@ -637,11 +684,34 @@ static void tcm_qla2xxx_queue_tm_rsp(struct se_cmd *se_cmd)
 	qlt_xmit_tm_rsp(mcmd);
 }
 
+
+#define DATA_WORK_NOT_FREE(_flags) \
+	(( _flags & (CMD_FLAG_DATA_WORK|CMD_FLAG_DATA_WORK_FREE)) == \
+	 CMD_FLAG_DATA_WORK)
 static void tcm_qla2xxx_aborted_task(struct se_cmd *se_cmd)
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
-	qlt_abort_cmd(cmd);
+	unsigned long flags;
+
+	if (qlt_abort_cmd(cmd))
+		return;
+
+	spin_lock_irqsave(&cmd->cmd_lock, flags);
+	if ((cmd->state == QLA_TGT_STATE_NEW)||
+		((cmd->state == QLA_TGT_STATE_DATA_IN) &&
+		 DATA_WORK_NOT_FREE(cmd->cmd_flags)) ) {
+
+		cmd->cmd_flags |= CMD_FLAG_DATA_WORK_FREE;
+		spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+		/* Cmd have not reached firmware.
+		 * Use this trigger to free it. */
+		tcm_qla2xxx_free_cmd(cmd);
+		return;
+	}
+	spin_unlock_irqrestore(&cmd->cmd_lock, flags);
+	return;
+
 }
 
 static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *,
diff --git a/drivers/scsi/qla4xxx/ql4_83xx.c b/drivers/scsi/qla4xxx/ql4_83xx.c
index 5d4f8e67fb25..638f72c5ab05 100644
--- a/drivers/scsi/qla4xxx/ql4_83xx.c
+++ b/drivers/scsi/qla4xxx/ql4_83xx.c
@@ -46,11 +46,13 @@ int qla4_83xx_rd_reg_indirect(struct scsi_qla_host *ha, uint32_t addr,
 
 	ret_val = qla4_83xx_set_win_base(ha, addr);
 
-	if (ret_val == QLA_SUCCESS)
+	if (ret_val == QLA_SUCCESS) {
 		*data = qla4_83xx_rd_reg(ha, QLA83XX_WILDCARD);
-	else
+	} else {
+		*data = 0xffffffff;
 		ql4_printk(KERN_ERR, ha, "%s: failed read of addr 0x%x!\n",
 			   __func__, addr);
+	}
 
 	return ret_val;
 }
diff --git a/drivers/scsi/qlogicpti.c b/drivers/scsi/qlogicpti.c
index 676385ff28ef..69bfc0a1aea3 100644
--- a/drivers/scsi/qlogicpti.c
+++ b/drivers/scsi/qlogicpti.c
@@ -710,7 +710,7 @@ static int qpti_map_regs(struct qlogicpti *qpti)
 				 "PTI Qlogic/ISP");
 	if (!qpti->qregs) {
 		printk("PTI: Qlogic/ISP registers are unmappable\n");
-		return -1;
+		return -ENODEV;
 	}
 	if (qpti->is_pti) {
 		qpti->sreg = of_ioremap(&op->resource[0], (16 * 4096),
@@ -718,7 +718,7 @@ static int qpti_map_regs(struct qlogicpti *qpti)
 					"PTI Qlogic/ISP statreg");
 		if (!qpti->sreg) {
 			printk("PTI: Qlogic/ISP status register is unmappable\n");
-			return -1;
+			return -ENODEV;
 		}
 	}
 	return 0;
diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c
index 47b9d13f97b8..3408578b08d6 100644
--- a/drivers/scsi/scsi_devinfo.c
+++ b/drivers/scsi/scsi_devinfo.c
@@ -205,6 +205,8 @@ static struct {
 	{"Intel", "Multi-Flex", NULL, BLIST_NO_RSOC},
 	{"iRiver", "iFP Mass Driver", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36},
 	{"LASOUND", "CDX7405", "3.10", BLIST_MAX5LUN | BLIST_SINGLELUN},
+	{"Marvell", "Console", NULL, BLIST_SKIP_VPD_PAGES},
+	{"Marvell", "91xx Config", "1.01", BLIST_SKIP_VPD_PAGES},
 	{"MATSHITA", "PD-1", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
 	{"MATSHITA", "DMC-LC5", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36},
 	{"MATSHITA", "DMC-LC40", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36},
@@ -218,6 +220,8 @@ static struct {
 	{"NAKAMICH", "MJ-5.16S", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
 	{"NEC", "PD-1 ODX654P", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
 	{"NEC", "iStorage", NULL, BLIST_REPORTLUN2},
+	{"NETAPP", "LUN C-Mode", NULL, BLIST_SYNC_ALUA},
+	{"NETAPP", "INF-01-00", NULL, BLIST_SYNC_ALUA},
 	{"NRC", "MBR-7", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
 	{"NRC", "MBR-7.4", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
 	{"PIONEER", "CD-ROM DRM-600", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index fa6b2c4eb7a2..8106515d1df8 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1344,6 +1344,7 @@ scsi_prep_return(struct request_queue *q, struct request *req, int ret)
 
 	switch (ret) {
 	case BLKPREP_KILL:
+	case BLKPREP_INVALID:
 		req->errors = DID_NO_CONNECT << 16;
 		/* release the command and kill it */
 		if (req->special) {
@@ -2699,6 +2700,7 @@ static void scsi_evt_emit(struct scsi_device *sdev, struct scsi_event *evt)
 		envp[idx++] = "SDEV_MEDIA_CHANGE=1";
 		break;
 	case SDEV_EVT_INQUIRY_CHANGE_REPORTED:
+		scsi_rescan_device(&sdev->sdev_gendev);
 		envp[idx++] = "SDEV_UA=INQUIRY_DATA_HAS_CHANGED";
 		break;
 	case SDEV_EVT_CAPACITY_CHANGE_REPORTED:
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 6a820668d442..97074c91e328 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -43,6 +43,7 @@
 #include <scsi/scsi_devinfo.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_transport.h>
+#include <scsi/scsi_dh.h>
 #include <scsi/scsi_eh.h>
 
 #include "scsi_priv.h"
@@ -518,7 +519,8 @@ void scsi_target_reap(struct scsi_target *starget)
 }
 
 /**
- * sanitize_inquiry_string - remove non-graphical chars from an INQUIRY result string
+ * scsi_sanitize_inquiry_string - remove non-graphical chars from an
+ *                                INQUIRY result string
  * @s: INQUIRY result string to sanitize
  * @len: length of the string
  *
@@ -531,7 +533,7 @@ void scsi_target_reap(struct scsi_target *starget)
  *	string terminator, so all the following characters are set to
  *	spaces.
  **/
-static void sanitize_inquiry_string(unsigned char *s, int len)
+void scsi_sanitize_inquiry_string(unsigned char *s, int len)
 {
 	int terminated = 0;
 
@@ -542,6 +544,7 @@ static void sanitize_inquiry_string(unsigned char *s, int len)
 			*s = ' ';
 	}
 }
+EXPORT_SYMBOL(scsi_sanitize_inquiry_string);
 
 /**
  * scsi_probe_lun - probe a single LUN using a SCSI INQUIRY
@@ -627,9 +630,9 @@ static int scsi_probe_lun(struct scsi_device *sdev, unsigned char *inq_result,
 	}
 
 	if (result == 0) {
-		sanitize_inquiry_string(&inq_result[8], 8);
-		sanitize_inquiry_string(&inq_result[16], 16);
-		sanitize_inquiry_string(&inq_result[32], 4);
+		scsi_sanitize_inquiry_string(&inq_result[8], 8);
+		scsi_sanitize_inquiry_string(&inq_result[16], 16);
+		scsi_sanitize_inquiry_string(&inq_result[32], 4);
 
 		response_len = inq_result[4] + 5;
 		if (response_len > 255)
@@ -962,6 +965,9 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result,
 	if (*bflags & BLIST_NO_DIF)
 		sdev->no_dif = 1;
 
+	if (*bflags & BLIST_SYNC_ALUA)
+		sdev->synchronous_alua = 1;
+
 	sdev->eh_timeout = SCSI_DEFAULT_EH_TIMEOUT;
 
 	if (*bflags & BLIST_TRY_VPD_PAGES)
@@ -1519,9 +1525,14 @@ EXPORT_SYMBOL(scsi_add_device);
 
 void scsi_rescan_device(struct device *dev)
 {
+	struct scsi_device *sdev = to_scsi_device(dev);
+
 	device_lock(dev);
 
-	scsi_attach_vpd(to_scsi_device(dev));
+	scsi_attach_vpd(sdev);
+
+	if (sdev->handler && sdev->handler->rescan)
+		sdev->handler->rescan(sdev);
 
 	if (dev->driver && try_module_get(dev->driver->owner)) {
 		struct scsi_driver *drv = to_scsi_driver(dev->driver);
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 4f18a851e2c7..d16441961f3a 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -81,6 +81,33 @@ const char *scsi_host_state_name(enum scsi_host_state state)
 	return name;
 }
 
+static const struct {
+	unsigned char	value;
+	char		*name;
+} sdev_access_states[] = {
+	{ SCSI_ACCESS_STATE_OPTIMAL, "active/optimized" },
+	{ SCSI_ACCESS_STATE_ACTIVE, "active/non-optimized" },
+	{ SCSI_ACCESS_STATE_STANDBY, "standby" },
+	{ SCSI_ACCESS_STATE_UNAVAILABLE, "unavailable" },
+	{ SCSI_ACCESS_STATE_LBA, "lba-dependent" },
+	{ SCSI_ACCESS_STATE_OFFLINE, "offline" },
+	{ SCSI_ACCESS_STATE_TRANSITIONING, "transitioning" },
+};
+
+const char *scsi_access_state_name(unsigned char state)
+{
+	int i;
+	char *name = NULL;
+
+	for (i = 0; i < ARRAY_SIZE(sdev_access_states); i++) {
+		if (sdev_access_states[i].value == state) {
+			name = sdev_access_states[i].name;
+			break;
+		}
+	}
+	return name;
+}
+
 static int check_set(unsigned long long *val, char *src)
 {
 	char *last;
@@ -973,6 +1000,43 @@ sdev_store_dh_state(struct device *dev, struct device_attribute *attr,
 
 static DEVICE_ATTR(dh_state, S_IRUGO | S_IWUSR, sdev_show_dh_state,
 		   sdev_store_dh_state);
+
+static ssize_t
+sdev_show_access_state(struct device *dev,
+		       struct device_attribute *attr,
+		       char *buf)
+{
+	struct scsi_device *sdev = to_scsi_device(dev);
+	unsigned char access_state;
+	const char *access_state_name;
+
+	if (!sdev->handler)
+		return -EINVAL;
+
+	access_state = (sdev->access_state & SCSI_ACCESS_STATE_MASK);
+	access_state_name = scsi_access_state_name(access_state);
+
+	return sprintf(buf, "%s\n",
+		       access_state_name ? access_state_name : "unknown");
+}
+static DEVICE_ATTR(access_state, S_IRUGO, sdev_show_access_state, NULL);
+
+static ssize_t
+sdev_show_preferred_path(struct device *dev,
+			 struct device_attribute *attr,
+			 char *buf)
+{
+	struct scsi_device *sdev = to_scsi_device(dev);
+
+	if (!sdev->handler)
+		return -EINVAL;
+
+	if (sdev->access_state & SCSI_ACCESS_STATE_PREFERRED)
+		return sprintf(buf, "1\n");
+	else
+		return sprintf(buf, "0\n");
+}
+static DEVICE_ATTR(preferred_path, S_IRUGO, sdev_show_preferred_path, NULL);
 #endif
 
 static ssize_t
@@ -1020,9 +1084,33 @@ static umode_t scsi_sdev_attr_is_visible(struct kobject *kobj,
 	    !sdev->host->hostt->change_queue_depth)
 		return 0;
 
+#ifdef CONFIG_SCSI_DH
+	if (attr == &dev_attr_access_state.attr &&
+	    !sdev->handler)
+		return 0;
+	if (attr == &dev_attr_preferred_path.attr &&
+	    !sdev->handler)
+		return 0;
+#endif
 	return attr->mode;
 }
 
+static umode_t scsi_sdev_bin_attr_is_visible(struct kobject *kobj,
+					     struct bin_attribute *attr, int i)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct scsi_device *sdev = to_scsi_device(dev);
+
+
+	if (attr == &dev_attr_vpd_pg80 && !sdev->vpd_pg80)
+		return 0;
+
+	if (attr == &dev_attr_vpd_pg83 && sdev->vpd_pg83)
+		return 0;
+
+	return S_IRUGO;
+}
+
 /* Default template for device attributes.  May NOT be modified */
 static struct attribute *scsi_sdev_attrs[] = {
 	&dev_attr_device_blocked.attr,
@@ -1047,6 +1135,8 @@ static struct attribute *scsi_sdev_attrs[] = {
 	&dev_attr_wwid.attr,
 #ifdef CONFIG_SCSI_DH
 	&dev_attr_dh_state.attr,
+	&dev_attr_access_state.attr,
+	&dev_attr_preferred_path.attr,
 #endif
 	&dev_attr_queue_ramp_up_period.attr,
 	REF_EVT(media_change),
@@ -1068,6 +1158,7 @@ static struct attribute_group scsi_sdev_attr_group = {
 	.attrs =	scsi_sdev_attrs,
 	.bin_attrs =	scsi_sdev_bin_attrs,
 	.is_visible =	scsi_sdev_attr_is_visible,
+	.is_bin_visible = scsi_sdev_bin_attr_is_visible,
 };
 
 static const struct attribute_group *scsi_sdev_attr_groups[] = {
@@ -1129,13 +1220,6 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev)
 
 	scsi_autopm_get_device(sdev);
 
-	error = device_add(&sdev->sdev_gendev);
-	if (error) {
-		sdev_printk(KERN_INFO, sdev,
-				"failed to add device: %d\n", error);
-		return error;
-	}
-
 	error = scsi_dh_add_device(sdev);
 	if (error)
 		/*
@@ -1144,6 +1228,14 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev)
 		sdev_printk(KERN_INFO, sdev,
 				"failed to add device handler: %d\n", error);
 
+	error = device_add(&sdev->sdev_gendev);
+	if (error) {
+		sdev_printk(KERN_INFO, sdev,
+				"failed to add device: %d\n", error);
+		scsi_dh_remove_device(sdev);
+		return error;
+	}
+
 	device_enable_async_suspend(&sdev->sdev_dev);
 	error = device_add(&sdev->sdev_dev);
 	if (error) {
@@ -1272,16 +1364,18 @@ static void __scsi_remove_target(struct scsi_target *starget)
 void scsi_remove_target(struct device *dev)
 {
 	struct Scsi_Host *shost = dev_to_shost(dev->parent);
-	struct scsi_target *starget;
+	struct scsi_target *starget, *last_target = NULL;
 	unsigned long flags;
 
 restart:
 	spin_lock_irqsave(shost->host_lock, flags);
 	list_for_each_entry(starget, &shost->__targets, siblings) {
-		if (starget->state == STARGET_DEL)
+		if (starget->state == STARGET_DEL ||
+		    starget == last_target)
 			continue;
 		if (starget->dev.parent == dev || &starget->dev == dev) {
 			kref_get(&starget->reap_ref);
+			last_target = starget;
 			spin_unlock_irqrestore(shost->host_lock, flags);
 			__scsi_remove_target(starget);
 			scsi_target_reap(starget);
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index e4b3d8f4fd85..441481623fb9 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -4308,6 +4308,8 @@ static const struct {
 	{ISCSI_PORT_SPEED_100MBPS,	"100 Mbps" },
 	{ISCSI_PORT_SPEED_1GBPS,	"1 Gbps" },
 	{ISCSI_PORT_SPEED_10GBPS,	"10 Gbps" },
+	{ISCSI_PORT_SPEED_25GBPS,       "25 Gbps" },
+	{ISCSI_PORT_SPEED_40GBPS,       "40 Gbps" },
 };
 
 char *iscsi_get_port_speed_name(struct Scsi_Host *shost)
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index bb669d32ccd0..5a5457ac9cdb 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -648,7 +648,7 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 	 */
 	if (sdkp->lbprz) {
 		q->limits.discard_alignment = 0;
-		q->limits.discard_granularity = 1;
+		q->limits.discard_granularity = logical_block_size;
 	} else {
 		q->limits.discard_alignment = sdkp->unmap_alignment *
 			logical_block_size;
@@ -761,7 +761,7 @@ static int sd_setup_discard_cmnd(struct scsi_cmnd *cmd)
 		break;
 
 	default:
-		ret = BLKPREP_KILL;
+		ret = BLKPREP_INVALID;
 		goto out;
 	}
 
@@ -839,7 +839,7 @@ static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd)
 	int ret;
 
 	if (sdkp->device->no_write_same)
-		return BLKPREP_KILL;
+		return BLKPREP_INVALID;
 
 	BUG_ON(bio_offset(bio) || bio_iovec(bio).bv_len != sdp->sector_size);
 
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 5e820674432c..ae7d9bdf409c 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -652,7 +652,8 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 	else
 		hp->dxfer_direction = (mxsize > 0) ? SG_DXFER_FROM_DEV : SG_DXFER_NONE;
 	hp->dxfer_len = mxsize;
-	if (hp->dxfer_direction == SG_DXFER_TO_DEV)
+	if ((hp->dxfer_direction == SG_DXFER_TO_DEV) ||
+	    (hp->dxfer_direction == SG_DXFER_TO_FROM_DEV))
 		hp->dxferp = (char __user *)buf + cmd_size;
 	else
 		hp->dxferp = NULL;
diff --git a/drivers/scsi/sim710.c b/drivers/scsi/sim710.c
index 3b3b56f4a830..82ed99848378 100644
--- a/drivers/scsi/sim710.c
+++ b/drivers/scsi/sim710.c
@@ -176,8 +176,7 @@ static struct eisa_device_id sim710_eisa_ids[] = {
 };
 MODULE_DEVICE_TABLE(eisa, sim710_eisa_ids);
 
-static __init int
-sim710_eisa_probe(struct device *dev)
+static int sim710_eisa_probe(struct device *dev)
 {
 	struct eisa_device *edev = to_eisa_device(dev);
 	unsigned long io_addr = edev->base_addr;
diff --git a/drivers/scsi/snic/snic_ctl.c b/drivers/scsi/snic/snic_ctl.c
index aebe75320ed3..ab0e06b0b4ff 100644
--- a/drivers/scsi/snic/snic_ctl.c
+++ b/drivers/scsi/snic/snic_ctl.c
@@ -75,7 +75,7 @@ snic_ver_enc(const char *s)
 			continue;
 		}
 
-		if (i > 4 || !isdigit(c))
+		if (i > 3 || !isdigit(c))
 			goto end;
 
 		v[i] = v[i] * 10 + (c - '0');
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 2e522951b619..607b0a505844 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -9,7 +9,7 @@
    Steve Hirsch, Andreas Koppenh"ofer, Michael Leodolter, Eyal Lebedinsky,
    Michael Schaefer, J"org Weule, and Eric Youngdale.
 
-   Copyright 1992 - 2010 Kai Makisara
+   Copyright 1992 - 2016 Kai Makisara
    email Kai.Makisara@kolumbus.fi
 
    Some small formal changes - aeb, 950809
@@ -17,7 +17,7 @@
    Last modified: 18-JAN-1998 Richard Gooch <rgooch@atnf.csiro.au> Devfs support
  */
 
-static const char *verstr = "20101219";
+static const char *verstr = "20160209";
 
 #include <linux/module.h>
 
@@ -3296,7 +3296,10 @@ static int switch_partition(struct scsi_tape *STp)
 #define PP_OFF_RESERVED        7
 
 #define PP_BIT_IDP             0x20
+#define PP_BIT_FDP             0x80
 #define PP_MSK_PSUM_MB         0x10
+#define PP_MSK_PSUM_UNITS      0x18
+#define PP_MSK_POFM            0x04
 
 /* Get the number of partitions on the tape. As a side effect reads the
    mode page into the tape buffer. */
@@ -3322,6 +3325,29 @@ static int nbr_partitions(struct scsi_tape *STp)
 }
 
 
+static int format_medium(struct scsi_tape *STp, int format)
+{
+	int result = 0;
+	int timeout = STp->long_timeout;
+	unsigned char scmd[MAX_COMMAND_SIZE];
+	struct st_request *SRpnt;
+
+	memset(scmd, 0, MAX_COMMAND_SIZE);
+	scmd[0] = FORMAT_UNIT;
+	scmd[2] = format;
+	if (STp->immediate) {
+		scmd[1] |= 1;		/* Don't wait for completion */
+		timeout = STp->device->request_queue->rq_timeout;
+	}
+	DEBC_printk(STp, "Sending FORMAT MEDIUM\n");
+	SRpnt = st_do_scsi(NULL, STp, scmd, 0, DMA_NONE,
+			   timeout, MAX_RETRIES, 1);
+	if (!SRpnt)
+		result = STp->buffer->syscall_result;
+	return result;
+}
+
+
 /* Partition the tape into two partitions if size > 0 or one partition if
    size == 0.
 
@@ -3340,11 +3366,16 @@ static int nbr_partitions(struct scsi_tape *STp)
    and 10 when 1 partition is defined (information from Eric Lee Green). This is
    is acceptable also to some other old drives and enforced if the first partition
    size field is used for the first additional partition size.
+
+   For drives that advertize SCSI-3 or newer, use the SSC-3 methods.
  */
 static int partition_tape(struct scsi_tape *STp, int size)
 {
 	int result;
+	int target_partition;
+	bool scsi3 = STp->device->scsi_level >= SCSI_3, needs_format = false;
 	int pgo, psd_cnt, psdo;
+	int psum = PP_MSK_PSUM_MB, units = 0;
 	unsigned char *bp;
 
 	result = read_mode_page(STp, PART_PAGE, 0);
@@ -3352,6 +3383,12 @@ static int partition_tape(struct scsi_tape *STp, int size)
 		DEBC_printk(STp, "Can't read partition mode page.\n");
 		return result;
 	}
+	target_partition = 1;
+	if (size < 0) {
+		target_partition = 0;
+		size = -size;
+	}
+
 	/* The mode page is in the buffer. Let's modify it and write it. */
 	bp = (STp->buffer)->b_data;
 	pgo = MODE_HEADER_LENGTH + bp[MH_OFF_BDESCS_LENGTH];
@@ -3359,9 +3396,52 @@ static int partition_tape(struct scsi_tape *STp, int size)
 		    bp[pgo + MP_OFF_PAGE_LENGTH] + 2);
 
 	psd_cnt = (bp[pgo + MP_OFF_PAGE_LENGTH] + 2 - PART_PAGE_FIXED_LENGTH) / 2;
+
+	if (scsi3) {
+		needs_format = (bp[pgo + PP_OFF_FLAGS] & PP_MSK_POFM) != 0;
+		if (needs_format && size == 0) {
+			/* No need to write the mode page when clearing
+			 *  partitioning
+			 */
+			DEBC_printk(STp, "Formatting tape with one partition.\n");
+			result = format_medium(STp, 0);
+			goto out;
+		}
+		if (needs_format)  /* Leave the old value for HP DATs claiming SCSI_3 */
+			psd_cnt = 2;
+		if ((bp[pgo + PP_OFF_FLAGS] & PP_MSK_PSUM_UNITS) == PP_MSK_PSUM_UNITS) {
+			/* Use units scaling for large partitions if the device
+			 * suggests it and no precision lost. Required for IBM
+			 * TS1140/50 drives that don't support MB units.
+			 */
+			if (size >= 1000 && (size % 1000) == 0) {
+				size /= 1000;
+				psum = PP_MSK_PSUM_UNITS;
+				units = 9; /* GB */
+			}
+		}
+		/* Try it anyway if too large to specify in MB */
+		if (psum == PP_MSK_PSUM_MB && size >= 65534) {
+			size /= 1000;
+			psum = PP_MSK_PSUM_UNITS;
+			units = 9;  /* GB */
+		}
+	}
+
+	if (size >= 65535 ||  /* Does not fit into two bytes */
+	    (target_partition == 0 && psd_cnt < 2)) {
+		result = -EINVAL;
+		goto out;
+	}
+
 	psdo = pgo + PART_PAGE_FIXED_LENGTH;
-	if (psd_cnt > bp[pgo + PP_OFF_MAX_ADD_PARTS]) {
-		bp[psdo] = bp[psdo + 1] = 0xff;  /* Rest of the tape */
+	/* The second condition is for HP DDS which use only one partition size
+	 * descriptor
+	 */
+	if (target_partition > 0 &&
+	    (psd_cnt > bp[pgo + PP_OFF_MAX_ADD_PARTS] ||
+	     bp[pgo + PP_OFF_MAX_ADD_PARTS] != 1)) {
+		bp[psdo] = bp[psdo + 1] = 0xff;  /* Rest to partition 0 */
 		psdo += 2;
 	}
 	memset(bp + psdo, 0, bp[pgo + PP_OFF_NBR_ADD_PARTS] * 2);
@@ -3370,7 +3450,7 @@ static int partition_tape(struct scsi_tape *STp, int size)
 		    psd_cnt, bp[pgo + PP_OFF_MAX_ADD_PARTS],
 		    bp[pgo + PP_OFF_NBR_ADD_PARTS]);
 
-	if (size <= 0) {
+	if (size == 0) {
 		bp[pgo + PP_OFF_NBR_ADD_PARTS] = 0;
 		if (psd_cnt <= bp[pgo + PP_OFF_MAX_ADD_PARTS])
 		    bp[pgo + MP_OFF_PAGE_LENGTH] = 6;
@@ -3378,22 +3458,37 @@ static int partition_tape(struct scsi_tape *STp, int size)
 	} else {
 		bp[psdo] = (size >> 8) & 0xff;
 		bp[psdo + 1] = size & 0xff;
+		if (target_partition == 0)
+			bp[psdo + 2] = bp[psdo + 3] = 0xff;
 		bp[pgo + 3] = 1;
 		if (bp[pgo + MP_OFF_PAGE_LENGTH] < 8)
 		    bp[pgo + MP_OFF_PAGE_LENGTH] = 8;
-		DEBC_printk(STp, "Formatting tape with two partitions "
-			    "(1 = %d MB).\n", size);
+		DEBC_printk(STp,
+			    "Formatting tape with two partitions (%i = %d MB).\n",
+			    target_partition, units > 0 ? size * 1000 : size);
 	}
 	bp[pgo + PP_OFF_PART_UNITS] = 0;
 	bp[pgo + PP_OFF_RESERVED] = 0;
-	bp[pgo + PP_OFF_FLAGS] = PP_BIT_IDP | PP_MSK_PSUM_MB;
+	if (size != 1 || units != 0) {
+		bp[pgo + PP_OFF_FLAGS] = PP_BIT_IDP | psum |
+			(bp[pgo + PP_OFF_FLAGS] & 0x07);
+		bp[pgo + PP_OFF_PART_UNITS] = units;
+	} else
+		bp[pgo + PP_OFF_FLAGS] = PP_BIT_FDP |
+			(bp[pgo + PP_OFF_FLAGS] & 0x1f);
+	bp[pgo + MP_OFF_PAGE_LENGTH] = 6 + psd_cnt * 2;
 
 	result = write_mode_page(STp, PART_PAGE, 1);
+
+	if (!result && needs_format)
+		result = format_medium(STp, 1);
+
 	if (result) {
 		st_printk(KERN_INFO, STp, "Partitioning of tape failed.\n");
 		result = (-EIO);
 	}
 
+out:
 	return result;
 }
 
@@ -3570,8 +3665,13 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg)
 				retval = (-EINVAL);
 				goto out;
 			}
-			if ((i = st_int_ioctl(STp, MTREW, 0)) < 0 ||
-			    (i = partition_tape(STp, mtc.mt_count)) < 0) {
+			i = do_load_unload(STp, file, 1);
+			if (i < 0) {
+				retval = i;
+				goto out;
+			}
+			i = partition_tape(STp, mtc.mt_count);
+			if (i < 0) {
 				retval = i;
 				goto out;
 			}
@@ -3581,7 +3681,7 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg)
 				STp->ps[i].last_block_valid = 0;
 			}
 			STp->partition = STp->new_partition = 0;
-			STp->nbr_partitions = 1;	/* Bad guess ?-) */
+			STp->nbr_partitions = mtc.mt_count != 0 ? 2 : 1;
 			STps->drv_block = STps->drv_file = 0;
 			retval = 0;
 			goto out;
diff --git a/drivers/scsi/stex.c b/drivers/scsi/stex.c
index 2de28d7a0b04..5b23175a584c 100644
--- a/drivers/scsi/stex.c
+++ b/drivers/scsi/stex.c
@@ -1,7 +1,7 @@
 /*
  * SuperTrak EX Series Storage Controller driver for Linux
  *
- *	Copyright (C) 2005-2009 Promise Technology Inc.
+ *	Copyright (C) 2005-2015 Promise Technology Inc.
  *
  *	This program is free software; you can redistribute it and/or
  *	modify it under the terms of the GNU General Public License
@@ -38,11 +38,11 @@
 #include <scsi/scsi_eh.h>
 
 #define DRV_NAME "stex"
-#define ST_DRIVER_VERSION "4.6.0000.4"
-#define ST_VER_MAJOR		4
-#define ST_VER_MINOR		6
-#define ST_OEM			0
-#define ST_BUILD_VER		4
+#define ST_DRIVER_VERSION	"5.00.0000.01"
+#define ST_VER_MAJOR		5
+#define ST_VER_MINOR		00
+#define ST_OEM				0000
+#define ST_BUILD_VER		01
 
 enum {
 	/* MU register offset */
@@ -84,6 +84,8 @@ enum {
 	MU_STATE_STARTED			= 2,
 	MU_STATE_RESETTING			= 3,
 	MU_STATE_FAILED				= 4,
+	MU_STATE_STOP				= 5,
+	MU_STATE_NOCONNECT			= 6,
 
 	MU_MAX_DELAY				= 120,
 	MU_HANDSHAKE_SIGNATURE			= 0x55aaaa55,
@@ -165,6 +167,14 @@ enum {
 
 	ST_ADDITIONAL_MEM			= 0x200000,
 	ST_ADDITIONAL_MEM_MIN			= 0x80000,
+	PMIC_SHUTDOWN				= 0x0D,
+	PMIC_REUMSE					= 0x10,
+	ST_IGNORED					= -1,
+	ST_NOTHANDLED				= 7,
+	ST_S3						= 3,
+	ST_S4						= 4,
+	ST_S5						= 5,
+	ST_S6						= 6,
 };
 
 struct st_sgitem {
@@ -328,6 +338,7 @@ struct st_hba {
 	u16 rq_count;
 	u16 rq_size;
 	u16 sts_count;
+	u8  supports_pm;
 };
 
 struct st_card_info {
@@ -536,6 +547,27 @@ stex_ss_send_cmd(struct st_hba *hba, struct req_msg *req, u16 tag)
 	readl(hba->mmio_base + YH2I_REQ); /* flush */
 }
 
+static void return_abnormal_state(struct st_hba *hba, int status)
+{
+	struct st_ccb *ccb;
+	unsigned long flags;
+	u16 tag;
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	for (tag = 0; tag < hba->host->can_queue; tag++) {
+		ccb = &hba->ccb[tag];
+		if (ccb->req == NULL)
+			continue;
+		ccb->req = NULL;
+		if (ccb->cmd) {
+			scsi_dma_unmap(ccb->cmd);
+			ccb->cmd->result = status << 16;
+			ccb->cmd->scsi_done(ccb->cmd);
+			ccb->cmd = NULL;
+		}
+	}
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+}
 static int
 stex_slave_config(struct scsi_device *sdev)
 {
@@ -559,8 +591,12 @@ stex_queuecommand_lck(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *))
 	id = cmd->device->id;
 	lun = cmd->device->lun;
 	hba = (struct st_hba *) &host->hostdata[0];
-
-	if (unlikely(hba->mu_status == MU_STATE_RESETTING))
+	if (hba->mu_status == MU_STATE_NOCONNECT) {
+		cmd->result = DID_NO_CONNECT;
+		done(cmd);
+		return 0;
+	}
+	if (unlikely(hba->mu_status != MU_STATE_STARTED))
 		return SCSI_MLQUEUE_HOST_BUSY;
 
 	switch (cmd->cmnd[0]) {
@@ -1259,10 +1295,8 @@ static void stex_ss_reset(struct st_hba *hba)
 
 static int stex_do_reset(struct st_hba *hba)
 {
-	struct st_ccb *ccb;
 	unsigned long flags;
 	unsigned int mu_status = MU_STATE_RESETTING;
-	u16 tag;
 
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	if (hba->mu_status == MU_STATE_STARTING) {
@@ -1296,20 +1330,8 @@ static int stex_do_reset(struct st_hba *hba)
 	else if (hba->cardtype == st_yel)
 		stex_ss_reset(hba);
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
-	for (tag = 0; tag < hba->host->can_queue; tag++) {
-		ccb = &hba->ccb[tag];
-		if (ccb->req == NULL)
-			continue;
-		ccb->req = NULL;
-		if (ccb->cmd) {
-			scsi_dma_unmap(ccb->cmd);
-			ccb->cmd->result = DID_RESET << 16;
-			ccb->cmd->scsi_done(ccb->cmd);
-			ccb->cmd = NULL;
-		}
-	}
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
+	return_abnormal_state(hba, DID_RESET);
 
 	if (stex_handshake(hba) == 0)
 		return 0;
@@ -1560,6 +1582,25 @@ static int stex_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	hba->cardtype = (unsigned int) id->driver_data;
 	ci = &stex_card_info[hba->cardtype];
+	switch (id->subdevice) {
+	case 0x4221:
+	case 0x4222:
+	case 0x4223:
+	case 0x4224:
+	case 0x4225:
+	case 0x4226:
+	case 0x4227:
+	case 0x4261:
+	case 0x4262:
+	case 0x4263:
+	case 0x4264:
+	case 0x4265:
+		break;
+	default:
+		if (hba->cardtype == st_yel)
+			hba->supports_pm = 1;
+	}
+
 	sts_offset = scratch_offset = (ci->rq_count+1) * ci->rq_size;
 	if (hba->cardtype == st_yel)
 		sts_offset += (ci->sts_count+1) * sizeof(u32);
@@ -1685,7 +1726,7 @@ out_disable:
 	return err;
 }
 
-static void stex_hba_stop(struct st_hba *hba)
+static void stex_hba_stop(struct st_hba *hba, int st_sleep_mic)
 {
 	struct req_msg *req;
 	struct st_msg_header *msg_h;
@@ -1694,6 +1735,15 @@ static void stex_hba_stop(struct st_hba *hba)
 	u16 tag = 0;
 
 	spin_lock_irqsave(hba->host->host_lock, flags);
+
+	if (hba->cardtype == st_yel && hba->supports_pm == 1)
+	{
+		if(st_sleep_mic == ST_NOTHANDLED)
+		{
+			spin_unlock_irqrestore(hba->host->host_lock, flags);
+			return;
+		}
+	}
 	req = hba->alloc_rq(hba);
 	if (hba->cardtype == st_yel) {
 		msg_h = (struct st_msg_header *)req - 1;
@@ -1701,11 +1751,18 @@ static void stex_hba_stop(struct st_hba *hba)
 	} else
 		memset(req, 0, hba->rq_size);
 
-	if (hba->cardtype == st_yosemite || hba->cardtype == st_yel) {
+	if ((hba->cardtype == st_yosemite || hba->cardtype == st_yel)
+		&& st_sleep_mic == ST_IGNORED) {
 		req->cdb[0] = MGT_CMD;
 		req->cdb[1] = MGT_CMD_SIGNATURE;
 		req->cdb[2] = CTLR_CONFIG_CMD;
 		req->cdb[3] = CTLR_SHUTDOWN;
+	} else if (hba->cardtype == st_yel && st_sleep_mic != ST_IGNORED) {
+		req->cdb[0] = MGT_CMD;
+		req->cdb[1] = MGT_CMD_SIGNATURE;
+		req->cdb[2] = CTLR_CONFIG_CMD;
+		req->cdb[3] = PMIC_SHUTDOWN;
+		req->cdb[4] = st_sleep_mic;
 	} else {
 		req->cdb[0] = CONTROLLER_CMD;
 		req->cdb[1] = CTLR_POWER_STATE_CHANGE;
@@ -1725,10 +1782,12 @@ static void stex_hba_stop(struct st_hba *hba)
 	while (hba->ccb[tag].req_type & PASSTHRU_REQ_TYPE) {
 		if (time_after(jiffies, before + ST_INTERNAL_TIMEOUT * HZ)) {
 			hba->ccb[tag].req_type = 0;
+			hba->mu_status = MU_STATE_STOP;
 			return;
 		}
 		msleep(1);
 	}
+	hba->mu_status = MU_STATE_STOP;
 }
 
 static void stex_hba_free(struct st_hba *hba)
@@ -1751,9 +1810,11 @@ static void stex_remove(struct pci_dev *pdev)
 {
 	struct st_hba *hba = pci_get_drvdata(pdev);
 
+	hba->mu_status = MU_STATE_NOCONNECT;
+	return_abnormal_state(hba, DID_NO_CONNECT);
 	scsi_remove_host(hba->host);
 
-	stex_hba_stop(hba);
+	scsi_block_requests(hba->host);
 
 	stex_hba_free(hba);
 
@@ -1766,9 +1827,43 @@ static void stex_shutdown(struct pci_dev *pdev)
 {
 	struct st_hba *hba = pci_get_drvdata(pdev);
 
-	stex_hba_stop(hba);
+	if (hba->supports_pm == 0)
+		stex_hba_stop(hba, ST_IGNORED);
+	else
+		stex_hba_stop(hba, ST_S5);
+}
+
+static int stex_choice_sleep_mic(pm_message_t state)
+{
+	switch (state.event) {
+	case PM_EVENT_SUSPEND:
+		return ST_S3;
+	case PM_EVENT_HIBERNATE:
+		return ST_S4;
+	default:
+		return ST_NOTHANDLED;
+	}
+}
+
+static int stex_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	struct st_hba *hba = pci_get_drvdata(pdev);
+
+	if (hba->cardtype == st_yel && hba->supports_pm == 1)
+		stex_hba_stop(hba, stex_choice_sleep_mic(state));
+	else
+		stex_hba_stop(hba, ST_IGNORED);
+	return 0;
 }
 
+static int stex_resume(struct pci_dev *pdev)
+{
+	struct st_hba *hba = pci_get_drvdata(pdev);
+
+	hba->mu_status = MU_STATE_STARTING;
+	stex_handshake(hba);
+	return 0;
+}
 MODULE_DEVICE_TABLE(pci, stex_pci_tbl);
 
 static struct pci_driver stex_pci_driver = {
@@ -1777,6 +1872,8 @@ static struct pci_driver stex_pci_driver = {
 	.probe		= stex_probe,
 	.remove		= stex_remove,
 	.shutdown	= stex_shutdown,
+	.suspend	= stex_suspend,
+	.resume		= stex_resume,
 };
 
 static int __init stex_init(void)
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 55627d097873..3ddcabb790a8 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -42,6 +42,7 @@
 #include <scsi/scsi_devinfo.h>
 #include <scsi/scsi_dbg.h>
 #include <scsi/scsi_transport_fc.h>
+#include <scsi/scsi_transport.h>
 
 /*
  * All wire protocol details (storage protocol between the guest and the host)
@@ -477,19 +478,18 @@ struct hv_host_device {
 struct storvsc_scan_work {
 	struct work_struct work;
 	struct Scsi_Host *host;
-	uint lun;
+	u8 lun;
+	u8 tgt_id;
 };
 
 static void storvsc_device_scan(struct work_struct *work)
 {
 	struct storvsc_scan_work *wrk;
-	uint lun;
 	struct scsi_device *sdev;
 
 	wrk = container_of(work, struct storvsc_scan_work, work);
-	lun = wrk->lun;
 
-	sdev = scsi_device_lookup(wrk->host, 0, 0, lun);
+	sdev = scsi_device_lookup(wrk->host, 0, wrk->tgt_id, wrk->lun);
 	if (!sdev)
 		goto done;
 	scsi_rescan_device(&sdev->sdev_gendev);
@@ -540,7 +540,7 @@ static void storvsc_remove_lun(struct work_struct *work)
 	if (!scsi_host_get(wrk->host))
 		goto done;
 
-	sdev = scsi_device_lookup(wrk->host, 0, 0, wrk->lun);
+	sdev = scsi_device_lookup(wrk->host, 0, wrk->tgt_id, wrk->lun);
 
 	if (sdev) {
 		scsi_remove_device(sdev);
@@ -914,8 +914,9 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb,
 		do_work = true;
 		process_err_fn = storvsc_remove_lun;
 		break;
-	case (SRB_STATUS_ABORTED | SRB_STATUS_AUTOSENSE_VALID):
-		if ((asc == 0x2a) && (ascq == 0x9)) {
+	case SRB_STATUS_ABORTED:
+		if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID &&
+		    (asc == 0x2a) && (ascq == 0x9)) {
 			do_work = true;
 			process_err_fn = storvsc_device_scan;
 			/*
@@ -940,6 +941,7 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb,
 
 	wrk->host = host;
 	wrk->lun = vm_srb->lun;
+	wrk->tgt_id = vm_srb->target_id;
 	INIT_WORK(&wrk->work, process_err_fn);
 	schedule_work(&wrk->work);
 }
@@ -1770,6 +1772,11 @@ static int __init storvsc_drv_init(void)
 	fc_transport_template = fc_attach_transport(&fc_transport_functions);
 	if (!fc_transport_template)
 		return -ENODEV;
+
+	/*
+	 * Install Hyper-V specific timeout handler.
+	 */
+	fc_transport_template->eh_timed_out = storvsc_eh_timed_out;
 #endif
 
 	ret = vmbus_driver_register(&storvsc_drv);
diff --git a/drivers/scsi/ufs/ufs.h b/drivers/scsi/ufs/ufs.h
index 42c459a9d3fe..54a16cef0367 100644
--- a/drivers/scsi/ufs/ufs.h
+++ b/drivers/scsi/ufs/ufs.h
@@ -170,7 +170,7 @@ enum ufs_desc_max_size {
 	 * of descriptor header.
 	 */
 	QUERY_DESC_STRING_MAX_SIZE		= 0xFE,
-	QUERY_DESC_GEOMETRY_MAZ_SIZE		= 0x44,
+	QUERY_DESC_GEOMETRY_MAX_SIZE		= 0x44,
 	QUERY_DESC_POWER_MAX_SIZE		= 0x62,
 	QUERY_DESC_RFU_MAX_SIZE			= 0x00,
 };
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 85cd2564c157..9c1b94bef8f3 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -3,7 +3,7 @@
  *
  * This code is based on drivers/scsi/ufs/ufshcd.c
  * Copyright (C) 2011-2013 Samsung India Software Operations
- * Copyright (c) 2013-2014, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2013-2016, The Linux Foundation. All rights reserved.
  *
  * Authors:
  *	Santosh Yaraganavi <santosh.sy@samsung.com>
@@ -58,13 +58,25 @@
 #define QUERY_REQ_RETRIES 10
 /* Query request timeout */
 #define QUERY_REQ_TIMEOUT 30 /* msec */
+/*
+ * Query request timeout for fDeviceInit flag
+ * fDeviceInit query response time for some devices is too large that default
+ * QUERY_REQ_TIMEOUT may not be enough for such devices.
+ */
+#define QUERY_FDEVICEINIT_REQ_TIMEOUT 600 /* msec */
 
 /* Task management command timeout */
 #define TM_CMD_TIMEOUT	100 /* msecs */
 
+/* maximum number of retries for a general UIC command  */
+#define UFS_UIC_COMMAND_RETRIES 3
+
 /* maximum number of link-startup retries */
 #define DME_LINKSTARTUP_RETRIES 3
 
+/* Maximum retries for Hibern8 enter */
+#define UIC_HIBERN8_ENTER_RETRIES 3
+
 /* maximum number of reset retries before giving up */
 #define MAX_HOST_RESET_RETRIES 5
 
@@ -92,7 +104,7 @@ static u32 ufs_query_desc_max_size[] = {
 	QUERY_DESC_INTERCONNECT_MAX_SIZE,
 	QUERY_DESC_STRING_MAX_SIZE,
 	QUERY_DESC_RFU_MAX_SIZE,
-	QUERY_DESC_GEOMETRY_MAZ_SIZE,
+	QUERY_DESC_GEOMETRY_MAX_SIZE,
 	QUERY_DESC_POWER_MAX_SIZE,
 	QUERY_DESC_RFU_MAX_SIZE,
 };
@@ -190,6 +202,10 @@ static int ufshcd_config_pwr_mode(struct ufs_hba *hba,
 		struct ufs_pa_layer_attr *desired_pwr_mode);
 static int ufshcd_change_power_mode(struct ufs_hba *hba,
 			     struct ufs_pa_layer_attr *pwr_mode);
+static inline bool ufshcd_valid_tag(struct ufs_hba *hba, int tag)
+{
+	return tag >= 0 && tag < hba->nutrs;
+}
 
 static inline int ufshcd_enable_irq(struct ufs_hba *hba)
 {
@@ -360,6 +376,16 @@ static inline void ufshcd_utrl_clear(struct ufs_hba *hba, u32 pos)
 }
 
 /**
+ * ufshcd_outstanding_req_clear - Clear a bit in outstanding request field
+ * @hba: per adapter instance
+ * @tag: position of the bit to be cleared
+ */
+static inline void ufshcd_outstanding_req_clear(struct ufs_hba *hba, int tag)
+{
+	__clear_bit(tag, &hba->outstanding_reqs);
+}
+
+/**
  * ufshcd_get_lists_status - Check UCRDY, UTRLRDY and UTMRLRDY
  * @reg: Register value of host controller status
  *
@@ -374,11 +400,9 @@ static inline int ufshcd_get_lists_status(u32 reg)
 	 *  1		UTRLRDY
 	 *  2		UTMRLRDY
 	 *  3		UCRDY
-	 *  4		HEI
-	 *  5		DEI
-	 * 6-7		reserved
+	 * 4-7		reserved
 	 */
-	return (((reg) & (0xFF)) >> 1) ^ (0x07);
+	return ((reg & 0xFF) >> 1) ^ 0x07;
 }
 
 /**
@@ -582,6 +606,11 @@ int ufshcd_hold(struct ufs_hba *hba, bool async)
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	hba->clk_gating.active_reqs++;
 
+	if (ufshcd_eh_in_progress(hba)) {
+		spin_unlock_irqrestore(hba->host->host_lock, flags);
+		return 0;
+	}
+
 start:
 	switch (hba->clk_gating.state) {
 	case CLKS_ON:
@@ -697,7 +726,8 @@ static void __ufshcd_release(struct ufs_hba *hba)
 	if (hba->clk_gating.active_reqs || hba->clk_gating.is_suspended
 		|| hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL
 		|| hba->lrb_in_use || hba->outstanding_tasks
-		|| hba->active_uic_cmd || hba->uic_async_done)
+		|| hba->active_uic_cmd || hba->uic_async_done
+		|| ufshcd_eh_in_progress(hba))
 		return;
 
 	hba->clk_gating.state = REQ_CLKS_OFF;
@@ -953,13 +983,15 @@ ufshcd_wait_for_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
  * __ufshcd_send_uic_cmd - Send UIC commands and retrieve the result
  * @hba: per adapter instance
  * @uic_cmd: UIC command
+ * @completion: initialize the completion only if this is set to true
  *
  * Identical to ufshcd_send_uic_cmd() expect mutex. Must be called
  * with mutex held and host_lock locked.
  * Returns 0 only if success.
  */
 static int
-__ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
+__ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd,
+		      bool completion)
 {
 	if (!ufshcd_ready_for_uic_cmd(hba)) {
 		dev_err(hba->dev,
@@ -967,7 +999,8 @@ __ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
 		return -EIO;
 	}
 
-	init_completion(&uic_cmd->done);
+	if (completion)
+		init_completion(&uic_cmd->done);
 
 	ufshcd_dispatch_uic_cmd(hba, uic_cmd);
 
@@ -992,7 +1025,7 @@ ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
 	ufshcd_add_delay_before_dme_cmd(hba);
 
 	spin_lock_irqsave(hba->host->host_lock, flags);
-	ret = __ufshcd_send_uic_cmd(hba, uic_cmd);
+	ret = __ufshcd_send_uic_cmd(hba, uic_cmd, true);
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 	if (!ret)
 		ret = ufshcd_wait_for_uic_cmd(hba, uic_cmd);
@@ -1035,6 +1068,7 @@ static int ufshcd_map_sg(struct ufshcd_lrb *lrbp)
 				cpu_to_le32(lower_32_bits(sg->dma_address));
 			prd_table[i].upper_addr =
 				cpu_to_le32(upper_32_bits(sg->dma_address));
+			prd_table[i].reserved = 0;
 		}
 	} else {
 		lrbp->utr_descriptor_ptr->prd_table_length = 0;
@@ -1117,7 +1151,8 @@ static void ufshcd_prepare_req_desc_hdr(struct ufshcd_lrb *lrbp,
 
 	/* Transfer request descriptor header fields */
 	req_desc->header.dword_0 = cpu_to_le32(dword_0);
-
+	/* dword_1 is reserved, hence it is set to 0 */
+	req_desc->header.dword_1 = 0;
 	/*
 	 * assigning invalid value for command status. Controller
 	 * updates OCS on command completion, with the command
@@ -1125,6 +1160,10 @@ static void ufshcd_prepare_req_desc_hdr(struct ufshcd_lrb *lrbp,
 	 */
 	req_desc->header.dword_2 =
 		cpu_to_le32(OCS_INVALID_COMMAND_STATUS);
+	/* dword_3 is reserved, hence it is set to 0 */
+	req_desc->header.dword_3 = 0;
+
+	req_desc->prd_table_length = 0;
 }
 
 /**
@@ -1137,6 +1176,7 @@ static
 void ufshcd_prepare_utp_scsi_cmd_upiu(struct ufshcd_lrb *lrbp, u32 upiu_flags)
 {
 	struct utp_upiu_req *ucd_req_ptr = lrbp->ucd_req_ptr;
+	unsigned short cdb_len;
 
 	/* command descriptor fields */
 	ucd_req_ptr->header.dword_0 = UPIU_HEADER_DWORD(
@@ -1151,8 +1191,11 @@ void ufshcd_prepare_utp_scsi_cmd_upiu(struct ufshcd_lrb *lrbp, u32 upiu_flags)
 	ucd_req_ptr->sc.exp_data_transfer_len =
 		cpu_to_be32(lrbp->cmd->sdb.length);
 
-	memcpy(ucd_req_ptr->sc.cdb, lrbp->cmd->cmnd,
-		(min_t(unsigned short, lrbp->cmd->cmd_len, MAX_CDB_SIZE)));
+	cdb_len = min_t(unsigned short, lrbp->cmd->cmd_len, MAX_CDB_SIZE);
+	memset(ucd_req_ptr->sc.cdb, 0, MAX_CDB_SIZE);
+	memcpy(ucd_req_ptr->sc.cdb, lrbp->cmd->cmnd, cdb_len);
+
+	memset(lrbp->ucd_rsp_ptr, 0, sizeof(struct utp_upiu_rsp));
 }
 
 /**
@@ -1189,6 +1232,7 @@ static void ufshcd_prepare_utp_query_req_upiu(struct ufs_hba *hba,
 	if (query->request.upiu_req.opcode == UPIU_QUERY_OPCODE_WRITE_DESC)
 		memcpy(descp, query->descriptor, len);
 
+	memset(lrbp->ucd_rsp_ptr, 0, sizeof(struct utp_upiu_rsp));
 }
 
 static inline void ufshcd_prepare_utp_nop_upiu(struct ufshcd_lrb *lrbp)
@@ -1201,6 +1245,11 @@ static inline void ufshcd_prepare_utp_nop_upiu(struct ufshcd_lrb *lrbp)
 	ucd_req_ptr->header.dword_0 =
 		UPIU_HEADER_DWORD(
 			UPIU_TRANSACTION_NOP_OUT, 0, 0, lrbp->task_tag);
+	/* clear rest of the fields of basic header */
+	ucd_req_ptr->header.dword_1 = 0;
+	ucd_req_ptr->header.dword_2 = 0;
+
+	memset(lrbp->ucd_rsp_ptr, 0, sizeof(struct utp_upiu_rsp));
 }
 
 /**
@@ -1293,6 +1342,12 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	hba = shost_priv(host);
 
 	tag = cmd->request->tag;
+	if (!ufshcd_valid_tag(hba, tag)) {
+		dev_err(hba->dev,
+			"%s: invalid command tag %d: cmd=0x%p, cmd->request=0x%p",
+			__func__, tag, cmd, cmd->request);
+		BUG();
+	}
 
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	switch (hba->ufshcd_state) {
@@ -1312,6 +1367,13 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 		cmd->scsi_done(cmd);
 		goto out_unlock;
 	}
+
+	/* if error handling is in progress, don't issue commands */
+	if (ufshcd_eh_in_progress(hba)) {
+		set_host_byte(cmd, DID_ERROR);
+		cmd->scsi_done(cmd);
+		goto out_unlock;
+	}
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 
 	/* acquire the tag to make sure device cmds don't use it */
@@ -1475,9 +1537,17 @@ static int ufshcd_wait_for_dev_cmd(struct ufs_hba *hba,
 
 	if (!time_left) {
 		err = -ETIMEDOUT;
+		dev_dbg(hba->dev, "%s: dev_cmd request timedout, tag %d\n",
+			__func__, lrbp->task_tag);
 		if (!ufshcd_clear_cmd(hba, lrbp->task_tag))
-			/* sucessfully cleared the command, retry if needed */
+			/* successfully cleared the command, retry if needed */
 			err = -EAGAIN;
+		/*
+		 * in case of an error, after clearing the doorbell,
+		 * we also need to clear the outstanding_request
+		 * field in hba
+		 */
+		ufshcd_outstanding_req_clear(hba, lrbp->task_tag);
 	}
 
 	return err;
@@ -1555,6 +1625,8 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba,
 
 	hba->dev_cmd.complete = &wait;
 
+	/* Make sure descriptors are ready before ringing the doorbell */
+	wmb();
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	ufshcd_send_command(hba, tag);
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
@@ -1591,6 +1663,29 @@ static inline void ufshcd_init_query(struct ufs_hba *hba,
 	(*request)->upiu_req.selector = selector;
 }
 
+static int ufshcd_query_flag_retry(struct ufs_hba *hba,
+	enum query_opcode opcode, enum flag_idn idn, bool *flag_res)
+{
+	int ret;
+	int retries;
+
+	for (retries = 0; retries < QUERY_REQ_RETRIES; retries++) {
+		ret = ufshcd_query_flag(hba, opcode, idn, flag_res);
+		if (ret)
+			dev_dbg(hba->dev,
+				"%s: failed with error %d, retries %d\n",
+				__func__, ret, retries);
+		else
+			break;
+	}
+
+	if (ret)
+		dev_err(hba->dev,
+			"%s: query attribute, opcode %d, idn %d, failed with error %d after %d retires\n",
+			__func__, opcode, idn, ret, retries);
+	return ret;
+}
+
 /**
  * ufshcd_query_flag() - API function for sending flag query requests
  * hba: per-adapter instance
@@ -1600,12 +1695,13 @@ static inline void ufshcd_init_query(struct ufs_hba *hba,
  *
  * Returns 0 for success, non-zero in case of failure
  */
-static int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode,
+int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode,
 			enum flag_idn idn, bool *flag_res)
 {
 	struct ufs_query_req *request = NULL;
 	struct ufs_query_res *response = NULL;
 	int err, index = 0, selector = 0;
+	int timeout = QUERY_REQ_TIMEOUT;
 
 	BUG_ON(!hba);
 
@@ -1638,7 +1734,10 @@ static int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode,
 		goto out_unlock;
 	}
 
-	err = ufshcd_exec_dev_cmd(hba, DEV_CMD_TYPE_QUERY, QUERY_REQ_TIMEOUT);
+	if (idn == QUERY_FLAG_IDN_FDEVICEINIT)
+		timeout = QUERY_FDEVICEINIT_REQ_TIMEOUT;
+
+	err = ufshcd_exec_dev_cmd(hba, DEV_CMD_TYPE_QUERY, timeout);
 
 	if (err) {
 		dev_err(hba->dev,
@@ -1722,6 +1821,43 @@ out:
 }
 
 /**
+ * ufshcd_query_attr_retry() - API function for sending query
+ * attribute with retries
+ * @hba: per-adapter instance
+ * @opcode: attribute opcode
+ * @idn: attribute idn to access
+ * @index: index field
+ * @selector: selector field
+ * @attr_val: the attribute value after the query request
+ * completes
+ *
+ * Returns 0 for success, non-zero in case of failure
+*/
+static int ufshcd_query_attr_retry(struct ufs_hba *hba,
+	enum query_opcode opcode, enum attr_idn idn, u8 index, u8 selector,
+	u32 *attr_val)
+{
+	int ret = 0;
+	u32 retries;
+
+	 for (retries = QUERY_REQ_RETRIES; retries > 0; retries--) {
+		ret = ufshcd_query_attr(hba, opcode, idn, index,
+						selector, attr_val);
+		if (ret)
+			dev_dbg(hba->dev, "%s: failed with error %d, retries %d\n",
+				__func__, ret, retries);
+		else
+			break;
+	}
+
+	if (ret)
+		dev_err(hba->dev,
+			"%s: query attribute, idn %d, failed with error %d after %d retires\n",
+			__func__, idn, ret, QUERY_REQ_RETRIES);
+	return ret;
+}
+
+/**
  * ufshcd_query_descriptor - API function for sending descriptor requests
  * hba: per-adapter instance
  * opcode: attribute opcode
@@ -2128,6 +2264,7 @@ int ufshcd_dme_set_attr(struct ufs_hba *hba, u32 attr_sel,
 	};
 	const char *set = action[!!peer];
 	int ret;
+	int retries = UFS_UIC_COMMAND_RETRIES;
 
 	uic_cmd.command = peer ?
 		UIC_CMD_DME_PEER_SET : UIC_CMD_DME_SET;
@@ -2135,10 +2272,18 @@ int ufshcd_dme_set_attr(struct ufs_hba *hba, u32 attr_sel,
 	uic_cmd.argument2 = UIC_ARG_ATTR_TYPE(attr_set);
 	uic_cmd.argument3 = mib_val;
 
-	ret = ufshcd_send_uic_cmd(hba, &uic_cmd);
-	if (ret)
-		dev_err(hba->dev, "%s: attr-id 0x%x val 0x%x error code %d\n",
-			set, UIC_GET_ATTR_ID(attr_sel), mib_val, ret);
+	do {
+		/* for peer attributes we retry upon failure */
+		ret = ufshcd_send_uic_cmd(hba, &uic_cmd);
+		if (ret)
+			dev_dbg(hba->dev, "%s: attr-id 0x%x val 0x%x error code %d\n",
+				set, UIC_GET_ATTR_ID(attr_sel), mib_val, ret);
+	} while (ret && peer && --retries);
+
+	if (!retries)
+		dev_err(hba->dev, "%s: attr-id 0x%x val 0x%x failed %d retries\n",
+				set, UIC_GET_ATTR_ID(attr_sel), mib_val,
+				retries);
 
 	return ret;
 }
@@ -2163,6 +2308,7 @@ int ufshcd_dme_get_attr(struct ufs_hba *hba, u32 attr_sel,
 	};
 	const char *get = action[!!peer];
 	int ret;
+	int retries = UFS_UIC_COMMAND_RETRIES;
 	struct ufs_pa_layer_attr orig_pwr_info;
 	struct ufs_pa_layer_attr temp_pwr_info;
 	bool pwr_mode_change = false;
@@ -2193,14 +2339,19 @@ int ufshcd_dme_get_attr(struct ufs_hba *hba, u32 attr_sel,
 		UIC_CMD_DME_PEER_GET : UIC_CMD_DME_GET;
 	uic_cmd.argument1 = attr_sel;
 
-	ret = ufshcd_send_uic_cmd(hba, &uic_cmd);
-	if (ret) {
-		dev_err(hba->dev, "%s: attr-id 0x%x error code %d\n",
-			get, UIC_GET_ATTR_ID(attr_sel), ret);
-		goto out;
-	}
+	do {
+		/* for peer attributes we retry upon failure */
+		ret = ufshcd_send_uic_cmd(hba, &uic_cmd);
+		if (ret)
+			dev_dbg(hba->dev, "%s: attr-id 0x%x error code %d\n",
+				get, UIC_GET_ATTR_ID(attr_sel), ret);
+	} while (ret && peer && --retries);
 
-	if (mib_val)
+	if (!retries)
+		dev_err(hba->dev, "%s: attr-id 0x%x failed %d retries\n",
+				get, UIC_GET_ATTR_ID(attr_sel), retries);
+
+	if (mib_val && !ret)
 		*mib_val = uic_cmd.argument3;
 
 	if (peer && (hba->quirks & UFSHCD_QUIRK_DME_PEER_ACCESS_AUTO_MODE)
@@ -2233,6 +2384,7 @@ static int ufshcd_uic_pwr_ctrl(struct ufs_hba *hba, struct uic_command *cmd)
 	unsigned long flags;
 	u8 status;
 	int ret;
+	bool reenable_intr = false;
 
 	mutex_lock(&hba->uic_cmd_mutex);
 	init_completion(&uic_async_done);
@@ -2240,15 +2392,17 @@ static int ufshcd_uic_pwr_ctrl(struct ufs_hba *hba, struct uic_command *cmd)
 
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	hba->uic_async_done = &uic_async_done;
-	ret = __ufshcd_send_uic_cmd(hba, cmd);
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
-	if (ret) {
-		dev_err(hba->dev,
-			"pwr ctrl cmd 0x%x with mode 0x%x uic error %d\n",
-			cmd->command, cmd->argument3, ret);
-		goto out;
+	if (ufshcd_readl(hba, REG_INTERRUPT_ENABLE) & UIC_COMMAND_COMPL) {
+		ufshcd_disable_intr(hba, UIC_COMMAND_COMPL);
+		/*
+		 * Make sure UIC command completion interrupt is disabled before
+		 * issuing UIC command.
+		 */
+		wmb();
+		reenable_intr = true;
 	}
-	ret = ufshcd_wait_for_uic_cmd(hba, cmd);
+	ret = __ufshcd_send_uic_cmd(hba, cmd, false);
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
 	if (ret) {
 		dev_err(hba->dev,
 			"pwr ctrl cmd 0x%x with mode 0x%x uic error %d\n",
@@ -2274,7 +2428,10 @@ static int ufshcd_uic_pwr_ctrl(struct ufs_hba *hba, struct uic_command *cmd)
 	}
 out:
 	spin_lock_irqsave(hba->host->host_lock, flags);
+	hba->active_uic_cmd = NULL;
 	hba->uic_async_done = NULL;
+	if (reenable_intr)
+		ufshcd_enable_intr(hba, UIC_COMMAND_COMPL);
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 	mutex_unlock(&hba->uic_cmd_mutex);
 
@@ -2315,13 +2472,65 @@ out:
 	return ret;
 }
 
-static int ufshcd_uic_hibern8_enter(struct ufs_hba *hba)
+static int ufshcd_link_recovery(struct ufs_hba *hba)
 {
+	int ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	hba->ufshcd_state = UFSHCD_STATE_RESET;
+	ufshcd_set_eh_in_progress(hba);
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
+	ret = ufshcd_host_reset_and_restore(hba);
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	if (ret)
+		hba->ufshcd_state = UFSHCD_STATE_ERROR;
+	ufshcd_clear_eh_in_progress(hba);
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
+	if (ret)
+		dev_err(hba->dev, "%s: link recovery failed, err %d",
+			__func__, ret);
+
+	return ret;
+}
+
+static int __ufshcd_uic_hibern8_enter(struct ufs_hba *hba)
+{
+	int ret;
 	struct uic_command uic_cmd = {0};
 
 	uic_cmd.command = UIC_CMD_DME_HIBER_ENTER;
+	ret = ufshcd_uic_pwr_ctrl(hba, &uic_cmd);
+
+	if (ret) {
+		dev_err(hba->dev, "%s: hibern8 enter failed. ret = %d\n",
+			__func__, ret);
+
+		/*
+		 * If link recovery fails then return error so that caller
+		 * don't retry the hibern8 enter again.
+		 */
+		if (ufshcd_link_recovery(hba))
+			ret = -ENOLINK;
+	}
 
-	return ufshcd_uic_pwr_ctrl(hba, &uic_cmd);
+	return ret;
+}
+
+static int ufshcd_uic_hibern8_enter(struct ufs_hba *hba)
+{
+	int ret = 0, retries;
+
+	for (retries = UIC_HIBERN8_ENTER_RETRIES; retries > 0; retries--) {
+		ret = __ufshcd_uic_hibern8_enter(hba);
+		if (!ret || ret == -ENOLINK)
+			goto out;
+	}
+out:
+	return ret;
 }
 
 static int ufshcd_uic_hibern8_exit(struct ufs_hba *hba)
@@ -2332,8 +2541,9 @@ static int ufshcd_uic_hibern8_exit(struct ufs_hba *hba)
 	uic_cmd.command = UIC_CMD_DME_HIBER_EXIT;
 	ret = ufshcd_uic_pwr_ctrl(hba, &uic_cmd);
 	if (ret) {
-		ufshcd_set_link_off(hba);
-		ret = ufshcd_host_reset_and_restore(hba);
+		dev_err(hba->dev, "%s: hibern8 exit failed. ret = %d\n",
+			__func__, ret);
+		ret = ufshcd_link_recovery(hba);
 	}
 
 	return ret;
@@ -2513,17 +2723,12 @@ static int ufshcd_config_pwr_mode(struct ufs_hba *hba,
  */
 static int ufshcd_complete_dev_init(struct ufs_hba *hba)
 {
-	int i, retries, err = 0;
+	int i;
+	int err;
 	bool flag_res = 1;
 
-	for (retries = QUERY_REQ_RETRIES; retries > 0; retries--) {
-		/* Set the fDeviceInit flag */
-		err = ufshcd_query_flag(hba, UPIU_QUERY_OPCODE_SET_FLAG,
-					QUERY_FLAG_IDN_FDEVICEINIT, NULL);
-		if (!err || err == -ETIMEDOUT)
-			break;
-		dev_dbg(hba->dev, "%s: error %d retrying\n", __func__, err);
-	}
+	err = ufshcd_query_flag_retry(hba, UPIU_QUERY_OPCODE_SET_FLAG,
+		QUERY_FLAG_IDN_FDEVICEINIT, NULL);
 	if (err) {
 		dev_err(hba->dev,
 			"%s setting fDeviceInit flag failed with error %d\n",
@@ -2531,18 +2736,11 @@ static int ufshcd_complete_dev_init(struct ufs_hba *hba)
 		goto out;
 	}
 
-	/* poll for max. 100 iterations for fDeviceInit flag to clear */
-	for (i = 0; i < 100 && !err && flag_res; i++) {
-		for (retries = QUERY_REQ_RETRIES; retries > 0; retries--) {
-			err = ufshcd_query_flag(hba,
-					UPIU_QUERY_OPCODE_READ_FLAG,
-					QUERY_FLAG_IDN_FDEVICEINIT, &flag_res);
-			if (!err || err == -ETIMEDOUT)
-				break;
-			dev_dbg(hba->dev, "%s: error %d retrying\n", __func__,
-					err);
-		}
-	}
+	/* poll for max. 1000 iterations for fDeviceInit flag to clear */
+	for (i = 0; i < 1000 && !err && flag_res; i++)
+		err = ufshcd_query_flag_retry(hba, UPIU_QUERY_OPCODE_READ_FLAG,
+			QUERY_FLAG_IDN_FDEVICEINIT, &flag_res);
+
 	if (err)
 		dev_err(hba->dev,
 			"%s reading fDeviceInit flag failed with error %d\n",
@@ -2563,7 +2761,7 @@ out:
  * To bring UFS host controller to operational state,
  * 1. Enable required interrupts
  * 2. Configure interrupt aggregation
- * 3. Program UTRL and UTMRL base addres
+ * 3. Program UTRL and UTMRL base address
  * 4. Configure run-stop-registers
  *
  * Returns 0 on success, non-zero value on failure
@@ -2593,8 +2791,13 @@ static int ufshcd_make_hba_operational(struct ufs_hba *hba)
 			REG_UTP_TASK_REQ_LIST_BASE_H);
 
 	/*
+	 * Make sure base address and interrupt setup are updated before
+	 * enabling the run/stop registers below.
+	 */
+	wmb();
+
+	/*
 	 * UCRDY, UTMRLDY and UTRLRDY bits must be 1
-	 * DEI, HEI bits must be 0
 	 */
 	reg = ufshcd_readl(hba, REG_CONTROLLER_STATUS);
 	if (!(ufshcd_get_lists_status(reg))) {
@@ -3090,7 +3293,20 @@ ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 			scsi_status = result & MASK_SCSI_STATUS;
 			result = ufshcd_scsi_cmd_status(lrbp, scsi_status);
 
-			if (ufshcd_is_exception_event(lrbp->ucd_rsp_ptr))
+			/*
+			 * Currently we are only supporting BKOPs exception
+			 * events hence we can ignore BKOPs exception event
+			 * during power management callbacks. BKOPs exception
+			 * event is not expected to be raised in runtime suspend
+			 * callback as it allows the urgent bkops.
+			 * During system suspend, we are anyway forcefully
+			 * disabling the bkops and if urgent bkops is needed
+			 * it will be enabled on system resume. Long term
+			 * solution could be to abort the system suspend if
+			 * UFS device needs urgent BKOPs.
+			 */
+			if (!hba->pm_op_in_progress &&
+			    ufshcd_is_exception_event(lrbp->ucd_rsp_ptr))
 				schedule_work(&hba->eeh_work);
 			break;
 		case UPIU_TRANSACTION_REJECT_UPIU:
@@ -3222,7 +3438,7 @@ static int ufshcd_disable_ee(struct ufs_hba *hba, u16 mask)
 
 	val = hba->ee_ctrl_mask & ~mask;
 	val &= 0xFFFF; /* 2 bytes */
-	err = ufshcd_query_attr(hba, UPIU_QUERY_OPCODE_WRITE_ATTR,
+	err = ufshcd_query_attr_retry(hba, UPIU_QUERY_OPCODE_WRITE_ATTR,
 			QUERY_ATTR_IDN_EE_CONTROL, 0, 0, &val);
 	if (!err)
 		hba->ee_ctrl_mask &= ~mask;
@@ -3250,7 +3466,7 @@ static int ufshcd_enable_ee(struct ufs_hba *hba, u16 mask)
 
 	val = hba->ee_ctrl_mask | mask;
 	val &= 0xFFFF; /* 2 bytes */
-	err = ufshcd_query_attr(hba, UPIU_QUERY_OPCODE_WRITE_ATTR,
+	err = ufshcd_query_attr_retry(hba, UPIU_QUERY_OPCODE_WRITE_ATTR,
 			QUERY_ATTR_IDN_EE_CONTROL, 0, 0, &val);
 	if (!err)
 		hba->ee_ctrl_mask |= mask;
@@ -3276,7 +3492,7 @@ static int ufshcd_enable_auto_bkops(struct ufs_hba *hba)
 	if (hba->auto_bkops_enabled)
 		goto out;
 
-	err = ufshcd_query_flag(hba, UPIU_QUERY_OPCODE_SET_FLAG,
+	err = ufshcd_query_flag_retry(hba, UPIU_QUERY_OPCODE_SET_FLAG,
 			QUERY_FLAG_IDN_BKOPS_EN, NULL);
 	if (err) {
 		dev_err(hba->dev, "%s: failed to enable bkops %d\n",
@@ -3325,7 +3541,7 @@ static int ufshcd_disable_auto_bkops(struct ufs_hba *hba)
 		goto out;
 	}
 
-	err = ufshcd_query_flag(hba, UPIU_QUERY_OPCODE_CLEAR_FLAG,
+	err = ufshcd_query_flag_retry(hba, UPIU_QUERY_OPCODE_CLEAR_FLAG,
 			QUERY_FLAG_IDN_BKOPS_EN, NULL);
 	if (err) {
 		dev_err(hba->dev, "%s: failed to disable bkops %d\n",
@@ -3356,7 +3572,7 @@ static void  ufshcd_force_reset_auto_bkops(struct ufs_hba *hba)
 
 static inline int ufshcd_get_bkops_status(struct ufs_hba *hba, u32 *status)
 {
-	return ufshcd_query_attr(hba, UPIU_QUERY_OPCODE_READ_ATTR,
+	return ufshcd_query_attr_retry(hba, UPIU_QUERY_OPCODE_READ_ATTR,
 			QUERY_ATTR_IDN_BKOPS_STATUS, 0, 0, status);
 }
 
@@ -3419,7 +3635,7 @@ static int ufshcd_urgent_bkops(struct ufs_hba *hba)
 
 static inline int ufshcd_get_ee_status(struct ufs_hba *hba, u32 *status)
 {
-	return ufshcd_query_attr(hba, UPIU_QUERY_OPCODE_READ_ATTR,
+	return ufshcd_query_attr_retry(hba, UPIU_QUERY_OPCODE_READ_ATTR,
 			QUERY_ATTR_IDN_EE_STATUS, 0, 0, status);
 }
 
@@ -3645,16 +3861,20 @@ static void ufshcd_sl_intr(struct ufs_hba *hba, u32 intr_status)
  */
 static irqreturn_t ufshcd_intr(int irq, void *__hba)
 {
-	u32 intr_status;
+	u32 intr_status, enabled_intr_status;
 	irqreturn_t retval = IRQ_NONE;
 	struct ufs_hba *hba = __hba;
 
 	spin_lock(hba->host->host_lock);
 	intr_status = ufshcd_readl(hba, REG_INTERRUPT_STATUS);
+	enabled_intr_status =
+		intr_status & ufshcd_readl(hba, REG_INTERRUPT_ENABLE);
 
-	if (intr_status) {
+	if (intr_status)
 		ufshcd_writel(hba, intr_status, REG_INTERRUPT_STATUS);
-		ufshcd_sl_intr(hba, intr_status);
+
+	if (enabled_intr_status) {
+		ufshcd_sl_intr(hba, enabled_intr_status);
 		retval = IRQ_HANDLED;
 	}
 	spin_unlock(hba->host->host_lock);
@@ -3740,6 +3960,10 @@ static int ufshcd_issue_tm_cmd(struct ufs_hba *hba, int lun_id, int task_id,
 
 	/* send command to the controller */
 	__set_bit(free_slot, &hba->outstanding_tasks);
+
+	/* Make sure descriptors are ready before ringing the task doorbell */
+	wmb();
+
 	ufshcd_writel(hba, 1 << free_slot, REG_UTP_TASK_REQ_DOOR_BELL);
 
 	spin_unlock_irqrestore(host->host_lock, flags);
@@ -3845,13 +4069,23 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 	host = cmd->device->host;
 	hba = shost_priv(host);
 	tag = cmd->request->tag;
+	if (!ufshcd_valid_tag(hba, tag)) {
+		dev_err(hba->dev,
+			"%s: invalid command tag %d: cmd=0x%p, cmd->request=0x%p",
+			__func__, tag, cmd, cmd->request);
+		BUG();
+	}
 
 	ufshcd_hold(hba, false);
+	reg = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
 	/* If command is already aborted/completed, return SUCCESS */
-	if (!(test_bit(tag, &hba->outstanding_reqs)))
+	if (!(test_bit(tag, &hba->outstanding_reqs))) {
+		dev_err(hba->dev,
+			"%s: cmd at tag %d already completed, outstanding=0x%lx, doorbell=0x%x\n",
+			__func__, tag, hba->outstanding_reqs, reg);
 		goto out;
+	}
 
-	reg = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
 	if (!(reg & (1 << tag))) {
 		dev_err(hba->dev,
 		"%s: cmd was completed, but without a notifying intr, tag = %d",
@@ -3905,7 +4139,7 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 	scsi_dma_unmap(cmd);
 
 	spin_lock_irqsave(host->host_lock, flags);
-	__clear_bit(tag, &hba->outstanding_reqs);
+	ufshcd_outstanding_req_clear(hba, tag);
 	hba->lrb[tag].cmd = NULL;
 	spin_unlock_irqrestore(host->host_lock, flags);
 
@@ -4155,9 +4389,9 @@ static void ufshcd_init_icc_levels(struct ufs_hba *hba)
 	dev_dbg(hba->dev, "%s: setting icc_level 0x%x",
 			__func__, hba->init_prefetch_data.icc_level);
 
-	ret = ufshcd_query_attr(hba, UPIU_QUERY_OPCODE_WRITE_ATTR,
-			QUERY_ATTR_IDN_ACTIVE_ICC_LVL, 0, 0,
-			&hba->init_prefetch_data.icc_level);
+	ret = ufshcd_query_attr_retry(hba, UPIU_QUERY_OPCODE_WRITE_ATTR,
+		QUERY_ATTR_IDN_ACTIVE_ICC_LVL, 0, 0,
+		&hba->init_prefetch_data.icc_level);
 
 	if (ret)
 		dev_err(hba->dev,
@@ -4262,7 +4496,6 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 	/* UFS device is also active now */
 	ufshcd_set_ufs_dev_active(hba);
 	ufshcd_force_reset_auto_bkops(hba);
-	hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL;
 	hba->wlun_dev_clr_ua = true;
 
 	if (ufshcd_get_max_pwr_mode(hba)) {
@@ -4276,6 +4509,8 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 					__func__, ret);
 	}
 
+	/* set the state as operational after switching to desired gear */
+	hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL;
 	/*
 	 * If we are in error handling context or in power management callbacks
 	 * context, no need to scan the host
@@ -4285,8 +4520,8 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 
 		/* clear any previous UFS device information */
 		memset(&hba->dev_info, 0, sizeof(hba->dev_info));
-		if (!ufshcd_query_flag(hba, UPIU_QUERY_OPCODE_READ_FLAG,
-				       QUERY_FLAG_IDN_PWR_ON_WPE, &flag))
+		if (!ufshcd_query_flag_retry(hba, UPIU_QUERY_OPCODE_READ_FLAG,
+				QUERY_FLAG_IDN_PWR_ON_WPE, &flag))
 			hba->dev_info.f_power_on_wp_en = flag;
 
 		if (!hba->is_init_prefetch)
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 2570d9477b37..e3931d0c94eb 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -3,6 +3,7 @@
  *
  * This code is based on drivers/scsi/ufs/ufshcd.h
  * Copyright (C) 2011-2013 Samsung India Software Operations
+ * Copyright (c) 2013-2016, The Linux Foundation. All rights reserved.
  *
  * Authors:
  *	Santosh Yaraganavi <santosh.sy@samsung.com>
@@ -177,7 +178,7 @@ struct ufshcd_lrb {
 };
 
 /**
- * struct ufs_query - holds relevent data structures for query request
+ * struct ufs_query - holds relevant data structures for query request
  * @request: request upiu and function
  * @descriptor: buffer for sending/receiving descriptor
  * @response: response upiu and response
@@ -681,6 +682,9 @@ static inline int ufshcd_dme_peer_get(struct ufs_hba *hba,
 	return ufshcd_dme_get_attr(hba, attr_sel, mib_val, DME_PEER);
 }
 
+/* Expose Query-Request API */
+int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode,
+	enum flag_idn idn, bool *flag_res);
 int ufshcd_hold(struct ufs_hba *hba, bool async);
 void ufshcd_release(struct ufs_hba *hba);
 
diff --git a/drivers/sh/pm_runtime.c b/drivers/sh/pm_runtime.c
index 91a003011acf..a9bac3bf20de 100644
--- a/drivers/sh/pm_runtime.c
+++ b/drivers/sh/pm_runtime.c
@@ -34,7 +34,7 @@ static struct pm_clk_notifier_block platform_bus_notifier = {
 
 static int __init sh_pm_runtime_init(void)
 {
-	if (IS_ENABLED(CONFIG_ARCH_SHMOBILE)) {
+	if (IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_ARCH_SHMOBILE)) {
 		if (!of_find_compatible_node(NULL, NULL,
 					     "renesas,cpg-mstp-clocks"))
 			return 0;
diff --git a/drivers/sh/superhyway/superhyway.c b/drivers/sh/superhyway/superhyway.c
index 2d9e7f3d5611..bb1fb7712134 100644
--- a/drivers/sh/superhyway/superhyway.c
+++ b/drivers/sh/superhyway/superhyway.c
@@ -66,7 +66,7 @@ int superhyway_add_device(unsigned long base, struct superhyway_device *sdev,
 	superhyway_read_vcr(dev, base, &dev->vcr);
 
 	if (!dev->resource) {
-		dev->resource = kmalloc(sizeof(struct resource), GFP_KERNEL);
+		dev->resource = kzalloc(sizeof(struct resource), GFP_KERNEL);
 		if (!dev->resource) {
 			kfree(dev);
 			return -ENOMEM;
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 77064160dd76..9d8c84bb1544 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -75,11 +75,26 @@ config SPI_ATMEL
 	  This selects a driver for the Atmel SPI Controller, present on
 	  many AT32 (AVR32) and AT91 (ARM) chips.
 
+config SPI_AU1550
+	tristate "Au1550/Au1200/Au1300 SPI Controller"
+	depends on MIPS_ALCHEMY
+	select SPI_BITBANG
+	help
+	  If you say yes to this option, support will be included for the
+	  PSC SPI controller found on Au1550, Au1200 and Au1300 series.
+
+config SPI_AXI_SPI_ENGINE
+	tristate "Analog Devices AXI SPI Engine controller"
+	depends on HAS_IOMEM
+	help
+	  This enables support for the Analog Devices AXI SPI Engine SPI controller.
+	  It is part of the SPI Engine framework that is used in some Analog Devices
+	  reference designs for FPGAs.
+
 config SPI_BCM2835
 	tristate "BCM2835 SPI controller"
 	depends on GPIOLIB
 	depends on ARCH_BCM2835 || COMPILE_TEST
-	depends on GPIOLIB
 	help
 	  This selects a driver for the Broadcom BCM2835 SPI master.
 
@@ -90,8 +105,7 @@ config SPI_BCM2835
 
 config SPI_BCM2835AUX
 	tristate "BCM2835 SPI auxiliary controller"
-	depends on ARCH_BCM2835 || COMPILE_TEST
-	depends on GPIOLIB
+	depends on (ARCH_BCM2835 && GPIOLIB) || COMPILE_TEST
 	help
 	  This selects a driver for the Broadcom BCM2835 SPI aux master.
 
@@ -118,14 +132,6 @@ config SPI_BFIN_SPORT
 	help
 	  Enable support for a SPI bus via the Blackfin SPORT peripheral.
 
-config SPI_AU1550
-	tristate "Au1550/Au1200/Au1300 SPI Controller"
-	depends on MIPS_ALCHEMY
-	select SPI_BITBANG
-	help
-	  If you say yes to this option, support will be included for the
-	  PSC SPI controller found on Au1550, Au1200 and Au1300 series.
-
 config SPI_BCM53XX
 	tristate "Broadcom BCM53xx SPI controller"
 	depends on ARCH_BCM_5301X
@@ -197,6 +203,23 @@ config SPI_DAVINCI
 	help
 	  SPI master controller for DaVinci/DA8x/OMAP-L/AM1x SPI modules.
 
+config SPI_DESIGNWARE
+	tristate "DesignWare SPI controller core support"
+	help
+	  general driver for SPI controller core from DesignWare
+
+config SPI_DW_PCI
+	tristate "PCI interface driver for DW SPI core"
+	depends on SPI_DESIGNWARE && PCI
+
+config SPI_DW_MID_DMA
+	bool "DMA support for DW SPI controller on Intel MID platform"
+	depends on SPI_DW_PCI && DW_DMAC_PCI
+
+config SPI_DW_MMIO
+	tristate "Memory-mapped io interface driver for DW SPI core"
+	depends on SPI_DESIGNWARE
+
 config SPI_DLN2
        tristate "Diolan DLN-2 USB SPI adapter"
        depends on MFD_DLN2
@@ -271,6 +294,16 @@ config SPI_LM70_LLP
 	  which interfaces to an LM70 temperature sensor using
 	  a parallel port.
 
+config SPI_LP8841_RTC
+	tristate "ICP DAS LP-8841 SPI Controller for RTC"
+	depends on MACH_PXA27X_DT || COMPILE_TEST
+	help
+	  This driver provides an SPI master device to drive Maxim
+	  DS-1302 real time clock.
+
+	  Say N here unless you plan to run the kernel on an ICP DAS
+	  LP-8x4x industrial computer.
+
 config SPI_MPC52xx
 	tristate "Freescale MPC52xx SPI (non-PSC) controller support"
 	depends on PPC_MPC52xx
@@ -346,6 +379,13 @@ config SPI_MT65XX
 	  say Y or M here.If you are not sure, say N.
 	  SPI drivers for Mediatek MT65XX and MT81XX series ARM SoCs.
 
+config SPI_NUC900
+	tristate "Nuvoton NUC900 series SPI"
+	depends on ARCH_W90X900
+	select SPI_BITBANG
+	help
+	  SPI driver for Nuvoton NUC900 series ARM SoCs
+
 config SPI_OC_TINY
 	tristate "OpenCores tiny SPI"
 	depends on GPIOLIB || COMPILE_TEST
@@ -415,10 +455,6 @@ config SPI_PPC4xx
 	help
 	  This selects a driver for the PPC4xx SPI Controller.
 
-config SPI_PXA2XX_DMA
-	def_bool y
-	depends on SPI_PXA2XX
-
 config SPI_PXA2XX
 	tristate "PXA2xx SSP SPI master"
 	depends on (ARCH_PXA || PCI || ACPI)
@@ -451,7 +487,7 @@ config SPI_RB4XX
 
 config SPI_RSPI
 	tristate "Renesas RSPI/QSPI controller"
-	depends on SUPERH || ARCH_SHMOBILE || COMPILE_TEST
+	depends on SUPERH || ARCH_RENESAS || COMPILE_TEST
 	help
 	  SPI driver for Renesas RSPI and QSPI blocks.
 
@@ -501,7 +537,7 @@ config SPI_SC18IS602
 config SPI_SH_MSIOF
 	tristate "SuperH MSIOF SPI controller"
 	depends on HAVE_CLK && HAS_DMA
-	depends on SUPERH || ARCH_SHMOBILE || COMPILE_TEST
+	depends on SUPERH || ARCH_RENESAS || COMPILE_TEST
 	help
 	  SPI driver for SuperH and SH Mobile MSIOF blocks.
 
@@ -520,7 +556,7 @@ config SPI_SH_SCI
 
 config SPI_SH_HSPI
 	tristate "SuperH HSPI controller"
-	depends on ARCH_SHMOBILE || COMPILE_TEST
+	depends on ARCH_RENESAS || COMPILE_TEST
 	help
 	  SPI driver for SuperH HSPI blocks.
 
@@ -647,34 +683,10 @@ config SPI_ZYNQMP_GQSPI
 	help
 	  Enables Xilinx GQSPI controller driver for Zynq UltraScale+ MPSoC.
 
-config SPI_NUC900
-	tristate "Nuvoton NUC900 series SPI"
-	depends on ARCH_W90X900
-	select SPI_BITBANG
-	help
-	  SPI driver for Nuvoton NUC900 series ARM SoCs
-
 #
 # Add new SPI master controllers in alphabetical order above this line
 #
 
-config SPI_DESIGNWARE
-	tristate "DesignWare SPI controller core support"
-	help
-	  general driver for SPI controller core from DesignWare
-
-config SPI_DW_PCI
-	tristate "PCI interface driver for DW SPI core"
-	depends on SPI_DESIGNWARE && PCI
-
-config SPI_DW_MID_DMA
-	bool "DMA support for DW SPI controller on Intel MID platform"
-	depends on SPI_DW_PCI && DW_DMAC_PCI
-
-config SPI_DW_MMIO
-	tristate "Memory-mapped io interface driver for DW SPI core"
-	depends on SPI_DESIGNWARE
-
 #
 # There are lots of SPI device types, with sensors and memory
 # being probably the most widely used ones.
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index 8991ffce6e12..fbb255c5a608 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -15,6 +15,7 @@ obj-$(CONFIG_SPI_ALTERA)		+= spi-altera.o
 obj-$(CONFIG_SPI_ATMEL)			+= spi-atmel.o
 obj-$(CONFIG_SPI_ATH79)			+= spi-ath79.o
 obj-$(CONFIG_SPI_AU1550)		+= spi-au1550.o
+obj-$(CONFIG_SPI_AXI_SPI_ENGINE)	+= spi-axi-spi-engine.o
 obj-$(CONFIG_SPI_BCM2835)		+= spi-bcm2835.o
 obj-$(CONFIG_SPI_BCM2835AUX)		+= spi-bcm2835aux.o
 obj-$(CONFIG_SPI_BCM53XX)		+= spi-bcm53xx.o
@@ -46,6 +47,7 @@ obj-$(CONFIG_SPI_GPIO)			+= spi-gpio.o
 obj-$(CONFIG_SPI_IMG_SPFI)		+= spi-img-spfi.o
 obj-$(CONFIG_SPI_IMX)			+= spi-imx.o
 obj-$(CONFIG_SPI_LM70_LLP)		+= spi-lm70llp.o
+obj-$(CONFIG_SPI_LP8841_RTC)		+= spi-lp8841-rtc.o
 obj-$(CONFIG_SPI_MESON_SPIFC)		+= spi-meson-spifc.o
 obj-$(CONFIG_SPI_MPC512x_PSC)		+= spi-mpc512x-psc.o
 obj-$(CONFIG_SPI_MPC52xx_PSC)		+= spi-mpc52xx-psc.o
@@ -62,8 +64,7 @@ obj-$(CONFIG_SPI_TI_QSPI)		+= spi-ti-qspi.o
 obj-$(CONFIG_SPI_ORION)			+= spi-orion.o
 obj-$(CONFIG_SPI_PL022)			+= spi-pl022.o
 obj-$(CONFIG_SPI_PPC4xx)		+= spi-ppc4xx.o
-spi-pxa2xx-platform-objs		:= spi-pxa2xx.o
-spi-pxa2xx-platform-$(CONFIG_SPI_PXA2XX_DMA)	+= spi-pxa2xx-dma.o
+spi-pxa2xx-platform-objs		:= spi-pxa2xx.o spi-pxa2xx-dma.o
 obj-$(CONFIG_SPI_PXA2XX)		+= spi-pxa2xx-platform.o
 obj-$(CONFIG_SPI_PXA2XX_PCI)		+= spi-pxa2xx-pci.o
 obj-$(CONFIG_SPI_QUP)			+= spi-qup.o
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index aebad36391c9..8feac599e9ab 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -1571,6 +1571,7 @@ static int atmel_spi_probe(struct platform_device *pdev)
 
 	as->use_cs_gpios = true;
 	if (atmel_spi_is_v2(as) &&
+	    pdev->dev.of_node &&
 	    !of_get_property(pdev->dev.of_node, "cs-gpios", NULL)) {
 		as->use_cs_gpios = false;
 		master->num_chipselect = 4;
diff --git a/drivers/spi/spi-axi-spi-engine.c b/drivers/spi/spi-axi-spi-engine.c
new file mode 100644
index 000000000000..c968ab210a51
--- /dev/null
+++ b/drivers/spi/spi-axi-spi-engine.c
@@ -0,0 +1,591 @@
+/*
+ * SPI-Engine SPI controller driver
+ * Copyright 2015 Analog Devices Inc.
+ *  Author: Lars-Peter Clausen <lars@metafoo.de>
+ *
+ * Licensed under the GPL-2.
+ */
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+
+#define SPI_ENGINE_VERSION_MAJOR(x)	((x >> 16) & 0xff)
+#define SPI_ENGINE_VERSION_MINOR(x)	((x >> 8) & 0xff)
+#define SPI_ENGINE_VERSION_PATCH(x)	(x & 0xff)
+
+#define SPI_ENGINE_REG_VERSION			0x00
+
+#define SPI_ENGINE_REG_RESET			0x40
+
+#define SPI_ENGINE_REG_INT_ENABLE		0x80
+#define SPI_ENGINE_REG_INT_PENDING		0x84
+#define SPI_ENGINE_REG_INT_SOURCE		0x88
+
+#define SPI_ENGINE_REG_SYNC_ID			0xc0
+
+#define SPI_ENGINE_REG_CMD_FIFO_ROOM		0xd0
+#define SPI_ENGINE_REG_SDO_FIFO_ROOM		0xd4
+#define SPI_ENGINE_REG_SDI_FIFO_LEVEL		0xd8
+
+#define SPI_ENGINE_REG_CMD_FIFO			0xe0
+#define SPI_ENGINE_REG_SDO_DATA_FIFO		0xe4
+#define SPI_ENGINE_REG_SDI_DATA_FIFO		0xe8
+#define SPI_ENGINE_REG_SDI_DATA_FIFO_PEEK	0xec
+
+#define SPI_ENGINE_INT_CMD_ALMOST_EMPTY		BIT(0)
+#define SPI_ENGINE_INT_SDO_ALMOST_EMPTY		BIT(1)
+#define SPI_ENGINE_INT_SDI_ALMOST_FULL		BIT(2)
+#define SPI_ENGINE_INT_SYNC			BIT(3)
+
+#define SPI_ENGINE_CONFIG_CPHA			BIT(0)
+#define SPI_ENGINE_CONFIG_CPOL			BIT(1)
+#define SPI_ENGINE_CONFIG_3WIRE			BIT(2)
+
+#define SPI_ENGINE_INST_TRANSFER		0x0
+#define SPI_ENGINE_INST_ASSERT			0x1
+#define SPI_ENGINE_INST_WRITE			0x2
+#define SPI_ENGINE_INST_MISC			0x3
+
+#define SPI_ENGINE_CMD_REG_CLK_DIV		0x0
+#define SPI_ENGINE_CMD_REG_CONFIG		0x1
+
+#define SPI_ENGINE_MISC_SYNC			0x0
+#define SPI_ENGINE_MISC_SLEEP			0x1
+
+#define SPI_ENGINE_TRANSFER_WRITE		0x1
+#define SPI_ENGINE_TRANSFER_READ		0x2
+
+#define SPI_ENGINE_CMD(inst, arg1, arg2) \
+	(((inst) << 12) | ((arg1) << 8) | (arg2))
+
+#define SPI_ENGINE_CMD_TRANSFER(flags, n) \
+	SPI_ENGINE_CMD(SPI_ENGINE_INST_TRANSFER, (flags), (n))
+#define SPI_ENGINE_CMD_ASSERT(delay, cs) \
+	SPI_ENGINE_CMD(SPI_ENGINE_INST_ASSERT, (delay), (cs))
+#define SPI_ENGINE_CMD_WRITE(reg, val) \
+	SPI_ENGINE_CMD(SPI_ENGINE_INST_WRITE, (reg), (val))
+#define SPI_ENGINE_CMD_SLEEP(delay) \
+	SPI_ENGINE_CMD(SPI_ENGINE_INST_MISC, SPI_ENGINE_MISC_SLEEP, (delay))
+#define SPI_ENGINE_CMD_SYNC(id) \
+	SPI_ENGINE_CMD(SPI_ENGINE_INST_MISC, SPI_ENGINE_MISC_SYNC, (id))
+
+struct spi_engine_program {
+	unsigned int length;
+	uint16_t instructions[];
+};
+
+struct spi_engine {
+	struct clk *clk;
+	struct clk *ref_clk;
+
+	spinlock_t lock;
+
+	void __iomem *base;
+
+	struct spi_message *msg;
+	struct spi_engine_program *p;
+	unsigned cmd_length;
+	const uint16_t *cmd_buf;
+
+	struct spi_transfer *tx_xfer;
+	unsigned int tx_length;
+	const uint8_t *tx_buf;
+
+	struct spi_transfer *rx_xfer;
+	unsigned int rx_length;
+	uint8_t *rx_buf;
+
+	unsigned int sync_id;
+	unsigned int completed_id;
+
+	unsigned int int_enable;
+};
+
+static void spi_engine_program_add_cmd(struct spi_engine_program *p,
+	bool dry, uint16_t cmd)
+{
+	if (!dry)
+		p->instructions[p->length] = cmd;
+	p->length++;
+}
+
+static unsigned int spi_engine_get_config(struct spi_device *spi)
+{
+	unsigned int config = 0;
+
+	if (spi->mode & SPI_CPOL)
+		config |= SPI_ENGINE_CONFIG_CPOL;
+	if (spi->mode & SPI_CPHA)
+		config |= SPI_ENGINE_CONFIG_CPHA;
+	if (spi->mode & SPI_3WIRE)
+		config |= SPI_ENGINE_CONFIG_3WIRE;
+
+	return config;
+}
+
+static unsigned int spi_engine_get_clk_div(struct spi_engine *spi_engine,
+	struct spi_device *spi, struct spi_transfer *xfer)
+{
+	unsigned int clk_div;
+
+	clk_div = DIV_ROUND_UP(clk_get_rate(spi_engine->ref_clk),
+		xfer->speed_hz * 2);
+	if (clk_div > 255)
+		clk_div = 255;
+	else if (clk_div > 0)
+		clk_div -= 1;
+
+	return clk_div;
+}
+
+static void spi_engine_gen_xfer(struct spi_engine_program *p, bool dry,
+	struct spi_transfer *xfer)
+{
+	unsigned int len = xfer->len;
+
+	while (len) {
+		unsigned int n = min(len, 256U);
+		unsigned int flags = 0;
+
+		if (xfer->tx_buf)
+			flags |= SPI_ENGINE_TRANSFER_WRITE;
+		if (xfer->rx_buf)
+			flags |= SPI_ENGINE_TRANSFER_READ;
+
+		spi_engine_program_add_cmd(p, dry,
+			SPI_ENGINE_CMD_TRANSFER(flags, n - 1));
+		len -= n;
+	}
+}
+
+static void spi_engine_gen_sleep(struct spi_engine_program *p, bool dry,
+	struct spi_engine *spi_engine, unsigned int clk_div, unsigned int delay)
+{
+	unsigned int spi_clk = clk_get_rate(spi_engine->ref_clk);
+	unsigned int t;
+
+	if (delay == 0)
+		return;
+
+	t = DIV_ROUND_UP(delay * spi_clk, (clk_div + 1) * 2);
+	while (t) {
+		unsigned int n = min(t, 256U);
+
+		spi_engine_program_add_cmd(p, dry, SPI_ENGINE_CMD_SLEEP(n - 1));
+		t -= n;
+	}
+}
+
+static void spi_engine_gen_cs(struct spi_engine_program *p, bool dry,
+		struct spi_device *spi, bool assert)
+{
+	unsigned int mask = 0xff;
+
+	if (assert)
+		mask ^= BIT(spi->chip_select);
+
+	spi_engine_program_add_cmd(p, dry, SPI_ENGINE_CMD_ASSERT(1, mask));
+}
+
+static int spi_engine_compile_message(struct spi_engine *spi_engine,
+	struct spi_message *msg, bool dry, struct spi_engine_program *p)
+{
+	struct spi_device *spi = msg->spi;
+	struct spi_transfer *xfer;
+	int clk_div, new_clk_div;
+	bool cs_change = true;
+
+	clk_div = -1;
+
+	spi_engine_program_add_cmd(p, dry,
+		SPI_ENGINE_CMD_WRITE(SPI_ENGINE_CMD_REG_CONFIG,
+			spi_engine_get_config(spi)));
+
+	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+		new_clk_div = spi_engine_get_clk_div(spi_engine, spi, xfer);
+		if (new_clk_div != clk_div) {
+			clk_div = new_clk_div;
+			spi_engine_program_add_cmd(p, dry,
+				SPI_ENGINE_CMD_WRITE(SPI_ENGINE_CMD_REG_CLK_DIV,
+					clk_div));
+		}
+
+		if (cs_change)
+			spi_engine_gen_cs(p, dry, spi, true);
+
+		spi_engine_gen_xfer(p, dry, xfer);
+		spi_engine_gen_sleep(p, dry, spi_engine, clk_div,
+			xfer->delay_usecs);
+
+		cs_change = xfer->cs_change;
+		if (list_is_last(&xfer->transfer_list, &msg->transfers))
+			cs_change = !cs_change;
+
+		if (cs_change)
+			spi_engine_gen_cs(p, dry, spi, false);
+	}
+
+	return 0;
+}
+
+static void spi_engine_xfer_next(struct spi_engine *spi_engine,
+	struct spi_transfer **_xfer)
+{
+	struct spi_message *msg = spi_engine->msg;
+	struct spi_transfer *xfer = *_xfer;
+
+	if (!xfer) {
+		xfer = list_first_entry(&msg->transfers,
+			struct spi_transfer, transfer_list);
+	} else if (list_is_last(&xfer->transfer_list, &msg->transfers)) {
+		xfer = NULL;
+	} else {
+		xfer = list_next_entry(xfer, transfer_list);
+	}
+
+	*_xfer = xfer;
+}
+
+static void spi_engine_tx_next(struct spi_engine *spi_engine)
+{
+	struct spi_transfer *xfer = spi_engine->tx_xfer;
+
+	do {
+		spi_engine_xfer_next(spi_engine, &xfer);
+	} while (xfer && !xfer->tx_buf);
+
+	spi_engine->tx_xfer = xfer;
+	if (xfer) {
+		spi_engine->tx_length = xfer->len;
+		spi_engine->tx_buf = xfer->tx_buf;
+	} else {
+		spi_engine->tx_buf = NULL;
+	}
+}
+
+static void spi_engine_rx_next(struct spi_engine *spi_engine)
+{
+	struct spi_transfer *xfer = spi_engine->rx_xfer;
+
+	do {
+		spi_engine_xfer_next(spi_engine, &xfer);
+	} while (xfer && !xfer->rx_buf);
+
+	spi_engine->rx_xfer = xfer;
+	if (xfer) {
+		spi_engine->rx_length = xfer->len;
+		spi_engine->rx_buf = xfer->rx_buf;
+	} else {
+		spi_engine->rx_buf = NULL;
+	}
+}
+
+static bool spi_engine_write_cmd_fifo(struct spi_engine *spi_engine)
+{
+	void __iomem *addr = spi_engine->base + SPI_ENGINE_REG_CMD_FIFO;
+	unsigned int n, m, i;
+	const uint16_t *buf;
+
+	n = readl_relaxed(spi_engine->base + SPI_ENGINE_REG_CMD_FIFO_ROOM);
+	while (n && spi_engine->cmd_length) {
+		m = min(n, spi_engine->cmd_length);
+		buf = spi_engine->cmd_buf;
+		for (i = 0; i < m; i++)
+			writel_relaxed(buf[i], addr);
+		spi_engine->cmd_buf += m;
+		spi_engine->cmd_length -= m;
+		n -= m;
+	}
+
+	return spi_engine->cmd_length != 0;
+}
+
+static bool spi_engine_write_tx_fifo(struct spi_engine *spi_engine)
+{
+	void __iomem *addr = spi_engine->base + SPI_ENGINE_REG_SDO_DATA_FIFO;
+	unsigned int n, m, i;
+	const uint8_t *buf;
+
+	n = readl_relaxed(spi_engine->base + SPI_ENGINE_REG_SDO_FIFO_ROOM);
+	while (n && spi_engine->tx_length) {
+		m = min(n, spi_engine->tx_length);
+		buf = spi_engine->tx_buf;
+		for (i = 0; i < m; i++)
+			writel_relaxed(buf[i], addr);
+		spi_engine->tx_buf += m;
+		spi_engine->tx_length -= m;
+		n -= m;
+		if (spi_engine->tx_length == 0)
+			spi_engine_tx_next(spi_engine);
+	}
+
+	return spi_engine->tx_length != 0;
+}
+
+static bool spi_engine_read_rx_fifo(struct spi_engine *spi_engine)
+{
+	void __iomem *addr = spi_engine->base + SPI_ENGINE_REG_SDI_DATA_FIFO;
+	unsigned int n, m, i;
+	uint8_t *buf;
+
+	n = readl_relaxed(spi_engine->base + SPI_ENGINE_REG_SDI_FIFO_LEVEL);
+	while (n && spi_engine->rx_length) {
+		m = min(n, spi_engine->rx_length);
+		buf = spi_engine->rx_buf;
+		for (i = 0; i < m; i++)
+			buf[i] = readl_relaxed(addr);
+		spi_engine->rx_buf += m;
+		spi_engine->rx_length -= m;
+		n -= m;
+		if (spi_engine->rx_length == 0)
+			spi_engine_rx_next(spi_engine);
+	}
+
+	return spi_engine->rx_length != 0;
+}
+
+static irqreturn_t spi_engine_irq(int irq, void *devid)
+{
+	struct spi_master *master = devid;
+	struct spi_engine *spi_engine = spi_master_get_devdata(master);
+	unsigned int disable_int = 0;
+	unsigned int pending;
+
+	pending = readl_relaxed(spi_engine->base + SPI_ENGINE_REG_INT_PENDING);
+
+	if (pending & SPI_ENGINE_INT_SYNC) {
+		writel_relaxed(SPI_ENGINE_INT_SYNC,
+			spi_engine->base + SPI_ENGINE_REG_INT_PENDING);
+		spi_engine->completed_id = readl_relaxed(
+			spi_engine->base + SPI_ENGINE_REG_SYNC_ID);
+	}
+
+	spin_lock(&spi_engine->lock);
+
+	if (pending & SPI_ENGINE_INT_CMD_ALMOST_EMPTY) {
+		if (!spi_engine_write_cmd_fifo(spi_engine))
+			disable_int |= SPI_ENGINE_INT_CMD_ALMOST_EMPTY;
+	}
+
+	if (pending & SPI_ENGINE_INT_SDO_ALMOST_EMPTY) {
+		if (!spi_engine_write_tx_fifo(spi_engine))
+			disable_int |= SPI_ENGINE_INT_SDO_ALMOST_EMPTY;
+	}
+
+	if (pending & (SPI_ENGINE_INT_SDI_ALMOST_FULL | SPI_ENGINE_INT_SYNC)) {
+		if (!spi_engine_read_rx_fifo(spi_engine))
+			disable_int |= SPI_ENGINE_INT_SDI_ALMOST_FULL;
+	}
+
+	if (pending & SPI_ENGINE_INT_SYNC) {
+		if (spi_engine->msg &&
+		    spi_engine->completed_id == spi_engine->sync_id) {
+			struct spi_message *msg = spi_engine->msg;
+
+			kfree(spi_engine->p);
+			msg->status = 0;
+			msg->actual_length = msg->frame_length;
+			spi_engine->msg = NULL;
+			spi_finalize_current_message(master);
+			disable_int |= SPI_ENGINE_INT_SYNC;
+		}
+	}
+
+	if (disable_int) {
+		spi_engine->int_enable &= ~disable_int;
+		writel_relaxed(spi_engine->int_enable,
+			spi_engine->base + SPI_ENGINE_REG_INT_ENABLE);
+	}
+
+	spin_unlock(&spi_engine->lock);
+
+	return IRQ_HANDLED;
+}
+
+static int spi_engine_transfer_one_message(struct spi_master *master,
+	struct spi_message *msg)
+{
+	struct spi_engine_program p_dry, *p;
+	struct spi_engine *spi_engine = spi_master_get_devdata(master);
+	unsigned int int_enable = 0;
+	unsigned long flags;
+	size_t size;
+
+	p_dry.length = 0;
+	spi_engine_compile_message(spi_engine, msg, true, &p_dry);
+
+	size = sizeof(*p->instructions) * (p_dry.length + 1);
+	p = kzalloc(sizeof(*p) + size, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+	spi_engine_compile_message(spi_engine, msg, false, p);
+
+	spin_lock_irqsave(&spi_engine->lock, flags);
+	spi_engine->sync_id = (spi_engine->sync_id + 1) & 0xff;
+	spi_engine_program_add_cmd(p, false,
+		SPI_ENGINE_CMD_SYNC(spi_engine->sync_id));
+
+	spi_engine->msg = msg;
+	spi_engine->p = p;
+
+	spi_engine->cmd_buf = p->instructions;
+	spi_engine->cmd_length = p->length;
+	if (spi_engine_write_cmd_fifo(spi_engine))
+		int_enable |= SPI_ENGINE_INT_CMD_ALMOST_EMPTY;
+
+	spi_engine_tx_next(spi_engine);
+	if (spi_engine_write_tx_fifo(spi_engine))
+		int_enable |= SPI_ENGINE_INT_SDO_ALMOST_EMPTY;
+
+	spi_engine_rx_next(spi_engine);
+	if (spi_engine->rx_length != 0)
+		int_enable |= SPI_ENGINE_INT_SDI_ALMOST_FULL;
+
+	int_enable |= SPI_ENGINE_INT_SYNC;
+
+	writel_relaxed(int_enable,
+		spi_engine->base + SPI_ENGINE_REG_INT_ENABLE);
+	spi_engine->int_enable = int_enable;
+	spin_unlock_irqrestore(&spi_engine->lock, flags);
+
+	return 0;
+}
+
+static int spi_engine_probe(struct platform_device *pdev)
+{
+	struct spi_engine *spi_engine;
+	struct spi_master *master;
+	unsigned int version;
+	struct resource *res;
+	int irq;
+	int ret;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq <= 0)
+		return -ENXIO;
+
+	spi_engine = devm_kzalloc(&pdev->dev, sizeof(*spi_engine), GFP_KERNEL);
+	if (!spi_engine)
+		return -ENOMEM;
+
+	master = spi_alloc_master(&pdev->dev, 0);
+	if (!master)
+		return -ENOMEM;
+
+	spi_master_set_devdata(master, spi_engine);
+
+	spin_lock_init(&spi_engine->lock);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	spi_engine->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(spi_engine->base)) {
+		ret = PTR_ERR(spi_engine->base);
+		goto err_put_master;
+	}
+
+	version = readl(spi_engine->base + SPI_ENGINE_REG_VERSION);
+	if (SPI_ENGINE_VERSION_MAJOR(version) != 1) {
+		dev_err(&pdev->dev, "Unsupported peripheral version %u.%u.%c\n",
+			SPI_ENGINE_VERSION_MAJOR(version),
+			SPI_ENGINE_VERSION_MINOR(version),
+			SPI_ENGINE_VERSION_PATCH(version));
+		return -ENODEV;
+	}
+
+	spi_engine->clk = devm_clk_get(&pdev->dev, "s_axi_aclk");
+	if (IS_ERR(spi_engine->clk)) {
+		ret = PTR_ERR(spi_engine->clk);
+		goto err_put_master;
+	}
+
+	spi_engine->ref_clk = devm_clk_get(&pdev->dev, "spi_clk");
+	if (IS_ERR(spi_engine->ref_clk)) {
+		ret = PTR_ERR(spi_engine->ref_clk);
+		goto err_put_master;
+	}
+
+	ret = clk_prepare_enable(spi_engine->clk);
+	if (ret)
+		goto err_put_master;
+
+	ret = clk_prepare_enable(spi_engine->ref_clk);
+	if (ret)
+		goto err_clk_disable;
+
+	writel_relaxed(0x00, spi_engine->base + SPI_ENGINE_REG_RESET);
+	writel_relaxed(0xff, spi_engine->base + SPI_ENGINE_REG_INT_PENDING);
+	writel_relaxed(0x00, spi_engine->base + SPI_ENGINE_REG_INT_ENABLE);
+
+	ret = request_irq(irq, spi_engine_irq, 0, pdev->name, master);
+	if (ret)
+		goto err_ref_clk_disable;
+
+	master->dev.parent = &pdev->dev;
+	master->dev.of_node = pdev->dev.of_node;
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_3WIRE;
+	master->bits_per_word_mask = SPI_BPW_MASK(8);
+	master->max_speed_hz = clk_get_rate(spi_engine->ref_clk) / 2;
+	master->transfer_one_message = spi_engine_transfer_one_message;
+	master->num_chipselect = 8;
+
+	ret = spi_register_master(master);
+	if (ret)
+		goto err_free_irq;
+
+	platform_set_drvdata(pdev, master);
+
+	return 0;
+err_free_irq:
+	free_irq(irq, master);
+err_ref_clk_disable:
+	clk_disable_unprepare(spi_engine->ref_clk);
+err_clk_disable:
+	clk_disable_unprepare(spi_engine->clk);
+err_put_master:
+	spi_master_put(master);
+	return ret;
+}
+
+static int spi_engine_remove(struct platform_device *pdev)
+{
+	struct spi_master *master = platform_get_drvdata(pdev);
+	struct spi_engine *spi_engine = spi_master_get_devdata(master);
+	int irq = platform_get_irq(pdev, 0);
+
+	spi_unregister_master(master);
+
+	free_irq(irq, master);
+
+	writel_relaxed(0xff, spi_engine->base + SPI_ENGINE_REG_INT_PENDING);
+	writel_relaxed(0x00, spi_engine->base + SPI_ENGINE_REG_INT_ENABLE);
+	writel_relaxed(0x01, spi_engine->base + SPI_ENGINE_REG_RESET);
+
+	clk_disable_unprepare(spi_engine->ref_clk);
+	clk_disable_unprepare(spi_engine->clk);
+
+	return 0;
+}
+
+static const struct of_device_id spi_engine_match_table[] = {
+	{ .compatible = "adi,axi-spi-engine-1.00.a" },
+	{ },
+};
+
+static struct platform_driver spi_engine_driver = {
+	.probe = spi_engine_probe,
+	.remove = spi_engine_remove,
+	.driver = {
+		.name = "spi-engine",
+		.of_match_table = spi_engine_match_table,
+	},
+};
+module_platform_driver(spi_engine_driver);
+
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_DESCRIPTION("Analog Devices SPI engine peripheral driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index cf04960cc3e6..f35cc10772f6 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -727,11 +727,6 @@ static int bcm2835_spi_setup(struct spi_device *spi)
 			spi->chip_select, spi->cs_gpio, err);
 		return err;
 	}
-	/* the implementation of pinctrl-bcm2835 currently does not
-	 * set the GPIO value when using gpio_direction_output
-	 * so we are setting it here explicitly
-	 */
-	gpio_set_value(spi->cs_gpio, (spi->mode & SPI_CS_HIGH) ? 0 : 1);
 
 	return 0;
 }
diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c
index 7de6f8472a81..7428091d3f5b 100644
--- a/drivers/spi/spi-bcm2835aux.c
+++ b/drivers/spi/spi-bcm2835aux.c
@@ -64,17 +64,17 @@
 #define BCM2835_AUX_SPI_CNTL0_VAR_WIDTH	0x00004000
 #define BCM2835_AUX_SPI_CNTL0_DOUTHOLD	0x00003000
 #define BCM2835_AUX_SPI_CNTL0_ENABLE	0x00000800
-#define BCM2835_AUX_SPI_CNTL0_CPHA_IN	0x00000400
+#define BCM2835_AUX_SPI_CNTL0_IN_RISING	0x00000400
 #define BCM2835_AUX_SPI_CNTL0_CLEARFIFO	0x00000200
-#define BCM2835_AUX_SPI_CNTL0_CPHA_OUT	0x00000100
+#define BCM2835_AUX_SPI_CNTL0_OUT_RISING	0x00000100
 #define BCM2835_AUX_SPI_CNTL0_CPOL	0x00000080
 #define BCM2835_AUX_SPI_CNTL0_MSBF_OUT	0x00000040
 #define BCM2835_AUX_SPI_CNTL0_SHIFTLEN	0x0000003F
 
 /* Bitfields in CNTL1 */
 #define BCM2835_AUX_SPI_CNTL1_CSHIGH	0x00000700
-#define BCM2835_AUX_SPI_CNTL1_IDLE	0x00000080
-#define BCM2835_AUX_SPI_CNTL1_TXEMPTY	0x00000040
+#define BCM2835_AUX_SPI_CNTL1_TXEMPTY	0x00000080
+#define BCM2835_AUX_SPI_CNTL1_IDLE	0x00000040
 #define BCM2835_AUX_SPI_CNTL1_MSBF_IN	0x00000002
 #define BCM2835_AUX_SPI_CNTL1_KEEP_IN	0x00000001
 
@@ -92,9 +92,6 @@
 #define BCM2835_AUX_SPI_POLLING_LIMIT_US	30
 #define BCM2835_AUX_SPI_POLLING_JIFFIES		2
 
-#define BCM2835_AUX_SPI_MODE_BITS (SPI_CPOL | SPI_CPHA | SPI_CS_HIGH \
-				  | SPI_NO_CS)
-
 struct bcm2835aux_spi {
 	void __iomem *regs;
 	struct clk *clk;
@@ -212,9 +209,15 @@ static irqreturn_t bcm2835aux_spi_interrupt(int irq, void *dev_id)
 		ret = IRQ_HANDLED;
 	}
 
-	/* and if rx_len is 0 then wake up completion and disable spi */
+	if (!bs->tx_len) {
+		/* disable tx fifo empty interrupt */
+		bcm2835aux_wr(bs, BCM2835_AUX_SPI_CNTL1, bs->cntl[1] |
+			BCM2835_AUX_SPI_CNTL1_IDLE);
+	}
+
+	/* and if rx_len is 0 then disable interrupts and wake up completion */
 	if (!bs->rx_len) {
-		bcm2835aux_spi_reset_hw(bs);
+		bcm2835aux_wr(bs, BCM2835_AUX_SPI_CNTL1, bs->cntl[1]);
 		complete(&master->xfer_completion);
 	}
 
@@ -307,9 +310,6 @@ static int bcm2835aux_spi_transfer_one_poll(struct spi_master *master,
 		}
 	}
 
-	/* Transfer complete - reset SPI HW */
-	bcm2835aux_spi_reset_hw(bs);
-
 	/* and return without waiting for completion */
 	return 0;
 }
@@ -330,10 +330,6 @@ static int bcm2835aux_spi_transfer_one(struct spi_master *master,
 	 * resulting (potentially) in more interrupts when transferring
 	 * more than 12 bytes
 	 */
-	bs->cntl[0] = BCM2835_AUX_SPI_CNTL0_ENABLE |
-		      BCM2835_AUX_SPI_CNTL0_VAR_WIDTH |
-		      BCM2835_AUX_SPI_CNTL0_MSBF_OUT;
-	bs->cntl[1] = BCM2835_AUX_SPI_CNTL1_MSBF_IN;
 
 	/* set clock */
 	spi_hz = tfr->speed_hz;
@@ -348,17 +344,13 @@ static int bcm2835aux_spi_transfer_one(struct spi_master *master,
 	} else { /* the slowest we can go */
 		speed = BCM2835_AUX_SPI_CNTL0_SPEED_MAX;
 	}
+	/* mask out old speed from previous spi_transfer */
+	bs->cntl[0] &= ~(BCM2835_AUX_SPI_CNTL0_SPEED);
+	/* set the new speed */
 	bs->cntl[0] |= speed << BCM2835_AUX_SPI_CNTL0_SPEED_SHIFT;
 
 	spi_used_hz = clk_hz / (2 * (speed + 1));
 
-	/* handle all the modes */
-	if (spi->mode & SPI_CPOL)
-		bs->cntl[0] |= BCM2835_AUX_SPI_CNTL0_CPOL;
-	if (spi->mode & SPI_CPHA)
-		bs->cntl[0] |= BCM2835_AUX_SPI_CNTL0_CPHA_OUT |
-			       BCM2835_AUX_SPI_CNTL0_CPHA_IN;
-
 	/* set transmit buffers and length */
 	bs->tx_buf = tfr->tx_buf;
 	bs->rx_buf = tfr->rx_buf;
@@ -382,6 +374,40 @@ static int bcm2835aux_spi_transfer_one(struct spi_master *master,
 	return bcm2835aux_spi_transfer_one_irq(master, spi, tfr);
 }
 
+static int bcm2835aux_spi_prepare_message(struct spi_master *master,
+					  struct spi_message *msg)
+{
+	struct spi_device *spi = msg->spi;
+	struct bcm2835aux_spi *bs = spi_master_get_devdata(master);
+
+	bs->cntl[0] = BCM2835_AUX_SPI_CNTL0_ENABLE |
+		      BCM2835_AUX_SPI_CNTL0_VAR_WIDTH |
+		      BCM2835_AUX_SPI_CNTL0_MSBF_OUT;
+	bs->cntl[1] = BCM2835_AUX_SPI_CNTL1_MSBF_IN;
+
+	/* handle all the modes */
+	if (spi->mode & SPI_CPOL) {
+		bs->cntl[0] |= BCM2835_AUX_SPI_CNTL0_CPOL;
+		bs->cntl[0] |= BCM2835_AUX_SPI_CNTL0_OUT_RISING;
+	} else {
+		bs->cntl[0] |= BCM2835_AUX_SPI_CNTL0_IN_RISING;
+	}
+	bcm2835aux_wr(bs, BCM2835_AUX_SPI_CNTL1, bs->cntl[1]);
+	bcm2835aux_wr(bs, BCM2835_AUX_SPI_CNTL0, bs->cntl[0]);
+
+	return 0;
+}
+
+static int bcm2835aux_spi_unprepare_message(struct spi_master *master,
+					    struct spi_message *msg)
+{
+	struct bcm2835aux_spi *bs = spi_master_get_devdata(master);
+
+	bcm2835aux_spi_reset_hw(bs);
+
+	return 0;
+}
+
 static void bcm2835aux_spi_handle_err(struct spi_master *master,
 				      struct spi_message *msg)
 {
@@ -405,11 +431,13 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev)
 	}
 
 	platform_set_drvdata(pdev, master);
-	master->mode_bits = BCM2835_AUX_SPI_MODE_BITS;
+	master->mode_bits = (SPI_CPOL | SPI_CS_HIGH | SPI_NO_CS);
 	master->bits_per_word_mask = SPI_BPW_MASK(8);
 	master->num_chipselect = -1;
 	master->transfer_one = bcm2835aux_spi_transfer_one;
 	master->handle_err = bcm2835aux_spi_handle_err;
+	master->prepare_message = bcm2835aux_spi_prepare_message;
+	master->unprepare_message = bcm2835aux_spi_unprepare_message;
 	master->dev.of_node = pdev->dev.of_node;
 
 	bs = spi_master_get_devdata(master);
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index 9185f6c08459..e31971f91475 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -89,10 +89,10 @@ static void mid_spi_dma_exit(struct dw_spi *dws)
 	if (!dws->dma_inited)
 		return;
 
-	dmaengine_terminate_all(dws->txchan);
+	dmaengine_terminate_sync(dws->txchan);
 	dma_release_channel(dws->txchan);
 
-	dmaengine_terminate_all(dws->rxchan);
+	dmaengine_terminate_sync(dws->rxchan);
 	dma_release_channel(dws->rxchan);
 }
 
diff --git a/drivers/spi/spi-dw-mmio.c b/drivers/spi/spi-dw-mmio.c
index a6d7029a85ac..447497e9124c 100644
--- a/drivers/spi/spi-dw-mmio.c
+++ b/drivers/spi/spi-dw-mmio.c
@@ -47,11 +47,6 @@ static int dw_spi_mmio_probe(struct platform_device *pdev)
 
 	/* Get basic io resource and map it */
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!mem) {
-		dev_err(&pdev->dev, "no mem resource?\n");
-		return -EINVAL;
-	}
-
 	dws->regs = devm_ioremap_resource(&pdev->dev, mem);
 	if (IS_ERR(dws->regs)) {
 		dev_err(&pdev->dev, "SPI region map failed\n");
diff --git a/drivers/spi/spi-fsl-espi.c b/drivers/spi/spi-fsl-espi.c
index 7fd6a4c009d2..7cb0c1921495 100644
--- a/drivers/spi/spi-fsl-espi.c
+++ b/drivers/spi/spi-fsl-espi.c
@@ -84,7 +84,7 @@ struct fsl_espi_transfer {
 /* SPCOM register values */
 #define SPCOM_CS(x)		((x) << 30)
 #define SPCOM_TRANLEN(x)	((x) << 0)
-#define	SPCOM_TRANLEN_MAX	0xFFFF	/* Max transaction length */
+#define	SPCOM_TRANLEN_MAX	0x10000	/* Max transaction length */
 
 #define AUTOSUSPEND_TIMEOUT 2000
 
@@ -233,7 +233,7 @@ static int fsl_espi_bufs(struct spi_device *spi, struct spi_transfer *t)
 	reinit_completion(&mpc8xxx_spi->done);
 
 	/* Set SPCOM[CS] and SPCOM[TRANLEN] field */
-	if ((t->len - 1) > SPCOM_TRANLEN_MAX) {
+	if (t->len > SPCOM_TRANLEN_MAX) {
 		dev_err(mpc8xxx_spi->dev, "Transaction length (%d)"
 				" beyond the SPCOM[TRANLEN] field\n", t->len);
 		return -EINVAL;
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index d98c33cb64f9..e7a19be87c38 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -56,7 +56,6 @@
 
 /* The maximum  bytes that a sdma BD can transfer.*/
 #define MAX_SDMA_BD_BYTES  (1 << 15)
-#define IMX_DMA_TIMEOUT (msecs_to_jiffies(3000))
 struct spi_imx_config {
 	unsigned int speed_hz;
 	unsigned int bpw;
@@ -86,12 +85,18 @@ struct spi_imx_devtype_data {
 
 struct spi_imx_data {
 	struct spi_bitbang bitbang;
+	struct device *dev;
 
 	struct completion xfer_done;
 	void __iomem *base;
+	unsigned long base_phys;
+
 	struct clk *clk_per;
 	struct clk *clk_ipg;
 	unsigned long spi_clk;
+	unsigned int spi_bus_clk;
+
+	unsigned int bytes_per_word;
 
 	unsigned int count;
 	void (*tx)(struct spi_imx_data *);
@@ -101,8 +106,6 @@ struct spi_imx_data {
 	unsigned int txfifo; /* number of words pushed in tx FIFO */
 
 	/* DMA */
-	unsigned int dma_is_inited;
-	unsigned int dma_finished;
 	bool usedma;
 	u32 wml;
 	struct completion dma_rx_completion;
@@ -199,15 +202,35 @@ static unsigned int spi_imx_clkdiv_2(unsigned int fin,
 	return 7;
 }
 
+static int spi_imx_bytes_per_word(const int bpw)
+{
+	return DIV_ROUND_UP(bpw, BITS_PER_BYTE);
+}
+
 static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
 			 struct spi_transfer *transfer)
 {
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(master);
+	unsigned int bpw = transfer->bits_per_word;
+
+	if (!master->dma_rx)
+		return false;
 
-	if (spi_imx->dma_is_inited &&
-	    transfer->len > spi_imx->wml * sizeof(u32))
-		return true;
-	return false;
+	if (!bpw)
+		bpw = spi->bits_per_word;
+
+	bpw = spi_imx_bytes_per_word(bpw);
+
+	if (bpw != 1 && bpw != 2 && bpw != 4)
+		return false;
+
+	if (transfer->len < spi_imx->wml * bpw)
+		return false;
+
+	if (transfer->len % (spi_imx->wml * bpw))
+		return false;
+
+	return true;
 }
 
 #define MX51_ECSPI_CTRL		0x08
@@ -232,16 +255,13 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
 #define MX51_ECSPI_INT_RREN		(1 <<  3)
 
 #define MX51_ECSPI_DMA      0x14
-#define MX51_ECSPI_DMA_TX_WML_OFFSET	0
-#define MX51_ECSPI_DMA_TX_WML_MASK	0x3F
-#define MX51_ECSPI_DMA_RX_WML_OFFSET	16
-#define MX51_ECSPI_DMA_RX_WML_MASK	(0x3F << 16)
-#define MX51_ECSPI_DMA_RXT_WML_OFFSET	24
-#define MX51_ECSPI_DMA_RXT_WML_MASK	(0x3F << 24)
+#define MX51_ECSPI_DMA_TX_WML(wml)	((wml) & 0x3f)
+#define MX51_ECSPI_DMA_RX_WML(wml)	(((wml) & 0x3f) << 16)
+#define MX51_ECSPI_DMA_RXT_WML(wml)	(((wml) & 0x3f) << 24)
 
-#define MX51_ECSPI_DMA_TEDEN_OFFSET	7
-#define MX51_ECSPI_DMA_RXDEN_OFFSET	23
-#define MX51_ECSPI_DMA_RXTDEN_OFFSET	31
+#define MX51_ECSPI_DMA_TEDEN		(1 << 7)
+#define MX51_ECSPI_DMA_RXDEN		(1 << 23)
+#define MX51_ECSPI_DMA_RXTDEN		(1 << 31)
 
 #define MX51_ECSPI_STAT		0x18
 #define MX51_ECSPI_STAT_RR		(1 <<  3)
@@ -250,14 +270,15 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
 #define MX51_ECSPI_TESTREG_LBC	BIT(31)
 
 /* MX51 eCSPI */
-static unsigned int mx51_ecspi_clkdiv(unsigned int fin, unsigned int fspi,
-				      unsigned int *fres)
+static unsigned int mx51_ecspi_clkdiv(struct spi_imx_data *spi_imx,
+				      unsigned int fspi, unsigned int *fres)
 {
 	/*
 	 * there are two 4-bit dividers, the pre-divider divides by
 	 * $pre, the post-divider by 2^$post
 	 */
 	unsigned int pre, post;
+	unsigned int fin = spi_imx->spi_clk;
 
 	if (unlikely(fspi > fin))
 		return 0;
@@ -270,14 +291,14 @@ static unsigned int mx51_ecspi_clkdiv(unsigned int fin, unsigned int fspi,
 
 	post = max(4U, post) - 4;
 	if (unlikely(post > 0xf)) {
-		pr_err("%s: cannot set clock freq: %u (base freq: %u)\n",
-				__func__, fspi, fin);
+		dev_err(spi_imx->dev, "cannot set clock freq: %u (base freq: %u)\n",
+				fspi, fin);
 		return 0xff;
 	}
 
 	pre = DIV_ROUND_UP(fin, fspi << post) - 1;
 
-	pr_debug("%s: fin: %u, fspi: %u, post: %u, pre: %u\n",
+	dev_dbg(spi_imx->dev, "%s: fin: %u, fspi: %u, post: %u, pre: %u\n",
 			__func__, fin, fspi, post, pre);
 
 	/* Resulting frequency for the SCLK line. */
@@ -302,22 +323,17 @@ static void __maybe_unused mx51_ecspi_intctrl(struct spi_imx_data *spi_imx, int
 
 static void __maybe_unused mx51_ecspi_trigger(struct spi_imx_data *spi_imx)
 {
-	u32 reg = readl(spi_imx->base + MX51_ECSPI_CTRL);
+	u32 reg;
 
-	if (!spi_imx->usedma)
-		reg |= MX51_ECSPI_CTRL_XCH;
-	else if (!spi_imx->dma_finished)
-		reg |= MX51_ECSPI_CTRL_SMC;
-	else
-		reg &= ~MX51_ECSPI_CTRL_SMC;
+	reg = readl(spi_imx->base + MX51_ECSPI_CTRL);
+	reg |= MX51_ECSPI_CTRL_XCH;
 	writel(reg, spi_imx->base + MX51_ECSPI_CTRL);
 }
 
 static int __maybe_unused mx51_ecspi_config(struct spi_imx_data *spi_imx,
 		struct spi_imx_config *config)
 {
-	u32 ctrl = MX51_ECSPI_CTRL_ENABLE, cfg = 0, dma = 0;
-	u32 tx_wml_cfg, rx_wml_cfg, rxt_wml_cfg;
+	u32 ctrl = MX51_ECSPI_CTRL_ENABLE, cfg = 0;
 	u32 clk = config->speed_hz, delay, reg;
 
 	/*
@@ -330,7 +346,8 @@ static int __maybe_unused mx51_ecspi_config(struct spi_imx_data *spi_imx,
 	ctrl |= MX51_ECSPI_CTRL_MODE_MASK;
 
 	/* set clock speed */
-	ctrl |= mx51_ecspi_clkdiv(spi_imx->spi_clk, config->speed_hz, &clk);
+	ctrl |= mx51_ecspi_clkdiv(spi_imx, config->speed_hz, &clk);
+	spi_imx->spi_bus_clk = clk;
 
 	/* set chip select to use */
 	ctrl |= MX51_ECSPI_CTRL_CS(config->cs);
@@ -341,20 +358,16 @@ static int __maybe_unused mx51_ecspi_config(struct spi_imx_data *spi_imx,
 
 	if (config->mode & SPI_CPHA)
 		cfg |= MX51_ECSPI_CONFIG_SCLKPHA(config->cs);
-	else
-		cfg &= ~MX51_ECSPI_CONFIG_SCLKPHA(config->cs);
 
 	if (config->mode & SPI_CPOL) {
 		cfg |= MX51_ECSPI_CONFIG_SCLKPOL(config->cs);
 		cfg |= MX51_ECSPI_CONFIG_SCLKCTL(config->cs);
-	} else {
-		cfg &= ~MX51_ECSPI_CONFIG_SCLKPOL(config->cs);
-		cfg &= ~MX51_ECSPI_CONFIG_SCLKCTL(config->cs);
 	}
 	if (config->mode & SPI_CS_HIGH)
 		cfg |= MX51_ECSPI_CONFIG_SSBPOL(config->cs);
-	else
-		cfg &= ~MX51_ECSPI_CONFIG_SSBPOL(config->cs);
+
+	if (spi_imx->usedma)
+		ctrl |= MX51_ECSPI_CTRL_SMC;
 
 	/* CTRL register always go first to bring out controller from reset */
 	writel(ctrl, spi_imx->base + MX51_ECSPI_CTRL);
@@ -389,22 +402,12 @@ static int __maybe_unused mx51_ecspi_config(struct spi_imx_data *spi_imx,
 	 * Configure the DMA register: setup the watermark
 	 * and enable DMA request.
 	 */
-	if (spi_imx->dma_is_inited) {
-		dma = readl(spi_imx->base + MX51_ECSPI_DMA);
-
-		rx_wml_cfg = spi_imx->wml << MX51_ECSPI_DMA_RX_WML_OFFSET;
-		tx_wml_cfg = spi_imx->wml << MX51_ECSPI_DMA_TX_WML_OFFSET;
-		rxt_wml_cfg = spi_imx->wml << MX51_ECSPI_DMA_RXT_WML_OFFSET;
-		dma = (dma & ~MX51_ECSPI_DMA_TX_WML_MASK
-			   & ~MX51_ECSPI_DMA_RX_WML_MASK
-			   & ~MX51_ECSPI_DMA_RXT_WML_MASK)
-			   | rx_wml_cfg | tx_wml_cfg | rxt_wml_cfg
-			   |(1 << MX51_ECSPI_DMA_TEDEN_OFFSET)
-			   |(1 << MX51_ECSPI_DMA_RXDEN_OFFSET)
-			   |(1 << MX51_ECSPI_DMA_RXTDEN_OFFSET);
-
-		writel(dma, spi_imx->base + MX51_ECSPI_DMA);
-	}
+
+	writel(MX51_ECSPI_DMA_RX_WML(spi_imx->wml) |
+		MX51_ECSPI_DMA_TX_WML(spi_imx->wml) |
+		MX51_ECSPI_DMA_RXT_WML(spi_imx->wml) |
+		MX51_ECSPI_DMA_TEDEN | MX51_ECSPI_DMA_RXDEN |
+		MX51_ECSPI_DMA_RXTDEN, spi_imx->base + MX51_ECSPI_DMA);
 
 	return 0;
 }
@@ -784,11 +787,63 @@ static irqreturn_t spi_imx_isr(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static int spi_imx_dma_configure(struct spi_master *master,
+				 int bytes_per_word)
+{
+	int ret;
+	enum dma_slave_buswidth buswidth;
+	struct dma_slave_config rx = {}, tx = {};
+	struct spi_imx_data *spi_imx = spi_master_get_devdata(master);
+
+	if (bytes_per_word == spi_imx->bytes_per_word)
+		/* Same as last time */
+		return 0;
+
+	switch (bytes_per_word) {
+	case 4:
+		buswidth = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		break;
+	case 2:
+		buswidth = DMA_SLAVE_BUSWIDTH_2_BYTES;
+		break;
+	case 1:
+		buswidth = DMA_SLAVE_BUSWIDTH_1_BYTE;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	tx.direction = DMA_MEM_TO_DEV;
+	tx.dst_addr = spi_imx->base_phys + MXC_CSPITXDATA;
+	tx.dst_addr_width = buswidth;
+	tx.dst_maxburst = spi_imx->wml;
+	ret = dmaengine_slave_config(master->dma_tx, &tx);
+	if (ret) {
+		dev_err(spi_imx->dev, "TX dma configuration failed with %d\n", ret);
+		return ret;
+	}
+
+	rx.direction = DMA_DEV_TO_MEM;
+	rx.src_addr = spi_imx->base_phys + MXC_CSPIRXDATA;
+	rx.src_addr_width = buswidth;
+	rx.src_maxburst = spi_imx->wml;
+	ret = dmaengine_slave_config(master->dma_rx, &rx);
+	if (ret) {
+		dev_err(spi_imx->dev, "RX dma configuration failed with %d\n", ret);
+		return ret;
+	}
+
+	spi_imx->bytes_per_word = bytes_per_word;
+
+	return 0;
+}
+
 static int spi_imx_setupxfer(struct spi_device *spi,
 				 struct spi_transfer *t)
 {
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(spi->master);
 	struct spi_imx_config config;
+	int ret;
 
 	config.bpw = t ? t->bits_per_word : spi->bits_per_word;
 	config.speed_hz  = t ? t->speed_hz : spi->max_speed_hz;
@@ -812,6 +867,18 @@ static int spi_imx_setupxfer(struct spi_device *spi,
 		spi_imx->tx = spi_imx_buf_tx_u32;
 	}
 
+	if (spi_imx_can_dma(spi_imx->bitbang.master, spi, t))
+		spi_imx->usedma = 1;
+	else
+		spi_imx->usedma = 0;
+
+	if (spi_imx->usedma) {
+		ret = spi_imx_dma_configure(spi->master,
+					    spi_imx_bytes_per_word(config.bpw));
+		if (ret)
+			return ret;
+	}
+
 	spi_imx->devtype_data->config(spi_imx, &config);
 
 	return 0;
@@ -830,15 +897,11 @@ static void spi_imx_sdma_exit(struct spi_imx_data *spi_imx)
 		dma_release_channel(master->dma_tx);
 		master->dma_tx = NULL;
 	}
-
-	spi_imx->dma_is_inited = 0;
 }
 
 static int spi_imx_sdma_init(struct device *dev, struct spi_imx_data *spi_imx,
-			     struct spi_master *master,
-			     const struct resource *res)
+			     struct spi_master *master)
 {
-	struct dma_slave_config slave_config = {};
 	int ret;
 
 	/* use pio mode for i.mx6dl chip TKT238285 */
@@ -856,16 +919,6 @@ static int spi_imx_sdma_init(struct device *dev, struct spi_imx_data *spi_imx,
 		goto err;
 	}
 
-	slave_config.direction = DMA_MEM_TO_DEV;
-	slave_config.dst_addr = res->start + MXC_CSPITXDATA;
-	slave_config.dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
-	slave_config.dst_maxburst = spi_imx->wml;
-	ret = dmaengine_slave_config(master->dma_tx, &slave_config);
-	if (ret) {
-		dev_err(dev, "error in TX dma configuration.\n");
-		goto err;
-	}
-
 	/* Prepare for RX : */
 	master->dma_rx = dma_request_slave_channel_reason(dev, "rx");
 	if (IS_ERR(master->dma_rx)) {
@@ -875,15 +928,7 @@ static int spi_imx_sdma_init(struct device *dev, struct spi_imx_data *spi_imx,
 		goto err;
 	}
 
-	slave_config.direction = DMA_DEV_TO_MEM;
-	slave_config.src_addr = res->start + MXC_CSPIRXDATA;
-	slave_config.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
-	slave_config.src_maxburst = spi_imx->wml;
-	ret = dmaengine_slave_config(master->dma_rx, &slave_config);
-	if (ret) {
-		dev_err(dev, "error in RX dma configuration.\n");
-		goto err;
-	}
+	spi_imx_dma_configure(master, 1);
 
 	init_completion(&spi_imx->dma_rx_completion);
 	init_completion(&spi_imx->dma_tx_completion);
@@ -891,7 +936,6 @@ static int spi_imx_sdma_init(struct device *dev, struct spi_imx_data *spi_imx,
 	master->max_dma_len = MAX_SDMA_BD_BYTES;
 	spi_imx->bitbang.master->flags = SPI_MASTER_MUST_RX |
 					 SPI_MASTER_MUST_TX;
-	spi_imx->dma_is_inited = 1;
 
 	return 0;
 err:
@@ -913,106 +957,81 @@ static void spi_imx_dma_tx_callback(void *cookie)
 	complete(&spi_imx->dma_tx_completion);
 }
 
+static int spi_imx_calculate_timeout(struct spi_imx_data *spi_imx, int size)
+{
+	unsigned long timeout = 0;
+
+	/* Time with actual data transfer and CS change delay related to HW */
+	timeout = (8 + 4) * size / spi_imx->spi_bus_clk;
+
+	/* Add extra second for scheduler related activities */
+	timeout += 1;
+
+	/* Double calculated timeout */
+	return msecs_to_jiffies(2 * timeout * MSEC_PER_SEC);
+}
+
 static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx,
 				struct spi_transfer *transfer)
 {
-	struct dma_async_tx_descriptor *desc_tx = NULL, *desc_rx = NULL;
-	int ret;
+	struct dma_async_tx_descriptor *desc_tx, *desc_rx;
+	unsigned long transfer_timeout;
 	unsigned long timeout;
-	u32 dma;
-	int left;
 	struct spi_master *master = spi_imx->bitbang.master;
 	struct sg_table *tx = &transfer->tx_sg, *rx = &transfer->rx_sg;
 
-	if (tx) {
-		desc_tx = dmaengine_prep_slave_sg(master->dma_tx,
-					tx->sgl, tx->nents, DMA_MEM_TO_DEV,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
-		if (!desc_tx)
-			goto no_dma;
-
-		desc_tx->callback = spi_imx_dma_tx_callback;
-		desc_tx->callback_param = (void *)spi_imx;
-		dmaengine_submit(desc_tx);
-	}
+	/*
+	 * The TX DMA setup starts the transfer, so make sure RX is configured
+	 * before TX.
+	 */
+	desc_rx = dmaengine_prep_slave_sg(master->dma_rx,
+				rx->sgl, rx->nents, DMA_DEV_TO_MEM,
+				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!desc_rx)
+		return -EINVAL;
 
-	if (rx) {
-		desc_rx = dmaengine_prep_slave_sg(master->dma_rx,
-					rx->sgl, rx->nents, DMA_DEV_TO_MEM,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
-		if (!desc_rx)
-			goto no_dma;
+	desc_rx->callback = spi_imx_dma_rx_callback;
+	desc_rx->callback_param = (void *)spi_imx;
+	dmaengine_submit(desc_rx);
+	reinit_completion(&spi_imx->dma_rx_completion);
+	dma_async_issue_pending(master->dma_rx);
 
-		desc_rx->callback = spi_imx_dma_rx_callback;
-		desc_rx->callback_param = (void *)spi_imx;
-		dmaengine_submit(desc_rx);
+	desc_tx = dmaengine_prep_slave_sg(master->dma_tx,
+				tx->sgl, tx->nents, DMA_MEM_TO_DEV,
+				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!desc_tx) {
+		dmaengine_terminate_all(master->dma_tx);
+		return -EINVAL;
 	}
 
-	reinit_completion(&spi_imx->dma_rx_completion);
+	desc_tx->callback = spi_imx_dma_tx_callback;
+	desc_tx->callback_param = (void *)spi_imx;
+	dmaengine_submit(desc_tx);
 	reinit_completion(&spi_imx->dma_tx_completion);
-
-	/* Trigger the cspi module. */
-	spi_imx->dma_finished = 0;
-
-	dma = readl(spi_imx->base + MX51_ECSPI_DMA);
-	dma = dma & (~MX51_ECSPI_DMA_RXT_WML_MASK);
-	/* Change RX_DMA_LENGTH trigger dma fetch tail data */
-	left = transfer->len % spi_imx->wml;
-	if (left)
-		writel(dma | (left << MX51_ECSPI_DMA_RXT_WML_OFFSET),
-				spi_imx->base + MX51_ECSPI_DMA);
-	/*
-	 * Set these order to avoid potential RX overflow. The overflow may
-	 * happen if we enable SPI HW before starting RX DMA due to rescheduling
-	 * for another task and/or interrupt.
-	 * So RX DMA enabled first to make sure data would be read out from FIFO
-	 * ASAP. TX DMA enabled next to start filling TX FIFO with new data.
-	 * And finaly SPI HW enabled to start actual data transfer.
-	 */
-	dma_async_issue_pending(master->dma_rx);
 	dma_async_issue_pending(master->dma_tx);
-	spi_imx->devtype_data->trigger(spi_imx);
+
+	transfer_timeout = spi_imx_calculate_timeout(spi_imx, transfer->len);
 
 	/* Wait SDMA to finish the data transfer.*/
 	timeout = wait_for_completion_timeout(&spi_imx->dma_tx_completion,
-						IMX_DMA_TIMEOUT);
+						transfer_timeout);
 	if (!timeout) {
-		pr_warn("%s %s: I/O Error in DMA TX\n",
-			dev_driver_string(&master->dev),
-			dev_name(&master->dev));
+		dev_err(spi_imx->dev, "I/O Error in DMA TX\n");
 		dmaengine_terminate_all(master->dma_tx);
 		dmaengine_terminate_all(master->dma_rx);
-	} else {
-		timeout = wait_for_completion_timeout(
-				&spi_imx->dma_rx_completion, IMX_DMA_TIMEOUT);
-		if (!timeout) {
-			pr_warn("%s %s: I/O Error in DMA RX\n",
-				dev_driver_string(&master->dev),
-				dev_name(&master->dev));
-			spi_imx->devtype_data->reset(spi_imx);
-			dmaengine_terminate_all(master->dma_rx);
-		}
-		dma &= ~MX51_ECSPI_DMA_RXT_WML_MASK;
-		writel(dma |
-		       spi_imx->wml << MX51_ECSPI_DMA_RXT_WML_OFFSET,
-		       spi_imx->base + MX51_ECSPI_DMA);
+		return -ETIMEDOUT;
 	}
 
-	spi_imx->dma_finished = 1;
-	spi_imx->devtype_data->trigger(spi_imx);
-
-	if (!timeout)
-		ret = -ETIMEDOUT;
-	else
-		ret = transfer->len;
-
-	return ret;
+	timeout = wait_for_completion_timeout(&spi_imx->dma_rx_completion,
+					      transfer_timeout);
+	if (!timeout) {
+		dev_err(&master->dev, "I/O Error in DMA RX\n");
+		spi_imx->devtype_data->reset(spi_imx);
+		dmaengine_terminate_all(master->dma_rx);
+		return -ETIMEDOUT;
+	}
 
-no_dma:
-	pr_warn_once("%s %s: DMA not available, falling back to PIO\n",
-		     dev_driver_string(&master->dev),
-		     dev_name(&master->dev));
-	return -EAGAIN;
+	return transfer->len;
 }
 
 static int spi_imx_pio_transfer(struct spi_device *spi,
@@ -1039,19 +1058,12 @@ static int spi_imx_pio_transfer(struct spi_device *spi,
 static int spi_imx_transfer(struct spi_device *spi,
 				struct spi_transfer *transfer)
 {
-	int ret;
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(spi->master);
 
-	if (spi_imx->bitbang.master->can_dma &&
-	    spi_imx_can_dma(spi_imx->bitbang.master, spi, transfer)) {
-		spi_imx->usedma = true;
-		ret = spi_imx_dma_transfer(spi_imx, transfer);
-		if (ret != -EAGAIN)
-			return ret;
-	}
-	spi_imx->usedma = false;
-
-	return spi_imx_pio_transfer(spi, transfer);
+	if (spi_imx->usedma)
+		return spi_imx_dma_transfer(spi_imx, transfer);
+	else
+		return spi_imx_pio_transfer(spi, transfer);
 }
 
 static int spi_imx_setup(struct spi_device *spi)
@@ -1141,6 +1153,7 @@ static int spi_imx_probe(struct platform_device *pdev)
 
 	spi_imx = spi_master_get_devdata(master);
 	spi_imx->bitbang.master = master;
+	spi_imx->dev = &pdev->dev;
 
 	spi_imx->devtype_data = of_id ? of_id->data :
 		(struct spi_imx_devtype_data *)pdev->id_entry->driver_data;
@@ -1181,6 +1194,7 @@ static int spi_imx_probe(struct platform_device *pdev)
 		ret = PTR_ERR(spi_imx->base);
 		goto out_master_put;
 	}
+	spi_imx->base_phys = res->start;
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
@@ -1221,7 +1235,7 @@ static int spi_imx_probe(struct platform_device *pdev)
 	 * other chips.
 	 */
 	if (is_imx51_ecspi(spi_imx)) {
-		ret = spi_imx_sdma_init(&pdev->dev, spi_imx, master, res);
+		ret = spi_imx_sdma_init(&pdev->dev, spi_imx, master);
 		if (ret == -EPROBE_DEFER)
 			goto out_clk_put;
 
diff --git a/drivers/spi/spi-loopback-test.c b/drivers/spi/spi-loopback-test.c
index 894616f687b0..cf4bb36bee25 100644
--- a/drivers/spi/spi-loopback-test.c
+++ b/drivers/spi/spi-loopback-test.c
@@ -761,6 +761,7 @@ static int spi_test_run_iter(struct spi_device *spi,
 		test.iterate_transfer_mask = 1;
 
 	/* count number of transfers with tx/rx_buf != NULL */
+	rx_count = tx_count = 0;
 	for (i = 0; i < test.transfer_count; i++) {
 		if (test.transfers[i].tx_buf)
 			tx_count++;
diff --git a/drivers/spi/spi-lp8841-rtc.c b/drivers/spi/spi-lp8841-rtc.c
new file mode 100644
index 000000000000..faa577d282c0
--- /dev/null
+++ b/drivers/spi/spi-lp8841-rtc.c
@@ -0,0 +1,256 @@
+/*
+ * SPI master driver for ICP DAS LP-8841 RTC
+ *
+ * Copyright (C) 2016 Sergei Ianovich
+ *
+ * based on
+ *
+ * Dallas DS1302 RTC Support
+ * Copyright (C) 2002 David McCullough
+ * Copyright (C) 2003 - 2007 Paul Mundt
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/delay.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/spi/spi.h>
+
+#define DRIVER_NAME	"spi_lp8841_rtc"
+
+#define SPI_LP8841_RTC_CE	0x01
+#define SPI_LP8841_RTC_CLK	0x02
+#define SPI_LP8841_RTC_nWE	0x04
+#define SPI_LP8841_RTC_MOSI	0x08
+#define SPI_LP8841_RTC_MISO	0x01
+
+/*
+ * REVISIT If there is support for SPI_3WIRE and SPI_LSB_FIRST in SPI
+ * GPIO driver, this SPI driver can be replaced by a simple GPIO driver
+ * providing 3 GPIO pins.
+ */
+
+struct spi_lp8841_rtc {
+	void		*iomem;
+	unsigned long	state;
+};
+
+static inline void
+setsck(struct spi_lp8841_rtc *data, int is_on)
+{
+	if (is_on)
+		data->state |= SPI_LP8841_RTC_CLK;
+	else
+		data->state &= ~SPI_LP8841_RTC_CLK;
+	writeb(data->state, data->iomem);
+}
+
+static inline void
+setmosi(struct spi_lp8841_rtc *data, int is_on)
+{
+	if (is_on)
+		data->state |= SPI_LP8841_RTC_MOSI;
+	else
+		data->state &= ~SPI_LP8841_RTC_MOSI;
+	writeb(data->state, data->iomem);
+}
+
+static inline int
+getmiso(struct spi_lp8841_rtc *data)
+{
+	return ioread8(data->iomem) & SPI_LP8841_RTC_MISO;
+}
+
+static inline u32
+bitbang_txrx_be_cpha0_lsb(struct spi_lp8841_rtc *data,
+		unsigned usecs, unsigned cpol, unsigned flags,
+		u32 word, u8 bits)
+{
+	/* if (cpol == 0) this is SPI_MODE_0; else this is SPI_MODE_2 */
+
+	u32 shift = 32 - bits;
+	/* clock starts at inactive polarity */
+	for (; likely(bits); bits--) {
+
+		/* setup LSB (to slave) on leading edge */
+		if ((flags & SPI_MASTER_NO_TX) == 0)
+			setmosi(data, (word & 1));
+
+		usleep_range(usecs, usecs + 1);	/* T(setup) */
+
+		/* sample LSB (from slave) on trailing edge */
+		word >>= 1;
+		if ((flags & SPI_MASTER_NO_RX) == 0)
+			word |= (getmiso(data) << 31);
+
+		setsck(data, !cpol);
+		usleep_range(usecs, usecs + 1);
+
+		setsck(data, cpol);
+	}
+
+	word >>= shift;
+	return word;
+}
+
+static int
+spi_lp8841_rtc_transfer_one(struct spi_master *master,
+			    struct spi_device *spi,
+			    struct spi_transfer *t)
+{
+	struct spi_lp8841_rtc	*data = spi_master_get_devdata(master);
+	unsigned		count = t->len;
+	const u8		*tx = t->tx_buf;
+	u8			*rx = t->rx_buf;
+	u8			word = 0;
+	int			ret = 0;
+
+	if (tx) {
+		data->state &= ~SPI_LP8841_RTC_nWE;
+		writeb(data->state, data->iomem);
+		while (likely(count > 0)) {
+			word = *tx++;
+			bitbang_txrx_be_cpha0_lsb(data, 1, 0,
+					SPI_MASTER_NO_RX, word, 8);
+			count--;
+		}
+	} else if (rx) {
+		data->state |= SPI_LP8841_RTC_nWE;
+		writeb(data->state, data->iomem);
+		while (likely(count > 0)) {
+			word = bitbang_txrx_be_cpha0_lsb(data, 1, 0,
+					SPI_MASTER_NO_TX, word, 8);
+			*rx++ = word;
+			count--;
+		}
+	} else {
+		ret = -EINVAL;
+	}
+
+	spi_finalize_current_transfer(master);
+
+	return ret;
+}
+
+static void
+spi_lp8841_rtc_set_cs(struct spi_device *spi, bool enable)
+{
+	struct spi_lp8841_rtc *data = spi_master_get_devdata(spi->master);
+
+	data->state = 0;
+	writeb(data->state, data->iomem);
+	if (enable) {
+		usleep_range(4, 5);
+		data->state |= SPI_LP8841_RTC_CE;
+		writeb(data->state, data->iomem);
+		usleep_range(4, 5);
+	}
+}
+
+static int
+spi_lp8841_rtc_setup(struct spi_device *spi)
+{
+	if ((spi->mode & SPI_CS_HIGH) == 0) {
+		dev_err(&spi->dev, "unsupported active low chip select\n");
+		return -EINVAL;
+	}
+
+	if ((spi->mode & SPI_LSB_FIRST) == 0) {
+		dev_err(&spi->dev, "unsupported MSB first mode\n");
+		return -EINVAL;
+	}
+
+	if ((spi->mode & SPI_3WIRE) == 0) {
+		dev_err(&spi->dev, "unsupported wiring. 3 wires required\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id spi_lp8841_rtc_dt_ids[] = {
+	{ .compatible = "icpdas,lp8841-spi-rtc" },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, spi_lp8841_rtc_dt_ids);
+#endif
+
+static int
+spi_lp8841_rtc_probe(struct platform_device *pdev)
+{
+	int				ret;
+	struct spi_master		*master;
+	struct spi_lp8841_rtc		*data;
+	void				*iomem;
+
+	master = spi_alloc_master(&pdev->dev, sizeof(*data));
+	if (!master)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, master);
+
+	master->flags = SPI_MASTER_HALF_DUPLEX;
+	master->mode_bits = SPI_CS_HIGH | SPI_3WIRE | SPI_LSB_FIRST;
+
+	master->bus_num = pdev->id;
+	master->num_chipselect = 1;
+	master->setup = spi_lp8841_rtc_setup;
+	master->set_cs = spi_lp8841_rtc_set_cs;
+	master->transfer_one = spi_lp8841_rtc_transfer_one;
+	master->bits_per_word_mask = SPI_BPW_MASK(8);
+#ifdef CONFIG_OF
+	master->dev.of_node = pdev->dev.of_node;
+#endif
+
+	data = spi_master_get_devdata(master);
+
+	iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	data->iomem = devm_ioremap_resource(&pdev->dev, iomem);
+	ret = PTR_ERR_OR_ZERO(data->iomem);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to get IO address\n");
+		goto err_put_master;
+	}
+
+	/* register with the SPI framework */
+	ret = devm_spi_register_master(&pdev->dev, master);
+	if (ret) {
+		dev_err(&pdev->dev, "cannot register spi master\n");
+		goto err_put_master;
+	}
+
+	return ret;
+
+
+err_put_master:
+	spi_master_put(master);
+
+	return ret;
+}
+
+MODULE_ALIAS("platform:" DRIVER_NAME);
+
+static struct platform_driver spi_lp8841_rtc_driver = {
+	.driver = {
+		.name	= DRIVER_NAME,
+		.of_match_table = of_match_ptr(spi_lp8841_rtc_dt_ids),
+	},
+	.probe		= spi_lp8841_rtc_probe,
+};
+module_platform_driver(spi_lp8841_rtc_driver);
+
+MODULE_DESCRIPTION("SPI master driver for ICP DAS LP-8841 RTC");
+MODULE_AUTHOR("Sergei Ianovich");
+MODULE_LICENSE("GPL");
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 7273820275e9..0caa3c8bef46 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -1490,6 +1490,8 @@ static int omap2_mcspi_probe(struct platform_device *pdev)
 	return status;
 
 disable_pm:
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
+	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 free_master:
 	spi_master_put(master);
@@ -1501,6 +1503,7 @@ static int omap2_mcspi_remove(struct platform_device *pdev)
 	struct spi_master *master = platform_get_drvdata(pdev);
 	struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
 
+	pm_runtime_dont_use_autosuspend(mcspi->dev);
 	pm_runtime_put_sync(mcspi->dev);
 	pm_runtime_disable(&pdev->dev);
 
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index 5e5fd77e2711..f7f7ba17b40e 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -346,13 +346,6 @@ struct vendor_data {
  * @clk: outgoing clock "SPICLK" for the SPI bus
  * @master: SPI framework hookup
  * @master_info: controller-specific data from machine setup
- * @kworker: thread struct for message pump
- * @kworker_task: pointer to task for message pump kworker thread
- * @pump_messages: work struct for scheduling work to the message pump
- * @queue_lock: spinlock to syncronise access to message queue
- * @queue: message queue
- * @busy: message pump is busy
- * @running: message pump is running
  * @pump_transfers: Tasklet used in Interrupt Transfer mode
  * @cur_msg: Pointer to current spi_message being processed
  * @cur_transfer: Pointer to current spi_transfer
diff --git a/drivers/spi/spi-pxa2xx-dma.c b/drivers/spi/spi-pxa2xx-dma.c
index bd8b369a343c..365fc22c3572 100644
--- a/drivers/spi/spi-pxa2xx-dma.c
+++ b/drivers/spi/spi-pxa2xx-dma.c
@@ -254,8 +254,8 @@ irqreturn_t pxa2xx_spi_dma_transfer(struct driver_data *drv_data)
 	if (status & SSSR_ROR) {
 		dev_err(&drv_data->pdev->dev, "FIFO overrun\n");
 
-		dmaengine_terminate_all(drv_data->rx_chan);
-		dmaengine_terminate_all(drv_data->tx_chan);
+		dmaengine_terminate_async(drv_data->rx_chan);
+		dmaengine_terminate_async(drv_data->tx_chan);
 
 		pxa2xx_spi_dma_transfer_complete(drv_data, true);
 		return IRQ_HANDLED;
@@ -331,13 +331,13 @@ int pxa2xx_spi_dma_setup(struct driver_data *drv_data)
 void pxa2xx_spi_dma_release(struct driver_data *drv_data)
 {
 	if (drv_data->rx_chan) {
-		dmaengine_terminate_all(drv_data->rx_chan);
+		dmaengine_terminate_sync(drv_data->rx_chan);
 		dma_release_channel(drv_data->rx_chan);
 		sg_free_table(&drv_data->rx_sgt);
 		drv_data->rx_chan = NULL;
 	}
 	if (drv_data->tx_chan) {
-		dmaengine_terminate_all(drv_data->tx_chan);
+		dmaengine_terminate_sync(drv_data->tx_chan);
 		dma_release_channel(drv_data->tx_chan);
 		sg_free_table(&drv_data->tx_sgt);
 		drv_data->tx_chan = NULL;
diff --git a/drivers/spi/spi-pxa2xx-pci.c b/drivers/spi/spi-pxa2xx-pci.c
index d19d7f28aecb..520ed1dd5780 100644
--- a/drivers/spi/spi-pxa2xx-pci.c
+++ b/drivers/spi/spi-pxa2xx-pci.c
@@ -19,6 +19,7 @@ enum {
 	PORT_BSW1,
 	PORT_BSW2,
 	PORT_QUARK_X1000,
+	PORT_LPT,
 };
 
 struct pxa_spi_info {
@@ -42,6 +43,9 @@ static struct dw_dma_slave bsw1_rx_param = { .src_id = 7 };
 static struct dw_dma_slave bsw2_tx_param = { .dst_id = 8 };
 static struct dw_dma_slave bsw2_rx_param = { .src_id = 9 };
 
+static struct dw_dma_slave lpt_tx_param = { .dst_id = 0 };
+static struct dw_dma_slave lpt_rx_param = { .src_id = 1 };
+
 static bool lpss_dma_filter(struct dma_chan *chan, void *param)
 {
 	struct dw_dma_slave *dws = param;
@@ -98,6 +102,14 @@ static struct pxa_spi_info spi_info_configs[] = {
 		.num_chipselect = 1,
 		.max_clk_rate = 50000000,
 	},
+	[PORT_LPT] = {
+		.type = LPSS_LPT_SSP,
+		.port_id = 0,
+		.num_chipselect = 1,
+		.max_clk_rate = 50000000,
+		.tx_param = &lpt_tx_param,
+		.rx_param = &lpt_rx_param,
+	},
 };
 
 static int pxa2xx_spi_pci_probe(struct pci_dev *dev,
@@ -202,6 +214,7 @@ static const struct pci_device_id pxa2xx_spi_pci_devices[] = {
 	{ PCI_VDEVICE(INTEL, 0x228e), PORT_BSW0 },
 	{ PCI_VDEVICE(INTEL, 0x2290), PORT_BSW1 },
 	{ PCI_VDEVICE(INTEL, 0x22ac), PORT_BSW2 },
+	{ PCI_VDEVICE(INTEL, 0x9ce6), PORT_LPT },
 	{ },
 };
 MODULE_DEVICE_TABLE(pci, pxa2xx_spi_pci_devices);
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index ab9914ad8365..85e59a406a4c 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -65,8 +65,6 @@ MODULE_ALIAS("platform:pxa2xx-spi");
 #define LPSS_GENERAL_REG_RXTO_HOLDOFF_DISABLE	BIT(24)
 #define LPSS_CS_CONTROL_SW_MODE			BIT(0)
 #define LPSS_CS_CONTROL_CS_HIGH			BIT(1)
-#define LPSS_CS_CONTROL_CS_SEL_SHIFT		8
-#define LPSS_CS_CONTROL_CS_SEL_MASK		(3 << LPSS_CS_CONTROL_CS_SEL_SHIFT)
 #define LPSS_CAPS_CS_EN_SHIFT			9
 #define LPSS_CAPS_CS_EN_MASK			(0xf << LPSS_CAPS_CS_EN_SHIFT)
 
@@ -82,6 +80,10 @@ struct lpss_config {
 	u32 rx_threshold;
 	u32 tx_threshold_lo;
 	u32 tx_threshold_hi;
+	/* Chip select control */
+	unsigned cs_sel_shift;
+	unsigned cs_sel_mask;
+	unsigned cs_num;
 };
 
 /* Keep these sorted with enum pxa_ssp_type */
@@ -106,6 +108,19 @@ static const struct lpss_config lpss_platforms[] = {
 		.tx_threshold_lo = 160,
 		.tx_threshold_hi = 224,
 	},
+	{	/* LPSS_BSW_SSP */
+		.offset = 0x400,
+		.reg_general = 0x08,
+		.reg_ssp = 0x0c,
+		.reg_cs_ctrl = 0x18,
+		.reg_capabilities = -1,
+		.rx_threshold = 64,
+		.tx_threshold_lo = 160,
+		.tx_threshold_hi = 224,
+		.cs_sel_shift = 2,
+		.cs_sel_mask = 1 << 2,
+		.cs_num = 2,
+	},
 	{	/* LPSS_SPT_SSP */
 		.offset = 0x200,
 		.reg_general = -1,
@@ -125,6 +140,8 @@ static const struct lpss_config lpss_platforms[] = {
 		.rx_threshold = 1,
 		.tx_threshold_lo = 16,
 		.tx_threshold_hi = 48,
+		.cs_sel_shift = 8,
+		.cs_sel_mask = 3 << 8,
 	},
 };
 
@@ -139,6 +156,7 @@ static bool is_lpss_ssp(const struct driver_data *drv_data)
 	switch (drv_data->ssp_type) {
 	case LPSS_LPT_SSP:
 	case LPSS_BYT_SSP:
+	case LPSS_BSW_SSP:
 	case LPSS_SPT_SSP:
 	case LPSS_BXT_SSP:
 		return true;
@@ -288,37 +306,50 @@ static void lpss_ssp_setup(struct driver_data *drv_data)
 	}
 }
 
+static void lpss_ssp_select_cs(struct driver_data *drv_data,
+			       const struct lpss_config *config)
+{
+	u32 value, cs;
+
+	if (!config->cs_sel_mask)
+		return;
+
+	value = __lpss_ssp_read_priv(drv_data, config->reg_cs_ctrl);
+
+	cs = drv_data->cur_msg->spi->chip_select;
+	cs <<= config->cs_sel_shift;
+	if (cs != (value & config->cs_sel_mask)) {
+		/*
+		 * When switching another chip select output active the
+		 * output must be selected first and wait 2 ssp_clk cycles
+		 * before changing state to active. Otherwise a short
+		 * glitch will occur on the previous chip select since
+		 * output select is latched but state control is not.
+		 */
+		value &= ~config->cs_sel_mask;
+		value |= cs;
+		__lpss_ssp_write_priv(drv_data,
+				      config->reg_cs_ctrl, value);
+		ndelay(1000000000 /
+		       (drv_data->master->max_speed_hz / 2));
+	}
+}
+
 static void lpss_ssp_cs_control(struct driver_data *drv_data, bool enable)
 {
 	const struct lpss_config *config;
-	u32 value, cs;
+	u32 value;
 
 	config = lpss_get_config(drv_data);
 
+	if (enable)
+		lpss_ssp_select_cs(drv_data, config);
+
 	value = __lpss_ssp_read_priv(drv_data, config->reg_cs_ctrl);
-	if (enable) {
-		cs = drv_data->cur_msg->spi->chip_select;
-		cs <<= LPSS_CS_CONTROL_CS_SEL_SHIFT;
-		if (cs != (value & LPSS_CS_CONTROL_CS_SEL_MASK)) {
-			/*
-			 * When switching another chip select output active
-			 * the output must be selected first and wait 2 ssp_clk
-			 * cycles before changing state to active. Otherwise
-			 * a short glitch will occur on the previous chip
-			 * select since output select is latched but state
-			 * control is not.
-			 */
-			value &= ~LPSS_CS_CONTROL_CS_SEL_MASK;
-			value |= cs;
-			__lpss_ssp_write_priv(drv_data,
-					      config->reg_cs_ctrl, value);
-			ndelay(1000000000 /
-			       (drv_data->master->max_speed_hz / 2));
-		}
+	if (enable)
 		value &= ~LPSS_CS_CONTROL_CS_HIGH;
-	} else {
+	else
 		value |= LPSS_CS_CONTROL_CS_HIGH;
-	}
 	__lpss_ssp_write_priv(drv_data, config->reg_cs_ctrl, value);
 }
 
@@ -496,6 +527,7 @@ static void giveback(struct driver_data *drv_data)
 {
 	struct spi_transfer* last_transfer;
 	struct spi_message *msg;
+	unsigned long timeout;
 
 	msg = drv_data->cur_msg;
 	drv_data->cur_msg = NULL;
@@ -508,6 +540,12 @@ static void giveback(struct driver_data *drv_data)
 	if (last_transfer->delay_usecs)
 		udelay(last_transfer->delay_usecs);
 
+	/* Wait until SSP becomes idle before deasserting the CS */
+	timeout = jiffies + msecs_to_jiffies(10);
+	while (pxa2xx_spi_read(drv_data, SSSR) & SSSR_BSY &&
+	       !time_after(jiffies, timeout))
+		cpu_relax();
+
 	/* Drop chip select UNLESS cs_change is true or we are returning
 	 * a message with an error, or next message is for another chip
 	 */
@@ -572,7 +610,7 @@ static void int_error_stop(struct driver_data *drv_data, const char* msg)
 
 static void int_transfer_complete(struct driver_data *drv_data)
 {
-	/* Stop SSP */
+	/* Clear and disable interrupts */
 	write_SSSR_CS(drv_data, drv_data->clear_sr);
 	reset_sccr1(drv_data);
 	if (!pxa25x_ssp_comp(drv_data))
@@ -957,8 +995,6 @@ static void pump_transfers(unsigned long data)
 	drv_data->tx_end = drv_data->tx + transfer->len;
 	drv_data->rx = transfer->rx_buf;
 	drv_data->rx_end = drv_data->rx + transfer->len;
-	drv_data->rx_dma = transfer->rx_dma;
-	drv_data->tx_dma = transfer->tx_dma;
 	drv_data->len = transfer->len;
 	drv_data->write = drv_data->tx ? chip->write : null_writer;
 	drv_data->read = drv_data->rx ? chip->read : null_reader;
@@ -1001,19 +1037,6 @@ static void pump_transfers(unsigned long data)
 					     "pump_transfers: DMA burst size reduced to match bits_per_word\n");
 	}
 
-	/* NOTE:  PXA25x_SSP _could_ use external clocking ... */
-	cr0 = pxa2xx_configure_sscr0(drv_data, clk_div, bits);
-	if (!pxa25x_ssp_comp(drv_data))
-		dev_dbg(&message->spi->dev, "%u Hz actual, %s\n",
-			drv_data->master->max_speed_hz
-				/ (1 + ((cr0 & SSCR0_SCR(0xfff)) >> 8)),
-			chip->enable_dma ? "DMA" : "PIO");
-	else
-		dev_dbg(&message->spi->dev, "%u Hz actual, %s\n",
-			drv_data->master->max_speed_hz / 2
-				/ (1 + ((cr0 & SSCR0_SCR(0x0ff)) >> 8)),
-			chip->enable_dma ? "DMA" : "PIO");
-
 	message->state = RUNNING_STATE;
 
 	drv_data->dma_mapped = 0;
@@ -1040,6 +1063,19 @@ static void pump_transfers(unsigned long data)
 		write_SSSR_CS(drv_data, drv_data->clear_sr);
 	}
 
+	/* NOTE:  PXA25x_SSP _could_ use external clocking ... */
+	cr0 = pxa2xx_configure_sscr0(drv_data, clk_div, bits);
+	if (!pxa25x_ssp_comp(drv_data))
+		dev_dbg(&message->spi->dev, "%u Hz actual, %s\n",
+			drv_data->master->max_speed_hz
+				/ (1 + ((cr0 & SSCR0_SCR(0xfff)) >> 8)),
+			drv_data->dma_mapped ? "DMA" : "PIO");
+	else
+		dev_dbg(&message->spi->dev, "%u Hz actual, %s\n",
+			drv_data->master->max_speed_hz / 2
+				/ (1 + ((cr0 & SSCR0_SCR(0x0ff)) >> 8)),
+			drv_data->dma_mapped ? "DMA" : "PIO");
+
 	if (is_lpss_ssp(drv_data)) {
 		if ((pxa2xx_spi_read(drv_data, SSIRF) & 0xff)
 		    != chip->lpss_rx_threshold)
@@ -1166,6 +1202,7 @@ static int setup(struct spi_device *spi)
 		break;
 	case LPSS_LPT_SSP:
 	case LPSS_BYT_SSP:
+	case LPSS_BSW_SSP:
 	case LPSS_SPT_SSP:
 	case LPSS_BXT_SSP:
 		config = lpss_get_config(drv_data);
@@ -1313,7 +1350,7 @@ static const struct acpi_device_id pxa2xx_spi_acpi_match[] = {
 	{ "INT3430", LPSS_LPT_SSP },
 	{ "INT3431", LPSS_LPT_SSP },
 	{ "80860F0E", LPSS_BYT_SSP },
-	{ "8086228E", LPSS_BYT_SSP },
+	{ "8086228E", LPSS_BSW_SSP },
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, pxa2xx_spi_acpi_match);
@@ -1347,10 +1384,14 @@ static const struct pci_device_id pxa2xx_spi_pci_compound_match[] = {
 	/* SPT-H */
 	{ PCI_VDEVICE(INTEL, 0xa129), LPSS_SPT_SSP },
 	{ PCI_VDEVICE(INTEL, 0xa12a), LPSS_SPT_SSP },
-	/* BXT */
+	/* BXT A-Step */
 	{ PCI_VDEVICE(INTEL, 0x0ac2), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x0ac4), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x0ac6), LPSS_BXT_SSP },
+	/* BXT B-Step */
+	{ PCI_VDEVICE(INTEL, 0x1ac2), LPSS_BXT_SSP },
+	{ PCI_VDEVICE(INTEL, 0x1ac4), LPSS_BXT_SSP },
+	{ PCI_VDEVICE(INTEL, 0x1ac6), LPSS_BXT_SSP },
 	/* APL */
 	{ PCI_VDEVICE(INTEL, 0x5ac2), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x5ac4), LPSS_BXT_SSP },
@@ -1438,6 +1479,29 @@ pxa2xx_spi_init_pdata(struct platform_device *pdev)
 }
 #endif
 
+static int pxa2xx_spi_fw_translate_cs(struct spi_master *master, unsigned cs)
+{
+	struct driver_data *drv_data = spi_master_get_devdata(master);
+
+	if (has_acpi_companion(&drv_data->pdev->dev)) {
+		switch (drv_data->ssp_type) {
+		/*
+		 * For Atoms the ACPI DeviceSelection used by the Windows
+		 * driver starts from 1 instead of 0 so translate it here
+		 * to match what Linux expects.
+		 */
+		case LPSS_BYT_SSP:
+		case LPSS_BSW_SSP:
+			return cs - 1;
+
+		default:
+			break;
+		}
+	}
+
+	return cs;
+}
+
 static int pxa2xx_spi_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -1490,6 +1554,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 	master->setup = setup;
 	master->transfer_one_message = pxa2xx_spi_transfer_one_message;
 	master->unprepare_transfer_hardware = pxa2xx_spi_unprepare_transfer;
+	master->fw_translate_cs = pxa2xx_spi_fw_translate_cs;
 	master->auto_runtime_pm = true;
 
 	drv_data->ssp_type = ssp->type;
@@ -1576,6 +1641,8 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 			tmp &= LPSS_CAPS_CS_EN_MASK;
 			tmp >>= LPSS_CAPS_CS_EN_SHIFT;
 			platform_info->num_chipselect = ffz(tmp);
+		} else if (config->cs_num) {
+			platform_info->num_chipselect = config->cs_num;
 		}
 	}
 	master->num_chipselect = platform_info->num_chipselect;
diff --git a/drivers/spi/spi-pxa2xx.h b/drivers/spi/spi-pxa2xx.h
index 58efa98313aa..a1ef88948144 100644
--- a/drivers/spi/spi-pxa2xx.h
+++ b/drivers/spi/spi-pxa2xx.h
@@ -69,8 +69,6 @@ struct driver_data {
 	void *rx;
 	void *rx_end;
 	int dma_mapped;
-	dma_addr_t rx_dma;
-	dma_addr_t tx_dma;
 	size_t rx_map_len;
 	size_t tx_map_len;
 	u8 n_bytes;
@@ -147,20 +145,9 @@ static inline void write_SSSR_CS(struct driver_data *drv_data, u32 val)
 extern int pxa2xx_spi_flush(struct driver_data *drv_data);
 extern void *pxa2xx_spi_next_transfer(struct driver_data *drv_data);
 
-/*
- * Select the right DMA implementation.
- */
-#if defined(CONFIG_SPI_PXA2XX_DMA)
-#define SPI_PXA2XX_USE_DMA	1
 #define MAX_DMA_LEN		SZ_64K
 #define DEFAULT_DMA_CR1		(SSCR1_TSRE | SSCR1_RSRE | SSCR1_TRAIL)
-#else
-#undef SPI_PXA2XX_USE_DMA
-#define MAX_DMA_LEN		0
-#define DEFAULT_DMA_CR1		0
-#endif
 
-#ifdef SPI_PXA2XX_USE_DMA
 extern bool pxa2xx_spi_dma_is_possible(size_t len);
 extern int pxa2xx_spi_map_dma_buffers(struct driver_data *drv_data);
 extern irqreturn_t pxa2xx_spi_dma_transfer(struct driver_data *drv_data);
@@ -173,29 +160,5 @@ extern int pxa2xx_spi_set_dma_burst_and_threshold(struct chip_data *chip,
 						  u8 bits_per_word,
 						  u32 *burst_code,
 						  u32 *threshold);
-#else
-static inline bool pxa2xx_spi_dma_is_possible(size_t len) { return false; }
-static inline int pxa2xx_spi_map_dma_buffers(struct driver_data *drv_data)
-{
-	return 0;
-}
-#define pxa2xx_spi_dma_transfer NULL
-static inline void pxa2xx_spi_dma_prepare(struct driver_data *drv_data,
-					  u32 dma_burst) {}
-static inline void pxa2xx_spi_dma_start(struct driver_data *drv_data) {}
-static inline int pxa2xx_spi_dma_setup(struct driver_data *drv_data)
-{
-	return 0;
-}
-static inline void pxa2xx_spi_dma_release(struct driver_data *drv_data) {}
-static inline int pxa2xx_spi_set_dma_burst_and_threshold(struct chip_data *chip,
-							 struct spi_device *spi,
-							 u8 bits_per_word,
-							 u32 *burst_code,
-							 u32 *threshold)
-{
-	return -ENODEV;
-}
-#endif
 
 #endif /* SPI_PXA2XX_H */
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index 79a8bc4f6cec..26e2688c104e 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -13,20 +13,14 @@
  *
  */
 
-#include <linux/init.h>
-#include <linux/module.h>
 #include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
+#include <linux/dmaengine.h>
+#include <linux/module.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
-#include <linux/slab.h>
 #include <linux/spi/spi.h>
-#include <linux/scatterlist.h>
-#include <linux/of.h>
 #include <linux/pm_runtime.h>
-#include <linux/io.h>
-#include <linux/dmaengine.h>
+#include <linux/scatterlist.h>
 
 #define DRIVER_NAME "rockchip-spi"
 
@@ -179,7 +173,7 @@ struct rockchip_spi {
 	u8 tmode;
 	u8 bpw;
 	u8 n_bytes;
-	u8 rsd_nsecs;
+	u32 rsd_nsecs;
 	unsigned len;
 	u32 speed;
 
@@ -192,8 +186,6 @@ struct rockchip_spi {
 	/* protect state */
 	spinlock_t lock;
 
-	struct completion xfer_completion;
-
 	u32 use_dma;
 	struct sg_table tx_sg;
 	struct sg_table rx_sg;
@@ -265,7 +257,10 @@ static inline u32 rx_max(struct rockchip_spi *rs)
 static void rockchip_spi_set_cs(struct spi_device *spi, bool enable)
 {
 	u32 ser;
-	struct rockchip_spi *rs = spi_master_get_devdata(spi->master);
+	struct spi_master *master = spi->master;
+	struct rockchip_spi *rs = spi_master_get_devdata(master);
+
+	pm_runtime_get_sync(rs->dev);
 
 	ser = readl_relaxed(rs->regs + ROCKCHIP_SPI_SER) & SER_MASK;
 
@@ -290,6 +285,8 @@ static void rockchip_spi_set_cs(struct spi_device *spi, bool enable)
 		ser &= ~(1 << spi->chip_select);
 
 	writel_relaxed(ser, rs->regs + ROCKCHIP_SPI_SER);
+
+	pm_runtime_put_sync(rs->dev);
 }
 
 static int rockchip_spi_prepare_message(struct spi_master *master,
@@ -319,12 +316,12 @@ static void rockchip_spi_handle_err(struct spi_master *master,
 	 */
 	if (rs->use_dma) {
 		if (rs->state & RXBUSY) {
-			dmaengine_terminate_all(rs->dma_rx.ch);
+			dmaengine_terminate_async(rs->dma_rx.ch);
 			flush_fifo(rs);
 		}
 
 		if (rs->state & TXBUSY)
-			dmaengine_terminate_all(rs->dma_tx.ch);
+			dmaengine_terminate_async(rs->dma_tx.ch);
 	}
 
 	spin_unlock_irqrestore(&rs->lock, flags);
@@ -433,7 +430,7 @@ static void rockchip_spi_dma_txcb(void *data)
 	spin_unlock_irqrestore(&rs->lock, flags);
 }
 
-static void rockchip_spi_prepare_dma(struct rockchip_spi *rs)
+static int rockchip_spi_prepare_dma(struct rockchip_spi *rs)
 {
 	unsigned long flags;
 	struct dma_slave_config rxconf, txconf;
@@ -456,6 +453,8 @@ static void rockchip_spi_prepare_dma(struct rockchip_spi *rs)
 				rs->dma_rx.ch,
 				rs->rx_sg.sgl, rs->rx_sg.nents,
 				rs->dma_rx.direction, DMA_PREP_INTERRUPT);
+		if (!rxdesc)
+			return -EINVAL;
 
 		rxdesc->callback = rockchip_spi_dma_rxcb;
 		rxdesc->callback_param = rs;
@@ -473,6 +472,11 @@ static void rockchip_spi_prepare_dma(struct rockchip_spi *rs)
 				rs->dma_tx.ch,
 				rs->tx_sg.sgl, rs->tx_sg.nents,
 				rs->dma_tx.direction, DMA_PREP_INTERRUPT);
+		if (!txdesc) {
+			if (rxdesc)
+				dmaengine_terminate_sync(rs->dma_rx.ch);
+			return -EINVAL;
+		}
 
 		txdesc->callback = rockchip_spi_dma_txcb;
 		txdesc->callback_param = rs;
@@ -494,6 +498,8 @@ static void rockchip_spi_prepare_dma(struct rockchip_spi *rs)
 		dmaengine_submit(txdesc);
 		dma_async_issue_pending(rs->dma_tx.ch);
 	}
+
+	return 0;
 }
 
 static void rockchip_spi_config(struct rockchip_spi *rs)
@@ -503,7 +509,8 @@ static void rockchip_spi_config(struct rockchip_spi *rs)
 	int rsd = 0;
 
 	u32 cr0 = (CR0_BHT_8BIT << CR0_BHT_OFFSET)
-		| (CR0_SSD_ONE << CR0_SSD_OFFSET);
+		| (CR0_SSD_ONE << CR0_SSD_OFFSET)
+		| (CR0_EM_BIG << CR0_EM_OFFSET);
 
 	cr0 |= (rs->n_bytes << CR0_DFS_OFFSET);
 	cr0 |= ((rs->mode & 0x3) << CR0_SCPH_OFFSET);
@@ -606,12 +613,12 @@ static int rockchip_spi_transfer_one(
 	if (rs->use_dma) {
 		if (rs->tmode == CR0_XFM_RO) {
 			/* rx: dma must be prepared first */
-			rockchip_spi_prepare_dma(rs);
+			ret = rockchip_spi_prepare_dma(rs);
 			spi_enable_chip(rs, 1);
 		} else {
 			/* tx or tr: spi must be enabled first */
 			spi_enable_chip(rs, 1);
-			rockchip_spi_prepare_dma(rs);
+			ret = rockchip_spi_prepare_dma(rs);
 		}
 	} else {
 		spi_enable_chip(rs, 1);
@@ -717,8 +724,14 @@ static int rockchip_spi_probe(struct platform_device *pdev)
 	master->handle_err = rockchip_spi_handle_err;
 
 	rs->dma_tx.ch = dma_request_slave_channel(rs->dev, "tx");
-	if (!rs->dma_tx.ch)
+	if (IS_ERR_OR_NULL(rs->dma_tx.ch)) {
+		/* Check tx to see if we need defer probing driver */
+		if (PTR_ERR(rs->dma_tx.ch) == -EPROBE_DEFER) {
+			ret = -EPROBE_DEFER;
+			goto err_get_fifo_len;
+		}
 		dev_warn(rs->dev, "Failed to request TX DMA channel\n");
+	}
 
 	rs->dma_rx.ch = dma_request_slave_channel(rs->dev, "rx");
 	if (!rs->dma_rx.ch) {
@@ -749,6 +762,7 @@ static int rockchip_spi_probe(struct platform_device *pdev)
 	return 0;
 
 err_register_master:
+	pm_runtime_disable(&pdev->dev);
 	if (rs->dma_tx.ch)
 		dma_release_channel(rs->dma_tx.ch);
 	if (rs->dma_rx.ch)
@@ -778,6 +792,8 @@ static int rockchip_spi_remove(struct platform_device *pdev)
 	if (rs->dma_rx.ch)
 		dma_release_channel(rs->dma_rx.ch);
 
+	spi_master_put(master);
+
 	return 0;
 }
 
@@ -868,6 +884,7 @@ static const struct of_device_id rockchip_spi_dt_match[] = {
 	{ .compatible = "rockchip,rk3066-spi", },
 	{ .compatible = "rockchip,rk3188-spi", },
 	{ .compatible = "rockchip,rk3288-spi", },
+	{ .compatible = "rockchip,rk3399-spi", },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, rockchip_spi_dt_match);
diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c
index 64318fcfacf2..eac3c960b2de 100644
--- a/drivers/spi/spi-ti-qspi.c
+++ b/drivers/spi/spi-ti-qspi.c
@@ -31,6 +31,8 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/pinctrl/consumer.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 #include <linux/spi/spi.h>
 
@@ -44,8 +46,9 @@ struct ti_qspi {
 
 	struct spi_master	*master;
 	void __iomem            *base;
-	void __iomem            *ctrl_base;
 	void __iomem            *mmap_base;
+	struct regmap		*ctrl_base;
+	unsigned int		ctrl_reg;
 	struct clk		*fclk;
 	struct device           *dev;
 
@@ -55,7 +58,7 @@ struct ti_qspi {
 	u32 cmd;
 	u32 dc;
 
-	bool ctrl_mod;
+	bool mmap_enabled;
 };
 
 #define QSPI_PID			(0x0)
@@ -65,11 +68,8 @@ struct ti_qspi {
 #define QSPI_SPI_CMD_REG		(0x48)
 #define QSPI_SPI_STATUS_REG		(0x4c)
 #define QSPI_SPI_DATA_REG		(0x50)
-#define QSPI_SPI_SETUP0_REG		(0x54)
+#define QSPI_SPI_SETUP_REG(n)		((0x54 + 4 * n))
 #define QSPI_SPI_SWITCH_REG		(0x64)
-#define QSPI_SPI_SETUP1_REG		(0x58)
-#define QSPI_SPI_SETUP2_REG		(0x5c)
-#define QSPI_SPI_SETUP3_REG		(0x60)
 #define QSPI_SPI_DATA_REG_1		(0x68)
 #define QSPI_SPI_DATA_REG_2		(0x6c)
 #define QSPI_SPI_DATA_REG_3		(0x70)
@@ -109,6 +109,17 @@ struct ti_qspi {
 
 #define QSPI_AUTOSUSPEND_TIMEOUT         2000
 
+#define MEM_CS_EN(n)			((n + 1) << 8)
+#define MEM_CS_MASK			(7 << 8)
+
+#define MM_SWITCH			0x1
+
+#define QSPI_SETUP_RD_NORMAL		(0x0 << 12)
+#define QSPI_SETUP_RD_DUAL		(0x1 << 12)
+#define QSPI_SETUP_RD_QUAD		(0x3 << 12)
+#define QSPI_SETUP_ADDR_SHIFT		8
+#define QSPI_SETUP_DUMMY_SHIFT		10
+
 static inline unsigned long ti_qspi_read(struct ti_qspi *qspi,
 		unsigned long reg)
 {
@@ -366,6 +377,72 @@ static int qspi_transfer_msg(struct ti_qspi *qspi, struct spi_transfer *t)
 	return 0;
 }
 
+static void ti_qspi_enable_memory_map(struct spi_device *spi)
+{
+	struct ti_qspi  *qspi = spi_master_get_devdata(spi->master);
+
+	ti_qspi_write(qspi, MM_SWITCH, QSPI_SPI_SWITCH_REG);
+	if (qspi->ctrl_base) {
+		regmap_update_bits(qspi->ctrl_base, qspi->ctrl_reg,
+				   MEM_CS_EN(spi->chip_select),
+				   MEM_CS_MASK);
+	}
+	qspi->mmap_enabled = true;
+}
+
+static void ti_qspi_disable_memory_map(struct spi_device *spi)
+{
+	struct ti_qspi  *qspi = spi_master_get_devdata(spi->master);
+
+	ti_qspi_write(qspi, 0, QSPI_SPI_SWITCH_REG);
+	if (qspi->ctrl_base)
+		regmap_update_bits(qspi->ctrl_base, qspi->ctrl_reg,
+				   0, MEM_CS_MASK);
+	qspi->mmap_enabled = false;
+}
+
+static void ti_qspi_setup_mmap_read(struct spi_device *spi,
+				    struct spi_flash_read_message *msg)
+{
+	struct ti_qspi  *qspi = spi_master_get_devdata(spi->master);
+	u32 memval = msg->read_opcode;
+
+	switch (msg->data_nbits) {
+	case SPI_NBITS_QUAD:
+		memval |= QSPI_SETUP_RD_QUAD;
+		break;
+	case SPI_NBITS_DUAL:
+		memval |= QSPI_SETUP_RD_DUAL;
+		break;
+	default:
+		memval |= QSPI_SETUP_RD_NORMAL;
+		break;
+	}
+	memval |= ((msg->addr_width - 1) << QSPI_SETUP_ADDR_SHIFT |
+		   msg->dummy_bytes << QSPI_SETUP_DUMMY_SHIFT);
+	ti_qspi_write(qspi, memval,
+		      QSPI_SPI_SETUP_REG(spi->chip_select));
+}
+
+static int ti_qspi_spi_flash_read(struct  spi_device *spi,
+				  struct spi_flash_read_message *msg)
+{
+	struct ti_qspi *qspi = spi_master_get_devdata(spi->master);
+	int ret = 0;
+
+	mutex_lock(&qspi->list_lock);
+
+	if (!qspi->mmap_enabled)
+		ti_qspi_enable_memory_map(spi);
+	ti_qspi_setup_mmap_read(spi, msg);
+	memcpy_fromio(msg->buf, qspi->mmap_base + msg->from, msg->len);
+	msg->retlen = msg->len;
+
+	mutex_unlock(&qspi->list_lock);
+
+	return ret;
+}
+
 static int ti_qspi_start_transfer_one(struct spi_master *master,
 		struct spi_message *m)
 {
@@ -398,6 +475,9 @@ static int ti_qspi_start_transfer_one(struct spi_master *master,
 
 	mutex_lock(&qspi->list_lock);
 
+	if (qspi->mmap_enabled)
+		ti_qspi_disable_memory_map(spi);
+
 	list_for_each_entry(t, &m->transfers, transfer_list) {
 		qspi->cmd |= QSPI_WLEN(t->bits_per_word);
 
@@ -441,7 +521,7 @@ static int ti_qspi_probe(struct platform_device *pdev)
 {
 	struct  ti_qspi *qspi;
 	struct spi_master *master;
-	struct resource         *r, *res_ctrl, *res_mmap;
+	struct resource         *r, *res_mmap;
 	struct device_node *np = pdev->dev.of_node;
 	u32 max_freq;
 	int ret = 0, num_cs, irq;
@@ -487,16 +567,6 @@ static int ti_qspi_probe(struct platform_device *pdev)
 		}
 	}
 
-	res_ctrl = platform_get_resource_byname(pdev,
-			IORESOURCE_MEM, "qspi_ctrlmod");
-	if (res_ctrl == NULL) {
-		res_ctrl = platform_get_resource(pdev, IORESOURCE_MEM, 2);
-		if (res_ctrl == NULL) {
-			dev_dbg(&pdev->dev,
-				"control module resources not required\n");
-		}
-	}
-
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
 		dev_err(&pdev->dev, "no irq resource?\n");
@@ -511,20 +581,31 @@ static int ti_qspi_probe(struct platform_device *pdev)
 		goto free_master;
 	}
 
-	if (res_ctrl) {
-		qspi->ctrl_mod = true;
-		qspi->ctrl_base = devm_ioremap_resource(&pdev->dev, res_ctrl);
-		if (IS_ERR(qspi->ctrl_base)) {
-			ret = PTR_ERR(qspi->ctrl_base);
-			goto free_master;
-		}
-	}
-
 	if (res_mmap) {
-		qspi->mmap_base = devm_ioremap_resource(&pdev->dev, res_mmap);
+		qspi->mmap_base = devm_ioremap_resource(&pdev->dev,
+							res_mmap);
+		master->spi_flash_read = ti_qspi_spi_flash_read;
 		if (IS_ERR(qspi->mmap_base)) {
-			ret = PTR_ERR(qspi->mmap_base);
-			goto free_master;
+			dev_err(&pdev->dev,
+				"falling back to PIO mode\n");
+			master->spi_flash_read = NULL;
+		}
+	}
+	qspi->mmap_enabled = false;
+
+	if (of_property_read_bool(np, "syscon-chipselects")) {
+		qspi->ctrl_base =
+		syscon_regmap_lookup_by_phandle(np,
+						"syscon-chipselects");
+		if (IS_ERR(qspi->ctrl_base))
+			return PTR_ERR(qspi->ctrl_base);
+		ret = of_property_read_u32_index(np,
+						 "syscon-chipselects",
+						 1, &qspi->ctrl_reg);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"couldn't get ctrl_mod reg index\n");
+			return ret;
 		}
 	}
 
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 47eff8012a77..de2f2f90d799 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -144,6 +144,8 @@ SPI_STATISTICS_TRANSFER_BYTES_HISTO(14, "16384-32767");
 SPI_STATISTICS_TRANSFER_BYTES_HISTO(15, "32768-65535");
 SPI_STATISTICS_TRANSFER_BYTES_HISTO(16, "65536+");
 
+SPI_STATISTICS_SHOW(transfers_split_maxsize, "%lu");
+
 static struct attribute *spi_dev_attrs[] = {
 	&dev_attr_modalias.attr,
 	NULL,
@@ -181,6 +183,7 @@ static struct attribute *spi_device_statistics_attrs[] = {
 	&dev_attr_spi_device_transfer_bytes_histo14.attr,
 	&dev_attr_spi_device_transfer_bytes_histo15.attr,
 	&dev_attr_spi_device_transfer_bytes_histo16.attr,
+	&dev_attr_spi_device_transfers_split_maxsize.attr,
 	NULL,
 };
 
@@ -223,6 +226,7 @@ static struct attribute *spi_master_statistics_attrs[] = {
 	&dev_attr_spi_master_transfer_bytes_histo14.attr,
 	&dev_attr_spi_master_transfer_bytes_histo15.attr,
 	&dev_attr_spi_master_transfer_bytes_histo16.attr,
+	&dev_attr_spi_master_transfers_split_maxsize.attr,
 	NULL,
 };
 
@@ -702,6 +706,7 @@ static int spi_map_buf(struct spi_master *master, struct device *dev,
 		       enum dma_data_direction dir)
 {
 	const bool vmalloced_buf = is_vmalloc_addr(buf);
+	unsigned int max_seg_size = dma_get_max_seg_size(dev);
 	int desc_len;
 	int sgs;
 	struct page *vm_page;
@@ -710,10 +715,10 @@ static int spi_map_buf(struct spi_master *master, struct device *dev,
 	int i, ret;
 
 	if (vmalloced_buf) {
-		desc_len = PAGE_SIZE;
+		desc_len = min_t(int, max_seg_size, PAGE_SIZE);
 		sgs = DIV_ROUND_UP(len + offset_in_page(buf), desc_len);
 	} else {
-		desc_len = master->max_dma_len;
+		desc_len = min_t(int, max_seg_size, master->max_dma_len);
 		sgs = DIV_ROUND_UP(len, desc_len);
 	}
 
@@ -739,7 +744,6 @@ static int spi_map_buf(struct spi_master *master, struct device *dev,
 			sg_set_buf(&sgt->sgl[i], sg_buf, min);
 		}
 
-
 		buf += min;
 		len -= min;
 	}
@@ -1024,6 +1028,8 @@ out:
 	if (msg->status && master->handle_err)
 		master->handle_err(master, msg);
 
+	spi_res_release(master, msg);
+
 	spi_finalize_current_message(master);
 
 	return ret;
@@ -1047,6 +1053,7 @@ EXPORT_SYMBOL_GPL(spi_finalize_current_transfer);
  * __spi_pump_messages - function which processes spi message queue
  * @master: master to process queue for
  * @in_kthread: true if we are in the context of the message pump thread
+ * @bus_locked: true if the bus mutex is held when calling this function
  *
  * This function checks if there is any spi message in the queue that
  * needs processing and if so call out to the driver to initialize hardware
@@ -1056,7 +1063,8 @@ EXPORT_SYMBOL_GPL(spi_finalize_current_transfer);
  * inside spi_sync(); the queue extraction handling at the top of the
  * function should deal with this safely.
  */
-static void __spi_pump_messages(struct spi_master *master, bool in_kthread)
+static void __spi_pump_messages(struct spi_master *master, bool in_kthread,
+				bool bus_locked)
 {
 	unsigned long flags;
 	bool was_busy = false;
@@ -1152,6 +1160,9 @@ static void __spi_pump_messages(struct spi_master *master, bool in_kthread)
 		}
 	}
 
+	if (!bus_locked)
+		mutex_lock(&master->bus_lock_mutex);
+
 	trace_spi_message_start(master->cur_msg);
 
 	if (master->prepare_message) {
@@ -1161,7 +1172,7 @@ static void __spi_pump_messages(struct spi_master *master, bool in_kthread)
 				"failed to prepare message: %d\n", ret);
 			master->cur_msg->status = ret;
 			spi_finalize_current_message(master);
-			return;
+			goto out;
 		}
 		master->cur_msg_prepared = true;
 	}
@@ -1170,15 +1181,23 @@ static void __spi_pump_messages(struct spi_master *master, bool in_kthread)
 	if (ret) {
 		master->cur_msg->status = ret;
 		spi_finalize_current_message(master);
-		return;
+		goto out;
 	}
 
 	ret = master->transfer_one_message(master, master->cur_msg);
 	if (ret) {
 		dev_err(&master->dev,
 			"failed to transfer one message from queue\n");
-		return;
+		goto out;
 	}
+
+out:
+	if (!bus_locked)
+		mutex_unlock(&master->bus_lock_mutex);
+
+	/* Prod the scheduler in case transfer_one() was busy waiting */
+	if (!ret)
+		cond_resched();
 }
 
 /**
@@ -1190,7 +1209,7 @@ static void spi_pump_messages(struct kthread_work *work)
 	struct spi_master *master =
 		container_of(work, struct spi_master, pump_messages);
 
-	__spi_pump_messages(master, true);
+	__spi_pump_messages(master, true, false);
 }
 
 static int spi_init_queue(struct spi_master *master)
@@ -1581,13 +1600,30 @@ static void of_register_spi_devices(struct spi_master *master) { }
 static int acpi_spi_add_resource(struct acpi_resource *ares, void *data)
 {
 	struct spi_device *spi = data;
+	struct spi_master *master = spi->master;
 
 	if (ares->type == ACPI_RESOURCE_TYPE_SERIAL_BUS) {
 		struct acpi_resource_spi_serialbus *sb;
 
 		sb = &ares->data.spi_serial_bus;
 		if (sb->type == ACPI_RESOURCE_SERIAL_TYPE_SPI) {
-			spi->chip_select = sb->device_selection;
+			/*
+			 * ACPI DeviceSelection numbering is handled by the
+			 * host controller driver in Windows and can vary
+			 * from driver to driver. In Linux we always expect
+			 * 0 .. max - 1 so we need to ask the driver to
+			 * translate between the two schemes.
+			 */
+			if (master->fw_translate_cs) {
+				int cs = master->fw_translate_cs(master,
+						sb->device_selection);
+				if (cs < 0)
+					return cs;
+				spi->chip_select = cs;
+			} else {
+				spi->chip_select = sb->device_selection;
+			}
+
 			spi->max_speed_hz = sb->connection_speed;
 
 			if (sb->clock_phase == ACPI_SPI_SECOND_PHASE)
@@ -2013,6 +2049,336 @@ struct spi_master *spi_busnum_to_master(u16 bus_num)
 }
 EXPORT_SYMBOL_GPL(spi_busnum_to_master);
 
+/*-------------------------------------------------------------------------*/
+
+/* Core methods for SPI resource management */
+
+/**
+ * spi_res_alloc - allocate a spi resource that is life-cycle managed
+ *                 during the processing of a spi_message while using
+ *                 spi_transfer_one
+ * @spi:     the spi device for which we allocate memory
+ * @release: the release code to execute for this resource
+ * @size:    size to alloc and return
+ * @gfp:     GFP allocation flags
+ *
+ * Return: the pointer to the allocated data
+ *
+ * This may get enhanced in the future to allocate from a memory pool
+ * of the @spi_device or @spi_master to avoid repeated allocations.
+ */
+void *spi_res_alloc(struct spi_device *spi,
+		    spi_res_release_t release,
+		    size_t size, gfp_t gfp)
+{
+	struct spi_res *sres;
+
+	sres = kzalloc(sizeof(*sres) + size, gfp);
+	if (!sres)
+		return NULL;
+
+	INIT_LIST_HEAD(&sres->entry);
+	sres->release = release;
+
+	return sres->data;
+}
+EXPORT_SYMBOL_GPL(spi_res_alloc);
+
+/**
+ * spi_res_free - free an spi resource
+ * @res: pointer to the custom data of a resource
+ *
+ */
+void spi_res_free(void *res)
+{
+	struct spi_res *sres = container_of(res, struct spi_res, data);
+
+	if (!res)
+		return;
+
+	WARN_ON(!list_empty(&sres->entry));
+	kfree(sres);
+}
+EXPORT_SYMBOL_GPL(spi_res_free);
+
+/**
+ * spi_res_add - add a spi_res to the spi_message
+ * @message: the spi message
+ * @res:     the spi_resource
+ */
+void spi_res_add(struct spi_message *message, void *res)
+{
+	struct spi_res *sres = container_of(res, struct spi_res, data);
+
+	WARN_ON(!list_empty(&sres->entry));
+	list_add_tail(&sres->entry, &message->resources);
+}
+EXPORT_SYMBOL_GPL(spi_res_add);
+
+/**
+ * spi_res_release - release all spi resources for this message
+ * @master:  the @spi_master
+ * @message: the @spi_message
+ */
+void spi_res_release(struct spi_master *master,
+		     struct spi_message *message)
+{
+	struct spi_res *res;
+
+	while (!list_empty(&message->resources)) {
+		res = list_last_entry(&message->resources,
+				      struct spi_res, entry);
+
+		if (res->release)
+			res->release(master, message, res->data);
+
+		list_del(&res->entry);
+
+		kfree(res);
+	}
+}
+EXPORT_SYMBOL_GPL(spi_res_release);
+
+/*-------------------------------------------------------------------------*/
+
+/* Core methods for spi_message alterations */
+
+static void __spi_replace_transfers_release(struct spi_master *master,
+					    struct spi_message *msg,
+					    void *res)
+{
+	struct spi_replaced_transfers *rxfer = res;
+	size_t i;
+
+	/* call extra callback if requested */
+	if (rxfer->release)
+		rxfer->release(master, msg, res);
+
+	/* insert replaced transfers back into the message */
+	list_splice(&rxfer->replaced_transfers, rxfer->replaced_after);
+
+	/* remove the formerly inserted entries */
+	for (i = 0; i < rxfer->inserted; i++)
+		list_del(&rxfer->inserted_transfers[i].transfer_list);
+}
+
+/**
+ * spi_replace_transfers - replace transfers with several transfers
+ *                         and register change with spi_message.resources
+ * @msg:           the spi_message we work upon
+ * @xfer_first:    the first spi_transfer we want to replace
+ * @remove:        number of transfers to remove
+ * @insert:        the number of transfers we want to insert instead
+ * @release:       extra release code necessary in some circumstances
+ * @extradatasize: extra data to allocate (with alignment guarantees
+ *                 of struct @spi_transfer)
+ * @gfp:           gfp flags
+ *
+ * Returns: pointer to @spi_replaced_transfers,
+ *          PTR_ERR(...) in case of errors.
+ */
+struct spi_replaced_transfers *spi_replace_transfers(
+	struct spi_message *msg,
+	struct spi_transfer *xfer_first,
+	size_t remove,
+	size_t insert,
+	spi_replaced_release_t release,
+	size_t extradatasize,
+	gfp_t gfp)
+{
+	struct spi_replaced_transfers *rxfer;
+	struct spi_transfer *xfer;
+	size_t i;
+
+	/* allocate the structure using spi_res */
+	rxfer = spi_res_alloc(msg->spi, __spi_replace_transfers_release,
+			      insert * sizeof(struct spi_transfer)
+			      + sizeof(struct spi_replaced_transfers)
+			      + extradatasize,
+			      gfp);
+	if (!rxfer)
+		return ERR_PTR(-ENOMEM);
+
+	/* the release code to invoke before running the generic release */
+	rxfer->release = release;
+
+	/* assign extradata */
+	if (extradatasize)
+		rxfer->extradata =
+			&rxfer->inserted_transfers[insert];
+
+	/* init the replaced_transfers list */
+	INIT_LIST_HEAD(&rxfer->replaced_transfers);
+
+	/* assign the list_entry after which we should reinsert
+	 * the @replaced_transfers - it may be spi_message.messages!
+	 */
+	rxfer->replaced_after = xfer_first->transfer_list.prev;
+
+	/* remove the requested number of transfers */
+	for (i = 0; i < remove; i++) {
+		/* if the entry after replaced_after it is msg->transfers
+		 * then we have been requested to remove more transfers
+		 * than are in the list
+		 */
+		if (rxfer->replaced_after->next == &msg->transfers) {
+			dev_err(&msg->spi->dev,
+				"requested to remove more spi_transfers than are available\n");
+			/* insert replaced transfers back into the message */
+			list_splice(&rxfer->replaced_transfers,
+				    rxfer->replaced_after);
+
+			/* free the spi_replace_transfer structure */
+			spi_res_free(rxfer);
+
+			/* and return with an error */
+			return ERR_PTR(-EINVAL);
+		}
+
+		/* remove the entry after replaced_after from list of
+		 * transfers and add it to list of replaced_transfers
+		 */
+		list_move_tail(rxfer->replaced_after->next,
+			       &rxfer->replaced_transfers);
+	}
+
+	/* create copy of the given xfer with identical settings
+	 * based on the first transfer to get removed
+	 */
+	for (i = 0; i < insert; i++) {
+		/* we need to run in reverse order */
+		xfer = &rxfer->inserted_transfers[insert - 1 - i];
+
+		/* copy all spi_transfer data */
+		memcpy(xfer, xfer_first, sizeof(*xfer));
+
+		/* add to list */
+		list_add(&xfer->transfer_list, rxfer->replaced_after);
+
+		/* clear cs_change and delay_usecs for all but the last */
+		if (i) {
+			xfer->cs_change = false;
+			xfer->delay_usecs = 0;
+		}
+	}
+
+	/* set up inserted */
+	rxfer->inserted = insert;
+
+	/* and register it with spi_res/spi_message */
+	spi_res_add(msg, rxfer);
+
+	return rxfer;
+}
+EXPORT_SYMBOL_GPL(spi_replace_transfers);
+
+static int __spi_split_transfer_maxsize(struct spi_master *master,
+					struct spi_message *msg,
+					struct spi_transfer **xferp,
+					size_t maxsize,
+					gfp_t gfp)
+{
+	struct spi_transfer *xfer = *xferp, *xfers;
+	struct spi_replaced_transfers *srt;
+	size_t offset;
+	size_t count, i;
+
+	/* warn once about this fact that we are splitting a transfer */
+	dev_warn_once(&msg->spi->dev,
+		      "spi_transfer of length %i exceed max length of %zu - needed to split transfers\n",
+		      xfer->len, maxsize);
+
+	/* calculate how many we have to replace */
+	count = DIV_ROUND_UP(xfer->len, maxsize);
+
+	/* create replacement */
+	srt = spi_replace_transfers(msg, xfer, 1, count, NULL, 0, gfp);
+	if (IS_ERR(srt))
+		return PTR_ERR(srt);
+	xfers = srt->inserted_transfers;
+
+	/* now handle each of those newly inserted spi_transfers
+	 * note that the replacements spi_transfers all are preset
+	 * to the same values as *xferp, so tx_buf, rx_buf and len
+	 * are all identical (as well as most others)
+	 * so we just have to fix up len and the pointers.
+	 *
+	 * this also includes support for the depreciated
+	 * spi_message.is_dma_mapped interface
+	 */
+
+	/* the first transfer just needs the length modified, so we
+	 * run it outside the loop
+	 */
+	xfers[0].len = min_t(size_t, maxsize, xfer[0].len);
+
+	/* all the others need rx_buf/tx_buf also set */
+	for (i = 1, offset = maxsize; i < count; offset += maxsize, i++) {
+		/* update rx_buf, tx_buf and dma */
+		if (xfers[i].rx_buf)
+			xfers[i].rx_buf += offset;
+		if (xfers[i].rx_dma)
+			xfers[i].rx_dma += offset;
+		if (xfers[i].tx_buf)
+			xfers[i].tx_buf += offset;
+		if (xfers[i].tx_dma)
+			xfers[i].tx_dma += offset;
+
+		/* update length */
+		xfers[i].len = min(maxsize, xfers[i].len - offset);
+	}
+
+	/* we set up xferp to the last entry we have inserted,
+	 * so that we skip those already split transfers
+	 */
+	*xferp = &xfers[count - 1];
+
+	/* increment statistics counters */
+	SPI_STATISTICS_INCREMENT_FIELD(&master->statistics,
+				       transfers_split_maxsize);
+	SPI_STATISTICS_INCREMENT_FIELD(&msg->spi->statistics,
+				       transfers_split_maxsize);
+
+	return 0;
+}
+
+/**
+ * spi_split_tranfers_maxsize - split spi transfers into multiple transfers
+ *                              when an individual transfer exceeds a
+ *                              certain size
+ * @master:    the @spi_master for this transfer
+ * @msg:   the @spi_message to transform
+ * @maxsize:  the maximum when to apply this
+ * @gfp: GFP allocation flags
+ *
+ * Return: status of transformation
+ */
+int spi_split_transfers_maxsize(struct spi_master *master,
+				struct spi_message *msg,
+				size_t maxsize,
+				gfp_t gfp)
+{
+	struct spi_transfer *xfer;
+	int ret;
+
+	/* iterate over the transfer_list,
+	 * but note that xfer is advanced to the last transfer inserted
+	 * to avoid checking sizes again unnecessarily (also xfer does
+	 * potentiall belong to a different list by the time the
+	 * replacement has happened
+	 */
+	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+		if (xfer->len > maxsize) {
+			ret = __spi_split_transfer_maxsize(
+				master, msg, &xfer, maxsize, gfp);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(spi_split_transfers_maxsize);
 
 /*-------------------------------------------------------------------------*/
 
@@ -2351,6 +2717,46 @@ int spi_async_locked(struct spi_device *spi, struct spi_message *message)
 EXPORT_SYMBOL_GPL(spi_async_locked);
 
 
+int spi_flash_read(struct spi_device *spi,
+		   struct spi_flash_read_message *msg)
+
+{
+	struct spi_master *master = spi->master;
+	int ret;
+
+	if ((msg->opcode_nbits == SPI_NBITS_DUAL ||
+	     msg->addr_nbits == SPI_NBITS_DUAL) &&
+	    !(spi->mode & (SPI_TX_DUAL | SPI_TX_QUAD)))
+		return -EINVAL;
+	if ((msg->opcode_nbits == SPI_NBITS_QUAD ||
+	     msg->addr_nbits == SPI_NBITS_QUAD) &&
+	    !(spi->mode & SPI_TX_QUAD))
+		return -EINVAL;
+	if (msg->data_nbits == SPI_NBITS_DUAL &&
+	    !(spi->mode & (SPI_RX_DUAL | SPI_RX_QUAD)))
+		return -EINVAL;
+	if (msg->data_nbits == SPI_NBITS_QUAD &&
+	    !(spi->mode &  SPI_RX_QUAD))
+		return -EINVAL;
+
+	if (master->auto_runtime_pm) {
+		ret = pm_runtime_get_sync(master->dev.parent);
+		if (ret < 0) {
+			dev_err(&master->dev, "Failed to power device: %d\n",
+				ret);
+			return ret;
+		}
+	}
+	mutex_lock(&master->bus_lock_mutex);
+	ret = master->spi_flash_read(spi, msg);
+	mutex_unlock(&master->bus_lock_mutex);
+	if (master->auto_runtime_pm)
+		pm_runtime_put(master->dev.parent);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(spi_flash_read);
+
 /*-------------------------------------------------------------------------*/
 
 /* Utility methods for SPI master protocol drivers, layered on
@@ -2414,7 +2820,7 @@ static int __spi_sync(struct spi_device *spi, struct spi_message *message,
 						       spi_sync_immediate);
 			SPI_STATISTICS_INCREMENT_FIELD(&spi->statistics,
 						       spi_sync_immediate);
-			__spi_pump_messages(master, false);
+			__spi_pump_messages(master, false, bus_locked);
 		}
 
 		wait_for_completion(&done);
diff --git a/drivers/ssb/Kconfig b/drivers/ssb/Kconfig
index 0c675861623f..d8e4219c2324 100644
--- a/drivers/ssb/Kconfig
+++ b/drivers/ssb/Kconfig
@@ -83,6 +83,7 @@ config SSB_SDIOHOST
 config SSB_HOST_SOC
 	bool "Support for SSB bus on SoC"
 	depends on SSB && BCM47XX_NVRAM
+	select SSB_SPROM
 	help
 	  Host interface for a SSB directly mapped into memory. This is
 	  for some Broadcom SoCs from the BCM47xx and BCM53xx lines.
diff --git a/drivers/staging/lustre/lustre/libcfs/linux/linux-crypto.c b/drivers/staging/lustre/lustre/libcfs/linux/linux-crypto.c
index 079d50ebfa3a..94c01aad844b 100644
--- a/drivers/staging/lustre/lustre/libcfs/linux/linux-crypto.c
+++ b/drivers/staging/lustre/lustre/libcfs/linux/linux-crypto.c
@@ -27,7 +27,7 @@
  * Copyright (c) 2012, Intel Corporation.
  */
 
-#include <linux/crypto.h>
+#include <crypto/hash.h>
 #include <linux/scatterlist.h>
 #include "../../../include/linux/libcfs/libcfs.h"
 #include "linux-crypto.h"
@@ -38,9 +38,11 @@ static int cfs_crypto_hash_speeds[CFS_HASH_ALG_MAX];
 
 static int cfs_crypto_hash_alloc(unsigned char alg_id,
 				 const struct cfs_crypto_hash_type **type,
-				 struct hash_desc *desc, unsigned char *key,
+				 struct ahash_request **req,
+				 unsigned char *key,
 				 unsigned int key_len)
 {
+	struct crypto_ahash *tfm;
 	int     err = 0;
 
 	*type = cfs_crypto_hash_type(alg_id);
@@ -50,18 +52,23 @@ static int cfs_crypto_hash_alloc(unsigned char alg_id,
 		      alg_id, CFS_HASH_ALG_MAX);
 		return -EINVAL;
 	}
-	desc->tfm = crypto_alloc_hash((*type)->cht_name, 0, 0);
+	tfm = crypto_alloc_ahash((*type)->cht_name, 0, CRYPTO_ALG_ASYNC);
 
-	if (desc->tfm == NULL)
-		return -EINVAL;
-
-	if (IS_ERR(desc->tfm)) {
+	if (IS_ERR(tfm)) {
 		CDEBUG(D_INFO, "Failed to alloc crypto hash %s\n",
 		       (*type)->cht_name);
-		return PTR_ERR(desc->tfm);
+		return PTR_ERR(tfm);
 	}
 
-	desc->flags = 0;
+	*req = ahash_request_alloc(tfm, GFP_KERNEL);
+	if (!*req) {
+		CDEBUG(D_INFO, "Failed to alloc ahash_request for %s\n",
+		       (*type)->cht_name);
+		crypto_free_ahash(tfm);
+		return -ENOMEM;
+	}
+
+	ahash_request_set_callback(*req, 0, NULL, NULL);
 
 	/** Shash have different logic for initialization then digest
 	 * shash: crypto_hash_setkey, crypto_hash_init
@@ -70,23 +77,27 @@ static int cfs_crypto_hash_alloc(unsigned char alg_id,
 	 * cfs_crypto_hash_alloc.
 	 */
 	if (key != NULL)
-		err = crypto_hash_setkey(desc->tfm, key, key_len);
+		err = crypto_ahash_setkey(tfm, key, key_len);
 	else if ((*type)->cht_key != 0)
-		err = crypto_hash_setkey(desc->tfm,
+		err = crypto_ahash_setkey(tfm,
 					 (unsigned char *)&((*type)->cht_key),
 					 (*type)->cht_size);
 
 	if (err != 0) {
-		crypto_free_hash(desc->tfm);
+		crypto_free_ahash(tfm);
 		return err;
 	}
 
 	CDEBUG(D_INFO, "Using crypto hash: %s (%s) speed %d MB/s\n",
-	       (crypto_hash_tfm(desc->tfm))->__crt_alg->cra_name,
-	       (crypto_hash_tfm(desc->tfm))->__crt_alg->cra_driver_name,
+	       crypto_ahash_alg_name(tfm), crypto_ahash_driver_name(tfm),
 	       cfs_crypto_hash_speeds[alg_id]);
 
-	return crypto_hash_init(desc);
+	err = crypto_ahash_init(*req);
+	if (err) {
+		ahash_request_free(*req);
+		crypto_free_ahash(tfm);
+	}
+	return err;
 }
 
 int cfs_crypto_hash_digest(unsigned char alg_id,
@@ -95,27 +106,29 @@ int cfs_crypto_hash_digest(unsigned char alg_id,
 			   unsigned char *hash, unsigned int *hash_len)
 {
 	struct scatterlist	sl;
-	struct hash_desc	hdesc;
+	struct ahash_request *req;
 	int			err;
 	const struct cfs_crypto_hash_type	*type;
 
 	if (buf == NULL || buf_len == 0 || hash_len == NULL)
 		return -EINVAL;
 
-	err = cfs_crypto_hash_alloc(alg_id, &type, &hdesc, key, key_len);
+	err = cfs_crypto_hash_alloc(alg_id, &type, &req, key, key_len);
 	if (err != 0)
 		return err;
 
 	if (hash == NULL || *hash_len < type->cht_size) {
 		*hash_len = type->cht_size;
-		crypto_free_hash(hdesc.tfm);
+		crypto_free_ahash(crypto_ahash_reqtfm(req));
+		ahash_request_free(req);
 		return -ENOSPC;
 	}
 	sg_init_one(&sl, buf, buf_len);
 
-	hdesc.flags = 0;
-	err = crypto_hash_digest(&hdesc, &sl, sl.length, hash);
-	crypto_free_hash(hdesc.tfm);
+	ahash_request_set_crypt(req, &sl, hash, sl.length);
+	err = crypto_ahash_digest(req);
+	crypto_free_ahash(crypto_ahash_reqtfm(req));
+	ahash_request_free(req);
 
 	return err;
 }
@@ -125,22 +138,15 @@ struct cfs_crypto_hash_desc *
 	cfs_crypto_hash_init(unsigned char alg_id,
 			     unsigned char *key, unsigned int key_len)
 {
-
-	struct  hash_desc       *hdesc;
+	struct ahash_request *req;
 	int		     err;
 	const struct cfs_crypto_hash_type       *type;
 
-	hdesc = kmalloc(sizeof(*hdesc), 0);
-	if (hdesc == NULL)
-		return ERR_PTR(-ENOMEM);
+	err = cfs_crypto_hash_alloc(alg_id, &type, &req, key, key_len);
 
-	err = cfs_crypto_hash_alloc(alg_id, &type, hdesc, key, key_len);
-
-	if (err) {
-		kfree(hdesc);
+	if (err)
 		return ERR_PTR(err);
-	}
-	return (struct cfs_crypto_hash_desc *)hdesc;
+	return (struct cfs_crypto_hash_desc *)req;
 }
 EXPORT_SYMBOL(cfs_crypto_hash_init);
 
@@ -148,23 +154,27 @@ int cfs_crypto_hash_update_page(struct cfs_crypto_hash_desc *hdesc,
 				struct page *page, unsigned int offset,
 				unsigned int len)
 {
+	struct ahash_request *req = (void *)hdesc;
 	struct scatterlist sl;
 
 	sg_init_table(&sl, 1);
 	sg_set_page(&sl, page, len, offset & ~CFS_PAGE_MASK);
 
-	return crypto_hash_update((struct hash_desc *)hdesc, &sl, sl.length);
+	ahash_request_set_crypt(req, &sl, NULL, sl.length);
+	return crypto_ahash_update(req);
 }
 EXPORT_SYMBOL(cfs_crypto_hash_update_page);
 
 int cfs_crypto_hash_update(struct cfs_crypto_hash_desc *hdesc,
 			   const void *buf, unsigned int buf_len)
 {
+	struct ahash_request *req = (void *)hdesc;
 	struct scatterlist sl;
 
 	sg_init_one(&sl, buf, buf_len);
 
-	return crypto_hash_update((struct hash_desc *)hdesc, &sl, sl.length);
+	ahash_request_set_crypt(req, &sl, NULL, sl.length);
+	return crypto_ahash_update(req);
 }
 EXPORT_SYMBOL(cfs_crypto_hash_update);
 
@@ -173,25 +183,27 @@ int cfs_crypto_hash_final(struct cfs_crypto_hash_desc *hdesc,
 			  unsigned char *hash, unsigned int *hash_len)
 {
 	int     err;
-	int     size = crypto_hash_digestsize(((struct hash_desc *)hdesc)->tfm);
+	struct ahash_request *req = (void *)hdesc;
+	int size = crypto_ahash_digestsize(crypto_ahash_reqtfm(req));
 
 	if (hash_len == NULL) {
-		crypto_free_hash(((struct hash_desc *)hdesc)->tfm);
-		kfree(hdesc);
+		crypto_free_ahash(crypto_ahash_reqtfm(req));
+		ahash_request_free(req);
 		return 0;
 	}
 	if (hash == NULL || *hash_len < size) {
 		*hash_len = size;
 		return -ENOSPC;
 	}
-	err = crypto_hash_final((struct hash_desc *) hdesc, hash);
+	ahash_request_set_crypt(req, NULL, hash, 0);
+	err = crypto_ahash_final(req);
 
 	if (err < 0) {
 		/* May be caller can fix error */
 		return err;
 	}
-	crypto_free_hash(((struct hash_desc *)hdesc)->tfm);
-	kfree(hdesc);
+	crypto_free_ahash(crypto_ahash_reqtfm(req));
+	ahash_request_free(req);
 	return err;
 }
 EXPORT_SYMBOL(cfs_crypto_hash_final);
diff --git a/drivers/staging/media/Kconfig b/drivers/staging/media/Kconfig
index 14697686eea5..0078b6a92f0b 100644
--- a/drivers/staging/media/Kconfig
+++ b/drivers/staging/media/Kconfig
@@ -27,10 +27,16 @@ source "drivers/staging/media/davinci_vpfe/Kconfig"
 
 source "drivers/staging/media/mn88472/Kconfig"
 
-source "drivers/staging/media/mn88473/Kconfig"
+source "drivers/staging/media/mx2/Kconfig"
+
+source "drivers/staging/media/mx3/Kconfig"
+
+source "drivers/staging/media/omap1/Kconfig"
 
 source "drivers/staging/media/omap4iss/Kconfig"
 
+source "drivers/staging/media/timb/Kconfig"
+
 # Keep LIRC at the end, as it has sub-menus
 source "drivers/staging/media/lirc/Kconfig"
 
diff --git a/drivers/staging/media/Makefile b/drivers/staging/media/Makefile
index 34c557b4c6d6..91495882a36c 100644
--- a/drivers/staging/media/Makefile
+++ b/drivers/staging/media/Makefile
@@ -2,6 +2,9 @@ obj-$(CONFIG_I2C_BCM2048)	+= bcm2048/
 obj-$(CONFIG_DVB_CXD2099)	+= cxd2099/
 obj-$(CONFIG_LIRC_STAGING)	+= lirc/
 obj-$(CONFIG_VIDEO_DM365_VPFE)	+= davinci_vpfe/
+obj-$(CONFIG_VIDEO_MX2)		+= mx2/
+obj-$(CONFIG_VIDEO_MX3)		+= mx3/
+obj-$(CONFIG_VIDEO_OMAP1)	+= omap1/
 obj-$(CONFIG_VIDEO_OMAP4)	+= omap4iss/
 obj-$(CONFIG_DVB_MN88472)       += mn88472/
-obj-$(CONFIG_DVB_MN88473)       += mn88473/
+obj-$(CONFIG_VIDEO_TIMBERDALE)  += timb/
diff --git a/drivers/staging/media/davinci_vpfe/davinci_vpfe_user.h b/drivers/staging/media/davinci_vpfe/davinci_vpfe_user.h
index 7b7e7b26c1e8..3cc9be776f8b 100644
--- a/drivers/staging/media/davinci_vpfe/davinci_vpfe_user.h
+++ b/drivers/staging/media/davinci_vpfe/davinci_vpfe_user.h
@@ -538,7 +538,7 @@ struct vpfe_isif_raw_config {
 };
 
 /**********************************************************************
-      IPIPE API Structures
+*      IPIPE API Structures
 **********************************************************************/
 
 /* IPIPE module configurations */
diff --git a/drivers/staging/media/davinci_vpfe/vpfe_video.c b/drivers/staging/media/davinci_vpfe/vpfe_video.c
index 3ec7e65a3ffa..db49af90217e 100644
--- a/drivers/staging/media/davinci_vpfe/vpfe_video.c
+++ b/drivers/staging/media/davinci_vpfe/vpfe_video.c
@@ -147,7 +147,7 @@ static int vpfe_prepare_pipeline(struct vpfe_video_device *video)
 	mutex_lock(&mdev->graph_mutex);
 	ret = media_entity_graph_walk_init(&graph, entity->graph_obj.mdev);
 	if (ret) {
-		mutex_unlock(&video->lock);
+		mutex_unlock(&mdev->graph_mutex);
 		return -ENOMEM;
 	}
 	media_entity_graph_walk_start(&graph, entity);
diff --git a/drivers/staging/media/lirc/lirc_parallel.c b/drivers/staging/media/lirc/lirc_parallel.c
index d009bcb439f0..68ede6c56e6d 100644
--- a/drivers/staging/media/lirc/lirc_parallel.c
+++ b/drivers/staging/media/lirc/lirc_parallel.c
@@ -193,7 +193,7 @@ static int lirc_claim(void)
 			return 0;
 		}
 	}
-	out(LIRC_LP_CONTROL, LP_PSELECP|LP_PINITP);
+	out(LIRC_LP_CONTROL, LP_PSELECP | LP_PINITP);
 	is_claimed = 1;
 	return 1;
 }
@@ -264,7 +264,7 @@ static void lirc_lirc_irq_handler(void *blah)
 		init = 1;
 	}
 
-	timeout = timer/10;	/* timeout after 1/10 sec. */
+	timeout = timer / 10;	/* timeout after 1/10 sec. */
 	signal = 1;
 	level = lirc_get_timer();
 	do {
@@ -286,15 +286,15 @@ static void lirc_lirc_irq_handler(void *blah)
 		/* adjust value to usecs */
 		__u64 helper;
 
-		helper = ((__u64) signal)*1000000;
+		helper = ((__u64)signal) * 1000000;
 		do_div(helper, timer);
-		signal = (long) helper;
+		signal = (long)helper;
 
 		if (signal > LIRC_SFH506_DELAY)
 			data = signal - LIRC_SFH506_DELAY;
 		else
 			data = 1;
-		rbuf_write(PULSE_BIT|data); /* pulse */
+		rbuf_write(PULSE_BIT | data); /* pulse */
 	}
 	lastkt = ktime_get();
 #else
@@ -331,7 +331,7 @@ static ssize_t lirc_read(struct file *filep, char __user *buf, size_t n,
 	set_current_state(TASK_INTERRUPTIBLE);
 	while (count < n) {
 		if (rptr != wptr) {
-			if (copy_to_user(buf+count, &rbuf[rptr],
+			if (copy_to_user(buf + count, &rbuf[rptr],
 					 sizeof(int))) {
 				result = -EFAULT;
 				break;
@@ -393,9 +393,9 @@ static ssize_t lirc_write(struct file *filep, const char __user *buf, size_t n,
 	for (i = 0; i < count; i++) {
 		__u64 helper;
 
-		helper = ((__u64) wbuf[i])*timer;
+		helper = ((__u64)wbuf[i]) * timer;
 		do_div(helper, 1000000);
-		wbuf[i] = (int) helper;
+		wbuf[i] = (int)helper;
 	}
 
 	local_irq_save(flags);
@@ -647,7 +647,7 @@ static int __init lirc_parallel_init(void)
 		goto exit_device_put;
 
 	pport = parport_find_base(io);
-	if (pport == NULL) {
+	if (!pport) {
 		pr_notice("no port at %x found\n", io);
 		result = -ENXIO;
 		goto exit_device_put;
@@ -656,7 +656,7 @@ static int __init lirc_parallel_init(void)
 					   pf, kf, lirc_lirc_irq_handler, 0,
 					   NULL);
 	parport_put_port(pport);
-	if (ppdevice == NULL) {
+	if (!ppdevice) {
 		pr_notice("parport_register_device() failed\n");
 		result = -ENXIO;
 		goto exit_device_put;
@@ -664,7 +664,7 @@ static int __init lirc_parallel_init(void)
 	if (parport_claim(ppdevice) != 0)
 		goto skip_init;
 	is_claimed = 1;
-	out(LIRC_LP_CONTROL, LP_PSELECP|LP_PINITP);
+	out(LIRC_LP_CONTROL, LP_PSELECP | LP_PINITP);
 
 #ifdef LIRC_TIMER
 	if (debug)
@@ -730,7 +730,7 @@ module_param(irq, int, S_IRUGO);
 MODULE_PARM_DESC(irq, "Interrupt (7 or 5)");
 
 module_param(tx_mask, int, S_IRUGO);
-MODULE_PARM_DESC(tx_maxk, "Transmitter mask (default: 0x01)");
+MODULE_PARM_DESC(tx_mask, "Transmitter mask (default: 0x01)");
 
 module_param(debug, bool, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(debug, "Enable debugging messages");
diff --git a/drivers/staging/media/lirc/lirc_zilog.c b/drivers/staging/media/lirc/lirc_zilog.c
index ce3b5f230e2e..3551aed589c0 100644
--- a/drivers/staging/media/lirc/lirc_zilog.c
+++ b/drivers/staging/media/lirc/lirc_zilog.c
@@ -1680,9 +1680,7 @@ module_init(zilog_init);
 module_exit(zilog_exit);
 
 MODULE_DESCRIPTION("Zilog/Hauppauge infrared transmitter driver (i2c stack)");
-MODULE_AUTHOR("Gerd Knorr, Michal Kochanowicz, Christoph Bartelmus, "
-	      "Ulrich Mueller, Stefan Jahn, Jerome Brock, Mark Weaver, "
-	      "Andy Walls");
+MODULE_AUTHOR("Gerd Knorr, Michal Kochanowicz, Christoph Bartelmus, Ulrich Mueller, Stefan Jahn, Jerome Brock, Mark Weaver, Andy Walls");
 MODULE_LICENSE("GPL");
 /* for compat with old name, which isn't all that accurate anymore */
 MODULE_ALIAS("lirc_pvr150");
diff --git a/drivers/staging/media/mn88473/Kconfig b/drivers/staging/media/mn88473/Kconfig
deleted file mode 100644
index 6c9ebf51c2c7..000000000000
--- a/drivers/staging/media/mn88473/Kconfig
+++ /dev/null
@@ -1,7 +0,0 @@
-config DVB_MN88473
-	tristate "Panasonic MN88473"
-	depends on DVB_CORE && I2C
-	select REGMAP_I2C
-	default m if !MEDIA_SUBDRV_AUTOSELECT
-	help
-	  Say Y when you want to support this frontend.
diff --git a/drivers/staging/media/mn88473/Makefile b/drivers/staging/media/mn88473/Makefile
deleted file mode 100644
index fac55410ce55..000000000000
--- a/drivers/staging/media/mn88473/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-obj-$(CONFIG_DVB_MN88473) += mn88473.o
-
-ccflags-y += -Idrivers/media/dvb-core/
-ccflags-y += -Idrivers/media/dvb-frontends/
-ccflags-y += -Idrivers/media/tuners/
diff --git a/drivers/staging/media/mn88473/TODO b/drivers/staging/media/mn88473/TODO
deleted file mode 100644
index b90a14be3beb..000000000000
--- a/drivers/staging/media/mn88473/TODO
+++ /dev/null
@@ -1,21 +0,0 @@
-Driver general quality is not good enough for mainline. Also, other
-device drivers (USB-bridge, tuner) needed for Astrometa receiver in
-question could need some changes. However, if that driver is mainlined
-due to some other device than Astrometa, unrelated TODOs could be
-skipped. In that case rtl28xxu driver needs module parameter to prevent
-driver loading.
-
-Required TODOs:
-* missing lock flags
-* I2C errors
-* tuner sensitivity
-
-*Do not* send any patch fixing checkpatch.pl issues. Currently it passes
-checkpatch.pl tests. I don't want waste my time to review this kind of
-trivial stuff. *Do not* add missing register I/O error checks. Those are
-missing for the reason it is much easier to compare I2C data sniffs when
-there is less lines. Those error checks are about the last thing to be added.
-
-Patches should be submitted to:
-linux-media@vger.kernel.org and Antti Palosaari <crope@iki.fi>
-
diff --git a/drivers/staging/media/mx2/Kconfig b/drivers/staging/media/mx2/Kconfig
new file mode 100644
index 000000000000..beaa885cf104
--- /dev/null
+++ b/drivers/staging/media/mx2/Kconfig
@@ -0,0 +1,15 @@
+config VIDEO_MX2
+	tristate "i.MX27 Camera Sensor Interface driver"
+	depends on VIDEO_DEV && SOC_CAMERA
+	depends on SOC_IMX27 || COMPILE_TEST
+	depends on HAS_DMA
+	select VIDEOBUF2_DMA_CONTIG
+	---help---
+	  This is a v4l2 driver for the i.MX27 Camera Sensor Interface
+
+	  This driver is deprecated: it should become a stand-alone driver
+	  instead of using the soc-camera framework.
+
+	  Unless someone is willing to take this on (unlikely with such
+	  ancient hardware) it is going to be removed from the kernel
+	  soon.
diff --git a/drivers/staging/media/mx2/Makefile b/drivers/staging/media/mx2/Makefile
new file mode 100644
index 000000000000..fc5b2826a558
--- /dev/null
+++ b/drivers/staging/media/mx2/Makefile
@@ -0,0 +1,3 @@
+# Makefile for i.MX27 Camera Sensor driver
+
+obj-$(CONFIG_VIDEO_MX2) += mx2_camera.o
diff --git a/drivers/staging/media/mx2/TODO b/drivers/staging/media/mx2/TODO
new file mode 100644
index 000000000000..bc68fa443a3e
--- /dev/null
+++ b/drivers/staging/media/mx2/TODO
@@ -0,0 +1,10 @@
+This driver is deprecated: it should become a stand-alone driver instead of
+using the soc-camera framework.
+
+Unless someone is willing to take this on (unlikely with such ancient
+hardware) it is going to be removed from the kernel soon.
+
+Note that trivial patches will not be accepted anymore, only a full conversion.
+
+If you want to convert this driver, please contact the linux-media mailinglist
+(see http://linuxtv.org/lists.php).
diff --git a/drivers/media/platform/soc_camera/mx2_camera.c b/drivers/staging/media/mx2/mx2_camera.c
index 48dd5b7851b5..48dd5b7851b5 100644
--- a/drivers/media/platform/soc_camera/mx2_camera.c
+++ b/drivers/staging/media/mx2/mx2_camera.c
diff --git a/drivers/staging/media/mx3/Kconfig b/drivers/staging/media/mx3/Kconfig
new file mode 100644
index 000000000000..595d5fe7cad1
--- /dev/null
+++ b/drivers/staging/media/mx3/Kconfig
@@ -0,0 +1,15 @@
+config VIDEO_MX3
+	tristate "i.MX3x Camera Sensor Interface driver"
+	depends on VIDEO_DEV && MX3_IPU && SOC_CAMERA
+	depends on MX3_IPU || COMPILE_TEST
+	depends on HAS_DMA
+	select VIDEOBUF2_DMA_CONTIG
+	---help---
+	  This is a v4l2 driver for the i.MX3x Camera Sensor Interface
+
+	  This driver is deprecated: it should become a stand-alone driver
+	  instead of using the soc-camera framework.
+
+	  Unless someone is willing to take this on (unlikely with such
+	  ancient hardware) it is going to be removed from the kernel
+	  soon.
diff --git a/drivers/staging/media/mx3/Makefile b/drivers/staging/media/mx3/Makefile
new file mode 100644
index 000000000000..6d91dcd80c1d
--- /dev/null
+++ b/drivers/staging/media/mx3/Makefile
@@ -0,0 +1,3 @@
+# Makefile for i.MX3x Camera Sensor driver
+
+obj-$(CONFIG_VIDEO_MX3) += mx3_camera.o
diff --git a/drivers/staging/media/mx3/TODO b/drivers/staging/media/mx3/TODO
new file mode 100644
index 000000000000..bc68fa443a3e
--- /dev/null
+++ b/drivers/staging/media/mx3/TODO
@@ -0,0 +1,10 @@
+This driver is deprecated: it should become a stand-alone driver instead of
+using the soc-camera framework.
+
+Unless someone is willing to take this on (unlikely with such ancient
+hardware) it is going to be removed from the kernel soon.
+
+Note that trivial patches will not be accepted anymore, only a full conversion.
+
+If you want to convert this driver, please contact the linux-media mailinglist
+(see http://linuxtv.org/lists.php).
diff --git a/drivers/media/platform/soc_camera/mx3_camera.c b/drivers/staging/media/mx3/mx3_camera.c
index 169ed1150226..aa39e9569b1a 100644
--- a/drivers/media/platform/soc_camera/mx3_camera.c
+++ b/drivers/staging/media/mx3/mx3_camera.c
@@ -146,8 +146,8 @@ static void mx3_cam_dma_done(void *arg)
 	struct idmac_channel *ichannel = to_idmac_chan(chan);
 	struct mx3_camera_dev *mx3_cam = ichannel->client;
 
-	dev_dbg(chan->device->dev, "callback cookie %d, active DMA 0x%08x\n",
-		desc->txd.cookie, mx3_cam->active ? sg_dma_address(&mx3_cam->active->sg) : 0);
+	dev_dbg(chan->device->dev, "callback cookie %d, active DMA %pad\n",
+		desc->txd.cookie, mx3_cam->active ? &sg_dma_address(&mx3_cam->active->sg) : NULL);
 
 	spin_lock(&mx3_cam->lock);
 	if (mx3_cam->active) {
@@ -314,8 +314,8 @@ static void mx3_videobuf_queue(struct vb2_buffer *vb)
 	spin_unlock_irq(&mx3_cam->lock);
 
 	cookie = txd->tx_submit(txd);
-	dev_dbg(icd->parent, "Submitted cookie %d DMA 0x%08x\n",
-		cookie, sg_dma_address(&buf->sg));
+	dev_dbg(icd->parent, "Submitted cookie %d DMA %pad\n",
+		cookie, &sg_dma_address(&buf->sg));
 
 	if (cookie >= 0)
 		return;
@@ -344,8 +344,8 @@ static void mx3_videobuf_release(struct vb2_buffer *vb)
 	unsigned long flags;
 
 	dev_dbg(icd->parent,
-		"Release%s DMA 0x%08x, queue %sempty\n",
-		mx3_cam->active == buf ? " active" : "", sg_dma_address(&buf->sg),
+		"Release%s DMA %pad, queue %sempty\n",
+		mx3_cam->active == buf ? " active" : "", &sg_dma_address(&buf->sg),
 		list_empty(&buf->queue) ? "" : "not ");
 
 	spin_lock_irqsave(&mx3_cam->lock, flags);
diff --git a/drivers/staging/media/omap1/Kconfig b/drivers/staging/media/omap1/Kconfig
new file mode 100644
index 000000000000..6cfab3a04ae1
--- /dev/null
+++ b/drivers/staging/media/omap1/Kconfig
@@ -0,0 +1,13 @@
+config VIDEO_OMAP1
+	tristate "OMAP1 Camera Interface driver"
+	depends on VIDEO_DEV && SOC_CAMERA
+	depends on ARCH_OMAP1
+	depends on HAS_DMA
+	select VIDEOBUF_DMA_CONTIG
+	select VIDEOBUF_DMA_SG
+	---help---
+	  This is a v4l2 driver for the TI OMAP1 camera interface
+
+	  This driver is deprecated and will be removed soon unless someone
+	  will start the work to convert this driver to the vb2 framework
+	  and remove the soc-camera dependency.
diff --git a/drivers/staging/media/omap1/Makefile b/drivers/staging/media/omap1/Makefile
new file mode 100644
index 000000000000..2885622600f2
--- /dev/null
+++ b/drivers/staging/media/omap1/Makefile
@@ -0,0 +1,3 @@
+# Makefile for OMAP1 driver
+
+obj-$(CONFIG_VIDEO_OMAP1) += omap1_camera.o
diff --git a/drivers/staging/media/omap1/TODO b/drivers/staging/media/omap1/TODO
new file mode 100644
index 000000000000..1025f9f60ff0
--- /dev/null
+++ b/drivers/staging/media/omap1/TODO
@@ -0,0 +1,8 @@
+This driver is deprecated and will be removed soon unless someone will start
+the work to convert this driver to the vb2 framework and remove the
+soc-camera dependency.
+
+Note that trivial patches will not be accepted anymore, only a full conversion.
+
+If you want to convert this driver, please contact the linux-media mailinglist
+(see http://linuxtv.org/lists.php).
diff --git a/drivers/media/platform/soc_camera/omap1_camera.c b/drivers/staging/media/omap1/omap1_camera.c
index bd721e35474a..bd721e35474a 100644
--- a/drivers/media/platform/soc_camera/omap1_camera.c
+++ b/drivers/staging/media/omap1/omap1_camera.c
diff --git a/drivers/staging/media/omap4iss/iss.c b/drivers/staging/media/omap4iss/iss.c
index 30b473cfb020..fb80d2bc5a25 100644
--- a/drivers/staging/media/omap4iss/iss.c
+++ b/drivers/staging/media/omap4iss/iss.c
@@ -363,215 +363,6 @@ static irqreturn_t iss_isr(int irq, void *_iss)
 }
 
 /* -----------------------------------------------------------------------------
- * Pipeline power management
- *
- * Entities must be powered up when part of a pipeline that contains at least
- * one open video device node.
- *
- * To achieve this use the entity use_count field to track the number of users.
- * For entities corresponding to video device nodes the use_count field stores
- * the users count of the node. For entities corresponding to subdevs the
- * use_count field stores the total number of users of all video device nodes
- * in the pipeline.
- *
- * The omap4iss_pipeline_pm_use() function must be called in the open() and
- * close() handlers of video device nodes. It increments or decrements the use
- * count of all subdev entities in the pipeline.
- *
- * To react to link management on powered pipelines, the link setup notification
- * callback updates the use count of all entities in the source and sink sides
- * of the link.
- */
-
-/*
- * iss_pipeline_pm_use_count - Count the number of users of a pipeline
- * @entity: The entity
- *
- * Return the total number of users of all video device nodes in the pipeline.
- */
-static int iss_pipeline_pm_use_count(struct media_entity *entity,
-				     struct media_entity_graph *graph)
-{
-	int use = 0;
-
-	media_entity_graph_walk_start(graph, entity);
-
-	while ((entity = media_entity_graph_walk_next(graph))) {
-		if (is_media_entity_v4l2_io(entity))
-			use += entity->use_count;
-	}
-
-	return use;
-}
-
-/*
- * iss_pipeline_pm_power_one - Apply power change to an entity
- * @entity: The entity
- * @change: Use count change
- *
- * Change the entity use count by @change. If the entity is a subdev update its
- * power state by calling the core::s_power operation when the use count goes
- * from 0 to != 0 or from != 0 to 0.
- *
- * Return 0 on success or a negative error code on failure.
- */
-static int iss_pipeline_pm_power_one(struct media_entity *entity, int change)
-{
-	struct v4l2_subdev *subdev;
-
-	subdev = is_media_entity_v4l2_subdev(entity)
-	       ? media_entity_to_v4l2_subdev(entity) : NULL;
-
-	if (entity->use_count == 0 && change > 0 && subdev) {
-		int ret;
-
-		ret = v4l2_subdev_call(subdev, core, s_power, 1);
-		if (ret < 0 && ret != -ENOIOCTLCMD)
-			return ret;
-	}
-
-	entity->use_count += change;
-	WARN_ON(entity->use_count < 0);
-
-	if (entity->use_count == 0 && change < 0 && subdev)
-		v4l2_subdev_call(subdev, core, s_power, 0);
-
-	return 0;
-}
-
-/*
- * iss_pipeline_pm_power - Apply power change to all entities in a pipeline
- * @entity: The entity
- * @change: Use count change
- *
- * Walk the pipeline to update the use count and the power state of all non-node
- * entities.
- *
- * Return 0 on success or a negative error code on failure.
- */
-static int iss_pipeline_pm_power(struct media_entity *entity, int change,
-				 struct media_entity_graph *graph)
-{
-	struct media_entity *first = entity;
-	int ret = 0;
-
-	if (!change)
-		return 0;
-
-	media_entity_graph_walk_start(graph, entity);
-
-	while (!ret && (entity = media_entity_graph_walk_next(graph)))
-		if (is_media_entity_v4l2_subdev(entity))
-			ret = iss_pipeline_pm_power_one(entity, change);
-
-	if (!ret)
-		return 0;
-
-	media_entity_graph_walk_start(graph, first);
-
-	while ((first = media_entity_graph_walk_next(graph)) &&
-	       first != entity)
-		if (is_media_entity_v4l2_subdev(first))
-			iss_pipeline_pm_power_one(first, -change);
-
-	return ret;
-}
-
-/*
- * omap4iss_pipeline_pm_use - Update the use count of an entity
- * @entity: The entity
- * @use: Use (1) or stop using (0) the entity
- *
- * Update the use count of all entities in the pipeline and power entities on or
- * off accordingly.
- *
- * Return 0 on success or a negative error code on failure. Powering entities
- * off is assumed to never fail. No failure can occur when the use parameter is
- * set to 0.
- */
-int omap4iss_pipeline_pm_use(struct media_entity *entity, int use,
-			     struct media_entity_graph *graph)
-{
-	int change = use ? 1 : -1;
-	int ret;
-
-	mutex_lock(&entity->graph_obj.mdev->graph_mutex);
-
-	/* Apply use count to node. */
-	entity->use_count += change;
-	WARN_ON(entity->use_count < 0);
-
-	/* Apply power change to connected non-nodes. */
-	ret = iss_pipeline_pm_power(entity, change, graph);
-	if (ret < 0)
-		entity->use_count -= change;
-
-	mutex_unlock(&entity->graph_obj.mdev->graph_mutex);
-
-	return ret;
-}
-
-/*
- * iss_pipeline_link_notify - Link management notification callback
- * @link: The link
- * @flags: New link flags that will be applied
- *
- * React to link management on powered pipelines by updating the use count of
- * all entities in the source and sink sides of the link. Entities are powered
- * on or off accordingly.
- *
- * Return 0 on success or a negative error code on failure. Powering entities
- * off is assumed to never fail. This function will not fail for disconnection
- * events.
- */
-static int iss_pipeline_link_notify(struct media_link *link, u32 flags,
-				    unsigned int notification)
-{
-	struct media_entity_graph *graph =
-		&container_of(link->graph_obj.mdev, struct iss_device,
-			      media_dev)->pm_count_graph;
-	struct media_entity *source = link->source->entity;
-	struct media_entity *sink = link->sink->entity;
-	int source_use;
-	int sink_use;
-	int ret;
-
-	if (notification == MEDIA_DEV_NOTIFY_PRE_LINK_CH) {
-		ret = media_entity_graph_walk_init(graph,
-						   link->graph_obj.mdev);
-		if (ret)
-			return ret;
-	}
-
-	source_use = iss_pipeline_pm_use_count(source, graph);
-	sink_use = iss_pipeline_pm_use_count(sink, graph);
-
-	if (notification == MEDIA_DEV_NOTIFY_POST_LINK_CH &&
-	    !(flags & MEDIA_LNK_FL_ENABLED)) {
-		/* Powering off entities is assumed to never fail. */
-		iss_pipeline_pm_power(source, -sink_use, graph);
-		iss_pipeline_pm_power(sink, -source_use, graph);
-		return 0;
-	}
-
-	if (notification == MEDIA_DEV_NOTIFY_PRE_LINK_CH &&
-	    (flags & MEDIA_LNK_FL_ENABLED)) {
-		ret = iss_pipeline_pm_power(source, sink_use, graph);
-		if (ret < 0)
-			return ret;
-
-		ret = iss_pipeline_pm_power(sink, source_use, graph);
-		if (ret < 0)
-			iss_pipeline_pm_power(source, -sink_use, graph);
-	}
-
-	if (notification == MEDIA_DEV_NOTIFY_POST_LINK_CH)
-		media_entity_graph_walk_cleanup(graph);
-
-	return ret;
-}
-
-/* -----------------------------------------------------------------------------
  * Pipeline stream management
  */
 
@@ -1197,7 +988,7 @@ static int iss_register_entities(struct iss_device *iss)
 	strlcpy(iss->media_dev.model, "TI OMAP4 ISS",
 		sizeof(iss->media_dev.model));
 	iss->media_dev.hw_revision = iss->revision;
-	iss->media_dev.link_notify = iss_pipeline_link_notify;
+	iss->media_dev.link_notify = v4l2_pipeline_link_notify;
 	ret = media_device_register(&iss->media_dev);
 	if (ret < 0) {
 		dev_err(iss->dev, "Media device registration failed (%d)\n",
diff --git a/drivers/staging/media/omap4iss/iss.h b/drivers/staging/media/omap4iss/iss.h
index 05f08a3caa19..760ee27da704 100644
--- a/drivers/staging/media/omap4iss/iss.h
+++ b/drivers/staging/media/omap4iss/iss.h
@@ -15,6 +15,8 @@
 #define _OMAP4_ISS_H_
 
 #include <media/v4l2-device.h>
+#include <media/v4l2-mc.h>
+
 #include <linux/device.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
@@ -87,7 +89,6 @@ struct iss_reg {
 struct iss_device {
 	struct v4l2_device v4l2_dev;
 	struct media_device media_dev;
-	struct media_entity_graph pm_count_graph;
 	struct device *dev;
 	u32 revision;
 
@@ -152,9 +153,6 @@ void omap4iss_isp_subclk_enable(struct iss_device *iss,
 void omap4iss_isp_subclk_disable(struct iss_device *iss,
 				 enum iss_isp_subclk_resource res);
 
-int omap4iss_pipeline_pm_use(struct media_entity *entity, int use,
-			     struct media_entity_graph *graph);
-
 int omap4iss_register_entities(struct platform_device *pdev,
 			       struct v4l2_device *v4l2_dev);
 void omap4iss_unregister_entities(struct platform_device *pdev);
diff --git a/drivers/staging/media/omap4iss/iss_video.c b/drivers/staging/media/omap4iss/iss_video.c
index 058233a9de67..f54349bce4de 100644
--- a/drivers/staging/media/omap4iss/iss_video.c
+++ b/drivers/staging/media/omap4iss/iss_video.c
@@ -19,8 +19,10 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/module.h>
+
 #include <media/v4l2-dev.h>
 #include <media/v4l2-ioctl.h>
+#include <media/v4l2-mc.h>
 
 #include "iss_video.h"
 #include "iss.h"
@@ -1009,13 +1011,7 @@ static int iss_video_open(struct file *file)
 		goto done;
 	}
 
-	ret = media_entity_graph_walk_init(&handle->graph,
-					   &video->iss->media_dev);
-	if (ret)
-		goto done;
-
-	ret = omap4iss_pipeline_pm_use(&video->video.entity, 1,
-				       &handle->graph);
+	ret = v4l2_pipeline_pm_use(&video->video.entity, 1);
 	if (ret < 0) {
 		omap4iss_put(video->iss);
 		goto done;
@@ -1054,7 +1050,6 @@ static int iss_video_open(struct file *file)
 done:
 	if (ret < 0) {
 		v4l2_fh_del(&handle->vfh);
-		media_entity_graph_walk_cleanup(&handle->graph);
 		kfree(handle);
 	}
 
@@ -1070,13 +1065,11 @@ static int iss_video_release(struct file *file)
 	/* Disable streaming and free the buffers queue resources. */
 	iss_video_streamoff(file, vfh, video->type);
 
-	omap4iss_pipeline_pm_use(&video->video.entity, 0, &handle->graph);
+	v4l2_pipeline_pm_use(&video->video.entity, 0);
 
 	/* Release the videobuf2 queue */
 	vb2_queue_release(&handle->queue);
 
-	/* Release the file handle. */
-	media_entity_graph_walk_cleanup(&handle->graph);
 	v4l2_fh_del(vfh);
 	kfree(handle);
 	file->private_data = NULL;
diff --git a/drivers/staging/media/omap4iss/iss_video.h b/drivers/staging/media/omap4iss/iss_video.h
index 34588b7176ca..c8bd2958a3f8 100644
--- a/drivers/staging/media/omap4iss/iss_video.h
+++ b/drivers/staging/media/omap4iss/iss_video.h
@@ -183,7 +183,6 @@ struct iss_video_fh {
 	struct vb2_queue queue;
 	struct v4l2_format format;
 	struct v4l2_fract timeperframe;
-	struct media_entity_graph graph;
 };
 
 #define to_iss_video_fh(fh)	container_of(fh, struct iss_video_fh, vfh)
diff --git a/drivers/staging/media/timb/Kconfig b/drivers/staging/media/timb/Kconfig
new file mode 100644
index 000000000000..e413fecc1e67
--- /dev/null
+++ b/drivers/staging/media/timb/Kconfig
@@ -0,0 +1,11 @@
+config VIDEO_TIMBERDALE
+	tristate "Support for timberdale Video In/LogiWIN"
+	depends on VIDEO_V4L2 && I2C && VIDEO_V4L2_SUBDEV_API && HAS_DMA
+	depends on (MFD_TIMBERDALE && TIMB_DMA) || COMPILE_TEST
+	select VIDEO_ADV7180
+	select VIDEOBUF_DMA_CONTIG
+	---help---
+	  Add support for the Video In peripherial of the timberdale FPGA.
+
+	  This driver is deprecated and will be removed soon unless someone
+	  will start the work to convert this driver to the vb2 framework.
diff --git a/drivers/staging/media/timb/Makefile b/drivers/staging/media/timb/Makefile
new file mode 100644
index 000000000000..4c989c23a0e0
--- /dev/null
+++ b/drivers/staging/media/timb/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_VIDEO_TIMBERDALE)	+= timblogiw.o
diff --git a/drivers/media/platform/timblogiw.c b/drivers/staging/media/timb/timblogiw.c
index 113c9f3c0b3e..113c9f3c0b3e 100644
--- a/drivers/media/platform/timblogiw.c
+++ b/drivers/staging/media/timb/timblogiw.c
diff --git a/drivers/staging/rtl8192e/rtllib_crypt_tkip.c b/drivers/staging/rtl8192e/rtllib_crypt_tkip.c
index 2096d78913bd..8eac7cdd5f3e 100644
--- a/drivers/staging/rtl8192e/rtllib_crypt_tkip.c
+++ b/drivers/staging/rtl8192e/rtllib_crypt_tkip.c
@@ -9,6 +9,8 @@
  * more details.
  */
 
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -18,7 +20,6 @@
 #include <linux/if_ether.h>
 #include <linux/if_arp.h>
 #include <linux/string.h>
-#include <linux/crypto.h>
 #include <linux/scatterlist.h>
 #include <linux/crc32.h>
 #include <linux/etherdevice.h>
@@ -48,10 +49,10 @@ struct rtllib_tkip_data {
 	u32 dot11RSNAStatsTKIPLocalMICFailures;
 
 	int key_idx;
-	struct crypto_blkcipher *rx_tfm_arc4;
-	struct crypto_hash *rx_tfm_michael;
-	struct crypto_blkcipher *tx_tfm_arc4;
-	struct crypto_hash *tx_tfm_michael;
+	struct crypto_skcipher *rx_tfm_arc4;
+	struct crypto_ahash *rx_tfm_michael;
+	struct crypto_skcipher *tx_tfm_arc4;
+	struct crypto_ahash *tx_tfm_michael;
 	/* scratch buffers for virt_to_page() (crypto API) */
 	u8 rx_hdr[16];
 	u8 tx_hdr[16];
@@ -65,32 +66,32 @@ static void *rtllib_tkip_init(int key_idx)
 	if (priv == NULL)
 		goto fail;
 	priv->key_idx = key_idx;
-	priv->tx_tfm_arc4 = crypto_alloc_blkcipher("ecb(arc4)", 0,
-			CRYPTO_ALG_ASYNC);
+	priv->tx_tfm_arc4 = crypto_alloc_skcipher("ecb(arc4)", 0,
+						  CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->tx_tfm_arc4)) {
 		pr_debug("Could not allocate crypto API arc4\n");
 		priv->tx_tfm_arc4 = NULL;
 		goto fail;
 	}
 
-	priv->tx_tfm_michael = crypto_alloc_hash("michael_mic", 0,
-			CRYPTO_ALG_ASYNC);
+	priv->tx_tfm_michael = crypto_alloc_ahash("michael_mic", 0,
+						  CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->tx_tfm_michael)) {
 		pr_debug("Could not allocate crypto API michael_mic\n");
 		priv->tx_tfm_michael = NULL;
 		goto fail;
 	}
 
-	priv->rx_tfm_arc4 = crypto_alloc_blkcipher("ecb(arc4)", 0,
-			CRYPTO_ALG_ASYNC);
+	priv->rx_tfm_arc4 = crypto_alloc_skcipher("ecb(arc4)", 0,
+						  CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->rx_tfm_arc4)) {
 		pr_debug("Could not allocate crypto API arc4\n");
 		priv->rx_tfm_arc4 = NULL;
 		goto fail;
 	}
 
-	priv->rx_tfm_michael = crypto_alloc_hash("michael_mic", 0,
-			CRYPTO_ALG_ASYNC);
+	priv->rx_tfm_michael = crypto_alloc_ahash("michael_mic", 0,
+						  CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->rx_tfm_michael)) {
 		pr_debug("Could not allocate crypto API michael_mic\n");
 		priv->rx_tfm_michael = NULL;
@@ -100,14 +101,10 @@ static void *rtllib_tkip_init(int key_idx)
 
 fail:
 	if (priv) {
-		if (priv->tx_tfm_michael)
-			crypto_free_hash(priv->tx_tfm_michael);
-		if (priv->tx_tfm_arc4)
-			crypto_free_blkcipher(priv->tx_tfm_arc4);
-		if (priv->rx_tfm_michael)
-			crypto_free_hash(priv->rx_tfm_michael);
-		if (priv->rx_tfm_arc4)
-			crypto_free_blkcipher(priv->rx_tfm_arc4);
+		crypto_free_ahash(priv->tx_tfm_michael);
+		crypto_free_skcipher(priv->tx_tfm_arc4);
+		crypto_free_ahash(priv->rx_tfm_michael);
+		crypto_free_skcipher(priv->rx_tfm_arc4);
 		kfree(priv);
 	}
 
@@ -120,14 +117,10 @@ static void rtllib_tkip_deinit(void *priv)
 	struct rtllib_tkip_data *_priv = priv;
 
 	if (_priv) {
-		if (_priv->tx_tfm_michael)
-			crypto_free_hash(_priv->tx_tfm_michael);
-		if (_priv->tx_tfm_arc4)
-			crypto_free_blkcipher(_priv->tx_tfm_arc4);
-		if (_priv->rx_tfm_michael)
-			crypto_free_hash(_priv->rx_tfm_michael);
-		if (_priv->rx_tfm_arc4)
-			crypto_free_blkcipher(_priv->rx_tfm_arc4);
+		crypto_free_ahash(_priv->tx_tfm_michael);
+		crypto_free_skcipher(_priv->tx_tfm_arc4);
+		crypto_free_ahash(_priv->rx_tfm_michael);
+		crypto_free_skcipher(_priv->rx_tfm_arc4);
 	}
 	kfree(priv);
 }
@@ -301,7 +294,6 @@ static int rtllib_tkip_encrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	struct rtllib_hdr_4addr *hdr;
 	struct cb_desc *tcb_desc = (struct cb_desc *)(skb->cb +
 				    MAX_DEV_ADDR_SIZE);
-	struct blkcipher_desc desc = {.tfm = tkey->tx_tfm_arc4};
 	int ret = 0;
 	u8 rc4key[16],  *icv;
 	u32 crc;
@@ -347,6 +339,8 @@ static int rtllib_tkip_encrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	*pos++ = (tkey->tx_iv32 >> 24) & 0xff;
 
 	if (!tcb_desc->bHwSec) {
+		SKCIPHER_REQUEST_ON_STACK(req, tkey->tx_tfm_arc4);
+
 		icv = skb_put(skb, 4);
 		crc = ~crc32_le(~0, pos, len);
 		icv[0] = crc;
@@ -357,8 +351,12 @@ static int rtllib_tkip_encrypt(struct sk_buff *skb, int hdr_len, void *priv)
 		sg_init_one(&sg, pos, len+4);
 
 
-		crypto_blkcipher_setkey(tkey->tx_tfm_arc4, rc4key, 16);
-		ret = crypto_blkcipher_encrypt(&desc, &sg, &sg, len + 4);
+		crypto_skcipher_setkey(tkey->tx_tfm_arc4, rc4key, 16);
+		skcipher_request_set_tfm(req, tkey->tx_tfm_arc4);
+		skcipher_request_set_callback(req, 0, NULL, NULL);
+		skcipher_request_set_crypt(req, &sg, &sg, len + 4, NULL);
+		ret = crypto_skcipher_encrypt(req);
+		skcipher_request_zero(req);
 	}
 
 	tkey->tx_iv16++;
@@ -384,12 +382,12 @@ static int rtllib_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	struct rtllib_hdr_4addr *hdr;
 	struct cb_desc *tcb_desc = (struct cb_desc *)(skb->cb +
 				    MAX_DEV_ADDR_SIZE);
-	struct blkcipher_desc desc = {.tfm = tkey->rx_tfm_arc4};
 	u8 rc4key[16];
 	u8 icv[4];
 	u32 crc;
 	struct scatterlist sg;
 	int plen;
+	int err;
 
 	if (skb->len < hdr_len + 8 + 4)
 		return -1;
@@ -425,6 +423,8 @@ static int rtllib_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	pos += 8;
 
 	if (!tcb_desc->bHwSec || (skb->cb[0] == 1)) {
+		SKCIPHER_REQUEST_ON_STACK(req, tkey->rx_tfm_arc4);
+
 		if ((iv32 < tkey->rx_iv32 ||
 		    (iv32 == tkey->rx_iv32 && iv16 <= tkey->rx_iv16)) &&
 		    tkey->initialized) {
@@ -450,8 +450,13 @@ static int rtllib_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 
 		sg_init_one(&sg, pos, plen+4);
 
-		crypto_blkcipher_setkey(tkey->rx_tfm_arc4, rc4key, 16);
-		if (crypto_blkcipher_decrypt(&desc, &sg, &sg, plen + 4)) {
+		crypto_skcipher_setkey(tkey->rx_tfm_arc4, rc4key, 16);
+		skcipher_request_set_tfm(req, tkey->rx_tfm_arc4);
+		skcipher_request_set_callback(req, 0, NULL, NULL);
+		skcipher_request_set_crypt(req, &sg, &sg, plen + 4, NULL);
+		err = crypto_skcipher_decrypt(req);
+		skcipher_request_zero(req);
+		if (err) {
 			if (net_ratelimit()) {
 				netdev_dbg(skb->dev,
 					   "Failed to decrypt received packet from %pM\n",
@@ -500,11 +505,12 @@ static int rtllib_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 }
 
 
-static int michael_mic(struct crypto_hash *tfm_michael, u8 *key, u8 *hdr,
+static int michael_mic(struct crypto_ahash *tfm_michael, u8 *key, u8 *hdr,
 		       u8 *data, size_t data_len, u8 *mic)
 {
-	struct hash_desc desc;
+	AHASH_REQUEST_ON_STACK(req, tfm_michael);
 	struct scatterlist sg[2];
+	int err;
 
 	if (tfm_michael == NULL) {
 		pr_warn("michael_mic: tfm_michael == NULL\n");
@@ -514,12 +520,15 @@ static int michael_mic(struct crypto_hash *tfm_michael, u8 *key, u8 *hdr,
 	sg_set_buf(&sg[0], hdr, 16);
 	sg_set_buf(&sg[1], data, data_len);
 
-	if (crypto_hash_setkey(tfm_michael, key, 8))
+	if (crypto_ahash_setkey(tfm_michael, key, 8))
 		return -1;
 
-	desc.tfm = tfm_michael;
-	desc.flags = 0;
-	return crypto_hash_digest(&desc, sg, data_len + 16, mic);
+	ahash_request_set_tfm(req, tfm_michael);
+	ahash_request_set_callback(req, 0, NULL, NULL);
+	ahash_request_set_crypt(req, sg, mic, data_len + 16);
+	err = crypto_ahash_digest(req);
+	ahash_request_zero(req);
+	return err;
 }
 
 static void michael_mic_hdr(struct sk_buff *skb, u8 *hdr)
@@ -655,10 +664,10 @@ static int rtllib_tkip_set_key(void *key, int len, u8 *seq, void *priv)
 {
 	struct rtllib_tkip_data *tkey = priv;
 	int keyidx;
-	struct crypto_hash *tfm = tkey->tx_tfm_michael;
-	struct crypto_blkcipher *tfm2 = tkey->tx_tfm_arc4;
-	struct crypto_hash *tfm3 = tkey->rx_tfm_michael;
-	struct crypto_blkcipher *tfm4 = tkey->rx_tfm_arc4;
+	struct crypto_ahash *tfm = tkey->tx_tfm_michael;
+	struct crypto_skcipher *tfm2 = tkey->tx_tfm_arc4;
+	struct crypto_ahash *tfm3 = tkey->rx_tfm_michael;
+	struct crypto_skcipher *tfm4 = tkey->rx_tfm_arc4;
 
 	keyidx = tkey->key_idx;
 	memset(tkey, 0, sizeof(*tkey));
diff --git a/drivers/staging/rtl8192e/rtllib_crypt_wep.c b/drivers/staging/rtl8192e/rtllib_crypt_wep.c
index 21d7eee4c9a9..b3343a5d0fd6 100644
--- a/drivers/staging/rtl8192e/rtllib_crypt_wep.c
+++ b/drivers/staging/rtl8192e/rtllib_crypt_wep.c
@@ -9,6 +9,7 @@
  * more details.
  */
 
+#include <crypto/skcipher.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -17,8 +18,6 @@
 #include <linux/string.h>
 #include "rtllib.h"
 
-#include <linux/crypto.h>
-
 #include <linux/scatterlist.h>
 #include <linux/crc32.h>
 
@@ -28,8 +27,8 @@ struct prism2_wep_data {
 	u8 key[WEP_KEY_LEN + 1];
 	u8 key_len;
 	u8 key_idx;
-	struct crypto_blkcipher *tx_tfm;
-	struct crypto_blkcipher *rx_tfm;
+	struct crypto_skcipher *tx_tfm;
+	struct crypto_skcipher *rx_tfm;
 };
 
 
@@ -42,13 +41,13 @@ static void *prism2_wep_init(int keyidx)
 		goto fail;
 	priv->key_idx = keyidx;
 
-	priv->tx_tfm = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
+	priv->tx_tfm = crypto_alloc_skcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->tx_tfm)) {
 		pr_debug("rtllib_crypt_wep: could not allocate crypto API arc4\n");
 		priv->tx_tfm = NULL;
 		goto fail;
 	}
-	priv->rx_tfm = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
+	priv->rx_tfm = crypto_alloc_skcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->rx_tfm)) {
 		pr_debug("rtllib_crypt_wep: could not allocate crypto API arc4\n");
 		priv->rx_tfm = NULL;
@@ -62,10 +61,8 @@ static void *prism2_wep_init(int keyidx)
 
 fail:
 	if (priv) {
-		if (priv->tx_tfm)
-			crypto_free_blkcipher(priv->tx_tfm);
-		if (priv->rx_tfm)
-			crypto_free_blkcipher(priv->rx_tfm);
+		crypto_free_skcipher(priv->tx_tfm);
+		crypto_free_skcipher(priv->rx_tfm);
 		kfree(priv);
 	}
 	return NULL;
@@ -77,10 +74,8 @@ static void prism2_wep_deinit(void *priv)
 	struct prism2_wep_data *_priv = priv;
 
 	if (_priv) {
-		if (_priv->tx_tfm)
-			crypto_free_blkcipher(_priv->tx_tfm);
-		if (_priv->rx_tfm)
-			crypto_free_blkcipher(_priv->rx_tfm);
+		crypto_free_skcipher(_priv->tx_tfm);
+		crypto_free_skcipher(_priv->rx_tfm);
 	}
 	kfree(priv);
 }
@@ -99,10 +94,10 @@ static int prism2_wep_encrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	u8 *pos;
 	struct cb_desc *tcb_desc = (struct cb_desc *)(skb->cb +
 				    MAX_DEV_ADDR_SIZE);
-	struct blkcipher_desc desc = {.tfm = wep->tx_tfm};
 	u32 crc;
 	u8 *icv;
 	struct scatterlist sg;
+	int err;
 
 	if (skb_headroom(skb) < 4 || skb_tailroom(skb) < 4 ||
 	    skb->len < hdr_len){
@@ -140,6 +135,7 @@ static int prism2_wep_encrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	memcpy(key + 3, wep->key, wep->key_len);
 
 	if (!tcb_desc->bHwSec) {
+		SKCIPHER_REQUEST_ON_STACK(req, wep->tx_tfm);
 
 		/* Append little-endian CRC32 and encrypt it to produce ICV */
 		crc = ~crc32_le(~0, pos, len);
@@ -150,8 +146,13 @@ static int prism2_wep_encrypt(struct sk_buff *skb, int hdr_len, void *priv)
 		icv[3] = crc >> 24;
 
 		sg_init_one(&sg, pos, len+4);
-		crypto_blkcipher_setkey(wep->tx_tfm, key, klen);
-		return crypto_blkcipher_encrypt(&desc, &sg, &sg, len + 4);
+		crypto_skcipher_setkey(wep->tx_tfm, key, klen);
+		skcipher_request_set_tfm(req, wep->tx_tfm);
+		skcipher_request_set_callback(req, 0, NULL, NULL);
+		skcipher_request_set_crypt(req, &sg, &sg, len + 4, NULL);
+		err = crypto_skcipher_encrypt(req);
+		skcipher_request_zero(req);
+		return err;
 	}
 
 	return 0;
@@ -173,10 +174,10 @@ static int prism2_wep_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	u8 keyidx, *pos;
 	struct cb_desc *tcb_desc = (struct cb_desc *)(skb->cb +
 				    MAX_DEV_ADDR_SIZE);
-	struct blkcipher_desc desc = {.tfm = wep->rx_tfm};
 	u32 crc;
 	u8 icv[4];
 	struct scatterlist sg;
+	int err;
 
 	if (skb->len < hdr_len + 8)
 		return -1;
@@ -198,9 +199,16 @@ static int prism2_wep_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	plen = skb->len - hdr_len - 8;
 
 	if (!tcb_desc->bHwSec) {
+		SKCIPHER_REQUEST_ON_STACK(req, wep->rx_tfm);
+
 		sg_init_one(&sg, pos, plen+4);
-		crypto_blkcipher_setkey(wep->rx_tfm, key, klen);
-		if (crypto_blkcipher_decrypt(&desc, &sg, &sg, plen + 4))
+		crypto_skcipher_setkey(wep->rx_tfm, key, klen);
+		skcipher_request_set_tfm(req, wep->rx_tfm);
+		skcipher_request_set_callback(req, 0, NULL, NULL);
+		skcipher_request_set_crypt(req, &sg, &sg, plen + 4, NULL);
+		err = crypto_skcipher_decrypt(req);
+		skcipher_request_zero(req);
+		if (err)
 			return -7;
 		crc = ~crc32_le(~0, pos, plen);
 		icv[0] = crc;
diff --git a/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_tkip.c b/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_tkip.c
index 908bc2eb4d29..6fa96d57d316 100644
--- a/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_tkip.c
+++ b/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_tkip.c
@@ -21,7 +21,8 @@
 
 #include "ieee80211.h"
 
-#include <linux/crypto.h>
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
 	#include <linux/scatterlist.h>
 #include <linux/crc32.h>
 
@@ -52,10 +53,10 @@ struct ieee80211_tkip_data {
 
 	int key_idx;
 
-	struct crypto_blkcipher *rx_tfm_arc4;
-	struct crypto_hash *rx_tfm_michael;
-	struct crypto_blkcipher *tx_tfm_arc4;
-	struct crypto_hash *tx_tfm_michael;
+	struct crypto_skcipher *rx_tfm_arc4;
+	struct crypto_ahash *rx_tfm_michael;
+	struct crypto_skcipher *tx_tfm_arc4;
+	struct crypto_ahash *tx_tfm_michael;
 
 	/* scratch buffers for virt_to_page() (crypto API) */
 	u8 rx_hdr[16], tx_hdr[16];
@@ -70,7 +71,7 @@ static void *ieee80211_tkip_init(int key_idx)
 		goto fail;
 	priv->key_idx = key_idx;
 
-	priv->tx_tfm_arc4 = crypto_alloc_blkcipher("ecb(arc4)", 0,
+	priv->tx_tfm_arc4 = crypto_alloc_skcipher("ecb(arc4)", 0,
 			CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->tx_tfm_arc4)) {
 		printk(KERN_DEBUG "ieee80211_crypt_tkip: could not allocate "
@@ -79,7 +80,7 @@ static void *ieee80211_tkip_init(int key_idx)
 		goto fail;
 	}
 
-	priv->tx_tfm_michael = crypto_alloc_hash("michael_mic", 0,
+	priv->tx_tfm_michael = crypto_alloc_ahash("michael_mic", 0,
 			CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->tx_tfm_michael)) {
 		printk(KERN_DEBUG "ieee80211_crypt_tkip: could not allocate "
@@ -88,7 +89,7 @@ static void *ieee80211_tkip_init(int key_idx)
 		goto fail;
 	}
 
-	priv->rx_tfm_arc4 = crypto_alloc_blkcipher("ecb(arc4)", 0,
+	priv->rx_tfm_arc4 = crypto_alloc_skcipher("ecb(arc4)", 0,
 			CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->rx_tfm_arc4)) {
 		printk(KERN_DEBUG "ieee80211_crypt_tkip: could not allocate "
@@ -97,7 +98,7 @@ static void *ieee80211_tkip_init(int key_idx)
 		goto fail;
 	}
 
-	priv->rx_tfm_michael = crypto_alloc_hash("michael_mic", 0,
+	priv->rx_tfm_michael = crypto_alloc_ahash("michael_mic", 0,
 			CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->rx_tfm_michael)) {
 		printk(KERN_DEBUG "ieee80211_crypt_tkip: could not allocate "
@@ -110,14 +111,10 @@ static void *ieee80211_tkip_init(int key_idx)
 
 fail:
 	if (priv) {
-		if (priv->tx_tfm_michael)
-			crypto_free_hash(priv->tx_tfm_michael);
-		if (priv->tx_tfm_arc4)
-			crypto_free_blkcipher(priv->tx_tfm_arc4);
-		if (priv->rx_tfm_michael)
-			crypto_free_hash(priv->rx_tfm_michael);
-		if (priv->rx_tfm_arc4)
-			crypto_free_blkcipher(priv->rx_tfm_arc4);
+		crypto_free_ahash(priv->tx_tfm_michael);
+		crypto_free_skcipher(priv->tx_tfm_arc4);
+		crypto_free_ahash(priv->rx_tfm_michael);
+		crypto_free_skcipher(priv->rx_tfm_arc4);
 		kfree(priv);
 	}
 
@@ -130,14 +127,10 @@ static void ieee80211_tkip_deinit(void *priv)
 	struct ieee80211_tkip_data *_priv = priv;
 
 	if (_priv) {
-		if (_priv->tx_tfm_michael)
-			crypto_free_hash(_priv->tx_tfm_michael);
-		if (_priv->tx_tfm_arc4)
-			crypto_free_blkcipher(_priv->tx_tfm_arc4);
-		if (_priv->rx_tfm_michael)
-			crypto_free_hash(_priv->rx_tfm_michael);
-		if (_priv->rx_tfm_arc4)
-			crypto_free_blkcipher(_priv->rx_tfm_arc4);
+		crypto_free_ahash(_priv->tx_tfm_michael);
+		crypto_free_skcipher(_priv->tx_tfm_arc4);
+		crypto_free_ahash(_priv->rx_tfm_michael);
+		crypto_free_skcipher(_priv->rx_tfm_arc4);
 	}
 	kfree(priv);
 }
@@ -312,7 +305,6 @@ static int ieee80211_tkip_encrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	u8 *pos;
 	struct rtl_80211_hdr_4addr *hdr;
 	cb_desc *tcb_desc = (cb_desc *)(skb->cb + MAX_DEV_ADDR_SIZE);
-	struct blkcipher_desc desc = {.tfm = tkey->tx_tfm_arc4};
 	int ret = 0;
 	u8 rc4key[16],  *icv;
 	u32 crc;
@@ -357,15 +349,21 @@ static int ieee80211_tkip_encrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	*pos++ = (tkey->tx_iv32 >> 24) & 0xff;
 
 	if (!tcb_desc->bHwSec) {
+		SKCIPHER_REQUEST_ON_STACK(req, tkey->tx_tfm_arc4);
+
 		icv = skb_put(skb, 4);
 		crc = ~crc32_le(~0, pos, len);
 		icv[0] = crc;
 		icv[1] = crc >> 8;
 		icv[2] = crc >> 16;
 		icv[3] = crc >> 24;
-		crypto_blkcipher_setkey(tkey->tx_tfm_arc4, rc4key, 16);
+		crypto_skcipher_setkey(tkey->tx_tfm_arc4, rc4key, 16);
 		sg_init_one(&sg, pos, len+4);
-		ret = crypto_blkcipher_encrypt(&desc, &sg, &sg, len + 4);
+		skcipher_request_set_tfm(req, tkey->tx_tfm_arc4);
+		skcipher_request_set_callback(req, 0, NULL, NULL);
+		skcipher_request_set_crypt(req, &sg, &sg, len + 4, NULL);
+		ret = crypto_skcipher_encrypt(req);
+		skcipher_request_zero(req);
 	}
 
 	tkey->tx_iv16++;
@@ -390,12 +388,12 @@ static int ieee80211_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	u16 iv16;
 	struct rtl_80211_hdr_4addr *hdr;
 	cb_desc *tcb_desc = (cb_desc *)(skb->cb + MAX_DEV_ADDR_SIZE);
-	struct blkcipher_desc desc = {.tfm = tkey->rx_tfm_arc4};
 	u8 rc4key[16];
 	u8 icv[4];
 	u32 crc;
 	struct scatterlist sg;
 	int plen;
+	int err;
 
 	if (skb->len < hdr_len + 8 + 4)
 		return -1;
@@ -429,6 +427,8 @@ static int ieee80211_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	pos += 8;
 
 	if (!tcb_desc->bHwSec) {
+		SKCIPHER_REQUEST_ON_STACK(req, tkey->rx_tfm_arc4);
+
 		if (iv32 < tkey->rx_iv32 ||
 		(iv32 == tkey->rx_iv32 && iv16 <= tkey->rx_iv16)) {
 			if (net_ratelimit()) {
@@ -449,10 +449,16 @@ static int ieee80211_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 
 		plen = skb->len - hdr_len - 12;
 
-		crypto_blkcipher_setkey(tkey->rx_tfm_arc4, rc4key, 16);
+		crypto_skcipher_setkey(tkey->rx_tfm_arc4, rc4key, 16);
 		sg_init_one(&sg, pos, plen+4);
 
-		if (crypto_blkcipher_decrypt(&desc, &sg, &sg, plen + 4)) {
+		skcipher_request_set_tfm(req, tkey->rx_tfm_arc4);
+		skcipher_request_set_callback(req, 0, NULL, NULL);
+		skcipher_request_set_crypt(req, &sg, &sg, plen + 4, NULL);
+
+		err = crypto_skcipher_decrypt(req);
+		skcipher_request_zero(req);
+		if (err) {
 			if (net_ratelimit()) {
 				printk(KERN_DEBUG ": TKIP: failed to decrypt "
 						"received packet from %pM\n",
@@ -501,11 +507,12 @@ static int ieee80211_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	return keyidx;
 }
 
-static int michael_mic(struct crypto_hash *tfm_michael, u8 *key, u8 *hdr,
+static int michael_mic(struct crypto_ahash *tfm_michael, u8 *key, u8 *hdr,
 		       u8 *data, size_t data_len, u8 *mic)
 {
-	struct hash_desc desc;
+	AHASH_REQUEST_ON_STACK(req, tfm_michael);
 	struct scatterlist sg[2];
+	int err;
 
 	if (tfm_michael == NULL) {
 		printk(KERN_WARNING "michael_mic: tfm_michael == NULL\n");
@@ -516,12 +523,15 @@ static int michael_mic(struct crypto_hash *tfm_michael, u8 *key, u8 *hdr,
 	sg_set_buf(&sg[0], hdr, 16);
 	sg_set_buf(&sg[1], data, data_len);
 
-	if (crypto_hash_setkey(tfm_michael, key, 8))
+	if (crypto_ahash_setkey(tfm_michael, key, 8))
 		return -1;
 
-	desc.tfm = tfm_michael;
-	desc.flags = 0;
-	return crypto_hash_digest(&desc, sg, data_len + 16, mic);
+	ahash_request_set_tfm(req, tfm_michael);
+	ahash_request_set_callback(req, 0, NULL, NULL);
+	ahash_request_set_crypt(req, sg, mic, data_len + 16);
+	err = crypto_ahash_digest(req);
+	ahash_request_zero(req);
+	return err;
 }
 
 static void michael_mic_hdr(struct sk_buff *skb, u8 *hdr)
@@ -660,10 +670,10 @@ static int ieee80211_tkip_set_key(void *key, int len, u8 *seq, void *priv)
 {
 	struct ieee80211_tkip_data *tkey = priv;
 	int keyidx;
-	struct crypto_hash *tfm = tkey->tx_tfm_michael;
-	struct crypto_blkcipher *tfm2 = tkey->tx_tfm_arc4;
-	struct crypto_hash *tfm3 = tkey->rx_tfm_michael;
-	struct crypto_blkcipher *tfm4 = tkey->rx_tfm_arc4;
+	struct crypto_ahash *tfm = tkey->tx_tfm_michael;
+	struct crypto_skcipher *tfm2 = tkey->tx_tfm_arc4;
+	struct crypto_ahash *tfm3 = tkey->rx_tfm_michael;
+	struct crypto_skcipher *tfm4 = tkey->rx_tfm_arc4;
 
 	keyidx = tkey->key_idx;
 	memset(tkey, 0, sizeof(*tkey));
diff --git a/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_wep.c b/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_wep.c
index 681611dc93d3..ababb6de125b 100644
--- a/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_wep.c
+++ b/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_wep.c
@@ -18,7 +18,7 @@
 
 #include "ieee80211.h"
 
-#include <linux/crypto.h>
+#include <crypto/skcipher.h>
 #include <linux/scatterlist.h>
 #include <linux/crc32.h>
 
@@ -32,8 +32,8 @@ struct prism2_wep_data {
 	u8 key[WEP_KEY_LEN + 1];
 	u8 key_len;
 	u8 key_idx;
-	struct crypto_blkcipher *tx_tfm;
-	struct crypto_blkcipher *rx_tfm;
+	struct crypto_skcipher *tx_tfm;
+	struct crypto_skcipher *rx_tfm;
 };
 
 
@@ -46,10 +46,10 @@ static void *prism2_wep_init(int keyidx)
 		return NULL;
 	priv->key_idx = keyidx;
 
-	priv->tx_tfm = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
+	priv->tx_tfm = crypto_alloc_skcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->tx_tfm))
 		goto free_priv;
-	priv->rx_tfm = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
+	priv->rx_tfm = crypto_alloc_skcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->rx_tfm))
 		goto free_tx;
 
@@ -58,7 +58,7 @@ static void *prism2_wep_init(int keyidx)
 
 	return priv;
 free_tx:
-	crypto_free_blkcipher(priv->tx_tfm);
+	crypto_free_skcipher(priv->tx_tfm);
 free_priv:
 	kfree(priv);
 	return NULL;
@@ -70,10 +70,8 @@ static void prism2_wep_deinit(void *priv)
 	struct prism2_wep_data *_priv = priv;
 
 	if (_priv) {
-		if (_priv->tx_tfm)
-			crypto_free_blkcipher(_priv->tx_tfm);
-		if (_priv->rx_tfm)
-			crypto_free_blkcipher(_priv->rx_tfm);
+		crypto_free_skcipher(_priv->tx_tfm);
+		crypto_free_skcipher(_priv->rx_tfm);
 	}
 	kfree(priv);
 }
@@ -91,10 +89,10 @@ static int prism2_wep_encrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	u8 key[WEP_KEY_LEN + 3];
 	u8 *pos;
 	cb_desc *tcb_desc = (cb_desc *)(skb->cb + MAX_DEV_ADDR_SIZE);
-	struct blkcipher_desc desc = {.tfm = wep->tx_tfm};
 	u32 crc;
 	u8 *icv;
 	struct scatterlist sg;
+	int err;
 
 	if (skb_headroom(skb) < 4 || skb_tailroom(skb) < 4 ||
 	    skb->len < hdr_len)
@@ -129,6 +127,8 @@ static int prism2_wep_encrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	memcpy(key + 3, wep->key, wep->key_len);
 
 	if (!tcb_desc->bHwSec) {
+		SKCIPHER_REQUEST_ON_STACK(req, wep->tx_tfm);
+
 		/* Append little-endian CRC32 and encrypt it to produce ICV */
 		crc = ~crc32_le(~0, pos, len);
 		icv = skb_put(skb, 4);
@@ -137,10 +137,16 @@ static int prism2_wep_encrypt(struct sk_buff *skb, int hdr_len, void *priv)
 		icv[2] = crc >> 16;
 		icv[3] = crc >> 24;
 
-		crypto_blkcipher_setkey(wep->tx_tfm, key, klen);
+		crypto_skcipher_setkey(wep->tx_tfm, key, klen);
 		sg_init_one(&sg, pos, len+4);
 
-		return crypto_blkcipher_encrypt(&desc, &sg, &sg, len + 4);
+		skcipher_request_set_tfm(req, wep->tx_tfm);
+		skcipher_request_set_callback(req, 0, NULL, NULL);
+		skcipher_request_set_crypt(req, &sg, &sg, len + 4, NULL);
+
+		err = crypto_skcipher_encrypt(req);
+		skcipher_request_zero(req);
+		return err;
 	}
 
 	return 0;
@@ -161,10 +167,10 @@ static int prism2_wep_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	u8 key[WEP_KEY_LEN + 3];
 	u8 keyidx, *pos;
 	cb_desc *tcb_desc = (cb_desc *)(skb->cb + MAX_DEV_ADDR_SIZE);
-	struct blkcipher_desc desc = {.tfm = wep->rx_tfm};
 	u32 crc;
 	u8 icv[4];
 	struct scatterlist sg;
+	int err;
 
 	if (skb->len < hdr_len + 8)
 		return -1;
@@ -186,10 +192,18 @@ static int prism2_wep_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	plen = skb->len - hdr_len - 8;
 
 	if (!tcb_desc->bHwSec) {
-		crypto_blkcipher_setkey(wep->rx_tfm, key, klen);
+		SKCIPHER_REQUEST_ON_STACK(req, wep->rx_tfm);
+
+		crypto_skcipher_setkey(wep->rx_tfm, key, klen);
 		sg_init_one(&sg, pos, plen+4);
 
-		if (crypto_blkcipher_decrypt(&desc, &sg, &sg, plen + 4))
+		skcipher_request_set_tfm(req, wep->rx_tfm);
+		skcipher_request_set_callback(req, 0, NULL, NULL);
+		skcipher_request_set_crypt(req, &sg, &sg, plen + 4, NULL);
+
+		err = crypto_skcipher_decrypt(req);
+		skcipher_request_zero(req);
+		if (err)
 			return -7;
 
 		crc = ~crc32_le(~0, pos, plen);
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 576a7a43470c..961202f4e9aa 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -16,9 +16,9 @@
  * GNU General Public License for more details.
  ******************************************************************************/
 
+#include <crypto/hash.h>
 #include <linux/string.h>
 #include <linux/kthread.h>
-#include <linux/crypto.h>
 #include <linux/completion.h>
 #include <linux/module.h>
 #include <linux/vmalloc.h>
@@ -1190,7 +1190,7 @@ iscsit_handle_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 }
 
 static u32 iscsit_do_crypto_hash_sg(
-	struct hash_desc *hash,
+	struct ahash_request *hash,
 	struct iscsi_cmd *cmd,
 	u32 data_offset,
 	u32 data_length,
@@ -1201,7 +1201,7 @@ static u32 iscsit_do_crypto_hash_sg(
 	struct scatterlist *sg;
 	unsigned int page_off;
 
-	crypto_hash_init(hash);
+	crypto_ahash_init(hash);
 
 	sg = cmd->first_data_sg;
 	page_off = cmd->first_data_sg_off;
@@ -1209,7 +1209,8 @@ static u32 iscsit_do_crypto_hash_sg(
 	while (data_length) {
 		u32 cur_len = min_t(u32, data_length, (sg->length - page_off));
 
-		crypto_hash_update(hash, sg, cur_len);
+		ahash_request_set_crypt(hash, sg, NULL, cur_len);
+		crypto_ahash_update(hash);
 
 		data_length -= cur_len;
 		page_off = 0;
@@ -1221,33 +1222,34 @@ static u32 iscsit_do_crypto_hash_sg(
 		struct scatterlist pad_sg;
 
 		sg_init_one(&pad_sg, pad_bytes, padding);
-		crypto_hash_update(hash, &pad_sg, padding);
+		ahash_request_set_crypt(hash, &pad_sg, (u8 *)&data_crc,
+					padding);
+		crypto_ahash_finup(hash);
+	} else {
+		ahash_request_set_crypt(hash, NULL, (u8 *)&data_crc, 0);
+		crypto_ahash_final(hash);
 	}
-	crypto_hash_final(hash, (u8 *) &data_crc);
 
 	return data_crc;
 }
 
 static void iscsit_do_crypto_hash_buf(
-	struct hash_desc *hash,
+	struct ahash_request *hash,
 	const void *buf,
 	u32 payload_length,
 	u32 padding,
 	u8 *pad_bytes,
 	u8 *data_crc)
 {
-	struct scatterlist sg;
+	struct scatterlist sg[2];
 
-	crypto_hash_init(hash);
+	sg_init_table(sg, ARRAY_SIZE(sg));
+	sg_set_buf(sg, buf, payload_length);
+	sg_set_buf(sg + 1, pad_bytes, padding);
 
-	sg_init_one(&sg, buf, payload_length);
-	crypto_hash_update(hash, &sg, payload_length);
+	ahash_request_set_crypt(hash, sg, data_crc, payload_length + padding);
 
-	if (padding) {
-		sg_init_one(&sg, pad_bytes, padding);
-		crypto_hash_update(hash, &sg, padding);
-	}
-	crypto_hash_final(hash, data_crc);
+	crypto_ahash_digest(hash);
 }
 
 int
@@ -1422,7 +1424,7 @@ iscsit_get_dataout(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	if (conn->conn_ops->DataDigest) {
 		u32 data_crc;
 
-		data_crc = iscsit_do_crypto_hash_sg(&conn->conn_rx_hash, cmd,
+		data_crc = iscsit_do_crypto_hash_sg(conn->conn_rx_hash, cmd,
 						    be32_to_cpu(hdr->offset),
 						    payload_length, padding,
 						    cmd->pad_bytes);
@@ -1682,7 +1684,7 @@ static int iscsit_handle_nop_out(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 		}
 
 		if (conn->conn_ops->DataDigest) {
-			iscsit_do_crypto_hash_buf(&conn->conn_rx_hash,
+			iscsit_do_crypto_hash_buf(conn->conn_rx_hash,
 					ping_data, payload_length,
 					padding, cmd->pad_bytes,
 					(u8 *)&data_crc);
@@ -2101,7 +2103,7 @@ iscsit_handle_text_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 			goto reject;
 
 		if (conn->conn_ops->DataDigest) {
-			iscsit_do_crypto_hash_buf(&conn->conn_rx_hash,
+			iscsit_do_crypto_hash_buf(conn->conn_rx_hash,
 					text_in, payload_length,
 					padding, (u8 *)&pad_bytes,
 					(u8 *)&data_crc);
@@ -2440,7 +2442,7 @@ static int iscsit_handle_immediate_data(
 	if (conn->conn_ops->DataDigest) {
 		u32 data_crc;
 
-		data_crc = iscsit_do_crypto_hash_sg(&conn->conn_rx_hash, cmd,
+		data_crc = iscsit_do_crypto_hash_sg(conn->conn_rx_hash, cmd,
 						    cmd->write_data_done, length, padding,
 						    cmd->pad_bytes);
 
@@ -2553,7 +2555,7 @@ static int iscsit_send_conn_drop_async_message(
 	if (conn->conn_ops->HeaderDigest) {
 		u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
 
-		iscsit_do_crypto_hash_buf(&conn->conn_tx_hash, hdr,
+		iscsit_do_crypto_hash_buf(conn->conn_tx_hash, hdr,
 				ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
 
 		cmd->tx_size += ISCSI_CRC_LEN;
@@ -2683,7 +2685,7 @@ static int iscsit_send_datain(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
 	if (conn->conn_ops->HeaderDigest) {
 		u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
 
-		iscsit_do_crypto_hash_buf(&conn->conn_tx_hash, cmd->pdu,
+		iscsit_do_crypto_hash_buf(conn->conn_tx_hash, cmd->pdu,
 				ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
 
 		iov[0].iov_len += ISCSI_CRC_LEN;
@@ -2711,7 +2713,7 @@ static int iscsit_send_datain(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
 				cmd->padding);
 	}
 	if (conn->conn_ops->DataDigest) {
-		cmd->data_crc = iscsit_do_crypto_hash_sg(&conn->conn_tx_hash, cmd,
+		cmd->data_crc = iscsit_do_crypto_hash_sg(conn->conn_tx_hash, cmd,
 			 datain.offset, datain.length, cmd->padding, cmd->pad_bytes);
 
 		iov[iov_count].iov_base	= &cmd->data_crc;
@@ -2857,7 +2859,7 @@ iscsit_send_logout(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
 	if (conn->conn_ops->HeaderDigest) {
 		u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
 
-		iscsit_do_crypto_hash_buf(&conn->conn_tx_hash, &cmd->pdu[0],
+		iscsit_do_crypto_hash_buf(conn->conn_tx_hash, &cmd->pdu[0],
 				ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
 
 		iov[0].iov_len += ISCSI_CRC_LEN;
@@ -2915,7 +2917,7 @@ static int iscsit_send_unsolicited_nopin(
 	if (conn->conn_ops->HeaderDigest) {
 		u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
 
-		iscsit_do_crypto_hash_buf(&conn->conn_tx_hash, hdr,
+		iscsit_do_crypto_hash_buf(conn->conn_tx_hash, hdr,
 				ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
 
 		tx_size += ISCSI_CRC_LEN;
@@ -2963,7 +2965,7 @@ iscsit_send_nopin(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
 	if (conn->conn_ops->HeaderDigest) {
 		u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
 
-		iscsit_do_crypto_hash_buf(&conn->conn_tx_hash, hdr,
+		iscsit_do_crypto_hash_buf(conn->conn_tx_hash, hdr,
 				ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
 
 		iov[0].iov_len += ISCSI_CRC_LEN;
@@ -2993,7 +2995,7 @@ iscsit_send_nopin(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
 				" padding bytes.\n", padding);
 		}
 		if (conn->conn_ops->DataDigest) {
-			iscsit_do_crypto_hash_buf(&conn->conn_tx_hash,
+			iscsit_do_crypto_hash_buf(conn->conn_tx_hash,
 				cmd->buf_ptr, cmd->buf_ptr_size,
 				padding, (u8 *)&cmd->pad_bytes,
 				(u8 *)&cmd->data_crc);
@@ -3049,7 +3051,7 @@ static int iscsit_send_r2t(
 	if (conn->conn_ops->HeaderDigest) {
 		u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
 
-		iscsit_do_crypto_hash_buf(&conn->conn_tx_hash, hdr,
+		iscsit_do_crypto_hash_buf(conn->conn_tx_hash, hdr,
 				ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
 
 		cmd->iov_misc[0].iov_len += ISCSI_CRC_LEN;
@@ -3239,7 +3241,7 @@ static int iscsit_send_response(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
 		}
 
 		if (conn->conn_ops->DataDigest) {
-			iscsit_do_crypto_hash_buf(&conn->conn_tx_hash,
+			iscsit_do_crypto_hash_buf(conn->conn_tx_hash,
 				cmd->sense_buffer,
 				(cmd->se_cmd.scsi_sense_length + padding),
 				0, NULL, (u8 *)&cmd->data_crc);
@@ -3262,7 +3264,7 @@ static int iscsit_send_response(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
 	if (conn->conn_ops->HeaderDigest) {
 		u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
 
-		iscsit_do_crypto_hash_buf(&conn->conn_tx_hash, cmd->pdu,
+		iscsit_do_crypto_hash_buf(conn->conn_tx_hash, cmd->pdu,
 				ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
 
 		iov[0].iov_len += ISCSI_CRC_LEN;
@@ -3332,7 +3334,7 @@ iscsit_send_task_mgt_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
 	if (conn->conn_ops->HeaderDigest) {
 		u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
 
-		iscsit_do_crypto_hash_buf(&conn->conn_tx_hash, hdr,
+		iscsit_do_crypto_hash_buf(conn->conn_tx_hash, hdr,
 				ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
 
 		cmd->iov_misc[0].iov_len += ISCSI_CRC_LEN;
@@ -3601,7 +3603,7 @@ static int iscsit_send_text_rsp(
 	if (conn->conn_ops->HeaderDigest) {
 		u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
 
-		iscsit_do_crypto_hash_buf(&conn->conn_tx_hash, hdr,
+		iscsit_do_crypto_hash_buf(conn->conn_tx_hash, hdr,
 				ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
 
 		iov[0].iov_len += ISCSI_CRC_LEN;
@@ -3611,7 +3613,7 @@ static int iscsit_send_text_rsp(
 	}
 
 	if (conn->conn_ops->DataDigest) {
-		iscsit_do_crypto_hash_buf(&conn->conn_tx_hash,
+		iscsit_do_crypto_hash_buf(conn->conn_tx_hash,
 				cmd->buf_ptr, text_length,
 				0, NULL, (u8 *)&cmd->data_crc);
 
@@ -3668,7 +3670,7 @@ static int iscsit_send_reject(
 	if (conn->conn_ops->HeaderDigest) {
 		u32 *header_digest = (u32 *)&cmd->pdu[ISCSI_HDR_LEN];
 
-		iscsit_do_crypto_hash_buf(&conn->conn_tx_hash, hdr,
+		iscsit_do_crypto_hash_buf(conn->conn_tx_hash, hdr,
 				ISCSI_HDR_LEN, 0, NULL, (u8 *)header_digest);
 
 		iov[0].iov_len += ISCSI_CRC_LEN;
@@ -3678,7 +3680,7 @@ static int iscsit_send_reject(
 	}
 
 	if (conn->conn_ops->DataDigest) {
-		iscsit_do_crypto_hash_buf(&conn->conn_tx_hash, cmd->buf_ptr,
+		iscsit_do_crypto_hash_buf(conn->conn_tx_hash, cmd->buf_ptr,
 				ISCSI_HDR_LEN, 0, NULL, (u8 *)&cmd->data_crc);
 
 		iov[iov_count].iov_base = &cmd->data_crc;
@@ -4145,7 +4147,7 @@ int iscsi_target_rx_thread(void *arg)
 				goto transport_err;
 			}
 
-			iscsit_do_crypto_hash_buf(&conn->conn_rx_hash,
+			iscsit_do_crypto_hash_buf(conn->conn_rx_hash,
 					buffer, ISCSI_HDR_LEN,
 					0, NULL, (u8 *)&checksum);
 
@@ -4359,10 +4361,14 @@ int iscsit_close_connection(
 	 */
 	iscsit_check_conn_usage_count(conn);
 
-	if (conn->conn_rx_hash.tfm)
-		crypto_free_hash(conn->conn_rx_hash.tfm);
-	if (conn->conn_tx_hash.tfm)
-		crypto_free_hash(conn->conn_tx_hash.tfm);
+	ahash_request_free(conn->conn_tx_hash);
+	if (conn->conn_rx_hash) {
+		struct crypto_ahash *tfm;
+
+		tfm = crypto_ahash_reqtfm(conn->conn_rx_hash);
+		ahash_request_free(conn->conn_rx_hash);
+		crypto_free_ahash(tfm);
+	}
 
 	free_cpumask_var(conn->conn_cpumask);
 
diff --git a/drivers/target/iscsi/iscsi_target_auth.c b/drivers/target/iscsi/iscsi_target_auth.c
index 47e249dccb5f..667406fcf4d3 100644
--- a/drivers/target/iscsi/iscsi_target_auth.c
+++ b/drivers/target/iscsi/iscsi_target_auth.c
@@ -16,9 +16,9 @@
  * GNU General Public License for more details.
  ******************************************************************************/
 
+#include <crypto/hash.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/crypto.h>
 #include <linux/err.h>
 #include <linux/scatterlist.h>
 
@@ -185,9 +185,8 @@ static int chap_server_compute_md5(
 	unsigned char chap_n[MAX_CHAP_N_SIZE], chap_r[MAX_RESPONSE_LENGTH];
 	size_t compare_len;
 	struct iscsi_chap *chap = conn->auth_protocol;
-	struct crypto_hash *tfm;
-	struct hash_desc desc;
-	struct scatterlist sg;
+	struct crypto_shash *tfm = NULL;
+	struct shash_desc *desc = NULL;
 	int auth_ret = -1, ret, challenge_len;
 
 	memset(identifier, 0, 10);
@@ -245,52 +244,47 @@ static int chap_server_compute_md5(
 	pr_debug("[server] Got CHAP_R=%s\n", chap_r);
 	chap_string_to_hex(client_digest, chap_r, strlen(chap_r));
 
-	tfm = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
+	tfm = crypto_alloc_shash("md5", 0, 0);
 	if (IS_ERR(tfm)) {
-		pr_err("Unable to allocate struct crypto_hash\n");
+		tfm = NULL;
+		pr_err("Unable to allocate struct crypto_shash\n");
 		goto out;
 	}
-	desc.tfm = tfm;
-	desc.flags = 0;
 
-	ret = crypto_hash_init(&desc);
-	if (ret < 0) {
-		pr_err("crypto_hash_init() failed\n");
-		crypto_free_hash(tfm);
+	desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(tfm), GFP_KERNEL);
+	if (!desc) {
+		pr_err("Unable to allocate struct shash_desc\n");
 		goto out;
 	}
 
-	sg_init_one(&sg, &chap->id, 1);
-	ret = crypto_hash_update(&desc, &sg, 1);
+	desc->tfm = tfm;
+	desc->flags = 0;
+
+	ret = crypto_shash_init(desc);
 	if (ret < 0) {
-		pr_err("crypto_hash_update() failed for id\n");
-		crypto_free_hash(tfm);
+		pr_err("crypto_shash_init() failed\n");
 		goto out;
 	}
 
-	sg_init_one(&sg, &auth->password, strlen(auth->password));
-	ret = crypto_hash_update(&desc, &sg, strlen(auth->password));
+	ret = crypto_shash_update(desc, &chap->id, 1);
 	if (ret < 0) {
-		pr_err("crypto_hash_update() failed for password\n");
-		crypto_free_hash(tfm);
+		pr_err("crypto_shash_update() failed for id\n");
 		goto out;
 	}
 
-	sg_init_one(&sg, chap->challenge, CHAP_CHALLENGE_LENGTH);
-	ret = crypto_hash_update(&desc, &sg, CHAP_CHALLENGE_LENGTH);
+	ret = crypto_shash_update(desc, (char *)&auth->password,
+				  strlen(auth->password));
 	if (ret < 0) {
-		pr_err("crypto_hash_update() failed for challenge\n");
-		crypto_free_hash(tfm);
+		pr_err("crypto_shash_update() failed for password\n");
 		goto out;
 	}
 
-	ret = crypto_hash_final(&desc, server_digest);
+	ret = crypto_shash_finup(desc, chap->challenge,
+				 CHAP_CHALLENGE_LENGTH, server_digest);
 	if (ret < 0) {
-		pr_err("crypto_hash_final() failed for server digest\n");
-		crypto_free_hash(tfm);
+		pr_err("crypto_shash_finup() failed for challenge\n");
 		goto out;
 	}
-	crypto_free_hash(tfm);
 
 	chap_binaryhex_to_asciihex(response, server_digest, MD5_SIGNATURE_SIZE);
 	pr_debug("[server] MD5 Server Digest: %s\n", response);
@@ -306,9 +300,8 @@ static int chap_server_compute_md5(
 	 * authentication is not enabled.
 	 */
 	if (!auth->authenticate_target) {
-		kfree(challenge);
-		kfree(challenge_binhex);
-		return 0;
+		auth_ret = 0;
+		goto out;
 	}
 	/*
 	 * Get CHAP_I.
@@ -372,58 +365,37 @@ static int chap_server_compute_md5(
 	/*
 	 * Generate CHAP_N and CHAP_R for mutual authentication.
 	 */
-	tfm = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(tfm)) {
-		pr_err("Unable to allocate struct crypto_hash\n");
-		goto out;
-	}
-	desc.tfm = tfm;
-	desc.flags = 0;
-
-	ret = crypto_hash_init(&desc);
+	ret = crypto_shash_init(desc);
 	if (ret < 0) {
-		pr_err("crypto_hash_init() failed\n");
-		crypto_free_hash(tfm);
+		pr_err("crypto_shash_init() failed\n");
 		goto out;
 	}
 
 	/* To handle both endiannesses */
 	id_as_uchar = id;
-	sg_init_one(&sg, &id_as_uchar, 1);
-	ret = crypto_hash_update(&desc, &sg, 1);
+	ret = crypto_shash_update(desc, &id_as_uchar, 1);
 	if (ret < 0) {
-		pr_err("crypto_hash_update() failed for id\n");
-		crypto_free_hash(tfm);
+		pr_err("crypto_shash_update() failed for id\n");
 		goto out;
 	}
 
-	sg_init_one(&sg, auth->password_mutual,
-				strlen(auth->password_mutual));
-	ret = crypto_hash_update(&desc, &sg, strlen(auth->password_mutual));
+	ret = crypto_shash_update(desc, auth->password_mutual,
+				  strlen(auth->password_mutual));
 	if (ret < 0) {
-		pr_err("crypto_hash_update() failed for"
+		pr_err("crypto_shash_update() failed for"
 				" password_mutual\n");
-		crypto_free_hash(tfm);
 		goto out;
 	}
 	/*
 	 * Convert received challenge to binary hex.
 	 */
-	sg_init_one(&sg, challenge_binhex, challenge_len);
-	ret = crypto_hash_update(&desc, &sg, challenge_len);
+	ret = crypto_shash_finup(desc, challenge_binhex, challenge_len,
+				 digest);
 	if (ret < 0) {
-		pr_err("crypto_hash_update() failed for ma challenge\n");
-		crypto_free_hash(tfm);
+		pr_err("crypto_shash_finup() failed for ma challenge\n");
 		goto out;
 	}
 
-	ret = crypto_hash_final(&desc, digest);
-	if (ret < 0) {
-		pr_err("crypto_hash_final() failed for ma digest\n");
-		crypto_free_hash(tfm);
-		goto out;
-	}
-	crypto_free_hash(tfm);
 	/*
 	 * Generate CHAP_N and CHAP_R.
 	 */
@@ -440,6 +412,8 @@ static int chap_server_compute_md5(
 	pr_debug("[server] Sending CHAP_R=0x%s\n", response);
 	auth_ret = 0;
 out:
+	kzfree(desc);
+	crypto_free_shash(tfm);
 	kfree(challenge);
 	kfree(challenge_binhex);
 	return auth_ret;
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 96e78c823d13..8436d56c5f0c 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -16,9 +16,9 @@
  * GNU General Public License for more details.
  ******************************************************************************/
 
+#include <crypto/hash.h>
 #include <linux/string.h>
 #include <linux/kthread.h>
-#include <linux/crypto.h>
 #include <linux/idr.h>
 #include <scsi/iscsi_proto.h>
 #include <target/target_core_base.h>
@@ -115,27 +115,36 @@ out_login:
  */
 int iscsi_login_setup_crypto(struct iscsi_conn *conn)
 {
+	struct crypto_ahash *tfm;
+
 	/*
 	 * Setup slicing by CRC32C algorithm for RX and TX libcrypto contexts
 	 * which will default to crc32c_intel.ko for cpu_has_xmm4_2, or fallback
 	 * to software 1x8 byte slicing from crc32c.ko
 	 */
-	conn->conn_rx_hash.flags = 0;
-	conn->conn_rx_hash.tfm = crypto_alloc_hash("crc32c", 0,
-						CRYPTO_ALG_ASYNC);
-	if (IS_ERR(conn->conn_rx_hash.tfm)) {
-		pr_err("crypto_alloc_hash() failed for conn_rx_tfm\n");
+	tfm = crypto_alloc_ahash("crc32c", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm)) {
+		pr_err("crypto_alloc_ahash() failed\n");
 		return -ENOMEM;
 	}
 
-	conn->conn_tx_hash.flags = 0;
-	conn->conn_tx_hash.tfm = crypto_alloc_hash("crc32c", 0,
-						CRYPTO_ALG_ASYNC);
-	if (IS_ERR(conn->conn_tx_hash.tfm)) {
-		pr_err("crypto_alloc_hash() failed for conn_tx_tfm\n");
-		crypto_free_hash(conn->conn_rx_hash.tfm);
+	conn->conn_rx_hash = ahash_request_alloc(tfm, GFP_KERNEL);
+	if (!conn->conn_rx_hash) {
+		pr_err("ahash_request_alloc() failed for conn_rx_hash\n");
+		crypto_free_ahash(tfm);
+		return -ENOMEM;
+	}
+	ahash_request_set_callback(conn->conn_rx_hash, 0, NULL, NULL);
+
+	conn->conn_tx_hash = ahash_request_alloc(tfm, GFP_KERNEL);
+	if (!conn->conn_tx_hash) {
+		pr_err("ahash_request_alloc() failed for conn_tx_hash\n");
+		ahash_request_free(conn->conn_rx_hash);
+		conn->conn_rx_hash = NULL;
+		crypto_free_ahash(tfm);
 		return -ENOMEM;
 	}
+	ahash_request_set_callback(conn->conn_tx_hash, 0, NULL, NULL);
 
 	return 0;
 }
@@ -1174,10 +1183,14 @@ old_sess_out:
 		iscsit_dec_session_usage_count(conn->sess);
 	}
 
-	if (!IS_ERR(conn->conn_rx_hash.tfm))
-		crypto_free_hash(conn->conn_rx_hash.tfm);
-	if (!IS_ERR(conn->conn_tx_hash.tfm))
-		crypto_free_hash(conn->conn_tx_hash.tfm);
+	ahash_request_free(conn->conn_tx_hash);
+	if (conn->conn_rx_hash) {
+		struct crypto_ahash *tfm;
+
+		tfm = crypto_ahash_reqtfm(conn->conn_rx_hash);
+		ahash_request_free(conn->conn_rx_hash);
+		crypto_free_ahash(tfm);
+	}
 
 	free_cpumask_var(conn->conn_cpumask);
 
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 3327c49674d3..713c63d9681b 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -898,7 +898,7 @@ static ssize_t unmap_zeroes_data_store(struct config_item *item,
 	da->unmap_zeroes_data = flag;
 	pr_debug("dev[%p]: SE Device Thin Provisioning LBPRZ bit: %d\n",
 		 da->da_dev, flag);
-	return 0;
+	return count;
 }
 
 /*
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index cacd97a8cbd0..da457e25717a 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -828,6 +828,50 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	return dev;
 }
 
+/*
+ * Check if the underlying struct block_device request_queue supports
+ * the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM
+ * in ATA and we need to set TPE=1
+ */
+bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
+				       struct request_queue *q, int block_size)
+{
+	if (!blk_queue_discard(q))
+		return false;
+
+	attrib->max_unmap_lba_count = (q->limits.max_discard_sectors << 9) /
+								block_size;
+	/*
+	 * Currently hardcoded to 1 in Linux/SCSI code..
+	 */
+	attrib->max_unmap_block_desc_count = 1;
+	attrib->unmap_granularity = q->limits.discard_granularity / block_size;
+	attrib->unmap_granularity_alignment = q->limits.discard_alignment /
+								block_size;
+	attrib->unmap_zeroes_data = q->limits.discard_zeroes_data;
+	return true;
+}
+EXPORT_SYMBOL(target_configure_unmap_from_queue);
+
+/*
+ * Convert from blocksize advertised to the initiator to the 512 byte
+ * units unconditionally used by the Linux block layer.
+ */
+sector_t target_to_linux_sector(struct se_device *dev, sector_t lb)
+{
+	switch (dev->dev_attrib.block_size) {
+	case 4096:
+		return lb << 3;
+	case 2048:
+		return lb << 2;
+	case 1024:
+		return lb << 1;
+	default:
+		return lb;
+	}
+}
+EXPORT_SYMBOL(target_to_linux_sector);
+
 int target_configure_device(struct se_device *dev)
 {
 	struct se_hba *hba = dev->se_hba;
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index e3195700211a..75f0f08b2a34 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -160,25 +160,11 @@ static int fd_configure_device(struct se_device *dev)
 			" block_device blocks: %llu logical_block_size: %d\n",
 			dev_size, div_u64(dev_size, fd_dev->fd_block_size),
 			fd_dev->fd_block_size);
-		/*
-		 * Check if the underlying struct block_device request_queue supports
-		 * the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM
-		 * in ATA and we need to set TPE=1
-		 */
-		if (blk_queue_discard(q)) {
-			dev->dev_attrib.max_unmap_lba_count =
-				q->limits.max_discard_sectors;
-			/*
-			 * Currently hardcoded to 1 in Linux/SCSI code..
-			 */
-			dev->dev_attrib.max_unmap_block_desc_count = 1;
-			dev->dev_attrib.unmap_granularity =
-				q->limits.discard_granularity >> 9;
-			dev->dev_attrib.unmap_granularity_alignment =
-				q->limits.discard_alignment;
+
+		if (target_configure_unmap_from_queue(&dev->dev_attrib, q,
+						      fd_dev->fd_block_size))
 			pr_debug("IFILE: BLOCK Discard support available,"
-					" disabled by default\n");
-		}
+				 " disabled by default\n");
 		/*
 		 * Enable write same emulation for IBLOCK and use 0xFFFF as
 		 * the smaller WRITE_SAME(10) only has a two-byte block count.
@@ -490,9 +476,12 @@ fd_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb)
 	if (S_ISBLK(inode->i_mode)) {
 		/* The backend is block device, use discard */
 		struct block_device *bdev = inode->i_bdev;
+		struct se_device *dev = cmd->se_dev;
 
-		ret = blkdev_issue_discard(bdev, lba,
-				nolb, GFP_KERNEL, 0);
+		ret = blkdev_issue_discard(bdev,
+					   target_to_linux_sector(dev, lba),
+					   target_to_linux_sector(dev,  nolb),
+					   GFP_KERNEL, 0);
 		if (ret < 0) {
 			pr_warn("FILEIO: blkdev_issue_discard() failed: %d\n",
 				ret);
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 5a2899f9f50b..abe4eb997a84 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -121,29 +121,11 @@ static int iblock_configure_device(struct se_device *dev)
 	dev->dev_attrib.hw_max_sectors = queue_max_hw_sectors(q);
 	dev->dev_attrib.hw_queue_depth = q->nr_requests;
 
-	/*
-	 * Check if the underlying struct block_device request_queue supports
-	 * the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM
-	 * in ATA and we need to set TPE=1
-	 */
-	if (blk_queue_discard(q)) {
-		dev->dev_attrib.max_unmap_lba_count =
-				q->limits.max_discard_sectors;
-
-		/*
-		 * Currently hardcoded to 1 in Linux/SCSI code..
-		 */
-		dev->dev_attrib.max_unmap_block_desc_count = 1;
-		dev->dev_attrib.unmap_granularity =
-				q->limits.discard_granularity >> 9;
-		dev->dev_attrib.unmap_granularity_alignment =
-				q->limits.discard_alignment;
-		dev->dev_attrib.unmap_zeroes_data =
-				q->limits.discard_zeroes_data;
-
+	if (target_configure_unmap_from_queue(&dev->dev_attrib, q,
+					      dev->dev_attrib.hw_block_size))
 		pr_debug("IBLOCK: BLOCK Discard support available,"
-				" disabled by default\n");
-	}
+			 " disabled by default\n");
+
 	/*
 	 * Enable write same emulation for IBLOCK and use 0xFFFF as
 	 * the smaller WRITE_SAME(10) only has a two-byte block count.
@@ -415,9 +397,13 @@ static sense_reason_t
 iblock_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb)
 {
 	struct block_device *bdev = IBLOCK_DEV(cmd->se_dev)->ibd_bd;
+	struct se_device *dev = cmd->se_dev;
 	int ret;
 
-	ret = blkdev_issue_discard(bdev, lba, nolb, GFP_KERNEL, 0);
+	ret = blkdev_issue_discard(bdev,
+				   target_to_linux_sector(dev, lba),
+				   target_to_linux_sector(dev,  nolb),
+				   GFP_KERNEL, 0);
 	if (ret < 0) {
 		pr_err("blkdev_issue_discard() failed: %d\n", ret);
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
@@ -433,8 +419,10 @@ iblock_execute_write_same(struct se_cmd *cmd)
 	struct scatterlist *sg;
 	struct bio *bio;
 	struct bio_list list;
-	sector_t block_lba = cmd->t_task_lba;
-	sector_t sectors = sbc_get_write_same_sectors(cmd);
+	struct se_device *dev = cmd->se_dev;
+	sector_t block_lba = target_to_linux_sector(dev, cmd->t_task_lba);
+	sector_t sectors = target_to_linux_sector(dev,
+					sbc_get_write_same_sectors(cmd));
 
 	if (cmd->prot_op) {
 		pr_err("WRITE_SAME: Protection information with IBLOCK"
@@ -648,12 +636,12 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 		  enum dma_data_direction data_direction)
 {
 	struct se_device *dev = cmd->se_dev;
+	sector_t block_lba = target_to_linux_sector(dev, cmd->t_task_lba);
 	struct iblock_req *ibr;
 	struct bio *bio, *bio_start;
 	struct bio_list list;
 	struct scatterlist *sg;
 	u32 sg_num = sgl_nents;
-	sector_t block_lba;
 	unsigned bio_cnt;
 	int rw = 0;
 	int i;
@@ -679,24 +667,6 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 		rw = READ;
 	}
 
-	/*
-	 * Convert the blocksize advertised to the initiator to the 512 byte
-	 * units unconditionally used by the Linux block layer.
-	 */
-	if (dev->dev_attrib.block_size == 4096)
-		block_lba = (cmd->t_task_lba << 3);
-	else if (dev->dev_attrib.block_size == 2048)
-		block_lba = (cmd->t_task_lba << 2);
-	else if (dev->dev_attrib.block_size == 1024)
-		block_lba = (cmd->t_task_lba << 1);
-	else if (dev->dev_attrib.block_size == 512)
-		block_lba = cmd->t_task_lba;
-	else {
-		pr_err("Unsupported SCSI -> BLOCK LBA conversion:"
-				" %u\n", dev->dev_attrib.block_size);
-		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-	}
-
 	ibr = kzalloc(sizeof(struct iblock_req), GFP_KERNEL);
 	if (!ibr)
 		goto fail;
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index dae0750c2032..db4412fe6b8a 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -141,7 +141,6 @@ void	transport_dump_vpd_proto_id(struct t10_vpd *, unsigned char *, int);
 int	transport_dump_vpd_assoc(struct t10_vpd *, unsigned char *, int);
 int	transport_dump_vpd_ident_type(struct t10_vpd *, unsigned char *, int);
 int	transport_dump_vpd_ident(struct t10_vpd *, unsigned char *, int);
-bool	target_stop_cmd(struct se_cmd *cmd, unsigned long *flags);
 void	transport_clear_lun_ref(struct se_lun *);
 void	transport_send_task_abort(struct se_cmd *);
 sense_reason_t	target_cmd_size_check(struct se_cmd *cmd, unsigned int size);
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index fcdcb117c60d..4f229e711e1c 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -68,23 +68,25 @@ void core_tmr_release_req(struct se_tmr_req *tmr)
 
 	if (dev) {
 		spin_lock_irqsave(&dev->se_tmr_lock, flags);
-		list_del(&tmr->tmr_list);
+		list_del_init(&tmr->tmr_list);
 		spin_unlock_irqrestore(&dev->se_tmr_lock, flags);
 	}
 
 	kfree(tmr);
 }
 
-static void core_tmr_handle_tas_abort(
-	struct se_node_acl *tmr_nacl,
-	struct se_cmd *cmd,
-	int tas)
+static void core_tmr_handle_tas_abort(struct se_cmd *cmd, int tas)
 {
-	bool remove = true;
+	unsigned long flags;
+	bool remove = true, send_tas;
 	/*
 	 * TASK ABORTED status (TAS) bit support
 	 */
-	if ((tmr_nacl && (tmr_nacl != cmd->se_sess->se_node_acl)) && tas) {
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	send_tas = (cmd->transport_state & CMD_T_TAS);
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
+	if (send_tas) {
 		remove = false;
 		transport_send_task_abort(cmd);
 	}
@@ -107,6 +109,46 @@ static int target_check_cdb_and_preempt(struct list_head *list,
 	return 1;
 }
 
+static bool __target_check_io_state(struct se_cmd *se_cmd,
+				    struct se_session *tmr_sess, int tas)
+{
+	struct se_session *sess = se_cmd->se_sess;
+
+	assert_spin_locked(&sess->sess_cmd_lock);
+	WARN_ON_ONCE(!irqs_disabled());
+	/*
+	 * If command already reached CMD_T_COMPLETE state within
+	 * target_complete_cmd() or CMD_T_FABRIC_STOP due to shutdown,
+	 * this se_cmd has been passed to fabric driver and will
+	 * not be aborted.
+	 *
+	 * Otherwise, obtain a local se_cmd->cmd_kref now for TMR
+	 * ABORT_TASK + LUN_RESET for CMD_T_ABORTED processing as
+	 * long as se_cmd->cmd_kref is still active unless zero.
+	 */
+	spin_lock(&se_cmd->t_state_lock);
+	if (se_cmd->transport_state & (CMD_T_COMPLETE | CMD_T_FABRIC_STOP)) {
+		pr_debug("Attempted to abort io tag: %llu already complete or"
+			" fabric stop, skipping\n", se_cmd->tag);
+		spin_unlock(&se_cmd->t_state_lock);
+		return false;
+	}
+	if (sess->sess_tearing_down || se_cmd->cmd_wait_set) {
+		pr_debug("Attempted to abort io tag: %llu already shutdown,"
+			" skipping\n", se_cmd->tag);
+		spin_unlock(&se_cmd->t_state_lock);
+		return false;
+	}
+	se_cmd->transport_state |= CMD_T_ABORTED;
+
+	if ((tmr_sess != se_cmd->se_sess) && tas)
+		se_cmd->transport_state |= CMD_T_TAS;
+
+	spin_unlock(&se_cmd->t_state_lock);
+
+	return kref_get_unless_zero(&se_cmd->cmd_kref);
+}
+
 void core_tmr_abort_task(
 	struct se_device *dev,
 	struct se_tmr_req *tmr,
@@ -130,34 +172,21 @@ void core_tmr_abort_task(
 		if (tmr->ref_task_tag != ref_tag)
 			continue;
 
-		if (!kref_get_unless_zero(&se_cmd->cmd_kref))
-			continue;
-
 		printk("ABORT_TASK: Found referenced %s task_tag: %llu\n",
 			se_cmd->se_tfo->get_fabric_name(), ref_tag);
 
-		spin_lock(&se_cmd->t_state_lock);
-		if (se_cmd->transport_state & CMD_T_COMPLETE) {
-			printk("ABORT_TASK: ref_tag: %llu already complete,"
-			       " skipping\n", ref_tag);
-			spin_unlock(&se_cmd->t_state_lock);
+		if (!__target_check_io_state(se_cmd, se_sess, 0)) {
 			spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
-
-			target_put_sess_cmd(se_cmd);
-
 			goto out;
 		}
-		se_cmd->transport_state |= CMD_T_ABORTED;
-		spin_unlock(&se_cmd->t_state_lock);
-
 		list_del_init(&se_cmd->se_cmd_list);
 		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
 		cancel_work_sync(&se_cmd->work);
 		transport_wait_for_tasks(se_cmd);
 
-		target_put_sess_cmd(se_cmd);
 		transport_cmd_finish_abort(se_cmd, true);
+		target_put_sess_cmd(se_cmd);
 
 		printk("ABORT_TASK: Sending TMR_FUNCTION_COMPLETE for"
 				" ref_tag: %llu\n", ref_tag);
@@ -178,9 +207,11 @@ static void core_tmr_drain_tmr_list(
 	struct list_head *preempt_and_abort_list)
 {
 	LIST_HEAD(drain_tmr_list);
+	struct se_session *sess;
 	struct se_tmr_req *tmr_p, *tmr_pp;
 	struct se_cmd *cmd;
 	unsigned long flags;
+	bool rc;
 	/*
 	 * Release all pending and outgoing TMRs aside from the received
 	 * LUN_RESET tmr..
@@ -206,17 +237,39 @@ static void core_tmr_drain_tmr_list(
 		if (target_check_cdb_and_preempt(preempt_and_abort_list, cmd))
 			continue;
 
+		sess = cmd->se_sess;
+		if (WARN_ON_ONCE(!sess))
+			continue;
+
+		spin_lock(&sess->sess_cmd_lock);
 		spin_lock(&cmd->t_state_lock);
-		if (!(cmd->transport_state & CMD_T_ACTIVE)) {
+		if (!(cmd->transport_state & CMD_T_ACTIVE) ||
+		     (cmd->transport_state & CMD_T_FABRIC_STOP)) {
 			spin_unlock(&cmd->t_state_lock);
+			spin_unlock(&sess->sess_cmd_lock);
 			continue;
 		}
 		if (cmd->t_state == TRANSPORT_ISTATE_PROCESSING) {
 			spin_unlock(&cmd->t_state_lock);
+			spin_unlock(&sess->sess_cmd_lock);
 			continue;
 		}
+		if (sess->sess_tearing_down || cmd->cmd_wait_set) {
+			spin_unlock(&cmd->t_state_lock);
+			spin_unlock(&sess->sess_cmd_lock);
+			continue;
+		}
+		cmd->transport_state |= CMD_T_ABORTED;
 		spin_unlock(&cmd->t_state_lock);
 
+		rc = kref_get_unless_zero(&cmd->cmd_kref);
+		if (!rc) {
+			printk("LUN_RESET TMR: non-zero kref_get_unless_zero\n");
+			spin_unlock(&sess->sess_cmd_lock);
+			continue;
+		}
+		spin_unlock(&sess->sess_cmd_lock);
+
 		list_move_tail(&tmr_p->tmr_list, &drain_tmr_list);
 	}
 	spin_unlock_irqrestore(&dev->se_tmr_lock, flags);
@@ -230,20 +283,26 @@ static void core_tmr_drain_tmr_list(
 			(preempt_and_abort_list) ? "Preempt" : "", tmr_p,
 			tmr_p->function, tmr_p->response, cmd->t_state);
 
+		cancel_work_sync(&cmd->work);
+		transport_wait_for_tasks(cmd);
+
 		transport_cmd_finish_abort(cmd, 1);
+		target_put_sess_cmd(cmd);
 	}
 }
 
 static void core_tmr_drain_state_list(
 	struct se_device *dev,
 	struct se_cmd *prout_cmd,
-	struct se_node_acl *tmr_nacl,
+	struct se_session *tmr_sess,
 	int tas,
 	struct list_head *preempt_and_abort_list)
 {
 	LIST_HEAD(drain_task_list);
+	struct se_session *sess;
 	struct se_cmd *cmd, *next;
 	unsigned long flags;
+	int rc;
 
 	/*
 	 * Complete outstanding commands with TASK_ABORTED SAM status.
@@ -282,6 +341,16 @@ static void core_tmr_drain_state_list(
 		if (prout_cmd == cmd)
 			continue;
 
+		sess = cmd->se_sess;
+		if (WARN_ON_ONCE(!sess))
+			continue;
+
+		spin_lock(&sess->sess_cmd_lock);
+		rc = __target_check_io_state(cmd, tmr_sess, tas);
+		spin_unlock(&sess->sess_cmd_lock);
+		if (!rc)
+			continue;
+
 		list_move_tail(&cmd->state_list, &drain_task_list);
 		cmd->state_active = false;
 	}
@@ -289,7 +358,7 @@ static void core_tmr_drain_state_list(
 
 	while (!list_empty(&drain_task_list)) {
 		cmd = list_entry(drain_task_list.next, struct se_cmd, state_list);
-		list_del(&cmd->state_list);
+		list_del_init(&cmd->state_list);
 
 		pr_debug("LUN_RESET: %s cmd: %p"
 			" ITT/CmdSN: 0x%08llx/0x%08x, i_state: %d, t_state: %d"
@@ -313,16 +382,11 @@ static void core_tmr_drain_state_list(
 		 * loop above, but we do it down here given that
 		 * cancel_work_sync may block.
 		 */
-		if (cmd->t_state == TRANSPORT_COMPLETE)
-			cancel_work_sync(&cmd->work);
-
-		spin_lock_irqsave(&cmd->t_state_lock, flags);
-		target_stop_cmd(cmd, &flags);
-
-		cmd->transport_state |= CMD_T_ABORTED;
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+		cancel_work_sync(&cmd->work);
+		transport_wait_for_tasks(cmd);
 
-		core_tmr_handle_tas_abort(tmr_nacl, cmd, tas);
+		core_tmr_handle_tas_abort(cmd, tas);
+		target_put_sess_cmd(cmd);
 	}
 }
 
@@ -334,6 +398,7 @@ int core_tmr_lun_reset(
 {
 	struct se_node_acl *tmr_nacl = NULL;
 	struct se_portal_group *tmr_tpg = NULL;
+	struct se_session *tmr_sess = NULL;
 	int tas;
         /*
 	 * TASK_ABORTED status bit, this is configurable via ConfigFS
@@ -352,8 +417,9 @@ int core_tmr_lun_reset(
 	 * or struct se_device passthrough..
 	 */
 	if (tmr && tmr->task_cmd && tmr->task_cmd->se_sess) {
-		tmr_nacl = tmr->task_cmd->se_sess->se_node_acl;
-		tmr_tpg = tmr->task_cmd->se_sess->se_tpg;
+		tmr_sess = tmr->task_cmd->se_sess;
+		tmr_nacl = tmr_sess->se_node_acl;
+		tmr_tpg = tmr_sess->se_tpg;
 		if (tmr_nacl && tmr_tpg) {
 			pr_debug("LUN_RESET: TMR caller fabric: %s"
 				" initiator port %s\n",
@@ -366,7 +432,7 @@ int core_tmr_lun_reset(
 		dev->transport->name, tas);
 
 	core_tmr_drain_tmr_list(dev, tmr, preempt_and_abort_list);
-	core_tmr_drain_state_list(dev, prout_cmd, tmr_nacl, tas,
+	core_tmr_drain_state_list(dev, prout_cmd, tmr_sess, tas,
 				preempt_and_abort_list);
 
 	/*
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 9f3608e10f25..867bc6d0a68a 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -534,9 +534,6 @@ void transport_deregister_session(struct se_session *se_sess)
 }
 EXPORT_SYMBOL(transport_deregister_session);
 
-/*
- * Called with cmd->t_state_lock held.
- */
 static void target_remove_from_state_list(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
@@ -561,10 +558,6 @@ static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists,
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&cmd->t_state_lock, flags);
-	if (write_pending)
-		cmd->t_state = TRANSPORT_WRITE_PENDING;
-
 	if (remove_from_lists) {
 		target_remove_from_state_list(cmd);
 
@@ -574,6 +567,10 @@ static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists,
 		cmd->se_lun = NULL;
 	}
 
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	if (write_pending)
+		cmd->t_state = TRANSPORT_WRITE_PENDING;
+
 	/*
 	 * Determine if frontend context caller is requesting the stopping of
 	 * this command for frontend exceptions.
@@ -627,6 +624,8 @@ static void transport_lun_remove_cmd(struct se_cmd *cmd)
 
 void transport_cmd_finish_abort(struct se_cmd *cmd, int remove)
 {
+	bool ack_kref = (cmd->se_cmd_flags & SCF_ACK_KREF);
+
 	if (cmd->se_cmd_flags & SCF_SE_LUN_CMD)
 		transport_lun_remove_cmd(cmd);
 	/*
@@ -638,7 +637,7 @@ void transport_cmd_finish_abort(struct se_cmd *cmd, int remove)
 
 	if (transport_cmd_check_stop_to_fabric(cmd))
 		return;
-	if (remove)
+	if (remove && ack_kref)
 		transport_put_cmd(cmd);
 }
 
@@ -694,19 +693,10 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
 	}
 
 	/*
-	 * See if we are waiting to complete for an exception condition.
-	 */
-	if (cmd->transport_state & CMD_T_REQUEST_STOP) {
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-		complete(&cmd->task_stop_comp);
-		return;
-	}
-
-	/*
 	 * Check for case where an explicit ABORT_TASK has been received
 	 * and transport_wait_for_tasks() will be waiting for completion..
 	 */
-	if (cmd->transport_state & CMD_T_ABORTED &&
+	if (cmd->transport_state & CMD_T_ABORTED ||
 	    cmd->transport_state & CMD_T_STOP) {
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 		complete_all(&cmd->t_transport_stop_comp);
@@ -721,10 +711,10 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
 	cmd->transport_state |= (CMD_T_COMPLETE | CMD_T_ACTIVE);
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
-	if (cmd->cpuid == -1)
-		queue_work(target_completion_wq, &cmd->work);
-	else
+	if (cmd->se_cmd_flags & SCF_USE_CPUID)
 		queue_work_on(cmd->cpuid, target_completion_wq, &cmd->work);
+	else
+		queue_work(target_completion_wq, &cmd->work);
 }
 EXPORT_SYMBOL(target_complete_cmd);
 
@@ -1203,7 +1193,6 @@ void transport_init_se_cmd(
 	INIT_LIST_HEAD(&cmd->state_list);
 	init_completion(&cmd->t_transport_stop_comp);
 	init_completion(&cmd->cmd_wait_comp);
-	init_completion(&cmd->task_stop_comp);
 	spin_lock_init(&cmd->t_state_lock);
 	kref_init(&cmd->cmd_kref);
 	cmd->transport_state = CMD_T_DEV_ACTIVE;
@@ -1437,6 +1426,12 @@ int target_submit_cmd_map_sgls(struct se_cmd *se_cmd, struct se_session *se_sess
 	 */
 	transport_init_se_cmd(se_cmd, se_tpg->se_tpg_tfo, se_sess,
 				data_length, data_dir, task_attr, sense);
+
+	if (flags & TARGET_SCF_USE_CPUID)
+		se_cmd->se_cmd_flags |= SCF_USE_CPUID;
+	else
+		se_cmd->cpuid = WORK_CPU_UNBOUND;
+
 	if (flags & TARGET_SCF_UNKNOWN_SIZE)
 		se_cmd->unknown_data_length = 1;
 	/*
@@ -1635,33 +1630,6 @@ int target_submit_tmr(struct se_cmd *se_cmd, struct se_session *se_sess,
 EXPORT_SYMBOL(target_submit_tmr);
 
 /*
- * If the cmd is active, request it to be stopped and sleep until it
- * has completed.
- */
-bool target_stop_cmd(struct se_cmd *cmd, unsigned long *flags)
-	__releases(&cmd->t_state_lock)
-	__acquires(&cmd->t_state_lock)
-{
-	bool was_active = false;
-
-	if (cmd->transport_state & CMD_T_BUSY) {
-		cmd->transport_state |= CMD_T_REQUEST_STOP;
-		spin_unlock_irqrestore(&cmd->t_state_lock, *flags);
-
-		pr_debug("cmd %p waiting to complete\n", cmd);
-		wait_for_completion(&cmd->task_stop_comp);
-		pr_debug("cmd %p stopped successfully\n", cmd);
-
-		spin_lock_irqsave(&cmd->t_state_lock, *flags);
-		cmd->transport_state &= ~CMD_T_REQUEST_STOP;
-		cmd->transport_state &= ~CMD_T_BUSY;
-		was_active = true;
-	}
-
-	return was_active;
-}
-
-/*
  * Handle SAM-esque emulation for generic transport request failures.
  */
 void transport_generic_request_failure(struct se_cmd *cmd,
@@ -1859,19 +1827,21 @@ static bool target_handle_task_attr(struct se_cmd *cmd)
 	return true;
 }
 
+static int __transport_check_aborted_status(struct se_cmd *, int);
+
 void target_execute_cmd(struct se_cmd *cmd)
 {
 	/*
-	 * If the received CDB has aleady been aborted stop processing it here.
-	 */
-	if (transport_check_aborted_status(cmd, 1))
-		return;
-
-	/*
 	 * Determine if frontend context caller is requesting the stopping of
 	 * this command for frontend exceptions.
+	 *
+	 * If the received CDB has aleady been aborted stop processing it here.
 	 */
 	spin_lock_irq(&cmd->t_state_lock);
+	if (__transport_check_aborted_status(cmd, 1)) {
+		spin_unlock_irq(&cmd->t_state_lock);
+		return;
+	}
 	if (cmd->transport_state & CMD_T_STOP) {
 		pr_debug("%s:%d CMD_T_STOP for ITT: 0x%08llx\n",
 			__func__, __LINE__, cmd->tag);
@@ -2222,20 +2192,14 @@ static inline void transport_free_pages(struct se_cmd *cmd)
 }
 
 /**
- * transport_release_cmd - free a command
- * @cmd:       command to free
+ * transport_put_cmd - release a reference to a command
+ * @cmd:       command to release
  *
- * This routine unconditionally frees a command, and reference counting
- * or list removal must be done in the caller.
+ * This routine releases our reference to the command and frees it if possible.
  */
-static int transport_release_cmd(struct se_cmd *cmd)
+static int transport_put_cmd(struct se_cmd *cmd)
 {
 	BUG_ON(!cmd->se_tfo);
-
-	if (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)
-		core_tmr_release_req(cmd->se_tmr_req);
-	if (cmd->t_task_cdb != cmd->__t_task_cdb)
-		kfree(cmd->t_task_cdb);
 	/*
 	 * If this cmd has been setup with target_get_sess_cmd(), drop
 	 * the kref and call ->release_cmd() in kref callback.
@@ -2243,18 +2207,6 @@ static int transport_release_cmd(struct se_cmd *cmd)
 	return target_put_sess_cmd(cmd);
 }
 
-/**
- * transport_put_cmd - release a reference to a command
- * @cmd:       command to release
- *
- * This routine releases our reference to the command and frees it if possible.
- */
-static int transport_put_cmd(struct se_cmd *cmd)
-{
-	transport_free_pages(cmd);
-	return transport_release_cmd(cmd);
-}
-
 void *transport_kmap_data_sg(struct se_cmd *cmd)
 {
 	struct scatterlist *sg = cmd->t_data_sg;
@@ -2450,34 +2402,58 @@ static void transport_write_pending_qf(struct se_cmd *cmd)
 	}
 }
 
-int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
+static bool
+__transport_wait_for_tasks(struct se_cmd *, bool, bool *, bool *,
+			   unsigned long *flags);
+
+static void target_wait_free_cmd(struct se_cmd *cmd, bool *aborted, bool *tas)
 {
 	unsigned long flags;
+
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	__transport_wait_for_tasks(cmd, true, aborted, tas, &flags);
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+}
+
+int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
+{
 	int ret = 0;
+	bool aborted = false, tas = false;
 
 	if (!(cmd->se_cmd_flags & SCF_SE_LUN_CMD)) {
 		if (wait_for_tasks && (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB))
-			 transport_wait_for_tasks(cmd);
+			target_wait_free_cmd(cmd, &aborted, &tas);
 
-		ret = transport_release_cmd(cmd);
+		if (!aborted || tas)
+			ret = transport_put_cmd(cmd);
 	} else {
 		if (wait_for_tasks)
-			transport_wait_for_tasks(cmd);
+			target_wait_free_cmd(cmd, &aborted, &tas);
 		/*
 		 * Handle WRITE failure case where transport_generic_new_cmd()
 		 * has already added se_cmd to state_list, but fabric has
 		 * failed command before I/O submission.
 		 */
-		if (cmd->state_active) {
-			spin_lock_irqsave(&cmd->t_state_lock, flags);
+		if (cmd->state_active)
 			target_remove_from_state_list(cmd);
-			spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-		}
 
 		if (cmd->se_lun)
 			transport_lun_remove_cmd(cmd);
 
-		ret = transport_put_cmd(cmd);
+		if (!aborted || tas)
+			ret = transport_put_cmd(cmd);
+	}
+	/*
+	 * If the task has been internally aborted due to TMR ABORT_TASK
+	 * or LUN_RESET, target_core_tmr.c is responsible for performing
+	 * the remaining calls to target_put_sess_cmd(), and not the
+	 * callers of this function.
+	 */
+	if (aborted) {
+		pr_debug("Detected CMD_T_ABORTED for ITT: %llu\n", cmd->tag);
+		wait_for_completion(&cmd->cmd_wait_comp);
+		cmd->se_tfo->release_cmd(cmd);
+		ret = 1;
 	}
 	return ret;
 }
@@ -2517,26 +2493,46 @@ out:
 }
 EXPORT_SYMBOL(target_get_sess_cmd);
 
+static void target_free_cmd_mem(struct se_cmd *cmd)
+{
+	transport_free_pages(cmd);
+
+	if (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)
+		core_tmr_release_req(cmd->se_tmr_req);
+	if (cmd->t_task_cdb != cmd->__t_task_cdb)
+		kfree(cmd->t_task_cdb);
+}
+
 static void target_release_cmd_kref(struct kref *kref)
 {
 	struct se_cmd *se_cmd = container_of(kref, struct se_cmd, cmd_kref);
 	struct se_session *se_sess = se_cmd->se_sess;
 	unsigned long flags;
+	bool fabric_stop;
 
 	spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
 	if (list_empty(&se_cmd->se_cmd_list)) {
 		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
+		target_free_cmd_mem(se_cmd);
 		se_cmd->se_tfo->release_cmd(se_cmd);
 		return;
 	}
-	if (se_sess->sess_tearing_down && se_cmd->cmd_wait_set) {
+
+	spin_lock(&se_cmd->t_state_lock);
+	fabric_stop = (se_cmd->transport_state & CMD_T_FABRIC_STOP);
+	spin_unlock(&se_cmd->t_state_lock);
+
+	if (se_cmd->cmd_wait_set || fabric_stop) {
+		list_del_init(&se_cmd->se_cmd_list);
 		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
+		target_free_cmd_mem(se_cmd);
 		complete(&se_cmd->cmd_wait_comp);
 		return;
 	}
-	list_del(&se_cmd->se_cmd_list);
+	list_del_init(&se_cmd->se_cmd_list);
 	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
+	target_free_cmd_mem(se_cmd);
 	se_cmd->se_tfo->release_cmd(se_cmd);
 }
 
@@ -2548,6 +2544,7 @@ int target_put_sess_cmd(struct se_cmd *se_cmd)
 	struct se_session *se_sess = se_cmd->se_sess;
 
 	if (!se_sess) {
+		target_free_cmd_mem(se_cmd);
 		se_cmd->se_tfo->release_cmd(se_cmd);
 		return 1;
 	}
@@ -2564,6 +2561,7 @@ void target_sess_cmd_list_set_waiting(struct se_session *se_sess)
 {
 	struct se_cmd *se_cmd;
 	unsigned long flags;
+	int rc;
 
 	spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
 	if (se_sess->sess_tearing_down) {
@@ -2573,8 +2571,15 @@ void target_sess_cmd_list_set_waiting(struct se_session *se_sess)
 	se_sess->sess_tearing_down = 1;
 	list_splice_init(&se_sess->sess_cmd_list, &se_sess->sess_wait_list);
 
-	list_for_each_entry(se_cmd, &se_sess->sess_wait_list, se_cmd_list)
-		se_cmd->cmd_wait_set = 1;
+	list_for_each_entry(se_cmd, &se_sess->sess_wait_list, se_cmd_list) {
+		rc = kref_get_unless_zero(&se_cmd->cmd_kref);
+		if (rc) {
+			se_cmd->cmd_wait_set = 1;
+			spin_lock(&se_cmd->t_state_lock);
+			se_cmd->transport_state |= CMD_T_FABRIC_STOP;
+			spin_unlock(&se_cmd->t_state_lock);
+		}
+	}
 
 	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 }
@@ -2587,15 +2592,25 @@ void target_wait_for_sess_cmds(struct se_session *se_sess)
 {
 	struct se_cmd *se_cmd, *tmp_cmd;
 	unsigned long flags;
+	bool tas;
 
 	list_for_each_entry_safe(se_cmd, tmp_cmd,
 				&se_sess->sess_wait_list, se_cmd_list) {
-		list_del(&se_cmd->se_cmd_list);
+		list_del_init(&se_cmd->se_cmd_list);
 
 		pr_debug("Waiting for se_cmd: %p t_state: %d, fabric state:"
 			" %d\n", se_cmd, se_cmd->t_state,
 			se_cmd->se_tfo->get_cmd_state(se_cmd));
 
+		spin_lock_irqsave(&se_cmd->t_state_lock, flags);
+		tas = (se_cmd->transport_state & CMD_T_TAS);
+		spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
+
+		if (!target_put_sess_cmd(se_cmd)) {
+			if (tas)
+				target_put_sess_cmd(se_cmd);
+		}
+
 		wait_for_completion(&se_cmd->cmd_wait_comp);
 		pr_debug("After cmd_wait_comp: se_cmd: %p t_state: %d"
 			" fabric state: %d\n", se_cmd, se_cmd->t_state,
@@ -2617,53 +2632,75 @@ void transport_clear_lun_ref(struct se_lun *lun)
 	wait_for_completion(&lun->lun_ref_comp);
 }
 
-/**
- * transport_wait_for_tasks - wait for completion to occur
- * @cmd:	command to wait
- *
- * Called from frontend fabric context to wait for storage engine
- * to pause and/or release frontend generated struct se_cmd.
- */
-bool transport_wait_for_tasks(struct se_cmd *cmd)
+static bool
+__transport_wait_for_tasks(struct se_cmd *cmd, bool fabric_stop,
+			   bool *aborted, bool *tas, unsigned long *flags)
+	__releases(&cmd->t_state_lock)
+	__acquires(&cmd->t_state_lock)
 {
-	unsigned long flags;
 
-	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	assert_spin_locked(&cmd->t_state_lock);
+	WARN_ON_ONCE(!irqs_disabled());
+
+	if (fabric_stop)
+		cmd->transport_state |= CMD_T_FABRIC_STOP;
+
+	if (cmd->transport_state & CMD_T_ABORTED)
+		*aborted = true;
+
+	if (cmd->transport_state & CMD_T_TAS)
+		*tas = true;
+
 	if (!(cmd->se_cmd_flags & SCF_SE_LUN_CMD) &&
-	    !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)) {
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+	    !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB))
 		return false;
-	}
 
 	if (!(cmd->se_cmd_flags & SCF_SUPPORTED_SAM_OPCODE) &&
-	    !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)) {
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+	    !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB))
 		return false;
-	}
 
-	if (!(cmd->transport_state & CMD_T_ACTIVE)) {
-		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+	if (!(cmd->transport_state & CMD_T_ACTIVE))
+		return false;
+
+	if (fabric_stop && *aborted)
 		return false;
-	}
 
 	cmd->transport_state |= CMD_T_STOP;
 
-	pr_debug("wait_for_tasks: Stopping %p ITT: 0x%08llx i_state: %d, t_state: %d, CMD_T_STOP\n",
-		cmd, cmd->tag, cmd->se_tfo->get_cmd_state(cmd), cmd->t_state);
+	pr_debug("wait_for_tasks: Stopping %p ITT: 0x%08llx i_state: %d,"
+		 " t_state: %d, CMD_T_STOP\n", cmd, cmd->tag,
+		 cmd->se_tfo->get_cmd_state(cmd), cmd->t_state);
 
-	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+	spin_unlock_irqrestore(&cmd->t_state_lock, *flags);
 
 	wait_for_completion(&cmd->t_transport_stop_comp);
 
-	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	spin_lock_irqsave(&cmd->t_state_lock, *flags);
 	cmd->transport_state &= ~(CMD_T_ACTIVE | CMD_T_STOP);
 
-	pr_debug("wait_for_tasks: Stopped wait_for_completion(&cmd->t_transport_stop_comp) for ITT: 0x%08llx\n",
-		cmd->tag);
+	pr_debug("wait_for_tasks: Stopped wait_for_completion(&cmd->"
+		 "t_transport_stop_comp) for ITT: 0x%08llx\n", cmd->tag);
 
+	return true;
+}
+
+/**
+ * transport_wait_for_tasks - wait for completion to occur
+ * @cmd:	command to wait
+ *
+ * Called from frontend fabric context to wait for storage engine
+ * to pause and/or release frontend generated struct se_cmd.
+ */
+bool transport_wait_for_tasks(struct se_cmd *cmd)
+{
+	unsigned long flags;
+	bool ret, aborted = false, tas = false;
+
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	ret = __transport_wait_for_tasks(cmd, false, &aborted, &tas, &flags);
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
-	return true;
+	return ret;
 }
 EXPORT_SYMBOL(transport_wait_for_tasks);
 
@@ -2845,28 +2882,49 @@ transport_send_check_condition_and_sense(struct se_cmd *cmd,
 }
 EXPORT_SYMBOL(transport_send_check_condition_and_sense);
 
-int transport_check_aborted_status(struct se_cmd *cmd, int send_status)
+static int __transport_check_aborted_status(struct se_cmd *cmd, int send_status)
+	__releases(&cmd->t_state_lock)
+	__acquires(&cmd->t_state_lock)
 {
+	assert_spin_locked(&cmd->t_state_lock);
+	WARN_ON_ONCE(!irqs_disabled());
+
 	if (!(cmd->transport_state & CMD_T_ABORTED))
 		return 0;
-
 	/*
 	 * If cmd has been aborted but either no status is to be sent or it has
 	 * already been sent, just return
 	 */
-	if (!send_status || !(cmd->se_cmd_flags & SCF_SEND_DELAYED_TAS))
+	if (!send_status || !(cmd->se_cmd_flags & SCF_SEND_DELAYED_TAS)) {
+		if (send_status)
+			cmd->se_cmd_flags |= SCF_SEND_DELAYED_TAS;
 		return 1;
+	}
 
-	pr_debug("Sending delayed SAM_STAT_TASK_ABORTED status for CDB: 0x%02x ITT: 0x%08llx\n",
-		 cmd->t_task_cdb[0], cmd->tag);
+	pr_debug("Sending delayed SAM_STAT_TASK_ABORTED status for CDB:"
+		" 0x%02x ITT: 0x%08llx\n", cmd->t_task_cdb[0], cmd->tag);
 
 	cmd->se_cmd_flags &= ~SCF_SEND_DELAYED_TAS;
 	cmd->scsi_status = SAM_STAT_TASK_ABORTED;
 	trace_target_cmd_complete(cmd);
+
+	spin_unlock_irq(&cmd->t_state_lock);
 	cmd->se_tfo->queue_status(cmd);
+	spin_lock_irq(&cmd->t_state_lock);
 
 	return 1;
 }
+
+int transport_check_aborted_status(struct se_cmd *cmd, int send_status)
+{
+	int ret;
+
+	spin_lock_irq(&cmd->t_state_lock);
+	ret = __transport_check_aborted_status(cmd, send_status);
+	spin_unlock_irq(&cmd->t_state_lock);
+
+	return ret;
+}
 EXPORT_SYMBOL(transport_check_aborted_status);
 
 void transport_send_task_abort(struct se_cmd *cmd)
@@ -2888,11 +2946,17 @@ void transport_send_task_abort(struct se_cmd *cmd)
 	 */
 	if (cmd->data_direction == DMA_TO_DEVICE) {
 		if (cmd->se_tfo->write_pending_status(cmd) != 0) {
-			cmd->transport_state |= CMD_T_ABORTED;
+			spin_lock_irqsave(&cmd->t_state_lock, flags);
+			if (cmd->se_cmd_flags & SCF_SEND_DELAYED_TAS) {
+				spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+				goto send_abort;
+			}
 			cmd->se_cmd_flags |= SCF_SEND_DELAYED_TAS;
+			spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 			return;
 		}
 	}
+send_abort:
 	cmd->scsi_status = SAM_STAT_TASK_ABORTED;
 
 	transport_lun_remove_cmd(cmd);
@@ -2909,8 +2973,17 @@ static void target_tmr_work(struct work_struct *work)
 	struct se_cmd *cmd = container_of(work, struct se_cmd, work);
 	struct se_device *dev = cmd->se_dev;
 	struct se_tmr_req *tmr = cmd->se_tmr_req;
+	unsigned long flags;
 	int ret;
 
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	if (cmd->transport_state & CMD_T_ABORTED) {
+		tmr->response = TMR_FUNCTION_REJECTED;
+		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+		goto check_stop;
+	}
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
 	switch (tmr->function) {
 	case TMR_ABORT_TASK:
 		core_tmr_abort_task(dev, tmr, cmd->se_sess);
@@ -2943,9 +3016,17 @@ static void target_tmr_work(struct work_struct *work)
 		break;
 	}
 
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	if (cmd->transport_state & CMD_T_ABORTED) {
+		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+		goto check_stop;
+	}
 	cmd->t_state = TRANSPORT_ISTATE_PROCESSING;
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
 	cmd->se_tfo->queue_tm_rsp(cmd);
 
+check_stop:
 	transport_cmd_check_stop_to_fabric(cmd);
 }
 
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index dd600e5ead71..94f5154ac788 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -903,7 +903,7 @@ static int tcmu_configure_device(struct se_device *dev)
 	info->version = __stringify(TCMU_MAILBOX_VERSION);
 
 	info->mem[0].name = "tcm-user command & data buffer";
-	info->mem[0].addr = (phys_addr_t) udev->mb_addr;
+	info->mem[0].addr = (phys_addr_t)(uintptr_t)udev->mb_addr;
 	info->mem[0].size = TCMU_RING_SIZE;
 	info->mem[0].memtype = UIO_MEM_VIRTUAL;
 
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 8cc4ac64a91c..7c92c09be213 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -195,7 +195,7 @@ config IMX_THERMAL
 	  passive trip is crossed.
 
 config SPEAR_THERMAL
-	bool "SPEAr thermal sensor driver"
+	tristate "SPEAr thermal sensor driver"
 	depends on PLAT_SPEAR || COMPILE_TEST
 	depends on OF
 	help
@@ -237,8 +237,8 @@ config DOVE_THERMAL
 	  framework.
 
 config DB8500_THERMAL
-	bool "DB8500 thermal management"
-	depends on ARCH_U8500
+	tristate "DB8500 thermal management"
+	depends on MFD_DB8500_PRCMU
 	default y
 	help
 	  Adds DB8500 thermal management implementation according to the thermal
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index e3fbc5a5d88f..6ceac4f2d4b2 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -377,26 +377,28 @@ static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_device,
  * get_load() - get load for a cpu since last updated
  * @cpufreq_device:	&struct cpufreq_cooling_device for this cpu
  * @cpu:	cpu number
+ * @cpu_idx:	index of the cpu in cpufreq_device->allowed_cpus
  *
  * Return: The average load of cpu @cpu in percentage since this
  * function was last called.
  */
-static u32 get_load(struct cpufreq_cooling_device *cpufreq_device, int cpu)
+static u32 get_load(struct cpufreq_cooling_device *cpufreq_device, int cpu,
+		    int cpu_idx)
 {
 	u32 load;
 	u64 now, now_idle, delta_time, delta_idle;
 
 	now_idle = get_cpu_idle_time(cpu, &now, 0);
-	delta_idle = now_idle - cpufreq_device->time_in_idle[cpu];
-	delta_time = now - cpufreq_device->time_in_idle_timestamp[cpu];
+	delta_idle = now_idle - cpufreq_device->time_in_idle[cpu_idx];
+	delta_time = now - cpufreq_device->time_in_idle_timestamp[cpu_idx];
 
 	if (delta_time <= delta_idle)
 		load = 0;
 	else
 		load = div64_u64(100 * (delta_time - delta_idle), delta_time);
 
-	cpufreq_device->time_in_idle[cpu] = now_idle;
-	cpufreq_device->time_in_idle_timestamp[cpu] = now;
+	cpufreq_device->time_in_idle[cpu_idx] = now_idle;
+	cpufreq_device->time_in_idle_timestamp[cpu_idx] = now;
 
 	return load;
 }
@@ -598,7 +600,7 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
 		u32 load;
 
 		if (cpu_online(cpu))
-			load = get_load(cpufreq_device, cpu);
+			load = get_load(cpufreq_device, cpu, i);
 		else
 			load = 0;
 
diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c
index be4eedcb839a..9043f8f91852 100644
--- a/drivers/thermal/of-thermal.c
+++ b/drivers/thermal/of-thermal.c
@@ -475,14 +475,10 @@ thermal_zone_of_sensor_register(struct device *dev, int sensor_id, void *data,
 
 	sensor_np = of_node_get(dev->of_node);
 
-	for_each_child_of_node(np, child) {
+	for_each_available_child_of_node(np, child) {
 		struct of_phandle_args sensor_specs;
 		int ret, id;
 
-		/* Check whether child is enabled or not */
-		if (!of_device_is_available(child))
-			continue;
-
 		/* For now, thermal framework supports only 1 sensor per zone */
 		ret = of_parse_phandle_with_args(child, "thermal-sensors",
 						 "#thermal-sensor-cells",
@@ -881,16 +877,12 @@ int __init of_parse_thermal_zones(void)
 		return 0; /* Run successfully on systems without thermal DT */
 	}
 
-	for_each_child_of_node(np, child) {
+	for_each_available_child_of_node(np, child) {
 		struct thermal_zone_device *zone;
 		struct thermal_zone_params *tzp;
 		int i, mask = 0;
 		u32 prop;
 
-		/* Check whether child is enabled or not */
-		if (!of_device_is_available(child))
-			continue;
-
 		tz = thermal_of_build_thermal_zone(child);
 		if (IS_ERR(tz)) {
 			pr_err("failed to build thermal zone %s: %ld\n",
@@ -968,13 +960,9 @@ void of_thermal_destroy_zones(void)
 		return;
 	}
 
-	for_each_child_of_node(np, child) {
+	for_each_available_child_of_node(np, child) {
 		struct thermal_zone_device *zone;
 
-		/* Check whether child is enabled or not */
-		if (!of_device_is_available(child))
-			continue;
-
 		zone = thermal_zone_get_zone_by_name(child->name);
 		if (IS_ERR(zone))
 			continue;
diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c
index 44b9c485157d..0e735acea33a 100644
--- a/drivers/thermal/rcar_thermal.c
+++ b/drivers/thermal/rcar_thermal.c
@@ -23,6 +23,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/reboot.h>
@@ -75,8 +76,10 @@ struct rcar_thermal_priv {
 #define rcar_has_irq_support(priv)	((priv)->common->base)
 #define rcar_id_to_shift(priv)		((priv)->id * 8)
 
+#define USE_OF_THERMAL	1
 static const struct of_device_id rcar_thermal_dt_ids[] = {
 	{ .compatible = "renesas,rcar-thermal", },
+	{ .compatible = "renesas,rcar-gen2-thermal", .data = (void *)USE_OF_THERMAL },
 	{},
 };
 MODULE_DEVICE_TABLE(of, rcar_thermal_dt_ids);
@@ -200,9 +203,9 @@ err_out_unlock:
 	return ret;
 }
 
-static int rcar_thermal_get_temp(struct thermal_zone_device *zone, int *temp)
+static int rcar_thermal_get_current_temp(struct rcar_thermal_priv *priv,
+					 int *temp)
 {
-	struct rcar_thermal_priv *priv = rcar_zone_to_priv(zone);
 	int tmp;
 	int ret;
 
@@ -226,6 +229,20 @@ static int rcar_thermal_get_temp(struct thermal_zone_device *zone, int *temp)
 	return 0;
 }
 
+static int rcar_thermal_of_get_temp(void *data, int *temp)
+{
+	struct rcar_thermal_priv *priv = data;
+
+	return rcar_thermal_get_current_temp(priv, temp);
+}
+
+static int rcar_thermal_get_temp(struct thermal_zone_device *zone, int *temp)
+{
+	struct rcar_thermal_priv *priv = rcar_zone_to_priv(zone);
+
+	return rcar_thermal_get_current_temp(priv, temp);
+}
+
 static int rcar_thermal_get_trip_type(struct thermal_zone_device *zone,
 				      int trip, enum thermal_trip_type *type)
 {
@@ -282,6 +299,10 @@ static int rcar_thermal_notify(struct thermal_zone_device *zone,
 	return 0;
 }
 
+static const struct thermal_zone_of_device_ops rcar_thermal_zone_of_ops = {
+	.get_temp	= rcar_thermal_of_get_temp,
+};
+
 static struct thermal_zone_device_ops rcar_thermal_zone_ops = {
 	.get_temp	= rcar_thermal_get_temp,
 	.get_trip_type	= rcar_thermal_get_trip_type,
@@ -318,14 +339,20 @@ static void rcar_thermal_work(struct work_struct *work)
 
 	priv = container_of(work, struct rcar_thermal_priv, work.work);
 
-	rcar_thermal_get_temp(priv->zone, &cctemp);
+	ret = rcar_thermal_get_current_temp(priv, &cctemp);
+	if (ret < 0)
+		return;
+
 	ret = rcar_thermal_update_temp(priv);
 	if (ret < 0)
 		return;
 
 	rcar_thermal_irq_enable(priv);
 
-	rcar_thermal_get_temp(priv->zone, &nctemp);
+	ret = rcar_thermal_get_current_temp(priv, &nctemp);
+	if (ret < 0)
+		return;
+
 	if (nctemp != cctemp)
 		thermal_zone_device_update(priv->zone);
 }
@@ -403,6 +430,8 @@ static int rcar_thermal_probe(struct platform_device *pdev)
 	struct rcar_thermal_priv *priv;
 	struct device *dev = &pdev->dev;
 	struct resource *res, *irq;
+	const struct of_device_id *of_id = of_match_device(rcar_thermal_dt_ids, dev);
+	unsigned long of_data = (unsigned long)of_id->data;
 	int mres = 0;
 	int i;
 	int ret = -ENODEV;
@@ -463,7 +492,13 @@ static int rcar_thermal_probe(struct platform_device *pdev)
 		if (ret < 0)
 			goto error_unregister;
 
-		priv->zone = thermal_zone_device_register("rcar_thermal",
+		if (of_data == USE_OF_THERMAL)
+			priv->zone = thermal_zone_of_sensor_register(
+						dev, i, priv,
+						&rcar_thermal_zone_of_ops);
+		else
+			priv->zone = thermal_zone_device_register(
+						"rcar_thermal",
 						1, 0, priv,
 						&rcar_thermal_zone_ops, NULL, 0,
 						idle);
diff --git a/drivers/thermal/spear_thermal.c b/drivers/thermal/spear_thermal.c
index 534dd9136662..81b35aace9de 100644
--- a/drivers/thermal/spear_thermal.c
+++ b/drivers/thermal/spear_thermal.c
@@ -54,8 +54,7 @@ static struct thermal_zone_device_ops ops = {
 	.get_temp = thermal_get_temp,
 };
 
-#ifdef CONFIG_PM
-static int spear_thermal_suspend(struct device *dev)
+static int __maybe_unused spear_thermal_suspend(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct thermal_zone_device *spear_thermal = platform_get_drvdata(pdev);
@@ -72,7 +71,7 @@ static int spear_thermal_suspend(struct device *dev)
 	return 0;
 }
 
-static int spear_thermal_resume(struct device *dev)
+static int __maybe_unused spear_thermal_resume(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct thermal_zone_device *spear_thermal = platform_get_drvdata(pdev);
@@ -94,7 +93,6 @@ static int spear_thermal_resume(struct device *dev)
 
 	return 0;
 }
-#endif
 
 static SIMPLE_DEV_PM_OPS(spear_thermal_pm_ops, spear_thermal_suspend,
 		spear_thermal_resume);
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index b3110040164a..2348fa613707 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -681,7 +681,14 @@ static void pty_unix98_remove(struct tty_driver *driver, struct tty_struct *tty)
 /* this is called once with whichever end is closed last */
 static void pty_unix98_shutdown(struct tty_struct *tty)
 {
-	devpts_kill_index(tty->driver_data, tty->index);
+	struct inode *ptmx_inode;
+
+	if (tty->driver->subtype == PTY_TYPE_MASTER)
+		ptmx_inode = tty->driver_data;
+	else
+		ptmx_inode = tty->link->driver_data;
+	devpts_kill_index(ptmx_inode, tty->index);
+	devpts_del_ref(ptmx_inode);
 }
 
 static const struct tty_operations ptm_unix98_ops = {
@@ -773,6 +780,18 @@ static int ptmx_open(struct inode *inode, struct file *filp)
 	set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */
 	tty->driver_data = inode;
 
+	/*
+	 * In the case where all references to ptmx inode are dropped and we
+	 * still have /dev/tty opened pointing to the master/slave pair (ptmx
+	 * is closed/released before /dev/tty), we must make sure that the inode
+	 * is still valid when we call the final pty_unix98_shutdown, thus we
+	 * hold an additional reference to the ptmx inode. For the same /dev/tty
+	 * last close case, we also need to make sure the super_block isn't
+	 * destroyed (devpts instance unmounted), before /dev/tty is closed and
+	 * on its release devpts_kill_index is called.
+	 */
+	devpts_add_ref(inode);
+
 	tty_add_file(tty, filp);
 
 	slave_inode = devpts_pty_new(inode,
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index e71ec78fc11e..7cd6f9a90542 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -1941,6 +1941,7 @@ pci_wch_ch38x_setup(struct serial_private *priv,
 #define PCIE_VENDOR_ID_WCH		0x1c00
 #define PCIE_DEVICE_ID_WCH_CH382_2S1P	0x3250
 #define PCIE_DEVICE_ID_WCH_CH384_4S	0x3470
+#define PCIE_DEVICE_ID_WCH_CH382_2S	0x3253
 
 #define PCI_VENDOR_ID_PERICOM			0x12D8
 #define PCI_DEVICE_ID_PERICOM_PI7C9X7951	0x7951
@@ -2637,6 +2638,14 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = {
 		.subdevice	= PCI_ANY_ID,
 		.setup		= pci_wch_ch353_setup,
 	},
+	/* WCH CH382 2S card (16850 clone) */
+	{
+		.vendor         = PCIE_VENDOR_ID_WCH,
+		.device         = PCIE_DEVICE_ID_WCH_CH382_2S,
+		.subvendor      = PCI_ANY_ID,
+		.subdevice      = PCI_ANY_ID,
+		.setup          = pci_wch_ch38x_setup,
+	},
 	/* WCH CH382 2S1P card (16850 clone) */
 	{
 		.vendor         = PCIE_VENDOR_ID_WCH,
@@ -2955,6 +2964,7 @@ enum pci_board_num_t {
 	pbn_fintek_4,
 	pbn_fintek_8,
 	pbn_fintek_12,
+	pbn_wch382_2,
 	pbn_wch384_4,
 	pbn_pericom_PI7C9X7951,
 	pbn_pericom_PI7C9X7952,
@@ -3775,6 +3785,13 @@ static struct pciserial_board pci_boards[] = {
 		.base_baud	= 115200,
 		.first_offset	= 0x40,
 	},
+	[pbn_wch382_2] = {
+		.flags		= FL_BASE0,
+		.num_ports	= 2,
+		.base_baud	= 115200,
+		.uart_offset	= 8,
+		.first_offset	= 0xC0,
+	},
 	[pbn_wch384_4] = {
 		.flags		= FL_BASE0,
 		.num_ports	= 4,
@@ -5574,6 +5591,10 @@ static struct pci_device_id serial_pci_tbl[] = {
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_b0_bt_2_115200 },
 
+	{	PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH382_2S,
+		PCI_ANY_ID, PCI_ANY_ID,
+		0, 0, pbn_wch382_2 },
+
 	{	PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH384_4S,
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_wch384_4 },
diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index b645f9228ed7..fa49eb1e2fa2 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -1165,7 +1165,7 @@ serial_omap_type(struct uart_port *port)
 
 #define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE)
 
-static void wait_for_xmitr(struct uart_omap_port *up)
+static void __maybe_unused wait_for_xmitr(struct uart_omap_port *up)
 {
 	unsigned int status, tmout = 10000;
 
@@ -1343,7 +1343,7 @@ static inline void serial_omap_add_console_port(struct uart_omap_port *up)
 
 /* Enable or disable the rs485 support */
 static int
-serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485conf)
+serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485)
 {
 	struct uart_omap_port *up = to_uart_omap_port(port);
 	unsigned int mode;
@@ -1356,8 +1356,12 @@ serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485conf)
 	up->ier = 0;
 	serial_out(up, UART_IER, 0);
 
+	/* Clamp the delays to [0, 100ms] */
+	rs485->delay_rts_before_send = min(rs485->delay_rts_before_send, 100U);
+	rs485->delay_rts_after_send  = min(rs485->delay_rts_after_send, 100U);
+
 	/* store new config */
-	port->rs485 = *rs485conf;
+	port->rs485 = *rs485;
 
 	/*
 	 * Just as a precaution, only allow rs485
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 5cec01c75691..a7eacef1bd22 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2066,13 +2066,12 @@ retry_open:
 		if (tty) {
 			mutex_unlock(&tty_mutex);
 			retval = tty_lock_interruptible(tty);
+			tty_kref_put(tty);  /* drop kref from tty_driver_lookup_tty() */
 			if (retval) {
 				if (retval == -EINTR)
 					retval = -ERESTARTSYS;
 				goto err_unref;
 			}
-			/* safe to drop the kref from tty_driver_lookup_tty() */
-			tty_kref_put(tty);
 			retval = tty_reopen(tty);
 			if (retval < 0) {
 				tty_unlock(tty);
diff --git a/drivers/tty/tty_mutex.c b/drivers/tty/tty_mutex.c
index d2f3c4cd697f..dfa9ec03fa8e 100644
--- a/drivers/tty/tty_mutex.c
+++ b/drivers/tty/tty_mutex.c
@@ -21,10 +21,15 @@ EXPORT_SYMBOL(tty_lock);
 
 int tty_lock_interruptible(struct tty_struct *tty)
 {
+	int ret;
+
 	if (WARN(tty->magic != TTY_MAGIC, "L Bad %p\n", tty))
 		return -EIO;
 	tty_kref_get(tty);
-	return mutex_lock_interruptible(&tty->legacy_mutex);
+	ret = mutex_lock_interruptible(&tty->legacy_mutex);
+	if (ret)
+		tty_kref_put(tty);
+	return ret;
 }
 
 void __lockfunc tty_unlock(struct tty_struct *tty)
diff --git a/drivers/usb/chipidea/ci_hdrc_pci.c b/drivers/usb/chipidea/ci_hdrc_pci.c
index b59195edf636..b635ab67490d 100644
--- a/drivers/usb/chipidea/ci_hdrc_pci.c
+++ b/drivers/usb/chipidea/ci_hdrc_pci.c
@@ -85,8 +85,8 @@ static int ci_hdrc_pci_probe(struct pci_dev *pdev,
 
 	/* register a nop PHY */
 	ci->phy = usb_phy_generic_register();
-	if (!ci->phy)
-		return -ENOMEM;
+	if (IS_ERR(ci->phy))
+		return PTR_ERR(ci->phy);
 
 	memset(res, 0, sizeof(res));
 	res[0].start	= pci_resource_start(pdev, 0);
diff --git a/drivers/usb/chipidea/debug.c b/drivers/usb/chipidea/debug.c
index a4f7db2e18dd..df47110bad2d 100644
--- a/drivers/usb/chipidea/debug.c
+++ b/drivers/usb/chipidea/debug.c
@@ -100,6 +100,9 @@ static ssize_t ci_port_test_write(struct file *file, const char __user *ubuf,
 	if (sscanf(buf, "%u", &mode) != 1)
 		return -EINVAL;
 
+	if (mode > 255)
+		return -EBADRQC;
+
 	pm_runtime_get_sync(ci->dev);
 	spin_lock_irqsave(&ci->lock, flags);
 	ret = hw_port_test_set(ci, mode);
diff --git a/drivers/usb/chipidea/otg.c b/drivers/usb/chipidea/otg.c
index 45f86da1d6d3..03b6743461d1 100644
--- a/drivers/usb/chipidea/otg.c
+++ b/drivers/usb/chipidea/otg.c
@@ -158,7 +158,7 @@ static void ci_otg_work(struct work_struct *work)
 int ci_hdrc_otg_init(struct ci_hdrc *ci)
 {
 	INIT_WORK(&ci->work, ci_otg_work);
-	ci->wq = create_singlethread_workqueue("ci_otg");
+	ci->wq = create_freezable_workqueue("ci_otg");
 	if (!ci->wq) {
 		dev_err(ci->dev, "can't create workqueue\n");
 		return -ENODEV;
diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c
index 9eb1cff28bd4..c3640f8a8fb3 100644
--- a/drivers/usb/core/hcd-pci.c
+++ b/drivers/usb/core/hcd-pci.c
@@ -28,7 +28,6 @@
 #ifdef CONFIG_PPC_PMAC
 #include <asm/machdep.h>
 #include <asm/pmac_feature.h>
-#include <asm/pci-bridge.h>
 #include <asm/prom.h>
 #endif
 
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 350dcd9af5d8..51b436918f78 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -5401,6 +5401,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
 	}
 
 	bos = udev->bos;
+	udev->bos = NULL;
 
 	for (i = 0; i < SET_CONFIG_TRIES; ++i) {
 
@@ -5493,11 +5494,8 @@ done:
 	usb_set_usb2_hardware_lpm(udev, 1);
 	usb_unlocked_enable_lpm(udev);
 	usb_enable_ltm(udev);
-	/* release the new BOS descriptor allocated  by hub_port_init() */
-	if (udev->bos != bos) {
-		usb_release_bos_descriptor(udev);
-		udev->bos = bos;
-	}
+	usb_release_bos_descriptor(udev);
+	udev->bos = bos;
 	return 0;
 
 re_enumerate:
diff --git a/drivers/usb/dwc2/Kconfig b/drivers/usb/dwc2/Kconfig
index fd95ba6ec317..f0decc0d69b5 100644
--- a/drivers/usb/dwc2/Kconfig
+++ b/drivers/usb/dwc2/Kconfig
@@ -1,5 +1,6 @@
 config USB_DWC2
 	tristate "DesignWare USB2 DRD Core Support"
+	depends on HAS_DMA
 	depends on USB || USB_GADGET
 	help
 	  Say Y here if your system has a Dual Role Hi-Speed USB
diff --git a/drivers/usb/dwc2/core.c b/drivers/usb/dwc2/core.c
index e991d55914db..46c4ba75dc2a 100644
--- a/drivers/usb/dwc2/core.c
+++ b/drivers/usb/dwc2/core.c
@@ -619,6 +619,12 @@ void dwc2_force_dr_mode(struct dwc2_hsotg *hsotg)
 			 __func__, hsotg->dr_mode);
 		break;
 	}
+
+	/*
+	 * NOTE: This is required for some rockchip soc based
+	 * platforms.
+	 */
+	msleep(50);
 }
 
 /*
diff --git a/drivers/usb/dwc2/hcd_ddma.c b/drivers/usb/dwc2/hcd_ddma.c
index 36606fc33c0d..a41274aa52ad 100644
--- a/drivers/usb/dwc2/hcd_ddma.c
+++ b/drivers/usb/dwc2/hcd_ddma.c
@@ -1174,14 +1174,11 @@ static int dwc2_process_non_isoc_desc(struct dwc2_hsotg *hsotg,
 	failed = dwc2_update_non_isoc_urb_state_ddma(hsotg, chan, qtd, dma_desc,
 						     halt_status, n_bytes,
 						     xfer_done);
-	if (*xfer_done && urb->status != -EINPROGRESS)
-		failed = 1;
-
-	if (failed) {
+	if (failed || (*xfer_done && urb->status != -EINPROGRESS)) {
 		dwc2_host_complete(hsotg, qtd, urb->status);
 		dwc2_hcd_qtd_unlink_and_free(hsotg, qtd, qh);
-		dev_vdbg(hsotg->dev, "failed=%1x xfer_done=%1x status=%08x\n",
-			 failed, *xfer_done, urb->status);
+		dev_vdbg(hsotg->dev, "failed=%1x xfer_done=%1x\n",
+			 failed, *xfer_done);
 		return failed;
 	}
 
@@ -1236,21 +1233,23 @@ static void dwc2_complete_non_isoc_xfer_ddma(struct dwc2_hsotg *hsotg,
 
 	list_for_each_safe(qtd_item, qtd_tmp, &qh->qtd_list) {
 		int i;
+		int qtd_desc_count;
 
 		qtd = list_entry(qtd_item, struct dwc2_qtd, qtd_list_entry);
 		xfer_done = 0;
+		qtd_desc_count = qtd->n_desc;
 
-		for (i = 0; i < qtd->n_desc; i++) {
+		for (i = 0; i < qtd_desc_count; i++) {
 			if (dwc2_process_non_isoc_desc(hsotg, chan, chnum, qtd,
 						       desc_num, halt_status,
-						       &xfer_done)) {
-				qtd = NULL;
-				break;
-			}
+						       &xfer_done))
+				goto stop_scan;
+
 			desc_num++;
 		}
 	}
 
+stop_scan:
 	if (qh->ep_type != USB_ENDPOINT_XFER_CONTROL) {
 		/*
 		 * Resetting the data toggle for bulk and interrupt endpoints
@@ -1258,7 +1257,7 @@ static void dwc2_complete_non_isoc_xfer_ddma(struct dwc2_hsotg *hsotg,
 		 */
 		if (halt_status == DWC2_HC_XFER_STALL)
 			qh->data_toggle = DWC2_HC_PID_DATA0;
-		else if (qtd)
+		else
 			dwc2_hcd_save_data_toggle(hsotg, chan, chnum, qtd);
 	}
 
diff --git a/drivers/usb/dwc2/hcd_intr.c b/drivers/usb/dwc2/hcd_intr.c
index f8253803a050..cadba8b13c48 100644
--- a/drivers/usb/dwc2/hcd_intr.c
+++ b/drivers/usb/dwc2/hcd_intr.c
@@ -525,11 +525,19 @@ void dwc2_hcd_save_data_toggle(struct dwc2_hsotg *hsotg,
 	u32 pid = (hctsiz & TSIZ_SC_MC_PID_MASK) >> TSIZ_SC_MC_PID_SHIFT;
 
 	if (chan->ep_type != USB_ENDPOINT_XFER_CONTROL) {
+		if (WARN(!chan || !chan->qh,
+			 "chan->qh must be specified for non-control eps\n"))
+			return;
+
 		if (pid == TSIZ_SC_MC_PID_DATA0)
 			chan->qh->data_toggle = DWC2_HC_PID_DATA0;
 		else
 			chan->qh->data_toggle = DWC2_HC_PID_DATA1;
 	} else {
+		if (WARN(!qtd,
+			 "qtd must be specified for control eps\n"))
+			return;
+
 		if (pid == TSIZ_SC_MC_PID_DATA0)
 			qtd->data_toggle = DWC2_HC_PID_DATA0;
 		else
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 29130682e547..e4f8b90d9627 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -856,7 +856,6 @@ struct dwc3 {
 	unsigned		pullups_connected:1;
 	unsigned		resize_fifos:1;
 	unsigned		setup_packet_pending:1;
-	unsigned		start_config_issued:1;
 	unsigned		three_stage_setup:1;
 	unsigned		usb3_lpm_capable:1;
 
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index 3a9354abcb68..8d6b75c2f53b 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -555,7 +555,6 @@ static int dwc3_ep0_set_config(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl)
 	int ret;
 	u32 reg;
 
-	dwc->start_config_issued = false;
 	cfg = le16_to_cpu(ctrl->wValue);
 
 	switch (state) {
@@ -737,10 +736,6 @@ static int dwc3_ep0_std_request(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl)
 		dwc3_trace(trace_dwc3_ep0, "USB_REQ_SET_ISOCH_DELAY");
 		ret = dwc3_ep0_set_isoch_delay(dwc, ctrl);
 		break;
-	case USB_REQ_SET_INTERFACE:
-		dwc3_trace(trace_dwc3_ep0, "USB_REQ_SET_INTERFACE");
-		dwc->start_config_issued = false;
-		/* Fall through */
 	default:
 		dwc3_trace(trace_dwc3_ep0, "Forwarding to gadget driver");
 		ret = dwc3_ep0_delegate_req(dwc, ctrl);
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 7d1dd82a95ac..2363bad45af8 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -385,24 +385,66 @@ static void dwc3_free_trb_pool(struct dwc3_ep *dep)
 	dep->trb_pool_dma = 0;
 }
 
+static int dwc3_gadget_set_xfer_resource(struct dwc3 *dwc, struct dwc3_ep *dep);
+
+/**
+ * dwc3_gadget_start_config - Configure EP resources
+ * @dwc: pointer to our controller context structure
+ * @dep: endpoint that is being enabled
+ *
+ * The assignment of transfer resources cannot perfectly follow the
+ * data book due to the fact that the controller driver does not have
+ * all knowledge of the configuration in advance. It is given this
+ * information piecemeal by the composite gadget framework after every
+ * SET_CONFIGURATION and SET_INTERFACE. Trying to follow the databook
+ * programming model in this scenario can cause errors. For two
+ * reasons:
+ *
+ * 1) The databook says to do DEPSTARTCFG for every SET_CONFIGURATION
+ * and SET_INTERFACE (8.1.5). This is incorrect in the scenario of
+ * multiple interfaces.
+ *
+ * 2) The databook does not mention doing more DEPXFERCFG for new
+ * endpoint on alt setting (8.1.6).
+ *
+ * The following simplified method is used instead:
+ *
+ * All hardware endpoints can be assigned a transfer resource and this
+ * setting will stay persistent until either a core reset or
+ * hibernation. So whenever we do a DEPSTARTCFG(0) we can go ahead and
+ * do DEPXFERCFG for every hardware endpoint as well. We are
+ * guaranteed that there are as many transfer resources as endpoints.
+ *
+ * This function is called for each endpoint when it is being enabled
+ * but is triggered only when called for EP0-out, which always happens
+ * first, and which should only happen in one of the above conditions.
+ */
 static int dwc3_gadget_start_config(struct dwc3 *dwc, struct dwc3_ep *dep)
 {
 	struct dwc3_gadget_ep_cmd_params params;
 	u32			cmd;
+	int			i;
+	int			ret;
+
+	if (dep->number)
+		return 0;
 
 	memset(&params, 0x00, sizeof(params));
+	cmd = DWC3_DEPCMD_DEPSTARTCFG;
 
-	if (dep->number != 1) {
-		cmd = DWC3_DEPCMD_DEPSTARTCFG;
-		/* XferRscIdx == 0 for ep0 and 2 for the remaining */
-		if (dep->number > 1) {
-			if (dwc->start_config_issued)
-				return 0;
-			dwc->start_config_issued = true;
-			cmd |= DWC3_DEPCMD_PARAM(2);
-		}
+	ret = dwc3_send_gadget_ep_cmd(dwc, 0, cmd, &params);
+	if (ret)
+		return ret;
 
-		return dwc3_send_gadget_ep_cmd(dwc, 0, cmd, &params);
+	for (i = 0; i < DWC3_ENDPOINTS_NUM; i++) {
+		struct dwc3_ep *dep = dwc->eps[i];
+
+		if (!dep)
+			continue;
+
+		ret = dwc3_gadget_set_xfer_resource(dwc, dep);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
@@ -516,10 +558,6 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep,
 		struct dwc3_trb	*trb_st_hw;
 		struct dwc3_trb	*trb_link;
 
-		ret = dwc3_gadget_set_xfer_resource(dwc, dep);
-		if (ret)
-			return ret;
-
 		dep->endpoint.desc = desc;
 		dep->comp_desc = comp_desc;
 		dep->type = usb_endpoint_type(desc);
@@ -1636,8 +1674,6 @@ static int dwc3_gadget_start(struct usb_gadget *g,
 	}
 	dwc3_writel(dwc->regs, DWC3_DCFG, reg);
 
-	dwc->start_config_issued = false;
-
 	/* Start with SuperSpeed Default */
 	dwc3_gadget_ep0_desc.wMaxPacketSize = cpu_to_le16(512);
 
@@ -2237,7 +2273,6 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc)
 	dwc3_writel(dwc->regs, DWC3_DCTL, reg);
 
 	dwc3_disconnect_gadget(dwc);
-	dwc->start_config_issued = false;
 
 	dwc->gadget.speed = USB_SPEED_UNKNOWN;
 	dwc->setup_packet_pending = false;
@@ -2288,7 +2323,6 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc)
 
 	dwc3_stop_active_transfers(dwc);
 	dwc3_clear_stall_all_ep(dwc);
-	dwc->start_config_issued = false;
 
 	/* Reset device address to zero */
 	reg = dwc3_readl(dwc->regs, DWC3_DCFG);
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index 7e179f81d05c..87fb0fd6aaab 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -130,7 +130,8 @@ struct dev_data {
 					setup_can_stall : 1,
 					setup_out_ready : 1,
 					setup_out_error : 1,
-					setup_abort : 1;
+					setup_abort : 1,
+					gadget_registered : 1;
 	unsigned			setup_wLength;
 
 	/* the rest is basically write-once */
@@ -1179,7 +1180,8 @@ dev_release (struct inode *inode, struct file *fd)
 
 	/* closing ep0 === shutdown all */
 
-	usb_gadget_unregister_driver (&gadgetfs_driver);
+	if (dev->gadget_registered)
+		usb_gadget_unregister_driver (&gadgetfs_driver);
 
 	/* at this point "good" hardware has disconnected the
 	 * device from USB; the host won't see it any more.
@@ -1847,6 +1849,7 @@ dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr)
 		 * kick in after the ep0 descriptor is closed.
 		 */
 		value = len;
+		dev->gadget_registered = true;
 	}
 	return value;
 
diff --git a/drivers/usb/gadget/udc/amd5536udc.c b/drivers/usb/gadget/udc/amd5536udc.c
index cd8764150861..39d70b4a8958 100644
--- a/drivers/usb/gadget/udc/amd5536udc.c
+++ b/drivers/usb/gadget/udc/amd5536udc.c
@@ -3397,7 +3397,7 @@ err_pcidev:
 static const struct pci_device_id pci_id[] = {
 	{
 		PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x2096),
-		.class =	(PCI_CLASS_SERIAL_USB << 8) | 0xfe,
+		.class =	PCI_CLASS_SERIAL_USB_DEVICE,
 		.class_mask =	0xffffffff,
 	},
 	{},
diff --git a/drivers/usb/gadget/udc/fsl_qe_udc.c b/drivers/usb/gadget/udc/fsl_qe_udc.c
index 53c0692f1b09..93d28cb00b76 100644
--- a/drivers/usb/gadget/udc/fsl_qe_udc.c
+++ b/drivers/usb/gadget/udc/fsl_qe_udc.c
@@ -2340,7 +2340,7 @@ static struct qe_udc *qe_udc_config(struct platform_device *ofdev)
 {
 	struct qe_udc *udc;
 	struct device_node *np = ofdev->dev.of_node;
-	unsigned int tmp_addr = 0;
+	unsigned long tmp_addr = 0;
 	struct usb_device_para __iomem *usbpram;
 	unsigned int i;
 	u64 size;
diff --git a/drivers/usb/gadget/udc/goku_udc.c b/drivers/usb/gadget/udc/goku_udc.c
index 1fdfec14a3ba..d2205d9e0c8b 100644
--- a/drivers/usb/gadget/udc/goku_udc.c
+++ b/drivers/usb/gadget/udc/goku_udc.c
@@ -1846,7 +1846,7 @@ err:
 /*-------------------------------------------------------------------------*/
 
 static const struct pci_device_id pci_ids[] = { {
-	.class =	((PCI_CLASS_SERIAL_USB << 8) | 0xfe),
+	.class =	PCI_CLASS_SERIAL_USB_DEVICE,
 	.class_mask =	~0,
 	.vendor =	0x102f,		/* Toshiba */
 	.device =	0x0107,		/* this UDC */
diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c
index 6706aef907f4..c894b94b234b 100644
--- a/drivers/usb/gadget/udc/net2280.c
+++ b/drivers/usb/gadget/udc/net2280.c
@@ -3735,7 +3735,7 @@ static void net2280_shutdown(struct pci_dev *pdev)
 /*-------------------------------------------------------------------------*/
 
 static const struct pci_device_id pci_ids[] = { {
-	.class =	((PCI_CLASS_SERIAL_USB << 8) | 0xfe),
+	.class =	PCI_CLASS_SERIAL_USB_DEVICE,
 	.class_mask =	~0,
 	.vendor =	PCI_VENDOR_ID_PLX_LEGACY,
 	.device =	0x2280,
@@ -3743,7 +3743,7 @@ static const struct pci_device_id pci_ids[] = { {
 	.subdevice =	PCI_ANY_ID,
 	.driver_data =	PLX_LEGACY | PLX_2280,
 	}, {
-	.class =	((PCI_CLASS_SERIAL_USB << 8) | 0xfe),
+	.class =	PCI_CLASS_SERIAL_USB_DEVICE,
 	.class_mask =	~0,
 	.vendor =	PCI_VENDOR_ID_PLX_LEGACY,
 	.device =	0x2282,
@@ -3752,7 +3752,7 @@ static const struct pci_device_id pci_ids[] = { {
 	.driver_data =	PLX_LEGACY,
 	},
 	{
-	.class =	((PCI_CLASS_SERIAL_USB << 8) | 0xfe),
+	.class =	PCI_CLASS_SERIAL_USB_DEVICE,
 	.class_mask =	~0,
 	.vendor =	PCI_VENDOR_ID_PLX,
 	.device =	0x3380,
@@ -3761,7 +3761,7 @@ static const struct pci_device_id pci_ids[] = { {
 	.driver_data =	PLX_SUPERSPEED,
 	 },
 	{
-	.class =	((PCI_CLASS_SERIAL_USB << 8) | 0xfe),
+	.class =	PCI_CLASS_SERIAL_USB_DEVICE,
 	.class_mask =	~0,
 	.vendor =	PCI_VENDOR_ID_PLX,
 	.device =	0x3382,
diff --git a/drivers/usb/gadget/udc/net2280.h b/drivers/usb/gadget/udc/net2280.h
index 4dff60d34f73..0d32052bf16f 100644
--- a/drivers/usb/gadget/udc/net2280.h
+++ b/drivers/usb/gadget/udc/net2280.h
@@ -369,9 +369,20 @@ static inline void set_max_speed(struct net2280_ep *ep, u32 max)
 	static const u32 ep_enhanced[9] = { 0x10, 0x60, 0x30, 0x80,
 					  0x50, 0x20, 0x70, 0x40, 0x90 };
 
-	if (ep->dev->enhanced_mode)
+	if (ep->dev->enhanced_mode) {
 		reg = ep_enhanced[ep->num];
-	else{
+		switch (ep->dev->gadget.speed) {
+		case USB_SPEED_SUPER:
+			reg += 2;
+			break;
+		case USB_SPEED_FULL:
+			reg += 1;
+			break;
+		case USB_SPEED_HIGH:
+		default:
+			break;
+		}
+	} else {
 		reg = (ep->num + 1) * 0x10;
 		if (ep->dev->gadget.speed != USB_SPEED_HIGH)
 			reg += 1;
diff --git a/drivers/usb/gadget/udc/pch_udc.c b/drivers/usb/gadget/udc/pch_udc.c
index 7a04157ff579..9571ef54b86b 100644
--- a/drivers/usb/gadget/udc/pch_udc.c
+++ b/drivers/usb/gadget/udc/pch_udc.c
@@ -3234,22 +3234,22 @@ static const struct pci_device_id pch_udc_pcidev_id[] = {
 	{
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL,
 			   PCI_DEVICE_ID_INTEL_QUARK_X1000_UDC),
-		.class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe,
+		.class = PCI_CLASS_SERIAL_USB_DEVICE,
 		.class_mask = 0xffffffff,
 	},
 	{
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_EG20T_UDC),
-		.class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe,
+		.class = PCI_CLASS_SERIAL_USB_DEVICE,
 		.class_mask = 0xffffffff,
 	},
 	{
 		PCI_DEVICE(PCI_VENDOR_ID_ROHM, PCI_DEVICE_ID_ML7213_IOH_UDC),
-		.class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe,
+		.class = PCI_CLASS_SERIAL_USB_DEVICE,
 		.class_mask = 0xffffffff,
 	},
 	{
 		PCI_DEVICE(PCI_VENDOR_ID_ROHM, PCI_DEVICE_ID_ML7831_IOH_UDC),
-		.class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe,
+		.class = PCI_CLASS_SERIAL_USB_DEVICE,
 		.class_mask = 0xffffffff,
 	},
 	{ 0 },
diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c
index fd73a3ea07c2..b86a6f03592e 100644
--- a/drivers/usb/gadget/udc/udc-core.c
+++ b/drivers/usb/gadget/udc/udc-core.c
@@ -413,9 +413,10 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget,
 		if (!driver->udc_name || strcmp(driver->udc_name,
 						dev_name(&udc->dev)) == 0) {
 			ret = udc_bind_to_driver(udc, driver);
+			if (ret != -EPROBE_DEFER)
+				list_del(&driver->pending);
 			if (ret)
 				goto err4;
-			list_del(&driver->pending);
 			break;
 		}
 	}
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index 795a45b1b25b..58487a473521 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -662,7 +662,7 @@ static int musb_tx_dma_set_mode_mentor(struct dma_controller *dma,
 		csr &= ~(MUSB_TXCSR_AUTOSET | MUSB_TXCSR_DMAMODE);
 		csr |= MUSB_TXCSR_DMAENAB; /* against programmer's guide */
 	}
-	channel->desired_mode = mode;
+	channel->desired_mode = *mode;
 	musb_writew(epio, MUSB_TXCSR, csr);
 
 	return 0;
@@ -2003,10 +2003,8 @@ void musb_host_rx(struct musb *musb, u8 epnum)
 				qh->offset,
 				urb->transfer_buffer_length);
 
-			done = musb_rx_dma_in_inventra_cppi41(c, hw_ep, qh,
-							      urb, xfer_len,
-							      iso_err);
-			if (done)
+			if (musb_rx_dma_in_inventra_cppi41(c, hw_ep, qh, urb,
+							   xfer_len, iso_err))
 				goto finish;
 			else
 				dev_err(musb->controller, "error: rx_dma failed\n");
diff --git a/drivers/usb/musb/sunxi.c b/drivers/usb/musb/sunxi.c
index d9b0dc461439..fdab4232cfbf 100644
--- a/drivers/usb/musb/sunxi.c
+++ b/drivers/usb/musb/sunxi.c
@@ -752,6 +752,7 @@ static const struct of_device_id sunxi_musb_match[] = {
 	{ .compatible = "allwinner,sun8i-a33-musb", },
 	{}
 };
+MODULE_DEVICE_TABLE(of, sunxi_musb_match);
 
 static struct platform_driver sunxi_musb_driver = {
 	.probe = sunxi_musb_probe,
diff --git a/drivers/usb/phy/phy-msm-usb.c b/drivers/usb/phy/phy-msm-usb.c
index 970a30e155cb..72b387d592c2 100644
--- a/drivers/usb/phy/phy-msm-usb.c
+++ b/drivers/usb/phy/phy-msm-usb.c
@@ -757,14 +757,8 @@ static int msm_otg_set_host(struct usb_otg *otg, struct usb_bus *host)
 	otg->host = host;
 	dev_dbg(otg->usb_phy->dev, "host driver registered w/ tranceiver\n");
 
-	/*
-	 * Kick the state machine work, if peripheral is not supported
-	 * or peripheral is already registered with us.
-	 */
-	if (motg->pdata->mode == USB_DR_MODE_HOST || otg->gadget) {
-		pm_runtime_get_sync(otg->usb_phy->dev);
-		schedule_work(&motg->sm_work);
-	}
+	pm_runtime_get_sync(otg->usb_phy->dev);
+	schedule_work(&motg->sm_work);
 
 	return 0;
 }
@@ -827,14 +821,8 @@ static int msm_otg_set_peripheral(struct usb_otg *otg,
 	dev_dbg(otg->usb_phy->dev,
 		"peripheral driver registered w/ tranceiver\n");
 
-	/*
-	 * Kick the state machine work, if host is not supported
-	 * or host is already registered with us.
-	 */
-	if (motg->pdata->mode == USB_DR_MODE_PERIPHERAL || otg->host) {
-		pm_runtime_get_sync(otg->usb_phy->dev);
-		schedule_work(&motg->sm_work);
-	}
+	pm_runtime_get_sync(otg->usb_phy->dev);
+	schedule_work(&motg->sm_work);
 
 	return 0;
 }
diff --git a/drivers/usb/serial/Kconfig b/drivers/usb/serial/Kconfig
index f612dda9c977..56ecb8b5115d 100644
--- a/drivers/usb/serial/Kconfig
+++ b/drivers/usb/serial/Kconfig
@@ -475,22 +475,6 @@ config USB_SERIAL_MOS7840
 	  To compile this driver as a module, choose M here: the
 	  module will be called mos7840.  If unsure, choose N.
 
-config USB_SERIAL_MXUPORT11
-	tristate "USB Moxa UPORT 11x0 Serial Driver"
-	---help---
-	  Say Y here if you want to use a MOXA UPort 11x0 Serial hub.
-
-	  This driver supports:
-
-	  - UPort 1110  : 1 port RS-232 USB to Serial Hub.
-	  - UPort 1130  : 1 port RS-422/485 USB to Serial Hub.
-	  - UPort 1130I : 1 port RS-422/485 USB to Serial Hub with Isolation.
-	  - UPort 1150  : 1 port RS-232/422/485 USB to Serial Hub.
-	  - UPort 1150I : 1 port RS-232/422/485 USB to Serial Hub with Isolation.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called mxu11x0.
-
 config USB_SERIAL_MXUPORT
 	tristate "USB Moxa UPORT Serial Driver"
 	---help---
diff --git a/drivers/usb/serial/Makefile b/drivers/usb/serial/Makefile
index f3fa5e53702d..349d9df0895f 100644
--- a/drivers/usb/serial/Makefile
+++ b/drivers/usb/serial/Makefile
@@ -38,7 +38,6 @@ obj-$(CONFIG_USB_SERIAL_METRO)			+= metro-usb.o
 obj-$(CONFIG_USB_SERIAL_MOS7720)		+= mos7720.o
 obj-$(CONFIG_USB_SERIAL_MOS7840)		+= mos7840.o
 obj-$(CONFIG_USB_SERIAL_MXUPORT)		+= mxuport.o
-obj-$(CONFIG_USB_SERIAL_MXUPORT11)		+= mxu11x0.o
 obj-$(CONFIG_USB_SERIAL_NAVMAN)			+= navman.o
 obj-$(CONFIG_USB_SERIAL_OMNINET)		+= omninet.o
 obj-$(CONFIG_USB_SERIAL_OPTICON)		+= opticon.o
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 987813b8a7f9..73a366de5102 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -163,6 +163,9 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */
 	{ USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */
 	{ USB_DEVICE(0x18EF, 0xE025) }, /* ELV Marble Sound Board 1 */
+	{ USB_DEVICE(0x1901, 0x0190) }, /* GE B850 CP2105 Recorder interface */
+	{ USB_DEVICE(0x1901, 0x0193) }, /* GE B650 CP2104 PMC interface */
+	{ USB_DEVICE(0x19CF, 0x3000) }, /* Parrot NMEA GPS Flight Recorder */
 	{ USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */
 	{ USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */
 	{ USB_DEVICE(0x1BA4, 0x0002) },	/* Silicon Labs 358x factory default */
diff --git a/drivers/usb/serial/mxu11x0.c b/drivers/usb/serial/mxu11x0.c
deleted file mode 100644
index 619607323bfd..000000000000
--- a/drivers/usb/serial/mxu11x0.c
+++ /dev/null
@@ -1,1006 +0,0 @@
-/*
- * USB Moxa UPORT 11x0 Serial Driver
- *
- * Copyright (C) 2007 MOXA Technologies Co., Ltd.
- * Copyright (C) 2015 Mathieu Othacehe <m.othacehe@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- *
- * Supports the following Moxa USB to serial converters:
- *  UPort 1110,  1 port RS-232 USB to Serial Hub.
- *  UPort 1130,  1 port RS-422/485 USB to Serial Hub.
- *  UPort 1130I, 1 port RS-422/485 USB to Serial Hub with isolation
- *    protection.
- *  UPort 1150,  1 port RS-232/422/485 USB to Serial Hub.
- *  UPort 1150I, 1 port RS-232/422/485 USB to Serial Hub with isolation
- *  protection.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/firmware.h>
-#include <linux/jiffies.h>
-#include <linux/serial.h>
-#include <linux/serial_reg.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/mutex.h>
-#include <linux/tty.h>
-#include <linux/tty_driver.h>
-#include <linux/tty_flip.h>
-#include <linux/uaccess.h>
-#include <linux/usb.h>
-#include <linux/usb/serial.h>
-
-/* Vendor and product ids */
-#define MXU1_VENDOR_ID				0x110a
-#define MXU1_1110_PRODUCT_ID			0x1110
-#define MXU1_1130_PRODUCT_ID			0x1130
-#define MXU1_1150_PRODUCT_ID			0x1150
-#define MXU1_1151_PRODUCT_ID			0x1151
-#define MXU1_1131_PRODUCT_ID			0x1131
-
-/* Commands */
-#define MXU1_GET_VERSION			0x01
-#define MXU1_GET_PORT_STATUS			0x02
-#define MXU1_GET_PORT_DEV_INFO			0x03
-#define MXU1_GET_CONFIG				0x04
-#define MXU1_SET_CONFIG				0x05
-#define MXU1_OPEN_PORT				0x06
-#define MXU1_CLOSE_PORT				0x07
-#define MXU1_START_PORT				0x08
-#define MXU1_STOP_PORT				0x09
-#define MXU1_TEST_PORT				0x0A
-#define MXU1_PURGE_PORT				0x0B
-#define MXU1_RESET_EXT_DEVICE			0x0C
-#define MXU1_GET_OUTQUEUE			0x0D
-#define MXU1_WRITE_DATA				0x80
-#define MXU1_READ_DATA				0x81
-#define MXU1_REQ_TYPE_CLASS			0x82
-
-/* Module identifiers */
-#define MXU1_I2C_PORT				0x01
-#define MXU1_IEEE1284_PORT			0x02
-#define MXU1_UART1_PORT				0x03
-#define MXU1_UART2_PORT				0x04
-#define MXU1_RAM_PORT				0x05
-
-/* Modem status */
-#define MXU1_MSR_DELTA_CTS			0x01
-#define MXU1_MSR_DELTA_DSR			0x02
-#define MXU1_MSR_DELTA_RI			0x04
-#define MXU1_MSR_DELTA_CD			0x08
-#define MXU1_MSR_CTS				0x10
-#define MXU1_MSR_DSR				0x20
-#define MXU1_MSR_RI				0x40
-#define MXU1_MSR_CD				0x80
-#define MXU1_MSR_DELTA_MASK			0x0F
-#define MXU1_MSR_MASK				0xF0
-
-/* Line status */
-#define MXU1_LSR_OVERRUN_ERROR			0x01
-#define MXU1_LSR_PARITY_ERROR			0x02
-#define MXU1_LSR_FRAMING_ERROR			0x04
-#define MXU1_LSR_BREAK				0x08
-#define MXU1_LSR_ERROR				0x0F
-#define MXU1_LSR_RX_FULL			0x10
-#define MXU1_LSR_TX_EMPTY			0x20
-
-/* Modem control */
-#define MXU1_MCR_LOOP				0x04
-#define MXU1_MCR_DTR				0x10
-#define MXU1_MCR_RTS				0x20
-
-/* Mask settings */
-#define MXU1_UART_ENABLE_RTS_IN			0x0001
-#define MXU1_UART_DISABLE_RTS			0x0002
-#define MXU1_UART_ENABLE_PARITY_CHECKING	0x0008
-#define MXU1_UART_ENABLE_DSR_OUT		0x0010
-#define MXU1_UART_ENABLE_CTS_OUT		0x0020
-#define MXU1_UART_ENABLE_X_OUT			0x0040
-#define MXU1_UART_ENABLE_XA_OUT			0x0080
-#define MXU1_UART_ENABLE_X_IN			0x0100
-#define MXU1_UART_ENABLE_DTR_IN			0x0800
-#define MXU1_UART_DISABLE_DTR			0x1000
-#define MXU1_UART_ENABLE_MS_INTS		0x2000
-#define MXU1_UART_ENABLE_AUTO_START_DMA		0x4000
-#define MXU1_UART_SEND_BREAK_SIGNAL		0x8000
-
-/* Parity */
-#define MXU1_UART_NO_PARITY			0x00
-#define MXU1_UART_ODD_PARITY			0x01
-#define MXU1_UART_EVEN_PARITY			0x02
-#define MXU1_UART_MARK_PARITY			0x03
-#define MXU1_UART_SPACE_PARITY			0x04
-
-/* Stop bits */
-#define MXU1_UART_1_STOP_BITS			0x00
-#define MXU1_UART_1_5_STOP_BITS			0x01
-#define MXU1_UART_2_STOP_BITS			0x02
-
-/* Bits per character */
-#define MXU1_UART_5_DATA_BITS			0x00
-#define MXU1_UART_6_DATA_BITS			0x01
-#define MXU1_UART_7_DATA_BITS			0x02
-#define MXU1_UART_8_DATA_BITS			0x03
-
-/* Operation modes */
-#define MXU1_UART_232				0x00
-#define MXU1_UART_485_RECEIVER_DISABLED		0x01
-#define MXU1_UART_485_RECEIVER_ENABLED		0x02
-
-/* Pipe transfer mode and timeout */
-#define MXU1_PIPE_MODE_CONTINUOUS		0x01
-#define MXU1_PIPE_MODE_MASK			0x03
-#define MXU1_PIPE_TIMEOUT_MASK			0x7C
-#define MXU1_PIPE_TIMEOUT_ENABLE		0x80
-
-/* Config struct */
-struct mxu1_uart_config {
-	__be16	wBaudRate;
-	__be16	wFlags;
-	u8	bDataBits;
-	u8	bParity;
-	u8	bStopBits;
-	char	cXon;
-	char	cXoff;
-	u8	bUartMode;
-} __packed;
-
-/* Purge modes */
-#define MXU1_PURGE_OUTPUT			0x00
-#define MXU1_PURGE_INPUT			0x80
-
-/* Read/Write data */
-#define MXU1_RW_DATA_ADDR_SFR			0x10
-#define MXU1_RW_DATA_ADDR_IDATA			0x20
-#define MXU1_RW_DATA_ADDR_XDATA			0x30
-#define MXU1_RW_DATA_ADDR_CODE			0x40
-#define MXU1_RW_DATA_ADDR_GPIO			0x50
-#define MXU1_RW_DATA_ADDR_I2C			0x60
-#define MXU1_RW_DATA_ADDR_FLASH			0x70
-#define MXU1_RW_DATA_ADDR_DSP			0x80
-
-#define MXU1_RW_DATA_UNSPECIFIED		0x00
-#define MXU1_RW_DATA_BYTE			0x01
-#define MXU1_RW_DATA_WORD			0x02
-#define MXU1_RW_DATA_DOUBLE_WORD		0x04
-
-struct mxu1_write_data_bytes {
-	u8	bAddrType;
-	u8	bDataType;
-	u8	bDataCounter;
-	__be16	wBaseAddrHi;
-	__be16	wBaseAddrLo;
-	u8	bData[0];
-} __packed;
-
-/* Interrupt codes */
-#define MXU1_CODE_HARDWARE_ERROR		0xFF
-#define MXU1_CODE_DATA_ERROR			0x03
-#define MXU1_CODE_MODEM_STATUS			0x04
-
-static inline int mxu1_get_func_from_code(unsigned char code)
-{
-	return code & 0x0f;
-}
-
-/* Download firmware max packet size */
-#define MXU1_DOWNLOAD_MAX_PACKET_SIZE		64
-
-/* Firmware image header */
-struct mxu1_firmware_header {
-	__le16 wLength;
-	u8 bCheckSum;
-} __packed;
-
-#define MXU1_UART_BASE_ADDR	    0xFFA0
-#define MXU1_UART_OFFSET_MCR	    0x0004
-
-#define MXU1_BAUD_BASE              923077
-
-#define MXU1_TRANSFER_TIMEOUT	    2
-#define MXU1_DOWNLOAD_TIMEOUT       1000
-#define MXU1_DEFAULT_CLOSING_WAIT   4000 /* in .01 secs */
-
-struct mxu1_port {
-	u8 msr;
-	u8 mcr;
-	u8 uart_mode;
-	spinlock_t spinlock; /* Protects msr */
-	struct mutex mutex; /* Protects mcr */
-	bool send_break;
-};
-
-struct mxu1_device {
-	u16 mxd_model;
-};
-
-static const struct usb_device_id mxu1_idtable[] = {
-	{ USB_DEVICE(MXU1_VENDOR_ID, MXU1_1110_PRODUCT_ID) },
-	{ USB_DEVICE(MXU1_VENDOR_ID, MXU1_1130_PRODUCT_ID) },
-	{ USB_DEVICE(MXU1_VENDOR_ID, MXU1_1150_PRODUCT_ID) },
-	{ USB_DEVICE(MXU1_VENDOR_ID, MXU1_1151_PRODUCT_ID) },
-	{ USB_DEVICE(MXU1_VENDOR_ID, MXU1_1131_PRODUCT_ID) },
-	{ }
-};
-
-MODULE_DEVICE_TABLE(usb, mxu1_idtable);
-
-/* Write the given buffer out to the control pipe.  */
-static int mxu1_send_ctrl_data_urb(struct usb_serial *serial,
-				   u8 request,
-				   u16 value, u16 index,
-				   void *data, size_t size)
-{
-	int status;
-
-	status = usb_control_msg(serial->dev,
-				 usb_sndctrlpipe(serial->dev, 0),
-				 request,
-				 (USB_DIR_OUT | USB_TYPE_VENDOR |
-				  USB_RECIP_DEVICE), value, index,
-				 data, size,
-				 USB_CTRL_SET_TIMEOUT);
-	if (status < 0) {
-		dev_err(&serial->interface->dev,
-			"%s - usb_control_msg failed: %d\n",
-			__func__, status);
-		return status;
-	}
-
-	if (status != size) {
-		dev_err(&serial->interface->dev,
-			"%s - short write (%d / %zd)\n",
-			__func__, status, size);
-		return -EIO;
-	}
-
-	return 0;
-}
-
-/* Send a vendor request without any data */
-static int mxu1_send_ctrl_urb(struct usb_serial *serial,
-			      u8 request, u16 value, u16 index)
-{
-	return mxu1_send_ctrl_data_urb(serial, request, value, index,
-				       NULL, 0);
-}
-
-static int mxu1_download_firmware(struct usb_serial *serial,
-				  const struct firmware *fw_p)
-{
-	int status = 0;
-	int buffer_size;
-	int pos;
-	int len;
-	int done;
-	u8 cs = 0;
-	u8 *buffer;
-	struct usb_device *dev = serial->dev;
-	struct mxu1_firmware_header *header;
-	unsigned int pipe;
-
-	pipe = usb_sndbulkpipe(dev, serial->port[0]->bulk_out_endpointAddress);
-
-	buffer_size = fw_p->size + sizeof(*header);
-	buffer = kmalloc(buffer_size, GFP_KERNEL);
-	if (!buffer)
-		return -ENOMEM;
-
-	memcpy(buffer, fw_p->data, fw_p->size);
-	memset(buffer + fw_p->size, 0xff, buffer_size - fw_p->size);
-
-	for (pos = sizeof(*header); pos < buffer_size; pos++)
-		cs = (u8)(cs + buffer[pos]);
-
-	header = (struct mxu1_firmware_header *)buffer;
-	header->wLength = cpu_to_le16(buffer_size - sizeof(*header));
-	header->bCheckSum = cs;
-
-	dev_dbg(&dev->dev, "%s - downloading firmware\n", __func__);
-
-	for (pos = 0; pos < buffer_size; pos += done) {
-		len = min(buffer_size - pos, MXU1_DOWNLOAD_MAX_PACKET_SIZE);
-
-		status = usb_bulk_msg(dev, pipe, buffer + pos, len, &done,
-				MXU1_DOWNLOAD_TIMEOUT);
-		if (status)
-			break;
-	}
-
-	kfree(buffer);
-
-	if (status) {
-		dev_err(&dev->dev, "failed to download firmware: %d\n", status);
-		return status;
-	}
-
-	msleep_interruptible(100);
-	usb_reset_device(dev);
-
-	dev_dbg(&dev->dev, "%s - download successful\n", __func__);
-
-	return 0;
-}
-
-static int mxu1_port_probe(struct usb_serial_port *port)
-{
-	struct mxu1_port *mxport;
-	struct mxu1_device *mxdev;
-
-	if (!port->interrupt_in_urb) {
-		dev_err(&port->dev, "no interrupt urb\n");
-		return -ENODEV;
-	}
-
-	mxport = kzalloc(sizeof(struct mxu1_port), GFP_KERNEL);
-	if (!mxport)
-		return -ENOMEM;
-
-	spin_lock_init(&mxport->spinlock);
-	mutex_init(&mxport->mutex);
-
-	mxdev = usb_get_serial_data(port->serial);
-
-	switch (mxdev->mxd_model) {
-	case MXU1_1110_PRODUCT_ID:
-	case MXU1_1150_PRODUCT_ID:
-	case MXU1_1151_PRODUCT_ID:
-		mxport->uart_mode = MXU1_UART_232;
-		break;
-	case MXU1_1130_PRODUCT_ID:
-	case MXU1_1131_PRODUCT_ID:
-		mxport->uart_mode = MXU1_UART_485_RECEIVER_DISABLED;
-		break;
-	}
-
-	usb_set_serial_port_data(port, mxport);
-
-	port->port.closing_wait =
-			msecs_to_jiffies(MXU1_DEFAULT_CLOSING_WAIT * 10);
-	port->port.drain_delay = 1;
-
-	return 0;
-}
-
-static int mxu1_port_remove(struct usb_serial_port *port)
-{
-	struct mxu1_port *mxport;
-
-	mxport = usb_get_serial_port_data(port);
-	kfree(mxport);
-
-	return 0;
-}
-
-static int mxu1_startup(struct usb_serial *serial)
-{
-	struct mxu1_device *mxdev;
-	struct usb_device *dev = serial->dev;
-	struct usb_host_interface *cur_altsetting;
-	char fw_name[32];
-	const struct firmware *fw_p = NULL;
-	int err;
-
-	dev_dbg(&serial->interface->dev, "%s - product 0x%04X, num configurations %d, configuration value %d\n",
-		__func__, le16_to_cpu(dev->descriptor.idProduct),
-		dev->descriptor.bNumConfigurations,
-		dev->actconfig->desc.bConfigurationValue);
-
-	/* create device structure */
-	mxdev = kzalloc(sizeof(struct mxu1_device), GFP_KERNEL);
-	if (!mxdev)
-		return -ENOMEM;
-
-	usb_set_serial_data(serial, mxdev);
-
-	mxdev->mxd_model = le16_to_cpu(dev->descriptor.idProduct);
-
-	cur_altsetting = serial->interface->cur_altsetting;
-
-	/* if we have only 1 configuration, download firmware */
-	if (cur_altsetting->desc.bNumEndpoints == 1) {
-
-		snprintf(fw_name,
-			 sizeof(fw_name),
-			 "moxa/moxa-%04x.fw",
-			 mxdev->mxd_model);
-
-		err = request_firmware(&fw_p, fw_name, &serial->interface->dev);
-		if (err) {
-			dev_err(&serial->interface->dev, "failed to request firmware: %d\n",
-				err);
-			goto err_free_mxdev;
-		}
-
-		err = mxu1_download_firmware(serial, fw_p);
-		if (err)
-			goto err_release_firmware;
-
-		/* device is being reset */
-		err = -ENODEV;
-		goto err_release_firmware;
-	}
-
-	return 0;
-
-err_release_firmware:
-	release_firmware(fw_p);
-err_free_mxdev:
-	kfree(mxdev);
-
-	return err;
-}
-
-static void mxu1_release(struct usb_serial *serial)
-{
-	struct mxu1_device *mxdev;
-
-	mxdev = usb_get_serial_data(serial);
-	kfree(mxdev);
-}
-
-static int mxu1_write_byte(struct usb_serial_port *port, u32 addr,
-			   u8 mask, u8 byte)
-{
-	int status;
-	size_t size;
-	struct mxu1_write_data_bytes *data;
-
-	dev_dbg(&port->dev, "%s - addr 0x%08X, mask 0x%02X, byte 0x%02X\n",
-		__func__, addr, mask, byte);
-
-	size = sizeof(struct mxu1_write_data_bytes) + 2;
-	data = kzalloc(size, GFP_KERNEL);
-	if (!data)
-		return -ENOMEM;
-
-	data->bAddrType = MXU1_RW_DATA_ADDR_XDATA;
-	data->bDataType = MXU1_RW_DATA_BYTE;
-	data->bDataCounter = 1;
-	data->wBaseAddrHi = cpu_to_be16(addr >> 16);
-	data->wBaseAddrLo = cpu_to_be16(addr);
-	data->bData[0] = mask;
-	data->bData[1] = byte;
-
-	status = mxu1_send_ctrl_data_urb(port->serial, MXU1_WRITE_DATA, 0,
-					 MXU1_RAM_PORT, data, size);
-	if (status < 0)
-		dev_err(&port->dev, "%s - failed: %d\n", __func__, status);
-
-	kfree(data);
-
-	return status;
-}
-
-static int mxu1_set_mcr(struct usb_serial_port *port, unsigned int mcr)
-{
-	int status;
-
-	status = mxu1_write_byte(port,
-				 MXU1_UART_BASE_ADDR + MXU1_UART_OFFSET_MCR,
-				 MXU1_MCR_RTS | MXU1_MCR_DTR | MXU1_MCR_LOOP,
-				 mcr);
-	return status;
-}
-
-static void mxu1_set_termios(struct tty_struct *tty,
-			     struct usb_serial_port *port,
-			     struct ktermios *old_termios)
-{
-	struct mxu1_port *mxport = usb_get_serial_port_data(port);
-	struct mxu1_uart_config *config;
-	tcflag_t cflag, iflag;
-	speed_t baud;
-	int status;
-	unsigned int mcr;
-
-	cflag = tty->termios.c_cflag;
-	iflag = tty->termios.c_iflag;
-
-	if (old_termios &&
-	    !tty_termios_hw_change(&tty->termios, old_termios) &&
-	    tty->termios.c_iflag == old_termios->c_iflag) {
-		dev_dbg(&port->dev, "%s - nothing to change\n", __func__);
-		return;
-	}
-
-	dev_dbg(&port->dev,
-		"%s - cflag 0x%08x, iflag 0x%08x\n", __func__, cflag, iflag);
-
-	if (old_termios) {
-		dev_dbg(&port->dev, "%s - old cflag 0x%08x, old iflag 0x%08x\n",
-			__func__,
-			old_termios->c_cflag,
-			old_termios->c_iflag);
-	}
-
-	config = kzalloc(sizeof(*config), GFP_KERNEL);
-	if (!config)
-		return;
-
-	/* these flags must be set */
-	config->wFlags |= MXU1_UART_ENABLE_MS_INTS;
-	config->wFlags |= MXU1_UART_ENABLE_AUTO_START_DMA;
-	if (mxport->send_break)
-		config->wFlags |= MXU1_UART_SEND_BREAK_SIGNAL;
-	config->bUartMode = mxport->uart_mode;
-
-	switch (C_CSIZE(tty)) {
-	case CS5:
-		config->bDataBits = MXU1_UART_5_DATA_BITS;
-		break;
-	case CS6:
-		config->bDataBits = MXU1_UART_6_DATA_BITS;
-		break;
-	case CS7:
-		config->bDataBits = MXU1_UART_7_DATA_BITS;
-		break;
-	default:
-	case CS8:
-		config->bDataBits = MXU1_UART_8_DATA_BITS;
-		break;
-	}
-
-	if (C_PARENB(tty)) {
-		config->wFlags |= MXU1_UART_ENABLE_PARITY_CHECKING;
-		if (C_CMSPAR(tty)) {
-			if (C_PARODD(tty))
-				config->bParity = MXU1_UART_MARK_PARITY;
-			else
-				config->bParity = MXU1_UART_SPACE_PARITY;
-		} else {
-			if (C_PARODD(tty))
-				config->bParity = MXU1_UART_ODD_PARITY;
-			else
-				config->bParity = MXU1_UART_EVEN_PARITY;
-		}
-	} else {
-		config->bParity = MXU1_UART_NO_PARITY;
-	}
-
-	if (C_CSTOPB(tty))
-		config->bStopBits = MXU1_UART_2_STOP_BITS;
-	else
-		config->bStopBits = MXU1_UART_1_STOP_BITS;
-
-	if (C_CRTSCTS(tty)) {
-		/* RTS flow control must be off to drop RTS for baud rate B0 */
-		if (C_BAUD(tty) != B0)
-			config->wFlags |= MXU1_UART_ENABLE_RTS_IN;
-		config->wFlags |= MXU1_UART_ENABLE_CTS_OUT;
-	}
-
-	if (I_IXOFF(tty) || I_IXON(tty)) {
-		config->cXon  = START_CHAR(tty);
-		config->cXoff = STOP_CHAR(tty);
-
-		if (I_IXOFF(tty))
-			config->wFlags |= MXU1_UART_ENABLE_X_IN;
-
-		if (I_IXON(tty))
-			config->wFlags |= MXU1_UART_ENABLE_X_OUT;
-	}
-
-	baud = tty_get_baud_rate(tty);
-	if (!baud)
-		baud = 9600;
-	config->wBaudRate = MXU1_BAUD_BASE / baud;
-
-	dev_dbg(&port->dev, "%s - BaudRate=%d, wBaudRate=%d, wFlags=0x%04X, bDataBits=%d, bParity=%d, bStopBits=%d, cXon=%d, cXoff=%d, bUartMode=%d\n",
-		__func__, baud, config->wBaudRate, config->wFlags,
-		config->bDataBits, config->bParity, config->bStopBits,
-		config->cXon, config->cXoff, config->bUartMode);
-
-	cpu_to_be16s(&config->wBaudRate);
-	cpu_to_be16s(&config->wFlags);
-
-	status = mxu1_send_ctrl_data_urb(port->serial, MXU1_SET_CONFIG, 0,
-					 MXU1_UART1_PORT, config,
-					 sizeof(*config));
-	if (status)
-		dev_err(&port->dev, "cannot set config: %d\n", status);
-
-	mutex_lock(&mxport->mutex);
-	mcr = mxport->mcr;
-
-	if (C_BAUD(tty) == B0)
-		mcr &= ~(MXU1_MCR_DTR | MXU1_MCR_RTS);
-	else if (old_termios && (old_termios->c_cflag & CBAUD) == B0)
-		mcr |= MXU1_MCR_DTR | MXU1_MCR_RTS;
-
-	status = mxu1_set_mcr(port, mcr);
-	if (status)
-		dev_err(&port->dev, "cannot set modem control: %d\n", status);
-	else
-		mxport->mcr = mcr;
-
-	mutex_unlock(&mxport->mutex);
-
-	kfree(config);
-}
-
-static int mxu1_get_serial_info(struct usb_serial_port *port,
-				struct serial_struct __user *ret_arg)
-{
-	struct serial_struct ret_serial;
-	unsigned cwait;
-
-	if (!ret_arg)
-		return -EFAULT;
-
-	cwait = port->port.closing_wait;
-	if (cwait != ASYNC_CLOSING_WAIT_NONE)
-		cwait = jiffies_to_msecs(cwait) / 10;
-
-	memset(&ret_serial, 0, sizeof(ret_serial));
-
-	ret_serial.type = PORT_16550A;
-	ret_serial.line = port->minor;
-	ret_serial.port = 0;
-	ret_serial.xmit_fifo_size = port->bulk_out_size;
-	ret_serial.baud_base = MXU1_BAUD_BASE;
-	ret_serial.close_delay = 5*HZ;
-	ret_serial.closing_wait = cwait;
-
-	if (copy_to_user(ret_arg, &ret_serial, sizeof(*ret_arg)))
-		return -EFAULT;
-
-	return 0;
-}
-
-
-static int mxu1_set_serial_info(struct usb_serial_port *port,
-				struct serial_struct __user *new_arg)
-{
-	struct serial_struct new_serial;
-	unsigned cwait;
-
-	if (copy_from_user(&new_serial, new_arg, sizeof(new_serial)))
-		return -EFAULT;
-
-	cwait = new_serial.closing_wait;
-	if (cwait != ASYNC_CLOSING_WAIT_NONE)
-		cwait = msecs_to_jiffies(10 * new_serial.closing_wait);
-
-	port->port.closing_wait = cwait;
-
-	return 0;
-}
-
-static int mxu1_ioctl(struct tty_struct *tty,
-		      unsigned int cmd, unsigned long arg)
-{
-	struct usb_serial_port *port = tty->driver_data;
-
-	switch (cmd) {
-	case TIOCGSERIAL:
-		return mxu1_get_serial_info(port,
-					    (struct serial_struct __user *)arg);
-	case TIOCSSERIAL:
-		return mxu1_set_serial_info(port,
-					    (struct serial_struct __user *)arg);
-	}
-
-	return -ENOIOCTLCMD;
-}
-
-static int mxu1_tiocmget(struct tty_struct *tty)
-{
-	struct usb_serial_port *port = tty->driver_data;
-	struct mxu1_port *mxport = usb_get_serial_port_data(port);
-	unsigned int result;
-	unsigned int msr;
-	unsigned int mcr;
-	unsigned long flags;
-
-	mutex_lock(&mxport->mutex);
-	spin_lock_irqsave(&mxport->spinlock, flags);
-
-	msr = mxport->msr;
-	mcr = mxport->mcr;
-
-	spin_unlock_irqrestore(&mxport->spinlock, flags);
-	mutex_unlock(&mxport->mutex);
-
-	result = ((mcr & MXU1_MCR_DTR)	? TIOCM_DTR	: 0) |
-		 ((mcr & MXU1_MCR_RTS)	? TIOCM_RTS	: 0) |
-		 ((mcr & MXU1_MCR_LOOP) ? TIOCM_LOOP	: 0) |
-		 ((msr & MXU1_MSR_CTS)	? TIOCM_CTS	: 0) |
-		 ((msr & MXU1_MSR_CD)	? TIOCM_CAR	: 0) |
-		 ((msr & MXU1_MSR_RI)	? TIOCM_RI	: 0) |
-		 ((msr & MXU1_MSR_DSR)	? TIOCM_DSR	: 0);
-
-	dev_dbg(&port->dev, "%s - 0x%04X\n", __func__, result);
-
-	return result;
-}
-
-static int mxu1_tiocmset(struct tty_struct *tty,
-			 unsigned int set, unsigned int clear)
-{
-	struct usb_serial_port *port = tty->driver_data;
-	struct mxu1_port *mxport = usb_get_serial_port_data(port);
-	int err;
-	unsigned int mcr;
-
-	mutex_lock(&mxport->mutex);
-	mcr = mxport->mcr;
-
-	if (set & TIOCM_RTS)
-		mcr |= MXU1_MCR_RTS;
-	if (set & TIOCM_DTR)
-		mcr |= MXU1_MCR_DTR;
-	if (set & TIOCM_LOOP)
-		mcr |= MXU1_MCR_LOOP;
-
-	if (clear & TIOCM_RTS)
-		mcr &= ~MXU1_MCR_RTS;
-	if (clear & TIOCM_DTR)
-		mcr &= ~MXU1_MCR_DTR;
-	if (clear & TIOCM_LOOP)
-		mcr &= ~MXU1_MCR_LOOP;
-
-	err = mxu1_set_mcr(port, mcr);
-	if (!err)
-		mxport->mcr = mcr;
-
-	mutex_unlock(&mxport->mutex);
-
-	return err;
-}
-
-static void mxu1_break(struct tty_struct *tty, int break_state)
-{
-	struct usb_serial_port *port = tty->driver_data;
-	struct mxu1_port *mxport = usb_get_serial_port_data(port);
-
-	if (break_state == -1)
-		mxport->send_break = true;
-	else
-		mxport->send_break = false;
-
-	mxu1_set_termios(tty, port, NULL);
-}
-
-static int mxu1_open(struct tty_struct *tty, struct usb_serial_port *port)
-{
-	struct mxu1_port *mxport = usb_get_serial_port_data(port);
-	struct usb_serial *serial = port->serial;
-	int status;
-	u16 open_settings;
-
-	open_settings = (MXU1_PIPE_MODE_CONTINUOUS |
-			 MXU1_PIPE_TIMEOUT_ENABLE |
-			 (MXU1_TRANSFER_TIMEOUT << 2));
-
-	mxport->msr = 0;
-
-	status = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL);
-	if (status) {
-		dev_err(&port->dev, "failed to submit interrupt urb: %d\n",
-			status);
-		return status;
-	}
-
-	if (tty)
-		mxu1_set_termios(tty, port, NULL);
-
-	status = mxu1_send_ctrl_urb(serial, MXU1_OPEN_PORT,
-				    open_settings, MXU1_UART1_PORT);
-	if (status) {
-		dev_err(&port->dev, "cannot send open command: %d\n", status);
-		goto unlink_int_urb;
-	}
-
-	status = mxu1_send_ctrl_urb(serial, MXU1_START_PORT,
-				    0, MXU1_UART1_PORT);
-	if (status) {
-		dev_err(&port->dev, "cannot send start command: %d\n", status);
-		goto unlink_int_urb;
-	}
-
-	status = mxu1_send_ctrl_urb(serial, MXU1_PURGE_PORT,
-				    MXU1_PURGE_INPUT, MXU1_UART1_PORT);
-	if (status) {
-		dev_err(&port->dev, "cannot clear input buffers: %d\n",
-			status);
-
-		goto unlink_int_urb;
-	}
-
-	status = mxu1_send_ctrl_urb(serial, MXU1_PURGE_PORT,
-				    MXU1_PURGE_OUTPUT, MXU1_UART1_PORT);
-	if (status) {
-		dev_err(&port->dev, "cannot clear output buffers: %d\n",
-			status);
-
-		goto unlink_int_urb;
-	}
-
-	/*
-	 * reset the data toggle on the bulk endpoints to work around bug in
-	 * host controllers where things get out of sync some times
-	 */
-	usb_clear_halt(serial->dev, port->write_urb->pipe);
-	usb_clear_halt(serial->dev, port->read_urb->pipe);
-
-	if (tty)
-		mxu1_set_termios(tty, port, NULL);
-
-	status = mxu1_send_ctrl_urb(serial, MXU1_OPEN_PORT,
-				    open_settings, MXU1_UART1_PORT);
-	if (status) {
-		dev_err(&port->dev, "cannot send open command: %d\n", status);
-		goto unlink_int_urb;
-	}
-
-	status = mxu1_send_ctrl_urb(serial, MXU1_START_PORT,
-				    0, MXU1_UART1_PORT);
-	if (status) {
-		dev_err(&port->dev, "cannot send start command: %d\n", status);
-		goto unlink_int_urb;
-	}
-
-	status = usb_serial_generic_open(tty, port);
-	if (status)
-		goto unlink_int_urb;
-
-	return 0;
-
-unlink_int_urb:
-	usb_kill_urb(port->interrupt_in_urb);
-
-	return status;
-}
-
-static void mxu1_close(struct usb_serial_port *port)
-{
-	int status;
-
-	usb_serial_generic_close(port);
-	usb_kill_urb(port->interrupt_in_urb);
-
-	status = mxu1_send_ctrl_urb(port->serial, MXU1_CLOSE_PORT,
-				    0, MXU1_UART1_PORT);
-	if (status) {
-		dev_err(&port->dev, "failed to send close port command: %d\n",
-			status);
-	}
-}
-
-static void mxu1_handle_new_msr(struct usb_serial_port *port, u8 msr)
-{
-	struct mxu1_port *mxport = usb_get_serial_port_data(port);
-	struct async_icount *icount;
-	unsigned long flags;
-
-	dev_dbg(&port->dev, "%s - msr 0x%02X\n", __func__, msr);
-
-	spin_lock_irqsave(&mxport->spinlock, flags);
-	mxport->msr = msr & MXU1_MSR_MASK;
-	spin_unlock_irqrestore(&mxport->spinlock, flags);
-
-	if (msr & MXU1_MSR_DELTA_MASK) {
-		icount = &port->icount;
-		if (msr & MXU1_MSR_DELTA_CTS)
-			icount->cts++;
-		if (msr & MXU1_MSR_DELTA_DSR)
-			icount->dsr++;
-		if (msr & MXU1_MSR_DELTA_CD)
-			icount->dcd++;
-		if (msr & MXU1_MSR_DELTA_RI)
-			icount->rng++;
-
-		wake_up_interruptible(&port->port.delta_msr_wait);
-	}
-}
-
-static void mxu1_interrupt_callback(struct urb *urb)
-{
-	struct usb_serial_port *port = urb->context;
-	unsigned char *data = urb->transfer_buffer;
-	int length = urb->actual_length;
-	int function;
-	int status;
-	u8 msr;
-
-	switch (urb->status) {
-	case 0:
-		break;
-	case -ECONNRESET:
-	case -ENOENT:
-	case -ESHUTDOWN:
-		dev_dbg(&port->dev, "%s - urb shutting down: %d\n",
-			__func__, urb->status);
-		return;
-	default:
-		dev_dbg(&port->dev, "%s - nonzero urb status: %d\n",
-			__func__, urb->status);
-		goto exit;
-	}
-
-	if (length != 2) {
-		dev_dbg(&port->dev, "%s - bad packet size: %d\n",
-			__func__, length);
-		goto exit;
-	}
-
-	if (data[0] == MXU1_CODE_HARDWARE_ERROR) {
-		dev_err(&port->dev, "hardware error: %d\n", data[1]);
-		goto exit;
-	}
-
-	function = mxu1_get_func_from_code(data[0]);
-
-	dev_dbg(&port->dev, "%s - function %d, data 0x%02X\n",
-		 __func__, function, data[1]);
-
-	switch (function) {
-	case MXU1_CODE_DATA_ERROR:
-		dev_dbg(&port->dev, "%s - DATA ERROR, data 0x%02X\n",
-			 __func__, data[1]);
-		break;
-
-	case MXU1_CODE_MODEM_STATUS:
-		msr = data[1];
-		mxu1_handle_new_msr(port, msr);
-		break;
-
-	default:
-		dev_err(&port->dev, "unknown interrupt code: 0x%02X\n",
-			data[1]);
-		break;
-	}
-
-exit:
-	status = usb_submit_urb(urb, GFP_ATOMIC);
-	if (status) {
-		dev_err(&port->dev, "resubmit interrupt urb failed: %d\n",
-			status);
-	}
-}
-
-static struct usb_serial_driver mxu11x0_device = {
-	.driver = {
-		.owner		= THIS_MODULE,
-		.name		= "mxu11x0",
-	},
-	.description		= "MOXA UPort 11x0",
-	.id_table		= mxu1_idtable,
-	.num_ports		= 1,
-	.port_probe             = mxu1_port_probe,
-	.port_remove            = mxu1_port_remove,
-	.attach			= mxu1_startup,
-	.release                = mxu1_release,
-	.open			= mxu1_open,
-	.close			= mxu1_close,
-	.ioctl			= mxu1_ioctl,
-	.set_termios		= mxu1_set_termios,
-	.tiocmget		= mxu1_tiocmget,
-	.tiocmset		= mxu1_tiocmset,
-	.tiocmiwait		= usb_serial_generic_tiocmiwait,
-	.get_icount		= usb_serial_generic_get_icount,
-	.break_ctl		= mxu1_break,
-	.read_int_callback	= mxu1_interrupt_callback,
-};
-
-static struct usb_serial_driver *const serial_drivers[] = {
-	&mxu11x0_device, NULL
-};
-
-module_usb_serial_driver(serial_drivers, mxu1_idtable);
-
-MODULE_AUTHOR("Mathieu Othacehe <m.othacehe@gmail.com>");
-MODULE_DESCRIPTION("MOXA UPort 11x0 USB to Serial Hub Driver");
-MODULE_LICENSE("GPL");
-MODULE_FIRMWARE("moxa/moxa-1110.fw");
-MODULE_FIRMWARE("moxa/moxa-1130.fw");
-MODULE_FIRMWARE("moxa/moxa-1131.fw");
-MODULE_FIRMWARE("moxa/moxa-1150.fw");
-MODULE_FIRMWARE("moxa/moxa-1151.fw");
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index db86e512e0fc..348e19834b83 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -270,6 +270,7 @@ static void option_instat_callback(struct urb *urb);
 #define TELIT_PRODUCT_UE910_V2			0x1012
 #define TELIT_PRODUCT_LE922_USBCFG0		0x1042
 #define TELIT_PRODUCT_LE922_USBCFG3		0x1043
+#define TELIT_PRODUCT_LE922_USBCFG5		0x1045
 #define TELIT_PRODUCT_LE920			0x1200
 #define TELIT_PRODUCT_LE910			0x1201
 
@@ -315,6 +316,7 @@ static void option_instat_callback(struct urb *urb);
 #define TOSHIBA_PRODUCT_G450			0x0d45
 
 #define ALINK_VENDOR_ID				0x1e0e
+#define SIMCOM_PRODUCT_SIM7100E			0x9001 /* Yes, ALINK_VENDOR_ID */
 #define ALINK_PRODUCT_PH300			0x9100
 #define ALINK_PRODUCT_3GU			0x9200
 
@@ -607,6 +609,10 @@ static const struct option_blacklist_info zte_1255_blacklist = {
 	.reserved = BIT(3) | BIT(4),
 };
 
+static const struct option_blacklist_info simcom_sim7100e_blacklist = {
+	.reserved = BIT(5) | BIT(6),
+};
+
 static const struct option_blacklist_info telit_le910_blacklist = {
 	.sendsetup = BIT(0),
 	.reserved = BIT(1) | BIT(2),
@@ -1122,9 +1128,13 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC650) },
 	{ USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC680) },
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6000)}, /* ZTE AC8700 */
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUALCOMM_VENDOR_ID, 0x6001, 0xff, 0xff, 0xff), /* 4G LTE usb-modem U901 */
+	  .driver_info = (kernel_ulong_t)&net_intf3_blacklist },
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */
+	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9003), /* Quectel UC20 */
+	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003),
@@ -1176,6 +1186,8 @@ static const struct usb_device_id option_ids[] = {
 		.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG3),
 		.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG5, 0xff),
+		.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910),
 		.driver_info = (kernel_ulong_t)&telit_le910_blacklist },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920),
@@ -1645,6 +1657,8 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(ALINK_VENDOR_ID, 0x9000) },
 	{ USB_DEVICE(ALINK_VENDOR_ID, ALINK_PRODUCT_PH300) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ALINK_VENDOR_ID, ALINK_PRODUCT_3GU, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE(ALINK_VENDOR_ID, SIMCOM_PRODUCT_SIM7100E),
+	  .driver_info = (kernel_ulong_t)&simcom_sim7100e_blacklist },
 	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X060S_X200),
 	  .driver_info = (kernel_ulong_t)&alcatel_x200_blacklist
 	},
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index 9919d2a9faf2..1bc6089b9008 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -157,14 +157,17 @@ static const struct usb_device_id id_table[] = {
 	{DEVICE_SWI(0x1199, 0x9056)},	/* Sierra Wireless Modem */
 	{DEVICE_SWI(0x1199, 0x9060)},	/* Sierra Wireless Modem */
 	{DEVICE_SWI(0x1199, 0x9061)},	/* Sierra Wireless Modem */
-	{DEVICE_SWI(0x1199, 0x9070)},	/* Sierra Wireless MC74xx/EM74xx */
-	{DEVICE_SWI(0x1199, 0x9071)},	/* Sierra Wireless MC74xx/EM74xx */
+	{DEVICE_SWI(0x1199, 0x9070)},	/* Sierra Wireless MC74xx */
+	{DEVICE_SWI(0x1199, 0x9071)},	/* Sierra Wireless MC74xx */
+	{DEVICE_SWI(0x1199, 0x9078)},	/* Sierra Wireless EM74xx */
+	{DEVICE_SWI(0x1199, 0x9079)},	/* Sierra Wireless EM74xx */
 	{DEVICE_SWI(0x413c, 0x81a2)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */
 	{DEVICE_SWI(0x413c, 0x81a3)},	/* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */
 	{DEVICE_SWI(0x413c, 0x81a4)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */
 	{DEVICE_SWI(0x413c, 0x81a8)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */
 	{DEVICE_SWI(0x413c, 0x81a9)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
 	{DEVICE_SWI(0x413c, 0x81b1)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */
+	{DEVICE_SWI(0x413c, 0x81b3)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
 
 	/* Huawei devices */
 	{DEVICE_HWI(0x03f0, 0x581d)},	/* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */
diff --git a/drivers/usb/wusbcore/crypto.c b/drivers/usb/wusbcore/crypto.c
index 50ce80d604f3..8ed8e34c3492 100644
--- a/drivers/usb/wusbcore/crypto.c
+++ b/drivers/usb/wusbcore/crypto.c
@@ -45,6 +45,7 @@
  *             funneled through AES are...16 bytes in size!
  */
 
+#include <crypto/skcipher.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
 #include <linux/err.h>
@@ -195,21 +196,22 @@ static void bytewise_xor(void *_bo, const void *_bi1, const void *_bi2,
  * NOTE: blen is not aligned to a block size, we'll pad zeros, that's
  *       what sg[4] is for. Maybe there is a smarter way to do this.
  */
-static int wusb_ccm_mac(struct crypto_blkcipher *tfm_cbc,
+static int wusb_ccm_mac(struct crypto_skcipher *tfm_cbc,
 			struct crypto_cipher *tfm_aes, void *mic,
 			const struct aes_ccm_nonce *n,
 			const struct aes_ccm_label *a, const void *b,
 			size_t blen)
 {
 	int result = 0;
-	struct blkcipher_desc desc;
+	SKCIPHER_REQUEST_ON_STACK(req, tfm_cbc);
 	struct aes_ccm_b0 b0;
 	struct aes_ccm_b1 b1;
 	struct aes_ccm_a ax;
 	struct scatterlist sg[4], sg_dst;
-	void *iv, *dst_buf;
-	size_t ivsize, dst_size;
+	void *dst_buf;
+	size_t dst_size;
 	const u8 bzero[16] = { 0 };
+	u8 iv[crypto_skcipher_ivsize(tfm_cbc)];
 	size_t zero_padding;
 
 	/*
@@ -232,9 +234,7 @@ static int wusb_ccm_mac(struct crypto_blkcipher *tfm_cbc,
 		goto error_dst_buf;
 	}
 
-	iv = crypto_blkcipher_crt(tfm_cbc)->iv;
-	ivsize = crypto_blkcipher_ivsize(tfm_cbc);
-	memset(iv, 0, ivsize);
+	memset(iv, 0, sizeof(iv));
 
 	/* Setup B0 */
 	b0.flags = 0x59;	/* Format B0 */
@@ -259,9 +259,11 @@ static int wusb_ccm_mac(struct crypto_blkcipher *tfm_cbc,
 	sg_set_buf(&sg[3], bzero, zero_padding);
 	sg_init_one(&sg_dst, dst_buf, dst_size);
 
-	desc.tfm = tfm_cbc;
-	desc.flags = 0;
-	result = crypto_blkcipher_encrypt(&desc, &sg_dst, sg, dst_size);
+	skcipher_request_set_tfm(req, tfm_cbc);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, sg, &sg_dst, dst_size, iv);
+	result = crypto_skcipher_encrypt(req);
+	skcipher_request_zero(req);
 	if (result < 0) {
 		printk(KERN_ERR "E: can't compute CBC-MAC tag (MIC): %d\n",
 		       result);
@@ -301,18 +303,18 @@ ssize_t wusb_prf(void *out, size_t out_size,
 {
 	ssize_t result, bytes = 0, bitr;
 	struct aes_ccm_nonce n = *_n;
-	struct crypto_blkcipher *tfm_cbc;
+	struct crypto_skcipher *tfm_cbc;
 	struct crypto_cipher *tfm_aes;
 	u64 sfn = 0;
 	__le64 sfn_le;
 
-	tfm_cbc = crypto_alloc_blkcipher("cbc(aes)", 0, CRYPTO_ALG_ASYNC);
+	tfm_cbc = crypto_alloc_skcipher("cbc(aes)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm_cbc)) {
 		result = PTR_ERR(tfm_cbc);
 		printk(KERN_ERR "E: can't load CBC(AES): %d\n", (int)result);
 		goto error_alloc_cbc;
 	}
-	result = crypto_blkcipher_setkey(tfm_cbc, key, 16);
+	result = crypto_skcipher_setkey(tfm_cbc, key, 16);
 	if (result < 0) {
 		printk(KERN_ERR "E: can't set CBC key: %d\n", (int)result);
 		goto error_setkey_cbc;
@@ -345,7 +347,7 @@ error_setkey_aes:
 	crypto_free_cipher(tfm_aes);
 error_alloc_aes:
 error_setkey_cbc:
-	crypto_free_blkcipher(tfm_cbc);
+	crypto_free_skcipher(tfm_cbc);
 error_alloc_cbc:
 	return result;
 }
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 2760a7ba3f30..8c80a48e3233 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -446,7 +446,8 @@ static long vfio_pci_ioctl(void *device_data,
 		info.num_regions = VFIO_PCI_NUM_REGIONS;
 		info.num_irqs = VFIO_PCI_NUM_IRQS;
 
-		return copy_to_user((void __user *)arg, &info, minsz);
+		return copy_to_user((void __user *)arg, &info, minsz) ?
+			-EFAULT : 0;
 
 	} else if (cmd == VFIO_DEVICE_GET_REGION_INFO) {
 		struct pci_dev *pdev = vdev->pdev;
@@ -520,7 +521,8 @@ static long vfio_pci_ioctl(void *device_data,
 			return -EINVAL;
 		}
 
-		return copy_to_user((void __user *)arg, &info, minsz);
+		return copy_to_user((void __user *)arg, &info, minsz) ?
+			-EFAULT : 0;
 
 	} else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) {
 		struct vfio_irq_info info;
@@ -555,7 +557,8 @@ static long vfio_pci_ioctl(void *device_data,
 		else
 			info.flags |= VFIO_IRQ_INFO_NORESIZE;
 
-		return copy_to_user((void __user *)arg, &info, minsz);
+		return copy_to_user((void __user *)arg, &info, minsz) ?
+			-EFAULT : 0;
 
 	} else if (cmd == VFIO_DEVICE_SET_IRQS) {
 		struct vfio_irq_set hdr;
diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c
index 418cdd9ba3f4..e65b142d3422 100644
--- a/drivers/vfio/platform/vfio_platform_common.c
+++ b/drivers/vfio/platform/vfio_platform_common.c
@@ -219,7 +219,8 @@ static long vfio_platform_ioctl(void *device_data,
 		info.num_regions = vdev->num_regions;
 		info.num_irqs = vdev->num_irqs;
 
-		return copy_to_user((void __user *)arg, &info, minsz);
+		return copy_to_user((void __user *)arg, &info, minsz) ?
+			-EFAULT : 0;
 
 	} else if (cmd == VFIO_DEVICE_GET_REGION_INFO) {
 		struct vfio_region_info info;
@@ -240,7 +241,8 @@ static long vfio_platform_ioctl(void *device_data,
 		info.size = vdev->regions[info.index].size;
 		info.flags = vdev->regions[info.index].flags;
 
-		return copy_to_user((void __user *)arg, &info, minsz);
+		return copy_to_user((void __user *)arg, &info, minsz) ?
+			-EFAULT : 0;
 
 	} else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) {
 		struct vfio_irq_info info;
@@ -259,7 +261,8 @@ static long vfio_platform_ioctl(void *device_data,
 		info.flags = vdev->irqs[info.index].flags;
 		info.count = vdev->irqs[info.index].count;
 
-		return copy_to_user((void __user *)arg, &info, minsz);
+		return copy_to_user((void __user *)arg, &info, minsz) ?
+			-EFAULT : 0;
 
 	} else if (cmd == VFIO_DEVICE_SET_IRQS) {
 		struct vfio_irq_set hdr;
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 6f1ea3dddbad..75b24e93cedb 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -999,7 +999,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 
 		info.iova_pgsizes = vfio_pgsize_bitmap(iommu);
 
-		return copy_to_user((void __user *)arg, &info, minsz);
+		return copy_to_user((void __user *)arg, &info, minsz) ?
+			-EFAULT : 0;
 
 	} else if (cmd == VFIO_IOMMU_MAP_DMA) {
 		struct vfio_iommu_type1_dma_map map;
@@ -1032,7 +1033,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 		if (ret)
 			return ret;
 
-		return copy_to_user((void __user *)arg, &unmap, minsz);
+		return copy_to_user((void __user *)arg, &unmap, minsz) ?
+			-EFAULT : 0;
 	}
 
 	return -ENOTTY;
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index ad2146a9ab2d..236553e81027 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1156,6 +1156,8 @@ int vhost_init_used(struct vhost_virtqueue *vq)
 {
 	__virtio16 last_used_idx;
 	int r;
+	bool is_le = vq->is_le;
+
 	if (!vq->private_data) {
 		vq->is_le = virtio_legacy_is_little_endian();
 		return 0;
@@ -1165,15 +1167,20 @@ int vhost_init_used(struct vhost_virtqueue *vq)
 
 	r = vhost_update_used_flags(vq);
 	if (r)
-		return r;
+		goto err;
 	vq->signalled_used_valid = false;
-	if (!access_ok(VERIFY_READ, &vq->used->idx, sizeof vq->used->idx))
-		return -EFAULT;
+	if (!access_ok(VERIFY_READ, &vq->used->idx, sizeof vq->used->idx)) {
+		r = -EFAULT;
+		goto err;
+	}
 	r = __get_user(last_used_idx, &vq->used->idx);
 	if (r)
-		return r;
+		goto err;
 	vq->last_used_idx = vhost16_to_cpu(vq, last_used_idx);
 	return 0;
+err:
+	vq->is_le = is_le;
+	return r;
 }
 EXPORT_SYMBOL_GPL(vhost_init_used);
 
diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c
index 92f394927f24..6e92917ba77a 100644
--- a/drivers/video/console/fbcon.c
+++ b/drivers/video/console/fbcon.c
@@ -709,6 +709,7 @@ static int con2fb_acquire_newinfo(struct vc_data *vc, struct fb_info *info,
 	}
 
 	if (!err) {
+		ops->cur_blink_jiffies = HZ / 5;
 		info->fbcon_par = ops;
 
 		if (vc)
@@ -956,6 +957,7 @@ static const char *fbcon_startup(void)
 	ops->currcon = -1;
 	ops->graphics = 1;
 	ops->cur_rotate = -1;
+	ops->cur_blink_jiffies = HZ / 5;
 	info->fbcon_par = ops;
 	p->con_rotate = initial_rotation;
 	set_blitting_type(vc, info);
diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig
index 8ea45a5cd806..983280e8d93f 100644
--- a/drivers/video/fbdev/Kconfig
+++ b/drivers/video/fbdev/Kconfig
@@ -1808,8 +1808,8 @@ config FB_HIT
 	  frame buffer card.
 
 config FB_PMAG_AA
-	bool "PMAG-AA TURBOchannel framebuffer support"
-	depends on (FB = y) && TC
+	tristate "PMAG-AA TURBOchannel framebuffer support"
+	depends on FB && TC
  	select FB_CFB_FILLRECT
  	select FB_CFB_COPYAREA
  	select FB_CFB_IMAGEBLIT
@@ -1985,7 +1985,7 @@ config FB_W100
 
 config FB_SH_MOBILE_LCDC
 	tristate "SuperH Mobile LCDC framebuffer support"
-	depends on FB && (SUPERH || ARCH_SHMOBILE) && HAVE_CLK
+	depends on FB && (SUPERH || ARCH_RENESAS) && HAVE_CLK
 	depends on FB_SH_MOBILE_MERAM || !FB_SH_MOBILE_MERAM
 	select FB_SYS_FILLRECT
 	select FB_SYS_COPYAREA
@@ -2246,7 +2246,6 @@ config XEN_FBDEV_FRONTEND
 	select FB_SYS_IMAGEBLIT
 	select FB_SYS_FOPS
 	select FB_DEFERRED_IO
-	select INPUT_XEN_KBDDEV_FRONTEND if INPUT_MISC
 	select XEN_XENBUS_FRONTEND
 	default y
 	help
diff --git a/drivers/video/fbdev/acornfb.c b/drivers/video/fbdev/acornfb.c
index a305caea58ee..fb75b7e5a19a 100644
--- a/drivers/video/fbdev/acornfb.c
+++ b/drivers/video/fbdev/acornfb.c
@@ -1040,8 +1040,8 @@ static int acornfb_probe(struct platform_device *dev)
 		 * for the framebuffer if we are not using
 		 * VRAM.
 		 */
-		base = dma_alloc_writecombine(current_par.dev, size, &handle,
-					      GFP_KERNEL);
+		base = dma_alloc_wc(current_par.dev, size, &handle,
+				    GFP_KERNEL);
 		if (base == NULL) {
 			printk(KERN_ERR "acornfb: unable to allocate screen "
 			       "memory\n");
diff --git a/drivers/video/fbdev/amba-clcd-versatile.c b/drivers/video/fbdev/amba-clcd-versatile.c
index 7a8afcd4573e..a8a22daa3f9d 100644
--- a/drivers/video/fbdev/amba-clcd-versatile.c
+++ b/drivers/video/fbdev/amba-clcd-versatile.c
@@ -154,8 +154,8 @@ int versatile_clcd_setup_dma(struct clcd_fb *fb, unsigned long framesize)
 {
 	dma_addr_t dma;
 
-	fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev, framesize,
-						    &dma, GFP_KERNEL);
+	fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, framesize, &dma,
+					  GFP_KERNEL);
 	if (!fb->fb.screen_base) {
 		pr_err("CLCD: unable to map framebuffer\n");
 		return -ENOMEM;
@@ -169,14 +169,12 @@ int versatile_clcd_setup_dma(struct clcd_fb *fb, unsigned long framesize)
 
 int versatile_clcd_mmap_dma(struct clcd_fb *fb, struct vm_area_struct *vma)
 {
-	return dma_mmap_writecombine(&fb->dev->dev, vma,
-				     fb->fb.screen_base,
-				     fb->fb.fix.smem_start,
-				     fb->fb.fix.smem_len);
+	return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base,
+			   fb->fb.fix.smem_start, fb->fb.fix.smem_len);
 }
 
 void versatile_clcd_remove_dma(struct clcd_fb *fb)
 {
-	dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len,
-			      fb->fb.screen_base, fb->fb.fix.smem_start);
+	dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base,
+		    fb->fb.fix.smem_start);
 }
diff --git a/drivers/video/fbdev/amba-clcd.c b/drivers/video/fbdev/amba-clcd.c
index 9362424c2340..fe274b5851c7 100644
--- a/drivers/video/fbdev/amba-clcd.c
+++ b/drivers/video/fbdev/amba-clcd.c
@@ -774,8 +774,8 @@ static int clcdfb_of_dma_setup(struct clcd_fb *fb)
 
 static int clcdfb_of_dma_mmap(struct clcd_fb *fb, struct vm_area_struct *vma)
 {
-	return dma_mmap_writecombine(&fb->dev->dev, vma, fb->fb.screen_base,
-			fb->fb.fix.smem_start, fb->fb.fix.smem_len);
+	return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base,
+			   fb->fb.fix.smem_start, fb->fb.fix.smem_len);
 }
 
 static void clcdfb_of_dma_remove(struct clcd_fb *fb)
diff --git a/drivers/video/fbdev/atafb.c b/drivers/video/fbdev/atafb.c
index d6ce613e12ad..fcd2dd670a65 100644
--- a/drivers/video/fbdev/atafb.c
+++ b/drivers/video/fbdev/atafb.c
@@ -313,9 +313,6 @@ extern unsigned char fontdata_8x16[];
  *	* Draws cursor *
  *	int (*fb_cursor) (struct fb_info *info, struct fb_cursor *cursor);
  *
- *	* Rotates the display *
- *	void (*fb_rotate)(struct fb_info *info, int angle);
- *
  *	* wait for blit idle, optional *
  *	int (*fb_sync)(struct fb_info *info);
  *
diff --git a/drivers/video/fbdev/atmel_lcdfb.c b/drivers/video/fbdev/atmel_lcdfb.c
index 19eb42b57d87..56c60e67316a 100644
--- a/drivers/video/fbdev/atmel_lcdfb.c
+++ b/drivers/video/fbdev/atmel_lcdfb.c
@@ -414,8 +414,8 @@ static inline void atmel_lcdfb_free_video_memory(struct atmel_lcdfb_info *sinfo)
 {
 	struct fb_info *info = sinfo->info;
 
-	dma_free_writecombine(info->device, info->fix.smem_len,
-				info->screen_base, info->fix.smem_start);
+	dma_free_wc(info->device, info->fix.smem_len, info->screen_base,
+		    info->fix.smem_start);
 }
 
 /**
@@ -435,8 +435,9 @@ static int atmel_lcdfb_alloc_video_memory(struct atmel_lcdfb_info *sinfo)
 		    * ((var->bits_per_pixel + 7) / 8));
 	info->fix.smem_len = max(smem_len, sinfo->smem_len);
 
-	info->screen_base = dma_alloc_writecombine(info->device, info->fix.smem_len,
-					(dma_addr_t *)&info->fix.smem_start, GFP_KERNEL);
+	info->screen_base = dma_alloc_wc(info->device, info->fix.smem_len,
+					 (dma_addr_t *)&info->fix.smem_start,
+					 GFP_KERNEL);
 
 	if (!info->screen_base) {
 		return -ENOMEM;
diff --git a/drivers/video/fbdev/aty/aty128fb.c b/drivers/video/fbdev/aty/aty128fb.c
index c42ce2fdfd44..0a4626886b00 100644
--- a/drivers/video/fbdev/aty/aty128fb.c
+++ b/drivers/video/fbdev/aty/aty128fb.c
@@ -68,7 +68,6 @@
 #include <asm/machdep.h>
 #include <asm/pmac_feature.h>
 #include <asm/prom.h>
-#include <asm/pci-bridge.h>
 #include "../macmodes.h"
 #endif
 
diff --git a/drivers/video/fbdev/aty/radeon_base.c b/drivers/video/fbdev/aty/radeon_base.c
index ce0b1d05a388..218339a4edaa 100644
--- a/drivers/video/fbdev/aty/radeon_base.c
+++ b/drivers/video/fbdev/aty/radeon_base.c
@@ -76,7 +76,6 @@
 
 #ifdef CONFIG_PPC
 
-#include <asm/pci-bridge.h>
 #include "../macmodes.h"
 
 #ifdef CONFIG_BOOTX_TEXT
diff --git a/drivers/video/fbdev/au1100fb.c b/drivers/video/fbdev/au1100fb.c
index 59560189b24a..35df2c1a8a63 100644
--- a/drivers/video/fbdev/au1100fb.c
+++ b/drivers/video/fbdev/au1100fb.c
@@ -334,27 +334,6 @@ int au1100fb_fb_pan_display(struct fb_var_screeninfo *var, struct fb_info *fbi)
 	return 0;
 }
 
-/* fb_rotate
- * Rotate the display of this angle. This doesn't seems to be used by the core,
- * but as our hardware supports it, so why not implementing it...
- */
-void au1100fb_fb_rotate(struct fb_info *fbi, int angle)
-{
-	struct au1100fb_device *fbdev = to_au1100fb_device(fbi);
-
-	print_dbg("fb_rotate %p %d", fbi, angle);
-
-	if (fbdev && (angle > 0) && !(angle % 90)) {
-
-		fbdev->regs->lcd_control &= ~LCD_CONTROL_GO;
-
-		fbdev->regs->lcd_control &= ~(LCD_CONTROL_SM_MASK);
-		fbdev->regs->lcd_control |= ((angle/90) << LCD_CONTROL_SM_BIT);
-
-		fbdev->regs->lcd_control |= LCD_CONTROL_GO;
-	}
-}
-
 /* fb_mmap
  * Map video memory in user space. We don't use the generic fb_mmap method mainly
  * to allow the use of the TLB streaming flag (CCA=6)
@@ -380,7 +359,6 @@ static struct fb_ops au1100fb_ops =
 	.fb_fillrect		= cfb_fillrect,
 	.fb_copyarea		= cfb_copyarea,
 	.fb_imageblit		= cfb_imageblit,
-	.fb_rotate		= au1100fb_fb_rotate,
 	.fb_mmap		= au1100fb_fb_mmap,
 };
 
diff --git a/drivers/video/fbdev/bf537-lq035.c b/drivers/video/fbdev/bf537-lq035.c
index 7db3052b471d..ef29fb425122 100644
--- a/drivers/video/fbdev/bf537-lq035.c
+++ b/drivers/video/fbdev/bf537-lq035.c
@@ -554,28 +554,6 @@ static int bfin_lq035_fb_check_var(struct fb_var_screeninfo *var,
 	return 0;
 }
 
-/* fb_rotate
- * Rotate the display of this angle. This doesn't seems to be used by the core,
- * but as our hardware supports it, so why not implementing it...
- */
-static void bfin_lq035_fb_rotate(struct fb_info *fbi, int angle)
-{
-	pr_debug("%s: %p %d", __func__, fbi, angle);
-#if (defined(UD) && defined(LBR))
-	switch (angle) {
-
-	case 180:
-		gpio_set_value(LBR, 0);
-		gpio_set_value(UD, 1);
-		break;
-	default:
-		gpio_set_value(LBR, 1);
-		gpio_set_value(UD, 0);
-		break;
-	}
-#endif
-}
-
 static int bfin_lq035_fb_cursor(struct fb_info *info, struct fb_cursor *cursor)
 {
 	if (nocursor)
@@ -623,7 +601,6 @@ static struct fb_ops bfin_lq035_fb_ops = {
 	.fb_open		= bfin_lq035_fb_open,
 	.fb_release		= bfin_lq035_fb_release,
 	.fb_check_var		= bfin_lq035_fb_check_var,
-	.fb_rotate		= bfin_lq035_fb_rotate,
 	.fb_fillrect		= cfb_fillrect,
 	.fb_copyarea		= cfb_copyarea,
 	.fb_imageblit		= cfb_imageblit,
diff --git a/drivers/video/fbdev/bt431.h b/drivers/video/fbdev/bt431.h
index 04e0cfbba538..3929602f5867 100644
--- a/drivers/video/fbdev/bt431.h
+++ b/drivers/video/fbdev/bt431.h
@@ -2,6 +2,7 @@
  *	linux/drivers/video/bt431.h
  *
  *	Copyright 2003  Thiemo Seufer <seufer@csv.ica.uni-stuttgart.de>
+ *	Copyright 2016  Maciej W. Rozycki <macro@linux-mips.org>
  *
  *	This file is subject to the terms and conditions of the GNU General
  *	Public License. See the file COPYING in the main directory of this
@@ -9,6 +10,8 @@
  */
 #include <linux/types.h>
 
+#define BT431_CURSOR_SIZE	64
+
 /*
  * Bt431 cursor generator registers, 32-bit aligned.
  * Two twin Bt431 are used on the DECstation's PMAG-AA.
@@ -60,7 +63,7 @@ static inline u8 bt431_get_value(u16 val)
 #define BT431_CMD_CURS_ENABLE	0x40
 #define BT431_CMD_XHAIR_ENABLE	0x20
 #define BT431_CMD_OR_CURSORS	0x10
-#define BT431_CMD_AND_CURSORS	0x00
+#define BT431_CMD_XOR_CURSORS	0x00
 #define BT431_CMD_1_1_MUX	0x00
 #define BT431_CMD_4_1_MUX	0x04
 #define BT431_CMD_5_1_MUX	0x08
@@ -196,28 +199,30 @@ static inline void bt431_position_cursor(struct bt431_regs *regs, u16 x, u16 y)
 	bt431_write_reg_inc(regs, (y >> 8) & 0x0f); /* BT431_REG_CYHI */
 }
 
-static inline void bt431_set_font(struct bt431_regs *regs, u8 fgc,
-				  u16 width, u16 height)
+static inline void bt431_set_cursor(struct bt431_regs *regs,
+				    const char *data, const char *mask,
+				    u16 rop, u16 width, u16 height)
 {
+	u16 x, y;
 	int i;
-	u16 fgp = fgc ? 0xffff : 0x0000;
-	u16 bgp = fgc ? 0x0000 : 0xffff;
 
+	i = 0;
+	width = DIV_ROUND_UP(width, 8);
 	bt431_select_reg(regs, BT431_REG_CRAM_BASE);
-	for (i = BT431_REG_CRAM_BASE; i <= BT431_REG_CRAM_END; i++) {
-		u16 value;
-
-		if (height << 6 <= i << 3)
-			value = bgp;
-		else if (width <= i % 8 << 3)
-			value = bgp;
-		else if (((width >> 3) & 0xffff) > i % 8)
-			value = fgp;
-		else
-			value = fgp & ~(bgp << (width % 8 << 1));
-
-		bt431_write_cmap_inc(regs, value);
-	}
+	for (y = 0; y < BT431_CURSOR_SIZE; y++)
+		for (x = 0; x < BT431_CURSOR_SIZE / 8; x++) {
+			u16 val = 0;
+
+			if (y < height && x < width) {
+				val = mask[i];
+				if (rop == ROP_XOR)
+					val = (val << 8) | (val ^ data[i]);
+				else
+					val = (val << 8) | (val & data[i]);
+				i++;
+			}
+			bt431_write_cmap_inc(regs, val);
+		}
 }
 
 static inline void bt431_init_cursor(struct bt431_regs *regs)
diff --git a/drivers/video/fbdev/bt455.h b/drivers/video/fbdev/bt455.h
index 80f61b03e9ae..dd1404b40611 100644
--- a/drivers/video/fbdev/bt455.h
+++ b/drivers/video/fbdev/bt455.h
@@ -2,6 +2,7 @@
  *	linux/drivers/video/bt455.h
  *
  *	Copyright 2003  Thiemo Seufer <seufer@csv.ica.uni-stuttgart.de>
+ *	Copyright 2016  Maciej W. Rozycki <macro@linux-mips.org>
  *
  *	This file is subject to the terms and conditions of the GNU General
  *	Public License. See the file COPYING in the main directory of this
@@ -29,66 +30,61 @@ static inline void bt455_select_reg(struct bt455_regs *regs, int ir)
 	regs->addr_cmap = ir & 0x0f;
 }
 
+static inline void bt455_reset_reg(struct bt455_regs *regs)
+{
+	mb();
+	regs->addr_clr = 0;
+}
+
 /*
  * Read/write to a Bt455 color map register.
  */
-static inline void bt455_read_cmap_entry(struct bt455_regs *regs, int cr,
-					 u8* red, u8* green, u8* blue)
+static inline void bt455_read_cmap_next(struct bt455_regs *regs, u8 *grey)
 {
-	bt455_select_reg(regs, cr);
 	mb();
-	*red = regs->addr_cmap_data & 0x0f;
+	regs->addr_cmap_data;
 	rmb();
-	*green = regs->addr_cmap_data & 0x0f;
+	*grey = regs->addr_cmap_data & 0xf;
 	rmb();
-	*blue = regs->addr_cmap_data & 0x0f;
+	regs->addr_cmap_data;
 }
 
-static inline void bt455_write_cmap_entry(struct bt455_regs *regs, int cr,
-					  u8 red, u8 green, u8 blue)
+static inline void bt455_write_cmap_next(struct bt455_regs *regs, u8 grey)
 {
-	bt455_select_reg(regs, cr);
 	wmb();
-	regs->addr_cmap_data = red & 0x0f;
+	regs->addr_cmap_data = 0x0;
 	wmb();
-	regs->addr_cmap_data = green & 0x0f;
+	regs->addr_cmap_data = grey & 0xf;
 	wmb();
-	regs->addr_cmap_data = blue & 0x0f;
+	regs->addr_cmap_data = 0x0;
 }
 
-static inline void bt455_write_ovly_entry(struct bt455_regs *regs, int cr,
-					  u8 red, u8 green, u8 blue)
+static inline void bt455_write_ovly_next(struct bt455_regs *regs, u8 grey)
 {
-	bt455_select_reg(regs, cr);
 	wmb();
-	regs->addr_ovly = red & 0x0f;
+	regs->addr_ovly = 0x0;
 	wmb();
-	regs->addr_ovly = green & 0x0f;
+	regs->addr_ovly = grey & 0xf;
 	wmb();
-	regs->addr_ovly = blue & 0x0f;
+	regs->addr_ovly = 0x0;
 }
 
-static inline void bt455_set_cursor(struct bt455_regs *regs)
+static inline void bt455_read_cmap_entry(struct bt455_regs *regs,
+					 int cr, u8 *grey)
 {
-	mb();
-	regs->addr_ovly = 0x0f;
-	wmb();
-	regs->addr_ovly = 0x0f;
-	wmb();
-	regs->addr_ovly = 0x0f;
+	bt455_select_reg(regs, cr);
+	bt455_read_cmap_next(regs, grey);
 }
 
-static inline void bt455_erase_cursor(struct bt455_regs *regs)
+static inline void bt455_write_cmap_entry(struct bt455_regs *regs,
+					  int cr, u8 grey)
 {
-	/* bt455_write_cmap_entry(regs, 8, 0x00, 0x00, 0x00); */
-	/* bt455_write_cmap_entry(regs, 9, 0x00, 0x00, 0x00); */
-	bt455_write_ovly_entry(regs, 8, 0x03, 0x03, 0x03);
-	bt455_write_ovly_entry(regs, 9, 0x07, 0x07, 0x07);
+	bt455_select_reg(regs, cr);
+	bt455_write_cmap_next(regs, grey);
+}
 
-	wmb();
-	regs->addr_ovly = 0x09;
-	wmb();
-	regs->addr_ovly = 0x09;
-	wmb();
-	regs->addr_ovly = 0x09;
+static inline void bt455_write_ovly_entry(struct bt455_regs *regs, u8 grey)
+{
+	bt455_reset_reg(regs);
+	bt455_write_ovly_next(regs, grey);
 }
diff --git a/drivers/video/fbdev/da8xx-fb.c b/drivers/video/fbdev/da8xx-fb.c
index 0081725c6b5b..d8d583d32a37 100644
--- a/drivers/video/fbdev/da8xx-fb.c
+++ b/drivers/video/fbdev/da8xx-fb.c
@@ -152,7 +152,7 @@ static void lcdc_write(unsigned int val, unsigned int addr)
 
 struct da8xx_fb_par {
 	struct device		*dev;
-	resource_size_t p_palette_base;
+	dma_addr_t		p_palette_base;
 	unsigned char *v_palette_base;
 	dma_addr_t		vram_phys;
 	unsigned long		vram_size;
@@ -209,8 +209,7 @@ static struct fb_videomode known_lcd_panels[] = {
 		.lower_margin   = 2,
 		.hsync_len      = 0,
 		.vsync_len      = 0,
-		.sync           = FB_SYNC_CLK_INVERT |
-			FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.sync           = FB_SYNC_CLK_INVERT,
 	},
 	/* Sharp LK043T1DG01 */
 	[1] = {
@@ -224,7 +223,7 @@ static struct fb_videomode known_lcd_panels[] = {
 		.lower_margin   = 2,
 		.hsync_len      = 41,
 		.vsync_len      = 10,
-		.sync           = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.sync           = 0,
 		.flag           = 0,
 	},
 	[2] = {
@@ -239,7 +238,7 @@ static struct fb_videomode known_lcd_panels[] = {
 		.lower_margin   = 10,
 		.hsync_len      = 10,
 		.vsync_len      = 10,
-		.sync           = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.sync           = 0,
 		.flag           = 0,
 	},
 	[3] = {
@@ -1428,7 +1427,7 @@ static int fb_probe(struct platform_device *device)
 
 	par->vram_virt = dma_alloc_coherent(NULL,
 					    par->vram_size,
-					    (resource_size_t *) &par->vram_phys,
+					    &par->vram_phys,
 					    GFP_KERNEL | GFP_DMA);
 	if (!par->vram_virt) {
 		dev_err(&device->dev,
@@ -1448,7 +1447,7 @@ static int fb_probe(struct platform_device *device)
 
 	/* allocate palette buffer */
 	par->v_palette_base = dma_zalloc_coherent(NULL, PALETTE_SIZE,
-						  (resource_size_t *)&par->p_palette_base,
+						  &par->p_palette_base,
 						  GFP_KERNEL | GFP_DMA);
 	if (!par->v_palette_base) {
 		dev_err(&device->dev,
diff --git a/drivers/video/fbdev/ep93xx-fb.c b/drivers/video/fbdev/ep93xx-fb.c
index 5b1081030cbb..75f0db25d19f 100644
--- a/drivers/video/fbdev/ep93xx-fb.c
+++ b/drivers/video/fbdev/ep93xx-fb.c
@@ -316,9 +316,8 @@ static int ep93xxfb_mmap(struct fb_info *info, struct vm_area_struct *vma)
 	unsigned int offset = vma->vm_pgoff << PAGE_SHIFT;
 
 	if (offset < info->fix.smem_len) {
-		return dma_mmap_writecombine(info->dev, vma, info->screen_base,
-					     info->fix.smem_start,
-					     info->fix.smem_len);
+		return dma_mmap_wc(info->dev, vma, info->screen_base,
+				   info->fix.smem_start, info->fix.smem_len);
 	}
 
 	return -EINVAL;
@@ -428,8 +427,7 @@ static int ep93xxfb_alloc_videomem(struct fb_info *info)
 	/* Maximum 16bpp -> used memory is maximum x*y*2 bytes */
 	fb_size = EP93XXFB_MAX_XRES * EP93XXFB_MAX_YRES * 2;
 
-	virt_addr = dma_alloc_writecombine(info->dev, fb_size,
-					   &phys_addr, GFP_KERNEL);
+	virt_addr = dma_alloc_wc(info->dev, fb_size, &phys_addr, GFP_KERNEL);
 	if (!virt_addr)
 		return -ENOMEM;
 
diff --git a/drivers/video/fbdev/exynos/Kconfig b/drivers/video/fbdev/exynos/Kconfig
index 1f16b4678c71..d916bef94f25 100644
--- a/drivers/video/fbdev/exynos/Kconfig
+++ b/drivers/video/fbdev/exynos/Kconfig
@@ -3,7 +3,7 @@
 #
 
 menuconfig EXYNOS_VIDEO
-	bool "Exynos Video driver support"
+	tristate "Exynos Video driver support"
 	depends on ARCH_S5PV210 || ARCH_EXYNOS
 	help
 	  This enables support for EXYNOS Video device.
@@ -15,13 +15,13 @@ if EXYNOS_VIDEO
 #
 
 config EXYNOS_MIPI_DSI
-	bool "EXYNOS MIPI DSI driver support."
+	tristate "EXYNOS MIPI DSI driver support."
 	select GENERIC_PHY
 	help
 	  This enables support for MIPI-DSI device.
 
 config EXYNOS_LCD_S6E8AX0
-	bool "S6E8AX0 MIPI AMOLED LCD Driver"
+	tristate "S6E8AX0 MIPI AMOLED LCD Driver"
 	depends on EXYNOS_MIPI_DSI && BACKLIGHT_CLASS_DEVICE
 	depends on (LCD_CLASS_DEVICE = y)
 	default n
diff --git a/drivers/video/fbdev/exynos/Makefile b/drivers/video/fbdev/exynos/Makefile
index b5b1bd228abb..02d8dc522fea 100644
--- a/drivers/video/fbdev/exynos/Makefile
+++ b/drivers/video/fbdev/exynos/Makefile
@@ -2,6 +2,8 @@
 # Makefile for the exynos video drivers.
 #
 
-obj-$(CONFIG_EXYNOS_MIPI_DSI)		+= exynos_mipi_dsi.o exynos_mipi_dsi_common.o \
-				     	exynos_mipi_dsi_lowlevel.o
+obj-$(CONFIG_EXYNOS_MIPI_DSI)		+= exynos-mipi-dsi-mod.o
+
+exynos-mipi-dsi-mod-objs		+= exynos_mipi_dsi.o exynos_mipi_dsi_common.o \
+					   exynos_mipi_dsi_lowlevel.o
 obj-$(CONFIG_EXYNOS_LCD_S6E8AX0)	+= s6e8ax0.o
diff --git a/drivers/video/fbdev/exynos/exynos_mipi_dsi.c b/drivers/video/fbdev/exynos/exynos_mipi_dsi.c
index b527fe464628..92e4af3caaf8 100644
--- a/drivers/video/fbdev/exynos/exynos_mipi_dsi.c
+++ b/drivers/video/fbdev/exynos/exynos_mipi_dsi.c
@@ -263,6 +263,7 @@ int exynos_mipi_dsi_register_lcd_driver(struct mipi_dsim_lcd_driver *lcd_drv)
 	return 0;
 
 }
+EXPORT_SYMBOL_GPL(exynos_mipi_dsi_register_lcd_driver);
 
 static struct mipi_dsim_ddi *exynos_mipi_dsi_bind_lcd_ddi(
 						struct mipi_dsim_device *dsim,
@@ -402,12 +403,12 @@ static int exynos_mipi_dsi_probe(struct platform_device *pdev)
 		goto error;
 	}
 
-	dsim->irq = platform_get_irq(pdev, 0);
-	if (IS_ERR_VALUE(dsim->irq)) {
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to request dsim irq resource\n");
-		ret = -EINVAL;
 		goto error;
 	}
+	dsim->irq = ret;
 
 	init_completion(&dsim_wr_comp);
 	init_completion(&dsim_rd_comp);
diff --git a/drivers/video/fbdev/exynos/s6e8ax0.c b/drivers/video/fbdev/exynos/s6e8ax0.c
index 95873f26e39c..de2f3e793786 100644
--- a/drivers/video/fbdev/exynos/s6e8ax0.c
+++ b/drivers/video/fbdev/exynos/s6e8ax0.c
@@ -829,8 +829,7 @@ static int s6e8ax0_probe(struct mipi_dsim_lcd_device *dsim_dev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int s6e8ax0_suspend(struct mipi_dsim_lcd_device *dsim_dev)
+static int __maybe_unused s6e8ax0_suspend(struct mipi_dsim_lcd_device *dsim_dev)
 {
 	struct s6e8ax0 *lcd = dev_get_drvdata(&dsim_dev->dev);
 
@@ -843,7 +842,7 @@ static int s6e8ax0_suspend(struct mipi_dsim_lcd_device *dsim_dev)
 	return 0;
 }
 
-static int s6e8ax0_resume(struct mipi_dsim_lcd_device *dsim_dev)
+static int __maybe_unused s6e8ax0_resume(struct mipi_dsim_lcd_device *dsim_dev)
 {
 	struct s6e8ax0 *lcd = dev_get_drvdata(&dsim_dev->dev);
 
@@ -855,10 +854,6 @@ static int s6e8ax0_resume(struct mipi_dsim_lcd_device *dsim_dev)
 
 	return 0;
 }
-#else
-#define s6e8ax0_suspend		NULL
-#define s6e8ax0_resume		NULL
-#endif
 
 static struct mipi_dsim_lcd_driver s6e8ax0_dsim_ddi_driver = {
 	.name = "s6e8ax0",
@@ -867,8 +862,8 @@ static struct mipi_dsim_lcd_driver s6e8ax0_dsim_ddi_driver = {
 	.power_on = s6e8ax0_power_on,
 	.set_sequence = s6e8ax0_set_sequence,
 	.probe = s6e8ax0_probe,
-	.suspend = s6e8ax0_suspend,
-	.resume = s6e8ax0_resume,
+	.suspend = IS_ENABLED(CONFIG_PM) ? s6e8ax0_suspend : NULL,
+	.resume = IS_ENABLED(CONFIG_PM) ? s6e8ax0_resume : NULL,
 };
 
 static int s6e8ax0_init(void)
diff --git a/drivers/video/fbdev/gbefb.c b/drivers/video/fbdev/gbefb.c
index b63d55f481fa..1a242b1338e9 100644
--- a/drivers/video/fbdev/gbefb.c
+++ b/drivers/video/fbdev/gbefb.c
@@ -1185,8 +1185,8 @@ static int gbefb_probe(struct platform_device *p_dev)
 	} else {
 		/* try to allocate memory with the classical allocator
 		 * this has high chance to fail on low memory machines */
-		gbe_mem = dma_alloc_writecombine(NULL, gbe_mem_size,
-						 &gbe_dma_addr, GFP_KERNEL);
+		gbe_mem = dma_alloc_wc(NULL, gbe_mem_size, &gbe_dma_addr,
+				       GFP_KERNEL);
 		if (!gbe_mem) {
 			printk(KERN_ERR "gbefb: couldn't allocate framebuffer memory\n");
 			ret = -ENOMEM;
@@ -1238,7 +1238,7 @@ static int gbefb_probe(struct platform_device *p_dev)
 out_gbe_unmap:
 	arch_phys_wc_del(par->wc_cookie);
 	if (gbe_dma_addr)
-		dma_free_writecombine(NULL, gbe_mem_size, gbe_mem, gbe_mem_phys);
+		dma_free_wc(NULL, gbe_mem_size, gbe_mem, gbe_mem_phys);
 out_tiles_free:
 	dma_free_coherent(NULL, GBE_TLB_SIZE * sizeof(uint16_t),
 			  (void *)gbe_tiles.cpu, gbe_tiles.dma);
@@ -1259,7 +1259,7 @@ static int gbefb_remove(struct platform_device* p_dev)
 	gbe_turn_off();
 	arch_phys_wc_del(par->wc_cookie);
 	if (gbe_dma_addr)
-		dma_free_writecombine(NULL, gbe_mem_size, gbe_mem, gbe_mem_phys);
+		dma_free_wc(NULL, gbe_mem_size, gbe_mem, gbe_mem_phys);
 	dma_free_coherent(NULL, GBE_TLB_SIZE * sizeof(uint16_t),
 			  (void *)gbe_tiles.cpu, gbe_tiles.dma);
 	release_mem_region(GBE_BASE, sizeof(struct sgi_gbe));
diff --git a/drivers/video/fbdev/imsttfb.c b/drivers/video/fbdev/imsttfb.c
index 9b167f7ef6c6..4363c64d74e8 100644
--- a/drivers/video/fbdev/imsttfb.c
+++ b/drivers/video/fbdev/imsttfb.c
@@ -33,7 +33,6 @@
 #if defined(CONFIG_PPC)
 #include <linux/nvram.h>
 #include <asm/prom.h>
-#include <asm/pci-bridge.h>
 #include "macmodes.h"
 #endif
 
diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c
index cee88603efc9..76b6a7784b06 100644
--- a/drivers/video/fbdev/imxfb.c
+++ b/drivers/video/fbdev/imxfb.c
@@ -902,6 +902,21 @@ static int imxfb_probe(struct platform_device *pdev)
 		goto failed_getclock;
 	}
 
+	/*
+	 * The LCDC controller does not have an enable bit. The
+	 * controller starts directly when the clocks are enabled.
+	 * If the clocks are enabled when the controller is not yet
+	 * programmed with proper register values (enabled at the
+	 * bootloader, for example) then it just goes into some undefined
+	 * state.
+	 * To avoid this issue, let's enable and disable LCDC IPG clock
+	 * so that we force some kind of 'reset' to the LCDC block.
+	 */
+	ret = clk_prepare_enable(fbi->clk_ipg);
+	if (ret)
+		goto failed_getclock;
+	clk_disable_unprepare(fbi->clk_ipg);
+
 	fbi->clk_ahb = devm_clk_get(&pdev->dev, "ahb");
 	if (IS_ERR(fbi->clk_ahb)) {
 		ret = PTR_ERR(fbi->clk_ahb);
@@ -922,8 +937,8 @@ static int imxfb_probe(struct platform_device *pdev)
 	}
 
 	fbi->map_size = PAGE_ALIGN(info->fix.smem_len);
-	info->screen_base = dma_alloc_writecombine(&pdev->dev, fbi->map_size,
-						   &fbi->map_dma, GFP_KERNEL);
+	info->screen_base = dma_alloc_wc(&pdev->dev, fbi->map_size,
+					 &fbi->map_dma, GFP_KERNEL);
 
 	if (!info->screen_base) {
 		dev_err(&pdev->dev, "Failed to allocate video RAM: %d\n", ret);
@@ -990,8 +1005,8 @@ failed_cmap:
 	if (pdata && pdata->exit)
 		pdata->exit(fbi->pdev);
 failed_platform_init:
-	dma_free_writecombine(&pdev->dev, fbi->map_size, info->screen_base,
-			      fbi->map_dma);
+	dma_free_wc(&pdev->dev, fbi->map_size, info->screen_base,
+		    fbi->map_dma);
 failed_map:
 	iounmap(fbi->regs);
 failed_ioremap:
@@ -1026,8 +1041,8 @@ static int imxfb_remove(struct platform_device *pdev)
 	kfree(info->pseudo_palette);
 	framebuffer_release(info);
 
-	dma_free_writecombine(&pdev->dev, fbi->map_size, info->screen_base,
-			      fbi->map_dma);
+	dma_free_wc(&pdev->dev, fbi->map_size, info->screen_base,
+		    fbi->map_dma);
 
 	iounmap(fbi->regs);
 	release_mem_region(res->start, resource_size(res));
diff --git a/drivers/video/fbdev/intelfb/intelfbdrv.c b/drivers/video/fbdev/intelfb/intelfbdrv.c
index bbec737eef30..bf207444ba0c 100644
--- a/drivers/video/fbdev/intelfb/intelfbdrv.c
+++ b/drivers/video/fbdev/intelfb/intelfbdrv.c
@@ -302,7 +302,7 @@ static __inline__ int get_opt_int(const char *this_opt, const char *name,
 }
 
 static __inline__ int get_opt_bool(const char *this_opt, const char *name,
-				   int *ret)
+				   bool *ret)
 {
 	if (!ret)
 		return 0;
diff --git a/drivers/video/fbdev/matrox/matroxfb_base.h b/drivers/video/fbdev/matrox/matroxfb_base.h
index 09b02cd1eb0e..7a90ea2c4613 100644
--- a/drivers/video/fbdev/matrox/matroxfb_base.h
+++ b/drivers/video/fbdev/matrox/matroxfb_base.h
@@ -47,7 +47,6 @@
 
 #if defined(CONFIG_PPC_PMAC)
 #include <asm/prom.h>
-#include <asm/pci-bridge.h>
 #include "../macmodes.h"
 #endif
 
diff --git a/drivers/video/fbdev/metronomefb.c b/drivers/video/fbdev/metronomefb.c
index ad04a01e2761..abb6bbf226d5 100644
--- a/drivers/video/fbdev/metronomefb.c
+++ b/drivers/video/fbdev/metronomefb.c
@@ -354,7 +354,8 @@ static int metronome_powerup_cmd(struct metronomefb_par *par)
 	}
 
 	/* the rest are 0 */
-	memset((u8 *) (par->metromem_cmd->args + i), 0, (32-i)*2);
+	memset(&par->metromem_cmd->args[i], 0,
+	       (ARRAY_SIZE(par->metromem_cmd->args) - i) * 2);
 
 	par->metromem_cmd->csum = cs;
 
@@ -376,7 +377,8 @@ static int metronome_config_cmd(struct metronomefb_par *par)
 	memcpy(par->metromem_cmd->args, epd_frame_table[par->dt].config,
 		sizeof(epd_frame_table[par->dt].config));
 	/* the rest are 0 */
-	memset((u8 *) (par->metromem_cmd->args + 4), 0, (32-4)*2);
+	memset(&par->metromem_cmd->args[4], 0,
+	       (ARRAY_SIZE(par->metromem_cmd->args) - 4) * 2);
 
 	par->metromem_cmd->csum = 0xCC10;
 	par->metromem_cmd->csum += calc_img_cksum(par->metromem_cmd->args, 4);
diff --git a/drivers/video/fbdev/mmp/hw/mmp_ctrl.c b/drivers/video/fbdev/mmp/hw/mmp_ctrl.c
index de54a4748065..b6f83d5df9fd 100644
--- a/drivers/video/fbdev/mmp/hw/mmp_ctrl.c
+++ b/drivers/video/fbdev/mmp/hw/mmp_ctrl.c
@@ -503,8 +503,7 @@ static int mmphw_probe(struct platform_device *pdev)
 	ctrl->reg_base = devm_ioremap_nocache(ctrl->dev,
 			res->start, resource_size(res));
 	if (ctrl->reg_base == NULL) {
-		dev_err(ctrl->dev, "%s: res %x - %x map failed\n", __func__,
-			res->start, res->end);
+		dev_err(ctrl->dev, "%s: res %pR map failed\n", __func__, res);
 		ret = -ENOMEM;
 		goto failed;
 	}
diff --git a/drivers/video/fbdev/mx3fb.c b/drivers/video/fbdev/mx3fb.c
index 7947634ee6b0..f91b1db262b0 100644
--- a/drivers/video/fbdev/mx3fb.c
+++ b/drivers/video/fbdev/mx3fb.c
@@ -1336,9 +1336,8 @@ static int mx3fb_map_video_memory(struct fb_info *fbi, unsigned int mem_len,
 	int retval = 0;
 	dma_addr_t addr;
 
-	fbi->screen_base = dma_alloc_writecombine(fbi->device,
-						  mem_len,
-						  &addr, GFP_DMA | GFP_KERNEL);
+	fbi->screen_base = dma_alloc_wc(fbi->device, mem_len, &addr,
+					GFP_DMA | GFP_KERNEL);
 
 	if (!fbi->screen_base) {
 		dev_err(fbi->device, "Cannot allocate %u bytes framebuffer memory\n",
@@ -1378,8 +1377,8 @@ err0:
  */
 static int mx3fb_unmap_video_memory(struct fb_info *fbi)
 {
-	dma_free_writecombine(fbi->device, fbi->fix.smem_len,
-			      fbi->screen_base, fbi->fix.smem_start);
+	dma_free_wc(fbi->device, fbi->fix.smem_len, fbi->screen_base,
+		    fbi->fix.smem_start);
 
 	fbi->screen_base = NULL;
 	mutex_lock(&fbi->mm_lock);
diff --git a/drivers/video/fbdev/n411.c b/drivers/video/fbdev/n411.c
index 935830fea7b6..053deacad7cc 100644
--- a/drivers/video/fbdev/n411.c
+++ b/drivers/video/fbdev/n411.c
@@ -165,16 +165,22 @@ static int __init n411_init(void)
 	if (!n411_device)
 		return -ENOMEM;
 
-	platform_device_add_data(n411_device, &n411_board, sizeof(n411_board));
+	ret = platform_device_add_data(n411_device, &n411_board,
+				       sizeof(n411_board));
+	if (ret)
+		goto put_plat_device;
 
 	/* this _add binds hecubafb to n411. hecubafb refcounts n411 */
 	ret = platform_device_add(n411_device);
 
 	if (ret)
-		platform_device_put(n411_device);
+		goto put_plat_device;
 
-	return ret;
+	return 0;
 
+put_plat_device:
+	platform_device_put(n411_device);
+	return ret;
 }
 
 static void __exit n411_exit(void)
diff --git a/drivers/video/fbdev/nuc900fb.c b/drivers/video/fbdev/nuc900fb.c
index 389fa2cbb713..6680edae4696 100644
--- a/drivers/video/fbdev/nuc900fb.c
+++ b/drivers/video/fbdev/nuc900fb.c
@@ -396,8 +396,8 @@ static int nuc900fb_map_video_memory(struct fb_info *info)
 	dev_dbg(fbi->dev, "nuc900fb_map_video_memory(fbi=%p) map_size %lu\n",
 		fbi, map_size);
 
-	info->screen_base = dma_alloc_writecombine(fbi->dev, map_size,
-							&map_dma, GFP_KERNEL);
+	info->screen_base = dma_alloc_wc(fbi->dev, map_size, &map_dma,
+					 GFP_KERNEL);
 
 	if (!info->screen_base)
 		return -ENOMEM;
@@ -411,8 +411,8 @@ static int nuc900fb_map_video_memory(struct fb_info *info)
 static inline void nuc900fb_unmap_video_memory(struct fb_info *info)
 {
 	struct nuc900fb_info *fbi = info->par;
-	dma_free_writecombine(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
-			      info->screen_base, info->fix.smem_start);
+	dma_free_wc(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
+		    info->screen_base, info->fix.smem_start);
 }
 
 static irqreturn_t nuc900fb_irqhandler(int irq, void *dev_id)
diff --git a/drivers/video/fbdev/ocfb.c b/drivers/video/fbdev/ocfb.c
index c9293aea8ec3..a970edc2a6f8 100644
--- a/drivers/video/fbdev/ocfb.c
+++ b/drivers/video/fbdev/ocfb.c
@@ -123,11 +123,11 @@ static int ocfb_setupfb(struct ocfb_dev *fbdev)
 
 	/* Horizontal timings */
 	ocfb_writereg(fbdev, OCFB_HTIM, (var->hsync_len - 1) << 24 |
-		      (var->right_margin - 1) << 16 | (var->xres - 1));
+		      (var->left_margin - 1) << 16 | (var->xres - 1));
 
 	/* Vertical timings */
 	ocfb_writereg(fbdev, OCFB_VTIM, (var->vsync_len - 1) << 24 |
-		      (var->lower_margin - 1) << 16 | (var->yres - 1));
+		      (var->upper_margin - 1) << 16 | (var->yres - 1));
 
 	/* Total length of frame */
 	hlen = var->left_margin + var->right_margin + var->hsync_len +
diff --git a/drivers/video/fbdev/offb.c b/drivers/video/fbdev/offb.c
index 43a0a52fc527..fb60a8f0cc94 100644
--- a/drivers/video/fbdev/offb.c
+++ b/drivers/video/fbdev/offb.c
@@ -28,10 +28,6 @@
 #include <linux/pci.h>
 #include <asm/io.h>
 
-#ifdef CONFIG_PPC64
-#include <asm/pci-bridge.h>
-#endif
-
 #ifdef CONFIG_PPC32
 #include <asm/bootx.h>
 #endif
diff --git a/drivers/video/fbdev/omap/lcdc.c b/drivers/video/fbdev/omap/lcdc.c
index 6efa2591eaa8..e3d9b9ea5498 100644
--- a/drivers/video/fbdev/omap/lcdc.c
+++ b/drivers/video/fbdev/omap/lcdc.c
@@ -612,8 +612,8 @@ static void lcdc_dma_handler(u16 status, void *data)
 
 static int alloc_palette_ram(void)
 {
-	lcdc.palette_virt = dma_alloc_writecombine(lcdc.fbdev->dev,
-		MAX_PALETTE_SIZE, &lcdc.palette_phys, GFP_KERNEL);
+	lcdc.palette_virt = dma_alloc_wc(lcdc.fbdev->dev, MAX_PALETTE_SIZE,
+					 &lcdc.palette_phys, GFP_KERNEL);
 	if (lcdc.palette_virt == NULL) {
 		dev_err(lcdc.fbdev->dev, "failed to alloc palette memory\n");
 		return -ENOMEM;
@@ -625,8 +625,8 @@ static int alloc_palette_ram(void)
 
 static void free_palette_ram(void)
 {
-	dma_free_writecombine(lcdc.fbdev->dev, MAX_PALETTE_SIZE,
-			lcdc.palette_virt, lcdc.palette_phys);
+	dma_free_wc(lcdc.fbdev->dev, MAX_PALETTE_SIZE, lcdc.palette_virt,
+		    lcdc.palette_phys);
 }
 
 static int alloc_fbmem(struct omapfb_mem_region *region)
@@ -642,8 +642,8 @@ static int alloc_fbmem(struct omapfb_mem_region *region)
 	if (region->size > frame_size)
 		frame_size = region->size;
 	lcdc.vram_size = frame_size;
-	lcdc.vram_virt = dma_alloc_writecombine(lcdc.fbdev->dev,
-			lcdc.vram_size, &lcdc.vram_phys, GFP_KERNEL);
+	lcdc.vram_virt = dma_alloc_wc(lcdc.fbdev->dev, lcdc.vram_size,
+				      &lcdc.vram_phys, GFP_KERNEL);
 	if (lcdc.vram_virt == NULL) {
 		dev_err(lcdc.fbdev->dev, "unable to allocate FB DMA memory\n");
 		return -ENOMEM;
@@ -660,8 +660,8 @@ static int alloc_fbmem(struct omapfb_mem_region *region)
 
 static void free_fbmem(void)
 {
-	dma_free_writecombine(lcdc.fbdev->dev, lcdc.vram_size,
-			      lcdc.vram_virt, lcdc.vram_phys);
+	dma_free_wc(lcdc.fbdev->dev, lcdc.vram_size, lcdc.vram_virt,
+		    lcdc.vram_phys);
 }
 
 static int setup_fbmem(struct omapfb_mem_desc *req_md)
diff --git a/drivers/video/fbdev/omap/omapfb_main.c b/drivers/video/fbdev/omap/omapfb_main.c
index 393ae1bc07e8..6429f33167f5 100644
--- a/drivers/video/fbdev/omap/omapfb_main.c
+++ b/drivers/video/fbdev/omap/omapfb_main.c
@@ -594,27 +594,6 @@ static int set_fb_var(struct fb_info *fbi,
 }
 
 
-/* Set rotation (0, 90, 180, 270 degree), and switch to the new mode. */
-static void omapfb_rotate(struct fb_info *fbi, int rotate)
-{
-	struct omapfb_plane_struct *plane = fbi->par;
-	struct omapfb_device *fbdev = plane->fbdev;
-
-	omapfb_rqueue_lock(fbdev);
-	if (rotate != fbi->var.rotate) {
-		struct fb_var_screeninfo *new_var = &fbdev->new_var;
-
-		memcpy(new_var, &fbi->var, sizeof(*new_var));
-		new_var->rotate = rotate;
-		if (set_fb_var(fbi, new_var) == 0 &&
-		    memcmp(new_var, &fbi->var, sizeof(*new_var))) {
-			memcpy(&fbi->var, new_var, sizeof(*new_var));
-			ctrl_change_mode(fbi);
-		}
-	}
-	omapfb_rqueue_unlock(fbdev);
-}
-
 /*
  * Set new x,y offsets in the virtual display for the visible area and switch
  * to the new mode.
@@ -1256,7 +1235,6 @@ static struct fb_ops omapfb_ops = {
 	.fb_ioctl	= omapfb_ioctl,
 	.fb_check_var	= omapfb_check_var,
 	.fb_set_par	= omapfb_set_par,
-	.fb_rotate	= omapfb_rotate,
 	.fb_pan_display = omapfb_pan_display,
 };
 
diff --git a/drivers/video/fbdev/pmag-aa-fb.c b/drivers/video/fbdev/pmag-aa-fb.c
index 838424817de2..ffe2dd482f84 100644
--- a/drivers/video/fbdev/pmag-aa-fb.c
+++ b/drivers/video/fbdev/pmag-aa-fb.c
@@ -8,6 +8,7 @@
  *	and Harald Koerfgen <hkoerfg@web.de>, which itself is derived from
  *	"HP300 Topcat framebuffer support (derived from macfb of all things)
  *	Phil Blundell <philb@gnu.org> 1998"
+ *	Copyright (c) 2016  Maciej W. Rozycki
  *
  *	This file is subject to the terms and conditions of the GNU General
  *	Public License.  See the file COPYING in the main directory of this
@@ -21,37 +22,29 @@
  *
  *	2003-09-21  Thiemo Seufer  <seufer@csv.ica.uni-stuttgart.de>
  *		Hardware cursor support.
+ *
+ *	2016-02-21  Maciej W. Rozycki  <macro@linux-mips.org>
+ *		Version 0.03: Rewritten for the new FB and TC APIs.
  */
-#include <linux/module.h>
-#include <linux/kernel.h>
+
+#include <linux/compiler.h>
 #include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/timer.h>
-#include <linux/mm.h>
-#include <linux/delay.h>
-#include <linux/init.h>
 #include <linux/fb.h>
-#include <linux/console.h>
-
-#include <asm/bootinfo.h>
-#include <asm/dec/machtype.h>
-#include <asm/dec/tc.h>
-
-#include <video/fbcon.h>
-#include <video/fbcon-cfb8.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/tc.h>
+#include <linux/timer.h>
 
 #include "bt455.h"
 #include "bt431.h"
 
 /* Version information */
-#define DRIVER_VERSION "0.02"
+#define DRIVER_VERSION "0.03"
 #define DRIVER_AUTHOR "Karsten Merker <merker@linuxtag.org>"
 #define DRIVER_DESCRIPTION "PMAG-AA Framebuffer Driver"
 
-/* Prototypes */
-static int aafb_set_var(struct fb_var_screeninfo *var, int con,
-			struct fb_info *info);
-
 /*
  * Bt455 RAM DAC register base offset (rel. to TC slot base address).
  */
@@ -68,443 +61,246 @@ static int aafb_set_var(struct fb_var_screeninfo *var, int con,
  */
 #define PMAG_AA_ONBOARD_FBMEM_OFFSET	0x200000
 
-struct aafb_cursor {
-	struct timer_list timer;
-	int enable;
-	int on;
-	int vbl_cnt;
-	int blink_rate;
-	u16 x, y, width, height;
+struct aafb_par {
+	void __iomem *mmio;
+	struct bt455_regs __iomem *bt455;
+	struct bt431_regs __iomem *bt431;
 };
 
-#define CURSOR_TIMER_FREQ	(HZ / 50)
-#define CURSOR_BLINK_RATE	(20)
-#define CURSOR_DRAW_DELAY	(2)
-
-struct aafb_info {
-	struct fb_info info;
-	struct display disp;
-	struct aafb_cursor cursor;
-	struct bt455_regs *bt455;
-	struct bt431_regs *bt431;
-	unsigned long fb_start;
-	unsigned long fb_size;
-	unsigned long fb_line_length;
+static struct fb_var_screeninfo aafb_defined = {
+	.xres		= 1280,
+	.yres		= 1024,
+	.xres_virtual	= 2048,
+	.yres_virtual	= 1024,
+	.bits_per_pixel	= 8,
+	.grayscale	= 1,
+	.red.length	= 0,
+	.green.length	= 1,
+	.blue.length	= 0,
+	.activate	= FB_ACTIVATE_NOW,
+	.accel_flags	= FB_ACCEL_NONE,
+	.pixclock	= 7645,
+	.left_margin	= 224,
+	.right_margin	= 32,
+	.upper_margin	= 33,
+	.lower_margin	= 3,
+	.hsync_len	= 160,
+	.vsync_len	= 3,
+	.sync		= FB_SYNC_ON_GREEN,
+	.vmode		= FB_VMODE_NONINTERLACED,
 };
 
-/*
- * Max 3 TURBOchannel slots -> max 3 PMAG-AA.
- */
-static struct aafb_info my_fb_info[3];
-
-static struct aafb_par {
-} current_par;
-
-static int currcon = -1;
-
-static void aafb_set_cursor(struct aafb_info *info, int on)
-{
-	struct aafb_cursor *c = &info->cursor;
-
-	if (on) {
-		bt431_position_cursor(info->bt431, c->x, c->y);
-		bt431_enable_cursor(info->bt431);
-	} else
-		bt431_erase_cursor(info->bt431);
-}
-
-static void aafbcon_cursor(struct display *disp, int mode, int x, int y)
-{
-	struct aafb_info *info = (struct aafb_info *)disp->fb_info;
-	struct aafb_cursor *c = &info->cursor;
-
-	x *= fontwidth(disp);
-	y *= fontheight(disp);
-
-	if (c->x == x && c->y == y && (mode == CM_ERASE) == !c->enable)
-		return;
-
-	c->enable = 0;
-	if (c->on)
-		aafb_set_cursor(info, 0);
-	c->x = x - disp->var.xoffset;
-	c->y = y - disp->var.yoffset;
-
-	switch (mode) {
-		case CM_ERASE:
-			c->on = 0;
-			break;
-		case CM_DRAW:
-		case CM_MOVE:
-			if (c->on)
-				aafb_set_cursor(info, c->on);
-			else
-				c->vbl_cnt = CURSOR_DRAW_DELAY;
-			c->enable = 1;
-			break;
-	}
-}
+static struct fb_fix_screeninfo aafb_fix = {
+	.id		= "PMAG-AA",
+	.smem_len	= (2048 * 1024),
+	.type		= FB_TYPE_PACKED_PIXELS,
+	.visual		= FB_VISUAL_MONO10,
+	.ypanstep	= 1,
+	.ywrapstep	= 1,
+	.line_length	= 2048,
+	.mmio_len	= PMAG_AA_ONBOARD_FBMEM_OFFSET - PMAG_AA_BT455_OFFSET,
+};
 
-static int aafbcon_set_font(struct display *disp, int width, int height)
+static int aafb_cursor(struct fb_info *info, struct fb_cursor *cursor)
 {
-	struct aafb_info *info = (struct aafb_info *)disp->fb_info;
-	struct aafb_cursor *c = &info->cursor;
-	u8 fgc = ~attr_bgcol_ec(disp, disp->conp, &info->info);
+	struct aafb_par *par = info->par;
 
-	if (width > 64 || height > 64 || width < 0 || height < 0)
+	if (cursor->image.height > BT431_CURSOR_SIZE ||
+	    cursor->image.width > BT431_CURSOR_SIZE) {
+		bt431_erase_cursor(par->bt431);
 		return -EINVAL;
-
-	c->height = height;
-	c->width = width;
-
-	bt431_set_font(info->bt431, fgc, width, height);
-
-	return 1;
-}
-
-static void aafb_cursor_timer_handler(unsigned long data)
-{
-	struct aafb_info *info = (struct aafb_info *)data;
-	struct aafb_cursor *c = &info->cursor;
-
-	if (!c->enable)
-		goto out;
-
-	if (c->vbl_cnt && --c->vbl_cnt == 0) {
-		c->on ^= 1;
-		aafb_set_cursor(info, c->on);
-		c->vbl_cnt = c->blink_rate;
 	}
 
-out:
-	c->timer.expires = jiffies + CURSOR_TIMER_FREQ;
-	add_timer(&c->timer);
-}
-
-static void __init aafb_cursor_init(struct aafb_info *info)
-{
-	struct aafb_cursor *c = &info->cursor;
-
-	c->enable = 1;
-	c->on = 1;
-	c->x = c->y = 0;
-	c->width = c->height = 0;
-	c->vbl_cnt = CURSOR_DRAW_DELAY;
-	c->blink_rate = CURSOR_BLINK_RATE;
-
-	init_timer(&c->timer);
-	c->timer.data = (unsigned long)info;
-	c->timer.function = aafb_cursor_timer_handler;
-	mod_timer(&c->timer, jiffies + CURSOR_TIMER_FREQ);
-}
-
-static void __exit aafb_cursor_exit(struct aafb_info *info)
-{
-	struct aafb_cursor *c = &info->cursor;
-
-	del_timer_sync(&c->timer);
-}
-
-static struct display_switch aafb_switch8 = {
-	.setup = fbcon_cfb8_setup,
-	.bmove = fbcon_cfb8_bmove,
-	.clear = fbcon_cfb8_clear,
-	.putc = fbcon_cfb8_putc,
-	.putcs = fbcon_cfb8_putcs,
-	.revc = fbcon_cfb8_revc,
-	.cursor = aafbcon_cursor,
-	.set_font = aafbcon_set_font,
-	.clear_margins = fbcon_cfb8_clear_margins,
-	.fontwidthmask = FONTWIDTH(4)|FONTWIDTH(8)|FONTWIDTH(12)|FONTWIDTH(16)
-};
-
-static void aafb_get_par(struct aafb_par *par)
-{
-	*par = current_par;
-}
-
-static int aafb_get_fix(struct fb_fix_screeninfo *fix, int con,
-			struct fb_info *info)
-{
-	struct aafb_info *ip = (struct aafb_info *)info;
-
-	memset(fix, 0, sizeof(struct fb_fix_screeninfo));
-	strcpy(fix->id, "PMAG-AA");
-	fix->smem_start = ip->fb_start;
-	fix->smem_len = ip->fb_size;
-	fix->type = FB_TYPE_PACKED_PIXELS;
-	fix->ypanstep = 1;
-	fix->ywrapstep = 1;
-	fix->visual = FB_VISUAL_MONO10;
-	fix->line_length = 1280;
-	fix->accel = FB_ACCEL_NONE;
+	if (!cursor->enable)
+		bt431_erase_cursor(par->bt431);
 
-	return 0;
-}
+	if (cursor->set & FB_CUR_SETPOS)
+		bt431_position_cursor(par->bt431,
+				      cursor->image.dx, cursor->image.dy);
+	if (cursor->set & FB_CUR_SETCMAP) {
+		u8 fg = cursor->image.fg_color ? 0xf : 0x0;
+		u8 bg = cursor->image.bg_color ? 0xf : 0x0;
 
-static void aafb_set_disp(struct display *disp, int con,
-			  struct aafb_info *info)
-{
-	struct fb_fix_screeninfo fix;
-
-	disp->fb_info = &info->info;
-	aafb_set_var(&disp->var, con, &info->info);
-	if (disp->conp && disp->conp->vc_sw && disp->conp->vc_sw->con_cursor)
-		disp->conp->vc_sw->con_cursor(disp->conp, CM_ERASE);
-	disp->dispsw = &aafb_switch8;
-	disp->dispsw_data = 0;
-
-	aafb_get_fix(&fix, con, &info->info);
-	disp->screen_base = (u8 *) fix.smem_start;
-	disp->visual = fix.visual;
-	disp->type = fix.type;
-	disp->type_aux = fix.type_aux;
-	disp->ypanstep = fix.ypanstep;
-	disp->ywrapstep = fix.ywrapstep;
-	disp->line_length = fix.line_length;
-	disp->next_line = 2048;
-	disp->can_soft_blank = 1;
-	disp->inverse = 0;
-	disp->scrollmode = SCROLL_YREDRAW;
-
-	aafbcon_set_font(disp, fontwidth(disp), fontheight(disp));
-}
+		bt455_write_cmap_entry(par->bt455, 8, bg);
+		bt455_write_cmap_next(par->bt455, bg);
+		bt455_write_ovly_next(par->bt455, fg);
+	}
+	if (cursor->set & (FB_CUR_SETSIZE | FB_CUR_SETSHAPE | FB_CUR_SETIMAGE))
+		bt431_set_cursor(par->bt431,
+				 cursor->image.data, cursor->mask, cursor->rop,
+				 cursor->image.width, cursor->image.height);
 
-static int aafb_get_cmap(struct fb_cmap *cmap, int kspc, int con,
-			 struct fb_info *info)
-{
-	static u16 color[2] = {0x0000, 0x000f};
-	static struct fb_cmap aafb_cmap = {0, 2, color, color, color, NULL};
+	if (cursor->enable)
+		bt431_enable_cursor(par->bt431);
 
-	fb_copy_cmap(&aafb_cmap, cmap, kspc ? 0 : 2);
 	return 0;
 }
 
-static int aafb_set_cmap(struct fb_cmap *cmap, int kspc, int con,
-			 struct fb_info *info)
-{
-	u16 color[2] = {0x0000, 0x000f};
-
-	if (cmap->start == 0
-	    && cmap->len == 2
-	    && memcmp(cmap->red, color, sizeof(color)) == 0
-	    && memcmp(cmap->green, color, sizeof(color)) == 0
-	    && memcmp(cmap->blue, color, sizeof(color)) == 0
-	    && cmap->transp == NULL)
-		return 0;
-	else
-		return -EINVAL;
-}
-
-static int aafb_ioctl(struct fb_info *info, u32 cmd, unsigned long arg)
-{
-	/* TODO: Not yet implemented */
-	return -ENOIOCTLCMD;
-}
+/* 0 unblanks, any other blanks. */
 
-static int aafb_switch(int con, struct fb_info *info)
+static int aafb_blank(int blank, struct fb_info *info)
 {
-	struct aafb_info *ip = (struct aafb_info *)info;
-	struct display *old = (currcon < 0) ? &ip->disp : (fb_display + currcon);
-	struct display *new = (con < 0) ? &ip->disp : (fb_display + con);
-
-	if (old->conp && old->conp->vc_sw && old->conp->vc_sw->con_cursor)
-		old->conp->vc_sw->con_cursor(old->conp, CM_ERASE);
-
-	/* Set the current console. */
-	currcon = con;
-	aafb_set_disp(new, con, ip);
+	struct aafb_par *par = info->par;
+	u8 val = blank ? 0x00 : 0x0f;
 
+	bt455_write_cmap_entry(par->bt455, 1, val);
 	return 0;
 }
 
-static void aafb_encode_var(struct fb_var_screeninfo *var,
-			    struct aafb_par *par)
-{
-	var->xres = 1280;
-	var->yres = 1024;
-	var->xres_virtual = 2048;
-	var->yres_virtual = 1024;
-	var->xoffset = 0;
-	var->yoffset = 0;
-	var->bits_per_pixel = 8;
-	var->grayscale = 1;
-	var->red.offset = 0;
-	var->red.length = 0;
-	var->red.msb_right = 0;
-	var->green.offset = 0;
-	var->green.length = 1;
-	var->green.msb_right = 0;
-	var->blue.offset = 0;
-	var->blue.length = 0;
-	var->blue.msb_right = 0;
-	var->transp.offset = 0;
-	var->transp.length = 0;
-	var->transp.msb_right = 0;
-	var->nonstd = 0;
-	var->activate &= ~FB_ACTIVATE_MASK & FB_ACTIVATE_NOW;
-	var->accel_flags = 0;
-	var->sync = FB_SYNC_ON_GREEN;
-	var->vmode &= ~FB_VMODE_MASK & FB_VMODE_NONINTERLACED;
-}
+static struct fb_ops aafb_ops = {
+	.owner		= THIS_MODULE,
+	.fb_blank	= aafb_blank,
+	.fb_fillrect	= cfb_fillrect,
+	.fb_copyarea	= cfb_copyarea,
+	.fb_imageblit	= cfb_imageblit,
+	.fb_cursor	= aafb_cursor,
+};
 
-static int aafb_get_var(struct fb_var_screeninfo *var, int con,
-			struct fb_info *info)
+static int pmagaafb_probe(struct device *dev)
 {
-	if (con < 0) {
-		struct aafb_par par;
-
-		memset(var, 0, sizeof(struct fb_var_screeninfo));
-		aafb_get_par(&par);
-		aafb_encode_var(var, &par);
-	} else
-		*var = info->var;
+	struct tc_dev *tdev = to_tc_dev(dev);
+	resource_size_t start, len;
+	struct fb_info *info;
+	struct aafb_par *par;
+	int err;
+
+	info = framebuffer_alloc(sizeof(struct aafb_par), dev);
+	if (!info) {
+		printk(KERN_ERR "%s: Cannot allocate memory\n", dev_name(dev));
+		return -ENOMEM;
+	}
 
-	return 0;
-}
+	par = info->par;
+	dev_set_drvdata(dev, info);
+
+	info->fbops = &aafb_ops;
+	info->fix = aafb_fix;
+	info->var = aafb_defined;
+	info->flags = FBINFO_DEFAULT;
+
+	/* Request the I/O MEM resource. */
+	start = tdev->resource.start;
+	len = tdev->resource.end - start + 1;
+	if (!request_mem_region(start, len, dev_name(dev))) {
+		printk(KERN_ERR "%s: Cannot reserve FB region\n",
+		       dev_name(dev));
+		err = -EBUSY;
+		goto err_alloc;
+	}
 
-static int aafb_set_var(struct fb_var_screeninfo *var, int con,
-			struct fb_info *info)
-{
-	struct aafb_par par;
+	/* MMIO mapping setup. */
+	info->fix.mmio_start = start + PMAG_AA_BT455_OFFSET;
+	par->mmio = ioremap_nocache(info->fix.mmio_start, info->fix.mmio_len);
+	if (!par->mmio) {
+		printk(KERN_ERR "%s: Cannot map MMIO\n", dev_name(dev));
+		err = -ENOMEM;
+		goto err_resource;
+	}
+	par->bt455 = par->mmio - PMAG_AA_BT455_OFFSET + PMAG_AA_BT455_OFFSET;
+	par->bt431 = par->mmio - PMAG_AA_BT455_OFFSET + PMAG_AA_BT431_OFFSET;
+
+	/* Frame buffer mapping setup. */
+	info->fix.smem_start = start + PMAG_AA_ONBOARD_FBMEM_OFFSET;
+	info->screen_base = ioremap_nocache(info->fix.smem_start,
+					    info->fix.smem_len);
+	if (!info->screen_base) {
+		printk(KERN_ERR "%s: Cannot map FB\n", dev_name(dev));
+		err = -ENOMEM;
+		goto err_mmio_map;
+	}
+	info->screen_size = info->fix.smem_len;
 
-	aafb_get_par(&par);
-	aafb_encode_var(var, &par);
-	info->var = *var;
+	/* Init colormap. */
+	bt455_write_cmap_entry(par->bt455, 0, 0x0);
+	bt455_write_cmap_next(par->bt455, 0xf);
 
-	return 0;
-}
+	/* Init hardware cursor. */
+	bt431_erase_cursor(par->bt431);
+	bt431_init_cursor(par->bt431);
+
+	err = register_framebuffer(info);
+	if (err < 0) {
+		printk(KERN_ERR "%s: Cannot register framebuffer\n",
+		       dev_name(dev));
+		goto err_smem_map;
+	}
 
-static int aafb_update_var(int con, struct fb_info *info)
-{
-	struct aafb_info *ip = (struct aafb_info *)info;
-	struct display *disp = (con < 0) ? &ip->disp : (fb_display + con);
+	get_device(dev);
 
-	if (con == currcon)
-		aafbcon_cursor(disp, CM_ERASE, ip->cursor.x, ip->cursor.y);
+	pr_info("fb%d: %s frame buffer device at %s\n",
+		info->node, info->fix.id, dev_name(dev));
 
 	return 0;
-}
 
-/* 0 unblanks, any other blanks. */
 
-static void aafb_blank(int blank, struct fb_info *info)
-{
-	struct aafb_info *ip = (struct aafb_info *)info;
-	u8 val = blank ? 0x00 : 0x0f;
+err_smem_map:
+	iounmap(info->screen_base);
 
-	bt455_write_cmap_entry(ip->bt455, 1, val, val, val);
-	aafbcon_cursor(&ip->disp, CM_ERASE, ip->cursor.x, ip->cursor.y);
-}
+err_mmio_map:
+	iounmap(par->mmio);
 
-static struct fb_ops aafb_ops = {
-	.owner = THIS_MODULE,
-	.fb_get_fix = aafb_get_fix,
-	.fb_get_var = aafb_get_var,
-	.fb_set_var = aafb_set_var,
-	.fb_get_cmap = aafb_get_cmap,
-	.fb_set_cmap = aafb_set_cmap,
-	.fb_ioctl = aafb_ioctl
-};
+err_resource:
+	release_mem_region(start, len);
 
-static int __init init_one(int slot)
-{
-	unsigned long base_addr = CKSEG1ADDR(get_tc_base_addr(slot));
-	struct aafb_info *ip = &my_fb_info[slot];
-
-	memset(ip, 0, sizeof(struct aafb_info));
-
-	/*
-	 * Framebuffer display memory base address and friends.
-	 */
-	ip->bt455 = (struct bt455_regs *) (base_addr + PMAG_AA_BT455_OFFSET);
-	ip->bt431 = (struct bt431_regs *) (base_addr + PMAG_AA_BT431_OFFSET);
-	ip->fb_start = base_addr + PMAG_AA_ONBOARD_FBMEM_OFFSET;
-	ip->fb_size = 2048 * 1024; /* fb_fix_screeninfo.smem_length
-				      seems to be physical */
-	ip->fb_line_length = 2048;
-
-	/*
-	 * Let there be consoles..
-	 */
-	strcpy(ip->info.modename, "PMAG-AA");
-	ip->info.node = -1;
-	ip->info.flags = FBINFO_FLAG_DEFAULT;
-	ip->info.fbops = &aafb_ops;
-	ip->info.disp = &ip->disp;
-	ip->info.changevar = NULL;
-	ip->info.switch_con = &aafb_switch;
-	ip->info.updatevar = &aafb_update_var;
-	ip->info.blank = &aafb_blank;
-
-	aafb_set_disp(&ip->disp, currcon, ip);
-
-	/*
-	 * Configure the RAM DACs.
-	 */
-	bt455_erase_cursor(ip->bt455);
-
-	/* Init colormap. */
-	bt455_write_cmap_entry(ip->bt455, 0, 0x00, 0x00, 0x00);
-	bt455_write_cmap_entry(ip->bt455, 1, 0x0f, 0x0f, 0x0f);
-
-	/* Init hardware cursor. */
-	bt431_init_cursor(ip->bt431);
-	aafb_cursor_init(ip);
-
-	/* Clear the screen. */
-	memset ((void *)ip->fb_start, 0, ip->fb_size);
-
-	if (register_framebuffer(&ip->info) < 0)
-		return -EINVAL;
-
-	printk(KERN_INFO "fb%d: %s frame buffer in TC slot %d\n",
-	       GET_FB_IDX(ip->info.node), ip->info.modename, slot);
-
-	return 0;
+err_alloc:
+	framebuffer_release(info);
+	return err;
 }
 
-static int __exit exit_one(int slot)
+static int __exit pmagaafb_remove(struct device *dev)
 {
-	struct aafb_info *ip = &my_fb_info[slot];
-
-	if (unregister_framebuffer(&ip->info) < 0)
-		return -EINVAL;
-
+	struct tc_dev *tdev = to_tc_dev(dev);
+	struct fb_info *info = dev_get_drvdata(dev);
+	struct aafb_par *par = info->par;
+	resource_size_t start, len;
+
+	put_device(dev);
+	unregister_framebuffer(info);
+	iounmap(info->screen_base);
+	iounmap(par->mmio);
+	start = tdev->resource.start;
+	len = tdev->resource.end - start + 1;
+	release_mem_region(start, len);
+	framebuffer_release(info);
 	return 0;
 }
 
 /*
  * Initialise the framebuffer.
  */
-int __init pmagaafb_init(void)
-{
-	int sid;
-	int found = 0;
-
-	while ((sid = search_tc_card("PMAG-AA")) >= 0) {
-		found = 1;
-		claim_tc_card(sid);
-		init_one(sid);
-	}
+static const struct tc_device_id pmagaafb_tc_table[] = {
+	{ "DEC     ", "PMAG-AA " },
+	{ }
+};
+MODULE_DEVICE_TABLE(tc, pmagaafb_tc_table);
+
+static struct tc_driver pmagaafb_driver = {
+	.id_table	= pmagaafb_tc_table,
+	.driver		= {
+		.name	= "pmagaafb",
+		.bus	= &tc_bus_type,
+		.probe	= pmagaafb_probe,
+		.remove	= __exit_p(pmagaafb_remove),
+	},
+};
 
-	return found ? 0 : -ENXIO;
+static int __init pmagaafb_init(void)
+{
+#ifndef MODULE
+	if (fb_get_options("pmagaafb", NULL))
+		return -ENXIO;
+#endif
+	return tc_register_driver(&pmagaafb_driver);
 }
 
 static void __exit pmagaafb_exit(void)
 {
-	int sid;
-
-	while ((sid = search_tc_card("PMAG-AA")) >= 0) {
-		exit_one(sid);
-		release_tc_card(sid);
-	}
+	tc_unregister_driver(&pmagaafb_driver);
 }
 
+module_init(pmagaafb_init);
+module_exit(pmagaafb_exit);
+
 MODULE_AUTHOR(DRIVER_AUTHOR);
 MODULE_DESCRIPTION(DRIVER_DESCRIPTION);
 MODULE_LICENSE("GPL");
-#ifdef MODULE
-module_init(pmagaafb_init);
-module_exit(pmagaafb_exit);
-#endif
diff --git a/drivers/video/fbdev/pmag-ba-fb.c b/drivers/video/fbdev/pmag-ba-fb.c
index 914a52ba8477..5872bc4af3ce 100644
--- a/drivers/video/fbdev/pmag-ba-fb.c
+++ b/drivers/video/fbdev/pmag-ba-fb.c
@@ -60,7 +60,7 @@ static struct fb_var_screeninfo pmagbafb_defined = {
 	.left_margin	= 116,
 	.right_margin	= 12,
 	.upper_margin	= 34,
-	.lower_margin	= 12,
+	.lower_margin	= 0,
 	.hsync_len	= 128,
 	.vsync_len	= 3,
 	.sync		= FB_SYNC_ON_GREEN,
diff --git a/drivers/video/fbdev/pxa168fb.c b/drivers/video/fbdev/pxa168fb.c
index efb57c059997..def3a501acd6 100644
--- a/drivers/video/fbdev/pxa168fb.c
+++ b/drivers/video/fbdev/pxa168fb.c
@@ -680,8 +680,8 @@ static int pxa168fb_probe(struct platform_device *pdev)
 	 */
 	info->fix.smem_len = PAGE_ALIGN(DEFAULT_FB_SIZE);
 
-	info->screen_base = dma_alloc_writecombine(fbi->dev, info->fix.smem_len,
-						&fbi->fb_start_dma, GFP_KERNEL);
+	info->screen_base = dma_alloc_wc(fbi->dev, info->fix.smem_len,
+					 &fbi->fb_start_dma, GFP_KERNEL);
 	if (info->screen_base == NULL) {
 		ret = -ENOMEM;
 		goto failed_free_info;
@@ -804,8 +804,8 @@ static int pxa168fb_remove(struct platform_device *pdev)
 
 	irq = platform_get_irq(pdev, 0);
 
-	dma_free_writecombine(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
-				info->screen_base, info->fix.smem_start);
+	dma_free_wc(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
+		    info->screen_base, info->fix.smem_start);
 
 	clk_disable(fbi->clk);
 
diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c
index 33b2bb315a2a..2c0487f4f805 100644
--- a/drivers/video/fbdev/pxafb.c
+++ b/drivers/video/fbdev/pxafb.c
@@ -2446,8 +2446,8 @@ static int pxafb_remove(struct platform_device *dev)
 
 	free_pages_exact(fbi->video_mem, fbi->video_mem_size);
 
-	dma_free_writecombine(&dev->dev, fbi->dma_buff_size,
-			fbi->dma_buff, fbi->dma_buff_phys);
+	dma_free_wc(&dev->dev, fbi->dma_buff_size, fbi->dma_buff,
+		    fbi->dma_buff_phys);
 
 	iounmap(fbi->mmio_base);
 
diff --git a/drivers/video/fbdev/s3c-fb.c b/drivers/video/fbdev/s3c-fb.c
index f72dd12456f9..5f4f696c2ecf 100644
--- a/drivers/video/fbdev/s3c-fb.c
+++ b/drivers/video/fbdev/s3c-fb.c
@@ -1105,8 +1105,7 @@ static int s3c_fb_alloc_memory(struct s3c_fb *sfb, struct s3c_fb_win *win)
 
 	dev_dbg(sfb->dev, "want %u bytes for window\n", size);
 
-	fbi->screen_base = dma_alloc_writecombine(sfb->dev, size,
-						  &map_dma, GFP_KERNEL);
+	fbi->screen_base = dma_alloc_wc(sfb->dev, size, &map_dma, GFP_KERNEL);
 	if (!fbi->screen_base)
 		return -ENOMEM;
 
@@ -1131,8 +1130,8 @@ static void s3c_fb_free_memory(struct s3c_fb *sfb, struct s3c_fb_win *win)
 	struct fb_info *fbi = win->fbinfo;
 
 	if (fbi->screen_base)
-		dma_free_writecombine(sfb->dev, PAGE_ALIGN(fbi->fix.smem_len),
-			      fbi->screen_base, fbi->fix.smem_start);
+		dma_free_wc(sfb->dev, PAGE_ALIGN(fbi->fix.smem_len),
+		            fbi->screen_base, fbi->fix.smem_start);
 }
 
 /**
diff --git a/drivers/video/fbdev/s3c2410fb.c b/drivers/video/fbdev/s3c2410fb.c
index d6704add1601..0dd86be36afb 100644
--- a/drivers/video/fbdev/s3c2410fb.c
+++ b/drivers/video/fbdev/s3c2410fb.c
@@ -645,8 +645,8 @@ static int s3c2410fb_map_video_memory(struct fb_info *info)
 
 	dprintk("map_video_memory(fbi=%p) map_size %u\n", fbi, map_size);
 
-	info->screen_base = dma_alloc_writecombine(fbi->dev, map_size,
-						   &map_dma, GFP_KERNEL);
+	info->screen_base = dma_alloc_wc(fbi->dev, map_size, &map_dma,
+					 GFP_KERNEL);
 
 	if (info->screen_base) {
 		/* prevent initial garbage on screen */
@@ -667,8 +667,8 @@ static inline void s3c2410fb_unmap_video_memory(struct fb_info *info)
 {
 	struct s3c2410fb_info *fbi = info->par;
 
-	dma_free_writecombine(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
-			      info->screen_base, info->fix.smem_start);
+	dma_free_wc(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
+		    info->screen_base, info->fix.smem_start);
 }
 
 static inline void modify_gpio(void __iomem *reg,
diff --git a/drivers/video/fbdev/sa1100fb.c b/drivers/video/fbdev/sa1100fb.c
index dcf774c15889..fc2aaa5aca23 100644
--- a/drivers/video/fbdev/sa1100fb.c
+++ b/drivers/video/fbdev/sa1100fb.c
@@ -567,8 +567,8 @@ static int sa1100fb_mmap(struct fb_info *info,
 
 	if (off < info->fix.smem_len) {
 		vma->vm_pgoff += 1; /* skip over the palette */
-		return dma_mmap_writecombine(fbi->dev, vma, fbi->map_cpu,
-					     fbi->map_dma, fbi->map_size);
+		return dma_mmap_wc(fbi->dev, vma, fbi->map_cpu, fbi->map_dma,
+				   fbi->map_size);
 	}
 
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
@@ -1099,8 +1099,8 @@ static int sa1100fb_map_video_memory(struct sa1100fb_info *fbi)
 	 * of the framebuffer.
 	 */
 	fbi->map_size = PAGE_ALIGN(fbi->fb.fix.smem_len + PAGE_SIZE);
-	fbi->map_cpu = dma_alloc_writecombine(fbi->dev, fbi->map_size,
-					      &fbi->map_dma, GFP_KERNEL);
+	fbi->map_cpu = dma_alloc_wc(fbi->dev, fbi->map_size, &fbi->map_dma,
+				    GFP_KERNEL);
 
 	if (fbi->map_cpu) {
 		fbi->fb.screen_base = fbi->map_cpu + PAGE_SIZE;
diff --git a/drivers/video/fbdev/sis/init301.c b/drivers/video/fbdev/sis/init301.c
index 295e0dedaf1f..20f7234e809e 100644
--- a/drivers/video/fbdev/sis/init301.c
+++ b/drivers/video/fbdev/sis/init301.c
@@ -2151,17 +2151,15 @@ SiS_GetVCLK2Ptr(struct SiS_Private *SiS_Pr, unsigned short ModeNo, unsigned shor
 		unsigned short RefreshRateTableIndex)
 {
   unsigned short CRT2Index, VCLKIndex = 0, VCLKIndexGEN = 0, VCLKIndexGENCRT = 0;
-  unsigned short modeflag, resinfo, tempbx;
+  unsigned short resinfo, tempbx;
   const unsigned char *CHTVVCLKPtr = NULL;
 
   if(ModeNo <= 0x13) {
-     modeflag = SiS_Pr->SiS_SModeIDTable[ModeIdIndex].St_ModeFlag;
      resinfo = SiS_Pr->SiS_SModeIDTable[ModeIdIndex].St_ResInfo;
      CRT2Index = SiS_Pr->SiS_SModeIDTable[ModeIdIndex].St_CRT2CRTC;
      VCLKIndexGEN = (SiS_GetRegByte((SiS_Pr->SiS_P3ca+0x02)) >> 2) & 0x03;
      VCLKIndexGENCRT = VCLKIndexGEN;
   } else {
-     modeflag = SiS_Pr->SiS_EModeIDTable[ModeIdIndex].Ext_ModeFlag;
      resinfo = SiS_Pr->SiS_EModeIDTable[ModeIdIndex].Ext_RESINFO;
      CRT2Index = SiS_Pr->SiS_RefIndex[RefreshRateTableIndex].Ext_CRT2CRTC;
      VCLKIndexGEN = SiS_Pr->SiS_RefIndex[RefreshRateTableIndex].Ext_CRTVCLK;
@@ -7270,7 +7268,7 @@ SiS_ShiftXPos(struct SiS_Private *SiS_Pr, int shift)
 static void
 SiS_SetGroup4_C_ELV(struct SiS_Private *SiS_Pr, unsigned short ModeNo, unsigned short ModeIdIndex)
 {
-   unsigned short temp, temp1, resinfo = 0;
+   unsigned short temp, temp1;
    unsigned char  *ROMAddr = SiS_Pr->VirtualRomBase;
 
    if(!(SiS_Pr->SiS_VBType & VB_SIS30xCLV)) return;
@@ -7282,10 +7280,6 @@ SiS_SetGroup4_C_ELV(struct SiS_Private *SiS_Pr, unsigned short ModeNo, unsigned
       if(!(ROMAddr[0x61] & 0x04)) return;
    }
 
-   if(ModeNo > 0x13) {
-      resinfo = SiS_Pr->SiS_EModeIDTable[ModeIdIndex].Ext_RESINFO;
-   }
-
    SiS_SetRegOR(SiS_Pr->SiS_Part4Port,0x3a,0x08);
    temp = SiS_GetReg(SiS_Pr->SiS_Part4Port,0x3a);
    if(!(temp & 0x01)) {
diff --git a/drivers/video/fbdev/skeletonfb.c b/drivers/video/fbdev/skeletonfb.c
index fefde7c6add7..f948baa16d82 100644
--- a/drivers/video/fbdev/skeletonfb.c
+++ b/drivers/video/fbdev/skeletonfb.c
@@ -614,22 +614,6 @@ int xxxfb_cursor(struct fb_info *info, struct fb_cursor *cursor)
 }
 
 /**
- *	xxxfb_rotate -  NOT a required function. If your hardware
- *			supports rotation the whole screen then 
- *			you would provide a hook for this. 
- *
- *      @info: frame buffer structure that represents a single frame buffer
- *	@angle: The angle we rotate the screen.   
- *
- *      This operation is used to set or alter the properities of the
- *	cursor.
- */
-void xxxfb_rotate(struct fb_info *info, int angle)
-{
-/* Will be deprecated */
-}
-
-/**
  *	xxxfb_sync - NOT a required function. Normally the accel engine 
  *		     for a graphics card take a specific amount of time.
  *		     Often we have to wait for the accelerator to finish
@@ -665,7 +649,6 @@ static struct fb_ops xxxfb_ops = {
 	.fb_copyarea	= xxxfb_copyarea,	/* Needed !!! */
 	.fb_imageblit	= xxxfb_imageblit,	/* Needed !!! */
 	.fb_cursor	= xxxfb_cursor,		/* Optional !!! */
-	.fb_rotate	= xxxfb_rotate,
 	.fb_sync	= xxxfb_sync,
 	.fb_ioctl	= xxxfb_ioctl,
 	.fb_mmap	= xxxfb_mmap,
diff --git a/drivers/video/fbdev/sunxvr1000.c b/drivers/video/fbdev/sunxvr1000.c
index 08879bdfad35..fb37f6e05391 100644
--- a/drivers/video/fbdev/sunxvr1000.c
+++ b/drivers/video/fbdev/sunxvr1000.c
@@ -1,9 +1,10 @@
-/* sunxvr1000.c: Sun XVR-1000 driver for sparc64 systems
+/* sunxvr1000.c: Sun XVR-1000 fb driver for sparc64 systems
+ *
+ * License: GPL
  *
  * Copyright (C) 2010 David S. Miller (davem@davemloft.net)
  */
 
-#include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/fb.h>
 #include <linux/init.h>
@@ -173,36 +174,19 @@ err_out:
 	return err;
 }
 
-static int gfb_remove(struct platform_device *op)
-{
-	struct fb_info *info = dev_get_drvdata(&op->dev);
-	struct gfb_info *gp = info->par;
-
-	unregister_framebuffer(info);
-
-	iounmap(gp->fb_base);
-
-	of_iounmap(&op->resource[6], gp->fb_base, gp->fb_size);
-
-        framebuffer_release(info);
-
-	return 0;
-}
-
 static const struct of_device_id gfb_match[] = {
 	{
 		.name = "SUNW,gfb",
 	},
 	{},
 };
-MODULE_DEVICE_TABLE(of, ffb_match);
 
 static struct platform_driver gfb_driver = {
 	.probe		= gfb_probe,
-	.remove		= gfb_remove,
 	.driver = {
-		.name		= "gfb",
-		.of_match_table	= gfb_match,
+		.name			= "gfb",
+		.of_match_table		= gfb_match,
+		.suppress_bind_attrs	= true,
 	},
 };
 
@@ -213,16 +197,4 @@ static int __init gfb_init(void)
 
 	return platform_driver_register(&gfb_driver);
 }
-
-static void __exit gfb_exit(void)
-{
-	platform_driver_unregister(&gfb_driver);
-}
-
-module_init(gfb_init);
-module_exit(gfb_exit);
-
-MODULE_DESCRIPTION("framebuffer driver for Sun XVR-1000 graphics");
-MODULE_AUTHOR("David S. Miller <davem@davemloft.net>");
-MODULE_VERSION("1.0");
-MODULE_LICENSE("GPL");
+device_initcall(gfb_init);
diff --git a/drivers/video/fbdev/sunxvr2500.c b/drivers/video/fbdev/sunxvr2500.c
index 843b6bab0483..1a053292f2eb 100644
--- a/drivers/video/fbdev/sunxvr2500.c
+++ b/drivers/video/fbdev/sunxvr2500.c
@@ -1,9 +1,10 @@
-/* s3d.c: Sun 3DLABS XVR-2500 et al. driver for sparc64 systems
+/* sunxvr2500.c: Sun 3DLABS XVR-2500 et al. fb driver for sparc64 systems
+ *
+ * License: GPL
  *
  * Copyright (C) 2007 David S. Miller (davem@davemloft.net)
  */
 
-#include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/fb.h>
 #include <linux/pci.h>
@@ -219,22 +220,6 @@ err_out:
 	return err;
 }
 
-static void s3d_pci_unregister(struct pci_dev *pdev)
-{
-	struct fb_info *info = pci_get_drvdata(pdev);
-	struct s3d_info *sp = info->par;
-
-	unregister_framebuffer(info);
-
-	iounmap(sp->fb_base);
-
-	pci_release_region(pdev, 1);
-
-        framebuffer_release(info);
-
-	pci_disable_device(pdev);
-}
-
 static struct pci_device_id s3d_pci_table[] = {
 	{	PCI_DEVICE(PCI_VENDOR_ID_3DLABS, 0x002c),	},
 	{	PCI_DEVICE(PCI_VENDOR_ID_3DLABS, 0x002d),	},
@@ -248,10 +233,12 @@ static struct pci_device_id s3d_pci_table[] = {
 };
 
 static struct pci_driver s3d_driver = {
+	.driver = {
+		.suppress_bind_attrs = true,
+	},
 	.name		= "s3d",
 	.id_table	= s3d_pci_table,
 	.probe		= s3d_pci_register,
-	.remove		= s3d_pci_unregister,
 };
 
 static int __init s3d_init(void)
@@ -261,16 +248,4 @@ static int __init s3d_init(void)
 
 	return pci_register_driver(&s3d_driver);
 }
-
-static void __exit s3d_exit(void)
-{
-	pci_unregister_driver(&s3d_driver);
-}
-
-module_init(s3d_init);
-module_exit(s3d_exit);
-
-MODULE_DESCRIPTION("framebuffer driver for Sun XVR-2500 graphics");
-MODULE_AUTHOR("David S. Miller <davem@davemloft.net>");
-MODULE_VERSION("1.0");
-MODULE_LICENSE("GPL");
+device_initcall(s3d_init);
diff --git a/drivers/video/fbdev/sunxvr500.c b/drivers/video/fbdev/sunxvr500.c
index 387350d004df..dc0d886e4e7e 100644
--- a/drivers/video/fbdev/sunxvr500.c
+++ b/drivers/video/fbdev/sunxvr500.c
@@ -1,9 +1,10 @@
-/* sunxvr500.c: Sun 3DLABS XVR-500 Expert3D driver for sparc64 systems
+/* sunxvr500.c: Sun 3DLABS XVR-500 Expert3D fb driver for sparc64 systems
+ *
+ * License: GPL
  *
  * Copyright (C) 2007 David S. Miller (davem@davemloft.net)
  */
 
-#include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/fb.h>
 #include <linux/pci.h>
@@ -392,25 +393,6 @@ err_out:
 	return err;
 }
 
-static void e3d_pci_unregister(struct pci_dev *pdev)
-{
-	struct fb_info *info = pci_get_drvdata(pdev);
-	struct e3d_info *ep = info->par;
-
-	unregister_framebuffer(info);
-
-	iounmap(ep->ramdac);
-	iounmap(ep->fb_base);
-
-	pci_release_region(pdev, 0);
-	pci_release_region(pdev, 1);
-
-	fb_dealloc_cmap(&info->cmap);
-        framebuffer_release(info);
-
-	pci_disable_device(pdev);
-}
-
 static struct pci_device_id e3d_pci_table[] = {
 	{	PCI_DEVICE(PCI_VENDOR_ID_3DLABS, 0x7a0),	},
 	{	PCI_DEVICE(0x1091, 0x7a0),			},
@@ -434,10 +416,12 @@ static struct pci_device_id e3d_pci_table[] = {
 };
 
 static struct pci_driver e3d_driver = {
+	.driver = {
+		.suppress_bind_attrs = true,
+	},
 	.name		= "e3d",
 	.id_table	= e3d_pci_table,
 	.probe		= e3d_pci_register,
-	.remove		= e3d_pci_unregister,
 };
 
 static int __init e3d_init(void)
@@ -447,16 +431,4 @@ static int __init e3d_init(void)
 
 	return pci_register_driver(&e3d_driver);
 }
-
-static void __exit e3d_exit(void)
-{
-	pci_unregister_driver(&e3d_driver);
-}
-
-module_init(e3d_init);
-module_exit(e3d_exit);
-
-MODULE_DESCRIPTION("framebuffer driver for Sun XVR-500 graphics");
-MODULE_AUTHOR("David S. Miller <davem@davemloft.net>");
-MODULE_VERSION("1.0");
-MODULE_LICENSE("GPL");
+device_initcall(e3d_init);
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index f6bed86c17f9..d9a905827967 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -467,7 +467,7 @@ static const struct dev_pm_ops virtio_pci_pm_ops = {
 
 /* Qumranet donated their vendor ID for devices 0x1000 thru 0x10FF. */
 static const struct pci_device_id virtio_pci_id_table[] = {
-	{ PCI_DEVICE(0x1af4, PCI_ANY_ID) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_REDHAT_QUMRANET, PCI_ANY_ID) },
 	{ 0 }
 };
 
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index c0c11fad4611..7760fc1a2218 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -679,7 +679,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 
 	pci_read_config_dword(pci_dev,
 			      notify + offsetof(struct virtio_pci_notify_cap,
-						cap.length),
+						cap.offset),
 			      &notify_offset);
 
 	/* We don't know how many VQs we'll map, ahead of the time.
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 0f6d8515ba4f..80825a7e8e48 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -1569,6 +1569,17 @@ config WATCHDOG_RIO
 	  machines.  The watchdog timeout period is normally one minute but
 	  can be changed with a boot-time parameter.
 
+config WATCHDOG_SUN4V
+	tristate "Sun4v Watchdog support"
+	select WATCHDOG_CORE
+	depends on SPARC64
+	help
+	  Say Y here to support the hypervisor watchdog capability embedded
+	  in the SPARC sun4v architecture.
+
+	  To compile this driver as a module, choose M here. The module will
+	  be called sun4v_wdt.
+
 # XTENSA Architecture
 
 # Xen Architecture
diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile
index f566753256ab..f6a6a387c6c7 100644
--- a/drivers/watchdog/Makefile
+++ b/drivers/watchdog/Makefile
@@ -179,6 +179,7 @@ obj-$(CONFIG_SH_WDT) += shwdt.o
 
 obj-$(CONFIG_WATCHDOG_RIO)		+= riowd.o
 obj-$(CONFIG_WATCHDOG_CP1XXX)		+= cpwd.o
+obj-$(CONFIG_WATCHDOG_SUN4V)		+= sun4v_wdt.o
 
 # XTENSA Architecture
 
diff --git a/drivers/watchdog/sun4v_wdt.c b/drivers/watchdog/sun4v_wdt.c
new file mode 100644
index 000000000000..1467fe50a76f
--- /dev/null
+++ b/drivers/watchdog/sun4v_wdt.c
@@ -0,0 +1,191 @@
+/*
+ *	sun4v watchdog timer
+ *	(c) Copyright 2016 Oracle Corporation
+ *
+ *	Implement a simple watchdog driver using the built-in sun4v hypervisor
+ *	watchdog support. If time expires, the hypervisor stops or bounces
+ *	the guest domain.
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/watchdog.h>
+#include <asm/hypervisor.h>
+#include <asm/mdesc.h>
+
+#define WDT_TIMEOUT			60
+#define WDT_MAX_TIMEOUT			31536000
+#define WDT_MIN_TIMEOUT			1
+#define WDT_DEFAULT_RESOLUTION_MS	1000	/* 1 second */
+
+static unsigned int timeout;
+module_param(timeout, uint, 0);
+MODULE_PARM_DESC(timeout, "Watchdog timeout in seconds (default="
+	__MODULE_STRING(WDT_TIMEOUT) ")");
+
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, S_IRUGO);
+MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
+	__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
+
+static int sun4v_wdt_stop(struct watchdog_device *wdd)
+{
+	sun4v_mach_set_watchdog(0, NULL);
+
+	return 0;
+}
+
+static int sun4v_wdt_ping(struct watchdog_device *wdd)
+{
+	int hverr;
+
+	/*
+	 * HV watchdog timer will round up the timeout
+	 * passed in to the nearest multiple of the
+	 * watchdog resolution in milliseconds.
+	 */
+	hverr = sun4v_mach_set_watchdog(wdd->timeout * 1000, NULL);
+	if (hverr == HV_EINVAL)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int sun4v_wdt_set_timeout(struct watchdog_device *wdd,
+				 unsigned int timeout)
+{
+	wdd->timeout = timeout;
+
+	return 0;
+}
+
+static const struct watchdog_info sun4v_wdt_ident = {
+	.options =	WDIOF_SETTIMEOUT |
+			WDIOF_MAGICCLOSE |
+			WDIOF_KEEPALIVEPING,
+	.identity =	"sun4v hypervisor watchdog",
+	.firmware_version = 0,
+};
+
+static struct watchdog_ops sun4v_wdt_ops = {
+	.owner =	THIS_MODULE,
+	.start =	sun4v_wdt_ping,
+	.stop =		sun4v_wdt_stop,
+	.ping =		sun4v_wdt_ping,
+	.set_timeout =	sun4v_wdt_set_timeout,
+};
+
+static struct watchdog_device wdd = {
+	.info = &sun4v_wdt_ident,
+	.ops = &sun4v_wdt_ops,
+	.min_timeout = WDT_MIN_TIMEOUT,
+	.max_timeout = WDT_MAX_TIMEOUT,
+	.timeout = WDT_TIMEOUT,
+};
+
+static int __init sun4v_wdt_init(void)
+{
+	struct mdesc_handle *handle;
+	u64 node;
+	const u64 *value;
+	int err = 0;
+	unsigned long major = 1, minor = 1;
+
+	/*
+	 * There are 2 properties that can be set from the control
+	 * domain for the watchdog.
+	 * watchdog-resolution
+	 * watchdog-max-timeout
+	 *
+	 * We can expect a handle to be returned otherwise something
+	 * serious is wrong. Correct to return -ENODEV here.
+	 */
+
+	handle = mdesc_grab();
+	if (!handle)
+		return -ENODEV;
+
+	node = mdesc_node_by_name(handle, MDESC_NODE_NULL, "platform");
+	err = -ENODEV;
+	if (node == MDESC_NODE_NULL)
+		goto out_release;
+
+	/*
+	 * This is a safe way to validate if we are on the right
+	 * platform.
+	 */
+	if (sun4v_hvapi_register(HV_GRP_CORE, major, &minor))
+		goto out_hv_unreg;
+
+	/* Allow value of watchdog-resolution up to 1s (default) */
+	value = mdesc_get_property(handle, node, "watchdog-resolution", NULL);
+	err = -EINVAL;
+	if (value) {
+		if (*value == 0 ||
+		    *value > WDT_DEFAULT_RESOLUTION_MS)
+			goto out_hv_unreg;
+	}
+
+	value = mdesc_get_property(handle, node, "watchdog-max-timeout", NULL);
+	if (value) {
+		/*
+		 * If the property value (in ms) is smaller than
+		 * min_timeout, return -EINVAL.
+		 */
+		if (*value < wdd.min_timeout * 1000)
+			goto out_hv_unreg;
+
+		/*
+		 * If the property value is smaller than
+		 * default max_timeout  then set watchdog max_timeout to
+		 * the value of the property in seconds.
+		 */
+		if (*value < wdd.max_timeout * 1000)
+			wdd.max_timeout = *value  / 1000;
+	}
+
+	watchdog_init_timeout(&wdd, timeout, NULL);
+
+	watchdog_set_nowayout(&wdd, nowayout);
+
+	err = watchdog_register_device(&wdd);
+	if (err)
+		goto out_hv_unreg;
+
+	pr_info("initialized (timeout=%ds, nowayout=%d)\n",
+		 wdd.timeout, nowayout);
+
+	mdesc_release(handle);
+
+	return 0;
+
+out_hv_unreg:
+	sun4v_hvapi_unregister(HV_GRP_CORE);
+
+out_release:
+	mdesc_release(handle);
+	return err;
+}
+
+static void __exit sun4v_wdt_exit(void)
+{
+	sun4v_hvapi_unregister(HV_GRP_CORE);
+	watchdog_unregister_device(&wdd);
+}
+
+module_init(sun4v_wdt_init);
+module_exit(sun4v_wdt_exit);
+
+MODULE_AUTHOR("Wim Coekaerts <wim.coekaerts@oracle.com>");
+MODULE_DESCRIPTION("sun4v watchdog driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 73708acce3ca..979a8317204f 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -37,23 +37,30 @@ config XEN_BALLOON_MEMORY_HOTPLUG
 
 	  Memory could be hotplugged in following steps:
 
-	    1) dom0: xl mem-max <domU> <maxmem>
+	    1) target domain: ensure that memory auto online policy is in
+	       effect by checking /sys/devices/system/memory/auto_online_blocks
+	       file (should be 'online').
+
+	    2) control domain: xl mem-max <target-domain> <maxmem>
 	       where <maxmem> is >= requested memory size,
 
-	    2) dom0: xl mem-set <domU> <memory>
+	    3) control domain: xl mem-set <target-domain> <memory>
 	       where <memory> is requested memory size; alternatively memory
 	       could be added by writing proper value to
 	       /sys/devices/system/xen_memory/xen_memory0/target or
-	       /sys/devices/system/xen_memory/xen_memory0/target_kb on dumU,
+	       /sys/devices/system/xen_memory/xen_memory0/target_kb on the
+	       target domain.
 
-	    3) domU: for i in /sys/devices/system/memory/memory*/state; do \
-	               [ "`cat "$i"`" = offline ] && echo online > "$i"; done
+	  Alternatively, if memory auto onlining was not requested at step 1
+	  the newly added memory can be manually onlined in the target domain
+	  by doing the following:
 
-	  Memory could be onlined automatically on domU by adding following line to udev rules:
+		for i in /sys/devices/system/memory/memory*/state; do \
+		  [ "`cat "$i"`" = offline ] && echo online > "$i"; done
 
-	  SUBSYSTEM=="memory", ACTION=="add", RUN+="/bin/sh -c '[ -f /sys$devpath/state ] && echo online > /sys$devpath/state'"
+	  or by adding the following line to udev rules:
 
-	  In that case step 3 should be omitted.
+	  SUBSYSTEM=="memory", ACTION=="add", RUN+="/bin/sh -c '[ -f /sys$devpath/state ] && echo online > /sys$devpath/state'"
 
 config XEN_BALLOON_MEMORY_HOTPLUG_LIMIT
 	int "Hotplugged memory limit (in GiB) for a PV guest"
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 12eab503efd1..7c8a2cf16f58 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -257,7 +257,7 @@ static struct resource *additional_memory_resource(phys_addr_t size)
 		return NULL;
 
 	res->name = "System RAM";
-	res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
 	ret = allocate_resource(&iomem_resource, res,
 				size, 0, -1,
@@ -338,7 +338,16 @@ static enum bp_state reserve_additional_memory(void)
 	}
 #endif
 
-	rc = add_memory_resource(nid, resource);
+	/*
+	 * add_memory_resource() will call online_pages() which in its turn
+	 * will call xen_online_page() callback causing deadlock if we don't
+	 * release balloon_mutex here. Unlocking here is safe because the
+	 * callers drop the mutex before trying again.
+	 */
+	mutex_unlock(&balloon_mutex);
+	rc = add_memory_resource(nid, resource, memhp_auto_online);
+	mutex_lock(&balloon_mutex);
+
 	if (rc) {
 		pr_warn("Cannot add additional memory (%i)\n", rc);
 		goto err;
diff --git a/drivers/xen/events/events_2l.c b/drivers/xen/events/events_2l.c
index 7dd46312c180..403fe3955393 100644
--- a/drivers/xen/events/events_2l.c
+++ b/drivers/xen/events/events_2l.c
@@ -38,8 +38,9 @@
 /* Find the first set bit in a evtchn mask */
 #define EVTCHN_FIRST_BIT(w) find_first_bit(BM(&(w)), BITS_PER_EVTCHN_WORD)
 
-static DEFINE_PER_CPU(xen_ulong_t [EVTCHN_2L_NR_CHANNELS/BITS_PER_EVTCHN_WORD],
-		      cpu_evtchn_mask);
+#define EVTCHN_MASK_SIZE (EVTCHN_2L_NR_CHANNELS/BITS_PER_EVTCHN_WORD)
+
+static DEFINE_PER_CPU(xen_ulong_t [EVTCHN_MASK_SIZE], cpu_evtchn_mask);
 
 static unsigned evtchn_2l_max_channels(void)
 {
diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c
index 73dafdc494aa..fb0221434f81 100644
--- a/drivers/xen/xen-pciback/pciback_ops.c
+++ b/drivers/xen/xen-pciback/pciback_ops.c
@@ -227,8 +227,9 @@ int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev,
 	/*
 	 * PCI_COMMAND_MEMORY must be enabled, otherwise we may not be able
 	 * to access the BARs where the MSI-X entries reside.
+	 * But VF devices are unique in which the PF needs to be checked.
 	 */
-	pci_read_config_word(dev, PCI_COMMAND, &cmd);
+	pci_read_config_word(pci_physfn(dev), PCI_COMMAND, &cmd);
 	if (dev->msi_enabled || !(cmd & PCI_COMMAND_MEMORY))
 		return -ENXIO;
 
@@ -332,6 +333,9 @@ void xen_pcibk_do_op(struct work_struct *data)
 	struct xen_pcibk_dev_data *dev_data = NULL;
 	struct xen_pci_op *op = &pdev->op;
 	int test_intx = 0;
+#ifdef CONFIG_PCI_MSI
+	unsigned int nr = 0;
+#endif
 
 	*op = pdev->sh_info->op;
 	barrier();
@@ -360,6 +364,7 @@ void xen_pcibk_do_op(struct work_struct *data)
 			op->err = xen_pcibk_disable_msi(pdev, dev, op);
 			break;
 		case XEN_PCI_OP_enable_msix:
+			nr = op->value;
 			op->err = xen_pcibk_enable_msix(pdev, dev, op);
 			break;
 		case XEN_PCI_OP_disable_msix:
@@ -382,7 +387,7 @@ void xen_pcibk_do_op(struct work_struct *data)
 	if (op->cmd == XEN_PCI_OP_enable_msix && op->err == 0) {
 		unsigned int i;
 
-		for (i = 0; i < op->value; i++)
+		for (i = 0; i < nr; i++)
 			pdev->sh_info->op.msix_entries[i].vector =
 				op->msix_entries[i].vector;
 	}
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index ad4eb1024d1f..c46ee189466f 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -849,15 +849,31 @@ static int scsiback_map(struct vscsibk_info *info)
 }
 
 /*
+  Check for a translation entry being present
+*/
+static struct v2p_entry *scsiback_chk_translation_entry(
+	struct vscsibk_info *info, struct ids_tuple *v)
+{
+	struct list_head *head = &(info->v2p_entry_lists);
+	struct v2p_entry *entry;
+
+	list_for_each_entry(entry, head, l)
+		if ((entry->v.chn == v->chn) &&
+		    (entry->v.tgt == v->tgt) &&
+		    (entry->v.lun == v->lun))
+			return entry;
+
+	return NULL;
+}
+
+/*
   Add a new translation entry
 */
 static int scsiback_add_translation_entry(struct vscsibk_info *info,
 					  char *phy, struct ids_tuple *v)
 {
 	int err = 0;
-	struct v2p_entry *entry;
 	struct v2p_entry *new;
-	struct list_head *head = &(info->v2p_entry_lists);
 	unsigned long flags;
 	char *lunp;
 	unsigned long long unpacked_lun;
@@ -917,15 +933,10 @@ static int scsiback_add_translation_entry(struct vscsibk_info *info,
 	spin_lock_irqsave(&info->v2p_lock, flags);
 
 	/* Check double assignment to identical virtual ID */
-	list_for_each_entry(entry, head, l) {
-		if ((entry->v.chn == v->chn) &&
-		    (entry->v.tgt == v->tgt) &&
-		    (entry->v.lun == v->lun)) {
-			pr_warn("Virtual ID is already used. Assignment was not performed.\n");
-			err = -EEXIST;
-			goto out;
-		}
-
+	if (scsiback_chk_translation_entry(info, v)) {
+		pr_warn("Virtual ID is already used. Assignment was not performed.\n");
+		err = -EEXIST;
+		goto out;
 	}
 
 	/* Create a new translation entry and add to the list */
@@ -933,18 +944,18 @@ static int scsiback_add_translation_entry(struct vscsibk_info *info,
 	new->v = *v;
 	new->tpg = tpg;
 	new->lun = unpacked_lun;
-	list_add_tail(&new->l, head);
+	list_add_tail(&new->l, &info->v2p_entry_lists);
 
 out:
 	spin_unlock_irqrestore(&info->v2p_lock, flags);
 
 out_free:
-	mutex_lock(&tpg->tv_tpg_mutex);
-	tpg->tv_tpg_fe_count--;
-	mutex_unlock(&tpg->tv_tpg_mutex);
-
-	if (err)
+	if (err) {
+		mutex_lock(&tpg->tv_tpg_mutex);
+		tpg->tv_tpg_fe_count--;
+		mutex_unlock(&tpg->tv_tpg_mutex);
 		kfree(new);
+	}
 
 	return err;
 }
@@ -956,39 +967,40 @@ static void __scsiback_del_translation_entry(struct v2p_entry *entry)
 }
 
 /*
-  Delete the translation entry specfied
+  Delete the translation entry specified
 */
 static int scsiback_del_translation_entry(struct vscsibk_info *info,
 					  struct ids_tuple *v)
 {
 	struct v2p_entry *entry;
-	struct list_head *head = &(info->v2p_entry_lists);
 	unsigned long flags;
+	int ret = 0;
 
 	spin_lock_irqsave(&info->v2p_lock, flags);
 	/* Find out the translation entry specified */
-	list_for_each_entry(entry, head, l) {
-		if ((entry->v.chn == v->chn) &&
-		    (entry->v.tgt == v->tgt) &&
-		    (entry->v.lun == v->lun)) {
-			goto found;
-		}
-	}
-
-	spin_unlock_irqrestore(&info->v2p_lock, flags);
-	return 1;
-
-found:
-	/* Delete the translation entry specfied */
-	__scsiback_del_translation_entry(entry);
+	entry = scsiback_chk_translation_entry(info, v);
+	if (entry)
+		__scsiback_del_translation_entry(entry);
+	else
+		ret = -ENOENT;
 
 	spin_unlock_irqrestore(&info->v2p_lock, flags);
-	return 0;
+	return ret;
 }
 
 static void scsiback_do_add_lun(struct vscsibk_info *info, const char *state,
 				char *phy, struct ids_tuple *vir, int try)
 {
+	struct v2p_entry *entry;
+	unsigned long flags;
+
+	if (try) {
+		spin_lock_irqsave(&info->v2p_lock, flags);
+		entry = scsiback_chk_translation_entry(info, vir);
+		spin_unlock_irqrestore(&info->v2p_lock, flags);
+		if (entry)
+			return;
+	}
 	if (!scsiback_add_translation_entry(info, phy, vir)) {
 		if (xenbus_printf(XBT_NIL, info->dev->nodename, state,
 				  "%d", XenbusStateInitialised)) {
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 9433e46518c8..912b64edb42b 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -188,6 +188,8 @@ static int queue_reply(struct list_head *queue, const void *data, size_t len)
 
 	if (len == 0)
 		return 0;
+	if (len > XENSTORE_PAYLOAD_MAX)
+		return -EINVAL;
 
 	rb = kmalloc(sizeof(*rb) + len, GFP_KERNEL);
 	if (rb == NULL)
diff --git a/drivers/zorro/zorro-sysfs.c b/drivers/zorro/zorro-sysfs.c
index 36b210f9b6b2..9282dbf5abdb 100644
--- a/drivers/zorro/zorro-sysfs.c
+++ b/drivers/zorro/zorro-sysfs.c
@@ -65,8 +65,7 @@ static ssize_t zorro_read_config(struct file *filp, struct kobject *kobj,
 				 struct bin_attribute *bin_attr,
 				 char *buf, loff_t off, size_t count)
 {
-	struct zorro_dev *z = to_zorro_dev(container_of(kobj, struct device,
-					   kobj));
+	struct zorro_dev *z = to_zorro_dev(kobj_to_dev(kobj));
 	struct ConfigDev cd;
 
 	/* Construct a ConfigDev */
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 0548c53f41d5..22fc7c802d69 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -511,8 +511,6 @@ affs_do_readpage_ofs(struct page *page, unsigned to)
 	pr_debug("%s(%lu, %ld, 0, %d)\n", __func__, inode->i_ino,
 		 page->index, to);
 	BUG_ON(to > PAGE_CACHE_SIZE);
-	kmap(page);
-	data = page_address(page);
 	bsize = AFFS_SB(sb)->s_data_blksize;
 	tmp = page->index << PAGE_CACHE_SHIFT;
 	bidx = tmp / bsize;
@@ -524,14 +522,15 @@ affs_do_readpage_ofs(struct page *page, unsigned to)
 			return PTR_ERR(bh);
 		tmp = min(bsize - boff, to - pos);
 		BUG_ON(pos + tmp > to || tmp > bsize);
+		data = kmap_atomic(page);
 		memcpy(data + pos, AFFS_DATA(bh) + boff, tmp);
+		kunmap_atomic(data);
 		affs_brelse(bh);
 		bidx++;
 		pos += tmp;
 		boff = 0;
 	}
 	flush_dcache_page(page);
-	kunmap(page);
 	return 0;
 }
 
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index c37149b929be..f0d268b97d19 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -1,15 +1,11 @@
-/* -*- c -*- ------------------------------------------------------------- *
- *   
- * linux/fs/autofs/autofs_i.h
- *
- *   Copyright 1997-1998 Transmeta Corporation - All Rights Reserved
- *   Copyright 2005-2006 Ian Kent <raven@themaw.net>
+/*
+ *  Copyright 1997-1998 Transmeta Corporation - All Rights Reserved
+ *  Copyright 2005-2006 Ian Kent <raven@themaw.net>
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ----------------------------------------------------------------------- */
+ */
 
 /* Internal header file for autofs */
 
@@ -35,28 +31,23 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <asm/current.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /* #define DEBUG */
 
-#define DPRINTK(fmt, ...)				\
-	pr_debug("pid %d: %s: " fmt "\n",		\
-		current->pid, __func__, ##__VA_ARGS__)
-
-#define AUTOFS_WARN(fmt, ...)				\
-	printk(KERN_WARNING "pid %d: %s: " fmt "\n",	\
-		current->pid, __func__, ##__VA_ARGS__)
-
-#define AUTOFS_ERROR(fmt, ...)				\
-	printk(KERN_ERR "pid %d: %s: " fmt "\n",	\
-		current->pid, __func__, ##__VA_ARGS__)
-
-/* Unified info structure.  This is pointed to by both the dentry and
-   inode structures.  Each file in the filesystem has an instance of this
-   structure.  It holds a reference to the dentry, so dentries are never
-   flushed while the file exists.  All name lookups are dealt with at the
-   dentry level, although the filesystem can interfere in the validation
-   process.  Readdir is implemented by traversing the dentry lists. */
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+#define pr_fmt(fmt) KBUILD_MODNAME ":pid:%d:%s: " fmt, current->pid, __func__
+
+/*
+ * Unified info structure.  This is pointed to by both the dentry and
+ * inode structures.  Each file in the filesystem has an instance of this
+ * structure.  It holds a reference to the dentry, so dentries are never
+ * flushed while the file exists.  All name lookups are dealt with at the
+ * dentry level, although the filesystem can interfere in the validation
+ * process.  Readdir is implemented by traversing the dentry lists.
+ */
 struct autofs_info {
 	struct dentry	*dentry;
 	struct inode	*inode;
@@ -78,7 +69,7 @@ struct autofs_info {
 	kgid_t gid;
 };
 
-#define AUTOFS_INF_EXPIRING	(1<<0) /* dentry is in the process of expiring */
+#define AUTOFS_INF_EXPIRING	(1<<0) /* dentry in the process of expiring */
 #define AUTOFS_INF_NO_RCU	(1<<1) /* the dentry is being considered
 					* for expiry, so RCU_walk is
 					* not permitted
@@ -140,10 +131,11 @@ static inline struct autofs_info *autofs4_dentry_ino(struct dentry *dentry)
 }
 
 /* autofs4_oz_mode(): do we see the man behind the curtain?  (The
-   processes which do manipulations for us in user space sees the raw
-   filesystem without "magic".) */
-
-static inline int autofs4_oz_mode(struct autofs_sb_info *sbi) {
+ * processes which do manipulations for us in user space sees the raw
+ * filesystem without "magic".)
+ */
+static inline int autofs4_oz_mode(struct autofs_sb_info *sbi)
+{
 	return sbi->catatonic || task_pgrp(current) == sbi->oz_pgrp;
 }
 
@@ -154,12 +146,12 @@ void autofs4_free_ino(struct autofs_info *);
 int is_autofs4_dentry(struct dentry *);
 int autofs4_expire_wait(struct dentry *dentry, int rcu_walk);
 int autofs4_expire_run(struct super_block *, struct vfsmount *,
-			struct autofs_sb_info *,
-			struct autofs_packet_expire __user *);
+		       struct autofs_sb_info *,
+		       struct autofs_packet_expire __user *);
 int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 			    struct autofs_sb_info *sbi, int when);
 int autofs4_expire_multi(struct super_block *, struct vfsmount *,
-			struct autofs_sb_info *, int __user *);
+			 struct autofs_sb_info *, int __user *);
 struct dentry *autofs4_expire_direct(struct super_block *sb,
 				     struct vfsmount *mnt,
 				     struct autofs_sb_info *sbi, int how);
@@ -224,8 +216,8 @@ static inline int autofs_prepare_pipe(struct file *pipe)
 
 /* Queue management functions */
 
-int autofs4_wait(struct autofs_sb_info *,struct dentry *, enum autofs_notify);
-int autofs4_wait_release(struct autofs_sb_info *,autofs_wqt_t,int);
+int autofs4_wait(struct autofs_sb_info *, struct dentry *, enum autofs_notify);
+int autofs4_wait_release(struct autofs_sb_info *, autofs_wqt_t, int);
 void autofs4_catatonic_mode(struct autofs_sb_info *);
 
 static inline u32 autofs4_get_dev(struct autofs_sb_info *sbi)
@@ -242,37 +234,37 @@ static inline void __autofs4_add_expiring(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+
 	if (ino) {
 		if (list_empty(&ino->expiring))
 			list_add(&ino->expiring, &sbi->expiring_list);
 	}
-	return;
 }
 
 static inline void autofs4_add_expiring(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+
 	if (ino) {
 		spin_lock(&sbi->lookup_lock);
 		if (list_empty(&ino->expiring))
 			list_add(&ino->expiring, &sbi->expiring_list);
 		spin_unlock(&sbi->lookup_lock);
 	}
-	return;
 }
 
 static inline void autofs4_del_expiring(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+
 	if (ino) {
 		spin_lock(&sbi->lookup_lock);
 		if (!list_empty(&ino->expiring))
 			list_del_init(&ino->expiring);
 		spin_unlock(&sbi->lookup_lock);
 	}
-	return;
 }
 
 extern void autofs4_kill_sb(struct super_block *);
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index ac7d921ed984..c7fcc7438843 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -72,13 +72,13 @@ static int check_dev_ioctl_version(int cmd, struct autofs_dev_ioctl *param)
 {
 	int err = 0;
 
-	if ((AUTOFS_DEV_IOCTL_VERSION_MAJOR != param->ver_major) ||
-	    (AUTOFS_DEV_IOCTL_VERSION_MINOR < param->ver_minor)) {
-		AUTOFS_WARN("ioctl control interface version mismatch: "
-		     "kernel(%u.%u), user(%u.%u), cmd(%d)",
-		     AUTOFS_DEV_IOCTL_VERSION_MAJOR,
-		     AUTOFS_DEV_IOCTL_VERSION_MINOR,
-		     param->ver_major, param->ver_minor, cmd);
+	if ((param->ver_major != AUTOFS_DEV_IOCTL_VERSION_MAJOR) ||
+	    (param->ver_minor > AUTOFS_DEV_IOCTL_VERSION_MINOR)) {
+		pr_warn("ioctl control interface version mismatch: "
+			"kernel(%u.%u), user(%u.%u), cmd(%d)\n",
+			AUTOFS_DEV_IOCTL_VERSION_MAJOR,
+			AUTOFS_DEV_IOCTL_VERSION_MINOR,
+			param->ver_major, param->ver_minor, cmd);
 		err = -EINVAL;
 	}
 
@@ -93,7 +93,8 @@ static int check_dev_ioctl_version(int cmd, struct autofs_dev_ioctl *param)
  * Copy parameter control struct, including a possible path allocated
  * at the end of the struct.
  */
-static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *in)
+static struct autofs_dev_ioctl *
+		copy_dev_ioctl(struct autofs_dev_ioctl __user *in)
 {
 	struct autofs_dev_ioctl tmp, *res;
 
@@ -116,7 +117,6 @@ static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *i
 static inline void free_dev_ioctl(struct autofs_dev_ioctl *param)
 {
 	kfree(param);
-	return;
 }
 
 /*
@@ -129,24 +129,24 @@ static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param)
 
 	err = check_dev_ioctl_version(cmd, param);
 	if (err) {
-		AUTOFS_WARN("invalid device control module version "
-		     "supplied for cmd(0x%08x)", cmd);
+		pr_warn("invalid device control module version "
+			"supplied for cmd(0x%08x)\n", cmd);
 		goto out;
 	}
 
 	if (param->size > sizeof(*param)) {
 		err = invalid_str(param->path, param->size - sizeof(*param));
 		if (err) {
-			AUTOFS_WARN(
-			  "path string terminator missing for cmd(0x%08x)",
+			pr_warn(
+			  "path string terminator missing for cmd(0x%08x)\n",
 			  cmd);
 			goto out;
 		}
 
 		err = check_name(param->path);
 		if (err) {
-			AUTOFS_WARN("invalid path supplied for cmd(0x%08x)",
-				    cmd);
+			pr_warn("invalid path supplied for cmd(0x%08x)\n",
+				cmd);
 			goto out;
 		}
 	}
@@ -197,7 +197,9 @@ static int find_autofs_mount(const char *pathname,
 			     void *data)
 {
 	struct path path;
-	int err = kern_path_mountpoint(AT_FDCWD, pathname, &path, 0);
+	int err;
+
+	err = kern_path_mountpoint(AT_FDCWD, pathname, &path, 0);
 	if (err)
 		return err;
 	err = -ENOENT;
@@ -225,6 +227,7 @@ static int test_by_dev(struct path *path, void *p)
 static int test_by_type(struct path *path, void *p)
 {
 	struct autofs_info *ino = autofs4_dentry_ino(path->dentry);
+
 	return ino && ino->sbi->type & *(unsigned *)p;
 }
 
@@ -370,7 +373,7 @@ static int autofs_dev_ioctl_setpipefd(struct file *fp,
 		new_pid = get_task_pid(current, PIDTYPE_PGID);
 
 		if (ns_of_pid(new_pid) != ns_of_pid(sbi->oz_pgrp)) {
-			AUTOFS_WARN("Not allowed to change PID namespace");
+			pr_warn("not allowed to change PID namespace\n");
 			err = -EINVAL;
 			goto out;
 		}
@@ -456,8 +459,10 @@ static int autofs_dev_ioctl_requester(struct file *fp,
 		err = 0;
 		autofs4_expire_wait(path.dentry, 0);
 		spin_lock(&sbi->fs_lock);
-		param->requester.uid = from_kuid_munged(current_user_ns(), ino->uid);
-		param->requester.gid = from_kgid_munged(current_user_ns(), ino->gid);
+		param->requester.uid =
+			from_kuid_munged(current_user_ns(), ino->uid);
+		param->requester.gid =
+			from_kgid_munged(current_user_ns(), ino->gid);
 		spin_unlock(&sbi->fs_lock);
 	}
 	path_put(&path);
@@ -619,7 +624,8 @@ static ioctl_fn lookup_dev_ioctl(unsigned int cmd)
 }
 
 /* ioctl dispatcher */
-static int _autofs_dev_ioctl(unsigned int command, struct autofs_dev_ioctl __user *user)
+static int _autofs_dev_ioctl(unsigned int command,
+			     struct autofs_dev_ioctl __user *user)
 {
 	struct autofs_dev_ioctl *param;
 	struct file *fp;
@@ -655,7 +661,7 @@ static int _autofs_dev_ioctl(unsigned int command, struct autofs_dev_ioctl __use
 
 	fn = lookup_dev_ioctl(cmd);
 	if (!fn) {
-		AUTOFS_WARN("unknown command 0x%08x", command);
+		pr_warn("unknown command 0x%08x\n", command);
 		return -ENOTTY;
 	}
 
@@ -711,6 +717,7 @@ out:
 static long autofs_dev_ioctl(struct file *file, uint command, ulong u)
 {
 	int err;
+
 	err = _autofs_dev_ioctl(command, (struct autofs_dev_ioctl __user *) u);
 	return (long) err;
 }
@@ -733,8 +740,8 @@ static const struct file_operations _dev_ioctl_fops = {
 
 static struct miscdevice _autofs_dev_ioctl_misc = {
 	.minor		= AUTOFS_MINOR,
-	.name  		= AUTOFS_DEVICE_NAME,
-	.fops  		= &_dev_ioctl_fops
+	.name		= AUTOFS_DEVICE_NAME,
+	.fops		= &_dev_ioctl_fops
 };
 
 MODULE_ALIAS_MISCDEV(AUTOFS_MINOR);
@@ -747,7 +754,7 @@ int __init autofs_dev_ioctl_init(void)
 
 	r = misc_register(&_autofs_dev_ioctl_misc);
 	if (r) {
-		AUTOFS_ERROR("misc_register failed for control device");
+		pr_err("misc_register failed for control device\n");
 		return r;
 	}
 
@@ -757,6 +764,4 @@ int __init autofs_dev_ioctl_init(void)
 void autofs_dev_ioctl_exit(void)
 {
 	misc_deregister(&_autofs_dev_ioctl_misc);
-	return;
 }
-
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 1cebc3c52fa5..9510d8d2e9cd 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -1,16 +1,12 @@
-/* -*- c -*- --------------------------------------------------------------- *
- *
- * linux/fs/autofs/expire.c
- *
- *  Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
- *  Copyright 1999-2000 Jeremy Fitzhardinge <jeremy@goop.org>
- *  Copyright 2001-2006 Ian Kent <raven@themaw.net>
+/*
+ * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
+ * Copyright 1999-2000 Jeremy Fitzhardinge <jeremy@goop.org>
+ * Copyright 2001-2006 Ian Kent <raven@themaw.net>
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ------------------------------------------------------------------------- */
+ */
 
 #include "autofs_i.h"
 
@@ -18,7 +14,7 @@ static unsigned long now;
 
 /* Check if a dentry can be expired */
 static inline int autofs4_can_expire(struct dentry *dentry,
-					unsigned long timeout, int do_now)
+				     unsigned long timeout, int do_now)
 {
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 
@@ -41,7 +37,7 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry)
 	struct path path = {.mnt = mnt, .dentry = dentry};
 	int status = 1;
 
-	DPRINTK("dentry %p %pd", dentry, dentry);
+	pr_debug("dentry %p %pd\n", dentry, dentry);
 
 	path_get(&path);
 
@@ -58,14 +54,16 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry)
 
 	/* Update the expiry counter if fs is busy */
 	if (!may_umount_tree(path.mnt)) {
-		struct autofs_info *ino = autofs4_dentry_ino(top);
+		struct autofs_info *ino;
+
+		ino = autofs4_dentry_ino(top);
 		ino->last_used = jiffies;
 		goto done;
 	}
 
 	status = 0;
 done:
-	DPRINTK("returning = %d", status);
+	pr_debug("returning = %d\n", status);
 	path_put(&path);
 	return status;
 }
@@ -74,7 +72,7 @@ done:
  * Calculate and dget next entry in the subdirs list under root.
  */
 static struct dentry *get_next_positive_subdir(struct dentry *prev,
-						struct dentry *root)
+					       struct dentry *root)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb);
 	struct list_head *next;
@@ -121,7 +119,7 @@ cont:
  * Calculate and dget next entry in top down tree traversal.
  */
 static struct dentry *get_next_positive_dentry(struct dentry *prev,
-						struct dentry *root)
+					       struct dentry *root)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb);
 	struct list_head *next;
@@ -187,15 +185,17 @@ again:
  * autofs submounts.
  */
 static int autofs4_direct_busy(struct vfsmount *mnt,
-				struct dentry *top,
-				unsigned long timeout,
-				int do_now)
+			       struct dentry *top,
+			       unsigned long timeout,
+			       int do_now)
 {
-	DPRINTK("top %p %pd", top, top);
+	pr_debug("top %p %pd\n", top, top);
 
 	/* If it's busy update the expiry counters */
 	if (!may_umount_tree(mnt)) {
-		struct autofs_info *ino = autofs4_dentry_ino(top);
+		struct autofs_info *ino;
+
+		ino = autofs4_dentry_ino(top);
 		if (ino)
 			ino->last_used = jiffies;
 		return 1;
@@ -208,7 +208,8 @@ static int autofs4_direct_busy(struct vfsmount *mnt,
 	return 0;
 }
 
-/* Check a directory tree of mount points for busyness
+/*
+ * Check a directory tree of mount points for busyness
  * The tree is not busy iff no mountpoints are busy
  */
 static int autofs4_tree_busy(struct vfsmount *mnt,
@@ -219,7 +220,7 @@ static int autofs4_tree_busy(struct vfsmount *mnt,
 	struct autofs_info *top_ino = autofs4_dentry_ino(top);
 	struct dentry *p;
 
-	DPRINTK("top %p %pd", top, top);
+	pr_debug("top %p %pd\n", top, top);
 
 	/* Negative dentry - give up */
 	if (!simple_positive(top))
@@ -227,7 +228,7 @@ static int autofs4_tree_busy(struct vfsmount *mnt,
 
 	p = NULL;
 	while ((p = get_next_positive_dentry(p, top))) {
-		DPRINTK("dentry %p %pd", p, p);
+		pr_debug("dentry %p %pd\n", p, p);
 
 		/*
 		 * Is someone visiting anywhere in the subtree ?
@@ -273,11 +274,11 @@ static struct dentry *autofs4_check_leaves(struct vfsmount *mnt,
 {
 	struct dentry *p;
 
-	DPRINTK("parent %p %pd", parent, parent);
+	pr_debug("parent %p %pd\n", parent, parent);
 
 	p = NULL;
 	while ((p = get_next_positive_dentry(p, parent))) {
-		DPRINTK("dentry %p %pd", p, p);
+		pr_debug("dentry %p %pd\n", p, p);
 
 		if (d_mountpoint(p)) {
 			/* Can we umount this guy */
@@ -362,7 +363,7 @@ static struct dentry *should_expire(struct dentry *dentry,
 	 *	   offset (autofs-5.0+).
 	 */
 	if (d_mountpoint(dentry)) {
-		DPRINTK("checking mountpoint %p %pd", dentry, dentry);
+		pr_debug("checking mountpoint %p %pd\n", dentry, dentry);
 
 		/* Can we umount this guy */
 		if (autofs4_mount_busy(mnt, dentry))
@@ -375,7 +376,7 @@ static struct dentry *should_expire(struct dentry *dentry,
 	}
 
 	if (d_really_is_positive(dentry) && d_is_symlink(dentry)) {
-		DPRINTK("checking symlink %p %pd", dentry, dentry);
+		pr_debug("checking symlink %p %pd\n", dentry, dentry);
 		/*
 		 * A symlink can't be "busy" in the usual sense so
 		 * just check last used for expire timeout.
@@ -404,6 +405,7 @@ static struct dentry *should_expire(struct dentry *dentry,
 	} else {
 		/* Path walk currently on this dentry? */
 		struct dentry *expired;
+
 		ino_count = atomic_read(&ino->count) + 1;
 		if (d_count(dentry) > ino_count)
 			return NULL;
@@ -471,7 +473,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 	return NULL;
 
 found:
-	DPRINTK("returning %p %pd", expired, expired);
+	pr_debug("returning %p %pd\n", expired, expired);
 	ino->flags |= AUTOFS_INF_EXPIRING;
 	smp_mb();
 	ino->flags &= ~AUTOFS_INF_NO_RCU;
@@ -503,12 +505,12 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
 	if (ino->flags & AUTOFS_INF_EXPIRING) {
 		spin_unlock(&sbi->fs_lock);
 
-		DPRINTK("waiting for expire %p name=%pd", dentry, dentry);
+		pr_debug("waiting for expire %p name=%pd\n", dentry, dentry);
 
 		status = autofs4_wait(sbi, dentry, NFY_NONE);
 		wait_for_completion(&ino->expire_complete);
 
-		DPRINTK("expire done status=%d", status);
+		pr_debug("expire done status=%d\n", status);
 
 		if (d_unhashed(dentry))
 			return -EAGAIN;
@@ -522,21 +524,22 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
 
 /* Perform an expiry operation */
 int autofs4_expire_run(struct super_block *sb,
-		      struct vfsmount *mnt,
-		      struct autofs_sb_info *sbi,
-		      struct autofs_packet_expire __user *pkt_p)
+		       struct vfsmount *mnt,
+		       struct autofs_sb_info *sbi,
+		       struct autofs_packet_expire __user *pkt_p)
 {
 	struct autofs_packet_expire pkt;
 	struct autofs_info *ino;
 	struct dentry *dentry;
 	int ret = 0;
 
-	memset(&pkt,0,sizeof pkt);
+	memset(&pkt, 0, sizeof(pkt));
 
 	pkt.hdr.proto_version = sbi->version;
 	pkt.hdr.type = autofs_ptype_expire;
 
-	if ((dentry = autofs4_expire_indirect(sb, mnt, sbi, 0)) == NULL)
+	dentry = autofs4_expire_indirect(sb, mnt, sbi, 0);
+	if (!dentry)
 		return -EAGAIN;
 
 	pkt.len = dentry->d_name.len;
@@ -544,7 +547,7 @@ int autofs4_expire_run(struct super_block *sb,
 	pkt.name[pkt.len] = '\0';
 	dput(dentry);
 
-	if ( copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)) )
+	if (copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)))
 		ret = -EFAULT;
 
 	spin_lock(&sbi->fs_lock);
@@ -573,7 +576,8 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 		struct autofs_info *ino = autofs4_dentry_ino(dentry);
 
 		/* This is synchronous because it makes the daemon a
-                   little easier */
+		 * little easier
+		 */
 		ret = autofs4_wait(sbi, dentry, NFY_EXPIRE);
 
 		spin_lock(&sbi->fs_lock);
@@ -588,8 +592,10 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 	return ret;
 }
 
-/* Call repeatedly until it returns -EAGAIN, meaning there's nothing
-   more to be done */
+/*
+ * Call repeatedly until it returns -EAGAIN, meaning there's nothing
+ * more to be done.
+ */
 int autofs4_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 			struct autofs_sb_info *sbi, int __user *arg)
 {
diff --git a/fs/autofs4/init.c b/fs/autofs4/init.c
index b3db517e89ec..8cf0e63389ae 100644
--- a/fs/autofs4/init.c
+++ b/fs/autofs4/init.c
@@ -1,14 +1,10 @@
-/* -*- c -*- --------------------------------------------------------------- *
- *
- * linux/fs/autofs/init.c
- *
- *  Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
+/*
+ * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ------------------------------------------------------------------------- */
+ */
 
 #include <linux/module.h>
 #include <linux/init.h>
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index a3ae0b2aeb5a..61b21051bd5a 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -1,15 +1,11 @@
-/* -*- c -*- --------------------------------------------------------------- *
- *
- * linux/fs/autofs/inode.c
- *
- *  Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
- *  Copyright 2005-2006 Ian Kent <raven@themaw.net>
+/*
+ * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
+ * Copyright 2005-2006 Ian Kent <raven@themaw.net>
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ------------------------------------------------------------------------- */
+ */
 
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -24,7 +20,9 @@
 
 struct autofs_info *autofs4_new_ino(struct autofs_sb_info *sbi)
 {
-	struct autofs_info *ino = kzalloc(sizeof(*ino), GFP_KERNEL);
+	struct autofs_info *ino;
+
+	ino = kzalloc(sizeof(*ino), GFP_KERNEL);
 	if (ino) {
 		INIT_LIST_HEAD(&ino->active);
 		INIT_LIST_HEAD(&ino->expiring);
@@ -62,7 +60,7 @@ void autofs4_kill_sb(struct super_block *sb)
 		put_pid(sbi->oz_pgrp);
 	}
 
-	DPRINTK("shutting down");
+	pr_debug("shutting down\n");
 	kill_litter_super(sb);
 	if (sbi)
 		kfree_rcu(sbi, rcu);
@@ -94,7 +92,12 @@ static int autofs4_show_options(struct seq_file *m, struct dentry *root)
 		seq_printf(m, ",direct");
 	else
 		seq_printf(m, ",indirect");
-
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	if (sbi->pipe)
+		seq_printf(m, ",pipe_ino=%ld", sbi->pipe->f_inode->i_ino);
+	else
+		seq_printf(m, ",pipe_ino=-1");
+#endif
 	return 0;
 }
 
@@ -147,6 +150,7 @@ static int parse_options(char *options, int *pipefd, kuid_t *uid, kgid_t *gid,
 
 	while ((p = strsep(&options, ",")) != NULL) {
 		int token;
+
 		if (!*p)
 			continue;
 
@@ -204,9 +208,9 @@ static int parse_options(char *options, int *pipefd, kuid_t *uid, kgid_t *gid,
 
 int autofs4_fill_super(struct super_block *s, void *data, int silent)
 {
-	struct inode * root_inode;
-	struct dentry * root;
-	struct file * pipe;
+	struct inode *root_inode;
+	struct dentry *root;
+	struct file *pipe;
 	int pipefd;
 	struct autofs_sb_info *sbi;
 	struct autofs_info *ino;
@@ -217,7 +221,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
 	if (!sbi)
 		return -ENOMEM;
-	DPRINTK("starting up, sbi = %p",sbi);
+	pr_debug("starting up, sbi = %p\n", sbi);
 
 	s->s_fs_info = sbi;
 	sbi->magic = AUTOFS_SBI_MAGIC;
@@ -266,14 +270,14 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	if (parse_options(data, &pipefd, &root_inode->i_uid, &root_inode->i_gid,
 			  &pgrp, &pgrp_set, &sbi->type, &sbi->min_proto,
 			  &sbi->max_proto)) {
-		printk("autofs: called with bogus options\n");
+		pr_err("called with bogus options\n");
 		goto fail_dput;
 	}
 
 	if (pgrp_set) {
 		sbi->oz_pgrp = find_get_pid(pgrp);
 		if (!sbi->oz_pgrp) {
-			pr_warn("autofs: could not find process group %d\n",
+			pr_err("could not find process group %d\n",
 				pgrp);
 			goto fail_dput;
 		}
@@ -290,10 +294,10 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	/* Couldn't this be tested earlier? */
 	if (sbi->max_proto < AUTOFS_MIN_PROTO_VERSION ||
 	    sbi->min_proto > AUTOFS_MAX_PROTO_VERSION) {
-		printk("autofs: kernel does not match daemon version "
+		pr_err("kernel does not match daemon version "
 		       "daemon (%d, %d) kernel (%d, %d)\n",
-			sbi->min_proto, sbi->max_proto,
-			AUTOFS_MIN_PROTO_VERSION, AUTOFS_MAX_PROTO_VERSION);
+		       sbi->min_proto, sbi->max_proto,
+		       AUTOFS_MIN_PROTO_VERSION, AUTOFS_MAX_PROTO_VERSION);
 		goto fail_dput;
 	}
 
@@ -304,11 +308,11 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 		sbi->version = sbi->max_proto;
 	sbi->sub_version = AUTOFS_PROTO_SUBVERSION;
 
-	DPRINTK("pipe fd = %d, pgrp = %u", pipefd, pid_nr(sbi->oz_pgrp));
+	pr_debug("pipe fd = %d, pgrp = %u\n", pipefd, pid_nr(sbi->oz_pgrp));
 	pipe = fget(pipefd);
 
 	if (!pipe) {
-		printk("autofs: could not open pipe file descriptor\n");
+		pr_err("could not open pipe file descriptor\n");
 		goto fail_dput;
 	}
 	ret = autofs_prepare_pipe(pipe);
@@ -323,12 +327,12 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	 */
 	s->s_root = root;
 	return 0;
-	
+
 	/*
 	 * Failure ... clean up.
 	 */
 fail_fput:
-	printk("autofs: pipe file descriptor does not contain proper ops\n");
+	pr_err("pipe file descriptor does not contain proper ops\n");
 	fput(pipe);
 	/* fall through */
 fail_dput:
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index c6d7d3dbd52a..9328b5861c7a 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -1,16 +1,12 @@
-/* -*- c -*- --------------------------------------------------------------- *
- *
- * linux/fs/autofs/root.c
- *
- *  Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
- *  Copyright 1999-2000 Jeremy Fitzhardinge <jeremy@goop.org>
- *  Copyright 2001-2006 Ian Kent <raven@themaw.net>
+/*
+ * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
+ * Copyright 1999-2000 Jeremy Fitzhardinge <jeremy@goop.org>
+ * Copyright 2001-2006 Ian Kent <raven@themaw.net>
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ------------------------------------------------------------------------- */
+ */
 
 #include <linux/capability.h>
 #include <linux/errno.h>
@@ -23,16 +19,18 @@
 
 #include "autofs_i.h"
 
-static int autofs4_dir_symlink(struct inode *,struct dentry *,const char *);
-static int autofs4_dir_unlink(struct inode *,struct dentry *);
-static int autofs4_dir_rmdir(struct inode *,struct dentry *);
-static int autofs4_dir_mkdir(struct inode *,struct dentry *,umode_t);
-static long autofs4_root_ioctl(struct file *,unsigned int,unsigned long);
+static int autofs4_dir_symlink(struct inode *, struct dentry *, const char *);
+static int autofs4_dir_unlink(struct inode *, struct dentry *);
+static int autofs4_dir_rmdir(struct inode *, struct dentry *);
+static int autofs4_dir_mkdir(struct inode *, struct dentry *, umode_t);
+static long autofs4_root_ioctl(struct file *, unsigned int, unsigned long);
 #ifdef CONFIG_COMPAT
-static long autofs4_root_compat_ioctl(struct file *,unsigned int,unsigned long);
+static long autofs4_root_compat_ioctl(struct file *,
+				      unsigned int, unsigned long);
 #endif
 static int autofs4_dir_open(struct inode *inode, struct file *file);
-static struct dentry *autofs4_lookup(struct inode *,struct dentry *, unsigned int);
+static struct dentry *autofs4_lookup(struct inode *,
+				     struct dentry *, unsigned int);
 static struct vfsmount *autofs4_d_automount(struct path *);
 static int autofs4_d_manage(struct dentry *, bool);
 static void autofs4_dentry_release(struct dentry *);
@@ -74,7 +72,9 @@ const struct dentry_operations autofs4_dentry_operations = {
 static void autofs4_add_active(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
-	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+	struct autofs_info *ino;
+
+	ino = autofs4_dentry_ino(dentry);
 	if (ino) {
 		spin_lock(&sbi->lookup_lock);
 		if (!ino->active_count) {
@@ -84,13 +84,14 @@ static void autofs4_add_active(struct dentry *dentry)
 		ino->active_count++;
 		spin_unlock(&sbi->lookup_lock);
 	}
-	return;
 }
 
 static void autofs4_del_active(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
-	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+	struct autofs_info *ino;
+
+	ino = autofs4_dentry_ino(dentry);
 	if (ino) {
 		spin_lock(&sbi->lookup_lock);
 		ino->active_count--;
@@ -100,7 +101,6 @@ static void autofs4_del_active(struct dentry *dentry)
 		}
 		spin_unlock(&sbi->lookup_lock);
 	}
-	return;
 }
 
 static int autofs4_dir_open(struct inode *inode, struct file *file)
@@ -108,7 +108,7 @@ static int autofs4_dir_open(struct inode *inode, struct file *file)
 	struct dentry *dentry = file->f_path.dentry;
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 
-	DPRINTK("file=%p dentry=%p %pd", file, dentry, dentry);
+	pr_debug("file=%p dentry=%p %pd\n", file, dentry, dentry);
 
 	if (autofs4_oz_mode(sbi))
 		goto out;
@@ -138,7 +138,7 @@ static void autofs4_dentry_release(struct dentry *de)
 	struct autofs_info *ino = autofs4_dentry_ino(de);
 	struct autofs_sb_info *sbi = autofs4_sbi(de->d_sb);
 
-	DPRINTK("releasing %p", de);
+	pr_debug("releasing %p\n", de);
 
 	if (!ino)
 		return;
@@ -278,9 +278,9 @@ static int autofs4_mount_wait(struct dentry *dentry, bool rcu_walk)
 	if (ino->flags & AUTOFS_INF_PENDING) {
 		if (rcu_walk)
 			return -ECHILD;
-		DPRINTK("waiting for mount name=%pd", dentry);
+		pr_debug("waiting for mount name=%pd\n", dentry);
 		status = autofs4_wait(sbi, dentry, NFY_MOUNT);
-		DPRINTK("mount wait done status=%d", status);
+		pr_debug("mount wait done status=%d\n", status);
 	}
 	ino->last_used = jiffies;
 	return status;
@@ -320,7 +320,9 @@ static struct dentry *autofs4_mountpoint_changed(struct path *path)
 	if (autofs_type_indirect(sbi->type) && d_unhashed(dentry)) {
 		struct dentry *parent = dentry->d_parent;
 		struct autofs_info *ino;
-		struct dentry *new = d_lookup(parent, &dentry->d_name);
+		struct dentry *new;
+
+		new = d_lookup(parent, &dentry->d_name);
 		if (!new)
 			return NULL;
 		ino = autofs4_dentry_ino(new);
@@ -338,7 +340,7 @@ static struct vfsmount *autofs4_d_automount(struct path *path)
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	int status;
 
-	DPRINTK("dentry=%p %pd", dentry, dentry);
+	pr_debug("dentry=%p %pd\n", dentry, dentry);
 
 	/* The daemon never triggers a mount. */
 	if (autofs4_oz_mode(sbi))
@@ -425,7 +427,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	int status;
 
-	DPRINTK("dentry=%p %pd", dentry, dentry);
+	pr_debug("dentry=%p %pd\n", dentry, dentry);
 
 	/* The daemon never waits. */
 	if (autofs4_oz_mode(sbi)) {
@@ -455,6 +457,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
 		 * a mount-trap.
 		 */
 		struct inode *inode;
+
 		if (ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU))
 			return 0;
 		if (d_mountpoint(dentry))
@@ -494,13 +497,14 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
 }
 
 /* Lookups in the root directory */
-static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
+static struct dentry *autofs4_lookup(struct inode *dir,
+				     struct dentry *dentry, unsigned int flags)
 {
 	struct autofs_sb_info *sbi;
 	struct autofs_info *ino;
 	struct dentry *active;
 
-	DPRINTK("name = %pd", dentry);
+	pr_debug("name = %pd\n", dentry);
 
 	/* File name too long to exist */
 	if (dentry->d_name.len > NAME_MAX)
@@ -508,14 +512,14 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, u
 
 	sbi = autofs4_sbi(dir->i_sb);
 
-	DPRINTK("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d",
-		current->pid, task_pgrp_nr(current), sbi->catatonic,
-		autofs4_oz_mode(sbi));
+	pr_debug("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d\n",
+		 current->pid, task_pgrp_nr(current), sbi->catatonic,
+		 autofs4_oz_mode(sbi));
 
 	active = autofs4_lookup_active(dentry);
-	if (active) {
+	if (active)
 		return active;
-	} else {
+	else {
 		/*
 		 * A dentry that is not within the root can never trigger a
 		 * mount operation, unless the directory already exists, so we
@@ -526,7 +530,8 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, u
 			return ERR_PTR(-ENOENT);
 
 		/* Mark entries in the root as mount triggers */
-		if (autofs_type_indirect(sbi->type) && IS_ROOT(dentry->d_parent))
+		if (IS_ROOT(dentry->d_parent) &&
+		    autofs_type_indirect(sbi->type))
 			__managed_dentry_set_managed(dentry);
 
 		ino = autofs4_new_ino(sbi);
@@ -554,7 +559,7 @@ static int autofs4_dir_symlink(struct inode *dir,
 	size_t size = strlen(symname);
 	char *cp;
 
-	DPRINTK("%s <- %pd", symname, dentry);
+	pr_debug("%s <- %pd\n", symname, dentry);
 
 	if (!autofs4_oz_mode(sbi))
 		return -EACCES;
@@ -613,7 +618,7 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry)
 	struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	struct autofs_info *p_ino;
-	
+
 	/* This allows root to remove symlinks */
 	if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -664,7 +669,6 @@ static void autofs_set_leaf_automount_flags(struct dentry *dentry)
 	if (IS_ROOT(parent->d_parent))
 		return;
 	managed_dentry_clear_managed(parent);
-	return;
 }
 
 static void autofs_clear_leaf_automount_flags(struct dentry *dentry)
@@ -687,7 +691,6 @@ static void autofs_clear_leaf_automount_flags(struct dentry *dentry)
 	if (d_child->next == &parent->d_subdirs &&
 	    d_child->prev == &parent->d_subdirs)
 		managed_dentry_set_managed(parent);
-	return;
 }
 
 static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
@@ -695,8 +698,8 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
 	struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	struct autofs_info *p_ino;
-	
-	DPRINTK("dentry %p, removing %pd", dentry, dentry);
+
+	pr_debug("dentry %p, removing %pd\n", dentry, dentry);
 
 	if (!autofs4_oz_mode(sbi))
 		return -EACCES;
@@ -728,7 +731,8 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
 	return 0;
 }
 
-static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int autofs4_dir_mkdir(struct inode *dir,
+			     struct dentry *dentry, umode_t mode)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
@@ -738,7 +742,7 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, umode_t m
 	if (!autofs4_oz_mode(sbi))
 		return -EACCES;
 
-	DPRINTK("dentry %p, creating %pd", dentry, dentry);
+	pr_debug("dentry %p, creating %pd\n", dentry, dentry);
 
 	BUG_ON(!ino);
 
@@ -768,14 +772,18 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, umode_t m
 /* Get/set timeout ioctl() operation */
 #ifdef CONFIG_COMPAT
 static inline int autofs4_compat_get_set_timeout(struct autofs_sb_info *sbi,
-					 compat_ulong_t __user *p)
+						 compat_ulong_t __user *p)
 {
-	int rv;
 	unsigned long ntimeout;
+	int rv;
 
-	if ((rv = get_user(ntimeout, p)) ||
-	     (rv = put_user(sbi->exp_timeout/HZ, p)))
-		return rv;
+	rv = get_user(ntimeout, p);
+	if (rv)
+		goto error;
+
+	rv = put_user(sbi->exp_timeout/HZ, p);
+	if (rv)
+		goto error;
 
 	if (ntimeout > UINT_MAX/HZ)
 		sbi->exp_timeout = 0;
@@ -783,18 +791,24 @@ static inline int autofs4_compat_get_set_timeout(struct autofs_sb_info *sbi,
 		sbi->exp_timeout = ntimeout * HZ;
 
 	return 0;
+error:
+	return rv;
 }
 #endif
 
 static inline int autofs4_get_set_timeout(struct autofs_sb_info *sbi,
-					 unsigned long __user *p)
+					  unsigned long __user *p)
 {
-	int rv;
 	unsigned long ntimeout;
+	int rv;
 
-	if ((rv = get_user(ntimeout, p)) ||
-	     (rv = put_user(sbi->exp_timeout/HZ, p)))
-		return rv;
+	rv = get_user(ntimeout, p);
+	if (rv)
+		goto error;
+
+	rv = put_user(sbi->exp_timeout/HZ, p);
+	if (rv)
+		goto error;
 
 	if (ntimeout > ULONG_MAX/HZ)
 		sbi->exp_timeout = 0;
@@ -802,16 +816,20 @@ static inline int autofs4_get_set_timeout(struct autofs_sb_info *sbi,
 		sbi->exp_timeout = ntimeout * HZ;
 
 	return 0;
+error:
+	return rv;
 }
 
 /* Return protocol version */
-static inline int autofs4_get_protover(struct autofs_sb_info *sbi, int __user *p)
+static inline int autofs4_get_protover(struct autofs_sb_info *sbi,
+				       int __user *p)
 {
 	return put_user(sbi->version, p);
 }
 
 /* Return protocol sub version */
-static inline int autofs4_get_protosubver(struct autofs_sb_info *sbi, int __user *p)
+static inline int autofs4_get_protosubver(struct autofs_sb_info *sbi,
+					  int __user *p)
 {
 	return put_user(sbi->sub_version, p);
 }
@@ -826,7 +844,7 @@ static inline int autofs4_ask_umount(struct vfsmount *mnt, int __user *p)
 	if (may_umount(mnt))
 		status = 1;
 
-	DPRINTK("returning %d", status);
+	pr_debug("returning %d\n", status);
 
 	status = put_user(status, p);
 
@@ -834,9 +852,9 @@ static inline int autofs4_ask_umount(struct vfsmount *mnt, int __user *p)
 }
 
 /* Identify autofs4_dentries - this is so we can tell if there's
-   an extra dentry refcount or not.  We only hold a refcount on the
-   dentry if its non-negative (ie, d_inode != NULL)
-*/
+ * an extra dentry refcount or not.  We only hold a refcount on the
+ * dentry if its non-negative (ie, d_inode != NULL)
+ */
 int is_autofs4_dentry(struct dentry *dentry)
 {
 	return dentry && d_really_is_positive(dentry) &&
@@ -854,21 +872,21 @@ static int autofs4_root_ioctl_unlocked(struct inode *inode, struct file *filp,
 	struct autofs_sb_info *sbi = autofs4_sbi(inode->i_sb);
 	void __user *p = (void __user *)arg;
 
-	DPRINTK("cmd = 0x%08x, arg = 0x%08lx, sbi = %p, pgrp = %u",
-		cmd,arg,sbi,task_pgrp_nr(current));
+	pr_debug("cmd = 0x%08x, arg = 0x%08lx, sbi = %p, pgrp = %u\n",
+		 cmd, arg, sbi, task_pgrp_nr(current));
 
 	if (_IOC_TYPE(cmd) != _IOC_TYPE(AUTOFS_IOC_FIRST) ||
 	     _IOC_NR(cmd) - _IOC_NR(AUTOFS_IOC_FIRST) >= AUTOFS_IOC_COUNT)
 		return -ENOTTY;
-	
+
 	if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
-	
-	switch(cmd) {
+
+	switch (cmd) {
 	case AUTOFS_IOC_READY:	/* Wait queue: go ahead and retry */
-		return autofs4_wait_release(sbi,(autofs_wqt_t)arg,0);
+		return autofs4_wait_release(sbi, (autofs_wqt_t) arg, 0);
 	case AUTOFS_IOC_FAIL:	/* Wait queue: fail with ENOENT */
-		return autofs4_wait_release(sbi,(autofs_wqt_t)arg,-ENOENT);
+		return autofs4_wait_release(sbi, (autofs_wqt_t) arg, -ENOENT);
 	case AUTOFS_IOC_CATATONIC: /* Enter catatonic mode (daemon shutdown) */
 		autofs4_catatonic_mode(sbi);
 		return 0;
@@ -888,13 +906,15 @@ static int autofs4_root_ioctl_unlocked(struct inode *inode, struct file *filp,
 
 	/* return a single thing to expire */
 	case AUTOFS_IOC_EXPIRE:
-		return autofs4_expire_run(inode->i_sb,filp->f_path.mnt,sbi, p);
+		return autofs4_expire_run(inode->i_sb,
+					  filp->f_path.mnt, sbi, p);
 	/* same as above, but can send multiple expires through pipe */
 	case AUTOFS_IOC_EXPIRE_MULTI:
-		return autofs4_expire_multi(inode->i_sb,filp->f_path.mnt,sbi, p);
+		return autofs4_expire_multi(inode->i_sb,
+					    filp->f_path.mnt, sbi, p);
 
 	default:
-		return -ENOSYS;
+		return -EINVAL;
 	}
 }
 
@@ -902,12 +922,13 @@ static long autofs4_root_ioctl(struct file *filp,
 			       unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
+
 	return autofs4_root_ioctl_unlocked(inode, filp, cmd, arg);
 }
 
 #ifdef CONFIG_COMPAT
 static long autofs4_root_compat_ioctl(struct file *filp,
-			     unsigned int cmd, unsigned long arg)
+				      unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
 	int ret;
@@ -916,7 +937,7 @@ static long autofs4_root_compat_ioctl(struct file *filp,
 		ret = autofs4_root_ioctl_unlocked(inode, filp, cmd, arg);
 	else
 		ret = autofs4_root_ioctl_unlocked(inode, filp, cmd,
-			(unsigned long)compat_ptr(arg));
+					      (unsigned long) compat_ptr(arg));
 
 	return ret;
 }
diff --git a/fs/autofs4/symlink.c b/fs/autofs4/symlink.c
index 84e037d1d129..99aab00dc217 100644
--- a/fs/autofs4/symlink.c
+++ b/fs/autofs4/symlink.c
@@ -1,14 +1,10 @@
-/* -*- c -*- --------------------------------------------------------------- *
- *
- * linux/fs/autofs/symlink.c
- *
- *  Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
+/*
+ * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ------------------------------------------------------------------------- */
+ */
 
 #include "autofs_i.h"
 
@@ -18,6 +14,7 @@ static const char *autofs4_get_link(struct dentry *dentry,
 {
 	struct autofs_sb_info *sbi;
 	struct autofs_info *ino;
+
 	if (!dentry)
 		return ERR_PTR(-ECHILD);
 	sbi = autofs4_sbi(dentry->d_sb);
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 35b755e79c2d..0146d911f468 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -1,15 +1,11 @@
-/* -*- c -*- --------------------------------------------------------------- *
- *
- * linux/fs/autofs/waitq.c
- *
- *  Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
- *  Copyright 2001-2006 Ian Kent <raven@themaw.net>
+/*
+ * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved
+ * Copyright 2001-2006 Ian Kent <raven@themaw.net>
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ------------------------------------------------------------------------- */
+ */
 
 #include <linux/slab.h>
 #include <linux/time.h>
@@ -18,7 +14,8 @@
 #include "autofs_i.h"
 
 /* We make this a static variable rather than a part of the superblock; it
-   is better if we don't reassign numbers easily even across filesystems */
+ * is better if we don't reassign numbers easily even across filesystems
+ */
 static autofs_wqt_t autofs4_next_wait_queue = 1;
 
 /* These are the signals we allow interrupting a pending mount */
@@ -34,7 +31,7 @@ void autofs4_catatonic_mode(struct autofs_sb_info *sbi)
 		return;
 	}
 
-	DPRINTK("entering catatonic mode");
+	pr_debug("entering catatonic mode\n");
 
 	sbi->catatonic = 1;
 	wq = sbi->queues;
@@ -69,17 +66,19 @@ static int autofs4_write(struct autofs_sb_info *sbi,
 	set_fs(KERNEL_DS);
 
 	mutex_lock(&sbi->pipe_mutex);
-	while (bytes &&
-	       (wr = __vfs_write(file,data,bytes,&file->f_pos)) > 0) {
+	wr = __vfs_write(file, data, bytes, &file->f_pos);
+	while (bytes && wr) {
 		data += wr;
 		bytes -= wr;
+		wr = __vfs_write(file, data, bytes, &file->f_pos);
 	}
 	mutex_unlock(&sbi->pipe_mutex);
 
 	set_fs(fs);
 
 	/* Keep the currently executing process from receiving a
-	   SIGPIPE unless it was already supposed to get one */
+	 * SIGPIPE unless it was already supposed to get one
+	 */
 	if (wr == -EPIPE && !sigpipe) {
 		spin_lock_irqsave(&current->sighand->siglock, flags);
 		sigdelset(&current->pending.signal, SIGPIPE);
@@ -89,7 +88,7 @@ static int autofs4_write(struct autofs_sb_info *sbi,
 
 	return (bytes > 0);
 }
-	
+
 static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 				 struct autofs_wait_queue *wq,
 				 int type)
@@ -102,10 +101,11 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 	struct file *pipe = NULL;
 	size_t pktsz;
 
-	DPRINTK("wait id = 0x%08lx, name = %.*s, type=%d",
-		(unsigned long) wq->wait_queue_token, wq->name.len, wq->name.name, type);
+	pr_debug("wait id = 0x%08lx, name = %.*s, type=%d\n",
+		 (unsigned long) wq->wait_queue_token,
+		 wq->name.len, wq->name.name, type);
 
-	memset(&pkt,0,sizeof pkt); /* For security reasons */
+	memset(&pkt, 0, sizeof(pkt)); /* For security reasons */
 
 	pkt.hdr.proto_version = sbi->version;
 	pkt.hdr.type = type;
@@ -126,7 +126,8 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 	}
 	case autofs_ptype_expire_multi:
 	{
-		struct autofs_packet_expire_multi *ep = &pkt.v4_pkt.expire_multi;
+		struct autofs_packet_expire_multi *ep =
+					&pkt.v4_pkt.expire_multi;
 
 		pktsz = sizeof(*ep);
 
@@ -163,7 +164,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 		break;
 	}
 	default:
-		printk("autofs4_notify_daemon: bad type %d!\n", type);
+		pr_warn("bad type %d!\n", type);
 		mutex_unlock(&sbi->wq_mutex);
 		return;
 	}
@@ -231,7 +232,7 @@ autofs4_find_wait(struct autofs_sb_info *sbi, struct qstr *qstr)
 		if (wq->name.hash == qstr->hash &&
 		    wq->name.len == qstr->len &&
 		    wq->name.name &&
-			 !memcmp(wq->name.name, qstr->name, qstr->len))
+		    !memcmp(wq->name.name, qstr->name, qstr->len))
 			break;
 	}
 	return wq;
@@ -248,7 +249,7 @@ autofs4_find_wait(struct autofs_sb_info *sbi, struct qstr *qstr)
 static int validate_request(struct autofs_wait_queue **wait,
 			    struct autofs_sb_info *sbi,
 			    struct qstr *qstr,
-			    struct dentry*dentry, enum autofs_notify notify)
+			    struct dentry *dentry, enum autofs_notify notify)
 {
 	struct autofs_wait_queue *wq;
 	struct autofs_info *ino;
@@ -322,8 +323,10 @@ static int validate_request(struct autofs_wait_queue **wait,
 		 * continue on and create a new request.
 		 */
 		if (!IS_ROOT(dentry)) {
-			if (d_really_is_positive(dentry) && d_unhashed(dentry)) {
+			if (d_unhashed(dentry) &&
+			    d_really_is_positive(dentry)) {
 				struct dentry *parent = dentry->d_parent;
+
 				new = d_lookup(parent, &dentry->d_name);
 				if (new)
 					dentry = new;
@@ -340,8 +343,8 @@ static int validate_request(struct autofs_wait_queue **wait,
 	return 1;
 }
 
-int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
-		enum autofs_notify notify)
+int autofs4_wait(struct autofs_sb_info *sbi,
+		 struct dentry *dentry, enum autofs_notify notify)
 {
 	struct autofs_wait_queue *wq;
 	struct qstr qstr;
@@ -411,7 +414,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
 
 	if (!wq) {
 		/* Create a new wait queue */
-		wq = kmalloc(sizeof(struct autofs_wait_queue),GFP_KERNEL);
+		wq = kmalloc(sizeof(struct autofs_wait_queue), GFP_KERNEL);
 		if (!wq) {
 			kfree(qstr.name);
 			mutex_unlock(&sbi->wq_mutex);
@@ -450,17 +453,19 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
 					autofs_ptype_expire_indirect;
 		}
 
-		DPRINTK("new wait id = 0x%08lx, name = %.*s, nfy=%d\n",
-			(unsigned long) wq->wait_queue_token, wq->name.len,
-			wq->name.name, notify);
+		pr_debug("new wait id = 0x%08lx, name = %.*s, nfy=%d\n",
+			 (unsigned long) wq->wait_queue_token, wq->name.len,
+			 wq->name.name, notify);
 
-		/* autofs4_notify_daemon() may block; it will unlock ->wq_mutex */
+		/*
+		 * autofs4_notify_daemon() may block; it will unlock ->wq_mutex
+		 */
 		autofs4_notify_daemon(sbi, wq, type);
 	} else {
 		wq->wait_ctr++;
-		DPRINTK("existing wait id = 0x%08lx, name = %.*s, nfy=%d",
-			(unsigned long) wq->wait_queue_token, wq->name.len,
-			wq->name.name, notify);
+		pr_debug("existing wait id = 0x%08lx, name = %.*s, nfy=%d\n",
+			 (unsigned long) wq->wait_queue_token, wq->name.len,
+			 wq->name.name, notify);
 		mutex_unlock(&sbi->wq_mutex);
 		kfree(qstr.name);
 	}
@@ -471,12 +476,14 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
 	 */
 	if (wq->name.name) {
 		/* Block all but "shutdown" signals while waiting */
-		sigset_t oldset;
+		unsigned long shutdown_sigs_mask;
 		unsigned long irqflags;
+		sigset_t oldset;
 
 		spin_lock_irqsave(&current->sighand->siglock, irqflags);
 		oldset = current->blocked;
-		siginitsetinv(&current->blocked, SHUTDOWN_SIGS & ~oldset.sig[0]);
+		shutdown_sigs_mask = SHUTDOWN_SIGS & ~oldset.sig[0];
+		siginitsetinv(&current->blocked, shutdown_sigs_mask);
 		recalc_sigpending();
 		spin_unlock_irqrestore(&current->sighand->siglock, irqflags);
 
@@ -487,7 +494,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
 		recalc_sigpending();
 		spin_unlock_irqrestore(&current->sighand->siglock, irqflags);
 	} else {
-		DPRINTK("skipped sleeping");
+		pr_debug("skipped sleeping\n");
 	}
 
 	status = wq->status;
@@ -562,4 +569,3 @@ int autofs4_wait_release(struct autofs_sb_info *sbi, autofs_wqt_t wait_queue_tok
 
 	return 0;
 }
-
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 051ea4809c14..7d914c67a9d0 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -653,7 +653,7 @@ static unsigned long randomize_stack_top(unsigned long stack_top)
 
 	if ((current->flags & PF_RANDOMIZE) &&
 		!(current->personality & ADDR_NO_RANDOMIZE)) {
-		random_variable = (unsigned long) get_random_int();
+		random_variable = get_random_long();
 		random_variable &= STACK_RND_MASK;
 		random_variable <<= PAGE_SHIFT;
 	}
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 39b3a174a425..826b164a4b5b 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1201,7 +1201,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 		bdev->bd_disk = disk;
 		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
-		bdev->bd_inode->i_flags = disk->fops->direct_access ? S_DAX : 0;
+		if (IS_ENABLED(CONFIG_BLK_DEV_DAX) && disk->fops->direct_access)
+			bdev->bd_inode->i_flags = S_DAX;
+		else
+			bdev->bd_inode->i_flags = 0;
+
 		if (!partno) {
 			ret = -ENXIO;
 			bdev->bd_part = disk_get_part(disk, partno);
@@ -1693,13 +1697,24 @@ static int blkdev_releasepage(struct page *page, gfp_t wait)
 	return try_to_free_buffers(page);
 }
 
+static int blkdev_writepages(struct address_space *mapping,
+			     struct writeback_control *wbc)
+{
+	if (dax_mapping(mapping)) {
+		struct block_device *bdev = I_BDEV(mapping->host);
+
+		return dax_writeback_mapping_range(mapping, bdev, wbc);
+	}
+	return generic_writepages(mapping, wbc);
+}
+
 static const struct address_space_operations def_blk_aops = {
 	.readpage	= blkdev_readpage,
 	.readpages	= blkdev_readpages,
 	.writepage	= blkdev_writepage,
 	.write_begin	= blkdev_write_begin,
 	.write_end	= blkdev_write_end,
-	.writepages	= generic_writepages,
+	.writepages	= blkdev_writepages,
 	.releasepage	= blkdev_releasepage,
 	.direct_IO	= blkdev_direct_IO,
 	.is_dirty_writeback = buffer_check_dirty_writeback,
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index b90cd3776f8e..f6dac40f87ff 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1406,7 +1406,8 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 			read_extent_buffer(eb, dest + bytes_left,
 					   name_off, name_len);
 		if (eb != eb_in) {
-			btrfs_tree_read_unlock_blocking(eb);
+			if (!path->skip_locking)
+				btrfs_tree_read_unlock_blocking(eb);
 			free_extent_buffer(eb);
 		}
 		ret = btrfs_find_item(fs_root, path, parent, 0,
@@ -1426,9 +1427,10 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 		eb = path->nodes[0];
 		/* make sure we can use eb after releasing the path */
 		if (eb != eb_in) {
-			atomic_inc(&eb->refs);
-			btrfs_tree_read_lock(eb);
-			btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+			if (!path->skip_locking)
+				btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+			path->nodes[0] = NULL;
+			path->locks[0] = 0;
 		}
 		btrfs_release_path(path);
 		iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index c473c42d7d6c..3346cd8f9910 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -637,11 +637,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	faili = nr_pages - 1;
 	cb->nr_pages = nr_pages;
 
-	/* In the parent-locked case, we only locked the range we are
-	 * interested in.  In all other cases, we can opportunistically
-	 * cache decompressed data that goes beyond the requested range. */
-	if (!(bio_flags & EXTENT_BIO_PARENT_LOCKED))
-		add_ra_bio_pages(inode, em_start + em_len, cb);
+	add_ra_bio_pages(inode, em_start + em_len, cb);
 
 	/* include any pages we added in add_ra-bio_pages */
 	uncompressed_len = bio->bi_vcnt * PAGE_CACHE_SIZE;
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 0be47e4b8136..b57daa895cea 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1689,7 +1689,7 @@ int btrfs_should_delete_dir_index(struct list_head *del_list,
  *
  */
 int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
-				    struct list_head *ins_list)
+				    struct list_head *ins_list, bool *emitted)
 {
 	struct btrfs_dir_item *di;
 	struct btrfs_delayed_item *curr, *next;
@@ -1733,6 +1733,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
 
 		if (over)
 			return 1;
+		*emitted = true;
 	}
 	return 0;
 }
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index f70119f25421..0167853c84ae 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -144,7 +144,7 @@ void btrfs_put_delayed_items(struct list_head *ins_list,
 int btrfs_should_delete_dir_index(struct list_head *del_list,
 				  u64 index);
 int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
-				    struct list_head *ins_list);
+				    struct list_head *ins_list, bool *emitted);
 
 /* for init */
 int __init btrfs_delayed_inode_init(void);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 4545e2e2ad45..5699bbc23feb 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -931,7 +931,7 @@ static int check_async_write(struct inode *inode, unsigned long bio_flags)
 	if (bio_flags & EXTENT_BIO_TREE_LOG)
 		return 0;
 #ifdef CONFIG_X86
-	if (static_cpu_has_safe(X86_FEATURE_XMM4_2))
+	if (static_cpu_has(X86_FEATURE_XMM4_2))
 		return 0;
 #endif
 	return 1;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 2e7c97a3f344..392592dc7010 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2897,12 +2897,11 @@ static int __do_readpage(struct extent_io_tree *tree,
 	struct block_device *bdev;
 	int ret;
 	int nr = 0;
-	int parent_locked = *bio_flags & EXTENT_BIO_PARENT_LOCKED;
 	size_t pg_offset = 0;
 	size_t iosize;
 	size_t disk_io_size;
 	size_t blocksize = inode->i_sb->s_blocksize;
-	unsigned long this_bio_flag = *bio_flags & EXTENT_BIO_PARENT_LOCKED;
+	unsigned long this_bio_flag = 0;
 
 	set_page_extent_mapped(page);
 
@@ -2942,18 +2941,16 @@ static int __do_readpage(struct extent_io_tree *tree,
 			kunmap_atomic(userpage);
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
 					    &cached, GFP_NOFS);
-			if (!parent_locked)
-				unlock_extent_cached(tree, cur,
-						     cur + iosize - 1,
-						     &cached, GFP_NOFS);
+			unlock_extent_cached(tree, cur,
+					     cur + iosize - 1,
+					     &cached, GFP_NOFS);
 			break;
 		}
 		em = __get_extent_map(inode, page, pg_offset, cur,
 				      end - cur + 1, get_extent, em_cached);
 		if (IS_ERR_OR_NULL(em)) {
 			SetPageError(page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, end);
+			unlock_extent(tree, cur, end);
 			break;
 		}
 		extent_offset = cur - em->start;
@@ -3038,12 +3035,9 @@ static int __do_readpage(struct extent_io_tree *tree,
 
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
 					    &cached, GFP_NOFS);
-			if (parent_locked)
-				free_extent_state(cached);
-			else
-				unlock_extent_cached(tree, cur,
-						     cur + iosize - 1,
-						     &cached, GFP_NOFS);
+			unlock_extent_cached(tree, cur,
+					     cur + iosize - 1,
+					     &cached, GFP_NOFS);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -3052,8 +3046,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 		if (test_range_bit(tree, cur, cur_end,
 				   EXTENT_UPTODATE, 1, NULL)) {
 			check_page_uptodate(tree, page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, cur + iosize - 1);
+			unlock_extent(tree, cur, cur + iosize - 1);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -3063,8 +3056,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 		 */
 		if (block_start == EXTENT_MAP_INLINE) {
 			SetPageError(page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, cur + iosize - 1);
+			unlock_extent(tree, cur, cur + iosize - 1);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -3083,8 +3075,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 			*bio_flags = this_bio_flag;
 		} else {
 			SetPageError(page);
-			if (!parent_locked)
-				unlock_extent(tree, cur, cur + iosize - 1);
+			unlock_extent(tree, cur, cur + iosize - 1);
 		}
 		cur = cur + iosize;
 		pg_offset += iosize;
@@ -3213,20 +3204,6 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 	return ret;
 }
 
-int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
-				 get_extent_t *get_extent, int mirror_num)
-{
-	struct bio *bio = NULL;
-	unsigned long bio_flags = EXTENT_BIO_PARENT_LOCKED;
-	int ret;
-
-	ret = __do_readpage(tree, page, get_extent, NULL, &bio, mirror_num,
-			    &bio_flags, READ, NULL);
-	if (bio)
-		ret = submit_one_bio(READ, bio, mirror_num, bio_flags);
-	return ret;
-}
-
 static noinline void update_nr_written(struct page *page,
 				      struct writeback_control *wbc,
 				      unsigned long nr_written)
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 0377413bd4b9..880d5292e972 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -29,7 +29,6 @@
  */
 #define EXTENT_BIO_COMPRESSED 1
 #define EXTENT_BIO_TREE_LOG 2
-#define EXTENT_BIO_PARENT_LOCKED 4
 #define EXTENT_BIO_FLAG_SHIFT 16
 
 /* these are bit numbers for test/set bit */
@@ -210,8 +209,6 @@ static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
 int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
 int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 			  get_extent_t *get_extent, int mirror_num);
-int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
-				 get_extent_t *get_extent, int mirror_num);
 int __init extent_io_init(void);
 void extent_io_exit(void);
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5f06eb1f4384..d96f5cf38a2d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5717,6 +5717,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	char *name_ptr;
 	int name_len;
 	int is_curr = 0;	/* ctx->pos points to the current index? */
+	bool emitted;
 
 	/* FIXME, use a real flag for deciding about the key type */
 	if (root->fs_info->tree_root == root)
@@ -5745,6 +5746,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	if (ret < 0)
 		goto err;
 
+	emitted = false;
 	while (1) {
 		leaf = path->nodes[0];
 		slot = path->slots[0];
@@ -5824,6 +5826,7 @@ skip:
 
 			if (over)
 				goto nopos;
+			emitted = true;
 			di_len = btrfs_dir_name_len(leaf, di) +
 				 btrfs_dir_data_len(leaf, di) + sizeof(*di);
 			di_cur += di_len;
@@ -5836,11 +5839,20 @@ next:
 	if (key_type == BTRFS_DIR_INDEX_KEY) {
 		if (is_curr)
 			ctx->pos++;
-		ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list);
+		ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list, &emitted);
 		if (ret)
 			goto nopos;
 	}
 
+	/*
+	 * If we haven't emitted any dir entry, we must not touch ctx->pos as
+	 * it was was set to the termination value in previous call. We assume
+	 * that "." and ".." were emitted if we reach this point and set the
+	 * termination value as well for an empty directory.
+	 */
+	if (ctx->pos > 2 && !emitted)
+		goto nopos;
+
 	/* Reached end of directory/root. Bump pos past the last item. */
 	ctx->pos++;
 
@@ -7974,6 +7986,7 @@ static void btrfs_endio_direct_read(struct bio *bio)
 
 	kfree(dip);
 
+	dio_bio->bi_error = bio->bi_error;
 	dio_end_io(dio_bio, bio->bi_error);
 
 	if (io_bio->end_io)
@@ -8028,6 +8041,7 @@ static void btrfs_endio_direct_write(struct bio *bio)
 
 	kfree(dip);
 
+	dio_bio->bi_error = bio->bi_error;
 	dio_end_io(dio_bio, bio->bi_error);
 	bio_put(bio);
 }
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 952172ca7e45..48aee9846329 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2794,24 +2794,29 @@ out:
 static struct page *extent_same_get_page(struct inode *inode, pgoff_t index)
 {
 	struct page *page;
-	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
 
 	page = grab_cache_page(inode->i_mapping, index);
 	if (!page)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	if (!PageUptodate(page)) {
-		if (extent_read_full_page_nolock(tree, page, btrfs_get_extent,
-						 0))
-			return NULL;
+		int ret;
+
+		ret = btrfs_readpage(NULL, page);
+		if (ret)
+			return ERR_PTR(ret);
 		lock_page(page);
 		if (!PageUptodate(page)) {
 			unlock_page(page);
 			page_cache_release(page);
-			return NULL;
+			return ERR_PTR(-EIO);
+		}
+		if (page->mapping != inode->i_mapping) {
+			unlock_page(page);
+			page_cache_release(page);
+			return ERR_PTR(-EAGAIN);
 		}
 	}
-	unlock_page(page);
 
 	return page;
 }
@@ -2823,17 +2828,31 @@ static int gather_extent_pages(struct inode *inode, struct page **pages,
 	pgoff_t index = off >> PAGE_CACHE_SHIFT;
 
 	for (i = 0; i < num_pages; i++) {
+again:
 		pages[i] = extent_same_get_page(inode, index + i);
-		if (!pages[i])
-			return -ENOMEM;
+		if (IS_ERR(pages[i])) {
+			int err = PTR_ERR(pages[i]);
+
+			if (err == -EAGAIN)
+				goto again;
+			pages[i] = NULL;
+			return err;
+		}
 	}
 	return 0;
 }
 
-static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
+static int lock_extent_range(struct inode *inode, u64 off, u64 len,
+			     bool retry_range_locking)
 {
-	/* do any pending delalloc/csum calc on src, one way or
-	   another, and lock file content */
+	/*
+	 * Do any pending delalloc/csum calculations on inode, one way or
+	 * another, and lock file content.
+	 * The locking order is:
+	 *
+	 *   1) pages
+	 *   2) range in the inode's io tree
+	 */
 	while (1) {
 		struct btrfs_ordered_extent *ordered;
 		lock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
@@ -2851,8 +2870,11 @@ static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
 		unlock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
 		if (ordered)
 			btrfs_put_ordered_extent(ordered);
+		if (!retry_range_locking)
+			return -EAGAIN;
 		btrfs_wait_ordered_range(inode, off, len);
 	}
+	return 0;
 }
 
 static void btrfs_double_inode_unlock(struct inode *inode1, struct inode *inode2)
@@ -2877,15 +2899,24 @@ static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
 	unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
 }
 
-static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
-				     struct inode *inode2, u64 loff2, u64 len)
+static int btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
+				    struct inode *inode2, u64 loff2, u64 len,
+				    bool retry_range_locking)
 {
+	int ret;
+
 	if (inode1 < inode2) {
 		swap(inode1, inode2);
 		swap(loff1, loff2);
 	}
-	lock_extent_range(inode1, loff1, len);
-	lock_extent_range(inode2, loff2, len);
+	ret = lock_extent_range(inode1, loff1, len, retry_range_locking);
+	if (ret)
+		return ret;
+	ret = lock_extent_range(inode2, loff2, len, retry_range_locking);
+	if (ret)
+		unlock_extent(&BTRFS_I(inode1)->io_tree, loff1,
+			      loff1 + len - 1);
+	return ret;
 }
 
 struct cmp_pages {
@@ -2901,11 +2932,15 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp)
 
 	for (i = 0; i < cmp->num_pages; i++) {
 		pg = cmp->src_pages[i];
-		if (pg)
+		if (pg) {
+			unlock_page(pg);
 			page_cache_release(pg);
+		}
 		pg = cmp->dst_pages[i];
-		if (pg)
+		if (pg) {
+			unlock_page(pg);
 			page_cache_release(pg);
+		}
 	}
 	kfree(cmp->src_pages);
 	kfree(cmp->dst_pages);
@@ -2966,6 +3001,8 @@ static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst,
 
 		src_page = cmp->src_pages[i];
 		dst_page = cmp->dst_pages[i];
+		ASSERT(PageLocked(src_page));
+		ASSERT(PageLocked(dst_page));
 
 		addr = kmap_atomic(src_page);
 		dst_addr = kmap_atomic(dst_page);
@@ -3078,14 +3115,46 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 		goto out_unlock;
 	}
 
+again:
 	ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp);
 	if (ret)
 		goto out_unlock;
 
 	if (same_inode)
-		lock_extent_range(src, same_lock_start, same_lock_len);
+		ret = lock_extent_range(src, same_lock_start, same_lock_len,
+					false);
 	else
-		btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
+		ret = btrfs_double_extent_lock(src, loff, dst, dst_loff, len,
+					       false);
+	/*
+	 * If one of the inodes has dirty pages in the respective range or
+	 * ordered extents, we need to flush dellaloc and wait for all ordered
+	 * extents in the range. We must unlock the pages and the ranges in the
+	 * io trees to avoid deadlocks when flushing delalloc (requires locking
+	 * pages) and when waiting for ordered extents to complete (they require
+	 * range locking).
+	 */
+	if (ret == -EAGAIN) {
+		/*
+		 * Ranges in the io trees already unlocked. Now unlock all
+		 * pages before waiting for all IO to complete.
+		 */
+		btrfs_cmp_data_free(&cmp);
+		if (same_inode) {
+			btrfs_wait_ordered_range(src, same_lock_start,
+						 same_lock_len);
+		} else {
+			btrfs_wait_ordered_range(src, loff, len);
+			btrfs_wait_ordered_range(dst, dst_loff, len);
+		}
+		goto again;
+	}
+	ASSERT(ret == 0);
+	if (WARN_ON(ret)) {
+		/* ranges in the io trees already unlocked */
+		btrfs_cmp_data_free(&cmp);
+		return ret;
+	}
 
 	/* pass original length for comparison so we stay within i_size */
 	ret = btrfs_cmp_data(src, loff, dst, dst_loff, olen, &cmp);
@@ -3795,9 +3864,15 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
 		u64 lock_start = min_t(u64, off, destoff);
 		u64 lock_len = max_t(u64, off, destoff) + len - lock_start;
 
-		lock_extent_range(src, lock_start, lock_len);
+		ret = lock_extent_range(src, lock_start, lock_len, true);
 	} else {
-		btrfs_double_extent_lock(src, off, inode, destoff, len);
+		ret = btrfs_double_extent_lock(src, off, inode, destoff, len,
+					       true);
+	}
+	ASSERT(ret == 0);
+	if (WARN_ON(ret)) {
+		/* ranges in the io trees already unlocked */
+		goto out_unlock;
 	}
 
 	ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 7cf8509deda7..2c849b08a91b 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -310,8 +310,16 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
 		set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state);
 
 		err = btrfs_insert_fs_root(root->fs_info, root);
+		/*
+		 * The root might have been inserted already, as before we look
+		 * for orphan roots, log replay might have happened, which
+		 * triggers a transaction commit and qgroup accounting, which
+		 * in turn reads and inserts fs roots while doing backref
+		 * walking.
+		 */
+		if (err == -EEXIST)
+			err = 0;
 		if (err) {
-			BUG_ON(err == -EEXIST);
 			btrfs_free_fs_root(root);
 			break;
 		}
diff --git a/fs/buffer.c b/fs/buffer.c
index e1632abb4ca9..33be29675358 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -621,17 +621,17 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode);
  * If warn is true, then emit a warning if the page is not uptodate and has
  * not been truncated.
  *
- * The caller must hold mem_cgroup_begin_page_stat() lock.
+ * The caller must hold lock_page_memcg().
  */
 static void __set_page_dirty(struct page *page, struct address_space *mapping,
-			     struct mem_cgroup *memcg, int warn)
+			     int warn)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&mapping->tree_lock, flags);
 	if (page->mapping) {	/* Race with truncate? */
 		WARN_ON_ONCE(warn && !PageUptodate(page));
-		account_page_dirtied(page, mapping, memcg);
+		account_page_dirtied(page, mapping);
 		radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 	}
@@ -666,7 +666,6 @@ static void __set_page_dirty(struct page *page, struct address_space *mapping,
 int __set_page_dirty_buffers(struct page *page)
 {
 	int newly_dirty;
-	struct mem_cgroup *memcg;
 	struct address_space *mapping = page_mapping(page);
 
 	if (unlikely(!mapping))
@@ -683,17 +682,17 @@ int __set_page_dirty_buffers(struct page *page)
 		} while (bh != head);
 	}
 	/*
-	 * Use mem_group_begin_page_stat() to keep PageDirty synchronized with
-	 * per-memcg dirty page counters.
+	 * Lock out page->mem_cgroup migration to keep PageDirty
+	 * synchronized with per-memcg dirty page counters.
 	 */
-	memcg = mem_cgroup_begin_page_stat(page);
+	lock_page_memcg(page);
 	newly_dirty = !TestSetPageDirty(page);
 	spin_unlock(&mapping->private_lock);
 
 	if (newly_dirty)
-		__set_page_dirty(page, mapping, memcg, 1);
+		__set_page_dirty(page, mapping, 1);
 
-	mem_cgroup_end_page_stat(memcg);
+	unlock_page_memcg(page);
 
 	if (newly_dirty)
 		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
@@ -1167,15 +1166,14 @@ void mark_buffer_dirty(struct buffer_head *bh)
 	if (!test_set_buffer_dirty(bh)) {
 		struct page *page = bh->b_page;
 		struct address_space *mapping = NULL;
-		struct mem_cgroup *memcg;
 
-		memcg = mem_cgroup_begin_page_stat(page);
+		lock_page_memcg(page);
 		if (!TestSetPageDirty(page)) {
 			mapping = page_mapping(page);
 			if (mapping)
-				__set_page_dirty(page, mapping, memcg, 0);
+				__set_page_dirty(page, mapping, 0);
 		}
-		mem_cgroup_end_page_stat(memcg);
+		unlock_page_memcg(page);
 		if (mapping)
 			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 	}
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index c22213789090..19adeb0ef82a 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1756,6 +1756,10 @@ int ceph_pool_perm_check(struct ceph_inode_info *ci, int need)
 	u32 pool;
 	int ret, flags;
 
+	/* does not support pool namespace yet */
+	if (ci->i_pool_ns_len)
+		return -EIO;
+
 	if (ceph_test_mount_opt(ceph_inode_to_client(&ci->vfs_inode),
 				NOPOOLPERM))
 		return 0;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index cdbf8cf3d52c..6fe0ad26a7df 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2753,7 +2753,8 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 			     void *inline_data, int inline_len,
 			     struct ceph_buffer *xattr_buf,
 			     struct ceph_mds_session *session,
-			     struct ceph_cap *cap, int issued)
+			     struct ceph_cap *cap, int issued,
+			     u32 pool_ns_len)
 	__releases(ci->i_ceph_lock)
 	__releases(mdsc->snap_rwsem)
 {
@@ -2873,6 +2874,8 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 	if (newcaps & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR)) {
 		/* file layout may have changed */
 		ci->i_layout = grant->layout;
+		ci->i_pool_ns_len = pool_ns_len;
+
 		/* size/truncate_seq? */
 		queue_trunc = ceph_fill_file_size(inode, issued,
 					le32_to_cpu(grant->truncate_seq),
@@ -3411,6 +3414,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	u32  inline_len = 0;
 	void *snaptrace;
 	size_t snaptrace_len;
+	u32 pool_ns_len = 0;
 	void *p, *end;
 
 	dout("handle_caps from mds%d\n", mds);
@@ -3463,6 +3467,21 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		p += inline_len;
 	}
 
+	if (le16_to_cpu(msg->hdr.version) >= 8) {
+		u64 flush_tid;
+		u32 caller_uid, caller_gid;
+		u32 osd_epoch_barrier;
+		/* version >= 5 */
+		ceph_decode_32_safe(&p, end, osd_epoch_barrier, bad);
+		/* version >= 6 */
+		ceph_decode_64_safe(&p, end, flush_tid, bad);
+		/* version >= 7 */
+		ceph_decode_32_safe(&p, end, caller_uid, bad);
+		ceph_decode_32_safe(&p, end, caller_gid, bad);
+		/* version >= 8 */
+		ceph_decode_32_safe(&p, end, pool_ns_len, bad);
+	}
+
 	/* lookup ino */
 	inode = ceph_find_inode(sb, vino);
 	ci = ceph_inode(inode);
@@ -3518,7 +3537,8 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 				  &cap, &issued);
 		handle_cap_grant(mdsc, inode, h,
 				 inline_version, inline_data, inline_len,
-				 msg->middle, session, cap, issued);
+				 msg->middle, session, cap, issued,
+				 pool_ns_len);
 		if (realm)
 			ceph_put_snap_realm(mdsc, realm);
 		goto done_unlocked;
@@ -3542,7 +3562,8 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		issued |= __ceph_caps_dirty(ci);
 		handle_cap_grant(mdsc, inode, h,
 				 inline_version, inline_data, inline_len,
-				 msg->middle, session, cap, issued);
+				 msg->middle, session, cap, issued,
+				 pool_ns_len);
 		goto done_unlocked;
 
 	case CEPH_CAP_OP_FLUSH_ACK:
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index fb4ba2e4e2a5..5849b88bbed3 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -396,6 +396,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	ci->i_symlink = NULL;
 
 	memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout));
+	ci->i_pool_ns_len = 0;
 
 	ci->i_fragtree = RB_ROOT;
 	mutex_init(&ci->i_fragtree_mutex);
@@ -756,6 +757,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 		if (ci->i_layout.fl_pg_pool != info->layout.fl_pg_pool)
 			ci->i_ceph_flags &= ~CEPH_I_POOL_PERM;
 		ci->i_layout = info->layout;
+		ci->i_pool_ns_len = iinfo->pool_ns_len;
 
 		queue_trunc = ceph_fill_file_size(inode, issued,
 					le32_to_cpu(info->truncate_seq),
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index e7b130a637f9..911d64d865f1 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -100,6 +100,14 @@ static int parse_reply_info_in(void **p, void *end,
 	} else
 		info->inline_version = CEPH_INLINE_NONE;
 
+	if (features & CEPH_FEATURE_FS_FILE_LAYOUT_V2) {
+		ceph_decode_32_safe(p, end, info->pool_ns_len, bad);
+		ceph_decode_need(p, end, info->pool_ns_len, bad);
+		*p += info->pool_ns_len;
+	} else {
+		info->pool_ns_len = 0;
+	}
+
 	return 0;
 bad:
 	return err;
@@ -2298,6 +2306,14 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
 		ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir),
 				  CEPH_CAP_PIN);
 
+	/* deny access to directories with pool_ns layouts */
+	if (req->r_inode && S_ISDIR(req->r_inode->i_mode) &&
+	    ceph_inode(req->r_inode)->i_pool_ns_len)
+		return -EIO;
+	if (req->r_locked_dir &&
+	    ceph_inode(req->r_locked_dir)->i_pool_ns_len)
+		return -EIO;
+
 	/* issue */
 	mutex_lock(&mdsc->mutex);
 	__register_request(mdsc, req, dir);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index ccf11ef0ca87..37712ccffcc6 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -44,6 +44,7 @@ struct ceph_mds_reply_info_in {
 	u64 inline_version;
 	u32 inline_len;
 	char *inline_data;
+	u32 pool_ns_len;
 };
 
 /*
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 75b7d125ce66..9c458eb52245 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -287,6 +287,7 @@ struct ceph_inode_info {
 
 	struct ceph_dir_layout i_dir_layout;
 	struct ceph_file_layout i_layout;
+	size_t i_pool_ns_len;
 	char *i_symlink;
 
 	/* for dirs */
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 7dc886c9a78f..e956cba94338 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -175,7 +175,7 @@ char *cifs_compose_mount_options(const char *sb_mountdata,
 	 * string to the length of the original string to allow for worst case.
 	 */
 	md_len = strlen(sb_mountdata) + INET6_ADDRSTRLEN;
-	mountdata = kzalloc(md_len + 1, GFP_KERNEL);
+	mountdata = kzalloc(md_len + sizeof("ip=") + 1, GFP_KERNEL);
 	if (mountdata == NULL) {
 		rc = -ENOMEM;
 		goto compose_mount_options_err;
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index afa09fce8151..4897dacf8944 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -33,6 +33,7 @@
 #include <linux/ctype.h>
 #include <linux/random.h>
 #include <linux/highmem.h>
+#include <crypto/skcipher.h>
 
 static int
 cifs_crypto_shash_md5_allocate(struct TCP_Server_Info *server)
@@ -714,7 +715,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 
 	ses->auth_key.response = kmalloc(baselen + tilen, GFP_KERNEL);
 	if (!ses->auth_key.response) {
-		rc = ENOMEM;
+		rc = -ENOMEM;
 		ses->auth_key.len = 0;
 		goto setup_ntlmv2_rsp_ret;
 	}
@@ -789,38 +790,46 @@ int
 calc_seckey(struct cifs_ses *ses)
 {
 	int rc;
-	struct crypto_blkcipher *tfm_arc4;
+	struct crypto_skcipher *tfm_arc4;
 	struct scatterlist sgin, sgout;
-	struct blkcipher_desc desc;
+	struct skcipher_request *req;
 	unsigned char sec_key[CIFS_SESS_KEY_SIZE]; /* a nonce */
 
 	get_random_bytes(sec_key, CIFS_SESS_KEY_SIZE);
 
-	tfm_arc4 = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
+	tfm_arc4 = crypto_alloc_skcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm_arc4)) {
 		rc = PTR_ERR(tfm_arc4);
 		cifs_dbg(VFS, "could not allocate crypto API arc4\n");
 		return rc;
 	}
 
-	desc.tfm = tfm_arc4;
-
-	rc = crypto_blkcipher_setkey(tfm_arc4, ses->auth_key.response,
+	rc = crypto_skcipher_setkey(tfm_arc4, ses->auth_key.response,
 					CIFS_SESS_KEY_SIZE);
 	if (rc) {
 		cifs_dbg(VFS, "%s: Could not set response as a key\n",
 			 __func__);
-		return rc;
+		goto out_free_cipher;
+	}
+
+	req = skcipher_request_alloc(tfm_arc4, GFP_KERNEL);
+	if (!req) {
+		rc = -ENOMEM;
+		cifs_dbg(VFS, "could not allocate crypto API arc4 request\n");
+		goto out_free_cipher;
 	}
 
 	sg_init_one(&sgin, sec_key, CIFS_SESS_KEY_SIZE);
 	sg_init_one(&sgout, ses->ntlmssp->ciphertext, CIFS_CPHTXT_SIZE);
 
-	rc = crypto_blkcipher_encrypt(&desc, &sgout, &sgin, CIFS_CPHTXT_SIZE);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, &sgin, &sgout, CIFS_CPHTXT_SIZE, NULL);
+
+	rc = crypto_skcipher_encrypt(req);
+	skcipher_request_free(req);
 	if (rc) {
 		cifs_dbg(VFS, "could not encrypt session key rc: %d\n", rc);
-		crypto_free_blkcipher(tfm_arc4);
-		return rc;
+		goto out_free_cipher;
 	}
 
 	/* make secondary_key/nonce as session key */
@@ -828,7 +837,8 @@ calc_seckey(struct cifs_ses *ses)
 	/* and make len as that of session key only */
 	ses->auth_key.len = CIFS_SESS_KEY_SIZE;
 
-	crypto_free_blkcipher(tfm_arc4);
+out_free_cipher:
+	crypto_free_skcipher(tfm_arc4);
 
 	return rc;
 }
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index c48ca13673e3..2eea40353e60 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -1013,7 +1013,6 @@ const struct file_operations cifs_file_strict_ops = {
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
 	.clone_file_range = cifs_clone_file_range,
-	.clone_file_range = cifs_clone_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
 };
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 68c4547528c4..83aac8ba50b0 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -31,19 +31,15 @@
  * so that it will fit. We use hash_64 to convert the value to 31 bits, and
  * then add 1, to ensure that we don't end up with a 0 as the value.
  */
-#if BITS_PER_LONG == 64
 static inline ino_t
 cifs_uniqueid_to_ino_t(u64 fileid)
 {
+	if ((sizeof(ino_t)) < (sizeof(u64)))
+		return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1;
+
 	return (ino_t)fileid;
+
 }
-#else
-static inline ino_t
-cifs_uniqueid_to_ino_t(u64 fileid)
-{
-	return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1;
-}
-#endif
 
 extern struct file_system_type cifs_fs_type;
 extern const struct address_space_operations cifs_addr_ops;
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 90b4f9f7de66..76fcb50295a3 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1396,11 +1396,10 @@ openRetry:
  * current bigbuf.
  */
 static int
-cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
+discard_remaining_data(struct TCP_Server_Info *server)
 {
 	unsigned int rfclen = get_rfc1002_length(server->smallbuf);
 	int remaining = rfclen + 4 - server->total_read;
-	struct cifs_readdata *rdata = mid->callback_data;
 
 	while (remaining > 0) {
 		int length;
@@ -1414,10 +1413,20 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 		remaining -= length;
 	}
 
-	dequeue_mid(mid, rdata->result);
 	return 0;
 }
 
+static int
+cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
+{
+	int length;
+	struct cifs_readdata *rdata = mid->callback_data;
+
+	length = discard_remaining_data(server);
+	dequeue_mid(mid, rdata->result);
+	return length;
+}
+
 int
 cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 {
@@ -1446,6 +1455,12 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 		return length;
 	server->total_read += length;
 
+	if (server->ops->is_status_pending &&
+	    server->ops->is_status_pending(buf, server, 0)) {
+		discard_remaining_data(server);
+		return -1;
+	}
+
 	/* Was the SMB read successful? */
 	rdata->result = server->ops->map_error(buf, false);
 	if (rdata->result != 0) {
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 4fbd92d2e113..a763cd3d9e7c 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2999,8 +2999,7 @@ ip_rfc1001_connect(struct TCP_Server_Info *server)
 	if (ses_init_buf) {
 		ses_init_buf->trailer.session_req.called_len = 32;
 
-		if (server->server_RFC1001_name &&
-		    server->server_RFC1001_name[0] != 0)
+		if (server->server_RFC1001_name[0] != 0)
 			rfc1002mangle(ses_init_buf->trailer.
 				      session_req.called_name,
 				      server->server_RFC1001_name,
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 10f8d5cf5681..42e1f440eb1e 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1106,21 +1106,25 @@ parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp,
 {
 	char *data_offset;
 	struct create_context *cc;
-	unsigned int next = 0;
+	unsigned int next;
+	unsigned int remaining;
 	char *name;
 
 	data_offset = (char *)rsp + 4 + le32_to_cpu(rsp->CreateContextsOffset);
+	remaining = le32_to_cpu(rsp->CreateContextsLength);
 	cc = (struct create_context *)data_offset;
-	do {
-		cc = (struct create_context *)((char *)cc + next);
+	while (remaining >= sizeof(struct create_context)) {
 		name = le16_to_cpu(cc->NameOffset) + (char *)cc;
-		if (le16_to_cpu(cc->NameLength) != 4 ||
-		    strncmp(name, "RqLs", 4)) {
-			next = le32_to_cpu(cc->Next);
-			continue;
-		}
-		return server->ops->parse_lease_buf(cc, epoch);
-	} while (next != 0);
+		if (le16_to_cpu(cc->NameLength) == 4 &&
+		    strncmp(name, "RqLs", 4) == 0)
+			return server->ops->parse_lease_buf(cc, epoch);
+
+		next = le32_to_cpu(cc->Next);
+		if (!next)
+			break;
+		remaining -= next;
+		cc = (struct create_context *)((char *)cc + next);
+	}
 
 	return 0;
 }
diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c
index a4232ec4f2ba..699b7868108f 100644
--- a/fs/cifs/smbencrypt.c
+++ b/fs/cifs/smbencrypt.c
@@ -23,6 +23,7 @@
    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */
 
+#include <crypto/skcipher.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
@@ -70,31 +71,42 @@ smbhash(unsigned char *out, const unsigned char *in, unsigned char *key)
 {
 	int rc;
 	unsigned char key2[8];
-	struct crypto_blkcipher *tfm_des;
+	struct crypto_skcipher *tfm_des;
 	struct scatterlist sgin, sgout;
-	struct blkcipher_desc desc;
+	struct skcipher_request *req;
 
 	str_to_key(key, key2);
 
-	tfm_des = crypto_alloc_blkcipher("ecb(des)", 0, CRYPTO_ALG_ASYNC);
+	tfm_des = crypto_alloc_skcipher("ecb(des)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm_des)) {
 		rc = PTR_ERR(tfm_des);
 		cifs_dbg(VFS, "could not allocate des crypto API\n");
 		goto smbhash_err;
 	}
 
-	desc.tfm = tfm_des;
+	req = skcipher_request_alloc(tfm_des, GFP_KERNEL);
+	if (!req) {
+		rc = -ENOMEM;
+		cifs_dbg(VFS, "could not allocate des crypto API\n");
+		goto smbhash_free_skcipher;
+	}
 
-	crypto_blkcipher_setkey(tfm_des, key2, 8);
+	crypto_skcipher_setkey(tfm_des, key2, 8);
 
 	sg_init_one(&sgin, in, 8);
 	sg_init_one(&sgout, out, 8);
 
-	rc = crypto_blkcipher_encrypt(&desc, &sgout, &sgin, 8);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, &sgin, &sgout, 8, NULL);
+
+	rc = crypto_skcipher_encrypt(req);
 	if (rc)
 		cifs_dbg(VFS, "could not encrypt crypt key rc: %d\n", rc);
 
-	crypto_free_blkcipher(tfm_des);
+	skcipher_request_free(req);
+
+smbhash_free_skcipher:
+	crypto_free_skcipher(tfm_des);
 smbhash_err:
 	return rc;
 }
diff --git a/fs/dax.c b/fs/dax.c
index fc2e3141138b..bbb2ad783770 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -79,15 +79,14 @@ struct page *read_dax_sector(struct block_device *bdev, sector_t n)
 }
 
 /*
- * dax_clear_blocks() is called from within transaction context from XFS,
+ * dax_clear_sectors() is called from within transaction context from XFS,
  * and hence this means the stack from this point must follow GFP_NOFS
  * semantics for all operations.
  */
-int dax_clear_blocks(struct inode *inode, sector_t block, long _size)
+int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size)
 {
-	struct block_device *bdev = inode->i_sb->s_bdev;
 	struct blk_dax_ctl dax = {
-		.sector = block << (inode->i_blkbits - 9),
+		.sector = _sector,
 		.size = _size,
 	};
 
@@ -109,7 +108,7 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long _size)
 	wmb_pmem();
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dax_clear_blocks);
+EXPORT_SYMBOL_GPL(dax_clear_sectors);
 
 /* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */
 static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first,
@@ -485,11 +484,10 @@ static int dax_writeback_one(struct block_device *bdev,
  * end]. This is required by data integrity operations to ensure file data is
  * on persistent storage prior to completion of the operation.
  */
-int dax_writeback_mapping_range(struct address_space *mapping, loff_t start,
-		loff_t end)
+int dax_writeback_mapping_range(struct address_space *mapping,
+		struct block_device *bdev, struct writeback_control *wbc)
 {
 	struct inode *inode = mapping->host;
-	struct block_device *bdev = inode->i_sb->s_bdev;
 	pgoff_t start_index, end_index, pmd_index;
 	pgoff_t indices[PAGEVEC_SIZE];
 	struct pagevec pvec;
@@ -500,8 +498,11 @@ int dax_writeback_mapping_range(struct address_space *mapping, loff_t start,
 	if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
 		return -EIO;
 
-	start_index = start >> PAGE_CACHE_SHIFT;
-	end_index = end >> PAGE_CACHE_SHIFT;
+	if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL)
+		return 0;
+
+	start_index = wbc->range_start >> PAGE_CACHE_SHIFT;
+	end_index = wbc->range_end >> PAGE_CACHE_SHIFT;
 	pmd_index = DAX_PMD_INDEX(start_index);
 
 	rcu_read_lock();
@@ -1055,6 +1056,7 @@ EXPORT_SYMBOL_GPL(dax_pmd_fault);
 int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct file *file = vma->vm_file;
+	int error;
 
 	/*
 	 * We pass NO_SECTOR to dax_radix_entry() because we expect that a
@@ -1064,7 +1066,13 @@ int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	 * saves us from having to make a call to get_block() here to look
 	 * up the sector.
 	 */
-	dax_radix_entry(file->f_mapping, vmf->pgoff, NO_SECTOR, false, true);
+	error = dax_radix_entry(file->f_mapping, vmf->pgoff, NO_SECTOR, false,
+			true);
+
+	if (error == -ENOMEM)
+		return VM_FAULT_OOM;
+	if (error)
+		return VM_FAULT_SIGBUS;
 	return VM_FAULT_NOPAGE;
 }
 EXPORT_SYMBOL_GPL(dax_pfn_mkwrite);
diff --git a/fs/dcache.c b/fs/dcache.c
index 92d5140de851..2398f9f94337 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -269,9 +269,6 @@ static inline int dname_external(const struct dentry *dentry)
 	return dentry->d_name.name != dentry->d_iname;
 }
 
-/*
- * Make sure other CPUs see the inode attached before the type is set.
- */
 static inline void __d_set_inode_and_type(struct dentry *dentry,
 					  struct inode *inode,
 					  unsigned type_flags)
@@ -279,28 +276,18 @@ static inline void __d_set_inode_and_type(struct dentry *dentry,
 	unsigned flags;
 
 	dentry->d_inode = inode;
-	smp_wmb();
 	flags = READ_ONCE(dentry->d_flags);
 	flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
 	flags |= type_flags;
 	WRITE_ONCE(dentry->d_flags, flags);
 }
 
-/*
- * Ideally, we want to make sure that other CPUs see the flags cleared before
- * the inode is detached, but this is really a violation of RCU principles
- * since the ordering suggests we should always set inode before flags.
- *
- * We should instead replace or discard the entire dentry - but that sucks
- * performancewise on mass deletion/rename.
- */
 static inline void __d_clear_type_and_inode(struct dentry *dentry)
 {
 	unsigned flags = READ_ONCE(dentry->d_flags);
 
 	flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
 	WRITE_ONCE(dentry->d_flags, flags);
-	smp_wmb();
 	dentry->d_inode = NULL;
 }
 
@@ -370,9 +357,11 @@ static void dentry_unlink_inode(struct dentry * dentry)
 	__releases(dentry->d_inode->i_lock)
 {
 	struct inode *inode = dentry->d_inode;
+
+	raw_write_seqcount_begin(&dentry->d_seq);
 	__d_clear_type_and_inode(dentry);
 	hlist_del_init(&dentry->d_u.d_alias);
-	dentry_rcuwalk_invalidate(dentry);
+	raw_write_seqcount_end(&dentry->d_seq);
 	spin_unlock(&dentry->d_lock);
 	spin_unlock(&inode->i_lock);
 	if (!inode->i_nlink)
@@ -1758,8 +1747,9 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 	spin_lock(&dentry->d_lock);
 	if (inode)
 		hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
+	raw_write_seqcount_begin(&dentry->d_seq);
 	__d_set_inode_and_type(dentry, inode, add_flags);
-	dentry_rcuwalk_invalidate(dentry);
+	raw_write_seqcount_end(&dentry->d_seq);
 	spin_unlock(&dentry->d_lock);
 	fsnotify_d_instantiate(dentry, inode);
 }
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 1f107fd51328..655f21f99160 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -575,6 +575,26 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx)
 	mutex_unlock(&allocated_ptys_lock);
 }
 
+/*
+ * pty code needs to hold extra references in case of last /dev/tty close
+ */
+
+void devpts_add_ref(struct inode *ptmx_inode)
+{
+	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+
+	atomic_inc(&sb->s_active);
+	ihold(ptmx_inode);
+}
+
+void devpts_del_ref(struct inode *ptmx_inode)
+{
+	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+
+	iput(ptmx_inode);
+	deactivate_super(sb);
+}
+
 /**
  * devpts_pty_new -- create a new inode in /dev/pts/
  * @ptmx_inode: inode of the master
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 1b2f7ffc8b84..d6a9012d42ad 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -472,8 +472,8 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio)
 		dio->io_error = -EIO;
 
 	if (dio->is_async && dio->rw == READ && dio->should_dirty) {
-		bio_check_pages_dirty(bio);	/* transfers ownership */
 		err = bio->bi_error;
+		bio_check_pages_dirty(bio);	/* transfers ownership */
 	} else {
 		bio_for_each_segment_all(bvec, bio, i) {
 			struct page *page = bvec->bv_page;
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 80d6901493cf..11255cbcb2db 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -23,6 +23,8 @@
  * 02111-1307, USA.
  */
 
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
 #include <linux/fs.h>
 #include <linux/mount.h>
 #include <linux/pagemap.h>
@@ -30,7 +32,6 @@
 #include <linux/compiler.h>
 #include <linux/key.h>
 #include <linux/namei.h>
-#include <linux/crypto.h>
 #include <linux/file.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
@@ -74,6 +75,19 @@ void ecryptfs_from_hex(char *dst, char *src, int dst_size)
 	}
 }
 
+static int ecryptfs_hash_digest(struct crypto_shash *tfm,
+				char *src, int len, char *dst)
+{
+	SHASH_DESC_ON_STACK(desc, tfm);
+	int err;
+
+	desc->tfm = tfm;
+	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	err = crypto_shash_digest(desc, src, len, dst);
+	shash_desc_zero(desc);
+	return err;
+}
+
 /**
  * ecryptfs_calculate_md5 - calculates the md5 of @src
  * @dst: Pointer to 16 bytes of allocated memory
@@ -88,45 +102,26 @@ static int ecryptfs_calculate_md5(char *dst,
 				  struct ecryptfs_crypt_stat *crypt_stat,
 				  char *src, int len)
 {
-	struct scatterlist sg;
-	struct hash_desc desc = {
-		.tfm = crypt_stat->hash_tfm,
-		.flags = CRYPTO_TFM_REQ_MAY_SLEEP
-	};
+	struct crypto_shash *tfm;
 	int rc = 0;
 
 	mutex_lock(&crypt_stat->cs_hash_tfm_mutex);
-	sg_init_one(&sg, (u8 *)src, len);
-	if (!desc.tfm) {
-		desc.tfm = crypto_alloc_hash(ECRYPTFS_DEFAULT_HASH, 0,
-					     CRYPTO_ALG_ASYNC);
-		if (IS_ERR(desc.tfm)) {
-			rc = PTR_ERR(desc.tfm);
+	tfm = crypt_stat->hash_tfm;
+	if (!tfm) {
+		tfm = crypto_alloc_shash(ECRYPTFS_DEFAULT_HASH, 0, 0);
+		if (IS_ERR(tfm)) {
+			rc = PTR_ERR(tfm);
 			ecryptfs_printk(KERN_ERR, "Error attempting to "
 					"allocate crypto context; rc = [%d]\n",
 					rc);
 			goto out;
 		}
-		crypt_stat->hash_tfm = desc.tfm;
-	}
-	rc = crypto_hash_init(&desc);
-	if (rc) {
-		printk(KERN_ERR
-		       "%s: Error initializing crypto hash; rc = [%d]\n",
-		       __func__, rc);
-		goto out;
+		crypt_stat->hash_tfm = tfm;
 	}
-	rc = crypto_hash_update(&desc, &sg, len);
+	rc = ecryptfs_hash_digest(tfm, src, len, dst);
 	if (rc) {
 		printk(KERN_ERR
-		       "%s: Error updating crypto hash; rc = [%d]\n",
-		       __func__, rc);
-		goto out;
-	}
-	rc = crypto_hash_final(&desc, dst);
-	if (rc) {
-		printk(KERN_ERR
-		       "%s: Error finalizing crypto hash; rc = [%d]\n",
+		       "%s: Error computing crypto hash; rc = [%d]\n",
 		       __func__, rc);
 		goto out;
 	}
@@ -234,10 +229,8 @@ void ecryptfs_destroy_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat)
 {
 	struct ecryptfs_key_sig *key_sig, *key_sig_tmp;
 
-	if (crypt_stat->tfm)
-		crypto_free_ablkcipher(crypt_stat->tfm);
-	if (crypt_stat->hash_tfm)
-		crypto_free_hash(crypt_stat->hash_tfm);
+	crypto_free_skcipher(crypt_stat->tfm);
+	crypto_free_shash(crypt_stat->hash_tfm);
 	list_for_each_entry_safe(key_sig, key_sig_tmp,
 				 &crypt_stat->keysig_list, crypt_stat_list) {
 		list_del(&key_sig->crypt_stat_list);
@@ -342,7 +335,7 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
 			     struct scatterlist *src_sg, int size,
 			     unsigned char *iv, int op)
 {
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	struct extent_crypt_result ecr;
 	int rc = 0;
 
@@ -358,20 +351,20 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
 	init_completion(&ecr.completion);
 
 	mutex_lock(&crypt_stat->cs_tfm_mutex);
-	req = ablkcipher_request_alloc(crypt_stat->tfm, GFP_NOFS);
+	req = skcipher_request_alloc(crypt_stat->tfm, GFP_NOFS);
 	if (!req) {
 		mutex_unlock(&crypt_stat->cs_tfm_mutex);
 		rc = -ENOMEM;
 		goto out;
 	}
 
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 			extent_crypt_complete, &ecr);
 	/* Consider doing this once, when the file is opened */
 	if (!(crypt_stat->flags & ECRYPTFS_KEY_SET)) {
-		rc = crypto_ablkcipher_setkey(crypt_stat->tfm, crypt_stat->key,
-					      crypt_stat->key_size);
+		rc = crypto_skcipher_setkey(crypt_stat->tfm, crypt_stat->key,
+					    crypt_stat->key_size);
 		if (rc) {
 			ecryptfs_printk(KERN_ERR,
 					"Error setting key; rc = [%d]\n",
@@ -383,9 +376,9 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
 		crypt_stat->flags |= ECRYPTFS_KEY_SET;
 	}
 	mutex_unlock(&crypt_stat->cs_tfm_mutex);
-	ablkcipher_request_set_crypt(req, src_sg, dst_sg, size, iv);
-	rc = op == ENCRYPT ? crypto_ablkcipher_encrypt(req) :
-			     crypto_ablkcipher_decrypt(req);
+	skcipher_request_set_crypt(req, src_sg, dst_sg, size, iv);
+	rc = op == ENCRYPT ? crypto_skcipher_encrypt(req) :
+			     crypto_skcipher_decrypt(req);
 	if (rc == -EINPROGRESS || rc == -EBUSY) {
 		struct extent_crypt_result *ecr = req->base.data;
 
@@ -394,7 +387,7 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
 		reinit_completion(&ecr->completion);
 	}
 out:
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	return rc;
 }
 
@@ -622,7 +615,7 @@ int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat)
 						    crypt_stat->cipher, "cbc");
 	if (rc)
 		goto out_unlock;
-	crypt_stat->tfm = crypto_alloc_ablkcipher(full_alg_name, 0, 0);
+	crypt_stat->tfm = crypto_alloc_skcipher(full_alg_name, 0, 0);
 	if (IS_ERR(crypt_stat->tfm)) {
 		rc = PTR_ERR(crypt_stat->tfm);
 		crypt_stat->tfm = NULL;
@@ -631,7 +624,7 @@ int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat)
 				full_alg_name);
 		goto out_free;
 	}
-	crypto_ablkcipher_set_flags(crypt_stat->tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	crypto_skcipher_set_flags(crypt_stat->tfm, CRYPTO_TFM_REQ_WEAK_KEY);
 	rc = 0;
 out_free:
 	kfree(full_alg_name);
@@ -1591,7 +1584,7 @@ out:
  * event, regardless of whether this function succeeds for fails.
  */
 static int
-ecryptfs_process_key_cipher(struct crypto_blkcipher **key_tfm,
+ecryptfs_process_key_cipher(struct crypto_skcipher **key_tfm,
 			    char *cipher_name, size_t *key_size)
 {
 	char dummy_key[ECRYPTFS_MAX_KEY_BYTES];
@@ -1609,21 +1602,18 @@ ecryptfs_process_key_cipher(struct crypto_blkcipher **key_tfm,
 						    "ecb");
 	if (rc)
 		goto out;
-	*key_tfm = crypto_alloc_blkcipher(full_alg_name, 0, CRYPTO_ALG_ASYNC);
+	*key_tfm = crypto_alloc_skcipher(full_alg_name, 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(*key_tfm)) {
 		rc = PTR_ERR(*key_tfm);
 		printk(KERN_ERR "Unable to allocate crypto cipher with name "
 		       "[%s]; rc = [%d]\n", full_alg_name, rc);
 		goto out;
 	}
-	crypto_blkcipher_set_flags(*key_tfm, CRYPTO_TFM_REQ_WEAK_KEY);
-	if (*key_size == 0) {
-		struct blkcipher_alg *alg = crypto_blkcipher_alg(*key_tfm);
-
-		*key_size = alg->max_keysize;
-	}
+	crypto_skcipher_set_flags(*key_tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	if (*key_size == 0)
+		*key_size = crypto_skcipher_default_keysize(*key_tfm);
 	get_random_bytes(dummy_key, *key_size);
-	rc = crypto_blkcipher_setkey(*key_tfm, dummy_key, *key_size);
+	rc = crypto_skcipher_setkey(*key_tfm, dummy_key, *key_size);
 	if (rc) {
 		printk(KERN_ERR "Error attempting to set key of size [%zd] for "
 		       "cipher [%s]; rc = [%d]\n", *key_size, full_alg_name,
@@ -1660,8 +1650,7 @@ int ecryptfs_destroy_crypto(void)
 	list_for_each_entry_safe(key_tfm, key_tfm_tmp, &key_tfm_list,
 				 key_tfm_list) {
 		list_del(&key_tfm->key_tfm_list);
-		if (key_tfm->key_tfm)
-			crypto_free_blkcipher(key_tfm->key_tfm);
+		crypto_free_skcipher(key_tfm->key_tfm);
 		kmem_cache_free(ecryptfs_key_tfm_cache, key_tfm);
 	}
 	mutex_unlock(&key_tfm_list_mutex);
@@ -1747,7 +1736,7 @@ int ecryptfs_tfm_exists(char *cipher_name, struct ecryptfs_key_tfm **key_tfm)
  * Searches for cached item first, and creates new if not found.
  * Returns 0 on success, non-zero if adding new cipher failed
  */
-int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_blkcipher **tfm,
+int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_skcipher **tfm,
 					       struct mutex **tfm_mutex,
 					       char *cipher_name)
 {
@@ -2120,7 +2109,7 @@ out:
 int ecryptfs_set_f_namelen(long *namelen, long lower_namelen,
 			   struct ecryptfs_mount_crypt_stat *mount_crypt_stat)
 {
-	struct blkcipher_desc desc;
+	struct crypto_skcipher *tfm;
 	struct mutex *tfm_mutex;
 	size_t cipher_blocksize;
 	int rc;
@@ -2130,7 +2119,7 @@ int ecryptfs_set_f_namelen(long *namelen, long lower_namelen,
 		return 0;
 	}
 
-	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&desc.tfm, &tfm_mutex,
+	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&tfm, &tfm_mutex,
 			mount_crypt_stat->global_default_fn_cipher_name);
 	if (unlikely(rc)) {
 		(*namelen) = 0;
@@ -2138,7 +2127,7 @@ int ecryptfs_set_f_namelen(long *namelen, long lower_namelen,
 	}
 
 	mutex_lock(tfm_mutex);
-	cipher_blocksize = crypto_blkcipher_blocksize(desc.tfm);
+	cipher_blocksize = crypto_skcipher_blocksize(tfm);
 	mutex_unlock(tfm_mutex);
 
 	/* Return an exact amount for the common cases */
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 7b39260c7bba..b7f81287c688 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -28,6 +28,7 @@
 #ifndef ECRYPTFS_KERNEL_H
 #define ECRYPTFS_KERNEL_H
 
+#include <crypto/skcipher.h>
 #include <keys/user-type.h>
 #include <keys/encrypted-type.h>
 #include <linux/fs.h>
@@ -38,7 +39,6 @@
 #include <linux/nsproxy.h>
 #include <linux/backing-dev.h>
 #include <linux/ecryptfs.h>
-#include <linux/crypto.h>
 
 #define ECRYPTFS_DEFAULT_IV_BYTES 16
 #define ECRYPTFS_DEFAULT_EXTENT_SIZE 4096
@@ -233,9 +233,9 @@ struct ecryptfs_crypt_stat {
 	size_t extent_shift;
 	unsigned int extent_mask;
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
-	struct crypto_ablkcipher *tfm;
-	struct crypto_hash *hash_tfm; /* Crypto context for generating
-				       * the initialization vectors */
+	struct crypto_skcipher *tfm;
+	struct crypto_shash *hash_tfm; /* Crypto context for generating
+					* the initialization vectors */
 	unsigned char cipher[ECRYPTFS_MAX_CIPHER_NAME_SIZE + 1];
 	unsigned char key[ECRYPTFS_MAX_KEY_BYTES];
 	unsigned char root_iv[ECRYPTFS_MAX_IV_BYTES];
@@ -309,7 +309,7 @@ struct ecryptfs_global_auth_tok {
  * keeps a list of crypto API contexts around to use when needed.
  */
 struct ecryptfs_key_tfm {
-	struct crypto_blkcipher *key_tfm;
+	struct crypto_skcipher *key_tfm;
 	size_t key_size;
 	struct mutex key_tfm_mutex;
 	struct list_head key_tfm_list;
@@ -659,7 +659,7 @@ ecryptfs_add_new_key_tfm(struct ecryptfs_key_tfm **key_tfm, char *cipher_name,
 int ecryptfs_init_crypto(void);
 int ecryptfs_destroy_crypto(void);
 int ecryptfs_tfm_exists(char *cipher_name, struct ecryptfs_key_tfm **key_tfm);
-int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_blkcipher **tfm,
+int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_skcipher **tfm,
 					       struct mutex **tfm_mutex,
 					       char *cipher_name);
 int ecryptfs_keyring_auth_tok_for_sig(struct key **auth_tok_key,
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 4e685ac1024d..0a8f1b469a63 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -29,7 +29,6 @@
 #include <linux/dcache.h>
 #include <linux/namei.h>
 #include <linux/mount.h>
-#include <linux/crypto.h>
 #include <linux/fs_stack.h>
 #include <linux/slab.h>
 #include <linux/xattr.h>
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 6bd67e2011f0..c5c84dfb5b3e 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -25,11 +25,12 @@
  * 02111-1307, USA.
  */
 
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
 #include <linux/string.h>
 #include <linux/pagemap.h>
 #include <linux/key.h>
 #include <linux/random.h>
-#include <linux/crypto.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include "ecryptfs_kernel.h"
@@ -601,12 +602,13 @@ struct ecryptfs_write_tag_70_packet_silly_stack {
 	struct ecryptfs_auth_tok *auth_tok;
 	struct scatterlist src_sg[2];
 	struct scatterlist dst_sg[2];
-	struct blkcipher_desc desc;
+	struct crypto_skcipher *skcipher_tfm;
+	struct skcipher_request *skcipher_req;
 	char iv[ECRYPTFS_MAX_IV_BYTES];
 	char hash[ECRYPTFS_TAG_70_DIGEST_SIZE];
 	char tmp_hash[ECRYPTFS_TAG_70_DIGEST_SIZE];
-	struct hash_desc hash_desc;
-	struct scatterlist hash_sg;
+	struct crypto_shash *hash_tfm;
+	struct shash_desc *hash_desc;
 };
 
 /**
@@ -629,14 +631,13 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 	struct key *auth_tok_key = NULL;
 	int rc = 0;
 
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	s = kzalloc(sizeof(*s), GFP_KERNEL);
 	if (!s) {
 		printk(KERN_ERR "%s: Out of memory whilst trying to kmalloc "
 		       "[%zd] bytes of kernel memory\n", __func__, sizeof(*s));
 		rc = -ENOMEM;
 		goto out;
 	}
-	s->desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 	(*packet_size) = 0;
 	rc = ecryptfs_find_auth_tok_for_sig(
 		&auth_tok_key,
@@ -649,7 +650,7 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		goto out;
 	}
 	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(
-		&s->desc.tfm,
+		&s->skcipher_tfm,
 		&s->tfm_mutex, mount_crypt_stat->global_default_fn_cipher_name);
 	if (unlikely(rc)) {
 		printk(KERN_ERR "Internal error whilst attempting to get "
@@ -658,7 +659,7 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		goto out;
 	}
 	mutex_lock(s->tfm_mutex);
-	s->block_size = crypto_blkcipher_blocksize(s->desc.tfm);
+	s->block_size = crypto_skcipher_blocksize(s->skcipher_tfm);
 	/* Plus one for the \0 separator between the random prefix
 	 * and the plaintext filename */
 	s->num_rand_bytes = (ECRYPTFS_FILENAME_MIN_RANDOM_PREPEND_BYTES + 1);
@@ -691,6 +692,19 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		rc = -EINVAL;
 		goto out_unlock;
 	}
+
+	s->skcipher_req = skcipher_request_alloc(s->skcipher_tfm, GFP_KERNEL);
+	if (!s->skcipher_req) {
+		printk(KERN_ERR "%s: Out of kernel memory whilst attempting to "
+		       "skcipher_request_alloc for %s\n", __func__,
+		       crypto_skcipher_driver_name(s->skcipher_tfm));
+		rc = -ENOMEM;
+		goto out_unlock;
+	}
+
+	skcipher_request_set_callback(s->skcipher_req,
+				      CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
+
 	s->block_aligned_filename = kzalloc(s->block_aligned_filename_size,
 					    GFP_KERNEL);
 	if (!s->block_aligned_filename) {
@@ -700,7 +714,6 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		rc = -ENOMEM;
 		goto out_unlock;
 	}
-	s->i = 0;
 	dest[s->i++] = ECRYPTFS_TAG_70_PACKET_TYPE;
 	rc = ecryptfs_write_packet_length(&dest[s->i],
 					  (ECRYPTFS_SIG_SIZE
@@ -738,40 +751,36 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		       "password tokens\n", __func__);
 		goto out_free_unlock;
 	}
-	sg_init_one(
-		&s->hash_sg,
-		(u8 *)s->auth_tok->token.password.session_key_encryption_key,
-		s->auth_tok->token.password.session_key_encryption_key_bytes);
-	s->hash_desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
-	s->hash_desc.tfm = crypto_alloc_hash(ECRYPTFS_TAG_70_DIGEST, 0,
-					     CRYPTO_ALG_ASYNC);
-	if (IS_ERR(s->hash_desc.tfm)) {
-			rc = PTR_ERR(s->hash_desc.tfm);
+	s->hash_tfm = crypto_alloc_shash(ECRYPTFS_TAG_70_DIGEST, 0, 0);
+	if (IS_ERR(s->hash_tfm)) {
+			rc = PTR_ERR(s->hash_tfm);
 			printk(KERN_ERR "%s: Error attempting to "
 			       "allocate hash crypto context; rc = [%d]\n",
 			       __func__, rc);
 			goto out_free_unlock;
 	}
-	rc = crypto_hash_init(&s->hash_desc);
-	if (rc) {
-		printk(KERN_ERR
-		       "%s: Error initializing crypto hash; rc = [%d]\n",
-		       __func__, rc);
-		goto out_release_free_unlock;
-	}
-	rc = crypto_hash_update(
-		&s->hash_desc, &s->hash_sg,
-		s->auth_tok->token.password.session_key_encryption_key_bytes);
-	if (rc) {
-		printk(KERN_ERR
-		       "%s: Error updating crypto hash; rc = [%d]\n",
-		       __func__, rc);
+
+	s->hash_desc = kmalloc(sizeof(*s->hash_desc) +
+			       crypto_shash_descsize(s->hash_tfm), GFP_KERNEL);
+	if (!s->hash_desc) {
+		printk(KERN_ERR "%s: Out of kernel memory whilst attempting to "
+		       "kmalloc [%zd] bytes\n", __func__,
+		       sizeof(*s->hash_desc) +
+		       crypto_shash_descsize(s->hash_tfm));
+		rc = -ENOMEM;
 		goto out_release_free_unlock;
 	}
-	rc = crypto_hash_final(&s->hash_desc, s->hash);
+
+	s->hash_desc->tfm = s->hash_tfm;
+	s->hash_desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	rc = crypto_shash_digest(s->hash_desc,
+				 (u8 *)s->auth_tok->token.password.session_key_encryption_key,
+				 s->auth_tok->token.password.session_key_encryption_key_bytes,
+				 s->hash);
 	if (rc) {
 		printk(KERN_ERR
-		       "%s: Error finalizing crypto hash; rc = [%d]\n",
+		       "%s: Error computing crypto hash; rc = [%d]\n",
 		       __func__, rc);
 		goto out_release_free_unlock;
 	}
@@ -780,27 +789,12 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 			s->hash[(s->j % ECRYPTFS_TAG_70_DIGEST_SIZE)];
 		if ((s->j % ECRYPTFS_TAG_70_DIGEST_SIZE)
 		    == (ECRYPTFS_TAG_70_DIGEST_SIZE - 1)) {
-			sg_init_one(&s->hash_sg, (u8 *)s->hash,
-				    ECRYPTFS_TAG_70_DIGEST_SIZE);
-			rc = crypto_hash_init(&s->hash_desc);
-			if (rc) {
-				printk(KERN_ERR
-				       "%s: Error initializing crypto hash; "
-				       "rc = [%d]\n", __func__, rc);
-				goto out_release_free_unlock;
-			}
-			rc = crypto_hash_update(&s->hash_desc, &s->hash_sg,
-						ECRYPTFS_TAG_70_DIGEST_SIZE);
+			rc = crypto_shash_digest(s->hash_desc, (u8 *)s->hash,
+						ECRYPTFS_TAG_70_DIGEST_SIZE,
+						s->tmp_hash);
 			if (rc) {
 				printk(KERN_ERR
-				       "%s: Error updating crypto hash; "
-				       "rc = [%d]\n", __func__, rc);
-				goto out_release_free_unlock;
-			}
-			rc = crypto_hash_final(&s->hash_desc, s->tmp_hash);
-			if (rc) {
-				printk(KERN_ERR
-				       "%s: Error finalizing crypto hash; "
+				       "%s: Error computing crypto hash; "
 				       "rc = [%d]\n", __func__, rc);
 				goto out_release_free_unlock;
 			}
@@ -834,10 +828,8 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 	 * of the IV here, so we just use 0's for the IV. Note the
 	 * constraint that ECRYPTFS_FILENAME_MIN_RANDOM_PREPEND_BYTES
 	 * >= ECRYPTFS_MAX_IV_BYTES. */
-	memset(s->iv, 0, ECRYPTFS_MAX_IV_BYTES);
-	s->desc.info = s->iv;
-	rc = crypto_blkcipher_setkey(
-		s->desc.tfm,
+	rc = crypto_skcipher_setkey(
+		s->skcipher_tfm,
 		s->auth_tok->token.password.session_key_encryption_key,
 		mount_crypt_stat->global_default_fn_cipher_key_bytes);
 	if (rc < 0) {
@@ -850,8 +842,9 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 		       mount_crypt_stat->global_default_fn_cipher_key_bytes);
 		goto out_release_free_unlock;
 	}
-	rc = crypto_blkcipher_encrypt_iv(&s->desc, s->dst_sg, s->src_sg,
-					 s->block_aligned_filename_size);
+	skcipher_request_set_crypt(s->skcipher_req, s->src_sg, s->dst_sg,
+				   s->block_aligned_filename_size, s->iv);
+	rc = crypto_skcipher_encrypt(s->skcipher_req);
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to encrypt filename; "
 		       "rc = [%d]\n", __func__, rc);
@@ -861,7 +854,7 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 	(*packet_size) = s->i;
 	(*remaining_bytes) -= (*packet_size);
 out_release_free_unlock:
-	crypto_free_hash(s->hash_desc.tfm);
+	crypto_free_shash(s->hash_tfm);
 out_free_unlock:
 	kzfree(s->block_aligned_filename);
 out_unlock:
@@ -871,6 +864,8 @@ out:
 		up_write(&(auth_tok_key->sem));
 		key_put(auth_tok_key);
 	}
+	skcipher_request_free(s->skcipher_req);
+	kzfree(s->hash_desc);
 	kfree(s);
 	return rc;
 }
@@ -888,7 +883,8 @@ struct ecryptfs_parse_tag_70_packet_silly_stack {
 	struct ecryptfs_auth_tok *auth_tok;
 	struct scatterlist src_sg[2];
 	struct scatterlist dst_sg[2];
-	struct blkcipher_desc desc;
+	struct crypto_skcipher *skcipher_tfm;
+	struct skcipher_request *skcipher_req;
 	char fnek_sig_hex[ECRYPTFS_SIG_SIZE_HEX + 1];
 	char iv[ECRYPTFS_MAX_IV_BYTES];
 	char cipher_string[ECRYPTFS_MAX_CIPHER_NAME_SIZE + 1];
@@ -922,14 +918,13 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
 	(*packet_size) = 0;
 	(*filename_size) = 0;
 	(*filename) = NULL;
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	s = kzalloc(sizeof(*s), GFP_KERNEL);
 	if (!s) {
 		printk(KERN_ERR "%s: Out of memory whilst trying to kmalloc "
 		       "[%zd] bytes of kernel memory\n", __func__, sizeof(*s));
 		rc = -ENOMEM;
 		goto out;
 	}
-	s->desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 	if (max_packet_size < ECRYPTFS_TAG_70_MIN_METADATA_SIZE) {
 		printk(KERN_WARNING "%s: max_packet_size is [%zd]; it must be "
 		       "at least [%d]\n", __func__, max_packet_size,
@@ -992,7 +987,7 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
 		       rc);
 		goto out;
 	}
-	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&s->desc.tfm,
+	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&s->skcipher_tfm,
 							&s->tfm_mutex,
 							s->cipher_string);
 	if (unlikely(rc)) {
@@ -1030,12 +1025,23 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
 		       __func__, rc, s->block_aligned_filename_size);
 		goto out_free_unlock;
 	}
+
+	s->skcipher_req = skcipher_request_alloc(s->skcipher_tfm, GFP_KERNEL);
+	if (!s->skcipher_req) {
+		printk(KERN_ERR "%s: Out of kernel memory whilst attempting to "
+		       "skcipher_request_alloc for %s\n", __func__,
+		       crypto_skcipher_driver_name(s->skcipher_tfm));
+		rc = -ENOMEM;
+		goto out_free_unlock;
+	}
+
+	skcipher_request_set_callback(s->skcipher_req,
+				      CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
+
 	/* The characters in the first block effectively do the job of
 	 * the IV here, so we just use 0's for the IV. Note the
 	 * constraint that ECRYPTFS_FILENAME_MIN_RANDOM_PREPEND_BYTES
 	 * >= ECRYPTFS_MAX_IV_BYTES. */
-	memset(s->iv, 0, ECRYPTFS_MAX_IV_BYTES);
-	s->desc.info = s->iv;
 	/* TODO: Support other key modules than passphrase for
 	 * filename encryption */
 	if (s->auth_tok->token_type != ECRYPTFS_PASSWORD) {
@@ -1044,8 +1050,8 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
 		       "password tokens\n", __func__);
 		goto out_free_unlock;
 	}
-	rc = crypto_blkcipher_setkey(
-		s->desc.tfm,
+	rc = crypto_skcipher_setkey(
+		s->skcipher_tfm,
 		s->auth_tok->token.password.session_key_encryption_key,
 		mount_crypt_stat->global_default_fn_cipher_key_bytes);
 	if (rc < 0) {
@@ -1058,14 +1064,14 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
 		       mount_crypt_stat->global_default_fn_cipher_key_bytes);
 		goto out_free_unlock;
 	}
-	rc = crypto_blkcipher_decrypt_iv(&s->desc, s->dst_sg, s->src_sg,
-					 s->block_aligned_filename_size);
+	skcipher_request_set_crypt(s->skcipher_req, s->src_sg, s->dst_sg,
+				   s->block_aligned_filename_size, s->iv);
+	rc = crypto_skcipher_decrypt(s->skcipher_req);
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to decrypt filename; "
 		       "rc = [%d]\n", __func__, rc);
 		goto out_free_unlock;
 	}
-	s->i = 0;
 	while (s->decrypted_filename[s->i] != '\0'
 	       && s->i < s->block_aligned_filename_size)
 		s->i++;
@@ -1108,6 +1114,7 @@ out:
 		up_write(&(auth_tok_key->sem));
 		key_put(auth_tok_key);
 	}
+	skcipher_request_free(s->skcipher_req);
 	kfree(s);
 	return rc;
 }
@@ -1667,9 +1674,8 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 	struct scatterlist dst_sg[2];
 	struct scatterlist src_sg[2];
 	struct mutex *tfm_mutex;
-	struct blkcipher_desc desc = {
-		.flags = CRYPTO_TFM_REQ_MAY_SLEEP
-	};
+	struct crypto_skcipher *tfm;
+	struct skcipher_request *req = NULL;
 	int rc = 0;
 
 	if (unlikely(ecryptfs_verbosity > 0)) {
@@ -1680,7 +1686,7 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 			auth_tok->token.password.session_key_encryption_key,
 			auth_tok->token.password.session_key_encryption_key_bytes);
 	}
-	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&desc.tfm, &tfm_mutex,
+	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&tfm, &tfm_mutex,
 							crypt_stat->cipher);
 	if (unlikely(rc)) {
 		printk(KERN_ERR "Internal error whilst attempting to get "
@@ -1711,8 +1717,20 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 		goto out;
 	}
 	mutex_lock(tfm_mutex);
-	rc = crypto_blkcipher_setkey(
-		desc.tfm, auth_tok->token.password.session_key_encryption_key,
+	req = skcipher_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		mutex_unlock(tfm_mutex);
+		printk(KERN_ERR "%s: Out of kernel memory whilst attempting to "
+		       "skcipher_request_alloc for %s\n", __func__,
+		       crypto_skcipher_driver_name(tfm));
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
+				      NULL, NULL);
+	rc = crypto_skcipher_setkey(
+		tfm, auth_tok->token.password.session_key_encryption_key,
 		crypt_stat->key_size);
 	if (unlikely(rc < 0)) {
 		mutex_unlock(tfm_mutex);
@@ -1720,8 +1738,10 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 		rc = -EINVAL;
 		goto out;
 	}
-	rc = crypto_blkcipher_decrypt(&desc, dst_sg, src_sg,
-				      auth_tok->session_key.encrypted_key_size);
+	skcipher_request_set_crypt(req, src_sg, dst_sg,
+				   auth_tok->session_key.encrypted_key_size,
+				   NULL);
+	rc = crypto_skcipher_decrypt(req);
 	mutex_unlock(tfm_mutex);
 	if (unlikely(rc)) {
 		printk(KERN_ERR "Error decrypting; rc = [%d]\n", rc);
@@ -1738,6 +1758,7 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 				  crypt_stat->key_size);
 	}
 out:
+	skcipher_request_free(req);
 	return rc;
 }
 
@@ -2191,16 +2212,14 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 	size_t max_packet_size;
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat =
 		crypt_stat->mount_crypt_stat;
-	struct blkcipher_desc desc = {
-		.tfm = NULL,
-		.flags = CRYPTO_TFM_REQ_MAY_SLEEP
-	};
+	struct crypto_skcipher *tfm;
+	struct skcipher_request *req;
 	int rc = 0;
 
 	(*packet_size) = 0;
 	ecryptfs_from_hex(key_rec->sig, auth_tok->token.password.signature,
 			  ECRYPTFS_SIG_SIZE);
-	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&desc.tfm, &tfm_mutex,
+	rc = ecryptfs_get_tfm_and_mutex_for_cipher_name(&tfm, &tfm_mutex,
 							crypt_stat->cipher);
 	if (unlikely(rc)) {
 		printk(KERN_ERR "Internal error whilst attempting to get "
@@ -2209,12 +2228,11 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 		goto out;
 	}
 	if (mount_crypt_stat->global_default_cipher_key_size == 0) {
-		struct blkcipher_alg *alg = crypto_blkcipher_alg(desc.tfm);
-
 		printk(KERN_WARNING "No key size specified at mount; "
-		       "defaulting to [%d]\n", alg->max_keysize);
+		       "defaulting to [%d]\n",
+		       crypto_skcipher_default_keysize(tfm));
 		mount_crypt_stat->global_default_cipher_key_size =
-			alg->max_keysize;
+			crypto_skcipher_default_keysize(tfm);
 	}
 	if (crypt_stat->key_size == 0)
 		crypt_stat->key_size =
@@ -2284,20 +2302,36 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 		goto out;
 	}
 	mutex_lock(tfm_mutex);
-	rc = crypto_blkcipher_setkey(desc.tfm, session_key_encryption_key,
-				     crypt_stat->key_size);
+	rc = crypto_skcipher_setkey(tfm, session_key_encryption_key,
+				    crypt_stat->key_size);
 	if (rc < 0) {
 		mutex_unlock(tfm_mutex);
 		ecryptfs_printk(KERN_ERR, "Error setting key for crypto "
 				"context; rc = [%d]\n", rc);
 		goto out;
 	}
+
+	req = skcipher_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		mutex_unlock(tfm_mutex);
+		ecryptfs_printk(KERN_ERR, "Out of kernel memory whilst "
+				"attempting to skcipher_request_alloc for "
+				"%s\n", crypto_skcipher_driver_name(tfm));
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
+				      NULL, NULL);
+
 	rc = 0;
 	ecryptfs_printk(KERN_DEBUG, "Encrypting [%zd] bytes of the key\n",
 			crypt_stat->key_size);
-	rc = crypto_blkcipher_encrypt(&desc, dst_sg, src_sg,
-				      (*key_rec).enc_key_size);
+	skcipher_request_set_crypt(req, src_sg, dst_sg,
+				   (*key_rec).enc_key_size, NULL);
+	rc = crypto_skcipher_encrypt(req);
 	mutex_unlock(tfm_mutex);
+	skcipher_request_free(req);
 	if (rc) {
 		printk(KERN_ERR "Error encrypting; rc = [%d]\n", rc);
 		goto out;
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index e25b6b06bacf..8b0b4a73116d 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -29,7 +29,6 @@
 #include <linux/module.h>
 #include <linux/namei.h>
 #include <linux/skbuff.h>
-#include <linux/crypto.h>
 #include <linux/mount.h>
 #include <linux/pagemap.h>
 #include <linux/key.h>
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index c6ced4cbf0cf..1f5865263b3e 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -30,7 +30,6 @@
 #include <linux/page-flags.h>
 #include <linux/mount.h>
 #include <linux/file.h>
-#include <linux/crypto.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <asm/unaligned.h>
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index afa1b81c3418..77a486d3a51b 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -29,7 +29,6 @@
 #include <linux/slab.h>
 #include <linux/seq_file.h>
 #include <linux/file.h>
-#include <linux/crypto.h>
 #include <linux/statfs.h>
 #include <linux/magic.h>
 #include "ecryptfs_kernel.h"
diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c
index c424e4813ec8..d48e0d261d78 100644
--- a/fs/efivarfs/file.c
+++ b/fs/efivarfs/file.c
@@ -10,6 +10,7 @@
 #include <linux/efi.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/mount.h>
 
 #include "internal.h"
 
@@ -103,9 +104,78 @@ out_free:
 	return size;
 }
 
+static int
+efivarfs_ioc_getxflags(struct file *file, void __user *arg)
+{
+	struct inode *inode = file->f_mapping->host;
+	unsigned int i_flags;
+	unsigned int flags = 0;
+
+	i_flags = inode->i_flags;
+	if (i_flags & S_IMMUTABLE)
+		flags |= FS_IMMUTABLE_FL;
+
+	if (copy_to_user(arg, &flags, sizeof(flags)))
+		return -EFAULT;
+	return 0;
+}
+
+static int
+efivarfs_ioc_setxflags(struct file *file, void __user *arg)
+{
+	struct inode *inode = file->f_mapping->host;
+	unsigned int flags;
+	unsigned int i_flags = 0;
+	int error;
+
+	if (!inode_owner_or_capable(inode))
+		return -EACCES;
+
+	if (copy_from_user(&flags, arg, sizeof(flags)))
+		return -EFAULT;
+
+	if (flags & ~FS_IMMUTABLE_FL)
+		return -EOPNOTSUPP;
+
+	if (!capable(CAP_LINUX_IMMUTABLE))
+		return -EPERM;
+
+	if (flags & FS_IMMUTABLE_FL)
+		i_flags |= S_IMMUTABLE;
+
+
+	error = mnt_want_write_file(file);
+	if (error)
+		return error;
+
+	inode_lock(inode);
+	inode_set_flags(inode, i_flags, S_IMMUTABLE);
+	inode_unlock(inode);
+
+	mnt_drop_write_file(file);
+
+	return 0;
+}
+
+long
+efivarfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long p)
+{
+	void __user *arg = (void __user *)p;
+
+	switch (cmd) {
+	case FS_IOC_GETFLAGS:
+		return efivarfs_ioc_getxflags(file, arg);
+	case FS_IOC_SETFLAGS:
+		return efivarfs_ioc_setxflags(file, arg);
+	}
+
+	return -ENOTTY;
+}
+
 const struct file_operations efivarfs_file_operations = {
 	.open	= simple_open,
 	.read	= efivarfs_file_read,
 	.write	= efivarfs_file_write,
 	.llseek	= no_llseek,
+	.unlocked_ioctl = efivarfs_file_ioctl,
 };
diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
index 3381b9da9ee6..e2ab6d0497f2 100644
--- a/fs/efivarfs/inode.c
+++ b/fs/efivarfs/inode.c
@@ -15,7 +15,8 @@
 #include "internal.h"
 
 struct inode *efivarfs_get_inode(struct super_block *sb,
-				const struct inode *dir, int mode, dev_t dev)
+				const struct inode *dir, int mode,
+				dev_t dev, bool is_removable)
 {
 	struct inode *inode = new_inode(sb);
 
@@ -23,6 +24,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb,
 		inode->i_ino = get_next_ino();
 		inode->i_mode = mode;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		inode->i_flags = is_removable ? 0 : S_IMMUTABLE;
 		switch (mode & S_IFMT) {
 		case S_IFREG:
 			inode->i_fop = &efivarfs_file_operations;
@@ -102,22 +104,17 @@ static void efivarfs_hex_to_guid(const char *str, efi_guid_t *guid)
 static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 			  umode_t mode, bool excl)
 {
-	struct inode *inode;
+	struct inode *inode = NULL;
 	struct efivar_entry *var;
 	int namelen, i = 0, err = 0;
+	bool is_removable = false;
 
 	if (!efivarfs_valid_name(dentry->d_name.name, dentry->d_name.len))
 		return -EINVAL;
 
-	inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0);
-	if (!inode)
-		return -ENOMEM;
-
 	var = kzalloc(sizeof(struct efivar_entry), GFP_KERNEL);
-	if (!var) {
-		err = -ENOMEM;
-		goto out;
-	}
+	if (!var)
+		return -ENOMEM;
 
 	/* length of the variable name itself: remove GUID and separator */
 	namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1;
@@ -125,6 +122,16 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 	efivarfs_hex_to_guid(dentry->d_name.name + namelen + 1,
 			&var->var.VendorGuid);
 
+	if (efivar_variable_is_removable(var->var.VendorGuid,
+					 dentry->d_name.name, namelen))
+		is_removable = true;
+
+	inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0, is_removable);
+	if (!inode) {
+		err = -ENOMEM;
+		goto out;
+	}
+
 	for (i = 0; i < namelen; i++)
 		var->var.VariableName[i] = dentry->d_name.name[i];
 
@@ -138,7 +145,8 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 out:
 	if (err) {
 		kfree(var);
-		iput(inode);
+		if (inode)
+			iput(inode);
 	}
 	return err;
 }
diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h
index b5ff16addb7c..b4505188e799 100644
--- a/fs/efivarfs/internal.h
+++ b/fs/efivarfs/internal.h
@@ -15,7 +15,8 @@ extern const struct file_operations efivarfs_file_operations;
 extern const struct inode_operations efivarfs_dir_inode_operations;
 extern bool efivarfs_valid_name(const char *str, int len);
 extern struct inode *efivarfs_get_inode(struct super_block *sb,
-			const struct inode *dir, int mode, dev_t dev);
+			const struct inode *dir, int mode, dev_t dev,
+			bool is_removable);
 
 extern struct list_head efivarfs_list;
 
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index b8a564f29107..dd029d13ea61 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -118,8 +118,9 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 	struct dentry *dentry, *root = sb->s_root;
 	unsigned long size = 0;
 	char *name;
-	int len, i;
+	int len;
 	int err = -ENOMEM;
+	bool is_removable = false;
 
 	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
@@ -128,15 +129,17 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 	memcpy(entry->var.VariableName, name16, name_size);
 	memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t));
 
-	len = ucs2_strlen(entry->var.VariableName);
+	len = ucs2_utf8size(entry->var.VariableName);
 
 	/* name, plus '-', plus GUID, plus NUL*/
 	name = kmalloc(len + 1 + EFI_VARIABLE_GUID_LEN + 1, GFP_KERNEL);
 	if (!name)
 		goto fail;
 
-	for (i = 0; i < len; i++)
-		name[i] = entry->var.VariableName[i] & 0xFF;
+	ucs2_as_utf8(name, entry->var.VariableName, len);
+
+	if (efivar_variable_is_removable(entry->var.VendorGuid, name, len))
+		is_removable = true;
 
 	name[len] = '-';
 
@@ -144,7 +147,8 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 
 	name[len + EFI_VARIABLE_GUID_LEN+1] = '\0';
 
-	inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0);
+	inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0,
+				   is_removable);
 	if (!inode)
 		goto fail_name;
 
@@ -200,7 +204,7 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_d_op		= &efivarfs_d_ops;
 	sb->s_time_gran         = 1;
 
-	inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0);
+	inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0, true);
 	if (!inode)
 		return -ENOMEM;
 	inode->i_op = &efivarfs_dir_inode_operations;
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 2c88d683cd91..c1400b109805 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -80,23 +80,6 @@ static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	return ret;
 }
 
-static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct inode *inode = file_inode(vma->vm_file);
-	struct ext2_inode_info *ei = EXT2_I(inode);
-	int ret;
-
-	sb_start_pagefault(inode->i_sb);
-	file_update_time(vma->vm_file);
-	down_read(&ei->dax_sem);
-
-	ret = __dax_mkwrite(vma, vmf, ext2_get_block, NULL);
-
-	up_read(&ei->dax_sem);
-	sb_end_pagefault(inode->i_sb);
-	return ret;
-}
-
 static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
 		struct vm_fault *vmf)
 {
@@ -124,7 +107,7 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
 static const struct vm_operations_struct ext2_dax_vm_ops = {
 	.fault		= ext2_dax_fault,
 	.pmd_fault	= ext2_dax_pmd_fault,
-	.page_mkwrite	= ext2_dax_mkwrite,
+	.page_mkwrite	= ext2_dax_fault,
 	.pfn_mkwrite	= ext2_dax_pfn_mkwrite,
 };
 
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 338eefda70c6..6bd58e6ff038 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -737,8 +737,10 @@ static int ext2_get_blocks(struct inode *inode,
 		 * so that it's not found by another thread before it's
 		 * initialised
 		 */
-		err = dax_clear_blocks(inode, le32_to_cpu(chain[depth-1].key),
-						1 << inode->i_blkbits);
+		err = dax_clear_sectors(inode->i_sb->s_bdev,
+				le32_to_cpu(chain[depth-1].key) <<
+				(inode->i_blkbits - 9),
+				1 << inode->i_blkbits);
 		if (err) {
 			mutex_unlock(&ei->truncate_mutex);
 			goto cleanup;
@@ -874,6 +876,14 @@ ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 static int
 ext2_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
+#ifdef CONFIG_FS_DAX
+	if (dax_mapping(mapping)) {
+		return dax_writeback_mapping_range(mapping,
+						   mapping->host->i_sb->s_bdev,
+						   wbc);
+	}
+#endif
+
 	return mpage_writepages(mapping, wbc, ext2_get_block);
 }
 
@@ -1296,7 +1306,7 @@ void ext2_set_inode_flags(struct inode *inode)
 		inode->i_flags |= S_NOATIME;
 	if (flags & EXT2_DIRSYNC_FL)
 		inode->i_flags |= S_DIRSYNC;
-	if (test_opt(inode->i_sb, DAX))
+	if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode))
 		inode->i_flags |= S_DAX;
 }
 
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index ec0668a60678..fe1f50fe764f 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -191,7 +191,6 @@ static int ext4_init_block_bitmap(struct super_block *sb,
 	/* If checksum is bad mark all blocks used to prevent allocation
 	 * essentially implementing a per-group read-only flag. */
 	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
-		ext4_error(sb, "Checksum bad for group %u", block_group);
 		grp = ext4_get_group_info(sb, block_group);
 		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
 			percpu_counter_sub(&sbi->s_freeclusters_counter,
@@ -442,14 +441,16 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 	}
 	ext4_lock_group(sb, block_group);
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
-
 		err = ext4_init_block_bitmap(sb, bh, block_group, desc);
 		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
 		ext4_unlock_group(sb, block_group);
 		unlock_buffer(bh);
-		if (err)
+		if (err) {
+			ext4_error(sb, "Failed to init block bitmap for group "
+				   "%u: %d", block_group, err);
 			goto out;
+		}
 		goto verify;
 	}
 	ext4_unlock_group(sb, block_group);
diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c
index c8021208a7eb..edc053a81914 100644
--- a/fs/ext4/crypto.c
+++ b/fs/ext4/crypto.c
@@ -18,11 +18,9 @@
  * Special Publication 800-38E and IEEE P1619/D16.
  */
 
-#include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/skcipher.h>
 #include <keys/user-type.h>
 #include <keys/encrypted-type.h>
-#include <linux/crypto.h>
 #include <linux/ecryptfs.h>
 #include <linux/gfp.h>
 #include <linux/kernel.h>
@@ -261,21 +259,21 @@ static int ext4_page_crypto(struct inode *inode,
 
 {
 	u8 xts_tweak[EXT4_XTS_TWEAK_SIZE];
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	DECLARE_EXT4_COMPLETION_RESULT(ecr);
 	struct scatterlist dst, src;
 	struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
 
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		printk_ratelimited(KERN_ERR
 				   "%s: crypto_request_alloc() failed\n",
 				   __func__);
 		return -ENOMEM;
 	}
-	ablkcipher_request_set_callback(
+	skcipher_request_set_callback(
 		req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 		ext4_crypt_complete, &ecr);
 
@@ -288,21 +286,21 @@ static int ext4_page_crypto(struct inode *inode,
 	sg_set_page(&dst, dest_page, PAGE_CACHE_SIZE, 0);
 	sg_init_table(&src, 1);
 	sg_set_page(&src, src_page, PAGE_CACHE_SIZE, 0);
-	ablkcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE,
-				     xts_tweak);
+	skcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE,
+				   xts_tweak);
 	if (rw == EXT4_DECRYPT)
-		res = crypto_ablkcipher_decrypt(req);
+		res = crypto_skcipher_decrypt(req);
 	else
-		res = crypto_ablkcipher_encrypt(req);
+		res = crypto_skcipher_encrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	if (res) {
 		printk_ratelimited(
 			KERN_ERR
-			"%s: crypto_ablkcipher_encrypt() returned %d\n",
+			"%s: crypto_skcipher_encrypt() returned %d\n",
 			__func__, res);
 		return res;
 	}
@@ -467,3 +465,59 @@ uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size)
 		return size;
 	return 0;
 }
+
+/*
+ * Validate dentries for encrypted directories to make sure we aren't
+ * potentially caching stale data after a key has been added or
+ * removed.
+ */
+static int ext4_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct inode *dir = d_inode(dentry->d_parent);
+	struct ext4_crypt_info *ci = EXT4_I(dir)->i_crypt_info;
+	int dir_has_key, cached_with_key;
+
+	if (!ext4_encrypted_inode(dir))
+		return 0;
+
+	if (ci && ci->ci_keyring_key &&
+	    (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+					  (1 << KEY_FLAG_REVOKED) |
+					  (1 << KEY_FLAG_DEAD))))
+		ci = NULL;
+
+	/* this should eventually be an flag in d_flags */
+	cached_with_key = dentry->d_fsdata != NULL;
+	dir_has_key = (ci != NULL);
+
+	/*
+	 * If the dentry was cached without the key, and it is a
+	 * negative dentry, it might be a valid name.  We can't check
+	 * if the key has since been made available due to locking
+	 * reasons, so we fail the validation so ext4_lookup() can do
+	 * this check.
+	 *
+	 * We also fail the validation if the dentry was created with
+	 * the key present, but we no longer have the key, or vice versa.
+	 */
+	if ((!cached_with_key && d_is_negative(dentry)) ||
+	    (!cached_with_key && dir_has_key) ||
+	    (cached_with_key && !dir_has_key)) {
+#if 0				/* Revalidation debug */
+		char buf[80];
+		char *cp = simple_dname(dentry, buf, sizeof(buf));
+
+		if (IS_ERR(cp))
+			cp = (char *) "???";
+		pr_err("revalidate: %s %p %d %d %d\n", cp, dentry->d_fsdata,
+		       cached_with_key, d_is_negative(dentry),
+		       dir_has_key);
+#endif
+		return 0;
+	}
+	return 1;
+}
+
+const struct dentry_operations ext4_encrypted_d_ops = {
+	.d_revalidate = ext4_d_revalidate,
+};
diff --git a/fs/ext4/crypto_fname.c b/fs/ext4/crypto_fname.c
index 2fbef8a14760..1a2f360405db 100644
--- a/fs/ext4/crypto_fname.c
+++ b/fs/ext4/crypto_fname.c
@@ -11,11 +11,9 @@
  *
  */
 
-#include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/skcipher.h>
 #include <keys/encrypted-type.h>
 #include <keys/user-type.h>
-#include <linux/crypto.h>
 #include <linux/gfp.h>
 #include <linux/kernel.h>
 #include <linux/key.h>
@@ -65,10 +63,10 @@ static int ext4_fname_encrypt(struct inode *inode,
 			      struct ext4_str *oname)
 {
 	u32 ciphertext_len;
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	DECLARE_EXT4_COMPLETION_RESULT(ecr);
 	struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
 	char iv[EXT4_CRYPTO_BLOCK_SIZE];
 	struct scatterlist src_sg, dst_sg;
@@ -95,14 +93,14 @@ static int ext4_fname_encrypt(struct inode *inode,
 	}
 
 	/* Allocate request */
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		printk_ratelimited(
 		    KERN_ERR "%s: crypto_request_alloc() failed\n", __func__);
 		kfree(alloc_buf);
 		return -ENOMEM;
 	}
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 		CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 		ext4_dir_crypt_complete, &ecr);
 
@@ -117,14 +115,14 @@ static int ext4_fname_encrypt(struct inode *inode,
 	/* Create encryption request */
 	sg_init_one(&src_sg, workbuf, ciphertext_len);
 	sg_init_one(&dst_sg, oname->name, ciphertext_len);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
-	res = crypto_ablkcipher_encrypt(req);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
+	res = crypto_skcipher_encrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
 	kfree(alloc_buf);
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	if (res < 0) {
 		printk_ratelimited(
 		    KERN_ERR "%s: Error (error code %d)\n", __func__, res);
@@ -145,11 +143,11 @@ static int ext4_fname_decrypt(struct inode *inode,
 			      struct ext4_str *oname)
 {
 	struct ext4_str tmp_in[2], tmp_out[1];
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	DECLARE_EXT4_COMPLETION_RESULT(ecr);
 	struct scatterlist src_sg, dst_sg;
 	struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
 	char iv[EXT4_CRYPTO_BLOCK_SIZE];
 	unsigned lim = max_name_len(inode);
@@ -162,13 +160,13 @@ static int ext4_fname_decrypt(struct inode *inode,
 	tmp_out[0].name = oname->name;
 
 	/* Allocate request */
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		printk_ratelimited(
 		    KERN_ERR "%s: crypto_request_alloc() failed\n",  __func__);
 		return -ENOMEM;
 	}
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 		CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 		ext4_dir_crypt_complete, &ecr);
 
@@ -178,13 +176,13 @@ static int ext4_fname_decrypt(struct inode *inode,
 	/* Create encryption request */
 	sg_init_one(&src_sg, iname->name, iname->len);
 	sg_init_one(&dst_sg, oname->name, oname->len);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
-	res = crypto_ablkcipher_decrypt(req);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
+	res = crypto_skcipher_decrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	if (res < 0) {
 		printk_ratelimited(
 		    KERN_ERR "%s: Error in ext4_fname_encrypt (error code %d)\n",
diff --git a/fs/ext4/crypto_key.c b/fs/ext4/crypto_key.c
index 9a16d1e75a49..0129d688d1f7 100644
--- a/fs/ext4/crypto_key.c
+++ b/fs/ext4/crypto_key.c
@@ -8,6 +8,7 @@
  * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
  */
 
+#include <crypto/skcipher.h>
 #include <keys/encrypted-type.h>
 #include <keys/user-type.h>
 #include <linux/random.h>
@@ -41,45 +42,42 @@ static int ext4_derive_key_aes(char deriving_key[EXT4_AES_128_ECB_KEY_SIZE],
 			       char derived_key[EXT4_AES_256_XTS_KEY_SIZE])
 {
 	int res = 0;
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	DECLARE_EXT4_COMPLETION_RESULT(ecr);
 	struct scatterlist src_sg, dst_sg;
-	struct crypto_ablkcipher *tfm = crypto_alloc_ablkcipher("ecb(aes)", 0,
-								0);
+	struct crypto_skcipher *tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0);
 
 	if (IS_ERR(tfm)) {
 		res = PTR_ERR(tfm);
 		tfm = NULL;
 		goto out;
 	}
-	crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		res = -ENOMEM;
 		goto out;
 	}
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 			derive_crypt_complete, &ecr);
-	res = crypto_ablkcipher_setkey(tfm, deriving_key,
-				       EXT4_AES_128_ECB_KEY_SIZE);
+	res = crypto_skcipher_setkey(tfm, deriving_key,
+				     EXT4_AES_128_ECB_KEY_SIZE);
 	if (res < 0)
 		goto out;
 	sg_init_one(&src_sg, source_key, EXT4_AES_256_XTS_KEY_SIZE);
 	sg_init_one(&dst_sg, derived_key, EXT4_AES_256_XTS_KEY_SIZE);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg,
-				     EXT4_AES_256_XTS_KEY_SIZE, NULL);
-	res = crypto_ablkcipher_encrypt(req);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg,
+				   EXT4_AES_256_XTS_KEY_SIZE, NULL);
+	res = crypto_skcipher_encrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
 
 out:
-	if (req)
-		ablkcipher_request_free(req);
-	if (tfm)
-		crypto_free_ablkcipher(tfm);
+	skcipher_request_free(req);
+	crypto_free_skcipher(tfm);
 	return res;
 }
 
@@ -90,7 +88,7 @@ void ext4_free_crypt_info(struct ext4_crypt_info *ci)
 
 	if (ci->ci_keyring_key)
 		key_put(ci->ci_keyring_key);
-	crypto_free_ablkcipher(ci->ci_ctfm);
+	crypto_free_skcipher(ci->ci_ctfm);
 	kmem_cache_free(ext4_crypt_info_cachep, ci);
 }
 
@@ -122,7 +120,7 @@ int _ext4_get_encryption_info(struct inode *inode)
 	struct ext4_encryption_context ctx;
 	const struct user_key_payload *ukp;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	struct crypto_ablkcipher *ctfm;
+	struct crypto_skcipher *ctfm;
 	const char *cipher_str;
 	char raw_key[EXT4_MAX_KEY_SIZE];
 	char mode;
@@ -237,7 +235,7 @@ retry:
 	if (res)
 		goto out;
 got_key:
-	ctfm = crypto_alloc_ablkcipher(cipher_str, 0, 0);
+	ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
 	if (!ctfm || IS_ERR(ctfm)) {
 		res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
 		printk(KERN_DEBUG
@@ -246,11 +244,11 @@ got_key:
 		goto out;
 	}
 	crypt_info->ci_ctfm = ctfm;
-	crypto_ablkcipher_clear_flags(ctfm, ~0);
-	crypto_tfm_set_flags(crypto_ablkcipher_tfm(ctfm),
+	crypto_skcipher_clear_flags(ctfm, ~0);
+	crypto_tfm_set_flags(crypto_skcipher_tfm(ctfm),
 			     CRYPTO_TFM_REQ_WEAK_KEY);
-	res = crypto_ablkcipher_setkey(ctfm, raw_key,
-				       ext4_encryption_key_size(mode));
+	res = crypto_skcipher_setkey(ctfm, raw_key,
+				     ext4_encryption_key_size(mode));
 	if (res)
 		goto out;
 	memzero_explicit(raw_key, sizeof(raw_key));
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 1d1bca74f844..33f5e2a50cf8 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -111,6 +111,12 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 	int dir_has_error = 0;
 	struct ext4_str fname_crypto_str = {.name = NULL, .len = 0};
 
+	if (ext4_encrypted_inode(inode)) {
+		err = ext4_get_encryption_info(inode);
+		if (err && err != -ENOKEY)
+			return err;
+	}
+
 	if (is_dx_dir(inode)) {
 		err = ext4_dx_readdir(file, ctx);
 		if (err != ERR_BAD_DX_DIR) {
@@ -157,8 +163,11 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 					index, 1);
 			file->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;
 			bh = ext4_bread(NULL, inode, map.m_lblk, 0);
-			if (IS_ERR(bh))
-				return PTR_ERR(bh);
+			if (IS_ERR(bh)) {
+				err = PTR_ERR(bh);
+				bh = NULL;
+				goto errout;
+			}
 		}
 
 		if (!bh) {
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0662b285dc8a..157b458a69d4 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2302,6 +2302,7 @@ struct page *ext4_encrypt(struct inode *inode,
 int ext4_decrypt(struct page *page);
 int ext4_encrypted_zeroout(struct inode *inode, ext4_lblk_t lblk,
 			   ext4_fsblk_t pblk, ext4_lblk_t len);
+extern const struct dentry_operations ext4_encrypted_d_ops;
 
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
 int ext4_init_crypto(void);
diff --git a/fs/ext4/ext4_crypto.h b/fs/ext4/ext4_crypto.h
index ac7d4e813796..1f73c29717e1 100644
--- a/fs/ext4/ext4_crypto.h
+++ b/fs/ext4/ext4_crypto.h
@@ -77,7 +77,7 @@ struct ext4_crypt_info {
 	char		ci_data_mode;
 	char		ci_filename_mode;
 	char		ci_flags;
-	struct crypto_ablkcipher *ci_ctfm;
+	struct crypto_skcipher *ci_ctfm;
 	struct key	*ci_keyring_key;
 	char		ci_master_key[EXT4_KEY_DESCRIPTOR_SIZE];
 };
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 0ffabaf90aa5..3753ceb0b0dd 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3928,7 +3928,7 @@ static int
 convert_initialized_extent(handle_t *handle, struct inode *inode,
 			   struct ext4_map_blocks *map,
 			   struct ext4_ext_path **ppath, int flags,
-			   unsigned int allocated, ext4_fsblk_t newblock)
+			   unsigned int allocated)
 {
 	struct ext4_ext_path *path = *ppath;
 	struct ext4_extent *ex;
@@ -4347,7 +4347,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			    (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) {
 				allocated = convert_initialized_extent(
 						handle, inode, map, &path,
-						flags, allocated, newblock);
+						flags, allocated);
 				goto out2;
 			} else if (!ext4_ext_is_unwritten(ex))
 				goto out;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 1126436dada1..4cd318f31cbe 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -262,23 +262,8 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	return result;
 }
 
-static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	int err;
-	struct inode *inode = file_inode(vma->vm_file);
-
-	sb_start_pagefault(inode->i_sb);
-	file_update_time(vma->vm_file);
-	down_read(&EXT4_I(inode)->i_mmap_sem);
-	err = __dax_mkwrite(vma, vmf, ext4_dax_mmap_get_block, NULL);
-	up_read(&EXT4_I(inode)->i_mmap_sem);
-	sb_end_pagefault(inode->i_sb);
-
-	return err;
-}
-
 /*
- * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_mkwrite()
+ * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_fault()
  * handler we check for races agaist truncate. Note that since we cycle through
  * i_mmap_sem, we are sure that also any hole punching that began before we
  * were called is finished by now and so if it included part of the file we
@@ -311,7 +296,7 @@ static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
 static const struct vm_operations_struct ext4_dax_vm_ops = {
 	.fault		= ext4_dax_fault,
 	.pmd_fault	= ext4_dax_pmd_fault,
-	.page_mkwrite	= ext4_dax_mkwrite,
+	.page_mkwrite	= ext4_dax_fault,
 	.pfn_mkwrite	= ext4_dax_pfn_mkwrite,
 };
 #else
@@ -350,6 +335,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 	struct super_block *sb = inode->i_sb;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct vfsmount *mnt = filp->f_path.mnt;
+	struct inode *dir = filp->f_path.dentry->d_parent->d_inode;
 	struct path path;
 	char buf[64], *cp;
 	int ret;
@@ -393,6 +379,14 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 		if (ext4_encryption_info(inode) == NULL)
 			return -ENOKEY;
 	}
+	if (ext4_encrypted_inode(dir) &&
+	    !ext4_is_child_context_consistent_with_parent(dir, inode)) {
+		ext4_warning(inode->i_sb,
+			     "Inconsistent encryption contexts: %lu/%lu\n",
+			     (unsigned long) dir->i_ino,
+			     (unsigned long) inode->i_ino);
+		return -EPERM;
+	}
 	/*
 	 * Set up the jbd2_inode if we are opening the inode for
 	 * writing and the journal is present
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 3fcfd50a2e8a..acc0ad56bf2f 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -76,7 +76,6 @@ static int ext4_init_inode_bitmap(struct super_block *sb,
 	/* If checksum is bad mark all blocks and inodes use to prevent
 	 * allocation, essentially implementing a per-group read-only flag. */
 	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
-		ext4_error(sb, "Checksum bad for group %u", block_group);
 		grp = ext4_get_group_info(sb, block_group);
 		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
 			percpu_counter_sub(&sbi->s_freeclusters_counter,
@@ -191,8 +190,11 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 		set_buffer_verified(bh);
 		ext4_unlock_group(sb, block_group);
 		unlock_buffer(bh);
-		if (err)
+		if (err) {
+			ext4_error(sb, "Failed to init inode bitmap for group "
+				   "%u: %d", block_group, err);
 			goto out;
+		}
 		return bh;
 	}
 	ext4_unlock_group(sb, block_group);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 83bc8bfb3bea..aee960b1af34 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -686,6 +686,34 @@ out_sem:
 	return retval;
 }
 
+/*
+ * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages
+ * we have to be careful as someone else may be manipulating b_state as well.
+ */
+static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags)
+{
+	unsigned long old_state;
+	unsigned long new_state;
+
+	flags &= EXT4_MAP_FLAGS;
+
+	/* Dummy buffer_head? Set non-atomically. */
+	if (!bh->b_page) {
+		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags;
+		return;
+	}
+	/*
+	 * Someone else may be modifying b_state. Be careful! This is ugly but
+	 * once we get rid of using bh as a container for mapping information
+	 * to pass to / from get_block functions, this can go away.
+	 */
+	do {
+		old_state = READ_ONCE(bh->b_state);
+		new_state = (old_state & ~EXT4_MAP_FLAGS) | flags;
+	} while (unlikely(
+		 cmpxchg(&bh->b_state, old_state, new_state) != old_state));
+}
+
 /* Maximum number of blocks we map for direct IO at once. */
 #define DIO_MAX_BLOCKS 4096
 
@@ -722,7 +750,7 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 		ext4_io_end_t *io_end = ext4_inode_aio(inode);
 
 		map_bh(bh, inode->i_sb, map.m_pblk);
-		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+		ext4_update_bh_state(bh, map.m_flags);
 		if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN)
 			set_buffer_defer_completion(bh);
 		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
@@ -1685,7 +1713,7 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 		return ret;
 
 	map_bh(bh, inode->i_sb, map.m_pblk);
-	bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+	ext4_update_bh_state(bh, map.m_flags);
 
 	if (buffer_unwritten(bh)) {
 		/* A delayed write to unwritten bh should be marked
@@ -2450,6 +2478,10 @@ static int ext4_writepages(struct address_space *mapping,
 
 	trace_ext4_writepages(inode, wbc);
 
+	if (dax_mapping(mapping))
+		return dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev,
+						   wbc);
+
 	/*
 	 * No pages to write? This is mainly a kludge to avoid starting
 	 * a transaction for special inodes like journal inode on last iput()
@@ -3253,29 +3285,29 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	 * case, we allocate an io_end structure to hook to the iocb.
 	 */
 	iocb->private = NULL;
-	ext4_inode_aio_set(inode, NULL);
-	if (!is_sync_kiocb(iocb)) {
-		io_end = ext4_init_io_end(inode, GFP_NOFS);
-		if (!io_end) {
-			ret = -ENOMEM;
-			goto retake_lock;
-		}
-		/*
-		 * Grab reference for DIO. Will be dropped in ext4_end_io_dio()
-		 */
-		iocb->private = ext4_get_io_end(io_end);
-		/*
-		 * we save the io structure for current async direct
-		 * IO, so that later ext4_map_blocks() could flag the
-		 * io structure whether there is a unwritten extents
-		 * needs to be converted when IO is completed.
-		 */
-		ext4_inode_aio_set(inode, io_end);
-	}
-
 	if (overwrite) {
 		get_block_func = ext4_get_block_overwrite;
 	} else {
+		ext4_inode_aio_set(inode, NULL);
+		if (!is_sync_kiocb(iocb)) {
+			io_end = ext4_init_io_end(inode, GFP_NOFS);
+			if (!io_end) {
+				ret = -ENOMEM;
+				goto retake_lock;
+			}
+			/*
+			 * Grab reference for DIO. Will be dropped in
+			 * ext4_end_io_dio()
+			 */
+			iocb->private = ext4_get_io_end(io_end);
+			/*
+			 * we save the io structure for current async direct
+			 * IO, so that later ext4_map_blocks() could flag the
+			 * io structure whether there is a unwritten extents
+			 * needs to be converted when IO is completed.
+			 */
+			ext4_inode_aio_set(inode, io_end);
+		}
 		get_block_func = ext4_get_block_write;
 		dio_flags = DIO_LOCKING;
 	}
@@ -4127,7 +4159,7 @@ void ext4_set_inode_flags(struct inode *inode)
 		new_fl |= S_NOATIME;
 	if (flags & EXT4_DIRSYNC_FL)
 		new_fl |= S_DIRSYNC;
-	if (test_opt(inode->i_sb, DAX))
+	if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode))
 		new_fl |= S_DAX;
 	inode_set_flags(inode, new_fl,
 			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 0f6c36922c24..eae5917c534e 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -208,7 +208,7 @@ static int ext4_ioctl_setflags(struct inode *inode,
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	handle_t *handle = NULL;
-	int err = EPERM, migrate = 0;
+	int err = -EPERM, migrate = 0;
 	struct ext4_iloc iloc;
 	unsigned int oldflags, mask, i;
 	unsigned int jflag;
@@ -583,6 +583,11 @@ group_extend_out:
 				 "Online defrag not supported with bigalloc");
 			err = -EOPNOTSUPP;
 			goto mext_out;
+		} else if (IS_DAX(inode)) {
+			ext4_msg(sb, KERN_ERR,
+				 "Online defrag not supported with DAX");
+			err = -EOPNOTSUPP;
+			goto mext_out;
 		}
 
 		err = mnt_want_write_file(filp);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 61eaf74dca37..4424b7bf8ac6 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2285,7 +2285,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 	if (group == 0)
 		seq_puts(seq, "#group: free  frags first ["
 			      " 2^0   2^1   2^2   2^3   2^4   2^5   2^6  "
-			      " 2^7   2^8   2^9   2^10  2^11  2^12  2^13  ]");
+			      " 2^7   2^8   2^9   2^10  2^11  2^12  2^13  ]\n");
 
 	i = (sb->s_blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) +
 		sizeof(struct ext4_group_info);
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index fb6f11709ae6..4098acc701c3 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -265,11 +265,12 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
 	ext4_lblk_t orig_blk_offset, donor_blk_offset;
 	unsigned long blocksize = orig_inode->i_sb->s_blocksize;
 	unsigned int tmp_data_size, data_size, replaced_size;
-	int err2, jblocks, retries = 0;
+	int i, err2, jblocks, retries = 0;
 	int replaced_count = 0;
 	int from = data_offset_in_page << orig_inode->i_blkbits;
 	int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
 	struct super_block *sb = orig_inode->i_sb;
+	struct buffer_head *bh = NULL;
 
 	/*
 	 * It needs twice the amount of ordinary journal buffers because
@@ -380,8 +381,17 @@ data_copy:
 	}
 	/* Perform all necessary steps similar write_begin()/write_end()
 	 * but keeping in mind that i_size will not change */
-	*err = __block_write_begin(pagep[0], from, replaced_size,
-				   ext4_get_block);
+	if (!page_has_buffers(pagep[0]))
+		create_empty_buffers(pagep[0], 1 << orig_inode->i_blkbits, 0);
+	bh = page_buffers(pagep[0]);
+	for (i = 0; i < data_offset_in_page; i++)
+		bh = bh->b_this_page;
+	for (i = 0; i < block_len_in_page; i++) {
+		*err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0);
+		if (*err < 0)
+			break;
+		bh = bh->b_this_page;
+	}
 	if (!*err)
 		*err = block_commit_write(pagep[0], from, from + replaced_size);
 
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 06574dd77614..48e4b8907826 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1558,6 +1558,24 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 	struct ext4_dir_entry_2 *de;
 	struct buffer_head *bh;
 
+       if (ext4_encrypted_inode(dir)) {
+               int res = ext4_get_encryption_info(dir);
+
+		/*
+		 * This should be a properly defined flag for
+		 * dentry->d_flags when we uplift this to the VFS.
+		 * d_fsdata is set to (void *) 1 if if the dentry is
+		 * created while the directory was encrypted and we
+		 * don't have access to the key.
+		 */
+	       dentry->d_fsdata = NULL;
+	       if (ext4_encryption_info(dir))
+		       dentry->d_fsdata = (void *) 1;
+	       d_set_d_op(dentry, &ext4_encrypted_d_ops);
+	       if (res && res != -ENOKEY)
+		       return ERR_PTR(res);
+       }
+
 	if (dentry->d_name.len > EXT4_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
@@ -1585,11 +1603,15 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 			return ERR_PTR(-EFSCORRUPTED);
 		}
 		if (!IS_ERR(inode) && ext4_encrypted_inode(dir) &&
-		    (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-		     S_ISLNK(inode->i_mode)) &&
+		    (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
 		    !ext4_is_child_context_consistent_with_parent(dir,
 								  inode)) {
+			int nokey = ext4_encrypted_inode(inode) &&
+				!ext4_encryption_info(inode);
+
 			iput(inode);
+			if (nokey)
+				return ERR_PTR(-ENOKEY);
 			ext4_warning(inode->i_sb,
 				     "Inconsistent encryption contexts: %lu/%lu\n",
 				     (unsigned long) dir->i_ino,
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index ad62d7acc315..34038e3598d5 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -198,7 +198,7 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size)
 	if (flex_gd == NULL)
 		goto out3;
 
-	if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data))
+	if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data))
 		goto out2;
 	flex_gd->count = flexbg_size;
 
diff --git a/fs/f2fs/crypto.c b/fs/f2fs/crypto.c
index 4a62ef14e932..95c5cf039711 100644
--- a/fs/f2fs/crypto.c
+++ b/fs/f2fs/crypto.c
@@ -23,11 +23,9 @@
  * The usage of AES-XTS should conform to recommendations in NIST
  * Special Publication 800-38E and IEEE P1619/D16.
  */
-#include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/skcipher.h>
 #include <keys/user-type.h>
 #include <keys/encrypted-type.h>
-#include <linux/crypto.h>
 #include <linux/ecryptfs.h>
 #include <linux/gfp.h>
 #include <linux/kernel.h>
@@ -328,21 +326,21 @@ static int f2fs_page_crypto(struct f2fs_crypto_ctx *ctx,
 				struct page *dest_page)
 {
 	u8 xts_tweak[F2FS_XTS_TWEAK_SIZE];
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	DECLARE_F2FS_COMPLETION_RESULT(ecr);
 	struct scatterlist dst, src;
 	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
 
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		printk_ratelimited(KERN_ERR
 				"%s: crypto_request_alloc() failed\n",
 				__func__);
 		return -ENOMEM;
 	}
-	ablkcipher_request_set_callback(
+	skcipher_request_set_callback(
 		req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 		f2fs_crypt_complete, &ecr);
 
@@ -355,21 +353,21 @@ static int f2fs_page_crypto(struct f2fs_crypto_ctx *ctx,
 	sg_set_page(&dst, dest_page, PAGE_CACHE_SIZE, 0);
 	sg_init_table(&src, 1);
 	sg_set_page(&src, src_page, PAGE_CACHE_SIZE, 0);
-	ablkcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE,
-					xts_tweak);
+	skcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE,
+				   xts_tweak);
 	if (rw == F2FS_DECRYPT)
-		res = crypto_ablkcipher_decrypt(req);
+		res = crypto_skcipher_decrypt(req);
 	else
-		res = crypto_ablkcipher_encrypt(req);
+		res = crypto_skcipher_encrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
 		BUG_ON(req->base.data != &ecr);
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	if (res) {
 		printk_ratelimited(KERN_ERR
-			"%s: crypto_ablkcipher_encrypt() returned %d\n",
+			"%s: crypto_skcipher_encrypt() returned %d\n",
 			__func__, res);
 		return res;
 	}
diff --git a/fs/f2fs/crypto_fname.c b/fs/f2fs/crypto_fname.c
index ab377d496a39..16aec6653291 100644
--- a/fs/f2fs/crypto_fname.c
+++ b/fs/f2fs/crypto_fname.c
@@ -15,11 +15,9 @@
  *
  * This has not yet undergone a rigorous security audit.
  */
-#include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/skcipher.h>
 #include <keys/encrypted-type.h>
 #include <keys/user-type.h>
-#include <linux/crypto.h>
 #include <linux/gfp.h>
 #include <linux/kernel.h>
 #include <linux/key.h>
@@ -70,10 +68,10 @@ static int f2fs_fname_encrypt(struct inode *inode,
 			const struct qstr *iname, struct f2fs_str *oname)
 {
 	u32 ciphertext_len;
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	DECLARE_F2FS_COMPLETION_RESULT(ecr);
 	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
 	char iv[F2FS_CRYPTO_BLOCK_SIZE];
 	struct scatterlist src_sg, dst_sg;
@@ -99,14 +97,14 @@ static int f2fs_fname_encrypt(struct inode *inode,
 	}
 
 	/* Allocate request */
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		printk_ratelimited(KERN_ERR
 			"%s: crypto_request_alloc() failed\n", __func__);
 		kfree(alloc_buf);
 		return -ENOMEM;
 	}
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 			f2fs_dir_crypt_complete, &ecr);
 
@@ -121,15 +119,15 @@ static int f2fs_fname_encrypt(struct inode *inode,
 	/* Create encryption request */
 	sg_init_one(&src_sg, workbuf, ciphertext_len);
 	sg_init_one(&dst_sg, oname->name, ciphertext_len);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
-	res = crypto_ablkcipher_encrypt(req);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
+	res = crypto_skcipher_encrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
 		BUG_ON(req->base.data != &ecr);
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
 	kfree(alloc_buf);
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	if (res < 0) {
 		printk_ratelimited(KERN_ERR
 				"%s: Error (error code %d)\n", __func__, res);
@@ -148,11 +146,11 @@ static int f2fs_fname_encrypt(struct inode *inode,
 static int f2fs_fname_decrypt(struct inode *inode,
 			const struct f2fs_str *iname, struct f2fs_str *oname)
 {
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	DECLARE_F2FS_COMPLETION_RESULT(ecr);
 	struct scatterlist src_sg, dst_sg;
 	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
 	char iv[F2FS_CRYPTO_BLOCK_SIZE];
 	unsigned lim = max_name_len(inode);
@@ -161,13 +159,13 @@ static int f2fs_fname_decrypt(struct inode *inode,
 		return -EIO;
 
 	/* Allocate request */
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		printk_ratelimited(KERN_ERR
 			"%s: crypto_request_alloc() failed\n",  __func__);
 		return -ENOMEM;
 	}
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 		CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 		f2fs_dir_crypt_complete, &ecr);
 
@@ -177,14 +175,14 @@ static int f2fs_fname_decrypt(struct inode *inode,
 	/* Create decryption request */
 	sg_init_one(&src_sg, iname->name, iname->len);
 	sg_init_one(&dst_sg, oname->name, oname->len);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
-	res = crypto_ablkcipher_decrypt(req);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
+	res = crypto_skcipher_decrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
 		BUG_ON(req->base.data != &ecr);
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	if (res < 0) {
 		printk_ratelimited(KERN_ERR
 			"%s: Error in f2fs_fname_decrypt (error code %d)\n",
diff --git a/fs/f2fs/crypto_key.c b/fs/f2fs/crypto_key.c
index 5de2d866a25c..2aeb6273bd8f 100644
--- a/fs/f2fs/crypto_key.c
+++ b/fs/f2fs/crypto_key.c
@@ -14,7 +14,7 @@
 #include <linux/random.h>
 #include <linux/scatterlist.h>
 #include <uapi/linux/keyctl.h>
-#include <crypto/hash.h>
+#include <crypto/skcipher.h>
 #include <linux/f2fs_fs.h>
 
 #include "f2fs.h"
@@ -44,46 +44,43 @@ static int f2fs_derive_key_aes(char deriving_key[F2FS_AES_128_ECB_KEY_SIZE],
 				char derived_key[F2FS_AES_256_XTS_KEY_SIZE])
 {
 	int res = 0;
-	struct ablkcipher_request *req = NULL;
+	struct skcipher_request *req = NULL;
 	DECLARE_F2FS_COMPLETION_RESULT(ecr);
 	struct scatterlist src_sg, dst_sg;
-	struct crypto_ablkcipher *tfm = crypto_alloc_ablkcipher("ecb(aes)", 0,
-								0);
+	struct crypto_skcipher *tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0);
 
 	if (IS_ERR(tfm)) {
 		res = PTR_ERR(tfm);
 		tfm = NULL;
 		goto out;
 	}
-	crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		res = -ENOMEM;
 		goto out;
 	}
-	ablkcipher_request_set_callback(req,
+	skcipher_request_set_callback(req,
 			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 			derive_crypt_complete, &ecr);
-	res = crypto_ablkcipher_setkey(tfm, deriving_key,
+	res = crypto_skcipher_setkey(tfm, deriving_key,
 				F2FS_AES_128_ECB_KEY_SIZE);
 	if (res < 0)
 		goto out;
 
 	sg_init_one(&src_sg, source_key, F2FS_AES_256_XTS_KEY_SIZE);
 	sg_init_one(&dst_sg, derived_key, F2FS_AES_256_XTS_KEY_SIZE);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg,
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg,
 					F2FS_AES_256_XTS_KEY_SIZE, NULL);
-	res = crypto_ablkcipher_encrypt(req);
+	res = crypto_skcipher_encrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
 		BUG_ON(req->base.data != &ecr);
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
 out:
-	if (req)
-		ablkcipher_request_free(req);
-	if (tfm)
-		crypto_free_ablkcipher(tfm);
+	skcipher_request_free(req);
+	crypto_free_skcipher(tfm);
 	return res;
 }
 
@@ -93,7 +90,7 @@ static void f2fs_free_crypt_info(struct f2fs_crypt_info *ci)
 		return;
 
 	key_put(ci->ci_keyring_key);
-	crypto_free_ablkcipher(ci->ci_ctfm);
+	crypto_free_skcipher(ci->ci_ctfm);
 	kmem_cache_free(f2fs_crypt_info_cachep, ci);
 }
 
@@ -123,7 +120,7 @@ int _f2fs_get_encryption_info(struct inode *inode)
 	struct f2fs_encryption_key *master_key;
 	struct f2fs_encryption_context ctx;
 	const struct user_key_payload *ukp;
-	struct crypto_ablkcipher *ctfm;
+	struct crypto_skcipher *ctfm;
 	const char *cipher_str;
 	char raw_key[F2FS_MAX_KEY_SIZE];
 	char mode;
@@ -213,7 +210,7 @@ retry:
 	if (res)
 		goto out;
 
-	ctfm = crypto_alloc_ablkcipher(cipher_str, 0, 0);
+	ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
 	if (!ctfm || IS_ERR(ctfm)) {
 		res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
 		printk(KERN_DEBUG
@@ -222,11 +219,10 @@ retry:
 		goto out;
 	}
 	crypt_info->ci_ctfm = ctfm;
-	crypto_ablkcipher_clear_flags(ctfm, ~0);
-	crypto_tfm_set_flags(crypto_ablkcipher_tfm(ctfm),
-			     CRYPTO_TFM_REQ_WEAK_KEY);
-	res = crypto_ablkcipher_setkey(ctfm, raw_key,
-					f2fs_encryption_key_size(mode));
+	crypto_skcipher_clear_flags(ctfm, ~0);
+	crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	res = crypto_skcipher_setkey(ctfm, raw_key,
+				     f2fs_encryption_key_size(mode));
 	if (res)
 		goto out;
 
diff --git a/fs/f2fs/f2fs_crypto.h b/fs/f2fs/f2fs_crypto.h
index c2c1c2b63b25..ea3d1d7c97f3 100644
--- a/fs/f2fs/f2fs_crypto.h
+++ b/fs/f2fs/f2fs_crypto.h
@@ -78,7 +78,7 @@ struct f2fs_crypt_info {
 	char		ci_data_mode;
 	char		ci_filename_mode;
 	char		ci_flags;
-	struct crypto_ablkcipher *ci_ctfm;
+	struct crypto_skcipher *ci_ctfm;
 	struct key	*ci_keyring_key;
 	char		ci_master_key[F2FS_KEY_DESCRIPTOR_SIZE];
 };
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 6915c950e6e8..5c46ed9f3e14 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -223,6 +223,9 @@ static void wb_wait_for_completion(struct backing_dev_info *bdi,
 #define WB_FRN_HIST_MAX_SLOTS	(WB_FRN_HIST_THR_SLOTS / 2 + 1)
 					/* one round can affect upto 5 slots */
 
+static atomic_t isw_nr_in_flight = ATOMIC_INIT(0);
+static struct workqueue_struct *isw_wq;
+
 void __inode_attach_wb(struct inode *inode, struct page *page)
 {
 	struct backing_dev_info *bdi = inode_to_bdi(inode);
@@ -424,6 +427,8 @@ skip_switch:
 
 	iput(inode);
 	kfree(isw);
+
+	atomic_dec(&isw_nr_in_flight);
 }
 
 static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head)
@@ -433,7 +438,7 @@ static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head)
 
 	/* needs to grab bh-unsafe locks, bounce to work item */
 	INIT_WORK(&isw->work, inode_switch_wbs_work_fn);
-	schedule_work(&isw->work);
+	queue_work(isw_wq, &isw->work);
 }
 
 /**
@@ -469,7 +474,8 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 
 	/* while holding I_WB_SWITCH, no one else can update the association */
 	spin_lock(&inode->i_lock);
-	if (inode->i_state & (I_WB_SWITCH | I_FREEING) ||
+	if (!(inode->i_sb->s_flags & MS_ACTIVE) ||
+	    inode->i_state & (I_WB_SWITCH | I_FREEING) ||
 	    inode_to_wb(inode) == isw->new_wb) {
 		spin_unlock(&inode->i_lock);
 		goto out_free;
@@ -480,6 +486,8 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 	ihold(inode);
 	isw->inode = inode;
 
+	atomic_inc(&isw_nr_in_flight);
+
 	/*
 	 * In addition to synchronizing among switchers, I_WB_SWITCH tells
 	 * the RCU protected stat update paths to grab the mapping's
@@ -840,6 +848,33 @@ restart:
 		wb_put(last_wb);
 }
 
+/**
+ * cgroup_writeback_umount - flush inode wb switches for umount
+ *
+ * This function is called when a super_block is about to be destroyed and
+ * flushes in-flight inode wb switches.  An inode wb switch goes through
+ * RCU and then workqueue, so the two need to be flushed in order to ensure
+ * that all previously scheduled switches are finished.  As wb switches are
+ * rare occurrences and synchronize_rcu() can take a while, perform
+ * flushing iff wb switches are in flight.
+ */
+void cgroup_writeback_umount(void)
+{
+	if (atomic_read(&isw_nr_in_flight)) {
+		synchronize_rcu();
+		flush_workqueue(isw_wq);
+	}
+}
+
+static int __init cgroup_writeback_init(void)
+{
+	isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0);
+	if (!isw_wq)
+		return -ENOMEM;
+	return 0;
+}
+fs_initcall(cgroup_writeback_init);
+
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
 static struct bdi_writeback *
diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index 506765afa1a3..bb8d67e2740a 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -376,12 +376,11 @@ static int hpfs_unlink(struct inode *dir, struct dentry *dentry)
 	struct inode *inode = d_inode(dentry);
 	dnode_secno dno;
 	int r;
-	int rep = 0;
 	int err;
 
 	hpfs_lock(dir->i_sb);
 	hpfs_adjust_length(name, &len);
-again:
+
 	err = -ENOENT;
 	de = map_dirent(dir, hpfs_i(dir)->i_dno, name, len, &dno, &qbh);
 	if (!de)
@@ -401,33 +400,9 @@ again:
 		hpfs_error(dir->i_sb, "there was error when removing dirent");
 		err = -EFSERROR;
 		break;
-	case 2:		/* no space for deleting, try to truncate file */
-
+	case 2:		/* no space for deleting */
 		err = -ENOSPC;
-		if (rep++)
-			break;
-
-		dentry_unhash(dentry);
-		if (!d_unhashed(dentry)) {
-			hpfs_unlock(dir->i_sb);
-			return -ENOSPC;
-		}
-		if (generic_permission(inode, MAY_WRITE) ||
-		    !S_ISREG(inode->i_mode) ||
-		    get_write_access(inode)) {
-			d_rehash(dentry);
-		} else {
-			struct iattr newattrs;
-			/*pr_info("truncating file before delete.\n");*/
-			newattrs.ia_size = 0;
-			newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME;
-			err = notify_change(dentry, &newattrs, NULL);
-			put_write_access(inode);
-			if (!err)
-				goto again;
-		}
-		hpfs_unlock(dir->i_sb);
-		return -ENOSPC;
+		break;
 	default:
 		drop_nlink(inode);
 		err = 0;
diff --git a/fs/inode.c b/fs/inode.c
index 9f62db3bcc3e..69b8b526c194 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -154,6 +154,12 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_rdev = 0;
 	inode->dirtied_when = 0;
 
+#ifdef CONFIG_CGROUP_WRITEBACK
+	inode->i_wb_frn_winner = 0;
+	inode->i_wb_frn_avg_time = 0;
+	inode->i_wb_frn_history = 0;
+#endif
+
 	if (security_inode_alloc(inode))
 		goto out;
 	spin_lock_init(&inode->i_lock);
diff --git a/fs/jffs2/README.Locking b/fs/jffs2/README.Locking
index 3ea36554107f..8918ac905a3b 100644
--- a/fs/jffs2/README.Locking
+++ b/fs/jffs2/README.Locking
@@ -2,10 +2,6 @@
 	JFFS2 LOCKING DOCUMENTATION
 	---------------------------
 
-At least theoretically, JFFS2 does not require the Big Kernel Lock
-(BKL), which was always helpfully obtained for it by Linux 2.4 VFS
-code. It has its own locking, as described below.
-
 This document attempts to describe the existing locking rules for
 JFFS2. It is not expected to remain perfectly up to date, but ought to
 be fairly close.
@@ -69,6 +65,7 @@ Ordering constraints:
 	   any f->sem held.
 	2. Never attempt to lock two file mutexes in one thread.
 	   No ordering rules have been made for doing so.
+	3. Never lock a page cache page with f->sem held.
 
 
 	erase_completion_lock spinlock
diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c
index 0ae91ad6df2d..b288c8ae1236 100644
--- a/fs/jffs2/build.c
+++ b/fs/jffs2/build.c
@@ -50,7 +50,8 @@ next_inode(int *i, struct jffs2_inode_cache *ic, struct jffs2_sb_info *c)
 
 
 static void jffs2_build_inode_pass1(struct jffs2_sb_info *c,
-				    struct jffs2_inode_cache *ic)
+				    struct jffs2_inode_cache *ic,
+				    int *dir_hardlinks)
 {
 	struct jffs2_full_dirent *fd;
 
@@ -69,19 +70,21 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c,
 			dbg_fsbuild("child \"%s\" (ino #%u) of dir ino #%u doesn't exist!\n",
 				  fd->name, fd->ino, ic->ino);
 			jffs2_mark_node_obsolete(c, fd->raw);
+			/* Clear the ic/raw union so it doesn't cause problems later. */
+			fd->ic = NULL;
 			continue;
 		}
 
+		/* From this point, fd->raw is no longer used so we can set fd->ic */
+		fd->ic = child_ic;
+		child_ic->pino_nlink++;
+		/* If we appear (at this stage) to have hard-linked directories,
+		 * set a flag to trigger a scan later */
 		if (fd->type == DT_DIR) {
-			if (child_ic->pino_nlink) {
-				JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u appears to be a hard link\n",
-					    fd->name, fd->ino, ic->ino);
-				/* TODO: What do we do about it? */
-			} else {
-				child_ic->pino_nlink = ic->ino;
-			}
-		} else
-			child_ic->pino_nlink++;
+			child_ic->flags |= INO_FLAGS_IS_DIR;
+			if (child_ic->pino_nlink > 1)
+				*dir_hardlinks = 1;
+		}
 
 		dbg_fsbuild("increased nlink for child \"%s\" (ino #%u)\n", fd->name, fd->ino);
 		/* Can't free scan_dents so far. We might need them in pass 2 */
@@ -95,8 +98,7 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c,
 */
 static int jffs2_build_filesystem(struct jffs2_sb_info *c)
 {
-	int ret;
-	int i;
+	int ret, i, dir_hardlinks = 0;
 	struct jffs2_inode_cache *ic;
 	struct jffs2_full_dirent *fd;
 	struct jffs2_full_dirent *dead_fds = NULL;
@@ -120,7 +122,7 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c)
 	/* Now scan the directory tree, increasing nlink according to every dirent found. */
 	for_each_inode(i, c, ic) {
 		if (ic->scan_dents) {
-			jffs2_build_inode_pass1(c, ic);
+			jffs2_build_inode_pass1(c, ic, &dir_hardlinks);
 			cond_resched();
 		}
 	}
@@ -156,6 +158,20 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c)
 	}
 
 	dbg_fsbuild("pass 2a complete\n");
+
+	if (dir_hardlinks) {
+		/* If we detected directory hardlinks earlier, *hopefully*
+		 * they are gone now because some of the links were from
+		 * dead directories which still had some old dirents lying
+		 * around and not yet garbage-collected, but which have
+		 * been discarded above. So clear the pino_nlink field
+		 * in each directory, so that the final scan below can
+		 * print appropriate warnings. */
+		for_each_inode(i, c, ic) {
+			if (ic->flags & INO_FLAGS_IS_DIR)
+				ic->pino_nlink = 0;
+		}
+	}
 	dbg_fsbuild("freeing temporary data structures\n");
 
 	/* Finally, we can scan again and free the dirent structs */
@@ -163,6 +179,33 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c)
 		while(ic->scan_dents) {
 			fd = ic->scan_dents;
 			ic->scan_dents = fd->next;
+			/* We do use the pino_nlink field to count nlink of
+			 * directories during fs build, so set it to the
+			 * parent ino# now. Now that there's hopefully only
+			 * one. */
+			if (fd->type == DT_DIR) {
+				if (!fd->ic) {
+					/* We'll have complained about it and marked the coresponding
+					   raw node obsolete already. Just skip it. */
+					continue;
+				}
+
+				/* We *have* to have set this in jffs2_build_inode_pass1() */
+				BUG_ON(!(fd->ic->flags & INO_FLAGS_IS_DIR));
+
+				/* We clear ic->pino_nlink ∀ directories' ic *only* if dir_hardlinks
+				 * is set. Otherwise, we know this should never trigger anyway, so
+				 * we don't do the check. And ic->pino_nlink still contains the nlink
+				 * value (which is 1). */
+				if (dir_hardlinks && fd->ic->pino_nlink) {
+					JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u is also hard linked from dir ino #%u\n",
+						    fd->name, fd->ino, ic->ino, fd->ic->pino_nlink);
+					/* Should we unlink it from its previous parent? */
+				}
+
+				/* For directories, ic->pino_nlink holds that parent inode # */
+				fd->ic->pino_nlink = ic->ino;
+			}
 			jffs2_free_full_dirent(fd);
 		}
 		ic->scan_dents = NULL;
@@ -241,11 +284,7 @@ static void jffs2_build_remove_unlinked_inode(struct jffs2_sb_info *c,
 
 			/* Reduce nlink of the child. If it's now zero, stick it on the
 			   dead_fds list to be cleaned up later. Else just free the fd */
-
-			if (fd->type == DT_DIR)
-				child_ic->pino_nlink = 0;
-			else
-				child_ic->pino_nlink--;
+			child_ic->pino_nlink--;
 
 			if (!child_ic->pino_nlink) {
 				dbg_fsbuild("inode #%u (\"%s\") now has no links; adding to dead_fds list.\n",
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index d211b8e18566..30c4c9ebb693 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -843,9 +843,14 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 
 		pr_notice("%s(): Link succeeded, unlink failed (err %d). You now have a hard link\n",
 			  __func__, ret);
-		/* Might as well let the VFS know */
-		d_instantiate(new_dentry, d_inode(old_dentry));
-		ihold(d_inode(old_dentry));
+		/*
+		 * We can't keep the target in dcache after that.
+		 * For one thing, we can't afford dentry aliases for directories.
+		 * For another, if there was a victim, we _can't_ set new inode
+		 * for that sucker and we have to trigger mount eviction - the
+		 * caller won't do it on its own since we are returning an error.
+		 */
+		d_invalidate(new_dentry);
 		new_dir_i->i_mtime = new_dir_i->i_ctime = ITIME(now);
 		return ret;
 	}
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index c5ac5944bc1b..cad86bac3453 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -137,39 +137,33 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 	struct page *pg;
 	struct inode *inode = mapping->host;
 	struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode);
-	struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
-	struct jffs2_raw_inode ri;
-	uint32_t alloc_len = 0;
 	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
 	uint32_t pageofs = index << PAGE_CACHE_SHIFT;
 	int ret = 0;
 
-	jffs2_dbg(1, "%s()\n", __func__);
-
-	if (pageofs > inode->i_size) {
-		ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
-					  ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
-		if (ret)
-			return ret;
-	}
-
-	mutex_lock(&f->sem);
 	pg = grab_cache_page_write_begin(mapping, index, flags);
-	if (!pg) {
-		if (alloc_len)
-			jffs2_complete_reservation(c);
-		mutex_unlock(&f->sem);
+	if (!pg)
 		return -ENOMEM;
-	}
 	*pagep = pg;
 
-	if (alloc_len) {
+	jffs2_dbg(1, "%s()\n", __func__);
+
+	if (pageofs > inode->i_size) {
 		/* Make new hole frag from old EOF to new page */
+		struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
+		struct jffs2_raw_inode ri;
 		struct jffs2_full_dnode *fn;
+		uint32_t alloc_len;
 
 		jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n",
 			  (unsigned int)inode->i_size, pageofs);
 
+		ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
+					  ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
+		if (ret)
+			goto out_page;
+
+		mutex_lock(&f->sem);
 		memset(&ri, 0, sizeof(ri));
 
 		ri.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK);
@@ -196,6 +190,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 		if (IS_ERR(fn)) {
 			ret = PTR_ERR(fn);
 			jffs2_complete_reservation(c);
+			mutex_unlock(&f->sem);
 			goto out_page;
 		}
 		ret = jffs2_add_full_dnode_to_inode(c, f, fn);
@@ -210,10 +205,12 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 			jffs2_mark_node_obsolete(c, fn->raw);
 			jffs2_free_full_dnode(fn);
 			jffs2_complete_reservation(c);
+			mutex_unlock(&f->sem);
 			goto out_page;
 		}
 		jffs2_complete_reservation(c);
 		inode->i_size = pageofs;
+		mutex_unlock(&f->sem);
 	}
 
 	/*
@@ -222,18 +219,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 	 * case of a short-copy.
 	 */
 	if (!PageUptodate(pg)) {
+		mutex_lock(&f->sem);
 		ret = jffs2_do_readpage_nolock(inode, pg);
+		mutex_unlock(&f->sem);
 		if (ret)
 			goto out_page;
 	}
-	mutex_unlock(&f->sem);
 	jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags);
 	return ret;
 
 out_page:
 	unlock_page(pg);
 	page_cache_release(pg);
-	mutex_unlock(&f->sem);
 	return ret;
 }
 
diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c
index 5a2dec2b064c..95d5880a63ee 100644
--- a/fs/jffs2/gc.c
+++ b/fs/jffs2/gc.c
@@ -1296,14 +1296,17 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
 		BUG_ON(start > orig_start);
 	}
 
-	/* First, use readpage() to read the appropriate page into the page cache */
-	/* Q: What happens if we actually try to GC the _same_ page for which commit_write()
-	 *    triggered garbage collection in the first place?
-	 * A: I _think_ it's OK. read_cache_page shouldn't deadlock, we'll write out the
-	 *    page OK. We'll actually write it out again in commit_write, which is a little
-	 *    suboptimal, but at least we're correct.
-	 */
+	/* The rules state that we must obtain the page lock *before* f->sem, so
+	 * drop f->sem temporarily. Since we also hold c->alloc_sem, nothing's
+	 * actually going to *change* so we're safe; we only allow reading.
+	 *
+	 * It is important to note that jffs2_write_begin() will ensure that its
+	 * page is marked Uptodate before allocating space. That means that if we
+	 * end up here trying to GC the *same* page that jffs2_write_begin() is
+	 * trying to write out, read_cache_page() will not deadlock. */
+	mutex_unlock(&f->sem);
 	pg_ptr = jffs2_gc_fetch_page(c, f, start, &pg);
+	mutex_lock(&f->sem);
 
 	if (IS_ERR(pg_ptr)) {
 		pr_warn("read_cache_page() returned error: %ld\n",
diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h
index fa35ff79ab35..0637271f3770 100644
--- a/fs/jffs2/nodelist.h
+++ b/fs/jffs2/nodelist.h
@@ -194,6 +194,7 @@ struct jffs2_inode_cache {
 #define INO_STATE_CLEARING	6	/* In clear_inode() */
 
 #define INO_FLAGS_XATTR_CHECKED	0x01	/* has no duplicate xattr_ref */
+#define INO_FLAGS_IS_DIR	0x02	/* is a directory */
 
 #define RAWNODE_CLASS_INODE_CACHE	0
 #define RAWNODE_CLASS_XATTR_DATUM	1
@@ -249,7 +250,10 @@ struct jffs2_readinode_info
 
 struct jffs2_full_dirent
 {
-	struct jffs2_raw_node_ref *raw;
+	union {
+		struct jffs2_raw_node_ref *raw;
+		struct jffs2_inode_cache *ic; /* Just during part of build */
+	};
 	struct jffs2_full_dirent *next;
 	uint32_t version;
 	uint32_t ino; /* == zero for unlink */
diff --git a/fs/mpage.c b/fs/mpage.c
index 1480d3a18037..6bd9fd90964e 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -24,6 +24,7 @@
 #include <linux/highmem.h>
 #include <linux/prefetch.h>
 #include <linux/mpage.h>
+#include <linux/mm_inline.h>
 #include <linux/writeback.h>
 #include <linux/backing-dev.h>
 #include <linux/pagevec.h>
@@ -366,7 +367,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
 	map_bh.b_state = 0;
 	map_bh.b_size = 0;
 	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
-		struct page *page = list_entry(pages->prev, struct page, lru);
+		struct page *page = lru_to_page(pages);
 
 		prefetchw(&page->flags);
 		list_del(&page->lru);
diff --git a/fs/namei.c b/fs/namei.c
index f624d132e01e..9c590e0f66e9 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1712,6 +1712,11 @@ static inline int should_follow_link(struct nameidata *nd, struct path *link,
 		return 0;
 	if (!follow)
 		return 0;
+	/* make sure that d_is_symlink above matches inode */
+	if (nd->flags & LOOKUP_RCU) {
+		if (read_seqcount_retry(&link->dentry->d_seq, seq))
+			return -ECHILD;
+	}
 	return pick_link(nd, link, inode, seq);
 }
 
@@ -1743,11 +1748,11 @@ static int walk_component(struct nameidata *nd, int flags)
 		if (err < 0)
 			return err;
 
-		inode = d_backing_inode(path.dentry);
 		seq = 0;	/* we are already out of RCU mode */
 		err = -ENOENT;
 		if (d_is_negative(path.dentry))
 			goto out_path_put;
+		inode = d_backing_inode(path.dentry);
 	}
 
 	if (flags & WALK_PUT)
@@ -3192,12 +3197,12 @@ retry_lookup:
 		return error;
 
 	BUG_ON(nd->flags & LOOKUP_RCU);
-	inode = d_backing_inode(path.dentry);
 	seq = 0;	/* out of RCU mode, so the value doesn't matter */
 	if (unlikely(d_is_negative(path.dentry))) {
 		path_to_nameidata(&path, nd);
 		return -ENOENT;
 	}
+	inode = d_backing_inode(path.dentry);
 finish_lookup:
 	if (nd->depth)
 		put_link(nd);
@@ -3206,11 +3211,6 @@ finish_lookup:
 	if (unlikely(error))
 		return error;
 
-	if (unlikely(d_is_symlink(path.dentry)) && !(open_flag & O_PATH)) {
-		path_to_nameidata(&path, nd);
-		return -ELOOP;
-	}
-
 	if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path.mnt) {
 		path_to_nameidata(&path, nd);
 	} else {
@@ -3229,6 +3229,10 @@ finish_open:
 		return error;
 	}
 	audit_inode(nd->name, nd->path.dentry, 0);
+	if (unlikely(d_is_symlink(nd->path.dentry)) && !(open_flag & O_PATH)) {
+		error = -ELOOP;
+		goto out;
+	}
 	error = -EISDIR;
 	if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry))
 		goto out;
@@ -3273,6 +3277,10 @@ opened:
 			goto exit_fput;
 	}
 out:
+	if (unlikely(error > 0)) {
+		WARN_ON(1);
+		error = -EINVAL;
+	}
 	if (got_write)
 		mnt_drop_write(nd->path.mnt);
 	path_put(&save_parent);
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index 26c2de2de13f..b7f8eaeea5d8 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -633,7 +633,7 @@ ncp_fill_cache(struct file *file, struct dir_context *ctx,
 				d_rehash(newdent);
 		} else {
 			spin_lock(&dentry->d_lock);
-			NCP_FINFO(inode)->flags &= ~NCPI_DIR_CACHE;
+			NCP_FINFO(dir)->flags &= ~NCPI_DIR_CACHE;
 			spin_unlock(&dentry->d_lock);
 		}
 	} else {
diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c
index c59a59c37f3d..35ab51c04814 100644
--- a/fs/nfs/blocklayout/extent_tree.c
+++ b/fs/nfs/blocklayout/extent_tree.c
@@ -476,6 +476,7 @@ static void ext_tree_free_commitdata(struct nfs4_layoutcommit_args *arg,
 
 		for (i = 0; i < nr_pages; i++)
 			put_page(arg->layoutupdate_pages[i]);
+		vfree(arg->start_p);
 		kfree(arg->layoutupdate_pages);
 	} else {
 		put_page(arg->layoutupdate_page);
@@ -559,10 +560,15 @@ retry:
 
 	if (unlikely(arg->layoutupdate_pages != &arg->layoutupdate_page)) {
 		void *p = start_p, *end = p + arg->layoutupdate_len;
+		struct page *page = NULL;
 		int i = 0;
 
-		for ( ; p < end; p += PAGE_SIZE)
-			arg->layoutupdate_pages[i++] = vmalloc_to_page(p);
+		arg->start_p = start_p;
+		for ( ; p < end; p += PAGE_SIZE) {
+			page = vmalloc_to_page(p);
+			arg->layoutupdate_pages[i++] = page;
+			get_page(page);
+		}
 	}
 
 	dprintk("%s found %zu ranges\n", __func__, count);
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index bd25dc7077f7..dff83460e5a6 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -16,29 +16,8 @@
 
 #define NFSDBG_FACILITY NFSDBG_PROC
 
-static int nfs42_set_rw_stateid(nfs4_stateid *dst, struct file *file,
-				fmode_t fmode)
-{
-	struct nfs_open_context *open;
-	struct nfs_lock_context *lock;
-	int ret;
-
-	open = get_nfs_open_context(nfs_file_open_context(file));
-	lock = nfs_get_lock_context(open);
-	if (IS_ERR(lock)) {
-		put_nfs_open_context(open);
-		return PTR_ERR(lock);
-	}
-
-	ret = nfs4_set_rw_stateid(dst, open, lock, fmode);
-
-	nfs_put_lock_context(lock);
-	put_nfs_open_context(open);
-	return ret;
-}
-
 static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
-				 loff_t offset, loff_t len)
+		struct nfs_lock_context *lock, loff_t offset, loff_t len)
 {
 	struct inode *inode = file_inode(filep);
 	struct nfs_server *server = NFS_SERVER(inode);
@@ -56,7 +35,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 	msg->rpc_argp = &args;
 	msg->rpc_resp = &res;
 
-	status = nfs42_set_rw_stateid(&args.falloc_stateid, filep, FMODE_WRITE);
+	status = nfs4_set_rw_stateid(&args.falloc_stateid, lock->open_context,
+			lock, FMODE_WRITE);
 	if (status)
 		return status;
 
@@ -78,15 +58,26 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 {
 	struct nfs_server *server = NFS_SERVER(file_inode(filep));
 	struct nfs4_exception exception = { };
+	struct nfs_lock_context *lock;
 	int err;
 
+	lock = nfs_get_lock_context(nfs_file_open_context(filep));
+	if (IS_ERR(lock))
+		return PTR_ERR(lock);
+
+	exception.inode = file_inode(filep);
+	exception.state = lock->open_context->state;
+
 	do {
-		err = _nfs42_proc_fallocate(msg, filep, offset, len);
-		if (err == -ENOTSUPP)
-			return -EOPNOTSUPP;
+		err = _nfs42_proc_fallocate(msg, filep, lock, offset, len);
+		if (err == -ENOTSUPP) {
+			err = -EOPNOTSUPP;
+			break;
+		}
 		err = nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
 
+	nfs_put_lock_context(lock);
 	return err;
 }
 
@@ -135,7 +126,8 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
 	return err;
 }
 
-static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
+static loff_t _nfs42_proc_llseek(struct file *filep,
+		struct nfs_lock_context *lock, loff_t offset, int whence)
 {
 	struct inode *inode = file_inode(filep);
 	struct nfs42_seek_args args = {
@@ -156,7 +148,8 @@ static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
 	if (!nfs_server_capable(inode, NFS_CAP_SEEK))
 		return -ENOTSUPP;
 
-	status = nfs42_set_rw_stateid(&args.sa_stateid, filep, FMODE_READ);
+	status = nfs4_set_rw_stateid(&args.sa_stateid, lock->open_context,
+			lock, FMODE_READ);
 	if (status)
 		return status;
 
@@ -175,17 +168,28 @@ loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
 {
 	struct nfs_server *server = NFS_SERVER(file_inode(filep));
 	struct nfs4_exception exception = { };
+	struct nfs_lock_context *lock;
 	loff_t err;
 
+	lock = nfs_get_lock_context(nfs_file_open_context(filep));
+	if (IS_ERR(lock))
+		return PTR_ERR(lock);
+
+	exception.inode = file_inode(filep);
+	exception.state = lock->open_context->state;
+
 	do {
-		err = _nfs42_proc_llseek(filep, offset, whence);
+		err = _nfs42_proc_llseek(filep, lock, offset, whence);
 		if (err >= 0)
 			break;
-		if (err == -ENOTSUPP)
-			return -EOPNOTSUPP;
+		if (err == -ENOTSUPP) {
+			err = -EOPNOTSUPP;
+			break;
+		}
 		err = nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
 
+	nfs_put_lock_context(lock);
 	return err;
 }
 
@@ -298,8 +302,9 @@ int nfs42_proc_layoutstats_generic(struct nfs_server *server,
 }
 
 static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
-			     struct file *dst_f, loff_t src_offset,
-			     loff_t dst_offset, loff_t count)
+		struct file *dst_f, struct nfs_lock_context *src_lock,
+		struct nfs_lock_context *dst_lock, loff_t src_offset,
+		loff_t dst_offset, loff_t count)
 {
 	struct inode *src_inode = file_inode(src_f);
 	struct inode *dst_inode = file_inode(dst_f);
@@ -320,11 +325,13 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
 	msg->rpc_argp = &args;
 	msg->rpc_resp = &res;
 
-	status = nfs42_set_rw_stateid(&args.src_stateid, src_f, FMODE_READ);
+	status = nfs4_set_rw_stateid(&args.src_stateid, src_lock->open_context,
+			src_lock, FMODE_READ);
 	if (status)
 		return status;
 
-	status = nfs42_set_rw_stateid(&args.dst_stateid, dst_f, FMODE_WRITE);
+	status = nfs4_set_rw_stateid(&args.dst_stateid, dst_lock->open_context,
+			dst_lock, FMODE_WRITE);
 	if (status)
 		return status;
 
@@ -349,22 +356,48 @@ int nfs42_proc_clone(struct file *src_f, struct file *dst_f,
 	};
 	struct inode *inode = file_inode(src_f);
 	struct nfs_server *server = NFS_SERVER(file_inode(src_f));
-	struct nfs4_exception exception = { };
-	int err;
+	struct nfs_lock_context *src_lock;
+	struct nfs_lock_context *dst_lock;
+	struct nfs4_exception src_exception = { };
+	struct nfs4_exception dst_exception = { };
+	int err, err2;
 
 	if (!nfs_server_capable(inode, NFS_CAP_CLONE))
 		return -EOPNOTSUPP;
 
+	src_lock = nfs_get_lock_context(nfs_file_open_context(src_f));
+	if (IS_ERR(src_lock))
+		return PTR_ERR(src_lock);
+
+	src_exception.inode = file_inode(src_f);
+	src_exception.state = src_lock->open_context->state;
+
+	dst_lock = nfs_get_lock_context(nfs_file_open_context(dst_f));
+	if (IS_ERR(dst_lock)) {
+		err = PTR_ERR(dst_lock);
+		goto out_put_src_lock;
+	}
+
+	dst_exception.inode = file_inode(dst_f);
+	dst_exception.state = dst_lock->open_context->state;
+
 	do {
-		err = _nfs42_proc_clone(&msg, src_f, dst_f, src_offset,
-					dst_offset, count);
+		err = _nfs42_proc_clone(&msg, src_f, dst_f, src_lock, dst_lock,
+					src_offset, dst_offset, count);
 		if (err == -ENOTSUPP || err == -EOPNOTSUPP) {
 			NFS_SERVER(inode)->caps &= ~NFS_CAP_CLONE;
-			return -EOPNOTSUPP;
+			err = -EOPNOTSUPP;
+			break;
 		}
-		err = nfs4_handle_exception(server, err, &exception);
-	} while (exception.retry);
 
-	return err;
+		err2 = nfs4_handle_exception(server, err, &src_exception);
+		err = nfs4_handle_exception(server, err, &dst_exception);
+		if (!err)
+			err = err2;
+	} while (src_exception.retry || dst_exception.retry);
 
+	nfs_put_lock_context(dst_lock);
+out_put_src_lock:
+	nfs_put_lock_context(src_lock);
+	return err;
 }
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 4bfc33ad0563..14881594dd07 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2466,9 +2466,9 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 		dentry = d_add_unique(dentry, igrab(state->inode));
 		if (dentry == NULL) {
 			dentry = opendata->dentry;
-		} else if (dentry != ctx->dentry) {
+		} else {
 			dput(ctx->dentry);
-			ctx->dentry = dget(dentry);
+			ctx->dentry = dentry;
 		}
 		nfs_set_verifier(dentry,
 				nfs_save_change_attribute(d_inode(opendata->dir)));
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 482b6e94bb37..2fa483e6dbe2 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -252,6 +252,27 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo)
 	}
 }
 
+/*
+ * Mark a pnfs_layout_hdr and all associated layout segments as invalid
+ *
+ * In order to continue using the pnfs_layout_hdr, a full recovery
+ * is required.
+ * Note that caller must hold inode->i_lock.
+ */
+static int
+pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo,
+		struct list_head *lseg_list)
+{
+	struct pnfs_layout_range range = {
+		.iomode = IOMODE_ANY,
+		.offset = 0,
+		.length = NFS4_MAX_UINT64,
+	};
+
+	set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+	return pnfs_mark_matching_lsegs_invalid(lo, lseg_list, &range);
+}
+
 static int
 pnfs_iomode_to_fail_bit(u32 iomode)
 {
@@ -554,9 +575,8 @@ pnfs_destroy_layout(struct nfs_inode *nfsi)
 	spin_lock(&nfsi->vfs_inode.i_lock);
 	lo = nfsi->layout;
 	if (lo) {
-		lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */
-		pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
 		pnfs_get_layout_hdr(lo);
+		pnfs_mark_layout_stateid_invalid(lo, &tmp_list);
 		pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RO_FAILED);
 		pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED);
 		spin_unlock(&nfsi->vfs_inode.i_lock);
@@ -617,11 +637,6 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list,
 {
 	struct pnfs_layout_hdr *lo;
 	struct inode *inode;
-	struct pnfs_layout_range range = {
-		.iomode = IOMODE_ANY,
-		.offset = 0,
-		.length = NFS4_MAX_UINT64,
-	};
 	LIST_HEAD(lseg_list);
 	int ret = 0;
 
@@ -636,11 +651,11 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list,
 
 		spin_lock(&inode->i_lock);
 		list_del_init(&lo->plh_bulk_destroy);
-		lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */
-		if (is_bulk_recall)
-			set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
-		if (pnfs_mark_matching_lsegs_invalid(lo, &lseg_list, &range))
+		if (pnfs_mark_layout_stateid_invalid(lo, &lseg_list)) {
+			if (is_bulk_recall)
+				set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
 			ret = -EAGAIN;
+		}
 		spin_unlock(&inode->i_lock);
 		pnfs_free_lseg_list(&lseg_list);
 		/* Free all lsegs that are attached to commit buckets */
@@ -1738,8 +1753,19 @@ pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode)
 	if (lo->plh_return_iomode != 0)
 		iomode = IOMODE_ANY;
 	lo->plh_return_iomode = iomode;
+	set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
 }
 
+/**
+ * pnfs_mark_matching_lsegs_return - Free or return matching layout segments
+ * @lo: pointer to layout header
+ * @tmp_list: list header to be used with pnfs_free_lseg_list()
+ * @return_range: describe layout segment ranges to be returned
+ *
+ * This function is mainly intended for use by layoutrecall. It attempts
+ * to free the layout segment immediately, or else to mark it for return
+ * as soon as its reference count drops to zero.
+ */
 int
 pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
 				struct list_head *tmp_list,
@@ -1762,12 +1788,11 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
 				lseg, lseg->pls_range.iomode,
 				lseg->pls_range.offset,
 				lseg->pls_range.length);
+			if (mark_lseg_invalid(lseg, tmp_list))
+				continue;
+			remaining++;
 			set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags);
 			pnfs_set_plh_return_iomode(lo, return_range->iomode);
-			if (!mark_lseg_invalid(lseg, tmp_list))
-				remaining++;
-			set_bit(NFS_LAYOUT_RETURN_REQUESTED,
-					&lo->plh_flags);
 		}
 	return remaining;
 }
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index dc8ebecf5618..195fe2668207 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -32,10 +32,10 @@
 *
 */
 
+#include <crypto/hash.h>
 #include <linux/file.h>
 #include <linux/slab.h>
 #include <linux/namei.h>
-#include <linux/crypto.h>
 #include <linux/sched.h>
 #include <linux/fs.h>
 #include <linux/module.h>
@@ -104,29 +104,35 @@ static int
 nfs4_make_rec_clidname(char *dname, const struct xdr_netobj *clname)
 {
 	struct xdr_netobj cksum;
-	struct hash_desc desc;
-	struct scatterlist sg;
+	struct crypto_shash *tfm;
 	int status;
 
 	dprintk("NFSD: nfs4_make_rec_clidname for %.*s\n",
 			clname->len, clname->data);
-	desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
-	desc.tfm = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(desc.tfm)) {
-		status = PTR_ERR(desc.tfm);
+	tfm = crypto_alloc_shash("md5", 0, 0);
+	if (IS_ERR(tfm)) {
+		status = PTR_ERR(tfm);
 		goto out_no_tfm;
 	}
 
-	cksum.len = crypto_hash_digestsize(desc.tfm);
+	cksum.len = crypto_shash_digestsize(tfm);
 	cksum.data = kmalloc(cksum.len, GFP_KERNEL);
 	if (cksum.data == NULL) {
 		status = -ENOMEM;
  		goto out;
 	}
 
-	sg_init_one(&sg, clname->data, clname->len);
+	{
+		SHASH_DESC_ON_STACK(desc, tfm);
+
+		desc->tfm = tfm;
+		desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+		status = crypto_shash_digest(desc, clname->data, clname->len,
+					     cksum.data);
+		shash_desc_zero(desc);
+	}
 
-	status = crypto_hash_digest(&desc, &sg, sg.length, cksum.data);
 	if (status)
 		goto out;
 
@@ -135,7 +141,7 @@ nfs4_make_rec_clidname(char *dname, const struct xdr_netobj *clname)
 	status = 0;
 out:
 	kfree(cksum.data);
-	crypto_free_hash(desc.tfm);
+	crypto_free_shash(tfm);
 out_no_tfm:
 	return status;
 }
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index cfcbf114676e..7115c5d7d373 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -91,7 +91,14 @@
 #include <linux/fsnotify_backend.h>
 #include "fsnotify.h"
 
+#define FSNOTIFY_REAPER_DELAY	(1)	/* 1 jiffy */
+
 struct srcu_struct fsnotify_mark_srcu;
+static DEFINE_SPINLOCK(destroy_lock);
+static LIST_HEAD(destroy_list);
+
+static void fsnotify_mark_destroy(struct work_struct *work);
+static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy);
 
 void fsnotify_get_mark(struct fsnotify_mark *mark)
 {
@@ -165,19 +172,10 @@ void fsnotify_detach_mark(struct fsnotify_mark *mark)
 	atomic_dec(&group->num_marks);
 }
 
-static void
-fsnotify_mark_free_rcu(struct rcu_head *rcu)
-{
-	struct fsnotify_mark	*mark;
-
-	mark = container_of(rcu, struct fsnotify_mark, g_rcu);
-	fsnotify_put_mark(mark);
-}
-
 /*
- * Free fsnotify mark. The freeing is actually happening from a call_srcu
- * callback. Caller must have a reference to the mark or be protected by
- * fsnotify_mark_srcu.
+ * Free fsnotify mark. The freeing is actually happening from a kthread which
+ * first waits for srcu period end. Caller must have a reference to the mark
+ * or be protected by fsnotify_mark_srcu.
  */
 void fsnotify_free_mark(struct fsnotify_mark *mark)
 {
@@ -192,7 +190,11 @@ void fsnotify_free_mark(struct fsnotify_mark *mark)
 	mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
 	spin_unlock(&mark->lock);
 
-	call_srcu(&fsnotify_mark_srcu, &mark->g_rcu, fsnotify_mark_free_rcu);
+	spin_lock(&destroy_lock);
+	list_add(&mark->g_list, &destroy_list);
+	spin_unlock(&destroy_lock);
+	queue_delayed_work(system_unbound_wq, &reaper_work,
+				FSNOTIFY_REAPER_DELAY);
 
 	/*
 	 * Some groups like to know that marks are being freed.  This is a
@@ -388,7 +390,12 @@ err:
 
 	spin_unlock(&mark->lock);
 
-	call_srcu(&fsnotify_mark_srcu, &mark->g_rcu, fsnotify_mark_free_rcu);
+	spin_lock(&destroy_lock);
+	list_add(&mark->g_list, &destroy_list);
+	spin_unlock(&destroy_lock);
+	queue_delayed_work(system_unbound_wq, &reaper_work,
+				FSNOTIFY_REAPER_DELAY);
+
 	return ret;
 }
 
@@ -491,3 +498,21 @@ void fsnotify_init_mark(struct fsnotify_mark *mark,
 	atomic_set(&mark->refcnt, 1);
 	mark->free_mark = free_mark;
 }
+
+static void fsnotify_mark_destroy(struct work_struct *work)
+{
+	struct fsnotify_mark *mark, *next;
+	struct list_head private_destroy_list;
+
+	spin_lock(&destroy_lock);
+	/* exchange the list head */
+	list_replace_init(&destroy_list, &private_destroy_list);
+	spin_unlock(&destroy_lock);
+
+	synchronize_srcu(&fsnotify_mark_srcu);
+
+	list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) {
+		list_del_init(&mark->g_list);
+		fsnotify_put_mark(mark);
+	}
+}
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 794fd1587f34..cda0361e95a4 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -956,6 +956,7 @@ clean_orphan:
 		tmp_ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh,
 				update_isize, end);
 		if (tmp_ret < 0) {
+			ocfs2_inode_unlock(inode, 1);
 			ret = tmp_ret;
 			mlog_errno(ret);
 			brelse(di_bh);
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index a76b9ea7722e..ef6a2ec494de 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -287,7 +287,6 @@ struct o2hb_bio_wait_ctxt {
 static void o2hb_write_timeout(struct work_struct *work)
 {
 	int failed, quorum;
-	unsigned long flags;
 	struct o2hb_region *reg =
 		container_of(work, struct o2hb_region,
 			     hr_write_timeout_work.work);
@@ -297,14 +296,14 @@ static void o2hb_write_timeout(struct work_struct *work)
 	     jiffies_to_msecs(jiffies - reg->hr_last_timeout_start));
 
 	if (o2hb_global_heartbeat_active()) {
-		spin_lock_irqsave(&o2hb_live_lock, flags);
+		spin_lock(&o2hb_live_lock);
 		if (test_bit(reg->hr_region_num, o2hb_quorum_region_bitmap))
 			set_bit(reg->hr_region_num, o2hb_failed_region_bitmap);
 		failed = bitmap_weight(o2hb_failed_region_bitmap,
 					O2NM_MAX_REGIONS);
 		quorum = bitmap_weight(o2hb_quorum_region_bitmap,
 					O2NM_MAX_REGIONS);
-		spin_unlock_irqrestore(&o2hb_live_lock, flags);
+		spin_unlock(&o2hb_live_lock);
 
 		mlog(ML_HEARTBEAT, "Number of regions %d, failed regions %d\n",
 		     quorum, failed);
@@ -2425,11 +2424,10 @@ EXPORT_SYMBOL_GPL(o2hb_check_node_heartbeating);
 int o2hb_check_node_heartbeating_no_sem(u8 node_num)
 {
 	unsigned long testing_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
-	unsigned long flags;
 
-	spin_lock_irqsave(&o2hb_live_lock, flags);
+	spin_lock(&o2hb_live_lock);
 	o2hb_fill_node_map_from_callback(testing_map, sizeof(testing_map));
-	spin_unlock_irqrestore(&o2hb_live_lock, flags);
+	spin_unlock(&o2hb_live_lock);
 	if (!test_bit(node_num, testing_map)) {
 		mlog(ML_HEARTBEAT,
 		     "node (%u) does not have heartbeating enabled.\n",
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index 68c607e63ff6..004f2cbe8f71 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -282,6 +282,7 @@ static inline void __dlm_set_joining_node(struct dlm_ctxt *dlm,
 #define DLM_LOCK_RES_DROPPING_REF         0x00000040
 #define DLM_LOCK_RES_BLOCK_DIRTY          0x00001000
 #define DLM_LOCK_RES_SETREF_INPROG        0x00002000
+#define DLM_LOCK_RES_RECOVERY_WAITING     0x00004000
 
 /* max milliseconds to wait to sync up a network failure with a node death */
 #define DLM_NODE_DEATH_WAIT_MAX (5 * 1000)
@@ -451,6 +452,7 @@ enum {
 	DLM_QUERY_REGION		= 519,
 	DLM_QUERY_NODEINFO		= 520,
 	DLM_BEGIN_EXIT_DOMAIN_MSG	= 521,
+	DLM_DEREF_LOCKRES_DONE		= 522,
 };
 
 struct dlm_reco_node_data
@@ -545,7 +547,7 @@ struct dlm_master_requery
  * };
  *
  * from ../cluster/tcp.h
- *    NET_MAX_PAYLOAD_BYTES  (4096 - sizeof(net_msg))
+ *    O2NET_MAX_PAYLOAD_BYTES  (4096 - sizeof(net_msg))
  *    (roughly 4080 bytes)
  * and sizeof(dlm_migratable_lockres) = 112 bytes
  * and sizeof(dlm_migratable_lock) = 16 bytes
@@ -586,7 +588,7 @@ struct dlm_migratable_lockres
 
 /* from above, 128 bytes
  * for some undetermined future use */
-#define DLM_MIG_LOCKRES_RESERVED   (NET_MAX_PAYLOAD_BYTES - \
+#define DLM_MIG_LOCKRES_RESERVED   (O2NET_MAX_PAYLOAD_BYTES - \
 				    DLM_MIG_LOCKRES_MAX_LEN)
 
 struct dlm_create_lock
@@ -782,6 +784,20 @@ struct dlm_deref_lockres
 	u8 name[O2NM_MAX_NAME_LEN];
 };
 
+enum {
+	DLM_DEREF_RESPONSE_DONE = 0,
+	DLM_DEREF_RESPONSE_INPROG = 1,
+};
+
+struct dlm_deref_lockres_done {
+	u32 pad1;
+	u16 pad2;
+	u8 node_idx;
+	u8 namelen;
+
+	u8 name[O2NM_MAX_NAME_LEN];
+};
+
 static inline enum dlm_status
 __dlm_lockres_state_to_status(struct dlm_lock_resource *res)
 {
@@ -789,7 +805,8 @@ __dlm_lockres_state_to_status(struct dlm_lock_resource *res)
 
 	assert_spin_locked(&res->spinlock);
 
-	if (res->state & DLM_LOCK_RES_RECOVERING)
+	if (res->state & (DLM_LOCK_RES_RECOVERING|
+			DLM_LOCK_RES_RECOVERY_WAITING))
 		status = DLM_RECOVERING;
 	else if (res->state & DLM_LOCK_RES_MIGRATING)
 		status = DLM_MIGRATING;
@@ -968,6 +985,8 @@ int dlm_assert_master_handler(struct o2net_msg *msg, u32 len, void *data,
 void dlm_assert_master_post_handler(int status, void *data, void *ret_data);
 int dlm_deref_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 			      void **ret_data);
+int dlm_deref_lockres_done_handler(struct o2net_msg *msg, u32 len, void *data,
+			      void **ret_data);
 int dlm_migrate_request_handler(struct o2net_msg *msg, u32 len, void *data,
 				void **ret_data);
 int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
@@ -1009,6 +1028,7 @@ static inline void __dlm_wait_on_lockres(struct dlm_lock_resource *res)
 {
 	__dlm_wait_on_lockres_flags(res, (DLM_LOCK_RES_IN_PROGRESS|
 				    	  DLM_LOCK_RES_RECOVERING|
+					  DLM_LOCK_RES_RECOVERY_WAITING|
 					  DLM_LOCK_RES_MIGRATING));
 }
 
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 2ee7fe747cea..12e064b8be9a 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -132,10 +132,13 @@ static DECLARE_WAIT_QUEUE_HEAD(dlm_domain_events);
  *	- Message DLM_QUERY_NODEINFO added to allow online node removes
  * New in version 1.2:
  * 	- Message DLM_BEGIN_EXIT_DOMAIN_MSG added to mark start of exit domain
+ * New in version 1.3:
+ *	- Message DLM_DEREF_LOCKRES_DONE added to inform non-master that the
+ *	  refmap is cleared
  */
 static const struct dlm_protocol_version dlm_protocol = {
 	.pv_major = 1,
-	.pv_minor = 2,
+	.pv_minor = 3,
 };
 
 #define DLM_DOMAIN_BACKOFF_MS 200
@@ -1396,7 +1399,7 @@ static int dlm_send_join_cancels(struct dlm_ctxt *dlm,
 				 unsigned int map_size)
 {
 	int status, tmpstat;
-	unsigned int node;
+	int node;
 
 	if (map_size != (BITS_TO_LONGS(O2NM_MAX_NODES) *
 			 sizeof(unsigned long))) {
@@ -1853,7 +1856,13 @@ static int dlm_register_domain_handlers(struct dlm_ctxt *dlm)
 					sizeof(struct dlm_exit_domain),
 					dlm_begin_exit_domain_handler,
 					dlm, NULL, &dlm->dlm_domain_handlers);
+	if (status)
+		goto bail;
 
+	status = o2net_register_handler(DLM_DEREF_LOCKRES_DONE, dlm->key,
+					sizeof(struct dlm_deref_lockres_done),
+					dlm_deref_lockres_done_handler,
+					dlm, NULL, &dlm->dlm_domain_handlers);
 bail:
 	if (status)
 		dlm_unregister_domain_handlers(dlm);
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 9477d6e1de37..9aed6e202201 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2278,7 +2278,7 @@ int dlm_drop_lockres_ref(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
 		dlm_print_one_lock_resource(res);
 		BUG();
 	}
-	return ret;
+	return ret ? ret : r;
 }
 
 int dlm_deref_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
@@ -2345,7 +2345,7 @@ int dlm_deref_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 		     	res->lockname.len, res->lockname.name, node);
 			dlm_print_one_lock_resource(res);
 		}
-		ret = 0;
+		ret = DLM_DEREF_RESPONSE_DONE;
 		goto done;
 	}
 
@@ -2365,7 +2365,7 @@ int dlm_deref_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 	spin_unlock(&dlm->work_lock);
 
 	queue_work(dlm->dlm_worker, &dlm->dispatched_work);
-	return 0;
+	return DLM_DEREF_RESPONSE_INPROG;
 
 done:
 	if (res)
@@ -2375,6 +2375,122 @@ done:
 	return ret;
 }
 
+int dlm_deref_lockres_done_handler(struct o2net_msg *msg, u32 len, void *data,
+			      void **ret_data)
+{
+	struct dlm_ctxt *dlm = data;
+	struct dlm_deref_lockres_done *deref
+			= (struct dlm_deref_lockres_done *)msg->buf;
+	struct dlm_lock_resource *res = NULL;
+	char *name;
+	unsigned int namelen;
+	int ret = -EINVAL;
+	u8 node;
+	unsigned int hash;
+
+	if (!dlm_grab(dlm))
+		return 0;
+
+	name = deref->name;
+	namelen = deref->namelen;
+	node = deref->node_idx;
+
+	if (namelen > DLM_LOCKID_NAME_MAX) {
+		mlog(ML_ERROR, "Invalid name length!");
+		goto done;
+	}
+	if (deref->node_idx >= O2NM_MAX_NODES) {
+		mlog(ML_ERROR, "Invalid node number: %u\n", node);
+		goto done;
+	}
+
+	hash = dlm_lockid_hash(name, namelen);
+
+	spin_lock(&dlm->spinlock);
+	res = __dlm_lookup_lockres_full(dlm, name, namelen, hash);
+	if (!res) {
+		spin_unlock(&dlm->spinlock);
+		mlog(ML_ERROR, "%s:%.*s: bad lockres name\n",
+		     dlm->name, namelen, name);
+		goto done;
+	}
+
+	spin_lock(&res->spinlock);
+	BUG_ON(!(res->state & DLM_LOCK_RES_DROPPING_REF));
+	if (!list_empty(&res->purge)) {
+		mlog(0, "%s: Removing res %.*s from purgelist\n",
+			dlm->name, res->lockname.len, res->lockname.name);
+		list_del_init(&res->purge);
+		dlm_lockres_put(res);
+		dlm->purge_count--;
+	}
+
+	if (!__dlm_lockres_unused(res)) {
+		mlog(ML_ERROR, "%s: res %.*s in use after deref\n",
+			dlm->name, res->lockname.len, res->lockname.name);
+		__dlm_print_one_lock_resource(res);
+		BUG();
+	}
+
+	__dlm_unhash_lockres(dlm, res);
+
+	spin_lock(&dlm->track_lock);
+	if (!list_empty(&res->tracking))
+		list_del_init(&res->tracking);
+	else {
+		mlog(ML_ERROR, "%s: Resource %.*s not on the Tracking list\n",
+		     dlm->name, res->lockname.len, res->lockname.name);
+		__dlm_print_one_lock_resource(res);
+	}
+	spin_unlock(&dlm->track_lock);
+
+	/* lockres is not in the hash now. drop the flag and wake up
+	 * any processes waiting in dlm_get_lock_resource.
+	 */
+	res->state &= ~DLM_LOCK_RES_DROPPING_REF;
+	spin_unlock(&res->spinlock);
+	wake_up(&res->wq);
+
+	dlm_lockres_put(res);
+
+	spin_unlock(&dlm->spinlock);
+
+done:
+	dlm_put(dlm);
+	return ret;
+}
+
+static void dlm_drop_lockres_ref_done(struct dlm_ctxt *dlm,
+		struct dlm_lock_resource *res, u8 node)
+{
+	struct dlm_deref_lockres_done deref;
+	int ret = 0, r;
+	const char *lockname;
+	unsigned int namelen;
+
+	lockname = res->lockname.name;
+	namelen = res->lockname.len;
+	BUG_ON(namelen > O2NM_MAX_NAME_LEN);
+
+	memset(&deref, 0, sizeof(deref));
+	deref.node_idx = dlm->node_num;
+	deref.namelen = namelen;
+	memcpy(deref.name, lockname, namelen);
+
+	ret = o2net_send_message(DLM_DEREF_LOCKRES_DONE, dlm->key,
+				 &deref, sizeof(deref), node, &r);
+	if (ret < 0) {
+		mlog(ML_ERROR, "%s: res %.*s, error %d send DEREF DONE "
+				" to node %u\n", dlm->name, namelen,
+				lockname, ret, node);
+	} else if (r < 0) {
+		/* ignore the error */
+		mlog(ML_ERROR, "%s: res %.*s, DEREF to node %u got %d\n",
+		     dlm->name, namelen, lockname, node, r);
+		dlm_print_one_lock_resource(res);
+	}
+}
+
 static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data)
 {
 	struct dlm_ctxt *dlm;
@@ -2395,6 +2511,8 @@ static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data)
 	}
 	spin_unlock(&res->spinlock);
 
+	dlm_drop_lockres_ref_done(dlm, res, node);
+
 	if (cleared) {
 		mlog(0, "%s:%.*s node %u ref dropped in dispatch\n",
 		     dlm->name, res->lockname.len, res->lockname.name, node);
@@ -2432,7 +2550,8 @@ static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
 		return 0;
 
 	/* delay migration when the lockres is in RECOCERING state */
-	if (res->state & DLM_LOCK_RES_RECOVERING)
+	if (res->state & (DLM_LOCK_RES_RECOVERING|
+			DLM_LOCK_RES_RECOVERY_WAITING))
 		return 0;
 
 	if (res->owner != dlm->node_num)
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index b94a425f0175..cd38488a10fc 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1403,12 +1403,24 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 	 * and RECOVERY flag changed when it completes. */
 	hash = dlm_lockid_hash(mres->lockname, mres->lockname_len);
 	spin_lock(&dlm->spinlock);
-	res = __dlm_lookup_lockres(dlm, mres->lockname, mres->lockname_len,
+	res = __dlm_lookup_lockres_full(dlm, mres->lockname, mres->lockname_len,
 			hash);
 	if (res) {
 	 	/* this will get a ref on res */
 		/* mark it as recovering/migrating and hash it */
 		spin_lock(&res->spinlock);
+		if (res->state & DLM_LOCK_RES_DROPPING_REF) {
+			mlog(0, "%s: node is attempting to migrate "
+				"lockres %.*s, but marked as dropping "
+				" ref!\n", dlm->name,
+				mres->lockname_len, mres->lockname);
+			ret = -EINVAL;
+			spin_unlock(&res->spinlock);
+			spin_unlock(&dlm->spinlock);
+			dlm_lockres_put(res);
+			goto leave;
+		}
+
 		if (mres->flags & DLM_MRES_RECOVERY) {
 			res->state |= DLM_LOCK_RES_RECOVERING;
 		} else {
@@ -2163,6 +2175,13 @@ static void dlm_finish_local_lockres_recovery(struct dlm_ctxt *dlm,
 	for (i = 0; i < DLM_HASH_BUCKETS; i++) {
 		bucket = dlm_lockres_hash(dlm, i);
 		hlist_for_each_entry(res, bucket, hash_node) {
+			if (res->state & DLM_LOCK_RES_RECOVERY_WAITING) {
+				spin_lock(&res->spinlock);
+				res->state &= ~DLM_LOCK_RES_RECOVERY_WAITING;
+				spin_unlock(&res->spinlock);
+				wake_up(&res->wq);
+			}
+
 			if (!(res->state & DLM_LOCK_RES_RECOVERING))
 				continue;
 
@@ -2300,6 +2319,7 @@ static void dlm_free_dead_locks(struct dlm_ctxt *dlm,
 			     res->lockname.len, res->lockname.name, freed, dead_node);
 			__dlm_print_one_lock_resource(res);
 		}
+		res->state |= DLM_LOCK_RES_RECOVERY_WAITING;
 		dlm_lockres_clear_refmap_bit(dlm, res, dead_node);
 	} else if (test_bit(dead_node, res->refmap)) {
 		mlog(0, "%s:%.*s: dead node %u had a ref, but had "
@@ -2377,14 +2397,16 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 			dlm_revalidate_lvb(dlm, res, dead_node);
 			if (res->owner == dead_node) {
 				if (res->state & DLM_LOCK_RES_DROPPING_REF) {
-					mlog(ML_NOTICE, "%s: res %.*s, Skip "
-					     "recovery as it is being freed\n",
-					     dlm->name, res->lockname.len,
-					     res->lockname.name);
-				} else
-					dlm_move_lockres_to_recovery_list(dlm,
-									  res);
-
+					mlog(0, "%s:%.*s: owned by "
+						"dead node %u, this node was "
+						"dropping its ref when it died. "
+						"continue, dropping the flag.\n",
+						dlm->name, res->lockname.len,
+						res->lockname.name, dead_node);
+				}
+				res->state &= ~DLM_LOCK_RES_DROPPING_REF;
+				dlm_move_lockres_to_recovery_list(dlm,
+						res);
 			} else if (res->owner == dlm->node_num) {
 				dlm_free_dead_locks(dlm, res, dead_node);
 				__dlm_lockres_calc_usage(dlm, res);
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index c5f6c241ecd7..68d239ba0c63 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -106,7 +106,8 @@ int __dlm_lockres_unused(struct dlm_lock_resource *res)
 	if (!list_empty(&res->dirty) || res->state & DLM_LOCK_RES_DIRTY)
 		return 0;
 
-	if (res->state & DLM_LOCK_RES_RECOVERING)
+	if (res->state & (DLM_LOCK_RES_RECOVERING|
+			DLM_LOCK_RES_RECOVERY_WAITING))
 		return 0;
 
 	/* Another node has this resource with this node as the master */
@@ -202,6 +203,13 @@ static void dlm_purge_lockres(struct dlm_ctxt *dlm,
 		dlm->purge_count--;
 	}
 
+	if (!master && ret != 0) {
+		mlog(0, "%s: deref %.*s in progress or master goes down\n",
+			dlm->name, res->lockname.len, res->lockname.name);
+		spin_unlock(&res->spinlock);
+		return;
+	}
+
 	if (!__dlm_lockres_unused(res)) {
 		mlog(ML_ERROR, "%s: res %.*s in use after deref\n",
 		     dlm->name, res->lockname.len, res->lockname.name);
@@ -700,7 +708,8 @@ static int dlm_thread(void *data)
 			 * dirty for a short while. */
 			BUG_ON(res->state & DLM_LOCK_RES_MIGRATING);
 			if (res->state & (DLM_LOCK_RES_IN_PROGRESS |
-					  DLM_LOCK_RES_RECOVERING)) {
+					  DLM_LOCK_RES_RECOVERING |
+					  DLM_LOCK_RES_RECOVERY_WAITING)) {
 				/* move it to the tail and keep going */
 				res->state &= ~DLM_LOCK_RES_DIRTY;
 				spin_unlock(&res->spinlock);
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 9581d190f6e1..77ebc2bc1cca 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -147,6 +147,10 @@ static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	ret = ocfs2_inode_lock(inode, &di_bh, 1);
 	if (ret < 0) {
 		mlog_errno(ret);
+		if (ret == -ENOMEM)
+			ret = VM_FAULT_OOM;
+		else
+			ret = VM_FAULT_SIGBUS;
 		goto out;
 	}
 
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index faa1365097bc..302854ee0985 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -236,6 +236,7 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len)
 	struct ocfs2_recovery_map *rm = osb->recovery_map;
 	struct ocfs2_orphan_scan *os = &osb->osb_orphan_scan;
 	int i, out = 0;
+	unsigned long flags;
 
 	out += snprintf(buf + out, len - out,
 			"%10s => Id: %-s  Uuid: %-s  Gen: 0x%X  Label: %-s\n",
@@ -271,14 +272,14 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len)
 				cconn->cc_version.pv_minor);
 	}
 
-	spin_lock(&osb->dc_task_lock);
+	spin_lock_irqsave(&osb->dc_task_lock, flags);
 	out += snprintf(buf + out, len - out,
 			"%10s => Pid: %d  Count: %lu  WakeSeq: %lu  "
 			"WorkSeq: %lu\n", "DownCnvt",
 			(osb->dc_task ?  task_pid_nr(osb->dc_task) : -1),
 			osb->blocked_lock_count, osb->dc_wake_sequence,
 			osb->dc_work_sequence);
-	spin_unlock(&osb->dc_task_lock);
+	spin_unlock_irqrestore(&osb->dc_task_lock, flags);
 
 	spin_lock(&osb->osb_lock);
 	out += snprintf(buf + out, len - out, "%10s => Pid: %d  Nodes:",
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index ed95272d57a6..52f6de5d40a9 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -618,7 +618,8 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
 	 * sole user of this dentry.  Too tricky...  Just unhash for
 	 * now.
 	 */
-	d_drop(dentry);
+	if (!err)
+		d_drop(dentry);
 	inode_unlock(dir);
 
 	return err;
@@ -903,6 +904,13 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 	if (!overwrite && new_is_dir && !old_opaque && new_opaque)
 		ovl_remove_opaque(newdentry);
 
+	/*
+	 * Old dentry now lives in different location. Dentries in
+	 * lowerstack are stale. We cannot drop them here because
+	 * access to them is lockless. This could be only pure upper
+	 * or opaque directory - numlower is zero. Or upper non-dir
+	 * entry - its pureness is tracked by flag opaque.
+	 */
 	if (old_opaque != new_opaque) {
 		ovl_dentry_set_opaque(old, new_opaque);
 		if (!overwrite)
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 49e204560655..a4ff5d0d7db9 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -65,6 +65,8 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 
 		inode_lock(upperdentry->d_inode);
 		err = notify_change(upperdentry, attr, NULL);
+		if (!err)
+			ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
 		inode_unlock(upperdentry->d_inode);
 	}
 	ovl_drop_write(dentry);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 8d826bd56b26..619ad4b016d2 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -76,12 +76,14 @@ enum ovl_path_type ovl_path_type(struct dentry *dentry)
 	if (oe->__upperdentry) {
 		type = __OVL_PATH_UPPER;
 
-		if (oe->numlower) {
-			if (S_ISDIR(dentry->d_inode->i_mode))
-				type |= __OVL_PATH_MERGE;
-		} else if (!oe->opaque) {
+		/*
+		 * Non-dir dentry can hold lower dentry from previous
+		 * location. Its purity depends only on opaque flag.
+		 */
+		if (oe->numlower && S_ISDIR(dentry->d_inode->i_mode))
+			type |= __OVL_PATH_MERGE;
+		else if (!oe->opaque)
 			type |= __OVL_PATH_PURE;
-		}
 	} else {
 		if (oe->numlower > 1)
 			type |= __OVL_PATH_MERGE;
@@ -341,6 +343,7 @@ static const struct dentry_operations ovl_dentry_operations = {
 
 static const struct dentry_operations ovl_reval_dentry_operations = {
 	.d_release = ovl_dentry_release,
+	.d_select_inode = ovl_d_select_inode,
 	.d_revalidate = ovl_dentry_revalidate,
 	.d_weak_revalidate = ovl_dentry_weak_revalidate,
 };
diff --git a/fs/pnode.c b/fs/pnode.c
index 6367e1e435c6..c524fdddc7fb 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -202,6 +202,11 @@ static struct mount *last_dest, *last_source, *dest_master;
 static struct mountpoint *mp;
 static struct hlist_head *list;
 
+static inline bool peers(struct mount *m1, struct mount *m2)
+{
+	return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id;
+}
+
 static int propagate_one(struct mount *m)
 {
 	struct mount *child;
@@ -212,7 +217,7 @@ static int propagate_one(struct mount *m)
 	/* skip if mountpoint isn't covered by it */
 	if (!is_subdir(mp->m_dentry, m->mnt.mnt_root))
 		return 0;
-	if (m->mnt_group_id == last_dest->mnt_group_id) {
+	if (peers(m, last_dest)) {
 		type = CL_MAKE_SHARED;
 	} else {
 		struct mount *n, *p;
@@ -223,7 +228,7 @@ static int propagate_one(struct mount *m)
 					last_source = last_source->mnt_master;
 					last_dest = last_source->mnt_parent;
 				}
-				if (n->mnt_group_id != last_dest->mnt_group_id) {
+				if (!peers(n, last_dest)) {
 					last_source = last_source->mnt_master;
 					last_dest = last_source->mnt_parent;
 				}
diff --git a/fs/read_write.c b/fs/read_write.c
index 324ec271cc4e..dadf24e5c95b 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -17,6 +17,7 @@
 #include <linux/splice.h>
 #include <linux/compat.h>
 #include <linux/mount.h>
+#include <linux/fs.h>
 #include "internal.h"
 
 #include <asm/uaccess.h>
@@ -183,7 +184,7 @@ loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence)
 	switch (whence) {
 	case SEEK_SET: case SEEK_CUR:
 		return generic_file_llseek_size(file, offset, whence,
-						~0ULL, 0);
+						OFFSET_MAX, 0);
 	default:
 		return -EINVAL;
 	}
@@ -1532,10 +1533,12 @@ int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 
 	if (!(file_in->f_mode & FMODE_READ) ||
 	    !(file_out->f_mode & FMODE_WRITE) ||
-	    (file_out->f_flags & O_APPEND) ||
-	    !file_in->f_op->clone_file_range)
+	    (file_out->f_flags & O_APPEND))
 		return -EBADF;
 
+	if (!file_in->f_op->clone_file_range)
+		return -EOPNOTSUPP;
+
 	ret = clone_verify_area(file_in, pos_in, len, false);
 	if (ret)
 		return ret;
diff --git a/fs/super.c b/fs/super.c
index 1182af8fd5ff..74914b1bae70 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -415,6 +415,7 @@ void generic_shutdown_super(struct super_block *sb)
 		sb->s_flags &= ~MS_ACTIVE;
 
 		fsnotify_unmount_inodes(sb);
+		cgroup_writeback_umount();
 
 		evict_inodes(sb);
 
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 50311703135b..66cdb44616d5 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -287,6 +287,12 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 		goto out;
 
 	/*
+	 * We don't do userfault handling for the final child pid update.
+	 */
+	if (current->flags & PF_EXITING)
+		goto out;
+
+	/*
 	 * Check that we can return VM_FAULT_RETRY.
 	 *
 	 * NOTE: it should become possible to return VM_FAULT_RETRY
diff --git a/fs/xattr.c b/fs/xattr.c
index 07d0e47f6a7f..4861322e28e8 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -940,7 +940,7 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
 	bool trusted = capable(CAP_SYS_ADMIN);
 	struct simple_xattr *xattr;
 	ssize_t remaining_size = size;
-	int err;
+	int err = 0;
 
 #ifdef CONFIG_FS_POSIX_ACL
 	if (inode->i_acl) {
@@ -965,11 +965,11 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
 
 		err = xattr_list_one(&buffer, &remaining_size, xattr->name);
 		if (err)
-			return err;
+			break;
 	}
 	spin_unlock(&xattrs->lock);
 
-	return size - remaining_size;
+	return err ? err : size - remaining_size;
 }
 
 /*
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 379c089fb051..5c57b7b40728 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -55,7 +55,7 @@ xfs_count_page_state(
 	} while ((bh = bh->b_this_page) != head);
 }
 
-STATIC struct block_device *
+struct block_device *
 xfs_find_bdev_for_inode(
 	struct inode		*inode)
 {
@@ -1208,6 +1208,10 @@ xfs_vm_writepages(
 	struct writeback_control *wbc)
 {
 	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
+	if (dax_mapping(mapping))
+		return dax_writeback_mapping_range(mapping,
+				xfs_find_bdev_for_inode(mapping->host), wbc);
+
 	return generic_writepages(mapping, wbc);
 }
 
@@ -1953,7 +1957,6 @@ xfs_vm_set_page_dirty(
 	loff_t			end_offset;
 	loff_t			offset;
 	int			newly_dirty;
-	struct mem_cgroup	*memcg;
 
 	if (unlikely(!mapping))
 		return !TestSetPageDirty(page);
@@ -1974,10 +1977,10 @@ xfs_vm_set_page_dirty(
 		} while (bh != head);
 	}
 	/*
-	 * Use mem_group_begin_page_stat() to keep PageDirty synchronized with
-	 * per-memcg dirty page counters.
+	 * Lock out page->mem_cgroup migration to keep PageDirty
+	 * synchronized with per-memcg dirty page counters.
 	 */
-	memcg = mem_cgroup_begin_page_stat(page);
+	lock_page_memcg(page);
 	newly_dirty = !TestSetPageDirty(page);
 	spin_unlock(&mapping->private_lock);
 
@@ -1988,13 +1991,13 @@ xfs_vm_set_page_dirty(
 		spin_lock_irqsave(&mapping->tree_lock, flags);
 		if (page->mapping) {	/* Race with truncate? */
 			WARN_ON_ONCE(!PageUptodate(page));
-			account_page_dirtied(page, mapping, memcg);
+			account_page_dirtied(page, mapping);
 			radix_tree_tag_set(&mapping->page_tree,
 					page_index(page), PAGECACHE_TAG_DIRTY);
 		}
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
 	}
-	mem_cgroup_end_page_stat(memcg);
+	unlock_page_memcg(page);
 	if (newly_dirty)
 		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 	return newly_dirty;
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index f6ffc9ae5ceb..a4343c63fb38 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -62,5 +62,6 @@ int	xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset,
 			         struct buffer_head *map_bh, int create);
 
 extern void xfs_count_page_state(struct page *, int *, int *);
+extern struct block_device *xfs_find_bdev_for_inode(struct inode *);
 
 #endif /* __XFS_AOPS_H__ */
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 45ec9e40150c..6c876012b2e5 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -75,7 +75,8 @@ xfs_zero_extent(
 	ssize_t		size = XFS_FSB_TO_B(mp, count_fsb);
 
 	if (IS_DAX(VFS_I(ip)))
-		return dax_clear_blocks(VFS_I(ip), block, size);
+		return dax_clear_sectors(xfs_find_bdev_for_inode(VFS_I(ip)),
+				sector, size);
 
 	/*
 	 * let the block layer decide on the fastest method of
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index da37beb76f6e..be5568839442 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1109,27 +1109,10 @@ xlog_verify_head(
 	bool			tmp_wrapped;
 
 	/*
-	 * Search backwards through the log looking for the log record header
-	 * block. This wraps all the way back around to the head so something is
-	 * seriously wrong if we can't find it.
-	 */
-	found = xlog_rseek_logrec_hdr(log, *head_blk, *head_blk, 1, bp, rhead_blk,
-				      rhead, wrapped);
-	if (found < 0)
-		return found;
-	if (!found) {
-		xfs_warn(log->l_mp, "%s: couldn't find sync record", __func__);
-		return -EIO;
-	}
-
-	*tail_blk = BLOCK_LSN(be64_to_cpu((*rhead)->h_tail_lsn));
-
-	/*
-	 * Now that we have a tail block, check the head of the log for torn
-	 * writes. Search again until we hit the tail or the maximum number of
-	 * log record I/Os that could have been in flight at one time. Use a
-	 * temporary buffer so we don't trash the rhead/bp pointer from the
-	 * call above.
+	 * Check the head of the log for torn writes. Search backwards from the
+	 * head until we hit the tail or the maximum number of log record I/Os
+	 * that could have been in flight at one time. Use a temporary buffer so
+	 * we don't trash the rhead/bp pointers from the caller.
 	 */
 	tmp_bp = xlog_get_bp(log, 1);
 	if (!tmp_bp)
@@ -1216,6 +1199,115 @@ xlog_verify_head(
 }
 
 /*
+ * Check whether the head of the log points to an unmount record. In other
+ * words, determine whether the log is clean. If so, update the in-core state
+ * appropriately.
+ */
+static int
+xlog_check_unmount_rec(
+	struct xlog		*log,
+	xfs_daddr_t		*head_blk,
+	xfs_daddr_t		*tail_blk,
+	struct xlog_rec_header	*rhead,
+	xfs_daddr_t		rhead_blk,
+	struct xfs_buf		*bp,
+	bool			*clean)
+{
+	struct xlog_op_header	*op_head;
+	xfs_daddr_t		umount_data_blk;
+	xfs_daddr_t		after_umount_blk;
+	int			hblks;
+	int			error;
+	char			*offset;
+
+	*clean = false;
+
+	/*
+	 * Look for unmount record. If we find it, then we know there was a
+	 * clean unmount. Since 'i' could be the last block in the physical
+	 * log, we convert to a log block before comparing to the head_blk.
+	 *
+	 * Save the current tail lsn to use to pass to xlog_clear_stale_blocks()
+	 * below. We won't want to clear the unmount record if there is one, so
+	 * we pass the lsn of the unmount record rather than the block after it.
+	 */
+	if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) {
+		int	h_size = be32_to_cpu(rhead->h_size);
+		int	h_version = be32_to_cpu(rhead->h_version);
+
+		if ((h_version & XLOG_VERSION_2) &&
+		    (h_size > XLOG_HEADER_CYCLE_SIZE)) {
+			hblks = h_size / XLOG_HEADER_CYCLE_SIZE;
+			if (h_size % XLOG_HEADER_CYCLE_SIZE)
+				hblks++;
+		} else {
+			hblks = 1;
+		}
+	} else {
+		hblks = 1;
+	}
+	after_umount_blk = rhead_blk + hblks + BTOBB(be32_to_cpu(rhead->h_len));
+	after_umount_blk = do_mod(after_umount_blk, log->l_logBBsize);
+	if (*head_blk == after_umount_blk &&
+	    be32_to_cpu(rhead->h_num_logops) == 1) {
+		umount_data_blk = rhead_blk + hblks;
+		umount_data_blk = do_mod(umount_data_blk, log->l_logBBsize);
+		error = xlog_bread(log, umount_data_blk, 1, bp, &offset);
+		if (error)
+			return error;
+
+		op_head = (struct xlog_op_header *)offset;
+		if (op_head->oh_flags & XLOG_UNMOUNT_TRANS) {
+			/*
+			 * Set tail and last sync so that newly written log
+			 * records will point recovery to after the current
+			 * unmount record.
+			 */
+			xlog_assign_atomic_lsn(&log->l_tail_lsn,
+					log->l_curr_cycle, after_umount_blk);
+			xlog_assign_atomic_lsn(&log->l_last_sync_lsn,
+					log->l_curr_cycle, after_umount_blk);
+			*tail_blk = after_umount_blk;
+
+			*clean = true;
+		}
+	}
+
+	return 0;
+}
+
+static void
+xlog_set_state(
+	struct xlog		*log,
+	xfs_daddr_t		head_blk,
+	struct xlog_rec_header	*rhead,
+	xfs_daddr_t		rhead_blk,
+	bool			bump_cycle)
+{
+	/*
+	 * Reset log values according to the state of the log when we
+	 * crashed.  In the case where head_blk == 0, we bump curr_cycle
+	 * one because the next write starts a new cycle rather than
+	 * continuing the cycle of the last good log record.  At this
+	 * point we have guaranteed that all partial log records have been
+	 * accounted for.  Therefore, we know that the last good log record
+	 * written was complete and ended exactly on the end boundary
+	 * of the physical log.
+	 */
+	log->l_prev_block = rhead_blk;
+	log->l_curr_block = (int)head_blk;
+	log->l_curr_cycle = be32_to_cpu(rhead->h_cycle);
+	if (bump_cycle)
+		log->l_curr_cycle++;
+	atomic64_set(&log->l_tail_lsn, be64_to_cpu(rhead->h_tail_lsn));
+	atomic64_set(&log->l_last_sync_lsn, be64_to_cpu(rhead->h_lsn));
+	xlog_assign_grant_head(&log->l_reserve_head.grant, log->l_curr_cycle,
+					BBTOB(log->l_curr_block));
+	xlog_assign_grant_head(&log->l_write_head.grant, log->l_curr_cycle,
+					BBTOB(log->l_curr_block));
+}
+
+/*
  * Find the sync block number or the tail of the log.
  *
  * This will be the block number of the last record to have its
@@ -1238,22 +1330,20 @@ xlog_find_tail(
 	xfs_daddr_t		*tail_blk)
 {
 	xlog_rec_header_t	*rhead;
-	xlog_op_header_t	*op_head;
 	char			*offset = NULL;
 	xfs_buf_t		*bp;
 	int			error;
-	xfs_daddr_t		umount_data_blk;
-	xfs_daddr_t		after_umount_blk;
 	xfs_daddr_t		rhead_blk;
 	xfs_lsn_t		tail_lsn;
-	int			hblks;
 	bool			wrapped = false;
+	bool			clean = false;
 
 	/*
 	 * Find previous log record
 	 */
 	if ((error = xlog_find_head(log, head_blk)))
 		return error;
+	ASSERT(*head_blk < INT_MAX);
 
 	bp = xlog_get_bp(log, 1);
 	if (!bp)
@@ -1271,100 +1361,75 @@ xlog_find_tail(
 	}
 
 	/*
-	 * Trim the head block back to skip over torn records. We can have
-	 * multiple log I/Os in flight at any time, so we assume CRC failures
-	 * back through the previous several records are torn writes and skip
-	 * them.
+	 * Search backwards through the log looking for the log record header
+	 * block. This wraps all the way back around to the head so something is
+	 * seriously wrong if we can't find it.
 	 */
-	ASSERT(*head_blk < INT_MAX);
-	error = xlog_verify_head(log, head_blk, tail_blk, bp, &rhead_blk,
-				 &rhead, &wrapped);
-	if (error)
-		goto done;
+	error = xlog_rseek_logrec_hdr(log, *head_blk, *head_blk, 1, bp,
+				      &rhead_blk, &rhead, &wrapped);
+	if (error < 0)
+		return error;
+	if (!error) {
+		xfs_warn(log->l_mp, "%s: couldn't find sync record", __func__);
+		return -EIO;
+	}
+	*tail_blk = BLOCK_LSN(be64_to_cpu(rhead->h_tail_lsn));
 
 	/*
-	 * Reset log values according to the state of the log when we
-	 * crashed.  In the case where head_blk == 0, we bump curr_cycle
-	 * one because the next write starts a new cycle rather than
-	 * continuing the cycle of the last good log record.  At this
-	 * point we have guaranteed that all partial log records have been
-	 * accounted for.  Therefore, we know that the last good log record
-	 * written was complete and ended exactly on the end boundary
-	 * of the physical log.
+	 * Set the log state based on the current head record.
 	 */
-	log->l_prev_block = rhead_blk;
-	log->l_curr_block = (int)*head_blk;
-	log->l_curr_cycle = be32_to_cpu(rhead->h_cycle);
-	if (wrapped)
-		log->l_curr_cycle++;
-	atomic64_set(&log->l_tail_lsn, be64_to_cpu(rhead->h_tail_lsn));
-	atomic64_set(&log->l_last_sync_lsn, be64_to_cpu(rhead->h_lsn));
-	xlog_assign_grant_head(&log->l_reserve_head.grant, log->l_curr_cycle,
-					BBTOB(log->l_curr_block));
-	xlog_assign_grant_head(&log->l_write_head.grant, log->l_curr_cycle,
-					BBTOB(log->l_curr_block));
+	xlog_set_state(log, *head_blk, rhead, rhead_blk, wrapped);
+	tail_lsn = atomic64_read(&log->l_tail_lsn);
 
 	/*
-	 * Look for unmount record.  If we find it, then we know there
-	 * was a clean unmount.  Since 'i' could be the last block in
-	 * the physical log, we convert to a log block before comparing
-	 * to the head_blk.
+	 * Look for an unmount record at the head of the log. This sets the log
+	 * state to determine whether recovery is necessary.
+	 */
+	error = xlog_check_unmount_rec(log, head_blk, tail_blk, rhead,
+				       rhead_blk, bp, &clean);
+	if (error)
+		goto done;
+
+	/*
+	 * Verify the log head if the log is not clean (e.g., we have anything
+	 * but an unmount record at the head). This uses CRC verification to
+	 * detect and trim torn writes. If discovered, CRC failures are
+	 * considered torn writes and the log head is trimmed accordingly.
 	 *
-	 * Save the current tail lsn to use to pass to
-	 * xlog_clear_stale_blocks() below.  We won't want to clear the
-	 * unmount record if there is one, so we pass the lsn of the
-	 * unmount record rather than the block after it.
+	 * Note that we can only run CRC verification when the log is dirty
+	 * because there's no guarantee that the log data behind an unmount
+	 * record is compatible with the current architecture.
 	 */
-	if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) {
-		int	h_size = be32_to_cpu(rhead->h_size);
-		int	h_version = be32_to_cpu(rhead->h_version);
+	if (!clean) {
+		xfs_daddr_t	orig_head = *head_blk;
 
-		if ((h_version & XLOG_VERSION_2) &&
-		    (h_size > XLOG_HEADER_CYCLE_SIZE)) {
-			hblks = h_size / XLOG_HEADER_CYCLE_SIZE;
-			if (h_size % XLOG_HEADER_CYCLE_SIZE)
-				hblks++;
-		} else {
-			hblks = 1;
-		}
-	} else {
-		hblks = 1;
-	}
-	after_umount_blk = rhead_blk + hblks + BTOBB(be32_to_cpu(rhead->h_len));
-	after_umount_blk = do_mod(after_umount_blk, log->l_logBBsize);
-	tail_lsn = atomic64_read(&log->l_tail_lsn);
-	if (*head_blk == after_umount_blk &&
-	    be32_to_cpu(rhead->h_num_logops) == 1) {
-		umount_data_blk = rhead_blk + hblks;
-		umount_data_blk = do_mod(umount_data_blk, log->l_logBBsize);
-		error = xlog_bread(log, umount_data_blk, 1, bp, &offset);
+		error = xlog_verify_head(log, head_blk, tail_blk, bp,
+					 &rhead_blk, &rhead, &wrapped);
 		if (error)
 			goto done;
 
-		op_head = (xlog_op_header_t *)offset;
-		if (op_head->oh_flags & XLOG_UNMOUNT_TRANS) {
-			/*
-			 * Set tail and last sync so that newly written
-			 * log records will point recovery to after the
-			 * current unmount record.
-			 */
-			xlog_assign_atomic_lsn(&log->l_tail_lsn,
-					log->l_curr_cycle, after_umount_blk);
-			xlog_assign_atomic_lsn(&log->l_last_sync_lsn,
-					log->l_curr_cycle, after_umount_blk);
-			*tail_blk = after_umount_blk;
-
-			/*
-			 * Note that the unmount was clean. If the unmount
-			 * was not clean, we need to know this to rebuild the
-			 * superblock counters from the perag headers if we
-			 * have a filesystem using non-persistent counters.
-			 */
-			log->l_mp->m_flags |= XFS_MOUNT_WAS_CLEAN;
+		/* update in-core state again if the head changed */
+		if (*head_blk != orig_head) {
+			xlog_set_state(log, *head_blk, rhead, rhead_blk,
+				       wrapped);
+			tail_lsn = atomic64_read(&log->l_tail_lsn);
+			error = xlog_check_unmount_rec(log, head_blk, tail_blk,
+						       rhead, rhead_blk, bp,
+						       &clean);
+			if (error)
+				goto done;
 		}
 	}
 
 	/*
+	 * Note that the unmount was clean. If the unmount was not clean, we
+	 * need to know this to rebuild the superblock counters from the perag
+	 * headers if we have a filesystem using non-persistent counters.
+	 */
+	if (clean)
+		log->l_mp->m_flags |= XFS_MOUNT_WAS_CLEAN;
+
+	/*
 	 * Make sure that there are no blocks in front of the head
 	 * with the same cycle number as the head.  This can happen
 	 * because we allow multiple outstanding log writes concurrently,
@@ -4491,7 +4556,7 @@ xlog_recover_process(
 	 * know precisely what failed.
 	 */
 	if (pass == XLOG_RECOVER_CRCPASS) {
-		if (rhead->h_crc && crc != le32_to_cpu(rhead->h_crc))
+		if (rhead->h_crc && crc != rhead->h_crc)
 			return -EFSBADCRC;
 		return 0;
 	}
@@ -4502,7 +4567,7 @@ xlog_recover_process(
 	 * zero CRC check prevents warnings from being emitted when upgrading
 	 * the kernel from one that does not add CRCs by default.
 	 */
-	if (crc != le32_to_cpu(rhead->h_crc)) {
+	if (crc != rhead->h_crc) {
 		if (rhead->h_crc || xfs_sb_version_hascrc(&log->l_mp->m_sb)) {
 			xfs_alert(log->l_mp,
 		"log record CRC mismatch: found 0x%x, expected 0x%x.",
diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h
index 5bfc61943f88..34f601e7b88d 100644
--- a/include/acpi/acoutput.h
+++ b/include/acpi/acoutput.h
@@ -262,7 +262,7 @@
 #define ACPI_GET_FUNCTION_NAME          _acpi_function_name
 
 /*
- * The Name parameter should be the procedure name as a quoted string.
+ * The Name parameter should be the procedure name as a non-quoted string.
  * The function name is also used by the function exit macros below.
  * Note: (const char) is used to be compatible with the debug interfaces
  * and macros such as __func__.
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index c96621e87c19..17556979dc79 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -897,11 +897,9 @@ ACPI_MSG_DEPENDENT_RETURN_VOID(ACPI_PRINTF_LIKE(3)
 				acpi_warning(const char *module_name,
 					     u32 line_number,
 					     const char *format, ...))
-ACPI_MSG_DEPENDENT_RETURN_VOID(ACPI_PRINTF_LIKE(3)
+ACPI_MSG_DEPENDENT_RETURN_VOID(ACPI_PRINTF_LIKE(1)
 				void ACPI_INTERNAL_VAR_XFACE
-				acpi_info(const char *module_name,
-					  u32 line_number,
-					  const char *format, ...))
+				acpi_info(const char *format, ...))
 ACPI_MSG_DEPENDENT_RETURN_VOID(ACPI_PRINTF_LIKE(3)
 				void ACPI_INTERNAL_VAR_XFACE
 				acpi_bios_error(const char *module_name,
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index 07fb100bcc68..6f1805dd5d3c 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -9,6 +9,7 @@
 #define ACPI_PROCESSOR_CLASS		"processor"
 #define ACPI_PROCESSOR_DEVICE_NAME	"Processor"
 #define ACPI_PROCESSOR_DEVICE_HID	"ACPI0007"
+#define ACPI_PROCESSOR_CONTAINER_HID	"ACPI0010"
 
 #define ACPI_PROCESSOR_BUSY_METRIC	10
 
@@ -394,14 +395,6 @@ static inline int acpi_processor_hotplug(struct acpi_processor *pr)
 }
 #endif /* CONFIG_ACPI_PROCESSOR_IDLE */
 
-#if defined(CONFIG_PM_SLEEP) & defined(CONFIG_ACPI_PROCESSOR_IDLE)
-void acpi_processor_syscore_init(void);
-void acpi_processor_syscore_exit(void);
-#else
-static inline void acpi_processor_syscore_init(void) {}
-static inline void acpi_processor_syscore_exit(void) {}
-#endif
-
 /* in processor_thermal.c */
 int acpi_processor_get_limit_info(struct acpi_processor *pr);
 extern const struct thermal_cooling_device_ops processor_cooling_ops;
diff --git a/include/asm-generic/cputime_nsecs.h b/include/asm-generic/cputime_nsecs.h
index 0419485891f2..0f1c6f315cdc 100644
--- a/include/asm-generic/cputime_nsecs.h
+++ b/include/asm-generic/cputime_nsecs.h
@@ -75,7 +75,7 @@ typedef u64 __nocast cputime64_t;
  */
 static inline cputime_t timespec_to_cputime(const struct timespec *val)
 {
-	u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_nsec;
+	u64 ret = (u64)val->tv_sec * NSEC_PER_SEC + val->tv_nsec;
 	return (__force cputime_t) ret;
 }
 static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val)
@@ -91,7 +91,8 @@ static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val)
  */
 static inline cputime_t timeval_to_cputime(const struct timeval *val)
 {
-	u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_usec * NSEC_PER_USEC;
+	u64 ret = (u64)val->tv_sec * NSEC_PER_SEC +
+			val->tv_usec * NSEC_PER_USEC;
 	return (__force cputime_t) ret;
 }
 static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val)
diff --git a/include/asm-generic/pci-bridge.h b/include/asm-generic/pci-bridge.h
deleted file mode 100644
index 20db2e5a0a69..000000000000
--- a/include/asm-generic/pci-bridge.h
+++ /dev/null
@@ -1,74 +0,0 @@
-/*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-#ifndef _ASM_GENERIC_PCI_BRIDGE_H
-#define _ASM_GENERIC_PCI_BRIDGE_H
-
-#ifdef __KERNEL__
-
-enum {
-	/* Force re-assigning all resources (ignore firmware
-	 * setup completely)
-	 */
-	PCI_REASSIGN_ALL_RSRC	= 0x00000001,
-
-	/* Re-assign all bus numbers */
-	PCI_REASSIGN_ALL_BUS	= 0x00000002,
-
-	/* Do not try to assign, just use existing setup */
-	PCI_PROBE_ONLY		= 0x00000004,
-
-	/* Don't bother with ISA alignment unless the bridge has
-	 * ISA forwarding enabled
-	 */
-	PCI_CAN_SKIP_ISA_ALIGN	= 0x00000008,
-
-	/* Enable domain numbers in /proc */
-	PCI_ENABLE_PROC_DOMAINS	= 0x00000010,
-	/* ... except for domain 0 */
-	PCI_COMPAT_DOMAIN_0	= 0x00000020,
-
-	/* PCIe downstream ports are bridges that normally lead to only a
-	 * device 0, but if this is set, we scan all possible devices, not
-	 * just device 0.
-	 */
-	PCI_SCAN_ALL_PCIE_DEVS	= 0x00000040,
-};
-
-#ifdef CONFIG_PCI
-extern unsigned int pci_flags;
-
-static inline void pci_set_flags(int flags)
-{
-	pci_flags = flags;
-}
-
-static inline void pci_add_flags(int flags)
-{
-	pci_flags |= flags;
-}
-
-static inline void pci_clear_flags(int flags)
-{
-	pci_flags &= ~flags;
-}
-
-static inline int pci_has_flag(int flag)
-{
-	return pci_flags & flag;
-}
-#else
-static inline void pci_set_flags(int flags) { }
-static inline void pci_add_flags(int flags) { }
-static inline void pci_clear_flags(int flags) { }
-static inline int pci_has_flag(int flag)
-{
-	return 0;
-}
-#endif	/* CONFIG_PCI */
-
-#endif	/* __KERNEL__ */
-#endif	/* _ASM_GENERIC_PCI_BRIDGE_H */
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 0b3c0d39ef75..c370b261c720 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -239,6 +239,14 @@ extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 			    pmd_t *pmdp);
 #endif
 
+#ifndef __HAVE_ARCH_PMDP_HUGE_SPLIT_PREPARE
+static inline void pmdp_huge_split_prepare(struct vm_area_struct *vma,
+					   unsigned long address, pmd_t *pmdp)
+{
+
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTE_SAME
 static inline int pte_same(pte_t pte_a, pte_t pte_b)
 {
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 39e1cb201b8e..35a52a880b2f 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -120,11 +120,6 @@ static __always_inline bool virt_spin_lock(struct qspinlock *lock)
 #endif
 
 /*
- * Initializier
- */
-#define	__ARCH_SPIN_LOCK_UNLOCKED	{ ATOMIC_INIT(0) }
-
-/*
  * Remapping spinlock architecture specific functions to the corresponding
  * queued spinlock functions.
  */
diff --git a/include/asm-generic/qspinlock_types.h b/include/asm-generic/qspinlock_types.h
index 85f888e86761..034acd0c4956 100644
--- a/include/asm-generic/qspinlock_types.h
+++ b/include/asm-generic/qspinlock_types.h
@@ -33,6 +33,11 @@ typedef struct qspinlock {
 } arch_spinlock_t;
 
 /*
+ * Initializier
+ */
+#define	__ARCH_SPIN_LOCK_UNLOCKED	{ ATOMIC_INIT(0) }
+
+/*
  * Bitfields in the atomic value:
  *
  * When NR_CPUS < 16K
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index c4bd0e2c173c..772c784ba763 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -256,6 +256,7 @@
 	.rodata           : AT(ADDR(.rodata) - LOAD_OFFSET) {		\
 		VMLINUX_SYMBOL(__start_rodata) = .;			\
 		*(.rodata) *(.rodata.*)					\
+		*(.data..ro_after_init)	/* Read only after init */	\
 		*(__vermagic)		/* Kernel version magic */	\
 		. = ALIGN(8);						\
 		VMLINUX_SYMBOL(__start___tracepoints_ptrs) = .;		\
diff --git a/include/crypto/aead.h b/include/crypto/aead.h
index 84d13b11ad7b..957bb8763219 100644
--- a/include/crypto/aead.h
+++ b/include/crypto/aead.h
@@ -31,10 +31,10 @@
  *
  * For example: authenc(hmac(sha256), cbc(aes))
  *
- * The example code provided for the asynchronous block cipher operation
- * applies here as well. Naturally all *ablkcipher* symbols must be exchanged
+ * The example code provided for the symmetric key cipher operation
+ * applies here as well. Naturally all *skcipher* symbols must be exchanged
  * the *aead* pendants discussed in the following. In addition, for the AEAD
- * operation, the aead_request_set_assoc function must be used to set the
+ * operation, the aead_request_set_ad function must be used to set the
  * pointer to the associated data memory location before performing the
  * encryption or decryption operation. In case of an encryption, the associated
  * data memory is filled during the encryption operation. For decryption, the
diff --git a/include/crypto/akcipher.h b/include/crypto/akcipher.h
index 354de15cea6b..c37cc59e9bf2 100644
--- a/include/crypto/akcipher.h
+++ b/include/crypto/akcipher.h
@@ -114,7 +114,7 @@ struct akcipher_alg {
  */
 
 /**
- * crypto_alloc_akcipher() -- allocate AKCIPHER tfm handle
+ * crypto_alloc_akcipher() - allocate AKCIPHER tfm handle
  * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
  *	      public key algorithm e.g. "rsa"
  * @type: specifies the type of the algorithm
@@ -171,7 +171,7 @@ static inline struct crypto_akcipher *crypto_akcipher_reqtfm(
 }
 
 /**
- * crypto_free_akcipher() -- free AKCIPHER tfm handle
+ * crypto_free_akcipher() - free AKCIPHER tfm handle
  *
  * @tfm: AKCIPHER tfm handle allocated with crypto_alloc_akcipher()
  */
@@ -181,7 +181,7 @@ static inline void crypto_free_akcipher(struct crypto_akcipher *tfm)
 }
 
 /**
- * akcipher_request_alloc() -- allocates public key request
+ * akcipher_request_alloc() - allocates public key request
  *
  * @tfm:	AKCIPHER tfm handle allocated with crypto_alloc_akcipher()
  * @gfp:	allocation flags
@@ -201,7 +201,7 @@ static inline struct akcipher_request *akcipher_request_alloc(
 }
 
 /**
- * akcipher_request_free() -- zeroize and free public key request
+ * akcipher_request_free() - zeroize and free public key request
  *
  * @req:	request to free
  */
@@ -211,14 +211,14 @@ static inline void akcipher_request_free(struct akcipher_request *req)
 }
 
 /**
- * akcipher_request_set_callback() -- Sets an asynchronous callback.
+ * akcipher_request_set_callback() - Sets an asynchronous callback.
  *
  * Callback will be called when an asynchronous operation on a given
  * request is finished.
  *
  * @req:	request that the callback will be set for
  * @flgs:	specify for instance if the operation may backlog
- * @cmlp:	callback which will be called
+ * @cmpl:	callback which will be called
  * @data:	private data used by the caller
  */
 static inline void akcipher_request_set_callback(struct akcipher_request *req,
@@ -232,7 +232,7 @@ static inline void akcipher_request_set_callback(struct akcipher_request *req,
 }
 
 /**
- * akcipher_request_set_crypt() -- Sets request parameters
+ * akcipher_request_set_crypt() - Sets request parameters
  *
  * Sets parameters required by crypto operation
  *
@@ -255,7 +255,7 @@ static inline void akcipher_request_set_crypt(struct akcipher_request *req,
 }
 
 /**
- * crypto_akcipher_maxsize() -- Get len for output buffer
+ * crypto_akcipher_maxsize() - Get len for output buffer
  *
  * Function returns the dest buffer size required for a given key
  *
@@ -271,7 +271,7 @@ static inline int crypto_akcipher_maxsize(struct crypto_akcipher *tfm)
 }
 
 /**
- * crypto_akcipher_encrypt() -- Invoke public key encrypt operation
+ * crypto_akcipher_encrypt() - Invoke public key encrypt operation
  *
  * Function invokes the specific public key encrypt operation for a given
  * public key algorithm
@@ -289,7 +289,7 @@ static inline int crypto_akcipher_encrypt(struct akcipher_request *req)
 }
 
 /**
- * crypto_akcipher_decrypt() -- Invoke public key decrypt operation
+ * crypto_akcipher_decrypt() - Invoke public key decrypt operation
  *
  * Function invokes the specific public key decrypt operation for a given
  * public key algorithm
@@ -307,7 +307,7 @@ static inline int crypto_akcipher_decrypt(struct akcipher_request *req)
 }
 
 /**
- * crypto_akcipher_sign() -- Invoke public key sign operation
+ * crypto_akcipher_sign() - Invoke public key sign operation
  *
  * Function invokes the specific public key sign operation for a given
  * public key algorithm
@@ -325,7 +325,7 @@ static inline int crypto_akcipher_sign(struct akcipher_request *req)
 }
 
 /**
- * crypto_akcipher_verify() -- Invoke public key verify operation
+ * crypto_akcipher_verify() - Invoke public key verify operation
  *
  * Function invokes the specific public key verify operation for a given
  * public key algorithm
@@ -343,7 +343,7 @@ static inline int crypto_akcipher_verify(struct akcipher_request *req)
 }
 
 /**
- * crypto_akcipher_set_pub_key() -- Invoke set public key operation
+ * crypto_akcipher_set_pub_key() - Invoke set public key operation
  *
  * Function invokes the algorithm specific set key function, which knows
  * how to decode and interpret the encoded key
@@ -364,7 +364,7 @@ static inline int crypto_akcipher_set_pub_key(struct crypto_akcipher *tfm,
 }
 
 /**
- * crypto_akcipher_set_priv_key() -- Invoke set private key operation
+ * crypto_akcipher_set_priv_key() - Invoke set private key operation
  *
  * Function invokes the algorithm specific set key function, which knows
  * how to decode and interpret the encoded key
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index c9fe145f7dd3..eeafd21afb44 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -15,6 +15,7 @@
 #include <linux/crypto.h>
 #include <linux/list.h>
 #include <linux/kernel.h>
+#include <linux/kthread.h>
 #include <linux/skbuff.h>
 
 struct crypto_aead;
@@ -128,6 +129,75 @@ struct ablkcipher_walk {
 	unsigned int		blocksize;
 };
 
+#define ENGINE_NAME_LEN	30
+/*
+ * struct crypto_engine - crypto hardware engine
+ * @name: the engine name
+ * @idling: the engine is entering idle state
+ * @busy: request pump is busy
+ * @running: the engine is on working
+ * @cur_req_prepared: current request is prepared
+ * @list: link with the global crypto engine list
+ * @queue_lock: spinlock to syncronise access to request queue
+ * @queue: the crypto queue of the engine
+ * @rt: whether this queue is set to run as a realtime task
+ * @prepare_crypt_hardware: a request will soon arrive from the queue
+ * so the subsystem requests the driver to prepare the hardware
+ * by issuing this call
+ * @unprepare_crypt_hardware: there are currently no more requests on the
+ * queue so the subsystem notifies the driver that it may relax the
+ * hardware by issuing this call
+ * @prepare_request: do some prepare if need before handle the current request
+ * @unprepare_request: undo any work done by prepare_message()
+ * @crypt_one_request: do encryption for current request
+ * @kworker: thread struct for request pump
+ * @kworker_task: pointer to task for request pump kworker thread
+ * @pump_requests: work struct for scheduling work to the request pump
+ * @priv_data: the engine private data
+ * @cur_req: the current request which is on processing
+ */
+struct crypto_engine {
+	char			name[ENGINE_NAME_LEN];
+	bool			idling;
+	bool			busy;
+	bool			running;
+	bool			cur_req_prepared;
+
+	struct list_head	list;
+	spinlock_t		queue_lock;
+	struct crypto_queue	queue;
+
+	bool			rt;
+
+	int (*prepare_crypt_hardware)(struct crypto_engine *engine);
+	int (*unprepare_crypt_hardware)(struct crypto_engine *engine);
+
+	int (*prepare_request)(struct crypto_engine *engine,
+			       struct ablkcipher_request *req);
+	int (*unprepare_request)(struct crypto_engine *engine,
+				 struct ablkcipher_request *req);
+	int (*crypt_one_request)(struct crypto_engine *engine,
+				 struct ablkcipher_request *req);
+
+	struct kthread_worker           kworker;
+	struct task_struct              *kworker_task;
+	struct kthread_work             pump_requests;
+
+	void				*priv_data;
+	struct ablkcipher_request	*cur_req;
+};
+
+int crypto_transfer_request(struct crypto_engine *engine,
+			    struct ablkcipher_request *req, bool need_pump);
+int crypto_transfer_request_to_engine(struct crypto_engine *engine,
+				      struct ablkcipher_request *req);
+void crypto_finalize_request(struct crypto_engine *engine,
+			     struct ablkcipher_request *req, int err);
+int crypto_engine_start(struct crypto_engine *engine);
+int crypto_engine_stop(struct crypto_engine *engine);
+struct crypto_engine *crypto_engine_alloc_init(struct device *dev, bool rt);
+int crypto_engine_exit(struct crypto_engine *engine);
+
 extern const struct crypto_type crypto_ablkcipher_type;
 extern const struct crypto_type crypto_blkcipher_type;
 
@@ -184,6 +254,10 @@ int crypto_enqueue_request(struct crypto_queue *queue,
 			   struct crypto_async_request *request);
 struct crypto_async_request *crypto_dequeue_request(struct crypto_queue *queue);
 int crypto_tfm_in_queue(struct crypto_queue *queue, struct crypto_tfm *tfm);
+static inline unsigned int crypto_queue_len(struct crypto_queue *queue)
+{
+	return queue->qlen;
+}
 
 /* These functions require the input/output to be aligned as u32. */
 void crypto_inc(u8 *a, unsigned int size);
@@ -275,24 +349,6 @@ static inline struct cipher_alg *crypto_cipher_alg(struct crypto_cipher *tfm)
 	return &crypto_cipher_tfm(tfm)->__crt_alg->cra_cipher;
 }
 
-static inline struct crypto_hash *crypto_spawn_hash(struct crypto_spawn *spawn)
-{
-	u32 type = CRYPTO_ALG_TYPE_HASH;
-	u32 mask = CRYPTO_ALG_TYPE_HASH_MASK;
-
-	return __crypto_hash_cast(crypto_spawn_tfm(spawn, type, mask));
-}
-
-static inline void *crypto_hash_ctx(struct crypto_hash *tfm)
-{
-	return crypto_tfm_ctx(&tfm->base);
-}
-
-static inline void *crypto_hash_ctx_aligned(struct crypto_hash *tfm)
-{
-	return crypto_tfm_ctx_aligned(&tfm->base);
-}
-
 static inline void blkcipher_walk_init(struct blkcipher_walk *walk,
 				       struct scatterlist *dst,
 				       struct scatterlist *src,
diff --git a/include/crypto/compress.h b/include/crypto/compress.h
deleted file mode 100644
index 5b67af834d83..000000000000
--- a/include/crypto/compress.h
+++ /dev/null
@@ -1,145 +0,0 @@
-/*
- * Compress: Compression algorithms under the cryptographic API.
- *
- * Copyright 2008 Sony Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.
- * If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef _CRYPTO_COMPRESS_H
-#define _CRYPTO_COMPRESS_H
-
-#include <linux/crypto.h>
-
-
-struct comp_request {
-	const void *next_in;		/* next input byte */
-	void *next_out;			/* next output byte */
-	unsigned int avail_in;		/* bytes available at next_in */
-	unsigned int avail_out;		/* bytes available at next_out */
-};
-
-enum zlib_comp_params {
-	ZLIB_COMP_LEVEL = 1,		/* e.g. Z_DEFAULT_COMPRESSION */
-	ZLIB_COMP_METHOD,		/* e.g. Z_DEFLATED */
-	ZLIB_COMP_WINDOWBITS,		/* e.g. MAX_WBITS */
-	ZLIB_COMP_MEMLEVEL,		/* e.g. DEF_MEM_LEVEL */
-	ZLIB_COMP_STRATEGY,		/* e.g. Z_DEFAULT_STRATEGY */
-	__ZLIB_COMP_MAX,
-};
-
-#define ZLIB_COMP_MAX	(__ZLIB_COMP_MAX - 1)
-
-
-enum zlib_decomp_params {
-	ZLIB_DECOMP_WINDOWBITS = 1,	/* e.g. DEF_WBITS */
-	__ZLIB_DECOMP_MAX,
-};
-
-#define ZLIB_DECOMP_MAX	(__ZLIB_DECOMP_MAX - 1)
-
-
-struct crypto_pcomp {
-	struct crypto_tfm base;
-};
-
-struct pcomp_alg {
-	int (*compress_setup)(struct crypto_pcomp *tfm, const void *params,
-			      unsigned int len);
-	int (*compress_init)(struct crypto_pcomp *tfm);
-	int (*compress_update)(struct crypto_pcomp *tfm,
-			       struct comp_request *req);
-	int (*compress_final)(struct crypto_pcomp *tfm,
-			      struct comp_request *req);
-	int (*decompress_setup)(struct crypto_pcomp *tfm, const void *params,
-				unsigned int len);
-	int (*decompress_init)(struct crypto_pcomp *tfm);
-	int (*decompress_update)(struct crypto_pcomp *tfm,
-				 struct comp_request *req);
-	int (*decompress_final)(struct crypto_pcomp *tfm,
-				struct comp_request *req);
-
-	struct crypto_alg base;
-};
-
-extern struct crypto_pcomp *crypto_alloc_pcomp(const char *alg_name, u32 type,
-					       u32 mask);
-
-static inline struct crypto_tfm *crypto_pcomp_tfm(struct crypto_pcomp *tfm)
-{
-	return &tfm->base;
-}
-
-static inline void crypto_free_pcomp(struct crypto_pcomp *tfm)
-{
-	crypto_destroy_tfm(tfm, crypto_pcomp_tfm(tfm));
-}
-
-static inline struct pcomp_alg *__crypto_pcomp_alg(struct crypto_alg *alg)
-{
-	return container_of(alg, struct pcomp_alg, base);
-}
-
-static inline struct pcomp_alg *crypto_pcomp_alg(struct crypto_pcomp *tfm)
-{
-	return __crypto_pcomp_alg(crypto_pcomp_tfm(tfm)->__crt_alg);
-}
-
-static inline int crypto_compress_setup(struct crypto_pcomp *tfm,
-					const void *params, unsigned int len)
-{
-	return crypto_pcomp_alg(tfm)->compress_setup(tfm, params, len);
-}
-
-static inline int crypto_compress_init(struct crypto_pcomp *tfm)
-{
-	return crypto_pcomp_alg(tfm)->compress_init(tfm);
-}
-
-static inline int crypto_compress_update(struct crypto_pcomp *tfm,
-					 struct comp_request *req)
-{
-	return crypto_pcomp_alg(tfm)->compress_update(tfm, req);
-}
-
-static inline int crypto_compress_final(struct crypto_pcomp *tfm,
-					struct comp_request *req)
-{
-	return crypto_pcomp_alg(tfm)->compress_final(tfm, req);
-}
-
-static inline int crypto_decompress_setup(struct crypto_pcomp *tfm,
-					  const void *params, unsigned int len)
-{
-	return crypto_pcomp_alg(tfm)->decompress_setup(tfm, params, len);
-}
-
-static inline int crypto_decompress_init(struct crypto_pcomp *tfm)
-{
-	return crypto_pcomp_alg(tfm)->decompress_init(tfm);
-}
-
-static inline int crypto_decompress_update(struct crypto_pcomp *tfm,
-					   struct comp_request *req)
-{
-	return crypto_pcomp_alg(tfm)->decompress_update(tfm, req);
-}
-
-static inline int crypto_decompress_final(struct crypto_pcomp *tfm,
-					  struct comp_request *req)
-{
-	return crypto_pcomp_alg(tfm)->decompress_final(tfm, req);
-}
-
-#endif	/* _CRYPTO_COMPRESS_H */
diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h
index 9756c70899d8..d961b2b16f55 100644
--- a/include/crypto/drbg.h
+++ b/include/crypto/drbg.h
@@ -117,10 +117,6 @@ struct drbg_state {
 	void *priv_data;	/* Cipher handle */
 	bool seeded;		/* DRBG fully seeded? */
 	bool pr;		/* Prediction resistance enabled? */
-#ifdef CONFIG_CRYPTO_FIPS
-	bool fips_primed;	/* Continuous test primed? */
-	unsigned char *prev;	/* FIPS 140-2 continuous test value */
-#endif
 	struct work_struct seed_work;	/* asynchronous seeding support */
 	struct crypto_rng *jent;
 	const struct drbg_state_ops *d_ops;
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index 6361892ea737..1969f1416658 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -14,6 +14,7 @@
 #define _CRYPTO_HASH_H
 
 #include <linux/crypto.h>
+#include <linux/string.h>
 
 struct crypto_ahash;
 
@@ -259,6 +260,28 @@ static inline void crypto_free_ahash(struct crypto_ahash *tfm)
 	crypto_destroy_tfm(tfm, crypto_ahash_tfm(tfm));
 }
 
+/**
+ * crypto_has_ahash() - Search for the availability of an ahash.
+ * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
+ *	      ahash
+ * @type: specifies the type of the ahash
+ * @mask: specifies the mask for the ahash
+ *
+ * Return: true when the ahash is known to the kernel crypto API; false
+ *	   otherwise
+ */
+int crypto_has_ahash(const char *alg_name, u32 type, u32 mask);
+
+static inline const char *crypto_ahash_alg_name(struct crypto_ahash *tfm)
+{
+	return crypto_tfm_alg_name(crypto_ahash_tfm(tfm));
+}
+
+static inline const char *crypto_ahash_driver_name(struct crypto_ahash *tfm)
+{
+	return crypto_tfm_alg_driver_name(crypto_ahash_tfm(tfm));
+}
+
 static inline unsigned int crypto_ahash_alignmask(
 	struct crypto_ahash *tfm)
 {
@@ -550,6 +573,12 @@ static inline void ahash_request_free(struct ahash_request *req)
 	kzfree(req);
 }
 
+static inline void ahash_request_zero(struct ahash_request *req)
+{
+	memzero_explicit(req, sizeof(*req) +
+			      crypto_ahash_reqsize(crypto_ahash_reqtfm(req)));
+}
+
 static inline struct ahash_request *ahash_request_cast(
 	struct crypto_async_request *req)
 {
@@ -657,6 +686,16 @@ static inline void crypto_free_shash(struct crypto_shash *tfm)
 	crypto_destroy_tfm(tfm, crypto_shash_tfm(tfm));
 }
 
+static inline const char *crypto_shash_alg_name(struct crypto_shash *tfm)
+{
+	return crypto_tfm_alg_name(crypto_shash_tfm(tfm));
+}
+
+static inline const char *crypto_shash_driver_name(struct crypto_shash *tfm)
+{
+	return crypto_tfm_alg_driver_name(crypto_shash_tfm(tfm));
+}
+
 static inline unsigned int crypto_shash_alignmask(
 	struct crypto_shash *tfm)
 {
@@ -872,4 +911,10 @@ int crypto_shash_final(struct shash_desc *desc, u8 *out);
 int crypto_shash_finup(struct shash_desc *desc, const u8 *data,
 		       unsigned int len, u8 *out);
 
+static inline void shash_desc_zero(struct shash_desc *desc)
+{
+	memzero_explicit(desc,
+			 sizeof(*desc) + crypto_shash_descsize(desc->tfm));
+}
+
 #endif	/* _CRYPTO_HASH_H */
diff --git a/include/crypto/internal/aead.h b/include/crypto/internal/aead.h
index 5554cdd8d6c1..da3864991d4c 100644
--- a/include/crypto/internal/aead.h
+++ b/include/crypto/internal/aead.h
@@ -80,6 +80,12 @@ static inline u32 aead_request_flags(struct aead_request *req)
 	return req->base.flags;
 }
 
+static inline struct aead_request *aead_request_cast(
+	struct crypto_async_request *req)
+{
+	return container_of(req, struct aead_request, base);
+}
+
 static inline void crypto_set_aead_spawn(
 	struct crypto_aead_spawn *spawn, struct crypto_instance *inst)
 {
diff --git a/include/crypto/internal/compress.h b/include/crypto/internal/compress.h
deleted file mode 100644
index 178a888d1d93..000000000000
--- a/include/crypto/internal/compress.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * Compress: Compression algorithms under the cryptographic API.
- *
- * Copyright 2008 Sony Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.
- * If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef _CRYPTO_INTERNAL_COMPRESS_H
-#define _CRYPTO_INTERNAL_COMPRESS_H
-
-#include <crypto/compress.h>
-
-extern int crypto_register_pcomp(struct pcomp_alg *alg);
-extern int crypto_unregister_pcomp(struct pcomp_alg *alg);
-
-#endif	/* _CRYPTO_INTERNAL_COMPRESS_H */
diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h
index 3b4af1d7c7e9..49dae16f8929 100644
--- a/include/crypto/internal/hash.h
+++ b/include/crypto/internal/hash.h
@@ -57,9 +57,6 @@ int crypto_hash_walk_first(struct ahash_request *req,
 			   struct crypto_hash_walk *walk);
 int crypto_ahash_walk_first(struct ahash_request *req,
 			   struct crypto_hash_walk *walk);
-int crypto_hash_walk_first_compat(struct hash_desc *hdesc,
-				  struct crypto_hash_walk *walk,
-				  struct scatterlist *sg, unsigned int len);
 
 static inline int crypto_ahash_walk_done(struct crypto_hash_walk *walk,
 					 int err)
diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h
index fd8742a40ff3..905490c1da89 100644
--- a/include/crypto/skcipher.h
+++ b/include/crypto/skcipher.h
@@ -60,8 +60,7 @@ struct crypto_skcipher {
 
 	unsigned int ivsize;
 	unsigned int reqsize;
-
-	bool has_setkey;
+	unsigned int keysize;
 
 	struct crypto_tfm base;
 };
@@ -232,6 +231,12 @@ static inline int crypto_has_skcipher(const char *alg_name, u32 type,
 			      crypto_skcipher_mask(mask));
 }
 
+static inline const char *crypto_skcipher_driver_name(
+	struct crypto_skcipher *tfm)
+{
+	return crypto_tfm_alg_driver_name(crypto_skcipher_tfm(tfm));
+}
+
 /**
  * crypto_skcipher_ivsize() - obtain IV size
  * @tfm: cipher handle
@@ -309,7 +314,13 @@ static inline int crypto_skcipher_setkey(struct crypto_skcipher *tfm,
 
 static inline bool crypto_skcipher_has_setkey(struct crypto_skcipher *tfm)
 {
-	return tfm->has_setkey;
+	return tfm->keysize;
+}
+
+static inline unsigned int crypto_skcipher_default_keysize(
+	struct crypto_skcipher *tfm)
+{
+	return tfm->keysize;
 }
 
 /**
@@ -440,6 +451,13 @@ static inline void skcipher_request_free(struct skcipher_request *req)
 	kzfree(req);
 }
 
+static inline void skcipher_request_zero(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+
+	memzero_explicit(req, sizeof(*req) + crypto_skcipher_reqsize(tfm));
+}
+
 /**
  * skcipher_request_set_callback() - set asynchronous callback function
  * @req: request handle
diff --git a/include/crypto/xts.h b/include/crypto/xts.h
index 72c09eb56437..ede6b97b24cc 100644
--- a/include/crypto/xts.h
+++ b/include/crypto/xts.h
@@ -2,6 +2,9 @@
 #define _CRYPTO_XTS_H
 
 #include <crypto/b128ops.h>
+#include <linux/crypto.h>
+#include <crypto/algapi.h>
+#include <linux/fips.h>
 
 struct scatterlist;
 struct blkcipher_desc;
@@ -24,4 +27,28 @@ int xts_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 	      struct scatterlist *src, unsigned int nbytes,
 	      struct xts_crypt_req *req);
 
+static inline int xts_check_key(struct crypto_tfm *tfm,
+				const u8 *key, unsigned int keylen)
+{
+	u32 *flags = &tfm->crt_flags;
+
+	/*
+	 * key consists of keys of equal size concatenated, therefore
+	 * the length must be even.
+	 */
+	if (keylen % 2) {
+		*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		return -EINVAL;
+	}
+
+	/* ensure that the AES and tweak key are not identical */
+	if (fips_enabled &&
+	    !crypto_memneq(key, key + (keylen / 2), keylen / 2)) {
+		*flags |= CRYPTO_TFM_RES_WEAK_KEY;
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 #endif  /* _CRYPTO_XTS_H */
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index c65a212db77e..c5b4b81a831b 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -1166,6 +1166,7 @@ struct drm_connector {
 	struct drm_mode_object base;
 
 	char *name;
+	int connector_id;
 	int connector_type;
 	int connector_type_id;
 	bool interlace_allowed;
@@ -2047,6 +2048,7 @@ struct drm_mode_config {
 	struct list_head fb_list;
 
 	int num_connector;
+	struct ida connector_ida;
 	struct list_head connector_list;
 	int num_encoder;
 	struct list_head encoder_list;
@@ -2200,7 +2202,11 @@ int drm_connector_register(struct drm_connector *connector);
 void drm_connector_unregister(struct drm_connector *connector);
 
 extern void drm_connector_cleanup(struct drm_connector *connector);
-extern unsigned int drm_connector_index(struct drm_connector *connector);
+static inline unsigned drm_connector_index(struct drm_connector *connector)
+{
+	return connector->connector_id;
+}
+
 /* helper to unplug all connectors from sysfs for device */
 extern void drm_connector_unplug_all(struct drm_device *dev);
 
diff --git a/include/dt-bindings/clock/tegra210-car.h b/include/dt-bindings/clock/tegra210-car.h
index 6f45aea49e4f..0a05b0d36ae7 100644
--- a/include/dt-bindings/clock/tegra210-car.h
+++ b/include/dt-bindings/clock/tegra210-car.h
@@ -126,7 +126,7 @@
 /* 104 */
 /* 105 */
 #define TEGRA210_CLK_D_AUDIO 106
-/* 107 ( affects abp -> ape) */
+#define TEGRA210_CLK_APB2APE 107
 /* 108 */
 /* 109 */
 /* 110 */
diff --git a/include/media/i2c/tvp5150.h b/include/dt-bindings/media/tvp5150.h
index 649908a25605..c852a35e916e 100644
--- a/include/media/i2c/tvp5150.h
+++ b/include/dt-bindings/media/tvp5150.h
@@ -18,16 +18,18 @@
     Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */
 
-#ifndef _TVP5150_H_
-#define _TVP5150_H_
+#ifndef _DT_BINDINGS_MEDIA_TVP5150_H
+#define _DT_BINDINGS_MEDIA_TVP5150_H
 
 /* TVP5150 HW inputs */
 #define TVP5150_COMPOSITE0 0
 #define TVP5150_COMPOSITE1 1
 #define TVP5150_SVIDEO     2
 
+#define TVP5150_INPUT_NUM  3
+
 /* TVP5150 HW outputs */
 #define TVP5150_NORMAL       0
 #define TVP5150_BLACK_SCREEN 1
 
-#endif
+#endif /* _DT_BINDINGS_MEDIA_TVP5150_H */
diff --git a/include/dt-bindings/pinctrl/mt7623-pinfunc.h b/include/dt-bindings/pinctrl/mt7623-pinfunc.h
new file mode 100644
index 000000000000..2f00bdc42442
--- /dev/null
+++ b/include/dt-bindings/pinctrl/mt7623-pinfunc.h
@@ -0,0 +1,520 @@
+#ifndef __DTS_MT7623_PINFUNC_H
+#define __DTS_MT7623_PINFUNC_H
+
+#include <dt-bindings/pinctrl/mt65xx.h>
+
+#define MT7623_PIN_0_PWRAP_SPI0_MI_FUNC_GPIO0 (MTK_PIN_NO(0) | 0)
+#define MT7623_PIN_0_PWRAP_SPI0_MI_FUNC_PWRAP_SPIDO (MTK_PIN_NO(0) | 1)
+#define MT7623_PIN_0_PWRAP_SPI0_MI_FUNC_PWRAP_SPIDI (MTK_PIN_NO(0) | 2)
+
+#define MT7623_PIN_1_PWRAP_SPI0_MO_FUNC_GPIO1 (MTK_PIN_NO(1) | 0)
+#define MT7623_PIN_1_PWRAP_SPI0_MO_FUNC_PWRAP_SPIDI (MTK_PIN_NO(1) | 1)
+#define MT7623_PIN_1_PWRAP_SPI0_MO_FUNC_PWRAP_SPIDO (MTK_PIN_NO(1) | 2)
+
+#define MT7623_PIN_2_PWRAP_INT_FUNC_GPIO2 (MTK_PIN_NO(2) | 0)
+#define MT7623_PIN_2_PWRAP_INT_FUNC_PWRAP_INT (MTK_PIN_NO(2) | 1)
+
+#define MT7623_PIN_3_PWRAP_SPI0_CK_FUNC_GPIO3 (MTK_PIN_NO(3) | 0)
+#define MT7623_PIN_3_PWRAP_SPI0_CK_FUNC_PWRAP_SPICK_I (MTK_PIN_NO(3) | 1)
+
+#define MT7623_PIN_4_PWRAP_SPI0_CSN_FUNC_GPIO4 (MTK_PIN_NO(4) | 0)
+#define MT7623_PIN_4_PWRAP_SPI0_CSN_FUNC_PWRAP_SPICS_B_I (MTK_PIN_NO(4) | 1)
+
+#define MT7623_PIN_5_PWRAP_SPI0_CK2_FUNC_GPIO5 (MTK_PIN_NO(5) | 0)
+#define MT7623_PIN_5_PWRAP_SPI0_CK2_FUNC_PWRAP_SPICK2_I (MTK_PIN_NO(5) | 1)
+
+#define MT7623_PIN_6_PWRAP_SPI0_CSN2_FUNC_GPIO6 (MTK_PIN_NO(6) | 0)
+#define MT7623_PIN_6_PWRAP_SPI0_CSN2_FUNC_PWRAP_SPICS2_B_I (MTK_PIN_NO(6) | 1)
+
+#define MT7623_PIN_7_SPI1_CSN_FUNC_GPIO7 (MTK_PIN_NO(7) | 0)
+#define MT7623_PIN_7_SPI1_CSN_FUNC_SPI1_CS (MTK_PIN_NO(7) | 1)
+
+#define MT7623_PIN_8_SPI1_MI_FUNC_GPIO8 (MTK_PIN_NO(8) | 0)
+#define MT7623_PIN_8_SPI1_MI_FUNC_SPI1_MI (MTK_PIN_NO(8) | 1)
+#define MT7623_PIN_8_SPI1_MI_FUNC_SPI1_MO (MTK_PIN_NO(8) | 2)
+
+#define MT7623_PIN_9_SPI1_MO_FUNC_GPIO9 (MTK_PIN_NO(9) | 0)
+#define MT7623_PIN_9_SPI1_MO_FUNC_SPI1_MO (MTK_PIN_NO(9) | 1)
+#define MT7623_PIN_9_SPI1_MO_FUNC_SPI1_MI (MTK_PIN_NO(9) | 2)
+
+#define MT7623_PIN_10_RTC32K_CK_FUNC_GPIO10 (MTK_PIN_NO(10) | 0)
+#define MT7623_PIN_10_RTC32K_CK_FUNC_RTC32K_CK (MTK_PIN_NO(10) | 1)
+
+#define MT7623_PIN_11_WATCHDOG_FUNC_GPIO11 (MTK_PIN_NO(11) | 0)
+#define MT7623_PIN_11_WATCHDOG_FUNC_WATCHDOG (MTK_PIN_NO(11) | 1)
+
+#define MT7623_PIN_12_SRCLKENA_FUNC_GPIO12 (MTK_PIN_NO(12) | 0)
+#define MT7623_PIN_12_SRCLKENA_FUNC_SRCLKENA (MTK_PIN_NO(12) | 1)
+
+#define MT7623_PIN_13_SRCLKENAI_FUNC_GPIO13 (MTK_PIN_NO(13) | 0)
+#define MT7623_PIN_13_SRCLKENAI_FUNC_SRCLKENAI (MTK_PIN_NO(13) | 1)
+
+#define MT7623_PIN_14_GPIO14_FUNC_GPIO14 (MTK_PIN_NO(14) | 0)
+#define MT7623_PIN_14_GPIO14_FUNC_URXD2 (MTK_PIN_NO(14) | 1)
+#define MT7623_PIN_14_GPIO14_FUNC_UTXD2 (MTK_PIN_NO(14) | 2)
+
+#define MT7623_PIN_15_GPIO15_FUNC_GPIO15 (MTK_PIN_NO(15) | 0)
+#define MT7623_PIN_15_GPIO15_FUNC_UTXD2 (MTK_PIN_NO(15) | 1)
+#define MT7623_PIN_15_GPIO15_FUNC_URXD2 (MTK_PIN_NO(15) | 2)
+
+#define MT7623_PIN_18_PCM_CLK_FUNC_GPIO18 (MTK_PIN_NO(18) | 0)
+#define MT7623_PIN_18_PCM_CLK_FUNC_PCM_CLK0 (MTK_PIN_NO(18) | 1)
+#define MT7623_PIN_18_PCM_CLK_FUNC_AP_PCM_CLKO (MTK_PIN_NO(18) | 6)
+
+#define MT7623_PIN_19_PCM_SYNC_FUNC_GPIO19 (MTK_PIN_NO(19) | 0)
+#define MT7623_PIN_19_PCM_SYNC_FUNC_PCM_SYNC (MTK_PIN_NO(19) | 1)
+#define MT7623_PIN_19_PCM_SYNC_FUNC_AP_PCM_SYNC (MTK_PIN_NO(19) | 6)
+
+#define MT7623_PIN_20_PCM_RX_FUNC_GPIO20 (MTK_PIN_NO(20) | 0)
+#define MT7623_PIN_20_PCM_RX_FUNC_PCM_RX (MTK_PIN_NO(20) | 1)
+#define MT7623_PIN_20_PCM_RX_FUNC_PCM_TX (MTK_PIN_NO(20) | 4)
+#define MT7623_PIN_20_PCM_RX_FUNC_AP_PCM_RX (MTK_PIN_NO(20) | 6)
+
+#define MT7623_PIN_21_PCM_TX_FUNC_GPIO21 (MTK_PIN_NO(21) | 0)
+#define MT7623_PIN_21_PCM_TX_FUNC_PCM_TX (MTK_PIN_NO(21) | 1)
+#define MT7623_PIN_21_PCM_TX_FUNC_PCM_RX (MTK_PIN_NO(21) | 4)
+#define MT7623_PIN_21_PCM_TX_FUNC_AP_PCM_TX (MTK_PIN_NO(21) | 6)
+
+#define MT7623_PIN_22_EINT0_FUNC_GPIO22 (MTK_PIN_NO(22) | 0)
+#define MT7623_PIN_22_EINT0_FUNC_UCTS0 (MTK_PIN_NO(22) | 1)
+#define MT7623_PIN_22_EINT0_FUNC_PCIE0_PERST_N (MTK_PIN_NO(22) | 2)
+
+#define MT7623_PIN_23_EINT1_FUNC_GPIO23 (MTK_PIN_NO(23) | 0)
+#define MT7623_PIN_23_EINT1_FUNC_URTS0 (MTK_PIN_NO(23) | 1)
+#define MT7623_PIN_23_EINT1_FUNC_PCIE1_PERST_N (MTK_PIN_NO(23) | 2)
+
+#define MT7623_PIN_24_EINT2_FUNC_GPIO24 (MTK_PIN_NO(24) | 0)
+#define MT7623_PIN_24_EINT2_FUNC_UCTS1 (MTK_PIN_NO(24) | 1)
+#define MT7623_PIN_24_EINT2_FUNC_PCIE2_PERST_N (MTK_PIN_NO(24) | 2)
+
+#define MT7623_PIN_25_EINT3_FUNC_GPIO25 (MTK_PIN_NO(25) | 0)
+#define MT7623_PIN_25_EINT3_FUNC_URTS1 (MTK_PIN_NO(25) | 1)
+
+#define MT7623_PIN_26_EINT4_FUNC_GPIO26 (MTK_PIN_NO(26) | 0)
+#define MT7623_PIN_26_EINT4_FUNC_UCTS3 (MTK_PIN_NO(26) | 1)
+#define MT7623_PIN_26_EINT4_FUNC_PCIE2_WAKE_N (MTK_PIN_NO(26) | 6)
+
+#define MT7623_PIN_27_EINT5_FUNC_GPIO27 (MTK_PIN_NO(27) | 0)
+#define MT7623_PIN_27_EINT5_FUNC_URTS3 (MTK_PIN_NO(27) | 1)
+#define MT7623_PIN_27_EINT5_FUNC_PCIE1_WAKE_N (MTK_PIN_NO(27) | 6)
+
+#define MT7623_PIN_28_EINT6_FUNC_GPIO28 (MTK_PIN_NO(28) | 0)
+#define MT7623_PIN_28_EINT6_FUNC_DRV_VBUS (MTK_PIN_NO(28) | 1)
+#define MT7623_PIN_28_EINT6_FUNC_PCIE0_WAKE_N (MTK_PIN_NO(28) | 6)
+
+#define MT7623_PIN_29_EINT7_FUNC_GPIO29 (MTK_PIN_NO(29) | 0)
+#define MT7623_PIN_29_EINT7_FUNC_IDDIG (MTK_PIN_NO(29) | 1)
+#define MT7623_PIN_29_EINT7_FUNC_MSDC1_WP (MTK_PIN_NO(29) | 2)
+#define MT7623_PIN_29_EINT7_FUNC_PCIE2_PERST_N (MTK_PIN_NO(29) | 6)
+
+#define MT7623_PIN_33_I2S1_DATA_FUNC_GPIO33 (MTK_PIN_NO(33) | 0)
+#define MT7623_PIN_33_I2S1_DATA_FUNC_I2S1_DATA (MTK_PIN_NO(33) | 1)
+#define MT7623_PIN_33_I2S1_DATA_FUNC_PCM_TX (MTK_PIN_NO(33) | 3)
+#define MT7623_PIN_33_I2S1_DATA_FUNC_AP_PCM_TX (MTK_PIN_NO(33) | 6)
+
+#define MT7623_PIN_34_I2S1_DATA_IN_FUNC_GPIO34 (MTK_PIN_NO(34) | 0)
+#define MT7623_PIN_34_I2S1_DATA_IN_FUNC_I2S1_DATA_IN (MTK_PIN_NO(34) | 1)
+#define MT7623_PIN_34_I2S1_DATA_IN_FUNC_PCM_RX (MTK_PIN_NO(34) | 3)
+#define MT7623_PIN_34_I2S1_DATA_IN_FUNC_AP_PCM_RX (MTK_PIN_NO(34) | 6)
+
+#define MT7623_PIN_35_I2S1_BCK_FUNC_GPIO35 (MTK_PIN_NO(35) | 0)
+#define MT7623_PIN_35_I2S1_BCK_FUNC_I2S1_BCK (MTK_PIN_NO(35) | 1)
+#define MT7623_PIN_35_I2S1_BCK_FUNC_PCM_CLK0 (MTK_PIN_NO(35) | 3)
+#define MT7623_PIN_35_I2S1_BCK_FUNC_AP_PCM_CLKO (MTK_PIN_NO(35) | 6)
+
+#define MT7623_PIN_36_I2S1_LRCK_FUNC_GPIO36 (MTK_PIN_NO(36) | 0)
+#define MT7623_PIN_36_I2S1_LRCK_FUNC_I2S1_LRCK (MTK_PIN_NO(36) | 1)
+#define MT7623_PIN_36_I2S1_LRCK_FUNC_PCM_SYNC (MTK_PIN_NO(36) | 3)
+#define MT7623_PIN_36_I2S1_LRCK_FUNC_AP_PCM_SYNC (MTK_PIN_NO(36) | 6)
+
+#define MT7623_PIN_37_I2S1_MCLK_FUNC_GPIO37 (MTK_PIN_NO(37) | 0)
+#define MT7623_PIN_37_I2S1_MCLK_FUNC_I2S1_MCLK (MTK_PIN_NO(37) | 1)
+
+#define MT7623_PIN_39_JTMS_FUNC_GPIO39 (MTK_PIN_NO(39) | 0)
+#define MT7623_PIN_39_JTMS_FUNC_JTMS (MTK_PIN_NO(39) | 1)
+
+#define MT7623_PIN_40_JTCK_FUNC_GPIO40 (MTK_PIN_NO(40) | 0)
+#define MT7623_PIN_40_JTCK_FUNC_JTCK (MTK_PIN_NO(40) | 1)
+
+#define MT7623_PIN_41_JTDI_FUNC_GPIO41 (MTK_PIN_NO(41) | 0)
+#define MT7623_PIN_41_JTDI_FUNC_JTDI (MTK_PIN_NO(41) | 1)
+
+#define MT7623_PIN_42_JTDO_FUNC_GPIO42 (MTK_PIN_NO(42) | 0)
+#define MT7623_PIN_42_JTDO_FUNC_JTDO (MTK_PIN_NO(42) | 1)
+
+#define MT7623_PIN_43_NCLE_FUNC_GPIO43 (MTK_PIN_NO(43) | 0)
+#define MT7623_PIN_43_NCLE_FUNC_NCLE (MTK_PIN_NO(43) | 1)
+#define MT7623_PIN_43_NCLE_FUNC_EXT_XCS2 (MTK_PIN_NO(43) | 2)
+
+#define MT7623_PIN_44_NCEB1_FUNC_GPIO44 (MTK_PIN_NO(44) | 0)
+#define MT7623_PIN_44_NCEB1_FUNC_NCEB1 (MTK_PIN_NO(44) | 1)
+#define MT7623_PIN_44_NCEB1_FUNC_IDDIG (MTK_PIN_NO(44) | 2)
+
+#define MT7623_PIN_45_NCEB0_FUNC_GPIO45 (MTK_PIN_NO(45) | 0)
+#define MT7623_PIN_45_NCEB0_FUNC_NCEB0 (MTK_PIN_NO(45) | 1)
+#define MT7623_PIN_45_NCEB0_FUNC_DRV_VBUS (MTK_PIN_NO(45) | 2)
+
+#define MT7623_PIN_46_IR_FUNC_GPIO46 (MTK_PIN_NO(46) | 0)
+#define MT7623_PIN_46_IR_FUNC_IR (MTK_PIN_NO(46) | 1)
+
+#define MT7623_PIN_47_NREB_FUNC_GPIO47 (MTK_PIN_NO(47) | 0)
+#define MT7623_PIN_47_NREB_FUNC_NREB (MTK_PIN_NO(47) | 1)
+
+#define MT7623_PIN_48_NRNB_FUNC_GPIO48 (MTK_PIN_NO(48) | 0)
+#define MT7623_PIN_48_NRNB_FUNC_NRNB (MTK_PIN_NO(48) | 1)
+
+#define MT7623_PIN_49_I2S0_DATA_FUNC_GPIO49 (MTK_PIN_NO(49) | 0)
+#define MT7623_PIN_49_I2S0_DATA_FUNC_I2S0_DATA (MTK_PIN_NO(49) | 1)
+#define MT7623_PIN_49_I2S0_DATA_FUNC_PCM_TX (MTK_PIN_NO(49) | 3)
+#define MT7623_PIN_49_I2S0_DATA_FUNC_AP_I2S_DO (MTK_PIN_NO(49) | 6)
+
+#define MT7623_PIN_53_SPI0_CSN_FUNC_GPIO53 (MTK_PIN_NO(53) | 0)
+#define MT7623_PIN_53_SPI0_CSN_FUNC_SPI0_CS (MTK_PIN_NO(53) | 1)
+#define MT7623_PIN_53_SPI0_CSN_FUNC_PWM1 (MTK_PIN_NO(53) | 5)
+
+#define MT7623_PIN_54_SPI0_CK_FUNC_GPIO54 (MTK_PIN_NO(54) | 0)
+#define MT7623_PIN_54_SPI0_CK_FUNC_SPI0_CK (MTK_PIN_NO(54) | 1)
+
+#define MT7623_PIN_55_SPI0_MI_FUNC_GPIO55 (MTK_PIN_NO(55) | 0)
+#define MT7623_PIN_55_SPI0_MI_FUNC_SPI0_MI (MTK_PIN_NO(55) | 1)
+#define MT7623_PIN_55_SPI0_MI_FUNC_SPI0_MO (MTK_PIN_NO(55) | 2)
+#define MT7623_PIN_55_SPI0_MI_FUNC_MSDC1_WP (MTK_PIN_NO(55) | 3)
+#define MT7623_PIN_55_SPI0_MI_FUNC_PWM2 (MTK_PIN_NO(55) | 5)
+
+#define MT7623_PIN_56_SPI0_MO_FUNC_GPIO56 (MTK_PIN_NO(56) | 0)
+#define MT7623_PIN_56_SPI0_MO_FUNC_SPI0_MO (MTK_PIN_NO(56) | 1)
+#define MT7623_PIN_56_SPI0_MO_FUNC_SPI0_MI (MTK_PIN_NO(56) | 2)
+
+#define MT7623_PIN_60_WB_RSTB_FUNC_GPIO60 (MTK_PIN_NO(60) | 0)
+#define MT7623_PIN_60_WB_RSTB_FUNC_WB_RSTB (MTK_PIN_NO(60) | 1)
+
+#define MT7623_PIN_61_GPIO61_FUNC_GPIO61 (MTK_PIN_NO(61) | 0)
+#define MT7623_PIN_61_GPIO61_FUNC_TEST_FD (MTK_PIN_NO(61) | 1)
+
+#define MT7623_PIN_62_GPIO62_FUNC_GPIO62 (MTK_PIN_NO(62) | 0)
+#define MT7623_PIN_62_GPIO62_FUNC_TEST_FC (MTK_PIN_NO(62) | 1)
+
+#define MT7623_PIN_63_WB_SCLK_FUNC_GPIO63 (MTK_PIN_NO(63) | 0)
+#define MT7623_PIN_63_WB_SCLK_FUNC_WB_SCLK (MTK_PIN_NO(63) | 1)
+
+#define MT7623_PIN_64_WB_SDATA_FUNC_GPIO64 (MTK_PIN_NO(64) | 0)
+#define MT7623_PIN_64_WB_SDATA_FUNC_WB_SDATA (MTK_PIN_NO(64) | 1)
+
+#define MT7623_PIN_65_WB_SEN_FUNC_GPIO65 (MTK_PIN_NO(65) | 0)
+#define MT7623_PIN_65_WB_SEN_FUNC_WB_SEN (MTK_PIN_NO(65) | 1)
+
+#define MT7623_PIN_66_WB_CRTL0_FUNC_GPIO66 (MTK_PIN_NO(66) | 0)
+#define MT7623_PIN_66_WB_CRTL0_FUNC_WB_CRTL0 (MTK_PIN_NO(66) | 1)
+
+#define MT7623_PIN_67_WB_CRTL1_FUNC_GPIO67 (MTK_PIN_NO(67) | 0)
+#define MT7623_PIN_67_WB_CRTL1_FUNC_WB_CRTL1 (MTK_PIN_NO(67) | 1)
+
+#define MT7623_PIN_68_WB_CRTL2_FUNC_GPIO68 (MTK_PIN_NO(68) | 0)
+#define MT7623_PIN_68_WB_CRTL2_FUNC_WB_CRTL2 (MTK_PIN_NO(68) | 1)
+
+#define MT7623_PIN_69_WB_CRTL3_FUNC_GPIO69 (MTK_PIN_NO(69) | 0)
+#define MT7623_PIN_69_WB_CRTL3_FUNC_WB_CRTL3 (MTK_PIN_NO(69) | 1)
+
+#define MT7623_PIN_70_WB_CRTL4_FUNC_GPIO70 (MTK_PIN_NO(70) | 0)
+#define MT7623_PIN_70_WB_CRTL4_FUNC_WB_CRTL4 (MTK_PIN_NO(70) | 1)
+
+#define MT7623_PIN_71_WB_CRTL5_FUNC_GPIO71 (MTK_PIN_NO(71) | 0)
+#define MT7623_PIN_71_WB_CRTL5_FUNC_WB_CRTL5 (MTK_PIN_NO(71) | 1)
+
+#define MT7623_PIN_72_I2S0_DATA_IN_FUNC_GPIO72 (MTK_PIN_NO(72) | 0)
+#define MT7623_PIN_72_I2S0_DATA_IN_FUNC_I2S0_DATA_IN (MTK_PIN_NO(72) | 1)
+#define MT7623_PIN_72_I2S0_DATA_IN_FUNC_PCM_RX (MTK_PIN_NO(72) | 3)
+#define MT7623_PIN_72_I2S0_DATA_IN_FUNC_PWM0 (MTK_PIN_NO(72) | 4)
+#define MT7623_PIN_72_I2S0_DATA_IN_FUNC_DISP_PWM (MTK_PIN_NO(72) | 5)
+#define MT7623_PIN_72_I2S0_DATA_IN_FUNC_AP_I2S_DI (MTK_PIN_NO(72) | 6)
+
+#define MT7623_PIN_73_I2S0_LRCK_FUNC_GPIO73 (MTK_PIN_NO(73) | 0)
+#define MT7623_PIN_73_I2S0_LRCK_FUNC_I2S0_LRCK (MTK_PIN_NO(73) | 1)
+#define MT7623_PIN_73_I2S0_LRCK_FUNC_PCM_SYNC (MTK_PIN_NO(73) | 3)
+#define MT7623_PIN_73_I2S0_LRCK_FUNC_AP_I2S_LRCK (MTK_PIN_NO(73) | 6)
+
+#define MT7623_PIN_74_I2S0_BCK_FUNC_GPIO74 (MTK_PIN_NO(74) | 0)
+#define MT7623_PIN_74_I2S0_BCK_FUNC_I2S0_BCK (MTK_PIN_NO(74) | 1)
+#define MT7623_PIN_74_I2S0_BCK_FUNC_PCM_CLK0 (MTK_PIN_NO(74) | 3)
+#define MT7623_PIN_74_I2S0_BCK_FUNC_AP_I2S_BCK (MTK_PIN_NO(74) | 6)
+
+#define MT7623_PIN_75_SDA0_FUNC_GPIO75 (MTK_PIN_NO(75) | 0)
+#define MT7623_PIN_75_SDA0_FUNC_SDA0 (MTK_PIN_NO(75) | 1)
+
+#define MT7623_PIN_76_SCL0_FUNC_GPIO76 (MTK_PIN_NO(76) | 0)
+#define MT7623_PIN_76_SCL0_FUNC_SCL0 (MTK_PIN_NO(76) | 1)
+
+#define MT7623_PIN_83_LCM_RST_FUNC_GPIO83 (MTK_PIN_NO(83) | 0)
+#define MT7623_PIN_83_LCM_RST_FUNC_LCM_RST (MTK_PIN_NO(83) | 1)
+
+#define MT7623_PIN_84_DSI_TE_FUNC_GPIO84 (MTK_PIN_NO(84) | 0)
+#define MT7623_PIN_84_DSI_TE_FUNC_DSI_TE (MTK_PIN_NO(84) | 1)
+
+#define MT7623_PIN_95_MIPI_TCN_FUNC_GPIO95 (MTK_PIN_NO(95) | 0)
+#define MT7623_PIN_95_MIPI_TCN_FUNC_TCN (MTK_PIN_NO(95) | 1)
+
+#define MT7623_PIN_96_MIPI_TCP_FUNC_GPIO96 (MTK_PIN_NO(96) | 0)
+#define MT7623_PIN_96_MIPI_TCP_FUNC_TCP (MTK_PIN_NO(96) | 1)
+
+#define MT7623_PIN_97_MIPI_TDN1_FUNC_GPIO97 (MTK_PIN_NO(97) | 0)
+#define MT7623_PIN_97_MIPI_TDN1_FUNC_TDN1 (MTK_PIN_NO(97) | 1)
+
+#define MT7623_PIN_98_MIPI_TDP1_FUNC_GPIO98 (MTK_PIN_NO(98) | 0)
+#define MT7623_PIN_98_MIPI_TDP1_FUNC_TDP1 (MTK_PIN_NO(98) | 1)
+
+#define MT7623_PIN_99_MIPI_TDN0_FUNC_GPIO99 (MTK_PIN_NO(99) | 0)
+#define MT7623_PIN_99_MIPI_TDN0_FUNC_TDN0 (MTK_PIN_NO(99) | 1)
+
+#define MT7623_PIN_100_MIPI_TDP0_FUNC_GPIO100 (MTK_PIN_NO(100) | 0)
+#define MT7623_PIN_100_MIPI_TDP0_FUNC_TDP0 (MTK_PIN_NO(100) | 1)
+
+#define MT7623_PIN_105_MSDC1_CMD_FUNC_GPIO105 (MTK_PIN_NO(105) | 0)
+#define MT7623_PIN_105_MSDC1_CMD_FUNC_MSDC1_CMD (MTK_PIN_NO(105) | 1)
+#define MT7623_PIN_105_MSDC1_CMD_FUNC_SDA1 (MTK_PIN_NO(105) | 3)
+#define MT7623_PIN_105_MSDC1_CMD_FUNC_I2SOUT_BCK (MTK_PIN_NO(105) | 6)
+
+#define MT7623_PIN_106_MSDC1_CLK_FUNC_GPIO106 (MTK_PIN_NO(106) | 0)
+#define MT7623_PIN_106_MSDC1_CLK_FUNC_MSDC1_CLK (MTK_PIN_NO(106) | 1)
+#define MT7623_PIN_106_MSDC1_CLK_FUNC_SCL1 (MTK_PIN_NO(106) | 3)
+#define MT7623_PIN_106_MSDC1_CLK_FUNC_I2SOUT_LRCK (MTK_PIN_NO(106) | 6)
+
+#define MT7623_PIN_107_MSDC1_DAT0_FUNC_GPIO107 (MTK_PIN_NO(107) | 0)
+#define MT7623_PIN_107_MSDC1_DAT0_FUNC_MSDC1_DAT0 (MTK_PIN_NO(107) | 1)
+#define MT7623_PIN_107_MSDC1_DAT0_FUNC_UTXD0 (MTK_PIN_NO(107) | 5)
+#define MT7623_PIN_107_MSDC1_DAT0_FUNC_I2SOUT_DATA_OUT (MTK_PIN_NO(107) | 6)
+
+#define MT7623_PIN_108_MSDC1_DAT1_FUNC_GPIO108 (MTK_PIN_NO(108) | 0)
+#define MT7623_PIN_108_MSDC1_DAT1_FUNC_MSDC1_DAT1 (MTK_PIN_NO(108) | 1)
+#define MT7623_PIN_108_MSDC1_DAT1_FUNC_PWM0 (MTK_PIN_NO(108) | 3)
+#define MT7623_PIN_108_MSDC1_DAT1_FUNC_URXD0 (MTK_PIN_NO(108) | 5)
+#define MT7623_PIN_108_MSDC1_DAT1_FUNC_PWM1 (MTK_PIN_NO(108) | 6)
+
+#define MT7623_PIN_109_MSDC1_DAT2_FUNC_GPIO109 (MTK_PIN_NO(109) | 0)
+#define MT7623_PIN_109_MSDC1_DAT2_FUNC_MSDC1_DAT2 (MTK_PIN_NO(109) | 1)
+#define MT7623_PIN_109_MSDC1_DAT2_FUNC_SDA2 (MTK_PIN_NO(109) | 3)
+#define MT7623_PIN_109_MSDC1_DAT2_FUNC_UTXD1 (MTK_PIN_NO(109) | 5)
+#define MT7623_PIN_109_MSDC1_DAT2_FUNC_PWM2 (MTK_PIN_NO(109) | 6)
+
+#define MT7623_PIN_110_MSDC1_DAT3_FUNC_GPIO110 (MTK_PIN_NO(110) | 0)
+#define MT7623_PIN_110_MSDC1_DAT3_FUNC_MSDC1_DAT3 (MTK_PIN_NO(110) | 1)
+#define MT7623_PIN_110_MSDC1_DAT3_FUNC_SCL2 (MTK_PIN_NO(110) | 3)
+#define MT7623_PIN_110_MSDC1_DAT3_FUNC_URXD1 (MTK_PIN_NO(110) | 5)
+#define MT7623_PIN_110_MSDC1_DAT3_FUNC_PWM3 (MTK_PIN_NO(110) | 6)
+
+#define MT7623_PIN_111_MSDC0_DAT7_FUNC_GPIO111 (MTK_PIN_NO(111) | 0)
+#define MT7623_PIN_111_MSDC0_DAT7_FUNC_MSDC0_DAT7 (MTK_PIN_NO(111) | 1)
+#define MT7623_PIN_111_MSDC0_DAT7_FUNC_NLD7 (MTK_PIN_NO(111) | 4)
+
+#define MT7623_PIN_112_MSDC0_DAT6_FUNC_GPIO112 (MTK_PIN_NO(112) | 0)
+#define MT7623_PIN_112_MSDC0_DAT6_FUNC_MSDC0_DAT6 (MTK_PIN_NO(112) | 1)
+#define MT7623_PIN_112_MSDC0_DAT6_FUNC_NLD6 (MTK_PIN_NO(112) | 4)
+
+#define MT7623_PIN_113_MSDC0_DAT5_FUNC_GPIO113 (MTK_PIN_NO(113) | 0)
+#define MT7623_PIN_113_MSDC0_DAT5_FUNC_MSDC0_DAT5 (MTK_PIN_NO(113) | 1)
+#define MT7623_PIN_113_MSDC0_DAT5_FUNC_NLD5 (MTK_PIN_NO(113) | 4)
+
+#define MT7623_PIN_114_MSDC0_DAT4_FUNC_GPIO114 (MTK_PIN_NO(114) | 0)
+#define MT7623_PIN_114_MSDC0_DAT4_FUNC_MSDC0_DAT4 (MTK_PIN_NO(114) | 1)
+#define MT7623_PIN_114_MSDC0_DAT4_FUNC_NLD4 (MTK_PIN_NO(114) | 4)
+
+#define MT7623_PIN_115_MSDC0_RSTB_FUNC_GPIO115 (MTK_PIN_NO(115) | 0)
+#define MT7623_PIN_115_MSDC0_RSTB_FUNC_MSDC0_RSTB (MTK_PIN_NO(115) | 1)
+#define MT7623_PIN_115_MSDC0_RSTB_FUNC_NLD8 (MTK_PIN_NO(115) | 4)
+
+#define MT7623_PIN_116_MSDC0_CMD_FUNC_GPIO116 (MTK_PIN_NO(116) | 0)
+#define MT7623_PIN_116_MSDC0_CMD_FUNC_MSDC0_CMD (MTK_PIN_NO(116) | 1)
+#define MT7623_PIN_116_MSDC0_CMD_FUNC_NALE (MTK_PIN_NO(116) | 4)
+
+#define MT7623_PIN_117_MSDC0_CLK_FUNC_GPIO117 (MTK_PIN_NO(117) | 0)
+#define MT7623_PIN_117_MSDC0_CLK_FUNC_MSDC0_CLK (MTK_PIN_NO(117) | 1)
+#define MT7623_PIN_117_MSDC0_CLK_FUNC_NWEB (MTK_PIN_NO(117) | 4)
+
+#define MT7623_PIN_118_MSDC0_DAT3_FUNC_GPIO118 (MTK_PIN_NO(118) | 0)
+#define MT7623_PIN_118_MSDC0_DAT3_FUNC_MSDC0_DAT3 (MTK_PIN_NO(118) | 1)
+#define MT7623_PIN_118_MSDC0_DAT3_FUNC_NLD3 (MTK_PIN_NO(118) | 4)
+
+#define MT7623_PIN_119_MSDC0_DAT2_FUNC_GPIO119 (MTK_PIN_NO(119) | 0)
+#define MT7623_PIN_119_MSDC0_DAT2_FUNC_MSDC0_DAT2 (MTK_PIN_NO(119) | 1)
+#define MT7623_PIN_119_MSDC0_DAT2_FUNC_NLD2 (MTK_PIN_NO(119) | 4)
+
+#define MT7623_PIN_120_MSDC0_DAT1_FUNC_GPIO120 (MTK_PIN_NO(120) | 0)
+#define MT7623_PIN_120_MSDC0_DAT1_FUNC_MSDC0_DAT1 (MTK_PIN_NO(120) | 1)
+#define MT7623_PIN_120_MSDC0_DAT1_FUNC_NLD1 (MTK_PIN_NO(120) | 4)
+
+#define MT7623_PIN_121_MSDC0_DAT0_FUNC_GPIO121 (MTK_PIN_NO(121) | 0)
+#define MT7623_PIN_121_MSDC0_DAT0_FUNC_MSDC0_DAT0 (MTK_PIN_NO(121) | 1)
+#define MT7623_PIN_121_MSDC0_DAT0_FUNC_NLD0 (MTK_PIN_NO(121) | 4)
+#define MT7623_PIN_121_MSDC0_DAT0_FUNC_WATCHDOG (MTK_PIN_NO(121) | 5)
+
+#define MT7623_PIN_122_GPIO122_FUNC_GPIO122 (MTK_PIN_NO(122) | 0)
+#define MT7623_PIN_122_GPIO122_FUNC_TEST (MTK_PIN_NO(122) | 1)
+#define MT7623_PIN_122_GPIO122_FUNC_SDA2 (MTK_PIN_NO(122) | 4)
+#define MT7623_PIN_122_GPIO122_FUNC_URXD0 (MTK_PIN_NO(122) | 5)
+
+#define MT7623_PIN_123_GPIO123_FUNC_GPIO123 (MTK_PIN_NO(123) | 0)
+#define MT7623_PIN_123_GPIO123_FUNC_TEST (MTK_PIN_NO(123) | 1)
+#define MT7623_PIN_123_GPIO123_FUNC_SCL2 (MTK_PIN_NO(123) | 4)
+#define MT7623_PIN_123_GPIO123_FUNC_UTXD0 (MTK_PIN_NO(123) | 5)
+
+#define MT7623_PIN_124_GPIO124_FUNC_GPIO124 (MTK_PIN_NO(124) | 0)
+#define MT7623_PIN_124_GPIO124_FUNC_TEST (MTK_PIN_NO(124) | 1)
+#define MT7623_PIN_124_GPIO124_FUNC_SDA1 (MTK_PIN_NO(124) | 4)
+#define MT7623_PIN_124_GPIO124_FUNC_PWM3 (MTK_PIN_NO(124) | 5)
+
+#define MT7623_PIN_125_GPIO125_FUNC_GPIO125 (MTK_PIN_NO(125) | 0)
+#define MT7623_PIN_125_GPIO125_FUNC_TEST (MTK_PIN_NO(125) | 1)
+#define MT7623_PIN_125_GPIO125_FUNC_SCL1 (MTK_PIN_NO(125) | 4)
+#define MT7623_PIN_125_GPIO125_FUNC_PWM4 (MTK_PIN_NO(125) | 5)
+
+#define MT7623_PIN_126_I2S0_MCLK_FUNC_GPIO126 (MTK_PIN_NO(126) | 0)
+#define MT7623_PIN_126_I2S0_MCLK_FUNC_I2S0_MCLK (MTK_PIN_NO(126) | 1)
+#define MT7623_PIN_126_I2S0_MCLK_FUNC_AP_I2S_MCLK (MTK_PIN_NO(126) | 6)
+
+#define MT7623_PIN_199_SPI1_CK_FUNC_GPIO199 (MTK_PIN_NO(199) | 0)
+#define MT7623_PIN_199_SPI1_CK_FUNC_SPI1_CK (MTK_PIN_NO(199) | 1)
+
+#define MT7623_PIN_200_URXD2_FUNC_GPIO200 (MTK_PIN_NO(200) | 0)
+#define MT7623_PIN_200_URXD2_FUNC_URXD2 (MTK_PIN_NO(200) | 6)
+
+#define MT7623_PIN_201_UTXD2_FUNC_GPIO201 (MTK_PIN_NO(201) | 0)
+#define MT7623_PIN_201_UTXD2_FUNC_UTXD2 (MTK_PIN_NO(201) | 6)
+
+#define MT7623_PIN_203_PWM0_FUNC_GPIO203 (MTK_PIN_NO(203) | 0)
+#define MT7623_PIN_203_PWM0_FUNC_PWM0 (MTK_PIN_NO(203) | 1)
+#define MT7623_PIN_203_PWM0_FUNC_DISP_PWM (MTK_PIN_NO(203) | 2)
+
+#define MT7623_PIN_204_PWM1_FUNC_GPIO204 (MTK_PIN_NO(204) | 0)
+#define MT7623_PIN_204_PWM1_FUNC_PWM1 (MTK_PIN_NO(204) | 1)
+
+#define MT7623_PIN_205_PWM2_FUNC_GPIO205 (MTK_PIN_NO(205) | 0)
+#define MT7623_PIN_205_PWM2_FUNC_PWM2 (MTK_PIN_NO(205) | 1)
+
+#define MT7623_PIN_206_PWM3_FUNC_GPIO206 (MTK_PIN_NO(206) | 0)
+#define MT7623_PIN_206_PWM3_FUNC_PWM3 (MTK_PIN_NO(206) | 1)
+
+#define MT7623_PIN_207_PWM4_FUNC_GPIO207 (MTK_PIN_NO(207) | 0)
+#define MT7623_PIN_207_PWM4_FUNC_PWM4 (MTK_PIN_NO(207) | 1)
+
+#define MT7623_PIN_208_AUD_EXT_CK1_FUNC_GPIO208 (MTK_PIN_NO(208) | 0)
+#define MT7623_PIN_208_AUD_EXT_CK1_FUNC_AUD_EXT_CK1 (MTK_PIN_NO(208) | 1)
+#define MT7623_PIN_208_AUD_EXT_CK1_FUNC_PWM0 (MTK_PIN_NO(208) | 2)
+#define MT7623_PIN_208_AUD_EXT_CK1_FUNC_PCIE0_PERST_N (MTK_PIN_NO(208) | 3)
+#define MT7623_PIN_208_AUD_EXT_CK1_FUNC_DISP_PWM (MTK_PIN_NO(208) | 5)
+
+#define MT7623_PIN_209_AUD_EXT_CK2_FUNC_GPIO209 (MTK_PIN_NO(209) | 0)
+#define MT7623_PIN_209_AUD_EXT_CK2_FUNC_AUD_EXT_CK2 (MTK_PIN_NO(209) | 1)
+#define MT7623_PIN_209_AUD_EXT_CK2_FUNC_MSDC1_WP (MTK_PIN_NO(209) | 2)
+#define MT7623_PIN_209_AUD_EXT_CK2_FUNC_PCIE1_PERST_N (MTK_PIN_NO(209) | 3)
+#define MT7623_PIN_209_AUD_EXT_CK2_FUNC_PWM1 (MTK_PIN_NO(209) | 5)
+
+#define MT7623_PIN_236_EXT_SDIO3_FUNC_GPIO236 (MTK_PIN_NO(236) | 0)
+#define MT7623_PIN_236_EXT_SDIO3_FUNC_EXT_SDIO3 (MTK_PIN_NO(236) | 1)
+#define MT7623_PIN_236_EXT_SDIO3_FUNC_IDDIG (MTK_PIN_NO(236) | 2)
+
+#define MT7623_PIN_237_EXT_SDIO2_FUNC_GPIO237 (MTK_PIN_NO(237) | 0)
+#define MT7623_PIN_237_EXT_SDIO2_FUNC_EXT_SDIO2 (MTK_PIN_NO(237) | 1)
+#define MT7623_PIN_237_EXT_SDIO2_FUNC_DRV_VBUS (MTK_PIN_NO(237) | 2)
+
+#define MT7623_PIN_238_EXT_SDIO1_FUNC_GPIO238 (MTK_PIN_NO(238) | 0)
+#define MT7623_PIN_238_EXT_SDIO1_FUNC_EXT_SDIO1 (MTK_PIN_NO(238) | 1)
+
+#define MT7623_PIN_239_EXT_SDIO0_FUNC_GPIO239 (MTK_PIN_NO(239) | 0)
+#define MT7623_PIN_239_EXT_SDIO0_FUNC_EXT_SDIO0 (MTK_PIN_NO(239) | 1)
+
+#define MT7623_PIN_240_EXT_XCS_FUNC_GPIO240 (MTK_PIN_NO(240) | 0)
+#define MT7623_PIN_240_EXT_XCS_FUNC_EXT_XCS (MTK_PIN_NO(240) | 1)
+
+#define MT7623_PIN_241_EXT_SCK_FUNC_GPIO241 (MTK_PIN_NO(241) | 0)
+#define MT7623_PIN_241_EXT_SCK_FUNC_EXT_SCK (MTK_PIN_NO(241) | 1)
+
+#define MT7623_PIN_242_URTS2_FUNC_GPIO242 (MTK_PIN_NO(242) | 0)
+#define MT7623_PIN_242_URTS2_FUNC_URTS2 (MTK_PIN_NO(242) | 1)
+#define MT7623_PIN_242_URTS2_FUNC_UTXD3 (MTK_PIN_NO(242) | 2)
+#define MT7623_PIN_242_URTS2_FUNC_URXD3 (MTK_PIN_NO(242) | 3)
+#define MT7623_PIN_242_URTS2_FUNC_SCL1 (MTK_PIN_NO(242) | 4)
+
+#define MT7623_PIN_243_UCTS2_FUNC_GPIO243 (MTK_PIN_NO(243) | 0)
+#define MT7623_PIN_243_UCTS2_FUNC_UCTS2 (MTK_PIN_NO(243) | 1)
+#define MT7623_PIN_243_UCTS2_FUNC_URXD3 (MTK_PIN_NO(243) | 2)
+#define MT7623_PIN_243_UCTS2_FUNC_UTXD3 (MTK_PIN_NO(243) | 3)
+#define MT7623_PIN_243_UCTS2_FUNC_SDA1 (MTK_PIN_NO(243) | 4)
+
+#define MT7623_PIN_250_GPIO250_FUNC_GPIO250 (MTK_PIN_NO(250) | 0)
+#define MT7623_PIN_250_GPIO250_FUNC_TEST_MD7 (MTK_PIN_NO(250) | 1)
+#define MT7623_PIN_250_GPIO250_FUNC_PCIE0_CLKREQ_N (MTK_PIN_NO(250) | 6)
+
+#define MT7623_PIN_251_GPIO251_FUNC_GPIO251 (MTK_PIN_NO(251) | 0)
+#define MT7623_PIN_251_GPIO251_FUNC_TEST_MD6 (MTK_PIN_NO(251) | 1)
+#define MT7623_PIN_251_GPIO251_FUNC_PCIE0_WAKE_N (MTK_PIN_NO(251) | 6)
+
+#define MT7623_PIN_252_GPIO252_FUNC_GPIO252 (MTK_PIN_NO(252) | 0)
+#define MT7623_PIN_252_GPIO252_FUNC_TEST_MD5 (MTK_PIN_NO(252) | 1)
+#define MT7623_PIN_252_GPIO252_FUNC_PCIE1_CLKREQ_N (MTK_PIN_NO(252) | 6)
+
+#define MT7623_PIN_253_GPIO253_FUNC_GPIO253 (MTK_PIN_NO(253) | 0)
+#define MT7623_PIN_253_GPIO253_FUNC_TEST_MD4 (MTK_PIN_NO(253) | 1)
+#define MT7623_PIN_253_GPIO253_FUNC_PCIE1_WAKE_N (MTK_PIN_NO(253) | 6)
+
+#define MT7623_PIN_254_GPIO254_FUNC_GPIO254 (MTK_PIN_NO(254) | 0)
+#define MT7623_PIN_254_GPIO254_FUNC_TEST_MD3 (MTK_PIN_NO(254) | 1)
+#define MT7623_PIN_254_GPIO254_FUNC_PCIE2_CLKREQ_N (MTK_PIN_NO(254) | 6)
+
+#define MT7623_PIN_255_GPIO255_FUNC_GPIO255 (MTK_PIN_NO(255) | 0)
+#define MT7623_PIN_255_GPIO255_FUNC_TEST_MD2 (MTK_PIN_NO(255) | 1)
+#define MT7623_PIN_255_GPIO255_FUNC_PCIE2_WAKE_N (MTK_PIN_NO(255) | 6)
+
+#define MT7623_PIN_256_GPIO256_FUNC_GPIO256 (MTK_PIN_NO(256) | 0)
+#define MT7623_PIN_256_GPIO256_FUNC_TEST_MD1 (MTK_PIN_NO(256) | 1)
+
+#define MT7623_PIN_257_GPIO257_FUNC_GPIO257 (MTK_PIN_NO(257) | 0)
+#define MT7623_PIN_257_GPIO257_FUNC_TEST_MD0 (MTK_PIN_NO(257) | 1)
+
+#define MT7623_PIN_261_MSDC1_INS_FUNC_GPIO261 (MTK_PIN_NO(261) | 0)
+#define MT7623_PIN_261_MSDC1_INS_FUNC_MSDC1_INS (MTK_PIN_NO(261) | 1)
+
+#define MT7623_PIN_262_G2_TXEN_FUNC_GPIO262 (MTK_PIN_NO(262) | 0)
+#define MT7623_PIN_262_G2_TXEN_FUNC_G2_TXEN (MTK_PIN_NO(262) | 1)
+
+#define MT7623_PIN_263_G2_TXD3_FUNC_GPIO263 (MTK_PIN_NO(263) | 0)
+#define MT7623_PIN_263_G2_TXD3_FUNC_G2_TXD3 (MTK_PIN_NO(263) | 1)
+
+#define MT7623_PIN_264_G2_TXD2_FUNC_GPIO264 (MTK_PIN_NO(264) | 0)
+#define MT7623_PIN_264_G2_TXD2_FUNC_G2_TXD2 (MTK_PIN_NO(264) | 1)
+
+#define MT7623_PIN_265_G2_TXD1_FUNC_GPIO265 (MTK_PIN_NO(265) | 0)
+#define MT7623_PIN_265_G2_TXD1_FUNC_G2_TXD1 (MTK_PIN_NO(265) | 1)
+
+#define MT7623_PIN_266_G2_TXD0_FUNC_GPIO266 (MTK_PIN_NO(266) | 0)
+#define MT7623_PIN_266_G2_TXD0_FUNC_G2_TXD0 (MTK_PIN_NO(266) | 1)
+
+#define MT7623_PIN_267_G2_TXCLK_FUNC_GPIO267 (MTK_PIN_NO(267) | 0)
+#define MT7623_PIN_267_G2_TXCLK_FUNC_G2_TXC (MTK_PIN_NO(267) | 1)
+
+#define MT7623_PIN_268_G2_RXCLK_FUNC_GPIO268 (MTK_PIN_NO(268) | 0)
+#define MT7623_PIN_268_G2_RXCLK_FUNC_G2_RXC (MTK_PIN_NO(268) | 1)
+
+#define MT7623_PIN_269_G2_RXD0_FUNC_GPIO269 (MTK_PIN_NO(269) | 0)
+#define MT7623_PIN_269_G2_RXD0_FUNC_G2_RXD0 (MTK_PIN_NO(269) | 1)
+
+#define MT7623_PIN_270_G2_RXD1_FUNC_GPIO270 (MTK_PIN_NO(270) | 0)
+#define MT7623_PIN_270_G2_RXD1_FUNC_G2_RXD1 (MTK_PIN_NO(270) | 1)
+
+#define MT7623_PIN_271_G2_RXD2_FUNC_GPIO271 (MTK_PIN_NO(271) | 0)
+#define MT7623_PIN_271_G2_RXD2_FUNC_G2_RXD2 (MTK_PIN_NO(271) | 1)
+
+#define MT7623_PIN_272_G2_RXD3_FUNC_GPIO272 (MTK_PIN_NO(272) | 0)
+#define MT7623_PIN_272_G2_RXD3_FUNC_G2_RXD3 (MTK_PIN_NO(272) | 1)
+
+#define MT7623_PIN_274_G2_RXDV_FUNC_GPIO274 (MTK_PIN_NO(274) | 0)
+#define MT7623_PIN_274_G2_RXDV_FUNC_G2_RXDV (MTK_PIN_NO(274) | 1)
+
+#define MT7623_PIN_275_G2_MDC_FUNC_GPIO275 (MTK_PIN_NO(275) | 0)
+#define MT7623_PIN_275_G2_MDC_FUNC_MDC (MTK_PIN_NO(275) | 1)
+
+#define MT7623_PIN_276_G2_MDIO_FUNC_GPIO276 (MTK_PIN_NO(276) | 0)
+#define MT7623_PIN_276_G2_MDIO_FUNC_MDIO (MTK_PIN_NO(276) | 1)
+
+#define MT7623_PIN_278_JTAG_RESET_FUNC_GPIO278 (MTK_PIN_NO(278) | 0)
+#define MT7623_PIN_278_JTAG_RESET_FUNC_JTAG_RESET (MTK_PIN_NO(278) | 1)
+
+#endif /* __DTS_MT7623_PINFUNC_H */
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index 1800227af9d6..b651aed9dc6b 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -55,6 +55,9 @@ struct arch_timer_cpu {
 
 	/* VGIC mapping */
 	struct irq_phys_map		*map;
+
+	/* Active IRQ state caching */
+	bool				active_cleared_last;
 };
 
 int kvm_timer_hyp_init(void);
@@ -74,4 +77,6 @@ bool kvm_timer_should_fire(struct kvm_vcpu *vcpu);
 void kvm_timer_schedule(struct kvm_vcpu *vcpu);
 void kvm_timer_unschedule(struct kvm_vcpu *vcpu);
 
+void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu);
+
 #endif
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
new file mode 100644
index 000000000000..fe389ac31489
--- /dev/null
+++ b/include/kvm/arm_pmu.h
@@ -0,0 +1,110 @@
+/*
+ * Copyright (C) 2015 Linaro Ltd.
+ * Author: Shannon Zhao <shannon.zhao@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ASM_ARM_KVM_PMU_H
+#define __ASM_ARM_KVM_PMU_H
+
+#ifdef CONFIG_KVM_ARM_PMU
+
+#include <linux/perf_event.h>
+#include <asm/perf_event.h>
+
+#define ARMV8_PMU_CYCLE_IDX		(ARMV8_PMU_MAX_COUNTERS - 1)
+
+struct kvm_pmc {
+	u8 idx;	/* index into the pmu->pmc array */
+	struct perf_event *perf_event;
+	u64 bitmask;
+};
+
+struct kvm_pmu {
+	int irq_num;
+	struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS];
+	bool ready;
+	bool irq_level;
+};
+
+#define kvm_arm_pmu_v3_ready(v)		((v)->arch.pmu.ready)
+#define kvm_arm_pmu_irq_initialized(v)	((v)->arch.pmu.irq_num >= VGIC_NR_SGIS)
+u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx);
+void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val);
+u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu);
+void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu);
+void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu);
+void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val);
+void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val);
+void kvm_pmu_overflow_set(struct kvm_vcpu *vcpu, u64 val);
+void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu);
+void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu);
+void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val);
+void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val);
+void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
+				    u64 select_idx);
+bool kvm_arm_support_pmu_v3(void);
+int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr);
+int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr);
+int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu,
+			    struct kvm_device_attr *attr);
+#else
+struct kvm_pmu {
+};
+
+#define kvm_arm_pmu_v3_ready(v)		(false)
+#define kvm_arm_pmu_irq_initialized(v)	(false)
+static inline u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu,
+					    u64 select_idx)
+{
+	return 0;
+}
+static inline void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu,
+					     u64 select_idx, u64 val) {}
+static inline u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+static inline void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) {}
+static inline void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) {}
+static inline void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val) {}
+static inline void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val) {}
+static inline void kvm_pmu_overflow_set(struct kvm_vcpu *vcpu, u64 val) {}
+static inline void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) {}
+static inline void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu) {}
+static inline void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) {}
+static inline void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) {}
+static inline void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu,
+						  u64 data, u64 select_idx) {}
+static inline bool kvm_arm_support_pmu_v3(void) { return false; }
+static inline int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu,
+					  struct kvm_device_attr *attr)
+{
+	return -ENXIO;
+}
+static inline int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu,
+					  struct kvm_device_attr *attr)
+{
+	return -ENXIO;
+}
+static inline int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu,
+					  struct kvm_device_attr *attr)
+{
+	return -ENXIO;
+}
+#endif
+
+#endif
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 13a3d537811b..281caf847fad 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -279,12 +279,6 @@ struct vgic_v2_cpu_if {
 	u32		vgic_lr[VGIC_V2_MAX_LRS];
 };
 
-/*
- * LRs are stored in reverse order in memory. make sure we index them
- * correctly.
- */
-#define VGIC_V3_LR_INDEX(lr)		(VGIC_V3_MAX_LRS - 1 - lr)
-
 struct vgic_v3_cpu_if {
 #ifdef CONFIG_KVM_ARM_VGIC_V3
 	u32		vgic_hcr;
@@ -321,6 +315,8 @@ struct vgic_cpu {
 
 	/* Protected by the distributor's irq_phys_map_lock */
 	struct list_head	irq_phys_map_list;
+
+	u64		live_lrs;
 };
 
 #define LR_EMPTY	0xff
diff --git a/include/linux/ata.h b/include/linux/ata.h
index d2992bfa1706..c1a2f345cbe6 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -487,8 +487,8 @@ enum ata_tf_protocols {
 };
 
 enum ata_ioctls {
-	ATA_IOC_GET_IO32	= 0x309,
-	ATA_IOC_SET_IO32	= 0x324,
+	ATA_IOC_GET_IO32	= 0x309, /* HDIO_GET_32BIT */
+	ATA_IOC_SET_IO32	= 0x324, /* HDIO_SET_32BIT */
 };
 
 /* core structures */
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 301de78d65f7..6c502cb13c95 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -548,6 +548,27 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 }
 #endif
 
+/**
+ * fetch_or - perform *ptr |= mask and return old value of *ptr
+ * @ptr: pointer to value
+ * @mask: mask to OR on the value
+ *
+ * cmpxchg based fetch_or, macro so it works for different integer types
+ */
+#ifndef fetch_or
+#define fetch_or(ptr, mask)						\
+({	typeof(*(ptr)) __old, __val = *(ptr);				\
+	for (;;) {							\
+		__old = cmpxchg((ptr), __val, __val | (mask));		\
+		if (__old == __val)					\
+			break;						\
+		__val = __old;						\
+	}								\
+	__old;								\
+})
+#endif
+
+
 #ifdef CONFIG_GENERIC_ATOMIC64
 #include <asm-generic/atomic64.h>
 #endif
diff --git a/include/linux/auto_dev-ioctl.h b/include/linux/auto_dev-ioctl.h
index 850f39b33e74..7caaf298f539 100644
--- a/include/linux/auto_dev-ioctl.h
+++ b/include/linux/auto_dev-ioctl.h
@@ -11,12 +11,7 @@
 #define _LINUX_AUTO_DEV_IOCTL_H
 
 #include <linux/auto_fs.h>
-
-#ifdef __KERNEL__
 #include <linux/string.h>
-#else
-#include <string.h>
-#endif /* __KERNEL__ */
 
 #define AUTOFS_DEVICE_NAME		"autofs"
 
@@ -125,7 +120,6 @@ static inline void init_autofs_dev_ioctl(struct autofs_dev_ioctl *in)
 	in->ver_minor = AUTOFS_DEV_IOCTL_VERSION_MINOR;
 	in->size = sizeof(struct autofs_dev_ioctl);
 	in->ioctlfd = -1;
-	return;
 }
 
 /*
diff --git a/include/linux/auto_fs.h b/include/linux/auto_fs.h
index fcd704d354c4..b4066bb89083 100644
--- a/include/linux/auto_fs.h
+++ b/include/linux/auto_fs.h
@@ -1,14 +1,10 @@
-/* -*- linux-c -*- ------------------------------------------------------- *
- *   
- * linux/include/linux/auto_fs.h
- *
- *   Copyright 1997 Transmeta Corporation - All Rights Reserved
+/*
+ * Copyright 1997 Transmeta Corporation - All Rights Reserved
  *
  * This file is part of the Linux kernel and is made available under
  * the terms of the GNU General Public License, version 2, or at your
  * option, any later version, incorporated herein by reference.
- *
- * ----------------------------------------------------------------------- */
+ */
 
 #ifndef _LINUX_AUTO_FS_H
 #define _LINUX_AUTO_FS_H
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 5349e6816cbb..88bc64f00bb5 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -310,6 +310,38 @@ static inline void bio_clear_flag(struct bio *bio, unsigned int bit)
 	bio->bi_flags &= ~(1U << bit);
 }
 
+static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv)
+{
+	*bv = bio_iovec(bio);
+}
+
+static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv)
+{
+	struct bvec_iter iter = bio->bi_iter;
+	int idx;
+
+	if (unlikely(!bio_multiple_segments(bio))) {
+		*bv = bio_iovec(bio);
+		return;
+	}
+
+	bio_advance_iter(bio, &iter, iter.bi_size);
+
+	if (!iter.bi_bvec_done)
+		idx = iter.bi_idx - 1;
+	else	/* in the middle of bvec */
+		idx = iter.bi_idx;
+
+	*bv = bio->bi_io_vec[idx];
+
+	/*
+	 * iter.bi_bvec_done records actual length of the last bvec
+	 * if this bio ends in the middle of one io vector
+	 */
+	if (iter.bi_bvec_done)
+		bv->bv_len = iter.bi_bvec_done;
+}
+
 enum bip_flags {
 	BIP_BLOCK_INTEGRITY	= 1 << 0, /* block layer owns integrity data */
 	BIP_MAPPED_INTEGRITY	= 1 << 1, /* ref tag has been remapped */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 29189aeace19..413c84fbc4ed 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -682,9 +682,12 @@ static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b)
 /*
  * q->prep_rq_fn return values
  */
-#define BLKPREP_OK		0	/* serve it */
-#define BLKPREP_KILL		1	/* fatal error, kill */
-#define BLKPREP_DEFER		2	/* leave on queue */
+enum {
+	BLKPREP_OK,		/* serve it */
+	BLKPREP_KILL,		/* fatal error, kill, return -EIO */
+	BLKPREP_DEFER,		/* leave on queue */
+	BLKPREP_INVALID,	/* invalid command, kill, return -EREMOTEIO */
+};
 
 extern unsigned long blk_max_low_pfn, blk_max_pfn;
 
@@ -892,7 +895,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
-	if (unlikely(rq->cmd_type == REQ_TYPE_BLOCK_PC))
+	if (unlikely(rq->cmd_type != REQ_TYPE_FS))
 		return q->limits.max_hw_sectors;
 
 	if (!q->limits.chunk_sectors || (rq->cmd_flags & REQ_DISCARD))
@@ -1369,6 +1372,13 @@ static inline void put_dev_sector(Sector p)
 	page_cache_release(p.v);
 }
 
+static inline bool __bvec_gap_to_prev(struct request_queue *q,
+				struct bio_vec *bprv, unsigned int offset)
+{
+	return offset ||
+		((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q));
+}
+
 /*
  * Check if adding a bio_vec after bprv with offset would create a gap in
  * the SG list. Most drivers don't care about this, but some do.
@@ -1378,18 +1388,22 @@ static inline bool bvec_gap_to_prev(struct request_queue *q,
 {
 	if (!queue_virt_boundary(q))
 		return false;
-	return offset ||
-		((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q));
+	return __bvec_gap_to_prev(q, bprv, offset);
 }
 
 static inline bool bio_will_gap(struct request_queue *q, struct bio *prev,
 			 struct bio *next)
 {
-	if (!bio_has_data(prev))
-		return false;
+	if (bio_has_data(prev) && queue_virt_boundary(q)) {
+		struct bio_vec pb, nb;
+
+		bio_get_last_bvec(prev, &pb);
+		bio_get_first_bvec(next, &nb);
 
-	return bvec_gap_to_prev(q, &prev->bi_io_vec[prev->bi_vcnt - 1],
-				next->bi_io_vec[0].bv_offset);
+		return __bvec_gap_to_prev(q, &pb, nb.bv_offset);
+	}
+
+	return false;
 }
 
 static inline bool req_gap_back_merge(struct request *req, struct bio *bio)
diff --git a/include/linux/cache.h b/include/linux/cache.h
index 17e7e82d2aa7..1be04f8c563a 100644
--- a/include/linux/cache.h
+++ b/include/linux/cache.h
@@ -12,10 +12,24 @@
 #define SMP_CACHE_BYTES L1_CACHE_BYTES
 #endif
 
+/*
+ * __read_mostly is used to keep rarely changing variables out of frequently
+ * updated cachelines. If an architecture doesn't support it, ignore the
+ * hint.
+ */
 #ifndef __read_mostly
 #define __read_mostly
 #endif
 
+/*
+ * __ro_after_init is used to mark things that are read-only after init (i.e.
+ * after mark_rodata_ro() has been called). These are effectively read-only,
+ * but may get written to during init, so can't live in .rodata (via "const").
+ */
+#ifndef __ro_after_init
+#define __ro_after_init __attribute__((__section__(".data..ro_after_init")))
+#endif
+
 #ifndef ____cacheline_aligned
 #define ____cacheline_aligned __attribute__((__aligned__(SMP_CACHE_BYTES)))
 #endif
diff --git a/include/linux/ccp.h b/include/linux/ccp.h
index 7f437036baa4..915af3095b39 100644
--- a/include/linux/ccp.h
+++ b/include/linux/ccp.h
@@ -33,6 +33,18 @@ struct ccp_cmd;
  */
 int ccp_present(void);
 
+#define	CCP_VSIZE 16
+#define	CCP_VMASK		((unsigned int)((1 << CCP_VSIZE) - 1))
+#define	CCP_VERSION(v, r)	((unsigned int)((v << CCP_VSIZE) \
+					       | (r & CCP_VMASK)))
+
+/**
+ * ccp_version - get the version of the CCP
+ *
+ * Returns a positive version number, or zero if no CCP
+ */
+unsigned int ccp_version(void);
+
 /**
  * ccp_enqueue_cmd - queue an operation for processing by the CCP
  *
@@ -65,6 +77,11 @@ static inline int ccp_present(void)
 	return -ENODEV;
 }
 
+static inline unsigned int ccp_version(void)
+{
+	return 0;
+}
+
 static inline int ccp_enqueue_cmd(struct ccp_cmd *cmd)
 {
 	return -ENODEV;
diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index c1ef6f14e7be..15151f3c4120 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -75,6 +75,7 @@
 #define CEPH_FEATURE_CRUSH_TUNABLES5	(1ULL<<58) /* chooseleaf stable mode */
 // duplicated since it was introduced at the same time as CEPH_FEATURE_CRUSH_TUNABLES5
 #define CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING   (1ULL<<58) /* New, v7 encoding */
+#define CEPH_FEATURE_FS_FILE_LAYOUT_V2       (1ULL<<58) /* file_layout_t */
 
 /*
  * The introduction of CEPH_FEATURE_OSD_SNAPMAPPER caused the feature
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 7f540f7f588d..789471dba6fb 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -127,6 +127,12 @@ struct cgroup_subsys_state {
 	 */
 	u64 serial_nr;
 
+	/*
+	 * Incremented by online self and children.  Used to guarantee that
+	 * parents are not offlined before their children.
+	 */
+	atomic_t online_cnt;
+
 	/* percpu_ref killing and RCU release */
 	struct rcu_head rcu_head;
 	struct work_struct destroy_work;
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index bdcf358dfce2..0d442e34c349 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -190,9 +190,9 @@ extern void clockevents_config_and_register(struct clock_event_device *dev,
 extern int clockevents_update_freq(struct clock_event_device *ce, u32 freq);
 
 static inline void
-clockevents_calc_mult_shift(struct clock_event_device *ce, u32 freq, u32 minsec)
+clockevents_calc_mult_shift(struct clock_event_device *ce, u32 freq, u32 maxsec)
 {
-	return clocks_calc_mult_shift(&ce->mult, &ce->shift, NSEC_PER_SEC, freq, minsec);
+	return clocks_calc_mult_shift(&ce->mult, &ce->shift, NSEC_PER_SEC, freq, maxsec);
 }
 
 extern void clockevents_suspend(void);
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 6013021a3b39..a307bf62974f 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -118,6 +118,23 @@ struct clocksource {
 /* simplify initialization of mask field */
 #define CLOCKSOURCE_MASK(bits) (cycle_t)((bits) < 64 ? ((1ULL<<(bits))-1) : -1)
 
+static inline u32 clocksource_freq2mult(u32 freq, u32 shift_constant, u64 from)
+{
+	/*  freq = cyc/from
+	 *  mult/2^shift  = ns/cyc
+	 *  mult = ns/cyc * 2^shift
+	 *  mult = from/freq * 2^shift
+	 *  mult = from * 2^shift / freq
+	 *  mult = (from<<shift) / freq
+	 */
+	u64 tmp = ((u64)from) << shift_constant;
+
+	tmp += freq/2; /* round for do_div */
+	do_div(tmp, freq);
+
+	return (u32)tmp;
+}
+
 /**
  * clocksource_khz2mult - calculates mult from khz and shift
  * @khz:		Clocksource frequency in KHz
@@ -128,19 +145,7 @@ struct clocksource {
  */
 static inline u32 clocksource_khz2mult(u32 khz, u32 shift_constant)
 {
-	/*  khz = cyc/(Million ns)
-	 *  mult/2^shift  = ns/cyc
-	 *  mult = ns/cyc * 2^shift
-	 *  mult = 1Million/khz * 2^shift
-	 *  mult = 1000000 * 2^shift / khz
-	 *  mult = (1000000<<shift) / khz
-	 */
-	u64 tmp = ((u64)1000000) << shift_constant;
-
-	tmp += khz/2; /* round for do_div */
-	do_div(tmp, khz);
-
-	return (u32)tmp;
+	return clocksource_freq2mult(khz, shift_constant, NSEC_PER_MSEC);
 }
 
 /**
@@ -154,19 +159,7 @@ static inline u32 clocksource_khz2mult(u32 khz, u32 shift_constant)
  */
 static inline u32 clocksource_hz2mult(u32 hz, u32 shift_constant)
 {
-	/*  hz = cyc/(Billion ns)
-	 *  mult/2^shift  = ns/cyc
-	 *  mult = ns/cyc * 2^shift
-	 *  mult = 1Billion/hz * 2^shift
-	 *  mult = 1000000000 * 2^shift / hz
-	 *  mult = (1000000000<<shift) / hz
-	 */
-	u64 tmp = ((u64)1000000000) << shift_constant;
-
-	tmp += hz/2; /* round for do_div */
-	do_div(tmp, hz);
-
-	return (u32)tmp;
+	return clocksource_freq2mult(hz, shift_constant, NSEC_PER_SEC);
 }
 
 /**
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 00b042c49ccd..b5ff9881bef8 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -20,12 +20,14 @@
 # define __pmem		__attribute__((noderef, address_space(5)))
 #ifdef CONFIG_SPARSE_RCU_POINTER
 # define __rcu		__attribute__((noderef, address_space(4)))
-#else
+#else /* CONFIG_SPARSE_RCU_POINTER */
 # define __rcu
-#endif
+#endif /* CONFIG_SPARSE_RCU_POINTER */
+# define __private	__attribute__((noderef))
 extern void __chk_user_ptr(const volatile void __user *);
 extern void __chk_io_ptr(const volatile void __iomem *);
-#else
+# define ACCESS_PRIVATE(p, member) (*((typeof((p)->member) __force *) &(p)->member))
+#else /* __CHECKER__ */
 # define __user
 # define __kernel
 # define __safe
@@ -44,7 +46,9 @@ extern void __chk_io_ptr(const volatile void __iomem *);
 # define __percpu
 # define __rcu
 # define __pmem
-#endif
+# define __private
+# define ACCESS_PRIVATE(p, member) ((p)->member)
+#endif /* __CHECKER__ */
 
 /* Indirect macros required for expanded argument pasting, eg. __LINE__. */
 #define ___PASTE(a,b) a##b
@@ -144,7 +148,7 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
  */
 #define if(cond, ...) __trace_if( (cond , ## __VA_ARGS__) )
 #define __trace_if(cond) \
-	if (__builtin_constant_p((cond)) ? !!(cond) :			\
+	if (__builtin_constant_p(!!(cond)) ? !!(cond) :			\
 	({								\
 		int ______r;						\
 		static struct ftrace_branch_data			\
@@ -263,8 +267,9 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
  * In contrast to ACCESS_ONCE these two macros will also work on aggregate
  * data types like structs or unions. If the size of the accessed data
  * type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
- * READ_ONCE() and WRITE_ONCE()  will fall back to memcpy and print a
- * compile-time warning.
+ * READ_ONCE() and WRITE_ONCE() will fall back to memcpy(). There's at
+ * least two memcpy()s: one for the __builtin_memcpy() and then one for
+ * the macro doing the copy of variable - '__u' allocated on the stack.
  *
  * Their two major use cases are: (1) Mediating communication between
  * process-level code and irq/NMI handlers, all running on the same CPU,
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index d2ca8c38f9c4..f9b1fab4388a 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -16,6 +16,7 @@
 #include <linux/node.h>
 #include <linux/compiler.h>
 #include <linux/cpumask.h>
+#include <linux/cpuhotplug.h>
 
 struct device;
 struct device_node;
@@ -27,6 +28,9 @@ struct cpu {
 	struct device dev;
 };
 
+extern void boot_cpu_init(void);
+extern void boot_cpu_state_init(void);
+
 extern int register_cpu(struct cpu *cpu, int num);
 extern struct device *get_cpu_device(unsigned cpu);
 extern bool cpu_is_hotpluggable(unsigned cpu);
@@ -74,7 +78,7 @@ enum {
 	/* migration should happen before other stuff but after perf */
 	CPU_PRI_PERF		= 20,
 	CPU_PRI_MIGRATION	= 10,
-	CPU_PRI_SMPBOOT		= 9,
+
 	/* bring up workqueues before normal notifiers and down after */
 	CPU_PRI_WORKQUEUE_UP	= 5,
 	CPU_PRI_WORKQUEUE_DOWN	= -5,
@@ -97,9 +101,7 @@ enum {
 					* Called on the new cpu, just before
 					* enabling interrupts. Must not sleep,
 					* must not fail */
-#define CPU_DYING_IDLE		0x000B /* CPU (unsigned)v dying, reached
-					* idle loop. */
-#define CPU_BROKEN		0x000C /* CPU (unsigned)v did not die properly,
+#define CPU_BROKEN		0x000B /* CPU (unsigned)v did not die properly,
 					* perhaps due to preemption. */
 
 /* Used for CPU hotplug events occurring while tasks are frozen due to a suspend
@@ -118,6 +120,7 @@ enum {
 
 
 #ifdef CONFIG_SMP
+extern bool cpuhp_tasks_frozen;
 /* Need to know about CPUs going up/down? */
 #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE)
 #define cpu_notifier(fn, pri) {					\
@@ -167,7 +170,6 @@ static inline void __unregister_cpu_notifier(struct notifier_block *nb)
 }
 #endif
 
-void smpboot_thread_init(void);
 int cpu_up(unsigned int cpu);
 void notify_cpu_starting(unsigned int cpu);
 extern void cpu_maps_update_begin(void);
@@ -177,6 +179,7 @@ extern void cpu_maps_update_done(void);
 #define cpu_notifier_register_done	cpu_maps_update_done
 
 #else	/* CONFIG_SMP */
+#define cpuhp_tasks_frozen	0
 
 #define cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
 #define __cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
@@ -215,10 +218,6 @@ static inline void cpu_notifier_register_done(void)
 {
 }
 
-static inline void smpboot_thread_init(void)
-{
-}
-
 #endif /* CONFIG_SMP */
 extern struct bus_type cpu_subsys;
 
@@ -265,11 +264,6 @@ static inline int disable_nonboot_cpus(void) { return 0; }
 static inline void enable_nonboot_cpus(void) {}
 #endif /* !CONFIG_PM_SLEEP_SMP */
 
-enum cpuhp_state {
-	CPUHP_OFFLINE,
-	CPUHP_ONLINE,
-};
-
 void cpu_startup_entry(enum cpuhp_state state);
 
 void cpu_idle_poll_ctrl(bool enable);
@@ -280,14 +274,15 @@ void arch_cpu_idle_enter(void);
 void arch_cpu_idle_exit(void);
 void arch_cpu_idle_dead(void);
 
-DECLARE_PER_CPU(bool, cpu_dead_idle);
-
 int cpu_report_state(int cpu);
 int cpu_check_up_prepare(int cpu);
 void cpu_set_state_online(int cpu);
 #ifdef CONFIG_HOTPLUG_CPU
 bool cpu_wait_death(unsigned int cpu, int seconds);
 bool cpu_report_death(void);
+void cpuhp_report_idle_dead(void);
+#else
+static inline void cpuhp_report_idle_dead(void) { }
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
 #endif /* _LINUX_CPU_H_ */
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 88a4215125bc..718e8725de8a 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -80,7 +80,6 @@ struct cpufreq_policy {
 	unsigned int		last_policy; /* policy before unplug */
 	struct cpufreq_governor	*governor; /* see below */
 	void			*governor_data;
-	bool			governor_enabled; /* governor start/stop flag */
 	char			last_governor[CPUFREQ_NAME_LEN]; /* last governor used */
 
 	struct work_struct	update; /* if update_policy() needs to be
@@ -100,10 +99,6 @@ struct cpufreq_policy {
 	 * - Any routine that will write to the policy structure and/or may take away
 	 *   the policy altogether (eg. CPU hotplug), will hold this lock in write
 	 *   mode before doing so.
-	 *
-	 * Additional rules:
-	 * - Lock should not be held across
-	 *     __cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
 	 */
 	struct rw_semaphore	rwsem;
 
@@ -464,29 +459,8 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 int cpufreq_register_governor(struct cpufreq_governor *governor);
 void cpufreq_unregister_governor(struct cpufreq_governor *governor);
 
-/* CPUFREQ DEFAULT GOVERNOR */
-/*
- * Performance governor is fallback governor if any other gov failed to auto
- * load due latency restrictions
- */
-#ifdef CONFIG_CPU_FREQ_GOV_PERFORMANCE
-extern struct cpufreq_governor cpufreq_gov_performance;
-#endif
-#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE
-#define CPUFREQ_DEFAULT_GOVERNOR	(&cpufreq_gov_performance)
-#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE)
-extern struct cpufreq_governor cpufreq_gov_powersave;
-#define CPUFREQ_DEFAULT_GOVERNOR	(&cpufreq_gov_powersave)
-#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE)
-extern struct cpufreq_governor cpufreq_gov_userspace;
-#define CPUFREQ_DEFAULT_GOVERNOR	(&cpufreq_gov_userspace)
-#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND)
-extern struct cpufreq_governor cpufreq_gov_ondemand;
-#define CPUFREQ_DEFAULT_GOVERNOR	(&cpufreq_gov_ondemand)
-#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE)
-extern struct cpufreq_governor cpufreq_gov_conservative;
-#define CPUFREQ_DEFAULT_GOVERNOR	(&cpufreq_gov_conservative)
-#endif
+struct cpufreq_governor *cpufreq_default_governor(void);
+struct cpufreq_governor *cpufreq_fallback_governor(void);
 
 /*********************************************************************
  *                     FREQUENCY TABLE HELPERS                       *
@@ -525,16 +499,6 @@ static inline void dev_pm_opp_free_cpufreq_table(struct device *dev,
 }
 #endif
 
-static inline bool cpufreq_next_valid(struct cpufreq_frequency_table **pos)
-{
-	while ((*pos)->frequency != CPUFREQ_TABLE_END)
-		if ((*pos)->frequency != CPUFREQ_ENTRY_INVALID)
-			return true;
-		else
-			(*pos)++;
-	return false;
-}
-
 /*
  * cpufreq_for_each_entry -	iterate over a cpufreq_frequency_table
  * @pos:	the cpufreq_frequency_table * to use as a loop cursor.
@@ -551,8 +515,11 @@ static inline bool cpufreq_next_valid(struct cpufreq_frequency_table **pos)
  * @table:      the cpufreq_frequency_table * to iterate over.
  */
 
-#define cpufreq_for_each_valid_entry(pos, table)	\
-	for (pos = table; cpufreq_next_valid(&pos); pos++)
+#define cpufreq_for_each_valid_entry(pos, table)			\
+	for (pos = table; pos->frequency != CPUFREQ_TABLE_END; pos++)	\
+		if (pos->frequency == CPUFREQ_ENTRY_INVALID)		\
+			continue;					\
+		else
 
 int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
 				    struct cpufreq_frequency_table *table);
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
new file mode 100644
index 000000000000..5d68e15e46b7
--- /dev/null
+++ b/include/linux/cpuhotplug.h
@@ -0,0 +1,93 @@
+#ifndef __CPUHOTPLUG_H
+#define __CPUHOTPLUG_H
+
+enum cpuhp_state {
+	CPUHP_OFFLINE,
+	CPUHP_CREATE_THREADS,
+	CPUHP_NOTIFY_PREPARE,
+	CPUHP_BRINGUP_CPU,
+	CPUHP_AP_IDLE_DEAD,
+	CPUHP_AP_OFFLINE,
+	CPUHP_AP_NOTIFY_STARTING,
+	CPUHP_AP_ONLINE,
+	CPUHP_TEARDOWN_CPU,
+	CPUHP_AP_ONLINE_IDLE,
+	CPUHP_AP_SMPBOOT_THREADS,
+	CPUHP_AP_NOTIFY_ONLINE,
+	CPUHP_AP_ONLINE_DYN,
+	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 30,
+	CPUHP_ONLINE,
+};
+
+int __cpuhp_setup_state(enum cpuhp_state state,	const char *name, bool invoke,
+			int (*startup)(unsigned int cpu),
+			int (*teardown)(unsigned int cpu));
+
+/**
+ * cpuhp_setup_state - Setup hotplug state callbacks with calling the callbacks
+ * @state:	The state for which the calls are installed
+ * @name:	Name of the callback (will be used in debug output)
+ * @startup:	startup callback function
+ * @teardown:	teardown callback function
+ *
+ * Installs the callback functions and invokes the startup callback on
+ * the present cpus which have already reached the @state.
+ */
+static inline int cpuhp_setup_state(enum cpuhp_state state,
+				    const char *name,
+				    int (*startup)(unsigned int cpu),
+				    int (*teardown)(unsigned int cpu))
+{
+	return __cpuhp_setup_state(state, name, true, startup, teardown);
+}
+
+/**
+ * cpuhp_setup_state_nocalls - Setup hotplug state callbacks without calling the
+ *			       callbacks
+ * @state:	The state for which the calls are installed
+ * @name:	Name of the callback.
+ * @startup:	startup callback function
+ * @teardown:	teardown callback function
+ *
+ * Same as @cpuhp_setup_state except that no calls are executed are invoked
+ * during installation of this callback. NOP if SMP=n or HOTPLUG_CPU=n.
+ */
+static inline int cpuhp_setup_state_nocalls(enum cpuhp_state state,
+					    const char *name,
+					    int (*startup)(unsigned int cpu),
+					    int (*teardown)(unsigned int cpu))
+{
+	return __cpuhp_setup_state(state, name, false, startup, teardown);
+}
+
+void __cpuhp_remove_state(enum cpuhp_state state, bool invoke);
+
+/**
+ * cpuhp_remove_state - Remove hotplug state callbacks and invoke the teardown
+ * @state:	The state for which the calls are removed
+ *
+ * Removes the callback functions and invokes the teardown callback on
+ * the present cpus which have already reached the @state.
+ */
+static inline void cpuhp_remove_state(enum cpuhp_state state)
+{
+	__cpuhp_remove_state(state, true);
+}
+
+/**
+ * cpuhp_remove_state_nocalls - Remove hotplug state callbacks without invoking
+ *				teardown
+ * @state:	The state for which the calls are removed
+ */
+static inline void cpuhp_remove_state_nocalls(enum cpuhp_state state)
+{
+	__cpuhp_remove_state(state, false);
+}
+
+#ifdef CONFIG_SMP
+void cpuhp_online_idle(enum cpuhp_state state);
+#else
+static inline void cpuhp_online_idle(enum cpuhp_state state) { }
+#endif
+
+#endif
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 85a868ccb493..fea160ee5803 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -137,6 +137,8 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 	task_unlock(current);
 }
 
+extern void cpuset_post_attach_flush(void);
+
 #else /* !CONFIG_CPUSETS */
 
 static inline bool cpusets_enabled(void) { return false; }
@@ -243,6 +245,10 @@ static inline bool read_mems_allowed_retry(unsigned int seq)
 	return false;
 }
 
+static inline void cpuset_post_attach_flush(void)
+{
+}
+
 #endif /* !CONFIG_CPUSETS */
 
 #endif /* _LINUX_CPUSET_H */
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index e71cb70a1ac2..99c94899ad0f 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -54,7 +54,6 @@
 #define CRYPTO_ALG_TYPE_AHASH		0x0000000a
 #define CRYPTO_ALG_TYPE_RNG		0x0000000c
 #define CRYPTO_ALG_TYPE_AKCIPHER	0x0000000d
-#define CRYPTO_ALG_TYPE_PCOMPRESS	0x0000000f
 
 #define CRYPTO_ALG_TYPE_HASH_MASK	0x0000000e
 #define CRYPTO_ALG_TYPE_AHASH_MASK	0x0000000c
@@ -137,7 +136,6 @@ struct scatterlist;
 struct crypto_ablkcipher;
 struct crypto_async_request;
 struct crypto_blkcipher;
-struct crypto_hash;
 struct crypto_tfm;
 struct crypto_type;
 struct skcipher_givcrypt_request;
@@ -187,11 +185,6 @@ struct cipher_desc {
 	void *info;
 };
 
-struct hash_desc {
-	struct crypto_hash *tfm;
-	u32 flags;
-};
-
 /**
  * DOC: Block Cipher Algorithm Definitions
  *
@@ -519,18 +512,6 @@ struct cipher_tfm {
 	void (*cit_decrypt_one)(struct crypto_tfm *tfm, u8 *dst, const u8 *src);
 };
 
-struct hash_tfm {
-	int (*init)(struct hash_desc *desc);
-	int (*update)(struct hash_desc *desc,
-		      struct scatterlist *sg, unsigned int nsg);
-	int (*final)(struct hash_desc *desc, u8 *out);
-	int (*digest)(struct hash_desc *desc, struct scatterlist *sg,
-		      unsigned int nsg, u8 *out);
-	int (*setkey)(struct crypto_hash *tfm, const u8 *key,
-		      unsigned int keylen);
-	unsigned int digestsize;
-};
-
 struct compress_tfm {
 	int (*cot_compress)(struct crypto_tfm *tfm,
 	                    const u8 *src, unsigned int slen,
@@ -543,7 +524,6 @@ struct compress_tfm {
 #define crt_ablkcipher	crt_u.ablkcipher
 #define crt_blkcipher	crt_u.blkcipher
 #define crt_cipher	crt_u.cipher
-#define crt_hash	crt_u.hash
 #define crt_compress	crt_u.compress
 
 struct crypto_tfm {
@@ -554,7 +534,6 @@ struct crypto_tfm {
 		struct ablkcipher_tfm ablkcipher;
 		struct blkcipher_tfm blkcipher;
 		struct cipher_tfm cipher;
-		struct hash_tfm hash;
 		struct compress_tfm compress;
 	} crt_u;
 
@@ -581,10 +560,6 @@ struct crypto_comp {
 	struct crypto_tfm base;
 };
 
-struct crypto_hash {
-	struct crypto_tfm base;
-};
-
 enum {
 	CRYPTOA_UNSPEC,
 	CRYPTOA_ALG,
@@ -1577,233 +1552,6 @@ static inline void crypto_cipher_decrypt_one(struct crypto_cipher *tfm,
 						dst, src);
 }
 
-/**
- * DOC: Synchronous Message Digest API
- *
- * The synchronous message digest API is used with the ciphers of type
- * CRYPTO_ALG_TYPE_HASH (listed as type "hash" in /proc/crypto)
- */
-
-static inline struct crypto_hash *__crypto_hash_cast(struct crypto_tfm *tfm)
-{
-	return (struct crypto_hash *)tfm;
-}
-
-static inline struct crypto_hash *crypto_hash_cast(struct crypto_tfm *tfm)
-{
-	BUG_ON((crypto_tfm_alg_type(tfm) ^ CRYPTO_ALG_TYPE_HASH) &
-	       CRYPTO_ALG_TYPE_HASH_MASK);
-	return __crypto_hash_cast(tfm);
-}
-
-/**
- * crypto_alloc_hash() - allocate synchronous message digest handle
- * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
- *	      message digest cipher
- * @type: specifies the type of the cipher
- * @mask: specifies the mask for the cipher
- *
- * Allocate a cipher handle for a message digest. The returned struct
- * crypto_hash is the cipher handle that is required for any subsequent
- * API invocation for that message digest.
- *
- * Return: allocated cipher handle in case of success; IS_ERR() is true in case
- * of an error, PTR_ERR() returns the error code.
- */
-static inline struct crypto_hash *crypto_alloc_hash(const char *alg_name,
-						    u32 type, u32 mask)
-{
-	type &= ~CRYPTO_ALG_TYPE_MASK;
-	mask &= ~CRYPTO_ALG_TYPE_MASK;
-	type |= CRYPTO_ALG_TYPE_HASH;
-	mask |= CRYPTO_ALG_TYPE_HASH_MASK;
-
-	return __crypto_hash_cast(crypto_alloc_base(alg_name, type, mask));
-}
-
-static inline struct crypto_tfm *crypto_hash_tfm(struct crypto_hash *tfm)
-{
-	return &tfm->base;
-}
-
-/**
- * crypto_free_hash() - zeroize and free message digest handle
- * @tfm: cipher handle to be freed
- */
-static inline void crypto_free_hash(struct crypto_hash *tfm)
-{
-	crypto_free_tfm(crypto_hash_tfm(tfm));
-}
-
-/**
- * crypto_has_hash() - Search for the availability of a message digest
- * @alg_name: is the cra_name / name or cra_driver_name / driver name of the
- *	      message digest cipher
- * @type: specifies the type of the cipher
- * @mask: specifies the mask for the cipher
- *
- * Return: true when the message digest cipher is known to the kernel crypto
- *	   API; false otherwise
- */
-static inline int crypto_has_hash(const char *alg_name, u32 type, u32 mask)
-{
-	type &= ~CRYPTO_ALG_TYPE_MASK;
-	mask &= ~CRYPTO_ALG_TYPE_MASK;
-	type |= CRYPTO_ALG_TYPE_HASH;
-	mask |= CRYPTO_ALG_TYPE_HASH_MASK;
-
-	return crypto_has_alg(alg_name, type, mask);
-}
-
-static inline struct hash_tfm *crypto_hash_crt(struct crypto_hash *tfm)
-{
-	return &crypto_hash_tfm(tfm)->crt_hash;
-}
-
-/**
- * crypto_hash_blocksize() - obtain block size for message digest
- * @tfm: cipher handle
- *
- * The block size for the message digest cipher referenced with the cipher
- * handle is returned.
- *
- * Return: block size of cipher
- */
-static inline unsigned int crypto_hash_blocksize(struct crypto_hash *tfm)
-{
-	return crypto_tfm_alg_blocksize(crypto_hash_tfm(tfm));
-}
-
-static inline unsigned int crypto_hash_alignmask(struct crypto_hash *tfm)
-{
-	return crypto_tfm_alg_alignmask(crypto_hash_tfm(tfm));
-}
-
-/**
- * crypto_hash_digestsize() - obtain message digest size
- * @tfm: cipher handle
- *
- * The size for the message digest created by the message digest cipher
- * referenced with the cipher handle is returned.
- *
- * Return: message digest size
- */
-static inline unsigned int crypto_hash_digestsize(struct crypto_hash *tfm)
-{
-	return crypto_hash_crt(tfm)->digestsize;
-}
-
-static inline u32 crypto_hash_get_flags(struct crypto_hash *tfm)
-{
-	return crypto_tfm_get_flags(crypto_hash_tfm(tfm));
-}
-
-static inline void crypto_hash_set_flags(struct crypto_hash *tfm, u32 flags)
-{
-	crypto_tfm_set_flags(crypto_hash_tfm(tfm), flags);
-}
-
-static inline void crypto_hash_clear_flags(struct crypto_hash *tfm, u32 flags)
-{
-	crypto_tfm_clear_flags(crypto_hash_tfm(tfm), flags);
-}
-
-/**
- * crypto_hash_init() - (re)initialize message digest handle
- * @desc: cipher request handle that to be filled by caller --
- *	  desc.tfm is filled with the hash cipher handle;
- *	  desc.flags is filled with either CRYPTO_TFM_REQ_MAY_SLEEP or 0.
- *
- * The call (re-)initializes the message digest referenced by the hash cipher
- * request handle. Any potentially existing state created by previous
- * operations is discarded.
- *
- * Return: 0 if the message digest initialization was successful; < 0 if an
- *	   error occurred
- */
-static inline int crypto_hash_init(struct hash_desc *desc)
-{
-	return crypto_hash_crt(desc->tfm)->init(desc);
-}
-
-/**
- * crypto_hash_update() - add data to message digest for processing
- * @desc: cipher request handle
- * @sg: scatter / gather list pointing to the data to be added to the message
- *      digest
- * @nbytes: number of bytes to be processed from @sg
- *
- * Updates the message digest state of the cipher handle pointed to by the
- * hash cipher request handle with the input data pointed to by the
- * scatter/gather list.
- *
- * Return: 0 if the message digest update was successful; < 0 if an error
- *	   occurred
- */
-static inline int crypto_hash_update(struct hash_desc *desc,
-				     struct scatterlist *sg,
-				     unsigned int nbytes)
-{
-	return crypto_hash_crt(desc->tfm)->update(desc, sg, nbytes);
-}
-
-/**
- * crypto_hash_final() - calculate message digest
- * @desc: cipher request handle
- * @out: message digest output buffer -- The caller must ensure that the out
- *	 buffer has a sufficient size (e.g. by using the crypto_hash_digestsize
- *	 function).
- *
- * Finalize the message digest operation and create the message digest
- * based on all data added to the cipher handle. The message digest is placed
- * into the output buffer.
- *
- * Return: 0 if the message digest creation was successful; < 0 if an error
- *	   occurred
- */
-static inline int crypto_hash_final(struct hash_desc *desc, u8 *out)
-{
-	return crypto_hash_crt(desc->tfm)->final(desc, out);
-}
-
-/**
- * crypto_hash_digest() - calculate message digest for a buffer
- * @desc: see crypto_hash_final()
- * @sg: see crypto_hash_update()
- * @nbytes:  see crypto_hash_update()
- * @out: see crypto_hash_final()
- *
- * This function is a "short-hand" for the function calls of crypto_hash_init,
- * crypto_hash_update and crypto_hash_final. The parameters have the same
- * meaning as discussed for those separate three functions.
- *
- * Return: 0 if the message digest creation was successful; < 0 if an error
- *	   occurred
- */
-static inline int crypto_hash_digest(struct hash_desc *desc,
-				     struct scatterlist *sg,
-				     unsigned int nbytes, u8 *out)
-{
-	return crypto_hash_crt(desc->tfm)->digest(desc, sg, nbytes, out);
-}
-
-/**
- * crypto_hash_setkey() - set key for message digest
- * @hash: cipher handle
- * @key: buffer holding the key
- * @keylen: length of the key in bytes
- *
- * The caller provided key is set for the message digest cipher. The cipher
- * handle must point to a keyed hash in order for this function to succeed.
- *
- * Return: 0 if the setting of the key was successful; < 0 if an error occurred
- */
-static inline int crypto_hash_setkey(struct crypto_hash *hash,
-				     const u8 *key, unsigned int keylen)
-{
-	return crypto_hash_crt(hash)->setkey(hash, key, keylen);
-}
-
 static inline struct crypto_comp *__crypto_comp_cast(struct crypto_tfm *tfm)
 {
 	return (struct crypto_comp *)tfm;
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 818e45078929..636dd59ab505 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -7,7 +7,7 @@
 
 ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t,
 		  get_block_t, dio_iodone_t, int flags);
-int dax_clear_blocks(struct inode *, sector_t block, long size);
+int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size);
 int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
 int dax_truncate_page(struct inode *, loff_t from, get_block_t);
 int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
@@ -52,6 +52,8 @@ static inline bool dax_mapping(struct address_space *mapping)
 {
 	return mapping->host && IS_DAX(mapping->host);
 }
-int dax_writeback_mapping_range(struct address_space *mapping, loff_t start,
-		loff_t end);
+
+struct writeback_control;
+int dax_writeback_mapping_range(struct address_space *mapping,
+		struct block_device *bdev, struct writeback_control *wbc);
 #endif
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 7781ce110503..c4b5f4b3f8f8 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -409,9 +409,7 @@ static inline bool d_mountpoint(const struct dentry *dentry)
  */
 static inline unsigned __d_entry_type(const struct dentry *dentry)
 {
-	unsigned type = READ_ONCE(dentry->d_flags);
-	smp_rmb();
-	return type & DCACHE_ENTRY_TYPE;
+	return dentry->d_flags & DCACHE_ENTRY_TYPE;
 }
 
 static inline bool d_is_miss(const struct dentry *dentry)
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index ec1c61c87d89..0830c9e86f0d 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -124,6 +124,8 @@ struct dm_dev {
 	char name[16];
 };
 
+dev_t dm_get_dev_t(const char *path);
+
 /*
  * Constructors should call these functions to ensure destination devices
  * are opened/closed correctly.
@@ -190,6 +192,13 @@ struct target_type {
 #define dm_target_is_immutable(type)	((type)->features & DM_TARGET_IMMUTABLE)
 
 /*
+ * Indicates that a target may replace any target; even immutable targets.
+ * .map, .map_rq, .clone_and_map_rq and .release_clone_rq are all defined.
+ */
+#define DM_TARGET_WILDCARD		0x00000008
+#define dm_target_is_wildcard(type)	((type)->features & DM_TARGET_WILDCARD)
+
+/*
  * Some targets need to be sent the same WRITE bio severals times so
  * that they can send copies of it to different devices.  This function
  * examines any supplied bio and returns the number of copies of it the
@@ -231,10 +240,10 @@ struct dm_target {
 	unsigned num_write_same_bios;
 
 	/*
-	 * The minimum number of extra bytes allocated in each bio for the
-	 * target to use.  dm_per_bio_data returns the data location.
+	 * The minimum number of extra bytes allocated in each io for the
+	 * target to use.
 	 */
-	unsigned per_bio_data_size;
+	unsigned per_io_data_size;
 
 	/*
 	 * If defined, this function is called to find out how many
diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h
index 251a2090a554..e0ee0b3000b2 100644
--- a/include/linux/devpts_fs.h
+++ b/include/linux/devpts_fs.h
@@ -19,6 +19,8 @@
 
 int devpts_new_index(struct inode *ptmx_inode);
 void devpts_kill_index(struct inode *ptmx_inode, int idx);
+void devpts_add_ref(struct inode *ptmx_inode);
+void devpts_del_ref(struct inode *ptmx_inode);
 /* mknod in devpts */
 struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
 		void *priv);
@@ -32,6 +34,8 @@ void devpts_pty_kill(struct inode *inode);
 /* Dummy stubs in the no-pty case */
 static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; }
 static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { }
+static inline void devpts_add_ref(struct inode *ptmx_inode) { }
+static inline void devpts_del_ref(struct inode *ptmx_inode) { }
 static inline struct inode *devpts_pty_new(struct inode *ptmx_inode,
 		dev_t device, int index, void *priv)
 {
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 75857cda38e9..5e45cf930a3f 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -386,7 +386,7 @@ static inline void dma_free_attrs(struct device *dev, size_t size,
 	if (dma_release_from_coherent(dev, get_order(size), cpu_addr))
 		return;
 
-	if (!ops->free)
+	if (!ops->free || !cpu_addr)
 		return;
 
 	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
@@ -641,31 +641,40 @@ static inline void dmam_release_declared_memory(struct device *dev)
 }
 #endif /* CONFIG_HAVE_GENERIC_DMA_COHERENT */
 
-static inline void *dma_alloc_writecombine(struct device *dev, size_t size,
-					   dma_addr_t *dma_addr, gfp_t gfp)
+static inline void *dma_alloc_wc(struct device *dev, size_t size,
+				 dma_addr_t *dma_addr, gfp_t gfp)
 {
 	DEFINE_DMA_ATTRS(attrs);
 	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
 	return dma_alloc_attrs(dev, size, dma_addr, gfp, &attrs);
 }
+#ifndef dma_alloc_writecombine
+#define dma_alloc_writecombine dma_alloc_wc
+#endif
 
-static inline void dma_free_writecombine(struct device *dev, size_t size,
-					 void *cpu_addr, dma_addr_t dma_addr)
+static inline void dma_free_wc(struct device *dev, size_t size,
+			       void *cpu_addr, dma_addr_t dma_addr)
 {
 	DEFINE_DMA_ATTRS(attrs);
 	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
 	return dma_free_attrs(dev, size, cpu_addr, dma_addr, &attrs);
 }
+#ifndef dma_free_writecombine
+#define dma_free_writecombine dma_free_wc
+#endif
 
-static inline int dma_mmap_writecombine(struct device *dev,
-					struct vm_area_struct *vma,
-					void *cpu_addr, dma_addr_t dma_addr,
-					size_t size)
+static inline int dma_mmap_wc(struct device *dev,
+			      struct vm_area_struct *vma,
+			      void *cpu_addr, dma_addr_t dma_addr,
+			      size_t size)
 {
 	DEFINE_DMA_ATTRS(attrs);
 	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
 	return dma_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, &attrs);
 }
+#ifndef dma_mmap_writecombine
+#define dma_mmap_writecombine dma_mmap_wc
+#endif
 
 #ifdef CONFIG_NEED_DMA_MAP_STATE
 #define DEFINE_DMA_UNMAP_ADDR(ADDR_NAME)        dma_addr_t ADDR_NAME
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 569b5a866bb1..47be3ad7d3e5 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1199,7 +1199,10 @@ int efivar_entry_iter(int (*func)(struct efivar_entry *, void *),
 struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid,
 				       struct list_head *head, bool remove);
 
-bool efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len);
+bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
+		     unsigned long data_size);
+bool efivar_variable_is_removable(efi_guid_t vendor, const char *name,
+				  size_t len);
 
 extern struct work_struct efivar_work;
 void efivar_run_worker(void);
diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h
index 3159a7dba034..9f4956d8601c 100644
--- a/include/linux/fault-inject.h
+++ b/include/linux/fault-inject.h
@@ -62,10 +62,9 @@ static inline struct dentry *fault_create_debugfs_attr(const char *name,
 #endif /* CONFIG_FAULT_INJECTION */
 
 #ifdef CONFIG_FAILSLAB
-extern bool should_failslab(size_t size, gfp_t gfpflags, unsigned long flags);
+extern bool should_failslab(struct kmem_cache *s, gfp_t gfpflags);
 #else
-static inline bool should_failslab(size_t size, gfp_t gfpflags,
-				unsigned long flags)
+static inline bool should_failslab(struct kmem_cache *s, gfp_t gfpflags)
 {
 	return false;
 }
diff --git a/include/linux/fb.h b/include/linux/fb.h
index 55433f86f0a3..dfe88351341f 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -296,9 +296,6 @@ struct fb_ops {
 	/* Draws cursor */
 	int (*fb_cursor) (struct fb_info *info, struct fb_cursor *cursor);
 
-	/* Rotates the display */
-	void (*fb_rotate)(struct fb_info *info, int angle);
-
 	/* wait for blit idle, optional */
 	int (*fb_sync)(struct fb_info *info);
 
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 6b7e89f45aa4..533c4408529a 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -220,10 +220,7 @@ struct fsnotify_mark {
 	/* List of marks by group->i_fsnotify_marks. Also reused for queueing
 	 * mark into destroy_list when it's waiting for the end of SRCU period
 	 * before it can be freed. [group->mark_mutex] */
-	union {
-		struct list_head g_list;
-		struct rcu_head g_rcu;
-	};
+	struct list_head g_list;
 	/* Protects inode / mnt pointers, flags, masks */
 	spinlock_t lock;
 	/* List of marks for inode / vfsmount [obj_lock] */
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 81de7123959d..6d9df3f7e334 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -603,6 +603,7 @@ extern int ftrace_arch_read_dyn_info(char *buf, int size);
 
 extern int skip_trace(unsigned long ip);
 extern void ftrace_module_init(struct module *mod);
+extern void ftrace_module_enable(struct module *mod);
 extern void ftrace_release_mod(struct module *mod);
 
 extern void ftrace_disable_daemon(void);
@@ -612,8 +613,9 @@ static inline int skip_trace(unsigned long ip) { return 0; }
 static inline int ftrace_force_update(void) { return 0; }
 static inline void ftrace_disable_daemon(void) { }
 static inline void ftrace_enable_daemon(void) { }
-static inline void ftrace_release_mod(struct module *mod) {}
-static inline void ftrace_module_init(struct module *mod) {}
+static inline void ftrace_module_init(struct module *mod) { }
+static inline void ftrace_module_enable(struct module *mod) { }
+static inline void ftrace_release_mod(struct module *mod) { }
 static inline __init int register_ftrace_command(struct ftrace_func_command *cmd)
 {
 	return -EINVAL;
@@ -711,6 +713,18 @@ static inline void __ftrace_enabled_restore(int enabled)
 #define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5))
 #define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6))
 
+static inline unsigned long get_lock_parent_ip(void)
+{
+	unsigned long addr = CALLER_ADDR0;
+
+	if (!in_lock_functions(addr))
+		return addr;
+	addr = CALLER_ADDR1;
+	if (!in_lock_functions(addr))
+		return addr;
+	return CALLER_ADDR2;
+}
+
 #ifdef CONFIG_IRQSOFF_TRACER
   extern void time_hardirqs_on(unsigned long a0, unsigned long a1);
   extern void time_hardirqs_off(unsigned long a0, unsigned long a1);
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index af1f2b24bbe4..bb16dfeb917e 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -9,6 +9,11 @@
 
 struct vm_area_struct;
 
+/*
+ * In case of changes, please don't forget to update
+ * include/trace/events/mmflags.h and tools/perf/builtin-kmem.c
+ */
+
 /* Plain integer GFP bitmasks. Do not use this directly. */
 #define ___GFP_DMA		0x01u
 #define ___GFP_HIGHMEM		0x02u
@@ -48,7 +53,6 @@ struct vm_area_struct;
 #define __GFP_DMA	((__force gfp_t)___GFP_DMA)
 #define __GFP_HIGHMEM	((__force gfp_t)___GFP_HIGHMEM)
 #define __GFP_DMA32	((__force gfp_t)___GFP_DMA32)
-#define __GFP_MOVABLE	((__force gfp_t)___GFP_MOVABLE)  /* Page is movable */
 #define __GFP_MOVABLE	((__force gfp_t)___GFP_MOVABLE)  /* ZONE_MOVABLE allowed */
 #define GFP_ZONEMASK	(__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE)
 
@@ -515,13 +519,7 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp);
 void drain_all_pages(struct zone *zone);
 void drain_local_pages(struct zone *zone);
 
-#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 void page_alloc_init_late(void);
-#else
-static inline void page_alloc_init_late(void)
-{
-}
-#endif
 
 /*
  * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what
diff --git a/include/linux/init.h b/include/linux/init.h
index b449f378f995..aedb254abc37 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -142,6 +142,10 @@ void prepare_namespace(void);
 void __init load_default_modules(void);
 int __init init_rootfs(void);
 
+#ifdef CONFIG_DEBUG_RODATA
+void mark_rodata_ro(void);
+#endif
+
 extern void (*late_time_init)(void);
 
 extern bool initcall_debug;
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 821273ca4873..2d9b650047a5 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -235,6 +235,9 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 /* low 64 bit */
 #define dma_frcd_page_addr(d) (d & (((u64)-1) << PAGE_SHIFT))
 
+/* PRS_REG */
+#define DMA_PRS_PPR	((u32)1)
+
 #define IOMMU_WAIT_OP(iommu, offset, op, cond, sts)			\
 do {									\
 	cycles_t start_time = get_cycles();				\
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 0e95fcc75b2a..358076eda364 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -125,6 +125,16 @@ struct irqaction {
 
 extern irqreturn_t no_action(int cpl, void *dev_id);
 
+/*
+ * If a (PCI) device interrupt is not connected we set dev->irq to
+ * IRQ_NOTCONNECTED. This causes request_irq() to fail with -ENOTCONN, so we
+ * can distingiush that case from other error returns.
+ *
+ * 0x80000000 is guaranteed to be outside the available range of interrupts
+ * and easy to distinguish from other possible incorrect values.
+ */
+#define IRQ_NOTCONNECTED	(1U << 31)
+
 extern int __must_check
 request_threaded_irq(unsigned int irq, irq_handler_t handler,
 		     irq_handler_t thread_fn,
diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 24bea087e7af..0b65543dc6cf 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -20,6 +20,7 @@ struct resource {
 	resource_size_t end;
 	const char *name;
 	unsigned long flags;
+	unsigned long desc;
 	struct resource *parent, *sibling, *child;
 };
 
@@ -49,12 +50,19 @@ struct resource {
 #define IORESOURCE_WINDOW	0x00200000	/* forwarded by bridge */
 #define IORESOURCE_MUXED	0x00400000	/* Resource is software muxed */
 
+#define IORESOURCE_EXT_TYPE_BITS 0x01000000	/* Resource extended types */
+#define IORESOURCE_SYSRAM	0x01000000	/* System RAM (modifier) */
+
 #define IORESOURCE_EXCLUSIVE	0x08000000	/* Userland may not map this resource */
+
 #define IORESOURCE_DISABLED	0x10000000
 #define IORESOURCE_UNSET	0x20000000	/* No address assigned yet */
 #define IORESOURCE_AUTO		0x40000000
 #define IORESOURCE_BUSY		0x80000000	/* Driver has marked this resource busy */
 
+/* I/O resource extended types */
+#define IORESOURCE_SYSTEM_RAM		(IORESOURCE_MEM|IORESOURCE_SYSRAM)
+
 /* PnP IRQ specific bits (IORESOURCE_BITS) */
 #define IORESOURCE_IRQ_HIGHEDGE		(1<<0)
 #define IORESOURCE_IRQ_LOWEDGE		(1<<1)
@@ -98,13 +106,27 @@ struct resource {
 
 /* PCI ROM control bits (IORESOURCE_BITS) */
 #define IORESOURCE_ROM_ENABLE		(1<<0)	/* ROM is enabled, same as PCI_ROM_ADDRESS_ENABLE */
-#define IORESOURCE_ROM_SHADOW		(1<<1)	/* ROM is copy at C000:0 */
-#define IORESOURCE_ROM_COPY		(1<<2)	/* ROM is alloc'd copy, resource field overlaid */
-#define IORESOURCE_ROM_BIOS_COPY	(1<<3)	/* ROM is BIOS copy, resource field overlaid */
+#define IORESOURCE_ROM_SHADOW		(1<<1)	/* Use RAM image, not ROM BAR */
 
 /* PCI control bits.  Shares IORESOURCE_BITS with above PCI ROM.  */
 #define IORESOURCE_PCI_FIXED		(1<<4)	/* Do not move resource */
 
+/*
+ * I/O Resource Descriptors
+ *
+ * Descriptors are used by walk_iomem_res_desc() and region_intersects()
+ * for searching a specific resource range in the iomem table.  Assign
+ * a new descriptor when a resource range supports the search interfaces.
+ * Otherwise, resource.desc must be set to IORES_DESC_NONE (0).
+ */
+enum {
+	IORES_DESC_NONE				= 0,
+	IORES_DESC_CRASH_KERNEL			= 1,
+	IORES_DESC_ACPI_TABLES			= 2,
+	IORES_DESC_ACPI_NV_STORAGE		= 3,
+	IORES_DESC_PERSISTENT_MEMORY		= 4,
+	IORES_DESC_PERSISTENT_MEMORY_LEGACY	= 5,
+};
 
 /* helpers to define resources */
 #define DEFINE_RES_NAMED(_start, _size, _name, _flags)			\
@@ -113,6 +135,7 @@ struct resource {
 		.end = (_start) + (_size) - 1,				\
 		.name = (_name),					\
 		.flags = (_flags),					\
+		.desc = IORES_DESC_NONE,				\
 	}
 
 #define DEFINE_RES_IO_NAMED(_start, _size, _name)			\
@@ -149,6 +172,7 @@ extern void reserve_region_with_split(struct resource *root,
 extern struct resource *insert_resource_conflict(struct resource *parent, struct resource *new);
 extern int insert_resource(struct resource *parent, struct resource *new);
 extern void insert_resource_expand_to_fit(struct resource *root, struct resource *new);
+extern int remove_resource(struct resource *old);
 extern void arch_remove_reservations(struct resource *avail);
 extern int allocate_resource(struct resource *root, struct resource *new,
 			     resource_size_t size, resource_size_t min,
@@ -170,6 +194,10 @@ static inline unsigned long resource_type(const struct resource *res)
 {
 	return res->flags & IORESOURCE_TYPE_BITS;
 }
+static inline unsigned long resource_ext_type(const struct resource *res)
+{
+	return res->flags & IORESOURCE_EXT_TYPE_BITS;
+}
 /* True iff r1 completely contains r2 */
 static inline bool resource_contains(struct resource *r1, struct resource *r2)
 {
@@ -239,8 +267,8 @@ extern int
 walk_system_ram_res(u64 start, u64 end, void *arg,
 		    int (*func)(u64, u64, void *));
 extern int
-walk_iomem_res(char *name, unsigned long flags, u64 start, u64 end, void *arg,
-	       int (*func)(u64, u64, void *));
+walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, u64 end,
+		    void *arg, int (*func)(u64, u64, void *));
 
 /* True if any part of r1 overlaps r2 */
 static inline bool resource_overlaps(struct resource *r1, struct resource *r2)
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 3c1c96786248..c4de62348ff2 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -133,17 +133,23 @@ struct irq_domain;
  *			Use accessor functions to deal with it
  * @node:		node index useful for balancing
  * @handler_data:	per-IRQ data for the irq_chip methods
- * @affinity:		IRQ affinity on SMP
+ * @affinity:		IRQ affinity on SMP. If this is an IPI
+ *			related irq, then this is the mask of the
+ *			CPUs to which an IPI can be sent.
  * @msi_desc:		MSI descriptor
+ * @ipi_offset:		Offset of first IPI target cpu in @affinity. Optional.
  */
 struct irq_common_data {
-	unsigned int		state_use_accessors;
+	unsigned int		__private state_use_accessors;
 #ifdef CONFIG_NUMA
 	unsigned int		node;
 #endif
 	void			*handler_data;
 	struct msi_desc		*msi_desc;
 	cpumask_var_t		affinity;
+#ifdef CONFIG_GENERIC_IRQ_IPI
+	unsigned int		ipi_offset;
+#endif
 };
 
 /**
@@ -208,7 +214,7 @@ enum {
 	IRQD_FORWARDED_TO_VCPU		= (1 << 20),
 };
 
-#define __irqd_to_state(d)		((d)->common->state_use_accessors)
+#define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors)
 
 static inline bool irqd_is_setaffinity_pending(struct irq_data *d)
 {
@@ -299,6 +305,8 @@ static inline void irqd_clr_forwarded_to_vcpu(struct irq_data *d)
 	__irqd_to_state(d) &= ~IRQD_FORWARDED_TO_VCPU;
 }
 
+#undef __irqd_to_state
+
 static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
 {
 	return d->hwirq;
@@ -341,6 +349,8 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
  * @irq_get_irqchip_state:	return the internal state of an interrupt
  * @irq_set_irqchip_state:	set the internal state of a interrupt
  * @irq_set_vcpu_affinity:	optional to target a vCPU in a virtual machine
+ * @ipi_send_single:	send a single IPI to destination cpus
+ * @ipi_send_mask:	send an IPI to destination cpus in cpumask
  * @flags:		chip specific flags
  */
 struct irq_chip {
@@ -385,6 +395,9 @@ struct irq_chip {
 
 	int		(*irq_set_vcpu_affinity)(struct irq_data *data, void *vcpu_info);
 
+	void		(*ipi_send_single)(struct irq_data *data, unsigned int cpu);
+	void		(*ipi_send_mask)(struct irq_data *data, const struct cpumask *dest);
+
 	unsigned long	flags;
 };
 
@@ -934,4 +947,12 @@ static inline u32 irq_reg_readl(struct irq_chip_generic *gc,
 		return readl(gc->reg_base + reg_offset);
 }
 
+/* Contrary to Linux irqs, for hardware irqs the irq number 0 is valid */
+#define INVALID_HWIRQ	(~0UL)
+irq_hw_number_t ipi_get_hwirq(unsigned int irq, unsigned int cpu);
+int __ipi_send_single(struct irq_desc *desc, unsigned int cpu);
+int __ipi_send_mask(struct irq_desc *desc, const struct cpumask *dest);
+int ipi_send_single(unsigned int virq, unsigned int cpu);
+int ipi_send_mask(unsigned int virq, const struct cpumask *dest);
+
 #endif /* _LINUX_IRQ_H */
diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h
index ce824db48d64..80f89e4a29ac 100644
--- a/include/linux/irqchip/mips-gic.h
+++ b/include/linux/irqchip/mips-gic.h
@@ -261,9 +261,6 @@ extern void gic_write_compare(cycle_t cnt);
 extern void gic_write_cpu_compare(cycle_t cnt, int cpu);
 extern void gic_start_count(void);
 extern void gic_stop_count(void);
-extern void gic_send_ipi(unsigned int intr);
-extern unsigned int plat_ipi_call_int_xlate(unsigned int);
-extern unsigned int plat_ipi_resched_int_xlate(unsigned int);
 extern int gic_get_c0_compare_int(void);
 extern int gic_get_c0_perfcount_int(void);
 extern int gic_get_c0_fdc_int(void);
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 04579d9fbce4..ed48594e96d2 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -74,6 +74,7 @@ enum irq_domain_bus_token {
 	DOMAIN_BUS_PCI_MSI,
 	DOMAIN_BUS_PLATFORM_MSI,
 	DOMAIN_BUS_NEXUS,
+	DOMAIN_BUS_IPI,
 };
 
 /**
@@ -172,6 +173,12 @@ enum {
 	/* Core calls alloc/free recursive through the domain hierarchy. */
 	IRQ_DOMAIN_FLAG_AUTO_RECURSIVE	= (1 << 1),
 
+	/* Irq domain is an IPI domain with virq per cpu */
+	IRQ_DOMAIN_FLAG_IPI_PER_CPU	= (1 << 2),
+
+	/* Irq domain is an IPI domain with single virq */
+	IRQ_DOMAIN_FLAG_IPI_SINGLE	= (1 << 3),
+
 	/*
 	 * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved
 	 * for implementation specific purposes and ignored by the
@@ -206,6 +213,8 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node,
 extern struct irq_domain *irq_find_matching_fwnode(struct fwnode_handle *fwnode,
 						   enum irq_domain_bus_token bus_token);
 extern void irq_set_default_host(struct irq_domain *host);
+extern int irq_domain_alloc_descs(int virq, unsigned int nr_irqs,
+				  irq_hw_number_t hwirq, int node);
 
 static inline struct fwnode_handle *of_node_to_fwnode(struct device_node *node)
 {
@@ -335,6 +344,11 @@ int irq_domain_xlate_onetwocell(struct irq_domain *d, struct device_node *ctrlr,
 			const u32 *intspec, unsigned int intsize,
 			irq_hw_number_t *out_hwirq, unsigned int *out_type);
 
+/* IPI functions */
+unsigned int irq_reserve_ipi(struct irq_domain *domain,
+			     const struct cpumask *dest);
+void irq_destroy_ipi(unsigned int irq);
+
 /* V2 interfaces to support hierarchy IRQ domains. */
 extern struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain,
 						unsigned int virq);
@@ -400,6 +414,22 @@ static inline bool irq_domain_is_hierarchy(struct irq_domain *domain)
 {
 	return domain->flags & IRQ_DOMAIN_FLAG_HIERARCHY;
 }
+
+static inline bool irq_domain_is_ipi(struct irq_domain *domain)
+{
+	return domain->flags &
+		(IRQ_DOMAIN_FLAG_IPI_PER_CPU | IRQ_DOMAIN_FLAG_IPI_SINGLE);
+}
+
+static inline bool irq_domain_is_ipi_per_cpu(struct irq_domain *domain)
+{
+	return domain->flags & IRQ_DOMAIN_FLAG_IPI_PER_CPU;
+}
+
+static inline bool irq_domain_is_ipi_single(struct irq_domain *domain)
+{
+	return domain->flags & IRQ_DOMAIN_FLAG_IPI_SINGLE;
+}
 #else	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
 static inline void irq_domain_activate_irq(struct irq_data *data) { }
 static inline void irq_domain_deactivate_irq(struct irq_data *data) { }
@@ -413,6 +443,21 @@ static inline bool irq_domain_is_hierarchy(struct irq_domain *domain)
 {
 	return false;
 }
+
+static inline bool irq_domain_is_ipi(struct irq_domain *domain)
+{
+	return false;
+}
+
+static inline bool irq_domain_is_ipi_per_cpu(struct irq_domain *domain)
+{
+	return false;
+}
+
+static inline bool irq_domain_is_ipi_single(struct irq_domain *domain)
+{
+	return false;
+}
 #endif	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
 
 #else /* CONFIG_IRQ_DOMAIN */
diff --git a/include/linux/iscsi_boot_sysfs.h b/include/linux/iscsi_boot_sysfs.h
index 2a8b1659bf35..548d55395488 100644
--- a/include/linux/iscsi_boot_sysfs.h
+++ b/include/linux/iscsi_boot_sysfs.h
@@ -23,6 +23,7 @@ enum iscsi_boot_eth_properties_enum {
 	ISCSI_BOOT_ETH_INDEX,
 	ISCSI_BOOT_ETH_FLAGS,
 	ISCSI_BOOT_ETH_IP_ADDR,
+	ISCSI_BOOT_ETH_PREFIX_LEN,
 	ISCSI_BOOT_ETH_SUBNET_MASK,
 	ISCSI_BOOT_ETH_ORIGIN,
 	ISCSI_BOOT_ETH_GATEWAY,
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 4b9f85c963d0..0fdc798e3ff7 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -1,6 +1,7 @@
 #ifndef _LINUX_KASAN_H
 #define _LINUX_KASAN_H
 
+#include <linux/sched.h>
 #include <linux/types.h>
 
 struct kmem_cache;
@@ -13,7 +14,6 @@ struct vm_struct;
 
 #include <asm/kasan.h>
 #include <asm/pgtable.h>
-#include <linux/sched.h>
 
 extern unsigned char kasan_zero_page[PAGE_SIZE];
 extern pte_t kasan_zero_pte[PTRS_PER_PTE];
@@ -43,6 +43,8 @@ static inline void kasan_disable_current(void)
 
 void kasan_unpoison_shadow(const void *address, size_t size);
 
+void kasan_unpoison_task_stack(struct task_struct *task);
+
 void kasan_alloc_pages(struct page *page, unsigned int order);
 void kasan_free_pages(struct page *page, unsigned int order);
 
@@ -66,6 +68,8 @@ void kasan_free_shadow(const struct vm_struct *vm);
 
 static inline void kasan_unpoison_shadow(const void *address, size_t size) {}
 
+static inline void kasan_unpoison_task_stack(struct task_struct *task) {}
+
 static inline void kasan_enable_current(void) {}
 static inline void kasan_disable_current(void) {}
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 861f690aa791..5276fe0916fc 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -25,6 +25,7 @@
 #include <linux/irqflags.h>
 #include <linux/context_tracking.h>
 #include <linux/irqbypass.h>
+#include <linux/swait.h>
 #include <asm/signal.h>
 
 #include <linux/kvm.h>
@@ -218,7 +219,7 @@ struct kvm_vcpu {
 	int fpu_active;
 	int guest_fpu_loaded, guest_xcr0_loaded;
 	unsigned char fpu_counter;
-	wait_queue_head_t wq;
+	struct swait_queue_head wq;
 	struct pid *pid;
 	int sigset_active;
 	sigset_t sigset;
@@ -782,7 +783,7 @@ static inline bool kvm_arch_has_assigned_device(struct kvm *kvm)
 }
 #endif
 
-static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
+static inline struct swait_queue_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
 {
 #ifdef __KVM_HAVE_ARCH_WQP
 	return vcpu->arch.wqp;
diff --git a/include/linux/latencytop.h b/include/linux/latencytop.h
index e23121f9d82a..59ccab297ae0 100644
--- a/include/linux/latencytop.h
+++ b/include/linux/latencytop.h
@@ -37,6 +37,9 @@ account_scheduler_latency(struct task_struct *task, int usecs, int inter)
 
 void clear_all_latency_tracing(struct task_struct *p);
 
+extern int sysctl_latencytop(struct ctl_table *table, int write,
+			void __user *buffer, size_t *lenp, loff_t *ppos);
+
 #else
 
 static inline void
diff --git a/include/linux/leds.h b/include/linux/leds.h
index bc1476fda96e..f203a8f89d30 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -39,6 +39,7 @@ struct led_classdev {
 
 	/* Lower 16 bits reflect status */
 #define LED_SUSPENDED		(1 << 0)
+#define LED_UNREGISTERING	(1 << 1)
 	/* Upper 16 bits reflect control information */
 #define LED_CORE_SUSPENDRESUME	(1 << 16)
 #define LED_BLINK_ONESHOT	(1 << 17)
@@ -48,9 +49,12 @@ struct led_classdev {
 #define LED_BLINK_DISABLE	(1 << 21)
 #define LED_SYSFS_DISABLE	(1 << 22)
 #define LED_DEV_CAP_FLASH	(1 << 23)
+#define LED_HW_PLUGGABLE	(1 << 24)
 
-	/* Set LED brightness level */
-	/* Must not sleep, use a workqueue if needed */
+	/* Set LED brightness level
+	 * Must not sleep. Use brightness_set_blocking for drivers
+	 * that can sleep while setting brightness.
+	 */
 	void		(*brightness_set)(struct led_classdev *led_cdev,
 					  enum led_brightness brightness);
 	/*
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 851821bfd553..2c4ebef79d0c 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -526,6 +526,7 @@ enum ata_lpm_policy {
 enum ata_lpm_hints {
 	ATA_LPM_EMPTY		= (1 << 0), /* port empty/probing */
 	ATA_LPM_HIPM		= (1 << 1), /* may use HIPM */
+	ATA_LPM_WAKE_ONLY	= (1 << 2), /* only wake up link */
 };
 
 /* forward declarations */
@@ -719,7 +720,7 @@ struct ata_device {
 	union {
 		u16		id[ATA_ID_WORDS]; /* IDENTIFY xxx DEVICE data */
 		u32		gscr[SATA_PMP_GSCR_DWORDS]; /* PMP GSCR block */
-	};
+	} ____cacheline_aligned;
 
 	/* DEVSLP Timing Variables from Identify Device Data Log */
 	u8			devslp_timing[ATA_LOG_DEVSLP_SIZE];
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index bed40dff0e86..833867b9ddc2 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -26,9 +26,8 @@ enum {
 
 	/* need to set a limit somewhere, but yes, this is likely overkill */
 	ND_IOCTL_MAX_BUFLEN = SZ_4M,
-	ND_CMD_MAX_ELEM = 4,
+	ND_CMD_MAX_ELEM = 5,
 	ND_CMD_MAX_ENVELOPE = 16,
-	ND_CMD_ARS_STATUS_MAX = SZ_4K,
 	ND_MAX_MAPPINGS = 32,
 
 	/* region flag indicating to direct-map persistent memory by default */
@@ -49,7 +48,7 @@ struct nvdimm;
 struct nvdimm_bus_descriptor;
 typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc,
 		struct nvdimm *nvdimm, unsigned int cmd, void *buf,
-		unsigned int buf_len);
+		unsigned int buf_len, int *cmd_rc);
 
 struct nd_namespace_label;
 struct nvdimm_drvdata;
@@ -72,6 +71,9 @@ struct nvdimm_bus_descriptor {
 	unsigned long dsm_mask;
 	char *provider_name;
 	ndctl_fn ndctl;
+	int (*flush_probe)(struct nvdimm_bus_descriptor *nd_desc);
+	int (*clear_to_send)(struct nvdimm_bus_descriptor *nd_desc,
+			struct nvdimm *nvdimm, unsigned int cmd);
 };
 
 struct nd_cmd_desc {
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index d6750111e48e..2190419bdf0a 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -135,6 +135,10 @@ enum {
 	/* Memory types */
 	NVM_ID_FMTYPE_SLC	= 0,
 	NVM_ID_FMTYPE_MLC	= 1,
+
+	/* Device capabilities */
+	NVM_ID_DCAP_BBLKMGMT	= 0x1,
+	NVM_UD_DCAP_ECC		= 0x2,
 };
 
 struct nvm_id_lp_mlc {
diff --git a/include/linux/list.h b/include/linux/list.h
index 30cf4200ab40..5356f4d661a7 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -113,17 +113,6 @@ extern void __list_del_entry(struct list_head *entry);
 extern void list_del(struct list_head *entry);
 #endif
 
-#ifdef CONFIG_DEBUG_LIST
-/*
- * See devm_memremap_pages() which wants DEBUG_LIST=y to assert if one
- * of the pages it allocates is ever passed to list_add()
- */
-extern void list_force_poison(struct list_head *entry);
-#else
-/* fallback to the less strict LIST_POISON* definitions */
-#define list_force_poison list_del
-#endif
-
 /**
  * list_replace - replace old entry by new one
  * @old : the element to be replaced
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index c57e424d914b..d026b190c530 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -66,7 +66,7 @@ struct lock_class {
 	/*
 	 * class-hash:
 	 */
-	struct list_head		hash_entry;
+	struct hlist_node		hash_entry;
 
 	/*
 	 * global list of all lock-classes:
@@ -199,7 +199,7 @@ struct lock_chain {
 	u8				irq_context;
 	u8				depth;
 	u16				base;
-	struct list_head		entry;
+	struct hlist_node		entry;
 	u64				chain_key;
 };
 
@@ -261,7 +261,6 @@ struct held_lock {
 /*
  * Initialization, self-test and debugging-output methods:
  */
-extern void lockdep_init(void);
 extern void lockdep_info(void);
 extern void lockdep_reset(void);
 extern void lockdep_reset_lock(struct lockdep_map *lock);
@@ -392,7 +391,6 @@ static inline void lockdep_on(void)
 # define lockdep_set_current_reclaim_state(g)	do { } while (0)
 # define lockdep_clear_current_reclaim_state()	do { } while (0)
 # define lockdep_trace_alloc(g)			do { } while (0)
-# define lockdep_init()				do { } while (0)
 # define lockdep_info()				do { } while (0)
 # define lockdep_init_map(lock, name, key, sub) \
 		do { (void)(name); (void)(key); } while (0)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 792c8981e633..f0c4bec6565b 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -28,6 +28,7 @@
 #include <linux/eventfd.h>
 #include <linux/mmzone.h>
 #include <linux/writeback.h>
+#include <linux/page-flags.h>
 
 struct mem_cgroup;
 struct page;
@@ -89,6 +90,10 @@ enum mem_cgroup_events_target {
 };
 
 #ifdef CONFIG_MEMCG
+
+#define MEM_CGROUP_ID_SHIFT	16
+#define MEM_CGROUP_ID_MAX	USHRT_MAX
+
 struct mem_cgroup_stat_cpu {
 	long count[MEMCG_NR_STAT];
 	unsigned long events[MEMCG_NR_EVENTS];
@@ -265,6 +270,11 @@ struct mem_cgroup {
 
 extern struct mem_cgroup *root_mem_cgroup;
 
+static inline bool mem_cgroup_disabled(void)
+{
+	return !cgroup_subsys_enabled(memory_cgrp_subsys);
+}
+
 /**
  * mem_cgroup_events - count memory events against a cgroup
  * @memcg: the memory cgroup
@@ -291,7 +301,7 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg,
 void mem_cgroup_uncharge(struct page *page);
 void mem_cgroup_uncharge_list(struct list_head *page_list);
 
-void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage);
+void mem_cgroup_migrate(struct page *oldpage, struct page *newpage);
 
 struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
 struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
@@ -312,6 +322,28 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
 				   struct mem_cgroup_reclaim_cookie *);
 void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
 
+static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
+{
+	if (mem_cgroup_disabled())
+		return 0;
+
+	return memcg->css.id;
+}
+
+/**
+ * mem_cgroup_from_id - look up a memcg from an id
+ * @id: the id to look up
+ *
+ * Caller must hold rcu_read_lock() and use css_tryget() as necessary.
+ */
+static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
+{
+	struct cgroup_subsys_state *css;
+
+	css = css_from_id(id, &memory_cgrp_subsys);
+	return mem_cgroup_from_css(css);
+}
+
 /**
  * parent_mem_cgroup - find the accounting parent of a memcg
  * @memcg: memcg whose parent to find
@@ -353,11 +385,6 @@ static inline bool mm_match_cgroup(struct mm_struct *mm,
 struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
 ino_t page_cgroup_ino(struct page *page);
 
-static inline bool mem_cgroup_disabled(void)
-{
-	return !cgroup_subsys_enabled(memory_cgrp_subsys);
-}
-
 static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
 {
 	if (mem_cgroup_disabled())
@@ -429,36 +456,43 @@ bool mem_cgroup_oom_synchronize(bool wait);
 extern int do_swap_account;
 #endif
 
-struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page);
-void mem_cgroup_end_page_stat(struct mem_cgroup *memcg);
+void lock_page_memcg(struct page *page);
+void unlock_page_memcg(struct page *page);
 
 /**
  * mem_cgroup_update_page_stat - update page state statistics
- * @memcg: memcg to account against
+ * @page: the page
  * @idx: page state item to account
  * @val: number of pages (positive or negative)
  *
- * See mem_cgroup_begin_page_stat() for locking requirements.
+ * The @page must be locked or the caller must use lock_page_memcg()
+ * to prevent double accounting when the page is concurrently being
+ * moved to another memcg:
+ *
+ *   lock_page(page) or lock_page_memcg(page)
+ *   if (TestClearPageState(page))
+ *     mem_cgroup_update_page_stat(page, state, -1);
+ *   unlock_page(page) or unlock_page_memcg(page)
  */
-static inline void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
+static inline void mem_cgroup_update_page_stat(struct page *page,
 				 enum mem_cgroup_stat_index idx, int val)
 {
-	VM_BUG_ON(!rcu_read_lock_held());
+	VM_BUG_ON(!(rcu_read_lock_held() || PageLocked(page)));
 
-	if (memcg)
-		this_cpu_add(memcg->stat->count[idx], val);
+	if (page->mem_cgroup)
+		this_cpu_add(page->mem_cgroup->stat->count[idx], val);
 }
 
-static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg,
+static inline void mem_cgroup_inc_page_stat(struct page *page,
 					    enum mem_cgroup_stat_index idx)
 {
-	mem_cgroup_update_page_stat(memcg, idx, 1);
+	mem_cgroup_update_page_stat(page, idx, 1);
 }
 
-static inline void mem_cgroup_dec_page_stat(struct mem_cgroup *memcg,
+static inline void mem_cgroup_dec_page_stat(struct page *page,
 					    enum mem_cgroup_stat_index idx)
 {
-	mem_cgroup_update_page_stat(memcg, idx, -1);
+	mem_cgroup_update_page_stat(page, idx, -1);
 }
 
 unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
@@ -496,8 +530,17 @@ void mem_cgroup_split_huge_fixup(struct page *head);
 #endif
 
 #else /* CONFIG_MEMCG */
+
+#define MEM_CGROUP_ID_SHIFT	0
+#define MEM_CGROUP_ID_MAX	0
+
 struct mem_cgroup;
 
+static inline bool mem_cgroup_disabled(void)
+{
+	return true;
+}
+
 static inline void mem_cgroup_events(struct mem_cgroup *memcg,
 				     enum mem_cgroup_events_index idx,
 				     unsigned int nr)
@@ -539,7 +582,7 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
 {
 }
 
-static inline void mem_cgroup_replace_page(struct page *old, struct page *new)
+static inline void mem_cgroup_migrate(struct page *old, struct page *new)
 {
 }
 
@@ -580,9 +623,16 @@ static inline void mem_cgroup_iter_break(struct mem_cgroup *root,
 {
 }
 
-static inline bool mem_cgroup_disabled(void)
+static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
 {
-	return true;
+	return 0;
+}
+
+static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
+{
+	WARN_ON_ONCE(id);
+	/* XXX: This should always return root_mem_cgroup */
+	return NULL;
 }
 
 static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
@@ -613,12 +663,11 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 {
 }
 
-static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page)
+static inline void lock_page_memcg(struct page *page)
 {
-	return NULL;
 }
 
-static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg)
+static inline void unlock_page_memcg(struct page *page)
 {
 }
 
@@ -644,12 +693,12 @@ static inline bool mem_cgroup_oom_synchronize(bool wait)
 	return false;
 }
 
-static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg,
+static inline void mem_cgroup_inc_page_stat(struct page *page,
 					    enum mem_cgroup_stat_index idx)
 {
 }
 
-static inline void mem_cgroup_dec_page_stat(struct mem_cgroup *memcg,
+static inline void mem_cgroup_dec_page_stat(struct page *page,
 					    enum mem_cgroup_stat_index idx)
 {
 }
@@ -765,7 +814,7 @@ int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order);
 void __memcg_kmem_uncharge(struct page *page, int order);
 
 /*
- * helper for acessing a memcg's index. It will be used as an index in the
+ * helper for accessing a memcg's index. It will be used as an index in the
  * child cache array in kmem_cache, and also to derive its name. This function
  * will return -1 when this is not a kmem-limited memcg.
  */
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 8b8d8d12348e..82730adba950 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -109,6 +109,9 @@ extern void unregister_memory_notifier(struct notifier_block *nb);
 extern int register_memory_isolate_notifier(struct notifier_block *nb);
 extern void unregister_memory_isolate_notifier(struct notifier_block *nb);
 extern int register_new_memory(int, struct mem_section *);
+extern int memory_block_change_state(struct memory_block *mem,
+				     unsigned long to_state,
+				     unsigned long from_state_req);
 #ifdef CONFIG_MEMORY_HOTREMOVE
 extern int unregister_memory_section(struct mem_section *);
 #endif
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 43405992d027..adbef586e696 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -99,6 +99,8 @@ extern void __online_page_free(struct page *page);
 
 extern int try_online_node(int nid);
 
+extern bool memhp_auto_online;
+
 #ifdef CONFIG_MEMORY_HOTREMOVE
 extern bool is_pageblock_removable_nolock(struct page *page);
 extern int arch_remove_memory(u64 start, u64 size);
@@ -196,6 +198,9 @@ void put_online_mems(void);
 void mem_hotplug_begin(void);
 void mem_hotplug_done(void);
 
+extern void set_zone_contiguous(struct zone *zone);
+extern void clear_zone_contiguous(struct zone *zone);
+
 #else /* ! CONFIG_MEMORY_HOTPLUG */
 /*
  * Stub functions for when hotplug is off
@@ -267,7 +272,7 @@ static inline void remove_memory(int nid, u64 start, u64 size) {}
 extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
 		void *arg, int (*func)(struct memory_block *, void *));
 extern int add_memory(int nid, u64 start, u64 size);
-extern int add_memory_resource(int nid, struct resource *resource);
+extern int add_memory_resource(int nid, struct resource *resource, bool online);
 extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default,
 		bool for_device);
 extern int arch_add_memory(int nid, u64 start, u64 size, bool for_device);
diff --git a/include/linux/mfd/max77686-private.h b/include/linux/mfd/max77686-private.h
index f5043490d67c..643dae777b43 100644
--- a/include/linux/mfd/max77686-private.h
+++ b/include/linux/mfd/max77686-private.h
@@ -437,14 +437,11 @@ enum max77686_irq {
 struct max77686_dev {
 	struct device *dev;
 	struct i2c_client *i2c; /* 0xcc / PMIC, Battery Control, and FLASH */
-	struct i2c_client *rtc; /* slave addr 0x0c */
 
 	unsigned long type;
 
 	struct regmap *regmap;		/* regmap for mfd */
-	struct regmap *rtc_regmap;	/* regmap for rtc */
 	struct regmap_irq_chip_data *irq_data;
-	struct regmap_irq_chip_data *rtc_irq_data;
 
 	int irq;
 	struct mutex irqlock;
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index cac1c0904d5f..9b50325e4ddf 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -23,9 +23,13 @@ enum migrate_reason {
 	MR_SYSCALL,		/* also applies to cpusets */
 	MR_MEMPOLICY_MBIND,
 	MR_NUMA_MISPLACED,
-	MR_CMA
+	MR_CMA,
+	MR_TYPES
 };
 
+/* In mm/debug.c; also keep sync with include/trace/events/migrate.h */
+extern char *migrate_reason_names[MR_TYPES];
+
 #ifdef CONFIG_MIGRATION
 
 extern void putback_movable_pages(struct list_head *l);
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 430a929f048b..a0e8cc8dcc67 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -44,6 +44,8 @@
 
 #include <linux/timecounter.h>
 
+#define DEFAULT_UAR_PAGE_SHIFT  12
+
 #define MAX_MSIX_P_PORT		17
 #define MAX_MSIX		64
 #define MIN_MSIX_P_PORT		5
@@ -856,6 +858,7 @@ struct mlx4_dev {
 	u64			regid_promisc_array[MLX4_MAX_PORTS + 1];
 	u64			regid_allmulti_array[MLX4_MAX_PORTS + 1];
 	struct mlx4_vf_dev     *dev_vfs;
+	u8  uar_page_shift;
 };
 
 struct mlx4_clock_params {
@@ -1528,4 +1531,14 @@ int mlx4_ACCESS_PTYS_REG(struct mlx4_dev *dev,
 int mlx4_get_internal_clock_params(struct mlx4_dev *dev,
 				   struct mlx4_clock_params *params);
 
+static inline int mlx4_to_hw_uar_index(struct mlx4_dev *dev, int index)
+{
+	return (index << (PAGE_SHIFT - dev->uar_page_shift));
+}
+
+static inline int mlx4_get_num_reserved_uar(struct mlx4_dev *dev)
+{
+	/* The first 128 UARs are used for EQ doorbells */
+	return (128 >> (PAGE_SHIFT - dev->uar_page_shift));
+}
 #endif /* MLX4_DEVICE_H */
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 231ab6bcea76..58eef02edc7e 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -207,15 +207,15 @@ struct mlx5_ifc_flow_table_fields_supported_bits {
 	u8         outer_dmac[0x1];
 	u8         outer_smac[0x1];
 	u8         outer_ether_type[0x1];
-	u8         reserved_0[0x1];
+	u8         reserved_at_3[0x1];
 	u8         outer_first_prio[0x1];
 	u8         outer_first_cfi[0x1];
 	u8         outer_first_vid[0x1];
-	u8         reserved_1[0x1];
+	u8         reserved_at_7[0x1];
 	u8         outer_second_prio[0x1];
 	u8         outer_second_cfi[0x1];
 	u8         outer_second_vid[0x1];
-	u8         reserved_2[0x1];
+	u8         reserved_at_b[0x1];
 	u8         outer_sip[0x1];
 	u8         outer_dip[0x1];
 	u8         outer_frag[0x1];
@@ -230,21 +230,21 @@ struct mlx5_ifc_flow_table_fields_supported_bits {
 	u8         outer_gre_protocol[0x1];
 	u8         outer_gre_key[0x1];
 	u8         outer_vxlan_vni[0x1];
-	u8         reserved_3[0x5];
+	u8         reserved_at_1a[0x5];
 	u8         source_eswitch_port[0x1];
 
 	u8         inner_dmac[0x1];
 	u8         inner_smac[0x1];
 	u8         inner_ether_type[0x1];
-	u8         reserved_4[0x1];
+	u8         reserved_at_23[0x1];
 	u8         inner_first_prio[0x1];
 	u8         inner_first_cfi[0x1];
 	u8         inner_first_vid[0x1];
-	u8         reserved_5[0x1];
+	u8         reserved_at_27[0x1];
 	u8         inner_second_prio[0x1];
 	u8         inner_second_cfi[0x1];
 	u8         inner_second_vid[0x1];
-	u8         reserved_6[0x1];
+	u8         reserved_at_2b[0x1];
 	u8         inner_sip[0x1];
 	u8         inner_dip[0x1];
 	u8         inner_frag[0x1];
@@ -256,37 +256,37 @@ struct mlx5_ifc_flow_table_fields_supported_bits {
 	u8         inner_tcp_sport[0x1];
 	u8         inner_tcp_dport[0x1];
 	u8         inner_tcp_flags[0x1];
-	u8         reserved_7[0x9];
+	u8         reserved_at_37[0x9];
 
-	u8         reserved_8[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8         ft_support[0x1];
-	u8         reserved_0[0x2];
+	u8         reserved_at_1[0x2];
 	u8	   flow_modify_en[0x1];
 	u8         modify_root[0x1];
 	u8         identified_miss_table_mode[0x1];
 	u8         flow_table_modify[0x1];
-	u8         reserved_1[0x19];
+	u8         reserved_at_7[0x19];
 
-	u8         reserved_2[0x2];
+	u8         reserved_at_20[0x2];
 	u8         log_max_ft_size[0x6];
-	u8         reserved_3[0x10];
+	u8         reserved_at_28[0x10];
 	u8         max_ft_level[0x8];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_40[0x20];
 
-	u8         reserved_5[0x18];
+	u8         reserved_at_60[0x18];
 	u8         log_max_ft_num[0x8];
 
-	u8         reserved_6[0x18];
+	u8         reserved_at_80[0x18];
 	u8         log_max_destination[0x8];
 
-	u8         reserved_7[0x18];
+	u8         reserved_at_a0[0x18];
 	u8         log_max_flow[0x8];
 
-	u8         reserved_8[0x40];
+	u8         reserved_at_c0[0x40];
 
 	struct mlx5_ifc_flow_table_fields_supported_bits ft_field_support;
 
@@ -298,13 +298,13 @@ struct mlx5_ifc_odp_per_transport_service_cap_bits {
 	u8         receive[0x1];
 	u8         write[0x1];
 	u8         read[0x1];
-	u8         reserved_0[0x1];
+	u8         reserved_at_4[0x1];
 	u8         srq_receive[0x1];
-	u8         reserved_1[0x1a];
+	u8         reserved_at_6[0x1a];
 };
 
 struct mlx5_ifc_ipv4_layout_bits {
-	u8         reserved_0[0x60];
+	u8         reserved_at_0[0x60];
 
 	u8         ipv4[0x20];
 };
@@ -316,7 +316,7 @@ struct mlx5_ifc_ipv6_layout_bits {
 union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits {
 	struct mlx5_ifc_ipv6_layout_bits ipv6_layout;
 	struct mlx5_ifc_ipv4_layout_bits ipv4_layout;
-	u8         reserved_0[0x80];
+	u8         reserved_at_0[0x80];
 };
 
 struct mlx5_ifc_fte_match_set_lyr_2_4_bits {
@@ -336,15 +336,15 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits {
 	u8         ip_dscp[0x6];
 	u8         ip_ecn[0x2];
 	u8         vlan_tag[0x1];
-	u8         reserved_0[0x1];
+	u8         reserved_at_91[0x1];
 	u8         frag[0x1];
-	u8         reserved_1[0x4];
+	u8         reserved_at_93[0x4];
 	u8         tcp_flags[0x9];
 
 	u8         tcp_sport[0x10];
 	u8         tcp_dport[0x10];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_c0[0x20];
 
 	u8         udp_sport[0x10];
 	u8         udp_dport[0x10];
@@ -355,9 +355,9 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits {
 };
 
 struct mlx5_ifc_fte_match_set_misc_bits {
-	u8         reserved_0[0x20];
+	u8         reserved_at_0[0x20];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         source_port[0x10];
 
 	u8         outer_second_prio[0x3];
@@ -369,31 +369,31 @@ struct mlx5_ifc_fte_match_set_misc_bits {
 
 	u8         outer_second_vlan_tag[0x1];
 	u8         inner_second_vlan_tag[0x1];
-	u8         reserved_2[0xe];
+	u8         reserved_at_62[0xe];
 	u8         gre_protocol[0x10];
 
 	u8         gre_key_h[0x18];
 	u8         gre_key_l[0x8];
 
 	u8         vxlan_vni[0x18];
-	u8         reserved_3[0x8];
+	u8         reserved_at_b8[0x8];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_c0[0x20];
 
-	u8         reserved_5[0xc];
+	u8         reserved_at_e0[0xc];
 	u8         outer_ipv6_flow_label[0x14];
 
-	u8         reserved_6[0xc];
+	u8         reserved_at_100[0xc];
 	u8         inner_ipv6_flow_label[0x14];
 
-	u8         reserved_7[0xe0];
+	u8         reserved_at_120[0xe0];
 };
 
 struct mlx5_ifc_cmd_pas_bits {
 	u8         pa_h[0x20];
 
 	u8         pa_l[0x14];
-	u8         reserved_0[0xc];
+	u8         reserved_at_34[0xc];
 };
 
 struct mlx5_ifc_uint64_bits {
@@ -418,31 +418,31 @@ enum {
 struct mlx5_ifc_ads_bits {
 	u8         fl[0x1];
 	u8         free_ar[0x1];
-	u8         reserved_0[0xe];
+	u8         reserved_at_2[0xe];
 	u8         pkey_index[0x10];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_20[0x8];
 	u8         grh[0x1];
 	u8         mlid[0x7];
 	u8         rlid[0x10];
 
 	u8         ack_timeout[0x5];
-	u8         reserved_2[0x3];
+	u8         reserved_at_45[0x3];
 	u8         src_addr_index[0x8];
-	u8         reserved_3[0x4];
+	u8         reserved_at_50[0x4];
 	u8         stat_rate[0x4];
 	u8         hop_limit[0x8];
 
-	u8         reserved_4[0x4];
+	u8         reserved_at_60[0x4];
 	u8         tclass[0x8];
 	u8         flow_label[0x14];
 
 	u8         rgid_rip[16][0x8];
 
-	u8         reserved_5[0x4];
+	u8         reserved_at_100[0x4];
 	u8         f_dscp[0x1];
 	u8         f_ecn[0x1];
-	u8         reserved_6[0x1];
+	u8         reserved_at_106[0x1];
 	u8         f_eth_prio[0x1];
 	u8         ecn[0x2];
 	u8         dscp[0x6];
@@ -458,25 +458,25 @@ struct mlx5_ifc_ads_bits {
 };
 
 struct mlx5_ifc_flow_table_nic_cap_bits {
-	u8         reserved_0[0x200];
+	u8         reserved_at_0[0x200];
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive;
 
-	u8         reserved_1[0x200];
+	u8         reserved_at_400[0x200];
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive_sniffer;
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit;
 
-	u8         reserved_2[0x200];
+	u8         reserved_at_a00[0x200];
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit_sniffer;
 
-	u8         reserved_3[0x7200];
+	u8         reserved_at_e00[0x7200];
 };
 
 struct mlx5_ifc_flow_table_eswitch_cap_bits {
-	u8     reserved_0[0x200];
+	u8     reserved_at_0[0x200];
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_esw_fdb;
 
@@ -484,7 +484,7 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits {
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_esw_acl_egress;
 
-	u8      reserved_1[0x7800];
+	u8      reserved_at_800[0x7800];
 };
 
 struct mlx5_ifc_e_switch_cap_bits {
@@ -493,9 +493,9 @@ struct mlx5_ifc_e_switch_cap_bits {
 	u8         vport_svlan_insert[0x1];
 	u8         vport_cvlan_insert_if_not_exist[0x1];
 	u8         vport_cvlan_insert_overwrite[0x1];
-	u8         reserved_0[0x1b];
+	u8         reserved_at_5[0x1b];
 
-	u8         reserved_1[0x7e0];
+	u8         reserved_at_20[0x7e0];
 };
 
 struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
@@ -504,51 +504,51 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
 	u8         lro_cap[0x1];
 	u8         lro_psh_flag[0x1];
 	u8         lro_time_stamp[0x1];
-	u8         reserved_0[0x3];
+	u8         reserved_at_5[0x3];
 	u8         self_lb_en_modifiable[0x1];
-	u8         reserved_1[0x2];
+	u8         reserved_at_9[0x2];
 	u8         max_lso_cap[0x5];
-	u8         reserved_2[0x4];
+	u8         reserved_at_10[0x4];
 	u8         rss_ind_tbl_cap[0x4];
-	u8         reserved_3[0x3];
+	u8         reserved_at_18[0x3];
 	u8         tunnel_lso_const_out_ip_id[0x1];
-	u8         reserved_4[0x2];
+	u8         reserved_at_1c[0x2];
 	u8         tunnel_statless_gre[0x1];
 	u8         tunnel_stateless_vxlan[0x1];
 
-	u8         reserved_5[0x20];
+	u8         reserved_at_20[0x20];
 
-	u8         reserved_6[0x10];
+	u8         reserved_at_40[0x10];
 	u8         lro_min_mss_size[0x10];
 
-	u8         reserved_7[0x120];
+	u8         reserved_at_60[0x120];
 
 	u8         lro_timer_supported_periods[4][0x20];
 
-	u8         reserved_8[0x600];
+	u8         reserved_at_200[0x600];
 };
 
 struct mlx5_ifc_roce_cap_bits {
 	u8         roce_apm[0x1];
-	u8         reserved_0[0x1f];
+	u8         reserved_at_1[0x1f];
 
-	u8         reserved_1[0x60];
+	u8         reserved_at_20[0x60];
 
-	u8         reserved_2[0xc];
+	u8         reserved_at_80[0xc];
 	u8         l3_type[0x4];
-	u8         reserved_3[0x8];
+	u8         reserved_at_90[0x8];
 	u8         roce_version[0x8];
 
-	u8         reserved_4[0x10];
+	u8         reserved_at_a0[0x10];
 	u8         r_roce_dest_udp_port[0x10];
 
 	u8         r_roce_max_src_udp_port[0x10];
 	u8         r_roce_min_src_udp_port[0x10];
 
-	u8         reserved_5[0x10];
+	u8         reserved_at_e0[0x10];
 	u8         roce_address_table_size[0x10];
 
-	u8         reserved_6[0x700];
+	u8         reserved_at_100[0x700];
 };
 
 enum {
@@ -576,35 +576,35 @@ enum {
 };
 
 struct mlx5_ifc_atomic_caps_bits {
-	u8         reserved_0[0x40];
+	u8         reserved_at_0[0x40];
 
 	u8         atomic_req_8B_endianess_mode[0x2];
-	u8         reserved_1[0x4];
+	u8         reserved_at_42[0x4];
 	u8         supported_atomic_req_8B_endianess_mode_1[0x1];
 
-	u8         reserved_2[0x19];
+	u8         reserved_at_47[0x19];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
-	u8         reserved_4[0x10];
+	u8         reserved_at_80[0x10];
 	u8         atomic_operations[0x10];
 
-	u8         reserved_5[0x10];
+	u8         reserved_at_a0[0x10];
 	u8         atomic_size_qp[0x10];
 
-	u8         reserved_6[0x10];
+	u8         reserved_at_c0[0x10];
 	u8         atomic_size_dc[0x10];
 
-	u8         reserved_7[0x720];
+	u8         reserved_at_e0[0x720];
 };
 
 struct mlx5_ifc_odp_cap_bits {
-	u8         reserved_0[0x40];
+	u8         reserved_at_0[0x40];
 
 	u8         sig[0x1];
-	u8         reserved_1[0x1f];
+	u8         reserved_at_41[0x1f];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 
 	struct mlx5_ifc_odp_per_transport_service_cap_bits rc_odp_caps;
 
@@ -612,7 +612,7 @@ struct mlx5_ifc_odp_cap_bits {
 
 	struct mlx5_ifc_odp_per_transport_service_cap_bits ud_odp_caps;
 
-	u8         reserved_3[0x720];
+	u8         reserved_at_e0[0x720];
 };
 
 enum {
@@ -660,55 +660,55 @@ enum {
 };
 
 struct mlx5_ifc_cmd_hca_cap_bits {
-	u8         reserved_0[0x80];
+	u8         reserved_at_0[0x80];
 
 	u8         log_max_srq_sz[0x8];
 	u8         log_max_qp_sz[0x8];
-	u8         reserved_1[0xb];
+	u8         reserved_at_90[0xb];
 	u8         log_max_qp[0x5];
 
-	u8         reserved_2[0xb];
+	u8         reserved_at_a0[0xb];
 	u8         log_max_srq[0x5];
-	u8         reserved_3[0x10];
+	u8         reserved_at_b0[0x10];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         log_max_cq_sz[0x8];
-	u8         reserved_5[0xb];
+	u8         reserved_at_d0[0xb];
 	u8         log_max_cq[0x5];
 
 	u8         log_max_eq_sz[0x8];
-	u8         reserved_6[0x2];
+	u8         reserved_at_e8[0x2];
 	u8         log_max_mkey[0x6];
-	u8         reserved_7[0xc];
+	u8         reserved_at_f0[0xc];
 	u8         log_max_eq[0x4];
 
 	u8         max_indirection[0x8];
-	u8         reserved_8[0x1];
+	u8         reserved_at_108[0x1];
 	u8         log_max_mrw_sz[0x7];
-	u8         reserved_9[0x2];
+	u8         reserved_at_110[0x2];
 	u8         log_max_bsf_list_size[0x6];
-	u8         reserved_10[0x2];
+	u8         reserved_at_118[0x2];
 	u8         log_max_klm_list_size[0x6];
 
-	u8         reserved_11[0xa];
+	u8         reserved_at_120[0xa];
 	u8         log_max_ra_req_dc[0x6];
-	u8         reserved_12[0xa];
+	u8         reserved_at_130[0xa];
 	u8         log_max_ra_res_dc[0x6];
 
-	u8         reserved_13[0xa];
+	u8         reserved_at_140[0xa];
 	u8         log_max_ra_req_qp[0x6];
-	u8         reserved_14[0xa];
+	u8         reserved_at_150[0xa];
 	u8         log_max_ra_res_qp[0x6];
 
 	u8         pad_cap[0x1];
 	u8         cc_query_allowed[0x1];
 	u8         cc_modify_allowed[0x1];
-	u8         reserved_15[0xd];
+	u8         reserved_at_163[0xd];
 	u8         gid_table_size[0x10];
 
 	u8         out_of_seq_cnt[0x1];
 	u8         vport_counters[0x1];
-	u8         reserved_16[0x4];
+	u8         reserved_at_182[0x4];
 	u8         max_qp_cnt[0xa];
 	u8         pkey_table_size[0x10];
 
@@ -716,158 +716,158 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         vhca_group_manager[0x1];
 	u8         ib_virt[0x1];
 	u8         eth_virt[0x1];
-	u8         reserved_17[0x1];
+	u8         reserved_at_1a4[0x1];
 	u8         ets[0x1];
 	u8         nic_flow_table[0x1];
 	u8         eswitch_flow_table[0x1];
 	u8	   early_vf_enable;
-	u8         reserved_18[0x2];
+	u8         reserved_at_1a8[0x2];
 	u8         local_ca_ack_delay[0x5];
-	u8         reserved_19[0x6];
+	u8         reserved_at_1af[0x6];
 	u8         port_type[0x2];
 	u8         num_ports[0x8];
 
-	u8         reserved_20[0x3];
+	u8         reserved_at_1bf[0x3];
 	u8         log_max_msg[0x5];
-	u8         reserved_21[0x18];
+	u8         reserved_at_1c7[0x18];
 
 	u8         stat_rate_support[0x10];
-	u8         reserved_22[0xc];
+	u8         reserved_at_1ef[0xc];
 	u8         cqe_version[0x4];
 
 	u8         compact_address_vector[0x1];
-	u8         reserved_23[0xe];
+	u8         reserved_at_200[0xe];
 	u8         drain_sigerr[0x1];
 	u8         cmdif_checksum[0x2];
 	u8         sigerr_cqe[0x1];
-	u8         reserved_24[0x1];
+	u8         reserved_at_212[0x1];
 	u8         wq_signature[0x1];
 	u8         sctr_data_cqe[0x1];
-	u8         reserved_25[0x1];
+	u8         reserved_at_215[0x1];
 	u8         sho[0x1];
 	u8         tph[0x1];
 	u8         rf[0x1];
 	u8         dct[0x1];
-	u8         reserved_26[0x1];
+	u8         reserved_at_21a[0x1];
 	u8         eth_net_offloads[0x1];
 	u8         roce[0x1];
 	u8         atomic[0x1];
-	u8         reserved_27[0x1];
+	u8         reserved_at_21e[0x1];
 
 	u8         cq_oi[0x1];
 	u8         cq_resize[0x1];
 	u8         cq_moderation[0x1];
-	u8         reserved_28[0x3];
+	u8         reserved_at_222[0x3];
 	u8         cq_eq_remap[0x1];
 	u8         pg[0x1];
 	u8         block_lb_mc[0x1];
-	u8         reserved_29[0x1];
+	u8         reserved_at_228[0x1];
 	u8         scqe_break_moderation[0x1];
-	u8         reserved_30[0x1];
+	u8         reserved_at_22a[0x1];
 	u8         cd[0x1];
-	u8         reserved_31[0x1];
+	u8         reserved_at_22c[0x1];
 	u8         apm[0x1];
-	u8         reserved_32[0x7];
+	u8         reserved_at_22e[0x7];
 	u8         qkv[0x1];
 	u8         pkv[0x1];
-	u8         reserved_33[0x4];
+	u8         reserved_at_237[0x4];
 	u8         xrc[0x1];
 	u8         ud[0x1];
 	u8         uc[0x1];
 	u8         rc[0x1];
 
-	u8         reserved_34[0xa];
+	u8         reserved_at_23f[0xa];
 	u8         uar_sz[0x6];
-	u8         reserved_35[0x8];
+	u8         reserved_at_24f[0x8];
 	u8         log_pg_sz[0x8];
 
 	u8         bf[0x1];
-	u8         reserved_36[0x1];
+	u8         reserved_at_260[0x1];
 	u8         pad_tx_eth_packet[0x1];
-	u8         reserved_37[0x8];
+	u8         reserved_at_262[0x8];
 	u8         log_bf_reg_size[0x5];
-	u8         reserved_38[0x10];
+	u8         reserved_at_26f[0x10];
 
-	u8         reserved_39[0x10];
+	u8         reserved_at_27f[0x10];
 	u8         max_wqe_sz_sq[0x10];
 
-	u8         reserved_40[0x10];
+	u8         reserved_at_29f[0x10];
 	u8         max_wqe_sz_rq[0x10];
 
-	u8         reserved_41[0x10];
+	u8         reserved_at_2bf[0x10];
 	u8         max_wqe_sz_sq_dc[0x10];
 
-	u8         reserved_42[0x7];
+	u8         reserved_at_2df[0x7];
 	u8         max_qp_mcg[0x19];
 
-	u8         reserved_43[0x18];
+	u8         reserved_at_2ff[0x18];
 	u8         log_max_mcg[0x8];
 
-	u8         reserved_44[0x3];
+	u8         reserved_at_31f[0x3];
 	u8         log_max_transport_domain[0x5];
-	u8         reserved_45[0x3];
+	u8         reserved_at_327[0x3];
 	u8         log_max_pd[0x5];
-	u8         reserved_46[0xb];
+	u8         reserved_at_32f[0xb];
 	u8         log_max_xrcd[0x5];
 
-	u8         reserved_47[0x20];
+	u8         reserved_at_33f[0x20];
 
-	u8         reserved_48[0x3];
+	u8         reserved_at_35f[0x3];
 	u8         log_max_rq[0x5];
-	u8         reserved_49[0x3];
+	u8         reserved_at_367[0x3];
 	u8         log_max_sq[0x5];
-	u8         reserved_50[0x3];
+	u8         reserved_at_36f[0x3];
 	u8         log_max_tir[0x5];
-	u8         reserved_51[0x3];
+	u8         reserved_at_377[0x3];
 	u8         log_max_tis[0x5];
 
 	u8         basic_cyclic_rcv_wqe[0x1];
-	u8         reserved_52[0x2];
+	u8         reserved_at_380[0x2];
 	u8         log_max_rmp[0x5];
-	u8         reserved_53[0x3];
+	u8         reserved_at_387[0x3];
 	u8         log_max_rqt[0x5];
-	u8         reserved_54[0x3];
+	u8         reserved_at_38f[0x3];
 	u8         log_max_rqt_size[0x5];
-	u8         reserved_55[0x3];
+	u8         reserved_at_397[0x3];
 	u8         log_max_tis_per_sq[0x5];
 
-	u8         reserved_56[0x3];
+	u8         reserved_at_39f[0x3];
 	u8         log_max_stride_sz_rq[0x5];
-	u8         reserved_57[0x3];
+	u8         reserved_at_3a7[0x3];
 	u8         log_min_stride_sz_rq[0x5];
-	u8         reserved_58[0x3];
+	u8         reserved_at_3af[0x3];
 	u8         log_max_stride_sz_sq[0x5];
-	u8         reserved_59[0x3];
+	u8         reserved_at_3b7[0x3];
 	u8         log_min_stride_sz_sq[0x5];
 
-	u8         reserved_60[0x1b];
+	u8         reserved_at_3bf[0x1b];
 	u8         log_max_wq_sz[0x5];
 
 	u8         nic_vport_change_event[0x1];
-	u8         reserved_61[0xa];
+	u8         reserved_at_3e0[0xa];
 	u8         log_max_vlan_list[0x5];
-	u8         reserved_62[0x3];
+	u8         reserved_at_3ef[0x3];
 	u8         log_max_current_mc_list[0x5];
-	u8         reserved_63[0x3];
+	u8         reserved_at_3f7[0x3];
 	u8         log_max_current_uc_list[0x5];
 
-	u8         reserved_64[0x80];
+	u8         reserved_at_3ff[0x80];
 
-	u8         reserved_65[0x3];
+	u8         reserved_at_47f[0x3];
 	u8         log_max_l2_table[0x5];
-	u8         reserved_66[0x8];
+	u8         reserved_at_487[0x8];
 	u8         log_uar_page_sz[0x10];
 
-	u8         reserved_67[0x20];
+	u8         reserved_at_49f[0x20];
 	u8         device_frequency_mhz[0x20];
 	u8         device_frequency_khz[0x20];
-	u8         reserved_68[0x5f];
+	u8         reserved_at_4ff[0x5f];
 	u8         cqe_zip[0x1];
 
 	u8         cqe_zip_timeout[0x10];
 	u8         cqe_zip_max_num[0x10];
 
-	u8         reserved_69[0x220];
+	u8         reserved_at_57f[0x220];
 };
 
 enum mlx5_flow_destination_type {
@@ -880,7 +880,7 @@ struct mlx5_ifc_dest_format_struct_bits {
 	u8         destination_type[0x8];
 	u8         destination_id[0x18];
 
-	u8         reserved_0[0x20];
+	u8         reserved_at_20[0x20];
 };
 
 struct mlx5_ifc_fte_match_param_bits {
@@ -890,7 +890,7 @@ struct mlx5_ifc_fte_match_param_bits {
 
 	struct mlx5_ifc_fte_match_set_lyr_2_4_bits inner_headers;
 
-	u8         reserved_0[0xa00];
+	u8         reserved_at_600[0xa00];
 };
 
 enum {
@@ -922,18 +922,18 @@ struct mlx5_ifc_wq_bits {
 	u8         wq_signature[0x1];
 	u8         end_padding_mode[0x2];
 	u8         cd_slave[0x1];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         hds_skip_first_sge[0x1];
 	u8         log2_hds_buf_size[0x3];
-	u8         reserved_1[0x7];
+	u8         reserved_at_24[0x7];
 	u8         page_offset[0x5];
 	u8         lwm[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         pd[0x18];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_60[0x8];
 	u8         uar_page[0x18];
 
 	u8         dbr_addr[0x40];
@@ -942,60 +942,60 @@ struct mlx5_ifc_wq_bits {
 
 	u8         sw_counter[0x20];
 
-	u8         reserved_4[0xc];
+	u8         reserved_at_100[0xc];
 	u8         log_wq_stride[0x4];
-	u8         reserved_5[0x3];
+	u8         reserved_at_110[0x3];
 	u8         log_wq_pg_sz[0x5];
-	u8         reserved_6[0x3];
+	u8         reserved_at_118[0x3];
 	u8         log_wq_sz[0x5];
 
-	u8         reserved_7[0x4e0];
+	u8         reserved_at_120[0x4e0];
 
 	struct mlx5_ifc_cmd_pas_bits pas[0];
 };
 
 struct mlx5_ifc_rq_num_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         rq_num[0x18];
 };
 
 struct mlx5_ifc_mac_address_layout_bits {
-	u8         reserved_0[0x10];
+	u8         reserved_at_0[0x10];
 	u8         mac_addr_47_32[0x10];
 
 	u8         mac_addr_31_0[0x20];
 };
 
 struct mlx5_ifc_vlan_layout_bits {
-	u8         reserved_0[0x14];
+	u8         reserved_at_0[0x14];
 	u8         vlan[0x0c];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_20[0x20];
 };
 
 struct mlx5_ifc_cong_control_r_roce_ecn_np_bits {
-	u8         reserved_0[0xa0];
+	u8         reserved_at_0[0xa0];
 
 	u8         min_time_between_cnps[0x20];
 
-	u8         reserved_1[0x12];
+	u8         reserved_at_c0[0x12];
 	u8         cnp_dscp[0x6];
-	u8         reserved_2[0x5];
+	u8         reserved_at_d8[0x5];
 	u8         cnp_802p_prio[0x3];
 
-	u8         reserved_3[0x720];
+	u8         reserved_at_e0[0x720];
 };
 
 struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits {
-	u8         reserved_0[0x60];
+	u8         reserved_at_0[0x60];
 
-	u8         reserved_1[0x4];
+	u8         reserved_at_60[0x4];
 	u8         clamp_tgt_rate[0x1];
-	u8         reserved_2[0x3];
+	u8         reserved_at_65[0x3];
 	u8         clamp_tgt_rate_after_time_inc[0x1];
-	u8         reserved_3[0x17];
+	u8         reserved_at_69[0x17];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_80[0x20];
 
 	u8         rpg_time_reset[0x20];
 
@@ -1015,7 +1015,7 @@ struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits {
 
 	u8         rpg_min_rate[0x20];
 
-	u8         reserved_5[0xe0];
+	u8         reserved_at_1c0[0xe0];
 
 	u8         rate_to_set_on_first_cnp[0x20];
 
@@ -1025,15 +1025,15 @@ struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits {
 
 	u8         rate_reduce_monitor_period[0x20];
 
-	u8         reserved_6[0x20];
+	u8         reserved_at_320[0x20];
 
 	u8         initial_alpha_value[0x20];
 
-	u8         reserved_7[0x4a0];
+	u8         reserved_at_360[0x4a0];
 };
 
 struct mlx5_ifc_cong_control_802_1qau_rp_bits {
-	u8         reserved_0[0x80];
+	u8         reserved_at_0[0x80];
 
 	u8         rppp_max_rps[0x20];
 
@@ -1055,7 +1055,7 @@ struct mlx5_ifc_cong_control_802_1qau_rp_bits {
 
 	u8         rpg_min_rate[0x20];
 
-	u8         reserved_1[0x640];
+	u8         reserved_at_1c0[0x640];
 };
 
 enum {
@@ -1205,7 +1205,7 @@ struct mlx5_ifc_phys_layer_cntrs_bits {
 
 	u8         successful_recovery_events[0x20];
 
-	u8         reserved_0[0x180];
+	u8         reserved_at_640[0x180];
 };
 
 struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits {
@@ -1213,7 +1213,7 @@ struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits {
 
 	u8         transmit_queue_low[0x20];
 
-	u8         reserved_0[0x780];
+	u8         reserved_at_40[0x780];
 };
 
 struct mlx5_ifc_eth_per_prio_grp_data_layout_bits {
@@ -1221,7 +1221,7 @@ struct mlx5_ifc_eth_per_prio_grp_data_layout_bits {
 
 	u8         rx_octets_low[0x20];
 
-	u8         reserved_0[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	u8         rx_frames_high[0x20];
 
@@ -1231,7 +1231,7 @@ struct mlx5_ifc_eth_per_prio_grp_data_layout_bits {
 
 	u8         tx_octets_low[0x20];
 
-	u8         reserved_1[0xc0];
+	u8         reserved_at_180[0xc0];
 
 	u8         tx_frames_high[0x20];
 
@@ -1257,7 +1257,7 @@ struct mlx5_ifc_eth_per_prio_grp_data_layout_bits {
 
 	u8         rx_pause_transition_low[0x20];
 
-	u8         reserved_2[0x400];
+	u8         reserved_at_3c0[0x400];
 };
 
 struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits {
@@ -1265,7 +1265,7 @@ struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits {
 
 	u8         port_transmit_wait_low[0x20];
 
-	u8         reserved_0[0x780];
+	u8         reserved_at_40[0x780];
 };
 
 struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits {
@@ -1333,7 +1333,7 @@ struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits {
 
 	u8         dot3out_pause_frames_low[0x20];
 
-	u8         reserved_0[0x3c0];
+	u8         reserved_at_400[0x3c0];
 };
 
 struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits {
@@ -1421,7 +1421,7 @@ struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits {
 
 	u8         ether_stats_pkts8192to10239octets_low[0x20];
 
-	u8         reserved_0[0x280];
+	u8         reserved_at_540[0x280];
 };
 
 struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits {
@@ -1477,7 +1477,7 @@ struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits {
 
 	u8         if_out_broadcast_pkts_low[0x20];
 
-	u8         reserved_0[0x480];
+	u8         reserved_at_340[0x480];
 };
 
 struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits {
@@ -1557,54 +1557,54 @@ struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits {
 
 	u8         a_pause_mac_ctrl_frames_transmitted_low[0x20];
 
-	u8         reserved_0[0x300];
+	u8         reserved_at_4c0[0x300];
 };
 
 struct mlx5_ifc_cmd_inter_comp_event_bits {
 	u8         command_completion_vector[0x20];
 
-	u8         reserved_0[0xc0];
+	u8         reserved_at_20[0xc0];
 };
 
 struct mlx5_ifc_stall_vl_event_bits {
-	u8         reserved_0[0x18];
+	u8         reserved_at_0[0x18];
 	u8         port_num[0x1];
-	u8         reserved_1[0x3];
+	u8         reserved_at_19[0x3];
 	u8         vl[0x4];
 
-	u8         reserved_2[0xa0];
+	u8         reserved_at_20[0xa0];
 };
 
 struct mlx5_ifc_db_bf_congestion_event_bits {
 	u8         event_subtype[0x8];
-	u8         reserved_0[0x8];
+	u8         reserved_at_8[0x8];
 	u8         congestion_level[0x8];
-	u8         reserved_1[0x8];
+	u8         reserved_at_18[0x8];
 
-	u8         reserved_2[0xa0];
+	u8         reserved_at_20[0xa0];
 };
 
 struct mlx5_ifc_gpio_event_bits {
-	u8         reserved_0[0x60];
+	u8         reserved_at_0[0x60];
 
 	u8         gpio_event_hi[0x20];
 
 	u8         gpio_event_lo[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_a0[0x40];
 };
 
 struct mlx5_ifc_port_state_change_event_bits {
-	u8         reserved_0[0x40];
+	u8         reserved_at_0[0x40];
 
 	u8         port_num[0x4];
-	u8         reserved_1[0x1c];
+	u8         reserved_at_44[0x1c];
 
-	u8         reserved_2[0x80];
+	u8         reserved_at_60[0x80];
 };
 
 struct mlx5_ifc_dropped_packet_logged_bits {
-	u8         reserved_0[0xe0];
+	u8         reserved_at_0[0xe0];
 };
 
 enum {
@@ -1613,15 +1613,15 @@ enum {
 };
 
 struct mlx5_ifc_cq_error_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         cqn[0x18];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_20[0x20];
 
-	u8         reserved_2[0x18];
+	u8         reserved_at_40[0x18];
 	u8         syndrome[0x8];
 
-	u8         reserved_3[0x80];
+	u8         reserved_at_60[0x80];
 };
 
 struct mlx5_ifc_rdma_page_fault_event_bits {
@@ -1629,14 +1629,14 @@ struct mlx5_ifc_rdma_page_fault_event_bits {
 
 	u8         r_key[0x20];
 
-	u8         reserved_0[0x10];
+	u8         reserved_at_40[0x10];
 	u8         packet_len[0x10];
 
 	u8         rdma_op_len[0x20];
 
 	u8         rdma_va[0x40];
 
-	u8         reserved_1[0x5];
+	u8         reserved_at_c0[0x5];
 	u8         rdma[0x1];
 	u8         write[0x1];
 	u8         requestor[0x1];
@@ -1646,15 +1646,15 @@ struct mlx5_ifc_rdma_page_fault_event_bits {
 struct mlx5_ifc_wqe_associated_page_fault_event_bits {
 	u8         bytes_committed[0x20];
 
-	u8         reserved_0[0x10];
+	u8         reserved_at_20[0x10];
 	u8         wqe_index[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_40[0x10];
 	u8         len[0x10];
 
-	u8         reserved_2[0x60];
+	u8         reserved_at_60[0x60];
 
-	u8         reserved_3[0x5];
+	u8         reserved_at_c0[0x5];
 	u8         rdma[0x1];
 	u8         write_read[0x1];
 	u8         requestor[0x1];
@@ -1662,26 +1662,26 @@ struct mlx5_ifc_wqe_associated_page_fault_event_bits {
 };
 
 struct mlx5_ifc_qp_events_bits {
-	u8         reserved_0[0xa0];
+	u8         reserved_at_0[0xa0];
 
 	u8         type[0x8];
-	u8         reserved_1[0x18];
+	u8         reserved_at_a8[0x18];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         qpn_rqn_sqn[0x18];
 };
 
 struct mlx5_ifc_dct_events_bits {
-	u8         reserved_0[0xc0];
+	u8         reserved_at_0[0xc0];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         dct_number[0x18];
 };
 
 struct mlx5_ifc_comp_event_bits {
-	u8         reserved_0[0xc0];
+	u8         reserved_at_0[0xc0];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         cq_number[0x18];
 };
 
@@ -1754,41 +1754,41 @@ enum {
 
 struct mlx5_ifc_qpc_bits {
 	u8         state[0x4];
-	u8         reserved_0[0x4];
+	u8         reserved_at_4[0x4];
 	u8         st[0x8];
-	u8         reserved_1[0x3];
+	u8         reserved_at_10[0x3];
 	u8         pm_state[0x2];
-	u8         reserved_2[0x7];
+	u8         reserved_at_15[0x7];
 	u8         end_padding_mode[0x2];
-	u8         reserved_3[0x2];
+	u8         reserved_at_1e[0x2];
 
 	u8         wq_signature[0x1];
 	u8         block_lb_mc[0x1];
 	u8         atomic_like_write_en[0x1];
 	u8         latency_sensitive[0x1];
-	u8         reserved_4[0x1];
+	u8         reserved_at_24[0x1];
 	u8         drain_sigerr[0x1];
-	u8         reserved_5[0x2];
+	u8         reserved_at_26[0x2];
 	u8         pd[0x18];
 
 	u8         mtu[0x3];
 	u8         log_msg_max[0x5];
-	u8         reserved_6[0x1];
+	u8         reserved_at_48[0x1];
 	u8         log_rq_size[0x4];
 	u8         log_rq_stride[0x3];
 	u8         no_sq[0x1];
 	u8         log_sq_size[0x4];
-	u8         reserved_7[0x6];
+	u8         reserved_at_55[0x6];
 	u8         rlky[0x1];
-	u8         reserved_8[0x4];
+	u8         reserved_at_5c[0x4];
 
 	u8         counter_set_id[0x8];
 	u8         uar_page[0x18];
 
-	u8         reserved_9[0x8];
+	u8         reserved_at_80[0x8];
 	u8         user_index[0x18];
 
-	u8         reserved_10[0x3];
+	u8         reserved_at_a0[0x3];
 	u8         log_page_size[0x5];
 	u8         remote_qpn[0x18];
 
@@ -1797,66 +1797,66 @@ struct mlx5_ifc_qpc_bits {
 	struct mlx5_ifc_ads_bits secondary_address_path;
 
 	u8         log_ack_req_freq[0x4];
-	u8         reserved_11[0x4];
+	u8         reserved_at_384[0x4];
 	u8         log_sra_max[0x3];
-	u8         reserved_12[0x2];
+	u8         reserved_at_38b[0x2];
 	u8         retry_count[0x3];
 	u8         rnr_retry[0x3];
-	u8         reserved_13[0x1];
+	u8         reserved_at_393[0x1];
 	u8         fre[0x1];
 	u8         cur_rnr_retry[0x3];
 	u8         cur_retry_count[0x3];
-	u8         reserved_14[0x5];
+	u8         reserved_at_39b[0x5];
 
-	u8         reserved_15[0x20];
+	u8         reserved_at_3a0[0x20];
 
-	u8         reserved_16[0x8];
+	u8         reserved_at_3c0[0x8];
 	u8         next_send_psn[0x18];
 
-	u8         reserved_17[0x8];
+	u8         reserved_at_3e0[0x8];
 	u8         cqn_snd[0x18];
 
-	u8         reserved_18[0x40];
+	u8         reserved_at_400[0x40];
 
-	u8         reserved_19[0x8];
+	u8         reserved_at_440[0x8];
 	u8         last_acked_psn[0x18];
 
-	u8         reserved_20[0x8];
+	u8         reserved_at_460[0x8];
 	u8         ssn[0x18];
 
-	u8         reserved_21[0x8];
+	u8         reserved_at_480[0x8];
 	u8         log_rra_max[0x3];
-	u8         reserved_22[0x1];
+	u8         reserved_at_48b[0x1];
 	u8         atomic_mode[0x4];
 	u8         rre[0x1];
 	u8         rwe[0x1];
 	u8         rae[0x1];
-	u8         reserved_23[0x1];
+	u8         reserved_at_493[0x1];
 	u8         page_offset[0x6];
-	u8         reserved_24[0x3];
+	u8         reserved_at_49a[0x3];
 	u8         cd_slave_receive[0x1];
 	u8         cd_slave_send[0x1];
 	u8         cd_master[0x1];
 
-	u8         reserved_25[0x3];
+	u8         reserved_at_4a0[0x3];
 	u8         min_rnr_nak[0x5];
 	u8         next_rcv_psn[0x18];
 
-	u8         reserved_26[0x8];
+	u8         reserved_at_4c0[0x8];
 	u8         xrcd[0x18];
 
-	u8         reserved_27[0x8];
+	u8         reserved_at_4e0[0x8];
 	u8         cqn_rcv[0x18];
 
 	u8         dbr_addr[0x40];
 
 	u8         q_key[0x20];
 
-	u8         reserved_28[0x5];
+	u8         reserved_at_560[0x5];
 	u8         rq_type[0x3];
 	u8         srqn_rmpn[0x18];
 
-	u8         reserved_29[0x8];
+	u8         reserved_at_580[0x8];
 	u8         rmsn[0x18];
 
 	u8         hw_sq_wqebb_counter[0x10];
@@ -1866,33 +1866,33 @@ struct mlx5_ifc_qpc_bits {
 
 	u8         sw_rq_counter[0x20];
 
-	u8         reserved_30[0x20];
+	u8         reserved_at_600[0x20];
 
-	u8         reserved_31[0xf];
+	u8         reserved_at_620[0xf];
 	u8         cgs[0x1];
 	u8         cs_req[0x8];
 	u8         cs_res[0x8];
 
 	u8         dc_access_key[0x40];
 
-	u8         reserved_32[0xc0];
+	u8         reserved_at_680[0xc0];
 };
 
 struct mlx5_ifc_roce_addr_layout_bits {
 	u8         source_l3_address[16][0x8];
 
-	u8         reserved_0[0x3];
+	u8         reserved_at_80[0x3];
 	u8         vlan_valid[0x1];
 	u8         vlan_id[0xc];
 	u8         source_mac_47_32[0x10];
 
 	u8         source_mac_31_0[0x20];
 
-	u8         reserved_1[0x14];
+	u8         reserved_at_c0[0x14];
 	u8         roce_l3_type[0x4];
 	u8         roce_version[0x8];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_e0[0x20];
 };
 
 union mlx5_ifc_hca_cap_union_bits {
@@ -1904,7 +1904,7 @@ union mlx5_ifc_hca_cap_union_bits {
 	struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap;
 	struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap;
 	struct mlx5_ifc_e_switch_cap_bits e_switch_cap;
-	u8         reserved_0[0x8000];
+	u8         reserved_at_0[0x8000];
 };
 
 enum {
@@ -1914,24 +1914,24 @@ enum {
 };
 
 struct mlx5_ifc_flow_context_bits {
-	u8         reserved_0[0x20];
+	u8         reserved_at_0[0x20];
 
 	u8         group_id[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         flow_tag[0x18];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_60[0x10];
 	u8         action[0x10];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_80[0x8];
 	u8         destination_list_size[0x18];
 
-	u8         reserved_4[0x160];
+	u8         reserved_at_a0[0x160];
 
 	struct mlx5_ifc_fte_match_param_bits match_value;
 
-	u8         reserved_5[0x600];
+	u8         reserved_at_1200[0x600];
 
 	struct mlx5_ifc_dest_format_struct_bits destination[0];
 };
@@ -1944,43 +1944,43 @@ enum {
 struct mlx5_ifc_xrc_srqc_bits {
 	u8         state[0x4];
 	u8         log_xrc_srq_size[0x4];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         wq_signature[0x1];
 	u8         cont_srq[0x1];
-	u8         reserved_1[0x1];
+	u8         reserved_at_22[0x1];
 	u8         rlky[0x1];
 	u8         basic_cyclic_rcv_wqe[0x1];
 	u8         log_rq_stride[0x3];
 	u8         xrcd[0x18];
 
 	u8         page_offset[0x6];
-	u8         reserved_2[0x2];
+	u8         reserved_at_46[0x2];
 	u8         cqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         user_index_equal_xrc_srqn[0x1];
-	u8         reserved_4[0x1];
+	u8         reserved_at_81[0x1];
 	u8         log_page_size[0x6];
 	u8         user_index[0x18];
 
-	u8         reserved_5[0x20];
+	u8         reserved_at_a0[0x20];
 
-	u8         reserved_6[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         pd[0x18];
 
 	u8         lwm[0x10];
 	u8         wqe_cnt[0x10];
 
-	u8         reserved_7[0x40];
+	u8         reserved_at_100[0x40];
 
 	u8         db_record_addr_h[0x20];
 
 	u8         db_record_addr_l[0x1e];
-	u8         reserved_8[0x2];
+	u8         reserved_at_17e[0x2];
 
-	u8         reserved_9[0x80];
+	u8         reserved_at_180[0x80];
 };
 
 struct mlx5_ifc_traffic_counter_bits {
@@ -1990,16 +1990,16 @@ struct mlx5_ifc_traffic_counter_bits {
 };
 
 struct mlx5_ifc_tisc_bits {
-	u8         reserved_0[0xc];
+	u8         reserved_at_0[0xc];
 	u8         prio[0x4];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_2[0x100];
+	u8         reserved_at_20[0x100];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_120[0x8];
 	u8         transport_domain[0x18];
 
-	u8         reserved_4[0x3c0];
+	u8         reserved_at_140[0x3c0];
 };
 
 enum {
@@ -2024,31 +2024,31 @@ enum {
 };
 
 struct mlx5_ifc_tirc_bits {
-	u8         reserved_0[0x20];
+	u8         reserved_at_0[0x20];
 
 	u8         disp_type[0x4];
-	u8         reserved_1[0x1c];
+	u8         reserved_at_24[0x1c];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
-	u8         reserved_3[0x4];
+	u8         reserved_at_80[0x4];
 	u8         lro_timeout_period_usecs[0x10];
 	u8         lro_enable_mask[0x4];
 	u8         lro_max_ip_payload_size[0x8];
 
-	u8         reserved_4[0x40];
+	u8         reserved_at_a0[0x40];
 
-	u8         reserved_5[0x8];
+	u8         reserved_at_e0[0x8];
 	u8         inline_rqn[0x18];
 
 	u8         rx_hash_symmetric[0x1];
-	u8         reserved_6[0x1];
+	u8         reserved_at_101[0x1];
 	u8         tunneled_offload_en[0x1];
-	u8         reserved_7[0x5];
+	u8         reserved_at_103[0x5];
 	u8         indirect_table[0x18];
 
 	u8         rx_hash_fn[0x4];
-	u8         reserved_8[0x2];
+	u8         reserved_at_124[0x2];
 	u8         self_lb_block[0x2];
 	u8         transport_domain[0x18];
 
@@ -2058,7 +2058,7 @@ struct mlx5_ifc_tirc_bits {
 
 	struct mlx5_ifc_rx_hash_field_select_bits rx_hash_field_selector_inner;
 
-	u8         reserved_9[0x4c0];
+	u8         reserved_at_2c0[0x4c0];
 };
 
 enum {
@@ -2069,39 +2069,39 @@ enum {
 struct mlx5_ifc_srqc_bits {
 	u8         state[0x4];
 	u8         log_srq_size[0x4];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         wq_signature[0x1];
 	u8         cont_srq[0x1];
-	u8         reserved_1[0x1];
+	u8         reserved_at_22[0x1];
 	u8         rlky[0x1];
-	u8         reserved_2[0x1];
+	u8         reserved_at_24[0x1];
 	u8         log_rq_stride[0x3];
 	u8         xrcd[0x18];
 
 	u8         page_offset[0x6];
-	u8         reserved_3[0x2];
+	u8         reserved_at_46[0x2];
 	u8         cqn[0x18];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_60[0x20];
 
-	u8         reserved_5[0x2];
+	u8         reserved_at_80[0x2];
 	u8         log_page_size[0x6];
-	u8         reserved_6[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_7[0x20];
+	u8         reserved_at_a0[0x20];
 
-	u8         reserved_8[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         pd[0x18];
 
 	u8         lwm[0x10];
 	u8         wqe_cnt[0x10];
 
-	u8         reserved_9[0x40];
+	u8         reserved_at_100[0x40];
 
 	u8         dbr_addr[0x40];
 
-	u8         reserved_10[0x80];
+	u8         reserved_at_180[0x80];
 };
 
 enum {
@@ -2115,39 +2115,39 @@ struct mlx5_ifc_sqc_bits {
 	u8         cd_master[0x1];
 	u8         fre[0x1];
 	u8         flush_in_error_en[0x1];
-	u8         reserved_0[0x4];
+	u8         reserved_at_4[0x4];
 	u8         state[0x4];
-	u8         reserved_1[0x14];
+	u8         reserved_at_c[0x14];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_20[0x8];
 	u8         user_index[0x18];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_40[0x8];
 	u8         cqn[0x18];
 
-	u8         reserved_4[0xa0];
+	u8         reserved_at_60[0xa0];
 
 	u8         tis_lst_sz[0x10];
-	u8         reserved_5[0x10];
+	u8         reserved_at_110[0x10];
 
-	u8         reserved_6[0x40];
+	u8         reserved_at_120[0x40];
 
-	u8         reserved_7[0x8];
+	u8         reserved_at_160[0x8];
 	u8         tis_num_0[0x18];
 
 	struct mlx5_ifc_wq_bits wq;
 };
 
 struct mlx5_ifc_rqtc_bits {
-	u8         reserved_0[0xa0];
+	u8         reserved_at_0[0xa0];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_a0[0x10];
 	u8         rqt_max_size[0x10];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_c0[0x10];
 	u8         rqt_actual_size[0x10];
 
-	u8         reserved_3[0x6a0];
+	u8         reserved_at_e0[0x6a0];
 
 	struct mlx5_ifc_rq_num_bits rq_num[0];
 };
@@ -2165,27 +2165,27 @@ enum {
 
 struct mlx5_ifc_rqc_bits {
 	u8         rlky[0x1];
-	u8         reserved_0[0x2];
+	u8         reserved_at_1[0x2];
 	u8         vsd[0x1];
 	u8         mem_rq_type[0x4];
 	u8         state[0x4];
-	u8         reserved_1[0x1];
+	u8         reserved_at_c[0x1];
 	u8         flush_in_error_en[0x1];
-	u8         reserved_2[0x12];
+	u8         reserved_at_e[0x12];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_20[0x8];
 	u8         user_index[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_40[0x8];
 	u8         cqn[0x18];
 
 	u8         counter_set_id[0x8];
-	u8         reserved_5[0x18];
+	u8         reserved_at_68[0x18];
 
-	u8         reserved_6[0x8];
+	u8         reserved_at_80[0x8];
 	u8         rmpn[0x18];
 
-	u8         reserved_7[0xe0];
+	u8         reserved_at_a0[0xe0];
 
 	struct mlx5_ifc_wq_bits wq;
 };
@@ -2196,31 +2196,31 @@ enum {
 };
 
 struct mlx5_ifc_rmpc_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         state[0x4];
-	u8         reserved_1[0x14];
+	u8         reserved_at_c[0x14];
 
 	u8         basic_cyclic_rcv_wqe[0x1];
-	u8         reserved_2[0x1f];
+	u8         reserved_at_21[0x1f];
 
-	u8         reserved_3[0x140];
+	u8         reserved_at_40[0x140];
 
 	struct mlx5_ifc_wq_bits wq;
 };
 
 struct mlx5_ifc_nic_vport_context_bits {
-	u8         reserved_0[0x1f];
+	u8         reserved_at_0[0x1f];
 	u8         roce_en[0x1];
 
 	u8         arm_change_event[0x1];
-	u8         reserved_1[0x1a];
+	u8         reserved_at_21[0x1a];
 	u8         event_on_mtu[0x1];
 	u8         event_on_promisc_change[0x1];
 	u8         event_on_vlan_change[0x1];
 	u8         event_on_mc_address_change[0x1];
 	u8         event_on_uc_address_change[0x1];
 
-	u8         reserved_2[0xf0];
+	u8         reserved_at_40[0xf0];
 
 	u8         mtu[0x10];
 
@@ -2228,21 +2228,21 @@ struct mlx5_ifc_nic_vport_context_bits {
 	u8         port_guid[0x40];
 	u8         node_guid[0x40];
 
-	u8         reserved_3[0x140];
+	u8         reserved_at_200[0x140];
 	u8         qkey_violation_counter[0x10];
-	u8         reserved_4[0x430];
+	u8         reserved_at_350[0x430];
 
 	u8         promisc_uc[0x1];
 	u8         promisc_mc[0x1];
 	u8         promisc_all[0x1];
-	u8         reserved_5[0x2];
+	u8         reserved_at_783[0x2];
 	u8         allowed_list_type[0x3];
-	u8         reserved_6[0xc];
+	u8         reserved_at_788[0xc];
 	u8         allowed_list_size[0xc];
 
 	struct mlx5_ifc_mac_address_layout_bits permanent_address;
 
-	u8         reserved_7[0x20];
+	u8         reserved_at_7e0[0x20];
 
 	u8         current_uc_mac_address[0][0x40];
 };
@@ -2254,9 +2254,9 @@ enum {
 };
 
 struct mlx5_ifc_mkc_bits {
-	u8         reserved_0[0x1];
+	u8         reserved_at_0[0x1];
 	u8         free[0x1];
-	u8         reserved_1[0xd];
+	u8         reserved_at_2[0xd];
 	u8         small_fence_on_rdma_read_response[0x1];
 	u8         umr_en[0x1];
 	u8         a[0x1];
@@ -2265,19 +2265,19 @@ struct mlx5_ifc_mkc_bits {
 	u8         lw[0x1];
 	u8         lr[0x1];
 	u8         access_mode[0x2];
-	u8         reserved_2[0x8];
+	u8         reserved_at_18[0x8];
 
 	u8         qpn[0x18];
 	u8         mkey_7_0[0x8];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_40[0x20];
 
 	u8         length64[0x1];
 	u8         bsf_en[0x1];
 	u8         sync_umr[0x1];
-	u8         reserved_4[0x2];
+	u8         reserved_at_63[0x2];
 	u8         expected_sigerr_count[0x1];
-	u8         reserved_5[0x1];
+	u8         reserved_at_66[0x1];
 	u8         en_rinval[0x1];
 	u8         pd[0x18];
 
@@ -2287,18 +2287,18 @@ struct mlx5_ifc_mkc_bits {
 
 	u8         bsf_octword_size[0x20];
 
-	u8         reserved_6[0x80];
+	u8         reserved_at_120[0x80];
 
 	u8         translations_octword_size[0x20];
 
-	u8         reserved_7[0x1b];
+	u8         reserved_at_1c0[0x1b];
 	u8         log_page_size[0x5];
 
-	u8         reserved_8[0x20];
+	u8         reserved_at_1e0[0x20];
 };
 
 struct mlx5_ifc_pkey_bits {
-	u8         reserved_0[0x10];
+	u8         reserved_at_0[0x10];
 	u8         pkey[0x10];
 };
 
@@ -2309,19 +2309,19 @@ struct mlx5_ifc_array128_auto_bits {
 struct mlx5_ifc_hca_vport_context_bits {
 	u8         field_select[0x20];
 
-	u8         reserved_0[0xe0];
+	u8         reserved_at_20[0xe0];
 
 	u8         sm_virt_aware[0x1];
 	u8         has_smi[0x1];
 	u8         has_raw[0x1];
 	u8         grh_required[0x1];
-	u8         reserved_1[0xc];
+	u8         reserved_at_104[0xc];
 	u8         port_physical_state[0x4];
 	u8         vport_state_policy[0x4];
 	u8         port_state[0x4];
 	u8         vport_state[0x4];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_120[0x20];
 
 	u8         system_image_guid[0x40];
 
@@ -2337,33 +2337,33 @@ struct mlx5_ifc_hca_vport_context_bits {
 
 	u8         cap_mask2_field_select[0x20];
 
-	u8         reserved_3[0x80];
+	u8         reserved_at_280[0x80];
 
 	u8         lid[0x10];
-	u8         reserved_4[0x4];
+	u8         reserved_at_310[0x4];
 	u8         init_type_reply[0x4];
 	u8         lmc[0x3];
 	u8         subnet_timeout[0x5];
 
 	u8         sm_lid[0x10];
 	u8         sm_sl[0x4];
-	u8         reserved_5[0xc];
+	u8         reserved_at_334[0xc];
 
 	u8         qkey_violation_counter[0x10];
 	u8         pkey_violation_counter[0x10];
 
-	u8         reserved_6[0xca0];
+	u8         reserved_at_360[0xca0];
 };
 
 struct mlx5_ifc_esw_vport_context_bits {
-	u8         reserved_0[0x3];
+	u8         reserved_at_0[0x3];
 	u8         vport_svlan_strip[0x1];
 	u8         vport_cvlan_strip[0x1];
 	u8         vport_svlan_insert[0x1];
 	u8         vport_cvlan_insert[0x2];
-	u8         reserved_1[0x18];
+	u8         reserved_at_8[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_20[0x20];
 
 	u8         svlan_cfi[0x1];
 	u8         svlan_pcp[0x3];
@@ -2372,7 +2372,7 @@ struct mlx5_ifc_esw_vport_context_bits {
 	u8         cvlan_pcp[0x3];
 	u8         cvlan_id[0xc];
 
-	u8         reserved_3[0x7a0];
+	u8         reserved_at_60[0x7a0];
 };
 
 enum {
@@ -2387,41 +2387,41 @@ enum {
 
 struct mlx5_ifc_eqc_bits {
 	u8         status[0x4];
-	u8         reserved_0[0x9];
+	u8         reserved_at_4[0x9];
 	u8         ec[0x1];
 	u8         oi[0x1];
-	u8         reserved_1[0x5];
+	u8         reserved_at_f[0x5];
 	u8         st[0x4];
-	u8         reserved_2[0x8];
+	u8         reserved_at_18[0x8];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_20[0x20];
 
-	u8         reserved_4[0x14];
+	u8         reserved_at_40[0x14];
 	u8         page_offset[0x6];
-	u8         reserved_5[0x6];
+	u8         reserved_at_5a[0x6];
 
-	u8         reserved_6[0x3];
+	u8         reserved_at_60[0x3];
 	u8         log_eq_size[0x5];
 	u8         uar_page[0x18];
 
-	u8         reserved_7[0x20];
+	u8         reserved_at_80[0x20];
 
-	u8         reserved_8[0x18];
+	u8         reserved_at_a0[0x18];
 	u8         intr[0x8];
 
-	u8         reserved_9[0x3];
+	u8         reserved_at_c0[0x3];
 	u8         log_page_size[0x5];
-	u8         reserved_10[0x18];
+	u8         reserved_at_c8[0x18];
 
-	u8         reserved_11[0x60];
+	u8         reserved_at_e0[0x60];
 
-	u8         reserved_12[0x8];
+	u8         reserved_at_140[0x8];
 	u8         consumer_counter[0x18];
 
-	u8         reserved_13[0x8];
+	u8         reserved_at_160[0x8];
 	u8         producer_counter[0x18];
 
-	u8         reserved_14[0x80];
+	u8         reserved_at_180[0x80];
 };
 
 enum {
@@ -2445,14 +2445,14 @@ enum {
 };
 
 struct mlx5_ifc_dctc_bits {
-	u8         reserved_0[0x4];
+	u8         reserved_at_0[0x4];
 	u8         state[0x4];
-	u8         reserved_1[0x18];
+	u8         reserved_at_8[0x18];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_20[0x8];
 	u8         user_index[0x18];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_40[0x8];
 	u8         cqn[0x18];
 
 	u8         counter_set_id[0x8];
@@ -2464,45 +2464,45 @@ struct mlx5_ifc_dctc_bits {
 	u8         latency_sensitive[0x1];
 	u8         rlky[0x1];
 	u8         free_ar[0x1];
-	u8         reserved_4[0xd];
+	u8         reserved_at_73[0xd];
 
-	u8         reserved_5[0x8];
+	u8         reserved_at_80[0x8];
 	u8         cs_res[0x8];
-	u8         reserved_6[0x3];
+	u8         reserved_at_90[0x3];
 	u8         min_rnr_nak[0x5];
-	u8         reserved_7[0x8];
+	u8         reserved_at_98[0x8];
 
-	u8         reserved_8[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         srqn[0x18];
 
-	u8         reserved_9[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         pd[0x18];
 
 	u8         tclass[0x8];
-	u8         reserved_10[0x4];
+	u8         reserved_at_e8[0x4];
 	u8         flow_label[0x14];
 
 	u8         dc_access_key[0x40];
 
-	u8         reserved_11[0x5];
+	u8         reserved_at_140[0x5];
 	u8         mtu[0x3];
 	u8         port[0x8];
 	u8         pkey_index[0x10];
 
-	u8         reserved_12[0x8];
+	u8         reserved_at_160[0x8];
 	u8         my_addr_index[0x8];
-	u8         reserved_13[0x8];
+	u8         reserved_at_170[0x8];
 	u8         hop_limit[0x8];
 
 	u8         dc_access_key_violation_count[0x20];
 
-	u8         reserved_14[0x14];
+	u8         reserved_at_1a0[0x14];
 	u8         dei_cfi[0x1];
 	u8         eth_prio[0x3];
 	u8         ecn[0x2];
 	u8         dscp[0x6];
 
-	u8         reserved_15[0x40];
+	u8         reserved_at_1c0[0x40];
 };
 
 enum {
@@ -2524,54 +2524,54 @@ enum {
 
 struct mlx5_ifc_cqc_bits {
 	u8         status[0x4];
-	u8         reserved_0[0x4];
+	u8         reserved_at_4[0x4];
 	u8         cqe_sz[0x3];
 	u8         cc[0x1];
-	u8         reserved_1[0x1];
+	u8         reserved_at_c[0x1];
 	u8         scqe_break_moderation_en[0x1];
 	u8         oi[0x1];
-	u8         reserved_2[0x2];
+	u8         reserved_at_f[0x2];
 	u8         cqe_zip_en[0x1];
 	u8         mini_cqe_res_format[0x2];
 	u8         st[0x4];
-	u8         reserved_3[0x8];
+	u8         reserved_at_18[0x8];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_20[0x20];
 
-	u8         reserved_5[0x14];
+	u8         reserved_at_40[0x14];
 	u8         page_offset[0x6];
-	u8         reserved_6[0x6];
+	u8         reserved_at_5a[0x6];
 
-	u8         reserved_7[0x3];
+	u8         reserved_at_60[0x3];
 	u8         log_cq_size[0x5];
 	u8         uar_page[0x18];
 
-	u8         reserved_8[0x4];
+	u8         reserved_at_80[0x4];
 	u8         cq_period[0xc];
 	u8         cq_max_count[0x10];
 
-	u8         reserved_9[0x18];
+	u8         reserved_at_a0[0x18];
 	u8         c_eqn[0x8];
 
-	u8         reserved_10[0x3];
+	u8         reserved_at_c0[0x3];
 	u8         log_page_size[0x5];
-	u8         reserved_11[0x18];
+	u8         reserved_at_c8[0x18];
 
-	u8         reserved_12[0x20];
+	u8         reserved_at_e0[0x20];
 
-	u8         reserved_13[0x8];
+	u8         reserved_at_100[0x8];
 	u8         last_notified_index[0x18];
 
-	u8         reserved_14[0x8];
+	u8         reserved_at_120[0x8];
 	u8         last_solicit_index[0x18];
 
-	u8         reserved_15[0x8];
+	u8         reserved_at_140[0x8];
 	u8         consumer_counter[0x18];
 
-	u8         reserved_16[0x8];
+	u8         reserved_at_160[0x8];
 	u8         producer_counter[0x18];
 
-	u8         reserved_17[0x40];
+	u8         reserved_at_180[0x40];
 
 	u8         dbr_addr[0x40];
 };
@@ -2580,16 +2580,16 @@ union mlx5_ifc_cong_control_roce_ecn_auto_bits {
 	struct mlx5_ifc_cong_control_802_1qau_rp_bits cong_control_802_1qau_rp;
 	struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits cong_control_r_roce_ecn_rp;
 	struct mlx5_ifc_cong_control_r_roce_ecn_np_bits cong_control_r_roce_ecn_np;
-	u8         reserved_0[0x800];
+	u8         reserved_at_0[0x800];
 };
 
 struct mlx5_ifc_query_adapter_param_block_bits {
-	u8         reserved_0[0xc0];
+	u8         reserved_at_0[0xc0];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         ieee_vendor_id[0x18];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_e0[0x10];
 	u8         vsd_vendor_id[0x10];
 
 	u8         vsd[208][0x8];
@@ -2600,14 +2600,14 @@ struct mlx5_ifc_query_adapter_param_block_bits {
 union mlx5_ifc_modify_field_select_resize_field_select_auto_bits {
 	struct mlx5_ifc_modify_field_select_bits modify_field_select;
 	struct mlx5_ifc_resize_field_select_bits resize_field_select;
-	u8         reserved_0[0x20];
+	u8         reserved_at_0[0x20];
 };
 
 union mlx5_ifc_field_select_802_1_r_roce_auto_bits {
 	struct mlx5_ifc_field_select_802_1qau_rp_bits field_select_802_1qau_rp;
 	struct mlx5_ifc_field_select_r_roce_rp_bits field_select_r_roce_rp;
 	struct mlx5_ifc_field_select_r_roce_np_bits field_select_r_roce_np;
-	u8         reserved_0[0x20];
+	u8         reserved_at_0[0x20];
 };
 
 union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits {
@@ -2619,7 +2619,7 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits {
 	struct mlx5_ifc_eth_per_prio_grp_data_layout_bits eth_per_prio_grp_data_layout;
 	struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits eth_per_traffic_grp_data_layout;
 	struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs;
-	u8         reserved_0[0x7c0];
+	u8         reserved_at_0[0x7c0];
 };
 
 union mlx5_ifc_event_auto_bits {
@@ -2635,23 +2635,23 @@ union mlx5_ifc_event_auto_bits {
 	struct mlx5_ifc_db_bf_congestion_event_bits db_bf_congestion_event;
 	struct mlx5_ifc_stall_vl_event_bits stall_vl_event;
 	struct mlx5_ifc_cmd_inter_comp_event_bits cmd_inter_comp_event;
-	u8         reserved_0[0xe0];
+	u8         reserved_at_0[0xe0];
 };
 
 struct mlx5_ifc_health_buffer_bits {
-	u8         reserved_0[0x100];
+	u8         reserved_at_0[0x100];
 
 	u8         assert_existptr[0x20];
 
 	u8         assert_callra[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_140[0x40];
 
 	u8         fw_version[0x20];
 
 	u8         hw_id[0x20];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_1c0[0x20];
 
 	u8         irisc_index[0x8];
 	u8         synd[0x8];
@@ -2660,20 +2660,20 @@ struct mlx5_ifc_health_buffer_bits {
 
 struct mlx5_ifc_register_loopback_control_bits {
 	u8         no_lb[0x1];
-	u8         reserved_0[0x7];
+	u8         reserved_at_1[0x7];
 	u8         port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_2[0x60];
+	u8         reserved_at_20[0x60];
 };
 
 struct mlx5_ifc_teardown_hca_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 enum {
@@ -2683,108 +2683,108 @@ enum {
 
 struct mlx5_ifc_teardown_hca_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_40[0x10];
 	u8         profile[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_sqerr2rts_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_sqerr2rts_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_a0[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_5[0x80];
+	u8         reserved_at_800[0x80];
 };
 
 struct mlx5_ifc_sqd2rts_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_sqd2rts_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_a0[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_5[0x80];
+	u8         reserved_at_800[0x80];
 };
 
 struct mlx5_ifc_set_roce_address_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_set_roce_address_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         roce_address_index[0x10];
-	u8         reserved_2[0x10];
+	u8         reserved_at_50[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	struct mlx5_ifc_roce_addr_layout_bits roce_address;
 };
 
 struct mlx5_ifc_set_mad_demux_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 enum {
@@ -2794,89 +2794,89 @@ enum {
 
 struct mlx5_ifc_set_mad_demux_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_40[0x20];
 
-	u8         reserved_3[0x6];
+	u8         reserved_at_60[0x6];
 	u8         demux_mode[0x2];
-	u8         reserved_4[0x18];
+	u8         reserved_at_68[0x18];
 };
 
 struct mlx5_ifc_set_l2_table_entry_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_set_l2_table_entry_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x60];
+	u8         reserved_at_40[0x60];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_index[0x18];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_c0[0x20];
 
-	u8         reserved_5[0x13];
+	u8         reserved_at_e0[0x13];
 	u8         vlan_valid[0x1];
 	u8         vlan[0xc];
 
 	struct mlx5_ifc_mac_address_layout_bits mac_address;
 
-	u8         reserved_6[0xc0];
+	u8         reserved_at_140[0xc0];
 };
 
 struct mlx5_ifc_set_issi_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_set_issi_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_40[0x10];
 	u8         current_issi[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_set_hca_cap_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_set_hca_cap_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	union mlx5_ifc_hca_cap_union_bits capability;
 };
@@ -2890,156 +2890,156 @@ enum {
 
 struct mlx5_ifc_set_fte_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_set_fte_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_5[0x18];
+	u8         reserved_at_c0[0x18];
 	u8         modify_enable_mask[0x8];
 
-	u8         reserved_6[0x20];
+	u8         reserved_at_e0[0x20];
 
 	u8         flow_index[0x20];
 
-	u8         reserved_7[0xe0];
+	u8         reserved_at_120[0xe0];
 
 	struct mlx5_ifc_flow_context_bits flow_context;
 };
 
 struct mlx5_ifc_rts2rts_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_rts2rts_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_a0[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_5[0x80];
+	u8         reserved_at_800[0x80];
 };
 
 struct mlx5_ifc_rtr2rts_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_rtr2rts_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_a0[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_5[0x80];
+	u8         reserved_at_800[0x80];
 };
 
 struct mlx5_ifc_rst2init_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_rst2init_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_a0[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_5[0x80];
+	u8         reserved_at_800[0x80];
 };
 
 struct mlx5_ifc_query_xrc_srq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry;
 
-	u8         reserved_2[0x600];
+	u8         reserved_at_280[0x600];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_query_xrc_srq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         xrc_srqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 enum {
@@ -3049,13 +3049,13 @@ enum {
 
 struct mlx5_ifc_query_vport_state_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_40[0x20];
 
-	u8         reserved_2[0x18];
+	u8         reserved_at_60[0x18];
 	u8         admin_state[0x4];
 	u8         state[0x4];
 };
@@ -3067,25 +3067,25 @@ enum {
 
 struct mlx5_ifc_query_vport_state_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xf];
+	u8         reserved_at_41[0xf];
 	u8         vport_number[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_vport_counter_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_traffic_counter_bits received_errors;
 
@@ -3111,7 +3111,7 @@ struct mlx5_ifc_query_vport_counter_out_bits {
 
 	struct mlx5_ifc_traffic_counter_bits transmitted_eth_multicast;
 
-	u8         reserved_2[0xa00];
+	u8         reserved_at_680[0xa00];
 };
 
 enum {
@@ -3120,328 +3120,328 @@ enum {
 
 struct mlx5_ifc_query_vport_counter_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xf];
+	u8         reserved_at_41[0xf];
 	u8         vport_number[0x10];
 
-	u8         reserved_3[0x60];
+	u8         reserved_at_60[0x60];
 
 	u8         clear[0x1];
-	u8         reserved_4[0x1f];
+	u8         reserved_at_c1[0x1f];
 
-	u8         reserved_5[0x20];
+	u8         reserved_at_e0[0x20];
 };
 
 struct mlx5_ifc_query_tis_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_tisc_bits tis_context;
 };
 
 struct mlx5_ifc_query_tis_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         tisn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_tir_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_tirc_bits tir_context;
 };
 
 struct mlx5_ifc_query_tir_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         tirn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_srq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_srqc_bits srq_context_entry;
 
-	u8         reserved_2[0x600];
+	u8         reserved_at_280[0x600];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_query_srq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         srqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_sq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_sqc_bits sq_context;
 };
 
 struct mlx5_ifc_query_sq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         sqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_special_contexts_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_40[0x20];
 
 	u8         resd_lkey[0x20];
 };
 
 struct mlx5_ifc_query_special_contexts_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_query_rqt_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_rqtc_bits rqt_context;
 };
 
 struct mlx5_ifc_query_rqt_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rqtn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_rq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_rqc_bits rq_context;
 };
 
 struct mlx5_ifc_query_rq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_roce_address_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_roce_addr_layout_bits roce_address;
 };
 
 struct mlx5_ifc_query_roce_address_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         roce_address_index[0x10];
-	u8         reserved_2[0x10];
+	u8         reserved_at_50[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_rmp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_rmpc_bits rmp_context;
 };
 
 struct mlx5_ifc_query_rmp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rmpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_a0[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_3[0x80];
+	u8         reserved_at_800[0x80];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_query_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_q_counter_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         rx_write_requests[0x20];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_a0[0x20];
 
 	u8         rx_read_requests[0x20];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_e0[0x20];
 
 	u8         rx_atomic_requests[0x20];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_120[0x20];
 
 	u8         rx_dct_connect[0x20];
 
-	u8         reserved_5[0x20];
+	u8         reserved_at_160[0x20];
 
 	u8         out_of_buffer[0x20];
 
-	u8         reserved_6[0x20];
+	u8         reserved_at_1a0[0x20];
 
 	u8         out_of_sequence[0x20];
 
-	u8         reserved_7[0x620];
+	u8         reserved_at_1e0[0x620];
 };
 
 struct mlx5_ifc_query_q_counter_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x80];
+	u8         reserved_at_40[0x80];
 
 	u8         clear[0x1];
-	u8         reserved_3[0x1f];
+	u8         reserved_at_c1[0x1f];
 
-	u8         reserved_4[0x18];
+	u8         reserved_at_e0[0x18];
 	u8         counter_set_id[0x8];
 };
 
 struct mlx5_ifc_query_pages_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_40[0x10];
 	u8         function_id[0x10];
 
 	u8         num_pages[0x20];
@@ -3455,55 +3455,55 @@ enum {
 
 struct mlx5_ifc_query_pages_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_40[0x10];
 	u8         function_id[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_nic_vport_context_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_nic_vport_context_bits nic_vport_context;
 };
 
 struct mlx5_ifc_query_nic_vport_context_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xf];
+	u8         reserved_at_41[0xf];
 	u8         vport_number[0x10];
 
-	u8         reserved_3[0x5];
+	u8         reserved_at_60[0x5];
 	u8         allowed_list_type[0x3];
-	u8         reserved_4[0x18];
+	u8         reserved_at_68[0x18];
 };
 
 struct mlx5_ifc_query_mkey_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_mkc_bits memory_key_mkey_entry;
 
-	u8         reserved_2[0x600];
+	u8         reserved_at_280[0x600];
 
 	u8         bsf0_klm0_pas_mtt0_1[16][0x8];
 
@@ -3512,265 +3512,265 @@ struct mlx5_ifc_query_mkey_out_bits {
 
 struct mlx5_ifc_query_mkey_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         mkey_index[0x18];
 
 	u8         pg_access[0x1];
-	u8         reserved_3[0x1f];
+	u8         reserved_at_61[0x1f];
 };
 
 struct mlx5_ifc_query_mad_demux_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         mad_dumux_parameters_block[0x20];
 };
 
 struct mlx5_ifc_query_mad_demux_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_query_l2_table_entry_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0xa0];
+	u8         reserved_at_40[0xa0];
 
-	u8         reserved_2[0x13];
+	u8         reserved_at_e0[0x13];
 	u8         vlan_valid[0x1];
 	u8         vlan[0xc];
 
 	struct mlx5_ifc_mac_address_layout_bits mac_address;
 
-	u8         reserved_3[0xc0];
+	u8         reserved_at_140[0xc0];
 };
 
 struct mlx5_ifc_query_l2_table_entry_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x60];
+	u8         reserved_at_40[0x60];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_index[0x18];
 
-	u8         reserved_4[0x140];
+	u8         reserved_at_c0[0x140];
 };
 
 struct mlx5_ifc_query_issi_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_40[0x10];
 	u8         current_issi[0x10];
 
-	u8         reserved_2[0xa0];
+	u8         reserved_at_60[0xa0];
 
-	u8         supported_issi_reserved[76][0x8];
+	u8         reserved_at_100[76][0x8];
 	u8         supported_issi_dw0[0x20];
 };
 
 struct mlx5_ifc_query_issi_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_query_hca_vport_pkey_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_pkey_bits pkey[0];
 };
 
 struct mlx5_ifc_query_hca_vport_pkey_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xb];
+	u8         reserved_at_41[0xb];
 	u8         port_num[0x4];
 	u8         vport_number[0x10];
 
-	u8         reserved_3[0x10];
+	u8         reserved_at_60[0x10];
 	u8         pkey_index[0x10];
 };
 
 struct mlx5_ifc_query_hca_vport_gid_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_40[0x20];
 
 	u8         gids_num[0x10];
-	u8         reserved_2[0x10];
+	u8         reserved_at_70[0x10];
 
 	struct mlx5_ifc_array128_auto_bits gid[0];
 };
 
 struct mlx5_ifc_query_hca_vport_gid_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xb];
+	u8         reserved_at_41[0xb];
 	u8         port_num[0x4];
 	u8         vport_number[0x10];
 
-	u8         reserved_3[0x10];
+	u8         reserved_at_60[0x10];
 	u8         gid_index[0x10];
 };
 
 struct mlx5_ifc_query_hca_vport_context_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_hca_vport_context_bits hca_vport_context;
 };
 
 struct mlx5_ifc_query_hca_vport_context_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xb];
+	u8         reserved_at_41[0xb];
 	u8         port_num[0x4];
 	u8         vport_number[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_hca_cap_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	union mlx5_ifc_hca_cap_union_bits capability;
 };
 
 struct mlx5_ifc_query_hca_cap_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_query_flow_table_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x80];
+	u8         reserved_at_40[0x80];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         level[0x8];
-	u8         reserved_3[0x8];
+	u8         reserved_at_d0[0x8];
 	u8         log_size[0x8];
 
-	u8         reserved_4[0x120];
+	u8         reserved_at_e0[0x120];
 };
 
 struct mlx5_ifc_query_flow_table_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_5[0x140];
+	u8         reserved_at_c0[0x140];
 };
 
 struct mlx5_ifc_query_fte_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x1c0];
+	u8         reserved_at_40[0x1c0];
 
 	struct mlx5_ifc_flow_context_bits flow_context;
 };
 
 struct mlx5_ifc_query_fte_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_5[0x40];
+	u8         reserved_at_c0[0x40];
 
 	u8         flow_index[0x20];
 
-	u8         reserved_6[0xe0];
+	u8         reserved_at_120[0xe0];
 };
 
 enum {
@@ -3781,84 +3781,84 @@ enum {
 
 struct mlx5_ifc_query_flow_group_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0xa0];
+	u8         reserved_at_40[0xa0];
 
 	u8         start_flow_index[0x20];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_100[0x20];
 
 	u8         end_flow_index[0x20];
 
-	u8         reserved_3[0xa0];
+	u8         reserved_at_140[0xa0];
 
-	u8         reserved_4[0x18];
+	u8         reserved_at_1e0[0x18];
 	u8         match_criteria_enable[0x8];
 
 	struct mlx5_ifc_fte_match_param_bits match_criteria;
 
-	u8         reserved_5[0xe00];
+	u8         reserved_at_1200[0xe00];
 };
 
 struct mlx5_ifc_query_flow_group_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
 	u8         group_id[0x20];
 
-	u8         reserved_5[0x120];
+	u8         reserved_at_e0[0x120];
 };
 
 struct mlx5_ifc_query_esw_vport_context_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_esw_vport_context_bits esw_vport_context;
 };
 
 struct mlx5_ifc_query_esw_vport_context_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xf];
+	u8         reserved_at_41[0xf];
 	u8         vport_number[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_modify_esw_vport_context_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_esw_vport_context_fields_select_bits {
-	u8         reserved[0x1c];
+	u8         reserved_at_0[0x1c];
 	u8         vport_cvlan_insert[0x1];
 	u8         vport_svlan_insert[0x1];
 	u8         vport_cvlan_strip[0x1];
@@ -3867,13 +3867,13 @@ struct mlx5_ifc_esw_vport_context_fields_select_bits {
 
 struct mlx5_ifc_modify_esw_vport_context_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xf];
+	u8         reserved_at_41[0xf];
 	u8         vport_number[0x10];
 
 	struct mlx5_ifc_esw_vport_context_fields_select_bits field_select;
@@ -3883,124 +3883,124 @@ struct mlx5_ifc_modify_esw_vport_context_in_bits {
 
 struct mlx5_ifc_query_eq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_eqc_bits eq_context_entry;
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_280[0x40];
 
 	u8         event_bitmask[0x40];
 
-	u8         reserved_3[0x580];
+	u8         reserved_at_300[0x580];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_query_eq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x18];
+	u8         reserved_at_40[0x18];
 	u8         eq_number[0x8];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_dct_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_dctc_bits dct_context_entry;
 
-	u8         reserved_2[0x180];
+	u8         reserved_at_280[0x180];
 };
 
 struct mlx5_ifc_query_dct_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         dctn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_cq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_cqc_bits cq_context;
 
-	u8         reserved_2[0x600];
+	u8         reserved_at_280[0x600];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_query_cq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         cqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_cong_status_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_40[0x20];
 
 	u8         enable[0x1];
 	u8         tag_enable[0x1];
-	u8         reserved_2[0x1e];
+	u8         reserved_at_62[0x1e];
 };
 
 struct mlx5_ifc_query_cong_status_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x18];
+	u8         reserved_at_40[0x18];
 	u8         priority[0x4];
 	u8         cong_protocol[0x4];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_cong_statistics_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         cur_flows[0x20];
 
@@ -4014,7 +4014,7 @@ struct mlx5_ifc_query_cong_statistics_out_bits {
 
 	u8         cnp_handled_low[0x20];
 
-	u8         reserved_2[0x100];
+	u8         reserved_at_140[0x100];
 
 	u8         time_stamp_high[0x20];
 
@@ -4030,453 +4030,455 @@ struct mlx5_ifc_query_cong_statistics_out_bits {
 
 	u8         cnps_sent_low[0x20];
 
-	u8         reserved_3[0x560];
+	u8         reserved_at_320[0x560];
 };
 
 struct mlx5_ifc_query_cong_statistics_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         clear[0x1];
-	u8         reserved_2[0x1f];
+	u8         reserved_at_41[0x1f];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_cong_params_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	union mlx5_ifc_cong_control_roce_ecn_auto_bits congestion_parameters;
 };
 
 struct mlx5_ifc_query_cong_params_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x1c];
+	u8         reserved_at_40[0x1c];
 	u8         cong_protocol[0x4];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_query_adapter_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_query_adapter_param_block_bits query_adapter_struct;
 };
 
 struct mlx5_ifc_query_adapter_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_qp_2rst_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_qp_2rst_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_qp_2err_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_qp_2err_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_page_fault_resume_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_page_fault_resume_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         error[0x1];
-	u8         reserved_2[0x4];
+	u8         reserved_at_41[0x4];
 	u8         rdma[0x1];
 	u8         read_write[0x1];
 	u8         req_res[0x1];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_nop_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_nop_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_vport_state_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_vport_state_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xf];
+	u8         reserved_at_41[0xf];
 	u8         vport_number[0x10];
 
-	u8         reserved_3[0x18];
+	u8         reserved_at_60[0x18];
 	u8         admin_state[0x4];
-	u8         reserved_4[0x4];
+	u8         reserved_at_7c[0x4];
 };
 
 struct mlx5_ifc_modify_tis_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_tis_bitmask_bits {
-	u8         reserved_0[0x20];
+	u8         reserved_at_0[0x20];
 
-	u8         reserved_1[0x1f];
+	u8         reserved_at_20[0x1f];
 	u8         prio[0x1];
 };
 
 struct mlx5_ifc_modify_tis_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         tisn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	struct mlx5_ifc_modify_tis_bitmask_bits bitmask;
 
-	u8         reserved_4[0x40];
+	u8         reserved_at_c0[0x40];
 
 	struct mlx5_ifc_tisc_bits ctx;
 };
 
 struct mlx5_ifc_modify_tir_bitmask_bits {
-	u8	   reserved_0[0x20];
+	u8	   reserved_at_0[0x20];
 
-	u8         reserved_1[0x1b];
+	u8         reserved_at_20[0x1b];
 	u8         self_lb_en[0x1];
-	u8         reserved_2[0x3];
+	u8         reserved_at_3c[0x1];
+	u8         hash[0x1];
+	u8         reserved_at_3e[0x1];
 	u8         lro[0x1];
 };
 
 struct mlx5_ifc_modify_tir_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_tir_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         tirn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	struct mlx5_ifc_modify_tir_bitmask_bits bitmask;
 
-	u8         reserved_4[0x40];
+	u8         reserved_at_c0[0x40];
 
 	struct mlx5_ifc_tirc_bits ctx;
 };
 
 struct mlx5_ifc_modify_sq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_sq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         sq_state[0x4];
-	u8         reserved_2[0x4];
+	u8         reserved_at_44[0x4];
 	u8         sqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         modify_bitmask[0x40];
 
-	u8         reserved_4[0x40];
+	u8         reserved_at_c0[0x40];
 
 	struct mlx5_ifc_sqc_bits ctx;
 };
 
 struct mlx5_ifc_modify_rqt_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_rqt_bitmask_bits {
-	u8	   reserved[0x20];
+	u8	   reserved_at_0[0x20];
 
-	u8         reserved1[0x1f];
+	u8         reserved_at_20[0x1f];
 	u8         rqn_list[0x1];
 };
 
 struct mlx5_ifc_modify_rqt_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rqtn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	struct mlx5_ifc_rqt_bitmask_bits bitmask;
 
-	u8         reserved_4[0x40];
+	u8         reserved_at_c0[0x40];
 
 	struct mlx5_ifc_rqtc_bits ctx;
 };
 
 struct mlx5_ifc_modify_rq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_rq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         rq_state[0x4];
-	u8         reserved_2[0x4];
+	u8         reserved_at_44[0x4];
 	u8         rqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         modify_bitmask[0x40];
 
-	u8         reserved_4[0x40];
+	u8         reserved_at_c0[0x40];
 
 	struct mlx5_ifc_rqc_bits ctx;
 };
 
 struct mlx5_ifc_modify_rmp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_rmp_bitmask_bits {
-	u8	   reserved[0x20];
+	u8	   reserved_at_0[0x20];
 
-	u8         reserved1[0x1f];
+	u8         reserved_at_20[0x1f];
 	u8         lwm[0x1];
 };
 
 struct mlx5_ifc_modify_rmp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         rmp_state[0x4];
-	u8         reserved_2[0x4];
+	u8         reserved_at_44[0x4];
 	u8         rmpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	struct mlx5_ifc_rmp_bitmask_bits bitmask;
 
-	u8         reserved_4[0x40];
+	u8         reserved_at_c0[0x40];
 
 	struct mlx5_ifc_rmpc_bits ctx;
 };
 
 struct mlx5_ifc_modify_nic_vport_context_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_nic_vport_field_select_bits {
-	u8         reserved_0[0x19];
+	u8         reserved_at_0[0x19];
 	u8         mtu[0x1];
 	u8         change_event[0x1];
 	u8         promisc[0x1];
 	u8         permanent_address[0x1];
 	u8         addresses_list[0x1];
 	u8         roce_en[0x1];
-	u8         reserved_1[0x1];
+	u8         reserved_at_1f[0x1];
 };
 
 struct mlx5_ifc_modify_nic_vport_context_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xf];
+	u8         reserved_at_41[0xf];
 	u8         vport_number[0x10];
 
 	struct mlx5_ifc_modify_nic_vport_field_select_bits field_select;
 
-	u8         reserved_3[0x780];
+	u8         reserved_at_80[0x780];
 
 	struct mlx5_ifc_nic_vport_context_bits nic_vport_context;
 };
 
 struct mlx5_ifc_modify_hca_vport_context_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_hca_vport_context_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_2[0xb];
+	u8         reserved_at_41[0xb];
 	u8         port_num[0x4];
 	u8         vport_number[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	struct mlx5_ifc_hca_vport_context_bits hca_vport_context;
 };
 
 struct mlx5_ifc_modify_cq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 enum {
@@ -4486,83 +4488,83 @@ enum {
 
 struct mlx5_ifc_modify_cq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         cqn[0x18];
 
 	union mlx5_ifc_modify_field_select_resize_field_select_auto_bits modify_field_select_resize_field_select;
 
 	struct mlx5_ifc_cqc_bits cq_context;
 
-	u8         reserved_3[0x600];
+	u8         reserved_at_280[0x600];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_modify_cong_status_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_cong_status_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x18];
+	u8         reserved_at_40[0x18];
 	u8         priority[0x4];
 	u8         cong_protocol[0x4];
 
 	u8         enable[0x1];
 	u8         tag_enable[0x1];
-	u8         reserved_3[0x1e];
+	u8         reserved_at_62[0x1e];
 };
 
 struct mlx5_ifc_modify_cong_params_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_cong_params_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x1c];
+	u8         reserved_at_40[0x1c];
 	u8         cong_protocol[0x4];
 
 	union mlx5_ifc_field_select_802_1_r_roce_auto_bits field_select;
 
-	u8         reserved_3[0x80];
+	u8         reserved_at_80[0x80];
 
 	union mlx5_ifc_cong_control_roce_ecn_auto_bits congestion_parameters;
 };
 
 struct mlx5_ifc_manage_pages_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
 	u8         output_num_entries[0x20];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         pas[0][0x40];
 };
@@ -4575,12 +4577,12 @@ enum {
 
 struct mlx5_ifc_manage_pages_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_40[0x10];
 	u8         function_id[0x10];
 
 	u8         input_num_entries[0x20];
@@ -4590,117 +4592,117 @@ struct mlx5_ifc_manage_pages_in_bits {
 
 struct mlx5_ifc_mad_ifc_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         response_mad_packet[256][0x8];
 };
 
 struct mlx5_ifc_mad_ifc_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         remote_lid[0x10];
-	u8         reserved_2[0x8];
+	u8         reserved_at_50[0x8];
 	u8         port[0x8];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         mad[256][0x8];
 };
 
 struct mlx5_ifc_init_hca_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_init_hca_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_init2rtr_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_init2rtr_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_a0[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_5[0x80];
+	u8         reserved_at_800[0x80];
 };
 
 struct mlx5_ifc_init2init_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_init2init_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_a0[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_5[0x80];
+	u8         reserved_at_800[0x80];
 };
 
 struct mlx5_ifc_get_dropped_packet_log_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         packet_headers_log[128][0x8];
 
@@ -4709,1029 +4711,1029 @@ struct mlx5_ifc_get_dropped_packet_log_out_bits {
 
 struct mlx5_ifc_get_dropped_packet_log_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_gen_eqe_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x18];
+	u8         reserved_at_40[0x18];
 	u8         eq_number[0x8];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         eqe[64][0x8];
 };
 
 struct mlx5_ifc_gen_eq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_enable_hca_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_40[0x20];
 };
 
 struct mlx5_ifc_enable_hca_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_40[0x10];
 	u8         function_id[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_drain_dct_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_drain_dct_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         dctn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_disable_hca_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_40[0x20];
 };
 
 struct mlx5_ifc_disable_hca_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_40[0x10];
 	u8         function_id[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_detach_from_mcg_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_detach_from_mcg_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         multicast_gid[16][0x8];
 };
 
 struct mlx5_ifc_destroy_xrc_srq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_xrc_srq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         xrc_srqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_tis_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_tis_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         tisn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_tir_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_tir_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         tirn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_srq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_srq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         srqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_sq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_sq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         sqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_rqt_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_rqt_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rqtn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_rq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_rq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_rmp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_rmp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rmpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_psv_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_psv_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         psvn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_mkey_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_mkey_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         mkey_index[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_flow_table_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_flow_table_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_5[0x140];
+	u8         reserved_at_c0[0x140];
 };
 
 struct mlx5_ifc_destroy_flow_group_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_flow_group_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
 	u8         group_id[0x20];
 
-	u8         reserved_5[0x120];
+	u8         reserved_at_e0[0x120];
 };
 
 struct mlx5_ifc_destroy_eq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_eq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x18];
+	u8         reserved_at_40[0x18];
 	u8         eq_number[0x8];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_dct_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_dct_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         dctn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_destroy_cq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_destroy_cq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         cqn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_delete_vxlan_udp_dport_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_delete_vxlan_udp_dport_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_40[0x20];
 
-	u8         reserved_3[0x10];
+	u8         reserved_at_60[0x10];
 	u8         vxlan_udp_port[0x10];
 };
 
 struct mlx5_ifc_delete_l2_table_entry_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_delete_l2_table_entry_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x60];
+	u8         reserved_at_40[0x60];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_index[0x18];
 
-	u8         reserved_4[0x140];
+	u8         reserved_at_c0[0x140];
 };
 
 struct mlx5_ifc_delete_fte_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_delete_fte_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_5[0x40];
+	u8         reserved_at_c0[0x40];
 
 	u8         flow_index[0x20];
 
-	u8         reserved_6[0xe0];
+	u8         reserved_at_120[0xe0];
 };
 
 struct mlx5_ifc_dealloc_xrcd_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_dealloc_xrcd_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         xrcd[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_dealloc_uar_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_dealloc_uar_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         uar[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_dealloc_transport_domain_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_dealloc_transport_domain_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         transport_domain[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_dealloc_q_counter_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_dealloc_q_counter_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x18];
+	u8         reserved_at_40[0x18];
 	u8         counter_set_id[0x8];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_dealloc_pd_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_dealloc_pd_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         pd[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_xrc_srq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         xrc_srqn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_xrc_srq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry;
 
-	u8         reserved_3[0x600];
+	u8         reserved_at_280[0x600];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_create_tis_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         tisn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_tis_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_tisc_bits ctx;
 };
 
 struct mlx5_ifc_create_tir_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         tirn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_tir_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_tirc_bits ctx;
 };
 
 struct mlx5_ifc_create_srq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         srqn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_srq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_srqc_bits srq_context_entry;
 
-	u8         reserved_3[0x600];
+	u8         reserved_at_280[0x600];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_create_sq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         sqn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_sq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_sqc_bits ctx;
 };
 
 struct mlx5_ifc_create_rqt_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rqtn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_rqt_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_rqtc_bits rqt_context;
 };
 
 struct mlx5_ifc_create_rq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rqn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_rq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_rqc_bits ctx;
 };
 
 struct mlx5_ifc_create_rmp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         rmpn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_rmp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0xc0];
+	u8         reserved_at_40[0xc0];
 
 	struct mlx5_ifc_rmpc_bits ctx;
 };
 
 struct mlx5_ifc_create_qp_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_qp_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_a0[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_4[0x80];
+	u8         reserved_at_800[0x80];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_create_psv_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_80[0x8];
 	u8         psv0_index[0x18];
 
-	u8         reserved_3[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         psv1_index[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         psv2_index[0x18];
 
-	u8         reserved_5[0x8];
+	u8         reserved_at_e0[0x8];
 	u8         psv3_index[0x18];
 };
 
 struct mlx5_ifc_create_psv_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         num_psv[0x4];
-	u8         reserved_2[0x4];
+	u8         reserved_at_44[0x4];
 	u8         pd[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_mkey_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         mkey_index[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_mkey_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_40[0x20];
 
 	u8         pg_access[0x1];
-	u8         reserved_3[0x1f];
+	u8         reserved_at_61[0x1f];
 
 	struct mlx5_ifc_mkc_bits memory_key_mkey_entry;
 
-	u8         reserved_4[0x80];
+	u8         reserved_at_280[0x80];
 
 	u8         translations_octword_actual_size[0x20];
 
-	u8         reserved_5[0x560];
+	u8         reserved_at_320[0x560];
 
 	u8         klm_pas_mtt[0][0x20];
 };
 
 struct mlx5_ifc_create_flow_table_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_flow_table_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_a0[0x20];
 
-	u8         reserved_5[0x4];
+	u8         reserved_at_c0[0x4];
 	u8         table_miss_mode[0x4];
 	u8         level[0x8];
-	u8         reserved_6[0x8];
+	u8         reserved_at_d0[0x8];
 	u8         log_size[0x8];
 
-	u8         reserved_7[0x8];
+	u8         reserved_at_e0[0x8];
 	u8         table_miss_id[0x18];
 
-	u8         reserved_8[0x100];
+	u8         reserved_at_100[0x100];
 };
 
 struct mlx5_ifc_create_flow_group_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         group_id[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 enum {
@@ -5742,134 +5744,134 @@ enum {
 
 struct mlx5_ifc_create_flow_group_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_5[0x20];
+	u8         reserved_at_c0[0x20];
 
 	u8         start_flow_index[0x20];
 
-	u8         reserved_6[0x20];
+	u8         reserved_at_100[0x20];
 
 	u8         end_flow_index[0x20];
 
-	u8         reserved_7[0xa0];
+	u8         reserved_at_140[0xa0];
 
-	u8         reserved_8[0x18];
+	u8         reserved_at_1e0[0x18];
 	u8         match_criteria_enable[0x8];
 
 	struct mlx5_ifc_fte_match_param_bits match_criteria;
 
-	u8         reserved_9[0xe00];
+	u8         reserved_at_1200[0xe00];
 };
 
 struct mlx5_ifc_create_eq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x18];
+	u8         reserved_at_40[0x18];
 	u8         eq_number[0x8];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_eq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_eqc_bits eq_context_entry;
 
-	u8         reserved_3[0x40];
+	u8         reserved_at_280[0x40];
 
 	u8         event_bitmask[0x40];
 
-	u8         reserved_4[0x580];
+	u8         reserved_at_300[0x580];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_create_dct_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         dctn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_dct_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_dctc_bits dct_context_entry;
 
-	u8         reserved_3[0x180];
+	u8         reserved_at_280[0x180];
 };
 
 struct mlx5_ifc_create_cq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         cqn[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_create_cq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	struct mlx5_ifc_cqc_bits cq_context;
 
-	u8         reserved_3[0x600];
+	u8         reserved_at_280[0x600];
 
 	u8         pas[0][0x40];
 };
 
 struct mlx5_ifc_config_int_moderation_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x4];
+	u8         reserved_at_40[0x4];
 	u8         min_delay[0xc];
 	u8         int_vector[0x10];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 enum {
@@ -5879,49 +5881,49 @@ enum {
 
 struct mlx5_ifc_config_int_moderation_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x4];
+	u8         reserved_at_40[0x4];
 	u8         min_delay[0xc];
 	u8         int_vector[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_attach_to_mcg_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_attach_to_mcg_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         qpn[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 
 	u8         multicast_gid[16][0x8];
 };
 
 struct mlx5_ifc_arm_xrc_srq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 enum {
@@ -5930,25 +5932,25 @@ enum {
 
 struct mlx5_ifc_arm_xrc_srq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         xrc_srqn[0x18];
 
-	u8         reserved_3[0x10];
+	u8         reserved_at_60[0x10];
 	u8         lwm[0x10];
 };
 
 struct mlx5_ifc_arm_rq_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 enum {
@@ -5957,179 +5959,179 @@ enum {
 
 struct mlx5_ifc_arm_rq_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         srq_number[0x18];
 
-	u8         reserved_3[0x10];
+	u8         reserved_at_60[0x10];
 	u8         lwm[0x10];
 };
 
 struct mlx5_ifc_arm_dct_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_arm_dct_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_40[0x8];
 	u8         dct_number[0x18];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_alloc_xrcd_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         xrcd[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_alloc_xrcd_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_alloc_uar_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         uar[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_alloc_uar_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_alloc_transport_domain_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         transport_domain[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_alloc_transport_domain_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_alloc_q_counter_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x18];
+	u8         reserved_at_40[0x18];
 	u8         counter_set_id[0x8];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_alloc_q_counter_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_alloc_pd_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x8];
+	u8         reserved_at_40[0x8];
 	u8         pd[0x18];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_60[0x20];
 };
 
 struct mlx5_ifc_alloc_pd_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_add_vxlan_udp_dport_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_add_vxlan_udp_dport_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_40[0x20];
 
-	u8         reserved_3[0x10];
+	u8         reserved_at_60[0x10];
 	u8         vxlan_udp_port[0x10];
 };
 
 struct mlx5_ifc_access_register_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         register_data[0][0x20];
 };
@@ -6141,12 +6143,12 @@ enum {
 
 struct mlx5_ifc_access_register_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x10];
+	u8         reserved_at_40[0x10];
 	u8         register_id[0x10];
 
 	u8         argument[0x20];
@@ -6159,24 +6161,24 @@ struct mlx5_ifc_sltp_reg_bits {
 	u8         version[0x4];
 	u8         local_port[0x8];
 	u8         pnat[0x2];
-	u8         reserved_0[0x2];
+	u8         reserved_at_12[0x2];
 	u8         lane[0x4];
-	u8         reserved_1[0x8];
+	u8         reserved_at_18[0x8];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_20[0x20];
 
-	u8         reserved_3[0x7];
+	u8         reserved_at_40[0x7];
 	u8         polarity[0x1];
 	u8         ob_tap0[0x8];
 	u8         ob_tap1[0x8];
 	u8         ob_tap2[0x8];
 
-	u8         reserved_4[0xc];
+	u8         reserved_at_60[0xc];
 	u8         ob_preemp_mode[0x4];
 	u8         ob_reg[0x8];
 	u8         ob_bias[0x8];
 
-	u8         reserved_5[0x20];
+	u8         reserved_at_80[0x20];
 };
 
 struct mlx5_ifc_slrg_reg_bits {
@@ -6184,36 +6186,36 @@ struct mlx5_ifc_slrg_reg_bits {
 	u8         version[0x4];
 	u8         local_port[0x8];
 	u8         pnat[0x2];
-	u8         reserved_0[0x2];
+	u8         reserved_at_12[0x2];
 	u8         lane[0x4];
-	u8         reserved_1[0x8];
+	u8         reserved_at_18[0x8];
 
 	u8         time_to_link_up[0x10];
-	u8         reserved_2[0xc];
+	u8         reserved_at_30[0xc];
 	u8         grade_lane_speed[0x4];
 
 	u8         grade_version[0x8];
 	u8         grade[0x18];
 
-	u8         reserved_3[0x4];
+	u8         reserved_at_60[0x4];
 	u8         height_grade_type[0x4];
 	u8         height_grade[0x18];
 
 	u8         height_dz[0x10];
 	u8         height_dv[0x10];
 
-	u8         reserved_4[0x10];
+	u8         reserved_at_a0[0x10];
 	u8         height_sigma[0x10];
 
-	u8         reserved_5[0x20];
+	u8         reserved_at_c0[0x20];
 
-	u8         reserved_6[0x4];
+	u8         reserved_at_e0[0x4];
 	u8         phase_grade_type[0x4];
 	u8         phase_grade[0x18];
 
-	u8         reserved_7[0x8];
+	u8         reserved_at_100[0x8];
 	u8         phase_eo_pos[0x8];
-	u8         reserved_8[0x8];
+	u8         reserved_at_110[0x8];
 	u8         phase_eo_neg[0x8];
 
 	u8         ffe_set_tested[0x10];
@@ -6221,70 +6223,70 @@ struct mlx5_ifc_slrg_reg_bits {
 };
 
 struct mlx5_ifc_pvlc_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_2[0x1c];
+	u8         reserved_at_20[0x1c];
 	u8         vl_hw_cap[0x4];
 
-	u8         reserved_3[0x1c];
+	u8         reserved_at_40[0x1c];
 	u8         vl_admin[0x4];
 
-	u8         reserved_4[0x1c];
+	u8         reserved_at_60[0x1c];
 	u8         vl_operational[0x4];
 };
 
 struct mlx5_ifc_pude_reg_bits {
 	u8         swid[0x8];
 	u8         local_port[0x8];
-	u8         reserved_0[0x4];
+	u8         reserved_at_10[0x4];
 	u8         admin_status[0x4];
-	u8         reserved_1[0x4];
+	u8         reserved_at_18[0x4];
 	u8         oper_status[0x4];
 
-	u8         reserved_2[0x60];
+	u8         reserved_at_20[0x60];
 };
 
 struct mlx5_ifc_ptys_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0xd];
+	u8         reserved_at_10[0xd];
 	u8         proto_mask[0x3];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_20[0x40];
 
 	u8         eth_proto_capability[0x20];
 
 	u8         ib_link_width_capability[0x10];
 	u8         ib_proto_capability[0x10];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_a0[0x20];
 
 	u8         eth_proto_admin[0x20];
 
 	u8         ib_link_width_admin[0x10];
 	u8         ib_proto_admin[0x10];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_100[0x20];
 
 	u8         eth_proto_oper[0x20];
 
 	u8         ib_link_width_oper[0x10];
 	u8         ib_proto_oper[0x10];
 
-	u8         reserved_5[0x20];
+	u8         reserved_at_160[0x20];
 
 	u8         eth_proto_lp_advertise[0x20];
 
-	u8         reserved_6[0x60];
+	u8         reserved_at_1a0[0x60];
 };
 
 struct mlx5_ifc_ptas_reg_bits {
-	u8         reserved_0[0x20];
+	u8         reserved_at_0[0x20];
 
 	u8         algorithm_options[0x10];
-	u8         reserved_1[0x4];
+	u8         reserved_at_30[0x4];
 	u8         repetitions_mode[0x4];
 	u8         num_of_repetitions[0x8];
 
@@ -6310,13 +6312,13 @@ struct mlx5_ifc_ptas_reg_bits {
 	u8         ndeo_error_threshold[0x10];
 
 	u8         mixer_offset_step_size[0x10];
-	u8         reserved_2[0x8];
+	u8         reserved_at_110[0x8];
 	u8         mix90_phase_for_voltage_bath[0x8];
 
 	u8         mixer_offset_start[0x10];
 	u8         mixer_offset_end[0x10];
 
-	u8         reserved_3[0x15];
+	u8         reserved_at_140[0x15];
 	u8         ber_test_time[0xb];
 };
 
@@ -6324,154 +6326,154 @@ struct mlx5_ifc_pspa_reg_bits {
 	u8         swid[0x8];
 	u8         local_port[0x8];
 	u8         sub_port[0x8];
-	u8         reserved_0[0x8];
+	u8         reserved_at_18[0x8];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_20[0x20];
 };
 
 struct mlx5_ifc_pqdr_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x5];
+	u8         reserved_at_10[0x5];
 	u8         prio[0x3];
-	u8         reserved_2[0x6];
+	u8         reserved_at_18[0x6];
 	u8         mode[0x2];
 
-	u8         reserved_3[0x20];
+	u8         reserved_at_20[0x20];
 
-	u8         reserved_4[0x10];
+	u8         reserved_at_40[0x10];
 	u8         min_threshold[0x10];
 
-	u8         reserved_5[0x10];
+	u8         reserved_at_60[0x10];
 	u8         max_threshold[0x10];
 
-	u8         reserved_6[0x10];
+	u8         reserved_at_80[0x10];
 	u8         mark_probability_denominator[0x10];
 
-	u8         reserved_7[0x60];
+	u8         reserved_at_a0[0x60];
 };
 
 struct mlx5_ifc_ppsc_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_2[0x60];
+	u8         reserved_at_20[0x60];
 
-	u8         reserved_3[0x1c];
+	u8         reserved_at_80[0x1c];
 	u8         wrps_admin[0x4];
 
-	u8         reserved_4[0x1c];
+	u8         reserved_at_a0[0x1c];
 	u8         wrps_status[0x4];
 
-	u8         reserved_5[0x8];
+	u8         reserved_at_c0[0x8];
 	u8         up_threshold[0x8];
-	u8         reserved_6[0x8];
+	u8         reserved_at_d0[0x8];
 	u8         down_threshold[0x8];
 
-	u8         reserved_7[0x20];
+	u8         reserved_at_e0[0x20];
 
-	u8         reserved_8[0x1c];
+	u8         reserved_at_100[0x1c];
 	u8         srps_admin[0x4];
 
-	u8         reserved_9[0x1c];
+	u8         reserved_at_120[0x1c];
 	u8         srps_status[0x4];
 
-	u8         reserved_10[0x40];
+	u8         reserved_at_140[0x40];
 };
 
 struct mlx5_ifc_pplr_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_20[0x8];
 	u8         lb_cap[0x8];
-	u8         reserved_3[0x8];
+	u8         reserved_at_30[0x8];
 	u8         lb_en[0x8];
 };
 
 struct mlx5_ifc_pplm_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_20[0x20];
 
 	u8         port_profile_mode[0x8];
 	u8         static_port_profile[0x8];
 	u8         active_port_profile[0x8];
-	u8         reserved_3[0x8];
+	u8         reserved_at_58[0x8];
 
 	u8         retransmission_active[0x8];
 	u8         fec_mode_active[0x18];
 
-	u8         reserved_4[0x20];
+	u8         reserved_at_80[0x20];
 };
 
 struct mlx5_ifc_ppcnt_reg_bits {
 	u8         swid[0x8];
 	u8         local_port[0x8];
 	u8         pnat[0x2];
-	u8         reserved_0[0x8];
+	u8         reserved_at_12[0x8];
 	u8         grp[0x6];
 
 	u8         clr[0x1];
-	u8         reserved_1[0x1c];
+	u8         reserved_at_21[0x1c];
 	u8         prio_tc[0x3];
 
 	union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set;
 };
 
 struct mlx5_ifc_ppad_reg_bits {
-	u8         reserved_0[0x3];
+	u8         reserved_at_0[0x3];
 	u8         single_mac[0x1];
-	u8         reserved_1[0x4];
+	u8         reserved_at_4[0x4];
 	u8         local_port[0x8];
 	u8         mac_47_32[0x10];
 
 	u8         mac_31_0[0x20];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_pmtu_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
 	u8         max_mtu[0x10];
-	u8         reserved_2[0x10];
+	u8         reserved_at_30[0x10];
 
 	u8         admin_mtu[0x10];
-	u8         reserved_3[0x10];
+	u8         reserved_at_50[0x10];
 
 	u8         oper_mtu[0x10];
-	u8         reserved_4[0x10];
+	u8         reserved_at_70[0x10];
 };
 
 struct mlx5_ifc_pmpr_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         module[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_2[0x18];
+	u8         reserved_at_20[0x18];
 	u8         attenuation_5g[0x8];
 
-	u8         reserved_3[0x18];
+	u8         reserved_at_40[0x18];
 	u8         attenuation_7g[0x8];
 
-	u8         reserved_4[0x18];
+	u8         reserved_at_60[0x18];
 	u8         attenuation_12g[0x8];
 };
 
 struct mlx5_ifc_pmpe_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         module[0x8];
-	u8         reserved_1[0xc];
+	u8         reserved_at_10[0xc];
 	u8         module_status[0x4];
 
-	u8         reserved_2[0x60];
+	u8         reserved_at_20[0x60];
 };
 
 struct mlx5_ifc_pmpc_reg_bits {
@@ -6479,20 +6481,20 @@ struct mlx5_ifc_pmpc_reg_bits {
 };
 
 struct mlx5_ifc_pmlpn_reg_bits {
-	u8         reserved_0[0x4];
+	u8         reserved_at_0[0x4];
 	u8         mlpn_status[0x4];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
 	u8         e[0x1];
-	u8         reserved_2[0x1f];
+	u8         reserved_at_21[0x1f];
 };
 
 struct mlx5_ifc_pmlp_reg_bits {
 	u8         rxtx[0x1];
-	u8         reserved_0[0x7];
+	u8         reserved_at_1[0x7];
 	u8         local_port[0x8];
-	u8         reserved_1[0x8];
+	u8         reserved_at_10[0x8];
 	u8         width[0x8];
 
 	u8         lane0_module_mapping[0x20];
@@ -6503,36 +6505,36 @@ struct mlx5_ifc_pmlp_reg_bits {
 
 	u8         lane3_module_mapping[0x20];
 
-	u8         reserved_2[0x160];
+	u8         reserved_at_a0[0x160];
 };
 
 struct mlx5_ifc_pmaos_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         module[0x8];
-	u8         reserved_1[0x4];
+	u8         reserved_at_10[0x4];
 	u8         admin_status[0x4];
-	u8         reserved_2[0x4];
+	u8         reserved_at_18[0x4];
 	u8         oper_status[0x4];
 
 	u8         ase[0x1];
 	u8         ee[0x1];
-	u8         reserved_3[0x1c];
+	u8         reserved_at_22[0x1c];
 	u8         e[0x2];
 
-	u8         reserved_4[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_plpc_reg_bits {
-	u8         reserved_0[0x4];
+	u8         reserved_at_0[0x4];
 	u8         profile_id[0xc];
-	u8         reserved_1[0x4];
+	u8         reserved_at_10[0x4];
 	u8         proto_mask[0x4];
-	u8         reserved_2[0x8];
+	u8         reserved_at_18[0x8];
 
-	u8         reserved_3[0x10];
+	u8         reserved_at_20[0x10];
 	u8         lane_speed[0x10];
 
-	u8         reserved_4[0x17];
+	u8         reserved_at_40[0x17];
 	u8         lpbf[0x1];
 	u8         fec_mode_policy[0x8];
 
@@ -6545,44 +6547,44 @@ struct mlx5_ifc_plpc_reg_bits {
 	u8         retransmission_request_admin[0x8];
 	u8         fec_mode_request_admin[0x18];
 
-	u8         reserved_5[0x80];
+	u8         reserved_at_c0[0x80];
 };
 
 struct mlx5_ifc_plib_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x8];
+	u8         reserved_at_10[0x8];
 	u8         ib_port[0x8];
 
-	u8         reserved_2[0x60];
+	u8         reserved_at_20[0x60];
 };
 
 struct mlx5_ifc_plbf_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0xd];
+	u8         reserved_at_10[0xd];
 	u8         lbf_mode[0x3];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_20[0x20];
 };
 
 struct mlx5_ifc_pipg_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
 	u8         dic[0x1];
-	u8         reserved_2[0x19];
+	u8         reserved_at_21[0x19];
 	u8         ipg[0x4];
-	u8         reserved_3[0x2];
+	u8         reserved_at_3e[0x2];
 };
 
 struct mlx5_ifc_pifr_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_2[0xe0];
+	u8         reserved_at_20[0xe0];
 
 	u8         port_filter[8][0x20];
 
@@ -6590,36 +6592,36 @@ struct mlx5_ifc_pifr_reg_bits {
 };
 
 struct mlx5_ifc_pfcc_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
 	u8         ppan[0x4];
-	u8         reserved_2[0x4];
+	u8         reserved_at_24[0x4];
 	u8         prio_mask_tx[0x8];
-	u8         reserved_3[0x8];
+	u8         reserved_at_30[0x8];
 	u8         prio_mask_rx[0x8];
 
 	u8         pptx[0x1];
 	u8         aptx[0x1];
-	u8         reserved_4[0x6];
+	u8         reserved_at_42[0x6];
 	u8         pfctx[0x8];
-	u8         reserved_5[0x10];
+	u8         reserved_at_50[0x10];
 
 	u8         pprx[0x1];
 	u8         aprx[0x1];
-	u8         reserved_6[0x6];
+	u8         reserved_at_62[0x6];
 	u8         pfcrx[0x8];
-	u8         reserved_7[0x10];
+	u8         reserved_at_70[0x10];
 
-	u8         reserved_8[0x80];
+	u8         reserved_at_80[0x80];
 };
 
 struct mlx5_ifc_pelc_reg_bits {
 	u8         op[0x4];
-	u8         reserved_0[0x4];
+	u8         reserved_at_4[0x4];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
 	u8         op_admin[0x8];
 	u8         op_capability[0x8];
@@ -6634,28 +6636,28 @@ struct mlx5_ifc_pelc_reg_bits {
 
 	u8         active[0x40];
 
-	u8         reserved_2[0x80];
+	u8         reserved_at_140[0x80];
 };
 
 struct mlx5_ifc_peir_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_2[0xc];
+	u8         reserved_at_20[0xc];
 	u8         error_count[0x4];
-	u8         reserved_3[0x10];
+	u8         reserved_at_30[0x10];
 
-	u8         reserved_4[0xc];
+	u8         reserved_at_40[0xc];
 	u8         lane[0x4];
-	u8         reserved_5[0x8];
+	u8         reserved_at_50[0x8];
 	u8         error_type[0x8];
 };
 
 struct mlx5_ifc_pcap_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
-	u8         reserved_1[0x10];
+	u8         reserved_at_10[0x10];
 
 	u8         port_capability_mask[4][0x20];
 };
@@ -6663,46 +6665,46 @@ struct mlx5_ifc_pcap_reg_bits {
 struct mlx5_ifc_paos_reg_bits {
 	u8         swid[0x8];
 	u8         local_port[0x8];
-	u8         reserved_0[0x4];
+	u8         reserved_at_10[0x4];
 	u8         admin_status[0x4];
-	u8         reserved_1[0x4];
+	u8         reserved_at_18[0x4];
 	u8         oper_status[0x4];
 
 	u8         ase[0x1];
 	u8         ee[0x1];
-	u8         reserved_2[0x1c];
+	u8         reserved_at_22[0x1c];
 	u8         e[0x2];
 
-	u8         reserved_3[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_pamp_reg_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         opamp_group[0x8];
-	u8         reserved_1[0xc];
+	u8         reserved_at_10[0xc];
 	u8         opamp_group_type[0x4];
 
 	u8         start_index[0x10];
-	u8         reserved_2[0x4];
+	u8         reserved_at_30[0x4];
 	u8         num_of_indices[0xc];
 
 	u8         index_data[18][0x10];
 };
 
 struct mlx5_ifc_lane_2_module_mapping_bits {
-	u8         reserved_0[0x6];
+	u8         reserved_at_0[0x6];
 	u8         rx_lane[0x2];
-	u8         reserved_1[0x6];
+	u8         reserved_at_8[0x6];
 	u8         tx_lane[0x2];
-	u8         reserved_2[0x8];
+	u8         reserved_at_10[0x8];
 	u8         module[0x8];
 };
 
 struct mlx5_ifc_bufferx_reg_bits {
-	u8         reserved_0[0x6];
+	u8         reserved_at_0[0x6];
 	u8         lossy[0x1];
 	u8         epsb[0x1];
-	u8         reserved_1[0xc];
+	u8         reserved_at_8[0xc];
 	u8         size[0xc];
 
 	u8         xoff_threshold[0x10];
@@ -6714,21 +6716,21 @@ struct mlx5_ifc_set_node_in_bits {
 };
 
 struct mlx5_ifc_register_power_settings_bits {
-	u8         reserved_0[0x18];
+	u8         reserved_at_0[0x18];
 	u8         power_settings_level[0x8];
 
-	u8         reserved_1[0x60];
+	u8         reserved_at_20[0x60];
 };
 
 struct mlx5_ifc_register_host_endianness_bits {
 	u8         he[0x1];
-	u8         reserved_0[0x1f];
+	u8         reserved_at_1[0x1f];
 
-	u8         reserved_1[0x60];
+	u8         reserved_at_20[0x60];
 };
 
 struct mlx5_ifc_umr_pointer_desc_argument_bits {
-	u8         reserved_0[0x20];
+	u8         reserved_at_0[0x20];
 
 	u8         mkey[0x20];
 
@@ -6741,7 +6743,7 @@ struct mlx5_ifc_ud_adrs_vector_bits {
 	u8         dc_key[0x40];
 
 	u8         ext[0x1];
-	u8         reserved_0[0x7];
+	u8         reserved_at_41[0x7];
 	u8         destination_qp_dct[0x18];
 
 	u8         static_rate[0x4];
@@ -6750,7 +6752,7 @@ struct mlx5_ifc_ud_adrs_vector_bits {
 	u8         mlid[0x7];
 	u8         rlid_udp_sport[0x10];
 
-	u8         reserved_1[0x20];
+	u8         reserved_at_80[0x20];
 
 	u8         rmac_47_16[0x20];
 
@@ -6758,9 +6760,9 @@ struct mlx5_ifc_ud_adrs_vector_bits {
 	u8         tclass[0x8];
 	u8         hop_limit[0x8];
 
-	u8         reserved_2[0x1];
+	u8         reserved_at_e0[0x1];
 	u8         grh[0x1];
-	u8         reserved_3[0x2];
+	u8         reserved_at_e2[0x2];
 	u8         src_addr_index[0x8];
 	u8         flow_label[0x14];
 
@@ -6768,27 +6770,27 @@ struct mlx5_ifc_ud_adrs_vector_bits {
 };
 
 struct mlx5_ifc_pages_req_event_bits {
-	u8         reserved_0[0x10];
+	u8         reserved_at_0[0x10];
 	u8         function_id[0x10];
 
 	u8         num_pages[0x20];
 
-	u8         reserved_1[0xa0];
+	u8         reserved_at_40[0xa0];
 };
 
 struct mlx5_ifc_eqe_bits {
-	u8         reserved_0[0x8];
+	u8         reserved_at_0[0x8];
 	u8         event_type[0x8];
-	u8         reserved_1[0x8];
+	u8         reserved_at_10[0x8];
 	u8         event_sub_type[0x8];
 
-	u8         reserved_2[0xe0];
+	u8         reserved_at_20[0xe0];
 
 	union mlx5_ifc_event_auto_bits event_data;
 
-	u8         reserved_3[0x10];
+	u8         reserved_at_1e0[0x10];
 	u8         signature[0x8];
-	u8         reserved_4[0x7];
+	u8         reserved_at_1f8[0x7];
 	u8         owner[0x1];
 };
 
@@ -6798,14 +6800,14 @@ enum {
 
 struct mlx5_ifc_cmd_queue_entry_bits {
 	u8         type[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         input_length[0x20];
 
 	u8         input_mailbox_pointer_63_32[0x20];
 
 	u8         input_mailbox_pointer_31_9[0x17];
-	u8         reserved_1[0x9];
+	u8         reserved_at_77[0x9];
 
 	u8         command_input_inline_data[16][0x8];
 
@@ -6814,20 +6816,20 @@ struct mlx5_ifc_cmd_queue_entry_bits {
 	u8         output_mailbox_pointer_63_32[0x20];
 
 	u8         output_mailbox_pointer_31_9[0x17];
-	u8         reserved_2[0x9];
+	u8         reserved_at_1b7[0x9];
 
 	u8         output_length[0x20];
 
 	u8         token[0x8];
 	u8         signature[0x8];
-	u8         reserved_3[0x8];
+	u8         reserved_at_1f0[0x8];
 	u8         status[0x7];
 	u8         ownership[0x1];
 };
 
 struct mlx5_ifc_cmd_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
@@ -6836,9 +6838,9 @@ struct mlx5_ifc_cmd_out_bits {
 
 struct mlx5_ifc_cmd_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
 	u8         command[0][0x20];
@@ -6847,16 +6849,16 @@ struct mlx5_ifc_cmd_in_bits {
 struct mlx5_ifc_cmd_if_box_bits {
 	u8         mailbox_data[512][0x8];
 
-	u8         reserved_0[0x180];
+	u8         reserved_at_1000[0x180];
 
 	u8         next_pointer_63_32[0x20];
 
 	u8         next_pointer_31_10[0x16];
-	u8         reserved_1[0xa];
+	u8         reserved_at_11b6[0xa];
 
 	u8         block_number[0x20];
 
-	u8         reserved_2[0x8];
+	u8         reserved_at_11e0[0x8];
 	u8         token[0x8];
 	u8         ctrl_signature[0x8];
 	u8         signature[0x8];
@@ -6866,7 +6868,7 @@ struct mlx5_ifc_mtt_bits {
 	u8         ptag_63_32[0x20];
 
 	u8         ptag_31_8[0x18];
-	u8         reserved_0[0x6];
+	u8         reserved_at_38[0x6];
 	u8         wr_en[0x1];
 	u8         rd_en[0x1];
 };
@@ -6904,38 +6906,38 @@ struct mlx5_ifc_initial_seg_bits {
 	u8         cmd_interface_rev[0x10];
 	u8         fw_rev_subminor[0x10];
 
-	u8         reserved_0[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         cmdq_phy_addr_63_32[0x20];
 
 	u8         cmdq_phy_addr_31_12[0x14];
-	u8         reserved_1[0x2];
+	u8         reserved_at_b4[0x2];
 	u8         nic_interface[0x2];
 	u8         log_cmdq_size[0x4];
 	u8         log_cmdq_stride[0x4];
 
 	u8         command_doorbell_vector[0x20];
 
-	u8         reserved_2[0xf00];
+	u8         reserved_at_e0[0xf00];
 
 	u8         initializing[0x1];
-	u8         reserved_3[0x4];
+	u8         reserved_at_fe1[0x4];
 	u8         nic_interface_supported[0x3];
-	u8         reserved_4[0x18];
+	u8         reserved_at_fe8[0x18];
 
 	struct mlx5_ifc_health_buffer_bits health_buffer;
 
 	u8         no_dram_nic_offset[0x20];
 
-	u8         reserved_5[0x6e40];
+	u8         reserved_at_1220[0x6e40];
 
-	u8         reserved_6[0x1f];
+	u8         reserved_at_8060[0x1f];
 	u8         clear_int[0x1];
 
 	u8         health_syndrome[0x8];
 	u8         health_counter[0x18];
 
-	u8         reserved_7[0x17fc0];
+	u8         reserved_at_80a0[0x17fc0];
 };
 
 union mlx5_ifc_ports_control_registers_document_bits {
@@ -6980,44 +6982,44 @@ union mlx5_ifc_ports_control_registers_document_bits {
 	struct mlx5_ifc_pvlc_reg_bits pvlc_reg;
 	struct mlx5_ifc_slrg_reg_bits slrg_reg;
 	struct mlx5_ifc_sltp_reg_bits sltp_reg;
-	u8         reserved_0[0x60e0];
+	u8         reserved_at_0[0x60e0];
 };
 
 union mlx5_ifc_debug_enhancements_document_bits {
 	struct mlx5_ifc_health_buffer_bits health_buffer;
-	u8         reserved_0[0x200];
+	u8         reserved_at_0[0x200];
 };
 
 union mlx5_ifc_uplink_pci_interface_document_bits {
 	struct mlx5_ifc_initial_seg_bits initial_seg;
-	u8         reserved_0[0x20060];
+	u8         reserved_at_0[0x20060];
 };
 
 struct mlx5_ifc_set_flow_table_root_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_set_flow_table_root_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x40];
+	u8         reserved_at_40[0x40];
 
 	u8         table_type[0x8];
-	u8         reserved_3[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_4[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_5[0x140];
+	u8         reserved_at_c0[0x140];
 };
 
 enum {
@@ -7026,39 +7028,39 @@ enum {
 
 struct mlx5_ifc_modify_flow_table_out_bits {
 	u8         status[0x8];
-	u8         reserved_0[0x18];
+	u8         reserved_at_8[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_1[0x40];
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_modify_flow_table_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_0[0x10];
+	u8         reserved_at_10[0x10];
 
-	u8         reserved_1[0x10];
+	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_2[0x20];
+	u8         reserved_at_40[0x20];
 
-	u8         reserved_3[0x10];
+	u8         reserved_at_60[0x10];
 	u8         modify_field_select[0x10];
 
 	u8         table_type[0x8];
-	u8         reserved_4[0x18];
+	u8         reserved_at_88[0x18];
 
-	u8         reserved_5[0x8];
+	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_6[0x4];
+	u8         reserved_at_c0[0x4];
 	u8         table_miss_mode[0x4];
-	u8         reserved_7[0x18];
+	u8         reserved_at_c8[0x18];
 
-	u8         reserved_8[0x8];
+	u8         reserved_at_e0[0x8];
 	u8         table_miss_id[0x18];
 
-	u8         reserved_9[0x100];
+	u8         reserved_at_100[0x100];
 };
 
 #endif /* MLX5_IFC_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 516e14944339..dbf1eddab964 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -387,7 +387,8 @@ enum {
 	REGION_MIXED,
 };
 
-int region_intersects(resource_size_t offset, size_t size, const char *type);
+int region_intersects(resource_size_t offset, size_t size, unsigned long flags,
+		      unsigned long desc);
 
 /* Support for virtually mapped pages */
 struct page *vmalloc_to_page(const void *addr);
@@ -904,20 +905,11 @@ static inline struct mem_cgroup *page_memcg(struct page *page)
 {
 	return page->mem_cgroup;
 }
-
-static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg)
-{
-	page->mem_cgroup = memcg;
-}
 #else
 static inline struct mem_cgroup *page_memcg(struct page *page)
 {
 	return NULL;
 }
-
-static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg)
-{
-}
 #endif
 
 /*
@@ -1299,10 +1291,9 @@ int __set_page_dirty_nobuffers(struct page *page);
 int __set_page_dirty_no_writeback(struct page *page);
 int redirty_page_for_writepage(struct writeback_control *wbc,
 				struct page *page);
-void account_page_dirtied(struct page *page, struct address_space *mapping,
-			  struct mem_cgroup *memcg);
+void account_page_dirtied(struct page *page, struct address_space *mapping);
 void account_page_cleaned(struct page *page, struct address_space *mapping,
-			  struct mem_cgroup *memcg, struct bdi_writeback *wb);
+			  struct bdi_writeback *wb);
 int set_page_dirty(struct page *page);
 int set_page_dirty_lock(struct page *page);
 void cancel_dirty_page(struct page *page);
@@ -2138,6 +2129,8 @@ int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
 int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
 int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn);
+int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
+			unsigned long pfn, pgprot_t pgprot);
 int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 			pfn_t pfn);
 int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);
@@ -2175,6 +2168,17 @@ extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
 			       unsigned long size, pte_fn_t fn, void *data);
 
 
+#ifdef CONFIG_PAGE_POISONING
+extern bool page_poisoning_enabled(void);
+extern void kernel_poison_pages(struct page *page, int numpages, int enable);
+extern bool page_is_poisoned(struct page *page);
+#else
+static inline bool page_poisoning_enabled(void) { return false; }
+static inline void kernel_poison_pages(struct page *page, int numpages,
+					int enable) { }
+static inline bool page_is_poisoned(struct page *page) { return false; }
+#endif
+
 #ifdef CONFIG_DEBUG_PAGEALLOC
 extern bool _debug_pagealloc_enabled;
 extern void __kernel_map_pages(struct page *page, int numpages, int enable);
@@ -2194,14 +2198,18 @@ kernel_map_pages(struct page *page, int numpages, int enable)
 }
 #ifdef CONFIG_HIBERNATION
 extern bool kernel_page_present(struct page *page);
-#endif /* CONFIG_HIBERNATION */
-#else
+#endif	/* CONFIG_HIBERNATION */
+#else	/* CONFIG_DEBUG_PAGEALLOC */
 static inline void
 kernel_map_pages(struct page *page, int numpages, int enable) {}
 #ifdef CONFIG_HIBERNATION
 static inline bool kernel_page_present(struct page *page) { return true; }
-#endif /* CONFIG_HIBERNATION */
-#endif
+#endif	/* CONFIG_HIBERNATION */
+static inline bool debug_pagealloc_enabled(void)
+{
+	return false;
+}
+#endif	/* CONFIG_DEBUG_PAGEALLOC */
 
 #ifdef __HAVE_ARCH_GATE_AREA
 extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 624b78b848b8..944b2b37313b 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -566,10 +566,26 @@ static inline void clear_tlb_flush_pending(struct mm_struct *mm)
 }
 #endif
 
-struct vm_special_mapping
-{
-	const char *name;
+struct vm_fault;
+
+struct vm_special_mapping {
+	const char *name;	/* The name, e.g. "[vdso]". */
+
+	/*
+	 * If .fault is not provided, this points to a
+	 * NULL-terminated array of pages that back the special mapping.
+	 *
+	 * This must not be NULL unless .fault is provided.
+	 */
 	struct page **pages;
+
+	/*
+	 * If non-NULL, then this is called to resolve page faults
+	 * on the special mapping.  If used, .pages is not checked.
+	 */
+	int (*fault)(const struct vm_special_mapping *sm,
+		     struct vm_area_struct *vma,
+		     struct vm_fault *vmf);
 };
 
 enum tlb_flush_reason {
diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index 053824b0a412..de7be78c6f0e 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -9,8 +9,7 @@ struct vm_area_struct;
 struct mm_struct;
 
 extern void dump_page(struct page *page, const char *reason);
-extern void dump_page_badflags(struct page *page, const char *reason,
-			       unsigned long badflags);
+extern void __dump_page(struct page *page, const char *reason);
 void dump_vma(const struct vm_area_struct *vma);
 void dump_mm(const struct mm_struct *mm);
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 7b6c2cfee390..6de02ac378a0 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -63,6 +63,9 @@ enum {
 	MIGRATE_TYPES
 };
 
+/* In mm/page_alloc.c; keep in sync also with show_migration_types() there */
+extern char * const migratetype_names[MIGRATE_TYPES];
+
 #ifdef CONFIG_CMA
 #  define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA)
 #else
@@ -209,10 +212,12 @@ struct zone_reclaim_stat {
 };
 
 struct lruvec {
-	struct list_head lists[NR_LRU_LISTS];
-	struct zone_reclaim_stat reclaim_stat;
+	struct list_head		lists[NR_LRU_LISTS];
+	struct zone_reclaim_stat	reclaim_stat;
+	/* Evictions & activations on the inactive file list */
+	atomic_long_t			inactive_age;
 #ifdef CONFIG_MEMCG
-	struct zone *zone;
+	struct zone			*zone;
 #endif
 };
 
@@ -487,9 +492,6 @@ struct zone {
 	spinlock_t		lru_lock;
 	struct lruvec		lruvec;
 
-	/* Evictions & activations on the inactive file list */
-	atomic_long_t		inactive_age;
-
 	/*
 	 * When free pages are below this point, additional steps are taken
 	 * when reading the number of free pages to avoid per-cpu counter
@@ -520,6 +522,8 @@ struct zone {
 	bool			compact_blockskip_flush;
 #endif
 
+	bool			contiguous;
+
 	ZONE_PADDING(_pad3_)
 	/* Zone statistics */
 	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];
@@ -758,6 +762,8 @@ static inline struct zone *lruvec_zone(struct lruvec *lruvec)
 #endif
 }
 
+extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru);
+
 #ifdef CONFIG_HAVE_MEMORY_PRESENT
 void memory_present(int nid, unsigned long start, unsigned long end);
 #else
diff --git a/include/linux/module.h b/include/linux/module.h
index 4560d8f1545d..2bb0c3085706 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -324,6 +324,12 @@ struct module_layout {
 #define __module_layout_align
 #endif
 
+struct mod_kallsyms {
+	Elf_Sym *symtab;
+	unsigned int num_symtab;
+	char *strtab;
+};
+
 struct module {
 	enum module_state state;
 
@@ -405,15 +411,10 @@ struct module {
 #endif
 
 #ifdef CONFIG_KALLSYMS
-	/*
-	 * We keep the symbol and string tables for kallsyms.
-	 * The core_* fields below are temporary, loader-only (they
-	 * could really be discarded after module init).
-	 */
-	Elf_Sym *symtab, *core_symtab;
-	unsigned int num_symtab, core_num_syms;
-	char *strtab, *core_strtab;
-
+	/* Protected by RCU and/or module_mutex: use rcu_dereference() */
+	struct mod_kallsyms *kallsyms;
+	struct mod_kallsyms core_kallsyms;
+	
 	/* Section attributes */
 	struct module_sect_attrs *sect_attrs;
 
diff --git a/include/linux/nd.h b/include/linux/nd.h
index 507e47c86737..5489ab756d1a 100644
--- a/include/linux/nd.h
+++ b/include/linux/nd.h
@@ -16,11 +16,16 @@
 #include <linux/ndctl.h>
 #include <linux/device.h>
 
+enum nvdimm_event {
+	NVDIMM_REVALIDATE_POISON,
+};
+
 struct nd_device_driver {
 	struct device_driver drv;
 	unsigned long type;
 	int (*probe)(struct device *dev);
 	int (*remove)(struct device *dev);
+	void (*notify)(struct device *dev, enum nvdimm_event event);
 };
 
 static inline struct nd_device_driver *to_nd_device_driver(
@@ -144,6 +149,8 @@ static inline int nvdimm_write_bytes(struct nd_namespace_common *ndns,
 	MODULE_ALIAS("nd:t" __stringify(type) "*")
 #define ND_DEVICE_MODALIAS_FMT "nd:t%d"
 
+struct nd_region;
+void nvdimm_region_notify(struct nd_region *nd_region, enum nvdimm_event event);
 int __must_check __nd_driver_register(struct nd_device_driver *nd_drv,
 		struct module *module, const char *mod_name);
 #define nd_driver_register(driver) \
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 289c2314d766..5440b7b705eb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3718,7 +3718,7 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev,
 void *netdev_lower_get_next(struct net_device *dev,
 				struct list_head **iter);
 #define netdev_for_each_lower_dev(dev, ldev, iter) \
-	for (iter = &(dev)->adj_list.lower, \
+	for (iter = (dev)->adj_list.lower.next, \
 	     ldev = netdev_lower_get_next(dev, &(iter)); \
 	     ldev; \
 	     ldev = netdev_lower_get_next(dev, &(iter)))
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 48e0320cd643..67300f8e5f2f 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -550,9 +550,7 @@ extern int  nfs_readpage_async(struct nfs_open_context *, struct inode *,
 
 static inline loff_t nfs_size_to_loff_t(__u64 size)
 {
-	if (size > (__u64) OFFSET_MAX - 1)
-		return OFFSET_MAX - 1;
-	return (loff_t) size;
+	return min_t(u64, size, OFFSET_MAX);
 }
 
 static inline ino_t
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 791098a08a87..d320906cf13e 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -275,6 +275,7 @@ struct nfs4_layoutcommit_args {
 	size_t layoutupdate_len;
 	struct page *layoutupdate_page;
 	struct page **layoutupdate_pages;
+	__be32 *start_p;
 };
 
 struct nfs4_layoutcommit_res {
diff --git a/include/linux/notifier.h b/include/linux/notifier.h
index d14a4c362465..4149868de4e6 100644
--- a/include/linux/notifier.h
+++ b/include/linux/notifier.h
@@ -47,6 +47,8 @@
  * runtime initialization.
  */
 
+struct notifier_block;
+
 typedef	int (*notifier_fn_t)(struct notifier_block *nb,
 			unsigned long action, void *data);
 
diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index 17f118a82854..e1fe7cf5bddf 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -45,6 +45,7 @@ struct page_ext {
 	unsigned int order;
 	gfp_t gfp_mask;
 	unsigned int nr_entries;
+	int last_migrate_reason;
 	unsigned long trace_entries[8];
 #endif
 };
diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h
index cacaabea8a09..46f1b939948c 100644
--- a/include/linux/page_owner.h
+++ b/include/linux/page_owner.h
@@ -1,38 +1,54 @@
 #ifndef __LINUX_PAGE_OWNER_H
 #define __LINUX_PAGE_OWNER_H
 
+#include <linux/jump_label.h>
+
 #ifdef CONFIG_PAGE_OWNER
-extern bool page_owner_inited;
+extern struct static_key_false page_owner_inited;
 extern struct page_ext_operations page_owner_ops;
 
 extern void __reset_page_owner(struct page *page, unsigned int order);
 extern void __set_page_owner(struct page *page,
 			unsigned int order, gfp_t gfp_mask);
 extern gfp_t __get_page_owner_gfp(struct page *page);
+extern void __copy_page_owner(struct page *oldpage, struct page *newpage);
+extern void __set_page_owner_migrate_reason(struct page *page, int reason);
+extern void __dump_page_owner(struct page *page);
 
 static inline void reset_page_owner(struct page *page, unsigned int order)
 {
-	if (likely(!page_owner_inited))
-		return;
-
-	__reset_page_owner(page, order);
+	if (static_branch_unlikely(&page_owner_inited))
+		__reset_page_owner(page, order);
 }
 
 static inline void set_page_owner(struct page *page,
 			unsigned int order, gfp_t gfp_mask)
 {
-	if (likely(!page_owner_inited))
-		return;
-
-	__set_page_owner(page, order, gfp_mask);
+	if (static_branch_unlikely(&page_owner_inited))
+		__set_page_owner(page, order, gfp_mask);
 }
 
 static inline gfp_t get_page_owner_gfp(struct page *page)
 {
-	if (likely(!page_owner_inited))
+	if (static_branch_unlikely(&page_owner_inited))
+		return __get_page_owner_gfp(page);
+	else
 		return 0;
-
-	return __get_page_owner_gfp(page);
+}
+static inline void copy_page_owner(struct page *oldpage, struct page *newpage)
+{
+	if (static_branch_unlikely(&page_owner_inited))
+		__copy_page_owner(oldpage, newpage);
+}
+static inline void set_page_owner_migrate_reason(struct page *page, int reason)
+{
+	if (static_branch_unlikely(&page_owner_inited))
+		__set_page_owner_migrate_reason(page, reason);
+}
+static inline void dump_page_owner(struct page *page)
+{
+	if (static_branch_unlikely(&page_owner_inited))
+		__dump_page_owner(page);
 }
 #else
 static inline void reset_page_owner(struct page *page, unsigned int order)
@@ -46,6 +62,14 @@ static inline gfp_t get_page_owner_gfp(struct page *page)
 {
 	return 0;
 }
-
+static inline void copy_page_owner(struct page *oldpage, struct page *newpage)
+{
+}
+static inline void set_page_owner_migrate_reason(struct page *page, int reason)
+{
+}
+static inline void dump_page_owner(struct page *page)
+{
+}
 #endif /* CONFIG_PAGE_OWNER */
 #endif /* __LINUX_PAGE_OWNER_H */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 92395a0a7dc5..183b15ea052b 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -663,8 +663,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 				pgoff_t index, gfp_t gfp_mask);
 extern void delete_from_page_cache(struct page *page);
-extern void __delete_from_page_cache(struct page *page, void *shadow,
-				     struct mem_cgroup *memcg);
+extern void __delete_from_page_cache(struct page *page, void *shadow);
 int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
 
 /*
diff --git a/include/asm-generic/pci-dma-compat.h b/include/linux/pci-dma-compat.h
index eafce7b6f052..39726caef5b1 100644
--- a/include/asm-generic/pci-dma-compat.h
+++ b/include/linux/pci-dma-compat.h
@@ -6,6 +6,12 @@
 
 #include <linux/dma-mapping.h>
 
+/* This defines the direction arg to the DMA mapping routines. */
+#define PCI_DMA_BIDIRECTIONAL	0
+#define PCI_DMA_TODEVICE	1
+#define PCI_DMA_FROMDEVICE	2
+#define PCI_DMA_NONE		3
+
 static inline void *
 pci_alloc_consistent(struct pci_dev *hwdev, size_t size,
 		     dma_addr_t *dma_handle)
@@ -113,6 +119,29 @@ static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask)
 {
 	return dma_set_coherent_mask(&dev->dev, mask);
 }
+
+static inline int pci_set_dma_max_seg_size(struct pci_dev *dev,
+					   unsigned int size)
+{
+	return dma_set_max_seg_size(&dev->dev, size);
+}
+
+static inline int pci_set_dma_seg_boundary(struct pci_dev *dev,
+					   unsigned long mask)
+{
+	return dma_set_seg_boundary(&dev->dev, mask);
+}
+#else
+static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask)
+{ return -EIO; }
+static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask)
+{ return -EIO; }
+static inline int pci_set_dma_max_seg_size(struct pci_dev *dev,
+					   unsigned int size)
+{ return -EIO; }
+static inline int pci_set_dma_seg_boundary(struct pci_dev *dev,
+					   unsigned long mask)
+{ return -EIO; }
 #endif
 
 #endif
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 27df4a6585da..17e17c2ee1e6 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -70,12 +70,6 @@ enum pci_mmap_state {
 	pci_mmap_mem
 };
 
-/* This defines the direction arg to the DMA mapping routines. */
-#define PCI_DMA_BIDIRECTIONAL	0
-#define PCI_DMA_TODEVICE	1
-#define PCI_DMA_FROMDEVICE	2
-#define PCI_DMA_NONE		3
-
 /*
  *  For PCI devices, the region numbers are assigned this way:
  */
@@ -359,6 +353,7 @@ struct pci_dev {
 	unsigned int	io_window_1k:1;	/* Intel P2P bridge 1K I/O windows */
 	unsigned int	irq_managed:1;
 	unsigned int	has_secondary_link:1;
+	unsigned int	non_compliant_bars:1;	/* broken BARs; ignore them */
 	pci_dev_flags_t dev_flags;
 	atomic_t	enable_cnt;	/* pci_enable_device has been called */
 
@@ -578,6 +573,8 @@ static inline int pcibios_err_to_errno(int err)
 /* Low-level architecture-dependent routines */
 
 struct pci_ops {
+	int (*add_bus)(struct pci_bus *bus);
+	void (*remove_bus)(struct pci_bus *bus);
 	void __iomem *(*map_bus)(struct pci_bus *bus, unsigned int devfn, int where);
 	int (*read)(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val);
 	int (*write)(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val);
@@ -746,9 +743,26 @@ struct pci_driver {
 	.vendor = PCI_VENDOR_ID_##vend, .device = (dev), \
 	.subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, 0, 0
 
+enum {
+	PCI_REASSIGN_ALL_RSRC	= 0x00000001,	/* ignore firmware setup */
+	PCI_REASSIGN_ALL_BUS	= 0x00000002,	/* reassign all bus numbers */
+	PCI_PROBE_ONLY		= 0x00000004,	/* use existing setup */
+	PCI_CAN_SKIP_ISA_ALIGN	= 0x00000008,	/* don't do ISA alignment */
+	PCI_ENABLE_PROC_DOMAINS	= 0x00000010,	/* enable domains in /proc */
+	PCI_COMPAT_DOMAIN_0	= 0x00000020,	/* ... except domain 0 */
+	PCI_SCAN_ALL_PCIE_DEVS	= 0x00000040,	/* scan all, not just dev 0 */
+};
+
 /* these external functions are only available when PCI support is enabled */
 #ifdef CONFIG_PCI
 
+extern unsigned int pci_flags;
+
+static inline void pci_set_flags(int flags) { pci_flags = flags; }
+static inline void pci_add_flags(int flags) { pci_flags |= flags; }
+static inline void pci_clear_flags(int flags) { pci_flags &= ~flags; }
+static inline int pci_has_flag(int flag) { return pci_flags & flag; }
+
 void pcie_bus_configure_settings(struct pci_bus *bus);
 
 enum pcie_bus_config_types {
@@ -988,23 +1002,6 @@ static inline int pci_is_managed(struct pci_dev *pdev)
 	return pdev->is_managed;
 }
 
-static inline void pci_set_managed_irq(struct pci_dev *pdev, unsigned int irq)
-{
-	pdev->irq = irq;
-	pdev->irq_managed = 1;
-}
-
-static inline void pci_reset_managed_irq(struct pci_dev *pdev)
-{
-	pdev->irq = 0;
-	pdev->irq_managed = 0;
-}
-
-static inline bool pci_has_managed_irq(struct pci_dev *pdev)
-{
-	return pdev->irq_managed && pdev->irq > 0;
-}
-
 void pci_disable_device(struct pci_dev *dev);
 
 extern unsigned int pcibios_max_latency;
@@ -1021,8 +1018,6 @@ void pci_intx(struct pci_dev *dev, int enable);
 bool pci_intx_mask_supported(struct pci_dev *dev);
 bool pci_check_and_mask_intx(struct pci_dev *dev);
 bool pci_check_and_unmask_intx(struct pci_dev *dev);
-int pci_set_dma_max_seg_size(struct pci_dev *dev, unsigned int size);
-int pci_set_dma_seg_boundary(struct pci_dev *dev, unsigned long mask);
 int pci_wait_for_pending(struct pci_dev *dev, int pos, u16 mask);
 int pci_wait_for_pending_transaction(struct pci_dev *dev);
 int pcix_get_max_mmrbc(struct pci_dev *dev);
@@ -1238,6 +1233,7 @@ resource_size_t pcibios_iov_resource_alignment(struct pci_dev *dev, int resno);
 
 int pci_set_vga_state(struct pci_dev *pdev, bool decode,
 		      unsigned int command_bits, u32 flags);
+
 /* kmem_cache style wrapper around pci_alloc_consistent() */
 
 #include <linux/pci-dma.h>
@@ -1405,6 +1401,11 @@ void pci_register_set_vga_state(arch_set_vga_state_t func);
 
 #else /* CONFIG_PCI is not enabled */
 
+static inline void pci_set_flags(int flags) { }
+static inline void pci_add_flags(int flags) { }
+static inline void pci_clear_flags(int flags) { }
+static inline int pci_has_flag(int flag) { return 0; }
+
 /*
  *  If the system does not have PCI, clearly these return errors.  Define
  *  these as simple inline functions to avoid hair in drivers.
@@ -1444,16 +1445,6 @@ static inline struct pci_dev *pci_get_class(unsigned int class,
 static inline void pci_set_master(struct pci_dev *dev) { }
 static inline int pci_enable_device(struct pci_dev *dev) { return -EIO; }
 static inline void pci_disable_device(struct pci_dev *dev) { }
-static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask)
-{ return -EIO; }
-static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask)
-{ return -EIO; }
-static inline int pci_set_dma_max_seg_size(struct pci_dev *dev,
-					unsigned int size)
-{ return -EIO; }
-static inline int pci_set_dma_seg_boundary(struct pci_dev *dev,
-					unsigned long mask)
-{ return -EIO; }
 static inline int pci_assign_resource(struct pci_dev *dev, int i)
 { return -EBUSY; }
 static inline int __pci_register_driver(struct pci_driver *drv,
@@ -1515,6 +1506,10 @@ static inline int pci_get_new_domain_nr(void) { return -ENOSYS; }
 
 #include <asm/pci.h>
 
+#ifndef pci_root_bus_fwnode
+#define pci_root_bus_fwnode(bus)	NULL
+#endif
+
 /* these helpers provide future and backwards compatibility
  * for accessing popular PCI BAR info */
 #define pci_resource_start(dev, bar)	((dev)->resource[(bar)].start)
@@ -1834,12 +1829,13 @@ bool pci_acs_path_enabled(struct pci_dev *start,
 #define PCI_VPD_LRDT_RW_DATA		PCI_VPD_LRDT_ID(PCI_VPD_LTIN_RW_DATA)
 
 /* Small Resource Data Type Tag Item Names */
-#define PCI_VPD_STIN_END		0x78	/* End */
+#define PCI_VPD_STIN_END		0x0f	/* End */
 
-#define PCI_VPD_SRDT_END		PCI_VPD_STIN_END
+#define PCI_VPD_SRDT_END		(PCI_VPD_STIN_END << 3)
 
 #define PCI_VPD_SRDT_TIN_MASK		0x78
 #define PCI_VPD_SRDT_LEN_MASK		0x07
+#define PCI_VPD_LRDT_TIN_MASK		0x7f
 
 #define PCI_VPD_LRDT_TAG_SIZE		3
 #define PCI_VPD_SRDT_TAG_SIZE		1
@@ -1863,6 +1859,17 @@ static inline u16 pci_vpd_lrdt_size(const u8 *lrdt)
 }
 
 /**
+ * pci_vpd_lrdt_tag - Extracts the Large Resource Data Type Tag Item
+ * @lrdt: Pointer to the beginning of the Large Resource Data Type tag
+ *
+ * Returns the extracted Large Resource Data Type Tag item.
+ */
+static inline u16 pci_vpd_lrdt_tag(const u8 *lrdt)
+{
+    return (u16)(lrdt[0] & PCI_VPD_LRDT_TIN_MASK);
+}
+
+/**
  * pci_vpd_srdt_size - Extracts the Small Resource Data Type length
  * @lrdt: Pointer to the beginning of the Small Resource Data Type tag
  *
@@ -1874,6 +1881,17 @@ static inline u8 pci_vpd_srdt_size(const u8 *srdt)
 }
 
 /**
+ * pci_vpd_srdt_tag - Extracts the Small Resource Data Type Tag Item
+ * @lrdt: Pointer to the beginning of the Small Resource Data Type tag
+ *
+ * Returns the extracted Small Resource Data Type Tag Item.
+ */
+static inline u8 pci_vpd_srdt_tag(const u8 *srdt)
+{
+	return ((*srdt) & PCI_VPD_SRDT_TIN_MASK) >> 3;
+}
+
+/**
  * pci_vpd_info_field_size - Extracts the information field length
  * @lrdt: Pointer to the beginning of an information field header
  *
@@ -1989,4 +2007,8 @@ static inline bool pci_ari_enabled(struct pci_bus *bus)
 {
 	return bus->self && bus->self->ari_enabled;
 }
+
+/* provide the legacy pci_dma_* API */
+#include <linux/pci-dma-compat.h>
+
 #endif /* LINUX_PCI_H */
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 37f05cb1dfd6..247da8c95860 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -110,6 +110,7 @@
 #define PCI_CLASS_SERIAL_USB_OHCI	0x0c0310
 #define PCI_CLASS_SERIAL_USB_EHCI	0x0c0320
 #define PCI_CLASS_SERIAL_USB_XHCI	0x0c0330
+#define PCI_CLASS_SERIAL_USB_DEVICE	0x0c03fe
 #define PCI_CLASS_SERIAL_FIBER		0x0c04
 #define PCI_CLASS_SERIAL_SMBUS		0x0c05
 
@@ -2506,6 +2507,10 @@
 
 #define PCI_VENDOR_ID_AZWAVE		0x1a3b
 
+#define PCI_VENDOR_ID_REDHAT_QUMRANET    0x1af4
+#define PCI_SUBVENDOR_ID_REDHAT_QUMRANET 0x1af4
+#define PCI_SUBDEVICE_ID_QEMU            0x1100
+
 #define PCI_VENDOR_ID_ASMEDIA		0x1b21
 
 #define PCI_VENDOR_ID_CIRCUITCO		0x1cc8
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b35a61a481fa..79ec7bbf0155 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -397,6 +397,7 @@ struct pmu {
  * enum perf_event_active_state - the states of a event
  */
 enum perf_event_active_state {
+	PERF_EVENT_STATE_DEAD		= -4,
 	PERF_EVENT_STATE_EXIT		= -3,
 	PERF_EVENT_STATE_ERROR		= -2,
 	PERF_EVENT_STATE_OFF		= -1,
@@ -467,6 +468,7 @@ struct perf_event {
 	int				group_flags;
 	struct perf_event		*group_leader;
 	struct pmu			*pmu;
+	void				*pmu_private;
 
 	enum perf_event_active_state	state;
 	unsigned int			attach_state;
@@ -905,7 +907,7 @@ perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)
 	}
 }
 
-extern struct static_key_deferred perf_sched_events;
+extern struct static_key_false perf_sched_events;
 
 static __always_inline bool
 perf_sw_migrate_enabled(void)
@@ -924,7 +926,7 @@ static inline void perf_event_task_migrate(struct task_struct *task)
 static inline void perf_event_task_sched_in(struct task_struct *prev,
 					    struct task_struct *task)
 {
-	if (static_key_false(&perf_sched_events.key))
+	if (static_branch_unlikely(&perf_sched_events))
 		__perf_event_task_sched_in(prev, task);
 
 	if (perf_sw_migrate_enabled() && task->sched_migrated) {
@@ -941,7 +943,7 @@ static inline void perf_event_task_sched_out(struct task_struct *prev,
 {
 	perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0);
 
-	if (static_key_false(&perf_sched_events.key))
+	if (static_branch_unlikely(&perf_sched_events))
 		__perf_event_task_sched_out(prev, next);
 }
 
@@ -1108,12 +1110,6 @@ static inline void perf_event_task_tick(void)				{ }
 static inline int perf_event_release_kernel(struct perf_event *event)	{ return 0; }
 #endif
 
-#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_NO_HZ_FULL)
-extern bool perf_event_can_stop_tick(void);
-#else
-static inline bool perf_event_can_stop_tick(void)			{ return true; }
-#endif
-
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
 extern void perf_restore_debug_store(void);
 #else
diff --git a/include/linux/pfn.h b/include/linux/pfn.h
index 2d8e49711b63..1132953235c0 100644
--- a/include/linux/pfn.h
+++ b/include/linux/pfn.h
@@ -10,7 +10,7 @@
  * backing is indicated by flags in the high bits of the value.
  */
 typedef struct {
-	unsigned long val;
+	u64 val;
 } pfn_t;
 #endif
 
diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h
index 37448ab5fb5c..94994810c7c0 100644
--- a/include/linux/pfn_t.h
+++ b/include/linux/pfn_t.h
@@ -9,14 +9,13 @@
  * PFN_DEV - pfn is not covered by system memmap by default
  * PFN_MAP - pfn has a dynamic page mapping established by a device driver
  */
-#define PFN_FLAGS_MASK (((unsigned long) ~PAGE_MASK) \
-		<< (BITS_PER_LONG - PAGE_SHIFT))
-#define PFN_SG_CHAIN (1UL << (BITS_PER_LONG - 1))
-#define PFN_SG_LAST (1UL << (BITS_PER_LONG - 2))
-#define PFN_DEV (1UL << (BITS_PER_LONG - 3))
-#define PFN_MAP (1UL << (BITS_PER_LONG - 4))
-
-static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, unsigned long flags)
+#define PFN_FLAGS_MASK (((u64) ~PAGE_MASK) << (BITS_PER_LONG_LONG - PAGE_SHIFT))
+#define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1))
+#define PFN_SG_LAST (1ULL << (BITS_PER_LONG_LONG - 2))
+#define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3))
+#define PFN_MAP (1ULL << (BITS_PER_LONG_LONG - 4))
+
+static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, u64 flags)
 {
 	pfn_t pfn_t = { .val = pfn | (flags & PFN_FLAGS_MASK), };
 
@@ -29,7 +28,7 @@ static inline pfn_t pfn_to_pfn_t(unsigned long pfn)
 	return __pfn_to_pfn_t(pfn, 0);
 }
 
-extern pfn_t phys_to_pfn_t(phys_addr_t addr, unsigned long flags);
+extern pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags);
 
 static inline bool pfn_t_has_page(pfn_t pfn)
 {
@@ -87,7 +86,7 @@ static inline pmd_t pfn_t_pmd(pfn_t pfn, pgprot_t pgprot)
 #ifdef __HAVE_ARCH_PTE_DEVMAP
 static inline bool pfn_t_devmap(pfn_t pfn)
 {
-	const unsigned long flags = PFN_DEV|PFN_MAP;
+	const u64 flags = PFN_DEV|PFN_MAP;
 
 	return (pfn.val & flags) == flags;
 }
diff --git a/include/linux/platform_data/ntc_thermistor.h b/include/linux/platform_data/ntc_thermistor.h
index aed170588b74..698d0d59db76 100644
--- a/include/linux/platform_data/ntc_thermistor.h
+++ b/include/linux/platform_data/ntc_thermistor.h
@@ -28,6 +28,7 @@ enum ntc_thermistor_type {
 	TYPE_NCPXXWL333,
 	TYPE_B57330V2103,
 	TYPE_NCPXXWF104,
+	TYPE_NCPXXXH103,
 };
 
 struct ntc_thermistor_platform_data {
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index db21d3995f7e..49cd8890b873 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -19,6 +19,8 @@
 /* Defines used for the flags field in the struct generic_pm_domain */
 #define GENPD_FLAG_PM_CLK	(1U << 0) /* PM domain uses PM clk */
 
+#define GENPD_MAX_NUM_STATES	8 /* Number of possible low power states */
+
 enum gpd_status {
 	GPD_STATE_ACTIVE = 0,	/* PM domain is active */
 	GPD_STATE_POWER_OFF,	/* PM domain is off */
@@ -37,6 +39,11 @@ struct gpd_dev_ops {
 	bool (*active_wakeup)(struct device *dev);
 };
 
+struct genpd_power_state {
+	s64 power_off_latency_ns;
+	s64 power_on_latency_ns;
+};
+
 struct generic_pm_domain {
 	struct dev_pm_domain domain;	/* PM domain operations */
 	struct list_head gpd_list_node;	/* Node in the global PM domains list */
@@ -54,9 +61,7 @@ struct generic_pm_domain {
 	unsigned int prepared_count;	/* Suspend counter of prepared devices */
 	bool suspend_power_off;	/* Power status before system suspend */
 	int (*power_off)(struct generic_pm_domain *domain);
-	s64 power_off_latency_ns;
 	int (*power_on)(struct generic_pm_domain *domain);
-	s64 power_on_latency_ns;
 	struct gpd_dev_ops dev_ops;
 	s64 max_off_time_ns;	/* Maximum allowed "suspended" time. */
 	bool max_off_time_changed;
@@ -66,6 +71,10 @@ struct generic_pm_domain {
 	void (*detach_dev)(struct generic_pm_domain *domain,
 			   struct device *dev);
 	unsigned int flags;		/* Bit field of configs for genpd */
+	struct genpd_power_state states[GENPD_MAX_NUM_STATES];
+	unsigned int state_count; /* number of states */
+	unsigned int state_idx; /* state that genpd will go to when off */
+
 };
 
 static inline struct generic_pm_domain *pd_to_genpd(struct dev_pm_domain *pd)
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 95403d2ccaf5..cccaf4a29e9f 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -34,6 +34,8 @@ bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp);
 
 int dev_pm_opp_get_opp_count(struct device *dev);
 unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev);
+unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev);
+unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev);
 struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev);
 
 struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
@@ -60,6 +62,9 @@ int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions,
 void dev_pm_opp_put_supported_hw(struct device *dev);
 int dev_pm_opp_set_prop_name(struct device *dev, const char *name);
 void dev_pm_opp_put_prop_name(struct device *dev);
+int dev_pm_opp_set_regulator(struct device *dev, const char *name);
+void dev_pm_opp_put_regulator(struct device *dev);
+int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq);
 #else
 static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 {
@@ -86,6 +91,16 @@ static inline unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev)
 	return 0;
 }
 
+static inline unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
+{
+	return 0;
+}
+
+static inline unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev)
+{
+	return 0;
+}
+
 static inline struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev)
 {
 	return NULL;
@@ -151,6 +166,18 @@ static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 
 static inline void dev_pm_opp_put_prop_name(struct device *dev) {}
 
+static inline int dev_pm_opp_set_regulator(struct device *dev, const char *name)
+{
+	return -EINVAL;
+}
+
+static inline void dev_pm_opp_put_regulator(struct device *dev) {}
+
+static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
+{
+	return -EINVAL;
+}
+
 #endif		/* CONFIG_PM_OPP */
 
 #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF)
diff --git a/include/linux/pmem.h b/include/linux/pmem.h
index 7c3d11a6b4ad..3ec5309e29f3 100644
--- a/include/linux/pmem.h
+++ b/include/linux/pmem.h
@@ -58,6 +58,11 @@ static inline void arch_wb_cache_pmem(void __pmem *addr, size_t size)
 {
 	BUG();
 }
+
+static inline void arch_invalidate_pmem(void __pmem *addr, size_t size)
+{
+	BUG();
+}
 #endif
 
 /*
@@ -186,6 +191,20 @@ static inline void clear_pmem(void __pmem *addr, size_t size)
 }
 
 /**
+ * invalidate_pmem - flush a pmem range from the cache hierarchy
+ * @addr:	virtual start address
+ * @size:	bytes to invalidate (internally aligned to cache line size)
+ *
+ * For platforms that support clearing poison this flushes any poisoned
+ * ranges out of the cache
+ */
+static inline void invalidate_pmem(void __pmem *addr, size_t size)
+{
+	if (arch_has_pmem_api())
+		arch_invalidate_pmem(addr, size);
+}
+
+/**
  * wb_cache_pmem - write back processor cache for PMEM memory range
  * @addr:	virtual start address
  * @size:	number of bytes to write back
diff --git a/include/linux/poison.h b/include/linux/poison.h
index 4a27153574e2..51334edec506 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -30,7 +30,11 @@
 #define TIMER_ENTRY_STATIC	((void *) 0x300 + POISON_POINTER_DELTA)
 
 /********** mm/debug-pagealloc.c **********/
+#ifdef CONFIG_PAGE_POISONING_ZERO
+#define PAGE_POISON 0x00
+#else
 #define PAGE_POISON 0xaa
+#endif
 
 /********** mm/page_alloc.c ************/
 
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 907f3fd191ac..62d44c176071 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -128,9 +128,6 @@ void posix_cpu_timer_schedule(struct k_itimer *timer);
 void run_posix_cpu_timers(struct task_struct *task);
 void posix_cpu_timers_exit(struct task_struct *task);
 void posix_cpu_timers_exit_group(struct task_struct *task);
-
-bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk);
-
 void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx,
 			   cputime_t *newval, cputime_t *oldval);
 
diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h
index 998d8f1c3c91..b50c0492629d 100644
--- a/include/linux/power/bq27xxx_battery.h
+++ b/include/linux/power/bq27xxx_battery.h
@@ -49,6 +49,7 @@ struct bq27xxx_reg_cache {
 
 struct bq27xxx_device_info {
 	struct device *dev;
+	int id;
 	enum bq27xxx_chip chip;
 	const char *name;
 	struct bq27xxx_access_methods bus;
diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h
index 54bf1484d41f..35ac903956c7 100644
--- a/include/linux/pps_kernel.h
+++ b/include/linux/pps_kernel.h
@@ -111,22 +111,17 @@ static inline void timespec_to_pps_ktime(struct pps_ktime *kt,
 	kt->nsec = ts.tv_nsec;
 }
 
-#ifdef CONFIG_NTP_PPS
-
 static inline void pps_get_ts(struct pps_event_time *ts)
 {
-	ktime_get_raw_and_real_ts64(&ts->ts_raw, &ts->ts_real);
-}
+	struct system_time_snapshot snap;
 
-#else /* CONFIG_NTP_PPS */
-
-static inline void pps_get_ts(struct pps_event_time *ts)
-{
-	ktime_get_real_ts64(&ts->ts_real);
+	ktime_get_snapshot(&snap);
+	ts->ts_real = ktime_to_timespec64(snap.real);
+#ifdef CONFIG_NTP_PPS
+	ts->ts_raw = ktime_to_timespec64(snap.raw);
+#endif
 }
 
-#endif /* CONFIG_NTP_PPS */
-
 /* Subtract known time delay from PPS event time(s) */
 static inline void pps_sub_ts(struct pps_event_time *ts, struct timespec64 delta)
 {
diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index b8b73066d137..6b15e168148a 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -38,6 +38,7 @@ struct ptp_clock_request {
 	};
 };
 
+struct system_device_crosststamp;
 /**
  * struct ptp_clock_info - decribes a PTP hardware clock
  *
@@ -67,6 +68,11 @@ struct ptp_clock_request {
  * @gettime64:  Reads the current time from the hardware clock.
  *              parameter ts: Holds the result.
  *
+ * @getcrosststamp:  Reads the current time from the hardware clock and
+ *                   system clock simultaneously.
+ *                   parameter cts: Contains timestamp (device,system) pair,
+ *                   where system time is realtime and monotonic.
+ *
  * @settime64:  Set the current time on the hardware clock.
  *              parameter ts: Time value to set.
  *
@@ -105,6 +111,8 @@ struct ptp_clock_info {
 	int (*adjfreq)(struct ptp_clock_info *ptp, s32 delta);
 	int (*adjtime)(struct ptp_clock_info *ptp, s64 delta);
 	int (*gettime64)(struct ptp_clock_info *ptp, struct timespec64 *ts);
+	int (*getcrosststamp)(struct ptp_clock_info *ptp,
+			      struct system_device_crosststamp *cts);
 	int (*settime64)(struct ptp_clock_info *p, const struct timespec64 *ts);
 	int (*enable)(struct ptp_clock_info *ptp,
 		      struct ptp_clock_request *request, int on);
diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h
index c2f2574ff61c..2a097d176ba9 100644
--- a/include/linux/pxa2xx_ssp.h
+++ b/include/linux/pxa2xx_ssp.h
@@ -197,6 +197,7 @@ enum pxa_ssp_type {
 	QUARK_X1000_SSP,
 	LPSS_LPT_SSP, /* Keep LPSS types sorted with lpss_platforms[] */
 	LPSS_BYT_SSP,
+	LPSS_BSW_SSP,
 	LPSS_SPT_SSP,
 	LPSS_BXT_SSP,
 };
diff --git a/include/linux/random.h b/include/linux/random.h
index a75840c1aa71..9c29122037f9 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -34,6 +34,7 @@ extern const struct file_operations random_fops, urandom_fops;
 #endif
 
 unsigned int get_random_int(void);
+unsigned long get_random_long(void);
 unsigned long randomize_range(unsigned long start, unsigned long end, unsigned long len);
 
 u32 prandom_u32(void);
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 14e6f47ee16f..2657aff2725b 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -332,9 +332,7 @@ void rcu_init(void);
 void rcu_sched_qs(void);
 void rcu_bh_qs(void);
 void rcu_check_callbacks(int user);
-struct notifier_block;
-int rcu_cpu_notify(struct notifier_block *self,
-		   unsigned long action, void *hcpu);
+void rcu_report_dead(unsigned int cpu);
 
 #ifndef CONFIG_TINY_RCU
 void rcu_end_inkernel_boot(void);
@@ -360,8 +358,6 @@ void rcu_user_exit(void);
 #else
 static inline void rcu_user_enter(void) { }
 static inline void rcu_user_exit(void) { }
-static inline void rcu_user_hooks_switch(struct task_struct *prev,
-					 struct task_struct *next) { }
 #endif /* CONFIG_NO_HZ_FULL */
 
 #ifdef CONFIG_RCU_NOCB_CPU
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 18394343f489..3dc08ce15426 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -65,6 +65,36 @@ struct reg_sequence {
 	unsigned int delay_us;
 };
 
+#define	regmap_update_bits(map, reg, mask, val) \
+	regmap_update_bits_base(map, reg, mask, val, NULL, false, false)
+#define	regmap_update_bits_async(map, reg, mask, val)\
+	regmap_update_bits_base(map, reg, mask, val, NULL, true, false)
+#define	regmap_update_bits_check(map, reg, mask, val, change)\
+	regmap_update_bits_base(map, reg, mask, val, change, false, false)
+#define	regmap_update_bits_check_async(map, reg, mask, val, change)\
+	regmap_update_bits_base(map, reg, mask, val, change, true, false)
+
+#define	regmap_write_bits(map, reg, mask, val) \
+	regmap_update_bits_base(map, reg, mask, val, NULL, false, true)
+
+#define	regmap_field_write(field, val) \
+	regmap_field_update_bits_base(field, ~0, val, NULL, false, false)
+#define	regmap_field_force_write(field, val) \
+	regmap_field_update_bits_base(field, ~0, val, NULL, false, true)
+#define	regmap_field_update_bits(field, mask, val)\
+	regmap_field_update_bits_base(field, mask, val, NULL, false, false)
+#define	regmap_field_force_update_bits(field, mask, val) \
+	regmap_field_update_bits_base(field, mask, val, NULL, false, true)
+
+#define	regmap_fields_write(field, id, val) \
+	regmap_fields_update_bits_base(field, id, ~0, val, NULL, false, false)
+#define	regmap_fields_force_write(field, id, val) \
+	regmap_fields_update_bits_base(field, id, ~0, val, NULL, false, true)
+#define	regmap_fields_update_bits(field, id, mask, val)\
+	regmap_fields_update_bits_base(field, id, mask, val, NULL, false, false)
+#define	regmap_fields_force_update_bits(field, id, mask, val) \
+	regmap_fields_update_bits_base(field, id, mask, val, NULL, false, true)
+
 #ifdef CONFIG_REGMAP
 
 enum regmap_endian {
@@ -162,7 +192,7 @@ typedef void (*regmap_unlock)(void *);
  *		  This field is a duplicate of a similar file in
  *		  'struct regmap_bus' and serves exact same purpose.
  *		   Use it only for "no-bus" cases.
- * @max_register: Optional, specifies the maximum valid register index.
+ * @max_register: Optional, specifies the maximum valid register address.
  * @wr_table:     Optional, points to a struct regmap_access_table specifying
  *                valid ranges for write access.
  * @rd_table:     As above, for read access.
@@ -691,18 +721,9 @@ int regmap_raw_read(struct regmap *map, unsigned int reg,
 		    void *val, size_t val_len);
 int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val,
 		     size_t val_count);
-int regmap_update_bits(struct regmap *map, unsigned int reg,
-		       unsigned int mask, unsigned int val);
-int regmap_write_bits(struct regmap *map, unsigned int reg,
-		       unsigned int mask, unsigned int val);
-int regmap_update_bits_async(struct regmap *map, unsigned int reg,
-			     unsigned int mask, unsigned int val);
-int regmap_update_bits_check(struct regmap *map, unsigned int reg,
-			     unsigned int mask, unsigned int val,
-			     bool *change);
-int regmap_update_bits_check_async(struct regmap *map, unsigned int reg,
-				   unsigned int mask, unsigned int val,
-				   bool *change);
+int regmap_update_bits_base(struct regmap *map, unsigned int reg,
+			    unsigned int mask, unsigned int val,
+			    bool *change, bool async, bool force);
 int regmap_get_val_bytes(struct regmap *map);
 int regmap_get_max_register(struct regmap *map);
 int regmap_get_reg_stride(struct regmap *map);
@@ -770,18 +791,14 @@ struct regmap_field *devm_regmap_field_alloc(struct device *dev,
 void devm_regmap_field_free(struct device *dev,	struct regmap_field *field);
 
 int regmap_field_read(struct regmap_field *field, unsigned int *val);
-int regmap_field_write(struct regmap_field *field, unsigned int val);
-int regmap_field_update_bits(struct regmap_field *field,
-			     unsigned int mask, unsigned int val);
-
-int regmap_fields_write(struct regmap_field *field, unsigned int id,
-			unsigned int val);
-int regmap_fields_force_write(struct regmap_field *field, unsigned int id,
-			unsigned int val);
+int regmap_field_update_bits_base(struct regmap_field *field,
+				  unsigned int mask, unsigned int val,
+				  bool *change, bool async, bool force);
 int regmap_fields_read(struct regmap_field *field, unsigned int id,
 		       unsigned int *val);
-int regmap_fields_update_bits(struct regmap_field *field,  unsigned int id,
-			      unsigned int mask, unsigned int val);
+int regmap_fields_update_bits_base(struct regmap_field *field,  unsigned int id,
+				   unsigned int mask, unsigned int val,
+				   bool *change, bool async, bool force);
 
 /**
  * Description of an IRQ for the generic regmap irq_chip.
@@ -868,6 +885,14 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags,
 			int irq_base, const struct regmap_irq_chip *chip,
 			struct regmap_irq_chip_data **data);
 void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *data);
+
+int devm_regmap_add_irq_chip(struct device *dev, struct regmap *map, int irq,
+			     int irq_flags, int irq_base,
+			     const struct regmap_irq_chip *chip,
+			     struct regmap_irq_chip_data **data);
+void devm_regmap_del_irq_chip(struct device *dev, int irq,
+			      struct regmap_irq_chip_data *data);
+
 int regmap_irq_chip_get_base(struct regmap_irq_chip_data *data);
 int regmap_irq_get_virq(struct regmap_irq_chip_data *data, int irq);
 struct irq_domain *regmap_irq_get_domain(struct regmap_irq_chip_data *data);
@@ -937,42 +962,26 @@ static inline int regmap_bulk_read(struct regmap *map, unsigned int reg,
 	return -EINVAL;
 }
 
-static inline int regmap_update_bits(struct regmap *map, unsigned int reg,
-				     unsigned int mask, unsigned int val)
-{
-	WARN_ONCE(1, "regmap API is disabled");
-	return -EINVAL;
-}
-
-static inline int regmap_write_bits(struct regmap *map, unsigned int reg,
-				     unsigned int mask, unsigned int val)
-{
-	WARN_ONCE(1, "regmap API is disabled");
-	return -EINVAL;
-}
-
-static inline int regmap_update_bits_async(struct regmap *map,
-					   unsigned int reg,
-					   unsigned int mask, unsigned int val)
+static inline int regmap_update_bits_base(struct regmap *map, unsigned int reg,
+					  unsigned int mask, unsigned int val,
+					  bool *change, bool async, bool force)
 {
 	WARN_ONCE(1, "regmap API is disabled");
 	return -EINVAL;
 }
 
-static inline int regmap_update_bits_check(struct regmap *map,
-					   unsigned int reg,
-					   unsigned int mask, unsigned int val,
-					   bool *change)
+static inline int regmap_field_update_bits_base(struct regmap_field *field,
+					unsigned int mask, unsigned int val,
+					bool *change, bool async, bool force)
 {
 	WARN_ONCE(1, "regmap API is disabled");
 	return -EINVAL;
 }
 
-static inline int regmap_update_bits_check_async(struct regmap *map,
-						 unsigned int reg,
-						 unsigned int mask,
-						 unsigned int val,
-						 bool *change)
+static inline int regmap_fields_update_bits_base(struct regmap_field *field,
+				   unsigned int id,
+				   unsigned int mask, unsigned int val,
+				   bool *change, bool async, bool force)
 {
 	WARN_ONCE(1, "regmap API is disabled");
 	return -EINVAL;
diff --git a/include/linux/regulator/act8865.h b/include/linux/regulator/act8865.h
index 15fa8f2d35c9..2eb386017fa5 100644
--- a/include/linux/regulator/act8865.h
+++ b/include/linux/regulator/act8865.h
@@ -68,12 +68,12 @@ enum {
  * act8865_regulator_data - regulator data
  * @id: regulator id
  * @name: regulator name
- * @platform_data: regulator init data
+ * @init_data: regulator init data
  */
 struct act8865_regulator_data {
 	int id;
 	const char *name;
-	struct regulator_init_data *platform_data;
+	struct regulator_init_data *init_data;
 };
 
 /**
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 16ac9e108806..cd271e89a7e6 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -93,6 +93,8 @@ struct regulator_linear_range {
  * @get_current_limit: Get the configured limit for a current-limited regulator.
  * @set_input_current_limit: Configure an input limit.
  *
+ * @set_active_discharge: Set active discharge enable/disable of regulators.
+ *
  * @set_mode: Set the configured operating mode for the regulator.
  * @get_mode: Get the configured operating mode for the regulator.
  * @get_status: Return actual (not as-configured) status of regulator, as a
@@ -149,6 +151,7 @@ struct regulator_ops {
 
 	int (*set_input_current_limit) (struct regulator_dev *, int lim_uA);
 	int (*set_over_current_protection) (struct regulator_dev *);
+	int (*set_active_discharge) (struct regulator_dev *, bool enable);
 
 	/* enable/disable regulator */
 	int (*enable) (struct regulator_dev *);
@@ -266,6 +269,14 @@ enum regulator_type {
  * @bypass_mask: Mask for control when using regmap set_bypass
  * @bypass_val_on: Enabling value for control when using regmap set_bypass
  * @bypass_val_off: Disabling value for control when using regmap set_bypass
+ * @active_discharge_off: Enabling value for control when using regmap
+ *			  set_active_discharge
+ * @active_discharge_on: Disabling value for control when using regmap
+ *			 set_active_discharge
+ * @active_discharge_mask: Mask for control when using regmap
+ *			   set_active_discharge
+ * @active_discharge_reg: Register for control when using regmap
+ *			  set_active_discharge
  *
  * @enable_time: Time taken for initial enable of regulator (in uS).
  * @off_on_delay: guard time (in uS), before re-enabling a regulator
@@ -315,6 +326,10 @@ struct regulator_desc {
 	unsigned int bypass_mask;
 	unsigned int bypass_val_on;
 	unsigned int bypass_val_off;
+	unsigned int active_discharge_on;
+	unsigned int active_discharge_off;
+	unsigned int active_discharge_mask;
+	unsigned int active_discharge_reg;
 
 	unsigned int enable_time;
 
@@ -447,6 +462,8 @@ int regulator_set_voltage_time_sel(struct regulator_dev *rdev,
 int regulator_set_bypass_regmap(struct regulator_dev *rdev, bool enable);
 int regulator_get_bypass_regmap(struct regulator_dev *rdev, bool *enable);
 
+int regulator_set_active_discharge_regmap(struct regulator_dev *rdev,
+					  bool enable);
 void *regulator_get_init_drvdata(struct regulator_init_data *reg_init_data);
 
 #endif
diff --git a/include/linux/regulator/lp872x.h b/include/linux/regulator/lp872x.h
index 132e05c46661..6029279f4eed 100644
--- a/include/linux/regulator/lp872x.h
+++ b/include/linux/regulator/lp872x.h
@@ -18,6 +18,9 @@
 
 #define LP872X_MAX_REGULATORS		9
 
+#define LP8720_ENABLE_DELAY		200
+#define LP8725_ENABLE_DELAY		30000
+
 enum lp872x_regulator_id {
 	LP8720_ID_BASE,
 	LP8720_ID_LDO1 = LP8720_ID_BASE,
@@ -79,12 +82,14 @@ struct lp872x_regulator_data {
  * @update_config     : if LP872X_GENERAL_CFG register is updated, set true
  * @regulator_data    : platform regulator id and init data
  * @dvs               : dvs data for buck voltage control
+ * @enable_gpio       : gpio pin number for enable control
  */
 struct lp872x_platform_data {
 	u8 general_config;
 	bool update_config;
 	struct lp872x_regulator_data regulator_data[LP872X_MAX_REGULATORS];
 	struct lp872x_dvs *dvs;
+	int enable_gpio;
 };
 
 #endif
diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h
index a1067d0b3991..5d627c83a630 100644
--- a/include/linux/regulator/machine.h
+++ b/include/linux/regulator/machine.h
@@ -42,6 +42,13 @@ struct regulator;
 #define REGULATOR_CHANGE_DRMS		0x10
 #define REGULATOR_CHANGE_BYPASS		0x20
 
+/* Regulator active discharge flags */
+enum regulator_active_discharge {
+	REGULATOR_ACTIVE_DISCHARGE_DEFAULT,
+	REGULATOR_ACTIVE_DISCHARGE_DISABLE,
+	REGULATOR_ACTIVE_DISCHARGE_ENABLE,
+};
+
 /**
  * struct regulator_state - regulator state during low power system states
  *
@@ -100,6 +107,9 @@ struct regulator_state {
  * @initial_state: Suspend state to set by default.
  * @initial_mode: Mode to set at startup.
  * @ramp_delay: Time to settle down after voltage change (unit: uV/us)
+ * @active_discharge: Enable/disable active discharge. The enum
+ *		      regulator_active_discharge values are used for
+ *		      initialisation.
  * @enable_time: Turn-on time of the rails (unit: microseconds)
  */
 struct regulation_constraints {
@@ -140,6 +150,8 @@ struct regulation_constraints {
 	unsigned int ramp_delay;
 	unsigned int enable_time;
 
+	unsigned int active_discharge;
+
 	/* constraint flags */
 	unsigned always_on:1;	/* regulator never off when system is on */
 	unsigned boot_on:1;	/* bootloader/firmware enabled regulator */
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 3359f0422c6b..b693adac853b 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -89,6 +89,8 @@ struct rtc_class_ops {
 	int (*set_mmss)(struct device *, unsigned long secs);
 	int (*read_callback)(struct device *, int data);
 	int (*alarm_irq_enable)(struct device *, unsigned int enabled);
+	int (*read_offset)(struct device *, long *offset);
+	int (*set_offset)(struct device *, long offset);
 };
 
 #define RTC_DEVICE_NAME_SIZE 20
@@ -208,6 +210,8 @@ void rtc_timer_init(struct rtc_timer *timer, void (*f)(void *p), void *data);
 int rtc_timer_start(struct rtc_device *rtc, struct rtc_timer *timer,
 		    ktime_t expires, ktime_t period);
 void rtc_timer_cancel(struct rtc_device *rtc, struct rtc_timer *timer);
+int rtc_read_offset(struct rtc_device *rtc, long *offset);
+int rtc_set_offset(struct rtc_device *rtc, long offset);
 void rtc_timer_do_work(struct work_struct *work);
 
 static inline bool is_leap_year(unsigned int year)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a10494a94cc3..eb7f2f84009b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -182,8 +182,6 @@ extern void update_cpu_load_nohz(int active);
 static inline void update_cpu_load_nohz(int active) { }
 #endif
 
-extern unsigned long get_parent_ip(unsigned long addr);
-
 extern void dump_cpu_task(int cpu);
 
 struct seq_file;
@@ -719,6 +717,10 @@ struct signal_struct {
 	/* Earliest-expiration cache. */
 	struct task_cputime cputime_expires;
 
+#ifdef CONFIG_NO_HZ_FULL
+	unsigned long tick_dep_mask;
+#endif
+
 	struct list_head cpu_timers[3];
 
 	struct pid *tty_old_pgrp;
@@ -920,6 +922,10 @@ static inline int sched_info_on(void)
 #endif
 }
 
+#ifdef CONFIG_SCHEDSTATS
+void force_schedstat_enabled(void);
+#endif
+
 enum cpu_idle_type {
 	CPU_IDLE,
 	CPU_NOT_IDLE,
@@ -1289,6 +1295,8 @@ struct sched_rt_entity {
 	unsigned long timeout;
 	unsigned long watchdog_stamp;
 	unsigned int time_slice;
+	unsigned short on_rq;
+	unsigned short on_list;
 
 	struct sched_rt_entity *back;
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -1329,10 +1337,6 @@ struct sched_dl_entity {
 	 * task has to wait for a replenishment to be performed at the
 	 * next firing of dl_timer.
 	 *
-	 * @dl_new tells if a new instance arrived. If so we must
-	 * start executing it with full runtime and reset its absolute
-	 * deadline;
-	 *
 	 * @dl_boosted tells if we are boosted due to DI. If so we are
 	 * outside bandwidth enforcement mechanism (but only until we
 	 * exit the critical section);
@@ -1340,7 +1344,7 @@ struct sched_dl_entity {
 	 * @dl_yielded tells if task gave up the cpu before consuming
 	 * all its available runtime during the last job.
 	 */
-	int dl_throttled, dl_new, dl_boosted, dl_yielded;
+	int dl_throttled, dl_boosted, dl_yielded;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
@@ -1542,6 +1546,10 @@ struct task_struct {
 		VTIME_SYS,
 	} vtime_snap_whence;
 #endif
+
+#ifdef CONFIG_NO_HZ_FULL
+	unsigned long tick_dep_mask;
+#endif
 	unsigned long nvcsw, nivcsw; /* context switch counts */
 	u64 start_time;		/* monotonic time in nsec */
 	u64 real_start_time;	/* boot based time in nsec */
@@ -2356,10 +2364,7 @@ static inline void wake_up_nohz_cpu(int cpu) { }
 #endif
 
 #ifdef CONFIG_NO_HZ_FULL
-extern bool sched_can_stop_tick(void);
 extern u64 scheduler_tick_max_deferment(void);
-#else
-static inline bool sched_can_stop_tick(void) { return false; }
 #endif
 
 #ifdef CONFIG_SCHED_AUTOGROUP
@@ -3207,4 +3212,13 @@ static inline unsigned long rlimit_max(unsigned int limit)
 	return task_rlimit_max(current, limit);
 }
 
+#ifdef CONFIG_CPU_FREQ
+struct update_util_data {
+	void (*func)(struct update_util_data *data,
+		     u64 time, unsigned long util, unsigned long max);
+};
+
+void cpufreq_set_update_util_data(int cpu, struct update_util_data *data);
+#endif /* CONFIG_CPU_FREQ */
+
 #endif
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index c9e4731cf10b..4f080ab4f2cd 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -95,4 +95,8 @@ extern int sysctl_numa_balancing(struct ctl_table *table, int write,
 				 void __user *buffer, size_t *lenp,
 				 loff_t *ppos);
 
+extern int sysctl_schedstats(struct ctl_table *table, int write,
+				 void __user *buffer, size_t *lenp,
+				 loff_t *ppos);
+
 #endif /* _SCHED_SYSCTL_H */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 11f935c1a090..d3fcd4591ce4 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -299,6 +299,7 @@ struct sk_buff;
 #else
 #define MAX_SKB_FRAGS (65536/PAGE_SIZE + 1)
 #endif
+extern int sysctl_max_skb_frags;
 
 typedef struct skb_frag_struct skb_frag_t;
 
@@ -1984,6 +1985,30 @@ static inline void skb_reserve(struct sk_buff *skb, int len)
 	skb->tail += len;
 }
 
+/**
+ *	skb_tailroom_reserve - adjust reserved_tailroom
+ *	@skb: buffer to alter
+ *	@mtu: maximum amount of headlen permitted
+ *	@needed_tailroom: minimum amount of reserved_tailroom
+ *
+ *	Set reserved_tailroom so that headlen can be as large as possible but
+ *	not larger than mtu and tailroom cannot be smaller than
+ *	needed_tailroom.
+ *	The required headroom should already have been reserved before using
+ *	this function.
+ */
+static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu,
+					unsigned int needed_tailroom)
+{
+	SKB_LINEAR_ASSERT(skb);
+	if (mtu < skb_tailroom(skb) - needed_tailroom)
+		/* use at most mtu */
+		skb->reserved_tailroom = skb_tailroom(skb) - mtu;
+	else
+		/* use up to all available space */
+		skb->reserved_tailroom = needed_tailroom;
+}
+
 #define ENCAP_TYPE_ETHER	0
 #define ENCAP_TYPE_IPPROTO	1
 
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 3627d5c1bc47..e4b568738ca3 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -20,7 +20,7 @@
  * Flags to pass to kmem_cache_create().
  * The ones marked DEBUG are only valid if CONFIG_DEBUG_SLAB is set.
  */
-#define SLAB_DEBUG_FREE		0x00000100UL	/* DEBUG: Perform (expensive) checks on free */
+#define SLAB_CONSISTENCY_CHECKS	0x00000100UL	/* DEBUG: Perform (expensive) checks on alloc/free */
 #define SLAB_RED_ZONE		0x00000400UL	/* DEBUG: Red zone objs in a cache */
 #define SLAB_POISON		0x00000800UL	/* DEBUG: Poison objects */
 #define SLAB_HWCACHE_ALIGN	0x00002000UL	/* Align objs on cache lines */
@@ -314,7 +314,7 @@ void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags) __assume_slab_alignment
 void kmem_cache_free(struct kmem_cache *, void *);
 
 /*
- * Bulk allocation and freeing operations. These are accellerated in an
+ * Bulk allocation and freeing operations. These are accelerated in an
  * allocator specific way to avoid taking locks repeatedly or building
  * metadata structures unnecessarily.
  *
@@ -323,6 +323,15 @@ void kmem_cache_free(struct kmem_cache *, void *);
 void kmem_cache_free_bulk(struct kmem_cache *, size_t, void **);
 int kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **);
 
+/*
+ * Caller must not use kfree_bulk() on memory not originally allocated
+ * by kmalloc(), because the SLOB allocator cannot handle this.
+ */
+static __always_inline void kfree_bulk(size_t size, void **p)
+{
+	kmem_cache_free_bulk(NULL, size, p);
+}
+
 #ifdef CONFIG_NUMA
 void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment;
 void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment;
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index cf139d3fa513..e878ba35ae91 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -60,6 +60,9 @@ struct kmem_cache {
 	atomic_t allocmiss;
 	atomic_t freehit;
 	atomic_t freemiss;
+#ifdef CONFIG_DEBUG_SLAB_LEAK
+	atomic_t store_user_clean;
+#endif
 
 	/*
 	 * If debugging is enabled, then the allocator can add additional
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index b7e57927f521..ac5143f95ee6 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -81,6 +81,7 @@ struct kmem_cache {
 	int reserved;		/* Reserved bytes at the end of slabs */
 	const char *name;	/* Name (only for display!) */
 	struct list_head list;	/* List of slab caches */
+	int red_left_pad;	/* Left redzone padding size */
 #ifdef CONFIG_SYSFS
 	struct kobject kobj;	/* For sysfs */
 #endif
diff --git a/include/linux/soc/ti/knav_dma.h b/include/linux/soc/ti/knav_dma.h
index 343c13ac4f71..35cb9264e0d5 100644
--- a/include/linux/soc/ti/knav_dma.h
+++ b/include/linux/soc/ti/knav_dma.h
@@ -44,6 +44,7 @@
 
 #define KNAV_DMA_NUM_EPIB_WORDS			4
 #define KNAV_DMA_NUM_PS_WORDS			16
+#define KNAV_DMA_NUM_SW_DATA_WORDS		4
 #define KNAV_DMA_FDQ_PER_CHAN			4
 
 /* Tx channel scheduling priority */
@@ -142,6 +143,7 @@ struct knav_dma_cfg {
  * @orig_buff:			buff pointer since 'buff' can be overwritten
  * @epib:			Extended packet info block
  * @psdata:			Protocol specific
+ * @sw_data:			Software private data not touched by h/w
  */
 struct knav_dma_desc {
 	__le32	desc_info;
@@ -154,7 +156,7 @@ struct knav_dma_desc {
 	__le32	orig_buff;
 	__le32	epib[KNAV_DMA_NUM_EPIB_WORDS];
 	__le32	psdata[KNAV_DMA_NUM_PS_WORDS];
-	__le32	pad[4];
+	u32	sw_data[KNAV_DMA_NUM_SW_DATA_WORDS];
 } ____cacheline_aligned;
 
 #if IS_ENABLED(CONFIG_KEYSTONE_NAVIGATOR_DMA)
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 53be3a4c60cb..857a9a1d82b5 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -25,6 +25,7 @@
 struct dma_chan;
 struct spi_master;
 struct spi_transfer;
+struct spi_flash_read_message;
 
 /*
  * INTERFACES between SPI master-side drivers and SPI infrastructure.
@@ -53,6 +54,10 @@ extern struct bus_type spi_bus_type;
  *
  * @transfer_bytes_histo:
  *                 transfer bytes histogramm
+ *
+ * @transfers_split_maxsize:
+ *                 number of transfers that have been split because of
+ *                 maxsize limit
  */
 struct spi_statistics {
 	spinlock_t		lock; /* lock for the whole structure */
@@ -72,6 +77,8 @@ struct spi_statistics {
 
 #define SPI_STATISTICS_HISTO_SIZE 17
 	unsigned long transfer_bytes_histo[SPI_STATISTICS_HISTO_SIZE];
+
+	unsigned long transfers_split_maxsize;
 };
 
 void spi_statistics_add_transfer_stats(struct spi_statistics *stats,
@@ -303,6 +310,8 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @min_speed_hz: Lowest supported transfer speed
  * @max_speed_hz: Highest supported transfer speed
  * @flags: other constraints relevant to this driver
+ * @max_transfer_size: function that returns the max transfer size for
+ *	a &spi_device; may be %NULL, so the default %SIZE_MAX will be used.
  * @bus_lock_spinlock: spinlock for SPI bus locking
  * @bus_lock_mutex: mutex for SPI bus locking
  * @bus_lock_flag: indicates that the SPI bus is locked for exclusive use
@@ -361,6 +370,8 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @handle_err: the subsystem calls the driver to handle an error that occurs
  *		in the generic implementation of transfer_one_message().
  * @unprepare_message: undo any work done by prepare_message().
+ * @spi_flash_read: to support spi-controller hardwares that provide
+ *                  accelerated interface to read from flash devices.
  * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS
  *	number. Any individual value may be -ENOENT for CS lines that
  *	are not GPIOs (driven by the SPI controller itself).
@@ -369,6 +380,9 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @dma_rx: DMA receive channel
  * @dummy_rx: dummy receive buffer for full-duplex devices
  * @dummy_tx: dummy transmit buffer for full-duplex devices
+ * @fw_translate_cs: If the boot firmware uses different numbering scheme
+ *	what Linux expects, this optional hook can be used to translate
+ *	between the two.
  *
  * Each SPI master controller can communicate with one or more @spi_device
  * children.  These make a small bus, sharing MOSI, MISO and SCK signals
@@ -513,6 +527,8 @@ struct spi_master {
 			       struct spi_message *message);
 	int (*unprepare_message)(struct spi_master *master,
 				 struct spi_message *message);
+	int (*spi_flash_read)(struct  spi_device *spi,
+			      struct spi_flash_read_message *msg);
 
 	/*
 	 * These hooks are for drivers that use a generic implementation
@@ -537,6 +553,8 @@ struct spi_master {
 	/* dummy data for full duplex devices */
 	void			*dummy_rx;
 	void			*dummy_tx;
+
+	int (*fw_translate_cs)(struct spi_master *master, unsigned cs);
 };
 
 static inline void *spi_master_get_devdata(struct spi_master *master)
@@ -582,6 +600,38 @@ extern void spi_unregister_master(struct spi_master *master);
 
 extern struct spi_master *spi_busnum_to_master(u16 busnum);
 
+/*
+ * SPI resource management while processing a SPI message
+ */
+
+typedef void (*spi_res_release_t)(struct spi_master *master,
+				  struct spi_message *msg,
+				  void *res);
+
+/**
+ * struct spi_res - spi resource management structure
+ * @entry:   list entry
+ * @release: release code called prior to freeing this resource
+ * @data:    extra data allocated for the specific use-case
+ *
+ * this is based on ideas from devres, but focused on life-cycle
+ * management during spi_message processing
+ */
+struct spi_res {
+	struct list_head        entry;
+	spi_res_release_t       release;
+	unsigned long long      data[]; /* guarantee ull alignment */
+};
+
+extern void *spi_res_alloc(struct spi_device *spi,
+			   spi_res_release_t release,
+			   size_t size, gfp_t gfp);
+extern void spi_res_add(struct spi_message *message, void *res);
+extern void spi_res_free(void *res);
+
+extern void spi_res_release(struct spi_master *master,
+			    struct spi_message *message);
+
 /*---------------------------------------------------------------------------*/
 
 /*
@@ -720,6 +770,7 @@ struct spi_transfer {
  * @status: zero for success, else negative errno
  * @queue: for use by whichever driver currently owns the message
  * @state: for use by whichever driver currently owns the message
+ * @resources: for resource management when the spi message is processed
  *
  * A @spi_message is used to execute an atomic sequence of data transfers,
  * each represented by a struct spi_transfer.  The sequence is "atomic"
@@ -766,11 +817,15 @@ struct spi_message {
 	 */
 	struct list_head	queue;
 	void			*state;
+
+	/* list of spi_res reources when the spi message is processed */
+	struct list_head        resources;
 };
 
 static inline void spi_message_init_no_memset(struct spi_message *m)
 {
 	INIT_LIST_HEAD(&m->transfers);
+	INIT_LIST_HEAD(&m->resources);
 }
 
 static inline void spi_message_init(struct spi_message *m)
@@ -854,6 +909,60 @@ spi_max_transfer_size(struct spi_device *spi)
 
 /*---------------------------------------------------------------------------*/
 
+/* SPI transfer replacement methods which make use of spi_res */
+
+struct spi_replaced_transfers;
+typedef void (*spi_replaced_release_t)(struct spi_master *master,
+				       struct spi_message *msg,
+				       struct spi_replaced_transfers *res);
+/**
+ * struct spi_replaced_transfers - structure describing the spi_transfer
+ *                                 replacements that have occurred
+ *                                 so that they can get reverted
+ * @release:            some extra release code to get executed prior to
+ *                      relasing this structure
+ * @extradata:          pointer to some extra data if requested or NULL
+ * @replaced_transfers: transfers that have been replaced and which need
+ *                      to get restored
+ * @replaced_after:     the transfer after which the @replaced_transfers
+ *                      are to get re-inserted
+ * @inserted:           number of transfers inserted
+ * @inserted_transfers: array of spi_transfers of array-size @inserted,
+ *                      that have been replacing replaced_transfers
+ *
+ * note: that @extradata will point to @inserted_transfers[@inserted]
+ * if some extra allocation is requested, so alignment will be the same
+ * as for spi_transfers
+ */
+struct spi_replaced_transfers {
+	spi_replaced_release_t release;
+	void *extradata;
+	struct list_head replaced_transfers;
+	struct list_head *replaced_after;
+	size_t inserted;
+	struct spi_transfer inserted_transfers[];
+};
+
+extern struct spi_replaced_transfers *spi_replace_transfers(
+	struct spi_message *msg,
+	struct spi_transfer *xfer_first,
+	size_t remove,
+	size_t insert,
+	spi_replaced_release_t release,
+	size_t extradatasize,
+	gfp_t gfp);
+
+/*---------------------------------------------------------------------------*/
+
+/* SPI transfer transformation methods */
+
+extern int spi_split_transfers_maxsize(struct spi_master *master,
+				       struct spi_message *msg,
+				       size_t maxsize,
+				       gfp_t gfp);
+
+/*---------------------------------------------------------------------------*/
+
 /* All these synchronous SPI transfer routines are utilities layered
  * over the core async transfer primitive.  Here, "synchronous" means
  * they will sleep uninterruptibly until the async transfer completes.
@@ -1019,6 +1128,42 @@ static inline ssize_t spi_w8r16be(struct spi_device *spi, u8 cmd)
 	return be16_to_cpu(result);
 }
 
+/**
+ * struct spi_flash_read_message - flash specific information for
+ * spi-masters that provide accelerated flash read interfaces
+ * @buf: buffer to read data
+ * @from: offset within the flash from where data is to be read
+ * @len: length of data to be read
+ * @retlen: actual length of data read
+ * @read_opcode: read_opcode to be used to communicate with flash
+ * @addr_width: number of address bytes
+ * @dummy_bytes: number of dummy bytes
+ * @opcode_nbits: number of lines to send opcode
+ * @addr_nbits: number of lines to send address
+ * @data_nbits: number of lines for data
+ */
+struct spi_flash_read_message {
+	void *buf;
+	loff_t from;
+	size_t len;
+	size_t retlen;
+	u8 read_opcode;
+	u8 addr_width;
+	u8 dummy_bytes;
+	u8 opcode_nbits;
+	u8 addr_nbits;
+	u8 data_nbits;
+};
+
+/* SPI core interface for flash read support */
+static inline bool spi_flash_read_supported(struct spi_device *spi)
+{
+	return spi->master->spi_flash_read ? true : false;
+}
+
+int spi_flash_read(struct spi_device *spi,
+		   struct spi_flash_read_message *msg);
+
 /*---------------------------------------------------------------------------*/
 
 /*
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index f5f80c5643ac..dc8eb63c6568 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -99,8 +99,23 @@ void process_srcu(struct work_struct *work);
 	}
 
 /*
- * define and init a srcu struct at build time.
- * dont't call init_srcu_struct() nor cleanup_srcu_struct() on it.
+ * Define and initialize a srcu struct at build time.
+ * Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it.
+ *
+ * Note that although DEFINE_STATIC_SRCU() hides the name from other
+ * files, the per-CPU variable rules nevertheless require that the
+ * chosen name be globally unique.  These rules also prohibit use of
+ * DEFINE_STATIC_SRCU() within a function.  If these rules are too
+ * restrictive, declare the srcu_struct manually.  For example, in
+ * each file:
+ *
+ *	static struct srcu_struct my_srcu;
+ *
+ * Then, before the first use of each my_srcu, manually initialize it:
+ *
+ *	init_srcu_struct(&my_srcu);
+ *
+ * See include/linux/percpu-defs.h for the rules on per-CPU variables.
  */
 #define __DEFINE_SRCU(name, is_static)					\
 	static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index eead8ab93c0a..881a79d52467 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -100,6 +100,7 @@ struct plat_stmmacenet_data {
 	int interface;
 	struct stmmac_mdio_bus_data *mdio_bus_data;
 	struct device_node *phy_node;
+	struct device_node *mdio_node;
 	struct stmmac_dma_cfg *dma_cfg;
 	int clk_csr;
 	int has_gmac;
diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h
index df02a4188487..7df625d41e35 100644
--- a/include/linux/sunrpc/gss_krb5.h
+++ b/include/linux/sunrpc/gss_krb5.h
@@ -36,7 +36,7 @@
  *
  */
 
-#include <linux/crypto.h>
+#include <crypto/skcipher.h>
 #include <linux/sunrpc/auth_gss.h>
 #include <linux/sunrpc/gss_err.h>
 #include <linux/sunrpc/gss_asn1.h>
@@ -71,10 +71,10 @@ struct gss_krb5_enctype {
 	const u32		keyed_cksum;	/* is it a keyed cksum? */
 	const u32		keybytes;	/* raw key len, in bytes */
 	const u32		keylength;	/* final key len, in bytes */
-	u32 (*encrypt) (struct crypto_blkcipher *tfm,
+	u32 (*encrypt) (struct crypto_skcipher *tfm,
 			void *iv, void *in, void *out,
 			int length);		/* encryption function */
-	u32 (*decrypt) (struct crypto_blkcipher *tfm,
+	u32 (*decrypt) (struct crypto_skcipher *tfm,
 			void *iv, void *in, void *out,
 			int length);		/* decryption function */
 	u32 (*mk_key) (const struct gss_krb5_enctype *gk5e,
@@ -98,12 +98,12 @@ struct krb5_ctx {
 	u32			enctype;
 	u32			flags;
 	const struct gss_krb5_enctype *gk5e; /* enctype-specific info */
-	struct crypto_blkcipher	*enc;
-	struct crypto_blkcipher	*seq;
-	struct crypto_blkcipher *acceptor_enc;
-	struct crypto_blkcipher *initiator_enc;
-	struct crypto_blkcipher *acceptor_enc_aux;
-	struct crypto_blkcipher *initiator_enc_aux;
+	struct crypto_skcipher	*enc;
+	struct crypto_skcipher	*seq;
+	struct crypto_skcipher *acceptor_enc;
+	struct crypto_skcipher *initiator_enc;
+	struct crypto_skcipher *acceptor_enc_aux;
+	struct crypto_skcipher *initiator_enc_aux;
 	u8			Ksess[GSS_KRB5_MAX_KEYLEN]; /* session key */
 	u8			cksum[GSS_KRB5_MAX_KEYLEN];
 	s32			endtime;
@@ -262,24 +262,24 @@ gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset,
 
 
 u32
-krb5_encrypt(struct crypto_blkcipher *key,
+krb5_encrypt(struct crypto_skcipher *key,
 	     void *iv, void *in, void *out, int length);
 
 u32
-krb5_decrypt(struct crypto_blkcipher *key,
+krb5_decrypt(struct crypto_skcipher *key,
 	     void *iv, void *in, void *out, int length); 
 
 int
-gss_encrypt_xdr_buf(struct crypto_blkcipher *tfm, struct xdr_buf *outbuf,
+gss_encrypt_xdr_buf(struct crypto_skcipher *tfm, struct xdr_buf *outbuf,
 		    int offset, struct page **pages);
 
 int
-gss_decrypt_xdr_buf(struct crypto_blkcipher *tfm, struct xdr_buf *inbuf,
+gss_decrypt_xdr_buf(struct crypto_skcipher *tfm, struct xdr_buf *inbuf,
 		    int offset);
 
 s32
 krb5_make_seq_num(struct krb5_ctx *kctx,
-		struct crypto_blkcipher *key,
+		struct crypto_skcipher *key,
 		int direction,
 		u32 seqnum, unsigned char *cksum, unsigned char *buf);
 
@@ -320,12 +320,12 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset,
 
 int
 krb5_rc4_setup_seq_key(struct krb5_ctx *kctx,
-		       struct crypto_blkcipher *cipher,
+		       struct crypto_skcipher *cipher,
 		       unsigned char *cksum);
 
 int
 krb5_rc4_setup_enc_key(struct krb5_ctx *kctx,
-		       struct crypto_blkcipher *cipher,
+		       struct crypto_skcipher *cipher,
 		       s32 seqnum);
 void
 gss_krb5_make_confounder(char *p, u32 conflen);
diff --git a/include/linux/swait.h b/include/linux/swait.h
new file mode 100644
index 000000000000..c1f9c62a8a50
--- /dev/null
+++ b/include/linux/swait.h
@@ -0,0 +1,172 @@
+#ifndef _LINUX_SWAIT_H
+#define _LINUX_SWAIT_H
+
+#include <linux/list.h>
+#include <linux/stddef.h>
+#include <linux/spinlock.h>
+#include <asm/current.h>
+
+/*
+ * Simple wait queues
+ *
+ * While these are very similar to the other/complex wait queues (wait.h) the
+ * most important difference is that the simple waitqueue allows for
+ * deterministic behaviour -- IOW it has strictly bounded IRQ and lock hold
+ * times.
+ *
+ * In order to make this so, we had to drop a fair number of features of the
+ * other waitqueue code; notably:
+ *
+ *  - mixing INTERRUPTIBLE and UNINTERRUPTIBLE sleeps on the same waitqueue;
+ *    all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right
+ *    sleeper state.
+ *
+ *  - the exclusive mode; because this requires preserving the list order
+ *    and this is hard.
+ *
+ *  - custom wake functions; because you cannot give any guarantees about
+ *    random code.
+ *
+ * As a side effect of this; the data structures are slimmer.
+ *
+ * One would recommend using this wait queue where possible.
+ */
+
+struct task_struct;
+
+struct swait_queue_head {
+	raw_spinlock_t		lock;
+	struct list_head	task_list;
+};
+
+struct swait_queue {
+	struct task_struct	*task;
+	struct list_head	task_list;
+};
+
+#define __SWAITQUEUE_INITIALIZER(name) {				\
+	.task		= current,					\
+	.task_list	= LIST_HEAD_INIT((name).task_list),		\
+}
+
+#define DECLARE_SWAITQUEUE(name)					\
+	struct swait_queue name = __SWAITQUEUE_INITIALIZER(name)
+
+#define __SWAIT_QUEUE_HEAD_INITIALIZER(name) {				\
+	.lock		= __RAW_SPIN_LOCK_UNLOCKED(name.lock),		\
+	.task_list	= LIST_HEAD_INIT((name).task_list),		\
+}
+
+#define DECLARE_SWAIT_QUEUE_HEAD(name)					\
+	struct swait_queue_head name = __SWAIT_QUEUE_HEAD_INITIALIZER(name)
+
+extern void __init_swait_queue_head(struct swait_queue_head *q, const char *name,
+				    struct lock_class_key *key);
+
+#define init_swait_queue_head(q)				\
+	do {							\
+		static struct lock_class_key __key;		\
+		__init_swait_queue_head((q), #q, &__key);	\
+	} while (0)
+
+#ifdef CONFIG_LOCKDEP
+# define __SWAIT_QUEUE_HEAD_INIT_ONSTACK(name)			\
+	({ init_swait_queue_head(&name); name; })
+# define DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(name)			\
+	struct swait_queue_head name = __SWAIT_QUEUE_HEAD_INIT_ONSTACK(name)
+#else
+# define DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(name)			\
+	DECLARE_SWAIT_QUEUE_HEAD(name)
+#endif
+
+static inline int swait_active(struct swait_queue_head *q)
+{
+	return !list_empty(&q->task_list);
+}
+
+extern void swake_up(struct swait_queue_head *q);
+extern void swake_up_all(struct swait_queue_head *q);
+extern void swake_up_locked(struct swait_queue_head *q);
+
+extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
+extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state);
+extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state);
+
+extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
+extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
+
+/* as per ___wait_event() but for swait, therefore "exclusive == 0" */
+#define ___swait_event(wq, condition, state, ret, cmd)			\
+({									\
+	struct swait_queue __wait;					\
+	long __ret = ret;						\
+									\
+	INIT_LIST_HEAD(&__wait.task_list);				\
+	for (;;) {							\
+		long __int = prepare_to_swait_event(&wq, &__wait, state);\
+									\
+		if (condition)						\
+			break;						\
+									\
+		if (___wait_is_interruptible(state) && __int) {		\
+			__ret = __int;					\
+			break;						\
+		}							\
+									\
+		cmd;							\
+	}								\
+	finish_swait(&wq, &__wait);					\
+	__ret;								\
+})
+
+#define __swait_event(wq, condition)					\
+	(void)___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0,	\
+			    schedule())
+
+#define swait_event(wq, condition)					\
+do {									\
+	if (condition)							\
+		break;							\
+	__swait_event(wq, condition);					\
+} while (0)
+
+#define __swait_event_timeout(wq, condition, timeout)			\
+	___swait_event(wq, ___wait_cond_timeout(condition),		\
+		      TASK_UNINTERRUPTIBLE, timeout,			\
+		      __ret = schedule_timeout(__ret))
+
+#define swait_event_timeout(wq, condition, timeout)			\
+({									\
+	long __ret = timeout;						\
+	if (!___wait_cond_timeout(condition))				\
+		__ret = __swait_event_timeout(wq, condition, timeout);	\
+	__ret;								\
+})
+
+#define __swait_event_interruptible(wq, condition)			\
+	___swait_event(wq, condition, TASK_INTERRUPTIBLE, 0,		\
+		      schedule())
+
+#define swait_event_interruptible(wq, condition)			\
+({									\
+	int __ret = 0;							\
+	if (!(condition))						\
+		__ret = __swait_event_interruptible(wq, condition);	\
+	__ret;								\
+})
+
+#define __swait_event_interruptible_timeout(wq, condition, timeout)	\
+	___swait_event(wq, ___wait_cond_timeout(condition),		\
+		      TASK_INTERRUPTIBLE, timeout,			\
+		      __ret = schedule_timeout(__ret))
+
+#define swait_event_interruptible_timeout(wq, condition, timeout)	\
+({									\
+	long __ret = timeout;						\
+	if (!___wait_cond_timeout(condition))				\
+		__ret = __swait_event_interruptible_timeout(wq,		\
+						condition, timeout);	\
+	__ret;								\
+})
+
+#endif /* _LINUX_SWAIT_H */
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 97fd4e543846..21f73649a4dc 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -97,6 +97,19 @@ static inline void tick_broadcast_exit(void)
 	tick_broadcast_oneshot_control(TICK_BROADCAST_EXIT);
 }
 
+enum tick_dep_bits {
+	TICK_DEP_BIT_POSIX_TIMER	= 0,
+	TICK_DEP_BIT_PERF_EVENTS	= 1,
+	TICK_DEP_BIT_SCHED		= 2,
+	TICK_DEP_BIT_CLOCK_UNSTABLE	= 3
+};
+
+#define TICK_DEP_MASK_NONE		0
+#define TICK_DEP_MASK_POSIX_TIMER	(1 << TICK_DEP_BIT_POSIX_TIMER)
+#define TICK_DEP_MASK_PERF_EVENTS	(1 << TICK_DEP_BIT_PERF_EVENTS)
+#define TICK_DEP_MASK_SCHED		(1 << TICK_DEP_BIT_SCHED)
+#define TICK_DEP_MASK_CLOCK_UNSTABLE	(1 << TICK_DEP_BIT_CLOCK_UNSTABLE)
+
 #ifdef CONFIG_NO_HZ_COMMON
 extern int tick_nohz_enabled;
 extern int tick_nohz_tick_stopped(void);
@@ -154,9 +167,73 @@ static inline int housekeeping_any_cpu(void)
 	return cpumask_any_and(housekeeping_mask, cpu_online_mask);
 }
 
-extern void tick_nohz_full_kick(void);
+extern void tick_nohz_dep_set(enum tick_dep_bits bit);
+extern void tick_nohz_dep_clear(enum tick_dep_bits bit);
+extern void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit);
+extern void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit);
+extern void tick_nohz_dep_set_task(struct task_struct *tsk,
+				   enum tick_dep_bits bit);
+extern void tick_nohz_dep_clear_task(struct task_struct *tsk,
+				     enum tick_dep_bits bit);
+extern void tick_nohz_dep_set_signal(struct signal_struct *signal,
+				     enum tick_dep_bits bit);
+extern void tick_nohz_dep_clear_signal(struct signal_struct *signal,
+				       enum tick_dep_bits bit);
+
+/*
+ * The below are tick_nohz_[set,clear]_dep() wrappers that optimize off-cases
+ * on top of static keys.
+ */
+static inline void tick_dep_set(enum tick_dep_bits bit)
+{
+	if (tick_nohz_full_enabled())
+		tick_nohz_dep_set(bit);
+}
+
+static inline void tick_dep_clear(enum tick_dep_bits bit)
+{
+	if (tick_nohz_full_enabled())
+		tick_nohz_dep_clear(bit);
+}
+
+static inline void tick_dep_set_cpu(int cpu, enum tick_dep_bits bit)
+{
+	if (tick_nohz_full_cpu(cpu))
+		tick_nohz_dep_set_cpu(cpu, bit);
+}
+
+static inline void tick_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
+{
+	if (tick_nohz_full_cpu(cpu))
+		tick_nohz_dep_clear_cpu(cpu, bit);
+}
+
+static inline void tick_dep_set_task(struct task_struct *tsk,
+				     enum tick_dep_bits bit)
+{
+	if (tick_nohz_full_enabled())
+		tick_nohz_dep_set_task(tsk, bit);
+}
+static inline void tick_dep_clear_task(struct task_struct *tsk,
+				       enum tick_dep_bits bit)
+{
+	if (tick_nohz_full_enabled())
+		tick_nohz_dep_clear_task(tsk, bit);
+}
+static inline void tick_dep_set_signal(struct signal_struct *signal,
+				       enum tick_dep_bits bit)
+{
+	if (tick_nohz_full_enabled())
+		tick_nohz_dep_set_signal(signal, bit);
+}
+static inline void tick_dep_clear_signal(struct signal_struct *signal,
+					 enum tick_dep_bits bit)
+{
+	if (tick_nohz_full_enabled())
+		tick_nohz_dep_clear_signal(signal, bit);
+}
+
 extern void tick_nohz_full_kick_cpu(int cpu);
-extern void tick_nohz_full_kick_all(void);
 extern void __tick_nohz_task_switch(void);
 #else
 static inline int housekeeping_any_cpu(void)
@@ -166,9 +243,21 @@ static inline int housekeeping_any_cpu(void)
 static inline bool tick_nohz_full_enabled(void) { return false; }
 static inline bool tick_nohz_full_cpu(int cpu) { return false; }
 static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { }
+
+static inline void tick_dep_set(enum tick_dep_bits bit) { }
+static inline void tick_dep_clear(enum tick_dep_bits bit) { }
+static inline void tick_dep_set_cpu(int cpu, enum tick_dep_bits bit) { }
+static inline void tick_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { }
+static inline void tick_dep_set_task(struct task_struct *tsk,
+				     enum tick_dep_bits bit) { }
+static inline void tick_dep_clear_task(struct task_struct *tsk,
+				       enum tick_dep_bits bit) { }
+static inline void tick_dep_set_signal(struct signal_struct *signal,
+				       enum tick_dep_bits bit) { }
+static inline void tick_dep_clear_signal(struct signal_struct *signal,
+					 enum tick_dep_bits bit) { }
+
 static inline void tick_nohz_full_kick_cpu(int cpu) { }
-static inline void tick_nohz_full_kick(void) { }
-static inline void tick_nohz_full_kick_all(void) { }
 static inline void __tick_nohz_task_switch(void) { }
 #endif
 
diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index 25247220b4b7..e88005459035 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -50,6 +50,7 @@ struct tk_read_base {
  * @offs_tai:		Offset clock monotonic -> clock tai
  * @tai_offset:		The current UTC to TAI offset in seconds
  * @clock_was_set_seq:	The sequence number of clock was set events
+ * @cs_was_changed_seq:	The sequence number of clocksource change events
  * @next_leap_ktime:	CLOCK_MONOTONIC time value of a pending leap-second
  * @raw_time:		Monotonic raw base time in timespec64 format
  * @cycle_interval:	Number of clock cycles in one NTP interval
@@ -91,6 +92,7 @@ struct timekeeper {
 	ktime_t			offs_tai;
 	s32			tai_offset;
 	unsigned int		clock_was_set_seq;
+	u8			cs_was_changed_seq;
 	ktime_t			next_leap_ktime;
 	struct timespec64	raw_time;
 
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index ec89d846324c..96f37bee3bc1 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -267,6 +267,64 @@ extern void ktime_get_raw_and_real_ts64(struct timespec64 *ts_raw,
 				        struct timespec64 *ts_real);
 
 /*
+ * struct system_time_snapshot - simultaneous raw/real time capture with
+ *	counter value
+ * @cycles:	Clocksource counter value to produce the system times
+ * @real:	Realtime system time
+ * @raw:	Monotonic raw system time
+ * @clock_was_set_seq:	The sequence number of clock was set events
+ * @cs_was_changed_seq:	The sequence number of clocksource change events
+ */
+struct system_time_snapshot {
+	cycle_t		cycles;
+	ktime_t		real;
+	ktime_t		raw;
+	unsigned int	clock_was_set_seq;
+	u8		cs_was_changed_seq;
+};
+
+/*
+ * struct system_device_crosststamp - system/device cross-timestamp
+ *	(syncronized capture)
+ * @device:		Device time
+ * @sys_realtime:	Realtime simultaneous with device time
+ * @sys_monoraw:	Monotonic raw simultaneous with device time
+ */
+struct system_device_crosststamp {
+	ktime_t device;
+	ktime_t sys_realtime;
+	ktime_t sys_monoraw;
+};
+
+/*
+ * struct system_counterval_t - system counter value with the pointer to the
+ *	corresponding clocksource
+ * @cycles:	System counter value
+ * @cs:		Clocksource corresponding to system counter value. Used by
+ *	timekeeping code to verify comparibility of two cycle values
+ */
+struct system_counterval_t {
+	cycle_t			cycles;
+	struct clocksource	*cs;
+};
+
+/*
+ * Get cross timestamp between system clock and device clock
+ */
+extern int get_device_system_crosststamp(
+			int (*get_time_fn)(ktime_t *device_time,
+				struct system_counterval_t *system_counterval,
+				void *ctx),
+			void *ctx,
+			struct system_time_snapshot *history,
+			struct system_device_crosststamp *xtstamp);
+
+/*
+ * Simultaneously snapshot realtime and monotonic raw clocks
+ */
+extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot);
+
+/*
  * Persistent clock related interfaces
  */
 extern int persistent_clock_is_local;
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 429fdfc3baf5..705df7db4482 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -15,16 +15,6 @@ struct tracer;
 struct dentry;
 struct bpf_prog;
 
-struct trace_print_flags {
-	unsigned long		mask;
-	const char		*name;
-};
-
-struct trace_print_flags_u64 {
-	unsigned long long	mask;
-	const char		*name;
-};
-
 const char *trace_print_flags_seq(struct trace_seq *p, const char *delim,
 				  unsigned long flags,
 				  const struct trace_print_flags *flag_array);
@@ -568,6 +558,8 @@ enum {
 	FILTER_DYN_STRING,
 	FILTER_PTR_STRING,
 	FILTER_TRACE_FN,
+	FILTER_COMM,
+	FILTER_CPU,
 };
 
 extern int trace_event_raw_init(struct trace_event_call *call);
diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h
index e1ee97c713bf..4ac89acb6136 100644
--- a/include/linux/tracepoint-defs.h
+++ b/include/linux/tracepoint-defs.h
@@ -3,13 +3,23 @@
 
 /*
  * File can be included directly by headers who only want to access
- * tracepoint->key to guard out of line trace calls. Otherwise
- * linux/tracepoint.h should be used.
+ * tracepoint->key to guard out of line trace calls, or the definition of
+ * trace_print_flags{_u64}. Otherwise linux/tracepoint.h should be used.
  */
 
 #include <linux/atomic.h>
 #include <linux/static_key.h>
 
+struct trace_print_flags {
+	unsigned long		mask;
+	const char		*name;
+};
+
+struct trace_print_flags_u64 {
+	unsigned long long	mask;
+	const char		*name;
+};
+
 struct tracepoint_func {
 	void *func;
 	void *data;
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index acd522a91539..be586c632a0c 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -14,8 +14,10 @@
  * See the file COPYING for more details.
  */
 
+#include <linux/smp.h>
 #include <linux/errno.h>
 #include <linux/types.h>
+#include <linux/cpumask.h>
 #include <linux/rcupdate.h>
 #include <linux/tracepoint-defs.h>
 
@@ -338,15 +340,19 @@ extern void syscall_unregfunc(void);
  * "void *__data, proto" as the callback prototype.
  */
 #define DECLARE_TRACE_NOARGS(name)					\
-		__DECLARE_TRACE(name, void, , 1, void *__data, __data)
+	__DECLARE_TRACE(name, void, ,					\
+			cpu_online(raw_smp_processor_id()),		\
+			void *__data, __data)
 
 #define DECLARE_TRACE(name, proto, args)				\
-		__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), 1,	\
-				PARAMS(void *__data, proto),		\
-				PARAMS(__data, args))
+	__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args),		\
+			cpu_online(raw_smp_processor_id()),		\
+			PARAMS(void *__data, proto),			\
+			PARAMS(__data, args))
 
 #define DECLARE_TRACE_CONDITION(name, proto, args, cond)		\
-	__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), PARAMS(cond), \
+	__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args),		\
+			cpu_online(raw_smp_processor_id()) && (PARAMS(cond)), \
 			PARAMS(void *__data, proto),			\
 			PARAMS(__data, args))
 
diff --git a/include/linux/ucs2_string.h b/include/linux/ucs2_string.h
index cbb20afdbc01..bb679b48f408 100644
--- a/include/linux/ucs2_string.h
+++ b/include/linux/ucs2_string.h
@@ -11,4 +11,8 @@ unsigned long ucs2_strlen(const ucs2_char_t *s);
 unsigned long ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength);
 int ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len);
 
+unsigned long ucs2_utf8size(const ucs2_char_t *src);
+unsigned long ucs2_as_utf8(u8 *dest, const ucs2_char_t *src,
+			   unsigned long maxlength);
+
 #endif /* _LINUX_UCS2_STRING_H_ */
diff --git a/include/linux/wait.h b/include/linux/wait.h
index ae71a769b89e..27d7a0ab5da3 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -338,7 +338,7 @@ do {									\
 			    schedule(); try_to_freeze())
 
 /**
- * wait_event - sleep (or freeze) until a condition gets true
+ * wait_event_freezable - sleep (or freeze) until a condition gets true
  * @wq: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  *
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 0e32bc71245e..ca73c503b92a 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -311,6 +311,7 @@ enum {
 
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
+	__WQ_LEGACY		= 1 << 18, /* internal: create*_workqueue() */
 
 	WQ_MAX_ACTIVE		= 512,	  /* I like 512, better ideas? */
 	WQ_MAX_UNBOUND_PER_CPU	= 4,	  /* 4 * #cpus for unbound wq */
@@ -411,12 +412,12 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
 	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
 
 #define create_workqueue(name)						\
-	alloc_workqueue("%s", WQ_MEM_RECLAIM, 1, (name))
+	alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name))
 #define create_freezable_workqueue(name)				\
-	alloc_workqueue("%s", WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, \
-			1, (name))
+	alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND |	\
+			WQ_MEM_RECLAIM, 1, (name))
 #define create_singlethread_workqueue(name)				\
-	alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, name)
+	alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name)
 
 extern void destroy_workqueue(struct workqueue_struct *wq);
 
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index b333c945e571..d0b5ca5d4e08 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -198,6 +198,7 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
 void wbc_detach_inode(struct writeback_control *wbc);
 void wbc_account_io(struct writeback_control *wbc, struct page *page,
 		    size_t bytes);
+void cgroup_writeback_umount(void);
 
 /**
  * inode_attach_wb - associate an inode with its wb
@@ -301,6 +302,10 @@ static inline void wbc_account_io(struct writeback_control *wbc,
 {
 }
 
+static inline void cgroup_writeback_umount(void)
+{
+}
+
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 
 /*
diff --git a/include/media/media-device.h b/include/media/media-device.h
index d3855898c3fc..df74cfa7da4a 100644
--- a/include/media/media-device.h
+++ b/include/media/media-device.h
@@ -265,9 +265,29 @@ struct ida;
 struct device;
 
 /**
+ * struct media_entity_notify - Media Entity Notify
+ *
+ * @list: List head
+ * @notify_data: Input data to invoke the callback
+ * @notify: Callback function pointer
+ *
+ * Drivers may register a callback to take action when
+ * new entities get registered with the media device.
+ */
+struct media_entity_notify {
+	struct list_head list;
+	void *notify_data;
+	void (*notify)(struct media_entity *entity, void *notify_data);
+};
+
+/**
  * struct media_device - Media device
  * @dev:	Parent device
  * @devnode:	Media device node
+ * @driver_name: Optional device driver name. If not set, calls to
+ *		%MEDIA_IOC_DEVICE_INFO will return dev->driver->name.
+ *		This is needed for USB drivers for example, as otherwise
+ *		they'll all appear as if the driver name was "usb".
  * @model:	Device model name
  * @serial:	Device serial number (optional)
  * @bus_info:	Unique and stable device location identifier
@@ -283,8 +303,16 @@ struct device;
  * @interfaces:	List of registered interfaces
  * @pads:	List of registered pads
  * @links:	List of registered links
+ * @entity_notify: List of registered entity_notify callbacks
  * @lock:	Entities list lock
  * @graph_mutex: Entities graph operation lock
+ * @pm_count_walk: Graph walk for power state walk. Access serialised using
+ *		   graph_mutex.
+ *
+ * @source_priv: Driver Private data for enable/disable source handlers
+ * @enable_source: Enable Source Handler function pointer
+ * @disable_source: Disable Source Handler function pointer
+ *
  * @link_notify: Link state change notification callback
  *
  * This structure represents an abstract high-level media device. It allows easy
@@ -296,6 +324,26 @@ struct device;
  *
  * @model is a descriptive model name exported through sysfs. It doesn't have to
  * be unique.
+ *
+ * @enable_source is a handler to find source entity for the
+ * sink entity  and activate the link between them if source
+ * entity is free. Drivers should call this handler before
+ * accessing the source.
+ *
+ * @disable_source is a handler to find source entity for the
+ * sink entity  and deactivate the link between them. Drivers
+ * should call this handler to release the source.
+ *
+ * Note: Bridge driver is expected to implement and set the
+ * handler when media_device is registered or when
+ * bridge driver finds the media_device during probe.
+ * Bridge driver sets source_priv with information
+ * necessary to run enable/disable source handlers.
+ *
+ * Use-case: find tuner entity connected to the decoder
+ * entity and check if it is available, and activate the
+ * the link between them from enable_source and deactivate
+ * from disable_source.
  */
 struct media_device {
 	/* dev->driver_data points to this struct. */
@@ -303,6 +351,7 @@ struct media_device {
 	struct media_devnode devnode;
 
 	char model[32];
+	char driver_name[32];
 	char serial[40];
 	char bus_info[32];
 	u32 hw_revision;
@@ -319,15 +368,28 @@ struct media_device {
 	struct list_head pads;
 	struct list_head links;
 
+	/* notify callback list invoked when a new entity is registered */
+	struct list_head entity_notify;
+
 	/* Protects the graph objects creation/removal */
 	spinlock_t lock;
 	/* Serializes graph operations. */
 	struct mutex graph_mutex;
+	struct media_entity_graph pm_count_walk;
+
+	void *source_priv;
+	int (*enable_source)(struct media_entity *entity,
+			     struct media_pipeline *pipe);
+	void (*disable_source)(struct media_entity *entity);
 
 	int (*link_notify)(struct media_link *link, u32 flags,
 			   unsigned int notification);
 };
 
+/* We don't need to include pci.h or usb.h here */
+struct pci_dev;
+struct usb_device;
+
 #ifdef CONFIG_MEDIA_CONTROLLER
 
 /* Supported link_notify @notification values. */
@@ -498,6 +560,31 @@ int __must_check media_device_register_entity(struct media_device *mdev,
 void media_device_unregister_entity(struct media_entity *entity);
 
 /**
+ * media_device_register_entity_notify() - Registers a media entity_notify
+ *					   callback
+ *
+ * @mdev:      The media device
+ * @nptr:      The media_entity_notify
+ *
+ * Note: When a new entity is registered, all the registered
+ * media_entity_notify callbacks are invoked.
+ */
+
+int __must_check media_device_register_entity_notify(struct media_device *mdev,
+					struct media_entity_notify *nptr);
+
+/**
+ * media_device_unregister_entity_notify() - Unregister a media entity notify
+ *					     callback
+ *
+ * @mdev:      The media device
+ * @nptr:      The media_entity_notify
+ *
+ */
+void media_device_unregister_entity_notify(struct media_device *mdev,
+					struct media_entity_notify *nptr);
+
+/**
  * media_device_get_devres() -	get media device as device resource
  *				creates if one doesn't exist
  *
@@ -536,6 +623,39 @@ struct media_device *media_device_find_devres(struct device *dev);
 /* Iterate over all links. */
 #define media_device_for_each_link(link, mdev)			\
 	list_for_each_entry(link, &(mdev)->links, graph_obj.list)
+
+/**
+ * media_device_pci_init() - create and initialize a
+ *	struct &media_device from a PCI device.
+ *
+ * @mdev:	pointer to struct &media_device
+ * @pci_dev:	pointer to struct pci_dev
+ * @name:	media device name. If %NULL, the routine will use the default
+ *		name for the pci device, given by pci_name() macro.
+ */
+void media_device_pci_init(struct media_device *mdev,
+			   struct pci_dev *pci_dev,
+			   const char *name);
+/**
+ * __media_device_usb_init() - create and initialize a
+ *	struct &media_device from a PCI device.
+ *
+ * @mdev:	pointer to struct &media_device
+ * @udev:	pointer to struct usb_device
+ * @board_name:	media device name. If %NULL, the routine will use the usb
+ *		product name, if available.
+ * @driver_name: name of the driver. if %NULL, the routine will use the name
+ *		given by udev->dev->driver->name, with is usually the wrong
+ *		thing to do.
+ *
+ * NOTE: It is better to call media_device_usb_init() instead, as
+ * such macro fills driver_name with %KBUILD_MODNAME.
+ */
+void __media_device_usb_init(struct media_device *mdev,
+			     struct usb_device *udev,
+			     const char *board_name,
+			     const char *driver_name);
+
 #else
 static inline int media_device_register(struct media_device *mdev)
 {
@@ -552,6 +672,17 @@ static inline int media_device_register_entity(struct media_device *mdev,
 static inline void media_device_unregister_entity(struct media_entity *entity)
 {
 }
+static inline int media_device_register_entity_notify(
+					struct media_device *mdev,
+					struct media_entity_notify *nptr)
+{
+	return 0;
+}
+static inline void media_device_unregister_entity_notify(
+					struct media_device *mdev,
+					struct media_entity_notify *nptr)
+{
+}
 static inline struct media_device *media_device_get_devres(struct device *dev)
 {
 	return NULL;
@@ -560,5 +691,23 @@ static inline struct media_device *media_device_find_devres(struct device *dev)
 {
 	return NULL;
 }
+
+static inline void media_device_pci_init(struct media_device *mdev,
+					 struct pci_dev *pci_dev,
+					 char *name)
+{
+}
+
+static inline void __media_device_usb_init(struct media_device *mdev,
+					   struct usb_device *udev,
+					   char *board_name,
+					   char *driver_name)
+{
+}
+
 #endif /* CONFIG_MEDIA_CONTROLLER */
+
+#define media_device_usb_init(mdev, udev, name) \
+	__media_device_usb_init(mdev, udev, name, KBUILD_MODNAME)
+
 #endif
diff --git a/include/media/media-entity.h b/include/media/media-entity.h
index fe485d367985..6dc9e4e8cbd4 100644
--- a/include/media/media-entity.h
+++ b/include/media/media-entity.h
@@ -24,6 +24,7 @@
 #define _MEDIA_ENTITY_H
 
 #include <linux/bitmap.h>
+#include <linux/bug.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/media.h>
@@ -832,6 +833,16 @@ media_entity_graph_walk_next(struct media_entity_graph *graph);
  */
 __must_check int media_entity_pipeline_start(struct media_entity *entity,
 					     struct media_pipeline *pipe);
+/**
+ * __media_entity_pipeline_start - Mark a pipeline as streaming
+ *
+ * @entity: Starting entity
+ * @pipe: Media pipeline to be assigned to all entities in the pipeline.
+ *
+ * Note: This is the non-locking version of media_entity_pipeline_start()
+ */
+__must_check int __media_entity_pipeline_start(struct media_entity *entity,
+					       struct media_pipeline *pipe);
 
 /**
  * media_entity_pipeline_stop - Mark a pipeline as not streaming
@@ -848,6 +859,15 @@ __must_check int media_entity_pipeline_start(struct media_entity *entity,
 void media_entity_pipeline_stop(struct media_entity *entity);
 
 /**
+ * __media_entity_pipeline_stop - Mark a pipeline as not streaming
+ *
+ * @entity: Starting entity
+ *
+ * Note: This is the non-locking version of media_entity_pipeline_stop()
+ */
+void __media_entity_pipeline_stop(struct media_entity *entity);
+
+/**
  * media_devnode_create() - creates and initializes a device node interface
  *
  * @mdev:	pointer to struct &media_device
diff --git a/include/media/rc-core.h b/include/media/rc-core.h
index f6494709e230..0f77b3dffb37 100644
--- a/include/media/rc-core.h
+++ b/include/media/rc-core.h
@@ -60,6 +60,7 @@ enum rc_filter_type {
 /**
  * struct rc_dev - represents a remote control device
  * @dev: driver model's view of this device
+ * @initialized: 1 if the device init has completed, 0 otherwise
  * @sysfs_groups: sysfs attribute groups
  * @input_name: name of the input child device
  * @input_phys: physical path to the input child device
@@ -121,6 +122,7 @@ enum rc_filter_type {
  */
 struct rc_dev {
 	struct device			dev;
+	atomic_t			initialized;
 	const struct attribute_group	*sysfs_groups[5];
 	const char			*input_name;
 	const char			*input_phys;
diff --git a/include/media/tuner.h b/include/media/tuner.h
index e5321fda5489..b3edc14e763f 100644
--- a/include/media/tuner.h
+++ b/include/media/tuner.h
@@ -20,14 +20,7 @@
 #ifdef __KERNEL__
 
 #include <linux/videodev2.h>
-
-/* Tuner PADs */
-/* FIXME: is this the right place for it? */
-enum tuner_pad_index {
-	TUNER_PAD_RF_INPUT,
-	TUNER_PAD_IF_OUTPUT,
-	TUNER_NUM_PADS
-};
+#include <media/v4l2-mc.h>
 
 #define ADDR_UNSET (255)
 
diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h
index da6fe9802fee..0bc9b35b8f3e 100644
--- a/include/media/v4l2-ctrls.h
+++ b/include/media/v4l2-ctrls.h
@@ -535,18 +535,6 @@ struct v4l2_ctrl *v4l2_ctrl_new_int_menu(struct v4l2_ctrl_handler *hdl,
 			u32 id, u8 max, u8 def, const s64 *qmenu_int);
 
 /**
- * v4l2_ctrl_add_ctrl() - Add a control from another handler to this handler.
- * @hdl:	The control handler.
- * @ctrl:	The control to add.
- *
- * It will return NULL if it was unable to add the control reference.
- * If the control already belonged to the handler, then it will do
- * nothing and just return @ctrl.
- */
-struct v4l2_ctrl *v4l2_ctrl_add_ctrl(struct v4l2_ctrl_handler *hdl,
-					  struct v4l2_ctrl *ctrl);
-
-/**
  * v4l2_ctrl_add_handler() - Add all controls from handler @add to
  * handler @hdl.
  * @hdl:	The control handler.
diff --git a/include/media/v4l2-dev.h b/include/media/v4l2-dev.h
index eeabf20e87a6..76056ab5c5bd 100644
--- a/include/media/v4l2-dev.h
+++ b/include/media/v4l2-dev.h
@@ -87,6 +87,7 @@ struct video_device
 #if defined(CONFIG_MEDIA_CONTROLLER)
 	struct media_entity entity;
 	struct media_intf_devnode *intf_devnode;
+	struct media_pipeline pipe;
 #endif
 	/* device ops */
 	const struct v4l2_file_operations *fops;
diff --git a/include/media/v4l2-mc.h b/include/media/v4l2-mc.h
new file mode 100644
index 000000000000..98a938aabdfb
--- /dev/null
+++ b/include/media/v4l2-mc.h
@@ -0,0 +1,243 @@
+/*
+ * v4l2-mc.h - Media Controller V4L2 types and prototypes
+ *
+ * Copyright (C) 2016 Mauro Carvalho Chehab <mchehab@osg.samsung.com>
+ * Copyright (C) 2006-2010 Nokia Corporation
+ * Copyright (c) 2016 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _V4L2_MC_H
+#define _V4L2_MC_H
+
+#include <media/media-device.h>
+#include <media/v4l2-dev.h>
+#include <linux/types.h>
+
+/**
+ * enum tuner_pad_index - tuner pad index for MEDIA_ENT_F_TUNER
+ *
+ * @TUNER_PAD_RF_INPUT:	Radiofrequency (RF) sink pad, usually linked to a
+ *			RF connector entity.
+ * @TUNER_PAD_OUTPUT:	Tuner video output source pad. Contains the video
+ *			chrominance and luminance or the hole bandwidth
+ *			of the signal converted to an Intermediate Frequency
+ *			(IF) or to baseband (on zero-IF tuners).
+ * @TUNER_PAD_AUD_OUT:	Tuner audio output source pad. Tuners used to decode
+ *			analog TV signals have an extra pad for audio output.
+ *			Old tuners use an analog stage with a saw filter for
+ *			the audio IF frequency. The output of the pad is, in
+ *			this case, the audio IF, with should be decoded either
+ *			by the bridge chipset (that's the case of cx2388x
+ *			chipsets) or may require an external IF sound
+ *			processor, like msp34xx. On modern silicon tuners,
+ *			the audio IF decoder is usually incorporated at the
+ *			tuner. On such case, the output of this pad is an
+ *			audio sampled data.
+ * @TUNER_NUM_PADS:	Number of pads of the tuner.
+ */
+enum tuner_pad_index {
+	TUNER_PAD_RF_INPUT,
+	TUNER_PAD_OUTPUT,
+	TUNER_PAD_AUD_OUT,
+	TUNER_NUM_PADS
+};
+
+/**
+ * enum if_vid_dec_index - video IF-PLL pad index for
+ *			   MEDIA_ENT_F_IF_VID_DECODER
+ *
+ * @IF_VID_DEC_PAD_IF_INPUT:	video Intermediate Frequency (IF) sink pad
+ * @IF_VID_DEC_PAD_OUT:		IF-PLL video output source pad. Contains the
+ *				video chrominance and luminance IF signals.
+ * @IF_VID_DEC_PAD_NUM_PADS:	Number of pads of the video IF-PLL.
+ */
+enum if_vid_dec_pad_index {
+	IF_VID_DEC_PAD_IF_INPUT,
+	IF_VID_DEC_PAD_OUT,
+	IF_VID_DEC_PAD_NUM_PADS
+};
+
+/**
+ * enum if_aud_dec_index - audio/sound IF-PLL pad index for
+ *			   MEDIA_ENT_F_IF_AUD_DECODER
+ *
+ * @IF_AUD_DEC_PAD_IF_INPUT:	audio Intermediate Frequency (IF) sink pad
+ * @IF_AUD_DEC_PAD_OUT:		IF-PLL audio output source pad. Contains the
+ *				audio sampled stream data, usually connected
+ *				to the bridge bus via an Inter-IC Sound (I2S)
+ *				bus.
+ * @IF_AUD_DEC_PAD_NUM_PADS:	Number of pads of the audio IF-PLL.
+ */
+enum if_aud_dec_pad_index {
+	IF_AUD_DEC_PAD_IF_INPUT,
+	IF_AUD_DEC_PAD_OUT,
+	IF_AUD_DEC_PAD_NUM_PADS
+};
+
+/**
+ * enum demod_pad_index - analog TV pad index for MEDIA_ENT_F_ATV_DECODER
+ *
+ * @DEMOD_PAD_IF_INPUT:	IF input sink pad.
+ * @DEMOD_PAD_VID_OUT:	Video output source pad.
+ * @DEMOD_PAD_VBI_OUT:	Vertical Blank Interface (VBI) output source pad.
+ * @DEMOD_PAD_AUDIO_OUT: Audio output source pad.
+ * @DEMOD_NUM_PADS:	Maximum number of output pads.
+ */
+enum demod_pad_index {
+	DEMOD_PAD_IF_INPUT,
+	DEMOD_PAD_VID_OUT,
+	DEMOD_PAD_VBI_OUT,
+	DEMOD_PAD_AUDIO_OUT,
+	DEMOD_NUM_PADS
+};
+
+/* We don't need to include pci.h or usb.h here */
+struct pci_dev;
+struct usb_device;
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+/**
+ * v4l2_mc_create_media_graph() - create Media Controller links at the graph.
+ *
+ * @mdev:	pointer to the &media_device struct.
+ *
+ * Add links between the entities commonly found on PC customer's hardware at
+ * the V4L2 side: camera sensors, audio and video PLL-IF decoders, tuners,
+ * analog TV decoder and I/O entities (video, VBI and Software Defined Radio).
+ * NOTE: webcams are modelled on a very simple way: the sensor is
+ * connected directly to the I/O entity. All dirty details, like
+ * scaler and crop HW are hidden. While such mapping is enough for v4l2
+ * interface centric PC-consumer's hardware, V4L2 subdev centric camera
+ * hardware should not use this routine, as it will not build the right graph.
+ */
+int v4l2_mc_create_media_graph(struct media_device *mdev);
+
+/**
+ * v4l_enable_media_source() -	Hold media source for exclusive use
+ *				if free
+ *
+ * @vdev:	pointer to struct video_device
+ *
+ * This interface calls enable_source handler to determine if
+ * media source is free for use. The enable_source handler is
+ * responsible for checking is the media source is free and
+ * start a pipeline between the media source and the media
+ * entity associated with the video device. This interface
+ * should be called from v4l2-core and dvb-core interfaces
+ * that change the source configuration.
+ *
+ * Return: returns zero on success or a negative error code.
+ */
+int v4l_enable_media_source(struct video_device *vdev);
+
+/**
+ * v4l_disable_media_source() -	Release media source
+ *
+ * @vdev:	pointer to struct video_device
+ *
+ * This interface calls disable_source handler to release
+ * the media source. The disable_source handler stops the
+ * active media pipeline between the media source and the
+ * media entity associated with the video device.
+ *
+ * Return: returns zero on success or a negative error code.
+ */
+void v4l_disable_media_source(struct video_device *vdev);
+
+/*
+ * v4l_vb2q_enable_media_tuner -  Hold media source for exclusive use
+ *				  if free.
+ * @q - pointer to struct vb2_queue
+ *
+ * Wrapper for v4l_enable_media_source(). This function should
+ * be called from v4l2-core to enable the media source with
+ * pointer to struct vb2_queue as the input argument. Some
+ * v4l2-core interfaces don't have access to video device and
+ * this interface finds the struct video_device for the q and
+ * calls v4l_enable_media_source().
+ */
+int v4l_vb2q_enable_media_source(struct vb2_queue *q);
+
+
+/**
+ * v4l2_pipeline_pm_use - Update the use count of an entity
+ * @entity: The entity
+ * @use: Use (1) or stop using (0) the entity
+ *
+ * Update the use count of all entities in the pipeline and power entities on or
+ * off accordingly.
+ *
+ * This function is intended to be called in video node open (use ==
+ * 1) and release (use == 0). It uses struct media_entity.use_count to
+ * track the power status. The use of this function should be paired
+ * with v4l2_pipeline_link_notify().
+ *
+ * Return 0 on success or a negative error code on failure. Powering entities
+ * off is assumed to never fail. No failure can occur when the use parameter is
+ * set to 0.
+ */
+int v4l2_pipeline_pm_use(struct media_entity *entity, int use);
+
+
+/**
+ * v4l2_pipeline_link_notify - Link management notification callback
+ * @link: The link
+ * @flags: New link flags that will be applied
+ * @notification: The link's state change notification type (MEDIA_DEV_NOTIFY_*)
+ *
+ * React to link management on powered pipelines by updating the use count of
+ * all entities in the source and sink sides of the link. Entities are powered
+ * on or off accordingly. The use of this function should be paired
+ * with v4l2_pipeline_pm_use().
+ *
+ * Return 0 on success or a negative error code on failure. Powering entities
+ * off is assumed to never fail. This function will not fail for disconnection
+ * events.
+ */
+int v4l2_pipeline_link_notify(struct media_link *link, u32 flags,
+			      unsigned int notification);
+
+#else /* CONFIG_MEDIA_CONTROLLER */
+
+static inline int v4l2_mc_create_media_graph(struct media_device *mdev)
+{
+	return 0;
+}
+
+static inline int v4l_enable_media_source(struct video_device *vdev)
+{
+	return 0;
+}
+
+static inline void v4l_disable_media_source(struct video_device *vdev)
+{
+}
+
+static inline int v4l_vb2q_enable_media_source(struct vb2_queue *q)
+{
+	return 0;
+}
+
+static inline int v4l2_pipeline_pm_use(struct media_entity *entity, int use)
+{
+	return 0;
+}
+
+static inline int v4l2_pipeline_link_notify(struct media_link *link, u32 flags,
+					    unsigned int notification)
+{
+	return 0;
+}
+
+#endif /* CONFIG_MEDIA_CONTROLLER */
+#endif /* _V4L2_MC_H */
diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index b273cf9ac047..11e2dfec0198 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -179,6 +179,8 @@ struct v4l2_subdev_io_pin_config {
  *		     for it to be warned when the value of a control changes.
  *
  * @unsubscribe_event: remove event subscription from the control framework.
+ *
+ * @registered_async: the subdevice has been registered async.
  */
 struct v4l2_subdev_core_ops {
 	int (*log_status)(struct v4l2_subdev *sd);
@@ -211,6 +213,7 @@ struct v4l2_subdev_core_ops {
 			       struct v4l2_event_subscription *sub);
 	int (*unsubscribe_event)(struct v4l2_subdev *sd, struct v4l2_fh *fh,
 				 struct v4l2_event_subscription *sub);
+	int (*registered_async)(struct v4l2_subdev *sd);
 };
 
 /**
diff --git a/include/media/videobuf2-dvb.h b/include/media/videobuf2-dvb.h
index 5b64c9eac2c9..87b559024b4a 100644
--- a/include/media/videobuf2-dvb.h
+++ b/include/media/videobuf2-dvb.h
@@ -8,6 +8,10 @@
 #include <dvb_frontend.h>
 
 #include <media/videobuf2-v4l2.h>
+
+/* We don't actually need to include media-device.h here */
+struct media_device;
+
 /*
  * TODO: This header file should be replaced with videobuf2-core.h
  * Currently, vb2_thread is not a stuff of videobuf2-core,
@@ -50,6 +54,7 @@ int vb2_dvb_register_bus(struct vb2_dvb_frontends *f,
 			 struct module *module,
 			 void *adapter_priv,
 			 struct device *device,
+			 struct media_device *mdev,
 			 short *adapter_nr,
 			 int mfe_shared);
 
diff --git a/include/media/vsp1.h b/include/media/vsp1.h
new file mode 100644
index 000000000000..cc541753896f
--- /dev/null
+++ b/include/media/vsp1.h
@@ -0,0 +1,33 @@
+/*
+ * vsp1.h  --  R-Car VSP1 API
+ *
+ * Copyright (C) 2015 Renesas Electronics Corporation
+ *
+ * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#ifndef __MEDIA_VSP1_H__
+#define __MEDIA_VSP1_H__
+
+#include <linux/types.h>
+
+struct device;
+struct v4l2_rect;
+
+int vsp1_du_init(struct device *dev);
+
+int vsp1_du_setup_lif(struct device *dev, unsigned int width,
+		      unsigned int height);
+
+int vsp1_du_atomic_begin(struct device *dev);
+int vsp1_du_atomic_update(struct device *dev, unsigned int rpf, u32 pixelformat,
+			  unsigned int pitch, dma_addr_t mem[2],
+			  const struct v4l2_rect *src,
+			  const struct v4l2_rect *dst);
+int vsp1_du_atomic_flush(struct device *dev);
+
+#endif /* __MEDIA_VSP1_H__ */
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 2a91a0561a47..9b4c418bebd8 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -6,8 +6,8 @@
 #include <linux/mutex.h>
 #include <net/sock.h>
 
-void unix_inflight(struct file *fp);
-void unix_notinflight(struct file *fp);
+void unix_inflight(struct user_struct *user, struct file *fp);
+void unix_notinflight(struct user_struct *user, struct file *fp);
 void unix_gc(void);
 void wait_for_unix_gc(void);
 struct sock *unix_get_socket(struct file *filp);
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 481fe1c9044c..49dcad4fe99e 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -270,8 +270,9 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 					    struct sock *newsk,
 					    const struct request_sock *req);
 
-void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
-			      struct sock *child);
+struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
+				      struct request_sock *req,
+				      struct sock *child);
 void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
 				   unsigned long timeout);
 struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 7029527725dd..4079fc18ffe4 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -61,6 +61,7 @@ struct fib_nh_exception {
 	struct rtable __rcu		*fnhe_rth_input;
 	struct rtable __rcu		*fnhe_rth_output;
 	unsigned long			fnhe_stamp;
+	struct rcu_head			rcu;
 };
 
 struct fnhe_hash_bucket {
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 6db96ea0144f..dda9abf6b89c 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -230,6 +230,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd);
 int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
 		    u8 *protocol, struct flowi4 *fl4);
+int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict);
 int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu);
 
 struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h
index 8f81bbbc38fc..e0f4109e64c6 100644
--- a/include/net/iw_handler.h
+++ b/include/net/iw_handler.h
@@ -439,6 +439,12 @@ int dev_get_wireless_info(char *buffer, char **start, off_t offset, int length);
 /* Send a single event to user space */
 void wireless_send_event(struct net_device *dev, unsigned int cmd,
 			 union iwreq_data *wrqu, const char *extra);
+#ifdef CONFIG_WEXT_CORE
+/* flush all previous wext events - if work is done from netdev notifiers */
+void wireless_nlevent_flush(void);
+#else
+static inline void wireless_nlevent_flush(void) {}
+#endif
 
 /* We may need a function to send a stream of events to user space.
  * More on that later... */
diff --git a/include/net/scm.h b/include/net/scm.h
index 262532d111f5..59fa93c01d2a 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -21,6 +21,7 @@ struct scm_creds {
 struct scm_fp_list {
 	short			count;
 	short			max;
+	struct user_struct	*user;
 	struct file		*fp[SCM_MAX_FD];
 };
 
diff --git a/include/net/sctp/auth.h b/include/net/sctp/auth.h
index f2d58aa37a6f..9b9fb122b31f 100644
--- a/include/net/sctp/auth.h
+++ b/include/net/sctp/auth.h
@@ -31,12 +31,12 @@
 #define __sctp_auth_h__
 
 #include <linux/list.h>
-#include <linux/crypto.h>
 
 struct sctp_endpoint;
 struct sctp_association;
 struct sctp_authkey;
 struct sctp_hmacalgo;
+struct crypto_shash;
 
 /*
  * Define a generic struct that will hold all the info
@@ -90,7 +90,7 @@ int sctp_auth_asoc_copy_shkeys(const struct sctp_endpoint *ep,
 				struct sctp_association *asoc,
 				gfp_t gfp);
 int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp);
-void sctp_auth_destroy_hmacs(struct crypto_hash *auth_hmacs[]);
+void sctp_auth_destroy_hmacs(struct crypto_shash *auth_hmacs[]);
 struct sctp_hmac *sctp_auth_get_hmac(__u16 hmac_id);
 struct sctp_hmac *sctp_auth_asoc_get_hmac(const struct sctp_association *asoc);
 void sctp_auth_asoc_set_default_hmac(struct sctp_association *asoc,
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 205630bb5010..5a57409da37b 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -82,7 +82,7 @@ struct sctp_bind_addr;
 struct sctp_ulpq;
 struct sctp_ep_common;
 struct sctp_ssnmap;
-struct crypto_hash;
+struct crypto_shash;
 
 
 #include <net/sctp/tsnmap.h>
@@ -166,7 +166,7 @@ struct sctp_sock {
 	struct sctp_pf *pf;
 
 	/* Access to HMAC transform. */
-	struct crypto_hash *hmac;
+	struct crypto_shash *hmac;
 	char *sctp_hmac_alg;
 
 	/* What is our base endpointer? */
@@ -1234,7 +1234,7 @@ struct sctp_endpoint {
 	/* SCTP AUTH: array of the HMACs that will be allocated
 	 * we need this per association so that we don't serialize
 	 */
-	struct crypto_hash **auth_hmacs;
+	struct crypto_shash **auth_hmacs;
 
 	/* SCTP-AUTH: hmacs for the endpoint encoded into parameter */
 	 struct sctp_hmac_algo_param *auth_hmacs_list;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f6f8f032c73e..b04bc989ad6c 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -27,7 +27,6 @@
 #include <linux/cache.h>
 #include <linux/percpu.h>
 #include <linux/skbuff.h>
-#include <linux/crypto.h>
 #include <linux/cryptohash.h>
 #include <linux/kref.h>
 #include <linux/ktime.h>
@@ -447,7 +446,7 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th);
 
 void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb);
 void tcp_v4_mtu_reduced(struct sock *sk);
-void tcp_req_err(struct sock *sk, u32 seq);
+void tcp_req_err(struct sock *sk, u32 seq, bool abort);
 int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
 struct sock *tcp_create_openreq_child(const struct sock *sk,
 				      struct request_sock *req,
@@ -1325,9 +1324,6 @@ static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp)
 	tp->retransmit_skb_hint = NULL;
 }
 
-/* MD5 Signature */
-struct crypto_hash;
-
 union tcp_md5_addr {
 	struct in_addr  a4;
 #if IS_ENABLED(CONFIG_IPV6)
@@ -1376,7 +1372,7 @@ union tcp_md5sum_block {
 
 /* - pool: digest algorithm, hash description and scratch buffer */
 struct tcp_md5sig_pool {
-	struct hash_desc	md5_desc;
+	struct ahash_request	*md5_req;
 	union tcp_md5sum_block	md5_blk;
 };
 
diff --git a/include/scsi/iscsi_if.h b/include/scsi/iscsi_if.h
index 95ed9424a11a..d66c07077d68 100644
--- a/include/scsi/iscsi_if.h
+++ b/include/scsi/iscsi_if.h
@@ -724,6 +724,8 @@ enum iscsi_port_speed {
 	ISCSI_PORT_SPEED_100MBPS	= 0x4,
 	ISCSI_PORT_SPEED_1GBPS		= 0x8,
 	ISCSI_PORT_SPEED_10GBPS		= 0x10,
+	ISCSI_PORT_SPEED_25GBPS         = 0x20,
+	ISCSI_PORT_SPEED_40GBPS         = 0x40,
 };
 
 /* iSCSI port state */
diff --git a/include/scsi/libiscsi_tcp.h b/include/scsi/libiscsi_tcp.h
index 2a7aa75dd009..30520d5ee3d1 100644
--- a/include/scsi/libiscsi_tcp.h
+++ b/include/scsi/libiscsi_tcp.h
@@ -26,7 +26,7 @@
 struct iscsi_tcp_conn;
 struct iscsi_segment;
 struct sk_buff;
-struct hash_desc;
+struct ahash_request;
 
 typedef int iscsi_segment_done_fn_t(struct iscsi_tcp_conn *,
 				    struct iscsi_segment *);
@@ -38,7 +38,7 @@ struct iscsi_segment {
 	unsigned int		total_size;
 	unsigned int		total_copied;
 
-	struct hash_desc	*hash;
+	struct ahash_request	*hash;
 	unsigned char		padbuf[ISCSI_PAD_LEN];
 	unsigned char		recv_digest[ISCSI_DIGEST_SIZE];
 	unsigned char		digest[ISCSI_DIGEST_SIZE];
@@ -73,7 +73,7 @@ struct iscsi_tcp_conn {
 	/* control data */
 	struct iscsi_tcp_recv	in;		/* TCP receive context */
 	/* CRC32C (Rx) LLD should set this is they do not offload */
-	struct hash_desc	*rx_hash;
+	struct ahash_request	*rx_hash;
 };
 
 struct iscsi_tcp_task {
@@ -111,15 +111,16 @@ extern void iscsi_tcp_segment_unmap(struct iscsi_segment *segment);
 extern void iscsi_segment_init_linear(struct iscsi_segment *segment,
 				      void *data, size_t size,
 				      iscsi_segment_done_fn_t *done,
-				      struct hash_desc *hash);
+				      struct ahash_request *hash);
 extern int
 iscsi_segment_seek_sg(struct iscsi_segment *segment,
 		      struct scatterlist *sg_list, unsigned int sg_count,
 		      unsigned int offset, size_t size,
-		      iscsi_segment_done_fn_t *done, struct hash_desc *hash);
+		      iscsi_segment_done_fn_t *done,
+		      struct ahash_request *hash);
 
 /* digest helpers */
-extern void iscsi_tcp_dgst_header(struct hash_desc *hash, const void *hdr,
+extern void iscsi_tcp_dgst_header(struct ahash_request *hash, const void *hdr,
 				  size_t hdrlen,
 				  unsigned char digest[ISCSI_DIGEST_SIZE]);
 extern struct iscsi_cls_conn *
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index f63a16760ae9..c067019ed12a 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -176,6 +176,7 @@ struct scsi_device {
 	unsigned no_dif:1;	/* T10 PI (DIF) should be disabled */
 	unsigned broken_fua:1;		/* Don't set FUA bit */
 	unsigned lun_in_cdb:1;		/* Store LUN bits in CDB[1] */
+	unsigned synchronous_alua:1;	/* Synchronous ALUA commands */
 
 	atomic_t disk_events_disable_depth; /* disable depth for disk events */
 
@@ -200,6 +201,7 @@ struct scsi_device {
 	struct scsi_device_handler *handler;
 	void			*handler_data;
 
+	unsigned char		access_state;
 	enum scsi_device_state sdev_state;
 	unsigned long		sdev_data[0];
 } __attribute__((aligned(sizeof(unsigned long))));
@@ -397,6 +399,7 @@ extern void scsi_remove_target(struct device *);
 extern const char *scsi_device_state_name(enum scsi_device_state);
 extern int scsi_is_sdev_device(const struct device *);
 extern int scsi_is_target_device(const struct device *);
+extern void scsi_sanitize_inquiry_string(unsigned char *s, int len);
 extern int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 			int data_direction, void *buffer, unsigned bufflen,
 			unsigned char *sense, int timeout, int retries,
diff --git a/include/scsi/scsi_devinfo.h b/include/scsi/scsi_devinfo.h
index 96e3f56519e7..9f750cb63b03 100644
--- a/include/scsi/scsi_devinfo.h
+++ b/include/scsi/scsi_devinfo.h
@@ -37,5 +37,6 @@
 #define BLIST_TRY_VPD_PAGES	0x10000000 /* Attempt to read VPD pages */
 #define BLIST_NO_RSOC		0x20000000 /* don't try to issue RSOC */
 #define BLIST_MAX_1024		0x40000000 /* maximum 1024 sector cdb length */
+#define BLIST_SYNC_ALUA		0x80000000 /* Synchronous ALUA commands */
 
 #endif
diff --git a/include/scsi/scsi_dh.h b/include/scsi/scsi_dh.h
index 85d731746834..c7bba2b24849 100644
--- a/include/scsi/scsi_dh.h
+++ b/include/scsi/scsi_dh.h
@@ -52,6 +52,7 @@ enum {
 	SCSI_DH_TIMED_OUT,
 	SCSI_DH_RES_TEMP_UNAVAIL,
 	SCSI_DH_DEV_OFFLINED,
+	SCSI_DH_NOMEM,
 	SCSI_DH_NOSYS,
 	SCSI_DH_DRIVER_MAX,
 };
@@ -70,6 +71,7 @@ struct scsi_device_handler {
 	int (*activate)(struct scsi_device *, activate_complete, void *);
 	int (*prep_fn)(struct scsi_device *, struct request *);
 	int (*set_params)(struct scsi_device *, const char *);
+	void (*rescan)(struct scsi_device *);
 };
 
 #ifdef CONFIG_SCSI_DH
diff --git a/include/scsi/scsi_proto.h b/include/scsi/scsi_proto.h
index a9fbf1b38e71..c2ae21cbaa2c 100644
--- a/include/scsi/scsi_proto.h
+++ b/include/scsi/scsi_proto.h
@@ -277,5 +277,17 @@ struct scsi_lun {
 	__u8 scsi_lun[8];
 };
 
+/* SPC asymmetric access states */
+#define SCSI_ACCESS_STATE_OPTIMAL     0x00
+#define SCSI_ACCESS_STATE_ACTIVE      0x01
+#define SCSI_ACCESS_STATE_STANDBY     0x02
+#define SCSI_ACCESS_STATE_UNAVAILABLE 0x03
+#define SCSI_ACCESS_STATE_LBA         0x04
+#define SCSI_ACCESS_STATE_OFFLINE     0x0e
+#define SCSI_ACCESS_STATE_TRANSITIONING 0x0f
+
+/* Values for REPORT TARGET GROUP STATES */
+#define SCSI_ACCESS_STATE_MASK        0x0f
+#define SCSI_ACCESS_STATE_PREFERRED   0x80
 
 #endif /* _SCSI_PROTO_H_ */
diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h
index e2b712c90d3f..c21c38ce7450 100644
--- a/include/sound/hdaudio.h
+++ b/include/sound/hdaudio.h
@@ -343,7 +343,7 @@ void snd_hdac_bus_enter_link_reset(struct hdac_bus *bus);
 void snd_hdac_bus_exit_link_reset(struct hdac_bus *bus);
 
 void snd_hdac_bus_update_rirb(struct hdac_bus *bus);
-void snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status,
+int snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status,
 				    void (*ack)(struct hdac_bus *,
 						struct hdac_stream *));
 
diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h
index 373d3342002b..c3371fa548cb 100644
--- a/include/target/iscsi/iscsi_target_core.h
+++ b/include/target/iscsi/iscsi_target_core.h
@@ -570,8 +570,8 @@ struct iscsi_conn {
 	spinlock_t		response_queue_lock;
 	spinlock_t		state_lock;
 	/* libcrypto RX and TX contexts for crc32c */
-	struct hash_desc	conn_rx_hash;
-	struct hash_desc	conn_tx_hash;
+	struct ahash_request	*conn_rx_hash;
+	struct ahash_request	*conn_tx_hash;
 	/* Used for scheduling TX and RX connection kthreads */
 	cpumask_var_t		conn_cpumask;
 	unsigned int		conn_rx_reset_cpumask:1;
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 56cf8e485ef2..28ee5c2e6bcd 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -94,5 +94,8 @@ sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd,
 	sense_reason_t (*exec_cmd)(struct se_cmd *cmd));
 
 bool target_sense_desc_format(struct se_device *dev);
+sector_t target_to_linux_sector(struct se_device *dev, sector_t lb);
+bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
+				       struct request_queue *q, int block_size);
 
 #endif /* TARGET_CORE_BACKEND_H */
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 5d82816cc4e3..e8c8c08bf575 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -140,6 +140,8 @@ enum se_cmd_flags_table {
 	SCF_COMPARE_AND_WRITE		= 0x00080000,
 	SCF_COMPARE_AND_WRITE_POST	= 0x00100000,
 	SCF_PASSTHROUGH_PROT_SG_TO_MEM_NOALLOC = 0x00200000,
+	SCF_ACK_KREF			= 0x00400000,
+	SCF_USE_CPUID			= 0x00800000,
 };
 
 /* struct se_dev_entry->lun_flags and struct se_lun->lun_access */
@@ -187,6 +189,7 @@ enum target_sc_flags_table {
 	TARGET_SCF_BIDI_OP		= 0x01,
 	TARGET_SCF_ACK_KREF		= 0x02,
 	TARGET_SCF_UNKNOWN_SIZE		= 0x04,
+	TARGET_SCF_USE_CPUID	= 0x08,
 };
 
 /* fabric independent task management function values */
@@ -490,8 +493,9 @@ struct se_cmd {
 #define CMD_T_SENT		(1 << 4)
 #define CMD_T_STOP		(1 << 5)
 #define CMD_T_DEV_ACTIVE	(1 << 7)
-#define CMD_T_REQUEST_STOP	(1 << 8)
 #define CMD_T_BUSY		(1 << 9)
+#define CMD_T_TAS		(1 << 10)
+#define CMD_T_FABRIC_STOP	(1 << 11)
 	spinlock_t		t_state_lock;
 	struct kref		cmd_kref;
 	struct completion	t_transport_stop_comp;
@@ -511,9 +515,6 @@ struct se_cmd {
 
 	struct list_head	state_list;
 
-	/* old task stop completion, consider merging with some of the above */
-	struct completion	task_stop_comp;
-
 	/* backend private data */
 	void			*priv;
 
diff --git a/include/trace/events/asoc.h b/include/trace/events/asoc.h
index 317a1ed2f4ac..9130dd5a184a 100644
--- a/include/trace/events/asoc.h
+++ b/include/trace/events/asoc.h
@@ -231,13 +231,13 @@ TRACE_EVENT(snd_soc_jack_report,
 	TP_ARGS(jack, mask, val),
 
 	TP_STRUCT__entry(
-		__string(	name,		jack->jack->name	)
+		__string(	name,		jack->jack->id		)
 		__field(	int,		mask			)
 		__field(	int,		val			)
 	),
 
 	TP_fast_assign(
-		__assign_str(name, jack->jack->name);
+		__assign_str(name, jack->jack->id);
 		__entry->mask = mask;
 		__entry->val = val;
 	),
@@ -253,12 +253,12 @@ TRACE_EVENT(snd_soc_jack_notify,
 	TP_ARGS(jack, val),
 
 	TP_STRUCT__entry(
-		__string(	name,		jack->jack->name	)
+		__string(	name,		jack->jack->id		)
 		__field(	int,		val			)
 	),
 
 	TP_fast_assign(
-		__assign_str(name, jack->jack->name);
+		__assign_str(name, jack->jack->id);
 		__entry->val = val;
 	),
 
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index d866f21efbbf..677807f29a1c 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -6,7 +6,7 @@
 
 #include <linux/writeback.h>
 #include <linux/tracepoint.h>
-#include <trace/events/gfpflags.h>
+#include <trace/events/mmflags.h>
 
 struct btrfs_root;
 struct btrfs_fs_info;
diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index c92d1e1cbad9..111e5666e5eb 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -7,7 +7,7 @@
 #include <linux/types.h>
 #include <linux/list.h>
 #include <linux/tracepoint.h>
-#include <trace/events/gfpflags.h>
+#include <trace/events/mmflags.h>
 
 #define COMPACTION_STATUS					\
 	EM( COMPACT_DEFERRED,		"deferred")		\
diff --git a/include/trace/events/cpuhp.h b/include/trace/events/cpuhp.h
new file mode 100644
index 000000000000..a72bd93ec7e5
--- /dev/null
+++ b/include/trace/events/cpuhp.h
@@ -0,0 +1,66 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM cpuhp
+
+#if !defined(_TRACE_CPUHP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_CPUHP_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(cpuhp_enter,
+
+	TP_PROTO(unsigned int cpu,
+		 int target,
+		 int idx,
+		 int (*fun)(unsigned int)),
+
+	TP_ARGS(cpu, target, idx, fun),
+
+	TP_STRUCT__entry(
+		__field( unsigned int,	cpu		)
+		__field( int,		target		)
+		__field( int,		idx		)
+		__field( void *,	fun		)
+	),
+
+	TP_fast_assign(
+		__entry->cpu	= cpu;
+		__entry->target	= target;
+		__entry->idx	= idx;
+		__entry->fun	= fun;
+	),
+
+	TP_printk("cpu: %04u target: %3d step: %3d (%pf)",
+		  __entry->cpu, __entry->target, __entry->idx, __entry->fun)
+);
+
+TRACE_EVENT(cpuhp_exit,
+
+	TP_PROTO(unsigned int cpu,
+		 int state,
+		 int idx,
+		 int ret),
+
+	TP_ARGS(cpu, state, idx, ret),
+
+	TP_STRUCT__entry(
+		__field( unsigned int,	cpu		)
+		__field( int,		state		)
+		__field( int,		idx		)
+		__field( int,		ret		)
+	),
+
+	TP_fast_assign(
+		__entry->cpu	= cpu;
+		__entry->state	= state;
+		__entry->idx	= idx;
+		__entry->ret	= ret;
+	),
+
+	TP_printk(" cpu: %04u  state: %3d step: %3d ret: %d",
+		  __entry->cpu, __entry->state, __entry->idx,  __entry->ret)
+);
+
+#endif
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h
deleted file mode 100644
index dde6bf092c8a..000000000000
--- a/include/trace/events/gfpflags.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * The order of these masks is important. Matching masks will be seen
- * first and the left over flags will end up showing by themselves.
- *
- * For example, if we have GFP_KERNEL before GFP_USER we wil get:
- *
- *  GFP_KERNEL|GFP_HARDWALL
- *
- * Thus most bits set go first.
- */
-#define show_gfp_flags(flags)						\
-	(flags) ? __print_flags(flags, "|",				\
-	{(unsigned long)GFP_TRANSHUGE,		"GFP_TRANSHUGE"},	\
-	{(unsigned long)GFP_HIGHUSER_MOVABLE,	"GFP_HIGHUSER_MOVABLE"}, \
-	{(unsigned long)GFP_HIGHUSER,		"GFP_HIGHUSER"},	\
-	{(unsigned long)GFP_USER,		"GFP_USER"},		\
-	{(unsigned long)GFP_TEMPORARY,		"GFP_TEMPORARY"},	\
-	{(unsigned long)GFP_KERNEL,		"GFP_KERNEL"},		\
-	{(unsigned long)GFP_NOFS,		"GFP_NOFS"},		\
-	{(unsigned long)GFP_ATOMIC,		"GFP_ATOMIC"},		\
-	{(unsigned long)GFP_NOIO,		"GFP_NOIO"},		\
-	{(unsigned long)__GFP_HIGH,		"GFP_HIGH"},		\
-	{(unsigned long)__GFP_ATOMIC,		"GFP_ATOMIC"},		\
-	{(unsigned long)__GFP_IO,		"GFP_IO"},		\
-	{(unsigned long)__GFP_COLD,		"GFP_COLD"},		\
-	{(unsigned long)__GFP_NOWARN,		"GFP_NOWARN"},		\
-	{(unsigned long)__GFP_REPEAT,		"GFP_REPEAT"},		\
-	{(unsigned long)__GFP_NOFAIL,		"GFP_NOFAIL"},		\
-	{(unsigned long)__GFP_NORETRY,		"GFP_NORETRY"},		\
-	{(unsigned long)__GFP_COMP,		"GFP_COMP"},		\
-	{(unsigned long)__GFP_ZERO,		"GFP_ZERO"},		\
-	{(unsigned long)__GFP_NOMEMALLOC,	"GFP_NOMEMALLOC"},	\
-	{(unsigned long)__GFP_MEMALLOC,		"GFP_MEMALLOC"},	\
-	{(unsigned long)__GFP_HARDWALL,		"GFP_HARDWALL"},	\
-	{(unsigned long)__GFP_THISNODE,		"GFP_THISNODE"},	\
-	{(unsigned long)__GFP_RECLAIMABLE,	"GFP_RECLAIMABLE"},	\
-	{(unsigned long)__GFP_MOVABLE,		"GFP_MOVABLE"},		\
-	{(unsigned long)__GFP_NOTRACK,		"GFP_NOTRACK"},		\
-	{(unsigned long)__GFP_DIRECT_RECLAIM,	"GFP_DIRECT_RECLAIM"},	\
-	{(unsigned long)__GFP_KSWAPD_RECLAIM,	"GFP_KSWAPD_RECLAIM"},	\
-	{(unsigned long)__GFP_OTHER_NODE,	"GFP_OTHER_NODE"}	\
-	) : "GFP_NOWAIT"
-
diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h
index 47c6212d8f3c..551ba4acde4d 100644
--- a/include/trace/events/huge_memory.h
+++ b/include/trace/events/huge_memory.h
@@ -6,8 +6,6 @@
 
 #include  <linux/tracepoint.h>
 
-#include <trace/events/gfpflags.h>
-
 #define SCAN_STATUS							\
 	EM( SCAN_FAIL,			"failed")			\
 	EM( SCAN_SUCCEED,		"succeeded")			\
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index f7554fd7fc62..ca7217389067 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -6,7 +6,7 @@
 
 #include <linux/types.h>
 #include <linux/tracepoint.h>
-#include <trace/events/gfpflags.h>
+#include <trace/events/mmflags.h>
 
 DECLARE_EVENT_CLASS(kmem_alloc,
 
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index d6f83222a6a1..aa69253ecc7d 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -359,14 +359,15 @@ TRACE_EVENT(
 #endif
 
 TRACE_EVENT(kvm_halt_poll_ns,
-	TP_PROTO(bool grow, unsigned int vcpu_id, int new, int old),
+	TP_PROTO(bool grow, unsigned int vcpu_id, unsigned int new,
+		 unsigned int old),
 	TP_ARGS(grow, vcpu_id, new, old),
 
 	TP_STRUCT__entry(
 		__field(bool, grow)
 		__field(unsigned int, vcpu_id)
-		__field(int, new)
-		__field(int, old)
+		__field(unsigned int, new)
+		__field(unsigned int, old)
 	),
 
 	TP_fast_assign(
@@ -376,7 +377,7 @@ TRACE_EVENT(kvm_halt_poll_ns,
 		__entry->old            = old;
 	),
 
-	TP_printk("vcpu %u: halt_poll_ns %d (%s %d)",
+	TP_printk("vcpu %u: halt_poll_ns %u (%s %u)",
 			__entry->vcpu_id,
 			__entry->new,
 			__entry->grow ? "grow" : "shrink",
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
new file mode 100644
index 000000000000..a849185c82f0
--- /dev/null
+++ b/include/trace/events/mmflags.h
@@ -0,0 +1,164 @@
+/*
+ * The order of these masks is important. Matching masks will be seen
+ * first and the left over flags will end up showing by themselves.
+ *
+ * For example, if we have GFP_KERNEL before GFP_USER we wil get:
+ *
+ *  GFP_KERNEL|GFP_HARDWALL
+ *
+ * Thus most bits set go first.
+ */
+
+#define __def_gfpflag_names						\
+	{(unsigned long)GFP_TRANSHUGE,		"GFP_TRANSHUGE"},	\
+	{(unsigned long)GFP_HIGHUSER_MOVABLE,	"GFP_HIGHUSER_MOVABLE"},\
+	{(unsigned long)GFP_HIGHUSER,		"GFP_HIGHUSER"},	\
+	{(unsigned long)GFP_USER,		"GFP_USER"},		\
+	{(unsigned long)GFP_TEMPORARY,		"GFP_TEMPORARY"},	\
+	{(unsigned long)GFP_KERNEL_ACCOUNT,	"GFP_KERNEL_ACCOUNT"},	\
+	{(unsigned long)GFP_KERNEL,		"GFP_KERNEL"},		\
+	{(unsigned long)GFP_NOFS,		"GFP_NOFS"},		\
+	{(unsigned long)GFP_ATOMIC,		"GFP_ATOMIC"},		\
+	{(unsigned long)GFP_NOIO,		"GFP_NOIO"},		\
+	{(unsigned long)GFP_NOWAIT,		"GFP_NOWAIT"},		\
+	{(unsigned long)GFP_DMA,		"GFP_DMA"},		\
+	{(unsigned long)__GFP_HIGHMEM,		"__GFP_HIGHMEM"},	\
+	{(unsigned long)GFP_DMA32,		"GFP_DMA32"},		\
+	{(unsigned long)__GFP_HIGH,		"__GFP_HIGH"},		\
+	{(unsigned long)__GFP_ATOMIC,		"__GFP_ATOMIC"},	\
+	{(unsigned long)__GFP_IO,		"__GFP_IO"},		\
+	{(unsigned long)__GFP_FS,		"__GFP_FS"},		\
+	{(unsigned long)__GFP_COLD,		"__GFP_COLD"},		\
+	{(unsigned long)__GFP_NOWARN,		"__GFP_NOWARN"},	\
+	{(unsigned long)__GFP_REPEAT,		"__GFP_REPEAT"},	\
+	{(unsigned long)__GFP_NOFAIL,		"__GFP_NOFAIL"},	\
+	{(unsigned long)__GFP_NORETRY,		"__GFP_NORETRY"},	\
+	{(unsigned long)__GFP_COMP,		"__GFP_COMP"},		\
+	{(unsigned long)__GFP_ZERO,		"__GFP_ZERO"},		\
+	{(unsigned long)__GFP_NOMEMALLOC,	"__GFP_NOMEMALLOC"},	\
+	{(unsigned long)__GFP_MEMALLOC,		"__GFP_MEMALLOC"},	\
+	{(unsigned long)__GFP_HARDWALL,		"__GFP_HARDWALL"},	\
+	{(unsigned long)__GFP_THISNODE,		"__GFP_THISNODE"},	\
+	{(unsigned long)__GFP_RECLAIMABLE,	"__GFP_RECLAIMABLE"},	\
+	{(unsigned long)__GFP_MOVABLE,		"__GFP_MOVABLE"},	\
+	{(unsigned long)__GFP_ACCOUNT,		"__GFP_ACCOUNT"},	\
+	{(unsigned long)__GFP_NOTRACK,		"__GFP_NOTRACK"},	\
+	{(unsigned long)__GFP_WRITE,		"__GFP_WRITE"},		\
+	{(unsigned long)__GFP_RECLAIM,		"__GFP_RECLAIM"},	\
+	{(unsigned long)__GFP_DIRECT_RECLAIM,	"__GFP_DIRECT_RECLAIM"},\
+	{(unsigned long)__GFP_KSWAPD_RECLAIM,	"__GFP_KSWAPD_RECLAIM"},\
+	{(unsigned long)__GFP_OTHER_NODE,	"__GFP_OTHER_NODE"}	\
+
+#define show_gfp_flags(flags)						\
+	(flags) ? __print_flags(flags, "|",				\
+	__def_gfpflag_names						\
+	) : "none"
+
+#ifdef CONFIG_MMU
+#define IF_HAVE_PG_MLOCK(flag,string) ,{1UL << flag, string}
+#else
+#define IF_HAVE_PG_MLOCK(flag,string)
+#endif
+
+#ifdef CONFIG_ARCH_USES_PG_UNCACHED
+#define IF_HAVE_PG_UNCACHED(flag,string) ,{1UL << flag, string}
+#else
+#define IF_HAVE_PG_UNCACHED(flag,string)
+#endif
+
+#ifdef CONFIG_MEMORY_FAILURE
+#define IF_HAVE_PG_HWPOISON(flag,string) ,{1UL << flag, string}
+#else
+#define IF_HAVE_PG_HWPOISON(flag,string)
+#endif
+
+#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
+#define IF_HAVE_PG_IDLE(flag,string) ,{1UL << flag, string}
+#else
+#define IF_HAVE_PG_IDLE(flag,string)
+#endif
+
+#define __def_pageflag_names						\
+	{1UL << PG_locked,		"locked"	},		\
+	{1UL << PG_error,		"error"		},		\
+	{1UL << PG_referenced,		"referenced"	},		\
+	{1UL << PG_uptodate,		"uptodate"	},		\
+	{1UL << PG_dirty,		"dirty"		},		\
+	{1UL << PG_lru,			"lru"		},		\
+	{1UL << PG_active,		"active"	},		\
+	{1UL << PG_slab,		"slab"		},		\
+	{1UL << PG_owner_priv_1,	"owner_priv_1"	},		\
+	{1UL << PG_arch_1,		"arch_1"	},		\
+	{1UL << PG_reserved,		"reserved"	},		\
+	{1UL << PG_private,		"private"	},		\
+	{1UL << PG_private_2,		"private_2"	},		\
+	{1UL << PG_writeback,		"writeback"	},		\
+	{1UL << PG_head,		"head"		},		\
+	{1UL << PG_swapcache,		"swapcache"	},		\
+	{1UL << PG_mappedtodisk,	"mappedtodisk"	},		\
+	{1UL << PG_reclaim,		"reclaim"	},		\
+	{1UL << PG_swapbacked,		"swapbacked"	},		\
+	{1UL << PG_unevictable,		"unevictable"	}		\
+IF_HAVE_PG_MLOCK(PG_mlocked,		"mlocked"	)		\
+IF_HAVE_PG_UNCACHED(PG_uncached,	"uncached"	)		\
+IF_HAVE_PG_HWPOISON(PG_hwpoison,	"hwpoison"	)		\
+IF_HAVE_PG_IDLE(PG_young,		"young"		)		\
+IF_HAVE_PG_IDLE(PG_idle,		"idle"		)
+
+#define show_page_flags(flags)						\
+	(flags) ? __print_flags(flags, "|",				\
+	__def_pageflag_names						\
+	) : "none"
+
+#if defined(CONFIG_X86)
+#define __VM_ARCH_SPECIFIC {VM_PAT,     "pat"           }
+#elif defined(CONFIG_PPC)
+#define __VM_ARCH_SPECIFIC {VM_SAO,     "sao"           }
+#elif defined(CONFIG_PARISC) || defined(CONFIG_METAG) || defined(CONFIG_IA64)
+#define __VM_ARCH_SPECIFIC {VM_GROWSUP,	"growsup"	}
+#elif !defined(CONFIG_MMU)
+#define __VM_ARCH_SPECIFIC {VM_MAPPED_COPY,"mappedcopy"	}
+#else
+#define __VM_ARCH_SPECIFIC {VM_ARCH_1,	"arch_1"	}
+#endif
+
+#ifdef CONFIG_MEM_SOFT_DIRTY
+#define IF_HAVE_VM_SOFTDIRTY(flag,name) {flag, name },
+#else
+#define IF_HAVE_VM_SOFTDIRTY(flag,name)
+#endif
+
+#define __def_vmaflag_names						\
+	{VM_READ,			"read"		},		\
+	{VM_WRITE,			"write"		},		\
+	{VM_EXEC,			"exec"		},		\
+	{VM_SHARED,			"shared"	},		\
+	{VM_MAYREAD,			"mayread"	},		\
+	{VM_MAYWRITE,			"maywrite"	},		\
+	{VM_MAYEXEC,			"mayexec"	},		\
+	{VM_MAYSHARE,			"mayshare"	},		\
+	{VM_GROWSDOWN,			"growsdown"	},		\
+	{VM_PFNMAP,			"pfnmap"	},		\
+	{VM_DENYWRITE,			"denywrite"	},		\
+	{VM_LOCKONFAULT,		"lockonfault"	},		\
+	{VM_LOCKED,			"locked"	},		\
+	{VM_IO,				"io"		},		\
+	{VM_SEQ_READ,			"seqread"	},		\
+	{VM_RAND_READ,			"randread"	},		\
+	{VM_DONTCOPY,			"dontcopy"	},		\
+	{VM_DONTEXPAND,			"dontexpand"	},		\
+	{VM_ACCOUNT,			"account"	},		\
+	{VM_NORESERVE,			"noreserve"	},		\
+	{VM_HUGETLB,			"hugetlb"	},		\
+	__VM_ARCH_SPECIFIC				,		\
+	{VM_DONTDUMP,			"dontdump"	},		\
+IF_HAVE_VM_SOFTDIRTY(VM_SOFTDIRTY,	"softdirty"	)		\
+	{VM_MIXEDMAP,			"mixedmap"	},		\
+	{VM_HUGEPAGE,			"hugepage"	},		\
+	{VM_NOHUGEPAGE,			"nohugepage"	},		\
+	{VM_MERGEABLE,			"mergeable"	}		\
+
+#define show_vma_flags(flags)						\
+	(flags) ? __print_flags(flags, "|",				\
+	__def_vmaflag_names						\
+	) : "none"
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index 284244ebfe8d..19e50300ce7d 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -38,6 +38,28 @@ DEFINE_EVENT(cpu, cpu_idle,
 	TP_ARGS(state, cpu_id)
 );
 
+TRACE_EVENT(powernv_throttle,
+
+	TP_PROTO(int chip_id, const char *reason, int pmax),
+
+	TP_ARGS(chip_id, reason, pmax),
+
+	TP_STRUCT__entry(
+		__field(int, chip_id)
+		__string(reason, reason)
+		__field(int, pmax)
+	),
+
+	TP_fast_assign(
+		__entry->chip_id = chip_id;
+		__assign_str(reason, reason);
+		__entry->pmax = pmax;
+	),
+
+	TP_printk("Chip %d Pmax %d %s", __entry->chip_id,
+		  __entry->pmax, __get_str(reason))
+);
+
 TRACE_EVENT(pstate_sample,
 
 	TP_PROTO(u32 core_busy,
diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index 073b9ac245ba..51440131d337 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -328,23 +328,49 @@ TRACE_EVENT(itimer_expire,
 );
 
 #ifdef CONFIG_NO_HZ_COMMON
+
+#define TICK_DEP_NAMES					\
+		tick_dep_name(NONE)			\
+		tick_dep_name(POSIX_TIMER)		\
+		tick_dep_name(PERF_EVENTS)		\
+		tick_dep_name(SCHED)			\
+		tick_dep_name_end(CLOCK_UNSTABLE)
+
+#undef tick_dep_name
+#undef tick_dep_name_end
+
+#define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep);
+#define tick_dep_name_end(sdep)  TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep);
+
+TICK_DEP_NAMES
+
+#undef tick_dep_name
+#undef tick_dep_name_end
+
+#define tick_dep_name(sdep) { TICK_DEP_MASK_##sdep, #sdep },
+#define tick_dep_name_end(sdep) { TICK_DEP_MASK_##sdep, #sdep }
+
+#define show_tick_dep_name(val)				\
+	__print_symbolic(val, TICK_DEP_NAMES)
+
 TRACE_EVENT(tick_stop,
 
-	TP_PROTO(int success, char *error_msg),
+	TP_PROTO(int success, int dependency),
 
-	TP_ARGS(success, error_msg),
+	TP_ARGS(success, dependency),
 
 	TP_STRUCT__entry(
 		__field( int ,		success	)
-		__string( msg, 		error_msg )
+		__field( int ,		dependency )
 	),
 
 	TP_fast_assign(
 		__entry->success	= success;
-		__assign_str(msg, error_msg);
+		__entry->dependency	= dependency;
 	),
 
-	TP_printk("success=%s msg=%s",  __entry->success ? "yes" : "no", __get_str(msg))
+	TP_printk("success=%d dependency=%s",  __entry->success, \
+			show_tick_dep_name(__entry->dependency))
 );
 #endif
 
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 31763dd8db1c..0101ef37f1ee 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -8,7 +8,7 @@
 #include <linux/tracepoint.h>
 #include <linux/mm.h>
 #include <linux/memcontrol.h>
-#include <trace/events/gfpflags.h>
+#include <trace/events/mmflags.h>
 
 #define RECLAIM_WB_ANON		0x0001u
 #define RECLAIM_WB_FILE		0x0002u
diff --git a/include/uapi/linux/auto_fs.h b/include/uapi/linux/auto_fs.h
index bb991dfe134f..9175a1b4dc69 100644
--- a/include/uapi/linux/auto_fs.h
+++ b/include/uapi/linux/auto_fs.h
@@ -1,7 +1,4 @@
-/* -*- linux-c -*- ------------------------------------------------------- *
- *   
- * linux/include/linux/auto_fs.h
- *
+/*
  *   Copyright 1997 Transmeta Corporation - All Rights Reserved
  *
  * This file is part of the Linux kernel and is made available under
@@ -51,7 +48,7 @@ struct autofs_packet_hdr {
 
 struct autofs_packet_missing {
 	struct autofs_packet_hdr hdr;
-        autofs_wqt_t wait_queue_token;
+	autofs_wqt_t wait_queue_token;
 	int len;
 	char name[NAME_MAX+1];
 };	
@@ -63,12 +60,12 @@ struct autofs_packet_expire {
 	char name[NAME_MAX+1];
 };
 
-#define AUTOFS_IOC_READY      _IO(0x93,0x60)
-#define AUTOFS_IOC_FAIL       _IO(0x93,0x61)
-#define AUTOFS_IOC_CATATONIC  _IO(0x93,0x62)
-#define AUTOFS_IOC_PROTOVER   _IOR(0x93,0x63,int)
-#define AUTOFS_IOC_SETTIMEOUT32 _IOWR(0x93,0x64,compat_ulong_t)
-#define AUTOFS_IOC_SETTIMEOUT _IOWR(0x93,0x64,unsigned long)
-#define AUTOFS_IOC_EXPIRE     _IOR(0x93,0x65,struct autofs_packet_expire)
+#define AUTOFS_IOC_READY      _IO(0x93, 0x60)
+#define AUTOFS_IOC_FAIL       _IO(0x93, 0x61)
+#define AUTOFS_IOC_CATATONIC  _IO(0x93, 0x62)
+#define AUTOFS_IOC_PROTOVER   _IOR(0x93, 0x63, int)
+#define AUTOFS_IOC_SETTIMEOUT32 _IOWR(0x93, 0x64, compat_ulong_t)
+#define AUTOFS_IOC_SETTIMEOUT _IOWR(0x93, 0x64, unsigned long)
+#define AUTOFS_IOC_EXPIRE     _IOR(0x93, 0x65, struct autofs_packet_expire)
 
 #endif /* _UAPI_LINUX_AUTO_FS_H */
diff --git a/include/uapi/linux/auto_fs4.h b/include/uapi/linux/auto_fs4.h
index e02982fa2953..8f8f1bdcca8c 100644
--- a/include/uapi/linux/auto_fs4.h
+++ b/include/uapi/linux/auto_fs4.h
@@ -1,6 +1,4 @@
-/* -*- c -*-
- * linux/include/linux/auto_fs4.h
- *
+/*
  * Copyright 1999-2000 Jeremy Fitzhardinge <jeremy@goop.org>
  *
  * This file is part of the Linux kernel and is made available under
@@ -38,7 +36,6 @@
 static inline void set_autofs_type_indirect(unsigned int *type)
 {
 	*type = AUTOFS_TYPE_INDIRECT;
-	return;
 }
 
 static inline unsigned int autofs_type_indirect(unsigned int type)
@@ -49,7 +46,6 @@ static inline unsigned int autofs_type_indirect(unsigned int type)
 static inline void set_autofs_type_direct(unsigned int *type)
 {
 	*type = AUTOFS_TYPE_DIRECT;
-	return;
 }
 
 static inline unsigned int autofs_type_direct(unsigned int type)
@@ -60,7 +56,6 @@ static inline unsigned int autofs_type_direct(unsigned int type)
 static inline void set_autofs_type_offset(unsigned int *type)
 {
 	*type = AUTOFS_TYPE_OFFSET;
-	return;
 }
 
 static inline unsigned int autofs_type_offset(unsigned int type)
@@ -81,7 +76,6 @@ static inline unsigned int autofs_type_trigger(unsigned int type)
 static inline void set_autofs_type_any(unsigned int *type)
 {
 	*type = AUTOFS_TYPE_ANY;
-	return;
 }
 
 static inline unsigned int autofs_type_any(unsigned int type)
@@ -114,7 +108,7 @@ enum autofs_notify {
 /* v4 multi expire (via pipe) */
 struct autofs_packet_expire_multi {
 	struct autofs_packet_hdr hdr;
-        autofs_wqt_t wait_queue_token;
+	autofs_wqt_t wait_queue_token;
 	int len;
 	char name[NAME_MAX+1];
 };
@@ -154,11 +148,10 @@ union autofs_v5_packet_union {
 	autofs_packet_expire_direct_t expire_direct;
 };
 
-#define AUTOFS_IOC_EXPIRE_MULTI		_IOW(0x93,0x66,int)
+#define AUTOFS_IOC_EXPIRE_MULTI		_IOW(0x93, 0x66, int)
 #define AUTOFS_IOC_EXPIRE_INDIRECT	AUTOFS_IOC_EXPIRE_MULTI
 #define AUTOFS_IOC_EXPIRE_DIRECT	AUTOFS_IOC_EXPIRE_MULTI
-#define AUTOFS_IOC_PROTOSUBVER		_IOR(0x93,0x67,int)
-#define AUTOFS_IOC_ASKUMOUNT		_IOR(0x93,0x70,int)
-
+#define AUTOFS_IOC_PROTOSUBVER		_IOR(0x93, 0x67, int)
+#define AUTOFS_IOC_ASKUMOUNT		_IOR(0x93, 0x70, int)
 
 #endif /* _LINUX_AUTO_FS4_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index aa6f8571de13..5df4881dea7b 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -292,6 +292,9 @@ enum bpf_func_id {
 /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
 #define BPF_F_TUNINFO_IPV6		(1ULL << 0)
 
+/* BPF_FUNC_skb_set_tunnel_key flags. */
+#define BPF_F_ZERO_CSUM_TX		(1ULL << 1)
+
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
  */
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 9da905157cee..a7f1f8032ec1 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -157,6 +157,7 @@ struct kvm_s390_skeys {
 
 struct kvm_hyperv_exit {
 #define KVM_EXIT_HYPERV_SYNIC          1
+#define KVM_EXIT_HYPERV_HCALL          2
 	__u32 type;
 	union {
 		struct {
@@ -165,6 +166,11 @@ struct kvm_hyperv_exit {
 			__u64 evt_page;
 			__u64 msg_page;
 		} synic;
+		struct {
+			__u64 input;
+			__u64 result;
+			__u64 params[2];
+		} hcall;
 	} u;
 };
 
@@ -541,7 +547,13 @@ struct kvm_s390_pgm_info {
 	__u8 exc_access_id;
 	__u8 per_access_id;
 	__u8 op_access_id;
-	__u8 pad[3];
+#define KVM_S390_PGM_FLAGS_ILC_VALID	0x01
+#define KVM_S390_PGM_FLAGS_ILC_0	0x02
+#define KVM_S390_PGM_FLAGS_ILC_1	0x04
+#define KVM_S390_PGM_FLAGS_ILC_MASK	0x06
+#define KVM_S390_PGM_FLAGS_NO_REWIND	0x08
+	__u8 flags;
+	__u8 pad[2];
 };
 
 struct kvm_s390_prefix_info {
@@ -850,6 +862,9 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_IOEVENTFD_ANY_LENGTH 122
 #define KVM_CAP_HYPERV_SYNIC 123
 #define KVM_CAP_S390_RI 124
+#define KVM_CAP_SPAPR_TCE_64 125
+#define KVM_CAP_ARM_PMU_V3 126
+#define KVM_CAP_VCPU_ATTRIBUTES 127
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1142,6 +1157,8 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_PPC_ALLOC_HTAB */
 #define KVM_PPC_ALLOCATE_HTAB	  _IOWR(KVMIO, 0xa7, __u32)
 #define KVM_CREATE_SPAPR_TCE	  _IOW(KVMIO,  0xa8, struct kvm_create_spapr_tce)
+#define KVM_CREATE_SPAPR_TCE_64	  _IOW(KVMIO,  0xa8, \
+				       struct kvm_create_spapr_tce_64)
 /* Available with KVM_CAP_RMA */
 #define KVM_ALLOCATE_RMA	  _IOR(KVMIO,  0xa9, struct kvm_allocate_rma)
 /* Available with KVM_CAP_PPC_HTAB_FD */
diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h
index 1e3c8cb43bd7..df59edee25d1 100644
--- a/include/uapi/linux/media.h
+++ b/include/uapi/linux/media.h
@@ -66,27 +66,49 @@ struct media_device_info {
 /*
  * DVB entities
  */
-#define MEDIA_ENT_F_DTV_DEMOD		(MEDIA_ENT_F_BASE + 1)
-#define MEDIA_ENT_F_TS_DEMUX		(MEDIA_ENT_F_BASE + 2)
-#define MEDIA_ENT_F_DTV_CA		(MEDIA_ENT_F_BASE + 3)
-#define MEDIA_ENT_F_DTV_NET_DECAP	(MEDIA_ENT_F_BASE + 4)
+#define MEDIA_ENT_F_DTV_DEMOD		(MEDIA_ENT_F_BASE + 0x00001)
+#define MEDIA_ENT_F_TS_DEMUX		(MEDIA_ENT_F_BASE + 0x00002)
+#define MEDIA_ENT_F_DTV_CA		(MEDIA_ENT_F_BASE + 0x00003)
+#define MEDIA_ENT_F_DTV_NET_DECAP	(MEDIA_ENT_F_BASE + 0x00004)
 
 /*
- * Connectors
+ * I/O entities
  */
-/* It is a responsibility of the entity drivers to add connectors and links */
-#define MEDIA_ENT_F_CONN_RF		(MEDIA_ENT_F_BASE + 21)
-#define MEDIA_ENT_F_CONN_SVIDEO		(MEDIA_ENT_F_BASE + 22)
-#define MEDIA_ENT_F_CONN_COMPOSITE	(MEDIA_ENT_F_BASE + 23)
-/* For internal test signal generators and other debug connectors */
-#define MEDIA_ENT_F_CONN_TEST		(MEDIA_ENT_F_BASE + 24)
+#define MEDIA_ENT_F_IO_DTV		(MEDIA_ENT_F_BASE + 0x01001)
+#define MEDIA_ENT_F_IO_VBI		(MEDIA_ENT_F_BASE + 0x01002)
+#define MEDIA_ENT_F_IO_SWRADIO		(MEDIA_ENT_F_BASE + 0x01003)
 
 /*
- * I/O entities
+ * Analog TV IF-PLL decoders
+ *
+ * It is a responsibility of the master/bridge drivers to create links
+ * for MEDIA_ENT_F_IF_VID_DECODER and MEDIA_ENT_F_IF_AUD_DECODER.
+ */
+#define MEDIA_ENT_F_IF_VID_DECODER	(MEDIA_ENT_F_BASE + 0x02001)
+#define MEDIA_ENT_F_IF_AUD_DECODER	(MEDIA_ENT_F_BASE + 0x02002)
+
+/*
+ * Audio Entity Functions
  */
-#define MEDIA_ENT_F_IO_DTV  		(MEDIA_ENT_F_BASE + 31)
-#define MEDIA_ENT_F_IO_VBI  		(MEDIA_ENT_F_BASE + 32)
-#define MEDIA_ENT_F_IO_SWRADIO		(MEDIA_ENT_F_BASE + 33)
+#define MEDIA_ENT_F_AUDIO_CAPTURE	(MEDIA_ENT_F_BASE + 0x03001)
+#define MEDIA_ENT_F_AUDIO_PLAYBACK	(MEDIA_ENT_F_BASE + 0x03002)
+#define MEDIA_ENT_F_AUDIO_MIXER		(MEDIA_ENT_F_BASE + 0x03003)
+
+/*
+ * Connectors
+ */
+/* It is a responsibility of the entity drivers to add connectors and links */
+#ifdef __KERNEL__
+	/*
+	 * For now, it should not be used in userspace, as some
+	 * definitions may change
+	 */
+
+#define MEDIA_ENT_F_CONN_RF		(MEDIA_ENT_F_BASE + 0x30001)
+#define MEDIA_ENT_F_CONN_SVIDEO		(MEDIA_ENT_F_BASE + 0x30002)
+#define MEDIA_ENT_F_CONN_COMPOSITE	(MEDIA_ENT_F_BASE + 0x30003)
+
+#endif
 
 /*
  * Don't touch on those. The ranges MEDIA_ENT_F_OLD_BASE and
@@ -107,14 +129,18 @@ struct media_device_info {
 #define MEDIA_ENT_F_LENS		(MEDIA_ENT_F_OLD_SUBDEV_BASE + 3)
 #define MEDIA_ENT_F_ATV_DECODER		(MEDIA_ENT_F_OLD_SUBDEV_BASE + 4)
 /*
- * It is a responsibility of the entity drivers to add connectors and links
- *	for the tuner entities.
+ * It is a responsibility of the master/bridge drivers to add connectors
+ * and links for MEDIA_ENT_F_TUNER. Please notice that some old tuners
+ * may require the usage of separate I2C chips to decode analog TV signals,
+ * when the master/bridge chipset doesn't have its own TV standard decoder.
+ * On such cases, the IF-PLL staging is mapped via one or two entities:
+ * MEDIA_ENT_F_IF_VID_DECODER and/or MEDIA_ENT_F_IF_AUD_DECODER.
  */
 #define MEDIA_ENT_F_TUNER		(MEDIA_ENT_F_OLD_SUBDEV_BASE + 5)
 
 #define MEDIA_ENT_F_V4L2_SUBDEV_UNKNOWN	MEDIA_ENT_F_OLD_SUBDEV_BASE
 
-#ifndef __KERNEL__
+#if !defined(__KERNEL__) || defined(__NEED_MEDIA_LEGACY_API)
 
 /*
  * Legacy symbols used to avoid userspace compilation breakages
@@ -127,6 +153,10 @@ struct media_device_info {
 #define MEDIA_ENT_TYPE_MASK		0x00ff0000
 #define MEDIA_ENT_SUBTYPE_MASK		0x0000ffff
 
+/* End of the old subdev reserved numberspace */
+#define MEDIA_ENT_T_DEVNODE_UNKNOWN	(MEDIA_ENT_T_DEVNODE | \
+					 MEDIA_ENT_SUBTYPE_MASK)
+
 #define MEDIA_ENT_T_DEVNODE		MEDIA_ENT_F_OLD_BASE
 #define MEDIA_ENT_T_DEVNODE_V4L		MEDIA_ENT_F_IO_V4L
 #define MEDIA_ENT_T_DEVNODE_FB		(MEDIA_ENT_T_DEVNODE + 2)
@@ -252,6 +282,7 @@ struct media_links_enum {
 
 #define MEDIA_INTF_T_DVB_BASE	0x00000100
 #define MEDIA_INTF_T_V4L_BASE	0x00000200
+#define MEDIA_INTF_T_ALSA_BASE	0x00000300
 
 /* Interface types */
 
@@ -267,6 +298,15 @@ struct media_links_enum {
 #define MEDIA_INTF_T_V4L_SUBDEV (MEDIA_INTF_T_V4L_BASE + 3)
 #define MEDIA_INTF_T_V4L_SWRADIO (MEDIA_INTF_T_V4L_BASE + 4)
 
+#define MEDIA_INTF_T_ALSA_PCM_CAPTURE   (MEDIA_INTF_T_ALSA_BASE)
+#define MEDIA_INTF_T_ALSA_PCM_PLAYBACK  (MEDIA_INTF_T_ALSA_BASE + 1)
+#define MEDIA_INTF_T_ALSA_CONTROL       (MEDIA_INTF_T_ALSA_BASE + 2)
+#define MEDIA_INTF_T_ALSA_COMPRESS      (MEDIA_INTF_T_ALSA_BASE + 3)
+#define MEDIA_INTF_T_ALSA_RAWMIDI       (MEDIA_INTF_T_ALSA_BASE + 4)
+#define MEDIA_INTF_T_ALSA_HWDEP         (MEDIA_INTF_T_ALSA_BASE + 5)
+#define MEDIA_INTF_T_ALSA_SEQUENCER     (MEDIA_INTF_T_ALSA_BASE + 6)
+#define MEDIA_INTF_T_ALSA_TIMER         (MEDIA_INTF_T_ALSA_BASE + 7)
+
 /*
  * MC next gen API definitions
  *
@@ -286,19 +326,19 @@ struct media_links_enum {
  *	  later, before the adding this API upstream.
  */
 
-#if 0 /* Let's postpone it to Kernel 4.6 */
+
 struct media_v2_entity {
 	__u32 id;
 	char name[64];		/* FIXME: move to a property? (RFC says so) */
 	__u32 function;		/* Main function of the entity */
-	__u16 reserved[12];
-};
+	__u32 reserved[6];
+} __attribute__ ((packed));
 
 /* Should match the specific fields at media_intf_devnode */
 struct media_v2_intf_devnode {
 	__u32 major;
 	__u32 minor;
-};
+} __attribute__ ((packed));
 
 struct media_v2_interface {
 	__u32 id;
@@ -310,22 +350,22 @@ struct media_v2_interface {
 		struct media_v2_intf_devnode devnode;
 		__u32 raw[16];
 	};
-};
+} __attribute__ ((packed));
 
 struct media_v2_pad {
 	__u32 id;
 	__u32 entity_id;
 	__u32 flags;
-	__u16 reserved[9];
-};
+	__u32 reserved[5];
+} __attribute__ ((packed));
 
 struct media_v2_link {
 	__u32 id;
 	__u32 source_id;
 	__u32 sink_id;
 	__u32 flags;
-	__u32 reserved[5];
-};
+	__u32 reserved[6];
+} __attribute__ ((packed));
 
 struct media_v2_topology {
 	__u64 topology_version;
@@ -345,13 +385,7 @@ struct media_v2_topology {
 	__u32 num_links;
 	__u32 reserved4;
 	__u64 ptr_links;
-};
-
-static inline void __user *media_get_uptr(__u64 arg)
-{
-	return (void __user *)(uintptr_t)arg;
-}
-#endif
+} __attribute__ ((packed));
 
 /* ioctls */
 
@@ -359,9 +393,6 @@ static inline void __user *media_get_uptr(__u64 arg)
 #define MEDIA_IOC_ENUM_ENTITIES		_IOWR('|', 0x01, struct media_entity_desc)
 #define MEDIA_IOC_ENUM_LINKS		_IOWR('|', 0x02, struct media_links_enum)
 #define MEDIA_IOC_SETUP_LINK		_IOWR('|', 0x03, struct media_link_desc)
-
-#if 0 /* Let's postpone it to Kernel 4.6 */
 #define MEDIA_IOC_G_TOPOLOGY		_IOWR('|', 0x04, struct media_v2_topology)
-#endif
 
 #endif /* __LINUX_MEDIA_H */
diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h
index 5b4a4be06e2b..7cc28ab05b87 100644
--- a/include/uapi/linux/ndctl.h
+++ b/include/uapi/linux/ndctl.h
@@ -66,14 +66,18 @@ struct nd_cmd_ars_cap {
 	__u64 length;
 	__u32 status;
 	__u32 max_ars_out;
+	__u32 clear_err_unit;
+	__u32 reserved;
 } __packed;
 
 struct nd_cmd_ars_start {
 	__u64 address;
 	__u64 length;
 	__u16 type;
-	__u8 reserved[6];
+	__u8 flags;
+	__u8 reserved[5];
 	__u32 status;
+	__u32 scrub_time;
 } __packed;
 
 struct nd_cmd_ars_status {
@@ -81,16 +85,27 @@ struct nd_cmd_ars_status {
 	__u32 out_length;
 	__u64 address;
 	__u64 length;
+	__u64 restart_address;
+	__u64 restart_length;
 	__u16 type;
+	__u16 flags;
 	__u32 num_records;
 	struct nd_ars_record {
 		__u32 handle;
-		__u32 flags;
+		__u32 reserved;
 		__u64 err_address;
 		__u64 length;
 	} __packed records[0];
 } __packed;
 
+struct nd_cmd_clear_error {
+	__u64 address;
+	__u64 length;
+	__u32 status;
+	__u8 reserved[4];
+	__u64 cleared;
+} __packed;
+
 enum {
 	ND_CMD_IMPLEMENTED = 0,
 
@@ -98,6 +113,7 @@ enum {
 	ND_CMD_ARS_CAP = 1,
 	ND_CMD_ARS_START = 2,
 	ND_CMD_ARS_STATUS = 3,
+	ND_CMD_CLEAR_ERROR = 4,
 
 	/* per-dimm commands */
 	ND_CMD_SMART = 1,
@@ -122,6 +138,7 @@ static inline const char *nvdimm_bus_cmd_name(unsigned cmd)
 		[ND_CMD_ARS_CAP] = "ars_cap",
 		[ND_CMD_ARS_START] = "ars_start",
 		[ND_CMD_ARS_STATUS] = "ars_status",
+		[ND_CMD_CLEAR_ERROR] = "clear_error",
 	};
 
 	if (cmd < ARRAY_SIZE(names) && names[cmd])
@@ -180,6 +197,9 @@ static inline const char *nvdimm_cmd_name(unsigned cmd)
 #define ND_IOCTL_ARS_STATUS		_IOWR(ND_IOCTL, ND_CMD_ARS_STATUS,\
 					struct nd_cmd_ars_status)
 
+#define ND_IOCTL_CLEAR_ERROR		_IOWR(ND_IOCTL, ND_CMD_CLEAR_ERROR,\
+					struct nd_cmd_clear_error)
+
 #define ND_DEVICE_DIMM 1            /* nd_dimm: container for "config data" */
 #define ND_DEVICE_REGION_PMEM 2     /* nd_region: (parent of PMEM namespaces) */
 #define ND_DEVICE_REGION_BLK 3      /* nd_region: (parent of BLK namespaces) */
diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h
index f0b7bfe5da92..ac6dded80ffa 100644
--- a/include/uapi/linux/ptp_clock.h
+++ b/include/uapi/linux/ptp_clock.h
@@ -51,7 +51,9 @@ struct ptp_clock_caps {
 	int n_per_out; /* Number of programmable periodic signals. */
 	int pps;       /* Whether the clock supports a PPS callback. */
 	int n_pins;    /* Number of input/output pins. */
-	int rsv[14];   /* Reserved for future use. */
+	/* Whether the clock supports precise system-device cross timestamps */
+	int cross_timestamping;
+	int rsv[13];   /* Reserved for future use. */
 };
 
 struct ptp_extts_request {
@@ -81,6 +83,13 @@ struct ptp_sys_offset {
 	struct ptp_clock_time ts[2 * PTP_MAX_SAMPLES + 1];
 };
 
+struct ptp_sys_offset_precise {
+	struct ptp_clock_time device;
+	struct ptp_clock_time sys_realtime;
+	struct ptp_clock_time sys_monoraw;
+	unsigned int rsv[4];    /* Reserved for future use. */
+};
+
 enum ptp_pin_function {
 	PTP_PF_NONE,
 	PTP_PF_EXTTS,
@@ -124,6 +133,8 @@ struct ptp_pin_desc {
 #define PTP_SYS_OFFSET     _IOW(PTP_CLK_MAGIC, 5, struct ptp_sys_offset)
 #define PTP_PIN_GETFUNC    _IOWR(PTP_CLK_MAGIC, 6, struct ptp_pin_desc)
 #define PTP_PIN_SETFUNC    _IOW(PTP_CLK_MAGIC, 7, struct ptp_pin_desc)
+#define PTP_SYS_OFFSET_PRECISE \
+	_IOWR(PTP_CLK_MAGIC, 8, struct ptp_sys_offset_precise)
 
 struct ptp_extts_event {
 	struct ptp_clock_time t; /* Time event occured. */
diff --git a/include/uapi/linux/v4l2-common.h b/include/uapi/linux/v4l2-common.h
index 15273987093e..5b3f685a2d50 100644
--- a/include/uapi/linux/v4l2-common.h
+++ b/include/uapi/linux/v4l2-common.h
@@ -10,19 +10,43 @@
  * Copyright (C) 2012 Nokia Corporation
  * Contact: Sakari Ailus <sakari.ailus@iki.fi>
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
  *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
+ *  Alternatively you can redistribute this file under the terms of the
+ *  BSD license as stated below:
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *  3. The names of its contributors may not be used to endorse or promote
+ *     products derived from this software without specific prior written
+ *     permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
+ *  TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+ *  PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  */
 
diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h
index 2d225bcdb831..b6a357a5f053 100644
--- a/include/uapi/linux/v4l2-controls.h
+++ b/include/uapi/linux/v4l2-controls.h
@@ -390,6 +390,7 @@ enum v4l2_mpeg_video_multi_slice_mode {
 #define V4L2_CID_MPEG_VIDEO_REPEAT_SEQ_HEADER		(V4L2_CID_MPEG_BASE+226)
 #define V4L2_CID_MPEG_VIDEO_MV_H_SEARCH_RANGE		(V4L2_CID_MPEG_BASE+227)
 #define V4L2_CID_MPEG_VIDEO_MV_V_SEARCH_RANGE		(V4L2_CID_MPEG_BASE+228)
+#define V4L2_CID_MPEG_VIDEO_FORCE_KEY_FRAME		(V4L2_CID_MPEG_BASE+229)
 
 #define V4L2_CID_MPEG_VIDEO_H263_I_FRAME_QP		(V4L2_CID_MPEG_BASE+300)
 #define V4L2_CID_MPEG_VIDEO_H263_P_FRAME_QP		(V4L2_CID_MPEG_BASE+301)
@@ -912,8 +913,18 @@ enum v4l2_dv_rgb_range {
 	V4L2_DV_RGB_RANGE_FULL	  = 2,
 };
 
+#define V4L2_CID_DV_TX_IT_CONTENT_TYPE		(V4L2_CID_DV_CLASS_BASE + 6)
+enum v4l2_dv_it_content_type {
+	V4L2_DV_IT_CONTENT_TYPE_GRAPHICS  = 0,
+	V4L2_DV_IT_CONTENT_TYPE_PHOTO	  = 1,
+	V4L2_DV_IT_CONTENT_TYPE_CINEMA	  = 2,
+	V4L2_DV_IT_CONTENT_TYPE_GAME	  = 3,
+	V4L2_DV_IT_CONTENT_TYPE_NO_ITC	  = 4,
+};
+
 #define	V4L2_CID_DV_RX_POWER_PRESENT		(V4L2_CID_DV_CLASS_BASE + 100)
 #define V4L2_CID_DV_RX_RGB_RANGE		(V4L2_CID_DV_CLASS_BASE + 101)
+#define V4L2_CID_DV_RX_IT_CONTENT_TYPE		(V4L2_CID_DV_CLASS_BASE + 102)
 
 #define V4L2_CID_FM_RX_CLASS_BASE		(V4L2_CTRL_CLASS_FM_RX | 0x900)
 #define V4L2_CID_FM_RX_CLASS			(V4L2_CTRL_CLASS_FM_RX | 1)
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 14cd5ebfee6d..e895975c5b0e 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -546,6 +546,10 @@ struct v4l2_pix_format {
 /* three non contiguous planes - Y, Cb, Cr */
 #define V4L2_PIX_FMT_YUV420M v4l2_fourcc('Y', 'M', '1', '2') /* 12  YUV420 planar */
 #define V4L2_PIX_FMT_YVU420M v4l2_fourcc('Y', 'M', '2', '1') /* 12  YVU420 planar */
+#define V4L2_PIX_FMT_YUV422M v4l2_fourcc('Y', 'M', '1', '6') /* 16  YUV422 planar */
+#define V4L2_PIX_FMT_YVU422M v4l2_fourcc('Y', 'M', '6', '1') /* 16  YVU422 planar */
+#define V4L2_PIX_FMT_YUV444M v4l2_fourcc('Y', 'M', '2', '4') /* 24  YUV444 planar */
+#define V4L2_PIX_FMT_YVU444M v4l2_fourcc('Y', 'M', '4', '2') /* 24  YVU444 planar */
 
 /* Bayer formats - see http://www.siliconimaging.com/RGB%20Bayer.htm */
 #define V4L2_PIX_FMT_SBGGR8  v4l2_fourcc('B', 'A', '8', '1') /*  8  BGBG.. GRGR.. */
@@ -621,6 +625,9 @@ struct v4l2_pix_format {
 #define V4L2_PIX_FMT_JPGL	v4l2_fourcc('J', 'P', 'G', 'L') /* JPEG-Lite */
 #define V4L2_PIX_FMT_SE401      v4l2_fourcc('S', '4', '0', '1') /* se401 janggu compressed rgb */
 #define V4L2_PIX_FMT_S5C_UYVY_JPG v4l2_fourcc('S', '5', 'C', 'I') /* S5C73M3 interleaved UYVY/JPEG */
+#define V4L2_PIX_FMT_Y8I      v4l2_fourcc('Y', '8', 'I', ' ') /* Greyscale 8-bit L/R interleaved */
+#define V4L2_PIX_FMT_Y12I     v4l2_fourcc('Y', '1', '2', 'I') /* Greyscale 12-bit L/R interleaved */
+#define V4L2_PIX_FMT_Z16      v4l2_fourcc('Z', '1', '6', ' ') /* Depth data 16-bit */
 
 /* SDR formats - used only for Software Defined Radio devices */
 #define V4L2_SDR_FMT_CU8          v4l2_fourcc('C', 'U', '0', '8') /* IQ u8 */
diff --git a/init/Kconfig b/init/Kconfig
index af4de4f1b02c..2d70c8c4b1d8 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1420,6 +1420,28 @@ config KALLSYMS_ALL
 
 	   Say N unless you really need all symbols.
 
+config KALLSYMS_ABSOLUTE_PERCPU
+	bool
+	default X86_64 && SMP
+
+config KALLSYMS_BASE_RELATIVE
+	bool
+	depends on KALLSYMS
+	default !IA64 && !(TILE && 64BIT)
+	help
+	  Instead of emitting them as absolute values in the native word size,
+	  emit the symbol references in the kallsyms table as 32-bit entries,
+	  each containing a relative value in the range [base, base + U32_MAX]
+	  or, when KALLSYMS_ABSOLUTE_PERCPU is in effect, each containing either
+	  an absolute value in the range [0, S32_MAX] or a relative value in the
+	  range [base, base + S32_MAX], where base is the lowest relative symbol
+	  address encountered in the image.
+
+	  On 64-bit builds, this reduces the size of the address table by 50%,
+	  but more importantly, it results in entries whose values are build
+	  time constants, and no relocation pass is required at runtime to fix
+	  up the entries based on the runtime load address of the kernel.
+
 config PRINTK
 	default y
 	bool "Enable support for printk" if EXPERT
diff --git a/init/main.c b/init/main.c
index 58c9e374704b..b3c6e363ae18 100644
--- a/init/main.c
+++ b/init/main.c
@@ -93,9 +93,6 @@ static int kernel_init(void *);
 extern void init_IRQ(void);
 extern void fork_init(void);
 extern void radix_tree_init(void);
-#ifndef CONFIG_DEBUG_RODATA
-static inline void mark_rodata_ro(void) { }
-#endif
 
 /*
  * Debug helper: via this flag we know that we are in 'early bootup code'
@@ -388,7 +385,6 @@ static noinline void __init_refok rest_init(void)
 	int pid;
 
 	rcu_scheduler_starting();
-	smpboot_thread_init();
 	/*
 	 * We need to spawn init first so that it obtains pid 1, however
 	 * the init task will end up wanting to create kthreads, which, if
@@ -452,20 +448,6 @@ void __init parse_early_param(void)
 	done = 1;
 }
 
-/*
- *	Activate the first processor.
- */
-
-static void __init boot_cpu_init(void)
-{
-	int cpu = smp_processor_id();
-	/* Mark the boot cpu "present", "online" etc for SMP and UP case */
-	set_cpu_online(cpu, true);
-	set_cpu_active(cpu, true);
-	set_cpu_present(cpu, true);
-	set_cpu_possible(cpu, true);
-}
-
 void __init __weak smp_setup_processor_id(void)
 {
 }
@@ -499,11 +481,6 @@ asmlinkage __visible void __init start_kernel(void)
 	char *command_line;
 	char *after_dashes;
 
-	/*
-	 * Need to run as early as possible, to initialize the
-	 * lockdep hash:
-	 */
-	lockdep_init();
 	set_task_stack_end_magic(&init_task);
 	smp_setup_processor_id();
 	debug_objects_early_init();
@@ -530,6 +507,7 @@ asmlinkage __visible void __init start_kernel(void)
 	setup_command_line(command_line);
 	setup_nr_cpu_ids();
 	setup_per_cpu_areas();
+	boot_cpu_state_init();
 	smp_prepare_boot_cpu();	/* arch-specific boot-cpu hooks */
 
 	build_all_zonelists(NULL, NULL);
@@ -727,7 +705,6 @@ static int __init initcall_blacklist(char *str)
 
 static bool __init_or_module initcall_blacklisted(initcall_t fn)
 {
-	struct list_head *tmp;
 	struct blacklist_entry *entry;
 	char *fn_name;
 
@@ -735,8 +712,7 @@ static bool __init_or_module initcall_blacklisted(initcall_t fn)
 	if (!fn_name)
 		return false;
 
-	list_for_each(tmp, &blacklisted_initcalls) {
-		entry = list_entry(tmp, struct blacklist_entry, next);
+	list_for_each_entry(entry, &blacklisted_initcalls, next) {
 		if (!strcmp(fn_name, entry->buf)) {
 			pr_debug("initcall %s blacklisted\n", fn_name);
 			kfree(fn_name);
@@ -929,6 +905,28 @@ static int try_to_run_init_process(const char *init_filename)
 
 static noinline void __init kernel_init_freeable(void);
 
+#ifdef CONFIG_DEBUG_RODATA
+static bool rodata_enabled = true;
+static int __init set_debug_rodata(char *str)
+{
+	return strtobool(str, &rodata_enabled);
+}
+__setup("rodata=", set_debug_rodata);
+
+static void mark_readonly(void)
+{
+	if (rodata_enabled)
+		mark_rodata_ro();
+	else
+		pr_info("Kernel memory protection disabled.\n");
+}
+#else
+static inline void mark_readonly(void)
+{
+	pr_warn("This architecture does not have kernel memory protection.\n");
+}
+#endif
+
 static int __ref kernel_init(void *unused)
 {
 	int ret;
@@ -937,7 +935,7 @@ static int __ref kernel_init(void *unused)
 	/* need to finish all async __init code before freeing the memory */
 	async_synchronize_full();
 	free_initmem();
-	mark_rodata_ro();
+	mark_readonly();
 	system_state = SYSTEM_RUNNING;
 	numa_default_policy();
 
diff --git a/ipc/shm.c b/ipc/shm.c
index ed3027d0f277..331fc1b0b3c7 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -156,11 +156,12 @@ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id)
 	struct kern_ipc_perm *ipcp = ipc_lock(&shm_ids(ns), id);
 
 	/*
-	 * We raced in the idr lookup or with shm_destroy().  Either way, the
-	 * ID is busted.
+	 * Callers of shm_lock() must validate the status of the returned ipc
+	 * object pointer (as returned by ipc_lock()), and error out as
+	 * appropriate.
 	 */
-	WARN_ON(IS_ERR(ipcp));
-
+	if (IS_ERR(ipcp))
+		return (void *)ipcp;
 	return container_of(ipcp, struct shmid_kernel, shm_perm);
 }
 
@@ -186,18 +187,33 @@ static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
 }
 
 
-/* This is called by fork, once for every shm attach. */
-static void shm_open(struct vm_area_struct *vma)
+static int __shm_open(struct vm_area_struct *vma)
 {
 	struct file *file = vma->vm_file;
 	struct shm_file_data *sfd = shm_file_data(file);
 	struct shmid_kernel *shp;
 
 	shp = shm_lock(sfd->ns, sfd->id);
+
+	if (IS_ERR(shp))
+		return PTR_ERR(shp);
+
 	shp->shm_atim = get_seconds();
 	shp->shm_lprid = task_tgid_vnr(current);
 	shp->shm_nattch++;
 	shm_unlock(shp);
+	return 0;
+}
+
+/* This is called by fork, once for every shm attach. */
+static void shm_open(struct vm_area_struct *vma)
+{
+	int err = __shm_open(vma);
+	/*
+	 * We raced in the idr lookup or with shm_destroy().
+	 * Either way, the ID is busted.
+	 */
+	WARN_ON_ONCE(err);
 }
 
 /*
@@ -260,6 +276,14 @@ static void shm_close(struct vm_area_struct *vma)
 	down_write(&shm_ids(ns).rwsem);
 	/* remove from the list of attaches of the shm segment */
 	shp = shm_lock(ns, sfd->id);
+
+	/*
+	 * We raced in the idr lookup or with shm_destroy().
+	 * Either way, the ID is busted.
+	 */
+	if (WARN_ON_ONCE(IS_ERR(shp)))
+		goto done; /* no-op */
+
 	shp->shm_lprid = task_tgid_vnr(current);
 	shp->shm_dtim = get_seconds();
 	shp->shm_nattch--;
@@ -267,6 +291,7 @@ static void shm_close(struct vm_area_struct *vma)
 		shm_destroy(ns, shp);
 	else
 		shm_unlock(shp);
+done:
 	up_write(&shm_ids(ns).rwsem);
 }
 
@@ -388,17 +413,25 @@ static int shm_mmap(struct file *file, struct vm_area_struct *vma)
 	struct shm_file_data *sfd = shm_file_data(file);
 	int ret;
 
+	/*
+	 * In case of remap_file_pages() emulation, the file can represent
+	 * removed IPC ID: propogate shm_lock() error to caller.
+	 */
+	ret =__shm_open(vma);
+	if (ret)
+		return ret;
+
 	ret = sfd->file->f_op->mmap(sfd->file, vma);
-	if (ret != 0)
+	if (ret) {
+		shm_close(vma);
 		return ret;
+	}
 	sfd->vm_ops = vma->vm_ops;
 #ifdef CONFIG_MMU
 	WARN_ON(!sfd->vm_ops->fault);
 #endif
 	vma->vm_ops = &shm_vm_ops;
-	shm_open(vma);
-
-	return ret;
+	return 0;
 }
 
 static int shm_release(struct inode *ino, struct file *file)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d1d3e8f57de9..2e7f7ab739e4 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2082,7 +2082,7 @@ static void adjust_branches(struct bpf_prog *prog, int pos, int delta)
 		/* adjust offset of jmps if necessary */
 		if (i < pos && i + insn->off + 1 > pos)
 			insn->off += delta;
-		else if (i > pos && i + insn->off + 1 < pos)
+		else if (i > pos + delta && i + insn->off + 1 <= pos + delta)
 			insn->off -= delta;
 	}
 }
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c03a640ef6da..d27904c193da 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -58,6 +58,7 @@
 #include <linux/kthread.h>
 #include <linux/delay.h>
 #include <linux/atomic.h>
+#include <linux/cpuset.h>
 #include <net/sock.h>
 
 /*
@@ -2739,6 +2740,7 @@ out_unlock_rcu:
 out_unlock_threadgroup:
 	percpu_up_write(&cgroup_threadgroup_rwsem);
 	cgroup_kn_unlock(of->kn);
+	cpuset_post_attach_flush();
 	return ret ?: nbytes;
 }
 
@@ -4655,14 +4657,15 @@ static void css_free_work_fn(struct work_struct *work)
 
 	if (ss) {
 		/* css free path */
+		struct cgroup_subsys_state *parent = css->parent;
 		int id = css->id;
 
-		if (css->parent)
-			css_put(css->parent);
-
 		ss->css_free(css);
 		cgroup_idr_remove(&ss->css_idr, id);
 		cgroup_put(cgrp);
+
+		if (parent)
+			css_put(parent);
 	} else {
 		/* cgroup free path */
 		atomic_dec(&cgrp->root->nr_cgrps);
@@ -4758,6 +4761,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 	INIT_LIST_HEAD(&css->sibling);
 	INIT_LIST_HEAD(&css->children);
 	css->serial_nr = css_serial_nr_next++;
+	atomic_set(&css->online_cnt, 0);
 
 	if (cgroup_parent(cgrp)) {
 		css->parent = cgroup_css(cgroup_parent(cgrp), ss);
@@ -4780,6 +4784,10 @@ static int online_css(struct cgroup_subsys_state *css)
 	if (!ret) {
 		css->flags |= CSS_ONLINE;
 		rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
+
+		atomic_inc(&css->online_cnt);
+		if (css->parent)
+			atomic_inc(&css->parent->online_cnt);
 	}
 	return ret;
 }
@@ -5017,10 +5025,15 @@ static void css_killed_work_fn(struct work_struct *work)
 		container_of(work, struct cgroup_subsys_state, destroy_work);
 
 	mutex_lock(&cgroup_mutex);
-	offline_css(css);
-	mutex_unlock(&cgroup_mutex);
 
-	css_put(css);
+	do {
+		offline_css(css);
+		css_put(css);
+		/* @css can't go away while we're holding cgroup_mutex */
+		css = css->parent;
+	} while (css && atomic_dec_and_test(&css->online_cnt));
+
+	mutex_unlock(&cgroup_mutex);
 }
 
 /* css kill confirmation processing requires process context, bounce */
@@ -5029,8 +5042,10 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
 	struct cgroup_subsys_state *css =
 		container_of(ref, struct cgroup_subsys_state, refcnt);
 
-	INIT_WORK(&css->destroy_work, css_killed_work_fn);
-	queue_work(cgroup_destroy_wq, &css->destroy_work);
+	if (atomic_dec_and_test(&css->online_cnt)) {
+		INIT_WORK(&css->destroy_work, css_killed_work_fn);
+		queue_work(cgroup_destroy_wq, &css->destroy_work);
+	}
 }
 
 /**
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 5b9d39633ce9..6ea42e8da861 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -22,13 +22,88 @@
 #include <linux/lockdep.h>
 #include <linux/tick.h>
 #include <linux/irq.h>
+#include <linux/smpboot.h>
+
 #include <trace/events/power.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/cpuhp.h>
 
 #include "smpboot.h"
 
+/**
+ * cpuhp_cpu_state - Per cpu hotplug state storage
+ * @state:	The current cpu state
+ * @target:	The target state
+ * @thread:	Pointer to the hotplug thread
+ * @should_run:	Thread should execute
+ * @cb_stat:	The state for a single callback (install/uninstall)
+ * @cb:		Single callback function (install/uninstall)
+ * @result:	Result of the operation
+ * @done:	Signal completion to the issuer of the task
+ */
+struct cpuhp_cpu_state {
+	enum cpuhp_state	state;
+	enum cpuhp_state	target;
+#ifdef CONFIG_SMP
+	struct task_struct	*thread;
+	bool			should_run;
+	enum cpuhp_state	cb_state;
+	int			(*cb)(unsigned int cpu);
+	int			result;
+	struct completion	done;
+#endif
+};
+
+static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state);
+
+/**
+ * cpuhp_step - Hotplug state machine step
+ * @name:	Name of the step
+ * @startup:	Startup function of the step
+ * @teardown:	Teardown function of the step
+ * @skip_onerr:	Do not invoke the functions on error rollback
+ *		Will go away once the notifiers	are gone
+ * @cant_stop:	Bringup/teardown can't be stopped at this step
+ */
+struct cpuhp_step {
+	const char	*name;
+	int		(*startup)(unsigned int cpu);
+	int		(*teardown)(unsigned int cpu);
+	bool		skip_onerr;
+	bool		cant_stop;
+};
+
+static DEFINE_MUTEX(cpuhp_state_mutex);
+static struct cpuhp_step cpuhp_bp_states[];
+static struct cpuhp_step cpuhp_ap_states[];
+
+/**
+ * cpuhp_invoke_callback _ Invoke the callbacks for a given state
+ * @cpu:	The cpu for which the callback should be invoked
+ * @step:	The step in the state machine
+ * @cb:		The callback function to invoke
+ *
+ * Called from cpu hotplug and from the state register machinery
+ */
+static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state step,
+				 int (*cb)(unsigned int))
+{
+	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+	int ret = 0;
+
+	if (cb) {
+		trace_cpuhp_enter(cpu, st->target, step, cb);
+		ret = cb(cpu);
+		trace_cpuhp_exit(cpu, st->state, step, ret);
+	}
+	return ret;
+}
+
 #ifdef CONFIG_SMP
 /* Serializes the updates to cpu_online_mask, cpu_present_mask */
 static DEFINE_MUTEX(cpu_add_remove_lock);
+bool cpuhp_tasks_frozen;
+EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen);
 
 /*
  * The following two APIs (cpu_maps_update_begin/done) must be used when
@@ -207,31 +282,281 @@ int __register_cpu_notifier(struct notifier_block *nb)
 	return raw_notifier_chain_register(&cpu_chain, nb);
 }
 
-static int __cpu_notify(unsigned long val, void *v, int nr_to_call,
+static int __cpu_notify(unsigned long val, unsigned int cpu, int nr_to_call,
 			int *nr_calls)
 {
+	unsigned long mod = cpuhp_tasks_frozen ? CPU_TASKS_FROZEN : 0;
+	void *hcpu = (void *)(long)cpu;
+
 	int ret;
 
-	ret = __raw_notifier_call_chain(&cpu_chain, val, v, nr_to_call,
+	ret = __raw_notifier_call_chain(&cpu_chain, val | mod, hcpu, nr_to_call,
 					nr_calls);
 
 	return notifier_to_errno(ret);
 }
 
-static int cpu_notify(unsigned long val, void *v)
+static int cpu_notify(unsigned long val, unsigned int cpu)
 {
-	return __cpu_notify(val, v, -1, NULL);
+	return __cpu_notify(val, cpu, -1, NULL);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
+/* Notifier wrappers for transitioning to state machine */
+static int notify_prepare(unsigned int cpu)
+{
+	int nr_calls = 0;
+	int ret;
+
+	ret = __cpu_notify(CPU_UP_PREPARE, cpu, -1, &nr_calls);
+	if (ret) {
+		nr_calls--;
+		printk(KERN_WARNING "%s: attempt to bring up CPU %u failed\n",
+				__func__, cpu);
+		__cpu_notify(CPU_UP_CANCELED, cpu, nr_calls, NULL);
+	}
+	return ret;
+}
+
+static int notify_online(unsigned int cpu)
+{
+	cpu_notify(CPU_ONLINE, cpu);
+	return 0;
+}
+
+static int notify_starting(unsigned int cpu)
+{
+	cpu_notify(CPU_STARTING, cpu);
+	return 0;
+}
+
+static int bringup_wait_for_ap(unsigned int cpu)
+{
+	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+
+	wait_for_completion(&st->done);
+	return st->result;
+}
+
+static int bringup_cpu(unsigned int cpu)
+{
+	struct task_struct *idle = idle_thread_get(cpu);
+	int ret;
+
+	/* Arch-specific enabling code. */
+	ret = __cpu_up(cpu, idle);
+	if (ret) {
+		cpu_notify(CPU_UP_CANCELED, cpu);
+		return ret;
+	}
+	ret = bringup_wait_for_ap(cpu);
+	BUG_ON(!cpu_online(cpu));
+	return ret;
+}
+
+/*
+ * Hotplug state machine related functions
+ */
+static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st,
+			  struct cpuhp_step *steps)
+{
+	for (st->state++; st->state < st->target; st->state++) {
+		struct cpuhp_step *step = steps + st->state;
+
+		if (!step->skip_onerr)
+			cpuhp_invoke_callback(cpu, st->state, step->startup);
+	}
+}
+
+static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
+				struct cpuhp_step *steps, enum cpuhp_state target)
+{
+	enum cpuhp_state prev_state = st->state;
+	int ret = 0;
+
+	for (; st->state > target; st->state--) {
+		struct cpuhp_step *step = steps + st->state;
+
+		ret = cpuhp_invoke_callback(cpu, st->state, step->teardown);
+		if (ret) {
+			st->target = prev_state;
+			undo_cpu_down(cpu, st, steps);
+			break;
+		}
+	}
+	return ret;
+}
+
+static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st,
+			struct cpuhp_step *steps)
+{
+	for (st->state--; st->state > st->target; st->state--) {
+		struct cpuhp_step *step = steps + st->state;
+
+		if (!step->skip_onerr)
+			cpuhp_invoke_callback(cpu, st->state, step->teardown);
+	}
+}
+
+static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
+			      struct cpuhp_step *steps, enum cpuhp_state target)
+{
+	enum cpuhp_state prev_state = st->state;
+	int ret = 0;
+
+	while (st->state < target) {
+		struct cpuhp_step *step;
+
+		st->state++;
+		step = steps + st->state;
+		ret = cpuhp_invoke_callback(cpu, st->state, step->startup);
+		if (ret) {
+			st->target = prev_state;
+			undo_cpu_up(cpu, st, steps);
+			break;
+		}
+	}
+	return ret;
+}
+
+/*
+ * The cpu hotplug threads manage the bringup and teardown of the cpus
+ */
+static void cpuhp_create(unsigned int cpu)
+{
+	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+
+	init_completion(&st->done);
+}
+
+static int cpuhp_should_run(unsigned int cpu)
+{
+	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
+
+	return st->should_run;
+}
+
+/* Execute the teardown callbacks. Used to be CPU_DOWN_PREPARE */
+static int cpuhp_ap_offline(unsigned int cpu, struct cpuhp_cpu_state *st)
+{
+	enum cpuhp_state target = max((int)st->target, CPUHP_TEARDOWN_CPU);
+
+	return cpuhp_down_callbacks(cpu, st, cpuhp_ap_states, target);
+}
+
+/* Execute the online startup callbacks. Used to be CPU_ONLINE */
+static int cpuhp_ap_online(unsigned int cpu, struct cpuhp_cpu_state *st)
+{
+	return cpuhp_up_callbacks(cpu, st, cpuhp_ap_states, st->target);
+}
+
+/*
+ * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke
+ * callbacks when a state gets [un]installed at runtime.
+ */
+static void cpuhp_thread_fun(unsigned int cpu)
+{
+	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
+	int ret = 0;
+
+	/*
+	 * Paired with the mb() in cpuhp_kick_ap_work and
+	 * cpuhp_invoke_ap_callback, so the work set is consistent visible.
+	 */
+	smp_mb();
+	if (!st->should_run)
+		return;
+
+	st->should_run = false;
+
+	/* Single callback invocation for [un]install ? */
+	if (st->cb) {
+		if (st->cb_state < CPUHP_AP_ONLINE) {
+			local_irq_disable();
+			ret = cpuhp_invoke_callback(cpu, st->cb_state, st->cb);
+			local_irq_enable();
+		} else {
+			ret = cpuhp_invoke_callback(cpu, st->cb_state, st->cb);
+		}
+	} else {
+		/* Cannot happen .... */
+		BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
+
+		/* Regular hotplug work */
+		if (st->state < st->target)
+			ret = cpuhp_ap_online(cpu, st);
+		else if (st->state > st->target)
+			ret = cpuhp_ap_offline(cpu, st);
+	}
+	st->result = ret;
+	complete(&st->done);
+}
 
-static void cpu_notify_nofail(unsigned long val, void *v)
+/* Invoke a single callback on a remote cpu */
+static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state,
+				    int (*cb)(unsigned int))
 {
-	BUG_ON(cpu_notify(val, v));
+	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+
+	if (!cpu_online(cpu))
+		return 0;
+
+	st->cb_state = state;
+	st->cb = cb;
+	/*
+	 * Make sure the above stores are visible before should_run becomes
+	 * true. Paired with the mb() above in cpuhp_thread_fun()
+	 */
+	smp_mb();
+	st->should_run = true;
+	wake_up_process(st->thread);
+	wait_for_completion(&st->done);
+	return st->result;
 }
+
+/* Regular hotplug invocation of the AP hotplug thread */
+static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st)
+{
+	st->result = 0;
+	st->cb = NULL;
+	/*
+	 * Make sure the above stores are visible before should_run becomes
+	 * true. Paired with the mb() above in cpuhp_thread_fun()
+	 */
+	smp_mb();
+	st->should_run = true;
+	wake_up_process(st->thread);
+}
+
+static int cpuhp_kick_ap_work(unsigned int cpu)
+{
+	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+	enum cpuhp_state state = st->state;
+
+	trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work);
+	__cpuhp_kick_ap_work(st);
+	wait_for_completion(&st->done);
+	trace_cpuhp_exit(cpu, st->state, state, st->result);
+	return st->result;
+}
+
+static struct smp_hotplug_thread cpuhp_threads = {
+	.store			= &cpuhp_state.thread,
+	.create			= &cpuhp_create,
+	.thread_should_run	= cpuhp_should_run,
+	.thread_fn		= cpuhp_thread_fun,
+	.thread_comm		= "cpuhp/%u",
+	.selfparking		= true,
+};
+
+void __init cpuhp_threads_init(void)
+{
+	BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads));
+	kthread_unpark(this_cpu_read(cpuhp_state.thread));
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
 EXPORT_SYMBOL(register_cpu_notifier);
 EXPORT_SYMBOL(__register_cpu_notifier);
-
 void unregister_cpu_notifier(struct notifier_block *nb)
 {
 	cpu_maps_update_begin();
@@ -311,57 +636,60 @@ static inline void check_for_tasks(int dead_cpu)
 	read_unlock(&tasklist_lock);
 }
 
-struct take_cpu_down_param {
-	unsigned long mod;
-	void *hcpu;
-};
+static void cpu_notify_nofail(unsigned long val, unsigned int cpu)
+{
+	BUG_ON(cpu_notify(val, cpu));
+}
+
+static int notify_down_prepare(unsigned int cpu)
+{
+	int err, nr_calls = 0;
+
+	err = __cpu_notify(CPU_DOWN_PREPARE, cpu, -1, &nr_calls);
+	if (err) {
+		nr_calls--;
+		__cpu_notify(CPU_DOWN_FAILED, cpu, nr_calls, NULL);
+		pr_warn("%s: attempt to take down CPU %u failed\n",
+				__func__, cpu);
+	}
+	return err;
+}
+
+static int notify_dying(unsigned int cpu)
+{
+	cpu_notify(CPU_DYING, cpu);
+	return 0;
+}
 
 /* Take this CPU down. */
 static int take_cpu_down(void *_param)
 {
-	struct take_cpu_down_param *param = _param;
-	int err;
+	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
+	enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE);
+	int err, cpu = smp_processor_id();
 
 	/* Ensure this CPU doesn't handle any more interrupts. */
 	err = __cpu_disable();
 	if (err < 0)
 		return err;
 
-	cpu_notify(CPU_DYING | param->mod, param->hcpu);
+	/* Invoke the former CPU_DYING callbacks */
+	for (; st->state > target; st->state--) {
+		struct cpuhp_step *step = cpuhp_ap_states + st->state;
+
+		cpuhp_invoke_callback(cpu, st->state, step->teardown);
+	}
 	/* Give up timekeeping duties */
 	tick_handover_do_timer();
 	/* Park the stopper thread */
-	stop_machine_park((long)param->hcpu);
+	stop_machine_park(cpu);
 	return 0;
 }
 
-/* Requires cpu_add_remove_lock to be held */
-static int _cpu_down(unsigned int cpu, int tasks_frozen)
+static int takedown_cpu(unsigned int cpu)
 {
-	int err, nr_calls = 0;
-	void *hcpu = (void *)(long)cpu;
-	unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
-	struct take_cpu_down_param tcd_param = {
-		.mod = mod,
-		.hcpu = hcpu,
-	};
-
-	if (num_online_cpus() == 1)
-		return -EBUSY;
-
-	if (!cpu_online(cpu))
-		return -EINVAL;
-
-	cpu_hotplug_begin();
-
-	err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls);
-	if (err) {
-		nr_calls--;
-		__cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL);
-		pr_warn("%s: attempt to take down CPU %u failed\n",
-			__func__, cpu);
-		goto out_release;
-	}
+	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+	int err;
 
 	/*
 	 * By now we've cleared cpu_active_mask, wait for all preempt-disabled
@@ -378,6 +706,8 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen)
 	else
 		synchronize_rcu();
 
+	/* Park the smpboot threads */
+	kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread);
 	smpboot_park_threads(cpu);
 
 	/*
@@ -389,12 +719,12 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen)
 	/*
 	 * So now all preempt/rcu users must observe !cpu_active().
 	 */
-	err = stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
+	err = stop_machine(take_cpu_down, NULL, cpumask_of(cpu));
 	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
-		cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
+		cpu_notify_nofail(CPU_DOWN_FAILED, cpu);
 		irq_unlock_sparse();
-		goto out_release;
+		return err;
 	}
 	BUG_ON(cpu_online(cpu));
 
@@ -405,10 +735,8 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen)
 	 *
 	 * Wait for the stop thread to go away.
 	 */
-	while (!per_cpu(cpu_dead_idle, cpu))
-		cpu_relax();
-	smp_mb(); /* Read from cpu_dead_idle before __cpu_die(). */
-	per_cpu(cpu_dead_idle, cpu) = false;
+	wait_for_completion(&st->done);
+	BUG_ON(st->state != CPUHP_AP_IDLE_DEAD);
 
 	/* Interrupts are moved away from the dying cpu, reenable alloc/free */
 	irq_unlock_sparse();
@@ -417,20 +745,104 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen)
 	/* This actually kills the CPU. */
 	__cpu_die(cpu);
 
-	/* CPU is completely dead: tell everyone.  Too late to complain. */
 	tick_cleanup_dead_cpu(cpu);
-	cpu_notify_nofail(CPU_DEAD | mod, hcpu);
+	return 0;
+}
 
+static int notify_dead(unsigned int cpu)
+{
+	cpu_notify_nofail(CPU_DEAD, cpu);
 	check_for_tasks(cpu);
+	return 0;
+}
 
-out_release:
+static void cpuhp_complete_idle_dead(void *arg)
+{
+	struct cpuhp_cpu_state *st = arg;
+
+	complete(&st->done);
+}
+
+void cpuhp_report_idle_dead(void)
+{
+	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
+
+	BUG_ON(st->state != CPUHP_AP_OFFLINE);
+	rcu_report_dead(smp_processor_id());
+	st->state = CPUHP_AP_IDLE_DEAD;
+	/*
+	 * We cannot call complete after rcu_report_dead() so we delegate it
+	 * to an online cpu.
+	 */
+	smp_call_function_single(cpumask_first(cpu_online_mask),
+				 cpuhp_complete_idle_dead, st, 0);
+}
+
+#else
+#define notify_down_prepare	NULL
+#define takedown_cpu		NULL
+#define notify_dead		NULL
+#define notify_dying		NULL
+#endif
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/* Requires cpu_add_remove_lock to be held */
+static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
+			   enum cpuhp_state target)
+{
+	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+	int prev_state, ret = 0;
+	bool hasdied = false;
+
+	if (num_online_cpus() == 1)
+		return -EBUSY;
+
+	if (!cpu_present(cpu))
+		return -EINVAL;
+
+	cpu_hotplug_begin();
+
+	cpuhp_tasks_frozen = tasks_frozen;
+
+	prev_state = st->state;
+	st->target = target;
+	/*
+	 * If the current CPU state is in the range of the AP hotplug thread,
+	 * then we need to kick the thread.
+	 */
+	if (st->state > CPUHP_TEARDOWN_CPU) {
+		ret = cpuhp_kick_ap_work(cpu);
+		/*
+		 * The AP side has done the error rollback already. Just
+		 * return the error code..
+		 */
+		if (ret)
+			goto out;
+
+		/*
+		 * We might have stopped still in the range of the AP hotplug
+		 * thread. Nothing to do anymore.
+		 */
+		if (st->state > CPUHP_TEARDOWN_CPU)
+			goto out;
+	}
+	/*
+	 * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need
+	 * to do the further cleanups.
+	 */
+	ret = cpuhp_down_callbacks(cpu, st, cpuhp_bp_states, target);
+
+	hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE;
+out:
 	cpu_hotplug_done();
-	if (!err)
-		cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu);
-	return err;
+	/* This post dead nonsense must die */
+	if (!ret && hasdied)
+		cpu_notify_nofail(CPU_POST_DEAD, cpu);
+	return ret;
 }
 
-int cpu_down(unsigned int cpu)
+static int do_cpu_down(unsigned int cpu, enum cpuhp_state target)
 {
 	int err;
 
@@ -441,100 +853,131 @@ int cpu_down(unsigned int cpu)
 		goto out;
 	}
 
-	err = _cpu_down(cpu, 0);
+	err = _cpu_down(cpu, 0, target);
 
 out:
 	cpu_maps_update_done();
 	return err;
 }
+int cpu_down(unsigned int cpu)
+{
+	return do_cpu_down(cpu, CPUHP_OFFLINE);
+}
 EXPORT_SYMBOL(cpu_down);
 #endif /*CONFIG_HOTPLUG_CPU*/
 
-/*
- * Unpark per-CPU smpboot kthreads at CPU-online time.
+/**
+ * notify_cpu_starting(cpu) - call the CPU_STARTING notifiers
+ * @cpu: cpu that just started
+ *
+ * This function calls the cpu_chain notifiers with CPU_STARTING.
+ * It must be called by the arch code on the new cpu, before the new cpu
+ * enables interrupts and before the "boot" cpu returns from __cpu_up().
  */
-static int smpboot_thread_call(struct notifier_block *nfb,
-			       unsigned long action, void *hcpu)
+void notify_cpu_starting(unsigned int cpu)
 {
-	int cpu = (long)hcpu;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
+	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+	enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE);
 
-	case CPU_DOWN_FAILED:
-	case CPU_ONLINE:
-		smpboot_unpark_threads(cpu);
-		break;
+	while (st->state < target) {
+		struct cpuhp_step *step;
 
-	default:
-		break;
+		st->state++;
+		step = cpuhp_ap_states + st->state;
+		cpuhp_invoke_callback(cpu, st->state, step->startup);
 	}
-
-	return NOTIFY_OK;
 }
 
-static struct notifier_block smpboot_thread_notifier = {
-	.notifier_call = smpboot_thread_call,
-	.priority = CPU_PRI_SMPBOOT,
-};
-
-void smpboot_thread_init(void)
+/*
+ * Called from the idle task. We need to set active here, so we can kick off
+ * the stopper thread and unpark the smpboot threads. If the target state is
+ * beyond CPUHP_AP_ONLINE_IDLE we kick cpuhp thread and let it bring up the
+ * cpu further.
+ */
+void cpuhp_online_idle(enum cpuhp_state state)
 {
-	register_cpu_notifier(&smpboot_thread_notifier);
+	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
+	unsigned int cpu = smp_processor_id();
+
+	/* Happens for the boot cpu */
+	if (state != CPUHP_AP_ONLINE_IDLE)
+		return;
+
+	st->state = CPUHP_AP_ONLINE_IDLE;
+
+	/* The cpu is marked online, set it active now */
+	set_cpu_active(cpu, true);
+	/* Unpark the stopper thread and the hotplug thread of this cpu */
+	stop_machine_unpark(cpu);
+	kthread_unpark(st->thread);
+
+	/* Should we go further up ? */
+	if (st->target > CPUHP_AP_ONLINE_IDLE)
+		__cpuhp_kick_ap_work(st);
+	else
+		complete(&st->done);
 }
 
 /* Requires cpu_add_remove_lock to be held */
-static int _cpu_up(unsigned int cpu, int tasks_frozen)
+static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target)
 {
-	int ret, nr_calls = 0;
-	void *hcpu = (void *)(long)cpu;
-	unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
+	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
 	struct task_struct *idle;
+	int ret = 0;
 
 	cpu_hotplug_begin();
 
-	if (cpu_online(cpu) || !cpu_present(cpu)) {
+	if (!cpu_present(cpu)) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	idle = idle_thread_get(cpu);
-	if (IS_ERR(idle)) {
-		ret = PTR_ERR(idle);
-		goto out;
-	}
-
-	ret = smpboot_create_threads(cpu);
-	if (ret)
+	/*
+	 * The caller of do_cpu_up might have raced with another
+	 * caller. Ignore it for now.
+	 */
+	if (st->state >= target)
 		goto out;
 
-	ret = __cpu_notify(CPU_UP_PREPARE | mod, hcpu, -1, &nr_calls);
-	if (ret) {
-		nr_calls--;
-		pr_warn("%s: attempt to bring up CPU %u failed\n",
-			__func__, cpu);
-		goto out_notify;
+	if (st->state == CPUHP_OFFLINE) {
+		/* Let it fail before we try to bring the cpu up */
+		idle = idle_thread_get(cpu);
+		if (IS_ERR(idle)) {
+			ret = PTR_ERR(idle);
+			goto out;
+		}
 	}
 
-	/* Arch-specific enabling code. */
-	ret = __cpu_up(cpu, idle);
-
-	if (ret != 0)
-		goto out_notify;
-	BUG_ON(!cpu_online(cpu));
+	cpuhp_tasks_frozen = tasks_frozen;
 
-	/* Now call notifier in preparation. */
-	cpu_notify(CPU_ONLINE | mod, hcpu);
+	st->target = target;
+	/*
+	 * If the current CPU state is in the range of the AP hotplug thread,
+	 * then we need to kick the thread once more.
+	 */
+	if (st->state > CPUHP_BRINGUP_CPU) {
+		ret = cpuhp_kick_ap_work(cpu);
+		/*
+		 * The AP side has done the error rollback already. Just
+		 * return the error code..
+		 */
+		if (ret)
+			goto out;
+	}
 
-out_notify:
-	if (ret != 0)
-		__cpu_notify(CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL);
+	/*
+	 * Try to reach the target state. We max out on the BP at
+	 * CPUHP_BRINGUP_CPU. After that the AP hotplug thread is
+	 * responsible for bringing it up to the target state.
+	 */
+	target = min((int)target, CPUHP_BRINGUP_CPU);
+	ret = cpuhp_up_callbacks(cpu, st, cpuhp_bp_states, target);
 out:
 	cpu_hotplug_done();
-
 	return ret;
 }
 
-int cpu_up(unsigned int cpu)
+static int do_cpu_up(unsigned int cpu, enum cpuhp_state target)
 {
 	int err = 0;
 
@@ -558,12 +1001,16 @@ int cpu_up(unsigned int cpu)
 		goto out;
 	}
 
-	err = _cpu_up(cpu, 0);
-
+	err = _cpu_up(cpu, 0, target);
 out:
 	cpu_maps_update_done();
 	return err;
 }
+
+int cpu_up(unsigned int cpu)
+{
+	return do_cpu_up(cpu, CPUHP_ONLINE);
+}
 EXPORT_SYMBOL_GPL(cpu_up);
 
 #ifdef CONFIG_PM_SLEEP_SMP
@@ -586,7 +1033,7 @@ int disable_nonboot_cpus(void)
 		if (cpu == first_cpu)
 			continue;
 		trace_suspend_resume(TPS("CPU_OFF"), cpu, true);
-		error = _cpu_down(cpu, 1);
+		error = _cpu_down(cpu, 1, CPUHP_OFFLINE);
 		trace_suspend_resume(TPS("CPU_OFF"), cpu, false);
 		if (!error)
 			cpumask_set_cpu(cpu, frozen_cpus);
@@ -636,7 +1083,7 @@ void enable_nonboot_cpus(void)
 
 	for_each_cpu(cpu, frozen_cpus) {
 		trace_suspend_resume(TPS("CPU_ON"), cpu, true);
-		error = _cpu_up(cpu, 1);
+		error = _cpu_up(cpu, 1, CPUHP_ONLINE);
 		trace_suspend_resume(TPS("CPU_ON"), cpu, false);
 		if (!error) {
 			pr_info("CPU%d is up\n", cpu);
@@ -709,26 +1156,463 @@ core_initcall(cpu_hotplug_pm_sync_init);
 
 #endif /* CONFIG_PM_SLEEP_SMP */
 
+#endif /* CONFIG_SMP */
+
+/* Boot processor state steps */
+static struct cpuhp_step cpuhp_bp_states[] = {
+	[CPUHP_OFFLINE] = {
+		.name			= "offline",
+		.startup		= NULL,
+		.teardown		= NULL,
+	},
+#ifdef CONFIG_SMP
+	[CPUHP_CREATE_THREADS]= {
+		.name			= "threads:create",
+		.startup		= smpboot_create_threads,
+		.teardown		= NULL,
+		.cant_stop		= true,
+	},
+	/*
+	 * Preparatory and dead notifiers. Will be replaced once the notifiers
+	 * are converted to states.
+	 */
+	[CPUHP_NOTIFY_PREPARE] = {
+		.name			= "notify:prepare",
+		.startup		= notify_prepare,
+		.teardown		= notify_dead,
+		.skip_onerr		= true,
+		.cant_stop		= true,
+	},
+	/* Kicks the plugged cpu into life */
+	[CPUHP_BRINGUP_CPU] = {
+		.name			= "cpu:bringup",
+		.startup		= bringup_cpu,
+		.teardown		= NULL,
+		.cant_stop		= true,
+	},
+	/*
+	 * Handled on controll processor until the plugged processor manages
+	 * this itself.
+	 */
+	[CPUHP_TEARDOWN_CPU] = {
+		.name			= "cpu:teardown",
+		.startup		= NULL,
+		.teardown		= takedown_cpu,
+		.cant_stop		= true,
+	},
+#endif
+};
+
+/* Application processor state steps */
+static struct cpuhp_step cpuhp_ap_states[] = {
+#ifdef CONFIG_SMP
+	/* Final state before CPU kills itself */
+	[CPUHP_AP_IDLE_DEAD] = {
+		.name			= "idle:dead",
+	},
+	/*
+	 * Last state before CPU enters the idle loop to die. Transient state
+	 * for synchronization.
+	 */
+	[CPUHP_AP_OFFLINE] = {
+		.name			= "ap:offline",
+		.cant_stop		= true,
+	},
+	/*
+	 * Low level startup/teardown notifiers. Run with interrupts
+	 * disabled. Will be removed once the notifiers are converted to
+	 * states.
+	 */
+	[CPUHP_AP_NOTIFY_STARTING] = {
+		.name			= "notify:starting",
+		.startup		= notify_starting,
+		.teardown		= notify_dying,
+		.skip_onerr		= true,
+		.cant_stop		= true,
+	},
+	/* Entry state on starting. Interrupts enabled from here on. Transient
+	 * state for synchronsization */
+	[CPUHP_AP_ONLINE] = {
+		.name			= "ap:online",
+	},
+	/* Handle smpboot threads park/unpark */
+	[CPUHP_AP_SMPBOOT_THREADS] = {
+		.name			= "smpboot:threads",
+		.startup		= smpboot_unpark_threads,
+		.teardown		= NULL,
+	},
+	/*
+	 * Online/down_prepare notifiers. Will be removed once the notifiers
+	 * are converted to states.
+	 */
+	[CPUHP_AP_NOTIFY_ONLINE] = {
+		.name			= "notify:online",
+		.startup		= notify_online,
+		.teardown		= notify_down_prepare,
+	},
+#endif
+	/*
+	 * The dynamically registered state space is here
+	 */
+
+	/* CPU is fully up and running. */
+	[CPUHP_ONLINE] = {
+		.name			= "online",
+		.startup		= NULL,
+		.teardown		= NULL,
+	},
+};
+
+/* Sanity check for callbacks */
+static int cpuhp_cb_check(enum cpuhp_state state)
+{
+	if (state <= CPUHP_OFFLINE || state >= CPUHP_ONLINE)
+		return -EINVAL;
+	return 0;
+}
+
+static bool cpuhp_is_ap_state(enum cpuhp_state state)
+{
+	/*
+	 * The extra check for CPUHP_TEARDOWN_CPU is only for documentation
+	 * purposes as that state is handled explicitely in cpu_down.
+	 */
+	return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU;
+}
+
+static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state)
+{
+	struct cpuhp_step *sp;
+
+	sp = cpuhp_is_ap_state(state) ? cpuhp_ap_states : cpuhp_bp_states;
+	return sp + state;
+}
+
+static void cpuhp_store_callbacks(enum cpuhp_state state,
+				  const char *name,
+				  int (*startup)(unsigned int cpu),
+				  int (*teardown)(unsigned int cpu))
+{
+	/* (Un)Install the callbacks for further cpu hotplug operations */
+	struct cpuhp_step *sp;
+
+	mutex_lock(&cpuhp_state_mutex);
+	sp = cpuhp_get_step(state);
+	sp->startup = startup;
+	sp->teardown = teardown;
+	sp->name = name;
+	mutex_unlock(&cpuhp_state_mutex);
+}
+
+static void *cpuhp_get_teardown_cb(enum cpuhp_state state)
+{
+	return cpuhp_get_step(state)->teardown;
+}
+
+/*
+ * Call the startup/teardown function for a step either on the AP or
+ * on the current CPU.
+ */
+static int cpuhp_issue_call(int cpu, enum cpuhp_state state,
+			    int (*cb)(unsigned int), bool bringup)
+{
+	int ret;
+
+	if (!cb)
+		return 0;
+	/*
+	 * The non AP bound callbacks can fail on bringup. On teardown
+	 * e.g. module removal we crash for now.
+	 */
+#ifdef CONFIG_SMP
+	if (cpuhp_is_ap_state(state))
+		ret = cpuhp_invoke_ap_callback(cpu, state, cb);
+	else
+		ret = cpuhp_invoke_callback(cpu, state, cb);
+#else
+	ret = cpuhp_invoke_callback(cpu, state, cb);
+#endif
+	BUG_ON(ret && !bringup);
+	return ret;
+}
+
+/*
+ * Called from __cpuhp_setup_state on a recoverable failure.
+ *
+ * Note: The teardown callbacks for rollback are not allowed to fail!
+ */
+static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state,
+				   int (*teardown)(unsigned int cpu))
+{
+	int cpu;
+
+	if (!teardown)
+		return;
+
+	/* Roll back the already executed steps on the other cpus */
+	for_each_present_cpu(cpu) {
+		struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+		int cpustate = st->state;
+
+		if (cpu >= failedcpu)
+			break;
+
+		/* Did we invoke the startup call on that cpu ? */
+		if (cpustate >= state)
+			cpuhp_issue_call(cpu, state, teardown, false);
+	}
+}
+
+/*
+ * Returns a free for dynamic slot assignment of the Online state. The states
+ * are protected by the cpuhp_slot_states mutex and an empty slot is identified
+ * by having no name assigned.
+ */
+static int cpuhp_reserve_state(enum cpuhp_state state)
+{
+	enum cpuhp_state i;
+
+	mutex_lock(&cpuhp_state_mutex);
+	for (i = CPUHP_AP_ONLINE_DYN; i <= CPUHP_AP_ONLINE_DYN_END; i++) {
+		if (cpuhp_ap_states[i].name)
+			continue;
+
+		cpuhp_ap_states[i].name = "Reserved";
+		mutex_unlock(&cpuhp_state_mutex);
+		return i;
+	}
+	mutex_unlock(&cpuhp_state_mutex);
+	WARN(1, "No more dynamic states available for CPU hotplug\n");
+	return -ENOSPC;
+}
+
 /**
- * notify_cpu_starting(cpu) - call the CPU_STARTING notifiers
- * @cpu: cpu that just started
+ * __cpuhp_setup_state - Setup the callbacks for an hotplug machine state
+ * @state:	The state to setup
+ * @invoke:	If true, the startup function is invoked for cpus where
+ *		cpu state >= @state
+ * @startup:	startup callback function
+ * @teardown:	teardown callback function
  *
- * This function calls the cpu_chain notifiers with CPU_STARTING.
- * It must be called by the arch code on the new cpu, before the new cpu
- * enables interrupts and before the "boot" cpu returns from __cpu_up().
+ * Returns 0 if successful, otherwise a proper error code
  */
-void notify_cpu_starting(unsigned int cpu)
+int __cpuhp_setup_state(enum cpuhp_state state,
+			const char *name, bool invoke,
+			int (*startup)(unsigned int cpu),
+			int (*teardown)(unsigned int cpu))
 {
-	unsigned long val = CPU_STARTING;
+	int cpu, ret = 0;
+	int dyn_state = 0;
 
-#ifdef CONFIG_PM_SLEEP_SMP
-	if (frozen_cpus != NULL && cpumask_test_cpu(cpu, frozen_cpus))
-		val = CPU_STARTING_FROZEN;
-#endif /* CONFIG_PM_SLEEP_SMP */
-	cpu_notify(val, (void *)(long)cpu);
+	if (cpuhp_cb_check(state) || !name)
+		return -EINVAL;
+
+	get_online_cpus();
+
+	/* currently assignments for the ONLINE state are possible */
+	if (state == CPUHP_AP_ONLINE_DYN) {
+		dyn_state = 1;
+		ret = cpuhp_reserve_state(state);
+		if (ret < 0)
+			goto out;
+		state = ret;
+	}
+
+	cpuhp_store_callbacks(state, name, startup, teardown);
+
+	if (!invoke || !startup)
+		goto out;
+
+	/*
+	 * Try to call the startup callback for each present cpu
+	 * depending on the hotplug state of the cpu.
+	 */
+	for_each_present_cpu(cpu) {
+		struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+		int cpustate = st->state;
+
+		if (cpustate < state)
+			continue;
+
+		ret = cpuhp_issue_call(cpu, state, startup, true);
+		if (ret) {
+			cpuhp_rollback_install(cpu, state, teardown);
+			cpuhp_store_callbacks(state, NULL, NULL, NULL);
+			goto out;
+		}
+	}
+out:
+	put_online_cpus();
+	if (!ret && dyn_state)
+		return state;
+	return ret;
 }
+EXPORT_SYMBOL(__cpuhp_setup_state);
 
-#endif /* CONFIG_SMP */
+/**
+ * __cpuhp_remove_state - Remove the callbacks for an hotplug machine state
+ * @state:	The state to remove
+ * @invoke:	If true, the teardown function is invoked for cpus where
+ *		cpu state >= @state
+ *
+ * The teardown callback is currently not allowed to fail. Think
+ * about module removal!
+ */
+void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
+{
+	int (*teardown)(unsigned int cpu) = cpuhp_get_teardown_cb(state);
+	int cpu;
+
+	BUG_ON(cpuhp_cb_check(state));
+
+	get_online_cpus();
+
+	if (!invoke || !teardown)
+		goto remove;
+
+	/*
+	 * Call the teardown callback for each present cpu depending
+	 * on the hotplug state of the cpu. This function is not
+	 * allowed to fail currently!
+	 */
+	for_each_present_cpu(cpu) {
+		struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+		int cpustate = st->state;
+
+		if (cpustate >= state)
+			cpuhp_issue_call(cpu, state, teardown, false);
+	}
+remove:
+	cpuhp_store_callbacks(state, NULL, NULL, NULL);
+	put_online_cpus();
+}
+EXPORT_SYMBOL(__cpuhp_remove_state);
+
+#if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU)
+static ssize_t show_cpuhp_state(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
+
+	return sprintf(buf, "%d\n", st->state);
+}
+static DEVICE_ATTR(state, 0444, show_cpuhp_state, NULL);
+
+static ssize_t write_cpuhp_target(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
+{
+	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
+	struct cpuhp_step *sp;
+	int target, ret;
+
+	ret = kstrtoint(buf, 10, &target);
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_CPU_HOTPLUG_STATE_CONTROL
+	if (target < CPUHP_OFFLINE || target > CPUHP_ONLINE)
+		return -EINVAL;
+#else
+	if (target != CPUHP_OFFLINE && target != CPUHP_ONLINE)
+		return -EINVAL;
+#endif
+
+	ret = lock_device_hotplug_sysfs();
+	if (ret)
+		return ret;
+
+	mutex_lock(&cpuhp_state_mutex);
+	sp = cpuhp_get_step(target);
+	ret = !sp->name || sp->cant_stop ? -EINVAL : 0;
+	mutex_unlock(&cpuhp_state_mutex);
+	if (ret)
+		return ret;
+
+	if (st->state < target)
+		ret = do_cpu_up(dev->id, target);
+	else
+		ret = do_cpu_down(dev->id, target);
+
+	unlock_device_hotplug();
+	return ret ? ret : count;
+}
+
+static ssize_t show_cpuhp_target(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
+
+	return sprintf(buf, "%d\n", st->target);
+}
+static DEVICE_ATTR(target, 0644, show_cpuhp_target, write_cpuhp_target);
+
+static struct attribute *cpuhp_cpu_attrs[] = {
+	&dev_attr_state.attr,
+	&dev_attr_target.attr,
+	NULL
+};
+
+static struct attribute_group cpuhp_cpu_attr_group = {
+	.attrs = cpuhp_cpu_attrs,
+	.name = "hotplug",
+	NULL
+};
+
+static ssize_t show_cpuhp_states(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	ssize_t cur, res = 0;
+	int i;
+
+	mutex_lock(&cpuhp_state_mutex);
+	for (i = CPUHP_OFFLINE; i <= CPUHP_ONLINE; i++) {
+		struct cpuhp_step *sp = cpuhp_get_step(i);
+
+		if (sp->name) {
+			cur = sprintf(buf, "%3d: %s\n", i, sp->name);
+			buf += cur;
+			res += cur;
+		}
+	}
+	mutex_unlock(&cpuhp_state_mutex);
+	return res;
+}
+static DEVICE_ATTR(states, 0444, show_cpuhp_states, NULL);
+
+static struct attribute *cpuhp_cpu_root_attrs[] = {
+	&dev_attr_states.attr,
+	NULL
+};
+
+static struct attribute_group cpuhp_cpu_root_attr_group = {
+	.attrs = cpuhp_cpu_root_attrs,
+	.name = "hotplug",
+	NULL
+};
+
+static int __init cpuhp_sysfs_init(void)
+{
+	int cpu, ret;
+
+	ret = sysfs_create_group(&cpu_subsys.dev_root->kobj,
+				 &cpuhp_cpu_root_attr_group);
+	if (ret)
+		return ret;
+
+	for_each_possible_cpu(cpu) {
+		struct device *dev = get_cpu_device(cpu);
+
+		if (!dev)
+			continue;
+		ret = sysfs_create_group(&dev->kobj, &cpuhp_cpu_attr_group);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+device_initcall(cpuhp_sysfs_init);
+#endif
 
 /*
  * cpu_bit_bitmap[] is a special, "compressed" data structure that
@@ -789,3 +1673,25 @@ void init_cpu_online(const struct cpumask *src)
 {
 	cpumask_copy(&__cpu_online_mask, src);
 }
+
+/*
+ * Activate the first processor.
+ */
+void __init boot_cpu_init(void)
+{
+	int cpu = smp_processor_id();
+
+	/* Mark the boot cpu "present", "online" etc for SMP and UP case */
+	set_cpu_online(cpu, true);
+	set_cpu_active(cpu, true);
+	set_cpu_present(cpu, true);
+	set_cpu_possible(cpu, true);
+}
+
+/*
+ * Must be called _AFTER_ setting up the per_cpu areas
+ */
+void __init boot_cpu_state_init(void)
+{
+	per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE;
+}
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 3e945fcd8179..41989ab4db57 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -287,6 +287,8 @@ static struct cpuset top_cpuset = {
 static DEFINE_MUTEX(cpuset_mutex);
 static DEFINE_SPINLOCK(callback_lock);
 
+static struct workqueue_struct *cpuset_migrate_mm_wq;
+
 /*
  * CPU / memory hotplug is handled asynchronously.
  */
@@ -972,31 +974,51 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 }
 
 /*
- * cpuset_migrate_mm
- *
- *    Migrate memory region from one set of nodes to another.
- *
- *    Temporarilly set tasks mems_allowed to target nodes of migration,
- *    so that the migration code can allocate pages on these nodes.
- *
- *    While the mm_struct we are migrating is typically from some
- *    other task, the task_struct mems_allowed that we are hacking
- *    is for our current task, which must allocate new pages for that
- *    migrating memory region.
+ * Migrate memory region from one set of nodes to another.  This is
+ * performed asynchronously as it can be called from process migration path
+ * holding locks involved in process management.  All mm migrations are
+ * performed in the queued order and can be waited for by flushing
+ * cpuset_migrate_mm_wq.
  */
 
+struct cpuset_migrate_mm_work {
+	struct work_struct	work;
+	struct mm_struct	*mm;
+	nodemask_t		from;
+	nodemask_t		to;
+};
+
+static void cpuset_migrate_mm_workfn(struct work_struct *work)
+{
+	struct cpuset_migrate_mm_work *mwork =
+		container_of(work, struct cpuset_migrate_mm_work, work);
+
+	/* on a wq worker, no need to worry about %current's mems_allowed */
+	do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL);
+	mmput(mwork->mm);
+	kfree(mwork);
+}
+
 static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
 							const nodemask_t *to)
 {
-	struct task_struct *tsk = current;
-
-	tsk->mems_allowed = *to;
+	struct cpuset_migrate_mm_work *mwork;
 
-	do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
+	mwork = kzalloc(sizeof(*mwork), GFP_KERNEL);
+	if (mwork) {
+		mwork->mm = mm;
+		mwork->from = *from;
+		mwork->to = *to;
+		INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn);
+		queue_work(cpuset_migrate_mm_wq, &mwork->work);
+	} else {
+		mmput(mm);
+	}
+}
 
-	rcu_read_lock();
-	guarantee_online_mems(task_cs(tsk), &tsk->mems_allowed);
-	rcu_read_unlock();
+void cpuset_post_attach_flush(void)
+{
+	flush_workqueue(cpuset_migrate_mm_wq);
 }
 
 /*
@@ -1097,7 +1119,8 @@ static void update_tasks_nodemask(struct cpuset *cs)
 		mpol_rebind_mm(mm, &cs->mems_allowed);
 		if (migrate)
 			cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems);
-		mmput(mm);
+		else
+			mmput(mm);
 	}
 	css_task_iter_end(&it);
 
@@ -1545,11 +1568,11 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 			 * @old_mems_allowed is the right nodesets that we
 			 * migrate mm from.
 			 */
-			if (is_memory_migrate(cs)) {
+			if (is_memory_migrate(cs))
 				cpuset_migrate_mm(mm, &oldcs->old_mems_allowed,
 						  &cpuset_attach_nodemask_to);
-			}
-			mmput(mm);
+			else
+				mmput(mm);
 		}
 	}
 
@@ -1714,6 +1737,7 @@ out_unlock:
 	mutex_unlock(&cpuset_mutex);
 	kernfs_unbreak_active_protection(of->kn);
 	css_put(&cs->css);
+	flush_workqueue(cpuset_migrate_mm_wq);
 	return retval ?: nbytes;
 }
 
@@ -2359,6 +2383,9 @@ void __init cpuset_init_smp(void)
 	top_cpuset.effective_mems = node_states[N_MEMORY];
 
 	register_hotmemory_notifier(&cpuset_track_online_nodes_nb);
+
+	cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0);
+	BUG_ON(!cpuset_migrate_mm_wq);
 }
 
 /**
diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c
index e1dbf4a2c69e..90ff129c88a2 100644
--- a/kernel/debug/kdb/kdb_bp.c
+++ b/kernel/debug/kdb/kdb_bp.c
@@ -153,13 +153,11 @@ static int _kdb_bp_install(struct pt_regs *regs, kdb_bp_t *bp)
 	} else {
 		kdb_printf("%s: failed to set breakpoint at 0x%lx\n",
 			   __func__, bp->bp_addr);
-#ifdef CONFIG_DEBUG_RODATA
 		if (!bp->bp_type) {
 			kdb_printf("Software breakpoints are unavailable.\n"
-				   "  Change the kernel CONFIG_DEBUG_RODATA=n\n"
+				   "  Boot the kernel with rodata=off\n"
 				   "  OR use hw breaks: help bph\n");
 		}
-#endif
 		return 1;
 	}
 	return 0;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5946460b2425..712570dddacd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -64,8 +64,17 @@ static void remote_function(void *data)
 	struct task_struct *p = tfc->p;
 
 	if (p) {
-		tfc->ret = -EAGAIN;
-		if (task_cpu(p) != smp_processor_id() || !task_curr(p))
+		/* -EAGAIN */
+		if (task_cpu(p) != smp_processor_id())
+			return;
+
+		/*
+		 * Now that we're on right CPU with IRQs disabled, we can test
+		 * if we hit the right task without races.
+		 */
+
+		tfc->ret = -ESRCH; /* No such (running) process */
+		if (p != current)
 			return;
 	}
 
@@ -92,13 +101,17 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info)
 		.p	= p,
 		.func	= func,
 		.info	= info,
-		.ret	= -ESRCH, /* No such (running) process */
+		.ret	= -EAGAIN,
 	};
+	int ret;
 
-	if (task_curr(p))
-		smp_call_function_single(task_cpu(p), remote_function, &data, 1);
+	do {
+		ret = smp_call_function_single(task_cpu(p), remote_function, &data, 1);
+		if (!ret)
+			ret = data.ret;
+	} while (ret == -EAGAIN);
 
-	return data.ret;
+	return ret;
 }
 
 /**
@@ -169,19 +182,6 @@ static bool is_kernel_event(struct perf_event *event)
  *    rely on ctx->is_active and therefore cannot use event_function_call().
  *    See perf_install_in_context().
  *
- * This is because we need a ctx->lock serialized variable (ctx->is_active)
- * to reliably determine if a particular task/context is scheduled in. The
- * task_curr() use in task_function_call() is racy in that a remote context
- * switch is not a single atomic operation.
- *
- * As is, the situation is 'safe' because we set rq->curr before we do the
- * actual context switch. This means that task_curr() will fail early, but
- * we'll continue spinning on ctx->is_active until we've passed
- * perf_event_task_sched_out().
- *
- * Without this ctx->lock serialized variable we could have race where we find
- * the task (and hence the context) would not be active while in fact they are.
- *
  * If ctx->nr_events, then ctx->is_active and cpuctx->task_ctx are set.
  */
 
@@ -212,7 +212,7 @@ static int event_function(void *info)
 	 */
 	if (ctx->task) {
 		if (ctx->task != current) {
-			ret = -EAGAIN;
+			ret = -ESRCH;
 			goto unlock;
 		}
 
@@ -276,10 +276,10 @@ static void event_function_call(struct perf_event *event, event_f func, void *da
 		return;
 	}
 
-again:
 	if (task == TASK_TOMBSTONE)
 		return;
 
+again:
 	if (!task_function_call(task, event_function, &efs))
 		return;
 
@@ -289,13 +289,15 @@ again:
 	 * a concurrent perf_event_context_sched_out().
 	 */
 	task = ctx->task;
-	if (task != TASK_TOMBSTONE) {
-		if (ctx->is_active) {
-			raw_spin_unlock_irq(&ctx->lock);
-			goto again;
-		}
-		func(event, NULL, ctx, data);
+	if (task == TASK_TOMBSTONE) {
+		raw_spin_unlock_irq(&ctx->lock);
+		return;
 	}
+	if (ctx->is_active) {
+		raw_spin_unlock_irq(&ctx->lock);
+		goto again;
+	}
+	func(event, NULL, ctx, data);
 	raw_spin_unlock_irq(&ctx->lock);
 }
 
@@ -314,6 +316,7 @@ again:
 enum event_type_t {
 	EVENT_FLEXIBLE = 0x1,
 	EVENT_PINNED = 0x2,
+	EVENT_TIME = 0x4,
 	EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
 };
 
@@ -321,7 +324,13 @@ enum event_type_t {
  * perf_sched_events : >0 events exist
  * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
  */
-struct static_key_deferred perf_sched_events __read_mostly;
+
+static void perf_sched_delayed(struct work_struct *work);
+DEFINE_STATIC_KEY_FALSE(perf_sched_events);
+static DECLARE_DELAYED_WORK(perf_sched_work, perf_sched_delayed);
+static DEFINE_MUTEX(perf_sched_mutex);
+static atomic_t perf_sched_count;
+
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
 static DEFINE_PER_CPU(int, perf_sched_cb_usages);
 
@@ -1288,16 +1297,18 @@ static u64 perf_event_time(struct perf_event *event)
 
 /*
  * Update the total_time_enabled and total_time_running fields for a event.
- * The caller of this function needs to hold the ctx->lock.
  */
 static void update_event_times(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
 	u64 run_end;
 
+	lockdep_assert_held(&ctx->lock);
+
 	if (event->state < PERF_EVENT_STATE_INACTIVE ||
 	    event->group_leader->state < PERF_EVENT_STATE_INACTIVE)
 		return;
+
 	/*
 	 * in cgroup mode, time_enabled represents
 	 * the time the event was enabled AND active
@@ -1645,7 +1656,7 @@ out:
 
 static bool is_orphaned_event(struct perf_event *event)
 {
-	return event->state == PERF_EVENT_STATE_EXIT;
+	return event->state == PERF_EVENT_STATE_DEAD;
 }
 
 static inline int pmu_filter_match(struct perf_event *event)
@@ -1690,14 +1701,14 @@ event_sched_out(struct perf_event *event,
 
 	perf_pmu_disable(event->pmu);
 
+	event->tstamp_stopped = tstamp;
+	event->pmu->del(event, 0);
+	event->oncpu = -1;
 	event->state = PERF_EVENT_STATE_INACTIVE;
 	if (event->pending_disable) {
 		event->pending_disable = 0;
 		event->state = PERF_EVENT_STATE_OFF;
 	}
-	event->tstamp_stopped = tstamp;
-	event->pmu->del(event, 0);
-	event->oncpu = -1;
 
 	if (!is_software_event(event))
 		cpuctx->active_oncpu--;
@@ -1732,7 +1743,6 @@ group_sched_out(struct perf_event *group_event,
 }
 
 #define DETACH_GROUP	0x01UL
-#define DETACH_STATE	0x02UL
 
 /*
  * Cross CPU call to remove a performance event
@@ -1752,8 +1762,6 @@ __perf_remove_from_context(struct perf_event *event,
 	if (flags & DETACH_GROUP)
 		perf_group_detach(event);
 	list_del_event(event, ctx);
-	if (flags & DETACH_STATE)
-		event->state = PERF_EVENT_STATE_EXIT;
 
 	if (!ctx->nr_events && ctx->is_active) {
 		ctx->is_active = 0;
@@ -2063,14 +2071,27 @@ static void add_event_to_ctx(struct perf_event *event,
 	event->tstamp_stopped = tstamp;
 }
 
-static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
-			       struct perf_event_context *ctx);
+static void ctx_sched_out(struct perf_event_context *ctx,
+			  struct perf_cpu_context *cpuctx,
+			  enum event_type_t event_type);
 static void
 ctx_sched_in(struct perf_event_context *ctx,
 	     struct perf_cpu_context *cpuctx,
 	     enum event_type_t event_type,
 	     struct task_struct *task);
 
+static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
+			       struct perf_event_context *ctx)
+{
+	if (!cpuctx->task_ctx)
+		return;
+
+	if (WARN_ON_ONCE(ctx != cpuctx->task_ctx))
+		return;
+
+	ctx_sched_out(ctx, cpuctx, EVENT_ALL);
+}
+
 static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
 				struct perf_event_context *ctx,
 				struct task_struct *task)
@@ -2097,49 +2118,68 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
 /*
  * Cross CPU call to install and enable a performance event
  *
- * Must be called with ctx->mutex held
+ * Very similar to remote_function() + event_function() but cannot assume that
+ * things like ctx->is_active and cpuctx->task_ctx are set.
  */
 static int  __perf_install_in_context(void *info)
 {
-	struct perf_event_context *ctx = info;
+	struct perf_event *event = info;
+	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 	struct perf_event_context *task_ctx = cpuctx->task_ctx;
+	bool activate = true;
+	int ret = 0;
 
 	raw_spin_lock(&cpuctx->ctx.lock);
 	if (ctx->task) {
 		raw_spin_lock(&ctx->lock);
-		/*
-		 * If we hit the 'wrong' task, we've since scheduled and
-		 * everything should be sorted, nothing to do!
-		 */
 		task_ctx = ctx;
-		if (ctx->task != current)
+
+		/* If we're on the wrong CPU, try again */
+		if (task_cpu(ctx->task) != smp_processor_id()) {
+			ret = -ESRCH;
 			goto unlock;
+		}
 
 		/*
-		 * If task_ctx is set, it had better be to us.
+		 * If we're on the right CPU, see if the task we target is
+		 * current, if not we don't have to activate the ctx, a future
+		 * context switch will do that for us.
 		 */
-		WARN_ON_ONCE(cpuctx->task_ctx != ctx && cpuctx->task_ctx);
+		if (ctx->task != current)
+			activate = false;
+		else
+			WARN_ON_ONCE(cpuctx->task_ctx && cpuctx->task_ctx != ctx);
+
 	} else if (task_ctx) {
 		raw_spin_lock(&task_ctx->lock);
 	}
 
-	ctx_resched(cpuctx, task_ctx);
+	if (activate) {
+		ctx_sched_out(ctx, cpuctx, EVENT_TIME);
+		add_event_to_ctx(event, ctx);
+		ctx_resched(cpuctx, task_ctx);
+	} else {
+		add_event_to_ctx(event, ctx);
+	}
+
 unlock:
 	perf_ctx_unlock(cpuctx, task_ctx);
 
-	return 0;
+	return ret;
 }
 
 /*
- * Attach a performance event to a context
+ * Attach a performance event to a context.
+ *
+ * Very similar to event_function_call, see comment there.
  */
 static void
 perf_install_in_context(struct perf_event_context *ctx,
 			struct perf_event *event,
 			int cpu)
 {
-	struct task_struct *task = NULL;
+	struct task_struct *task = READ_ONCE(ctx->task);
 
 	lockdep_assert_held(&ctx->mutex);
 
@@ -2147,40 +2187,46 @@ perf_install_in_context(struct perf_event_context *ctx,
 	if (event->cpu != -1)
 		event->cpu = cpu;
 
+	if (!task) {
+		cpu_function_call(cpu, __perf_install_in_context, event);
+		return;
+	}
+
+	/*
+	 * Should not happen, we validate the ctx is still alive before calling.
+	 */
+	if (WARN_ON_ONCE(task == TASK_TOMBSTONE))
+		return;
+
 	/*
 	 * Installing events is tricky because we cannot rely on ctx->is_active
 	 * to be set in case this is the nr_events 0 -> 1 transition.
-	 *
-	 * So what we do is we add the event to the list here, which will allow
-	 * a future context switch to DTRT and then send a racy IPI. If the IPI
-	 * fails to hit the right task, this means a context switch must have
-	 * happened and that will have taken care of business.
 	 */
-	raw_spin_lock_irq(&ctx->lock);
-	task = ctx->task;
+again:
 	/*
-	 * Worse, we cannot even rely on the ctx actually existing anymore. If
-	 * between find_get_context() and perf_install_in_context() the task
-	 * went through perf_event_exit_task() its dead and we should not be
-	 * adding new events.
+	 * Cannot use task_function_call() because we need to run on the task's
+	 * CPU regardless of whether its current or not.
 	 */
-	if (task == TASK_TOMBSTONE) {
+	if (!cpu_function_call(task_cpu(task), __perf_install_in_context, event))
+		return;
+
+	raw_spin_lock_irq(&ctx->lock);
+	task = ctx->task;
+	if (WARN_ON_ONCE(task == TASK_TOMBSTONE)) {
+		/*
+		 * Cannot happen because we already checked above (which also
+		 * cannot happen), and we hold ctx->mutex, which serializes us
+		 * against perf_event_exit_task_context().
+		 */
 		raw_spin_unlock_irq(&ctx->lock);
 		return;
 	}
-	update_context_time(ctx);
+	raw_spin_unlock_irq(&ctx->lock);
 	/*
-	 * Update cgrp time only if current cgrp matches event->cgrp.
-	 * Must be done before calling add_event_to_ctx().
+	 * Since !ctx->is_active doesn't mean anything, we must IPI
+	 * unconditionally.
 	 */
-	update_cgrp_time_from_event(event);
-	add_event_to_ctx(event, ctx);
-	raw_spin_unlock_irq(&ctx->lock);
-
-	if (task)
-		task_function_call(task, __perf_install_in_context, ctx);
-	else
-		cpu_function_call(cpu, __perf_install_in_context, ctx);
+	goto again;
 }
 
 /*
@@ -2219,17 +2265,18 @@ static void __perf_event_enable(struct perf_event *event,
 	    event->state <= PERF_EVENT_STATE_ERROR)
 		return;
 
-	update_context_time(ctx);
+	if (ctx->is_active)
+		ctx_sched_out(ctx, cpuctx, EVENT_TIME);
+
 	__perf_event_mark_enabled(event);
 
 	if (!ctx->is_active)
 		return;
 
 	if (!event_filter_match(event)) {
-		if (is_cgroup_event(event)) {
-			perf_cgroup_set_timestamp(current, ctx); // XXX ?
+		if (is_cgroup_event(event))
 			perf_cgroup_defer_enabled(event);
-		}
+		ctx_sched_in(ctx, cpuctx, EVENT_TIME, current);
 		return;
 	}
 
@@ -2237,8 +2284,10 @@ static void __perf_event_enable(struct perf_event *event,
 	 * If the event is in a group and isn't the group leader,
 	 * then don't put it on unless the group is on.
 	 */
-	if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE)
+	if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) {
+		ctx_sched_in(ctx, cpuctx, EVENT_TIME, current);
 		return;
+	}
 
 	task_ctx = cpuctx->task_ctx;
 	if (ctx->task)
@@ -2344,24 +2393,33 @@ static void ctx_sched_out(struct perf_event_context *ctx,
 	}
 
 	ctx->is_active &= ~event_type;
+	if (!(ctx->is_active & EVENT_ALL))
+		ctx->is_active = 0;
+
 	if (ctx->task) {
 		WARN_ON_ONCE(cpuctx->task_ctx != ctx);
 		if (!ctx->is_active)
 			cpuctx->task_ctx = NULL;
 	}
 
-	update_context_time(ctx);
-	update_cgrp_time_from_cpuctx(cpuctx);
-	if (!ctx->nr_active)
+	is_active ^= ctx->is_active; /* changed bits */
+
+	if (is_active & EVENT_TIME) {
+		/* update (and stop) ctx time */
+		update_context_time(ctx);
+		update_cgrp_time_from_cpuctx(cpuctx);
+	}
+
+	if (!ctx->nr_active || !(is_active & EVENT_ALL))
 		return;
 
 	perf_pmu_disable(ctx->pmu);
-	if ((is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) {
+	if (is_active & EVENT_PINNED) {
 		list_for_each_entry(event, &ctx->pinned_groups, group_entry)
 			group_sched_out(event, cpuctx, ctx);
 	}
 
-	if ((is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) {
+	if (is_active & EVENT_FLEXIBLE) {
 		list_for_each_entry(event, &ctx->flexible_groups, group_entry)
 			group_sched_out(event, cpuctx, ctx);
 	}
@@ -2641,18 +2699,6 @@ void __perf_event_task_sched_out(struct task_struct *task,
 		perf_cgroup_sched_out(task, next);
 }
 
-static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
-			       struct perf_event_context *ctx)
-{
-	if (!cpuctx->task_ctx)
-		return;
-
-	if (WARN_ON_ONCE(ctx != cpuctx->task_ctx))
-		return;
-
-	ctx_sched_out(ctx, cpuctx, EVENT_ALL);
-}
-
 /*
  * Called with IRQs disabled
  */
@@ -2735,7 +2781,7 @@ ctx_sched_in(struct perf_event_context *ctx,
 	if (likely(!ctx->nr_events))
 		return;
 
-	ctx->is_active |= event_type;
+	ctx->is_active |= (event_type | EVENT_TIME);
 	if (ctx->task) {
 		if (!is_active)
 			cpuctx->task_ctx = ctx;
@@ -2743,18 +2789,24 @@ ctx_sched_in(struct perf_event_context *ctx,
 			WARN_ON_ONCE(cpuctx->task_ctx != ctx);
 	}
 
-	now = perf_clock();
-	ctx->timestamp = now;
-	perf_cgroup_set_timestamp(task, ctx);
+	is_active ^= ctx->is_active; /* changed bits */
+
+	if (is_active & EVENT_TIME) {
+		/* start ctx time */
+		now = perf_clock();
+		ctx->timestamp = now;
+		perf_cgroup_set_timestamp(task, ctx);
+	}
+
 	/*
 	 * First go through the list and put on any pinned groups
 	 * in order to give them the best chance of going on.
 	 */
-	if (!(is_active & EVENT_PINNED) && (event_type & EVENT_PINNED))
+	if (is_active & EVENT_PINNED)
 		ctx_pinned_sched_in(ctx, cpuctx);
 
 	/* Then walk through the lower prio flexible groups */
-	if (!(is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE))
+	if (is_active & EVENT_FLEXIBLE)
 		ctx_flexible_sched_in(ctx, cpuctx);
 }
 
@@ -3060,17 +3112,6 @@ done:
 	return rotate;
 }
 
-#ifdef CONFIG_NO_HZ_FULL
-bool perf_event_can_stop_tick(void)
-{
-	if (atomic_read(&nr_freq_events) ||
-	    __this_cpu_read(perf_throttled_count))
-		return false;
-	else
-		return true;
-}
-#endif
-
 void perf_event_task_tick(void)
 {
 	struct list_head *head = this_cpu_ptr(&active_ctx_list);
@@ -3081,6 +3122,7 @@ void perf_event_task_tick(void)
 
 	__this_cpu_inc(perf_throttled_seq);
 	throttled = __this_cpu_xchg(perf_throttled_count, 0);
+	tick_dep_clear_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS);
 
 	list_for_each_entry_safe(ctx, tmp, head, active_ctx_list)
 		perf_adjust_freq_unthr_context(ctx, throttled);
@@ -3120,6 +3162,7 @@ static void perf_event_enable_on_exec(int ctxn)
 
 	cpuctx = __get_cpu_context(ctx);
 	perf_ctx_lock(cpuctx, ctx);
+	ctx_sched_out(ctx, cpuctx, EVENT_TIME);
 	list_for_each_entry(event, &ctx->event_list, event_entry)
 		enabled |= event_enable_on_exec(event, ctx);
 
@@ -3511,6 +3554,28 @@ static void unaccount_event_cpu(struct perf_event *event, int cpu)
 		atomic_dec(&per_cpu(perf_cgroup_events, cpu));
 }
 
+#ifdef CONFIG_NO_HZ_FULL
+static DEFINE_SPINLOCK(nr_freq_lock);
+#endif
+
+static void unaccount_freq_event_nohz(void)
+{
+#ifdef CONFIG_NO_HZ_FULL
+	spin_lock(&nr_freq_lock);
+	if (atomic_dec_and_test(&nr_freq_events))
+		tick_nohz_dep_clear(TICK_DEP_BIT_PERF_EVENTS);
+	spin_unlock(&nr_freq_lock);
+#endif
+}
+
+static void unaccount_freq_event(void)
+{
+	if (tick_nohz_full_enabled())
+		unaccount_freq_event_nohz();
+	else
+		atomic_dec(&nr_freq_events);
+}
+
 static void unaccount_event(struct perf_event *event)
 {
 	bool dec = false;
@@ -3527,7 +3592,7 @@ static void unaccount_event(struct perf_event *event)
 	if (event->attr.task)
 		atomic_dec(&nr_task_events);
 	if (event->attr.freq)
-		atomic_dec(&nr_freq_events);
+		unaccount_freq_event();
 	if (event->attr.context_switch) {
 		dec = true;
 		atomic_dec(&nr_switch_events);
@@ -3537,12 +3602,22 @@ static void unaccount_event(struct perf_event *event)
 	if (has_branch_stack(event))
 		dec = true;
 
-	if (dec)
-		static_key_slow_dec_deferred(&perf_sched_events);
+	if (dec) {
+		if (!atomic_add_unless(&perf_sched_count, -1, 1))
+			schedule_delayed_work(&perf_sched_work, HZ);
+	}
 
 	unaccount_event_cpu(event, event->cpu);
 }
 
+static void perf_sched_delayed(struct work_struct *work)
+{
+	mutex_lock(&perf_sched_mutex);
+	if (atomic_dec_and_test(&perf_sched_count))
+		static_branch_disable(&perf_sched_events);
+	mutex_unlock(&perf_sched_mutex);
+}
+
 /*
  * The following implement mutual exclusion of events on "exclusive" pmus
  * (PERF_PMU_CAP_EXCLUSIVE). Such pmus can only have one event scheduled
@@ -3752,30 +3827,42 @@ static void put_event(struct perf_event *event)
  */
 int perf_event_release_kernel(struct perf_event *event)
 {
-	struct perf_event_context *ctx;
+	struct perf_event_context *ctx = event->ctx;
 	struct perf_event *child, *tmp;
 
+	/*
+	 * If we got here through err_file: fput(event_file); we will not have
+	 * attached to a context yet.
+	 */
+	if (!ctx) {
+		WARN_ON_ONCE(event->attach_state &
+				(PERF_ATTACH_CONTEXT|PERF_ATTACH_GROUP));
+		goto no_ctx;
+	}
+
 	if (!is_kernel_event(event))
 		perf_remove_from_owner(event);
 
 	ctx = perf_event_ctx_lock(event);
 	WARN_ON_ONCE(ctx->parent_ctx);
-	perf_remove_from_context(event, DETACH_GROUP | DETACH_STATE);
-	perf_event_ctx_unlock(event, ctx);
+	perf_remove_from_context(event, DETACH_GROUP);
 
+	raw_spin_lock_irq(&ctx->lock);
 	/*
-	 * At this point we must have event->state == PERF_EVENT_STATE_EXIT,
-	 * either from the above perf_remove_from_context() or through
-	 * perf_event_exit_event().
+	 * Mark this even as STATE_DEAD, there is no external reference to it
+	 * anymore.
 	 *
-	 * Therefore, anybody acquiring event->child_mutex after the below
-	 * loop _must_ also see this, most importantly inherit_event() which
-	 * will avoid placing more children on the list.
+	 * Anybody acquiring event->child_mutex after the below loop _must_
+	 * also see this, most importantly inherit_event() which will avoid
+	 * placing more children on the list.
 	 *
 	 * Thus this guarantees that we will in fact observe and kill _ALL_
 	 * child events.
 	 */
-	WARN_ON_ONCE(event->state != PERF_EVENT_STATE_EXIT);
+	event->state = PERF_EVENT_STATE_DEAD;
+	raw_spin_unlock_irq(&ctx->lock);
+
+	perf_event_ctx_unlock(event, ctx);
 
 again:
 	mutex_lock(&event->child_mutex);
@@ -3830,8 +3917,8 @@ again:
 	}
 	mutex_unlock(&event->child_mutex);
 
-	/* Must be the last reference */
-	put_event(event);
+no_ctx:
+	put_event(event); /* Must be the 'last' reference */
 	return 0;
 }
 EXPORT_SYMBOL_GPL(perf_event_release_kernel);
@@ -3988,7 +4075,7 @@ static bool is_event_hup(struct perf_event *event)
 {
 	bool no_children;
 
-	if (event->state != PERF_EVENT_STATE_EXIT)
+	if (event->state > PERF_EVENT_STATE_EXIT)
 		return false;
 
 	mutex_lock(&event->child_mutex);
@@ -6349,9 +6436,9 @@ static int __perf_event_overflow(struct perf_event *event,
 		if (unlikely(throttle
 			     && hwc->interrupts >= max_samples_per_tick)) {
 			__this_cpu_inc(perf_throttled_count);
+			tick_dep_set_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS);
 			hwc->interrupts = MAX_INTERRUPTS;
 			perf_log_throttle(event, 0);
-			tick_nohz_full_kick();
 			ret = 1;
 		}
 	}
@@ -6710,7 +6797,7 @@ static void swevent_hlist_release(struct swevent_htable *swhash)
 	kfree_rcu(hlist, rcu_head);
 }
 
-static void swevent_hlist_put_cpu(struct perf_event *event, int cpu)
+static void swevent_hlist_put_cpu(int cpu)
 {
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
@@ -6722,15 +6809,15 @@ static void swevent_hlist_put_cpu(struct perf_event *event, int cpu)
 	mutex_unlock(&swhash->hlist_mutex);
 }
 
-static void swevent_hlist_put(struct perf_event *event)
+static void swevent_hlist_put(void)
 {
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		swevent_hlist_put_cpu(event, cpu);
+		swevent_hlist_put_cpu(cpu);
 }
 
-static int swevent_hlist_get_cpu(struct perf_event *event, int cpu)
+static int swevent_hlist_get_cpu(int cpu)
 {
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 	int err = 0;
@@ -6753,14 +6840,13 @@ exit:
 	return err;
 }
 
-static int swevent_hlist_get(struct perf_event *event)
+static int swevent_hlist_get(void)
 {
-	int err;
-	int cpu, failed_cpu;
+	int err, cpu, failed_cpu;
 
 	get_online_cpus();
 	for_each_possible_cpu(cpu) {
-		err = swevent_hlist_get_cpu(event, cpu);
+		err = swevent_hlist_get_cpu(cpu);
 		if (err) {
 			failed_cpu = cpu;
 			goto fail;
@@ -6773,7 +6859,7 @@ fail:
 	for_each_possible_cpu(cpu) {
 		if (cpu == failed_cpu)
 			break;
-		swevent_hlist_put_cpu(event, cpu);
+		swevent_hlist_put_cpu(cpu);
 	}
 
 	put_online_cpus();
@@ -6789,7 +6875,7 @@ static void sw_perf_event_destroy(struct perf_event *event)
 	WARN_ON(event->parent);
 
 	static_key_slow_dec(&perf_swevent_enabled[event_id]);
-	swevent_hlist_put(event);
+	swevent_hlist_put();
 }
 
 static int perf_swevent_init(struct perf_event *event)
@@ -6820,7 +6906,7 @@ static int perf_swevent_init(struct perf_event *event)
 	if (!event->parent) {
 		int err;
 
-		err = swevent_hlist_get(event);
+		err = swevent_hlist_get();
 		if (err)
 			return err;
 
@@ -7741,6 +7827,27 @@ static void account_event_cpu(struct perf_event *event, int cpu)
 		atomic_inc(&per_cpu(perf_cgroup_events, cpu));
 }
 
+/* Freq events need the tick to stay alive (see perf_event_task_tick). */
+static void account_freq_event_nohz(void)
+{
+#ifdef CONFIG_NO_HZ_FULL
+	/* Lock so we don't race with concurrent unaccount */
+	spin_lock(&nr_freq_lock);
+	if (atomic_inc_return(&nr_freq_events) == 1)
+		tick_nohz_dep_set(TICK_DEP_BIT_PERF_EVENTS);
+	spin_unlock(&nr_freq_lock);
+#endif
+}
+
+static void account_freq_event(void)
+{
+	if (tick_nohz_full_enabled())
+		account_freq_event_nohz();
+	else
+		atomic_inc(&nr_freq_events);
+}
+
+
 static void account_event(struct perf_event *event)
 {
 	bool inc = false;
@@ -7756,10 +7863,8 @@ static void account_event(struct perf_event *event)
 		atomic_inc(&nr_comm_events);
 	if (event->attr.task)
 		atomic_inc(&nr_task_events);
-	if (event->attr.freq) {
-		if (atomic_inc_return(&nr_freq_events) == 1)
-			tick_nohz_full_kick_all();
-	}
+	if (event->attr.freq)
+		account_freq_event();
 	if (event->attr.context_switch) {
 		atomic_inc(&nr_switch_events);
 		inc = true;
@@ -7769,8 +7874,28 @@ static void account_event(struct perf_event *event)
 	if (is_cgroup_event(event))
 		inc = true;
 
-	if (inc)
-		static_key_slow_inc(&perf_sched_events.key);
+	if (inc) {
+		if (atomic_inc_not_zero(&perf_sched_count))
+			goto enabled;
+
+		mutex_lock(&perf_sched_mutex);
+		if (!atomic_read(&perf_sched_count)) {
+			static_branch_enable(&perf_sched_events);
+			/*
+			 * Guarantee that all CPUs observe they key change and
+			 * call the perf scheduling hooks before proceeding to
+			 * install events that need them.
+			 */
+			synchronize_sched();
+		}
+		/*
+		 * Now that we have waited for the sync_sched(), allow further
+		 * increments to by-pass the mutex.
+		 */
+		atomic_inc(&perf_sched_count);
+		mutex_unlock(&perf_sched_mutex);
+	}
+enabled:
 
 	account_event_cpu(event, event->cpu);
 }
@@ -7906,6 +8031,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		}
 	}
 
+	/* symmetric to unaccount_event() in _free_event() */
+	account_event(event);
+
 	return event;
 
 err_per_task:
@@ -8269,8 +8397,6 @@ SYSCALL_DEFINE5(perf_event_open,
 		}
 	}
 
-	account_event(event);
-
 	/*
 	 * Special case software events and allow them to be part of
 	 * any hardware group.
@@ -8389,10 +8515,19 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (move_group) {
 		gctx = group_leader->ctx;
 		mutex_lock_double(&gctx->mutex, &ctx->mutex);
+		if (gctx->task == TASK_TOMBSTONE) {
+			err = -ESRCH;
+			goto err_locked;
+		}
 	} else {
 		mutex_lock(&ctx->mutex);
 	}
 
+	if (ctx->task == TASK_TOMBSTONE) {
+		err = -ESRCH;
+		goto err_locked;
+	}
+
 	if (!perf_event_validate_size(event)) {
 		err = -E2BIG;
 		goto err_locked;
@@ -8509,7 +8644,12 @@ err_context:
 	perf_unpin_context(ctx);
 	put_ctx(ctx);
 err_alloc:
-	free_event(event);
+	/*
+	 * If event_file is set, the fput() above will have called ->release()
+	 * and that will take care of freeing the event.
+	 */
+	if (!event_file)
+		free_event(event);
 err_cpus:
 	put_online_cpus();
 err_task:
@@ -8553,8 +8693,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	/* Mark owner so we could distinguish it from user events. */
 	event->owner = TASK_TOMBSTONE;
 
-	account_event(event);
-
 	ctx = find_get_context(event->pmu, task, event);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
@@ -8563,12 +8701,14 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 
 	WARN_ON_ONCE(ctx->parent_ctx);
 	mutex_lock(&ctx->mutex);
+	if (ctx->task == TASK_TOMBSTONE) {
+		err = -ESRCH;
+		goto err_unlock;
+	}
+
 	if (!exclusive_event_installable(event, ctx)) {
-		mutex_unlock(&ctx->mutex);
-		perf_unpin_context(ctx);
-		put_ctx(ctx);
 		err = -EBUSY;
-		goto err_free;
+		goto err_unlock;
 	}
 
 	perf_install_in_context(ctx, event, cpu);
@@ -8577,6 +8717,10 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 
 	return event;
 
+err_unlock:
+	mutex_unlock(&ctx->mutex);
+	perf_unpin_context(ctx);
+	put_ctx(ctx);
 err_free:
 	free_event(event);
 err:
@@ -8695,7 +8839,7 @@ perf_event_exit_event(struct perf_event *child_event,
 	if (parent_event)
 		perf_group_detach(child_event);
 	list_del_event(child_event, child_ctx);
-	child_event->state = PERF_EVENT_STATE_EXIT; /* see perf_event_release_kernel() */
+	child_event->state = PERF_EVENT_STATE_EXIT; /* is_event_hup() */
 	raw_spin_unlock_irq(&child_ctx->lock);
 
 	/*
@@ -9206,7 +9350,7 @@ static void perf_event_init_cpu(int cpu)
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
 	mutex_lock(&swhash->hlist_mutex);
-	if (swhash->hlist_refcount > 0) {
+	if (swhash->hlist_refcount > 0 && !swevent_hlist_deref(swhash)) {
 		struct swevent_hlist *hlist;
 
 		hlist = kzalloc_node(sizeof(*hlist), GFP_KERNEL, cpu_to_node(cpu));
@@ -9282,11 +9426,9 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 	switch (action & ~CPU_TASKS_FROZEN) {
 
 	case CPU_UP_PREPARE:
-	case CPU_DOWN_FAILED:
 		perf_event_init_cpu(cpu);
 		break;
 
-	case CPU_UP_CANCELED:
 	case CPU_DOWN_PREPARE:
 		perf_event_exit_cpu(cpu);
 		break;
@@ -9315,9 +9457,6 @@ void __init perf_event_init(void)
 	ret = init_hw_breakpoint();
 	WARN(ret, "hw_breakpoint initialization failed with: %d", ret);
 
-	/* do not patch jump label more than once per second */
-	jump_label_rate_limit(&perf_sched_events, HZ);
-
 	/*
 	 * Build time assertion that we keep the data_head at the intended
 	 * location.  IOW, validation we got the __reserved[] size right.
@@ -9337,6 +9476,7 @@ ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(perf_event_sysfs_show);
 
 static int __init perf_event_sysfs_init(void)
 {
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 0167679182c0..5f6ce931f1ea 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1178,6 +1178,7 @@ static struct xol_area *__create_xol_area(unsigned long vaddr)
 		goto free_area;
 
 	area->xol_mapping.name = "[uprobes]";
+	area->xol_mapping.fault = NULL;
 	area->xol_mapping.pages = area->pages;
 	area->pages[0] = alloc_page(GFP_HIGHUSER);
 	if (!area->pages[0])
diff --git a/kernel/futex.c b/kernel/futex.c
index 5d6ce6413ef1..a5d2e74c89e0 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -124,16 +124,16 @@
  *   futex_wait(futex, val);
  *
  *   waiters++; (a)
- *   mb(); (A) <-- paired with -.
- *                              |
- *   lock(hash_bucket(futex));  |
- *                              |
- *   uval = *futex;             |
- *                              |        *futex = newval;
- *                              |        sys_futex(WAKE, futex);
- *                              |          futex_wake(futex);
- *                              |
- *                              `------->  mb(); (B)
+ *   smp_mb(); (A) <-- paired with -.
+ *                                  |
+ *   lock(hash_bucket(futex));      |
+ *                                  |
+ *   uval = *futex;                 |
+ *                                  |        *futex = newval;
+ *                                  |        sys_futex(WAKE, futex);
+ *                                  |          futex_wake(futex);
+ *                                  |
+ *                                  `--------> smp_mb(); (B)
  *   if (uval == val)
  *     queue();
  *     unlock(hash_bucket(futex));
@@ -334,7 +334,7 @@ static inline void futex_get_mm(union futex_key *key)
 	/*
 	 * Ensure futex_get_mm() implies a full barrier such that
 	 * get_futex_key() implies a full barrier. This is relied upon
-	 * as full barrier (B), see the ordering comment above.
+	 * as smp_mb(); (B), see the ordering comment above.
 	 */
 	smp_mb__after_atomic();
 }
@@ -407,10 +407,10 @@ static void get_futex_key_refs(union futex_key *key)
 
 	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
 	case FUT_OFF_INODE:
-		ihold(key->shared.inode); /* implies MB (B) */
+		ihold(key->shared.inode); /* implies smp_mb(); (B) */
 		break;
 	case FUT_OFF_MMSHARED:
-		futex_get_mm(key); /* implies MB (B) */
+		futex_get_mm(key); /* implies smp_mb(); (B) */
 		break;
 	default:
 		/*
@@ -418,7 +418,7 @@ static void get_futex_key_refs(union futex_key *key)
 		 * mm, therefore the only purpose of calling get_futex_key_refs
 		 * is because we need the barrier for the lockless waiter check.
 		 */
-		smp_mb(); /* explicit MB (B) */
+		smp_mb(); /* explicit smp_mb(); (B) */
 	}
 }
 
@@ -497,7 +497,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 	if (!fshared) {
 		key->private.mm = mm;
 		key->private.address = address;
-		get_futex_key_refs(key);  /* implies MB (B) */
+		get_futex_key_refs(key);  /* implies smp_mb(); (B) */
 		return 0;
 	}
 
@@ -520,7 +520,20 @@ again:
 	else
 		err = 0;
 
-	lock_page(page);
+	/*
+	 * The treatment of mapping from this point on is critical. The page
+	 * lock protects many things but in this context the page lock
+	 * stabilizes mapping, prevents inode freeing in the shared
+	 * file-backed region case and guards against movement to swap cache.
+	 *
+	 * Strictly speaking the page lock is not needed in all cases being
+	 * considered here and page lock forces unnecessarily serialization
+	 * From this point on, mapping will be re-verified if necessary and
+	 * page lock will be acquired only if it is unavoidable
+	 */
+	page = compound_head(page);
+	mapping = READ_ONCE(page->mapping);
+
 	/*
 	 * If page->mapping is NULL, then it cannot be a PageAnon
 	 * page; but it might be the ZERO_PAGE or in the gate area or
@@ -536,19 +549,31 @@ again:
 	 * shmem_writepage move it from filecache to swapcache beneath us:
 	 * an unlikely race, but we do need to retry for page->mapping.
 	 */
-	mapping = compound_head(page)->mapping;
-	if (!mapping) {
-		int shmem_swizzled = PageSwapCache(page);
+	if (unlikely(!mapping)) {
+		int shmem_swizzled;
+
+		/*
+		 * Page lock is required to identify which special case above
+		 * applies. If this is really a shmem page then the page lock
+		 * will prevent unexpected transitions.
+		 */
+		lock_page(page);
+		shmem_swizzled = PageSwapCache(page) || page->mapping;
 		unlock_page(page);
 		put_page(page);
+
 		if (shmem_swizzled)
 			goto again;
+
 		return -EFAULT;
 	}
 
 	/*
 	 * Private mappings are handled in a simple way.
 	 *
+	 * If the futex key is stored on an anonymous page, then the associated
+	 * object is the mm which is implicitly pinned by the calling process.
+	 *
 	 * NOTE: When userspace waits on a MAP_SHARED mapping, even if
 	 * it's a read-only handle, it's expected that futexes attach to
 	 * the object not the particular process.
@@ -566,16 +591,74 @@ again:
 		key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */
 		key->private.mm = mm;
 		key->private.address = address;
+
+		get_futex_key_refs(key); /* implies smp_mb(); (B) */
+
 	} else {
+		struct inode *inode;
+
+		/*
+		 * The associated futex object in this case is the inode and
+		 * the page->mapping must be traversed. Ordinarily this should
+		 * be stabilised under page lock but it's not strictly
+		 * necessary in this case as we just want to pin the inode, not
+		 * update the radix tree or anything like that.
+		 *
+		 * The RCU read lock is taken as the inode is finally freed
+		 * under RCU. If the mapping still matches expectations then the
+		 * mapping->host can be safely accessed as being a valid inode.
+		 */
+		rcu_read_lock();
+
+		if (READ_ONCE(page->mapping) != mapping) {
+			rcu_read_unlock();
+			put_page(page);
+
+			goto again;
+		}
+
+		inode = READ_ONCE(mapping->host);
+		if (!inode) {
+			rcu_read_unlock();
+			put_page(page);
+
+			goto again;
+		}
+
+		/*
+		 * Take a reference unless it is about to be freed. Previously
+		 * this reference was taken by ihold under the page lock
+		 * pinning the inode in place so i_lock was unnecessary. The
+		 * only way for this check to fail is if the inode was
+		 * truncated in parallel so warn for now if this happens.
+		 *
+		 * We are not calling into get_futex_key_refs() in file-backed
+		 * cases, therefore a successful atomic_inc return below will
+		 * guarantee that get_futex_key() will still imply smp_mb(); (B).
+		 */
+		if (WARN_ON_ONCE(!atomic_inc_not_zero(&inode->i_count))) {
+			rcu_read_unlock();
+			put_page(page);
+
+			goto again;
+		}
+
+		/* Should be impossible but lets be paranoid for now */
+		if (WARN_ON_ONCE(inode->i_mapping != mapping)) {
+			err = -EFAULT;
+			rcu_read_unlock();
+			iput(inode);
+
+			goto out;
+		}
+
 		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
-		key->shared.inode = mapping->host;
+		key->shared.inode = inode;
 		key->shared.pgoff = basepage_index(page);
+		rcu_read_unlock();
 	}
 
-	get_futex_key_refs(key); /* implies MB (B) */
-
 out:
-	unlock_page(page);
 	put_page(page);
 	return err;
 }
@@ -1864,7 +1947,7 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 
 	q->lock_ptr = &hb->lock;
 
-	spin_lock(&hb->lock); /* implies MB (A) */
+	spin_lock(&hb->lock); /* implies smp_mb(); (A) */
 	return hb;
 }
 
@@ -1927,8 +2010,12 @@ static int unqueue_me(struct futex_q *q)
 
 	/* In the common case we don't take the spinlock, which is nice. */
 retry:
-	lock_ptr = q->lock_ptr;
-	barrier();
+	/*
+	 * q->lock_ptr can change between this read and the following spin_lock.
+	 * Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and
+	 * optimizing lock_ptr out of the logic below.
+	 */
+	lock_ptr = READ_ONCE(q->lock_ptr);
 	if (lock_ptr != NULL) {
 		spin_lock(lock_ptr);
 		/*
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 3b48dab80164..3bbfd6a9c475 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -64,6 +64,10 @@ config IRQ_DOMAIN_HIERARCHY
 	bool
 	select IRQ_DOMAIN
 
+# Generic IRQ IPI support
+config GENERIC_IRQ_IPI
+	bool
+
 # Generic MSI interrupt support
 config GENERIC_MSI_IRQ
 	bool
diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile
index 2fc9cbdf35b6..2ee42e95a3ce 100644
--- a/kernel/irq/Makefile
+++ b/kernel/irq/Makefile
@@ -8,3 +8,4 @@ obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o
 obj-$(CONFIG_GENERIC_IRQ_MIGRATION) += cpuhotplug.o
 obj-$(CONFIG_PM_SLEEP) += pm.o
 obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o
+obj-$(CONFIG_GENERIC_IRQ_IPI) += ipi.o
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 5797909f4e5b..2f9f2b0e79f2 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -961,6 +961,7 @@ void irq_chip_mask_parent(struct irq_data *data)
 	data = data->parent_data;
 	data->chip->irq_mask(data);
 }
+EXPORT_SYMBOL_GPL(irq_chip_mask_parent);
 
 /**
  * irq_chip_unmask_parent - Unmask the parent interrupt
@@ -971,6 +972,7 @@ void irq_chip_unmask_parent(struct irq_data *data)
 	data = data->parent_data;
 	data->chip->irq_unmask(data);
 }
+EXPORT_SYMBOL_GPL(irq_chip_unmask_parent);
 
 /**
  * irq_chip_eoi_parent - Invoke EOI on the parent interrupt
@@ -981,6 +983,7 @@ void irq_chip_eoi_parent(struct irq_data *data)
 	data = data->parent_data;
 	data->chip->irq_eoi(data);
 }
+EXPORT_SYMBOL_GPL(irq_chip_eoi_parent);
 
 /**
  * irq_chip_set_affinity_parent - Set affinity on the parent interrupt
@@ -1016,6 +1019,7 @@ int irq_chip_set_type_parent(struct irq_data *data, unsigned int type)
 
 	return -ENOSYS;
 }
+EXPORT_SYMBOL_GPL(irq_chip_set_type_parent);
 
 /**
  * irq_chip_retrigger_hierarchy - Retrigger an interrupt in hardware
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 57bff7857e87..a15b5485b446 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -136,10 +136,9 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc)
 {
 	irqreturn_t retval = IRQ_NONE;
 	unsigned int flags = 0, irq = desc->irq_data.irq;
-	struct irqaction *action = desc->action;
+	struct irqaction *action;
 
-	/* action might have become NULL since we dropped the lock */
-	while (action) {
+	for_each_action_of_desc(desc, action) {
 		irqreturn_t res;
 
 		trace_irq_handler_entry(irq, action);
@@ -173,7 +172,6 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc)
 		}
 
 		retval |= res;
-		action = action->next;
 	}
 
 	add_interrupt_randomness(irq, flags);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index fcab63c66905..09be2c903c6d 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -131,6 +131,9 @@ static inline void chip_bus_sync_unlock(struct irq_desc *desc)
 #define IRQ_GET_DESC_CHECK_GLOBAL	(_IRQ_DESC_CHECK)
 #define IRQ_GET_DESC_CHECK_PERCPU	(_IRQ_DESC_CHECK | _IRQ_DESC_PERCPU)
 
+#define for_each_action_of_desc(desc, act)			\
+	for (act = desc->act; act; act = act->next)
+
 struct irq_desc *
 __irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus,
 		    unsigned int check);
@@ -160,6 +163,8 @@ irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags)
 	__irq_put_desc_unlock(desc, flags, false);
 }
 
+#define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors)
+
 /*
  * Manipulation functions for irq_data.state
  */
@@ -188,6 +193,8 @@ static inline bool irqd_has_set(struct irq_data *d, unsigned int mask)
 	return __irqd_to_state(d) & mask;
 }
 
+#undef __irqd_to_state
+
 static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc)
 {
 	__this_cpu_inc(*desc->kstat_irqs);
diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c
new file mode 100644
index 000000000000..c37f34b00a11
--- /dev/null
+++ b/kernel/irq/ipi.c
@@ -0,0 +1,326 @@
+/*
+ * linux/kernel/irq/ipi.c
+ *
+ * Copyright (C) 2015 Imagination Technologies Ltd
+ * Author: Qais Yousef <qais.yousef@imgtec.com>
+ *
+ * This file contains driver APIs to the IPI subsystem.
+ */
+
+#define pr_fmt(fmt) "genirq/ipi: " fmt
+
+#include <linux/irqdomain.h>
+#include <linux/irq.h>
+
+/**
+ * irq_reserve_ipi() - Setup an IPI to destination cpumask
+ * @domain:	IPI domain
+ * @dest:	cpumask of cpus which can receive the IPI
+ *
+ * Allocate a virq that can be used to send IPI to any CPU in dest mask.
+ *
+ * On success it'll return linux irq number and 0 on failure
+ */
+unsigned int irq_reserve_ipi(struct irq_domain *domain,
+			     const struct cpumask *dest)
+{
+	unsigned int nr_irqs, offset;
+	struct irq_data *data;
+	int virq, i;
+
+	if (!domain ||!irq_domain_is_ipi(domain)) {
+		pr_warn("Reservation on a non IPI domain\n");
+		return 0;
+	}
+
+	if (!cpumask_subset(dest, cpu_possible_mask)) {
+		pr_warn("Reservation is not in possible_cpu_mask\n");
+		return 0;
+	}
+
+	nr_irqs = cpumask_weight(dest);
+	if (!nr_irqs) {
+		pr_warn("Reservation for empty destination mask\n");
+		return 0;
+	}
+
+	if (irq_domain_is_ipi_single(domain)) {
+		/*
+		 * If the underlying implementation uses a single HW irq on
+		 * all cpus then we only need a single Linux irq number for
+		 * it. We have no restrictions vs. the destination mask. The
+		 * underlying implementation can deal with holes nicely.
+		 */
+		nr_irqs = 1;
+		offset = 0;
+	} else {
+		unsigned int next;
+
+		/*
+		 * The IPI requires a seperate HW irq on each CPU. We require
+		 * that the destination mask is consecutive. If an
+		 * implementation needs to support holes, it can reserve
+		 * several IPI ranges.
+		 */
+		offset = cpumask_first(dest);
+		/*
+		 * Find a hole and if found look for another set bit after the
+		 * hole. For now we don't support this scenario.
+		 */
+		next = cpumask_next_zero(offset, dest);
+		if (next < nr_cpu_ids)
+			next = cpumask_next(next, dest);
+		if (next < nr_cpu_ids) {
+			pr_warn("Destination mask has holes\n");
+			return 0;
+		}
+	}
+
+	virq = irq_domain_alloc_descs(-1, nr_irqs, 0, NUMA_NO_NODE);
+	if (virq <= 0) {
+		pr_warn("Can't reserve IPI, failed to alloc descs\n");
+		return 0;
+	}
+
+	virq = __irq_domain_alloc_irqs(domain, virq, nr_irqs, NUMA_NO_NODE,
+				       (void *) dest, true);
+
+	if (virq <= 0) {
+		pr_warn("Can't reserve IPI, failed to alloc hw irqs\n");
+		goto free_descs;
+	}
+
+	for (i = 0; i < nr_irqs; i++) {
+		data = irq_get_irq_data(virq + i);
+		cpumask_copy(data->common->affinity, dest);
+		data->common->ipi_offset = offset;
+	}
+	return virq;
+
+free_descs:
+	irq_free_descs(virq, nr_irqs);
+	return 0;
+}
+
+/**
+ * irq_destroy_ipi() - unreserve an IPI that was previously allocated
+ * @irq:	linux irq number to be destroyed
+ *
+ * Return the IPIs allocated with irq_reserve_ipi() to the system destroying
+ * all virqs associated with them.
+ */
+void irq_destroy_ipi(unsigned int irq)
+{
+	struct irq_data *data = irq_get_irq_data(irq);
+	struct cpumask *ipimask = data ? irq_data_get_affinity_mask(data) : NULL;
+	struct irq_domain *domain;
+	unsigned int nr_irqs;
+
+	if (!irq || !data || !ipimask)
+		return;
+
+	domain = data->domain;
+	if (WARN_ON(domain == NULL))
+		return;
+
+	if (!irq_domain_is_ipi(domain)) {
+		pr_warn("Trying to destroy a non IPI domain!\n");
+		return;
+	}
+
+	if (irq_domain_is_ipi_per_cpu(domain))
+		nr_irqs = cpumask_weight(ipimask);
+	else
+		nr_irqs = 1;
+
+	irq_domain_free_irqs(irq, nr_irqs);
+}
+
+/**
+ * ipi_get_hwirq - Get the hwirq associated with an IPI to a cpu
+ * @irq:	linux irq number
+ * @cpu:	the target cpu
+ *
+ * When dealing with coprocessors IPI, we need to inform the coprocessor of
+ * the hwirq it needs to use to receive and send IPIs.
+ *
+ * Returns hwirq value on success and INVALID_HWIRQ on failure.
+ */
+irq_hw_number_t ipi_get_hwirq(unsigned int irq, unsigned int cpu)
+{
+	struct irq_data *data = irq_get_irq_data(irq);
+	struct cpumask *ipimask = data ? irq_data_get_affinity_mask(data) : NULL;
+
+	if (!data || !ipimask || cpu > nr_cpu_ids)
+		return INVALID_HWIRQ;
+
+	if (!cpumask_test_cpu(cpu, ipimask))
+		return INVALID_HWIRQ;
+
+	/*
+	 * Get the real hardware irq number if the underlying implementation
+	 * uses a seperate irq per cpu. If the underlying implementation uses
+	 * a single hardware irq for all cpus then the IPI send mechanism
+	 * needs to take care of the cpu destinations.
+	 */
+	if (irq_domain_is_ipi_per_cpu(data->domain))
+		data = irq_get_irq_data(irq + cpu - data->common->ipi_offset);
+
+	return data ? irqd_to_hwirq(data) : INVALID_HWIRQ;
+}
+EXPORT_SYMBOL_GPL(ipi_get_hwirq);
+
+static int ipi_send_verify(struct irq_chip *chip, struct irq_data *data,
+			   const struct cpumask *dest, unsigned int cpu)
+{
+	struct cpumask *ipimask = irq_data_get_affinity_mask(data);
+
+	if (!chip || !ipimask)
+		return -EINVAL;
+
+	if (!chip->ipi_send_single && !chip->ipi_send_mask)
+		return -EINVAL;
+
+	if (cpu > nr_cpu_ids)
+		return -EINVAL;
+
+	if (dest) {
+		if (!cpumask_subset(dest, ipimask))
+			return -EINVAL;
+	} else {
+		if (!cpumask_test_cpu(cpu, ipimask))
+			return -EINVAL;
+	}
+	return 0;
+}
+
+/**
+ * __ipi_send_single - send an IPI to a target Linux SMP CPU
+ * @desc:	pointer to irq_desc of the IRQ
+ * @cpu:	destination CPU, must in the destination mask passed to
+ *		irq_reserve_ipi()
+ *
+ * This function is for architecture or core code to speed up IPI sending. Not
+ * usable from driver code.
+ *
+ * Returns zero on success and negative error number on failure.
+ */
+int __ipi_send_single(struct irq_desc *desc, unsigned int cpu)
+{
+	struct irq_data *data = irq_desc_get_irq_data(desc);
+	struct irq_chip *chip = irq_data_get_irq_chip(data);
+
+#ifdef DEBUG
+	/*
+	 * Minimise the overhead by omitting the checks for Linux SMP IPIs.
+	 * Since the callers should be arch or core code which is generally
+	 * trusted, only check for errors when debugging.
+	 */
+	if (WARN_ON_ONCE(ipi_send_verify(chip, data, NULL, cpu)))
+		return -EINVAL;
+#endif
+	if (!chip->ipi_send_single) {
+		chip->ipi_send_mask(data, cpumask_of(cpu));
+		return 0;
+	}
+
+	/* FIXME: Store this information in irqdata flags */
+	if (irq_domain_is_ipi_per_cpu(data->domain) &&
+	    cpu != data->common->ipi_offset) {
+		/* use the correct data for that cpu */
+		unsigned irq = data->irq + cpu - data->common->ipi_offset;
+
+		data = irq_get_irq_data(irq);
+	}
+	chip->ipi_send_single(data, cpu);
+	return 0;
+}
+
+/**
+ * ipi_send_mask - send an IPI to target Linux SMP CPU(s)
+ * @desc:	pointer to irq_desc of the IRQ
+ * @dest:	dest CPU(s), must be a subset of the mask passed to
+ *		irq_reserve_ipi()
+ *
+ * This function is for architecture or core code to speed up IPI sending. Not
+ * usable from driver code.
+ *
+ * Returns zero on success and negative error number on failure.
+ */
+int __ipi_send_mask(struct irq_desc *desc, const struct cpumask *dest)
+{
+	struct irq_data *data = irq_desc_get_irq_data(desc);
+	struct irq_chip *chip = irq_data_get_irq_chip(data);
+	unsigned int cpu;
+
+#ifdef DEBUG
+	/*
+	 * Minimise the overhead by omitting the checks for Linux SMP IPIs.
+	 * Since the callers should be arch or core code which is generally
+	 * trusted, only check for errors when debugging.
+	 */
+	if (WARN_ON_ONCE(ipi_send_verify(chip, data, dest, 0)))
+		return -EINVAL;
+#endif
+	if (chip->ipi_send_mask) {
+		chip->ipi_send_mask(data, dest);
+		return 0;
+	}
+
+	if (irq_domain_is_ipi_per_cpu(data->domain)) {
+		unsigned int base = data->irq;
+
+		for_each_cpu(cpu, dest) {
+			unsigned irq = base + cpu - data->common->ipi_offset;
+
+			data = irq_get_irq_data(irq);
+			chip->ipi_send_single(data, cpu);
+		}
+	} else {
+		for_each_cpu(cpu, dest)
+			chip->ipi_send_single(data, cpu);
+	}
+	return 0;
+}
+
+/**
+ * ipi_send_single - Send an IPI to a single CPU
+ * @virq:	linux irq number from irq_reserve_ipi()
+ * @cpu:	destination CPU, must in the destination mask passed to
+ *		irq_reserve_ipi()
+ *
+ * Returns zero on success and negative error number on failure.
+ */
+int ipi_send_single(unsigned int virq, unsigned int cpu)
+{
+	struct irq_desc *desc = irq_to_desc(virq);
+	struct irq_data *data = desc ? irq_desc_get_irq_data(desc) : NULL;
+	struct irq_chip *chip = data ? irq_data_get_irq_chip(data) : NULL;
+
+	if (WARN_ON_ONCE(ipi_send_verify(chip, data, NULL, cpu)))
+		return -EINVAL;
+
+	return __ipi_send_single(desc, cpu);
+}
+EXPORT_SYMBOL_GPL(ipi_send_single);
+
+/**
+ * ipi_send_mask - Send an IPI to target CPU(s)
+ * @virq:	linux irq number from irq_reserve_ipi()
+ * @dest:	dest CPU(s), must be a subset of the mask passed to
+ *		irq_reserve_ipi()
+ *
+ * Returns zero on success and negative error number on failure.
+ */
+int ipi_send_mask(unsigned int virq, const struct cpumask *dest)
+{
+	struct irq_desc *desc = irq_to_desc(virq);
+	struct irq_data *data = desc ? irq_desc_get_irq_data(desc) : NULL;
+	struct irq_chip *chip = data ? irq_data_get_irq_chip(data) : NULL;
+
+	if (WARN_ON_ONCE(ipi_send_verify(chip, data, dest, 0)))
+		return -EINVAL;
+
+	return __ipi_send_mask(desc, dest);
+}
+EXPORT_SYMBOL_GPL(ipi_send_mask);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 0409da0bcc33..0ccd028817d7 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -24,10 +24,27 @@
 static struct lock_class_key irq_desc_lock_class;
 
 #if defined(CONFIG_SMP)
+static int __init irq_affinity_setup(char *str)
+{
+	zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
+	cpulist_parse(str, irq_default_affinity);
+	/*
+	 * Set at least the boot cpu. We don't want to end up with
+	 * bugreports caused by random comandline masks
+	 */
+	cpumask_set_cpu(smp_processor_id(), irq_default_affinity);
+	return 1;
+}
+__setup("irqaffinity=", irq_affinity_setup);
+
 static void __init init_irq_default_affinity(void)
 {
-	alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
-	cpumask_setall(irq_default_affinity);
+#ifdef CONFIG_CPUMASK_OFFSTACK
+	if (!irq_default_affinity)
+		zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
+#endif
+	if (cpumask_empty(irq_default_affinity))
+		cpumask_setall(irq_default_affinity);
 }
 #else
 static void __init init_irq_default_affinity(void)
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 3e56d2f03e24..3a519a01118b 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -23,8 +23,6 @@ static DEFINE_MUTEX(irq_domain_mutex);
 static DEFINE_MUTEX(revmap_trees_mutex);
 static struct irq_domain *irq_default_domain;
 
-static int irq_domain_alloc_descs(int virq, unsigned int nr_irqs,
-				  irq_hw_number_t hwirq, int node);
 static void irq_domain_check_hierarchy(struct irq_domain *domain);
 
 struct irqchip_fwid {
@@ -840,8 +838,8 @@ const struct irq_domain_ops irq_domain_simple_ops = {
 };
 EXPORT_SYMBOL_GPL(irq_domain_simple_ops);
 
-static int irq_domain_alloc_descs(int virq, unsigned int cnt,
-				  irq_hw_number_t hwirq, int node)
+int irq_domain_alloc_descs(int virq, unsigned int cnt, irq_hw_number_t hwirq,
+			   int node)
 {
 	unsigned int hint;
 
@@ -895,6 +893,7 @@ struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent,
 
 	return domain;
 }
+EXPORT_SYMBOL_GPL(irq_domain_create_hierarchy);
 
 static void irq_domain_insert_irq(int virq)
 {
@@ -1045,6 +1044,7 @@ int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(irq_domain_set_hwirq_and_chip);
 
 /**
  * irq_domain_set_info - Set the complete data for a @virq in @domain
@@ -1078,6 +1078,7 @@ void irq_domain_reset_irq_data(struct irq_data *irq_data)
 	irq_data->chip = &no_irq_chip;
 	irq_data->chip_data = NULL;
 }
+EXPORT_SYMBOL_GPL(irq_domain_reset_irq_data);
 
 /**
  * irq_domain_free_irqs_common - Clear irq_data and free the parent
@@ -1275,6 +1276,7 @@ int irq_domain_alloc_irqs_parent(struct irq_domain *domain,
 						       nr_irqs, arg);
 	return -ENOSYS;
 }
+EXPORT_SYMBOL_GPL(irq_domain_alloc_irqs_parent);
 
 /**
  * irq_domain_free_irqs_parent - Free interrupts from parent domain
@@ -1292,6 +1294,7 @@ void irq_domain_free_irqs_parent(struct irq_domain *domain,
 		irq_domain_free_irqs_recursive(domain->parent, irq_base,
 					       nr_irqs);
 }
+EXPORT_SYMBOL_GPL(irq_domain_free_irqs_parent);
 
 /**
  * irq_domain_activate_irq - Call domain_ops->activate recursively to activate
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 841187239adc..64731e84c982 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -144,13 +144,11 @@ int irq_can_set_affinity(unsigned int irq)
  */
 void irq_set_thread_affinity(struct irq_desc *desc)
 {
-	struct irqaction *action = desc->action;
+	struct irqaction *action;
 
-	while (action) {
+	for_each_action_of_desc(desc, action)
 		if (action->thread)
 			set_bit(IRQTF_AFFINITY, &action->thread_flags);
-		action = action->next;
-	}
 }
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
@@ -994,7 +992,7 @@ void irq_wake_thread(unsigned int irq, void *dev_id)
 		return;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	for (action = desc->action; action; action = action->next) {
+	for_each_action_of_desc(desc, action) {
 		if (action->dev_id == dev_id) {
 			if (action->thread)
 				__irq_wake_thread(desc, action);
@@ -1609,6 +1607,9 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 	struct irq_desc *desc;
 	int retval;
 
+	if (irq == IRQ_NOTCONNECTED)
+		return -ENOTCONN;
+
 	/*
 	 * Sanity-check: shared interrupts must pass in a real dev-ID,
 	 * otherwise we'll have trouble later trying to figure out
@@ -1699,9 +1700,13 @@ EXPORT_SYMBOL(request_threaded_irq);
 int request_any_context_irq(unsigned int irq, irq_handler_t handler,
 			    unsigned long flags, const char *name, void *dev_id)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_desc *desc;
 	int ret;
 
+	if (irq == IRQ_NOTCONNECTED)
+		return -ENOTCONN;
+
+	desc = irq_to_desc(irq);
 	if (!desc)
 		return -EINVAL;
 
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index a2c02fd5d6d0..4e1b94726818 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -291,7 +291,7 @@ static int name_unique(unsigned int irq, struct irqaction *new_action)
 	int ret = 1;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	for (action = desc->action ; action; action = action->next) {
+	for_each_action_of_desc(desc, action) {
 		if ((action != new_action) && action->name &&
 				!strcmp(new_action->name, action->name)) {
 			ret = 0;
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 32144175458d..5707f97a3e6a 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -211,14 +211,12 @@ static void __report_bad_irq(struct irq_desc *desc, irqreturn_t action_ret)
 	 * desc->lock here. See synchronize_irq().
 	 */
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	action = desc->action;
-	while (action) {
+	for_each_action_of_desc(desc, action) {
 		printk(KERN_ERR "[<%p>] %pf", action->handler, action->handler);
 		if (action->thread_fn)
 			printk(KERN_CONT " threaded [<%p>] %pf",
 					action->thread_fn, action->thread_fn);
 		printk(KERN_CONT "\n");
-		action = action->next;
 	}
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 5c5987f10819..fafd1a3ef0da 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -38,6 +38,7 @@
  * during the second link stage.
  */
 extern const unsigned long kallsyms_addresses[] __weak;
+extern const int kallsyms_offsets[] __weak;
 extern const u8 kallsyms_names[] __weak;
 
 /*
@@ -47,6 +48,9 @@ extern const u8 kallsyms_names[] __weak;
 extern const unsigned long kallsyms_num_syms
 __attribute__((weak, section(".rodata")));
 
+extern const unsigned long kallsyms_relative_base
+__attribute__((weak, section(".rodata")));
+
 extern const u8 kallsyms_token_table[] __weak;
 extern const u16 kallsyms_token_index[] __weak;
 
@@ -176,6 +180,23 @@ static unsigned int get_symbol_offset(unsigned long pos)
 	return name - kallsyms_names;
 }
 
+static unsigned long kallsyms_sym_address(int idx)
+{
+	if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE))
+		return kallsyms_addresses[idx];
+
+	/* values are unsigned offsets if --absolute-percpu is not in effect */
+	if (!IS_ENABLED(CONFIG_KALLSYMS_ABSOLUTE_PERCPU))
+		return kallsyms_relative_base + (u32)kallsyms_offsets[idx];
+
+	/* ...otherwise, positive offsets are absolute values */
+	if (kallsyms_offsets[idx] >= 0)
+		return kallsyms_offsets[idx];
+
+	/* ...and negative offsets are relative to kallsyms_relative_base - 1 */
+	return kallsyms_relative_base - 1 - kallsyms_offsets[idx];
+}
+
 /* Lookup the address for this symbol. Returns 0 if not found. */
 unsigned long kallsyms_lookup_name(const char *name)
 {
@@ -187,7 +208,7 @@ unsigned long kallsyms_lookup_name(const char *name)
 		off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
 
 		if (strcmp(namebuf, name) == 0)
-			return kallsyms_addresses[i];
+			return kallsyms_sym_address(i);
 	}
 	return module_kallsyms_lookup_name(name);
 }
@@ -204,7 +225,7 @@ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
 
 	for (i = 0, off = 0; i < kallsyms_num_syms; i++) {
 		off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
-		ret = fn(data, namebuf, NULL, kallsyms_addresses[i]);
+		ret = fn(data, namebuf, NULL, kallsyms_sym_address(i));
 		if (ret != 0)
 			return ret;
 	}
@@ -220,7 +241,10 @@ static unsigned long get_symbol_pos(unsigned long addr,
 	unsigned long i, low, high, mid;
 
 	/* This kernel should never had been booted. */
-	BUG_ON(!kallsyms_addresses);
+	if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE))
+		BUG_ON(!kallsyms_addresses);
+	else
+		BUG_ON(!kallsyms_offsets);
 
 	/* Do a binary search on the sorted kallsyms_addresses array. */
 	low = 0;
@@ -228,7 +252,7 @@ static unsigned long get_symbol_pos(unsigned long addr,
 
 	while (high - low > 1) {
 		mid = low + (high - low) / 2;
-		if (kallsyms_addresses[mid] <= addr)
+		if (kallsyms_sym_address(mid) <= addr)
 			low = mid;
 		else
 			high = mid;
@@ -238,15 +262,15 @@ static unsigned long get_symbol_pos(unsigned long addr,
 	 * Search for the first aliased symbol. Aliased
 	 * symbols are symbols with the same address.
 	 */
-	while (low && kallsyms_addresses[low-1] == kallsyms_addresses[low])
+	while (low && kallsyms_sym_address(low-1) == kallsyms_sym_address(low))
 		--low;
 
-	symbol_start = kallsyms_addresses[low];
+	symbol_start = kallsyms_sym_address(low);
 
 	/* Search for next non-aliased symbol. */
 	for (i = low + 1; i < kallsyms_num_syms; i++) {
-		if (kallsyms_addresses[i] > symbol_start) {
-			symbol_end = kallsyms_addresses[i];
+		if (kallsyms_sym_address(i) > symbol_start) {
+			symbol_end = kallsyms_sym_address(i);
 			break;
 		}
 	}
@@ -470,7 +494,7 @@ static unsigned long get_ksymbol_core(struct kallsym_iter *iter)
 	unsigned off = iter->nameoff;
 
 	iter->module_name[0] = '\0';
-	iter->value = kallsyms_addresses[iter->pos];
+	iter->value = kallsyms_sym_address(iter->pos);
 
 	iter->type = kallsyms_get_symbol_type(off);
 
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 8dc659144869..8d34308ea449 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -66,13 +66,15 @@ struct resource crashk_res = {
 	.name  = "Crash kernel",
 	.start = 0,
 	.end   = 0,
-	.flags = IORESOURCE_BUSY | IORESOURCE_MEM
+	.flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
+	.desc  = IORES_DESC_CRASH_KERNEL
 };
 struct resource crashk_low_res = {
 	.name  = "Crash kernel",
 	.start = 0,
 	.end   = 0,
-	.flags = IORESOURCE_BUSY | IORESOURCE_MEM
+	.flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,
+	.desc  = IORES_DESC_CRASH_KERNEL
 };
 
 int kexec_should_crash(struct task_struct *p)
@@ -959,7 +961,7 @@ int crash_shrink_memory(unsigned long new_size)
 
 	ram_res->start = end;
 	ram_res->end = crashk_res.end;
-	ram_res->flags = IORESOURCE_BUSY | IORESOURCE_MEM;
+	ram_res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM;
 	ram_res->name = "System RAM";
 
 	crashk_res.end = end - 1;
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index b696c3f3708f..c72d2ff5896e 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -469,10 +469,10 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
 
 	/* Walk the RAM ranges and allocate a suitable range for the buffer */
 	if (image->type == KEXEC_TYPE_CRASH)
-		ret = walk_iomem_res("Crash kernel",
-				     IORESOURCE_MEM | IORESOURCE_BUSY,
-				     crashk_res.start, crashk_res.end, kbuf,
-				     locate_mem_hole_callback);
+		ret = walk_iomem_res_desc(crashk_res.desc,
+				IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
+				crashk_res.start, crashk_res.end, kbuf,
+				locate_mem_hole_callback);
 	else
 		ret = walk_system_ram_res(0, -1, kbuf,
 					  locate_mem_hole_callback);
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index a02812743a7e..b5c30d9f46c5 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -47,12 +47,12 @@
  * of times)
  */
 
-#include <linux/latencytop.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
 #include <linux/notifier.h>
 #include <linux/spinlock.h>
 #include <linux/proc_fs.h>
+#include <linux/latencytop.h>
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/list.h>
@@ -289,4 +289,16 @@ static int __init init_lstats_procfs(void)
 	proc_create("latency_stats", 0644, NULL, &lstats_fops);
 	return 0;
 }
+
+int sysctl_latencytop(struct ctl_table *table, int write,
+			void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int err;
+
+	err = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (latencytop_enabled)
+		force_schedstat_enabled();
+
+	return err;
+}
 device_initcall(init_lstats_procfs);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 60ace56618f6..53ab2f85d77e 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -123,8 +123,6 @@ static inline int debug_locks_off_graph_unlock(void)
 	return ret;
 }
 
-static int lockdep_initialized;
-
 unsigned long nr_list_entries;
 static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES];
 
@@ -150,8 +148,7 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock)
 }
 
 #ifdef CONFIG_LOCK_STAT
-static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS],
-		      cpu_lock_stats);
+static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], cpu_lock_stats);
 
 static inline u64 lockstat_clock(void)
 {
@@ -292,7 +289,7 @@ LIST_HEAD(all_lock_classes);
 #define __classhashfn(key)	hash_long((unsigned long)key, CLASSHASH_BITS)
 #define classhashentry(key)	(classhash_table + __classhashfn((key)))
 
-static struct list_head classhash_table[CLASSHASH_SIZE];
+static struct hlist_head classhash_table[CLASSHASH_SIZE];
 
 /*
  * We put the lock dependency chains into a hash-table as well, to cache
@@ -303,7 +300,7 @@ static struct list_head classhash_table[CLASSHASH_SIZE];
 #define __chainhashfn(chain)	hash_long(chain, CHAINHASH_BITS)
 #define chainhashentry(chain)	(chainhash_table + __chainhashfn((chain)))
 
-static struct list_head chainhash_table[CHAINHASH_SIZE];
+static struct hlist_head chainhash_table[CHAINHASH_SIZE];
 
 /*
  * The hash key of the lock dependency chains is a hash itself too:
@@ -434,19 +431,6 @@ unsigned int max_lockdep_depth;
 
 #ifdef CONFIG_DEBUG_LOCKDEP
 /*
- * We cannot printk in early bootup code. Not even early_printk()
- * might work. So we mark any initialization errors and printk
- * about it later on, in lockdep_info().
- */
-static int lockdep_init_error;
-static const char *lock_init_error;
-static unsigned long lockdep_init_trace_data[20];
-static struct stack_trace lockdep_init_trace = {
-	.max_entries = ARRAY_SIZE(lockdep_init_trace_data),
-	.entries = lockdep_init_trace_data,
-};
-
-/*
  * Various lockdep statistics:
  */
 DEFINE_PER_CPU(struct lockdep_stats, lockdep_stats);
@@ -666,23 +650,9 @@ static inline struct lock_class *
 look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
 {
 	struct lockdep_subclass_key *key;
-	struct list_head *hash_head;
+	struct hlist_head *hash_head;
 	struct lock_class *class;
 
-#ifdef CONFIG_DEBUG_LOCKDEP
-	/*
-	 * If the architecture calls into lockdep before initializing
-	 * the hashes then we'll warn about it later. (we cannot printk
-	 * right now)
-	 */
-	if (unlikely(!lockdep_initialized)) {
-		lockdep_init();
-		lockdep_init_error = 1;
-		lock_init_error = lock->name;
-		save_stack_trace(&lockdep_init_trace);
-	}
-#endif
-
 	if (unlikely(subclass >= MAX_LOCKDEP_SUBCLASSES)) {
 		debug_locks_off();
 		printk(KERN_ERR
@@ -719,7 +689,7 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return NULL;
 
-	list_for_each_entry_rcu(class, hash_head, hash_entry) {
+	hlist_for_each_entry_rcu(class, hash_head, hash_entry) {
 		if (class->key == key) {
 			/*
 			 * Huh! same key, different name? Did someone trample
@@ -742,7 +712,7 @@ static inline struct lock_class *
 register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 {
 	struct lockdep_subclass_key *key;
-	struct list_head *hash_head;
+	struct hlist_head *hash_head;
 	struct lock_class *class;
 
 	DEBUG_LOCKS_WARN_ON(!irqs_disabled());
@@ -774,7 +744,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	 * We have to do the hash-walk again, to avoid races
 	 * with another CPU:
 	 */
-	list_for_each_entry_rcu(class, hash_head, hash_entry) {
+	hlist_for_each_entry_rcu(class, hash_head, hash_entry) {
 		if (class->key == key)
 			goto out_unlock_set;
 	}
@@ -805,7 +775,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	 * We use RCU's safe list-add method to make
 	 * parallel walking of the hash-list safe:
 	 */
-	list_add_tail_rcu(&class->hash_entry, hash_head);
+	hlist_add_head_rcu(&class->hash_entry, hash_head);
 	/*
 	 * Add it to the global list of classes:
 	 */
@@ -1822,7 +1792,7 @@ check_deadlock(struct task_struct *curr, struct held_lock *next,
  */
 static int
 check_prev_add(struct task_struct *curr, struct held_lock *prev,
-	       struct held_lock *next, int distance, int trylock_loop)
+	       struct held_lock *next, int distance, int *stack_saved)
 {
 	struct lock_list *entry;
 	int ret;
@@ -1883,8 +1853,11 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 		}
 	}
 
-	if (!trylock_loop && !save_trace(&trace))
-		return 0;
+	if (!*stack_saved) {
+		if (!save_trace(&trace))
+			return 0;
+		*stack_saved = 1;
+	}
 
 	/*
 	 * Ok, all validations passed, add the new lock
@@ -1907,6 +1880,8 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	 * Debugging printouts:
 	 */
 	if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) {
+		/* We drop graph lock, so another thread can overwrite trace. */
+		*stack_saved = 0;
 		graph_unlock();
 		printk("\n new dependency: ");
 		print_lock_name(hlock_class(prev));
@@ -1929,7 +1904,7 @@ static int
 check_prevs_add(struct task_struct *curr, struct held_lock *next)
 {
 	int depth = curr->lockdep_depth;
-	int trylock_loop = 0;
+	int stack_saved = 0;
 	struct held_lock *hlock;
 
 	/*
@@ -1956,7 +1931,7 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 		 */
 		if (hlock->read != 2 && hlock->check) {
 			if (!check_prev_add(curr, hlock, next,
-						distance, trylock_loop))
+						distance, &stack_saved))
 				return 0;
 			/*
 			 * Stop after the first non-trylock entry,
@@ -1979,7 +1954,6 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 		if (curr->held_locks[depth].irq_context !=
 				curr->held_locks[depth-1].irq_context)
 			break;
-		trylock_loop = 1;
 	}
 	return 1;
 out_bug:
@@ -2007,6 +1981,53 @@ struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i)
 }
 
 /*
+ * Returns the index of the first held_lock of the current chain
+ */
+static inline int get_first_held_lock(struct task_struct *curr,
+					struct held_lock *hlock)
+{
+	int i;
+	struct held_lock *hlock_curr;
+
+	for (i = curr->lockdep_depth - 1; i >= 0; i--) {
+		hlock_curr = curr->held_locks + i;
+		if (hlock_curr->irq_context != hlock->irq_context)
+			break;
+
+	}
+
+	return ++i;
+}
+
+/*
+ * Checks whether the chain and the current held locks are consistent
+ * in depth and also in content. If they are not it most likely means
+ * that there was a collision during the calculation of the chain_key.
+ * Returns: 0 not passed, 1 passed
+ */
+static int check_no_collision(struct task_struct *curr,
+			struct held_lock *hlock,
+			struct lock_chain *chain)
+{
+#ifdef CONFIG_DEBUG_LOCKDEP
+	int i, j, id;
+
+	i = get_first_held_lock(curr, hlock);
+
+	if (DEBUG_LOCKS_WARN_ON(chain->depth != curr->lockdep_depth - (i - 1)))
+		return 0;
+
+	for (j = 0; j < chain->depth - 1; j++, i++) {
+		id = curr->held_locks[i].class_idx - 1;
+
+		if (DEBUG_LOCKS_WARN_ON(chain_hlocks[chain->base + j] != id))
+			return 0;
+	}
+#endif
+	return 1;
+}
+
+/*
  * Look up a dependency chain. If the key is not present yet then
  * add it and return 1 - in this case the new dependency chain is
  * validated. If the key is already hashed, return 0.
@@ -2017,9 +2038,8 @@ static inline int lookup_chain_cache(struct task_struct *curr,
 				     u64 chain_key)
 {
 	struct lock_class *class = hlock_class(hlock);
-	struct list_head *hash_head = chainhashentry(chain_key);
+	struct hlist_head *hash_head = chainhashentry(chain_key);
 	struct lock_chain *chain;
-	struct held_lock *hlock_curr;
 	int i, j;
 
 	/*
@@ -2033,10 +2053,13 @@ static inline int lookup_chain_cache(struct task_struct *curr,
 	 * We can walk it lock-free, because entries only get added
 	 * to the hash:
 	 */
-	list_for_each_entry_rcu(chain, hash_head, entry) {
+	hlist_for_each_entry_rcu(chain, hash_head, entry) {
 		if (chain->chain_key == chain_key) {
 cache_hit:
 			debug_atomic_inc(chain_lookup_hits);
+			if (!check_no_collision(curr, hlock, chain))
+				return 0;
+
 			if (very_verbose(class))
 				printk("\nhash chain already cached, key: "
 					"%016Lx tail class: [%p] %s\n",
@@ -2057,7 +2080,7 @@ cache_hit:
 	/*
 	 * We have to walk the chain again locked - to avoid duplicates:
 	 */
-	list_for_each_entry(chain, hash_head, entry) {
+	hlist_for_each_entry(chain, hash_head, entry) {
 		if (chain->chain_key == chain_key) {
 			graph_unlock();
 			goto cache_hit;
@@ -2074,13 +2097,7 @@ cache_hit:
 	chain = lock_chains + nr_lock_chains++;
 	chain->chain_key = chain_key;
 	chain->irq_context = hlock->irq_context;
-	/* Find the first held_lock of current chain */
-	for (i = curr->lockdep_depth - 1; i >= 0; i--) {
-		hlock_curr = curr->held_locks + i;
-		if (hlock_curr->irq_context != hlock->irq_context)
-			break;
-	}
-	i++;
+	i = get_first_held_lock(curr, hlock);
 	chain->depth = curr->lockdep_depth + 1 - i;
 	if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) {
 		chain->base = nr_chain_hlocks;
@@ -2091,7 +2108,7 @@ cache_hit:
 		}
 		chain_hlocks[chain->base + j] = class - lock_classes;
 	}
-	list_add_tail_rcu(&chain->entry, hash_head);
+	hlist_add_head_rcu(&chain->entry, hash_head);
 	debug_atomic_inc(chain_lookup_misses);
 	inc_chains();
 
@@ -2168,7 +2185,7 @@ static void check_chain_key(struct task_struct *curr)
 {
 #ifdef CONFIG_DEBUG_LOCKDEP
 	struct held_lock *hlock, *prev_hlock = NULL;
-	unsigned int i, id;
+	unsigned int i;
 	u64 chain_key = 0;
 
 	for (i = 0; i < curr->lockdep_depth; i++) {
@@ -2185,17 +2202,16 @@ static void check_chain_key(struct task_struct *curr)
 				(unsigned long long)hlock->prev_chain_key);
 			return;
 		}
-		id = hlock->class_idx - 1;
 		/*
 		 * Whoops ran out of static storage again?
 		 */
-		if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS))
+		if (DEBUG_LOCKS_WARN_ON(hlock->class_idx > MAX_LOCKDEP_KEYS))
 			return;
 
 		if (prev_hlock && (prev_hlock->irq_context !=
 							hlock->irq_context))
 			chain_key = 0;
-		chain_key = iterate_chain_key(chain_key, id);
+		chain_key = iterate_chain_key(chain_key, hlock->class_idx);
 		prev_hlock = hlock;
 	}
 	if (chain_key != curr->curr_chain_key) {
@@ -3073,7 +3089,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	struct task_struct *curr = current;
 	struct lock_class *class = NULL;
 	struct held_lock *hlock;
-	unsigned int depth, id;
+	unsigned int depth;
 	int chain_head = 0;
 	int class_idx;
 	u64 chain_key;
@@ -3176,11 +3192,10 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	 * The 'key ID' is what is the most compact key value to drive
 	 * the hash, not class->key.
 	 */
-	id = class - lock_classes;
 	/*
 	 * Whoops, we did it again.. ran straight out of our static allocation.
 	 */
-	if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS))
+	if (DEBUG_LOCKS_WARN_ON(class_idx > MAX_LOCKDEP_KEYS))
 		return 0;
 
 	chain_key = curr->curr_chain_key;
@@ -3198,7 +3213,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 		chain_key = 0;
 		chain_head = 1;
 	}
-	chain_key = iterate_chain_key(chain_key, id);
+	chain_key = iterate_chain_key(chain_key, class_idx);
 
 	if (nest_lock && !__lock_is_held(nest_lock))
 		return print_lock_nested_lock_not_held(curr, hlock, ip);
@@ -3875,7 +3890,7 @@ void lockdep_reset(void)
 	nr_process_chains = 0;
 	debug_locks = 1;
 	for (i = 0; i < CHAINHASH_SIZE; i++)
-		INIT_LIST_HEAD(chainhash_table + i);
+		INIT_HLIST_HEAD(chainhash_table + i);
 	raw_local_irq_restore(flags);
 }
 
@@ -3894,7 +3909,7 @@ static void zap_class(struct lock_class *class)
 	/*
 	 * Unhash the class and remove it from the all_lock_classes list:
 	 */
-	list_del_rcu(&class->hash_entry);
+	hlist_del_rcu(&class->hash_entry);
 	list_del_rcu(&class->lock_entry);
 
 	RCU_INIT_POINTER(class->key, NULL);
@@ -3917,7 +3932,7 @@ static inline int within(const void *addr, void *start, unsigned long size)
 void lockdep_free_key_range(void *start, unsigned long size)
 {
 	struct lock_class *class;
-	struct list_head *head;
+	struct hlist_head *head;
 	unsigned long flags;
 	int i;
 	int locked;
@@ -3930,9 +3945,7 @@ void lockdep_free_key_range(void *start, unsigned long size)
 	 */
 	for (i = 0; i < CLASSHASH_SIZE; i++) {
 		head = classhash_table + i;
-		if (list_empty(head))
-			continue;
-		list_for_each_entry_rcu(class, head, hash_entry) {
+		hlist_for_each_entry_rcu(class, head, hash_entry) {
 			if (within(class->key, start, size))
 				zap_class(class);
 			else if (within(class->name, start, size))
@@ -3962,7 +3975,7 @@ void lockdep_free_key_range(void *start, unsigned long size)
 void lockdep_reset_lock(struct lockdep_map *lock)
 {
 	struct lock_class *class;
-	struct list_head *head;
+	struct hlist_head *head;
 	unsigned long flags;
 	int i, j;
 	int locked;
@@ -3987,9 +4000,7 @@ void lockdep_reset_lock(struct lockdep_map *lock)
 	locked = graph_lock();
 	for (i = 0; i < CLASSHASH_SIZE; i++) {
 		head = classhash_table + i;
-		if (list_empty(head))
-			continue;
-		list_for_each_entry_rcu(class, head, hash_entry) {
+		hlist_for_each_entry_rcu(class, head, hash_entry) {
 			int match = 0;
 
 			for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++)
@@ -4013,28 +4024,6 @@ out_restore:
 	raw_local_irq_restore(flags);
 }
 
-void lockdep_init(void)
-{
-	int i;
-
-	/*
-	 * Some architectures have their own start_kernel()
-	 * code which calls lockdep_init(), while we also
-	 * call lockdep_init() from the start_kernel() itself,
-	 * and we want to initialize the hashes only once:
-	 */
-	if (lockdep_initialized)
-		return;
-
-	for (i = 0; i < CLASSHASH_SIZE; i++)
-		INIT_LIST_HEAD(classhash_table + i);
-
-	for (i = 0; i < CHAINHASH_SIZE; i++)
-		INIT_LIST_HEAD(chainhash_table + i);
-
-	lockdep_initialized = 1;
-}
-
 void __init lockdep_info(void)
 {
 	printk("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n");
@@ -4061,14 +4050,6 @@ void __init lockdep_info(void)
 
 	printk(" per task-struct memory footprint: %lu bytes\n",
 		sizeof(struct held_lock) * MAX_LOCK_DEPTH);
-
-#ifdef CONFIG_DEBUG_LOCKDEP
-	if (lockdep_init_error) {
-		printk("WARNING: lockdep init error: lock '%s' was acquired before lockdep_init().\n", lock_init_error);
-		printk("Call stack leading to lockdep invocation was:\n");
-		print_stack_trace(&lockdep_init_trace, 0);
-	}
-#endif
 }
 
 static void
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index 5b9102a47ea5..c835270f0c2f 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -67,7 +67,13 @@ void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
 	node->locked = 0;
 	node->next   = NULL;
 
-	prev = xchg_acquire(lock, node);
+	/*
+	 * We rely on the full barrier with global transitivity implied by the
+	 * below xchg() to order the initialization stores above against any
+	 * observation of @node. And to provide the ACQUIRE ordering associated
+	 * with a LOCK primitive.
+	 */
+	prev = xchg(lock, node);
 	if (likely(prev == NULL)) {
 		/*
 		 * Lock acquired, don't need to set node->locked to 1. Threads
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 0551c219c40e..e364b424b019 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -716,6 +716,7 @@ static inline void
 __mutex_unlock_common_slowpath(struct mutex *lock, int nested)
 {
 	unsigned long flags;
+	WAKE_Q(wake_q);
 
 	/*
 	 * As a performance measurement, release the lock before doing other
@@ -743,11 +744,11 @@ __mutex_unlock_common_slowpath(struct mutex *lock, int nested)
 					   struct mutex_waiter, list);
 
 		debug_mutex_wake_waiter(lock, waiter);
-
-		wake_up_process(waiter->task);
+		wake_q_add(&wake_q, waiter->task);
 	}
 
 	spin_unlock_mutex(&lock->wait_lock, flags);
+	wake_up_q(&wake_q);
 }
 
 /*
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 393d1874b9e0..ce2f75e32ae1 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -358,8 +358,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	 * sequentiality; this is because not all clear_pending_set_locked()
 	 * implementations imply full barriers.
 	 */
-	while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_MASK)
-		cpu_relax();
+	smp_cond_acquire(!(atomic_read(&lock->val) & _Q_LOCKED_MASK));
 
 	/*
 	 * take ownership and clear the pending bit.
@@ -435,7 +434,7 @@ queue:
 	 *
 	 * The PV pv_wait_head_or_lock function, if active, will acquire
 	 * the lock and return a non-zero value. So we have to skip the
-	 * smp_load_acquire() call. As the next PV queue head hasn't been
+	 * smp_cond_acquire() call. As the next PV queue head hasn't been
 	 * designated yet, there is no way for the locked value to become
 	 * _Q_SLOW_VAL. So both the set_locked() and the
 	 * atomic_cmpxchg_relaxed() calls will be safe.
@@ -466,7 +465,7 @@ locked:
 			break;
 		}
 		/*
-		 * The smp_load_acquire() call above has provided the necessary
+		 * The smp_cond_acquire() call above has provided the necessary
 		 * acquire semantics required for locking. At most two
 		 * iterations of this loop may be ran.
 		 */
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 87bb235c3448..21ede57f68b3 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -55,6 +55,11 @@ struct pv_node {
 };
 
 /*
+ * Include queued spinlock statistics code
+ */
+#include "qspinlock_stat.h"
+
+/*
  * By replacing the regular queued_spin_trylock() with the function below,
  * it will be called once when a lock waiter enter the PV slowpath before
  * being queued. By allowing one lock stealing attempt here when the pending
@@ -65,9 +70,11 @@ struct pv_node {
 static inline bool pv_queued_spin_steal_lock(struct qspinlock *lock)
 {
 	struct __qspinlock *l = (void *)lock;
+	int ret = !(atomic_read(&lock->val) & _Q_LOCKED_PENDING_MASK) &&
+		   (cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0);
 
-	return !(atomic_read(&lock->val) & _Q_LOCKED_PENDING_MASK) &&
-		(cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0);
+	qstat_inc(qstat_pv_lock_stealing, ret);
+	return ret;
 }
 
 /*
@@ -138,11 +145,6 @@ static __always_inline int trylock_clear_pending(struct qspinlock *lock)
 #endif /* _Q_PENDING_BITS == 8 */
 
 /*
- * Include queued spinlock statistics code
- */
-#include "qspinlock_stat.h"
-
-/*
  * Lock and MCS node addresses hash table for fast lookup
  *
  * Hashing is done on a per-cacheline basis to minimize the need to access
@@ -398,6 +400,11 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 	if (READ_ONCE(pn->state) == vcpu_hashed)
 		lp = (struct qspinlock **)1;
 
+	/*
+	 * Tracking # of slowpath locking operations
+	 */
+	qstat_inc(qstat_pv_lock_slowpath, true);
+
 	for (;; waitcnt++) {
 		/*
 		 * Set correct vCPU state to be used by queue node wait-early
diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h
index 640dcecdd1df..eb2a2c9bc3fc 100644
--- a/kernel/locking/qspinlock_stat.h
+++ b/kernel/locking/qspinlock_stat.h
@@ -22,6 +22,7 @@
  *   pv_kick_wake	- # of vCPU kicks used for computing pv_latency_wake
  *   pv_latency_kick	- average latency (ns) of vCPU kick operation
  *   pv_latency_wake	- average latency (ns) from vCPU kick to wakeup
+ *   pv_lock_slowpath	- # of locking operations via the slowpath
  *   pv_lock_stealing	- # of lock stealing operations
  *   pv_spurious_wakeup	- # of spurious wakeups
  *   pv_wait_again	- # of vCPU wait's that happened after a vCPU kick
@@ -45,6 +46,7 @@ enum qlock_stats {
 	qstat_pv_kick_wake,
 	qstat_pv_latency_kick,
 	qstat_pv_latency_wake,
+	qstat_pv_lock_slowpath,
 	qstat_pv_lock_stealing,
 	qstat_pv_spurious_wakeup,
 	qstat_pv_wait_again,
@@ -70,6 +72,7 @@ static const char * const qstat_names[qstat_num + 1] = {
 	[qstat_pv_spurious_wakeup] = "pv_spurious_wakeup",
 	[qstat_pv_latency_kick]	   = "pv_latency_kick",
 	[qstat_pv_latency_wake]    = "pv_latency_wake",
+	[qstat_pv_lock_slowpath]   = "pv_lock_slowpath",
 	[qstat_pv_lock_stealing]   = "pv_lock_stealing",
 	[qstat_pv_wait_again]      = "pv_wait_again",
 	[qstat_pv_wait_early]      = "pv_wait_early",
@@ -279,19 +282,6 @@ static inline void __pv_wait(u8 *ptr, u8 val)
 #define pv_kick(c)	__pv_kick(c)
 #define pv_wait(p, v)	__pv_wait(p, v)
 
-/*
- * PV unfair trylock count tracking function
- */
-static inline int qstat_spin_steal_lock(struct qspinlock *lock)
-{
-	int ret = pv_queued_spin_steal_lock(lock);
-
-	qstat_inc(qstat_pv_lock_stealing, ret);
-	return ret;
-}
-#undef  queued_spin_trylock
-#define queued_spin_trylock(l)	qstat_spin_steal_lock(l)
-
 #else /* CONFIG_QUEUED_LOCK_STAT */
 
 static inline void qstat_inc(enum qlock_stats stat, bool cond)	{ }
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 70ee3775de24..584febd13e2e 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -29,10 +29,10 @@ __weak void __iomem *ioremap_cache(resource_size_t offset, unsigned long size)
 
 static void *try_ram_remap(resource_size_t offset, size_t size)
 {
-	struct page *page = pfn_to_page(offset >> PAGE_SHIFT);
+	unsigned long pfn = PHYS_PFN(offset);
 
 	/* In the simple case just return the existing linear address */
-	if (!PageHighMem(page))
+	if (pfn_valid(pfn) && !PageHighMem(pfn_to_page(pfn)))
 		return __va(offset);
 	return NULL; /* fallback to ioremap_cache */
 }
@@ -47,7 +47,7 @@ static void *try_ram_remap(resource_size_t offset, size_t size)
  * being mapped does not have i/o side effects and the __iomem
  * annotation is not applicable.
  *
- * MEMREMAP_WB - matches the default mapping for "System RAM" on
+ * MEMREMAP_WB - matches the default mapping for System RAM on
  * the architecture.  This is usually a read-allocate write-back cache.
  * Morever, if MEMREMAP_WB is specified and the requested remap region is RAM
  * memremap() will bypass establishing a new mapping and instead return
@@ -56,11 +56,12 @@ static void *try_ram_remap(resource_size_t offset, size_t size)
  * MEMREMAP_WT - establish a mapping whereby writes either bypass the
  * cache or are written through to memory and never exist in a
  * cache-dirty state with respect to program visibility.  Attempts to
- * map "System RAM" with this mapping type will fail.
+ * map System RAM with this mapping type will fail.
  */
 void *memremap(resource_size_t offset, size_t size, unsigned long flags)
 {
-	int is_ram = region_intersects(offset, size, "System RAM");
+	int is_ram = region_intersects(offset, size,
+				       IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
 	void *addr = NULL;
 
 	if (is_ram == REGION_MIXED) {
@@ -76,7 +77,7 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags)
 		 * MEMREMAP_WB is special in that it can be satisifed
 		 * from the direct map.  Some archs depend on the
 		 * capability of memremap() to autodetect cases where
-		 * the requested range is potentially in "System RAM"
+		 * the requested range is potentially in System RAM.
 		 */
 		if (is_ram == REGION_INTERSECTS)
 			addr = try_ram_remap(offset, size);
@@ -88,7 +89,7 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags)
 	 * If we don't have a mapping yet and more request flags are
 	 * pending then we will be attempting to establish a new virtual
 	 * address mapping.  Enforce that this mapping is not aliasing
-	 * "System RAM"
+	 * System RAM.
 	 */
 	if (!addr && is_ram == REGION_INTERSECTS && flags) {
 		WARN_ONCE(1, "memremap attempted on ram %pa size: %#lx\n",
@@ -114,7 +115,7 @@ EXPORT_SYMBOL(memunmap);
 
 static void devm_memremap_release(struct device *dev, void *res)
 {
-	memunmap(res);
+	memunmap(*(void **)res);
 }
 
 static int devm_memremap_match(struct device *dev, void *res, void *match_data)
@@ -136,8 +137,10 @@ void *devm_memremap(struct device *dev, resource_size_t offset,
 	if (addr) {
 		*ptr = addr;
 		devres_add(dev, ptr);
-	} else
+	} else {
 		devres_free(ptr);
+		return ERR_PTR(-ENXIO);
+	}
 
 	return addr;
 }
@@ -150,7 +153,7 @@ void devm_memunmap(struct device *dev, void *addr)
 }
 EXPORT_SYMBOL(devm_memunmap);
 
-pfn_t phys_to_pfn_t(phys_addr_t addr, unsigned long flags)
+pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags)
 {
 	return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags);
 }
@@ -268,13 +271,17 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
 void *devm_memremap_pages(struct device *dev, struct resource *res,
 		struct percpu_ref *ref, struct vmem_altmap *altmap)
 {
-	int is_ram = region_intersects(res->start, resource_size(res),
-			"System RAM");
 	resource_size_t key, align_start, align_size, align_end;
 	struct dev_pagemap *pgmap;
 	struct page_map *page_map;
+	int error, nid, is_ram;
 	unsigned long pfn;
-	int error, nid;
+
+	align_start = res->start & ~(SECTION_SIZE - 1);
+	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
+		- align_start;
+	is_ram = region_intersects(align_start, align_size,
+		IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
 
 	if (is_ram == REGION_MIXED) {
 		WARN_ONCE(1, "%s attempted on mixed region %pr\n",
@@ -312,8 +319,6 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 
 	mutex_lock(&pgmap_lock);
 	error = 0;
-	align_start = res->start & ~(SECTION_SIZE - 1);
-	align_size = ALIGN(resource_size(res), SECTION_SIZE);
 	align_end = align_start + align_size - 1;
 	for (key = align_start; key <= align_end; key += SECTION_SIZE) {
 		struct dev_pagemap *dup;
@@ -349,8 +354,13 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	for_each_device_pfn(pfn, page_map) {
 		struct page *page = pfn_to_page(pfn);
 
-		/* ZONE_DEVICE pages must never appear on a slab lru */
-		list_force_poison(&page->lru);
+		/*
+		 * ZONE_DEVICE pages union ->lru with a ->pgmap back
+		 * pointer.  It is a bug if a ZONE_DEVICE page is ever
+		 * freed or placed on a driver-private list.  Seed the
+		 * storage with LIST_POISON* values.
+		 */
+		list_del(&page->lru);
 		page->pgmap = pgmap;
 	}
 	devres_add(dev, page_map);
@@ -381,7 +391,7 @@ struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)
 	/*
 	 * 'memmap_start' is the virtual address for the first "struct
 	 * page" in this range of the vmemmap array.  In the case of
-	 * CONFIG_SPARSE_VMEMMAP a page_to_pfn conversion is simple
+	 * CONFIG_SPARSEMEM_VMEMMAP a page_to_pfn conversion is simple
 	 * pointer arithmetic, so we can perform this to_vmem_altmap()
 	 * conversion without concern for the initialization state of
 	 * the struct page fields.
@@ -390,7 +400,7 @@ struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)
 	struct dev_pagemap *pgmap;
 
 	/*
-	 * Uncoditionally retrieve a dev_pagemap associated with the
+	 * Unconditionally retrieve a dev_pagemap associated with the
 	 * given physical address, this is only for use in the
 	 * arch_{add|remove}_memory() for setting up and tearing down
 	 * the memmap.
diff --git a/kernel/module.c b/kernel/module.c
index 955410928696..87cfeb25cf65 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -303,6 +303,9 @@ struct load_info {
 	struct _ddebug *debug;
 	unsigned int num_debug;
 	bool sig_ok;
+#ifdef CONFIG_KALLSYMS
+	unsigned long mod_kallsyms_init_off;
+#endif
 	struct {
 		unsigned int sym, str, mod, vers, info, pcpu;
 	} index;
@@ -981,6 +984,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 		mod->exit();
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_GOING, mod);
+	ftrace_release_mod(mod);
+
 	async_synchronize_full();
 
 	/* Store the name of the last unloaded module for diagnostic purposes */
@@ -2480,10 +2485,21 @@ static void layout_symtab(struct module *mod, struct load_info *info)
 	strsect->sh_flags |= SHF_ALLOC;
 	strsect->sh_entsize = get_offset(mod, &mod->init_layout.size, strsect,
 					 info->index.str) | INIT_OFFSET_MASK;
-	mod->init_layout.size = debug_align(mod->init_layout.size);
 	pr_debug("\t%s\n", info->secstrings + strsect->sh_name);
+
+	/* We'll tack temporary mod_kallsyms on the end. */
+	mod->init_layout.size = ALIGN(mod->init_layout.size,
+				      __alignof__(struct mod_kallsyms));
+	info->mod_kallsyms_init_off = mod->init_layout.size;
+	mod->init_layout.size += sizeof(struct mod_kallsyms);
+	mod->init_layout.size = debug_align(mod->init_layout.size);
 }
 
+/*
+ * We use the full symtab and strtab which layout_symtab arranged to
+ * be appended to the init section.  Later we switch to the cut-down
+ * core-only ones.
+ */
 static void add_kallsyms(struct module *mod, const struct load_info *info)
 {
 	unsigned int i, ndst;
@@ -2492,29 +2508,34 @@ static void add_kallsyms(struct module *mod, const struct load_info *info)
 	char *s;
 	Elf_Shdr *symsec = &info->sechdrs[info->index.sym];
 
-	mod->symtab = (void *)symsec->sh_addr;
-	mod->num_symtab = symsec->sh_size / sizeof(Elf_Sym);
+	/* Set up to point into init section. */
+	mod->kallsyms = mod->init_layout.base + info->mod_kallsyms_init_off;
+
+	mod->kallsyms->symtab = (void *)symsec->sh_addr;
+	mod->kallsyms->num_symtab = symsec->sh_size / sizeof(Elf_Sym);
 	/* Make sure we get permanent strtab: don't use info->strtab. */
-	mod->strtab = (void *)info->sechdrs[info->index.str].sh_addr;
+	mod->kallsyms->strtab = (void *)info->sechdrs[info->index.str].sh_addr;
 
 	/* Set types up while we still have access to sections. */
-	for (i = 0; i < mod->num_symtab; i++)
-		mod->symtab[i].st_info = elf_type(&mod->symtab[i], info);
-
-	mod->core_symtab = dst = mod->core_layout.base + info->symoffs;
-	mod->core_strtab = s = mod->core_layout.base + info->stroffs;
-	src = mod->symtab;
-	for (ndst = i = 0; i < mod->num_symtab; i++) {
+	for (i = 0; i < mod->kallsyms->num_symtab; i++)
+		mod->kallsyms->symtab[i].st_info
+			= elf_type(&mod->kallsyms->symtab[i], info);
+
+	/* Now populate the cut down core kallsyms for after init. */
+	mod->core_kallsyms.symtab = dst = mod->core_layout.base + info->symoffs;
+	mod->core_kallsyms.strtab = s = mod->core_layout.base + info->stroffs;
+	src = mod->kallsyms->symtab;
+	for (ndst = i = 0; i < mod->kallsyms->num_symtab; i++) {
 		if (i == 0 ||
 		    is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum,
 				   info->index.pcpu)) {
 			dst[ndst] = src[i];
-			dst[ndst++].st_name = s - mod->core_strtab;
-			s += strlcpy(s, &mod->strtab[src[i].st_name],
+			dst[ndst++].st_name = s - mod->core_kallsyms.strtab;
+			s += strlcpy(s, &mod->kallsyms->strtab[src[i].st_name],
 				     KSYM_NAME_LEN) + 1;
 		}
 	}
-	mod->core_num_syms = ndst;
+	mod->core_kallsyms.num_symtab = ndst;
 }
 #else
 static inline void layout_symtab(struct module *mod, struct load_info *info)
@@ -3206,9 +3227,8 @@ static noinline int do_init_module(struct module *mod)
 	module_put(mod);
 	trim_init_extable(mod);
 #ifdef CONFIG_KALLSYMS
-	mod->num_symtab = mod->core_num_syms;
-	mod->symtab = mod->core_symtab;
-	mod->strtab = mod->core_strtab;
+	/* Switch to core kallsyms now init is done: kallsyms may be walking! */
+	rcu_assign_pointer(mod->kallsyms, &mod->core_kallsyms);
 #endif
 	mod_tree_remove_init(mod);
 	disable_ro_nx(&mod->init_layout);
@@ -3238,6 +3258,7 @@ fail:
 	module_put(mod);
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_GOING, mod);
+	ftrace_release_mod(mod);
 	free_module(mod);
 	wake_up_all(&module_wq);
 	return ret;
@@ -3314,6 +3335,7 @@ static int complete_formation(struct module *mod, struct load_info *info)
 	mod->state = MODULE_STATE_COMING;
 	mutex_unlock(&module_mutex);
 
+	ftrace_module_enable(mod);
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_COMING, mod);
 	return 0;
@@ -3439,7 +3461,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
 
 	/* Module is ready to execute: parsing args may do that. */
 	after_dashes = parse_args(mod->name, mod->args, mod->kp, mod->num_kp,
-				  -32768, 32767, NULL,
+				  -32768, 32767, mod,
 				  unknown_module_param_cb);
 	if (IS_ERR(after_dashes)) {
 		err = PTR_ERR(after_dashes);
@@ -3575,6 +3597,11 @@ static inline int is_arm_mapping_symbol(const char *str)
 	       && (str[2] == '\0' || str[2] == '.');
 }
 
+static const char *symname(struct mod_kallsyms *kallsyms, unsigned int symnum)
+{
+	return kallsyms->strtab + kallsyms->symtab[symnum].st_name;
+}
+
 static const char *get_ksymbol(struct module *mod,
 			       unsigned long addr,
 			       unsigned long *size,
@@ -3582,6 +3609,7 @@ static const char *get_ksymbol(struct module *mod,
 {
 	unsigned int i, best = 0;
 	unsigned long nextval;
+	struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms);
 
 	/* At worse, next value is at end of module */
 	if (within_module_init(addr, mod))
@@ -3591,32 +3619,32 @@ static const char *get_ksymbol(struct module *mod,
 
 	/* Scan for closest preceding symbol, and next symbol. (ELF
 	   starts real symbols at 1). */
-	for (i = 1; i < mod->num_symtab; i++) {
-		if (mod->symtab[i].st_shndx == SHN_UNDEF)
+	for (i = 1; i < kallsyms->num_symtab; i++) {
+		if (kallsyms->symtab[i].st_shndx == SHN_UNDEF)
 			continue;
 
 		/* We ignore unnamed symbols: they're uninformative
 		 * and inserted at a whim. */
-		if (mod->symtab[i].st_value <= addr
-		    && mod->symtab[i].st_value > mod->symtab[best].st_value
-		    && *(mod->strtab + mod->symtab[i].st_name) != '\0'
-		    && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name))
+		if (*symname(kallsyms, i) == '\0'
+		    || is_arm_mapping_symbol(symname(kallsyms, i)))
+			continue;
+
+		if (kallsyms->symtab[i].st_value <= addr
+		    && kallsyms->symtab[i].st_value > kallsyms->symtab[best].st_value)
 			best = i;
-		if (mod->symtab[i].st_value > addr
-		    && mod->symtab[i].st_value < nextval
-		    && *(mod->strtab + mod->symtab[i].st_name) != '\0'
-		    && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name))
-			nextval = mod->symtab[i].st_value;
+		if (kallsyms->symtab[i].st_value > addr
+		    && kallsyms->symtab[i].st_value < nextval)
+			nextval = kallsyms->symtab[i].st_value;
 	}
 
 	if (!best)
 		return NULL;
 
 	if (size)
-		*size = nextval - mod->symtab[best].st_value;
+		*size = nextval - kallsyms->symtab[best].st_value;
 	if (offset)
-		*offset = addr - mod->symtab[best].st_value;
-	return mod->strtab + mod->symtab[best].st_name;
+		*offset = addr - kallsyms->symtab[best].st_value;
+	return symname(kallsyms, best);
 }
 
 /* For kallsyms to ask for address resolution.  NULL means not found.  Careful
@@ -3706,19 +3734,21 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 
 	preempt_disable();
 	list_for_each_entry_rcu(mod, &modules, list) {
+		struct mod_kallsyms *kallsyms;
+
 		if (mod->state == MODULE_STATE_UNFORMED)
 			continue;
-		if (symnum < mod->num_symtab) {
-			*value = mod->symtab[symnum].st_value;
-			*type = mod->symtab[symnum].st_info;
-			strlcpy(name, mod->strtab + mod->symtab[symnum].st_name,
-				KSYM_NAME_LEN);
+		kallsyms = rcu_dereference_sched(mod->kallsyms);
+		if (symnum < kallsyms->num_symtab) {
+			*value = kallsyms->symtab[symnum].st_value;
+			*type = kallsyms->symtab[symnum].st_info;
+			strlcpy(name, symname(kallsyms, symnum), KSYM_NAME_LEN);
 			strlcpy(module_name, mod->name, MODULE_NAME_LEN);
 			*exported = is_exported(name, *value, mod);
 			preempt_enable();
 			return 0;
 		}
-		symnum -= mod->num_symtab;
+		symnum -= kallsyms->num_symtab;
 	}
 	preempt_enable();
 	return -ERANGE;
@@ -3727,11 +3757,12 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 static unsigned long mod_find_symname(struct module *mod, const char *name)
 {
 	unsigned int i;
+	struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms);
 
-	for (i = 0; i < mod->num_symtab; i++)
-		if (strcmp(name, mod->strtab+mod->symtab[i].st_name) == 0 &&
-		    mod->symtab[i].st_info != 'U')
-			return mod->symtab[i].st_value;
+	for (i = 0; i < kallsyms->num_symtab; i++)
+		if (strcmp(name, symname(kallsyms, i)) == 0 &&
+		    kallsyms->symtab[i].st_info != 'U')
+			return kallsyms->symtab[i].st_value;
 	return 0;
 }
 
@@ -3770,11 +3801,14 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
 	module_assert_mutex();
 
 	list_for_each_entry(mod, &modules, list) {
+		/* We hold module_mutex: no need for rcu_dereference_sched */
+		struct mod_kallsyms *kallsyms = mod->kallsyms;
+
 		if (mod->state == MODULE_STATE_UNFORMED)
 			continue;
-		for (i = 0; i < mod->num_symtab; i++) {
-			ret = fn(data, mod->strtab + mod->symtab[i].st_name,
-				 mod, mod->symtab[i].st_value);
+		for (i = 0; i < kallsyms->num_symtab; i++) {
+			ret = fn(data, symname(kallsyms, i),
+				 mod, kallsyms->symtab[i].st_value);
 			if (ret != 0)
 				return ret;
 		}
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index b7342a24f559..aa0f26b58426 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -1158,6 +1158,22 @@ static int __init kaslr_nohibernate_setup(char *str)
 	return nohibernate_setup(str);
 }
 
+static int __init page_poison_nohibernate_setup(char *str)
+{
+#ifdef CONFIG_PAGE_POISONING_ZERO
+	/*
+	 * The zeroing option for page poison skips the checks on alloc.
+	 * since hibernation doesn't save free pages there's no way to
+	 * guarantee the pages will still be zeroed.
+	 */
+	if (!strcmp(str, "on")) {
+		pr_info("Disabling hibernation due to page poisoning\n");
+		return nohibernate_setup(str);
+	}
+#endif
+	return 1;
+}
+
 __setup("noresume", noresume_setup);
 __setup("resume_offset=", resume_offset_setup);
 __setup("resume=", resume_setup);
@@ -1166,3 +1182,4 @@ __setup("resumewait", resumewait_setup);
 __setup("resumedelay=", resumedelay_setup);
 __setup("nohibernate", nohibernate_setup);
 __setup("kaslr", kaslr_nohibernate_setup);
+__setup("page_poison=", page_poison_nohibernate_setup);
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 564f786df470..df058bed53ce 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -30,13 +30,12 @@ static int try_to_freeze_tasks(bool user_only)
 	unsigned long end_time;
 	unsigned int todo;
 	bool wq_busy = false;
-	struct timeval start, end;
-	u64 elapsed_msecs64;
+	ktime_t start, end, elapsed;
 	unsigned int elapsed_msecs;
 	bool wakeup = false;
 	int sleep_usecs = USEC_PER_MSEC;
 
-	do_gettimeofday(&start);
+	start = ktime_get_boottime();
 
 	end_time = jiffies + msecs_to_jiffies(freeze_timeout_msecs);
 
@@ -78,10 +77,9 @@ static int try_to_freeze_tasks(bool user_only)
 			sleep_usecs *= 2;
 	}
 
-	do_gettimeofday(&end);
-	elapsed_msecs64 = timeval_to_ns(&end) - timeval_to_ns(&start);
-	do_div(elapsed_msecs64, NSEC_PER_MSEC);
-	elapsed_msecs = elapsed_msecs64;
+	end = ktime_get_boottime();
+	elapsed = ktime_sub(end, start);
+	elapsed_msecs = ktime_to_ms(elapsed);
 
 	if (todo) {
 		pr_cont("\n");
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index f9fe133c13e2..230a77225e2e 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -248,7 +248,7 @@ static int suspend_test(int level)
 {
 #ifdef CONFIG_PM_DEBUG
 	if (pm_test_level == level) {
-		printk(KERN_INFO "suspend debug: Waiting for %d second(s).\n",
+		pr_info("suspend debug: Waiting for %d second(s).\n",
 				pm_test_delay);
 		mdelay(pm_test_delay * 1000);
 		return 1;
@@ -320,7 +320,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 
 	error = dpm_suspend_late(PMSG_SUSPEND);
 	if (error) {
-		printk(KERN_ERR "PM: late suspend of devices failed\n");
+		pr_err("PM: late suspend of devices failed\n");
 		goto Platform_finish;
 	}
 	error = platform_suspend_prepare_late(state);
@@ -329,7 +329,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 
 	error = dpm_suspend_noirq(PMSG_SUSPEND);
 	if (error) {
-		printk(KERN_ERR "PM: noirq suspend of devices failed\n");
+		pr_err("PM: noirq suspend of devices failed\n");
 		goto Platform_early_resume;
 	}
 	error = platform_suspend_prepare_noirq(state);
diff --git a/kernel/profile.c b/kernel/profile.c
index 99513e1160e5..51369697466e 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -59,6 +59,7 @@ int profile_setup(char *str)
 
 	if (!strncmp(str, sleepstr, strlen(sleepstr))) {
 #ifdef CONFIG_SCHEDSTATS
+		force_schedstat_enabled();
 		prof_on = SLEEP_PROFILING;
 		if (str[strlen(sleepstr)] == ',')
 			str += strlen(sleepstr) + 1;
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index d2988d047d66..250ea67c1615 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -130,10 +130,8 @@ static struct rcu_torture __rcu *rcu_torture_current;
 static unsigned long rcu_torture_current_version;
 static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN];
 static DEFINE_SPINLOCK(rcu_torture_lock);
-static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1],
-		      rcu_torture_count) = { 0 };
-static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1],
-		      rcu_torture_batch) = { 0 };
+static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_count) = { 0 };
+static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_batch) = { 0 };
 static atomic_t rcu_torture_wcount[RCU_TORTURE_PIPE_LEN + 1];
 static atomic_t n_rcu_torture_alloc;
 static atomic_t n_rcu_torture_alloc_fail;
@@ -932,12 +930,14 @@ rcu_torture_writer(void *arg)
 	int nsynctypes = 0;
 
 	VERBOSE_TOROUT_STRING("rcu_torture_writer task started");
-	pr_alert("%s" TORTURE_FLAG
-		 " Grace periods expedited from boot/sysfs for %s,\n",
-		 torture_type, cur_ops->name);
-	pr_alert("%s" TORTURE_FLAG
-		 " Testing of dynamic grace-period expediting diabled.\n",
-		 torture_type);
+	if (!can_expedite) {
+		pr_alert("%s" TORTURE_FLAG
+			 " Grace periods expedited from boot/sysfs for %s,\n",
+			 torture_type, cur_ops->name);
+		pr_alert("%s" TORTURE_FLAG
+			 " Disabled dynamic grace-period expediting.\n",
+			 torture_type);
+	}
 
 	/* Initialize synctype[] array.  If none set, take default. */
 	if (!gp_cond1 && !gp_exp1 && !gp_normal1 && !gp_sync1)
diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h
index e492a5253e0f..196f0302e2f4 100644
--- a/kernel/rcu/tiny_plugin.h
+++ b/kernel/rcu/tiny_plugin.h
@@ -23,7 +23,7 @@
  */
 
 #include <linux/kthread.h>
-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 
@@ -122,18 +122,7 @@ free_out:
 	debugfs_remove_recursive(rcudir);
 	return 1;
 }
-
-static void __exit rcutiny_trace_cleanup(void)
-{
-	debugfs_remove_recursive(rcudir);
-}
-
-module_init(rcutiny_trace_init);
-module_exit(rcutiny_trace_cleanup);
-
-MODULE_AUTHOR("Paul E. McKenney");
-MODULE_DESCRIPTION("Read-Copy Update tracing for tiny implementation");
-MODULE_LICENSE("GPL");
+device_initcall(rcutiny_trace_init);
 
 static void check_cpu_stall(struct rcu_ctrlblk *rcp)
 {
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index e41dd4131f7a..9a535a86e732 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -108,7 +108,6 @@ RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
 RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh);
 
 static struct rcu_state *const rcu_state_p;
-static struct rcu_data __percpu *const rcu_data_p;
 LIST_HEAD(rcu_struct_flavors);
 
 /* Dump rcu_node combining tree at boot to verify correct setup. */
@@ -1083,13 +1082,12 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp,
 	rcu_sysidle_check_cpu(rdp, isidle, maxj);
 	if ((rdp->dynticks_snap & 0x1) == 0) {
 		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
-		return 1;
-	} else {
 		if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4,
 				 rdp->mynode->gpnum))
 			WRITE_ONCE(rdp->gpwrap, true);
-		return 0;
+		return 1;
 	}
+	return 0;
 }
 
 /*
@@ -1173,15 +1171,16 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 			smp_mb(); /* ->cond_resched_completed before *rcrmp. */
 			WRITE_ONCE(*rcrmp,
 				   READ_ONCE(*rcrmp) + rdp->rsp->flavor_mask);
-			resched_cpu(rdp->cpu);  /* Force CPU into scheduler. */
-			rdp->rsp->jiffies_resched += 5; /* Enable beating. */
-		} else if (ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
-			/* Time to beat on that CPU again! */
-			resched_cpu(rdp->cpu);  /* Force CPU into scheduler. */
-			rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */
 		}
+		rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */
 	}
 
+	/* And if it has been a really long time, kick the CPU as well. */
+	if (ULONG_CMP_GE(jiffies,
+			 rdp->rsp->gp_start + 2 * jiffies_till_sched_qs) ||
+	    ULONG_CMP_GE(jiffies, rdp->rsp->gp_start + jiffies_till_sched_qs))
+		resched_cpu(rdp->cpu);  /* Force CPU into scheduler. */
+
 	return 0;
 }
 
@@ -1246,7 +1245,7 @@ static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
 				if (rnp->qsmask & (1UL << cpu))
 					dump_cpu_task(rnp->grplo + cpu);
 		}
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	}
 }
 
@@ -1266,12 +1265,12 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	delta = jiffies - READ_ONCE(rsp->jiffies_stall);
 	if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;
 	}
 	WRITE_ONCE(rsp->jiffies_stall,
 		   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 
 	/*
 	 * OK, time to rat on our buddy...
@@ -1292,7 +1291,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 					ndetected++;
 				}
 		}
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	}
 
 	print_cpu_stall_info_end();
@@ -1357,7 +1356,7 @@ static void print_cpu_stall(struct rcu_state *rsp)
 	if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
 		WRITE_ONCE(rsp->jiffies_stall,
 			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 
 	/*
 	 * Attempt to revive the RCU machinery by forcing a context switch.
@@ -1595,7 +1594,7 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 	}
 unlock_out:
 	if (rnp != rnp_root)
-		raw_spin_unlock(&rnp_root->lock);
+		raw_spin_unlock_rcu_node(rnp_root);
 out:
 	if (c_out != NULL)
 		*c_out = c;
@@ -1614,7 +1613,6 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
 	int needmore;
 	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
 
-	rcu_nocb_gp_cleanup(rsp, rnp);
 	rnp->need_future_gp[c & 0x1] = 0;
 	needmore = rnp->need_future_gp[(c + 1) & 0x1];
 	trace_rcu_future_gp(rnp, rdp, c,
@@ -1635,7 +1633,7 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp)
 	    !READ_ONCE(rsp->gp_flags) ||
 	    !rsp->gp_kthread)
 		return;
-	wake_up(&rsp->gp_wq);
+	swake_up(&rsp->gp_wq);
 }
 
 /*
@@ -1815,7 +1813,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 		return;
 	}
 	needwake = __note_gp_changes(rsp, rnp, rdp);
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	if (needwake)
 		rcu_gp_kthread_wake(rsp);
 }
@@ -1840,7 +1838,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 	raw_spin_lock_irq_rcu_node(rnp);
 	if (!READ_ONCE(rsp->gp_flags)) {
 		/* Spurious wakeup, tell caller to go back to sleep.  */
-		raw_spin_unlock_irq(&rnp->lock);
+		raw_spin_unlock_irq_rcu_node(rnp);
 		return false;
 	}
 	WRITE_ONCE(rsp->gp_flags, 0); /* Clear all flags: New grace period. */
@@ -1850,7 +1848,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 		 * Grace period already in progress, don't start another.
 		 * Not supposed to be able to happen.
 		 */
-		raw_spin_unlock_irq(&rnp->lock);
+		raw_spin_unlock_irq_rcu_node(rnp);
 		return false;
 	}
 
@@ -1859,7 +1857,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 	/* Record GP times before starting GP, hence smp_store_release(). */
 	smp_store_release(&rsp->gpnum, rsp->gpnum + 1);
 	trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start"));
-	raw_spin_unlock_irq(&rnp->lock);
+	raw_spin_unlock_irq_rcu_node(rnp);
 
 	/*
 	 * Apply per-leaf buffered online and offline operations to the
@@ -1873,7 +1871,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 		if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
 		    !rnp->wait_blkd_tasks) {
 			/* Nothing to do on this leaf rcu_node structure. */
-			raw_spin_unlock_irq(&rnp->lock);
+			raw_spin_unlock_irq_rcu_node(rnp);
 			continue;
 		}
 
@@ -1907,7 +1905,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 			rcu_cleanup_dead_rnp(rnp);
 		}
 
-		raw_spin_unlock_irq(&rnp->lock);
+		raw_spin_unlock_irq_rcu_node(rnp);
 	}
 
 	/*
@@ -1938,7 +1936,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 		trace_rcu_grace_period_init(rsp->name, rnp->gpnum,
 					    rnp->level, rnp->grplo,
 					    rnp->grphi, rnp->qsmask);
-		raw_spin_unlock_irq(&rnp->lock);
+		raw_spin_unlock_irq_rcu_node(rnp);
 		cond_resched_rcu_qs();
 		WRITE_ONCE(rsp->gp_activity, jiffies);
 	}
@@ -1996,7 +1994,7 @@ static void rcu_gp_fqs(struct rcu_state *rsp, bool first_time)
 		raw_spin_lock_irq_rcu_node(rnp);
 		WRITE_ONCE(rsp->gp_flags,
 			   READ_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS);
-		raw_spin_unlock_irq(&rnp->lock);
+		raw_spin_unlock_irq_rcu_node(rnp);
 	}
 }
 
@@ -2010,6 +2008,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	int nocb = 0;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
+	struct swait_queue_head *sq;
 
 	WRITE_ONCE(rsp->gp_activity, jiffies);
 	raw_spin_lock_irq_rcu_node(rnp);
@@ -2025,7 +2024,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	 * safe for us to drop the lock in order to mark the grace
 	 * period as completed in all of the rcu_node structures.
 	 */
-	raw_spin_unlock_irq(&rnp->lock);
+	raw_spin_unlock_irq_rcu_node(rnp);
 
 	/*
 	 * Propagate new ->completed value to rcu_node structures so
@@ -2046,7 +2045,9 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 			needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
 		/* smp_mb() provided by prior unlock-lock pair. */
 		nocb += rcu_future_gp_cleanup(rsp, rnp);
-		raw_spin_unlock_irq(&rnp->lock);
+		sq = rcu_nocb_gp_get(rnp);
+		raw_spin_unlock_irq_rcu_node(rnp);
+		rcu_nocb_gp_cleanup(sq);
 		cond_resched_rcu_qs();
 		WRITE_ONCE(rsp->gp_activity, jiffies);
 		rcu_gp_slow(rsp, gp_cleanup_delay);
@@ -2068,7 +2069,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 				       READ_ONCE(rsp->gpnum),
 				       TPS("newreq"));
 	}
-	raw_spin_unlock_irq(&rnp->lock);
+	raw_spin_unlock_irq_rcu_node(rnp);
 }
 
 /*
@@ -2092,7 +2093,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 					       READ_ONCE(rsp->gpnum),
 					       TPS("reqwait"));
 			rsp->gp_state = RCU_GP_WAIT_GPS;
-			wait_event_interruptible(rsp->gp_wq,
+			swait_event_interruptible(rsp->gp_wq,
 						 READ_ONCE(rsp->gp_flags) &
 						 RCU_GP_FLAG_INIT);
 			rsp->gp_state = RCU_GP_DONE_GPS;
@@ -2122,7 +2123,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 					       READ_ONCE(rsp->gpnum),
 					       TPS("fqswait"));
 			rsp->gp_state = RCU_GP_WAIT_FQS;
-			ret = wait_event_interruptible_timeout(rsp->gp_wq,
+			ret = swait_event_interruptible_timeout(rsp->gp_wq,
 					rcu_gp_fqs_check_wake(rsp, &gf), j);
 			rsp->gp_state = RCU_GP_DOING_FQS;
 			/* Locking provides needed memory barriers. */
@@ -2234,19 +2235,21 @@ static bool rcu_start_gp(struct rcu_state *rsp)
 }
 
 /*
- * Report a full set of quiescent states to the specified rcu_state
- * data structure.  This involves cleaning up after the prior grace
- * period and letting rcu_start_gp() start up the next grace period
- * if one is needed.  Note that the caller must hold rnp->lock, which
- * is released before return.
+ * Report a full set of quiescent states to the specified rcu_state data
+ * structure.  Invoke rcu_gp_kthread_wake() to awaken the grace-period
+ * kthread if another grace period is required.  Whether we wake
+ * the grace-period kthread or it awakens itself for the next round
+ * of quiescent-state forcing, that kthread will clean up after the
+ * just-completed grace period.  Note that the caller must hold rnp->lock,
+ * which is released before return.
  */
 static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
 	__releases(rcu_get_root(rsp)->lock)
 {
 	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
 	WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
-	raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
-	rcu_gp_kthread_wake(rsp);
+	raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags);
+	swake_up(&rsp->gp_wq);  /* Memory barrier implied by swake_up() path. */
 }
 
 /*
@@ -2275,7 +2278,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 			 * Our bit has already been cleared, or the
 			 * relevant grace period is already over, so done.
 			 */
-			raw_spin_unlock_irqrestore(&rnp->lock, flags);
+			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			return;
 		}
 		WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */
@@ -2287,7 +2290,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 		if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
 
 			/* Other bits still set at this level, so done. */
-			raw_spin_unlock_irqrestore(&rnp->lock, flags);
+			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			return;
 		}
 		mask = rnp->grpmask;
@@ -2297,7 +2300,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 
 			break;
 		}
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		rnp_c = rnp;
 		rnp = rnp->parent;
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
@@ -2329,7 +2332,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
 
 	if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p ||
 	    rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;  /* Still need more quiescent states! */
 	}
 
@@ -2346,19 +2349,14 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
 	/* Report up the rest of the hierarchy, tracking current ->gpnum. */
 	gps = rnp->gpnum;
 	mask = rnp->grpmask;
-	raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
+	raw_spin_unlock_rcu_node(rnp);	/* irqs remain disabled. */
 	raw_spin_lock_rcu_node(rnp_p);	/* irqs already disabled. */
 	rcu_report_qs_rnp(mask, rsp, rnp_p, gps, flags);
 }
 
 /*
  * Record a quiescent state for the specified CPU to that CPU's rcu_data
- * structure.  This must be either called from the specified CPU, or
- * called when the specified CPU is known to be offline (and when it is
- * also known that no other CPU is concurrently trying to help the offline
- * CPU).  The lastcomp argument is used to make sure we are still in the
- * grace period of interest.  We don't want to end the current grace period
- * based on quiescent states detected in an earlier grace period!
+ * structure.  This must be called from the specified CPU.
  */
 static void
 rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
@@ -2383,14 +2381,14 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 		 */
 		rdp->cpu_no_qs.b.norm = true;	/* need qs for new gp. */
 		rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;
 	}
 	mask = rdp->grpmask;
 	if ((rnp->qsmask & mask) == 0) {
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	} else {
-		rdp->core_needs_qs = 0;
+		rdp->core_needs_qs = false;
 
 		/*
 		 * This GP can't end until cpu checks in, so all of our
@@ -2599,36 +2597,15 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 		rnp->qsmaskinit &= ~mask;
 		rnp->qsmask &= ~mask;
 		if (rnp->qsmaskinit) {
-			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
+			raw_spin_unlock_rcu_node(rnp);
+			/* irqs remain disabled. */
 			return;
 		}
-		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
+		raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
 	}
 }
 
 /*
- * The CPU is exiting the idle loop into the arch_cpu_idle_dead()
- * function.  We now remove it from the rcu_node tree's ->qsmaskinit
- * bit masks.
- */
-static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
-{
-	unsigned long flags;
-	unsigned long mask;
-	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
-	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
-
-	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
-		return;
-
-	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
-	mask = rdp->grpmask;
-	raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
-	rnp->qsmaskinitnext &= ~mask;
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
-}
-
-/*
  * The CPU has been completely removed, and some other CPU is reporting
  * this fact from process context.  Do the remainder of the cleanup,
  * including orphaning the outgoing CPU's RCU callbacks, and also
@@ -2859,7 +2836,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
 			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags);
 		} else {
 			/* Nothing to do here, so just drop the lock. */
-			raw_spin_unlock_irqrestore(&rnp->lock, flags);
+			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		}
 	}
 }
@@ -2895,12 +2872,12 @@ static void force_quiescent_state(struct rcu_state *rsp)
 	raw_spin_unlock(&rnp_old->fqslock);
 	if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		rsp->n_force_qs_lh++;
-		raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags);
 		return;  /* Someone beat us to it. */
 	}
 	WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
-	raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
-	rcu_gp_kthread_wake(rsp);
+	raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags);
+	swake_up(&rsp->gp_wq); /* Memory barrier implied by swake_up() path. */
 }
 
 /*
@@ -2925,7 +2902,7 @@ __rcu_process_callbacks(struct rcu_state *rsp)
 	if (cpu_needs_another_gp(rsp, rdp)) {
 		raw_spin_lock_rcu_node(rcu_get_root(rsp)); /* irqs disabled. */
 		needwake = rcu_start_gp(rsp);
-		raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags);
 		if (needwake)
 			rcu_gp_kthread_wake(rsp);
 	} else {
@@ -3016,7 +2993,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 
 			raw_spin_lock_rcu_node(rnp_root);
 			needwake = rcu_start_gp(rsp);
-			raw_spin_unlock(&rnp_root->lock);
+			raw_spin_unlock_rcu_node(rnp_root);
 			if (needwake)
 				rcu_gp_kthread_wake(rsp);
 		} else {
@@ -3436,14 +3413,14 @@ static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp)
 	rcu_for_each_leaf_node(rsp, rnp) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->expmaskinit == rnp->expmaskinitnext) {
-			raw_spin_unlock_irqrestore(&rnp->lock, flags);
+			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			continue;  /* No new CPUs, nothing to do. */
 		}
 
 		/* Update this node's mask, track old value for propagation. */
 		oldmask = rnp->expmaskinit;
 		rnp->expmaskinit = rnp->expmaskinitnext;
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 
 		/* If was already nonzero, nothing to propagate. */
 		if (oldmask)
@@ -3458,7 +3435,7 @@ static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp)
 			if (rnp_up->expmaskinit)
 				done = true;
 			rnp_up->expmaskinit |= mask;
-			raw_spin_unlock_irqrestore(&rnp_up->lock, flags);
+			raw_spin_unlock_irqrestore_rcu_node(rnp_up, flags);
 			if (done)
 				break;
 			mask = rnp_up->grpmask;
@@ -3481,7 +3458,7 @@ static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp)
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		WARN_ON_ONCE(rnp->expmask);
 		rnp->expmask = rnp->expmaskinit;
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	}
 }
 
@@ -3522,19 +3499,19 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 			if (!rnp->expmask)
 				rcu_initiate_boost(rnp, flags);
 			else
-				raw_spin_unlock_irqrestore(&rnp->lock, flags);
+				raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			break;
 		}
 		if (rnp->parent == NULL) {
-			raw_spin_unlock_irqrestore(&rnp->lock, flags);
+			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			if (wake) {
 				smp_mb(); /* EGP done before wake_up(). */
-				wake_up(&rsp->expedited_wq);
+				swake_up(&rsp->expedited_wq);
 			}
 			break;
 		}
 		mask = rnp->grpmask;
-		raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
+		raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled */
 		rnp = rnp->parent;
 		raw_spin_lock_rcu_node(rnp); /* irqs already disabled */
 		WARN_ON_ONCE(!(rnp->expmask & mask));
@@ -3569,7 +3546,7 @@ static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp,
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	if (!(rnp->expmask & mask)) {
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;
 	}
 	rnp->expmask &= ~mask;
@@ -3730,7 +3707,7 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 		 */
 		if (rcu_preempt_has_tasks(rnp))
 			rnp->exp_tasks = rnp->blkd_tasks.next;
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 
 		/* IPI the remaining CPUs for expedited quiescent state. */
 		mask = 1;
@@ -3747,7 +3724,7 @@ retry_ipi:
 			raw_spin_lock_irqsave_rcu_node(rnp, flags);
 			if (cpu_online(cpu) &&
 			    (rnp->expmask & mask)) {
-				raw_spin_unlock_irqrestore(&rnp->lock, flags);
+				raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 				schedule_timeout_uninterruptible(1);
 				if (cpu_online(cpu) &&
 				    (rnp->expmask & mask))
@@ -3756,7 +3733,7 @@ retry_ipi:
 			}
 			if (!(rnp->expmask & mask))
 				mask_ofl_ipi &= ~mask;
-			raw_spin_unlock_irqrestore(&rnp->lock, flags);
+			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		}
 		/* Report quiescent states for those that went offline. */
 		mask_ofl_test |= mask_ofl_ipi;
@@ -3780,7 +3757,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 	jiffies_start = jiffies;
 
 	for (;;) {
-		ret = wait_event_interruptible_timeout(
+		ret = swait_event_timeout(
 				rsp->expedited_wq,
 				sync_rcu_preempt_exp_done(rnp_root),
 				jiffies_stall);
@@ -3788,7 +3765,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 			return;
 		if (ret < 0) {
 			/* Hit a signal, disable CPU stall warnings. */
-			wait_event(rsp->expedited_wq,
+			swait_event(rsp->expedited_wq,
 				   sync_rcu_preempt_exp_done(rnp_root));
 			return;
 		}
@@ -4163,7 +4140,7 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
 			return;
 		raw_spin_lock_rcu_node(rnp); /* Interrupts already disabled. */
 		rnp->qsmaskinit |= mask;
-		raw_spin_unlock(&rnp->lock); /* Interrupts remain disabled. */
+		raw_spin_unlock_rcu_node(rnp); /* Interrupts remain disabled. */
 	}
 }
 
@@ -4187,7 +4164,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->rsp = rsp;
 	mutex_init(&rdp->exp_funnel_mutex);
 	rcu_boot_init_nocb_percpu_data(rdp);
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
 
 /*
@@ -4215,7 +4192,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rcu_sysidle_init_percpu_data(rdp->dynticks);
 	atomic_set(&rdp->dynticks->dynticks,
 		   (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1);
-	raw_spin_unlock(&rnp->lock);		/* irqs remain disabled. */
+	raw_spin_unlock_rcu_node(rnp);		/* irqs remain disabled. */
 
 	/*
 	 * Add CPU to leaf rcu_node pending-online bitmask.  Any needed
@@ -4236,7 +4213,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu);
 	rdp->core_needs_qs = false;
 	trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
 
 static void rcu_prepare_cpu(int cpu)
@@ -4247,6 +4224,46 @@ static void rcu_prepare_cpu(int cpu)
 		rcu_init_percpu_data(cpu, rsp);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * The CPU is exiting the idle loop into the arch_cpu_idle_dead()
+ * function.  We now remove it from the rcu_node tree's ->qsmaskinit
+ * bit masks.
+ * The CPU is exiting the idle loop into the arch_cpu_idle_dead()
+ * function.  We now remove it from the rcu_node tree's ->qsmaskinit
+ * bit masks.
+ */
+static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
+{
+	unsigned long flags;
+	unsigned long mask;
+	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
+
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		return;
+
+	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
+	mask = rdp->grpmask;
+	raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
+	rnp->qsmaskinitnext &= ~mask;
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+}
+
+void rcu_report_dead(unsigned int cpu)
+{
+	struct rcu_state *rsp;
+
+	/* QS for any half-done expedited RCU-sched GP. */
+	preempt_disable();
+	rcu_report_exp_rdp(&rcu_sched_state,
+			   this_cpu_ptr(rcu_sched_state.rda), true);
+	preempt_enable();
+	for_each_rcu_flavor(rsp)
+		rcu_cleanup_dying_idle_cpu(cpu, rsp);
+}
+#endif
+
 /*
  * Handle CPU online/offline notification events.
  */
@@ -4278,17 +4295,6 @@ int rcu_cpu_notify(struct notifier_block *self,
 		for_each_rcu_flavor(rsp)
 			rcu_cleanup_dying_cpu(rsp);
 		break;
-	case CPU_DYING_IDLE:
-		/* QS for any half-done expedited RCU-sched GP. */
-		preempt_disable();
-		rcu_report_exp_rdp(&rcu_sched_state,
-				   this_cpu_ptr(rcu_sched_state.rda), true);
-		preempt_enable();
-
-		for_each_rcu_flavor(rsp) {
-			rcu_cleanup_dying_idle_cpu(cpu, rsp);
-		}
-		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 	case CPU_UP_CANCELED:
@@ -4358,7 +4364,7 @@ static int __init rcu_spawn_gp_kthread(void)
 			sp.sched_priority = kthread_prio;
 			sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 		}
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		wake_up_process(t);
 	}
 	rcu_spawn_nocb_kthreads();
@@ -4449,8 +4455,8 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 		cpustride *= levelspread[i];
 		rnp = rsp->level[i];
 		for (j = 0; j < levelcnt[i]; j++, rnp++) {
-			raw_spin_lock_init(&rnp->lock);
-			lockdep_set_class_and_name(&rnp->lock,
+			raw_spin_lock_init(&ACCESS_PRIVATE(rnp, lock));
+			lockdep_set_class_and_name(&ACCESS_PRIVATE(rnp, lock),
 						   &rcu_node_class[i], buf[i]);
 			raw_spin_lock_init(&rnp->fqslock);
 			lockdep_set_class_and_name(&rnp->fqslock,
@@ -4482,8 +4488,8 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 		}
 	}
 
-	init_waitqueue_head(&rsp->gp_wq);
-	init_waitqueue_head(&rsp->expedited_wq);
+	init_swait_queue_head(&rsp->gp_wq);
+	init_swait_queue_head(&rsp->expedited_wq);
 	rnp = rsp->level[rcu_num_lvls - 1];
 	for_each_possible_cpu(i) {
 		while (i > rnp->grphi)
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 83360b4f4352..df668c0f9e64 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -27,6 +27,7 @@
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/seqlock.h>
+#include <linux/swait.h>
 #include <linux/stop_machine.h>
 
 /*
@@ -149,8 +150,9 @@ struct rcu_dynticks {
  * Definition for node within the RCU grace-period-detection hierarchy.
  */
 struct rcu_node {
-	raw_spinlock_t lock;	/* Root rcu_node's lock protects some */
-				/*  rcu_state fields as well as following. */
+	raw_spinlock_t __private lock;	/* Root rcu_node's lock protects */
+					/*  some rcu_state fields as well as */
+					/*  following. */
 	unsigned long gpnum;	/* Current grace period for this node. */
 				/*  This will either be equal to or one */
 				/*  behind the root rcu_node's gpnum. */
@@ -243,7 +245,7 @@ struct rcu_node {
 				/* Refused to boost: not sure why, though. */
 				/*  This can happen due to race conditions. */
 #ifdef CONFIG_RCU_NOCB_CPU
-	wait_queue_head_t nocb_gp_wq[2];
+	struct swait_queue_head nocb_gp_wq[2];
 				/* Place for rcu_nocb_kthread() to wait GP. */
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 	int need_future_gp[2];
@@ -399,7 +401,7 @@ struct rcu_data {
 	atomic_long_t nocb_q_count_lazy; /*  invocation (all stages). */
 	struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */
 	struct rcu_head **nocb_follower_tail;
-	wait_queue_head_t nocb_wq;	/* For nocb kthreads to sleep on. */
+	struct swait_queue_head nocb_wq; /* For nocb kthreads to sleep on. */
 	struct task_struct *nocb_kthread;
 	int nocb_defer_wakeup;		/* Defer wakeup of nocb_kthread. */
 
@@ -478,7 +480,7 @@ struct rcu_state {
 	unsigned long gpnum;			/* Current gp number. */
 	unsigned long completed;		/* # of last completed gp. */
 	struct task_struct *gp_kthread;		/* Task for grace periods. */
-	wait_queue_head_t gp_wq;		/* Where GP task waits. */
+	struct swait_queue_head gp_wq;		/* Where GP task waits. */
 	short gp_flags;				/* Commands for GP task. */
 	short gp_state;				/* GP kthread sleep state. */
 
@@ -506,7 +508,7 @@ struct rcu_state {
 	unsigned long expedited_sequence;	/* Take a ticket. */
 	atomic_long_t expedited_normal;		/* # fallbacks to normal. */
 	atomic_t expedited_need_qs;		/* # CPUs left to check in. */
-	wait_queue_head_t expedited_wq;		/* Wait for check-ins. */
+	struct swait_queue_head expedited_wq;	/* Wait for check-ins. */
 	int ncpus_snap;				/* # CPUs seen last time. */
 
 	unsigned long jiffies_force_qs;		/* Time at which to invoke */
@@ -621,7 +623,8 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp);
 static void increment_cpu_stall_ticks(void);
 static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu);
 static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
-static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp);
+static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp);
+static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq);
 static void rcu_init_one_nocb(struct rcu_node *rnp);
 static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
 			    bool lazy, unsigned long flags);
@@ -680,7 +683,7 @@ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
 #endif /* #else #ifdef CONFIG_PPC */
 
 /*
- * Wrappers for the rcu_node::lock acquire.
+ * Wrappers for the rcu_node::lock acquire and release.
  *
  * Because the rcu_nodes form a tree, the tree traversal locking will observe
  * different lock values, this in turn means that an UNLOCK of one level
@@ -689,29 +692,48 @@ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
  *
  * In order to restore full ordering between tree levels, augment the regular
  * lock acquire functions with smp_mb__after_unlock_lock().
+ *
+ * As ->lock of struct rcu_node is a __private field, therefore one should use
+ * these wrappers rather than directly call raw_spin_{lock,unlock}* on ->lock.
  */
 static inline void raw_spin_lock_rcu_node(struct rcu_node *rnp)
 {
-	raw_spin_lock(&rnp->lock);
+	raw_spin_lock(&ACCESS_PRIVATE(rnp, lock));
 	smp_mb__after_unlock_lock();
 }
 
+static inline void raw_spin_unlock_rcu_node(struct rcu_node *rnp)
+{
+	raw_spin_unlock(&ACCESS_PRIVATE(rnp, lock));
+}
+
 static inline void raw_spin_lock_irq_rcu_node(struct rcu_node *rnp)
 {
-	raw_spin_lock_irq(&rnp->lock);
+	raw_spin_lock_irq(&ACCESS_PRIVATE(rnp, lock));
 	smp_mb__after_unlock_lock();
 }
 
-#define raw_spin_lock_irqsave_rcu_node(rnp, flags)	\
-do {							\
-	typecheck(unsigned long, flags);		\
-	raw_spin_lock_irqsave(&(rnp)->lock, flags);	\
-	smp_mb__after_unlock_lock();			\
+static inline void raw_spin_unlock_irq_rcu_node(struct rcu_node *rnp)
+{
+	raw_spin_unlock_irq(&ACCESS_PRIVATE(rnp, lock));
+}
+
+#define raw_spin_lock_irqsave_rcu_node(rnp, flags)			\
+do {									\
+	typecheck(unsigned long, flags);				\
+	raw_spin_lock_irqsave(&ACCESS_PRIVATE(rnp, lock), flags);	\
+	smp_mb__after_unlock_lock();					\
+} while (0)
+
+#define raw_spin_unlock_irqrestore_rcu_node(rnp, flags)			\
+do {									\
+	typecheck(unsigned long, flags);				\
+	raw_spin_unlock_irqrestore(&ACCESS_PRIVATE(rnp, lock), flags);	\
 } while (0)
 
 static inline bool raw_spin_trylock_rcu_node(struct rcu_node *rnp)
 {
-	bool locked = raw_spin_trylock(&rnp->lock);
+	bool locked = raw_spin_trylock(&ACCESS_PRIVATE(rnp, lock));
 
 	if (locked)
 		smp_mb__after_unlock_lock();
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 9467a8b7e756..efdf7b61ce12 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -235,7 +235,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 		rnp->gp_tasks = &t->rcu_node_entry;
 	if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD))
 		rnp->exp_tasks = &t->rcu_node_entry;
-	raw_spin_unlock(&rnp->lock); /* rrupts remain disabled. */
+	raw_spin_unlock_rcu_node(rnp); /* interrupts remain disabled. */
 
 	/*
 	 * Report the quiescent state for the expedited GP.  This expedited
@@ -489,7 +489,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 							 !!rnp->gp_tasks);
 			rcu_report_unblock_qs_rnp(rcu_state_p, rnp, flags);
 		} else {
-			raw_spin_unlock_irqrestore(&rnp->lock, flags);
+			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		}
 
 		/* Unboost if we were boosted. */
@@ -518,14 +518,14 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	if (!rcu_preempt_blocked_readers_cgp(rnp)) {
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;
 	}
 	t = list_entry(rnp->gp_tasks->prev,
 		       struct task_struct, rcu_node_entry);
 	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)
 		sched_show_task(t);
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
 
 /*
@@ -807,7 +807,6 @@ void exit_rcu(void)
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
 static struct rcu_state *const rcu_state_p = &rcu_sched_state;
-static struct rcu_data __percpu *const rcu_data_p = &rcu_sched_data;
 
 /*
  * Tell them what RCU they are running.
@@ -991,7 +990,7 @@ static int rcu_boost(struct rcu_node *rnp)
 	 * might exit their RCU read-side critical sections on their own.
 	 */
 	if (rnp->exp_tasks == NULL && rnp->boost_tasks == NULL) {
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return 0;
 	}
 
@@ -1028,7 +1027,7 @@ static int rcu_boost(struct rcu_node *rnp)
 	 */
 	t = container_of(tb, struct task_struct, rcu_node_entry);
 	rt_mutex_init_proxy_locked(&rnp->boost_mtx, t);
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	/* Lock only for side effect: boosts task t's priority. */
 	rt_mutex_lock(&rnp->boost_mtx);
 	rt_mutex_unlock(&rnp->boost_mtx);  /* Then keep lockdep happy. */
@@ -1088,7 +1087,7 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 
 	if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) {
 		rnp->n_balk_exp_gp_tasks++;
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;
 	}
 	if (rnp->exp_tasks != NULL ||
@@ -1098,13 +1097,13 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 	     ULONG_CMP_GE(jiffies, rnp->boost_time))) {
 		if (rnp->exp_tasks == NULL)
 			rnp->boost_tasks = rnp->gp_tasks;
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		t = rnp->boost_kthread_task;
 		if (t)
 			rcu_wake_cond(t, rnp->boost_kthread_status);
 	} else {
 		rcu_initiate_boost_trace(rnp);
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	}
 }
 
@@ -1172,7 +1171,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 		return PTR_ERR(t);
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	rnp->boost_kthread_task = t;
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	sp.sched_priority = kthread_prio;
 	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 	wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
@@ -1308,7 +1307,7 @@ static void rcu_prepare_kthreads(int cpu)
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 	__releases(rnp->lock)
 {
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
 
 static void invoke_rcu_callbacks_kthread(void)
@@ -1559,7 +1558,7 @@ static void rcu_prepare_for_idle(void)
 		rnp = rdp->mynode;
 		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
 		needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
-		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
+		raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
 		if (needwake)
 			rcu_gp_kthread_wake(rsp);
 	}
@@ -1811,9 +1810,9 @@ early_param("rcu_nocb_poll", parse_rcu_nocb_poll);
  * Wake up any no-CBs CPUs' kthreads that were waiting on the just-ended
  * grace period.
  */
-static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
+static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq)
 {
-	wake_up_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]);
+	swake_up_all(sq);
 }
 
 /*
@@ -1829,10 +1828,15 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq)
 	rnp->need_future_gp[(rnp->completed + 1) & 0x1] += nrq;
 }
 
+static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp)
+{
+	return &rnp->nocb_gp_wq[rnp->completed & 0x1];
+}
+
 static void rcu_init_one_nocb(struct rcu_node *rnp)
 {
-	init_waitqueue_head(&rnp->nocb_gp_wq[0]);
-	init_waitqueue_head(&rnp->nocb_gp_wq[1]);
+	init_swait_queue_head(&rnp->nocb_gp_wq[0]);
+	init_swait_queue_head(&rnp->nocb_gp_wq[1]);
 }
 
 #ifndef CONFIG_RCU_NOCB_CPU_ALL
@@ -1857,7 +1861,7 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force)
 	if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) {
 		/* Prior smp_mb__after_atomic() orders against prior enqueue. */
 		WRITE_ONCE(rdp_leader->nocb_leader_sleep, false);
-		wake_up(&rdp_leader->nocb_wq);
+		swake_up(&rdp_leader->nocb_wq);
 	}
 }
 
@@ -2059,7 +2063,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	needwake = rcu_start_future_gp(rnp, rdp, &c);
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	if (needwake)
 		rcu_gp_kthread_wake(rdp->rsp);
 
@@ -2069,7 +2073,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	 */
 	trace_rcu_future_gp(rnp, rdp, c, TPS("StartWait"));
 	for (;;) {
-		wait_event_interruptible(
+		swait_event_interruptible(
 			rnp->nocb_gp_wq[c & 0x1],
 			(d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c)));
 		if (likely(d))
@@ -2097,7 +2101,7 @@ wait_again:
 	/* Wait for callbacks to appear. */
 	if (!rcu_nocb_poll) {
 		trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep");
-		wait_event_interruptible(my_rdp->nocb_wq,
+		swait_event_interruptible(my_rdp->nocb_wq,
 				!READ_ONCE(my_rdp->nocb_leader_sleep));
 		/* Memory barrier handled by smp_mb() calls below and repoll. */
 	} else if (firsttime) {
@@ -2172,7 +2176,7 @@ wait_again:
 			 * List was empty, wake up the follower.
 			 * Memory barriers supplied by atomic_long_add().
 			 */
-			wake_up(&rdp->nocb_wq);
+			swake_up(&rdp->nocb_wq);
 		}
 	}
 
@@ -2193,7 +2197,7 @@ static void nocb_follower_wait(struct rcu_data *rdp)
 		if (!rcu_nocb_poll) {
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 					    "FollowerSleep");
-			wait_event_interruptible(rdp->nocb_wq,
+			swait_event_interruptible(rdp->nocb_wq,
 						 READ_ONCE(rdp->nocb_follower_head));
 		} else if (firsttime) {
 			/* Don't drown trace log with "Poll"! */
@@ -2352,7 +2356,7 @@ void __init rcu_init_nohz(void)
 static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 {
 	rdp->nocb_tail = &rdp->nocb_head;
-	init_waitqueue_head(&rdp->nocb_wq);
+	init_swait_queue_head(&rdp->nocb_wq);
 	rdp->nocb_follower_tail = &rdp->nocb_follower_head;
 }
 
@@ -2502,7 +2506,7 @@ static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu)
 	return false;
 }
 
-static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
+static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq)
 {
 }
 
@@ -2510,6 +2514,11 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq)
 {
 }
 
+static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp)
+{
+	return NULL;
+}
+
 static void rcu_init_one_nocb(struct rcu_node *rnp)
 {
 }
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 76b94e19430b..ca828b41c938 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -128,6 +128,7 @@ bool rcu_gp_is_normal(void)
 {
 	return READ_ONCE(rcu_normal);
 }
+EXPORT_SYMBOL_GPL(rcu_gp_is_normal);
 
 static atomic_t rcu_expedited_nesting =
 	ATOMIC_INIT(IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT) ? 1 : 0);
diff --git a/kernel/resource.c b/kernel/resource.c
index 09c0597840b0..2e78ead30934 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -233,9 +233,9 @@ static struct resource * __request_resource(struct resource *root, struct resour
 	}
 }
 
-static int __release_resource(struct resource *old)
+static int __release_resource(struct resource *old, bool release_child)
 {
-	struct resource *tmp, **p;
+	struct resource *tmp, **p, *chd;
 
 	p = &old->parent->child;
 	for (;;) {
@@ -243,7 +243,17 @@ static int __release_resource(struct resource *old)
 		if (!tmp)
 			break;
 		if (tmp == old) {
-			*p = tmp->sibling;
+			if (release_child || !(tmp->child)) {
+				*p = tmp->sibling;
+			} else {
+				for (chd = tmp->child;; chd = chd->sibling) {
+					chd->parent = tmp->parent;
+					if (!(chd->sibling))
+						break;
+				}
+				*p = tmp->child;
+				chd->sibling = tmp->sibling;
+			}
 			old->parent = NULL;
 			return 0;
 		}
@@ -325,7 +335,7 @@ int release_resource(struct resource *old)
 	int retval;
 
 	write_lock(&resource_lock);
-	retval = __release_resource(old);
+	retval = __release_resource(old, true);
 	write_unlock(&resource_lock);
 	return retval;
 }
@@ -333,13 +343,13 @@ int release_resource(struct resource *old)
 EXPORT_SYMBOL(release_resource);
 
 /*
- * Finds the lowest iomem reosurce exists with-in [res->start.res->end)
- * the caller must specify res->start, res->end, res->flags and "name".
- * If found, returns 0, res is overwritten, if not found, returns -1.
- * This walks through whole tree and not just first level children
- * until and unless first_level_children_only is true.
+ * Finds the lowest iomem resource existing within [res->start.res->end).
+ * The caller must specify res->start, res->end, res->flags, and optionally
+ * desc.  If found, returns 0, res is overwritten, if not found, returns -1.
+ * This function walks the whole tree and not just first level children until
+ * and unless first_level_children_only is true.
  */
-static int find_next_iomem_res(struct resource *res, char *name,
+static int find_next_iomem_res(struct resource *res, unsigned long desc,
 			       bool first_level_children_only)
 {
 	resource_size_t start, end;
@@ -358,9 +368,9 @@ static int find_next_iomem_res(struct resource *res, char *name,
 	read_lock(&resource_lock);
 
 	for (p = iomem_resource.child; p; p = next_resource(p, sibling_only)) {
-		if (p->flags != res->flags)
+		if ((p->flags & res->flags) != res->flags)
 			continue;
-		if (name && strcmp(p->name, name))
+		if ((desc != IORES_DESC_NONE) && (desc != p->desc))
 			continue;
 		if (p->start > end) {
 			p = NULL;
@@ -385,15 +395,18 @@ static int find_next_iomem_res(struct resource *res, char *name,
  * Walks through iomem resources and calls func() with matching resource
  * ranges. This walks through whole tree and not just first level children.
  * All the memory ranges which overlap start,end and also match flags and
- * name are valid candidates.
+ * desc are valid candidates.
  *
- * @name: name of resource
- * @flags: resource flags
+ * @desc: I/O resource descriptor. Use IORES_DESC_NONE to skip @desc check.
+ * @flags: I/O resource flags
  * @start: start addr
  * @end: end addr
+ *
+ * NOTE: For a new descriptor search, define a new IORES_DESC in
+ * <linux/ioport.h> and set it in 'desc' of a target resource entry.
  */
-int walk_iomem_res(char *name, unsigned long flags, u64 start, u64 end,
-		void *arg, int (*func)(u64, u64, void *))
+int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start,
+		u64 end, void *arg, int (*func)(u64, u64, void *))
 {
 	struct resource res;
 	u64 orig_end;
@@ -403,23 +416,27 @@ int walk_iomem_res(char *name, unsigned long flags, u64 start, u64 end,
 	res.end = end;
 	res.flags = flags;
 	orig_end = res.end;
+
 	while ((res.start < res.end) &&
-		(!find_next_iomem_res(&res, name, false))) {
+		(!find_next_iomem_res(&res, desc, false))) {
+
 		ret = (*func)(res.start, res.end, arg);
 		if (ret)
 			break;
+
 		res.start = res.end + 1;
 		res.end = orig_end;
 	}
+
 	return ret;
 }
 
 /*
- * This function calls callback against all memory range of "System RAM"
- * which are marked as IORESOURCE_MEM and IORESOUCE_BUSY.
- * Now, this function is only for "System RAM". This function deals with
- * full ranges and not pfn. If resources are not pfn aligned, dealing
- * with pfn can truncate ranges.
+ * This function calls the @func callback against all memory ranges of type
+ * System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY.
+ * Now, this function is only for System RAM, it deals with full ranges and
+ * not PFNs. If resources are not PFN-aligned, dealing with PFNs can truncate
+ * ranges.
  */
 int walk_system_ram_res(u64 start, u64 end, void *arg,
 				int (*func)(u64, u64, void *))
@@ -430,10 +447,10 @@ int walk_system_ram_res(u64 start, u64 end, void *arg,
 
 	res.start = start;
 	res.end = end;
-	res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 	orig_end = res.end;
 	while ((res.start < res.end) &&
-		(!find_next_iomem_res(&res, "System RAM", true))) {
+		(!find_next_iomem_res(&res, IORES_DESC_NONE, true))) {
 		ret = (*func)(res.start, res.end, arg);
 		if (ret)
 			break;
@@ -446,9 +463,9 @@ int walk_system_ram_res(u64 start, u64 end, void *arg,
 #if !defined(CONFIG_ARCH_HAS_WALK_MEMORY)
 
 /*
- * This function calls callback against all memory range of "System RAM"
- * which are marked as IORESOURCE_MEM and IORESOUCE_BUSY.
- * Now, this function is only for "System RAM".
+ * This function calls the @func callback against all memory ranges of type
+ * System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY.
+ * It is to be used only for System RAM.
  */
 int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
 		void *arg, int (*func)(unsigned long, unsigned long, void *))
@@ -460,10 +477,10 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
 
 	res.start = (u64) start_pfn << PAGE_SHIFT;
 	res.end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1;
-	res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 	orig_end = res.end;
 	while ((res.start < res.end) &&
-		(find_next_iomem_res(&res, "System RAM", true) >= 0)) {
+		(find_next_iomem_res(&res, IORES_DESC_NONE, true) >= 0)) {
 		pfn = (res.start + PAGE_SIZE - 1) >> PAGE_SHIFT;
 		end_pfn = (res.end + 1) >> PAGE_SHIFT;
 		if (end_pfn > pfn)
@@ -484,7 +501,7 @@ static int __is_ram(unsigned long pfn, unsigned long nr_pages, void *arg)
 }
 /*
  * This generic page_is_ram() returns true if specified address is
- * registered as "System RAM" in iomem_resource list.
+ * registered as System RAM in iomem_resource list.
  */
 int __weak page_is_ram(unsigned long pfn)
 {
@@ -496,30 +513,34 @@ EXPORT_SYMBOL_GPL(page_is_ram);
  * region_intersects() - determine intersection of region with known resources
  * @start: region start address
  * @size: size of region
- * @name: name of resource (in iomem_resource)
+ * @flags: flags of resource (in iomem_resource)
+ * @desc: descriptor of resource (in iomem_resource) or IORES_DESC_NONE
  *
  * Check if the specified region partially overlaps or fully eclipses a
- * resource identified by @name.  Return REGION_DISJOINT if the region
- * does not overlap @name, return REGION_MIXED if the region overlaps
- * @type and another resource, and return REGION_INTERSECTS if the
- * region overlaps @type and no other defined resource. Note, that
- * REGION_INTERSECTS is also returned in the case when the specified
- * region overlaps RAM and undefined memory holes.
+ * resource identified by @flags and @desc (optional with IORES_DESC_NONE).
+ * Return REGION_DISJOINT if the region does not overlap @flags/@desc,
+ * return REGION_MIXED if the region overlaps @flags/@desc and another
+ * resource, and return REGION_INTERSECTS if the region overlaps @flags/@desc
+ * and no other defined resource. Note that REGION_INTERSECTS is also
+ * returned in the case when the specified region overlaps RAM and undefined
+ * memory holes.
  *
  * region_intersect() is used by memory remapping functions to ensure
  * the user is not remapping RAM and is a vast speed up over walking
  * through the resource table page by page.
  */
-int region_intersects(resource_size_t start, size_t size, const char *name)
+int region_intersects(resource_size_t start, size_t size, unsigned long flags,
+		      unsigned long desc)
 {
-	unsigned long flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 	resource_size_t end = start + size - 1;
 	int type = 0; int other = 0;
 	struct resource *p;
 
 	read_lock(&resource_lock);
 	for (p = iomem_resource.child; p ; p = p->sibling) {
-		bool is_type = strcmp(p->name, name) == 0 && p->flags == flags;
+		bool is_type = (((p->flags & flags) == flags) &&
+				((desc == IORES_DESC_NONE) ||
+				 (desc == p->desc)));
 
 		if (start >= p->start && start <= p->end)
 			is_type ? type++ : other++;
@@ -538,6 +559,7 @@ int region_intersects(resource_size_t start, size_t size, const char *name)
 
 	return REGION_DISJOINT;
 }
+EXPORT_SYMBOL_GPL(region_intersects);
 
 void __weak arch_remove_reservations(struct resource *avail)
 {
@@ -667,7 +689,7 @@ static int reallocate_resource(struct resource *root, struct resource *old,
 		old->start = new.start;
 		old->end = new.end;
 	} else {
-		__release_resource(old);
+		__release_resource(old, true);
 		*old = new;
 		conflict = __request_resource(root, old);
 		BUG_ON(conflict);
@@ -813,6 +835,9 @@ static struct resource * __insert_resource(struct resource *parent, struct resou
  * entirely fit within the range of the new resource, then the new
  * resource is inserted and the conflicting resources become children of
  * the new resource.
+ *
+ * This function is intended for producers of resources, such as FW modules
+ * and bus drivers.
  */
 struct resource *insert_resource_conflict(struct resource *parent, struct resource *new)
 {
@@ -830,6 +855,9 @@ struct resource *insert_resource_conflict(struct resource *parent, struct resour
  * @new: new resource to insert
  *
  * Returns 0 on success, -EBUSY if the resource can't be inserted.
+ *
+ * This function is intended for producers of resources, such as FW modules
+ * and bus drivers.
  */
 int insert_resource(struct resource *parent, struct resource *new)
 {
@@ -838,6 +866,7 @@ int insert_resource(struct resource *parent, struct resource *new)
 	conflict = insert_resource_conflict(parent, new);
 	return conflict ? -EBUSY : 0;
 }
+EXPORT_SYMBOL_GPL(insert_resource);
 
 /**
  * insert_resource_expand_to_fit - Insert a resource into the resource tree
@@ -873,6 +902,32 @@ void insert_resource_expand_to_fit(struct resource *root, struct resource *new)
 	write_unlock(&resource_lock);
 }
 
+/**
+ * remove_resource - Remove a resource in the resource tree
+ * @old: resource to remove
+ *
+ * Returns 0 on success, -EINVAL if the resource is not valid.
+ *
+ * This function removes a resource previously inserted by insert_resource()
+ * or insert_resource_conflict(), and moves the children (if any) up to
+ * where they were before.  insert_resource() and insert_resource_conflict()
+ * insert a new resource, and move any conflicting resources down to the
+ * children of the new resource.
+ *
+ * insert_resource(), insert_resource_conflict() and remove_resource() are
+ * intended for producers of resources, such as FW modules and bus drivers.
+ */
+int remove_resource(struct resource *old)
+{
+	int retval;
+
+	write_lock(&resource_lock);
+	retval = __release_resource(old, false);
+	write_unlock(&resource_lock);
+	return retval;
+}
+EXPORT_SYMBOL_GPL(remove_resource);
+
 static int __adjust_resource(struct resource *res, resource_size_t start,
 				resource_size_t size)
 {
@@ -948,6 +1003,7 @@ static void __init __reserve_region_with_split(struct resource *root,
 	res->start = start;
 	res->end = end;
 	res->flags = IORESOURCE_BUSY;
+	res->desc = IORES_DESC_NONE;
 
 	while (1) {
 
@@ -982,6 +1038,7 @@ static void __init __reserve_region_with_split(struct resource *root,
 				next_res->start = conflict->end + 1;
 				next_res->end = end;
 				next_res->flags = IORESOURCE_BUSY;
+				next_res->desc = IORES_DESC_NONE;
 			}
 		} else {
 			res->start = conflict->end + 1;
@@ -1071,21 +1128,24 @@ struct resource * __request_region(struct resource *parent,
 	res->name = name;
 	res->start = start;
 	res->end = start + n - 1;
-	res->flags = resource_type(parent);
-	res->flags |= IORESOURCE_BUSY | flags;
 
 	write_lock(&resource_lock);
 
 	for (;;) {
 		struct resource *conflict;
 
+		res->flags = resource_type(parent) | resource_ext_type(parent);
+		res->flags |= IORESOURCE_BUSY | flags;
+		res->desc = parent->desc;
+
 		conflict = __request_resource(parent, res);
 		if (!conflict)
 			break;
 		if (conflict != parent) {
-			parent = conflict;
-			if (!(conflict->flags & IORESOURCE_BUSY))
+			if (!(conflict->flags & IORESOURCE_BUSY)) {
+				parent = conflict;
 				continue;
+			}
 		}
 		if (conflict->flags & flags & IORESOURCE_MUXED) {
 			add_wait_queue(&muxed_resource_wait, &wait);
@@ -1237,6 +1297,7 @@ int release_mem_region_adjustable(struct resource *parent,
 			new_res->start = end + 1;
 			new_res->end = res->end;
 			new_res->flags = res->flags;
+			new_res->desc = res->desc;
 			new_res->parent = res->parent;
 			new_res->sibling = res->sibling;
 			new_res->child = NULL;
@@ -1412,6 +1473,7 @@ static int __init reserve_setup(char *str)
 			res->start = io_start;
 			res->end = io_start + io_num - 1;
 			res->flags = IORESOURCE_BUSY;
+			res->desc = IORES_DESC_NONE;
 			res->child = NULL;
 			if (request_resource(res->start >= 0x10000 ? &iomem_resource : &ioport_resource, res) == 0)
 				reserved = x+1;
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 67687973ce80..302d6ebd64f7 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -13,9 +13,10 @@ endif
 
 obj-y += core.o loadavg.o clock.o cputime.o
 obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
-obj-y += wait.o completion.o idle.o
+obj-y += wait.o swait.o completion.o idle.o
 obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
 obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
+obj-$(CONFIG_CPU_FREQ) += cpufreq.o
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index bc54e84675da..fedb967a9841 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -61,6 +61,7 @@
 #include <linux/static_key.h>
 #include <linux/workqueue.h>
 #include <linux/compiler.h>
+#include <linux/tick.h>
 
 /*
  * Scheduler clock - returns current time in nanosec units.
@@ -89,6 +90,8 @@ static void __set_sched_clock_stable(void)
 {
 	if (!sched_clock_stable())
 		static_key_slow_inc(&__sched_clock_stable);
+
+	tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
 }
 
 void set_sched_clock_stable(void)
@@ -108,6 +111,8 @@ static void __clear_sched_clock_stable(struct work_struct *work)
 	/* XXX worry about clock continuity */
 	if (sched_clock_stable())
 		static_key_slow_dec(&__sched_clock_stable);
+
+	tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE);
 }
 
 static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9503d590e5ef..ea8f49ae0062 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -26,6 +26,7 @@
  *              Thomas Gleixner, Mike Kravetz
  */
 
+#include <linux/kasan.h>
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/nmi.h>
@@ -66,12 +67,10 @@
 #include <linux/pagemap.h>
 #include <linux/hrtimer.h>
 #include <linux/tick.h>
-#include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
 #include <linux/slab.h>
 #include <linux/init_task.h>
-#include <linux/binfmts.h>
 #include <linux/context_tracking.h>
 #include <linux/compiler.h>
 
@@ -124,138 +123,6 @@ const_debug unsigned int sysctl_sched_features =
 
 #undef SCHED_FEAT
 
-#ifdef CONFIG_SCHED_DEBUG
-#define SCHED_FEAT(name, enabled)	\
-	#name ,
-
-static const char * const sched_feat_names[] = {
-#include "features.h"
-};
-
-#undef SCHED_FEAT
-
-static int sched_feat_show(struct seq_file *m, void *v)
-{
-	int i;
-
-	for (i = 0; i < __SCHED_FEAT_NR; i++) {
-		if (!(sysctl_sched_features & (1UL << i)))
-			seq_puts(m, "NO_");
-		seq_printf(m, "%s ", sched_feat_names[i]);
-	}
-	seq_puts(m, "\n");
-
-	return 0;
-}
-
-#ifdef HAVE_JUMP_LABEL
-
-#define jump_label_key__true  STATIC_KEY_INIT_TRUE
-#define jump_label_key__false STATIC_KEY_INIT_FALSE
-
-#define SCHED_FEAT(name, enabled)	\
-	jump_label_key__##enabled ,
-
-struct static_key sched_feat_keys[__SCHED_FEAT_NR] = {
-#include "features.h"
-};
-
-#undef SCHED_FEAT
-
-static void sched_feat_disable(int i)
-{
-	static_key_disable(&sched_feat_keys[i]);
-}
-
-static void sched_feat_enable(int i)
-{
-	static_key_enable(&sched_feat_keys[i]);
-}
-#else
-static void sched_feat_disable(int i) { };
-static void sched_feat_enable(int i) { };
-#endif /* HAVE_JUMP_LABEL */
-
-static int sched_feat_set(char *cmp)
-{
-	int i;
-	int neg = 0;
-
-	if (strncmp(cmp, "NO_", 3) == 0) {
-		neg = 1;
-		cmp += 3;
-	}
-
-	for (i = 0; i < __SCHED_FEAT_NR; i++) {
-		if (strcmp(cmp, sched_feat_names[i]) == 0) {
-			if (neg) {
-				sysctl_sched_features &= ~(1UL << i);
-				sched_feat_disable(i);
-			} else {
-				sysctl_sched_features |= (1UL << i);
-				sched_feat_enable(i);
-			}
-			break;
-		}
-	}
-
-	return i;
-}
-
-static ssize_t
-sched_feat_write(struct file *filp, const char __user *ubuf,
-		size_t cnt, loff_t *ppos)
-{
-	char buf[64];
-	char *cmp;
-	int i;
-	struct inode *inode;
-
-	if (cnt > 63)
-		cnt = 63;
-
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-
-	buf[cnt] = 0;
-	cmp = strstrip(buf);
-
-	/* Ensure the static_key remains in a consistent state */
-	inode = file_inode(filp);
-	inode_lock(inode);
-	i = sched_feat_set(cmp);
-	inode_unlock(inode);
-	if (i == __SCHED_FEAT_NR)
-		return -EINVAL;
-
-	*ppos += cnt;
-
-	return cnt;
-}
-
-static int sched_feat_open(struct inode *inode, struct file *filp)
-{
-	return single_open(filp, sched_feat_show, NULL);
-}
-
-static const struct file_operations sched_feat_fops = {
-	.open		= sched_feat_open,
-	.write		= sched_feat_write,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static __init int sched_init_debug(void)
-{
-	debugfs_create_file("sched_features", 0644, NULL, NULL,
-			&sched_feat_fops);
-
-	return 0;
-}
-late_initcall(sched_init_debug);
-#endif /* CONFIG_SCHED_DEBUG */
-
 /*
  * Number of tasks to iterate in a single balance run.
  * Limited because this is done with IRQs disabled.
@@ -453,20 +320,6 @@ static inline void init_hrtick(void)
 }
 #endif	/* CONFIG_SCHED_HRTICK */
 
-/*
- * cmpxchg based fetch_or, macro so it works for different integer types
- */
-#define fetch_or(ptr, val)						\
-({	typeof(*(ptr)) __old, __val = *(ptr);				\
- 	for (;;) {							\
- 		__old = cmpxchg((ptr), __val, __val | (val));		\
- 		if (__old == __val)					\
- 			break;						\
- 		__val = __old;						\
- 	}								\
- 	__old;								\
-})
-
 #if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG)
 /*
  * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG,
@@ -715,31 +568,36 @@ static inline bool got_nohz_idle_kick(void)
 #endif /* CONFIG_NO_HZ_COMMON */
 
 #ifdef CONFIG_NO_HZ_FULL
-bool sched_can_stop_tick(void)
+bool sched_can_stop_tick(struct rq *rq)
 {
+	int fifo_nr_running;
+
+	/* Deadline tasks, even if single, need the tick */
+	if (rq->dl.dl_nr_running)
+		return false;
+
 	/*
-	 * FIFO realtime policy runs the highest priority task. Other runnable
-	 * tasks are of a lower priority. The scheduler tick does nothing.
+	 * FIFO realtime policy runs the highest priority task (after DEADLINE).
+	 * Other runnable tasks are of a lower priority. The scheduler tick
+	 * isn't needed.
 	 */
-	if (current->policy == SCHED_FIFO)
+	fifo_nr_running = rq->rt.rt_nr_running - rq->rt.rr_nr_running;
+	if (fifo_nr_running)
 		return true;
 
 	/*
 	 * Round-robin realtime tasks time slice with other tasks at the same
-	 * realtime priority. Is this task the only one at this priority?
+	 * realtime priority.
 	 */
-	if (current->policy == SCHED_RR) {
-		struct sched_rt_entity *rt_se = &current->rt;
-
-		return list_is_singular(&rt_se->run_list);
+	if (rq->rt.rr_nr_running) {
+		if (rq->rt.rr_nr_running == 1)
+			return true;
+		else
+			return false;
 	}
 
-	/*
-	 * More than one running task need preemption.
-	 * nr_running update is assumed to be visible
-	 * after IPI is sent from wakers.
-	 */
-	if (this_rq()->nr_running > 1)
+	/* Normal multitasking need periodic preemption checks */
+	if (rq->cfs.nr_running > 1)
 		return false;
 
 	return true;
@@ -2093,7 +1951,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 
 	ttwu_queue(p, cpu);
 stat:
-	ttwu_stat(p, cpu, wake_flags);
+	if (schedstat_enabled())
+		ttwu_stat(p, cpu, wake_flags);
 out:
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
@@ -2141,7 +2000,8 @@ static void try_to_wake_up_local(struct task_struct *p)
 		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
 
 	ttwu_do_wakeup(rq, p, 0);
-	ttwu_stat(p, smp_processor_id(), 0);
+	if (schedstat_enabled())
+		ttwu_stat(p, smp_processor_id(), 0);
 out:
 	raw_spin_unlock(&p->pi_lock);
 }
@@ -2183,7 +2043,6 @@ void __dl_clear_params(struct task_struct *p)
 	dl_se->dl_bw = 0;
 
 	dl_se->dl_throttled = 0;
-	dl_se->dl_new = 1;
 	dl_se->dl_yielded = 0;
 }
 
@@ -2210,6 +2069,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 #endif
 
 #ifdef CONFIG_SCHEDSTATS
+	/* Even if schedstat is disabled, there should not be garbage */
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
 
@@ -2218,6 +2078,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	__dl_clear_params(p);
 
 	INIT_LIST_HEAD(&p->rt.run_list);
+	p->rt.timeout		= 0;
+	p->rt.time_slice	= sched_rr_timeslice;
+	p->rt.on_rq		= 0;
+	p->rt.on_list		= 0;
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 	INIT_HLIST_HEAD(&p->preempt_notifiers);
@@ -2281,6 +2145,69 @@ int sysctl_numa_balancing(struct ctl_table *table, int write,
 #endif
 #endif
 
+DEFINE_STATIC_KEY_FALSE(sched_schedstats);
+
+#ifdef CONFIG_SCHEDSTATS
+static void set_schedstats(bool enabled)
+{
+	if (enabled)
+		static_branch_enable(&sched_schedstats);
+	else
+		static_branch_disable(&sched_schedstats);
+}
+
+void force_schedstat_enabled(void)
+{
+	if (!schedstat_enabled()) {
+		pr_info("kernel profiling enabled schedstats, disable via kernel.sched_schedstats.\n");
+		static_branch_enable(&sched_schedstats);
+	}
+}
+
+static int __init setup_schedstats(char *str)
+{
+	int ret = 0;
+	if (!str)
+		goto out;
+
+	if (!strcmp(str, "enable")) {
+		set_schedstats(true);
+		ret = 1;
+	} else if (!strcmp(str, "disable")) {
+		set_schedstats(false);
+		ret = 1;
+	}
+out:
+	if (!ret)
+		pr_warn("Unable to parse schedstats=\n");
+
+	return ret;
+}
+__setup("schedstats=", setup_schedstats);
+
+#ifdef CONFIG_PROC_SYSCTL
+int sysctl_schedstats(struct ctl_table *table, int write,
+			 void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table t;
+	int err;
+	int state = static_branch_likely(&sched_schedstats);
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	t = *table;
+	t.data = &state;
+	err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
+	if (err < 0)
+		return err;
+	if (write)
+		set_schedstats(state);
+	return err;
+}
+#endif
+#endif
+
 /*
  * fork()/clone()-time setup:
  */
@@ -3010,16 +2937,6 @@ u64 scheduler_tick_max_deferment(void)
 }
 #endif
 
-notrace unsigned long get_parent_ip(unsigned long addr)
-{
-	if (in_lock_functions(addr)) {
-		addr = CALLER_ADDR2;
-		if (in_lock_functions(addr))
-			addr = CALLER_ADDR3;
-	}
-	return addr;
-}
-
 #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
 				defined(CONFIG_PREEMPT_TRACER))
 
@@ -3041,7 +2958,7 @@ void preempt_count_add(int val)
 				PREEMPT_MASK - 10);
 #endif
 	if (preempt_count() == val) {
-		unsigned long ip = get_parent_ip(CALLER_ADDR1);
+		unsigned long ip = get_lock_parent_ip();
 #ifdef CONFIG_DEBUG_PREEMPT
 		current->preempt_disable_ip = ip;
 #endif
@@ -3068,7 +2985,7 @@ void preempt_count_sub(int val)
 #endif
 
 	if (preempt_count() == val)
-		trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
+		trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
 	__preempt_count_sub(val);
 }
 EXPORT_SYMBOL(preempt_count_sub);
@@ -3280,7 +3197,6 @@ static void __sched notrace __schedule(bool preempt)
 
 		trace_sched_switch(preempt, prev, next);
 		rq = context_switch(rq, prev, next); /* unlocks the rq */
-		cpu = cpu_of(rq);
 	} else {
 		lockdep_unpin_lock(&rq->lock);
 		raw_spin_unlock_irq(&rq->lock);
@@ -3466,7 +3382,7 @@ EXPORT_SYMBOL(default_wake_function);
  */
 void rt_mutex_setprio(struct task_struct *p, int prio)
 {
-	int oldprio, queued, running, enqueue_flag = ENQUEUE_RESTORE;
+	int oldprio, queued, running, queue_flag = DEQUEUE_SAVE | DEQUEUE_MOVE;
 	struct rq *rq;
 	const struct sched_class *prev_class;
 
@@ -3494,11 +3410,15 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
 	trace_sched_pi_setprio(p, prio);
 	oldprio = p->prio;
+
+	if (oldprio == prio)
+		queue_flag &= ~DEQUEUE_MOVE;
+
 	prev_class = p->sched_class;
 	queued = task_on_rq_queued(p);
 	running = task_current(rq, p);
 	if (queued)
-		dequeue_task(rq, p, DEQUEUE_SAVE);
+		dequeue_task(rq, p, queue_flag);
 	if (running)
 		put_prev_task(rq, p);
 
@@ -3516,7 +3436,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 		if (!dl_prio(p->normal_prio) ||
 		    (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
 			p->dl.dl_boosted = 1;
-			enqueue_flag |= ENQUEUE_REPLENISH;
+			queue_flag |= ENQUEUE_REPLENISH;
 		} else
 			p->dl.dl_boosted = 0;
 		p->sched_class = &dl_sched_class;
@@ -3524,7 +3444,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 		if (dl_prio(oldprio))
 			p->dl.dl_boosted = 0;
 		if (oldprio < prio)
-			enqueue_flag |= ENQUEUE_HEAD;
+			queue_flag |= ENQUEUE_HEAD;
 		p->sched_class = &rt_sched_class;
 	} else {
 		if (dl_prio(oldprio))
@@ -3539,7 +3459,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	if (running)
 		p->sched_class->set_curr_task(rq);
 	if (queued)
-		enqueue_task(rq, p, enqueue_flag);
+		enqueue_task(rq, p, queue_flag);
 
 	check_class_changed(rq, p, prev_class, oldprio);
 out_unlock:
@@ -3895,6 +3815,7 @@ static int __sched_setscheduler(struct task_struct *p,
 	const struct sched_class *prev_class;
 	struct rq *rq;
 	int reset_on_fork;
+	int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE;
 
 	/* may grab non-irq protected spin_locks */
 	BUG_ON(in_interrupt());
@@ -4077,17 +3998,14 @@ change:
 		 * itself.
 		 */
 		new_effective_prio = rt_mutex_get_effective_prio(p, newprio);
-		if (new_effective_prio == oldprio) {
-			__setscheduler_params(p, attr);
-			task_rq_unlock(rq, p, &flags);
-			return 0;
-		}
+		if (new_effective_prio == oldprio)
+			queue_flags &= ~DEQUEUE_MOVE;
 	}
 
 	queued = task_on_rq_queued(p);
 	running = task_current(rq, p);
 	if (queued)
-		dequeue_task(rq, p, DEQUEUE_SAVE);
+		dequeue_task(rq, p, queue_flags);
 	if (running)
 		put_prev_task(rq, p);
 
@@ -4097,15 +4015,14 @@ change:
 	if (running)
 		p->sched_class->set_curr_task(rq);
 	if (queued) {
-		int enqueue_flags = ENQUEUE_RESTORE;
 		/*
 		 * We enqueue to tail when the priority of a task is
 		 * increased (user space view).
 		 */
-		if (oldprio <= p->prio)
-			enqueue_flags |= ENQUEUE_HEAD;
+		if (oldprio < p->prio)
+			queue_flags |= ENQUEUE_HEAD;
 
-		enqueue_task(rq, p, enqueue_flags);
+		enqueue_task(rq, p, queue_flags);
 	}
 
 	check_class_changed(rq, p, prev_class, oldprio);
@@ -5096,6 +5013,8 @@ void init_idle(struct task_struct *idle, int cpu)
 	idle->state = TASK_RUNNING;
 	idle->se.exec_start = sched_clock();
 
+	kasan_unpoison_task_stack(idle);
+
 #ifdef CONFIG_SMP
 	/*
 	 * Its possible that init_idle() gets called multiple times on a task,
@@ -5405,183 +5324,6 @@ static void migrate_tasks(struct rq *dead_rq)
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
-#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
-
-static struct ctl_table sd_ctl_dir[] = {
-	{
-		.procname	= "sched_domain",
-		.mode		= 0555,
-	},
-	{}
-};
-
-static struct ctl_table sd_ctl_root[] = {
-	{
-		.procname	= "kernel",
-		.mode		= 0555,
-		.child		= sd_ctl_dir,
-	},
-	{}
-};
-
-static struct ctl_table *sd_alloc_ctl_entry(int n)
-{
-	struct ctl_table *entry =
-		kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL);
-
-	return entry;
-}
-
-static void sd_free_ctl_entry(struct ctl_table **tablep)
-{
-	struct ctl_table *entry;
-
-	/*
-	 * In the intermediate directories, both the child directory and
-	 * procname are dynamically allocated and could fail but the mode
-	 * will always be set. In the lowest directory the names are
-	 * static strings and all have proc handlers.
-	 */
-	for (entry = *tablep; entry->mode; entry++) {
-		if (entry->child)
-			sd_free_ctl_entry(&entry->child);
-		if (entry->proc_handler == NULL)
-			kfree(entry->procname);
-	}
-
-	kfree(*tablep);
-	*tablep = NULL;
-}
-
-static int min_load_idx = 0;
-static int max_load_idx = CPU_LOAD_IDX_MAX-1;
-
-static void
-set_table_entry(struct ctl_table *entry,
-		const char *procname, void *data, int maxlen,
-		umode_t mode, proc_handler *proc_handler,
-		bool load_idx)
-{
-	entry->procname = procname;
-	entry->data = data;
-	entry->maxlen = maxlen;
-	entry->mode = mode;
-	entry->proc_handler = proc_handler;
-
-	if (load_idx) {
-		entry->extra1 = &min_load_idx;
-		entry->extra2 = &max_load_idx;
-	}
-}
-
-static struct ctl_table *
-sd_alloc_ctl_domain_table(struct sched_domain *sd)
-{
-	struct ctl_table *table = sd_alloc_ctl_entry(14);
-
-	if (table == NULL)
-		return NULL;
-
-	set_table_entry(&table[0], "min_interval", &sd->min_interval,
-		sizeof(long), 0644, proc_doulongvec_minmax, false);
-	set_table_entry(&table[1], "max_interval", &sd->max_interval,
-		sizeof(long), 0644, proc_doulongvec_minmax, false);
-	set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
-	set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
-	set_table_entry(&table[9], "cache_nice_tries",
-		&sd->cache_nice_tries,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
-	set_table_entry(&table[10], "flags", &sd->flags,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
-	set_table_entry(&table[11], "max_newidle_lb_cost",
-		&sd->max_newidle_lb_cost,
-		sizeof(long), 0644, proc_doulongvec_minmax, false);
-	set_table_entry(&table[12], "name", sd->name,
-		CORENAME_MAX_SIZE, 0444, proc_dostring, false);
-	/* &table[13] is terminator */
-
-	return table;
-}
-
-static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu)
-{
-	struct ctl_table *entry, *table;
-	struct sched_domain *sd;
-	int domain_num = 0, i;
-	char buf[32];
-
-	for_each_domain(cpu, sd)
-		domain_num++;
-	entry = table = sd_alloc_ctl_entry(domain_num + 1);
-	if (table == NULL)
-		return NULL;
-
-	i = 0;
-	for_each_domain(cpu, sd) {
-		snprintf(buf, 32, "domain%d", i);
-		entry->procname = kstrdup(buf, GFP_KERNEL);
-		entry->mode = 0555;
-		entry->child = sd_alloc_ctl_domain_table(sd);
-		entry++;
-		i++;
-	}
-	return table;
-}
-
-static struct ctl_table_header *sd_sysctl_header;
-static void register_sched_domain_sysctl(void)
-{
-	int i, cpu_num = num_possible_cpus();
-	struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
-	char buf[32];
-
-	WARN_ON(sd_ctl_dir[0].child);
-	sd_ctl_dir[0].child = entry;
-
-	if (entry == NULL)
-		return;
-
-	for_each_possible_cpu(i) {
-		snprintf(buf, 32, "cpu%d", i);
-		entry->procname = kstrdup(buf, GFP_KERNEL);
-		entry->mode = 0555;
-		entry->child = sd_alloc_ctl_cpu_table(i);
-		entry++;
-	}
-
-	WARN_ON(sd_sysctl_header);
-	sd_sysctl_header = register_sysctl_table(sd_ctl_root);
-}
-
-/* may be called multiple times per register */
-static void unregister_sched_domain_sysctl(void)
-{
-	unregister_sysctl_table(sd_sysctl_header);
-	sd_sysctl_header = NULL;
-	if (sd_ctl_dir[0].child)
-		sd_free_ctl_entry(&sd_ctl_dir[0].child);
-}
-#else
-static void register_sched_domain_sysctl(void)
-{
-}
-static void unregister_sched_domain_sysctl(void)
-{
-}
-#endif /* CONFIG_SCHED_DEBUG && CONFIG_SYSCTL */
-
 static void set_rq_online(struct rq *rq)
 {
 	if (!rq->online) {
@@ -5692,16 +5434,6 @@ static int sched_cpu_active(struct notifier_block *nfb,
 		set_cpu_rq_start_time();
 		return NOTIFY_OK;
 
-	case CPU_ONLINE:
-		/*
-		 * At this point a starting CPU has marked itself as online via
-		 * set_cpu_online(). But it might not yet have marked itself
-		 * as active, which is essential from here on.
-		 */
-		set_cpu_active(cpu, true);
-		stop_machine_unpark(cpu);
-		return NOTIFY_OK;
-
 	case CPU_DOWN_FAILED:
 		set_cpu_active(cpu, true);
 		return NOTIFY_OK;
@@ -6173,11 +5905,16 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 /* Setup the mask of cpus configured for isolated domains */
 static int __init isolated_cpu_setup(char *str)
 {
+	int ret;
+
 	alloc_bootmem_cpumask_var(&cpu_isolated_map);
-	cpulist_parse(str, cpu_isolated_map);
+	ret = cpulist_parse(str, cpu_isolated_map);
+	if (ret) {
+		pr_err("sched: Error, all isolcpus= values must be between 0 and %d\n", nr_cpu_ids);
+		return 0;
+	}
 	return 1;
 }
-
 __setup("isolcpus=", isolated_cpu_setup);
 
 struct s_data {
@@ -7860,11 +7597,9 @@ void sched_destroy_group(struct task_group *tg)
 void sched_offline_group(struct task_group *tg)
 {
 	unsigned long flags;
-	int i;
 
 	/* end participation in shares distribution */
-	for_each_possible_cpu(i)
-		unregister_fair_sched_group(tg, i);
+	unregister_fair_sched_group(tg);
 
 	spin_lock_irqsave(&task_group_lock, flags);
 	list_del_rcu(&tg->list);
@@ -7890,7 +7625,7 @@ void sched_move_task(struct task_struct *tsk)
 	queued = task_on_rq_queued(tsk);
 
 	if (queued)
-		dequeue_task(rq, tsk, DEQUEUE_SAVE);
+		dequeue_task(rq, tsk, DEQUEUE_SAVE | DEQUEUE_MOVE);
 	if (unlikely(running))
 		put_prev_task(rq, tsk);
 
@@ -7914,7 +7649,7 @@ void sched_move_task(struct task_struct *tsk)
 	if (unlikely(running))
 		tsk->sched_class->set_curr_task(rq);
 	if (queued)
-		enqueue_task(rq, tsk, ENQUEUE_RESTORE);
+		enqueue_task(rq, tsk, ENQUEUE_RESTORE | ENQUEUE_MOVE);
 
 	task_rq_unlock(rq, tsk, &flags);
 }
diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
new file mode 100644
index 000000000000..928c4ba32f68
--- /dev/null
+++ b/kernel/sched/cpufreq.c
@@ -0,0 +1,37 @@
+/*
+ * Scheduler code and data structures related to cpufreq.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "sched.h"
+
+DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+
+/**
+ * cpufreq_set_update_util_data - Populate the CPU's update_util_data pointer.
+ * @cpu: The CPU to set the pointer for.
+ * @data: New pointer value.
+ *
+ * Set and publish the update_util_data pointer for the given CPU.  That pointer
+ * points to a struct update_util_data object containing a callback function
+ * to call from cpufreq_update_util().  That function will be called from an RCU
+ * read-side critical section, so it must not sleep.
+ *
+ * Callers must use RCU-sched callbacks to free any memory that might be
+ * accessed via the old update_util_data pointer or invoke synchronize_sched()
+ * right after this function to avoid use-after-free.
+ */
+void cpufreq_set_update_util_data(int cpu, struct update_util_data *data)
+{
+	if (WARN_ON(data && !data->func))
+		return;
+
+	rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), data);
+}
+EXPORT_SYMBOL_GPL(cpufreq_set_update_util_data);
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index b2ab2ffb1adc..75f98c5498d5 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -262,21 +262,21 @@ static __always_inline bool steal_account_process_tick(void)
 #ifdef CONFIG_PARAVIRT
 	if (static_key_false(&paravirt_steal_enabled)) {
 		u64 steal;
-		cputime_t steal_ct;
+		unsigned long steal_jiffies;
 
 		steal = paravirt_steal_clock(smp_processor_id());
 		steal -= this_rq()->prev_steal_time;
 
 		/*
-		 * cputime_t may be less precise than nsecs (eg: if it's
-		 * based on jiffies). Lets cast the result to cputime
+		 * steal is in nsecs but our caller is expecting steal
+		 * time in jiffies. Lets cast the result to jiffies
 		 * granularity and account the rest on the next rounds.
 		 */
-		steal_ct = nsecs_to_cputime(steal);
-		this_rq()->prev_steal_time += cputime_to_nsecs(steal_ct);
+		steal_jiffies = nsecs_to_jiffies(steal);
+		this_rq()->prev_steal_time += jiffies_to_nsecs(steal_jiffies);
 
-		account_steal_time(steal_ct);
-		return steal_ct;
+		account_steal_time(jiffies_to_cputime(steal_jiffies));
+		return steal_jiffies;
 	}
 #endif
 	return false;
@@ -668,26 +668,25 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime
 #endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-static unsigned long long vtime_delta(struct task_struct *tsk)
+static cputime_t vtime_delta(struct task_struct *tsk)
 {
-	unsigned long long clock;
+	unsigned long now = READ_ONCE(jiffies);
 
-	clock = local_clock();
-	if (clock < tsk->vtime_snap)
+	if (time_before(now, (unsigned long)tsk->vtime_snap))
 		return 0;
 
-	return clock - tsk->vtime_snap;
+	return jiffies_to_cputime(now - tsk->vtime_snap);
 }
 
 static cputime_t get_vtime_delta(struct task_struct *tsk)
 {
-	unsigned long long delta = vtime_delta(tsk);
+	unsigned long now = READ_ONCE(jiffies);
+	unsigned long delta = now - tsk->vtime_snap;
 
 	WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
-	tsk->vtime_snap += delta;
+	tsk->vtime_snap = now;
 
-	/* CHECKME: always safe to convert nsecs to cputime? */
-	return nsecs_to_cputime(delta);
+	return jiffies_to_cputime(delta);
 }
 
 static void __vtime_account_system(struct task_struct *tsk)
@@ -699,6 +698,9 @@ static void __vtime_account_system(struct task_struct *tsk)
 
 void vtime_account_system(struct task_struct *tsk)
 {
+	if (!vtime_delta(tsk))
+		return;
+
 	write_seqcount_begin(&tsk->vtime_seqcount);
 	__vtime_account_system(tsk);
 	write_seqcount_end(&tsk->vtime_seqcount);
@@ -707,7 +709,8 @@ void vtime_account_system(struct task_struct *tsk)
 void vtime_gen_account_irq_exit(struct task_struct *tsk)
 {
 	write_seqcount_begin(&tsk->vtime_seqcount);
-	__vtime_account_system(tsk);
+	if (vtime_delta(tsk))
+		__vtime_account_system(tsk);
 	if (context_tracking_in_user())
 		tsk->vtime_snap_whence = VTIME_USER;
 	write_seqcount_end(&tsk->vtime_seqcount);
@@ -718,16 +721,19 @@ void vtime_account_user(struct task_struct *tsk)
 	cputime_t delta_cpu;
 
 	write_seqcount_begin(&tsk->vtime_seqcount);
-	delta_cpu = get_vtime_delta(tsk);
 	tsk->vtime_snap_whence = VTIME_SYS;
-	account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu));
+	if (vtime_delta(tsk)) {
+		delta_cpu = get_vtime_delta(tsk);
+		account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu));
+	}
 	write_seqcount_end(&tsk->vtime_seqcount);
 }
 
 void vtime_user_enter(struct task_struct *tsk)
 {
 	write_seqcount_begin(&tsk->vtime_seqcount);
-	__vtime_account_system(tsk);
+	if (vtime_delta(tsk))
+		__vtime_account_system(tsk);
 	tsk->vtime_snap_whence = VTIME_USER;
 	write_seqcount_end(&tsk->vtime_seqcount);
 }
@@ -742,7 +748,8 @@ void vtime_guest_enter(struct task_struct *tsk)
 	 * that can thus safely catch up with a tickless delta.
 	 */
 	write_seqcount_begin(&tsk->vtime_seqcount);
-	__vtime_account_system(tsk);
+	if (vtime_delta(tsk))
+		__vtime_account_system(tsk);
 	current->flags |= PF_VCPU;
 	write_seqcount_end(&tsk->vtime_seqcount);
 }
@@ -772,7 +779,7 @@ void arch_vtime_task_switch(struct task_struct *prev)
 
 	write_seqcount_begin(&current->vtime_seqcount);
 	current->vtime_snap_whence = VTIME_SYS;
-	current->vtime_snap = sched_clock_cpu(smp_processor_id());
+	current->vtime_snap = jiffies;
 	write_seqcount_end(&current->vtime_seqcount);
 }
 
@@ -783,7 +790,7 @@ void vtime_init_idle(struct task_struct *t, int cpu)
 	local_irq_save(flags);
 	write_seqcount_begin(&t->vtime_seqcount);
 	t->vtime_snap_whence = VTIME_SYS;
-	t->vtime_snap = sched_clock_cpu(cpu);
+	t->vtime_snap = jiffies;
 	write_seqcount_end(&t->vtime_seqcount);
 	local_irq_restore(flags);
 }
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index cd64c979d0e1..affd97ec9f65 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -352,7 +352,15 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se,
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
-	WARN_ON(!dl_se->dl_new || dl_se->dl_throttled);
+	WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline));
+
+	/*
+	 * We are racing with the deadline timer. So, do nothing because
+	 * the deadline timer handler will take care of properly recharging
+	 * the runtime and postponing the deadline
+	 */
+	if (dl_se->dl_throttled)
+		return;
 
 	/*
 	 * We use the regular wall clock time to set deadlines in the
@@ -361,7 +369,6 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se,
 	 */
 	dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
 	dl_se->runtime = pi_se->dl_runtime;
-	dl_se->dl_new = 0;
 }
 
 /*
@@ -399,6 +406,9 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
 		dl_se->runtime = pi_se->dl_runtime;
 	}
 
+	if (dl_se->dl_yielded && dl_se->runtime > 0)
+		dl_se->runtime = 0;
+
 	/*
 	 * We keep moving the deadline away until we get some
 	 * available runtime for the entity. This ensures correct
@@ -420,7 +430,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
 	 * entity.
 	 */
 	if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
-		printk_deferred_once("sched: DL replenish lagged to much\n");
+		printk_deferred_once("sched: DL replenish lagged too much\n");
 		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
 		dl_se->runtime = pi_se->dl_runtime;
 	}
@@ -500,15 +510,6 @@ static void update_dl_entity(struct sched_dl_entity *dl_se,
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
-	/*
-	 * The arrival of a new instance needs special treatment, i.e.,
-	 * the actual scheduling parameters have to be "renewed".
-	 */
-	if (dl_se->dl_new) {
-		setup_new_dl_entity(dl_se, pi_se);
-		return;
-	}
-
 	if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
 	    dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
 		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
@@ -605,16 +606,6 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	}
 
 	/*
-	 * This is possible if switched_from_dl() raced against a running
-	 * callback that took the above !dl_task() path and we've since then
-	 * switched back into SCHED_DEADLINE.
-	 *
-	 * There's nothing to do except drop our task reference.
-	 */
-	if (dl_se->dl_new)
-		goto unlock;
-
-	/*
 	 * The task might have been boosted by someone else and might be in the
 	 * boosting/deboosting path, its not throttled.
 	 */
@@ -726,6 +717,10 @@ static void update_curr_dl(struct rq *rq)
 	if (!dl_task(curr) || !on_dl_rq(dl_se))
 		return;
 
+	/* Kick cpufreq (see the comment in linux/cpufreq.h). */
+	if (cpu_of(rq) == smp_processor_id())
+		cpufreq_trigger_update(rq_clock(rq));
+
 	/*
 	 * Consumed budget is computed considering the time as
 	 * observed by schedulable tasks (excluding time spent
@@ -735,8 +730,11 @@ static void update_curr_dl(struct rq *rq)
 	 * approach need further study.
 	 */
 	delta_exec = rq_clock_task(rq) - curr->se.exec_start;
-	if (unlikely((s64)delta_exec <= 0))
+	if (unlikely((s64)delta_exec <= 0)) {
+		if (unlikely(dl_se->dl_yielded))
+			goto throttle;
 		return;
+	}
 
 	schedstat_set(curr->se.statistics.exec_max,
 		      max(curr->se.statistics.exec_max, delta_exec));
@@ -749,8 +747,10 @@ static void update_curr_dl(struct rq *rq)
 
 	sched_rt_avg_update(rq, delta_exec);
 
-	dl_se->runtime -= dl_se->dl_yielded ? 0 : delta_exec;
-	if (dl_runtime_exceeded(dl_se)) {
+	dl_se->runtime -= delta_exec;
+
+throttle:
+	if (dl_runtime_exceeded(dl_se) || dl_se->dl_yielded) {
 		dl_se->dl_throttled = 1;
 		__dequeue_task_dl(rq, curr, 0);
 		if (unlikely(dl_se->dl_boosted || !start_dl_timer(curr)))
@@ -917,7 +917,7 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se,
 	 * parameters of the task might need updating. Otherwise,
 	 * we want a replenishment of its runtime.
 	 */
-	if (dl_se->dl_new || flags & ENQUEUE_WAKEUP)
+	if (flags & ENQUEUE_WAKEUP)
 		update_dl_entity(dl_se, pi_se);
 	else if (flags & ENQUEUE_REPLENISH)
 		replenish_dl_entity(dl_se, pi_se);
@@ -994,18 +994,14 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
  */
 static void yield_task_dl(struct rq *rq)
 {
-	struct task_struct *p = rq->curr;
-
 	/*
 	 * We make the task go to sleep until its current deadline by
 	 * forcing its runtime to zero. This way, update_curr_dl() stops
 	 * it and the bandwidth timer will wake it up and will give it
 	 * new scheduling parameters (thanks to dl_yielded=1).
 	 */
-	if (p->dl.runtime > 0) {
-		rq->curr->dl.dl_yielded = 1;
-		p->dl.runtime = 0;
-	}
+	rq->curr->dl.dl_yielded = 1;
+
 	update_rq_clock(rq);
 	update_curr_dl(rq);
 	/*
@@ -1722,6 +1718,9 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
  */
 static void switched_to_dl(struct rq *rq, struct task_struct *p)
 {
+	if (dl_time_before(p->dl.deadline, rq_clock(rq)))
+		setup_new_dl_entity(&p->dl, &p->dl);
+
 	if (task_on_rq_queued(p) && rq->curr != p) {
 #ifdef CONFIG_SMP
 		if (p->nr_cpus_allowed > 1 && rq->dl.overloaded)
@@ -1768,8 +1767,7 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p,
 		 */
 		resched_curr(rq);
 #endif /* CONFIG_SMP */
-	} else
-		switched_to_dl(rq, p);
+	}
 }
 
 const struct sched_class dl_sched_class = {
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 641511771ae6..4fbc3bd5ff60 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -16,6 +16,7 @@
 #include <linux/kallsyms.h>
 #include <linux/utsname.h>
 #include <linux/mempolicy.h>
+#include <linux/debugfs.h>
 
 #include "sched.h"
 
@@ -58,6 +59,309 @@ static unsigned long nsec_low(unsigned long long nsec)
 
 #define SPLIT_NS(x) nsec_high(x), nsec_low(x)
 
+#define SCHED_FEAT(name, enabled)	\
+	#name ,
+
+static const char * const sched_feat_names[] = {
+#include "features.h"
+};
+
+#undef SCHED_FEAT
+
+static int sched_feat_show(struct seq_file *m, void *v)
+{
+	int i;
+
+	for (i = 0; i < __SCHED_FEAT_NR; i++) {
+		if (!(sysctl_sched_features & (1UL << i)))
+			seq_puts(m, "NO_");
+		seq_printf(m, "%s ", sched_feat_names[i]);
+	}
+	seq_puts(m, "\n");
+
+	return 0;
+}
+
+#ifdef HAVE_JUMP_LABEL
+
+#define jump_label_key__true  STATIC_KEY_INIT_TRUE
+#define jump_label_key__false STATIC_KEY_INIT_FALSE
+
+#define SCHED_FEAT(name, enabled)	\
+	jump_label_key__##enabled ,
+
+struct static_key sched_feat_keys[__SCHED_FEAT_NR] = {
+#include "features.h"
+};
+
+#undef SCHED_FEAT
+
+static void sched_feat_disable(int i)
+{
+	static_key_disable(&sched_feat_keys[i]);
+}
+
+static void sched_feat_enable(int i)
+{
+	static_key_enable(&sched_feat_keys[i]);
+}
+#else
+static void sched_feat_disable(int i) { };
+static void sched_feat_enable(int i) { };
+#endif /* HAVE_JUMP_LABEL */
+
+static int sched_feat_set(char *cmp)
+{
+	int i;
+	int neg = 0;
+
+	if (strncmp(cmp, "NO_", 3) == 0) {
+		neg = 1;
+		cmp += 3;
+	}
+
+	for (i = 0; i < __SCHED_FEAT_NR; i++) {
+		if (strcmp(cmp, sched_feat_names[i]) == 0) {
+			if (neg) {
+				sysctl_sched_features &= ~(1UL << i);
+				sched_feat_disable(i);
+			} else {
+				sysctl_sched_features |= (1UL << i);
+				sched_feat_enable(i);
+			}
+			break;
+		}
+	}
+
+	return i;
+}
+
+static ssize_t
+sched_feat_write(struct file *filp, const char __user *ubuf,
+		size_t cnt, loff_t *ppos)
+{
+	char buf[64];
+	char *cmp;
+	int i;
+	struct inode *inode;
+
+	if (cnt > 63)
+		cnt = 63;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+	cmp = strstrip(buf);
+
+	/* Ensure the static_key remains in a consistent state */
+	inode = file_inode(filp);
+	inode_lock(inode);
+	i = sched_feat_set(cmp);
+	inode_unlock(inode);
+	if (i == __SCHED_FEAT_NR)
+		return -EINVAL;
+
+	*ppos += cnt;
+
+	return cnt;
+}
+
+static int sched_feat_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, sched_feat_show, NULL);
+}
+
+static const struct file_operations sched_feat_fops = {
+	.open		= sched_feat_open,
+	.write		= sched_feat_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static __init int sched_init_debug(void)
+{
+	debugfs_create_file("sched_features", 0644, NULL, NULL,
+			&sched_feat_fops);
+
+	return 0;
+}
+late_initcall(sched_init_debug);
+
+#ifdef CONFIG_SMP
+
+#ifdef CONFIG_SYSCTL
+
+static struct ctl_table sd_ctl_dir[] = {
+	{
+		.procname	= "sched_domain",
+		.mode		= 0555,
+	},
+	{}
+};
+
+static struct ctl_table sd_ctl_root[] = {
+	{
+		.procname	= "kernel",
+		.mode		= 0555,
+		.child		= sd_ctl_dir,
+	},
+	{}
+};
+
+static struct ctl_table *sd_alloc_ctl_entry(int n)
+{
+	struct ctl_table *entry =
+		kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL);
+
+	return entry;
+}
+
+static void sd_free_ctl_entry(struct ctl_table **tablep)
+{
+	struct ctl_table *entry;
+
+	/*
+	 * In the intermediate directories, both the child directory and
+	 * procname are dynamically allocated and could fail but the mode
+	 * will always be set. In the lowest directory the names are
+	 * static strings and all have proc handlers.
+	 */
+	for (entry = *tablep; entry->mode; entry++) {
+		if (entry->child)
+			sd_free_ctl_entry(&entry->child);
+		if (entry->proc_handler == NULL)
+			kfree(entry->procname);
+	}
+
+	kfree(*tablep);
+	*tablep = NULL;
+}
+
+static int min_load_idx = 0;
+static int max_load_idx = CPU_LOAD_IDX_MAX-1;
+
+static void
+set_table_entry(struct ctl_table *entry,
+		const char *procname, void *data, int maxlen,
+		umode_t mode, proc_handler *proc_handler,
+		bool load_idx)
+{
+	entry->procname = procname;
+	entry->data = data;
+	entry->maxlen = maxlen;
+	entry->mode = mode;
+	entry->proc_handler = proc_handler;
+
+	if (load_idx) {
+		entry->extra1 = &min_load_idx;
+		entry->extra2 = &max_load_idx;
+	}
+}
+
+static struct ctl_table *
+sd_alloc_ctl_domain_table(struct sched_domain *sd)
+{
+	struct ctl_table *table = sd_alloc_ctl_entry(14);
+
+	if (table == NULL)
+		return NULL;
+
+	set_table_entry(&table[0], "min_interval", &sd->min_interval,
+		sizeof(long), 0644, proc_doulongvec_minmax, false);
+	set_table_entry(&table[1], "max_interval", &sd->max_interval,
+		sizeof(long), 0644, proc_doulongvec_minmax, false);
+	set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
+		sizeof(int), 0644, proc_dointvec_minmax, false);
+	set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
+		sizeof(int), 0644, proc_dointvec_minmax, false);
+	set_table_entry(&table[9], "cache_nice_tries",
+		&sd->cache_nice_tries,
+		sizeof(int), 0644, proc_dointvec_minmax, false);
+	set_table_entry(&table[10], "flags", &sd->flags,
+		sizeof(int), 0644, proc_dointvec_minmax, false);
+	set_table_entry(&table[11], "max_newidle_lb_cost",
+		&sd->max_newidle_lb_cost,
+		sizeof(long), 0644, proc_doulongvec_minmax, false);
+	set_table_entry(&table[12], "name", sd->name,
+		CORENAME_MAX_SIZE, 0444, proc_dostring, false);
+	/* &table[13] is terminator */
+
+	return table;
+}
+
+static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu)
+{
+	struct ctl_table *entry, *table;
+	struct sched_domain *sd;
+	int domain_num = 0, i;
+	char buf[32];
+
+	for_each_domain(cpu, sd)
+		domain_num++;
+	entry = table = sd_alloc_ctl_entry(domain_num + 1);
+	if (table == NULL)
+		return NULL;
+
+	i = 0;
+	for_each_domain(cpu, sd) {
+		snprintf(buf, 32, "domain%d", i);
+		entry->procname = kstrdup(buf, GFP_KERNEL);
+		entry->mode = 0555;
+		entry->child = sd_alloc_ctl_domain_table(sd);
+		entry++;
+		i++;
+	}
+	return table;
+}
+
+static struct ctl_table_header *sd_sysctl_header;
+void register_sched_domain_sysctl(void)
+{
+	int i, cpu_num = num_possible_cpus();
+	struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
+	char buf[32];
+
+	WARN_ON(sd_ctl_dir[0].child);
+	sd_ctl_dir[0].child = entry;
+
+	if (entry == NULL)
+		return;
+
+	for_each_possible_cpu(i) {
+		snprintf(buf, 32, "cpu%d", i);
+		entry->procname = kstrdup(buf, GFP_KERNEL);
+		entry->mode = 0555;
+		entry->child = sd_alloc_ctl_cpu_table(i);
+		entry++;
+	}
+
+	WARN_ON(sd_sysctl_header);
+	sd_sysctl_header = register_sysctl_table(sd_ctl_root);
+}
+
+/* may be called multiple times per register */
+void unregister_sched_domain_sysctl(void)
+{
+	unregister_sysctl_table(sd_sysctl_header);
+	sd_sysctl_header = NULL;
+	if (sd_ctl_dir[0].child)
+		sd_free_ctl_entry(&sd_ctl_dir[0].child);
+}
+#endif /* CONFIG_SYSCTL */
+#endif /* CONFIG_SMP */
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg)
 {
@@ -75,16 +379,18 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	PN(se->vruntime);
 	PN(se->sum_exec_runtime);
 #ifdef CONFIG_SCHEDSTATS
-	PN(se->statistics.wait_start);
-	PN(se->statistics.sleep_start);
-	PN(se->statistics.block_start);
-	PN(se->statistics.sleep_max);
-	PN(se->statistics.block_max);
-	PN(se->statistics.exec_max);
-	PN(se->statistics.slice_max);
-	PN(se->statistics.wait_max);
-	PN(se->statistics.wait_sum);
-	P(se->statistics.wait_count);
+	if (schedstat_enabled()) {
+		PN(se->statistics.wait_start);
+		PN(se->statistics.sleep_start);
+		PN(se->statistics.block_start);
+		PN(se->statistics.sleep_max);
+		PN(se->statistics.block_max);
+		PN(se->statistics.exec_max);
+		PN(se->statistics.slice_max);
+		PN(se->statistics.wait_max);
+		PN(se->statistics.wait_sum);
+		P(se->statistics.wait_count);
+	}
 #endif
 	P(se->load.weight);
 #ifdef CONFIG_SMP
@@ -122,10 +428,12 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 		(long long)(p->nvcsw + p->nivcsw),
 		p->prio);
 #ifdef CONFIG_SCHEDSTATS
-	SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
-		SPLIT_NS(p->se.statistics.wait_sum),
-		SPLIT_NS(p->se.sum_exec_runtime),
-		SPLIT_NS(p->se.statistics.sum_sleep_runtime));
+	if (schedstat_enabled()) {
+		SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
+			SPLIT_NS(p->se.statistics.wait_sum),
+			SPLIT_NS(p->se.sum_exec_runtime),
+			SPLIT_NS(p->se.statistics.sum_sleep_runtime));
+	}
 #else
 	SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
 		0LL, 0L,
@@ -258,8 +566,17 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 
 void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq)
 {
+	struct dl_bw *dl_bw;
+
 	SEQ_printf(m, "\ndl_rq[%d]:\n", cpu);
 	SEQ_printf(m, "  .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running);
+#ifdef CONFIG_SMP
+	dl_bw = &cpu_rq(cpu)->rd->dl_bw;
+#else
+	dl_bw = &dl_rq->dl_bw;
+#endif
+	SEQ_printf(m, "  .%-30s: %lld\n", "dl_bw->bw", dl_bw->bw);
+	SEQ_printf(m, "  .%-30s: %lld\n", "dl_bw->total_bw", dl_bw->total_bw);
 }
 
 extern __read_mostly int sched_clock_running;
@@ -313,17 +630,18 @@ do {									\
 #define P(n) SEQ_printf(m, "  .%-30s: %d\n", #n, rq->n);
 #define P64(n) SEQ_printf(m, "  .%-30s: %Ld\n", #n, rq->n);
 
-	P(yld_count);
-
-	P(sched_count);
-	P(sched_goidle);
 #ifdef CONFIG_SMP
 	P64(avg_idle);
 	P64(max_idle_balance_cost);
 #endif
 
-	P(ttwu_count);
-	P(ttwu_local);
+	if (schedstat_enabled()) {
+		P(yld_count);
+		P(sched_count);
+		P(sched_goidle);
+		P(ttwu_count);
+		P(ttwu_local);
+	}
 
 #undef P
 #undef P64
@@ -569,38 +887,39 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	nr_switches = p->nvcsw + p->nivcsw;
 
 #ifdef CONFIG_SCHEDSTATS
-	PN(se.statistics.sum_sleep_runtime);
-	PN(se.statistics.wait_start);
-	PN(se.statistics.sleep_start);
-	PN(se.statistics.block_start);
-	PN(se.statistics.sleep_max);
-	PN(se.statistics.block_max);
-	PN(se.statistics.exec_max);
-	PN(se.statistics.slice_max);
-	PN(se.statistics.wait_max);
-	PN(se.statistics.wait_sum);
-	P(se.statistics.wait_count);
-	PN(se.statistics.iowait_sum);
-	P(se.statistics.iowait_count);
 	P(se.nr_migrations);
-	P(se.statistics.nr_migrations_cold);
-	P(se.statistics.nr_failed_migrations_affine);
-	P(se.statistics.nr_failed_migrations_running);
-	P(se.statistics.nr_failed_migrations_hot);
-	P(se.statistics.nr_forced_migrations);
-	P(se.statistics.nr_wakeups);
-	P(se.statistics.nr_wakeups_sync);
-	P(se.statistics.nr_wakeups_migrate);
-	P(se.statistics.nr_wakeups_local);
-	P(se.statistics.nr_wakeups_remote);
-	P(se.statistics.nr_wakeups_affine);
-	P(se.statistics.nr_wakeups_affine_attempts);
-	P(se.statistics.nr_wakeups_passive);
-	P(se.statistics.nr_wakeups_idle);
 
-	{
+	if (schedstat_enabled()) {
 		u64 avg_atom, avg_per_cpu;
 
+		PN(se.statistics.sum_sleep_runtime);
+		PN(se.statistics.wait_start);
+		PN(se.statistics.sleep_start);
+		PN(se.statistics.block_start);
+		PN(se.statistics.sleep_max);
+		PN(se.statistics.block_max);
+		PN(se.statistics.exec_max);
+		PN(se.statistics.slice_max);
+		PN(se.statistics.wait_max);
+		PN(se.statistics.wait_sum);
+		P(se.statistics.wait_count);
+		PN(se.statistics.iowait_sum);
+		P(se.statistics.iowait_count);
+		P(se.statistics.nr_migrations_cold);
+		P(se.statistics.nr_failed_migrations_affine);
+		P(se.statistics.nr_failed_migrations_running);
+		P(se.statistics.nr_failed_migrations_hot);
+		P(se.statistics.nr_forced_migrations);
+		P(se.statistics.nr_wakeups);
+		P(se.statistics.nr_wakeups_sync);
+		P(se.statistics.nr_wakeups_migrate);
+		P(se.statistics.nr_wakeups_local);
+		P(se.statistics.nr_wakeups_remote);
+		P(se.statistics.nr_wakeups_affine);
+		P(se.statistics.nr_wakeups_affine_attempts);
+		P(se.statistics.nr_wakeups_passive);
+		P(se.statistics.nr_wakeups_idle);
+
 		avg_atom = p->se.sum_exec_runtime;
 		if (nr_switches)
 			avg_atom = div64_ul(avg_atom, nr_switches);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 56b7d4b83947..46d64e4ccfde 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -20,8 +20,8 @@
  *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  */
 
-#include <linux/latencytop.h>
 #include <linux/sched.h>
+#include <linux/latencytop.h>
 #include <linux/cpumask.h>
 #include <linux/cpuidle.h>
 #include <linux/slab.h>
@@ -755,7 +755,9 @@ static void
 update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	struct task_struct *p;
-	u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start;
+	u64 delta;
+
+	delta = rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start;
 
 	if (entity_is_task(se)) {
 		p = task_of(se);
@@ -776,22 +778,12 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	se->statistics.wait_sum += delta;
 	se->statistics.wait_start = 0;
 }
-#else
-static inline void
-update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-}
-
-static inline void
-update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-}
-#endif
 
 /*
  * Task is being enqueued - update stats:
  */
-static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static inline void
+update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	/*
 	 * Are we enqueueing a waiting task? (for current tasks
@@ -802,7 +794,7 @@ static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 static inline void
-update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
+update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 	/*
 	 * Mark the end of the wait period if dequeueing a
@@ -810,8 +802,41 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 */
 	if (se != cfs_rq->curr)
 		update_stats_wait_end(cfs_rq, se);
+
+	if (flags & DEQUEUE_SLEEP) {
+		if (entity_is_task(se)) {
+			struct task_struct *tsk = task_of(se);
+
+			if (tsk->state & TASK_INTERRUPTIBLE)
+				se->statistics.sleep_start = rq_clock(rq_of(cfs_rq));
+			if (tsk->state & TASK_UNINTERRUPTIBLE)
+				se->statistics.block_start = rq_clock(rq_of(cfs_rq));
+		}
+	}
+
+}
+#else
+static inline void
+update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+}
+
+static inline void
+update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
 }
 
+static inline void
+update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+}
+
+static inline void
+update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
+{
+}
+#endif
+
 /*
  * We are picking a new current task - update its stats:
  */
@@ -907,10 +932,11 @@ struct numa_group {
 	spinlock_t lock; /* nr_tasks, tasks */
 	int nr_tasks;
 	pid_t gid;
+	int active_nodes;
 
 	struct rcu_head rcu;
-	nodemask_t active_nodes;
 	unsigned long total_faults;
+	unsigned long max_faults_cpu;
 	/*
 	 * Faults_cpu is used to decide whether memory should move
 	 * towards the CPU. As a consequence, these stats are weighted
@@ -969,6 +995,18 @@ static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
 		group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)];
 }
 
+/*
+ * A node triggering more than 1/3 as many NUMA faults as the maximum is
+ * considered part of a numa group's pseudo-interleaving set. Migrations
+ * between these nodes are slowed down, to allow things to settle down.
+ */
+#define ACTIVE_NODE_FRACTION 3
+
+static bool numa_is_active_node(int nid, struct numa_group *ng)
+{
+	return group_faults_cpu(ng, nid) * ACTIVE_NODE_FRACTION > ng->max_faults_cpu;
+}
+
 /* Handle placement on systems where not all nodes are directly connected. */
 static unsigned long score_nearby_nodes(struct task_struct *p, int nid,
 					int maxdist, bool task)
@@ -1118,27 +1156,23 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
 		return true;
 
 	/*
-	 * Do not migrate if the destination is not a node that
-	 * is actively used by this numa group.
-	 */
-	if (!node_isset(dst_nid, ng->active_nodes))
-		return false;
-
-	/*
-	 * Source is a node that is not actively used by this
-	 * numa group, while the destination is. Migrate.
+	 * Destination node is much more heavily used than the source
+	 * node? Allow migration.
 	 */
-	if (!node_isset(src_nid, ng->active_nodes))
+	if (group_faults_cpu(ng, dst_nid) > group_faults_cpu(ng, src_nid) *
+					ACTIVE_NODE_FRACTION)
 		return true;
 
 	/*
-	 * Both source and destination are nodes in active
-	 * use by this numa group. Maximize memory bandwidth
-	 * by migrating from more heavily used groups, to less
-	 * heavily used ones, spreading the load around.
-	 * Use a 1/4 hysteresis to avoid spurious page movement.
+	 * Distribute memory according to CPU & memory use on each node,
+	 * with 3/4 hysteresis to avoid unnecessary memory migrations:
+	 *
+	 * faults_cpu(dst)   3   faults_cpu(src)
+	 * --------------- * - > ---------------
+	 * faults_mem(dst)   4   faults_mem(src)
 	 */
-	return group_faults(p, dst_nid) < (group_faults(p, src_nid) * 3 / 4);
+	return group_faults_cpu(ng, dst_nid) * group_faults(p, src_nid) * 3 >
+	       group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4;
 }
 
 static unsigned long weighted_cpuload(const int cpu);
@@ -1484,7 +1518,7 @@ static int task_numa_migrate(struct task_struct *p)
 
 		.best_task = NULL,
 		.best_imp = 0,
-		.best_cpu = -1
+		.best_cpu = -1,
 	};
 	struct sched_domain *sd;
 	unsigned long taskweight, groupweight;
@@ -1536,8 +1570,7 @@ static int task_numa_migrate(struct task_struct *p)
 	 *   multiple NUMA nodes; in order to better consolidate the group,
 	 *   we need to check other locations.
 	 */
-	if (env.best_cpu == -1 || (p->numa_group &&
-			nodes_weight(p->numa_group->active_nodes) > 1)) {
+	if (env.best_cpu == -1 || (p->numa_group && p->numa_group->active_nodes > 1)) {
 		for_each_online_node(nid) {
 			if (nid == env.src_nid || nid == p->numa_preferred_nid)
 				continue;
@@ -1572,12 +1605,14 @@ static int task_numa_migrate(struct task_struct *p)
 	 * trying for a better one later. Do not set the preferred node here.
 	 */
 	if (p->numa_group) {
+		struct numa_group *ng = p->numa_group;
+
 		if (env.best_cpu == -1)
 			nid = env.src_nid;
 		else
 			nid = env.dst_nid;
 
-		if (node_isset(nid, p->numa_group->active_nodes))
+		if (ng->active_nodes > 1 && numa_is_active_node(env.dst_nid, ng))
 			sched_setnuma(p, env.dst_nid);
 	}
 
@@ -1627,20 +1662,15 @@ static void numa_migrate_preferred(struct task_struct *p)
 }
 
 /*
- * Find the nodes on which the workload is actively running. We do this by
+ * Find out how many nodes on the workload is actively running on. Do this by
  * tracking the nodes from which NUMA hinting faults are triggered. This can
  * be different from the set of nodes where the workload's memory is currently
  * located.
- *
- * The bitmask is used to make smarter decisions on when to do NUMA page
- * migrations, To prevent flip-flopping, and excessive page migrations, nodes
- * are added when they cause over 6/16 of the maximum number of faults, but
- * only removed when they drop below 3/16.
  */
-static void update_numa_active_node_mask(struct numa_group *numa_group)
+static void numa_group_count_active_nodes(struct numa_group *numa_group)
 {
 	unsigned long faults, max_faults = 0;
-	int nid;
+	int nid, active_nodes = 0;
 
 	for_each_online_node(nid) {
 		faults = group_faults_cpu(numa_group, nid);
@@ -1650,12 +1680,12 @@ static void update_numa_active_node_mask(struct numa_group *numa_group)
 
 	for_each_online_node(nid) {
 		faults = group_faults_cpu(numa_group, nid);
-		if (!node_isset(nid, numa_group->active_nodes)) {
-			if (faults > max_faults * 6 / 16)
-				node_set(nid, numa_group->active_nodes);
-		} else if (faults < max_faults * 3 / 16)
-			node_clear(nid, numa_group->active_nodes);
+		if (faults * ACTIVE_NODE_FRACTION > max_faults)
+			active_nodes++;
 	}
+
+	numa_group->max_faults_cpu = max_faults;
+	numa_group->active_nodes = active_nodes;
 }
 
 /*
@@ -1946,7 +1976,7 @@ static void task_numa_placement(struct task_struct *p)
 	update_task_scan_period(p, fault_types[0], fault_types[1]);
 
 	if (p->numa_group) {
-		update_numa_active_node_mask(p->numa_group);
+		numa_group_count_active_nodes(p->numa_group);
 		spin_unlock_irq(group_lock);
 		max_nid = preferred_group_nid(p, max_group_nid);
 	}
@@ -1990,14 +2020,14 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 			return;
 
 		atomic_set(&grp->refcount, 1);
+		grp->active_nodes = 1;
+		grp->max_faults_cpu = 0;
 		spin_lock_init(&grp->lock);
 		grp->gid = p->pid;
 		/* Second half of the array tracks nids where faults happen */
 		grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES *
 						nr_node_ids;
 
-		node_set(task_node(current), grp->active_nodes);
-
 		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
 			grp->faults[i] = p->numa_faults[i];
 
@@ -2111,6 +2141,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 	bool migrated = flags & TNF_MIGRATED;
 	int cpu_node = task_node(current);
 	int local = !!(flags & TNF_FAULT_LOCAL);
+	struct numa_group *ng;
 	int priv;
 
 	if (!static_branch_likely(&sched_numa_balancing))
@@ -2151,9 +2182,10 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 	 * actively using should be counted as local. This allows the
 	 * scan rate to slow down when a workload has settled down.
 	 */
-	if (!priv && !local && p->numa_group &&
-			node_isset(cpu_node, p->numa_group->active_nodes) &&
-			node_isset(mem_node, p->numa_group->active_nodes))
+	ng = p->numa_group;
+	if (!priv && !local && ng && ng->active_nodes > 1 &&
+				numa_is_active_node(cpu_node, ng) &&
+				numa_is_active_node(mem_node, ng))
 		local = 1;
 
 	task_numa_placement(p);
@@ -2824,7 +2856,8 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	u64 now = cfs_rq_clock_task(cfs_rq);
-	int cpu = cpu_of(rq_of(cfs_rq));
+	struct rq *rq = rq_of(cfs_rq);
+	int cpu = cpu_of(rq);
 
 	/*
 	 * Track task load average for carrying it to new CPU after migrated, and
@@ -2836,6 +2869,29 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg)
 
 	if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg)
 		update_tg_load_avg(cfs_rq, 0);
+
+	if (cpu == smp_processor_id() && &rq->cfs == cfs_rq) {
+		unsigned long max = rq->cpu_capacity_orig;
+
+		/*
+		 * There are a few boundary cases this might miss but it should
+		 * get called often enough that that should (hopefully) not be
+		 * a real problem -- added to that it only calls on the local
+		 * CPU, so if we enqueue remotely we'll miss an update, but
+		 * the next tick/schedule should update.
+		 *
+		 * It will not get called when we go idle, because the idle
+		 * thread is a different class (!fair), nor will the utilization
+		 * number include things like RT tasks.
+		 *
+		 * As is, the util number is not freq-invariant (we'd have to
+		 * implement arch_scale_freq_capacity() for that).
+		 *
+		 * See cpu_util().
+		 */
+		cpufreq_update_util(rq_clock(rq),
+				    min(cfs_rq->avg.util_avg, max), max);
+	}
 }
 
 static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -3102,6 +3158,26 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
 
+static inline void check_schedstat_required(void)
+{
+#ifdef CONFIG_SCHEDSTATS
+	if (schedstat_enabled())
+		return;
+
+	/* Force schedstat enabled if a dependent tracepoint is active */
+	if (trace_sched_stat_wait_enabled()    ||
+			trace_sched_stat_sleep_enabled()   ||
+			trace_sched_stat_iowait_enabled()  ||
+			trace_sched_stat_blocked_enabled() ||
+			trace_sched_stat_runtime_enabled())  {
+		pr_warn_once("Scheduler tracepoints stat_sleep, stat_iowait, "
+			     "stat_blocked and stat_runtime require the "
+			     "kernel parameter schedstats=enabled or "
+			     "kernel.sched_schedstats=1\n");
+	}
+#endif
+}
+
 static void
 enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
@@ -3122,11 +3198,15 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	if (flags & ENQUEUE_WAKEUP) {
 		place_entity(cfs_rq, se, 0);
-		enqueue_sleeper(cfs_rq, se);
+		if (schedstat_enabled())
+			enqueue_sleeper(cfs_rq, se);
 	}
 
-	update_stats_enqueue(cfs_rq, se);
-	check_spread(cfs_rq, se);
+	check_schedstat_required();
+	if (schedstat_enabled()) {
+		update_stats_enqueue(cfs_rq, se);
+		check_spread(cfs_rq, se);
+	}
 	if (se != cfs_rq->curr)
 		__enqueue_entity(cfs_rq, se);
 	se->on_rq = 1;
@@ -3193,19 +3273,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	update_curr(cfs_rq);
 	dequeue_entity_load_avg(cfs_rq, se);
 
-	update_stats_dequeue(cfs_rq, se);
-	if (flags & DEQUEUE_SLEEP) {
-#ifdef CONFIG_SCHEDSTATS
-		if (entity_is_task(se)) {
-			struct task_struct *tsk = task_of(se);
-
-			if (tsk->state & TASK_INTERRUPTIBLE)
-				se->statistics.sleep_start = rq_clock(rq_of(cfs_rq));
-			if (tsk->state & TASK_UNINTERRUPTIBLE)
-				se->statistics.block_start = rq_clock(rq_of(cfs_rq));
-		}
-#endif
-	}
+	if (schedstat_enabled())
+		update_stats_dequeue(cfs_rq, se, flags);
 
 	clear_buddies(cfs_rq, se);
 
@@ -3279,7 +3348,8 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		 * a CPU. So account for the time it spent waiting on the
 		 * runqueue.
 		 */
-		update_stats_wait_end(cfs_rq, se);
+		if (schedstat_enabled())
+			update_stats_wait_end(cfs_rq, se);
 		__dequeue_entity(cfs_rq, se);
 		update_load_avg(se, 1);
 	}
@@ -3292,7 +3362,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 * least twice that of our own weight (i.e. dont track it
 	 * when there are only lesser-weight tasks around):
 	 */
-	if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
+	if (schedstat_enabled() && rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
 		se->statistics.slice_max = max(se->statistics.slice_max,
 			se->sum_exec_runtime - se->prev_sum_exec_runtime);
 	}
@@ -3375,9 +3445,13 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 	/* throttle cfs_rqs exceeding runtime */
 	check_cfs_rq_runtime(cfs_rq);
 
-	check_spread(cfs_rq, prev);
+	if (schedstat_enabled()) {
+		check_spread(cfs_rq, prev);
+		if (prev->on_rq)
+			update_stats_wait_start(cfs_rq, prev);
+	}
+
 	if (prev->on_rq) {
-		update_stats_wait_start(cfs_rq, prev);
 		/* Put 'current' back into the tree. */
 		__enqueue_entity(cfs_rq, prev);
 		/* in !on_rq case, update occurred at dequeue */
@@ -4459,9 +4533,17 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
 
 		/* scale is effectively 1 << i now, and >> i divides by scale */
 
-		old_load = this_rq->cpu_load[i] - tickless_load;
+		old_load = this_rq->cpu_load[i];
 		old_load = decay_load_missed(old_load, pending_updates - 1, i);
-		old_load += tickless_load;
+		if (tickless_load) {
+			old_load -= decay_load_missed(tickless_load, pending_updates - 1, i);
+			/*
+			 * old_load can never be a negative value because a
+			 * decayed tickless_load cannot be greater than the
+			 * original tickless_load.
+			 */
+			old_load += tickless_load;
+		}
 		new_load = this_load;
 		/*
 		 * Round up the averaging division if load is increasing. This
@@ -4484,6 +4566,25 @@ static unsigned long weighted_cpuload(const int cpu)
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
+static void __update_cpu_load_nohz(struct rq *this_rq,
+				   unsigned long curr_jiffies,
+				   unsigned long load,
+				   int active)
+{
+	unsigned long pending_updates;
+
+	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+	if (pending_updates) {
+		this_rq->last_load_update_tick = curr_jiffies;
+		/*
+		 * In the regular NOHZ case, we were idle, this means load 0.
+		 * In the NOHZ_FULL case, we were non-idle, we should consider
+		 * its weighted load.
+		 */
+		__update_cpu_load(this_rq, load, pending_updates, active);
+	}
+}
+
 /*
  * There is no sane way to deal with nohz on smp when using jiffies because the
  * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
@@ -4501,22 +4602,15 @@ static unsigned long weighted_cpuload(const int cpu)
  * Called from nohz_idle_balance() to update the load ratings before doing the
  * idle balance.
  */
-static void update_idle_cpu_load(struct rq *this_rq)
+static void update_cpu_load_idle(struct rq *this_rq)
 {
-	unsigned long curr_jiffies = READ_ONCE(jiffies);
-	unsigned long load = weighted_cpuload(cpu_of(this_rq));
-	unsigned long pending_updates;
-
 	/*
 	 * bail if there's load or we're actually up-to-date.
 	 */
-	if (load || curr_jiffies == this_rq->last_load_update_tick)
+	if (weighted_cpuload(cpu_of(this_rq)))
 		return;
 
-	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
-	this_rq->last_load_update_tick = curr_jiffies;
-
-	__update_cpu_load(this_rq, load, pending_updates, 0);
+	__update_cpu_load_nohz(this_rq, READ_ONCE(jiffies), 0, 0);
 }
 
 /*
@@ -4527,22 +4621,12 @@ void update_cpu_load_nohz(int active)
 	struct rq *this_rq = this_rq();
 	unsigned long curr_jiffies = READ_ONCE(jiffies);
 	unsigned long load = active ? weighted_cpuload(cpu_of(this_rq)) : 0;
-	unsigned long pending_updates;
 
 	if (curr_jiffies == this_rq->last_load_update_tick)
 		return;
 
 	raw_spin_lock(&this_rq->lock);
-	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
-	if (pending_updates) {
-		this_rq->last_load_update_tick = curr_jiffies;
-		/*
-		 * In the regular NOHZ case, we were idle, this means load 0.
-		 * In the NOHZ_FULL case, we were non-idle, we should consider
-		 * its weighted load.
-		 */
-		__update_cpu_load(this_rq, load, pending_updates, active);
-	}
+	__update_cpu_load_nohz(this_rq, curr_jiffies, load, active);
 	raw_spin_unlock(&this_rq->lock);
 }
 #endif /* CONFIG_NO_HZ */
@@ -4554,7 +4638,7 @@ void update_cpu_load_active(struct rq *this_rq)
 {
 	unsigned long load = weighted_cpuload(cpu_of(this_rq));
 	/*
-	 * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
+	 * See the mess around update_cpu_load_idle() / update_cpu_load_nohz().
 	 */
 	this_rq->last_load_update_tick = jiffies;
 	__update_cpu_load(this_rq, load, 1, 1);
@@ -7848,7 +7932,7 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
 		if (time_after_eq(jiffies, rq->next_balance)) {
 			raw_spin_lock_irq(&rq->lock);
 			update_rq_clock(rq);
-			update_idle_cpu_load(rq);
+			update_cpu_load_idle(rq);
 			raw_spin_unlock_irq(&rq->lock);
 			rebalance_domains(rq, CPU_IDLE);
 		}
@@ -8234,11 +8318,8 @@ void free_fair_sched_group(struct task_group *tg)
 	for_each_possible_cpu(i) {
 		if (tg->cfs_rq)
 			kfree(tg->cfs_rq[i]);
-		if (tg->se) {
-			if (tg->se[i])
-				remove_entity_load_avg(tg->se[i]);
+		if (tg->se)
 			kfree(tg->se[i]);
-		}
 	}
 
 	kfree(tg->cfs_rq);
@@ -8286,21 +8367,29 @@ err:
 	return 0;
 }
 
-void unregister_fair_sched_group(struct task_group *tg, int cpu)
+void unregister_fair_sched_group(struct task_group *tg)
 {
-	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
+	struct rq *rq;
+	int cpu;
 
-	/*
-	* Only empty task groups can be destroyed; so we can speculatively
-	* check on_list without danger of it being re-added.
-	*/
-	if (!tg->cfs_rq[cpu]->on_list)
-		return;
+	for_each_possible_cpu(cpu) {
+		if (tg->se[cpu])
+			remove_entity_load_avg(tg->se[cpu]);
 
-	raw_spin_lock_irqsave(&rq->lock, flags);
-	list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+		/*
+		 * Only empty task groups can be destroyed; so we can speculatively
+		 * check on_list without danger of it being re-added.
+		 */
+		if (!tg->cfs_rq[cpu]->on_list)
+			continue;
+
+		rq = cpu_rq(cpu);
+
+		raw_spin_lock_irqsave(&rq->lock, flags);
+		list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
+		raw_spin_unlock_irqrestore(&rq->lock, flags);
+	}
 }
 
 void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
@@ -8382,7 +8471,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 	return 1;
 }
 
-void unregister_fair_sched_group(struct task_group *tg, int cpu) { }
+void unregister_fair_sched_group(struct task_group *tg) { }
 
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 544a7133cbd1..bd12c6c714ec 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -4,6 +4,7 @@
 #include <linux/sched.h>
 #include <linux/cpu.h>
 #include <linux/cpuidle.h>
+#include <linux/cpuhotplug.h>
 #include <linux/tick.h>
 #include <linux/mm.h>
 #include <linux/stackprotector.h>
@@ -193,8 +194,6 @@ exit_idle:
 	rcu_idle_exit();
 }
 
-DEFINE_PER_CPU(bool, cpu_dead_idle);
-
 /*
  * Generic idle loop implementation
  *
@@ -221,10 +220,7 @@ static void cpu_idle_loop(void)
 			rmb();
 
 			if (cpu_is_offline(smp_processor_id())) {
-				rcu_cpu_notify(NULL, CPU_DYING_IDLE,
-					       (void *)(long)smp_processor_id());
-				smp_mb(); /* all activity before dead. */
-				this_cpu_write(cpu_dead_idle, true);
+				cpuhp_report_idle_dead();
 				arch_cpu_idle_dead();
 			}
 
@@ -291,5 +287,6 @@ void cpu_startup_entry(enum cpuhp_state state)
 	boot_init_stack_canary();
 #endif
 	arch_cpu_idle_prepare();
+	cpuhp_online_idle(state);
 	cpu_idle_loop();
 }
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 8ec86abe0ea1..c41ea7ac1764 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -58,7 +58,15 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 	raw_spin_lock(&rt_b->rt_runtime_lock);
 	if (!rt_b->rt_period_active) {
 		rt_b->rt_period_active = 1;
-		hrtimer_forward_now(&rt_b->rt_period_timer, rt_b->rt_period);
+		/*
+		 * SCHED_DEADLINE updates the bandwidth, as a run away
+		 * RT task with a DL task could hog a CPU. But DL does
+		 * not reset the period. If a deadline task was running
+		 * without an RT task running, it can cause RT tasks to
+		 * throttle when they start up. Kick the timer right away
+		 * to update the period.
+		 */
+		hrtimer_forward_now(&rt_b->rt_period_timer, ns_to_ktime(0));
 		hrtimer_start_expires(&rt_b->rt_period_timer, HRTIMER_MODE_ABS_PINNED);
 	}
 	raw_spin_unlock(&rt_b->rt_runtime_lock);
@@ -436,7 +444,7 @@ static void dequeue_top_rt_rq(struct rt_rq *rt_rq);
 
 static inline int on_rt_rq(struct sched_rt_entity *rt_se)
 {
-	return !list_empty(&rt_se->run_list);
+	return rt_se->on_rq;
 }
 
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -482,8 +490,8 @@ static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
 	return rt_se->my_q;
 }
 
-static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head);
-static void dequeue_rt_entity(struct sched_rt_entity *rt_se);
+static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags);
+static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags);
 
 static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 {
@@ -499,7 +507,7 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 		if (!rt_se)
 			enqueue_top_rt_rq(rt_rq);
 		else if (!on_rt_rq(rt_se))
-			enqueue_rt_entity(rt_se, false);
+			enqueue_rt_entity(rt_se, 0);
 
 		if (rt_rq->highest_prio.curr < curr->prio)
 			resched_curr(rq);
@@ -516,7 +524,7 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 	if (!rt_se)
 		dequeue_top_rt_rq(rt_rq);
 	else if (on_rt_rq(rt_se))
-		dequeue_rt_entity(rt_se);
+		dequeue_rt_entity(rt_se, 0);
 }
 
 static inline int rt_rq_throttled(struct rt_rq *rt_rq)
@@ -945,6 +953,10 @@ static void update_curr_rt(struct rq *rq)
 	if (curr->sched_class != &rt_sched_class)
 		return;
 
+	/* Kick cpufreq (see the comment in linux/cpufreq.h). */
+	if (cpu_of(rq) == smp_processor_id())
+		cpufreq_trigger_update(rq_clock(rq));
+
 	delta_exec = rq_clock_task(rq) - curr->se.exec_start;
 	if (unlikely((s64)delta_exec <= 0))
 		return;
@@ -1142,12 +1154,27 @@ unsigned int rt_se_nr_running(struct sched_rt_entity *rt_se)
 }
 
 static inline
+unsigned int rt_se_rr_nr_running(struct sched_rt_entity *rt_se)
+{
+	struct rt_rq *group_rq = group_rt_rq(rt_se);
+	struct task_struct *tsk;
+
+	if (group_rq)
+		return group_rq->rr_nr_running;
+
+	tsk = rt_task_of(rt_se);
+
+	return (tsk->policy == SCHED_RR) ? 1 : 0;
+}
+
+static inline
 void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
 	int prio = rt_se_prio(rt_se);
 
 	WARN_ON(!rt_prio(prio));
 	rt_rq->rt_nr_running += rt_se_nr_running(rt_se);
+	rt_rq->rr_nr_running += rt_se_rr_nr_running(rt_se);
 
 	inc_rt_prio(rt_rq, prio);
 	inc_rt_migration(rt_se, rt_rq);
@@ -1160,13 +1187,37 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 	WARN_ON(!rt_prio(rt_se_prio(rt_se)));
 	WARN_ON(!rt_rq->rt_nr_running);
 	rt_rq->rt_nr_running -= rt_se_nr_running(rt_se);
+	rt_rq->rr_nr_running -= rt_se_rr_nr_running(rt_se);
 
 	dec_rt_prio(rt_rq, rt_se_prio(rt_se));
 	dec_rt_migration(rt_se, rt_rq);
 	dec_rt_group(rt_se, rt_rq);
 }
 
-static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
+/*
+ * Change rt_se->run_list location unless SAVE && !MOVE
+ *
+ * assumes ENQUEUE/DEQUEUE flags match
+ */
+static inline bool move_entity(unsigned int flags)
+{
+	if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) == DEQUEUE_SAVE)
+		return false;
+
+	return true;
+}
+
+static void __delist_rt_entity(struct sched_rt_entity *rt_se, struct rt_prio_array *array)
+{
+	list_del_init(&rt_se->run_list);
+
+	if (list_empty(array->queue + rt_se_prio(rt_se)))
+		__clear_bit(rt_se_prio(rt_se), array->bitmap);
+
+	rt_se->on_list = 0;
+}
+
+static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
 {
 	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
 	struct rt_prio_array *array = &rt_rq->active;
@@ -1179,26 +1230,37 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
 	 * get throttled and the current group doesn't have any other
 	 * active members.
 	 */
-	if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
+	if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) {
+		if (rt_se->on_list)
+			__delist_rt_entity(rt_se, array);
 		return;
+	}
 
-	if (head)
-		list_add(&rt_se->run_list, queue);
-	else
-		list_add_tail(&rt_se->run_list, queue);
-	__set_bit(rt_se_prio(rt_se), array->bitmap);
+	if (move_entity(flags)) {
+		WARN_ON_ONCE(rt_se->on_list);
+		if (flags & ENQUEUE_HEAD)
+			list_add(&rt_se->run_list, queue);
+		else
+			list_add_tail(&rt_se->run_list, queue);
+
+		__set_bit(rt_se_prio(rt_se), array->bitmap);
+		rt_se->on_list = 1;
+	}
+	rt_se->on_rq = 1;
 
 	inc_rt_tasks(rt_se, rt_rq);
 }
 
-static void __dequeue_rt_entity(struct sched_rt_entity *rt_se)
+static void __dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
 {
 	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
 	struct rt_prio_array *array = &rt_rq->active;
 
-	list_del_init(&rt_se->run_list);
-	if (list_empty(array->queue + rt_se_prio(rt_se)))
-		__clear_bit(rt_se_prio(rt_se), array->bitmap);
+	if (move_entity(flags)) {
+		WARN_ON_ONCE(!rt_se->on_list);
+		__delist_rt_entity(rt_se, array);
+	}
+	rt_se->on_rq = 0;
 
 	dec_rt_tasks(rt_se, rt_rq);
 }
@@ -1207,7 +1269,7 @@ static void __dequeue_rt_entity(struct sched_rt_entity *rt_se)
  * Because the prio of an upper entry depends on the lower
  * entries, we must remove entries top - down.
  */
-static void dequeue_rt_stack(struct sched_rt_entity *rt_se)
+static void dequeue_rt_stack(struct sched_rt_entity *rt_se, unsigned int flags)
 {
 	struct sched_rt_entity *back = NULL;
 
@@ -1220,31 +1282,31 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se)
 
 	for (rt_se = back; rt_se; rt_se = rt_se->back) {
 		if (on_rt_rq(rt_se))
-			__dequeue_rt_entity(rt_se);
+			__dequeue_rt_entity(rt_se, flags);
 	}
 }
 
-static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
+static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
 {
 	struct rq *rq = rq_of_rt_se(rt_se);
 
-	dequeue_rt_stack(rt_se);
+	dequeue_rt_stack(rt_se, flags);
 	for_each_sched_rt_entity(rt_se)
-		__enqueue_rt_entity(rt_se, head);
+		__enqueue_rt_entity(rt_se, flags);
 	enqueue_top_rt_rq(&rq->rt);
 }
 
-static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
+static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
 {
 	struct rq *rq = rq_of_rt_se(rt_se);
 
-	dequeue_rt_stack(rt_se);
+	dequeue_rt_stack(rt_se, flags);
 
 	for_each_sched_rt_entity(rt_se) {
 		struct rt_rq *rt_rq = group_rt_rq(rt_se);
 
 		if (rt_rq && rt_rq->rt_nr_running)
-			__enqueue_rt_entity(rt_se, false);
+			__enqueue_rt_entity(rt_se, flags);
 	}
 	enqueue_top_rt_rq(&rq->rt);
 }
@@ -1260,7 +1322,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 	if (flags & ENQUEUE_WAKEUP)
 		rt_se->timeout = 0;
 
-	enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD);
+	enqueue_rt_entity(rt_se, flags);
 
 	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
@@ -1271,7 +1333,7 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 	struct sched_rt_entity *rt_se = &p->rt;
 
 	update_curr_rt(rq);
-	dequeue_rt_entity(rt_se);
+	dequeue_rt_entity(rt_se, flags);
 
 	dequeue_pushable_task(rq, p);
 }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 10f16374df7f..382848a24ed9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3,6 +3,7 @@
 #include <linux/sched/sysctl.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/deadline.h>
+#include <linux/binfmts.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/stop_machine.h>
@@ -313,12 +314,11 @@ extern int tg_nop(struct task_group *tg, void *data);
 
 extern void free_fair_sched_group(struct task_group *tg);
 extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent);
-extern void unregister_fair_sched_group(struct task_group *tg, int cpu);
+extern void unregister_fair_sched_group(struct task_group *tg);
 extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 			struct sched_entity *se, int cpu,
 			struct sched_entity *parent);
 extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
-extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
 
 extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
 extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
@@ -450,6 +450,7 @@ static inline int rt_bandwidth_enabled(void)
 struct rt_rq {
 	struct rt_prio_array active;
 	unsigned int rt_nr_running;
+	unsigned int rr_nr_running;
 #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
 	struct {
 		int curr; /* highest queued rt task prio */
@@ -909,6 +910,18 @@ static inline unsigned int group_first_cpu(struct sched_group *group)
 
 extern int group_balance_cpu(struct sched_group *sg);
 
+#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
+void register_sched_domain_sysctl(void);
+void unregister_sched_domain_sysctl(void);
+#else
+static inline void register_sched_domain_sysctl(void)
+{
+}
+static inline void unregister_sched_domain_sysctl(void)
+{
+}
+#endif
+
 #else
 
 static inline void sched_ttwu_pending(void) { }
@@ -1022,6 +1035,7 @@ extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
 #endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */
 
 extern struct static_key_false sched_numa_balancing;
+extern struct static_key_false sched_schedstats;
 
 static inline u64 global_rt_period(void)
 {
@@ -1130,18 +1144,40 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 extern const int sched_prio_to_weight[40];
 extern const u32 sched_prio_to_wmult[40];
 
+/*
+ * {de,en}queue flags:
+ *
+ * DEQUEUE_SLEEP  - task is no longer runnable
+ * ENQUEUE_WAKEUP - task just became runnable
+ *
+ * SAVE/RESTORE - an otherwise spurious dequeue/enqueue, done to ensure tasks
+ *                are in a known state which allows modification. Such pairs
+ *                should preserve as much state as possible.
+ *
+ * MOVE - paired with SAVE/RESTORE, explicitly does not preserve the location
+ *        in the runqueue.
+ *
+ * ENQUEUE_HEAD      - place at front of runqueue (tail if not specified)
+ * ENQUEUE_REPLENISH - CBS (replenish runtime and postpone deadline)
+ * ENQUEUE_WAKING    - sched_class::task_waking was called
+ *
+ */
+
+#define DEQUEUE_SLEEP		0x01
+#define DEQUEUE_SAVE		0x02 /* matches ENQUEUE_RESTORE */
+#define DEQUEUE_MOVE		0x04 /* matches ENQUEUE_MOVE */
+
 #define ENQUEUE_WAKEUP		0x01
-#define ENQUEUE_HEAD		0x02
+#define ENQUEUE_RESTORE		0x02
+#define ENQUEUE_MOVE		0x04
+
+#define ENQUEUE_HEAD		0x08
+#define ENQUEUE_REPLENISH	0x10
 #ifdef CONFIG_SMP
-#define ENQUEUE_WAKING		0x04	/* sched_class::task_waking was called */
+#define ENQUEUE_WAKING		0x20
 #else
 #define ENQUEUE_WAKING		0x00
 #endif
-#define ENQUEUE_REPLENISH	0x08
-#define ENQUEUE_RESTORE	0x10
-
-#define DEQUEUE_SLEEP		0x01
-#define DEQUEUE_SAVE		0x02
 
 #define RETRY_TASK		((void *)-1UL)
 
@@ -1278,6 +1314,35 @@ unsigned long to_ratio(u64 period, u64 runtime);
 
 extern void init_entity_runnable_average(struct sched_entity *se);
 
+#ifdef CONFIG_NO_HZ_FULL
+extern bool sched_can_stop_tick(struct rq *rq);
+
+/*
+ * Tick may be needed by tasks in the runqueue depending on their policy and
+ * requirements. If tick is needed, lets send the target an IPI to kick it out of
+ * nohz mode if necessary.
+ */
+static inline void sched_update_tick_dependency(struct rq *rq)
+{
+	int cpu;
+
+	if (!tick_nohz_full_enabled())
+		return;
+
+	cpu = cpu_of(rq);
+
+	if (!tick_nohz_full_cpu(cpu))
+		return;
+
+	if (sched_can_stop_tick(rq))
+		tick_nohz_dep_clear_cpu(cpu, TICK_DEP_BIT_SCHED);
+	else
+		tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED);
+}
+#else
+static inline void sched_update_tick_dependency(struct rq *rq) { }
+#endif
+
 static inline void add_nr_running(struct rq *rq, unsigned count)
 {
 	unsigned prev_nr = rq->nr_running;
@@ -1289,26 +1354,16 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
 		if (!rq->rd->overload)
 			rq->rd->overload = true;
 #endif
-
-#ifdef CONFIG_NO_HZ_FULL
-		if (tick_nohz_full_cpu(rq->cpu)) {
-			/*
-			 * Tick is needed if more than one task runs on a CPU.
-			 * Send the target an IPI to kick it out of nohz mode.
-			 *
-			 * We assume that IPI implies full memory barrier and the
-			 * new value of rq->nr_running is visible on reception
-			 * from the target.
-			 */
-			tick_nohz_full_kick_cpu(rq->cpu);
-		}
-#endif
 	}
+
+	sched_update_tick_dependency(rq);
 }
 
 static inline void sub_nr_running(struct rq *rq, unsigned count)
 {
 	rq->nr_running -= count;
+	/* Check if we still need preemption */
+	sched_update_tick_dependency(rq);
 }
 
 static inline void rq_last_tick_reset(struct rq *rq)
@@ -1738,3 +1793,51 @@ static inline u64 irq_time_read(int cpu)
 }
 #endif /* CONFIG_64BIT */
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
+#ifdef CONFIG_CPU_FREQ
+DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+
+/**
+ * cpufreq_update_util - Take a note about CPU utilization changes.
+ * @time: Current time.
+ * @util: Current utilization.
+ * @max: Utilization ceiling.
+ *
+ * This function is called by the scheduler on every invocation of
+ * update_load_avg() on the CPU whose utilization is being updated.
+ *
+ * It can only be called from RCU-sched read-side critical sections.
+ */
+static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max)
+{
+       struct update_util_data *data;
+
+       data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data));
+       if (data)
+               data->func(data, time, util, max);
+}
+
+/**
+ * cpufreq_trigger_update - Trigger CPU performance state evaluation if needed.
+ * @time: Current time.
+ *
+ * The way cpufreq is currently arranged requires it to evaluate the CPU
+ * performance state (frequency/voltage) on a regular basis to prevent it from
+ * being stuck in a completely inadequate performance level for too long.
+ * That is not guaranteed to happen if the updates are only triggered from CFS,
+ * though, because they may not be coming in if RT or deadline tasks are active
+ * all the time (or there are RT and DL tasks only).
+ *
+ * As a workaround for that issue, this function is called by the RT and DL
+ * sched classes to trigger extra cpufreq updates to prevent it from stalling,
+ * but that really is a band-aid.  Going forward it should be replaced with
+ * solutions targeted more specifically at RT and DL tasks.
+ */
+static inline void cpufreq_trigger_update(u64 time)
+{
+	cpufreq_update_util(time, ULONG_MAX, 0);
+}
+#else
+static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) {}
+static inline void cpufreq_trigger_update(u64 time) {}
+#endif /* CONFIG_CPU_FREQ */
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index b0fbc7632de5..70b3b6a20fb0 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -29,9 +29,10 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
 	if (rq)
 		rq->rq_sched_info.run_delay += delta;
 }
-# define schedstat_inc(rq, field)	do { (rq)->field++; } while (0)
-# define schedstat_add(rq, field, amt)	do { (rq)->field += (amt); } while (0)
-# define schedstat_set(var, val)	do { var = (val); } while (0)
+# define schedstat_enabled()		static_branch_unlikely(&sched_schedstats)
+# define schedstat_inc(rq, field)	do { if (schedstat_enabled()) { (rq)->field++; } } while (0)
+# define schedstat_add(rq, field, amt)	do { if (schedstat_enabled()) { (rq)->field += (amt); } } while (0)
+# define schedstat_set(var, val)	do { if (schedstat_enabled()) { var = (val); } } while (0)
 #else /* !CONFIG_SCHEDSTATS */
 static inline void
 rq_sched_info_arrive(struct rq *rq, unsigned long long delta)
@@ -42,6 +43,7 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
 static inline void
 rq_sched_info_depart(struct rq *rq, unsigned long long delta)
 {}
+# define schedstat_enabled()		0
 # define schedstat_inc(rq, field)	do { } while (0)
 # define schedstat_add(rq, field, amt)	do { } while (0)
 # define schedstat_set(var, val)	do { } while (0)
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
new file mode 100644
index 000000000000..82f0dff90030
--- /dev/null
+++ b/kernel/sched/swait.c
@@ -0,0 +1,123 @@
+#include <linux/sched.h>
+#include <linux/swait.h>
+
+void __init_swait_queue_head(struct swait_queue_head *q, const char *name,
+			     struct lock_class_key *key)
+{
+	raw_spin_lock_init(&q->lock);
+	lockdep_set_class_and_name(&q->lock, key, name);
+	INIT_LIST_HEAD(&q->task_list);
+}
+EXPORT_SYMBOL(__init_swait_queue_head);
+
+/*
+ * The thing about the wake_up_state() return value; I think we can ignore it.
+ *
+ * If for some reason it would return 0, that means the previously waiting
+ * task is already running, so it will observe condition true (or has already).
+ */
+void swake_up_locked(struct swait_queue_head *q)
+{
+	struct swait_queue *curr;
+
+	if (list_empty(&q->task_list))
+		return;
+
+	curr = list_first_entry(&q->task_list, typeof(*curr), task_list);
+	wake_up_process(curr->task);
+	list_del_init(&curr->task_list);
+}
+EXPORT_SYMBOL(swake_up_locked);
+
+void swake_up(struct swait_queue_head *q)
+{
+	unsigned long flags;
+
+	if (!swait_active(q))
+		return;
+
+	raw_spin_lock_irqsave(&q->lock, flags);
+	swake_up_locked(q);
+	raw_spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(swake_up);
+
+/*
+ * Does not allow usage from IRQ disabled, since we must be able to
+ * release IRQs to guarantee bounded hold time.
+ */
+void swake_up_all(struct swait_queue_head *q)
+{
+	struct swait_queue *curr;
+	LIST_HEAD(tmp);
+
+	if (!swait_active(q))
+		return;
+
+	raw_spin_lock_irq(&q->lock);
+	list_splice_init(&q->task_list, &tmp);
+	while (!list_empty(&tmp)) {
+		curr = list_first_entry(&tmp, typeof(*curr), task_list);
+
+		wake_up_state(curr->task, TASK_NORMAL);
+		list_del_init(&curr->task_list);
+
+		if (list_empty(&tmp))
+			break;
+
+		raw_spin_unlock_irq(&q->lock);
+		raw_spin_lock_irq(&q->lock);
+	}
+	raw_spin_unlock_irq(&q->lock);
+}
+EXPORT_SYMBOL(swake_up_all);
+
+void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
+{
+	wait->task = current;
+	if (list_empty(&wait->task_list))
+		list_add(&wait->task_list, &q->task_list);
+}
+
+void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&q->lock, flags);
+	__prepare_to_swait(q, wait);
+	set_current_state(state);
+	raw_spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(prepare_to_swait);
+
+long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state)
+{
+	if (signal_pending_state(state, current))
+		return -ERESTARTSYS;
+
+	prepare_to_swait(q, wait, state);
+
+	return 0;
+}
+EXPORT_SYMBOL(prepare_to_swait_event);
+
+void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait)
+{
+	__set_current_state(TASK_RUNNING);
+	if (!list_empty(&wait->task_list))
+		list_del_init(&wait->task_list);
+}
+
+void finish_swait(struct swait_queue_head *q, struct swait_queue *wait)
+{
+	unsigned long flags;
+
+	__set_current_state(TASK_RUNNING);
+
+	if (!list_empty_careful(&wait->task_list)) {
+		raw_spin_lock_irqsave(&q->lock, flags);
+		list_del_init(&wait->task_list);
+		raw_spin_unlock_irqrestore(&q->lock, flags);
+	}
+}
+EXPORT_SYMBOL(finish_swait);
diff --git a/kernel/smp.c b/kernel/smp.c
index d903c02223af..74165443c240 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -105,13 +105,12 @@ void __init call_function_init(void)
  * previous function call. For multi-cpu calls its even more interesting
  * as we'll have to ensure no other cpu is observing our csd.
  */
-static void csd_lock_wait(struct call_single_data *csd)
+static __always_inline void csd_lock_wait(struct call_single_data *csd)
 {
-	while (smp_load_acquire(&csd->flags) & CSD_FLAG_LOCK)
-		cpu_relax();
+	smp_cond_acquire(!(csd->flags & CSD_FLAG_LOCK));
 }
 
-static void csd_lock(struct call_single_data *csd)
+static __always_inline void csd_lock(struct call_single_data *csd)
 {
 	csd_lock_wait(csd);
 	csd->flags |= CSD_FLAG_LOCK;
@@ -124,7 +123,7 @@ static void csd_lock(struct call_single_data *csd)
 	smp_wmb();
 }
 
-static void csd_unlock(struct call_single_data *csd)
+static __always_inline void csd_unlock(struct call_single_data *csd)
 {
 	WARN_ON(!(csd->flags & CSD_FLAG_LOCK));
 
@@ -569,6 +568,7 @@ void __init smp_init(void)
 	unsigned int cpu;
 
 	idle_threads_init();
+	cpuhp_threads_init();
 
 	/* FIXME: This should be done in userspace --RR */
 	for_each_present_cpu(cpu) {
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index d264f59bff56..13bc43d1fb22 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -226,7 +226,7 @@ static void smpboot_unpark_thread(struct smp_hotplug_thread *ht, unsigned int cp
 		kthread_unpark(tsk);
 }
 
-void smpboot_unpark_threads(unsigned int cpu)
+int smpboot_unpark_threads(unsigned int cpu)
 {
 	struct smp_hotplug_thread *cur;
 
@@ -235,6 +235,7 @@ void smpboot_unpark_threads(unsigned int cpu)
 		if (cpumask_test_cpu(cpu, cur->cpumask))
 			smpboot_unpark_thread(cur, cpu);
 	mutex_unlock(&smpboot_threads_lock);
+	return 0;
 }
 
 static void smpboot_park_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
@@ -245,7 +246,7 @@ static void smpboot_park_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
 		kthread_park(tsk);
 }
 
-void smpboot_park_threads(unsigned int cpu)
+int smpboot_park_threads(unsigned int cpu)
 {
 	struct smp_hotplug_thread *cur;
 
@@ -253,6 +254,7 @@ void smpboot_park_threads(unsigned int cpu)
 	list_for_each_entry_reverse(cur, &hotplug_threads, list)
 		smpboot_park_thread(cur, cpu);
 	mutex_unlock(&smpboot_threads_lock);
+	return 0;
 }
 
 static void smpboot_destroy_threads(struct smp_hotplug_thread *ht)
diff --git a/kernel/smpboot.h b/kernel/smpboot.h
index 72415a0eb955..485b81cfab34 100644
--- a/kernel/smpboot.h
+++ b/kernel/smpboot.h
@@ -14,7 +14,9 @@ static inline void idle_threads_init(void) { }
 #endif
 
 int smpboot_create_threads(unsigned int cpu);
-void smpboot_park_threads(unsigned int cpu);
-void smpboot_unpark_threads(unsigned int cpu);
+int smpboot_park_threads(unsigned int cpu);
+int smpboot_unpark_threads(unsigned int cpu);
+
+void __init cpuhp_threads_init(void);
 
 #endif
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 479e4436f787..8aae49dd7da8 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -116,9 +116,9 @@ void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
 
 	if (preempt_count() == cnt) {
 #ifdef CONFIG_DEBUG_PREEMPT
-		current->preempt_disable_ip = get_parent_ip(CALLER_ADDR1);
+		current->preempt_disable_ip = get_lock_parent_ip();
 #endif
-		trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
+		trace_preempt_off(CALLER_ADDR0, get_lock_parent_ip());
 	}
 }
 EXPORT_SYMBOL(__local_bh_disable_ip);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 97715fd9e790..f5102fabef7f 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -350,6 +350,17 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+#ifdef CONFIG_SCHEDSTATS
+	{
+		.procname	= "sched_schedstats",
+		.data		= NULL,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= sysctl_schedstats,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+#endif /* CONFIG_SCHEDSTATS */
 #endif /* CONFIG_SMP */
 #ifdef CONFIG_NUMA_BALANCING
 	{
@@ -505,7 +516,7 @@ static struct ctl_table kern_table[] = {
 		.data		= &latencytop_enabled,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= sysctl_latencytop,
 	},
 #endif
 #ifdef CONFIG_BLK_DEV_INITRD
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 664de539299b..56ece145a814 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -323,13 +323,42 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
 		/* cs is a watchdog. */
 		if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
 			cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
+	}
+	spin_unlock_irqrestore(&watchdog_lock, flags);
+}
+
+static void clocksource_select_watchdog(bool fallback)
+{
+	struct clocksource *cs, *old_wd;
+	unsigned long flags;
+
+	spin_lock_irqsave(&watchdog_lock, flags);
+	/* save current watchdog */
+	old_wd = watchdog;
+	if (fallback)
+		watchdog = NULL;
+
+	list_for_each_entry(cs, &clocksource_list, list) {
+		/* cs is a clocksource to be watched. */
+		if (cs->flags & CLOCK_SOURCE_MUST_VERIFY)
+			continue;
+
+		/* Skip current if we were requested for a fallback. */
+		if (fallback && cs == old_wd)
+			continue;
+
 		/* Pick the best watchdog. */
-		if (!watchdog || cs->rating > watchdog->rating) {
+		if (!watchdog || cs->rating > watchdog->rating)
 			watchdog = cs;
-			/* Reset watchdog cycles */
-			clocksource_reset_watchdog();
-		}
 	}
+	/* If we failed to find a fallback restore the old one. */
+	if (!watchdog)
+		watchdog = old_wd;
+
+	/* If we changed the watchdog we need to reset cycles. */
+	if (watchdog != old_wd)
+		clocksource_reset_watchdog();
+
 	/* Check if the watchdog timer needs to be started. */
 	clocksource_start_watchdog();
 	spin_unlock_irqrestore(&watchdog_lock, flags);
@@ -404,6 +433,7 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
 		cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES;
 }
 
+static void clocksource_select_watchdog(bool fallback) { }
 static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { }
 static inline void clocksource_resume_watchdog(void) { }
 static inline int __clocksource_watchdog_kthread(void) { return 0; }
@@ -736,6 +766,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 	clocksource_enqueue(cs);
 	clocksource_enqueue_watchdog(cs);
 	clocksource_select();
+	clocksource_select_watchdog(false);
 	mutex_unlock(&clocksource_mutex);
 	return 0;
 }
@@ -758,6 +789,7 @@ void clocksource_change_rating(struct clocksource *cs, int rating)
 	mutex_lock(&clocksource_mutex);
 	__clocksource_change_rating(cs, rating);
 	clocksource_select();
+	clocksource_select_watchdog(false);
 	mutex_unlock(&clocksource_mutex);
 }
 EXPORT_SYMBOL(clocksource_change_rating);
@@ -767,12 +799,12 @@ EXPORT_SYMBOL(clocksource_change_rating);
  */
 static int clocksource_unbind(struct clocksource *cs)
 {
-	/*
-	 * I really can't convince myself to support this on hardware
-	 * designed by lobotomized monkeys.
-	 */
-	if (clocksource_is_watchdog(cs))
-		return -EBUSY;
+	if (clocksource_is_watchdog(cs)) {
+		/* Select and try to install a replacement watchdog. */
+		clocksource_select_watchdog(true);
+		if (clocksource_is_watchdog(cs))
+			return -EBUSY;
+	}
 
 	if (cs == curr_clocksource) {
 		/* Select and try to install a replacement clock source */
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 347fecf86a3f..555e21f7b966 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -68,7 +68,7 @@ static struct clocksource clocksource_jiffies = {
 	.name		= "jiffies",
 	.rating		= 1, /* lowest valid rating*/
 	.read		= jiffies_read,
-	.mask		= 0xffffffff, /*32bits*/
+	.mask		= CLOCKSOURCE_MASK(32),
 	.mult		= NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */
 	.shift		= JIFFIES_SHIFT,
 	.max_cycles	= 10,
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index f5e86d282d52..1cafba860b08 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -333,7 +333,6 @@ static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
 	return err;
 }
 
-
 /*
  * Validate the clockid_t for a new CPU-clock timer, and initialize the timer.
  * This is called from sys_timer_create() and do_cpu_nanosleep() with the
@@ -517,6 +516,10 @@ static void arm_timer(struct k_itimer *timer)
 				cputime_expires->sched_exp = exp;
 			break;
 		}
+		if (CPUCLOCK_PERTHREAD(timer->it_clock))
+			tick_dep_set_task(p, TICK_DEP_BIT_POSIX_TIMER);
+		else
+			tick_dep_set_signal(p->signal, TICK_DEP_BIT_POSIX_TIMER);
 	}
 }
 
@@ -582,39 +585,6 @@ static int cpu_timer_sample_group(const clockid_t which_clock,
 	return 0;
 }
 
-#ifdef CONFIG_NO_HZ_FULL
-static void nohz_kick_work_fn(struct work_struct *work)
-{
-	tick_nohz_full_kick_all();
-}
-
-static DECLARE_WORK(nohz_kick_work, nohz_kick_work_fn);
-
-/*
- * We need the IPIs to be sent from sane process context.
- * The posix cpu timers are always set with irqs disabled.
- */
-static void posix_cpu_timer_kick_nohz(void)
-{
-	if (context_tracking_is_enabled())
-		schedule_work(&nohz_kick_work);
-}
-
-bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk)
-{
-	if (!task_cputime_zero(&tsk->cputime_expires))
-		return false;
-
-	/* Check if cputimer is running. This is accessed without locking. */
-	if (READ_ONCE(tsk->signal->cputimer.running))
-		return false;
-
-	return true;
-}
-#else
-static inline void posix_cpu_timer_kick_nohz(void) { }
-#endif
-
 /*
  * Guts of sys_timer_settime for CPU timers.
  * This is called with the timer locked and interrupts disabled.
@@ -761,8 +731,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 		sample_to_timespec(timer->it_clock,
 				   old_incr, &old->it_interval);
 	}
-	if (!ret)
-		posix_cpu_timer_kick_nohz();
+
 	return ret;
 }
 
@@ -911,6 +880,8 @@ static void check_thread_timers(struct task_struct *tsk,
 			__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
 		}
 	}
+	if (task_cputime_zero(tsk_expires))
+		tick_dep_clear_task(tsk, TICK_DEP_BIT_POSIX_TIMER);
 }
 
 static inline void stop_process_timers(struct signal_struct *sig)
@@ -919,6 +890,7 @@ static inline void stop_process_timers(struct signal_struct *sig)
 
 	/* Turn off cputimer->running. This is done without locking. */
 	WRITE_ONCE(cputimer->running, false);
+	tick_dep_clear_signal(sig, TICK_DEP_BIT_POSIX_TIMER);
 }
 
 static u32 onecputick;
@@ -1095,8 +1067,6 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 	arm_timer(timer);
 	unlock_task_sighand(p, &flags);
 
-	/* Kick full dynticks CPUs in case they need to tick on the new timer */
-	posix_cpu_timer_kick_nohz();
 out:
 	timer->it_overrun_last = timer->it_overrun;
 	timer->it_overrun = -1;
@@ -1270,7 +1240,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 		}
 
 		if (!*newval)
-			goto out;
+			return;
 		*newval += now;
 	}
 
@@ -1288,8 +1258,8 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 			tsk->signal->cputime_expires.virt_exp = *newval;
 		break;
 	}
-out:
-	posix_cpu_timer_kick_nohz();
+
+	tick_dep_set_signal(tsk->signal, TICK_DEP_BIT_POSIX_TIMER);
 }
 
 static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 0b17424349eb..969e6704c3c9 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -22,7 +22,6 @@
 #include <linux/module.h>
 #include <linux/irq_work.h>
 #include <linux/posix-timers.h>
-#include <linux/perf_event.h>
 #include <linux/context_tracking.h>
 
 #include <asm/irq_regs.h>
@@ -158,54 +157,63 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
 cpumask_var_t tick_nohz_full_mask;
 cpumask_var_t housekeeping_mask;
 bool tick_nohz_full_running;
+static unsigned long tick_dep_mask;
 
-static bool can_stop_full_tick(void)
+static void trace_tick_dependency(unsigned long dep)
+{
+	if (dep & TICK_DEP_MASK_POSIX_TIMER) {
+		trace_tick_stop(0, TICK_DEP_MASK_POSIX_TIMER);
+		return;
+	}
+
+	if (dep & TICK_DEP_MASK_PERF_EVENTS) {
+		trace_tick_stop(0, TICK_DEP_MASK_PERF_EVENTS);
+		return;
+	}
+
+	if (dep & TICK_DEP_MASK_SCHED) {
+		trace_tick_stop(0, TICK_DEP_MASK_SCHED);
+		return;
+	}
+
+	if (dep & TICK_DEP_MASK_CLOCK_UNSTABLE)
+		trace_tick_stop(0, TICK_DEP_MASK_CLOCK_UNSTABLE);
+}
+
+static bool can_stop_full_tick(struct tick_sched *ts)
 {
 	WARN_ON_ONCE(!irqs_disabled());
 
-	if (!sched_can_stop_tick()) {
-		trace_tick_stop(0, "more than 1 task in runqueue\n");
+	if (tick_dep_mask) {
+		trace_tick_dependency(tick_dep_mask);
 		return false;
 	}
 
-	if (!posix_cpu_timers_can_stop_tick(current)) {
-		trace_tick_stop(0, "posix timers running\n");
+	if (ts->tick_dep_mask) {
+		trace_tick_dependency(ts->tick_dep_mask);
 		return false;
 	}
 
-	if (!perf_event_can_stop_tick()) {
-		trace_tick_stop(0, "perf events running\n");
+	if (current->tick_dep_mask) {
+		trace_tick_dependency(current->tick_dep_mask);
 		return false;
 	}
 
-	/* sched_clock_tick() needs us? */
-#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-	/*
-	 * TODO: kick full dynticks CPUs when
-	 * sched_clock_stable is set.
-	 */
-	if (!sched_clock_stable()) {
-		trace_tick_stop(0, "unstable sched clock\n");
-		/*
-		 * Don't allow the user to think they can get
-		 * full NO_HZ with this machine.
-		 */
-		WARN_ONCE(tick_nohz_full_running,
-			  "NO_HZ FULL will not work with unstable sched clock");
+	if (current->signal->tick_dep_mask) {
+		trace_tick_dependency(current->signal->tick_dep_mask);
 		return false;
 	}
-#endif
 
 	return true;
 }
 
-static void nohz_full_kick_work_func(struct irq_work *work)
+static void nohz_full_kick_func(struct irq_work *work)
 {
 	/* Empty, the tick restart happens on tick_nohz_irq_exit() */
 }
 
 static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
-	.func = nohz_full_kick_work_func,
+	.func = nohz_full_kick_func,
 };
 
 /*
@@ -214,7 +222,7 @@ static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
  * This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(),
  * is NMI safe.
  */
-void tick_nohz_full_kick(void)
+static void tick_nohz_full_kick(void)
 {
 	if (!tick_nohz_full_cpu(smp_processor_id()))
 		return;
@@ -234,27 +242,112 @@ void tick_nohz_full_kick_cpu(int cpu)
 	irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu);
 }
 
-static void nohz_full_kick_ipi(void *info)
-{
-	/* Empty, the tick restart happens on tick_nohz_irq_exit() */
-}
-
 /*
  * Kick all full dynticks CPUs in order to force these to re-evaluate
  * their dependency on the tick and restart it if necessary.
  */
-void tick_nohz_full_kick_all(void)
+static void tick_nohz_full_kick_all(void)
 {
+	int cpu;
+
 	if (!tick_nohz_full_running)
 		return;
 
 	preempt_disable();
-	smp_call_function_many(tick_nohz_full_mask,
-			       nohz_full_kick_ipi, NULL, false);
-	tick_nohz_full_kick();
+	for_each_cpu_and(cpu, tick_nohz_full_mask, cpu_online_mask)
+		tick_nohz_full_kick_cpu(cpu);
 	preempt_enable();
 }
 
+static void tick_nohz_dep_set_all(unsigned long *dep,
+				  enum tick_dep_bits bit)
+{
+	unsigned long prev;
+
+	prev = fetch_or(dep, BIT_MASK(bit));
+	if (!prev)
+		tick_nohz_full_kick_all();
+}
+
+/*
+ * Set a global tick dependency. Used by perf events that rely on freq and
+ * by unstable clock.
+ */
+void tick_nohz_dep_set(enum tick_dep_bits bit)
+{
+	tick_nohz_dep_set_all(&tick_dep_mask, bit);
+}
+
+void tick_nohz_dep_clear(enum tick_dep_bits bit)
+{
+	clear_bit(bit, &tick_dep_mask);
+}
+
+/*
+ * Set per-CPU tick dependency. Used by scheduler and perf events in order to
+ * manage events throttling.
+ */
+void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit)
+{
+	unsigned long prev;
+	struct tick_sched *ts;
+
+	ts = per_cpu_ptr(&tick_cpu_sched, cpu);
+
+	prev = fetch_or(&ts->tick_dep_mask, BIT_MASK(bit));
+	if (!prev) {
+		preempt_disable();
+		/* Perf needs local kick that is NMI safe */
+		if (cpu == smp_processor_id()) {
+			tick_nohz_full_kick();
+		} else {
+			/* Remote irq work not NMI-safe */
+			if (!WARN_ON_ONCE(in_nmi()))
+				tick_nohz_full_kick_cpu(cpu);
+		}
+		preempt_enable();
+	}
+}
+
+void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
+{
+	struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu);
+
+	clear_bit(bit, &ts->tick_dep_mask);
+}
+
+/*
+ * Set a per-task tick dependency. Posix CPU timers need this in order to elapse
+ * per task timers.
+ */
+void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit)
+{
+	/*
+	 * We could optimize this with just kicking the target running the task
+	 * if that noise matters for nohz full users.
+	 */
+	tick_nohz_dep_set_all(&tsk->tick_dep_mask, bit);
+}
+
+void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit)
+{
+	clear_bit(bit, &tsk->tick_dep_mask);
+}
+
+/*
+ * Set a per-taskgroup tick dependency. Posix CPU timers need this in order to elapse
+ * per process timers.
+ */
+void tick_nohz_dep_set_signal(struct signal_struct *sig, enum tick_dep_bits bit)
+{
+	tick_nohz_dep_set_all(&sig->tick_dep_mask, bit);
+}
+
+void tick_nohz_dep_clear_signal(struct signal_struct *sig, enum tick_dep_bits bit)
+{
+	clear_bit(bit, &sig->tick_dep_mask);
+}
+
 /*
  * Re-evaluate the need for the tick as we switch the current task.
  * It might need the tick due to per task/process properties:
@@ -263,15 +356,19 @@ void tick_nohz_full_kick_all(void)
 void __tick_nohz_task_switch(void)
 {
 	unsigned long flags;
+	struct tick_sched *ts;
 
 	local_irq_save(flags);
 
 	if (!tick_nohz_full_cpu(smp_processor_id()))
 		goto out;
 
-	if (tick_nohz_tick_stopped() && !can_stop_full_tick())
-		tick_nohz_full_kick();
+	ts = this_cpu_ptr(&tick_cpu_sched);
 
+	if (ts->tick_stopped) {
+		if (current->tick_dep_mask || current->signal->tick_dep_mask)
+			tick_nohz_full_kick();
+	}
 out:
 	local_irq_restore(flags);
 }
@@ -689,7 +786,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 
 		ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
 		ts->tick_stopped = 1;
-		trace_tick_stop(1, " ");
+		trace_tick_stop(1, TICK_DEP_MASK_NONE);
 	}
 
 	/*
@@ -740,7 +837,7 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts)
 	if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE)
 		return;
 
-	if (can_stop_full_tick())
+	if (can_stop_full_tick(ts))
 		tick_nohz_stop_sched_tick(ts, ktime_get(), cpu);
 	else if (ts->tick_stopped)
 		tick_nohz_restart_sched_tick(ts, ktime_get(), 1);
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index a4a8d4e9baa1..eb4e32566a83 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -60,6 +60,7 @@ struct tick_sched {
 	u64				next_timer;
 	ktime_t				idle_expires;
 	int				do_timer_last;
+	unsigned long			tick_dep_mask;
 };
 
 extern struct tick_sched *tick_get_tick_sched(int cpu);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 34b4cedfa80d..9c629bbed572 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -233,6 +233,7 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
 	u64 tmp, ntpinterval;
 	struct clocksource *old_clock;
 
+	++tk->cs_was_changed_seq;
 	old_clock = tk->tkr_mono.clock;
 	tk->tkr_mono.clock = clock;
 	tk->tkr_mono.read = clock->read;
@@ -298,17 +299,34 @@ u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset;
 static inline u32 arch_gettimeoffset(void) { return 0; }
 #endif
 
+static inline s64 timekeeping_delta_to_ns(struct tk_read_base *tkr,
+					  cycle_t delta)
+{
+	s64 nsec;
+
+	nsec = delta * tkr->mult + tkr->xtime_nsec;
+	nsec >>= tkr->shift;
+
+	/* If arch requires, add in get_arch_timeoffset() */
+	return nsec + arch_gettimeoffset();
+}
+
 static inline s64 timekeeping_get_ns(struct tk_read_base *tkr)
 {
 	cycle_t delta;
-	s64 nsec;
 
 	delta = timekeeping_get_delta(tkr);
+	return timekeeping_delta_to_ns(tkr, delta);
+}
 
-	nsec = (delta * tkr->mult + tkr->xtime_nsec) >> tkr->shift;
+static inline s64 timekeeping_cycles_to_ns(struct tk_read_base *tkr,
+					    cycle_t cycles)
+{
+	cycle_t delta;
 
-	/* If arch requires, add in get_arch_timeoffset() */
-	return nsec + arch_gettimeoffset();
+	/* calculate the delta since the last update_wall_time */
+	delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask);
+	return timekeeping_delta_to_ns(tkr, delta);
 }
 
 /**
@@ -857,44 +875,262 @@ time64_t __ktime_get_real_seconds(void)
 	return tk->xtime_sec;
 }
 
+/**
+ * ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter
+ * @systime_snapshot:	pointer to struct receiving the system time snapshot
+ */
+void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot)
+{
+	struct timekeeper *tk = &tk_core.timekeeper;
+	unsigned long seq;
+	ktime_t base_raw;
+	ktime_t base_real;
+	s64 nsec_raw;
+	s64 nsec_real;
+	cycle_t now;
 
-#ifdef CONFIG_NTP_PPS
+	WARN_ON_ONCE(timekeeping_suspended);
+
+	do {
+		seq = read_seqcount_begin(&tk_core.seq);
+
+		now = tk->tkr_mono.read(tk->tkr_mono.clock);
+		systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq;
+		systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq;
+		base_real = ktime_add(tk->tkr_mono.base,
+				      tk_core.timekeeper.offs_real);
+		base_raw = tk->tkr_raw.base;
+		nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now);
+		nsec_raw  = timekeeping_cycles_to_ns(&tk->tkr_raw, now);
+	} while (read_seqcount_retry(&tk_core.seq, seq));
+
+	systime_snapshot->cycles = now;
+	systime_snapshot->real = ktime_add_ns(base_real, nsec_real);
+	systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw);
+}
+EXPORT_SYMBOL_GPL(ktime_get_snapshot);
+
+/* Scale base by mult/div checking for overflow */
+static int scale64_check_overflow(u64 mult, u64 div, u64 *base)
+{
+	u64 tmp, rem;
+
+	tmp = div64_u64_rem(*base, div, &rem);
+
+	if (((int)sizeof(u64)*8 - fls64(mult) < fls64(tmp)) ||
+	    ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem)))
+		return -EOVERFLOW;
+	tmp *= mult;
+	rem *= mult;
+
+	do_div(rem, div);
+	*base = tmp + rem;
+	return 0;
+}
 
 /**
- * ktime_get_raw_and_real_ts64 - get day and raw monotonic time in timespec format
- * @ts_raw:	pointer to the timespec to be set to raw monotonic time
- * @ts_real:	pointer to the timespec to be set to the time of day
+ * adjust_historical_crosststamp - adjust crosstimestamp previous to current interval
+ * @history:			Snapshot representing start of history
+ * @partial_history_cycles:	Cycle offset into history (fractional part)
+ * @total_history_cycles:	Total history length in cycles
+ * @discontinuity:		True indicates clock was set on history period
+ * @ts:				Cross timestamp that should be adjusted using
+ *	partial/total ratio
  *
- * This function reads both the time of day and raw monotonic time at the
- * same time atomically and stores the resulting timestamps in timespec
- * format.
+ * Helper function used by get_device_system_crosststamp() to correct the
+ * crosstimestamp corresponding to the start of the current interval to the
+ * system counter value (timestamp point) provided by the driver. The
+ * total_history_* quantities are the total history starting at the provided
+ * reference point and ending at the start of the current interval. The cycle
+ * count between the driver timestamp point and the start of the current
+ * interval is partial_history_cycles.
  */
-void ktime_get_raw_and_real_ts64(struct timespec64 *ts_raw, struct timespec64 *ts_real)
+static int adjust_historical_crosststamp(struct system_time_snapshot *history,
+					 cycle_t partial_history_cycles,
+					 cycle_t total_history_cycles,
+					 bool discontinuity,
+					 struct system_device_crosststamp *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
-	s64 nsecs_raw, nsecs_real;
+	u64 corr_raw, corr_real;
+	bool interp_forward;
+	int ret;
 
-	WARN_ON_ONCE(timekeeping_suspended);
+	if (total_history_cycles == 0 || partial_history_cycles == 0)
+		return 0;
+
+	/* Interpolate shortest distance from beginning or end of history */
+	interp_forward = partial_history_cycles > total_history_cycles/2 ?
+		true : false;
+	partial_history_cycles = interp_forward ?
+		total_history_cycles - partial_history_cycles :
+		partial_history_cycles;
+
+	/*
+	 * Scale the monotonic raw time delta by:
+	 *	partial_history_cycles / total_history_cycles
+	 */
+	corr_raw = (u64)ktime_to_ns(
+		ktime_sub(ts->sys_monoraw, history->raw));
+	ret = scale64_check_overflow(partial_history_cycles,
+				     total_history_cycles, &corr_raw);
+	if (ret)
+		return ret;
+
+	/*
+	 * If there is a discontinuity in the history, scale monotonic raw
+	 *	correction by:
+	 *	mult(real)/mult(raw) yielding the realtime correction
+	 * Otherwise, calculate the realtime correction similar to monotonic
+	 *	raw calculation
+	 */
+	if (discontinuity) {
+		corr_real = mul_u64_u32_div
+			(corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult);
+	} else {
+		corr_real = (u64)ktime_to_ns(
+			ktime_sub(ts->sys_realtime, history->real));
+		ret = scale64_check_overflow(partial_history_cycles,
+					     total_history_cycles, &corr_real);
+		if (ret)
+			return ret;
+	}
+
+	/* Fixup monotonic raw and real time time values */
+	if (interp_forward) {
+		ts->sys_monoraw = ktime_add_ns(history->raw, corr_raw);
+		ts->sys_realtime = ktime_add_ns(history->real, corr_real);
+	} else {
+		ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw);
+		ts->sys_realtime = ktime_sub_ns(ts->sys_realtime, corr_real);
+	}
+
+	return 0;
+}
+
+/*
+ * cycle_between - true if test occurs chronologically between before and after
+ */
+static bool cycle_between(cycle_t before, cycle_t test, cycle_t after)
+{
+	if (test > before && test < after)
+		return true;
+	if (test < before && before > after)
+		return true;
+	return false;
+}
+
+/**
+ * get_device_system_crosststamp - Synchronously capture system/device timestamp
+ * @get_time_fn:	Callback to get simultaneous device time and
+ *	system counter from the device driver
+ * @ctx:		Context passed to get_time_fn()
+ * @history_begin:	Historical reference point used to interpolate system
+ *	time when counter provided by the driver is before the current interval
+ * @xtstamp:		Receives simultaneously captured system and device time
+ *
+ * Reads a timestamp from a device and correlates it to system time
+ */
+int get_device_system_crosststamp(int (*get_time_fn)
+				  (ktime_t *device_time,
+				   struct system_counterval_t *sys_counterval,
+				   void *ctx),
+				  void *ctx,
+				  struct system_time_snapshot *history_begin,
+				  struct system_device_crosststamp *xtstamp)
+{
+	struct system_counterval_t system_counterval;
+	struct timekeeper *tk = &tk_core.timekeeper;
+	cycle_t cycles, now, interval_start;
+	unsigned int clock_was_set_seq = 0;
+	ktime_t base_real, base_raw;
+	s64 nsec_real, nsec_raw;
+	u8 cs_was_changed_seq;
+	unsigned long seq;
+	bool do_interp;
+	int ret;
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
+		/*
+		 * Try to synchronously capture device time and a system
+		 * counter value calling back into the device driver
+		 */
+		ret = get_time_fn(&xtstamp->device, &system_counterval, ctx);
+		if (ret)
+			return ret;
+
+		/*
+		 * Verify that the clocksource associated with the captured
+		 * system counter value is the same as the currently installed
+		 * timekeeper clocksource
+		 */
+		if (tk->tkr_mono.clock != system_counterval.cs)
+			return -ENODEV;
+		cycles = system_counterval.cycles;
 
-		*ts_raw = tk->raw_time;
-		ts_real->tv_sec = tk->xtime_sec;
-		ts_real->tv_nsec = 0;
+		/*
+		 * Check whether the system counter value provided by the
+		 * device driver is on the current timekeeping interval.
+		 */
+		now = tk->tkr_mono.read(tk->tkr_mono.clock);
+		interval_start = tk->tkr_mono.cycle_last;
+		if (!cycle_between(interval_start, cycles, now)) {
+			clock_was_set_seq = tk->clock_was_set_seq;
+			cs_was_changed_seq = tk->cs_was_changed_seq;
+			cycles = interval_start;
+			do_interp = true;
+		} else {
+			do_interp = false;
+		}
 
-		nsecs_raw  = timekeeping_get_ns(&tk->tkr_raw);
-		nsecs_real = timekeeping_get_ns(&tk->tkr_mono);
+		base_real = ktime_add(tk->tkr_mono.base,
+				      tk_core.timekeeper.offs_real);
+		base_raw = tk->tkr_raw.base;
 
+		nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono,
+						     system_counterval.cycles);
+		nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw,
+						    system_counterval.cycles);
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
-	timespec64_add_ns(ts_raw, nsecs_raw);
-	timespec64_add_ns(ts_real, nsecs_real);
-}
-EXPORT_SYMBOL(ktime_get_raw_and_real_ts64);
+	xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real);
+	xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw);
 
-#endif /* CONFIG_NTP_PPS */
+	/*
+	 * Interpolate if necessary, adjusting back from the start of the
+	 * current interval
+	 */
+	if (do_interp) {
+		cycle_t partial_history_cycles, total_history_cycles;
+		bool discontinuity;
+
+		/*
+		 * Check that the counter value occurs after the provided
+		 * history reference and that the history doesn't cross a
+		 * clocksource change
+		 */
+		if (!history_begin ||
+		    !cycle_between(history_begin->cycles,
+				   system_counterval.cycles, cycles) ||
+		    history_begin->cs_was_changed_seq != cs_was_changed_seq)
+			return -EINVAL;
+		partial_history_cycles = cycles - system_counterval.cycles;
+		total_history_cycles = cycles - history_begin->cycles;
+		discontinuity =
+			history_begin->clock_was_set_seq != clock_was_set_seq;
+
+		ret = adjust_historical_crosststamp(history_begin,
+						    partial_history_cycles,
+						    total_history_cycles,
+						    discontinuity, xtstamp);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(get_device_system_crosststamp);
 
 /**
  * do_gettimeofday - Returns the time of day in a timeval
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index eca592f977b2..57a6eea84694 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4961,7 +4961,7 @@ void ftrace_release_mod(struct module *mod)
 	mutex_unlock(&ftrace_lock);
 }
 
-static void ftrace_module_enable(struct module *mod)
+void ftrace_module_enable(struct module *mod)
 {
 	struct dyn_ftrace *rec;
 	struct ftrace_page *pg;
@@ -5038,38 +5038,8 @@ void ftrace_module_init(struct module *mod)
 	ftrace_process_locs(mod, mod->ftrace_callsites,
 			    mod->ftrace_callsites + mod->num_ftrace_callsites);
 }
-
-static int ftrace_module_notify(struct notifier_block *self,
-				unsigned long val, void *data)
-{
-	struct module *mod = data;
-
-	switch (val) {
-	case MODULE_STATE_COMING:
-		ftrace_module_enable(mod);
-		break;
-	case MODULE_STATE_GOING:
-		ftrace_release_mod(mod);
-		break;
-	default:
-		break;
-	}
-
-	return 0;
-}
-#else
-static int ftrace_module_notify(struct notifier_block *self,
-				unsigned long val, void *data)
-{
-	return 0;
-}
 #endif /* CONFIG_MODULES */
 
-struct notifier_block ftrace_module_nb = {
-	.notifier_call = ftrace_module_notify,
-	.priority = INT_MIN,	/* Run after anything that can remove kprobes */
-};
-
 void __init ftrace_init(void)
 {
 	extern unsigned long __start_mcount_loc[];
@@ -5098,10 +5068,6 @@ void __init ftrace_init(void)
 				  __start_mcount_loc,
 				  __stop_mcount_loc);
 
-	ret = register_module_notifier(&ftrace_module_nb);
-	if (ret)
-		pr_warning("Failed to register trace ftrace module exit notifier\n");
-
 	set_ftrace_early_filters();
 
 	return;
diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
index eb4220a132ec..81b87451c0ea 100644
--- a/kernel/trace/power-traces.c
+++ b/kernel/trace/power-traces.c
@@ -15,4 +15,5 @@
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(suspend_resume);
 EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);
+EXPORT_TRACEPOINT_SYMBOL_GPL(powernv_throttle);
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f333e57c4614..05ddc0820771 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -97,16 +97,16 @@ trace_find_event_field(struct trace_event_call *call, char *name)
 	struct ftrace_event_field *field;
 	struct list_head *head;
 
-	field = __find_event_field(&ftrace_generic_fields, name);
+	head = trace_get_fields(call);
+	field = __find_event_field(head, name);
 	if (field)
 		return field;
 
-	field = __find_event_field(&ftrace_common_fields, name);
+	field = __find_event_field(&ftrace_generic_fields, name);
 	if (field)
 		return field;
 
-	head = trace_get_fields(call);
-	return __find_event_field(head, name);
+	return __find_event_field(&ftrace_common_fields, name);
 }
 
 static int __trace_define_field(struct list_head *head, const char *type,
@@ -171,8 +171,10 @@ static int trace_define_generic_fields(void)
 {
 	int ret;
 
-	__generic_field(int, cpu, FILTER_OTHER);
-	__generic_field(char *, comm, FILTER_PTR_STRING);
+	__generic_field(int, CPU, FILTER_CPU);
+	__generic_field(int, cpu, FILTER_CPU);
+	__generic_field(char *, COMM, FILTER_COMM);
+	__generic_field(char *, comm, FILTER_COMM);
 
 	return ret;
 }
@@ -869,7 +871,8 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 		 * The ftrace subsystem is for showing formats only.
 		 * They can not be enabled or disabled via the event files.
 		 */
-		if (call->class && call->class->reg)
+		if (call->class && call->class->reg &&
+		    !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
 			return file;
 	}
 
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index f93a219b18da..6816302542b2 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1043,13 +1043,14 @@ static int init_pred(struct filter_parse_state *ps,
 		return -EINVAL;
 	}
 
-	if (is_string_field(field)) {
+	if (field->filter_type == FILTER_COMM) {
+		filter_build_regex(pred);
+		fn = filter_pred_comm;
+		pred->regex.field_len = TASK_COMM_LEN;
+	} else if (is_string_field(field)) {
 		filter_build_regex(pred);
 
-		if (!strcmp(field->name, "comm")) {
-			fn = filter_pred_comm;
-			pred->regex.field_len = TASK_COMM_LEN;
-		} else if (field->filter_type == FILTER_STATIC_STRING) {
+		if (field->filter_type == FILTER_STATIC_STRING) {
 			fn = filter_pred_string;
 			pred->regex.field_len = field->size;
 		} else if (field->filter_type == FILTER_DYN_STRING)
@@ -1072,7 +1073,7 @@ static int init_pred(struct filter_parse_state *ps,
 		}
 		pred->val = val;
 
-		if (!strcmp(field->name, "cpu"))
+		if (field->filter_type == FILTER_CPU)
 			fn = filter_pred_cpu;
 		else
 			fn = select_comparison_fn(pred->op, field->size,
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index c9956440d0e6..21b81a41dae5 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -30,7 +30,7 @@
 struct trace_kprobe {
 	struct list_head	list;
 	struct kretprobe	rp;	/* Use rp.kp for kprobe use */
-	unsigned long 		nhit;
+	unsigned long __percpu *nhit;
 	const char		*symbol;	/* symbol name */
 	struct trace_probe	tp;
 };
@@ -274,6 +274,10 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group,
 	if (!tk)
 		return ERR_PTR(ret);
 
+	tk->nhit = alloc_percpu(unsigned long);
+	if (!tk->nhit)
+		goto error;
+
 	if (symbol) {
 		tk->symbol = kstrdup(symbol, GFP_KERNEL);
 		if (!tk->symbol)
@@ -313,6 +317,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group,
 error:
 	kfree(tk->tp.call.name);
 	kfree(tk->symbol);
+	free_percpu(tk->nhit);
 	kfree(tk);
 	return ERR_PTR(ret);
 }
@@ -327,6 +332,7 @@ static void free_trace_kprobe(struct trace_kprobe *tk)
 	kfree(tk->tp.call.class->system);
 	kfree(tk->tp.call.name);
 	kfree(tk->symbol);
+	free_percpu(tk->nhit);
 	kfree(tk);
 }
 
@@ -874,9 +880,14 @@ static const struct file_operations kprobe_events_ops = {
 static int probes_profile_seq_show(struct seq_file *m, void *v)
 {
 	struct trace_kprobe *tk = v;
+	unsigned long nhit = 0;
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		nhit += *per_cpu_ptr(tk->nhit, cpu);
 
 	seq_printf(m, "  %-44s %15lu %15lu\n",
-		   trace_event_name(&tk->tp.call), tk->nhit,
+		   trace_event_name(&tk->tp.call), nhit,
 		   tk->rp.kp.nmissed);
 
 	return 0;
@@ -1225,7 +1236,7 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
 {
 	struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp);
 
-	tk->nhit++;
+	raw_cpu_inc(*tk->nhit);
 
 	if (tk->tp.flags & TP_FLAG_TRACE)
 		kprobe_trace_func(tk, regs);
@@ -1242,7 +1253,7 @@ kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
 	struct trace_kprobe *tk = container_of(ri->rp, struct trace_kprobe, rp);
 
-	tk->nhit++;
+	raw_cpu_inc(*tk->nhit);
 
 	if (tk->tp.flags & TP_FLAG_TRACE)
 		kretprobe_trace_func(tk, ri, regs);
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 202df6cffcca..2a1abbaca10e 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -156,7 +156,11 @@ check_stack(unsigned long ip, unsigned long *stack)
 		for (; p < top && i < stack_trace_max.nr_entries; p++) {
 			if (stack_dump_trace[i] == ULONG_MAX)
 				break;
-			if (*p == stack_dump_trace[i]) {
+			/*
+			 * The READ_ONCE_NOCHECK is used to let KASAN know that
+			 * this is not a stack-out-of-bounds error.
+			 */
+			if ((READ_ONCE_NOCHECK(*p)) == stack_dump_trace[i]) {
 				stack_dump_trace[x] = stack_dump_trace[i++];
 				this_size = stack_trace_index[x++] =
 					(top - p) * sizeof(unsigned long);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 0655afbea83f..d1663083d903 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -186,11 +186,11 @@ print_syscall_exit(struct trace_iterator *iter, int flags,
 
 extern char *__bad_type_size(void);
 
-#define SYSCALL_FIELD(type, name)					\
-	sizeof(type) != sizeof(trace.name) ?				\
+#define SYSCALL_FIELD(type, field, name)				\
+	sizeof(type) != sizeof(trace.field) ?				\
 		__bad_type_size() :					\
-		#type, #name, offsetof(typeof(trace), name),		\
-		sizeof(trace.name), is_signed_type(type)
+		#type, #name, offsetof(typeof(trace), field),		\
+		sizeof(trace.field), is_signed_type(type)
 
 static int __init
 __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
@@ -261,7 +261,8 @@ static int __init syscall_enter_define_fields(struct trace_event_call *call)
 	int i;
 	int offset = offsetof(typeof(trace), args);
 
-	ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
+	ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr),
+				 FILTER_OTHER);
 	if (ret)
 		return ret;
 
@@ -281,11 +282,12 @@ static int __init syscall_exit_define_fields(struct trace_event_call *call)
 	struct syscall_trace_exit trace;
 	int ret;
 
-	ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
+	ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr),
+				 FILTER_OTHER);
 	if (ret)
 		return ret;
 
-	ret = trace_define_field(call, SYSCALL_FIELD(long, ret),
+	ret = trace_define_field(call, SYSCALL_FIELD(long, ret, ret),
 				 FILTER_OTHER);
 
 	return ret;
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 975cb49e32bf..f8e26ab963ed 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -93,9 +93,11 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
 {
 	struct mm_struct *mm;
 
-	/* convert pages-usec to Mbyte-usec */
-	stats->coremem = p->acct_rss_mem1 * PAGE_SIZE / MB;
-	stats->virtmem = p->acct_vm_mem1 * PAGE_SIZE / MB;
+	/* convert pages-nsec/1024 to Mbyte-usec, see __acct_update_integrals */
+	stats->coremem = p->acct_rss_mem1 * PAGE_SIZE;
+	do_div(stats->coremem, 1000 * KB);
+	stats->virtmem = p->acct_vm_mem1 * PAGE_SIZE;
+	do_div(stats->virtmem, 1000 * KB);
 	mm = get_task_mm(p);
 	if (mm) {
 		/* adjust to KB unit */
@@ -123,27 +125,28 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
 static void __acct_update_integrals(struct task_struct *tsk,
 				    cputime_t utime, cputime_t stime)
 {
-	if (likely(tsk->mm)) {
-		cputime_t time, dtime;
-		struct timeval value;
-		unsigned long flags;
-		u64 delta;
-
-		local_irq_save(flags);
-		time = stime + utime;
-		dtime = time - tsk->acct_timexpd;
-		jiffies_to_timeval(cputime_to_jiffies(dtime), &value);
-		delta = value.tv_sec;
-		delta = delta * USEC_PER_SEC + value.tv_usec;
-
-		if (delta == 0)
-			goto out;
-		tsk->acct_timexpd = time;
-		tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm);
-		tsk->acct_vm_mem1 += delta * tsk->mm->total_vm;
-	out:
-		local_irq_restore(flags);
-	}
+	cputime_t time, dtime;
+	u64 delta;
+
+	if (!likely(tsk->mm))
+		return;
+
+	time = stime + utime;
+	dtime = time - tsk->acct_timexpd;
+	/* Avoid division: cputime_t is often in nanoseconds already. */
+	delta = cputime_to_nsecs(dtime);
+
+	if (delta < TICK_NSEC)
+		return;
+
+	tsk->acct_timexpd = time;
+	/*
+	 * Divide by 1024 to avoid overflow, and to avoid division.
+	 * The final unit reported to userspace is Mbyte-usecs,
+	 * the rest of the math is done in xacct_add_tsk.
+	 */
+	tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm) >> 10;
+	tsk->acct_vm_mem1 += delta * tsk->mm->total_vm >> 10;
 }
 
 /**
@@ -153,9 +156,12 @@ static void __acct_update_integrals(struct task_struct *tsk,
 void acct_update_integrals(struct task_struct *tsk)
 {
 	cputime_t utime, stime;
+	unsigned long flags;
 
+	local_irq_save(flags);
 	task_cputime(tsk, &utime, &stime);
 	__acct_update_integrals(tsk, utime, stime);
+	local_irq_restore(flags);
 }
 
 /**
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 61a0264e28f9..16e13d8628a3 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -301,11 +301,26 @@ static DEFINE_SPINLOCK(wq_mayday_lock);	/* protects wq->maydays list */
 static LIST_HEAD(workqueues);		/* PR: list of all workqueues */
 static bool workqueue_freezing;		/* PL: have wqs started freezing? */
 
-static cpumask_var_t wq_unbound_cpumask; /* PL: low level cpumask for all unbound wqs */
+/* PL: allowable cpus for unbound wqs and work items */
+static cpumask_var_t wq_unbound_cpumask;
+
+/* CPU where unbound work was last round robin scheduled from this CPU */
+static DEFINE_PER_CPU(int, wq_rr_cpu_last);
+
+/*
+ * Local execution of unbound work items is no longer guaranteed.  The
+ * following always forces round-robin CPU selection on unbound work items
+ * to uncover usages which depend on it.
+ */
+#ifdef CONFIG_DEBUG_WQ_FORCE_RR_CPU
+static bool wq_debug_force_rr_cpu = true;
+#else
+static bool wq_debug_force_rr_cpu = false;
+#endif
+module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644);
 
 /* the per-cpu worker pools */
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS],
-				     cpu_worker_pools);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], cpu_worker_pools);
 
 static DEFINE_IDR(worker_pool_idr);	/* PR: idr of all pools */
 
@@ -570,6 +585,16 @@ static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq,
 						  int node)
 {
 	assert_rcu_or_wq_mutex_or_pool_mutex(wq);
+
+	/*
+	 * XXX: @node can be NUMA_NO_NODE if CPU goes offline while a
+	 * delayed item is pending.  The plan is to keep CPU -> NODE
+	 * mapping valid and stable across CPU on/offlines.  Once that
+	 * happens, this workaround can be removed.
+	 */
+	if (unlikely(node == NUMA_NO_NODE))
+		return wq->dfl_pwq;
+
 	return rcu_dereference_raw(wq->numa_pwq_tbl[node]);
 }
 
@@ -1298,6 +1323,39 @@ static bool is_chained_work(struct workqueue_struct *wq)
 	return worker && worker->current_pwq->wq == wq;
 }
 
+/*
+ * When queueing an unbound work item to a wq, prefer local CPU if allowed
+ * by wq_unbound_cpumask.  Otherwise, round robin among the allowed ones to
+ * avoid perturbing sensitive tasks.
+ */
+static int wq_select_unbound_cpu(int cpu)
+{
+	static bool printed_dbg_warning;
+	int new_cpu;
+
+	if (likely(!wq_debug_force_rr_cpu)) {
+		if (cpumask_test_cpu(cpu, wq_unbound_cpumask))
+			return cpu;
+	} else if (!printed_dbg_warning) {
+		pr_warn("workqueue: round-robin CPU selection forced, expect performance impact\n");
+		printed_dbg_warning = true;
+	}
+
+	if (cpumask_empty(wq_unbound_cpumask))
+		return cpu;
+
+	new_cpu = __this_cpu_read(wq_rr_cpu_last);
+	new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask);
+	if (unlikely(new_cpu >= nr_cpu_ids)) {
+		new_cpu = cpumask_first_and(wq_unbound_cpumask, cpu_online_mask);
+		if (unlikely(new_cpu >= nr_cpu_ids))
+			return cpu;
+	}
+	__this_cpu_write(wq_rr_cpu_last, new_cpu);
+
+	return new_cpu;
+}
+
 static void __queue_work(int cpu, struct workqueue_struct *wq,
 			 struct work_struct *work)
 {
@@ -1323,7 +1381,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 		return;
 retry:
 	if (req_cpu == WORK_CPU_UNBOUND)
-		cpu = raw_smp_processor_id();
+		cpu = wq_select_unbound_cpu(raw_smp_processor_id());
 
 	/* pwq which will be used unless @work is executing elsewhere */
 	if (!(wq->flags & WQ_UNBOUND))
@@ -1464,13 +1522,13 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
 	timer_stats_timer_set_start_info(&dwork->timer);
 
 	dwork->wq = wq;
-	/* timer isn't guaranteed to run in this cpu, record earlier */
-	if (cpu == WORK_CPU_UNBOUND)
-		cpu = raw_smp_processor_id();
 	dwork->cpu = cpu;
 	timer->expires = jiffies + delay;
 
-	add_timer_on(timer, cpu);
+	if (unlikely(cpu != WORK_CPU_UNBOUND))
+		add_timer_on(timer, cpu);
+	else
+		add_timer(timer);
 }
 
 /**
@@ -2355,7 +2413,8 @@ static void check_flush_dependency(struct workqueue_struct *target_wq,
 	WARN_ONCE(current->flags & PF_MEMALLOC,
 		  "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%pf",
 		  current->pid, current->comm, target_wq->name, target_func);
-	WARN_ONCE(worker && (worker->current_pwq->wq->flags & WQ_MEM_RECLAIM),
+	WARN_ONCE(worker && ((worker->current_pwq->wq->flags &
+			      (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM),
 		  "workqueue: WQ_MEM_RECLAIM %s:%pf is flushing !WQ_MEM_RECLAIM %s:%pf",
 		  worker->current_pwq->wq->name, worker->current_func,
 		  target_wq->name, target_func);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index ecb9e75614bf..f28f7fad452f 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1400,6 +1400,21 @@ config RCU_EQS_DEBUG
 
 endmenu # "RCU Debugging"
 
+config DEBUG_WQ_FORCE_RR_CPU
+	bool "Force round-robin CPU selection for unbound work items"
+	depends on DEBUG_KERNEL
+	default n
+	help
+	  Workqueue used to implicitly guarantee that work items queued
+	  without explicit CPU specified are put on the local CPU.  This
+	  guarantee is no longer true and while local CPU is still
+	  preferred work items may be put on foreign CPUs.  Kernel
+	  parameter "workqueue.debug_force_rr_cpu" is added to force
+	  round-robin CPU selection to flush out usages which depend on the
+	  now broken guarantee.  This config option enables the debug
+	  feature by default.  When enabled, memory and cache locality will
+	  be impacted.
+
 config DEBUG_BLOCK_EXT_DEVT
         bool "Force extended block device numbers and spread them"
 	depends on DEBUG_KERNEL
@@ -1427,6 +1442,19 @@ config DEBUG_BLOCK_EXT_DEVT
 
 	  Say N if you are unsure.
 
+config CPU_HOTPLUG_STATE_CONTROL
+	bool "Enable CPU hotplug state control"
+	depends on DEBUG_KERNEL
+	depends on HOTPLUG_CPU
+	default n
+	help
+	  Allows to write steps between "offline" and "online" to the CPUs
+	  sysfs target file so states can be stepped granular. This is a debug
+	  option for now as the hotplug machinery cannot be stopped and
+	  restarted at arbitrary points yet.
+
+	  Say N if your are unsure.
+
 config NOTIFIER_ERROR_INJECTION
 	tristate "Notifier error injection"
 	depends on DEBUG_KERNEL
diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan
index 49518fb48cab..e07c1ba9ba13 100644
--- a/lib/Kconfig.ubsan
+++ b/lib/Kconfig.ubsan
@@ -18,6 +18,8 @@ config UBSAN_SANITIZE_ALL
 	  This option activates instrumentation for the entire kernel.
 	  If you don't enable this option, you have to explicitly specify
 	  UBSAN_SANITIZE := y for the files/directories you want to check for UB.
+	  Enabling this option will get kernel image size increased
+	  significantly.
 
 config UBSAN_ALIGNMENT
 	bool "Enable checking of pointers alignment"
@@ -25,5 +27,5 @@ config UBSAN_ALIGNMENT
 	default y if !HAVE_EFFICIENT_UNALIGNED_ACCESS
 	help
 	  This option enables detection of unaligned memory accesses.
-	  Enabling this option on architectures that support unalligned
+	  Enabling this option on architectures that support unaligned
 	  accesses may produce a lot of false positives.
diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c
index d62de8bf022d..123481814320 100644
--- a/lib/atomic64_test.c
+++ b/lib/atomic64_test.c
@@ -17,7 +17,7 @@
 #include <linux/atomic.h>
 
 #ifdef CONFIG_X86
-#include <asm/processor.h>	/* for boot_cpu_has below */
+#include <asm/cpufeature.h>	/* for boot_cpu_has below */
 #endif
 
 #define TEST(bit, op, c_op, val)				\
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 5a70f6196f57..81dedaab36cc 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -41,6 +41,7 @@ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
 			break;
 	return i;
 }
+EXPORT_SYMBOL(cpumask_any_but);
 
 /* These are not inline because of header tangles. */
 #ifdef CONFIG_CPUMASK_OFFSTACK
diff --git a/lib/klist.c b/lib/klist.c
index d74cf7a29afd..0507fa5d84c5 100644
--- a/lib/klist.c
+++ b/lib/klist.c
@@ -282,9 +282,9 @@ void klist_iter_init_node(struct klist *k, struct klist_iter *i,
 			  struct klist_node *n)
 {
 	i->i_klist = k;
-	i->i_cur = n;
-	if (n)
-		kref_get(&n->n_ref);
+	i->i_cur = NULL;
+	if (n && kref_get_unless_zero(&n->n_ref))
+		i->i_cur = n;
 }
 EXPORT_SYMBOL_GPL(klist_iter_init_node);
 
diff --git a/lib/list_debug.c b/lib/list_debug.c
index 3345a089ef7b..3859bf63561c 100644
--- a/lib/list_debug.c
+++ b/lib/list_debug.c
@@ -12,13 +12,6 @@
 #include <linux/kernel.h>
 #include <linux/rculist.h>
 
-static struct list_head force_poison;
-void list_force_poison(struct list_head *entry)
-{
-	entry->next = &force_poison;
-	entry->prev = &force_poison;
-}
-
 /*
  * Insert a new entry between two known consecutive entries.
  *
@@ -30,8 +23,6 @@ void __list_add(struct list_head *new,
 			      struct list_head *prev,
 			      struct list_head *next)
 {
-	WARN(new->next == &force_poison || new->prev == &force_poison,
-		"list_add attempted on force-poisoned entry\n");
 	WARN(next->prev != prev,
 		"list_add corruption. next->prev should be "
 		"prev (%p), but was %p. (next=%p).\n",
diff --git a/lib/mpi/longlong.h b/lib/mpi/longlong.h
index b90e255c2a68..93336502af08 100644
--- a/lib/mpi/longlong.h
+++ b/lib/mpi/longlong.h
@@ -216,7 +216,7 @@ extern UDItype __udiv_qrnnd(UDItype *, UDItype, UDItype, UDItype);
 	__asm__ ("%@ Inlined umul_ppmm\n" \
 		"umull %r1, %r0, %r2, %r3" \
 	: "=&r" ((USItype)(xh)), \
-			"=r" ((USItype)(xl)) \
+			"=&r" ((USItype)(xl)) \
 	: "r" ((USItype)(a)), \
 			"r" ((USItype)(b)) \
 	: "r0", "r1")
diff --git a/lib/mpi/mpi-inline.h b/lib/mpi/mpi-inline.h
index e2b39852b30a..c245ea31f785 100644
--- a/lib/mpi/mpi-inline.h
+++ b/lib/mpi/mpi-inline.h
@@ -30,7 +30,7 @@
 #define G10_MPI_INLINE_H
 
 #ifndef G10_MPI_INLINE_DECL
-#define G10_MPI_INLINE_DECL  extern inline
+#define G10_MPI_INLINE_DECL  static inline
 #endif
 
 G10_MPI_INLINE_DECL mpi_limb_t
diff --git a/lib/mpi/mpi-internal.h b/lib/mpi/mpi-internal.h
index c65dd1bff45a..7eceeddb3fb8 100644
--- a/lib/mpi/mpi-internal.h
+++ b/lib/mpi/mpi-internal.h
@@ -168,19 +168,19 @@ void mpi_rshift_limbs(MPI a, unsigned int count);
 int mpi_lshift_limbs(MPI a, unsigned int count);
 
 /*-- mpihelp-add.c --*/
-mpi_limb_t mpihelp_add_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
+static inline mpi_limb_t mpihelp_add_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
 			 mpi_size_t s1_size, mpi_limb_t s2_limb);
 mpi_limb_t mpihelp_add_n(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
 			 mpi_ptr_t s2_ptr, mpi_size_t size);
-mpi_limb_t mpihelp_add(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr, mpi_size_t s1_size,
+static inline mpi_limb_t mpihelp_add(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr, mpi_size_t s1_size,
 		       mpi_ptr_t s2_ptr, mpi_size_t s2_size);
 
 /*-- mpihelp-sub.c --*/
-mpi_limb_t mpihelp_sub_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
+static inline mpi_limb_t mpihelp_sub_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
 			 mpi_size_t s1_size, mpi_limb_t s2_limb);
 mpi_limb_t mpihelp_sub_n(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
 			 mpi_ptr_t s2_ptr, mpi_size_t size);
-mpi_limb_t mpihelp_sub(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr, mpi_size_t s1_size,
+static inline mpi_limb_t mpihelp_sub(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr, mpi_size_t s1_size,
 		       mpi_ptr_t s2_ptr, mpi_size_t s2_size);
 
 /*-- mpihelp-cmp.c --*/
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
index ec533a6c77b5..eb15e7dc7b65 100644
--- a/lib/mpi/mpicoder.c
+++ b/lib/mpi/mpicoder.c
@@ -128,6 +128,23 @@ leave:
 }
 EXPORT_SYMBOL_GPL(mpi_read_from_buffer);
 
+static int count_lzeros(MPI a)
+{
+	mpi_limb_t alimb;
+	int i, lzeros = 0;
+
+	for (i = a->nlimbs - 1; i >= 0; i--) {
+		alimb = a->d[i];
+		if (alimb == 0) {
+			lzeros += sizeof(mpi_limb_t);
+		} else {
+			lzeros += count_leading_zeros(alimb) / 8;
+			break;
+		}
+	}
+	return lzeros;
+}
+
 /**
  * mpi_read_buffer() - read MPI to a bufer provided by user (msb first)
  *
@@ -148,7 +165,7 @@ int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes,
 	uint8_t *p;
 	mpi_limb_t alimb;
 	unsigned int n = mpi_get_size(a);
-	int i, lzeros = 0;
+	int i, lzeros;
 
 	if (!buf || !nbytes)
 		return -EINVAL;
@@ -156,14 +173,7 @@ int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes,
 	if (sign)
 		*sign = a->sign;
 
-	p = (void *)&a->d[a->nlimbs] - 1;
-
-	for (i = a->nlimbs * sizeof(alimb) - 1; i >= 0; i--, p--) {
-		if (!*p)
-			lzeros++;
-		else
-			break;
-	}
+	lzeros = count_lzeros(a);
 
 	if (buf_len < n - lzeros) {
 		*nbytes = n - lzeros;
@@ -351,7 +361,7 @@ int mpi_write_to_sgl(MPI a, struct scatterlist *sgl, unsigned *nbytes,
 	u8 *p, *p2;
 	mpi_limb_t alimb, alimb2;
 	unsigned int n = mpi_get_size(a);
-	int i, x, y = 0, lzeros = 0, buf_len;
+	int i, x, y = 0, lzeros, buf_len;
 
 	if (!nbytes)
 		return -EINVAL;
@@ -359,14 +369,7 @@ int mpi_write_to_sgl(MPI a, struct scatterlist *sgl, unsigned *nbytes,
 	if (sign)
 		*sign = a->sign;
 
-	p = (void *)&a->d[a->nlimbs] - 1;
-
-	for (i = a->nlimbs * sizeof(alimb) - 1; i >= 0; i--, p--) {
-		if (!*p)
-			lzeros++;
-		else
-			break;
-	}
+	lzeros = count_lzeros(a);
 
 	if (*nbytes < n - lzeros) {
 		*nbytes = n - lzeros;
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index bafa9933fa76..004fc70fc56a 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -598,9 +598,9 @@ EXPORT_SYMBOL(sg_miter_next);
  *
  * Description:
  *   Stops mapping iterator @miter.  @miter should have been started
- *   started using sg_miter_start().  A stopped iteration can be
- *   resumed by calling sg_miter_next() on it.  This is useful when
- *   resources (kmap) need to be released during iteration.
+ *   using sg_miter_start().  A stopped iteration can be resumed by
+ *   calling sg_miter_next() on it.  This is useful when resources (kmap)
+ *   need to be released during iteration.
  *
  * Context:
  *   Preemption disabled if the SG_MITER_ATOMIC is set.  Don't care
diff --git a/lib/test_printf.c b/lib/test_printf.c
index 4f6ae60433bc..563f10e6876a 100644
--- a/lib/test_printf.c
+++ b/lib/test_printf.c
@@ -17,6 +17,9 @@
 #include <linux/socket.h>
 #include <linux/in.h>
 
+#include <linux/gfp.h>
+#include <linux/mm.h>
+
 #define BUF_SIZE 256
 #define PAD_SIZE 16
 #define FILL_CHAR '$'
@@ -411,6 +414,55 @@ netdev_features(void)
 }
 
 static void __init
+flags(void)
+{
+	unsigned long flags;
+	gfp_t gfp;
+	char *cmp_buffer;
+
+	flags = 0;
+	test("", "%pGp", &flags);
+
+	/* Page flags should filter the zone id */
+	flags = 1UL << NR_PAGEFLAGS;
+	test("", "%pGp", &flags);
+
+	flags |= 1UL << PG_uptodate | 1UL << PG_dirty | 1UL << PG_lru
+		| 1UL << PG_active | 1UL << PG_swapbacked;
+	test("uptodate|dirty|lru|active|swapbacked", "%pGp", &flags);
+
+
+	flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC
+			| VM_DENYWRITE;
+	test("read|exec|mayread|maywrite|mayexec|denywrite", "%pGv", &flags);
+
+	gfp = GFP_TRANSHUGE;
+	test("GFP_TRANSHUGE", "%pGg", &gfp);
+
+	gfp = GFP_ATOMIC|__GFP_DMA;
+	test("GFP_ATOMIC|GFP_DMA", "%pGg", &gfp);
+
+	gfp = __GFP_ATOMIC;
+	test("__GFP_ATOMIC", "%pGg", &gfp);
+
+	cmp_buffer = kmalloc(BUF_SIZE, GFP_KERNEL);
+	if (!cmp_buffer)
+		return;
+
+	/* Any flags not translated by the table should remain numeric */
+	gfp = ~__GFP_BITS_MASK;
+	snprintf(cmp_buffer, BUF_SIZE, "%#lx", (unsigned long) gfp);
+	test(cmp_buffer, "%pGg", &gfp);
+
+	snprintf(cmp_buffer, BUF_SIZE, "__GFP_ATOMIC|%#lx",
+							(unsigned long) gfp);
+	gfp |= __GFP_ATOMIC;
+	test(cmp_buffer, "%pGg", &gfp);
+
+	kfree(cmp_buffer);
+}
+
+static void __init
 test_pointer(void)
 {
 	plain();
@@ -428,6 +480,7 @@ test_pointer(void)
 	struct_clk();
 	bitmap();
 	netdev_features();
+	flags();
 }
 
 static int __init
diff --git a/lib/test_static_keys.c b/lib/test_static_keys.c
index c61b299e367f..915d75df2086 100644
--- a/lib/test_static_keys.c
+++ b/lib/test_static_keys.c
@@ -46,8 +46,11 @@ struct test_key {
 	bool			(*test_key)(void);
 };
 
-#define test_key_func(key, branch) \
-	({bool func(void) { return branch(key); } func;	})
+#define test_key_func(key, branch)	\
+static bool key ## _ ## branch(void)	\
+{					\
+	return branch(&key);		\
+}
 
 static void invert_key(struct static_key *key)
 {
@@ -92,6 +95,25 @@ static int verify_keys(struct test_key *keys, int size, bool invert)
 	return 0;
 }
 
+test_key_func(old_true_key, static_key_true)
+test_key_func(old_false_key, static_key_false)
+test_key_func(true_key, static_branch_likely)
+test_key_func(true_key, static_branch_unlikely)
+test_key_func(false_key, static_branch_likely)
+test_key_func(false_key, static_branch_unlikely)
+test_key_func(base_old_true_key, static_key_true)
+test_key_func(base_inv_old_true_key, static_key_true)
+test_key_func(base_old_false_key, static_key_false)
+test_key_func(base_inv_old_false_key, static_key_false)
+test_key_func(base_true_key, static_branch_likely)
+test_key_func(base_true_key, static_branch_unlikely)
+test_key_func(base_inv_true_key, static_branch_likely)
+test_key_func(base_inv_true_key, static_branch_unlikely)
+test_key_func(base_false_key, static_branch_likely)
+test_key_func(base_false_key, static_branch_unlikely)
+test_key_func(base_inv_false_key, static_branch_likely)
+test_key_func(base_inv_false_key, static_branch_unlikely)
+
 static int __init test_static_key_init(void)
 {
 	int ret;
@@ -102,95 +124,95 @@ static int __init test_static_key_init(void)
 		{
 			.init_state	= true,
 			.key		= &old_true_key,
-			.test_key	= test_key_func(&old_true_key, static_key_true),
+			.test_key	= &old_true_key_static_key_true,
 		},
 		{
 			.init_state	= false,
 			.key		= &old_false_key,
-			.test_key	= test_key_func(&old_false_key, static_key_false),
+			.test_key	= &old_false_key_static_key_false,
 		},
 		/* internal keys - new keys */
 		{
 			.init_state	= true,
 			.key		= &true_key.key,
-			.test_key	= test_key_func(&true_key, static_branch_likely),
+			.test_key	= &true_key_static_branch_likely,
 		},
 		{
 			.init_state	= true,
 			.key		= &true_key.key,
-			.test_key	= test_key_func(&true_key, static_branch_unlikely),
+			.test_key	= &true_key_static_branch_unlikely,
 		},
 		{
 			.init_state	= false,
 			.key		= &false_key.key,
-			.test_key	= test_key_func(&false_key, static_branch_likely),
+			.test_key	= &false_key_static_branch_likely,
 		},
 		{
 			.init_state	= false,
 			.key		= &false_key.key,
-			.test_key	= test_key_func(&false_key, static_branch_unlikely),
+			.test_key	= &false_key_static_branch_unlikely,
 		},
 		/* external keys - old keys */
 		{
 			.init_state	= true,
 			.key		= &base_old_true_key,
-			.test_key	= test_key_func(&base_old_true_key, static_key_true),
+			.test_key	= &base_old_true_key_static_key_true,
 		},
 		{
 			.init_state	= false,
 			.key		= &base_inv_old_true_key,
-			.test_key	= test_key_func(&base_inv_old_true_key, static_key_true),
+			.test_key	= &base_inv_old_true_key_static_key_true,
 		},
 		{
 			.init_state	= false,
 			.key		= &base_old_false_key,
-			.test_key	= test_key_func(&base_old_false_key, static_key_false),
+			.test_key	= &base_old_false_key_static_key_false,
 		},
 		{
 			.init_state	= true,
 			.key		= &base_inv_old_false_key,
-			.test_key	= test_key_func(&base_inv_old_false_key, static_key_false),
+			.test_key	= &base_inv_old_false_key_static_key_false,
 		},
 		/* external keys - new keys */
 		{
 			.init_state	= true,
 			.key		= &base_true_key.key,
-			.test_key	= test_key_func(&base_true_key, static_branch_likely),
+			.test_key	= &base_true_key_static_branch_likely,
 		},
 		{
 			.init_state	= true,
 			.key		= &base_true_key.key,
-			.test_key	= test_key_func(&base_true_key, static_branch_unlikely),
+			.test_key	= &base_true_key_static_branch_unlikely,
 		},
 		{
 			.init_state	= false,
 			.key		= &base_inv_true_key.key,
-			.test_key	= test_key_func(&base_inv_true_key, static_branch_likely),
+			.test_key	= &base_inv_true_key_static_branch_likely,
 		},
 		{
 			.init_state	= false,
 			.key		= &base_inv_true_key.key,
-			.test_key	= test_key_func(&base_inv_true_key, static_branch_unlikely),
+			.test_key	= &base_inv_true_key_static_branch_unlikely,
 		},
 		{
 			.init_state	= false,
 			.key		= &base_false_key.key,
-			.test_key	= test_key_func(&base_false_key, static_branch_likely),
+			.test_key	= &base_false_key_static_branch_likely,
 		},
 		{
 			.init_state	= false,
 			.key		= &base_false_key.key,
-			.test_key	= test_key_func(&base_false_key, static_branch_unlikely),
+			.test_key	= &base_false_key_static_branch_unlikely,
 		},
 		{
 			.init_state	= true,
 			.key		= &base_inv_false_key.key,
-			.test_key	= test_key_func(&base_inv_false_key, static_branch_likely),
+			.test_key	= &base_inv_false_key_static_branch_likely,
 		},
 		{
 			.init_state	= true,
 			.key		= &base_inv_false_key.key,
-			.test_key	= test_key_func(&base_inv_false_key, static_branch_unlikely),
+			.test_key	= &base_inv_false_key_static_branch_unlikely,
 		},
 	};
 
diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c
index 6f500ef2301d..f0b323abb4c6 100644
--- a/lib/ucs2_string.c
+++ b/lib/ucs2_string.c
@@ -49,3 +49,65 @@ ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len)
         }
 }
 EXPORT_SYMBOL(ucs2_strncmp);
+
+unsigned long
+ucs2_utf8size(const ucs2_char_t *src)
+{
+	unsigned long i;
+	unsigned long j = 0;
+
+	for (i = 0; i < ucs2_strlen(src); i++) {
+		u16 c = src[i];
+
+		if (c >= 0x800)
+			j += 3;
+		else if (c >= 0x80)
+			j += 2;
+		else
+			j += 1;
+	}
+
+	return j;
+}
+EXPORT_SYMBOL(ucs2_utf8size);
+
+/*
+ * copy at most maxlength bytes of whole utf8 characters to dest from the
+ * ucs2 string src.
+ *
+ * The return value is the number of characters copied, not including the
+ * final NUL character.
+ */
+unsigned long
+ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength)
+{
+	unsigned int i;
+	unsigned long j = 0;
+	unsigned long limit = ucs2_strnlen(src, maxlength);
+
+	for (i = 0; maxlength && i < limit; i++) {
+		u16 c = src[i];
+
+		if (c >= 0x800) {
+			if (maxlength < 3)
+				break;
+			maxlength -= 3;
+			dest[j++] = 0xe0 | (c & 0xf000) >> 12;
+			dest[j++] = 0x80 | (c & 0x0fc0) >> 6;
+			dest[j++] = 0x80 | (c & 0x003f);
+		} else if (c >= 0x80) {
+			if (maxlength < 2)
+				break;
+			maxlength -= 2;
+			dest[j++] = 0xc0 | (c & 0x7c0) >> 6;
+			dest[j++] = 0x80 | (c & 0x03f);
+		} else {
+			maxlength -= 1;
+			dest[j++] = c & 0x7f;
+		}
+	}
+	if (maxlength)
+		dest[j] = '\0';
+	return j;
+}
+EXPORT_SYMBOL(ucs2_as_utf8);
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 48ff9c36644d..525c8e19bda2 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -35,6 +35,8 @@
 #include <linux/blkdev.h>
 #endif
 
+#include "../mm/internal.h"	/* For the trace_print_flags arrays */
+
 #include <asm/page.h>		/* for PAGE_SIZE */
 #include <asm/sections.h>	/* for dereference_function_descriptor() */
 #include <asm/byteorder.h>	/* cpu_to_le16 */
@@ -1407,6 +1409,72 @@ char *clock(char *buf, char *end, struct clk *clk, struct printf_spec spec,
 	}
 }
 
+static
+char *format_flags(char *buf, char *end, unsigned long flags,
+					const struct trace_print_flags *names)
+{
+	unsigned long mask;
+	const struct printf_spec strspec = {
+		.field_width = -1,
+		.precision = -1,
+	};
+	const struct printf_spec numspec = {
+		.flags = SPECIAL|SMALL,
+		.field_width = -1,
+		.precision = -1,
+		.base = 16,
+	};
+
+	for ( ; flags && names->name; names++) {
+		mask = names->mask;
+		if ((flags & mask) != mask)
+			continue;
+
+		buf = string(buf, end, names->name, strspec);
+
+		flags &= ~mask;
+		if (flags) {
+			if (buf < end)
+				*buf = '|';
+			buf++;
+		}
+	}
+
+	if (flags)
+		buf = number(buf, end, flags, numspec);
+
+	return buf;
+}
+
+static noinline_for_stack
+char *flags_string(char *buf, char *end, void *flags_ptr, const char *fmt)
+{
+	unsigned long flags;
+	const struct trace_print_flags *names;
+
+	switch (fmt[1]) {
+	case 'p':
+		flags = *(unsigned long *)flags_ptr;
+		/* Remove zone id */
+		flags &= (1UL << NR_PAGEFLAGS) - 1;
+		names = pageflag_names;
+		break;
+	case 'v':
+		flags = *(unsigned long *)flags_ptr;
+		names = vmaflag_names;
+		break;
+	case 'g':
+		flags = *(gfp_t *)flags_ptr;
+		names = gfpflag_names;
+		break;
+	default:
+		WARN_ONCE(1, "Unsupported flags modifier: %c\n", fmt[1]);
+		return buf;
+	}
+
+	return format_flags(buf, end, flags, names);
+}
+
 int kptr_restrict __read_mostly;
 
 /*
@@ -1495,6 +1563,11 @@ int kptr_restrict __read_mostly;
  * - 'Cn' For a clock, it prints the name (Common Clock Framework) or address
  *        (legacy clock framework) of the clock
  * - 'Cr' For a clock, it prints the current rate of the clock
+ * - 'G' For flags to be printed as a collection of symbolic strings that would
+ *       construct the specific value. Supported flags given by option:
+ *       p page flags (see struct page) given as pointer to unsigned long
+ *       g gfp flags (GFP_* and __GFP_*) given as pointer to gfp_t
+ *       v vma flags (VM_*) given as pointer to unsigned long
  *
  * ** Please update also Documentation/printk-formats.txt when making changes **
  *
@@ -1590,22 +1663,23 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 			return buf;
 		}
 	case 'K':
-		/*
-		 * %pK cannot be used in IRQ context because its test
-		 * for CAP_SYSLOG would be meaningless.
-		 */
-		if (kptr_restrict && (in_irq() || in_serving_softirq() ||
-				      in_nmi())) {
-			if (spec.field_width == -1)
-				spec.field_width = default_width;
-			return string(buf, end, "pK-error", spec);
-		}
-
 		switch (kptr_restrict) {
 		case 0:
 			/* Always print %pK values */
 			break;
 		case 1: {
+			const struct cred *cred;
+
+			/*
+			 * kptr_restrict==1 cannot be used in IRQ context
+			 * because its test for CAP_SYSLOG would be meaningless.
+			 */
+			if (in_irq() || in_serving_softirq() || in_nmi()) {
+				if (spec.field_width == -1)
+					spec.field_width = default_width;
+				return string(buf, end, "pK-error", spec);
+			}
+
 			/*
 			 * Only print the real pointer value if the current
 			 * process has CAP_SYSLOG and is running with the
@@ -1615,8 +1689,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 			 * leak pointer values if a binary opens a file using
 			 * %pK and then elevates privileges before reading it.
 			 */
-			const struct cred *cred = current_cred();
-
+			cred = current_cred();
 			if (!has_capability_noaudit(current, CAP_SYSLOG) ||
 			    !uid_eq(cred->euid, cred->uid) ||
 			    !gid_eq(cred->egid, cred->gid))
@@ -1648,6 +1721,8 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 		return bdev_name(buf, end, ptr, spec, fmt);
 #endif
 
+	case 'G':
+		return flags_string(buf, end, ptr, fmt);
 	}
 	spec.flags |= SMALL;
 	if (spec.field_width == -1) {
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index 957d3da53ddd..5c50b238b770 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -16,8 +16,8 @@ config DEBUG_PAGEALLOC
 	select PAGE_POISONING if !ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	---help---
 	  Unmap pages from the kernel linear mapping after free_pages().
-	  This results in a large slowdown, but helps to find certain types
-	  of memory corruption.
+	  Depending on runtime enablement, this results in a small or large
+	  slowdown, but helps to find certain types of memory corruption.
 
 	  For architectures which don't enable ARCH_SUPPORTS_DEBUG_PAGEALLOC,
 	  fill the pages with poison patterns after free_pages() and verify
@@ -26,5 +26,56 @@ config DEBUG_PAGEALLOC
 	  that would result in incorrect warnings of memory corruption after
 	  a resume because free pages are not saved to the suspend image.
 
+	  By default this option will have a small overhead, e.g. by not
+	  allowing the kernel mapping to be backed by large pages on some
+	  architectures. Even bigger overhead comes when the debugging is
+	  enabled by DEBUG_PAGEALLOC_ENABLE_DEFAULT or the debug_pagealloc
+	  command line parameter.
+
+config DEBUG_PAGEALLOC_ENABLE_DEFAULT
+	bool "Enable debug page memory allocations by default?"
+	default n
+	depends on DEBUG_PAGEALLOC
+	---help---
+	  Enable debug page memory allocations by default? This value
+	  can be overridden by debug_pagealloc=off|on.
+
 config PAGE_POISONING
-	bool
+	bool "Poison pages after freeing"
+	select PAGE_EXTENSION
+	select PAGE_POISONING_NO_SANITY if HIBERNATION
+	---help---
+	  Fill the pages with poison patterns after free_pages() and verify
+	  the patterns before alloc_pages. The filling of the memory helps
+	  reduce the risk of information leaks from freed data. This does
+	  have a potential performance impact.
+
+	  Note that "poison" here is not the same thing as the "HWPoison"
+	  for CONFIG_MEMORY_FAILURE. This is software poisoning only.
+
+	  If unsure, say N
+
+config PAGE_POISONING_NO_SANITY
+	depends on PAGE_POISONING
+	bool "Only poison, don't sanity check"
+	---help---
+	   Skip the sanity checking on alloc, only fill the pages with
+	   poison on free. This reduces some of the overhead of the
+	   poisoning feature.
+
+	   If you are only interested in sanitization, say Y. Otherwise
+	   say N.
+
+config PAGE_POISONING_ZERO
+	bool "Use zero for poisoning instead of random data"
+	depends on PAGE_POISONING
+	---help---
+	   Instead of using the existing poison value, fill the pages with
+	   zeros. This makes it harder to detect when errors are occurring
+	   due to sanitization but the zeroing at free means that it is
+	   no longer necessary to write zeros when GFP_ZERO is used on
+	   allocation.
+
+	   Enabling page poisoning with this option will disable hibernation
+
+	   If unsure, say N
diff --git a/mm/Makefile b/mm/Makefile
index 2ed43191fc3b..cfdd481d27a5 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -48,7 +48,7 @@ obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o
 obj-$(CONFIG_SLOB) += slob.o
 obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o
 obj-$(CONFIG_KSM) += ksm.o
-obj-$(CONFIG_PAGE_POISONING) += debug-pagealloc.o
+obj-$(CONFIG_PAGE_POISONING) += page_poison.o
 obj-$(CONFIG_SLAB) += slab.o
 obj-$(CONFIG_SLUB) += slub.o
 obj-$(CONFIG_KMEMCHECK) += kmemcheck.o
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 926c76d56388..c554d173a65f 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -328,7 +328,7 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 	return 0;
 
 out_destroy_stat:
-	while (--i)
+	while (i--)
 		percpu_counter_destroy(&wb->stat[i]);
 	fprop_local_destroy_percpu(&wb->completions);
 out_put_cong:
diff --git a/mm/compaction.c b/mm/compaction.c
index 585de54dbe8c..93f71d968098 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -71,49 +71,6 @@ static inline bool migrate_async_suitable(int migratetype)
 	return is_migrate_cma(migratetype) || migratetype == MIGRATE_MOVABLE;
 }
 
-/*
- * Check that the whole (or subset of) a pageblock given by the interval of
- * [start_pfn, end_pfn) is valid and within the same zone, before scanning it
- * with the migration of free compaction scanner. The scanners then need to
- * use only pfn_valid_within() check for arches that allow holes within
- * pageblocks.
- *
- * Return struct page pointer of start_pfn, or NULL if checks were not passed.
- *
- * It's possible on some configurations to have a setup like node0 node1 node0
- * i.e. it's possible that all pages within a zones range of pages do not
- * belong to a single zone. We assume that a border between node0 and node1
- * can occur within a single pageblock, but not a node0 node1 node0
- * interleaving within a single pageblock. It is therefore sufficient to check
- * the first and last page of a pageblock and avoid checking each individual
- * page in a pageblock.
- */
-static struct page *pageblock_pfn_to_page(unsigned long start_pfn,
-				unsigned long end_pfn, struct zone *zone)
-{
-	struct page *start_page;
-	struct page *end_page;
-
-	/* end_pfn is one past the range we are checking */
-	end_pfn--;
-
-	if (!pfn_valid(start_pfn) || !pfn_valid(end_pfn))
-		return NULL;
-
-	start_page = pfn_to_page(start_pfn);
-
-	if (page_zone(start_page) != zone)
-		return NULL;
-
-	end_page = pfn_to_page(end_pfn);
-
-	/* This gives a shorter code than deriving page_zone(end_page) */
-	if (page_zone_id(start_page) != page_zone_id(end_page))
-		return NULL;
-
-	return start_page;
-}
-
 #ifdef CONFIG_COMPACTION
 
 /* Do not skip compaction more than 64 times */
@@ -200,7 +157,8 @@ static void reset_cached_positions(struct zone *zone)
 {
 	zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn;
 	zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn;
-	zone->compact_cached_free_pfn = zone_end_pfn(zone);
+	zone->compact_cached_free_pfn =
+			round_down(zone_end_pfn(zone) - 1, pageblock_nr_pages);
 }
 
 /*
@@ -554,13 +512,17 @@ unsigned long
 isolate_freepages_range(struct compact_control *cc,
 			unsigned long start_pfn, unsigned long end_pfn)
 {
-	unsigned long isolated, pfn, block_end_pfn;
+	unsigned long isolated, pfn, block_start_pfn, block_end_pfn;
 	LIST_HEAD(freelist);
 
 	pfn = start_pfn;
+	block_start_pfn = pfn & ~(pageblock_nr_pages - 1);
+	if (block_start_pfn < cc->zone->zone_start_pfn)
+		block_start_pfn = cc->zone->zone_start_pfn;
 	block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
 
 	for (; pfn < end_pfn; pfn += isolated,
+				block_start_pfn = block_end_pfn,
 				block_end_pfn += pageblock_nr_pages) {
 		/* Protect pfn from changing by isolate_freepages_block */
 		unsigned long isolate_start_pfn = pfn;
@@ -573,11 +535,13 @@ isolate_freepages_range(struct compact_control *cc,
 		 * scanning range to right one.
 		 */
 		if (pfn >= block_end_pfn) {
+			block_start_pfn = pfn & ~(pageblock_nr_pages - 1);
 			block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
 			block_end_pfn = min(block_end_pfn, end_pfn);
 		}
 
-		if (!pageblock_pfn_to_page(pfn, block_end_pfn, cc->zone))
+		if (!pageblock_pfn_to_page(block_start_pfn,
+					block_end_pfn, cc->zone))
 			break;
 
 		isolated = isolate_freepages_block(cc, &isolate_start_pfn,
@@ -863,18 +827,23 @@ unsigned long
 isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
 							unsigned long end_pfn)
 {
-	unsigned long pfn, block_end_pfn;
+	unsigned long pfn, block_start_pfn, block_end_pfn;
 
 	/* Scan block by block. First and last block may be incomplete */
 	pfn = start_pfn;
+	block_start_pfn = pfn & ~(pageblock_nr_pages - 1);
+	if (block_start_pfn < cc->zone->zone_start_pfn)
+		block_start_pfn = cc->zone->zone_start_pfn;
 	block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
 
 	for (; pfn < end_pfn; pfn = block_end_pfn,
+				block_start_pfn = block_end_pfn,
 				block_end_pfn += pageblock_nr_pages) {
 
 		block_end_pfn = min(block_end_pfn, end_pfn);
 
-		if (!pageblock_pfn_to_page(pfn, block_end_pfn, cc->zone))
+		if (!pageblock_pfn_to_page(block_start_pfn,
+					block_end_pfn, cc->zone))
 			continue;
 
 		pfn = isolate_migratepages_block(cc, pfn, block_end_pfn,
@@ -1103,7 +1072,9 @@ int sysctl_compact_unevictable_allowed __read_mostly = 1;
 static isolate_migrate_t isolate_migratepages(struct zone *zone,
 					struct compact_control *cc)
 {
-	unsigned long low_pfn, end_pfn;
+	unsigned long block_start_pfn;
+	unsigned long block_end_pfn;
+	unsigned long low_pfn;
 	unsigned long isolate_start_pfn;
 	struct page *page;
 	const isolate_mode_t isolate_mode =
@@ -1115,16 +1086,21 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 	 * initialized by compact_zone()
 	 */
 	low_pfn = cc->migrate_pfn;
+	block_start_pfn = cc->migrate_pfn & ~(pageblock_nr_pages - 1);
+	if (block_start_pfn < zone->zone_start_pfn)
+		block_start_pfn = zone->zone_start_pfn;
 
 	/* Only scan within a pageblock boundary */
-	end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages);
+	block_end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages);
 
 	/*
 	 * Iterate over whole pageblocks until we find the first suitable.
 	 * Do not cross the free scanner.
 	 */
-	for (; end_pfn <= cc->free_pfn;
-			low_pfn = end_pfn, end_pfn += pageblock_nr_pages) {
+	for (; block_end_pfn <= cc->free_pfn;
+			low_pfn = block_end_pfn,
+			block_start_pfn = block_end_pfn,
+			block_end_pfn += pageblock_nr_pages) {
 
 		/*
 		 * This can potentially iterate a massively long zone with
@@ -1135,7 +1111,8 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 						&& compact_should_abort(cc))
 			break;
 
-		page = pageblock_pfn_to_page(low_pfn, end_pfn, zone);
+		page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn,
+									zone);
 		if (!page)
 			continue;
 
@@ -1154,8 +1131,8 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 
 		/* Perform the isolation */
 		isolate_start_pfn = low_pfn;
-		low_pfn = isolate_migratepages_block(cc, low_pfn, end_pfn,
-								isolate_mode);
+		low_pfn = isolate_migratepages_block(cc, low_pfn,
+						block_end_pfn, isolate_mode);
 
 		if (!low_pfn || cc->contended) {
 			acct_isolated(zone, cc);
@@ -1371,11 +1348,11 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	 */
 	cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync];
 	cc->free_pfn = zone->compact_cached_free_pfn;
-	if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) {
-		cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1);
+	if (cc->free_pfn < start_pfn || cc->free_pfn >= end_pfn) {
+		cc->free_pfn = round_down(end_pfn - 1, pageblock_nr_pages);
 		zone->compact_cached_free_pfn = cc->free_pfn;
 	}
-	if (cc->migrate_pfn < start_pfn || cc->migrate_pfn > end_pfn) {
+	if (cc->migrate_pfn < start_pfn || cc->migrate_pfn >= end_pfn) {
 		cc->migrate_pfn = start_pfn;
 		zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn;
 		zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn;
diff --git a/mm/debug.c b/mm/debug.c
index f05b2d5d6481..df7247b0b532 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -9,75 +9,38 @@
 #include <linux/mm.h>
 #include <linux/trace_events.h>
 #include <linux/memcontrol.h>
-
-static const struct trace_print_flags pageflag_names[] = {
-	{1UL << PG_locked,		"locked"	},
-	{1UL << PG_error,		"error"		},
-	{1UL << PG_referenced,		"referenced"	},
-	{1UL << PG_uptodate,		"uptodate"	},
-	{1UL << PG_dirty,		"dirty"		},
-	{1UL << PG_lru,			"lru"		},
-	{1UL << PG_active,		"active"	},
-	{1UL << PG_slab,		"slab"		},
-	{1UL << PG_owner_priv_1,	"owner_priv_1"	},
-	{1UL << PG_arch_1,		"arch_1"	},
-	{1UL << PG_reserved,		"reserved"	},
-	{1UL << PG_private,		"private"	},
-	{1UL << PG_private_2,		"private_2"	},
-	{1UL << PG_writeback,		"writeback"	},
-	{1UL << PG_head,		"head"		},
-	{1UL << PG_swapcache,		"swapcache"	},
-	{1UL << PG_mappedtodisk,	"mappedtodisk"	},
-	{1UL << PG_reclaim,		"reclaim"	},
-	{1UL << PG_swapbacked,		"swapbacked"	},
-	{1UL << PG_unevictable,		"unevictable"	},
-#ifdef CONFIG_MMU
-	{1UL << PG_mlocked,		"mlocked"	},
-#endif
-#ifdef CONFIG_ARCH_USES_PG_UNCACHED
-	{1UL << PG_uncached,		"uncached"	},
-#endif
-#ifdef CONFIG_MEMORY_FAILURE
-	{1UL << PG_hwpoison,		"hwpoison"	},
-#endif
-#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
-	{1UL << PG_young,		"young"		},
-	{1UL << PG_idle,		"idle"		},
-#endif
+#include <trace/events/mmflags.h>
+#include <linux/migrate.h>
+#include <linux/page_owner.h>
+
+#include "internal.h"
+
+char *migrate_reason_names[MR_TYPES] = {
+	"compaction",
+	"memory_failure",
+	"memory_hotplug",
+	"syscall_or_cpuset",
+	"mempolicy_mbind",
+	"numa_misplaced",
+	"cma",
 };
 
-static void dump_flags(unsigned long flags,
-			const struct trace_print_flags *names, int count)
-{
-	const char *delim = "";
-	unsigned long mask;
-	int i;
-
-	pr_emerg("flags: %#lx(", flags);
-
-	/* remove zone id */
-	flags &= (1UL << NR_PAGEFLAGS) - 1;
-
-	for (i = 0; i < count && flags; i++) {
-
-		mask = names[i].mask;
-		if ((flags & mask) != mask)
-			continue;
-
-		flags &= ~mask;
-		pr_cont("%s%s", delim, names[i].name);
-		delim = "|";
-	}
+const struct trace_print_flags pageflag_names[] = {
+	__def_pageflag_names,
+	{0, NULL}
+};
 
-	/* check for left over flags */
-	if (flags)
-		pr_cont("%s%#lx", delim, flags);
+const struct trace_print_flags gfpflag_names[] = {
+	__def_gfpflag_names,
+	{0, NULL}
+};
 
-	pr_cont(")\n");
-}
+const struct trace_print_flags vmaflag_names[] = {
+	__def_vmaflag_names,
+	{0, NULL}
+};
 
-void dump_page_badflags(struct page *page, const char *reason,
-		unsigned long badflags)
+void __dump_page(struct page *page, const char *reason)
 {
 	pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx",
 		  page, atomic_read(&page->_count), page_mapcount(page),
@@ -85,15 +48,13 @@ void dump_page_badflags(struct page *page, const char *reason,
 	if (PageCompound(page))
 		pr_cont(" compound_mapcount: %d", compound_mapcount(page));
 	pr_cont("\n");
-	BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS);
-	dump_flags(page->flags, pageflag_names, ARRAY_SIZE(pageflag_names));
+	BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1);
+
+	pr_emerg("flags: %#lx(%pGp)\n", page->flags, &page->flags);
+
 	if (reason)
 		pr_alert("page dumped because: %s\n", reason);
-	if (page->flags & badflags) {
-		pr_alert("bad because of flags:\n");
-		dump_flags(page->flags & badflags,
-				pageflag_names, ARRAY_SIZE(pageflag_names));
-	}
+
 #ifdef CONFIG_MEMCG
 	if (page->mem_cgroup)
 		pr_alert("page->mem_cgroup:%p\n", page->mem_cgroup);
@@ -102,67 +63,26 @@ void dump_page_badflags(struct page *page, const char *reason,
 
 void dump_page(struct page *page, const char *reason)
 {
-	dump_page_badflags(page, reason, 0);
+	__dump_page(page, reason);
+	dump_page_owner(page);
 }
 EXPORT_SYMBOL(dump_page);
 
 #ifdef CONFIG_DEBUG_VM
 
-static const struct trace_print_flags vmaflags_names[] = {
-	{VM_READ,			"read"		},
-	{VM_WRITE,			"write"		},
-	{VM_EXEC,			"exec"		},
-	{VM_SHARED,			"shared"	},
-	{VM_MAYREAD,			"mayread"	},
-	{VM_MAYWRITE,			"maywrite"	},
-	{VM_MAYEXEC,			"mayexec"	},
-	{VM_MAYSHARE,			"mayshare"	},
-	{VM_GROWSDOWN,			"growsdown"	},
-	{VM_PFNMAP,			"pfnmap"	},
-	{VM_DENYWRITE,			"denywrite"	},
-	{VM_LOCKONFAULT,		"lockonfault"	},
-	{VM_LOCKED,			"locked"	},
-	{VM_IO,				"io"		},
-	{VM_SEQ_READ,			"seqread"	},
-	{VM_RAND_READ,			"randread"	},
-	{VM_DONTCOPY,			"dontcopy"	},
-	{VM_DONTEXPAND,			"dontexpand"	},
-	{VM_ACCOUNT,			"account"	},
-	{VM_NORESERVE,			"noreserve"	},
-	{VM_HUGETLB,			"hugetlb"	},
-#if defined(CONFIG_X86)
-	{VM_PAT,			"pat"		},
-#elif defined(CONFIG_PPC)
-	{VM_SAO,			"sao"		},
-#elif defined(CONFIG_PARISC) || defined(CONFIG_METAG) || defined(CONFIG_IA64)
-	{VM_GROWSUP,			"growsup"	},
-#elif !defined(CONFIG_MMU)
-	{VM_MAPPED_COPY,		"mappedcopy"	},
-#else
-	{VM_ARCH_1,			"arch_1"	},
-#endif
-	{VM_DONTDUMP,			"dontdump"	},
-#ifdef CONFIG_MEM_SOFT_DIRTY
-	{VM_SOFTDIRTY,			"softdirty"	},
-#endif
-	{VM_MIXEDMAP,			"mixedmap"	},
-	{VM_HUGEPAGE,			"hugepage"	},
-	{VM_NOHUGEPAGE,			"nohugepage"	},
-	{VM_MERGEABLE,			"mergeable"	},
-};
-
 void dump_vma(const struct vm_area_struct *vma)
 {
 	pr_emerg("vma %p start %p end %p\n"
 		"next %p prev %p mm %p\n"
 		"prot %lx anon_vma %p vm_ops %p\n"
-		"pgoff %lx file %p private_data %p\n",
+		"pgoff %lx file %p private_data %p\n"
+		"flags: %#lx(%pGv)\n",
 		vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_next,
 		vma->vm_prev, vma->vm_mm,
 		(unsigned long)pgprot_val(vma->vm_page_prot),
 		vma->anon_vma, vma->vm_ops, vma->vm_pgoff,
-		vma->vm_file, vma->vm_private_data);
-	dump_flags(vma->vm_flags, vmaflags_names, ARRAY_SIZE(vmaflags_names));
+		vma->vm_file, vma->vm_private_data,
+		vma->vm_flags, &vma->vm_flags);
 }
 EXPORT_SYMBOL(dump_vma);
 
@@ -196,7 +116,7 @@ void dump_mm(const struct mm_struct *mm)
 #if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
 		"tlb_flush_pending %d\n"
 #endif
-		"%s",	/* This is here to hold the comma */
+		"def_flags: %#lx(%pGv)\n",
 
 		mm, mm->mmap, mm->vmacache_seqnum, mm->task_size,
 #ifdef CONFIG_MMU
@@ -230,11 +150,8 @@ void dump_mm(const struct mm_struct *mm)
 #if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
 		mm->tlb_flush_pending,
 #endif
-		""		/* This is here to not have a comma! */
-		);
-
-		dump_flags(mm->def_flags, vmaflags_names,
-				ARRAY_SIZE(vmaflags_names));
+		mm->def_flags, &mm->def_flags
+	);
 }
 
 #endif		/* CONFIG_DEBUG_VM */
diff --git a/mm/failslab.c b/mm/failslab.c
index 79171b4a5826..b0fac98cd938 100644
--- a/mm/failslab.c
+++ b/mm/failslab.c
@@ -1,5 +1,7 @@
 #include <linux/fault-inject.h>
 #include <linux/slab.h>
+#include <linux/mm.h>
+#include "slab.h"
 
 static struct {
 	struct fault_attr attr;
@@ -11,18 +13,22 @@ static struct {
 	.cache_filter = false,
 };
 
-bool should_failslab(size_t size, gfp_t gfpflags, unsigned long cache_flags)
+bool should_failslab(struct kmem_cache *s, gfp_t gfpflags)
 {
+	/* No fault-injection for bootstrap cache */
+	if (unlikely(s == kmem_cache))
+		return false;
+
 	if (gfpflags & __GFP_NOFAIL)
 		return false;
 
 	if (failslab.ignore_gfp_reclaim && (gfpflags & __GFP_RECLAIM))
 		return false;
 
-	if (failslab.cache_filter && !(cache_flags & SLAB_FAILSLAB))
+	if (failslab.cache_filter && !(s->flags & SLAB_FAILSLAB))
 		return false;
 
-	return should_fail(&failslab.attr, size);
+	return should_fail(&failslab.attr, s->object_size);
 }
 
 static int __init setup_failslab(char *str)
diff --git a/mm/filemap.c b/mm/filemap.c
index bc943867d68c..61b441b191ad 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -101,7 +101,7 @@
  *    ->tree_lock		(page_remove_rmap->set_page_dirty)
  *    bdi.wb->list_lock		(page_remove_rmap->set_page_dirty)
  *    ->inode->i_lock		(page_remove_rmap->set_page_dirty)
- *    ->memcg->move_lock	(page_remove_rmap->mem_cgroup_begin_page_stat)
+ *    ->memcg->move_lock	(page_remove_rmap->lock_page_memcg)
  *    bdi.wb->list_lock		(zap_pte_range->set_page_dirty)
  *    ->inode->i_lock		(zap_pte_range->set_page_dirty)
  *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers)
@@ -176,11 +176,9 @@ static void page_cache_tree_delete(struct address_space *mapping,
 /*
  * Delete a page from the page cache and free it. Caller has to make
  * sure the page is locked and that nobody else uses it - or that usage
- * is safe.  The caller must hold the mapping's tree_lock and
- * mem_cgroup_begin_page_stat().
+ * is safe.  The caller must hold the mapping's tree_lock.
  */
-void __delete_from_page_cache(struct page *page, void *shadow,
-			      struct mem_cgroup *memcg)
+void __delete_from_page_cache(struct page *page, void *shadow)
 {
 	struct address_space *mapping = page->mapping;
 
@@ -195,6 +193,30 @@ void __delete_from_page_cache(struct page *page, void *shadow,
 	else
 		cleancache_invalidate_page(mapping, page);
 
+	VM_BUG_ON_PAGE(page_mapped(page), page);
+	if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) {
+		int mapcount;
+
+		pr_alert("BUG: Bad page cache in process %s  pfn:%05lx\n",
+			 current->comm, page_to_pfn(page));
+		dump_page(page, "still mapped when deleted");
+		dump_stack();
+		add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
+
+		mapcount = page_mapcount(page);
+		if (mapping_exiting(mapping) &&
+		    page_count(page) >= mapcount + 2) {
+			/*
+			 * All vmas have already been torn down, so it's
+			 * a good bet that actually the page is unmapped,
+			 * and we'd prefer not to leak it: if we're wrong,
+			 * some other bad page check should catch it later.
+			 */
+			page_mapcount_reset(page);
+			atomic_sub(mapcount, &page->_count);
+		}
+	}
+
 	page_cache_tree_delete(mapping, page, shadow);
 
 	page->mapping = NULL;
@@ -205,7 +227,6 @@ void __delete_from_page_cache(struct page *page, void *shadow,
 		__dec_zone_page_state(page, NR_FILE_PAGES);
 	if (PageSwapBacked(page))
 		__dec_zone_page_state(page, NR_SHMEM);
-	VM_BUG_ON_PAGE(page_mapped(page), page);
 
 	/*
 	 * At this point page must be either written or cleaned by truncate.
@@ -216,8 +237,7 @@ void __delete_from_page_cache(struct page *page, void *shadow,
 	 * anyway will be cleared before returning page into buddy allocator.
 	 */
 	if (WARN_ON_ONCE(PageDirty(page)))
-		account_page_cleaned(page, mapping, memcg,
-				     inode_to_wb(mapping->host));
+		account_page_cleaned(page, mapping, inode_to_wb(mapping->host));
 }
 
 /**
@@ -231,7 +251,6 @@ void __delete_from_page_cache(struct page *page, void *shadow,
 void delete_from_page_cache(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
-	struct mem_cgroup *memcg;
 	unsigned long flags;
 
 	void (*freepage)(struct page *);
@@ -240,11 +259,9 @@ void delete_from_page_cache(struct page *page)
 
 	freepage = mapping->a_ops->freepage;
 
-	memcg = mem_cgroup_begin_page_stat(page);
 	spin_lock_irqsave(&mapping->tree_lock, flags);
-	__delete_from_page_cache(page, NULL, memcg);
+	__delete_from_page_cache(page, NULL);
 	spin_unlock_irqrestore(&mapping->tree_lock, flags);
-	mem_cgroup_end_page_stat(memcg);
 
 	if (freepage)
 		freepage(page);
@@ -446,7 +463,8 @@ int filemap_write_and_wait(struct address_space *mapping)
 {
 	int err = 0;
 
-	if (mapping->nrpages) {
+	if ((!dax_mapping(mapping) && mapping->nrpages) ||
+	    (dax_mapping(mapping) && mapping->nrexceptional)) {
 		err = filemap_fdatawrite(mapping);
 		/*
 		 * Even if the above returned error, the pages may be
@@ -482,13 +500,8 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 {
 	int err = 0;
 
-	if (dax_mapping(mapping) && mapping->nrexceptional) {
-		err = dax_writeback_mapping_range(mapping, lstart, lend);
-		if (err)
-			return err;
-	}
-
-	if (mapping->nrpages) {
+	if ((!dax_mapping(mapping) && mapping->nrpages) ||
+	    (dax_mapping(mapping) && mapping->nrexceptional)) {
 		err = __filemap_fdatawrite_range(mapping, lstart, lend,
 						 WB_SYNC_ALL);
 		/* See comment of filemap_write_and_wait() */
@@ -532,7 +545,6 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 	if (!error) {
 		struct address_space *mapping = old->mapping;
 		void (*freepage)(struct page *);
-		struct mem_cgroup *memcg;
 		unsigned long flags;
 
 		pgoff_t offset = old->index;
@@ -542,9 +554,8 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 		new->mapping = mapping;
 		new->index = offset;
 
-		memcg = mem_cgroup_begin_page_stat(old);
 		spin_lock_irqsave(&mapping->tree_lock, flags);
-		__delete_from_page_cache(old, NULL, memcg);
+		__delete_from_page_cache(old, NULL);
 		error = radix_tree_insert(&mapping->page_tree, offset, new);
 		BUG_ON(error);
 		mapping->nrpages++;
@@ -557,8 +568,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 		if (PageSwapBacked(new))
 			__inc_zone_page_state(new, NR_SHMEM);
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
-		mem_cgroup_end_page_stat(memcg);
-		mem_cgroup_replace_page(old, new);
+		mem_cgroup_migrate(old, new);
 		radix_tree_preload_end();
 		if (freepage)
 			freepage(old);
@@ -1649,6 +1659,15 @@ find_page:
 					index, last_index - index);
 		}
 		if (!PageUptodate(page)) {
+			/*
+			 * See comment in do_read_cache_page on why
+			 * wait_on_page_locked is used to avoid unnecessarily
+			 * serialisations and why it's safe.
+			 */
+			wait_on_page_locked_killable(page);
+			if (PageUptodate(page))
+				goto page_ok;
+
 			if (inode->i_blkbits == PAGE_CACHE_SHIFT ||
 					!mapping->a_ops->is_partially_uptodate)
 				goto page_not_up_to_date;
@@ -1890,6 +1909,7 @@ EXPORT_SYMBOL(generic_file_read_iter);
  * page_cache_read - adds requested page to the page cache if not already there
  * @file:	file to read
  * @offset:	page index
+ * @gfp_mask:	memory allocation flags
  *
  * This adds the requested page to the page cache if it isn't already there,
  * and schedules an I/O to read in its contents from disk.
@@ -2283,7 +2303,7 @@ static struct page *wait_on_page_read(struct page *page)
 	return page;
 }
 
-static struct page *__read_cache_page(struct address_space *mapping,
+static struct page *do_read_cache_page(struct address_space *mapping,
 				pgoff_t index,
 				int (*filler)(void *, struct page *),
 				void *data,
@@ -2305,53 +2325,74 @@ repeat:
 			/* Presumably ENOMEM for radix tree node */
 			return ERR_PTR(err);
 		}
+
+filler:
 		err = filler(data, page);
 		if (err < 0) {
 			page_cache_release(page);
-			page = ERR_PTR(err);
-		} else {
-			page = wait_on_page_read(page);
+			return ERR_PTR(err);
 		}
-	}
-	return page;
-}
 
-static struct page *do_read_cache_page(struct address_space *mapping,
-				pgoff_t index,
-				int (*filler)(void *, struct page *),
-				void *data,
-				gfp_t gfp)
-
-{
-	struct page *page;
-	int err;
+		page = wait_on_page_read(page);
+		if (IS_ERR(page))
+			return page;
+		goto out;
+	}
+	if (PageUptodate(page))
+		goto out;
 
-retry:
-	page = __read_cache_page(mapping, index, filler, data, gfp);
-	if (IS_ERR(page))
-		return page;
+	/*
+	 * Page is not up to date and may be locked due one of the following
+	 * case a: Page is being filled and the page lock is held
+	 * case b: Read/write error clearing the page uptodate status
+	 * case c: Truncation in progress (page locked)
+	 * case d: Reclaim in progress
+	 *
+	 * Case a, the page will be up to date when the page is unlocked.
+	 *    There is no need to serialise on the page lock here as the page
+	 *    is pinned so the lock gives no additional protection. Even if the
+	 *    the page is truncated, the data is still valid if PageUptodate as
+	 *    it's a race vs truncate race.
+	 * Case b, the page will not be up to date
+	 * Case c, the page may be truncated but in itself, the data may still
+	 *    be valid after IO completes as it's a read vs truncate race. The
+	 *    operation must restart if the page is not uptodate on unlock but
+	 *    otherwise serialising on page lock to stabilise the mapping gives
+	 *    no additional guarantees to the caller as the page lock is
+	 *    released before return.
+	 * Case d, similar to truncation. If reclaim holds the page lock, it
+	 *    will be a race with remove_mapping that determines if the mapping
+	 *    is valid on unlock but otherwise the data is valid and there is
+	 *    no need to serialise with page lock.
+	 *
+	 * As the page lock gives no additional guarantee, we optimistically
+	 * wait on the page to be unlocked and check if it's up to date and
+	 * use the page if it is. Otherwise, the page lock is required to
+	 * distinguish between the different cases. The motivation is that we
+	 * avoid spurious serialisations and wakeups when multiple processes
+	 * wait on the same page for IO to complete.
+	 */
+	wait_on_page_locked(page);
 	if (PageUptodate(page))
 		goto out;
 
+	/* Distinguish between all the cases under the safety of the lock */
 	lock_page(page);
+
+	/* Case c or d, restart the operation */
 	if (!page->mapping) {
 		unlock_page(page);
 		page_cache_release(page);
-		goto retry;
+		goto repeat;
 	}
+
+	/* Someone else locked and filled the page in a very small window */
 	if (PageUptodate(page)) {
 		unlock_page(page);
 		goto out;
 	}
-	err = filler(data, page);
-	if (err < 0) {
-		page_cache_release(page);
-		return ERR_PTR(err);
-	} else {
-		page = wait_on_page_read(page);
-		if (IS_ERR(page))
-			return page;
-	}
+	goto filler;
+
 out:
 	mark_page_accessed(page);
 	return page;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 08fc0ba2207e..1ea21e203a70 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1700,7 +1700,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 		pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd);
 		VM_BUG_ON(!pmd_none(*new_pmd));
 
-		if (pmd_move_must_withdraw(new_ptl, old_ptl)) {
+		if (pmd_move_must_withdraw(new_ptl, old_ptl) &&
+				vma_is_anonymous(vma)) {
 			pgtable_t pgtable;
 			pgtable = pgtable_trans_huge_withdraw(mm, old_pmd);
 			pgtable_trans_huge_deposit(mm, new_pmd, pgtable);
@@ -2835,6 +2836,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	pgtable_t pgtable;
 	pmd_t _pmd;
 	bool young, write, dirty;
+	unsigned long addr;
 	int i;
 
 	VM_BUG_ON(haddr & ~HPAGE_PMD_MASK);
@@ -2860,10 +2862,11 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	young = pmd_young(*pmd);
 	dirty = pmd_dirty(*pmd);
 
+	pmdp_huge_split_prepare(vma, haddr, pmd);
 	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 	pmd_populate(mm, &_pmd, pgtable);
 
-	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+	for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) {
 		pte_t entry, *pte;
 		/*
 		 * Note that NUMA hinting access restrictions are not
@@ -2884,9 +2887,9 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		}
 		if (dirty)
 			SetPageDirty(page + i);
-		pte = pte_offset_map(&_pmd, haddr);
+		pte = pte_offset_map(&_pmd, addr);
 		BUG_ON(!pte_none(*pte));
-		set_pte_at(mm, haddr, pte, entry);
+		set_pte_at(mm, addr, pte, entry);
 		atomic_inc(&page[i]._mapcount);
 		pte_unmap(pte);
 	}
@@ -2936,7 +2939,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	pmd_populate(mm, pmd, pgtable);
 
 	if (freeze) {
-		for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+		for (i = 0; i < HPAGE_PMD_NR; i++) {
 			page_remove_rmap(page + i, false);
 			put_page(page + i);
 		}
@@ -3217,28 +3220,26 @@ static void unfreeze_page(struct anon_vma *anon_vma, struct page *page)
 	}
 }
 
-static int __split_huge_page_tail(struct page *head, int tail,
+static void __split_huge_page_tail(struct page *head, int tail,
 		struct lruvec *lruvec, struct list_head *list)
 {
-	int mapcount;
 	struct page *page_tail = head + tail;
 
-	mapcount = atomic_read(&page_tail->_mapcount) + 1;
+	VM_BUG_ON_PAGE(atomic_read(&page_tail->_mapcount) != -1, page_tail);
 	VM_BUG_ON_PAGE(atomic_read(&page_tail->_count) != 0, page_tail);
 
 	/*
 	 * tail_page->_count is zero and not changing from under us. But
 	 * get_page_unless_zero() may be running from under us on the
-	 * tail_page. If we used atomic_set() below instead of atomic_add(), we
+	 * tail_page. If we used atomic_set() below instead of atomic_inc(), we
 	 * would then run atomic_set() concurrently with
 	 * get_page_unless_zero(), and atomic_set() is implemented in C not
 	 * using locked ops. spin_unlock on x86 sometime uses locked ops
 	 * because of PPro errata 66, 92, so unless somebody can guarantee
 	 * atomic_set() here would be safe on all archs (and not only on x86),
-	 * it's safer to use atomic_add().
+	 * it's safer to use atomic_inc().
 	 */
-	atomic_add(mapcount + 1, &page_tail->_count);
-
+	atomic_inc(&page_tail->_count);
 
 	page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 	page_tail->flags |= (head->flags &
@@ -3272,8 +3273,6 @@ static int __split_huge_page_tail(struct page *head, int tail,
 	page_tail->index = head->index + tail;
 	page_cpupid_xchg_last(page_tail, page_cpupid_last(head));
 	lru_add_page_tail(head, page_tail, lruvec, list);
-
-	return mapcount;
 }
 
 static void __split_huge_page(struct page *page, struct list_head *list)
@@ -3281,7 +3280,7 @@ static void __split_huge_page(struct page *page, struct list_head *list)
 	struct page *head = compound_head(page);
 	struct zone *zone = page_zone(head);
 	struct lruvec *lruvec;
-	int i, tail_mapcount;
+	int i;
 
 	/* prevent PageLRU to go away from under us, and freeze lru stats */
 	spin_lock_irq(&zone->lru_lock);
@@ -3290,10 +3289,8 @@ static void __split_huge_page(struct page *page, struct list_head *list)
 	/* complete memcg works before add pages to LRU */
 	mem_cgroup_split_huge_fixup(head);
 
-	tail_mapcount = 0;
 	for (i = HPAGE_PMD_NR - 1; i >= 1; i--)
-		tail_mapcount += __split_huge_page_tail(head, i, lruvec, list);
-	atomic_sub(tail_mapcount, &head->_count);
+		__split_huge_page_tail(head, i, lruvec, list);
 
 	ClearPageCompound(head);
 	spin_unlock_irq(&zone->lru_lock);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 06ae13e869d0..aefba5a9cc47 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2630,8 +2630,10 @@ static int __init hugetlb_init(void)
 			hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
 	}
 	default_hstate_idx = hstate_index(size_to_hstate(default_hstate_size));
-	if (default_hstate_max_huge_pages)
-		default_hstate.max_huge_pages = default_hstate_max_huge_pages;
+	if (default_hstate_max_huge_pages) {
+		if (!default_hstate.max_huge_pages)
+			default_hstate.max_huge_pages = default_hstate_max_huge_pages;
+	}
 
 	hugetlb_init_hstates();
 	gather_bootmem_prealloc();
@@ -2749,7 +2751,7 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 	int ret;
 
 	if (!hugepages_supported())
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	table->data = &tmp;
 	table->maxlen = sizeof(unsigned long);
@@ -2790,7 +2792,7 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 	int ret;
 
 	if (!hugepages_supported())
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	tmp = h->nr_overcommit_huge_pages;
 
@@ -3500,7 +3502,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * COW. Warn that such a situation has occurred as it may not be obvious
 	 */
 	if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) {
-		pr_warning("PID %d killed due to inadequate hugepage pool\n",
+		pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n",
 			   current->pid);
 		return ret;
 	}
diff --git a/mm/internal.h b/mm/internal.h
index a38a21ebddb4..ad9400d759c8 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -14,6 +14,7 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
+#include <linux/tracepoint-defs.h>
 
 /*
  * The set of flags that only affect watermark checking and reclaim
@@ -131,6 +132,18 @@ __find_buddy_index(unsigned long page_idx, unsigned int order)
 	return page_idx ^ (1 << order);
 }
 
+extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn,
+				unsigned long end_pfn, struct zone *zone);
+
+static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn,
+				unsigned long end_pfn, struct zone *zone)
+{
+	if (zone->contiguous)
+		return pfn_to_page(start_pfn);
+
+	return __pageblock_pfn_to_page(start_pfn, end_pfn, zone);
+}
+
 extern int __isolate_free_page(struct page *page, unsigned int order);
 extern void __free_pages_bootmem(struct page *page, unsigned long pfn,
 					unsigned int order);
@@ -466,4 +479,9 @@ static inline void try_to_unmap_flush_dirty(void)
 }
 
 #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */
+
+extern const struct trace_print_flags pageflag_names[];
+extern const struct trace_print_flags vmaflag_names[];
+extern const struct trace_print_flags gfpflag_names[];
+
 #endif	/* __MM_INTERNAL_H */
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index bc0a8d8b8f42..1ad20ade8c91 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -20,6 +20,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/kmemleak.h>
+#include <linux/linkage.h>
 #include <linux/memblock.h>
 #include <linux/memory.h>
 #include <linux/mm.h>
@@ -60,6 +61,25 @@ void kasan_unpoison_shadow(const void *address, size_t size)
 	}
 }
 
+static void __kasan_unpoison_stack(struct task_struct *task, void *sp)
+{
+	void *base = task_stack_page(task);
+	size_t size = sp - base;
+
+	kasan_unpoison_shadow(base, size);
+}
+
+/* Unpoison the entire stack for a task. */
+void kasan_unpoison_task_stack(struct task_struct *task)
+{
+	__kasan_unpoison_stack(task, task_stack_page(task) + THREAD_SIZE);
+}
+
+/* Unpoison the stack for the current task beyond a watermark sp value. */
+asmlinkage void kasan_unpoison_remaining_stack(void *sp)
+{
+	__kasan_unpoison_stack(current, sp);
+}
 
 /*
  * All functions below always inlined so compiler could
diff --git a/mm/kmemcheck.c b/mm/kmemcheck.c
index cab58bb592d8..6f4f424037c0 100644
--- a/mm/kmemcheck.c
+++ b/mm/kmemcheck.c
@@ -60,6 +60,9 @@ void kmemcheck_free_shadow(struct page *page, int order)
 void kmemcheck_slab_alloc(struct kmem_cache *s, gfp_t gfpflags, void *object,
 			  size_t size)
 {
+	if (unlikely(!object)) /* Skip object if allocation failed */
+		return;
+
 	/*
 	 * Has already been memset(), which initializes the shadow for us
 	 * as well.
diff --git a/mm/madvise.c b/mm/madvise.c
index f56825b6d2e1..a01147359f3b 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -555,8 +555,9 @@ static int madvise_hwpoison(int bhv, unsigned long start, unsigned long end)
 		}
 		pr_info("Injecting memory failure for page %#lx at %#lx\n",
 		       page_to_pfn(p), start);
-		/* Ignore return value for now */
-		memory_failure(page_to_pfn(p), 0, MF_COUNT_INCREASED);
+		ret = memory_failure(page_to_pfn(p), 0, MF_COUNT_INCREASED);
+		if (ret)
+			return ret;
 	}
 	return 0;
 }
@@ -638,14 +639,28 @@ madvise_behavior_valid(int behavior)
  *		some pages ahead.
  *  MADV_DONTNEED - the application is finished with the given range,
  *		so the kernel can free resources associated with it.
+ *  MADV_FREE - the application marks pages in the given range as lazy free,
+ *		where actual purges are postponed until memory pressure happens.
  *  MADV_REMOVE - the application wants to free up the given range of
  *		pages and associated backing store.
  *  MADV_DONTFORK - omit this area from child's address space when forking:
  *		typically, to avoid COWing pages pinned by get_user_pages().
  *  MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking.
+ *  MADV_HWPOISON - trigger memory error handler as if the given memory range
+ *		were corrupted by unrecoverable hardware memory failure.
+ *  MADV_SOFT_OFFLINE - try to soft-offline the given range of memory.
  *  MADV_MERGEABLE - the application recommends that KSM try to merge pages in
  *		this area with pages of identical content from other such areas.
  *  MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others.
+ *  MADV_HUGEPAGE - the application wants to back the given range by transparent
+ *		huge pages in the future. Existing pages might be coalesced and
+ *		new pages might be allocated as THP.
+ *  MADV_NOHUGEPAGE - mark the given range as not worth being backed by
+ *		transparent huge pages so the existing pages will not be
+ *		coalesced into THP and new pages will not be allocated as THP.
+ *  MADV_DONTDUMP - the application wants to prevent pages in the given range
+ *		from being included in its core dump.
+ *  MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump.
  *
  * return values:
  *  zero    - success
diff --git a/mm/memblock.c b/mm/memblock.c
index dd7989929f13..fc7824fa1b42 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -612,14 +612,12 @@ static int __init_memblock memblock_add_region(phys_addr_t base,
 						int nid,
 						unsigned long flags)
 {
-	struct memblock_type *type = &memblock.memory;
-
 	memblock_dbg("memblock_add: [%#016llx-%#016llx] flags %#02lx %pF\n",
 		     (unsigned long long)base,
 		     (unsigned long long)base + size - 1,
 		     flags, (void *)_RET_IP_);
 
-	return memblock_add_range(type, base, size, nid, flags);
+	return memblock_add_range(&memblock.memory, base, size, nid, flags);
 }
 
 int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
@@ -740,14 +738,12 @@ static int __init_memblock memblock_reserve_region(phys_addr_t base,
 						   int nid,
 						   unsigned long flags)
 {
-	struct memblock_type *type = &memblock.reserved;
-
 	memblock_dbg("memblock_reserve: [%#016llx-%#016llx] flags %#02lx %pF\n",
 		     (unsigned long long)base,
 		     (unsigned long long)base + size - 1,
 		     flags, (void *)_RET_IP_);
 
-	return memblock_add_range(type, base, size, nid, flags);
+	return memblock_add_range(&memblock.reserved, base, size, nid, flags);
 }
 
 int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d06cae2de783..42882c1e7fce 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -268,31 +268,6 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
 	return (memcg == root_mem_cgroup);
 }
 
-/*
- * We restrict the id in the range of [1, 65535], so it can fit into
- * an unsigned short.
- */
-#define MEM_CGROUP_ID_MAX	USHRT_MAX
-
-static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
-{
-	return memcg->css.id;
-}
-
-/*
- * A helper function to get mem_cgroup from ID. must be called under
- * rcu_read_lock().  The caller is responsible for calling
- * css_tryget_online() if the mem_cgroup is used for charging. (dropping
- * refcnt from swap can be called against removed memcg.)
- */
-static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
-{
-	struct cgroup_subsys_state *css;
-
-	css = css_from_id(id, &memory_cgrp_subsys);
-	return mem_cgroup_from_css(css);
-}
-
 #ifndef CONFIG_SLOB
 /*
  * This will be the memcg's index in each cache's ->memcg_params.memcg_caches.
@@ -1709,19 +1684,13 @@ cleanup:
 }
 
 /**
- * mem_cgroup_begin_page_stat - begin a page state statistics transaction
- * @page: page that is going to change accounted state
- *
- * This function must mark the beginning of an accounted page state
- * change to prevent double accounting when the page is concurrently
- * being moved to another memcg:
+ * lock_page_memcg - lock a page->mem_cgroup binding
+ * @page: the page
  *
- *   memcg = mem_cgroup_begin_page_stat(page);
- *   if (TestClearPageState(page))
- *     mem_cgroup_update_page_stat(memcg, state, -1);
- *   mem_cgroup_end_page_stat(memcg);
+ * This function protects unlocked LRU pages from being moved to
+ * another cgroup and stabilizes their page->mem_cgroup binding.
  */
-struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page)
+void lock_page_memcg(struct page *page)
 {
 	struct mem_cgroup *memcg;
 	unsigned long flags;
@@ -1730,25 +1699,18 @@ struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page)
 	 * The RCU lock is held throughout the transaction.  The fast
 	 * path can get away without acquiring the memcg->move_lock
 	 * because page moving starts with an RCU grace period.
-	 *
-	 * The RCU lock also protects the memcg from being freed when
-	 * the page state that is going to change is the only thing
-	 * preventing the page from being uncharged.
-	 * E.g. end-writeback clearing PageWriteback(), which allows
-	 * migration to go ahead and uncharge the page before the
-	 * account transaction might be complete.
 	 */
 	rcu_read_lock();
 
 	if (mem_cgroup_disabled())
-		return NULL;
+		return;
 again:
 	memcg = page->mem_cgroup;
 	if (unlikely(!memcg))
-		return NULL;
+		return;
 
 	if (atomic_read(&memcg->moving_account) <= 0)
-		return memcg;
+		return;
 
 	spin_lock_irqsave(&memcg->move_lock, flags);
 	if (memcg != page->mem_cgroup) {
@@ -1759,21 +1721,23 @@ again:
 	/*
 	 * When charge migration first begins, we can have locked and
 	 * unlocked page stat updates happening concurrently.  Track
-	 * the task who has the lock for mem_cgroup_end_page_stat().
+	 * the task who has the lock for unlock_page_memcg().
 	 */
 	memcg->move_lock_task = current;
 	memcg->move_lock_flags = flags;
 
-	return memcg;
+	return;
 }
-EXPORT_SYMBOL(mem_cgroup_begin_page_stat);
+EXPORT_SYMBOL(lock_page_memcg);
 
 /**
- * mem_cgroup_end_page_stat - finish a page state statistics transaction
- * @memcg: the memcg that was accounted against
+ * unlock_page_memcg - unlock a page->mem_cgroup binding
+ * @page: the page
  */
-void mem_cgroup_end_page_stat(struct mem_cgroup *memcg)
+void unlock_page_memcg(struct page *page)
 {
+	struct mem_cgroup *memcg = page->mem_cgroup;
+
 	if (memcg && memcg->move_lock_task == current) {
 		unsigned long flags = memcg->move_lock_flags;
 
@@ -1785,7 +1749,7 @@ void mem_cgroup_end_page_stat(struct mem_cgroup *memcg)
 
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(mem_cgroup_end_page_stat);
+EXPORT_SYMBOL(unlock_page_memcg);
 
 /*
  * size of first charge trial. "32" comes from vmscan.c's magic value.
@@ -4488,7 +4452,7 @@ static int mem_cgroup_move_account(struct page *page,
 	VM_BUG_ON(compound && !PageTransHuge(page));
 
 	/*
-	 * Prevent mem_cgroup_replace_page() from looking at
+	 * Prevent mem_cgroup_migrate() from looking at
 	 * page->mem_cgroup of its source page while we change it.
 	 */
 	ret = -EBUSY;
@@ -4923,9 +4887,9 @@ static void mem_cgroup_move_charge(struct mm_struct *mm)
 
 	lru_add_drain_all();
 	/*
-	 * Signal mem_cgroup_begin_page_stat() to take the memcg's
-	 * move_lock while we're moving its pages to another memcg.
-	 * Then wait for already started RCU-only updates to finish.
+	 * Signal lock_page_memcg() to take the memcg's move_lock
+	 * while we're moving its pages to another memcg. Then wait
+	 * for already started RCU-only updates to finish.
 	 */
 	atomic_inc(&mc.from->moving_account);
 	synchronize_rcu();
@@ -5517,16 +5481,16 @@ void mem_cgroup_uncharge_list(struct list_head *page_list)
 }
 
 /**
- * mem_cgroup_replace_page - migrate a charge to another page
- * @oldpage: currently charged page
- * @newpage: page to transfer the charge to
+ * mem_cgroup_migrate - charge a page's replacement
+ * @oldpage: currently circulating page
+ * @newpage: replacement page
  *
- * Migrate the charge from @oldpage to @newpage.
+ * Charge @newpage as a replacement page for @oldpage. @oldpage will
+ * be uncharged upon free.
  *
  * Both pages must be locked, @newpage->mapping must be set up.
- * Either or both pages might be on the LRU already.
  */
-void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage)
+void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
 {
 	struct mem_cgroup *memcg;
 	unsigned int nr_pages;
@@ -5559,7 +5523,7 @@ void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage)
 		page_counter_charge(&memcg->memsw, nr_pages);
 	css_get_many(&memcg->css, nr_pages);
 
-	commit_charge(newpage, memcg, true);
+	commit_charge(newpage, memcg, false);
 
 	local_irq_disable();
 	mem_cgroup_charge_statistics(memcg, newpage, compound, nr_pages);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index ac595e7a3a95..67c30eb993f0 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -826,8 +826,6 @@ static struct page_state {
 #undef lru
 #undef swapbacked
 #undef head
-#undef tail
-#undef compound
 #undef slab
 #undef reserved
 
diff --git a/mm/memory.c b/mm/memory.c
index 635451abc8f7..0e247642ed5b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1551,8 +1551,29 @@ out:
 int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn)
 {
+	return vm_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(vm_insert_pfn);
+
+/**
+ * vm_insert_pfn_prot - insert single pfn into user vma with specified pgprot
+ * @vma: user vma to map to
+ * @addr: target user address of this page
+ * @pfn: source kernel pfn
+ * @pgprot: pgprot flags for the inserted page
+ *
+ * This is exactly like vm_insert_pfn, except that it allows drivers to
+ * to override pgprot on a per-page basis.
+ *
+ * This only makes sense for IO mappings, and it makes no sense for
+ * cow mappings.  In general, using multiple vmas is preferable;
+ * vm_insert_pfn_prot should only be used if using multiple VMAs is
+ * impractical.
+ */
+int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
+			unsigned long pfn, pgprot_t pgprot)
+{
 	int ret;
-	pgprot_t pgprot = vma->vm_page_prot;
 	/*
 	 * Technically, architectures with pte_special can avoid all these
 	 * restrictions (same for remap_pfn_range).  However we would like
@@ -1574,7 +1595,7 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 
 	return ret;
 }
-EXPORT_SYMBOL(vm_insert_pfn);
+EXPORT_SYMBOL(vm_insert_pfn_prot);
 
 int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 			pfn_t pfn)
@@ -1876,7 +1897,9 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 	unsigned long end = addr + size;
 	int err;
 
-	BUG_ON(addr >= end);
+	if (WARN_ON(addr >= end))
+		return -EINVAL;
+
 	pgd = pgd_offset(mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
@@ -3122,8 +3145,7 @@ static int do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned long address, pte_t *page_table, pmd_t *pmd,
 		unsigned int flags, pte_t orig_pte)
 {
-	pgoff_t pgoff = (((address & PAGE_MASK)
-			- vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
+	pgoff_t pgoff = linear_page_index(vma, address);
 
 	pte_unmap(page_table);
 	/* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */
@@ -3404,8 +3426,18 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (unlikely(pmd_none(*pmd)) &&
 	    unlikely(__pte_alloc(mm, vma, pmd, address)))
 		return VM_FAULT_OOM;
-	/* if an huge pmd materialized from under us just retry later */
-	if (unlikely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd)))
+	/*
+	 * If a huge pmd materialized under us just retry later.  Use
+	 * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd
+	 * didn't become pmd_trans_huge under us and then back to pmd_none, as
+	 * a result of MADV_DONTNEED running immediately after a huge pmd fault
+	 * in a different thread of this mm, in turn leading to a misleading
+	 * pmd_trans_huge() retval.  All we have to ensure is that it is a
+	 * regular pmd that we can walk with pte_offset_map() and we can do that
+	 * through an atomic read in C, which is what pmd_trans_unstable()
+	 * provides.
+	 */
+	if (unlikely(pmd_trans_unstable(pmd) || pmd_devmap(*pmd)))
 		return 0;
 	/*
 	 * A regular pmd is established and it can't morph into a huge pmd
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 4af58a3a8ffa..24ea06393816 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -77,6 +77,9 @@ static struct {
 #define memhp_lock_acquire()      lock_map_acquire(&mem_hotplug.dep_map)
 #define memhp_lock_release()      lock_map_release(&mem_hotplug.dep_map)
 
+bool memhp_auto_online;
+EXPORT_SYMBOL_GPL(memhp_auto_online);
+
 void get_online_mems(void)
 {
 	might_sleep();
@@ -138,7 +141,7 @@ static struct resource *register_memory_resource(u64 start, u64 size)
 	res->name = "System RAM";
 	res->start = start;
 	res->end = start + size - 1;
-	res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 	if (request_resource(&iomem_resource, res) < 0) {
 		pr_debug("System RAM resource %pR cannot be added\n", res);
 		kfree(res);
@@ -509,6 +512,8 @@ int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
 	int start_sec, end_sec;
 	struct vmem_altmap *altmap;
 
+	clear_zone_contiguous(zone);
+
 	/* during initialize mem_map, align hot-added range to section */
 	start_sec = pfn_to_section_nr(phys_start_pfn);
 	end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1);
@@ -521,7 +526,8 @@ int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
 		if (altmap->base_pfn != phys_start_pfn
 				|| vmem_altmap_offset(altmap) > nr_pages) {
 			pr_warn_once("memory add fail, invalid altmap\n");
-			return -EINVAL;
+			err = -EINVAL;
+			goto out;
 		}
 		altmap->alloc = 0;
 	}
@@ -539,7 +545,8 @@ int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
 		err = 0;
 	}
 	vmemmap_populate_print_last();
-
+out:
+	set_zone_contiguous(zone);
 	return err;
 }
 EXPORT_SYMBOL_GPL(__add_pages);
@@ -811,6 +818,8 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 		}
 	}
 
+	clear_zone_contiguous(zone);
+
 	/*
 	 * We can only remove entire sections
 	 */
@@ -826,6 +835,9 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 		if (ret)
 			break;
 	}
+
+	set_zone_contiguous(zone);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(__remove_pages);
@@ -1261,8 +1273,13 @@ int zone_for_memory(int nid, u64 start, u64 size, int zone_default,
 	return zone_default;
 }
 
+static int online_memory_block(struct memory_block *mem, void *arg)
+{
+	return memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
+}
+
 /* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
-int __ref add_memory_resource(int nid, struct resource *res)
+int __ref add_memory_resource(int nid, struct resource *res, bool online)
 {
 	u64 start, size;
 	pg_data_t *pgdat = NULL;
@@ -1322,6 +1339,11 @@ int __ref add_memory_resource(int nid, struct resource *res)
 	/* create new memmap entry */
 	firmware_map_add_hotplug(start, start + size, "System RAM");
 
+	/* online pages if requested */
+	if (online)
+		walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1),
+				  NULL, online_memory_block);
+
 	goto out;
 
 error:
@@ -1345,7 +1367,7 @@ int __ref add_memory(int nid, u64 start, u64 size)
 	if (IS_ERR(res))
 		return PTR_ERR(res);
 
-	ret = add_memory_resource(nid, res);
+	ret = add_memory_resource(nid, res, memhp_auto_online);
 	if (ret < 0)
 		release_memory_resource(res);
 	return ret;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 4c4187c0e1de..8cbc74387df3 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -532,7 +532,7 @@ retry:
 		nid = page_to_nid(page);
 		if (node_isset(nid, *qp->nmask) == !!(flags & MPOL_MF_INVERT))
 			continue;
-		if (PageTail(page) && PageAnon(page)) {
+		if (PageTransCompound(page) && PageAnon(page)) {
 			get_page(page);
 			pte_unmap_unlock(pte, ptl);
 			lock_page(page);
@@ -643,7 +643,9 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end,
 
 	if (flags & MPOL_MF_LAZY) {
 		/* Similar to task_numa_work, skip inaccessible VMAs */
-		if (vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))
+		if (!is_vm_hugetlb_page(vma) &&
+			(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)) &&
+			!(vma->vm_flags & VM_MIXEDMAP))
 			change_prot_numa(vma, start, endvma);
 		return 1;
 	}
diff --git a/mm/mempool.c b/mm/mempool.c
index 004d42b1dfaf..7924f4f58a6d 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -135,8 +135,8 @@ static void *remove_element(mempool_t *pool)
 	void *element = pool->elements[--pool->curr_nr];
 
 	BUG_ON(pool->curr_nr < 0);
-	check_element(pool, element);
 	kasan_unpoison_element(pool, element);
+	check_element(pool, element);
 	return element;
 }
 
diff --git a/mm/migrate.c b/mm/migrate.c
index b1034f9c77e7..568284ec75d4 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -38,6 +38,7 @@
 #include <linux/balloon_compaction.h>
 #include <linux/mmu_notifier.h>
 #include <linux/page_idle.h>
+#include <linux/page_owner.h>
 
 #include <asm/tlbflush.h>
 
@@ -325,7 +326,6 @@ int migrate_page_move_mapping(struct address_space *mapping,
 			return -EAGAIN;
 
 		/* No turning back from here */
-		set_page_memcg(newpage, page_memcg(page));
 		newpage->index = page->index;
 		newpage->mapping = page->mapping;
 		if (PageSwapBacked(page))
@@ -372,7 +372,6 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	 * Now we know that no one else is looking at the page:
 	 * no turning back from here.
 	 */
-	set_page_memcg(newpage, page_memcg(page));
 	newpage->index = page->index;
 	newpage->mapping = page->mapping;
 	if (PageSwapBacked(page))
@@ -457,9 +456,9 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
 		return -EAGAIN;
 	}
 
-	set_page_memcg(newpage, page_memcg(page));
 	newpage->index = page->index;
 	newpage->mapping = page->mapping;
+
 	get_page(newpage);
 
 	radix_tree_replace_slot(pslot, newpage);
@@ -467,6 +466,7 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
 	page_unfreeze_refs(page, expected_count - 1);
 
 	spin_unlock_irq(&mapping->tree_lock);
+
 	return MIGRATEPAGE_SUCCESS;
 }
 
@@ -578,6 +578,10 @@ void migrate_page_copy(struct page *newpage, struct page *page)
 	 */
 	if (PageWriteback(newpage))
 		end_page_writeback(newpage);
+
+	copy_page_owner(page, newpage);
+
+	mem_cgroup_migrate(page, newpage);
 }
 
 /************************************************************
@@ -772,7 +776,6 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 	 * page is freed; but stats require that PageAnon be left as PageAnon.
 	 */
 	if (rc == MIGRATEPAGE_SUCCESS) {
-		set_page_memcg(page, NULL);
 		if (!PageAnon(page))
 			page->mapping = NULL;
 	}
@@ -952,8 +955,10 @@ static ICE_noinline int unmap_and_move(new_page_t get_new_page,
 	}
 
 	rc = __unmap_and_move(page, newpage, force, mode);
-	if (rc == MIGRATEPAGE_SUCCESS)
+	if (rc == MIGRATEPAGE_SUCCESS) {
 		put_new_page = NULL;
+		set_page_owner_migrate_reason(newpage, reason);
+	}
 
 out:
 	if (rc != -EAGAIN) {
@@ -1018,7 +1023,7 @@ out:
 static int unmap_and_move_huge_page(new_page_t get_new_page,
 				free_page_t put_new_page, unsigned long private,
 				struct page *hpage, int force,
-				enum migrate_mode mode)
+				enum migrate_mode mode, int reason)
 {
 	int rc = -EAGAIN;
 	int *result = NULL;
@@ -1076,6 +1081,7 @@ put_anon:
 	if (rc == MIGRATEPAGE_SUCCESS) {
 		hugetlb_cgroup_migrate(hpage, new_hpage);
 		put_new_page = NULL;
+		set_page_owner_migrate_reason(new_hpage, reason);
 	}
 
 	unlock_page(hpage);
@@ -1148,7 +1154,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 			if (PageHuge(page))
 				rc = unmap_and_move_huge_page(get_new_page,
 						put_new_page, private, page,
-						pass > 2, mode);
+						pass > 2, mode, reason);
 			else
 				rc = unmap_and_move(get_new_page, put_new_page,
 						private, page, pass > 2, mode,
@@ -1582,7 +1588,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
 					 (GFP_HIGHUSER_MOVABLE |
 					  __GFP_THISNODE | __GFP_NOMEMALLOC |
 					  __GFP_NORETRY | __GFP_NOWARN) &
-					 ~(__GFP_IO | __GFP_FS), 0);
+					 ~__GFP_RECLAIM, 0);
 
 	return newpage;
 }
@@ -1836,9 +1842,8 @@ fail_putback:
 	}
 
 	mlock_migrate_page(new_page, page);
-	set_page_memcg(new_page, page_memcg(page));
-	set_page_memcg(page, NULL);
 	page_remove_rmap(page, true);
+	set_page_owner_migrate_reason(new_page, MR_NUMA_MISPLACED);
 
 	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
diff --git a/mm/mmap.c b/mm/mmap.c
index 2f2415a7a688..90e3b869a8b9 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2664,12 +2664,29 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	if (!vma || !(vma->vm_flags & VM_SHARED))
 		goto out;
 
-	if (start < vma->vm_start || start + size > vma->vm_end)
+	if (start < vma->vm_start)
 		goto out;
 
-	if (pgoff == linear_page_index(vma, start)) {
-		ret = 0;
-		goto out;
+	if (start + size > vma->vm_end) {
+		struct vm_area_struct *next;
+
+		for (next = vma->vm_next; next; next = next->vm_next) {
+			/* hole between vmas ? */
+			if (next->vm_start != next->vm_prev->vm_end)
+				goto out;
+
+			if (next->vm_file != vma->vm_file)
+				goto out;
+
+			if (next->vm_flags != vma->vm_flags)
+				goto out;
+
+			if (start + size <= next->vm_end)
+				break;
+		}
+
+		if (!next)
+			goto out;
 	}
 
 	prot |= vma->vm_flags & VM_READ ? PROT_READ : 0;
@@ -2679,9 +2696,16 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	flags &= MAP_NONBLOCK;
 	flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE;
 	if (vma->vm_flags & VM_LOCKED) {
+		struct vm_area_struct *tmp;
 		flags |= MAP_LOCKED;
+
 		/* drop PG_Mlocked flag for over-mapped range */
-		munlock_vma_pages_range(vma, start, start + size);
+		for (tmp = vma; tmp->vm_start >= start + size;
+				tmp = tmp->vm_next) {
+			munlock_vma_pages_range(tmp,
+					max(tmp->vm_start, start),
+					min(tmp->vm_end, start + size));
+		}
 	}
 
 	file = get_file(vma->vm_file);
@@ -3042,11 +3066,16 @@ static int special_mapping_fault(struct vm_area_struct *vma,
 	pgoff_t pgoff;
 	struct page **pages;
 
-	if (vma->vm_ops == &legacy_special_mapping_vmops)
+	if (vma->vm_ops == &legacy_special_mapping_vmops) {
 		pages = vma->vm_private_data;
-	else
-		pages = ((struct vm_special_mapping *)vma->vm_private_data)->
-			pages;
+	} else {
+		struct vm_special_mapping *sm = vma->vm_private_data;
+
+		if (sm->fault)
+			return sm->fault(sm, vma, vmf);
+
+		pages = sm->pages;
+	}
 
 	for (pgoff = vmf->pgoff; pgoff && *pages; ++pages)
 		pgoff--;
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 8eb7bb40dc40..f7cb3d4d9c2e 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -160,9 +160,11 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		}
 
 		if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
-			if (next - addr != HPAGE_PMD_SIZE)
+			if (next - addr != HPAGE_PMD_SIZE) {
 				split_huge_pmd(vma, pmd, addr);
-			else {
+				if (pmd_none(*pmd))
+					continue;
+			} else {
 				int nr_ptes = change_huge_pmd(vma, pmd, addr,
 						newprot, prot_numa);
 
diff --git a/mm/mremap.c b/mm/mremap.c
index d77946a997f7..8eeba02fc991 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -210,6 +210,8 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 				}
 			}
 			split_huge_pmd(vma, old_pmd, old_addr);
+			if (pmd_none(*old_pmd))
+				continue;
 			VM_BUG_ON(pmd_trans_huge(*old_pmd));
 		}
 		if (pmd_none(*new_pmd) && __pte_alloc(new_vma->vm_mm, new_vma,
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index dc490c06941b..e97a05d9621f 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -386,10 +386,11 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
 static void dump_header(struct oom_control *oc, struct task_struct *p,
 			struct mem_cgroup *memcg)
 {
-	pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, "
-		"oom_score_adj=%hd\n",
-		current->comm, oc->gfp_mask, oc->order,
+	pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), order=%d, "
+			"oom_score_adj=%hd\n",
+		current->comm, oc->gfp_mask, &oc->gfp_mask, oc->order,
 		current->signal->oom_score_adj);
+
 	cpuset_print_current_mems_allowed();
 	dump_stack();
 	if (memcg)
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 6fe7d15bd1f7..11ff8f758631 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1169,6 +1169,7 @@ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc,
 	unsigned long balanced_dirty_ratelimit;
 	unsigned long step;
 	unsigned long x;
+	unsigned long shift;
 
 	/*
 	 * The dirty rate will match the writeout rate in long term, except
@@ -1293,11 +1294,11 @@ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc,
 	 * rate itself is constantly fluctuating. So decrease the track speed
 	 * when it gets close to the target. Helps eliminate pointless tremors.
 	 */
-	step >>= dirty_ratelimit / (2 * step + 1);
-	/*
-	 * Limit the tracking speed to avoid overshooting.
-	 */
-	step = (step + 7) / 8;
+	shift = dirty_ratelimit / (2 * step + 1);
+	if (shift < BITS_PER_LONG)
+		step = DIV_ROUND_UP(step >> shift, 8);
+	else
+		step = 0;
 
 	if (dirty_ratelimit < balanced_dirty_ratelimit)
 		dirty_ratelimit += step;
@@ -2409,12 +2410,11 @@ int __set_page_dirty_no_writeback(struct page *page)
 /*
  * Helper function for set_page_dirty family.
  *
- * Caller must hold mem_cgroup_begin_page_stat().
+ * Caller must hold lock_page_memcg().
  *
  * NOTE: This relies on being atomic wrt interrupts.
  */
-void account_page_dirtied(struct page *page, struct address_space *mapping,
-			  struct mem_cgroup *memcg)
+void account_page_dirtied(struct page *page, struct address_space *mapping)
 {
 	struct inode *inode = mapping->host;
 
@@ -2426,7 +2426,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping,
 		inode_attach_wb(inode, page);
 		wb = inode_to_wb(inode);
 
-		mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_DIRTY);
+		mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_DIRTY);
 		__inc_zone_page_state(page, NR_FILE_DIRTY);
 		__inc_zone_page_state(page, NR_DIRTIED);
 		__inc_wb_stat(wb, WB_RECLAIMABLE);
@@ -2441,13 +2441,13 @@ EXPORT_SYMBOL(account_page_dirtied);
 /*
  * Helper function for deaccounting dirty page without writeback.
  *
- * Caller must hold mem_cgroup_begin_page_stat().
+ * Caller must hold lock_page_memcg().
  */
 void account_page_cleaned(struct page *page, struct address_space *mapping,
-			  struct mem_cgroup *memcg, struct bdi_writeback *wb)
+			  struct bdi_writeback *wb)
 {
 	if (mapping_cap_account_dirty(mapping)) {
-		mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_DIRTY);
+		mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY);
 		dec_zone_page_state(page, NR_FILE_DIRTY);
 		dec_wb_stat(wb, WB_RECLAIMABLE);
 		task_io_account_cancelled_write(PAGE_CACHE_SIZE);
@@ -2468,26 +2468,24 @@ void account_page_cleaned(struct page *page, struct address_space *mapping,
  */
 int __set_page_dirty_nobuffers(struct page *page)
 {
-	struct mem_cgroup *memcg;
-
-	memcg = mem_cgroup_begin_page_stat(page);
+	lock_page_memcg(page);
 	if (!TestSetPageDirty(page)) {
 		struct address_space *mapping = page_mapping(page);
 		unsigned long flags;
 
 		if (!mapping) {
-			mem_cgroup_end_page_stat(memcg);
+			unlock_page_memcg(page);
 			return 1;
 		}
 
 		spin_lock_irqsave(&mapping->tree_lock, flags);
 		BUG_ON(page_mapping(page) != mapping);
 		WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
-		account_page_dirtied(page, mapping, memcg);
+		account_page_dirtied(page, mapping);
 		radix_tree_tag_set(&mapping->page_tree, page_index(page),
 				   PAGECACHE_TAG_DIRTY);
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
-		mem_cgroup_end_page_stat(memcg);
+		unlock_page_memcg(page);
 
 		if (mapping->host) {
 			/* !PageAnon && !swapper_space */
@@ -2495,7 +2493,7 @@ int __set_page_dirty_nobuffers(struct page *page)
 		}
 		return 1;
 	}
-	mem_cgroup_end_page_stat(memcg);
+	unlock_page_memcg(page);
 	return 0;
 }
 EXPORT_SYMBOL(__set_page_dirty_nobuffers);
@@ -2625,17 +2623,16 @@ void cancel_dirty_page(struct page *page)
 	if (mapping_cap_account_dirty(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
-		struct mem_cgroup *memcg;
 		bool locked;
 
-		memcg = mem_cgroup_begin_page_stat(page);
+		lock_page_memcg(page);
 		wb = unlocked_inode_to_wb_begin(inode, &locked);
 
 		if (TestClearPageDirty(page))
-			account_page_cleaned(page, mapping, memcg, wb);
+			account_page_cleaned(page, mapping, wb);
 
 		unlocked_inode_to_wb_end(inode, locked);
-		mem_cgroup_end_page_stat(memcg);
+		unlock_page_memcg(page);
 	} else {
 		ClearPageDirty(page);
 	}
@@ -2666,7 +2663,6 @@ int clear_page_dirty_for_io(struct page *page)
 	if (mapping && mapping_cap_account_dirty(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
-		struct mem_cgroup *memcg;
 		bool locked;
 
 		/*
@@ -2704,16 +2700,14 @@ int clear_page_dirty_for_io(struct page *page)
 		 * always locked coming in here, so we get the desired
 		 * exclusion.
 		 */
-		memcg = mem_cgroup_begin_page_stat(page);
 		wb = unlocked_inode_to_wb_begin(inode, &locked);
 		if (TestClearPageDirty(page)) {
-			mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_DIRTY);
+			mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY);
 			dec_zone_page_state(page, NR_FILE_DIRTY);
 			dec_wb_stat(wb, WB_RECLAIMABLE);
 			ret = 1;
 		}
 		unlocked_inode_to_wb_end(inode, locked);
-		mem_cgroup_end_page_stat(memcg);
 		return ret;
 	}
 	return TestClearPageDirty(page);
@@ -2723,10 +2717,9 @@ EXPORT_SYMBOL(clear_page_dirty_for_io);
 int test_clear_page_writeback(struct page *page)
 {
 	struct address_space *mapping = page_mapping(page);
-	struct mem_cgroup *memcg;
 	int ret;
 
-	memcg = mem_cgroup_begin_page_stat(page);
+	lock_page_memcg(page);
 	if (mapping) {
 		struct inode *inode = mapping->host;
 		struct backing_dev_info *bdi = inode_to_bdi(inode);
@@ -2750,21 +2743,20 @@ int test_clear_page_writeback(struct page *page)
 		ret = TestClearPageWriteback(page);
 	}
 	if (ret) {
-		mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_WRITEBACK);
+		mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
 		dec_zone_page_state(page, NR_WRITEBACK);
 		inc_zone_page_state(page, NR_WRITTEN);
 	}
-	mem_cgroup_end_page_stat(memcg);
+	unlock_page_memcg(page);
 	return ret;
 }
 
 int __test_set_page_writeback(struct page *page, bool keep_write)
 {
 	struct address_space *mapping = page_mapping(page);
-	struct mem_cgroup *memcg;
 	int ret;
 
-	memcg = mem_cgroup_begin_page_stat(page);
+	lock_page_memcg(page);
 	if (mapping) {
 		struct inode *inode = mapping->host;
 		struct backing_dev_info *bdi = inode_to_bdi(inode);
@@ -2792,10 +2784,10 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 		ret = TestSetPageWriteback(page);
 	}
 	if (!ret) {
-		mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_WRITEBACK);
+		mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);
 		inc_zone_page_state(page, NR_WRITEBACK);
 	}
-	mem_cgroup_end_page_stat(memcg);
+	unlock_page_memcg(page);
 	return ret;
 
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 838ca8bb64f7..c46b75d14b6f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -223,6 +223,19 @@ static char * const zone_names[MAX_NR_ZONES] = {
 #endif
 };
 
+char * const migratetype_names[MIGRATE_TYPES] = {
+	"Unmovable",
+	"Movable",
+	"Reclaimable",
+	"HighAtomic",
+#ifdef CONFIG_CMA
+	"CMA",
+#endif
+#ifdef CONFIG_MEMORY_ISOLATION
+	"Isolate",
+#endif
+};
+
 compound_page_dtor * const compound_page_dtors[] = {
 	NULL,
 	free_compound_page,
@@ -247,6 +260,7 @@ static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
 static unsigned long __initdata required_kernelcore;
 static unsigned long __initdata required_movablecore;
 static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
+static bool mirrored_kernelcore;
 
 /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
 int movable_zone;
@@ -416,7 +430,7 @@ static void bad_page(struct page *page, const char *reason,
 			goto out;
 		}
 		if (nr_unshown) {
-			printk(KERN_ALERT
+			pr_alert(
 			      "BUG: Bad page state: %lu messages suppressed\n",
 				nr_unshown);
 			nr_unshown = 0;
@@ -426,9 +440,14 @@ static void bad_page(struct page *page, const char *reason,
 	if (nr_shown++ == 0)
 		resume = jiffies + 60 * HZ;
 
-	printk(KERN_ALERT "BUG: Bad page state in process %s  pfn:%05lx\n",
+	pr_alert("BUG: Bad page state in process %s  pfn:%05lx\n",
 		current->comm, page_to_pfn(page));
-	dump_page_badflags(page, reason, bad_flags);
+	__dump_page(page, reason);
+	bad_flags &= page->flags;
+	if (bad_flags)
+		pr_alert("bad because of flags: %#lx(%pGp)\n",
+						bad_flags, &bad_flags);
+	dump_page_owner(page);
 
 	print_modules();
 	dump_stack();
@@ -477,7 +496,8 @@ void prep_compound_page(struct page *page, unsigned int order)
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
 unsigned int _debug_guardpage_minorder;
-bool _debug_pagealloc_enabled __read_mostly;
+bool _debug_pagealloc_enabled __read_mostly
+			= IS_ENABLED(CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT);
 bool _debug_guardpage_enabled __read_mostly;
 
 static int __init early_debug_pagealloc(char *buf)
@@ -488,6 +508,9 @@ static int __init early_debug_pagealloc(char *buf)
 	if (strcmp(buf, "on") == 0)
 		_debug_pagealloc_enabled = true;
 
+	if (strcmp(buf, "off") == 0)
+		_debug_pagealloc_enabled = false;
+
 	return 0;
 }
 early_param("debug_pagealloc", early_debug_pagealloc);
@@ -1002,6 +1025,7 @@ static bool free_pages_prepare(struct page *page, unsigned int order)
 					   PAGE_SIZE << order);
 	}
 	arch_free_page(page, order);
+	kernel_poison_pages(page, 1 << order, 0);
 	kernel_map_pages(page, 1 << order, 0);
 
 	return true;
@@ -1104,6 +1128,75 @@ void __init __free_pages_bootmem(struct page *page, unsigned long pfn,
 	return __free_pages_boot_core(page, pfn, order);
 }
 
+/*
+ * Check that the whole (or subset of) a pageblock given by the interval of
+ * [start_pfn, end_pfn) is valid and within the same zone, before scanning it
+ * with the migration of free compaction scanner. The scanners then need to
+ * use only pfn_valid_within() check for arches that allow holes within
+ * pageblocks.
+ *
+ * Return struct page pointer of start_pfn, or NULL if checks were not passed.
+ *
+ * It's possible on some configurations to have a setup like node0 node1 node0
+ * i.e. it's possible that all pages within a zones range of pages do not
+ * belong to a single zone. We assume that a border between node0 and node1
+ * can occur within a single pageblock, but not a node0 node1 node0
+ * interleaving within a single pageblock. It is therefore sufficient to check
+ * the first and last page of a pageblock and avoid checking each individual
+ * page in a pageblock.
+ */
+struct page *__pageblock_pfn_to_page(unsigned long start_pfn,
+				     unsigned long end_pfn, struct zone *zone)
+{
+	struct page *start_page;
+	struct page *end_page;
+
+	/* end_pfn is one past the range we are checking */
+	end_pfn--;
+
+	if (!pfn_valid(start_pfn) || !pfn_valid(end_pfn))
+		return NULL;
+
+	start_page = pfn_to_page(start_pfn);
+
+	if (page_zone(start_page) != zone)
+		return NULL;
+
+	end_page = pfn_to_page(end_pfn);
+
+	/* This gives a shorter code than deriving page_zone(end_page) */
+	if (page_zone_id(start_page) != page_zone_id(end_page))
+		return NULL;
+
+	return start_page;
+}
+
+void set_zone_contiguous(struct zone *zone)
+{
+	unsigned long block_start_pfn = zone->zone_start_pfn;
+	unsigned long block_end_pfn;
+
+	block_end_pfn = ALIGN(block_start_pfn + 1, pageblock_nr_pages);
+	for (; block_start_pfn < zone_end_pfn(zone);
+			block_start_pfn = block_end_pfn,
+			 block_end_pfn += pageblock_nr_pages) {
+
+		block_end_pfn = min(block_end_pfn, zone_end_pfn(zone));
+
+		if (!__pageblock_pfn_to_page(block_start_pfn,
+					     block_end_pfn, zone))
+			return;
+	}
+
+	/* We confirm that there is no hole */
+	zone->contiguous = true;
+}
+
+void clear_zone_contiguous(struct zone *zone)
+{
+	zone->contiguous = false;
+}
+
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 static void __init deferred_free_range(struct page *page,
 					unsigned long pfn, int nr_pages)
@@ -1254,9 +1347,13 @@ free_range:
 	pgdat_init_report_one_done();
 	return 0;
 }
+#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 
 void __init page_alloc_init_late(void)
 {
+	struct zone *zone;
+
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 	int nid;
 
 	/* There will be num_node_state(N_MEMORY) threads */
@@ -1270,8 +1367,11 @@ void __init page_alloc_init_late(void)
 
 	/* Reinit limits that are based on free pages after the kernel is up */
 	files_maxfiles_init();
+#endif
+
+	for_each_populated_zone(zone)
+		set_zone_contiguous(zone);
 }
-#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 
 #ifdef CONFIG_CMA
 /* Free whole pageblock and set its migration type to MIGRATE_CMA. */
@@ -1381,15 +1481,24 @@ static inline int check_new_page(struct page *page)
 	return 0;
 }
 
+static inline bool free_pages_prezeroed(bool poisoned)
+{
+	return IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) &&
+		page_poisoning_enabled() && poisoned;
+}
+
 static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
 								int alloc_flags)
 {
 	int i;
+	bool poisoned = true;
 
 	for (i = 0; i < (1 << order); i++) {
 		struct page *p = page + i;
 		if (unlikely(check_new_page(p)))
 			return 1;
+		if (poisoned)
+			poisoned &= page_is_poisoned(p);
 	}
 
 	set_page_private(page, 0);
@@ -1397,9 +1506,10 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
 
 	arch_alloc_page(page, order);
 	kernel_map_pages(page, 1 << order, 1);
+	kernel_poison_pages(page, 1 << order, 1);
 	kasan_alloc_pages(page, order);
 
-	if (gfp_flags & __GFP_ZERO)
+	if (!free_pages_prezeroed(poisoned) && (gfp_flags & __GFP_ZERO))
 		for (i = 0; i < (1 << order); i++)
 			clear_highpage(page + i);
 
@@ -2690,9 +2800,8 @@ void warn_alloc_failed(gfp_t gfp_mask, unsigned int order, const char *fmt, ...)
 		va_end(args);
 	}
 
-	pr_warn("%s: page allocation failure: order:%u, mode:0x%x\n",
-		current->comm, order, gfp_mask);
-
+	pr_warn("%s: page allocation failure: order:%u, mode:%#x(%pGg)\n",
+		current->comm, order, gfp_mask, &gfp_mask);
 	dump_stack();
 	if (!should_suppress_show_mem())
 		show_mem(filter);
@@ -4491,6 +4600,9 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 	pg_data_t *pgdat = NODE_DATA(nid);
 	unsigned long pfn;
 	unsigned long nr_initialised = 0;
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+	struct memblock_region *r = NULL, *tmp;
+#endif
 
 	if (highest_memmap_pfn < end_pfn - 1)
 		highest_memmap_pfn = end_pfn - 1;
@@ -4504,20 +4616,51 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
 		/*
-		 * There can be holes in boot-time mem_map[]s
-		 * handed to this function.  They do not
-		 * exist on hotplugged memory.
+		 * There can be holes in boot-time mem_map[]s handed to this
+		 * function.  They do not exist on hotplugged memory.
 		 */
-		if (context == MEMMAP_EARLY) {
-			if (!early_pfn_valid(pfn))
+		if (context != MEMMAP_EARLY)
+			goto not_early;
+
+		if (!early_pfn_valid(pfn))
+			continue;
+		if (!early_pfn_in_nid(pfn, nid))
+			continue;
+		if (!update_defer_init(pgdat, pfn, end_pfn, &nr_initialised))
+			break;
+
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+		/*
+		 * If not mirrored_kernelcore and ZONE_MOVABLE exists, range
+		 * from zone_movable_pfn[nid] to end of each node should be
+		 * ZONE_MOVABLE not ZONE_NORMAL. skip it.
+		 */
+		if (!mirrored_kernelcore && zone_movable_pfn[nid])
+			if (zone == ZONE_NORMAL && pfn >= zone_movable_pfn[nid])
 				continue;
-			if (!early_pfn_in_nid(pfn, nid))
+
+		/*
+		 * Check given memblock attribute by firmware which can affect
+		 * kernel memory layout.  If zone==ZONE_MOVABLE but memory is
+		 * mirrored, it's an overlapped memmap init. skip it.
+		 */
+		if (mirrored_kernelcore && zone == ZONE_MOVABLE) {
+			if (!r || pfn >= memblock_region_memory_end_pfn(r)) {
+				for_each_memblock(memory, tmp)
+					if (pfn < memblock_region_memory_end_pfn(tmp))
+						break;
+				r = tmp;
+			}
+			if (pfn >= memblock_region_memory_base_pfn(r) &&
+			    memblock_is_mirror(r)) {
+				/* already initialized as NORMAL */
+				pfn = memblock_region_memory_end_pfn(r);
 				continue;
-			if (!update_defer_init(pgdat, pfn, end_pfn,
-						&nr_initialised))
-				break;
+			}
 		}
+#endif
 
+not_early:
 		/*
 		 * Mark the block movable so that blocks are reserved for
 		 * movable at startup. This will force kernel allocations
@@ -4934,11 +5077,6 @@ static void __meminit adjust_zone_range_for_zone_movable(int nid,
 			*zone_end_pfn = min(node_end_pfn,
 				arch_zone_highest_possible_pfn[movable_zone]);
 
-		/* Adjust for ZONE_MOVABLE starting within this range */
-		} else if (*zone_start_pfn < zone_movable_pfn[nid] &&
-				*zone_end_pfn > zone_movable_pfn[nid]) {
-			*zone_end_pfn = zone_movable_pfn[nid];
-
 		/* Check if this whole range is within ZONE_MOVABLE */
 		} else if (*zone_start_pfn >= zone_movable_pfn[nid])
 			*zone_start_pfn = *zone_end_pfn;
@@ -4953,31 +5091,31 @@ static unsigned long __meminit zone_spanned_pages_in_node(int nid,
 					unsigned long zone_type,
 					unsigned long node_start_pfn,
 					unsigned long node_end_pfn,
+					unsigned long *zone_start_pfn,
+					unsigned long *zone_end_pfn,
 					unsigned long *ignored)
 {
-	unsigned long zone_start_pfn, zone_end_pfn;
-
 	/* When hotadd a new node from cpu_up(), the node should be empty */
 	if (!node_start_pfn && !node_end_pfn)
 		return 0;
 
 	/* Get the start and end of the zone */
-	zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
-	zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
+	*zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
+	*zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
 	adjust_zone_range_for_zone_movable(nid, zone_type,
 				node_start_pfn, node_end_pfn,
-				&zone_start_pfn, &zone_end_pfn);
+				zone_start_pfn, zone_end_pfn);
 
 	/* Check that this node has pages within the zone's required range */
-	if (zone_end_pfn < node_start_pfn || zone_start_pfn > node_end_pfn)
+	if (*zone_end_pfn < node_start_pfn || *zone_start_pfn > node_end_pfn)
 		return 0;
 
 	/* Move the zone boundaries inside the node if necessary */
-	zone_end_pfn = min(zone_end_pfn, node_end_pfn);
-	zone_start_pfn = max(zone_start_pfn, node_start_pfn);
+	*zone_end_pfn = min(*zone_end_pfn, node_end_pfn);
+	*zone_start_pfn = max(*zone_start_pfn, node_start_pfn);
 
 	/* Return the spanned pages */
-	return zone_end_pfn - zone_start_pfn;
+	return *zone_end_pfn - *zone_start_pfn;
 }
 
 /*
@@ -5023,6 +5161,7 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid,
 	unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type];
 	unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
 	unsigned long zone_start_pfn, zone_end_pfn;
+	unsigned long nr_absent;
 
 	/* When hotadd a new node from cpu_up(), the node should be empty */
 	if (!node_start_pfn && !node_end_pfn)
@@ -5034,7 +5173,39 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid,
 	adjust_zone_range_for_zone_movable(nid, zone_type,
 			node_start_pfn, node_end_pfn,
 			&zone_start_pfn, &zone_end_pfn);
-	return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn);
+	nr_absent = __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn);
+
+	/*
+	 * ZONE_MOVABLE handling.
+	 * Treat pages to be ZONE_MOVABLE in ZONE_NORMAL as absent pages
+	 * and vice versa.
+	 */
+	if (zone_movable_pfn[nid]) {
+		if (mirrored_kernelcore) {
+			unsigned long start_pfn, end_pfn;
+			struct memblock_region *r;
+
+			for_each_memblock(memory, r) {
+				start_pfn = clamp(memblock_region_memory_base_pfn(r),
+						  zone_start_pfn, zone_end_pfn);
+				end_pfn = clamp(memblock_region_memory_end_pfn(r),
+						zone_start_pfn, zone_end_pfn);
+
+				if (zone_type == ZONE_MOVABLE &&
+				    memblock_is_mirror(r))
+					nr_absent += end_pfn - start_pfn;
+
+				if (zone_type == ZONE_NORMAL &&
+				    !memblock_is_mirror(r))
+					nr_absent += end_pfn - start_pfn;
+			}
+		} else {
+			if (zone_type == ZONE_NORMAL)
+				nr_absent += node_end_pfn - zone_movable_pfn[nid];
+		}
+	}
+
+	return nr_absent;
 }
 
 #else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
@@ -5042,8 +5213,18 @@ static inline unsigned long __meminit zone_spanned_pages_in_node(int nid,
 					unsigned long zone_type,
 					unsigned long node_start_pfn,
 					unsigned long node_end_pfn,
+					unsigned long *zone_start_pfn,
+					unsigned long *zone_end_pfn,
 					unsigned long *zones_size)
 {
+	unsigned int zone;
+
+	*zone_start_pfn = node_start_pfn;
+	for (zone = 0; zone < zone_type; zone++)
+		*zone_start_pfn += zones_size[zone];
+
+	*zone_end_pfn = *zone_start_pfn + zones_size[zone_type];
+
 	return zones_size[zone_type];
 }
 
@@ -5072,15 +5253,22 @@ static void __meminit calculate_node_totalpages(struct pglist_data *pgdat,
 
 	for (i = 0; i < MAX_NR_ZONES; i++) {
 		struct zone *zone = pgdat->node_zones + i;
+		unsigned long zone_start_pfn, zone_end_pfn;
 		unsigned long size, real_size;
 
 		size = zone_spanned_pages_in_node(pgdat->node_id, i,
 						  node_start_pfn,
 						  node_end_pfn,
+						  &zone_start_pfn,
+						  &zone_end_pfn,
 						  zones_size);
 		real_size = size - zone_absent_pages_in_node(pgdat->node_id, i,
 						  node_start_pfn, node_end_pfn,
 						  zholes_size);
+		if (size)
+			zone->zone_start_pfn = zone_start_pfn;
+		else
+			zone->zone_start_pfn = 0;
 		zone->spanned_pages = size;
 		zone->present_pages = real_size;
 
@@ -5201,7 +5389,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 {
 	enum zone_type j;
 	int nid = pgdat->node_id;
-	unsigned long zone_start_pfn = pgdat->node_start_pfn;
 	int ret;
 
 	pgdat_resize_init(pgdat);
@@ -5222,6 +5409,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 	for (j = 0; j < MAX_NR_ZONES; j++) {
 		struct zone *zone = pgdat->node_zones + j;
 		unsigned long size, realsize, freesize, memmap_pages;
+		unsigned long zone_start_pfn = zone->zone_start_pfn;
 
 		size = zone->spanned_pages;
 		realsize = freesize = zone->present_pages;
@@ -5290,7 +5478,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 		ret = init_currently_empty_zone(zone, zone_start_pfn, size);
 		BUG_ON(ret);
 		memmap_init(size, nid, j, zone_start_pfn);
-		zone_start_pfn += size;
 	}
 }
 
@@ -5358,6 +5545,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 	pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid,
 		(u64)start_pfn << PAGE_SHIFT,
 		end_pfn ? ((u64)end_pfn << PAGE_SHIFT) - 1 : 0);
+#else
+	start_pfn = node_start_pfn;
 #endif
 	calculate_node_totalpages(pgdat, start_pfn, end_pfn,
 				  zones_size, zholes_size);
@@ -5529,6 +5718,36 @@ static void __init find_zone_movable_pfns_for_nodes(void)
 	}
 
 	/*
+	 * If kernelcore=mirror is specified, ignore movablecore option
+	 */
+	if (mirrored_kernelcore) {
+		bool mem_below_4gb_not_mirrored = false;
+
+		for_each_memblock(memory, r) {
+			if (memblock_is_mirror(r))
+				continue;
+
+			nid = r->nid;
+
+			usable_startpfn = memblock_region_memory_base_pfn(r);
+
+			if (usable_startpfn < 0x100000) {
+				mem_below_4gb_not_mirrored = true;
+				continue;
+			}
+
+			zone_movable_pfn[nid] = zone_movable_pfn[nid] ?
+				min(usable_startpfn, zone_movable_pfn[nid]) :
+				usable_startpfn;
+		}
+
+		if (mem_below_4gb_not_mirrored)
+			pr_warn("This configuration results in unmirrored kernel memory.");
+
+		goto out2;
+	}
+
+	/*
 	 * If movablecore=nn[KMG] was specified, calculate what size of
 	 * kernelcore that corresponds so that memory usable for
 	 * any allocation type is evenly spread. If both kernelcore
@@ -5788,6 +6007,12 @@ static int __init cmdline_parse_core(char *p, unsigned long *core)
  */
 static int __init cmdline_parse_kernelcore(char *p)
 {
+	/* parse kernelcore=mirror */
+	if (parse_option_str(p, "mirror")) {
+		mirrored_kernelcore = true;
+		return 0;
+	}
+
 	return cmdline_parse_core(p, &required_kernelcore);
 }
 
diff --git a/mm/page_ext.c b/mm/page_ext.c
index 292ca7b8debd..2d864e64f7fe 100644
--- a/mm/page_ext.c
+++ b/mm/page_ext.c
@@ -106,12 +106,15 @@ struct page_ext *lookup_page_ext(struct page *page)
 	struct page_ext *base;
 
 	base = NODE_DATA(page_to_nid(page))->node_page_ext;
-#ifdef CONFIG_DEBUG_VM
+#if defined(CONFIG_DEBUG_VM) || defined(CONFIG_PAGE_POISONING)
 	/*
 	 * The sanity checks the page allocator does upon freeing a
 	 * page can reach here before the page_ext arrays are
 	 * allocated when feeding a range of pages to the allocator
 	 * for the first time during bootup or memory hotplug.
+	 *
+	 * This check is also necessary for ensuring page poisoning
+	 * works as expected when enabled
 	 */
 	if (unlikely(!base))
 		return NULL;
@@ -180,12 +183,15 @@ struct page_ext *lookup_page_ext(struct page *page)
 {
 	unsigned long pfn = page_to_pfn(page);
 	struct mem_section *section = __pfn_to_section(pfn);
-#ifdef CONFIG_DEBUG_VM
+#if defined(CONFIG_DEBUG_VM) || defined(CONFIG_PAGE_POISONING)
 	/*
 	 * The sanity checks the page allocator does upon freeing a
 	 * page can reach here before the page_ext arrays are
 	 * allocated when feeding a range of pages to the allocator
 	 * for the first time during bootup or memory hotplug.
+	 *
+	 * This check is also necessary for ensuring page poisoning
+	 * works as expected when enabled
 	 */
 	if (!section->page_ext)
 		return NULL;
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 983c3a10fa07..44ad1f00c4e1 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -5,10 +5,12 @@
 #include <linux/bootmem.h>
 #include <linux/stacktrace.h>
 #include <linux/page_owner.h>
+#include <linux/jump_label.h>
+#include <linux/migrate.h>
 #include "internal.h"
 
 static bool page_owner_disabled = true;
-bool page_owner_inited __read_mostly;
+DEFINE_STATIC_KEY_FALSE(page_owner_inited);
 
 static void init_early_allocated_pages(void);
 
@@ -37,7 +39,7 @@ static void init_page_owner(void)
 	if (page_owner_disabled)
 		return;
 
-	page_owner_inited = true;
+	static_branch_enable(&page_owner_inited);
 	init_early_allocated_pages();
 }
 
@@ -72,10 +74,18 @@ void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask)
 	page_ext->order = order;
 	page_ext->gfp_mask = gfp_mask;
 	page_ext->nr_entries = trace.nr_entries;
+	page_ext->last_migrate_reason = -1;
 
 	__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
 }
 
+void __set_page_owner_migrate_reason(struct page *page, int reason)
+{
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	page_ext->last_migrate_reason = reason;
+}
+
 gfp_t __get_page_owner_gfp(struct page *page)
 {
 	struct page_ext *page_ext = lookup_page_ext(page);
@@ -83,6 +93,31 @@ gfp_t __get_page_owner_gfp(struct page *page)
 	return page_ext->gfp_mask;
 }
 
+void __copy_page_owner(struct page *oldpage, struct page *newpage)
+{
+	struct page_ext *old_ext = lookup_page_ext(oldpage);
+	struct page_ext *new_ext = lookup_page_ext(newpage);
+	int i;
+
+	new_ext->order = old_ext->order;
+	new_ext->gfp_mask = old_ext->gfp_mask;
+	new_ext->nr_entries = old_ext->nr_entries;
+
+	for (i = 0; i < ARRAY_SIZE(new_ext->trace_entries); i++)
+		new_ext->trace_entries[i] = old_ext->trace_entries[i];
+
+	/*
+	 * We don't clear the bit on the oldpage as it's going to be freed
+	 * after migration. Until then, the info can be useful in case of
+	 * a bug, and the overal stats will be off a bit only temporarily.
+	 * Also, migrate_misplaced_transhuge_page() can still fail the
+	 * migration and then we want the oldpage to retain the info. But
+	 * in that case we also don't need to explicitly clear the info from
+	 * the new page, which will be freed.
+	 */
+	__set_bit(PAGE_EXT_OWNER, &new_ext->flags);
+}
+
 static ssize_t
 print_page_owner(char __user *buf, size_t count, unsigned long pfn,
 		struct page *page, struct page_ext *page_ext)
@@ -100,8 +135,9 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn,
 		return -ENOMEM;
 
 	ret = snprintf(kbuf, count,
-			"Page allocated via order %u, mask 0x%x\n",
-			page_ext->order, page_ext->gfp_mask);
+			"Page allocated via order %u, mask %#x(%pGg)\n",
+			page_ext->order, page_ext->gfp_mask,
+			&page_ext->gfp_mask);
 
 	if (ret >= count)
 		goto err;
@@ -110,23 +146,12 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn,
 	pageblock_mt = get_pfnblock_migratetype(page, pfn);
 	page_mt  = gfpflags_to_migratetype(page_ext->gfp_mask);
 	ret += snprintf(kbuf + ret, count - ret,
-			"PFN %lu Block %lu type %d %s Flags %s%s%s%s%s%s%s%s%s%s%s%s\n",
+			"PFN %lu type %s Block %lu type %s Flags %#lx(%pGp)\n",
 			pfn,
+			migratetype_names[page_mt],
 			pfn >> pageblock_order,
-			pageblock_mt,
-			pageblock_mt != page_mt ? "Fallback" : "        ",
-			PageLocked(page)	? "K" : " ",
-			PageError(page)		? "E" : " ",
-			PageReferenced(page)	? "R" : " ",
-			PageUptodate(page)	? "U" : " ",
-			PageDirty(page)		? "D" : " ",
-			PageLRU(page)		? "L" : " ",
-			PageActive(page)	? "A" : " ",
-			PageSlab(page)		? "S" : " ",
-			PageWriteback(page)	? "W" : " ",
-			PageCompound(page)	? "C" : " ",
-			PageSwapCache(page)	? "B" : " ",
-			PageMappedToDisk(page)	? "M" : " ");
+			migratetype_names[pageblock_mt],
+			page->flags, &page->flags);
 
 	if (ret >= count)
 		goto err;
@@ -135,6 +160,14 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn,
 	if (ret >= count)
 		goto err;
 
+	if (page_ext->last_migrate_reason != -1) {
+		ret += snprintf(kbuf + ret, count - ret,
+			"Page has been migrated, last migrate reason: %s\n",
+			migrate_reason_names[page_ext->last_migrate_reason]);
+		if (ret >= count)
+			goto err;
+	}
+
 	ret += snprintf(kbuf + ret, count - ret, "\n");
 	if (ret >= count)
 		goto err;
@@ -150,6 +183,31 @@ err:
 	return -ENOMEM;
 }
 
+void __dump_page_owner(struct page *page)
+{
+	struct page_ext *page_ext = lookup_page_ext(page);
+	struct stack_trace trace = {
+		.nr_entries = page_ext->nr_entries,
+		.entries = &page_ext->trace_entries[0],
+	};
+	gfp_t gfp_mask = page_ext->gfp_mask;
+	int mt = gfpflags_to_migratetype(gfp_mask);
+
+	if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) {
+		pr_alert("page_owner info is not active (free page?)\n");
+		return;
+	}
+
+	pr_alert("page allocated via order %u, migratetype %s, "
+			"gfp_mask %#x(%pGg)\n", page_ext->order,
+			migratetype_names[mt], gfp_mask, &gfp_mask);
+	print_stack_trace(&trace, 0);
+
+	if (page_ext->last_migrate_reason != -1)
+		pr_alert("page has been migrated, last migrate reason: %s\n",
+			migrate_reason_names[page_ext->last_migrate_reason]);
+}
+
 static ssize_t
 read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 {
@@ -157,7 +215,7 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 	struct page *page;
 	struct page_ext *page_ext;
 
-	if (!page_owner_inited)
+	if (!static_branch_unlikely(&page_owner_inited))
 		return -EINVAL;
 
 	page = NULL;
@@ -305,7 +363,7 @@ static int __init pageowner_init(void)
 {
 	struct dentry *dentry;
 
-	if (!page_owner_inited) {
+	if (!static_branch_unlikely(&page_owner_inited)) {
 		pr_info("page_owner is disabled\n");
 		return 0;
 	}
diff --git a/mm/debug-pagealloc.c b/mm/page_poison.c
index 5bf5906ce13b..479e7ea2bea6 100644
--- a/mm/debug-pagealloc.c
+++ b/mm/page_poison.c
@@ -6,22 +6,48 @@
 #include <linux/poison.h>
 #include <linux/ratelimit.h>
 
-static bool page_poisoning_enabled __read_mostly;
+static bool __page_poisoning_enabled __read_mostly;
+static bool want_page_poisoning __read_mostly;
 
-static bool need_page_poisoning(void)
+static int early_page_poison_param(char *buf)
 {
-	if (!debug_pagealloc_enabled())
-		return false;
+	if (!buf)
+		return -EINVAL;
+
+	if (strcmp(buf, "on") == 0)
+		want_page_poisoning = true;
+	else if (strcmp(buf, "off") == 0)
+		want_page_poisoning = false;
 
-	return true;
+	return 0;
+}
+early_param("page_poison", early_page_poison_param);
+
+bool page_poisoning_enabled(void)
+{
+	return __page_poisoning_enabled;
+}
+
+static bool need_page_poisoning(void)
+{
+	return want_page_poisoning;
 }
 
 static void init_page_poisoning(void)
 {
-	if (!debug_pagealloc_enabled())
-		return;
+	/*
+	 * page poisoning is debug page alloc for some arches. If either
+	 * of those options are enabled, enable poisoning
+	 */
+	if (!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC)) {
+		if (!want_page_poisoning && !debug_pagealloc_enabled())
+			return;
+	} else {
+		if (!want_page_poisoning)
+			return;
+	}
 
-	page_poisoning_enabled = true;
+	__page_poisoning_enabled = true;
 }
 
 struct page_ext_operations page_poisoning_ops = {
@@ -45,11 +71,14 @@ static inline void clear_page_poison(struct page *page)
 	__clear_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags);
 }
 
-static inline bool page_poison(struct page *page)
+bool page_is_poisoned(struct page *page)
 {
 	struct page_ext *page_ext;
 
 	page_ext = lookup_page_ext(page);
+	if (!page_ext)
+		return false;
+
 	return test_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags);
 }
 
@@ -83,6 +112,9 @@ static void check_poison_mem(unsigned char *mem, size_t bytes)
 	unsigned char *start;
 	unsigned char *end;
 
+	if (IS_ENABLED(CONFIG_PAGE_POISONING_NO_SANITY))
+		return;
+
 	start = memchr_inv(mem, PAGE_POISON, bytes);
 	if (!start)
 		return;
@@ -95,9 +127,9 @@ static void check_poison_mem(unsigned char *mem, size_t bytes)
 	if (!__ratelimit(&ratelimit))
 		return;
 	else if (start == end && single_bit_flip(*start, PAGE_POISON))
-		printk(KERN_ERR "pagealloc: single bit error\n");
+		pr_err("pagealloc: single bit error\n");
 	else
-		printk(KERN_ERR "pagealloc: memory corruption\n");
+		pr_err("pagealloc: memory corruption\n");
 
 	print_hex_dump(KERN_ERR, "", DUMP_PREFIX_ADDRESS, 16, 1, start,
 			end - start + 1, 1);
@@ -108,7 +140,7 @@ static void unpoison_page(struct page *page)
 {
 	void *addr;
 
-	if (!page_poison(page))
+	if (!page_is_poisoned(page))
 		return;
 
 	addr = kmap_atomic(page);
@@ -125,9 +157,9 @@ static void unpoison_pages(struct page *page, int n)
 		unpoison_page(page + i);
 }
 
-void __kernel_map_pages(struct page *page, int numpages, int enable)
+void kernel_poison_pages(struct page *page, int numpages, int enable)
 {
-	if (!page_poisoning_enabled)
+	if (!page_poisoning_enabled())
 		return;
 
 	if (enable)
@@ -135,3 +167,10 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
 	else
 		poison_pages(page, numpages);
 }
+
+#ifndef CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC
+void __kernel_map_pages(struct page *page, int numpages, int enable)
+{
+	/* This function does nothing, all work is done via poison pages */
+}
+#endif
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 9d4767698a1c..06a005b979a7 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -90,9 +90,9 @@ pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
  * ARCHes with special requirements for evicting THP backing TLB entries can
  * implement this. Otherwise also, it can help optimize normal TLB flush in
  * THP regime. stock flush_tlb_range() typically has optimization to nuke the
- * entire TLB TLB if flush span is greater than a threshhold, which will
+ * entire TLB if flush span is greater than a threshold, which will
  * likely be true for a single huge page. Thus a single thp flush will
- * invalidate the entire TLB which is not desitable.
+ * invalidate the entire TLB which is not desirable.
  * e.g. see arch/arc: flush_pmd_tlb_range
  */
 #define flush_pmd_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
@@ -195,7 +195,9 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address,
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 	VM_BUG_ON(pmd_trans_huge(*pmdp));
 	pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
-	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+
+	/* collapse entails shooting down ptes not pmd */
+	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	return pmd;
 }
 #endif
diff --git a/mm/rmap.c b/mm/rmap.c
index 79f3bf047f38..02f0bfc3c80a 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1287,21 +1287,17 @@ void page_add_new_anon_rmap(struct page *page,
  */
 void page_add_file_rmap(struct page *page)
 {
-	struct mem_cgroup *memcg;
-
-	memcg = mem_cgroup_begin_page_stat(page);
+	lock_page_memcg(page);
 	if (atomic_inc_and_test(&page->_mapcount)) {
 		__inc_zone_page_state(page, NR_FILE_MAPPED);
-		mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_FILE_MAPPED);
+		mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
 	}
-	mem_cgroup_end_page_stat(memcg);
+	unlock_page_memcg(page);
 }
 
 static void page_remove_file_rmap(struct page *page)
 {
-	struct mem_cgroup *memcg;
-
-	memcg = mem_cgroup_begin_page_stat(page);
+	lock_page_memcg(page);
 
 	/* Hugepages are not counted in NR_FILE_MAPPED for now. */
 	if (unlikely(PageHuge(page))) {
@@ -1320,12 +1316,12 @@ static void page_remove_file_rmap(struct page *page)
 	 * pte lock(a spinlock) is held, which implies preemption disabled.
 	 */
 	__dec_zone_page_state(page, NR_FILE_MAPPED);
-	mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_FILE_MAPPED);
+	mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_FILE_MAPPED);
 
 	if (unlikely(PageMlocked(page)))
 		clear_page_mlock(page);
 out:
-	mem_cgroup_end_page_stat(memcg);
+	unlock_page_memcg(page);
 }
 
 static void page_remove_anon_compound_rmap(struct page *page)
diff --git a/mm/shmem.c b/mm/shmem.c
index 440e2a7e6c1c..1acfdbc4bd9e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1116,7 +1116,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 		 */
 		oldpage = newpage;
 	} else {
-		mem_cgroup_replace_page(oldpage, newpage);
+		mem_cgroup_migrate(oldpage, newpage);
 		lru_cache_add_anon(newpage);
 		*pagep = newpage;
 	}
diff --git a/mm/slab.c b/mm/slab.c
index 6ecc697a8bc4..852fc5c79829 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -169,12 +169,6 @@ typedef unsigned short freelist_idx_t;
 #define SLAB_OBJ_MAX_NUM ((1 << sizeof(freelist_idx_t) * BITS_PER_BYTE) - 1)
 
 /*
- * true if a page was allocated from pfmemalloc reserves for network-based
- * swap
- */
-static bool pfmemalloc_active __read_mostly;
-
-/*
  * struct array_cache
  *
  * Purpose:
@@ -195,10 +189,6 @@ struct array_cache {
 			 * Must have this definition in here for the proper
 			 * alignment of array_cache. Also simplifies accessing
 			 * the entries.
-			 *
-			 * Entries should not be directly dereferenced as
-			 * entries belonging to slabs marked pfmemalloc will
-			 * have the lower bits set SLAB_OBJ_PFMEMALLOC
 			 */
 };
 
@@ -207,33 +197,6 @@ struct alien_cache {
 	struct array_cache ac;
 };
 
-#define SLAB_OBJ_PFMEMALLOC	1
-static inline bool is_obj_pfmemalloc(void *objp)
-{
-	return (unsigned long)objp & SLAB_OBJ_PFMEMALLOC;
-}
-
-static inline void set_obj_pfmemalloc(void **objp)
-{
-	*objp = (void *)((unsigned long)*objp | SLAB_OBJ_PFMEMALLOC);
-	return;
-}
-
-static inline void clear_obj_pfmemalloc(void **objp)
-{
-	*objp = (void *)((unsigned long)*objp & ~SLAB_OBJ_PFMEMALLOC);
-}
-
-/*
- * bootstrap: The caches do not work without cpuarrays anymore, but the
- * cpuarrays are allocated from the generic caches...
- */
-#define BOOT_CPUCACHE_ENTRIES	1
-struct arraycache_init {
-	struct array_cache cache;
-	void *entries[BOOT_CPUCACHE_ENTRIES];
-};
-
 /*
  * Need this for bootstrapping a per node allocator.
  */
@@ -280,9 +243,10 @@ static void kmem_cache_node_init(struct kmem_cache_node *parent)
 	MAKE_LIST((cachep), (&(ptr)->slabs_free), slabs_free, nodeid);	\
 	} while (0)
 
+#define CFLGS_OBJFREELIST_SLAB	(0x40000000UL)
 #define CFLGS_OFF_SLAB		(0x80000000UL)
+#define	OBJFREELIST_SLAB(x)	((x)->flags & CFLGS_OBJFREELIST_SLAB)
 #define	OFF_SLAB(x)	((x)->flags & CFLGS_OFF_SLAB)
-#define OFF_SLAB_MIN_SIZE (max_t(size_t, PAGE_SIZE >> 5, KMALLOC_MIN_SIZE + 1))
 
 #define BATCHREFILL_LIMIT	16
 /*
@@ -390,36 +354,26 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp)
 
 #endif
 
-#define OBJECT_FREE (0)
-#define OBJECT_ACTIVE (1)
-
 #ifdef CONFIG_DEBUG_SLAB_LEAK
 
-static void set_obj_status(struct page *page, int idx, int val)
+static inline bool is_store_user_clean(struct kmem_cache *cachep)
 {
-	int freelist_size;
-	char *status;
-	struct kmem_cache *cachep = page->slab_cache;
-
-	freelist_size = cachep->num * sizeof(freelist_idx_t);
-	status = (char *)page->freelist + freelist_size;
-	status[idx] = val;
+	return atomic_read(&cachep->store_user_clean) == 1;
 }
 
-static inline unsigned int get_obj_status(struct page *page, int idx)
+static inline void set_store_user_clean(struct kmem_cache *cachep)
 {
-	int freelist_size;
-	char *status;
-	struct kmem_cache *cachep = page->slab_cache;
-
-	freelist_size = cachep->num * sizeof(freelist_idx_t);
-	status = (char *)page->freelist + freelist_size;
+	atomic_set(&cachep->store_user_clean, 1);
+}
 
-	return status[idx];
+static inline void set_store_user_dirty(struct kmem_cache *cachep)
+{
+	if (is_store_user_clean(cachep))
+		atomic_set(&cachep->store_user_clean, 0);
 }
 
 #else
-static inline void set_obj_status(struct page *page, int idx, int val) {}
+static inline void set_store_user_dirty(struct kmem_cache *cachep) {}
 
 #endif
 
@@ -457,6 +411,7 @@ static inline unsigned int obj_to_index(const struct kmem_cache *cache,
 	return reciprocal_divide(offset, cache->reciprocal_buffer_size);
 }
 
+#define BOOT_CPUCACHE_ENTRIES	1
 /* internal cache of cache description objs */
 static struct kmem_cache kmem_cache_boot = {
 	.batchcount = 1,
@@ -475,61 +430,13 @@ static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
 	return this_cpu_ptr(cachep->cpu_cache);
 }
 
-static size_t calculate_freelist_size(int nr_objs, size_t align)
-{
-	size_t freelist_size;
-
-	freelist_size = nr_objs * sizeof(freelist_idx_t);
-	if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK))
-		freelist_size += nr_objs * sizeof(char);
-
-	if (align)
-		freelist_size = ALIGN(freelist_size, align);
-
-	return freelist_size;
-}
-
-static int calculate_nr_objs(size_t slab_size, size_t buffer_size,
-				size_t idx_size, size_t align)
-{
-	int nr_objs;
-	size_t remained_size;
-	size_t freelist_size;
-	int extra_space = 0;
-
-	if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK))
-		extra_space = sizeof(char);
-	/*
-	 * Ignore padding for the initial guess. The padding
-	 * is at most @align-1 bytes, and @buffer_size is at
-	 * least @align. In the worst case, this result will
-	 * be one greater than the number of objects that fit
-	 * into the memory allocation when taking the padding
-	 * into account.
-	 */
-	nr_objs = slab_size / (buffer_size + idx_size + extra_space);
-
-	/*
-	 * This calculated number will be either the right
-	 * amount, or one greater than what we want.
-	 */
-	remained_size = slab_size - nr_objs * buffer_size;
-	freelist_size = calculate_freelist_size(nr_objs, align);
-	if (remained_size < freelist_size)
-		nr_objs--;
-
-	return nr_objs;
-}
-
 /*
  * Calculate the number of objects and left-over bytes for a given buffer size.
  */
-static void cache_estimate(unsigned long gfporder, size_t buffer_size,
-			   size_t align, int flags, size_t *left_over,
-			   unsigned int *num)
+static unsigned int cache_estimate(unsigned long gfporder, size_t buffer_size,
+		unsigned long flags, size_t *left_over)
 {
-	int nr_objs;
-	size_t mgmt_size;
+	unsigned int num;
 	size_t slab_size = PAGE_SIZE << gfporder;
 
 	/*
@@ -537,26 +444,28 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size,
 	 * on it. For the latter case, the memory allocated for a
 	 * slab is used for:
 	 *
-	 * - One unsigned int for each object
-	 * - Padding to respect alignment of @align
 	 * - @buffer_size bytes for each object
+	 * - One freelist_idx_t for each object
+	 *
+	 * We don't need to consider alignment of freelist because
+	 * freelist will be at the end of slab page. The objects will be
+	 * at the correct alignment.
 	 *
 	 * If the slab management structure is off the slab, then the
 	 * alignment will already be calculated into the size. Because
 	 * the slabs are all pages aligned, the objects will be at the
 	 * correct alignment when allocated.
 	 */
-	if (flags & CFLGS_OFF_SLAB) {
-		mgmt_size = 0;
-		nr_objs = slab_size / buffer_size;
-
+	if (flags & (CFLGS_OBJFREELIST_SLAB | CFLGS_OFF_SLAB)) {
+		num = slab_size / buffer_size;
+		*left_over = slab_size % buffer_size;
 	} else {
-		nr_objs = calculate_nr_objs(slab_size, buffer_size,
-					sizeof(freelist_idx_t), align);
-		mgmt_size = calculate_freelist_size(nr_objs, align);
+		num = slab_size / (buffer_size + sizeof(freelist_idx_t));
+		*left_over = slab_size %
+			(buffer_size + sizeof(freelist_idx_t));
 	}
-	*num = nr_objs;
-	*left_over = slab_size - nr_objs*buffer_size - mgmt_size;
+
+	return num;
 }
 
 #if DEBUG
@@ -687,120 +596,21 @@ static struct array_cache *alloc_arraycache(int node, int entries,
 	return ac;
 }
 
-static inline bool is_slab_pfmemalloc(struct page *page)
-{
-	return PageSlabPfmemalloc(page);
-}
-
-/* Clears pfmemalloc_active if no slabs have pfmalloc set */
-static void recheck_pfmemalloc_active(struct kmem_cache *cachep,
-						struct array_cache *ac)
+static noinline void cache_free_pfmemalloc(struct kmem_cache *cachep,
+					struct page *page, void *objp)
 {
-	struct kmem_cache_node *n = get_node(cachep, numa_mem_id());
-	struct page *page;
-	unsigned long flags;
-
-	if (!pfmemalloc_active)
-		return;
-
-	spin_lock_irqsave(&n->list_lock, flags);
-	list_for_each_entry(page, &n->slabs_full, lru)
-		if (is_slab_pfmemalloc(page))
-			goto out;
-
-	list_for_each_entry(page, &n->slabs_partial, lru)
-		if (is_slab_pfmemalloc(page))
-			goto out;
-
-	list_for_each_entry(page, &n->slabs_free, lru)
-		if (is_slab_pfmemalloc(page))
-			goto out;
-
-	pfmemalloc_active = false;
-out:
-	spin_unlock_irqrestore(&n->list_lock, flags);
-}
-
-static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
-						gfp_t flags, bool force_refill)
-{
-	int i;
-	void *objp = ac->entry[--ac->avail];
-
-	/* Ensure the caller is allowed to use objects from PFMEMALLOC slab */
-	if (unlikely(is_obj_pfmemalloc(objp))) {
-		struct kmem_cache_node *n;
-
-		if (gfp_pfmemalloc_allowed(flags)) {
-			clear_obj_pfmemalloc(&objp);
-			return objp;
-		}
-
-		/* The caller cannot use PFMEMALLOC objects, find another one */
-		for (i = 0; i < ac->avail; i++) {
-			/* If a !PFMEMALLOC object is found, swap them */
-			if (!is_obj_pfmemalloc(ac->entry[i])) {
-				objp = ac->entry[i];
-				ac->entry[i] = ac->entry[ac->avail];
-				ac->entry[ac->avail] = objp;
-				return objp;
-			}
-		}
-
-		/*
-		 * If there are empty slabs on the slabs_free list and we are
-		 * being forced to refill the cache, mark this one !pfmemalloc.
-		 */
-		n = get_node(cachep, numa_mem_id());
-		if (!list_empty(&n->slabs_free) && force_refill) {
-			struct page *page = virt_to_head_page(objp);
-			ClearPageSlabPfmemalloc(page);
-			clear_obj_pfmemalloc(&objp);
-			recheck_pfmemalloc_active(cachep, ac);
-			return objp;
-		}
-
-		/* No !PFMEMALLOC objects available */
-		ac->avail++;
-		objp = NULL;
-	}
-
-	return objp;
-}
-
-static inline void *ac_get_obj(struct kmem_cache *cachep,
-			struct array_cache *ac, gfp_t flags, bool force_refill)
-{
-	void *objp;
-
-	if (unlikely(sk_memalloc_socks()))
-		objp = __ac_get_obj(cachep, ac, flags, force_refill);
-	else
-		objp = ac->entry[--ac->avail];
-
-	return objp;
-}
-
-static noinline void *__ac_put_obj(struct kmem_cache *cachep,
-			struct array_cache *ac, void *objp)
-{
-	if (unlikely(pfmemalloc_active)) {
-		/* Some pfmemalloc slabs exist, check if this is one */
-		struct page *page = virt_to_head_page(objp);
-		if (PageSlabPfmemalloc(page))
-			set_obj_pfmemalloc(&objp);
-	}
+	struct kmem_cache_node *n;
+	int page_node;
+	LIST_HEAD(list);
 
-	return objp;
-}
+	page_node = page_to_nid(page);
+	n = get_node(cachep, page_node);
 
-static inline void ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
-								void *objp)
-{
-	if (unlikely(sk_memalloc_socks()))
-		objp = __ac_put_obj(cachep, ac, objp);
+	spin_lock(&n->list_lock);
+	free_block(cachep, &objp, 1, page_node, &list);
+	spin_unlock(&n->list_lock);
 
-	ac->entry[ac->avail++] = objp;
+	slabs_destroy(cachep, &list);
 }
 
 /*
@@ -1003,7 +813,7 @@ static int __cache_free_alien(struct kmem_cache *cachep, void *objp,
 			STATS_INC_ACOVERFLOW(cachep);
 			__drain_alien_cache(cachep, ac, page_node, &list);
 		}
-		ac_put_obj(cachep, ac, objp);
+		ac->entry[ac->avail++] = objp;
 		spin_unlock(&alien->lock);
 		slabs_destroy(cachep, &list);
 	} else {
@@ -1540,10 +1350,9 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
 	if ((gfpflags & __GFP_NOWARN) || !__ratelimit(&slab_oom_rs))
 		return;
 
-	printk(KERN_WARNING
-		"SLAB: Unable to allocate memory on node %d (gfp=0x%x)\n",
-		nodeid, gfpflags);
-	printk(KERN_WARNING "  cache: %s, object size: %d, order: %d\n",
+	pr_warn("SLAB: Unable to allocate memory on node %d, gfp=%#x(%pGg)\n",
+		nodeid, gfpflags, &gfpflags);
+	pr_warn("  cache: %s, object size: %d, order: %d\n",
 		cachep->name, cachep->size, cachep->gfporder);
 
 	for_each_kmem_cache_node(cachep, node, n) {
@@ -1567,8 +1376,7 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
 
 		num_slabs += active_slabs;
 		num_objs = num_slabs * cachep->num;
-		printk(KERN_WARNING
-			"  node %d: slabs: %ld/%ld, objs: %ld/%ld, free: %ld\n",
+		pr_warn("  node %d: slabs: %ld/%ld, objs: %ld/%ld, free: %ld\n",
 			node, active_slabs, num_slabs, active_objs, num_objs,
 			free_objects);
 	}
@@ -1604,10 +1412,6 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
 		return NULL;
 	}
 
-	/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
-	if (page_is_pfmemalloc(page))
-		pfmemalloc_active = true;
-
 	nr_pages = (1 << cachep->gfporder);
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
 		add_zone_page_state(page_zone(page),
@@ -1615,8 +1419,10 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
 	else
 		add_zone_page_state(page_zone(page),
 			NR_SLAB_UNRECLAIMABLE, nr_pages);
+
 	__SetPageSlab(page);
-	if (page_is_pfmemalloc(page))
+	/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
+	if (sk_memalloc_socks() && page_is_pfmemalloc(page))
 		SetPageSlabPfmemalloc(page);
 
 	if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) {
@@ -1670,6 +1476,14 @@ static void kmem_rcu_free(struct rcu_head *head)
 }
 
 #if DEBUG
+static bool is_debug_pagealloc_cache(struct kmem_cache *cachep)
+{
+	if (debug_pagealloc_enabled() && OFF_SLAB(cachep) &&
+		(cachep->size % PAGE_SIZE) == 0)
+		return true;
+
+	return false;
+}
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
 static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr,
@@ -1703,6 +1517,23 @@ static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr,
 	}
 	*addr++ = 0x87654321;
 }
+
+static void slab_kernel_map(struct kmem_cache *cachep, void *objp,
+				int map, unsigned long caller)
+{
+	if (!is_debug_pagealloc_cache(cachep))
+		return;
+
+	if (caller)
+		store_stackinfo(cachep, objp, caller);
+
+	kernel_map_pages(virt_to_page(objp), cachep->size / PAGE_SIZE, map);
+}
+
+#else
+static inline void slab_kernel_map(struct kmem_cache *cachep, void *objp,
+				int map, unsigned long caller) {}
+
 #endif
 
 static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val)
@@ -1781,6 +1612,9 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp)
 	int size, i;
 	int lines = 0;
 
+	if (is_debug_pagealloc_cache(cachep))
+		return;
+
 	realobj = (char *)objp + obj_offset(cachep);
 	size = cachep->object_size;
 
@@ -1842,20 +1676,18 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep,
 						struct page *page)
 {
 	int i;
+
+	if (OBJFREELIST_SLAB(cachep) && cachep->flags & SLAB_POISON) {
+		poison_obj(cachep, page->freelist - obj_offset(cachep),
+			POISON_FREE);
+	}
+
 	for (i = 0; i < cachep->num; i++) {
 		void *objp = index_to_obj(cachep, page, i);
 
 		if (cachep->flags & SLAB_POISON) {
-#ifdef CONFIG_DEBUG_PAGEALLOC
-			if (cachep->size % PAGE_SIZE == 0 &&
-					OFF_SLAB(cachep))
-				kernel_map_pages(virt_to_page(objp),
-					cachep->size / PAGE_SIZE, 1);
-			else
-				check_poison_obj(cachep, objp);
-#else
 			check_poison_obj(cachep, objp);
-#endif
+			slab_kernel_map(cachep, objp, 1, 0);
 		}
 		if (cachep->flags & SLAB_RED_ZONE) {
 			if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
@@ -1916,7 +1748,6 @@ static void slabs_destroy(struct kmem_cache *cachep, struct list_head *list)
  * calculate_slab_order - calculate size (page order) of slabs
  * @cachep: pointer to the cache that is being created
  * @size: size of objects to be created in this cache.
- * @align: required alignment for the objects.
  * @flags: slab allocation flags
  *
  * Also calculates the number of objects per slab.
@@ -1926,9 +1757,8 @@ static void slabs_destroy(struct kmem_cache *cachep, struct list_head *list)
  * towards high-order requests, this should be changed.
  */
 static size_t calculate_slab_order(struct kmem_cache *cachep,
-			size_t size, size_t align, unsigned long flags)
+				size_t size, unsigned long flags)
 {
-	unsigned long offslab_limit;
 	size_t left_over = 0;
 	int gfporder;
 
@@ -1936,7 +1766,7 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
 		unsigned int num;
 		size_t remainder;
 
-		cache_estimate(gfporder, size, align, flags, &remainder, &num);
+		num = cache_estimate(gfporder, size, flags, &remainder);
 		if (!num)
 			continue;
 
@@ -1945,19 +1775,24 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
 			break;
 
 		if (flags & CFLGS_OFF_SLAB) {
-			size_t freelist_size_per_obj = sizeof(freelist_idx_t);
+			struct kmem_cache *freelist_cache;
+			size_t freelist_size;
+
+			freelist_size = num * sizeof(freelist_idx_t);
+			freelist_cache = kmalloc_slab(freelist_size, 0u);
+			if (!freelist_cache)
+				continue;
+
 			/*
-			 * Max number of objs-per-slab for caches which
-			 * use off-slab slabs. Needed to avoid a possible
-			 * looping condition in cache_grow().
+			 * Needed to avoid possible looping condition
+			 * in cache_grow()
 			 */
-			if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK))
-				freelist_size_per_obj += sizeof(char);
-			offslab_limit = size;
-			offslab_limit /= freelist_size_per_obj;
+			if (OFF_SLAB(freelist_cache))
+				continue;
 
- 			if (num > offslab_limit)
-				break;
+			/* check if off slab has enough benefit */
+			if (freelist_cache->size > cachep->size / 2)
+				continue;
 		}
 
 		/* Found something acceptable - save it away */
@@ -2075,6 +1910,79 @@ __kmem_cache_alias(const char *name, size_t size, size_t align,
 	return cachep;
 }
 
+static bool set_objfreelist_slab_cache(struct kmem_cache *cachep,
+			size_t size, unsigned long flags)
+{
+	size_t left;
+
+	cachep->num = 0;
+
+	if (cachep->ctor || flags & SLAB_DESTROY_BY_RCU)
+		return false;
+
+	left = calculate_slab_order(cachep, size,
+			flags | CFLGS_OBJFREELIST_SLAB);
+	if (!cachep->num)
+		return false;
+
+	if (cachep->num * sizeof(freelist_idx_t) > cachep->object_size)
+		return false;
+
+	cachep->colour = left / cachep->colour_off;
+
+	return true;
+}
+
+static bool set_off_slab_cache(struct kmem_cache *cachep,
+			size_t size, unsigned long flags)
+{
+	size_t left;
+
+	cachep->num = 0;
+
+	/*
+	 * Always use on-slab management when SLAB_NOLEAKTRACE
+	 * to avoid recursive calls into kmemleak.
+	 */
+	if (flags & SLAB_NOLEAKTRACE)
+		return false;
+
+	/*
+	 * Size is large, assume best to place the slab management obj
+	 * off-slab (should allow better packing of objs).
+	 */
+	left = calculate_slab_order(cachep, size, flags | CFLGS_OFF_SLAB);
+	if (!cachep->num)
+		return false;
+
+	/*
+	 * If the slab has been placed off-slab, and we have enough space then
+	 * move it on-slab. This is at the expense of any extra colouring.
+	 */
+	if (left >= cachep->num * sizeof(freelist_idx_t))
+		return false;
+
+	cachep->colour = left / cachep->colour_off;
+
+	return true;
+}
+
+static bool set_on_slab_cache(struct kmem_cache *cachep,
+			size_t size, unsigned long flags)
+{
+	size_t left;
+
+	cachep->num = 0;
+
+	left = calculate_slab_order(cachep, size, flags);
+	if (!cachep->num)
+		return false;
+
+	cachep->colour = left / cachep->colour_off;
+
+	return true;
+}
+
 /**
  * __kmem_cache_create - Create a cache.
  * @cachep: cache management descriptor
@@ -2099,7 +2007,6 @@ __kmem_cache_alias(const char *name, size_t size, size_t align,
 int
 __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 {
-	size_t left_over, freelist_size;
 	size_t ralign = BYTES_PER_WORD;
 	gfp_t gfp;
 	int err;
@@ -2119,8 +2026,6 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 	if (!(flags & SLAB_DESTROY_BY_RCU))
 		flags |= SLAB_POISON;
 #endif
-	if (flags & SLAB_DESTROY_BY_RCU)
-		BUG_ON(flags & SLAB_POISON);
 #endif
 
 	/*
@@ -2152,6 +2057,10 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 	 * 4) Store it.
 	 */
 	cachep->align = ralign;
+	cachep->colour_off = cache_line_size();
+	/* Offset must be a multiple of the alignment. */
+	if (cachep->colour_off < cachep->align)
+		cachep->colour_off = cachep->align;
 
 	if (slab_is_available())
 		gfp = GFP_KERNEL;
@@ -2179,37 +2088,8 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 		else
 			size += BYTES_PER_WORD;
 	}
-#if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
-	/*
-	 * To activate debug pagealloc, off-slab management is necessary
-	 * requirement. In early phase of initialization, small sized slab
-	 * doesn't get initialized so it would not be possible. So, we need
-	 * to check size >= 256. It guarantees that all necessary small
-	 * sized slab is initialized in current slab initialization sequence.
-	 */
-	if (!slab_early_init && size >= kmalloc_size(INDEX_NODE) &&
-		size >= 256 && cachep->object_size > cache_line_size() &&
-		ALIGN(size, cachep->align) < PAGE_SIZE) {
-		cachep->obj_offset += PAGE_SIZE - ALIGN(size, cachep->align);
-		size = PAGE_SIZE;
-	}
-#endif
 #endif
 
-	/*
-	 * Determine if the slab management is 'on' or 'off' slab.
-	 * (bootstrapping cannot cope with offslab caches so don't do
-	 * it too early on. Always use on-slab management when
-	 * SLAB_NOLEAKTRACE to avoid recursive calls into kmemleak)
-	 */
-	if (size >= OFF_SLAB_MIN_SIZE && !slab_early_init &&
-	    !(flags & SLAB_NOLEAKTRACE))
-		/*
-		 * Size is large, assume best to place the slab management obj
-		 * off-slab (should allow better packing of objs).
-		 */
-		flags |= CFLGS_OFF_SLAB;
-
 	size = ALIGN(size, cachep->align);
 	/*
 	 * We should restrict the number of objects in a slab to implement
@@ -2218,42 +2098,46 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 	if (FREELIST_BYTE_INDEX && size < SLAB_OBJ_MIN_SIZE)
 		size = ALIGN(SLAB_OBJ_MIN_SIZE, cachep->align);
 
-	left_over = calculate_slab_order(cachep, size, cachep->align, flags);
-
-	if (!cachep->num)
-		return -E2BIG;
-
-	freelist_size = calculate_freelist_size(cachep->num, cachep->align);
-
+#if DEBUG
 	/*
-	 * If the slab has been placed off-slab, and we have enough space then
-	 * move it on-slab. This is at the expense of any extra colouring.
+	 * To activate debug pagealloc, off-slab management is necessary
+	 * requirement. In early phase of initialization, small sized slab
+	 * doesn't get initialized so it would not be possible. So, we need
+	 * to check size >= 256. It guarantees that all necessary small
+	 * sized slab is initialized in current slab initialization sequence.
 	 */
-	if (flags & CFLGS_OFF_SLAB && left_over >= freelist_size) {
-		flags &= ~CFLGS_OFF_SLAB;
-		left_over -= freelist_size;
+	if (debug_pagealloc_enabled() && (flags & SLAB_POISON) &&
+		size >= 256 && cachep->object_size > cache_line_size()) {
+		if (size < PAGE_SIZE || size % PAGE_SIZE == 0) {
+			size_t tmp_size = ALIGN(size, PAGE_SIZE);
+
+			if (set_off_slab_cache(cachep, tmp_size, flags)) {
+				flags |= CFLGS_OFF_SLAB;
+				cachep->obj_offset += tmp_size - size;
+				size = tmp_size;
+				goto done;
+			}
+		}
 	}
+#endif
 
-	if (flags & CFLGS_OFF_SLAB) {
-		/* really off slab. No need for manual alignment */
-		freelist_size = calculate_freelist_size(cachep->num, 0);
+	if (set_objfreelist_slab_cache(cachep, size, flags)) {
+		flags |= CFLGS_OBJFREELIST_SLAB;
+		goto done;
+	}
 
-#ifdef CONFIG_PAGE_POISONING
-		/* If we're going to use the generic kernel_map_pages()
-		 * poisoning, then it's going to smash the contents of
-		 * the redzone and userword anyhow, so switch them off.
-		 */
-		if (size % PAGE_SIZE == 0 && flags & SLAB_POISON)
-			flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
-#endif
+	if (set_off_slab_cache(cachep, size, flags)) {
+		flags |= CFLGS_OFF_SLAB;
+		goto done;
 	}
 
-	cachep->colour_off = cache_line_size();
-	/* Offset must be a multiple of the alignment. */
-	if (cachep->colour_off < cachep->align)
-		cachep->colour_off = cachep->align;
-	cachep->colour = left_over / cachep->colour_off;
-	cachep->freelist_size = freelist_size;
+	if (set_on_slab_cache(cachep, size, flags))
+		goto done;
+
+	return -E2BIG;
+
+done:
+	cachep->freelist_size = cachep->num * sizeof(freelist_idx_t);
 	cachep->flags = flags;
 	cachep->allocflags = __GFP_COMP;
 	if (CONFIG_ZONE_DMA_FLAG && (flags & SLAB_CACHE_DMA))
@@ -2261,21 +2145,26 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 	cachep->size = size;
 	cachep->reciprocal_buffer_size = reciprocal_value(size);
 
-	if (flags & CFLGS_OFF_SLAB) {
-		cachep->freelist_cache = kmalloc_slab(freelist_size, 0u);
-		/*
-		 * This is a possibility for one of the kmalloc_{dma,}_caches.
-		 * But since we go off slab only for object size greater than
-		 * OFF_SLAB_MIN_SIZE, and kmalloc_{dma,}_caches get created
-		 * in ascending order,this should not happen at all.
-		 * But leave a BUG_ON for some lucky dude.
-		 */
-		BUG_ON(ZERO_OR_NULL_PTR(cachep->freelist_cache));
+#if DEBUG
+	/*
+	 * If we're going to use the generic kernel_map_pages()
+	 * poisoning, then it's going to smash the contents of
+	 * the redzone and userword anyhow, so switch them off.
+	 */
+	if (IS_ENABLED(CONFIG_PAGE_POISONING) &&
+		(cachep->flags & SLAB_POISON) &&
+		is_debug_pagealloc_cache(cachep))
+		cachep->flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
+#endif
+
+	if (OFF_SLAB(cachep)) {
+		cachep->freelist_cache =
+			kmalloc_slab(cachep->freelist_size, 0u);
 	}
 
 	err = setup_cpu_cache(cachep, gfp);
 	if (err) {
-		__kmem_cache_shutdown(cachep);
+		__kmem_cache_release(cachep);
 		return err;
 	}
 
@@ -2377,9 +2266,6 @@ static int drain_freelist(struct kmem_cache *cache,
 		}
 
 		page = list_entry(p, struct page, lru);
-#if DEBUG
-		BUG_ON(page->active);
-#endif
 		list_del(&page->lru);
 		/*
 		 * Safe to drop the lock. The slab is no longer linked
@@ -2414,12 +2300,13 @@ int __kmem_cache_shrink(struct kmem_cache *cachep, bool deactivate)
 
 int __kmem_cache_shutdown(struct kmem_cache *cachep)
 {
+	return __kmem_cache_shrink(cachep, false);
+}
+
+void __kmem_cache_release(struct kmem_cache *cachep)
+{
 	int i;
 	struct kmem_cache_node *n;
-	int rc = __kmem_cache_shrink(cachep, false);
-
-	if (rc)
-		return rc;
 
 	free_percpu(cachep->cpu_cache);
 
@@ -2430,7 +2317,6 @@ int __kmem_cache_shutdown(struct kmem_cache *cachep)
 		kfree(n);
 		cachep->node[i] = NULL;
 	}
-	return 0;
 }
 
 /*
@@ -2454,18 +2340,23 @@ static void *alloc_slabmgmt(struct kmem_cache *cachep,
 	void *freelist;
 	void *addr = page_address(page);
 
-	if (OFF_SLAB(cachep)) {
+	page->s_mem = addr + colour_off;
+	page->active = 0;
+
+	if (OBJFREELIST_SLAB(cachep))
+		freelist = NULL;
+	else if (OFF_SLAB(cachep)) {
 		/* Slab management obj is off-slab. */
 		freelist = kmem_cache_alloc_node(cachep->freelist_cache,
 					      local_flags, nodeid);
 		if (!freelist)
 			return NULL;
 	} else {
-		freelist = addr + colour_off;
-		colour_off += cachep->freelist_size;
+		/* We will use last bytes at the slab for freelist */
+		freelist = addr + (PAGE_SIZE << cachep->gfporder) -
+				cachep->freelist_size;
 	}
-	page->active = 0;
-	page->s_mem = addr + colour_off;
+
 	return freelist;
 }
 
@@ -2480,17 +2371,14 @@ static inline void set_free_obj(struct page *page,
 	((freelist_idx_t *)(page->freelist))[idx] = val;
 }
 
-static void cache_init_objs(struct kmem_cache *cachep,
-			    struct page *page)
+static void cache_init_objs_debug(struct kmem_cache *cachep, struct page *page)
 {
+#if DEBUG
 	int i;
 
 	for (i = 0; i < cachep->num; i++) {
 		void *objp = index_to_obj(cachep, page, i);
-#if DEBUG
-		/* need to poison the objs? */
-		if (cachep->flags & SLAB_POISON)
-			poison_obj(cachep, objp, POISON_FREE);
+
 		if (cachep->flags & SLAB_STORE_USER)
 			*dbg_userword(cachep, objp) = NULL;
 
@@ -2514,15 +2402,32 @@ static void cache_init_objs(struct kmem_cache *cachep,
 				slab_error(cachep, "constructor overwrote the"
 					   " start of an object");
 		}
-		if ((cachep->size % PAGE_SIZE) == 0 &&
-			    OFF_SLAB(cachep) && cachep->flags & SLAB_POISON)
-			kernel_map_pages(virt_to_page(objp),
-					 cachep->size / PAGE_SIZE, 0);
-#else
-		if (cachep->ctor)
-			cachep->ctor(objp);
+		/* need to poison the objs? */
+		if (cachep->flags & SLAB_POISON) {
+			poison_obj(cachep, objp, POISON_FREE);
+			slab_kernel_map(cachep, objp, 0, 0);
+		}
+	}
 #endif
-		set_obj_status(page, i, OBJECT_FREE);
+}
+
+static void cache_init_objs(struct kmem_cache *cachep,
+			    struct page *page)
+{
+	int i;
+
+	cache_init_objs_debug(cachep, page);
+
+	if (OBJFREELIST_SLAB(cachep)) {
+		page->freelist = index_to_obj(cachep, page, cachep->num - 1) +
+						obj_offset(cachep);
+	}
+
+	for (i = 0; i < cachep->num; i++) {
+		/* constructor could break poison info */
+		if (DEBUG == 0 && cachep->ctor)
+			cachep->ctor(index_to_obj(cachep, page, i));
+
 		set_free_obj(page, i, i);
 	}
 }
@@ -2537,30 +2442,28 @@ static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags)
 	}
 }
 
-static void *slab_get_obj(struct kmem_cache *cachep, struct page *page,
-				int nodeid)
+static void *slab_get_obj(struct kmem_cache *cachep, struct page *page)
 {
 	void *objp;
 
 	objp = index_to_obj(cachep, page, get_free_obj(page, page->active));
 	page->active++;
+
 #if DEBUG
-	WARN_ON(page_to_nid(virt_to_page(objp)) != nodeid);
+	if (cachep->flags & SLAB_STORE_USER)
+		set_store_user_dirty(cachep);
 #endif
 
 	return objp;
 }
 
-static void slab_put_obj(struct kmem_cache *cachep, struct page *page,
-				void *objp, int nodeid)
+static void slab_put_obj(struct kmem_cache *cachep,
+			struct page *page, void *objp)
 {
 	unsigned int objnr = obj_to_index(cachep, page, objp);
 #if DEBUG
 	unsigned int i;
 
-	/* Verify that the slab belongs to the intended node */
-	WARN_ON(page_to_nid(virt_to_page(objp)) != nodeid);
-
 	/* Verify double free bug */
 	for (i = page->active; i < cachep->num; i++) {
 		if (get_free_obj(page, i) == objnr) {
@@ -2571,6 +2474,9 @@ static void slab_put_obj(struct kmem_cache *cachep, struct page *page,
 	}
 #endif
 	page->active--;
+	if (!page->freelist)
+		page->freelist = objp + obj_offset(cachep);
+
 	set_free_obj(page, page->active, objnr);
 }
 
@@ -2645,7 +2551,7 @@ static int cache_grow(struct kmem_cache *cachep,
 	/* Get slab management. */
 	freelist = alloc_slabmgmt(cachep, page, offset,
 			local_flags & ~GFP_CONSTRAINT_MASK, nodeid);
-	if (!freelist)
+	if (OFF_SLAB(cachep) && !freelist)
 		goto opps1;
 
 	slab_map_pages(cachep, page, freelist);
@@ -2726,27 +2632,19 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 		*dbg_redzone1(cachep, objp) = RED_INACTIVE;
 		*dbg_redzone2(cachep, objp) = RED_INACTIVE;
 	}
-	if (cachep->flags & SLAB_STORE_USER)
+	if (cachep->flags & SLAB_STORE_USER) {
+		set_store_user_dirty(cachep);
 		*dbg_userword(cachep, objp) = (void *)caller;
+	}
 
 	objnr = obj_to_index(cachep, page, objp);
 
 	BUG_ON(objnr >= cachep->num);
 	BUG_ON(objp != index_to_obj(cachep, page, objnr));
 
-	set_obj_status(page, objnr, OBJECT_FREE);
 	if (cachep->flags & SLAB_POISON) {
-#ifdef CONFIG_DEBUG_PAGEALLOC
-		if ((cachep->size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) {
-			store_stackinfo(cachep, objp, caller);
-			kernel_map_pages(virt_to_page(objp),
-					 cachep->size / PAGE_SIZE, 0);
-		} else {
-			poison_obj(cachep, objp, POISON_FREE);
-		}
-#else
 		poison_obj(cachep, objp, POISON_FREE);
-#endif
+		slab_kernel_map(cachep, objp, 0, caller);
 	}
 	return objp;
 }
@@ -2756,7 +2654,85 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 #define cache_free_debugcheck(x,objp,z) (objp)
 #endif
 
-static struct page *get_first_slab(struct kmem_cache_node *n)
+static inline void fixup_objfreelist_debug(struct kmem_cache *cachep,
+						void **list)
+{
+#if DEBUG
+	void *next = *list;
+	void *objp;
+
+	while (next) {
+		objp = next - obj_offset(cachep);
+		next = *(void **)next;
+		poison_obj(cachep, objp, POISON_FREE);
+	}
+#endif
+}
+
+static inline void fixup_slab_list(struct kmem_cache *cachep,
+				struct kmem_cache_node *n, struct page *page,
+				void **list)
+{
+	/* move slabp to correct slabp list: */
+	list_del(&page->lru);
+	if (page->active == cachep->num) {
+		list_add(&page->lru, &n->slabs_full);
+		if (OBJFREELIST_SLAB(cachep)) {
+#if DEBUG
+			/* Poisoning will be done without holding the lock */
+			if (cachep->flags & SLAB_POISON) {
+				void **objp = page->freelist;
+
+				*objp = *list;
+				*list = objp;
+			}
+#endif
+			page->freelist = NULL;
+		}
+	} else
+		list_add(&page->lru, &n->slabs_partial);
+}
+
+/* Try to find non-pfmemalloc slab if needed */
+static noinline struct page *get_valid_first_slab(struct kmem_cache_node *n,
+					struct page *page, bool pfmemalloc)
+{
+	if (!page)
+		return NULL;
+
+	if (pfmemalloc)
+		return page;
+
+	if (!PageSlabPfmemalloc(page))
+		return page;
+
+	/* No need to keep pfmemalloc slab if we have enough free objects */
+	if (n->free_objects > n->free_limit) {
+		ClearPageSlabPfmemalloc(page);
+		return page;
+	}
+
+	/* Move pfmemalloc slab to the end of list to speed up next search */
+	list_del(&page->lru);
+	if (!page->active)
+		list_add_tail(&page->lru, &n->slabs_free);
+	else
+		list_add_tail(&page->lru, &n->slabs_partial);
+
+	list_for_each_entry(page, &n->slabs_partial, lru) {
+		if (!PageSlabPfmemalloc(page))
+			return page;
+	}
+
+	list_for_each_entry(page, &n->slabs_free, lru) {
+		if (!PageSlabPfmemalloc(page))
+			return page;
+	}
+
+	return NULL;
+}
+
+static struct page *get_first_slab(struct kmem_cache_node *n, bool pfmemalloc)
 {
 	struct page *page;
 
@@ -2768,21 +2744,51 @@ static struct page *get_first_slab(struct kmem_cache_node *n)
 				struct page, lru);
 	}
 
+	if (sk_memalloc_socks())
+		return get_valid_first_slab(n, page, pfmemalloc);
+
 	return page;
 }
 
-static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags,
-							bool force_refill)
+static noinline void *cache_alloc_pfmemalloc(struct kmem_cache *cachep,
+				struct kmem_cache_node *n, gfp_t flags)
+{
+	struct page *page;
+	void *obj;
+	void *list = NULL;
+
+	if (!gfp_pfmemalloc_allowed(flags))
+		return NULL;
+
+	spin_lock(&n->list_lock);
+	page = get_first_slab(n, true);
+	if (!page) {
+		spin_unlock(&n->list_lock);
+		return NULL;
+	}
+
+	obj = slab_get_obj(cachep, page);
+	n->free_objects--;
+
+	fixup_slab_list(cachep, n, page, &list);
+
+	spin_unlock(&n->list_lock);
+	fixup_objfreelist_debug(cachep, &list);
+
+	return obj;
+}
+
+static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags)
 {
 	int batchcount;
 	struct kmem_cache_node *n;
 	struct array_cache *ac;
 	int node;
+	void *list = NULL;
 
 	check_irq_off();
 	node = numa_mem_id();
-	if (unlikely(force_refill))
-		goto force_grow;
+
 retry:
 	ac = cpu_cache_get(cachep);
 	batchcount = ac->batchcount;
@@ -2808,7 +2814,7 @@ retry:
 	while (batchcount > 0) {
 		struct page *page;
 		/* Get slab alloc is to come from. */
-		page = get_first_slab(n);
+		page = get_first_slab(n, false);
 		if (!page)
 			goto must_grow;
 
@@ -2826,26 +2832,29 @@ retry:
 			STATS_INC_ACTIVE(cachep);
 			STATS_SET_HIGH(cachep);
 
-			ac_put_obj(cachep, ac, slab_get_obj(cachep, page,
-									node));
+			ac->entry[ac->avail++] = slab_get_obj(cachep, page);
 		}
 
-		/* move slabp to correct slabp list: */
-		list_del(&page->lru);
-		if (page->active == cachep->num)
-			list_add(&page->lru, &n->slabs_full);
-		else
-			list_add(&page->lru, &n->slabs_partial);
+		fixup_slab_list(cachep, n, page, &list);
 	}
 
 must_grow:
 	n->free_objects -= ac->avail;
 alloc_done:
 	spin_unlock(&n->list_lock);
+	fixup_objfreelist_debug(cachep, &list);
 
 	if (unlikely(!ac->avail)) {
 		int x;
-force_grow:
+
+		/* Check if we can use obj in pfmemalloc slab */
+		if (sk_memalloc_socks()) {
+			void *obj = cache_alloc_pfmemalloc(cachep, n, flags);
+
+			if (obj)
+				return obj;
+		}
+
 		x = cache_grow(cachep, gfp_exact_node(flags), node, NULL);
 
 		/* cache_grow can reenable interrupts, then ac could change. */
@@ -2853,7 +2862,7 @@ force_grow:
 		node = numa_mem_id();
 
 		/* no objects in sight? abort */
-		if (!x && (ac->avail == 0 || force_refill))
+		if (!x && ac->avail == 0)
 			return NULL;
 
 		if (!ac->avail)		/* objects refilled by interrupt? */
@@ -2861,7 +2870,7 @@ force_grow:
 	}
 	ac->touched = 1;
 
-	return ac_get_obj(cachep, ac, flags, force_refill);
+	return ac->entry[--ac->avail];
 }
 
 static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep,
@@ -2877,20 +2886,11 @@ static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep,
 static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 				gfp_t flags, void *objp, unsigned long caller)
 {
-	struct page *page;
-
 	if (!objp)
 		return objp;
 	if (cachep->flags & SLAB_POISON) {
-#ifdef CONFIG_DEBUG_PAGEALLOC
-		if ((cachep->size % PAGE_SIZE) == 0 && OFF_SLAB(cachep))
-			kernel_map_pages(virt_to_page(objp),
-					 cachep->size / PAGE_SIZE, 1);
-		else
-			check_poison_obj(cachep, objp);
-#else
 		check_poison_obj(cachep, objp);
-#endif
+		slab_kernel_map(cachep, objp, 1, 0);
 		poison_obj(cachep, objp, POISON_INUSE);
 	}
 	if (cachep->flags & SLAB_STORE_USER)
@@ -2910,8 +2910,6 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 		*dbg_redzone2(cachep, objp) = RED_ACTIVE;
 	}
 
-	page = virt_to_head_page(objp);
-	set_obj_status(page, obj_to_index(cachep, page, objp), OBJECT_ACTIVE);
 	objp += obj_offset(cachep);
 	if (cachep->ctor && cachep->flags & SLAB_POISON)
 		cachep->ctor(objp);
@@ -2926,40 +2924,24 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 #define cache_alloc_debugcheck_after(a,b,objp,d) (objp)
 #endif
 
-static bool slab_should_failslab(struct kmem_cache *cachep, gfp_t flags)
-{
-	if (unlikely(cachep == kmem_cache))
-		return false;
-
-	return should_failslab(cachep->object_size, flags, cachep->flags);
-}
-
 static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 {
 	void *objp;
 	struct array_cache *ac;
-	bool force_refill = false;
 
 	check_irq_off();
 
 	ac = cpu_cache_get(cachep);
 	if (likely(ac->avail)) {
 		ac->touched = 1;
-		objp = ac_get_obj(cachep, ac, flags, false);
+		objp = ac->entry[--ac->avail];
 
-		/*
-		 * Allow for the possibility all avail objects are not allowed
-		 * by the current flags
-		 */
-		if (objp) {
-			STATS_INC_ALLOCHIT(cachep);
-			goto out;
-		}
-		force_refill = true;
+		STATS_INC_ALLOCHIT(cachep);
+		goto out;
 	}
 
 	STATS_INC_ALLOCMISS(cachep);
-	objp = cache_alloc_refill(cachep, flags, force_refill);
+	objp = cache_alloc_refill(cachep, flags);
 	/*
 	 * the 'ac' may be updated by cache_alloc_refill(),
 	 * and kmemleak_erase() requires its correct value.
@@ -3097,6 +3079,7 @@ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
 	struct page *page;
 	struct kmem_cache_node *n;
 	void *obj;
+	void *list = NULL;
 	int x;
 
 	VM_BUG_ON(nodeid < 0 || nodeid >= MAX_NUMNODES);
@@ -3106,7 +3089,7 @@ static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
 retry:
 	check_irq_off();
 	spin_lock(&n->list_lock);
-	page = get_first_slab(n);
+	page = get_first_slab(n, false);
 	if (!page)
 		goto must_grow;
 
@@ -3118,17 +3101,13 @@ retry:
 
 	BUG_ON(page->active == cachep->num);
 
-	obj = slab_get_obj(cachep, page, nodeid);
+	obj = slab_get_obj(cachep, page);
 	n->free_objects--;
-	/* move slabp to correct slabp list: */
-	list_del(&page->lru);
 
-	if (page->active == cachep->num)
-		list_add(&page->lru, &n->slabs_full);
-	else
-		list_add(&page->lru, &n->slabs_partial);
+	fixup_slab_list(cachep, n, page, &list);
 
 	spin_unlock(&n->list_lock);
+	fixup_objfreelist_debug(cachep, &list);
 	goto done;
 
 must_grow:
@@ -3152,14 +3131,10 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
 	int slab_node = numa_mem_id();
 
 	flags &= gfp_allowed_mask;
-
-	lockdep_trace_alloc(flags);
-
-	if (slab_should_failslab(cachep, flags))
+	cachep = slab_pre_alloc_hook(cachep, flags);
+	if (unlikely(!cachep))
 		return NULL;
 
-	cachep = memcg_kmem_get_cache(cachep, flags);
-
 	cache_alloc_debugcheck_before(cachep, flags);
 	local_irq_save(save_flags);
 
@@ -3188,16 +3163,11 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
   out:
 	local_irq_restore(save_flags);
 	ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller);
-	kmemleak_alloc_recursive(ptr, cachep->object_size, 1, cachep->flags,
-				 flags);
 
-	if (likely(ptr)) {
-		kmemcheck_slab_alloc(cachep, flags, ptr, cachep->object_size);
-		if (unlikely(flags & __GFP_ZERO))
-			memset(ptr, 0, cachep->object_size);
-	}
+	if (unlikely(flags & __GFP_ZERO) && ptr)
+		memset(ptr, 0, cachep->object_size);
 
-	memcg_kmem_put_cache(cachep);
+	slab_post_alloc_hook(cachep, flags, 1, &ptr);
 	return ptr;
 }
 
@@ -3240,30 +3210,21 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller)
 	void *objp;
 
 	flags &= gfp_allowed_mask;
-
-	lockdep_trace_alloc(flags);
-
-	if (slab_should_failslab(cachep, flags))
+	cachep = slab_pre_alloc_hook(cachep, flags);
+	if (unlikely(!cachep))
 		return NULL;
 
-	cachep = memcg_kmem_get_cache(cachep, flags);
-
 	cache_alloc_debugcheck_before(cachep, flags);
 	local_irq_save(save_flags);
 	objp = __do_cache_alloc(cachep, flags);
 	local_irq_restore(save_flags);
 	objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller);
-	kmemleak_alloc_recursive(objp, cachep->object_size, 1, cachep->flags,
-				 flags);
 	prefetchw(objp);
 
-	if (likely(objp)) {
-		kmemcheck_slab_alloc(cachep, flags, objp, cachep->object_size);
-		if (unlikely(flags & __GFP_ZERO))
-			memset(objp, 0, cachep->object_size);
-	}
+	if (unlikely(flags & __GFP_ZERO) && objp)
+		memset(objp, 0, cachep->object_size);
 
-	memcg_kmem_put_cache(cachep);
+	slab_post_alloc_hook(cachep, flags, 1, &objp);
 	return objp;
 }
 
@@ -3281,13 +3242,12 @@ static void free_block(struct kmem_cache *cachep, void **objpp,
 		void *objp;
 		struct page *page;
 
-		clear_obj_pfmemalloc(&objpp[i]);
 		objp = objpp[i];
 
 		page = virt_to_head_page(objp);
 		list_del(&page->lru);
 		check_spinlock_acquired_node(cachep, node);
-		slab_put_obj(cachep, page, objp, node);
+		slab_put_obj(cachep, page, objp);
 		STATS_DEC_ACTIVE(cachep);
 		n->free_objects++;
 
@@ -3317,9 +3277,7 @@ static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac)
 	LIST_HEAD(list);
 
 	batchcount = ac->batchcount;
-#if DEBUG
-	BUG_ON(!batchcount || batchcount > ac->avail);
-#endif
+
 	check_irq_off();
 	n = get_node(cachep, node);
 	spin_lock(&n->list_lock);
@@ -3389,7 +3347,16 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp,
 		cache_flusharray(cachep, ac);
 	}
 
-	ac_put_obj(cachep, ac, objp);
+	if (sk_memalloc_socks()) {
+		struct page *page = virt_to_head_page(objp);
+
+		if (unlikely(PageSlabPfmemalloc(page))) {
+			cache_free_pfmemalloc(cachep, page, objp);
+			return;
+		}
+	}
+
+	ac->entry[ac->avail++] = objp;
 }
 
 /**
@@ -3411,16 +3378,53 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 }
 EXPORT_SYMBOL(kmem_cache_alloc);
 
-void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
+static __always_inline void
+cache_alloc_debugcheck_after_bulk(struct kmem_cache *s, gfp_t flags,
+				  size_t size, void **p, unsigned long caller)
 {
-	__kmem_cache_free_bulk(s, size, p);
+	size_t i;
+
+	for (i = 0; i < size; i++)
+		p[i] = cache_alloc_debugcheck_after(s, flags, p[i], caller);
 }
-EXPORT_SYMBOL(kmem_cache_free_bulk);
 
 int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
-								void **p)
+			  void **p)
 {
-	return __kmem_cache_alloc_bulk(s, flags, size, p);
+	size_t i;
+
+	s = slab_pre_alloc_hook(s, flags);
+	if (!s)
+		return 0;
+
+	cache_alloc_debugcheck_before(s, flags);
+
+	local_irq_disable();
+	for (i = 0; i < size; i++) {
+		void *objp = __do_cache_alloc(s, flags);
+
+		if (unlikely(!objp))
+			goto error;
+		p[i] = objp;
+	}
+	local_irq_enable();
+
+	cache_alloc_debugcheck_after_bulk(s, flags, size, p, _RET_IP_);
+
+	/* Clear memory outside IRQ disabled section */
+	if (unlikely(flags & __GFP_ZERO))
+		for (i = 0; i < size; i++)
+			memset(p[i], 0, s->object_size);
+
+	slab_post_alloc_hook(s, flags, size, p);
+	/* FIXME: Trace call missing. Christoph would like a bulk variant */
+	return size;
+error:
+	local_irq_enable();
+	cache_alloc_debugcheck_after_bulk(s, flags, i, p, _RET_IP_);
+	slab_post_alloc_hook(s, flags, i, p);
+	__kmem_cache_free_bulk(s, i, p);
+	return 0;
 }
 EXPORT_SYMBOL(kmem_cache_alloc_bulk);
 
@@ -3567,6 +3571,32 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
+void kmem_cache_free_bulk(struct kmem_cache *orig_s, size_t size, void **p)
+{
+	struct kmem_cache *s;
+	size_t i;
+
+	local_irq_disable();
+	for (i = 0; i < size; i++) {
+		void *objp = p[i];
+
+		if (!orig_s) /* called via kfree_bulk */
+			s = virt_to_cache(objp);
+		else
+			s = cache_from_obj(orig_s, objp);
+
+		debug_check_no_locks_freed(objp, s->object_size);
+		if (!(s->flags & SLAB_DEBUG_OBJECTS))
+			debug_check_no_obj_freed(objp, s->object_size);
+
+		__cache_free(s, objp, _RET_IP_);
+	}
+	local_irq_enable();
+
+	/* FIXME: add tracing */
+}
+EXPORT_SYMBOL(kmem_cache_free_bulk);
+
 /**
  * kfree - free previously allocated memory
  * @objp: pointer returned by kmalloc.
@@ -4102,15 +4132,34 @@ static void handle_slab(unsigned long *n, struct kmem_cache *c,
 						struct page *page)
 {
 	void *p;
-	int i;
+	int i, j;
+	unsigned long v;
 
 	if (n[0] == n[1])
 		return;
 	for (i = 0, p = page->s_mem; i < c->num; i++, p += c->size) {
-		if (get_obj_status(page, i) != OBJECT_ACTIVE)
+		bool active = true;
+
+		for (j = page->active; j < c->num; j++) {
+			if (get_free_obj(page, j) == i) {
+				active = false;
+				break;
+			}
+		}
+
+		if (!active)
+			continue;
+
+		/*
+		 * probe_kernel_read() is used for DEBUG_PAGEALLOC. page table
+		 * mapping is established when actual object allocation and
+		 * we could mistakenly access the unmapped object in the cpu
+		 * cache.
+		 */
+		if (probe_kernel_read(&v, dbg_userword(c, p), sizeof(v)))
 			continue;
 
-		if (!add_caller(n, (unsigned long)*dbg_userword(c, p)))
+		if (!add_caller(n, v))
 			return;
 	}
 }
@@ -4146,21 +4195,31 @@ static int leaks_show(struct seq_file *m, void *p)
 	if (!(cachep->flags & SLAB_RED_ZONE))
 		return 0;
 
-	/* OK, we can do it */
+	/*
+	 * Set store_user_clean and start to grab stored user information
+	 * for all objects on this cache. If some alloc/free requests comes
+	 * during the processing, information would be wrong so restart
+	 * whole processing.
+	 */
+	do {
+		set_store_user_clean(cachep);
+		drain_cpu_caches(cachep);
 
-	x[1] = 0;
+		x[1] = 0;
 
-	for_each_kmem_cache_node(cachep, node, n) {
+		for_each_kmem_cache_node(cachep, node, n) {
 
-		check_irq_on();
-		spin_lock_irq(&n->list_lock);
+			check_irq_on();
+			spin_lock_irq(&n->list_lock);
+
+			list_for_each_entry(page, &n->slabs_full, lru)
+				handle_slab(x, cachep, page);
+			list_for_each_entry(page, &n->slabs_partial, lru)
+				handle_slab(x, cachep, page);
+			spin_unlock_irq(&n->list_lock);
+		}
+	} while (!is_store_user_clean(cachep));
 
-		list_for_each_entry(page, &n->slabs_full, lru)
-			handle_slab(x, cachep, page);
-		list_for_each_entry(page, &n->slabs_partial, lru)
-			handle_slab(x, cachep, page);
-		spin_unlock_irq(&n->list_lock);
-	}
 	name = cachep->name;
 	if (x[0] == x[1]) {
 		/* Increase the buffer size */
diff --git a/mm/slab.h b/mm/slab.h
index 834ad240c0bb..b7934361f026 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -38,6 +38,10 @@ struct kmem_cache {
 #endif
 
 #include <linux/memcontrol.h>
+#include <linux/fault-inject.h>
+#include <linux/kmemcheck.h>
+#include <linux/kasan.h>
+#include <linux/kmemleak.h>
 
 /*
  * State of the slab allocator.
@@ -121,7 +125,7 @@ static inline unsigned long kmem_cache_flags(unsigned long object_size,
 #define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER)
 #elif defined(CONFIG_SLUB_DEBUG)
 #define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
-			  SLAB_TRACE | SLAB_DEBUG_FREE)
+			  SLAB_TRACE | SLAB_CONSISTENCY_CHECKS)
 #else
 #define SLAB_DEBUG_FLAGS (0)
 #endif
@@ -140,6 +144,7 @@ static inline unsigned long kmem_cache_flags(unsigned long object_size,
 #define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS)
 
 int __kmem_cache_shutdown(struct kmem_cache *);
+void __kmem_cache_release(struct kmem_cache *);
 int __kmem_cache_shrink(struct kmem_cache *, bool);
 void slab_kmem_cache_release(struct kmem_cache *);
 
@@ -167,7 +172,7 @@ ssize_t slabinfo_write(struct file *file, const char __user *buffer,
 /*
  * Generic implementation of bulk operations
  * These are useful for situations in which the allocator cannot
- * perform optimizations. In that case segments of the objecct listed
+ * perform optimizations. In that case segments of the object listed
  * may be allocated or freed using these operations.
  */
 void __kmem_cache_free_bulk(struct kmem_cache *, size_t, void **);
@@ -306,7 +311,8 @@ static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
 	 * to not do even the assignment. In that case, slab_equal_or_root
 	 * will also be a constant.
 	 */
-	if (!memcg_kmem_enabled() && !unlikely(s->flags & SLAB_DEBUG_FREE))
+	if (!memcg_kmem_enabled() &&
+	    !unlikely(s->flags & SLAB_CONSISTENCY_CHECKS))
 		return s;
 
 	page = virt_to_head_page(x);
@@ -320,6 +326,64 @@ static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
 	return s;
 }
 
+static inline size_t slab_ksize(const struct kmem_cache *s)
+{
+#ifndef CONFIG_SLUB
+	return s->object_size;
+
+#else /* CONFIG_SLUB */
+# ifdef CONFIG_SLUB_DEBUG
+	/*
+	 * Debugging requires use of the padding between object
+	 * and whatever may come after it.
+	 */
+	if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
+		return s->object_size;
+# endif
+	/*
+	 * If we have the need to store the freelist pointer
+	 * back there or track user information then we can
+	 * only use the space before that information.
+	 */
+	if (s->flags & (SLAB_DESTROY_BY_RCU | SLAB_STORE_USER))
+		return s->inuse;
+	/*
+	 * Else we can use all the padding etc for the allocation
+	 */
+	return s->size;
+#endif
+}
+
+static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
+						     gfp_t flags)
+{
+	flags &= gfp_allowed_mask;
+	lockdep_trace_alloc(flags);
+	might_sleep_if(gfpflags_allow_blocking(flags));
+
+	if (should_failslab(s, flags))
+		return NULL;
+
+	return memcg_kmem_get_cache(s, flags);
+}
+
+static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
+					size_t size, void **p)
+{
+	size_t i;
+
+	flags &= gfp_allowed_mask;
+	for (i = 0; i < size; i++) {
+		void *object = p[i];
+
+		kmemcheck_slab_alloc(s, flags, object, slab_ksize(s));
+		kmemleak_alloc_recursive(object, s->object_size, 1,
+					 s->flags, flags);
+		kasan_slab_alloc(s, object);
+	}
+	memcg_kmem_put_cache(s);
+}
+
 #ifndef CONFIG_SLOB
 /*
  * The slab lists for all objects.
diff --git a/mm/slab_common.c b/mm/slab_common.c
index b50aef01ccf7..6afb2263a5c5 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -109,8 +109,12 @@ void __kmem_cache_free_bulk(struct kmem_cache *s, size_t nr, void **p)
 {
 	size_t i;
 
-	for (i = 0; i < nr; i++)
-		kmem_cache_free(s, p[i]);
+	for (i = 0; i < nr; i++) {
+		if (s)
+			kmem_cache_free(s, p[i]);
+		else
+			kfree(p[i]);
+	}
 }
 
 int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr,
@@ -693,6 +697,7 @@ static inline int shutdown_memcg_caches(struct kmem_cache *s,
 
 void slab_kmem_cache_release(struct kmem_cache *s)
 {
+	__kmem_cache_release(s);
 	destroy_memcg_params(s);
 	kfree_const(s->name);
 	kmem_cache_free(kmem_cache, s);
diff --git a/mm/slob.c b/mm/slob.c
index 17e8f8cc7c53..5ec158054ffe 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -630,6 +630,10 @@ int __kmem_cache_shutdown(struct kmem_cache *c)
 	return 0;
 }
 
+void __kmem_cache_release(struct kmem_cache *c)
+{
+}
+
 int __kmem_cache_shrink(struct kmem_cache *d, bool deactivate)
 {
 	return 0;
diff --git a/mm/slub.c b/mm/slub.c
index 2e1355ac056b..6c91324f9370 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -124,6 +124,14 @@ static inline int kmem_cache_debug(struct kmem_cache *s)
 #endif
 }
 
+static inline void *fixup_red_left(struct kmem_cache *s, void *p)
+{
+	if (kmem_cache_debug(s) && s->flags & SLAB_RED_ZONE)
+		p += s->red_left_pad;
+
+	return p;
+}
+
 static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
 {
 #ifdef CONFIG_SLUB_CPU_PARTIAL
@@ -160,10 +168,18 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
  */
 #define MAX_PARTIAL 10
 
-#define DEBUG_DEFAULT_FLAGS (SLAB_DEBUG_FREE | SLAB_RED_ZONE | \
+#define DEBUG_DEFAULT_FLAGS (SLAB_CONSISTENCY_CHECKS | SLAB_RED_ZONE | \
 				SLAB_POISON | SLAB_STORE_USER)
 
 /*
+ * These debug flags cannot use CMPXCHG because there might be consistency
+ * issues when checking or reading debug information
+ */
+#define SLAB_NO_CMPXCHG (SLAB_CONSISTENCY_CHECKS | SLAB_STORE_USER | \
+				SLAB_TRACE)
+
+
+/*
  * Debugging flags that require metadata to be stored in the slab.  These get
  * disabled when slub_debug=O is used and a cache's min order increases with
  * metadata.
@@ -224,24 +240,6 @@ static inline void stat(const struct kmem_cache *s, enum stat_item si)
  * 			Core slab cache functions
  *******************************************************************/
 
-/* Verify that a pointer has an address that is valid within a slab page */
-static inline int check_valid_pointer(struct kmem_cache *s,
-				struct page *page, const void *object)
-{
-	void *base;
-
-	if (!object)
-		return 1;
-
-	base = page_address(page);
-	if (object < base || object >= base + page->objects * s->size ||
-		(object - base) % s->size) {
-		return 0;
-	}
-
-	return 1;
-}
-
 static inline void *get_freepointer(struct kmem_cache *s, void *object)
 {
 	return *(void **)(object + s->offset);
@@ -271,12 +269,14 @@ static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp)
 
 /* Loop over all objects in a slab */
 #define for_each_object(__p, __s, __addr, __objects) \
-	for (__p = (__addr); __p < (__addr) + (__objects) * (__s)->size;\
-			__p += (__s)->size)
+	for (__p = fixup_red_left(__s, __addr); \
+		__p < (__addr) + (__objects) * (__s)->size; \
+		__p += (__s)->size)
 
 #define for_each_object_idx(__p, __idx, __s, __addr, __objects) \
-	for (__p = (__addr), __idx = 1; __idx <= __objects;\
-			__p += (__s)->size, __idx++)
+	for (__p = fixup_red_left(__s, __addr), __idx = 1; \
+		__idx <= __objects; \
+		__p += (__s)->size, __idx++)
 
 /* Determine object index from a given position */
 static inline int slab_index(void *p, struct kmem_cache *s, void *addr)
@@ -284,30 +284,6 @@ static inline int slab_index(void *p, struct kmem_cache *s, void *addr)
 	return (p - addr) / s->size;
 }
 
-static inline size_t slab_ksize(const struct kmem_cache *s)
-{
-#ifdef CONFIG_SLUB_DEBUG
-	/*
-	 * Debugging requires use of the padding between object
-	 * and whatever may come after it.
-	 */
-	if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
-		return s->object_size;
-
-#endif
-	/*
-	 * If we have the need to store the freelist pointer
-	 * back there or track user information then we can
-	 * only use the space before that information.
-	 */
-	if (s->flags & (SLAB_DESTROY_BY_RCU | SLAB_STORE_USER))
-		return s->inuse;
-	/*
-	 * Else we can use all the padding etc for the allocation
-	 */
-	return s->size;
-}
-
 static inline int order_objects(int order, unsigned long size, int reserved)
 {
 	return ((PAGE_SIZE << order) - reserved) / size;
@@ -458,6 +434,22 @@ static void get_map(struct kmem_cache *s, struct page *page, unsigned long *map)
 		set_bit(slab_index(p, s, addr), map);
 }
 
+static inline int size_from_object(struct kmem_cache *s)
+{
+	if (s->flags & SLAB_RED_ZONE)
+		return s->size - s->red_left_pad;
+
+	return s->size;
+}
+
+static inline void *restore_red_left(struct kmem_cache *s, void *p)
+{
+	if (s->flags & SLAB_RED_ZONE)
+		p -= s->red_left_pad;
+
+	return p;
+}
+
 /*
  * Debug settings:
  */
@@ -491,6 +483,26 @@ static inline void metadata_access_disable(void)
 /*
  * Object debugging
  */
+
+/* Verify that a pointer has an address that is valid within a slab page */
+static inline int check_valid_pointer(struct kmem_cache *s,
+				struct page *page, void *object)
+{
+	void *base;
+
+	if (!object)
+		return 1;
+
+	base = page_address(page);
+	object = restore_red_left(s, object);
+	if (object < base || object >= base + page->objects * s->size ||
+		(object - base) % s->size) {
+		return 0;
+	}
+
+	return 1;
+}
+
 static void print_section(char *text, u8 *addr, unsigned int length)
 {
 	metadata_access_enable();
@@ -630,7 +642,9 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 	pr_err("INFO: Object 0x%p @offset=%tu fp=0x%p\n\n",
 	       p, p - addr, get_freepointer(s, p));
 
-	if (p > addr + 16)
+	if (s->flags & SLAB_RED_ZONE)
+		print_section("Redzone ", p - s->red_left_pad, s->red_left_pad);
+	else if (p > addr + 16)
 		print_section("Bytes b4 ", p - 16, 16);
 
 	print_section("Object ", p, min_t(unsigned long, s->object_size,
@@ -647,9 +661,9 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 	if (s->flags & SLAB_STORE_USER)
 		off += 2 * sizeof(struct track);
 
-	if (off != s->size)
+	if (off != size_from_object(s))
 		/* Beginning of the filler is the free pointer */
-		print_section("Padding ", p + off, s->size - off);
+		print_section("Padding ", p + off, size_from_object(s) - off);
 
 	dump_stack();
 }
@@ -679,6 +693,9 @@ static void init_object(struct kmem_cache *s, void *object, u8 val)
 {
 	u8 *p = object;
 
+	if (s->flags & SLAB_RED_ZONE)
+		memset(p - s->red_left_pad, val, s->red_left_pad);
+
 	if (s->flags & __OBJECT_POISON) {
 		memset(p, POISON_FREE, s->object_size - 1);
 		p[s->object_size - 1] = POISON_END;
@@ -771,11 +788,11 @@ static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p)
 		/* We also have user information there */
 		off += 2 * sizeof(struct track);
 
-	if (s->size == off)
+	if (size_from_object(s) == off)
 		return 1;
 
 	return check_bytes_and_report(s, page, p, "Object padding",
-				p + off, POISON_INUSE, s->size - off);
+			p + off, POISON_INUSE, size_from_object(s) - off);
 }
 
 /* Check the pad bytes at the end of a slab page */
@@ -820,6 +837,10 @@ static int check_object(struct kmem_cache *s, struct page *page,
 
 	if (s->flags & SLAB_RED_ZONE) {
 		if (!check_bytes_and_report(s, page, object, "Redzone",
+			object - s->red_left_pad, val, s->red_left_pad))
+			return 0;
+
+		if (!check_bytes_and_report(s, page, object, "Redzone",
 			endobject, val, s->inuse - s->object_size))
 			return 0;
 	} else {
@@ -1031,20 +1052,32 @@ static void setup_object_debug(struct kmem_cache *s, struct page *page,
 	init_tracking(s, object);
 }
 
-static noinline int alloc_debug_processing(struct kmem_cache *s,
+static inline int alloc_consistency_checks(struct kmem_cache *s,
 					struct page *page,
 					void *object, unsigned long addr)
 {
 	if (!check_slab(s, page))
-		goto bad;
+		return 0;
 
 	if (!check_valid_pointer(s, page, object)) {
 		object_err(s, page, object, "Freelist Pointer check fails");
-		goto bad;
+		return 0;
 	}
 
 	if (!check_object(s, page, object, SLUB_RED_INACTIVE))
-		goto bad;
+		return 0;
+
+	return 1;
+}
+
+static noinline int alloc_debug_processing(struct kmem_cache *s,
+					struct page *page,
+					void *object, unsigned long addr)
+{
+	if (s->flags & SLAB_CONSISTENCY_CHECKS) {
+		if (!alloc_consistency_checks(s, page, object, addr))
+			goto bad;
+	}
 
 	/* Success perform special debug activities for allocs */
 	if (s->flags & SLAB_STORE_USER)
@@ -1067,37 +1100,21 @@ bad:
 	return 0;
 }
 
-/* Supports checking bulk free of a constructed freelist */
-static noinline struct kmem_cache_node *free_debug_processing(
-	struct kmem_cache *s, struct page *page,
-	void *head, void *tail, int bulk_cnt,
-	unsigned long addr, unsigned long *flags)
+static inline int free_consistency_checks(struct kmem_cache *s,
+		struct page *page, void *object, unsigned long addr)
 {
-	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
-	void *object = head;
-	int cnt = 0;
-
-	spin_lock_irqsave(&n->list_lock, *flags);
-	slab_lock(page);
-
-	if (!check_slab(s, page))
-		goto fail;
-
-next_object:
-	cnt++;
-
 	if (!check_valid_pointer(s, page, object)) {
 		slab_err(s, page, "Invalid object pointer 0x%p", object);
-		goto fail;
+		return 0;
 	}
 
 	if (on_freelist(s, page, object)) {
 		object_err(s, page, object, "Object already free");
-		goto fail;
+		return 0;
 	}
 
 	if (!check_object(s, page, object, SLUB_RED_ACTIVE))
-		goto out;
+		return 0;
 
 	if (unlikely(s != page->slab_cache)) {
 		if (!PageSlab(page)) {
@@ -1110,7 +1127,37 @@ next_object:
 		} else
 			object_err(s, page, object,
 					"page slab pointer corrupt.");
-		goto fail;
+		return 0;
+	}
+	return 1;
+}
+
+/* Supports checking bulk free of a constructed freelist */
+static noinline int free_debug_processing(
+	struct kmem_cache *s, struct page *page,
+	void *head, void *tail, int bulk_cnt,
+	unsigned long addr)
+{
+	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
+	void *object = head;
+	int cnt = 0;
+	unsigned long uninitialized_var(flags);
+	int ret = 0;
+
+	spin_lock_irqsave(&n->list_lock, flags);
+	slab_lock(page);
+
+	if (s->flags & SLAB_CONSISTENCY_CHECKS) {
+		if (!check_slab(s, page))
+			goto out;
+	}
+
+next_object:
+	cnt++;
+
+	if (s->flags & SLAB_CONSISTENCY_CHECKS) {
+		if (!free_consistency_checks(s, page, object, addr))
+			goto out;
 	}
 
 	if (s->flags & SLAB_STORE_USER)
@@ -1124,23 +1171,18 @@ next_object:
 		object = get_freepointer(s, object);
 		goto next_object;
 	}
+	ret = 1;
+
 out:
 	if (cnt != bulk_cnt)
 		slab_err(s, page, "Bulk freelist count(%d) invalid(%d)\n",
 			 bulk_cnt, cnt);
 
 	slab_unlock(page);
-	/*
-	 * Keep node_lock to preserve integrity
-	 * until the object is actually freed
-	 */
-	return n;
-
-fail:
-	slab_unlock(page);
-	spin_unlock_irqrestore(&n->list_lock, *flags);
-	slab_fix(s, "Object at 0x%p not freed", object);
-	return NULL;
+	spin_unlock_irqrestore(&n->list_lock, flags);
+	if (!ret)
+		slab_fix(s, "Object at 0x%p not freed", object);
+	return ret;
 }
 
 static int __init setup_slub_debug(char *str)
@@ -1172,7 +1214,7 @@ static int __init setup_slub_debug(char *str)
 	for (; *str && *str != ','; str++) {
 		switch (tolower(*str)) {
 		case 'f':
-			slub_debug |= SLAB_DEBUG_FREE;
+			slub_debug |= SLAB_CONSISTENCY_CHECKS;
 			break;
 		case 'z':
 			slub_debug |= SLAB_RED_ZONE;
@@ -1231,10 +1273,10 @@ static inline void setup_object_debug(struct kmem_cache *s,
 static inline int alloc_debug_processing(struct kmem_cache *s,
 	struct page *page, void *object, unsigned long addr) { return 0; }
 
-static inline struct kmem_cache_node *free_debug_processing(
+static inline int free_debug_processing(
 	struct kmem_cache *s, struct page *page,
 	void *head, void *tail, int bulk_cnt,
-	unsigned long addr, unsigned long *flags) { return NULL; }
+	unsigned long addr) { return 0; }
 
 static inline int slab_pad_check(struct kmem_cache *s, struct page *page)
 			{ return 1; }
@@ -1281,36 +1323,6 @@ static inline void kfree_hook(const void *x)
 	kasan_kfree_large(x);
 }
 
-static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
-						     gfp_t flags)
-{
-	flags &= gfp_allowed_mask;
-	lockdep_trace_alloc(flags);
-	might_sleep_if(gfpflags_allow_blocking(flags));
-
-	if (should_failslab(s->object_size, flags, s->flags))
-		return NULL;
-
-	return memcg_kmem_get_cache(s, flags);
-}
-
-static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
-					size_t size, void **p)
-{
-	size_t i;
-
-	flags &= gfp_allowed_mask;
-	for (i = 0; i < size; i++) {
-		void *object = p[i];
-
-		kmemcheck_slab_alloc(s, flags, object, slab_ksize(s));
-		kmemleak_alloc_recursive(object, s->object_size, 1,
-					 s->flags, flags);
-		kasan_slab_alloc(s, object);
-	}
-	memcg_kmem_put_cache(s);
-}
-
 static inline void slab_free_hook(struct kmem_cache *s, void *x)
 {
 	kmemleak_free_recursive(x, s->flags);
@@ -1470,7 +1482,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 			set_freepointer(s, p, NULL);
 	}
 
-	page->freelist = start;
+	page->freelist = fixup_red_left(s, start);
 	page->inuse = page->objects;
 	page->frozen = 1;
 
@@ -1506,7 +1518,7 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
 	int order = compound_order(page);
 	int pages = 1 << order;
 
-	if (kmem_cache_debug(s)) {
+	if (s->flags & SLAB_CONSISTENCY_CHECKS) {
 		void *p;
 
 		slab_pad_check(s, page);
@@ -1592,18 +1604,12 @@ static inline void add_partial(struct kmem_cache_node *n,
 	__add_partial(n, page, tail);
 }
 
-static inline void
-__remove_partial(struct kmem_cache_node *n, struct page *page)
-{
-	list_del(&page->lru);
-	n->nr_partial--;
-}
-
 static inline void remove_partial(struct kmem_cache_node *n,
 					struct page *page)
 {
 	lockdep_assert_held(&n->list_lock);
-	__remove_partial(n, page);
+	list_del(&page->lru);
+	n->nr_partial--;
 }
 
 /*
@@ -2230,8 +2236,8 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
 	if ((gfpflags & __GFP_NOWARN) || !__ratelimit(&slub_oom_rs))
 		return;
 
-	pr_warn("SLUB: Unable to allocate memory on node %d (gfp=0x%x)\n",
-		nid, gfpflags);
+	pr_warn("SLUB: Unable to allocate memory on node %d, gfp=%#x(%pGg)\n",
+		nid, gfpflags, &gfpflags);
 	pr_warn("  cache: %s, object size: %d, buffer size: %d, default order: %d, min order: %d\n",
 		s->name, s->object_size, s->size, oo_order(s->oo),
 		oo_order(s->min));
@@ -2648,8 +2654,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 	stat(s, FREE_SLOWPATH);
 
 	if (kmem_cache_debug(s) &&
-	    !(n = free_debug_processing(s, page, head, tail, cnt,
-					addr, &flags)))
+	    !free_debug_processing(s, page, head, tail, cnt, addr))
 		return;
 
 	do {
@@ -2821,6 +2826,7 @@ struct detached_freelist {
 	void *tail;
 	void *freelist;
 	int cnt;
+	struct kmem_cache *s;
 };
 
 /*
@@ -2835,26 +2841,45 @@ struct detached_freelist {
  * synchronization primitive.  Look ahead in the array is limited due
  * to performance reasons.
  */
-static int build_detached_freelist(struct kmem_cache *s, size_t size,
-				   void **p, struct detached_freelist *df)
+static inline
+int build_detached_freelist(struct kmem_cache *s, size_t size,
+			    void **p, struct detached_freelist *df)
 {
 	size_t first_skipped_index = 0;
 	int lookahead = 3;
 	void *object;
+	struct page *page;
 
 	/* Always re-init detached_freelist */
 	df->page = NULL;
 
 	do {
 		object = p[--size];
+		/* Do we need !ZERO_OR_NULL_PTR(object) here? (for kfree) */
 	} while (!object && size);
 
 	if (!object)
 		return 0;
 
+	page = virt_to_head_page(object);
+	if (!s) {
+		/* Handle kalloc'ed objects */
+		if (unlikely(!PageSlab(page))) {
+			BUG_ON(!PageCompound(page));
+			kfree_hook(object);
+			__free_kmem_pages(page, compound_order(page));
+			p[size] = NULL; /* mark object processed */
+			return size;
+		}
+		/* Derive kmem_cache from object */
+		df->s = page->slab_cache;
+	} else {
+		df->s = cache_from_obj(s, object); /* Support for memcg */
+	}
+
 	/* Start new detached freelist */
-	set_freepointer(s, object, NULL);
-	df->page = virt_to_head_page(object);
+	df->page = page;
+	set_freepointer(df->s, object, NULL);
 	df->tail = object;
 	df->freelist = object;
 	p[size] = NULL; /* mark object processed */
@@ -2868,7 +2893,7 @@ static int build_detached_freelist(struct kmem_cache *s, size_t size,
 		/* df->page is always set at this point */
 		if (df->page == virt_to_head_page(object)) {
 			/* Opportunity build freelist */
-			set_freepointer(s, object, df->freelist);
+			set_freepointer(df->s, object, df->freelist);
 			df->freelist = object;
 			df->cnt++;
 			p[size] = NULL; /* mark object processed */
@@ -2887,25 +2912,20 @@ static int build_detached_freelist(struct kmem_cache *s, size_t size,
 	return first_skipped_index;
 }
 
-
 /* Note that interrupts must be enabled when calling this function. */
-void kmem_cache_free_bulk(struct kmem_cache *orig_s, size_t size, void **p)
+void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
 {
 	if (WARN_ON(!size))
 		return;
 
 	do {
 		struct detached_freelist df;
-		struct kmem_cache *s;
-
-		/* Support for memcg */
-		s = cache_from_obj(orig_s, p[size - 1]);
 
 		size = build_detached_freelist(s, size, p, &df);
 		if (unlikely(!df.page))
 			continue;
 
-		slab_free(s, df.page, df.freelist, df.tail, df.cnt, _RET_IP_);
+		slab_free(df.s, df.page, df.freelist, df.tail, df.cnt,_RET_IP_);
 	} while (likely(size));
 }
 EXPORT_SYMBOL(kmem_cache_free_bulk);
@@ -3184,6 +3204,12 @@ static void free_kmem_cache_nodes(struct kmem_cache *s)
 	}
 }
 
+void __kmem_cache_release(struct kmem_cache *s)
+{
+	free_percpu(s->cpu_slab);
+	free_kmem_cache_nodes(s);
+}
+
 static int init_kmem_cache_nodes(struct kmem_cache *s)
 {
 	int node;
@@ -3285,7 +3311,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 		 */
 		size += 2 * sizeof(struct track);
 
-	if (flags & SLAB_RED_ZONE)
+	if (flags & SLAB_RED_ZONE) {
 		/*
 		 * Add some empty padding so that we can catch
 		 * overwrites from earlier objects rather than let
@@ -3294,6 +3320,11 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 		 * of the object.
 		 */
 		size += sizeof(void *);
+
+		s->red_left_pad = sizeof(void *);
+		s->red_left_pad = ALIGN(s->red_left_pad, s->align);
+		size += s->red_left_pad;
+	}
 #endif
 
 	/*
@@ -3357,7 +3388,7 @@ static int kmem_cache_open(struct kmem_cache *s, unsigned long flags)
 
 #if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
     defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
-	if (system_has_cmpxchg_double() && (s->flags & SLAB_DEBUG_FLAGS) == 0)
+	if (system_has_cmpxchg_double() && (s->flags & SLAB_NO_CMPXCHG) == 0)
 		/* Enable fast mode */
 		s->flags |= __CMPXCHG_DOUBLE;
 #endif
@@ -3443,28 +3474,31 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
 
 /*
  * Attempt to free all partial slabs on a node.
- * This is called from kmem_cache_close(). We must be the last thread
- * using the cache and therefore we do not need to lock anymore.
+ * This is called from __kmem_cache_shutdown(). We must take list_lock
+ * because sysfs file might still access partial list after the shutdowning.
  */
 static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
 {
 	struct page *page, *h;
 
+	BUG_ON(irqs_disabled());
+	spin_lock_irq(&n->list_lock);
 	list_for_each_entry_safe(page, h, &n->partial, lru) {
 		if (!page->inuse) {
-			__remove_partial(n, page);
+			remove_partial(n, page);
 			discard_slab(s, page);
 		} else {
 			list_slab_objects(s, page,
-			"Objects remaining in %s on kmem_cache_close()");
+			"Objects remaining in %s on __kmem_cache_shutdown()");
 		}
 	}
+	spin_unlock_irq(&n->list_lock);
 }
 
 /*
  * Release all resources used by a slab cache.
  */
-static inline int kmem_cache_close(struct kmem_cache *s)
+int __kmem_cache_shutdown(struct kmem_cache *s)
 {
 	int node;
 	struct kmem_cache_node *n;
@@ -3476,16 +3510,9 @@ static inline int kmem_cache_close(struct kmem_cache *s)
 		if (n->nr_partial || slabs_node(s, node))
 			return 1;
 	}
-	free_percpu(s->cpu_slab);
-	free_kmem_cache_nodes(s);
 	return 0;
 }
 
-int __kmem_cache_shutdown(struct kmem_cache *s)
-{
-	return kmem_cache_close(s);
-}
-
 /********************************************************************
  *		Kmalloc subsystem
  *******************************************************************/
@@ -3980,7 +4007,7 @@ int __kmem_cache_create(struct kmem_cache *s, unsigned long flags)
 	memcg_propagate_slab_attrs(s);
 	err = sysfs_slab_add(s);
 	if (err)
-		kmem_cache_close(s);
+		__kmem_cache_release(s);
 
 	return err;
 }
@@ -4816,16 +4843,16 @@ SLAB_ATTR_RO(total_objects);
 
 static ssize_t sanity_checks_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", !!(s->flags & SLAB_DEBUG_FREE));
+	return sprintf(buf, "%d\n", !!(s->flags & SLAB_CONSISTENCY_CHECKS));
 }
 
 static ssize_t sanity_checks_store(struct kmem_cache *s,
 				const char *buf, size_t length)
 {
-	s->flags &= ~SLAB_DEBUG_FREE;
+	s->flags &= ~SLAB_CONSISTENCY_CHECKS;
 	if (buf[0] == '1') {
 		s->flags &= ~__CMPXCHG_DOUBLE;
-		s->flags |= SLAB_DEBUG_FREE;
+		s->flags |= SLAB_CONSISTENCY_CHECKS;
 	}
 	return length;
 }
@@ -4869,7 +4896,6 @@ static ssize_t red_zone_store(struct kmem_cache *s,
 
 	s->flags &= ~SLAB_RED_ZONE;
 	if (buf[0] == '1') {
-		s->flags &= ~__CMPXCHG_DOUBLE;
 		s->flags |= SLAB_RED_ZONE;
 	}
 	calculate_sizes(s, -1);
@@ -4890,7 +4916,6 @@ static ssize_t poison_store(struct kmem_cache *s,
 
 	s->flags &= ~SLAB_POISON;
 	if (buf[0] == '1') {
-		s->flags &= ~__CMPXCHG_DOUBLE;
 		s->flags |= SLAB_POISON;
 	}
 	calculate_sizes(s, -1);
@@ -5360,7 +5385,7 @@ static char *create_unique_id(struct kmem_cache *s)
 		*p++ = 'd';
 	if (s->flags & SLAB_RECLAIM_ACCOUNT)
 		*p++ = 'a';
-	if (s->flags & SLAB_DEBUG_FREE)
+	if (s->flags & SLAB_CONSISTENCY_CHECKS)
 		*p++ = 'F';
 	if (!(s->flags & SLAB_NOTRACK))
 		*p++ = 't';
diff --git a/mm/truncate.c b/mm/truncate.c
index e3ee0e27cd17..7598b552ae03 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -519,7 +519,6 @@ EXPORT_SYMBOL(invalidate_mapping_pages);
 static int
 invalidate_complete_page2(struct address_space *mapping, struct page *page)
 {
-	struct mem_cgroup *memcg;
 	unsigned long flags;
 
 	if (page->mapping != mapping)
@@ -528,15 +527,13 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 	if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL))
 		return 0;
 
-	memcg = mem_cgroup_begin_page_stat(page);
 	spin_lock_irqsave(&mapping->tree_lock, flags);
 	if (PageDirty(page))
 		goto failed;
 
 	BUG_ON(page_has_private(page));
-	__delete_from_page_cache(page, NULL, memcg);
+	__delete_from_page_cache(page, NULL);
 	spin_unlock_irqrestore(&mapping->tree_lock, flags);
-	mem_cgroup_end_page_stat(memcg);
 
 	if (mapping->a_ops->freepage)
 		mapping->a_ops->freepage(page);
@@ -545,7 +542,6 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 	return 1;
 failed:
 	spin_unlock_irqrestore(&mapping->tree_lock, flags);
-	mem_cgroup_end_page_stat(memcg);
 	return 0;
 }
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 71b1c29948db..dd984470248f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -195,25 +195,25 @@ static unsigned long zone_reclaimable_pages(struct zone *zone)
 {
 	unsigned long nr;
 
-	nr = zone_page_state(zone, NR_ACTIVE_FILE) +
-	     zone_page_state(zone, NR_INACTIVE_FILE) +
-	     zone_page_state(zone, NR_ISOLATED_FILE);
+	nr = zone_page_state_snapshot(zone, NR_ACTIVE_FILE) +
+	     zone_page_state_snapshot(zone, NR_INACTIVE_FILE) +
+	     zone_page_state_snapshot(zone, NR_ISOLATED_FILE);
 
 	if (get_nr_swap_pages() > 0)
-		nr += zone_page_state(zone, NR_ACTIVE_ANON) +
-		      zone_page_state(zone, NR_INACTIVE_ANON) +
-		      zone_page_state(zone, NR_ISOLATED_ANON);
+		nr += zone_page_state_snapshot(zone, NR_ACTIVE_ANON) +
+		      zone_page_state_snapshot(zone, NR_INACTIVE_ANON) +
+		      zone_page_state_snapshot(zone, NR_ISOLATED_ANON);
 
 	return nr;
 }
 
 bool zone_reclaimable(struct zone *zone)
 {
-	return zone_page_state(zone, NR_PAGES_SCANNED) <
+	return zone_page_state_snapshot(zone, NR_PAGES_SCANNED) <
 		zone_reclaimable_pages(zone) * 6;
 }
 
-static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru)
+unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru)
 {
 	if (!mem_cgroup_disabled())
 		return mem_cgroup_get_lru_size(lruvec, lru);
@@ -228,14 +228,6 @@ int register_shrinker(struct shrinker *shrinker)
 {
 	size_t size = sizeof(*shrinker->nr_deferred);
 
-	/*
-	 * If we only have one possible node in the system anyway, save
-	 * ourselves the trouble and disable NUMA aware behavior. This way we
-	 * will save memory and some small loop time later.
-	 */
-	if (nr_node_ids == 1)
-		shrinker->flags &= ~SHRINKER_NUMA_AWARE;
-
 	if (shrinker->flags & SHRINKER_NUMA_AWARE)
 		size *= nr_node_ids;
 
@@ -611,12 +603,10 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 			    bool reclaimed)
 {
 	unsigned long flags;
-	struct mem_cgroup *memcg;
 
 	BUG_ON(!PageLocked(page));
 	BUG_ON(mapping != page_mapping(page));
 
-	memcg = mem_cgroup_begin_page_stat(page);
 	spin_lock_irqsave(&mapping->tree_lock, flags);
 	/*
 	 * The non racy check for a busy page.
@@ -656,7 +646,6 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 		mem_cgroup_swapout(page, swap);
 		__delete_from_swap_cache(page);
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
-		mem_cgroup_end_page_stat(memcg);
 		swapcache_free(swap);
 	} else {
 		void (*freepage)(struct page *);
@@ -682,9 +671,8 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 		if (reclaimed && page_is_file_cache(page) &&
 		    !mapping_exiting(mapping) && !dax_mapping(mapping))
 			shadow = workingset_eviction(mapping, page);
-		__delete_from_page_cache(page, shadow, memcg);
+		__delete_from_page_cache(page, shadow);
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
-		mem_cgroup_end_page_stat(memcg);
 
 		if (freepage != NULL)
 			freepage(page);
@@ -694,7 +682,6 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 
 cannot_free:
 	spin_unlock_irqrestore(&mapping->tree_lock, flags);
-	mem_cgroup_end_page_stat(memcg);
 	return 0;
 }
 
@@ -1931,8 +1918,8 @@ static bool inactive_file_is_low(struct lruvec *lruvec)
 	unsigned long inactive;
 	unsigned long active;
 
-	inactive = get_lru_size(lruvec, LRU_INACTIVE_FILE);
-	active = get_lru_size(lruvec, LRU_ACTIVE_FILE);
+	inactive = lruvec_lru_size(lruvec, LRU_INACTIVE_FILE);
+	active = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE);
 
 	return active > inactive;
 }
@@ -2071,7 +2058,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	 * system is under heavy pressure.
 	 */
 	if (!inactive_file_is_low(lruvec) &&
-	    get_lru_size(lruvec, LRU_INACTIVE_FILE) >> sc->priority) {
+	    lruvec_lru_size(lruvec, LRU_INACTIVE_FILE) >> sc->priority) {
 		scan_balance = SCAN_FILE;
 		goto out;
 	}
@@ -2097,10 +2084,10 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	 * anon in [0], file in [1]
 	 */
 
-	anon  = get_lru_size(lruvec, LRU_ACTIVE_ANON) +
-		get_lru_size(lruvec, LRU_INACTIVE_ANON);
-	file  = get_lru_size(lruvec, LRU_ACTIVE_FILE) +
-		get_lru_size(lruvec, LRU_INACTIVE_FILE);
+	anon  = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON) +
+		lruvec_lru_size(lruvec, LRU_INACTIVE_ANON);
+	file  = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE) +
+		lruvec_lru_size(lruvec, LRU_INACTIVE_FILE);
 
 	spin_lock_irq(&zone->lru_lock);
 	if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
@@ -2138,7 +2125,7 @@ out:
 			unsigned long size;
 			unsigned long scan;
 
-			size = get_lru_size(lruvec, lru);
+			size = lruvec_lru_size(lruvec, lru);
 			scan = size >> sc->priority;
 
 			if (!scan && pass && force_scan)
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 084c6725b373..69ce64f7b8d7 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -924,19 +924,6 @@ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat,
 #endif
 
 #ifdef CONFIG_PROC_FS
-static char * const migratetype_names[MIGRATE_TYPES] = {
-	"Unmovable",
-	"Movable",
-	"Reclaimable",
-	"HighAtomic",
-#ifdef CONFIG_CMA
-	"CMA",
-#endif
-#ifdef CONFIG_MEMORY_ISOLATION
-	"Isolate",
-#endif
-};
-
 static void frag_show_print(struct seq_file *m, pg_data_t *pgdat,
 						struct zone *zone)
 {
@@ -1133,7 +1120,7 @@ static void pagetypeinfo_showmixedcount(struct seq_file *m, pg_data_t *pgdat)
 #ifdef CONFIG_PAGE_OWNER
 	int mtype;
 
-	if (!page_owner_inited)
+	if (!static_branch_unlikely(&page_owner_inited))
 		return;
 
 	drain_all_pages(NULL);
diff --git a/mm/workingset.c b/mm/workingset.c
index 61ead9e5549d..6130ba0b2641 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -152,8 +152,25 @@
  * refault distance will immediately activate the refaulting page.
  */
 
-static void *pack_shadow(unsigned long eviction, struct zone *zone)
+#define EVICTION_SHIFT	(RADIX_TREE_EXCEPTIONAL_ENTRY + \
+			 ZONES_SHIFT + NODES_SHIFT +	\
+			 MEM_CGROUP_ID_SHIFT)
+#define EVICTION_MASK	(~0UL >> EVICTION_SHIFT)
+
+/*
+ * Eviction timestamps need to be able to cover the full range of
+ * actionable refaults. However, bits are tight in the radix tree
+ * entry, and after storing the identifier for the lruvec there might
+ * not be enough left to represent every single actionable refault. In
+ * that case, we have to sacrifice granularity for distance, and group
+ * evictions into coarser buckets by shaving off lower timestamp bits.
+ */
+static unsigned int bucket_order __read_mostly;
+
+static void *pack_shadow(int memcgid, struct zone *zone, unsigned long eviction)
 {
+	eviction >>= bucket_order;
+	eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
 	eviction = (eviction << NODES_SHIFT) | zone_to_nid(zone);
 	eviction = (eviction << ZONES_SHIFT) | zone_idx(zone);
 	eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT);
@@ -161,45 +178,23 @@ static void *pack_shadow(unsigned long eviction, struct zone *zone)
 	return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY);
 }
 
-static void unpack_shadow(void *shadow,
-			  struct zone **zone,
-			  unsigned long *distance)
+static void unpack_shadow(void *shadow, int *memcgidp, struct zone **zonep,
+			  unsigned long *evictionp)
 {
 	unsigned long entry = (unsigned long)shadow;
-	unsigned long eviction;
-	unsigned long refault;
-	unsigned long mask;
-	int zid, nid;
+	int memcgid, nid, zid;
 
 	entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT;
 	zid = entry & ((1UL << ZONES_SHIFT) - 1);
 	entry >>= ZONES_SHIFT;
 	nid = entry & ((1UL << NODES_SHIFT) - 1);
 	entry >>= NODES_SHIFT;
-	eviction = entry;
+	memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1);
+	entry >>= MEM_CGROUP_ID_SHIFT;
 
-	*zone = NODE_DATA(nid)->node_zones + zid;
-
-	refault = atomic_long_read(&(*zone)->inactive_age);
-	mask = ~0UL >> (NODES_SHIFT + ZONES_SHIFT +
-			RADIX_TREE_EXCEPTIONAL_SHIFT);
-	/*
-	 * The unsigned subtraction here gives an accurate distance
-	 * across inactive_age overflows in most cases.
-	 *
-	 * There is a special case: usually, shadow entries have a
-	 * short lifetime and are either refaulted or reclaimed along
-	 * with the inode before they get too old.  But it is not
-	 * impossible for the inactive_age to lap a shadow entry in
-	 * the field, which can then can result in a false small
-	 * refault distance, leading to a false activation should this
-	 * old entry actually refault again.  However, earlier kernels
-	 * used to deactivate unconditionally with *every* reclaim
-	 * invocation for the longest time, so the occasional
-	 * inappropriate activation leading to pressure on the active
-	 * list is not a problem.
-	 */
-	*distance = (refault - eviction) & mask;
+	*memcgidp = memcgid;
+	*zonep = NODE_DATA(nid)->node_zones + zid;
+	*evictionp = entry << bucket_order;
 }
 
 /**
@@ -212,11 +207,20 @@ static void unpack_shadow(void *shadow,
  */
 void *workingset_eviction(struct address_space *mapping, struct page *page)
 {
+	struct mem_cgroup *memcg = page_memcg(page);
 	struct zone *zone = page_zone(page);
+	int memcgid = mem_cgroup_id(memcg);
 	unsigned long eviction;
+	struct lruvec *lruvec;
 
-	eviction = atomic_long_inc_return(&zone->inactive_age);
-	return pack_shadow(eviction, zone);
+	/* Page is fully exclusive and pins page->mem_cgroup */
+	VM_BUG_ON_PAGE(PageLRU(page), page);
+	VM_BUG_ON_PAGE(page_count(page), page);
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+
+	lruvec = mem_cgroup_zone_lruvec(zone, memcg);
+	eviction = atomic_long_inc_return(&lruvec->inactive_age);
+	return pack_shadow(memcgid, zone, eviction);
 }
 
 /**
@@ -231,12 +235,64 @@ void *workingset_eviction(struct address_space *mapping, struct page *page)
 bool workingset_refault(void *shadow)
 {
 	unsigned long refault_distance;
+	unsigned long active_file;
+	struct mem_cgroup *memcg;
+	unsigned long eviction;
+	struct lruvec *lruvec;
+	unsigned long refault;
 	struct zone *zone;
+	int memcgid;
+
+	unpack_shadow(shadow, &memcgid, &zone, &eviction);
+
+	rcu_read_lock();
+	/*
+	 * Look up the memcg associated with the stored ID. It might
+	 * have been deleted since the page's eviction.
+	 *
+	 * Note that in rare events the ID could have been recycled
+	 * for a new cgroup that refaults a shared page. This is
+	 * impossible to tell from the available data. However, this
+	 * should be a rare and limited disturbance, and activations
+	 * are always speculative anyway. Ultimately, it's the aging
+	 * algorithm's job to shake out the minimum access frequency
+	 * for the active cache.
+	 *
+	 * XXX: On !CONFIG_MEMCG, this will always return NULL; it
+	 * would be better if the root_mem_cgroup existed in all
+	 * configurations instead.
+	 */
+	memcg = mem_cgroup_from_id(memcgid);
+	if (!mem_cgroup_disabled() && !memcg) {
+		rcu_read_unlock();
+		return false;
+	}
+	lruvec = mem_cgroup_zone_lruvec(zone, memcg);
+	refault = atomic_long_read(&lruvec->inactive_age);
+	active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE);
+	rcu_read_unlock();
+
+	/*
+	 * The unsigned subtraction here gives an accurate distance
+	 * across inactive_age overflows in most cases.
+	 *
+	 * There is a special case: usually, shadow entries have a
+	 * short lifetime and are either refaulted or reclaimed along
+	 * with the inode before they get too old.  But it is not
+	 * impossible for the inactive_age to lap a shadow entry in
+	 * the field, which can then can result in a false small
+	 * refault distance, leading to a false activation should this
+	 * old entry actually refault again.  However, earlier kernels
+	 * used to deactivate unconditionally with *every* reclaim
+	 * invocation for the longest time, so the occasional
+	 * inappropriate activation leading to pressure on the active
+	 * list is not a problem.
+	 */
+	refault_distance = (refault - eviction) & EVICTION_MASK;
 
-	unpack_shadow(shadow, &zone, &refault_distance);
 	inc_zone_state(zone, WORKINGSET_REFAULT);
 
-	if (refault_distance <= zone_page_state(zone, NR_ACTIVE_FILE)) {
+	if (refault_distance <= active_file) {
 		inc_zone_state(zone, WORKINGSET_ACTIVATE);
 		return true;
 	}
@@ -249,7 +305,22 @@ bool workingset_refault(void *shadow)
  */
 void workingset_activation(struct page *page)
 {
-	atomic_long_inc(&page_zone(page)->inactive_age);
+	struct lruvec *lruvec;
+
+	lock_page_memcg(page);
+	/*
+	 * Filter non-memcg pages here, e.g. unmap can call
+	 * mark_page_accessed() on VDSO pages.
+	 *
+	 * XXX: See workingset_refault() - this should return
+	 * root_mem_cgroup even for !CONFIG_MEMCG.
+	 */
+	if (!mem_cgroup_disabled() && !page_memcg(page))
+		goto out;
+	lruvec = mem_cgroup_zone_lruvec(page_zone(page), page_memcg(page));
+	atomic_long_inc(&lruvec->inactive_age);
+out:
+	unlock_page_memcg(page);
 }
 
 /*
@@ -398,8 +469,25 @@ static struct lock_class_key shadow_nodes_key;
 
 static int __init workingset_init(void)
 {
+	unsigned int timestamp_bits;
+	unsigned int max_order;
 	int ret;
 
+	BUILD_BUG_ON(BITS_PER_LONG < EVICTION_SHIFT);
+	/*
+	 * Calculate the eviction bucket size to cover the longest
+	 * actionable refault distance, which is currently half of
+	 * memory (totalram_pages/2). However, memory hotplug may add
+	 * some more pages at runtime, so keep working with up to
+	 * double the initial memory by using totalram_pages as-is.
+	 */
+	timestamp_bits = BITS_PER_LONG - EVICTION_SHIFT;
+	max_order = fls_long(totalram_pages - 1);
+	if (max_order > timestamp_bits)
+		bucket_order = max_order - timestamp_bits;
+	printk("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n",
+	       timestamp_bits, max_order, bucket_order);
+
 	ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key);
 	if (ret)
 		goto err;
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index d5871ac493eb..f066781be3c8 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1625,7 +1625,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 
 		rt = atrtr_find(&at_hint);
 	}
-	err = ENETUNREACH;
+	err = -ENETUNREACH;
 	if (!rt)
 		goto out;
 
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index e6c8382c79ba..ccf70bed0d0c 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -527,11 +527,12 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv,
 		 * gets dereferenced.
 		 */
 		spin_lock_bh(&bat_priv->gw.list_lock);
-		hlist_del_init_rcu(&gw_node->list);
+		if (!hlist_unhashed(&gw_node->list)) {
+			hlist_del_init_rcu(&gw_node->list);
+			batadv_gw_node_free_ref(gw_node);
+		}
 		spin_unlock_bh(&bat_priv->gw.list_lock);
 
-		batadv_gw_node_free_ref(gw_node);
-
 		curr_gw = batadv_gw_get_selected_gw_node(bat_priv);
 		if (gw_node == curr_gw)
 			batadv_gw_reselect(bat_priv);
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 01acccc4d218..57f7107169f5 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -76,6 +76,28 @@ out:
 }
 
 /**
+ * batadv_mutual_parents - check if two devices are each others parent
+ * @dev1: 1st net_device
+ * @dev2: 2nd net_device
+ *
+ * veth devices come in pairs and each is the parent of the other!
+ *
+ * Return: true if the devices are each others parent, otherwise false
+ */
+static bool batadv_mutual_parents(const struct net_device *dev1,
+				  const struct net_device *dev2)
+{
+	int dev1_parent_iflink = dev_get_iflink(dev1);
+	int dev2_parent_iflink = dev_get_iflink(dev2);
+
+	if (!dev1_parent_iflink || !dev2_parent_iflink)
+		return false;
+
+	return (dev1_parent_iflink == dev2->ifindex) &&
+	       (dev2_parent_iflink == dev1->ifindex);
+}
+
+/**
  * batadv_is_on_batman_iface - check if a device is a batman iface descendant
  * @net_dev: the device to check
  *
@@ -108,6 +130,9 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev)
 	if (WARN(!parent_dev, "Cannot find parent device"))
 		return false;
 
+	if (batadv_mutual_parents(net_dev, parent_dev))
+		return false;
+
 	ret = batadv_is_on_batman_iface(parent_dev);
 
 	return ret;
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index cdfc85fa2743..0e80fd1461ab 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -303,9 +303,11 @@ static void batadv_tt_global_size_mod(struct batadv_orig_node *orig_node,
 
 	if (atomic_add_return(v, &vlan->tt.num_entries) == 0) {
 		spin_lock_bh(&orig_node->vlan_list_lock);
-		hlist_del_init_rcu(&vlan->list);
+		if (!hlist_unhashed(&vlan->list)) {
+			hlist_del_init_rcu(&vlan->list);
+			batadv_orig_node_vlan_free_ref(vlan);
+		}
 		spin_unlock_bh(&orig_node->vlan_list_lock);
-		batadv_orig_node_vlan_free_ref(vlan);
 	}
 
 	batadv_orig_node_vlan_free_ref(vlan);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 47bcef754796..883c821a9e78 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -4112,8 +4112,10 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status,
 			break;
 		}
 
-		*req_complete = bt_cb(skb)->hci.req_complete;
-		*req_complete_skb = bt_cb(skb)->hci.req_complete_skb;
+		if (bt_cb(skb)->hci.req_flags & HCI_REQ_SKB)
+			*req_complete_skb = bt_cb(skb)->hci.req_complete_skb;
+		else
+			*req_complete = bt_cb(skb)->hci.req_complete;
 		kfree_skb(skb);
 	}
 	spin_unlock_irqrestore(&hdev->cmd_q.lock, flags);
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 4b175df35184..50976a6481f3 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -21,9 +21,10 @@
 */
 
 #include <linux/debugfs.h>
-#include <linux/crypto.h>
 #include <linux/scatterlist.h>
 #include <crypto/b128ops.h>
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
@@ -87,8 +88,8 @@ struct smp_dev {
 	u8			min_key_size;
 	u8			max_key_size;
 
-	struct crypto_blkcipher	*tfm_aes;
-	struct crypto_hash	*tfm_cmac;
+	struct crypto_skcipher	*tfm_aes;
+	struct crypto_shash	*tfm_cmac;
 };
 
 struct smp_chan {
@@ -126,8 +127,8 @@ struct smp_chan {
 	u8			dhkey[32];
 	u8			mackey[16];
 
-	struct crypto_blkcipher	*tfm_aes;
-	struct crypto_hash	*tfm_cmac;
+	struct crypto_skcipher	*tfm_aes;
+	struct crypto_shash	*tfm_cmac;
 };
 
 /* These debug key values are defined in the SMP section of the core
@@ -165,12 +166,11 @@ static inline void swap_buf(const u8 *src, u8 *dst, size_t len)
  * AES-CMAC, f4, f5, f6, g2 and h6.
  */
 
-static int aes_cmac(struct crypto_hash *tfm, const u8 k[16], const u8 *m,
+static int aes_cmac(struct crypto_shash *tfm, const u8 k[16], const u8 *m,
 		    size_t len, u8 mac[16])
 {
 	uint8_t tmp[16], mac_msb[16], msg_msb[CMAC_MSG_MAX];
-	struct hash_desc desc;
-	struct scatterlist sg;
+	SHASH_DESC_ON_STACK(desc, tfm);
 	int err;
 
 	if (len > CMAC_MSG_MAX)
@@ -181,10 +181,8 @@ static int aes_cmac(struct crypto_hash *tfm, const u8 k[16], const u8 *m,
 		return -EINVAL;
 	}
 
-	desc.tfm = tfm;
-	desc.flags = 0;
-
-	crypto_hash_init(&desc);
+	desc->tfm = tfm;
+	desc->flags = 0;
 
 	/* Swap key and message from LSB to MSB */
 	swap_buf(k, tmp, 16);
@@ -193,23 +191,16 @@ static int aes_cmac(struct crypto_hash *tfm, const u8 k[16], const u8 *m,
 	SMP_DBG("msg (len %zu) %*phN", len, (int) len, m);
 	SMP_DBG("key %16phN", k);
 
-	err = crypto_hash_setkey(tfm, tmp, 16);
+	err = crypto_shash_setkey(tfm, tmp, 16);
 	if (err) {
 		BT_ERR("cipher setkey failed: %d", err);
 		return err;
 	}
 
-	sg_init_one(&sg, msg_msb, len);
-
-	err = crypto_hash_update(&desc, &sg, len);
+	err = crypto_shash_digest(desc, msg_msb, len, mac_msb);
+	shash_desc_zero(desc);
 	if (err) {
-		BT_ERR("Hash update error %d", err);
-		return err;
-	}
-
-	err = crypto_hash_final(&desc, mac_msb);
-	if (err) {
-		BT_ERR("Hash final error %d", err);
+		BT_ERR("Hash computation error %d", err);
 		return err;
 	}
 
@@ -220,8 +211,8 @@ static int aes_cmac(struct crypto_hash *tfm, const u8 k[16], const u8 *m,
 	return 0;
 }
 
-static int smp_f4(struct crypto_hash *tfm_cmac, const u8 u[32], const u8 v[32],
-		  const u8 x[16], u8 z, u8 res[16])
+static int smp_f4(struct crypto_shash *tfm_cmac, const u8 u[32],
+		  const u8 v[32], const u8 x[16], u8 z, u8 res[16])
 {
 	u8 m[65];
 	int err;
@@ -243,7 +234,7 @@ static int smp_f4(struct crypto_hash *tfm_cmac, const u8 u[32], const u8 v[32],
 	return err;
 }
 
-static int smp_f5(struct crypto_hash *tfm_cmac, const u8 w[32],
+static int smp_f5(struct crypto_shash *tfm_cmac, const u8 w[32],
 		  const u8 n1[16], const u8 n2[16], const u8 a1[7],
 		  const u8 a2[7], u8 mackey[16], u8 ltk[16])
 {
@@ -296,7 +287,7 @@ static int smp_f5(struct crypto_hash *tfm_cmac, const u8 w[32],
 	return 0;
 }
 
-static int smp_f6(struct crypto_hash *tfm_cmac, const u8 w[16],
+static int smp_f6(struct crypto_shash *tfm_cmac, const u8 w[16],
 		  const u8 n1[16], const u8 n2[16], const u8 r[16],
 		  const u8 io_cap[3], const u8 a1[7], const u8 a2[7],
 		  u8 res[16])
@@ -324,7 +315,7 @@ static int smp_f6(struct crypto_hash *tfm_cmac, const u8 w[16],
 	return err;
 }
 
-static int smp_g2(struct crypto_hash *tfm_cmac, const u8 u[32], const u8 v[32],
+static int smp_g2(struct crypto_shash *tfm_cmac, const u8 u[32], const u8 v[32],
 		  const u8 x[16], const u8 y[16], u32 *val)
 {
 	u8 m[80], tmp[16];
@@ -350,7 +341,7 @@ static int smp_g2(struct crypto_hash *tfm_cmac, const u8 u[32], const u8 v[32],
 	return 0;
 }
 
-static int smp_h6(struct crypto_hash *tfm_cmac, const u8 w[16],
+static int smp_h6(struct crypto_shash *tfm_cmac, const u8 w[16],
 		  const u8 key_id[4], u8 res[16])
 {
 	int err;
@@ -370,9 +361,9 @@ static int smp_h6(struct crypto_hash *tfm_cmac, const u8 w[16],
  * s1 and ah.
  */
 
-static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r)
+static int smp_e(struct crypto_skcipher *tfm, const u8 *k, u8 *r)
 {
-	struct blkcipher_desc desc;
+	SKCIPHER_REQUEST_ON_STACK(req, tfm);
 	struct scatterlist sg;
 	uint8_t tmp[16], data[16];
 	int err;
@@ -384,13 +375,10 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r)
 		return -EINVAL;
 	}
 
-	desc.tfm = tfm;
-	desc.flags = 0;
-
 	/* The most significant octet of key corresponds to k[0] */
 	swap_buf(k, tmp, 16);
 
-	err = crypto_blkcipher_setkey(tfm, tmp, 16);
+	err = crypto_skcipher_setkey(tfm, tmp, 16);
 	if (err) {
 		BT_ERR("cipher setkey failed: %d", err);
 		return err;
@@ -401,7 +389,12 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r)
 
 	sg_init_one(&sg, data, 16);
 
-	err = crypto_blkcipher_encrypt(&desc, &sg, &sg, 16);
+	skcipher_request_set_tfm(req, tfm);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, &sg, &sg, 16, NULL);
+
+	err = crypto_skcipher_encrypt(req);
+	skcipher_request_zero(req);
 	if (err)
 		BT_ERR("Encrypt data error %d", err);
 
@@ -413,7 +406,7 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r)
 	return err;
 }
 
-static int smp_c1(struct crypto_blkcipher *tfm_aes, const u8 k[16],
+static int smp_c1(struct crypto_skcipher *tfm_aes, const u8 k[16],
 		  const u8 r[16], const u8 preq[7], const u8 pres[7], u8 _iat,
 		  const bdaddr_t *ia, u8 _rat, const bdaddr_t *ra, u8 res[16])
 {
@@ -462,7 +455,7 @@ static int smp_c1(struct crypto_blkcipher *tfm_aes, const u8 k[16],
 	return err;
 }
 
-static int smp_s1(struct crypto_blkcipher *tfm_aes, const u8 k[16],
+static int smp_s1(struct crypto_skcipher *tfm_aes, const u8 k[16],
 		  const u8 r1[16], const u8 r2[16], u8 _r[16])
 {
 	int err;
@@ -478,7 +471,7 @@ static int smp_s1(struct crypto_blkcipher *tfm_aes, const u8 k[16],
 	return err;
 }
 
-static int smp_ah(struct crypto_blkcipher *tfm, const u8 irk[16],
+static int smp_ah(struct crypto_skcipher *tfm, const u8 irk[16],
 		  const u8 r[3], u8 res[3])
 {
 	u8 _res[16];
@@ -766,8 +759,8 @@ static void smp_chan_destroy(struct l2cap_conn *conn)
 	kzfree(smp->slave_csrk);
 	kzfree(smp->link_key);
 
-	crypto_free_blkcipher(smp->tfm_aes);
-	crypto_free_hash(smp->tfm_cmac);
+	crypto_free_skcipher(smp->tfm_aes);
+	crypto_free_shash(smp->tfm_cmac);
 
 	/* Ensure that we don't leave any debug key around if debug key
 	 * support hasn't been explicitly enabled.
@@ -1366,17 +1359,17 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
 	if (!smp)
 		return NULL;
 
-	smp->tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC);
+	smp->tfm_aes = crypto_alloc_skcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(smp->tfm_aes)) {
 		BT_ERR("Unable to create ECB crypto context");
 		kzfree(smp);
 		return NULL;
 	}
 
-	smp->tfm_cmac = crypto_alloc_hash("cmac(aes)", 0, CRYPTO_ALG_ASYNC);
+	smp->tfm_cmac = crypto_alloc_shash("cmac(aes)", 0, 0);
 	if (IS_ERR(smp->tfm_cmac)) {
 		BT_ERR("Unable to create CMAC crypto context");
-		crypto_free_blkcipher(smp->tfm_aes);
+		crypto_free_skcipher(smp->tfm_aes);
 		kzfree(smp);
 		return NULL;
 	}
@@ -3127,8 +3120,8 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid)
 {
 	struct l2cap_chan *chan;
 	struct smp_dev *smp;
-	struct crypto_blkcipher *tfm_aes;
-	struct crypto_hash *tfm_cmac;
+	struct crypto_skcipher *tfm_aes;
+	struct crypto_shash *tfm_cmac;
 
 	if (cid == L2CAP_CID_SMP_BREDR) {
 		smp = NULL;
@@ -3139,17 +3132,17 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid)
 	if (!smp)
 		return ERR_PTR(-ENOMEM);
 
-	tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC);
+	tfm_aes = crypto_alloc_skcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm_aes)) {
 		BT_ERR("Unable to create ECB crypto context");
 		kzfree(smp);
 		return ERR_CAST(tfm_aes);
 	}
 
-	tfm_cmac = crypto_alloc_hash("cmac(aes)", 0, CRYPTO_ALG_ASYNC);
+	tfm_cmac = crypto_alloc_shash("cmac(aes)", 0, 0);
 	if (IS_ERR(tfm_cmac)) {
 		BT_ERR("Unable to create CMAC crypto context");
-		crypto_free_blkcipher(tfm_aes);
+		crypto_free_skcipher(tfm_aes);
 		kzfree(smp);
 		return ERR_CAST(tfm_cmac);
 	}
@@ -3163,8 +3156,8 @@ create_chan:
 	chan = l2cap_chan_create();
 	if (!chan) {
 		if (smp) {
-			crypto_free_blkcipher(smp->tfm_aes);
-			crypto_free_hash(smp->tfm_cmac);
+			crypto_free_skcipher(smp->tfm_aes);
+			crypto_free_shash(smp->tfm_cmac);
 			kzfree(smp);
 		}
 		return ERR_PTR(-ENOMEM);
@@ -3210,10 +3203,8 @@ static void smp_del_chan(struct l2cap_chan *chan)
 	smp = chan->data;
 	if (smp) {
 		chan->data = NULL;
-		if (smp->tfm_aes)
-			crypto_free_blkcipher(smp->tfm_aes);
-		if (smp->tfm_cmac)
-			crypto_free_hash(smp->tfm_cmac);
+		crypto_free_skcipher(smp->tfm_aes);
+		crypto_free_shash(smp->tfm_cmac);
 		kzfree(smp);
 	}
 
@@ -3449,7 +3440,7 @@ void smp_unregister(struct hci_dev *hdev)
 
 #if IS_ENABLED(CONFIG_BT_SELFTEST_SMP)
 
-static int __init test_ah(struct crypto_blkcipher *tfm_aes)
+static int __init test_ah(struct crypto_skcipher *tfm_aes)
 {
 	const u8 irk[16] = {
 			0x9b, 0x7d, 0x39, 0x0a, 0xa6, 0x10, 0x10, 0x34,
@@ -3469,7 +3460,7 @@ static int __init test_ah(struct crypto_blkcipher *tfm_aes)
 	return 0;
 }
 
-static int __init test_c1(struct crypto_blkcipher *tfm_aes)
+static int __init test_c1(struct crypto_skcipher *tfm_aes)
 {
 	const u8 k[16] = {
 			0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
@@ -3499,7 +3490,7 @@ static int __init test_c1(struct crypto_blkcipher *tfm_aes)
 	return 0;
 }
 
-static int __init test_s1(struct crypto_blkcipher *tfm_aes)
+static int __init test_s1(struct crypto_skcipher *tfm_aes)
 {
 	const u8 k[16] = {
 			0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
@@ -3524,7 +3515,7 @@ static int __init test_s1(struct crypto_blkcipher *tfm_aes)
 	return 0;
 }
 
-static int __init test_f4(struct crypto_hash *tfm_cmac)
+static int __init test_f4(struct crypto_shash *tfm_cmac)
 {
 	const u8 u[32] = {
 			0xe6, 0x9d, 0x35, 0x0e, 0x48, 0x01, 0x03, 0xcc,
@@ -3556,7 +3547,7 @@ static int __init test_f4(struct crypto_hash *tfm_cmac)
 	return 0;
 }
 
-static int __init test_f5(struct crypto_hash *tfm_cmac)
+static int __init test_f5(struct crypto_shash *tfm_cmac)
 {
 	const u8 w[32] = {
 			0x98, 0xa6, 0xbf, 0x73, 0xf3, 0x34, 0x8d, 0x86,
@@ -3593,7 +3584,7 @@ static int __init test_f5(struct crypto_hash *tfm_cmac)
 	return 0;
 }
 
-static int __init test_f6(struct crypto_hash *tfm_cmac)
+static int __init test_f6(struct crypto_shash *tfm_cmac)
 {
 	const u8 w[16] = {
 			0x20, 0x6e, 0x63, 0xce, 0x20, 0x6a, 0x3f, 0xfd,
@@ -3626,7 +3617,7 @@ static int __init test_f6(struct crypto_hash *tfm_cmac)
 	return 0;
 }
 
-static int __init test_g2(struct crypto_hash *tfm_cmac)
+static int __init test_g2(struct crypto_shash *tfm_cmac)
 {
 	const u8 u[32] = {
 			0xe6, 0x9d, 0x35, 0x0e, 0x48, 0x01, 0x03, 0xcc,
@@ -3658,7 +3649,7 @@ static int __init test_g2(struct crypto_hash *tfm_cmac)
 	return 0;
 }
 
-static int __init test_h6(struct crypto_hash *tfm_cmac)
+static int __init test_h6(struct crypto_shash *tfm_cmac)
 {
 	const u8 w[16] = {
 			0x9b, 0x7d, 0x39, 0x0a, 0xa6, 0x10, 0x10, 0x34,
@@ -3695,8 +3686,8 @@ static const struct file_operations test_smp_fops = {
 	.llseek		= default_llseek,
 };
 
-static int __init run_selftests(struct crypto_blkcipher *tfm_aes,
-				struct crypto_hash *tfm_cmac)
+static int __init run_selftests(struct crypto_skcipher *tfm_aes,
+				struct crypto_shash *tfm_cmac)
 {
 	ktime_t calltime, delta, rettime;
 	unsigned long long duration;
@@ -3773,27 +3764,27 @@ done:
 
 int __init bt_selftest_smp(void)
 {
-	struct crypto_blkcipher *tfm_aes;
-	struct crypto_hash *tfm_cmac;
+	struct crypto_skcipher *tfm_aes;
+	struct crypto_shash *tfm_cmac;
 	int err;
 
-	tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC);
+	tfm_aes = crypto_alloc_skcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm_aes)) {
 		BT_ERR("Unable to create ECB crypto context");
 		return PTR_ERR(tfm_aes);
 	}
 
-	tfm_cmac = crypto_alloc_hash("cmac(aes)", 0, CRYPTO_ALG_ASYNC);
+	tfm_cmac = crypto_alloc_shash("cmac(aes)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm_cmac)) {
 		BT_ERR("Unable to create CMAC crypto context");
-		crypto_free_blkcipher(tfm_aes);
+		crypto_free_skcipher(tfm_aes);
 		return PTR_ERR(tfm_cmac);
 	}
 
 	err = run_selftests(tfm_aes, tfm_cmac);
 
-	crypto_free_hash(tfm_cmac);
-	crypto_free_blkcipher(tfm_aes);
+	crypto_free_shash(tfm_cmac);
+	crypto_free_skcipher(tfm_aes);
 
 	return err;
 }
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 82e3e9705017..dcea4f4c62b3 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -723,6 +723,8 @@ int br_fdb_dump(struct sk_buff *skb,
 		struct net_bridge_fdb_entry *f;
 
 		hlist_for_each_entry_rcu(f, &br->hash[i], hlist) {
+			int err;
+
 			if (idx < cb->args[0])
 				goto skip;
 
@@ -741,12 +743,15 @@ int br_fdb_dump(struct sk_buff *skb,
 			if (!filter_dev && f->dst)
 				goto skip;
 
-			if (fdb_fill_info(skb, br, f,
-					  NETLINK_CB(cb->skb).portid,
-					  cb->nlh->nlmsg_seq,
-					  RTM_NEWNEIGH,
-					  NLM_F_MULTI) < 0)
+			err = fdb_fill_info(skb, br, f,
+					    NETLINK_CB(cb->skb).portid,
+					    cb->nlh->nlmsg_seq,
+					    RTM_NEWNEIGH,
+					    NLM_F_MULTI);
+			if (err < 0) {
+				cb->args[1] = err;
 				break;
+			}
 skip:
 			++idx;
 		}
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 30e105f57f0d..74c278e00225 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -425,8 +425,8 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 	mp = br_mdb_ip_get(mdb, group);
 	if (!mp) {
 		mp = br_multicast_new_group(br, port, group);
-		err = PTR_ERR(mp);
-		if (IS_ERR(mp))
+		err = PTR_ERR_OR_ZERO(mp);
+		if (err)
 			return err;
 	}
 
diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c
index 61d7617d9249..b82440e1fcb4 100644
--- a/net/caif/cfrfml.c
+++ b/net/caif/cfrfml.c
@@ -159,7 +159,7 @@ static int cfrfml_receive(struct cflayer *layr, struct cfpkt *pkt)
 		tmppkt = NULL;
 
 		/* Verify that length is correct */
-		err = EPROTO;
+		err = -EPROTO;
 		if (rfml->pdu_size != cfpkt_getlen(pkt) - RFM_HEAD_SIZE + 1)
 			goto out;
 	}
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
index 42e8649c6e79..db2847ac5f12 100644
--- a/net/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -4,7 +4,8 @@
 #include <linux/err.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
-#include <crypto/hash.h>
+#include <crypto/aes.h>
+#include <crypto/skcipher.h>
 #include <linux/key-type.h>
 
 #include <keys/ceph-type.h>
@@ -79,9 +80,9 @@ int ceph_crypto_key_unarmor(struct ceph_crypto_key *key, const char *inkey)
 	return 0;
 }
 
-static struct crypto_blkcipher *ceph_crypto_alloc_cipher(void)
+static struct crypto_skcipher *ceph_crypto_alloc_cipher(void)
 {
-	return crypto_alloc_blkcipher("cbc(aes)", 0, CRYPTO_ALG_ASYNC);
+	return crypto_alloc_skcipher("cbc(aes)", 0, CRYPTO_ALG_ASYNC);
 }
 
 static const u8 *aes_iv = (u8 *)CEPH_AES_IV;
@@ -162,11 +163,10 @@ static int ceph_aes_encrypt(const void *key, int key_len,
 {
 	struct scatterlist sg_in[2], prealloc_sg;
 	struct sg_table sg_out;
-	struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
-	struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 };
+	struct crypto_skcipher *tfm = ceph_crypto_alloc_cipher();
+	SKCIPHER_REQUEST_ON_STACK(req, tfm);
 	int ret;
-	void *iv;
-	int ivsize;
+	char iv[AES_BLOCK_SIZE];
 	size_t zero_padding = (0x10 - (src_len & 0x0f));
 	char pad[16];
 
@@ -184,10 +184,13 @@ static int ceph_aes_encrypt(const void *key, int key_len,
 	if (ret)
 		goto out_tfm;
 
-	crypto_blkcipher_setkey((void *)tfm, key, key_len);
-	iv = crypto_blkcipher_crt(tfm)->iv;
-	ivsize = crypto_blkcipher_ivsize(tfm);
-	memcpy(iv, aes_iv, ivsize);
+	crypto_skcipher_setkey((void *)tfm, key, key_len);
+	memcpy(iv, aes_iv, AES_BLOCK_SIZE);
+
+	skcipher_request_set_tfm(req, tfm);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, sg_in, sg_out.sgl,
+				   src_len + zero_padding, iv);
 
 	/*
 	print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1,
@@ -197,8 +200,8 @@ static int ceph_aes_encrypt(const void *key, int key_len,
 	print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1,
 			pad, zero_padding, 1);
 	*/
-	ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in,
-				     src_len + zero_padding);
+	ret = crypto_skcipher_encrypt(req);
+	skcipher_request_zero(req);
 	if (ret < 0) {
 		pr_err("ceph_aes_crypt failed %d\n", ret);
 		goto out_sg;
@@ -211,7 +214,7 @@ static int ceph_aes_encrypt(const void *key, int key_len,
 out_sg:
 	teardown_sgtable(&sg_out);
 out_tfm:
-	crypto_free_blkcipher(tfm);
+	crypto_free_skcipher(tfm);
 	return ret;
 }
 
@@ -222,11 +225,10 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
 {
 	struct scatterlist sg_in[3], prealloc_sg;
 	struct sg_table sg_out;
-	struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
-	struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 };
+	struct crypto_skcipher *tfm = ceph_crypto_alloc_cipher();
+	SKCIPHER_REQUEST_ON_STACK(req, tfm);
 	int ret;
-	void *iv;
-	int ivsize;
+	char iv[AES_BLOCK_SIZE];
 	size_t zero_padding = (0x10 - ((src1_len + src2_len) & 0x0f));
 	char pad[16];
 
@@ -245,10 +247,13 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
 	if (ret)
 		goto out_tfm;
 
-	crypto_blkcipher_setkey((void *)tfm, key, key_len);
-	iv = crypto_blkcipher_crt(tfm)->iv;
-	ivsize = crypto_blkcipher_ivsize(tfm);
-	memcpy(iv, aes_iv, ivsize);
+	crypto_skcipher_setkey((void *)tfm, key, key_len);
+	memcpy(iv, aes_iv, AES_BLOCK_SIZE);
+
+	skcipher_request_set_tfm(req, tfm);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, sg_in, sg_out.sgl,
+				   src1_len + src2_len + zero_padding, iv);
 
 	/*
 	print_hex_dump(KERN_ERR, "enc  key: ", DUMP_PREFIX_NONE, 16, 1,
@@ -260,8 +265,8 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
 	print_hex_dump(KERN_ERR, "enc  pad: ", DUMP_PREFIX_NONE, 16, 1,
 			pad, zero_padding, 1);
 	*/
-	ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in,
-				     src1_len + src2_len + zero_padding);
+	ret = crypto_skcipher_encrypt(req);
+	skcipher_request_zero(req);
 	if (ret < 0) {
 		pr_err("ceph_aes_crypt2 failed %d\n", ret);
 		goto out_sg;
@@ -274,7 +279,7 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
 out_sg:
 	teardown_sgtable(&sg_out);
 out_tfm:
-	crypto_free_blkcipher(tfm);
+	crypto_free_skcipher(tfm);
 	return ret;
 }
 
@@ -284,11 +289,10 @@ static int ceph_aes_decrypt(const void *key, int key_len,
 {
 	struct sg_table sg_in;
 	struct scatterlist sg_out[2], prealloc_sg;
-	struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
-	struct blkcipher_desc desc = { .tfm = tfm };
+	struct crypto_skcipher *tfm = ceph_crypto_alloc_cipher();
+	SKCIPHER_REQUEST_ON_STACK(req, tfm);
 	char pad[16];
-	void *iv;
-	int ivsize;
+	char iv[AES_BLOCK_SIZE];
 	int ret;
 	int last_byte;
 
@@ -302,10 +306,13 @@ static int ceph_aes_decrypt(const void *key, int key_len,
 	if (ret)
 		goto out_tfm;
 
-	crypto_blkcipher_setkey((void *)tfm, key, key_len);
-	iv = crypto_blkcipher_crt(tfm)->iv;
-	ivsize = crypto_blkcipher_ivsize(tfm);
-	memcpy(iv, aes_iv, ivsize);
+	crypto_skcipher_setkey((void *)tfm, key, key_len);
+	memcpy(iv, aes_iv, AES_BLOCK_SIZE);
+
+	skcipher_request_set_tfm(req, tfm);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, sg_in.sgl, sg_out,
+				   src_len, iv);
 
 	/*
 	print_hex_dump(KERN_ERR, "dec key: ", DUMP_PREFIX_NONE, 16, 1,
@@ -313,7 +320,8 @@ static int ceph_aes_decrypt(const void *key, int key_len,
 	print_hex_dump(KERN_ERR, "dec  in: ", DUMP_PREFIX_NONE, 16, 1,
 		       src, src_len, 1);
 	*/
-	ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len);
+	ret = crypto_skcipher_decrypt(req);
+	skcipher_request_zero(req);
 	if (ret < 0) {
 		pr_err("ceph_aes_decrypt failed %d\n", ret);
 		goto out_sg;
@@ -338,7 +346,7 @@ static int ceph_aes_decrypt(const void *key, int key_len,
 out_sg:
 	teardown_sgtable(&sg_in);
 out_tfm:
-	crypto_free_blkcipher(tfm);
+	crypto_free_skcipher(tfm);
 	return ret;
 }
 
@@ -349,11 +357,10 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
 {
 	struct sg_table sg_in;
 	struct scatterlist sg_out[3], prealloc_sg;
-	struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
-	struct blkcipher_desc desc = { .tfm = tfm };
+	struct crypto_skcipher *tfm = ceph_crypto_alloc_cipher();
+	SKCIPHER_REQUEST_ON_STACK(req, tfm);
 	char pad[16];
-	void *iv;
-	int ivsize;
+	char iv[AES_BLOCK_SIZE];
 	int ret;
 	int last_byte;
 
@@ -368,10 +375,13 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
 	if (ret)
 		goto out_tfm;
 
-	crypto_blkcipher_setkey((void *)tfm, key, key_len);
-	iv = crypto_blkcipher_crt(tfm)->iv;
-	ivsize = crypto_blkcipher_ivsize(tfm);
-	memcpy(iv, aes_iv, ivsize);
+	crypto_skcipher_setkey((void *)tfm, key, key_len);
+	memcpy(iv, aes_iv, AES_BLOCK_SIZE);
+
+	skcipher_request_set_tfm(req, tfm);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, sg_in.sgl, sg_out,
+				   src_len, iv);
 
 	/*
 	print_hex_dump(KERN_ERR, "dec  key: ", DUMP_PREFIX_NONE, 16, 1,
@@ -379,7 +389,8 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
 	print_hex_dump(KERN_ERR, "dec   in: ", DUMP_PREFIX_NONE, 16, 1,
 		       src, src_len, 1);
 	*/
-	ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len);
+	ret = crypto_skcipher_decrypt(req);
+	skcipher_request_zero(req);
 	if (ret < 0) {
 		pr_err("ceph_aes_decrypt failed %d\n", ret);
 		goto out_sg;
@@ -415,7 +426,7 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
 out_sg:
 	teardown_sgtable(&sg_in);
 out_tfm:
-	crypto_free_blkcipher(tfm);
+	crypto_free_skcipher(tfm);
 	return ret;
 }
 
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 9cfedf565f5b..9382619a405b 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1197,6 +1197,13 @@ static bool ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor,
 	return new_piece;
 }
 
+static size_t sizeof_footer(struct ceph_connection *con)
+{
+	return (con->peer_features & CEPH_FEATURE_MSG_AUTH) ?
+	    sizeof(struct ceph_msg_footer) :
+	    sizeof(struct ceph_msg_footer_old);
+}
+
 static void prepare_message_data(struct ceph_msg *msg, u32 data_len)
 {
 	BUG_ON(!msg);
@@ -2335,9 +2342,9 @@ static int read_partial_message(struct ceph_connection *con)
 			ceph_pr_addr(&con->peer_addr.in_addr),
 			seq, con->in_seq + 1);
 		con->in_base_pos = -front_len - middle_len - data_len -
-			sizeof(m->footer);
+			sizeof_footer(con);
 		con->in_tag = CEPH_MSGR_TAG_READY;
-		return 0;
+		return 1;
 	} else if ((s64)seq - (s64)con->in_seq > 1) {
 		pr_err("read_partial_message bad seq %lld expected %lld\n",
 		       seq, con->in_seq + 1);
@@ -2360,10 +2367,10 @@ static int read_partial_message(struct ceph_connection *con)
 			/* skip this message */
 			dout("alloc_msg said skip message\n");
 			con->in_base_pos = -front_len - middle_len - data_len -
-				sizeof(m->footer);
+				sizeof_footer(con);
 			con->in_tag = CEPH_MSGR_TAG_READY;
 			con->in_seq++;
-			return 0;
+			return 1;
 		}
 
 		BUG_ON(!con->in_msg);
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 3534e12683d3..5bc053778fed 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -2853,8 +2853,8 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
 	mutex_lock(&osdc->request_mutex);
 	req = __lookup_request(osdc, tid);
 	if (!req) {
-		pr_warn("%s osd%d tid %llu unknown, skipping\n",
-			__func__, osd->o_osd, tid);
+		dout("%s osd%d tid %llu unknown, skipping\n", __func__,
+		     osd->o_osd, tid);
 		m = NULL;
 		*skip = 1;
 		goto out;
diff --git a/net/core/dev.c b/net/core/dev.c
index 8cba3d852f25..0ef061b2badc 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5379,12 +5379,12 @@ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter)
 {
 	struct netdev_adjacent *lower;
 
-	lower = list_entry((*iter)->next, struct netdev_adjacent, list);
+	lower = list_entry(*iter, struct netdev_adjacent, list);
 
 	if (&lower->list == &dev->adj_list.lower)
 		return NULL;
 
-	*iter = &lower->list;
+	*iter = lower->list.next;
 
 	return lower->dev;
 }
@@ -7422,8 +7422,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM;
 	setup(dev);
 
-	if (!dev->tx_queue_len)
+	if (!dev->tx_queue_len) {
 		dev->priv_flags |= IFF_NO_QUEUE;
+		dev->tx_queue_len = 1;
+	}
 
 	dev->num_tx_queues = txqs;
 	dev->real_num_tx_queues = txqs;
diff --git a/net/core/filter.c b/net/core/filter.c
index 94d26201080d..bba502f7cd57 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1752,7 +1752,7 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5)
 	u8 compat[sizeof(struct bpf_tunnel_key)];
 	struct ip_tunnel_info *info;
 
-	if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6)))
+	if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX)))
 		return -EINVAL;
 	if (unlikely(size != sizeof(struct bpf_tunnel_key))) {
 		switch (size) {
@@ -1776,7 +1776,7 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5)
 	info = &md->u.tun_info;
 	info->mode = IP_TUNNEL_INFO_TX;
 
-	info->key.tun_flags = TUNNEL_KEY;
+	info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM;
 	info->key.tun_id = cpu_to_be64(from->tunnel_id);
 	info->key.tos = from->tunnel_tos;
 	info->key.ttl = from->tunnel_ttl;
@@ -1787,6 +1787,8 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5)
 		       sizeof(from->remote_ipv6));
 	} else {
 		info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4);
+		if (flags & BPF_F_ZERO_CSUM_TX)
+			info->key.tun_flags &= ~TUNNEL_CSUM;
 	}
 
 	return 0;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index d79699c9d1b9..12e700332010 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -208,7 +208,6 @@ ip:
 	case htons(ETH_P_IPV6): {
 		const struct ipv6hdr *iph;
 		struct ipv6hdr _iph;
-		__be32 flow_label;
 
 ipv6:
 		iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
@@ -230,8 +229,12 @@ ipv6:
 			key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
 		}
 
-		flow_label = ip6_flowlabel(iph);
-		if (flow_label) {
+		if ((dissector_uses_key(flow_dissector,
+					FLOW_DISSECTOR_KEY_FLOW_LABEL) ||
+		     (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL)) &&
+		    ip6_flowlabel(iph)) {
+			__be32 flow_label = ip6_flowlabel(iph);
+
 			if (dissector_uses_key(flow_dissector,
 					       FLOW_DISSECTOR_KEY_FLOW_LABEL)) {
 				key_tags = skb_flow_dissector_target(flow_dissector,
@@ -396,6 +399,13 @@ ip_proto_again:
 				goto out_bad;
 			proto = eth->h_proto;
 			nhoff += sizeof(*eth);
+
+			/* Cap headers that we access via pointers at the
+			 * end of the Ethernet header as our maximum alignment
+			 * at that point is only 2 bytes.
+			 */
+			if (NET_IP_ALIGN)
+				hlen = nhoff;
 		}
 
 		key_control->flags |= FLOW_DIS_ENCAPSULATION;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index d735e854f916..8261d95dd846 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2911,6 +2911,7 @@ int ndo_dflt_fdb_dump(struct sk_buff *skb,
 	nlmsg_populate_fdb(skb, cb, dev, &idx, &dev->mc);
 out:
 	netif_addr_unlock_bh(dev);
+	cb->args[1] = err;
 	return idx;
 }
 EXPORT_SYMBOL(ndo_dflt_fdb_dump);
@@ -2944,6 +2945,7 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		ops = br_dev->netdev_ops;
 	}
 
+	cb->args[1] = 0;
 	for_each_netdev(net, dev) {
 		if (brport_idx && (dev->ifindex != brport_idx))
 			continue;
@@ -2971,12 +2973,16 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 				idx = cops->ndo_fdb_dump(skb, cb, br_dev, dev,
 							 idx);
 		}
+		if (cb->args[1] == -EMSGSIZE)
+			break;
 
 		if (dev->netdev_ops->ndo_fdb_dump)
 			idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, NULL,
 							    idx);
 		else
 			idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx);
+		if (cb->args[1] == -EMSGSIZE)
+			break;
 
 		cops = NULL;
 	}
diff --git a/net/core/scm.c b/net/core/scm.c
index 14596fb37172..2696aefdc148 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -87,6 +87,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp)
 		*fplp = fpl;
 		fpl->count = 0;
 		fpl->max = SCM_MAX_FD;
+		fpl->user = NULL;
 	}
 	fpp = &fpl->fp[fpl->count];
 
@@ -107,6 +108,10 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp)
 		*fpp++ = file;
 		fpl->count++;
 	}
+
+	if (!fpl->user)
+		fpl->user = get_uid(current_user());
+
 	return num;
 }
 
@@ -119,6 +124,7 @@ void __scm_destroy(struct scm_cookie *scm)
 		scm->fp = NULL;
 		for (i=fpl->count-1; i>=0; i--)
 			fput(fpl->fp[i]);
+		free_uid(fpl->user);
 		kfree(fpl);
 	}
 }
@@ -336,6 +342,7 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl)
 		for (i = 0; i < fpl->count; i++)
 			get_file(fpl->fp[i]);
 		new_fpl->max = new_fpl->count;
+		new_fpl->user = get_uid(fpl->user);
 	}
 	return new_fpl;
 }
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b2df375ec9c2..8616d1147c93 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -79,6 +79,8 @@
 
 struct kmem_cache *skbuff_head_cache __read_mostly;
 static struct kmem_cache *skbuff_fclone_cache __read_mostly;
+int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
+EXPORT_SYMBOL(sysctl_max_skb_frags);
 
 /**
  *	skb_panic - private function for out-of-line support
@@ -2946,6 +2948,24 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page,
 EXPORT_SYMBOL_GPL(skb_append_pagefrags);
 
 /**
+ *	skb_push_rcsum - push skb and update receive checksum
+ *	@skb: buffer to update
+ *	@len: length of data pulled
+ *
+ *	This function performs an skb_push on the packet and updates
+ *	the CHECKSUM_COMPLETE checksum.  It should be used on
+ *	receive path processing instead of skb_push unless you know
+ *	that the checksum difference is zero (e.g., a valid IP header)
+ *	or you are setting ip_summed to CHECKSUM_NONE.
+ */
+static unsigned char *skb_push_rcsum(struct sk_buff *skb, unsigned len)
+{
+	skb_push(skb, len);
+	skb_postpush_rcsum(skb, skb->data, len);
+	return skb->data;
+}
+
+/**
  *	skb_pull_rcsum - pull skb and update receive checksum
  *	@skb: buffer to update
  *	@len: length of data pulled
@@ -4082,9 +4102,9 @@ struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb,
 	if (!pskb_may_pull(skb_chk, offset))
 		goto err;
 
-	__skb_pull(skb_chk, offset);
+	skb_pull_rcsum(skb_chk, offset);
 	ret = skb_chkf(skb_chk);
-	__skb_push(skb_chk, offset);
+	skb_push_rcsum(skb_chk, offset);
 
 	if (ret)
 		goto err;
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 95b6139d710c..a6beb7b6ae55 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -26,6 +26,7 @@ static int zero = 0;
 static int one = 1;
 static int min_sndbuf = SOCK_MIN_SNDBUF;
 static int min_rcvbuf = SOCK_MIN_RCVBUF;
+static int max_skb_frags = MAX_SKB_FRAGS;
 
 static int net_msg_warn;	/* Unused, but still a sysctl */
 
@@ -392,6 +393,15 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "max_skb_frags",
+		.data		= &sysctl_max_skb_frags,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
+		.extra2		= &max_skb_frags,
+	},
 	{ }
 };
 
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 5684e14932bd..902d606324a0 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -824,26 +824,26 @@ lookup:
 
 	if (sk->sk_state == DCCP_NEW_SYN_RECV) {
 		struct request_sock *req = inet_reqsk(sk);
-		struct sock *nsk = NULL;
+		struct sock *nsk;
 
 		sk = req->rsk_listener;
-		if (likely(sk->sk_state == DCCP_LISTEN)) {
-			nsk = dccp_check_req(sk, skb, req);
-		} else {
+		if (unlikely(sk->sk_state != DCCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
 		}
+		sock_hold(sk);
+		nsk = dccp_check_req(sk, skb, req);
 		if (!nsk) {
 			reqsk_put(req);
-			goto discard_it;
+			goto discard_and_relse;
 		}
 		if (nsk == sk) {
-			sock_hold(sk);
 			reqsk_put(req);
 		} else if (dccp_child_process(sk, nsk, skb)) {
 			dccp_v4_ctl_send_reset(sk, skb);
-			goto discard_it;
+			goto discard_and_relse;
 		} else {
+			sock_put(sk);
 			return 0;
 		}
 	}
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 9c6d0508e63a..b8608b71a66d 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -691,26 +691,26 @@ lookup:
 
 	if (sk->sk_state == DCCP_NEW_SYN_RECV) {
 		struct request_sock *req = inet_reqsk(sk);
-		struct sock *nsk = NULL;
+		struct sock *nsk;
 
 		sk = req->rsk_listener;
-		if (likely(sk->sk_state == DCCP_LISTEN)) {
-			nsk = dccp_check_req(sk, skb, req);
-		} else {
+		if (unlikely(sk->sk_state != DCCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
 		}
+		sock_hold(sk);
+		nsk = dccp_check_req(sk, skb, req);
 		if (!nsk) {
 			reqsk_put(req);
-			goto discard_it;
+			goto discard_and_relse;
 		}
 		if (nsk == sk) {
-			sock_hold(sk);
 			reqsk_put(req);
 		} else if (dccp_child_process(sk, nsk, skb)) {
 			dccp_v6_ctl_send_reset(sk, skb);
-			goto discard_it;
+			goto discard_and_relse;
 		} else {
+			sock_put(sk);
 			return 0;
 		}
 	}
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 40b9ca72aae3..ab24521beb4d 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1194,7 +1194,6 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 	if (ret) {
 		netdev_err(master, "error %d registering interface %s\n",
 			   ret, slave_dev->name);
-		phy_disconnect(p->phy);
 		ds->ports[port] = NULL;
 		free_netdev(slave_dev);
 		return ret;
@@ -1205,6 +1204,7 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 	ret = dsa_slave_phy_setup(p, slave_dev);
 	if (ret) {
 		netdev_err(master, "error %d setting up slave phy\n", ret);
+		unregister_netdev(slave_dev);
 		free_netdev(slave_dev);
 		return ret;
 	}
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index cebd9d31e65a..f6303b17546b 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1847,7 +1847,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb,
 	if (err < 0)
 		goto errout;
 
-	err = EINVAL;
+	err = -EINVAL;
 	if (!tb[NETCONFA_IFINDEX])
 		goto errout;
 
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 05e4cba14162..b3086cf27027 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -356,9 +356,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
 	skb_dst_set(skb, &rt->dst);
 	skb->dev = dev;
 
-	skb->reserved_tailroom = skb_end_offset(skb) -
-				 min(mtu, skb_end_offset(skb));
 	skb_reserve(skb, hlen);
+	skb_tailroom_reserve(skb, mtu, tlen);
 
 	skb_reset_network_header(skb);
 	pip = ip_hdr(skb);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 46b9c887bede..64148914803a 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -789,14 +789,16 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req,
 	reqsk_put(req);
 }
 
-void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
-			      struct sock *child)
+struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
+				      struct request_sock *req,
+				      struct sock *child)
 {
 	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
 
 	spin_lock(&queue->rskq_lock);
 	if (unlikely(sk->sk_state != TCP_LISTEN)) {
 		inet_child_forget(sk, req, child);
+		child = NULL;
 	} else {
 		req->sk = child;
 		req->dl_next = NULL;
@@ -808,6 +810,7 @@ void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
 		sk_acceptq_added(sk);
 	}
 	spin_unlock(&queue->rskq_lock);
+	return child;
 }
 EXPORT_SYMBOL(inet_csk_reqsk_queue_add);
 
@@ -817,11 +820,8 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
 	if (own_req) {
 		inet_csk_reqsk_queue_drop(sk, req);
 		reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
-		inet_csk_reqsk_queue_add(sk, req, child);
-		/* Warning: caller must not call reqsk_put(req);
-		 * child stole last reference on it.
-		 */
-		return child;
+		if (inet_csk_reqsk_queue_add(sk, req, child))
+			return child;
 	}
 	/* Too bad, another child took ownership of the request, undo. */
 	bh_unlock_sock(child);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 7c51c4e1661f..41ba68de46d8 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1054,8 +1054,9 @@ static const struct net_device_ops gre_tap_netdev_ops = {
 static void ipgre_tap_setup(struct net_device *dev)
 {
 	ether_setup(dev);
-	dev->netdev_ops		= &gre_tap_netdev_ops;
-	dev->priv_flags 	|= IFF_LIVE_ADDR_CHANGE;
+	dev->netdev_ops	= &gre_tap_netdev_ops;
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+	dev->priv_flags	|= IFF_LIVE_ADDR_CHANGE;
 	ip_tunnel_setup(dev, gre_tap_net_id);
 }
 
@@ -1240,6 +1241,14 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 	err = ipgre_newlink(net, dev, tb, NULL);
 	if (err < 0)
 		goto out;
+
+	/* openvswitch users expect packet sizes to be unrestricted,
+	 * so set the largest MTU we can.
+	 */
+	err = __ip_tunnel_change_mtu(dev, IP_MAX_MTU, false);
+	if (err)
+		goto out;
+
 	return dev;
 out:
 	free_netdev(dev);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 64878efa045c..565bf64b2b7d 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1236,13 +1236,16 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 	if (!skb)
 		return -EINVAL;
 
-	cork->length += size;
 	if ((size + skb->len > mtu) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO)) {
+		if (skb->ip_summed != CHECKSUM_PARTIAL)
+			return -EOPNOTSUPP;
+
 		skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
 		skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
 	}
+	cork->length += size;
 
 	while (size > 0) {
 		if (skb_is_gso(skb)) {
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 5f73a7c03e27..a50124260f5a 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -249,6 +249,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc,
 		switch (cmsg->cmsg_type) {
 		case IP_RETOPTS:
 			err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr));
+
+			/* Our caller is responsible for freeing ipc->opt */
 			err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg),
 					     err < 40 ? err : 40);
 			if (err)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index c7bd72e9b544..336e6892a93c 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -661,6 +661,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
 	connected = (tunnel->parms.iph.daddr != 0);
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	dst = tnl_params->daddr;
 	if (dst == 0) {
 		/* NBMA tunnel */
@@ -758,7 +760,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 				tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
 			tunnel->err_count--;
 
-			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 			dst_link_failure(skb);
 		} else
 			tunnel->err_count = 0;
@@ -943,17 +944,31 @@ done:
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_ioctl);
 
-int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
+	int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
 
-	if (new_mtu < 68 ||
-	    new_mtu > 0xFFF8 - dev->hard_header_len - t_hlen)
+	if (new_mtu < 68)
 		return -EINVAL;
+
+	if (new_mtu > max_mtu) {
+		if (strict)
+			return -EINVAL;
+
+		new_mtu = max_mtu;
+	}
+
 	dev->mtu = new_mtu;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(__ip_tunnel_change_mtu);
+
+int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+{
+	return __ip_tunnel_change_mtu(dev, new_mtu, true);
+}
 EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu);
 
 static void ip_tunnel_dev_free(struct net_device *dev)
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index c117b21b937d..d3a27165f9cc 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -746,8 +746,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			return err;
+		}
 		if (ipc.opt)
 			free = 1;
 	}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index bc35f1842512..7113bae4e6a0 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -547,8 +547,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(net, msg, &ipc, false);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			goto out;
+		}
 		if (ipc.opt)
 			free = 1;
 	}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 85f184e429c6..02c62299d717 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -129,6 +129,7 @@ static int ip_rt_mtu_expires __read_mostly	= 10 * 60 * HZ;
 static int ip_rt_min_pmtu __read_mostly		= 512 + 20 + 20;
 static int ip_rt_min_advmss __read_mostly	= 256;
 
+static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
 /*
  *	Interface to generic destination cache.
  */
@@ -755,7 +756,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 				struct fib_nh *nh = &FIB_RES_NH(res);
 
 				update_or_create_fnhe(nh, fl4->daddr, new_gw,
-						      0, 0);
+						0, jiffies + ip_rt_gc_timeout);
 			}
 			if (kill_route)
 				rt->dst.obsolete = DST_OBSOLETE_KILL;
@@ -1556,6 +1557,36 @@ static void ip_handle_martian_source(struct net_device *dev,
 #endif
 }
 
+static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
+{
+	struct fnhe_hash_bucket *hash;
+	struct fib_nh_exception *fnhe, __rcu **fnhe_p;
+	u32 hval = fnhe_hashfun(daddr);
+
+	spin_lock_bh(&fnhe_lock);
+
+	hash = rcu_dereference_protected(nh->nh_exceptions,
+					 lockdep_is_held(&fnhe_lock));
+	hash += hval;
+
+	fnhe_p = &hash->chain;
+	fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
+	while (fnhe) {
+		if (fnhe->fnhe_daddr == daddr) {
+			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
+				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+			fnhe_flush_routes(fnhe);
+			kfree_rcu(fnhe, rcu);
+			break;
+		}
+		fnhe_p = &fnhe->fnhe_next;
+		fnhe = rcu_dereference_protected(fnhe->fnhe_next,
+						 lockdep_is_held(&fnhe_lock));
+	}
+
+	spin_unlock_bh(&fnhe_lock);
+}
+
 /* called in rcu_read_lock() section */
 static int __mkroute_input(struct sk_buff *skb,
 			   const struct fib_result *res,
@@ -1609,11 +1640,20 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	fnhe = find_exception(&FIB_RES_NH(*res), daddr);
 	if (do_cache) {
-		if (fnhe)
+		if (fnhe) {
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
-		else
-			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+			if (rth && rth->dst.expires &&
+			    time_after(jiffies, rth->dst.expires)) {
+				ip_del_fnhe(&FIB_RES_NH(*res), daddr);
+				fnhe = NULL;
+			} else {
+				goto rt_cache;
+			}
+		}
+
+		rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
 
+rt_cache:
 		if (rt_cache_valid(rth)) {
 			skb_dst_set_noref(skb, &rth->dst);
 			goto out;
@@ -2014,19 +2054,29 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		struct fib_nh *nh = &FIB_RES_NH(*res);
 
 		fnhe = find_exception(nh, fl4->daddr);
-		if (fnhe)
+		if (fnhe) {
 			prth = &fnhe->fnhe_rth_output;
-		else {
-			if (unlikely(fl4->flowi4_flags &
-				     FLOWI_FLAG_KNOWN_NH &&
-				     !(nh->nh_gw &&
-				       nh->nh_scope == RT_SCOPE_LINK))) {
-				do_cache = false;
-				goto add;
+			rth = rcu_dereference(*prth);
+			if (rth && rth->dst.expires &&
+			    time_after(jiffies, rth->dst.expires)) {
+				ip_del_fnhe(nh, fl4->daddr);
+				fnhe = NULL;
+			} else {
+				goto rt_cache;
 			}
-			prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		}
+
+		if (unlikely(fl4->flowi4_flags &
+			     FLOWI_FLAG_KNOWN_NH &&
+			     !(nh->nh_gw &&
+			       nh->nh_scope == RT_SCOPE_LINK))) {
+			do_cache = false;
+			goto add;
+		}
+		prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		rth = rcu_dereference(*prth);
+
+rt_cache:
 		if (rt_cache_valid(rth)) {
 			dst_hold(&rth->dst);
 			return rth;
@@ -2569,7 +2619,6 @@ void ip_rt_multicast_event(struct in_device *in_dev)
 }
 
 #ifdef CONFIG_SYSCTL
-static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
 static int ip_rt_gc_interval __read_mostly  = 60 * HZ;
 static int ip_rt_gc_min_interval __read_mostly	= HZ / 2;
 static int ip_rt_gc_elasticity __read_mostly	= 8;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 643a86c49020..2d5589b61e9f 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -50,8 +50,7 @@ static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
 #define TSBITS	6
 #define TSMASK	(((__u32)1 << TSBITS) - 1)
 
-static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS],
-		      ipv4_cookie_scratch);
+static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], ipv4_cookie_scratch);
 
 static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
 		       u32 count, int c)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 19746b3fcbbe..4804645bdf02 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -247,6 +247,7 @@
 
 #define pr_fmt(fmt) "TCP: " fmt
 
+#include <crypto/hash.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/types.h>
@@ -266,7 +267,6 @@
 #include <linux/swap.h>
 #include <linux/cache.h>
 #include <linux/err.h>
-#include <linux/crypto.h>
 #include <linux/time.h>
 #include <linux/slab.h>
 
@@ -940,7 +940,7 @@ new_segment:
 
 		i = skb_shinfo(skb)->nr_frags;
 		can_coalesce = skb_can_coalesce(skb, i, page, offset);
-		if (!can_coalesce && i >= MAX_SKB_FRAGS) {
+		if (!can_coalesce && i >= sysctl_max_skb_frags) {
 			tcp_mark_push(tp, skb);
 			goto new_segment;
 		}
@@ -1213,7 +1213,7 @@ new_segment:
 
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
-				if (i == MAX_SKB_FRAGS || !sg) {
+				if (i == sysctl_max_skb_frags || !sg) {
 					tcp_mark_push(tp, skb);
 					goto new_segment;
 				}
@@ -2943,17 +2943,26 @@ static bool tcp_md5sig_pool_populated = false;
 
 static void __tcp_alloc_md5sig_pool(void)
 {
+	struct crypto_ahash *hash;
 	int cpu;
 
+	hash = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(hash))
+		return;
+
 	for_each_possible_cpu(cpu) {
-		if (!per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm) {
-			struct crypto_hash *hash;
+		struct ahash_request *req;
 
-			hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
-			if (IS_ERR_OR_NULL(hash))
-				return;
-			per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm = hash;
-		}
+		if (per_cpu(tcp_md5sig_pool, cpu).md5_req)
+			continue;
+
+		req = ahash_request_alloc(hash, GFP_KERNEL);
+		if (!req)
+			return;
+
+		ahash_request_set_callback(req, 0, NULL, NULL);
+
+		per_cpu(tcp_md5sig_pool, cpu).md5_req = req;
 	}
 	/* before setting tcp_md5sig_pool_populated, we must commit all writes
 	 * to memory. See smp_rmb() in tcp_get_md5sig_pool()
@@ -3003,7 +3012,6 @@ int tcp_md5_hash_header(struct tcp_md5sig_pool *hp,
 {
 	struct scatterlist sg;
 	struct tcphdr hdr;
-	int err;
 
 	/* We are not allowed to change tcphdr, make a local copy */
 	memcpy(&hdr, th, sizeof(hdr));
@@ -3011,8 +3019,8 @@ int tcp_md5_hash_header(struct tcp_md5sig_pool *hp,
 
 	/* options aren't included in the hash */
 	sg_init_one(&sg, &hdr, sizeof(hdr));
-	err = crypto_hash_update(&hp->md5_desc, &sg, sizeof(hdr));
-	return err;
+	ahash_request_set_crypt(hp->md5_req, &sg, NULL, sizeof(hdr));
+	return crypto_ahash_update(hp->md5_req);
 }
 EXPORT_SYMBOL(tcp_md5_hash_header);
 
@@ -3021,7 +3029,7 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
 {
 	struct scatterlist sg;
 	const struct tcphdr *tp = tcp_hdr(skb);
-	struct hash_desc *desc = &hp->md5_desc;
+	struct ahash_request *req = hp->md5_req;
 	unsigned int i;
 	const unsigned int head_data_len = skb_headlen(skb) > header_len ?
 					   skb_headlen(skb) - header_len : 0;
@@ -3031,7 +3039,8 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
 	sg_init_table(&sg, 1);
 
 	sg_set_buf(&sg, ((u8 *) tp) + header_len, head_data_len);
-	if (crypto_hash_update(desc, &sg, head_data_len))
+	ahash_request_set_crypt(req, &sg, NULL, head_data_len);
+	if (crypto_ahash_update(req))
 		return 1;
 
 	for (i = 0; i < shi->nr_frags; ++i) {
@@ -3041,7 +3050,8 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
 
 		sg_set_page(&sg, page, skb_frag_size(f),
 			    offset_in_page(offset));
-		if (crypto_hash_update(desc, &sg, skb_frag_size(f)))
+		ahash_request_set_crypt(req, &sg, NULL, skb_frag_size(f));
+		if (crypto_ahash_update(req))
 			return 1;
 	}
 
@@ -3058,7 +3068,8 @@ int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *ke
 	struct scatterlist sg;
 
 	sg_init_one(&sg, key->key, key->keylen);
-	return crypto_hash_update(&hp->md5_desc, &sg, key->keylen);
+	ahash_request_set_crypt(hp->md5_req, &sg, NULL, key->keylen);
+	return crypto_ahash_update(hp->md5_req);
 }
 EXPORT_SYMBOL(tcp_md5_hash_key);
 
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 55be6ac70cff..4c65ca1a86d1 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -1,3 +1,4 @@
+#include <linux/crypto.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1c2a73406261..3b2c8e90a475 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2896,7 +2896,10 @@ static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us)
 {
 	const u32 now = tcp_time_stamp, wlen = sysctl_tcp_min_rtt_wlen * HZ;
 	struct rtt_meas *m = tcp_sk(sk)->rtt_min;
-	struct rtt_meas rttm = { .rtt = (rtt_us ? : 1), .ts = now };
+	struct rtt_meas rttm = {
+		.rtt = likely(rtt_us) ? rtt_us : jiffies_to_usecs(1),
+		.ts = now,
+	};
 	u32 elapsed;
 
 	/* Check if the new measurement updates the 1st, 2nd, or 3rd choices */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a4d523709ab3..4fdbf4e56797 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -81,7 +81,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 
-#include <linux/crypto.h>
+#include <crypto/hash.h>
 #include <linux/scatterlist.h>
 
 int sysctl_tcp_tw_reuse __read_mostly;
@@ -311,7 +311,7 @@ static void do_redirect(struct sk_buff *skb, struct sock *sk)
 
 
 /* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */
-void tcp_req_err(struct sock *sk, u32 seq)
+void tcp_req_err(struct sock *sk, u32 seq, bool abort)
 {
 	struct request_sock *req = inet_reqsk(sk);
 	struct net *net = sock_net(sk);
@@ -323,7 +323,7 @@ void tcp_req_err(struct sock *sk, u32 seq)
 
 	if (seq != tcp_rsk(req)->snt_isn) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
-	} else {
+	} else if (abort) {
 		/*
 		 * Still in SYN_RECV, just remove it silently.
 		 * There is no good way to pass the error to the newly
@@ -383,7 +383,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	}
 	seq = ntohl(th->seq);
 	if (sk->sk_state == TCP_NEW_SYN_RECV)
-		return tcp_req_err(sk, seq);
+		return tcp_req_err(sk, seq,
+				  type == ICMP_PARAMETERPROB ||
+				  type == ICMP_TIME_EXCEEDED ||
+				  (type == ICMP_DEST_UNREACH &&
+				   (code == ICMP_NET_UNREACH ||
+				    code == ICMP_HOST_UNREACH)));
 
 	bh_lock_sock(sk);
 	/* If too many ICMPs get dropped on busy
@@ -1034,21 +1039,22 @@ static int tcp_v4_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
 	bp->len = cpu_to_be16(nbytes);
 
 	sg_init_one(&sg, bp, sizeof(*bp));
-	return crypto_hash_update(&hp->md5_desc, &sg, sizeof(*bp));
+	ahash_request_set_crypt(hp->md5_req, &sg, NULL, sizeof(*bp));
+	return crypto_ahash_update(hp->md5_req);
 }
 
 static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 			       __be32 daddr, __be32 saddr, const struct tcphdr *th)
 {
 	struct tcp_md5sig_pool *hp;
-	struct hash_desc *desc;
+	struct ahash_request *req;
 
 	hp = tcp_get_md5sig_pool();
 	if (!hp)
 		goto clear_hash_noput;
-	desc = &hp->md5_desc;
+	req = hp->md5_req;
 
-	if (crypto_hash_init(desc))
+	if (crypto_ahash_init(req))
 		goto clear_hash;
 	if (tcp_v4_md5_hash_pseudoheader(hp, daddr, saddr, th->doff << 2))
 		goto clear_hash;
@@ -1056,7 +1062,8 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 		goto clear_hash;
 	if (tcp_md5_hash_key(hp, key))
 		goto clear_hash;
-	if (crypto_hash_final(desc, md5_hash))
+	ahash_request_set_crypt(req, NULL, md5_hash, 0);
+	if (crypto_ahash_final(req))
 		goto clear_hash;
 
 	tcp_put_md5sig_pool();
@@ -1074,7 +1081,7 @@ int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key,
 			const struct sk_buff *skb)
 {
 	struct tcp_md5sig_pool *hp;
-	struct hash_desc *desc;
+	struct ahash_request *req;
 	const struct tcphdr *th = tcp_hdr(skb);
 	__be32 saddr, daddr;
 
@@ -1090,9 +1097,9 @@ int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key,
 	hp = tcp_get_md5sig_pool();
 	if (!hp)
 		goto clear_hash_noput;
-	desc = &hp->md5_desc;
+	req = hp->md5_req;
 
-	if (crypto_hash_init(desc))
+	if (crypto_ahash_init(req))
 		goto clear_hash;
 
 	if (tcp_v4_md5_hash_pseudoheader(hp, daddr, saddr, skb->len))
@@ -1103,7 +1110,8 @@ int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key,
 		goto clear_hash;
 	if (tcp_md5_hash_key(hp, key))
 		goto clear_hash;
-	if (crypto_hash_final(desc, md5_hash))
+	ahash_request_set_crypt(req, NULL, md5_hash, 0);
+	if (crypto_ahash_final(req))
 		goto clear_hash;
 
 	tcp_put_md5sig_pool();
@@ -1592,28 +1600,30 @@ process:
 
 	if (sk->sk_state == TCP_NEW_SYN_RECV) {
 		struct request_sock *req = inet_reqsk(sk);
-		struct sock *nsk = NULL;
+		struct sock *nsk;
 
 		sk = req->rsk_listener;
-		if (tcp_v4_inbound_md5_hash(sk, skb))
-			goto discard_and_relse;
-		if (likely(sk->sk_state == TCP_LISTEN)) {
-			nsk = tcp_check_req(sk, skb, req, false);
-		} else {
+		if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) {
+			reqsk_put(req);
+			goto discard_it;
+		}
+		if (unlikely(sk->sk_state != TCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
 		}
+		sock_hold(sk);
+		nsk = tcp_check_req(sk, skb, req, false);
 		if (!nsk) {
 			reqsk_put(req);
-			goto discard_it;
+			goto discard_and_relse;
 		}
 		if (nsk == sk) {
-			sock_hold(sk);
 			reqsk_put(req);
 		} else if (tcp_child_process(sk, nsk, skb)) {
 			tcp_v4_send_reset(nsk, skb);
-			goto discard_it;
+			goto discard_and_relse;
 		} else {
+			sock_put(sk);
 			return 0;
 		}
 	}
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index c8cbc2b4b792..a726d7853ce5 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -550,7 +550,7 @@ reset:
 	 */
 	if (crtt > tp->srtt_us) {
 		/* Set RTO like tcp_rtt_estimator(), but from cached RTT. */
-		crtt /= 8 * USEC_PER_MSEC;
+		crtt /= 8 * USEC_PER_SEC / HZ;
 		inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk));
 	} else if (tp->srtt_us == 0) {
 		/* RFC6298: 5.7 We've failed to get a valid RTT sample from
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 75632a925824..9b02af2139d3 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -455,7 +455,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 
 		newtp->rcv_wup = newtp->copied_seq =
 		newtp->rcv_nxt = treq->rcv_isn + 1;
-		newtp->segs_in = 0;
+		newtp->segs_in = 1;
 
 		newtp->snd_sml = newtp->snd_una =
 		newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
@@ -815,6 +815,7 @@ int tcp_child_process(struct sock *parent, struct sock *child,
 	int ret = 0;
 	int state = child->sk_state;
 
+	tcp_sk(child)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs);
 	if (!sock_owned_by_user(child)) {
 		ret = tcp_rcv_state_process(child, skb);
 		/* Wakeup parent, send SIGIO */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index be0b21852b13..95d2f198017e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1048,8 +1048,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc,
 				   sk->sk_family == AF_INET6);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			return err;
+		}
 		if (ipc.opt)
 			free = 1;
 		connected = 0;
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 0ec08814f37d..96599d1a1318 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -89,6 +89,8 @@ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb
 	uh->source = src_port;
 	uh->len = htons(skb->len);
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	udp_set_csum(nocheck, skb, src, dst, skb->len);
 
 	iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df, xnet);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 38eeddedfc21..bdd7eac4307a 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -583,7 +583,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
 	if (err < 0)
 		goto errout;
 
-	err = EINVAL;
+	err = -EINVAL;
 	if (!tb[NETCONFA_IFINDEX])
 		goto errout;
 
@@ -3538,6 +3538,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 {
 	struct inet6_dev *idev = ifp->idev;
 	struct net_device *dev = idev->dev;
+	bool notify = false;
 
 	addrconf_join_solict(dev, &ifp->addr);
 
@@ -3583,7 +3584,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 			/* Because optimistic nodes can use this address,
 			 * notify listeners. If DAD fails, RTM_DELADDR is sent.
 			 */
-			ipv6_ifa_notify(RTM_NEWADDR, ifp);
+			notify = true;
 		}
 	}
 
@@ -3591,6 +3592,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
 out:
 	spin_unlock(&ifp->lock);
 	read_unlock_bh(&idev->lock);
+	if (notify)
+		ipv6_ifa_notify(RTM_NEWADDR, ifp);
 }
 
 static void addrconf_dad_start(struct inet6_ifaddr *ifp)
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 5c5d23e59da5..9508a20fbf61 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -257,7 +257,11 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset,
 						*fragoff = _frag_off;
 					return hp->nexthdr;
 				}
-				return -ENOENT;
+				if (!found)
+					return -ENOENT;
+				if (fragoff)
+					*fragoff = _frag_off;
+				break;
 			}
 			hdrlen = 8;
 		} else if (nexthdr == NEXTHDR_AUTH) {
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 1f9ebe3cbb4a..dc2db4f7b182 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -540,12 +540,13 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
 		}
 		spin_lock_bh(&ip6_sk_fl_lock);
 		for (sflp = &np->ipv6_fl_list;
-		     (sfl = rcu_dereference(*sflp)) != NULL;
+		     (sfl = rcu_dereference_protected(*sflp,
+						      lockdep_is_held(&ip6_sk_fl_lock))) != NULL;
 		     sflp = &sfl->next) {
 			if (sfl->fl->label == freq.flr_label) {
 				if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK))
 					np->flow_label &= ~IPV6_FLOWLABEL_MASK;
-				*sflp = rcu_dereference(sfl->next);
+				*sflp = sfl->next;
 				spin_unlock_bh(&ip6_sk_fl_lock);
 				fl_release(sfl->fl);
 				kfree_rcu(sfl, rcu);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index f37f18b6b40c..c0d4dc1c5ea4 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -777,6 +777,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev)
 	__u32 mtu;
 	int err;
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 		encap_limit = t->parms.encap_limit;
 
@@ -1512,6 +1514,7 @@ static void ip6gre_tap_setup(struct net_device *dev)
 	dev->destructor = ip6gre_dev_free;
 
 	dev->features |= NETIF_F_NETNS_LOCAL;
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 }
 
 static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 137fca42aaa6..6c5dfec7a377 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1180,6 +1180,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	u8 tproto;
 	int err;
 
+	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
 	tproto = ACCESS_ONCE(t->parms.proto);
 	if (tproto != IPPROTO_IPIP && tproto != 0)
 		return -1;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 5ee56d0a8699..d64ee7e83664 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1574,9 +1574,8 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu)
 		return NULL;
 
 	skb->priority = TC_PRIO_CONTROL;
-	skb->reserved_tailroom = skb_end_offset(skb) -
-				 min(mtu, skb_end_offset(skb));
 	skb_reserve(skb, hlen);
+	skb_tailroom_reserve(skb, mtu, tlen);
 
 	if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) {
 		/* <draft-ietf-magma-mld-source-05.txt>:
diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
index 31ba7ca19757..051b6a6bfff6 100644
--- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
@@ -21,6 +21,10 @@
 #include <net/ipv6.h>
 #include <net/netfilter/ipv6/nf_nat_masquerade.h>
 
+#define MAX_WORK_COUNT	16
+
+static atomic_t v6_worker_count;
+
 unsigned int
 nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range,
 		       const struct net_device *out)
@@ -78,14 +82,78 @@ static struct notifier_block masq_dev_notifier = {
 	.notifier_call	= masq_device_event,
 };
 
+struct masq_dev_work {
+	struct work_struct work;
+	struct net *net;
+	int ifindex;
+};
+
+static void iterate_cleanup_work(struct work_struct *work)
+{
+	struct masq_dev_work *w;
+	long index;
+
+	w = container_of(work, struct masq_dev_work, work);
+
+	index = w->ifindex;
+	nf_ct_iterate_cleanup(w->net, device_cmp, (void *)index, 0, 0);
+
+	put_net(w->net);
+	kfree(w);
+	atomic_dec(&v6_worker_count);
+	module_put(THIS_MODULE);
+}
+
+/* ipv6 inet notifier is an atomic notifier, i.e. we cannot
+ * schedule.
+ *
+ * Unfortunately, nf_ct_iterate_cleanup can run for a long
+ * time if there are lots of conntracks and the system
+ * handles high softirq load, so it frequently calls cond_resched
+ * while iterating the conntrack table.
+ *
+ * So we defer nf_ct_iterate_cleanup walk to the system workqueue.
+ *
+ * As we can have 'a lot' of inet_events (depending on amount
+ * of ipv6 addresses being deleted), we also need to add an upper
+ * limit to the number of queued work items.
+ */
 static int masq_inet_event(struct notifier_block *this,
 			   unsigned long event, void *ptr)
 {
 	struct inet6_ifaddr *ifa = ptr;
-	struct netdev_notifier_info info;
+	const struct net_device *dev;
+	struct masq_dev_work *w;
+	struct net *net;
+
+	if (event != NETDEV_DOWN ||
+	    atomic_read(&v6_worker_count) >= MAX_WORK_COUNT)
+		return NOTIFY_DONE;
+
+	dev = ifa->idev->dev;
+	net = maybe_get_net(dev_net(dev));
+	if (!net)
+		return NOTIFY_DONE;
 
-	netdev_notifier_info_init(&info, ifa->idev->dev);
-	return masq_device_event(this, event, &info);
+	if (!try_module_get(THIS_MODULE))
+		goto err_module;
+
+	w = kmalloc(sizeof(*w), GFP_ATOMIC);
+	if (w) {
+		atomic_inc(&v6_worker_count);
+
+		INIT_WORK(&w->work, iterate_cleanup_work);
+		w->ifindex = dev->ifindex;
+		w->net = net;
+		schedule_work(&w->work);
+
+		return NOTIFY_DONE;
+	}
+
+	module_put(THIS_MODULE);
+ err_module:
+	put_net(net);
+	return NOTIFY_DONE;
 }
 
 static struct notifier_block masq_inet_notifier = {
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 2906ef20795e..aae3e5ca63ea 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -41,8 +41,7 @@ static __u16 const msstab[] = {
 	9000 - 60,
 };
 
-static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS],
-		      ipv6_cookie_scratch);
+static DEFINE_PER_CPU(__u32 [16 + 5 + SHA_WORKSPACE_WORDS], ipv6_cookie_scratch);
 
 static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *daddr,
 		       __be16 sport, __be16 dport, u32 count, int c)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 006396e31cb0..3447859bdc57 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -66,7 +66,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 
-#include <linux/crypto.h>
+#include <crypto/hash.h>
 #include <linux/scatterlist.h>
 
 static void	tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb);
@@ -327,6 +327,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	struct tcp_sock *tp;
 	__u32 seq, snd_una;
 	struct sock *sk;
+	bool fatal;
 	int err;
 
 	sk = __inet6_lookup_established(net, &tcp_hashinfo,
@@ -345,8 +346,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		return;
 	}
 	seq = ntohl(th->seq);
+	fatal = icmpv6_err_convert(type, code, &err);
 	if (sk->sk_state == TCP_NEW_SYN_RECV)
-		return tcp_req_err(sk, seq);
+		return tcp_req_err(sk, seq, fatal);
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG)
@@ -400,7 +402,6 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		goto out;
 	}
 
-	icmpv6_err_convert(type, code, &err);
 
 	/* Might be for an request_sock */
 	switch (sk->sk_state) {
@@ -540,7 +541,8 @@ static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
 	bp->len = cpu_to_be32(nbytes);
 
 	sg_init_one(&sg, bp, sizeof(*bp));
-	return crypto_hash_update(&hp->md5_desc, &sg, sizeof(*bp));
+	ahash_request_set_crypt(hp->md5_req, &sg, NULL, sizeof(*bp));
+	return crypto_ahash_update(hp->md5_req);
 }
 
 static int tcp_v6_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
@@ -548,14 +550,14 @@ static int tcp_v6_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
 			       const struct tcphdr *th)
 {
 	struct tcp_md5sig_pool *hp;
-	struct hash_desc *desc;
+	struct ahash_request *req;
 
 	hp = tcp_get_md5sig_pool();
 	if (!hp)
 		goto clear_hash_noput;
-	desc = &hp->md5_desc;
+	req = hp->md5_req;
 
-	if (crypto_hash_init(desc))
+	if (crypto_ahash_init(req))
 		goto clear_hash;
 	if (tcp_v6_md5_hash_pseudoheader(hp, daddr, saddr, th->doff << 2))
 		goto clear_hash;
@@ -563,7 +565,8 @@ static int tcp_v6_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
 		goto clear_hash;
 	if (tcp_md5_hash_key(hp, key))
 		goto clear_hash;
-	if (crypto_hash_final(desc, md5_hash))
+	ahash_request_set_crypt(req, NULL, md5_hash, 0);
+	if (crypto_ahash_final(req))
 		goto clear_hash;
 
 	tcp_put_md5sig_pool();
@@ -583,7 +586,7 @@ static int tcp_v6_md5_hash_skb(char *md5_hash,
 {
 	const struct in6_addr *saddr, *daddr;
 	struct tcp_md5sig_pool *hp;
-	struct hash_desc *desc;
+	struct ahash_request *req;
 	const struct tcphdr *th = tcp_hdr(skb);
 
 	if (sk) { /* valid for establish/request sockets */
@@ -598,9 +601,9 @@ static int tcp_v6_md5_hash_skb(char *md5_hash,
 	hp = tcp_get_md5sig_pool();
 	if (!hp)
 		goto clear_hash_noput;
-	desc = &hp->md5_desc;
+	req = hp->md5_req;
 
-	if (crypto_hash_init(desc))
+	if (crypto_ahash_init(req))
 		goto clear_hash;
 
 	if (tcp_v6_md5_hash_pseudoheader(hp, daddr, saddr, skb->len))
@@ -611,7 +614,8 @@ static int tcp_v6_md5_hash_skb(char *md5_hash,
 		goto clear_hash;
 	if (tcp_md5_hash_key(hp, key))
 		goto clear_hash;
-	if (crypto_hash_final(desc, md5_hash))
+	ahash_request_set_crypt(req, NULL, md5_hash, 0);
+	if (crypto_ahash_final(req))
 		goto clear_hash;
 
 	tcp_put_md5sig_pool();
@@ -1386,7 +1390,7 @@ process:
 
 	if (sk->sk_state == TCP_NEW_SYN_RECV) {
 		struct request_sock *req = inet_reqsk(sk);
-		struct sock *nsk = NULL;
+		struct sock *nsk;
 
 		sk = req->rsk_listener;
 		tcp_v6_fill_cb(skb, hdr, th);
@@ -1394,24 +1398,24 @@ process:
 			reqsk_put(req);
 			goto discard_it;
 		}
-		if (likely(sk->sk_state == TCP_LISTEN)) {
-			nsk = tcp_check_req(sk, skb, req, false);
-		} else {
+		if (unlikely(sk->sk_state != TCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
 		}
+		sock_hold(sk);
+		nsk = tcp_check_req(sk, skb, req, false);
 		if (!nsk) {
 			reqsk_put(req);
-			goto discard_it;
+			goto discard_and_relse;
 		}
 		if (nsk == sk) {
-			sock_hold(sk);
 			reqsk_put(req);
 			tcp_v6_restore_cb(skb);
 		} else if (tcp_child_process(sk, nsk, skb)) {
 			tcp_v6_send_reset(nsk, skb);
-			goto discard_it;
+			goto discard_and_relse;
 		} else {
+			sock_put(sk);
 			return 0;
 		}
 	}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 22e28a44e3c8..422dd014aa2c 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -962,11 +962,9 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		ret = udpv6_queue_rcv_skb(sk, skb);
 		sock_put(sk);
 
-		/* a return value > 0 means to resubmit the input, but
-		 * it wants the return to be -protocol, or 0
-		 */
+		/* a return value > 0 means to resubmit the input */
 		if (ret > 0)
-			return -ret;
+			return ret;
 
 		return 0;
 	}
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index f93c5be612a7..2caaa84ce92d 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -124,8 +124,13 @@ static int l2tp_tunnel_notify(struct genl_family *family,
 	ret = l2tp_nl_tunnel_send(msg, info->snd_portid, info->snd_seq,
 				  NLM_F_ACK, tunnel, cmd);
 
-	if (ret >= 0)
-		return genlmsg_multicast_allns(family, msg, 0,	0, GFP_ATOMIC);
+	if (ret >= 0) {
+		ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC);
+		/* We don't care if no one is listening */
+		if (ret == -ESRCH)
+			ret = 0;
+		return ret;
+	}
 
 	nlmsg_free(msg);
 
@@ -147,8 +152,13 @@ static int l2tp_session_notify(struct genl_family *family,
 	ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq,
 				   NLM_F_ACK, session, cmd);
 
-	if (ret >= 0)
-		return genlmsg_multicast_allns(family, msg, 0,	0, GFP_ATOMIC);
+	if (ret >= 0) {
+		ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC);
+		/* We don't care if no one is listening */
+		if (ret == -ESRCH)
+			ret = 0;
+		return ret;
+	}
 
 	nlmsg_free(msg);
 
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index 10ad4ac1fa0b..367784be5df2 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -291,7 +291,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta,
 	}
 
 	/* prepare A-MPDU MLME for Rx aggregation */
-	tid_agg_rx = kmalloc(sizeof(struct tid_ampdu_rx), GFP_KERNEL);
+	tid_agg_rx = kzalloc(sizeof(*tid_agg_rx), GFP_KERNEL);
 	if (!tid_agg_rx)
 		goto end;
 
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index b84f6aa32c08..f006f4a44c0e 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -92,7 +92,7 @@ struct ieee80211_fragment_entry {
 	u16 extra_len;
 	u16 last_frag;
 	u8 rx_queue;
-	bool ccmp; /* Whether fragments were encrypted with CCMP */
+	bool check_sequential_pn; /* needed for CCMP/GCMP */
 	u8 last_pn[6]; /* PN of the last fragment if CCMP was used */
 };
 
diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c
index 3ece7d1034c8..b54f398cda5d 100644
--- a/net/mac80211/rc80211_minstrel.c
+++ b/net/mac80211/rc80211_minstrel.c
@@ -711,7 +711,7 @@ static u32 minstrel_get_expected_throughput(void *priv_sta)
 	 * computing cur_tp
 	 */
 	tmp_mrs = &mi->r[idx].stats;
-	tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma);
+	tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma) * 10;
 	tmp_cur_tp = tmp_cur_tp * 1200 * 8 / 1024;
 
 	return tmp_cur_tp;
diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index 3928dbd24e25..370d677b547b 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -414,15 +414,16 @@ minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index)
 	    (max_tp_group != MINSTREL_CCK_GROUP))
 		return;
 
+	max_gpr_group = mg->max_group_prob_rate / MCS_GROUP_RATES;
+	max_gpr_idx = mg->max_group_prob_rate % MCS_GROUP_RATES;
+	max_gpr_prob = mi->groups[max_gpr_group].rates[max_gpr_idx].prob_ewma;
+
 	if (mrs->prob_ewma > MINSTREL_FRAC(75, 100)) {
 		cur_tp_avg = minstrel_ht_get_tp_avg(mi, cur_group, cur_idx,
 						    mrs->prob_ewma);
 		if (cur_tp_avg > tmp_tp_avg)
 			mi->max_prob_rate = index;
 
-		max_gpr_group = mg->max_group_prob_rate / MCS_GROUP_RATES;
-		max_gpr_idx = mg->max_group_prob_rate %	MCS_GROUP_RATES;
-		max_gpr_prob = mi->groups[max_gpr_group].rates[max_gpr_idx].prob_ewma;
 		max_gpr_tp_avg = minstrel_ht_get_tp_avg(mi, max_gpr_group,
 							max_gpr_idx,
 							max_gpr_prob);
@@ -431,7 +432,7 @@ minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index)
 	} else {
 		if (mrs->prob_ewma > tmp_prob)
 			mi->max_prob_rate = index;
-		if (mrs->prob_ewma > mg->rates[mg->max_group_prob_rate].prob_ewma)
+		if (mrs->prob_ewma > max_gpr_prob)
 			mg->max_group_prob_rate = index;
 	}
 }
@@ -691,7 +692,7 @@ minstrel_aggr_check(struct ieee80211_sta *pubsta, struct sk_buff *skb)
 	if (likely(sta->ampdu_mlme.tid_tx[tid]))
 		return;
 
-	ieee80211_start_tx_ba_session(pubsta, tid, 5000);
+	ieee80211_start_tx_ba_session(pubsta, tid, 0);
 }
 
 static void
@@ -871,7 +872,7 @@ minstrel_ht_set_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi,
 	 *  - if station is in dynamic SMPS (and streams > 1)
 	 *  - for fallback rates, to increase chances of getting through
 	 */
-	if (offset > 0 &&
+	if (offset > 0 ||
 	    (mi->sta->smps_mode == IEEE80211_SMPS_DYNAMIC &&
 	     group->streams > 1)) {
 		ratetbl->rate[offset].count = ratetbl->rate[offset].count_rts;
@@ -1334,7 +1335,8 @@ static u32 minstrel_ht_get_expected_throughput(void *priv_sta)
 	prob = mi->groups[i].rates[j].prob_ewma;
 
 	/* convert tp_avg from pkt per second in kbps */
-	tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * AVG_PKT_SIZE * 8 / 1024;
+	tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * 10;
+	tp_avg = tp_avg * AVG_PKT_SIZE * 8 / 1024;
 
 	return tp_avg;
 }
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index bc081850ac0e..60d093f40f1d 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1753,7 +1753,7 @@ ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata,
 	entry->seq = seq;
 	entry->rx_queue = rx_queue;
 	entry->last_frag = frag;
-	entry->ccmp = 0;
+	entry->check_sequential_pn = false;
 	entry->extra_len = 0;
 
 	return entry;
@@ -1849,15 +1849,27 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
 						 rx->seqno_idx, &(rx->skb));
 		if (rx->key &&
 		    (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP ||
-		     rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256) &&
+		     rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256 ||
+		     rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP ||
+		     rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP_256) &&
 		    ieee80211_has_protected(fc)) {
 			int queue = rx->security_idx;
-			/* Store CCMP PN so that we can verify that the next
-			 * fragment has a sequential PN value. */
-			entry->ccmp = 1;
+
+			/* Store CCMP/GCMP PN so that we can verify that the
+			 * next fragment has a sequential PN value.
+			 */
+			entry->check_sequential_pn = true;
 			memcpy(entry->last_pn,
 			       rx->key->u.ccmp.rx_pn[queue],
 			       IEEE80211_CCMP_PN_LEN);
+			BUILD_BUG_ON(offsetof(struct ieee80211_key,
+					      u.ccmp.rx_pn) !=
+				     offsetof(struct ieee80211_key,
+					      u.gcmp.rx_pn));
+			BUILD_BUG_ON(sizeof(rx->key->u.ccmp.rx_pn[queue]) !=
+				     sizeof(rx->key->u.gcmp.rx_pn[queue]));
+			BUILD_BUG_ON(IEEE80211_CCMP_PN_LEN !=
+				     IEEE80211_GCMP_PN_LEN);
 		}
 		return RX_QUEUED;
 	}
@@ -1872,15 +1884,21 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
 		return RX_DROP_MONITOR;
 	}
 
-	/* Verify that MPDUs within one MSDU have sequential PN values.
-	 * (IEEE 802.11i, 8.3.3.4.5) */
-	if (entry->ccmp) {
+	/* "The receiver shall discard MSDUs and MMPDUs whose constituent
+	 *  MPDU PN values are not incrementing in steps of 1."
+	 * see IEEE P802.11-REVmc/D5.0, 12.5.3.4.4, item d (for CCMP)
+	 * and IEEE P802.11-REVmc/D5.0, 12.5.5.4.4, item d (for GCMP)
+	 */
+	if (entry->check_sequential_pn) {
 		int i;
 		u8 pn[IEEE80211_CCMP_PN_LEN], *rpn;
 		int queue;
+
 		if (!rx->key ||
 		    (rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP &&
-		     rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256))
+		     rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256 &&
+		     rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP &&
+		     rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP_256))
 			return RX_DROP_UNUSABLE;
 		memcpy(pn, entry->last_pn, IEEE80211_CCMP_PN_LEN);
 		for (i = IEEE80211_CCMP_PN_LEN - 1; i >= 0; i--) {
@@ -3366,6 +3384,7 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx)
 				return false;
 			/* ignore action frames to TDLS-peers */
 			if (ieee80211_is_action(hdr->frame_control) &&
+			    !is_broadcast_ether_addr(bssid) &&
 			    !ether_addr_equal(bssid, hdr->addr1))
 				return false;
 		}
diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c
index a13d02b7cee4..6a3e1c2181d3 100644
--- a/net/mac802154/llsec.c
+++ b/net/mac802154/llsec.c
@@ -17,9 +17,9 @@
 #include <linux/err.h>
 #include <linux/bug.h>
 #include <linux/completion.h>
-#include <linux/crypto.h>
 #include <linux/ieee802154.h>
 #include <crypto/aead.h>
+#include <crypto/skcipher.h>
 
 #include "ieee802154_i.h"
 #include "llsec.h"
@@ -144,18 +144,18 @@ llsec_key_alloc(const struct ieee802154_llsec_key *template)
 			goto err_tfm;
 	}
 
-	key->tfm0 = crypto_alloc_blkcipher("ctr(aes)", 0, CRYPTO_ALG_ASYNC);
+	key->tfm0 = crypto_alloc_skcipher("ctr(aes)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(key->tfm0))
 		goto err_tfm;
 
-	if (crypto_blkcipher_setkey(key->tfm0, template->key,
-				    IEEE802154_LLSEC_KEY_SIZE))
+	if (crypto_skcipher_setkey(key->tfm0, template->key,
+				   IEEE802154_LLSEC_KEY_SIZE))
 		goto err_tfm0;
 
 	return key;
 
 err_tfm0:
-	crypto_free_blkcipher(key->tfm0);
+	crypto_free_skcipher(key->tfm0);
 err_tfm:
 	for (i = 0; i < ARRAY_SIZE(key->tfm); i++)
 		if (key->tfm[i])
@@ -175,7 +175,7 @@ static void llsec_key_release(struct kref *ref)
 	for (i = 0; i < ARRAY_SIZE(key->tfm); i++)
 		crypto_free_aead(key->tfm[i]);
 
-	crypto_free_blkcipher(key->tfm0);
+	crypto_free_skcipher(key->tfm0);
 	kzfree(key);
 }
 
@@ -620,15 +620,17 @@ llsec_do_encrypt_unauth(struct sk_buff *skb, const struct mac802154_llsec *sec,
 {
 	u8 iv[16];
 	struct scatterlist src;
-	struct blkcipher_desc req = {
-		.tfm = key->tfm0,
-		.info = iv,
-		.flags = 0,
-	};
+	SKCIPHER_REQUEST_ON_STACK(req, key->tfm0);
+	int err;
 
 	llsec_geniv(iv, sec->params.hwaddr, &hdr->sec);
 	sg_init_one(&src, skb->data, skb->len);
-	return crypto_blkcipher_encrypt_iv(&req, &src, &src, skb->len);
+	skcipher_request_set_tfm(req, key->tfm0);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, &src, &src, skb->len, iv);
+	err = crypto_skcipher_encrypt(req);
+	skcipher_request_zero(req);
+	return err;
 }
 
 static struct crypto_aead*
@@ -830,11 +832,8 @@ llsec_do_decrypt_unauth(struct sk_buff *skb, const struct mac802154_llsec *sec,
 	unsigned char *data;
 	int datalen;
 	struct scatterlist src;
-	struct blkcipher_desc req = {
-		.tfm = key->tfm0,
-		.info = iv,
-		.flags = 0,
-	};
+	SKCIPHER_REQUEST_ON_STACK(req, key->tfm0);
+	int err;
 
 	llsec_geniv(iv, dev_addr, &hdr->sec);
 	data = skb_mac_header(skb) + skb->mac_len;
@@ -842,7 +841,13 @@ llsec_do_decrypt_unauth(struct sk_buff *skb, const struct mac802154_llsec *sec,
 
 	sg_init_one(&src, data, datalen);
 
-	return crypto_blkcipher_decrypt_iv(&req, &src, &src, datalen);
+	skcipher_request_set_tfm(req, key->tfm0);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, &src, &src, datalen, iv);
+
+	err = crypto_skcipher_decrypt(req);
+	skcipher_request_zero(req);
+	return err;
 }
 
 static int
diff --git a/net/mac802154/llsec.h b/net/mac802154/llsec.h
index 950578e1d7be..6f3b658e3279 100644
--- a/net/mac802154/llsec.h
+++ b/net/mac802154/llsec.h
@@ -19,7 +19,6 @@
 
 #include <linux/slab.h>
 #include <linux/hashtable.h>
-#include <linux/crypto.h>
 #include <linux/kref.h>
 #include <linux/spinlock.h>
 #include <net/af_ieee802154.h>
@@ -30,7 +29,7 @@ struct mac802154_llsec_key {
 
 	/* one tfm for each authsize (4/8/16) */
 	struct crypto_aead *tfm[3];
-	struct crypto_blkcipher *tfm0;
+	struct crypto_skcipher *tfm0;
 
 	struct kref ref;
 };
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 8c067e6663a1..95e757c377f9 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -891,7 +891,7 @@ config NETFILTER_XT_TARGET_TEE
 	depends on IPV6 || IPV6=n
 	depends on !NF_CONNTRACK || NF_CONNTRACK
 	select NF_DUP_IPV4
-	select NF_DUP_IPV6 if IP6_NF_IPTABLES != n
+	select NF_DUP_IPV6 if IPV6
 	---help---
 	This option adds a "TEE" target with which a packet can be cloned and
 	this clone be rerouted to another nexthop.
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 58882de06bd7..f60b4fdeeb8c 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1412,6 +1412,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data),
 		}
 		spin_unlock(lockp);
 		local_bh_enable();
+		cond_resched();
 	}
 
 	for_each_possible_cpu(cpu) {
@@ -1424,6 +1425,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data),
 				set_bit(IPS_DYING_BIT, &ct->status);
 		}
 		spin_unlock_bh(&pcpu->lock);
+		cond_resched();
 	}
 	return NULL;
 found:
@@ -1440,6 +1442,8 @@ void nf_ct_iterate_cleanup(struct net *net,
 	struct nf_conn *ct;
 	unsigned int bucket = 0;
 
+	might_sleep();
+
 	while ((ct = get_next_corpse(net, iter, data, &bucket)) != NULL) {
 		/* Time to push up daises... */
 		if (del_timer(&ct->timeout))
@@ -1448,6 +1452,7 @@ void nf_ct_iterate_cleanup(struct net *net,
 		/* ... else the timer will get him soon. */
 
 		nf_ct_put(ct);
+		cond_resched();
 	}
 }
 EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup);
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index a7ba23353dab..857ae89633af 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -311,14 +311,14 @@ replay:
 #endif
 		{
 			nfnl_unlock(subsys_id);
-			netlink_ack(skb, nlh, -EOPNOTSUPP);
+			netlink_ack(oskb, nlh, -EOPNOTSUPP);
 			return kfree_skb(skb);
 		}
 	}
 
 	if (!ss->commit || !ss->abort) {
 		nfnl_unlock(subsys_id);
-		netlink_ack(skb, nlh, -EOPNOTSUPP);
+		netlink_ack(oskb, nlh, -EOPNOTSUPP);
 		return kfree_skb(skb);
 	}
 
@@ -328,10 +328,12 @@ replay:
 		nlh = nlmsg_hdr(skb);
 		err = 0;
 
-		if (nlmsg_len(nlh) < sizeof(struct nfgenmsg) ||
-		    skb->len < nlh->nlmsg_len) {
-			err = -EINVAL;
-			goto ack;
+		if (nlh->nlmsg_len < NLMSG_HDRLEN ||
+		    skb->len < nlh->nlmsg_len ||
+		    nlmsg_len(nlh) < sizeof(struct nfgenmsg)) {
+			nfnl_err_reset(&err_list);
+			status |= NFNL_BATCH_FAILURE;
+			goto done;
 		}
 
 		/* Only requests are handled by the kernel */
@@ -406,7 +408,7 @@ ack:
 				 * pointing to the batch header.
 				 */
 				nfnl_err_reset(&err_list);
-				netlink_ack(skb, nlmsg_hdr(oskb), -ENOMEM);
+				netlink_ack(oskb, nlmsg_hdr(oskb), -ENOMEM);
 				status |= NFNL_BATCH_FAILURE;
 				goto done;
 			}
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 94837d236ab0..2671b9deb103 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -312,7 +312,7 @@ static void ctnl_untimeout(struct net *net, struct ctnl_timeout *timeout)
 			hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode)
 				untimeout(h, timeout);
 		}
-		nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
+		spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
 	}
 	local_bh_enable();
 }
diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c
index c7808fc19719..c9743f78f219 100644
--- a/net/netfilter/nft_counter.c
+++ b/net/netfilter/nft_counter.c
@@ -100,7 +100,7 @@ static int nft_counter_init(const struct nft_ctx *ctx,
 
 	cpu_stats = netdev_alloc_pcpu_stats(struct nft_counter_percpu);
 	if (cpu_stats == NULL)
-		return ENOMEM;
+		return -ENOMEM;
 
 	preempt_disable();
 	this_cpu = this_cpu_ptr(cpu_stats);
@@ -138,7 +138,7 @@ static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src)
 	cpu_stats = __netdev_alloc_pcpu_stats(struct nft_counter_percpu,
 					      GFP_ATOMIC);
 	if (cpu_stats == NULL)
-		return ENOMEM;
+		return -ENOMEM;
 
 	preempt_disable();
 	this_cpu = this_cpu_ptr(cpu_stats);
diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c
index 3eff7b67cdf2..6e57a3966dc5 100644
--- a/net/netfilter/xt_TEE.c
+++ b/net/netfilter/xt_TEE.c
@@ -38,7 +38,7 @@ tee_tg4(struct sk_buff *skb, const struct xt_action_param *par)
 	return XT_CONTINUE;
 }
 
-#if IS_ENABLED(CONFIG_NF_DUP_IPV6)
+#if IS_ENABLED(CONFIG_IPV6)
 static unsigned int
 tee_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 {
@@ -131,7 +131,7 @@ static struct xt_target tee_tg_reg[] __read_mostly = {
 		.destroy    = tee_tg_destroy,
 		.me         = THIS_MODULE,
 	},
-#if IS_ENABLED(CONFIG_NF_DUP_IPV6)
+#if IS_ENABLED(CONFIG_IPV6)
 	{
 		.name       = "TEE",
 		.revision   = 1,
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index 1605691d9414..5eb7694348b5 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -90,7 +90,9 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
 	int err;
 	struct vxlan_config conf = {
 		.no_share = true,
-		.flags = VXLAN_F_COLLECT_METADATA,
+		.flags = VXLAN_F_COLLECT_METADATA | VXLAN_F_UDP_ZERO_CSUM6_RX,
+		/* Don't restrict the packets that can be sent by MTU */
+		.mtu = IP_MAX_MTU,
 	};
 
 	if (!options) {
diff --git a/net/rds/page.c b/net/rds/page.c
index 5a14e6d6a926..616f21f4e7d7 100644
--- a/net/rds/page.c
+++ b/net/rds/page.c
@@ -42,8 +42,8 @@ struct rds_page_remainder {
 	unsigned long	r_offset;
 };
 
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_page_remainder,
-				     rds_page_remainders);
+static
+DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_page_remainder, rds_page_remainders);
 
 /*
  * returns 0 on success or -errno on failure.
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 2934a73a5981..71598f5b11b7 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -252,7 +252,7 @@ struct rxrpc_connection {
 	struct rxrpc_security	*security;	/* applied security module */
 	struct key		*key;		/* security for this connection (client) */
 	struct key		*server_key;	/* security for this service */
-	struct crypto_blkcipher	*cipher;	/* encryption handle */
+	struct crypto_skcipher	*cipher;	/* encryption handle */
 	struct rxrpc_crypt	csum_iv;	/* packet checksum base */
 	unsigned long		events;
 #define RXRPC_CONN_CHALLENGE	0		/* send challenge packet */
diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c
index 3f6571651d32..3fb492eedeb9 100644
--- a/net/rxrpc/ar-key.c
+++ b/net/rxrpc/ar-key.c
@@ -12,11 +12,11 @@
  *	"afs@CAMBRIDGE.REDHAT.COM>
  */
 
+#include <crypto/skcipher.h>
 #include <linux/module.h>
 #include <linux/net.h>
 #include <linux/skbuff.h>
 #include <linux/key-type.h>
-#include <linux/crypto.h>
 #include <linux/ctype.h>
 #include <linux/slab.h>
 #include <net/sock.h>
@@ -824,7 +824,7 @@ static void rxrpc_free_preparse(struct key_preparsed_payload *prep)
  */
 static int rxrpc_preparse_s(struct key_preparsed_payload *prep)
 {
-	struct crypto_blkcipher *ci;
+	struct crypto_skcipher *ci;
 
 	_enter("%zu", prep->datalen);
 
@@ -833,13 +833,13 @@ static int rxrpc_preparse_s(struct key_preparsed_payload *prep)
 
 	memcpy(&prep->payload.data[2], prep->data, 8);
 
-	ci = crypto_alloc_blkcipher("pcbc(des)", 0, CRYPTO_ALG_ASYNC);
+	ci = crypto_alloc_skcipher("pcbc(des)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(ci)) {
 		_leave(" = %ld", PTR_ERR(ci));
 		return PTR_ERR(ci);
 	}
 
-	if (crypto_blkcipher_setkey(ci, prep->data, 8) < 0)
+	if (crypto_skcipher_setkey(ci, prep->data, 8) < 0)
 		BUG();
 
 	prep->payload.data[0] = ci;
@@ -853,7 +853,7 @@ static int rxrpc_preparse_s(struct key_preparsed_payload *prep)
 static void rxrpc_free_preparse_s(struct key_preparsed_payload *prep)
 {
 	if (prep->payload.data[0])
-		crypto_free_blkcipher(prep->payload.data[0]);
+		crypto_free_skcipher(prep->payload.data[0]);
 }
 
 /*
@@ -870,7 +870,7 @@ static void rxrpc_destroy(struct key *key)
 static void rxrpc_destroy_s(struct key *key)
 {
 	if (key->payload.data[0]) {
-		crypto_free_blkcipher(key->payload.data[0]);
+		crypto_free_skcipher(key->payload.data[0]);
 		key->payload.data[0] = NULL;
 	}
 }
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index d7a9ab5a9d9c..0d96b48a6492 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -9,11 +9,11 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#include <crypto/skcipher.h>
 #include <linux/module.h>
 #include <linux/net.h>
 #include <linux/skbuff.h>
 #include <linux/udp.h>
-#include <linux/crypto.h>
 #include <linux/scatterlist.h>
 #include <linux/ctype.h>
 #include <linux/slab.h>
@@ -53,7 +53,7 @@ MODULE_LICENSE("GPL");
  * alloc routine, but since we have it to hand, we use it to decrypt RESPONSE
  * packets
  */
-static struct crypto_blkcipher *rxkad_ci;
+static struct crypto_skcipher *rxkad_ci;
 static DEFINE_MUTEX(rxkad_ci_mutex);
 
 /*
@@ -61,7 +61,7 @@ static DEFINE_MUTEX(rxkad_ci_mutex);
  */
 static int rxkad_init_connection_security(struct rxrpc_connection *conn)
 {
-	struct crypto_blkcipher *ci;
+	struct crypto_skcipher *ci;
 	struct rxrpc_key_token *token;
 	int ret;
 
@@ -70,15 +70,15 @@ static int rxkad_init_connection_security(struct rxrpc_connection *conn)
 	token = conn->key->payload.data[0];
 	conn->security_ix = token->security_index;
 
-	ci = crypto_alloc_blkcipher("pcbc(fcrypt)", 0, CRYPTO_ALG_ASYNC);
+	ci = crypto_alloc_skcipher("pcbc(fcrypt)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(ci)) {
 		_debug("no cipher");
 		ret = PTR_ERR(ci);
 		goto error;
 	}
 
-	if (crypto_blkcipher_setkey(ci, token->kad->session_key,
-				    sizeof(token->kad->session_key)) < 0)
+	if (crypto_skcipher_setkey(ci, token->kad->session_key,
+				   sizeof(token->kad->session_key)) < 0)
 		BUG();
 
 	switch (conn->security_level) {
@@ -113,7 +113,7 @@ error:
 static void rxkad_prime_packet_security(struct rxrpc_connection *conn)
 {
 	struct rxrpc_key_token *token;
-	struct blkcipher_desc desc;
+	SKCIPHER_REQUEST_ON_STACK(req, conn->cipher);
 	struct scatterlist sg[2];
 	struct rxrpc_crypt iv;
 	struct {
@@ -128,10 +128,6 @@ static void rxkad_prime_packet_security(struct rxrpc_connection *conn)
 	token = conn->key->payload.data[0];
 	memcpy(&iv, token->kad->session_key, sizeof(iv));
 
-	desc.tfm = conn->cipher;
-	desc.info = iv.x;
-	desc.flags = 0;
-
 	tmpbuf.x[0] = conn->epoch;
 	tmpbuf.x[1] = conn->cid;
 	tmpbuf.x[2] = 0;
@@ -139,7 +135,13 @@ static void rxkad_prime_packet_security(struct rxrpc_connection *conn)
 
 	sg_init_one(&sg[0], &tmpbuf, sizeof(tmpbuf));
 	sg_init_one(&sg[1], &tmpbuf, sizeof(tmpbuf));
-	crypto_blkcipher_encrypt_iv(&desc, &sg[0], &sg[1], sizeof(tmpbuf));
+
+	skcipher_request_set_tfm(req, conn->cipher);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, &sg[1], &sg[0], sizeof(tmpbuf), iv.x);
+
+	crypto_skcipher_encrypt(req);
+	skcipher_request_zero(req);
 
 	memcpy(&conn->csum_iv, &tmpbuf.x[2], sizeof(conn->csum_iv));
 	ASSERTCMP(conn->csum_iv.n[0], ==, tmpbuf.x[2]);
@@ -156,7 +158,7 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call,
 				    void *sechdr)
 {
 	struct rxrpc_skb_priv *sp;
-	struct blkcipher_desc desc;
+	SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher);
 	struct rxrpc_crypt iv;
 	struct scatterlist sg[2];
 	struct {
@@ -177,13 +179,16 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call,
 
 	/* start the encryption afresh */
 	memset(&iv, 0, sizeof(iv));
-	desc.tfm = call->conn->cipher;
-	desc.info = iv.x;
-	desc.flags = 0;
 
 	sg_init_one(&sg[0], &tmpbuf, sizeof(tmpbuf));
 	sg_init_one(&sg[1], &tmpbuf, sizeof(tmpbuf));
-	crypto_blkcipher_encrypt_iv(&desc, &sg[0], &sg[1], sizeof(tmpbuf));
+
+	skcipher_request_set_tfm(req, call->conn->cipher);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, &sg[1], &sg[0], sizeof(tmpbuf), iv.x);
+
+	crypto_skcipher_encrypt(req);
+	skcipher_request_zero(req);
 
 	memcpy(sechdr, &tmpbuf, sizeof(tmpbuf));
 
@@ -203,13 +208,14 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call,
 	struct rxkad_level2_hdr rxkhdr
 		__attribute__((aligned(8))); /* must be all on one page */
 	struct rxrpc_skb_priv *sp;
-	struct blkcipher_desc desc;
+	SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher);
 	struct rxrpc_crypt iv;
 	struct scatterlist sg[16];
 	struct sk_buff *trailer;
 	unsigned int len;
 	u16 check;
 	int nsg;
+	int err;
 
 	sp = rxrpc_skb(skb);
 
@@ -223,28 +229,38 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call,
 	/* encrypt from the session key */
 	token = call->conn->key->payload.data[0];
 	memcpy(&iv, token->kad->session_key, sizeof(iv));
-	desc.tfm = call->conn->cipher;
-	desc.info = iv.x;
-	desc.flags = 0;
 
 	sg_init_one(&sg[0], sechdr, sizeof(rxkhdr));
 	sg_init_one(&sg[1], &rxkhdr, sizeof(rxkhdr));
-	crypto_blkcipher_encrypt_iv(&desc, &sg[0], &sg[1], sizeof(rxkhdr));
+
+	skcipher_request_set_tfm(req, call->conn->cipher);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, &sg[1], &sg[0], sizeof(rxkhdr), iv.x);
+
+	crypto_skcipher_encrypt(req);
 
 	/* we want to encrypt the skbuff in-place */
 	nsg = skb_cow_data(skb, 0, &trailer);
+	err = -ENOMEM;
 	if (nsg < 0 || nsg > 16)
-		return -ENOMEM;
+		goto out;
 
 	len = data_size + call->conn->size_align - 1;
 	len &= ~(call->conn->size_align - 1);
 
 	sg_init_table(sg, nsg);
 	skb_to_sgvec(skb, sg, 0, len);
-	crypto_blkcipher_encrypt_iv(&desc, sg, sg, len);
+
+	skcipher_request_set_crypt(req, sg, sg, len, iv.x);
+
+	crypto_skcipher_encrypt(req);
 
 	_leave(" = 0");
-	return 0;
+	err = 0;
+
+out:
+	skcipher_request_zero(req);
+	return err;
 }
 
 /*
@@ -256,7 +272,7 @@ static int rxkad_secure_packet(const struct rxrpc_call *call,
 				void *sechdr)
 {
 	struct rxrpc_skb_priv *sp;
-	struct blkcipher_desc desc;
+	SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher);
 	struct rxrpc_crypt iv;
 	struct scatterlist sg[2];
 	struct {
@@ -281,9 +297,6 @@ static int rxkad_secure_packet(const struct rxrpc_call *call,
 
 	/* continue encrypting from where we left off */
 	memcpy(&iv, call->conn->csum_iv.x, sizeof(iv));
-	desc.tfm = call->conn->cipher;
-	desc.info = iv.x;
-	desc.flags = 0;
 
 	/* calculate the security checksum */
 	x = htonl(call->channel << (32 - RXRPC_CIDSHIFT));
@@ -293,7 +306,13 @@ static int rxkad_secure_packet(const struct rxrpc_call *call,
 
 	sg_init_one(&sg[0], &tmpbuf, sizeof(tmpbuf));
 	sg_init_one(&sg[1], &tmpbuf, sizeof(tmpbuf));
-	crypto_blkcipher_encrypt_iv(&desc, &sg[0], &sg[1], sizeof(tmpbuf));
+
+	skcipher_request_set_tfm(req, call->conn->cipher);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, &sg[1], &sg[0], sizeof(tmpbuf), iv.x);
+
+	crypto_skcipher_encrypt(req);
+	skcipher_request_zero(req);
 
 	y = ntohl(tmpbuf.x[1]);
 	y = (y >> 16) & 0xffff;
@@ -330,7 +349,7 @@ static int rxkad_verify_packet_auth(const struct rxrpc_call *call,
 {
 	struct rxkad_level1_hdr sechdr;
 	struct rxrpc_skb_priv *sp;
-	struct blkcipher_desc desc;
+	SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher);
 	struct rxrpc_crypt iv;
 	struct scatterlist sg[16];
 	struct sk_buff *trailer;
@@ -352,11 +371,13 @@ static int rxkad_verify_packet_auth(const struct rxrpc_call *call,
 
 	/* start the decryption afresh */
 	memset(&iv, 0, sizeof(iv));
-	desc.tfm = call->conn->cipher;
-	desc.info = iv.x;
-	desc.flags = 0;
 
-	crypto_blkcipher_decrypt_iv(&desc, sg, sg, 8);
+	skcipher_request_set_tfm(req, call->conn->cipher);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, sg, sg, 8, iv.x);
+
+	crypto_skcipher_decrypt(req);
+	skcipher_request_zero(req);
 
 	/* remove the decrypted packet length */
 	if (skb_copy_bits(skb, 0, &sechdr, sizeof(sechdr)) < 0)
@@ -405,7 +426,7 @@ static int rxkad_verify_packet_encrypt(const struct rxrpc_call *call,
 	const struct rxrpc_key_token *token;
 	struct rxkad_level2_hdr sechdr;
 	struct rxrpc_skb_priv *sp;
-	struct blkcipher_desc desc;
+	SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher);
 	struct rxrpc_crypt iv;
 	struct scatterlist _sg[4], *sg;
 	struct sk_buff *trailer;
@@ -435,11 +456,13 @@ static int rxkad_verify_packet_encrypt(const struct rxrpc_call *call,
 	/* decrypt from the session key */
 	token = call->conn->key->payload.data[0];
 	memcpy(&iv, token->kad->session_key, sizeof(iv));
-	desc.tfm = call->conn->cipher;
-	desc.info = iv.x;
-	desc.flags = 0;
 
-	crypto_blkcipher_decrypt_iv(&desc, sg, sg, skb->len);
+	skcipher_request_set_tfm(req, call->conn->cipher);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, sg, sg, skb->len, iv.x);
+
+	crypto_skcipher_decrypt(req);
+	skcipher_request_zero(req);
 	if (sg != _sg)
 		kfree(sg);
 
@@ -487,7 +510,7 @@ static int rxkad_verify_packet(const struct rxrpc_call *call,
 			       struct sk_buff *skb,
 			       u32 *_abort_code)
 {
-	struct blkcipher_desc desc;
+	SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher);
 	struct rxrpc_skb_priv *sp;
 	struct rxrpc_crypt iv;
 	struct scatterlist sg[2];
@@ -516,9 +539,6 @@ static int rxkad_verify_packet(const struct rxrpc_call *call,
 
 	/* continue encrypting from where we left off */
 	memcpy(&iv, call->conn->csum_iv.x, sizeof(iv));
-	desc.tfm = call->conn->cipher;
-	desc.info = iv.x;
-	desc.flags = 0;
 
 	/* validate the security checksum */
 	x = htonl(call->channel << (32 - RXRPC_CIDSHIFT));
@@ -528,7 +548,13 @@ static int rxkad_verify_packet(const struct rxrpc_call *call,
 
 	sg_init_one(&sg[0], &tmpbuf, sizeof(tmpbuf));
 	sg_init_one(&sg[1], &tmpbuf, sizeof(tmpbuf));
-	crypto_blkcipher_encrypt_iv(&desc, &sg[0], &sg[1], sizeof(tmpbuf));
+
+	skcipher_request_set_tfm(req, call->conn->cipher);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, &sg[1], &sg[0], sizeof(tmpbuf), iv.x);
+
+	crypto_skcipher_encrypt(req);
+	skcipher_request_zero(req);
 
 	y = ntohl(tmpbuf.x[1]);
 	y = (y >> 16) & 0xffff;
@@ -718,18 +744,21 @@ static void rxkad_encrypt_response(struct rxrpc_connection *conn,
 				   struct rxkad_response *resp,
 				   const struct rxkad_key *s2)
 {
-	struct blkcipher_desc desc;
+	SKCIPHER_REQUEST_ON_STACK(req, conn->cipher);
 	struct rxrpc_crypt iv;
 	struct scatterlist sg[2];
 
 	/* continue encrypting from where we left off */
 	memcpy(&iv, s2->session_key, sizeof(iv));
-	desc.tfm = conn->cipher;
-	desc.info = iv.x;
-	desc.flags = 0;
 
 	rxkad_sg_set_buf2(sg, &resp->encrypted, sizeof(resp->encrypted));
-	crypto_blkcipher_encrypt_iv(&desc, sg, sg, sizeof(resp->encrypted));
+
+	skcipher_request_set_tfm(req, conn->cipher);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, sg, sg, sizeof(resp->encrypted), iv.x);
+
+	crypto_skcipher_encrypt(req);
+	skcipher_request_zero(req);
 }
 
 /*
@@ -822,7 +851,7 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
 				time_t *_expiry,
 				u32 *_abort_code)
 {
-	struct blkcipher_desc desc;
+	struct skcipher_request *req;
 	struct rxrpc_crypt iv, key;
 	struct scatterlist sg[1];
 	struct in_addr addr;
@@ -853,12 +882,21 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
 
 	memcpy(&iv, &conn->server_key->payload.data[2], sizeof(iv));
 
-	desc.tfm = conn->server_key->payload.data[0];
-	desc.info = iv.x;
-	desc.flags = 0;
+	req = skcipher_request_alloc(conn->server_key->payload.data[0],
+				     GFP_NOFS);
+	if (!req) {
+		*_abort_code = RXKADNOAUTH;
+		ret = -ENOMEM;
+		goto error;
+	}
 
 	sg_init_one(&sg[0], ticket, ticket_len);
-	crypto_blkcipher_decrypt_iv(&desc, sg, sg, ticket_len);
+
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, sg, sg, ticket_len, iv.x);
+
+	crypto_skcipher_decrypt(req);
+	skcipher_request_free(req);
 
 	p = ticket;
 	end = p + ticket_len;
@@ -966,7 +1004,7 @@ static void rxkad_decrypt_response(struct rxrpc_connection *conn,
 				   struct rxkad_response *resp,
 				   const struct rxrpc_crypt *session_key)
 {
-	struct blkcipher_desc desc;
+	SKCIPHER_REQUEST_ON_STACK(req, rxkad_ci);
 	struct scatterlist sg[2];
 	struct rxrpc_crypt iv;
 
@@ -976,17 +1014,21 @@ static void rxkad_decrypt_response(struct rxrpc_connection *conn,
 	ASSERT(rxkad_ci != NULL);
 
 	mutex_lock(&rxkad_ci_mutex);
-	if (crypto_blkcipher_setkey(rxkad_ci, session_key->x,
-				    sizeof(*session_key)) < 0)
+	if (crypto_skcipher_setkey(rxkad_ci, session_key->x,
+				   sizeof(*session_key)) < 0)
 		BUG();
 
 	memcpy(&iv, session_key, sizeof(iv));
-	desc.tfm = rxkad_ci;
-	desc.info = iv.x;
-	desc.flags = 0;
 
 	rxkad_sg_set_buf2(sg, &resp->encrypted, sizeof(resp->encrypted));
-	crypto_blkcipher_decrypt_iv(&desc, sg, sg, sizeof(resp->encrypted));
+
+	skcipher_request_set_tfm(req, rxkad_ci);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, sg, sg, sizeof(resp->encrypted), iv.x);
+
+	crypto_skcipher_decrypt(req);
+	skcipher_request_zero(req);
+
 	mutex_unlock(&rxkad_ci_mutex);
 
 	_leave("");
@@ -1115,7 +1157,7 @@ static void rxkad_clear(struct rxrpc_connection *conn)
 	_enter("");
 
 	if (conn->cipher)
-		crypto_free_blkcipher(conn->cipher);
+		crypto_free_skcipher(conn->cipher);
 }
 
 /*
@@ -1141,7 +1183,7 @@ static __init int rxkad_init(void)
 
 	/* pin the cipher we need so that the crypto layer doesn't invoke
 	 * keventd to go get it */
-	rxkad_ci = crypto_alloc_blkcipher("pcbc(fcrypt)", 0, CRYPTO_ALG_ASYNC);
+	rxkad_ci = crypto_alloc_skcipher("pcbc(fcrypt)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(rxkad_ci))
 		return PTR_ERR(rxkad_ci);
 
@@ -1155,7 +1197,7 @@ static __exit void rxkad_exit(void)
 	_enter("");
 
 	rxrpc_unregister_security(&rxkad);
-	crypto_free_blkcipher(rxkad_ci);
+	crypto_free_skcipher(rxkad_ci);
 }
 
 module_exit(rxkad_exit);
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index d05869646515..6b70399ab781 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -62,6 +62,7 @@ static void ipt_destroy_target(struct xt_entry_target *t)
 	struct xt_tgdtor_param par = {
 		.target   = t->u.kernel.target,
 		.targinfo = t->data,
+		.family   = NFPROTO_IPV4,
 	};
 	if (par.target->destroy != NULL)
 		par.target->destroy(&par);
@@ -195,6 +196,7 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a,
 	par.hooknum  = ipt->tcfi_hook;
 	par.target   = ipt->tcfi_t->u.kernel.target;
 	par.targinfo = ipt->tcfi_t->data;
+	par.family   = NFPROTO_IPV4;
 	ret = par.target->target(skb, &par);
 
 	switch (ret) {
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index b5c2cf2aa6d4..af1acf009866 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1852,6 +1852,7 @@ reset:
 	}
 
 	tp = old_tp;
+	protocol = tc_skb_protocol(skb);
 	goto reclassify;
 #endif
 }
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 1543e39f47c3..912eb1685a5d 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -27,9 +27,9 @@
  *   Vlad Yasevich     <vladislav.yasevich@hp.com>
  */
 
+#include <crypto/hash.h>
 #include <linux/slab.h>
 #include <linux/types.h>
-#include <linux/crypto.h>
 #include <linux/scatterlist.h>
 #include <net/sctp/sctp.h>
 #include <net/sctp/auth.h>
@@ -448,7 +448,7 @@ struct sctp_shared_key *sctp_auth_get_shkey(
  */
 int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp)
 {
-	struct crypto_hash *tfm = NULL;
+	struct crypto_shash *tfm = NULL;
 	__u16   id;
 
 	/* If AUTH extension is disabled, we are done */
@@ -462,9 +462,8 @@ int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp)
 		return 0;
 
 	/* Allocated the array of pointers to transorms */
-	ep->auth_hmacs = kzalloc(
-			    sizeof(struct crypto_hash *) * SCTP_AUTH_NUM_HMACS,
-			    gfp);
+	ep->auth_hmacs = kzalloc(sizeof(struct crypto_shash *) *
+				 SCTP_AUTH_NUM_HMACS, gfp);
 	if (!ep->auth_hmacs)
 		return -ENOMEM;
 
@@ -483,8 +482,7 @@ int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp)
 			continue;
 
 		/* Allocate the ID */
-		tfm = crypto_alloc_hash(sctp_hmac_list[id].hmac_name, 0,
-					CRYPTO_ALG_ASYNC);
+		tfm = crypto_alloc_shash(sctp_hmac_list[id].hmac_name, 0, 0);
 		if (IS_ERR(tfm))
 			goto out_err;
 
@@ -500,7 +498,7 @@ out_err:
 }
 
 /* Destroy the hmac tfm array */
-void sctp_auth_destroy_hmacs(struct crypto_hash *auth_hmacs[])
+void sctp_auth_destroy_hmacs(struct crypto_shash *auth_hmacs[])
 {
 	int i;
 
@@ -508,8 +506,7 @@ void sctp_auth_destroy_hmacs(struct crypto_hash *auth_hmacs[])
 		return;
 
 	for (i = 0; i < SCTP_AUTH_NUM_HMACS; i++) {
-		if (auth_hmacs[i])
-			crypto_free_hash(auth_hmacs[i]);
+		crypto_free_shash(auth_hmacs[i]);
 	}
 	kfree(auth_hmacs);
 }
@@ -709,8 +706,7 @@ void sctp_auth_calculate_hmac(const struct sctp_association *asoc,
 			      struct sctp_auth_chunk *auth,
 			      gfp_t gfp)
 {
-	struct scatterlist sg;
-	struct hash_desc desc;
+	struct crypto_shash *tfm;
 	struct sctp_auth_bytes *asoc_key;
 	__u16 key_id, hmac_id;
 	__u8 *digest;
@@ -742,16 +738,22 @@ void sctp_auth_calculate_hmac(const struct sctp_association *asoc,
 
 	/* set up scatter list */
 	end = skb_tail_pointer(skb);
-	sg_init_one(&sg, auth, end - (unsigned char *)auth);
 
-	desc.tfm = asoc->ep->auth_hmacs[hmac_id];
-	desc.flags = 0;
+	tfm = asoc->ep->auth_hmacs[hmac_id];
 
 	digest = auth->auth_hdr.hmac;
-	if (crypto_hash_setkey(desc.tfm, &asoc_key->data[0], asoc_key->len))
+	if (crypto_shash_setkey(tfm, &asoc_key->data[0], asoc_key->len))
 		goto free;
 
-	crypto_hash_digest(&desc, &sg, sg.length, digest);
+	{
+		SHASH_DESC_ON_STACK(desc, tfm);
+
+		desc->tfm = tfm;
+		desc->flags = 0;
+		crypto_shash_digest(desc, (u8 *)auth,
+				    end - (unsigned char *)auth, digest);
+		shash_desc_zero(desc);
+	}
 
 free:
 	if (free_key)
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 2522a6175291..9d494e35e7f9 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -42,7 +42,6 @@
 #include <linux/slab.h>
 #include <linux/in.h>
 #include <linux/random.h>	/* get_random_bytes() */
-#include <linux/crypto.h>
 #include <net/sock.h>
 #include <net/ipv6.h>
 #include <net/sctp/sctp.h>
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index ec529121f38a..ce46f1c7f133 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -526,6 +526,8 @@ static int sctp_v6_cmp_addr(const union sctp_addr *addr1,
 		}
 		return 0;
 	}
+	if (addr1->v6.sin6_port != addr2->v6.sin6_port)
+		return 0;
 	if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr))
 		return 0;
 	/* If this is a linklocal address, compare the scope_id. */
diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index ded7d931a6a5..963dffcc2618 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -482,7 +482,7 @@ static void sctp_remaddr_seq_stop(struct seq_file *seq, void *v)
 static int sctp_remaddr_seq_show(struct seq_file *seq, void *v)
 {
 	struct sctp_association *assoc;
-	struct sctp_transport *tsp;
+	struct sctp_transport *transport, *tsp;
 
 	if (v == SEQ_START_TOKEN) {
 		seq_printf(seq, "ADDR ASSOC_ID HB_ACT RTO MAX_PATH_RTX "
@@ -490,10 +490,10 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v)
 		return 0;
 	}
 
-	tsp = (struct sctp_transport *)v;
-	if (!sctp_transport_hold(tsp))
+	transport = (struct sctp_transport *)v;
+	if (!sctp_transport_hold(transport))
 		return 0;
-	assoc = tsp->asoc;
+	assoc = transport->asoc;
 
 	list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list,
 				transports) {
@@ -546,7 +546,7 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v)
 		seq_printf(seq, "\n");
 	}
 
-	sctp_transport_put(tsp);
+	sctp_transport_put(transport);
 
 	return 0;
 }
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index ab0d538a74ed..1099e99a53c4 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -60,6 +60,8 @@
 #include <net/inet_common.h>
 #include <net/inet_ecn.h>
 
+#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024)
+
 /* Global data structures. */
 struct sctp_globals sctp_globals __read_mostly;
 
@@ -1355,6 +1357,8 @@ static __init int sctp_init(void)
 	unsigned long limit;
 	int max_share;
 	int order;
+	int num_entries;
+	int max_entry_order;
 
 	sock_skb_cb_check_size(sizeof(struct sctp_ulpevent));
 
@@ -1407,14 +1411,24 @@ static __init int sctp_init(void)
 
 	/* Size and allocate the association hash table.
 	 * The methodology is similar to that of the tcp hash tables.
+	 * Though not identical.  Start by getting a goal size
 	 */
 	if (totalram_pages >= (128 * 1024))
 		goal = totalram_pages >> (22 - PAGE_SHIFT);
 	else
 		goal = totalram_pages >> (24 - PAGE_SHIFT);
 
-	for (order = 0; (1UL << order) < goal; order++)
-		;
+	/* Then compute the page order for said goal */
+	order = get_order(goal);
+
+	/* Now compute the required page order for the maximum sized table we
+	 * want to create
+	 */
+	max_entry_order = get_order(MAX_SCTP_PORT_HASH_ENTRIES *
+				    sizeof(struct sctp_bind_hashbucket));
+
+	/* Limit the page order by that maximum hash table size */
+	order = min(order, max_entry_order);
 
 	/* Allocate and initialize the endpoint hash table.  */
 	sctp_ep_hashsize = 64;
@@ -1430,20 +1444,35 @@ static __init int sctp_init(void)
 		INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain);
 	}
 
-	/* Allocate and initialize the SCTP port hash table.  */
+	/* Allocate and initialize the SCTP port hash table.
+	 * Note that order is initalized to start at the max sized
+	 * table we want to support.  If we can't get that many pages
+	 * reduce the order and try again
+	 */
 	do {
-		sctp_port_hashsize = (1UL << order) * PAGE_SIZE /
-					sizeof(struct sctp_bind_hashbucket);
-		if ((sctp_port_hashsize > (64 * 1024)) && order > 0)
-			continue;
 		sctp_port_hashtable = (struct sctp_bind_hashbucket *)
 			__get_free_pages(GFP_KERNEL | __GFP_NOWARN, order);
 	} while (!sctp_port_hashtable && --order > 0);
+
 	if (!sctp_port_hashtable) {
 		pr_err("Failed bind hash alloc\n");
 		status = -ENOMEM;
 		goto err_bhash_alloc;
 	}
+
+	/* Now compute the number of entries that will fit in the
+	 * port hash space we allocated
+	 */
+	num_entries = (1UL << order) * PAGE_SIZE /
+		      sizeof(struct sctp_bind_hashbucket);
+
+	/* And finish by rounding it down to the nearest power of two
+	 * this wastes some memory of course, but its needed because
+	 * the hash function operates based on the assumption that
+	 * that the number of entries is a power of two
+	 */
+	sctp_port_hashsize = rounddown_pow_of_two(num_entries);
+
 	for (i = 0; i < sctp_port_hashsize; i++) {
 		spin_lock_init(&sctp_port_hashtable[i].lock);
 		INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain);
@@ -1452,7 +1481,8 @@ static __init int sctp_init(void)
 	if (sctp_transport_hashtable_init())
 		goto err_thash_alloc;
 
-	pr_info("Hash tables configured (bind %d)\n", sctp_port_hashsize);
+	pr_info("Hash tables configured (bind %d/%d)\n", sctp_port_hashsize,
+		num_entries);
 
 	sctp_sysctl_register();
 
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 5d6a03fad378..1296e555fe29 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -45,6 +45,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <crypto/hash.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/ip.h>
@@ -52,7 +53,6 @@
 #include <linux/net.h>
 #include <linux/inet.h>
 #include <linux/scatterlist.h>
-#include <linux/crypto.h>
 #include <linux/slab.h>
 #include <net/sock.h>
 
@@ -1606,7 +1606,6 @@ static sctp_cookie_param_t *sctp_pack_cookie(const struct sctp_endpoint *ep,
 {
 	sctp_cookie_param_t *retval;
 	struct sctp_signed_cookie *cookie;
-	struct scatterlist sg;
 	int headersize, bodysize;
 
 	/* Header size is static data prior to the actual cookie, including
@@ -1663,16 +1662,19 @@ static sctp_cookie_param_t *sctp_pack_cookie(const struct sctp_endpoint *ep,
 	       ntohs(init_chunk->chunk_hdr->length), raw_addrs, addrs_len);
 
 	if (sctp_sk(ep->base.sk)->hmac) {
-		struct hash_desc desc;
+		SHASH_DESC_ON_STACK(desc, sctp_sk(ep->base.sk)->hmac);
+		int err;
 
 		/* Sign the message.  */
-		sg_init_one(&sg, &cookie->c, bodysize);
-		desc.tfm = sctp_sk(ep->base.sk)->hmac;
-		desc.flags = 0;
-
-		if (crypto_hash_setkey(desc.tfm, ep->secret_key,
-				       sizeof(ep->secret_key)) ||
-		    crypto_hash_digest(&desc, &sg, bodysize, cookie->signature))
+		desc->tfm = sctp_sk(ep->base.sk)->hmac;
+		desc->flags = 0;
+
+		err = crypto_shash_setkey(desc->tfm, ep->secret_key,
+					  sizeof(ep->secret_key)) ?:
+		      crypto_shash_digest(desc, (u8 *)&cookie->c, bodysize,
+					  cookie->signature);
+		shash_desc_zero(desc);
+		if (err)
 			goto free_cookie;
 	}
 
@@ -1697,12 +1699,10 @@ struct sctp_association *sctp_unpack_cookie(
 	struct sctp_cookie *bear_cookie;
 	int headersize, bodysize, fixed_size;
 	__u8 *digest = ep->digest;
-	struct scatterlist sg;
 	unsigned int len;
 	sctp_scope_t scope;
 	struct sk_buff *skb = chunk->skb;
 	ktime_t kt;
-	struct hash_desc desc;
 
 	/* Header size is static data prior to the actual cookie, including
 	 * any padding.
@@ -1733,16 +1733,23 @@ struct sctp_association *sctp_unpack_cookie(
 		goto no_hmac;
 
 	/* Check the signature.  */
-	sg_init_one(&sg, bear_cookie, bodysize);
-	desc.tfm = sctp_sk(ep->base.sk)->hmac;
-	desc.flags = 0;
-
-	memset(digest, 0x00, SCTP_SIGNATURE_SIZE);
-	if (crypto_hash_setkey(desc.tfm, ep->secret_key,
-			       sizeof(ep->secret_key)) ||
-	    crypto_hash_digest(&desc, &sg, bodysize, digest)) {
-		*error = -SCTP_IERROR_NOMEM;
-		goto fail;
+	{
+		SHASH_DESC_ON_STACK(desc, sctp_sk(ep->base.sk)->hmac);
+		int err;
+
+		desc->tfm = sctp_sk(ep->base.sk)->hmac;
+		desc->flags = 0;
+
+		err = crypto_shash_setkey(desc->tfm, ep->secret_key,
+					  sizeof(ep->secret_key)) ?:
+		      crypto_shash_digest(desc, (u8 *)bear_cookie, bodysize,
+					  digest);
+		shash_desc_zero(desc);
+
+		if (err) {
+			*error = -SCTP_IERROR_NOMEM;
+			goto fail;
+		}
 	}
 
 	if (memcmp(digest, cookie->signature, SCTP_SIGNATURE_SIZE)) {
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 5ca2ebfe0be8..de8eabf03eed 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -52,6 +52,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <crypto/hash.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/wait.h>
@@ -61,7 +62,6 @@
 #include <linux/fcntl.h>
 #include <linux/poll.h>
 #include <linux/init.h>
-#include <linux/crypto.h>
 #include <linux/slab.h>
 #include <linux/file.h>
 #include <linux/compat.h>
@@ -4160,7 +4160,7 @@ static void sctp_destruct_sock(struct sock *sk)
 	struct sctp_sock *sp = sctp_sk(sk);
 
 	/* Free up the HMAC transform. */
-	crypto_free_hash(sp->hmac);
+	crypto_free_shash(sp->hmac);
 
 	inet_sock_destruct(sk);
 }
@@ -5538,6 +5538,7 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len,
 	struct sctp_hmac_algo_param *hmacs;
 	__u16 data_len = 0;
 	u32 num_idents;
+	int i;
 
 	if (!ep->auth_enable)
 		return -EACCES;
@@ -5555,8 +5556,12 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len,
 		return -EFAULT;
 	if (put_user(num_idents, &p->shmac_num_idents))
 		return -EFAULT;
-	if (copy_to_user(p->shmac_idents, hmacs->hmac_ids, data_len))
-		return -EFAULT;
+	for (i = 0; i < num_idents; i++) {
+		__u16 hmacid = ntohs(hmacs->hmac_ids[i]);
+
+		if (copy_to_user(&p->shmac_idents[i], &hmacid, sizeof(__u16)))
+			return -EFAULT;
+	}
 	return 0;
 }
 
@@ -6299,13 +6304,13 @@ static int sctp_listen_start(struct sock *sk, int backlog)
 {
 	struct sctp_sock *sp = sctp_sk(sk);
 	struct sctp_endpoint *ep = sp->ep;
-	struct crypto_hash *tfm = NULL;
+	struct crypto_shash *tfm = NULL;
 	char alg[32];
 
 	/* Allocate HMAC for generating cookie. */
 	if (!sp->hmac && sp->sctp_hmac_alg) {
 		sprintf(alg, "hmac(%s)", sp->sctp_hmac_alg);
-		tfm = crypto_alloc_hash(alg, 0, CRYPTO_ALG_ASYNC);
+		tfm = crypto_alloc_shash(alg, 0, 0);
 		if (IS_ERR(tfm)) {
 			net_info_ratelimited("failed to load transform for %s: %ld\n",
 					     sp->sctp_hmac_alg, PTR_ERR(tfm));
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 799e65b944b9..cabf586f47d7 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -740,7 +740,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 		default:
 			printk(KERN_CRIT "%s: bad return from "
 				"gss_fill_context: %zd\n", __func__, err);
-			BUG();
+			gss_msg->msg.errno = -EIO;
 		}
 		goto err_release_msg;
 	}
diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index fee3c15a4b52..d94a8e1e9f05 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -34,11 +34,12 @@
  * WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR A PARTICULAR PURPOSE.
  */
 
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
 #include <linux/err.h>
 #include <linux/types.h>
 #include <linux/mm.h>
 #include <linux/scatterlist.h>
-#include <linux/crypto.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
 #include <linux/random.h>
@@ -51,7 +52,7 @@
 
 u32
 krb5_encrypt(
-	struct crypto_blkcipher *tfm,
+	struct crypto_skcipher *tfm,
 	void * iv,
 	void * in,
 	void * out,
@@ -60,24 +61,28 @@ krb5_encrypt(
 	u32 ret = -EINVAL;
 	struct scatterlist sg[1];
 	u8 local_iv[GSS_KRB5_MAX_BLOCKSIZE] = {0};
-	struct blkcipher_desc desc = { .tfm = tfm, .info = local_iv };
+	SKCIPHER_REQUEST_ON_STACK(req, tfm);
 
-	if (length % crypto_blkcipher_blocksize(tfm) != 0)
+	if (length % crypto_skcipher_blocksize(tfm) != 0)
 		goto out;
 
-	if (crypto_blkcipher_ivsize(tfm) > GSS_KRB5_MAX_BLOCKSIZE) {
+	if (crypto_skcipher_ivsize(tfm) > GSS_KRB5_MAX_BLOCKSIZE) {
 		dprintk("RPC:       gss_k5encrypt: tfm iv size too large %d\n",
-			crypto_blkcipher_ivsize(tfm));
+			crypto_skcipher_ivsize(tfm));
 		goto out;
 	}
 
 	if (iv)
-		memcpy(local_iv, iv, crypto_blkcipher_ivsize(tfm));
+		memcpy(local_iv, iv, crypto_skcipher_ivsize(tfm));
 
 	memcpy(out, in, length);
 	sg_init_one(sg, out, length);
 
-	ret = crypto_blkcipher_encrypt_iv(&desc, sg, sg, length);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, sg, sg, length, local_iv);
+
+	ret = crypto_skcipher_encrypt(req);
+	skcipher_request_zero(req);
 out:
 	dprintk("RPC:       krb5_encrypt returns %d\n", ret);
 	return ret;
@@ -85,7 +90,7 @@ out:
 
 u32
 krb5_decrypt(
-     struct crypto_blkcipher *tfm,
+     struct crypto_skcipher *tfm,
      void * iv,
      void * in,
      void * out,
@@ -94,23 +99,27 @@ krb5_decrypt(
 	u32 ret = -EINVAL;
 	struct scatterlist sg[1];
 	u8 local_iv[GSS_KRB5_MAX_BLOCKSIZE] = {0};
-	struct blkcipher_desc desc = { .tfm = tfm, .info = local_iv };
+	SKCIPHER_REQUEST_ON_STACK(req, tfm);
 
-	if (length % crypto_blkcipher_blocksize(tfm) != 0)
+	if (length % crypto_skcipher_blocksize(tfm) != 0)
 		goto out;
 
-	if (crypto_blkcipher_ivsize(tfm) > GSS_KRB5_MAX_BLOCKSIZE) {
+	if (crypto_skcipher_ivsize(tfm) > GSS_KRB5_MAX_BLOCKSIZE) {
 		dprintk("RPC:       gss_k5decrypt: tfm iv size too large %d\n",
-			crypto_blkcipher_ivsize(tfm));
+			crypto_skcipher_ivsize(tfm));
 		goto out;
 	}
 	if (iv)
-		memcpy(local_iv,iv, crypto_blkcipher_ivsize(tfm));
+		memcpy(local_iv,iv, crypto_skcipher_ivsize(tfm));
 
 	memcpy(out, in, length);
 	sg_init_one(sg, out, length);
 
-	ret = crypto_blkcipher_decrypt_iv(&desc, sg, sg, length);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, sg, sg, length, local_iv);
+
+	ret = crypto_skcipher_decrypt(req);
+	skcipher_request_zero(req);
 out:
 	dprintk("RPC:       gss_k5decrypt returns %d\n",ret);
 	return ret;
@@ -119,9 +128,11 @@ out:
 static int
 checksummer(struct scatterlist *sg, void *data)
 {
-	struct hash_desc *desc = data;
+	struct ahash_request *req = data;
+
+	ahash_request_set_crypt(req, sg, NULL, sg->length);
 
-	return crypto_hash_update(desc, sg, sg->length);
+	return crypto_ahash_update(req);
 }
 
 static int
@@ -152,13 +163,13 @@ make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen,
 		       struct xdr_buf *body, int body_offset, u8 *cksumkey,
 		       unsigned int usage, struct xdr_netobj *cksumout)
 {
-	struct hash_desc                desc;
 	struct scatterlist              sg[1];
 	int err;
 	u8 checksumdata[GSS_KRB5_MAX_CKSUM_LEN];
 	u8 rc4salt[4];
-	struct crypto_hash *md5;
-	struct crypto_hash *hmac_md5;
+	struct crypto_ahash *md5;
+	struct crypto_ahash *hmac_md5;
+	struct ahash_request *req;
 
 	if (cksumkey == NULL)
 		return GSS_S_FAILURE;
@@ -174,61 +185,79 @@ make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen,
 		return GSS_S_FAILURE;
 	}
 
-	md5 = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
+	md5 = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(md5))
 		return GSS_S_FAILURE;
 
-	hmac_md5 = crypto_alloc_hash(kctx->gk5e->cksum_name, 0,
-				     CRYPTO_ALG_ASYNC);
+	hmac_md5 = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0,
+				      CRYPTO_ALG_ASYNC);
 	if (IS_ERR(hmac_md5)) {
-		crypto_free_hash(md5);
+		crypto_free_ahash(md5);
+		return GSS_S_FAILURE;
+	}
+
+	req = ahash_request_alloc(md5, GFP_KERNEL);
+	if (!req) {
+		crypto_free_ahash(hmac_md5);
+		crypto_free_ahash(md5);
 		return GSS_S_FAILURE;
 	}
 
-	desc.tfm = md5;
-	desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
 
-	err = crypto_hash_init(&desc);
+	err = crypto_ahash_init(req);
 	if (err)
 		goto out;
 	sg_init_one(sg, rc4salt, 4);
-	err = crypto_hash_update(&desc, sg, 4);
+	ahash_request_set_crypt(req, sg, NULL, 4);
+	err = crypto_ahash_update(req);
 	if (err)
 		goto out;
 
 	sg_init_one(sg, header, hdrlen);
-	err = crypto_hash_update(&desc, sg, hdrlen);
+	ahash_request_set_crypt(req, sg, NULL, hdrlen);
+	err = crypto_ahash_update(req);
 	if (err)
 		goto out;
 	err = xdr_process_buf(body, body_offset, body->len - body_offset,
-			      checksummer, &desc);
+			      checksummer, req);
 	if (err)
 		goto out;
-	err = crypto_hash_final(&desc, checksumdata);
+	ahash_request_set_crypt(req, NULL, checksumdata, 0);
+	err = crypto_ahash_final(req);
 	if (err)
 		goto out;
 
-	desc.tfm = hmac_md5;
-	desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	ahash_request_free(req);
+	req = ahash_request_alloc(hmac_md5, GFP_KERNEL);
+	if (!req) {
+		crypto_free_ahash(hmac_md5);
+		crypto_free_ahash(md5);
+		return GSS_S_FAILURE;
+	}
+
+	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
 
-	err = crypto_hash_init(&desc);
+	err = crypto_ahash_init(req);
 	if (err)
 		goto out;
-	err = crypto_hash_setkey(hmac_md5, cksumkey, kctx->gk5e->keylength);
+	err = crypto_ahash_setkey(hmac_md5, cksumkey, kctx->gk5e->keylength);
 	if (err)
 		goto out;
 
-	sg_init_one(sg, checksumdata, crypto_hash_digestsize(md5));
-	err = crypto_hash_digest(&desc, sg, crypto_hash_digestsize(md5),
-				 checksumdata);
+	sg_init_one(sg, checksumdata, crypto_ahash_digestsize(md5));
+	ahash_request_set_crypt(req, sg, checksumdata,
+				crypto_ahash_digestsize(md5));
+	err = crypto_ahash_digest(req);
 	if (err)
 		goto out;
 
 	memcpy(cksumout->data, checksumdata, kctx->gk5e->cksumlength);
 	cksumout->len = kctx->gk5e->cksumlength;
 out:
-	crypto_free_hash(md5);
-	crypto_free_hash(hmac_md5);
+	ahash_request_free(req);
+	crypto_free_ahash(md5);
+	crypto_free_ahash(hmac_md5);
 	return err ? GSS_S_FAILURE : 0;
 }
 
@@ -242,7 +271,8 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen,
 	      struct xdr_buf *body, int body_offset, u8 *cksumkey,
 	      unsigned int usage, struct xdr_netobj *cksumout)
 {
-	struct hash_desc                desc;
+	struct crypto_ahash *tfm;
+	struct ahash_request *req;
 	struct scatterlist              sg[1];
 	int err;
 	u8 checksumdata[GSS_KRB5_MAX_CKSUM_LEN];
@@ -259,32 +289,41 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen,
 		return GSS_S_FAILURE;
 	}
 
-	desc.tfm = crypto_alloc_hash(kctx->gk5e->cksum_name, 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(desc.tfm))
+	tfm = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm))
 		return GSS_S_FAILURE;
-	desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
-	checksumlen = crypto_hash_digestsize(desc.tfm);
+	req = ahash_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		crypto_free_ahash(tfm);
+		return GSS_S_FAILURE;
+	}
+
+	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
+
+	checksumlen = crypto_ahash_digestsize(tfm);
 
 	if (cksumkey != NULL) {
-		err = crypto_hash_setkey(desc.tfm, cksumkey,
-					 kctx->gk5e->keylength);
+		err = crypto_ahash_setkey(tfm, cksumkey,
+					  kctx->gk5e->keylength);
 		if (err)
 			goto out;
 	}
 
-	err = crypto_hash_init(&desc);
+	err = crypto_ahash_init(req);
 	if (err)
 		goto out;
 	sg_init_one(sg, header, hdrlen);
-	err = crypto_hash_update(&desc, sg, hdrlen);
+	ahash_request_set_crypt(req, sg, NULL, hdrlen);
+	err = crypto_ahash_update(req);
 	if (err)
 		goto out;
 	err = xdr_process_buf(body, body_offset, body->len - body_offset,
-			      checksummer, &desc);
+			      checksummer, req);
 	if (err)
 		goto out;
-	err = crypto_hash_final(&desc, checksumdata);
+	ahash_request_set_crypt(req, NULL, checksumdata, 0);
+	err = crypto_ahash_final(req);
 	if (err)
 		goto out;
 
@@ -307,7 +346,8 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen,
 	}
 	cksumout->len = kctx->gk5e->cksumlength;
 out:
-	crypto_free_hash(desc.tfm);
+	ahash_request_free(req);
+	crypto_free_ahash(tfm);
 	return err ? GSS_S_FAILURE : 0;
 }
 
@@ -323,7 +363,8 @@ make_checksum_v2(struct krb5_ctx *kctx, char *header, int hdrlen,
 		 struct xdr_buf *body, int body_offset, u8 *cksumkey,
 		 unsigned int usage, struct xdr_netobj *cksumout)
 {
-	struct hash_desc desc;
+	struct crypto_ahash *tfm;
+	struct ahash_request *req;
 	struct scatterlist sg[1];
 	int err;
 	u8 checksumdata[GSS_KRB5_MAX_CKSUM_LEN];
@@ -340,31 +381,39 @@ make_checksum_v2(struct krb5_ctx *kctx, char *header, int hdrlen,
 		return GSS_S_FAILURE;
 	}
 
-	desc.tfm = crypto_alloc_hash(kctx->gk5e->cksum_name, 0,
-							CRYPTO_ALG_ASYNC);
-	if (IS_ERR(desc.tfm))
+	tfm = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm))
 		return GSS_S_FAILURE;
-	checksumlen = crypto_hash_digestsize(desc.tfm);
-	desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	checksumlen = crypto_ahash_digestsize(tfm);
+
+	req = ahash_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		crypto_free_ahash(tfm);
+		return GSS_S_FAILURE;
+	}
 
-	err = crypto_hash_setkey(desc.tfm, cksumkey, kctx->gk5e->keylength);
+	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
+
+	err = crypto_ahash_setkey(tfm, cksumkey, kctx->gk5e->keylength);
 	if (err)
 		goto out;
 
-	err = crypto_hash_init(&desc);
+	err = crypto_ahash_init(req);
 	if (err)
 		goto out;
 	err = xdr_process_buf(body, body_offset, body->len - body_offset,
-			      checksummer, &desc);
+			      checksummer, req);
 	if (err)
 		goto out;
 	if (header != NULL) {
 		sg_init_one(sg, header, hdrlen);
-		err = crypto_hash_update(&desc, sg, hdrlen);
+		ahash_request_set_crypt(req, sg, NULL, hdrlen);
+		err = crypto_ahash_update(req);
 		if (err)
 			goto out;
 	}
-	err = crypto_hash_final(&desc, checksumdata);
+	ahash_request_set_crypt(req, NULL, checksumdata, 0);
+	err = crypto_ahash_final(req);
 	if (err)
 		goto out;
 
@@ -381,13 +430,14 @@ make_checksum_v2(struct krb5_ctx *kctx, char *header, int hdrlen,
 		break;
 	}
 out:
-	crypto_free_hash(desc.tfm);
+	ahash_request_free(req);
+	crypto_free_ahash(tfm);
 	return err ? GSS_S_FAILURE : 0;
 }
 
 struct encryptor_desc {
 	u8 iv[GSS_KRB5_MAX_BLOCKSIZE];
-	struct blkcipher_desc desc;
+	struct skcipher_request *req;
 	int pos;
 	struct xdr_buf *outbuf;
 	struct page **pages;
@@ -402,6 +452,7 @@ encryptor(struct scatterlist *sg, void *data)
 {
 	struct encryptor_desc *desc = data;
 	struct xdr_buf *outbuf = desc->outbuf;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(desc->req);
 	struct page *in_page;
 	int thislen = desc->fraglen + sg->length;
 	int fraglen, ret;
@@ -427,7 +478,7 @@ encryptor(struct scatterlist *sg, void *data)
 	desc->fraglen += sg->length;
 	desc->pos += sg->length;
 
-	fraglen = thislen & (crypto_blkcipher_blocksize(desc->desc.tfm) - 1);
+	fraglen = thislen & (crypto_skcipher_blocksize(tfm) - 1);
 	thislen -= fraglen;
 
 	if (thislen == 0)
@@ -436,8 +487,10 @@ encryptor(struct scatterlist *sg, void *data)
 	sg_mark_end(&desc->infrags[desc->fragno - 1]);
 	sg_mark_end(&desc->outfrags[desc->fragno - 1]);
 
-	ret = crypto_blkcipher_encrypt_iv(&desc->desc, desc->outfrags,
-					  desc->infrags, thislen);
+	skcipher_request_set_crypt(desc->req, desc->infrags, desc->outfrags,
+				   thislen, desc->iv);
+
+	ret = crypto_skcipher_encrypt(desc->req);
 	if (ret)
 		return ret;
 
@@ -459,18 +512,20 @@ encryptor(struct scatterlist *sg, void *data)
 }
 
 int
-gss_encrypt_xdr_buf(struct crypto_blkcipher *tfm, struct xdr_buf *buf,
+gss_encrypt_xdr_buf(struct crypto_skcipher *tfm, struct xdr_buf *buf,
 		    int offset, struct page **pages)
 {
 	int ret;
 	struct encryptor_desc desc;
+	SKCIPHER_REQUEST_ON_STACK(req, tfm);
+
+	BUG_ON((buf->len - offset) % crypto_skcipher_blocksize(tfm) != 0);
 
-	BUG_ON((buf->len - offset) % crypto_blkcipher_blocksize(tfm) != 0);
+	skcipher_request_set_tfm(req, tfm);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
 
 	memset(desc.iv, 0, sizeof(desc.iv));
-	desc.desc.tfm = tfm;
-	desc.desc.info = desc.iv;
-	desc.desc.flags = 0;
+	desc.req = req;
 	desc.pos = offset;
 	desc.outbuf = buf;
 	desc.pages = pages;
@@ -481,12 +536,13 @@ gss_encrypt_xdr_buf(struct crypto_blkcipher *tfm, struct xdr_buf *buf,
 	sg_init_table(desc.outfrags, 4);
 
 	ret = xdr_process_buf(buf, offset, buf->len - offset, encryptor, &desc);
+	skcipher_request_zero(req);
 	return ret;
 }
 
 struct decryptor_desc {
 	u8 iv[GSS_KRB5_MAX_BLOCKSIZE];
-	struct blkcipher_desc desc;
+	struct skcipher_request *req;
 	struct scatterlist frags[4];
 	int fragno;
 	int fraglen;
@@ -497,6 +553,7 @@ decryptor(struct scatterlist *sg, void *data)
 {
 	struct decryptor_desc *desc = data;
 	int thislen = desc->fraglen + sg->length;
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(desc->req);
 	int fraglen, ret;
 
 	/* Worst case is 4 fragments: head, end of page 1, start
@@ -507,7 +564,7 @@ decryptor(struct scatterlist *sg, void *data)
 	desc->fragno++;
 	desc->fraglen += sg->length;
 
-	fraglen = thislen & (crypto_blkcipher_blocksize(desc->desc.tfm) - 1);
+	fraglen = thislen & (crypto_skcipher_blocksize(tfm) - 1);
 	thislen -= fraglen;
 
 	if (thislen == 0)
@@ -515,8 +572,10 @@ decryptor(struct scatterlist *sg, void *data)
 
 	sg_mark_end(&desc->frags[desc->fragno - 1]);
 
-	ret = crypto_blkcipher_decrypt_iv(&desc->desc, desc->frags,
-					  desc->frags, thislen);
+	skcipher_request_set_crypt(desc->req, desc->frags, desc->frags,
+				   thislen, desc->iv);
+
+	ret = crypto_skcipher_decrypt(desc->req);
 	if (ret)
 		return ret;
 
@@ -535,24 +594,29 @@ decryptor(struct scatterlist *sg, void *data)
 }
 
 int
-gss_decrypt_xdr_buf(struct crypto_blkcipher *tfm, struct xdr_buf *buf,
+gss_decrypt_xdr_buf(struct crypto_skcipher *tfm, struct xdr_buf *buf,
 		    int offset)
 {
+	int ret;
 	struct decryptor_desc desc;
+	SKCIPHER_REQUEST_ON_STACK(req, tfm);
 
 	/* XXXJBF: */
-	BUG_ON((buf->len - offset) % crypto_blkcipher_blocksize(tfm) != 0);
+	BUG_ON((buf->len - offset) % crypto_skcipher_blocksize(tfm) != 0);
+
+	skcipher_request_set_tfm(req, tfm);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
 
 	memset(desc.iv, 0, sizeof(desc.iv));
-	desc.desc.tfm = tfm;
-	desc.desc.info = desc.iv;
-	desc.desc.flags = 0;
+	desc.req = req;
 	desc.fragno = 0;
 	desc.fraglen = 0;
 
 	sg_init_table(desc.frags, 4);
 
-	return xdr_process_buf(buf, offset, buf->len - offset, decryptor, &desc);
+	ret = xdr_process_buf(buf, offset, buf->len - offset, decryptor, &desc);
+	skcipher_request_zero(req);
+	return ret;
 }
 
 /*
@@ -594,12 +658,12 @@ xdr_extend_head(struct xdr_buf *buf, unsigned int base, unsigned int shiftlen)
 }
 
 static u32
-gss_krb5_cts_crypt(struct crypto_blkcipher *cipher, struct xdr_buf *buf,
+gss_krb5_cts_crypt(struct crypto_skcipher *cipher, struct xdr_buf *buf,
 		   u32 offset, u8 *iv, struct page **pages, int encrypt)
 {
 	u32 ret;
 	struct scatterlist sg[1];
-	struct blkcipher_desc desc = { .tfm = cipher, .info = iv };
+	SKCIPHER_REQUEST_ON_STACK(req, cipher);
 	u8 data[GSS_KRB5_MAX_BLOCKSIZE * 2];
 	struct page **save_pages;
 	u32 len = buf->len - offset;
@@ -625,10 +689,16 @@ gss_krb5_cts_crypt(struct crypto_blkcipher *cipher, struct xdr_buf *buf,
 
 	sg_init_one(sg, data, len);
 
+	skcipher_request_set_tfm(req, cipher);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, sg, sg, len, iv);
+
 	if (encrypt)
-		ret = crypto_blkcipher_encrypt_iv(&desc, sg, sg, len);
+		ret = crypto_skcipher_encrypt(req);
 	else
-		ret = crypto_blkcipher_decrypt_iv(&desc, sg, sg, len);
+		ret = crypto_skcipher_decrypt(req);
+
+	skcipher_request_zero(req);
 
 	if (ret)
 		goto out;
@@ -647,7 +717,7 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset,
 	struct xdr_netobj hmac;
 	u8 *cksumkey;
 	u8 *ecptr;
-	struct crypto_blkcipher *cipher, *aux_cipher;
+	struct crypto_skcipher *cipher, *aux_cipher;
 	int blocksize;
 	struct page **save_pages;
 	int nblocks, nbytes;
@@ -666,7 +736,7 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset,
 		cksumkey = kctx->acceptor_integ;
 		usage = KG_USAGE_ACCEPTOR_SEAL;
 	}
-	blocksize = crypto_blkcipher_blocksize(cipher);
+	blocksize = crypto_skcipher_blocksize(cipher);
 
 	/* hide the gss token header and insert the confounder */
 	offset += GSS_KRB5_TOK_HDR_LEN;
@@ -719,20 +789,24 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset,
 	memset(desc.iv, 0, sizeof(desc.iv));
 
 	if (cbcbytes) {
+		SKCIPHER_REQUEST_ON_STACK(req, aux_cipher);
+
 		desc.pos = offset + GSS_KRB5_TOK_HDR_LEN;
 		desc.fragno = 0;
 		desc.fraglen = 0;
 		desc.pages = pages;
 		desc.outbuf = buf;
-		desc.desc.info = desc.iv;
-		desc.desc.flags = 0;
-		desc.desc.tfm = aux_cipher;
+		desc.req = req;
+
+		skcipher_request_set_tfm(req, aux_cipher);
+		skcipher_request_set_callback(req, 0, NULL, NULL);
 
 		sg_init_table(desc.infrags, 4);
 		sg_init_table(desc.outfrags, 4);
 
 		err = xdr_process_buf(buf, offset + GSS_KRB5_TOK_HDR_LEN,
 				      cbcbytes, encryptor, &desc);
+		skcipher_request_zero(req);
 		if (err)
 			goto out_err;
 	}
@@ -763,7 +837,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf,
 	struct xdr_buf subbuf;
 	u32 ret = 0;
 	u8 *cksum_key;
-	struct crypto_blkcipher *cipher, *aux_cipher;
+	struct crypto_skcipher *cipher, *aux_cipher;
 	struct xdr_netobj our_hmac_obj;
 	u8 our_hmac[GSS_KRB5_MAX_CKSUM_LEN];
 	u8 pkt_hmac[GSS_KRB5_MAX_CKSUM_LEN];
@@ -782,7 +856,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf,
 		cksum_key = kctx->initiator_integ;
 		usage = KG_USAGE_INITIATOR_SEAL;
 	}
-	blocksize = crypto_blkcipher_blocksize(cipher);
+	blocksize = crypto_skcipher_blocksize(cipher);
 
 
 	/* create a segment skipping the header and leaving out the checksum */
@@ -799,15 +873,19 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf,
 	memset(desc.iv, 0, sizeof(desc.iv));
 
 	if (cbcbytes) {
+		SKCIPHER_REQUEST_ON_STACK(req, aux_cipher);
+
 		desc.fragno = 0;
 		desc.fraglen = 0;
-		desc.desc.info = desc.iv;
-		desc.desc.flags = 0;
-		desc.desc.tfm = aux_cipher;
+		desc.req = req;
+
+		skcipher_request_set_tfm(req, aux_cipher);
+		skcipher_request_set_callback(req, 0, NULL, NULL);
 
 		sg_init_table(desc.frags, 4);
 
 		ret = xdr_process_buf(&subbuf, 0, cbcbytes, decryptor, &desc);
+		skcipher_request_zero(req);
 		if (ret)
 			goto out_err;
 	}
@@ -850,61 +928,62 @@ out_err:
  * Set the key of the given cipher.
  */
 int
-krb5_rc4_setup_seq_key(struct krb5_ctx *kctx, struct crypto_blkcipher *cipher,
+krb5_rc4_setup_seq_key(struct krb5_ctx *kctx, struct crypto_skcipher *cipher,
 		       unsigned char *cksum)
 {
-	struct crypto_hash *hmac;
-	struct hash_desc desc;
-	struct scatterlist sg[1];
+	struct crypto_shash *hmac;
+	struct shash_desc *desc;
 	u8 Kseq[GSS_KRB5_MAX_KEYLEN];
 	u32 zeroconstant = 0;
 	int err;
 
 	dprintk("%s: entered\n", __func__);
 
-	hmac = crypto_alloc_hash(kctx->gk5e->cksum_name, 0, CRYPTO_ALG_ASYNC);
+	hmac = crypto_alloc_shash(kctx->gk5e->cksum_name, 0, 0);
 	if (IS_ERR(hmac)) {
 		dprintk("%s: error %ld, allocating hash '%s'\n",
 			__func__, PTR_ERR(hmac), kctx->gk5e->cksum_name);
 		return PTR_ERR(hmac);
 	}
 
-	desc.tfm = hmac;
-	desc.flags = 0;
+	desc = kmalloc(sizeof(*desc), GFP_KERNEL);
+	if (!desc) {
+		dprintk("%s: failed to allocate shash descriptor for '%s'\n",
+			__func__, kctx->gk5e->cksum_name);
+		crypto_free_shash(hmac);
+		return -ENOMEM;
+	}
 
-	err = crypto_hash_init(&desc);
-	if (err)
-		goto out_err;
+	desc->tfm = hmac;
+	desc->flags = 0;
 
 	/* Compute intermediate Kseq from session key */
-	err = crypto_hash_setkey(hmac, kctx->Ksess, kctx->gk5e->keylength);
+	err = crypto_shash_setkey(hmac, kctx->Ksess, kctx->gk5e->keylength);
 	if (err)
 		goto out_err;
 
-	sg_init_one(sg, &zeroconstant, 4);
-	err = crypto_hash_digest(&desc, sg, 4, Kseq);
+	err = crypto_shash_digest(desc, (u8 *)&zeroconstant, 4, Kseq);
 	if (err)
 		goto out_err;
 
 	/* Compute final Kseq from the checksum and intermediate Kseq */
-	err = crypto_hash_setkey(hmac, Kseq, kctx->gk5e->keylength);
+	err = crypto_shash_setkey(hmac, Kseq, kctx->gk5e->keylength);
 	if (err)
 		goto out_err;
 
-	sg_set_buf(sg, cksum, 8);
-
-	err = crypto_hash_digest(&desc, sg, 8, Kseq);
+	err = crypto_shash_digest(desc, cksum, 8, Kseq);
 	if (err)
 		goto out_err;
 
-	err = crypto_blkcipher_setkey(cipher, Kseq, kctx->gk5e->keylength);
+	err = crypto_skcipher_setkey(cipher, Kseq, kctx->gk5e->keylength);
 	if (err)
 		goto out_err;
 
 	err = 0;
 
 out_err:
-	crypto_free_hash(hmac);
+	kzfree(desc);
+	crypto_free_shash(hmac);
 	dprintk("%s: returning %d\n", __func__, err);
 	return err;
 }
@@ -914,12 +993,11 @@ out_err:
  * Set the key of cipher kctx->enc.
  */
 int
-krb5_rc4_setup_enc_key(struct krb5_ctx *kctx, struct crypto_blkcipher *cipher,
+krb5_rc4_setup_enc_key(struct krb5_ctx *kctx, struct crypto_skcipher *cipher,
 		       s32 seqnum)
 {
-	struct crypto_hash *hmac;
-	struct hash_desc desc;
-	struct scatterlist sg[1];
+	struct crypto_shash *hmac;
+	struct shash_desc *desc;
 	u8 Kcrypt[GSS_KRB5_MAX_KEYLEN];
 	u8 zeroconstant[4] = {0};
 	u8 seqnumarray[4];
@@ -927,35 +1005,38 @@ krb5_rc4_setup_enc_key(struct krb5_ctx *kctx, struct crypto_blkcipher *cipher,
 
 	dprintk("%s: entered, seqnum %u\n", __func__, seqnum);
 
-	hmac = crypto_alloc_hash(kctx->gk5e->cksum_name, 0, CRYPTO_ALG_ASYNC);
+	hmac = crypto_alloc_shash(kctx->gk5e->cksum_name, 0, 0);
 	if (IS_ERR(hmac)) {
 		dprintk("%s: error %ld, allocating hash '%s'\n",
 			__func__, PTR_ERR(hmac), kctx->gk5e->cksum_name);
 		return PTR_ERR(hmac);
 	}
 
-	desc.tfm = hmac;
-	desc.flags = 0;
+	desc = kmalloc(sizeof(*desc), GFP_KERNEL);
+	if (!desc) {
+		dprintk("%s: failed to allocate shash descriptor for '%s'\n",
+			__func__, kctx->gk5e->cksum_name);
+		crypto_free_shash(hmac);
+		return -ENOMEM;
+	}
 
-	err = crypto_hash_init(&desc);
-	if (err)
-		goto out_err;
+	desc->tfm = hmac;
+	desc->flags = 0;
 
 	/* Compute intermediate Kcrypt from session key */
 	for (i = 0; i < kctx->gk5e->keylength; i++)
 		Kcrypt[i] = kctx->Ksess[i] ^ 0xf0;
 
-	err = crypto_hash_setkey(hmac, Kcrypt, kctx->gk5e->keylength);
+	err = crypto_shash_setkey(hmac, Kcrypt, kctx->gk5e->keylength);
 	if (err)
 		goto out_err;
 
-	sg_init_one(sg, zeroconstant, 4);
-	err = crypto_hash_digest(&desc, sg, 4, Kcrypt);
+	err = crypto_shash_digest(desc, zeroconstant, 4, Kcrypt);
 	if (err)
 		goto out_err;
 
 	/* Compute final Kcrypt from the seqnum and intermediate Kcrypt */
-	err = crypto_hash_setkey(hmac, Kcrypt, kctx->gk5e->keylength);
+	err = crypto_shash_setkey(hmac, Kcrypt, kctx->gk5e->keylength);
 	if (err)
 		goto out_err;
 
@@ -964,20 +1045,19 @@ krb5_rc4_setup_enc_key(struct krb5_ctx *kctx, struct crypto_blkcipher *cipher,
 	seqnumarray[2] = (unsigned char) ((seqnum >> 8) & 0xff);
 	seqnumarray[3] = (unsigned char) ((seqnum >> 0) & 0xff);
 
-	sg_set_buf(sg, seqnumarray, 4);
-
-	err = crypto_hash_digest(&desc, sg, 4, Kcrypt);
+	err = crypto_shash_digest(desc, seqnumarray, 4, Kcrypt);
 	if (err)
 		goto out_err;
 
-	err = crypto_blkcipher_setkey(cipher, Kcrypt, kctx->gk5e->keylength);
+	err = crypto_skcipher_setkey(cipher, Kcrypt, kctx->gk5e->keylength);
 	if (err)
 		goto out_err;
 
 	err = 0;
 
 out_err:
-	crypto_free_hash(hmac);
+	kzfree(desc);
+	crypto_free_shash(hmac);
 	dprintk("%s: returning %d\n", __func__, err);
 	return err;
 }
diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c
index 234fa8d0fd9b..870133146026 100644
--- a/net/sunrpc/auth_gss/gss_krb5_keys.c
+++ b/net/sunrpc/auth_gss/gss_krb5_keys.c
@@ -54,9 +54,9 @@
  * WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR A PARTICULAR PURPOSE.
  */
 
+#include <crypto/skcipher.h>
 #include <linux/err.h>
 #include <linux/types.h>
-#include <linux/crypto.h>
 #include <linux/sunrpc/gss_krb5.h>
 #include <linux/sunrpc/xdr.h>
 #include <linux/lcm.h>
@@ -147,7 +147,7 @@ u32 krb5_derive_key(const struct gss_krb5_enctype *gk5e,
 	size_t blocksize, keybytes, keylength, n;
 	unsigned char *inblockdata, *outblockdata, *rawkey;
 	struct xdr_netobj inblock, outblock;
-	struct crypto_blkcipher *cipher;
+	struct crypto_skcipher *cipher;
 	u32 ret = EINVAL;
 
 	blocksize = gk5e->blocksize;
@@ -157,11 +157,11 @@ u32 krb5_derive_key(const struct gss_krb5_enctype *gk5e,
 	if ((inkey->len != keylength) || (outkey->len != keylength))
 		goto err_return;
 
-	cipher = crypto_alloc_blkcipher(gk5e->encrypt_name, 0,
-					CRYPTO_ALG_ASYNC);
+	cipher = crypto_alloc_skcipher(gk5e->encrypt_name, 0,
+				       CRYPTO_ALG_ASYNC);
 	if (IS_ERR(cipher))
 		goto err_return;
-	if (crypto_blkcipher_setkey(cipher, inkey->data, inkey->len))
+	if (crypto_skcipher_setkey(cipher, inkey->data, inkey->len))
 		goto err_return;
 
 	/* allocate and set up buffers */
@@ -238,7 +238,7 @@ err_free_in:
 	memset(inblockdata, 0, blocksize);
 	kfree(inblockdata);
 err_free_cipher:
-	crypto_free_blkcipher(cipher);
+	crypto_free_skcipher(cipher);
 err_return:
 	return ret;
 }
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index 28db442a0034..71341ccb9890 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -34,6 +34,8 @@
  *
  */
 
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -42,7 +44,6 @@
 #include <linux/sunrpc/auth.h>
 #include <linux/sunrpc/gss_krb5.h>
 #include <linux/sunrpc/xdr.h>
-#include <linux/crypto.h>
 #include <linux/sunrpc/gss_krb5_enctypes.h>
 
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
@@ -217,7 +218,7 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *res)
 
 static inline const void *
 get_key(const void *p, const void *end,
-	struct krb5_ctx *ctx, struct crypto_blkcipher **res)
+	struct krb5_ctx *ctx, struct crypto_skcipher **res)
 {
 	struct xdr_netobj	key;
 	int			alg;
@@ -245,7 +246,7 @@ get_key(const void *p, const void *end,
 	if (IS_ERR(p))
 		goto out_err;
 
-	*res = crypto_alloc_blkcipher(ctx->gk5e->encrypt_name, 0,
+	*res = crypto_alloc_skcipher(ctx->gk5e->encrypt_name, 0,
 							CRYPTO_ALG_ASYNC);
 	if (IS_ERR(*res)) {
 		printk(KERN_WARNING "gss_kerberos_mech: unable to initialize "
@@ -253,7 +254,7 @@ get_key(const void *p, const void *end,
 		*res = NULL;
 		goto out_err_free_key;
 	}
-	if (crypto_blkcipher_setkey(*res, key.data, key.len)) {
+	if (crypto_skcipher_setkey(*res, key.data, key.len)) {
 		printk(KERN_WARNING "gss_kerberos_mech: error setting key for "
 			"crypto algorithm %s\n", ctx->gk5e->encrypt_name);
 		goto out_err_free_tfm;
@@ -263,7 +264,7 @@ get_key(const void *p, const void *end,
 	return p;
 
 out_err_free_tfm:
-	crypto_free_blkcipher(*res);
+	crypto_free_skcipher(*res);
 out_err_free_key:
 	kfree(key.data);
 	p = ERR_PTR(-EINVAL);
@@ -335,30 +336,30 @@ gss_import_v1_context(const void *p, const void *end, struct krb5_ctx *ctx)
 	return 0;
 
 out_err_free_key2:
-	crypto_free_blkcipher(ctx->seq);
+	crypto_free_skcipher(ctx->seq);
 out_err_free_key1:
-	crypto_free_blkcipher(ctx->enc);
+	crypto_free_skcipher(ctx->enc);
 out_err_free_mech:
 	kfree(ctx->mech_used.data);
 out_err:
 	return PTR_ERR(p);
 }
 
-static struct crypto_blkcipher *
+static struct crypto_skcipher *
 context_v2_alloc_cipher(struct krb5_ctx *ctx, const char *cname, u8 *key)
 {
-	struct crypto_blkcipher *cp;
+	struct crypto_skcipher *cp;
 
-	cp = crypto_alloc_blkcipher(cname, 0, CRYPTO_ALG_ASYNC);
+	cp = crypto_alloc_skcipher(cname, 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(cp)) {
 		dprintk("gss_kerberos_mech: unable to initialize "
 			"crypto algorithm %s\n", cname);
 		return NULL;
 	}
-	if (crypto_blkcipher_setkey(cp, key, ctx->gk5e->keylength)) {
+	if (crypto_skcipher_setkey(cp, key, ctx->gk5e->keylength)) {
 		dprintk("gss_kerberos_mech: error setting key for "
 			"crypto algorithm %s\n", cname);
-		crypto_free_blkcipher(cp);
+		crypto_free_skcipher(cp);
 		return NULL;
 	}
 	return cp;
@@ -412,9 +413,9 @@ context_derive_keys_des3(struct krb5_ctx *ctx, gfp_t gfp_mask)
 	return 0;
 
 out_free_enc:
-	crypto_free_blkcipher(ctx->enc);
+	crypto_free_skcipher(ctx->enc);
 out_free_seq:
-	crypto_free_blkcipher(ctx->seq);
+	crypto_free_skcipher(ctx->seq);
 out_err:
 	return -EINVAL;
 }
@@ -427,18 +428,17 @@ out_err:
 static int
 context_derive_keys_rc4(struct krb5_ctx *ctx)
 {
-	struct crypto_hash *hmac;
+	struct crypto_shash *hmac;
 	char sigkeyconstant[] = "signaturekey";
 	int slen = strlen(sigkeyconstant) + 1;	/* include null terminator */
-	struct hash_desc desc;
-	struct scatterlist sg[1];
+	struct shash_desc *desc;
 	int err;
 
 	dprintk("RPC:       %s: entered\n", __func__);
 	/*
 	 * derive cksum (aka Ksign) key
 	 */
-	hmac = crypto_alloc_hash(ctx->gk5e->cksum_name, 0, CRYPTO_ALG_ASYNC);
+	hmac = crypto_alloc_shash(ctx->gk5e->cksum_name, 0, 0);
 	if (IS_ERR(hmac)) {
 		dprintk("%s: error %ld allocating hash '%s'\n",
 			__func__, PTR_ERR(hmac), ctx->gk5e->cksum_name);
@@ -446,37 +446,40 @@ context_derive_keys_rc4(struct krb5_ctx *ctx)
 		goto out_err;
 	}
 
-	err = crypto_hash_setkey(hmac, ctx->Ksess, ctx->gk5e->keylength);
+	err = crypto_shash_setkey(hmac, ctx->Ksess, ctx->gk5e->keylength);
 	if (err)
 		goto out_err_free_hmac;
 
-	sg_init_table(sg, 1);
-	sg_set_buf(sg, sigkeyconstant, slen);
 
-	desc.tfm = hmac;
-	desc.flags = 0;
-
-	err = crypto_hash_init(&desc);
-	if (err)
+	desc = kmalloc(sizeof(*desc), GFP_KERNEL);
+	if (!desc) {
+		dprintk("%s: failed to allocate hash descriptor for '%s'\n",
+			__func__, ctx->gk5e->cksum_name);
+		err = -ENOMEM;
 		goto out_err_free_hmac;
+	}
+
+	desc->tfm = hmac;
+	desc->flags = 0;
 
-	err = crypto_hash_digest(&desc, sg, slen, ctx->cksum);
+	err = crypto_shash_digest(desc, sigkeyconstant, slen, ctx->cksum);
+	kzfree(desc);
 	if (err)
 		goto out_err_free_hmac;
 	/*
-	 * allocate hash, and blkciphers for data and seqnum encryption
+	 * allocate hash, and skciphers for data and seqnum encryption
 	 */
-	ctx->enc = crypto_alloc_blkcipher(ctx->gk5e->encrypt_name, 0,
-					  CRYPTO_ALG_ASYNC);
+	ctx->enc = crypto_alloc_skcipher(ctx->gk5e->encrypt_name, 0,
+					 CRYPTO_ALG_ASYNC);
 	if (IS_ERR(ctx->enc)) {
 		err = PTR_ERR(ctx->enc);
 		goto out_err_free_hmac;
 	}
 
-	ctx->seq = crypto_alloc_blkcipher(ctx->gk5e->encrypt_name, 0,
-					  CRYPTO_ALG_ASYNC);
+	ctx->seq = crypto_alloc_skcipher(ctx->gk5e->encrypt_name, 0,
+					 CRYPTO_ALG_ASYNC);
 	if (IS_ERR(ctx->seq)) {
-		crypto_free_blkcipher(ctx->enc);
+		crypto_free_skcipher(ctx->enc);
 		err = PTR_ERR(ctx->seq);
 		goto out_err_free_hmac;
 	}
@@ -486,7 +489,7 @@ context_derive_keys_rc4(struct krb5_ctx *ctx)
 	err = 0;
 
 out_err_free_hmac:
-	crypto_free_hash(hmac);
+	crypto_free_shash(hmac);
 out_err:
 	dprintk("RPC:       %s: returning %d\n", __func__, err);
 	return err;
@@ -588,7 +591,7 @@ context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask)
 			context_v2_alloc_cipher(ctx, "cbc(aes)",
 						ctx->acceptor_seal);
 		if (ctx->acceptor_enc_aux == NULL) {
-			crypto_free_blkcipher(ctx->initiator_enc_aux);
+			crypto_free_skcipher(ctx->initiator_enc_aux);
 			goto out_free_acceptor_enc;
 		}
 	}
@@ -596,9 +599,9 @@ context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask)
 	return 0;
 
 out_free_acceptor_enc:
-	crypto_free_blkcipher(ctx->acceptor_enc);
+	crypto_free_skcipher(ctx->acceptor_enc);
 out_free_initiator_enc:
-	crypto_free_blkcipher(ctx->initiator_enc);
+	crypto_free_skcipher(ctx->initiator_enc);
 out_err:
 	return -EINVAL;
 }
@@ -710,12 +713,12 @@ static void
 gss_delete_sec_context_kerberos(void *internal_ctx) {
 	struct krb5_ctx *kctx = internal_ctx;
 
-	crypto_free_blkcipher(kctx->seq);
-	crypto_free_blkcipher(kctx->enc);
-	crypto_free_blkcipher(kctx->acceptor_enc);
-	crypto_free_blkcipher(kctx->initiator_enc);
-	crypto_free_blkcipher(kctx->acceptor_enc_aux);
-	crypto_free_blkcipher(kctx->initiator_enc_aux);
+	crypto_free_skcipher(kctx->seq);
+	crypto_free_skcipher(kctx->enc);
+	crypto_free_skcipher(kctx->acceptor_enc);
+	crypto_free_skcipher(kctx->initiator_enc);
+	crypto_free_skcipher(kctx->acceptor_enc_aux);
+	crypto_free_skcipher(kctx->initiator_enc_aux);
 	kfree(kctx->mech_used.data);
 	kfree(kctx);
 }
diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c
index 20d55c793eb6..c8b9082f4a9d 100644
--- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c
+++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c
@@ -31,9 +31,9 @@
  * PERFORMANCE OF THIS SOFTWARE.
  */
 
+#include <crypto/skcipher.h>
 #include <linux/types.h>
 #include <linux/sunrpc/gss_krb5.h>
-#include <linux/crypto.h>
 
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY        RPCDBG_AUTH
@@ -43,13 +43,13 @@ static s32
 krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum,
 		      unsigned char *cksum, unsigned char *buf)
 {
-	struct crypto_blkcipher *cipher;
+	struct crypto_skcipher *cipher;
 	unsigned char plain[8];
 	s32 code;
 
 	dprintk("RPC:       %s:\n", __func__);
-	cipher = crypto_alloc_blkcipher(kctx->gk5e->encrypt_name, 0,
-					CRYPTO_ALG_ASYNC);
+	cipher = crypto_alloc_skcipher(kctx->gk5e->encrypt_name, 0,
+				       CRYPTO_ALG_ASYNC);
 	if (IS_ERR(cipher))
 		return PTR_ERR(cipher);
 
@@ -68,12 +68,12 @@ krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum,
 
 	code = krb5_encrypt(cipher, cksum, plain, buf, 8);
 out:
-	crypto_free_blkcipher(cipher);
+	crypto_free_skcipher(cipher);
 	return code;
 }
 s32
 krb5_make_seq_num(struct krb5_ctx *kctx,
-		struct crypto_blkcipher *key,
+		struct crypto_skcipher *key,
 		int direction,
 		u32 seqnum,
 		unsigned char *cksum, unsigned char *buf)
@@ -101,13 +101,13 @@ static s32
 krb5_get_rc4_seq_num(struct krb5_ctx *kctx, unsigned char *cksum,
 		     unsigned char *buf, int *direction, s32 *seqnum)
 {
-	struct crypto_blkcipher *cipher;
+	struct crypto_skcipher *cipher;
 	unsigned char plain[8];
 	s32 code;
 
 	dprintk("RPC:       %s:\n", __func__);
-	cipher = crypto_alloc_blkcipher(kctx->gk5e->encrypt_name, 0,
-					CRYPTO_ALG_ASYNC);
+	cipher = crypto_alloc_skcipher(kctx->gk5e->encrypt_name, 0,
+				       CRYPTO_ALG_ASYNC);
 	if (IS_ERR(cipher))
 		return PTR_ERR(cipher);
 
@@ -130,7 +130,7 @@ krb5_get_rc4_seq_num(struct krb5_ctx *kctx, unsigned char *cksum,
 	*seqnum = ((plain[0] << 24) | (plain[1] << 16) |
 					(plain[2] << 8) | (plain[3]));
 out:
-	crypto_free_blkcipher(cipher);
+	crypto_free_skcipher(cipher);
 	return code;
 }
 
@@ -142,7 +142,7 @@ krb5_get_seq_num(struct krb5_ctx *kctx,
 {
 	s32 code;
 	unsigned char plain[8];
-	struct crypto_blkcipher *key = kctx->seq;
+	struct crypto_skcipher *key = kctx->seq;
 
 	dprintk("RPC:       krb5_get_seq_num:\n");
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c
index ca7e92a32f84..765088e4ad84 100644
--- a/net/sunrpc/auth_gss/gss_krb5_wrap.c
+++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c
@@ -28,12 +28,12 @@
  * SUCH DAMAGES.
  */
 
+#include <crypto/skcipher.h>
 #include <linux/types.h>
 #include <linux/jiffies.h>
 #include <linux/sunrpc/gss_krb5.h>
 #include <linux/random.h>
 #include <linux/pagemap.h>
-#include <linux/crypto.h>
 
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
@@ -174,7 +174,7 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset,
 
 	now = get_seconds();
 
-	blocksize = crypto_blkcipher_blocksize(kctx->enc);
+	blocksize = crypto_skcipher_blocksize(kctx->enc);
 	gss_krb5_add_padding(buf, offset, blocksize);
 	BUG_ON((buf->len - offset) % blocksize);
 	plainlen = conflen + buf->len - offset;
@@ -239,10 +239,10 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset,
 		return GSS_S_FAILURE;
 
 	if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) {
-		struct crypto_blkcipher *cipher;
+		struct crypto_skcipher *cipher;
 		int err;
-		cipher = crypto_alloc_blkcipher(kctx->gk5e->encrypt_name, 0,
-						CRYPTO_ALG_ASYNC);
+		cipher = crypto_alloc_skcipher(kctx->gk5e->encrypt_name, 0,
+					       CRYPTO_ALG_ASYNC);
 		if (IS_ERR(cipher))
 			return GSS_S_FAILURE;
 
@@ -250,7 +250,7 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset,
 
 		err = gss_encrypt_xdr_buf(cipher, buf,
 					  offset + headlen - conflen, pages);
-		crypto_free_blkcipher(cipher);
+		crypto_free_skcipher(cipher);
 		if (err)
 			return GSS_S_FAILURE;
 	} else {
@@ -327,18 +327,18 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
 		return GSS_S_BAD_SIG;
 
 	if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) {
-		struct crypto_blkcipher *cipher;
+		struct crypto_skcipher *cipher;
 		int err;
 
-		cipher = crypto_alloc_blkcipher(kctx->gk5e->encrypt_name, 0,
-						CRYPTO_ALG_ASYNC);
+		cipher = crypto_alloc_skcipher(kctx->gk5e->encrypt_name, 0,
+					       CRYPTO_ALG_ASYNC);
 		if (IS_ERR(cipher))
 			return GSS_S_FAILURE;
 
 		krb5_rc4_setup_enc_key(kctx, cipher, seqnum);
 
 		err = gss_decrypt_xdr_buf(cipher, buf, crypt_offset);
-		crypto_free_blkcipher(cipher);
+		crypto_free_skcipher(cipher);
 		if (err)
 			return GSS_S_DEFECTIVE_TOKEN;
 	} else {
@@ -371,7 +371,7 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf)
 	/* Copy the data back to the right position.  XXX: Would probably be
 	 * better to copy and encrypt at the same time. */
 
-	blocksize = crypto_blkcipher_blocksize(kctx->enc);
+	blocksize = crypto_skcipher_blocksize(kctx->enc);
 	data_start = ptr + (GSS_KRB5_TOK_HDR_LEN + kctx->gk5e->cksumlength) +
 					conflen;
 	orig_start = buf->head[0].iov_base + offset;
@@ -473,7 +473,7 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset,
 	*ptr++ = 0xff;
 	be16ptr = (__be16 *)ptr;
 
-	blocksize = crypto_blkcipher_blocksize(kctx->acceptor_enc);
+	blocksize = crypto_skcipher_blocksize(kctx->acceptor_enc);
 	*be16ptr++ = 0;
 	/* "inner" token header always uses 0 for RRC */
 	*be16ptr++ = 0;
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 2b32fd602669..273bc3a35425 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1225,7 +1225,7 @@ int qword_get(char **bpp, char *dest, int bufsize)
 	if (bp[0] == '\\' && bp[1] == 'x') {
 		/* HEX STRING */
 		bp += 2;
-		while (len < bufsize) {
+		while (len < bufsize - 1) {
 			int h, l;
 
 			h = hex_to_bin(bp[0]);
diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c
index cc1251d07297..2dcd7640eeb5 100644
--- a/net/sunrpc/xprtrdma/backchannel.c
+++ b/net/sunrpc/xprtrdma/backchannel.c
@@ -341,6 +341,8 @@ void rpcrdma_bc_receive_call(struct rpcrdma_xprt *r_xprt,
 	rqst->rq_reply_bytes_recvd = 0;
 	rqst->rq_bytes_sent = 0;
 	rqst->rq_xid = headerp->rm_xid;
+
+	rqst->rq_private_buf.len = size;
 	set_bit(RPC_BC_PA_IN_USE, &rqst->rq_bc_pa_state);
 
 	buf = &rqst->rq_rcv_buf;
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 47f7da58a7f0..8b5833c1ff2e 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -1093,8 +1093,11 @@ int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 		.cb = cb,
 		.idx = idx,
 	};
+	int err;
 
-	switchdev_port_obj_dump(dev, &dump.fdb.obj, switchdev_port_fdb_dump_cb);
+	err = switchdev_port_obj_dump(dev, &dump.fdb.obj,
+				      switchdev_port_fdb_dump_cb);
+	cb->args[1] = err;
 	return dump.idx;
 }
 EXPORT_SYMBOL_GPL(switchdev_port_fdb_dump);
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 0c2944fb9ae0..347cdc99ed09 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1973,8 +1973,10 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg)
 
 	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
 			  NLM_F_MULTI, TIPC_NL_LINK_GET);
-	if (!hdr)
+	if (!hdr) {
+		tipc_bcast_unlock(net);
 		return -EMSGSIZE;
+	}
 
 	attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK);
 	if (!attrs)
diff --git a/net/tipc/node.c b/net/tipc/node.c
index fa97d9649a28..9d7a16fc5ca4 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -346,12 +346,6 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities)
 	skb_queue_head_init(&n->bc_entry.inputq2);
 	for (i = 0; i < MAX_BEARERS; i++)
 		spin_lock_init(&n->links[i].lock);
-	hlist_add_head_rcu(&n->hash, &tn->node_htable[tipc_hashfn(addr)]);
-	list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
-		if (n->addr < temp_node->addr)
-			break;
-	}
-	list_add_tail_rcu(&n->list, &temp_node->list);
 	n->state = SELF_DOWN_PEER_LEAVING;
 	n->signature = INVALID_NODE_SIG;
 	n->active_links[0] = INVALID_BEARER_ID;
@@ -372,6 +366,12 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities)
 	tipc_node_get(n);
 	setup_timer(&n->timer, tipc_node_timeout, (unsigned long)n);
 	n->keepalive_intv = U32_MAX;
+	hlist_add_head_rcu(&n->hash, &tn->node_htable[tipc_hashfn(addr)]);
+	list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
+		if (n->addr < temp_node->addr)
+			break;
+	}
+	list_add_tail_rcu(&n->list, &temp_node->list);
 exit:
 	spin_unlock_bh(&tn->node_list_lock);
 	return n;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 69c29050f14a..4d420bb27396 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -673,7 +673,7 @@ static int tipc_sendmcast(struct  socket *sock, struct tipc_name_seq *seq,
 	struct tipc_sock *tsk = tipc_sk(sk);
 	struct net *net = sock_net(sk);
 	struct tipc_msg *mhdr = &tsk->phdr;
-	struct sk_buff_head *pktchain = &sk->sk_write_queue;
+	struct sk_buff_head pktchain;
 	struct iov_iter save = msg->msg_iter;
 	uint mtu;
 	int rc;
@@ -687,14 +687,16 @@ static int tipc_sendmcast(struct  socket *sock, struct tipc_name_seq *seq,
 	msg_set_nameupper(mhdr, seq->upper);
 	msg_set_hdr_sz(mhdr, MCAST_H_SIZE);
 
+	skb_queue_head_init(&pktchain);
+
 new_mtu:
 	mtu = tipc_bcast_get_mtu(net);
-	rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, pktchain);
+	rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, &pktchain);
 	if (unlikely(rc < 0))
 		return rc;
 
 	do {
-		rc = tipc_bcast_xmit(net, pktchain);
+		rc = tipc_bcast_xmit(net, &pktchain);
 		if (likely(!rc))
 			return dsz;
 
@@ -704,7 +706,7 @@ new_mtu:
 			if (!rc)
 				continue;
 		}
-		__skb_queue_purge(pktchain);
+		__skb_queue_purge(&pktchain);
 		if (rc == -EMSGSIZE) {
 			msg->msg_iter = save;
 			goto new_mtu;
@@ -863,7 +865,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
 	struct net *net = sock_net(sk);
 	struct tipc_msg *mhdr = &tsk->phdr;
 	u32 dnode, dport;
-	struct sk_buff_head *pktchain = &sk->sk_write_queue;
+	struct sk_buff_head pktchain;
 	struct sk_buff *skb;
 	struct tipc_name_seq *seq;
 	struct iov_iter save;
@@ -924,17 +926,18 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
 		msg_set_hdr_sz(mhdr, BASIC_H_SIZE);
 	}
 
+	skb_queue_head_init(&pktchain);
 	save = m->msg_iter;
 new_mtu:
 	mtu = tipc_node_get_mtu(net, dnode, tsk->portid);
-	rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, pktchain);
+	rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, &pktchain);
 	if (rc < 0)
 		return rc;
 
 	do {
-		skb = skb_peek(pktchain);
+		skb = skb_peek(&pktchain);
 		TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong;
-		rc = tipc_node_xmit(net, pktchain, dnode, tsk->portid);
+		rc = tipc_node_xmit(net, &pktchain, dnode, tsk->portid);
 		if (likely(!rc)) {
 			if (sock->state != SS_READY)
 				sock->state = SS_CONNECTING;
@@ -946,7 +949,7 @@ new_mtu:
 			if (!rc)
 				continue;
 		}
-		__skb_queue_purge(pktchain);
+		__skb_queue_purge(&pktchain);
 		if (rc == -EMSGSIZE) {
 			m->msg_iter = save;
 			goto new_mtu;
@@ -1016,7 +1019,7 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz)
 	struct net *net = sock_net(sk);
 	struct tipc_sock *tsk = tipc_sk(sk);
 	struct tipc_msg *mhdr = &tsk->phdr;
-	struct sk_buff_head *pktchain = &sk->sk_write_queue;
+	struct sk_buff_head pktchain;
 	DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
 	u32 portid = tsk->portid;
 	int rc = -EINVAL;
@@ -1044,17 +1047,19 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz)
 
 	timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
 	dnode = tsk_peer_node(tsk);
+	skb_queue_head_init(&pktchain);
 
 next:
 	save = m->msg_iter;
 	mtu = tsk->max_pkt;
 	send = min_t(uint, dsz - sent, TIPC_MAX_USER_MSG_SIZE);
-	rc = tipc_msg_build(mhdr, m, sent, send, mtu, pktchain);
+	rc = tipc_msg_build(mhdr, m, sent, send, mtu, &pktchain);
 	if (unlikely(rc < 0))
 		return rc;
+
 	do {
 		if (likely(!tsk_conn_cong(tsk))) {
-			rc = tipc_node_xmit(net, pktchain, dnode, portid);
+			rc = tipc_node_xmit(net, &pktchain, dnode, portid);
 			if (likely(!rc)) {
 				tsk->sent_unacked++;
 				sent += send;
@@ -1063,7 +1068,7 @@ next:
 				goto next;
 			}
 			if (rc == -EMSGSIZE) {
-				__skb_queue_purge(pktchain);
+				__skb_queue_purge(&pktchain);
 				tsk->max_pkt = tipc_node_get_mtu(net, dnode,
 								 portid);
 				m->msg_iter = save;
@@ -1077,7 +1082,7 @@ next:
 		rc = tipc_wait_for_sndpkt(sock, &timeo);
 	} while (!rc);
 
-	__skb_queue_purge(pktchain);
+	__skb_queue_purge(&pktchain);
 	return sent ? sent : rc;
 }
 
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 69ee2eeef968..f9ff73a8d815 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -296,7 +296,8 @@ static void tipc_subscrb_rcv_cb(struct net *net, int conid,
 	if (tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscrb, &sub))
 		return tipc_conn_terminate(tn->topsrv, subscrb->conid);
 
-	tipc_nametbl_subscribe(sub);
+	if (sub)
+		tipc_nametbl_subscribe(sub);
 }
 
 /* Handle one request to establish a new subscriber */
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 49d5093eb055..f75f847e688d 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1496,7 +1496,7 @@ static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 	UNIXCB(skb).fp = NULL;
 
 	for (i = scm->fp->count-1; i >= 0; i--)
-		unix_notinflight(scm->fp->fp[i]);
+		unix_notinflight(scm->fp->user, scm->fp->fp[i]);
 }
 
 static void unix_destruct_scm(struct sk_buff *skb)
@@ -1561,7 +1561,7 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 		return -ENOMEM;
 
 	for (i = scm->fp->count - 1; i >= 0; i--)
-		unix_inflight(scm->fp->fp[i]);
+		unix_inflight(scm->fp->user, scm->fp->fp[i]);
 	return max_level;
 }
 
@@ -1781,7 +1781,12 @@ restart_locked:
 			goto out_unlock;
 	}
 
-	if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
+	/* other == sk && unix_peer(other) != sk if
+	 * - unix_peer(sk) == NULL, destination address bound to sk
+	 * - unix_peer(sk) == sk by time of get but disconnected before lock
+	 */
+	if (other != sk &&
+	    unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
 		if (timeo) {
 			timeo = unix_wait_for_peer(other, timeo);
 
@@ -2277,13 +2282,15 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state)
 	size_t size = state->size;
 	unsigned int last_len;
 
-	err = -EINVAL;
-	if (sk->sk_state != TCP_ESTABLISHED)
+	if (unlikely(sk->sk_state != TCP_ESTABLISHED)) {
+		err = -EINVAL;
 		goto out;
+	}
 
-	err = -EOPNOTSUPP;
-	if (flags & MSG_OOB)
+	if (unlikely(flags & MSG_OOB)) {
+		err = -EOPNOTSUPP;
 		goto out;
+	}
 
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, size);
 	timeo = sock_rcvtimeo(sk, noblock);
@@ -2305,6 +2312,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state)
 		bool drop_skb;
 		struct sk_buff *skb, *last;
 
+redo:
 		unix_state_lock(sk);
 		if (sock_flag(sk, SOCK_DEAD)) {
 			err = -ECONNRESET;
@@ -2329,9 +2337,11 @@ again:
 				goto unlock;
 
 			unix_state_unlock(sk);
-			err = -EAGAIN;
-			if (!timeo)
+			if (!timeo) {
+				err = -EAGAIN;
 				break;
+			}
+
 			mutex_unlock(&u->readlock);
 
 			timeo = unix_stream_data_wait(sk, timeo, last,
@@ -2344,7 +2354,7 @@ again:
 			}
 
 			mutex_lock(&u->readlock);
-			continue;
+			goto redo;
 unlock:
 			unix_state_unlock(sk);
 			break;
diff --git a/net/unix/diag.c b/net/unix/diag.c
index c512f64d5287..4d9679701a6d 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -220,7 +220,7 @@ done:
 	return skb->len;
 }
 
-static struct sock *unix_lookup_by_ino(int ino)
+static struct sock *unix_lookup_by_ino(unsigned int ino)
 {
 	int i;
 	struct sock *sk;
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 8fcdc2283af5..6a0d48525fcf 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -116,7 +116,7 @@ struct sock *unix_get_socket(struct file *filp)
  * descriptor if it is for an AF_UNIX socket.
  */
 
-void unix_inflight(struct file *fp)
+void unix_inflight(struct user_struct *user, struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
 
@@ -133,11 +133,11 @@ void unix_inflight(struct file *fp)
 		}
 		unix_tot_inflight++;
 	}
-	fp->f_cred->user->unix_inflight++;
+	user->unix_inflight++;
 	spin_unlock(&unix_gc_lock);
 }
 
-void unix_notinflight(struct file *fp)
+void unix_notinflight(struct user_struct *user, struct file *fp)
 {
 	struct sock *s = unix_get_socket(fp);
 
@@ -152,7 +152,7 @@ void unix_notinflight(struct file *fp)
 			list_del_init(&u->link);
 		unix_tot_inflight--;
 	}
-	fp->f_cred->user->unix_inflight--;
+	user->unix_inflight--;
 	spin_unlock(&unix_gc_lock);
 }
 
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 7fd1220fbfa0..bbe65dcb9738 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1557,8 +1557,6 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 	if (err < 0)
 		goto out;
 
-	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
-
 	while (total_written < len) {
 		ssize_t written;
 
@@ -1578,7 +1576,9 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 				goto out_wait;
 
 			release_sock(sk);
+			prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 			timeout = schedule_timeout(timeout);
+			finish_wait(sk_sleep(sk), &wait);
 			lock_sock(sk);
 			if (signal_pending(current)) {
 				err = sock_intr_errno(timeout);
@@ -1588,8 +1588,6 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 				goto out_wait;
 			}
 
-			prepare_to_wait(sk_sleep(sk), &wait,
-					TASK_INTERRUPTIBLE);
 		}
 
 		/* These checks occur both as part of and after the loop
@@ -1635,7 +1633,6 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 out_wait:
 	if (total_written > 0)
 		err = total_written;
-	finish_wait(sk_sleep(sk), &wait);
 out:
 	release_sock(sk);
 	return err;
@@ -1716,7 +1713,6 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	if (err < 0)
 		goto out;
 
-	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 
 	while (1) {
 		s64 ready = vsock_stream_has_data(vsk);
@@ -1727,7 +1723,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 			 */
 
 			err = -ENOMEM;
-			goto out_wait;
+			goto out;
 		} else if (ready > 0) {
 			ssize_t read;
 
@@ -1750,7 +1746,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 					vsk, target, read,
 					!(flags & MSG_PEEK), &recv_data);
 			if (err < 0)
-				goto out_wait;
+				goto out;
 
 			if (read >= target || flags & MSG_PEEK)
 				break;
@@ -1773,7 +1769,9 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 				break;
 
 			release_sock(sk);
+			prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 			timeout = schedule_timeout(timeout);
+			finish_wait(sk_sleep(sk), &wait);
 			lock_sock(sk);
 
 			if (signal_pending(current)) {
@@ -1783,9 +1781,6 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 				err = -EAGAIN;
 				break;
 			}
-
-			prepare_to_wait(sk_sleep(sk), &wait,
-					TASK_INTERRUPTIBLE);
 		}
 	}
 
@@ -1816,8 +1811,6 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		err = copied;
 	}
 
-out_wait:
-	finish_wait(sk_sleep(sk), &wait);
 out:
 	release_sock(sk);
 	return err;
diff --git a/net/wireless/core.c b/net/wireless/core.c
index b0915515640e..8f0bac7e03c4 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1147,6 +1147,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 		return NOTIFY_DONE;
 	}
 
+	wireless_nlevent_flush();
+
 	return NOTIFY_OK;
 }
 
diff --git a/net/wireless/lib80211_crypt_tkip.c b/net/wireless/lib80211_crypt_tkip.c
index 3cd819539241..71447cf86306 100644
--- a/net/wireless/lib80211_crypt_tkip.c
+++ b/net/wireless/lib80211_crypt_tkip.c
@@ -29,7 +29,8 @@
 #include <linux/ieee80211.h>
 #include <net/iw_handler.h>
 
-#include <linux/crypto.h>
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
 #include <linux/crc32.h>
 
 #include <net/lib80211.h>
@@ -63,10 +64,10 @@ struct lib80211_tkip_data {
 
 	int key_idx;
 
-	struct crypto_blkcipher *rx_tfm_arc4;
-	struct crypto_hash *rx_tfm_michael;
-	struct crypto_blkcipher *tx_tfm_arc4;
-	struct crypto_hash *tx_tfm_michael;
+	struct crypto_skcipher *rx_tfm_arc4;
+	struct crypto_ahash *rx_tfm_michael;
+	struct crypto_skcipher *tx_tfm_arc4;
+	struct crypto_ahash *tx_tfm_michael;
 
 	/* scratch buffers for virt_to_page() (crypto API) */
 	u8 rx_hdr[16], tx_hdr[16];
@@ -98,29 +99,29 @@ static void *lib80211_tkip_init(int key_idx)
 
 	priv->key_idx = key_idx;
 
-	priv->tx_tfm_arc4 = crypto_alloc_blkcipher("ecb(arc4)", 0,
-						CRYPTO_ALG_ASYNC);
+	priv->tx_tfm_arc4 = crypto_alloc_skcipher("ecb(arc4)", 0,
+						  CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->tx_tfm_arc4)) {
 		priv->tx_tfm_arc4 = NULL;
 		goto fail;
 	}
 
-	priv->tx_tfm_michael = crypto_alloc_hash("michael_mic", 0,
-						 CRYPTO_ALG_ASYNC);
+	priv->tx_tfm_michael = crypto_alloc_ahash("michael_mic", 0,
+						  CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->tx_tfm_michael)) {
 		priv->tx_tfm_michael = NULL;
 		goto fail;
 	}
 
-	priv->rx_tfm_arc4 = crypto_alloc_blkcipher("ecb(arc4)", 0,
-						CRYPTO_ALG_ASYNC);
+	priv->rx_tfm_arc4 = crypto_alloc_skcipher("ecb(arc4)", 0,
+						  CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->rx_tfm_arc4)) {
 		priv->rx_tfm_arc4 = NULL;
 		goto fail;
 	}
 
-	priv->rx_tfm_michael = crypto_alloc_hash("michael_mic", 0,
-						 CRYPTO_ALG_ASYNC);
+	priv->rx_tfm_michael = crypto_alloc_ahash("michael_mic", 0,
+						  CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->rx_tfm_michael)) {
 		priv->rx_tfm_michael = NULL;
 		goto fail;
@@ -130,14 +131,10 @@ static void *lib80211_tkip_init(int key_idx)
 
       fail:
 	if (priv) {
-		if (priv->tx_tfm_michael)
-			crypto_free_hash(priv->tx_tfm_michael);
-		if (priv->tx_tfm_arc4)
-			crypto_free_blkcipher(priv->tx_tfm_arc4);
-		if (priv->rx_tfm_michael)
-			crypto_free_hash(priv->rx_tfm_michael);
-		if (priv->rx_tfm_arc4)
-			crypto_free_blkcipher(priv->rx_tfm_arc4);
+		crypto_free_ahash(priv->tx_tfm_michael);
+		crypto_free_skcipher(priv->tx_tfm_arc4);
+		crypto_free_ahash(priv->rx_tfm_michael);
+		crypto_free_skcipher(priv->rx_tfm_arc4);
 		kfree(priv);
 	}
 
@@ -148,14 +145,10 @@ static void lib80211_tkip_deinit(void *priv)
 {
 	struct lib80211_tkip_data *_priv = priv;
 	if (_priv) {
-		if (_priv->tx_tfm_michael)
-			crypto_free_hash(_priv->tx_tfm_michael);
-		if (_priv->tx_tfm_arc4)
-			crypto_free_blkcipher(_priv->tx_tfm_arc4);
-		if (_priv->rx_tfm_michael)
-			crypto_free_hash(_priv->rx_tfm_michael);
-		if (_priv->rx_tfm_arc4)
-			crypto_free_blkcipher(_priv->rx_tfm_arc4);
+		crypto_free_ahash(_priv->tx_tfm_michael);
+		crypto_free_skcipher(_priv->tx_tfm_arc4);
+		crypto_free_ahash(_priv->rx_tfm_michael);
+		crypto_free_skcipher(_priv->rx_tfm_arc4);
 	}
 	kfree(priv);
 }
@@ -353,11 +346,12 @@ static int lib80211_tkip_hdr(struct sk_buff *skb, int hdr_len,
 static int lib80211_tkip_encrypt(struct sk_buff *skb, int hdr_len, void *priv)
 {
 	struct lib80211_tkip_data *tkey = priv;
-	struct blkcipher_desc desc = { .tfm = tkey->tx_tfm_arc4 };
+	SKCIPHER_REQUEST_ON_STACK(req, tkey->tx_tfm_arc4);
 	int len;
 	u8 rc4key[16], *pos, *icv;
 	u32 crc;
 	struct scatterlist sg;
+	int err;
 
 	if (tkey->flags & IEEE80211_CRYPTO_TKIP_COUNTERMEASURES) {
 		struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
@@ -382,9 +376,14 @@ static int lib80211_tkip_encrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	icv[2] = crc >> 16;
 	icv[3] = crc >> 24;
 
-	crypto_blkcipher_setkey(tkey->tx_tfm_arc4, rc4key, 16);
+	crypto_skcipher_setkey(tkey->tx_tfm_arc4, rc4key, 16);
 	sg_init_one(&sg, pos, len + 4);
-	return crypto_blkcipher_encrypt(&desc, &sg, &sg, len + 4);
+	skcipher_request_set_tfm(req, tkey->tx_tfm_arc4);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, &sg, &sg, len + 4, NULL);
+	err = crypto_skcipher_encrypt(req);
+	skcipher_request_zero(req);
+	return err;
 }
 
 /*
@@ -403,7 +402,7 @@ static inline int tkip_replay_check(u32 iv32_n, u16 iv16_n,
 static int lib80211_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 {
 	struct lib80211_tkip_data *tkey = priv;
-	struct blkcipher_desc desc = { .tfm = tkey->rx_tfm_arc4 };
+	SKCIPHER_REQUEST_ON_STACK(req, tkey->rx_tfm_arc4);
 	u8 rc4key[16];
 	u8 keyidx, *pos;
 	u32 iv32;
@@ -413,6 +412,7 @@ static int lib80211_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	u32 crc;
 	struct scatterlist sg;
 	int plen;
+	int err;
 
 	hdr = (struct ieee80211_hdr *)skb->data;
 
@@ -465,9 +465,14 @@ static int lib80211_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 
 	plen = skb->len - hdr_len - 12;
 
-	crypto_blkcipher_setkey(tkey->rx_tfm_arc4, rc4key, 16);
+	crypto_skcipher_setkey(tkey->rx_tfm_arc4, rc4key, 16);
 	sg_init_one(&sg, pos, plen + 4);
-	if (crypto_blkcipher_decrypt(&desc, &sg, &sg, plen + 4)) {
+	skcipher_request_set_tfm(req, tkey->rx_tfm_arc4);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, &sg, &sg, plen + 4, NULL);
+	err = crypto_skcipher_decrypt(req);
+	skcipher_request_zero(req);
+	if (err) {
 		net_dbg_ratelimited("TKIP: failed to decrypt received packet from %pM\n",
 				    hdr->addr2);
 		return -7;
@@ -505,11 +510,12 @@ static int lib80211_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	return keyidx;
 }
 
-static int michael_mic(struct crypto_hash *tfm_michael, u8 * key, u8 * hdr,
+static int michael_mic(struct crypto_ahash *tfm_michael, u8 * key, u8 * hdr,
 		       u8 * data, size_t data_len, u8 * mic)
 {
-	struct hash_desc desc;
+	AHASH_REQUEST_ON_STACK(req, tfm_michael);
 	struct scatterlist sg[2];
+	int err;
 
 	if (tfm_michael == NULL) {
 		pr_warn("%s(): tfm_michael == NULL\n", __func__);
@@ -519,12 +525,15 @@ static int michael_mic(struct crypto_hash *tfm_michael, u8 * key, u8 * hdr,
 	sg_set_buf(&sg[0], hdr, 16);
 	sg_set_buf(&sg[1], data, data_len);
 
-	if (crypto_hash_setkey(tfm_michael, key, 8))
+	if (crypto_ahash_setkey(tfm_michael, key, 8))
 		return -1;
 
-	desc.tfm = tfm_michael;
-	desc.flags = 0;
-	return crypto_hash_digest(&desc, sg, data_len + 16, mic);
+	ahash_request_set_tfm(req, tfm_michael);
+	ahash_request_set_callback(req, 0, NULL, NULL);
+	ahash_request_set_crypt(req, sg, mic, data_len + 16);
+	err = crypto_ahash_digest(req);
+	ahash_request_zero(req);
+	return err;
 }
 
 static void michael_mic_hdr(struct sk_buff *skb, u8 * hdr)
@@ -645,10 +654,10 @@ static int lib80211_tkip_set_key(void *key, int len, u8 * seq, void *priv)
 {
 	struct lib80211_tkip_data *tkey = priv;
 	int keyidx;
-	struct crypto_hash *tfm = tkey->tx_tfm_michael;
-	struct crypto_blkcipher *tfm2 = tkey->tx_tfm_arc4;
-	struct crypto_hash *tfm3 = tkey->rx_tfm_michael;
-	struct crypto_blkcipher *tfm4 = tkey->rx_tfm_arc4;
+	struct crypto_ahash *tfm = tkey->tx_tfm_michael;
+	struct crypto_skcipher *tfm2 = tkey->tx_tfm_arc4;
+	struct crypto_ahash *tfm3 = tkey->rx_tfm_michael;
+	struct crypto_skcipher *tfm4 = tkey->rx_tfm_arc4;
 
 	keyidx = tkey->key_idx;
 	memset(tkey, 0, sizeof(*tkey));
diff --git a/net/wireless/lib80211_crypt_wep.c b/net/wireless/lib80211_crypt_wep.c
index 1c292e4ea7b6..d05f58b0fd04 100644
--- a/net/wireless/lib80211_crypt_wep.c
+++ b/net/wireless/lib80211_crypt_wep.c
@@ -22,7 +22,7 @@
 
 #include <net/lib80211.h>
 
-#include <linux/crypto.h>
+#include <crypto/skcipher.h>
 #include <linux/crc32.h>
 
 MODULE_AUTHOR("Jouni Malinen");
@@ -35,8 +35,8 @@ struct lib80211_wep_data {
 	u8 key[WEP_KEY_LEN + 1];
 	u8 key_len;
 	u8 key_idx;
-	struct crypto_blkcipher *tx_tfm;
-	struct crypto_blkcipher *rx_tfm;
+	struct crypto_skcipher *tx_tfm;
+	struct crypto_skcipher *rx_tfm;
 };
 
 static void *lib80211_wep_init(int keyidx)
@@ -48,13 +48,13 @@ static void *lib80211_wep_init(int keyidx)
 		goto fail;
 	priv->key_idx = keyidx;
 
-	priv->tx_tfm = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
+	priv->tx_tfm = crypto_alloc_skcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->tx_tfm)) {
 		priv->tx_tfm = NULL;
 		goto fail;
 	}
 
-	priv->rx_tfm = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
+	priv->rx_tfm = crypto_alloc_skcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(priv->rx_tfm)) {
 		priv->rx_tfm = NULL;
 		goto fail;
@@ -66,10 +66,8 @@ static void *lib80211_wep_init(int keyidx)
 
       fail:
 	if (priv) {
-		if (priv->tx_tfm)
-			crypto_free_blkcipher(priv->tx_tfm);
-		if (priv->rx_tfm)
-			crypto_free_blkcipher(priv->rx_tfm);
+		crypto_free_skcipher(priv->tx_tfm);
+		crypto_free_skcipher(priv->rx_tfm);
 		kfree(priv);
 	}
 	return NULL;
@@ -79,10 +77,8 @@ static void lib80211_wep_deinit(void *priv)
 {
 	struct lib80211_wep_data *_priv = priv;
 	if (_priv) {
-		if (_priv->tx_tfm)
-			crypto_free_blkcipher(_priv->tx_tfm);
-		if (_priv->rx_tfm)
-			crypto_free_blkcipher(_priv->rx_tfm);
+		crypto_free_skcipher(_priv->tx_tfm);
+		crypto_free_skcipher(_priv->rx_tfm);
 	}
 	kfree(priv);
 }
@@ -133,11 +129,12 @@ static int lib80211_wep_build_iv(struct sk_buff *skb, int hdr_len,
 static int lib80211_wep_encrypt(struct sk_buff *skb, int hdr_len, void *priv)
 {
 	struct lib80211_wep_data *wep = priv;
-	struct blkcipher_desc desc = { .tfm = wep->tx_tfm };
+	SKCIPHER_REQUEST_ON_STACK(req, wep->tx_tfm);
 	u32 crc, klen, len;
 	u8 *pos, *icv;
 	struct scatterlist sg;
 	u8 key[WEP_KEY_LEN + 3];
+	int err;
 
 	/* other checks are in lib80211_wep_build_iv */
 	if (skb_tailroom(skb) < 4)
@@ -165,9 +162,14 @@ static int lib80211_wep_encrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	icv[2] = crc >> 16;
 	icv[3] = crc >> 24;
 
-	crypto_blkcipher_setkey(wep->tx_tfm, key, klen);
+	crypto_skcipher_setkey(wep->tx_tfm, key, klen);
 	sg_init_one(&sg, pos, len + 4);
-	return crypto_blkcipher_encrypt(&desc, &sg, &sg, len + 4);
+	skcipher_request_set_tfm(req, wep->tx_tfm);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, &sg, &sg, len + 4, NULL);
+	err = crypto_skcipher_encrypt(req);
+	skcipher_request_zero(req);
+	return err;
 }
 
 /* Perform WEP decryption on given buffer. Buffer includes whole WEP part of
@@ -180,11 +182,12 @@ static int lib80211_wep_encrypt(struct sk_buff *skb, int hdr_len, void *priv)
 static int lib80211_wep_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 {
 	struct lib80211_wep_data *wep = priv;
-	struct blkcipher_desc desc = { .tfm = wep->rx_tfm };
+	SKCIPHER_REQUEST_ON_STACK(req, wep->rx_tfm);
 	u32 crc, klen, plen;
 	u8 key[WEP_KEY_LEN + 3];
 	u8 keyidx, *pos, icv[4];
 	struct scatterlist sg;
+	int err;
 
 	if (skb->len < hdr_len + 8)
 		return -1;
@@ -205,9 +208,14 @@ static int lib80211_wep_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	/* Apply RC4 to data and compute CRC32 over decrypted data */
 	plen = skb->len - hdr_len - 8;
 
-	crypto_blkcipher_setkey(wep->rx_tfm, key, klen);
+	crypto_skcipher_setkey(wep->rx_tfm, key, klen);
 	sg_init_one(&sg, pos, plen + 4);
-	if (crypto_blkcipher_decrypt(&desc, &sg, &sg, plen + 4))
+	skcipher_request_set_tfm(req, wep->rx_tfm);
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	skcipher_request_set_crypt(req, &sg, &sg, plen + 4, NULL);
+	err = crypto_skcipher_decrypt(req);
+	skcipher_request_zero(req);
+	if (err)
 		return -7;
 
 	crc = ~crc32_le(~0, pos, plen);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d4786f2802aa..711cb7ad6ae0 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -7547,7 +7547,7 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info)
 
 		if ((ibss.chandef.width != NL80211_CHAN_WIDTH_20_NOHT) &&
 		    no_ht) {
-			kfree(connkeys);
+			kzfree(connkeys);
 			return -EINVAL;
 		}
 	}
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 8020b5b094d4..d49ed7666d4c 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -917,6 +917,12 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie,
 
 	nl80211_send_disconnected(rdev, dev, reason, ie, ie_len, from_ap);
 
+	/* stop critical protocol if supported */
+	if (rdev->ops->crit_proto_stop && rdev->crit_proto_nlportid) {
+		rdev->crit_proto_nlportid = 0;
+		rdev_crit_proto_stop(rdev, wdev);
+	}
+
 	/*
 	 * Delete all the keys ... pairwise keys can't really
 	 * exist any more anyway, but default keys might.
diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c
index c8717c1d082e..b50ee5d622e1 100644
--- a/net/wireless/wext-core.c
+++ b/net/wireless/wext-core.c
@@ -342,6 +342,40 @@ static const int compat_event_type_size[] = {
 
 /* IW event code */
 
+void wireless_nlevent_flush(void)
+{
+	struct sk_buff *skb;
+	struct net *net;
+
+	ASSERT_RTNL();
+
+	for_each_net(net) {
+		while ((skb = skb_dequeue(&net->wext_nlevents)))
+			rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL,
+				    GFP_KERNEL);
+	}
+}
+EXPORT_SYMBOL_GPL(wireless_nlevent_flush);
+
+static int wext_netdev_notifier_call(struct notifier_block *nb,
+				     unsigned long state, void *ptr)
+{
+	/*
+	 * When a netdev changes state in any way, flush all pending messages
+	 * to avoid them going out in a strange order, e.g. RTM_NEWLINK after
+	 * RTM_DELLINK, or with IFF_UP after without IFF_UP during dev_close()
+	 * or similar - all of which could otherwise happen due to delays from
+	 * schedule_work().
+	 */
+	wireless_nlevent_flush();
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block wext_netdev_notifier = {
+	.notifier_call = wext_netdev_notifier_call,
+};
+
 static int __net_init wext_pernet_init(struct net *net)
 {
 	skb_queue_head_init(&net->wext_nlevents);
@@ -360,7 +394,12 @@ static struct pernet_operations wext_pernet_ops = {
 
 static int __init wireless_nlevent_init(void)
 {
-	return register_pernet_subsys(&wext_pernet_ops);
+	int err = register_pernet_subsys(&wext_pernet_ops);
+
+	if (err)
+		return err;
+
+	return register_netdevice_notifier(&wext_netdev_notifier);
 }
 
 subsys_initcall(wireless_nlevent_init);
@@ -368,17 +407,8 @@ subsys_initcall(wireless_nlevent_init);
 /* Process events generated by the wireless layer or the driver. */
 static void wireless_nlevent_process(struct work_struct *work)
 {
-	struct sk_buff *skb;
-	struct net *net;
-
 	rtnl_lock();
-
-	for_each_net(net) {
-		while ((skb = skb_dequeue(&net->wext_nlevents)))
-			rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL,
-				    GFP_KERNEL);
-	}
-
+	wireless_nlevent_flush();
 	rtnl_unlock();
 }
 
diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c
index f07224d8b88f..250e567ba3d6 100644
--- a/net/xfrm/xfrm_algo.c
+++ b/net/xfrm/xfrm_algo.c
@@ -9,6 +9,8 @@
  * any later version.
  */
 
+#include <crypto/hash.h>
+#include <crypto/skcipher.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/pfkeyv2.h>
@@ -782,14 +784,13 @@ void xfrm_probe_algs(void)
 	BUG_ON(in_softirq());
 
 	for (i = 0; i < aalg_entries(); i++) {
-		status = crypto_has_hash(aalg_list[i].name, 0,
-					 CRYPTO_ALG_ASYNC);
+		status = crypto_has_ahash(aalg_list[i].name, 0, 0);
 		if (aalg_list[i].available != status)
 			aalg_list[i].available = status;
 	}
 
 	for (i = 0; i < ealg_entries(); i++) {
-		status = crypto_has_ablkcipher(ealg_list[i].name, 0, 0);
+		status = crypto_has_skcipher(ealg_list[i].name, 0, 0);
 		if (ealg_list[i].available != status)
 			ealg_list[i].available = status;
 	}
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 0147c91fa549..d574d13ba963 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -269,7 +269,8 @@ our $Sparse	= qr{
 			__init_refok|
 			__kprobes|
 			__ref|
-			__rcu
+			__rcu|
+			__private
 		}x;
 our $InitAttributePrefix = qr{__(?:mem|cpu|dev|net_|)};
 our $InitAttributeData = qr{$InitAttributePrefix(?:initdata\b)};
@@ -3239,6 +3240,30 @@ sub process {
 #ignore lines not being added
 		next if ($line =~ /^[^\+]/);
 
+# check for declarations of signed or unsigned without int
+		while ($line =~ m{($Declare)\s*(?!char\b|short\b|int\b|long\b)\s*($Ident)?\s*[=,;\[\)\(]}g) {
+			my $type = $1;
+			my $var = $2;
+			$var = "" if (!defined $var);
+			if ($type =~ /^(?:(?:$Storage|$Inline|$Attribute)\s+)*((?:un)?signed)((?:\s*\*)*)\s*$/) {
+				my $sign = $1;
+				my $pointer = $2;
+
+				$pointer = "" if (!defined $pointer);
+
+				if (WARN("UNSPECIFIED_INT",
+					 "Prefer '" . trim($sign) . " int" . rtrim($pointer) . "' to bare use of '$sign" . rtrim($pointer) . "'\n" . $herecurr) &&
+				    $fix) {
+					my $decl = trim($sign) . " int ";
+					my $comp_pointer = $pointer;
+					$comp_pointer =~ s/\s//g;
+					$decl .= $comp_pointer;
+					$decl = rtrim($decl) if ($var eq "");
+					$fixed[$fixlinenr] =~ s@\b$sign\s*\Q$pointer\E\s*$var\b@$decl$var@;
+				}
+			}
+		}
+
 # TEST: allow direct testing of the type matcher.
 		if ($dbg_type) {
 			if ($line =~ /^.\s*$Declare\s*$/) {
@@ -4108,7 +4133,7 @@ sub process {
 ## 		}
 
 #need space before brace following if, while, etc
-		if (($line =~ /\(.*\)\{/ && $line !~ /\($Type\){/) ||
+		if (($line =~ /\(.*\)\{/ && $line !~ /\($Type\)\{/) ||
 		    $line =~ /do\{/) {
 			if (ERROR("SPACING",
 				  "space required before the open brace '{'\n" . $herecurr) &&
@@ -4560,6 +4585,9 @@ sub process {
 			{
 			}
 
+			# Make asm volatile uses seem like a generic function
+			$dstat =~ s/\b_*asm_*\s+_*volatile_*\b/asm_volatile/g;
+
 			my $exceptions = qr{
 				$Declare|
 				module_param_named|
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 8fa81e84e295..638b143ee60f 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -22,6 +22,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <ctype.h>
+#include <limits.h>
 
 #ifndef ARRAY_SIZE
 #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0]))
@@ -34,6 +35,7 @@ struct sym_entry {
 	unsigned int len;
 	unsigned int start_pos;
 	unsigned char *sym;
+	unsigned int percpu_absolute;
 };
 
 struct addr_range {
@@ -42,6 +44,7 @@ struct addr_range {
 };
 
 static unsigned long long _text;
+static unsigned long long relative_base;
 static struct addr_range text_ranges[] = {
 	{ "_stext",     "_etext"     },
 	{ "_sinittext", "_einittext" },
@@ -61,6 +64,7 @@ static int all_symbols = 0;
 static int absolute_percpu = 0;
 static char symbol_prefix_char = '\0';
 static unsigned long long kernel_start_addr = 0;
+static int base_relative = 0;
 
 int token_profit[0x10000];
 
@@ -74,7 +78,7 @@ static void usage(void)
 	fprintf(stderr, "Usage: kallsyms [--all-symbols] "
 			"[--symbol-prefix=<prefix char>] "
 			"[--page-offset=<CONFIG_PAGE_OFFSET>] "
-			"< in.map > out.S\n");
+			"[--base-relative] < in.map > out.S\n");
 	exit(1);
 }
 
@@ -171,6 +175,8 @@ static int read_symbol(FILE *in, struct sym_entry *s)
 	strcpy((char *)s->sym + 1, str);
 	s->sym[0] = stype;
 
+	s->percpu_absolute = 0;
+
 	/* Record if we've found __per_cpu_start/end. */
 	check_symbol_range(sym, s->addr, &percpu_range, 1);
 
@@ -202,6 +208,8 @@ static int symbol_valid(struct sym_entry *s)
 	 */
 	static char *special_symbols[] = {
 		"kallsyms_addresses",
+		"kallsyms_offsets",
+		"kallsyms_relative_base",
 		"kallsyms_num_syms",
 		"kallsyms_names",
 		"kallsyms_markers",
@@ -325,7 +333,7 @@ static int expand_symbol(unsigned char *data, int len, char *result)
 
 static int symbol_absolute(struct sym_entry *s)
 {
-	return toupper(s->sym[0]) == 'A';
+	return s->percpu_absolute;
 }
 
 static void write_src(void)
@@ -346,16 +354,48 @@ static void write_src(void)
 
 	printf("\t.section .rodata, \"a\"\n");
 
-	/* Provide proper symbols relocatability by their '_text'
-	 * relativeness.  The symbol names cannot be used to construct
-	 * normal symbol references as the list of symbols contains
-	 * symbols that are declared static and are private to their
-	 * .o files.  This prevents .tmp_kallsyms.o or any other
-	 * object from referencing them.
+	/* Provide proper symbols relocatability by their relativeness
+	 * to a fixed anchor point in the runtime image, either '_text'
+	 * for absolute address tables, in which case the linker will
+	 * emit the final addresses at build time. Otherwise, use the
+	 * offset relative to the lowest value encountered of all relative
+	 * symbols, and emit non-relocatable fixed offsets that will be fixed
+	 * up at runtime.
+	 *
+	 * The symbol names cannot be used to construct normal symbol
+	 * references as the list of symbols contains symbols that are
+	 * declared static and are private to their .o files.  This prevents
+	 * .tmp_kallsyms.o or any other object from referencing them.
 	 */
-	output_label("kallsyms_addresses");
+	if (!base_relative)
+		output_label("kallsyms_addresses");
+	else
+		output_label("kallsyms_offsets");
+
 	for (i = 0; i < table_cnt; i++) {
-		if (!symbol_absolute(&table[i])) {
+		if (base_relative) {
+			long long offset;
+			int overflow;
+
+			if (!absolute_percpu) {
+				offset = table[i].addr - relative_base;
+				overflow = (offset < 0 || offset > UINT_MAX);
+			} else if (symbol_absolute(&table[i])) {
+				offset = table[i].addr;
+				overflow = (offset < 0 || offset > INT_MAX);
+			} else {
+				offset = relative_base - table[i].addr - 1;
+				overflow = (offset < INT_MIN || offset >= 0);
+			}
+			if (overflow) {
+				fprintf(stderr, "kallsyms failure: "
+					"%s symbol value %#llx out of range in relative mode\n",
+					symbol_absolute(&table[i]) ? "absolute" : "relative",
+					table[i].addr);
+				exit(EXIT_FAILURE);
+			}
+			printf("\t.long\t%#x\n", (int)offset);
+		} else if (!symbol_absolute(&table[i])) {
 			if (_text <= table[i].addr)
 				printf("\tPTR\t_text + %#llx\n",
 					table[i].addr - _text);
@@ -368,6 +408,12 @@ static void write_src(void)
 	}
 	printf("\n");
 
+	if (base_relative) {
+		output_label("kallsyms_relative_base");
+		printf("\tPTR\t_text - %#llx\n", _text - relative_base);
+		printf("\n");
+	}
+
 	output_label("kallsyms_num_syms");
 	printf("\tPTR\t%d\n", table_cnt);
 	printf("\n");
@@ -681,8 +727,27 @@ static void make_percpus_absolute(void)
 	unsigned int i;
 
 	for (i = 0; i < table_cnt; i++)
-		if (symbol_in_range(&table[i], &percpu_range, 1))
+		if (symbol_in_range(&table[i], &percpu_range, 1)) {
+			/*
+			 * Keep the 'A' override for percpu symbols to
+			 * ensure consistent behavior compared to older
+			 * versions of this tool.
+			 */
 			table[i].sym[0] = 'A';
+			table[i].percpu_absolute = 1;
+		}
+}
+
+/* find the minimum non-absolute symbol address */
+static void record_relative_base(void)
+{
+	unsigned int i;
+
+	relative_base = -1ULL;
+	for (i = 0; i < table_cnt; i++)
+		if (!symbol_absolute(&table[i]) &&
+		    table[i].addr < relative_base)
+			relative_base = table[i].addr;
 }
 
 int main(int argc, char **argv)
@@ -703,7 +768,9 @@ int main(int argc, char **argv)
 			} else if (strncmp(argv[i], "--page-offset=", 14) == 0) {
 				const char *p = &argv[i][14];
 				kernel_start_addr = strtoull(p, NULL, 16);
-			} else
+			} else if (strcmp(argv[i], "--base-relative") == 0)
+				base_relative = 1;
+			else
 				usage();
 		}
 	} else if (argc != 1)
@@ -712,6 +779,8 @@ int main(int argc, char **argv)
 	read_map(stdin);
 	if (absolute_percpu)
 		make_percpus_absolute();
+	if (base_relative)
+		record_relative_base();
 	sort_symbols();
 	optimize_token_table();
 	write_src();
diff --git a/scripts/ld-version.sh b/scripts/ld-version.sh
index d154f0877fd8..7bfe9fa1c8dc 100755
--- a/scripts/ld-version.sh
+++ b/scripts/ld-version.sh
@@ -1,7 +1,7 @@
 #!/usr/bin/awk -f
 # extract linker version number from stdin and turn into single number
 	{
-	gsub(".*)", "");
+	gsub(".*\\)", "");
 	gsub(".*version ", "");
 	gsub("-.*", "");
 	split($1,a, ".");
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index ba6c34ea5429..453ede9d2f3d 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -86,10 +86,14 @@ kallsyms()
 		kallsymopt="${kallsymopt} --page-offset=$CONFIG_PAGE_OFFSET"
 	fi
 
-	if [ -n "${CONFIG_X86_64}" ]; then
+	if [ -n "${CONFIG_KALLSYMS_ABSOLUTE_PERCPU}" ]; then
 		kallsymopt="${kallsymopt} --absolute-percpu"
 	fi
 
+	if [ -n "${CONFIG_KALLSYMS_BASE_RELATIVE}" ]; then
+		kallsymopt="${kallsymopt} --base-relative"
+	fi
+
 	local aflags="${KBUILD_AFLAGS} ${KBUILD_AFLAGS_KERNEL}               \
 		      ${NOSTDINC_FLAGS} ${LINUXINCLUDE} ${KBUILD_CPPFLAGS}"
 
diff --git a/scripts/namespace.pl b/scripts/namespace.pl
index a71be6b7cdec..9f3c9d47a4a5 100755
--- a/scripts/namespace.pl
+++ b/scripts/namespace.pl
@@ -117,6 +117,8 @@ my %nameexception = (
     'kallsyms_names'	=> 1,
     'kallsyms_num_syms'	=> 1,
     'kallsyms_addresses'=> 1,
+    'kallsyms_offsets'	=> 1,
+    'kallsyms_relative_base'=> 1,
     '__this_module'	=> 1,
     '_etext'		=> 1,
     '_edata'		=> 1,
diff --git a/scripts/prune-kernel b/scripts/prune-kernel
new file mode 100755
index 000000000000..ab5034e1d081
--- /dev/null
+++ b/scripts/prune-kernel
@@ -0,0 +1,20 @@
+#!/bin/bash
+
+# because I use CONFIG_LOCALVERSION_AUTO, not the same version again and
+# again, /boot and /lib/modules/ eventually fill up.
+# Dumb script to purge that stuff:
+
+for f in "$@"
+do
+        if rpm -qf "/lib/modules/$f" >/dev/null; then
+                echo "keeping $f (installed from rpm)"
+        elif [ $(uname -r) = "$f" ]; then
+                echo "keeping $f (running kernel) "
+        else
+                echo "removing $f"
+                rm -f "/boot/initramfs-$f.img" "/boot/System.map-$f"
+                rm -f "/boot/vmlinuz-$f"   "/boot/config-$f"
+                rm -rf "/lib/modules/$f"
+                new-kernel-pkg --remove $f
+        fi
+done
diff --git a/scripts/sortextable.c b/scripts/sortextable.c
index c2423d913b46..7b29fb14f870 100644
--- a/scripts/sortextable.c
+++ b/scripts/sortextable.c
@@ -209,6 +209,35 @@ static int compare_relative_table(const void *a, const void *b)
 	return 0;
 }
 
+static void x86_sort_relative_table(char *extab_image, int image_size)
+{
+	int i;
+
+	i = 0;
+	while (i < image_size) {
+		uint32_t *loc = (uint32_t *)(extab_image + i);
+
+		w(r(loc) + i, loc);
+		w(r(loc + 1) + i + 4, loc + 1);
+		w(r(loc + 2) + i + 8, loc + 2);
+
+		i += sizeof(uint32_t) * 3;
+	}
+
+	qsort(extab_image, image_size / 12, 12, compare_relative_table);
+
+	i = 0;
+	while (i < image_size) {
+		uint32_t *loc = (uint32_t *)(extab_image + i);
+
+		w(r(loc) - i, loc);
+		w(r(loc + 1) - (i + 4), loc + 1);
+		w(r(loc + 2) - (i + 8), loc + 2);
+
+		i += sizeof(uint32_t) * 3;
+	}
+}
+
 static void sort_relative_table(char *extab_image, int image_size)
 {
 	int i;
@@ -281,6 +310,9 @@ do_file(char const *const fname)
 		break;
 	case EM_386:
 	case EM_X86_64:
+		custom_sort = x86_sort_relative_table;
+		break;
+
 	case EM_S390:
 		custom_sort = sort_relative_table;
 		break;
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index f7160253f17f..e6ea9d4b1de9 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -23,6 +23,7 @@
 #include <linux/integrity.h>
 #include <linux/evm.h>
 #include <crypto/hash.h>
+#include <crypto/algapi.h>
 #include "evm.h"
 
 int evm_initialized;
@@ -148,7 +149,7 @@ static enum integrity_status evm_verify_hmac(struct dentry *dentry,
 				   xattr_value_len, calc.digest);
 		if (rc)
 			break;
-		rc = memcmp(xattr_data->digest, calc.digest,
+		rc = crypto_memneq(xattr_data->digest, calc.digest,
 			    sizeof(calc.digest));
 		if (rc)
 			rc = -EINVAL;
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 696ccfa08d10..5adbfc32242f 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -28,11 +28,10 @@
 #include <linux/random.h>
 #include <linux/rcupdate.h>
 #include <linux/scatterlist.h>
-#include <linux/crypto.h>
 #include <linux/ctype.h>
 #include <crypto/hash.h>
 #include <crypto/sha.h>
-#include <crypto/aes.h>
+#include <crypto/skcipher.h>
 
 #include "encrypted.h"
 #include "ecryptfs_format.h"
@@ -85,17 +84,17 @@ static const match_table_t key_tokens = {
 
 static int aes_get_sizes(void)
 {
-	struct crypto_blkcipher *tfm;
+	struct crypto_skcipher *tfm;
 
-	tfm = crypto_alloc_blkcipher(blkcipher_alg, 0, CRYPTO_ALG_ASYNC);
+	tfm = crypto_alloc_skcipher(blkcipher_alg, 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm)) {
 		pr_err("encrypted_key: failed to alloc_cipher (%ld)\n",
 		       PTR_ERR(tfm));
 		return PTR_ERR(tfm);
 	}
-	ivsize = crypto_blkcipher_ivsize(tfm);
-	blksize = crypto_blkcipher_blocksize(tfm);
-	crypto_free_blkcipher(tfm);
+	ivsize = crypto_skcipher_ivsize(tfm);
+	blksize = crypto_skcipher_blocksize(tfm);
+	crypto_free_skcipher(tfm);
 	return 0;
 }
 
@@ -401,28 +400,37 @@ static int get_derived_key(u8 *derived_key, enum derived_key_type key_type,
 	return ret;
 }
 
-static int init_blkcipher_desc(struct blkcipher_desc *desc, const u8 *key,
-			       unsigned int key_len, const u8 *iv,
-			       unsigned int ivsize)
+static struct skcipher_request *init_skcipher_req(const u8 *key,
+						  unsigned int key_len)
 {
+	struct skcipher_request *req;
+	struct crypto_skcipher *tfm;
 	int ret;
 
-	desc->tfm = crypto_alloc_blkcipher(blkcipher_alg, 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(desc->tfm)) {
+	tfm = crypto_alloc_skcipher(blkcipher_alg, 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm)) {
 		pr_err("encrypted_key: failed to load %s transform (%ld)\n",
-		       blkcipher_alg, PTR_ERR(desc->tfm));
-		return PTR_ERR(desc->tfm);
+		       blkcipher_alg, PTR_ERR(tfm));
+		return ERR_CAST(tfm);
 	}
-	desc->flags = 0;
 
-	ret = crypto_blkcipher_setkey(desc->tfm, key, key_len);
+	ret = crypto_skcipher_setkey(tfm, key, key_len);
 	if (ret < 0) {
 		pr_err("encrypted_key: failed to setkey (%d)\n", ret);
-		crypto_free_blkcipher(desc->tfm);
-		return ret;
+		crypto_free_skcipher(tfm);
+		return ERR_PTR(ret);
 	}
-	crypto_blkcipher_set_iv(desc->tfm, iv, ivsize);
-	return 0;
+
+	req = skcipher_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		pr_err("encrypted_key: failed to allocate request for %s\n",
+		       blkcipher_alg);
+		crypto_free_skcipher(tfm);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	return req;
 }
 
 static struct key *request_master_key(struct encrypted_key_payload *epayload,
@@ -467,7 +475,8 @@ static int derived_key_encrypt(struct encrypted_key_payload *epayload,
 {
 	struct scatterlist sg_in[2];
 	struct scatterlist sg_out[1];
-	struct blkcipher_desc desc;
+	struct crypto_skcipher *tfm;
+	struct skcipher_request *req;
 	unsigned int encrypted_datalen;
 	unsigned int padlen;
 	char pad[16];
@@ -476,9 +485,9 @@ static int derived_key_encrypt(struct encrypted_key_payload *epayload,
 	encrypted_datalen = roundup(epayload->decrypted_datalen, blksize);
 	padlen = encrypted_datalen - epayload->decrypted_datalen;
 
-	ret = init_blkcipher_desc(&desc, derived_key, derived_keylen,
-				  epayload->iv, ivsize);
-	if (ret < 0)
+	req = init_skcipher_req(derived_key, derived_keylen);
+	ret = PTR_ERR(req);
+	if (IS_ERR(req))
 		goto out;
 	dump_decrypted_data(epayload);
 
@@ -491,8 +500,12 @@ static int derived_key_encrypt(struct encrypted_key_payload *epayload,
 	sg_init_table(sg_out, 1);
 	sg_set_buf(sg_out, epayload->encrypted_data, encrypted_datalen);
 
-	ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in, encrypted_datalen);
-	crypto_free_blkcipher(desc.tfm);
+	skcipher_request_set_crypt(req, sg_in, sg_out, encrypted_datalen,
+				   epayload->iv);
+	ret = crypto_skcipher_encrypt(req);
+	tfm = crypto_skcipher_reqtfm(req);
+	skcipher_request_free(req);
+	crypto_free_skcipher(tfm);
 	if (ret < 0)
 		pr_err("encrypted_key: failed to encrypt (%d)\n", ret);
 	else
@@ -565,15 +578,16 @@ static int derived_key_decrypt(struct encrypted_key_payload *epayload,
 {
 	struct scatterlist sg_in[1];
 	struct scatterlist sg_out[2];
-	struct blkcipher_desc desc;
+	struct crypto_skcipher *tfm;
+	struct skcipher_request *req;
 	unsigned int encrypted_datalen;
 	char pad[16];
 	int ret;
 
 	encrypted_datalen = roundup(epayload->decrypted_datalen, blksize);
-	ret = init_blkcipher_desc(&desc, derived_key, derived_keylen,
-				  epayload->iv, ivsize);
-	if (ret < 0)
+	req = init_skcipher_req(derived_key, derived_keylen);
+	ret = PTR_ERR(req);
+	if (IS_ERR(req))
 		goto out;
 	dump_encrypted_data(epayload, encrypted_datalen);
 
@@ -585,8 +599,12 @@ static int derived_key_decrypt(struct encrypted_key_payload *epayload,
 		   epayload->decrypted_datalen);
 	sg_set_buf(&sg_out[1], pad, sizeof pad);
 
-	ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, encrypted_datalen);
-	crypto_free_blkcipher(desc.tfm);
+	skcipher_request_set_crypt(req, sg_in, sg_out, encrypted_datalen,
+				   epayload->iv);
+	ret = crypto_skcipher_decrypt(req);
+	tfm = crypto_skcipher_reqtfm(req);
+	skcipher_request_free(req);
+	crypto_free_skcipher(tfm);
 	if (ret < 0)
 		goto out;
 	dump_decrypted_data(epayload);
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index f8110cfd80ff..f1ab71504e1d 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3249,7 +3249,7 @@ static int selinux_inode_listsecurity(struct inode *inode, char *buffer, size_t
 
 static void selinux_inode_getsecid(struct inode *inode, u32 *secid)
 {
-	struct inode_security_struct *isec = inode_security(inode);
+	struct inode_security_struct *isec = inode_security_novalidate(inode);
 	*secid = isec->sid;
 }
 
diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c
index 2bbb41822d8e..8495b9368190 100644
--- a/security/selinux/nlmsgtab.c
+++ b/security/selinux/nlmsgtab.c
@@ -83,6 +83,7 @@ static struct nlmsg_perm nlmsg_tcpdiag_perms[] =
 	{ TCPDIAG_GETSOCK,	NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
 	{ DCCPDIAG_GETSOCK,	NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
 	{ SOCK_DIAG_BY_FAMILY,	NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
+	{ SOCK_DESTROY,		NETLINK_TCPDIAG_SOCKET__NLMSG_WRITE },
 };
 
 static struct nlmsg_perm nlmsg_xfrm_perms[] =
diff --git a/sound/arm/pxa2xx-pcm-lib.c b/sound/arm/pxa2xx-pcm-lib.c
index e9b98af6b52c..e8da3b8ee721 100644
--- a/sound/arm/pxa2xx-pcm-lib.c
+++ b/sound/arm/pxa2xx-pcm-lib.c
@@ -141,10 +141,8 @@ int pxa2xx_pcm_mmap(struct snd_pcm_substream *substream,
 	struct vm_area_struct *vma)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	return dma_mmap_writecombine(substream->pcm->card->dev, vma,
-				     runtime->dma_area,
-				     runtime->dma_addr,
-				     runtime->dma_bytes);
+	return dma_mmap_wc(substream->pcm->card->dev, vma, runtime->dma_area,
+			   runtime->dma_addr, runtime->dma_bytes);
 }
 EXPORT_SYMBOL(pxa2xx_pcm_mmap);
 
@@ -156,8 +154,7 @@ int pxa2xx_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream)
 	buf->dev.type = SNDRV_DMA_TYPE_DEV;
 	buf->dev.dev = pcm->card->dev;
 	buf->private_data = NULL;
-	buf->area = dma_alloc_writecombine(pcm->card->dev, size,
-					   &buf->addr, GFP_KERNEL);
+	buf->area = dma_alloc_wc(pcm->card->dev, size, &buf->addr, GFP_KERNEL);
 	if (!buf->area)
 		return -ENOMEM;
 	buf->bytes = size;
@@ -178,8 +175,7 @@ void pxa2xx_pcm_free_dma_buffers(struct snd_pcm *pcm)
 		buf = &substream->dma_buffer;
 		if (!buf->area)
 			continue;
-		dma_free_writecombine(pcm->card->dev, buf->bytes,
-				      buf->area, buf->addr);
+		dma_free_wc(pcm->card->dev, buf->bytes, buf->area, buf->addr);
 		buf->area = NULL;
 	}
 }
diff --git a/sound/core/control_compat.c b/sound/core/control_compat.c
index b9c0910fb8c4..0608f216f359 100644
--- a/sound/core/control_compat.c
+++ b/sound/core/control_compat.c
@@ -170,6 +170,19 @@ struct snd_ctl_elem_value32 {
         unsigned char reserved[128];
 };
 
+#ifdef CONFIG_X86_X32
+/* x32 has a different alignment for 64bit values from ia32 */
+struct snd_ctl_elem_value_x32 {
+	struct snd_ctl_elem_id id;
+	unsigned int indirect;	/* bit-field causes misalignment */
+	union {
+		s32 integer[128];
+		unsigned char data[512];
+		s64 integer64[64];
+	} value;
+	unsigned char reserved[128];
+};
+#endif /* CONFIG_X86_X32 */
 
 /* get the value type and count of the control */
 static int get_ctl_type(struct snd_card *card, struct snd_ctl_elem_id *id,
@@ -219,9 +232,11 @@ static int get_elem_size(int type, int count)
 
 static int copy_ctl_value_from_user(struct snd_card *card,
 				    struct snd_ctl_elem_value *data,
-				    struct snd_ctl_elem_value32 __user *data32,
+				    void __user *userdata,
+				    void __user *valuep,
 				    int *typep, int *countp)
 {
+	struct snd_ctl_elem_value32 __user *data32 = userdata;
 	int i, type, size;
 	int uninitialized_var(count);
 	unsigned int indirect;
@@ -239,8 +254,9 @@ static int copy_ctl_value_from_user(struct snd_card *card,
 	if (type == SNDRV_CTL_ELEM_TYPE_BOOLEAN ||
 	    type == SNDRV_CTL_ELEM_TYPE_INTEGER) {
 		for (i = 0; i < count; i++) {
+			s32 __user *intp = valuep;
 			int val;
-			if (get_user(val, &data32->value.integer[i]))
+			if (get_user(val, &intp[i]))
 				return -EFAULT;
 			data->value.integer.value[i] = val;
 		}
@@ -250,8 +266,7 @@ static int copy_ctl_value_from_user(struct snd_card *card,
 			dev_err(card->dev, "snd_ioctl32_ctl_elem_value: unknown type %d\n", type);
 			return -EINVAL;
 		}
-		if (copy_from_user(data->value.bytes.data,
-				   data32->value.data, size))
+		if (copy_from_user(data->value.bytes.data, valuep, size))
 			return -EFAULT;
 	}
 
@@ -261,7 +276,8 @@ static int copy_ctl_value_from_user(struct snd_card *card,
 }
 
 /* restore the value to 32bit */
-static int copy_ctl_value_to_user(struct snd_ctl_elem_value32 __user *data32,
+static int copy_ctl_value_to_user(void __user *userdata,
+				  void __user *valuep,
 				  struct snd_ctl_elem_value *data,
 				  int type, int count)
 {
@@ -270,22 +286,22 @@ static int copy_ctl_value_to_user(struct snd_ctl_elem_value32 __user *data32,
 	if (type == SNDRV_CTL_ELEM_TYPE_BOOLEAN ||
 	    type == SNDRV_CTL_ELEM_TYPE_INTEGER) {
 		for (i = 0; i < count; i++) {
+			s32 __user *intp = valuep;
 			int val;
 			val = data->value.integer.value[i];
-			if (put_user(val, &data32->value.integer[i]))
+			if (put_user(val, &intp[i]))
 				return -EFAULT;
 		}
 	} else {
 		size = get_elem_size(type, count);
-		if (copy_to_user(data32->value.data,
-				 data->value.bytes.data, size))
+		if (copy_to_user(valuep, data->value.bytes.data, size))
 			return -EFAULT;
 	}
 	return 0;
 }
 
-static int snd_ctl_elem_read_user_compat(struct snd_card *card, 
-					 struct snd_ctl_elem_value32 __user *data32)
+static int ctl_elem_read_user(struct snd_card *card,
+			      void __user *userdata, void __user *valuep)
 {
 	struct snd_ctl_elem_value *data;
 	int err, type, count;
@@ -294,7 +310,9 @@ static int snd_ctl_elem_read_user_compat(struct snd_card *card,
 	if (data == NULL)
 		return -ENOMEM;
 
-	if ((err = copy_ctl_value_from_user(card, data, data32, &type, &count)) < 0)
+	err = copy_ctl_value_from_user(card, data, userdata, valuep,
+				       &type, &count);
+	if (err < 0)
 		goto error;
 
 	snd_power_lock(card);
@@ -303,14 +321,15 @@ static int snd_ctl_elem_read_user_compat(struct snd_card *card,
 		err = snd_ctl_elem_read(card, data);
 	snd_power_unlock(card);
 	if (err >= 0)
-		err = copy_ctl_value_to_user(data32, data, type, count);
+		err = copy_ctl_value_to_user(userdata, valuep, data,
+					     type, count);
  error:
 	kfree(data);
 	return err;
 }
 
-static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file,
-					  struct snd_ctl_elem_value32 __user *data32)
+static int ctl_elem_write_user(struct snd_ctl_file *file,
+			       void __user *userdata, void __user *valuep)
 {
 	struct snd_ctl_elem_value *data;
 	struct snd_card *card = file->card;
@@ -320,7 +339,9 @@ static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file,
 	if (data == NULL)
 		return -ENOMEM;
 
-	if ((err = copy_ctl_value_from_user(card, data, data32, &type, &count)) < 0)
+	err = copy_ctl_value_from_user(card, data, userdata, valuep,
+				       &type, &count);
+	if (err < 0)
 		goto error;
 
 	snd_power_lock(card);
@@ -329,12 +350,39 @@ static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file,
 		err = snd_ctl_elem_write(card, file, data);
 	snd_power_unlock(card);
 	if (err >= 0)
-		err = copy_ctl_value_to_user(data32, data, type, count);
+		err = copy_ctl_value_to_user(userdata, valuep, data,
+					     type, count);
  error:
 	kfree(data);
 	return err;
 }
 
+static int snd_ctl_elem_read_user_compat(struct snd_card *card,
+					 struct snd_ctl_elem_value32 __user *data32)
+{
+	return ctl_elem_read_user(card, data32, &data32->value);
+}
+
+static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file,
+					  struct snd_ctl_elem_value32 __user *data32)
+{
+	return ctl_elem_write_user(file, data32, &data32->value);
+}
+
+#ifdef CONFIG_X86_X32
+static int snd_ctl_elem_read_user_x32(struct snd_card *card,
+				      struct snd_ctl_elem_value_x32 __user *data32)
+{
+	return ctl_elem_read_user(card, data32, &data32->value);
+}
+
+static int snd_ctl_elem_write_user_x32(struct snd_ctl_file *file,
+				       struct snd_ctl_elem_value_x32 __user *data32)
+{
+	return ctl_elem_write_user(file, data32, &data32->value);
+}
+#endif /* CONFIG_X86_X32 */
+
 /* add or replace a user control */
 static int snd_ctl_elem_add_compat(struct snd_ctl_file *file,
 				   struct snd_ctl_elem_info32 __user *data32,
@@ -393,6 +441,10 @@ enum {
 	SNDRV_CTL_IOCTL_ELEM_WRITE32 = _IOWR('U', 0x13, struct snd_ctl_elem_value32),
 	SNDRV_CTL_IOCTL_ELEM_ADD32 = _IOWR('U', 0x17, struct snd_ctl_elem_info32),
 	SNDRV_CTL_IOCTL_ELEM_REPLACE32 = _IOWR('U', 0x18, struct snd_ctl_elem_info32),
+#ifdef CONFIG_X86_X32
+	SNDRV_CTL_IOCTL_ELEM_READ_X32 = _IOWR('U', 0x12, struct snd_ctl_elem_value_x32),
+	SNDRV_CTL_IOCTL_ELEM_WRITE_X32 = _IOWR('U', 0x13, struct snd_ctl_elem_value_x32),
+#endif /* CONFIG_X86_X32 */
 };
 
 static inline long snd_ctl_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg)
@@ -431,6 +483,12 @@ static inline long snd_ctl_ioctl_compat(struct file *file, unsigned int cmd, uns
 		return snd_ctl_elem_add_compat(ctl, argp, 0);
 	case SNDRV_CTL_IOCTL_ELEM_REPLACE32:
 		return snd_ctl_elem_add_compat(ctl, argp, 1);
+#ifdef CONFIG_X86_X32
+	case SNDRV_CTL_IOCTL_ELEM_READ_X32:
+		return snd_ctl_elem_read_user_x32(ctl->card, argp);
+	case SNDRV_CTL_IOCTL_ELEM_WRITE_X32:
+		return snd_ctl_elem_write_user_x32(ctl, argp);
+#endif /* CONFIG_X86_X32 */
 	}
 
 	down_read(&snd_ioctl_rwsem);
diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c
index 9630e9f72b7b..1f64ab0c2a95 100644
--- a/sound/core/pcm_compat.c
+++ b/sound/core/pcm_compat.c
@@ -183,6 +183,14 @@ static int snd_pcm_ioctl_channel_info_compat(struct snd_pcm_substream *substream
 	return err;
 }
 
+#ifdef CONFIG_X86_X32
+/* X32 ABI has the same struct as x86-64 for snd_pcm_channel_info */
+static int snd_pcm_channel_info_user(struct snd_pcm_substream *substream,
+				     struct snd_pcm_channel_info __user *src);
+#define snd_pcm_ioctl_channel_info_x32(s, p)	\
+	snd_pcm_channel_info_user(s, p)
+#endif /* CONFIG_X86_X32 */
+
 struct snd_pcm_status32 {
 	s32 state;
 	struct compat_timespec trigger_tstamp;
@@ -243,6 +251,71 @@ static int snd_pcm_status_user_compat(struct snd_pcm_substream *substream,
 	return err;
 }
 
+#ifdef CONFIG_X86_X32
+/* X32 ABI has 64bit timespec and 64bit alignment */
+struct snd_pcm_status_x32 {
+	s32 state;
+	u32 rsvd; /* alignment */
+	struct timespec trigger_tstamp;
+	struct timespec tstamp;
+	u32 appl_ptr;
+	u32 hw_ptr;
+	s32 delay;
+	u32 avail;
+	u32 avail_max;
+	u32 overrange;
+	s32 suspended_state;
+	u32 audio_tstamp_data;
+	struct timespec audio_tstamp;
+	struct timespec driver_tstamp;
+	u32 audio_tstamp_accuracy;
+	unsigned char reserved[52-2*sizeof(struct timespec)];
+} __packed;
+
+#define put_timespec(src, dst) copy_to_user(dst, src, sizeof(*dst))
+
+static int snd_pcm_status_user_x32(struct snd_pcm_substream *substream,
+				   struct snd_pcm_status_x32 __user *src,
+				   bool ext)
+{
+	struct snd_pcm_status status;
+	int err;
+
+	memset(&status, 0, sizeof(status));
+	/*
+	 * with extension, parameters are read/write,
+	 * get audio_tstamp_data from user,
+	 * ignore rest of status structure
+	 */
+	if (ext && get_user(status.audio_tstamp_data,
+				(u32 __user *)(&src->audio_tstamp_data)))
+		return -EFAULT;
+	err = snd_pcm_status(substream, &status);
+	if (err < 0)
+		return err;
+
+	if (clear_user(src, sizeof(*src)))
+		return -EFAULT;
+	if (put_user(status.state, &src->state) ||
+	    put_timespec(&status.trigger_tstamp, &src->trigger_tstamp) ||
+	    put_timespec(&status.tstamp, &src->tstamp) ||
+	    put_user(status.appl_ptr, &src->appl_ptr) ||
+	    put_user(status.hw_ptr, &src->hw_ptr) ||
+	    put_user(status.delay, &src->delay) ||
+	    put_user(status.avail, &src->avail) ||
+	    put_user(status.avail_max, &src->avail_max) ||
+	    put_user(status.overrange, &src->overrange) ||
+	    put_user(status.suspended_state, &src->suspended_state) ||
+	    put_user(status.audio_tstamp_data, &src->audio_tstamp_data) ||
+	    put_timespec(&status.audio_tstamp, &src->audio_tstamp) ||
+	    put_timespec(&status.driver_tstamp, &src->driver_tstamp) ||
+	    put_user(status.audio_tstamp_accuracy, &src->audio_tstamp_accuracy))
+		return -EFAULT;
+
+	return err;
+}
+#endif /* CONFIG_X86_X32 */
+
 /* both for HW_PARAMS and HW_REFINE */
 static int snd_pcm_ioctl_hw_params_compat(struct snd_pcm_substream *substream,
 					  int refine, 
@@ -469,6 +542,93 @@ static int snd_pcm_ioctl_sync_ptr_compat(struct snd_pcm_substream *substream,
 	return 0;
 }
 
+#ifdef CONFIG_X86_X32
+/* X32 ABI has 64bit timespec and 64bit alignment */
+struct snd_pcm_mmap_status_x32 {
+	s32 state;
+	s32 pad1;
+	u32 hw_ptr;
+	u32 pad2; /* alignment */
+	struct timespec tstamp;
+	s32 suspended_state;
+	struct timespec audio_tstamp;
+} __packed;
+
+struct snd_pcm_mmap_control_x32 {
+	u32 appl_ptr;
+	u32 avail_min;
+};
+
+struct snd_pcm_sync_ptr_x32 {
+	u32 flags;
+	u32 rsvd; /* alignment */
+	union {
+		struct snd_pcm_mmap_status_x32 status;
+		unsigned char reserved[64];
+	} s;
+	union {
+		struct snd_pcm_mmap_control_x32 control;
+		unsigned char reserved[64];
+	} c;
+} __packed;
+
+static int snd_pcm_ioctl_sync_ptr_x32(struct snd_pcm_substream *substream,
+				      struct snd_pcm_sync_ptr_x32 __user *src)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	volatile struct snd_pcm_mmap_status *status;
+	volatile struct snd_pcm_mmap_control *control;
+	u32 sflags;
+	struct snd_pcm_mmap_control scontrol;
+	struct snd_pcm_mmap_status sstatus;
+	snd_pcm_uframes_t boundary;
+	int err;
+
+	if (snd_BUG_ON(!runtime))
+		return -EINVAL;
+
+	if (get_user(sflags, &src->flags) ||
+	    get_user(scontrol.appl_ptr, &src->c.control.appl_ptr) ||
+	    get_user(scontrol.avail_min, &src->c.control.avail_min))
+		return -EFAULT;
+	if (sflags & SNDRV_PCM_SYNC_PTR_HWSYNC) {
+		err = snd_pcm_hwsync(substream);
+		if (err < 0)
+			return err;
+	}
+	status = runtime->status;
+	control = runtime->control;
+	boundary = recalculate_boundary(runtime);
+	if (!boundary)
+		boundary = 0x7fffffff;
+	snd_pcm_stream_lock_irq(substream);
+	/* FIXME: we should consider the boundary for the sync from app */
+	if (!(sflags & SNDRV_PCM_SYNC_PTR_APPL))
+		control->appl_ptr = scontrol.appl_ptr;
+	else
+		scontrol.appl_ptr = control->appl_ptr % boundary;
+	if (!(sflags & SNDRV_PCM_SYNC_PTR_AVAIL_MIN))
+		control->avail_min = scontrol.avail_min;
+	else
+		scontrol.avail_min = control->avail_min;
+	sstatus.state = status->state;
+	sstatus.hw_ptr = status->hw_ptr % boundary;
+	sstatus.tstamp = status->tstamp;
+	sstatus.suspended_state = status->suspended_state;
+	sstatus.audio_tstamp = status->audio_tstamp;
+	snd_pcm_stream_unlock_irq(substream);
+	if (put_user(sstatus.state, &src->s.status.state) ||
+	    put_user(sstatus.hw_ptr, &src->s.status.hw_ptr) ||
+	    put_timespec(&sstatus.tstamp, &src->s.status.tstamp) ||
+	    put_user(sstatus.suspended_state, &src->s.status.suspended_state) ||
+	    put_timespec(&sstatus.audio_tstamp, &src->s.status.audio_tstamp) ||
+	    put_user(scontrol.appl_ptr, &src->c.control.appl_ptr) ||
+	    put_user(scontrol.avail_min, &src->c.control.avail_min))
+		return -EFAULT;
+
+	return 0;
+}
+#endif /* CONFIG_X86_X32 */
 
 /*
  */
@@ -487,7 +647,12 @@ enum {
 	SNDRV_PCM_IOCTL_WRITEN_FRAMES32 = _IOW('A', 0x52, struct snd_xfern32),
 	SNDRV_PCM_IOCTL_READN_FRAMES32 = _IOR('A', 0x53, struct snd_xfern32),
 	SNDRV_PCM_IOCTL_SYNC_PTR32 = _IOWR('A', 0x23, struct snd_pcm_sync_ptr32),
-
+#ifdef CONFIG_X86_X32
+	SNDRV_PCM_IOCTL_CHANNEL_INFO_X32 = _IOR('A', 0x32, struct snd_pcm_channel_info),
+	SNDRV_PCM_IOCTL_STATUS_X32 = _IOR('A', 0x20, struct snd_pcm_status_x32),
+	SNDRV_PCM_IOCTL_STATUS_EXT_X32 = _IOWR('A', 0x24, struct snd_pcm_status_x32),
+	SNDRV_PCM_IOCTL_SYNC_PTR_X32 = _IOWR('A', 0x23, struct snd_pcm_sync_ptr_x32),
+#endif /* CONFIG_X86_X32 */
 };
 
 static long snd_pcm_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg)
@@ -559,6 +724,16 @@ static long snd_pcm_ioctl_compat(struct file *file, unsigned int cmd, unsigned l
 		return snd_pcm_ioctl_rewind_compat(substream, argp);
 	case SNDRV_PCM_IOCTL_FORWARD32:
 		return snd_pcm_ioctl_forward_compat(substream, argp);
+#ifdef CONFIG_X86_X32
+	case SNDRV_PCM_IOCTL_STATUS_X32:
+		return snd_pcm_status_user_x32(substream, argp, false);
+	case SNDRV_PCM_IOCTL_STATUS_EXT_X32:
+		return snd_pcm_status_user_x32(substream, argp, true);
+	case SNDRV_PCM_IOCTL_SYNC_PTR_X32:
+		return snd_pcm_ioctl_sync_ptr_x32(substream, argp);
+	case SNDRV_PCM_IOCTL_CHANNEL_INFO_X32:
+		return snd_pcm_ioctl_channel_info_x32(substream, argp);
+#endif /* CONFIG_X86_X32 */
 	}
 
 	return -ENOIOCTLCMD;
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index fadd3eb8e8bb..9106d8e2300e 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -74,6 +74,18 @@ static int snd_pcm_open(struct file *file, struct snd_pcm *pcm, int stream);
 static DEFINE_RWLOCK(snd_pcm_link_rwlock);
 static DECLARE_RWSEM(snd_pcm_link_rwsem);
 
+/* Writer in rwsem may block readers even during its waiting in queue,
+ * and this may lead to a deadlock when the code path takes read sem
+ * twice (e.g. one in snd_pcm_action_nonatomic() and another in
+ * snd_pcm_stream_lock()).  As a (suboptimal) workaround, let writer to
+ * spin until it gets the lock.
+ */
+static inline void down_write_nonblock(struct rw_semaphore *lock)
+{
+	while (!down_write_trylock(lock))
+		cond_resched();
+}
+
 /**
  * snd_pcm_stream_lock - Lock the PCM stream
  * @substream: PCM substream
@@ -1813,7 +1825,7 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd)
 		res = -ENOMEM;
 		goto _nolock;
 	}
-	down_write(&snd_pcm_link_rwsem);
+	down_write_nonblock(&snd_pcm_link_rwsem);
 	write_lock_irq(&snd_pcm_link_rwlock);
 	if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN ||
 	    substream->runtime->status->state != substream1->runtime->status->state ||
@@ -1860,7 +1872,7 @@ static int snd_pcm_unlink(struct snd_pcm_substream *substream)
 	struct snd_pcm_substream *s;
 	int res = 0;
 
-	down_write(&snd_pcm_link_rwsem);
+	down_write_nonblock(&snd_pcm_link_rwsem);
 	write_lock_irq(&snd_pcm_link_rwlock);
 	if (!snd_pcm_stream_linked(substream)) {
 		res = -EALREADY;
diff --git a/sound/core/rawmidi_compat.c b/sound/core/rawmidi_compat.c
index 5268c1f58c25..f69764d7cdd7 100644
--- a/sound/core/rawmidi_compat.c
+++ b/sound/core/rawmidi_compat.c
@@ -85,8 +85,7 @@ static int snd_rawmidi_ioctl_status_compat(struct snd_rawmidi_file *rfile,
 	if (err < 0)
 		return err;
 
-	if (put_user(status.tstamp.tv_sec, &src->tstamp.tv_sec) ||
-	    put_user(status.tstamp.tv_nsec, &src->tstamp.tv_nsec) ||
+	if (compat_put_timespec(&status.tstamp, &src->tstamp) ||
 	    put_user(status.avail, &src->avail) ||
 	    put_user(status.xruns, &src->xruns))
 		return -EFAULT;
@@ -94,9 +93,58 @@ static int snd_rawmidi_ioctl_status_compat(struct snd_rawmidi_file *rfile,
 	return 0;
 }
 
+#ifdef CONFIG_X86_X32
+/* X32 ABI has 64bit timespec and 64bit alignment */
+struct snd_rawmidi_status_x32 {
+	s32 stream;
+	u32 rsvd; /* alignment */
+	struct timespec tstamp;
+	u32 avail;
+	u32 xruns;
+	unsigned char reserved[16];
+} __attribute__((packed));
+
+#define put_timespec(src, dst) copy_to_user(dst, src, sizeof(*dst))
+
+static int snd_rawmidi_ioctl_status_x32(struct snd_rawmidi_file *rfile,
+					struct snd_rawmidi_status_x32 __user *src)
+{
+	int err;
+	struct snd_rawmidi_status status;
+
+	if (rfile->output == NULL)
+		return -EINVAL;
+	if (get_user(status.stream, &src->stream))
+		return -EFAULT;
+
+	switch (status.stream) {
+	case SNDRV_RAWMIDI_STREAM_OUTPUT:
+		err = snd_rawmidi_output_status(rfile->output, &status);
+		break;
+	case SNDRV_RAWMIDI_STREAM_INPUT:
+		err = snd_rawmidi_input_status(rfile->input, &status);
+		break;
+	default:
+		return -EINVAL;
+	}
+	if (err < 0)
+		return err;
+
+	if (put_timespec(&status.tstamp, &src->tstamp) ||
+	    put_user(status.avail, &src->avail) ||
+	    put_user(status.xruns, &src->xruns))
+		return -EFAULT;
+
+	return 0;
+}
+#endif /* CONFIG_X86_X32 */
+
 enum {
 	SNDRV_RAWMIDI_IOCTL_PARAMS32 = _IOWR('W', 0x10, struct snd_rawmidi_params32),
 	SNDRV_RAWMIDI_IOCTL_STATUS32 = _IOWR('W', 0x20, struct snd_rawmidi_status32),
+#ifdef CONFIG_X86_X32
+	SNDRV_RAWMIDI_IOCTL_STATUS_X32 = _IOWR('W', 0x20, struct snd_rawmidi_status_x32),
+#endif /* CONFIG_X86_X32 */
 };
 
 static long snd_rawmidi_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg)
@@ -115,6 +163,10 @@ static long snd_rawmidi_ioctl_compat(struct file *file, unsigned int cmd, unsign
 		return snd_rawmidi_ioctl_params_compat(rfile, argp);
 	case SNDRV_RAWMIDI_IOCTL_STATUS32:
 		return snd_rawmidi_ioctl_status_compat(rfile, argp);
+#ifdef CONFIG_X86_X32
+	case SNDRV_RAWMIDI_IOCTL_STATUS_X32:
+		return snd_rawmidi_ioctl_status_x32(rfile, argp);
+#endif /* CONFIG_X86_X32 */
 	}
 	return -ENOIOCTLCMD;
 }
diff --git a/sound/core/seq/oss/seq_oss.c b/sound/core/seq/oss/seq_oss.c
index 8db156b207f1..8cdf489df80e 100644
--- a/sound/core/seq/oss/seq_oss.c
+++ b/sound/core/seq/oss/seq_oss.c
@@ -149,8 +149,6 @@ odev_release(struct inode *inode, struct file *file)
 	if ((dp = file->private_data) == NULL)
 		return 0;
 
-	snd_seq_oss_drain_write(dp);
-
 	mutex_lock(&register_mutex);
 	snd_seq_oss_release(dp);
 	mutex_unlock(&register_mutex);
diff --git a/sound/core/seq/oss/seq_oss_device.h b/sound/core/seq/oss/seq_oss_device.h
index b43924325249..d7b4d016b547 100644
--- a/sound/core/seq/oss/seq_oss_device.h
+++ b/sound/core/seq/oss/seq_oss_device.h
@@ -127,7 +127,6 @@ int snd_seq_oss_write(struct seq_oss_devinfo *dp, const char __user *buf, int co
 unsigned int snd_seq_oss_poll(struct seq_oss_devinfo *dp, struct file *file, poll_table * wait);
 
 void snd_seq_oss_reset(struct seq_oss_devinfo *dp);
-void snd_seq_oss_drain_write(struct seq_oss_devinfo *dp);
 
 /* */
 void snd_seq_oss_process_queue(struct seq_oss_devinfo *dp, abstime_t time);
diff --git a/sound/core/seq/oss/seq_oss_init.c b/sound/core/seq/oss/seq_oss_init.c
index 6779e82b46dd..92c96a95a903 100644
--- a/sound/core/seq/oss/seq_oss_init.c
+++ b/sound/core/seq/oss/seq_oss_init.c
@@ -436,22 +436,6 @@ snd_seq_oss_release(struct seq_oss_devinfo *dp)
 
 
 /*
- * Wait until the queue is empty (if we don't have nonblock)
- */
-void
-snd_seq_oss_drain_write(struct seq_oss_devinfo *dp)
-{
-	if (! dp->timer->running)
-		return;
-	if (is_write_mode(dp->file_mode) && !is_nonblock_mode(dp->file_mode) &&
-	    dp->writeq) {
-		while (snd_seq_oss_writeq_sync(dp->writeq))
-			;
-	}
-}
-
-
-/*
  * reset sequencer devices
  */
 void
diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c
index 801076687bb1..c850345c43b5 100644
--- a/sound/core/seq/seq_memory.c
+++ b/sound/core/seq/seq_memory.c
@@ -383,15 +383,20 @@ int snd_seq_pool_init(struct snd_seq_pool *pool)
 
 	if (snd_BUG_ON(!pool))
 		return -EINVAL;
-	if (pool->ptr)			/* should be atomic? */
-		return 0;
 
-	pool->ptr = vmalloc(sizeof(struct snd_seq_event_cell) * pool->size);
-	if (!pool->ptr)
+	cellptr = vmalloc(sizeof(struct snd_seq_event_cell) * pool->size);
+	if (!cellptr)
 		return -ENOMEM;
 
 	/* add new cells to the free cell list */
 	spin_lock_irqsave(&pool->lock, flags);
+	if (pool->ptr) {
+		spin_unlock_irqrestore(&pool->lock, flags);
+		vfree(cellptr);
+		return 0;
+	}
+
+	pool->ptr = cellptr;
 	pool->free = NULL;
 
 	for (cell = 0; cell < pool->size; cell++) {
diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c
index 921fb2bd8fad..fe686ee41c6d 100644
--- a/sound/core/seq/seq_ports.c
+++ b/sound/core/seq/seq_ports.c
@@ -535,19 +535,22 @@ static void delete_and_unsubscribe_port(struct snd_seq_client *client,
 					bool is_src, bool ack)
 {
 	struct snd_seq_port_subs_info *grp;
+	struct list_head *list;
+	bool empty;
 
 	grp = is_src ? &port->c_src : &port->c_dest;
+	list = is_src ? &subs->src_list : &subs->dest_list;
 	down_write(&grp->list_mutex);
 	write_lock_irq(&grp->list_lock);
-	if (is_src)
-		list_del(&subs->src_list);
-	else
-		list_del(&subs->dest_list);
+	empty = list_empty(list);
+	if (!empty)
+		list_del_init(list);
 	grp->exclusive = 0;
 	write_unlock_irq(&grp->list_lock);
 	up_write(&grp->list_mutex);
 
-	unsubscribe_port(client, port, grp, &subs->info, ack);
+	if (!empty)
+		unsubscribe_port(client, port, grp, &subs->info, ack);
 }
 
 /* connect two ports */
diff --git a/sound/core/timer.c b/sound/core/timer.c
index 9b513a05765a..dca817fc7894 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -422,7 +422,7 @@ static void snd_timer_notify1(struct snd_timer_instance *ti, int event)
 	spin_lock_irqsave(&timer->lock, flags);
 	list_for_each_entry(ts, &ti->slave_active_head, active_list)
 		if (ts->ccallback)
-			ts->ccallback(ti, event + 100, &tstamp, resolution);
+			ts->ccallback(ts, event + 100, &tstamp, resolution);
 	spin_unlock_irqrestore(&timer->lock, flags);
 }
 
@@ -518,9 +518,13 @@ static int _snd_timer_stop(struct snd_timer_instance *timeri, int event)
 			spin_unlock_irqrestore(&slave_active_lock, flags);
 			return -EBUSY;
 		}
+		if (timeri->timer)
+			spin_lock(&timeri->timer->lock);
 		timeri->flags &= ~SNDRV_TIMER_IFLG_RUNNING;
 		list_del_init(&timeri->ack_list);
 		list_del_init(&timeri->active_list);
+		if (timeri->timer)
+			spin_unlock(&timeri->timer->lock);
 		spin_unlock_irqrestore(&slave_active_lock, flags);
 		goto __end;
 	}
@@ -1929,6 +1933,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 {
 	struct snd_timer_user *tu;
 	long result = 0, unit;
+	int qhead;
 	int err = 0;
 
 	tu = file->private_data;
@@ -1940,7 +1945,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 
 			if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) {
 				err = -EAGAIN;
-				break;
+				goto _error;
 			}
 
 			set_current_state(TASK_INTERRUPTIBLE);
@@ -1955,42 +1960,37 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer,
 
 			if (tu->disconnected) {
 				err = -ENODEV;
-				break;
+				goto _error;
 			}
 			if (signal_pending(current)) {
 				err = -ERESTARTSYS;
-				break;
+				goto _error;
 			}
 		}
 
+		qhead = tu->qhead++;
+		tu->qhead %= tu->queue_size;
 		spin_unlock_irq(&tu->qlock);
-		if (err < 0)
-			goto _error;
 
 		if (tu->tread) {
-			if (copy_to_user(buffer, &tu->tqueue[tu->qhead++],
-					 sizeof(struct snd_timer_tread))) {
+			if (copy_to_user(buffer, &tu->tqueue[qhead],
+					 sizeof(struct snd_timer_tread)))
 				err = -EFAULT;
-				goto _error;
-			}
 		} else {
-			if (copy_to_user(buffer, &tu->queue[tu->qhead++],
-					 sizeof(struct snd_timer_read))) {
+			if (copy_to_user(buffer, &tu->queue[qhead],
+					 sizeof(struct snd_timer_read)))
 				err = -EFAULT;
-				goto _error;
-			}
 		}
 
-		tu->qhead %= tu->queue_size;
-
-		result += unit;
-		buffer += unit;
-
 		spin_lock_irq(&tu->qlock);
 		tu->qused--;
+		if (err < 0)
+			goto _error;
+		result += unit;
+		buffer += unit;
 	}
-	spin_unlock_irq(&tu->qlock);
  _error:
+	spin_unlock_irq(&tu->qlock);
 	return result > 0 ? result : err;
 }
 
diff --git a/sound/core/timer_compat.c b/sound/core/timer_compat.c
index e05802ae6e1b..2e908225d754 100644
--- a/sound/core/timer_compat.c
+++ b/sound/core/timer_compat.c
@@ -70,13 +70,14 @@ static int snd_timer_user_status_compat(struct file *file,
 					struct snd_timer_status32 __user *_status)
 {
 	struct snd_timer_user *tu;
-	struct snd_timer_status status;
+	struct snd_timer_status32 status;
 	
 	tu = file->private_data;
 	if (snd_BUG_ON(!tu->timeri))
 		return -ENXIO;
 	memset(&status, 0, sizeof(status));
-	status.tstamp = tu->tstamp;
+	status.tstamp.tv_sec = tu->tstamp.tv_sec;
+	status.tstamp.tv_nsec = tu->tstamp.tv_nsec;
 	status.resolution = snd_timer_resolution(tu->timeri);
 	status.lost = tu->timeri->lost;
 	status.overrun = tu->overrun;
@@ -88,12 +89,21 @@ static int snd_timer_user_status_compat(struct file *file,
 	return 0;
 }
 
+#ifdef CONFIG_X86_X32
+/* X32 ABI has the same struct as x86-64 */
+#define snd_timer_user_status_x32(file, s) \
+	snd_timer_user_status(file, s)
+#endif /* CONFIG_X86_X32 */
+
 /*
  */
 
 enum {
 	SNDRV_TIMER_IOCTL_INFO32 = _IOR('T', 0x11, struct snd_timer_info32),
 	SNDRV_TIMER_IOCTL_STATUS32 = _IOW('T', 0x14, struct snd_timer_status32),
+#ifdef CONFIG_X86_X32
+	SNDRV_TIMER_IOCTL_STATUS_X32 = _IOW('T', 0x14, struct snd_timer_status),
+#endif /* CONFIG_X86_X32 */
 };
 
 static long snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg)
@@ -122,6 +132,10 @@ static long snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd, uns
 		return snd_timer_user_info_compat(file, argp);
 	case SNDRV_TIMER_IOCTL_STATUS32:
 		return snd_timer_user_status_compat(file, argp);
+#ifdef CONFIG_X86_X32
+	case SNDRV_TIMER_IOCTL_STATUS_X32:
+		return snd_timer_user_status_x32(file, argp);
+#endif /* CONFIG_X86_X32 */
 	}
 	return -ENOIOCTLCMD;
 }
diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c
index bde33308f0d6..c0f8f613f1f1 100644
--- a/sound/drivers/dummy.c
+++ b/sound/drivers/dummy.c
@@ -87,7 +87,7 @@ MODULE_PARM_DESC(pcm_substreams, "PCM substreams # (1-128) for dummy driver.");
 module_param(fake_buffer, bool, 0444);
 MODULE_PARM_DESC(fake_buffer, "Fake buffer allocations.");
 #ifdef CONFIG_HIGH_RES_TIMERS
-module_param(hrtimer, bool, 0444);
+module_param(hrtimer, bool, 0644);
 MODULE_PARM_DESC(hrtimer, "Use hrtimer as the timer source.");
 #endif
 
@@ -109,6 +109,9 @@ struct dummy_timer_ops {
 	snd_pcm_uframes_t (*pointer)(struct snd_pcm_substream *);
 };
 
+#define get_dummy_ops(substream) \
+	(*(const struct dummy_timer_ops **)(substream)->runtime->private_data)
+
 struct dummy_model {
 	const char *name;
 	int (*playback_constraints)(struct snd_pcm_runtime *runtime);
@@ -137,7 +140,6 @@ struct snd_dummy {
 	int iobox;
 	struct snd_kcontrol *cd_volume_ctl;
 	struct snd_kcontrol *cd_switch_ctl;
-	const struct dummy_timer_ops *timer_ops;
 };
 
 /*
@@ -231,6 +233,8 @@ static struct dummy_model *dummy_models[] = {
  */
 
 struct dummy_systimer_pcm {
+	/* ops must be the first item */
+	const struct dummy_timer_ops *timer_ops;
 	spinlock_t lock;
 	struct timer_list timer;
 	unsigned long base_time;
@@ -366,6 +370,8 @@ static const struct dummy_timer_ops dummy_systimer_ops = {
  */
 
 struct dummy_hrtimer_pcm {
+	/* ops must be the first item */
+	const struct dummy_timer_ops *timer_ops;
 	ktime_t base_time;
 	ktime_t period_time;
 	atomic_t running;
@@ -492,31 +498,25 @@ static const struct dummy_timer_ops dummy_hrtimer_ops = {
 
 static int dummy_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 {
-	struct snd_dummy *dummy = snd_pcm_substream_chip(substream);
-
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_RESUME:
-		return dummy->timer_ops->start(substream);
+		return get_dummy_ops(substream)->start(substream);
 	case SNDRV_PCM_TRIGGER_STOP:
 	case SNDRV_PCM_TRIGGER_SUSPEND:
-		return dummy->timer_ops->stop(substream);
+		return get_dummy_ops(substream)->stop(substream);
 	}
 	return -EINVAL;
 }
 
 static int dummy_pcm_prepare(struct snd_pcm_substream *substream)
 {
-	struct snd_dummy *dummy = snd_pcm_substream_chip(substream);
-
-	return dummy->timer_ops->prepare(substream);
+	return get_dummy_ops(substream)->prepare(substream);
 }
 
 static snd_pcm_uframes_t dummy_pcm_pointer(struct snd_pcm_substream *substream)
 {
-	struct snd_dummy *dummy = snd_pcm_substream_chip(substream);
-
-	return dummy->timer_ops->pointer(substream);
+	return get_dummy_ops(substream)->pointer(substream);
 }
 
 static struct snd_pcm_hardware dummy_pcm_hardware = {
@@ -562,17 +562,19 @@ static int dummy_pcm_open(struct snd_pcm_substream *substream)
 	struct snd_dummy *dummy = snd_pcm_substream_chip(substream);
 	struct dummy_model *model = dummy->model;
 	struct snd_pcm_runtime *runtime = substream->runtime;
+	const struct dummy_timer_ops *ops;
 	int err;
 
-	dummy->timer_ops = &dummy_systimer_ops;
+	ops = &dummy_systimer_ops;
 #ifdef CONFIG_HIGH_RES_TIMERS
 	if (hrtimer)
-		dummy->timer_ops = &dummy_hrtimer_ops;
+		ops = &dummy_hrtimer_ops;
 #endif
 
-	err = dummy->timer_ops->create(substream);
+	err = ops->create(substream);
 	if (err < 0)
 		return err;
+	get_dummy_ops(substream) = ops;
 
 	runtime->hw = dummy->pcm_hw;
 	if (substream->pcm->device & 1) {
@@ -594,7 +596,7 @@ static int dummy_pcm_open(struct snd_pcm_substream *substream)
 			err = model->capture_constraints(substream->runtime);
 	}
 	if (err < 0) {
-		dummy->timer_ops->free(substream);
+		get_dummy_ops(substream)->free(substream);
 		return err;
 	}
 	return 0;
@@ -602,8 +604,7 @@ static int dummy_pcm_open(struct snd_pcm_substream *substream)
 
 static int dummy_pcm_close(struct snd_pcm_substream *substream)
 {
-	struct snd_dummy *dummy = snd_pcm_substream_chip(substream);
-	dummy->timer_ops->free(substream);
+	get_dummy_ops(substream)->free(substream);
 	return 0;
 }
 
diff --git a/sound/firewire/digi00x/amdtp-dot.c b/sound/firewire/digi00x/amdtp-dot.c
index b02a5e8cad44..0ac92aba5bc1 100644
--- a/sound/firewire/digi00x/amdtp-dot.c
+++ b/sound/firewire/digi00x/amdtp-dot.c
@@ -63,7 +63,7 @@ struct amdtp_dot {
 #define BYTE_PER_SAMPLE (4)
 #define MAGIC_DOT_BYTE (2)
 #define MAGIC_BYTE_OFF(x) (((x) * BYTE_PER_SAMPLE) + MAGIC_DOT_BYTE)
-static const u8 dot_scrt(const u8 idx, const unsigned int off)
+static u8 dot_scrt(const u8 idx, const unsigned int off)
 {
 	/*
 	 * the length of the added pattern only depends on the lower nibble
diff --git a/sound/firewire/tascam/tascam-transaction.c b/sound/firewire/tascam/tascam-transaction.c
index 904ce0329fa1..040a96d1ba8e 100644
--- a/sound/firewire/tascam/tascam-transaction.c
+++ b/sound/firewire/tascam/tascam-transaction.c
@@ -230,6 +230,7 @@ int snd_tscm_transaction_register(struct snd_tscm *tscm)
 	return err;
 error:
 	fw_core_remove_address_handler(&tscm->async_handler);
+	tscm->async_handler.callback_data = NULL;
 	return err;
 }
 
@@ -276,6 +277,9 @@ void snd_tscm_transaction_unregister(struct snd_tscm *tscm)
 	__be32 reg;
 	unsigned int i;
 
+	if (tscm->async_handler.callback_data == NULL)
+		return;
+
 	/* Turn off FireWire LED. */
 	reg = cpu_to_be32(0x0000008e);
 	snd_fw_transaction(tscm->unit, TCODE_WRITE_QUADLET_REQUEST,
@@ -297,6 +301,8 @@ void snd_tscm_transaction_unregister(struct snd_tscm *tscm)
 			   &reg, sizeof(reg), 0);
 
 	fw_core_remove_address_handler(&tscm->async_handler);
+	tscm->async_handler.callback_data = NULL;
+
 	for (i = 0; i < TSCM_MIDI_OUT_PORT_MAX; i++)
 		snd_fw_async_midi_port_destroy(&tscm->out_ports[i]);
 }
diff --git a/sound/firewire/tascam/tascam.c b/sound/firewire/tascam/tascam.c
index ee0bc1839508..e281c338e562 100644
--- a/sound/firewire/tascam/tascam.c
+++ b/sound/firewire/tascam/tascam.c
@@ -21,7 +21,6 @@ static struct snd_tscm_spec model_specs[] = {
 		.pcm_playback_analog_channels = 8,
 		.midi_capture_ports = 4,
 		.midi_playback_ports = 4,
-		.is_controller = true,
 	},
 	{
 		.name = "FW-1082",
@@ -31,9 +30,16 @@ static struct snd_tscm_spec model_specs[] = {
 		.pcm_playback_analog_channels = 2,
 		.midi_capture_ports = 2,
 		.midi_playback_ports = 2,
-		.is_controller = true,
 	},
-	/* FW-1804 may be supported. */
+	{
+		.name = "FW-1804",
+		.has_adat = true,
+		.has_spdif = true,
+		.pcm_capture_analog_channels = 8,
+		.pcm_playback_analog_channels = 2,
+		.midi_capture_ports = 2,
+		.midi_playback_ports = 4,
+	},
 };
 
 static int identify_model(struct snd_tscm *tscm)
diff --git a/sound/firewire/tascam/tascam.h b/sound/firewire/tascam/tascam.h
index 2d028d2bd3bd..30ab77e924f7 100644
--- a/sound/firewire/tascam/tascam.h
+++ b/sound/firewire/tascam/tascam.h
@@ -39,7 +39,6 @@ struct snd_tscm_spec {
 	unsigned int pcm_playback_analog_channels;
 	unsigned int midi_capture_ports;
 	unsigned int midi_playback_ports;
-	bool is_controller;
 };
 
 #define TSCM_MIDI_IN_PORT_MAX	4
@@ -72,9 +71,6 @@ struct snd_tscm {
 	struct snd_fw_async_midi_port out_ports[TSCM_MIDI_OUT_PORT_MAX];
 	u8 running_status[TSCM_MIDI_OUT_PORT_MAX];
 	bool on_sysex[TSCM_MIDI_OUT_PORT_MAX];
-
-	/* For control messages. */
-	struct snd_firewire_tascam_status *status;
 };
 
 #define TSCM_ADDR_BASE			0xffff00000000ull
diff --git a/sound/hda/hdac_controller.c b/sound/hda/hdac_controller.c
index b5a17cb510a0..8c486235c905 100644
--- a/sound/hda/hdac_controller.c
+++ b/sound/hda/hdac_controller.c
@@ -426,18 +426,22 @@ EXPORT_SYMBOL_GPL(snd_hdac_bus_stop_chip);
  * @bus: HD-audio core bus
  * @status: INTSTS register value
  * @ask: callback to be called for woken streams
+ *
+ * Returns the bits of handled streams, or zero if no stream is handled.
  */
-void snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status,
+int snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status,
 				    void (*ack)(struct hdac_bus *,
 						struct hdac_stream *))
 {
 	struct hdac_stream *azx_dev;
 	u8 sd_status;
+	int handled = 0;
 
 	list_for_each_entry(azx_dev, &bus->stream_list, list) {
 		if (status & azx_dev->sd_int_sta_mask) {
 			sd_status = snd_hdac_stream_readb(azx_dev, SD_STS);
 			snd_hdac_stream_writeb(azx_dev, SD_STS, SD_INT_MASK);
+			handled |= 1 << azx_dev->index;
 			if (!azx_dev->substream || !azx_dev->running ||
 			    !(sd_status & SD_INT_COMPLETE))
 				continue;
@@ -445,6 +449,7 @@ void snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status,
 				ack(bus, azx_dev);
 		}
 	}
+	return handled;
 }
 EXPORT_SYMBOL_GPL(snd_hdac_bus_handle_stream_irq);
 
diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c
index 37cf9cee9835..27de8015717d 100644
--- a/sound/pci/hda/hda_controller.c
+++ b/sound/pci/hda/hda_controller.c
@@ -930,6 +930,8 @@ irqreturn_t azx_interrupt(int irq, void *dev_id)
 	struct azx *chip = dev_id;
 	struct hdac_bus *bus = azx_bus(chip);
 	u32 status;
+	bool active, handled = false;
+	int repeat = 0; /* count for avoiding endless loop */
 
 #ifdef CONFIG_PM
 	if (azx_has_pm_runtime(chip))
@@ -939,33 +941,36 @@ irqreturn_t azx_interrupt(int irq, void *dev_id)
 
 	spin_lock(&bus->reg_lock);
 
-	if (chip->disabled) {
-		spin_unlock(&bus->reg_lock);
-		return IRQ_NONE;
-	}
-
-	status = azx_readl(chip, INTSTS);
-	if (status == 0 || status == 0xffffffff) {
-		spin_unlock(&bus->reg_lock);
-		return IRQ_NONE;
-	}
+	if (chip->disabled)
+		goto unlock;
 
-	snd_hdac_bus_handle_stream_irq(bus, status, stream_update);
+	do {
+		status = azx_readl(chip, INTSTS);
+		if (status == 0 || status == 0xffffffff)
+			break;
 
-	/* clear rirb int */
-	status = azx_readb(chip, RIRBSTS);
-	if (status & RIRB_INT_MASK) {
-		if (status & RIRB_INT_RESPONSE) {
-			if (chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND)
-				udelay(80);
-			snd_hdac_bus_update_rirb(bus);
+		handled = true;
+		active = false;
+		if (snd_hdac_bus_handle_stream_irq(bus, status, stream_update))
+			active = true;
+
+		/* clear rirb int */
+		status = azx_readb(chip, RIRBSTS);
+		if (status & RIRB_INT_MASK) {
+			active = true;
+			if (status & RIRB_INT_RESPONSE) {
+				if (chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND)
+					udelay(80);
+				snd_hdac_bus_update_rirb(bus);
+			}
+			azx_writeb(chip, RIRBSTS, RIRB_INT_MASK);
 		}
-		azx_writeb(chip, RIRBSTS, RIRB_INT_MASK);
-	}
+	} while (active && ++repeat < 10);
 
+ unlock:
 	spin_unlock(&bus->reg_lock);
 
-	return IRQ_HANDLED;
+	return IRQ_RETVAL(handled);
 }
 EXPORT_SYMBOL_GPL(azx_interrupt);
 
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index 30c8efe0f80a..7ca5b89f088a 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -4028,9 +4028,9 @@ static void pin_power_callback(struct hda_codec *codec,
 			       struct hda_jack_callback *jack,
 			       bool on)
 {
-	if (jack && jack->tbl->nid)
+	if (jack && jack->nid)
 		sync_power_state_change(codec,
-					set_pin_power_jack(codec, jack->tbl->nid, on));
+					set_pin_power_jack(codec, jack->nid, on));
 }
 
 /* callback only doing power up -- called at first */
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 4045dca3d699..e5240cb3749f 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -363,7 +363,10 @@ enum {
 					((pci)->device == 0x0d0c) || \
 					((pci)->device == 0x160c))
 
-#define IS_BROXTON(pci)	((pci)->device == 0x5a98)
+#define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170)
+#define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70)
+#define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98)
+#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci))
 
 static char *driver_short_names[] = {
 	[AZX_DRIVER_ICH] = "HDA Intel",
@@ -540,13 +543,13 @@ static void hda_intel_init_chip(struct azx *chip, bool full_reset)
 
 	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL)
 		snd_hdac_set_codec_wakeup(bus, true);
-	if (IS_BROXTON(pci)) {
+	if (IS_SKL_PLUS(pci)) {
 		pci_read_config_dword(pci, INTEL_HDA_CGCTL, &val);
 		val = val & ~INTEL_HDA_CGCTL_MISCBDCGE;
 		pci_write_config_dword(pci, INTEL_HDA_CGCTL, val);
 	}
 	azx_init_chip(chip, full_reset);
-	if (IS_BROXTON(pci)) {
+	if (IS_SKL_PLUS(pci)) {
 		pci_read_config_dword(pci, INTEL_HDA_CGCTL, &val);
 		val = val | INTEL_HDA_CGCTL_MISCBDCGE;
 		pci_write_config_dword(pci, INTEL_HDA_CGCTL, val);
@@ -555,7 +558,7 @@ static void hda_intel_init_chip(struct azx *chip, bool full_reset)
 		snd_hdac_set_codec_wakeup(bus, false);
 
 	/* reduce dma latency to avoid noise */
-	if (IS_BROXTON(pci))
+	if (IS_BXT(pci))
 		bxt_reduce_dma_latency(chip);
 }
 
@@ -977,11 +980,6 @@ static int azx_resume(struct device *dev)
 /* put codec down to D3 at hibernation for Intel SKL+;
  * otherwise BIOS may still access the codec and screw up the driver
  */
-#define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170)
-#define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70)
-#define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98)
-#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci))
-
 static int azx_freeze_noirq(struct device *dev)
 {
 	struct pci_dev *pci = to_pci_dev(dev);
@@ -2168,10 +2166,10 @@ static void azx_remove(struct pci_dev *pci)
 	struct hda_intel *hda;
 
 	if (card) {
-		/* flush the pending probing work */
+		/* cancel the pending probing work */
 		chip = card->private_data;
 		hda = container_of(chip, struct hda_intel, chip);
-		flush_work(&hda->probe_work);
+		cancel_work_sync(&hda->probe_work);
 
 		snd_card_free(card);
 	}
diff --git a/sound/pci/hda/hda_jack.c b/sound/pci/hda/hda_jack.c
index c945e257d368..a33234e04d4f 100644
--- a/sound/pci/hda/hda_jack.c
+++ b/sound/pci/hda/hda_jack.c
@@ -259,7 +259,7 @@ snd_hda_jack_detect_enable_callback(struct hda_codec *codec, hda_nid_t nid,
 		if (!callback)
 			return ERR_PTR(-ENOMEM);
 		callback->func = func;
-		callback->tbl = jack;
+		callback->nid = jack->nid;
 		callback->next = jack->callback;
 		jack->callback = callback;
 	}
diff --git a/sound/pci/hda/hda_jack.h b/sound/pci/hda/hda_jack.h
index 858708a044f5..e9814c0168ea 100644
--- a/sound/pci/hda/hda_jack.h
+++ b/sound/pci/hda/hda_jack.h
@@ -21,7 +21,7 @@ struct hda_jack_callback;
 typedef void (*hda_jack_callback_fn) (struct hda_codec *, struct hda_jack_callback *);
 
 struct hda_jack_callback {
-	struct hda_jack_tbl *tbl;
+	hda_nid_t nid;
 	hda_jack_callback_fn func;
 	unsigned int private_data;	/* arbitrary data */
 	struct hda_jack_callback *next;
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 4ef2259f88ca..9ceb2bc36e68 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -4427,13 +4427,16 @@ static void ca0132_process_dsp_response(struct hda_codec *codec,
 static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb)
 {
 	struct ca0132_spec *spec = codec->spec;
+	struct hda_jack_tbl *tbl;
 
 	/* Delay enabling the HP amp, to let the mic-detection
 	 * state machine run.
 	 */
 	cancel_delayed_work_sync(&spec->unsol_hp_work);
 	schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500));
-	cb->tbl->block_report = 1;
+	tbl = snd_hda_jack_tbl_get(codec, cb->nid);
+	if (tbl)
+		tbl->block_report = 1;
 }
 
 static void amic_callback(struct hda_codec *codec, struct hda_jack_callback *cb)
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 1f52b55d77c9..bcbc4ee10130 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -448,7 +448,8 @@ static int hdmi_eld_ctl_get(struct snd_kcontrol *kcontrol,
 	eld = &per_pin->sink_eld;
 
 	mutex_lock(&per_pin->lock);
-	if (eld->eld_size > ARRAY_SIZE(ucontrol->value.bytes.data)) {
+	if (eld->eld_size > ARRAY_SIZE(ucontrol->value.bytes.data) ||
+	    eld->eld_size > ELD_MAX_SIZE) {
 		mutex_unlock(&per_pin->lock);
 		snd_BUG();
 		return -EINVAL;
@@ -1193,7 +1194,7 @@ static void check_presence_and_report(struct hda_codec *codec, hda_nid_t nid)
 static void jack_callback(struct hda_codec *codec,
 			  struct hda_jack_callback *jack)
 {
-	check_presence_and_report(codec, jack->tbl->nid);
+	check_presence_and_report(codec, jack->nid);
 }
 
 static void hdmi_intrinsic_event(struct hda_codec *codec, unsigned int res)
@@ -2476,13 +2477,6 @@ static int patch_generic_hdmi(struct hda_codec *codec)
 			is_broxton(codec))
 		codec->core.link_power_control = 1;
 
-	if (codec_has_acomp(codec)) {
-		codec->depop_delay = 0;
-		spec->i915_audio_ops.audio_ptr = codec;
-		spec->i915_audio_ops.pin_eld_notify = intel_pin_eld_notify;
-		snd_hdac_i915_register_notifier(&spec->i915_audio_ops);
-	}
-
 	if (hdmi_parse_codec(codec) < 0) {
 		if (spec->i915_bound)
 			snd_hdac_i915_exit(&codec->bus->core);
@@ -2504,6 +2498,18 @@ static int patch_generic_hdmi(struct hda_codec *codec)
 
 	init_channel_allocations();
 
+	if (codec_has_acomp(codec)) {
+		codec->depop_delay = 0;
+		spec->i915_audio_ops.audio_ptr = codec;
+		/* intel_audio_codec_enable() or intel_audio_codec_disable()
+		 * will call pin_eld_notify with using audio_ptr pointer
+		 * We need make sure audio_ptr is really setup
+		 */
+		wmb();
+		spec->i915_audio_ops.pin_eld_notify = intel_pin_eld_notify;
+		snd_hdac_i915_register_notifier(&spec->i915_audio_ops);
+	}
+
 	return 0;
 }
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 21992fb7035d..93d2156b6241 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -282,7 +282,7 @@ static void alc_update_knob_master(struct hda_codec *codec,
 	uctl = kzalloc(sizeof(*uctl), GFP_KERNEL);
 	if (!uctl)
 		return;
-	val = snd_hda_codec_read(codec, jack->tbl->nid, 0,
+	val = snd_hda_codec_read(codec, jack->nid, 0,
 				 AC_VERB_GET_VOLUME_KNOB_CONTROL, 0);
 	val &= HDA_AMP_VOLMASK;
 	uctl->value.integer.value[0] = val;
@@ -1787,7 +1787,6 @@ enum {
 	ALC882_FIXUP_NO_PRIMARY_HP,
 	ALC887_FIXUP_ASUS_BASS,
 	ALC887_FIXUP_BASS_CHMAP,
-	ALC882_FIXUP_DISABLE_AAMIX,
 };
 
 static void alc889_fixup_coef(struct hda_codec *codec,
@@ -1949,8 +1948,6 @@ static void alc882_fixup_no_primary_hp(struct hda_codec *codec,
 
 static void alc_fixup_bass_chmap(struct hda_codec *codec,
 				 const struct hda_fixup *fix, int action);
-static void alc_fixup_disable_aamix(struct hda_codec *codec,
-				    const struct hda_fixup *fix, int action);
 
 static const struct hda_fixup alc882_fixups[] = {
 	[ALC882_FIXUP_ABIT_AW9D_MAX] = {
@@ -2188,10 +2185,6 @@ static const struct hda_fixup alc882_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_bass_chmap,
 	},
-	[ALC882_FIXUP_DISABLE_AAMIX] = {
-		.type = HDA_FIXUP_FUNC,
-		.v.func = alc_fixup_disable_aamix,
-	},
 };
 
 static const struct snd_pci_quirk alc882_fixup_tbl[] = {
@@ -2230,6 +2223,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x104d, 0x9047, "Sony Vaio TT", ALC889_FIXUP_VAIO_TT),
 	SND_PCI_QUIRK(0x104d, 0x905a, "Sony Vaio Z", ALC882_FIXUP_NO_PRIMARY_HP),
 	SND_PCI_QUIRK(0x104d, 0x9043, "Sony Vaio VGC-LN51JGB", ALC882_FIXUP_NO_PRIMARY_HP),
+	SND_PCI_QUIRK(0x104d, 0x9044, "Sony VAIO AiO", ALC882_FIXUP_NO_PRIMARY_HP),
 
 	/* All Apple entries are in codec SSIDs */
 	SND_PCI_QUIRK(0x106b, 0x00a0, "MacBookPro 3,1", ALC889_FIXUP_MBP_VREF),
@@ -2259,7 +2253,6 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD),
 	SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
 	SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1458, 0xa182, "Gigabyte Z170X-UD3", ALC882_FIXUP_DISABLE_AAMIX),
 	SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX),
 	SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD),
@@ -3808,6 +3801,10 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin,
 
 static void alc_headset_mode_default(struct hda_codec *codec)
 {
+	static struct coef_fw coef0225[] = {
+		UPDATE_COEF(0x45, 0x3f<<10, 0x34<<10),
+		{}
+	};
 	static struct coef_fw coef0255[] = {
 		WRITE_COEF(0x45, 0xc089),
 		WRITE_COEF(0x45, 0xc489),
@@ -3849,6 +3846,9 @@ static void alc_headset_mode_default(struct hda_codec *codec)
 	};
 
 	switch (codec->core.vendor_id) {
+	case 0x10ec0225:
+		alc_process_coef_fw(codec, coef0225);
+		break;
 	case 0x10ec0255:
 	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0255);
@@ -4756,6 +4756,9 @@ enum {
 	ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE,
 	ALC293_FIXUP_LENOVO_SPK_NOISE,
 	ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY,
+	ALC255_FIXUP_DELL_SPK_NOISE,
+	ALC225_FIXUP_DELL1_MIC_NO_PRESENCE,
+	ALC280_FIXUP_HP_HEADSET_MIC,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -5375,6 +5378,29 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc233_fixup_lenovo_line2_mic_hotkey,
 	},
+	[ALC255_FIXUP_DELL_SPK_NOISE] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_disable_aamix,
+		.chained = true,
+		.chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE
+	},
+	[ALC225_FIXUP_DELL1_MIC_NO_PRESENCE] = {
+		.type = HDA_FIXUP_VERBS,
+		.v.verbs = (const struct hda_verb[]) {
+			/* Disable pass-through path for FRONT 14h */
+			{ 0x20, AC_VERB_SET_COEF_INDEX, 0x36 },
+			{ 0x20, AC_VERB_SET_PROC_COEF, 0x57d7 },
+			{}
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE
+	},
+	[ALC280_FIXUP_HP_HEADSET_MIC] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_disable_aamix,
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MIC,
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -5386,6 +5412,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x080d, "Acer Aspire V5-122P", ALC269_FIXUP_ASPIRE_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x0740, "Acer AO725", ALC271_FIXUP_HP_GATE_MIC_JACK),
 	SND_PCI_QUIRK(0x1025, 0x0742, "Acer AO756", ALC271_FIXUP_HP_GATE_MIC_JACK),
+	SND_PCI_QUIRK(0x1025, 0x0762, "Acer Aspire E1-472", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
 	SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
 	SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS),
 	SND_PCI_QUIRK(0x1025, 0x106d, "Acer Cloudbook 14", ALC283_FIXUP_CHROME_BOOK),
@@ -5417,6 +5444,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x06df, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
 	SND_PCI_QUIRK(0x1028, 0x06e0, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
 	SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
+	SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE),
 	SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
@@ -5477,6 +5505,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x2335, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2336, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2337, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x221c, "HP EliteBook 755 G2", ALC280_FIXUP_HP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -5645,10 +5674,10 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{0x21, 0x03211020}
 
 static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
-	SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+	SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC225_STANDARD_PINS,
 		{0x14, 0x901701a0}),
-	SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+	SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC225_STANDARD_PINS,
 		{0x14, 0x901701b0}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE,
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 2c7c5eb8b1e9..37b70f8e878f 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -493,9 +493,9 @@ static void jack_update_power(struct hda_codec *codec,
 	if (!spec->num_pwrs)
 		return;
 
-	if (jack && jack->tbl->nid) {
-		stac_toggle_power_map(codec, jack->tbl->nid,
-				      snd_hda_jack_detect(codec, jack->tbl->nid),
+	if (jack && jack->nid) {
+		stac_toggle_power_map(codec, jack->nid,
+				      snd_hda_jack_detect(codec, jack->nid),
 				      true);
 		return;
 	}
diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c
index 42bcbac801a3..12c2c180e407 100644
--- a/sound/pci/intel8x0.c
+++ b/sound/pci/intel8x0.c
@@ -2980,8 +2980,8 @@ static int snd_intel8x0_inside_vm(struct pci_dev *pci)
 		goto fini;
 
 	/* check for known (emulated) devices */
-	if (pci->subsystem_vendor == 0x1af4 &&
-	    pci->subsystem_device == 0x1100) {
+	if (pci->subsystem_vendor == PCI_SUBVENDOR_ID_REDHAT_QUMRANET &&
+	    pci->subsystem_device == PCI_SUBDEVICE_ID_QEMU) {
 		/* KVM emulated sound, PCI SSID: 1af4:1100 */
 		msg = "enable KVM";
 	} else if (pci->subsystem_vendor == 0x1ab8) {
diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c
index 2875b4f6d8c9..7c8941b8b2de 100644
--- a/sound/pci/rme9652/hdsp.c
+++ b/sound/pci/rme9652/hdsp.c
@@ -2879,7 +2879,7 @@ static int snd_hdsp_get_dds_offset(struct snd_kcontrol *kcontrol, struct snd_ctl
 {
 	struct hdsp *hdsp = snd_kcontrol_chip(kcontrol);
 
-	ucontrol->value.enumerated.item[0] = hdsp_dds_offset(hdsp);
+	ucontrol->value.integer.value[0] = hdsp_dds_offset(hdsp);
 	return 0;
 }
 
@@ -2891,7 +2891,7 @@ static int snd_hdsp_put_dds_offset(struct snd_kcontrol *kcontrol, struct snd_ctl
 
 	if (!snd_hdsp_use_is_exclusive(hdsp))
 		return -EBUSY;
-	val = ucontrol->value.enumerated.item[0];
+	val = ucontrol->value.integer.value[0];
 	spin_lock_irq(&hdsp->lock);
 	if (val != hdsp_dds_offset(hdsp))
 		change = (hdsp_set_dds_offset(hdsp, val) == 0) ? 1 : 0;
diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c
index 8bc8016c173d..a4a999a0317e 100644
--- a/sound/pci/rme9652/hdspm.c
+++ b/sound/pci/rme9652/hdspm.c
@@ -1601,6 +1601,9 @@ static void hdspm_set_dds_value(struct hdspm *hdspm, int rate)
 {
 	u64 n;
 
+	if (snd_BUG_ON(rate <= 0))
+		return;
+
 	if (rate >= 112000)
 		rate /= 4;
 	else if (rate >= 56000)
@@ -2215,6 +2218,8 @@ static int hdspm_get_system_sample_rate(struct hdspm *hdspm)
 		} else {
 			/* slave mode, return external sample rate */
 			rate = hdspm_external_sample_rate(hdspm);
+			if (!rate)
+				rate = hdspm->system_sample_rate;
 		}
 	}
 
@@ -2260,8 +2265,11 @@ static int snd_hdspm_put_system_sample_rate(struct snd_kcontrol *kcontrol,
 					    ucontrol)
 {
 	struct hdspm *hdspm = snd_kcontrol_chip(kcontrol);
+	int rate = ucontrol->value.integer.value[0];
 
-	hdspm_set_dds_value(hdspm, ucontrol->value.enumerated.item[0]);
+	if (rate < 27000 || rate > 207000)
+		return -EINVAL;
+	hdspm_set_dds_value(hdspm, ucontrol->value.integer.value[0]);
 	return 0;
 }
 
@@ -4449,7 +4457,7 @@ static int snd_hdspm_get_tco_word_term(struct snd_kcontrol *kcontrol,
 {
 	struct hdspm *hdspm = snd_kcontrol_chip(kcontrol);
 
-	ucontrol->value.enumerated.item[0] = hdspm->tco->term;
+	ucontrol->value.integer.value[0] = hdspm->tco->term;
 
 	return 0;
 }
@@ -4460,8 +4468,8 @@ static int snd_hdspm_put_tco_word_term(struct snd_kcontrol *kcontrol,
 {
 	struct hdspm *hdspm = snd_kcontrol_chip(kcontrol);
 
-	if (hdspm->tco->term != ucontrol->value.enumerated.item[0]) {
-		hdspm->tco->term = ucontrol->value.enumerated.item[0];
+	if (hdspm->tco->term != ucontrol->value.integer.value[0]) {
+		hdspm->tco->term = ucontrol->value.integer.value[0];
 
 		hdspm_tco_write(hdspm);
 
diff --git a/sound/ppc/pmac.c b/sound/ppc/pmac.c
index 0095a80a997f..a5843fc5ff20 100644
--- a/sound/ppc/pmac.c
+++ b/sound/ppc/pmac.c
@@ -34,7 +34,6 @@
 #include "pmac.h"
 #include <sound/pcm_params.h>
 #include <asm/pmac_feature.h>
-#include <asm/pci-bridge.h>
 
 
 /* fixed frequency table for awacs, screamer, burgundy, DACA (44100 max) */
diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index 3191e0a7d273..d1fb035f44db 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -635,6 +635,7 @@ static int acp_dma_open(struct snd_pcm_substream *substream)
 					    SNDRV_PCM_HW_PARAM_PERIODS);
 	if (ret < 0) {
 		dev_err(prtd->platform->dev, "set integer constraint failed\n");
+		kfree(adata);
 		return ret;
 	}
 
diff --git a/sound/soc/codecs/ab8500-codec.c b/sound/soc/codecs/ab8500-codec.c
index affb192238a4..faae6936bae4 100644
--- a/sound/soc/codecs/ab8500-codec.c
+++ b/sound/soc/codecs/ab8500-codec.c
@@ -1130,7 +1130,7 @@ static int sid_status_control_get(struct snd_kcontrol *kcontrol,
 	struct ab8500_codec_drvdata *drvdata = dev_get_drvdata(codec->dev);
 
 	mutex_lock(&drvdata->ctrl_lock);
-	ucontrol->value.integer.value[0] = drvdata->sid_status;
+	ucontrol->value.enumerated.item[0] = drvdata->sid_status;
 	mutex_unlock(&drvdata->ctrl_lock);
 
 	return 0;
@@ -1147,7 +1147,7 @@ static int sid_status_control_put(struct snd_kcontrol *kcontrol,
 
 	dev_dbg(codec->dev, "%s: Enter\n", __func__);
 
-	if (ucontrol->value.integer.value[0] != SID_APPLY_FIR) {
+	if (ucontrol->value.enumerated.item[0] != SID_APPLY_FIR) {
 		dev_err(codec->dev,
 			"%s: ERROR: This control supports '%s' only!\n",
 			__func__, enum_sid_state[SID_APPLY_FIR]);
@@ -1199,7 +1199,7 @@ static int anc_status_control_get(struct snd_kcontrol *kcontrol,
 	struct ab8500_codec_drvdata *drvdata = dev_get_drvdata(codec->dev);
 
 	mutex_lock(&drvdata->ctrl_lock);
-	ucontrol->value.integer.value[0] = drvdata->anc_status;
+	ucontrol->value.enumerated.item[0] = drvdata->anc_status;
 	mutex_unlock(&drvdata->ctrl_lock);
 
 	return 0;
@@ -1220,7 +1220,7 @@ static int anc_status_control_put(struct snd_kcontrol *kcontrol,
 
 	mutex_lock(&drvdata->ctrl_lock);
 
-	req = ucontrol->value.integer.value[0];
+	req = ucontrol->value.enumerated.item[0];
 	if (req >= ARRAY_SIZE(enum_anc_state)) {
 		status = -EINVAL;
 		goto cleanup;
diff --git a/sound/soc/codecs/adau17x1.h b/sound/soc/codecs/adau17x1.h
index e13583e6ff56..5ae87a084d97 100644
--- a/sound/soc/codecs/adau17x1.h
+++ b/sound/soc/codecs/adau17x1.h
@@ -103,9 +103,9 @@ bool adau17x1_has_dsp(struct adau *adau);
 #define ADAU17X1_CLOCK_CONTROL_CORECLK_SRC_PLL	BIT(3)
 #define ADAU17X1_CLOCK_CONTROL_SYSCLK_EN	BIT(0)
 
-#define ADAU17X1_SERIAL_PORT1_BCLK32		(0x0 << 5)
-#define ADAU17X1_SERIAL_PORT1_BCLK48		(0x1 << 5)
-#define ADAU17X1_SERIAL_PORT1_BCLK64		(0x2 << 5)
+#define ADAU17X1_SERIAL_PORT1_BCLK64		(0x0 << 5)
+#define ADAU17X1_SERIAL_PORT1_BCLK32		(0x1 << 5)
+#define ADAU17X1_SERIAL_PORT1_BCLK48		(0x2 << 5)
 #define ADAU17X1_SERIAL_PORT1_BCLK128		(0x3 << 5)
 #define ADAU17X1_SERIAL_PORT1_BCLK256		(0x4 << 5)
 #define ADAU17X1_SERIAL_PORT1_BCLK_MASK		(0x7 << 5)
diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c
index 33143fe1de0b..91785318b283 100644
--- a/sound/soc/codecs/arizona.c
+++ b/sound/soc/codecs/arizona.c
@@ -1929,6 +1929,25 @@ static struct {
 	{ 1000000, 13500000, 0,  1 },
 };
 
+static const unsigned int pseudo_fref_max[ARIZONA_FLL_MAX_FRATIO] = {
+	13500000,
+	 6144000,
+	 6144000,
+	 3072000,
+	 3072000,
+	 2822400,
+	 2822400,
+	 1536000,
+	 1536000,
+	 1536000,
+	 1536000,
+	 1536000,
+	 1536000,
+	 1536000,
+	 1536000,
+	  768000,
+};
+
 static struct {
 	unsigned int min;
 	unsigned int max;
@@ -2042,16 +2061,32 @@ static int arizona_calc_fratio(struct arizona_fll *fll,
 	/* Adjust FRATIO/refdiv to avoid integer mode if possible */
 	refdiv = cfg->refdiv;
 
+	arizona_fll_dbg(fll, "pseudo: initial ratio=%u fref=%u refdiv=%u\n",
+			init_ratio, Fref, refdiv);
+
 	while (div <= ARIZONA_FLL_MAX_REFDIV) {
 		for (ratio = init_ratio; ratio <= ARIZONA_FLL_MAX_FRATIO;
 		     ratio++) {
 			if ((ARIZONA_FLL_VCO_CORNER / 2) /
-			    (fll->vco_mult * ratio) < Fref)
+			    (fll->vco_mult * ratio) < Fref) {
+				arizona_fll_dbg(fll, "pseudo: hit VCO corner\n");
 				break;
+			}
+
+			if (Fref > pseudo_fref_max[ratio - 1]) {
+				arizona_fll_dbg(fll,
+					"pseudo: exceeded max fref(%u) for ratio=%u\n",
+					pseudo_fref_max[ratio - 1],
+					ratio);
+				break;
+			}
 
 			if (target % (ratio * Fref)) {
 				cfg->refdiv = refdiv;
 				cfg->fratio = ratio - 1;
+				arizona_fll_dbg(fll,
+					"pseudo: found fref=%u refdiv=%d(%d) ratio=%d\n",
+					Fref, refdiv, div, ratio);
 				return ratio;
 			}
 		}
@@ -2060,6 +2095,9 @@ static int arizona_calc_fratio(struct arizona_fll *fll,
 			if (target % (ratio * Fref)) {
 				cfg->refdiv = refdiv;
 				cfg->fratio = ratio - 1;
+				arizona_fll_dbg(fll,
+					"pseudo: found fref=%u refdiv=%d(%d) ratio=%d\n",
+					Fref, refdiv, div, ratio);
 				return ratio;
 			}
 		}
@@ -2068,6 +2106,9 @@ static int arizona_calc_fratio(struct arizona_fll *fll,
 		Fref /= 2;
 		refdiv++;
 		init_ratio = arizona_find_fratio(Fref, NULL);
+		arizona_fll_dbg(fll,
+				"pseudo: change fref=%u refdiv=%d(%d) ratio=%u\n",
+				Fref, refdiv, div, init_ratio);
 	}
 
 	arizona_fll_warn(fll, "Falling back to integer mode operation\n");
diff --git a/sound/soc/codecs/cs4271.c b/sound/soc/codecs/cs4271.c
index e770ee6f36da..0c0010b25421 100644
--- a/sound/soc/codecs/cs4271.c
+++ b/sound/soc/codecs/cs4271.c
@@ -26,6 +26,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/of_gpio.h>
+#include <linux/regulator/consumer.h>
 #include <sound/pcm.h>
 #include <sound/soc.h>
 #include <sound/tlv.h>
@@ -157,6 +158,10 @@ static bool cs4271_volatile_reg(struct device *dev, unsigned int reg)
 	return reg == CS4271_CHIPID;
 }
 
+static const char * const supply_names[] = {
+	"vd", "vl", "va"
+};
+
 struct cs4271_private {
 	unsigned int			mclk;
 	bool				master;
@@ -170,6 +175,7 @@ struct cs4271_private {
 	int				gpio_disable;
 	/* enable soft reset workaround */
 	bool				enable_soft_reset;
+	struct regulator_bulk_data      supplies[ARRAY_SIZE(supply_names)];
 };
 
 static const struct snd_soc_dapm_widget cs4271_dapm_widgets[] = {
@@ -487,6 +493,20 @@ static struct snd_soc_dai_driver cs4271_dai = {
 	.symmetric_rates = 1,
 };
 
+static int cs4271_reset(struct snd_soc_codec *codec)
+{
+	struct cs4271_private *cs4271 = snd_soc_codec_get_drvdata(codec);
+
+	if (gpio_is_valid(cs4271->gpio_nreset)) {
+		gpio_set_value(cs4271->gpio_nreset, 0);
+		mdelay(1);
+		gpio_set_value(cs4271->gpio_nreset, 1);
+		mdelay(1);
+	}
+
+	return 0;
+}
+
 #ifdef CONFIG_PM
 static int cs4271_soc_suspend(struct snd_soc_codec *codec)
 {
@@ -499,6 +519,9 @@ static int cs4271_soc_suspend(struct snd_soc_codec *codec)
 	if (ret < 0)
 		return ret;
 
+	regcache_mark_dirty(cs4271->regmap);
+	regulator_bulk_disable(ARRAY_SIZE(cs4271->supplies), cs4271->supplies);
+
 	return 0;
 }
 
@@ -507,6 +530,16 @@ static int cs4271_soc_resume(struct snd_soc_codec *codec)
 	int ret;
 	struct cs4271_private *cs4271 = snd_soc_codec_get_drvdata(codec);
 
+	ret = regulator_bulk_enable(ARRAY_SIZE(cs4271->supplies),
+				    cs4271->supplies);
+	if (ret < 0) {
+		dev_err(codec->dev, "Failed to enable regulators: %d\n", ret);
+		return ret;
+	}
+
+	/* Do a proper reset after power up */
+	cs4271_reset(codec);
+
 	/* Restore codec state */
 	ret = regcache_sync(cs4271->regmap);
 	if (ret < 0)
@@ -553,19 +586,24 @@ static int cs4271_codec_probe(struct snd_soc_codec *codec)
 	}
 #endif
 
+	ret = regulator_bulk_enable(ARRAY_SIZE(cs4271->supplies),
+				    cs4271->supplies);
+	if (ret < 0) {
+		dev_err(codec->dev, "Failed to enable regulators: %d\n", ret);
+		return ret;
+	}
+
 	if (cs4271plat) {
 		amutec_eq_bmutec = cs4271plat->amutec_eq_bmutec;
 		cs4271->enable_soft_reset = cs4271plat->enable_soft_reset;
 	}
 
-	if (gpio_is_valid(cs4271->gpio_nreset)) {
-		/* Reset codec */
-		gpio_direction_output(cs4271->gpio_nreset, 0);
-		mdelay(1);
-		gpio_set_value(cs4271->gpio_nreset, 1);
-		/* Give the codec time to wake up */
-		mdelay(1);
-	}
+	/* Reset codec */
+	cs4271_reset(codec);
+
+	ret = regcache_sync(cs4271->regmap);
+	if (ret < 0)
+		return ret;
 
 	ret = regmap_update_bits(cs4271->regmap, CS4271_MODE2,
 				 CS4271_MODE2_PDN | CS4271_MODE2_CPEN,
@@ -595,6 +633,9 @@ static int cs4271_codec_remove(struct snd_soc_codec *codec)
 		/* Set codec to the reset state */
 		gpio_set_value(cs4271->gpio_nreset, 0);
 
+	regcache_mark_dirty(cs4271->regmap);
+	regulator_bulk_disable(ARRAY_SIZE(cs4271->supplies), cs4271->supplies);
+
 	return 0;
 };
 
@@ -617,6 +658,7 @@ static int cs4271_common_probe(struct device *dev,
 {
 	struct cs4271_platform_data *cs4271plat = dev->platform_data;
 	struct cs4271_private *cs4271;
+	int i, ret;
 
 	cs4271 = devm_kzalloc(dev, sizeof(*cs4271), GFP_KERNEL);
 	if (!cs4271)
@@ -638,6 +680,17 @@ static int cs4271_common_probe(struct device *dev,
 			return ret;
 	}
 
+	for (i = 0; i < ARRAY_SIZE(supply_names); i++)
+		cs4271->supplies[i].supply = supply_names[i];
+
+	ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(cs4271->supplies),
+					cs4271->supplies);
+
+	if (ret < 0) {
+		dev_err(dev, "Failed to get regulators: %d\n", ret);
+		return ret;
+	}
+
 	*c = cs4271;
 	return 0;
 }
diff --git a/sound/soc/codecs/cs42l51.c b/sound/soc/codecs/cs42l51.c
index b3951524339f..35488f14e237 100644
--- a/sound/soc/codecs/cs42l51.c
+++ b/sound/soc/codecs/cs42l51.c
@@ -60,15 +60,15 @@ static int cs42l51_get_chan_mix(struct snd_kcontrol *kcontrol,
 	switch (value) {
 	default:
 	case 0:
-		ucontrol->value.integer.value[0] = 0;
+		ucontrol->value.enumerated.item[0] = 0;
 		break;
 	/* same value : (L+R)/2 and (R+L)/2 */
 	case 1:
 	case 2:
-		ucontrol->value.integer.value[0] = 1;
+		ucontrol->value.enumerated.item[0] = 1;
 		break;
 	case 3:
-		ucontrol->value.integer.value[0] = 2;
+		ucontrol->value.enumerated.item[0] = 2;
 		break;
 	}
 
@@ -85,7 +85,7 @@ static int cs42l51_set_chan_mix(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	unsigned char val;
 
-	switch (ucontrol->value.integer.value[0]) {
+	switch (ucontrol->value.enumerated.item[0]) {
 	default:
 	case 0:
 		val = CHAN_MIX_NORMAL;
diff --git a/sound/soc/codecs/da732x.c b/sound/soc/codecs/da732x.c
index 1d5a89c5164b..461506a4ca6a 100644
--- a/sound/soc/codecs/da732x.c
+++ b/sound/soc/codecs/da732x.c
@@ -334,7 +334,7 @@ static int da732x_hpf_set(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct soc_enum *enum_ctrl = (struct soc_enum *)kcontrol->private_value;
 	unsigned int reg = enum_ctrl->reg;
-	unsigned int sel = ucontrol->value.integer.value[0];
+	unsigned int sel = ucontrol->value.enumerated.item[0];
 	unsigned int bits;
 
 	switch (sel) {
@@ -368,13 +368,13 @@ static int da732x_hpf_get(struct snd_kcontrol *kcontrol,
 
 	switch (val) {
 	case DA732X_HPF_VOICE_EN:
-		ucontrol->value.integer.value[0] = DA732X_HPF_VOICE;
+		ucontrol->value.enumerated.item[0] = DA732X_HPF_VOICE;
 		break;
 	case DA732X_HPF_MUSIC_EN:
-		ucontrol->value.integer.value[0] = DA732X_HPF_MUSIC;
+		ucontrol->value.enumerated.item[0] = DA732X_HPF_MUSIC;
 		break;
 	default:
-		ucontrol->value.integer.value[0] = DA732X_HPF_DISABLED;
+		ucontrol->value.enumerated.item[0] = DA732X_HPF_DISABLED;
 		break;
 	}
 
diff --git a/sound/soc/codecs/max98088.c b/sound/soc/codecs/max98088.c
index 20dcc496d39c..fc22804cabc5 100644
--- a/sound/soc/codecs/max98088.c
+++ b/sound/soc/codecs/max98088.c
@@ -1496,7 +1496,7 @@ static int max98088_put_eq_enum(struct snd_kcontrol *kcontrol,
        struct max98088_pdata *pdata = max98088->pdata;
        int channel = max98088_get_channel(codec, kcontrol->id.name);
        struct max98088_cdata *cdata;
-       int sel = ucontrol->value.integer.value[0];
+	int sel = ucontrol->value.enumerated.item[0];
 
        if (channel < 0)
 	       return channel;
diff --git a/sound/soc/codecs/max98095.c b/sound/soc/codecs/max98095.c
index 1fedac50355e..3577003f39cf 100644
--- a/sound/soc/codecs/max98095.c
+++ b/sound/soc/codecs/max98095.c
@@ -1499,7 +1499,7 @@ static int max98095_put_eq_enum(struct snd_kcontrol *kcontrol,
 	struct max98095_pdata *pdata = max98095->pdata;
 	int channel = max98095_get_eq_channel(kcontrol->id.name);
 	struct max98095_cdata *cdata;
-	unsigned int sel = ucontrol->value.integer.value[0];
+	unsigned int sel = ucontrol->value.enumerated.item[0];
 	struct max98095_eq_cfg *coef_set;
 	int fs, best, best_val, i;
 	int regmask, regsave;
@@ -1653,7 +1653,7 @@ static int max98095_put_bq_enum(struct snd_kcontrol *kcontrol,
 	struct max98095_pdata *pdata = max98095->pdata;
 	int channel = max98095_get_bq_channel(codec, kcontrol->id.name);
 	struct max98095_cdata *cdata;
-	unsigned int sel = ucontrol->value.integer.value[0];
+	unsigned int sel = ucontrol->value.enumerated.item[0];
 	struct max98095_biquad_cfg *coef_set;
 	int fs, best, best_val, i;
 	int regmask, regsave;
diff --git a/sound/soc/codecs/rt286.c b/sound/soc/codecs/rt286.c
index bc08f0c5a5f6..1bd31644a782 100644
--- a/sound/soc/codecs/rt286.c
+++ b/sound/soc/codecs/rt286.c
@@ -266,6 +266,8 @@ static int rt286_jack_detect(struct rt286_priv *rt286, bool *hp, bool *mic)
 		} else {
 			*mic = false;
 			regmap_write(rt286->regmap, RT286_SET_MIC1, 0x20);
+			regmap_update_bits(rt286->regmap,
+				RT286_CBJ_CTRL1, 0x0400, 0x0000);
 		}
 	} else {
 		regmap_read(rt286->regmap, RT286_GET_HP_SENSE, &buf);
@@ -470,24 +472,6 @@ static int rt286_set_dmic1_event(struct snd_soc_dapm_widget *w,
 	return 0;
 }
 
-static int rt286_vref_event(struct snd_soc_dapm_widget *w,
-			     struct snd_kcontrol *kcontrol, int event)
-{
-	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(w->dapm);
-
-	switch (event) {
-	case SND_SOC_DAPM_PRE_PMU:
-		snd_soc_update_bits(codec,
-			RT286_CBJ_CTRL1, 0x0400, 0x0000);
-		mdelay(50);
-		break;
-	default:
-		return 0;
-	}
-
-	return 0;
-}
-
 static int rt286_ldo2_event(struct snd_soc_dapm_widget *w,
 			     struct snd_kcontrol *kcontrol, int event)
 {
@@ -536,7 +520,7 @@ static const struct snd_soc_dapm_widget rt286_dapm_widgets[] = {
 	SND_SOC_DAPM_SUPPLY_S("HV", 1, RT286_POWER_CTRL1,
 		12, 1, NULL, 0),
 	SND_SOC_DAPM_SUPPLY("VREF", RT286_POWER_CTRL1,
-		0, 1, rt286_vref_event, SND_SOC_DAPM_PRE_PMU),
+		0, 1, NULL, 0),
 	SND_SOC_DAPM_SUPPLY_S("LDO1", 1, RT286_POWER_CTRL2,
 		2, 0, NULL, 0),
 	SND_SOC_DAPM_SUPPLY_S("LDO2", 2, RT286_POWER_CTRL1,
@@ -911,8 +895,6 @@ static int rt286_set_bias_level(struct snd_soc_codec *codec,
 	case SND_SOC_BIAS_ON:
 		mdelay(10);
 		snd_soc_update_bits(codec,
-			RT286_CBJ_CTRL1, 0x0400, 0x0400);
-		snd_soc_update_bits(codec,
 			RT286_DC_GAIN, 0x200, 0x0);
 
 		break;
@@ -920,8 +902,6 @@ static int rt286_set_bias_level(struct snd_soc_codec *codec,
 	case SND_SOC_BIAS_STANDBY:
 		snd_soc_write(codec,
 			RT286_SET_AUDIO_POWER, AC_PWRST_D3);
-		snd_soc_update_bits(codec,
-			RT286_CBJ_CTRL1, 0x0400, 0x0000);
 		break;
 
 	default:
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index c61d38b585fb..93e8c9017633 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -776,7 +776,7 @@ static const struct snd_kcontrol_new rt5645_snd_controls[] = {
 
 	/* IN1/IN2 Control */
 	SOC_SINGLE_TLV("IN1 Boost", RT5645_IN1_CTRL1,
-		RT5645_BST_SFT1, 8, 0, bst_tlv),
+		RT5645_BST_SFT1, 12, 0, bst_tlv),
 	SOC_SINGLE_TLV("IN2 Boost", RT5645_IN2_CTRL,
 		RT5645_BST_SFT2, 8, 0, bst_tlv),
 
diff --git a/sound/soc/codecs/rt5659.c b/sound/soc/codecs/rt5659.c
index 820d8fa62b5e..fb8ea05c0de1 100644
--- a/sound/soc/codecs/rt5659.c
+++ b/sound/soc/codecs/rt5659.c
@@ -3985,7 +3985,6 @@ static int rt5659_i2c_probe(struct i2c_client *i2c,
 	if (rt5659 == NULL)
 		return -ENOMEM;
 
-	rt5659->i2c = i2c;
 	i2c_set_clientdata(i2c, rt5659);
 
 	if (pdata)
@@ -4157,24 +4156,17 @@ static int rt5659_i2c_probe(struct i2c_client *i2c,
 
 	INIT_DELAYED_WORK(&rt5659->jack_detect_work, rt5659_jack_detect_work);
 
-	if (rt5659->i2c->irq) {
-		ret = request_threaded_irq(rt5659->i2c->irq, NULL, rt5659_irq,
-			IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING
+	if (i2c->irq) {
+		ret = devm_request_threaded_irq(&i2c->dev, i2c->irq, NULL,
+			rt5659_irq, IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING
 			| IRQF_ONESHOT, "rt5659", rt5659);
 		if (ret)
 			dev_err(&i2c->dev, "Failed to reguest IRQ: %d\n", ret);
 
 	}
 
-	ret = snd_soc_register_codec(&i2c->dev, &soc_codec_dev_rt5659,
+	return snd_soc_register_codec(&i2c->dev, &soc_codec_dev_rt5659,
 			rt5659_dai, ARRAY_SIZE(rt5659_dai));
-
-	if (ret) {
-		if (rt5659->i2c->irq)
-			free_irq(rt5659->i2c->irq, rt5659);
-	}
-
-	return 0;
 }
 
 static int rt5659_i2c_remove(struct i2c_client *i2c)
@@ -4191,24 +4183,29 @@ void rt5659_i2c_shutdown(struct i2c_client *client)
 	regmap_write(rt5659->regmap, RT5659_RESET, 0);
 }
 
+#ifdef CONFIG_OF
 static const struct of_device_id rt5659_of_match[] = {
 	{ .compatible = "realtek,rt5658", },
 	{ .compatible = "realtek,rt5659", },
-	{},
+	{ },
 };
+MODULE_DEVICE_TABLE(of, rt5659_of_match);
+#endif
 
+#ifdef CONFIG_ACPI
 static struct acpi_device_id rt5659_acpi_match[] = {
-		{ "10EC5658", 0},
-		{ "10EC5659", 0},
-		{ },
+	{ "10EC5658", 0, },
+	{ "10EC5659", 0, },
+	{ },
 };
 MODULE_DEVICE_TABLE(acpi, rt5659_acpi_match);
+#endif
 
 struct i2c_driver rt5659_i2c_driver = {
 	.driver = {
 		.name = "rt5659",
 		.owner = THIS_MODULE,
-		.of_match_table = rt5659_of_match,
+		.of_match_table = of_match_ptr(rt5659_of_match),
 		.acpi_match_table = ACPI_PTR(rt5659_acpi_match),
 	},
 	.probe = rt5659_i2c_probe,
diff --git a/sound/soc/codecs/rt5659.h b/sound/soc/codecs/rt5659.h
index 8f07ee903eaa..d31c9e5bcec8 100644
--- a/sound/soc/codecs/rt5659.h
+++ b/sound/soc/codecs/rt5659.h
@@ -1792,7 +1792,6 @@ struct rt5659_priv {
 	struct snd_soc_codec *codec;
 	struct rt5659_platform_data pdata;
 	struct regmap *regmap;
-	struct i2c_client *i2c;
 	struct gpio_desc *gpiod_ldo1_en;
 	struct gpio_desc *gpiod_reset;
 	struct snd_soc_jack *hs_jack;
diff --git a/sound/soc/codecs/sigmadsp-i2c.c b/sound/soc/codecs/sigmadsp-i2c.c
index 21ca3a5e9f66..d374c18d4db7 100644
--- a/sound/soc/codecs/sigmadsp-i2c.c
+++ b/sound/soc/codecs/sigmadsp-i2c.c
@@ -31,7 +31,10 @@ static int sigmadsp_write_i2c(void *control_data,
 
 	kfree(buf);
 
-	return ret;
+	if (ret < 0)
+		return ret;
+
+	return 0;
 }
 
 static int sigmadsp_read_i2c(void *control_data,
diff --git a/sound/soc/codecs/tlv320dac33.c b/sound/soc/codecs/tlv320dac33.c
index 781398fb2841..f7a6ce7e5fb1 100644
--- a/sound/soc/codecs/tlv320dac33.c
+++ b/sound/soc/codecs/tlv320dac33.c
@@ -446,7 +446,7 @@ static int dac33_get_fifo_mode(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct tlv320dac33_priv *dac33 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.integer.value[0] = dac33->fifo_mode;
+	ucontrol->value.enumerated.item[0] = dac33->fifo_mode;
 
 	return 0;
 }
@@ -458,17 +458,16 @@ static int dac33_set_fifo_mode(struct snd_kcontrol *kcontrol,
 	struct tlv320dac33_priv *dac33 = snd_soc_codec_get_drvdata(codec);
 	int ret = 0;
 
-	if (dac33->fifo_mode == ucontrol->value.integer.value[0])
+	if (dac33->fifo_mode == ucontrol->value.enumerated.item[0])
 		return 0;
 	/* Do not allow changes while stream is running*/
 	if (snd_soc_codec_is_active(codec))
 		return -EPERM;
 
-	if (ucontrol->value.integer.value[0] < 0 ||
-	    ucontrol->value.integer.value[0] >= DAC33_FIFO_LAST_MODE)
+	if (ucontrol->value.enumerated.item[0] >= DAC33_FIFO_LAST_MODE)
 		ret = -EINVAL;
 	else
-		dac33->fifo_mode = ucontrol->value.integer.value[0];
+		dac33->fifo_mode = ucontrol->value.enumerated.item[0];
 
 	return ret;
 }
diff --git a/sound/soc/codecs/wl1273.c b/sound/soc/codecs/wl1273.c
index 7693c1129bab..1b79778098d2 100644
--- a/sound/soc/codecs/wl1273.c
+++ b/sound/soc/codecs/wl1273.c
@@ -175,7 +175,7 @@ static int snd_wl1273_get_audio_route(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wl1273_priv *wl1273 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.integer.value[0] = wl1273->mode;
+	ucontrol->value.enumerated.item[0] = wl1273->mode;
 
 	return 0;
 }
@@ -193,18 +193,17 @@ static int snd_wl1273_set_audio_route(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wl1273_priv *wl1273 = snd_soc_codec_get_drvdata(codec);
 
-	if (wl1273->mode == ucontrol->value.integer.value[0])
+	if (wl1273->mode == ucontrol->value.enumerated.item[0])
 		return 0;
 
 	/* Do not allow changes while stream is running */
 	if (snd_soc_codec_is_active(codec))
 		return -EPERM;
 
-	if (ucontrol->value.integer.value[0] < 0 ||
-	    ucontrol->value.integer.value[0] >=  ARRAY_SIZE(wl1273_audio_route))
+	if (ucontrol->value.enumerated.item[0] >=  ARRAY_SIZE(wl1273_audio_route))
 		return -EINVAL;
 
-	wl1273->mode = ucontrol->value.integer.value[0];
+	wl1273->mode = ucontrol->value.enumerated.item[0];
 
 	return 1;
 }
@@ -219,7 +218,7 @@ static int snd_wl1273_fm_audio_get(struct snd_kcontrol *kcontrol,
 
 	dev_dbg(codec->dev, "%s: enter.\n", __func__);
 
-	ucontrol->value.integer.value[0] = wl1273->core->audio_mode;
+	ucontrol->value.enumerated.item[0] = wl1273->core->audio_mode;
 
 	return 0;
 }
@@ -233,7 +232,7 @@ static int snd_wl1273_fm_audio_put(struct snd_kcontrol *kcontrol,
 
 	dev_dbg(codec->dev, "%s: enter.\n", __func__);
 
-	val = ucontrol->value.integer.value[0];
+	val = ucontrol->value.enumerated.item[0];
 	if (wl1273->core->audio_mode == val)
 		return 0;
 
diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c
index 6088d30962a9..97c0f1e23886 100644
--- a/sound/soc/codecs/wm5110.c
+++ b/sound/soc/codecs/wm5110.c
@@ -2382,6 +2382,7 @@ error:
 
 static int wm5110_remove(struct platform_device *pdev)
 {
+	snd_soc_unregister_platform(&pdev->dev);
 	snd_soc_unregister_codec(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
diff --git a/sound/soc/codecs/wm8753.c b/sound/soc/codecs/wm8753.c
index 61299ca372ff..6f1024f48b19 100644
--- a/sound/soc/codecs/wm8753.c
+++ b/sound/soc/codecs/wm8753.c
@@ -233,7 +233,7 @@ static int wm8753_get_dai(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8753_priv *wm8753 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.integer.value[0] = wm8753->dai_func;
+	ucontrol->value.enumerated.item[0] = wm8753->dai_func;
 	return 0;
 }
 
@@ -244,7 +244,7 @@ static int wm8753_set_dai(struct snd_kcontrol *kcontrol,
 	struct wm8753_priv *wm8753 = snd_soc_codec_get_drvdata(codec);
 	u16 ioctl;
 
-	if (wm8753->dai_func == ucontrol->value.integer.value[0])
+	if (wm8753->dai_func == ucontrol->value.enumerated.item[0])
 		return 0;
 
 	if (snd_soc_codec_is_active(codec))
@@ -252,7 +252,7 @@ static int wm8753_set_dai(struct snd_kcontrol *kcontrol,
 
 	ioctl = snd_soc_read(codec, WM8753_IOCTL);
 
-	wm8753->dai_func = ucontrol->value.integer.value[0];
+	wm8753->dai_func = ucontrol->value.enumerated.item[0];
 
 	if (((ioctl >> 2) & 0x3) == wm8753->dai_func)
 		return 1;
diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c
index 8172e499e6ed..edd7a7709194 100644
--- a/sound/soc/codecs/wm8904.c
+++ b/sound/soc/codecs/wm8904.c
@@ -396,7 +396,7 @@ static int wm8904_put_drc_enum(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec);
 	struct wm8904_pdata *pdata = wm8904->pdata;
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 
 	if (value >= pdata->num_drc_cfgs)
 		return -EINVAL;
@@ -467,7 +467,7 @@ static int wm8904_put_retune_mobile_enum(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec);
 	struct wm8904_pdata *pdata = wm8904->pdata;
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 
 	if (value >= pdata->num_retune_mobile_cfgs)
 		return -EINVAL;
diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c
index c799cca5abeb..6b864c0fc2b6 100644
--- a/sound/soc/codecs/wm8958-dsp2.c
+++ b/sound/soc/codecs/wm8958-dsp2.c
@@ -459,7 +459,7 @@ static int wm8958_put_mbc_enum(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
 	struct wm8994 *control = wm8994->wm8994;
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 	int reg;
 
 	/* Don't allow on the fly reconfiguration */
@@ -549,7 +549,7 @@ static int wm8958_put_vss_enum(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
 	struct wm8994 *control = wm8994->wm8994;
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 	int reg;
 
 	/* Don't allow on the fly reconfiguration */
@@ -582,7 +582,7 @@ static int wm8958_put_vss_hpf_enum(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
 	struct wm8994 *control = wm8994->wm8994;
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 	int reg;
 
 	/* Don't allow on the fly reconfiguration */
@@ -749,7 +749,7 @@ static int wm8958_put_enh_eq_enum(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
 	struct wm8994 *control = wm8994->wm8994;
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 	int reg;
 
 	/* Don't allow on the fly reconfiguration */
diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c
index ff237726775a..d7f444f87460 100644
--- a/sound/soc/codecs/wm8960.c
+++ b/sound/soc/codecs/wm8960.c
@@ -240,13 +240,13 @@ SOC_DOUBLE_R("Capture Volume ZC Switch", WM8960_LINVOL, WM8960_RINVOL,
 SOC_DOUBLE_R("Capture Switch", WM8960_LINVOL, WM8960_RINVOL,
 	7, 1, 1),
 
-SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT3 Volume",
+SOC_SINGLE_TLV("Left Input Boost Mixer LINPUT3 Volume",
 	       WM8960_INBMIX1, 4, 7, 0, lineinboost_tlv),
-SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT2 Volume",
+SOC_SINGLE_TLV("Left Input Boost Mixer LINPUT2 Volume",
 	       WM8960_INBMIX1, 1, 7, 0, lineinboost_tlv),
-SOC_SINGLE_TLV("Left Input Boost Mixer LINPUT3 Volume",
+SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT3 Volume",
 	       WM8960_INBMIX2, 4, 7, 0, lineinboost_tlv),
-SOC_SINGLE_TLV("Left Input Boost Mixer LINPUT2 Volume",
+SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT2 Volume",
 	       WM8960_INBMIX2, 1, 7, 0, lineinboost_tlv),
 SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT1 Volume",
 		WM8960_RINPATH, 4, 3, 0, micboost_tlv),
@@ -643,29 +643,31 @@ static int wm8960_configure_clocking(struct snd_soc_codec *codec)
 		return -EINVAL;
 	}
 
-	/* check if the sysclk frequency is available. */
-	for (i = 0; i < ARRAY_SIZE(sysclk_divs); ++i) {
-		if (sysclk_divs[i] == -1)
-			continue;
-		sysclk = freq_out / sysclk_divs[i];
-		for (j = 0; j < ARRAY_SIZE(dac_divs); ++j) {
-			if (sysclk == dac_divs[j] * lrclk) {
+	if (wm8960->clk_id != WM8960_SYSCLK_PLL) {
+		/* check if the sysclk frequency is available. */
+		for (i = 0; i < ARRAY_SIZE(sysclk_divs); ++i) {
+			if (sysclk_divs[i] == -1)
+				continue;
+			sysclk = freq_out / sysclk_divs[i];
+			for (j = 0; j < ARRAY_SIZE(dac_divs); ++j) {
+				if (sysclk != dac_divs[j] * lrclk)
+					continue;
 				for (k = 0; k < ARRAY_SIZE(bclk_divs); ++k)
 					if (sysclk == bclk * bclk_divs[k] / 10)
 						break;
 				if (k != ARRAY_SIZE(bclk_divs))
 					break;
 			}
+			if (j != ARRAY_SIZE(dac_divs))
+				break;
 		}
-		if (j != ARRAY_SIZE(dac_divs))
-			break;
-	}
 
-	if (i != ARRAY_SIZE(sysclk_divs)) {
-		goto configure_clock;
-	} else if (wm8960->clk_id != WM8960_SYSCLK_AUTO) {
-		dev_err(codec->dev, "failed to configure clock\n");
-		return -EINVAL;
+		if (i != ARRAY_SIZE(sysclk_divs)) {
+			goto configure_clock;
+		} else if (wm8960->clk_id != WM8960_SYSCLK_AUTO) {
+			dev_err(codec->dev, "failed to configure clock\n");
+			return -EINVAL;
+		}
 	}
 	/* get a available pll out frequency and set pll */
 	for (i = 0; i < ARRAY_SIZE(sysclk_divs); ++i) {
diff --git a/sound/soc/codecs/wm8983.c b/sound/soc/codecs/wm8983.c
index 7350ff654bbf..0c002a5712cb 100644
--- a/sound/soc/codecs/wm8983.c
+++ b/sound/soc/codecs/wm8983.c
@@ -497,9 +497,9 @@ static int eqmode_get(struct snd_kcontrol *kcontrol,
 
 	reg = snd_soc_read(codec, WM8983_EQ1_LOW_SHELF);
 	if (reg & WM8983_EQ3DMODE)
-		ucontrol->value.integer.value[0] = 1;
+		ucontrol->value.enumerated.item[0] = 1;
 	else
-		ucontrol->value.integer.value[0] = 0;
+		ucontrol->value.enumerated.item[0] = 0;
 
 	return 0;
 }
@@ -511,18 +511,18 @@ static int eqmode_put(struct snd_kcontrol *kcontrol,
 	unsigned int regpwr2, regpwr3;
 	unsigned int reg_eq;
 
-	if (ucontrol->value.integer.value[0] != 0
-	    && ucontrol->value.integer.value[0] != 1)
+	if (ucontrol->value.enumerated.item[0] != 0
+	    && ucontrol->value.enumerated.item[0] != 1)
 		return -EINVAL;
 
 	reg_eq = snd_soc_read(codec, WM8983_EQ1_LOW_SHELF);
 	switch ((reg_eq & WM8983_EQ3DMODE) >> WM8983_EQ3DMODE_SHIFT) {
 	case 0:
-		if (!ucontrol->value.integer.value[0])
+		if (!ucontrol->value.enumerated.item[0])
 			return 0;
 		break;
 	case 1:
-		if (ucontrol->value.integer.value[0])
+		if (ucontrol->value.enumerated.item[0])
 			return 0;
 		break;
 	}
@@ -537,7 +537,7 @@ static int eqmode_put(struct snd_kcontrol *kcontrol,
 	/* set the desired eqmode */
 	snd_soc_update_bits(codec, WM8983_EQ1_LOW_SHELF,
 			    WM8983_EQ3DMODE_MASK,
-			    ucontrol->value.integer.value[0]
+			    ucontrol->value.enumerated.item[0]
 			    << WM8983_EQ3DMODE_SHIFT);
 	/* restore DAC/ADC configuration */
 	snd_soc_write(codec, WM8983_POWER_MANAGEMENT_2, regpwr2);
diff --git a/sound/soc/codecs/wm8985.c b/sound/soc/codecs/wm8985.c
index 9918152a03c7..6ac76fe116b0 100644
--- a/sound/soc/codecs/wm8985.c
+++ b/sound/soc/codecs/wm8985.c
@@ -531,9 +531,9 @@ static int eqmode_get(struct snd_kcontrol *kcontrol,
 
 	reg = snd_soc_read(codec, WM8985_EQ1_LOW_SHELF);
 	if (reg & WM8985_EQ3DMODE)
-		ucontrol->value.integer.value[0] = 1;
+		ucontrol->value.enumerated.item[0] = 1;
 	else
-		ucontrol->value.integer.value[0] = 0;
+		ucontrol->value.enumerated.item[0] = 0;
 
 	return 0;
 }
@@ -545,18 +545,18 @@ static int eqmode_put(struct snd_kcontrol *kcontrol,
 	unsigned int regpwr2, regpwr3;
 	unsigned int reg_eq;
 
-	if (ucontrol->value.integer.value[0] != 0
-			&& ucontrol->value.integer.value[0] != 1)
+	if (ucontrol->value.enumerated.item[0] != 0
+			&& ucontrol->value.enumerated.item[0] != 1)
 		return -EINVAL;
 
 	reg_eq = snd_soc_read(codec, WM8985_EQ1_LOW_SHELF);
 	switch ((reg_eq & WM8985_EQ3DMODE) >> WM8985_EQ3DMODE_SHIFT) {
 	case 0:
-		if (!ucontrol->value.integer.value[0])
+		if (!ucontrol->value.enumerated.item[0])
 			return 0;
 		break;
 	case 1:
-		if (ucontrol->value.integer.value[0])
+		if (ucontrol->value.enumerated.item[0])
 			return 0;
 		break;
 	}
@@ -573,7 +573,7 @@ static int eqmode_put(struct snd_kcontrol *kcontrol,
 	/* set the desired eqmode */
 	snd_soc_update_bits(codec, WM8985_EQ1_LOW_SHELF,
 			    WM8985_EQ3DMODE_MASK,
-			    ucontrol->value.integer.value[0]
+			    ucontrol->value.enumerated.item[0]
 			    << WM8985_EQ3DMODE_SHIFT);
 	/* restore DAC/ADC configuration */
 	snd_soc_write(codec, WM8985_POWER_MANAGEMENT_2, regpwr2);
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index 2ccbb322df77..a18aecb49935 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -362,7 +362,7 @@ static int wm8994_put_drc_enum(struct snd_kcontrol *kcontrol,
 	struct wm8994 *control = wm8994->wm8994;
 	struct wm8994_pdata *pdata = &control->pdata;
 	int drc = wm8994_get_drc(kcontrol->id.name);
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 
 	if (drc < 0)
 		return drc;
@@ -469,7 +469,7 @@ static int wm8994_put_retune_mobile_enum(struct snd_kcontrol *kcontrol,
 	struct wm8994 *control = wm8994->wm8994;
 	struct wm8994_pdata *pdata = &control->pdata;
 	int block = wm8994_get_retune_mobile_block(kcontrol->id.name);
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 
 	if (block < 0)
 		return block;
diff --git a/sound/soc/codecs/wm8996.c b/sound/soc/codecs/wm8996.c
index 8d7d6c01a2f7..f99b34f7647b 100644
--- a/sound/soc/codecs/wm8996.c
+++ b/sound/soc/codecs/wm8996.c
@@ -416,7 +416,7 @@ static int wm8996_put_retune_mobile_enum(struct snd_kcontrol *kcontrol,
 	struct wm8996_priv *wm8996 = snd_soc_codec_get_drvdata(codec);
 	struct wm8996_pdata *pdata = &wm8996->pdata;
 	int block = wm8996_get_retune_mobile_block(kcontrol->id.name);
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 
 	if (block < 0)
 		return block;
diff --git a/sound/soc/codecs/wm9081.c b/sound/soc/codecs/wm9081.c
index ccb3b15139ad..363b3b667616 100644
--- a/sound/soc/codecs/wm9081.c
+++ b/sound/soc/codecs/wm9081.c
@@ -344,9 +344,9 @@ static int speaker_mode_get(struct snd_kcontrol *kcontrol,
 
 	reg = snd_soc_read(codec, WM9081_ANALOGUE_SPEAKER_2);
 	if (reg & WM9081_SPK_MODE)
-		ucontrol->value.integer.value[0] = 1;
+		ucontrol->value.enumerated.item[0] = 1;
 	else
-		ucontrol->value.integer.value[0] = 0;
+		ucontrol->value.enumerated.item[0] = 0;
 
 	return 0;
 }
@@ -365,7 +365,7 @@ static int speaker_mode_put(struct snd_kcontrol *kcontrol,
 	unsigned int reg2 = snd_soc_read(codec, WM9081_ANALOGUE_SPEAKER_2);
 
 	/* Are we changing anything? */
-	if (ucontrol->value.integer.value[0] ==
+	if (ucontrol->value.enumerated.item[0] ==
 	    ((reg2 & WM9081_SPK_MODE) != 0))
 		return 0;
 
@@ -373,7 +373,7 @@ static int speaker_mode_put(struct snd_kcontrol *kcontrol,
 	if (reg_pwr & WM9081_SPK_ENA)
 		return -EINVAL;
 
-	if (ucontrol->value.integer.value[0]) {
+	if (ucontrol->value.enumerated.item[0]) {
 		/* Class AB */
 		reg2 &= ~(WM9081_SPK_INV_MUTE | WM9081_OUT_SPK_CTRL);
 		reg2 |= WM9081_SPK_MODE;
diff --git a/sound/soc/codecs/wm9713.c b/sound/soc/codecs/wm9713.c
index 79e143625ac3..9849643ef809 100644
--- a/sound/soc/codecs/wm9713.c
+++ b/sound/soc/codecs/wm9713.c
@@ -1212,7 +1212,7 @@ static int wm9713_soc_probe(struct snd_soc_codec *codec)
 	if (IS_ERR(wm9713->ac97))
 		return PTR_ERR(wm9713->ac97);
 
-	regmap = devm_regmap_init_ac97(wm9713->ac97, &wm9713_regmap_config);
+	regmap = regmap_init_ac97(wm9713->ac97, &wm9713_regmap_config);
 	if (IS_ERR(regmap)) {
 		snd_soc_free_ac97_codec(wm9713->ac97);
 		return PTR_ERR(regmap);
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 33806d487b8a..b9195b9c2b05 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -586,7 +586,7 @@ static int wm_adsp_fw_get(struct snd_kcontrol *kcontrol,
 	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
 	struct wm_adsp *dsp = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.integer.value[0] = dsp[e->shift_l].fw;
+	ucontrol->value.enumerated.item[0] = dsp[e->shift_l].fw;
 
 	return 0;
 }
@@ -599,10 +599,10 @@ static int wm_adsp_fw_put(struct snd_kcontrol *kcontrol,
 	struct wm_adsp *dsp = snd_soc_codec_get_drvdata(codec);
 	int ret = 0;
 
-	if (ucontrol->value.integer.value[0] == dsp[e->shift_l].fw)
+	if (ucontrol->value.enumerated.item[0] == dsp[e->shift_l].fw)
 		return 0;
 
-	if (ucontrol->value.integer.value[0] >= WM_ADSP_NUM_FW)
+	if (ucontrol->value.enumerated.item[0] >= WM_ADSP_NUM_FW)
 		return -EINVAL;
 
 	mutex_lock(&dsp[e->shift_l].pwr_lock);
@@ -610,7 +610,7 @@ static int wm_adsp_fw_put(struct snd_kcontrol *kcontrol,
 	if (dsp[e->shift_l].running || dsp[e->shift_l].compr)
 		ret = -EBUSY;
 	else
-		dsp[e->shift_l].fw = ucontrol->value.integer.value[0];
+		dsp[e->shift_l].fw = ucontrol->value.enumerated.item[0];
 
 	mutex_unlock(&dsp[e->shift_l].pwr_lock);
 
diff --git a/sound/soc/dwc/designware_i2s.c b/sound/soc/dwc/designware_i2s.c
index ce664c239be3..bff258d7bcea 100644
--- a/sound/soc/dwc/designware_i2s.c
+++ b/sound/soc/dwc/designware_i2s.c
@@ -645,6 +645,8 @@ static int dw_i2s_probe(struct platform_device *pdev)
 
 	dev->dev = &pdev->dev;
 
+	dev->i2s_reg_comp1 = I2S_COMP_PARAM_1;
+	dev->i2s_reg_comp2 = I2S_COMP_PARAM_2;
 	if (pdata) {
 		dev->capability = pdata->cap;
 		clk_id = NULL;
@@ -652,9 +654,6 @@ static int dw_i2s_probe(struct platform_device *pdev)
 		if (dev->quirks & DW_I2S_QUIRK_COMP_REG_OFFSET) {
 			dev->i2s_reg_comp1 = pdata->i2s_reg_comp1;
 			dev->i2s_reg_comp2 = pdata->i2s_reg_comp2;
-		} else {
-			dev->i2s_reg_comp1 = I2S_COMP_PARAM_1;
-			dev->i2s_reg_comp2 = I2S_COMP_PARAM_2;
 		}
 		ret = dw_configure_dai_by_pd(dev, dw_i2s_dai, res, pdata);
 	} else {
diff --git a/sound/soc/fsl/imx-pcm-fiq.c b/sound/soc/fsl/imx-pcm-fiq.c
index 49d7513f429e..e63cd5ecfd8f 100644
--- a/sound/soc/fsl/imx-pcm-fiq.c
+++ b/sound/soc/fsl/imx-pcm-fiq.c
@@ -217,8 +217,8 @@ static int snd_imx_pcm_mmap(struct snd_pcm_substream *substream,
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	int ret;
 
-	ret = dma_mmap_writecombine(substream->pcm->card->dev, vma,
-		runtime->dma_area, runtime->dma_addr, runtime->dma_bytes);
+	ret = dma_mmap_wc(substream->pcm->card->dev, vma, runtime->dma_area,
+			  runtime->dma_addr, runtime->dma_bytes);
 
 	pr_debug("%s: ret: %d %p %pad 0x%08x\n", __func__, ret,
 			runtime->dma_area,
@@ -247,8 +247,7 @@ static int imx_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream)
 	buf->dev.type = SNDRV_DMA_TYPE_DEV;
 	buf->dev.dev = pcm->card->dev;
 	buf->private_data = NULL;
-	buf->area = dma_alloc_writecombine(pcm->card->dev, size,
-					   &buf->addr, GFP_KERNEL);
+	buf->area = dma_alloc_wc(pcm->card->dev, size, &buf->addr, GFP_KERNEL);
 	if (!buf->area)
 		return -ENOMEM;
 	buf->bytes = size;
@@ -330,8 +329,7 @@ static void imx_pcm_free(struct snd_pcm *pcm)
 		if (!buf->area)
 			continue;
 
-		dma_free_writecombine(pcm->card->dev, buf->bytes,
-				      buf->area, buf->addr);
+		dma_free_wc(pcm->card->dev, buf->bytes, buf->area, buf->addr);
 		buf->area = NULL;
 	}
 }
diff --git a/sound/soc/fsl/imx-spdif.c b/sound/soc/fsl/imx-spdif.c
index a407e833c612..fb896b2c9ba3 100644
--- a/sound/soc/fsl/imx-spdif.c
+++ b/sound/soc/fsl/imx-spdif.c
@@ -72,8 +72,6 @@ static int imx_spdif_audio_probe(struct platform_device *pdev)
 		goto end;
 	}
 
-	platform_set_drvdata(pdev, data);
-
 end:
 	of_node_put(spdif_np);
 
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index 1ded8811598e..2389ab47e25f 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -99,7 +99,7 @@ static int asoc_simple_card_hw_params(struct snd_pcm_substream *substream,
 		if (ret && ret != -ENOTSUPP)
 			goto err;
 	}
-
+	return 0;
 err:
 	return ret;
 }
diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig
index 803f95e40679..7d7c872c280d 100644
--- a/sound/soc/intel/Kconfig
+++ b/sound/soc/intel/Kconfig
@@ -30,11 +30,15 @@ config SND_SST_IPC_ACPI
 config SND_SOC_INTEL_SST
 	tristate
 	select SND_SOC_INTEL_SST_ACPI if ACPI
+	select SND_SOC_INTEL_SST_MATCH if ACPI
 	depends on (X86 || COMPILE_TEST)
 
 config SND_SOC_INTEL_SST_ACPI
 	tristate
 
+config SND_SOC_INTEL_SST_MATCH
+	tristate
+
 config SND_SOC_INTEL_HASWELL
 	tristate
 
@@ -57,7 +61,7 @@ config SND_SOC_INTEL_HASWELL_MACH
 config SND_SOC_INTEL_BYT_RT5640_MACH
 	tristate "ASoC Audio driver for Intel Baytrail with RT5640 codec"
 	depends on X86_INTEL_LPSS && I2C
-	depends on DW_DMAC_CORE=y && (SND_SOC_INTEL_BYTCR_RT5640_MACH = n)
+	depends on DW_DMAC_CORE=y && (SND_SST_IPC_ACPI = n)
 	select SND_SOC_INTEL_SST
 	select SND_SOC_INTEL_BAYTRAIL
 	select SND_SOC_RT5640
@@ -69,7 +73,7 @@ config SND_SOC_INTEL_BYT_RT5640_MACH
 config SND_SOC_INTEL_BYT_MAX98090_MACH
 	tristate "ASoC Audio driver for Intel Baytrail with MAX98090 codec"
 	depends on X86_INTEL_LPSS && I2C
-	depends on DW_DMAC_CORE=y
+	depends on DW_DMAC_CORE=y && (SND_SST_IPC_ACPI = n)
 	select SND_SOC_INTEL_SST
 	select SND_SOC_INTEL_BAYTRAIL
 	select SND_SOC_MAX98090
@@ -97,6 +101,7 @@ config SND_SOC_INTEL_BYTCR_RT5640_MACH
 	select SND_SOC_RT5640
 	select SND_SST_MFLD_PLATFORM
 	select SND_SST_IPC_ACPI
+	select SND_SOC_INTEL_SST_MATCH if ACPI
 	help
           This adds support for ASoC machine driver for Intel(R) Baytrail and Baytrail-CR
           platforms with RT5640 audio codec.
@@ -109,6 +114,7 @@ config SND_SOC_INTEL_BYTCR_RT5651_MACH
 	select SND_SOC_RT5651
 	select SND_SST_MFLD_PLATFORM
 	select SND_SST_IPC_ACPI
+	select SND_SOC_INTEL_SST_MATCH if ACPI
 	help
           This adds support for ASoC machine driver for Intel(R) Baytrail and Baytrail-CR
           platforms with RT5651 audio codec.
@@ -121,6 +127,7 @@ config SND_SOC_INTEL_CHT_BSW_RT5672_MACH
         select SND_SOC_RT5670
         select SND_SST_MFLD_PLATFORM
         select SND_SST_IPC_ACPI
+	select SND_SOC_INTEL_SST_MATCH if ACPI
         help
           This adds support for ASoC machine driver for Intel(R) Cherrytrail & Braswell
           platforms with RT5672 audio codec.
@@ -133,6 +140,7 @@ config SND_SOC_INTEL_CHT_BSW_RT5645_MACH
 	select SND_SOC_RT5645
 	select SND_SST_MFLD_PLATFORM
 	select SND_SST_IPC_ACPI
+	select SND_SOC_INTEL_SST_MATCH if ACPI
 	help
 	  This adds support for ASoC machine driver for Intel(R) Cherrytrail & Braswell
 	  platforms with RT5645/5650 audio codec.
@@ -145,6 +153,7 @@ config SND_SOC_INTEL_CHT_BSW_MAX98090_TI_MACH
 	select SND_SOC_TS3A227E
 	select SND_SST_MFLD_PLATFORM
 	select SND_SST_IPC_ACPI
+	select SND_SOC_INTEL_SST_MATCH if ACPI
 	help
       This adds support for ASoC machine driver for Intel(R) Cherrytrail & Braswell
       platforms with MAX98090 audio codec it also can support TI jack chip as aux device.
diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
index 55c33dc76ce4..52ed434cbca6 100644
--- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c
+++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
@@ -528,6 +528,7 @@ static struct snd_soc_dai_driver sst_platform_dai[] = {
 	.ops = &sst_compr_dai_ops,
 	.playback = {
 		.stream_name = "Compress Playback",
+		.channels_min = 1,
 	},
 },
 /* BE CPU  Dais */
diff --git a/sound/soc/intel/boards/cht_bsw_rt5645.c b/sound/soc/intel/boards/cht_bsw_rt5645.c
index 2d3afddb0a2e..a7b96a9a4e0e 100644
--- a/sound/soc/intel/boards/cht_bsw_rt5645.c
+++ b/sound/soc/intel/boards/cht_bsw_rt5645.c
@@ -367,8 +367,12 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	}
 	card->dev = &pdev->dev;
 	sprintf(codec_name, "i2c-%s:00", drv->acpi_card->codec_id);
+
 	/* set correct codec name */
-	strcpy((char *)card->dai_link[2].codec_name, codec_name);
+	for (i = 0; i < ARRAY_SIZE(cht_dailink); i++)
+		if (!strcmp(card->dai_link[i].codec_name, "i2c-10EC5645:00"))
+			card->dai_link[i].codec_name = kstrdup(codec_name, GFP_KERNEL);
+
 	snd_soc_card_set_drvdata(card, drv);
 	ret_val = devm_snd_soc_register_card(&pdev->dev, card);
 	if (ret_val) {
diff --git a/sound/soc/intel/boards/mfld_machine.c b/sound/soc/intel/boards/mfld_machine.c
index 49c09a0add79..34f46c72a0e2 100644
--- a/sound/soc/intel/boards/mfld_machine.c
+++ b/sound/soc/intel/boards/mfld_machine.c
@@ -94,7 +94,7 @@ static const struct soc_enum lo_enum =
 static int headset_get_switch(struct snd_kcontrol *kcontrol,
 	struct snd_ctl_elem_value *ucontrol)
 {
-	ucontrol->value.integer.value[0] = hs_switch;
+	ucontrol->value.enumerated.item[0] = hs_switch;
 	return 0;
 }
 
@@ -104,12 +104,12 @@ static int headset_set_switch(struct snd_kcontrol *kcontrol,
 	struct snd_soc_card *card = snd_kcontrol_chip(kcontrol);
 	struct snd_soc_dapm_context *dapm = &card->dapm;
 
-	if (ucontrol->value.integer.value[0] == hs_switch)
+	if (ucontrol->value.enumerated.item[0] == hs_switch)
 		return 0;
 
 	snd_soc_dapm_mutex_lock(dapm);
 
-	if (ucontrol->value.integer.value[0]) {
+	if (ucontrol->value.enumerated.item[0]) {
 		pr_debug("hs_set HS path\n");
 		snd_soc_dapm_enable_pin_unlocked(dapm, "Headphones");
 		snd_soc_dapm_disable_pin_unlocked(dapm, "EPOUT");
@@ -123,7 +123,7 @@ static int headset_set_switch(struct snd_kcontrol *kcontrol,
 
 	snd_soc_dapm_mutex_unlock(dapm);
 
-	hs_switch = ucontrol->value.integer.value[0];
+	hs_switch = ucontrol->value.enumerated.item[0];
 
 	return 0;
 }
@@ -148,7 +148,7 @@ static void lo_enable_out_pins(struct snd_soc_dapm_context *dapm)
 static int lo_get_switch(struct snd_kcontrol *kcontrol,
 	struct snd_ctl_elem_value *ucontrol)
 {
-	ucontrol->value.integer.value[0] = lo_dac;
+	ucontrol->value.enumerated.item[0] = lo_dac;
 	return 0;
 }
 
@@ -158,7 +158,7 @@ static int lo_set_switch(struct snd_kcontrol *kcontrol,
 	struct snd_soc_card *card = snd_kcontrol_chip(kcontrol);
 	struct snd_soc_dapm_context *dapm = &card->dapm;
 
-	if (ucontrol->value.integer.value[0] == lo_dac)
+	if (ucontrol->value.enumerated.item[0] == lo_dac)
 		return 0;
 
 	snd_soc_dapm_mutex_lock(dapm);
@@ -168,7 +168,7 @@ static int lo_set_switch(struct snd_kcontrol *kcontrol,
 	 */
 	lo_enable_out_pins(dapm);
 
-	switch (ucontrol->value.integer.value[0]) {
+	switch (ucontrol->value.enumerated.item[0]) {
 	case 0:
 		pr_debug("set vibra path\n");
 		snd_soc_dapm_disable_pin_unlocked(dapm, "VIB1OUT");
@@ -202,7 +202,7 @@ static int lo_set_switch(struct snd_kcontrol *kcontrol,
 
 	snd_soc_dapm_mutex_unlock(dapm);
 
-	lo_dac = ucontrol->value.integer.value[0];
+	lo_dac = ucontrol->value.enumerated.item[0];
 	return 0;
 }
 
diff --git a/sound/soc/intel/boards/skl_rt286.c b/sound/soc/intel/boards/skl_rt286.c
index 7396ddb427d8..2cbcbe412661 100644
--- a/sound/soc/intel/boards/skl_rt286.c
+++ b/sound/soc/intel/boards/skl_rt286.c
@@ -212,7 +212,10 @@ static int skylake_dmic_fixup(struct snd_soc_pcm_runtime *rtd,
 {
 	struct snd_interval *channels = hw_param_interval(params,
 						SNDRV_PCM_HW_PARAM_CHANNELS);
-	channels->min = channels->max = 4;
+	if (params_channels(params) == 2)
+		channels->min = channels->max = 2;
+	else
+		channels->min = channels->max = 4;
 
 	return 0;
 }
diff --git a/sound/soc/intel/common/Makefile b/sound/soc/intel/common/Makefile
index 668fdeee195e..fbbb25c2ceed 100644
--- a/sound/soc/intel/common/Makefile
+++ b/sound/soc/intel/common/Makefile
@@ -1,13 +1,10 @@
 snd-soc-sst-dsp-objs := sst-dsp.o
-ifneq ($(CONFIG_SND_SST_IPC_ACPI),)
-snd-soc-sst-acpi-objs := sst-match-acpi.o
-else
-snd-soc-sst-acpi-objs := sst-acpi.o sst-match-acpi.o
-endif
-
+snd-soc-sst-acpi-objs := sst-acpi.o
+snd-soc-sst-match-objs := sst-match-acpi.o
 snd-soc-sst-ipc-objs := sst-ipc.o
 
 snd-soc-sst-dsp-$(CONFIG_DW_DMAC_CORE) += sst-firmware.o
 
 obj-$(CONFIG_SND_SOC_INTEL_SST) += snd-soc-sst-dsp.o snd-soc-sst-ipc.o
 obj-$(CONFIG_SND_SOC_INTEL_SST_ACPI) += snd-soc-sst-acpi.o
+obj-$(CONFIG_SND_SOC_INTEL_SST_MATCH) += snd-soc-sst-match.o
diff --git a/sound/soc/intel/common/sst-acpi.c b/sound/soc/intel/common/sst-acpi.c
index 7a85c576dad3..2c5eda14d510 100644
--- a/sound/soc/intel/common/sst-acpi.c
+++ b/sound/soc/intel/common/sst-acpi.c
@@ -215,6 +215,7 @@ static struct sst_acpi_desc sst_acpi_broadwell_desc = {
 	.dma_size = SST_LPT_DSP_DMA_SIZE,
 };
 
+#if !IS_ENABLED(CONFIG_SND_SST_IPC_ACPI)
 static struct sst_acpi_mach baytrail_machines[] = {
 	{ "10EC5640", "byt-rt5640", "intel/fw_sst_0f28.bin-48kHz_i2s_master", NULL, NULL, NULL },
 	{ "193C9890", "byt-max98090", "intel/fw_sst_0f28.bin-48kHz_i2s_master", NULL, NULL, NULL },
@@ -231,11 +232,14 @@ static struct sst_acpi_desc sst_acpi_baytrail_desc = {
 	.sst_id = SST_DEV_ID_BYT,
 	.resindex_dma_base = -1,
 };
+#endif
 
 static const struct acpi_device_id sst_acpi_match[] = {
 	{ "INT33C8", (unsigned long)&sst_acpi_haswell_desc },
 	{ "INT3438", (unsigned long)&sst_acpi_broadwell_desc },
+#if !IS_ENABLED(CONFIG_SND_SST_IPC_ACPI)
 	{ "80860F28", (unsigned long)&sst_acpi_baytrail_desc },
+#endif
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, sst_acpi_match);
diff --git a/sound/soc/intel/common/sst-match-acpi.c b/sound/soc/intel/common/sst-match-acpi.c
index dd077e116d25..3b4539d21492 100644
--- a/sound/soc/intel/common/sst-match-acpi.c
+++ b/sound/soc/intel/common/sst-match-acpi.c
@@ -41,3 +41,6 @@ struct sst_acpi_mach *sst_acpi_find_machine(struct sst_acpi_mach *machines)
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(sst_acpi_find_machine);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Intel Common ACPI Match module");
diff --git a/sound/soc/intel/skylake/skl-messages.c b/sound/soc/intel/skylake/skl-messages.c
index de6dac496a0d..4629372d7c8e 100644
--- a/sound/soc/intel/skylake/skl-messages.c
+++ b/sound/soc/intel/skylake/skl-messages.c
@@ -688,14 +688,14 @@ int skl_unbind_modules(struct skl_sst *ctx,
 	/* get src queue index */
 	src_index = skl_get_queue_index(src_mcfg->m_out_pin, dst_id, out_max);
 	if (src_index < 0)
-		return -EINVAL;
+		return 0;
 
 	msg.src_queue = src_index;
 
 	/* get dst queue index */
 	dst_index  = skl_get_queue_index(dst_mcfg->m_in_pin, src_id, in_max);
 	if (dst_index < 0)
-		return -EINVAL;
+		return 0;
 
 	msg.dst_queue = dst_index;
 
@@ -747,7 +747,7 @@ int skl_bind_modules(struct skl_sst *ctx,
 
 	skl_dump_bind_info(ctx, src_mcfg, dst_mcfg);
 
-	if (src_mcfg->m_state < SKL_MODULE_INIT_DONE &&
+	if (src_mcfg->m_state < SKL_MODULE_INIT_DONE ||
 		dst_mcfg->m_state < SKL_MODULE_INIT_DONE)
 		return 0;
 
diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c
index f3553258091a..b6e6b61d10ec 100644
--- a/sound/soc/intel/skylake/skl-pcm.c
+++ b/sound/soc/intel/skylake/skl-pcm.c
@@ -863,6 +863,7 @@ static int skl_get_delay_from_lpib(struct hdac_ext_bus *ebus,
 		else
 			delay += hstream->bufsize;
 	}
+	delay = (hstream->bufsize == delay) ? 0 : delay;
 
 	if (delay >= hstream->period_bytes) {
 		dev_info(bus->dev,
diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c
index 4624556f486d..5a4837dcfce3 100644
--- a/sound/soc/intel/skylake/skl-topology.c
+++ b/sound/soc/intel/skylake/skl-topology.c
@@ -54,12 +54,9 @@ static int is_skl_dsp_widget_type(struct snd_soc_dapm_widget *w)
 
 /*
  * Each pipelines needs memory to be allocated. Check if we have free memory
- * from available pool. Then only add this to pool
- * This is freed when pipe is deleted
- * Note: DSP does actual memory management we only keep track for complete
- * pool
+ * from available pool.
  */
-static bool skl_tplg_alloc_pipe_mem(struct skl *skl,
+static bool skl_is_pipe_mem_avail(struct skl *skl,
 				struct skl_module_cfg *mconfig)
 {
 	struct skl_sst *ctx = skl->skl_sst;
@@ -74,10 +71,20 @@ static bool skl_tplg_alloc_pipe_mem(struct skl *skl,
 				"exceeds ppl memory available %d mem %d\n",
 				skl->resource.max_mem, skl->resource.mem);
 		return false;
+	} else {
+		return true;
 	}
+}
 
+/*
+ * Add the mem to the mem pool. This is freed when pipe is deleted.
+ * Note: DSP does actual memory management we only keep track for complete
+ * pool
+ */
+static void skl_tplg_alloc_pipe_mem(struct skl *skl,
+				struct skl_module_cfg *mconfig)
+{
 	skl->resource.mem += mconfig->pipe->memory_pages;
-	return true;
 }
 
 /*
@@ -85,10 +92,10 @@ static bool skl_tplg_alloc_pipe_mem(struct skl *skl,
  * quantified in MCPS (Million Clocks Per Second) required for module/pipe
  *
  * Each pipelines needs mcps to be allocated. Check if we have mcps for this
- * pipe. This adds the mcps to driver counter
- * This is removed on pipeline delete
+ * pipe.
  */
-static bool skl_tplg_alloc_pipe_mcps(struct skl *skl,
+
+static bool skl_is_pipe_mcps_avail(struct skl *skl,
 				struct skl_module_cfg *mconfig)
 {
 	struct skl_sst *ctx = skl->skl_sst;
@@ -98,13 +105,18 @@ static bool skl_tplg_alloc_pipe_mcps(struct skl *skl,
 			"%s: module_id %d instance %d\n", __func__,
 			mconfig->id.module_id, mconfig->id.instance_id);
 		dev_err(ctx->dev,
-			"exceeds ppl memory available %d > mem %d\n",
+			"exceeds ppl mcps available %d > mem %d\n",
 			skl->resource.max_mcps, skl->resource.mcps);
 		return false;
+	} else {
+		return true;
 	}
+}
 
+static void skl_tplg_alloc_pipe_mcps(struct skl *skl,
+				struct skl_module_cfg *mconfig)
+{
 	skl->resource.mcps += mconfig->mcps;
-	return true;
 }
 
 /*
@@ -411,7 +423,7 @@ skl_tplg_init_pipe_modules(struct skl *skl, struct skl_pipe *pipe)
 		mconfig = w->priv;
 
 		/* check resource available */
-		if (!skl_tplg_alloc_pipe_mcps(skl, mconfig))
+		if (!skl_is_pipe_mcps_avail(skl, mconfig))
 			return -ENOMEM;
 
 		if (mconfig->is_loadable && ctx->dsp->fw_ops.load_mod) {
@@ -435,6 +447,7 @@ skl_tplg_init_pipe_modules(struct skl *skl, struct skl_pipe *pipe)
 		ret = skl_tplg_set_module_params(w, ctx);
 		if (ret < 0)
 			return ret;
+		skl_tplg_alloc_pipe_mcps(skl, mconfig);
 	}
 
 	return 0;
@@ -477,10 +490,10 @@ static int skl_tplg_mixer_dapm_pre_pmu_event(struct snd_soc_dapm_widget *w,
 	struct skl_sst *ctx = skl->skl_sst;
 
 	/* check resource available */
-	if (!skl_tplg_alloc_pipe_mcps(skl, mconfig))
+	if (!skl_is_pipe_mcps_avail(skl, mconfig))
 		return -EBUSY;
 
-	if (!skl_tplg_alloc_pipe_mem(skl, mconfig))
+	if (!skl_is_pipe_mem_avail(skl, mconfig))
 		return -ENOMEM;
 
 	/*
@@ -526,11 +539,15 @@ static int skl_tplg_mixer_dapm_pre_pmu_event(struct snd_soc_dapm_widget *w,
 		src_module = dst_module;
 	}
 
+	skl_tplg_alloc_pipe_mem(skl, mconfig);
+	skl_tplg_alloc_pipe_mcps(skl, mconfig);
+
 	return 0;
 }
 
 static int skl_tplg_bind_sinks(struct snd_soc_dapm_widget *w,
 				struct skl *skl,
+				struct snd_soc_dapm_widget *src_w,
 				struct skl_module_cfg *src_mconfig)
 {
 	struct snd_soc_dapm_path *p;
@@ -547,6 +564,10 @@ static int skl_tplg_bind_sinks(struct snd_soc_dapm_widget *w,
 		dev_dbg(ctx->dev, "%s: sink widget=%s\n", __func__, p->sink->name);
 
 		next_sink = p->sink;
+
+		if (!is_skl_dsp_widget_type(p->sink))
+			return skl_tplg_bind_sinks(p->sink, skl, src_w, src_mconfig);
+
 		/*
 		 * here we will check widgets in sink pipelines, so that
 		 * can be any widgets type and we are only interested if
@@ -576,7 +597,7 @@ static int skl_tplg_bind_sinks(struct snd_soc_dapm_widget *w,
 	}
 
 	if (!sink)
-		return skl_tplg_bind_sinks(next_sink, skl, src_mconfig);
+		return skl_tplg_bind_sinks(next_sink, skl, src_w, src_mconfig);
 
 	return 0;
 }
@@ -605,7 +626,7 @@ static int skl_tplg_pga_dapm_pre_pmu_event(struct snd_soc_dapm_widget *w,
 	 * if sink is not started, start sink pipe first, then start
 	 * this pipe
 	 */
-	ret = skl_tplg_bind_sinks(w, skl, src_mconfig);
+	ret = skl_tplg_bind_sinks(w, skl, w, src_mconfig);
 	if (ret)
 		return ret;
 
@@ -773,10 +794,7 @@ static int skl_tplg_mixer_dapm_post_pmd_event(struct snd_soc_dapm_widget *w,
 			continue;
 		}
 
-		ret = skl_unbind_modules(ctx, src_module, dst_module);
-		if (ret < 0)
-			return ret;
-
+		skl_unbind_modules(ctx, src_module, dst_module);
 		src_module = dst_module;
 	}
 
@@ -814,9 +832,6 @@ static int skl_tplg_pga_dapm_post_pmd_event(struct snd_soc_dapm_widget *w,
 			 * This is a connecter and if path is found that means
 			 * unbind between source and sink has not happened yet
 			 */
-			ret = skl_stop_pipe(ctx, sink_mconfig->pipe);
-			if (ret < 0)
-				return ret;
 			ret = skl_unbind_modules(ctx, src_mconfig,
 							sink_mconfig);
 		}
@@ -842,6 +857,12 @@ static int skl_tplg_vmixer_event(struct snd_soc_dapm_widget *w,
 	case SND_SOC_DAPM_PRE_PMU:
 		return skl_tplg_mixer_dapm_pre_pmu_event(w, skl);
 
+	case SND_SOC_DAPM_POST_PMU:
+		return skl_tplg_mixer_dapm_post_pmu_event(w, skl);
+
+	case SND_SOC_DAPM_PRE_PMD:
+		return skl_tplg_mixer_dapm_pre_pmd_event(w, skl);
+
 	case SND_SOC_DAPM_POST_PMD:
 		return skl_tplg_mixer_dapm_post_pmd_event(w, skl);
 	}
@@ -916,6 +937,13 @@ static int skl_tplg_tlv_control_get(struct snd_kcontrol *kcontrol,
 		skl_get_module_params(skl->skl_sst, (u32 *)bc->params,
 				      bc->max, bc->param_id, mconfig);
 
+	/* decrement size for TLV header */
+	size -= 2 * sizeof(u32);
+
+	/* check size as we don't want to send kernel data */
+	if (size > bc->max)
+		size = bc->max;
+
 	if (bc->params) {
 		if (copy_to_user(data, &bc->param_id, sizeof(u32)))
 			return -EFAULT;
@@ -950,7 +978,7 @@ static int skl_tplg_tlv_control_set(struct snd_kcontrol *kcontrol,
 				return -EFAULT;
 		} else {
 			if (copy_from_user(ac->params,
-					   data + 2 * sizeof(u32), size))
+					   data + 2, size))
 				return -EFAULT;
 		}
 
@@ -1510,6 +1538,7 @@ int skl_tplg_init(struct snd_soc_platform *platform, struct hdac_ext_bus *ebus)
 					&skl_tplg_ops, fw, 0);
 	if (ret < 0) {
 		dev_err(bus->dev, "tplg component load failed%d\n", ret);
+		release_firmware(fw);
 		return -EINVAL;
 	}
 
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index 443a15de94b5..092705e73db4 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -614,8 +614,6 @@ static int skl_probe(struct pci_dev *pci,
 		goto out_unregister;
 
 	/*configure PM */
-	pm_runtime_set_autosuspend_delay(bus->dev, SKL_SUSPEND_DELAY);
-	pm_runtime_use_autosuspend(bus->dev);
 	pm_runtime_put_noidle(bus->dev);
 	pm_runtime_allow(bus->dev);
 
diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig
index 15c04e2eae34..976967675387 100644
--- a/sound/soc/mediatek/Kconfig
+++ b/sound/soc/mediatek/Kconfig
@@ -9,7 +9,7 @@ config SND_SOC_MEDIATEK
 
 config SND_SOC_MT8173_MAX98090
 	tristate "ASoC Audio driver for MT8173 with MAX98090 codec"
-	depends on SND_SOC_MEDIATEK
+	depends on SND_SOC_MEDIATEK && I2C
 	select SND_SOC_MAX98090
 	help
 	  This adds ASoC driver for Mediatek MT8173 boards
@@ -19,7 +19,7 @@ config SND_SOC_MT8173_MAX98090
 
 config SND_SOC_MT8173_RT5650_RT5676
 	tristate "ASoC Audio driver for MT8173 with RT5650 RT5676 codecs"
-	depends on SND_SOC_MEDIATEK
+	depends on SND_SOC_MEDIATEK && I2C
 	select SND_SOC_RT5645
 	select SND_SOC_RT5677
 	help
diff --git a/sound/soc/mxs/mxs-saif.c b/sound/soc/mxs/mxs-saif.c
index c866ade28ad0..a6c7b8d87cd2 100644
--- a/sound/soc/mxs/mxs-saif.c
+++ b/sound/soc/mxs/mxs-saif.c
@@ -381,9 +381,19 @@ static int mxs_saif_startup(struct snd_pcm_substream *substream,
 	__raw_writel(BM_SAIF_CTRL_CLKGATE,
 		saif->base + SAIF_CTRL + MXS_CLR_ADDR);
 
+	clk_prepare(saif->clk);
+
 	return 0;
 }
 
+static void mxs_saif_shutdown(struct snd_pcm_substream *substream,
+			      struct snd_soc_dai *cpu_dai)
+{
+	struct mxs_saif *saif = snd_soc_dai_get_drvdata(cpu_dai);
+
+	clk_unprepare(saif->clk);
+}
+
 /*
  * Should only be called when port is inactive.
  * although can be called multiple times by upper layers.
@@ -424,8 +434,6 @@ static int mxs_saif_hw_params(struct snd_pcm_substream *substream,
 		return ret;
 	}
 
-	/* prepare clk in hw_param, enable in trigger */
-	clk_prepare(saif->clk);
 	if (saif != master_saif) {
 		/*
 		* Set an initial clock rate for the saif internal logic to work
@@ -611,6 +619,7 @@ static int mxs_saif_trigger(struct snd_pcm_substream *substream, int cmd,
 
 static const struct snd_soc_dai_ops mxs_saif_dai_ops = {
 	.startup = mxs_saif_startup,
+	.shutdown = mxs_saif_shutdown,
 	.trigger = mxs_saif_trigger,
 	.prepare = mxs_saif_prepare,
 	.hw_params = mxs_saif_hw_params,
diff --git a/sound/soc/nuc900/nuc900-pcm.c b/sound/soc/nuc900/nuc900-pcm.c
index e09326158bc2..2cca055fd806 100644
--- a/sound/soc/nuc900/nuc900-pcm.c
+++ b/sound/soc/nuc900/nuc900-pcm.c
@@ -267,10 +267,8 @@ static int nuc900_dma_mmap(struct snd_pcm_substream *substream,
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 
-	return dma_mmap_writecombine(substream->pcm->card->dev, vma,
-					runtime->dma_area,
-					runtime->dma_addr,
-					runtime->dma_bytes);
+	return dma_mmap_wc(substream->pcm->card->dev, vma, runtime->dma_area,
+			   runtime->dma_addr, runtime->dma_bytes);
 }
 
 static struct snd_pcm_ops nuc900_dma_ops = {
diff --git a/sound/soc/omap/n810.c b/sound/soc/omap/n810.c
index 190f868e78b2..fdecb7043174 100644
--- a/sound/soc/omap/n810.c
+++ b/sound/soc/omap/n810.c
@@ -133,7 +133,7 @@ static struct snd_soc_ops n810_ops = {
 static int n810_get_spk(struct snd_kcontrol *kcontrol,
 			struct snd_ctl_elem_value *ucontrol)
 {
-	ucontrol->value.integer.value[0] = n810_spk_func;
+	ucontrol->value.enumerated.item[0] = n810_spk_func;
 
 	return 0;
 }
@@ -143,10 +143,10 @@ static int n810_set_spk(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_card *card =  snd_kcontrol_chip(kcontrol);
 
-	if (n810_spk_func == ucontrol->value.integer.value[0])
+	if (n810_spk_func == ucontrol->value.enumerated.item[0])
 		return 0;
 
-	n810_spk_func = ucontrol->value.integer.value[0];
+	n810_spk_func = ucontrol->value.enumerated.item[0];
 	n810_ext_control(&card->dapm);
 
 	return 1;
@@ -155,7 +155,7 @@ static int n810_set_spk(struct snd_kcontrol *kcontrol,
 static int n810_get_jack(struct snd_kcontrol *kcontrol,
 			 struct snd_ctl_elem_value *ucontrol)
 {
-	ucontrol->value.integer.value[0] = n810_jack_func;
+	ucontrol->value.enumerated.item[0] = n810_jack_func;
 
 	return 0;
 }
@@ -165,10 +165,10 @@ static int n810_set_jack(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_card *card =  snd_kcontrol_chip(kcontrol);
 
-	if (n810_jack_func == ucontrol->value.integer.value[0])
+	if (n810_jack_func == ucontrol->value.enumerated.item[0])
 		return 0;
 
-	n810_jack_func = ucontrol->value.integer.value[0];
+	n810_jack_func = ucontrol->value.enumerated.item[0];
 	n810_ext_control(&card->dapm);
 
 	return 1;
@@ -177,7 +177,7 @@ static int n810_set_jack(struct snd_kcontrol *kcontrol,
 static int n810_get_input(struct snd_kcontrol *kcontrol,
 			  struct snd_ctl_elem_value *ucontrol)
 {
-	ucontrol->value.integer.value[0] = n810_dmic_func;
+	ucontrol->value.enumerated.item[0] = n810_dmic_func;
 
 	return 0;
 }
@@ -187,10 +187,10 @@ static int n810_set_input(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_card *card =  snd_kcontrol_chip(kcontrol);
 
-	if (n810_dmic_func == ucontrol->value.integer.value[0])
+	if (n810_dmic_func == ucontrol->value.enumerated.item[0])
 		return 0;
 
-	n810_dmic_func = ucontrol->value.integer.value[0];
+	n810_dmic_func = ucontrol->value.enumerated.item[0];
 	n810_ext_control(&card->dapm);
 
 	return 1;
diff --git a/sound/soc/omap/omap-pcm.c b/sound/soc/omap/omap-pcm.c
index 6bb623a2a4df..99381a27295b 100644
--- a/sound/soc/omap/omap-pcm.c
+++ b/sound/soc/omap/omap-pcm.c
@@ -156,10 +156,8 @@ static int omap_pcm_mmap(struct snd_pcm_substream *substream,
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 
-	return dma_mmap_writecombine(substream->pcm->card->dev, vma,
-				     runtime->dma_area,
-				     runtime->dma_addr,
-				     runtime->dma_bytes);
+	return dma_mmap_wc(substream->pcm->card->dev, vma, runtime->dma_area,
+			   runtime->dma_addr, runtime->dma_bytes);
 }
 
 static struct snd_pcm_ops omap_pcm_ops = {
@@ -183,8 +181,7 @@ static int omap_pcm_preallocate_dma_buffer(struct snd_pcm *pcm,
 	buf->dev.type = SNDRV_DMA_TYPE_DEV;
 	buf->dev.dev = pcm->card->dev;
 	buf->private_data = NULL;
-	buf->area = dma_alloc_writecombine(pcm->card->dev, size,
-					   &buf->addr, GFP_KERNEL);
+	buf->area = dma_alloc_wc(pcm->card->dev, size, &buf->addr, GFP_KERNEL);
 	if (!buf->area)
 		return -ENOMEM;
 
@@ -207,8 +204,7 @@ static void omap_pcm_free_dma_buffers(struct snd_pcm *pcm)
 		if (!buf->area)
 			continue;
 
-		dma_free_writecombine(pcm->card->dev, buf->bytes,
-				      buf->area, buf->addr);
+		dma_free_wc(pcm->card->dev, buf->bytes, buf->area, buf->addr);
 		buf->area = NULL;
 	}
 }
diff --git a/sound/soc/omap/rx51.c b/sound/soc/omap/rx51.c
index 5e21f08579d8..54949242bc70 100644
--- a/sound/soc/omap/rx51.c
+++ b/sound/soc/omap/rx51.c
@@ -132,7 +132,7 @@ static struct snd_soc_ops rx51_ops = {
 static int rx51_get_spk(struct snd_kcontrol *kcontrol,
 			struct snd_ctl_elem_value *ucontrol)
 {
-	ucontrol->value.integer.value[0] = rx51_spk_func;
+	ucontrol->value.enumerated.item[0] = rx51_spk_func;
 
 	return 0;
 }
@@ -142,10 +142,10 @@ static int rx51_set_spk(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_card *card = snd_kcontrol_chip(kcontrol);
 
-	if (rx51_spk_func == ucontrol->value.integer.value[0])
+	if (rx51_spk_func == ucontrol->value.enumerated.item[0])
 		return 0;
 
-	rx51_spk_func = ucontrol->value.integer.value[0];
+	rx51_spk_func = ucontrol->value.enumerated.item[0];
 	rx51_ext_control(&card->dapm);
 
 	return 1;
@@ -180,7 +180,7 @@ static int rx51_hp_event(struct snd_soc_dapm_widget *w,
 static int rx51_get_input(struct snd_kcontrol *kcontrol,
 			  struct snd_ctl_elem_value *ucontrol)
 {
-	ucontrol->value.integer.value[0] = rx51_dmic_func;
+	ucontrol->value.enumerated.item[0] = rx51_dmic_func;
 
 	return 0;
 }
@@ -190,10 +190,10 @@ static int rx51_set_input(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_card *card = snd_kcontrol_chip(kcontrol);
 
-	if (rx51_dmic_func == ucontrol->value.integer.value[0])
+	if (rx51_dmic_func == ucontrol->value.enumerated.item[0])
 		return 0;
 
-	rx51_dmic_func = ucontrol->value.integer.value[0];
+	rx51_dmic_func = ucontrol->value.enumerated.item[0];
 	rx51_ext_control(&card->dapm);
 
 	return 1;
@@ -202,7 +202,7 @@ static int rx51_set_input(struct snd_kcontrol *kcontrol,
 static int rx51_get_jack(struct snd_kcontrol *kcontrol,
 			 struct snd_ctl_elem_value *ucontrol)
 {
-	ucontrol->value.integer.value[0] = rx51_jack_func;
+	ucontrol->value.enumerated.item[0] = rx51_jack_func;
 
 	return 0;
 }
@@ -212,10 +212,10 @@ static int rx51_set_jack(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_card *card = snd_kcontrol_chip(kcontrol);
 
-	if (rx51_jack_func == ucontrol->value.integer.value[0])
+	if (rx51_jack_func == ucontrol->value.enumerated.item[0])
 		return 0;
 
-	rx51_jack_func = ucontrol->value.integer.value[0];
+	rx51_jack_func = ucontrol->value.enumerated.item[0];
 	rx51_ext_control(&card->dapm);
 
 	return 1;
diff --git a/sound/soc/pxa/corgi.c b/sound/soc/pxa/corgi.c
index c97dc13d3608..dcbb7aa9830c 100644
--- a/sound/soc/pxa/corgi.c
+++ b/sound/soc/pxa/corgi.c
@@ -163,7 +163,7 @@ static struct snd_soc_ops corgi_ops = {
 static int corgi_get_jack(struct snd_kcontrol *kcontrol,
 	struct snd_ctl_elem_value *ucontrol)
 {
-	ucontrol->value.integer.value[0] = corgi_jack_func;
+	ucontrol->value.enumerated.item[0] = corgi_jack_func;
 	return 0;
 }
 
@@ -172,10 +172,10 @@ static int corgi_set_jack(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_card *card = snd_kcontrol_chip(kcontrol);
 
-	if (corgi_jack_func == ucontrol->value.integer.value[0])
+	if (corgi_jack_func == ucontrol->value.enumerated.item[0])
 		return 0;
 
-	corgi_jack_func = ucontrol->value.integer.value[0];
+	corgi_jack_func = ucontrol->value.enumerated.item[0];
 	corgi_ext_control(&card->dapm);
 	return 1;
 }
@@ -183,7 +183,7 @@ static int corgi_set_jack(struct snd_kcontrol *kcontrol,
 static int corgi_get_spk(struct snd_kcontrol *kcontrol,
 	struct snd_ctl_elem_value *ucontrol)
 {
-	ucontrol->value.integer.value[0] = corgi_spk_func;
+	ucontrol->value.enumerated.item[0] = corgi_spk_func;
 	return 0;
 }
 
@@ -192,10 +192,10 @@ static int corgi_set_spk(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_card *card =  snd_kcontrol_chip(kcontrol);
 
-	if (corgi_spk_func == ucontrol->value.integer.value[0])
+	if (corgi_spk_func == ucontrol->value.enumerated.item[0])
 		return 0;
 
-	corgi_spk_func = ucontrol->value.integer.value[0];
+	corgi_spk_func = ucontrol->value.enumerated.item[0];
 	corgi_ext_control(&card->dapm);
 	return 1;
 }
diff --git a/sound/soc/pxa/magician.c b/sound/soc/pxa/magician.c
index 241d0be42d7a..62b8377a9d2b 100644
--- a/sound/soc/pxa/magician.c
+++ b/sound/soc/pxa/magician.c
@@ -308,17 +308,17 @@ static int magician_set_spk(struct snd_kcontrol *kcontrol,
 static int magician_get_input(struct snd_kcontrol *kcontrol,
 			      struct snd_ctl_elem_value *ucontrol)
 {
-	ucontrol->value.integer.value[0] = magician_in_sel;
+	ucontrol->value.enumerated.item[0] = magician_in_sel;
 	return 0;
 }
 
 static int magician_set_input(struct snd_kcontrol *kcontrol,
 			      struct snd_ctl_elem_value *ucontrol)
 {
-	if (magician_in_sel == ucontrol->value.integer.value[0])
+	if (magician_in_sel == ucontrol->value.enumerated.item[0])
 		return 0;
 
-	magician_in_sel = ucontrol->value.integer.value[0];
+	magician_in_sel = ucontrol->value.enumerated.item[0];
 
 	switch (magician_in_sel) {
 	case MAGICIAN_MIC:
diff --git a/sound/soc/pxa/poodle.c b/sound/soc/pxa/poodle.c
index 84d0e2e50808..4b3b714f5ee7 100644
--- a/sound/soc/pxa/poodle.c
+++ b/sound/soc/pxa/poodle.c
@@ -138,7 +138,7 @@ static struct snd_soc_ops poodle_ops = {
 static int poodle_get_jack(struct snd_kcontrol *kcontrol,
 	struct snd_ctl_elem_value *ucontrol)
 {
-	ucontrol->value.integer.value[0] = poodle_jack_func;
+	ucontrol->value.enumerated.item[0] = poodle_jack_func;
 	return 0;
 }
 
@@ -147,10 +147,10 @@ static int poodle_set_jack(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_card *card =  snd_kcontrol_chip(kcontrol);
 
-	if (poodle_jack_func == ucontrol->value.integer.value[0])
+	if (poodle_jack_func == ucontrol->value.enumerated.item[0])
 		return 0;
 
-	poodle_jack_func = ucontrol->value.integer.value[0];
+	poodle_jack_func = ucontrol->value.enumerated.item[0];
 	poodle_ext_control(&card->dapm);
 	return 1;
 }
@@ -158,7 +158,7 @@ static int poodle_set_jack(struct snd_kcontrol *kcontrol,
 static int poodle_get_spk(struct snd_kcontrol *kcontrol,
 	struct snd_ctl_elem_value *ucontrol)
 {
-	ucontrol->value.integer.value[0] = poodle_spk_func;
+	ucontrol->value.enumerated.item[0] = poodle_spk_func;
 	return 0;
 }
 
@@ -167,10 +167,10 @@ static int poodle_set_spk(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_card *card =  snd_kcontrol_chip(kcontrol);
 
-	if (poodle_spk_func == ucontrol->value.integer.value[0])
+	if (poodle_spk_func == ucontrol->value.enumerated.item[0])
 		return 0;
 
-	poodle_spk_func = ucontrol->value.integer.value[0];
+	poodle_spk_func = ucontrol->value.enumerated.item[0];
 	poodle_ext_control(&card->dapm);
 	return 1;
 }
diff --git a/sound/soc/pxa/spitz.c b/sound/soc/pxa/spitz.c
index b00222620fd0..0e02634c8b7f 100644
--- a/sound/soc/pxa/spitz.c
+++ b/sound/soc/pxa/spitz.c
@@ -164,7 +164,7 @@ static struct snd_soc_ops spitz_ops = {
 static int spitz_get_jack(struct snd_kcontrol *kcontrol,
 	struct snd_ctl_elem_value *ucontrol)
 {
-	ucontrol->value.integer.value[0] = spitz_jack_func;
+	ucontrol->value.enumerated.item[0] = spitz_jack_func;
 	return 0;
 }
 
@@ -173,10 +173,10 @@ static int spitz_set_jack(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_card *card = snd_kcontrol_chip(kcontrol);
 
-	if (spitz_jack_func == ucontrol->value.integer.value[0])
+	if (spitz_jack_func == ucontrol->value.enumerated.item[0])
 		return 0;
 
-	spitz_jack_func = ucontrol->value.integer.value[0];
+	spitz_jack_func = ucontrol->value.enumerated.item[0];
 	spitz_ext_control(&card->dapm);
 	return 1;
 }
@@ -184,7 +184,7 @@ static int spitz_set_jack(struct snd_kcontrol *kcontrol,
 static int spitz_get_spk(struct snd_kcontrol *kcontrol,
 	struct snd_ctl_elem_value *ucontrol)
 {
-	ucontrol->value.integer.value[0] = spitz_spk_func;
+	ucontrol->value.enumerated.item[0] = spitz_spk_func;
 	return 0;
 }
 
@@ -193,10 +193,10 @@ static int spitz_set_spk(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_card *card = snd_kcontrol_chip(kcontrol);
 
-	if (spitz_spk_func == ucontrol->value.integer.value[0])
+	if (spitz_spk_func == ucontrol->value.enumerated.item[0])
 		return 0;
 
-	spitz_spk_func = ucontrol->value.integer.value[0];
+	spitz_spk_func = ucontrol->value.enumerated.item[0];
 	spitz_ext_control(&card->dapm);
 	return 1;
 }
diff --git a/sound/soc/pxa/tosa.c b/sound/soc/pxa/tosa.c
index 49518dd642aa..c508f024ecfb 100644
--- a/sound/soc/pxa/tosa.c
+++ b/sound/soc/pxa/tosa.c
@@ -95,7 +95,7 @@ static struct snd_soc_ops tosa_ops = {
 static int tosa_get_jack(struct snd_kcontrol *kcontrol,
 	struct snd_ctl_elem_value *ucontrol)
 {
-	ucontrol->value.integer.value[0] = tosa_jack_func;
+	ucontrol->value.enumerated.item[0] = tosa_jack_func;
 	return 0;
 }
 
@@ -104,10 +104,10 @@ static int tosa_set_jack(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_card *card = snd_kcontrol_chip(kcontrol);
 
-	if (tosa_jack_func == ucontrol->value.integer.value[0])
+	if (tosa_jack_func == ucontrol->value.enumerated.item[0])
 		return 0;
 
-	tosa_jack_func = ucontrol->value.integer.value[0];
+	tosa_jack_func = ucontrol->value.enumerated.item[0];
 	tosa_ext_control(&card->dapm);
 	return 1;
 }
@@ -115,7 +115,7 @@ static int tosa_set_jack(struct snd_kcontrol *kcontrol,
 static int tosa_get_spk(struct snd_kcontrol *kcontrol,
 	struct snd_ctl_elem_value *ucontrol)
 {
-	ucontrol->value.integer.value[0] = tosa_spk_func;
+	ucontrol->value.enumerated.item[0] = tosa_spk_func;
 	return 0;
 }
 
@@ -124,10 +124,10 @@ static int tosa_set_spk(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_card *card = snd_kcontrol_chip(kcontrol);
 
-	if (tosa_spk_func == ucontrol->value.integer.value[0])
+	if (tosa_spk_func == ucontrol->value.enumerated.item[0])
 		return 0;
 
-	tosa_spk_func = ucontrol->value.integer.value[0];
+	tosa_spk_func = ucontrol->value.enumerated.item[0];
 	tosa_ext_control(&card->dapm);
 	return 1;
 }
diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c
index 00b6c9d039cf..e5101e0d2d37 100644
--- a/sound/soc/qcom/lpass-cpu.c
+++ b/sound/soc/qcom/lpass-cpu.c
@@ -355,7 +355,6 @@ static struct regmap_config lpass_cpu_regmap_config = {
 	.readable_reg = lpass_cpu_regmap_readable,
 	.volatile_reg = lpass_cpu_regmap_volatile,
 	.cache_type = REGCACHE_FLAT,
-	.val_format_endian = REGMAP_ENDIAN_LITTLE,
 };
 
 int asoc_qcom_lpass_cpu_platform_probe(struct platform_device *pdev)
diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c
index 79688aa1941a..4aeb8e1a7160 100644
--- a/sound/soc/qcom/lpass-platform.c
+++ b/sound/soc/qcom/lpass-platform.c
@@ -440,18 +440,18 @@ static irqreturn_t lpass_platform_lpaif_irq(int irq, void *data)
 }
 
 static int lpass_platform_alloc_buffer(struct snd_pcm_substream *substream,
-		struct snd_soc_pcm_runtime *soc_runtime)
+		struct snd_soc_pcm_runtime *rt)
 {
 	struct snd_dma_buffer *buf = &substream->dma_buffer;
 	size_t size = lpass_platform_pcm_hardware.buffer_bytes_max;
 
 	buf->dev.type = SNDRV_DMA_TYPE_DEV;
-	buf->dev.dev = soc_runtime->dev;
+	buf->dev.dev = rt->platform->dev;
 	buf->private_data = NULL;
-	buf->area = dma_alloc_coherent(soc_runtime->dev, size, &buf->addr,
+	buf->area = dma_alloc_coherent(rt->platform->dev, size, &buf->addr,
 			GFP_KERNEL);
 	if (!buf->area) {
-		dev_err(soc_runtime->dev, "%s: Could not allocate DMA buffer\n",
+		dev_err(rt->platform->dev, "%s: Could not allocate DMA buffer\n",
 				__func__);
 		return -ENOMEM;
 	}
@@ -461,12 +461,12 @@ static int lpass_platform_alloc_buffer(struct snd_pcm_substream *substream,
 }
 
 static void lpass_platform_free_buffer(struct snd_pcm_substream *substream,
-		struct snd_soc_pcm_runtime *soc_runtime)
+		struct snd_soc_pcm_runtime *rt)
 {
 	struct snd_dma_buffer *buf = &substream->dma_buffer;
 
 	if (buf->area) {
-		dma_free_coherent(soc_runtime->dev, buf->bytes, buf->area,
+		dma_free_coherent(rt->dev, buf->bytes, buf->area,
 				buf->addr);
 	}
 	buf->area = NULL;
@@ -499,9 +499,6 @@ static int lpass_platform_pcm_new(struct snd_soc_pcm_runtime *soc_runtime)
 
 	snd_soc_pcm_set_drvdata(soc_runtime, data);
 
-	soc_runtime->dev->coherent_dma_mask = DMA_BIT_MASK(32);
-	soc_runtime->dev->dma_mask = &soc_runtime->dev->coherent_dma_mask;
-
 	ret = lpass_platform_alloc_buffer(substream, soc_runtime);
 	if (ret)
 		return ret;
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index 84d9e77c0fbe..70a2559b63f9 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -481,10 +481,11 @@ static int i2s_set_sysclk(struct snd_soc_dai *dai,
 	unsigned int cdcon_mask = 1 << i2s_regs->cdclkcon_off;
 	unsigned int rsrc_mask = 1 << i2s_regs->rclksrc_off;
 	u32 mod, mask, val = 0;
+	unsigned long flags;
 
-	spin_lock(i2s->lock);
+	spin_lock_irqsave(i2s->lock, flags);
 	mod = readl(i2s->addr + I2SMOD);
-	spin_unlock(i2s->lock);
+	spin_unlock_irqrestore(i2s->lock, flags);
 
 	switch (clk_id) {
 	case SAMSUNG_I2S_OPCLK:
@@ -575,11 +576,11 @@ static int i2s_set_sysclk(struct snd_soc_dai *dai,
 		return -EINVAL;
 	}
 
-	spin_lock(i2s->lock);
+	spin_lock_irqsave(i2s->lock, flags);
 	mod = readl(i2s->addr + I2SMOD);
 	mod = (mod & ~mask) | val;
 	writel(mod, i2s->addr + I2SMOD);
-	spin_unlock(i2s->lock);
+	spin_unlock_irqrestore(i2s->lock, flags);
 
 	return 0;
 }
@@ -590,6 +591,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai,
 	struct i2s_dai *i2s = to_info(dai);
 	int lrp_shift, sdf_shift, sdf_mask, lrp_rlow, mod_slave;
 	u32 mod, tmp = 0;
+	unsigned long flags;
 
 	lrp_shift = i2s->variant_regs->lrp_off;
 	sdf_shift = i2s->variant_regs->sdf_off;
@@ -649,7 +651,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai,
 		return -EINVAL;
 	}
 
-	spin_lock(i2s->lock);
+	spin_lock_irqsave(i2s->lock, flags);
 	mod = readl(i2s->addr + I2SMOD);
 	/*
 	 * Don't change the I2S mode if any controller is active on this
@@ -657,7 +659,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai,
 	 */
 	if (any_active(i2s) &&
 		((mod & (sdf_mask | lrp_rlow | mod_slave)) != tmp)) {
-		spin_unlock(i2s->lock);
+		spin_unlock_irqrestore(i2s->lock, flags);
 		dev_err(&i2s->pdev->dev,
 				"%s:%d Other DAI busy\n", __func__, __LINE__);
 		return -EAGAIN;
@@ -666,7 +668,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai,
 	mod &= ~(sdf_mask | lrp_rlow | mod_slave);
 	mod |= tmp;
 	writel(mod, i2s->addr + I2SMOD);
-	spin_unlock(i2s->lock);
+	spin_unlock_irqrestore(i2s->lock, flags);
 
 	return 0;
 }
@@ -676,6 +678,7 @@ static int i2s_hw_params(struct snd_pcm_substream *substream,
 {
 	struct i2s_dai *i2s = to_info(dai);
 	u32 mod, mask = 0, val = 0;
+	unsigned long flags;
 
 	if (!is_secondary(i2s))
 		mask |= (MOD_DC2_EN | MOD_DC1_EN);
@@ -744,11 +747,11 @@ static int i2s_hw_params(struct snd_pcm_substream *substream,
 		return -EINVAL;
 	}
 
-	spin_lock(i2s->lock);
+	spin_lock_irqsave(i2s->lock, flags);
 	mod = readl(i2s->addr + I2SMOD);
 	mod = (mod & ~mask) | val;
 	writel(mod, i2s->addr + I2SMOD);
-	spin_unlock(i2s->lock);
+	spin_unlock_irqrestore(i2s->lock, flags);
 
 	samsung_asoc_init_dma_data(dai, &i2s->dma_playback, &i2s->dma_capture);
 
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 5a2812fa8946..581175a51ecf 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -310,7 +310,7 @@ struct dapm_kcontrol_data {
 };
 
 static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget,
-	struct snd_kcontrol *kcontrol)
+	struct snd_kcontrol *kcontrol, const char *ctrl_name)
 {
 	struct dapm_kcontrol_data *data;
 	struct soc_mixer_control *mc;
@@ -333,7 +333,7 @@ static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget,
 		if (mc->autodisable) {
 			struct snd_soc_dapm_widget template;
 
-			name = kasprintf(GFP_KERNEL, "%s %s", kcontrol->id.name,
+			name = kasprintf(GFP_KERNEL, "%s %s", ctrl_name,
 					 "Autodisable");
 			if (!name) {
 				ret = -ENOMEM;
@@ -371,7 +371,7 @@ static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget,
 		if (e->autodisable) {
 			struct snd_soc_dapm_widget template;
 
-			name = kasprintf(GFP_KERNEL, "%s %s", kcontrol->id.name,
+			name = kasprintf(GFP_KERNEL, "%s %s", ctrl_name,
 					 "Autodisable");
 			if (!name) {
 				ret = -ENOMEM;
@@ -871,7 +871,7 @@ static int dapm_create_or_share_kcontrol(struct snd_soc_dapm_widget *w,
 
 		kcontrol->private_free = dapm_kcontrol_free;
 
-		ret = dapm_kcontrol_data_alloc(w, kcontrol);
+		ret = dapm_kcontrol_data_alloc(w, kcontrol, name);
 		if (ret) {
 			snd_ctl_free_one(kcontrol);
 			goto exit_free;
@@ -3573,7 +3573,7 @@ static int snd_soc_dapm_dai_link_get(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_dapm_widget *w = snd_kcontrol_chip(kcontrol);
 
-	ucontrol->value.integer.value[0] = w->params_select;
+	ucontrol->value.enumerated.item[0] = w->params_select;
 
 	return 0;
 }
@@ -3587,13 +3587,13 @@ static int snd_soc_dapm_dai_link_put(struct snd_kcontrol *kcontrol,
 	if (w->power)
 		return -EBUSY;
 
-	if (ucontrol->value.integer.value[0] == w->params_select)
+	if (ucontrol->value.enumerated.item[0] == w->params_select)
 		return 0;
 
-	if (ucontrol->value.integer.value[0] >= w->num_params)
+	if (ucontrol->value.enumerated.item[0] >= w->num_params)
 		return -EINVAL;
 
-	w->params_select = ucontrol->value.integer.value[0];
+	w->params_select = ucontrol->value.enumerated.item[0];
 
 	return 0;
 }
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index e898b427be7e..1af4f23697a7 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1810,7 +1810,8 @@ int dpcm_be_dai_hw_free(struct snd_soc_pcm_runtime *fe, int stream)
 		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_PREPARE) &&
 		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_HW_FREE) &&
 		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_PAUSED) &&
-		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP))
+		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP) &&
+		    (be->dpcm[stream].state != SND_SOC_DPCM_STATE_SUSPEND))
 			continue;
 
 		dev_dbg(be->dev, "ASoC: hw_free BE %s\n",
diff --git a/sound/usb/Kconfig b/sound/usb/Kconfig
index a452ad7cec40..d14bf411515b 100644
--- a/sound/usb/Kconfig
+++ b/sound/usb/Kconfig
@@ -15,6 +15,7 @@ config SND_USB_AUDIO
 	select SND_RAWMIDI
 	select SND_PCM
 	select BITREVERSE
+	select SND_USB_AUDIO_USE_MEDIA_CONTROLLER if MEDIA_CONTROLLER && (MEDIA_SUPPORT=y || MEDIA_SUPPORT=SND_USB_AUDIO)
 	help
 	  Say Y here to include support for USB audio and USB MIDI
 	  devices.
@@ -22,6 +23,9 @@ config SND_USB_AUDIO
 	  To compile this driver as a module, choose M here: the module
 	  will be called snd-usb-audio.
 
+config SND_USB_AUDIO_USE_MEDIA_CONTROLLER
+	bool
+
 config SND_USB_UA101
 	tristate "Edirol UA-101/UA-1000 driver"
 	select SND_PCM
diff --git a/sound/usb/Makefile b/sound/usb/Makefile
index 2d2d122b069f..8dca3c407f5a 100644
--- a/sound/usb/Makefile
+++ b/sound/usb/Makefile
@@ -15,6 +15,8 @@ snd-usb-audio-objs := 	card.o \
 			quirks.o \
 			stream.o
 
+snd-usb-audio-$(CONFIG_SND_USB_AUDIO_USE_MEDIA_CONTROLLER) += media.o
+
 snd-usbmidi-lib-objs := midi.o
 
 # Toplevel Module Dependency
diff --git a/sound/usb/card.c b/sound/usb/card.c
index 1f09d9591276..258cf7015ce2 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -66,6 +66,7 @@
 #include "format.h"
 #include "power.h"
 #include "stream.h"
+#include "media.h"
 
 MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
 MODULE_DESCRIPTION("USB Audio");
@@ -561,6 +562,11 @@ static int usb_audio_probe(struct usb_interface *intf,
 	if (err < 0)
 		goto __error;
 
+	if (quirk->media_device) {
+		/* don't want to fail when media_snd_device_create() fails */
+		media_snd_device_create(chip, intf);
+	}
+
 	usb_chip[chip->index] = chip;
 	chip->num_interfaces++;
 	usb_set_intfdata(intf, chip);
@@ -617,6 +623,14 @@ static void usb_audio_disconnect(struct usb_interface *intf)
 		list_for_each(p, &chip->midi_list) {
 			snd_usbmidi_disconnect(p);
 		}
+		/*
+		 * Nice to check quirk && quirk->media_device
+		 * need some special handlings. Doesn't look like
+		 * we have access to quirk here
+		 * Acceses mixer_list
+		*/
+		media_snd_device_delete(chip);
+
 		/* release mixer resources */
 		list_for_each_entry(mixer, &chip->mixer_list, list) {
 			snd_usb_mixer_disconnect(mixer);
diff --git a/sound/usb/card.h b/sound/usb/card.h
index 71778ca4b26a..34a0898e2238 100644
--- a/sound/usb/card.h
+++ b/sound/usb/card.h
@@ -105,6 +105,8 @@ struct snd_usb_endpoint {
 	struct list_head list;
 };
 
+struct media_ctl;
+
 struct snd_usb_substream {
 	struct snd_usb_stream *stream;
 	struct usb_device *dev;
@@ -156,6 +158,7 @@ struct snd_usb_substream {
 	} dsd_dop;
 
 	bool trigger_tstamp_pending_update; /* trigger timestamp being updated from initial estimate */
+	struct media_ctl *media_ctl;
 };
 
 struct snd_usb_stream {
diff --git a/sound/usb/media.c b/sound/usb/media.c
new file mode 100644
index 000000000000..93a50d01490c
--- /dev/null
+++ b/sound/usb/media.c
@@ -0,0 +1,318 @@
+/*
+ * media.c - Media Controller specific ALSA driver code
+ *
+ * Copyright (c) 2016 Shuah Khan <shuahkh@osg.samsung.com>
+ * Copyright (c) 2016 Samsung Electronics Co., Ltd.
+ *
+ * This file is released under the GPLv2.
+ */
+
+/*
+ * This file adds Media Controller support to ALSA driver
+ * to use the Media Controller API to share tuner with DVB
+ * and V4L2 drivers that control media device. Media device
+ * is created based on existing quirks framework. Using this
+ * approach, the media controller API usage can be added for
+ * a specific device.
+*/
+
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/usb.h>
+
+#include <sound/pcm.h>
+#include <sound/core.h>
+
+#include "usbaudio.h"
+#include "card.h"
+#include "mixer.h"
+#include "media.h"
+
+static int media_snd_enable_source(struct media_ctl *mctl)
+{
+	if (mctl && mctl->media_dev->enable_source)
+		return mctl->media_dev->enable_source(&mctl->media_entity,
+						      &mctl->media_pipe);
+	return 0;
+}
+
+static void media_snd_disable_source(struct media_ctl *mctl)
+{
+	if (mctl && mctl->media_dev->disable_source)
+		mctl->media_dev->disable_source(&mctl->media_entity);
+}
+
+int media_snd_stream_init(struct snd_usb_substream *subs, struct snd_pcm *pcm,
+			int stream)
+{
+	struct media_device *mdev;
+	struct media_ctl *mctl;
+	struct device *pcm_dev = &pcm->streams[stream].dev;
+	u32 intf_type;
+	int ret = 0;
+	u16 mixer_pad;
+	struct media_entity *entity;
+
+	mdev = subs->stream->chip->media_dev;
+	if (!mdev)
+		return -ENODEV;
+
+	if (subs->media_ctl)
+		return 0;
+
+	/* allocate media_ctl */
+	mctl = kzalloc(sizeof(*mctl), GFP_KERNEL);
+	if (!mctl)
+		return -ENOMEM;
+
+	mctl->media_dev = mdev;
+	if (stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		intf_type = MEDIA_INTF_T_ALSA_PCM_PLAYBACK;
+		mctl->media_entity.function = MEDIA_ENT_F_AUDIO_PLAYBACK;
+		mctl->media_pad.flags = MEDIA_PAD_FL_SOURCE;
+		mixer_pad = 1;
+	} else {
+		intf_type = MEDIA_INTF_T_ALSA_PCM_CAPTURE;
+		mctl->media_entity.function = MEDIA_ENT_F_AUDIO_CAPTURE;
+		mctl->media_pad.flags = MEDIA_PAD_FL_SINK;
+		mixer_pad = 2;
+	}
+	mctl->media_entity.name = pcm->name;
+	media_entity_pads_init(&mctl->media_entity, 1, &mctl->media_pad);
+	ret =  media_device_register_entity(mctl->media_dev,
+					    &mctl->media_entity);
+	if (ret)
+		goto free_mctl;
+
+	mctl->intf_devnode = media_devnode_create(mdev, intf_type, 0,
+						  MAJOR(pcm_dev->devt),
+						  MINOR(pcm_dev->devt));
+	if (!mctl->intf_devnode) {
+		ret = -ENOMEM;
+		goto unregister_entity;
+	}
+	mctl->intf_link = media_create_intf_link(&mctl->media_entity,
+						 &mctl->intf_devnode->intf,
+						 MEDIA_LNK_FL_ENABLED);
+	if (!mctl->intf_link) {
+		ret = -ENOMEM;
+		goto devnode_remove;
+	}
+
+	/* create link between mixer and audio */
+	media_device_for_each_entity(entity, mdev) {
+		switch (entity->function) {
+		case MEDIA_ENT_F_AUDIO_MIXER:
+			ret = media_create_pad_link(entity, mixer_pad,
+						    &mctl->media_entity, 0,
+						    MEDIA_LNK_FL_ENABLED);
+			if (ret)
+				goto remove_intf_link;
+			break;
+		}
+	}
+
+	subs->media_ctl = mctl;
+	return 0;
+
+remove_intf_link:
+	media_remove_intf_link(mctl->intf_link);
+devnode_remove:
+	media_devnode_remove(mctl->intf_devnode);
+unregister_entity:
+	media_device_unregister_entity(&mctl->media_entity);
+free_mctl:
+	kfree(mctl);
+	return ret;
+}
+
+void media_snd_stream_delete(struct snd_usb_substream *subs)
+{
+	struct media_ctl *mctl = subs->media_ctl;
+
+	if (mctl && mctl->media_dev) {
+		struct media_device *mdev;
+
+		mdev = subs->stream->chip->media_dev;
+		if (mdev && media_devnode_is_registered(&mdev->devnode)) {
+			media_devnode_remove(mctl->intf_devnode);
+			media_device_unregister_entity(&mctl->media_entity);
+			media_entity_cleanup(&mctl->media_entity);
+		}
+		kfree(mctl);
+		subs->media_ctl = NULL;
+	}
+}
+
+int media_snd_start_pipeline(struct snd_usb_substream *subs)
+{
+	struct media_ctl *mctl = subs->media_ctl;
+
+	if (mctl)
+		return media_snd_enable_source(mctl);
+	return 0;
+}
+
+void media_snd_stop_pipeline(struct snd_usb_substream *subs)
+{
+	struct media_ctl *mctl = subs->media_ctl;
+
+	if (mctl)
+		media_snd_disable_source(mctl);
+}
+
+int media_snd_mixer_init(struct snd_usb_audio *chip)
+{
+	struct device *ctl_dev = &chip->card->ctl_dev;
+	struct media_intf_devnode *ctl_intf;
+	struct usb_mixer_interface *mixer;
+	struct media_device *mdev = chip->media_dev;
+	struct media_mixer_ctl *mctl;
+	u32 intf_type = MEDIA_INTF_T_ALSA_CONTROL;
+	int ret;
+
+	if (!mdev)
+		return -ENODEV;
+
+	ctl_intf = chip->ctl_intf_media_devnode;
+	if (!ctl_intf) {
+		ctl_intf = media_devnode_create(mdev, intf_type, 0,
+						MAJOR(ctl_dev->devt),
+						MINOR(ctl_dev->devt));
+		if (!ctl_intf)
+			return -ENOMEM;
+		chip->ctl_intf_media_devnode = ctl_intf;
+	}
+
+	list_for_each_entry(mixer, &chip->mixer_list, list) {
+
+		if (mixer->media_mixer_ctl)
+			continue;
+
+		/* allocate media_mixer_ctl */
+		mctl = kzalloc(sizeof(*mctl), GFP_KERNEL);
+		if (!mctl)
+			return -ENOMEM;
+
+		mctl->media_dev = mdev;
+		mctl->media_entity.function = MEDIA_ENT_F_AUDIO_MIXER;
+		mctl->media_entity.name = chip->card->mixername;
+		mctl->media_pad[0].flags = MEDIA_PAD_FL_SINK;
+		mctl->media_pad[1].flags = MEDIA_PAD_FL_SOURCE;
+		mctl->media_pad[2].flags = MEDIA_PAD_FL_SOURCE;
+		media_entity_pads_init(&mctl->media_entity, MEDIA_MIXER_PAD_MAX,
+				  mctl->media_pad);
+		ret =  media_device_register_entity(mctl->media_dev,
+						    &mctl->media_entity);
+		if (ret) {
+			kfree(mctl);
+			return ret;
+		}
+
+		mctl->intf_link = media_create_intf_link(&mctl->media_entity,
+							 &ctl_intf->intf,
+							 MEDIA_LNK_FL_ENABLED);
+		if (!mctl->intf_link) {
+			media_device_unregister_entity(&mctl->media_entity);
+			media_entity_cleanup(&mctl->media_entity);
+			kfree(mctl);
+			return -ENOMEM;
+		}
+		mctl->intf_devnode = ctl_intf;
+		mixer->media_mixer_ctl = mctl;
+	}
+	return 0;
+}
+
+static void media_snd_mixer_delete(struct snd_usb_audio *chip)
+{
+	struct usb_mixer_interface *mixer;
+	struct media_device *mdev = chip->media_dev;
+
+	if (!mdev)
+		return;
+
+	list_for_each_entry(mixer, &chip->mixer_list, list) {
+		struct media_mixer_ctl *mctl;
+
+		mctl = mixer->media_mixer_ctl;
+		if (!mixer->media_mixer_ctl)
+			continue;
+
+		if (media_devnode_is_registered(&mdev->devnode)) {
+			media_device_unregister_entity(&mctl->media_entity);
+			media_entity_cleanup(&mctl->media_entity);
+		}
+		kfree(mctl);
+		mixer->media_mixer_ctl = NULL;
+	}
+	if (media_devnode_is_registered(&mdev->devnode))
+		media_devnode_remove(chip->ctl_intf_media_devnode);
+	chip->ctl_intf_media_devnode = NULL;
+}
+
+int media_snd_device_create(struct snd_usb_audio *chip,
+			struct usb_interface *iface)
+{
+	struct media_device *mdev;
+	struct usb_device *usbdev = interface_to_usbdev(iface);
+	int ret;
+
+	mdev = media_device_get_devres(&usbdev->dev);
+	if (!mdev)
+		return -ENOMEM;
+	if (!mdev->dev) {
+		/* register media device */
+		mdev->dev = &usbdev->dev;
+		if (usbdev->product)
+			strlcpy(mdev->model, usbdev->product,
+				sizeof(mdev->model));
+		if (usbdev->serial)
+			strlcpy(mdev->serial, usbdev->serial,
+				sizeof(mdev->serial));
+		strcpy(mdev->bus_info, usbdev->devpath);
+		mdev->hw_revision = le16_to_cpu(usbdev->descriptor.bcdDevice);
+		media_device_init(mdev);
+	}
+	if (!media_devnode_is_registered(&mdev->devnode)) {
+		ret = media_device_register(mdev);
+		if (ret) {
+			dev_err(&usbdev->dev,
+				"Couldn't register media device. Error: %d\n",
+				ret);
+			return ret;
+		}
+	}
+
+	/* save media device - avoid lookups */
+	chip->media_dev = mdev;
+
+	/* Create media entities for mixer and control dev */
+	ret = media_snd_mixer_init(chip);
+	if (ret) {
+		dev_err(&usbdev->dev,
+			"Couldn't create media mixer entities. Error: %d\n",
+			ret);
+
+		/* clear saved media_dev */
+		chip->media_dev = NULL;
+
+		return ret;
+	}
+	return 0;
+}
+
+void media_snd_device_delete(struct snd_usb_audio *chip)
+{
+	struct media_device *mdev = chip->media_dev;
+
+	media_snd_mixer_delete(chip);
+
+	if (mdev) {
+		if (media_devnode_is_registered(&mdev->devnode))
+			media_device_unregister(mdev);
+		chip->media_dev = NULL;
+	}
+}
diff --git a/sound/usb/media.h b/sound/usb/media.h
new file mode 100644
index 000000000000..1dcdcdc5f7aa
--- /dev/null
+++ b/sound/usb/media.h
@@ -0,0 +1,72 @@
+/*
+ * media.h - Media Controller specific ALSA driver code
+ *
+ * Copyright (c) 2016 Shuah Khan <shuahkh@osg.samsung.com>
+ * Copyright (c) 2016 Samsung Electronics Co., Ltd.
+ *
+ * This file is released under the GPLv2.
+ */
+
+/*
+ * This file adds Media Controller support to ALSA driver
+ * to use the Media Controller API to share tuner with DVB
+ * and V4L2 drivers that control media device. Media device
+ * is created based on existing quirks framework. Using this
+ * approach, the media controller API usage can be added for
+ * a specific device.
+*/
+#ifndef __MEDIA_H
+
+#ifdef CONFIG_SND_USB_AUDIO_USE_MEDIA_CONTROLLER
+
+#include <media/media-device.h>
+#include <media/media-entity.h>
+#include <sound/asound.h>
+
+struct media_ctl {
+	struct media_device *media_dev;
+	struct media_entity media_entity;
+	struct media_intf_devnode *intf_devnode;
+	struct media_link *intf_link;
+	struct media_pad media_pad;
+	struct media_pipeline media_pipe;
+};
+
+/*
+ * One source pad each for SNDRV_PCM_STREAM_CAPTURE and
+ * SNDRV_PCM_STREAM_PLAYBACK. One for sink pad to link
+ * to AUDIO Source
+*/
+#define MEDIA_MIXER_PAD_MAX    (SNDRV_PCM_STREAM_LAST + 2)
+
+struct media_mixer_ctl {
+	struct media_device *media_dev;
+	struct media_entity media_entity;
+	struct media_intf_devnode *intf_devnode;
+	struct media_link *intf_link;
+	struct media_pad media_pad[MEDIA_MIXER_PAD_MAX];
+	struct media_pipeline media_pipe;
+};
+
+int media_snd_device_create(struct snd_usb_audio *chip,
+			    struct usb_interface *iface);
+void media_snd_device_delete(struct snd_usb_audio *chip);
+int media_snd_stream_init(struct snd_usb_substream *subs, struct snd_pcm *pcm,
+			  int stream);
+void media_snd_stream_delete(struct snd_usb_substream *subs);
+int media_snd_start_pipeline(struct snd_usb_substream *subs);
+void media_snd_stop_pipeline(struct snd_usb_substream *subs);
+#else
+static inline int media_snd_device_create(struct snd_usb_audio *chip,
+					  struct usb_interface *iface)
+						{ return 0; }
+static inline void media_snd_device_delete(struct snd_usb_audio *chip) { }
+static inline int media_snd_stream_init(struct snd_usb_substream *subs,
+					struct snd_pcm *pcm, int stream)
+						{ return 0; }
+static inline void media_snd_stream_delete(struct snd_usb_substream *subs) { }
+static inline int media_snd_start_pipeline(struct snd_usb_substream *subs)
+					{ return 0; }
+static inline void media_snd_stop_pipeline(struct snd_usb_substream *subs) { }
+#endif
+#endif /* __MEDIA_H */
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index cc39f63299ef..007cf5831121 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -2455,7 +2455,6 @@ int snd_usbmidi_create(struct snd_card *card,
 	else
 		err = snd_usbmidi_create_endpoints(umidi, endpoints);
 	if (err < 0) {
-		snd_usbmidi_free(umidi);
 		return err;
 	}
 
diff --git a/sound/usb/mixer.h b/sound/usb/mixer.h
index 3417ef347e40..f3789446ab9c 100644
--- a/sound/usb/mixer.h
+++ b/sound/usb/mixer.h
@@ -3,6 +3,8 @@
 
 #include <sound/info.h>
 
+struct media_mixer_ctl;
+
 struct usb_mixer_interface {
 	struct snd_usb_audio *chip;
 	struct usb_host_interface *hostif;
@@ -22,6 +24,7 @@ struct usb_mixer_interface {
 	struct urb *rc_urb;
 	struct usb_ctrlrequest *rc_setup_packet;
 	u8 rc_buffer[6];
+	struct media_mixer_ctl *media_mixer_ctl;
 };
 
 #define MAX_CHANNELS	16	/* max logical channels */
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 9245f52d43bd..b0370d5f33f8 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -35,6 +35,7 @@
 #include "pcm.h"
 #include "clock.h"
 #include "power.h"
+#include "media.h"
 
 #define SUBSTREAM_FLAG_DATA_EP_STARTED	0
 #define SUBSTREAM_FLAG_SYNC_EP_STARTED	1
@@ -715,10 +716,14 @@ static int snd_usb_hw_params(struct snd_pcm_substream *substream,
 	struct audioformat *fmt;
 	int ret;
 
+	ret = media_snd_start_pipeline(subs);
+	if (ret)
+		return ret;
+
 	ret = snd_pcm_lib_alloc_vmalloc_buffer(substream,
 					       params_buffer_bytes(hw_params));
 	if (ret < 0)
-		return ret;
+		goto err_ret;
 
 	subs->pcm_format = params_format(hw_params);
 	subs->period_bytes = params_period_bytes(hw_params);
@@ -732,22 +737,27 @@ static int snd_usb_hw_params(struct snd_pcm_substream *substream,
 		dev_dbg(&subs->dev->dev,
 			"cannot set format: format = %#x, rate = %d, channels = %d\n",
 			   subs->pcm_format, subs->cur_rate, subs->channels);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_ret;
 	}
 
 	ret = snd_usb_lock_shutdown(subs->stream->chip);
 	if (ret < 0)
-		return ret;
+		goto err_ret;
 	ret = set_format(subs, fmt);
 	snd_usb_unlock_shutdown(subs->stream->chip);
 	if (ret < 0)
-		return ret;
+		goto err_ret;
 
 	subs->interface = fmt->iface;
 	subs->altset_idx = fmt->altset_idx;
 	subs->need_setup_ep = true;
 
 	return 0;
+
+err_ret:
+	media_snd_stop_pipeline(subs);
+	return ret;
 }
 
 /*
@@ -759,6 +769,7 @@ static int snd_usb_hw_free(struct snd_pcm_substream *substream)
 {
 	struct snd_usb_substream *subs = substream->runtime->private_data;
 
+	media_snd_stop_pipeline(subs);
 	subs->cur_audiofmt = NULL;
 	subs->cur_rate = 0;
 	subs->period_bytes = 0;
@@ -1219,6 +1230,7 @@ static int snd_usb_pcm_open(struct snd_pcm_substream *substream, int direction)
 	struct snd_usb_stream *as = snd_pcm_substream_chip(substream);
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_usb_substream *subs = &as->substream[direction];
+	int ret;
 
 	subs->interface = -1;
 	subs->altset_idx = 0;
@@ -1232,7 +1244,12 @@ static int snd_usb_pcm_open(struct snd_pcm_substream *substream, int direction)
 	subs->dsd_dop.channel = 0;
 	subs->dsd_dop.marker = 1;
 
-	return setup_hw_info(runtime, subs);
+	ret = setup_hw_info(runtime, subs);
+	if (ret == 0)
+		ret = media_snd_stream_init(subs, as->pcm, direction);
+	if (ret)
+		snd_usb_autosuspend(subs->stream->chip);
+	return ret;
 }
 
 static int snd_usb_pcm_close(struct snd_pcm_substream *substream, int direction)
@@ -1241,6 +1258,7 @@ static int snd_usb_pcm_close(struct snd_pcm_substream *substream, int direction)
 	struct snd_usb_substream *subs = &as->substream[direction];
 
 	stop_endpoints(subs, true);
+	media_snd_stop_pipeline(subs);
 
 	if (subs->interface >= 0 &&
 	    !snd_usb_lock_shutdown(subs->stream->chip)) {
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index c60a776e815d..9d087b19c70c 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -2886,6 +2886,7 @@ YAMAHA_DEVICE(0x7010, "UB99"),
 		.product_name = pname, \
 		.ifnum = QUIRK_ANY_INTERFACE, \
 		.type = QUIRK_AUDIO_ALIGN_TRANSFER, \
+		.media_device = 1, \
 	} \
 }
 
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 4f6ce1cac8e2..c458d60d5030 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1124,6 +1124,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip)
 	case USB_ID(0x045E, 0x076F): /* MS Lifecam HD-6000 */
 	case USB_ID(0x045E, 0x0772): /* MS Lifecam Studio */
 	case USB_ID(0x045E, 0x0779): /* MS Lifecam HD-3000 */
+	case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */
 	case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */
 	case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */
 	case USB_ID(0x21B4, 0x0081): /* AudioQuest DragonFly */
diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index c4dc577ab1bd..51258a15f653 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -36,6 +36,7 @@
 #include "format.h"
 #include "clock.h"
 #include "stream.h"
+#include "media.h"
 
 /*
  * free a substream
@@ -52,6 +53,7 @@ static void free_substream(struct snd_usb_substream *subs)
 		kfree(fp);
 	}
 	kfree(subs->rate_list.list);
+	media_snd_stream_delete(subs);
 }
 
 
diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h
index b665d85555cb..a161c7c1b126 100644
--- a/sound/usb/usbaudio.h
+++ b/sound/usb/usbaudio.h
@@ -30,6 +30,9 @@
  *
  */
 
+struct media_device;
+struct media_intf_devnode;
+
 struct snd_usb_audio {
 	int index;
 	struct usb_device *dev;
@@ -60,6 +63,8 @@ struct snd_usb_audio {
 	bool autoclock;			/* from the 'autoclock' module param */
 
 	struct usb_host_interface *ctrl_intf;	/* the audio control interface */
+	struct media_device *media_dev;
+	struct media_intf_devnode *ctl_intf_media_devnode;
 };
 
 #define usb_audio_err(chip, fmt, args...) \
@@ -110,6 +115,7 @@ struct snd_usb_audio_quirk {
 	const char *product_name;
 	int16_t ifnum;
 	uint16_t type;
+	bool media_device;
 	const void *data;
 };
 
diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index 4a96473b180f..ee566e8bd1cf 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -85,7 +85,7 @@ $(OUTPUT)%.i: %.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_i_c)
 
-$(OUTPUT)%.i: %.S FORCE
+$(OUTPUT)%.s: %.S FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_i_c)
 
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 02db3cdff20f..6b7707270aa3 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -27,7 +27,7 @@ endef
 #   the rule that uses them - an example for that is the 'bionic'
 #   feature check. ]
 #
-FEATURE_TESTS ?=			\
+FEATURE_TESTS_BASIC :=			\
 	backtrace			\
 	dwarf				\
 	fortify-source			\
@@ -46,6 +46,7 @@ FEATURE_TESTS ?=			\
 	libpython			\
 	libpython-version		\
 	libslang			\
+	libcrypto			\
 	libunwind			\
 	pthread-attr-setaffinity-np	\
 	stackprotector-all		\
@@ -56,6 +57,25 @@ FEATURE_TESTS ?=			\
 	get_cpuid			\
 	bpf
 
+# FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
+# of all feature tests
+FEATURE_TESTS_EXTRA :=			\
+	bionic				\
+	compile-32			\
+	compile-x32			\
+	cplus-demangle			\
+	hello				\
+	libbabeltrace			\
+	liberty				\
+	liberty-z			\
+	libunwind-debug-frame
+
+FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC)
+
+ifeq ($(FEATURE_TESTS),all)
+  FEATURE_TESTS := $(FEATURE_TESTS_BASIC) $(FEATURE_TESTS_EXTRA)
+endif
+
 FEATURE_DISPLAY ?=			\
 	dwarf				\
 	glibc				\
@@ -68,6 +88,7 @@ FEATURE_DISPLAY ?=			\
 	libperl				\
 	libpython			\
 	libslang			\
+	libcrypto			\
 	libunwind			\
 	libdw-dwarf-unwind		\
 	zlib				\
@@ -100,6 +121,14 @@ ifeq ($(feature-all), 1)
   # test-all.c passed - just set all the core feature flags to 1:
   #
   $(foreach feat,$(FEATURE_TESTS),$(call feature_set,$(feat)))
+  #
+  # test-all.c does not comprise these tests, so we need to
+  # for this case to get features proper values
+  #
+  $(call feature_check,compile-32)
+  $(call feature_check,compile-x32)
+  $(call feature_check,bionic)
+  $(call feature_check,libbabeltrace)
 else
   $(foreach feat,$(FEATURE_TESTS),$(call feature_check,$(feat)))
 endif
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index bf8f0352264d..c5f4c417428d 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -23,6 +23,7 @@ FILES=					\
 	test-libpython.bin		\
 	test-libpython-version.bin	\
 	test-libslang.bin		\
+	test-libcrypto.bin		\
 	test-libunwind.bin		\
 	test-libunwind-debug-frame.bin	\
 	test-pthread-attr-setaffinity-np.bin	\
@@ -105,6 +106,9 @@ $(OUTPUT)test-libaudit.bin:
 $(OUTPUT)test-libslang.bin:
 	$(BUILD) -I/usr/include/slang -lslang
 
+$(OUTPUT)test-libcrypto.bin:
+	$(BUILD) -lcrypto
+
 $(OUTPUT)test-gtk2.bin:
 	$(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null)
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 81025cade45f..e499a36c1e4a 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -129,6 +129,10 @@
 # include "test-bpf.c"
 #undef main
 
+#define main main_test_libcrypto
+# include "test-libcrypto.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -158,6 +162,7 @@ int main(int argc, char *argv[])
 	main_test_lzma();
 	main_test_get_cpuid();
 	main_test_bpf();
+	main_test_libcrypto();
 
 	return 0;
 }
diff --git a/tools/build/feature/test-compile.c b/tools/build/feature/test-compile.c
index 31dbf45bf99c..c54e6551ae4c 100644
--- a/tools/build/feature/test-compile.c
+++ b/tools/build/feature/test-compile.c
@@ -1,4 +1,6 @@
+#include <stdio.h>
 int main(void)
 {
+	printf("Hello World!\n");
 	return 0;
 }
diff --git a/tools/build/feature/test-libcrypto.c b/tools/build/feature/test-libcrypto.c
new file mode 100644
index 000000000000..bd79dc7f28d3
--- /dev/null
+++ b/tools/build/feature/test-libcrypto.c
@@ -0,0 +1,17 @@
+#include <openssl/sha.h>
+#include <openssl/md5.h>
+
+int main(void)
+{
+	MD5_CTX context;
+	unsigned char md[MD5_DIGEST_LENGTH + SHA_DIGEST_LENGTH];
+	unsigned char dat[] = "12345";
+
+	MD5_Init(&context);
+	MD5_Update(&context, &dat[0], sizeof(dat));
+	MD5_Final(&md[0], &context);
+
+	SHA1(&dat[0], sizeof(dat), &md[0]);
+
+	return 0;
+}
diff --git a/tools/lib/api/Build b/tools/lib/api/Build
index e8b8a23b9bf4..954c644f7ad9 100644
--- a/tools/lib/api/Build
+++ b/tools/lib/api/Build
@@ -1,3 +1,4 @@
 libapi-y += fd/
 libapi-y += fs/
 libapi-y += cpu.o
+libapi-y += debug.o
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index d85904dc9b38..bbc82c614bee 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -18,6 +18,7 @@ LIBFILE = $(OUTPUT)libapi.a
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
 CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
+CFLAGS += -I$(srctree)/tools/lib/api
 
 RM = rm -f
 
diff --git a/tools/lib/api/debug-internal.h b/tools/lib/api/debug-internal.h
new file mode 100644
index 000000000000..188f7880eafe
--- /dev/null
+++ b/tools/lib/api/debug-internal.h
@@ -0,0 +1,20 @@
+#ifndef __API_DEBUG_INTERNAL_H__
+#define __API_DEBUG_INTERNAL_H__
+
+#include "debug.h"
+
+#define __pr(func, fmt, ...)	\
+do {				\
+	if ((func))		\
+		(func)("libapi: " fmt, ##__VA_ARGS__); \
+} while (0)
+
+extern libapi_print_fn_t __pr_warning;
+extern libapi_print_fn_t __pr_info;
+extern libapi_print_fn_t __pr_debug;
+
+#define pr_warning(fmt, ...)	__pr(__pr_warning, fmt, ##__VA_ARGS__)
+#define pr_info(fmt, ...)	__pr(__pr_info, fmt, ##__VA_ARGS__)
+#define pr_debug(fmt, ...)	__pr(__pr_debug, fmt, ##__VA_ARGS__)
+
+#endif /* __API_DEBUG_INTERNAL_H__ */
diff --git a/tools/lib/api/debug.c b/tools/lib/api/debug.c
new file mode 100644
index 000000000000..5fa5cf500a1f
--- /dev/null
+++ b/tools/lib/api/debug.c
@@ -0,0 +1,28 @@
+#include <stdio.h>
+#include <stdarg.h>
+#include "debug.h"
+#include "debug-internal.h"
+
+static int __base_pr(const char *format, ...)
+{
+	va_list args;
+	int err;
+
+	va_start(args, format);
+	err = vfprintf(stderr, format, args);
+	va_end(args);
+	return err;
+}
+
+libapi_print_fn_t __pr_warning = __base_pr;
+libapi_print_fn_t __pr_info    = __base_pr;
+libapi_print_fn_t __pr_debug;
+
+void libapi_set_print(libapi_print_fn_t warn,
+		      libapi_print_fn_t info,
+		      libapi_print_fn_t debug)
+{
+	__pr_warning = warn;
+	__pr_info    = info;
+	__pr_debug   = debug;
+}
diff --git a/tools/lib/api/debug.h b/tools/lib/api/debug.h
new file mode 100644
index 000000000000..a0872f68fc56
--- /dev/null
+++ b/tools/lib/api/debug.h
@@ -0,0 +1,10 @@
+#ifndef __API_DEBUG_H__
+#define __API_DEBUG_H__
+
+typedef int (*libapi_print_fn_t)(const char *, ...);
+
+void libapi_set_print(libapi_print_fn_t warn,
+		      libapi_print_fn_t info,
+		      libapi_print_fn_t debug);
+
+#endif /* __API_DEBUG_H__ */
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 459599d1b6c4..ef78c22ff44d 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -13,6 +13,7 @@
 #include <sys/mount.h>
 
 #include "fs.h"
+#include "debug-internal.h"
 
 #define _STR(x) #x
 #define STR(x) _STR(x)
@@ -300,6 +301,56 @@ int filename__read_ull(const char *filename, unsigned long long *value)
 	return err;
 }
 
+#define STRERR_BUFSIZE  128     /* For the buffer size of strerror_r */
+
+int filename__read_str(const char *filename, char **buf, size_t *sizep)
+{
+	size_t size = 0, alloc_size = 0;
+	void *bf = NULL, *nbf;
+	int fd, n, err = 0;
+	char sbuf[STRERR_BUFSIZE];
+
+	fd = open(filename, O_RDONLY);
+	if (fd < 0)
+		return -errno;
+
+	do {
+		if (size == alloc_size) {
+			alloc_size += BUFSIZ;
+			nbf = realloc(bf, alloc_size);
+			if (!nbf) {
+				err = -ENOMEM;
+				break;
+			}
+
+			bf = nbf;
+		}
+
+		n = read(fd, bf + size, alloc_size - size);
+		if (n < 0) {
+			if (size) {
+				pr_warning("read failed %d: %s\n", errno,
+					 strerror_r(errno, sbuf, sizeof(sbuf)));
+				err = 0;
+			} else
+				err = -errno;
+
+			break;
+		}
+
+		size += n;
+	} while (n > 0);
+
+	if (!err) {
+		*sizep = size;
+		*buf   = bf;
+	} else
+		free(bf);
+
+	close(fd);
+	return err;
+}
+
 int sysfs__read_ull(const char *entry, unsigned long long *value)
 {
 	char path[PATH_MAX];
@@ -326,6 +377,19 @@ int sysfs__read_int(const char *entry, int *value)
 	return filename__read_int(path, value);
 }
 
+int sysfs__read_str(const char *entry, char **buf, size_t *sizep)
+{
+	char path[PATH_MAX];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (!sysfs)
+		return -1;
+
+	snprintf(path, sizeof(path), "%s/%s", sysfs, entry);
+
+	return filename__read_str(path, buf, sizep);
+}
+
 int sysctl__read_int(const char *sysctl, int *value)
 {
 	char path[PATH_MAX];
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index d024a7f682f6..9f6598098dc5 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -2,6 +2,7 @@
 #define __API_FS__
 
 #include <stdbool.h>
+#include <unistd.h>
 
 /*
  * On most systems <limits.h> would have given us this, but  not on some systems
@@ -26,8 +27,10 @@ FS(tracefs)
 
 int filename__read_int(const char *filename, int *value);
 int filename__read_ull(const char *filename, unsigned long long *value);
+int filename__read_str(const char *filename, char **buf, size_t *sizep);
 
 int sysctl__read_int(const char *sysctl, int *value);
 int sysfs__read_int(const char *entry, int *value);
 int sysfs__read_ull(const char *entry, unsigned long long *value);
+int sysfs__read_str(const char *entry, char **buf, size_t *sizep);
 #endif /* __API_FS__ */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 8334a5a9d5d7..7e543c3102d4 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -201,6 +201,7 @@ struct bpf_object {
 			Elf_Data *data;
 		} *reloc;
 		int nr_reloc;
+		int maps_shndx;
 	} efile;
 	/*
 	 * All loaded bpf_object is linked in a list, which is
@@ -350,6 +351,7 @@ static struct bpf_object *bpf_object__new(const char *path,
 	 */
 	obj->efile.obj_buf = obj_buf;
 	obj->efile.obj_buf_sz = obj_buf_sz;
+	obj->efile.maps_shndx = -1;
 
 	obj->loaded = false;
 
@@ -529,12 +531,12 @@ bpf_object__init_maps(struct bpf_object *obj, void *data,
 }
 
 static int
-bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx)
+bpf_object__init_maps_name(struct bpf_object *obj)
 {
 	int i;
 	Elf_Data *symbols = obj->efile.symbols;
 
-	if (!symbols || maps_shndx < 0)
+	if (!symbols || obj->efile.maps_shndx < 0)
 		return -EINVAL;
 
 	for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
@@ -544,7 +546,7 @@ bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx)
 
 		if (!gelf_getsym(symbols, i, &sym))
 			continue;
-		if (sym.st_shndx != maps_shndx)
+		if (sym.st_shndx != obj->efile.maps_shndx)
 			continue;
 
 		map_name = elf_strptr(obj->efile.elf,
@@ -572,7 +574,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 	Elf *elf = obj->efile.elf;
 	GElf_Ehdr *ep = &obj->efile.ehdr;
 	Elf_Scn *scn = NULL;
-	int idx = 0, err = 0, maps_shndx = -1;
+	int idx = 0, err = 0;
 
 	/* Elf is corrupted/truncated, avoid calling elf_strptr. */
 	if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) {
@@ -625,7 +627,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		else if (strcmp(name, "maps") == 0) {
 			err = bpf_object__init_maps(obj, data->d_buf,
 						    data->d_size);
-			maps_shndx = idx;
+			obj->efile.maps_shndx = idx;
 		} else if (sh.sh_type == SHT_SYMTAB) {
 			if (obj->efile.symbols) {
 				pr_warning("bpf: multiple SYMTAB in %s\n",
@@ -674,8 +676,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		pr_warning("Corrupted ELF file: index of strtab invalid\n");
 		return LIBBPF_ERRNO__FORMAT;
 	}
-	if (maps_shndx >= 0)
-		err = bpf_object__init_maps_name(obj, maps_shndx);
+	if (obj->efile.maps_shndx >= 0)
+		err = bpf_object__init_maps_name(obj);
 out:
 	return err;
 }
@@ -697,7 +699,8 @@ bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx)
 static int
 bpf_program__collect_reloc(struct bpf_program *prog,
 			   size_t nr_maps, GElf_Shdr *shdr,
-			   Elf_Data *data, Elf_Data *symbols)
+			   Elf_Data *data, Elf_Data *symbols,
+			   int maps_shndx)
 {
 	int i, nrels;
 
@@ -724,9 +727,6 @@ bpf_program__collect_reloc(struct bpf_program *prog,
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
-		insn_idx = rel.r_offset / sizeof(struct bpf_insn);
-		pr_debug("relocation: insn_idx=%u\n", insn_idx);
-
 		if (!gelf_getsym(symbols,
 				 GELF_R_SYM(rel.r_info),
 				 &sym)) {
@@ -735,6 +735,15 @@ bpf_program__collect_reloc(struct bpf_program *prog,
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
+		if (sym.st_shndx != maps_shndx) {
+			pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n",
+				   prog->section_name, sym.st_shndx);
+			return -LIBBPF_ERRNO__RELOC;
+		}
+
+		insn_idx = rel.r_offset / sizeof(struct bpf_insn);
+		pr_debug("relocation: insn_idx=%u\n", insn_idx);
+
 		if (insns[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) {
 			pr_warning("bpf: relocation: invalid relo for insns[%d].code 0x%x\n",
 				   insn_idx, insns[insn_idx].code);
@@ -863,7 +872,8 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 
 		err = bpf_program__collect_reloc(prog, nr_maps,
 						 shdr, data,
-						 obj->efile.symbols);
+						 obj->efile.symbols,
+						 obj->efile.maps_shndx);
 		if (err)
 			return err;
 	}
diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile
index 90d2baeb621a..1d57af56814b 100644
--- a/tools/lib/lockdep/Makefile
+++ b/tools/lib/lockdep/Makefile
@@ -100,7 +100,7 @@ include $(srctree)/tools/build/Makefile.include
 
 do_compile_shared_library =			\
 	($(print_shared_lib_compile)		\
-	$(CC) --shared $^ -o $@ -lpthread -ldl -Wl,-soname='"$@"';$(shell ln -s $@ liblockdep.so))
+	$(CC) --shared $^ -o $@ -lpthread -ldl -Wl,-soname='"$@"';$(shell ln -sf $@ liblockdep.so))
 
 do_build_static_lib =				\
 	($(print_static_lib_build)		\
diff --git a/tools/lib/lockdep/common.c b/tools/lib/lockdep/common.c
index 9be663340f0a..d1c89cc06f5f 100644
--- a/tools/lib/lockdep/common.c
+++ b/tools/lib/lockdep/common.c
@@ -11,11 +11,6 @@ static __thread struct task_struct current_obj;
 bool debug_locks = true;
 bool debug_locks_silent;
 
-__attribute__((constructor)) static void liblockdep_init(void)
-{
-	lockdep_init();
-}
-
 __attribute__((destructor)) static void liblockdep_exit(void)
 {
 	debug_check_no_locks_held();
diff --git a/tools/lib/lockdep/include/liblockdep/common.h b/tools/lib/lockdep/include/liblockdep/common.h
index a60c14b9662a..6e66277ec437 100644
--- a/tools/lib/lockdep/include/liblockdep/common.h
+++ b/tools/lib/lockdep/include/liblockdep/common.h
@@ -44,7 +44,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 void lock_release(struct lockdep_map *lock, int nested,
 			unsigned long ip);
 extern void debug_check_no_locks_freed(const void *from, unsigned long len);
-extern void lockdep_init(void);
 
 #define STATIC_LOCKDEP_MAP_INIT(_name, _key) \
 	{ .name = (_name), .key = (void *)(_key), }
diff --git a/tools/lib/lockdep/lockdep.c b/tools/lib/lockdep/lockdep.c
index f42b7e9aa48f..a0a2e3a266af 100644
--- a/tools/lib/lockdep/lockdep.c
+++ b/tools/lib/lockdep/lockdep.c
@@ -1,2 +1,8 @@
 #include <linux/lockdep.h>
+
+/* Trivial API wrappers, we don't (yet) have RCU in user-space: */
+#define hlist_for_each_entry_rcu	hlist_for_each_entry
+#define hlist_add_head_rcu		hlist_add_head
+#define hlist_del_rcu			hlist_del
+
 #include "../../../kernel/locking/lockdep.c"
diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c
index 21cdf869a01b..52844847569c 100644
--- a/tools/lib/lockdep/preload.c
+++ b/tools/lib/lockdep/preload.c
@@ -439,7 +439,5 @@ __attribute__((constructor)) static void init_preload(void)
 	ll_pthread_rwlock_unlock = dlsym(RTLD_NEXT, "pthread_rwlock_unlock");
 #endif
 
-	lockdep_init();
-
 	__init_state = done;
 }
diff --git a/tools/lib/lockdep/tests/AA.c b/tools/lib/lockdep/tests/AA.c
index 0f782ff404ac..18211a5f354f 100644
--- a/tools/lib/lockdep/tests/AA.c
+++ b/tools/lib/lockdep/tests/AA.c
@@ -1,13 +1,13 @@
 #include <liblockdep/mutex.h>
 
-void main(void)
+int main(void)
 {
-	pthread_mutex_t a, b;
+	pthread_mutex_t a;
 
 	pthread_mutex_init(&a, NULL);
-	pthread_mutex_init(&b, NULL);
 
 	pthread_mutex_lock(&a);
-	pthread_mutex_lock(&b);
 	pthread_mutex_lock(&a);
+
+	return 0;
 }
diff --git a/tools/lib/lockdep/tests/ABA.c b/tools/lib/lockdep/tests/ABA.c
new file mode 100644
index 000000000000..0f782ff404ac
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABA.c
@@ -0,0 +1,13 @@
+#include <liblockdep/mutex.h>
+
+void main(void)
+{
+	pthread_mutex_t a, b;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+
+	pthread_mutex_lock(&a);
+	pthread_mutex_lock(&b);
+	pthread_mutex_lock(&a);
+}
diff --git a/tools/lib/lockdep/tests/ABBA_2threads.c b/tools/lib/lockdep/tests/ABBA_2threads.c
new file mode 100644
index 000000000000..cd807d736361
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABBA_2threads.c
@@ -0,0 +1,46 @@
+#include <stdio.h>
+#include <pthread.h>
+
+pthread_mutex_t a = PTHREAD_MUTEX_INITIALIZER;
+pthread_mutex_t b = PTHREAD_MUTEX_INITIALIZER;
+pthread_barrier_t bar;
+
+void *ba_lock(void *arg)
+{
+	int ret, i;
+
+	pthread_mutex_lock(&b);
+
+	if (pthread_barrier_wait(&bar) == PTHREAD_BARRIER_SERIAL_THREAD)
+		pthread_barrier_destroy(&bar);
+
+	pthread_mutex_lock(&a);
+
+	pthread_mutex_unlock(&a);
+	pthread_mutex_unlock(&b);
+}
+
+int main(void)
+{
+	pthread_t t;
+
+	pthread_barrier_init(&bar, NULL, 2);
+
+	if (pthread_create(&t, NULL, ba_lock, NULL)) {
+		fprintf(stderr, "pthread_create() failed\n");
+		return 1;
+	}
+	pthread_mutex_lock(&a);
+
+	if (pthread_barrier_wait(&bar) == PTHREAD_BARRIER_SERIAL_THREAD)
+		pthread_barrier_destroy(&bar);
+
+	pthread_mutex_lock(&b);
+
+	pthread_mutex_unlock(&b);
+	pthread_mutex_unlock(&a);
+
+	pthread_join(t, NULL);
+
+	return 0;
+}
diff --git a/tools/lib/lockdep/uinclude/linux/compiler.h b/tools/lib/lockdep/uinclude/linux/compiler.h
index 6386dc3182a0..fd3e56a83fc2 100644
--- a/tools/lib/lockdep/uinclude/linux/compiler.h
+++ b/tools/lib/lockdep/uinclude/linux/compiler.h
@@ -3,6 +3,7 @@
 
 #define __used		__attribute__((__unused__))
 #define unlikely
+#define READ_ONCE(x) (x)
 #define WRITE_ONCE(x, val) x=(val)
 #define RCU_INIT_POINTER(p, v) p=(v)
 
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index c3bd294a63d1..190cc886ab91 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -1951,6 +1951,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
 		   strcmp(token, "*") == 0 ||
 		   strcmp(token, "^") == 0 ||
 		   strcmp(token, "/") == 0 ||
+		   strcmp(token, "%") == 0 ||
 		   strcmp(token, "<") == 0 ||
 		   strcmp(token, ">") == 0 ||
 		   strcmp(token, "<=") == 0 ||
@@ -2397,6 +2398,12 @@ static int arg_num_eval(struct print_arg *arg, long long *val)
 				break;
 			*val = left + right;
 			break;
+		case '~':
+			ret = arg_num_eval(arg->op.right, &right);
+			if (!ret)
+				break;
+			*val = ~right;
+			break;
 		default:
 			do_warning("unknown op '%s'", arg->op.op);
 			ret = 0;
@@ -2634,6 +2641,7 @@ process_hex(struct event_format *event, struct print_arg *arg, char **tok)
 
 free_field:
 	free_arg(arg->hex.field);
+	arg->hex.field = NULL;
 out:
 	*tok = NULL;
 	return EVENT_ERROR;
@@ -2658,8 +2666,10 @@ process_int_array(struct event_format *event, struct print_arg *arg, char **tok)
 
 free_size:
 	free_arg(arg->int_array.count);
+	arg->int_array.count = NULL;
 free_field:
 	free_arg(arg->int_array.field);
+	arg->int_array.field = NULL;
 out:
 	*tok = NULL;
 	return EVENT_ERROR;
@@ -3689,6 +3699,9 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 		case '/':
 			val = left / right;
 			break;
+		case '%':
+			val = left % right;
+			break;
 		case '*':
 			val = left * right;
 			break;
@@ -4971,7 +4984,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 						break;
 					}
 				}
-				if (pevent->long_size == 8 && ls &&
+				if (pevent->long_size == 8 && ls == 1 &&
 				    sizeof(long) != 8) {
 					char *p;
 
@@ -5335,41 +5348,45 @@ static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock)
 	return false;
 }
 
-void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
-			struct pevent_record *record, bool use_trace_clock)
+/**
+ * pevent_find_event_by_record - return the event from a given record
+ * @pevent: a handle to the pevent
+ * @record: The record to get the event from
+ *
+ * Returns the associated event for a given record, or NULL if non is
+ * is found.
+ */
+struct event_format *
+pevent_find_event_by_record(struct pevent *pevent, struct pevent_record *record)
 {
-	static const char *spaces = "                    "; /* 20 spaces */
-	struct event_format *event;
-	unsigned long secs;
-	unsigned long usecs;
-	unsigned long nsecs;
-	const char *comm;
-	void *data = record->data;
 	int type;
-	int pid;
-	int len;
-	int p;
-	bool use_usec_format;
-
-	use_usec_format = is_timestamp_in_us(pevent->trace_clock,
-							use_trace_clock);
-	if (use_usec_format) {
-		secs = record->ts / NSECS_PER_SEC;
-		nsecs = record->ts - secs * NSECS_PER_SEC;
-	}
 
 	if (record->size < 0) {
 		do_warning("ug! negative record size %d", record->size);
-		return;
+		return NULL;
 	}
 
-	type = trace_parse_common_type(pevent, data);
+	type = trace_parse_common_type(pevent, record->data);
 
-	event = pevent_find_event(pevent, type);
-	if (!event) {
-		do_warning("ug! no event found for type %d", type);
-		return;
-	}
+	return pevent_find_event(pevent, type);
+}
+
+/**
+ * pevent_print_event_task - Write the event task comm, pid and CPU
+ * @pevent: a handle to the pevent
+ * @s: the trace_seq to write to
+ * @event: the handle to the record's event
+ * @record: The record to get the event from
+ *
+ * Writes the tasks comm, pid and CPU to @s.
+ */
+void pevent_print_event_task(struct pevent *pevent, struct trace_seq *s,
+			     struct event_format *event,
+			     struct pevent_record *record)
+{
+	void *data = record->data;
+	const char *comm;
+	int pid;
 
 	pid = parse_common_pid(pevent, data);
 	comm = find_cmdline(pevent, pid);
@@ -5377,9 +5394,43 @@ void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
 	if (pevent->latency_format) {
 		trace_seq_printf(s, "%8.8s-%-5d %3d",
 		       comm, pid, record->cpu);
-		pevent_data_lat_fmt(pevent, s, record);
 	} else
 		trace_seq_printf(s, "%16s-%-5d [%03d]", comm, pid, record->cpu);
+}
+
+/**
+ * pevent_print_event_time - Write the event timestamp
+ * @pevent: a handle to the pevent
+ * @s: the trace_seq to write to
+ * @event: the handle to the record's event
+ * @record: The record to get the event from
+ * @use_trace_clock: Set to parse according to the @pevent->trace_clock
+ *
+ * Writes the timestamp of the record into @s.
+ */
+void pevent_print_event_time(struct pevent *pevent, struct trace_seq *s,
+			     struct event_format *event,
+			     struct pevent_record *record,
+			     bool use_trace_clock)
+{
+	unsigned long secs;
+	unsigned long usecs;
+	unsigned long nsecs;
+	int p;
+	bool use_usec_format;
+
+	use_usec_format = is_timestamp_in_us(pevent->trace_clock,
+							use_trace_clock);
+	if (use_usec_format) {
+		secs = record->ts / NSECS_PER_SEC;
+		nsecs = record->ts - secs * NSECS_PER_SEC;
+	}
+
+	if (pevent->latency_format) {
+		trace_seq_printf(s, " %3d", record->cpu);
+		pevent_data_lat_fmt(pevent, s, record);
+	} else
+		trace_seq_printf(s, " [%03d]", record->cpu);
 
 	if (use_usec_format) {
 		if (pevent->flags & PEVENT_NSEC_OUTPUT) {
@@ -5387,14 +5438,36 @@ void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
 			p = 9;
 		} else {
 			usecs = (nsecs + 500) / NSECS_PER_USEC;
+			/* To avoid usecs larger than 1 sec */
+			if (usecs >= 1000000) {
+				usecs -= 1000000;
+				secs++;
+			}
 			p = 6;
 		}
 
-		trace_seq_printf(s, " %5lu.%0*lu: %s: ",
-					secs, p, usecs, event->name);
+		trace_seq_printf(s, " %5lu.%0*lu:", secs, p, usecs);
 	} else
-		trace_seq_printf(s, " %12llu: %s: ",
-					record->ts, event->name);
+		trace_seq_printf(s, " %12llu:", record->ts);
+}
+
+/**
+ * pevent_print_event_data - Write the event data section
+ * @pevent: a handle to the pevent
+ * @s: the trace_seq to write to
+ * @event: the handle to the record's event
+ * @record: The record to get the event from
+ *
+ * Writes the parsing of the record's data to @s.
+ */
+void pevent_print_event_data(struct pevent *pevent, struct trace_seq *s,
+			     struct event_format *event,
+			     struct pevent_record *record)
+{
+	static const char *spaces = "                    "; /* 20 spaces */
+	int len;
+
+	trace_seq_printf(s, " %s: ", event->name);
 
 	/* Space out the event names evenly. */
 	len = strlen(event->name);
@@ -5404,6 +5477,23 @@ void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
 	pevent_event_info(s, event, record);
 }
 
+void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
+			struct pevent_record *record, bool use_trace_clock)
+{
+	struct event_format *event;
+
+	event = pevent_find_event_by_record(pevent, record);
+	if (!event) {
+		do_warning("ug! no event found for type %d",
+			   trace_parse_common_type(pevent, record->data));
+		return;
+	}
+
+	pevent_print_event_task(pevent, s, event, record);
+	pevent_print_event_time(pevent, s, event, record, use_trace_clock);
+	pevent_print_event_data(pevent, s, event, record);
+}
+
 static int events_id_cmp(const void *a, const void *b)
 {
 	struct event_format * const * ea = a;
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 706d9bc24066..9ffde377e89d 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -628,6 +628,16 @@ int pevent_register_print_string(struct pevent *pevent, const char *fmt,
 				 unsigned long long addr);
 int pevent_pid_is_registered(struct pevent *pevent, int pid);
 
+void pevent_print_event_task(struct pevent *pevent, struct trace_seq *s,
+			     struct event_format *event,
+			     struct pevent_record *record);
+void pevent_print_event_time(struct pevent *pevent, struct trace_seq *s,
+			     struct event_format *event,
+			     struct pevent_record *record,
+			     bool use_trace_clock);
+void pevent_print_event_data(struct pevent *pevent, struct trace_seq *s,
+			     struct event_format *event,
+			     struct pevent_record *record);
 void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
 			struct pevent_record *record, bool use_trace_clock);
 
@@ -694,6 +704,9 @@ struct event_format *pevent_find_event(struct pevent *pevent, int id);
 struct event_format *
 pevent_find_event_by_name(struct pevent *pevent, const char *sys, const char *name);
 
+struct event_format *
+pevent_find_event_by_record(struct pevent *pevent, struct pevent_record *record);
+
 void pevent_data_lat_fmt(struct pevent *pevent,
 			 struct trace_seq *s, struct pevent_record *record);
 int pevent_data_type(struct pevent *pevent, struct pevent_record *rec);
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index b9ca1e304158..15949e2a7805 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -8,7 +8,7 @@ perf-config - Get and set variables in a configuration file.
 SYNOPSIS
 --------
 [verse]
-'perf config' -l | --list
+'perf config' [<file-option>] -l | --list
 
 DESCRIPTION
 -----------
@@ -21,6 +21,14 @@ OPTIONS
 --list::
 	Show current config variables, name and value, for all sections.
 
+--user::
+	For writing and reading options: write to user
+	'$HOME/.perfconfig' file or read it.
+
+--system::
+	For writing and reading options: write to system-wide
+	'$(sysconfdir)/perfconfig' or read it.
+
 CONFIGURATION FILE
 ------------------
 
@@ -30,6 +38,10 @@ The '$HOME/.perfconfig' file is used to store a per-user configuration.
 The file '$(sysconfdir)/perfconfig' can be used to
 store a system-wide default configuration.
 
+When reading or writing, the values are read from the system and user
+configuration files by default, and options '--system' and '--user'
+can be used to tell the command to read from or write to only that location.
+
 Syntax
 ~~~~~~
 
@@ -62,7 +74,7 @@ Given a $HOME/.perfconfig like this:
 		medium = green, default
 		normal = lightgray, default
 		selected = white, lightgray
-		code = blue, default
+		jump_arrows = blue, default
 		addr = magenta, default
 		root = white, blue
 
@@ -98,6 +110,347 @@ Given a $HOME/.perfconfig like this:
 		order = caller
 		sort-key = function
 
+Variables
+~~~~~~~~~
+
+colors.*::
+	The variables for customizing the colors used in the output for the
+	'report', 'top' and 'annotate' in the TUI. They should specify the
+	foreground and background colors, separated by a comma, for example:
+
+		medium = green, lightgray
+
+	If you want to use the color configured for you terminal, just leave it
+	as 'default', for example:
+
+		medium = default, lightgray
+
+	Available colors:
+	red, yellow, green, cyan, gray, black, blue,
+	white, default, magenta, lightgray
+
+	colors.top::
+		'top' means a overhead percentage which is more than 5%.
+		And values of this variable specify percentage colors.
+		Basic key values are foreground-color 'red' and
+		background-color 'default'.
+	colors.medium::
+		'medium' means a overhead percentage which has more than 0.5%.
+		Default values are 'green' and 'default'.
+	colors.normal::
+		'normal' means the rest of overhead percentages
+		except 'top', 'medium', 'selected'.
+		Default values are 'lightgray' and 'default'.
+	colors.selected::
+		This selects the colors for the current entry in a list of entries
+		from sub-commands (top, report, annotate).
+		Default values are 'black' and 'lightgray'.
+	colors.jump_arrows::
+		Colors for jump arrows on assembly code listings
+		such as 'jns', 'jmp', 'jane', etc.
+		Default values are 'blue', 'default'.
+	colors.addr::
+		This selects colors for addresses from 'annotate'.
+		Default values are 'magenta', 'default'.
+	colors.root::
+		Colors for headers in the output of a sub-commands (top, report).
+		Default values are 'white', 'blue'.
+
+tui.*, gtk.*::
+	Subcommands that can be configured here are 'top', 'report' and 'annotate'.
+	These values are booleans, for example:
+
+	[tui]
+		top = true
+
+	will make the TUI be the default for the 'top' subcommand. Those will be
+	available if the required libs were detected at tool build time.
+
+buildid.*::
+	buildid.dir::
+		Each executable and shared library in modern distributions comes with a
+		content based identifier that, if available, will be inserted in a
+		'perf.data' file header to, at analysis time find what is needed to do
+		symbol resolution, code annotation, etc.
+
+		The recording tools also stores a hard link or copy in a per-user
+		directory, $HOME/.debug/, of binaries, shared libraries, /proc/kallsyms
+		and /proc/kcore files to be used at analysis time.
+
+		The buildid.dir variable can be used to either change this directory
+		cache location, or to disable it altogether. If you want to disable it,
+		set buildid.dir to /dev/null. The default is $HOME/.debug
+
+annotate.*::
+	These options work only for TUI.
+	These are in control of addresses, jump function, source code
+	in lines of assembly code from a specific program.
+
+	annotate.hide_src_code::
+		If a program which is analyzed has source code,
+		this option lets 'annotate' print a list of assembly code with the source code.
+		For example, let's see a part of a program. There're four lines.
+		If this option is 'true', they can be printed
+		without source code from a program as below.
+
+		│        push   %rbp
+		│        mov    %rsp,%rbp
+		│        sub    $0x10,%rsp
+		│        mov    (%rdi),%rdx
+
+		But if this option is 'false', source code of the part
+		can be also printed as below. Default is 'false'.
+
+		│      struct rb_node *rb_next(const struct rb_node *node)
+		│      {
+		│        push   %rbp
+		│        mov    %rsp,%rbp
+		│        sub    $0x10,%rsp
+		│              struct rb_node *parent;
+		│
+		│              if (RB_EMPTY_NODE(node))
+		│        mov    (%rdi),%rdx
+		│              return n;
+
+        annotate.use_offset::
+		Basing on a first address of a loaded function, offset can be used.
+		Instead of using original addresses of assembly code,
+		addresses subtracted from a base address can be printed.
+		Let's illustrate an example.
+		If a base address is 0XFFFFFFFF81624d50 as below,
+
+		ffffffff81624d50 <load0>
+
+		an address on assembly code has a specific absolute address as below
+
+		ffffffff816250b8:│  mov    0x8(%r14),%rdi
+
+		but if use_offset is 'true', an address subtracted from a base address is printed.
+		Default is true. This option is only applied to TUI.
+
+		             368:│  mov    0x8(%r14),%rdi
+
+	annotate.jump_arrows::
+		There can be jump instruction among assembly code.
+		Depending on a boolean value of jump_arrows,
+		arrows can be printed or not which represent
+		where do the instruction jump into as below.
+
+		│     ┌──jmp    1333
+		│     │  xchg   %ax,%ax
+		│1330:│  mov    %r15,%r10
+		│1333:└─→cmp    %r15,%r14
+
+		If jump_arrow is 'false', the arrows isn't printed as below.
+		Default is 'false'.
+
+		│      ↓ jmp    1333
+		│        xchg   %ax,%ax
+		│1330:   mov    %r15,%r10
+		│1333:   cmp    %r15,%r14
+
+        annotate.show_linenr::
+		When showing source code if this option is 'true',
+		line numbers are printed as below.
+
+		│1628         if (type & PERF_SAMPLE_IDENTIFIER) {
+		│     ↓ jne    508
+		│1628                 data->id = *array;
+		│1629                 array++;
+		│1630         }
+
+		However if this option is 'false', they aren't printed as below.
+		Default is 'false'.
+
+		│             if (type & PERF_SAMPLE_IDENTIFIER) {
+		│     ↓ jne    508
+		│                     data->id = *array;
+		│                     array++;
+		│             }
+
+        annotate.show_nr_jumps::
+		Let's see a part of assembly code.
+
+		│1382:   movb   $0x1,-0x270(%rbp)
+
+		If use this, the number of branches jumping to that address can be printed as below.
+		Default is 'false'.
+
+		│1 1382:   movb   $0x1,-0x270(%rbp)
+
+        annotate.show_total_period::
+		To compare two records on an instruction base, with this option
+		provided, display total number of samples that belong to a line
+		in assembly code. If this option is 'true', total periods are printed
+		instead of percent values as below.
+
+		  302 │      mov    %eax,%eax
+
+		But if this option is 'false', percent values for overhead are printed i.e.
+		Default is 'false'.
+
+		99.93 │      mov    %eax,%eax
+
+hist.*::
+	hist.percentage::
+		This option control the way to calculate overhead of filtered entries -
+		that means the value of this option is effective only if there's a
+		filter (by comm, dso or symbol name). Suppose a following example:
+
+		       Overhead  Symbols
+		       ........  .......
+		        33.33%     foo
+		        33.33%     bar
+		        33.33%     baz
+
+	       This is an original overhead and we'll filter out the first 'foo'
+	       entry. The value of 'relative' would increase the overhead of 'bar'
+	       and 'baz' to 50.00% for each, while 'absolute' would show their
+	       current overhead (33.33%).
+
+ui.*::
+	ui.show-headers::
+		This option controls display of column headers (like 'Overhead' and 'Symbol')
+		in 'report' and 'top'. If this option is false, they are hidden.
+		This option is only applied to TUI.
+
+call-graph.*::
+	When sub-commands 'top' and 'report' work with -g/—-children
+	there're options in control of call-graph.
+
+	call-graph.record-mode::
+		The record-mode can be 'fp' (frame pointer), 'dwarf' and 'lbr'.
+		The value of 'dwarf' is effective only if perf detect needed library
+		(libunwind or a recent version of libdw).
+		'lbr' only work for cpus that support it.
+
+	call-graph.dump-size::
+		The size of stack to dump in order to do post-unwinding. Default is 8192 (byte).
+		When using dwarf into record-mode, the default size will be used if omitted.
+
+	call-graph.print-type::
+		The print-types can be graph (graph absolute), fractal (graph relative),
+		flat and folded. This option controls a way to show overhead for each callchain
+		entry. Suppose a following example.
+
+                Overhead  Symbols
+                ........  .......
+                  40.00%  foo
+                          |
+                          ---foo
+                             |
+                             |--50.00%--bar
+                             |          main
+                             |
+                              --50.00%--baz
+                                        main
+
+		This output is a 'fractal' format. The 'foo' came from 'bar' and 'baz' exactly
+		half and half so 'fractal' shows 50.00% for each
+		(meaning that it assumes 100% total overhead of 'foo').
+
+		The 'graph' uses absolute overhead value of 'foo' as total so each of
+		'bar' and 'baz' callchain will have 20.00% of overhead.
+		If 'flat' is used, single column and linear exposure of call chains.
+		'folded' mean call chains are displayed in a line, separated by semicolons.
+
+	call-graph.order::
+		This option controls print order of callchains. The default is
+		'callee' which means callee is printed at top and then followed by its
+		caller and so on. The 'caller' prints it in reverse order.
+
+		If this option is not set and report.children or top.children is
+		set to true (or the equivalent command line option is given),
+		the default value of this option is changed to 'caller' for the
+		execution of 'perf report' or 'perf top'. Other commands will
+		still default to 'callee'.
+
+	call-graph.sort-key::
+		The callchains are merged if they contain same information.
+		The sort-key option determines a way to compare the callchains.
+		A value of 'sort-key' can be 'function' or 'address'.
+		The default is 'function'.
+
+	call-graph.threshold::
+		When there're many callchains it'd print tons of lines. So perf omits
+		small callchains under a certain overhead (threshold) and this option
+		control the threshold. Default is 0.5 (%). The overhead is calculated
+		by value depends on call-graph.print-type.
+
+	call-graph.print-limit::
+		This is a maximum number of lines of callchain printed for a single
+		histogram entry. Default is 0 which means no limitation.
+
+report.*::
+	report.percent-limit::
+		This one is mostly the same as call-graph.threshold but works for
+		histogram entries. Entries having an overhead lower than this
+		percentage will not be printed. Default is '0'. If percent-limit
+		is '10', only entries which have more than 10% of overhead will be
+		printed.
+
+	report.queue-size::
+		This option sets up the maximum allocation size of the internal
+		event queue for ordering events. Default is 0, meaning no limit.
+
+	report.children::
+		'Children' means functions called from another function.
+		If this option is true, 'perf report' cumulates callchains of children
+		and show (accumulated) total overhead as well as 'Self' overhead.
+		Please refer to the 'perf report' manual. The default is 'true'.
+
+	report.group::
+		This option is to show event group information together.
+		Example output with this turned on, notice that there is one column
+		per event in the group, ref-cycles and cycles:
+
+		# group: {ref-cycles,cycles}
+		# ========
+		#
+		# Samples: 7K of event 'anon group { ref-cycles, cycles }'
+		# Event count (approx.): 6876107743
+		#
+		#         Overhead  Command      Shared Object               Symbol
+		# ................  .......  .................  ...................
+		#
+		    99.84%  99.76%  noploop  noploop            [.] main
+		     0.07%   0.00%  noploop  ld-2.15.so         [.] strcmp
+		     0.03%   0.00%  noploop  [kernel.kallsyms]  [k] timerqueue_del
+
+top.*::
+	top.children::
+		Same as 'report.children'. So if it is enabled, the output of 'top'
+		command will have 'Children' overhead column as well as 'Self' overhead
+		column by default.
+		The default is 'true'.
+
+man.*::
+	man.viewer::
+		This option can assign a tool to view manual pages when 'help'
+		subcommand was invoked. Supported tools are 'man', 'woman'
+		(with emacs client) and 'konqueror'. Default is 'man'.
+
+		New man viewer tool can be also added using 'man.<tool>.cmd'
+		or use different path using 'man.<tool>.path' config option.
+
+pager.*::
+	pager.<subcommand>::
+		When the subcommand is run on stdio, determine whether it uses
+		pager or not based on this value. Default is 'unspecified'.
+
+kmem.*::
+	kmem.default::
+		This option decides which allocator is to be analyzed if neither
+		'--slab' nor '--page' option is used. Default is 'slab'.
+
+record.*::
+	record.build-id::
+		This option can be 'cache', 'no-cache' or 'skip'.
+		'cache' is to post-process data and save/update the binaries into
+		the build-id cache (in ~/.debug). This is the default.
+		But if this option is 'no-cache', it will not update the build-id cache.
+		'skip' skips post-processing and does not update the cache.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
index 0b1cedeef895..87b2588d1cbd 100644
--- a/tools/perf/Documentation/perf-inject.txt
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -53,6 +53,13 @@ include::itrace.txt[]
 --strip::
 	Use with --itrace to strip out non-synthesized events.
 
+-j::
+--jit::
+	Process jitdump files by injecting the mmap records corresponding to jitted
+	functions. This option also generates the ELF images for each jitted function
+	found in the jitdumps files captured in the input perf.data file. Use this option
+	if you are monitoring environment using JIT runtimes, such as Java, DART or V8.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index fbceb631387c..19aa17532a16 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -341,6 +341,12 @@ Specify vmlinux path which has debuginfo.
 --buildid-all::
 Record build-id of all DSOs regardless whether it's actually hit or not.
 
+--all-kernel::
+Configure all used events to run in kernel space.
+
+--all-user::
+Configure all used events to run in user space.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 8a301f6afb37..12113992ac9d 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -117,6 +117,22 @@ OPTIONS
 	And default sort keys are changed to comm, dso_from, symbol_from, dso_to
 	and symbol_to, see '--branch-stack'.
 
+	If the --mem-mode option is used, the following sort keys are also available
+	(incompatible with --branch-stack):
+	symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline.
+
+	- symbol_daddr: name of data symbol being executed on at the time of sample
+	- dso_daddr: name of library or module containing the data being executed
+	on at the time of the sample
+	- locked: whether the bus was locked at the time of the sample
+	- tlb: type of tlb access for the data at the time of the sample
+	- mem: type of memory access for the data at the time of the sample
+	- snoop: type of snoop (if any) for the data at the time of the sample
+	- dcacheline: the cacheline the data address is on at the time of the sample
+
+	And the default sort keys are changed to local_weight, mem, sym, dso,
+	symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.
+
 	If the data file has tracepoint event(s), following (dynamic) sort keys
 	are also available:
 	trace, trace_fields, [<event>.]<field>[/raw]
@@ -151,22 +167,6 @@ OPTIONS
 	By default, every sort keys not specified in -F will be appended
 	automatically.
 
-	If --mem-mode option is used, following sort keys are also available
-	(incompatible with --branch-stack):
-	symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline.
-
-	- symbol_daddr: name of data symbol being executed on at the time of sample
-	- dso_daddr: name of library or module containing the data being executed
-	on at the time of sample
-	- locked: whether the bus was locked at the time of sample
-	- tlb: type of tlb access for the data at the time of sample
-	- mem: type of memory access for the data at the time of sample
-	- snoop: type of snoop (if any) for the data at the time of sample
-	- dcacheline: the cacheline the data address is on at the time of sample
-
-	And default sort keys are changed to local_weight, mem, sym, dso,
-	symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.
-
 -p::
 --parent=<regex>::
         A regex filter to identify parent. The parent is a caller of this
@@ -351,7 +351,10 @@ OPTIONS
 
 --percent-limit::
 	Do not show entries which have an overhead under that percent.
-	(Default: 0).
+	(Default: 0).  Note that this option also sets the percent limit (threshold)
+	of callchains.  However the default value of callchain threshold is
+	different than the default value of hist entries.  Please see the
+	--call-graph option for details.
 
 --percentage::
 	Determine how to display the overhead percentage of filtered entries.
@@ -398,6 +401,9 @@ include::itrace.txt[]
 --raw-trace::
 	When displaying traceevent output, do not use print fmt or plugins.
 
+--hierarchy::
+	Enable hierarchical output.
+
 include::callchain-overhead-calculation.txt[]
 
 SEE ALSO
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 52ef7a9d50aa..04f23b404bbc 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -69,6 +69,14 @@ report::
 --scale::
 	scale/normalize counter values
 
+-d::
+--detailed::
+	print more detailed statistics, can be specified up to 3 times
+
+	   -d:          detailed events, L1 and LLC data cache
+        -d -d:     more detailed events, dTLB and iTLB events
+     -d -d -d:     very detailed events, adding prefetch events
+
 -r::
 --repeat=<n>::
 	repeat command and print average + stddev (max: 100). 0 means forever.
@@ -139,6 +147,10 @@ Print count deltas every N milliseconds (minimum: 10ms)
 The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals.  Use with caution.
 	example: 'perf stat -I 1000 -e cycles -a sleep 5'
 
+--metric-only::
+Only print computed metrics. Print them in a single line.
+Don't show any raw values. Not supported with --per-thread.
+
 --per-socket::
 Aggregate counts per processor socket for system-wide mode measurements.  This
 is a useful mode to detect imbalance between sockets.  To enable this mode,
@@ -211,6 +223,29 @@ $ perf stat -- make -j
 
  Wall-clock time elapsed:   719.554352 msecs
 
+CSV FORMAT
+----------
+
+With -x, perf stat is able to output a not-quite-CSV format output
+Commas in the output are not put into "". To make it easy to parse
+it is recommended to use a different character like -x \;
+
+The fields are in this order:
+
+	- optional usec time stamp in fractions of second (with -I xxx)
+	- optional CPU, core, or socket identifier
+	- optional number of logical CPUs aggregated
+	- counter value
+	- unit of the counter value or empty
+	- event name
+	- run time of counter
+	- percentage of measurement time the counter was running
+	- optional variance if multiple values are collected with -r
+	- optional metric value
+	- optional unit of metric
+
+Additional metrics may be printed with all earlier fields being empty.
+
 SEE ALSO
 --------
 linkperf:perf-top[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index b0e60e17db38..19f046f027cd 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -233,6 +233,9 @@ Default is to monitor all CPUS.
 --raw-trace::
 	When displaying traceevent output, do not use print fmt or plugins.
 
+--hierarchy::
+	Enable hierarchy output.
+
 INTERACTIVE PROMPTING KEYS
 --------------------------
 
diff --git a/tools/perf/Documentation/perfconfig.example b/tools/perf/Documentation/perfconfig.example
index 767ea2436e1c..1d8d5bc4cd2d 100644
--- a/tools/perf/Documentation/perfconfig.example
+++ b/tools/perf/Documentation/perfconfig.example
@@ -5,7 +5,7 @@
 	medium = green, lightgray
 	normal = black, lightgray
 	selected = lightgray, magenta
-	code = blue, lightgray
+	jump_arrows = blue, lightgray
 	addr = magenta, lightgray
 
 [tui]
diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt
index e0ce9573b79b..5950b5a24efd 100644
--- a/tools/perf/Documentation/tips.txt
+++ b/tools/perf/Documentation/tips.txt
@@ -27,3 +27,4 @@ Skip collecing build-id when recording: perf record -B
 To change sampling frequency to 100 Hz: perf record -F 100
 See assembly instructions with percentage: perf annotate <symbol>
 If you prefer Intel style assembly, try: perf annotate -M intel
+For hierarchical output, try: perf report --hierarchy
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index dcd9a70c7193..32a64e619028 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -68,6 +68,20 @@ all tags TAGS:
 	$(print_msg)
 	$(make)
 
+ifdef MAKECMDGOALS
+has_clean := 0
+ifneq ($(filter clean,$(MAKECMDGOALS)),)
+  has_clean := 1
+endif # clean
+
+ifeq ($(has_clean),1)
+  rest := $(filter-out clean,$(MAKECMDGOALS))
+  ifneq ($(rest),)
+$(rest): clean
+  endif # rest
+endif # has_clean
+endif # MAKECMDGOALS
+
 #
 # The clean target is not really parallel, don't print the jobs info:
 #
@@ -75,10 +89,17 @@ clean:
 	$(make)
 
 #
-# The build-test target is not really parallel, don't print the jobs info:
+# The build-test target is not really parallel, don't print the jobs info,
+# it also uses only the tests/make targets that don't pollute the source
+# repository, i.e. that uses O= or builds the tarpkg outside the source
+# repo directories.
+#
+# For a full test, use:
+#
+# make -C tools/perf -f tests/make
 #
 build-test:
-	@$(MAKE) SHUF=1 -f tests/make --no-print-directory
+	@$(MAKE) SHUF=1 -f tests/make REUSE_FEATURES_DUMP=1 MK=Makefile SET_PARALLEL=1 --no-print-directory tarpkg out
 
 #
 # All other targets get passed through:
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 5d34815c7ccb..4a4fad4182f5 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -58,6 +58,9 @@ include config/utilities.mak
 #
 # Define NO_LIBBIONIC if you do not want bionic support
 #
+# Define NO_LIBCRYPTO if you do not want libcrypto (openssl) support
+# used for generating build-ids for ELFs generated by jitdump.
+#
 # Define NO_LIBDW_DWARF_UNWIND if you do not want libdw support
 # for dwarf backtrace post unwind.
 #
@@ -136,6 +139,8 @@ $(call allow-override,CC,$(CROSS_COMPILE)gcc)
 $(call allow-override,AR,$(CROSS_COMPILE)ar)
 $(call allow-override,LD,$(CROSS_COMPILE)ld)
 
+LD += $(EXTRA_LDFLAGS)
+
 PKG_CONFIG = $(CROSS_COMPILE)pkg-config
 
 RM      = rm -f
@@ -165,7 +170,16 @@ ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
 endif
 endif
 
+# Set FEATURE_TESTS to 'all' so all possible feature checkers are executed.
+# Without this setting the output feature dump file misses some features, for
+# example, liberty. Select all checkers so we won't get an incomplete feature
+# dump file.
 ifeq ($(config),1)
+ifdef MAKECMDGOALS
+ifeq ($(filter feature-dump,$(MAKECMDGOALS)),feature-dump)
+FEATURE_TESTS := all
+endif
+endif
 include config/Makefile
 endif
 
@@ -618,7 +632,7 @@ clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
 		$(OUTPUT)util/intel-pt-decoder/inat-tables.c $(OUTPUT)fixdep \
-		$(OUTPUT)tests/llvm-src-{base,kbuild,prologue}.c
+		$(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
 	$(python-clean)
 
diff --git a/tools/perf/arch/arm/Makefile b/tools/perf/arch/arm/Makefile
index 7fbca175099e..18b13518d8d8 100644
--- a/tools/perf/arch/arm/Makefile
+++ b/tools/perf/arch/arm/Makefile
@@ -1,3 +1,4 @@
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
+PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 7fbca175099e..18b13518d8d8 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -1,3 +1,4 @@
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
+PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index 7fbca175099e..56e05f126ad8 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -1,3 +1,6 @@
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
+
+HAVE_KVM_STAT_SUPPORT := 1
+PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 7b8b0d1a1b62..c8fe2074d217 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -1,5 +1,6 @@
 libperf-y += header.o
 libperf-y += sym-handling.o
+libperf-y += kvm-stat.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_DWARF) += skip-callchain-idx.o
diff --git a/tools/perf/arch/powerpc/util/book3s_hcalls.h b/tools/perf/arch/powerpc/util/book3s_hcalls.h
new file mode 100644
index 000000000000..0dd6b7f2d44f
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/book3s_hcalls.h
@@ -0,0 +1,123 @@
+#ifndef ARCH_PERF_BOOK3S_HV_HCALLS_H
+#define ARCH_PERF_BOOK3S_HV_HCALLS_H
+
+/*
+ * PowerPC HCALL codes : hcall code to name mapping
+ */
+#define kvm_trace_symbol_hcall \
+	{0x4, "H_REMOVE"},					\
+	{0x8, "H_ENTER"},					\
+	{0xc, "H_READ"},					\
+	{0x10, "H_CLEAR_MOD"},					\
+	{0x14, "H_CLEAR_REF"},					\
+	{0x18, "H_PROTECT"},					\
+	{0x1c, "H_GET_TCE"},					\
+	{0x20, "H_PUT_TCE"},					\
+	{0x24, "H_SET_SPRG0"},					\
+	{0x28, "H_SET_DABR"},					\
+	{0x2c, "H_PAGE_INIT"},					\
+	{0x30, "H_SET_ASR"},					\
+	{0x34, "H_ASR_ON"},					\
+	{0x38, "H_ASR_OFF"},					\
+	{0x3c, "H_LOGICAL_CI_LOAD"},				\
+	{0x40, "H_LOGICAL_CI_STORE"},				\
+	{0x44, "H_LOGICAL_CACHE_LOAD"},				\
+	{0x48, "H_LOGICAL_CACHE_STORE"},			\
+	{0x4c, "H_LOGICAL_ICBI"},				\
+	{0x50, "H_LOGICAL_DCBF"},				\
+	{0x54, "H_GET_TERM_CHAR"},				\
+	{0x58, "H_PUT_TERM_CHAR"},				\
+	{0x5c, "H_REAL_TO_LOGICAL"},				\
+	{0x60, "H_HYPERVISOR_DATA"},				\
+	{0x64, "H_EOI"},					\
+	{0x68, "H_CPPR"},					\
+	{0x6c, "H_IPI"},					\
+	{0x70, "H_IPOLL"},					\
+	{0x74, "H_XIRR"},					\
+	{0x78, "H_MIGRATE_DMA"},				\
+	{0x7c, "H_PERFMON"},					\
+	{0xdc, "H_REGISTER_VPA"},				\
+	{0xe0, "H_CEDE"},					\
+	{0xe4, "H_CONFER"},					\
+	{0xe8, "H_PROD"},					\
+	{0xec, "H_GET_PPP"},					\
+	{0xf0, "H_SET_PPP"},					\
+	{0xf4, "H_PURR"},					\
+	{0xf8, "H_PIC"},					\
+	{0xfc, "H_REG_CRQ"},					\
+	{0x100, "H_FREE_CRQ"},					\
+	{0x104, "H_VIO_SIGNAL"},				\
+	{0x108, "H_SEND_CRQ"},					\
+	{0x110, "H_COPY_RDMA"},					\
+	{0x114, "H_REGISTER_LOGICAL_LAN"},			\
+	{0x118, "H_FREE_LOGICAL_LAN"},				\
+	{0x11c, "H_ADD_LOGICAL_LAN_BUFFER"},			\
+	{0x120, "H_SEND_LOGICAL_LAN"},				\
+	{0x124, "H_BULK_REMOVE"},				\
+	{0x130, "H_MULTICAST_CTRL"},				\
+	{0x134, "H_SET_XDABR"},					\
+	{0x138, "H_STUFF_TCE"},					\
+	{0x13c, "H_PUT_TCE_INDIRECT"},				\
+	{0x14c, "H_CHANGE_LOGICAL_LAN_MAC"},			\
+	{0x150, "H_VTERM_PARTNER_INFO"},			\
+	{0x154, "H_REGISTER_VTERM"},				\
+	{0x158, "H_FREE_VTERM"},				\
+	{0x15c, "H_RESET_EVENTS"},				\
+	{0x160, "H_ALLOC_RESOURCE"},				\
+	{0x164, "H_FREE_RESOURCE"},				\
+	{0x168, "H_MODIFY_QP"},					\
+	{0x16c, "H_QUERY_QP"},					\
+	{0x170, "H_REREGISTER_PMR"},				\
+	{0x174, "H_REGISTER_SMR"},				\
+	{0x178, "H_QUERY_MR"},					\
+	{0x17c, "H_QUERY_MW"},					\
+	{0x180, "H_QUERY_HCA"},					\
+	{0x184, "H_QUERY_PORT"},				\
+	{0x188, "H_MODIFY_PORT"},				\
+	{0x18c, "H_DEFINE_AQP1"},				\
+	{0x190, "H_GET_TRACE_BUFFER"},				\
+	{0x194, "H_DEFINE_AQP0"},				\
+	{0x198, "H_RESIZE_MR"},					\
+	{0x19c, "H_ATTACH_MCQP"},				\
+	{0x1a0, "H_DETACH_MCQP"},				\
+	{0x1a4, "H_CREATE_RPT"},				\
+	{0x1a8, "H_REMOVE_RPT"},				\
+	{0x1ac, "H_REGISTER_RPAGES"},				\
+	{0x1b0, "H_DISABLE_AND_GETC"},				\
+	{0x1b4, "H_ERROR_DATA"},				\
+	{0x1b8, "H_GET_HCA_INFO"},				\
+	{0x1bc, "H_GET_PERF_COUNT"},				\
+	{0x1c0, "H_MANAGE_TRACE"},				\
+	{0x1d4, "H_FREE_LOGICAL_LAN_BUFFER"},			\
+	{0x1d8, "H_POLL_PENDING"},				\
+	{0x1e4, "H_QUERY_INT_STATE"},				\
+	{0x244, "H_ILLAN_ATTRIBUTES"},				\
+	{0x250, "H_MODIFY_HEA_QP"},				\
+	{0x254, "H_QUERY_HEA_QP"},				\
+	{0x258, "H_QUERY_HEA"},					\
+	{0x25c, "H_QUERY_HEA_PORT"},				\
+	{0x260, "H_MODIFY_HEA_PORT"},				\
+	{0x264, "H_REG_BCMC"},					\
+	{0x268, "H_DEREG_BCMC"},				\
+	{0x26c, "H_REGISTER_HEA_RPAGES"},			\
+	{0x270, "H_DISABLE_AND_GET_HEA"},			\
+	{0x274, "H_GET_HEA_INFO"},				\
+	{0x278, "H_ALLOC_HEA_RESOURCE"},			\
+	{0x284, "H_ADD_CONN"},					\
+	{0x288, "H_DEL_CONN"},					\
+	{0x298, "H_JOIN"},					\
+	{0x2a4, "H_VASI_STATE"},				\
+	{0x2b0, "H_ENABLE_CRQ"},				\
+	{0x2b8, "H_GET_EM_PARMS"},				\
+	{0x2d0, "H_SET_MPP"},					\
+	{0x2d4, "H_GET_MPP"},					\
+	{0x2ec, "H_HOME_NODE_ASSOCIATIVITY"},			\
+	{0x2f4, "H_BEST_ENERGY"},				\
+	{0x2fc, "H_XIRR_X"},					\
+	{0x300, "H_RANDOM"},					\
+	{0x304, "H_COP"},					\
+	{0x314, "H_GET_MPP_X"},					\
+	{0x31c, "H_SET_MODE"},					\
+	{0xf000, "H_RTAS"}					\
+
+#endif
diff --git a/tools/perf/arch/powerpc/util/book3s_hv_exits.h b/tools/perf/arch/powerpc/util/book3s_hv_exits.h
new file mode 100644
index 000000000000..e68ba2da8970
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/book3s_hv_exits.h
@@ -0,0 +1,33 @@
+#ifndef ARCH_PERF_BOOK3S_HV_EXITS_H
+#define ARCH_PERF_BOOK3S_HV_EXITS_H
+
+/*
+ * PowerPC Interrupt vectors : exit code to name mapping
+ */
+
+#define kvm_trace_symbol_exit \
+	{0x0,	"RETURN_TO_HOST"}, \
+	{0x100, "SYSTEM_RESET"}, \
+	{0x200, "MACHINE_CHECK"}, \
+	{0x300, "DATA_STORAGE"}, \
+	{0x380, "DATA_SEGMENT"}, \
+	{0x400, "INST_STORAGE"}, \
+	{0x480, "INST_SEGMENT"}, \
+	{0x500, "EXTERNAL"}, \
+	{0x501, "EXTERNAL_LEVEL"}, \
+	{0x502, "EXTERNAL_HV"}, \
+	{0x600, "ALIGNMENT"}, \
+	{0x700, "PROGRAM"}, \
+	{0x800, "FP_UNAVAIL"}, \
+	{0x900, "DECREMENTER"}, \
+	{0x980, "HV_DECREMENTER"}, \
+	{0xc00, "SYSCALL"}, \
+	{0xd00, "TRACE"}, \
+	{0xe00, "H_DATA_STORAGE"}, \
+	{0xe20, "H_INST_STORAGE"}, \
+	{0xe40, "H_EMUL_ASSIST"}, \
+	{0xf00, "PERFMON"}, \
+	{0xf20, "ALTIVEC"}, \
+	{0xf40, "VSX"}
+
+#endif
diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c
new file mode 100644
index 000000000000..74eee30398f8
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/kvm-stat.c
@@ -0,0 +1,170 @@
+#include "util/kvm-stat.h"
+#include "util/parse-events.h"
+#include "util/debug.h"
+
+#include "book3s_hv_exits.h"
+#include "book3s_hcalls.h"
+
+#define NR_TPS 4
+
+const char *vcpu_id_str = "vcpu_id";
+const int decode_str_len = 40;
+const char *kvm_entry_trace = "kvm_hv:kvm_guest_enter";
+const char *kvm_exit_trace = "kvm_hv:kvm_guest_exit";
+
+define_exit_reasons_table(hv_exit_reasons, kvm_trace_symbol_exit);
+define_exit_reasons_table(hcall_reasons, kvm_trace_symbol_hcall);
+
+/* Tracepoints specific to ppc_book3s_hv */
+const char *ppc_book3s_hv_kvm_tp[] = {
+	"kvm_hv:kvm_guest_enter",
+	"kvm_hv:kvm_guest_exit",
+	"kvm_hv:kvm_hcall_enter",
+	"kvm_hv:kvm_hcall_exit",
+	NULL,
+};
+
+/* 1 extra placeholder for NULL */
+const char *kvm_events_tp[NR_TPS + 1];
+const char *kvm_exit_reason;
+
+static void hcall_event_get_key(struct perf_evsel *evsel,
+				struct perf_sample *sample,
+				struct event_key *key)
+{
+	key->info = 0;
+	key->key = perf_evsel__intval(evsel, sample, "req");
+}
+
+static const char *get_hcall_exit_reason(u64 exit_code)
+{
+	struct exit_reasons_table *tbl = hcall_reasons;
+
+	while (tbl->reason != NULL) {
+		if (tbl->exit_code == exit_code)
+			return tbl->reason;
+		tbl++;
+	}
+
+	pr_debug("Unknown hcall code: %lld\n",
+	       (unsigned long long)exit_code);
+	return "UNKNOWN";
+}
+
+static bool hcall_event_end(struct perf_evsel *evsel,
+			    struct perf_sample *sample __maybe_unused,
+			    struct event_key *key __maybe_unused)
+{
+	return (!strcmp(evsel->name, kvm_events_tp[3]));
+}
+
+static bool hcall_event_begin(struct perf_evsel *evsel,
+			      struct perf_sample *sample, struct event_key *key)
+{
+	if (!strcmp(evsel->name, kvm_events_tp[2])) {
+		hcall_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+static void hcall_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
+				   struct event_key *key,
+				   char *decode)
+{
+	const char *hcall_reason = get_hcall_exit_reason(key->key);
+
+	scnprintf(decode, decode_str_len, "%s", hcall_reason);
+}
+
+static struct kvm_events_ops hcall_events = {
+	.is_begin_event = hcall_event_begin,
+	.is_end_event = hcall_event_end,
+	.decode_key = hcall_event_decode_key,
+	.name = "HCALL-EVENT",
+};
+
+static struct kvm_events_ops exit_events = {
+	.is_begin_event = exit_event_begin,
+	.is_end_event = exit_event_end,
+	.decode_key = exit_event_decode_key,
+	.name = "VM-EXIT"
+};
+
+struct kvm_reg_events_ops kvm_reg_events_ops[] = {
+	{ .name = "vmexit", .ops = &exit_events },
+	{ .name = "hcall", .ops = &hcall_events },
+	{ NULL, NULL },
+};
+
+const char * const kvm_skip_events[] = {
+	NULL,
+};
+
+
+static int is_tracepoint_available(const char *str, struct perf_evlist *evlist)
+{
+	struct parse_events_error err;
+	int ret;
+
+	err.str = NULL;
+	ret = parse_events(evlist, str, &err);
+	if (err.str)
+		pr_err("%s : %s\n", str, err.str);
+	return ret;
+}
+
+static int ppc__setup_book3s_hv(struct perf_kvm_stat *kvm,
+				struct perf_evlist *evlist)
+{
+	const char **events_ptr;
+	int i, nr_tp = 0, err = -1;
+
+	/* Check for book3s_hv tracepoints */
+	for (events_ptr = ppc_book3s_hv_kvm_tp; *events_ptr; events_ptr++) {
+		err = is_tracepoint_available(*events_ptr, evlist);
+		if (err)
+			return -1;
+		nr_tp++;
+	}
+
+	for (i = 0; i < nr_tp; i++)
+		kvm_events_tp[i] = ppc_book3s_hv_kvm_tp[i];
+
+	kvm_events_tp[i] = NULL;
+	kvm_exit_reason = "trap";
+	kvm->exit_reasons = hv_exit_reasons;
+	kvm->exit_reasons_isa = "HV";
+
+	return 0;
+}
+
+/* Wrapper to setup kvm tracepoints */
+static int ppc__setup_kvm_tp(struct perf_kvm_stat *kvm)
+{
+	struct perf_evlist *evlist = perf_evlist__new();
+
+	if (evlist == NULL)
+		return -ENOMEM;
+
+	/* Right now, only supported on book3s_hv */
+	return ppc__setup_book3s_hv(kvm, evlist);
+}
+
+int setup_kvm_events_tp(struct perf_kvm_stat *kvm)
+{
+	return ppc__setup_kvm_tp(kvm);
+}
+
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused)
+{
+	int ret;
+
+	ret = ppc__setup_kvm_tp(kvm);
+	if (ret) {
+		kvm->exit_reasons = NULL;
+		kvm->exit_reasons_isa = NULL;
+	}
+
+	return ret;
+}
diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c
index a5dbc07ec9dc..ed57df2e6d68 100644
--- a/tools/perf/arch/s390/util/kvm-stat.c
+++ b/tools/perf/arch/s390/util/kvm-stat.c
@@ -10,7 +10,7 @@
  */
 
 #include "../../util/kvm-stat.h"
-#include <asm/kvm_perf.h>
+#include <asm/sie.h>
 
 define_exit_reasons_table(sie_exit_reasons, sie_intercept_code);
 define_exit_reasons_table(sie_icpt_insn_codes, icpt_insn_codes);
@@ -18,6 +18,12 @@ define_exit_reasons_table(sie_sigp_order_codes, sigp_order_codes);
 define_exit_reasons_table(sie_diagnose_codes, diagnose_codes);
 define_exit_reasons_table(sie_icpt_prog_codes, icpt_prog_codes);
 
+const char *vcpu_id_str = "id";
+const int decode_str_len = 40;
+const char *kvm_exit_reason = "icptcode";
+const char *kvm_entry_trace = "kvm:kvm_s390_sie_enter";
+const char *kvm_exit_trace = "kvm:kvm_s390_sie_exit";
+
 static void event_icpt_insn_get_key(struct perf_evsel *evsel,
 				    struct perf_sample *sample,
 				    struct event_key *key)
@@ -73,7 +79,7 @@ static struct kvm_events_ops exit_events = {
 	.name = "VM-EXIT"
 };
 
-const char * const kvm_events_tp[] = {
+const char *kvm_events_tp[] = {
 	"kvm:kvm_s390_sie_enter",
 	"kvm:kvm_s390_sie_exit",
 	"kvm:kvm_s390_intercept_instruction",
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 09ba923debe8..269af2143735 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -3,3 +3,4 @@ PERF_HAVE_DWARF_REGS := 1
 endif
 HAVE_KVM_STAT_SUPPORT := 1
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
+PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c
index 7bb0d13c235f..72193f19d6d7 100644
--- a/tools/perf/arch/x86/tests/rdpmc.c
+++ b/tools/perf/arch/x86/tests/rdpmc.c
@@ -59,7 +59,7 @@ static u64 mmap_read_self(void *addr)
 		u64 quot, rem;
 
 		quot = (cyc >> time_shift);
-		rem = cyc & ((1 << time_shift) - 1);
+		rem = cyc & (((u64)1 << time_shift) - 1);
 		delta = time_offset + quot * time_mult +
 			((rem * time_mult) >> time_shift);
 
@@ -103,6 +103,7 @@ static int __test__rdpmc(void)
 
 	sigfillset(&sa.sa_mask);
 	sa.sa_sigaction = segfault_handler;
+	sa.sa_flags = 0;
 	sigaction(SIGSEGV, &sa, NULL);
 
 	fd = sys_perf_event_open(&attr, 0, -1, -1,
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 8d8150f1cf9b..d66f9ad4df2e 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -60,7 +60,9 @@ struct branch {
 	u64 misc;
 };
 
-static size_t intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused)
+static size_t
+intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+			 struct perf_evlist *evlist __maybe_unused)
 {
 	return INTEL_BTS_AUXTRACE_PRIV_SIZE;
 }
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index f05daacc9e78..a3395179c9ee 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -89,7 +89,7 @@ static int intel_pt_parse_terms_with_default(struct list_head *formats,
 
 	*config = attr.config;
 out_free:
-	parse_events__free_terms(terms);
+	parse_events_terms__delete(terms);
 	return err;
 }
 
@@ -273,7 +273,9 @@ intel_pt_pmu_default_config(struct perf_pmu *intel_pt_pmu)
 	return attr;
 }
 
-static size_t intel_pt_info_priv_size(struct auxtrace_record *itr __maybe_unused)
+static size_t
+intel_pt_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+			struct perf_evlist *evlist __maybe_unused)
 {
 	return INTEL_PT_AUXTRACE_PRIV_SIZE;
 }
diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c
index 14e4e668fad7..b63d4be655a2 100644
--- a/tools/perf/arch/x86/util/kvm-stat.c
+++ b/tools/perf/arch/x86/util/kvm-stat.c
@@ -1,5 +1,7 @@
 #include "../../util/kvm-stat.h"
-#include <asm/kvm_perf.h>
+#include <asm/svm.h>
+#include <asm/vmx.h>
+#include <asm/kvm.h>
 
 define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS);
 define_exit_reasons_table(svm_exit_reasons, SVM_EXIT_REASONS);
@@ -11,6 +13,12 @@ static struct kvm_events_ops exit_events = {
 	.name = "VM-EXIT"
 };
 
+const char *vcpu_id_str = "vcpu_id";
+const int decode_str_len = 20;
+const char *kvm_exit_reason = "exit_reason";
+const char *kvm_entry_trace = "kvm:kvm_entry";
+const char *kvm_exit_trace = "kvm:kvm_exit";
+
 /*
  * For the mmio events, we treat:
  * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry
@@ -65,7 +73,7 @@ static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
 				  struct event_key *key,
 				  char *decode)
 {
-	scnprintf(decode, DECODE_STR_LEN, "%#lx:%s",
+	scnprintf(decode, decode_str_len, "%#lx:%s",
 		  (unsigned long)key->key,
 		  key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R");
 }
@@ -109,7 +117,7 @@ static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
 				    struct event_key *key,
 				    char *decode)
 {
-	scnprintf(decode, DECODE_STR_LEN, "%#llx:%s",
+	scnprintf(decode, decode_str_len, "%#llx:%s",
 		  (unsigned long long)key->key,
 		  key->info ? "POUT" : "PIN");
 }
@@ -121,7 +129,7 @@ static struct kvm_events_ops ioport_events = {
 	.name = "IO Port Access"
 };
 
-const char * const kvm_events_tp[] = {
+const char *kvm_events_tp[] = {
 	"kvm:kvm_entry",
 	"kvm:kvm_exit",
 	"kvm:kvm_mmio",
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index e4c2c30143b9..5c3cce082cb8 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -1,6 +1,11 @@
+
+/* Various wrappers to make the kernel .S file build in user-space: */
+
 #define memcpy MEMCPY /* don't hide glibc's memcpy() */
 #define altinstr_replacement text
 #define globl p2align 4; .globl
+#define _ASM_EXTABLE_FAULT(x, y)
+
 #include "../../../arch/x86/lib/memcpy_64.S"
 /*
  * We need to provide note.GNU-stack section, saying that we want
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index cc5c1267c738..cfe366375c4b 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -245,7 +245,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
 			hists__collapse_resort(hists, NULL);
 			/* Don't sort callchain */
 			perf_evsel__reset_sample_bit(pos, CALLCHAIN);
-			hists__output_resort(hists, NULL);
+			perf_evsel__output_resort(pos, NULL);
 
 			if (symbol_conf.event_group &&
 			    !perf_evsel__is_group_leader(pos))
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index d93bff7fc0e4..632efc6b79a0 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -38,19 +38,7 @@ static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid)
 
 static int build_id_cache__kcore_dir(char *dir, size_t sz)
 {
-	struct timeval tv;
-	struct tm tm;
-	char dt[32];
-
-	if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm))
-		return -1;
-
-	if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm))
-		return -1;
-
-	scnprintf(dir, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000);
-
-	return 0;
+	return fetch_current_timestamp(dir, sz);
 }
 
 static bool same_kallsyms_reloc(const char *from_dir, char *to_dir)
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
index f04e804a9fad..c42448ed5dfe 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -13,8 +13,10 @@
 #include "util/util.h"
 #include "util/debug.h"
 
+static bool use_system_config, use_user_config;
+
 static const char * const config_usage[] = {
-	"perf config [options]",
+	"perf config [<file-option>] [options]",
 	NULL
 };
 
@@ -25,6 +27,8 @@ enum actions {
 static struct option config_options[] = {
 	OPT_SET_UINT('l', "list", &actions,
 		     "show current config variables", ACTION_LIST),
+	OPT_BOOLEAN(0, "system", &use_system_config, "use system config file"),
+	OPT_BOOLEAN(0, "user", &use_user_config, "use user config file"),
 	OPT_END()
 };
 
@@ -42,10 +46,23 @@ static int show_config(const char *key, const char *value,
 int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	int ret = 0;
+	char *user_config = mkpath("%s/.perfconfig", getenv("HOME"));
 
 	argc = parse_options(argc, argv, config_options, config_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 
+	if (use_system_config && use_user_config) {
+		pr_err("Error: only one config file at a time\n");
+		parse_options_usage(config_usage, config_options, "user", 0);
+		parse_options_usage(NULL, config_options, "system", 0);
+		return -1;
+	}
+
+	if (use_system_config)
+		config_exclusive_filename = perf_etc_perfconfig();
+	else if (use_user_config)
+		config_exclusive_filename = user_config;
+
 	switch (actions) {
 	case ACTION_LIST:
 		if (argc) {
@@ -53,9 +70,13 @@ int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
 			parse_options_usage(config_usage, config_options, "l", 1);
 		} else {
 			ret = perf_config(show_config, NULL);
-			if (ret < 0)
+			if (ret < 0) {
+				const char * config_filename = config_exclusive_filename;
+				if (!config_exclusive_filename)
+					config_filename = user_config;
 				pr_err("Nothing configured, "
-				       "please check your ~/.perfconfig file\n");
+				       "please check your %s \n", config_filename);
+			}
 		}
 		break;
 	default:
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 36ccc2b8827f..4d72359fd15a 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -1264,8 +1264,6 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (ret < 0)
 		return ret;
 
-	perf_config(perf_default_config, NULL);
-
 	argc = parse_options(argc, argv, options, diff_usage, 0);
 
 	if (symbol__init(NULL) < 0)
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 96c1a4cfbbbf..49d55e21b1b0 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -86,8 +86,7 @@ static int check_emacsclient_version(void)
 		return -1;
 	}
 
-	strbuf_remove(&buffer, 0, strlen("emacsclient"));
-	version = atoi(buffer.buf);
+	version = atoi(buffer.buf + strlen("emacsclient"));
 
 	if (version < 22) {
 		fprintf(stderr,
@@ -273,7 +272,7 @@ static int perf_help_config(const char *var, const char *value, void *cb)
 	if (!prefixcmp(var, "man."))
 		return add_man_viewer_info(var, value);
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 static struct cmdnames main_cmds, other_cmds;
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 0022e02ed31a..7fa68663ed72 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -17,6 +17,7 @@
 #include "util/build-id.h"
 #include "util/data.h"
 #include "util/auxtrace.h"
+#include "util/jit.h"
 
 #include <subcmd/parse-options.h>
 
@@ -29,6 +30,7 @@ struct perf_inject {
 	bool			sched_stat;
 	bool			have_auxtrace;
 	bool			strip;
+	bool			jit_mode;
 	const char		*input_name;
 	struct perf_data_file	output;
 	u64			bytes_written;
@@ -71,6 +73,15 @@ static int perf_event__repipe_oe_synth(struct perf_tool *tool,
 	return perf_event__repipe_synth(tool, event);
 }
 
+#ifdef HAVE_JITDUMP
+static int perf_event__drop_oe(struct perf_tool *tool __maybe_unused,
+			       union perf_event *event __maybe_unused,
+			       struct ordered_events *oe __maybe_unused)
+{
+	return 0;
+}
+#endif
+
 static int perf_event__repipe_op2_synth(struct perf_tool *tool,
 					union perf_event *event,
 					struct perf_session *session
@@ -234,6 +245,31 @@ static int perf_event__repipe_mmap(struct perf_tool *tool,
 	return err;
 }
 
+#ifdef HAVE_JITDUMP
+static int perf_event__jit_repipe_mmap(struct perf_tool *tool,
+				       union perf_event *event,
+				       struct perf_sample *sample,
+				       struct machine *machine)
+{
+	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
+	u64 n = 0;
+	int ret;
+
+	/*
+	 * if jit marker, then inject jit mmaps and generate ELF images
+	 */
+	ret = jit_process(inject->session, &inject->output, machine,
+			  event->mmap.filename, sample->pid, &n);
+	if (ret < 0)
+		return ret;
+	if (ret) {
+		inject->bytes_written += n;
+		return 0;
+	}
+	return perf_event__repipe_mmap(tool, event, sample, machine);
+}
+#endif
+
 static int perf_event__repipe_mmap2(struct perf_tool *tool,
 				   union perf_event *event,
 				   struct perf_sample *sample,
@@ -247,6 +283,31 @@ static int perf_event__repipe_mmap2(struct perf_tool *tool,
 	return err;
 }
 
+#ifdef HAVE_JITDUMP
+static int perf_event__jit_repipe_mmap2(struct perf_tool *tool,
+					union perf_event *event,
+					struct perf_sample *sample,
+					struct machine *machine)
+{
+	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
+	u64 n = 0;
+	int ret;
+
+	/*
+	 * if jit marker, then inject jit mmaps and generate ELF images
+	 */
+	ret = jit_process(inject->session, &inject->output, machine,
+			  event->mmap2.filename, sample->pid, &n);
+	if (ret < 0)
+		return ret;
+	if (ret) {
+		inject->bytes_written += n;
+		return 0;
+	}
+	return perf_event__repipe_mmap2(tool, event, sample, machine);
+}
+#endif
+
 static int perf_event__repipe_fork(struct perf_tool *tool,
 				   union perf_event *event,
 				   struct perf_sample *sample,
@@ -626,12 +687,16 @@ static int __cmd_inject(struct perf_inject *inject)
 	ret = perf_session__process_events(session);
 
 	if (!file_out->is_pipe) {
-		if (inject->build_ids) {
+		if (inject->build_ids)
 			perf_header__set_feat(&session->header,
 					      HEADER_BUILD_ID);
-			if (inject->have_auxtrace)
-				dsos__hit_all(session);
-		}
+		/*
+		 * Keep all buildids when there is unprocessed AUX data because
+		 * it is not known which ones the AUX trace hits.
+		 */
+		if (perf_header__has_feat(&session->header, HEADER_BUILD_ID) &&
+		    inject->have_auxtrace && !inject->itrace_synth_opts.set)
+			dsos__hit_all(session);
 		/*
 		 * The AUX areas have been removed and replaced with
 		 * synthesized hardware events, so clear the feature flag and
@@ -703,7 +768,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 	};
 	int ret;
 
-	const struct option options[] = {
+	struct option options[] = {
 		OPT_BOOLEAN('b', "build-ids", &inject.build_ids,
 			    "Inject build-ids into the output stream"),
 		OPT_STRING('i', "input", &inject.input_name, "file",
@@ -713,6 +778,9 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 		OPT_BOOLEAN('s', "sched-stat", &inject.sched_stat,
 			    "Merge sched-stat and sched-switch for getting events "
 			    "where and how long tasks slept"),
+#ifdef HAVE_JITDUMP
+		OPT_BOOLEAN('j', "jit", &inject.jit_mode, "merge jitdump files into perf.data file"),
+#endif
 		OPT_INCR('v', "verbose", &verbose,
 			 "be more verbose (show build ids, etc)"),
 		OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file",
@@ -729,7 +797,9 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 		"perf inject [<options>]",
 		NULL
 	};
-
+#ifndef HAVE_JITDUMP
+	set_option_nobuild(options, 'j', "jit", "NO_LIBELF=1", true);
+#endif
 	argc = parse_options(argc, argv, options, inject_usage, 0);
 
 	/*
@@ -755,6 +825,29 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (inject.session == NULL)
 		return -1;
 
+	if (inject.build_ids) {
+		/*
+		 * to make sure the mmap records are ordered correctly
+		 * and so that the correct especially due to jitted code
+		 * mmaps. We cannot generate the buildid hit list and
+		 * inject the jit mmaps at the same time for now.
+		 */
+		inject.tool.ordered_events = true;
+		inject.tool.ordering_requires_timestamps = true;
+	}
+#ifdef HAVE_JITDUMP
+	if (inject.jit_mode) {
+		inject.tool.mmap2	   = perf_event__jit_repipe_mmap2;
+		inject.tool.mmap	   = perf_event__jit_repipe_mmap;
+		inject.tool.ordered_events = true;
+		inject.tool.ordering_requires_timestamps = true;
+		/*
+		 * JIT MMAP injection injects all MMAP events in one go, so it
+		 * does not obey finished_round semantics.
+		 */
+		inject.tool.finished_round = perf_event__drop_oe;
+	}
+#endif
 	ret = symbol__init(&inject.session->header.env);
 	if (ret < 0)
 		goto out_delete;
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 118010553d0c..c9cb3be47cff 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -602,7 +602,7 @@ static int gfpcmp(const void *a, const void *b)
 	return fa->flags - fb->flags;
 }
 
-/* see include/trace/events/gfpflags.h */
+/* see include/trace/events/mmflags.h */
 static const struct {
 	const char *original;
 	const char *compact;
@@ -612,30 +612,39 @@ static const struct {
 	{ "GFP_HIGHUSER",		"HU" },
 	{ "GFP_USER",			"U" },
 	{ "GFP_TEMPORARY",		"TMP" },
+	{ "GFP_KERNEL_ACCOUNT",		"KAC" },
 	{ "GFP_KERNEL",			"K" },
 	{ "GFP_NOFS",			"NF" },
 	{ "GFP_ATOMIC",			"A" },
 	{ "GFP_NOIO",			"NI" },
-	{ "GFP_HIGH",			"H" },
-	{ "GFP_WAIT",			"W" },
-	{ "GFP_IO",			"I" },
-	{ "GFP_COLD",			"CO" },
-	{ "GFP_NOWARN",			"NWR" },
-	{ "GFP_REPEAT",			"R" },
-	{ "GFP_NOFAIL",			"NF" },
-	{ "GFP_NORETRY",		"NR" },
-	{ "GFP_COMP",			"C" },
-	{ "GFP_ZERO",			"Z" },
-	{ "GFP_NOMEMALLOC",		"NMA" },
-	{ "GFP_MEMALLOC",		"MA" },
-	{ "GFP_HARDWALL",		"HW" },
-	{ "GFP_THISNODE",		"TN" },
-	{ "GFP_RECLAIMABLE",		"RC" },
-	{ "GFP_MOVABLE",		"M" },
-	{ "GFP_NOTRACK",		"NT" },
-	{ "GFP_NO_KSWAPD",		"NK" },
-	{ "GFP_OTHER_NODE",		"ON" },
 	{ "GFP_NOWAIT",			"NW" },
+	{ "GFP_DMA",			"D" },
+	{ "__GFP_HIGHMEM",		"HM" },
+	{ "GFP_DMA32",			"D32" },
+	{ "__GFP_HIGH",			"H" },
+	{ "__GFP_ATOMIC",		"_A" },
+	{ "__GFP_IO",			"I" },
+	{ "__GFP_FS",			"F" },
+	{ "__GFP_COLD",			"CO" },
+	{ "__GFP_NOWARN",		"NWR" },
+	{ "__GFP_REPEAT",		"R" },
+	{ "__GFP_NOFAIL",		"NF" },
+	{ "__GFP_NORETRY",		"NR" },
+	{ "__GFP_COMP",			"C" },
+	{ "__GFP_ZERO",			"Z" },
+	{ "__GFP_NOMEMALLOC",		"NMA" },
+	{ "__GFP_MEMALLOC",		"MA" },
+	{ "__GFP_HARDWALL",		"HW" },
+	{ "__GFP_THISNODE",		"TN" },
+	{ "__GFP_RECLAIMABLE",		"RC" },
+	{ "__GFP_MOVABLE",		"M" },
+	{ "__GFP_ACCOUNT",		"AC" },
+	{ "__GFP_NOTRACK",		"NT" },
+	{ "__GFP_WRITE",		"WR" },
+	{ "__GFP_RECLAIM",		"R" },
+	{ "__GFP_DIRECT_RECLAIM",	"DR" },
+	{ "__GFP_KSWAPD_RECLAIM",	"KR" },
+	{ "__GFP_OTHER_NODE",		"ON" },
 };
 
 static size_t max_gfp_len;
@@ -1834,7 +1843,7 @@ static int __cmd_record(int argc, const char **argv)
 	return cmd_record(i, rec_argv, NULL);
 }
 
-static int kmem_config(const char *var, const char *value, void *cb)
+static int kmem_config(const char *var, const char *value, void *cb __maybe_unused)
 {
 	if (!strcmp(var, "kmem.default")) {
 		if (!strcmp(value, "slab"))
@@ -1847,7 +1856,7 @@ static int kmem_config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 4418d9214872..bff666458b28 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -30,7 +30,6 @@
 #include <math.h>
 
 #ifdef HAVE_KVM_STAT_SUPPORT
-#include <asm/kvm_perf.h>
 #include "util/kvm-stat.h"
 
 void exit_event_get_key(struct perf_evsel *evsel,
@@ -38,12 +37,12 @@ void exit_event_get_key(struct perf_evsel *evsel,
 			struct event_key *key)
 {
 	key->info = 0;
-	key->key = perf_evsel__intval(evsel, sample, KVM_EXIT_REASON);
+	key->key = perf_evsel__intval(evsel, sample, kvm_exit_reason);
 }
 
 bool kvm_exit_event(struct perf_evsel *evsel)
 {
-	return !strcmp(evsel->name, KVM_EXIT_TRACE);
+	return !strcmp(evsel->name, kvm_exit_trace);
 }
 
 bool exit_event_begin(struct perf_evsel *evsel,
@@ -59,7 +58,7 @@ bool exit_event_begin(struct perf_evsel *evsel,
 
 bool kvm_entry_event(struct perf_evsel *evsel)
 {
-	return !strcmp(evsel->name, KVM_ENTRY_TRACE);
+	return !strcmp(evsel->name, kvm_entry_trace);
 }
 
 bool exit_event_end(struct perf_evsel *evsel,
@@ -91,7 +90,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm,
 	const char *exit_reason = get_exit_reason(kvm, key->exit_reasons,
 						  key->key);
 
-	scnprintf(decode, DECODE_STR_LEN, "%s", exit_reason);
+	scnprintf(decode, decode_str_len, "%s", exit_reason);
 }
 
 static bool register_kvm_events_ops(struct perf_kvm_stat *kvm)
@@ -357,7 +356,7 @@ static bool handle_end_event(struct perf_kvm_stat *kvm,
 	time_diff = sample->time - time_begin;
 
 	if (kvm->duration && time_diff > kvm->duration) {
-		char decode[DECODE_STR_LEN];
+		char decode[decode_str_len];
 
 		kvm->events_ops->decode_key(kvm, &event->key, decode);
 		if (!skip_event(decode)) {
@@ -385,7 +384,8 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread,
 			return NULL;
 		}
 
-		vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, VCPU_ID);
+		vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample,
+							  vcpu_id_str);
 		thread__set_priv(thread, vcpu_record);
 	}
 
@@ -574,7 +574,7 @@ static void show_timeofday(void)
 
 static void print_result(struct perf_kvm_stat *kvm)
 {
-	char decode[DECODE_STR_LEN];
+	char decode[decode_str_len];
 	struct kvm_event *event;
 	int vcpu = kvm->trace_vcpu;
 
@@ -585,7 +585,7 @@ static void print_result(struct perf_kvm_stat *kvm)
 
 	pr_info("\n\n");
 	print_vcpu_info(kvm);
-	pr_info("%*s ", DECODE_STR_LEN, kvm->events_ops->name);
+	pr_info("%*s ", decode_str_len, kvm->events_ops->name);
 	pr_info("%10s ", "Samples");
 	pr_info("%9s ", "Samples%");
 
@@ -604,7 +604,7 @@ static void print_result(struct perf_kvm_stat *kvm)
 		min = get_event_min(event, vcpu);
 
 		kvm->events_ops->decode_key(kvm, &event->key, decode);
-		pr_info("%*s ", DECODE_STR_LEN, decode);
+		pr_info("%*s ", decode_str_len, decode);
 		pr_info("%10llu ", (unsigned long long)ecount);
 		pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100);
 		pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100);
@@ -1132,6 +1132,11 @@ exit:
 		_p;			\
 	})
 
+int __weak setup_kvm_events_tp(struct perf_kvm_stat *kvm __maybe_unused)
+{
+	return 0;
+}
+
 static int
 kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 {
@@ -1148,7 +1153,14 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 		NULL
 	};
 	const char * const *events_tp;
+	int ret;
+
 	events_tp_size = 0;
+	ret = setup_kvm_events_tp(kvm);
+	if (ret < 0) {
+		pr_err("Unable to setup the kvm tracepoints\n");
+		return ret;
+	}
 
 	for (events_tp = kvm_events_tp; *events_tp; events_tp++)
 		events_tp_size++;
@@ -1377,6 +1389,12 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	/*
 	 * generate the event list
 	 */
+	err = setup_kvm_events_tp(kvm);
+	if (err < 0) {
+		pr_err("Unable to setup the kvm tracepoints\n");
+		return err;
+	}
+
 	kvm->evlist = kvm_live_event_list();
 	if (kvm->evlist == NULL) {
 		err = -1;
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 390170041696..88aeac9aa1da 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -6,6 +6,8 @@
 #include "util/tool.h"
 #include "util/session.h"
 #include "util/data.h"
+#include "util/mem-events.h"
+#include "util/debug.h"
 
 #define MEM_OPERATION_LOAD	0x1
 #define MEM_OPERATION_STORE	0x2
@@ -21,11 +23,56 @@ struct perf_mem {
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
+static int parse_record_events(const struct option *opt,
+			       const char *str, int unset __maybe_unused)
+{
+	struct perf_mem *mem = *(struct perf_mem **)opt->value;
+	int j;
+
+	if (strcmp(str, "list")) {
+		if (!perf_mem_events__parse(str)) {
+			mem->operation = 0;
+			return 0;
+		}
+		exit(-1);
+	}
+
+	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+		struct perf_mem_event *e = &perf_mem_events[j];
+
+		fprintf(stderr, "%-13s%-*s%s\n",
+			e->tag,
+			verbose ? 25 : 0,
+			verbose ? perf_mem_events__name(j) : "",
+			e->supported ? ": available" : "");
+	}
+	exit(0);
+}
+
+static const char * const __usage[] = {
+	"perf mem record [<options>] [<command>]",
+	"perf mem record [<options>] -- <command> [<options>]",
+	NULL
+};
+
+static const char * const *record_mem_usage = __usage;
+
 static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 {
 	int rec_argc, i = 0, j;
 	const char **rec_argv;
 	int ret;
+	struct option options[] = {
+	OPT_CALLBACK('e', "event", &mem, "event",
+		     "event selector. use 'perf mem record -e list' to list available events",
+		     parse_record_events),
+	OPT_INCR('v', "verbose", &verbose,
+		 "be more verbose (show counter open errors, etc)"),
+	OPT_END()
+	};
+
+	argc = parse_options(argc, argv, options, record_mem_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
 
 	rec_argc = argc + 7; /* max number of arguments */
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
@@ -35,23 +82,40 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	rec_argv[i++] = "record";
 
 	if (mem->operation & MEM_OPERATION_LOAD)
+		perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true;
+
+	if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record)
 		rec_argv[i++] = "-W";
 
 	rec_argv[i++] = "-d";
 
-	if (mem->operation & MEM_OPERATION_LOAD) {
-		rec_argv[i++] = "-e";
-		rec_argv[i++] = "cpu/mem-loads/pp";
-	}
+	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+		if (!perf_mem_events[j].record)
+			continue;
+
+		if (!perf_mem_events[j].supported) {
+			pr_err("failed: event '%s' not supported\n",
+			       perf_mem_events__name(j));
+			return -1;
+		}
 
-	if (mem->operation & MEM_OPERATION_STORE) {
 		rec_argv[i++] = "-e";
-		rec_argv[i++] = "cpu/mem-stores/pp";
-	}
+		rec_argv[i++] = perf_mem_events__name(j);
+	};
 
-	for (j = 1; j < argc; j++, i++)
+	for (j = 0; j < argc; j++, i++)
 		rec_argv[i] = argv[j];
 
+	if (verbose > 0) {
+		pr_debug("calling: record ");
+
+		while (rec_argv[j]) {
+			pr_debug("%s ", rec_argv[j]);
+			j++;
+		}
+		pr_debug("\n");
+	}
+
 	ret = cmd_record(i, rec_argv, NULL);
 	free(rec_argv);
 	return ret;
@@ -298,6 +362,10 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
 		NULL
 	};
 
+	if (perf_mem_events__init()) {
+		pr_err("failed: memory events not supported\n");
+		return -1;
+	}
 
 	argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
 					mem_usage, PARSE_OPT_STOP_AT_NON_OPTION);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 319712a4e02b..515510ecc76a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -32,6 +32,8 @@
 #include "util/parse-branch-options.h"
 #include "util/parse-regs-options.h"
 #include "util/llvm-utils.h"
+#include "util/bpf-loader.h"
+#include "asm/bug.h"
 
 #include <unistd.h>
 #include <sched.h>
@@ -49,7 +51,9 @@ struct record {
 	const char		*progname;
 	int			realtime_prio;
 	bool			no_buildid;
+	bool			no_buildid_set;
 	bool			no_buildid_cache;
+	bool			no_buildid_cache_set;
 	bool			buildid_all;
 	unsigned long long	samples;
 };
@@ -320,7 +324,10 @@ try_again:
 		} else {
 			pr_err("failed to mmap with %d (%s)\n", errno,
 				strerror_r(errno, msg, sizeof(msg)));
-			rc = -errno;
+			if (errno)
+				rc = -errno;
+			else
+				rc = -EINVAL;
 		}
 		goto out;
 	}
@@ -464,6 +471,29 @@ static void record__init_features(struct record *rec)
 	perf_header__clear_feat(&session->header, HEADER_STAT);
 }
 
+static void
+record__finish_output(struct record *rec)
+{
+	struct perf_data_file *file = &rec->file;
+	int fd = perf_data_file__fd(file);
+
+	if (file->is_pipe)
+		return;
+
+	rec->session->header.data_size += rec->bytes_written;
+	file->size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
+
+	if (!rec->no_buildid) {
+		process_buildids(rec);
+
+		if (rec->buildid_all)
+			dsos__hit_all(rec->session);
+	}
+	perf_session__write_header(rec->session, rec->evlist, fd, true);
+
+	return;
+}
+
 static volatile int workload_exec_errno;
 
 /*
@@ -482,6 +512,74 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
 
 static void snapshot_sig_handler(int sig);
 
+static int record__synthesize(struct record *rec)
+{
+	struct perf_session *session = rec->session;
+	struct machine *machine = &session->machines.host;
+	struct perf_data_file *file = &rec->file;
+	struct record_opts *opts = &rec->opts;
+	struct perf_tool *tool = &rec->tool;
+	int fd = perf_data_file__fd(file);
+	int err = 0;
+
+	if (file->is_pipe) {
+		err = perf_event__synthesize_attrs(tool, session,
+						   process_synthesized_event);
+		if (err < 0) {
+			pr_err("Couldn't synthesize attrs.\n");
+			goto out;
+		}
+
+		if (have_tracepoints(&rec->evlist->entries)) {
+			/*
+			 * FIXME err <= 0 here actually means that
+			 * there were no tracepoints so its not really
+			 * an error, just that we don't need to
+			 * synthesize anything.  We really have to
+			 * return this more properly and also
+			 * propagate errors that now are calling die()
+			 */
+			err = perf_event__synthesize_tracing_data(tool,	fd, rec->evlist,
+								  process_synthesized_event);
+			if (err <= 0) {
+				pr_err("Couldn't record tracing data.\n");
+				goto out;
+			}
+			rec->bytes_written += err;
+		}
+	}
+
+	if (rec->opts.full_auxtrace) {
+		err = perf_event__synthesize_auxtrace_info(rec->itr, tool,
+					session, process_synthesized_event);
+		if (err)
+			goto out;
+	}
+
+	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
+						 machine);
+	WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n"
+			   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+			   "Check /proc/kallsyms permission or run as root.\n");
+
+	err = perf_event__synthesize_modules(tool, process_synthesized_event,
+					     machine);
+	WARN_ONCE(err < 0, "Couldn't record kernel module information.\n"
+			   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+			   "Check /proc/modules permission or run as root.\n");
+
+	if (perf_guest) {
+		machines__process_guests(&session->machines,
+					 perf_event__synthesize_guest_os, tool);
+	}
+
+	err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
+					    process_synthesized_event, opts->sample_address,
+					    opts->proc_map_timeout);
+out:
+	return err;
+}
+
 static int __cmd_record(struct record *rec, int argc, const char **argv)
 {
 	int err;
@@ -534,6 +632,16 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		goto out_child;
 	}
 
+	err = bpf__apply_obj_config();
+	if (err) {
+		char errbuf[BUFSIZ];
+
+		bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf));
+		pr_err("ERROR: Apply config to BPF failed: %s\n",
+			 errbuf);
+		goto out_child;
+	}
+
 	/*
 	 * Normally perf_session__new would do this, but it doesn't have the
 	 * evlist.
@@ -566,63 +674,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 	machine = &session->machines.host;
 
-	if (file->is_pipe) {
-		err = perf_event__synthesize_attrs(tool, session,
-						   process_synthesized_event);
-		if (err < 0) {
-			pr_err("Couldn't synthesize attrs.\n");
-			goto out_child;
-		}
-
-		if (have_tracepoints(&rec->evlist->entries)) {
-			/*
-			 * FIXME err <= 0 here actually means that
-			 * there were no tracepoints so its not really
-			 * an error, just that we don't need to
-			 * synthesize anything.  We really have to
-			 * return this more properly and also
-			 * propagate errors that now are calling die()
-			 */
-			err = perf_event__synthesize_tracing_data(tool,	fd, rec->evlist,
-								  process_synthesized_event);
-			if (err <= 0) {
-				pr_err("Couldn't record tracing data.\n");
-				goto out_child;
-			}
-			rec->bytes_written += err;
-		}
-	}
-
-	if (rec->opts.full_auxtrace) {
-		err = perf_event__synthesize_auxtrace_info(rec->itr, tool,
-					session, process_synthesized_event);
-		if (err)
-			goto out_delete_session;
-	}
-
-	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-						 machine);
-	if (err < 0)
-		pr_err("Couldn't record kernel reference relocation symbol\n"
-		       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
-		       "Check /proc/kallsyms permission or run as root.\n");
-
-	err = perf_event__synthesize_modules(tool, process_synthesized_event,
-					     machine);
+	err = record__synthesize(rec);
 	if (err < 0)
-		pr_err("Couldn't record kernel module information.\n"
-		       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
-		       "Check /proc/modules permission or run as root.\n");
-
-	if (perf_guest) {
-		machines__process_guests(&session->machines,
-					 perf_event__synthesize_guest_os, tool);
-	}
-
-	err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
-					    process_synthesized_event, opts->sample_address,
-					    opts->proc_map_timeout);
-	if (err != 0)
 		goto out_child;
 
 	if (rec->realtime_prio) {
@@ -758,18 +811,8 @@ out_child:
 	/* this will be recalculated during process_buildids() */
 	rec->samples = 0;
 
-	if (!err && !file->is_pipe) {
-		rec->session->header.data_size += rec->bytes_written;
-		file->size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
-
-		if (!rec->no_buildid) {
-			process_buildids(rec);
-
-			if (rec->buildid_all)
-				dsos__hit_all(rec->session);
-		}
-		perf_session__write_header(rec->session, rec->evlist, fd, true);
-	}
+	if (!err)
+		record__finish_output(rec);
 
 	if (!err && !quiet) {
 		char samples[128];
@@ -1097,10 +1140,12 @@ struct option __record_options[] = {
 	OPT_BOOLEAN('P', "period", &record.opts.period, "Record the sample period"),
 	OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
 		    "don't sample"),
-	OPT_BOOLEAN('N', "no-buildid-cache", &record.no_buildid_cache,
-		    "do not update the buildid cache"),
-	OPT_BOOLEAN('B', "no-buildid", &record.no_buildid,
-		    "do not collect buildids in perf.data"),
+	OPT_BOOLEAN_SET('N', "no-buildid-cache", &record.no_buildid_cache,
+			&record.no_buildid_cache_set,
+			"do not update the buildid cache"),
+	OPT_BOOLEAN_SET('B', "no-buildid", &record.no_buildid,
+			&record.no_buildid_set,
+			"do not collect buildids in perf.data"),
 	OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
 		     "monitor event in cgroup name only",
 		     parse_cgroups),
@@ -1136,6 +1181,12 @@ struct option __record_options[] = {
 			"per thread proc mmap processing timeout in ms"),
 	OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
 		    "Record context switch events"),
+	OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel,
+			 "Configure all used events to run in kernel space.",
+			 PARSE_OPT_EXCLUSIVE),
+	OPT_BOOLEAN_FLAG(0, "all-user", &record.opts.all_user,
+			 "Configure all used events to run in user space.",
+			 PARSE_OPT_EXCLUSIVE),
 	OPT_STRING(0, "clang-path", &llvm_param.clang_path, "clang path",
 		   "clang binary to use for compiling BPF scriptlets"),
 	OPT_STRING(0, "clang-opt", &llvm_param.clang_opt, "clang options",
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 2bf537f190a0..7eea49f9ed46 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -75,7 +75,10 @@ static int report__config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 	if (!strcmp(var, "report.percent-limit")) {
-		rep->min_percent = strtof(value, NULL);
+		double pcnt = strtof(value, NULL);
+
+		rep->min_percent = pcnt;
+		callchain_param.min_percent = pcnt;
 		return 0;
 	}
 	if (!strcmp(var, "report.children")) {
@@ -87,7 +90,7 @@ static int report__config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 static int hist_iter__report_callback(struct hist_entry_iter *iter,
@@ -466,10 +469,11 @@ static int report__browse_hists(struct report *rep)
 	return ret;
 }
 
-static void report__collapse_hists(struct report *rep)
+static int report__collapse_hists(struct report *rep)
 {
 	struct ui_progress prog;
 	struct perf_evsel *pos;
+	int ret = 0;
 
 	ui_progress__init(&prog, rep->nr_entries, "Merging related events...");
 
@@ -481,7 +485,9 @@ static void report__collapse_hists(struct report *rep)
 
 		hists->socket_filter = rep->socket_filter;
 
-		hists__collapse_resort(hists, &prog);
+		ret = hists__collapse_resort(hists, &prog);
+		if (ret < 0)
+			break;
 
 		/* Non-group events are considered as leader */
 		if (symbol_conf.event_group &&
@@ -494,6 +500,7 @@ static void report__collapse_hists(struct report *rep)
 	}
 
 	ui_progress__finish();
+	return ret;
 }
 
 static void report__output_resort(struct report *rep)
@@ -504,7 +511,7 @@ static void report__output_resort(struct report *rep)
 	ui_progress__init(&prog, rep->nr_entries, "Sorting events for output...");
 
 	evlist__for_each(rep->session->evlist, pos)
-		hists__output_resort(evsel__hists(pos), &prog);
+		perf_evsel__output_resort(pos, &prog);
 
 	ui_progress__finish();
 }
@@ -561,7 +568,11 @@ static int __cmd_report(struct report *rep)
 		}
 	}
 
-	report__collapse_hists(rep);
+	ret = report__collapse_hists(rep);
+	if (ret) {
+		ui__error("failed to process hist entry\n");
+		return ret;
+	}
 
 	if (session_done())
 		return 0;
@@ -633,8 +644,10 @@ parse_percent_limit(const struct option *opt, const char *str,
 		    int unset __maybe_unused)
 {
 	struct report *rep = opt->value;
+	double pcnt = strtof(str, NULL);
 
-	rep->min_percent = strtof(str, NULL);
+	rep->min_percent = pcnt;
+	callchain_param.min_percent = pcnt;
 	return 0;
 }
 
@@ -798,6 +811,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "only show processor socket that match with this filter"),
 	OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace,
 		    "Show raw trace event output (do not use print fmt or plugins)"),
+	OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
+		    "Show entries in a hierarchy"),
 	OPT_END()
 	};
 	struct perf_data_file file = {
@@ -907,13 +922,19 @@ repeat:
 		symbol_conf.cumulate_callchain = false;
 	}
 
-	if (setup_sorting(session->evlist) < 0) {
-		if (sort_order)
-			parse_options_usage(report_usage, options, "s", 1);
-		if (field_order)
-			parse_options_usage(sort_order ? NULL : report_usage,
-					    options, "F", 1);
-		goto error;
+	if (symbol_conf.report_hierarchy) {
+		/* disable incompatible options */
+		symbol_conf.event_group = false;
+		symbol_conf.cumulate_callchain = false;
+
+		if (field_order) {
+			pr_err("Error: --hierarchy and --fields options cannot be used together\n");
+			parse_options_usage(report_usage, options, "F", 1);
+			parse_options_usage(NULL, options, "hierarchy", 0);
+			goto error;
+		}
+
+		sort__need_collapse = true;
 	}
 
 	/* Force tty output for header output and per-thread stat. */
@@ -925,6 +946,15 @@ repeat:
 	else
 		use_browser = 0;
 
+	if (setup_sorting(session->evlist) < 0) {
+		if (sort_order)
+			parse_options_usage(report_usage, options, "s", 1);
+		if (field_order)
+			parse_options_usage(sort_order ? NULL : report_usage,
+					    options, "F", 1);
+		goto error;
+	}
+
 	if (report.header || report.header_only) {
 		perf_session__fprintf_info(session, stdout,
 					   report.show_full_info);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c691214d820f..57f9a7e7f7d3 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -23,6 +23,7 @@
 #include "util/stat.h"
 #include <linux/bitmap.h>
 #include "asm/bug.h"
+#include "util/mem-events.h"
 
 static char const		*script_name;
 static char const		*generate_script_lang;
@@ -58,6 +59,9 @@ enum perf_output_field {
 	PERF_OUTPUT_IREGS	    = 1U << 14,
 	PERF_OUTPUT_BRSTACK	    = 1U << 15,
 	PERF_OUTPUT_BRSTACKSYM	    = 1U << 16,
+	PERF_OUTPUT_DATA_SRC	    = 1U << 17,
+	PERF_OUTPUT_WEIGHT	    = 1U << 18,
+	PERF_OUTPUT_BPF_OUTPUT	    = 1U << 19,
 };
 
 struct output_option {
@@ -81,6 +85,9 @@ struct output_option {
 	{.str = "iregs", .field = PERF_OUTPUT_IREGS},
 	{.str = "brstack", .field = PERF_OUTPUT_BRSTACK},
 	{.str = "brstacksym", .field = PERF_OUTPUT_BRSTACKSYM},
+	{.str = "data_src", .field = PERF_OUTPUT_DATA_SRC},
+	{.str = "weight",   .field = PERF_OUTPUT_WEIGHT},
+	{.str = "bpf-output",   .field = PERF_OUTPUT_BPF_OUTPUT},
 };
 
 /* default set to maintain compatibility with current format */
@@ -101,7 +108,7 @@ static struct {
 			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
 			      PERF_OUTPUT_PERIOD,
 
-		.invalid_fields = PERF_OUTPUT_TRACE,
+		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
 
 	[PERF_TYPE_SOFTWARE] = {
@@ -111,7 +118,7 @@ static struct {
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
 			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD,
+			      PERF_OUTPUT_PERIOD | PERF_OUTPUT_BPF_OUTPUT,
 
 		.invalid_fields = PERF_OUTPUT_TRACE,
 	},
@@ -121,7 +128,7 @@ static struct {
 
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 				  PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
-				  PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE,
+				  PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE
 	},
 
 	[PERF_TYPE_RAW] = {
@@ -131,9 +138,10 @@ static struct {
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
 			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD,
+			      PERF_OUTPUT_PERIOD |  PERF_OUTPUT_ADDR |
+			      PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT,
 
-		.invalid_fields = PERF_OUTPUT_TRACE,
+		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
 
 	[PERF_TYPE_BREAKPOINT] = {
@@ -145,7 +153,7 @@ static struct {
 			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
 			      PERF_OUTPUT_PERIOD,
 
-		.invalid_fields = PERF_OUTPUT_TRACE,
+		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
 };
 
@@ -242,6 +250,16 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 					   PERF_OUTPUT_ADDR, allow_user_set))
 		return -EINVAL;
 
+	if (PRINT_FIELD(DATA_SRC) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC",
+					PERF_OUTPUT_DATA_SRC))
+		return -EINVAL;
+
+	if (PRINT_FIELD(WEIGHT) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT, "WEIGHT",
+					PERF_OUTPUT_WEIGHT))
+		return -EINVAL;
+
 	if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
 		pr_err("Display of symbols requested but neither sample IP nor "
 			   "sample address\nis selected. Hence, no addresses to convert "
@@ -608,6 +626,84 @@ static void print_sample_flags(u32 flags)
 	printf("  %-4s ", str);
 }
 
+struct printer_data {
+	int line_no;
+	bool hit_nul;
+	bool is_printable;
+};
+
+static void
+print_sample_bpf_output_printer(enum binary_printer_ops op,
+				unsigned int val,
+				void *extra)
+{
+	unsigned char ch = (unsigned char)val;
+	struct printer_data *printer_data = extra;
+
+	switch (op) {
+	case BINARY_PRINT_DATA_BEGIN:
+		printf("\n");
+		break;
+	case BINARY_PRINT_LINE_BEGIN:
+		printf("%17s", !printer_data->line_no ? "BPF output:" :
+						        "           ");
+		break;
+	case BINARY_PRINT_ADDR:
+		printf(" %04x:", val);
+		break;
+	case BINARY_PRINT_NUM_DATA:
+		printf(" %02x", val);
+		break;
+	case BINARY_PRINT_NUM_PAD:
+		printf("   ");
+		break;
+	case BINARY_PRINT_SEP:
+		printf("  ");
+		break;
+	case BINARY_PRINT_CHAR_DATA:
+		if (printer_data->hit_nul && ch)
+			printer_data->is_printable = false;
+
+		if (!isprint(ch)) {
+			printf("%c", '.');
+
+			if (!printer_data->is_printable)
+				break;
+
+			if (ch == '\0')
+				printer_data->hit_nul = true;
+			else
+				printer_data->is_printable = false;
+		} else {
+			printf("%c", ch);
+		}
+		break;
+	case BINARY_PRINT_CHAR_PAD:
+		printf(" ");
+		break;
+	case BINARY_PRINT_LINE_END:
+		printf("\n");
+		printer_data->line_no++;
+		break;
+	case BINARY_PRINT_DATA_END:
+	default:
+		break;
+	}
+}
+
+static void print_sample_bpf_output(struct perf_sample *sample)
+{
+	unsigned int nr_bytes = sample->raw_size;
+	struct printer_data printer_data = {0, false, true};
+
+	print_binary(sample->raw_data, nr_bytes, 8,
+		     print_sample_bpf_output_printer, &printer_data);
+
+	if (printer_data.is_printable && printer_data.hit_nul)
+		printf("%17s \"%s\"\n", "BPF string:",
+		       (char *)(sample->raw_data));
+}
+
 struct perf_script {
 	struct perf_tool	tool;
 	struct perf_session	*session;
@@ -634,6 +730,23 @@ static int perf_evlist__max_name_len(struct perf_evlist *evlist)
 	return max;
 }
 
+static size_t data_src__printf(u64 data_src)
+{
+	struct mem_info mi = { .data_src.val = data_src };
+	char decode[100];
+	char out[100];
+	static int maxlen;
+	int len;
+
+	perf_script__meminfo_scnprintf(decode, 100, &mi);
+
+	len = scnprintf(out, 100, "%16" PRIx64 " %s", data_src, decode);
+	if (maxlen < len)
+		maxlen = len;
+
+	return printf("%-*s", maxlen, out);
+}
+
 static void process_event(struct perf_script *script, union perf_event *event,
 			  struct perf_sample *sample, struct perf_evsel *evsel,
 			  struct addr_location *al)
@@ -673,6 +786,12 @@ static void process_event(struct perf_script *script, union perf_event *event,
 	if (PRINT_FIELD(ADDR))
 		print_sample_addr(event, sample, thread, attr);
 
+	if (PRINT_FIELD(DATA_SRC))
+		data_src__printf(sample->data_src);
+
+	if (PRINT_FIELD(WEIGHT))
+		printf("%16" PRIu64, sample->weight);
+
 	if (PRINT_FIELD(IP)) {
 		if (!symbol_conf.use_callchain)
 			printf(" ");
@@ -692,6 +811,9 @@ static void process_event(struct perf_script *script, union perf_event *event,
 	else if (PRINT_FIELD(BRSTACKSYM))
 		print_sample_brstacksym(event, sample, thread, attr);
 
+	if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
+		print_sample_bpf_output(sample);
+
 	printf("\n");
 }
 
@@ -1090,23 +1212,6 @@ static struct script_spec *script_spec__find(const char *spec)
 	return NULL;
 }
 
-static struct script_spec *script_spec__findnew(const char *spec,
-						struct scripting_ops *ops)
-{
-	struct script_spec *s = script_spec__find(spec);
-
-	if (s)
-		return s;
-
-	s = script_spec__new(spec, ops);
-	if (!s)
-		return NULL;
-
-	script_spec__add(s);
-
-	return s;
-}
-
 int script_spec_register(const char *spec, struct scripting_ops *ops)
 {
 	struct script_spec *s;
@@ -1115,9 +1220,11 @@ int script_spec_register(const char *spec, struct scripting_ops *ops)
 	if (s)
 		return -1;
 
-	s = script_spec__findnew(spec, ops);
+	s = script_spec__new(spec, ops);
 	if (!s)
 		return -1;
+	else
+		script_spec__add(s);
 
 	return 0;
 }
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 038e877081b6..1f19f2f999c8 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -122,6 +122,7 @@ static bool			sync_run			= false;
 static unsigned int		initial_delay			= 0;
 static unsigned int		unit_width			= 4; /* strlen("unit") */
 static bool			forever				= false;
+static bool			metric_only			= false;
 static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
@@ -735,6 +736,191 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 	}
 }
 
+struct outstate {
+	FILE *fh;
+	bool newline;
+	const char *prefix;
+	int  nfields;
+	int  id, nr;
+	struct perf_evsel *evsel;
+};
+
+#define METRIC_LEN  35
+
+static void new_line_std(void *ctx)
+{
+	struct outstate *os = ctx;
+
+	os->newline = true;
+}
+
+static void do_new_line_std(struct outstate *os)
+{
+	fputc('\n', os->fh);
+	fputs(os->prefix, os->fh);
+	aggr_printout(os->evsel, os->id, os->nr);
+	if (stat_config.aggr_mode == AGGR_NONE)
+		fprintf(os->fh, "        ");
+	fprintf(os->fh, "                                                 ");
+}
+
+static void print_metric_std(void *ctx, const char *color, const char *fmt,
+			     const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	int n;
+	bool newline = os->newline;
+
+	os->newline = false;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%-*s", METRIC_LEN, "");
+		return;
+	}
+
+	if (newline)
+		do_new_line_std(os);
+
+	n = fprintf(out, " # ");
+	if (color)
+		n += color_fprintf(out, color, fmt, val);
+	else
+		n += fprintf(out, fmt, val);
+	fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
+}
+
+static void new_line_csv(void *ctx)
+{
+	struct outstate *os = ctx;
+	int i;
+
+	fputc('\n', os->fh);
+	if (os->prefix)
+		fprintf(os->fh, "%s%s", os->prefix, csv_sep);
+	aggr_printout(os->evsel, os->id, os->nr);
+	for (i = 0; i < os->nfields; i++)
+		fputs(csv_sep, os->fh);
+}
+
+static void print_metric_csv(void *ctx,
+			     const char *color __maybe_unused,
+			     const char *fmt, const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[64], *vals, *ends;
+
+	if (unit == NULL || fmt == NULL) {
+		fprintf(out, "%s%s%s%s", csv_sep, csv_sep, csv_sep, csv_sep);
+		return;
+	}
+	snprintf(buf, sizeof(buf), fmt, val);
+	vals = buf;
+	while (isspace(*vals))
+		vals++;
+	ends = vals;
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	while (isspace(*unit))
+		unit++;
+	fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit);
+}
+
+#define METRIC_ONLY_LEN 20
+
+/* Filter out some columns that don't work well in metrics only mode */
+
+static bool valid_only_metric(const char *unit)
+{
+	if (!unit)
+		return false;
+	if (strstr(unit, "/sec") ||
+	    strstr(unit, "hz") ||
+	    strstr(unit, "Hz") ||
+	    strstr(unit, "CPUs utilized"))
+		return false;
+	return true;
+}
+
+static const char *fixunit(char *buf, struct perf_evsel *evsel,
+			   const char *unit)
+{
+	if (!strncmp(unit, "of all", 6)) {
+		snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
+			 unit);
+		return buf;
+	}
+	return unit;
+}
+
+static void print_metric_only(void *ctx, const char *color, const char *fmt,
+			      const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	int n;
+	char buf[1024];
+	unsigned mlen = METRIC_ONLY_LEN;
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(buf, os->evsel, unit);
+	if (color)
+		n = color_fprintf(out, color, fmt, val);
+	else
+		n = fprintf(out, fmt, val);
+	if (n > METRIC_ONLY_LEN)
+		n = METRIC_ONLY_LEN;
+	if (mlen < strlen(unit))
+		mlen = strlen(unit) + 1;
+	fprintf(out, "%*s", mlen - n, "");
+}
+
+static void print_metric_only_csv(void *ctx, const char *color __maybe_unused,
+				  const char *fmt,
+				  const char *unit, double val)
+{
+	struct outstate *os = ctx;
+	FILE *out = os->fh;
+	char buf[64], *vals, *ends;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	snprintf(buf, sizeof buf, fmt, val);
+	vals = buf;
+	while (isspace(*vals))
+		vals++;
+	ends = vals;
+	while (isdigit(*ends) || *ends == '.')
+		ends++;
+	*ends = 0;
+	fprintf(out, "%s%s", vals, csv_sep);
+}
+
+static void new_line_metric(void *ctx __maybe_unused)
+{
+}
+
+static void print_metric_header(void *ctx, const char *color __maybe_unused,
+				const char *fmt __maybe_unused,
+				const char *unit, double val __maybe_unused)
+{
+	struct outstate *os = ctx;
+	char tbuf[1024];
+
+	if (!valid_only_metric(unit))
+		return;
+	unit = fixunit(tbuf, os->evsel, unit);
+	if (csv_output)
+		fprintf(os->fh, "%s%s", unit, csv_sep);
+	else
+		fprintf(os->fh, "%-*s ", METRIC_ONLY_LEN, unit);
+}
+
 static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	FILE *output = stat_config.output;
@@ -763,6 +949,28 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 }
 
+static int first_shadow_cpu(struct perf_evsel *evsel, int id)
+{
+	int i;
+
+	if (!aggr_get_id)
+		return 0;
+
+	if (stat_config.aggr_mode == AGGR_NONE)
+		return id;
+
+	if (stat_config.aggr_mode == AGGR_GLOBAL)
+		return 0;
+
+	for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
+		int cpu2 = perf_evsel__cpus(evsel)->map[i];
+
+		if (aggr_get_id(evsel_list->cpus, cpu2) == id)
+			return cpu2;
+	}
+	return 0;
+}
+
 static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	FILE *output = stat_config.output;
@@ -793,22 +1001,124 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 }
 
-static void printout(int id, int nr, struct perf_evsel *counter, double uval)
+static void printout(int id, int nr, struct perf_evsel *counter, double uval,
+		     char *prefix, u64 run, u64 ena, double noise)
 {
-	int cpu = cpu_map__id_to_cpu(id);
+	struct perf_stat_output_ctx out;
+	struct outstate os = {
+		.fh = stat_config.output,
+		.prefix = prefix ? prefix : "",
+		.id = id,
+		.nr = nr,
+		.evsel = counter,
+	};
+	print_metric_t pm = print_metric_std;
+	void (*nl)(void *);
 
-	if (stat_config.aggr_mode == AGGR_GLOBAL)
-		cpu = 0;
+	if (metric_only) {
+		nl = new_line_metric;
+		if (csv_output)
+			pm = print_metric_only_csv;
+		else
+			pm = print_metric_only;
+	} else
+		nl = new_line_std;
+
+	if (csv_output && !metric_only) {
+		static int aggr_fields[] = {
+			[AGGR_GLOBAL] = 0,
+			[AGGR_THREAD] = 1,
+			[AGGR_NONE] = 1,
+			[AGGR_SOCKET] = 2,
+			[AGGR_CORE] = 2,
+		};
+
+		pm = print_metric_csv;
+		nl = new_line_csv;
+		os.nfields = 3;
+		os.nfields += aggr_fields[stat_config.aggr_mode];
+		if (counter->cgrp)
+			os.nfields++;
+	}
+	if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
+		if (metric_only) {
+			pm(&os, NULL, "", "", 0);
+			return;
+		}
+		aggr_printout(counter, id, nr);
+
+		fprintf(stat_config.output, "%*s%s",
+			csv_output ? 0 : 18,
+			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
+			csv_sep);
+
+		fprintf(stat_config.output, "%-*s%s",
+			csv_output ? 0 : unit_width,
+			counter->unit, csv_sep);
+
+		fprintf(stat_config.output, "%*s",
+			csv_output ? 0 : -25,
+			perf_evsel__name(counter));
+
+		if (counter->cgrp)
+			fprintf(stat_config.output, "%s%s",
+				csv_sep, counter->cgrp->name);
 
-	if (nsec_counter(counter))
+		if (!csv_output)
+			pm(&os, NULL, NULL, "", 0);
+		print_noise(counter, noise);
+		print_running(run, ena);
+		if (csv_output)
+			pm(&os, NULL, NULL, "", 0);
+		return;
+	}
+
+	if (metric_only)
+		/* nothing */;
+	else if (nsec_counter(counter))
 		nsec_printout(id, nr, counter, uval);
 	else
 		abs_printout(id, nr, counter, uval);
 
-	if (!csv_output && !stat_config.interval)
-		perf_stat__print_shadow_stats(stat_config.output, counter,
-					      uval, cpu,
-					      stat_config.aggr_mode);
+	out.print_metric = pm;
+	out.new_line = nl;
+	out.ctx = &os;
+
+	if (csv_output && !metric_only) {
+		print_noise(counter, noise);
+		print_running(run, ena);
+	}
+
+	perf_stat__print_shadow_stats(counter, uval,
+				first_shadow_cpu(counter, id),
+				&out);
+	if (!csv_output && !metric_only) {
+		print_noise(counter, noise);
+		print_running(run, ena);
+	}
+}
+
+static void aggr_update_shadow(void)
+{
+	int cpu, s2, id, s;
+	u64 val;
+	struct perf_evsel *counter;
+
+	for (s = 0; s < aggr_map->nr; s++) {
+		id = aggr_map->map[s];
+		evlist__for_each(evsel_list, counter) {
+			val = 0;
+			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+				s2 = aggr_get_id(evsel_list->cpus, cpu);
+				if (s2 != id)
+					continue;
+				val += perf_counts(counter->counts, cpu, 0)->val;
+			}
+			val = val * counter->scale;
+			perf_stat__update_shadow_stats(counter, &val,
+						       first_shadow_cpu(counter, id));
+		}
+	}
 }
 
 static void print_aggr(char *prefix)
@@ -818,12 +1128,23 @@ static void print_aggr(char *prefix)
 	int cpu, s, s2, id, nr;
 	double uval;
 	u64 ena, run, val;
+	bool first;
 
 	if (!(aggr_map || aggr_get_id))
 		return;
 
+	aggr_update_shadow();
+
+	/*
+	 * With metric_only everything is on a single line.
+	 * Without each counter has its own line.
+	 */
 	for (s = 0; s < aggr_map->nr; s++) {
+		if (prefix && metric_only)
+			fprintf(output, "%s", prefix);
+
 		id = aggr_map->map[s];
+		first = true;
 		evlist__for_each(evsel_list, counter) {
 			val = ena = run = 0;
 			nr = 0;
@@ -836,41 +1157,20 @@ static void print_aggr(char *prefix)
 				run += perf_counts(counter->counts, cpu, 0)->run;
 				nr++;
 			}
-			if (prefix)
-				fprintf(output, "%s", prefix);
-
-			if (run == 0 || ena == 0) {
+			if (first && metric_only) {
+				first = false;
 				aggr_printout(counter, id, nr);
-
-				fprintf(output, "%*s%s",
-					csv_output ? 0 : 18,
-					counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-					csv_sep);
-
-				fprintf(output, "%-*s%s",
-					csv_output ? 0 : unit_width,
-					counter->unit, csv_sep);
-
-				fprintf(output, "%*s",
-					csv_output ? 0 : -25,
-					perf_evsel__name(counter));
-
-				if (counter->cgrp)
-					fprintf(output, "%s%s",
-						csv_sep, counter->cgrp->name);
-
-				print_running(run, ena);
-				fputc('\n', output);
-				continue;
 			}
-			uval = val * counter->scale;
-			printout(id, nr, counter, uval);
-			if (!csv_output)
-				print_noise(counter, 1.0);
+			if (prefix && !metric_only)
+				fprintf(output, "%s", prefix);
 
-			print_running(run, ena);
-			fputc('\n', output);
+			uval = val * counter->scale;
+			printout(id, nr, counter, uval, prefix, run, ena, 1.0);
+			if (!metric_only)
+				fputc('\n', output);
 		}
+		if (metric_only)
+			fputc('\n', output);
 	}
 }
 
@@ -895,12 +1195,7 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 			fprintf(output, "%s", prefix);
 
 		uval = val * counter->scale;
-		printout(thread, 0, counter, uval);
-
-		if (!csv_output)
-			print_noise(counter, 1.0);
-
-		print_running(run, ena);
+		printout(thread, 0, counter, uval, prefix, run, ena, 1.0);
 		fputc('\n', output);
 	}
 }
@@ -914,43 +1209,19 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 	FILE *output = stat_config.output;
 	struct perf_stat_evsel *ps = counter->priv;
 	double avg = avg_stats(&ps->res_stats[0]);
-	int scaled = counter->counts->scaled;
 	double uval;
 	double avg_enabled, avg_running;
 
 	avg_enabled = avg_stats(&ps->res_stats[1]);
 	avg_running = avg_stats(&ps->res_stats[2]);
 
-	if (prefix)
+	if (prefix && !metric_only)
 		fprintf(output, "%s", prefix);
 
-	if (scaled == -1 || !counter->supported) {
-		fprintf(output, "%*s%s",
-			csv_output ? 0 : 18,
-			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-			csv_sep);
-		fprintf(output, "%-*s%s",
-			csv_output ? 0 : unit_width,
-			counter->unit, csv_sep);
-		fprintf(output, "%*s",
-			csv_output ? 0 : -25,
-			perf_evsel__name(counter));
-
-		if (counter->cgrp)
-			fprintf(output, "%s%s", csv_sep, counter->cgrp->name);
-
-		print_running(avg_running, avg_enabled);
-		fputc('\n', output);
-		return;
-	}
-
 	uval = avg * counter->scale;
-	printout(-1, 0, counter, uval);
-
-	print_noise(counter, avg);
-
-	print_running(avg_running, avg_enabled);
-	fprintf(output, "\n");
+	printout(-1, 0, counter, uval, prefix, avg_running, avg_enabled, avg);
+	if (!metric_only)
+		fprintf(output, "\n");
 }
 
 /*
@@ -972,39 +1243,78 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 		if (prefix)
 			fprintf(output, "%s", prefix);
 
-		if (run == 0 || ena == 0) {
-			fprintf(output, "CPU%*d%s%*s%s",
-				csv_output ? 0 : -4,
-				perf_evsel__cpus(counter)->map[cpu], csv_sep,
-				csv_output ? 0 : 18,
-				counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-				csv_sep);
+		uval = val * counter->scale;
+		printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
 
-				fprintf(output, "%-*s%s",
-					csv_output ? 0 : unit_width,
-					counter->unit, csv_sep);
+		fputc('\n', output);
+	}
+}
 
-				fprintf(output, "%*s",
-					csv_output ? 0 : -25,
-					perf_evsel__name(counter));
+static void print_no_aggr_metric(char *prefix)
+{
+	int cpu;
+	int nrcpus = 0;
+	struct perf_evsel *counter;
+	u64 ena, run, val;
+	double uval;
 
-			if (counter->cgrp)
-				fprintf(output, "%s%s",
-					csv_sep, counter->cgrp->name);
+	nrcpus = evsel_list->cpus->nr;
+	for (cpu = 0; cpu < nrcpus; cpu++) {
+		bool first = true;
 
-			print_running(run, ena);
-			fputc('\n', output);
-			continue;
+		if (prefix)
+			fputs(prefix, stat_config.output);
+		evlist__for_each(evsel_list, counter) {
+			if (first) {
+				aggr_printout(counter, cpu, 0);
+				first = false;
+			}
+			val = perf_counts(counter->counts, cpu, 0)->val;
+			ena = perf_counts(counter->counts, cpu, 0)->ena;
+			run = perf_counts(counter->counts, cpu, 0)->run;
+
+			uval = val * counter->scale;
+			printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
 		}
+		fputc('\n', stat_config.output);
+	}
+}
 
-		uval = val * counter->scale;
-		printout(cpu, 0, counter, uval);
-		if (!csv_output)
-			print_noise(counter, 1.0);
-		print_running(run, ena);
+static int aggr_header_lens[] = {
+	[AGGR_CORE] = 18,
+	[AGGR_SOCKET] = 12,
+	[AGGR_NONE] = 6,
+	[AGGR_THREAD] = 24,
+	[AGGR_GLOBAL] = 0,
+};
 
-		fputc('\n', output);
+static void print_metric_headers(char *prefix)
+{
+	struct perf_stat_output_ctx out;
+	struct perf_evsel *counter;
+	struct outstate os = {
+		.fh = stat_config.output
+	};
+
+	if (prefix)
+		fprintf(stat_config.output, "%s", prefix);
+
+	if (!csv_output)
+		fprintf(stat_config.output, "%*s",
+			aggr_header_lens[stat_config.aggr_mode], "");
+
+	/* Print metrics headers only */
+	evlist__for_each(evsel_list, counter) {
+		os.evsel = counter;
+		out.ctx = &os;
+		out.print_metric = print_metric_header;
+		out.new_line = new_line_metric;
+		os.evsel = counter;
+		perf_stat__print_shadow_stats(counter, 0,
+					      0,
+					      &out);
 	}
+	fputc('\n', stat_config.output);
 }
 
 static void print_interval(char *prefix, struct timespec *ts)
@@ -1014,7 +1324,7 @@ static void print_interval(char *prefix, struct timespec *ts)
 
 	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
 
-	if (num_print_interval == 0 && !csv_output) {
+	if (num_print_interval == 0 && !csv_output && !metric_only) {
 		switch (stat_config.aggr_mode) {
 		case AGGR_SOCKET:
 			fprintf(output, "#           time socket cpus             counts %*s events\n", unit_width, "unit");
@@ -1101,6 +1411,17 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	else
 		print_header(argc, argv);
 
+	if (metric_only) {
+		static int num_print_iv;
+
+		if (num_print_iv == 0)
+			print_metric_headers(prefix);
+		if (num_print_iv++ == 25)
+			num_print_iv = 0;
+		if (stat_config.aggr_mode == AGGR_GLOBAL && prefix)
+			fprintf(stat_config.output, "%s", prefix);
+	}
+
 	switch (stat_config.aggr_mode) {
 	case AGGR_CORE:
 	case AGGR_SOCKET:
@@ -1113,10 +1434,16 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	case AGGR_GLOBAL:
 		evlist__for_each(evsel_list, counter)
 			print_counter_aggr(counter, prefix);
+		if (metric_only)
+			fputc('\n', stat_config.output);
 		break;
 	case AGGR_NONE:
-		evlist__for_each(evsel_list, counter)
-			print_counter(counter, prefix);
+		if (metric_only)
+			print_no_aggr_metric(prefix);
+		else {
+			evlist__for_each(evsel_list, counter)
+				print_counter(counter, prefix);
+		}
 		break;
 	case AGGR_UNSET:
 	default:
@@ -1237,6 +1564,8 @@ static const struct option stat_options[] = {
 		     "aggregate counts per thread", AGGR_THREAD),
 	OPT_UINTEGER('D', "delay", &initial_delay,
 		     "ms to wait before starting measurement after program start"),
+	OPT_BOOLEAN(0, "metric-only", &metric_only,
+			"Only print computed metrics. No raw values"),
 	OPT_END()
 };
 
@@ -1435,7 +1764,7 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
  */
 static int add_default_attributes(void)
 {
-	struct perf_event_attr default_attrs[] = {
+	struct perf_event_attr default_attrs0[] = {
 
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK		},
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES	},
@@ -1443,8 +1772,14 @@ static int add_default_attributes(void)
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS		},
 
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES		},
+};
+	struct perf_event_attr frontend_attrs[] = {
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	},
+};
+	struct perf_event_attr backend_attrs[] = {
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND	},
+};
+	struct perf_event_attr default_attrs1[] = {
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS		},
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS	},
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES		},
@@ -1561,7 +1896,19 @@ static int add_default_attributes(void)
 	}
 
 	if (!evsel_list->nr_entries) {
-		if (perf_evlist__add_default_attrs(evsel_list, default_attrs) < 0)
+		if (perf_evlist__add_default_attrs(evsel_list, default_attrs0) < 0)
+			return -1;
+		if (pmu_have_event("cpu", "stalled-cycles-frontend")) {
+			if (perf_evlist__add_default_attrs(evsel_list,
+						frontend_attrs) < 0)
+				return -1;
+		}
+		if (pmu_have_event("cpu", "stalled-cycles-backend")) {
+			if (perf_evlist__add_default_attrs(evsel_list,
+						backend_attrs) < 0)
+				return -1;
+		}
+		if (perf_evlist__add_default_attrs(evsel_list, default_attrs1) < 0)
 			return -1;
 	}
 
@@ -1825,9 +2172,11 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (evsel_list == NULL)
 		return -ENOMEM;
 
+	parse_events__shrink_config_terms();
 	argc = parse_options_subcommand(argc, argv, stat_options, stat_subcommands,
 					(const char **) stat_usage,
 					PARSE_OPT_STOP_AT_NON_OPTION);
+	perf_stat__init_shadow_stats();
 
 	if (csv_sep) {
 		csv_output = true;
@@ -1858,6 +2207,16 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out;
 	}
 
+	if (metric_only && stat_config.aggr_mode == AGGR_THREAD) {
+		fprintf(stderr, "--metric-only is not supported with --per-thread\n");
+		goto out;
+	}
+
+	if (metric_only && run_count > 1) {
+		fprintf(stderr, "--metric-only is not supported with -r\n");
+		goto out;
+	}
+
 	if (output_fd < 0) {
 		fprintf(stderr, "argument to --log-fd must be a > 0\n");
 		parse_options_usage(stat_usage, stat_options, "log-fd", 0);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index bf01cbb0ef23..94af190f6843 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -252,7 +252,8 @@ static void perf_top__print_sym_table(struct perf_top *top)
 	char bf[160];
 	int printed = 0;
 	const int win_width = top->winsize.ws_col - 1;
-	struct hists *hists = evsel__hists(top->sym_evsel);
+	struct perf_evsel *evsel = top->sym_evsel;
+	struct hists *hists = evsel__hists(evsel);
 
 	puts(CONSOLE_CLEAR);
 
@@ -288,7 +289,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
 	}
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists, NULL);
+	perf_evsel__output_resort(evsel, NULL);
 
 	hists__output_recalc_col_len(hists, top->print_entries - printed);
 	putchar('\n');
@@ -540,6 +541,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 static void perf_top__sort_new_samples(void *arg)
 {
 	struct perf_top *t = arg;
+	struct perf_evsel *evsel = t->sym_evsel;
 	struct hists *hists;
 
 	perf_top__reset_sample_counters(t);
@@ -547,7 +549,7 @@ static void perf_top__sort_new_samples(void *arg)
 	if (t->evlist->selected != NULL)
 		t->sym_evsel = t->evlist->selected;
 
-	hists = evsel__hists(t->sym_evsel);
+	hists = evsel__hists(evsel);
 
 	if (t->evlist->enabled) {
 		if (t->zero) {
@@ -559,7 +561,7 @@ static void perf_top__sort_new_samples(void *arg)
 	}
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists, NULL);
+	perf_evsel__output_resort(evsel, NULL);
 }
 
 static void *display_thread_tui(void *arg)
@@ -1063,7 +1065,7 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 	return parse_callchain_top_opt(arg);
 }
 
-static int perf_top_config(const char *var, const char *value, void *cb)
+static int perf_top_config(const char *var, const char *value, void *cb __maybe_unused)
 {
 	if (!strcmp(var, "top.call-graph"))
 		var = "call-graph.record-mode"; /* fall-through */
@@ -1072,7 +1074,7 @@ static int perf_top_config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 static int
@@ -1212,6 +1214,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		     parse_branch_stack),
 	OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace,
 		    "Show raw trace event output (do not use print fmt or plugins)"),
+	OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
+		    "Show entries in a hierarchy"),
 	OPT_END()
 	};
 	const char * const top_usage[] = {
@@ -1239,10 +1243,30 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out_delete_evlist;
 	}
 
+	if (symbol_conf.report_hierarchy) {
+		/* disable incompatible options */
+		symbol_conf.event_group = false;
+		symbol_conf.cumulate_callchain = false;
+
+		if (field_order) {
+			pr_err("Error: --hierarchy and --fields options cannot be used together\n");
+			parse_options_usage(top_usage, options, "fields", 0);
+			parse_options_usage(NULL, options, "hierarchy", 0);
+			goto out_delete_evlist;
+		}
+	}
+
 	sort__mode = SORT_MODE__TOP;
 	/* display thread wants entries to be collapsed in a different tree */
 	sort__need_collapse = 1;
 
+	if (top.use_stdio)
+		use_browser = 0;
+	else if (top.use_tui)
+		use_browser = 1;
+
+	setup_browser(false);
+
 	if (setup_sorting(top.evlist) < 0) {
 		if (sort_order)
 			parse_options_usage(top_usage, options, "s", 1);
@@ -1252,13 +1276,6 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out_delete_evlist;
 	}
 
-	if (top.use_stdio)
-		use_browser = 0;
-	else if (top.use_tui)
-		use_browser = 1;
-
-	setup_browser(false);
-
 	status = target__validate(target);
 	if (status) {
 		target__strerror(target, status, errbuf, BUFSIZ);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 20916dd77aac..8dc98c598b1a 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -33,6 +33,7 @@
 #include "util/stat.h"
 #include "trace-event.h"
 #include "util/parse-events.h"
+#include "util/bpf-loader.h"
 
 #include <libaudit.h>
 #include <stdlib.h>
@@ -1724,8 +1725,12 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 
 	sc->args = sc->tp_format->format.fields;
 	sc->nr_args = sc->tp_format->format.nr_fields;
-	/* drop nr field - not relevant here; does not exist on older kernels */
-	if (sc->args && strcmp(sc->args->name, "nr") == 0) {
+	/*
+	 * We need to check and discard the first variable '__syscall_nr'
+	 * or 'nr' that mean the syscall number. It is needless here.
+	 * So drop '__syscall_nr' or 'nr' field but does not exist on older kernels.
+	 */
+	if (sc->args && (!strcmp(sc->args->name, "__syscall_nr") || !strcmp(sc->args->name, "nr"))) {
 		sc->args = sc->args->next;
 		--sc->nr_args;
 	}
@@ -2177,6 +2182,37 @@ out_dump:
 	return 0;
 }
 
+static void bpf_output__printer(enum binary_printer_ops op,
+				unsigned int val, void *extra)
+{
+	FILE *output = extra;
+	unsigned char ch = (unsigned char)val;
+
+	switch (op) {
+	case BINARY_PRINT_CHAR_DATA:
+		fprintf(output, "%c", isprint(ch) ? ch : '.');
+		break;
+	case BINARY_PRINT_DATA_BEGIN:
+	case BINARY_PRINT_LINE_BEGIN:
+	case BINARY_PRINT_ADDR:
+	case BINARY_PRINT_NUM_DATA:
+	case BINARY_PRINT_NUM_PAD:
+	case BINARY_PRINT_SEP:
+	case BINARY_PRINT_CHAR_PAD:
+	case BINARY_PRINT_LINE_END:
+	case BINARY_PRINT_DATA_END:
+	default:
+		break;
+	}
+}
+
+static void bpf_output__fprintf(struct trace *trace,
+				struct perf_sample *sample)
+{
+	print_binary(sample->raw_data, sample->raw_size, 8,
+		     bpf_output__printer, trace->output);
+}
+
 static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 				union perf_event *event __maybe_unused,
 				struct perf_sample *sample)
@@ -2189,7 +2225,9 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 
 	fprintf(trace->output, "%s:", evsel->name);
 
-	if (evsel->tp_format) {
+	if (perf_evsel__is_bpf_output(evsel)) {
+		bpf_output__fprintf(trace, sample);
+	} else if (evsel->tp_format) {
 		event_format__fprintf(evsel->tp_format, sample->cpu,
 				      sample->raw_data, sample->raw_size,
 				      trace->output);
@@ -2586,6 +2624,16 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (err < 0)
 		goto out_error_open;
 
+	err = bpf__apply_obj_config();
+	if (err) {
+		char errbuf[BUFSIZ];
+
+		bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf));
+		pr_err("ERROR: Apply config to BPF failed: %s\n",
+			 errbuf);
+		goto out_error_open;
+	}
+
 	/*
 	 * Better not use !target__has_task() here because we need to cover the
 	 * case where no threads were specified in the command line, but a
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 511141b102e8..eca6a912e8c2 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -61,50 +61,45 @@ endif
 
 ifeq ($(LIBUNWIND_LIBS),)
   NO_LIBUNWIND := 1
-else
-  #
-  # For linking with debug library, run like:
-  #
-  #   make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
-  #
-  ifdef LIBUNWIND_DIR
-    LIBUNWIND_CFLAGS  = -I$(LIBUNWIND_DIR)/include
-    LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib
-  endif
-  LIBUNWIND_LDFLAGS += $(LIBUNWIND_LIBS)
-
-  # Set per-feature check compilation flags
-  FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS)
-  FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS)
-  FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS)
-  FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS)
 endif
+#
+# For linking with debug library, run like:
+#
+#   make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
+#
+ifdef LIBUNWIND_DIR
+  LIBUNWIND_CFLAGS  = -I$(LIBUNWIND_DIR)/include
+  LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib
+endif
+LIBUNWIND_LDFLAGS += $(LIBUNWIND_LIBS)
+
+# Set per-feature check compilation flags
+FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS)
+FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS)
 
 ifeq ($(NO_PERF_REGS),0)
   CFLAGS += -DHAVE_PERF_REGS_SUPPORT
 endif
 
-ifndef NO_LIBELF
-  # for linking with debug library, run like:
-  # make DEBUG=1 LIBDW_DIR=/opt/libdw/
-  ifdef LIBDW_DIR
-    LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
-    LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
-  endif
-  FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
-  FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw
+# for linking with debug library, run like:
+# make DEBUG=1 LIBDW_DIR=/opt/libdw/
+ifdef LIBDW_DIR
+  LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
+  LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
 endif
+FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw
 
-ifdef LIBBABELTRACE
-  # for linking with debug library, run like:
-  # make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/
-  ifdef LIBBABELTRACE_DIR
-    LIBBABELTRACE_CFLAGS  := -I$(LIBBABELTRACE_DIR)/include
-    LIBBABELTRACE_LDFLAGS := -L$(LIBBABELTRACE_DIR)/lib
-  endif
-  FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
-  FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
+# for linking with debug library, run like:
+# make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/
+ifdef LIBBABELTRACE_DIR
+  LIBBABELTRACE_CFLAGS  := -I$(LIBBABELTRACE_DIR)/include
+  LIBBABELTRACE_LDFLAGS := -L$(LIBBABELTRACE_DIR)/lib
 endif
+FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
 
 FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi
 # include ARCH specific config
@@ -145,28 +140,26 @@ ifdef PARSER_DEBUG
   $(call detected_var,PARSER_DEBUG_FLEX)
 endif
 
-ifndef NO_LIBPYTHON
-  # Try different combinations to accommodate systems that only have
-  # python[2][-config] in weird combinations but always preferring
-  # python2 and python2-config as per pep-0394. If we catch a
-  # python[-config] in version 3, the version check will kill it.
-  PYTHON2 := $(if $(call get-executable,python2),python2,python)
-  override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2))
-  PYTHON2_CONFIG := \
-    $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config)
-  override PYTHON_CONFIG := \
-    $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG))
+# Try different combinations to accommodate systems that only have
+# python[2][-config] in weird combinations but always preferring
+# python2 and python2-config as per pep-0394. If we catch a
+# python[-config] in version 3, the version check will kill it.
+PYTHON2 := $(if $(call get-executable,python2),python2,python)
+override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2))
+PYTHON2_CONFIG := \
+  $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config)
+override PYTHON_CONFIG := \
+  $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG))
 
-  PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
+PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
 
-  PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
-  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
 
-  FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
-  FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
-  FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
-  FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
-endif
+FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
+FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
+FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
+FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
 
 CFLAGS += -fno-omit-frame-pointer
 CFLAGS += -ggdb3
@@ -335,6 +328,13 @@ ifndef NO_LIBELF
   endif # NO_LIBBPF
 endif # NO_LIBELF
 
+ifdef PERF_HAVE_JITDUMP
+  ifndef NO_DWARF
+    $(call detected,CONFIG_JITDUMP)
+    CFLAGS += -DHAVE_JITDUMP
+  endif
+endif
+
 ifeq ($(ARCH),powerpc)
   ifndef NO_DWARF
     CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX
@@ -411,6 +411,17 @@ ifndef NO_LIBAUDIT
   endif
 endif
 
+ifndef NO_LIBCRYPTO
+  ifneq ($(feature-libcrypto), 1)
+    msg := $(warning No libcrypto.h found, disables jitted code injection, please install libssl-devel or libssl-dev);
+    NO_LIBCRYPTO := 1
+  else
+    CFLAGS += -DHAVE_LIBCRYPTO_SUPPORT
+    EXTLIBS += -lcrypto
+    $(call detected,CONFIG_CRYPTO)
+  endif
+endif
+
 ifdef NO_NEWT
   NO_SLANG=1
 endif
diff --git a/tools/perf/jvmti/Makefile b/tools/perf/jvmti/Makefile
new file mode 100644
index 000000000000..5ce61a1bda9c
--- /dev/null
+++ b/tools/perf/jvmti/Makefile
@@ -0,0 +1,89 @@
+ARCH=$(shell uname -m)
+
+ifeq ($(ARCH), x86_64)
+JARCH=amd64
+endif
+ifeq ($(ARCH), armv7l)
+JARCH=armhf
+endif
+ifeq ($(ARCH), armv6l)
+JARCH=armhf
+endif
+ifeq ($(ARCH), aarch64)
+JARCH=aarch64
+endif
+ifeq ($(ARCH), ppc64)
+JARCH=powerpc
+endif
+ifeq ($(ARCH), ppc64le)
+JARCH=powerpc
+endif
+
+DESTDIR=/usr/local
+
+VERSION=1
+REVISION=0
+AGE=0
+
+LN=ln -sf
+RM=rm
+
+SLIBJVMTI=libjvmti.so.$(VERSION).$(REVISION).$(AGE)
+VLIBJVMTI=libjvmti.so.$(VERSION)
+SLDFLAGS=-shared -Wl,-soname -Wl,$(VLIBJVMTI)
+SOLIBEXT=so
+
+# The following works at least on fedora 23, you may need the next
+# line for other distros.
+ifneq (,$(wildcard /usr/sbin/update-java-alternatives))
+JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | cut -d ' ' -f 3)
+else
+  ifneq (,$(wildcard /usr/sbin/alternatives))
+    JDIR=$(shell alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
+  endif
+endif
+ifndef JDIR
+$(error Could not find alternatives command, you need to set JDIR= to point to the root of your Java directory)
+else
+  ifeq (,$(wildcard $(JDIR)/include/jvmti.h))
+  $(error the openjdk development package appears to me missing, install and try again)
+  endif
+endif
+$(info Using Java from $(JDIR))
+# -lrt required in 32-bit mode for clock_gettime()
+LIBS=-lelf -lrt
+INCDIR=-I $(JDIR)/include -I $(JDIR)/include/linux
+
+TARGETS=$(SLIBJVMTI)
+
+SRCS=libjvmti.c jvmti_agent.c
+OBJS=$(SRCS:.c=.o)
+SOBJS=$(OBJS:.o=.lo)
+OPT=-O2 -g -Werror -Wall
+
+CFLAGS=$(INCDIR) $(OPT)
+
+all: $(TARGETS)
+
+.c.o:
+	$(CC) $(CFLAGS) -c $*.c
+.c.lo:
+	$(CC) -fPIC -DPIC $(CFLAGS) -c $*.c -o $*.lo
+
+$(OBJS) $(SOBJS): Makefile jvmti_agent.h ../util/jitdump.h
+
+$(SLIBJVMTI):  $(SOBJS)
+	$(CC) $(CFLAGS) $(SLDFLAGS)  -o $@ $(SOBJS) $(LIBS)
+	$(LN) $@ libjvmti.$(SOLIBEXT)
+
+clean:
+	$(RM) -f *.o *.so.* *.so *.lo
+
+install:
+	-mkdir -p $(DESTDIR)/lib
+	install -m 755 $(SLIBJVMTI) $(DESTDIR)/lib/
+	(cd $(DESTDIR)/lib; $(LN) $(SLIBJVMTI) $(VLIBJVMTI))
+	(cd $(DESTDIR)/lib; $(LN) $(SLIBJVMTI) libjvmti.$(SOLIBEXT))
+	ldconfig
+
+.SUFFIXES: .c .S .o .lo
diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c
new file mode 100644
index 000000000000..6461e02ab940
--- /dev/null
+++ b/tools/perf/jvmti/jvmti_agent.c
@@ -0,0 +1,465 @@
+/*
+ * jvmti_agent.c: JVMTI agent interface
+ *
+ * Adapted from the Oprofile code in opagent.c:
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ * Copyright 2007 OProfile authors
+ * Jens Wilke
+ * Daniel Hansel
+ * Copyright IBM Corporation 2007
+ */
+#include <sys/types.h>
+#include <sys/stat.h> /* for mkdir() */
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <limits.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <time.h>
+#include <sys/mman.h>
+#include <syscall.h> /* for gettid() */
+#include <err.h>
+
+#include "jvmti_agent.h"
+#include "../util/jitdump.h"
+
+#define JIT_LANG "java"
+
+static char jit_path[PATH_MAX];
+static void *marker_addr;
+
+/*
+ * padding buffer
+ */
+static const char pad_bytes[7];
+
+static inline pid_t gettid(void)
+{
+	return (pid_t)syscall(__NR_gettid);
+}
+
+static int get_e_machine(struct jitheader *hdr)
+{
+	ssize_t sret;
+	char id[16];
+	int fd, ret = -1;
+	int m = -1;
+	struct {
+		uint16_t e_type;
+		uint16_t e_machine;
+	} info;
+
+	fd = open("/proc/self/exe", O_RDONLY);
+	if (fd == -1)
+		return -1;
+
+	sret = read(fd, id, sizeof(id));
+	if (sret != sizeof(id))
+		goto error;
+
+	/* check ELF signature */
+	if (id[0] != 0x7f || id[1] != 'E' || id[2] != 'L' || id[3] != 'F')
+		goto error;
+
+	sret = read(fd, &info, sizeof(info));
+	if (sret != sizeof(info))
+		goto error;
+
+	m = info.e_machine;
+	if (m < 0)
+		m = 0; /* ELF EM_NONE */
+
+	hdr->elf_mach = m;
+	ret = 0;
+error:
+	close(fd);
+	return ret;
+}
+
+#define NSEC_PER_SEC	1000000000
+static int perf_clk_id = CLOCK_MONOTONIC;
+
+static inline uint64_t
+timespec_to_ns(const struct timespec *ts)
+{
+        return ((uint64_t) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec;
+}
+
+static inline uint64_t
+perf_get_timestamp(void)
+{
+	struct timespec ts;
+	int ret;
+
+	ret = clock_gettime(perf_clk_id, &ts);
+	if (ret)
+		return 0;
+
+	return timespec_to_ns(&ts);
+}
+
+static int
+debug_cache_init(void)
+{
+	char str[32];
+	char *base, *p;
+	struct tm tm;
+	time_t t;
+	int ret;
+
+	time(&t);
+	localtime_r(&t, &tm);
+
+	base = getenv("JITDUMPDIR");
+	if (!base)
+		base = getenv("HOME");
+	if (!base)
+		base = ".";
+
+	strftime(str, sizeof(str), JIT_LANG"-jit-%Y%m%d", &tm);
+
+	snprintf(jit_path, PATH_MAX - 1, "%s/.debug/", base);
+
+	ret = mkdir(jit_path, 0755);
+	if (ret == -1) {
+		if (errno != EEXIST) {
+			warn("jvmti: cannot create jit cache dir %s", jit_path);
+			return -1;
+		}
+	}
+
+	snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit", base);
+	ret = mkdir(jit_path, 0755);
+	if (ret == -1) {
+		if (errno != EEXIST) {
+			warn("cannot create jit cache dir %s", jit_path);
+			return -1;
+		}
+	}
+
+	snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit/%s.XXXXXXXX", base, str);
+
+	p = mkdtemp(jit_path);
+	if (p != jit_path) {
+		warn("cannot create jit cache dir %s", jit_path);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int
+perf_open_marker_file(int fd)
+{
+	long pgsz;
+
+	pgsz = sysconf(_SC_PAGESIZE);
+	if (pgsz == -1)
+		return -1;
+
+	/*
+	 * we mmap the jitdump to create an MMAP RECORD in perf.data file.
+	 * The mmap is captured either live (perf record running when we mmap)
+	 * or  in deferred mode, via /proc/PID/maps
+	 * the MMAP record is used as a marker of a jitdump file for more meta
+	 * data info about the jitted code. Perf report/annotate detect this
+	 * special filename and process the jitdump file.
+	 *
+	 * mapping must be PROT_EXEC to ensure it is captured by perf record
+	 * even when not using -d option
+	 */
+	marker_addr = mmap(NULL, pgsz, PROT_READ|PROT_EXEC, MAP_PRIVATE, fd, 0);
+	return (marker_addr == MAP_FAILED) ? -1 : 0;
+}
+
+static void
+perf_close_marker_file(void)
+{
+	long pgsz;
+
+	if (!marker_addr)
+		return;
+
+	pgsz = sysconf(_SC_PAGESIZE);
+	if (pgsz == -1)
+		return;
+
+	munmap(marker_addr, pgsz);
+}
+
+void *jvmti_open(void)
+{
+	int pad_cnt;
+	char dump_path[PATH_MAX];
+	struct jitheader header;
+	int fd;
+	FILE *fp;
+
+	/*
+	 * check if clockid is supported
+	 */
+	if (!perf_get_timestamp())
+		warnx("jvmti: kernel does not support %d clock id", perf_clk_id);
+
+	memset(&header, 0, sizeof(header));
+
+	debug_cache_init();
+
+	/*
+	 * jitdump file name
+	 */
+	snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
+
+	fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666);
+	if (fd == -1)
+		return NULL;
+
+	/*
+	 * create perf.data maker for the jitdump file
+	 */
+	if (perf_open_marker_file(fd)) {
+		warnx("jvmti: failed to create marker file");
+		return NULL;
+	}
+
+	fp = fdopen(fd, "w+");
+	if (!fp) {
+		warn("jvmti: cannot create %s", dump_path);
+		close(fd);
+		goto error;
+	}
+
+	warnx("jvmti: jitdump in %s", dump_path);
+
+	if (get_e_machine(&header)) {
+		warn("get_e_machine failed\n");
+		goto error;
+	}
+
+	header.magic      = JITHEADER_MAGIC;
+	header.version    = JITHEADER_VERSION;
+	header.total_size = sizeof(header);
+	header.pid        = getpid();
+
+	/* calculate amount of padding '\0' */
+	pad_cnt = PADDING_8ALIGNED(header.total_size);
+	header.total_size += pad_cnt;
+
+	header.timestamp = perf_get_timestamp();
+
+	if (!fwrite(&header, sizeof(header), 1, fp)) {
+		warn("jvmti: cannot write dumpfile header");
+		goto error;
+	}
+
+	/* write padding '\0' if necessary */
+	if (pad_cnt && !fwrite(pad_bytes, pad_cnt, 1, fp)) {
+		warn("jvmti: cannot write dumpfile header padding");
+		goto error;
+	}
+
+	return fp;
+error:
+	fclose(fp);
+	return NULL;
+}
+
+int
+jvmti_close(void *agent)
+{
+	struct jr_code_close rec;
+	FILE *fp = agent;
+
+	if (!fp) {
+		warnx("jvmti: incalid fd in close_agent");
+		return -1;
+	}
+
+	rec.p.id = JIT_CODE_CLOSE;
+	rec.p.total_size = sizeof(rec);
+
+	rec.p.timestamp = perf_get_timestamp();
+
+	if (!fwrite(&rec, sizeof(rec), 1, fp))
+		return -1;
+
+	fclose(fp);
+
+	fp = NULL;
+
+	perf_close_marker_file();
+
+	return 0;
+}
+
+int
+jvmti_write_code(void *agent, char const *sym,
+	uint64_t vma, void const *code, unsigned int const size)
+{
+	static int code_generation = 1;
+	struct jr_code_load rec;
+	size_t sym_len;
+	size_t padding_count;
+	FILE *fp = agent;
+	int ret = -1;
+
+	/* don't care about 0 length function, no samples */
+	if (size == 0)
+		return 0;
+
+	if (!fp) {
+		warnx("jvmti: invalid fd in write_native_code");
+		return -1;
+	}
+
+	sym_len = strlen(sym) + 1;
+
+	rec.p.id           = JIT_CODE_LOAD;
+	rec.p.total_size   = sizeof(rec) + sym_len;
+	padding_count      = PADDING_8ALIGNED(rec.p.total_size);
+	rec.p. total_size += padding_count;
+	rec.p.timestamp    = perf_get_timestamp();
+
+	rec.code_size  = size;
+	rec.vma        = vma;
+	rec.code_addr  = vma;
+	rec.pid	       = getpid();
+	rec.tid	       = gettid();
+
+	if (code)
+		rec.p.total_size += size;
+
+	/*
+	 * If JVM is multi-threaded, nultiple concurrent calls to agent
+	 * may be possible, so protect file writes
+	 */
+	flockfile(fp);
+
+	/*
+	 * get code index inside lock to avoid race condition
+	 */
+	rec.code_index = code_generation++;
+
+	ret = fwrite_unlocked(&rec, sizeof(rec), 1, fp);
+	fwrite_unlocked(sym, sym_len, 1, fp);
+
+	if (padding_count)
+		fwrite_unlocked(pad_bytes, padding_count, 1, fp);
+
+	if (code)
+		fwrite_unlocked(code, size, 1, fp);
+
+	funlockfile(fp);
+
+	ret = 0;
+
+	return ret;
+}
+
+int
+jvmti_write_debug_info(void *agent, uint64_t code, const char *file,
+		       jvmti_line_info_t *li, int nr_lines)
+{
+	struct jr_code_debug_info rec;
+	size_t sret, len, size, flen;
+	size_t padding_count;
+	uint64_t addr;
+	const char *fn = file;
+	FILE *fp = agent;
+	int i;
+
+	/*
+	 * no entry to write
+	 */
+	if (!nr_lines)
+		return 0;
+
+	if (!fp) {
+		warnx("jvmti: invalid fd in write_debug_info");
+		return -1;
+	}
+
+	flen = strlen(file) + 1;
+
+	rec.p.id        = JIT_CODE_DEBUG_INFO;
+	size            = sizeof(rec);
+	rec.p.timestamp = perf_get_timestamp();
+	rec.code_addr   = (uint64_t)(uintptr_t)code;
+	rec.nr_entry    = nr_lines;
+
+	/*
+	 * on disk source line info layout:
+	 * uint64_t : addr
+	 * int      : line number
+	 * int      : column discriminator
+	 * file[]   : source file name
+	 * padding  : pad to multiple of 8 bytes
+	 */
+	size += nr_lines * sizeof(struct debug_entry);
+	size += flen * nr_lines;
+	/*
+	 * pad to 8 bytes
+	 */
+	padding_count = PADDING_8ALIGNED(size);
+
+	rec.p.total_size = size + padding_count;
+
+	/*
+	 * If JVM is multi-threaded, nultiple concurrent calls to agent
+	 * may be possible, so protect file writes
+	 */
+	flockfile(fp);
+
+	sret = fwrite_unlocked(&rec, sizeof(rec), 1, fp);
+	if (sret != 1)
+		goto error;
+
+	for (i = 0; i < nr_lines; i++) {
+
+		addr = (uint64_t)li[i].pc;
+		len  = sizeof(addr);
+		sret = fwrite_unlocked(&addr, len, 1, fp);
+		if (sret != 1)
+			goto error;
+
+		len  = sizeof(li[0].line_number);
+		sret = fwrite_unlocked(&li[i].line_number, len, 1, fp);
+		if (sret != 1)
+			goto error;
+
+		len  = sizeof(li[0].discrim);
+		sret = fwrite_unlocked(&li[i].discrim, len, 1, fp);
+		if (sret != 1)
+			goto error;
+
+		sret = fwrite_unlocked(fn, flen, 1, fp);
+		if (sret != 1)
+			goto error;
+	}
+	if (padding_count)
+		sret = fwrite_unlocked(pad_bytes, padding_count, 1, fp);
+		if (sret != 1)
+			goto error;
+
+	funlockfile(fp);
+	return 0;
+error:
+	funlockfile(fp);
+	return -1;
+}
diff --git a/tools/perf/jvmti/jvmti_agent.h b/tools/perf/jvmti/jvmti_agent.h
new file mode 100644
index 000000000000..bedf5d0ba9ff
--- /dev/null
+++ b/tools/perf/jvmti/jvmti_agent.h
@@ -0,0 +1,36 @@
+#ifndef __JVMTI_AGENT_H__
+#define __JVMTI_AGENT_H__
+
+#include <sys/types.h>
+#include <stdint.h>
+#include <jvmti.h>
+
+#define __unused __attribute__((unused))
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+typedef struct {
+	unsigned long	pc;
+	int		line_number;
+	int		discrim; /* discriminator -- 0 for now */
+} jvmti_line_info_t;
+
+void *jvmti_open(void);
+int   jvmti_close(void *agent);
+int   jvmti_write_code(void *agent, char const *symbol_name,
+		       uint64_t vma, void const *code,
+		       const unsigned int code_size);
+
+int   jvmti_write_debug_info(void *agent,
+		             uint64_t code,
+			     const char *file,
+			     jvmti_line_info_t *li,
+			     int nr_lines);
+
+#if defined(__cplusplus)
+}
+
+#endif
+#endif /* __JVMTI_H__ */
diff --git a/tools/perf/jvmti/libjvmti.c b/tools/perf/jvmti/libjvmti.c
new file mode 100644
index 000000000000..ac12e4b91a92
--- /dev/null
+++ b/tools/perf/jvmti/libjvmti.c
@@ -0,0 +1,304 @@
+#include <sys/types.h>
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+#include <err.h>
+#include <jvmti.h>
+#include <jvmticmlr.h>
+#include <limits.h>
+
+#include "jvmti_agent.h"
+
+static int has_line_numbers;
+void *jvmti_agent;
+
+static jvmtiError
+do_get_line_numbers(jvmtiEnv *jvmti, void *pc, jmethodID m, jint bci,
+		    jvmti_line_info_t *tab, jint *nr)
+{
+	jint i, lines = 0;
+	jint nr_lines = 0;
+	jvmtiLineNumberEntry *loc_tab = NULL;
+	jvmtiError ret;
+
+	ret = (*jvmti)->GetLineNumberTable(jvmti, m, &nr_lines, &loc_tab);
+	if (ret != JVMTI_ERROR_NONE)
+		return ret;
+
+	for (i = 0; i < nr_lines; i++) {
+		if (loc_tab[i].start_location < bci) {
+			tab[lines].pc = (unsigned long)pc;
+			tab[lines].line_number = loc_tab[i].line_number;
+			tab[lines].discrim = 0; /* not yet used */
+			lines++;
+		} else {
+			break;
+		}
+	}
+	(*jvmti)->Deallocate(jvmti, (unsigned char *)loc_tab);
+	*nr = lines;
+	return JVMTI_ERROR_NONE;
+}
+
+static jvmtiError
+get_line_numbers(jvmtiEnv *jvmti, const void *compile_info, jvmti_line_info_t **tab, int *nr_lines)
+{
+	const jvmtiCompiledMethodLoadRecordHeader *hdr;
+	jvmtiCompiledMethodLoadInlineRecord *rec;
+	jvmtiLineNumberEntry *lne = NULL;
+	PCStackInfo *c;
+	jint nr, ret;
+	int nr_total = 0;
+	int i, lines_total = 0;
+
+	if (!(tab && nr_lines))
+		return JVMTI_ERROR_NULL_POINTER;
+
+	/*
+	 * Phase 1 -- get the number of lines necessary
+	 */
+	for (hdr = compile_info; hdr != NULL; hdr = hdr->next) {
+		if (hdr->kind == JVMTI_CMLR_INLINE_INFO) {
+			rec = (jvmtiCompiledMethodLoadInlineRecord *)hdr;
+			for (i = 0; i < rec->numpcs; i++) {
+				c = rec->pcinfo + i;
+				nr = 0;
+				/*
+				 * unfortunately, need a tab to get the number of lines!
+				 */
+				ret = (*jvmti)->GetLineNumberTable(jvmti, c->methods[0], &nr, &lne);
+				if (ret == JVMTI_ERROR_NONE) {
+					/* free what was allocated for nothing */
+					(*jvmti)->Deallocate(jvmti, (unsigned char *)lne);
+					nr_total += (int)nr;
+				}
+			}
+		}
+	}
+
+	if (nr_total == 0)
+		return JVMTI_ERROR_NOT_FOUND;
+
+	/*
+	 * Phase 2 -- allocate big enough line table
+	 */
+	*tab = malloc(nr_total * sizeof(**tab));
+	if (!*tab)
+		return JVMTI_ERROR_OUT_OF_MEMORY;
+
+	for (hdr = compile_info; hdr != NULL; hdr = hdr->next) {
+		if (hdr->kind == JVMTI_CMLR_INLINE_INFO) {
+			rec = (jvmtiCompiledMethodLoadInlineRecord *)hdr;
+			for (i = 0; i < rec->numpcs; i++) {
+				c = rec->pcinfo + i;
+				nr = 0;
+				ret = do_get_line_numbers(jvmti, c->pc,
+							  c->methods[0],
+							  c->bcis[0],
+							  *tab + lines_total,
+							  &nr);
+				if (ret == JVMTI_ERROR_NONE)
+					lines_total += nr;
+			}
+		}
+	}
+	*nr_lines = lines_total;
+	return JVMTI_ERROR_NONE;
+}
+
+static void JNICALL
+compiled_method_load_cb(jvmtiEnv *jvmti,
+			jmethodID method,
+			jint code_size,
+			void const *code_addr,
+			jint map_length,
+			jvmtiAddrLocationMap const *map,
+			const void *compile_info)
+{
+	jvmti_line_info_t *line_tab = NULL;
+	jclass decl_class;
+	char *class_sign = NULL;
+	char *func_name = NULL;
+	char *func_sign = NULL;
+	char *file_name= NULL;
+	char fn[PATH_MAX];
+	uint64_t addr = (uint64_t)(uintptr_t)code_addr;
+	jvmtiError ret;
+	int nr_lines = 0; /* in line_tab[] */
+	size_t len;
+
+	ret = (*jvmti)->GetMethodDeclaringClass(jvmti, method,
+						&decl_class);
+	if (ret != JVMTI_ERROR_NONE) {
+		warnx("jvmti: cannot get declaring class");
+		return;
+	}
+
+	if (has_line_numbers && map && map_length) {
+		ret = get_line_numbers(jvmti, compile_info, &line_tab, &nr_lines);
+		if (ret != JVMTI_ERROR_NONE) {
+			warnx("jvmti: cannot get line table for method");
+			nr_lines = 0;
+		}
+	}
+
+	ret = (*jvmti)->GetSourceFileName(jvmti, decl_class, &file_name);
+	if (ret != JVMTI_ERROR_NONE) {
+		warnx("jvmti: cannot get source filename ret=%d", ret);
+		goto error;
+	}
+
+	ret = (*jvmti)->GetClassSignature(jvmti, decl_class,
+					  &class_sign, NULL);
+	if (ret != JVMTI_ERROR_NONE) {
+		warnx("jvmti: getclassignature failed");
+		goto error;
+	}
+
+	ret = (*jvmti)->GetMethodName(jvmti, method, &func_name,
+				      &func_sign, NULL);
+	if (ret != JVMTI_ERROR_NONE) {
+		warnx("jvmti: failed getmethodname");
+		goto error;
+	}
+
+	/*
+	 * Assume path name is class hierarchy, this is a common practice with Java programs
+	 */
+	if (*class_sign == 'L') {
+		int j, i = 0;
+		char *p = strrchr(class_sign, '/');
+		if (p) {
+			/* drop the 'L' prefix and copy up to the final '/' */
+			for (i = 0; i < (p - class_sign); i++)
+				fn[i] = class_sign[i+1];
+		}
+		/*
+		 * append file name, we use loops and not string ops to avoid modifying
+		 * class_sign which is used later for the symbol name
+		 */
+		for (j = 0; i < (PATH_MAX - 1) && file_name && j < strlen(file_name); j++, i++)
+			fn[i] = file_name[j];
+		fn[i] = '\0';
+	} else {
+		/* fallback case */
+		strcpy(fn, file_name);
+	}
+	/*
+	 * write source line info record if we have it
+	 */
+	if (jvmti_write_debug_info(jvmti_agent, addr, fn, line_tab, nr_lines))
+		warnx("jvmti: write_debug_info() failed");
+
+	len = strlen(func_name) + strlen(class_sign) + strlen(func_sign) + 2;
+	{
+		char str[len];
+		snprintf(str, len, "%s%s%s", class_sign, func_name, func_sign);
+
+		if (jvmti_write_code(jvmti_agent, str, addr, code_addr, code_size))
+			warnx("jvmti: write_code() failed");
+	}
+error:
+	(*jvmti)->Deallocate(jvmti, (unsigned char *)func_name);
+	(*jvmti)->Deallocate(jvmti, (unsigned char *)func_sign);
+	(*jvmti)->Deallocate(jvmti, (unsigned char *)class_sign);
+	(*jvmti)->Deallocate(jvmti, (unsigned char *)file_name);
+	free(line_tab);
+}
+
+static void JNICALL
+code_generated_cb(jvmtiEnv *jvmti,
+		  char const *name,
+		  void const *code_addr,
+		  jint code_size)
+{
+	uint64_t addr = (uint64_t)(unsigned long)code_addr;
+	int ret;
+
+	ret = jvmti_write_code(jvmti_agent, name, addr, code_addr, code_size);
+	if (ret)
+		warnx("jvmti: write_code() failed for code_generated");
+}
+
+JNIEXPORT jint JNICALL
+Agent_OnLoad(JavaVM *jvm, char *options, void *reserved __unused)
+{
+	jvmtiEventCallbacks cb;
+	jvmtiCapabilities caps1;
+	jvmtiJlocationFormat format;
+	jvmtiEnv *jvmti = NULL;
+	jint ret;
+
+	jvmti_agent = jvmti_open();
+	if (!jvmti_agent) {
+		warnx("jvmti: open_agent failed");
+		return -1;
+	}
+
+	/*
+	 * Request a JVMTI interface version 1 environment
+	 */
+	ret = (*jvm)->GetEnv(jvm, (void *)&jvmti, JVMTI_VERSION_1);
+	if (ret != JNI_OK) {
+		warnx("jvmti: jvmti version 1 not supported");
+		return -1;
+	}
+
+	/*
+	 * acquire method_load capability, we require it
+	 * request line numbers (optional)
+	 */
+	memset(&caps1, 0, sizeof(caps1));
+	caps1.can_generate_compiled_method_load_events = 1;
+
+	ret = (*jvmti)->AddCapabilities(jvmti, &caps1);
+	if (ret != JVMTI_ERROR_NONE) {
+		warnx("jvmti: acquire compiled_method capability failed");
+		return -1;
+	}
+	ret = (*jvmti)->GetJLocationFormat(jvmti, &format);
+        if (ret == JVMTI_ERROR_NONE && format == JVMTI_JLOCATION_JVMBCI) {
+                memset(&caps1, 0, sizeof(caps1));
+                caps1.can_get_line_numbers = 1;
+                caps1.can_get_source_file_name = 1;
+		ret = (*jvmti)->AddCapabilities(jvmti, &caps1);
+                if (ret == JVMTI_ERROR_NONE)
+                        has_line_numbers = 1;
+        }
+
+	memset(&cb, 0, sizeof(cb));
+
+	cb.CompiledMethodLoad   = compiled_method_load_cb;
+	cb.DynamicCodeGenerated = code_generated_cb;
+
+	ret = (*jvmti)->SetEventCallbacks(jvmti, &cb, sizeof(cb));
+	if (ret != JVMTI_ERROR_NONE) {
+		warnx("jvmti: cannot set event callbacks");
+		return -1;
+	}
+
+	ret = (*jvmti)->SetEventNotificationMode(jvmti, JVMTI_ENABLE,
+			JVMTI_EVENT_COMPILED_METHOD_LOAD, NULL);
+	if (ret != JVMTI_ERROR_NONE) {
+		warnx("jvmti: setnotification failed for method_load");
+		return -1;
+	}
+
+	ret = (*jvmti)->SetEventNotificationMode(jvmti, JVMTI_ENABLE,
+			JVMTI_EVENT_DYNAMIC_CODE_GENERATED, NULL);
+	if (ret != JVMTI_ERROR_NONE) {
+		warnx("jvmti: setnotification failed on code_generated");
+		return -1;
+	}
+	return 0;
+}
+
+JNIEXPORT void JNICALL
+Agent_OnUnload(JavaVM *jvm __unused)
+{
+	int ret;
+
+	ret = jvmti_close(jvmti_agent);
+	if (ret)
+		errx(1, "Error: op_close_agent()");
+}
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index a929618b8eb6..aaee0a782747 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -454,11 +454,12 @@ static void handle_internal_command(int argc, const char **argv)
 
 static void execv_dashed_external(const char **argv)
 {
-	struct strbuf cmd = STRBUF_INIT;
+	char *cmd;
 	const char *tmp;
 	int status;
 
-	strbuf_addf(&cmd, "perf-%s", argv[0]);
+	if (asprintf(&cmd, "perf-%s", argv[0]) < 0)
+		goto do_die;
 
 	/*
 	 * argv[0] must be the perf command, but the argv array
@@ -467,7 +468,7 @@ static void execv_dashed_external(const char **argv)
 	 * restore it on error.
 	 */
 	tmp = argv[0];
-	argv[0] = cmd.buf;
+	argv[0] = cmd;
 
 	/*
 	 * if we fail because the command is not found, it is
@@ -475,15 +476,16 @@ static void execv_dashed_external(const char **argv)
 	 */
 	status = run_command_v_opt(argv, 0);
 	if (status != -ERR_RUN_COMMAND_EXEC) {
-		if (IS_RUN_COMMAND_ERR(status))
+		if (IS_RUN_COMMAND_ERR(status)) {
+do_die:
 			die("unable to run '%s'", argv[0]);
+		}
 		exit(-status);
 	}
 	errno = ENOENT; /* as if we called execvp */
 
 	argv[0] = tmp;
-
-	strbuf_release(&cmd);
+	zfree(&cmd);
 }
 
 static int run_argv(int *argcp, const char ***argv)
@@ -546,6 +548,8 @@ int main(int argc, const char **argv)
 
 	srandom(time(NULL));
 
+	perf_config(perf_default_config, NULL);
+
 	/* get debugfs/tracefs mount point from /proc/mounts */
 	tracing_path_mount();
 
@@ -613,6 +617,8 @@ int main(int argc, const char **argv)
 	 */
 	pthread__block_sigwinch();
 
+	perf_debug_setup();
+
 	while (1) {
 		static int done_help;
 		int was_alias = run_argv(&argc, &argv);
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 90129accffbe..5381a01c0610 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -58,6 +58,8 @@ struct record_opts {
 	bool	     full_auxtrace;
 	bool	     auxtrace_snapshot_mode;
 	bool	     record_switch_events;
+	bool	     all_kernel;
+	bool	     all_user;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int auxtrace_mmap_pages;
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
index 15c8400240fd..1d95009592eb 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -71,7 +71,10 @@ try:
 except:
 	if not audit_package_warned:
 		audit_package_warned = True
-		print "Install the audit-libs-python package to get syscall names"
+		print "Install the audit-libs-python package to get syscall names.\n" \
+                    "For example:\n  # apt-get install python-audit (Ubuntu)" \
+                    "\n  # yum install audit-libs-python (Fedora)" \
+                    "\n  etc.\n"
 
 def syscall_name(id):
 	try:
diff --git a/tools/perf/tests/.gitignore b/tools/perf/tests/.gitignore
index bf016c439fbd..8cc30e731c73 100644
--- a/tools/perf/tests/.gitignore
+++ b/tools/perf/tests/.gitignore
@@ -1,3 +1,4 @@
 llvm-src-base.c
 llvm-src-kbuild.c
 llvm-src-prologue.c
+llvm-src-relocation.c
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 614899b88b37..1ba628ed049a 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -31,7 +31,7 @@ perf-y += sample-parsing.o
 perf-y += parse-no-sample-id-all.o
 perf-y += kmod-path.o
 perf-y += thread-map.o
-perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o
+perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o llvm-src-relocation.o
 perf-y += bpf.o
 perf-y += topology.o
 perf-y += cpumap.o
@@ -59,6 +59,13 @@ $(OUTPUT)tests/llvm-src-prologue.c: tests/bpf-script-test-prologue.c tests/Build
 	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
 	$(Q)echo ';' >> $@
 
+$(OUTPUT)tests/llvm-src-relocation.c: tests/bpf-script-test-relocation.c tests/Build
+	$(call rule_mkdir)
+	$(Q)echo '#include <tests/llvm.h>' > $@
+	$(Q)echo 'const char test_llvm__bpf_test_relocation[] =' >> $@
+	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
+	$(Q)echo ';' >> $@
+
 ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64))
 perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 endif
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index fb80c9eb6a95..e7664fe3bd33 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -29,14 +29,59 @@
 
 static int fd1;
 static int fd2;
+static int fd3;
 static int overflows;
+static int overflows_2;
+
+volatile long the_var;
+
+
+/*
+ * Use ASM to ensure watchpoint and breakpoint can be triggered
+ * at one instruction.
+ */
+#if defined (__x86_64__)
+extern void __test_function(volatile long *ptr);
+asm (
+	".globl __test_function\n"
+	"__test_function:\n"
+	"incq (%rdi)\n"
+	"ret\n");
+#elif defined (__aarch64__)
+extern void __test_function(volatile long *ptr);
+asm (
+	".globl __test_function\n"
+	"__test_function:\n"
+	"str x30, [x0]\n"
+	"ret\n");
+
+#else
+static void __test_function(volatile long *ptr)
+{
+	*ptr = 0x1234;
+}
+#endif
 
 __attribute__ ((noinline))
 static int test_function(void)
 {
+	__test_function(&the_var);
+	the_var++;
 	return time(NULL);
 }
 
+static void sig_handler_2(int signum __maybe_unused,
+			  siginfo_t *oh __maybe_unused,
+			  void *uc __maybe_unused)
+{
+	overflows_2++;
+	if (overflows_2 > 10) {
+		ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0);
+		ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0);
+		ioctl(fd3, PERF_EVENT_IOC_DISABLE, 0);
+	}
+}
+
 static void sig_handler(int signum __maybe_unused,
 			siginfo_t *oh __maybe_unused,
 			void *uc __maybe_unused)
@@ -54,10 +99,11 @@ static void sig_handler(int signum __maybe_unused,
 		 */
 		ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0);
 		ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0);
+		ioctl(fd3, PERF_EVENT_IOC_DISABLE, 0);
 	}
 }
 
-static int bp_event(void *fn, int setup_signal)
+static int __event(bool is_x, void *addr, int sig)
 {
 	struct perf_event_attr pe;
 	int fd;
@@ -67,8 +113,8 @@ static int bp_event(void *fn, int setup_signal)
 	pe.size = sizeof(struct perf_event_attr);
 
 	pe.config = 0;
-	pe.bp_type = HW_BREAKPOINT_X;
-	pe.bp_addr = (unsigned long) fn;
+	pe.bp_type = is_x ? HW_BREAKPOINT_X : HW_BREAKPOINT_W;
+	pe.bp_addr = (unsigned long) addr;
 	pe.bp_len = sizeof(long);
 
 	pe.sample_period = 1;
@@ -86,17 +132,25 @@ static int bp_event(void *fn, int setup_signal)
 		return TEST_FAIL;
 	}
 
-	if (setup_signal) {
-		fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC);
-		fcntl(fd, F_SETSIG, SIGIO);
-		fcntl(fd, F_SETOWN, getpid());
-	}
+	fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC);
+	fcntl(fd, F_SETSIG, sig);
+	fcntl(fd, F_SETOWN, getpid());
 
 	ioctl(fd, PERF_EVENT_IOC_RESET, 0);
 
 	return fd;
 }
 
+static int bp_event(void *addr, int sig)
+{
+	return __event(true, addr, sig);
+}
+
+static int wp_event(void *addr, int sig)
+{
+	return __event(false, addr, sig);
+}
+
 static long long bp_count(int fd)
 {
 	long long count;
@@ -114,7 +168,7 @@ static long long bp_count(int fd)
 int test__bp_signal(int subtest __maybe_unused)
 {
 	struct sigaction sa;
-	long long count1, count2;
+	long long count1, count2, count3;
 
 	/* setup SIGIO signal handler */
 	memset(&sa, 0, sizeof(struct sigaction));
@@ -126,21 +180,52 @@ int test__bp_signal(int subtest __maybe_unused)
 		return TEST_FAIL;
 	}
 
+	sa.sa_sigaction = (void *) sig_handler_2;
+	if (sigaction(SIGUSR1, &sa, NULL) < 0) {
+		pr_debug("failed setting up signal handler 2\n");
+		return TEST_FAIL;
+	}
+
 	/*
 	 * We create following events:
 	 *
-	 * fd1 - breakpoint event on test_function with SIGIO
+	 * fd1 - breakpoint event on __test_function with SIGIO
 	 *       signal configured. We should get signal
 	 *       notification each time the breakpoint is hit
 	 *
-	 * fd2 - breakpoint event on sig_handler without SIGIO
+	 * fd2 - breakpoint event on sig_handler with SIGUSR1
+	 *       configured. We should get SIGUSR1 each time when
+	 *       breakpoint is hit
+	 *
+	 * fd3 - watchpoint event on __test_function with SIGIO
 	 *       configured.
 	 *
 	 * Following processing should happen:
-	 *   - execute test_function
-	 *   - fd1 event breakpoint hit -> count1 == 1
-	 *   - SIGIO is delivered       -> overflows == 1
-	 *   - fd2 event breakpoint hit -> count2 == 1
+	 *   Exec:               Action:                       Result:
+	 *   incq (%rdi)       - fd1 event breakpoint hit   -> count1 == 1
+	 *                     - SIGIO is delivered
+	 *   sig_handler       - fd2 event breakpoint hit   -> count2 == 1
+	 *                     - SIGUSR1 is delivered
+	 *   sig_handler_2                                  -> overflows_2 == 1  (nested signal)
+	 *   sys_rt_sigreturn  - return from sig_handler_2
+	 *   overflows++                                    -> overflows = 1
+	 *   sys_rt_sigreturn  - return from sig_handler
+	 *   incq (%rdi)       - fd3 event watchpoint hit   -> count3 == 1       (wp and bp in one insn)
+	 *                     - SIGIO is delivered
+	 *   sig_handler       - fd2 event breakpoint hit   -> count2 == 2
+	 *                     - SIGUSR1 is delivered
+	 *   sig_handler_2                                  -> overflows_2 == 2  (nested signal)
+	 *   sys_rt_sigreturn  - return from sig_handler_2
+	 *   overflows++                                    -> overflows = 2
+	 *   sys_rt_sigreturn  - return from sig_handler
+	 *   the_var++         - fd3 event watchpoint hit   -> count3 == 2       (standalone watchpoint)
+	 *                     - SIGIO is delivered
+	 *   sig_handler       - fd2 event breakpoint hit   -> count2 == 3
+	 *                     - SIGUSR1 is delivered
+	 *   sig_handler_2                                  -> overflows_2 == 3  (nested signal)
+	 *   sys_rt_sigreturn  - return from sig_handler_2
+	 *   overflows++                                    -> overflows == 3
+	 *   sys_rt_sigreturn  - return from sig_handler
 	 *
 	 * The test case check following error conditions:
 	 * - we get stuck in signal handler because of debug
@@ -152,11 +237,13 @@ int test__bp_signal(int subtest __maybe_unused)
 	 *
 	 */
 
-	fd1 = bp_event(test_function, 1);
-	fd2 = bp_event(sig_handler, 0);
+	fd1 = bp_event(__test_function, SIGIO);
+	fd2 = bp_event(sig_handler, SIGUSR1);
+	fd3 = wp_event((void *)&the_var, SIGIO);
 
 	ioctl(fd1, PERF_EVENT_IOC_ENABLE, 0);
 	ioctl(fd2, PERF_EVENT_IOC_ENABLE, 0);
+	ioctl(fd3, PERF_EVENT_IOC_ENABLE, 0);
 
 	/*
 	 * Kick off the test by trigering 'fd1'
@@ -166,15 +253,18 @@ int test__bp_signal(int subtest __maybe_unused)
 
 	ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0);
 	ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0);
+	ioctl(fd3, PERF_EVENT_IOC_DISABLE, 0);
 
 	count1 = bp_count(fd1);
 	count2 = bp_count(fd2);
+	count3 = bp_count(fd3);
 
 	close(fd1);
 	close(fd2);
+	close(fd3);
 
-	pr_debug("count1 %lld, count2 %lld, overflow %d\n",
-		 count1, count2, overflows);
+	pr_debug("count1 %lld, count2 %lld, count3 %lld, overflow %d, overflows_2 %d\n",
+		 count1, count2, count3, overflows, overflows_2);
 
 	if (count1 != 1) {
 		if (count1 == 11)
@@ -183,12 +273,18 @@ int test__bp_signal(int subtest __maybe_unused)
 			pr_debug("failed: wrong count for bp1%lld\n", count1);
 	}
 
-	if (overflows != 1)
+	if (overflows != 3)
 		pr_debug("failed: wrong overflow hit\n");
 
-	if (count2 != 1)
+	if (overflows_2 != 3)
+		pr_debug("failed: wrong overflow_2 hit\n");
+
+	if (count2 != 3)
 		pr_debug("failed: wrong count for bp2\n");
 
-	return count1 == 1 && overflows == 1 && count2 == 1 ?
+	if (count3 != 2)
+		pr_debug("failed: wrong count for bp3\n");
+
+	return count1 == 1 && overflows == 3 && count2 == 3 && overflows_2 == 3 && count3 == 2 ?
 		TEST_OK : TEST_FAIL;
 }
diff --git a/tools/perf/tests/bpf-script-test-relocation.c b/tools/perf/tests/bpf-script-test-relocation.c
new file mode 100644
index 000000000000..93af77421816
--- /dev/null
+++ b/tools/perf/tests/bpf-script-test-relocation.c
@@ -0,0 +1,50 @@
+/*
+ * bpf-script-test-relocation.c
+ * Test BPF loader checking relocation
+ */
+#ifndef LINUX_VERSION_CODE
+# error Need LINUX_VERSION_CODE
+# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig'
+#endif
+#define BPF_ANY 0
+#define BPF_MAP_TYPE_ARRAY 2
+#define BPF_FUNC_map_lookup_elem 1
+#define BPF_FUNC_map_update_elem 2
+
+static void *(*bpf_map_lookup_elem)(void *map, void *key) =
+	(void *) BPF_FUNC_map_lookup_elem;
+static void *(*bpf_map_update_elem)(void *map, void *key, void *value, int flags) =
+	(void *) BPF_FUNC_map_update_elem;
+
+struct bpf_map_def {
+	unsigned int type;
+	unsigned int key_size;
+	unsigned int value_size;
+	unsigned int max_entries;
+};
+
+#define SEC(NAME) __attribute__((section(NAME), used))
+struct bpf_map_def SEC("maps") my_table = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.max_entries = 1,
+};
+
+int this_is_a_global_val;
+
+SEC("func=sys_write")
+int bpf_func__sys_write(void *ctx)
+{
+	int key = 0;
+	int value = 0;
+
+	/*
+	 * Incorrect relocation. Should not allow this program be
+	 * loaded into kernel.
+	 */
+	bpf_map_update_elem(&this_is_a_global_val, &key, &value, 0);
+	return 0;
+}
+char _license[] SEC("license") = "GPL";
+int _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 33689a0cf821..199501c71e27 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -1,7 +1,11 @@
 #include <stdio.h>
 #include <sys/epoll.h>
+#include <util/util.h>
 #include <util/bpf-loader.h>
 #include <util/evlist.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <bpf/bpf.h>
 #include "tests.h"
 #include "llvm.h"
 #include "debug.h"
@@ -71,6 +75,15 @@ static struct {
 		(NR_ITERS + 1) / 4,
 	},
 #endif
+	{
+		LLVM_TESTCASE_BPF_RELOCATION,
+		"Test BPF relocation checker",
+		"[bpf_relocation_test]",
+		"fix 'perf test LLVM' first",
+		"libbpf error when dealing with relocation",
+		NULL,
+		0,
+	},
 };
 
 static int do_test(struct bpf_object *obj, int (*func)(void),
@@ -99,7 +112,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
 	parse_evlist.error = &parse_error;
 	INIT_LIST_HEAD(&parse_evlist.list);
 
-	err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj);
+	err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj, NULL);
 	if (err || list_empty(&parse_evlist.list)) {
 		pr_debug("Failed to add events selected by BPF\n");
 		return TEST_FAIL;
@@ -190,7 +203,7 @@ static int __test__bpf(int idx)
 
 	ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
 				       bpf_testcase_table[idx].prog_id,
-				       true);
+				       true, NULL);
 	if (ret != TEST_OK || !obj_buf || !obj_buf_sz) {
 		pr_debug("Unable to get BPF object, %s\n",
 			 bpf_testcase_table[idx].msg_compile_fail);
@@ -202,14 +215,21 @@ static int __test__bpf(int idx)
 
 	obj = prepare_bpf(obj_buf, obj_buf_sz,
 			  bpf_testcase_table[idx].name);
-	if (!obj) {
+	if ((!!bpf_testcase_table[idx].target_func) != (!!obj)) {
+		if (!obj)
+			pr_debug("Fail to load BPF object: %s\n",
+				 bpf_testcase_table[idx].msg_load_fail);
+		else
+			pr_debug("Success unexpectedly: %s\n",
+				 bpf_testcase_table[idx].msg_load_fail);
 		ret = TEST_FAIL;
 		goto out;
 	}
 
-	ret = do_test(obj,
-		      bpf_testcase_table[idx].target_func,
-		      bpf_testcase_table[idx].expect_result);
+	if (obj)
+		ret = do_test(obj,
+			      bpf_testcase_table[idx].target_func,
+			      bpf_testcase_table[idx].expect_result);
 out:
 	bpf__clear();
 	return ret;
@@ -227,6 +247,36 @@ const char *test__bpf_subtest_get_desc(int i)
 	return bpf_testcase_table[i].desc;
 }
 
+static int check_env(void)
+{
+	int err;
+	unsigned int kver_int;
+	char license[] = "GPL";
+
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+	};
+
+	err = fetch_kernel_version(&kver_int, NULL, 0);
+	if (err) {
+		pr_debug("Unable to get kernel version\n");
+		return err;
+	}
+
+	err = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns,
+			       sizeof(insns) / sizeof(insns[0]),
+			       license, kver_int, NULL, 0);
+	if (err < 0) {
+		pr_err("Missing basic BPF support, skip this test: %s\n",
+		       strerror(errno));
+		return err;
+	}
+	close(err);
+
+	return 0;
+}
+
 int test__bpf(int i)
 {
 	int err;
@@ -239,6 +289,9 @@ int test__bpf(int i)
 		return TEST_SKIP;
 	}
 
+	if (check_env())
+		return TEST_SKIP;
+
 	err = __test__bpf(i);
 	return err;
 }
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 313a48c6b2bc..afc9ad0a0515 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -439,7 +439,7 @@ static int do_test_code_reading(bool try_kcore)
 		.mmap_pages	     = UINT_MAX,
 		.user_freq	     = UINT_MAX,
 		.user_interval	     = ULLONG_MAX,
-		.freq		     = 4000,
+		.freq		     = 500,
 		.target		     = {
 			.uses_mmap   = true,
 		},
@@ -559,7 +559,13 @@ static int do_test_code_reading(bool try_kcore)
 				evlist = NULL;
 				continue;
 			}
-			pr_debug("perf_evlist__open failed\n");
+
+			if (verbose) {
+				char errbuf[512];
+				perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
+				pr_debug("perf_evlist__open() failed!\n%s\n", errbuf);
+			}
+
 			goto out_put;
 		}
 		break;
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 5e6a86e50fb9..ecf136c385d5 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -191,7 +191,7 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec
 	 * function since TEST_ASSERT_VAL() returns in case of failure.
 	 */
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists, NULL);
+	perf_evsel__output_resort(hists_to_evsel(hists), NULL);
 
 	if (verbose > 2) {
 		pr_info("use callchain: %d, cumulate callchain: %d\n",
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 351a42463444..34b945a55d4d 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -145,7 +145,7 @@ int test__hists_filter(int subtest __maybe_unused)
 		struct hists *hists = evsel__hists(evsel);
 
 		hists__collapse_resort(hists, NULL);
-		hists__output_resort(hists, NULL);
+		perf_evsel__output_resort(evsel, NULL);
 
 		if (verbose > 2) {
 			pr_info("Normal histogram\n");
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index b231265148d8..23cce67c7e48 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -156,7 +156,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists, NULL);
+	perf_evsel__output_resort(evsel, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -256,7 +256,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists, NULL);
+	perf_evsel__output_resort(evsel, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -310,7 +310,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists, NULL);
+	perf_evsel__output_resort(evsel, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -388,7 +388,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists, NULL);
+	perf_evsel__output_resort(evsel, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -491,7 +491,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine)
 		goto out;
 
 	hists__collapse_resort(hists, NULL);
-	hists__output_resort(hists, NULL);
+	perf_evsel__output_resort(evsel, NULL);
 
 	if (verbose > 2) {
 		pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index 06f45c1d4256..cff564fb4b66 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -6,12 +6,6 @@
 #include "tests.h"
 #include "debug.h"
 
-static int perf_config_cb(const char *var, const char *val,
-			  void *arg __maybe_unused)
-{
-	return perf_default_config(var, val, arg);
-}
-
 #ifdef HAVE_LIBBPF_SUPPORT
 static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
 {
@@ -35,6 +29,7 @@ static int test__bpf_parsing(void *obj_buf __maybe_unused,
 static struct {
 	const char *source;
 	const char *desc;
+	bool should_load_fail;
 } bpf_source_table[__LLVM_TESTCASE_MAX] = {
 	[LLVM_TESTCASE_BASE] = {
 		.source = test_llvm__bpf_base_prog,
@@ -48,14 +43,19 @@ static struct {
 		.source = test_llvm__bpf_test_prologue_prog,
 		.desc = "Compile source for BPF prologue generation test",
 	},
+	[LLVM_TESTCASE_BPF_RELOCATION] = {
+		.source = test_llvm__bpf_test_relocation,
+		.desc = "Compile source for BPF relocation test",
+		.should_load_fail = true,
+	},
 };
 
-
 int
 test_llvm__fetch_bpf_obj(void **p_obj_buf,
 			 size_t *p_obj_buf_sz,
 			 enum test_llvm__testcase idx,
-			 bool force)
+			 bool force,
+			 bool *should_load_fail)
 {
 	const char *source;
 	const char *desc;
@@ -68,8 +68,8 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf,
 
 	source = bpf_source_table[idx].source;
 	desc = bpf_source_table[idx].desc;
-
-	perf_config(perf_config_cb, NULL);
+	if (should_load_fail)
+		*should_load_fail = bpf_source_table[idx].should_load_fail;
 
 	/*
 	 * Skip this test if user's .perfconfig doesn't set [llvm] section
@@ -136,14 +136,15 @@ int test__llvm(int subtest)
 	int ret;
 	void *obj_buf = NULL;
 	size_t obj_buf_sz = 0;
+	bool should_load_fail = false;
 
 	if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX))
 		return TEST_FAIL;
 
 	ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
-				       subtest, false);
+				       subtest, false, &should_load_fail);
 
-	if (ret == TEST_OK) {
+	if (ret == TEST_OK && !should_load_fail) {
 		ret = test__bpf_parsing(obj_buf, obj_buf_sz);
 		if (ret != TEST_OK) {
 			pr_debug("Failed to parse test case '%s'\n",
diff --git a/tools/perf/tests/llvm.h b/tools/perf/tests/llvm.h
index 5150b4d6ef50..0eaa604be99d 100644
--- a/tools/perf/tests/llvm.h
+++ b/tools/perf/tests/llvm.h
@@ -7,14 +7,17 @@
 extern const char test_llvm__bpf_base_prog[];
 extern const char test_llvm__bpf_test_kbuild_prog[];
 extern const char test_llvm__bpf_test_prologue_prog[];
+extern const char test_llvm__bpf_test_relocation[];
 
 enum test_llvm__testcase {
 	LLVM_TESTCASE_BASE,
 	LLVM_TESTCASE_KBUILD,
 	LLVM_TESTCASE_BPF_PROLOGUE,
+	LLVM_TESTCASE_BPF_RELOCATION,
 	__LLVM_TESTCASE_MAX,
 };
 
 int test_llvm__fetch_bpf_obj(void **p_obj_buf, size_t *p_obj_buf_sz,
-			     enum test_llvm__testcase index, bool force);
+			     enum test_llvm__testcase index, bool force,
+			     bool *should_load_fail);
 #endif
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index f918015512af..cac15d93aea6 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -15,6 +15,7 @@ else
 PERF := .
 PERF_O := $(PERF)
 O_OPT :=
+FULL_O := $(shell readlink -f $(PERF_O) || echo $(PERF_O))
 
 ifneq ($(O),)
   FULL_O := $(shell readlink -f $(O) || echo $(O))
@@ -79,6 +80,7 @@ make_no_libaudit    := NO_LIBAUDIT=1
 make_no_libbionic   := NO_LIBBIONIC=1
 make_no_auxtrace    := NO_AUXTRACE=1
 make_no_libbpf	    := NO_LIBBPF=1
+make_no_libcrypto   := NO_LIBCRYPTO=1
 make_tags           := tags
 make_cscope         := cscope
 make_help           := help
@@ -102,6 +104,7 @@ make_minimal        := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1
 make_minimal        += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1
 make_minimal        += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1
 make_minimal        += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1
+make_minimal        += NO_LIBCRYPTO=1
 
 # $(run) contains all available tests
 run := make_pure
@@ -110,6 +113,9 @@ run := make_pure
 # disable features detection
 ifeq ($(MK),Makefile)
 run += make_clean_all
+MAKE_F := $(MAKE)
+else
+MAKE_F := $(MAKE) -f $(MK)
 endif
 run += make_python_perf_so
 run += make_debug
@@ -260,6 +266,8 @@ run := $(shell shuf -e $(run))
 run_O := $(shell shuf -e $(run_O))
 endif
 
+max_width := $(shell echo $(run_O) | sed 's/ /\n/g' | wc -L)
+
 ifdef DEBUG
 d := $(info run   $(run))
 d := $(info run_O $(run_O))
@@ -267,13 +275,13 @@ endif
 
 MAKEFLAGS := --no-print-directory
 
-clean := @(cd $(PERF); make -s -f $(MK) $(O_OPT) clean >/dev/null)
+clean := @(cd $(PERF); $(MAKE_F) -s $(O_OPT) clean >/dev/null)
 
 $(run):
 	$(call clean)
 	@TMP_DEST=$$(mktemp -d); \
-	cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) $(O_OPT) DESTDIR=$$TMP_DEST $($@)"; \
-	echo "- $@: $$cmd" && echo $$cmd > $@ && \
+	cmd="cd $(PERF) && $(MAKE_F) $($@) $(PARALLEL_OPT) $(O_OPT) DESTDIR=$$TMP_DEST"; \
+	printf "%*.*s: %s\n" $(max_width) $(max_width) "$@" "$$cmd" && echo $$cmd > $@ && \
 	( eval $$cmd ) >> $@ 2>&1; \
 	echo "  test: $(call test,$@)" >> $@ 2>&1; \
 	$(call test,$@) && \
@@ -283,8 +291,8 @@ $(run_O):
 	$(call clean)
 	@TMP_O=$$(mktemp -d); \
 	TMP_DEST=$$(mktemp -d); \
-	cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \
-	echo "- $@: $$cmd" && echo $$cmd > $@ && \
+	cmd="cd $(PERF) && $(MAKE_F) $($(patsubst %_O,%,$@)) $(PARALLEL_OPT) O=$$TMP_O DESTDIR=$$TMP_DEST"; \
+	printf "%*.*s: %s\n" $(max_width) $(max_width) "$@" "$$cmd" && echo $$cmd > $@ && \
 	( eval $$cmd ) >> $@ 2>&1 && \
 	echo "  test: $(call test_O,$@)" >> $@ 2>&1; \
 	$(call test_O,$@) && \
@@ -313,11 +321,43 @@ make_kernelsrc_tools:
 	(make -C ../../tools $(PARALLEL_OPT) $(K_O_OPT) perf) > $@ 2>&1 && \
 	test -x $(KERNEL_O)/tools/perf/perf && rm -f $@ || (cat $@ ; false)
 
+FEATURES_DUMP_FILE := $(FULL_O)/BUILD_TEST_FEATURE_DUMP
+FEATURES_DUMP_FILE_STATIC := $(FULL_O)/BUILD_TEST_FEATURE_DUMP_STATIC
+
 all: $(run) $(run_O) tarpkg make_kernelsrc make_kernelsrc_tools
 	@echo OK
+	@rm -f $(FEATURES_DUMP_FILE) $(FEATURES_DUMP_FILE_STATIC)
 
 out: $(run_O)
 	@echo OK
+	@rm -f $(FEATURES_DUMP_FILE) $(FEATURES_DUMP_FILE_STATIC)
+
+ifeq ($(REUSE_FEATURES_DUMP),1)
+$(FEATURES_DUMP_FILE):
+	$(call clean)
+	@cmd="cd $(PERF) && make FEATURE_DUMP_COPY=$@ $(O_OPT) feature-dump"; \
+	echo "- $@: $$cmd" && echo $$cmd && \
+	( eval $$cmd ) > /dev/null 2>&1
+
+$(FEATURES_DUMP_FILE_STATIC):
+	$(call clean)
+	@cmd="cd $(PERF) && make FEATURE_DUMP_COPY=$@ $(O_OPT) LDFLAGS='-static' feature-dump"; \
+	echo "- $@: $$cmd" && echo $$cmd && \
+	( eval $$cmd ) > /dev/null 2>&1
+
+# Add feature dump dependency for run/run_O targets
+$(foreach t,$(run) $(run_O),$(eval \
+	$(t): $(if $(findstring make_static,$(t)),\
+		$(FEATURES_DUMP_FILE_STATIC),\
+		$(FEATURES_DUMP_FILE))))
+
+# Append 'FEATURES_DUMP=' option to all test cases. For example:
+# make_no_libbpf: NO_LIBBPF=1  --> NO_LIBBPF=1 FEATURES_DUMP=/a/b/BUILD_TEST_FEATURE_DUMP
+# make_static: LDFLAGS=-static --> LDFLAGS=-static FEATURES_DUMP=/a/b/BUILD_TEST_FEATURE_DUMP_STATIC
+$(foreach t,$(run),$(if $(findstring make_static,$(t)),\
+			$(eval $(t) := $($(t)) FEATURES_DUMP=$(FEATURES_DUMP_FILE_STATIC)),\
+			$(eval $(t) := $($(t)) FEATURES_DUMP=$(FEATURES_DUMP_FILE))))
+endif
 
 .PHONY: all $(run) $(run_O) tarpkg clean make_kernelsrc make_kernelsrc_tools
 endif # ifndef MK
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index abe8849d1d70..7865f68dc0d8 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1271,6 +1271,38 @@ static int test__checkevent_precise_max_modifier(struct perf_evlist *evlist)
 	return 0;
 }
 
+static int test__checkevent_config_symbol(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "insn") == 0);
+	return 0;
+}
+
+static int test__checkevent_config_raw(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "rawpmu") == 0);
+	return 0;
+}
+
+static int test__checkevent_config_num(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "numpmu") == 0);
+	return 0;
+}
+
+static int test__checkevent_config_cache(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "cachepmu") == 0);
+	return 0;
+}
+
 static int count_tracepoints(void)
 {
 	struct dirent *events_ent;
@@ -1579,6 +1611,26 @@ static struct evlist_test test__events[] = {
 		.check = test__checkevent_precise_max_modifier,
 		.id    = 47,
 	},
+	{
+		.name  = "instructions/name=insn/",
+		.check = test__checkevent_config_symbol,
+		.id    = 48,
+	},
+	{
+		.name  = "r1234/name=rawpmu/",
+		.check = test__checkevent_config_raw,
+		.id    = 49,
+	},
+	{
+		.name  = "4:0x6530160/name=numpmu/",
+		.check = test__checkevent_config_num,
+		.id    = 50,
+	},
+	{
+		.name  = "L1-dcache-misses/name=cachepmu/",
+		.check = test__checkevent_config_cache,
+		.id    = 51,
+	},
 };
 
 static struct evlist_test test__events_pmu[] = {
@@ -1666,7 +1718,7 @@ static int test_term(struct terms_test *t)
 	}
 
 	ret = t->check(&terms);
-	parse_events__free_terms(&terms);
+	parse_events_terms__purge(&terms);
 
 	return ret;
 }
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index f0bfc9e8fd9f..630b0b409b97 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -110,7 +110,6 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
 	 */
 	for (nd = rb_first(&vmlinux_map->dso->symbols[type]); nd; nd = rb_next(nd)) {
 		struct symbol *pair, *first_pair;
-		bool backwards = true;
 
 		sym  = rb_entry(nd, struct symbol, rb_node);
 
@@ -151,27 +150,14 @@ next_pair:
 				continue;
 
 			} else {
-				struct rb_node *nnd;
-detour:
-				nnd = backwards ? rb_prev(&pair->rb_node) :
-						  rb_next(&pair->rb_node);
-				if (nnd) {
-					struct symbol *next = rb_entry(nnd, struct symbol, rb_node);
-
-					if (UM(next->start) == mem_start) {
-						pair = next;
+				pair = machine__find_kernel_symbol_by_name(&kallsyms, type, sym->name, NULL, NULL);
+				if (pair) {
+					if (UM(pair->start) == mem_start)
 						goto next_pair;
-					}
-				}
 
-				if (backwards) {
-					backwards = false;
-					pair = first_pair;
-					goto detour;
+					pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n",
+						 mem_start, sym->name, pair->name);
 				}
-
-				pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n",
-					 mem_start, sym->name, pair->name);
 			}
 		} else
 			pr_debug("%#" PRIx64 ": %s not on kallsyms\n",
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index d37202121689..af68a9d488bf 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -531,8 +531,8 @@ static struct ui_browser_colorset {
 		.bg	  = "yellow",
 	},
 	{
-		.colorset = HE_COLORSET_CODE,
-		.name	  = "code",
+		.colorset = HE_COLORSET_JUMP_ARROWS,
+		.name	  = "jump_arrows",
 		.fg	  = "blue",
 		.bg	  = "default",
 	},
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index 01781de59532..be3b70eb5fca 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -7,7 +7,7 @@
 #define HE_COLORSET_MEDIUM	51
 #define HE_COLORSET_NORMAL	52
 #define HE_COLORSET_SELECTED	53
-#define HE_COLORSET_CODE	54
+#define HE_COLORSET_JUMP_ARROWS	54
 #define HE_COLORSET_ADDR	55
 #define HE_COLORSET_ROOT	56
 
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 718bd46d47fa..4fc208e82c6f 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -284,7 +284,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 		to = (u64)btarget->idx;
 	}
 
-	ui_browser__set_color(browser, HE_COLORSET_CODE);
+	ui_browser__set_color(browser, HE_COLORSET_JUMP_ARROWS);
 	__ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width,
 				 from, to);
 }
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 08c09ad755d2..4b9816555946 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -32,6 +32,7 @@ struct hist_browser {
 	bool		     show_headers;
 	float		     min_pcnt;
 	u64		     nr_non_filtered_entries;
+	u64		     nr_hierarchy_entries;
 	u64		     nr_callchain_rows;
 };
 
@@ -58,11 +59,11 @@ static int hist_browser__get_folding(struct hist_browser *browser)
 
 	for (nd = rb_first(&hists->entries);
 	     (nd = hists__filter_entries(nd, browser->min_pcnt)) != NULL;
-	     nd = rb_next(nd)) {
+	     nd = rb_hierarchy_next(nd)) {
 		struct hist_entry *he =
 			rb_entry(nd, struct hist_entry, rb_node);
 
-		if (he->unfolded)
+		if (he->leaf && he->unfolded)
 			unfolded_rows += he->nr_rows;
 	}
 	return unfolded_rows;
@@ -72,7 +73,9 @@ static u32 hist_browser__nr_entries(struct hist_browser *hb)
 {
 	u32 nr_entries;
 
-	if (hist_browser__has_filter(hb))
+	if (symbol_conf.report_hierarchy)
+		nr_entries = hb->nr_hierarchy_entries;
+	else if (hist_browser__has_filter(hb))
 		nr_entries = hb->nr_non_filtered_entries;
 	else
 		nr_entries = hb->hists->nr_entries;
@@ -247,6 +250,38 @@ static int callchain__count_rows(struct rb_root *chain)
 	return n;
 }
 
+static int hierarchy_count_rows(struct hist_browser *hb, struct hist_entry *he,
+				bool include_children)
+{
+	int count = 0;
+	struct rb_node *node;
+	struct hist_entry *child;
+
+	if (he->leaf)
+		return callchain__count_rows(&he->sorted_chain);
+
+	if (he->has_no_entry)
+		return 1;
+
+	node = rb_first(&he->hroot_out);
+	while (node) {
+		float percent;
+
+		child = rb_entry(node, struct hist_entry, rb_node);
+		percent = hist_entry__get_percent_limit(child);
+
+		if (!child->filtered && percent >= hb->min_pcnt) {
+			count++;
+
+			if (include_children && child->unfolded)
+				count += hierarchy_count_rows(hb, child, true);
+		}
+
+		node = rb_next(node);
+	}
+	return count;
+}
+
 static bool hist_entry__toggle_fold(struct hist_entry *he)
 {
 	if (!he)
@@ -326,11 +361,17 @@ static void callchain__init_have_children(struct rb_root *root)
 
 static void hist_entry__init_have_children(struct hist_entry *he)
 {
-	if (!he->init_have_children) {
+	if (he->init_have_children)
+		return;
+
+	if (he->leaf) {
 		he->has_children = !RB_EMPTY_ROOT(&he->sorted_chain);
 		callchain__init_have_children(&he->sorted_chain);
-		he->init_have_children = true;
+	} else {
+		he->has_children = !RB_EMPTY_ROOT(&he->hroot_out);
 	}
+
+	he->init_have_children = true;
 }
 
 static bool hist_browser__toggle_fold(struct hist_browser *browser)
@@ -349,17 +390,49 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser)
 		has_children = callchain_list__toggle_fold(cl);
 
 	if (has_children) {
+		int child_rows = 0;
+
 		hist_entry__init_have_children(he);
 		browser->b.nr_entries -= he->nr_rows;
-		browser->nr_callchain_rows -= he->nr_rows;
 
-		if (he->unfolded)
-			he->nr_rows = callchain__count_rows(&he->sorted_chain);
+		if (he->leaf)
+			browser->nr_callchain_rows -= he->nr_rows;
 		else
+			browser->nr_hierarchy_entries -= he->nr_rows;
+
+		if (symbol_conf.report_hierarchy)
+			child_rows = hierarchy_count_rows(browser, he, true);
+
+		if (he->unfolded) {
+			if (he->leaf)
+				he->nr_rows = callchain__count_rows(&he->sorted_chain);
+			else
+				he->nr_rows = hierarchy_count_rows(browser, he, false);
+
+			/* account grand children */
+			if (symbol_conf.report_hierarchy)
+				browser->b.nr_entries += child_rows - he->nr_rows;
+
+			if (!he->leaf && he->nr_rows == 0) {
+				he->has_no_entry = true;
+				he->nr_rows = 1;
+			}
+		} else {
+			if (symbol_conf.report_hierarchy)
+				browser->b.nr_entries -= child_rows - he->nr_rows;
+
+			if (he->has_no_entry)
+				he->has_no_entry = false;
+
 			he->nr_rows = 0;
+		}
 
 		browser->b.nr_entries += he->nr_rows;
-		browser->nr_callchain_rows += he->nr_rows;
+
+		if (he->leaf)
+			browser->nr_callchain_rows += he->nr_rows;
+		else
+			browser->nr_hierarchy_entries += he->nr_rows;
 
 		return true;
 	}
@@ -422,13 +495,38 @@ static int callchain__set_folding(struct rb_root *chain, bool unfold)
 	return n;
 }
 
-static void hist_entry__set_folding(struct hist_entry *he, bool unfold)
+static int hierarchy_set_folding(struct hist_browser *hb, struct hist_entry *he,
+				 bool unfold __maybe_unused)
+{
+	float percent;
+	struct rb_node *nd;
+	struct hist_entry *child;
+	int n = 0;
+
+	for (nd = rb_first(&he->hroot_out); nd; nd = rb_next(nd)) {
+		child = rb_entry(nd, struct hist_entry, rb_node);
+		percent = hist_entry__get_percent_limit(child);
+		if (!child->filtered && percent >= hb->min_pcnt)
+			n++;
+	}
+
+	return n;
+}
+
+static void hist_entry__set_folding(struct hist_entry *he,
+				    struct hist_browser *hb, bool unfold)
 {
 	hist_entry__init_have_children(he);
 	he->unfolded = unfold ? he->has_children : false;
 
 	if (he->has_children) {
-		int n = callchain__set_folding(&he->sorted_chain, unfold);
+		int n;
+
+		if (he->leaf)
+			n = callchain__set_folding(&he->sorted_chain, unfold);
+		else
+			n = hierarchy_set_folding(hb, he, unfold);
+
 		he->nr_rows = unfold ? n : 0;
 	} else
 		he->nr_rows = 0;
@@ -438,19 +536,38 @@ static void
 __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 {
 	struct rb_node *nd;
-	struct hists *hists = browser->hists;
+	struct hist_entry *he;
+	double percent;
 
-	for (nd = rb_first(&hists->entries);
-	     (nd = hists__filter_entries(nd, browser->min_pcnt)) != NULL;
-	     nd = rb_next(nd)) {
-		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
-		hist_entry__set_folding(he, unfold);
-		browser->nr_callchain_rows += he->nr_rows;
+	nd = rb_first(&browser->hists->entries);
+	while (nd) {
+		he = rb_entry(nd, struct hist_entry, rb_node);
+
+		/* set folding state even if it's currently folded */
+		nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD);
+
+		hist_entry__set_folding(he, browser, unfold);
+
+		percent = hist_entry__get_percent_limit(he);
+		if (he->filtered || percent < browser->min_pcnt)
+			continue;
+
+		if (!he->depth || unfold)
+			browser->nr_hierarchy_entries++;
+		if (he->leaf)
+			browser->nr_callchain_rows += he->nr_rows;
+		else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
+			browser->nr_hierarchy_entries++;
+			he->has_no_entry = true;
+			he->nr_rows = 1;
+		} else
+			he->has_no_entry = false;
 	}
 }
 
 static void hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 {
+	browser->nr_hierarchy_entries = 0;
 	browser->nr_callchain_rows = 0;
 	__hist_browser__set_folding(browser, unfold);
 
@@ -657,9 +774,24 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
 	return 1;
 }
 
+static bool check_percent_display(struct rb_node *node, u64 parent_total)
+{
+	struct callchain_node *child;
+
+	if (node == NULL)
+		return false;
+
+	if (rb_next(node))
+		return true;
+
+	child = rb_entry(node, struct callchain_node, rb_node);
+	return callchain_cumul_hits(child) != parent_total;
+}
+
 static int hist_browser__show_callchain_flat(struct hist_browser *browser,
 					     struct rb_root *root,
 					     unsigned short row, u64 total,
+					     u64 parent_total,
 					     print_callchain_entry_fn print,
 					     struct callchain_print_arg *arg,
 					     check_output_full_fn is_output_full)
@@ -669,7 +801,7 @@ static int hist_browser__show_callchain_flat(struct hist_browser *browser,
 	bool need_percent;
 
 	node = rb_first(root);
-	need_percent = node && rb_next(node);
+	need_percent = check_percent_display(node, parent_total);
 
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
@@ -763,6 +895,7 @@ static char *hist_browser__folded_callchain_str(struct hist_browser *browser,
 static int hist_browser__show_callchain_folded(struct hist_browser *browser,
 					       struct rb_root *root,
 					       unsigned short row, u64 total,
+					       u64 parent_total,
 					       print_callchain_entry_fn print,
 					       struct callchain_print_arg *arg,
 					       check_output_full_fn is_output_full)
@@ -772,7 +905,7 @@ static int hist_browser__show_callchain_folded(struct hist_browser *browser,
 	bool need_percent;
 
 	node = rb_first(root);
-	need_percent = node && rb_next(node);
+	need_percent = check_percent_display(node, parent_total);
 
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
@@ -844,20 +977,24 @@ next:
 	return row - first_row;
 }
 
-static int hist_browser__show_callchain(struct hist_browser *browser,
+static int hist_browser__show_callchain_graph(struct hist_browser *browser,
 					struct rb_root *root, int level,
 					unsigned short row, u64 total,
+					u64 parent_total,
 					print_callchain_entry_fn print,
 					struct callchain_print_arg *arg,
 					check_output_full_fn is_output_full)
 {
 	struct rb_node *node;
 	int first_row = row, offset = level * LEVEL_OFFSET_STEP;
-	u64 new_total;
 	bool need_percent;
+	u64 percent_total = total;
+
+	if (callchain_param.mode == CHAIN_GRAPH_REL)
+		percent_total = parent_total;
 
 	node = rb_first(root);
-	need_percent = node && rb_next(node);
+	need_percent = check_percent_display(node, parent_total);
 
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
@@ -878,7 +1015,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 			folded_sign = callchain_list__folded(chain);
 
 			row += hist_browser__show_callchain_list(browser, child,
-							chain, row, total,
+							chain, row, percent_total,
 							was_first && need_percent,
 							offset + extra_offset,
 							print, arg);
@@ -893,13 +1030,9 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 		if (folded_sign == '-') {
 			const int new_level = level + (extra_offset ? 2 : 1);
 
-			if (callchain_param.mode == CHAIN_GRAPH_REL)
-				new_total = child->children_hit;
-			else
-				new_total = total;
-
-			row += hist_browser__show_callchain(browser, &child->rb_root,
-							    new_level, row, new_total,
+			row += hist_browser__show_callchain_graph(browser, &child->rb_root,
+							    new_level, row, total,
+							    child->children_hit,
 							    print, arg, is_output_full);
 		}
 		if (is_output_full(browser, row))
@@ -910,6 +1043,45 @@ out:
 	return row - first_row;
 }
 
+static int hist_browser__show_callchain(struct hist_browser *browser,
+					struct hist_entry *entry, int level,
+					unsigned short row,
+					print_callchain_entry_fn print,
+					struct callchain_print_arg *arg,
+					check_output_full_fn is_output_full)
+{
+	u64 total = hists__total_period(entry->hists);
+	u64 parent_total;
+	int printed;
+
+	if (symbol_conf.cumulate_callchain)
+		parent_total = entry->stat_acc->period;
+	else
+		parent_total = entry->stat.period;
+
+	if (callchain_param.mode == CHAIN_FLAT) {
+		printed = hist_browser__show_callchain_flat(browser,
+						&entry->sorted_chain, row,
+						total, parent_total, print, arg,
+						is_output_full);
+	} else if (callchain_param.mode == CHAIN_FOLDED) {
+		printed = hist_browser__show_callchain_folded(browser,
+						&entry->sorted_chain, row,
+						total, parent_total, print, arg,
+						is_output_full);
+	} else {
+		printed = hist_browser__show_callchain_graph(browser,
+						&entry->sorted_chain, level, row,
+						total, parent_total, print, arg,
+						is_output_full);
+	}
+
+	if (arg->is_current_entry)
+		browser->he_selection = entry;
+
+	return printed;
+}
+
 struct hpp_arg {
 	struct ui_browser *b;
 	char folded_sign;
@@ -1006,7 +1178,6 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 				    struct hist_entry *entry,
 				    unsigned short row)
 {
-	char s[256];
 	int printed = 0;
 	int width = browser->b.width;
 	char folded_sign = ' ';
@@ -1031,16 +1202,18 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			.folded_sign	= folded_sign,
 			.current_entry	= current_entry,
 		};
-		struct perf_hpp hpp = {
-			.buf		= s,
-			.size		= sizeof(s),
-			.ptr		= &arg,
-		};
 		int column = 0;
 
 		hist_browser__gotorc(browser, row, 0);
 
-		perf_hpp__for_each_format(fmt) {
+		hists__for_each_format(browser->hists, fmt) {
+			char s[2048];
+			struct perf_hpp hpp = {
+				.buf	= s,
+				.size	= sizeof(s),
+				.ptr	= &arg,
+			};
+
 			if (perf_hpp__should_skip(fmt, entry->hists) ||
 			    column++ < browser->b.horiz_scroll)
 				continue;
@@ -1065,11 +1238,18 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			}
 
 			if (fmt->color) {
-				width -= fmt->color(fmt, &hpp, entry);
+				int ret = fmt->color(fmt, &hpp, entry);
+				hist_entry__snprintf_alignment(entry, &hpp, fmt, ret);
+				/*
+				 * fmt->color() already used ui_browser to
+				 * print the non alignment bits, skip it (+ret):
+				 */
+				ui_browser__printf(&browser->b, "%s", s + ret);
 			} else {
-				width -= fmt->entry(fmt, &hpp, entry);
+				hist_entry__snprintf_alignment(entry, &hpp, fmt, fmt->entry(fmt, &hpp, entry));
 				ui_browser__printf(&browser->b, "%s", s);
 			}
+			width -= hpp.buf - s;
 		}
 
 		/* The scroll bar isn't being used */
@@ -1084,43 +1264,246 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 		--row_offset;
 
 	if (folded_sign == '-' && row != browser->b.rows) {
-		u64 total = hists__total_period(entry->hists);
 		struct callchain_print_arg arg = {
 			.row_offset = row_offset,
 			.is_current_entry = current_entry,
 		};
 
-		if (callchain_param.mode == CHAIN_GRAPH_REL) {
-			if (symbol_conf.cumulate_callchain)
-				total = entry->stat_acc->period;
-			else
-				total = entry->stat.period;
-		}
-
-		if (callchain_param.mode == CHAIN_FLAT) {
-			printed += hist_browser__show_callchain_flat(browser,
-					&entry->sorted_chain, row, total,
-					hist_browser__show_callchain_entry, &arg,
-					hist_browser__check_output_full);
-		} else if (callchain_param.mode == CHAIN_FOLDED) {
-			printed += hist_browser__show_callchain_folded(browser,
-					&entry->sorted_chain, row, total,
+		printed += hist_browser__show_callchain(browser, entry, 1, row,
 					hist_browser__show_callchain_entry, &arg,
 					hist_browser__check_output_full);
+	}
+
+	return printed;
+}
+
+static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
+					      struct hist_entry *entry,
+					      unsigned short row,
+					      int level)
+{
+	int printed = 0;
+	int width = browser->b.width;
+	char folded_sign = ' ';
+	bool current_entry = ui_browser__is_current_entry(&browser->b, row);
+	off_t row_offset = entry->row_offset;
+	bool first = true;
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	struct hpp_arg arg = {
+		.b		= &browser->b,
+		.current_entry	= current_entry,
+	};
+	int column = 0;
+	int hierarchy_indent = (entry->hists->nr_hpp_node - 2) * HIERARCHY_INDENT;
+
+	if (current_entry) {
+		browser->he_selection = entry;
+		browser->selection = &entry->ms;
+	}
+
+	hist_entry__init_have_children(entry);
+	folded_sign = hist_entry__folded(entry);
+	arg.folded_sign = folded_sign;
+
+	if (entry->leaf && row_offset) {
+		row_offset--;
+		goto show_callchain;
+	}
+
+	hist_browser__gotorc(browser, row, 0);
+
+	if (current_entry && browser->b.navkeypressed)
+		ui_browser__set_color(&browser->b, HE_COLORSET_SELECTED);
+	else
+		ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL);
+
+	ui_browser__write_nstring(&browser->b, "", level * HIERARCHY_INDENT);
+	width -= level * HIERARCHY_INDENT;
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&entry->hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		char s[2048];
+		struct perf_hpp hpp = {
+			.buf		= s,
+			.size		= sizeof(s),
+			.ptr		= &arg,
+		};
+
+		if (perf_hpp__should_skip(fmt, entry->hists) ||
+		    column++ < browser->b.horiz_scroll)
+			continue;
+
+		if (current_entry && browser->b.navkeypressed) {
+			ui_browser__set_color(&browser->b,
+					      HE_COLORSET_SELECTED);
 		} else {
-			printed += hist_browser__show_callchain(browser,
-					&entry->sorted_chain, 1, row, total,
-					hist_browser__show_callchain_entry, &arg,
-					hist_browser__check_output_full);
+			ui_browser__set_color(&browser->b,
+					      HE_COLORSET_NORMAL);
+		}
+
+		if (first) {
+			ui_browser__printf(&browser->b, "%c", folded_sign);
+			width--;
+			first = false;
+		} else {
+			ui_browser__printf(&browser->b, "  ");
+			width -= 2;
+		}
+
+		if (fmt->color) {
+			int ret = fmt->color(fmt, &hpp, entry);
+			hist_entry__snprintf_alignment(entry, &hpp, fmt, ret);
+			/*
+			 * fmt->color() already used ui_browser to
+			 * print the non alignment bits, skip it (+ret):
+			 */
+			ui_browser__printf(&browser->b, "%s", s + ret);
+		} else {
+			int ret = fmt->entry(fmt, &hpp, entry);
+			hist_entry__snprintf_alignment(entry, &hpp, fmt, ret);
+			ui_browser__printf(&browser->b, "%s", s);
+		}
+		width -= hpp.buf - s;
+	}
+
+	ui_browser__write_nstring(&browser->b, "", hierarchy_indent);
+	width -= hierarchy_indent;
+
+	if (column >= browser->b.horiz_scroll) {
+		char s[2048];
+		struct perf_hpp hpp = {
+			.buf		= s,
+			.size		= sizeof(s),
+			.ptr		= &arg,
+		};
+
+		if (current_entry && browser->b.navkeypressed) {
+			ui_browser__set_color(&browser->b,
+					      HE_COLORSET_SELECTED);
+		} else {
+			ui_browser__set_color(&browser->b,
+					      HE_COLORSET_NORMAL);
 		}
 
-		if (arg.is_current_entry)
-			browser->he_selection = entry;
+		perf_hpp_list__for_each_format(entry->hpp_list, fmt) {
+			ui_browser__write_nstring(&browser->b, "", 2);
+			width -= 2;
+
+			/*
+			 * No need to call hist_entry__snprintf_alignment()
+			 * since this fmt is always the last column in the
+			 * hierarchy mode.
+			 */
+			if (fmt->color) {
+				width -= fmt->color(fmt, &hpp, entry);
+			} else {
+				int i = 0;
+
+				width -= fmt->entry(fmt, &hpp, entry);
+				ui_browser__printf(&browser->b, "%s", ltrim(s));
+
+				while (isspace(s[i++]))
+					width++;
+			}
+		}
+	}
+
+	/* The scroll bar isn't being used */
+	if (!browser->b.navkeypressed)
+		width += 1;
+
+	ui_browser__write_nstring(&browser->b, "", width);
+
+	++row;
+	++printed;
+
+show_callchain:
+	if (entry->leaf && folded_sign == '-' && row != browser->b.rows) {
+		struct callchain_print_arg carg = {
+			.row_offset = row_offset,
+		};
+
+		printed += hist_browser__show_callchain(browser, entry,
+					level + 1, row,
+					hist_browser__show_callchain_entry, &carg,
+					hist_browser__check_output_full);
 	}
 
 	return printed;
 }
 
+static int hist_browser__show_no_entry(struct hist_browser *browser,
+				       unsigned short row, int level)
+{
+	int width = browser->b.width;
+	bool current_entry = ui_browser__is_current_entry(&browser->b, row);
+	bool first = true;
+	int column = 0;
+	int ret;
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	int indent = browser->hists->nr_hpp_node - 2;
+
+	if (current_entry) {
+		browser->he_selection = NULL;
+		browser->selection = NULL;
+	}
+
+	hist_browser__gotorc(browser, row, 0);
+
+	if (current_entry && browser->b.navkeypressed)
+		ui_browser__set_color(&browser->b, HE_COLORSET_SELECTED);
+	else
+		ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL);
+
+	ui_browser__write_nstring(&browser->b, "", level * HIERARCHY_INDENT);
+	width -= level * HIERARCHY_INDENT;
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&browser->hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		if (perf_hpp__should_skip(fmt, browser->hists) ||
+		    column++ < browser->b.horiz_scroll)
+			continue;
+
+		ret = fmt->width(fmt, NULL, hists_to_evsel(browser->hists));
+
+		if (first) {
+			/* for folded sign */
+			first = false;
+			ret++;
+		} else {
+			/* space between columns */
+			ret += 2;
+		}
+
+		ui_browser__write_nstring(&browser->b, "", ret);
+		width -= ret;
+	}
+
+	ui_browser__write_nstring(&browser->b, "", indent * HIERARCHY_INDENT);
+	width -= indent * HIERARCHY_INDENT;
+
+	if (column >= browser->b.horiz_scroll) {
+		char buf[32];
+
+		ret = snprintf(buf, sizeof(buf), "no entry >= %.2f%%", browser->min_pcnt);
+		ui_browser__printf(&browser->b, "  %s", buf);
+		width -= ret + 2;
+	}
+
+	/* The scroll bar isn't being used */
+	if (!browser->b.navkeypressed)
+		width += 1;
+
+	ui_browser__write_nstring(&browser->b, "", width);
+	return 1;
+}
+
 static int advance_hpp_check(struct perf_hpp *hpp, int inc)
 {
 	advance_hpp(hpp, inc);
@@ -1144,7 +1527,7 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *
 			return ret;
 	}
 
-	perf_hpp__for_each_format(fmt) {
+	hists__for_each_format(browser->hists, fmt) {
 		if (perf_hpp__should_skip(fmt, hists)  || column++ < browser->b.horiz_scroll)
 			continue;
 
@@ -1160,11 +1543,96 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *
 	return ret;
 }
 
+static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *browser, char *buf, size_t size)
+{
+	struct hists *hists = browser->hists;
+	struct perf_hpp dummy_hpp = {
+		.buf    = buf,
+		.size   = size,
+	};
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	size_t ret = 0;
+	int column = 0;
+	int indent = hists->nr_hpp_node - 2;
+	bool first_node, first_col;
+
+	ret = scnprintf(buf, size, " ");
+	if (advance_hpp_check(&dummy_hpp, ret))
+		return ret;
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		if (column++ < browser->b.horiz_scroll)
+			continue;
+
+		ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+		if (advance_hpp_check(&dummy_hpp, ret))
+			break;
+
+		ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "  ");
+		if (advance_hpp_check(&dummy_hpp, ret))
+			break;
+	}
+
+	ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "%*s",
+			indent * HIERARCHY_INDENT, "");
+	if (advance_hpp_check(&dummy_hpp, ret))
+		return ret;
+
+	first_node = true;
+	list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+		if (!first_node) {
+			ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, " / ");
+			if (advance_hpp_check(&dummy_hpp, ret))
+				break;
+		}
+		first_node = false;
+
+		first_col = true;
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+			char *start;
+
+			if (perf_hpp__should_skip(fmt, hists))
+				continue;
+
+			if (!first_col) {
+				ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "+");
+				if (advance_hpp_check(&dummy_hpp, ret))
+					break;
+			}
+			first_col = false;
+
+			ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+			dummy_hpp.buf[ret] = '\0';
+			rtrim(dummy_hpp.buf);
+
+			start = ltrim(dummy_hpp.buf);
+			ret = strlen(start);
+
+			if (start != dummy_hpp.buf)
+				memmove(dummy_hpp.buf, start, ret + 1);
+
+			if (advance_hpp_check(&dummy_hpp, ret))
+				break;
+		}
+	}
+
+	return ret;
+}
+
 static void hist_browser__show_headers(struct hist_browser *browser)
 {
 	char headers[1024];
 
-	hists_browser__scnprintf_headers(browser, headers, sizeof(headers));
+	if (symbol_conf.report_hierarchy)
+		hists_browser__scnprintf_hierarchy_headers(browser, headers,
+							   sizeof(headers));
+	else
+		hists_browser__scnprintf_headers(browser, headers,
+						 sizeof(headers));
 	ui_browser__gotorc(&browser->b, 0, 0);
 	ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
 	ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
@@ -1196,18 +1664,34 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
 	hb->he_selection = NULL;
 	hb->selection = NULL;
 
-	for (nd = browser->top; nd; nd = rb_next(nd)) {
+	for (nd = browser->top; nd; nd = rb_hierarchy_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 		float percent;
 
-		if (h->filtered)
+		if (h->filtered) {
+			/* let it move to sibling */
+			h->unfolded = false;
 			continue;
+		}
 
 		percent = hist_entry__get_percent_limit(h);
 		if (percent < hb->min_pcnt)
 			continue;
 
-		row += hist_browser__show_entry(hb, h, row);
+		if (symbol_conf.report_hierarchy) {
+			row += hist_browser__show_hierarchy_entry(hb, h, row,
+								  h->depth);
+			if (row == browser->rows)
+				break;
+
+			if (h->has_no_entry) {
+				hist_browser__show_no_entry(hb, row, h->depth + 1);
+				row++;
+			}
+		} else {
+			row += hist_browser__show_entry(hb, h, row);
+		}
+
 		if (row == browser->rows)
 			break;
 	}
@@ -1225,7 +1709,14 @@ static struct rb_node *hists__filter_entries(struct rb_node *nd,
 		if (!h->filtered && percent >= min_pcnt)
 			return nd;
 
-		nd = rb_next(nd);
+		/*
+		 * If it's filtered, its all children also were filtered.
+		 * So move to sibling node.
+		 */
+		if (rb_next(nd))
+			nd = rb_next(nd);
+		else
+			nd = rb_hierarchy_next(nd);
 	}
 
 	return NULL;
@@ -1241,7 +1732,7 @@ static struct rb_node *hists__filter_prev_entries(struct rb_node *nd,
 		if (!h->filtered && percent >= min_pcnt)
 			return nd;
 
-		nd = rb_prev(nd);
+		nd = rb_hierarchy_prev(nd);
 	}
 
 	return NULL;
@@ -1271,8 +1762,8 @@ static void ui_browser__hists_seek(struct ui_browser *browser,
 		nd = browser->top;
 		goto do_offset;
 	case SEEK_END:
-		nd = hists__filter_prev_entries(rb_last(browser->entries),
-						hb->min_pcnt);
+		nd = rb_hierarchy_last(rb_last(browser->entries));
+		nd = hists__filter_prev_entries(nd, hb->min_pcnt);
 		first = false;
 		break;
 	default:
@@ -1306,7 +1797,7 @@ do_offset:
 	if (offset > 0) {
 		do {
 			h = rb_entry(nd, struct hist_entry, rb_node);
-			if (h->unfolded) {
+			if (h->unfolded && h->leaf) {
 				u16 remaining = h->nr_rows - h->row_offset;
 				if (offset > remaining) {
 					offset -= remaining;
@@ -1318,7 +1809,8 @@ do_offset:
 					break;
 				}
 			}
-			nd = hists__filter_entries(rb_next(nd), hb->min_pcnt);
+			nd = hists__filter_entries(rb_hierarchy_next(nd),
+						   hb->min_pcnt);
 			if (nd == NULL)
 				break;
 			--offset;
@@ -1327,7 +1819,7 @@ do_offset:
 	} else if (offset < 0) {
 		while (1) {
 			h = rb_entry(nd, struct hist_entry, rb_node);
-			if (h->unfolded) {
+			if (h->unfolded && h->leaf) {
 				if (first) {
 					if (-offset > h->row_offset) {
 						offset += h->row_offset;
@@ -1351,7 +1843,7 @@ do_offset:
 				}
 			}
 
-			nd = hists__filter_prev_entries(rb_prev(nd),
+			nd = hists__filter_prev_entries(rb_hierarchy_prev(nd),
 							hb->min_pcnt);
 			if (nd == NULL)
 				break;
@@ -1364,7 +1856,7 @@ do_offset:
 				 * row_offset at its last entry.
 				 */
 				h = rb_entry(nd, struct hist_entry, rb_node);
-				if (h->unfolded)
+				if (h->unfolded && h->leaf)
 					h->row_offset = h->nr_rows;
 				break;
 			}
@@ -1378,17 +1870,14 @@ do_offset:
 }
 
 static int hist_browser__fprintf_callchain(struct hist_browser *browser,
-					   struct hist_entry *he, FILE *fp)
+					   struct hist_entry *he, FILE *fp,
+					   int level)
 {
-	u64 total = hists__total_period(he->hists);
 	struct callchain_print_arg arg  = {
 		.fp = fp,
 	};
 
-	if (symbol_conf.cumulate_callchain)
-		total = he->stat_acc->period;
-
-	hist_browser__show_callchain(browser, &he->sorted_chain, 1, 0, total,
+	hist_browser__show_callchain(browser, he, level, 0,
 				     hist_browser__fprintf_callchain_entry, &arg,
 				     hist_browser__check_dump_full);
 	return arg.printed;
@@ -1414,7 +1903,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser,
 	if (symbol_conf.use_callchain)
 		printed += fprintf(fp, "%c ", folded_sign);
 
-	perf_hpp__for_each_format(fmt) {
+	hists__for_each_format(browser->hists, fmt) {
 		if (perf_hpp__should_skip(fmt, he->hists))
 			continue;
 
@@ -1425,12 +1914,71 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser,
 			first = false;
 
 		ret = fmt->entry(fmt, &hpp, he);
+		ret = hist_entry__snprintf_alignment(he, &hpp, fmt, ret);
 		advance_hpp(&hpp, ret);
 	}
-	printed += fprintf(fp, "%s\n", rtrim(s));
+	printed += fprintf(fp, "%s\n", s);
 
 	if (folded_sign == '-')
-		printed += hist_browser__fprintf_callchain(browser, he, fp);
+		printed += hist_browser__fprintf_callchain(browser, he, fp, 1);
+
+	return printed;
+}
+
+
+static int hist_browser__fprintf_hierarchy_entry(struct hist_browser *browser,
+						 struct hist_entry *he,
+						 FILE *fp, int level)
+{
+	char s[8192];
+	int printed = 0;
+	char folded_sign = ' ';
+	struct perf_hpp hpp = {
+		.buf = s,
+		.size = sizeof(s),
+	};
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	bool first = true;
+	int ret;
+	int hierarchy_indent = (he->hists->nr_hpp_node - 2) * HIERARCHY_INDENT;
+
+	printed = fprintf(fp, "%*s", level * HIERARCHY_INDENT, "");
+
+	folded_sign = hist_entry__folded(he);
+	printed += fprintf(fp, "%c", folded_sign);
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&he->hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		if (!first) {
+			ret = scnprintf(hpp.buf, hpp.size, "  ");
+			advance_hpp(&hpp, ret);
+		} else
+			first = false;
+
+		ret = fmt->entry(fmt, &hpp, he);
+		advance_hpp(&hpp, ret);
+	}
+
+	ret = scnprintf(hpp.buf, hpp.size, "%*s", hierarchy_indent, "");
+	advance_hpp(&hpp, ret);
+
+	perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+		ret = scnprintf(hpp.buf, hpp.size, "  ");
+		advance_hpp(&hpp, ret);
+
+		ret = fmt->entry(fmt, &hpp, he);
+		advance_hpp(&hpp, ret);
+	}
+
+	printed += fprintf(fp, "%s\n", rtrim(s));
+
+	if (he->leaf && folded_sign == '-') {
+		printed += hist_browser__fprintf_callchain(browser, he, fp,
+							   he->depth + 1);
+	}
 
 	return printed;
 }
@@ -1444,8 +1992,16 @@ static int hist_browser__fprintf(struct hist_browser *browser, FILE *fp)
 	while (nd) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
-		printed += hist_browser__fprintf_entry(browser, h, fp);
-		nd = hists__filter_entries(rb_next(nd), browser->min_pcnt);
+		if (symbol_conf.report_hierarchy) {
+			printed += hist_browser__fprintf_hierarchy_entry(browser,
+									 h, fp,
+									 h->depth);
+		} else {
+			printed += hist_browser__fprintf_entry(browser, h, fp);
+		}
+
+		nd = hists__filter_entries(rb_hierarchy_next(nd),
+					   browser->min_pcnt);
 	}
 
 	return printed;
@@ -1580,11 +2136,18 @@ static int hists__browser_title(struct hists *hists,
 	if (hists->uid_filter_str)
 		printed += snprintf(bf + printed, size - printed,
 				    ", UID: %s", hists->uid_filter_str);
-	if (thread)
-		printed += scnprintf(bf + printed, size - printed,
+	if (thread) {
+		if (sort__has_thread) {
+			printed += scnprintf(bf + printed, size - printed,
 				    ", Thread: %s(%d)",
 				     (thread->comm_set ? thread__comm_str(thread) : ""),
 				    thread->tid);
+		} else {
+			printed += scnprintf(bf + printed, size - printed,
+				    ", Thread: %s",
+				     (thread->comm_set ? thread__comm_str(thread) : ""));
+		}
+	}
 	if (dso)
 		printed += scnprintf(bf + printed, size - printed,
 				    ", DSO: %s", dso->short_name);
@@ -1759,15 +2322,24 @@ do_zoom_thread(struct hist_browser *browser, struct popup_action *act)
 {
 	struct thread *thread = act->thread;
 
+	if ((!sort__has_thread && !sort__has_comm) || thread == NULL)
+		return 0;
+
 	if (browser->hists->thread_filter) {
 		pstack__remove(browser->pstack, &browser->hists->thread_filter);
 		perf_hpp__set_elide(HISTC_THREAD, false);
 		thread__zput(browser->hists->thread_filter);
 		ui_helpline__pop();
 	} else {
-		ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s(%d) thread\"",
-				   thread->comm_set ? thread__comm_str(thread) : "",
-				   thread->tid);
+		if (sort__has_thread) {
+			ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s(%d) thread\"",
+					   thread->comm_set ? thread__comm_str(thread) : "",
+					   thread->tid);
+		} else {
+			ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s thread\"",
+					   thread->comm_set ? thread__comm_str(thread) : "");
+		}
+
 		browser->hists->thread_filter = thread__get(thread);
 		perf_hpp__set_elide(HISTC_THREAD, false);
 		pstack__push(browser->pstack, &browser->hists->thread_filter);
@@ -1782,13 +2354,22 @@ static int
 add_thread_opt(struct hist_browser *browser, struct popup_action *act,
 	       char **optstr, struct thread *thread)
 {
-	if (thread == NULL)
+	int ret;
+
+	if ((!sort__has_thread && !sort__has_comm) || thread == NULL)
 		return 0;
 
-	if (asprintf(optstr, "Zoom %s %s(%d) thread",
-		     browser->hists->thread_filter ? "out of" : "into",
-		     thread->comm_set ? thread__comm_str(thread) : "",
-		     thread->tid) < 0)
+	if (sort__has_thread) {
+		ret = asprintf(optstr, "Zoom %s %s(%d) thread",
+			       browser->hists->thread_filter ? "out of" : "into",
+			       thread->comm_set ? thread__comm_str(thread) : "",
+			       thread->tid);
+	} else {
+		ret = asprintf(optstr, "Zoom %s %s thread",
+			       browser->hists->thread_filter ? "out of" : "into",
+			       thread->comm_set ? thread__comm_str(thread) : "");
+	}
+	if (ret < 0)
 		return 0;
 
 	act->thread = thread;
@@ -1801,6 +2382,9 @@ do_zoom_dso(struct hist_browser *browser, struct popup_action *act)
 {
 	struct map *map = act->ms.map;
 
+	if (!sort__has_dso || map == NULL)
+		return 0;
+
 	if (browser->hists->dso_filter) {
 		pstack__remove(browser->pstack, &browser->hists->dso_filter);
 		perf_hpp__set_elide(HISTC_DSO, false);
@@ -1825,7 +2409,7 @@ static int
 add_dso_opt(struct hist_browser *browser, struct popup_action *act,
 	    char **optstr, struct map *map)
 {
-	if (map == NULL)
+	if (!sort__has_dso || map == NULL)
 		return 0;
 
 	if (asprintf(optstr, "Zoom %s %s DSO",
@@ -1850,7 +2434,7 @@ static int
 add_map_opt(struct hist_browser *browser __maybe_unused,
 	    struct popup_action *act, char **optstr, struct map *map)
 {
-	if (map == NULL)
+	if (!sort__has_dso || map == NULL)
 		return 0;
 
 	if (asprintf(optstr, "Browse map details") < 0)
@@ -1952,6 +2536,9 @@ add_exit_opt(struct hist_browser *browser __maybe_unused,
 static int
 do_zoom_socket(struct hist_browser *browser, struct popup_action *act)
 {
+	if (!sort__has_socket || act->socket < 0)
+		return 0;
+
 	if (browser->hists->socket_filter > -1) {
 		pstack__remove(browser->pstack, &browser->hists->socket_filter);
 		browser->hists->socket_filter = -1;
@@ -1971,7 +2558,7 @@ static int
 add_socket_opt(struct hist_browser *browser, struct popup_action *act,
 	       char **optstr, int socket_id)
 {
-	if (socket_id < 0)
+	if (!sort__has_socket || socket_id < 0)
 		return 0;
 
 	if (asprintf(optstr, "Zoom %s Processor Socket %d",
@@ -1989,17 +2576,60 @@ static void hist_browser__update_nr_entries(struct hist_browser *hb)
 	u64 nr_entries = 0;
 	struct rb_node *nd = rb_first(&hb->hists->entries);
 
-	if (hb->min_pcnt == 0) {
+	if (hb->min_pcnt == 0 && !symbol_conf.report_hierarchy) {
 		hb->nr_non_filtered_entries = hb->hists->nr_non_filtered_entries;
 		return;
 	}
 
 	while ((nd = hists__filter_entries(nd, hb->min_pcnt)) != NULL) {
 		nr_entries++;
-		nd = rb_next(nd);
+		nd = rb_hierarchy_next(nd);
 	}
 
 	hb->nr_non_filtered_entries = nr_entries;
+	hb->nr_hierarchy_entries = nr_entries;
+}
+
+static void hist_browser__update_percent_limit(struct hist_browser *hb,
+					       double percent)
+{
+	struct hist_entry *he;
+	struct rb_node *nd = rb_first(&hb->hists->entries);
+	u64 total = hists__total_period(hb->hists);
+	u64 min_callchain_hits = total * (percent / 100);
+
+	hb->min_pcnt = callchain_param.min_percent = percent;
+
+	while ((nd = hists__filter_entries(nd, hb->min_pcnt)) != NULL) {
+		he = rb_entry(nd, struct hist_entry, rb_node);
+
+		if (he->has_no_entry) {
+			he->has_no_entry = false;
+			he->nr_rows = 0;
+		}
+
+		if (!he->leaf || !symbol_conf.use_callchain)
+			goto next;
+
+		if (callchain_param.mode == CHAIN_GRAPH_REL) {
+			total = he->stat.period;
+
+			if (symbol_conf.cumulate_callchain)
+				total = he->stat_acc->period;
+
+			min_callchain_hits = total * (percent / 100);
+		}
+
+		callchain_param.sort(&he->sorted_chain, he->callchain,
+				     min_callchain_hits, &callchain_param);
+
+next:
+		nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD);
+
+		/* force to re-evaluate folding state of callchains */
+		he->init_have_children = false;
+		hist_entry__set_folding(he, hb, false);
+	}
 }
 
 static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
@@ -2037,6 +2667,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	"E             Expand all callchains\n"				\
 	"F             Toggle percentage of filtered entries\n"		\
 	"H             Display column headers\n"			\
+	"L             Change percent limit\n"				\
 	"m             Display context menu\n"				\
 	"S             Zoom into current Processor Socket\n"		\
 
@@ -2077,7 +2708,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	memset(options, 0, sizeof(options));
 	memset(actions, 0, sizeof(actions));
 
-	perf_hpp__for_each_format(fmt) {
+	hists__for_each_format(browser->hists, fmt) {
 		perf_hpp__reset_width(fmt, hists);
 		/*
 		 * This is done just once, and activates the horizontal scrolling
@@ -2192,6 +2823,24 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 				top->zero = !top->zero;
 			}
 			continue;
+		case 'L':
+			if (ui_browser__input_window("Percent Limit",
+					"Please enter the value you want to hide entries under that percent.",
+					buf, "ENTER: OK, ESC: Cancel",
+					delay_secs * 2) == K_ENTER) {
+				char *end;
+				double new_percent = strtod(buf, &end);
+
+				if (new_percent < 0 || new_percent > 100) {
+					ui_browser__warning(&browser->b, delay_secs * 2,
+						"Invalid percent: %.2f", new_percent);
+					continue;
+				}
+
+				hist_browser__update_percent_limit(browser, new_percent);
+				hist_browser__reset(browser);
+			}
+			continue;
 		case K_F1:
 		case 'h':
 		case '?':
@@ -2263,10 +2912,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			continue;
 		}
 
-		if (!sort__has_sym)
-			goto add_exit_option;
-
-		if (browser->selection == NULL)
+		if (!sort__has_sym || browser->selection == NULL)
 			goto skip_annotation;
 
 		if (sort__mode == SORT_MODE__BRANCH) {
@@ -2306,11 +2952,16 @@ skip_annotation:
 					     &options[nr_options],
 					     socked_id);
 		/* perf script support */
+		if (!is_report_browser(hbt))
+			goto skip_scripting;
+
 		if (browser->he_selection) {
-			nr_options += add_script_opt(browser,
-						     &actions[nr_options],
-						     &options[nr_options],
-						     thread, NULL);
+			if (sort__has_thread && thread) {
+				nr_options += add_script_opt(browser,
+							     &actions[nr_options],
+							     &options[nr_options],
+							     thread, NULL);
+			}
 			/*
 			 * Note that browser->selection != NULL
 			 * when browser->he_selection is not NULL,
@@ -2320,16 +2971,18 @@ skip_annotation:
 			 *
 			 * See hist_browser__show_entry.
 			 */
-			nr_options += add_script_opt(browser,
-						     &actions[nr_options],
-						     &options[nr_options],
-						     NULL, browser->selection->sym);
+			if (sort__has_sym && browser->selection->sym) {
+				nr_options += add_script_opt(browser,
+							     &actions[nr_options],
+							     &options[nr_options],
+							     NULL, browser->selection->sym);
+			}
 		}
 		nr_options += add_script_opt(browser, &actions[nr_options],
 					     &options[nr_options], NULL, NULL);
 		nr_options += add_switch_opt(browser, &actions[nr_options],
 					     &options[nr_options]);
-add_exit_option:
+skip_scripting:
 		nr_options += add_exit_opt(browser, &actions[nr_options],
 					   &options[nr_options]);
 
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 0f8dcfdfb10f..bd9bf7e343b1 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -306,7 +306,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 
 	nr_cols = 0;
 
-	perf_hpp__for_each_format(fmt)
+	hists__for_each_format(hists, fmt)
 		col_types[nr_cols++] = G_TYPE_STRING;
 
 	store = gtk_tree_store_newv(nr_cols, col_types);
@@ -317,7 +317,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 
 	col_idx = 0;
 
-	perf_hpp__for_each_format(fmt) {
+	hists__for_each_format(hists, fmt) {
 		if (perf_hpp__should_skip(fmt, hists))
 			continue;
 
@@ -367,7 +367,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 
 		col_idx = 0;
 
-		perf_hpp__for_each_format(fmt) {
+		hists__for_each_format(hists, fmt) {
 			if (perf_hpp__should_skip(fmt, h->hists))
 				continue;
 
@@ -396,6 +396,194 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 	gtk_container_add(GTK_CONTAINER(window), view);
 }
 
+static void perf_gtk__add_hierarchy_entries(struct hists *hists,
+					    struct rb_root *root,
+					    GtkTreeStore *store,
+					    GtkTreeIter *parent,
+					    struct perf_hpp *hpp,
+					    float min_pcnt)
+{
+	int col_idx = 0;
+	struct rb_node *node;
+	struct hist_entry *he;
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	u64 total = hists__total_period(hists);
+	int size;
+
+	for (node = rb_first(root); node; node = rb_next(node)) {
+		GtkTreeIter iter;
+		float percent;
+		char *bf;
+
+		he = rb_entry(node, struct hist_entry, rb_node);
+		if (he->filtered)
+			continue;
+
+		percent = hist_entry__get_percent_limit(he);
+		if (percent < min_pcnt)
+			continue;
+
+		gtk_tree_store_append(store, &iter, parent);
+
+		col_idx = 0;
+
+		/* the first hpp_list_node is for overhead columns */
+		fmt_node = list_first_entry(&hists->hpp_formats,
+					    struct perf_hpp_list_node, list);
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+			if (fmt->color)
+				fmt->color(fmt, hpp, he);
+			else
+				fmt->entry(fmt, hpp, he);
+
+			gtk_tree_store_set(store, &iter, col_idx++, hpp->buf, -1);
+		}
+
+		bf = hpp->buf;
+		size = hpp->size;
+		perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+			int ret;
+
+			if (fmt->color)
+				ret = fmt->color(fmt, hpp, he);
+			else
+				ret = fmt->entry(fmt, hpp, he);
+
+			snprintf(hpp->buf + ret, hpp->size - ret, "  ");
+			advance_hpp(hpp, ret + 2);
+		}
+
+		gtk_tree_store_set(store, &iter, col_idx, ltrim(rtrim(bf)), -1);
+
+		if (!he->leaf) {
+			hpp->buf = bf;
+			hpp->size = size;
+
+			perf_gtk__add_hierarchy_entries(hists, &he->hroot_out,
+							store, &iter, hpp,
+							min_pcnt);
+
+			if (!hist_entry__has_hierarchy_children(he, min_pcnt)) {
+				char buf[32];
+				GtkTreeIter child;
+
+				snprintf(buf, sizeof(buf), "no entry >= %.2f%%",
+					 min_pcnt);
+
+				gtk_tree_store_append(store, &child, &iter);
+				gtk_tree_store_set(store, &child, col_idx, buf, -1);
+			}
+		}
+
+		if (symbol_conf.use_callchain && he->leaf) {
+			if (callchain_param.mode == CHAIN_GRAPH_REL)
+				total = symbol_conf.cumulate_callchain ?
+					he->stat_acc->period : he->stat.period;
+
+			perf_gtk__add_callchain(&he->sorted_chain, store, &iter,
+						col_idx, total);
+		}
+	}
+
+}
+
+static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists,
+				     float min_pcnt)
+{
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	GType col_types[MAX_COLUMNS];
+	GtkCellRenderer *renderer;
+	GtkTreeStore *store;
+	GtkWidget *view;
+	int col_idx;
+	int nr_cols = 0;
+	char s[512];
+	char buf[512];
+	bool first_node, first_col;
+	struct perf_hpp hpp = {
+		.buf		= s,
+		.size		= sizeof(s),
+	};
+
+	hists__for_each_format(hists, fmt) {
+		if (perf_hpp__is_sort_entry(fmt) ||
+		    perf_hpp__is_dynamic_entry(fmt))
+			break;
+
+		col_types[nr_cols++] = G_TYPE_STRING;
+	}
+	col_types[nr_cols++] = G_TYPE_STRING;
+
+	store = gtk_tree_store_newv(nr_cols, col_types);
+	view = gtk_tree_view_new();
+	renderer = gtk_cell_renderer_text_new();
+
+	col_idx = 0;
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+							    -1, fmt->name,
+							    renderer, "markup",
+							    col_idx++, NULL);
+	}
+
+	/* construct merged column header since sort keys share single column */
+	buf[0] = '\0';
+	first_node = true;
+	list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+		if (!first_node)
+			strcat(buf, " / ");
+		first_node = false;
+
+		first_col = true;
+		perf_hpp_list__for_each_format(&fmt_node->hpp ,fmt) {
+			if (perf_hpp__should_skip(fmt, hists))
+				continue;
+
+			if (!first_col)
+				strcat(buf, "+");
+			first_col = false;
+
+			fmt->header(fmt, &hpp, hists_to_evsel(hists));
+			strcat(buf, ltrim(rtrim(hpp.buf)));
+		}
+	}
+
+	gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+						    -1, buf,
+						    renderer, "markup",
+						    col_idx++, NULL);
+
+	for (col_idx = 0; col_idx < nr_cols; col_idx++) {
+		GtkTreeViewColumn *column;
+
+		column = gtk_tree_view_get_column(GTK_TREE_VIEW(view), col_idx);
+		gtk_tree_view_column_set_resizable(column, TRUE);
+
+		if (col_idx == 0) {
+			gtk_tree_view_set_expander_column(GTK_TREE_VIEW(view),
+							  column);
+		}
+	}
+
+	gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store));
+	g_object_unref(GTK_TREE_MODEL(store));
+
+	perf_gtk__add_hierarchy_entries(hists, &hists->entries, store,
+					NULL, &hpp, min_pcnt);
+
+	gtk_tree_view_set_rules_hint(GTK_TREE_VIEW(view), TRUE);
+
+	g_signal_connect(view, "row-activated",
+			 G_CALLBACK(on_row_activated), NULL);
+	gtk_container_add(GTK_CONTAINER(window), view);
+}
+
 int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 				  const char *help,
 				  struct hist_browser_timer *hbt __maybe_unused,
@@ -463,7 +651,10 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 							GTK_POLICY_AUTOMATIC,
 							GTK_POLICY_AUTOMATIC);
 
-		perf_gtk__show_hists(scrolled_window, hists, min_pcnt);
+		if (symbol_conf.report_hierarchy)
+			perf_gtk__show_hierarchy(scrolled_window, hists, min_pcnt);
+		else
+			perf_gtk__show_hists(scrolled_window, hists, min_pcnt);
 
 		tab_label = gtk_label_new(evname);
 
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index bf2a66e254ea..3baeaa6e71b5 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -5,6 +5,7 @@
 #include "../util/util.h"
 #include "../util/sort.h"
 #include "../util/evsel.h"
+#include "../util/evlist.h"
 
 /* hist period print (hpp) functions */
 
@@ -371,7 +372,20 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 	return 0;
 }
 
-#define HPP__COLOR_PRINT_FNS(_name, _fn)		\
+static bool perf_hpp__is_hpp_entry(struct perf_hpp_fmt *a)
+{
+	return a->header == hpp__header_fn;
+}
+
+static bool hpp__equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+	if (!perf_hpp__is_hpp_entry(a) || !perf_hpp__is_hpp_entry(b))
+		return false;
+
+	return a->idx == b->idx;
+}
+
+#define HPP__COLOR_PRINT_FNS(_name, _fn, _idx)		\
 	{						\
 		.name   = _name,			\
 		.header	= hpp__header_fn,		\
@@ -381,9 +395,11 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 		.cmp	= hpp__nop_cmp,			\
 		.collapse = hpp__nop_cmp,		\
 		.sort	= hpp__sort_ ## _fn,		\
+		.idx	= PERF_HPP__ ## _idx,		\
+		.equal	= hpp__equal,			\
 	}
 
-#define HPP__COLOR_ACC_PRINT_FNS(_name, _fn)		\
+#define HPP__COLOR_ACC_PRINT_FNS(_name, _fn, _idx)	\
 	{						\
 		.name   = _name,			\
 		.header	= hpp__header_fn,		\
@@ -393,9 +409,11 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 		.cmp	= hpp__nop_cmp,			\
 		.collapse = hpp__nop_cmp,		\
 		.sort	= hpp__sort_ ## _fn,		\
+		.idx	= PERF_HPP__ ## _idx,		\
+		.equal	= hpp__equal,			\
 	}
 
-#define HPP__PRINT_FNS(_name, _fn)			\
+#define HPP__PRINT_FNS(_name, _fn, _idx)		\
 	{						\
 		.name   = _name,			\
 		.header	= hpp__header_fn,		\
@@ -404,22 +422,25 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 		.cmp	= hpp__nop_cmp,			\
 		.collapse = hpp__nop_cmp,		\
 		.sort	= hpp__sort_ ## _fn,		\
+		.idx	= PERF_HPP__ ## _idx,		\
+		.equal	= hpp__equal,			\
 	}
 
 struct perf_hpp_fmt perf_hpp__format[] = {
-	HPP__COLOR_PRINT_FNS("Overhead", overhead),
-	HPP__COLOR_PRINT_FNS("sys", overhead_sys),
-	HPP__COLOR_PRINT_FNS("usr", overhead_us),
-	HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys),
-	HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us),
-	HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc),
-	HPP__PRINT_FNS("Samples", samples),
-	HPP__PRINT_FNS("Period", period)
+	HPP__COLOR_PRINT_FNS("Overhead", overhead, OVERHEAD),
+	HPP__COLOR_PRINT_FNS("sys", overhead_sys, OVERHEAD_SYS),
+	HPP__COLOR_PRINT_FNS("usr", overhead_us, OVERHEAD_US),
+	HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys, OVERHEAD_GUEST_SYS),
+	HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us, OVERHEAD_GUEST_US),
+	HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc, OVERHEAD_ACC),
+	HPP__PRINT_FNS("Samples", samples, SAMPLES),
+	HPP__PRINT_FNS("Period", period, PERIOD)
 };
 
-LIST_HEAD(perf_hpp__list);
-LIST_HEAD(perf_hpp__sort_list);
-
+struct perf_hpp_list perf_hpp_list = {
+	.fields	= LIST_HEAD_INIT(perf_hpp_list.fields),
+	.sorts	= LIST_HEAD_INIT(perf_hpp_list.sorts),
+};
 
 #undef HPP__COLOR_PRINT_FNS
 #undef HPP__COLOR_ACC_PRINT_FNS
@@ -485,63 +506,60 @@ void perf_hpp__init(void)
 		hpp_dimension__add_output(PERF_HPP__PERIOD);
 }
 
-void perf_hpp__column_register(struct perf_hpp_fmt *format)
+void perf_hpp_list__column_register(struct perf_hpp_list *list,
+				    struct perf_hpp_fmt *format)
 {
-	list_add_tail(&format->list, &perf_hpp__list);
+	list_add_tail(&format->list, &list->fields);
 }
 
-void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
+void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
+					struct perf_hpp_fmt *format)
 {
-	list_del(&format->list);
+	list_add_tail(&format->sort_list, &list->sorts);
 }
 
-void perf_hpp__register_sort_field(struct perf_hpp_fmt *format)
-{
-	list_add_tail(&format->sort_list, &perf_hpp__sort_list);
-}
-
-void perf_hpp__column_enable(unsigned col)
-{
-	BUG_ON(col >= PERF_HPP__MAX_INDEX);
-	perf_hpp__column_register(&perf_hpp__format[col]);
-}
-
-void perf_hpp__column_disable(unsigned col)
+void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
-	BUG_ON(col >= PERF_HPP__MAX_INDEX);
-	perf_hpp__column_unregister(&perf_hpp__format[col]);
+	list_del(&format->list);
 }
 
 void perf_hpp__cancel_cumulate(void)
 {
+	struct perf_hpp_fmt *fmt, *acc, *ovh, *tmp;
+
 	if (is_strict_order(field_order))
 		return;
 
-	perf_hpp__column_disable(PERF_HPP__OVERHEAD_ACC);
-	perf_hpp__format[PERF_HPP__OVERHEAD].name = "Overhead";
+	ovh = &perf_hpp__format[PERF_HPP__OVERHEAD];
+	acc = &perf_hpp__format[PERF_HPP__OVERHEAD_ACC];
+
+	perf_hpp_list__for_each_format_safe(&perf_hpp_list, fmt, tmp) {
+		if (acc->equal(acc, fmt)) {
+			perf_hpp__column_unregister(fmt);
+			continue;
+		}
+
+		if (ovh->equal(ovh, fmt))
+			fmt->name = "Overhead";
+	}
 }
 
-void perf_hpp__setup_output_field(void)
+static bool fmt_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+	return a->equal && a->equal(a, b);
+}
+
+void perf_hpp__setup_output_field(struct perf_hpp_list *list)
 {
 	struct perf_hpp_fmt *fmt;
 
 	/* append sort keys to output field */
-	perf_hpp__for_each_sort_list(fmt) {
-		if (!list_empty(&fmt->list))
-			continue;
-
-		/*
-		 * sort entry fields are dynamically created,
-		 * so they can share a same sort key even though
-		 * the list is empty.
-		 */
-		if (perf_hpp__is_sort_entry(fmt)) {
-			struct perf_hpp_fmt *pos;
+	perf_hpp_list__for_each_sort_list(list, fmt) {
+		struct perf_hpp_fmt *pos;
 
-			perf_hpp__for_each_format(pos) {
-				if (perf_hpp__same_sort_entry(pos, fmt))
-					goto next;
-			}
+		perf_hpp_list__for_each_format(list, pos) {
+			if (fmt_equal(fmt, pos))
+				goto next;
 		}
 
 		perf_hpp__column_register(fmt);
@@ -550,27 +568,17 @@ next:
 	}
 }
 
-void perf_hpp__append_sort_keys(void)
+void perf_hpp__append_sort_keys(struct perf_hpp_list *list)
 {
 	struct perf_hpp_fmt *fmt;
 
 	/* append output fields to sort keys */
-	perf_hpp__for_each_format(fmt) {
-		if (!list_empty(&fmt->sort_list))
-			continue;
-
-		/*
-		 * sort entry fields are dynamically created,
-		 * so they can share a same sort key even though
-		 * the list is empty.
-		 */
-		if (perf_hpp__is_sort_entry(fmt)) {
-			struct perf_hpp_fmt *pos;
+	perf_hpp_list__for_each_format(list, fmt) {
+		struct perf_hpp_fmt *pos;
 
-			perf_hpp__for_each_sort_list(pos) {
-				if (perf_hpp__same_sort_entry(pos, fmt))
-					goto next;
-			}
+		perf_hpp_list__for_each_sort_list(list, pos) {
+			if (fmt_equal(fmt, pos))
+				goto next;
 		}
 
 		perf_hpp__register_sort_field(fmt);
@@ -579,20 +587,29 @@ next:
 	}
 }
 
-void perf_hpp__reset_output_field(void)
+
+static void fmt_free(struct perf_hpp_fmt *fmt)
+{
+	if (fmt->free)
+		fmt->free(fmt);
+}
+
+void perf_hpp__reset_output_field(struct perf_hpp_list *list)
 {
 	struct perf_hpp_fmt *fmt, *tmp;
 
 	/* reset output fields */
-	perf_hpp__for_each_format_safe(fmt, tmp) {
+	perf_hpp_list__for_each_format_safe(list, fmt, tmp) {
 		list_del_init(&fmt->list);
 		list_del_init(&fmt->sort_list);
+		fmt_free(fmt);
 	}
 
 	/* reset sort keys */
-	perf_hpp__for_each_sort_list_safe(fmt, tmp) {
+	perf_hpp_list__for_each_sort_list_safe(list, fmt, tmp) {
 		list_del_init(&fmt->list);
 		list_del_init(&fmt->sort_list);
+		fmt_free(fmt);
 	}
 }
 
@@ -606,7 +623,7 @@ unsigned int hists__sort_list_width(struct hists *hists)
 	bool first = true;
 	struct perf_hpp dummy_hpp;
 
-	perf_hpp__for_each_format(fmt) {
+	hists__for_each_format(hists, fmt) {
 		if (perf_hpp__should_skip(fmt, hists))
 			continue;
 
@@ -624,22 +641,39 @@ unsigned int hists__sort_list_width(struct hists *hists)
 	return ret;
 }
 
-void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+unsigned int hists__overhead_width(struct hists *hists)
 {
-	int idx;
-
-	if (perf_hpp__is_sort_entry(fmt))
-		return perf_hpp__reset_sort_width(fmt, hists);
+	struct perf_hpp_fmt *fmt;
+	int ret = 0;
+	bool first = true;
+	struct perf_hpp dummy_hpp;
 
-	for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) {
-		if (fmt == &perf_hpp__format[idx])
+	hists__for_each_format(hists, fmt) {
+		if (perf_hpp__is_sort_entry(fmt) || perf_hpp__is_dynamic_entry(fmt))
 			break;
+
+		if (first)
+			first = false;
+		else
+			ret += 2;
+
+		ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
 	}
 
-	if (idx == PERF_HPP__MAX_INDEX)
+	return ret;
+}
+
+void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+{
+	if (perf_hpp__is_sort_entry(fmt))
+		return perf_hpp__reset_sort_width(fmt, hists);
+
+	if (perf_hpp__is_dynamic_entry(fmt))
 		return;
 
-	switch (idx) {
+	BUG_ON(fmt->idx >= PERF_HPP__MAX_INDEX);
+
+	switch (fmt->idx) {
 	case PERF_HPP__OVERHEAD:
 	case PERF_HPP__OVERHEAD_SYS:
 	case PERF_HPP__OVERHEAD_US:
@@ -667,7 +701,7 @@ void perf_hpp__set_user_width(const char *width_list_str)
 	struct perf_hpp_fmt *fmt;
 	const char *ptr = width_list_str;
 
-	perf_hpp__for_each_format(fmt) {
+	perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
 		char *p;
 
 		int len = strtol(ptr, &p, 10);
@@ -679,3 +713,71 @@ void perf_hpp__set_user_width(const char *width_list_str)
 			break;
 	}
 }
+
+static int add_hierarchy_fmt(struct hists *hists, struct perf_hpp_fmt *fmt)
+{
+	struct perf_hpp_list_node *node = NULL;
+	struct perf_hpp_fmt *fmt_copy;
+	bool found = false;
+	bool skip = perf_hpp__should_skip(fmt, hists);
+
+	list_for_each_entry(node, &hists->hpp_formats, list) {
+		if (node->level == fmt->level) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		node = malloc(sizeof(*node));
+		if (node == NULL)
+			return -1;
+
+		node->skip = skip;
+		node->level = fmt->level;
+		perf_hpp_list__init(&node->hpp);
+
+		hists->nr_hpp_node++;
+		list_add_tail(&node->list, &hists->hpp_formats);
+	}
+
+	fmt_copy = perf_hpp_fmt__dup(fmt);
+	if (fmt_copy == NULL)
+		return -1;
+
+	if (!skip)
+		node->skip = false;
+
+	list_add_tail(&fmt_copy->list, &node->hpp.fields);
+	list_add_tail(&fmt_copy->sort_list, &node->hpp.sorts);
+
+	return 0;
+}
+
+int perf_hpp__setup_hists_formats(struct perf_hpp_list *list,
+				  struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	struct perf_hpp_fmt *fmt;
+	struct hists *hists;
+	int ret;
+
+	if (!symbol_conf.report_hierarchy)
+		return 0;
+
+	evlist__for_each(evlist, evsel) {
+		hists = evsel__hists(evsel);
+
+		perf_hpp_list__for_each_sort_list(list, fmt) {
+			if (perf_hpp__is_dynamic_entry(fmt) &&
+			    !perf_hpp__defined_dynamic_entry(fmt, hists))
+				continue;
+
+			ret = add_hierarchy_fmt(hists, fmt);
+			if (ret < 0)
+				return ret;
+		}
+	}
+
+	return 0;
+}
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 387110d50b00..7aff5acf3265 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -165,8 +165,28 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 	return ret;
 }
 
+/*
+ * If have one single callchain root, don't bother printing
+ * its percentage (100 % in fractal mode and the same percentage
+ * than the hist in graph mode). This also avoid one level of column.
+ *
+ * However when percent-limit applied, it's possible that single callchain
+ * node have different (non-100% in fractal mode) percentage.
+ */
+static bool need_percent_display(struct rb_node *node, u64 parent_samples)
+{
+	struct callchain_node *cnode;
+
+	if (rb_next(node))
+		return true;
+
+	cnode = rb_entry(node, struct callchain_node, rb_node);
+	return callchain_cumul_hits(cnode) != parent_samples;
+}
+
 static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
-				       u64 total_samples, int left_margin)
+				       u64 total_samples, u64 parent_samples,
+				       int left_margin)
 {
 	struct callchain_node *cnode;
 	struct callchain_list *chain;
@@ -177,13 +197,8 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 	int ret = 0;
 	char bf[1024];
 
-	/*
-	 * If have one single callchain root, don't bother printing
-	 * its percentage (100 % in fractal mode and the same percentage
-	 * than the hist in graph mode). This also avoid one level of column.
-	 */
 	node = rb_first(root);
-	if (node && !rb_next(node)) {
+	if (node && !need_percent_display(node, parent_samples)) {
 		cnode = rb_entry(node, struct callchain_node, rb_node);
 		list_for_each_entry(chain, &cnode->val, list) {
 			/*
@@ -213,9 +228,15 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 		root = &cnode->rb_root;
 	}
 
+	if (callchain_param.mode == CHAIN_GRAPH_REL)
+		total_samples = parent_samples;
+
 	ret += __callchain__fprintf_graph(fp, root, total_samples,
 					  1, 1, left_margin);
-	ret += fprintf(fp, "\n");
+	if (ret) {
+		/* do not add a blank line if it printed nothing */
+		ret += fprintf(fp, "\n");
+	}
 
 	return ret;
 }
@@ -323,16 +344,19 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
 					    u64 total_samples, int left_margin,
 					    FILE *fp)
 {
+	u64 parent_samples = he->stat.period;
+
+	if (symbol_conf.cumulate_callchain)
+		parent_samples = he->stat_acc->period;
+
 	switch (callchain_param.mode) {
 	case CHAIN_GRAPH_REL:
-		return callchain__fprintf_graph(fp, &he->sorted_chain,
-						symbol_conf.cumulate_callchain ?
-						he->stat_acc->period : he->stat.period,
-						left_margin);
+		return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples,
+						parent_samples, left_margin);
 		break;
 	case CHAIN_GRAPH_ABS:
 		return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples,
-						left_margin);
+						parent_samples, left_margin);
 		break;
 	case CHAIN_FLAT:
 		return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples);
@@ -349,45 +373,66 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
 	return 0;
 }
 
-static size_t hist_entry__callchain_fprintf(struct hist_entry *he,
-					    struct hists *hists,
-					    FILE *fp)
+static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
 {
-	int left_margin = 0;
-	u64 total_period = hists->stats.total_period;
+	const char *sep = symbol_conf.field_sep;
+	struct perf_hpp_fmt *fmt;
+	char *start = hpp->buf;
+	int ret;
+	bool first = true;
 
-	if (field_order == NULL && (sort_order == NULL ||
-				    !prefixcmp(sort_order, "comm"))) {
-		struct perf_hpp_fmt *fmt;
+	if (symbol_conf.exclude_other && !he->parent)
+		return 0;
 
-		perf_hpp__for_each_format(fmt) {
-			if (!perf_hpp__is_sort_entry(fmt))
-				continue;
+	hists__for_each_format(he->hists, fmt) {
+		if (perf_hpp__should_skip(fmt, he->hists))
+			continue;
 
-			/* must be 'comm' sort entry */
-			left_margin = fmt->width(fmt, NULL, hists_to_evsel(hists));
-			left_margin -= thread__comm_len(he->thread);
-			break;
-		}
+		/*
+		 * If there's no field_sep, we still need
+		 * to display initial '  '.
+		 */
+		if (!sep || !first) {
+			ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: "  ");
+			advance_hpp(hpp, ret);
+		} else
+			first = false;
+
+		if (perf_hpp__use_color() && fmt->color)
+			ret = fmt->color(fmt, hpp, he);
+		else
+			ret = fmt->entry(fmt, hpp, he);
+
+		ret = hist_entry__snprintf_alignment(he, hpp, fmt, ret);
+		advance_hpp(hpp, ret);
 	}
-	return hist_entry_callchain__fprintf(he, total_period, left_margin, fp);
+
+	return hpp->buf - start;
 }
 
-static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
+static int hist_entry__hierarchy_fprintf(struct hist_entry *he,
+					 struct perf_hpp *hpp,
+					 struct hists *hists,
+					 FILE *fp)
 {
 	const char *sep = symbol_conf.field_sep;
 	struct perf_hpp_fmt *fmt;
-	char *start = hpp->buf;
-	int ret;
+	struct perf_hpp_list_node *fmt_node;
+	char *buf = hpp->buf;
+	size_t size = hpp->size;
+	int ret, printed = 0;
 	bool first = true;
 
 	if (symbol_conf.exclude_other && !he->parent)
 		return 0;
 
-	perf_hpp__for_each_format(fmt) {
-		if (perf_hpp__should_skip(fmt, he->hists))
-			continue;
+	ret = scnprintf(hpp->buf, hpp->size, "%*s", he->depth * HIERARCHY_INDENT, "");
+	advance_hpp(hpp, ret);
 
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
 		/*
 		 * If there's no field_sep, we still need
 		 * to display initial '  '.
@@ -403,10 +448,47 @@ static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
 		else
 			ret = fmt->entry(fmt, hpp, he);
 
+		ret = hist_entry__snprintf_alignment(he, hpp, fmt, ret);
 		advance_hpp(hpp, ret);
 	}
 
-	return hpp->buf - start;
+	if (!sep)
+		ret = scnprintf(hpp->buf, hpp->size, "%*s",
+				(hists->nr_hpp_node - 2) * HIERARCHY_INDENT, "");
+	advance_hpp(hpp, ret);
+
+	printed += fprintf(fp, "%s", buf);
+
+	perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+		hpp->buf  = buf;
+		hpp->size = size;
+
+		/*
+		 * No need to call hist_entry__snprintf_alignment() since this
+		 * fmt is always the last column in the hierarchy mode.
+		 */
+		if (perf_hpp__use_color() && fmt->color)
+			fmt->color(fmt, hpp, he);
+		else
+			fmt->entry(fmt, hpp, he);
+
+		/*
+		 * dynamic entries are right-aligned but we want left-aligned
+		 * in the hierarchy mode
+		 */
+		printed += fprintf(fp, "%s%s", sep ?: "  ", ltrim(buf));
+	}
+	printed += putc('\n', fp);
+
+	if (symbol_conf.use_callchain && he->leaf) {
+		u64 total = hists__total_period(hists);
+
+		printed += hist_entry_callchain__fprintf(he, total, 0, fp);
+		goto out;
+	}
+
+out:
+	return printed;
 }
 
 static int hist_entry__fprintf(struct hist_entry *he, size_t size,
@@ -418,24 +500,134 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 		.buf		= bf,
 		.size		= size,
 	};
+	u64 total_period = hists->stats.total_period;
 
 	if (size == 0 || size > bfsz)
 		size = hpp.size = bfsz;
 
+	if (symbol_conf.report_hierarchy)
+		return hist_entry__hierarchy_fprintf(he, &hpp, hists, fp);
+
 	hist_entry__snprintf(he, &hpp);
 
 	ret = fprintf(fp, "%s\n", bf);
 
 	if (symbol_conf.use_callchain)
-		ret += hist_entry__callchain_fprintf(he, hists, fp);
+		ret += hist_entry_callchain__fprintf(he, total_period, 0, fp);
 
 	return ret;
 }
 
+static int print_hierarchy_indent(const char *sep, int indent,
+				  const char *line, FILE *fp)
+{
+	if (sep != NULL || indent < 2)
+		return 0;
+
+	return fprintf(fp, "%-.*s", (indent - 2) * HIERARCHY_INDENT, line);
+}
+
+static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
+				  const char *sep, FILE *fp)
+{
+	bool first_node, first_col;
+	int indent;
+	int depth;
+	unsigned width = 0;
+	unsigned header_width = 0;
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+
+	indent = hists->nr_hpp_node;
+
+	/* preserve max indent depth for column headers */
+	print_hierarchy_indent(sep, indent, spaces, fp);
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		fmt->header(fmt, hpp, hists_to_evsel(hists));
+		fprintf(fp, "%s%s", hpp->buf, sep ?: "  ");
+	}
+
+	/* combine sort headers with ' / ' */
+	first_node = true;
+	list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+		if (!first_node)
+			header_width += fprintf(fp, " / ");
+		first_node = false;
+
+		first_col = true;
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+			if (perf_hpp__should_skip(fmt, hists))
+				continue;
+
+			if (!first_col)
+				header_width += fprintf(fp, "+");
+			first_col = false;
+
+			fmt->header(fmt, hpp, hists_to_evsel(hists));
+			rtrim(hpp->buf);
+
+			header_width += fprintf(fp, "%s", ltrim(hpp->buf));
+		}
+	}
+
+	fprintf(fp, "\n# ");
+
+	/* preserve max indent depth for initial dots */
+	print_hierarchy_indent(sep, indent, dots, fp);
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+
+	first_col = true;
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		if (!first_col)
+			fprintf(fp, "%s", sep ?: "..");
+		first_col = false;
+
+		width = fmt->width(fmt, hpp, hists_to_evsel(hists));
+		fprintf(fp, "%.*s", width, dots);
+	}
+
+	depth = 0;
+	list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+		first_col = true;
+		width = depth * HIERARCHY_INDENT;
+
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+			if (perf_hpp__should_skip(fmt, hists))
+				continue;
+
+			if (!first_col)
+				width++;  /* for '+' sign between column header */
+			first_col = false;
+
+			width += fmt->width(fmt, hpp, hists_to_evsel(hists));
+		}
+
+		if (width > header_width)
+			header_width = width;
+
+		depth++;
+	}
+
+	fprintf(fp, "%s%-.*s", sep ?: "  ", header_width, dots);
+
+	fprintf(fp, "\n#\n");
+
+	return 2;
+}
+
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp)
 {
 	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
 	struct rb_node *nd;
 	size_t ret = 0;
 	unsigned int width;
@@ -449,10 +641,11 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 	bool first = true;
 	size_t linesz;
 	char *line = NULL;
+	unsigned indent;
 
 	init_rem_hits();
 
-	perf_hpp__for_each_format(fmt)
+	hists__for_each_format(hists, fmt)
 		perf_hpp__reset_width(fmt, hists);
 
 	if (symbol_conf.col_width_list_str)
@@ -463,7 +656,16 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 
 	fprintf(fp, "# ");
 
-	perf_hpp__for_each_format(fmt) {
+	if (symbol_conf.report_hierarchy) {
+		list_for_each_entry(fmt_node, &hists->hpp_formats, list) {
+			perf_hpp_list__for_each_format(&fmt_node->hpp, fmt)
+				perf_hpp__reset_width(fmt, hists);
+		}
+		nr_rows += print_hierarchy_header(hists, &dummy_hpp, sep, fp);
+		goto print_entries;
+	}
+
+	hists__for_each_format(hists, fmt) {
 		if (perf_hpp__should_skip(fmt, hists))
 			continue;
 
@@ -487,7 +689,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 
 	fprintf(fp, "# ");
 
-	perf_hpp__for_each_format(fmt) {
+	hists__for_each_format(hists, fmt) {
 		unsigned int i;
 
 		if (perf_hpp__should_skip(fmt, hists))
@@ -520,7 +722,9 @@ print_entries:
 		goto out;
 	}
 
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+	indent = hists__overhead_width(hists) + 4;
+
+	for (nd = rb_first(&hists->entries); nd; nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 		float percent;
 
@@ -536,6 +740,20 @@ print_entries:
 		if (max_rows && ++nr_rows >= max_rows)
 			break;
 
+		/*
+		 * If all children are filtered out or percent-limited,
+		 * display "no entry >= x.xx%" message.
+		 */
+		if (!h->leaf && !hist_entry__has_hierarchy_children(h, min_pcnt)) {
+			int depth = hists->nr_hpp_node + h->depth + 1;
+
+			print_hierarchy_indent(sep, depth, spaces, fp);
+			fprintf(fp, "%*sno entry >= %.2f%%\n", indent, "", min_pcnt);
+
+			if (max_rows && ++nr_rows >= max_rows)
+				break;
+		}
+
 		if (h->ms.map == NULL && verbose > 1) {
 			__map_groups__fprintf_maps(h->thread->mg,
 						   MAP__FUNCTION, fp);
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 5eec53a3f4ac..eea25e2424e9 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -82,6 +82,7 @@ libperf-y += parse-branch-options.o
 libperf-y += parse-regs-options.o
 libperf-y += term.o
 libperf-y += help-unknown-cmd.o
+libperf-y += mem-events.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
 libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
@@ -105,8 +106,17 @@ libperf-y += scripting-engines/
 
 libperf-$(CONFIG_ZLIB) += zlib.o
 libperf-$(CONFIG_LZMA) += lzma.o
+libperf-y += demangle-java.o
+
+ifdef CONFIG_JITDUMP
+libperf-$(CONFIG_LIBELF) += jitdump.o
+libperf-$(CONFIG_LIBELF) += genelf.o
+libperf-$(CONFIG_LIBELF) += genelf_debug.o
+endif
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+# avoid compiler warnings in 32-bit mode
+CFLAGS_genelf_debug.o  += -Wno-packed
 
 $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
 	$(call rule_mkdir)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 360fda01f3b0..ec164fe70718 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -478,10 +478,11 @@ void auxtrace_heap__pop(struct auxtrace_heap *heap)
 			 heap_array[last].ordinal);
 }
 
-size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr,
+				       struct perf_evlist *evlist)
 {
 	if (itr)
-		return itr->info_priv_size(itr);
+		return itr->info_priv_size(itr, evlist);
 	return 0;
 }
 
@@ -852,7 +853,7 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
 	int err;
 
 	pr_debug2("Synthesizing auxtrace information\n");
-	priv_size = auxtrace_record__info_priv_size(itr);
+	priv_size = auxtrace_record__info_priv_size(itr, session->evlist);
 	ev = zalloc(sizeof(struct auxtrace_info_event) + priv_size);
 	if (!ev)
 		return -ENOMEM;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index b86f90db1352..e5a8e2d4f2af 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -293,7 +293,8 @@ struct auxtrace_record {
 	int (*recording_options)(struct auxtrace_record *itr,
 				 struct perf_evlist *evlist,
 				 struct record_opts *opts);
-	size_t (*info_priv_size)(struct auxtrace_record *itr);
+	size_t (*info_priv_size)(struct auxtrace_record *itr,
+				 struct perf_evlist *evlist);
 	int (*info_fill)(struct auxtrace_record *itr,
 			 struct perf_session *session,
 			 struct auxtrace_info_event *auxtrace_info,
@@ -429,7 +430,8 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
 int auxtrace_record__options(struct auxtrace_record *itr,
 			     struct perf_evlist *evlist,
 			     struct record_opts *opts);
-size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr);
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr,
+				       struct perf_evlist *evlist);
 int auxtrace_record__info_fill(struct auxtrace_record *itr,
 			       struct perf_session *session,
 			       struct auxtrace_info_event *auxtrace_info,
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 540a7efa657e..0967ce601931 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -7,6 +7,7 @@
 
 #include <linux/bpf.h>
 #include <bpf/libbpf.h>
+#include <bpf/bpf.h>
 #include <linux/err.h>
 #include <linux/string.h>
 #include "perf.h"
@@ -16,6 +17,7 @@
 #include "llvm-utils.h"
 #include "probe-event.h"
 #include "probe-finder.h" // for MAX_PROBES
+#include "parse-events.h"
 #include "llvm-utils.h"
 
 #define DEFINE_PRINT_FN(name, level) \
@@ -108,8 +110,8 @@ void bpf__clear(void)
 }
 
 static void
-bpf_prog_priv__clear(struct bpf_program *prog __maybe_unused,
-		     void *_priv)
+clear_prog_priv(struct bpf_program *prog __maybe_unused,
+		void *_priv)
 {
 	struct bpf_prog_priv *priv = _priv;
 
@@ -337,7 +339,7 @@ config_bpf_program(struct bpf_program *prog)
 	}
 	pr_debug("bpf: config '%s' is ok\n", config_str);
 
-	err = bpf_program__set_private(prog, priv, bpf_prog_priv__clear);
+	err = bpf_program__set_private(prog, priv, clear_prog_priv);
 	if (err) {
 		pr_debug("Failed to set priv for program '%s'\n", config_str);
 		goto errout;
@@ -739,6 +741,682 @@ int bpf__foreach_tev(struct bpf_object *obj,
 	return 0;
 }
 
+enum bpf_map_op_type {
+	BPF_MAP_OP_SET_VALUE,
+	BPF_MAP_OP_SET_EVSEL,
+};
+
+enum bpf_map_key_type {
+	BPF_MAP_KEY_ALL,
+	BPF_MAP_KEY_RANGES,
+};
+
+struct bpf_map_op {
+	struct list_head list;
+	enum bpf_map_op_type op_type;
+	enum bpf_map_key_type key_type;
+	union {
+		struct parse_events_array array;
+	} k;
+	union {
+		u64 value;
+		struct perf_evsel *evsel;
+	} v;
+};
+
+struct bpf_map_priv {
+	struct list_head ops_list;
+};
+
+static void
+bpf_map_op__delete(struct bpf_map_op *op)
+{
+	if (!list_empty(&op->list))
+		list_del(&op->list);
+	if (op->key_type == BPF_MAP_KEY_RANGES)
+		parse_events__clear_array(&op->k.array);
+	free(op);
+}
+
+static void
+bpf_map_priv__purge(struct bpf_map_priv *priv)
+{
+	struct bpf_map_op *pos, *n;
+
+	list_for_each_entry_safe(pos, n, &priv->ops_list, list) {
+		list_del_init(&pos->list);
+		bpf_map_op__delete(pos);
+	}
+}
+
+static void
+bpf_map_priv__clear(struct bpf_map *map __maybe_unused,
+		    void *_priv)
+{
+	struct bpf_map_priv *priv = _priv;
+
+	bpf_map_priv__purge(priv);
+	free(priv);
+}
+
+static int
+bpf_map_op_setkey(struct bpf_map_op *op, struct parse_events_term *term)
+{
+	op->key_type = BPF_MAP_KEY_ALL;
+	if (!term)
+		return 0;
+
+	if (term->array.nr_ranges) {
+		size_t memsz = term->array.nr_ranges *
+				sizeof(op->k.array.ranges[0]);
+
+		op->k.array.ranges = memdup(term->array.ranges, memsz);
+		if (!op->k.array.ranges) {
+			pr_debug("No enough memory to alloc indices for map\n");
+			return -ENOMEM;
+		}
+		op->key_type = BPF_MAP_KEY_RANGES;
+		op->k.array.nr_ranges = term->array.nr_ranges;
+	}
+	return 0;
+}
+
+static struct bpf_map_op *
+bpf_map_op__new(struct parse_events_term *term)
+{
+	struct bpf_map_op *op;
+	int err;
+
+	op = zalloc(sizeof(*op));
+	if (!op) {
+		pr_debug("Failed to alloc bpf_map_op\n");
+		return ERR_PTR(-ENOMEM);
+	}
+	INIT_LIST_HEAD(&op->list);
+
+	err = bpf_map_op_setkey(op, term);
+	if (err) {
+		free(op);
+		return ERR_PTR(err);
+	}
+	return op;
+}
+
+static int
+bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op)
+{
+	struct bpf_map_priv *priv;
+	const char *map_name;
+	int err;
+
+	map_name = bpf_map__get_name(map);
+	err = bpf_map__get_private(map, (void **)&priv);
+	if (err) {
+		pr_debug("Failed to get private from map %s\n", map_name);
+		return err;
+	}
+
+	if (!priv) {
+		priv = zalloc(sizeof(*priv));
+		if (!priv) {
+			pr_debug("No enough memory to alloc map private\n");
+			return -ENOMEM;
+		}
+		INIT_LIST_HEAD(&priv->ops_list);
+
+		if (bpf_map__set_private(map, priv, bpf_map_priv__clear)) {
+			free(priv);
+			return -BPF_LOADER_ERRNO__INTERNAL;
+		}
+	}
+
+	list_add_tail(&op->list, &priv->ops_list);
+	return 0;
+}
+
+static struct bpf_map_op *
+bpf_map__add_newop(struct bpf_map *map, struct parse_events_term *term)
+{
+	struct bpf_map_op *op;
+	int err;
+
+	op = bpf_map_op__new(term);
+	if (IS_ERR(op))
+		return op;
+
+	err = bpf_map__add_op(map, op);
+	if (err) {
+		bpf_map_op__delete(op);
+		return ERR_PTR(err);
+	}
+	return op;
+}
+
+static int
+__bpf_map__config_value(struct bpf_map *map,
+			struct parse_events_term *term)
+{
+	struct bpf_map_def def;
+	struct bpf_map_op *op;
+	const char *map_name;
+	int err;
+
+	map_name = bpf_map__get_name(map);
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("Unable to get map definition from '%s'\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	if (def.type != BPF_MAP_TYPE_ARRAY) {
+		pr_debug("Map %s type is not BPF_MAP_TYPE_ARRAY\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
+	}
+	if (def.key_size < sizeof(unsigned int)) {
+		pr_debug("Map %s has incorrect key size\n", map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE;
+	}
+	switch (def.value_size) {
+	case 1:
+	case 2:
+	case 4:
+	case 8:
+		break;
+	default:
+		pr_debug("Map %s has incorrect value size\n", map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE;
+	}
+
+	op = bpf_map__add_newop(map, term);
+	if (IS_ERR(op))
+		return PTR_ERR(op);
+	op->op_type = BPF_MAP_OP_SET_VALUE;
+	op->v.value = term->val.num;
+	return 0;
+}
+
+static int
+bpf_map__config_value(struct bpf_map *map,
+		      struct parse_events_term *term,
+		      struct perf_evlist *evlist __maybe_unused)
+{
+	if (!term->err_val) {
+		pr_debug("Config value not set\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_CONF;
+	}
+
+	if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM) {
+		pr_debug("ERROR: wrong value type for 'value'\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
+	}
+
+	return __bpf_map__config_value(map, term);
+}
+
+static int
+__bpf_map__config_event(struct bpf_map *map,
+			struct parse_events_term *term,
+			struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	struct bpf_map_def def;
+	struct bpf_map_op *op;
+	const char *map_name;
+	int err;
+
+	map_name = bpf_map__get_name(map);
+	evsel = perf_evlist__find_evsel_by_str(evlist, term->val.str);
+	if (!evsel) {
+		pr_debug("Event (for '%s') '%s' doesn't exist\n",
+			 map_name, term->val.str);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT;
+	}
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("Unable to get map definition from '%s'\n",
+			 map_name);
+		return err;
+	}
+
+	/*
+	 * No need to check key_size and value_size:
+	 * kernel has already checked them.
+	 */
+	if (def.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
+		pr_debug("Map %s type is not BPF_MAP_TYPE_PERF_EVENT_ARRAY\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
+	}
+
+	op = bpf_map__add_newop(map, term);
+	if (IS_ERR(op))
+		return PTR_ERR(op);
+	op->op_type = BPF_MAP_OP_SET_EVSEL;
+	op->v.evsel = evsel;
+	return 0;
+}
+
+static int
+bpf_map__config_event(struct bpf_map *map,
+		      struct parse_events_term *term,
+		      struct perf_evlist *evlist)
+{
+	if (!term->err_val) {
+		pr_debug("Config value not set\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_CONF;
+	}
+
+	if (term->type_val != PARSE_EVENTS__TERM_TYPE_STR) {
+		pr_debug("ERROR: wrong value type for 'event'\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
+	}
+
+	return __bpf_map__config_event(map, term, evlist);
+}
+
+struct bpf_obj_config__map_func {
+	const char *config_opt;
+	int (*config_func)(struct bpf_map *, struct parse_events_term *,
+			   struct perf_evlist *);
+};
+
+struct bpf_obj_config__map_func bpf_obj_config__map_funcs[] = {
+	{"value", bpf_map__config_value},
+	{"event", bpf_map__config_event},
+};
+
+static int
+config_map_indices_range_check(struct parse_events_term *term,
+			       struct bpf_map *map,
+			       const char *map_name)
+{
+	struct parse_events_array *array = &term->array;
+	struct bpf_map_def def;
+	unsigned int i;
+	int err;
+
+	if (!array->nr_ranges)
+		return 0;
+	if (!array->ranges) {
+		pr_debug("ERROR: map %s: array->nr_ranges is %d but range array is NULL\n",
+			 map_name, (int)array->nr_ranges);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("ERROR: Unable to get map definition from '%s'\n",
+			 map_name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	for (i = 0; i < array->nr_ranges; i++) {
+		unsigned int start = array->ranges[i].start;
+		size_t length = array->ranges[i].length;
+		unsigned int idx = start + length - 1;
+
+		if (idx >= def.max_entries) {
+			pr_debug("ERROR: index %d too large\n", idx);
+			return -BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG;
+		}
+	}
+	return 0;
+}
+
+static int
+bpf__obj_config_map(struct bpf_object *obj,
+		    struct parse_events_term *term,
+		    struct perf_evlist *evlist,
+		    int *key_scan_pos)
+{
+	/* key is "map:<mapname>.<config opt>" */
+	char *map_name = strdup(term->config + sizeof("map:") - 1);
+	struct bpf_map *map;
+	int err = -BPF_LOADER_ERRNO__OBJCONF_OPT;
+	char *map_opt;
+	size_t i;
+
+	if (!map_name)
+		return -ENOMEM;
+
+	map_opt = strchr(map_name, '.');
+	if (!map_opt) {
+		pr_debug("ERROR: Invalid map config: %s\n", map_name);
+		goto out;
+	}
+
+	*map_opt++ = '\0';
+	if (*map_opt == '\0') {
+		pr_debug("ERROR: Invalid map option: %s\n", term->config);
+		goto out;
+	}
+
+	map = bpf_object__get_map_by_name(obj, map_name);
+	if (!map) {
+		pr_debug("ERROR: Map %s doesn't exist\n", map_name);
+		err = -BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST;
+		goto out;
+	}
+
+	*key_scan_pos += strlen(map_opt);
+	err = config_map_indices_range_check(term, map, map_name);
+	if (err)
+		goto out;
+	*key_scan_pos -= strlen(map_opt);
+
+	for (i = 0; i < ARRAY_SIZE(bpf_obj_config__map_funcs); i++) {
+		struct bpf_obj_config__map_func *func =
+				&bpf_obj_config__map_funcs[i];
+
+		if (strcmp(map_opt, func->config_opt) == 0) {
+			err = func->config_func(map, term, evlist);
+			goto out;
+		}
+	}
+
+	pr_debug("ERROR: Invalid map config option '%s'\n", map_opt);
+	err = -BPF_LOADER_ERRNO__OBJCONF_MAP_OPT;
+out:
+	free(map_name);
+	if (!err)
+		key_scan_pos += strlen(map_opt);
+	return err;
+}
+
+int bpf__config_obj(struct bpf_object *obj,
+		    struct parse_events_term *term,
+		    struct perf_evlist *evlist,
+		    int *error_pos)
+{
+	int key_scan_pos = 0;
+	int err;
+
+	if (!obj || !term || !term->config)
+		return -EINVAL;
+
+	if (!prefixcmp(term->config, "map:")) {
+		key_scan_pos = sizeof("map:") - 1;
+		err = bpf__obj_config_map(obj, term, evlist, &key_scan_pos);
+		goto out;
+	}
+	err = -BPF_LOADER_ERRNO__OBJCONF_OPT;
+out:
+	if (error_pos)
+		*error_pos = key_scan_pos;
+	return err;
+
+}
+
+typedef int (*map_config_func_t)(const char *name, int map_fd,
+				 struct bpf_map_def *pdef,
+				 struct bpf_map_op *op,
+				 void *pkey, void *arg);
+
+static int
+foreach_key_array_all(map_config_func_t func,
+		      void *arg, const char *name,
+		      int map_fd, struct bpf_map_def *pdef,
+		      struct bpf_map_op *op)
+{
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < pdef->max_entries; i++) {
+		err = func(name, map_fd, pdef, op, &i, arg);
+		if (err) {
+			pr_debug("ERROR: failed to insert value to %s[%u]\n",
+				 name, i);
+			return err;
+		}
+	}
+	return 0;
+}
+
+static int
+foreach_key_array_ranges(map_config_func_t func, void *arg,
+			 const char *name, int map_fd,
+			 struct bpf_map_def *pdef,
+			 struct bpf_map_op *op)
+{
+	unsigned int i, j;
+	int err;
+
+	for (i = 0; i < op->k.array.nr_ranges; i++) {
+		unsigned int start = op->k.array.ranges[i].start;
+		size_t length = op->k.array.ranges[i].length;
+
+		for (j = 0; j < length; j++) {
+			unsigned int idx = start + j;
+
+			err = func(name, map_fd, pdef, op, &idx, arg);
+			if (err) {
+				pr_debug("ERROR: failed to insert value to %s[%u]\n",
+					 name, idx);
+				return err;
+			}
+		}
+	}
+	return 0;
+}
+
+static int
+bpf_map_config_foreach_key(struct bpf_map *map,
+			   map_config_func_t func,
+			   void *arg)
+{
+	int err, map_fd;
+	const char *name;
+	struct bpf_map_op *op;
+	struct bpf_map_def def;
+	struct bpf_map_priv *priv;
+
+	name = bpf_map__get_name(map);
+
+	err = bpf_map__get_private(map, (void **)&priv);
+	if (err) {
+		pr_debug("ERROR: failed to get private from map %s\n", name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+	if (!priv || list_empty(&priv->ops_list)) {
+		pr_debug("INFO: nothing to config for map %s\n", name);
+		return 0;
+	}
+
+	err = bpf_map__get_def(map, &def);
+	if (err) {
+		pr_debug("ERROR: failed to get definition from map %s\n", name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+	map_fd = bpf_map__get_fd(map);
+	if (map_fd < 0) {
+		pr_debug("ERROR: failed to get fd from map %s\n", name);
+		return map_fd;
+	}
+
+	list_for_each_entry(op, &priv->ops_list, list) {
+		switch (def.type) {
+		case BPF_MAP_TYPE_ARRAY:
+		case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+			switch (op->key_type) {
+			case BPF_MAP_KEY_ALL:
+				err = foreach_key_array_all(func, arg, name,
+							    map_fd, &def, op);
+				break;
+			case BPF_MAP_KEY_RANGES:
+				err = foreach_key_array_ranges(func, arg, name,
+							       map_fd, &def,
+							       op);
+				break;
+			default:
+				pr_debug("ERROR: keytype for map '%s' invalid\n",
+					 name);
+				return -BPF_LOADER_ERRNO__INTERNAL;
+			}
+			if (err)
+				return err;
+			break;
+		default:
+			pr_debug("ERROR: type of '%s' incorrect\n", name);
+			return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
+		}
+	}
+
+	return 0;
+}
+
+static int
+apply_config_value_for_key(int map_fd, void *pkey,
+			   size_t val_size, u64 val)
+{
+	int err = 0;
+
+	switch (val_size) {
+	case 1: {
+		u8 _val = (u8)(val);
+		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
+		break;
+	}
+	case 2: {
+		u16 _val = (u16)(val);
+		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
+		break;
+	}
+	case 4: {
+		u32 _val = (u32)(val);
+		err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
+		break;
+	}
+	case 8: {
+		err = bpf_map_update_elem(map_fd, pkey, &val, BPF_ANY);
+		break;
+	}
+	default:
+		pr_debug("ERROR: invalid value size\n");
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE;
+	}
+	if (err && errno)
+		err = -errno;
+	return err;
+}
+
+static int
+apply_config_evsel_for_key(const char *name, int map_fd, void *pkey,
+			   struct perf_evsel *evsel)
+{
+	struct xyarray *xy = evsel->fd;
+	struct perf_event_attr *attr;
+	unsigned int key, events;
+	bool check_pass = false;
+	int *evt_fd;
+	int err;
+
+	if (!xy) {
+		pr_debug("ERROR: evsel not ready for map %s\n", name);
+		return -BPF_LOADER_ERRNO__INTERNAL;
+	}
+
+	if (xy->row_size / xy->entry_size != 1) {
+		pr_debug("ERROR: Dimension of target event is incorrect for map %s\n",
+			 name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM;
+	}
+
+	attr = &evsel->attr;
+	if (attr->inherit) {
+		pr_debug("ERROR: Can't put inherit event into map %s\n", name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH;
+	}
+
+	if (perf_evsel__is_bpf_output(evsel))
+		check_pass = true;
+	if (attr->type == PERF_TYPE_RAW)
+		check_pass = true;
+	if (attr->type == PERF_TYPE_HARDWARE)
+		check_pass = true;
+	if (!check_pass) {
+		pr_debug("ERROR: Event type is wrong for map %s\n", name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE;
+	}
+
+	events = xy->entries / (xy->row_size / xy->entry_size);
+	key = *((unsigned int *)pkey);
+	if (key >= events) {
+		pr_debug("ERROR: there is no event %d for map %s\n",
+			 key, name);
+		return -BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE;
+	}
+	evt_fd = xyarray__entry(xy, key, 0);
+	err = bpf_map_update_elem(map_fd, pkey, evt_fd, BPF_ANY);
+	if (err && errno)
+		err = -errno;
+	return err;
+}
+
+static int
+apply_obj_config_map_for_key(const char *name, int map_fd,
+			     struct bpf_map_def *pdef __maybe_unused,
+			     struct bpf_map_op *op,
+			     void *pkey, void *arg __maybe_unused)
+{
+	int err;
+
+	switch (op->op_type) {
+	case BPF_MAP_OP_SET_VALUE:
+		err = apply_config_value_for_key(map_fd, pkey,
+						 pdef->value_size,
+						 op->v.value);
+		break;
+	case BPF_MAP_OP_SET_EVSEL:
+		err = apply_config_evsel_for_key(name, map_fd, pkey,
+						 op->v.evsel);
+		break;
+	default:
+		pr_debug("ERROR: unknown value type for '%s'\n", name);
+		err = -BPF_LOADER_ERRNO__INTERNAL;
+	}
+	return err;
+}
+
+static int
+apply_obj_config_map(struct bpf_map *map)
+{
+	return bpf_map_config_foreach_key(map,
+					  apply_obj_config_map_for_key,
+					  NULL);
+}
+
+static int
+apply_obj_config_object(struct bpf_object *obj)
+{
+	struct bpf_map *map;
+	int err;
+
+	bpf_map__for_each(map, obj) {
+		err = apply_obj_config_map(map);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+int bpf__apply_obj_config(void)
+{
+	struct bpf_object *obj, *tmp;
+	int err;
+
+	bpf_object__for_each_safe(obj, tmp) {
+		err = apply_obj_config_object(obj);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 #define ERRNO_OFFSET(e)		((e) - __BPF_LOADER_ERRNO__START)
 #define ERRCODE_OFFSET(c)	ERRNO_OFFSET(BPF_LOADER_ERRNO__##c)
 #define NR_ERRNO	(__BPF_LOADER_ERRNO__END - __BPF_LOADER_ERRNO__START)
@@ -753,6 +1431,20 @@ static const char *bpf_loader_strerror_table[NR_ERRNO] = {
 	[ERRCODE_OFFSET(PROLOGUE)]	= "Failed to generate prologue",
 	[ERRCODE_OFFSET(PROLOGUE2BIG)]	= "Prologue too big for program",
 	[ERRCODE_OFFSET(PROLOGUEOOB)]	= "Offset out of bound for prologue",
+	[ERRCODE_OFFSET(OBJCONF_OPT)]	= "Invalid object config option",
+	[ERRCODE_OFFSET(OBJCONF_CONF)]	= "Config value not set (missing '=')",
+	[ERRCODE_OFFSET(OBJCONF_MAP_OPT)]	= "Invalid object map config option",
+	[ERRCODE_OFFSET(OBJCONF_MAP_NOTEXIST)]	= "Target map doesn't exist",
+	[ERRCODE_OFFSET(OBJCONF_MAP_VALUE)]	= "Incorrect value type for map",
+	[ERRCODE_OFFSET(OBJCONF_MAP_TYPE)]	= "Incorrect map type",
+	[ERRCODE_OFFSET(OBJCONF_MAP_KEYSIZE)]	= "Incorrect map key size",
+	[ERRCODE_OFFSET(OBJCONF_MAP_VALUESIZE)]	= "Incorrect map value size",
+	[ERRCODE_OFFSET(OBJCONF_MAP_NOEVT)]	= "Event not found for map setting",
+	[ERRCODE_OFFSET(OBJCONF_MAP_MAPSIZE)]	= "Invalid map size for event setting",
+	[ERRCODE_OFFSET(OBJCONF_MAP_EVTDIM)]	= "Event dimension too large",
+	[ERRCODE_OFFSET(OBJCONF_MAP_EVTINH)]	= "Doesn't support inherit event",
+	[ERRCODE_OFFSET(OBJCONF_MAP_EVTTYPE)]	= "Wrong event type for map",
+	[ERRCODE_OFFSET(OBJCONF_MAP_IDX2BIG)]	= "Index too large",
 };
 
 static int
@@ -872,3 +1564,29 @@ int bpf__strerror_load(struct bpf_object *obj,
 	bpf__strerror_end(buf, size);
 	return 0;
 }
+
+int bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
+			     struct parse_events_term *term __maybe_unused,
+			     struct perf_evlist *evlist __maybe_unused,
+			     int *error_pos __maybe_unused, int err,
+			     char *buf, size_t size)
+{
+	bpf__strerror_head(err, buf, size);
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE,
+			    "Can't use this config term with this map type");
+	bpf__strerror_end(buf, size);
+	return 0;
+}
+
+int bpf__strerror_apply_obj_config(int err, char *buf, size_t size)
+{
+	bpf__strerror_head(err, buf, size);
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,
+			    "Cannot set event to BPF map in multi-thread tracing");
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH,
+			    "%s (Hint: use -i to turn off inherit)", emsg);
+	bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE,
+			    "Can only put raw, hardware and BPF output event into a BPF map");
+	bpf__strerror_end(buf, size);
+	return 0;
+}
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 6fdc0457e2b6..be4311944e3d 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -10,6 +10,7 @@
 #include <string.h>
 #include <bpf/libbpf.h>
 #include "probe-event.h"
+#include "evlist.h"
 #include "debug.h"
 
 enum bpf_loader_errno {
@@ -24,10 +25,25 @@ enum bpf_loader_errno {
 	BPF_LOADER_ERRNO__PROLOGUE,	/* Failed to generate prologue */
 	BPF_LOADER_ERRNO__PROLOGUE2BIG,	/* Prologue too big for program */
 	BPF_LOADER_ERRNO__PROLOGUEOOB,	/* Offset out of bound for prologue */
+	BPF_LOADER_ERRNO__OBJCONF_OPT,	/* Invalid object config option */
+	BPF_LOADER_ERRNO__OBJCONF_CONF,	/* Config value not set (lost '=')) */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_OPT,	/* Invalid object map config option */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST,	/* Target map not exist */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE,	/* Incorrect value type for map */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE,	/* Incorrect map type */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE,	/* Incorrect map key size */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE,/* Incorrect map value size */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT,	/* Event not found for map setting */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE,	/* Invalid map size for event setting */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,	/* Event dimension too large */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH,	/* Doesn't support inherit event */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE,	/* Wrong event type for map */
+	BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG,	/* Index too large */
 	__BPF_LOADER_ERRNO__END,
 };
 
 struct bpf_object;
+struct parse_events_term;
 #define PERF_BPF_PROBE_GROUP "perf_bpf_probe"
 
 typedef int (*bpf_prog_iter_callback_t)(struct probe_trace_event *tev,
@@ -53,6 +69,16 @@ int bpf__strerror_load(struct bpf_object *obj, int err,
 		       char *buf, size_t size);
 int bpf__foreach_tev(struct bpf_object *obj,
 		     bpf_prog_iter_callback_t func, void *arg);
+
+int bpf__config_obj(struct bpf_object *obj, struct parse_events_term *term,
+		    struct perf_evlist *evlist, int *error_pos);
+int bpf__strerror_config_obj(struct bpf_object *obj,
+			     struct parse_events_term *term,
+			     struct perf_evlist *evlist,
+			     int *error_pos, int err, char *buf,
+			     size_t size);
+int bpf__apply_obj_config(void);
+int bpf__strerror_apply_obj_config(int err, char *buf, size_t size);
 #else
 static inline struct bpf_object *
 bpf__prepare_load(const char *filename __maybe_unused,
@@ -84,6 +110,21 @@ bpf__foreach_tev(struct bpf_object *obj __maybe_unused,
 }
 
 static inline int
+bpf__config_obj(struct bpf_object *obj __maybe_unused,
+		struct parse_events_term *term __maybe_unused,
+		struct perf_evlist *evlist __maybe_unused,
+		int *error_pos __maybe_unused)
+{
+	return 0;
+}
+
+static inline int
+bpf__apply_obj_config(void)
+{
+	return 0;
+}
+
+static inline int
 __bpf_strerror(char *buf, size_t size)
 {
 	if (!size)
@@ -118,5 +159,23 @@ static inline int bpf__strerror_load(struct bpf_object *obj __maybe_unused,
 {
 	return __bpf_strerror(buf, size);
 }
+
+static inline int
+bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
+			 struct parse_events_term *term __maybe_unused,
+			 struct perf_evlist *evlist __maybe_unused,
+			 int *error_pos __maybe_unused,
+			 int err __maybe_unused,
+			 char *buf, size_t size)
+{
+	return __bpf_strerror(buf, size);
+}
+
+static inline int
+bpf__strerror_apply_obj_config(int err __maybe_unused,
+			       char *buf, size_t size)
+{
+	return __bpf_strerror(buf, size);
+}
 #endif
 #endif
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 6a7e273a514a..f1479eeef7da 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -166,6 +166,50 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
 	return build_id__filename(build_id_hex, bf, size);
 }
 
+bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size)
+{
+	char *id_name, *ch;
+	struct stat sb;
+
+	id_name = dso__build_id_filename(dso, bf, size);
+	if (!id_name)
+		goto err;
+	if (access(id_name, F_OK))
+		goto err;
+	if (lstat(id_name, &sb) == -1)
+		goto err;
+	if ((size_t)sb.st_size > size - 1)
+		goto err;
+	if (readlink(id_name, bf, size - 1) < 0)
+		goto err;
+
+	bf[sb.st_size] = '\0';
+
+	/*
+	 * link should be:
+	 * ../../lib/modules/4.4.0-rc4/kernel/net/ipv4/netfilter/nf_nat_ipv4.ko/a09fe3eb3147dafa4e3b31dbd6257e4d696bdc92
+	 */
+	ch = strrchr(bf, '/');
+	if (!ch)
+		goto err;
+	if (ch - 3 < bf)
+		goto err;
+
+	return strncmp(".ko", ch - 3, 3) == 0;
+err:
+	/*
+	 * If dso__build_id_filename work, get id_name again,
+	 * because id_name points to bf and is broken.
+	 */
+	if (id_name)
+		id_name = dso__build_id_filename(dso, bf, size);
+	pr_err("Invalid build id: %s\n", id_name ? :
+					 dso->long_name ? :
+					 dso->short_name ? :
+					 "[unknown]");
+	return false;
+}
+
 #define dsos__for_each_with_build_id(pos, head)	\
 	list_for_each_entry(pos, head, node)	\
 		if (!pos->has_build_id)		\
@@ -211,6 +255,7 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
 	dsos__for_each_with_build_id(pos, &machine->dsos.head) {
 		const char *name;
 		size_t name_len;
+		bool in_kernel = false;
 
 		if (!pos->hit)
 			continue;
@@ -227,8 +272,11 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
 			name_len = pos->long_name_len + 1;
 		}
 
+		in_kernel = pos->kernel ||
+				is_kernel_module(name,
+					PERF_RECORD_MISC_CPUMODE_UNKNOWN);
 		err = write_buildid(name, name_len, pos->build_id, machine->pid,
-				    pos->kernel ? kmisc : umisc, fd);
+				    in_kernel ? kmisc : umisc, fd);
 		if (err)
 			break;
 	}
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 27a14a8a945b..64af3e20610d 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -16,6 +16,7 @@ int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id);
 int filename__sprintf_build_id(const char *pathname, char *sbuild_id);
 
 char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
+bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size);
 
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
 			   struct perf_sample *sample, struct perf_evsel *evsel,
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 07b5d63947b1..3ca453f0c51f 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -23,6 +23,8 @@
 #define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR"
 #define PERF_PAGER_ENVIRONMENT "PERF_PAGER"
 
+extern const char *config_exclusive_filename;
+
 typedef int (*config_fn_t)(const char *, const char *, void *);
 extern int perf_default_config(const char *, const char *, void *);
 extern int perf_config(config_fn_t fn, void *);
@@ -31,6 +33,7 @@ extern u64 perf_config_u64(const char *, const char *);
 extern int perf_config_bool(const char *, const char *);
 extern int config_error_nonbool(const char *);
 extern const char *perf_config_dirname(const char *, const char *);
+extern const char *perf_etc_perfconfig(void);
 
 char *alias_lookup(const char *alias);
 int split_cmdline(char *cmdline, const char ***argv);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 53c43eb9489e..24b4bd0d7754 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -416,7 +416,7 @@ create_child(struct callchain_node *parent, bool inherit_children)
 /*
  * Fill the node with callchain values
  */
-static void
+static int
 fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 {
 	struct callchain_cursor_node *cursor_node;
@@ -433,7 +433,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 		call = zalloc(sizeof(*call));
 		if (!call) {
 			perror("not enough memory for the code path tree");
-			return;
+			return -1;
 		}
 		call->ip = cursor_node->ip;
 		call->ms.sym = cursor_node->sym;
@@ -443,6 +443,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 		callchain_cursor_advance(cursor);
 		cursor_node = callchain_cursor_current(cursor);
 	}
+	return 0;
 }
 
 static struct callchain_node *
@@ -453,7 +454,19 @@ add_child(struct callchain_node *parent,
 	struct callchain_node *new;
 
 	new = create_child(parent, false);
-	fill_node(new, cursor);
+	if (new == NULL)
+		return NULL;
+
+	if (fill_node(new, cursor) < 0) {
+		struct callchain_list *call, *tmp;
+
+		list_for_each_entry_safe(call, tmp, &new->val, list) {
+			list_del(&call->list);
+			free(call);
+		}
+		free(new);
+		return NULL;
+	}
 
 	new->children_hit = 0;
 	new->hit = period;
@@ -462,16 +475,32 @@ add_child(struct callchain_node *parent,
 	return new;
 }
 
-static s64 match_chain(struct callchain_cursor_node *node,
-		      struct callchain_list *cnode)
+enum match_result {
+	MATCH_ERROR  = -1,
+	MATCH_EQ,
+	MATCH_LT,
+	MATCH_GT,
+};
+
+static enum match_result match_chain(struct callchain_cursor_node *node,
+				     struct callchain_list *cnode)
 {
 	struct symbol *sym = node->sym;
+	u64 left, right;
 
 	if (cnode->ms.sym && sym &&
-	    callchain_param.key == CCKEY_FUNCTION)
-		return cnode->ms.sym->start - sym->start;
-	else
-		return cnode->ip - node->ip;
+	    callchain_param.key == CCKEY_FUNCTION) {
+		left = cnode->ms.sym->start;
+		right = sym->start;
+	} else {
+		left = cnode->ip;
+		right = node->ip;
+	}
+
+	if (left == right)
+		return MATCH_EQ;
+
+	return left > right ? MATCH_GT : MATCH_LT;
 }
 
 /*
@@ -479,7 +508,7 @@ static s64 match_chain(struct callchain_cursor_node *node,
  * give a part of its callchain to the created child.
  * Then create another child to host the given callchain of new branch
  */
-static void
+static int
 split_add_child(struct callchain_node *parent,
 		struct callchain_cursor *cursor,
 		struct callchain_list *to_split,
@@ -491,6 +520,8 @@ split_add_child(struct callchain_node *parent,
 
 	/* split */
 	new = create_child(parent, true);
+	if (new == NULL)
+		return -1;
 
 	/* split the callchain and move a part to the new child */
 	old_tail = parent->val.prev;
@@ -524,6 +555,8 @@ split_add_child(struct callchain_node *parent,
 
 		node = callchain_cursor_current(cursor);
 		new = add_child(parent, cursor, period);
+		if (new == NULL)
+			return -1;
 
 		/*
 		 * This is second child since we moved parent's children
@@ -534,7 +567,7 @@ split_add_child(struct callchain_node *parent,
 		cnode = list_first_entry(&first->val, struct callchain_list,
 					 list);
 
-		if (match_chain(node, cnode) < 0)
+		if (match_chain(node, cnode) == MATCH_LT)
 			pp = &p->rb_left;
 		else
 			pp = &p->rb_right;
@@ -545,14 +578,15 @@ split_add_child(struct callchain_node *parent,
 		parent->hit = period;
 		parent->count = 1;
 	}
+	return 0;
 }
 
-static int
+static enum match_result
 append_chain(struct callchain_node *root,
 	     struct callchain_cursor *cursor,
 	     u64 period);
 
-static void
+static int
 append_chain_children(struct callchain_node *root,
 		      struct callchain_cursor *cursor,
 		      u64 period)
@@ -564,36 +598,42 @@ append_chain_children(struct callchain_node *root,
 
 	node = callchain_cursor_current(cursor);
 	if (!node)
-		return;
+		return -1;
 
 	/* lookup in childrens */
 	while (*p) {
-		s64 ret;
+		enum match_result ret;
 
 		parent = *p;
 		rnode = rb_entry(parent, struct callchain_node, rb_node_in);
 
 		/* If at least first entry matches, rely to children */
 		ret = append_chain(rnode, cursor, period);
-		if (ret == 0)
+		if (ret == MATCH_EQ)
 			goto inc_children_hit;
+		if (ret == MATCH_ERROR)
+			return -1;
 
-		if (ret < 0)
+		if (ret == MATCH_LT)
 			p = &parent->rb_left;
 		else
 			p = &parent->rb_right;
 	}
 	/* nothing in children, add to the current node */
 	rnode = add_child(root, cursor, period);
+	if (rnode == NULL)
+		return -1;
+
 	rb_link_node(&rnode->rb_node_in, parent, p);
 	rb_insert_color(&rnode->rb_node_in, &root->rb_root_in);
 
 inc_children_hit:
 	root->children_hit += period;
 	root->children_count++;
+	return 0;
 }
 
-static int
+static enum match_result
 append_chain(struct callchain_node *root,
 	     struct callchain_cursor *cursor,
 	     u64 period)
@@ -602,7 +642,7 @@ append_chain(struct callchain_node *root,
 	u64 start = cursor->pos;
 	bool found = false;
 	u64 matches;
-	int cmp = 0;
+	enum match_result cmp = MATCH_ERROR;
 
 	/*
 	 * Lookup in the current node
@@ -618,7 +658,7 @@ append_chain(struct callchain_node *root,
 			break;
 
 		cmp = match_chain(node, cnode);
-		if (cmp)
+		if (cmp != MATCH_EQ)
 			break;
 
 		found = true;
@@ -628,7 +668,7 @@ append_chain(struct callchain_node *root,
 
 	/* matches not, relay no the parent */
 	if (!found) {
-		WARN_ONCE(!cmp, "Chain comparison error\n");
+		WARN_ONCE(cmp == MATCH_ERROR, "Chain comparison error\n");
 		return cmp;
 	}
 
@@ -636,21 +676,25 @@ append_chain(struct callchain_node *root,
 
 	/* we match only a part of the node. Split it and add the new chain */
 	if (matches < root->val_nr) {
-		split_add_child(root, cursor, cnode, start, matches, period);
-		return 0;
+		if (split_add_child(root, cursor, cnode, start, matches,
+				    period) < 0)
+			return MATCH_ERROR;
+
+		return MATCH_EQ;
 	}
 
 	/* we match 100% of the path, increment the hit */
 	if (matches == root->val_nr && cursor->pos == cursor->nr) {
 		root->hit += period;
 		root->count++;
-		return 0;
+		return MATCH_EQ;
 	}
 
 	/* We match the node and still have a part remaining */
-	append_chain_children(root, cursor, period);
+	if (append_chain_children(root, cursor, period) < 0)
+		return MATCH_ERROR;
 
-	return 0;
+	return MATCH_EQ;
 }
 
 int callchain_append(struct callchain_root *root,
@@ -662,7 +706,8 @@ int callchain_append(struct callchain_root *root,
 
 	callchain_cursor_commit(cursor);
 
-	append_chain_children(&root->node, cursor, period);
+	if (append_chain_children(&root->node, cursor, period) < 0)
+		return -1;
 
 	if (cursor->nr > root->max_depth)
 		root->max_depth = cursor->nr;
@@ -690,7 +735,8 @@ merge_chain_branch(struct callchain_cursor *cursor,
 
 	if (src->hit) {
 		callchain_cursor_commit(cursor);
-		append_chain_children(dst, cursor, src->hit);
+		if (append_chain_children(dst, cursor, src->hit) < 0)
+			return -1;
 	}
 
 	n = rb_first(&src->rb_root_in);
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index e5fb88bab9e1..43e84aa27e4a 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -32,14 +32,15 @@ int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty)
 	return 0;
 }
 
-int perf_color_default_config(const char *var, const char *value, void *cb)
+int perf_color_default_config(const char *var, const char *value,
+			      void *cb __maybe_unused)
 {
 	if (!strcmp(var, "color.ui")) {
 		perf_use_color_default = perf_config_colorbool(var, value, -1);
 		return 0;
 	}
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 static int __color_vsnprintf(char *bf, size_t size, const char *color,
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index d3e12e30e1d5..4e727635476e 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -26,7 +26,7 @@ static const char *config_file_name;
 static int config_linenr;
 static int config_file_eof;
 
-static const char *config_exclusive_filename;
+const char *config_exclusive_filename;
 
 static int get_next_char(void)
 {
@@ -434,7 +434,7 @@ static int perf_config_from_file(config_fn_t fn, const char *filename, void *dat
 	return ret;
 }
 
-static const char *perf_etc_perfconfig(void)
+const char *perf_etc_perfconfig(void)
 {
 	static const char *system_wide;
 	if (!system_wide)
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index fa935093a599..9bcf2bed3a6d 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -8,6 +8,10 @@
 #include <linux/bitmap.h>
 #include "asm/bug.h"
 
+static int max_cpu_num;
+static int max_node_num;
+static int *cpunode_map;
+
 static struct cpu_map *cpu_map__default_new(void)
 {
 	struct cpu_map *cpus;
@@ -486,6 +490,32 @@ out:
 		pr_err("Failed to read max nodes, using default of %d\n", max_node_num);
 }
 
+int cpu__max_node(void)
+{
+	if (unlikely(!max_node_num))
+		set_max_node_num();
+
+	return max_node_num;
+}
+
+int cpu__max_cpu(void)
+{
+	if (unlikely(!max_cpu_num))
+		set_max_cpu_num();
+
+	return max_cpu_num;
+}
+
+int cpu__get_node(int cpu)
+{
+	if (unlikely(cpunode_map == NULL)) {
+		pr_debug("cpu_map not initialized\n");
+		return -1;
+	}
+
+	return cpunode_map[cpu];
+}
+
 static int init_cpunode_map(void)
 {
 	int i;
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 71c41b9efabb..81a2562aaa2b 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -57,37 +57,11 @@ static inline bool cpu_map__empty(const struct cpu_map *map)
 	return map ? map->map[0] == -1 : true;
 }
 
-int max_cpu_num;
-int max_node_num;
-int *cpunode_map;
-
 int cpu__setup_cpunode_map(void);
 
-static inline int cpu__max_node(void)
-{
-	if (unlikely(!max_node_num))
-		pr_debug("cpu_map not initialized\n");
-
-	return max_node_num;
-}
-
-static inline int cpu__max_cpu(void)
-{
-	if (unlikely(!max_cpu_num))
-		pr_debug("cpu_map not initialized\n");
-
-	return max_cpu_num;
-}
-
-static inline int cpu__get_node(int cpu)
-{
-	if (unlikely(cpunode_map == NULL)) {
-		pr_debug("cpu_map not initialized\n");
-		return -1;
-	}
-
-	return cpunode_map[cpu];
-}
+int cpu__max_node(void);
+int cpu__max_cpu(void);
+int cpu__get_node(int cpu);
 
 int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
 		       int (*f)(struct cpu_map *map, int cpu, void *data),
diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c
index aada3ac5e891..d4a5a21c2a7e 100644
--- a/tools/perf/util/ctype.c
+++ b/tools/perf/util/ctype.c
@@ -32,8 +32,17 @@ unsigned char sane_ctype[256] = {
 
 const char *graph_line =
 	"_____________________________________________________________________"
+	"_____________________________________________________________________"
 	"_____________________________________________________________________";
 const char *graph_dotted_line =
 	"---------------------------------------------------------------------"
 	"---------------------------------------------------------------------"
 	"---------------------------------------------------------------------";
+const char *spaces =
+	"                                                                     "
+	"                                                                     "
+	"                                                                     ";
+const char *dots =
+	"....................................................................."
+	"....................................................................."
+	".....................................................................";
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 34cd1e4039d3..811af89ce0bb 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -352,6 +352,84 @@ static int add_tracepoint_values(struct ctf_writer *cw,
 	return ret;
 }
 
+static int
+add_bpf_output_values(struct bt_ctf_event_class *event_class,
+		      struct bt_ctf_event *event,
+		      struct perf_sample *sample)
+{
+	struct bt_ctf_field_type *len_type, *seq_type;
+	struct bt_ctf_field *len_field, *seq_field;
+	unsigned int raw_size = sample->raw_size;
+	unsigned int nr_elements = raw_size / sizeof(u32);
+	unsigned int i;
+	int ret;
+
+	if (nr_elements * sizeof(u32) != raw_size)
+		pr_warning("Incorrect raw_size (%u) in bpf output event, skip %lu bytes\n",
+			   raw_size, nr_elements * sizeof(u32) - raw_size);
+
+	len_type = bt_ctf_event_class_get_field_by_name(event_class, "raw_len");
+	len_field = bt_ctf_field_create(len_type);
+	if (!len_field) {
+		pr_err("failed to create 'raw_len' for bpf output event\n");
+		ret = -1;
+		goto put_len_type;
+	}
+
+	ret = bt_ctf_field_unsigned_integer_set_value(len_field, nr_elements);
+	if (ret) {
+		pr_err("failed to set field value for raw_len\n");
+		goto put_len_field;
+	}
+	ret = bt_ctf_event_set_payload(event, "raw_len", len_field);
+	if (ret) {
+		pr_err("failed to set payload to raw_len\n");
+		goto put_len_field;
+	}
+
+	seq_type = bt_ctf_event_class_get_field_by_name(event_class, "raw_data");
+	seq_field = bt_ctf_field_create(seq_type);
+	if (!seq_field) {
+		pr_err("failed to create 'raw_data' for bpf output event\n");
+		ret = -1;
+		goto put_seq_type;
+	}
+
+	ret = bt_ctf_field_sequence_set_length(seq_field, len_field);
+	if (ret) {
+		pr_err("failed to set length of 'raw_data'\n");
+		goto put_seq_field;
+	}
+
+	for (i = 0; i < nr_elements; i++) {
+		struct bt_ctf_field *elem_field =
+			bt_ctf_field_sequence_get_field(seq_field, i);
+
+		ret = bt_ctf_field_unsigned_integer_set_value(elem_field,
+				((u32 *)(sample->raw_data))[i]);
+
+		bt_ctf_field_put(elem_field);
+		if (ret) {
+			pr_err("failed to set raw_data[%d]\n", i);
+			goto put_seq_field;
+		}
+	}
+
+	ret = bt_ctf_event_set_payload(event, "raw_data", seq_field);
+	if (ret)
+		pr_err("failed to set payload for raw_data\n");
+
+put_seq_field:
+	bt_ctf_field_put(seq_field);
+put_seq_type:
+	bt_ctf_field_type_put(seq_type);
+put_len_field:
+	bt_ctf_field_put(len_field);
+put_len_type:
+	bt_ctf_field_type_put(len_type);
+	return ret;
+}
+
 static int add_generic_values(struct ctf_writer *cw,
 			      struct bt_ctf_event *event,
 			      struct perf_evsel *evsel,
@@ -597,6 +675,12 @@ static int process_sample_event(struct perf_tool *tool,
 			return -1;
 	}
 
+	if (perf_evsel__is_bpf_output(evsel)) {
+		ret = add_bpf_output_values(event_class, event, sample);
+		if (ret)
+			return -1;
+	}
+
 	cs = ctf_stream(cw, get_sample_cpu(cw, sample, evsel));
 	if (cs) {
 		if (is_flush_needed(cs))
@@ -744,6 +828,25 @@ static int add_tracepoint_types(struct ctf_writer *cw,
 	return ret;
 }
 
+static int add_bpf_output_types(struct ctf_writer *cw,
+				struct bt_ctf_event_class *class)
+{
+	struct bt_ctf_field_type *len_type = cw->data.u32;
+	struct bt_ctf_field_type *seq_base_type = cw->data.u32_hex;
+	struct bt_ctf_field_type *seq_type;
+	int ret;
+
+	ret = bt_ctf_event_class_add_field(class, len_type, "raw_len");
+	if (ret)
+		return ret;
+
+	seq_type = bt_ctf_field_type_sequence_create(seq_base_type, "raw_len");
+	if (!seq_type)
+		return -1;
+
+	return bt_ctf_event_class_add_field(class, seq_type, "raw_data");
+}
+
 static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
 			     struct bt_ctf_event_class *event_class)
 {
@@ -755,7 +858,8 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
 	 *                              ctf event header
 	 *   PERF_SAMPLE_READ         - TODO
 	 *   PERF_SAMPLE_CALLCHAIN    - TODO
-	 *   PERF_SAMPLE_RAW          - tracepoint fields are handled separately
+	 *   PERF_SAMPLE_RAW          - tracepoint fields and BPF output
+	 *                              are handled separately
 	 *   PERF_SAMPLE_BRANCH_STACK - TODO
 	 *   PERF_SAMPLE_REGS_USER    - TODO
 	 *   PERF_SAMPLE_STACK_USER   - TODO
@@ -824,6 +928,12 @@ static int add_event(struct ctf_writer *cw, struct perf_evsel *evsel)
 			goto err;
 	}
 
+	if (perf_evsel__is_bpf_output(evsel)) {
+		ret = add_bpf_output_types(cw, event_class);
+		if (ret)
+			goto err;
+	}
+
 	ret = bt_ctf_stream_class_add_event_class(cw->stream_class, event_class);
 	if (ret) {
 		pr("Failed to add event class into stream.\n");
@@ -858,6 +968,23 @@ static int setup_events(struct ctf_writer *cw, struct perf_session *session)
 	return 0;
 }
 
+static void cleanup_events(struct perf_session *session)
+{
+	struct perf_evlist *evlist = session->evlist;
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		struct evsel_priv *priv;
+
+		priv = evsel->priv;
+		bt_ctf_event_class_put(priv->event_class);
+		zfree(&evsel->priv);
+	}
+
+	perf_evlist__delete(evlist);
+	session->evlist = NULL;
+}
+
 static int setup_streams(struct ctf_writer *cw, struct perf_session *session)
 {
 	struct ctf_stream **stream;
@@ -953,6 +1080,12 @@ static struct bt_ctf_field_type *create_int_type(int size, bool sign, bool hex)
 	    bt_ctf_field_type_integer_set_base(type, BT_CTF_INTEGER_BASE_HEXADECIMAL))
 		goto err;
 
+#if __BYTE_ORDER == __BIG_ENDIAN
+	bt_ctf_field_type_set_byte_order(type, BT_CTF_BYTE_ORDER_BIG_ENDIAN);
+#else
+	bt_ctf_field_type_set_byte_order(type, BT_CTF_BYTE_ORDER_LITTLE_ENDIAN);
+#endif
+
 	pr2("Created type: INTEGER %d-bit %ssigned %s\n",
 	    size, sign ? "un" : "", hex ? "hex" : "");
 	return type;
@@ -1100,7 +1233,7 @@ static int convert__config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 int bt_convert__perf2ctf(const char *input, const char *path, bool force)
@@ -1171,6 +1304,7 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 		(double) c.events_size / 1024.0 / 1024.0,
 		c.events_count);
 
+	cleanup_events(session);
 	perf_session__delete(session);
 	ctf_writer__cleanup(cw);
 
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 86d9c7302598..8c4212abd19b 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -5,6 +5,7 @@
 #include <string.h>
 #include <stdarg.h>
 #include <stdio.h>
+#include <api/debug.h>
 
 #include "cache.h"
 #include "color.h"
@@ -22,7 +23,7 @@ int debug_ordered_events;
 static int redirect_to_stderr;
 int debug_data_convert;
 
-static int _eprintf(int level, int var, const char *fmt, va_list args)
+int veprintf(int level, int var, const char *fmt, va_list args)
 {
 	int ret = 0;
 
@@ -36,24 +37,19 @@ static int _eprintf(int level, int var, const char *fmt, va_list args)
 	return ret;
 }
 
-int veprintf(int level, int var, const char *fmt, va_list args)
-{
-	return _eprintf(level, var, fmt, args);
-}
-
 int eprintf(int level, int var, const char *fmt, ...)
 {
 	va_list args;
 	int ret;
 
 	va_start(args, fmt);
-	ret = _eprintf(level, var, fmt, args);
+	ret = veprintf(level, var, fmt, args);
 	va_end(args);
 
 	return ret;
 }
 
-static int __eprintf_time(u64 t, const char *fmt, va_list args)
+static int veprintf_time(u64 t, const char *fmt, va_list args)
 {
 	int ret = 0;
 	u64 secs, usecs, nsecs = t;
@@ -75,7 +71,7 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...)
 
 	if (var >= level) {
 		va_start(args, fmt);
-		ret = __eprintf_time(t, fmt, args);
+		ret = veprintf_time(t, fmt, args);
 		va_end(args);
 	}
 
@@ -91,7 +87,7 @@ void pr_stat(const char *fmt, ...)
 	va_list args;
 
 	va_start(args, fmt);
-	_eprintf(1, verbose, fmt, args);
+	veprintf(1, verbose, fmt, args);
 	va_end(args);
 	eprintf(1, verbose, "\n");
 }
@@ -110,40 +106,61 @@ int dump_printf(const char *fmt, ...)
 	return ret;
 }
 
+static void trace_event_printer(enum binary_printer_ops op,
+				unsigned int val, void *extra)
+{
+	const char *color = PERF_COLOR_BLUE;
+	union perf_event *event = (union perf_event *)extra;
+	unsigned char ch = (unsigned char)val;
+
+	switch (op) {
+	case BINARY_PRINT_DATA_BEGIN:
+		printf(".");
+		color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n",
+				event->header.size);
+		break;
+	case BINARY_PRINT_LINE_BEGIN:
+		printf(".");
+		break;
+	case BINARY_PRINT_ADDR:
+		color_fprintf(stdout, color, "  %04x: ", val);
+		break;
+	case BINARY_PRINT_NUM_DATA:
+		color_fprintf(stdout, color, " %02x", val);
+		break;
+	case BINARY_PRINT_NUM_PAD:
+		color_fprintf(stdout, color, "   ");
+		break;
+	case BINARY_PRINT_SEP:
+		color_fprintf(stdout, color, "  ");
+		break;
+	case BINARY_PRINT_CHAR_DATA:
+		color_fprintf(stdout, color, "%c",
+			      isprint(ch) ? ch : '.');
+		break;
+	case BINARY_PRINT_CHAR_PAD:
+		color_fprintf(stdout, color, " ");
+		break;
+	case BINARY_PRINT_LINE_END:
+		color_fprintf(stdout, color, "\n");
+		break;
+	case BINARY_PRINT_DATA_END:
+		printf("\n");
+		break;
+	default:
+		break;
+	}
+}
+
 void trace_event(union perf_event *event)
 {
 	unsigned char *raw_event = (void *)event;
-	const char *color = PERF_COLOR_BLUE;
-	int i, j;
 
 	if (!dump_trace)
 		return;
 
-	printf(".");
-	color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n",
-		      event->header.size);
-
-	for (i = 0; i < event->header.size; i++) {
-		if ((i & 15) == 0) {
-			printf(".");
-			color_fprintf(stdout, color, "  %04x: ", i);
-		}
-
-		color_fprintf(stdout, color, " %02x", raw_event[i]);
-
-		if (((i & 15) == 15) || i == event->header.size-1) {
-			color_fprintf(stdout, color, "  ");
-			for (j = 0; j < 15-(i & 15); j++)
-				color_fprintf(stdout, color, "   ");
-			for (j = i & ~15; j <= i; j++) {
-				color_fprintf(stdout, color, "%c",
-					      isprint(raw_event[j]) ?
-					      raw_event[j] : '.');
-			}
-			color_fprintf(stdout, color, "\n");
-		}
-	}
-	printf(".\n");
+	print_binary(raw_event, event->header.size, 16,
+		     trace_event_printer, event);
 }
 
 static struct debug_variable {
@@ -192,3 +209,23 @@ int perf_debug_option(const char *str)
 	free(s);
 	return 0;
 }
+
+#define DEBUG_WRAPPER(__n, __l)				\
+static int pr_ ## __n ## _wrapper(const char *fmt, ...)	\
+{							\
+	va_list args;					\
+	int ret;					\
+							\
+	va_start(args, fmt);				\
+	ret = veprintf(__l, verbose, fmt, args);	\
+	va_end(args);					\
+	return ret;					\
+}
+
+DEBUG_WRAPPER(warning, 0);
+DEBUG_WRAPPER(debug, 1);
+
+void perf_debug_setup(void)
+{
+	libapi_set_print(pr_warning_wrapper, pr_warning_wrapper, pr_debug_wrapper);
+}
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 8b9a088c32ab..14bafda79eda 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -53,5 +53,6 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__(
 int veprintf(int level, int var, const char *fmt, va_list args);
 
 int perf_debug_option(const char *str);
+void perf_debug_setup(void);
 
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c
new file mode 100644
index 000000000000..3e6062ab2cdd
--- /dev/null
+++ b/tools/perf/util/demangle-java.c
@@ -0,0 +1,199 @@
+#include <sys/types.h>
+#include <stdio.h>
+#include <string.h>
+#include "util.h"
+#include "debug.h"
+#include "symbol.h"
+
+#include "demangle-java.h"
+
+enum {
+	MODE_PREFIX = 0,
+	MODE_CLASS  = 1,
+	MODE_FUNC   = 2,
+	MODE_TYPE   = 3,
+	MODE_CTYPE  = 3, /* class arg */
+};
+
+#define BASE_ENT(c, n)	[c - 'A']=n
+static const char *base_types['Z' - 'A' + 1] = {
+	BASE_ENT('B', "byte" ),
+	BASE_ENT('C', "char" ),
+	BASE_ENT('D', "double" ),
+	BASE_ENT('F', "float" ),
+	BASE_ENT('I', "int" ),
+	BASE_ENT('J', "long" ),
+	BASE_ENT('S', "short" ),
+	BASE_ENT('Z', "bool" ),
+};
+
+/*
+ * demangle Java symbol between str and end positions and stores
+ * up to maxlen characters into buf. The parser starts in mode.
+ *
+ * Use MODE_PREFIX to process entire prototype till end position
+ * Use MODE_TYPE to process return type if str starts on return type char
+ *
+ *  Return:
+ *	success: buf
+ *	error  : NULL
+ */
+static char *
+__demangle_java_sym(const char *str, const char *end, char *buf, int maxlen, int mode)
+{
+	int rlen = 0;
+	int array = 0;
+	int narg = 0;
+	const char *q;
+
+	if (!end)
+		end = str + strlen(str);
+
+	for (q = str; q != end; q++) {
+
+		if (rlen == (maxlen - 1))
+			break;
+
+		switch (*q) {
+		case 'L':
+			if (mode == MODE_PREFIX || mode == MODE_CTYPE) {
+				if (mode == MODE_CTYPE) {
+					if (narg)
+						rlen += scnprintf(buf + rlen, maxlen - rlen, ", ");
+					narg++;
+				}
+				rlen += scnprintf(buf + rlen, maxlen - rlen, "class ");
+				if (mode == MODE_PREFIX)
+					mode = MODE_CLASS;
+			} else
+				buf[rlen++] = *q;
+			break;
+		case 'B':
+		case 'C':
+		case 'D':
+		case 'F':
+		case 'I':
+		case 'J':
+		case 'S':
+		case 'Z':
+			if (mode == MODE_TYPE) {
+				if (narg)
+					rlen += scnprintf(buf + rlen, maxlen - rlen, ", ");
+				rlen += scnprintf(buf + rlen, maxlen - rlen, "%s", base_types[*q - 'A']);
+				while (array--)
+					rlen += scnprintf(buf + rlen, maxlen - rlen, "[]");
+				array = 0;
+				narg++;
+			} else
+				buf[rlen++] = *q;
+			break;
+		case 'V':
+			if (mode == MODE_TYPE) {
+				rlen += scnprintf(buf + rlen, maxlen - rlen, "void");
+				while (array--)
+					rlen += scnprintf(buf + rlen, maxlen - rlen, "[]");
+				array = 0;
+			} else
+				buf[rlen++] = *q;
+			break;
+		case '[':
+			if (mode != MODE_TYPE)
+				goto error;
+			array++;
+			break;
+		case '(':
+			if (mode != MODE_FUNC)
+				goto error;
+			buf[rlen++] = *q;
+			mode = MODE_TYPE;
+			break;
+		case ')':
+			if (mode != MODE_TYPE)
+				goto error;
+			buf[rlen++] = *q;
+			narg = 0;
+			break;
+		case ';':
+			if (mode != MODE_CLASS && mode != MODE_CTYPE)
+				goto error;
+			/* safe because at least one other char to process */
+			if (isalpha(*(q + 1)))
+				rlen += scnprintf(buf + rlen, maxlen - rlen, ".");
+			if (mode == MODE_CLASS)
+				mode = MODE_FUNC;
+			else if (mode == MODE_CTYPE)
+				mode = MODE_TYPE;
+			break;
+		case '/':
+			if (mode != MODE_CLASS && mode != MODE_CTYPE)
+				goto error;
+			rlen += scnprintf(buf + rlen, maxlen - rlen, ".");
+			break;
+		default :
+			buf[rlen++] = *q;
+		}
+	}
+	buf[rlen] = '\0';
+	return buf;
+error:
+	return NULL;
+}
+
+/*
+ * Demangle Java function signature (openJDK, not GCJ)
+ * input:
+ * 	str: string to parse. String is not modified
+ *    flags: comobination of JAVA_DEMANGLE_* flags to modify demangling
+ * return:
+ *	if input can be demangled, then a newly allocated string is returned.
+ *	if input cannot be demangled, then NULL is returned
+ *
+ * Note: caller is responsible for freeing demangled string
+ */
+char *
+java_demangle_sym(const char *str, int flags)
+{
+	char *buf, *ptr;
+	char *p;
+	size_t len, l1 = 0;
+
+	if (!str)
+		return NULL;
+
+	/* find start of retunr type */
+	p = strrchr(str, ')');
+	if (!p)
+		return NULL;
+
+	/*
+	 * expansion factor estimated to 3x
+	 */
+	len = strlen(str) * 3 + 1;
+	buf = malloc(len);
+	if (!buf)
+		return NULL;
+
+	buf[0] = '\0';
+	if (!(flags & JAVA_DEMANGLE_NORET)) {
+		/*
+		 * get return type first
+		 */
+		ptr = __demangle_java_sym(p + 1, NULL, buf, len, MODE_TYPE);
+		if (!ptr)
+			goto error;
+
+		/* add space between return type and function prototype */
+		l1 = strlen(buf);
+		buf[l1++] = ' ';
+	}
+
+	/* process function up to return type */
+	ptr = __demangle_java_sym(str, p + 1, buf + l1, len - l1, MODE_PREFIX);
+	if (!ptr)
+		goto error;
+
+	return buf;
+error:
+	free(buf);
+	return NULL;
+}
diff --git a/tools/perf/util/demangle-java.h b/tools/perf/util/demangle-java.h
new file mode 100644
index 000000000000..a981c1f968fe
--- /dev/null
+++ b/tools/perf/util/demangle-java.h
@@ -0,0 +1,10 @@
+#ifndef __PERF_DEMANGLE_JAVA
+#define __PERF_DEMANGLE_JAVA 1
+/*
+ * demangle function flags
+ */
+#define JAVA_DEMANGLE_NORET	0x1 /* do not process return type */
+
+char * java_demangle_sym(const char *str, int flags);
+
+#endif /* __PERF_DEMANGLE_JAVA */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index e8e9a9dbf5e3..8e6395439ca0 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -52,6 +52,11 @@ int dso__read_binary_type_filename(const struct dso *dso,
 			debuglink--;
 		if (*debuglink == '/')
 			debuglink++;
+
+		ret = -1;
+		if (!is_regular_file(filename))
+			break;
+
 		ret = filename__read_debuglink(filename, debuglink,
 					       size - (debuglink - filename));
 		}
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 7dd5939dea2e..49a11d9d8b8f 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -6,6 +6,8 @@ struct perf_env perf_env;
 
 void perf_env__exit(struct perf_env *env)
 {
+	int i;
+
 	zfree(&env->hostname);
 	zfree(&env->os_release);
 	zfree(&env->version);
@@ -19,6 +21,10 @@ void perf_env__exit(struct perf_env *env)
 	zfree(&env->numa_nodes);
 	zfree(&env->pmu_mappings);
 	zfree(&env->cpu);
+
+	for (i = 0; i < env->caches_cnt; i++)
+		cpu_cache_level__free(&env->caches[i]);
+	zfree(&env->caches);
 }
 
 int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
@@ -75,3 +81,10 @@ int perf_env__read_cpu_topology_map(struct perf_env *env)
 	env->nr_cpus_avail = nr_cpus;
 	return 0;
 }
+
+void cpu_cache_level__free(struct cpu_cache_level *cache)
+{
+	free(cache->type);
+	free(cache->map);
+	free(cache->size);
+}
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 0132b9557c02..56cffb60a0b4 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -1,11 +1,23 @@
 #ifndef __PERF_ENV_H
 #define __PERF_ENV_H
 
+#include <linux/types.h>
+
 struct cpu_topology_map {
 	int	socket_id;
 	int	core_id;
 };
 
+struct cpu_cache_level {
+	u32	level;
+	u32	line_size;
+	u32	sets;
+	u32	ways;
+	char	*type;
+	char	*size;
+	char	*map;
+};
+
 struct perf_env {
 	char			*hostname;
 	char			*os_release;
@@ -31,6 +43,8 @@ struct perf_env {
 	char			*numa_nodes;
 	char			*pmu_mappings;
 	struct cpu_topology_map	*cpu;
+	struct cpu_cache_level	*caches;
+	int			 caches_cnt;
 };
 
 extern struct perf_env perf_env;
@@ -41,4 +55,5 @@ int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]);
 
 int perf_env__read_cpu_topology_map(struct perf_env *env);
 
+void cpu_cache_level__free(struct cpu_cache_level *cache);
 #endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 85155e91b61b..7bad5c3fa7b7 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -282,7 +282,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		strcpy(execname, "");
 
 		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n",
+		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %[^\n]\n",
 		       &event->mmap2.start, &event->mmap2.len, prot,
 		       &event->mmap2.pgoff, &event->mmap2.maj,
 		       &event->mmap2.min,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d81f13de2476..86a03836a83f 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1181,12 +1181,12 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus,
 	 */
 	if (cpus != evlist->cpus) {
 		cpu_map__put(evlist->cpus);
-		evlist->cpus = cpus;
+		evlist->cpus = cpu_map__get(cpus);
 	}
 
 	if (threads != evlist->threads) {
 		thread_map__put(evlist->threads);
-		evlist->threads = threads;
+		evlist->threads = thread_map__get(threads);
 	}
 
 	perf_evlist__propagate_maps(evlist);
@@ -1223,6 +1223,9 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
 	int err = 0;
 
 	evlist__for_each(evlist, evsel) {
+		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+			continue;
+
 		err = perf_evsel__set_filter(evsel, filter);
 		if (err)
 			break;
@@ -1624,7 +1627,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
 	return printed + fprintf(fp, "\n");
 }
 
-int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
+int perf_evlist__strerror_open(struct perf_evlist *evlist,
 			       int err, char *buf, size_t size)
 {
 	int printed, value;
@@ -1652,7 +1655,25 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
 				    "Hint:\tTry: 'sudo sh -c \"echo -1 > /proc/sys/kernel/perf_event_paranoid\"'\n"
 				    "Hint:\tThe current value is %d.", value);
 		break;
+	case EINVAL: {
+		struct perf_evsel *first = perf_evlist__first(evlist);
+		int max_freq;
+
+		if (sysctl__read_int("kernel/perf_event_max_sample_rate", &max_freq) < 0)
+			goto out_default;
+
+		if (first->attr.sample_freq < (u64)max_freq)
+			goto out_default;
+
+		printed = scnprintf(buf, size,
+				    "Error:\t%s.\n"
+				    "Hint:\tCheck /proc/sys/kernel/perf_event_max_sample_rate.\n"
+				    "Hint:\tThe current value is %d and %" PRIu64 " is being requested.",
+				    emsg, max_freq, first->attr.sample_freq);
+		break;
+	}
 	default:
+out_default:
 		scnprintf(buf, size, "%s", emsg);
 		break;
 	}
@@ -1723,3 +1744,19 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 
 	tracking_evsel->tracking = true;
 }
+
+struct perf_evsel *
+perf_evlist__find_evsel_by_str(struct perf_evlist *evlist,
+			       const char *str)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		if (!evsel->name)
+			continue;
+		if (strcmp(str, evsel->name) == 0)
+			return evsel;
+	}
+
+	return NULL;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 7c4d9a206776..a0d15221db6e 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -294,4 +294,7 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 				     struct perf_evsel *tracking_evsel);
 
 void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
+
+struct perf_evsel *
+perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index cdbaf9b51e42..0902fe418754 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -225,6 +225,11 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 	if (evsel != NULL)
 		perf_evsel__init(evsel, attr, idx);
 
+	if (perf_evsel__is_bpf_output(evsel)) {
+		evsel->attr.sample_type |= PERF_SAMPLE_RAW;
+		evsel->attr.sample_period = 1;
+	}
+
 	return evsel;
 }
 
@@ -898,6 +903,16 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	if (evsel->precise_max)
 		perf_event_attr__set_max_precise_ip(attr);
 
+	if (opts->all_user) {
+		attr->exclude_kernel = 1;
+		attr->exclude_user   = 0;
+	}
+
+	if (opts->all_kernel) {
+		attr->exclude_kernel = 0;
+		attr->exclude_user   = 1;
+	}
+
 	/*
 	 * Apply event specific term settings,
 	 * it overloads any global configuration.
@@ -2362,12 +2377,15 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 	case EPERM:
 	case EACCES:
 		return scnprintf(msg, size,
-		 "You may not have permission to collect %sstats.\n"
-		 "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
-		 " -1 - Not paranoid at all\n"
-		 "  0 - Disallow raw tracepoint access for unpriv\n"
-		 "  1 - Disallow cpu events for unpriv\n"
-		 "  2 - Disallow kernel profiling for unpriv",
+		 "You may not have permission to collect %sstats.\n\n"
+		 "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n"
+		 "which controls use of the performance events system by\n"
+		 "unprivileged users (without CAP_SYS_ADMIN).\n\n"
+		 "The default value is 1:\n\n"
+		 "  -1: Allow use of (almost) all events by all users\n"
+		 ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n"
+		 ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n"
+		 ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN",
 				 target->system_wide ? "system-wide " : "");
 	case ENOENT:
 		return scnprintf(msg, size, "The %s event is not supported.",
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 8e75434bd01c..501ea6e565f1 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -93,10 +93,8 @@ struct perf_evsel {
 	const char		*unit;
 	struct event_format	*tp_format;
 	off_t			id_offset;
-	union {
-		void		*priv;
-		u64		db_id;
-	};
+	void			*priv;
+	u64			db_id;
 	struct cgroup_sel	*cgrp;
 	void			*handler;
 	struct cpu_map		*cpus;
@@ -364,6 +362,14 @@ static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel)
 #undef FUNCTION_EVENT
 }
 
+static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+
+	return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) &&
+		(attr->type == PERF_TYPE_SOFTWARE);
+}
+
 struct perf_attr_details {
 	bool freq;
 	bool verbose;
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
new file mode 100644
index 000000000000..c1ef805c6a8f
--- /dev/null
+++ b/tools/perf/util/genelf.c
@@ -0,0 +1,449 @@
+/*
+ * genelf.c
+ * Copyright (C) 2014, Google, Inc
+ *
+ * Contributed by:
+ * 	Stephane Eranian <eranian@gmail.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include <sys/types.h>
+#include <stdio.h>
+#include <getopt.h>
+#include <stddef.h>
+#include <libelf.h>
+#include <string.h>
+#include <stdlib.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <fcntl.h>
+#include <err.h>
+#include <dwarf.h>
+
+#include "perf.h"
+#include "genelf.h"
+#include "../util/jitdump.h"
+
+#define JVMTI
+
+#define BUILD_ID_URANDOM /* different uuid for each run */
+
+#ifdef HAVE_LIBCRYPTO
+
+#define BUILD_ID_MD5
+#undef BUILD_ID_SHA	/* does not seem to work well when linked with Java */
+#undef BUILD_ID_URANDOM /* different uuid for each run */
+
+#ifdef BUILD_ID_SHA
+#include <openssl/sha.h>
+#endif
+
+#ifdef BUILD_ID_MD5
+#include <openssl/md5.h>
+#endif
+#endif
+
+
+typedef struct {
+  unsigned int namesz;  /* Size of entry's owner string */
+  unsigned int descsz;  /* Size of the note descriptor */
+  unsigned int type;    /* Interpretation of the descriptor */
+  char         name[0]; /* Start of the name+desc data */
+} Elf_Note;
+
+struct options {
+	char *output;
+	int fd;
+};
+
+static char shd_string_table[] = {
+	0,
+	'.', 't', 'e', 'x', 't', 0,			/*  1 */
+	'.', 's', 'h', 's', 't', 'r', 't', 'a', 'b', 0, /*  7 */
+	'.', 's', 'y', 'm', 't', 'a', 'b', 0,		/* 17 */
+	'.', 's', 't', 'r', 't', 'a', 'b', 0,		/* 25 */
+	'.', 'n', 'o', 't', 'e', '.', 'g', 'n', 'u', '.', 'b', 'u', 'i', 'l', 'd', '-', 'i', 'd', 0, /* 33 */
+	'.', 'd', 'e', 'b', 'u', 'g', '_', 'l', 'i', 'n', 'e', 0, /* 52 */
+	'.', 'd', 'e', 'b', 'u', 'g', '_', 'i', 'n', 'f', 'o', 0, /* 64 */
+	'.', 'd', 'e', 'b', 'u', 'g', '_', 'a', 'b', 'b', 'r', 'e', 'v', 0, /* 76 */
+};
+
+static struct buildid_note {
+	Elf_Note desc;		/* descsz: size of build-id, must be multiple of 4 */
+	char	 name[4];	/* GNU\0 */
+	char	 build_id[20];
+} bnote;
+
+static Elf_Sym symtab[]={
+	/* symbol 0 MUST be the undefined symbol */
+	{ .st_name  = 0, /* index in sym_string table */
+	  .st_info  = ELF_ST_TYPE(STT_NOTYPE),
+	  .st_shndx = 0, /* for now */
+	  .st_value = 0x0,
+	  .st_other = ELF_ST_VIS(STV_DEFAULT),
+	  .st_size  = 0,
+	},
+	{ .st_name  = 1, /* index in sym_string table */
+	  .st_info  = ELF_ST_BIND(STB_LOCAL) | ELF_ST_TYPE(STT_FUNC),
+	  .st_shndx = 1,
+	  .st_value = 0, /* for now */
+	  .st_other = ELF_ST_VIS(STV_DEFAULT),
+	  .st_size  = 0, /* for now */
+	}
+};
+
+#ifdef BUILD_ID_URANDOM
+static void
+gen_build_id(struct buildid_note *note,
+	     unsigned long load_addr __maybe_unused,
+	     const void *code __maybe_unused,
+	     size_t csize __maybe_unused)
+{
+	int fd;
+	size_t sz = sizeof(note->build_id);
+	ssize_t sret;
+
+	fd = open("/dev/urandom", O_RDONLY);
+	if (fd == -1)
+		err(1, "cannot access /dev/urandom for builid");
+
+	sret = read(fd, note->build_id, sz);
+
+	close(fd);
+
+	if (sret != (ssize_t)sz)
+		memset(note->build_id, 0, sz);
+}
+#endif
+
+#ifdef BUILD_ID_SHA
+static void
+gen_build_id(struct buildid_note *note,
+	     unsigned long load_addr __maybe_unused,
+	     const void *code,
+	     size_t csize)
+{
+	if (sizeof(note->build_id) < SHA_DIGEST_LENGTH)
+		errx(1, "build_id too small for SHA1");
+
+	SHA1(code, csize, (unsigned char *)note->build_id);
+}
+#endif
+
+#ifdef BUILD_ID_MD5
+static void
+gen_build_id(struct buildid_note *note, unsigned long load_addr, const void *code, size_t csize)
+{
+	MD5_CTX context;
+
+	if (sizeof(note->build_id) < 16)
+		errx(1, "build_id too small for MD5");
+
+	MD5_Init(&context);
+	MD5_Update(&context, &load_addr, sizeof(load_addr));
+	MD5_Update(&context, code, csize);
+	MD5_Final((unsigned char *)note->build_id, &context);
+}
+#endif
+
+/*
+ * fd: file descriptor open for writing for the output file
+ * load_addr: code load address (could be zero, just used for buildid)
+ * sym: function name (for native code - used as the symbol)
+ * code: the native code
+ * csize: the code size in bytes
+ */
+int
+jit_write_elf(int fd, uint64_t load_addr, const char *sym,
+	      const void *code, int csize,
+	      void *debug, int nr_debug_entries)
+{
+	Elf *e;
+	Elf_Data *d;
+	Elf_Scn *scn;
+	Elf_Ehdr *ehdr;
+	Elf_Shdr *shdr;
+	char *strsym = NULL;
+	int symlen;
+	int retval = -1;
+
+	if (elf_version(EV_CURRENT) == EV_NONE) {
+		warnx("ELF initialization failed");
+		return -1;
+	}
+
+	e = elf_begin(fd, ELF_C_WRITE, NULL);
+	if (!e) {
+		warnx("elf_begin failed");
+		goto error;
+	}
+
+	/*
+	 * setup ELF header
+	 */
+	ehdr = elf_newehdr(e);
+	if (!ehdr) {
+		warnx("cannot get ehdr");
+		goto error;
+	}
+
+	ehdr->e_ident[EI_DATA] = GEN_ELF_ENDIAN;
+	ehdr->e_ident[EI_CLASS] = GEN_ELF_CLASS;
+	ehdr->e_machine = GEN_ELF_ARCH;
+	ehdr->e_type = ET_DYN;
+	ehdr->e_entry = GEN_ELF_TEXT_OFFSET;
+	ehdr->e_version = EV_CURRENT;
+	ehdr->e_shstrndx= 2; /* shdr index for section name */
+
+	/*
+	 * setup text section
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		goto error;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		goto error;
+	}
+
+	d->d_align = 16;
+	d->d_off = 0LL;
+	d->d_buf = (void *)code;
+	d->d_type = ELF_T_BYTE;
+	d->d_size = csize;
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		goto error;
+	}
+
+	shdr->sh_name = 1;
+	shdr->sh_type = SHT_PROGBITS;
+	shdr->sh_addr = GEN_ELF_TEXT_OFFSET;
+	shdr->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * setup section headers string table
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		goto error;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		goto error;
+	}
+
+	d->d_align = 1;
+	d->d_off = 0LL;
+	d->d_buf = shd_string_table;
+	d->d_type = ELF_T_BYTE;
+	d->d_size = sizeof(shd_string_table);
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		goto error;
+	}
+
+	shdr->sh_name = 7; /* offset of '.shstrtab' in shd_string_table */
+	shdr->sh_type = SHT_STRTAB;
+	shdr->sh_flags = 0;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * setup symtab section
+	 */
+	symtab[1].st_size  = csize;
+	symtab[1].st_value = GEN_ELF_TEXT_OFFSET;
+
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		goto error;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		goto error;
+	}
+
+	d->d_align = 8;
+	d->d_off = 0LL;
+	d->d_buf = symtab;
+	d->d_type = ELF_T_SYM;
+	d->d_size = sizeof(symtab);
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		goto error;
+	}
+
+	shdr->sh_name = 17; /* offset of '.symtab' in shd_string_table */
+	shdr->sh_type = SHT_SYMTAB;
+	shdr->sh_flags = 0;
+	shdr->sh_entsize = sizeof(Elf_Sym);
+	shdr->sh_link = 4; /* index of .strtab section */
+
+	/*
+	 * setup symbols string table
+	 * 2 = 1 for 0 in 1st entry, 1 for the 0 at end of symbol for 2nd entry
+	 */
+	symlen = 2 + strlen(sym);
+	strsym = calloc(1, symlen);
+	if (!strsym) {
+		warnx("cannot allocate strsym");
+		goto error;
+	}
+	strcpy(strsym + 1, sym);
+
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		goto error;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		goto error;
+	}
+
+	d->d_align = 1;
+	d->d_off = 0LL;
+	d->d_buf = strsym;
+	d->d_type = ELF_T_BYTE;
+	d->d_size = symlen;
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		goto error;
+	}
+
+	shdr->sh_name = 25; /* offset in shd_string_table */
+	shdr->sh_type = SHT_STRTAB;
+	shdr->sh_flags = 0;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * setup build-id section
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		goto error;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		goto error;
+	}
+
+	/*
+	 * build-id generation
+	 */
+	gen_build_id(&bnote, load_addr, code, csize);
+	bnote.desc.namesz = sizeof(bnote.name); /* must include 0 termination */
+	bnote.desc.descsz = sizeof(bnote.build_id);
+	bnote.desc.type   = NT_GNU_BUILD_ID;
+	strcpy(bnote.name, "GNU");
+
+	d->d_align = 4;
+	d->d_off = 0LL;
+	d->d_buf = &bnote;
+	d->d_type = ELF_T_BYTE;
+	d->d_size = sizeof(bnote);
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		goto error;
+	}
+
+	shdr->sh_name = 33; /* offset in shd_string_table */
+	shdr->sh_type = SHT_NOTE;
+	shdr->sh_addr = 0x0;
+	shdr->sh_flags = SHF_ALLOC;
+	shdr->sh_size = sizeof(bnote);
+	shdr->sh_entsize = 0;
+
+	if (debug && nr_debug_entries) {
+		retval = jit_add_debug_info(e, load_addr, debug, nr_debug_entries);
+		if (retval)
+			goto error;
+	} else {
+		if (elf_update(e, ELF_C_WRITE) < 0) {
+			warnx("elf_update 4 failed");
+			goto error;
+		}
+	}
+
+	retval = 0;
+error:
+	(void)elf_end(e);
+
+	free(strsym);
+
+
+	return retval;
+}
+
+#ifndef JVMTI
+
+static unsigned char x86_code[] = {
+    0xBB, 0x2A, 0x00, 0x00, 0x00, /* movl $42, %ebx */
+    0xB8, 0x01, 0x00, 0x00, 0x00, /* movl $1, %eax */
+    0xCD, 0x80            /* int $0x80 */
+};
+
+static struct options options;
+
+int main(int argc, char **argv)
+{
+	int c, fd, ret;
+
+	while ((c = getopt(argc, argv, "o:h")) != -1) {
+		switch (c) {
+		case 'o':
+			options.output = optarg;
+			break;
+		case 'h':
+			printf("Usage: genelf -o output_file [-h]\n");
+			return 0;
+		default:
+			errx(1, "unknown option");
+		}
+	}
+
+	fd = open(options.output, O_CREAT|O_TRUNC|O_RDWR, 0666);
+	if (fd == -1)
+		err(1, "cannot create file %s", options.output);
+
+	ret = jit_write_elf(fd, "main", x86_code, sizeof(x86_code));
+	close(fd);
+
+	if (ret != 0)
+		unlink(options.output);
+
+	return ret;
+}
+#endif
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
new file mode 100644
index 000000000000..45bf9c6d3257
--- /dev/null
+++ b/tools/perf/util/genelf.h
@@ -0,0 +1,67 @@
+#ifndef __GENELF_H__
+#define __GENELF_H__
+
+/* genelf.c */
+extern int jit_write_elf(int fd, uint64_t code_addr, const char *sym,
+			 const void *code, int csize,
+			 void *debug, int nr_debug_entries);
+/* genelf_debug.c */
+extern int jit_add_debug_info(Elf *e, uint64_t code_addr,
+			      void *debug, int nr_debug_entries);
+
+#if   defined(__arm__)
+#define GEN_ELF_ARCH	EM_ARM
+#define GEN_ELF_ENDIAN	ELFDATA2LSB
+#define GEN_ELF_CLASS	ELFCLASS32
+#elif defined(__aarch64__)
+#define GEN_ELF_ARCH	EM_AARCH64
+#define GEN_ELF_ENDIAN	ELFDATA2LSB
+#define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__x86_64__)
+#define GEN_ELF_ARCH	EM_X86_64
+#define GEN_ELF_ENDIAN	ELFDATA2LSB
+#define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__i386__)
+#define GEN_ELF_ARCH	EM_386
+#define GEN_ELF_ENDIAN	ELFDATA2LSB
+#define GEN_ELF_CLASS	ELFCLASS32
+#elif defined(__ppcle__)
+#define GEN_ELF_ARCH	EM_PPC
+#define GEN_ELF_ENDIAN	ELFDATA2LSB
+#define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__powerpc__)
+#define GEN_ELF_ARCH	EM_PPC64
+#define GEN_ELF_ENDIAN	ELFDATA2MSB
+#define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__powerpcle__)
+#define GEN_ELF_ARCH	EM_PPC64
+#define GEN_ELF_ENDIAN	ELFDATA2LSB
+#define GEN_ELF_CLASS	ELFCLASS64
+#else
+#error "unsupported architecture"
+#endif
+
+#if GEN_ELF_CLASS == ELFCLASS64
+#define elf_newehdr	elf64_newehdr
+#define elf_getshdr	elf64_getshdr
+#define Elf_Ehdr	Elf64_Ehdr
+#define Elf_Shdr	Elf64_Shdr
+#define Elf_Sym		Elf64_Sym
+#define ELF_ST_TYPE(a)	ELF64_ST_TYPE(a)
+#define ELF_ST_BIND(a)	ELF64_ST_BIND(a)
+#define ELF_ST_VIS(a)	ELF64_ST_VISIBILITY(a)
+#else
+#define elf_newehdr	elf32_newehdr
+#define elf_getshdr	elf32_getshdr
+#define Elf_Ehdr	Elf32_Ehdr
+#define Elf_Shdr	Elf32_Shdr
+#define Elf_Sym		Elf32_Sym
+#define ELF_ST_TYPE(a)	ELF32_ST_TYPE(a)
+#define ELF_ST_BIND(a)	ELF32_ST_BIND(a)
+#define ELF_ST_VIS(a)	ELF32_ST_VISIBILITY(a)
+#endif
+
+/* The .text section is directly after the ELF header */
+#define GEN_ELF_TEXT_OFFSET sizeof(Elf_Ehdr)
+
+#endif
diff --git a/tools/perf/util/genelf_debug.c b/tools/perf/util/genelf_debug.c
new file mode 100644
index 000000000000..5980f7d256b1
--- /dev/null
+++ b/tools/perf/util/genelf_debug.c
@@ -0,0 +1,610 @@
+/*
+ * genelf_debug.c
+ * Copyright (C) 2015, Google, Inc
+ *
+ * Contributed by:
+ * 	Stephane Eranian <eranian@google.com>
+ *
+ * Released under the GPL v2.
+ *
+ * based on GPLv2 source code from Oprofile
+ * @remark Copyright 2007 OProfile authors
+ * @author Philippe Elie
+ */
+#include <sys/types.h>
+#include <stdio.h>
+#include <getopt.h>
+#include <stddef.h>
+#include <libelf.h>
+#include <string.h>
+#include <stdlib.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <fcntl.h>
+#include <err.h>
+#include <dwarf.h>
+
+#include "perf.h"
+#include "genelf.h"
+#include "../util/jitdump.h"
+
+#define BUFFER_EXT_DFL_SIZE	(4 * 1024)
+
+typedef uint32_t uword;
+typedef uint16_t uhalf;
+typedef int32_t  sword;
+typedef int16_t  shalf;
+typedef uint8_t  ubyte;
+typedef int8_t   sbyte;
+
+struct buffer_ext {
+	size_t cur_pos;
+	size_t max_sz;
+	void *data;
+};
+
+static void
+buffer_ext_dump(struct buffer_ext *be, const char *msg)
+{
+	size_t i;
+	warnx("DUMP for %s", msg);
+	for (i = 0 ; i < be->cur_pos; i++)
+		warnx("%4zu 0x%02x", i, (((char *)be->data)[i]) & 0xff);
+}
+
+static inline int
+buffer_ext_add(struct buffer_ext *be, void *addr, size_t sz)
+{
+	void *tmp;
+	size_t be_sz = be->max_sz;
+
+retry:
+	if ((be->cur_pos + sz) < be_sz) {
+		memcpy(be->data + be->cur_pos, addr, sz);
+		be->cur_pos += sz;
+		return 0;
+	}
+
+	if (!be_sz)
+		be_sz = BUFFER_EXT_DFL_SIZE;
+	else
+		be_sz <<= 1;
+
+	tmp = realloc(be->data, be_sz);
+	if (!tmp)
+		return -1;
+
+	be->data   = tmp;
+	be->max_sz = be_sz;
+
+	goto retry;
+}
+
+static void
+buffer_ext_init(struct buffer_ext *be)
+{
+	be->data = NULL;
+	be->cur_pos = 0;
+	be->max_sz = 0;
+}
+
+static inline size_t
+buffer_ext_size(struct buffer_ext *be)
+{
+	return be->cur_pos;
+}
+
+static inline void *
+buffer_ext_addr(struct buffer_ext *be)
+{
+	return be->data;
+}
+
+struct debug_line_header {
+	// Not counting this field
+	uword total_length;
+	// version number (2 currently)
+	uhalf version;
+	// relative offset from next field to
+	// program statement
+	uword prolog_length;
+	ubyte minimum_instruction_length;
+	ubyte default_is_stmt;
+	// line_base - see DWARF 2 specs
+	sbyte line_base;
+	// line_range - see DWARF 2 specs
+	ubyte line_range;
+	// number of opcode + 1
+	ubyte opcode_base;
+	/* follow the array of opcode args nr: ubytes [nr_opcode_base] */
+	/* follow the search directories index, zero terminated string
+	 * terminated by an empty string.
+	 */
+	/* follow an array of { filename, LEB128, LEB128, LEB128 }, first is
+	 * the directory index entry, 0 means current directory, then mtime
+	 * and filesize, last entry is followed by en empty string.
+	 */
+	/* follow the first program statement */
+} __attribute__((packed));
+
+/* DWARF 2 spec talk only about one possible compilation unit header while
+ * binutils can handle two flavours of dwarf 2, 32 and 64 bits, this is not
+ * related to the used arch, an ELF 32 can hold more than 4 Go of debug
+ * information. For now we handle only DWARF 2 32 bits comp unit. It'll only
+ * become a problem if we generate more than 4GB of debug information.
+ */
+struct compilation_unit_header {
+	uword total_length;
+	uhalf version;
+	uword debug_abbrev_offset;
+	ubyte pointer_size;
+} __attribute__((packed));
+
+#define DW_LNS_num_opcode (DW_LNS_set_isa + 1)
+
+/* field filled at run time are marked with -1 */
+static struct debug_line_header const default_debug_line_header = {
+	.total_length = -1,
+	.version = 2,
+	.prolog_length = -1,
+	.minimum_instruction_length = 1,	/* could be better when min instruction size != 1 */
+	.default_is_stmt = 1,	/* we don't take care about basic block */
+	.line_base = -5,	/* sensible value for line base ... */
+	.line_range = -14,     /* ... and line range are guessed statically */
+	.opcode_base = DW_LNS_num_opcode
+};
+
+static ubyte standard_opcode_length[] =
+{
+	0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1
+};
+#if 0
+{
+	[DW_LNS_advance_pc]   = 1,
+	[DW_LNS_advance_line] = 1,
+	[DW_LNS_set_file] =  1,
+	[DW_LNS_set_column] = 1,
+	[DW_LNS_fixed_advance_pc] = 1,
+	[DW_LNS_set_isa] = 1,
+};
+#endif
+
+/* field filled at run time are marked with -1 */
+static struct compilation_unit_header default_comp_unit_header = {
+	.total_length = -1,
+	.version = 2,
+	.debug_abbrev_offset = 0,     /* we reuse the same abbrev entries for all comp unit */
+	.pointer_size = sizeof(void *)
+};
+
+static void emit_uword(struct buffer_ext *be, uword data)
+{
+	buffer_ext_add(be, &data, sizeof(uword));
+}
+
+static void emit_string(struct buffer_ext *be, const char *s)
+{
+	buffer_ext_add(be, (void *)s, strlen(s) + 1);
+}
+
+static void emit_unsigned_LEB128(struct buffer_ext *be,
+				 unsigned long data)
+{
+	do {
+		ubyte cur = data & 0x7F;
+		data >>= 7;
+		if (data)
+			cur |= 0x80;
+		buffer_ext_add(be, &cur, 1);
+	} while (data);
+}
+
+static void emit_signed_LEB128(struct buffer_ext *be, long data)
+{
+	int more = 1;
+	int negative = data < 0;
+	int size = sizeof(long) * CHAR_BIT;
+	while (more) {
+		ubyte cur = data & 0x7F;
+		data >>= 7;
+		if (negative)
+			data |= - (1 << (size - 7));
+		if ((data == 0 && !(cur & 0x40)) ||
+		    (data == -1l && (cur & 0x40)))
+			more = 0;
+		else
+			cur |= 0x80;
+		buffer_ext_add(be, &cur, 1);
+	}
+}
+
+static void emit_extended_opcode(struct buffer_ext *be, ubyte opcode,
+				 void *data, size_t data_len)
+{
+	buffer_ext_add(be, (char *)"", 1);
+
+	emit_unsigned_LEB128(be, data_len + 1);
+
+	buffer_ext_add(be, &opcode, 1);
+	buffer_ext_add(be, data, data_len);
+}
+
+static void emit_opcode(struct buffer_ext *be, ubyte opcode)
+{
+	buffer_ext_add(be, &opcode, 1);
+}
+
+static void emit_opcode_signed(struct buffer_ext  *be,
+			       ubyte opcode, long data)
+{
+	buffer_ext_add(be, &opcode, 1);
+	emit_signed_LEB128(be, data);
+}
+
+static void emit_opcode_unsigned(struct buffer_ext *be, ubyte opcode,
+				 unsigned long data)
+{
+	buffer_ext_add(be, &opcode, 1);
+	emit_unsigned_LEB128(be, data);
+}
+
+static void emit_advance_pc(struct buffer_ext *be, unsigned long delta_pc)
+{
+	emit_opcode_unsigned(be, DW_LNS_advance_pc, delta_pc);
+}
+
+static void emit_advance_lineno(struct buffer_ext  *be, long delta_lineno)
+{
+	emit_opcode_signed(be, DW_LNS_advance_line, delta_lineno);
+}
+
+static void emit_lne_end_of_sequence(struct buffer_ext *be)
+{
+	emit_extended_opcode(be, DW_LNE_end_sequence, NULL, 0);
+}
+
+static void emit_set_file(struct buffer_ext *be, unsigned long idx)
+{
+	emit_opcode_unsigned(be, DW_LNS_set_file, idx);
+}
+
+static void emit_lne_define_filename(struct buffer_ext *be,
+				     const char *filename)
+{
+	buffer_ext_add(be, (void *)"", 1);
+
+	/* LNE field, strlen(filename) + zero termination, 3 bytes for: the dir entry, timestamp, filesize */
+	emit_unsigned_LEB128(be, strlen(filename) + 5);
+	emit_opcode(be, DW_LNE_define_file);
+	emit_string(be, filename);
+	/* directory index 0=do not know */
+        emit_unsigned_LEB128(be, 0);
+	/* last modification date on file 0=do not know */
+        emit_unsigned_LEB128(be, 0);
+	/* filesize 0=do not know */
+        emit_unsigned_LEB128(be, 0);
+}
+
+static void emit_lne_set_address(struct buffer_ext *be,
+				 void *address)
+{
+	emit_extended_opcode(be, DW_LNE_set_address, &address, sizeof(unsigned long));
+}
+
+static ubyte get_special_opcode(struct debug_entry *ent,
+				unsigned int last_line,
+				unsigned long last_vma)
+{
+	unsigned int temp;
+	unsigned long delta_addr;
+
+	/*
+	 * delta from line_base
+	 */
+	temp = (ent->lineno - last_line) - default_debug_line_header.line_base;
+
+	if (temp >= default_debug_line_header.line_range)
+		return 0;
+
+	/*
+	 * delta of addresses
+	 */
+	delta_addr = (ent->addr - last_vma) / default_debug_line_header.minimum_instruction_length;
+
+	/* This is not sufficient to ensure opcode will be in [0-256] but
+	 * sufficient to ensure when summing with the delta lineno we will
+	 * not overflow the unsigned long opcode */
+
+	if (delta_addr <= 256 / default_debug_line_header.line_range) {
+		unsigned long opcode = temp +
+			(delta_addr * default_debug_line_header.line_range) +
+			default_debug_line_header.opcode_base;
+
+		return opcode <= 255 ? opcode : 0;
+	}
+	return 0;
+}
+
+static void emit_lineno_info(struct buffer_ext *be,
+			     struct debug_entry *ent, size_t nr_entry,
+			     unsigned long code_addr)
+{
+	size_t i;
+
+	/*
+	 * Machine state at start of a statement program
+	 * address = 0
+	 * file    = 1
+	 * line    = 1
+	 * column  = 0
+	 * is_stmt = default_is_stmt as given in the debug_line_header
+	 * basic block = 0
+	 * end sequence = 0
+	 */
+
+	/* start state of the state machine we take care of */
+	unsigned long last_vma = code_addr;
+	char const  *cur_filename = NULL;
+	unsigned long cur_file_idx = 0;
+	int last_line = 1;
+
+	emit_lne_set_address(be, (void *)code_addr);
+
+	for (i = 0; i < nr_entry; i++, ent = debug_entry_next(ent)) {
+		int need_copy = 0;
+		ubyte special_opcode;
+
+		/*
+		 * check if filename changed, if so add it
+		 */
+		if (!cur_filename || strcmp(cur_filename, ent->name)) {
+			emit_lne_define_filename(be, ent->name);
+			cur_filename = ent->name;
+			emit_set_file(be, ++cur_file_idx);
+			need_copy = 1;
+		}
+
+		special_opcode = get_special_opcode(ent, last_line, last_vma);
+		if (special_opcode != 0) {
+			last_line = ent->lineno;
+			last_vma  = ent->addr;
+			emit_opcode(be, special_opcode);
+		} else {
+			/*
+			 * lines differ, emit line delta
+			 */
+			if (last_line != ent->lineno) {
+				emit_advance_lineno(be, ent->lineno - last_line);
+				last_line = ent->lineno;
+				need_copy = 1;
+			}
+			/*
+			 * addresses differ, emit address delta
+			 */
+			if (last_vma != ent->addr) {
+				emit_advance_pc(be, ent->addr - last_vma);
+				last_vma = ent->addr;
+				need_copy = 1;
+			}
+			/*
+			 * add new row to matrix
+			 */
+			if (need_copy)
+				emit_opcode(be, DW_LNS_copy);
+		}
+	}
+}
+
+static void add_debug_line(struct buffer_ext *be,
+	struct debug_entry *ent, size_t nr_entry,
+	unsigned long code_addr)
+{
+	struct debug_line_header * dbg_header;
+	size_t old_size;
+
+	old_size = buffer_ext_size(be);
+
+	buffer_ext_add(be, (void *)&default_debug_line_header,
+		 sizeof(default_debug_line_header));
+
+	buffer_ext_add(be, &standard_opcode_length,  sizeof(standard_opcode_length));
+
+	// empty directory entry
+	buffer_ext_add(be, (void *)"", 1);
+
+	// empty filename directory
+	buffer_ext_add(be, (void *)"", 1);
+
+	dbg_header = buffer_ext_addr(be) + old_size;
+	dbg_header->prolog_length = (buffer_ext_size(be) - old_size) -
+		offsetof(struct debug_line_header, minimum_instruction_length);
+
+	emit_lineno_info(be, ent, nr_entry, code_addr);
+
+	emit_lne_end_of_sequence(be);
+
+	dbg_header = buffer_ext_addr(be) + old_size;
+	dbg_header->total_length = (buffer_ext_size(be) - old_size) -
+		offsetof(struct debug_line_header, version);
+}
+
+static void
+add_debug_abbrev(struct buffer_ext *be)
+{
+        emit_unsigned_LEB128(be, 1);
+        emit_unsigned_LEB128(be, DW_TAG_compile_unit);
+        emit_unsigned_LEB128(be, DW_CHILDREN_yes);
+        emit_unsigned_LEB128(be, DW_AT_stmt_list);
+        emit_unsigned_LEB128(be, DW_FORM_data4);
+        emit_unsigned_LEB128(be, 0);
+        emit_unsigned_LEB128(be, 0);
+        emit_unsigned_LEB128(be, 0);
+}
+
+static void
+add_compilation_unit(struct buffer_ext *be,
+		     size_t offset_debug_line)
+{
+	struct compilation_unit_header *comp_unit_header;
+	size_t old_size = buffer_ext_size(be);
+
+	buffer_ext_add(be, &default_comp_unit_header,
+		       sizeof(default_comp_unit_header));
+
+	emit_unsigned_LEB128(be, 1);
+	emit_uword(be, offset_debug_line);
+
+	comp_unit_header = buffer_ext_addr(be) + old_size;
+	comp_unit_header->total_length = (buffer_ext_size(be) - old_size) -
+		offsetof(struct compilation_unit_header, version);
+}
+
+static int
+jit_process_debug_info(uint64_t code_addr,
+		       void *debug, int nr_debug_entries,
+		       struct buffer_ext *dl,
+		       struct buffer_ext *da,
+		       struct buffer_ext *di)
+{
+	struct debug_entry *ent = debug;
+	int i;
+
+	for (i = 0; i < nr_debug_entries; i++) {
+		ent->addr = ent->addr - code_addr;
+		ent = debug_entry_next(ent);
+	}
+	add_compilation_unit(di, buffer_ext_size(dl));
+	add_debug_line(dl, debug, nr_debug_entries, 0);
+	add_debug_abbrev(da);
+	if (0) buffer_ext_dump(da, "abbrev");
+
+	return 0;
+}
+
+int
+jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_entries)
+{
+	Elf_Data *d;
+	Elf_Scn *scn;
+	Elf_Shdr *shdr;
+	struct buffer_ext dl, di, da;
+	int ret;
+
+	buffer_ext_init(&dl);
+	buffer_ext_init(&di);
+	buffer_ext_init(&da);
+
+	ret = jit_process_debug_info(code_addr, debug, nr_debug_entries, &dl, &da, &di);
+	if (ret)
+		return -1;
+	/*
+	 * setup .debug_line section
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		return -1;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		return -1;
+	}
+
+	d->d_align = 1;
+	d->d_off = 0LL;
+	d->d_buf = buffer_ext_addr(&dl);
+	d->d_type = ELF_T_BYTE;
+	d->d_size = buffer_ext_size(&dl);
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		return -1;
+	}
+
+	shdr->sh_name = 52; /* .debug_line */
+	shdr->sh_type = SHT_PROGBITS;
+	shdr->sh_addr = 0; /* must be zero or == sh_offset -> dynamic object */
+	shdr->sh_flags = 0;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * setup .debug_info section
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		return -1;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		return -1;
+	}
+
+	d->d_align = 1;
+	d->d_off = 0LL;
+	d->d_buf = buffer_ext_addr(&di);
+	d->d_type = ELF_T_BYTE;
+	d->d_size = buffer_ext_size(&di);
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		return -1;
+	}
+
+	shdr->sh_name = 64; /* .debug_info */
+	shdr->sh_type = SHT_PROGBITS;
+	shdr->sh_addr = 0; /* must be zero or == sh_offset -> dynamic object */
+	shdr->sh_flags = 0;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * setup .debug_abbrev section
+	 */
+	scn = elf_newscn(e);
+	if (!scn) {
+		warnx("cannot create section");
+		return -1;
+	}
+
+	d = elf_newdata(scn);
+	if (!d) {
+		warnx("cannot get new data");
+		return -1;
+	}
+
+	d->d_align = 1;
+	d->d_off = 0LL;
+	d->d_buf = buffer_ext_addr(&da);
+	d->d_type = ELF_T_BYTE;
+	d->d_size = buffer_ext_size(&da);
+	d->d_version = EV_CURRENT;
+
+	shdr = elf_getshdr(scn);
+	if (!shdr) {
+		warnx("cannot get section header");
+		return -1;
+	}
+
+	shdr->sh_name = 76; /* .debug_info */
+	shdr->sh_type = SHT_PROGBITS;
+	shdr->sh_addr = 0; /* must be zero or == sh_offset -> dynamic object */
+	shdr->sh_flags = 0;
+	shdr->sh_entsize = 0;
+
+	/*
+	 * now we update the ELF image with all the sections
+	 */
+	if (elf_update(e, ELF_C_WRITE) < 0) {
+		warnx("elf_update debug failed");
+		return -1;
+	}
+	return 0;
+}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index f50b7235ecb6..73e38e472ecd 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -23,6 +23,8 @@
 #include "strbuf.h"
 #include "build-id.h"
 #include "data.h"
+#include <api/fs/fs.h>
+#include "asm/bug.h"
 
 /*
  * magic2 = "PERFILE2"
@@ -868,6 +870,199 @@ static int write_auxtrace(int fd, struct perf_header *h,
 	return err;
 }
 
+static int cpu_cache_level__sort(const void *a, const void *b)
+{
+	struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a;
+	struct cpu_cache_level *cache_b = (struct cpu_cache_level *)b;
+
+	return cache_a->level - cache_b->level;
+}
+
+static bool cpu_cache_level__cmp(struct cpu_cache_level *a, struct cpu_cache_level *b)
+{
+	if (a->level != b->level)
+		return false;
+
+	if (a->line_size != b->line_size)
+		return false;
+
+	if (a->sets != b->sets)
+		return false;
+
+	if (a->ways != b->ways)
+		return false;
+
+	if (strcmp(a->type, b->type))
+		return false;
+
+	if (strcmp(a->size, b->size))
+		return false;
+
+	if (strcmp(a->map, b->map))
+		return false;
+
+	return true;
+}
+
+static int cpu_cache_level__read(struct cpu_cache_level *cache, u32 cpu, u16 level)
+{
+	char path[PATH_MAX], file[PATH_MAX];
+	struct stat st;
+	size_t len;
+
+	scnprintf(path, PATH_MAX, "devices/system/cpu/cpu%d/cache/index%d/", cpu, level);
+	scnprintf(file, PATH_MAX, "%s/%s", sysfs__mountpoint(), path);
+
+	if (stat(file, &st))
+		return 1;
+
+	scnprintf(file, PATH_MAX, "%s/level", path);
+	if (sysfs__read_int(file, (int *) &cache->level))
+		return -1;
+
+	scnprintf(file, PATH_MAX, "%s/coherency_line_size", path);
+	if (sysfs__read_int(file, (int *) &cache->line_size))
+		return -1;
+
+	scnprintf(file, PATH_MAX, "%s/number_of_sets", path);
+	if (sysfs__read_int(file, (int *) &cache->sets))
+		return -1;
+
+	scnprintf(file, PATH_MAX, "%s/ways_of_associativity", path);
+	if (sysfs__read_int(file, (int *) &cache->ways))
+		return -1;
+
+	scnprintf(file, PATH_MAX, "%s/type", path);
+	if (sysfs__read_str(file, &cache->type, &len))
+		return -1;
+
+	cache->type[len] = 0;
+	cache->type = rtrim(cache->type);
+
+	scnprintf(file, PATH_MAX, "%s/size", path);
+	if (sysfs__read_str(file, &cache->size, &len)) {
+		free(cache->type);
+		return -1;
+	}
+
+	cache->size[len] = 0;
+	cache->size = rtrim(cache->size);
+
+	scnprintf(file, PATH_MAX, "%s/shared_cpu_list", path);
+	if (sysfs__read_str(file, &cache->map, &len)) {
+		free(cache->map);
+		free(cache->type);
+		return -1;
+	}
+
+	cache->map[len] = 0;
+	cache->map = rtrim(cache->map);
+	return 0;
+}
+
+static void cpu_cache_level__fprintf(FILE *out, struct cpu_cache_level *c)
+{
+	fprintf(out, "L%d %-15s %8s [%s]\n", c->level, c->type, c->size, c->map);
+}
+
+static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp)
+{
+	u32 i, cnt = 0;
+	long ncpus;
+	u32 nr, cpu;
+	u16 level;
+
+	ncpus = sysconf(_SC_NPROCESSORS_CONF);
+	if (ncpus < 0)
+		return -1;
+
+	nr = (u32)(ncpus & UINT_MAX);
+
+	for (cpu = 0; cpu < nr; cpu++) {
+		for (level = 0; level < 10; level++) {
+			struct cpu_cache_level c;
+			int err;
+
+			err = cpu_cache_level__read(&c, cpu, level);
+			if (err < 0)
+				return err;
+
+			if (err == 1)
+				break;
+
+			for (i = 0; i < cnt; i++) {
+				if (cpu_cache_level__cmp(&c, &caches[i]))
+					break;
+			}
+
+			if (i == cnt)
+				caches[cnt++] = c;
+			else
+				cpu_cache_level__free(&c);
+
+			if (WARN_ONCE(cnt == size, "way too many cpu caches.."))
+				goto out;
+		}
+	}
+ out:
+	*cntp = cnt;
+	return 0;
+}
+
+#define MAX_CACHES 2000
+
+static int write_cache(int fd, struct perf_header *h __maybe_unused,
+			  struct perf_evlist *evlist __maybe_unused)
+{
+	struct cpu_cache_level caches[MAX_CACHES];
+	u32 cnt = 0, i, version = 1;
+	int ret;
+
+	ret = build_caches(caches, MAX_CACHES, &cnt);
+	if (ret)
+		goto out;
+
+	qsort(&caches, cnt, sizeof(struct cpu_cache_level), cpu_cache_level__sort);
+
+	ret = do_write(fd, &version, sizeof(u32));
+	if (ret < 0)
+		goto out;
+
+	ret = do_write(fd, &cnt, sizeof(u32));
+	if (ret < 0)
+		goto out;
+
+	for (i = 0; i < cnt; i++) {
+		struct cpu_cache_level *c = &caches[i];
+
+		#define _W(v)					\
+			ret = do_write(fd, &c->v, sizeof(u32));	\
+			if (ret < 0)				\
+				goto out;
+
+		_W(level)
+		_W(line_size)
+		_W(sets)
+		_W(ways)
+		#undef _W
+
+		#define _W(v)						\
+			ret = do_write_string(fd, (const char *) c->v);	\
+			if (ret < 0)					\
+				goto out;
+
+		_W(type)
+		_W(size)
+		_W(map)
+		#undef _W
+	}
+
+out:
+	for (i = 0; i < cnt; i++)
+		cpu_cache_level__free(&caches[i]);
+	return ret;
+}
+
 static int write_stat(int fd __maybe_unused,
 		      struct perf_header *h __maybe_unused,
 		      struct perf_evlist *evlist __maybe_unused)
@@ -1172,6 +1367,18 @@ static void print_stat(struct perf_header *ph __maybe_unused,
 	fprintf(fp, "# contains stat data\n");
 }
 
+static void print_cache(struct perf_header *ph __maybe_unused,
+			int fd __maybe_unused, FILE *fp __maybe_unused)
+{
+	int i;
+
+	fprintf(fp, "# CPU cache info:\n");
+	for (i = 0; i < ph->env.caches_cnt; i++) {
+		fprintf(fp, "#  ");
+		cpu_cache_level__fprintf(fp, &ph->env.caches[i]);
+	}
+}
+
 static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
 			       FILE *fp)
 {
@@ -1920,6 +2127,68 @@ static int process_auxtrace(struct perf_file_section *section,
 	return err;
 }
 
+static int process_cache(struct perf_file_section *section __maybe_unused,
+			 struct perf_header *ph __maybe_unused, int fd __maybe_unused,
+			 void *data __maybe_unused)
+{
+	struct cpu_cache_level *caches;
+	u32 cnt, i, version;
+
+	if (readn(fd, &version, sizeof(version)) != sizeof(version))
+		return -1;
+
+	if (ph->needs_swap)
+		version = bswap_32(version);
+
+	if (version != 1)
+		return -1;
+
+	if (readn(fd, &cnt, sizeof(cnt)) != sizeof(cnt))
+		return -1;
+
+	if (ph->needs_swap)
+		cnt = bswap_32(cnt);
+
+	caches = zalloc(sizeof(*caches) * cnt);
+	if (!caches)
+		return -1;
+
+	for (i = 0; i < cnt; i++) {
+		struct cpu_cache_level c;
+
+		#define _R(v)						\
+			if (readn(fd, &c.v, sizeof(u32)) != sizeof(u32))\
+				goto out_free_caches;			\
+			if (ph->needs_swap)				\
+				c.v = bswap_32(c.v);			\
+
+		_R(level)
+		_R(line_size)
+		_R(sets)
+		_R(ways)
+		#undef _R
+
+		#define _R(v)				\
+			c.v = do_read_string(fd, ph);	\
+			if (!c.v)			\
+				goto out_free_caches;
+
+		_R(type)
+		_R(size)
+		_R(map)
+		#undef _R
+
+		caches[i] = c;
+	}
+
+	ph->env.caches = caches;
+	ph->env.caches_cnt = cnt;
+	return 0;
+out_free_caches:
+	free(caches);
+	return -1;
+}
+
 struct feature_ops {
 	int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
 	void (*print)(struct perf_header *h, int fd, FILE *fp);
@@ -1962,6 +2231,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPP(HEADER_GROUP_DESC,	group_desc),
 	FEAT_OPP(HEADER_AUXTRACE,	auxtrace),
 	FEAT_OPA(HEADER_STAT,		stat),
+	FEAT_OPF(HEADER_CACHE,		cache),
 };
 
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index cff9892452ee..3d87ca823c0a 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -32,6 +32,7 @@ enum {
 	HEADER_GROUP_DESC,
 	HEADER_AUXTRACE,
 	HEADER_STAT,
+	HEADER_CACHE,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
index dc1e41c9b054..43a98a4dc1e1 100644
--- a/tools/perf/util/help-unknown-cmd.c
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -6,7 +6,8 @@
 static int autocorrect;
 static struct cmdnames aliases;
 
-static int perf_unknown_cmd_config(const char *var, const char *value, void *cb)
+static int perf_unknown_cmd_config(const char *var, const char *value,
+				   void *cb __maybe_unused)
 {
 	if (!strcmp(var, "help.autocorrect"))
 		autocorrect = perf_config_int(var,value);
@@ -14,7 +15,7 @@ static int perf_unknown_cmd_config(const char *var, const char *value, void *cb)
 	if (!prefixcmp(var, "alias."))
 		add_cmdname(&aliases, var + 6, strlen(var + 6));
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 static int levenshtein_compare(const void *p1, const void *p2)
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 68a7612019dc..290b3cbf6877 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -179,6 +179,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	if (h->transaction)
 		hists__new_col_len(hists, HISTC_TRANSACTION,
 				   hist_entry__transaction_len());
+
+	if (h->trace_output)
+		hists__new_col_len(hists, HISTC_TRACE, strlen(h->trace_output));
 }
 
 void hists__output_recalc_col_len(struct hists *hists, int max_rows)
@@ -245,6 +248,8 @@ static void he_stat__decay(struct he_stat *he_stat)
 	/* XXX need decay for weight too? */
 }
 
+static void hists__delete_entry(struct hists *hists, struct hist_entry *he);
+
 static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 {
 	u64 prev_period = he->stat.period;
@@ -260,21 +265,45 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 
 	diff = prev_period - he->stat.period;
 
-	hists->stats.total_period -= diff;
-	if (!he->filtered)
-		hists->stats.total_non_filtered_period -= diff;
+	if (!he->depth) {
+		hists->stats.total_period -= diff;
+		if (!he->filtered)
+			hists->stats.total_non_filtered_period -= diff;
+	}
+
+	if (!he->leaf) {
+		struct hist_entry *child;
+		struct rb_node *node = rb_first(&he->hroot_out);
+		while (node) {
+			child = rb_entry(node, struct hist_entry, rb_node);
+			node = rb_next(node);
+
+			if (hists__decay_entry(hists, child))
+				hists__delete_entry(hists, child);
+		}
+	}
 
 	return he->stat.period == 0;
 }
 
 static void hists__delete_entry(struct hists *hists, struct hist_entry *he)
 {
-	rb_erase(&he->rb_node, &hists->entries);
+	struct rb_root *root_in;
+	struct rb_root *root_out;
 
-	if (sort__need_collapse)
-		rb_erase(&he->rb_node_in, &hists->entries_collapsed);
-	else
-		rb_erase(&he->rb_node_in, hists->entries_in);
+	if (he->parent_he) {
+		root_in  = &he->parent_he->hroot_in;
+		root_out = &he->parent_he->hroot_out;
+	} else {
+		if (sort__need_collapse)
+			root_in = &hists->entries_collapsed;
+		else
+			root_in = hists->entries_in;
+		root_out = &hists->entries;
+	}
+
+	rb_erase(&he->rb_node_in, root_in);
+	rb_erase(&he->rb_node, root_out);
 
 	--hists->nr_entries;
 	if (!he->filtered)
@@ -393,6 +422,9 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 		}
 		INIT_LIST_HEAD(&he->pairs.node);
 		thread__get(he->thread);
+
+		if (!symbol_conf.report_hierarchy)
+			he->leaf = true;
 	}
 
 	return he;
@@ -405,6 +437,16 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 	return 0;
 }
 
+static void hist_entry__add_callchain_period(struct hist_entry *he, u64 period)
+{
+	if (!symbol_conf.use_callchain)
+		return;
+
+	he->hists->callchain_period += period;
+	if (!he->filtered)
+		he->hists->callchain_non_filtered_period += period;
+}
+
 static struct hist_entry *hists__findnew_entry(struct hists *hists,
 					       struct hist_entry *entry,
 					       struct addr_location *al,
@@ -432,8 +474,10 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 		cmp = hist_entry__cmp(he, entry);
 
 		if (!cmp) {
-			if (sample_self)
+			if (sample_self) {
 				he_stat__add_period(&he->stat, period, weight);
+				hist_entry__add_callchain_period(he, period);
+			}
 			if (symbol_conf.cumulate_callchain)
 				he_stat__add_period(he->stat_acc, period, weight);
 
@@ -466,6 +510,8 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 	if (!he)
 		return NULL;
 
+	if (sample_self)
+		hist_entry__add_callchain_period(he, period);
 	hists->nr_entries++;
 
 	rb_link_node(&he->rb_node_in, parent, p);
@@ -951,10 +997,15 @@ out:
 int64_t
 hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 {
+	struct hists *hists = left->hists;
 	struct perf_hpp_fmt *fmt;
 	int64_t cmp = 0;
 
-	perf_hpp__for_each_sort_list(fmt) {
+	hists__for_each_sort_list(hists, fmt) {
+		if (perf_hpp__is_dynamic_entry(fmt) &&
+		    !perf_hpp__defined_dynamic_entry(fmt, hists))
+			continue;
+
 		cmp = fmt->cmp(fmt, left, right);
 		if (cmp)
 			break;
@@ -966,10 +1017,15 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 int64_t
 hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 {
+	struct hists *hists = left->hists;
 	struct perf_hpp_fmt *fmt;
 	int64_t cmp = 0;
 
-	perf_hpp__for_each_sort_list(fmt) {
+	hists__for_each_sort_list(hists, fmt) {
+		if (perf_hpp__is_dynamic_entry(fmt) &&
+		    !perf_hpp__defined_dynamic_entry(fmt, hists))
+			continue;
+
 		cmp = fmt->collapse(fmt, left, right);
 		if (cmp)
 			break;
@@ -1006,17 +1062,250 @@ void hist_entry__delete(struct hist_entry *he)
 }
 
 /*
+ * If this is not the last column, then we need to pad it according to the
+ * pre-calculated max lenght for this column, otherwise don't bother adding
+ * spaces because that would break viewing this with, for instance, 'less',
+ * that would show tons of trailing spaces when a long C++ demangled method
+ * names is sampled.
+*/
+int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
+				   struct perf_hpp_fmt *fmt, int printed)
+{
+	if (!list_is_last(&fmt->list, &he->hists->hpp_list->fields)) {
+		const int width = fmt->width(fmt, hpp, hists_to_evsel(he->hists));
+		if (printed < width) {
+			advance_hpp(hpp, printed);
+			printed = scnprintf(hpp->buf, hpp->size, "%-*s", width - printed, " ");
+		}
+	}
+
+	return printed;
+}
+
+/*
  * collapse the histogram
  */
 
-bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
-				  struct rb_root *root, struct hist_entry *he)
+static void hists__apply_filters(struct hists *hists, struct hist_entry *he);
+static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *he,
+				       enum hist_filter type);
+
+typedef bool (*fmt_chk_fn)(struct perf_hpp_fmt *fmt);
+
+static bool check_thread_entry(struct perf_hpp_fmt *fmt)
+{
+	return perf_hpp__is_thread_entry(fmt) || perf_hpp__is_comm_entry(fmt);
+}
+
+static void hist_entry__check_and_remove_filter(struct hist_entry *he,
+						enum hist_filter type,
+						fmt_chk_fn check)
+{
+	struct perf_hpp_fmt *fmt;
+	bool type_match = false;
+	struct hist_entry *parent = he->parent_he;
+
+	switch (type) {
+	case HIST_FILTER__THREAD:
+		if (symbol_conf.comm_list == NULL &&
+		    symbol_conf.pid_list == NULL &&
+		    symbol_conf.tid_list == NULL)
+			return;
+		break;
+	case HIST_FILTER__DSO:
+		if (symbol_conf.dso_list == NULL)
+			return;
+		break;
+	case HIST_FILTER__SYMBOL:
+		if (symbol_conf.sym_list == NULL)
+			return;
+		break;
+	case HIST_FILTER__PARENT:
+	case HIST_FILTER__GUEST:
+	case HIST_FILTER__HOST:
+	case HIST_FILTER__SOCKET:
+	default:
+		return;
+	}
+
+	/* if it's filtered by own fmt, it has to have filter bits */
+	perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+		if (check(fmt)) {
+			type_match = true;
+			break;
+		}
+	}
+
+	if (type_match) {
+		/*
+		 * If the filter is for current level entry, propagate
+		 * filter marker to parents.  The marker bit was
+		 * already set by default so it only needs to clear
+		 * non-filtered entries.
+		 */
+		if (!(he->filtered & (1 << type))) {
+			while (parent) {
+				parent->filtered &= ~(1 << type);
+				parent = parent->parent_he;
+			}
+		}
+	} else {
+		/*
+		 * If current entry doesn't have matching formats, set
+		 * filter marker for upper level entries.  it will be
+		 * cleared if its lower level entries is not filtered.
+		 *
+		 * For lower-level entries, it inherits parent's
+		 * filter bit so that lower level entries of a
+		 * non-filtered entry won't set the filter marker.
+		 */
+		if (parent == NULL)
+			he->filtered |= (1 << type);
+		else
+			he->filtered |= (parent->filtered & (1 << type));
+	}
+}
+
+static void hist_entry__apply_hierarchy_filters(struct hist_entry *he)
+{
+	hist_entry__check_and_remove_filter(he, HIST_FILTER__THREAD,
+					    check_thread_entry);
+
+	hist_entry__check_and_remove_filter(he, HIST_FILTER__DSO,
+					    perf_hpp__is_dso_entry);
+
+	hist_entry__check_and_remove_filter(he, HIST_FILTER__SYMBOL,
+					    perf_hpp__is_sym_entry);
+
+	hists__apply_filters(he->hists, he);
+}
+
+static struct hist_entry *hierarchy_insert_entry(struct hists *hists,
+						 struct rb_root *root,
+						 struct hist_entry *he,
+						 struct hist_entry *parent_he,
+						 struct perf_hpp_list *hpp_list)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter, *new;
+	struct perf_hpp_fmt *fmt;
+	int64_t cmp;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node_in);
+
+		cmp = 0;
+		perf_hpp_list__for_each_sort_list(hpp_list, fmt) {
+			cmp = fmt->collapse(fmt, iter, he);
+			if (cmp)
+				break;
+		}
+
+		if (!cmp) {
+			he_stat__add_stat(&iter->stat, &he->stat);
+			return iter;
+		}
+
+		if (cmp < 0)
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
+	}
+
+	new = hist_entry__new(he, true);
+	if (new == NULL)
+		return NULL;
+
+	hists->nr_entries++;
+
+	/* save related format list for output */
+	new->hpp_list = hpp_list;
+	new->parent_he = parent_he;
+
+	hist_entry__apply_hierarchy_filters(new);
+
+	/* some fields are now passed to 'new' */
+	perf_hpp_list__for_each_sort_list(hpp_list, fmt) {
+		if (perf_hpp__is_trace_entry(fmt) || perf_hpp__is_dynamic_entry(fmt))
+			he->trace_output = NULL;
+		else
+			new->trace_output = NULL;
+
+		if (perf_hpp__is_srcline_entry(fmt))
+			he->srcline = NULL;
+		else
+			new->srcline = NULL;
+
+		if (perf_hpp__is_srcfile_entry(fmt))
+			he->srcfile = NULL;
+		else
+			new->srcfile = NULL;
+	}
+
+	rb_link_node(&new->rb_node_in, parent, p);
+	rb_insert_color(&new->rb_node_in, root);
+	return new;
+}
+
+static int hists__hierarchy_insert_entry(struct hists *hists,
+					 struct rb_root *root,
+					 struct hist_entry *he)
+{
+	struct perf_hpp_list_node *node;
+	struct hist_entry *new_he = NULL;
+	struct hist_entry *parent = NULL;
+	int depth = 0;
+	int ret = 0;
+
+	list_for_each_entry(node, &hists->hpp_formats, list) {
+		/* skip period (overhead) and elided columns */
+		if (node->level == 0 || node->skip)
+			continue;
+
+		/* insert copy of 'he' for each fmt into the hierarchy */
+		new_he = hierarchy_insert_entry(hists, root, he, parent, &node->hpp);
+		if (new_he == NULL) {
+			ret = -1;
+			break;
+		}
+
+		root = &new_he->hroot_in;
+		new_he->depth = depth++;
+		parent = new_he;
+	}
+
+	if (new_he) {
+		new_he->leaf = true;
+
+		if (symbol_conf.use_callchain) {
+			callchain_cursor_reset(&callchain_cursor);
+			if (callchain_merge(&callchain_cursor,
+					    new_he->callchain,
+					    he->callchain) < 0)
+				ret = -1;
+		}
+	}
+
+	/* 'he' is no longer used */
+	hist_entry__delete(he);
+
+	/* return 0 (or -1) since it already applied filters */
+	return ret;
+}
+
+int hists__collapse_insert_entry(struct hists *hists, struct rb_root *root,
+				 struct hist_entry *he)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
 	int64_t cmp;
 
+	if (symbol_conf.report_hierarchy)
+		return hists__hierarchy_insert_entry(hists, root, he);
+
 	while (*p != NULL) {
 		parent = *p;
 		iter = rb_entry(parent, struct hist_entry, rb_node_in);
@@ -1024,18 +1313,21 @@ bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 		cmp = hist_entry__collapse(iter, he);
 
 		if (!cmp) {
+			int ret = 0;
+
 			he_stat__add_stat(&iter->stat, &he->stat);
 			if (symbol_conf.cumulate_callchain)
 				he_stat__add_stat(iter->stat_acc, he->stat_acc);
 
 			if (symbol_conf.use_callchain) {
 				callchain_cursor_reset(&callchain_cursor);
-				callchain_merge(&callchain_cursor,
-						iter->callchain,
-						he->callchain);
+				if (callchain_merge(&callchain_cursor,
+						    iter->callchain,
+						    he->callchain) < 0)
+					ret = -1;
 			}
 			hist_entry__delete(he);
-			return false;
+			return ret;
 		}
 
 		if (cmp < 0)
@@ -1047,7 +1339,7 @@ bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, root);
-	return true;
+	return 1;
 }
 
 struct rb_root *hists__get_rotate_entries_in(struct hists *hists)
@@ -1073,14 +1365,15 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he)
 	hists__filter_entry_by_socket(hists, he);
 }
 
-void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
+int hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 {
 	struct rb_root *root;
 	struct rb_node *next;
 	struct hist_entry *n;
+	int ret;
 
 	if (!sort__need_collapse)
-		return;
+		return 0;
 
 	hists->nr_entries = 0;
 
@@ -1095,7 +1388,11 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 		next = rb_next(&n->rb_node_in);
 
 		rb_erase(&n->rb_node_in, root);
-		if (hists__collapse_insert_entry(hists, &hists->entries_collapsed, n)) {
+		ret = hists__collapse_insert_entry(hists, &hists->entries_collapsed, n);
+		if (ret < 0)
+			return -1;
+
+		if (ret) {
 			/*
 			 * If it wasn't combined with one of the entries already
 			 * collapsed, we need to apply the filters that may have
@@ -1106,14 +1403,16 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 		if (prog)
 			ui_progress__update(prog, 1);
 	}
+	return 0;
 }
 
 static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
 {
+	struct hists *hists = a->hists;
 	struct perf_hpp_fmt *fmt;
 	int64_t cmp = 0;
 
-	perf_hpp__for_each_sort_list(fmt) {
+	hists__for_each_sort_list(hists, fmt) {
 		if (perf_hpp__should_skip(fmt, a->hists))
 			continue;
 
@@ -1154,6 +1453,113 @@ void hists__inc_stats(struct hists *hists, struct hist_entry *h)
 	hists->stats.total_period += h->stat.period;
 }
 
+static void hierarchy_recalc_total_periods(struct hists *hists)
+{
+	struct rb_node *node;
+	struct hist_entry *he;
+
+	node = rb_first(&hists->entries);
+
+	hists->stats.total_period = 0;
+	hists->stats.total_non_filtered_period = 0;
+
+	/*
+	 * recalculate total period using top-level entries only
+	 * since lower level entries only see non-filtered entries
+	 * but upper level entries have sum of both entries.
+	 */
+	while (node) {
+		he = rb_entry(node, struct hist_entry, rb_node);
+		node = rb_next(node);
+
+		hists->stats.total_period += he->stat.period;
+		if (!he->filtered)
+			hists->stats.total_non_filtered_period += he->stat.period;
+	}
+}
+
+static void hierarchy_insert_output_entry(struct rb_root *root,
+					  struct hist_entry *he)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter;
+	struct perf_hpp_fmt *fmt;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node);
+
+		if (hist_entry__sort(he, iter) > 0)
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
+	}
+
+	rb_link_node(&he->rb_node, parent, p);
+	rb_insert_color(&he->rb_node, root);
+
+	/* update column width of dynamic entry */
+	perf_hpp_list__for_each_sort_list(he->hpp_list, fmt) {
+		if (perf_hpp__is_dynamic_entry(fmt))
+			fmt->sort(fmt, he, NULL);
+	}
+}
+
+static void hists__hierarchy_output_resort(struct hists *hists,
+					   struct ui_progress *prog,
+					   struct rb_root *root_in,
+					   struct rb_root *root_out,
+					   u64 min_callchain_hits,
+					   bool use_callchain)
+{
+	struct rb_node *node;
+	struct hist_entry *he;
+
+	*root_out = RB_ROOT;
+	node = rb_first(root_in);
+
+	while (node) {
+		he = rb_entry(node, struct hist_entry, rb_node_in);
+		node = rb_next(node);
+
+		hierarchy_insert_output_entry(root_out, he);
+
+		if (prog)
+			ui_progress__update(prog, 1);
+
+		if (!he->leaf) {
+			hists__hierarchy_output_resort(hists, prog,
+						       &he->hroot_in,
+						       &he->hroot_out,
+						       min_callchain_hits,
+						       use_callchain);
+			hists->nr_entries++;
+			if (!he->filtered) {
+				hists->nr_non_filtered_entries++;
+				hists__calc_col_len(hists, he);
+			}
+
+			continue;
+		}
+
+		if (!use_callchain)
+			continue;
+
+		if (callchain_param.mode == CHAIN_GRAPH_REL) {
+			u64 total = he->stat.period;
+
+			if (symbol_conf.cumulate_callchain)
+				total = he->stat_acc->period;
+
+			min_callchain_hits = total * (callchain_param.min_percent / 100);
+		}
+
+		callchain_param.sort(&he->sorted_chain, he->callchain,
+				     min_callchain_hits, &callchain_param);
+	}
+}
+
 static void __hists__insert_output_entry(struct rb_root *entries,
 					 struct hist_entry *he,
 					 u64 min_callchain_hits,
@@ -1162,10 +1568,20 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 	struct rb_node **p = &entries->rb_node;
 	struct rb_node *parent = NULL;
 	struct hist_entry *iter;
+	struct perf_hpp_fmt *fmt;
+
+	if (use_callchain) {
+		if (callchain_param.mode == CHAIN_GRAPH_REL) {
+			u64 total = he->stat.period;
+
+			if (symbol_conf.cumulate_callchain)
+				total = he->stat_acc->period;
 
-	if (use_callchain)
+			min_callchain_hits = total * (callchain_param.min_percent / 100);
+		}
 		callchain_param.sort(&he->sorted_chain, he->callchain,
 				      min_callchain_hits, &callchain_param);
+	}
 
 	while (*p != NULL) {
 		parent = *p;
@@ -1179,23 +1595,41 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 
 	rb_link_node(&he->rb_node, parent, p);
 	rb_insert_color(&he->rb_node, entries);
+
+	perf_hpp_list__for_each_sort_list(&perf_hpp_list, fmt) {
+		if (perf_hpp__is_dynamic_entry(fmt) &&
+		    perf_hpp__defined_dynamic_entry(fmt, he->hists))
+			fmt->sort(fmt, he, NULL);  /* update column width */
+	}
 }
 
-void hists__output_resort(struct hists *hists, struct ui_progress *prog)
+static void output_resort(struct hists *hists, struct ui_progress *prog,
+			  bool use_callchain)
 {
 	struct rb_root *root;
 	struct rb_node *next;
 	struct hist_entry *n;
+	u64 callchain_total;
 	u64 min_callchain_hits;
-	struct perf_evsel *evsel = hists_to_evsel(hists);
-	bool use_callchain;
 
-	if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph)
-		use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN;
-	else
-		use_callchain = symbol_conf.use_callchain;
+	callchain_total = hists->callchain_period;
+	if (symbol_conf.filter_relative)
+		callchain_total = hists->callchain_non_filtered_period;
 
-	min_callchain_hits = hists->stats.total_period * (callchain_param.min_percent / 100);
+	min_callchain_hits = callchain_total * (callchain_param.min_percent / 100);
+
+	hists__reset_stats(hists);
+	hists__reset_col_len(hists);
+
+	if (symbol_conf.report_hierarchy) {
+		hists__hierarchy_output_resort(hists, prog,
+					       &hists->entries_collapsed,
+					       &hists->entries,
+					       min_callchain_hits,
+					       use_callchain);
+		hierarchy_recalc_total_periods(hists);
+		return;
+	}
 
 	if (sort__need_collapse)
 		root = &hists->entries_collapsed;
@@ -1205,9 +1639,6 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 	next = rb_first(root);
 	hists->entries = RB_ROOT;
 
-	hists__reset_stats(hists);
-	hists__reset_col_len(hists);
-
 	while (next) {
 		n = rb_entry(next, struct hist_entry, rb_node_in);
 		next = rb_next(&n->rb_node_in);
@@ -1223,15 +1654,136 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 	}
 }
 
+void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog)
+{
+	bool use_callchain;
+
+	if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph)
+		use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN;
+	else
+		use_callchain = symbol_conf.use_callchain;
+
+	output_resort(evsel__hists(evsel), prog, use_callchain);
+}
+
+void hists__output_resort(struct hists *hists, struct ui_progress *prog)
+{
+	output_resort(hists, prog, symbol_conf.use_callchain);
+}
+
+static bool can_goto_child(struct hist_entry *he, enum hierarchy_move_dir hmd)
+{
+	if (he->leaf || hmd == HMD_FORCE_SIBLING)
+		return false;
+
+	if (he->unfolded || hmd == HMD_FORCE_CHILD)
+		return true;
+
+	return false;
+}
+
+struct rb_node *rb_hierarchy_last(struct rb_node *node)
+{
+	struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
+
+	while (can_goto_child(he, HMD_NORMAL)) {
+		node = rb_last(&he->hroot_out);
+		he = rb_entry(node, struct hist_entry, rb_node);
+	}
+	return node;
+}
+
+struct rb_node *__rb_hierarchy_next(struct rb_node *node, enum hierarchy_move_dir hmd)
+{
+	struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
+
+	if (can_goto_child(he, hmd))
+		node = rb_first(&he->hroot_out);
+	else
+		node = rb_next(node);
+
+	while (node == NULL) {
+		he = he->parent_he;
+		if (he == NULL)
+			break;
+
+		node = rb_next(&he->rb_node);
+	}
+	return node;
+}
+
+struct rb_node *rb_hierarchy_prev(struct rb_node *node)
+{
+	struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
+
+	node = rb_prev(node);
+	if (node)
+		return rb_hierarchy_last(node);
+
+	he = he->parent_he;
+	if (he == NULL)
+		return NULL;
+
+	return &he->rb_node;
+}
+
+bool hist_entry__has_hierarchy_children(struct hist_entry *he, float limit)
+{
+	struct rb_node *node;
+	struct hist_entry *child;
+	float percent;
+
+	if (he->leaf)
+		return false;
+
+	node = rb_first(&he->hroot_out);
+	child = rb_entry(node, struct hist_entry, rb_node);
+
+	while (node && child->filtered) {
+		node = rb_next(node);
+		child = rb_entry(node, struct hist_entry, rb_node);
+	}
+
+	if (node)
+		percent = hist_entry__get_percent_limit(child);
+	else
+		percent = 0;
+
+	return node && percent >= limit;
+}
+
 static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h,
 				       enum hist_filter filter)
 {
 	h->filtered &= ~(1 << filter);
+
+	if (symbol_conf.report_hierarchy) {
+		struct hist_entry *parent = h->parent_he;
+
+		while (parent) {
+			he_stat__add_stat(&parent->stat, &h->stat);
+
+			parent->filtered &= ~(1 << filter);
+
+			if (parent->filtered)
+				goto next;
+
+			/* force fold unfiltered entry for simplicity */
+			parent->unfolded = false;
+			parent->has_no_entry = false;
+			parent->row_offset = 0;
+			parent->nr_rows = 0;
+next:
+			parent = parent->parent_he;
+		}
+	}
+
 	if (h->filtered)
 		return;
 
 	/* force fold unfiltered entry for simplicity */
 	h->unfolded = false;
+	h->has_no_entry = false;
 	h->row_offset = 0;
 	h->nr_rows = 0;
 
@@ -1254,28 +1806,6 @@ static bool hists__filter_entry_by_dso(struct hists *hists,
 	return false;
 }
 
-void hists__filter_by_dso(struct hists *hists)
-{
-	struct rb_node *nd;
-
-	hists->stats.nr_non_filtered_samples = 0;
-
-	hists__reset_filter_stats(hists);
-	hists__reset_col_len(hists);
-
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
-		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-
-		if (symbol_conf.exclude_other && !h->parent)
-			continue;
-
-		if (hists__filter_entry_by_dso(hists, h))
-			continue;
-
-		hists__remove_entry_filter(hists, h, HIST_FILTER__DSO);
-	}
-}
-
 static bool hists__filter_entry_by_thread(struct hists *hists,
 					  struct hist_entry *he)
 {
@@ -1288,25 +1818,6 @@ static bool hists__filter_entry_by_thread(struct hists *hists,
 	return false;
 }
 
-void hists__filter_by_thread(struct hists *hists)
-{
-	struct rb_node *nd;
-
-	hists->stats.nr_non_filtered_samples = 0;
-
-	hists__reset_filter_stats(hists);
-	hists__reset_col_len(hists);
-
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
-		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-
-		if (hists__filter_entry_by_thread(hists, h))
-			continue;
-
-		hists__remove_entry_filter(hists, h, HIST_FILTER__THREAD);
-	}
-}
-
 static bool hists__filter_entry_by_symbol(struct hists *hists,
 					  struct hist_entry *he)
 {
@@ -1320,7 +1831,21 @@ static bool hists__filter_entry_by_symbol(struct hists *hists,
 	return false;
 }
 
-void hists__filter_by_symbol(struct hists *hists)
+static bool hists__filter_entry_by_socket(struct hists *hists,
+					  struct hist_entry *he)
+{
+	if ((hists->socket_filter > -1) &&
+	    (he->socket != hists->socket_filter)) {
+		he->filtered |= (1 << HIST_FILTER__SOCKET);
+		return true;
+	}
+
+	return false;
+}
+
+typedef bool (*filter_fn_t)(struct hists *hists, struct hist_entry *he);
+
+static void hists__filter_by_type(struct hists *hists, int type, filter_fn_t filter)
 {
 	struct rb_node *nd;
 
@@ -1332,42 +1857,155 @@ void hists__filter_by_symbol(struct hists *hists)
 	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
-		if (hists__filter_entry_by_symbol(hists, h))
+		if (filter(hists, h))
 			continue;
 
-		hists__remove_entry_filter(hists, h, HIST_FILTER__SYMBOL);
+		hists__remove_entry_filter(hists, h, type);
 	}
 }
 
-static bool hists__filter_entry_by_socket(struct hists *hists,
-					  struct hist_entry *he)
+static void resort_filtered_entry(struct rb_root *root, struct hist_entry *he)
 {
-	if ((hists->socket_filter > -1) &&
-	    (he->socket != hists->socket_filter)) {
-		he->filtered |= (1 << HIST_FILTER__SOCKET);
-		return true;
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter;
+	struct rb_root new_root = RB_ROOT;
+	struct rb_node *nd;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node);
+
+		if (hist_entry__sort(he, iter) > 0)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
 	}
 
-	return false;
+	rb_link_node(&he->rb_node, parent, p);
+	rb_insert_color(&he->rb_node, root);
+
+	if (he->leaf || he->filtered)
+		return;
+
+	nd = rb_first(&he->hroot_out);
+	while (nd) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		nd = rb_next(nd);
+		rb_erase(&h->rb_node, &he->hroot_out);
+
+		resort_filtered_entry(&new_root, h);
+	}
+
+	he->hroot_out = new_root;
 }
 
-void hists__filter_by_socket(struct hists *hists)
+static void hists__filter_hierarchy(struct hists *hists, int type, const void *arg)
 {
 	struct rb_node *nd;
+	struct rb_root new_root = RB_ROOT;
 
 	hists->stats.nr_non_filtered_samples = 0;
 
 	hists__reset_filter_stats(hists);
 	hists__reset_col_len(hists);
 
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+	nd = rb_first(&hists->entries);
+	while (nd) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+		int ret;
 
-		if (hists__filter_entry_by_socket(hists, h))
-			continue;
+		ret = hist_entry__filter(h, type, arg);
 
-		hists__remove_entry_filter(hists, h, HIST_FILTER__SOCKET);
+		/*
+		 * case 1. non-matching type
+		 * zero out the period, set filter marker and move to child
+		 */
+		if (ret < 0) {
+			memset(&h->stat, 0, sizeof(h->stat));
+			h->filtered |= (1 << type);
+
+			nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_CHILD);
+		}
+		/*
+		 * case 2. matched type (filter out)
+		 * set filter marker and move to next
+		 */
+		else if (ret == 1) {
+			h->filtered |= (1 << type);
+
+			nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_SIBLING);
+		}
+		/*
+		 * case 3. ok (not filtered)
+		 * add period to hists and parents, erase the filter marker
+		 * and move to next sibling
+		 */
+		else {
+			hists__remove_entry_filter(hists, h, type);
+
+			nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_SIBLING);
+		}
+	}
+
+	hierarchy_recalc_total_periods(hists);
+
+	/*
+	 * resort output after applying a new filter since filter in a lower
+	 * hierarchy can change periods in a upper hierarchy.
+	 */
+	nd = rb_first(&hists->entries);
+	while (nd) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		nd = rb_next(nd);
+		rb_erase(&h->rb_node, &hists->entries);
+
+		resort_filtered_entry(&new_root, h);
 	}
+
+	hists->entries = new_root;
+}
+
+void hists__filter_by_thread(struct hists *hists)
+{
+	if (symbol_conf.report_hierarchy)
+		hists__filter_hierarchy(hists, HIST_FILTER__THREAD,
+					hists->thread_filter);
+	else
+		hists__filter_by_type(hists, HIST_FILTER__THREAD,
+				      hists__filter_entry_by_thread);
+}
+
+void hists__filter_by_dso(struct hists *hists)
+{
+	if (symbol_conf.report_hierarchy)
+		hists__filter_hierarchy(hists, HIST_FILTER__DSO,
+					hists->dso_filter);
+	else
+		hists__filter_by_type(hists, HIST_FILTER__DSO,
+				      hists__filter_entry_by_dso);
+}
+
+void hists__filter_by_symbol(struct hists *hists)
+{
+	if (symbol_conf.report_hierarchy)
+		hists__filter_hierarchy(hists, HIST_FILTER__SYMBOL,
+					hists->symbol_filter_str);
+	else
+		hists__filter_by_type(hists, HIST_FILTER__SYMBOL,
+				      hists__filter_entry_by_symbol);
+}
+
+void hists__filter_by_socket(struct hists *hists)
+{
+	if (symbol_conf.report_hierarchy)
+		hists__filter_hierarchy(hists, HIST_FILTER__SOCKET,
+					&hists->socket_filter);
+	else
+		hists__filter_by_type(hists, HIST_FILTER__SOCKET,
+				      hists__filter_entry_by_socket);
 }
 
 void events_stats__inc(struct events_stats *stats, u32 type)
@@ -1585,7 +2223,7 @@ int perf_hist_config(const char *var, const char *value)
 	return 0;
 }
 
-int __hists__init(struct hists *hists)
+int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list)
 {
 	memset(hists, 0, sizeof(*hists));
 	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
@@ -1594,6 +2232,8 @@ int __hists__init(struct hists *hists)
 	hists->entries = RB_ROOT;
 	pthread_mutex_init(&hists->lock, NULL);
 	hists->socket_filter = -1;
+	hists->hpp_list = hpp_list;
+	INIT_LIST_HEAD(&hists->hpp_formats);
 	return 0;
 }
 
@@ -1622,15 +2262,26 @@ static void hists__delete_all_entries(struct hists *hists)
 static void hists_evsel__exit(struct perf_evsel *evsel)
 {
 	struct hists *hists = evsel__hists(evsel);
+	struct perf_hpp_fmt *fmt, *pos;
+	struct perf_hpp_list_node *node, *tmp;
 
 	hists__delete_all_entries(hists);
+
+	list_for_each_entry_safe(node, tmp, &hists->hpp_formats, list) {
+		perf_hpp_list__for_each_format_safe(&node->hpp, fmt, pos) {
+			list_del(&fmt->list);
+			free(fmt);
+		}
+		list_del(&node->list);
+		free(node);
+	}
 }
 
 static int hists_evsel__init(struct perf_evsel *evsel)
 {
 	struct hists *hists = evsel__hists(evsel);
 
-	__hists__init(hists);
+	__hists__init(hists, &perf_hpp_list);
 	return 0;
 }
 
@@ -1649,3 +2300,9 @@ int hists__init(void)
 
 	return err;
 }
+
+void perf_hpp_list__init(struct perf_hpp_list *list)
+{
+	INIT_LIST_HEAD(&list->fields);
+	INIT_LIST_HEAD(&list->sorts);
+}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index d4ec4822a103..ead18c82294f 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -66,6 +66,8 @@ struct hists {
 	struct rb_root		entries_collapsed;
 	u64			nr_entries;
 	u64			nr_non_filtered_entries;
+	u64			callchain_period;
+	u64			callchain_non_filtered_period;
 	struct thread		*thread_filter;
 	const struct dso	*dso_filter;
 	const char		*uid_filter_str;
@@ -75,6 +77,9 @@ struct hists {
 	u64			event_stream;
 	u16			col_len[HISTC_NR_COLS];
 	int			socket_filter;
+	struct perf_hpp_list	*hpp_list;
+	struct list_head	hpp_formats;
+	int			nr_hpp_node;
 };
 
 struct hist_entry_iter;
@@ -121,15 +126,21 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 			 int max_stack_depth, void *arg);
 
+struct perf_hpp;
+struct perf_hpp_fmt;
+
 int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
 int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
 int hist_entry__transaction_len(void);
 int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size,
 			      struct hists *hists);
+int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
+				   struct perf_hpp_fmt *fmt, int printed);
 void hist_entry__delete(struct hist_entry *he);
 
+void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog);
 void hists__output_resort(struct hists *hists, struct ui_progress *prog);
-void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
+int hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
 
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
 void hists__delete_entries(struct hists *hists);
@@ -185,10 +196,10 @@ static inline struct hists *evsel__hists(struct perf_evsel *evsel)
 }
 
 int hists__init(void);
-int __hists__init(struct hists *hists);
+int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list);
 
 struct rb_root *hists__get_rotate_entries_in(struct hists *hists);
-bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
+int hists__collapse_insert_entry(struct hists *hists,
 				  struct rb_root *root, struct hist_entry *he);
 
 struct perf_hpp {
@@ -214,28 +225,64 @@ struct perf_hpp_fmt {
 			    struct hist_entry *a, struct hist_entry *b);
 	int64_t (*sort)(struct perf_hpp_fmt *fmt,
 			struct hist_entry *a, struct hist_entry *b);
+	bool (*equal)(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
+	void (*free)(struct perf_hpp_fmt *fmt);
 
 	struct list_head list;
 	struct list_head sort_list;
 	bool elide;
 	int len;
 	int user_len;
+	int idx;
+	int level;
+};
+
+struct perf_hpp_list {
+	struct list_head fields;
+	struct list_head sorts;
 };
 
-extern struct list_head perf_hpp__list;
-extern struct list_head perf_hpp__sort_list;
+extern struct perf_hpp_list perf_hpp_list;
+
+struct perf_hpp_list_node {
+	struct list_head	list;
+	struct perf_hpp_list	hpp;
+	int			level;
+	bool			skip;
+};
+
+void perf_hpp_list__column_register(struct perf_hpp_list *list,
+				    struct perf_hpp_fmt *format);
+void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
+					struct perf_hpp_fmt *format);
+
+static inline void perf_hpp__column_register(struct perf_hpp_fmt *format)
+{
+	perf_hpp_list__column_register(&perf_hpp_list, format);
+}
+
+static inline void perf_hpp__register_sort_field(struct perf_hpp_fmt *format)
+{
+	perf_hpp_list__register_sort_field(&perf_hpp_list, format);
+}
+
+#define perf_hpp_list__for_each_format(_list, format) \
+	list_for_each_entry(format, &(_list)->fields, list)
 
-#define perf_hpp__for_each_format(format) \
-	list_for_each_entry(format, &perf_hpp__list, list)
+#define perf_hpp_list__for_each_format_safe(_list, format, tmp)	\
+	list_for_each_entry_safe(format, tmp, &(_list)->fields, list)
 
-#define perf_hpp__for_each_format_safe(format, tmp)	\
-	list_for_each_entry_safe(format, tmp, &perf_hpp__list, list)
+#define perf_hpp_list__for_each_sort_list(_list, format) \
+	list_for_each_entry(format, &(_list)->sorts, sort_list)
 
-#define perf_hpp__for_each_sort_list(format) \
-	list_for_each_entry(format, &perf_hpp__sort_list, sort_list)
+#define perf_hpp_list__for_each_sort_list_safe(_list, format, tmp)	\
+	list_for_each_entry_safe(format, tmp, &(_list)->sorts, sort_list)
 
-#define perf_hpp__for_each_sort_list_safe(format, tmp)	\
-	list_for_each_entry_safe(format, tmp, &perf_hpp__sort_list, sort_list)
+#define hists__for_each_format(hists, format) \
+	perf_hpp_list__for_each_format((hists)->hpp_list, fmt)
+
+#define hists__for_each_sort_list(hists, format) \
+	perf_hpp_list__for_each_sort_list((hists)->hpp_list, fmt)
 
 extern struct perf_hpp_fmt perf_hpp__format[];
 
@@ -254,21 +301,29 @@ enum {
 };
 
 void perf_hpp__init(void);
-void perf_hpp__column_register(struct perf_hpp_fmt *format);
 void perf_hpp__column_unregister(struct perf_hpp_fmt *format);
-void perf_hpp__column_enable(unsigned col);
-void perf_hpp__column_disable(unsigned col);
 void perf_hpp__cancel_cumulate(void);
+void perf_hpp__setup_output_field(struct perf_hpp_list *list);
+void perf_hpp__reset_output_field(struct perf_hpp_list *list);
+void perf_hpp__append_sort_keys(struct perf_hpp_list *list);
+int perf_hpp__setup_hists_formats(struct perf_hpp_list *list,
+				  struct perf_evlist *evlist);
 
-void perf_hpp__register_sort_field(struct perf_hpp_fmt *format);
-void perf_hpp__setup_output_field(void);
-void perf_hpp__reset_output_field(void);
-void perf_hpp__append_sort_keys(void);
 
 bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format);
-bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
 bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *format);
 bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *hists);
+bool perf_hpp__is_trace_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_srcline_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_srcfile_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_thread_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_comm_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_dso_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_sym_entry(struct perf_hpp_fmt *fmt);
+
+struct perf_hpp_fmt *perf_hpp_fmt__dup(struct perf_hpp_fmt *fmt);
+
+int hist_entry__filter(struct hist_entry *he, int type, const void *arg);
 
 static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format,
 					 struct hists *hists)
@@ -372,6 +427,7 @@ static inline int script_browse(const char *script_opt __maybe_unused)
 #endif
 
 unsigned int hists__sort_list_width(struct hists *hists);
+unsigned int hists__overhead_width(struct hists *hists);
 
 void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
 			  struct perf_sample *sample, bool nonany_branch_mode);
@@ -381,4 +437,26 @@ int parse_filter_percentage(const struct option *opt __maybe_unused,
 			    const char *arg, int unset __maybe_unused);
 int perf_hist_config(const char *var, const char *value);
 
+void perf_hpp_list__init(struct perf_hpp_list *list);
+
+enum hierarchy_move_dir {
+	HMD_NORMAL,
+	HMD_FORCE_SIBLING,
+	HMD_FORCE_CHILD,
+};
+
+struct rb_node *rb_hierarchy_last(struct rb_node *node);
+struct rb_node *__rb_hierarchy_next(struct rb_node *node,
+				    enum hierarchy_move_dir hmd);
+struct rb_node *rb_hierarchy_prev(struct rb_node *node);
+
+static inline struct rb_node *rb_hierarchy_next(struct rb_node *node)
+{
+	return __rb_hierarchy_next(node, HMD_NORMAL);
+}
+
+#define HIERARCHY_INDENT  3
+
+bool hist_entry__has_hierarchy_children(struct hist_entry *he, float limit);
+
 #endif	/* __PERF_HIST_H */
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 81a2eb77ba7f..05d815851be1 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2068,6 +2068,15 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 		err = -ENOMEM;
 		goto err_free_queues;
 	}
+
+	/*
+	 * Since this thread will not be kept in any rbtree not in a
+	 * list, initialize its list node so that at thread__put() the
+	 * current thread lifetime assuption is kept and we don't segfault
+	 * at list_del_init().
+	 */
+	INIT_LIST_HEAD(&pt->unknown_thread->node);
+
 	err = thread__set_comm(pt->unknown_thread, "unknown", 0);
 	if (err)
 		goto err_delete_thread;
diff --git a/tools/perf/util/jit.h b/tools/perf/util/jit.h
new file mode 100644
index 000000000000..a1e99da0715a
--- /dev/null
+++ b/tools/perf/util/jit.h
@@ -0,0 +1,15 @@
+#ifndef __JIT_H__
+#define __JIT_H__
+
+#include <data.h>
+
+extern int jit_process(struct perf_session *session,
+		       struct perf_data_file *output,
+		       struct machine *machine,
+		       char *filename,
+		       pid_t pid,
+		       u64 *nbytes);
+
+extern int jit_inject_record(const char *filename);
+
+#endif /* __JIT_H__ */
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
new file mode 100644
index 000000000000..cd272cc21e05
--- /dev/null
+++ b/tools/perf/util/jitdump.c
@@ -0,0 +1,697 @@
+#include <sys/types.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <inttypes.h>
+#include <byteswap.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+
+#include "util.h"
+#include "event.h"
+#include "debug.h"
+#include "evlist.h"
+#include "symbol.h"
+#include "strlist.h"
+#include <elf.h>
+
+#include "session.h"
+#include "jit.h"
+#include "jitdump.h"
+#include "genelf.h"
+#include "../builtin.h"
+
+struct jit_buf_desc {
+	struct perf_data_file *output;
+	struct perf_session *session;
+	struct machine *machine;
+	union jr_entry   *entry;
+	void             *buf;
+	uint64_t	 sample_type;
+	size_t           bufsize;
+	FILE             *in;
+	bool		 needs_bswap; /* handles cross-endianess */
+	void		 *debug_data;
+	size_t		 nr_debug_entries;
+	uint32_t         code_load_count;
+	u64		 bytes_written;
+	struct rb_root   code_root;
+	char		 dir[PATH_MAX];
+};
+
+struct debug_line_info {
+	unsigned long vma;
+	unsigned int lineno;
+	/* The filename format is unspecified, absolute path, relative etc. */
+	char const filename[0];
+};
+
+struct jit_tool {
+	struct perf_tool tool;
+	struct perf_data_file	output;
+	struct perf_data_file	input;
+	u64 bytes_written;
+};
+
+#define hmax(a, b) ((a) > (b) ? (a) : (b))
+#define get_jit_tool(t) (container_of(tool, struct jit_tool, tool))
+
+static int
+jit_emit_elf(char *filename,
+	     const char *sym,
+	     uint64_t code_addr,
+	     const void *code,
+	     int csize,
+	     void *debug,
+	     int nr_debug_entries)
+{
+	int ret, fd;
+
+	if (verbose > 0)
+		fprintf(stderr, "write ELF image %s\n", filename);
+
+	fd = open(filename, O_CREAT|O_TRUNC|O_WRONLY, 0644);
+	if (fd == -1) {
+		pr_warning("cannot create jit ELF %s: %s\n", filename, strerror(errno));
+		return -1;
+	}
+
+        ret = jit_write_elf(fd, code_addr, sym, (const void *)code, csize, debug, nr_debug_entries);
+
+        close(fd);
+
+        if (ret)
+                unlink(filename);
+
+	return ret;
+}
+
+static void
+jit_close(struct jit_buf_desc *jd)
+{
+	if (!(jd && jd->in))
+		return;
+	funlockfile(jd->in);
+	fclose(jd->in);
+	jd->in = NULL;
+}
+
+static int
+jit_validate_events(struct perf_session *session)
+{
+	struct perf_evsel *evsel;
+
+	/*
+	 * check that all events use CLOCK_MONOTONIC
+	 */
+	evlist__for_each(session->evlist, evsel) {
+		if (evsel->attr.use_clockid == 0 || evsel->attr.clockid != CLOCK_MONOTONIC)
+			return -1;
+	}
+	return 0;
+}
+
+static int
+jit_open(struct jit_buf_desc *jd, const char *name)
+{
+	struct jitheader header;
+	struct jr_prefix *prefix;
+	ssize_t bs, bsz = 0;
+	void *n, *buf = NULL;
+	int ret, retval = -1;
+
+	jd->in = fopen(name, "r");
+	if (!jd->in)
+		return -1;
+
+	bsz = hmax(sizeof(header), sizeof(*prefix));
+
+	buf = malloc(bsz);
+	if (!buf)
+		goto error;
+
+	/*
+	 * protect from writer modifying the file while we are reading it
+	 */
+	flockfile(jd->in);
+
+	ret = fread(buf, sizeof(header), 1, jd->in);
+	if (ret != 1)
+		goto error;
+
+	memcpy(&header, buf, sizeof(header));
+
+	if (header.magic != JITHEADER_MAGIC) {
+		if (header.magic != JITHEADER_MAGIC_SW)
+			goto error;
+		jd->needs_bswap = true;
+	}
+
+	if (jd->needs_bswap) {
+		header.version    = bswap_32(header.version);
+		header.total_size = bswap_32(header.total_size);
+		header.pid	  = bswap_32(header.pid);
+		header.elf_mach   = bswap_32(header.elf_mach);
+		header.timestamp  = bswap_64(header.timestamp);
+		header.flags      = bswap_64(header.flags);
+	}
+
+	if (verbose > 2)
+		pr_debug("version=%u\nhdr.size=%u\nts=0x%llx\npid=%d\nelf_mach=%d\n",
+			header.version,
+			header.total_size,
+			(unsigned long long)header.timestamp,
+			header.pid,
+			header.elf_mach);
+
+	if (header.flags & JITDUMP_FLAGS_RESERVED) {
+		pr_err("jitdump file contains invalid or unsupported flags 0x%llx\n",
+		       (unsigned long long)header.flags & JITDUMP_FLAGS_RESERVED);
+		goto error;
+	}
+
+	/*
+	 * validate event is using the correct clockid
+	 */
+	if (jit_validate_events(jd->session)) {
+		pr_err("error, jitted code must be sampled with perf record -k 1\n");
+		goto error;
+	}
+
+	bs = header.total_size - sizeof(header);
+
+	if (bs > bsz) {
+		n = realloc(buf, bs);
+		if (!n)
+			goto error;
+		bsz = bs;
+		buf = n;
+		/* read extra we do not know about */
+		ret = fread(buf, bs - bsz, 1, jd->in);
+		if (ret != 1)
+			goto error;
+	}
+	/*
+	 * keep dirname for generating files and mmap records
+	 */
+	strcpy(jd->dir, name);
+	dirname(jd->dir);
+
+	return 0;
+error:
+	funlockfile(jd->in);
+	fclose(jd->in);
+	return retval;
+}
+
+static union jr_entry *
+jit_get_next_entry(struct jit_buf_desc *jd)
+{
+	struct jr_prefix *prefix;
+	union jr_entry *jr;
+	void *addr;
+	size_t bs, size;
+	int id, ret;
+
+	if (!(jd && jd->in))
+		return NULL;
+
+	if (jd->buf == NULL) {
+		size_t sz = getpagesize();
+		if (sz < sizeof(*prefix))
+			sz = sizeof(*prefix);
+
+		jd->buf = malloc(sz);
+		if (jd->buf == NULL)
+			return NULL;
+
+		jd->bufsize = sz;
+	}
+
+	prefix = jd->buf;
+
+	/*
+	 * file is still locked at this point
+	 */
+	ret = fread(prefix, sizeof(*prefix), 1, jd->in);
+	if (ret  != 1)
+		return NULL;
+
+	if (jd->needs_bswap) {
+		prefix->id   	   = bswap_32(prefix->id);
+		prefix->total_size = bswap_32(prefix->total_size);
+		prefix->timestamp  = bswap_64(prefix->timestamp);
+	}
+	id   = prefix->id;
+	size = prefix->total_size;
+
+	bs = (size_t)size;
+	if (bs < sizeof(*prefix))
+		return NULL;
+
+	if (id >= JIT_CODE_MAX) {
+		pr_warning("next_entry: unknown prefix %d, skipping\n", id);
+		return NULL;
+	}
+	if (bs > jd->bufsize) {
+		void *n;
+		n = realloc(jd->buf, bs);
+		if (!n)
+			return NULL;
+		jd->buf = n;
+		jd->bufsize = bs;
+	}
+
+	addr = ((void *)jd->buf) + sizeof(*prefix);
+
+	ret = fread(addr, bs - sizeof(*prefix), 1, jd->in);
+	if (ret != 1)
+		return NULL;
+
+	jr = (union jr_entry *)jd->buf;
+
+	switch(id) {
+	case JIT_CODE_DEBUG_INFO:
+		if (jd->needs_bswap) {
+			uint64_t n;
+			jr->info.code_addr = bswap_64(jr->info.code_addr);
+			jr->info.nr_entry  = bswap_64(jr->info.nr_entry);
+			for (n = 0 ; n < jr->info.nr_entry; n++) {
+				jr->info.entries[n].addr    = bswap_64(jr->info.entries[n].addr);
+				jr->info.entries[n].lineno  = bswap_32(jr->info.entries[n].lineno);
+				jr->info.entries[n].discrim = bswap_32(jr->info.entries[n].discrim);
+			}
+		}
+		break;
+	case JIT_CODE_CLOSE:
+		break;
+	case JIT_CODE_LOAD:
+		if (jd->needs_bswap) {
+			jr->load.pid       = bswap_32(jr->load.pid);
+			jr->load.tid       = bswap_32(jr->load.tid);
+			jr->load.vma       = bswap_64(jr->load.vma);
+			jr->load.code_addr = bswap_64(jr->load.code_addr);
+			jr->load.code_size = bswap_64(jr->load.code_size);
+			jr->load.code_index= bswap_64(jr->load.code_index);
+		}
+		jd->code_load_count++;
+		break;
+	case JIT_CODE_MOVE:
+		if (jd->needs_bswap) {
+			jr->move.pid           = bswap_32(jr->move.pid);
+			jr->move.tid           = bswap_32(jr->move.tid);
+			jr->move.vma           = bswap_64(jr->move.vma);
+			jr->move.old_code_addr = bswap_64(jr->move.old_code_addr);
+			jr->move.new_code_addr = bswap_64(jr->move.new_code_addr);
+			jr->move.code_size     = bswap_64(jr->move.code_size);
+			jr->move.code_index    = bswap_64(jr->move.code_index);
+		}
+		break;
+	case JIT_CODE_MAX:
+	default:
+		return NULL;
+	}
+	return jr;
+}
+
+static int
+jit_inject_event(struct jit_buf_desc *jd, union perf_event *event)
+{
+	ssize_t size;
+
+	size = perf_data_file__write(jd->output, event, event->header.size);
+	if (size < 0)
+		return -1;
+
+	jd->bytes_written += size;
+	return 0;
+}
+
+static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+	struct perf_sample sample;
+	union perf_event *event;
+	struct perf_tool *tool = jd->session->tool;
+	uint64_t code, addr;
+	uintptr_t uaddr;
+	char *filename;
+	struct stat st;
+	size_t size;
+	u16 idr_size;
+	const char *sym;
+	uint32_t count;
+	int ret, csize;
+	pid_t pid, tid;
+	struct {
+		u32 pid, tid;
+		u64 time;
+	} *id;
+
+	pid   = jr->load.pid;
+	tid   = jr->load.tid;
+	csize = jr->load.code_size;
+	addr  = jr->load.code_addr;
+	sym   = (void *)((unsigned long)jr + sizeof(jr->load));
+	code  = (unsigned long)jr + jr->load.p.total_size - csize;
+	count = jr->load.code_index;
+	idr_size = jd->machine->id_hdr_size;
+
+	event = calloc(1, sizeof(*event) + idr_size);
+	if (!event)
+		return -1;
+
+	filename = event->mmap2.filename;
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%u.so",
+			jd->dir,
+			pid,
+			count);
+
+	size++; /* for \0 */
+
+	size = PERF_ALIGN(size, sizeof(u64));
+	uaddr = (uintptr_t)code;
+	ret = jit_emit_elf(filename, sym, addr, (const void *)uaddr, csize, jd->debug_data, jd->nr_debug_entries);
+
+	if (jd->debug_data && jd->nr_debug_entries) {
+		free(jd->debug_data);
+		jd->debug_data = NULL;
+		jd->nr_debug_entries = 0;
+	}
+
+	if (ret) {
+		free(event);
+		return -1;
+	}
+	if (stat(filename, &st))
+		memset(&st, 0, sizeof(stat));
+
+	event->mmap2.header.type = PERF_RECORD_MMAP2;
+	event->mmap2.header.misc = PERF_RECORD_MISC_USER;
+	event->mmap2.header.size = (sizeof(event->mmap2) -
+			(sizeof(event->mmap2.filename) - size) + idr_size);
+
+	event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET;
+	event->mmap2.start = addr;
+	event->mmap2.len   = csize;
+	event->mmap2.pid   = pid;
+	event->mmap2.tid   = tid;
+	event->mmap2.ino   = st.st_ino;
+	event->mmap2.maj   = major(st.st_dev);
+	event->mmap2.min   = minor(st.st_dev);
+	event->mmap2.prot  = st.st_mode;
+	event->mmap2.flags = MAP_SHARED;
+	event->mmap2.ino_generation = 1;
+
+	id = (void *)((unsigned long)event + event->mmap.header.size - idr_size);
+	if (jd->sample_type & PERF_SAMPLE_TID) {
+		id->pid  = pid;
+		id->tid  = tid;
+	}
+	if (jd->sample_type & PERF_SAMPLE_TIME)
+		id->time = jr->load.p.timestamp;
+
+	/*
+	 * create pseudo sample to induce dso hit increment
+	 * use first address as sample address
+	 */
+	memset(&sample, 0, sizeof(sample));
+	sample.pid  = pid;
+	sample.tid  = tid;
+	sample.time = id->time;
+	sample.ip   = addr;
+
+	ret = perf_event__process_mmap2(tool, event, &sample, jd->machine);
+	if (ret)
+		return ret;
+
+	ret = jit_inject_event(jd, event);
+	/*
+	 * mark dso as use to generate buildid in the header
+	 */
+	if (!ret)
+		build_id__mark_dso_hit(tool, event, &sample, NULL, jd->machine);
+
+	return ret;
+}
+
+static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+	struct perf_sample sample;
+	union perf_event *event;
+	struct perf_tool *tool = jd->session->tool;
+	char *filename;
+	size_t size;
+	struct stat st;
+	u16 idr_size;
+	int ret;
+	pid_t pid, tid;
+	struct {
+		u32 pid, tid;
+		u64 time;
+	} *id;
+
+	pid = jr->move.pid;
+	tid =  jr->move.tid;
+	idr_size = jd->machine->id_hdr_size;
+
+	/*
+	 * +16 to account for sample_id_all (hack)
+	 */
+	event = calloc(1, sizeof(*event) + 16);
+	if (!event)
+		return -1;
+
+	filename = event->mmap2.filename;
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%"PRIu64,
+	         jd->dir,
+	         pid,
+		 jr->move.code_index);
+
+	size++; /* for \0 */
+
+	if (stat(filename, &st))
+		memset(&st, 0, sizeof(stat));
+
+	size = PERF_ALIGN(size, sizeof(u64));
+
+	event->mmap2.header.type = PERF_RECORD_MMAP2;
+	event->mmap2.header.misc = PERF_RECORD_MISC_USER;
+	event->mmap2.header.size = (sizeof(event->mmap2) -
+			(sizeof(event->mmap2.filename) - size) + idr_size);
+	event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET;
+	event->mmap2.start = jr->move.new_code_addr;
+	event->mmap2.len   = jr->move.code_size;
+	event->mmap2.pid   = pid;
+	event->mmap2.tid   = tid;
+	event->mmap2.ino   = st.st_ino;
+	event->mmap2.maj   = major(st.st_dev);
+	event->mmap2.min   = minor(st.st_dev);
+	event->mmap2.prot  = st.st_mode;
+	event->mmap2.flags = MAP_SHARED;
+	event->mmap2.ino_generation = 1;
+
+	id = (void *)((unsigned long)event + event->mmap.header.size - idr_size);
+	if (jd->sample_type & PERF_SAMPLE_TID) {
+		id->pid  = pid;
+		id->tid  = tid;
+	}
+	if (jd->sample_type & PERF_SAMPLE_TIME)
+		id->time = jr->load.p.timestamp;
+
+	/*
+	 * create pseudo sample to induce dso hit increment
+	 * use first address as sample address
+	 */
+	memset(&sample, 0, sizeof(sample));
+	sample.pid  = pid;
+	sample.tid  = tid;
+	sample.time = id->time;
+	sample.ip   = jr->move.new_code_addr;
+
+	ret = perf_event__process_mmap2(tool, event, &sample, jd->machine);
+	if (ret)
+		return ret;
+
+	ret = jit_inject_event(jd, event);
+	if (!ret)
+		build_id__mark_dso_hit(tool, event, &sample, NULL, jd->machine);
+
+	return ret;
+}
+
+static int jit_repipe_debug_info(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+	void *data;
+	size_t sz;
+
+	if (!(jd && jr))
+		return -1;
+
+	sz  = jr->prefix.total_size - sizeof(jr->info);
+	data = malloc(sz);
+	if (!data)
+		return -1;
+
+	memcpy(data, &jr->info.entries, sz);
+
+	jd->debug_data       = data;
+
+	/*
+	 * we must use nr_entry instead of size here because
+	 * we cannot distinguish actual entry from padding otherwise
+	 */
+	jd->nr_debug_entries = jr->info.nr_entry;
+
+	return 0;
+}
+
+static int
+jit_process_dump(struct jit_buf_desc *jd)
+{
+	union jr_entry *jr;
+	int ret;
+
+	while ((jr = jit_get_next_entry(jd))) {
+		switch(jr->prefix.id) {
+		case JIT_CODE_LOAD:
+			ret = jit_repipe_code_load(jd, jr);
+			break;
+		case JIT_CODE_MOVE:
+			ret = jit_repipe_code_move(jd, jr);
+			break;
+		case JIT_CODE_DEBUG_INFO:
+			ret = jit_repipe_debug_info(jd, jr);
+			break;
+		default:
+			ret = 0;
+			continue;
+		}
+	}
+	return ret;
+}
+
+static int
+jit_inject(struct jit_buf_desc *jd, char *path)
+{
+	int ret;
+
+	if (verbose > 0)
+		fprintf(stderr, "injecting: %s\n", path);
+
+	ret = jit_open(jd, path);
+	if (ret)
+		return -1;
+
+	ret = jit_process_dump(jd);
+
+	jit_close(jd);
+
+	if (verbose > 0)
+		fprintf(stderr, "injected: %s (%d)\n", path, ret);
+
+	return 0;
+}
+
+/*
+ * File must be with pattern .../jit-XXXX.dump
+ * where XXXX is the PID of the process which did the mmap()
+ * as captured in the RECORD_MMAP record
+ */
+static int
+jit_detect(char *mmap_name, pid_t pid)
+ {
+	char *p;
+	char *end = NULL;
+	pid_t pid2;
+
+	if (verbose > 2)
+		fprintf(stderr, "jit marker trying : %s\n", mmap_name);
+	/*
+	 * get file name
+	 */
+	p = strrchr(mmap_name, '/');
+	if (!p)
+		return -1;
+
+	/*
+	 * match prefix
+	 */
+	if (strncmp(p, "/jit-", 5))
+		return -1;
+
+	/*
+	 * skip prefix
+	 */
+	p += 5;
+
+	/*
+	 * must be followed by a pid
+	 */
+	if (!isdigit(*p))
+		return -1;
+
+	pid2 = (int)strtol(p, &end, 10);
+	if (!end)
+		return -1;
+
+	/*
+	 * pid does not match mmap pid
+	 * pid==0 in system-wide mode (synthesized)
+	 */
+	if (pid && pid2 != pid)
+		return -1;
+	/*
+	 * validate suffix
+	 */
+	if (strcmp(end, ".dump"))
+		return -1;
+
+	if (verbose > 0)
+		fprintf(stderr, "jit marker found: %s\n", mmap_name);
+
+	return 0;
+}
+
+int
+jit_process(struct perf_session *session,
+	    struct perf_data_file *output,
+	    struct machine *machine,
+	    char *filename,
+	    pid_t pid,
+	    u64 *nbytes)
+{
+	struct perf_evsel *first;
+	struct jit_buf_desc jd;
+	int ret;
+
+	/*
+	 * first, detect marker mmap (i.e., the jitdump mmap)
+	 */
+	if (jit_detect(filename, pid))
+		return 0;
+
+	memset(&jd, 0, sizeof(jd));
+
+	jd.session = session;
+	jd.output  = output;
+	jd.machine = machine;
+
+	/*
+	 * track sample_type to compute id_all layout
+	 * perf sets the same sample type to all events as of now
+	 */
+	first = perf_evlist__first(session->evlist);
+	jd.sample_type = first->attr.sample_type;
+
+	*nbytes = 0;
+
+	ret = jit_inject(&jd, filename);
+	if (!ret) {
+		*nbytes = jd.bytes_written;
+		ret = 1;
+	}
+
+	return ret;
+}
diff --git a/tools/perf/util/jitdump.h b/tools/perf/util/jitdump.h
new file mode 100644
index 000000000000..b66c1f503d9e
--- /dev/null
+++ b/tools/perf/util/jitdump.h
@@ -0,0 +1,124 @@
+/*
+ * jitdump.h: jitted code info encapsulation file format
+ *
+ * Adapted from OProfile GPLv2 support jidump.h:
+ * Copyright 2007 OProfile authors
+ * Jens Wilke
+ * Daniel Hansel
+ * Copyright IBM Corporation 2007
+ */
+#ifndef JITDUMP_H
+#define JITDUMP_H
+
+#include <sys/time.h>
+#include <time.h>
+#include <stdint.h>
+
+/* JiTD */
+#define JITHEADER_MAGIC		0x4A695444
+#define JITHEADER_MAGIC_SW	0x4454694A
+
+#define PADDING_8ALIGNED(x) ((((x) + 7) & 7) ^ 7)
+
+#define JITHEADER_VERSION 1
+
+enum jitdump_flags_bits {
+	JITDUMP_FLAGS_MAX_BIT,
+};
+
+#define JITDUMP_FLAGS_RESERVED (JITDUMP_FLAGS_MAX_BIT < 64 ? \
+				(~((1ULL << JITDUMP_FLAGS_MAX_BIT) - 1)) : 0)
+
+struct jitheader {
+	uint32_t magic;		/* characters "jItD" */
+	uint32_t version;	/* header version */
+	uint32_t total_size;	/* total size of header */
+	uint32_t elf_mach;	/* elf mach target */
+	uint32_t pad1;		/* reserved */
+	uint32_t pid;		/* JIT process id */
+	uint64_t timestamp;	/* timestamp */
+	uint64_t flags;		/* flags */
+};
+
+enum jit_record_type {
+	JIT_CODE_LOAD		= 0,
+        JIT_CODE_MOVE           = 1,
+	JIT_CODE_DEBUG_INFO	= 2,
+	JIT_CODE_CLOSE		= 3,
+
+	JIT_CODE_MAX,
+};
+
+/* record prefix (mandatory in each record) */
+struct jr_prefix {
+	uint32_t id;
+	uint32_t total_size;
+	uint64_t timestamp;
+};
+
+struct jr_code_load {
+	struct jr_prefix p;
+
+	uint32_t pid;
+	uint32_t tid;
+	uint64_t vma;
+	uint64_t code_addr;
+	uint64_t code_size;
+	uint64_t code_index;
+};
+
+struct jr_code_close {
+	struct jr_prefix p;
+};
+
+struct jr_code_move {
+	struct jr_prefix p;
+
+	uint32_t pid;
+	uint32_t tid;
+	uint64_t vma;
+	uint64_t old_code_addr;
+	uint64_t new_code_addr;
+	uint64_t code_size;
+	uint64_t code_index;
+};
+
+struct debug_entry {
+	uint64_t addr;
+	int lineno;	    /* source line number starting at 1 */
+	int discrim;	    /* column discriminator, 0 is default */
+	const char name[0]; /* null terminated filename, \xff\0 if same as previous entry */
+};
+
+struct jr_code_debug_info {
+	struct jr_prefix p;
+
+	uint64_t code_addr;
+	uint64_t nr_entry;
+	struct debug_entry entries[0];
+};
+
+union jr_entry {
+        struct jr_code_debug_info info;
+        struct jr_code_close close;
+        struct jr_code_load load;
+        struct jr_code_move move;
+        struct jr_prefix prefix;
+};
+
+static inline struct debug_entry *
+debug_entry_next(struct debug_entry *ent)
+{
+	void *a = ent + 1;
+	size_t l = strlen(ent->name) + 1;
+	return a + l;
+}
+
+static inline char *
+debug_entry_file(struct debug_entry *ent)
+{
+	void *a = ent + 1;
+	return a;
+}
+
+#endif /* !JITDUMP_H */
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
index ae825d4ec110..d01e73592f6e 100644
--- a/tools/perf/util/kvm-stat.h
+++ b/tools/perf/util/kvm-stat.h
@@ -122,6 +122,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm,
 
 bool kvm_exit_event(struct perf_evsel *evsel);
 bool kvm_entry_event(struct perf_evsel *evsel);
+int setup_kvm_events_tp(struct perf_kvm_stat *kvm);
 
 #define define_exit_reasons_table(name, symbols)	\
 	static struct exit_reasons_table name[] = {	\
@@ -133,8 +134,13 @@ bool kvm_entry_event(struct perf_evsel *evsel);
  */
 int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid);
 
-extern const char * const kvm_events_tp[];
+extern const char *kvm_events_tp[];
 extern struct kvm_reg_events_ops kvm_reg_events_ops[];
 extern const char * const kvm_skip_events[];
+extern const char *vcpu_id_str;
+extern const int decode_str_len;
+extern const char *kvm_exit_reason;
+extern const char *kvm_entry_trace;
+extern const char *kvm_exit_trace;
 
 #endif /* __PERF_KVM_STAT_H */
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 2c2b443df5ba..1a3e45baf97f 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -180,6 +180,16 @@ struct symbol *machine__find_kernel_symbol(struct machine *machine,
 }
 
 static inline
+struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine,
+						   enum map_type type, const char *name,
+						   struct map **mapp,
+						   symbol_filter_t filter)
+{
+	return map_groups__find_symbol_by_name(&machine->kmaps, type, name,
+					       mapp, filter);
+}
+
+static inline
 struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr,
 					     struct map **mapp,
 					     symbol_filter_t filter)
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
new file mode 100644
index 000000000000..75465f89a413
--- /dev/null
+++ b/tools/perf/util/mem-events.c
@@ -0,0 +1,255 @@
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <api/fs/fs.h>
+#include "mem-events.h"
+#include "debug.h"
+#include "symbol.h"
+
+#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
+
+struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
+	E("ldlat-loads",	"cpu/mem-loads,ldlat=30/P",	"mem-loads"),
+	E("ldlat-stores",	"cpu/mem-stores/P",		"mem-stores"),
+};
+#undef E
+
+#undef E
+
+char *perf_mem_events__name(int i)
+{
+	return (char *)perf_mem_events[i].name;
+}
+
+int perf_mem_events__parse(const char *str)
+{
+	char *tok, *saveptr = NULL;
+	bool found = false;
+	char *buf;
+	int j;
+
+	/* We need buffer that we know we can write to. */
+	buf = malloc(strlen(str) + 1);
+	if (!buf)
+		return -ENOMEM;
+
+	strcpy(buf, str);
+
+	tok = strtok_r((char *)buf, ",", &saveptr);
+
+	while (tok) {
+		for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+			struct perf_mem_event *e = &perf_mem_events[j];
+
+			if (strstr(e->tag, tok))
+				e->record = found = true;
+		}
+
+		tok = strtok_r(NULL, ",", &saveptr);
+	}
+
+	free(buf);
+
+	if (found)
+		return 0;
+
+	pr_err("failed: event '%s' not found, use '-e list' to get list of available events\n", str);
+	return -1;
+}
+
+int perf_mem_events__init(void)
+{
+	const char *mnt = sysfs__mount();
+	bool found = false;
+	int j;
+
+	if (!mnt)
+		return -ENOENT;
+
+	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+		char path[PATH_MAX];
+		struct perf_mem_event *e = &perf_mem_events[j];
+		struct stat st;
+
+		scnprintf(path, PATH_MAX, "%s/devices/cpu/events/%s",
+			  mnt, e->sysfs_name);
+
+		if (!stat(path, &st))
+			e->supported = found = true;
+	}
+
+	return found ? 0 : -ENOENT;
+}
+
+static const char * const tlb_access[] = {
+	"N/A",
+	"HIT",
+	"MISS",
+	"L1",
+	"L2",
+	"Walker",
+	"Fault",
+};
+
+int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	size_t l = 0, i;
+	u64 m = PERF_MEM_TLB_NA;
+	u64 hit, miss;
+
+	sz -= 1; /* -1 for null termination */
+	out[0] = '\0';
+
+	if (mem_info)
+		m = mem_info->data_src.mem_dtlb;
+
+	hit = m & PERF_MEM_TLB_HIT;
+	miss = m & PERF_MEM_TLB_MISS;
+
+	/* already taken care of */
+	m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
+
+	for (i = 0; m && i < ARRAY_SIZE(tlb_access); i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		l += scnprintf(out + l, sz - l, tlb_access[i]);
+	}
+	if (*out == '\0')
+		l += scnprintf(out, sz - l, "N/A");
+	if (hit)
+		l += scnprintf(out + l, sz - l, " hit");
+	if (miss)
+		l += scnprintf(out + l, sz - l, " miss");
+
+	return l;
+}
+
+static const char * const mem_lvl[] = {
+	"N/A",
+	"HIT",
+	"MISS",
+	"L1",
+	"LFB",
+	"L2",
+	"L3",
+	"Local RAM",
+	"Remote RAM (1 hop)",
+	"Remote RAM (2 hops)",
+	"Remote Cache (1 hop)",
+	"Remote Cache (2 hops)",
+	"I/O",
+	"Uncached",
+};
+
+int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	size_t i, l = 0;
+	u64 m =  PERF_MEM_LVL_NA;
+	u64 hit, miss;
+
+	if (mem_info)
+		m  = mem_info->data_src.mem_lvl;
+
+	sz -= 1; /* -1 for null termination */
+	out[0] = '\0';
+
+	hit = m & PERF_MEM_LVL_HIT;
+	miss = m & PERF_MEM_LVL_MISS;
+
+	/* already taken care of */
+	m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
+
+	for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		l += scnprintf(out + l, sz - l, mem_lvl[i]);
+	}
+	if (*out == '\0')
+		l += scnprintf(out, sz - l, "N/A");
+	if (hit)
+		l += scnprintf(out + l, sz - l, " hit");
+	if (miss)
+		l += scnprintf(out + l, sz - l, " miss");
+
+	return l;
+}
+
+static const char * const snoop_access[] = {
+	"N/A",
+	"None",
+	"Miss",
+	"Hit",
+	"HitM",
+};
+
+int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	size_t i, l = 0;
+	u64 m = PERF_MEM_SNOOP_NA;
+
+	sz -= 1; /* -1 for null termination */
+	out[0] = '\0';
+
+	if (mem_info)
+		m = mem_info->data_src.mem_snoop;
+
+	for (i = 0; m && i < ARRAY_SIZE(snoop_access); i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		l += scnprintf(out + l, sz - l, snoop_access[i]);
+	}
+
+	if (*out == '\0')
+		l += scnprintf(out, sz - l, "N/A");
+
+	return l;
+}
+
+int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	u64 mask = PERF_MEM_LOCK_NA;
+	int l;
+
+	if (mem_info)
+		mask = mem_info->data_src.mem_lock;
+
+	if (mask & PERF_MEM_LOCK_NA)
+		l = scnprintf(out, sz, "N/A");
+	else if (mask & PERF_MEM_LOCK_LOCKED)
+		l = scnprintf(out, sz, "Yes");
+	else
+		l = scnprintf(out, sz, "No");
+
+	return l;
+}
+
+int perf_script__meminfo_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	int i = 0;
+
+	i += perf_mem__lvl_scnprintf(out, sz, mem_info);
+	i += scnprintf(out + i, sz - i, "|SNP ");
+	i += perf_mem__snp_scnprintf(out + i, sz - i, mem_info);
+	i += scnprintf(out + i, sz - i, "|TLB ");
+	i += perf_mem__tlb_scnprintf(out + i, sz - i, mem_info);
+	i += scnprintf(out + i, sz - i, "|LCK ");
+	i += perf_mem__lck_scnprintf(out + i, sz - i, mem_info);
+
+	return i;
+}
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
new file mode 100644
index 000000000000..5d6d93066a6e
--- /dev/null
+++ b/tools/perf/util/mem-events.h
@@ -0,0 +1,35 @@
+#ifndef __PERF_MEM_EVENTS_H
+#define __PERF_MEM_EVENTS_H
+
+#include <stdbool.h>
+
+struct perf_mem_event {
+	bool		record;
+	bool		supported;
+	const char	*tag;
+	const char	*name;
+	const char	*sysfs_name;
+};
+
+enum {
+	PERF_MEM_EVENTS__LOAD,
+	PERF_MEM_EVENTS__STORE,
+	PERF_MEM_EVENTS__MAX,
+};
+
+extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
+
+int perf_mem_events__parse(const char *str);
+int perf_mem_events__init(void);
+
+char *perf_mem_events__name(int i);
+
+struct mem_info;
+int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+
+int perf_script__meminfo_scnprintf(char *bf, size_t size, struct mem_info *mem_info);
+
+#endif /* __PERF_MEM_EVENTS_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 4f7b0efdde2f..4c19d5e79d8c 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -279,7 +279,24 @@ const char *event_type(int type)
 	return "unknown";
 }
 
+static int parse_events__is_name_term(struct parse_events_term *term)
+{
+	return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME;
+}
+
+static char *get_config_name(struct list_head *head_terms)
+{
+	struct parse_events_term *term;
+
+	if (!head_terms)
+		return NULL;
 
+	list_for_each_entry(term, head_terms, list)
+		if (parse_events__is_name_term(term))
+			return term->val.str;
+
+	return NULL;
+}
 
 static struct perf_evsel *
 __add_event(struct list_head *list, int *idx,
@@ -333,11 +350,25 @@ static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES]
 	return -1;
 }
 
+typedef int config_term_func_t(struct perf_event_attr *attr,
+			       struct parse_events_term *term,
+			       struct parse_events_error *err);
+static int config_term_common(struct perf_event_attr *attr,
+			      struct parse_events_term *term,
+			      struct parse_events_error *err);
+static int config_attr(struct perf_event_attr *attr,
+		       struct list_head *head,
+		       struct parse_events_error *err,
+		       config_term_func_t config_term);
+
 int parse_events_add_cache(struct list_head *list, int *idx,
-			   char *type, char *op_result1, char *op_result2)
+			   char *type, char *op_result1, char *op_result2,
+			   struct parse_events_error *err,
+			   struct list_head *head_config)
 {
 	struct perf_event_attr attr;
-	char name[MAX_NAME_LEN];
+	LIST_HEAD(config_terms);
+	char name[MAX_NAME_LEN], *config_name;
 	int cache_type = -1, cache_op = -1, cache_result = -1;
 	char *op_result[2] = { op_result1, op_result2 };
 	int i, n;
@@ -351,6 +382,7 @@ int parse_events_add_cache(struct list_head *list, int *idx,
 	if (cache_type == -1)
 		return -EINVAL;
 
+	config_name = get_config_name(head_config);
 	n = snprintf(name, MAX_NAME_LEN, "%s", type);
 
 	for (i = 0; (i < 2) && (op_result[i]); i++) {
@@ -391,7 +423,16 @@ int parse_events_add_cache(struct list_head *list, int *idx,
 	memset(&attr, 0, sizeof(attr));
 	attr.config = cache_type | (cache_op << 8) | (cache_result << 16);
 	attr.type = PERF_TYPE_HW_CACHE;
-	return add_event(list, idx, &attr, name, NULL);
+
+	if (head_config) {
+		if (config_attr(&attr, head_config, err,
+				config_term_common))
+			return -EINVAL;
+
+		if (get_config_terms(head_config, &config_terms))
+			return -ENOMEM;
+	}
+	return add_event(list, idx, &attr, config_name ? : name, &config_terms);
 }
 
 static void tracepoint_error(struct parse_events_error *e, int err,
@@ -399,6 +440,9 @@ static void tracepoint_error(struct parse_events_error *e, int err,
 {
 	char help[BUFSIZ];
 
+	if (!e)
+		return;
+
 	/*
 	 * We get error directly from syscall errno ( > 0),
 	 * or from encoded pointer's error ( < 0).
@@ -537,6 +581,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 struct __add_bpf_event_param {
 	struct parse_events_evlist *data;
 	struct list_head *list;
+	struct list_head *head_config;
 };
 
 static int add_bpf_event(struct probe_trace_event *tev, int fd,
@@ -553,7 +598,8 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd,
 		 tev->group, tev->event, fd);
 
 	err = parse_events_add_tracepoint(&new_evsels, &evlist->idx, tev->group,
-					  tev->event, evlist->error, NULL);
+					  tev->event, evlist->error,
+					  param->head_config);
 	if (err) {
 		struct perf_evsel *evsel, *tmp;
 
@@ -578,11 +624,12 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd,
 
 int parse_events_load_bpf_obj(struct parse_events_evlist *data,
 			      struct list_head *list,
-			      struct bpf_object *obj)
+			      struct bpf_object *obj,
+			      struct list_head *head_config)
 {
 	int err;
 	char errbuf[BUFSIZ];
-	struct __add_bpf_event_param param = {data, list};
+	struct __add_bpf_event_param param = {data, list, head_config};
 	static bool registered_unprobe_atexit = false;
 
 	if (IS_ERR(obj) || !obj) {
@@ -628,17 +675,99 @@ errout:
 	return err;
 }
 
+static int
+parse_events_config_bpf(struct parse_events_evlist *data,
+			struct bpf_object *obj,
+			struct list_head *head_config)
+{
+	struct parse_events_term *term;
+	int error_pos;
+
+	if (!head_config || list_empty(head_config))
+		return 0;
+
+	list_for_each_entry(term, head_config, list) {
+		char errbuf[BUFSIZ];
+		int err;
+
+		if (term->type_term != PARSE_EVENTS__TERM_TYPE_USER) {
+			snprintf(errbuf, sizeof(errbuf),
+				 "Invalid config term for BPF object");
+			errbuf[BUFSIZ - 1] = '\0';
+
+			data->error->idx = term->err_term;
+			data->error->str = strdup(errbuf);
+			return -EINVAL;
+		}
+
+		err = bpf__config_obj(obj, term, data->evlist, &error_pos);
+		if (err) {
+			bpf__strerror_config_obj(obj, term, data->evlist,
+						 &error_pos, err, errbuf,
+						 sizeof(errbuf));
+			data->error->help = strdup(
+"Hint:\tValid config terms:\n"
+"     \tmap:[<arraymap>].value<indices>=[value]\n"
+"     \tmap:[<eventmap>].event<indices>=[event]\n"
+"\n"
+"     \twhere <indices> is something like [0,3...5] or [all]\n"
+"     \t(add -v to see detail)");
+			data->error->str = strdup(errbuf);
+			if (err == -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE)
+				data->error->idx = term->err_val;
+			else
+				data->error->idx = term->err_term + error_pos;
+			return err;
+		}
+	}
+	return 0;
+}
+
+/*
+ * Split config terms:
+ * perf record -e bpf.c/call-graph=fp,map:array.value[0]=1/ ...
+ *  'call-graph=fp' is 'evt config', should be applied to each
+ *  events in bpf.c.
+ * 'map:array.value[0]=1' is 'obj config', should be processed
+ * with parse_events_config_bpf.
+ *
+ * Move object config terms from the first list to obj_head_config.
+ */
+static void
+split_bpf_config_terms(struct list_head *evt_head_config,
+		       struct list_head *obj_head_config)
+{
+	struct parse_events_term *term, *temp;
+
+	/*
+	 * Currectly, all possible user config term
+	 * belong to bpf object. parse_events__is_hardcoded_term()
+	 * happends to be a good flag.
+	 *
+	 * See parse_events_config_bpf() and
+	 * config_term_tracepoint().
+	 */
+	list_for_each_entry_safe(term, temp, evt_head_config, list)
+		if (!parse_events__is_hardcoded_term(term))
+			list_move_tail(&term->list, obj_head_config);
+}
+
 int parse_events_load_bpf(struct parse_events_evlist *data,
 			  struct list_head *list,
 			  char *bpf_file_name,
-			  bool source)
+			  bool source,
+			  struct list_head *head_config)
 {
+	int err;
 	struct bpf_object *obj;
+	LIST_HEAD(obj_head_config);
+
+	if (head_config)
+		split_bpf_config_terms(head_config, &obj_head_config);
 
 	obj = bpf__prepare_load(bpf_file_name, source);
 	if (IS_ERR(obj)) {
 		char errbuf[BUFSIZ];
-		int err;
 
 		err = PTR_ERR(obj);
 
@@ -656,7 +785,18 @@ int parse_events_load_bpf(struct parse_events_evlist *data,
 		return err;
 	}
 
-	return parse_events_load_bpf_obj(data, list, obj);
+	err = parse_events_load_bpf_obj(data, list, obj, head_config);
+	if (err)
+		return err;
+	err = parse_events_config_bpf(data, obj, &obj_head_config);
+
+	/*
+	 * Caller doesn't know anything about obj_head_config,
+	 * so combine them together again before returnning.
+	 */
+	if (head_config)
+		list_splice_tail(&obj_head_config, head_config);
+	return err;
 }
 
 static int
@@ -743,9 +883,59 @@ static int check_type_val(struct parse_events_term *term,
 	return -EINVAL;
 }
 
-typedef int config_term_func_t(struct perf_event_attr *attr,
-			       struct parse_events_term *term,
-			       struct parse_events_error *err);
+/*
+ * Update according to parse-events.l
+ */
+static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
+	[PARSE_EVENTS__TERM_TYPE_USER]			= "<sysfs term>",
+	[PARSE_EVENTS__TERM_TYPE_CONFIG]		= "config",
+	[PARSE_EVENTS__TERM_TYPE_CONFIG1]		= "config1",
+	[PARSE_EVENTS__TERM_TYPE_CONFIG2]		= "config2",
+	[PARSE_EVENTS__TERM_TYPE_NAME]			= "name",
+	[PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD]		= "period",
+	[PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ]		= "freq",
+	[PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE]	= "branch_type",
+	[PARSE_EVENTS__TERM_TYPE_TIME]			= "time",
+	[PARSE_EVENTS__TERM_TYPE_CALLGRAPH]		= "call-graph",
+	[PARSE_EVENTS__TERM_TYPE_STACKSIZE]		= "stack-size",
+	[PARSE_EVENTS__TERM_TYPE_NOINHERIT]		= "no-inherit",
+	[PARSE_EVENTS__TERM_TYPE_INHERIT]		= "inherit",
+};
+
+static bool config_term_shrinked;
+
+static bool
+config_term_avail(int term_type, struct parse_events_error *err)
+{
+	if (term_type < 0 || term_type >= __PARSE_EVENTS__TERM_TYPE_NR) {
+		err->str = strdup("Invalid term_type");
+		return false;
+	}
+	if (!config_term_shrinked)
+		return true;
+
+	switch (term_type) {
+	case PARSE_EVENTS__TERM_TYPE_CONFIG:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+	case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+	case PARSE_EVENTS__TERM_TYPE_NAME:
+		return true;
+	default:
+		if (!err)
+			return false;
+
+		/* term_type is validated so indexing is safe */
+		if (asprintf(&err->str, "'%s' is not usable in 'perf stat'",
+			     config_term_names[term_type]) < 0)
+			err->str = NULL;
+		return false;
+	}
+}
+
+void parse_events__shrink_config_terms(void)
+{
+	config_term_shrinked = true;
+}
 
 static int config_term_common(struct perf_event_attr *attr,
 			      struct parse_events_term *term,
@@ -812,6 +1002,17 @@ do {									   \
 		return -EINVAL;
 	}
 
+	/*
+	 * Check term availbility after basic checking so
+	 * PARSE_EVENTS__TERM_TYPE_USER can be found and filtered.
+	 *
+	 * If check availbility at the entry of this function,
+	 * user will see "'<sysfs term>' is not usable in 'perf stat'"
+	 * if an invalid config term is provided for legacy events
+	 * (for example, instructions/badterm/...), which is confusing.
+	 */
+	if (!config_term_avail(term->type_term, err))
+		return -EINVAL;
 	return 0;
 #undef CHECK_TYPE_VAL
 }
@@ -958,23 +1159,8 @@ int parse_events_add_numeric(struct parse_events_evlist *data,
 			return -ENOMEM;
 	}
 
-	return add_event(list, &data->idx, &attr, NULL, &config_terms);
-}
-
-static int parse_events__is_name_term(struct parse_events_term *term)
-{
-	return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME;
-}
-
-static char *pmu_event_name(struct list_head *head_terms)
-{
-	struct parse_events_term *term;
-
-	list_for_each_entry(term, head_terms, list)
-		if (parse_events__is_name_term(term))
-			return term->val.str;
-
-	return NULL;
+	return add_event(list, &data->idx, &attr,
+			 get_config_name(head_config), &config_terms);
 }
 
 int parse_events_add_pmu(struct parse_events_evlist *data,
@@ -1021,7 +1207,7 @@ int parse_events_add_pmu(struct parse_events_evlist *data,
 		return -EINVAL;
 
 	evsel = __add_event(list, &data->idx, &attr,
-			    pmu_event_name(head_config), pmu->cpus,
+			    get_config_name(head_config), pmu->cpus,
 			    &config_terms);
 	if (evsel) {
 		evsel->unit = info.unit;
@@ -1383,8 +1569,7 @@ int parse_events_terms(struct list_head *terms, const char *str)
 		return 0;
 	}
 
-	if (data.terms)
-		parse_events__free_terms(data.terms);
+	parse_events_terms__delete(data.terms);
 	return ret;
 }
 
@@ -1392,9 +1577,10 @@ int parse_events(struct perf_evlist *evlist, const char *str,
 		 struct parse_events_error *err)
 {
 	struct parse_events_evlist data = {
-		.list  = LIST_HEAD_INIT(data.list),
-		.idx   = evlist->nr_entries,
-		.error = err,
+		.list   = LIST_HEAD_INIT(data.list),
+		.idx    = evlist->nr_entries,
+		.error  = err,
+		.evlist = evlist,
 	};
 	int ret;
 
@@ -2065,12 +2251,29 @@ int parse_events_term__clone(struct parse_events_term **new,
 			term->err_term, term->err_val);
 }
 
-void parse_events__free_terms(struct list_head *terms)
+void parse_events_terms__purge(struct list_head *terms)
 {
 	struct parse_events_term *term, *h;
 
-	list_for_each_entry_safe(term, h, terms, list)
+	list_for_each_entry_safe(term, h, terms, list) {
+		if (term->array.nr_ranges)
+			free(term->array.ranges);
+		list_del_init(&term->list);
 		free(term);
+	}
+}
+
+void parse_events_terms__delete(struct list_head *terms)
+{
+	if (!terms)
+		return;
+	parse_events_terms__purge(terms);
+	free(terms);
+}
+
+void parse_events__clear_array(struct parse_events_array *a)
+{
+	free(a->ranges);
 }
 
 void parse_events_evlist_error(struct parse_events_evlist *data,
@@ -2085,6 +2288,33 @@ void parse_events_evlist_error(struct parse_events_evlist *data,
 	WARN_ONCE(!err->str, "WARNING: failed to allocate error string");
 }
 
+static void config_terms_list(char *buf, size_t buf_sz)
+{
+	int i;
+	bool first = true;
+
+	buf[0] = '\0';
+	for (i = 0; i < __PARSE_EVENTS__TERM_TYPE_NR; i++) {
+		const char *name = config_term_names[i];
+
+		if (!config_term_avail(i, NULL))
+			continue;
+		if (!name)
+			continue;
+		if (name[0] == '<')
+			continue;
+
+		if (strlen(buf) + strlen(name) + 2 >= buf_sz)
+			return;
+
+		if (!first)
+			strcat(buf, ",");
+		else
+			first = false;
+		strcat(buf, name);
+	}
+}
+
 /*
  * Return string contains valid config terms of an event.
  * @additional_terms: For terms such as PMU sysfs terms.
@@ -2092,17 +2322,18 @@ void parse_events_evlist_error(struct parse_events_evlist *data,
 char *parse_events_formats_error_string(char *additional_terms)
 {
 	char *str;
-	static const char *static_terms = "config,config1,config2,name,"
-					  "period,freq,branch_type,time,"
-					  "call-graph,stack-size\n";
+	/* "branch_type" is the longest name */
+	char static_terms[__PARSE_EVENTS__TERM_TYPE_NR *
+			  (sizeof("branch_type") - 1)];
 
+	config_terms_list(static_terms, sizeof(static_terms));
 	/* valid terms */
 	if (additional_terms) {
-		if (!asprintf(&str, "valid terms: %s,%s",
-			      additional_terms, static_terms))
+		if (asprintf(&str, "valid terms: %s,%s",
+			     additional_terms, static_terms) < 0)
 			goto fail;
 	} else {
-		if (!asprintf(&str, "valid terms: %s", static_terms))
+		if (asprintf(&str, "valid terms: %s", static_terms) < 0)
 			goto fail;
 	}
 	return str;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index f1a6db107241..67e493088e81 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -68,11 +68,21 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_CALLGRAPH,
 	PARSE_EVENTS__TERM_TYPE_STACKSIZE,
 	PARSE_EVENTS__TERM_TYPE_NOINHERIT,
-	PARSE_EVENTS__TERM_TYPE_INHERIT
+	PARSE_EVENTS__TERM_TYPE_INHERIT,
+	__PARSE_EVENTS__TERM_TYPE_NR,
+};
+
+struct parse_events_array {
+	size_t nr_ranges;
+	struct {
+		unsigned int start;
+		size_t length;
+	} *ranges;
 };
 
 struct parse_events_term {
 	char *config;
+	struct parse_events_array array;
 	union {
 		char *str;
 		u64  num;
@@ -98,12 +108,14 @@ struct parse_events_evlist {
 	int			   idx;
 	int			   nr_groups;
 	struct parse_events_error *error;
+	struct perf_evlist	  *evlist;
 };
 
 struct parse_events_terms {
 	struct list_head *terms;
 };
 
+void parse_events__shrink_config_terms(void);
 int parse_events__is_hardcoded_term(struct parse_events_term *term);
 int parse_events_term__num(struct parse_events_term **term,
 			   int type_term, char *config, u64 num,
@@ -115,7 +127,9 @@ int parse_events_term__sym_hw(struct parse_events_term **term,
 			      char *config, unsigned idx);
 int parse_events_term__clone(struct parse_events_term **new,
 			     struct parse_events_term *term);
-void parse_events__free_terms(struct list_head *terms);
+void parse_events_terms__delete(struct list_head *terms);
+void parse_events_terms__purge(struct list_head *terms);
+void parse_events__clear_array(struct parse_events_array *a);
 int parse_events__modifier_event(struct list_head *list, char *str, bool add);
 int parse_events__modifier_group(struct list_head *list, char *event_mod);
 int parse_events_name(struct list_head *list, char *name);
@@ -126,18 +140,22 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
 int parse_events_load_bpf(struct parse_events_evlist *data,
 			  struct list_head *list,
 			  char *bpf_file_name,
-			  bool source);
+			  bool source,
+			  struct list_head *head_config);
 /* Provide this function for perf test */
 struct bpf_object;
 int parse_events_load_bpf_obj(struct parse_events_evlist *data,
 			      struct list_head *list,
-			      struct bpf_object *obj);
+			      struct bpf_object *obj,
+			      struct list_head *head_config);
 int parse_events_add_numeric(struct parse_events_evlist *data,
 			     struct list_head *list,
 			     u32 type, u64 config,
 			     struct list_head *head_config);
 int parse_events_add_cache(struct list_head *list, int *idx,
-			   char *type, char *op_result1, char *op_result2);
+			   char *type, char *op_result1, char *op_result2,
+			   struct parse_events_error *error,
+			   struct list_head *head_config);
 int parse_events_add_breakpoint(struct list_head *list, int *idx,
 				void *ptr, char *type, u64 len);
 int parse_events_add_pmu(struct parse_events_evlist *data,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 58c5831ffd5c..1477fbc78993 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -9,8 +9,8 @@
 %{
 #include <errno.h>
 #include "../perf.h"
-#include "parse-events-bison.h"
 #include "parse-events.h"
+#include "parse-events-bison.h"
 
 char *parse_events_get_text(yyscan_t yyscanner);
 YYSTYPE *parse_events_get_lval(yyscan_t yyscanner);
@@ -111,6 +111,7 @@ do {							\
 %x mem
 %s config
 %x event
+%x array
 
 group		[^,{}/]*[{][^}]*[}][^,{}/]*
 event_pmu	[^,{}/]+[/][^/]*[/][^,{}/]*
@@ -122,7 +123,7 @@ num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
 num_raw_hex	[a-fA-F0-9]+
 name		[a-zA-Z_*?][a-zA-Z0-9_*?.]*
-name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.]*
+name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
 /* If you add a modifier you need to update check_modifier() */
 modifier_event	[ukhpPGHSDI]+
 modifier_bp	[rwx]{1,3}
@@ -176,10 +177,17 @@ modifier_bp	[rwx]{1,3}
 
 }
 
+<array>{
+"]"			{ BEGIN(config); return ']'; }
+{num_dec}		{ return value(yyscanner, 10); }
+{num_hex}		{ return value(yyscanner, 16); }
+,			{ return ','; }
+"\.\.\."		{ return PE_ARRAY_RANGE; }
+}
+
 <config>{
 	/*
-	 * Please update parse_events_formats_error_string any time
-	 * new static term is added.
+	 * Please update config_term_names when new static term is added.
 	 */
 config			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
 config1			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }
@@ -196,6 +204,8 @@ no-inherit		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
 ,			{ return ','; }
 "/"			{ BEGIN(INITIAL); return '/'; }
 {name_minus}		{ return str(yyscanner, PE_NAME); }
+\[all\]			{ return PE_ARRAY_ALL; }
+"["			{ BEGIN(array); return '['; }
 }
 
 <mem>{
@@ -238,6 +248,7 @@ cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU
 alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
 emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
+bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
 
 	/*
 	 * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately.
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index ad379968d4c1..5be4a5f216d6 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -28,7 +28,7 @@ do { \
 	INIT_LIST_HEAD(list);         \
 } while (0)
 
-static inc_group_count(struct list_head *list,
+static void inc_group_count(struct list_head *list,
 		       struct parse_events_evlist *data)
 {
 	/* Count groups only have more than 1 members */
@@ -48,6 +48,7 @@ static inc_group_count(struct list_head *list,
 %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
 %token PE_ERROR
 %token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
+%token PE_ARRAY_ALL PE_ARRAY_RANGE
 %type <num> PE_VALUE
 %type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
@@ -64,6 +65,7 @@ static inc_group_count(struct list_head *list,
 %type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
 %type <num> value_sym
 %type <head> event_config
+%type <head> opt_event_config
 %type <term> event_term
 %type <head> event_pmu
 %type <head> event_legacy_symbol
@@ -82,6 +84,9 @@ static inc_group_count(struct list_head *list,
 %type <head> group_def
 %type <head> group
 %type <head> groups
+%type <array> array
+%type <array> array_term
+%type <array> array_terms
 
 %union
 {
@@ -93,6 +98,7 @@ static inc_group_count(struct list_head *list,
 		char *sys;
 		char *event;
 	} tracepoint_name;
+	struct parse_events_array array;
 }
 %%
 
@@ -211,24 +217,14 @@ event_def: event_pmu |
 	   event_bpf_file
 
 event_pmu:
-PE_NAME '/' event_config '/'
+PE_NAME opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(data, list, $1, $3));
-	parse_events__free_terms($3);
-	$$ = list;
-}
-|
-PE_NAME '/' '/'
-{
-	struct parse_events_evlist *data = _data;
-	struct list_head *list;
-
-	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(data, list, $1, NULL));
+	ABORT_ON(parse_events_add_pmu(data, list, $1, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 |
@@ -246,7 +242,7 @@ PE_KERNEL_PMU_EVENT sep_dc
 
 	ALLOC_LIST(list);
 	ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
-	parse_events__free_terms(head);
+	parse_events_terms__delete(head);
 	$$ = list;
 }
 |
@@ -266,7 +262,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
 
 	ALLOC_LIST(list);
 	ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
-	parse_events__free_terms(head);
+	parse_events_terms__delete(head);
 	$$ = list;
 }
 
@@ -285,7 +281,7 @@ value_sym '/' event_config '/'
 
 	ALLOC_LIST(list);
 	ABORT_ON(parse_events_add_numeric(data, list, type, config, $3));
-	parse_events__free_terms($3);
+	parse_events_terms__delete($3);
 	$$ = list;
 }
 |
@@ -302,33 +298,39 @@ value_sym sep_slash_dc
 }
 
 event_legacy_cache:
-PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT
+PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_event_config
 {
 	struct parse_events_evlist *data = _data;
+	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5));
+	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5, error, $6));
+	parse_events_terms__delete($6);
 	$$ = list;
 }
 |
-PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT
+PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT opt_event_config
 {
 	struct parse_events_evlist *data = _data;
+	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL));
+	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL, error, $4));
+	parse_events_terms__delete($4);
 	$$ = list;
 }
 |
-PE_NAME_CACHE_TYPE
+PE_NAME_CACHE_TYPE opt_event_config
 {
 	struct parse_events_evlist *data = _data;
+	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL));
+	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL, error, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 
@@ -378,24 +380,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc
 }
 
 event_legacy_tracepoint:
-tracepoint_name
-{
-	struct parse_events_evlist *data = _data;
-	struct parse_events_error *error = data->error;
-	struct list_head *list;
-
-	ALLOC_LIST(list);
-	if (error)
-		error->idx = @1.first_column;
-
-	if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event,
-					error, NULL))
-		return -1;
-
-	$$ = list;
-}
-|
-tracepoint_name '/' event_config '/'
+tracepoint_name opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct parse_events_error *error = data->error;
@@ -406,7 +391,7 @@ tracepoint_name '/' event_config '/'
 		error->idx = @1.first_column;
 
 	if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event,
-					error, $3))
+					error, $2))
 		return -1;
 
 	$$ = list;
@@ -433,49 +418,68 @@ PE_NAME ':' PE_NAME
 }
 
 event_legacy_numeric:
-PE_VALUE ':' PE_VALUE
+PE_VALUE ':' PE_VALUE opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, NULL));
+	ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, $4));
+	parse_events_terms__delete($4);
 	$$ = list;
 }
 
 event_legacy_raw:
-PE_RAW
+PE_RAW opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, NULL));
+	ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 
 event_bpf_file:
-PE_BPF_OBJECT
+PE_BPF_OBJECT opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct parse_events_error *error = data->error;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_load_bpf(data, list, $1, false));
+	ABORT_ON(parse_events_load_bpf(data, list, $1, false, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 |
-PE_BPF_SOURCE
+PE_BPF_SOURCE opt_event_config
 {
 	struct parse_events_evlist *data = _data;
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_load_bpf(data, list, $1, true));
+	ABORT_ON(parse_events_load_bpf(data, list, $1, true, $2));
+	parse_events_terms__delete($2);
 	$$ = list;
 }
 
+opt_event_config:
+'/' event_config '/'
+{
+	$$ = $2;
+}
+|
+'/' '/'
+{
+	$$ = NULL;
+}
+|
+{
+	$$ = NULL;
+}
+
 start_terms: event_config
 {
 	struct parse_events_terms *data = _data;
@@ -573,6 +577,86 @@ PE_TERM
 	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, &@1, NULL));
 	$$ = term;
 }
+|
+PE_NAME array '=' PE_NAME
+{
+	struct parse_events_term *term;
+	int i;
+
+	ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					$1, $4, &@1, &@4));
+
+	term->array = $2;
+	$$ = term;
+}
+|
+PE_NAME array '=' PE_VALUE
+{
+	struct parse_events_term *term;
+
+	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					$1, $4, &@1, &@4));
+	term->array = $2;
+	$$ = term;
+}
+
+array:
+'[' array_terms ']'
+{
+	$$ = $2;
+}
+|
+PE_ARRAY_ALL
+{
+	$$.nr_ranges = 0;
+	$$.ranges = NULL;
+}
+
+array_terms:
+array_terms ',' array_term
+{
+	struct parse_events_array new_array;
+
+	new_array.nr_ranges = $1.nr_ranges + $3.nr_ranges;
+	new_array.ranges = malloc(sizeof(new_array.ranges[0]) *
+				  new_array.nr_ranges);
+	ABORT_ON(!new_array.ranges);
+	memcpy(&new_array.ranges[0], $1.ranges,
+	       $1.nr_ranges * sizeof(new_array.ranges[0]));
+	memcpy(&new_array.ranges[$1.nr_ranges], $3.ranges,
+	       $3.nr_ranges * sizeof(new_array.ranges[0]));
+	free($1.ranges);
+	free($3.ranges);
+	$$ = new_array;
+}
+|
+array_term
+
+array_term:
+PE_VALUE
+{
+	struct parse_events_array array;
+
+	array.nr_ranges = 1;
+	array.ranges = malloc(sizeof(array.ranges[0]));
+	ABORT_ON(!array.ranges);
+	array.ranges[0].start = $1;
+	array.ranges[0].length = 1;
+	$$ = array;
+}
+|
+PE_VALUE PE_ARRAY_RANGE PE_VALUE
+{
+	struct parse_events_array array;
+
+	ABORT_ON($3 < $1);
+	array.nr_ranges = 1;
+	array.ranges = malloc(sizeof(array.ranges[0]));
+	ABORT_ON(!array.ranges);
+	array.ranges[0].start = $1;
+	array.ranges[0].length = $3 - $1 + 1;
+	$$ = array;
+}
 
 sep_dc: ':' |
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index b597bcc8fc78..adef23b1352e 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -98,7 +98,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	char scale[128];
 	int fd, ret = -1;
 	char path[PATH_MAX];
-	const char *lc;
+	char *lc;
 
 	snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
 
@@ -124,6 +124,17 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	lc = setlocale(LC_NUMERIC, NULL);
 
 	/*
+	 * The lc string may be allocated in static storage,
+	 * so get a dynamic copy to make it survive setlocale
+	 * call below.
+	 */
+	lc = strdup(lc);
+	if (!lc) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	/*
 	 * force to C locale to ensure kernel
 	 * scale string is converted correctly.
 	 * kernel uses default C locale.
@@ -135,6 +146,8 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	/* restore locale */
 	setlocale(LC_NUMERIC, lc);
 
+	free(lc);
+
 	ret = 0;
 error:
 	close(fd);
@@ -153,7 +166,7 @@ static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *n
 	if (fd == -1)
 		return -1;
 
-		sret = read(fd, alias->unit, UNIT_MAX_LEN);
+	sret = read(fd, alias->unit, UNIT_MAX_LEN);
 	if (sret < 0)
 		goto error;
 
@@ -284,13 +297,12 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 {
 	struct dirent *evt_ent;
 	DIR *event_dir;
-	int ret = 0;
 
 	event_dir = opendir(dir);
 	if (!event_dir)
 		return -EINVAL;
 
-	while (!ret && (evt_ent = readdir(event_dir))) {
+	while ((evt_ent = readdir(event_dir))) {
 		char path[PATH_MAX];
 		char *name = evt_ent->d_name;
 		FILE *file;
@@ -306,17 +318,19 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 
 		snprintf(path, PATH_MAX, "%s/%s", dir, name);
 
-		ret = -EINVAL;
 		file = fopen(path, "r");
-		if (!file)
-			break;
+		if (!file) {
+			pr_debug("Cannot open %s\n", path);
+			continue;
+		}
 
-		ret = perf_pmu__new_alias(head, dir, name, file);
+		if (perf_pmu__new_alias(head, dir, name, file) < 0)
+			pr_debug("Cannot set up %s\n", name);
 		fclose(file);
 	}
 
 	closedir(event_dir);
-	return ret;
+	return 0;
 }
 
 /*
@@ -354,7 +368,7 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias,
 	list_for_each_entry(term, &alias->terms, list) {
 		ret = parse_events_term__clone(&cloned, term);
 		if (ret) {
-			parse_events__free_terms(&list);
+			parse_events_terms__purge(&list);
 			return ret;
 		}
 		list_add_tail(&cloned->list, &list);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 2be10fb27172..4ce5c5e18f48 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -686,8 +686,9 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 		pf->fb_ops = NULL;
 #if _ELFUTILS_PREREQ(0, 142)
 	} else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa &&
-		   pf->cfi != NULL) {
-		if (dwarf_cfi_addrframe(pf->cfi, pf->addr, &frame) != 0 ||
+		   (pf->cfi_eh != NULL || pf->cfi_dbg != NULL)) {
+		if ((dwarf_cfi_addrframe(pf->cfi_eh, pf->addr, &frame) != 0 &&
+		     (dwarf_cfi_addrframe(pf->cfi_dbg, pf->addr, &frame) != 0)) ||
 		    dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) {
 			pr_warning("Failed to get call frame on 0x%jx\n",
 				   (uintmax_t)pf->addr);
@@ -1015,8 +1016,7 @@ static int pubname_search_cb(Dwarf *dbg, Dwarf_Global *gl, void *data)
 	return DWARF_CB_OK;
 }
 
-/* Find probe points from debuginfo */
-static int debuginfo__find_probes(struct debuginfo *dbg,
+static int debuginfo__find_probe_location(struct debuginfo *dbg,
 				  struct probe_finder *pf)
 {
 	struct perf_probe_point *pp = &pf->pev->point;
@@ -1025,27 +1025,6 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 	Dwarf_Die *diep;
 	int ret = 0;
 
-#if _ELFUTILS_PREREQ(0, 142)
-	Elf *elf;
-	GElf_Ehdr ehdr;
-	GElf_Shdr shdr;
-
-	/* Get the call frame information from this dwarf */
-	elf = dwarf_getelf(dbg->dbg);
-	if (elf == NULL)
-		return -EINVAL;
-
-	if (gelf_getehdr(elf, &ehdr) == NULL)
-		return -EINVAL;
-
-	if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
-	    shdr.sh_type == SHT_PROGBITS) {
-		pf->cfi = dwarf_getcfi_elf(elf);
-	} else {
-		pf->cfi = dwarf_getcfi(dbg->dbg);
-	}
-#endif
-
 	off = 0;
 	pf->lcache = intlist__new(NULL);
 	if (!pf->lcache)
@@ -1108,6 +1087,39 @@ found:
 	return ret;
 }
 
+/* Find probe points from debuginfo */
+static int debuginfo__find_probes(struct debuginfo *dbg,
+				  struct probe_finder *pf)
+{
+	int ret = 0;
+
+#if _ELFUTILS_PREREQ(0, 142)
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr;
+
+	if (pf->cfi_eh || pf->cfi_dbg)
+		return debuginfo__find_probe_location(dbg, pf);
+
+	/* Get the call frame information from this dwarf */
+	elf = dwarf_getelf(dbg->dbg);
+	if (elf == NULL)
+		return -EINVAL;
+
+	if (gelf_getehdr(elf, &ehdr) == NULL)
+		return -EINVAL;
+
+	if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
+	    shdr.sh_type == SHT_PROGBITS)
+		pf->cfi_eh = dwarf_getcfi_elf(elf);
+
+	pf->cfi_dbg = dwarf_getcfi(dbg->dbg);
+#endif
+
+	ret = debuginfo__find_probe_location(dbg, pf);
+	return ret;
+}
+
 struct local_vars_finder {
 	struct probe_finder *pf;
 	struct perf_probe_arg *args;
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index bed82716e1b4..0aec7704e395 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -76,7 +76,10 @@ struct probe_finder {
 
 	/* For variable searching */
 #if _ELFUTILS_PREREQ(0, 142)
-	Dwarf_CFI		*cfi;		/* Call Frame Information */
+	/* Call Frame Information from .eh_frame */
+	Dwarf_CFI		*cfi_eh;
+	/* Call Frame Information from .debug_frame */
+	Dwarf_CFI		*cfi_dbg;
 #endif
 	Dwarf_Op		*fb_ops;	/* Frame base attribute */
 	struct perf_probe_arg	*pvar;		/* Current target variable */
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 544509c159ce..b3aabc0d4eb0 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -187,6 +187,9 @@ static void define_event_symbols(struct event_format *event,
 				 const char *ev_name,
 				 struct print_arg *args)
 {
+	if (args == NULL)
+		return;
+
 	switch (args->type) {
 	case PRINT_NULL:
 		break;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index d72fafc1c800..fbd05242b4e5 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -205,6 +205,9 @@ static void define_event_symbols(struct event_format *event,
 				 const char *ev_name,
 				 struct print_arg *args)
 {
+	if (args == NULL)
+		return;
+
 	switch (args->type) {
 	case PRINT_NULL:
 		break;
@@ -1091,8 +1094,6 @@ static int python_start_script(const char *script, int argc, const char **argv)
 		goto error;
 	}
 
-	free(command_line);
-
 	set_table_handlers(tables);
 
 	if (tables->db_export_mode) {
@@ -1101,6 +1102,8 @@ static int python_start_script(const char *script, int argc, const char **argv)
 			goto error;
 	}
 
+	free(command_line);
+
 	return err;
 error:
 	Py_Finalize();
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 40b7a0d0905b..60b3593d210d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -240,14 +240,6 @@ static int process_event_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int process_build_id_stub(struct perf_tool *tool __maybe_unused,
-				 union perf_event *event __maybe_unused,
-				 struct perf_session *session __maybe_unused)
-{
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
 static int process_finished_round_stub(struct perf_tool *tool __maybe_unused,
 				       union perf_event *event __maybe_unused,
 				       struct ordered_events *oe __maybe_unused)
@@ -260,23 +252,6 @@ static int process_finished_round(struct perf_tool *tool,
 				  union perf_event *event,
 				  struct ordered_events *oe);
 
-static int process_id_index_stub(struct perf_tool *tool __maybe_unused,
-				 union perf_event *event __maybe_unused,
-				 struct perf_session *perf_session
-				 __maybe_unused)
-{
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
-static int process_event_auxtrace_info_stub(struct perf_tool *tool __maybe_unused,
-				union perf_event *event __maybe_unused,
-				struct perf_session *session __maybe_unused)
-{
-	dump_printf(": unhandled!\n");
-	return 0;
-}
-
 static int skipn(int fd, off_t n)
 {
 	char buf[4096];
@@ -303,10 +278,9 @@ static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
 	return event->auxtrace.size;
 }
 
-static
-int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused,
-				      union perf_event *event __maybe_unused,
-				      struct perf_session *session __maybe_unused)
+static int process_event_op2_stub(struct perf_tool *tool __maybe_unused,
+				  union perf_event *event __maybe_unused,
+				  struct perf_session *session __maybe_unused)
 {
 	dump_printf(": unhandled!\n");
 	return 0;
@@ -410,7 +384,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 	if (tool->tracing_data == NULL)
 		tool->tracing_data = process_event_synth_tracing_data_stub;
 	if (tool->build_id == NULL)
-		tool->build_id = process_build_id_stub;
+		tool->build_id = process_event_op2_stub;
 	if (tool->finished_round == NULL) {
 		if (tool->ordered_events)
 			tool->finished_round = process_finished_round;
@@ -418,13 +392,13 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 			tool->finished_round = process_finished_round_stub;
 	}
 	if (tool->id_index == NULL)
-		tool->id_index = process_id_index_stub;
+		tool->id_index = process_event_op2_stub;
 	if (tool->auxtrace_info == NULL)
-		tool->auxtrace_info = process_event_auxtrace_info_stub;
+		tool->auxtrace_info = process_event_op2_stub;
 	if (tool->auxtrace == NULL)
 		tool->auxtrace = process_event_auxtrace_stub;
 	if (tool->auxtrace_error == NULL)
-		tool->auxtrace_error = process_event_auxtrace_error_stub;
+		tool->auxtrace_error = process_event_op2_stub;
 	if (tool->thread_map == NULL)
 		tool->thread_map = process_event_thread_map_stub;
 	if (tool->cpu_map == NULL)
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 1833103768cb..c8680984d2d6 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -22,6 +22,7 @@ cflags = getenv('CFLAGS', '').split()
 # switch off several checks (need to be at the end of cflags list)
 cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ]
 
+src_perf  = getenv('srctree') + '/tools/perf'
 build_lib = getenv('PYTHON_EXTBUILD_LIB')
 build_tmp = getenv('PYTHON_EXTBUILD_TMP')
 libtraceevent = getenv('LIBTRACEEVENT')
@@ -30,6 +31,9 @@ libapikfs = getenv('LIBAPI')
 ext_sources = [f.strip() for f in file('util/python-ext-sources')
 				if len(f.strip()) > 0 and f[0] != '#']
 
+# use full paths with source files
+ext_sources = map(lambda x: '%s/%s' % (src_perf, x) , ext_sources)
+
 perf = Extension('perf',
 		  sources = ext_sources,
 		  include_dirs = ['util/include'],
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index ec722346e6ff..93fa136b0025 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -6,6 +6,7 @@
 #include "evsel.h"
 #include "evlist.h"
 #include <traceevent/event-parse.h>
+#include "mem-events.h"
 
 regex_t		parent_regex;
 const char	default_parent_pattern[] = "^sys_|^do_page_fault";
@@ -25,9 +26,19 @@ int		sort__has_parent = 0;
 int		sort__has_sym = 0;
 int		sort__has_dso = 0;
 int		sort__has_socket = 0;
+int		sort__has_thread = 0;
+int		sort__has_comm = 0;
 enum sort_mode	sort__mode = SORT_MODE__NORMAL;
 
-
+/*
+ * Replaces all occurrences of a char used with the:
+ *
+ * -t, --field-separator
+ *
+ * option, that uses a special separator character and don't pad with spaces,
+ * replacing all occurances of this separator in symbol names (and other
+ * output) with a '.' character, that thus it's the only non valid separator.
+*/
 static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...)
 {
 	int n;
@@ -80,10 +91,21 @@ static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf,
 			       width, width, comm ?: "");
 }
 
+static int hist_entry__thread_filter(struct hist_entry *he, int type, const void *arg)
+{
+	const struct thread *th = arg;
+
+	if (type != HIST_FILTER__THREAD)
+		return -1;
+
+	return th && he->thread != th;
+}
+
 struct sort_entry sort_thread = {
 	.se_header	= "  Pid:Command",
 	.se_cmp		= sort__thread_cmp,
 	.se_snprintf	= hist_entry__thread_snprintf,
+	.se_filter	= hist_entry__thread_filter,
 	.se_width_idx	= HISTC_THREAD,
 };
 
@@ -121,6 +143,7 @@ struct sort_entry sort_comm = {
 	.se_collapse	= sort__comm_collapse,
 	.se_sort	= sort__comm_sort,
 	.se_snprintf	= hist_entry__comm_snprintf,
+	.se_filter	= hist_entry__thread_filter,
 	.se_width_idx	= HISTC_COMM,
 };
 
@@ -170,10 +193,21 @@ static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf,
 	return _hist_entry__dso_snprintf(he->ms.map, bf, size, width);
 }
 
+static int hist_entry__dso_filter(struct hist_entry *he, int type, const void *arg)
+{
+	const struct dso *dso = arg;
+
+	if (type != HIST_FILTER__DSO)
+		return -1;
+
+	return dso && (!he->ms.map || he->ms.map->dso != dso);
+}
+
 struct sort_entry sort_dso = {
 	.se_header	= "Shared Object",
 	.se_cmp		= sort__dso_cmp,
 	.se_snprintf	= hist_entry__dso_snprintf,
+	.se_filter	= hist_entry__dso_filter,
 	.se_width_idx	= HISTC_DSO,
 };
 
@@ -246,10 +280,8 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 			ret += repsep_snprintf(bf + ret, size - ret, "%s", sym->name);
 			ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx",
 					ip - map->unmap_ip(map, sym->start));
-			ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
-				       width - ret, "");
 		} else {
-			ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
+			ret += repsep_snprintf(bf + ret, size - ret, "%.*s",
 					       width - ret,
 					       sym->name);
 		}
@@ -257,14 +289,9 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 		size_t len = BITS_PER_LONG / 4;
 		ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx",
 				       len, ip);
-		ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
-				       width - ret, "");
 	}
 
-	if (ret > width)
-		bf[width] = '\0';
-
-	return width;
+	return ret;
 }
 
 static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
@@ -274,46 +301,56 @@ static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
 					 he->level, bf, size, width);
 }
 
+static int hist_entry__sym_filter(struct hist_entry *he, int type, const void *arg)
+{
+	const char *sym = arg;
+
+	if (type != HIST_FILTER__SYMBOL)
+		return -1;
+
+	return sym && (!he->ms.sym || !strstr(he->ms.sym->name, sym));
+}
+
 struct sort_entry sort_sym = {
 	.se_header	= "Symbol",
 	.se_cmp		= sort__sym_cmp,
 	.se_sort	= sort__sym_sort,
 	.se_snprintf	= hist_entry__sym_snprintf,
+	.se_filter	= hist_entry__sym_filter,
 	.se_width_idx	= HISTC_SYMBOL,
 };
 
 /* --sort srcline */
 
+static char *hist_entry__get_srcline(struct hist_entry *he)
+{
+	struct map *map = he->ms.map;
+
+	if (!map)
+		return SRCLINE_UNKNOWN;
+
+	return get_srcline(map->dso, map__rip_2objdump(map, he->ip),
+			   he->ms.sym, true);
+}
+
 static int64_t
 sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	if (!left->srcline) {
-		if (!left->ms.map)
-			left->srcline = SRCLINE_UNKNOWN;
-		else {
-			struct map *map = left->ms.map;
-			left->srcline = get_srcline(map->dso,
-					   map__rip_2objdump(map, left->ip),
-						    left->ms.sym, true);
-		}
-	}
-	if (!right->srcline) {
-		if (!right->ms.map)
-			right->srcline = SRCLINE_UNKNOWN;
-		else {
-			struct map *map = right->ms.map;
-			right->srcline = get_srcline(map->dso,
-					     map__rip_2objdump(map, right->ip),
-						     right->ms.sym, true);
-		}
-	}
+	if (!left->srcline)
+		left->srcline = hist_entry__get_srcline(left);
+	if (!right->srcline)
+		right->srcline = hist_entry__get_srcline(right);
+
 	return strcmp(right->srcline, left->srcline);
 }
 
 static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf,
 					size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcline);
+	if (!he->srcline)
+		he->srcline = hist_entry__get_srcline(he);
+
+	return repsep_snprintf(bf, size, "%-.*s", width, he->srcline);
 }
 
 struct sort_entry sort_srcline = {
@@ -327,11 +364,14 @@ struct sort_entry sort_srcline = {
 
 static char no_srcfile[1];
 
-static char *get_srcfile(struct hist_entry *e)
+static char *hist_entry__get_srcfile(struct hist_entry *e)
 {
 	char *sf, *p;
 	struct map *map = e->ms.map;
 
+	if (!map)
+		return no_srcfile;
+
 	sf = __get_srcline(map->dso, map__rip_2objdump(map, e->ip),
 			 e->ms.sym, false, true);
 	if (!strcmp(sf, SRCLINE_UNKNOWN))
@@ -348,25 +388,21 @@ static char *get_srcfile(struct hist_entry *e)
 static int64_t
 sort__srcfile_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	if (!left->srcfile) {
-		if (!left->ms.map)
-			left->srcfile = no_srcfile;
-		else
-			left->srcfile = get_srcfile(left);
-	}
-	if (!right->srcfile) {
-		if (!right->ms.map)
-			right->srcfile = no_srcfile;
-		else
-			right->srcfile = get_srcfile(right);
-	}
+	if (!left->srcfile)
+		left->srcfile = hist_entry__get_srcfile(left);
+	if (!right->srcfile)
+		right->srcfile = hist_entry__get_srcfile(right);
+
 	return strcmp(right->srcfile, left->srcfile);
 }
 
 static int hist_entry__srcfile_snprintf(struct hist_entry *he, char *bf,
 					size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcfile);
+	if (!he->srcfile)
+		he->srcfile = hist_entry__get_srcfile(he);
+
+	return repsep_snprintf(bf, size, "%-.*s", width, he->srcfile);
 }
 
 struct sort_entry sort_srcfile = {
@@ -439,10 +475,21 @@ static int hist_entry__socket_snprintf(struct hist_entry *he, char *bf,
 	return repsep_snprintf(bf, size, "%*.*d", width, width-3, he->socket);
 }
 
+static int hist_entry__socket_filter(struct hist_entry *he, int type, const void *arg)
+{
+	int sk = *(const int *)arg;
+
+	if (type != HIST_FILTER__SOCKET)
+		return -1;
+
+	return sk >= 0 && he->socket != sk;
+}
+
 struct sort_entry sort_socket = {
 	.se_header      = "Socket",
 	.se_cmp	        = sort__socket_cmp,
 	.se_snprintf    = hist_entry__socket_snprintf,
+	.se_filter      = hist_entry__socket_filter,
 	.se_width_idx	= HISTC_SOCKET,
 };
 
@@ -483,9 +530,6 @@ sort__trace_cmp(struct hist_entry *left, struct hist_entry *right)
 	if (right->trace_output == NULL)
 		right->trace_output = get_trace_output(right);
 
-	hists__new_col_len(left->hists, HISTC_TRACE, strlen(left->trace_output));
-	hists__new_col_len(right->hists, HISTC_TRACE, strlen(right->trace_output));
-
 	return strcmp(right->trace_output, left->trace_output);
 }
 
@@ -496,11 +540,11 @@ static int hist_entry__trace_snprintf(struct hist_entry *he, char *bf,
 
 	evsel = hists_to_evsel(he->hists);
 	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
-		return scnprintf(bf, size, "%-*.*s", width, width, "N/A");
+		return scnprintf(bf, size, "%-.*s", width, "N/A");
 
 	if (he->trace_output == NULL)
 		he->trace_output = get_trace_output(he);
-	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->trace_output);
+	return repsep_snprintf(bf, size, "%-.*s", width, he->trace_output);
 }
 
 struct sort_entry sort_trace = {
@@ -532,6 +576,18 @@ static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf,
 		return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
+static int hist_entry__dso_from_filter(struct hist_entry *he, int type,
+				       const void *arg)
+{
+	const struct dso *dso = arg;
+
+	if (type != HIST_FILTER__DSO)
+		return -1;
+
+	return dso && (!he->branch_info || !he->branch_info->from.map ||
+		       he->branch_info->from.map->dso != dso);
+}
+
 static int64_t
 sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -552,6 +608,18 @@ static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf,
 		return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
+static int hist_entry__dso_to_filter(struct hist_entry *he, int type,
+				     const void *arg)
+{
+	const struct dso *dso = arg;
+
+	if (type != HIST_FILTER__DSO)
+		return -1;
+
+	return dso && (!he->branch_info || !he->branch_info->to.map ||
+		       he->branch_info->to.map->dso != dso);
+}
+
 static int64_t
 sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -613,10 +681,35 @@ static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf,
 	return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
+static int hist_entry__sym_from_filter(struct hist_entry *he, int type,
+				       const void *arg)
+{
+	const char *sym = arg;
+
+	if (type != HIST_FILTER__SYMBOL)
+		return -1;
+
+	return sym && !(he->branch_info && he->branch_info->from.sym &&
+			strstr(he->branch_info->from.sym->name, sym));
+}
+
+static int hist_entry__sym_to_filter(struct hist_entry *he, int type,
+				       const void *arg)
+{
+	const char *sym = arg;
+
+	if (type != HIST_FILTER__SYMBOL)
+		return -1;
+
+	return sym && !(he->branch_info && he->branch_info->to.sym &&
+		        strstr(he->branch_info->to.sym->name, sym));
+}
+
 struct sort_entry sort_dso_from = {
 	.se_header	= "Source Shared Object",
 	.se_cmp		= sort__dso_from_cmp,
 	.se_snprintf	= hist_entry__dso_from_snprintf,
+	.se_filter	= hist_entry__dso_from_filter,
 	.se_width_idx	= HISTC_DSO_FROM,
 };
 
@@ -624,6 +717,7 @@ struct sort_entry sort_dso_to = {
 	.se_header	= "Target Shared Object",
 	.se_cmp		= sort__dso_to_cmp,
 	.se_snprintf	= hist_entry__dso_to_snprintf,
+	.se_filter	= hist_entry__dso_to_filter,
 	.se_width_idx	= HISTC_DSO_TO,
 };
 
@@ -631,6 +725,7 @@ struct sort_entry sort_sym_from = {
 	.se_header	= "Source Symbol",
 	.se_cmp		= sort__sym_from_cmp,
 	.se_snprintf	= hist_entry__sym_from_snprintf,
+	.se_filter	= hist_entry__sym_from_filter,
 	.se_width_idx	= HISTC_SYMBOL_FROM,
 };
 
@@ -638,6 +733,7 @@ struct sort_entry sort_sym_to = {
 	.se_header	= "Target Symbol",
 	.se_cmp		= sort__sym_to_cmp,
 	.se_snprintf	= hist_entry__sym_to_snprintf,
+	.se_filter	= hist_entry__sym_to_filter,
 	.se_width_idx	= HISTC_SYMBOL_TO,
 };
 
@@ -797,20 +893,10 @@ sort__locked_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__locked_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	const char *out;
-	u64 mask = PERF_MEM_LOCK_NA;
+	char out[10];
 
-	if (he->mem_info)
-		mask = he->mem_info->data_src.mem_lock;
-
-	if (mask & PERF_MEM_LOCK_NA)
-		out = "N/A";
-	else if (mask & PERF_MEM_LOCK_LOCKED)
-		out = "Yes";
-	else
-		out = "No";
-
-	return repsep_snprintf(bf, size, "%-*s", width, out);
+	perf_mem__lck_scnprintf(out, sizeof(out), he->mem_info);
+	return repsep_snprintf(bf, size, "%.*s", width, out);
 }
 
 static int64_t
@@ -832,54 +918,12 @@ sort__tlb_cmp(struct hist_entry *left, struct hist_entry *right)
 	return (int64_t)(data_src_r.mem_dtlb - data_src_l.mem_dtlb);
 }
 
-static const char * const tlb_access[] = {
-	"N/A",
-	"HIT",
-	"MISS",
-	"L1",
-	"L2",
-	"Walker",
-	"Fault",
-};
-#define NUM_TLB_ACCESS (sizeof(tlb_access)/sizeof(const char *))
-
 static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
 	char out[64];
-	size_t sz = sizeof(out) - 1; /* -1 for null termination */
-	size_t l = 0, i;
-	u64 m = PERF_MEM_TLB_NA;
-	u64 hit, miss;
-
-	out[0] = '\0';
-
-	if (he->mem_info)
-		m = he->mem_info->data_src.mem_dtlb;
-
-	hit = m & PERF_MEM_TLB_HIT;
-	miss = m & PERF_MEM_TLB_MISS;
-
-	/* already taken care of */
-	m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
-
-	for (i = 0; m && i < NUM_TLB_ACCESS; i++, m >>= 1) {
-		if (!(m & 0x1))
-			continue;
-		if (l) {
-			strcat(out, " or ");
-			l += 4;
-		}
-		strncat(out, tlb_access[i], sz - l);
-		l += strlen(tlb_access[i]);
-	}
-	if (*out == '\0')
-		strcpy(out, "N/A");
-	if (hit)
-		strncat(out, " hit", sz - l);
-	if (miss)
-		strncat(out, " miss", sz - l);
 
+	perf_mem__tlb_scnprintf(out, sizeof(out), he->mem_info);
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
@@ -902,61 +946,12 @@ sort__lvl_cmp(struct hist_entry *left, struct hist_entry *right)
 	return (int64_t)(data_src_r.mem_lvl - data_src_l.mem_lvl);
 }
 
-static const char * const mem_lvl[] = {
-	"N/A",
-	"HIT",
-	"MISS",
-	"L1",
-	"LFB",
-	"L2",
-	"L3",
-	"Local RAM",
-	"Remote RAM (1 hop)",
-	"Remote RAM (2 hops)",
-	"Remote Cache (1 hop)",
-	"Remote Cache (2 hops)",
-	"I/O",
-	"Uncached",
-};
-#define NUM_MEM_LVL (sizeof(mem_lvl)/sizeof(const char *))
-
 static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
 	char out[64];
-	size_t sz = sizeof(out) - 1; /* -1 for null termination */
-	size_t i, l = 0;
-	u64 m =  PERF_MEM_LVL_NA;
-	u64 hit, miss;
-
-	if (he->mem_info)
-		m  = he->mem_info->data_src.mem_lvl;
-
-	out[0] = '\0';
-
-	hit = m & PERF_MEM_LVL_HIT;
-	miss = m & PERF_MEM_LVL_MISS;
-
-	/* already taken care of */
-	m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
-
-	for (i = 0; m && i < NUM_MEM_LVL; i++, m >>= 1) {
-		if (!(m & 0x1))
-			continue;
-		if (l) {
-			strcat(out, " or ");
-			l += 4;
-		}
-		strncat(out, mem_lvl[i], sz - l);
-		l += strlen(mem_lvl[i]);
-	}
-	if (*out == '\0')
-		strcpy(out, "N/A");
-	if (hit)
-		strncat(out, " hit", sz - l);
-	if (miss)
-		strncat(out, " miss", sz - l);
 
+	perf_mem__lvl_scnprintf(out, sizeof(out), he->mem_info);
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
@@ -979,51 +974,15 @@ sort__snoop_cmp(struct hist_entry *left, struct hist_entry *right)
 	return (int64_t)(data_src_r.mem_snoop - data_src_l.mem_snoop);
 }
 
-static const char * const snoop_access[] = {
-	"N/A",
-	"None",
-	"Miss",
-	"Hit",
-	"HitM",
-};
-#define NUM_SNOOP_ACCESS (sizeof(snoop_access)/sizeof(const char *))
-
 static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
 	char out[64];
-	size_t sz = sizeof(out) - 1; /* -1 for null termination */
-	size_t i, l = 0;
-	u64 m = PERF_MEM_SNOOP_NA;
-
-	out[0] = '\0';
-
-	if (he->mem_info)
-		m = he->mem_info->data_src.mem_snoop;
-
-	for (i = 0; m && i < NUM_SNOOP_ACCESS; i++, m >>= 1) {
-		if (!(m & 0x1))
-			continue;
-		if (l) {
-			strcat(out, " or ");
-			l += 4;
-		}
-		strncat(out, snoop_access[i], sz - l);
-		l += strlen(snoop_access[i]);
-	}
-
-	if (*out == '\0')
-		strcpy(out, "N/A");
 
+	perf_mem__snp_scnprintf(out, sizeof(out), he->mem_info);
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
-static inline  u64 cl_address(u64 address)
-{
-	/* return the cacheline of the address */
-	return (address & ~(cacheline_size - 1));
-}
-
 static int64_t
 sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -1440,20 +1399,6 @@ struct hpp_sort_entry {
 	struct sort_entry *se;
 };
 
-bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
-{
-	struct hpp_sort_entry *hse_a;
-	struct hpp_sort_entry *hse_b;
-
-	if (!perf_hpp__is_sort_entry(a) || !perf_hpp__is_sort_entry(b))
-		return false;
-
-	hse_a = container_of(a, struct hpp_sort_entry, hpp);
-	hse_b = container_of(b, struct hpp_sort_entry, hpp);
-
-	return hse_a->se == hse_b->se;
-}
-
 void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 {
 	struct hpp_sort_entry *hse;
@@ -1539,8 +1484,56 @@ static int64_t __sort__hpp_sort(struct perf_hpp_fmt *fmt,
 	return sort_fn(a, b);
 }
 
+bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format)
+{
+	return format->header == __sort__hpp_header;
+}
+
+#define MK_SORT_ENTRY_CHK(key)					\
+bool perf_hpp__is_ ## key ## _entry(struct perf_hpp_fmt *fmt)	\
+{								\
+	struct hpp_sort_entry *hse;				\
+								\
+	if (!perf_hpp__is_sort_entry(fmt))			\
+		return false;					\
+								\
+	hse = container_of(fmt, struct hpp_sort_entry, hpp);	\
+	return hse->se == &sort_ ## key ;			\
+}
+
+MK_SORT_ENTRY_CHK(trace)
+MK_SORT_ENTRY_CHK(srcline)
+MK_SORT_ENTRY_CHK(srcfile)
+MK_SORT_ENTRY_CHK(thread)
+MK_SORT_ENTRY_CHK(comm)
+MK_SORT_ENTRY_CHK(dso)
+MK_SORT_ENTRY_CHK(sym)
+
+
+static bool __sort__hpp_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+	struct hpp_sort_entry *hse_a;
+	struct hpp_sort_entry *hse_b;
+
+	if (!perf_hpp__is_sort_entry(a) || !perf_hpp__is_sort_entry(b))
+		return false;
+
+	hse_a = container_of(a, struct hpp_sort_entry, hpp);
+	hse_b = container_of(b, struct hpp_sort_entry, hpp);
+
+	return hse_a->se == hse_b->se;
+}
+
+static void hse_free(struct perf_hpp_fmt *fmt)
+{
+	struct hpp_sort_entry *hse;
+
+	hse = container_of(fmt, struct hpp_sort_entry, hpp);
+	free(hse);
+}
+
 static struct hpp_sort_entry *
-__sort_dimension__alloc_hpp(struct sort_dimension *sd)
+__sort_dimension__alloc_hpp(struct sort_dimension *sd, int level)
 {
 	struct hpp_sort_entry *hse;
 
@@ -1560,40 +1553,92 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
 	hse->hpp.cmp = __sort__hpp_cmp;
 	hse->hpp.collapse = __sort__hpp_collapse;
 	hse->hpp.sort = __sort__hpp_sort;
+	hse->hpp.equal = __sort__hpp_equal;
+	hse->hpp.free = hse_free;
 
 	INIT_LIST_HEAD(&hse->hpp.list);
 	INIT_LIST_HEAD(&hse->hpp.sort_list);
 	hse->hpp.elide = false;
 	hse->hpp.len = 0;
 	hse->hpp.user_len = 0;
+	hse->hpp.level = level;
 
 	return hse;
 }
 
-bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format)
+static void hpp_free(struct perf_hpp_fmt *fmt)
 {
-	return format->header == __sort__hpp_header;
+	free(fmt);
+}
+
+static struct perf_hpp_fmt *__hpp_dimension__alloc_hpp(struct hpp_dimension *hd,
+						       int level)
+{
+	struct perf_hpp_fmt *fmt;
+
+	fmt = memdup(hd->fmt, sizeof(*fmt));
+	if (fmt) {
+		INIT_LIST_HEAD(&fmt->list);
+		INIT_LIST_HEAD(&fmt->sort_list);
+		fmt->free = hpp_free;
+		fmt->level = level;
+	}
+
+	return fmt;
+}
+
+int hist_entry__filter(struct hist_entry *he, int type, const void *arg)
+{
+	struct perf_hpp_fmt *fmt;
+	struct hpp_sort_entry *hse;
+	int ret = -1;
+	int r;
+
+	perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+		if (!perf_hpp__is_sort_entry(fmt))
+			continue;
+
+		hse = container_of(fmt, struct hpp_sort_entry, hpp);
+		if (hse->se->se_filter == NULL)
+			continue;
+
+		/*
+		 * hist entry is filtered if any of sort key in the hpp list
+		 * is applied.  But it should skip non-matched filter types.
+		 */
+		r = hse->se->se_filter(he, type, arg);
+		if (r >= 0) {
+			if (ret < 0)
+				ret = 0;
+			ret |= r;
+		}
+	}
+
+	return ret;
 }
 
-static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd)
+static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd,
+					  struct perf_hpp_list *list,
+					  int level)
 {
-	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
+	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, level);
 
 	if (hse == NULL)
 		return -1;
 
-	perf_hpp__register_sort_field(&hse->hpp);
+	perf_hpp_list__register_sort_field(list, &hse->hpp);
 	return 0;
 }
 
-static int __sort_dimension__add_hpp_output(struct sort_dimension *sd)
+static int __sort_dimension__add_hpp_output(struct sort_dimension *sd,
+					    struct perf_hpp_list *list)
 {
-	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
+	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, 0);
 
 	if (hse == NULL)
 		return -1;
 
-	perf_hpp__column_register(&hse->hpp);
+	perf_hpp_list__column_register(list, &hse->hpp);
 	return 0;
 }
 
@@ -1727,6 +1772,9 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	if (hde->raw_trace)
 		goto raw_field;
 
+	if (!he->trace_output)
+		he->trace_output = get_trace_output(he);
+
 	field = hde->field;
 	namelen = strlen(field->name);
 	str = he->trace_output;
@@ -1776,6 +1824,11 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
 
 	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
 
+	if (b == NULL) {
+		update_dynamic_len(hde, a);
+		return 0;
+	}
+
 	field = hde->field;
 	if (field->flags & FIELD_IS_DYNAMIC) {
 		unsigned long long dyn;
@@ -1790,9 +1843,6 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
 	} else {
 		offset = field->offset;
 		size = field->size;
-
-		update_dynamic_len(hde, a);
-		update_dynamic_len(hde, b);
 	}
 
 	return memcmp(a->raw_data + offset, b->raw_data + offset, size);
@@ -1803,8 +1853,31 @@ bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *fmt)
 	return fmt->cmp == __sort__hde_cmp;
 }
 
+static bool __sort__hde_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+	struct hpp_dynamic_entry *hde_a;
+	struct hpp_dynamic_entry *hde_b;
+
+	if (!perf_hpp__is_dynamic_entry(a) || !perf_hpp__is_dynamic_entry(b))
+		return false;
+
+	hde_a = container_of(a, struct hpp_dynamic_entry, hpp);
+	hde_b = container_of(b, struct hpp_dynamic_entry, hpp);
+
+	return hde_a->field == hde_b->field;
+}
+
+static void hde_free(struct perf_hpp_fmt *fmt)
+{
+	struct hpp_dynamic_entry *hde;
+
+	hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+	free(hde);
+}
+
 static struct hpp_dynamic_entry *
-__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field)
+__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field,
+		      int level)
 {
 	struct hpp_dynamic_entry *hde;
 
@@ -1827,16 +1900,47 @@ __alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field)
 	hde->hpp.cmp = __sort__hde_cmp;
 	hde->hpp.collapse = __sort__hde_cmp;
 	hde->hpp.sort = __sort__hde_cmp;
+	hde->hpp.equal = __sort__hde_equal;
+	hde->hpp.free = hde_free;
 
 	INIT_LIST_HEAD(&hde->hpp.list);
 	INIT_LIST_HEAD(&hde->hpp.sort_list);
 	hde->hpp.elide = false;
 	hde->hpp.len = 0;
 	hde->hpp.user_len = 0;
+	hde->hpp.level = level;
 
 	return hde;
 }
 
+struct perf_hpp_fmt *perf_hpp_fmt__dup(struct perf_hpp_fmt *fmt)
+{
+	struct perf_hpp_fmt *new_fmt = NULL;
+
+	if (perf_hpp__is_sort_entry(fmt)) {
+		struct hpp_sort_entry *hse, *new_hse;
+
+		hse = container_of(fmt, struct hpp_sort_entry, hpp);
+		new_hse = memdup(hse, sizeof(*hse));
+		if (new_hse)
+			new_fmt = &new_hse->hpp;
+	} else if (perf_hpp__is_dynamic_entry(fmt)) {
+		struct hpp_dynamic_entry *hde, *new_hde;
+
+		hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+		new_hde = memdup(hde, sizeof(*hde));
+		if (new_hde)
+			new_fmt = &new_hde->hpp;
+	} else {
+		new_fmt = memdup(fmt, sizeof(*fmt));
+	}
+
+	INIT_LIST_HEAD(&new_fmt->list);
+	INIT_LIST_HEAD(&new_fmt->sort_list);
+
+	return new_fmt;
+}
+
 static int parse_field_name(char *str, char **event, char **field, char **opt)
 {
 	char *event_name, *field_name, *opt_name;
@@ -1908,11 +2012,11 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam
 
 static int __dynamic_dimension__add(struct perf_evsel *evsel,
 				    struct format_field *field,
-				    bool raw_trace)
+				    bool raw_trace, int level)
 {
 	struct hpp_dynamic_entry *hde;
 
-	hde = __alloc_dynamic_entry(evsel, field);
+	hde = __alloc_dynamic_entry(evsel, field, level);
 	if (hde == NULL)
 		return -ENOMEM;
 
@@ -1922,14 +2026,14 @@ static int __dynamic_dimension__add(struct perf_evsel *evsel,
 	return 0;
 }
 
-static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace)
+static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace, int level)
 {
 	int ret;
 	struct format_field *field;
 
 	field = evsel->tp_format->format.fields;
 	while (field) {
-		ret = __dynamic_dimension__add(evsel, field, raw_trace);
+		ret = __dynamic_dimension__add(evsel, field, raw_trace, level);
 		if (ret < 0)
 			return ret;
 
@@ -1938,7 +2042,8 @@ static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace)
 	return 0;
 }
 
-static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace)
+static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace,
+				  int level)
 {
 	int ret;
 	struct perf_evsel *evsel;
@@ -1947,7 +2052,7 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace)
 		if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
 			continue;
 
-		ret = add_evsel_fields(evsel, raw_trace);
+		ret = add_evsel_fields(evsel, raw_trace, level);
 		if (ret < 0)
 			return ret;
 	}
@@ -1955,7 +2060,7 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace)
 }
 
 static int add_all_matching_fields(struct perf_evlist *evlist,
-				   char *field_name, bool raw_trace)
+				   char *field_name, bool raw_trace, int level)
 {
 	int ret = -ESRCH;
 	struct perf_evsel *evsel;
@@ -1969,14 +2074,15 @@ static int add_all_matching_fields(struct perf_evlist *evlist,
 		if (field == NULL)
 			continue;
 
-		ret = __dynamic_dimension__add(evsel, field, raw_trace);
+		ret = __dynamic_dimension__add(evsel, field, raw_trace, level);
 		if (ret < 0)
 			break;
 	}
 	return ret;
 }
 
-static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
+static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok,
+			     int level)
 {
 	char *str, *event_name, *field_name, *opt_name;
 	struct perf_evsel *evsel;
@@ -2006,12 +2112,12 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
 	}
 
 	if (!strcmp(field_name, "trace_fields")) {
-		ret = add_all_dynamic_fields(evlist, raw_trace);
+		ret = add_all_dynamic_fields(evlist, raw_trace, level);
 		goto out;
 	}
 
 	if (event_name == NULL) {
-		ret = add_all_matching_fields(evlist, field_name, raw_trace);
+		ret = add_all_matching_fields(evlist, field_name, raw_trace, level);
 		goto out;
 	}
 
@@ -2029,7 +2135,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
 	}
 
 	if (!strcmp(field_name, "*")) {
-		ret = add_evsel_fields(evsel, raw_trace);
+		ret = add_evsel_fields(evsel, raw_trace, level);
 	} else {
 		field = pevent_find_any_field(evsel->tp_format, field_name);
 		if (field == NULL) {
@@ -2038,7 +2144,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
 			return -ENOENT;
 		}
 
-		ret = __dynamic_dimension__add(evsel, field, raw_trace);
+		ret = __dynamic_dimension__add(evsel, field, raw_trace, level);
 	}
 
 out:
@@ -2046,12 +2152,14 @@ out:
 	return ret;
 }
 
-static int __sort_dimension__add(struct sort_dimension *sd)
+static int __sort_dimension__add(struct sort_dimension *sd,
+				 struct perf_hpp_list *list,
+				 int level)
 {
 	if (sd->taken)
 		return 0;
 
-	if (__sort_dimension__add_hpp_sort(sd) < 0)
+	if (__sort_dimension__add_hpp_sort(sd, list, level) < 0)
 		return -1;
 
 	if (sd->entry->se_collapse)
@@ -2062,46 +2170,63 @@ static int __sort_dimension__add(struct sort_dimension *sd)
 	return 0;
 }
 
-static int __hpp_dimension__add(struct hpp_dimension *hd)
+static int __hpp_dimension__add(struct hpp_dimension *hd,
+				struct perf_hpp_list *list,
+				int level)
 {
-	if (!hd->taken) {
-		hd->taken = 1;
+	struct perf_hpp_fmt *fmt;
 
-		perf_hpp__register_sort_field(hd->fmt);
-	}
+	if (hd->taken)
+		return 0;
+
+	fmt = __hpp_dimension__alloc_hpp(hd, level);
+	if (!fmt)
+		return -1;
+
+	hd->taken = 1;
+	perf_hpp_list__register_sort_field(list, fmt);
 	return 0;
 }
 
-static int __sort_dimension__add_output(struct sort_dimension *sd)
+static int __sort_dimension__add_output(struct perf_hpp_list *list,
+					struct sort_dimension *sd)
 {
 	if (sd->taken)
 		return 0;
 
-	if (__sort_dimension__add_hpp_output(sd) < 0)
+	if (__sort_dimension__add_hpp_output(sd, list) < 0)
 		return -1;
 
 	sd->taken = 1;
 	return 0;
 }
 
-static int __hpp_dimension__add_output(struct hpp_dimension *hd)
+static int __hpp_dimension__add_output(struct perf_hpp_list *list,
+				       struct hpp_dimension *hd)
 {
-	if (!hd->taken) {
-		hd->taken = 1;
+	struct perf_hpp_fmt *fmt;
 
-		perf_hpp__column_register(hd->fmt);
-	}
+	if (hd->taken)
+		return 0;
+
+	fmt = __hpp_dimension__alloc_hpp(hd, 0);
+	if (!fmt)
+		return -1;
+
+	hd->taken = 1;
+	perf_hpp_list__column_register(list, fmt);
 	return 0;
 }
 
 int hpp_dimension__add_output(unsigned col)
 {
 	BUG_ON(col >= PERF_HPP__MAX_INDEX);
-	return __hpp_dimension__add_output(&hpp_sort_dimensions[col]);
+	return __hpp_dimension__add_output(&perf_hpp_list, &hpp_sort_dimensions[col]);
 }
 
-static int sort_dimension__add(const char *tok,
-			       struct perf_evlist *evlist __maybe_unused)
+static int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
+			       struct perf_evlist *evlist __maybe_unused,
+			       int level)
 {
 	unsigned int i;
 
@@ -2136,9 +2261,13 @@ static int sort_dimension__add(const char *tok,
 			sort__has_dso = 1;
 		} else if (sd->entry == &sort_socket) {
 			sort__has_socket = 1;
+		} else if (sd->entry == &sort_thread) {
+			sort__has_thread = 1;
+		} else if (sd->entry == &sort_comm) {
+			sort__has_comm = 1;
 		}
 
-		return __sort_dimension__add(sd);
+		return __sort_dimension__add(sd, list, level);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
@@ -2147,7 +2276,7 @@ static int sort_dimension__add(const char *tok,
 		if (strncasecmp(tok, hd->name, strlen(tok)))
 			continue;
 
-		return __hpp_dimension__add(hd);
+		return __hpp_dimension__add(hd, list, level);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
@@ -2162,7 +2291,7 @@ static int sort_dimension__add(const char *tok,
 		if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to)
 			sort__has_sym = 1;
 
-		__sort_dimension__add(sd);
+		__sort_dimension__add(sd, list, level);
 		return 0;
 	}
 
@@ -2178,16 +2307,60 @@ static int sort_dimension__add(const char *tok,
 		if (sd->entry == &sort_mem_daddr_sym)
 			sort__has_sym = 1;
 
-		__sort_dimension__add(sd);
+		__sort_dimension__add(sd, list, level);
 		return 0;
 	}
 
-	if (!add_dynamic_entry(evlist, tok))
+	if (!add_dynamic_entry(evlist, tok, level))
 		return 0;
 
 	return -ESRCH;
 }
 
+static int setup_sort_list(struct perf_hpp_list *list, char *str,
+			   struct perf_evlist *evlist)
+{
+	char *tmp, *tok;
+	int ret = 0;
+	int level = 0;
+	int next_level = 1;
+	bool in_group = false;
+
+	do {
+		tok = str;
+		tmp = strpbrk(str, "{}, ");
+		if (tmp) {
+			if (in_group)
+				next_level = level;
+			else
+				next_level = level + 1;
+
+			if (*tmp == '{')
+				in_group = true;
+			else if (*tmp == '}')
+				in_group = false;
+
+			*tmp = '\0';
+			str = tmp + 1;
+		}
+
+		if (*tok) {
+			ret = sort_dimension__add(list, tok, evlist, level);
+			if (ret == -EINVAL) {
+				error("Invalid --sort key: `%s'", tok);
+				break;
+			} else if (ret == -ESRCH) {
+				error("Unknown --sort key: `%s'", tok);
+				break;
+			}
+		}
+
+		level = next_level;
+	} while (tmp);
+
+	return ret;
+}
+
 static const char *get_default_sort_order(struct perf_evlist *evlist)
 {
 	const char *default_sort_orders[] = {
@@ -2282,7 +2455,7 @@ static char *setup_overhead(char *keys)
 
 static int __setup_sorting(struct perf_evlist *evlist)
 {
-	char *tmp, *tok, *str;
+	char *str;
 	const char *sort_keys;
 	int ret = 0;
 
@@ -2320,17 +2493,7 @@ static int __setup_sorting(struct perf_evlist *evlist)
 		}
 	}
 
-	for (tok = strtok_r(str, ", ", &tmp);
-			tok; tok = strtok_r(NULL, ", ", &tmp)) {
-		ret = sort_dimension__add(tok, evlist);
-		if (ret == -EINVAL) {
-			error("Invalid --sort key: `%s'", tok);
-			break;
-		} else if (ret == -ESRCH) {
-			error("Unknown --sort key: `%s'", tok);
-			break;
-		}
-	}
+	ret = setup_sort_list(&perf_hpp_list, str, evlist);
 
 	free(str);
 	return ret;
@@ -2341,7 +2504,7 @@ void perf_hpp__set_elide(int idx, bool elide)
 	struct perf_hpp_fmt *fmt;
 	struct hpp_sort_entry *hse;
 
-	perf_hpp__for_each_format(fmt) {
+	perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
 		if (!perf_hpp__is_sort_entry(fmt))
 			continue;
 
@@ -2401,7 +2564,7 @@ void sort__setup_elide(FILE *output)
 	struct perf_hpp_fmt *fmt;
 	struct hpp_sort_entry *hse;
 
-	perf_hpp__for_each_format(fmt) {
+	perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
 		if (!perf_hpp__is_sort_entry(fmt))
 			continue;
 
@@ -2413,7 +2576,7 @@ void sort__setup_elide(FILE *output)
 	 * It makes no sense to elide all of sort entries.
 	 * Just revert them to show up again.
 	 */
-	perf_hpp__for_each_format(fmt) {
+	perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
 		if (!perf_hpp__is_sort_entry(fmt))
 			continue;
 
@@ -2421,7 +2584,7 @@ void sort__setup_elide(FILE *output)
 			return;
 	}
 
-	perf_hpp__for_each_format(fmt) {
+	perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
 		if (!perf_hpp__is_sort_entry(fmt))
 			continue;
 
@@ -2429,7 +2592,7 @@ void sort__setup_elide(FILE *output)
 	}
 }
 
-static int output_field_add(char *tok)
+static int output_field_add(struct perf_hpp_list *list, char *tok)
 {
 	unsigned int i;
 
@@ -2439,7 +2602,7 @@ static int output_field_add(char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		return __sort_dimension__add_output(sd);
+		return __sort_dimension__add_output(list, sd);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
@@ -2448,7 +2611,7 @@ static int output_field_add(char *tok)
 		if (strncasecmp(tok, hd->name, strlen(tok)))
 			continue;
 
-		return __hpp_dimension__add_output(hd);
+		return __hpp_dimension__add_output(list, hd);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
@@ -2457,7 +2620,7 @@ static int output_field_add(char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		return __sort_dimension__add_output(sd);
+		return __sort_dimension__add_output(list, sd);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) {
@@ -2466,12 +2629,32 @@ static int output_field_add(char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		return __sort_dimension__add_output(sd);
+		return __sort_dimension__add_output(list, sd);
 	}
 
 	return -ESRCH;
 }
 
+static int setup_output_list(struct perf_hpp_list *list, char *str)
+{
+	char *tmp, *tok;
+	int ret = 0;
+
+	for (tok = strtok_r(str, ", ", &tmp);
+			tok; tok = strtok_r(NULL, ", ", &tmp)) {
+		ret = output_field_add(list, tok);
+		if (ret == -EINVAL) {
+			error("Invalid --fields key: `%s'", tok);
+			break;
+		} else if (ret == -ESRCH) {
+			error("Unknown --fields key: `%s'", tok);
+			break;
+		}
+	}
+
+	return ret;
+}
+
 static void reset_dimensions(void)
 {
 	unsigned int i;
@@ -2496,7 +2679,7 @@ bool is_strict_order(const char *order)
 
 static int __setup_output_field(void)
 {
-	char *tmp, *tok, *str, *strp;
+	char *str, *strp;
 	int ret = -EINVAL;
 
 	if (field_order == NULL)
@@ -2516,17 +2699,7 @@ static int __setup_output_field(void)
 		goto out;
 	}
 
-	for (tok = strtok_r(strp, ", ", &tmp);
-			tok; tok = strtok_r(NULL, ", ", &tmp)) {
-		ret = output_field_add(tok);
-		if (ret == -EINVAL) {
-			error("Invalid --fields key: `%s'", tok);
-			break;
-		} else if (ret == -ESRCH) {
-			error("Unknown --fields key: `%s'", tok);
-			break;
-		}
-	}
+	ret = setup_output_list(&perf_hpp_list, strp);
 
 out:
 	free(str);
@@ -2542,7 +2715,7 @@ int setup_sorting(struct perf_evlist *evlist)
 		return err;
 
 	if (parent_pattern != default_parent_pattern) {
-		err = sort_dimension__add("parent", evlist);
+		err = sort_dimension__add(&perf_hpp_list, "parent", evlist, -1);
 		if (err < 0)
 			return err;
 	}
@@ -2560,9 +2733,13 @@ int setup_sorting(struct perf_evlist *evlist)
 		return err;
 
 	/* copy sort keys to output fields */
-	perf_hpp__setup_output_field();
+	perf_hpp__setup_output_field(&perf_hpp_list);
 	/* and then copy output fields to sort keys */
-	perf_hpp__append_sort_keys();
+	perf_hpp__append_sort_keys(&perf_hpp_list);
+
+	/* setup hists-specific output fields */
+	if (perf_hpp__setup_hists_formats(&perf_hpp_list, evlist) < 0)
+		return -1;
 
 	return 0;
 }
@@ -2578,5 +2755,5 @@ void reset_output_field(void)
 	sort_order = NULL;
 
 	reset_dimensions();
-	perf_hpp__reset_output_field();
+	perf_hpp__reset_output_field(&perf_hpp_list);
 }
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 687bbb124428..3f4e35998119 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -32,9 +32,12 @@ extern const char default_sort_order[];
 extern regex_t ignore_callees_regex;
 extern int have_ignore_callees;
 extern int sort__need_collapse;
+extern int sort__has_dso;
 extern int sort__has_parent;
 extern int sort__has_sym;
 extern int sort__has_socket;
+extern int sort__has_thread;
+extern int sort__has_comm;
 extern enum sort_mode sort__mode;
 extern struct sort_entry sort_comm;
 extern struct sort_entry sort_dso;
@@ -94,9 +97,11 @@ struct hist_entry {
 	s32			socket;
 	s32			cpu;
 	u8			cpumode;
+	u8			depth;
 
 	/* We are added by hists__add_dummy_entry. */
 	bool			dummy;
+	bool			leaf;
 
 	char			level;
 	u8			filtered;
@@ -113,18 +118,28 @@ struct hist_entry {
 			bool	init_have_children;
 			bool	unfolded;
 			bool	has_children;
+			bool	has_no_entry;
 		};
 	};
 	char			*srcline;
 	char			*srcfile;
 	struct symbol		*parent;
-	struct rb_root		sorted_chain;
 	struct branch_info	*branch_info;
 	struct hists		*hists;
 	struct mem_info		*mem_info;
 	void			*raw_data;
 	u32			raw_size;
 	void			*trace_output;
+	struct perf_hpp_list	*hpp_list;
+	struct hist_entry	*parent_he;
+	union {
+		/* this is for hierarchical entry structure */
+		struct {
+			struct rb_root	hroot_in;
+			struct rb_root  hroot_out;
+		};				/* non-leaf entries */
+		struct rb_root	sorted_chain;	/* leaf entry has callchains */
+	};
 	struct callchain_root	callchain[0]; /* must be last member */
 };
 
@@ -160,6 +175,17 @@ static inline float hist_entry__get_percent_limit(struct hist_entry *he)
 	return period * 100.0 / total_period;
 }
 
+static inline u64 cl_address(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & ~(cacheline_size - 1));
+}
+
+static inline u64 cl_offset(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & (cacheline_size - 1));
+}
 
 enum sort_mode {
 	SORT_MODE__NORMAL,
@@ -221,6 +247,7 @@ struct sort_entry {
 	int64_t	(*se_sort)(struct hist_entry *, struct hist_entry *);
 	int	(*se_snprintf)(struct hist_entry *he, char *bf, size_t size,
 			       unsigned int width);
+	int	(*se_filter)(struct hist_entry *he, int type, const void *arg);
 	u8	se_width_idx;
 };
 
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 6ac03146889d..b33ffb2af2cf 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -2,6 +2,7 @@
 #include "evsel.h"
 #include "stat.h"
 #include "color.h"
+#include "pmu.h"
 
 enum {
 	CTX_BIT_USER	= 1 << 0,
@@ -14,6 +15,13 @@ enum {
 
 #define NUM_CTX CTX_BIT_MAX
 
+/*
+ * AGGR_GLOBAL: Use CPU 0
+ * AGGR_SOCKET: Use first CPU of socket
+ * AGGR_CORE: Use first CPU of core
+ * AGGR_NONE: Use matching CPU
+ * AGGR_THREAD: Not supported?
+ */
 static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
 static struct stats runtime_cycles_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_stalled_cycles_front_stats[NUM_CTX][MAX_NR_CPUS];
@@ -28,9 +36,15 @@ static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS];
+static bool have_frontend_stalled;
 
 struct stats walltime_nsecs_stats;
 
+void perf_stat__init_shadow_stats(void)
+{
+	have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend");
+}
+
 static int evsel_context(struct perf_evsel *evsel)
 {
 	int ctx = 0;
@@ -137,9 +151,10 @@ static const char *get_ratio_color(enum grc_type type, double ratio)
 	return color;
 }
 
-static void print_stalled_cycles_frontend(FILE *out, int cpu,
+static void print_stalled_cycles_frontend(int cpu,
 					  struct perf_evsel *evsel
-					  __maybe_unused, double avg)
+					  __maybe_unused, double avg,
+					  struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -152,14 +167,17 @@ static void print_stalled_cycles_frontend(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " frontend cycles idle   ");
+	if (ratio)
+		out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle",
+				  ratio);
+	else
+		out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0);
 }
 
-static void print_stalled_cycles_backend(FILE *out, int cpu,
+static void print_stalled_cycles_backend(int cpu,
 					 struct perf_evsel *evsel
-					 __maybe_unused, double avg)
+					 __maybe_unused, double avg,
+					 struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -172,14 +190,13 @@ static void print_stalled_cycles_backend(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " backend  cycles idle   ");
+	out->print_metric(out->ctx, color, "%6.2f%%", "backend cycles idle", ratio);
 }
 
-static void print_branch_misses(FILE *out, int cpu,
+static void print_branch_misses(int cpu,
 				struct perf_evsel *evsel __maybe_unused,
-				double avg)
+				double avg,
+				struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -192,14 +209,13 @@ static void print_branch_misses(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all branches        ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all branches", ratio);
 }
 
-static void print_l1_dcache_misses(FILE *out, int cpu,
+static void print_l1_dcache_misses(int cpu,
 				   struct perf_evsel *evsel __maybe_unused,
-				   double avg)
+				   double avg,
+				   struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -212,14 +228,13 @@ static void print_l1_dcache_misses(FILE *out, int cpu,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all L1-dcache hits  ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
 }
 
-static void print_l1_icache_misses(FILE *out, int cpu,
+static void print_l1_icache_misses(int cpu,
 				   struct perf_evsel *evsel __maybe_unused,
-				   double avg)
+				   double avg,
+				   struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -231,15 +246,13 @@ static void print_l1_icache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all L1-icache hits  ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
 }
 
-static void print_dtlb_cache_misses(FILE *out, int cpu,
+static void print_dtlb_cache_misses(int cpu,
 				    struct perf_evsel *evsel __maybe_unused,
-				    double avg)
+				    double avg,
+				    struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -251,15 +264,13 @@ static void print_dtlb_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all dTLB cache hits ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
 }
 
-static void print_itlb_cache_misses(FILE *out, int cpu,
+static void print_itlb_cache_misses(int cpu,
 				    struct perf_evsel *evsel __maybe_unused,
-				    double avg)
+				    double avg,
+				    struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -271,15 +282,13 @@ static void print_itlb_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all iTLB cache hits ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
 }
 
-static void print_ll_cache_misses(FILE *out, int cpu,
+static void print_ll_cache_misses(int cpu,
 				  struct perf_evsel *evsel __maybe_unused,
-				  double avg)
+				  double avg,
+				  struct perf_stat_output_ctx *out)
 {
 	double total, ratio = 0.0;
 	const char *color;
@@ -291,15 +300,15 @@ static void print_ll_cache_misses(FILE *out, int cpu,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(out, " #  ");
-	color_fprintf(out, color, "%6.2f%%", ratio);
-	fprintf(out, " of all LL-cache hits   ");
+	out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
 }
 
-void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
-				   double avg, int cpu, enum aggr_mode aggr)
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+				   double avg, int cpu,
+				   struct perf_stat_output_ctx *out)
 {
+	void *ctxp = out->ctx;
+	print_metric_t print_metric = out->print_metric;
 	double total, ratio = 0.0, total2;
 	int ctx = evsel_context(evsel);
 
@@ -307,119 +316,145 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		if (total) {
 			ratio = avg / total;
-			fprintf(out, " #   %5.2f  insns per cycle        ", ratio);
+			print_metric(ctxp, NULL, "%7.2f ",
+					"insn per cycle", ratio);
 		} else {
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
 		}
 		total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
 		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
 
 		if (total && avg) {
+			out->new_line(ctxp);
 			ratio = total / avg;
-			fprintf(out, "\n");
-			if (aggr == AGGR_NONE)
-				fprintf(out, "        ");
-			fprintf(out, "                                                  #   %5.2f  stalled cycles per insn", ratio);
+			print_metric(ctxp, NULL, "%7.2f ",
+					"stalled cycles per insn",
+					ratio);
+		} else if (have_frontend_stalled) {
+			print_metric(ctxp, NULL, NULL,
+				     "stalled cycles per insn", 0);
 		}
-
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
-			runtime_branches_stats[ctx][cpu].n != 0) {
-		print_branch_misses(out, cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
+		if (runtime_branches_stats[ctx][cpu].n != 0)
+			print_branch_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all branches", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_l1_dcache_stats[ctx][cpu].n != 0) {
-		print_l1_dcache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_l1_dcache_stats[ctx][cpu].n != 0)
+			print_l1_dcache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_l1_icache_stats[ctx][cpu].n != 0) {
-		print_l1_icache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_l1_icache_stats[ctx][cpu].n != 0)
+			print_l1_icache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_dtlb_cache_stats[ctx][cpu].n != 0) {
-		print_dtlb_cache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_dtlb_cache_stats[ctx][cpu].n != 0)
+			print_dtlb_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_itlb_cache_stats[ctx][cpu].n != 0) {
-		print_itlb_cache_misses(out, cpu, evsel, avg);
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_itlb_cache_stats[ctx][cpu].n != 0)
+			print_itlb_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
 	} else if (
 		evsel->attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_ll_cache_stats[ctx][cpu].n != 0) {
-		print_ll_cache_misses(out, cpu, evsel, avg);
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
-			runtime_cacherefs_stats[ctx][cpu].n != 0) {
+					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+		if (runtime_ll_cache_stats[ctx][cpu].n != 0)
+			print_ll_cache_misses(cpu, evsel, avg, out);
+		else
+			print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
 		total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
 
 		if (total)
 			ratio = avg * 100 / total;
 
-		fprintf(out, " # %8.3f %% of all cache refs    ", ratio);
-
+		if (runtime_cacherefs_stats[ctx][cpu].n != 0)
+			print_metric(ctxp, NULL, "%8.3f %%",
+				     "of all cache refs", ratio);
+		else
+			print_metric(ctxp, NULL, NULL, "of all cache refs", 0);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-		print_stalled_cycles_frontend(out, cpu, evsel, avg);
+		print_stalled_cycles_frontend(cpu, evsel, avg, out);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-		print_stalled_cycles_backend(out, cpu, evsel, avg);
+		print_stalled_cycles_backend(cpu, evsel, avg, out);
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
 		if (total) {
 			ratio = avg / total;
-			fprintf(out, " # %8.3f GHz                    ", ratio);
+			print_metric(ctxp, NULL, "%8.3f", "GHz", ratio);
 		} else {
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "Ghz", 0);
 		}
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		if (total)
-			fprintf(out,
-				" #   %5.2f%% transactional cycles   ",
-				100.0 * (avg / total));
+			print_metric(ctxp, NULL,
+					"%7.2f%%", "transactional cycles",
+					100.0 * (avg / total));
+		else
+			print_metric(ctxp, NULL, NULL, "transactional cycles",
+				     0);
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
 		total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 		if (total2 < avg)
 			total2 = avg;
 		if (total)
-			fprintf(out,
-				" #   %5.2f%% aborted cycles         ",
+			print_metric(ctxp, NULL, "%7.2f%%", "aborted cycles",
 				100.0 * ((total2-avg) / total));
-	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
-		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		else
+			print_metric(ctxp, NULL, NULL, "aborted cycles", 0);
+	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
 		if (avg)
 			ratio = total / avg;
 
-		fprintf(out, " # %8.0f cycles / transaction   ", ratio);
-	} else if (perf_stat_evsel__is(evsel, ELISION_START) &&
-		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		if (runtime_cycles_in_tx_stats[ctx][cpu].n != 0)
+			print_metric(ctxp, NULL, "%8.0f",
+				     "cycles / transaction", ratio);
+		else
+			print_metric(ctxp, NULL, NULL, "cycles / transaction",
+				     0);
+	} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
 		if (avg)
 			ratio = total / avg;
 
-		fprintf(out, " # %8.0f cycles / elision       ", ratio);
+		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
 	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
-			fprintf(out, " # %8.3f CPUs utilized          ", avg / ratio);
+			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
+				     avg / ratio);
 		else
-			fprintf(out, "                                   ");
+			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
+		char unit_buf[10];
 
 		total = avg_stats(&runtime_nsecs_stats[cpu]);
 
@@ -429,9 +464,9 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 			ratio *= 1000;
 			unit = 'K';
 		}
-
-		fprintf(out, " # %8.3f %c/sec                  ", ratio, unit);
+		snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
+		print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
 	} else {
-		fprintf(out, "                                   ");
+		print_metric(ctxp, NULL, NULL, NULL, 0);
 	}
 }
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 2b58edccd56f..4d9b481cf3b6 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -97,7 +97,7 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel)
 	}
 }
 
-void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
+static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 {
 	int i;
 	struct perf_stat_evsel *ps = evsel->priv;
@@ -108,7 +108,7 @@ void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 	perf_stat_evsel_id_init(evsel);
 }
 
-int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
+static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 {
 	evsel->priv = zalloc(sizeof(struct perf_stat_evsel));
 	if (evsel->priv == NULL)
@@ -117,13 +117,13 @@ int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 	return 0;
 }
 
-void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
+static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 {
 	zfree(&evsel->priv);
 }
 
-int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
-				      int ncpus, int nthreads)
+static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
+					     int ncpus, int nthreads)
 {
 	struct perf_counts *counts;
 
@@ -134,13 +134,13 @@ int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
 	return counts ? 0 : -ENOMEM;
 }
 
-void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
+static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
 {
 	perf_counts__delete(evsel->prev_raw_counts);
 	evsel->prev_raw_counts = NULL;
 }
 
-int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
+static int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
 {
 	int ncpus = perf_evsel__nr_cpus(evsel);
 	int nthreads = thread_map__nr(evsel->threads);
@@ -311,6 +311,16 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 
 	aggr->val = aggr->ena = aggr->run = 0;
 
+	/*
+	 * We calculate counter's data every interval,
+	 * and the display code shows ps->res_stats
+	 * avg value. We need to zero the stats for
+	 * interval mode, otherwise overall avg running
+	 * averages will be shown for each interval.
+	 */
+	if (config->interval)
+		init_stats(ps->res_stats);
+
 	if (counter->per_pkg)
 		zero_per_pkg(counter);
 
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 086f4e128d63..0150e786ccc7 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -68,21 +68,23 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel);
 
 extern struct stats walltime_nsecs_stats;
 
+typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
+			       const char *fmt, double val);
+typedef void (*new_line_t )(void *ctx);
+
+void perf_stat__init_shadow_stats(void);
 void perf_stat__reset_shadow_stats(void);
 void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 				    int cpu);
-void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
-				   double avg, int cpu, enum aggr_mode aggr);
-
-void perf_evsel__reset_stat_priv(struct perf_evsel *evsel);
-int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel);
-void perf_evsel__free_stat_priv(struct perf_evsel *evsel);
-
-int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
-				      int ncpus, int nthreads);
-void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel);
+struct perf_stat_output_ctx {
+	void *ctx;
+	print_metric_t print_metric;
+	new_line_t new_line;
+};
 
-int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw);
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+				   double avg, int cpu,
+				   struct perf_stat_output_ctx *out);
 
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
 void perf_evlist__free_stats(struct perf_evlist *evlist);
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 25671fa16618..d3d279275432 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -51,30 +51,6 @@ void strbuf_grow(struct strbuf *sb, size_t extra)
 	ALLOC_GROW(sb->buf, sb->len + extra + 1, sb->alloc);
 }
 
-static void strbuf_splice(struct strbuf *sb, size_t pos, size_t len,
-				   const void *data, size_t dlen)
-{
-	if (pos + len < pos)
-		die("you want to use way too much memory");
-	if (pos > sb->len)
-		die("`pos' is too far after the end of the buffer");
-	if (pos + len > sb->len)
-		die("`pos + len' is too far after the end of the buffer");
-
-	if (dlen >= len)
-		strbuf_grow(sb, dlen - len);
-	memmove(sb->buf + pos + dlen,
-			sb->buf + pos + len,
-			sb->len - pos - len);
-	memcpy(sb->buf + pos, data, dlen);
-	strbuf_setlen(sb, sb->len + dlen - len);
-}
-
-void strbuf_remove(struct strbuf *sb, size_t pos, size_t len)
-{
-	strbuf_splice(sb, pos, len, NULL, 0);
-}
-
 void strbuf_add(struct strbuf *sb, const void *data, size_t len)
 {
 	strbuf_grow(sb, len);
diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h
index 529f2f035249..7a32c838884d 100644
--- a/tools/perf/util/strbuf.h
+++ b/tools/perf/util/strbuf.h
@@ -77,8 +77,6 @@ static inline void strbuf_addch(struct strbuf *sb, int c) {
 	sb->buf[sb->len] = '\0';
 }
 
-extern void strbuf_remove(struct strbuf *, size_t pos, size_t len);
-
 extern void strbuf_add(struct strbuf *, const void *, size_t);
 static inline void strbuf_addstr(struct strbuf *sb, const char *s) {
 	strbuf_add(sb, s, strlen(s));
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 562b8ebeae5b..b1dd68f358fc 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -6,6 +6,7 @@
 #include <inttypes.h>
 
 #include "symbol.h"
+#include "demangle-java.h"
 #include "machine.h"
 #include "vdso.h"
 #include <symbol/kallsyms.h>
@@ -1077,6 +1078,8 @@ new_symbol:
 				demangle_flags = DMGL_PARAMS | DMGL_ANSI;
 
 			demangled = bfd_demangle(NULL, elf_name, demangle_flags);
+			if (demangled == NULL)
+				demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET);
 			if (demangled != NULL)
 				elf_name = demangled;
 		}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index ab02209a7cf3..e7588dc91518 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1466,7 +1466,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	 * Read the build id if possible. This is required for
 	 * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
 	 */
-	if (filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
+	if (is_regular_file(name) &&
+	    filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
 		dso__set_build_id(dso, build_id);
 
 	/*
@@ -1487,6 +1488,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 						   root_dir, name, PATH_MAX))
 			continue;
 
+		if (!is_regular_file(name))
+			continue;
+
 		/* Name is now the name of the next image to try */
 		if (symsrc__init(ss, dso, name, symtab_type) < 0)
 			continue;
@@ -1525,6 +1529,10 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	if (!runtime_ss && syms_ss)
 		runtime_ss = syms_ss;
 
+	if (syms_ss && syms_ss->type == DSO_BINARY_TYPE__BUILD_ID_CACHE)
+		if (dso__build_id_is_kmod(dso, name, PATH_MAX))
+			kmod = true;
+
 	if (syms_ss)
 		ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, kmod);
 	else
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index ccd1caa40e11..a937053a0ae0 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -110,7 +110,8 @@ struct symbol_conf {
 			has_filter,
 			show_ref_callgraph,
 			hide_unresolved,
-			raw_trace;
+			raw_trace,
+			report_hierarchy;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 802bb868d446..8ae051e0ec79 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -10,6 +10,7 @@
 #include <linux/err.h>
 #include <traceevent/event-parse.h>
 #include <api/fs/tracing_path.h>
+#include <api/fs/fs.h>
 #include "trace-event.h"
 #include "machine.h"
 #include "util.h"
diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c
index 4d4210d4e13d..1b741646eed0 100644
--- a/tools/perf/util/tsc.c
+++ b/tools/perf/util/tsc.c
@@ -19,7 +19,7 @@ u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
 	u64 quot, rem;
 
 	quot = cyc >> tc->time_shift;
-	rem  = cyc & ((1 << tc->time_shift) - 1);
+	rem  = cyc & (((u64)1 << tc->time_shift) - 1);
 	return tc->time_zero + quot * tc->time_mult +
 	       ((rem * tc->time_mult) >> tc->time_shift);
 }
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index ead9509835d2..b7766c577b01 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -14,6 +14,7 @@
 #include <limits.h>
 #include <byteswap.h>
 #include <linux/kernel.h>
+#include <linux/log2.h>
 #include <unistd.h>
 #include "callchain.h"
 #include "strlist.h"
@@ -507,54 +508,6 @@ int parse_callchain_record(const char *arg, struct callchain_param *param)
 	return ret;
 }
 
-int filename__read_str(const char *filename, char **buf, size_t *sizep)
-{
-	size_t size = 0, alloc_size = 0;
-	void *bf = NULL, *nbf;
-	int fd, n, err = 0;
-	char sbuf[STRERR_BUFSIZE];
-
-	fd = open(filename, O_RDONLY);
-	if (fd < 0)
-		return -errno;
-
-	do {
-		if (size == alloc_size) {
-			alloc_size += BUFSIZ;
-			nbf = realloc(bf, alloc_size);
-			if (!nbf) {
-				err = -ENOMEM;
-				break;
-			}
-
-			bf = nbf;
-		}
-
-		n = read(fd, bf + size, alloc_size - size);
-		if (n < 0) {
-			if (size) {
-				pr_warning("read failed %d: %s\n", errno,
-					 strerror_r(errno, sbuf, sizeof(sbuf)));
-				err = 0;
-			} else
-				err = -errno;
-
-			break;
-		}
-
-		size += n;
-	} while (n > 0);
-
-	if (!err) {
-		*sizep = size;
-		*buf   = bf;
-	} else
-		free(bf);
-
-	close(fd);
-	return err;
-}
-
 const char *get_filename_for_perf_kvm(void)
 {
 	const char *filename;
@@ -691,3 +644,66 @@ out:
 
 	return tip;
 }
+
+bool is_regular_file(const char *file)
+{
+	struct stat st;
+
+	if (stat(file, &st))
+		return false;
+
+	return S_ISREG(st.st_mode);
+}
+
+int fetch_current_timestamp(char *buf, size_t sz)
+{
+	struct timeval tv;
+	struct tm tm;
+	char dt[32];
+
+	if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm))
+		return -1;
+
+	if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm))
+		return -1;
+
+	scnprintf(buf, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000);
+
+	return 0;
+}
+
+void print_binary(unsigned char *data, size_t len,
+		  size_t bytes_per_line, print_binary_t printer,
+		  void *extra)
+{
+	size_t i, j, mask;
+
+	if (!printer)
+		return;
+
+	bytes_per_line = roundup_pow_of_two(bytes_per_line);
+	mask = bytes_per_line - 1;
+
+	printer(BINARY_PRINT_DATA_BEGIN, 0, extra);
+	for (i = 0; i < len; i++) {
+		if ((i & mask) == 0) {
+			printer(BINARY_PRINT_LINE_BEGIN, -1, extra);
+			printer(BINARY_PRINT_ADDR, i, extra);
+		}
+
+		printer(BINARY_PRINT_NUM_DATA, data[i], extra);
+
+		if (((i & mask) == mask) || i == len - 1) {
+			for (j = 0; j < mask-(i & mask); j++)
+				printer(BINARY_PRINT_NUM_PAD, -1, extra);
+
+			printer(BINARY_PRINT_SEP, i, extra);
+			for (j = i & ~mask; j <= i; j++)
+				printer(BINARY_PRINT_CHAR_DATA, data[j], extra);
+			for (j = 0; j < mask-(i & mask); j++)
+				printer(BINARY_PRINT_CHAR_PAD, i, extra);
+			printer(BINARY_PRINT_LINE_END, -1, extra);
+		}
+	}
+	printer(BINARY_PRINT_DATA_END, -1, extra);
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index fe915e616f9b..d0d50cef8b2a 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -82,6 +82,8 @@
 
 extern const char *graph_line;
 extern const char *graph_dotted_line;
+extern const char *spaces;
+extern const char *dots;
 extern char buildid_dir[];
 
 /* On most systems <limits.h> would have given us this, but
@@ -303,7 +305,6 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 		  bool show_sym, bool unwind_inlines);
 void free_srcline(char *srcline);
 
-int filename__read_str(const char *filename, char **buf, size_t *sizep);
 int perf_event_paranoid(void);
 
 void mem_bswap_64(void *src, int byte_size);
@@ -343,5 +344,27 @@ int fetch_kernel_version(unsigned int *puint,
 #define KVER_PARAM(x)	KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x)
 
 const char *perf_tip(const char *dirpath);
+bool is_regular_file(const char *file);
+int fetch_current_timestamp(char *buf, size_t sz);
+
+enum binary_printer_ops {
+	BINARY_PRINT_DATA_BEGIN,
+	BINARY_PRINT_LINE_BEGIN,
+	BINARY_PRINT_ADDR,
+	BINARY_PRINT_NUM_DATA,
+	BINARY_PRINT_NUM_PAD,
+	BINARY_PRINT_SEP,
+	BINARY_PRINT_CHAR_DATA,
+	BINARY_PRINT_CHAR_PAD,
+	BINARY_PRINT_LINE_END,
+	BINARY_PRINT_DATA_END,
+};
+
+typedef void (*print_binary_t)(enum binary_printer_ops,
+			       unsigned int val,
+			       void *extra);
 
+void print_binary(unsigned char *data, size_t len,
+		  size_t bytes_per_line, print_binary_t printer,
+		  void *extra);
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index 622db685b4f9..89a55d5e32f3 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -34,7 +34,10 @@ name as necessary to disambiguate it from others is necessary.  Note that option
 \fB--debug\fP displays additional system configuration information.  Invoking this parameter
 more than once may also enable internal turbostat debug information.
 .PP
-\fB--interval seconds\fP overrides the default 5-second measurement interval.
+\fB--interval seconds\fP overrides the default 5.0 second measurement interval.
+.PP
+\fB--out output_file\fP turbostat output is written to the specified output_file.
+The file is truncated if it already exists, and it is created if it does not exist.
 .PP
 \fB--help\fP displays usage for the most common parameters.
 .PP
@@ -61,7 +64,7 @@ displays the statistics gathered since it was forked.
 .nf
 \fBCPU\fP Linux CPU (logical processor) number.  Yes, it is okay that on many systems the CPUs are not listed in numerical order -- for efficiency reasons, turbostat runs in topology order, so HT siblings appear together.
 \fBAVG_MHz\fP number of cycles executed divided by time elapsed.
-\fB%Busy\fP percent of the interval that the CPU retired instructions, aka. % of time in "C0" state.
+\fBBusy%\fP percent of the interval that the CPU retired instructions, aka. % of time in "C0" state.
 \fBBzy_MHz\fP average clock rate while the CPU was busy (in "c0" state).
 \fBTSC_MHz\fP average MHz that the TSC ran during the entire interval.
 .fi
@@ -83,13 +86,14 @@ Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading T
 \fBRAM_%\fP percent of the interval that RAPL throttling was active on DRAM.
 .fi
 .PP
-.SH EXAMPLE
+.SH PERIODIC EXAMPLE
 Without any parameters, turbostat displays statistics ever 5 seconds.
-(override interval with "-i sec" option, or specify a command
-for turbostat to fork).
+Periodic output goes to stdout, by default, unless --out is used to specify an output file.
+The 5-second interval can be changed with th "-i sec" option.
+Or a command may be specified as in "FORK EXAMPLE" below.
 .nf
 [root@hsw]# ./turbostat
-     CPU Avg_MHz   %Busy Bzy_MHz TSC_MHz
+     CPU Avg_MHz   Busy% Bzy_MHz TSC_MHz
        -     488   12.51    3898    3498
        0       0    0.01    3885    3498
        4    3897   99.99    3898    3498
@@ -145,7 +149,7 @@ cpu0: MSR_IA32_THERM_STATUS: 0x88340000 (48 C +/- 1)
 cpu1: MSR_IA32_THERM_STATUS: 0x88440000 (32 C +/- 1)
 cpu2: MSR_IA32_THERM_STATUS: 0x88450000 (31 C +/- 1)
 cpu3: MSR_IA32_THERM_STATUS: 0x88490000 (27 C +/- 1)
-    Core     CPU Avg_MHz   %Busy Bzy_MHz TSC_MHz     SMI  CPU%c1  CPU%c3  CPU%c6  CPU%c7 CoreTmp  PkgTmp PkgWatt CorWatt GFXWatt
+    Core     CPU Avg_MHz   Busy% Bzy_MHz TSC_MHz     SMI  CPU%c1  CPU%c3  CPU%c6  CPU%c7 CoreTmp  PkgTmp PkgWatt CorWatt GFXWatt
        -       -     493   12.64    3898    3498       0   12.64    0.00    0.00   74.72      47      47   21.62   13.74    0.00
        0       0       4    0.11    3894    3498       0   99.89    0.00    0.00    0.00      47      47   21.62   13.74    0.00
        0       4    3897   99.98    3898    3498       0    0.02
@@ -171,14 +175,16 @@ The --debug option adds additional columns to the measurement ouput, including C
 See the field definitions above.
 .SH FORK EXAMPLE
 If turbostat is invoked with a command, it will fork that command
-and output the statistics gathered when the command exits.
+and output the statistics gathered after the command exits.
+In this case, turbostat output goes to stderr, by default.
+Output can instead be saved to a file using the --out option.
 eg. Here a cycle soaker is run on 1 CPU (see %c0) for a few seconds
 until ^C while the other CPUs are mostly idle:
 
 .nf
 root@hsw: turbostat cat /dev/zero > /dev/null
 ^C
-     CPU Avg_MHz   %Busy Bzy_MHz TSC_MHz
+     CPU Avg_MHz   Busy% Bzy_MHz TSC_MHz
        -     482   12.51    3854    3498
        0       0    0.01    1960    3498
        4       0    0.00    2128    3498
@@ -192,12 +198,12 @@ root@hsw: turbostat cat /dev/zero > /dev/null
 
 .fi
 Above the cycle soaker drives cpu5 up its 3.9 GHz turbo limit.
-The first row shows the average MHz and %Busy across all the processors in the system.
+The first row shows the average MHz and Busy% across all the processors in the system.
 
 Note that the Avg_MHz column reflects the total number of cycles executed
-divided by the measurement interval.  If the %Busy column is 100%,
+divided by the measurement interval.  If the Busy% column is 100%,
 then the processor was running at that speed the entire interval.
-The Avg_MHz multiplied by the %Busy results in the Bzy_MHz --
+The Avg_MHz multiplied by the Busy% results in the Bzy_MHz --
 which is the average frequency while the processor was executing --
 not including any non-busy idle time.
 
@@ -233,7 +239,7 @@ in the brand string in /proc/cpuinfo.  On a system where
 the TSC stops in idle, TSC_MHz will drop
 below the processor's base frequency.
 
-%Busy = MPERF_delta/TSC_delta
+Busy% = MPERF_delta/TSC_delta
 
 Bzy_MHz = TSC_delta/APERF_delta/MPERF_delta/measurement_interval
 
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 0dac7e05a6ac..20a257a12ea5 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -38,12 +38,15 @@
 #include <string.h>
 #include <ctype.h>
 #include <sched.h>
+#include <time.h>
 #include <cpuid.h>
 #include <linux/capability.h>
 #include <errno.h>
 
 char *proc_stat = "/proc/stat";
-unsigned int interval_sec = 5;
+FILE *outf;
+int *fd_percpu;
+struct timespec interval_ts = {5, 0};
 unsigned int debug;
 unsigned int rapl_joules;
 unsigned int summary_only;
@@ -72,6 +75,7 @@ unsigned int extra_msr_offset64;
 unsigned int extra_delta_offset32;
 unsigned int extra_delta_offset64;
 unsigned int aperf_mperf_multiplier = 1;
+int do_irq = 1;
 int do_smi;
 double bclk;
 double base_hz;
@@ -86,6 +90,10 @@ char *output_buffer, *outp;
 unsigned int do_rapl;
 unsigned int do_dts;
 unsigned int do_ptm;
+unsigned int do_gfx_rc6_ms;
+unsigned long long  gfx_cur_rc6_ms;
+unsigned int do_gfx_mhz;
+unsigned int gfx_cur_mhz;
 unsigned int tcc_activation_temp;
 unsigned int tcc_activation_temp_override;
 double rapl_power_units, rapl_time_units;
@@ -98,6 +106,12 @@ unsigned int crystal_hz;
 unsigned long long tsc_hz;
 int base_cpu;
 double discover_bclk(unsigned int family, unsigned int model);
+unsigned int has_hwp;	/* IA32_PM_ENABLE, IA32_HWP_CAPABILITIES */
+			/* IA32_HWP_REQUEST, IA32_HWP_STATUS */
+unsigned int has_hwp_notify;		/* IA32_HWP_INTERRUPT */
+unsigned int has_hwp_activity_window;	/* IA32_HWP_REQUEST[bits 41:32] */
+unsigned int has_hwp_epp;		/* IA32_HWP_REQUEST[bits 31:24] */
+unsigned int has_hwp_pkg;		/* IA32_HWP_REQUEST_PKG */
 
 #define RAPL_PKG		(1 << 0)
 					/* 0x610 MSR_PKG_POWER_LIMIT */
@@ -145,6 +159,7 @@ struct thread_data {
 	unsigned long long extra_delta64;
 	unsigned long long extra_msr32;
 	unsigned long long extra_delta32;
+	unsigned int irq_count;
 	unsigned int smi_count;
 	unsigned int cpu_id;
 	unsigned int flags;
@@ -172,6 +187,8 @@ struct pkg_data {
 	unsigned long long pkg_any_core_c0;
 	unsigned long long pkg_any_gfxe_c0;
 	unsigned long long pkg_both_core_gfxe_c0;
+	unsigned long long gfx_rc6_ms;
+	unsigned int gfx_mhz;
 	unsigned int package_id;
 	unsigned int energy_pkg;	/* MSR_PKG_ENERGY_STATUS */
 	unsigned int energy_dram;	/* MSR_DRAM_ENERGY_STATUS */
@@ -212,6 +229,9 @@ struct topo_params {
 
 struct timeval tv_even, tv_odd, tv_delta;
 
+int *irq_column_2_cpu;	/* /proc/interrupts column numbers */
+int *irqs_per_cpu;		/* indexed by cpu_num */
+
 void setup_all_buffers(void);
 
 int cpu_is_not_present(int cpu)
@@ -262,23 +282,34 @@ int cpu_migrate(int cpu)
 	else
 		return 0;
 }
-
-int get_msr(int cpu, off_t offset, unsigned long long *msr)
+int get_msr_fd(int cpu)
 {
-	ssize_t retval;
 	char pathname[32];
 	int fd;
 
+	fd = fd_percpu[cpu];
+
+	if (fd)
+		return fd;
+
 	sprintf(pathname, "/dev/cpu/%d/msr", cpu);
 	fd = open(pathname, O_RDONLY);
 	if (fd < 0)
 		err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname);
 
-	retval = pread(fd, msr, sizeof *msr, offset);
-	close(fd);
+	fd_percpu[cpu] = fd;
+
+	return fd;
+}
+
+int get_msr(int cpu, off_t offset, unsigned long long *msr)
+{
+	ssize_t retval;
+
+	retval = pread(get_msr_fd(cpu), msr, sizeof(*msr), offset);
 
 	if (retval != sizeof *msr)
-		err(-1, "%s offset 0x%llx read failed", pathname, (unsigned long long)offset);
+		err(-1, "msr %d offset 0x%llx read failed", cpu, (unsigned long long)offset);
 
 	return 0;
 }
@@ -286,8 +317,8 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
 /*
  * Example Format w/ field column widths:
  *
- *  Package    Core     CPU Avg_MHz Bzy_MHz TSC_MHz     SMI   %Busy CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 CoreTmp  PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt
- * 123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678
+ *  Package    Core     CPU Avg_MHz Bzy_MHz TSC_MHz     IRQ   SMI   Busy% CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 CoreTmp  PkgTmp  GFXMHz Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt
+ * 12345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678
  */
 
 void print_header(void)
@@ -301,7 +332,7 @@ void print_header(void)
 	if (has_aperf)
 		outp += sprintf(outp, " Avg_MHz");
 	if (has_aperf)
-		outp += sprintf(outp, "   %%Busy");
+		outp += sprintf(outp, "   Busy%%");
 	if (has_aperf)
 		outp += sprintf(outp, " Bzy_MHz");
 	outp += sprintf(outp, " TSC_MHz");
@@ -318,6 +349,8 @@ void print_header(void)
 	if (!debug)
 		goto done;
 
+	if (do_irq)
+		outp += sprintf(outp, "     IRQ");
 	if (do_smi)
 		outp += sprintf(outp, "     SMI");
 
@@ -335,6 +368,12 @@ void print_header(void)
 	if (do_ptm)
 		outp += sprintf(outp, "  PkgTmp");
 
+	if (do_gfx_rc6_ms)
+		outp += sprintf(outp, " GFX%%rc6");
+
+	if (do_gfx_mhz)
+		outp += sprintf(outp, "  GFXMHz");
+
 	if (do_skl_residency) {
 		outp += sprintf(outp, " Totl%%C0");
 		outp += sprintf(outp, "  Any%%C0");
@@ -409,6 +448,8 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 			extra_msr_offset32, t->extra_msr32);
 		outp += sprintf(outp, "msr0x%x: %016llX\n",
 			extra_msr_offset64, t->extra_msr64);
+		if (do_irq)
+			outp += sprintf(outp, "IRQ: %08X\n", t->irq_count);
 		if (do_smi)
 			outp += sprintf(outp, "SMI: %08X\n", t->smi_count);
 	}
@@ -504,7 +545,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "%8.0f",
 			1.0 / units * t->aperf / interval_float);
 
-	/* %Busy */
+	/* Busy% */
 	if (has_aperf) {
 		if (!skip_c0)
 			outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc/tsc_tweak);
@@ -542,6 +583,10 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (!debug)
 		goto done;
 
+	/* IRQ */
+	if (do_irq)
+		outp += sprintf(outp, "%8d", t->irq_count);
+
 	/* SMI */
 	if (do_smi)
 		outp += sprintf(outp, "%8d", t->smi_count);
@@ -575,6 +620,14 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (do_ptm)
 		outp += sprintf(outp, "%8d", p->pkg_temp_c);
 
+	/* GFXrc6 */
+	if (do_gfx_rc6_ms)
+		outp += sprintf(outp, "%8.2f", 100.0 * p->gfx_rc6_ms / 1000.0 / interval_float);
+
+	/* GFXMHz */
+	if (do_gfx_mhz)
+		outp += sprintf(outp, "%8d", p->gfx_mhz);
+
 	/* Totl%C0, Any%C0 GFX%C0 CPUGFX% */
 	if (do_skl_residency) {
 		outp += sprintf(outp, "%8.2f", 100.0 * p->pkg_wtd_core_c0/t->tsc);
@@ -645,15 +698,24 @@ done:
 	return 0;
 }
 
-void flush_stdout()
+void flush_output_stdout(void)
 {
-	fputs(output_buffer, stdout);
-	fflush(stdout);
+	FILE *filep;
+
+	if (outf == stderr)
+		filep = stdout;
+	else
+		filep = outf;
+
+	fputs(output_buffer, filep);
+	fflush(filep);
+
 	outp = output_buffer;
 }
-void flush_stderr()
+void flush_output_stderr(void)
 {
-	fputs(output_buffer, stderr);
+	fputs(output_buffer, outf);
+	fflush(outf);
 	outp = output_buffer;
 }
 void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
@@ -704,6 +766,9 @@ delta_package(struct pkg_data *new, struct pkg_data *old)
 	old->pc10 = new->pc10 - old->pc10;
 	old->pkg_temp_c = new->pkg_temp_c;
 
+	old->gfx_rc6_ms = new->gfx_rc6_ms - old->gfx_rc6_ms;
+	old->gfx_mhz = new->gfx_mhz;
+
 	DELTA_WRAP32(new->energy_pkg, old->energy_pkg);
 	DELTA_WRAP32(new->energy_cores, old->energy_cores);
 	DELTA_WRAP32(new->energy_gfx, old->energy_gfx);
@@ -745,9 +810,9 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 		} else {
 
 			if (!aperf_mperf_unstable) {
-				fprintf(stderr, "%s: APERF or MPERF went backwards *\n", progname);
-				fprintf(stderr, "* Frequency results do not cover entire interval *\n");
-				fprintf(stderr, "* fix this by running Linux-2.6.30 or later *\n");
+				fprintf(outf, "%s: APERF or MPERF went backwards *\n", progname);
+				fprintf(outf, "* Frequency results do not cover entire interval *\n");
+				fprintf(outf, "* fix this by running Linux-2.6.30 or later *\n");
 
 				aperf_mperf_unstable = 1;
 			}
@@ -782,7 +847,8 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 	}
 
 	if (old->mperf == 0) {
-		if (debug > 1) fprintf(stderr, "cpu%d MPERF 0!\n", old->cpu_id);
+		if (debug > 1)
+			fprintf(outf, "cpu%d MPERF 0!\n", old->cpu_id);
 		old->mperf = 1;	/* divide by 0 protection */
 	}
 
@@ -797,6 +863,9 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 	old->extra_msr32 = new->extra_msr32;
 	old->extra_msr64 = new->extra_msr64;
 
+	if (do_irq)
+		old->irq_count = new->irq_count - old->irq_count;
+
 	if (do_smi)
 		old->smi_count = new->smi_count - old->smi_count;
 }
@@ -826,10 +895,12 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	t->mperf = 0;
 	t->c1 = 0;
 
-	t->smi_count = 0;
 	t->extra_delta32 = 0;
 	t->extra_delta64 = 0;
 
+	t->irq_count = 0;
+	t->smi_count = 0;
+
 	/* tells format_counters to dump all fields from this set */
 	t->flags = CPU_IS_FIRST_THREAD_IN_CORE | CPU_IS_FIRST_CORE_IN_PACKAGE;
 
@@ -861,6 +932,9 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	p->rapl_pkg_perf_status = 0;
 	p->rapl_dram_perf_status = 0;
 	p->pkg_temp_c = 0;
+
+	p->gfx_rc6_ms = 0;
+	p->gfx_mhz = 0;
 }
 int sum_counters(struct thread_data *t, struct core_data *c,
 	struct pkg_data *p)
@@ -873,6 +947,9 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 	average.threads.extra_delta32 += t->extra_delta32;
 	average.threads.extra_delta64 += t->extra_delta64;
 
+	average.threads.irq_count += t->irq_count;
+	average.threads.smi_count += t->smi_count;
+
 	/* sum per-core values only for 1st thread in core */
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		return 0;
@@ -910,6 +987,9 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 	average.packages.energy_cores += p->energy_cores;
 	average.packages.energy_gfx += p->energy_gfx;
 
+	average.packages.gfx_rc6_ms = p->gfx_rc6_ms;
+	average.packages.gfx_mhz = p->gfx_mhz;
+
 	average.packages.pkg_temp_c = MAX(average.packages.pkg_temp_c, p->pkg_temp_c);
 
 	average.packages.rapl_pkg_perf_status += p->rapl_pkg_perf_status;
@@ -970,7 +1050,6 @@ static unsigned long long rdtsc(void)
 	return low | ((unsigned long long)high) << 32;
 }
 
-
 /*
  * get_counters(...)
  * migrate to cpu
@@ -980,23 +1059,74 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 {
 	int cpu = t->cpu_id;
 	unsigned long long msr;
+	int aperf_mperf_retry_count = 0;
 
 	if (cpu_migrate(cpu)) {
-		fprintf(stderr, "Could not migrate to CPU %d\n", cpu);
+		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
+retry:
 	t->tsc = rdtsc();	/* we are running on local CPU of interest */
 
 	if (has_aperf) {
+		unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time;
+
+		/*
+		 * The TSC, APERF and MPERF must be read together for
+		 * APERF/MPERF and MPERF/TSC to give accurate results.
+		 *
+		 * Unfortunately, APERF and MPERF are read by
+		 * individual system call, so delays may occur
+		 * between them.  If the time to read them
+		 * varies by a large amount, we re-read them.
+		 */
+
+		/*
+		 * This initial dummy APERF read has been seen to
+		 * reduce jitter in the subsequent reads.
+		 */
+
+		if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
+			return -3;
+
+		t->tsc = rdtsc();	/* re-read close to APERF */
+
+		tsc_before = t->tsc;
+
 		if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
 			return -3;
+
+		tsc_between = rdtsc();
+
 		if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf))
 			return -4;
+
+		tsc_after = rdtsc();
+
+		aperf_time = tsc_between - tsc_before;
+		mperf_time = tsc_after - tsc_between;
+
+		/*
+		 * If the system call latency to read APERF and MPERF
+		 * differ by more than 2x, then try again.
+		 */
+		if ((aperf_time > (2 * mperf_time)) || (mperf_time > (2 * aperf_time))) {
+			aperf_mperf_retry_count++;
+			if (aperf_mperf_retry_count < 5)
+				goto retry;
+			else
+				warnx("cpu%d jitter %lld %lld",
+					cpu, aperf_time, mperf_time);
+		}
+		aperf_mperf_retry_count = 0;
+
 		t->aperf = t->aperf * aperf_mperf_multiplier;
 		t->mperf = t->mperf * aperf_mperf_multiplier;
 	}
 
+	if (do_irq)
+		t->irq_count = irqs_per_cpu[cpu];
 	if (do_smi) {
 		if (get_msr(cpu, MSR_SMI_COUNT, &msr))
 			return -5;
@@ -1124,6 +1254,13 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			return -17;
 		p->pkg_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F);
 	}
+
+	if (do_gfx_rc6_ms)
+		p->gfx_rc6_ms = gfx_cur_rc6_ms;
+
+	if (do_gfx_mhz)
+		p->gfx_mhz = gfx_cur_mhz;
+
 	return 0;
 }
 
@@ -1175,18 +1312,18 @@ dump_nhm_platform_info(void)
 
 	get_msr(base_cpu, MSR_PLATFORM_INFO, &msr);
 
-	fprintf(stderr, "cpu%d: MSR_PLATFORM_INFO: 0x%08llx\n", base_cpu, msr);
+	fprintf(outf, "cpu%d: MSR_PLATFORM_INFO: 0x%08llx\n", base_cpu, msr);
 
 	ratio = (msr >> 40) & 0xFF;
-	fprintf(stderr, "%d * %.0f = %.0f MHz max efficiency frequency\n",
+	fprintf(outf, "%d * %.0f = %.0f MHz max efficiency frequency\n",
 		ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 8) & 0xFF;
-	fprintf(stderr, "%d * %.0f = %.0f MHz base frequency\n",
+	fprintf(outf, "%d * %.0f = %.0f MHz base frequency\n",
 		ratio, bclk, ratio * bclk);
 
 	get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr);
-	fprintf(stderr, "cpu%d: MSR_IA32_POWER_CTL: 0x%08llx (C1E auto-promotion: %sabled)\n",
+	fprintf(outf, "cpu%d: MSR_IA32_POWER_CTL: 0x%08llx (C1E auto-promotion: %sabled)\n",
 		base_cpu, msr, msr & 0x2 ? "EN" : "DIS");
 
 	return;
@@ -1200,16 +1337,16 @@ dump_hsw_turbo_ratio_limits(void)
 
 	get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT2, &msr);
 
-	fprintf(stderr, "cpu%d: MSR_TURBO_RATIO_LIMIT2: 0x%08llx\n", base_cpu, msr);
+	fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT2: 0x%08llx\n", base_cpu, msr);
 
 	ratio = (msr >> 8) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 18 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 18 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 0) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 17 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 17 active cores\n",
 			ratio, bclk, ratio * bclk);
 	return;
 }
@@ -1222,46 +1359,46 @@ dump_ivt_turbo_ratio_limits(void)
 
 	get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT1, &msr);
 
-	fprintf(stderr, "cpu%d: MSR_TURBO_RATIO_LIMIT1: 0x%08llx\n", base_cpu, msr);
+	fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT1: 0x%08llx\n", base_cpu, msr);
 
 	ratio = (msr >> 56) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 16 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 16 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 48) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 15 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 15 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 40) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 14 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 14 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 32) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 13 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 13 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 24) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 12 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 12 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 16) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 11 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 11 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 8) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 10 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 10 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 0) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 9 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 9 active cores\n",
 			ratio, bclk, ratio * bclk);
 	return;
 }
@@ -1274,46 +1411,46 @@ dump_nhm_turbo_ratio_limits(void)
 
 	get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT, &msr);
 
-	fprintf(stderr, "cpu%d: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n", base_cpu, msr);
+	fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n", base_cpu, msr);
 
 	ratio = (msr >> 56) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 8 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 8 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 48) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 7 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 7 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 40) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 6 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 6 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 32) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 5 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 5 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 24) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 4 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 4 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 16) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 3 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 3 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 8) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 2 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 2 active cores\n",
 			ratio, bclk, ratio * bclk);
 
 	ratio = (msr >> 0) & 0xFF;
 	if (ratio)
-		fprintf(stderr, "%d * %.0f = %.0f MHz max turbo 1 active cores\n",
+		fprintf(outf, "%d * %.0f = %.0f MHz max turbo 1 active cores\n",
 			ratio, bclk, ratio * bclk);
 	return;
 }
@@ -1321,21 +1458,23 @@ dump_nhm_turbo_ratio_limits(void)
 static void
 dump_knl_turbo_ratio_limits(void)
 {
-	int cores;
-	unsigned int ratio;
+	const unsigned int buckets_no = 7;
+
 	unsigned long long msr;
-	int delta_cores;
-	int delta_ratio;
-	int i;
+	int delta_cores, delta_ratio;
+	int i, b_nr;
+	unsigned int cores[buckets_no];
+	unsigned int ratio[buckets_no];
 
 	get_msr(base_cpu, MSR_NHM_TURBO_RATIO_LIMIT, &msr);
 
-	fprintf(stderr, "cpu%d: MSR_NHM_TURBO_RATIO_LIMIT: 0x%08llx\n",
+	fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n",
 		base_cpu, msr);
 
 	/**
 	 * Turbo encoding in KNL is as follows:
-	 * [7:0] -- Base value of number of active cores of bucket 1.
+	 * [0] -- Reserved
+	 * [7:1] -- Base value of number of active cores of bucket 1.
 	 * [15:8] -- Base value of freq ratio of bucket 1.
 	 * [20:16] -- +ve delta of number of active cores of bucket 2.
 	 * i.e. active cores of bucket 2 =
@@ -1354,29 +1493,25 @@ dump_knl_turbo_ratio_limits(void)
 	 * [60:56]-- +ve delta of number of active cores of bucket 7.
 	 * [63:61]-- -ve delta of freq ratio of bucket 7.
 	 */
-	cores = msr & 0xFF;
-	ratio = (msr >> 8) && 0xFF;
-	if (ratio > 0)
-		fprintf(stderr,
-			"%d * %.0f = %.0f MHz max turbo %d active cores\n",
-			ratio, bclk, ratio * bclk, cores);
-
-	for (i = 16; i < 64; i = i + 8) {
+
+	b_nr = 0;
+	cores[b_nr] = (msr & 0xFF) >> 1;
+	ratio[b_nr] = (msr >> 8) & 0xFF;
+
+	for (i = 16; i < 64; i += 8) {
 		delta_cores = (msr >> i) & 0x1F;
-		delta_ratio = (msr >> (i + 5)) && 0x7;
-		if (!delta_cores || !delta_ratio)
-			return;
-		cores = cores + delta_cores;
-		ratio = ratio - delta_ratio;
-
-		/** -ve ratios will make successive ratio calculations
-		 * negative. Hence return instead of carrying on.
-		 */
-		if (ratio > 0)
-			fprintf(stderr,
-				"%d * %.0f = %.0f MHz max turbo %d active cores\n",
-				ratio, bclk, ratio * bclk, cores);
+		delta_ratio = (msr >> (i + 5)) & 0x7;
+
+		cores[b_nr + 1] = cores[b_nr] + delta_cores;
+		ratio[b_nr + 1] = ratio[b_nr] - delta_ratio;
+		b_nr++;
 	}
+
+	for (i = buckets_no - 1; i >= 0; i--)
+		if (i > 0 ? ratio[i] != ratio[i - 1] : 1)
+			fprintf(outf,
+				"%d * %.0f = %.0f MHz max turbo %d active cores\n",
+				ratio[i], bclk, ratio[i] * bclk, cores[i]);
 }
 
 static void
@@ -1389,15 +1524,15 @@ dump_nhm_cst_cfg(void)
 #define SNB_C1_AUTO_UNDEMOTE              (1UL << 27)
 #define SNB_C3_AUTO_UNDEMOTE              (1UL << 28)
 
-	fprintf(stderr, "cpu%d: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x%08llx", base_cpu, msr);
+	fprintf(outf, "cpu%d: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x%08llx", base_cpu, msr);
 
-	fprintf(stderr, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: %s)\n",
+	fprintf(outf, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: %s)\n",
 		(msr & SNB_C3_AUTO_UNDEMOTE) ? "UNdemote-C3, " : "",
 		(msr & SNB_C1_AUTO_UNDEMOTE) ? "UNdemote-C1, " : "",
 		(msr & NHM_C3_AUTO_DEMOTE) ? "demote-C3, " : "",
 		(msr & NHM_C1_AUTO_DEMOTE) ? "demote-C1, " : "",
 		(msr & (1 << 15)) ? "" : "UN",
-		(unsigned int)msr & 7,
+		(unsigned int)msr & 0xF,
 		pkg_cstate_limit_strings[pkg_cstate_limit]);
 	return;
 }
@@ -1408,48 +1543,59 @@ dump_config_tdp(void)
 	unsigned long long msr;
 
 	get_msr(base_cpu, MSR_CONFIG_TDP_NOMINAL, &msr);
-	fprintf(stderr, "cpu%d: MSR_CONFIG_TDP_NOMINAL: 0x%08llx", base_cpu, msr);
-	fprintf(stderr, " (base_ratio=%d)\n", (unsigned int)msr & 0xEF);
+	fprintf(outf, "cpu%d: MSR_CONFIG_TDP_NOMINAL: 0x%08llx", base_cpu, msr);
+	fprintf(outf, " (base_ratio=%d)\n", (unsigned int)msr & 0xFF);
 
 	get_msr(base_cpu, MSR_CONFIG_TDP_LEVEL_1, &msr);
-	fprintf(stderr, "cpu%d: MSR_CONFIG_TDP_LEVEL_1: 0x%08llx (", base_cpu, msr);
+	fprintf(outf, "cpu%d: MSR_CONFIG_TDP_LEVEL_1: 0x%08llx (", base_cpu, msr);
 	if (msr) {
-		fprintf(stderr, "PKG_MIN_PWR_LVL1=%d ", (unsigned int)(msr >> 48) & 0xEFFF);
-		fprintf(stderr, "PKG_MAX_PWR_LVL1=%d ", (unsigned int)(msr >> 32) & 0xEFFF);
-		fprintf(stderr, "LVL1_RATIO=%d ", (unsigned int)(msr >> 16) & 0xEF);
-		fprintf(stderr, "PKG_TDP_LVL1=%d", (unsigned int)(msr) & 0xEFFF);
+		fprintf(outf, "PKG_MIN_PWR_LVL1=%d ", (unsigned int)(msr >> 48) & 0x7FFF);
+		fprintf(outf, "PKG_MAX_PWR_LVL1=%d ", (unsigned int)(msr >> 32) & 0x7FFF);
+		fprintf(outf, "LVL1_RATIO=%d ", (unsigned int)(msr >> 16) & 0xFF);
+		fprintf(outf, "PKG_TDP_LVL1=%d", (unsigned int)(msr) & 0x7FFF);
 	}
-	fprintf(stderr, ")\n");
+	fprintf(outf, ")\n");
 
 	get_msr(base_cpu, MSR_CONFIG_TDP_LEVEL_2, &msr);
-	fprintf(stderr, "cpu%d: MSR_CONFIG_TDP_LEVEL_2: 0x%08llx (", base_cpu, msr);
+	fprintf(outf, "cpu%d: MSR_CONFIG_TDP_LEVEL_2: 0x%08llx (", base_cpu, msr);
 	if (msr) {
-		fprintf(stderr, "PKG_MIN_PWR_LVL2=%d ", (unsigned int)(msr >> 48) & 0xEFFF);
-		fprintf(stderr, "PKG_MAX_PWR_LVL2=%d ", (unsigned int)(msr >> 32) & 0xEFFF);
-		fprintf(stderr, "LVL2_RATIO=%d ", (unsigned int)(msr >> 16) & 0xEF);
-		fprintf(stderr, "PKG_TDP_LVL2=%d", (unsigned int)(msr) & 0xEFFF);
+		fprintf(outf, "PKG_MIN_PWR_LVL2=%d ", (unsigned int)(msr >> 48) & 0x7FFF);
+		fprintf(outf, "PKG_MAX_PWR_LVL2=%d ", (unsigned int)(msr >> 32) & 0x7FFF);
+		fprintf(outf, "LVL2_RATIO=%d ", (unsigned int)(msr >> 16) & 0xFF);
+		fprintf(outf, "PKG_TDP_LVL2=%d", (unsigned int)(msr) & 0x7FFF);
 	}
-	fprintf(stderr, ")\n");
+	fprintf(outf, ")\n");
 
 	get_msr(base_cpu, MSR_CONFIG_TDP_CONTROL, &msr);
-	fprintf(stderr, "cpu%d: MSR_CONFIG_TDP_CONTROL: 0x%08llx (", base_cpu, msr);
+	fprintf(outf, "cpu%d: MSR_CONFIG_TDP_CONTROL: 0x%08llx (", base_cpu, msr);
 	if ((msr) & 0x3)
-		fprintf(stderr, "TDP_LEVEL=%d ", (unsigned int)(msr) & 0x3);
-	fprintf(stderr, " lock=%d", (unsigned int)(msr >> 31) & 1);
-	fprintf(stderr, ")\n");
-	
+		fprintf(outf, "TDP_LEVEL=%d ", (unsigned int)(msr) & 0x3);
+	fprintf(outf, " lock=%d", (unsigned int)(msr >> 31) & 1);
+	fprintf(outf, ")\n");
+
 	get_msr(base_cpu, MSR_TURBO_ACTIVATION_RATIO, &msr);
-	fprintf(stderr, "cpu%d: MSR_TURBO_ACTIVATION_RATIO: 0x%08llx (", base_cpu, msr);
-	fprintf(stderr, "MAX_NON_TURBO_RATIO=%d", (unsigned int)(msr) & 0x7F);
-	fprintf(stderr, " lock=%d", (unsigned int)(msr >> 31) & 1);
-	fprintf(stderr, ")\n");
+	fprintf(outf, "cpu%d: MSR_TURBO_ACTIVATION_RATIO: 0x%08llx (", base_cpu, msr);
+	fprintf(outf, "MAX_NON_TURBO_RATIO=%d", (unsigned int)(msr) & 0xFF);
+	fprintf(outf, " lock=%d", (unsigned int)(msr >> 31) & 1);
+	fprintf(outf, ")\n");
+}
+void free_fd_percpu(void)
+{
+	int i;
+
+	for (i = 0; i < topo.max_cpu_num; ++i) {
+		if (fd_percpu[i] != 0)
+			close(fd_percpu[i]);
+	}
+
+	free(fd_percpu);
 }
 
 void free_all_buffers(void)
 {
 	CPU_FREE(cpu_present_set);
 	cpu_present_set = NULL;
-	cpu_present_set = 0;
+	cpu_present_setsize = 0;
 
 	CPU_FREE(cpu_affinity_set);
 	cpu_affinity_set = NULL;
@@ -1474,6 +1620,11 @@ void free_all_buffers(void)
 	free(output_buffer);
 	output_buffer = NULL;
 	outp = NULL;
+
+	free_fd_percpu();
+
+	free(irq_column_2_cpu);
+	free(irqs_per_cpu);
 }
 
 /*
@@ -1481,7 +1632,7 @@ void free_all_buffers(void)
  */
 FILE *fopen_or_die(const char *path, const char *mode)
 {
-	FILE *filep = fopen(path, "r");
+	FILE *filep = fopen(path, mode);
 	if (!filep)
 		err(1, "%s: open failed", path);
 	return filep;
@@ -1696,6 +1847,136 @@ int mark_cpu_present(int cpu)
 	return 0;
 }
 
+/*
+ * snapshot_proc_interrupts()
+ *
+ * read and record summary of /proc/interrupts
+ *
+ * return 1 if config change requires a restart, else return 0
+ */
+int snapshot_proc_interrupts(void)
+{
+	static FILE *fp;
+	int column, retval;
+
+	if (fp == NULL)
+		fp = fopen_or_die("/proc/interrupts", "r");
+	else
+		rewind(fp);
+
+	/* read 1st line of /proc/interrupts to get cpu* name for each column */
+	for (column = 0; column < topo.num_cpus; ++column) {
+		int cpu_number;
+
+		retval = fscanf(fp, " CPU%d", &cpu_number);
+		if (retval != 1)
+			break;
+
+		if (cpu_number > topo.max_cpu_num) {
+			warn("/proc/interrupts: cpu%d: > %d", cpu_number, topo.max_cpu_num);
+			return 1;
+		}
+
+		irq_column_2_cpu[column] = cpu_number;
+		irqs_per_cpu[cpu_number] = 0;
+	}
+
+	/* read /proc/interrupt count lines and sum up irqs per cpu */
+	while (1) {
+		int column;
+		char buf[64];
+
+		retval = fscanf(fp, " %s:", buf);	/* flush irq# "N:" */
+		if (retval != 1)
+			break;
+
+		/* read the count per cpu */
+		for (column = 0; column < topo.num_cpus; ++column) {
+
+			int cpu_number, irq_count;
+
+			retval = fscanf(fp, " %d", &irq_count);
+			if (retval != 1)
+				break;
+
+			cpu_number = irq_column_2_cpu[column];
+			irqs_per_cpu[cpu_number] += irq_count;
+
+		}
+
+		while (getc(fp) != '\n')
+			;	/* flush interrupt description */
+
+	}
+	return 0;
+}
+/*
+ * snapshot_gfx_rc6_ms()
+ *
+ * record snapshot of
+ * /sys/class/drm/card0/power/rc6_residency_ms
+ *
+ * return 1 if config change requires a restart, else return 0
+ */
+int snapshot_gfx_rc6_ms(void)
+{
+	FILE *fp;
+	int retval;
+
+	fp = fopen_or_die("/sys/class/drm/card0/power/rc6_residency_ms", "r");
+
+	retval = fscanf(fp, "%lld", &gfx_cur_rc6_ms);
+	if (retval != 1)
+		err(1, "GFX rc6");
+
+	fclose(fp);
+
+	return 0;
+}
+/*
+ * snapshot_gfx_mhz()
+ *
+ * record snapshot of
+ * /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz
+ *
+ * return 1 if config change requires a restart, else return 0
+ */
+int snapshot_gfx_mhz(void)
+{
+	static FILE *fp;
+	int retval;
+
+	if (fp == NULL)
+		fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r");
+	else
+		rewind(fp);
+
+	retval = fscanf(fp, "%d", &gfx_cur_mhz);
+	if (retval != 1)
+		err(1, "GFX MHz");
+
+	return 0;
+}
+
+/*
+ * snapshot /proc and /sys files
+ *
+ * return 1 if configuration restart needed, else return 0
+ */
+int snapshot_proc_sysfs_files(void)
+{
+	if (snapshot_proc_interrupts())
+		return 1;
+
+	if (do_gfx_rc6_ms)
+		snapshot_gfx_rc6_ms();
+
+	if (do_gfx_mhz)
+		snapshot_gfx_mhz();
+
+	return 0;
+}
+
 void turbostat_loop()
 {
 	int retval;
@@ -1704,6 +1985,7 @@ void turbostat_loop()
 restart:
 	restarted++;
 
+	snapshot_proc_sysfs_files();
 	retval = for_all_cpus(get_counters, EVEN_COUNTERS);
 	if (retval < -1) {
 		exit(retval);
@@ -1722,7 +2004,9 @@ restart:
 			re_initialize();
 			goto restart;
 		}
-		sleep(interval_sec);
+		nanosleep(&interval_ts, NULL);
+		if (snapshot_proc_sysfs_files())
+			goto restart;
 		retval = for_all_cpus(get_counters, ODD_COUNTERS);
 		if (retval < -1) {
 			exit(retval);
@@ -1735,8 +2019,10 @@ restart:
 		for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS);
 		compute_average(EVEN_COUNTERS);
 		format_all_counters(EVEN_COUNTERS);
-		flush_stdout();
-		sleep(interval_sec);
+		flush_output_stdout();
+		nanosleep(&interval_ts, NULL);
+		if (snapshot_proc_sysfs_files())
+			goto restart;
 		retval = for_all_cpus(get_counters, EVEN_COUNTERS);
 		if (retval < -1) {
 			exit(retval);
@@ -1749,7 +2035,7 @@ restart:
 		for_all_cpus_2(delta_cpu, EVEN_COUNTERS, ODD_COUNTERS);
 		compute_average(ODD_COUNTERS);
 		format_all_counters(ODD_COUNTERS);
-		flush_stdout();
+		flush_output_stdout();
 	}
 }
 
@@ -1889,6 +2175,7 @@ int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model)
 	/* Nehalem compatible, but do not include turbo-ratio limit support */
 	case 0x2E:	/* Nehalem-EX Xeon - Beckton */
 	case 0x2F:	/* Westmere-EX Xeon - Eagleton */
+	case 0x57:	/* PHI - Knights Landing (different MSR definition) */
 		return 0;
 	default:
 		return 1;
@@ -1970,7 +2257,7 @@ int has_config_tdp(unsigned int family, unsigned int model)
 }
 
 static void
-dump_cstate_pstate_config_info(family, model)
+dump_cstate_pstate_config_info(unsigned int family, unsigned int model)
 {
 	if (!do_nhm_platform_info)
 		return;
@@ -2016,7 +2303,7 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		return 0;
 
 	if (cpu_migrate(cpu)) {
-		fprintf(stderr, "Could not migrate to CPU %d\n", cpu);
+		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
@@ -2037,7 +2324,98 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		epb_string = "custom";
 		break;
 	}
-	fprintf(stderr, "cpu%d: MSR_IA32_ENERGY_PERF_BIAS: 0x%08llx (%s)\n", cpu, msr, epb_string);
+	fprintf(outf, "cpu%d: MSR_IA32_ENERGY_PERF_BIAS: 0x%08llx (%s)\n", cpu, msr, epb_string);
+
+	return 0;
+}
+/*
+ * print_hwp()
+ * Decode the MSR_HWP_CAPABILITIES
+ */
+int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+	unsigned long long msr;
+	int cpu;
+
+	if (!has_hwp)
+		return 0;
+
+	cpu = t->cpu_id;
+
+	/* MSR_HWP_CAPABILITIES is per-package */
+	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
+		return 0;
+
+	if (cpu_migrate(cpu)) {
+		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+		return -1;
+	}
+
+	if (get_msr(cpu, MSR_PM_ENABLE, &msr))
+		return 0;
+
+	fprintf(outf, "cpu%d: MSR_PM_ENABLE: 0x%08llx (%sHWP)\n",
+		cpu, msr, (msr & (1 << 0)) ? "" : "No-");
+
+	/* MSR_PM_ENABLE[1] == 1 if HWP is enabled and MSRs visible */
+	if ((msr & (1 << 0)) == 0)
+		return 0;
+
+	if (get_msr(cpu, MSR_HWP_CAPABILITIES, &msr))
+		return 0;
+
+	fprintf(outf, "cpu%d: MSR_HWP_CAPABILITIES: 0x%08llx "
+			"(high 0x%x guar 0x%x eff 0x%x low 0x%x)\n",
+			cpu, msr,
+			(unsigned int)HWP_HIGHEST_PERF(msr),
+			(unsigned int)HWP_GUARANTEED_PERF(msr),
+			(unsigned int)HWP_MOSTEFFICIENT_PERF(msr),
+			(unsigned int)HWP_LOWEST_PERF(msr));
+
+	if (get_msr(cpu, MSR_HWP_REQUEST, &msr))
+		return 0;
+
+	fprintf(outf, "cpu%d: MSR_HWP_REQUEST: 0x%08llx "
+			"(min 0x%x max 0x%x des 0x%x epp 0x%x window 0x%x pkg 0x%x)\n",
+			cpu, msr,
+			(unsigned int)(((msr) >> 0) & 0xff),
+			(unsigned int)(((msr) >> 8) & 0xff),
+			(unsigned int)(((msr) >> 16) & 0xff),
+			(unsigned int)(((msr) >> 24) & 0xff),
+			(unsigned int)(((msr) >> 32) & 0xff3),
+			(unsigned int)(((msr) >> 42) & 0x1));
+
+	if (has_hwp_pkg) {
+		if (get_msr(cpu, MSR_HWP_REQUEST_PKG, &msr))
+			return 0;
+
+		fprintf(outf, "cpu%d: MSR_HWP_REQUEST_PKG: 0x%08llx "
+			"(min 0x%x max 0x%x des 0x%x epp 0x%x window 0x%x)\n",
+			cpu, msr,
+			(unsigned int)(((msr) >> 0) & 0xff),
+			(unsigned int)(((msr) >> 8) & 0xff),
+			(unsigned int)(((msr) >> 16) & 0xff),
+			(unsigned int)(((msr) >> 24) & 0xff),
+			(unsigned int)(((msr) >> 32) & 0xff3));
+	}
+	if (has_hwp_notify) {
+		if (get_msr(cpu, MSR_HWP_INTERRUPT, &msr))
+			return 0;
+
+		fprintf(outf, "cpu%d: MSR_HWP_INTERRUPT: 0x%08llx "
+			"(%s_Guaranteed_Perf_Change, %s_Excursion_Min)\n",
+			cpu, msr,
+			((msr) & 0x1) ? "EN" : "Dis",
+			((msr) & 0x2) ? "EN" : "Dis");
+	}
+	if (get_msr(cpu, MSR_HWP_STATUS, &msr))
+		return 0;
+
+	fprintf(outf, "cpu%d: MSR_HWP_STATUS: 0x%08llx "
+			"(%sGuaranteed_Perf_Change, %sExcursion_Min)\n",
+			cpu, msr,
+			((msr) & 0x1) ? "" : "No-",
+			((msr) & 0x2) ? "" : "No-");
 
 	return 0;
 }
@@ -2057,14 +2435,14 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 		return 0;
 
 	if (cpu_migrate(cpu)) {
-		fprintf(stderr, "Could not migrate to CPU %d\n", cpu);
+		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
 	if (do_core_perf_limit_reasons) {
 		get_msr(cpu, MSR_CORE_PERF_LIMIT_REASONS, &msr);
-		fprintf(stderr, "cpu%d: MSR_CORE_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
-		fprintf(stderr, " (Active: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)",
+		fprintf(outf, "cpu%d: MSR_CORE_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
+		fprintf(outf, " (Active: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)",
 			(msr & 1 << 15) ? "bit15, " : "",
 			(msr & 1 << 14) ? "bit14, " : "",
 			(msr & 1 << 13) ? "Transitions, " : "",
@@ -2079,7 +2457,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 			(msr & 1 << 2) ? "bit2, " : "",
 			(msr & 1 << 1) ? "ThermStatus, " : "",
 			(msr & 1 << 0) ? "PROCHOT, " : "");
-		fprintf(stderr, " (Logged: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)\n",
+		fprintf(outf, " (Logged: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)\n",
 			(msr & 1 << 31) ? "bit31, " : "",
 			(msr & 1 << 30) ? "bit30, " : "",
 			(msr & 1 << 29) ? "Transitions, " : "",
@@ -2098,8 +2476,8 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 	}
 	if (do_gfx_perf_limit_reasons) {
 		get_msr(cpu, MSR_GFX_PERF_LIMIT_REASONS, &msr);
-		fprintf(stderr, "cpu%d: MSR_GFX_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
-		fprintf(stderr, " (Active: %s%s%s%s%s%s%s%s)",
+		fprintf(outf, "cpu%d: MSR_GFX_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
+		fprintf(outf, " (Active: %s%s%s%s%s%s%s%s)",
 			(msr & 1 << 0) ? "PROCHOT, " : "",
 			(msr & 1 << 1) ? "ThermStatus, " : "",
 			(msr & 1 << 4) ? "Graphics, " : "",
@@ -2108,7 +2486,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 			(msr & 1 << 9) ? "GFXPwr, " : "",
 			(msr & 1 << 10) ? "PkgPwrL1, " : "",
 			(msr & 1 << 11) ? "PkgPwrL2, " : "");
-		fprintf(stderr, " (Logged: %s%s%s%s%s%s%s%s)\n",
+		fprintf(outf, " (Logged: %s%s%s%s%s%s%s%s)\n",
 			(msr & 1 << 16) ? "PROCHOT, " : "",
 			(msr & 1 << 17) ? "ThermStatus, " : "",
 			(msr & 1 << 20) ? "Graphics, " : "",
@@ -2120,15 +2498,15 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 	}
 	if (do_ring_perf_limit_reasons) {
 		get_msr(cpu, MSR_RING_PERF_LIMIT_REASONS, &msr);
-		fprintf(stderr, "cpu%d: MSR_RING_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
-		fprintf(stderr, " (Active: %s%s%s%s%s%s)",
+		fprintf(outf, "cpu%d: MSR_RING_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr);
+		fprintf(outf, " (Active: %s%s%s%s%s%s)",
 			(msr & 1 << 0) ? "PROCHOT, " : "",
 			(msr & 1 << 1) ? "ThermStatus, " : "",
 			(msr & 1 << 6) ? "VR-Therm, " : "",
 			(msr & 1 << 8) ? "Amps, " : "",
 			(msr & 1 << 10) ? "PkgPwrL1, " : "",
 			(msr & 1 << 11) ? "PkgPwrL2, " : "");
-		fprintf(stderr, " (Logged: %s%s%s%s%s%s)\n",
+		fprintf(outf, " (Logged: %s%s%s%s%s%s)\n",
 			(msr & 1 << 16) ? "PROCHOT, " : "",
 			(msr & 1 << 17) ? "ThermStatus, " : "",
 			(msr & 1 << 22) ? "VR-Therm, " : "",
@@ -2142,7 +2520,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 #define	RAPL_POWER_GRANULARITY	0x7FFF	/* 15 bit power granularity */
 #define	RAPL_TIME_GRANULARITY	0x3F /* 6 bit time granularity */
 
-double get_tdp(model)
+double get_tdp(unsigned int model)
 {
 	unsigned long long msr;
 
@@ -2251,12 +2629,12 @@ void rapl_probe(unsigned int family, unsigned int model)
 
 	rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
 	if (debug)
-		fprintf(stderr, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
+		fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
 
 	return;
 }
 
-void perf_limit_reasons_probe(family, model)
+void perf_limit_reasons_probe(unsigned int family, unsigned int model)
 {
 	if (!genuine_intel)
 		return;
@@ -2293,7 +2671,7 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
 		return 0;
 
 	if (cpu_migrate(cpu)) {
-		fprintf(stderr, "Could not migrate to CPU %d\n", cpu);
+		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
@@ -2302,7 +2680,7 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
 			return 0;
 
 		dts = (msr >> 16) & 0x7F;
-		fprintf(stderr, "cpu%d: MSR_IA32_PACKAGE_THERM_STATUS: 0x%08llx (%d C)\n",
+		fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_STATUS: 0x%08llx (%d C)\n",
 			cpu, msr, tcc_activation_temp - dts);
 
 #ifdef	THERM_DEBUG
@@ -2311,7 +2689,7 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
 
 		dts = (msr >> 16) & 0x7F;
 		dts2 = (msr >> 8) & 0x7F;
-		fprintf(stderr, "cpu%d: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
+		fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
 			cpu, msr, tcc_activation_temp - dts, tcc_activation_temp - dts2);
 #endif
 	}
@@ -2325,7 +2703,7 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
 
 		dts = (msr >> 16) & 0x7F;
 		resolution = (msr >> 27) & 0xF;
-		fprintf(stderr, "cpu%d: MSR_IA32_THERM_STATUS: 0x%08llx (%d C +/- %d)\n",
+		fprintf(outf, "cpu%d: MSR_IA32_THERM_STATUS: 0x%08llx (%d C +/- %d)\n",
 			cpu, msr, tcc_activation_temp - dts, resolution);
 
 #ifdef THERM_DEBUG
@@ -2334,17 +2712,17 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
 
 		dts = (msr >> 16) & 0x7F;
 		dts2 = (msr >> 8) & 0x7F;
-		fprintf(stderr, "cpu%d: MSR_IA32_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
+		fprintf(outf, "cpu%d: MSR_IA32_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
 			cpu, msr, tcc_activation_temp - dts, tcc_activation_temp - dts2);
 #endif
 	}
 
 	return 0;
 }
-	
+
 void print_power_limit_msr(int cpu, unsigned long long msr, char *label)
 {
-	fprintf(stderr, "cpu%d: %s: %sabled (%f Watts, %f sec, clamp %sabled)\n",
+	fprintf(outf, "cpu%d: %s: %sabled (%f Watts, %f sec, clamp %sabled)\n",
 		cpu, label,
 		((msr >> 15) & 1) ? "EN" : "DIS",
 		((msr >> 0) & 0x7FFF) * rapl_power_units,
@@ -2368,7 +2746,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 
 	cpu = t->cpu_id;
 	if (cpu_migrate(cpu)) {
-		fprintf(stderr, "Could not migrate to CPU %d\n", cpu);
+		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
@@ -2376,7 +2754,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		return -1;
 
 	if (debug) {
-		fprintf(stderr, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx "
+		fprintf(outf, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx "
 			"(%f Watts, %f Joules, %f sec.)\n", cpu, msr,
 			rapl_power_units, rapl_energy_units, rapl_time_units);
 	}
@@ -2386,7 +2764,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
                 	return -5;
 
 
-		fprintf(stderr, "cpu%d: MSR_PKG_POWER_INFO: 0x%08llx (%.0f W TDP, RAPL %.0f - %.0f W, %f sec.)\n",
+		fprintf(outf, "cpu%d: MSR_PKG_POWER_INFO: 0x%08llx (%.0f W TDP, RAPL %.0f - %.0f W, %f sec.)\n",
 			cpu, msr,
 			((msr >>  0) & RAPL_POWER_GRANULARITY) * rapl_power_units,
 			((msr >> 16) & RAPL_POWER_GRANULARITY) * rapl_power_units,
@@ -2399,11 +2777,11 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		if (get_msr(cpu, MSR_PKG_POWER_LIMIT, &msr))
 			return -9;
 
-		fprintf(stderr, "cpu%d: MSR_PKG_POWER_LIMIT: 0x%08llx (%slocked)\n",
+		fprintf(outf, "cpu%d: MSR_PKG_POWER_LIMIT: 0x%08llx (%slocked)\n",
 			cpu, msr, (msr >> 63) & 1 ? "": "UN");
 
 		print_power_limit_msr(cpu, msr, "PKG Limit #1");
-		fprintf(stderr, "cpu%d: PKG Limit #2: %sabled (%f Watts, %f* sec, clamp %sabled)\n",
+		fprintf(outf, "cpu%d: PKG Limit #2: %sabled (%f Watts, %f* sec, clamp %sabled)\n",
 			cpu,
 			((msr >> 47) & 1) ? "EN" : "DIS",
 			((msr >> 32) & 0x7FFF) * rapl_power_units,
@@ -2415,7 +2793,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		if (get_msr(cpu, MSR_DRAM_POWER_INFO, &msr))
                 	return -6;
 
-		fprintf(stderr, "cpu%d: MSR_DRAM_POWER_INFO,: 0x%08llx (%.0f W TDP, RAPL %.0f - %.0f W, %f sec.)\n",
+		fprintf(outf, "cpu%d: MSR_DRAM_POWER_INFO,: 0x%08llx (%.0f W TDP, RAPL %.0f - %.0f W, %f sec.)\n",
 			cpu, msr,
 			((msr >>  0) & RAPL_POWER_GRANULARITY) * rapl_power_units,
 			((msr >> 16) & RAPL_POWER_GRANULARITY) * rapl_power_units,
@@ -2425,7 +2803,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	if (do_rapl & RAPL_DRAM) {
 		if (get_msr(cpu, MSR_DRAM_POWER_LIMIT, &msr))
 			return -9;
-		fprintf(stderr, "cpu%d: MSR_DRAM_POWER_LIMIT: 0x%08llx (%slocked)\n",
+		fprintf(outf, "cpu%d: MSR_DRAM_POWER_LIMIT: 0x%08llx (%slocked)\n",
 				cpu, msr, (msr >> 31) & 1 ? "": "UN");
 
 		print_power_limit_msr(cpu, msr, "DRAM Limit");
@@ -2435,7 +2813,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			if (get_msr(cpu, MSR_PP0_POLICY, &msr))
 				return -7;
 
-			fprintf(stderr, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF);
+			fprintf(outf, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF);
 		}
 	}
 	if (do_rapl & RAPL_CORES) {
@@ -2443,7 +2821,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 
 			if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr))
 				return -9;
-			fprintf(stderr, "cpu%d: MSR_PP0_POWER_LIMIT: 0x%08llx (%slocked)\n",
+			fprintf(outf, "cpu%d: MSR_PP0_POWER_LIMIT: 0x%08llx (%slocked)\n",
 					cpu, msr, (msr >> 31) & 1 ? "": "UN");
 			print_power_limit_msr(cpu, msr, "Cores Limit");
 		}
@@ -2453,11 +2831,11 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			if (get_msr(cpu, MSR_PP1_POLICY, &msr))
 				return -8;
 
-			fprintf(stderr, "cpu%d: MSR_PP1_POLICY: %lld\n", cpu, msr & 0xF);
+			fprintf(outf, "cpu%d: MSR_PP1_POLICY: %lld\n", cpu, msr & 0xF);
 
 			if (get_msr(cpu, MSR_PP1_POWER_LIMIT, &msr))
 				return -9;
-			fprintf(stderr, "cpu%d: MSR_PP1_POWER_LIMIT: 0x%08llx (%slocked)\n",
+			fprintf(outf, "cpu%d: MSR_PP1_POWER_LIMIT: 0x%08llx (%slocked)\n",
 					cpu, msr, (msr >> 31) & 1 ? "": "UN");
 			print_power_limit_msr(cpu, msr, "GFX Limit");
 		}
@@ -2583,23 +2961,23 @@ double slm_bclk(void)
 	double freq;
 
 	if (get_msr(base_cpu, MSR_FSB_FREQ, &msr))
-		fprintf(stderr, "SLM BCLK: unknown\n");
+		fprintf(outf, "SLM BCLK: unknown\n");
 
 	i = msr & 0xf;
 	if (i >= SLM_BCLK_FREQS) {
-		fprintf(stderr, "SLM BCLK[%d] invalid\n", i);
+		fprintf(outf, "SLM BCLK[%d] invalid\n", i);
 		msr = 3;
 	}
 	freq = slm_freq_table[i];
 
-	fprintf(stderr, "SLM BCLK: %.1f Mhz\n", freq);
+	fprintf(outf, "SLM BCLK: %.1f Mhz\n", freq);
 
 	return freq;
 }
 
 double discover_bclk(unsigned int family, unsigned int model)
 {
-	if (has_snb_msrs(family, model))
+	if (has_snb_msrs(family, model) || is_knl(family, model))
 		return 100.00;
 	else if (is_slm(family, model))
 		return slm_bclk();
@@ -2635,13 +3013,13 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
 
 	cpu = t->cpu_id;
 	if (cpu_migrate(cpu)) {
-		fprintf(stderr, "Could not migrate to CPU %d\n", cpu);
+		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
 	if (tcc_activation_temp_override != 0) {
 		tcc_activation_temp = tcc_activation_temp_override;
-		fprintf(stderr, "cpu%d: Using cmdline TCC Target (%d C)\n",
+		fprintf(outf, "cpu%d: Using cmdline TCC Target (%d C)\n",
 			cpu, tcc_activation_temp);
 		return 0;
 	}
@@ -2656,7 +3034,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
 	target_c_local = (msr >> 16) & 0xFF;
 
 	if (debug)
-		fprintf(stderr, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n",
+		fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n",
 			cpu, msr, target_c_local);
 
 	if (!target_c_local)
@@ -2668,37 +3046,93 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
 
 guess:
 	tcc_activation_temp = TJMAX_DEFAULT;
-	fprintf(stderr, "cpu%d: Guessing tjMax %d C, Please use -T to specify\n",
+	fprintf(outf, "cpu%d: Guessing tjMax %d C, Please use -T to specify\n",
 		cpu, tcc_activation_temp);
 
 	return 0;
 }
+
+void decode_feature_control_msr(void)
+{
+	unsigned long long msr;
+
+	if (!get_msr(base_cpu, MSR_IA32_FEATURE_CONTROL, &msr))
+		fprintf(outf, "cpu%d: MSR_IA32_FEATURE_CONTROL: 0x%08llx (%sLocked %s)\n",
+			base_cpu, msr,
+			msr & FEATURE_CONTROL_LOCKED ? "" : "UN-",
+			msr & (1 << 18) ? "SGX" : "");
+}
+
+void decode_misc_enable_msr(void)
+{
+	unsigned long long msr;
+
+	if (!get_msr(base_cpu, MSR_IA32_MISC_ENABLE, &msr))
+		fprintf(outf, "cpu%d: MSR_IA32_MISC_ENABLE: 0x%08llx (%s %s %s)\n",
+			base_cpu, msr,
+			msr & (1 << 3) ? "TCC" : "",
+			msr & (1 << 16) ? "EIST" : "",
+			msr & (1 << 18) ? "MONITOR" : "");
+}
+
+/*
+ * Decode MSR_MISC_PWR_MGMT
+ *
+ * Decode the bits according to the Nehalem documentation
+ * bit[0] seems to continue to have same meaning going forward
+ * bit[1] less so...
+ */
+void decode_misc_pwr_mgmt_msr(void)
+{
+	unsigned long long msr;
+
+	if (!do_nhm_platform_info)
+		return;
+
+	if (!get_msr(base_cpu, MSR_MISC_PWR_MGMT, &msr))
+		fprintf(outf, "cpu%d: MSR_MISC_PWR_MGMT: 0x%08llx (%sable-EIST_Coordination %sable-EPB)\n",
+			base_cpu, msr,
+			msr & (1 << 0) ? "DIS" : "EN",
+			msr & (1 << 1) ? "EN" : "DIS");
+}
+
 void process_cpuid()
 {
-	unsigned int eax, ebx, ecx, edx, max_level;
+	unsigned int eax, ebx, ecx, edx, max_level, max_extended_level;
 	unsigned int fms, family, model, stepping;
 
 	eax = ebx = ecx = edx = 0;
 
-	__get_cpuid(0, &max_level, &ebx, &ecx, &edx);
+	__cpuid(0, max_level, ebx, ecx, edx);
 
 	if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e)
 		genuine_intel = 1;
 
 	if (debug)
-		fprintf(stderr, "CPUID(0): %.4s%.4s%.4s ",
+		fprintf(outf, "CPUID(0): %.4s%.4s%.4s ",
 			(char *)&ebx, (char *)&edx, (char *)&ecx);
 
-	__get_cpuid(1, &fms, &ebx, &ecx, &edx);
+	__cpuid(1, fms, ebx, ecx, edx);
 	family = (fms >> 8) & 0xf;
 	model = (fms >> 4) & 0xf;
 	stepping = fms & 0xf;
 	if (family == 6 || family == 0xf)
 		model += ((fms >> 16) & 0xf) << 4;
 
-	if (debug)
-		fprintf(stderr, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n",
+	if (debug) {
+		fprintf(outf, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n",
 			max_level, family, model, stepping, family, model, stepping);
+		fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s\n",
+			ecx & (1 << 0) ? "SSE3" : "-",
+			ecx & (1 << 3) ? "MONITOR" : "-",
+			ecx & (1 << 6) ? "SMX" : "-",
+			ecx & (1 << 7) ? "EIST" : "-",
+			ecx & (1 << 8) ? "TM2" : "-",
+			edx & (1 << 4) ? "TSC" : "-",
+			edx & (1 << 5) ? "MSR" : "-",
+			edx & (1 << 22) ? "ACPI-TM" : "-",
+			edx & (1 << 29) ? "TM" : "-");
+	}
 
 	if (!(edx & (1 << 5)))
 		errx(1, "CPUID: no MSR");
@@ -2709,15 +3143,15 @@ void process_cpuid()
 	 * This check is valid for both Intel and AMD.
 	 */
 	ebx = ecx = edx = 0;
-	__get_cpuid(0x80000000, &max_level, &ebx, &ecx, &edx);
+	__cpuid(0x80000000, max_extended_level, ebx, ecx, edx);
 
-	if (max_level >= 0x80000007) {
+	if (max_extended_level >= 0x80000007) {
 
 		/*
 		 * Non-Stop TSC is advertised by CPUID.EAX=0x80000007: EDX.bit8
 		 * this check is valid for both Intel and AMD
 		 */
-		__get_cpuid(0x80000007, &eax, &ebx, &ecx, &edx);
+		__cpuid(0x80000007, eax, ebx, ecx, edx);
 		has_invariant_tsc = edx & (1 << 8);
 	}
 
@@ -2726,20 +3160,48 @@ void process_cpuid()
 	 * this check is valid for both Intel and AMD
 	 */
 
-	__get_cpuid(0x6, &eax, &ebx, &ecx, &edx);
+	__cpuid(0x6, eax, ebx, ecx, edx);
 	has_aperf = ecx & (1 << 0);
 	do_dts = eax & (1 << 0);
 	do_ptm = eax & (1 << 6);
+	has_hwp = eax & (1 << 7);
+	has_hwp_notify = eax & (1 << 8);
+	has_hwp_activity_window = eax & (1 << 9);
+	has_hwp_epp = eax & (1 << 10);
+	has_hwp_pkg = eax & (1 << 11);
 	has_epb = ecx & (1 << 3);
 
 	if (debug)
-		fprintf(stderr, "CPUID(6): %sAPERF, %sDTS, %sPTM, %sEPB\n",
-			has_aperf ? "" : "No ",
-			do_dts ? "" : "No ",
-			do_ptm ? "" : "No ",
-			has_epb ? "" : "No ");
+		fprintf(outf, "CPUID(6): %sAPERF, %sDTS, %sPTM, %sHWP, "
+			"%sHWPnotify, %sHWPwindow, %sHWPepp, %sHWPpkg, %sEPB\n",
+			has_aperf ? "" : "No-",
+			do_dts ? "" : "No-",
+			do_ptm ? "" : "No-",
+			has_hwp ? "" : "No-",
+			has_hwp_notify ? "" : "No-",
+			has_hwp_activity_window ? "" : "No-",
+			has_hwp_epp ? "" : "No-",
+			has_hwp_pkg ? "" : "No-",
+			has_epb ? "" : "No-");
+
+	if (debug)
+		decode_misc_enable_msr();
+
+	if (max_level >= 0x7) {
+		int has_sgx;
 
-	if (max_level > 0x15) {
+		ecx = 0;
+
+		__cpuid_count(0x7, 0, eax, ebx, ecx, edx);
+
+		has_sgx = ebx & (1 << 2);
+		fprintf(outf, "CPUID(7): %sSGX\n", has_sgx ? "" : "No-");
+
+		if (has_sgx)
+			decode_feature_control_msr();
+	}
+
+	if (max_level >= 0x15) {
 		unsigned int eax_crystal;
 		unsigned int ebx_tsc;
 
@@ -2747,12 +3209,12 @@ void process_cpuid()
 		 * CPUID 15H TSC/Crystal ratio, possibly Crystal Hz
 		 */
 		eax_crystal = ebx_tsc = crystal_hz = edx = 0;
-		__get_cpuid(0x15, &eax_crystal, &ebx_tsc, &crystal_hz, &edx);
+		__cpuid(0x15, eax_crystal, ebx_tsc, crystal_hz, edx);
 
 		if (ebx_tsc != 0) {
 
 			if (debug && (ebx != 0))
-				fprintf(stderr, "CPUID(0x15): eax_crystal: %d ebx_tsc: %d ecx_crystal_hz: %d\n",
+				fprintf(outf, "CPUID(0x15): eax_crystal: %d ebx_tsc: %d ecx_crystal_hz: %d\n",
 					eax_crystal, ebx_tsc, crystal_hz);
 
 			if (crystal_hz == 0)
@@ -2768,11 +3230,24 @@ void process_cpuid()
 			if (crystal_hz) {
 				tsc_hz =  (unsigned long long) crystal_hz * ebx_tsc / eax_crystal;
 				if (debug)
-					fprintf(stderr, "TSC: %lld MHz (%d Hz * %d / %d / 1000000)\n",
+					fprintf(outf, "TSC: %lld MHz (%d Hz * %d / %d / 1000000)\n",
 						tsc_hz / 1000000, crystal_hz, ebx_tsc,  eax_crystal);
 			}
 		}
 	}
+	if (max_level >= 0x16) {
+		unsigned int base_mhz, max_mhz, bus_mhz, edx;
+
+		/*
+		 * CPUID 16H Base MHz, Max MHz, Bus MHz
+		 */
+		base_mhz = max_mhz = bus_mhz = edx = 0;
+
+		__cpuid(0x16, base_mhz, max_mhz, bus_mhz, edx);
+		if (debug)
+			fprintf(outf, "CPUID(0x16): base_mhz: %d max_mhz: %d bus_mhz: %d\n",
+				base_mhz, max_mhz, bus_mhz);
+	}
 
 	if (has_aperf)
 		aperf_mperf_multiplier = get_aperf_mperf_multiplier(family, model);
@@ -2788,21 +3263,28 @@ void process_cpuid()
 	do_slm_cstates = is_slm(family, model);
 	do_knl_cstates  = is_knl(family, model);
 
+	if (debug)
+		decode_misc_pwr_mgmt_msr();
+
 	rapl_probe(family, model);
 	perf_limit_reasons_probe(family, model);
 
 	if (debug)
-		dump_cstate_pstate_config_info();
+		dump_cstate_pstate_config_info(family, model);
 
 	if (has_skl_msrs(family, model))
 		calculate_tsc_tweak();
 
+	do_gfx_rc6_ms = !access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK);
+
+	do_gfx_mhz = !access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK);
+
 	return;
 }
 
 void help()
 {
-	fprintf(stderr,
+	fprintf(outf,
 	"Usage: turbostat [OPTIONS][(--interval seconds) | COMMAND ...]\n"
 	"\n"
 	"Turbostat forks the specified COMMAND and prints statistics\n"
@@ -2814,6 +3296,7 @@ void help()
 	"--help		print this help message\n"
 	"--counter msr	print 32-bit counter at address \"msr\"\n"
 	"--Counter msr	print 64-bit Counter at address \"msr\"\n"
+	"--out file	create or truncate \"file\" for all output\n"
 	"--msr msr	print 32-bit value at address \"msr\"\n"
 	"--MSR msr	print 64-bit Value at address \"msr\"\n"
 	"--version	print version information\n"
@@ -2858,7 +3341,7 @@ void topology_probe()
 		show_cpu = 1;
 
 	if (debug > 1)
-		fprintf(stderr, "num_cpus %d max_cpu_num %d\n", topo.num_cpus, topo.max_cpu_num);
+		fprintf(outf, "num_cpus %d max_cpu_num %d\n", topo.num_cpus, topo.max_cpu_num);
 
 	cpus = calloc(1, (topo.max_cpu_num  + 1) * sizeof(struct cpu_topology));
 	if (cpus == NULL)
@@ -2893,7 +3376,7 @@ void topology_probe()
 
 		if (cpu_is_not_present(i)) {
 			if (debug > 1)
-				fprintf(stderr, "cpu%d NOT PRESENT\n", i);
+				fprintf(outf, "cpu%d NOT PRESENT\n", i);
 			continue;
 		}
 		cpus[i].core_id = get_core_id(i);
@@ -2908,26 +3391,26 @@ void topology_probe()
 		if (siblings > max_siblings)
 			max_siblings = siblings;
 		if (debug > 1)
-			fprintf(stderr, "cpu %d pkg %d core %d\n",
+			fprintf(outf, "cpu %d pkg %d core %d\n",
 				i, cpus[i].physical_package_id, cpus[i].core_id);
 	}
 	topo.num_cores_per_pkg = max_core_id + 1;
 	if (debug > 1)
-		fprintf(stderr, "max_core_id %d, sizing for %d cores per package\n",
+		fprintf(outf, "max_core_id %d, sizing for %d cores per package\n",
 			max_core_id, topo.num_cores_per_pkg);
 	if (debug && !summary_only && topo.num_cores_per_pkg > 1)
 		show_core = 1;
 
 	topo.num_packages = max_package_id + 1;
 	if (debug > 1)
-		fprintf(stderr, "max_package_id %d, sizing for %d packages\n",
+		fprintf(outf, "max_package_id %d, sizing for %d packages\n",
 			max_package_id, topo.num_packages);
 	if (debug && !summary_only && topo.num_packages > 1)
 		show_pkg = 1;
 
 	topo.num_threads_per_core = max_siblings;
 	if (debug > 1)
-		fprintf(stderr, "max_siblings %d\n", max_siblings);
+		fprintf(outf, "max_siblings %d\n", max_siblings);
 
 	free(cpus);
 }
@@ -3019,10 +3502,27 @@ void allocate_output_buffer()
 	if (outp == NULL)
 		err(-1, "calloc output buffer");
 }
+void allocate_fd_percpu(void)
+{
+	fd_percpu = calloc(topo.max_cpu_num, sizeof(int));
+	if (fd_percpu == NULL)
+		err(-1, "calloc fd_percpu");
+}
+void allocate_irq_buffers(void)
+{
+	irq_column_2_cpu = calloc(topo.num_cpus, sizeof(int));
+	if (irq_column_2_cpu == NULL)
+		err(-1, "calloc %d", topo.num_cpus);
 
+	irqs_per_cpu = calloc(topo.max_cpu_num, sizeof(int));
+	if (irqs_per_cpu == NULL)
+		err(-1, "calloc %d", topo.max_cpu_num);
+}
 void setup_all_buffers(void)
 {
 	topology_probe();
+	allocate_irq_buffers();
+	allocate_fd_percpu();
 	allocate_counters(&thread_even, &core_even, &package_even);
 	allocate_counters(&thread_odd, &core_odd, &package_odd);
 	allocate_output_buffer();
@@ -3036,7 +3536,7 @@ void set_base_cpu(void)
 		err(-ENODEV, "No valid cpus found");
 
 	if (debug > 1)
-		fprintf(stderr, "base_cpu = %d\n", base_cpu);
+		fprintf(outf, "base_cpu = %d\n", base_cpu);
 }
 
 void turbostat_init()
@@ -3049,6 +3549,9 @@ void turbostat_init()
 
 
 	if (debug)
+		for_all_cpus(print_hwp, ODD_COUNTERS);
+
+	if (debug)
 		for_all_cpus(print_epb, ODD_COUNTERS);
 
 	if (debug)
@@ -3100,9 +3603,10 @@ int fork_it(char **argv)
 	for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS);
 	compute_average(EVEN_COUNTERS);
 	format_all_counters(EVEN_COUNTERS);
-	flush_stderr();
 
-	fprintf(stderr, "%.6f sec\n", tv_delta.tv_sec + tv_delta.tv_usec/1000000.0);
+	fprintf(outf, "%.6f sec\n", tv_delta.tv_sec + tv_delta.tv_usec/1000000.0);
+
+	flush_output_stderr();
 
 	return status;
 }
@@ -3119,13 +3623,13 @@ int get_and_dump_counters(void)
 	if (status)
 		return status;
 
-	flush_stdout();
+	flush_output_stdout();
 
 	return status;
 }
 
 void print_version() {
-	fprintf(stderr, "turbostat version 4.8 26-Sep, 2015"
+	fprintf(outf, "turbostat version 4.11 27 Feb 2016"
 		" - Len Brown <lenb@kernel.org>\n");
 }
 
@@ -3143,6 +3647,7 @@ void cmdline(int argc, char **argv)
 		{"Joules",	no_argument,		0, 'J'},
 		{"MSR",		required_argument,	0, 'M'},
 		{"msr",		required_argument,	0, 'm'},
+		{"out",		required_argument,	0, 'o'},
 		{"Package",	no_argument,		0, 'p'},
 		{"processor",	no_argument,		0, 'p'},
 		{"Summary",	no_argument,		0, 'S'},
@@ -3153,7 +3658,7 @@ void cmdline(int argc, char **argv)
 
 	progname = argv[0];
 
-	while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:PpST:v",
+	while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:PpST:v",
 				long_options, &option_index)) != -1) {
 		switch (opt) {
 		case 'C':
@@ -3173,7 +3678,18 @@ void cmdline(int argc, char **argv)
 			help();
 			exit(1);
 		case 'i':
-			interval_sec = atoi(optarg);
+			{
+				double interval = strtod(optarg, NULL);
+
+				if (interval < 0.001) {
+					fprintf(outf, "interval %f seconds is too small\n",
+						interval);
+					exit(2);
+				}
+
+				interval_ts.tv_sec = interval;
+				interval_ts.tv_nsec = (interval - interval_ts.tv_sec) * 1000000000;
+			}
 			break;
 		case 'J':
 			rapl_joules++;
@@ -3184,6 +3700,9 @@ void cmdline(int argc, char **argv)
 		case 'm':
 			sscanf(optarg, "%x", &extra_msr_offset32);
 			break;
+		case 'o':
+			outf = fopen_or_die(optarg, "w");
+			break;
 		case 'P':
 			show_pkg_only++;
 			break;
@@ -3206,6 +3725,8 @@ void cmdline(int argc, char **argv)
 
 int main(int argc, char **argv)
 {
+	outf = stderr;
+
 	cmdline(argc, argv);
 
 	if (debug)
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 90bd2ea41032..3187322eeed7 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -151,6 +151,11 @@ struct nfit_test {
 	int (*alloc)(struct nfit_test *t);
 	void (*setup)(struct nfit_test *t);
 	int setup_hotplug;
+	struct ars_state {
+		struct nd_cmd_ars_status *ars_status;
+		unsigned long deadline;
+		spinlock_t lock;
+	} ars_state;
 };
 
 static struct nfit_test *to_nfit_test(struct device *dev)
@@ -217,51 +222,125 @@ static int nfit_test_cmd_set_config_data(struct nd_cmd_set_config_hdr *nd_cmd,
 	return rc;
 }
 
+#define NFIT_TEST_ARS_RECORDS 4
+#define NFIT_TEST_CLEAR_ERR_UNIT 256
+
 static int nfit_test_cmd_ars_cap(struct nd_cmd_ars_cap *nd_cmd,
 		unsigned int buf_len)
 {
 	if (buf_len < sizeof(*nd_cmd))
 		return -EINVAL;
 
-	nd_cmd->max_ars_out = 256;
+	nd_cmd->max_ars_out = sizeof(struct nd_cmd_ars_status)
+		+ NFIT_TEST_ARS_RECORDS * sizeof(struct nd_ars_record);
 	nd_cmd->status = (ND_ARS_PERSISTENT | ND_ARS_VOLATILE) << 16;
+	nd_cmd->clear_err_unit = NFIT_TEST_CLEAR_ERR_UNIT;
 
 	return 0;
 }
 
-static int nfit_test_cmd_ars_start(struct nd_cmd_ars_start *nd_cmd,
-		unsigned int buf_len)
+/*
+ * Initialize the ars_state to return an ars_result 1 second in the future with
+ * a 4K error range in the middle of the requested address range.
+ */
+static void post_ars_status(struct ars_state *ars_state, u64 addr, u64 len)
 {
-	if (buf_len < sizeof(*nd_cmd))
+	struct nd_cmd_ars_status *ars_status;
+	struct nd_ars_record *ars_record;
+
+	ars_state->deadline = jiffies + 1*HZ;
+	ars_status = ars_state->ars_status;
+	ars_status->status = 0;
+	ars_status->out_length = sizeof(struct nd_cmd_ars_status)
+		+ sizeof(struct nd_ars_record);
+	ars_status->address = addr;
+	ars_status->length = len;
+	ars_status->type = ND_ARS_PERSISTENT;
+	ars_status->num_records = 1;
+	ars_record = &ars_status->records[0];
+	ars_record->handle = 0;
+	ars_record->err_address = addr + len / 2;
+	ars_record->length = SZ_4K;
+}
+
+static int nfit_test_cmd_ars_start(struct ars_state *ars_state,
+		struct nd_cmd_ars_start *ars_start, unsigned int buf_len,
+		int *cmd_rc)
+{
+	if (buf_len < sizeof(*ars_start))
 		return -EINVAL;
 
-	nd_cmd->status = 0;
+	spin_lock(&ars_state->lock);
+	if (time_before(jiffies, ars_state->deadline)) {
+		ars_start->status = NFIT_ARS_START_BUSY;
+		*cmd_rc = -EBUSY;
+	} else {
+		ars_start->status = 0;
+		ars_start->scrub_time = 1;
+		post_ars_status(ars_state, ars_start->address,
+				ars_start->length);
+		*cmd_rc = 0;
+	}
+	spin_unlock(&ars_state->lock);
 
 	return 0;
 }
 
-static int nfit_test_cmd_ars_status(struct nd_cmd_ars_status *nd_cmd,
-		unsigned int buf_len)
+static int nfit_test_cmd_ars_status(struct ars_state *ars_state,
+		struct nd_cmd_ars_status *ars_status, unsigned int buf_len,
+		int *cmd_rc)
 {
-	if (buf_len < sizeof(*nd_cmd))
+	if (buf_len < ars_state->ars_status->out_length)
 		return -EINVAL;
 
-	nd_cmd->out_length = 256;
-	nd_cmd->num_records = 0;
-	nd_cmd->address = 0;
-	nd_cmd->length = -1ULL;
-	nd_cmd->status = 0;
+	spin_lock(&ars_state->lock);
+	if (time_before(jiffies, ars_state->deadline)) {
+		memset(ars_status, 0, buf_len);
+		ars_status->status = NFIT_ARS_STATUS_BUSY;
+		ars_status->out_length = sizeof(*ars_status);
+		*cmd_rc = -EBUSY;
+	} else {
+		memcpy(ars_status, ars_state->ars_status,
+				ars_state->ars_status->out_length);
+		*cmd_rc = 0;
+	}
+	spin_unlock(&ars_state->lock);
+	return 0;
+}
+
+static int nfit_test_cmd_clear_error(struct nd_cmd_clear_error *clear_err,
+		unsigned int buf_len, int *cmd_rc)
+{
+	const u64 mask = NFIT_TEST_CLEAR_ERR_UNIT - 1;
+	if (buf_len < sizeof(*clear_err))
+		return -EINVAL;
+
+	if ((clear_err->address & mask) || (clear_err->length & mask))
+		return -EINVAL;
 
+	/*
+	 * Report 'all clear' success for all commands even though a new
+	 * scrub will find errors again.  This is enough to have the
+	 * error removed from the 'badblocks' tracking in the pmem
+	 * driver.
+	 */
+	clear_err->status = 0;
+	clear_err->cleared = clear_err->length;
+	*cmd_rc = 0;
 	return 0;
 }
 
 static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
 		struct nvdimm *nvdimm, unsigned int cmd, void *buf,
-		unsigned int buf_len)
+		unsigned int buf_len, int *cmd_rc)
 {
 	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
 	struct nfit_test *t = container_of(acpi_desc, typeof(*t), acpi_desc);
-	int i, rc = 0;
+	int i, rc = 0, __cmd_rc;
+
+	if (!cmd_rc)
+		cmd_rc = &__cmd_rc;
+	*cmd_rc = 0;
 
 	if (nvdimm) {
 		struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
@@ -293,6 +372,8 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
 			return -ENOTTY;
 		}
 	} else {
+		struct ars_state *ars_state = &t->ars_state;
+
 		if (!nd_desc || !test_bit(cmd, &nd_desc->dsm_mask))
 			return -ENOTTY;
 
@@ -301,10 +382,15 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
 			rc = nfit_test_cmd_ars_cap(buf, buf_len);
 			break;
 		case ND_CMD_ARS_START:
-			rc = nfit_test_cmd_ars_start(buf, buf_len);
+			rc = nfit_test_cmd_ars_start(ars_state, buf, buf_len,
+					cmd_rc);
 			break;
 		case ND_CMD_ARS_STATUS:
-			rc = nfit_test_cmd_ars_status(buf, buf_len);
+			rc = nfit_test_cmd_ars_status(ars_state, buf, buf_len,
+					cmd_rc);
+			break;
+		case ND_CMD_CLEAR_ERROR:
+			rc = nfit_test_cmd_clear_error(buf, buf_len, cmd_rc);
 			break;
 		default:
 			return -ENOTTY;
@@ -420,11 +506,25 @@ static struct nfit_test_resource *nfit_test_lookup(resource_size_t addr)
 	return NULL;
 }
 
+static int ars_state_init(struct device *dev, struct ars_state *ars_state)
+{
+	ars_state->ars_status = devm_kzalloc(dev,
+			sizeof(struct nd_cmd_ars_status)
+			+ sizeof(struct nd_ars_record) * NFIT_TEST_ARS_RECORDS,
+			GFP_KERNEL);
+	if (!ars_state->ars_status)
+		return -ENOMEM;
+	spin_lock_init(&ars_state->lock);
+	return 0;
+}
+
 static int nfit_test0_alloc(struct nfit_test *t)
 {
 	size_t nfit_size = sizeof(struct acpi_nfit_system_address) * NUM_SPA
 			+ sizeof(struct acpi_nfit_memory_map) * NUM_MEM
 			+ sizeof(struct acpi_nfit_control_region) * NUM_DCR
+			+ offsetof(struct acpi_nfit_control_region,
+					window_size) * NUM_DCR
 			+ sizeof(struct acpi_nfit_data_region) * NUM_BDW
 			+ sizeof(struct acpi_nfit_flush_address) * NUM_DCR;
 	int i;
@@ -467,14 +567,14 @@ static int nfit_test0_alloc(struct nfit_test *t)
 			return -ENOMEM;
 	}
 
-	return 0;
+	return ars_state_init(&t->pdev.dev, &t->ars_state);
 }
 
 static int nfit_test1_alloc(struct nfit_test *t)
 {
 	size_t nfit_size = sizeof(struct acpi_nfit_system_address)
 		+ sizeof(struct acpi_nfit_memory_map)
-		+ sizeof(struct acpi_nfit_control_region);
+		+ offsetof(struct acpi_nfit_control_region, window_size);
 
 	t->nfit_buf = test_alloc(t, nfit_size, &t->nfit_dma);
 	if (!t->nfit_buf)
@@ -485,12 +585,11 @@ static int nfit_test1_alloc(struct nfit_test *t)
 	if (!t->spa_set[0])
 		return -ENOMEM;
 
-	return 0;
+	return ars_state_init(&t->pdev.dev, &t->ars_state);
 }
 
 static void nfit_test0_setup(struct nfit_test *t)
 {
-	struct nvdimm_bus_descriptor *nd_desc;
 	struct acpi_nfit_desc *acpi_desc;
 	struct acpi_nfit_memory_map *memdev;
 	void *nfit_buf = t->nfit_buf;
@@ -607,7 +706,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->physical_id = 0;
 	memdev->region_id = 0;
 	memdev->range_index = 0+1;
-	memdev->region_index = 0+1;
+	memdev->region_index = 4+1;
 	memdev->region_size = SPA0_SIZE/2;
 	memdev->region_offset = t->spa_set_dma[0];
 	memdev->address = 0;
@@ -622,7 +721,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->physical_id = 1;
 	memdev->region_id = 0;
 	memdev->range_index = 0+1;
-	memdev->region_index = 1+1;
+	memdev->region_index = 5+1;
 	memdev->region_size = SPA0_SIZE/2;
 	memdev->region_offset = t->spa_set_dma[0] + SPA0_SIZE/2;
 	memdev->address = 0;
@@ -637,7 +736,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->physical_id = 0;
 	memdev->region_id = 1;
 	memdev->range_index = 1+1;
-	memdev->region_index = 0+1;
+	memdev->region_index = 4+1;
 	memdev->region_size = SPA1_SIZE/4;
 	memdev->region_offset = t->spa_set_dma[1];
 	memdev->address = SPA0_SIZE/2;
@@ -652,7 +751,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->physical_id = 1;
 	memdev->region_id = 1;
 	memdev->range_index = 1+1;
-	memdev->region_index = 1+1;
+	memdev->region_index = 5+1;
 	memdev->region_size = SPA1_SIZE/4;
 	memdev->region_offset = t->spa_set_dma[1] + SPA1_SIZE/4;
 	memdev->address = SPA0_SIZE/2;
@@ -667,7 +766,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->physical_id = 2;
 	memdev->region_id = 0;
 	memdev->range_index = 1+1;
-	memdev->region_index = 2+1;
+	memdev->region_index = 6+1;
 	memdev->region_size = SPA1_SIZE/4;
 	memdev->region_offset = t->spa_set_dma[1] + 2*SPA1_SIZE/4;
 	memdev->address = SPA0_SIZE/2;
@@ -682,7 +781,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->physical_id = 3;
 	memdev->region_id = 0;
 	memdev->range_index = 1+1;
-	memdev->region_index = 3+1;
+	memdev->region_index = 7+1;
 	memdev->region_size = SPA1_SIZE/4;
 	memdev->region_offset = t->spa_set_dma[1] + 3*SPA1_SIZE/4;
 	memdev->address = SPA0_SIZE/2;
@@ -810,7 +909,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	memdev->interleave_ways = 1;
 
 	offset = offset + sizeof(struct acpi_nfit_memory_map) * 14;
-	/* dcr-descriptor0 */
+	/* dcr-descriptor0: blk */
 	dcr = nfit_buf + offset;
 	dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
 	dcr->header.length = sizeof(struct acpi_nfit_control_region);
@@ -819,6 +918,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	dcr->device_id = 0;
 	dcr->revision_id = 1;
 	dcr->serial_number = ~handle[0];
+	dcr->code = NFIT_FIC_BLK;
 	dcr->windows = 1;
 	dcr->window_size = DCR_SIZE;
 	dcr->command_offset = 0;
@@ -826,7 +926,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	dcr->status_offset = 8;
 	dcr->status_size = 4;
 
-	/* dcr-descriptor1 */
+	/* dcr-descriptor1: blk */
 	dcr = nfit_buf + offset + sizeof(struct acpi_nfit_control_region);
 	dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
 	dcr->header.length = sizeof(struct acpi_nfit_control_region);
@@ -835,6 +935,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	dcr->device_id = 0;
 	dcr->revision_id = 1;
 	dcr->serial_number = ~handle[1];
+	dcr->code = NFIT_FIC_BLK;
 	dcr->windows = 1;
 	dcr->window_size = DCR_SIZE;
 	dcr->command_offset = 0;
@@ -842,7 +943,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	dcr->status_offset = 8;
 	dcr->status_size = 4;
 
-	/* dcr-descriptor2 */
+	/* dcr-descriptor2: blk */
 	dcr = nfit_buf + offset + sizeof(struct acpi_nfit_control_region) * 2;
 	dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
 	dcr->header.length = sizeof(struct acpi_nfit_control_region);
@@ -851,6 +952,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	dcr->device_id = 0;
 	dcr->revision_id = 1;
 	dcr->serial_number = ~handle[2];
+	dcr->code = NFIT_FIC_BLK;
 	dcr->windows = 1;
 	dcr->window_size = DCR_SIZE;
 	dcr->command_offset = 0;
@@ -858,7 +960,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	dcr->status_offset = 8;
 	dcr->status_size = 4;
 
-	/* dcr-descriptor3 */
+	/* dcr-descriptor3: blk */
 	dcr = nfit_buf + offset + sizeof(struct acpi_nfit_control_region) * 3;
 	dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
 	dcr->header.length = sizeof(struct acpi_nfit_control_region);
@@ -867,6 +969,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	dcr->device_id = 0;
 	dcr->revision_id = 1;
 	dcr->serial_number = ~handle[3];
+	dcr->code = NFIT_FIC_BLK;
 	dcr->windows = 1;
 	dcr->window_size = DCR_SIZE;
 	dcr->command_offset = 0;
@@ -875,6 +978,63 @@ static void nfit_test0_setup(struct nfit_test *t)
 	dcr->status_size = 4;
 
 	offset = offset + sizeof(struct acpi_nfit_control_region) * 4;
+	/* dcr-descriptor0: pmem */
+	dcr = nfit_buf + offset;
+	dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
+	dcr->header.length = offsetof(struct acpi_nfit_control_region,
+			window_size);
+	dcr->region_index = 4+1;
+	dcr->vendor_id = 0xabcd;
+	dcr->device_id = 0;
+	dcr->revision_id = 1;
+	dcr->serial_number = ~handle[0];
+	dcr->code = NFIT_FIC_BYTEN;
+	dcr->windows = 0;
+
+	/* dcr-descriptor1: pmem */
+	dcr = nfit_buf + offset + offsetof(struct acpi_nfit_control_region,
+			window_size);
+	dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
+	dcr->header.length = offsetof(struct acpi_nfit_control_region,
+			window_size);
+	dcr->region_index = 5+1;
+	dcr->vendor_id = 0xabcd;
+	dcr->device_id = 0;
+	dcr->revision_id = 1;
+	dcr->serial_number = ~handle[1];
+	dcr->code = NFIT_FIC_BYTEN;
+	dcr->windows = 0;
+
+	/* dcr-descriptor2: pmem */
+	dcr = nfit_buf + offset + offsetof(struct acpi_nfit_control_region,
+			window_size) * 2;
+	dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
+	dcr->header.length = offsetof(struct acpi_nfit_control_region,
+			window_size);
+	dcr->region_index = 6+1;
+	dcr->vendor_id = 0xabcd;
+	dcr->device_id = 0;
+	dcr->revision_id = 1;
+	dcr->serial_number = ~handle[2];
+	dcr->code = NFIT_FIC_BYTEN;
+	dcr->windows = 0;
+
+	/* dcr-descriptor3: pmem */
+	dcr = nfit_buf + offset + offsetof(struct acpi_nfit_control_region,
+			window_size) * 3;
+	dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
+	dcr->header.length = offsetof(struct acpi_nfit_control_region,
+			window_size);
+	dcr->region_index = 7+1;
+	dcr->vendor_id = 0xabcd;
+	dcr->device_id = 0;
+	dcr->revision_id = 1;
+	dcr->serial_number = ~handle[3];
+	dcr->code = NFIT_FIC_BYTEN;
+	dcr->windows = 0;
+
+	offset = offset + offsetof(struct acpi_nfit_control_region,
+			window_size) * 4;
 	/* bdw0 (spa/dcr0, dimm0) */
 	bdw = nfit_buf + offset;
 	bdw->header.type = ACPI_NFIT_TYPE_DATA_REGION;
@@ -954,15 +1114,16 @@ static void nfit_test0_setup(struct nfit_test *t)
 
 	if (t->setup_hotplug) {
 		offset = offset + sizeof(struct acpi_nfit_flush_address) * 4;
-		/* dcr-descriptor4 */
+		/* dcr-descriptor4: blk */
 		dcr = nfit_buf + offset;
 		dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
 		dcr->header.length = sizeof(struct acpi_nfit_control_region);
-		dcr->region_index = 4+1;
+		dcr->region_index = 8+1;
 		dcr->vendor_id = 0xabcd;
 		dcr->device_id = 0;
 		dcr->revision_id = 1;
 		dcr->serial_number = ~handle[4];
+		dcr->code = NFIT_FIC_BLK;
 		dcr->windows = 1;
 		dcr->window_size = DCR_SIZE;
 		dcr->command_offset = 0;
@@ -971,11 +1132,26 @@ static void nfit_test0_setup(struct nfit_test *t)
 		dcr->status_size = 4;
 
 		offset = offset + sizeof(struct acpi_nfit_control_region);
+		/* dcr-descriptor4: pmem */
+		dcr = nfit_buf + offset;
+		dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
+		dcr->header.length = offsetof(struct acpi_nfit_control_region,
+				window_size);
+		dcr->region_index = 9+1;
+		dcr->vendor_id = 0xabcd;
+		dcr->device_id = 0;
+		dcr->revision_id = 1;
+		dcr->serial_number = ~handle[4];
+		dcr->code = NFIT_FIC_BYTEN;
+		dcr->windows = 0;
+
+		offset = offset + offsetof(struct acpi_nfit_control_region,
+				window_size);
 		/* bdw4 (spa/dcr4, dimm4) */
 		bdw = nfit_buf + offset;
 		bdw->header.type = ACPI_NFIT_TYPE_DATA_REGION;
 		bdw->header.length = sizeof(struct acpi_nfit_data_region);
-		bdw->region_index = 4+1;
+		bdw->region_index = 8+1;
 		bdw->windows = 1;
 		bdw->offset = 0;
 		bdw->size = BDW_SIZE;
@@ -1023,7 +1199,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 		memdev->physical_id = 4;
 		memdev->region_id = 0;
 		memdev->range_index = 10+1;
-		memdev->region_index = 4+1;
+		memdev->region_index = 8+1;
 		memdev->region_size = 0;
 		memdev->region_offset = 0;
 		memdev->address = 0;
@@ -1039,14 +1215,14 @@ static void nfit_test0_setup(struct nfit_test *t)
 		memdev->physical_id = 4;
 		memdev->region_id = 0;
 		memdev->range_index = 11+1;
-		memdev->region_index = 4+1;
+		memdev->region_index = 9+1;
 		memdev->region_size = SPA0_SIZE;
 		memdev->region_offset = t->spa_set_dma[2];
 		memdev->address = 0;
 		memdev->interleave_index = 0;
 		memdev->interleave_ways = 1;
 
-		/* mem-region16 (spa/dcr4, dimm4) */
+		/* mem-region16 (spa/bdw4, dimm4) */
 		memdev = nfit_buf + offset +
 				sizeof(struct acpi_nfit_memory_map) * 2;
 		memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
@@ -1055,7 +1231,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 		memdev->physical_id = 4;
 		memdev->region_id = 0;
 		memdev->range_index = 12+1;
-		memdev->region_index = 4+1;
+		memdev->region_index = 8+1;
 		memdev->region_size = 0;
 		memdev->region_offset = 0;
 		memdev->address = 0;
@@ -1072,6 +1248,8 @@ static void nfit_test0_setup(struct nfit_test *t)
 		flush->hint_address[0] = t->flush_dma[4];
 	}
 
+	post_ars_status(&t->ars_state, t->spa_set_dma[0], SPA0_SIZE);
+
 	acpi_desc = &t->acpi_desc;
 	set_bit(ND_CMD_GET_CONFIG_SIZE, &acpi_desc->dimm_dsm_force_en);
 	set_bit(ND_CMD_GET_CONFIG_DATA, &acpi_desc->dimm_dsm_force_en);
@@ -1079,8 +1257,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	set_bit(ND_CMD_ARS_CAP, &acpi_desc->bus_dsm_force_en);
 	set_bit(ND_CMD_ARS_START, &acpi_desc->bus_dsm_force_en);
 	set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_dsm_force_en);
-	nd_desc = &acpi_desc->nd_desc;
-	nd_desc->ndctl = nfit_test_ctl;
+	set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_dsm_force_en);
 }
 
 static void nfit_test1_setup(struct nfit_test *t)
@@ -1090,7 +1267,6 @@ static void nfit_test1_setup(struct nfit_test *t)
 	struct acpi_nfit_memory_map *memdev;
 	struct acpi_nfit_control_region *dcr;
 	struct acpi_nfit_system_address *spa;
-	struct nvdimm_bus_descriptor *nd_desc;
 	struct acpi_nfit_desc *acpi_desc;
 
 	offset = 0;
@@ -1126,26 +1302,23 @@ static void nfit_test1_setup(struct nfit_test *t)
 	/* dcr-descriptor0 */
 	dcr = nfit_buf + offset;
 	dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
-	dcr->header.length = sizeof(struct acpi_nfit_control_region);
+	dcr->header.length = offsetof(struct acpi_nfit_control_region,
+			window_size);
 	dcr->region_index = 0+1;
 	dcr->vendor_id = 0xabcd;
 	dcr->device_id = 0;
 	dcr->revision_id = 1;
 	dcr->serial_number = ~0;
-	dcr->code = 0x201;
+	dcr->code = NFIT_FIC_BYTE;
 	dcr->windows = 0;
-	dcr->window_size = 0;
-	dcr->command_offset = 0;
-	dcr->command_size = 0;
-	dcr->status_offset = 0;
-	dcr->status_size = 0;
+
+	post_ars_status(&t->ars_state, t->spa_set_dma[0], SPA2_SIZE);
 
 	acpi_desc = &t->acpi_desc;
 	set_bit(ND_CMD_ARS_CAP, &acpi_desc->bus_dsm_force_en);
 	set_bit(ND_CMD_ARS_START, &acpi_desc->bus_dsm_force_en);
 	set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_dsm_force_en);
-	nd_desc = &acpi_desc->nd_desc;
-	nd_desc->ndctl = nfit_test_ctl;
+	set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_dsm_force_en);
 }
 
 static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa,
@@ -1228,26 +1401,16 @@ static int nfit_test_probe(struct platform_device *pdev)
 
 	nfit_test->setup(nfit_test);
 	acpi_desc = &nfit_test->acpi_desc;
-	acpi_desc->dev = &pdev->dev;
+	acpi_nfit_desc_init(acpi_desc, &pdev->dev);
 	acpi_desc->nfit = nfit_test->nfit_buf;
 	acpi_desc->blk_do_io = nfit_test_blk_do_io;
 	nd_desc = &acpi_desc->nd_desc;
-	nd_desc->attr_groups = acpi_nfit_attribute_groups;
+	nd_desc->provider_name = NULL;
+	nd_desc->ndctl = nfit_test_ctl;
 	acpi_desc->nvdimm_bus = nvdimm_bus_register(&pdev->dev, nd_desc);
 	if (!acpi_desc->nvdimm_bus)
 		return -ENXIO;
 
-	INIT_LIST_HEAD(&acpi_desc->spa_maps);
-	INIT_LIST_HEAD(&acpi_desc->spas);
-	INIT_LIST_HEAD(&acpi_desc->dcrs);
-	INIT_LIST_HEAD(&acpi_desc->bdws);
-	INIT_LIST_HEAD(&acpi_desc->idts);
-	INIT_LIST_HEAD(&acpi_desc->flushes);
-	INIT_LIST_HEAD(&acpi_desc->memdevs);
-	INIT_LIST_HEAD(&acpi_desc->dimms);
-	mutex_init(&acpi_desc->spa_map_mutex);
-	mutex_init(&acpi_desc->init_mutex);
-
 	rc = acpi_nfit_init(acpi_desc, nfit_test->nfit_size);
 	if (rc) {
 		nvdimm_bus_unregister(acpi_desc->nvdimm_bus);
diff --git a/tools/testing/selftests/efivarfs/efivarfs.sh b/tools/testing/selftests/efivarfs/efivarfs.sh
index 77edcdcc016b..057278448515 100755
--- a/tools/testing/selftests/efivarfs/efivarfs.sh
+++ b/tools/testing/selftests/efivarfs/efivarfs.sh
@@ -88,7 +88,11 @@ test_delete()
 		exit 1
 	fi
 
-	rm $file
+	rm $file 2>/dev/null
+	if [ $? -ne 0 ]; then
+		chattr -i $file
+		rm $file
+	fi
 
 	if [ -e $file ]; then
 		echo "$file couldn't be deleted" >&2
@@ -111,6 +115,7 @@ test_zero_size_delete()
 		exit 1
 	fi
 
+	chattr -i $file
 	printf "$attrs" > $file
 
 	if [ -e $file ]; then
@@ -141,7 +146,11 @@ test_valid_filenames()
 			echo "$file could not be created" >&2
 			ret=1
 		else
-			rm $file
+			rm $file 2>/dev/null
+			if [ $? -ne 0 ]; then
+				chattr -i $file
+				rm $file
+			fi
 		fi
 	done
 
@@ -174,7 +183,11 @@ test_invalid_filenames()
 
 		if [ -e $file ]; then
 			echo "Creating $file should have failed" >&2
-			rm $file
+			rm $file 2>/dev/null
+			if [ $? -ne 0 ]; then
+				chattr -i $file
+				rm $file
+			fi
 			ret=1
 		fi
 	done
diff --git a/tools/testing/selftests/efivarfs/open-unlink.c b/tools/testing/selftests/efivarfs/open-unlink.c
index 8c0764407b3c..4af74f733036 100644
--- a/tools/testing/selftests/efivarfs/open-unlink.c
+++ b/tools/testing/selftests/efivarfs/open-unlink.c
@@ -1,10 +1,68 @@
+#include <errno.h>
 #include <stdio.h>
 #include <stdint.h>
 #include <stdlib.h>
 #include <unistd.h>
+#include <sys/ioctl.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
+#include <linux/fs.h>
+
+static int set_immutable(const char *path, int immutable)
+{
+	unsigned int flags;
+	int fd;
+	int rc;
+	int error;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return fd;
+
+	rc = ioctl(fd, FS_IOC_GETFLAGS, &flags);
+	if (rc < 0) {
+		error = errno;
+		close(fd);
+		errno = error;
+		return rc;
+	}
+
+	if (immutable)
+		flags |= FS_IMMUTABLE_FL;
+	else
+		flags &= ~FS_IMMUTABLE_FL;
+
+	rc = ioctl(fd, FS_IOC_SETFLAGS, &flags);
+	error = errno;
+	close(fd);
+	errno = error;
+	return rc;
+}
+
+static int get_immutable(const char *path)
+{
+	unsigned int flags;
+	int fd;
+	int rc;
+	int error;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return fd;
+
+	rc = ioctl(fd, FS_IOC_GETFLAGS, &flags);
+	if (rc < 0) {
+		error = errno;
+		close(fd);
+		errno = error;
+		return rc;
+	}
+	close(fd);
+	if (flags & FS_IMMUTABLE_FL)
+		return 1;
+	return 0;
+}
 
 int main(int argc, char **argv)
 {
@@ -27,7 +85,7 @@ int main(int argc, char **argv)
 	buf[4] = 0;
 
 	/* create a test variable */
-	fd = open(path, O_WRONLY | O_CREAT);
+	fd = open(path, O_WRONLY | O_CREAT, 0600);
 	if (fd < 0) {
 		perror("open(O_WRONLY)");
 		return EXIT_FAILURE;
@@ -41,6 +99,18 @@ int main(int argc, char **argv)
 
 	close(fd);
 
+	rc = get_immutable(path);
+	if (rc < 0) {
+		perror("ioctl(FS_IOC_GETFLAGS)");
+		return EXIT_FAILURE;
+	} else if (rc) {
+		rc = set_immutable(path, 0);
+		if (rc < 0) {
+			perror("ioctl(FS_IOC_SETFLAGS)");
+			return EXIT_FAILURE;
+		}
+	}
+
 	fd = open(path, O_RDONLY);
 	if (fd < 0) {
 		perror("open");
diff --git a/tools/testing/selftests/ftrace/test.d/instances/instance.tc b/tools/testing/selftests/ftrace/test.d/instances/instance.tc
index 773e276ff90b..1e1abe0ad354 100644
--- a/tools/testing/selftests/ftrace/test.d/instances/instance.tc
+++ b/tools/testing/selftests/ftrace/test.d/instances/instance.tc
@@ -39,28 +39,23 @@ instance_slam() {
 }
 
 instance_slam &
-x=`jobs -l`
-p1=`echo $x | cut -d' ' -f2`
+p1=$!
 echo $p1
 
 instance_slam &
-x=`jobs -l | tail -1`
-p2=`echo $x | cut -d' ' -f2`
+p2=$!
 echo $p2
 
 instance_slam &
-x=`jobs -l | tail -1`
-p3=`echo $x | cut -d' ' -f2`
+p3=$!
 echo $p3
 
 instance_slam &
-x=`jobs -l | tail -1`
-p4=`echo $x | cut -d' ' -f2`
+p4=$!
 echo $p4
 
 instance_slam &
-x=`jobs -l | tail -1`
-p5=`echo $x | cut -d' ' -f2`
+p5=$!
 echo $p5
 
 ls -lR >/dev/null
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 844787a0d7be..5eb49b7f864c 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -33,7 +33,7 @@ if grep -Pq '\x00' < $file
 then
 	print_warning Console output contains nul bytes, old qemu still running?
 fi
-egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|Stall ended before state dump start' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $1.diags
+egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $1.diags
 if test -s $1.diags
 then
 	print_warning Assertion failure in $file $title
@@ -64,10 +64,12 @@ then
 	then
 		summary="$summary  lockdep: $n_badness"
 	fi
-	n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|Stall ended before state dump start' $1`
+	n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state' $1`
 	if test "$n_stalls" -ne 0
 	then
 		summary="$summary  Stalls: $n_stalls"
 	fi
 	print_warning Summary: $summary
+else
+	rm $1.diags
 fi
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index d0c473f65850..d5ce7d7aae3e 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -4,15 +4,16 @@ include ../lib.mk
 
 .PHONY: all all_32 all_64 warn_32bit_failure clean
 
-TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall
-TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault sigreturn test_syscall_vdso unwind_vdso \
+TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall \
+			check_initial_reg_state sigreturn ldt_gdt
+TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \
-			ldt_gdt \
 			vdso_restorer
 
 TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
+TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY)
 BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32)
-BINARIES_64 := $(TARGETS_C_BOTHBITS:%=%_64)
+BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64)
 
 CFLAGS := -O2 -g -std=gnu99 -pthread -Wall
 
@@ -40,7 +41,7 @@ clean:
 $(TARGETS_C_32BIT_ALL:%=%_32): %_32: %.c
 	$(CC) -m32 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl -lm
 
-$(TARGETS_C_BOTHBITS:%=%_64): %_64: %.c
+$(TARGETS_C_64BIT_ALL:%=%_64): %_64: %.c
 	$(CC) -m64 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl
 
 # x86_64 users should be encouraged to install 32-bit libraries
@@ -65,3 +66,9 @@ endif
 sysret_ss_attrs_64: thunks.S
 ptrace_syscall_32: raw_syscall_helper_32.S
 test_syscall_vdso_32: thunks_32.S
+
+# check_initial_reg_state is special: it needs a custom entry, and it
+# needs to be static so that its interpreter doesn't destroy its initial
+# state.
+check_initial_reg_state_32: CFLAGS += -Wl,-ereal_start -static
+check_initial_reg_state_64: CFLAGS += -Wl,-ereal_start -static
diff --git a/tools/testing/selftests/x86/check_initial_reg_state.c b/tools/testing/selftests/x86/check_initial_reg_state.c
new file mode 100644
index 000000000000..6aaed9b85baf
--- /dev/null
+++ b/tools/testing/selftests/x86/check_initial_reg_state.c
@@ -0,0 +1,109 @@
+/*
+ * check_initial_reg_state.c - check that execve sets the correct state
+ * Copyright (c) 2014-2016 Andrew Lutomirski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+
+unsigned long ax, bx, cx, dx, si, di, bp, sp, flags;
+unsigned long r8, r9, r10, r11, r12, r13, r14, r15;
+
+asm (
+	".pushsection .text\n\t"
+	".type real_start, @function\n\t"
+	".global real_start\n\t"
+	"real_start:\n\t"
+#ifdef __x86_64__
+	"mov %rax, ax\n\t"
+	"mov %rbx, bx\n\t"
+	"mov %rcx, cx\n\t"
+	"mov %rdx, dx\n\t"
+	"mov %rsi, si\n\t"
+	"mov %rdi, di\n\t"
+	"mov %rbp, bp\n\t"
+	"mov %rsp, sp\n\t"
+	"mov %r8, r8\n\t"
+	"mov %r9, r9\n\t"
+	"mov %r10, r10\n\t"
+	"mov %r11, r11\n\t"
+	"mov %r12, r12\n\t"
+	"mov %r13, r13\n\t"
+	"mov %r14, r14\n\t"
+	"mov %r15, r15\n\t"
+	"pushfq\n\t"
+	"popq flags\n\t"
+#else
+	"mov %eax, ax\n\t"
+	"mov %ebx, bx\n\t"
+	"mov %ecx, cx\n\t"
+	"mov %edx, dx\n\t"
+	"mov %esi, si\n\t"
+	"mov %edi, di\n\t"
+	"mov %ebp, bp\n\t"
+	"mov %esp, sp\n\t"
+	"pushfl\n\t"
+	"popl flags\n\t"
+#endif
+	"jmp _start\n\t"
+	".size real_start, . - real_start\n\t"
+	".popsection");
+
+int main()
+{
+	int nerrs = 0;
+
+	if (sp == 0) {
+		printf("[FAIL]\tTest was built incorrectly\n");
+		return 1;
+	}
+
+	if (ax || bx || cx || dx || si || di || bp
+#ifdef __x86_64__
+	    || r8 || r9 || r10 || r11 || r12 || r13 || r14 || r15
+#endif
+		) {
+		printf("[FAIL]\tAll GPRs except SP should be 0\n");
+#define SHOW(x) printf("\t" #x " = 0x%lx\n", x);
+		SHOW(ax);
+		SHOW(bx);
+		SHOW(cx);
+		SHOW(dx);
+		SHOW(si);
+		SHOW(di);
+		SHOW(bp);
+		SHOW(sp);
+#ifdef __x86_64__
+		SHOW(r8);
+		SHOW(r9);
+		SHOW(r10);
+		SHOW(r11);
+		SHOW(r12);
+		SHOW(r13);
+		SHOW(r14);
+		SHOW(r15);
+#endif
+		nerrs++;
+	} else {
+		printf("[OK]\tAll GPRs except SP are 0\n");
+	}
+
+	if (flags != 0x202) {
+		printf("[FAIL]\tFLAGS is 0x%lx, but it should be 0x202\n", flags);
+		nerrs++;
+	} else {
+		printf("[OK]\tFLAGS is 0x202\n");
+	}
+
+	return nerrs ? 1 : 0;
+}
diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c
index 5105b49cd8aa..421456784bc6 100644
--- a/tools/testing/selftests/x86/ptrace_syscall.c
+++ b/tools/testing/selftests/x86/ptrace_syscall.c
@@ -103,6 +103,17 @@ static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
 		err(1, "sigaction");
 }
 
+static void setsigign(int sig, int flags)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = (void *)SIG_IGN;
+	sa.sa_flags = flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
 static void clearhandler(int sig)
 {
 	struct sigaction sa;
@@ -187,7 +198,7 @@ static void test_ptrace_syscall_restart(void)
 
 	printf("[RUN]\tSYSEMU\n");
 	if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0)
-		err(1, "PTRACE_SYSCALL");
+		err(1, "PTRACE_SYSEMU");
 	wait_trap(chld);
 
 	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
@@ -218,7 +229,7 @@ static void test_ptrace_syscall_restart(void)
 		err(1, "PTRACE_SETREGS");
 
 	if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0)
-		err(1, "PTRACE_SYSCALL");
+		err(1, "PTRACE_SYSEMU");
 	wait_trap(chld);
 
 	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
@@ -250,7 +261,7 @@ static void test_ptrace_syscall_restart(void)
 		err(1, "PTRACE_SETREGS");
 
 	if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0)
-		err(1, "PTRACE_SYSCALL");
+		err(1, "PTRACE_SYSEMU");
 	wait_trap(chld);
 
 	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
@@ -277,6 +288,119 @@ static void test_ptrace_syscall_restart(void)
 	}
 }
 
+static void test_restart_under_ptrace(void)
+{
+	printf("[RUN]\tkernel syscall restart under ptrace\n");
+	pid_t chld = fork();
+	if (chld < 0)
+		err(1, "fork");
+
+	if (chld == 0) {
+		if (ptrace(PTRACE_TRACEME, 0, 0, 0) != 0)
+			err(1, "PTRACE_TRACEME");
+
+		printf("\tChild will take a nap until signaled\n");
+		setsigign(SIGUSR1, SA_RESTART);
+		raise(SIGSTOP);
+
+		syscall(SYS_pause, 0, 0, 0, 0, 0, 0);
+		_exit(0);
+	}
+
+	int status;
+
+	/* Wait for SIGSTOP. */
+	if (waitpid(chld, &status, 0) != chld || !WIFSTOPPED(status))
+		err(1, "waitpid");
+
+	struct user_regs_struct regs;
+
+	printf("[RUN]\tSYSCALL\n");
+	if (ptrace(PTRACE_SYSCALL, chld, 0, 0) != 0)
+		err(1, "PTRACE_SYSCALL");
+	wait_trap(chld);
+
+	/* We should be stopped at pause(2) entry. */
+
+	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_GETREGS");
+
+	if (regs.user_syscall_nr != SYS_pause ||
+	    regs.user_arg0 != 0 || regs.user_arg1 != 0 ||
+	    regs.user_arg2 != 0 || regs.user_arg3 != 0 ||
+	    regs.user_arg4 != 0 || regs.user_arg5 != 0) {
+		printf("[FAIL]\tInitial args are wrong (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n", (unsigned long)regs.user_syscall_nr, (unsigned long)regs.user_arg0, (unsigned long)regs.user_arg1, (unsigned long)regs.user_arg2, (unsigned long)regs.user_arg3, (unsigned long)regs.user_arg4, (unsigned long)regs.user_arg5);
+		nerrs++;
+	} else {
+		printf("[OK]\tInitial nr and args are correct\n");
+	}
+
+	/* Interrupt it. */
+	kill(chld, SIGUSR1);
+
+	/* Advance.  We should be stopped at exit. */
+	printf("[RUN]\tSYSCALL\n");
+	if (ptrace(PTRACE_SYSCALL, chld, 0, 0) != 0)
+		err(1, "PTRACE_SYSCALL");
+	wait_trap(chld);
+
+	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_GETREGS");
+
+	if (regs.user_syscall_nr != SYS_pause ||
+	    regs.user_arg0 != 0 || regs.user_arg1 != 0 ||
+	    regs.user_arg2 != 0 || regs.user_arg3 != 0 ||
+	    regs.user_arg4 != 0 || regs.user_arg5 != 0) {
+		printf("[FAIL]\tArgs after SIGUSR1 are wrong (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n", (unsigned long)regs.user_syscall_nr, (unsigned long)regs.user_arg0, (unsigned long)regs.user_arg1, (unsigned long)regs.user_arg2, (unsigned long)regs.user_arg3, (unsigned long)regs.user_arg4, (unsigned long)regs.user_arg5);
+		nerrs++;
+	} else {
+		printf("[OK]\tArgs after SIGUSR1 are correct (ax = %ld)\n",
+		       (long)regs.user_ax);
+	}
+
+	/* Poke the regs back in.  This must not break anything. */
+	if (ptrace(PTRACE_SETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_SETREGS");
+
+	/* Catch the (ignored) SIGUSR1. */
+	if (ptrace(PTRACE_CONT, chld, 0, 0) != 0)
+		err(1, "PTRACE_CONT");
+	if (waitpid(chld, &status, 0) != chld)
+		err(1, "waitpid");
+	if (!WIFSTOPPED(status)) {
+		printf("[FAIL]\tChild was stopped for SIGUSR1 (status = 0x%x)\n", status);
+		nerrs++;
+	} else {
+		printf("[OK]\tChild got SIGUSR1\n");
+	}
+
+	/* The next event should be pause(2) again. */
+	printf("[RUN]\tStep again\n");
+	if (ptrace(PTRACE_SYSCALL, chld, 0, 0) != 0)
+		err(1, "PTRACE_SYSCALL");
+	wait_trap(chld);
+
+	/* We should be stopped at pause(2) entry. */
+
+	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_GETREGS");
+
+	if (regs.user_syscall_nr != SYS_pause ||
+	    regs.user_arg0 != 0 || regs.user_arg1 != 0 ||
+	    regs.user_arg2 != 0 || regs.user_arg3 != 0 ||
+	    regs.user_arg4 != 0 || regs.user_arg5 != 0) {
+		printf("[FAIL]\tpause did not restart (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n", (unsigned long)regs.user_syscall_nr, (unsigned long)regs.user_arg0, (unsigned long)regs.user_arg1, (unsigned long)regs.user_arg2, (unsigned long)regs.user_arg3, (unsigned long)regs.user_arg4, (unsigned long)regs.user_arg5);
+		nerrs++;
+	} else {
+		printf("[OK]\tpause(2) restarted correctly\n");
+	}
+
+	/* Kill it. */
+	kill(chld, SIGKILL);
+	if (waitpid(chld, &status, 0) != chld)
+		err(1, "waitpid");
+}
+
 int main()
 {
 	printf("[RUN]\tCheck int80 return regs\n");
@@ -290,5 +414,7 @@ int main()
 
 	test_ptrace_syscall_restart();
 
+	test_restart_under_ptrace();
+
 	return 0;
 }
diff --git a/tools/testing/selftests/x86/sigreturn.c b/tools/testing/selftests/x86/sigreturn.c
index b5aa1bab7416..8a577e7070c6 100644
--- a/tools/testing/selftests/x86/sigreturn.c
+++ b/tools/testing/selftests/x86/sigreturn.c
@@ -54,6 +54,37 @@
 #include <sys/ptrace.h>
 #include <sys/user.h>
 
+/* Pull in AR_xyz defines. */
+typedef unsigned int u32;
+typedef unsigned short u16;
+#include "../../../../arch/x86/include/asm/desc_defs.h"
+
+/*
+ * Copied from asm/ucontext.h, as asm/ucontext.h conflicts badly with the glibc
+ * headers.
+ */
+#ifdef __x86_64__
+/*
+ * UC_SIGCONTEXT_SS will be set when delivering 64-bit or x32 signals on
+ * kernels that save SS in the sigcontext.  All kernels that set
+ * UC_SIGCONTEXT_SS will correctly restore at least the low 32 bits of esp
+ * regardless of SS (i.e. they implement espfix).
+ *
+ * Kernels that set UC_SIGCONTEXT_SS will also set UC_STRICT_RESTORE_SS
+ * when delivering a signal that came from 64-bit code.
+ *
+ * Sigreturn restores SS as follows:
+ *
+ * if (saved SS is valid || UC_STRICT_RESTORE_SS is set ||
+ *     saved CS is not 64-bit)
+ *         new SS = saved SS  (will fail IRET and signal if invalid)
+ * else
+ *         new SS = a flat 32-bit data segment
+ */
+#define UC_SIGCONTEXT_SS       0x2
+#define UC_STRICT_RESTORE_SS   0x4
+#endif
+
 /*
  * In principle, this test can run on Linux emulation layers (e.g.
  * Illumos "LX branded zones").  Solaris-based kernels reserve LDT
@@ -267,6 +298,9 @@ static gregset_t initial_regs, requested_regs, resulting_regs;
 /* Instructions for the SIGUSR1 handler. */
 static volatile unsigned short sig_cs, sig_ss;
 static volatile sig_atomic_t sig_trapped, sig_err, sig_trapno;
+#ifdef __x86_64__
+static volatile sig_atomic_t sig_corrupt_final_ss;
+#endif
 
 /* Abstractions for some 32-bit vs 64-bit differences. */
 #ifdef __x86_64__
@@ -305,9 +339,105 @@ static greg_t *csptr(ucontext_t *ctx)
 }
 #endif
 
+/*
+ * Checks a given selector for its code bitness or returns -1 if it's not
+ * a usable code segment selector.
+ */
+int cs_bitness(unsigned short cs)
+{
+	uint32_t valid = 0, ar;
+	asm ("lar %[cs], %[ar]\n\t"
+	     "jnz 1f\n\t"
+	     "mov $1, %[valid]\n\t"
+	     "1:"
+	     : [ar] "=r" (ar), [valid] "+rm" (valid)
+	     : [cs] "r" (cs));
+
+	if (!valid)
+		return -1;
+
+	bool db = (ar & (1 << 22));
+	bool l = (ar & (1 << 21));
+
+	if (!(ar & (1<<11)))
+	    return -1;	/* Not code. */
+
+	if (l && !db)
+		return 64;
+	else if (!l && db)
+		return 32;
+	else if (!l && !db)
+		return 16;
+	else
+		return -1;	/* Unknown bitness. */
+}
+
+/*
+ * Checks a given selector for its code bitness or returns -1 if it's not
+ * a usable code segment selector.
+ */
+bool is_valid_ss(unsigned short cs)
+{
+	uint32_t valid = 0, ar;
+	asm ("lar %[cs], %[ar]\n\t"
+	     "jnz 1f\n\t"
+	     "mov $1, %[valid]\n\t"
+	     "1:"
+	     : [ar] "=r" (ar), [valid] "+rm" (valid)
+	     : [cs] "r" (cs));
+
+	if (!valid)
+		return false;
+
+	if ((ar & AR_TYPE_MASK) != AR_TYPE_RWDATA &&
+	    (ar & AR_TYPE_MASK) != AR_TYPE_RWDATA_EXPDOWN)
+		return false;
+
+	return (ar & AR_P);
+}
+
 /* Number of errors in the current test case. */
 static volatile sig_atomic_t nerrs;
 
+static void validate_signal_ss(int sig, ucontext_t *ctx)
+{
+#ifdef __x86_64__
+	bool was_64bit = (cs_bitness(*csptr(ctx)) == 64);
+
+	if (!(ctx->uc_flags & UC_SIGCONTEXT_SS)) {
+		printf("[FAIL]\tUC_SIGCONTEXT_SS was not set\n");
+		nerrs++;
+
+		/*
+		 * This happens on Linux 4.1.  The rest will fail, too, so
+		 * return now to reduce the noise.
+		 */
+		return;
+	}
+
+	/* UC_STRICT_RESTORE_SS is set iff we came from 64-bit mode. */
+	if (!!(ctx->uc_flags & UC_STRICT_RESTORE_SS) != was_64bit) {
+		printf("[FAIL]\tUC_STRICT_RESTORE_SS was wrong in signal %d\n",
+		       sig);
+		nerrs++;
+	}
+
+	if (is_valid_ss(*ssptr(ctx))) {
+		/*
+		 * DOSEMU was written before 64-bit sigcontext had SS, and
+		 * it tries to figure out the signal source SS by looking at
+		 * the physical register.  Make sure that keeps working.
+		 */
+		unsigned short hw_ss;
+		asm ("mov %%ss, %0" : "=rm" (hw_ss));
+		if (hw_ss != *ssptr(ctx)) {
+			printf("[FAIL]\tHW SS didn't match saved SS\n");
+			nerrs++;
+		}
+	}
+#endif
+}
+
 /*
  * SIGUSR1 handler.  Sets CS and SS as requested and points IP to the
  * int3 trampoline.  Sets SP to a large known value so that we can see
@@ -317,6 +447,8 @@ static void sigusr1(int sig, siginfo_t *info, void *ctx_void)
 {
 	ucontext_t *ctx = (ucontext_t*)ctx_void;
 
+	validate_signal_ss(sig, ctx);
+
 	memcpy(&initial_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t));
 
 	*csptr(ctx) = sig_cs;
@@ -334,13 +466,16 @@ static void sigusr1(int sig, siginfo_t *info, void *ctx_void)
 }
 
 /*
- * Called after a successful sigreturn.  Restores our state so that
- * the original raise(SIGUSR1) returns.
+ * Called after a successful sigreturn (via int3) or from a failed
+ * sigreturn (directly by kernel).  Restores our state so that the
+ * original raise(SIGUSR1) returns.
  */
 static void sigtrap(int sig, siginfo_t *info, void *ctx_void)
 {
 	ucontext_t *ctx = (ucontext_t*)ctx_void;
 
+	validate_signal_ss(sig, ctx);
+
 	sig_err = ctx->uc_mcontext.gregs[REG_ERR];
 	sig_trapno = ctx->uc_mcontext.gregs[REG_TRAPNO];
 
@@ -358,41 +493,62 @@ static void sigtrap(int sig, siginfo_t *info, void *ctx_void)
 	memcpy(&resulting_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t));
 	memcpy(&ctx->uc_mcontext.gregs, &initial_regs, sizeof(gregset_t));
 
+#ifdef __x86_64__
+	if (sig_corrupt_final_ss) {
+		if (ctx->uc_flags & UC_STRICT_RESTORE_SS) {
+			printf("[FAIL]\tUC_STRICT_RESTORE_SS was set inappropriately\n");
+			nerrs++;
+		} else {
+			/*
+			 * DOSEMU transitions from 32-bit to 64-bit mode by
+			 * adjusting sigcontext, and it requires that this work
+			 * even if the saved SS is bogus.
+			 */
+			printf("\tCorrupting SS on return to 64-bit mode\n");
+			*ssptr(ctx) = 0;
+		}
+	}
+#endif
+
 	sig_trapped = sig;
 }
 
-/*
- * Checks a given selector for its code bitness or returns -1 if it's not
- * a usable code segment selector.
- */
-int cs_bitness(unsigned short cs)
+#ifdef __x86_64__
+/* Tests recovery if !UC_STRICT_RESTORE_SS */
+static void sigusr2(int sig, siginfo_t *info, void *ctx_void)
 {
-	uint32_t valid = 0, ar;
-	asm ("lar %[cs], %[ar]\n\t"
-	     "jnz 1f\n\t"
-	     "mov $1, %[valid]\n\t"
-	     "1:"
-	     : [ar] "=r" (ar), [valid] "+rm" (valid)
-	     : [cs] "r" (cs));
+	ucontext_t *ctx = (ucontext_t*)ctx_void;
 
-	if (!valid)
-		return -1;
+	if (!(ctx->uc_flags & UC_STRICT_RESTORE_SS)) {
+		printf("[FAIL]\traise(2) didn't set UC_STRICT_RESTORE_SS\n");
+		nerrs++;
+		return;  /* We can't do the rest. */
+	}
 
-	bool db = (ar & (1 << 22));
-	bool l = (ar & (1 << 21));
+	ctx->uc_flags &= ~UC_STRICT_RESTORE_SS;
+	*ssptr(ctx) = 0;
 
-	if (!(ar & (1<<11)))
-	    return -1;	/* Not code. */
+	/* Return.  The kernel should recover without sending another signal. */
+}
 
-	if (l && !db)
-		return 64;
-	else if (!l && db)
-		return 32;
-	else if (!l && !db)
-		return 16;
-	else
-		return -1;	/* Unknown bitness. */
+static int test_nonstrict_ss(void)
+{
+	clearhandler(SIGUSR1);
+	clearhandler(SIGTRAP);
+	clearhandler(SIGSEGV);
+	clearhandler(SIGILL);
+	sethandler(SIGUSR2, sigusr2, 0);
+
+	nerrs = 0;
+
+	printf("[RUN]\tClear UC_STRICT_RESTORE_SS and corrupt SS\n");
+	raise(SIGUSR2);
+	if (!nerrs)
+		printf("[OK]\tIt worked\n");
+
+	return nerrs;
 }
+#endif
 
 /* Finds a usable code segment of the requested bitness. */
 int find_cs(int bitness)
@@ -576,6 +732,12 @@ static int test_bad_iret(int cs_bits, unsigned short ss, int force_cs)
 		       errdesc, strsignal(sig_trapped));
 		return 0;
 	} else {
+		/*
+		 * This also implicitly tests UC_STRICT_RESTORE_SS:
+		 * We check that these signals set UC_STRICT_RESTORE_SS and,
+		 * if UC_STRICT_RESTORE_SS doesn't cause strict behavior,
+		 * then we won't get SIGSEGV.
+		 */
 		printf("[FAIL]\tDid not get SIGSEGV\n");
 		return 1;
 	}
@@ -632,6 +794,14 @@ int main()
 						    GDT3(gdt_data16_idx));
 	}
 
+#ifdef __x86_64__
+	/* Nasty ABI case: check SS corruption handling. */
+	sig_corrupt_final_ss = 1;
+	total_nerrs += test_valid_sigreturn(32, false, -1);
+	total_nerrs += test_valid_sigreturn(32, true, -1);
+	sig_corrupt_final_ss = 0;
+#endif
+
 	/*
 	 * We're done testing valid sigreturn cases.  Now we test states
 	 * for which sigreturn itself will succeed but the subsequent
@@ -680,5 +850,9 @@ int main()
 	if (gdt_npdata32_idx)
 		test_bad_iret(32, GDT3(gdt_npdata32_idx), -1);
 
+#ifdef __x86_64__
+	total_nerrs += test_nonstrict_ss();
+#endif
+
 	return total_nerrs ? 1 : 0;
 }
diff --git a/tools/testing/selftests/x86/syscall_nt.c b/tools/testing/selftests/x86/syscall_nt.c
index 60c06af4646a..43fcab367fb0 100644
--- a/tools/testing/selftests/x86/syscall_nt.c
+++ b/tools/testing/selftests/x86/syscall_nt.c
@@ -17,6 +17,9 @@
 
 #include <stdio.h>
 #include <unistd.h>
+#include <string.h>
+#include <signal.h>
+#include <err.h>
 #include <sys/syscall.h>
 #include <asm/processor-flags.h>
 
@@ -26,6 +29,8 @@
 # define WIDTH "l"
 #endif
 
+static unsigned int nerrs;
+
 static unsigned long get_eflags(void)
 {
 	unsigned long eflags;
@@ -39,16 +44,52 @@ static void set_eflags(unsigned long eflags)
 		      : : "rm" (eflags) : "flags");
 }
 
-int main()
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+		       int flags)
 {
-	printf("[RUN]\tSet NT and issue a syscall\n");
-	set_eflags(get_eflags() | X86_EFLAGS_NT);
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+static void sigtrap(int sig, siginfo_t *si, void *ctx_void)
+{
+}
+
+static void do_it(unsigned long extraflags)
+{
+	unsigned long flags;
+
+	set_eflags(get_eflags() | extraflags);
 	syscall(SYS_getpid);
-	if (get_eflags() & X86_EFLAGS_NT) {
-		printf("[OK]\tThe syscall worked and NT is still set\n");
-		return 0;
+	flags = get_eflags();
+	if ((flags & extraflags) == extraflags) {
+		printf("[OK]\tThe syscall worked and flags are still set\n");
 	} else {
-		printf("[FAIL]\tThe syscall worked but NT was cleared\n");
-		return 1;
+		printf("[FAIL]\tThe syscall worked but flags were cleared (flags = 0x%lx but expected 0x%lx set)\n",
+		       flags, extraflags);
+		nerrs++;
 	}
 }
+
+int main(void)
+{
+	printf("[RUN]\tSet NT and issue a syscall\n");
+	do_it(X86_EFLAGS_NT);
+
+	/*
+	 * Now try it again with TF set -- TF forces returns via IRET in all
+	 * cases except non-ptregs-using 64-bit full fast path syscalls.
+	 */
+
+	sethandler(SIGTRAP, sigtrap, 0);
+
+	printf("[RUN]\tSet NT|TF and issue a syscall\n");
+	do_it(X86_EFLAGS_NT | X86_EFLAGS_TF);
+
+	return nerrs == 0 ? 0 : 1;
+}
diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
index 86e698d07e20..1889163f2f05 100644
--- a/tools/vm/slabinfo.c
+++ b/tools/vm/slabinfo.c
@@ -135,7 +135,7 @@ static void usage(void)
 		"\nValid debug options (FZPUT may be combined)\n"
 		"a / A          Switch on all debug options (=FZUP)\n"
 		"-              Switch off all debug options\n"
-		"f / F          Sanity Checks (SLAB_DEBUG_FREE)\n"
+		"f / F          Sanity Checks (SLAB_CONSISTENCY_CHECKS)\n"
 		"z / Z          Redzoning\n"
 		"p / P          Poisoning\n"
 		"u / U          Tracking\n"
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 69bca185c471..a9ad4fe3f68f 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -34,6 +34,11 @@ static struct timecounter *timecounter;
 static struct workqueue_struct *wqueue;
 static unsigned int host_vtimer_irq;
 
+void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.timer_cpu.active_cleared_last = false;
+}
+
 static cycle_t kvm_phys_timer_read(void)
 {
 	return timecounter->cc->read(timecounter->cc);
@@ -130,6 +135,7 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level)
 
 	BUG_ON(!vgic_initialized(vcpu->kvm));
 
+	timer->active_cleared_last = false;
 	timer->irq.level = new_level;
 	trace_kvm_timer_update_irq(vcpu->vcpu_id, timer->map->virt_irq,
 				   timer->irq.level);
@@ -143,7 +149,7 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level)
  * Check if there was a change in the timer state (should we raise or lower
  * the line level to the GIC).
  */
-static void kvm_timer_update_state(struct kvm_vcpu *vcpu)
+static int kvm_timer_update_state(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
 
@@ -154,10 +160,12 @@ static void kvm_timer_update_state(struct kvm_vcpu *vcpu)
 	 * until we call this function from kvm_timer_flush_hwstate.
 	 */
 	if (!vgic_initialized(vcpu->kvm))
-	    return;
+		return -ENODEV;
 
 	if (kvm_timer_should_fire(vcpu) != timer->irq.level)
 		kvm_timer_update_irq(vcpu, !timer->irq.level);
+
+	return 0;
 }
 
 /*
@@ -218,7 +226,8 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
 	bool phys_active;
 	int ret;
 
-	kvm_timer_update_state(vcpu);
+	if (kvm_timer_update_state(vcpu))
+		return;
 
 	/*
 	* If we enter the guest with the virtual input level to the VGIC
@@ -242,10 +251,35 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
 	else
 		phys_active = false;
 
+	/*
+	 * We want to avoid hitting the (re)distributor as much as
+	 * possible, as this is a potentially expensive MMIO access
+	 * (not to mention locks in the irq layer), and a solution for
+	 * this is to cache the "active" state in memory.
+	 *
+	 * Things to consider: we cannot cache an "active set" state,
+	 * because the HW can change this behind our back (it becomes
+	 * "clear" in the HW). We must then restrict the caching to
+	 * the "clear" state.
+	 *
+	 * The cache is invalidated on:
+	 * - vcpu put, indicating that the HW cannot be trusted to be
+	 *   in a sane state on the next vcpu load,
+	 * - any change in the interrupt state
+	 *
+	 * Usage conditions:
+	 * - cached value is "active clear"
+	 * - value to be programmed is "active clear"
+	 */
+	if (timer->active_cleared_last && !phys_active)
+		return;
+
 	ret = irq_set_irqchip_state(timer->map->irq,
 				    IRQCHIP_STATE_ACTIVE,
 				    phys_active);
 	WARN_ON(ret);
+
+	timer->active_cleared_last = !phys_active;
 }
 
 /**
diff --git a/arch/arm64/kvm/hyp/timer-sr.c b/virt/kvm/arm/hyp/timer-sr.c
index 1051e5d7320f..ea00d69e7078 100644
--- a/arch/arm64/kvm/hyp/timer-sr.c
+++ b/virt/kvm/arm/hyp/timer-sr.c
@@ -19,9 +19,7 @@
 #include <linux/compiler.h>
 #include <linux/kvm_host.h>
 
-#include <asm/kvm_mmu.h>
-
-#include "hyp.h"
+#include <asm/kvm_hyp.h>
 
 /* vcpu is already in the HYP VA space */
 void __hyp_text __timer_save_state(struct kvm_vcpu *vcpu)
@@ -31,12 +29,12 @@ void __hyp_text __timer_save_state(struct kvm_vcpu *vcpu)
 	u64 val;
 
 	if (kvm->arch.timer.enabled) {
-		timer->cntv_ctl = read_sysreg(cntv_ctl_el0);
-		timer->cntv_cval = read_sysreg(cntv_cval_el0);
+		timer->cntv_ctl = read_sysreg_el0(cntv_ctl);
+		timer->cntv_cval = read_sysreg_el0(cntv_cval);
 	}
 
 	/* Disable the virtual timer */
-	write_sysreg(0, cntv_ctl_el0);
+	write_sysreg_el0(0, cntv_ctl);
 
 	/* Allow physical timer/counter access for the host */
 	val = read_sysreg(cnthctl_el2);
@@ -64,8 +62,8 @@ void __hyp_text __timer_restore_state(struct kvm_vcpu *vcpu)
 
 	if (kvm->arch.timer.enabled) {
 		write_sysreg(kvm->arch.timer.cntvoff, cntvoff_el2);
-		write_sysreg(timer->cntv_cval, cntv_cval_el0);
+		write_sysreg_el0(timer->cntv_cval, cntv_cval);
 		isb();
-		write_sysreg(timer->cntv_ctl, cntv_ctl_el0);
+		write_sysreg_el0(timer->cntv_ctl, cntv_ctl);
 	}
 }
diff --git a/virt/kvm/arm/hyp/vgic-v2-sr.c b/virt/kvm/arm/hyp/vgic-v2-sr.c
new file mode 100644
index 000000000000..674bdf8ecf4f
--- /dev/null
+++ b/virt/kvm/arm/hyp/vgic-v2-sr.c
@@ -0,0 +1,170 @@
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/compiler.h>
+#include <linux/irqchip/arm-gic.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_hyp.h>
+
+static void __hyp_text save_maint_int_state(struct kvm_vcpu *vcpu,
+					    void __iomem *base)
+{
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	int nr_lr = vcpu->arch.vgic_cpu.nr_lr;
+	u32 eisr0, eisr1;
+	int i;
+	bool expect_mi;
+
+	expect_mi = !!(cpu_if->vgic_hcr & GICH_HCR_UIE);
+
+	for (i = 0; i < nr_lr; i++) {
+		if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
+				continue;
+
+		expect_mi |= (!(cpu_if->vgic_lr[i] & GICH_LR_HW) &&
+			      (cpu_if->vgic_lr[i] & GICH_LR_EOI));
+	}
+
+	if (expect_mi) {
+		cpu_if->vgic_misr = readl_relaxed(base + GICH_MISR);
+
+		if (cpu_if->vgic_misr & GICH_MISR_EOI) {
+			eisr0  = readl_relaxed(base + GICH_EISR0);
+			if (unlikely(nr_lr > 32))
+				eisr1  = readl_relaxed(base + GICH_EISR1);
+			else
+				eisr1 = 0;
+		} else {
+			eisr0 = eisr1 = 0;
+		}
+	} else {
+		cpu_if->vgic_misr = 0;
+		eisr0 = eisr1 = 0;
+	}
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	cpu_if->vgic_eisr = ((u64)eisr0 << 32) | eisr1;
+#else
+	cpu_if->vgic_eisr = ((u64)eisr1 << 32) | eisr0;
+#endif
+}
+
+static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base)
+{
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	int nr_lr = vcpu->arch.vgic_cpu.nr_lr;
+	u32 elrsr0, elrsr1;
+
+	elrsr0 = readl_relaxed(base + GICH_ELRSR0);
+	if (unlikely(nr_lr > 32))
+		elrsr1 = readl_relaxed(base + GICH_ELRSR1);
+	else
+		elrsr1 = 0;
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	cpu_if->vgic_elrsr = ((u64)elrsr0 << 32) | elrsr1;
+#else
+	cpu_if->vgic_elrsr = ((u64)elrsr1 << 32) | elrsr0;
+#endif
+}
+
+static void __hyp_text save_lrs(struct kvm_vcpu *vcpu, void __iomem *base)
+{
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	int nr_lr = vcpu->arch.vgic_cpu.nr_lr;
+	int i;
+
+	for (i = 0; i < nr_lr; i++) {
+		if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
+			continue;
+
+		if (cpu_if->vgic_elrsr & (1UL << i)) {
+			cpu_if->vgic_lr[i] &= ~GICH_LR_STATE;
+			continue;
+		}
+
+		cpu_if->vgic_lr[i] = readl_relaxed(base + GICH_LR0 + (i * 4));
+		writel_relaxed(0, base + GICH_LR0 + (i * 4));
+	}
+}
+
+/* vcpu is already in the HYP VA space */
+void __hyp_text __vgic_v2_save_state(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	struct vgic_dist *vgic = &kvm->arch.vgic;
+	void __iomem *base = kern_hyp_va(vgic->vctrl_base);
+
+	if (!base)
+		return;
+
+	cpu_if->vgic_vmcr = readl_relaxed(base + GICH_VMCR);
+
+	if (vcpu->arch.vgic_cpu.live_lrs) {
+		cpu_if->vgic_apr = readl_relaxed(base + GICH_APR);
+
+		save_maint_int_state(vcpu, base);
+		save_elrsr(vcpu, base);
+		save_lrs(vcpu, base);
+
+		writel_relaxed(0, base + GICH_HCR);
+
+		vcpu->arch.vgic_cpu.live_lrs = 0;
+	} else {
+		cpu_if->vgic_eisr = 0;
+		cpu_if->vgic_elrsr = ~0UL;
+		cpu_if->vgic_misr = 0;
+		cpu_if->vgic_apr = 0;
+	}
+}
+
+/* vcpu is already in the HYP VA space */
+void __hyp_text __vgic_v2_restore_state(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+	struct vgic_dist *vgic = &kvm->arch.vgic;
+	void __iomem *base = kern_hyp_va(vgic->vctrl_base);
+	int i, nr_lr;
+	u64 live_lrs = 0;
+
+	if (!base)
+		return;
+
+	nr_lr = vcpu->arch.vgic_cpu.nr_lr;
+
+	for (i = 0; i < nr_lr; i++)
+		if (cpu_if->vgic_lr[i] & GICH_LR_STATE)
+			live_lrs |= 1UL << i;
+
+	if (live_lrs) {
+		writel_relaxed(cpu_if->vgic_hcr, base + GICH_HCR);
+		writel_relaxed(cpu_if->vgic_apr, base + GICH_APR);
+		for (i = 0; i < nr_lr; i++) {
+			if (!(live_lrs & (1UL << i)))
+				continue;
+
+			writel_relaxed(cpu_if->vgic_lr[i],
+				       base + GICH_LR0 + (i * 4));
+		}
+	}
+
+	writel_relaxed(cpu_if->vgic_vmcr, base + GICH_VMCR);
+	vcpu->arch.vgic_cpu.live_lrs = live_lrs;
+}
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
new file mode 100644
index 000000000000..b5754c6c5508
--- /dev/null
+++ b/virt/kvm/arm/pmu.c
@@ -0,0 +1,529 @@
+/*
+ * Copyright (C) 2015 Linaro Ltd.
+ * Author: Shannon Zhao <shannon.zhao@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/cpu.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/perf_event.h>
+#include <linux/uaccess.h>
+#include <asm/kvm_emulate.h>
+#include <kvm/arm_pmu.h>
+#include <kvm/arm_vgic.h>
+
+/**
+ * kvm_pmu_get_counter_value - get PMU counter value
+ * @vcpu: The vcpu pointer
+ * @select_idx: The counter index
+ */
+u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
+{
+	u64 counter, reg, enabled, running;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
+
+	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
+	      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx;
+	counter = vcpu_sys_reg(vcpu, reg);
+
+	/* The real counter value is equal to the value of counter register plus
+	 * the value perf event counts.
+	 */
+	if (pmc->perf_event)
+		counter += perf_event_read_value(pmc->perf_event, &enabled,
+						 &running);
+
+	return counter & pmc->bitmask;
+}
+
+/**
+ * kvm_pmu_set_counter_value - set PMU counter value
+ * @vcpu: The vcpu pointer
+ * @select_idx: The counter index
+ * @val: The counter value
+ */
+void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
+{
+	u64 reg;
+
+	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
+	      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx;
+	vcpu_sys_reg(vcpu, reg) += (s64)val - kvm_pmu_get_counter_value(vcpu, select_idx);
+}
+
+/**
+ * kvm_pmu_stop_counter - stop PMU counter
+ * @pmc: The PMU counter pointer
+ *
+ * If this counter has been configured to monitor some event, release it here.
+ */
+static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
+{
+	u64 counter, reg;
+
+	if (pmc->perf_event) {
+		counter = kvm_pmu_get_counter_value(vcpu, pmc->idx);
+		reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
+		       ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx;
+		vcpu_sys_reg(vcpu, reg) = counter;
+		perf_event_disable(pmc->perf_event);
+		perf_event_release_kernel(pmc->perf_event);
+		pmc->perf_event = NULL;
+	}
+}
+
+/**
+ * kvm_pmu_vcpu_reset - reset pmu state for cpu
+ * @vcpu: The vcpu pointer
+ *
+ */
+void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu)
+{
+	int i;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+
+	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
+		kvm_pmu_stop_counter(vcpu, &pmu->pmc[i]);
+		pmu->pmc[i].idx = i;
+		pmu->pmc[i].bitmask = 0xffffffffUL;
+	}
+}
+
+/**
+ * kvm_pmu_vcpu_destroy - free perf event of PMU for cpu
+ * @vcpu: The vcpu pointer
+ *
+ */
+void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+	int i;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+
+	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
+		struct kvm_pmc *pmc = &pmu->pmc[i];
+
+		if (pmc->perf_event) {
+			perf_event_disable(pmc->perf_event);
+			perf_event_release_kernel(pmc->perf_event);
+			pmc->perf_event = NULL;
+		}
+	}
+}
+
+u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
+{
+	u64 val = vcpu_sys_reg(vcpu, PMCR_EL0) >> ARMV8_PMU_PMCR_N_SHIFT;
+
+	val &= ARMV8_PMU_PMCR_N_MASK;
+	if (val == 0)
+		return BIT(ARMV8_PMU_CYCLE_IDX);
+	else
+		return GENMASK(val - 1, 0) | BIT(ARMV8_PMU_CYCLE_IDX);
+}
+
+/**
+ * kvm_pmu_enable_counter - enable selected PMU counter
+ * @vcpu: The vcpu pointer
+ * @val: the value guest writes to PMCNTENSET register
+ *
+ * Call perf_event_enable to start counting the perf event
+ */
+void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val)
+{
+	int i;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc;
+
+	if (!(vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) || !val)
+		return;
+
+	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
+		if (!(val & BIT(i)))
+			continue;
+
+		pmc = &pmu->pmc[i];
+		if (pmc->perf_event) {
+			perf_event_enable(pmc->perf_event);
+			if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE)
+				kvm_debug("fail to enable perf event\n");
+		}
+	}
+}
+
+/**
+ * kvm_pmu_disable_counter - disable selected PMU counter
+ * @vcpu: The vcpu pointer
+ * @val: the value guest writes to PMCNTENCLR register
+ *
+ * Call perf_event_disable to stop counting the perf event
+ */
+void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val)
+{
+	int i;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc;
+
+	if (!val)
+		return;
+
+	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
+		if (!(val & BIT(i)))
+			continue;
+
+		pmc = &pmu->pmc[i];
+		if (pmc->perf_event)
+			perf_event_disable(pmc->perf_event);
+	}
+}
+
+static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu)
+{
+	u64 reg = 0;
+
+	if ((vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E))
+		reg = vcpu_sys_reg(vcpu, PMOVSSET_EL0);
+		reg &= vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
+		reg &= vcpu_sys_reg(vcpu, PMINTENSET_EL1);
+		reg &= kvm_pmu_valid_counter_mask(vcpu);
+
+	return reg;
+}
+
+/**
+ * kvm_pmu_overflow_set - set PMU overflow interrupt
+ * @vcpu: The vcpu pointer
+ * @val: the value guest writes to PMOVSSET register
+ */
+void kvm_pmu_overflow_set(struct kvm_vcpu *vcpu, u64 val)
+{
+	u64 reg;
+
+	if (val == 0)
+		return;
+
+	vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= val;
+	reg = kvm_pmu_overflow_status(vcpu);
+	if (reg != 0)
+		kvm_vcpu_kick(vcpu);
+}
+
+static void kvm_pmu_update_state(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	bool overflow;
+
+	if (!kvm_arm_pmu_v3_ready(vcpu))
+		return;
+
+	overflow = !!kvm_pmu_overflow_status(vcpu);
+	if (pmu->irq_level != overflow) {
+		pmu->irq_level = overflow;
+		kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
+				    pmu->irq_num, overflow);
+	}
+}
+
+/**
+ * kvm_pmu_flush_hwstate - flush pmu state to cpu
+ * @vcpu: The vcpu pointer
+ *
+ * Check if the PMU has overflowed while we were running in the host, and inject
+ * an interrupt if that was the case.
+ */
+void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu)
+{
+	kvm_pmu_update_state(vcpu);
+}
+
+/**
+ * kvm_pmu_sync_hwstate - sync pmu state from cpu
+ * @vcpu: The vcpu pointer
+ *
+ * Check if the PMU has overflowed while we were running in the guest, and
+ * inject an interrupt if that was the case.
+ */
+void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu)
+{
+	kvm_pmu_update_state(vcpu);
+}
+
+static inline struct kvm_vcpu *kvm_pmc_to_vcpu(struct kvm_pmc *pmc)
+{
+	struct kvm_pmu *pmu;
+	struct kvm_vcpu_arch *vcpu_arch;
+
+	pmc -= pmc->idx;
+	pmu = container_of(pmc, struct kvm_pmu, pmc[0]);
+	vcpu_arch = container_of(pmu, struct kvm_vcpu_arch, pmu);
+	return container_of(vcpu_arch, struct kvm_vcpu, arch);
+}
+
+/**
+ * When perf event overflows, call kvm_pmu_overflow_set to set overflow status.
+ */
+static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
+				  struct perf_sample_data *data,
+				  struct pt_regs *regs)
+{
+	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
+	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
+	int idx = pmc->idx;
+
+	kvm_pmu_overflow_set(vcpu, BIT(idx));
+}
+
+/**
+ * kvm_pmu_software_increment - do software increment
+ * @vcpu: The vcpu pointer
+ * @val: the value guest writes to PMSWINC register
+ */
+void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
+{
+	int i;
+	u64 type, enable, reg;
+
+	if (val == 0)
+		return;
+
+	enable = vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
+	for (i = 0; i < ARMV8_PMU_CYCLE_IDX; i++) {
+		if (!(val & BIT(i)))
+			continue;
+		type = vcpu_sys_reg(vcpu, PMEVTYPER0_EL0 + i)
+		       & ARMV8_PMU_EVTYPE_EVENT;
+		if ((type == ARMV8_PMU_EVTYPE_EVENT_SW_INCR)
+		    && (enable & BIT(i))) {
+			reg = vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) + 1;
+			reg = lower_32_bits(reg);
+			vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) = reg;
+			if (!reg)
+				kvm_pmu_overflow_set(vcpu, BIT(i));
+		}
+	}
+}
+
+/**
+ * kvm_pmu_handle_pmcr - handle PMCR register
+ * @vcpu: The vcpu pointer
+ * @val: the value guest writes to PMCR register
+ */
+void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
+{
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc;
+	u64 mask;
+	int i;
+
+	mask = kvm_pmu_valid_counter_mask(vcpu);
+	if (val & ARMV8_PMU_PMCR_E) {
+		kvm_pmu_enable_counter(vcpu,
+				vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask);
+	} else {
+		kvm_pmu_disable_counter(vcpu, mask);
+	}
+
+	if (val & ARMV8_PMU_PMCR_C)
+		kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0);
+
+	if (val & ARMV8_PMU_PMCR_P) {
+		for (i = 0; i < ARMV8_PMU_CYCLE_IDX; i++)
+			kvm_pmu_set_counter_value(vcpu, i, 0);
+	}
+
+	if (val & ARMV8_PMU_PMCR_LC) {
+		pmc = &pmu->pmc[ARMV8_PMU_CYCLE_IDX];
+		pmc->bitmask = 0xffffffffffffffffUL;
+	}
+}
+
+static bool kvm_pmu_counter_is_enabled(struct kvm_vcpu *vcpu, u64 select_idx)
+{
+	return (vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) &&
+	       (vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(select_idx));
+}
+
+/**
+ * kvm_pmu_set_counter_event_type - set selected counter to monitor some event
+ * @vcpu: The vcpu pointer
+ * @data: The data guest writes to PMXEVTYPER_EL0
+ * @select_idx: The number of selected counter
+ *
+ * When OS accesses PMXEVTYPER_EL0, that means it wants to set a PMC to count an
+ * event with given hardware event number. Here we call perf_event API to
+ * emulate this action and create a kernel perf event for it.
+ */
+void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
+				    u64 select_idx)
+{
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
+	struct perf_event *event;
+	struct perf_event_attr attr;
+	u64 eventsel, counter;
+
+	kvm_pmu_stop_counter(vcpu, pmc);
+	eventsel = data & ARMV8_PMU_EVTYPE_EVENT;
+
+	/* Software increment event does't need to be backed by a perf event */
+	if (eventsel == ARMV8_PMU_EVTYPE_EVENT_SW_INCR)
+		return;
+
+	memset(&attr, 0, sizeof(struct perf_event_attr));
+	attr.type = PERF_TYPE_RAW;
+	attr.size = sizeof(attr);
+	attr.pinned = 1;
+	attr.disabled = !kvm_pmu_counter_is_enabled(vcpu, select_idx);
+	attr.exclude_user = data & ARMV8_PMU_EXCLUDE_EL0 ? 1 : 0;
+	attr.exclude_kernel = data & ARMV8_PMU_EXCLUDE_EL1 ? 1 : 0;
+	attr.exclude_hv = 1; /* Don't count EL2 events */
+	attr.exclude_host = 1; /* Don't count host events */
+	attr.config = eventsel;
+
+	counter = kvm_pmu_get_counter_value(vcpu, select_idx);
+	/* The initial sample period (overflow count) of an event. */
+	attr.sample_period = (-counter) & pmc->bitmask;
+
+	event = perf_event_create_kernel_counter(&attr, -1, current,
+						 kvm_pmu_perf_overflow, pmc);
+	if (IS_ERR(event)) {
+		pr_err_once("kvm: pmu event creation failed %ld\n",
+			    PTR_ERR(event));
+		return;
+	}
+
+	pmc->perf_event = event;
+}
+
+bool kvm_arm_support_pmu_v3(void)
+{
+	/*
+	 * Check if HW_PERF_EVENTS are supported by checking the number of
+	 * hardware performance counters. This could ensure the presence of
+	 * a physical PMU and CONFIG_PERF_EVENT is selected.
+	 */
+	return (perf_num_counters() > 0);
+}
+
+static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_arm_support_pmu_v3())
+		return -ENODEV;
+
+	if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features) ||
+	    !kvm_arm_pmu_irq_initialized(vcpu))
+		return -ENXIO;
+
+	if (kvm_arm_pmu_v3_ready(vcpu))
+		return -EBUSY;
+
+	kvm_pmu_vcpu_reset(vcpu);
+	vcpu->arch.pmu.ready = true;
+
+	return 0;
+}
+
+static bool irq_is_valid(struct kvm *kvm, int irq, bool is_ppi)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (!kvm_arm_pmu_irq_initialized(vcpu))
+			continue;
+
+		if (is_ppi) {
+			if (vcpu->arch.pmu.irq_num != irq)
+				return false;
+		} else {
+			if (vcpu->arch.pmu.irq_num == irq)
+				return false;
+		}
+	}
+
+	return true;
+}
+
+
+int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
+{
+	switch (attr->attr) {
+	case KVM_ARM_VCPU_PMU_V3_IRQ: {
+		int __user *uaddr = (int __user *)(long)attr->addr;
+		int irq;
+
+		if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
+			return -ENODEV;
+
+		if (get_user(irq, uaddr))
+			return -EFAULT;
+
+		/*
+		 * The PMU overflow interrupt could be a PPI or SPI, but for one
+		 * VM the interrupt type must be same for each vcpu. As a PPI,
+		 * the interrupt number is the same for all vcpus, while as an
+		 * SPI it must be a separate number per vcpu.
+		 */
+		if (irq < VGIC_NR_SGIS || irq >= vcpu->kvm->arch.vgic.nr_irqs ||
+		    !irq_is_valid(vcpu->kvm, irq, irq < VGIC_NR_PRIVATE_IRQS))
+			return -EINVAL;
+
+		if (kvm_arm_pmu_irq_initialized(vcpu))
+			return -EBUSY;
+
+		kvm_debug("Set kvm ARM PMU irq: %d\n", irq);
+		vcpu->arch.pmu.irq_num = irq;
+		return 0;
+	}
+	case KVM_ARM_VCPU_PMU_V3_INIT:
+		return kvm_arm_pmu_v3_init(vcpu);
+	}
+
+	return -ENXIO;
+}
+
+int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
+{
+	switch (attr->attr) {
+	case KVM_ARM_VCPU_PMU_V3_IRQ: {
+		int __user *uaddr = (int __user *)(long)attr->addr;
+		int irq;
+
+		if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
+			return -ENODEV;
+
+		if (!kvm_arm_pmu_irq_initialized(vcpu))
+			return -ENXIO;
+
+		irq = vcpu->arch.pmu.irq_num;
+		return put_user(irq, uaddr);
+	}
+	}
+
+	return -ENXIO;
+}
+
+int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
+{
+	switch (attr->attr) {
+	case KVM_ARM_VCPU_PMU_V3_IRQ:
+	case KVM_ARM_VCPU_PMU_V3_INIT:
+		if (kvm_arm_support_pmu_v3() &&
+		    test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
+			return 0;
+	}
+
+	return -ENXIO;
+}
diff --git a/virt/kvm/arm/vgic-v2-emul.c b/virt/kvm/arm/vgic-v2-emul.c
index 13907970d11c..1b0bee095427 100644
--- a/virt/kvm/arm/vgic-v2-emul.c
+++ b/virt/kvm/arm/vgic-v2-emul.c
@@ -321,6 +321,11 @@ static bool handle_mmio_sgi_clear(struct kvm_vcpu *vcpu,
 
 static const struct vgic_io_range vgic_dist_ranges[] = {
 	{
+		.base		= GIC_DIST_SOFTINT,
+		.len		= 4,
+		.handle_mmio	= handle_mmio_sgi_reg,
+	},
+	{
 		.base		= GIC_DIST_CTRL,
 		.len		= 12,
 		.bits_per_irq	= 0,
@@ -387,11 +392,6 @@ static const struct vgic_io_range vgic_dist_ranges[] = {
 		.handle_mmio	= handle_mmio_cfg_reg,
 	},
 	{
-		.base		= GIC_DIST_SOFTINT,
-		.len		= 4,
-		.handle_mmio	= handle_mmio_sgi_reg,
-	},
-	{
 		.base		= GIC_DIST_SGI_PENDING_CLEAR,
 		.len		= VGIC_NR_SGIS,
 		.handle_mmio	= handle_mmio_sgi_clear,
diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c
index ff02f08df74d..67ec334ce1d0 100644
--- a/virt/kvm/arm/vgic-v2.c
+++ b/virt/kvm/arm/vgic-v2.c
@@ -176,6 +176,15 @@ static const struct vgic_ops vgic_v2_ops = {
 
 static struct vgic_params vgic_v2_params;
 
+static void vgic_cpu_init_lrs(void *params)
+{
+	struct vgic_params *vgic = params;
+	int i;
+
+	for (i = 0; i < vgic->nr_lr; i++)
+		writel_relaxed(0, vgic->vctrl_base + GICH_LR0 + (i * 4));
+}
+
 /**
  * vgic_v2_probe - probe for a GICv2 compatible interrupt controller in DT
  * @node:	pointer to the DT node
@@ -257,6 +266,9 @@ int vgic_v2_probe(struct device_node *vgic_node,
 
 	vgic->type = VGIC_V2;
 	vgic->max_gic_vcpus = VGIC_V2_MAX_CPUS;
+
+	on_each_cpu(vgic_cpu_init_lrs, vgic, 1);
+
 	*ops = &vgic_v2_ops;
 	*params = vgic;
 	goto out;
diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c
index 453eafd4dd6e..999bdc6d9d9f 100644
--- a/virt/kvm/arm/vgic-v3.c
+++ b/virt/kvm/arm/vgic-v3.c
@@ -42,7 +42,7 @@ static u32 ich_vtr_el2;
 static struct vgic_lr vgic_v3_get_lr(const struct kvm_vcpu *vcpu, int lr)
 {
 	struct vgic_lr lr_desc;
-	u64 val = vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[VGIC_V3_LR_INDEX(lr)];
+	u64 val = vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr];
 
 	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
 		lr_desc.irq = val & ICH_LR_VIRTUALID_MASK;
@@ -106,7 +106,7 @@ static void vgic_v3_set_lr(struct kvm_vcpu *vcpu, int lr,
 		lr_val |= ((u64)lr_desc.hwirq) << ICH_LR_PHYS_ID_SHIFT;
 	}
 
-	vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[VGIC_V3_LR_INDEX(lr)] = lr_val;
+	vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = lr_val;
 
 	if (!(lr_desc.state & LR_STATE_MASK))
 		vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr |= (1U << lr);
@@ -216,6 +216,11 @@ static const struct vgic_ops vgic_v3_ops = {
 
 static struct vgic_params vgic_v3_params;
 
+static void vgic_cpu_init_lrs(void *params)
+{
+	kvm_call_hyp(__vgic_v3_init_lrs);
+}
+
 /**
  * vgic_v3_probe - probe for a GICv3 compatible interrupt controller in DT
  * @node:	pointer to the DT node
@@ -284,6 +289,8 @@ int vgic_v3_probe(struct device_node *vgic_node,
 	kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
 		 vcpu_res.start, vgic->maint_irq);
 
+	on_each_cpu(vgic_cpu_init_lrs, vgic, 1);
+
 	*ops = &vgic_v3_ops;
 	*params = vgic;
 
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 043032c6a5a4..00429b392c61 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -1875,8 +1875,8 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
 static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
-
-	int sz = (nr_irqs - VGIC_NR_PRIVATE_IRQS) / 8;
+	int nr_longs = BITS_TO_LONGS(nr_irqs - VGIC_NR_PRIVATE_IRQS);
+	int sz = nr_longs * sizeof(unsigned long);
 	vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL);
 	vgic_cpu->active_shared = kzalloc(sz, GFP_KERNEL);
 	vgic_cpu->pend_act_shared = kzalloc(sz, GFP_KERNEL);
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 353159922456..f0d061f92674 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -97,8 +97,8 @@ static void async_pf_execute(struct work_struct *work)
 	 * This memory barrier pairs with prepare_to_wait's set_current_state()
 	 */
 	smp_mb();
-	if (waitqueue_active(&vcpu->wq))
-		wake_up_interruptible(&vcpu->wq);
+	if (swait_active(&vcpu->wq))
+		swake_up(&vcpu->wq);
 
 	mmput(mm);
 	kvm_put_kvm(vcpu->kvm);
@@ -109,8 +109,8 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 	/* cancel outstanding work queue item */
 	while (!list_empty(&vcpu->async_pf.queue)) {
 		struct kvm_async_pf *work =
-			list_entry(vcpu->async_pf.queue.next,
-				   typeof(*work), queue);
+			list_first_entry(&vcpu->async_pf.queue,
+					 typeof(*work), queue);
 		list_del(&work->queue);
 
 #ifdef CONFIG_KVM_ASYNC_PF_SYNC
@@ -127,8 +127,8 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 	spin_lock(&vcpu->async_pf.lock);
 	while (!list_empty(&vcpu->async_pf.done)) {
 		struct kvm_async_pf *work =
-			list_entry(vcpu->async_pf.done.next,
-				   typeof(*work), link);
+			list_first_entry(&vcpu->async_pf.done,
+					 typeof(*work), link);
 		list_del(&work->link);
 		kmem_cache_free(async_pf_cache, work);
 	}
@@ -172,7 +172,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
 	 * do alloc nowait since if we are going to sleep anyway we
 	 * may as well sleep faulting in page
 	 */
-	work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT);
+	work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT | __GFP_NOWARN);
 	if (!work)
 		return 0;
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a11cfd20a6a0..7ba1d10ffed2 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -72,11 +72,11 @@ module_param(halt_poll_ns, uint, S_IRUGO | S_IWUSR);
 
 /* Default doubles per-vcpu halt_poll_ns. */
 static unsigned int halt_poll_ns_grow = 2;
-module_param(halt_poll_ns_grow, int, S_IRUGO);
+module_param(halt_poll_ns_grow, uint, S_IRUGO | S_IWUSR);
 
 /* Default resets per-vcpu halt_poll_ns . */
 static unsigned int halt_poll_ns_shrink;
-module_param(halt_poll_ns_shrink, int, S_IRUGO);
+module_param(halt_poll_ns_shrink, uint, S_IRUGO | S_IWUSR);
 
 /*
  * Ordering of locks:
@@ -216,8 +216,7 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 	vcpu->kvm = kvm;
 	vcpu->vcpu_id = id;
 	vcpu->pid = NULL;
-	vcpu->halt_poll_ns = 0;
-	init_waitqueue_head(&vcpu->wq);
+	init_swait_queue_head(&vcpu->wq);
 	kvm_async_pf_vcpu_init(vcpu);
 
 	vcpu->pre_pcpu = -1;
@@ -620,13 +619,10 @@ void *kvm_kvzalloc(unsigned long size)
 
 static void kvm_destroy_devices(struct kvm *kvm)
 {
-	struct list_head *node, *tmp;
+	struct kvm_device *dev, *tmp;
 
-	list_for_each_safe(node, tmp, &kvm->devices) {
-		struct kvm_device *dev =
-			list_entry(node, struct kvm_device, vm_node);
-
-		list_del(node);
+	list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) {
+		list_del(&dev->vm_node);
 		dev->ops->destroy(dev);
 	}
 }
@@ -1437,11 +1433,17 @@ kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn,
 {
 	unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault);
 
-	if (addr == KVM_HVA_ERR_RO_BAD)
+	if (addr == KVM_HVA_ERR_RO_BAD) {
+		if (writable)
+			*writable = false;
 		return KVM_PFN_ERR_RO_FAULT;
+	}
 
-	if (kvm_is_error_hva(addr))
+	if (kvm_is_error_hva(addr)) {
+		if (writable)
+			*writable = false;
 		return KVM_PFN_NOSLOT;
+	}
 
 	/* Do not map writable pfn in the readonly memslot. */
 	if (writable && memslot_is_readonly(slot)) {
@@ -1943,14 +1945,18 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_mark_page_dirty);
 
 static void grow_halt_poll_ns(struct kvm_vcpu *vcpu)
 {
-	int old, val;
+	unsigned int old, val, grow;
 
 	old = val = vcpu->halt_poll_ns;
+	grow = READ_ONCE(halt_poll_ns_grow);
 	/* 10us base */
-	if (val == 0 && halt_poll_ns_grow)
+	if (val == 0 && grow)
 		val = 10000;
 	else
-		val *= halt_poll_ns_grow;
+		val *= grow;
+
+	if (val > halt_poll_ns)
+		val = halt_poll_ns;
 
 	vcpu->halt_poll_ns = val;
 	trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old);
@@ -1958,13 +1964,14 @@ static void grow_halt_poll_ns(struct kvm_vcpu *vcpu)
 
 static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu)
 {
-	int old, val;
+	unsigned int old, val, shrink;
 
 	old = val = vcpu->halt_poll_ns;
-	if (halt_poll_ns_shrink == 0)
+	shrink = READ_ONCE(halt_poll_ns_shrink);
+	if (shrink == 0)
 		val = 0;
 	else
-		val /= halt_poll_ns_shrink;
+		val /= shrink;
 
 	vcpu->halt_poll_ns = val;
 	trace_kvm_halt_poll_ns_shrink(vcpu->vcpu_id, val, old);
@@ -1990,7 +1997,7 @@ static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu)
 void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 {
 	ktime_t start, cur;
-	DEFINE_WAIT(wait);
+	DECLARE_SWAITQUEUE(wait);
 	bool waited = false;
 	u64 block_ns;
 
@@ -2015,7 +2022,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 	kvm_arch_vcpu_blocking(vcpu);
 
 	for (;;) {
-		prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
+		prepare_to_swait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
 
 		if (kvm_vcpu_check_block(vcpu) < 0)
 			break;
@@ -2024,7 +2031,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 		schedule();
 	}
 
-	finish_wait(&vcpu->wq, &wait);
+	finish_swait(&vcpu->wq, &wait);
 	cur = ktime_get();
 
 	kvm_arch_vcpu_unblocking(vcpu);
@@ -2056,11 +2063,11 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 {
 	int me;
 	int cpu = vcpu->cpu;
-	wait_queue_head_t *wqp;
+	struct swait_queue_head *wqp;
 
 	wqp = kvm_arch_vcpu_wq(vcpu);
-	if (waitqueue_active(wqp)) {
-		wake_up_interruptible(wqp);
+	if (swait_active(wqp)) {
+		swake_up(wqp);
 		++vcpu->stat.halt_wakeup;
 	}
 
@@ -2161,7 +2168,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 				continue;
 			if (vcpu == me)
 				continue;
-			if (waitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
+			if (swait_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
 				continue;
 			if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
 				continue;